{"current_steps": 5, "total_steps": 181800, "loss": 7.4226, "lr": 1.1001100110011e-08, "epoch": 0.00055005500550055, "percentage": 0.0, "elapsed_time": "0:00:01", "remaining_time": "11:40:31", "throughput": 913.46, "total_tokens": 1056} {"current_steps": 10, "total_steps": 181800, "loss": 7.157, "lr": 2.4752475247524754e-08, "epoch": 0.0011001100110011, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "9:20:52", "throughput": 1192.76, "total_tokens": 2208} {"current_steps": 15, "total_steps": 181800, "loss": 7.1223, "lr": 3.850385038503851e-08, "epoch": 0.0016501650165016502, "percentage": 0.01, "elapsed_time": "0:00:02", "remaining_time": "8:34:30", "throughput": 1281.34, "total_tokens": 3264} {"current_steps": 20, "total_steps": 181800, "loss": 7.3395, "lr": 5.225522552255226e-08, "epoch": 0.0022002200220022, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "8:10:47", "throughput": 1323.5, "total_tokens": 4288} {"current_steps": 25, "total_steps": 181800, "loss": 7.4389, "lr": 6.600660066006601e-08, "epoch": 0.0027502750275027505, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "7:56:47", "throughput": 1374.52, "total_tokens": 5408} {"current_steps": 30, "total_steps": 181800, "loss": 7.5022, "lr": 7.975797579757976e-08, "epoch": 0.0033003300330033004, "percentage": 0.02, "elapsed_time": "0:00:04", "remaining_time": "7:47:11", "throughput": 1397.16, "total_tokens": 6464} {"current_steps": 35, "total_steps": 181800, "loss": 7.2997, "lr": 9.350935093509352e-08, "epoch": 0.0038503850385038503, "percentage": 0.02, "elapsed_time": "0:00:05", "remaining_time": "7:40:25", "throughput": 1407.66, "total_tokens": 7488} {"current_steps": 40, "total_steps": 181800, "loss": 7.299, "lr": 1.0726072607260726e-07, "epoch": 0.0044004400440044, "percentage": 0.02, "elapsed_time": "0:00:06", "remaining_time": "7:34:53", "throughput": 1427.81, "total_tokens": 8576} {"current_steps": 45, "total_steps": 181800, "loss": 7.2658, "lr": 1.2101210121012102e-07, "epoch": 0.0049504950495049506, "percentage": 0.02, "elapsed_time": "0:00:06", "remaining_time": "7:30:26", "throughput": 1444.22, "total_tokens": 9664} {"current_steps": 50, "total_steps": 181800, "loss": 7.5561, "lr": 1.3476347634763477e-07, "epoch": 0.005500550055005501, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "7:26:55", "throughput": 1457.48, "total_tokens": 10752} {"current_steps": 55, "total_steps": 181800, "loss": 7.1142, "lr": 1.4851485148514852e-07, "epoch": 0.00605060506050605, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "7:24:23", "throughput": 1455.47, "total_tokens": 11744} {"current_steps": 60, "total_steps": 181800, "loss": 7.455, "lr": 1.622662266226623e-07, "epoch": 0.006600660066006601, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "7:22:07", "throughput": 1461.52, "total_tokens": 12800} {"current_steps": 65, "total_steps": 181800, "loss": 7.3046, "lr": 1.76017601760176e-07, "epoch": 0.007150715071507151, "percentage": 0.04, "elapsed_time": "0:00:09", "remaining_time": "7:20:12", "throughput": 1470.15, "total_tokens": 13888} {"current_steps": 70, "total_steps": 181800, "loss": 7.4093, "lr": 1.8976897689768978e-07, "epoch": 0.007700770077007701, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "7:18:35", "throughput": 1474.31, "total_tokens": 14944} {"current_steps": 75, "total_steps": 181800, "loss": 7.4127, "lr": 2.0352035203520353e-07, "epoch": 0.00825082508250825, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "7:17:08", "throughput": 1481.05, "total_tokens": 16032} {"current_steps": 80, "total_steps": 181800, "loss": 7.3939, "lr": 2.1727172717271727e-07, "epoch": 0.0088008800880088, "percentage": 0.04, "elapsed_time": "0:00:11", "remaining_time": "7:15:57", "throughput": 1483.89, "total_tokens": 17088} {"current_steps": 85, "total_steps": 181800, "loss": 7.3738, "lr": 2.3102310231023105e-07, "epoch": 0.00935093509350935, "percentage": 0.05, "elapsed_time": "0:00:12", "remaining_time": "7:14:53", "throughput": 1483.92, "total_tokens": 18112} {"current_steps": 90, "total_steps": 181800, "loss": 7.6104, "lr": 2.447744774477448e-07, "epoch": 0.009900990099009901, "percentage": 0.05, "elapsed_time": "0:00:12", "remaining_time": "7:13:54", "throughput": 1486.51, "total_tokens": 19168} {"current_steps": 95, "total_steps": 181800, "loss": 7.2874, "lr": 2.5852585258525854e-07, "epoch": 0.010451045104510451, "percentage": 0.05, "elapsed_time": "0:00:13", "remaining_time": "7:12:52", "throughput": 1486.97, "total_tokens": 20192} {"current_steps": 100, "total_steps": 181800, "loss": 7.3848, "lr": 2.7227722772277226e-07, "epoch": 0.011001100110011002, "percentage": 0.06, "elapsed_time": "0:00:14", "remaining_time": "7:12:03", "throughput": 1487.06, "total_tokens": 21216} {"current_steps": 105, "total_steps": 181800, "loss": 7.3297, "lr": 2.8602860286028603e-07, "epoch": 0.01155115511551155, "percentage": 0.06, "elapsed_time": "0:00:14", "remaining_time": "7:11:34", "throughput": 1488.38, "total_tokens": 22272} {"current_steps": 110, "total_steps": 181800, "loss": 7.523, "lr": 2.997799779977998e-07, "epoch": 0.0121012101210121, "percentage": 0.06, "elapsed_time": "0:00:15", "remaining_time": "7:10:59", "throughput": 1485.92, "total_tokens": 23264} {"current_steps": 115, "total_steps": 181800, "loss": 7.4726, "lr": 3.1353135313531353e-07, "epoch": 0.012651265126512651, "percentage": 0.06, "elapsed_time": "0:00:16", "remaining_time": "7:10:26", "throughput": 1485.77, "total_tokens": 24288} {"current_steps": 120, "total_steps": 181800, "loss": 7.5043, "lr": 3.272827282728273e-07, "epoch": 0.013201320132013201, "percentage": 0.07, "elapsed_time": "0:00:17", "remaining_time": "7:09:52", "throughput": 1491.4, "total_tokens": 25408} {"current_steps": 125, "total_steps": 181800, "loss": 7.3024, "lr": 3.4103410341034107e-07, "epoch": 0.013751375137513752, "percentage": 0.07, "elapsed_time": "0:00:17", "remaining_time": "7:09:21", "throughput": 1493.03, "total_tokens": 26464} {"current_steps": 130, "total_steps": 181800, "loss": 6.9611, "lr": 3.547854785478548e-07, "epoch": 0.014301430143014302, "percentage": 0.07, "elapsed_time": "0:00:18", "remaining_time": "7:08:58", "throughput": 1495.95, "total_tokens": 27552} {"current_steps": 135, "total_steps": 181800, "loss": 7.2915, "lr": 3.6853685368536857e-07, "epoch": 0.01485148514851485, "percentage": 0.07, "elapsed_time": "0:00:19", "remaining_time": "7:08:32", "throughput": 1497.2, "total_tokens": 28608} {"current_steps": 140, "total_steps": 181800, "loss": 7.5443, "lr": 3.822882288228823e-07, "epoch": 0.015401540154015401, "percentage": 0.08, "elapsed_time": "0:00:19", "remaining_time": "7:08:08", "throughput": 1498.37, "total_tokens": 29664} {"current_steps": 145, "total_steps": 181800, "loss": 7.2221, "lr": 3.9603960396039606e-07, "epoch": 0.01595159515951595, "percentage": 0.08, "elapsed_time": "0:00:20", "remaining_time": "7:07:50", "throughput": 1499.25, "total_tokens": 30720} {"current_steps": 150, "total_steps": 181800, "loss": 7.426, "lr": 4.097909790979098e-07, "epoch": 0.0165016501650165, "percentage": 0.08, "elapsed_time": "0:00:21", "remaining_time": "7:07:23", "throughput": 1497.57, "total_tokens": 31712} {"current_steps": 155, "total_steps": 181800, "loss": 7.3271, "lr": 4.235423542354236e-07, "epoch": 0.017051705170517052, "percentage": 0.09, "elapsed_time": "0:00:21", "remaining_time": "7:06:58", "throughput": 1496.02, "total_tokens": 32704} {"current_steps": 160, "total_steps": 181800, "loss": 7.163, "lr": 4.3729372937293727e-07, "epoch": 0.0176017601760176, "percentage": 0.09, "elapsed_time": "0:00:22", "remaining_time": "7:06:40", "throughput": 1494.24, "total_tokens": 33696} {"current_steps": 165, "total_steps": 181800, "loss": 7.5884, "lr": 4.510451045104511e-07, "epoch": 0.018151815181518153, "percentage": 0.09, "elapsed_time": "0:00:23", "remaining_time": "7:06:22", "throughput": 1495.39, "total_tokens": 34752} {"current_steps": 170, "total_steps": 181800, "loss": 7.3003, "lr": 4.647964796479648e-07, "epoch": 0.0187018701870187, "percentage": 0.09, "elapsed_time": "0:00:23", "remaining_time": "7:06:06", "throughput": 1499.06, "total_tokens": 35872} {"current_steps": 175, "total_steps": 181800, "loss": 7.6545, "lr": 4.785478547854785e-07, "epoch": 0.019251925192519254, "percentage": 0.1, "elapsed_time": "0:00:24", "remaining_time": "7:05:50", "throughput": 1500.03, "total_tokens": 36928} {"current_steps": 180, "total_steps": 181800, "loss": 7.3781, "lr": 4.922992299229923e-07, "epoch": 0.019801980198019802, "percentage": 0.1, "elapsed_time": "0:00:25", "remaining_time": "7:05:35", "throughput": 1499.59, "total_tokens": 37952} {"current_steps": 185, "total_steps": 181800, "loss": 7.1911, "lr": 5.060506050605061e-07, "epoch": 0.02035203520352035, "percentage": 0.1, "elapsed_time": "0:00:25", "remaining_time": "7:05:18", "throughput": 1498.2, "total_tokens": 38944} {"current_steps": 190, "total_steps": 181800, "loss": 7.3379, "lr": 5.198019801980199e-07, "epoch": 0.020902090209020903, "percentage": 0.1, "elapsed_time": "0:00:26", "remaining_time": "7:05:00", "throughput": 1499.31, "total_tokens": 40000} {"current_steps": 195, "total_steps": 181800, "loss": 7.194, "lr": 5.335533553355335e-07, "epoch": 0.02145214521452145, "percentage": 0.11, "elapsed_time": "0:00:27", "remaining_time": "7:04:44", "throughput": 1500.37, "total_tokens": 41056} {"current_steps": 200, "total_steps": 181800, "loss": 6.9885, "lr": 5.473047304730474e-07, "epoch": 0.022002200220022004, "percentage": 0.11, "elapsed_time": "0:00:28", "remaining_time": "7:04:28", "throughput": 1500.25, "total_tokens": 42080} {"current_steps": 205, "total_steps": 181800, "loss": 7.5386, "lr": 5.610561056105611e-07, "epoch": 0.022552255225522552, "percentage": 0.11, "elapsed_time": "0:00:28", "remaining_time": "7:04:13", "throughput": 1501.24, "total_tokens": 43136} {"current_steps": 210, "total_steps": 181800, "loss": 7.0949, "lr": 5.748074807480748e-07, "epoch": 0.0231023102310231, "percentage": 0.12, "elapsed_time": "0:00:29", "remaining_time": "7:03:59", "throughput": 1503.25, "total_tokens": 44224} {"current_steps": 215, "total_steps": 181800, "loss": 7.4771, "lr": 5.885588558855886e-07, "epoch": 0.023652365236523653, "percentage": 0.12, "elapsed_time": "0:00:30", "remaining_time": "7:03:49", "throughput": 1504.92, "total_tokens": 45312} {"current_steps": 220, "total_steps": 181800, "loss": 7.2583, "lr": 6.023102310231023e-07, "epoch": 0.0242024202420242, "percentage": 0.12, "elapsed_time": "0:00:30", "remaining_time": "7:03:41", "throughput": 1505.43, "total_tokens": 46368} {"current_steps": 225, "total_steps": 181800, "loss": 7.2495, "lr": 6.160616061606162e-07, "epoch": 0.024752475247524754, "percentage": 0.12, "elapsed_time": "0:00:31", "remaining_time": "7:03:31", "throughput": 1508.09, "total_tokens": 47488} {"current_steps": 230, "total_steps": 181800, "loss": 7.4122, "lr": 6.298129812981298e-07, "epoch": 0.025302530253025302, "percentage": 0.13, "elapsed_time": "0:00:32", "remaining_time": "7:03:20", "throughput": 1507.72, "total_tokens": 48512} {"current_steps": 235, "total_steps": 181800, "loss": 7.2682, "lr": 6.435643564356436e-07, "epoch": 0.02585258525852585, "percentage": 0.13, "elapsed_time": "0:00:32", "remaining_time": "7:03:14", "throughput": 1508.07, "total_tokens": 49568} {"current_steps": 240, "total_steps": 181800, "loss": 7.282, "lr": 6.573157315731574e-07, "epoch": 0.026402640264026403, "percentage": 0.13, "elapsed_time": "0:00:33", "remaining_time": "7:03:07", "throughput": 1509.46, "total_tokens": 50656} {"current_steps": 245, "total_steps": 181800, "loss": 7.4635, "lr": 6.71067106710671e-07, "epoch": 0.02695269526952695, "percentage": 0.13, "elapsed_time": "0:00:34", "remaining_time": "7:02:59", "throughput": 1509.92, "total_tokens": 51712} {"current_steps": 250, "total_steps": 181800, "loss": 7.7111, "lr": 6.848184818481849e-07, "epoch": 0.027502750275027504, "percentage": 0.14, "elapsed_time": "0:00:34", "remaining_time": "7:02:48", "throughput": 1509.61, "total_tokens": 52736} {"current_steps": 255, "total_steps": 181800, "loss": 7.1912, "lr": 6.985698569856986e-07, "epoch": 0.028052805280528052, "percentage": 0.14, "elapsed_time": "0:00:35", "remaining_time": "7:02:41", "throughput": 1510.94, "total_tokens": 53824} {"current_steps": 260, "total_steps": 181800, "loss": 7.4596, "lr": 7.123212321232124e-07, "epoch": 0.028602860286028604, "percentage": 0.14, "elapsed_time": "0:00:36", "remaining_time": "7:02:31", "throughput": 1511.48, "total_tokens": 54880} {"current_steps": 265, "total_steps": 181800, "loss": 7.5449, "lr": 7.260726072607261e-07, "epoch": 0.029152915291529153, "percentage": 0.15, "elapsed_time": "0:00:36", "remaining_time": "7:02:20", "throughput": 1513.86, "total_tokens": 56000} {"current_steps": 270, "total_steps": 181800, "loss": 7.2367, "lr": 7.398239823982398e-07, "epoch": 0.0297029702970297, "percentage": 0.15, "elapsed_time": "0:00:37", "remaining_time": "7:02:09", "throughput": 1512.79, "total_tokens": 56992} {"current_steps": 275, "total_steps": 181800, "loss": 7.5558, "lr": 7.535753575357537e-07, "epoch": 0.030253025302530254, "percentage": 0.15, "elapsed_time": "0:00:38", "remaining_time": "7:01:58", "throughput": 1514.21, "total_tokens": 58080} {"current_steps": 280, "total_steps": 181800, "loss": 7.1495, "lr": 7.673267326732673e-07, "epoch": 0.030803080308030802, "percentage": 0.15, "elapsed_time": "0:00:39", "remaining_time": "7:01:51", "throughput": 1515.42, "total_tokens": 59168} {"current_steps": 285, "total_steps": 181800, "loss": 7.343, "lr": 7.810781078107811e-07, "epoch": 0.03135313531353135, "percentage": 0.16, "elapsed_time": "0:00:39", "remaining_time": "7:01:44", "throughput": 1517.41, "total_tokens": 60288} {"current_steps": 290, "total_steps": 181800, "loss": 7.4844, "lr": 7.948294829482948e-07, "epoch": 0.0319031903190319, "percentage": 0.16, "elapsed_time": "0:00:40", "remaining_time": "7:01:37", "throughput": 1516.15, "total_tokens": 61280} {"current_steps": 295, "total_steps": 181800, "loss": 7.3166, "lr": 8.085808580858086e-07, "epoch": 0.032453245324532455, "percentage": 0.16, "elapsed_time": "0:00:41", "remaining_time": "7:01:31", "throughput": 1514.87, "total_tokens": 62272} {"current_steps": 300, "total_steps": 181800, "loss": 7.2489, "lr": 8.223322332233224e-07, "epoch": 0.033003300330033, "percentage": 0.17, "elapsed_time": "0:00:41", "remaining_time": "7:01:25", "throughput": 1515.25, "total_tokens": 63328} {"current_steps": 305, "total_steps": 181800, "loss": 7.5482, "lr": 8.360836083608362e-07, "epoch": 0.03355335533553355, "percentage": 0.17, "elapsed_time": "0:00:42", "remaining_time": "7:01:18", "throughput": 1514.87, "total_tokens": 64352} {"current_steps": 310, "total_steps": 181800, "loss": 7.3467, "lr": 8.498349834983498e-07, "epoch": 0.034103410341034104, "percentage": 0.17, "elapsed_time": "0:00:43", "remaining_time": "7:01:12", "throughput": 1515.98, "total_tokens": 65440} {"current_steps": 315, "total_steps": 181800, "loss": 7.214, "lr": 8.635863586358637e-07, "epoch": 0.034653465346534656, "percentage": 0.17, "elapsed_time": "0:00:43", "remaining_time": "7:01:05", "throughput": 1517.05, "total_tokens": 66528} {"current_steps": 320, "total_steps": 181800, "loss": 7.5557, "lr": 8.773377337733774e-07, "epoch": 0.0352035203520352, "percentage": 0.18, "elapsed_time": "0:00:44", "remaining_time": "7:00:57", "throughput": 1516.77, "total_tokens": 67552} {"current_steps": 325, "total_steps": 181800, "loss": 7.1758, "lr": 8.910891089108911e-07, "epoch": 0.035753575357535754, "percentage": 0.18, "elapsed_time": "0:00:45", "remaining_time": "7:00:51", "throughput": 1516.42, "total_tokens": 68576} {"current_steps": 330, "total_steps": 181800, "loss": 7.3479, "lr": 9.048404840484049e-07, "epoch": 0.036303630363036306, "percentage": 0.18, "elapsed_time": "0:00:45", "remaining_time": "7:00:44", "throughput": 1516.1, "total_tokens": 69600} {"current_steps": 335, "total_steps": 181800, "loss": 7.3781, "lr": 9.185918591859186e-07, "epoch": 0.03685368536853685, "percentage": 0.18, "elapsed_time": "0:00:46", "remaining_time": "7:00:37", "throughput": 1515.86, "total_tokens": 70624} {"current_steps": 340, "total_steps": 181800, "loss": 6.924, "lr": 9.323432343234324e-07, "epoch": 0.0374037403740374, "percentage": 0.19, "elapsed_time": "0:00:47", "remaining_time": "7:00:29", "throughput": 1516.32, "total_tokens": 71680} {"current_steps": 345, "total_steps": 181800, "loss": 7.2749, "lr": 9.460946094609461e-07, "epoch": 0.037953795379537955, "percentage": 0.19, "elapsed_time": "0:00:47", "remaining_time": "7:00:22", "throughput": 1515.42, "total_tokens": 72672} {"current_steps": 350, "total_steps": 181800, "loss": 7.1013, "lr": 9.5984598459846e-07, "epoch": 0.03850385038503851, "percentage": 0.19, "elapsed_time": "0:00:48", "remaining_time": "7:00:14", "throughput": 1515.23, "total_tokens": 73696} {"current_steps": 355, "total_steps": 181800, "loss": 7.6288, "lr": 9.735973597359737e-07, "epoch": 0.03905390539053905, "percentage": 0.2, "elapsed_time": "0:00:49", "remaining_time": "7:00:07", "throughput": 1515.66, "total_tokens": 74752} {"current_steps": 360, "total_steps": 181800, "loss": 7.2786, "lr": 9.873487348734873e-07, "epoch": 0.039603960396039604, "percentage": 0.2, "elapsed_time": "0:00:50", "remaining_time": "7:00:00", "throughput": 1515.47, "total_tokens": 75776} {"current_steps": 365, "total_steps": 181800, "loss": 7.156, "lr": 1.001100110011001e-06, "epoch": 0.040154015401540157, "percentage": 0.2, "elapsed_time": "0:00:50", "remaining_time": "6:59:54", "throughput": 1516.53, "total_tokens": 76864} {"current_steps": 370, "total_steps": 181800, "loss": 7.1695, "lr": 1.0148514851485148e-06, "epoch": 0.0407040704070407, "percentage": 0.2, "elapsed_time": "0:00:51", "remaining_time": "6:59:47", "throughput": 1517.58, "total_tokens": 77952} {"current_steps": 375, "total_steps": 181800, "loss": 7.151, "lr": 1.0286028602860288e-06, "epoch": 0.041254125412541254, "percentage": 0.21, "elapsed_time": "0:00:52", "remaining_time": "6:59:41", "throughput": 1518.57, "total_tokens": 79040} {"current_steps": 380, "total_steps": 181800, "loss": 7.5046, "lr": 1.0423542354235424e-06, "epoch": 0.041804180418041806, "percentage": 0.21, "elapsed_time": "0:00:52", "remaining_time": "6:59:34", "throughput": 1518.95, "total_tokens": 80096} {"current_steps": 385, "total_steps": 181800, "loss": 7.1479, "lr": 1.0561056105610562e-06, "epoch": 0.04235423542354235, "percentage": 0.21, "elapsed_time": "0:00:53", "remaining_time": "6:59:28", "throughput": 1519.92, "total_tokens": 81184} {"current_steps": 390, "total_steps": 181800, "loss": 7.3582, "lr": 1.06985698569857e-06, "epoch": 0.0429042904290429, "percentage": 0.21, "elapsed_time": "0:00:54", "remaining_time": "6:59:24", "throughput": 1520.17, "total_tokens": 82240} {"current_steps": 395, "total_steps": 181800, "loss": 7.447, "lr": 1.0836083608360837e-06, "epoch": 0.043454345434543455, "percentage": 0.22, "elapsed_time": "0:00:54", "remaining_time": "6:59:19", "throughput": 1521.05, "total_tokens": 83328} {"current_steps": 400, "total_steps": 181800, "loss": 7.3037, "lr": 1.0973597359735975e-06, "epoch": 0.04400440044004401, "percentage": 0.22, "elapsed_time": "0:00:55", "remaining_time": "6:59:14", "throughput": 1520.76, "total_tokens": 84352} {"current_steps": 405, "total_steps": 181800, "loss": 7.6311, "lr": 1.1111111111111112e-06, "epoch": 0.04455445544554455, "percentage": 0.22, "elapsed_time": "0:00:56", "remaining_time": "6:59:10", "throughput": 1520.97, "total_tokens": 85408} {"current_steps": 410, "total_steps": 181800, "loss": 7.3793, "lr": 1.1248624862486248e-06, "epoch": 0.045104510451045104, "percentage": 0.23, "elapsed_time": "0:00:56", "remaining_time": "6:59:06", "throughput": 1520.64, "total_tokens": 86432} {"current_steps": 415, "total_steps": 181800, "loss": 7.4169, "lr": 1.1386138613861386e-06, "epoch": 0.04565456545654566, "percentage": 0.23, "elapsed_time": "0:00:57", "remaining_time": "6:59:02", "throughput": 1520.85, "total_tokens": 87488} {"current_steps": 420, "total_steps": 181800, "loss": 7.4043, "lr": 1.1523652365236524e-06, "epoch": 0.0462046204620462, "percentage": 0.23, "elapsed_time": "0:00:58", "remaining_time": "6:58:59", "throughput": 1519.94, "total_tokens": 88480} {"current_steps": 425, "total_steps": 181800, "loss": 7.3328, "lr": 1.1661166116611663e-06, "epoch": 0.046754675467546754, "percentage": 0.23, "elapsed_time": "0:00:58", "remaining_time": "6:58:56", "throughput": 1519.6, "total_tokens": 89504} {"current_steps": 430, "total_steps": 181800, "loss": 7.3182, "lr": 1.17986798679868e-06, "epoch": 0.047304730473047306, "percentage": 0.24, "elapsed_time": "0:00:59", "remaining_time": "6:58:54", "throughput": 1519.74, "total_tokens": 90560} {"current_steps": 435, "total_steps": 181800, "loss": 7.4648, "lr": 1.1936193619361937e-06, "epoch": 0.04785478547854786, "percentage": 0.24, "elapsed_time": "0:01:00", "remaining_time": "6:58:52", "throughput": 1519.29, "total_tokens": 91584} {"current_steps": 440, "total_steps": 181800, "loss": 7.4546, "lr": 1.2073707370737074e-06, "epoch": 0.0484048404840484, "percentage": 0.24, "elapsed_time": "0:01:00", "remaining_time": "6:58:48", "throughput": 1519.57, "total_tokens": 92640} {"current_steps": 445, "total_steps": 181800, "loss": 7.5078, "lr": 1.221122112211221e-06, "epoch": 0.048954895489548955, "percentage": 0.24, "elapsed_time": "0:01:01", "remaining_time": "6:58:43", "throughput": 1519.34, "total_tokens": 93664} {"current_steps": 450, "total_steps": 181800, "loss": 7.5724, "lr": 1.234873487348735e-06, "epoch": 0.04950495049504951, "percentage": 0.25, "elapsed_time": "0:01:02", "remaining_time": "6:58:39", "throughput": 1520.15, "total_tokens": 94752} {"current_steps": 455, "total_steps": 181800, "loss": 7.4563, "lr": 1.2486248624862488e-06, "epoch": 0.05005500550055005, "percentage": 0.25, "elapsed_time": "0:01:03", "remaining_time": "6:58:36", "throughput": 1520.32, "total_tokens": 95808} {"current_steps": 460, "total_steps": 181800, "loss": 7.3836, "lr": 1.2623762376237625e-06, "epoch": 0.050605060506050605, "percentage": 0.25, "elapsed_time": "0:01:03", "remaining_time": "6:58:35", "throughput": 1519.4, "total_tokens": 96800} {"current_steps": 465, "total_steps": 181800, "loss": 7.2817, "lr": 1.276127612761276e-06, "epoch": 0.05115511551155116, "percentage": 0.26, "elapsed_time": "0:01:04", "remaining_time": "6:58:32", "throughput": 1520.08, "total_tokens": 97888} {"current_steps": 470, "total_steps": 181800, "loss": 7.2693, "lr": 1.2898789878987899e-06, "epoch": 0.0517051705170517, "percentage": 0.26, "elapsed_time": "0:01:05", "remaining_time": "6:58:30", "throughput": 1521.23, "total_tokens": 99008} {"current_steps": 475, "total_steps": 181800, "loss": 7.3842, "lr": 1.3036303630363036e-06, "epoch": 0.052255225522552254, "percentage": 0.26, "elapsed_time": "0:01:05", "remaining_time": "6:58:27", "throughput": 1521.88, "total_tokens": 100096} {"current_steps": 480, "total_steps": 181800, "loss": 7.094, "lr": 1.3173817381738174e-06, "epoch": 0.052805280528052806, "percentage": 0.26, "elapsed_time": "0:01:06", "remaining_time": "6:58:24", "throughput": 1522.04, "total_tokens": 101152} {"current_steps": 485, "total_steps": 181800, "loss": 7.3928, "lr": 1.3311331133113312e-06, "epoch": 0.05335533553355336, "percentage": 0.27, "elapsed_time": "0:01:07", "remaining_time": "6:58:23", "throughput": 1522.12, "total_tokens": 102208} {"current_steps": 490, "total_steps": 181800, "loss": 7.4333, "lr": 1.344884488448845e-06, "epoch": 0.0539053905390539, "percentage": 0.27, "elapsed_time": "0:01:07", "remaining_time": "6:58:18", "throughput": 1521.91, "total_tokens": 103232} {"current_steps": 495, "total_steps": 181800, "loss": 7.3685, "lr": 1.3586358635863585e-06, "epoch": 0.054455445544554455, "percentage": 0.27, "elapsed_time": "0:01:08", "remaining_time": "6:58:14", "throughput": 1522.63, "total_tokens": 104320} {"current_steps": 500, "total_steps": 181800, "loss": 7.2974, "lr": 1.3723872387238725e-06, "epoch": 0.05500550055005501, "percentage": 0.28, "elapsed_time": "0:01:09", "remaining_time": "6:58:11", "throughput": 1522.82, "total_tokens": 105376} {"current_steps": 505, "total_steps": 181800, "loss": 7.3134, "lr": 1.3861386138613863e-06, "epoch": 0.05555555555555555, "percentage": 0.28, "elapsed_time": "0:01:09", "remaining_time": "6:58:07", "throughput": 1523.03, "total_tokens": 106432} {"current_steps": 510, "total_steps": 181800, "loss": 7.302, "lr": 1.3998899889989e-06, "epoch": 0.056105610561056105, "percentage": 0.28, "elapsed_time": "0:01:10", "remaining_time": "6:58:04", "throughput": 1521.82, "total_tokens": 107392} {"current_steps": 515, "total_steps": 181800, "loss": 7.445, "lr": 1.4136413641364136e-06, "epoch": 0.05665566556655666, "percentage": 0.28, "elapsed_time": "0:01:11", "remaining_time": "6:58:02", "throughput": 1521.53, "total_tokens": 108416} {"current_steps": 520, "total_steps": 181800, "loss": 7.3436, "lr": 1.4273927392739274e-06, "epoch": 0.05720572057205721, "percentage": 0.29, "elapsed_time": "0:01:11", "remaining_time": "6:57:59", "throughput": 1522.13, "total_tokens": 109504} {"current_steps": 525, "total_steps": 181800, "loss": 7.318, "lr": 1.4411441144114412e-06, "epoch": 0.057755775577557754, "percentage": 0.29, "elapsed_time": "0:01:12", "remaining_time": "6:57:56", "throughput": 1521.87, "total_tokens": 110528} {"current_steps": 530, "total_steps": 181800, "loss": 7.2152, "lr": 1.454895489548955e-06, "epoch": 0.058305830583058306, "percentage": 0.29, "elapsed_time": "0:01:13", "remaining_time": "6:57:54", "throughput": 1521.15, "total_tokens": 111520} {"current_steps": 535, "total_steps": 181800, "loss": 7.4502, "lr": 1.4686468646864687e-06, "epoch": 0.05885588558855886, "percentage": 0.29, "elapsed_time": "0:01:13", "remaining_time": "6:57:52", "throughput": 1520.43, "total_tokens": 112512} {"current_steps": 540, "total_steps": 181800, "loss": 7.0791, "lr": 1.4823982398239825e-06, "epoch": 0.0594059405940594, "percentage": 0.3, "elapsed_time": "0:01:14", "remaining_time": "6:57:50", "throughput": 1520.12, "total_tokens": 113536} {"current_steps": 545, "total_steps": 181800, "loss": 7.1853, "lr": 1.4961496149614963e-06, "epoch": 0.059955995599559955, "percentage": 0.3, "elapsed_time": "0:01:15", "remaining_time": "6:57:48", "throughput": 1520.24, "total_tokens": 114592} {"current_steps": 550, "total_steps": 181800, "loss": 7.7481, "lr": 1.50990099009901e-06, "epoch": 0.06050605060506051, "percentage": 0.3, "elapsed_time": "0:01:16", "remaining_time": "6:57:45", "throughput": 1520.9, "total_tokens": 115680} {"current_steps": 555, "total_steps": 181800, "loss": 7.0417, "lr": 1.5236523652365238e-06, "epoch": 0.06105610561056106, "percentage": 0.31, "elapsed_time": "0:01:16", "remaining_time": "6:57:41", "throughput": 1520.3, "total_tokens": 116672} {"current_steps": 560, "total_steps": 181800, "loss": 7.6014, "lr": 1.5374037403740376e-06, "epoch": 0.061606160616061605, "percentage": 0.31, "elapsed_time": "0:01:17", "remaining_time": "6:57:37", "throughput": 1520.14, "total_tokens": 117696} {"current_steps": 565, "total_steps": 181800, "loss": 7.4048, "lr": 1.5511551155115511e-06, "epoch": 0.06215621562156216, "percentage": 0.31, "elapsed_time": "0:01:18", "remaining_time": "6:57:34", "throughput": 1519.96, "total_tokens": 118720} {"current_steps": 570, "total_steps": 181800, "loss": 7.2783, "lr": 1.5649064906490651e-06, "epoch": 0.0627062706270627, "percentage": 0.31, "elapsed_time": "0:01:18", "remaining_time": "6:57:31", "throughput": 1520.6, "total_tokens": 119808} {"current_steps": 575, "total_steps": 181800, "loss": 7.5366, "lr": 1.5786578657865787e-06, "epoch": 0.06325632563256325, "percentage": 0.32, "elapsed_time": "0:01:19", "remaining_time": "6:57:28", "throughput": 1520.79, "total_tokens": 120864} {"current_steps": 580, "total_steps": 181800, "loss": 7.451, "lr": 1.5924092409240925e-06, "epoch": 0.0638063806380638, "percentage": 0.32, "elapsed_time": "0:01:20", "remaining_time": "6:57:26", "throughput": 1521.32, "total_tokens": 121952} {"current_steps": 585, "total_steps": 181800, "loss": 7.4218, "lr": 1.6061606160616062e-06, "epoch": 0.06435643564356436, "percentage": 0.32, "elapsed_time": "0:01:20", "remaining_time": "6:57:24", "throughput": 1521.05, "total_tokens": 122976} {"current_steps": 590, "total_steps": 181800, "loss": 7.2462, "lr": 1.61991199119912e-06, "epoch": 0.06490649064906491, "percentage": 0.32, "elapsed_time": "0:01:21", "remaining_time": "6:57:22", "throughput": 1520.43, "total_tokens": 123968} {"current_steps": 595, "total_steps": 181800, "loss": 7.4717, "lr": 1.6336633663366338e-06, "epoch": 0.06545654565456546, "percentage": 0.33, "elapsed_time": "0:01:22", "remaining_time": "6:57:20", "throughput": 1520.19, "total_tokens": 124992} {"current_steps": 600, "total_steps": 181800, "loss": 7.5661, "lr": 1.6474147414741475e-06, "epoch": 0.066006600660066, "percentage": 0.33, "elapsed_time": "0:01:22", "remaining_time": "6:57:18", "throughput": 1520.34, "total_tokens": 126048} {"current_steps": 605, "total_steps": 181800, "loss": 7.1996, "lr": 1.6611661166116613e-06, "epoch": 0.06655665566556655, "percentage": 0.33, "elapsed_time": "0:01:23", "remaining_time": "6:57:15", "throughput": 1521.3, "total_tokens": 127168} {"current_steps": 610, "total_steps": 181800, "loss": 7.4235, "lr": 1.6749174917491749e-06, "epoch": 0.0671067106710671, "percentage": 0.34, "elapsed_time": "0:01:24", "remaining_time": "6:57:13", "throughput": 1521.45, "total_tokens": 128224} {"current_steps": 615, "total_steps": 181800, "loss": 7.3712, "lr": 1.6886688668866887e-06, "epoch": 0.06765676567656766, "percentage": 0.34, "elapsed_time": "0:01:24", "remaining_time": "6:57:11", "throughput": 1521.59, "total_tokens": 129280} {"current_steps": 620, "total_steps": 181800, "loss": 7.425, "lr": 1.7024202420242024e-06, "epoch": 0.06820682068206821, "percentage": 0.34, "elapsed_time": "0:01:25", "remaining_time": "6:57:09", "throughput": 1521.73, "total_tokens": 130336} {"current_steps": 625, "total_steps": 181800, "loss": 7.3354, "lr": 1.7161716171617162e-06, "epoch": 0.06875687568756876, "percentage": 0.34, "elapsed_time": "0:01:26", "remaining_time": "6:57:06", "throughput": 1522.3, "total_tokens": 131424} {"current_steps": 630, "total_steps": 181800, "loss": 7.3039, "lr": 1.72992299229923e-06, "epoch": 0.06930693069306931, "percentage": 0.35, "elapsed_time": "0:01:27", "remaining_time": "6:57:02", "throughput": 1522.5, "total_tokens": 132480} {"current_steps": 635, "total_steps": 181800, "loss": 7.3981, "lr": 1.743674367436744e-06, "epoch": 0.06985698569856985, "percentage": 0.35, "elapsed_time": "0:01:27", "remaining_time": "6:57:00", "throughput": 1522.68, "total_tokens": 133536} {"current_steps": 640, "total_steps": 181800, "loss": 7.075, "lr": 1.7574257425742577e-06, "epoch": 0.0704070407040704, "percentage": 0.35, "elapsed_time": "0:01:28", "remaining_time": "6:56:57", "throughput": 1522.83, "total_tokens": 134592} {"current_steps": 645, "total_steps": 181800, "loss": 7.1862, "lr": 1.771177117711771e-06, "epoch": 0.07095709570957096, "percentage": 0.35, "elapsed_time": "0:01:29", "remaining_time": "6:56:55", "throughput": 1522.99, "total_tokens": 135648} {"current_steps": 650, "total_steps": 181800, "loss": 7.5197, "lr": 1.7849284928492849e-06, "epoch": 0.07150715071507151, "percentage": 0.36, "elapsed_time": "0:01:29", "remaining_time": "6:56:55", "throughput": 1523.73, "total_tokens": 136768} {"current_steps": 655, "total_steps": 181800, "loss": 7.4261, "lr": 1.7986798679867988e-06, "epoch": 0.07205720572057206, "percentage": 0.36, "elapsed_time": "0:01:30", "remaining_time": "6:56:54", "throughput": 1524.45, "total_tokens": 137888} {"current_steps": 660, "total_steps": 181800, "loss": 7.33, "lr": 1.8124312431243126e-06, "epoch": 0.07260726072607261, "percentage": 0.36, "elapsed_time": "0:01:31", "remaining_time": "6:56:53", "throughput": 1524.55, "total_tokens": 138944} {"current_steps": 665, "total_steps": 181800, "loss": 7.3168, "lr": 1.8261826182618264e-06, "epoch": 0.07315731573157316, "percentage": 0.37, "elapsed_time": "0:01:31", "remaining_time": "6:56:51", "throughput": 1524.65, "total_tokens": 140000} {"current_steps": 670, "total_steps": 181800, "loss": 7.4884, "lr": 1.8399339933993402e-06, "epoch": 0.0737073707370737, "percentage": 0.37, "elapsed_time": "0:01:32", "remaining_time": "6:56:49", "throughput": 1524.39, "total_tokens": 141024} {"current_steps": 675, "total_steps": 181800, "loss": 7.3331, "lr": 1.8536853685368535e-06, "epoch": 0.07425742574257425, "percentage": 0.37, "elapsed_time": "0:01:33", "remaining_time": "6:56:48", "throughput": 1523.79, "total_tokens": 142016} {"current_steps": 680, "total_steps": 181800, "loss": 7.4635, "lr": 1.8674367436743675e-06, "epoch": 0.0748074807480748, "percentage": 0.37, "elapsed_time": "0:01:33", "remaining_time": "6:56:47", "throughput": 1523.53, "total_tokens": 143040} {"current_steps": 685, "total_steps": 181800, "loss": 7.1036, "lr": 1.8811881188118813e-06, "epoch": 0.07535753575357536, "percentage": 0.38, "elapsed_time": "0:01:34", "remaining_time": "6:56:45", "throughput": 1523.65, "total_tokens": 144096} {"current_steps": 690, "total_steps": 181800, "loss": 7.5572, "lr": 1.894939493949395e-06, "epoch": 0.07590759075907591, "percentage": 0.38, "elapsed_time": "0:01:35", "remaining_time": "6:56:43", "throughput": 1523.4, "total_tokens": 145120} {"current_steps": 695, "total_steps": 181800, "loss": 7.3631, "lr": 1.908690869086909e-06, "epoch": 0.07645764576457646, "percentage": 0.38, "elapsed_time": "0:01:35", "remaining_time": "6:56:41", "throughput": 1523.19, "total_tokens": 146144} {"current_steps": 700, "total_steps": 181800, "loss": 7.3748, "lr": 1.9224422442244226e-06, "epoch": 0.07700770077007701, "percentage": 0.39, "elapsed_time": "0:01:36", "remaining_time": "6:56:40", "throughput": 1523.96, "total_tokens": 147264} {"current_steps": 705, "total_steps": 181800, "loss": 7.4472, "lr": 1.9361936193619364e-06, "epoch": 0.07755775577557755, "percentage": 0.39, "elapsed_time": "0:01:37", "remaining_time": "6:56:38", "throughput": 1524.72, "total_tokens": 148384} {"current_steps": 710, "total_steps": 181800, "loss": 7.1466, "lr": 1.9499449944994497e-06, "epoch": 0.0781078107810781, "percentage": 0.39, "elapsed_time": "0:01:38", "remaining_time": "6:56:37", "throughput": 1524.15, "total_tokens": 149376} {"current_steps": 715, "total_steps": 181800, "loss": 7.1537, "lr": 1.9636963696369635e-06, "epoch": 0.07865786578657866, "percentage": 0.39, "elapsed_time": "0:01:38", "remaining_time": "6:56:34", "throughput": 1525.57, "total_tokens": 150560} {"current_steps": 720, "total_steps": 181800, "loss": 7.4277, "lr": 1.9774477447744777e-06, "epoch": 0.07920792079207921, "percentage": 0.4, "elapsed_time": "0:01:39", "remaining_time": "6:56:31", "throughput": 1526.07, "total_tokens": 151648} {"current_steps": 725, "total_steps": 181800, "loss": 7.2583, "lr": 1.9911991199119915e-06, "epoch": 0.07975797579757976, "percentage": 0.4, "elapsed_time": "0:01:40", "remaining_time": "6:56:29", "throughput": 1526.21, "total_tokens": 152704} {"current_steps": 730, "total_steps": 181800, "loss": 7.2974, "lr": 2.0049504950495052e-06, "epoch": 0.08030803080308031, "percentage": 0.4, "elapsed_time": "0:01:40", "remaining_time": "6:56:27", "throughput": 1526.35, "total_tokens": 153760} {"current_steps": 735, "total_steps": 181800, "loss": 7.5154, "lr": 2.018701870187019e-06, "epoch": 0.08085808580858085, "percentage": 0.4, "elapsed_time": "0:01:41", "remaining_time": "6:56:26", "throughput": 1525.75, "total_tokens": 154752} {"current_steps": 740, "total_steps": 181800, "loss": 7.3393, "lr": 2.0324532453245328e-06, "epoch": 0.0814081408140814, "percentage": 0.41, "elapsed_time": "0:01:42", "remaining_time": "6:56:24", "throughput": 1526.14, "total_tokens": 155840} {"current_steps": 745, "total_steps": 181800, "loss": 7.1618, "lr": 2.046204620462046e-06, "epoch": 0.08195819581958196, "percentage": 0.41, "elapsed_time": "0:01:42", "remaining_time": "6:56:23", "throughput": 1526.21, "total_tokens": 156896} {"current_steps": 750, "total_steps": 181800, "loss": 7.1599, "lr": 2.05995599559956e-06, "epoch": 0.08250825082508251, "percentage": 0.41, "elapsed_time": "0:01:43", "remaining_time": "6:56:22", "throughput": 1526.59, "total_tokens": 157984} {"current_steps": 755, "total_steps": 181800, "loss": 7.2782, "lr": 2.0737073707370737e-06, "epoch": 0.08305830583058306, "percentage": 0.42, "elapsed_time": "0:01:44", "remaining_time": "6:56:20", "throughput": 1526.95, "total_tokens": 159072} {"current_steps": 760, "total_steps": 181800, "loss": 7.1634, "lr": 2.0874587458745874e-06, "epoch": 0.08360836083608361, "percentage": 0.42, "elapsed_time": "0:01:44", "remaining_time": "6:56:20", "throughput": 1527.28, "total_tokens": 160160} {"current_steps": 765, "total_steps": 181800, "loss": 7.2706, "lr": 2.101210121012101e-06, "epoch": 0.08415841584158416, "percentage": 0.42, "elapsed_time": "0:01:45", "remaining_time": "6:56:20", "throughput": 1526.97, "total_tokens": 161184} {"current_steps": 770, "total_steps": 181800, "loss": 7.3434, "lr": 2.114961496149615e-06, "epoch": 0.0847084708470847, "percentage": 0.42, "elapsed_time": "0:01:46", "remaining_time": "6:56:18", "throughput": 1526.72, "total_tokens": 162208} {"current_steps": 775, "total_steps": 181800, "loss": 7.4966, "lr": 2.128712871287129e-06, "epoch": 0.08525852585258525, "percentage": 0.43, "elapsed_time": "0:01:46", "remaining_time": "6:56:16", "throughput": 1527.13, "total_tokens": 163296} {"current_steps": 780, "total_steps": 181800, "loss": 7.2157, "lr": 2.1424642464246425e-06, "epoch": 0.0858085808580858, "percentage": 0.43, "elapsed_time": "0:01:47", "remaining_time": "6:56:15", "throughput": 1527.8, "total_tokens": 164416} {"current_steps": 785, "total_steps": 181800, "loss": 7.4092, "lr": 2.1562156215621563e-06, "epoch": 0.08635863586358636, "percentage": 0.43, "elapsed_time": "0:01:48", "remaining_time": "6:56:13", "throughput": 1527.61, "total_tokens": 165440} {"current_steps": 790, "total_steps": 181800, "loss": 7.6004, "lr": 2.16996699669967e-06, "epoch": 0.08690869086908691, "percentage": 0.43, "elapsed_time": "0:01:48", "remaining_time": "6:56:10", "throughput": 1528.02, "total_tokens": 166528} {"current_steps": 795, "total_steps": 181800, "loss": 7.3321, "lr": 2.183718371837184e-06, "epoch": 0.08745874587458746, "percentage": 0.44, "elapsed_time": "0:01:49", "remaining_time": "6:56:09", "throughput": 1528.38, "total_tokens": 167616} {"current_steps": 800, "total_steps": 181800, "loss": 7.1959, "lr": 2.1974697469746976e-06, "epoch": 0.08800880088008801, "percentage": 0.44, "elapsed_time": "0:01:50", "remaining_time": "6:56:07", "throughput": 1528.19, "total_tokens": 168640} {"current_steps": 805, "total_steps": 181800, "loss": 7.3233, "lr": 2.2112211221122114e-06, "epoch": 0.08855885588558855, "percentage": 0.44, "elapsed_time": "0:01:51", "remaining_time": "6:56:05", "throughput": 1528.3, "total_tokens": 169696} {"current_steps": 810, "total_steps": 181800, "loss": 7.0411, "lr": 2.224972497249725e-06, "epoch": 0.0891089108910891, "percentage": 0.45, "elapsed_time": "0:01:51", "remaining_time": "6:56:02", "throughput": 1528.13, "total_tokens": 170720} {"current_steps": 815, "total_steps": 181800, "loss": 7.2513, "lr": 2.2387238723872385e-06, "epoch": 0.08965896589658966, "percentage": 0.45, "elapsed_time": "0:01:52", "remaining_time": "6:56:00", "throughput": 1527.4, "total_tokens": 171680} {"current_steps": 820, "total_steps": 181800, "loss": 7.315, "lr": 2.2524752475247523e-06, "epoch": 0.09020902090209021, "percentage": 0.45, "elapsed_time": "0:01:53", "remaining_time": "6:55:58", "throughput": 1528.08, "total_tokens": 172800} {"current_steps": 825, "total_steps": 181800, "loss": 7.4849, "lr": 2.2662266226622665e-06, "epoch": 0.09075907590759076, "percentage": 0.45, "elapsed_time": "0:01:53", "remaining_time": "6:55:56", "throughput": 1528.17, "total_tokens": 173856} {"current_steps": 830, "total_steps": 181800, "loss": 7.5908, "lr": 2.2799779977997803e-06, "epoch": 0.09130913091309131, "percentage": 0.46, "elapsed_time": "0:01:54", "remaining_time": "6:55:54", "throughput": 1527.73, "total_tokens": 174848} {"current_steps": 835, "total_steps": 181800, "loss": 7.2742, "lr": 2.293729372937294e-06, "epoch": 0.09185918591859187, "percentage": 0.46, "elapsed_time": "0:01:55", "remaining_time": "6:55:52", "throughput": 1528.08, "total_tokens": 175936} {"current_steps": 840, "total_steps": 181800, "loss": 7.1664, "lr": 2.307480748074808e-06, "epoch": 0.0924092409240924, "percentage": 0.46, "elapsed_time": "0:01:55", "remaining_time": "6:55:50", "throughput": 1528.17, "total_tokens": 176992} {"current_steps": 845, "total_steps": 181800, "loss": 7.2468, "lr": 2.3212321232123216e-06, "epoch": 0.09295929592959296, "percentage": 0.46, "elapsed_time": "0:01:56", "remaining_time": "6:55:48", "throughput": 1528.29, "total_tokens": 178048} {"current_steps": 850, "total_steps": 181800, "loss": 7.3711, "lr": 2.334983498349835e-06, "epoch": 0.09350935093509351, "percentage": 0.47, "elapsed_time": "0:01:57", "remaining_time": "6:55:46", "throughput": 1528.14, "total_tokens": 179072} {"current_steps": 855, "total_steps": 181800, "loss": 7.4862, "lr": 2.3487348734873487e-06, "epoch": 0.09405940594059406, "percentage": 0.47, "elapsed_time": "0:01:57", "remaining_time": "6:55:44", "throughput": 1527.96, "total_tokens": 180096} {"current_steps": 860, "total_steps": 181800, "loss": 7.0273, "lr": 2.3624862486248625e-06, "epoch": 0.09460946094609461, "percentage": 0.47, "elapsed_time": "0:01:58", "remaining_time": "6:55:42", "throughput": 1528.05, "total_tokens": 181152} {"current_steps": 865, "total_steps": 181800, "loss": 7.4026, "lr": 2.3762376237623762e-06, "epoch": 0.09515951595159516, "percentage": 0.48, "elapsed_time": "0:01:59", "remaining_time": "6:55:41", "throughput": 1528.12, "total_tokens": 182208} {"current_steps": 870, "total_steps": 181800, "loss": 7.0618, "lr": 2.38998899889989e-06, "epoch": 0.09570957095709572, "percentage": 0.48, "elapsed_time": "0:01:59", "remaining_time": "6:55:39", "throughput": 1527.9, "total_tokens": 183232} {"current_steps": 875, "total_steps": 181800, "loss": 7.3767, "lr": 2.403740374037404e-06, "epoch": 0.09625962596259625, "percentage": 0.48, "elapsed_time": "0:02:00", "remaining_time": "6:55:39", "throughput": 1527.64, "total_tokens": 184256} {"current_steps": 880, "total_steps": 181800, "loss": 7.2033, "lr": 2.4174917491749176e-06, "epoch": 0.0968096809680968, "percentage": 0.48, "elapsed_time": "0:02:01", "remaining_time": "6:55:38", "throughput": 1527.43, "total_tokens": 185280} {"current_steps": 885, "total_steps": 181800, "loss": 7.6114, "lr": 2.4312431243124313e-06, "epoch": 0.09735973597359736, "percentage": 0.49, "elapsed_time": "0:02:01", "remaining_time": "6:55:37", "throughput": 1527.48, "total_tokens": 186336} {"current_steps": 890, "total_steps": 181800, "loss": 7.6624, "lr": 2.444994499449945e-06, "epoch": 0.09790979097909791, "percentage": 0.49, "elapsed_time": "0:02:02", "remaining_time": "6:55:35", "throughput": 1527.57, "total_tokens": 187392} {"current_steps": 895, "total_steps": 181800, "loss": 7.2998, "lr": 2.458745874587459e-06, "epoch": 0.09845984598459846, "percentage": 0.49, "elapsed_time": "0:02:03", "remaining_time": "6:55:34", "throughput": 1527.37, "total_tokens": 188416} {"current_steps": 900, "total_steps": 181800, "loss": 7.3177, "lr": 2.4724972497249727e-06, "epoch": 0.09900990099009901, "percentage": 0.5, "elapsed_time": "0:02:04", "remaining_time": "6:55:33", "throughput": 1527.41, "total_tokens": 189472} {"current_steps": 905, "total_steps": 181800, "loss": 7.3102, "lr": 2.4862486248624864e-06, "epoch": 0.09955995599559957, "percentage": 0.5, "elapsed_time": "0:02:04", "remaining_time": "6:55:32", "throughput": 1527.48, "total_tokens": 190528} {"current_steps": 910, "total_steps": 181800, "loss": 7.3003, "lr": 2.5e-06, "epoch": 0.1001100110011001, "percentage": 0.5, "elapsed_time": "0:02:05", "remaining_time": "6:55:31", "throughput": 1528.05, "total_tokens": 191648} {"current_steps": 915, "total_steps": 181800, "loss": 7.4943, "lr": 2.5137513751375136e-06, "epoch": 0.10066006600660066, "percentage": 0.5, "elapsed_time": "0:02:06", "remaining_time": "6:55:29", "throughput": 1527.85, "total_tokens": 192672} {"current_steps": 920, "total_steps": 181800, "loss": 7.2136, "lr": 2.5275027502750273e-06, "epoch": 0.10121012101210121, "percentage": 0.51, "elapsed_time": "0:02:06", "remaining_time": "6:55:28", "throughput": 1528.15, "total_tokens": 193760} {"current_steps": 925, "total_steps": 181800, "loss": 7.5807, "lr": 2.5412541254125415e-06, "epoch": 0.10176017601760176, "percentage": 0.51, "elapsed_time": "0:02:07", "remaining_time": "6:55:27", "throughput": 1528.46, "total_tokens": 194848} {"current_steps": 930, "total_steps": 181800, "loss": 7.4138, "lr": 2.5550055005500553e-06, "epoch": 0.10231023102310231, "percentage": 0.51, "elapsed_time": "0:02:08", "remaining_time": "6:55:26", "throughput": 1529.01, "total_tokens": 195968} {"current_steps": 935, "total_steps": 181800, "loss": 7.3796, "lr": 2.568756875687569e-06, "epoch": 0.10286028602860287, "percentage": 0.51, "elapsed_time": "0:02:08", "remaining_time": "6:55:25", "throughput": 1528.82, "total_tokens": 196992} {"current_steps": 940, "total_steps": 181800, "loss": 7.561, "lr": 2.582508250825083e-06, "epoch": 0.1034103410341034, "percentage": 0.52, "elapsed_time": "0:02:09", "remaining_time": "6:55:24", "throughput": 1529.35, "total_tokens": 198112} {"current_steps": 945, "total_steps": 181800, "loss": 7.3158, "lr": 2.5962596259625966e-06, "epoch": 0.10396039603960396, "percentage": 0.52, "elapsed_time": "0:02:10", "remaining_time": "6:55:23", "throughput": 1529.09, "total_tokens": 199136} {"current_steps": 950, "total_steps": 181800, "loss": 7.1969, "lr": 2.61001100110011e-06, "epoch": 0.10451045104510451, "percentage": 0.52, "elapsed_time": "0:02:10", "remaining_time": "6:55:22", "throughput": 1529.36, "total_tokens": 200224} {"current_steps": 955, "total_steps": 181800, "loss": 7.3743, "lr": 2.6237623762376237e-06, "epoch": 0.10506050605060506, "percentage": 0.53, "elapsed_time": "0:02:11", "remaining_time": "6:55:22", "throughput": 1529.63, "total_tokens": 201312} {"current_steps": 960, "total_steps": 181800, "loss": 7.3584, "lr": 2.6375137513751375e-06, "epoch": 0.10561056105610561, "percentage": 0.53, "elapsed_time": "0:02:12", "remaining_time": "6:55:21", "throughput": 1529.89, "total_tokens": 202400} {"current_steps": 965, "total_steps": 181800, "loss": 7.352, "lr": 2.6512651265126513e-06, "epoch": 0.10616061606160616, "percentage": 0.53, "elapsed_time": "0:02:12", "remaining_time": "6:55:20", "throughput": 1529.2, "total_tokens": 203360} {"current_steps": 970, "total_steps": 181800, "loss": 7.4999, "lr": 2.665016501650165e-06, "epoch": 0.10671067106710672, "percentage": 0.53, "elapsed_time": "0:02:13", "remaining_time": "6:55:19", "throughput": 1528.74, "total_tokens": 204352} {"current_steps": 975, "total_steps": 181800, "loss": 7.5039, "lr": 2.678767876787679e-06, "epoch": 0.10726072607260725, "percentage": 0.54, "elapsed_time": "0:02:14", "remaining_time": "6:55:18", "throughput": 1528.53, "total_tokens": 205376} {"current_steps": 980, "total_steps": 181800, "loss": 7.3011, "lr": 2.6925192519251926e-06, "epoch": 0.1078107810781078, "percentage": 0.54, "elapsed_time": "0:02:15", "remaining_time": "6:55:18", "throughput": 1528.3, "total_tokens": 206400} {"current_steps": 985, "total_steps": 181800, "loss": 6.9919, "lr": 2.7062706270627064e-06, "epoch": 0.10836083608360836, "percentage": 0.54, "elapsed_time": "0:02:15", "remaining_time": "6:55:18", "throughput": 1528.27, "total_tokens": 207456} {"current_steps": 990, "total_steps": 181800, "loss": 7.2102, "lr": 2.72002200220022e-06, "epoch": 0.10891089108910891, "percentage": 0.54, "elapsed_time": "0:02:16", "remaining_time": "6:55:18", "throughput": 1528.02, "total_tokens": 208480} {"current_steps": 995, "total_steps": 181800, "loss": 7.7986, "lr": 2.733773377337734e-06, "epoch": 0.10946094609460946, "percentage": 0.55, "elapsed_time": "0:02:17", "remaining_time": "6:55:17", "throughput": 1528.05, "total_tokens": 209536} {"current_steps": 1000, "total_steps": 181800, "loss": 7.5316, "lr": 2.7475247524752477e-06, "epoch": 0.11001100110011001, "percentage": 0.55, "elapsed_time": "0:02:17", "remaining_time": "6:55:16", "throughput": 1527.86, "total_tokens": 210560} {"current_steps": 1005, "total_steps": 181800, "loss": 7.3361, "lr": 2.7612761276127615e-06, "epoch": 0.11056105610561057, "percentage": 0.55, "elapsed_time": "0:02:18", "remaining_time": "6:55:15", "throughput": 1527.69, "total_tokens": 211584} {"current_steps": 1010, "total_steps": 181800, "loss": 7.4872, "lr": 2.7750275027502752e-06, "epoch": 0.1111111111111111, "percentage": 0.56, "elapsed_time": "0:02:19", "remaining_time": "6:55:13", "throughput": 1528.01, "total_tokens": 212672} {"current_steps": 1015, "total_steps": 181800, "loss": 7.5535, "lr": 2.788778877887789e-06, "epoch": 0.11166116611661166, "percentage": 0.56, "elapsed_time": "0:02:19", "remaining_time": "6:55:11", "throughput": 1528.32, "total_tokens": 213760} {"current_steps": 1020, "total_steps": 181800, "loss": 7.4467, "lr": 2.8025302530253024e-06, "epoch": 0.11221122112211221, "percentage": 0.56, "elapsed_time": "0:02:20", "remaining_time": "6:55:10", "throughput": 1528.38, "total_tokens": 214816} {"current_steps": 1025, "total_steps": 181800, "loss": 7.4353, "lr": 2.816281628162816e-06, "epoch": 0.11276127612761276, "percentage": 0.56, "elapsed_time": "0:02:21", "remaining_time": "6:55:08", "throughput": 1528.69, "total_tokens": 215904} {"current_steps": 1030, "total_steps": 181800, "loss": 7.4279, "lr": 2.8300330033003303e-06, "epoch": 0.11331133113311331, "percentage": 0.57, "elapsed_time": "0:02:21", "remaining_time": "6:55:07", "throughput": 1528.99, "total_tokens": 216992} {"current_steps": 1035, "total_steps": 181800, "loss": 7.3641, "lr": 2.843784378437844e-06, "epoch": 0.11386138613861387, "percentage": 0.57, "elapsed_time": "0:02:22", "remaining_time": "6:55:05", "throughput": 1529.06, "total_tokens": 218048} {"current_steps": 1040, "total_steps": 181800, "loss": 7.3208, "lr": 2.857535753575358e-06, "epoch": 0.11441144114411442, "percentage": 0.57, "elapsed_time": "0:02:23", "remaining_time": "6:55:05", "throughput": 1529.28, "total_tokens": 219136} {"current_steps": 1045, "total_steps": 181800, "loss": 7.2384, "lr": 2.8712871287128717e-06, "epoch": 0.11496149614961496, "percentage": 0.57, "elapsed_time": "0:02:23", "remaining_time": "6:55:04", "throughput": 1528.85, "total_tokens": 220128} {"current_steps": 1050, "total_steps": 181800, "loss": 7.2621, "lr": 2.8850385038503854e-06, "epoch": 0.11551155115511551, "percentage": 0.58, "elapsed_time": "0:02:24", "remaining_time": "6:55:04", "throughput": 1528.87, "total_tokens": 221184} {"current_steps": 1055, "total_steps": 181800, "loss": 7.3663, "lr": 2.8987898789878988e-06, "epoch": 0.11606160616061606, "percentage": 0.58, "elapsed_time": "0:02:25", "remaining_time": "6:55:03", "throughput": 1529.12, "total_tokens": 222272} {"current_steps": 1060, "total_steps": 181800, "loss": 7.3285, "lr": 2.9125412541254125e-06, "epoch": 0.11661166116611661, "percentage": 0.58, "elapsed_time": "0:02:26", "remaining_time": "6:55:01", "throughput": 1528.99, "total_tokens": 223296} {"current_steps": 1065, "total_steps": 181800, "loss": 7.3486, "lr": 2.9262926292629263e-06, "epoch": 0.11716171617161716, "percentage": 0.59, "elapsed_time": "0:02:26", "remaining_time": "6:54:59", "throughput": 1529.07, "total_tokens": 224352} {"current_steps": 1070, "total_steps": 181800, "loss": 7.4935, "lr": 2.94004400440044e-06, "epoch": 0.11771177117711772, "percentage": 0.59, "elapsed_time": "0:02:27", "remaining_time": "6:54:58", "throughput": 1528.69, "total_tokens": 225344} {"current_steps": 1075, "total_steps": 181800, "loss": 7.4266, "lr": 2.953795379537954e-06, "epoch": 0.11826182618261827, "percentage": 0.59, "elapsed_time": "0:02:28", "remaining_time": "6:54:57", "throughput": 1528.73, "total_tokens": 226400} {"current_steps": 1080, "total_steps": 181800, "loss": 7.3714, "lr": 2.9675467546754676e-06, "epoch": 0.1188118811881188, "percentage": 0.59, "elapsed_time": "0:02:28", "remaining_time": "6:54:57", "throughput": 1529.17, "total_tokens": 227520} {"current_steps": 1085, "total_steps": 181800, "loss": 7.3534, "lr": 2.9812981298129814e-06, "epoch": 0.11936193619361936, "percentage": 0.6, "elapsed_time": "0:02:29", "remaining_time": "6:54:56", "throughput": 1529.39, "total_tokens": 228608} {"current_steps": 1090, "total_steps": 181800, "loss": 7.3666, "lr": 2.995049504950495e-06, "epoch": 0.11991199119911991, "percentage": 0.6, "elapsed_time": "0:02:30", "remaining_time": "6:54:55", "throughput": 1529.42, "total_tokens": 229664} {"current_steps": 1095, "total_steps": 181800, "loss": 7.1996, "lr": 3.008800880088009e-06, "epoch": 0.12046204620462046, "percentage": 0.6, "elapsed_time": "0:02:30", "remaining_time": "6:54:54", "throughput": 1529.23, "total_tokens": 230688} {"current_steps": 1100, "total_steps": 181800, "loss": 7.3358, "lr": 3.0225522552255227e-06, "epoch": 0.12101210121012101, "percentage": 0.61, "elapsed_time": "0:02:31", "remaining_time": "6:54:53", "throughput": 1529.5, "total_tokens": 231776} {"current_steps": 1105, "total_steps": 181800, "loss": 7.5826, "lr": 3.0363036303630365e-06, "epoch": 0.12156215621562157, "percentage": 0.61, "elapsed_time": "0:02:32", "remaining_time": "6:54:52", "throughput": 1529.77, "total_tokens": 232864} {"current_steps": 1110, "total_steps": 181800, "loss": 7.6291, "lr": 3.0500550055005503e-06, "epoch": 0.12211221122112212, "percentage": 0.61, "elapsed_time": "0:02:32", "remaining_time": "6:54:50", "throughput": 1529.83, "total_tokens": 233920} {"current_steps": 1115, "total_steps": 181800, "loss": 7.5185, "lr": 3.063806380638064e-06, "epoch": 0.12266226622662266, "percentage": 0.61, "elapsed_time": "0:02:33", "remaining_time": "6:54:49", "throughput": 1530.31, "total_tokens": 235040} {"current_steps": 1120, "total_steps": 181800, "loss": 7.7357, "lr": 3.0775577557755774e-06, "epoch": 0.12321232123212321, "percentage": 0.62, "elapsed_time": "0:02:34", "remaining_time": "6:54:47", "throughput": 1530.59, "total_tokens": 236128} {"current_steps": 1125, "total_steps": 181800, "loss": 7.2506, "lr": 3.091309130913091e-06, "epoch": 0.12376237623762376, "percentage": 0.62, "elapsed_time": "0:02:34", "remaining_time": "6:54:46", "throughput": 1530.24, "total_tokens": 237120} {"current_steps": 1130, "total_steps": 181800, "loss": 7.3958, "lr": 3.105060506050605e-06, "epoch": 0.12431243124312431, "percentage": 0.62, "elapsed_time": "0:02:35", "remaining_time": "6:54:44", "throughput": 1529.88, "total_tokens": 238112} {"current_steps": 1135, "total_steps": 181800, "loss": 7.4532, "lr": 3.118811881188119e-06, "epoch": 0.12486248624862487, "percentage": 0.62, "elapsed_time": "0:02:36", "remaining_time": "6:54:43", "throughput": 1529.94, "total_tokens": 239168} {"current_steps": 1140, "total_steps": 181800, "loss": 7.2466, "lr": 3.1325632563256325e-06, "epoch": 0.1254125412541254, "percentage": 0.63, "elapsed_time": "0:02:37", "remaining_time": "6:54:41", "throughput": 1530.21, "total_tokens": 240256} {"current_steps": 1145, "total_steps": 181800, "loss": 7.3145, "lr": 3.1463146314631467e-06, "epoch": 0.12596259625962597, "percentage": 0.63, "elapsed_time": "0:02:37", "remaining_time": "6:54:40", "throughput": 1530.07, "total_tokens": 241280} {"current_steps": 1150, "total_steps": 181800, "loss": 7.2879, "lr": 3.16006600660066e-06, "epoch": 0.1265126512651265, "percentage": 0.63, "elapsed_time": "0:02:38", "remaining_time": "6:54:38", "throughput": 1530.13, "total_tokens": 242336} {"current_steps": 1155, "total_steps": 181800, "loss": 7.4092, "lr": 3.1738173817381742e-06, "epoch": 0.12706270627062707, "percentage": 0.64, "elapsed_time": "0:02:39", "remaining_time": "6:54:37", "throughput": 1530.59, "total_tokens": 243456} {"current_steps": 1160, "total_steps": 181800, "loss": 7.4895, "lr": 3.1875687568756876e-06, "epoch": 0.1276127612761276, "percentage": 0.64, "elapsed_time": "0:02:39", "remaining_time": "6:54:36", "throughput": 1531.04, "total_tokens": 244576} {"current_steps": 1165, "total_steps": 181800, "loss": 7.2792, "lr": 3.2013201320132018e-06, "epoch": 0.12816281628162815, "percentage": 0.64, "elapsed_time": "0:02:40", "remaining_time": "6:54:35", "throughput": 1531.25, "total_tokens": 245664} {"current_steps": 1170, "total_steps": 181800, "loss": 7.4002, "lr": 3.215071507150715e-06, "epoch": 0.12871287128712872, "percentage": 0.64, "elapsed_time": "0:02:41", "remaining_time": "6:54:34", "throughput": 1531.5, "total_tokens": 246752} {"current_steps": 1175, "total_steps": 181800, "loss": 7.6029, "lr": 3.2288228822882285e-06, "epoch": 0.12926292629262925, "percentage": 0.65, "elapsed_time": "0:02:41", "remaining_time": "6:54:32", "throughput": 1531.16, "total_tokens": 247744} {"current_steps": 1180, "total_steps": 181800, "loss": 7.3566, "lr": 3.2425742574257427e-06, "epoch": 0.12981298129812982, "percentage": 0.65, "elapsed_time": "0:02:42", "remaining_time": "6:54:31", "throughput": 1531.03, "total_tokens": 248768} {"current_steps": 1185, "total_steps": 181800, "loss": 7.2982, "lr": 3.2563256325632564e-06, "epoch": 0.13036303630363036, "percentage": 0.65, "elapsed_time": "0:02:43", "remaining_time": "6:54:30", "throughput": 1531.04, "total_tokens": 249824} {"current_steps": 1190, "total_steps": 181800, "loss": 7.459, "lr": 3.2700770077007706e-06, "epoch": 0.13091309130913092, "percentage": 0.65, "elapsed_time": "0:02:43", "remaining_time": "6:54:29", "throughput": 1530.7, "total_tokens": 250816} {"current_steps": 1195, "total_steps": 181800, "loss": 7.405, "lr": 3.283828382838284e-06, "epoch": 0.13146314631463146, "percentage": 0.66, "elapsed_time": "0:02:44", "remaining_time": "6:54:27", "throughput": 1530.75, "total_tokens": 251872} {"current_steps": 1200, "total_steps": 181800, "loss": 7.6441, "lr": 3.297579757975798e-06, "epoch": 0.132013201320132, "percentage": 0.66, "elapsed_time": "0:02:45", "remaining_time": "6:54:27", "throughput": 1530.95, "total_tokens": 252960} {"current_steps": 1205, "total_steps": 181800, "loss": 7.5805, "lr": 3.3113311331133115e-06, "epoch": 0.13256325632563257, "percentage": 0.66, "elapsed_time": "0:02:45", "remaining_time": "6:54:26", "throughput": 1531.15, "total_tokens": 254048} {"current_steps": 1210, "total_steps": 181800, "loss": 7.4084, "lr": 3.325082508250825e-06, "epoch": 0.1331133113311331, "percentage": 0.67, "elapsed_time": "0:02:46", "remaining_time": "6:54:25", "throughput": 1531.57, "total_tokens": 255168} {"current_steps": 1215, "total_steps": 181800, "loss": 7.2141, "lr": 3.338833883388339e-06, "epoch": 0.13366336633663367, "percentage": 0.67, "elapsed_time": "0:02:47", "remaining_time": "6:54:24", "throughput": 1531.6, "total_tokens": 256224} {"current_steps": 1220, "total_steps": 181800, "loss": 7.4799, "lr": 3.3525852585258524e-06, "epoch": 0.1342134213421342, "percentage": 0.67, "elapsed_time": "0:02:47", "remaining_time": "6:54:23", "throughput": 1531.44, "total_tokens": 257248} {"current_steps": 1225, "total_steps": 181800, "loss": 7.0325, "lr": 3.3663366336633666e-06, "epoch": 0.13476347634763478, "percentage": 0.67, "elapsed_time": "0:02:48", "remaining_time": "6:54:22", "throughput": 1531.67, "total_tokens": 258336} {"current_steps": 1230, "total_steps": 181800, "loss": 7.2038, "lr": 3.38008800880088e-06, "epoch": 0.1353135313531353, "percentage": 0.68, "elapsed_time": "0:02:49", "remaining_time": "6:54:20", "throughput": 1531.55, "total_tokens": 259360} {"current_steps": 1235, "total_steps": 181800, "loss": 7.3499, "lr": 3.393839383938394e-06, "epoch": 0.13586358635863585, "percentage": 0.68, "elapsed_time": "0:02:50", "remaining_time": "6:54:19", "throughput": 1531.79, "total_tokens": 260448} {"current_steps": 1240, "total_steps": 181800, "loss": 7.343, "lr": 3.407590759075908e-06, "epoch": 0.13641364136413642, "percentage": 0.68, "elapsed_time": "0:02:50", "remaining_time": "6:54:18", "throughput": 1531.64, "total_tokens": 261472} {"current_steps": 1245, "total_steps": 181800, "loss": 6.8779, "lr": 3.4213421342134213e-06, "epoch": 0.13696369636963696, "percentage": 0.68, "elapsed_time": "0:02:51", "remaining_time": "6:54:17", "throughput": 1531.67, "total_tokens": 262528} {"current_steps": 1250, "total_steps": 181800, "loss": 7.0583, "lr": 3.4350935093509355e-06, "epoch": 0.13751375137513752, "percentage": 0.69, "elapsed_time": "0:02:52", "remaining_time": "6:54:16", "throughput": 1531.87, "total_tokens": 263616} {"current_steps": 1255, "total_steps": 181800, "loss": 6.7024, "lr": 3.448844884488449e-06, "epoch": 0.13806380638063806, "percentage": 0.69, "elapsed_time": "0:02:52", "remaining_time": "6:54:15", "throughput": 1531.7, "total_tokens": 264640} {"current_steps": 1260, "total_steps": 181800, "loss": 6.8789, "lr": 3.462596259625963e-06, "epoch": 0.13861386138613863, "percentage": 0.69, "elapsed_time": "0:02:53", "remaining_time": "6:54:15", "throughput": 1531.7, "total_tokens": 265696} {"current_steps": 1265, "total_steps": 181800, "loss": 6.789, "lr": 3.4763476347634764e-06, "epoch": 0.13916391639163916, "percentage": 0.7, "elapsed_time": "0:02:54", "remaining_time": "6:54:14", "throughput": 1531.52, "total_tokens": 266720} {"current_steps": 1270, "total_steps": 181800, "loss": 6.8071, "lr": 3.4900990099009906e-06, "epoch": 0.1397139713971397, "percentage": 0.7, "elapsed_time": "0:02:54", "remaining_time": "6:54:13", "throughput": 1531.54, "total_tokens": 267776} {"current_steps": 1275, "total_steps": 181800, "loss": 6.5955, "lr": 3.503850385038504e-06, "epoch": 0.14026402640264027, "percentage": 0.7, "elapsed_time": "0:02:55", "remaining_time": "6:54:12", "throughput": 1531.56, "total_tokens": 268832} {"current_steps": 1280, "total_steps": 181800, "loss": 6.929, "lr": 3.5176017601760177e-06, "epoch": 0.1408140814081408, "percentage": 0.7, "elapsed_time": "0:02:56", "remaining_time": "6:54:11", "throughput": 1531.95, "total_tokens": 269952} {"current_steps": 1285, "total_steps": 181800, "loss": 6.6871, "lr": 3.5313531353135315e-06, "epoch": 0.14136413641364137, "percentage": 0.71, "elapsed_time": "0:02:56", "remaining_time": "6:54:10", "throughput": 1532.0, "total_tokens": 271008} {"current_steps": 1290, "total_steps": 181800, "loss": 6.6865, "lr": 3.5451045104510453e-06, "epoch": 0.1419141914191419, "percentage": 0.71, "elapsed_time": "0:02:57", "remaining_time": "6:54:09", "throughput": 1532.22, "total_tokens": 272096} {"current_steps": 1295, "total_steps": 181800, "loss": 6.4958, "lr": 3.5588558855885595e-06, "epoch": 0.14246424642464248, "percentage": 0.71, "elapsed_time": "0:02:58", "remaining_time": "6:54:08", "throughput": 1532.06, "total_tokens": 273120} {"current_steps": 1300, "total_steps": 181800, "loss": 6.3162, "lr": 3.572607260726073e-06, "epoch": 0.14301430143014301, "percentage": 0.72, "elapsed_time": "0:02:58", "remaining_time": "6:54:07", "throughput": 1532.27, "total_tokens": 274208} {"current_steps": 1305, "total_steps": 181800, "loss": 6.3615, "lr": 3.586358635863587e-06, "epoch": 0.14356435643564355, "percentage": 0.72, "elapsed_time": "0:02:59", "remaining_time": "6:54:07", "throughput": 1532.24, "total_tokens": 275264} {"current_steps": 1310, "total_steps": 181800, "loss": 6.4205, "lr": 3.6001100110011004e-06, "epoch": 0.14411441144114412, "percentage": 0.72, "elapsed_time": "0:03:00", "remaining_time": "6:54:07", "throughput": 1531.81, "total_tokens": 276256} {"current_steps": 1315, "total_steps": 181800, "loss": 6.4182, "lr": 3.6138613861386137e-06, "epoch": 0.14466446644664466, "percentage": 0.72, "elapsed_time": "0:03:01", "remaining_time": "6:54:06", "throughput": 1531.67, "total_tokens": 277280} {"current_steps": 1320, "total_steps": 181800, "loss": 6.2854, "lr": 3.627612761276128e-06, "epoch": 0.14521452145214522, "percentage": 0.73, "elapsed_time": "0:03:01", "remaining_time": "6:54:05", "throughput": 1532.24, "total_tokens": 278432} {"current_steps": 1325, "total_steps": 181800, "loss": 6.032, "lr": 3.6413641364136412e-06, "epoch": 0.14576457645764576, "percentage": 0.73, "elapsed_time": "0:03:02", "remaining_time": "6:54:04", "throughput": 1532.29, "total_tokens": 279488} {"current_steps": 1330, "total_steps": 181800, "loss": 6.0312, "lr": 3.6551155115511554e-06, "epoch": 0.14631463146314633, "percentage": 0.73, "elapsed_time": "0:03:03", "remaining_time": "6:54:02", "throughput": 1532.51, "total_tokens": 280576} {"current_steps": 1335, "total_steps": 181800, "loss": 5.9493, "lr": 3.668866886688669e-06, "epoch": 0.14686468646864687, "percentage": 0.73, "elapsed_time": "0:03:03", "remaining_time": "6:54:01", "throughput": 1532.71, "total_tokens": 281664} {"current_steps": 1340, "total_steps": 181800, "loss": 6.0968, "lr": 3.682618261826183e-06, "epoch": 0.1474147414741474, "percentage": 0.74, "elapsed_time": "0:03:04", "remaining_time": "6:54:01", "throughput": 1532.71, "total_tokens": 282720} {"current_steps": 1345, "total_steps": 181800, "loss": 6.142, "lr": 3.6963696369636968e-06, "epoch": 0.14796479647964797, "percentage": 0.74, "elapsed_time": "0:03:05", "remaining_time": "6:53:59", "throughput": 1532.76, "total_tokens": 283776} {"current_steps": 1350, "total_steps": 181800, "loss": 5.9042, "lr": 3.71012101210121e-06, "epoch": 0.1485148514851485, "percentage": 0.74, "elapsed_time": "0:03:05", "remaining_time": "6:53:58", "throughput": 1532.97, "total_tokens": 284864} {"current_steps": 1355, "total_steps": 181800, "loss": 5.8249, "lr": 3.7238723872387243e-06, "epoch": 0.14906490649064907, "percentage": 0.75, "elapsed_time": "0:03:06", "remaining_time": "6:53:57", "throughput": 1533.35, "total_tokens": 285984} {"current_steps": 1360, "total_steps": 181800, "loss": 5.8849, "lr": 3.7376237623762377e-06, "epoch": 0.1496149614961496, "percentage": 0.75, "elapsed_time": "0:03:07", "remaining_time": "6:53:56", "throughput": 1533.39, "total_tokens": 287040} {"current_steps": 1365, "total_steps": 181800, "loss": 5.9874, "lr": 3.751375137513752e-06, "epoch": 0.15016501650165018, "percentage": 0.75, "elapsed_time": "0:03:07", "remaining_time": "6:53:54", "throughput": 1533.25, "total_tokens": 288064} {"current_steps": 1370, "total_steps": 181800, "loss": 5.5594, "lr": 3.765126512651265e-06, "epoch": 0.15071507150715072, "percentage": 0.75, "elapsed_time": "0:03:08", "remaining_time": "6:53:54", "throughput": 1533.08, "total_tokens": 289088} {"current_steps": 1375, "total_steps": 181800, "loss": 5.6341, "lr": 3.7788778877887786e-06, "epoch": 0.15126512651265125, "percentage": 0.76, "elapsed_time": "0:03:09", "remaining_time": "6:53:53", "throughput": 1532.59, "total_tokens": 290048} {"current_steps": 1380, "total_steps": 181800, "loss": 5.6814, "lr": 3.7926292629262927e-06, "epoch": 0.15181518151815182, "percentage": 0.76, "elapsed_time": "0:03:09", "remaining_time": "6:53:52", "throughput": 1532.76, "total_tokens": 291136} {"current_steps": 1385, "total_steps": 181800, "loss": 5.5651, "lr": 3.8063806380638065e-06, "epoch": 0.15236523652365236, "percentage": 0.76, "elapsed_time": "0:03:10", "remaining_time": "6:53:52", "throughput": 1532.77, "total_tokens": 292192} {"current_steps": 1390, "total_steps": 181800, "loss": 5.4306, "lr": 3.82013201320132e-06, "epoch": 0.15291529152915292, "percentage": 0.76, "elapsed_time": "0:03:11", "remaining_time": "6:53:51", "throughput": 1532.44, "total_tokens": 293184} {"current_steps": 1395, "total_steps": 181800, "loss": 5.5772, "lr": 3.833883388338834e-06, "epoch": 0.15346534653465346, "percentage": 0.77, "elapsed_time": "0:03:12", "remaining_time": "6:53:50", "throughput": 1532.61, "total_tokens": 294272} {"current_steps": 1400, "total_steps": 181800, "loss": 5.3978, "lr": 3.847634763476348e-06, "epoch": 0.15401540154015403, "percentage": 0.77, "elapsed_time": "0:03:12", "remaining_time": "6:53:49", "throughput": 1532.65, "total_tokens": 295328} {"current_steps": 1405, "total_steps": 181800, "loss": 5.2761, "lr": 3.861386138613861e-06, "epoch": 0.15456545654565457, "percentage": 0.77, "elapsed_time": "0:03:13", "remaining_time": "6:53:48", "throughput": 1532.82, "total_tokens": 296416} {"current_steps": 1410, "total_steps": 181800, "loss": 5.4516, "lr": 3.875137513751375e-06, "epoch": 0.1551155115511551, "percentage": 0.78, "elapsed_time": "0:03:14", "remaining_time": "6:53:48", "throughput": 1533.0, "total_tokens": 297504} {"current_steps": 1415, "total_steps": 181800, "loss": 5.2172, "lr": 3.888888888888889e-06, "epoch": 0.15566556655665567, "percentage": 0.78, "elapsed_time": "0:03:14", "remaining_time": "6:53:47", "throughput": 1532.67, "total_tokens": 298496} {"current_steps": 1420, "total_steps": 181800, "loss": 5.2467, "lr": 3.902640264026403e-06, "epoch": 0.1562156215621562, "percentage": 0.78, "elapsed_time": "0:03:15", "remaining_time": "6:53:47", "throughput": 1532.95, "total_tokens": 299616} {"current_steps": 1425, "total_steps": 181800, "loss": 5.1721, "lr": 3.916391639163917e-06, "epoch": 0.15676567656765678, "percentage": 0.78, "elapsed_time": "0:03:16", "remaining_time": "6:53:47", "throughput": 1532.95, "total_tokens": 300672} {"current_steps": 1430, "total_steps": 181800, "loss": 5.0744, "lr": 3.9301430143014305e-06, "epoch": 0.1573157315731573, "percentage": 0.79, "elapsed_time": "0:03:16", "remaining_time": "6:53:46", "throughput": 1532.64, "total_tokens": 301664} {"current_steps": 1435, "total_steps": 181800, "loss": 5.1807, "lr": 3.943894389438945e-06, "epoch": 0.15786578657865788, "percentage": 0.79, "elapsed_time": "0:03:17", "remaining_time": "6:53:45", "throughput": 1532.32, "total_tokens": 302656} {"current_steps": 1440, "total_steps": 181800, "loss": 5.0229, "lr": 3.957645764576458e-06, "epoch": 0.15841584158415842, "percentage": 0.79, "elapsed_time": "0:03:18", "remaining_time": "6:53:44", "throughput": 1532.49, "total_tokens": 303744} {"current_steps": 1445, "total_steps": 181800, "loss": 4.9634, "lr": 3.971397139713971e-06, "epoch": 0.15896589658965896, "percentage": 0.79, "elapsed_time": "0:03:18", "remaining_time": "6:53:44", "throughput": 1532.34, "total_tokens": 304768} {"current_steps": 1450, "total_steps": 181800, "loss": 4.7743, "lr": 3.9851485148514856e-06, "epoch": 0.15951595159515952, "percentage": 0.8, "elapsed_time": "0:03:19", "remaining_time": "6:53:43", "throughput": 1532.18, "total_tokens": 305792} {"current_steps": 1455, "total_steps": 181800, "loss": 4.9524, "lr": 3.998899889988999e-06, "epoch": 0.16006600660066006, "percentage": 0.8, "elapsed_time": "0:03:20", "remaining_time": "6:53:42", "throughput": 1532.2, "total_tokens": 306848} {"current_steps": 1460, "total_steps": 181800, "loss": 4.8292, "lr": 4.012651265126513e-06, "epoch": 0.16061606160616063, "percentage": 0.8, "elapsed_time": "0:03:20", "remaining_time": "6:53:41", "throughput": 1532.4, "total_tokens": 307936} {"current_steps": 1465, "total_steps": 181800, "loss": 4.7939, "lr": 4.0264026402640265e-06, "epoch": 0.16116611661166116, "percentage": 0.81, "elapsed_time": "0:03:21", "remaining_time": "6:53:40", "throughput": 1532.28, "total_tokens": 308960} {"current_steps": 1470, "total_steps": 181800, "loss": 4.8823, "lr": 4.040154015401541e-06, "epoch": 0.1617161716171617, "percentage": 0.81, "elapsed_time": "0:03:22", "remaining_time": "6:53:39", "throughput": 1532.63, "total_tokens": 310080} {"current_steps": 1475, "total_steps": 181800, "loss": 4.7777, "lr": 4.053905390539054e-06, "epoch": 0.16226622662266227, "percentage": 0.81, "elapsed_time": "0:03:23", "remaining_time": "6:53:37", "throughput": 1532.51, "total_tokens": 311104} {"current_steps": 1480, "total_steps": 181800, "loss": 4.7416, "lr": 4.067656765676567e-06, "epoch": 0.1628162816281628, "percentage": 0.81, "elapsed_time": "0:03:23", "remaining_time": "6:53:36", "throughput": 1532.7, "total_tokens": 312192} {"current_steps": 1485, "total_steps": 181800, "loss": 4.7181, "lr": 4.0814081408140816e-06, "epoch": 0.16336633663366337, "percentage": 0.82, "elapsed_time": "0:03:24", "remaining_time": "6:53:35", "throughput": 1532.72, "total_tokens": 313248} {"current_steps": 1490, "total_steps": 181800, "loss": 4.7193, "lr": 4.095159515951595e-06, "epoch": 0.1639163916391639, "percentage": 0.82, "elapsed_time": "0:03:25", "remaining_time": "6:53:34", "throughput": 1533.06, "total_tokens": 314368} {"current_steps": 1495, "total_steps": 181800, "loss": 4.6657, "lr": 4.108910891089109e-06, "epoch": 0.16446644664466448, "percentage": 0.82, "elapsed_time": "0:03:25", "remaining_time": "6:53:33", "throughput": 1533.4, "total_tokens": 315488} {"current_steps": 1500, "total_steps": 181800, "loss": 4.5255, "lr": 4.1226622662266225e-06, "epoch": 0.16501650165016502, "percentage": 0.83, "elapsed_time": "0:03:26", "remaining_time": "6:53:33", "throughput": 1533.72, "total_tokens": 316608} {"current_steps": 1505, "total_steps": 181800, "loss": 4.5752, "lr": 4.136413641364137e-06, "epoch": 0.16556655665566555, "percentage": 0.83, "elapsed_time": "0:03:27", "remaining_time": "6:53:32", "throughput": 1533.74, "total_tokens": 317664} {"current_steps": 1510, "total_steps": 181800, "loss": 4.4356, "lr": 4.15016501650165e-06, "epoch": 0.16611661166116612, "percentage": 0.83, "elapsed_time": "0:03:27", "remaining_time": "6:53:31", "throughput": 1534.07, "total_tokens": 318784} {"current_steps": 1515, "total_steps": 181800, "loss": 4.4716, "lr": 4.163916391639164e-06, "epoch": 0.16666666666666666, "percentage": 0.83, "elapsed_time": "0:03:28", "remaining_time": "6:53:29", "throughput": 1533.95, "total_tokens": 319808} {"current_steps": 1520, "total_steps": 181800, "loss": 4.3935, "lr": 4.1776677667766775e-06, "epoch": 0.16721672167216722, "percentage": 0.84, "elapsed_time": "0:03:29", "remaining_time": "6:53:29", "throughput": 1533.96, "total_tokens": 320864} {"current_steps": 1525, "total_steps": 181800, "loss": 4.3528, "lr": 4.191419141914192e-06, "epoch": 0.16776677667766776, "percentage": 0.84, "elapsed_time": "0:03:29", "remaining_time": "6:53:28", "throughput": 1533.67, "total_tokens": 321856} {"current_steps": 1530, "total_steps": 181800, "loss": 4.3166, "lr": 4.205170517051706e-06, "epoch": 0.16831683168316833, "percentage": 0.84, "elapsed_time": "0:03:30", "remaining_time": "6:53:28", "throughput": 1534.09, "total_tokens": 323008} {"current_steps": 1535, "total_steps": 181800, "loss": 4.261, "lr": 4.218921892189219e-06, "epoch": 0.16886688668866887, "percentage": 0.84, "elapsed_time": "0:03:31", "remaining_time": "6:53:27", "throughput": 1534.26, "total_tokens": 324096} {"current_steps": 1540, "total_steps": 181800, "loss": 4.2335, "lr": 4.2326732673267335e-06, "epoch": 0.1694169416941694, "percentage": 0.85, "elapsed_time": "0:03:31", "remaining_time": "6:53:26", "throughput": 1534.29, "total_tokens": 325152} {"current_steps": 1545, "total_steps": 181800, "loss": 4.1291, "lr": 4.246424642464247e-06, "epoch": 0.16996699669966997, "percentage": 0.85, "elapsed_time": "0:03:32", "remaining_time": "6:53:25", "throughput": 1534.61, "total_tokens": 326272} {"current_steps": 1550, "total_steps": 181800, "loss": 4.2598, "lr": 4.26017601760176e-06, "epoch": 0.1705170517051705, "percentage": 0.85, "elapsed_time": "0:03:33", "remaining_time": "6:53:24", "throughput": 1534.48, "total_tokens": 327296} {"current_steps": 1555, "total_steps": 181800, "loss": 4.1707, "lr": 4.273927392739274e-06, "epoch": 0.17106710671067107, "percentage": 0.86, "elapsed_time": "0:03:33", "remaining_time": "6:53:23", "throughput": 1534.18, "total_tokens": 328288} {"current_steps": 1560, "total_steps": 181800, "loss": 4.0399, "lr": 4.287678767876788e-06, "epoch": 0.1716171617161716, "percentage": 0.86, "elapsed_time": "0:03:34", "remaining_time": "6:53:22", "throughput": 1534.49, "total_tokens": 329408} {"current_steps": 1565, "total_steps": 181800, "loss": 4.1585, "lr": 4.301430143014302e-06, "epoch": 0.17216721672167218, "percentage": 0.86, "elapsed_time": "0:03:35", "remaining_time": "6:53:21", "throughput": 1534.35, "total_tokens": 330432} {"current_steps": 1570, "total_steps": 181800, "loss": 4.0821, "lr": 4.315181518151815e-06, "epoch": 0.17271727172717272, "percentage": 0.86, "elapsed_time": "0:03:36", "remaining_time": "6:53:20", "throughput": 1534.36, "total_tokens": 331488} {"current_steps": 1575, "total_steps": 181800, "loss": 4.0488, "lr": 4.3289328932893295e-06, "epoch": 0.17326732673267325, "percentage": 0.87, "elapsed_time": "0:03:36", "remaining_time": "6:53:19", "throughput": 1534.09, "total_tokens": 332480} {"current_steps": 1580, "total_steps": 181800, "loss": 4.0445, "lr": 4.342684268426843e-06, "epoch": 0.17381738173817382, "percentage": 0.87, "elapsed_time": "0:03:37", "remaining_time": "6:53:19", "throughput": 1534.09, "total_tokens": 333536} {"current_steps": 1585, "total_steps": 181800, "loss": 3.9162, "lr": 4.356435643564356e-06, "epoch": 0.17436743674367436, "percentage": 0.87, "elapsed_time": "0:03:38", "remaining_time": "6:53:18", "throughput": 1533.97, "total_tokens": 334560} {"current_steps": 1590, "total_steps": 181800, "loss": 3.9284, "lr": 4.37018701870187e-06, "epoch": 0.17491749174917492, "percentage": 0.87, "elapsed_time": "0:03:38", "remaining_time": "6:53:17", "throughput": 1534.0, "total_tokens": 335616} {"current_steps": 1595, "total_steps": 181800, "loss": 4.0068, "lr": 4.383938393839384e-06, "epoch": 0.17546754675467546, "percentage": 0.88, "elapsed_time": "0:03:39", "remaining_time": "6:53:15", "throughput": 1533.88, "total_tokens": 336640} {"current_steps": 1600, "total_steps": 181800, "loss": 3.9552, "lr": 4.397689768976898e-06, "epoch": 0.17601760176017603, "percentage": 0.88, "elapsed_time": "0:03:40", "remaining_time": "6:53:14", "throughput": 1534.05, "total_tokens": 337728} {"current_steps": 1605, "total_steps": 181800, "loss": 3.955, "lr": 4.411441144114411e-06, "epoch": 0.17656765676567657, "percentage": 0.88, "elapsed_time": "0:03:40", "remaining_time": "6:53:13", "throughput": 1534.08, "total_tokens": 338784} {"current_steps": 1610, "total_steps": 181800, "loss": 3.8774, "lr": 4.4251925192519255e-06, "epoch": 0.1771177117711771, "percentage": 0.89, "elapsed_time": "0:03:41", "remaining_time": "6:53:12", "throughput": 1533.81, "total_tokens": 339776} {"current_steps": 1615, "total_steps": 181800, "loss": 3.8536, "lr": 4.438943894389439e-06, "epoch": 0.17766776677667767, "percentage": 0.89, "elapsed_time": "0:03:42", "remaining_time": "6:53:11", "throughput": 1533.55, "total_tokens": 340768} {"current_steps": 1620, "total_steps": 181800, "loss": 3.8006, "lr": 4.452695269526953e-06, "epoch": 0.1782178217821782, "percentage": 0.89, "elapsed_time": "0:03:42", "remaining_time": "6:53:10", "throughput": 1533.3, "total_tokens": 341760} {"current_steps": 1625, "total_steps": 181800, "loss": 3.8889, "lr": 4.466446644664466e-06, "epoch": 0.17876787678767878, "percentage": 0.89, "elapsed_time": "0:03:43", "remaining_time": "6:53:09", "throughput": 1533.87, "total_tokens": 342944} {"current_steps": 1630, "total_steps": 181800, "loss": 3.8046, "lr": 4.4801980198019806e-06, "epoch": 0.1793179317931793, "percentage": 0.9, "elapsed_time": "0:03:44", "remaining_time": "6:53:08", "throughput": 1533.9, "total_tokens": 344000} {"current_steps": 1635, "total_steps": 181800, "loss": 3.7182, "lr": 4.493949394939495e-06, "epoch": 0.17986798679867988, "percentage": 0.9, "elapsed_time": "0:03:44", "remaining_time": "6:53:07", "throughput": 1534.2, "total_tokens": 345120} {"current_steps": 1640, "total_steps": 181800, "loss": 3.803, "lr": 4.507700770077008e-06, "epoch": 0.18041804180418042, "percentage": 0.9, "elapsed_time": "0:03:45", "remaining_time": "6:53:07", "throughput": 1534.49, "total_tokens": 346240} {"current_steps": 1645, "total_steps": 181800, "loss": 3.7695, "lr": 4.521452145214522e-06, "epoch": 0.18096809680968096, "percentage": 0.9, "elapsed_time": "0:03:46", "remaining_time": "6:53:05", "throughput": 1534.67, "total_tokens": 347328} {"current_steps": 1650, "total_steps": 181800, "loss": 3.6966, "lr": 4.535203520352036e-06, "epoch": 0.18151815181518152, "percentage": 0.91, "elapsed_time": "0:03:47", "remaining_time": "6:53:04", "throughput": 1534.84, "total_tokens": 348416} {"current_steps": 1655, "total_steps": 181800, "loss": 3.7095, "lr": 4.548954895489549e-06, "epoch": 0.18206820682068206, "percentage": 0.91, "elapsed_time": "0:03:47", "remaining_time": "6:53:03", "throughput": 1535.29, "total_tokens": 349568} {"current_steps": 1660, "total_steps": 181800, "loss": 3.6894, "lr": 4.562706270627063e-06, "epoch": 0.18261826182618263, "percentage": 0.91, "elapsed_time": "0:03:48", "remaining_time": "6:53:02", "throughput": 1535.61, "total_tokens": 350688} {"current_steps": 1665, "total_steps": 181800, "loss": 3.6925, "lr": 4.5764576457645765e-06, "epoch": 0.18316831683168316, "percentage": 0.92, "elapsed_time": "0:03:49", "remaining_time": "6:53:00", "throughput": 1535.51, "total_tokens": 351712} {"current_steps": 1670, "total_steps": 181800, "loss": 3.6686, "lr": 4.590209020902091e-06, "epoch": 0.18371837183718373, "percentage": 0.92, "elapsed_time": "0:03:49", "remaining_time": "6:52:59", "throughput": 1535.69, "total_tokens": 352800} {"current_steps": 1675, "total_steps": 181800, "loss": 3.608, "lr": 4.603960396039604e-06, "epoch": 0.18426842684268427, "percentage": 0.92, "elapsed_time": "0:03:50", "remaining_time": "6:52:58", "throughput": 1535.73, "total_tokens": 353856} {"current_steps": 1680, "total_steps": 181800, "loss": 3.6166, "lr": 4.617711771177118e-06, "epoch": 0.1848184818481848, "percentage": 0.92, "elapsed_time": "0:03:51", "remaining_time": "6:52:57", "throughput": 1535.75, "total_tokens": 354912} {"current_steps": 1685, "total_steps": 181800, "loss": 3.5695, "lr": 4.631463146314632e-06, "epoch": 0.18536853685368537, "percentage": 0.93, "elapsed_time": "0:03:51", "remaining_time": "6:52:55", "throughput": 1535.8, "total_tokens": 355968} {"current_steps": 1690, "total_steps": 181800, "loss": 3.599, "lr": 4.645214521452145e-06, "epoch": 0.1859185918591859, "percentage": 0.93, "elapsed_time": "0:03:52", "remaining_time": "6:52:54", "throughput": 1535.98, "total_tokens": 357056} {"current_steps": 1695, "total_steps": 181800, "loss": 3.6938, "lr": 4.658965896589659e-06, "epoch": 0.18646864686468648, "percentage": 0.93, "elapsed_time": "0:03:53", "remaining_time": "6:52:53", "throughput": 1536.14, "total_tokens": 358144} {"current_steps": 1700, "total_steps": 181800, "loss": 3.5958, "lr": 4.6727172717271725e-06, "epoch": 0.18701870187018702, "percentage": 0.94, "elapsed_time": "0:03:53", "remaining_time": "6:52:52", "throughput": 1536.01, "total_tokens": 359168} {"current_steps": 1705, "total_steps": 181800, "loss": 3.6366, "lr": 4.686468646864687e-06, "epoch": 0.18756875687568758, "percentage": 0.94, "elapsed_time": "0:03:54", "remaining_time": "6:52:51", "throughput": 1536.01, "total_tokens": 360224} {"current_steps": 1710, "total_steps": 181800, "loss": 3.5002, "lr": 4.7002200220022e-06, "epoch": 0.18811881188118812, "percentage": 0.94, "elapsed_time": "0:03:55", "remaining_time": "6:52:50", "throughput": 1535.9, "total_tokens": 361248} {"current_steps": 1715, "total_steps": 181800, "loss": 3.4902, "lr": 4.713971397139714e-06, "epoch": 0.18866886688668866, "percentage": 0.94, "elapsed_time": "0:03:55", "remaining_time": "6:52:49", "throughput": 1535.78, "total_tokens": 362272} {"current_steps": 1720, "total_steps": 181800, "loss": 3.5858, "lr": 4.727722772277228e-06, "epoch": 0.18921892189218922, "percentage": 0.95, "elapsed_time": "0:03:56", "remaining_time": "6:52:48", "throughput": 1536.07, "total_tokens": 363392} {"current_steps": 1725, "total_steps": 181800, "loss": 3.5347, "lr": 4.741474147414742e-06, "epoch": 0.18976897689768976, "percentage": 0.95, "elapsed_time": "0:03:57", "remaining_time": "6:52:47", "throughput": 1536.34, "total_tokens": 364512} {"current_steps": 1730, "total_steps": 181800, "loss": 3.5659, "lr": 4.755225522552256e-06, "epoch": 0.19031903190319033, "percentage": 0.95, "elapsed_time": "0:03:57", "remaining_time": "6:52:47", "throughput": 1536.35, "total_tokens": 365568} {"current_steps": 1735, "total_steps": 181800, "loss": 3.5397, "lr": 4.768976897689769e-06, "epoch": 0.19086908690869087, "percentage": 0.95, "elapsed_time": "0:03:58", "remaining_time": "6:52:46", "throughput": 1536.76, "total_tokens": 366720} {"current_steps": 1740, "total_steps": 181800, "loss": 3.5176, "lr": 4.7827282728272836e-06, "epoch": 0.19141914191419143, "percentage": 0.96, "elapsed_time": "0:03:59", "remaining_time": "6:52:44", "throughput": 1536.79, "total_tokens": 367776} {"current_steps": 1745, "total_steps": 181800, "loss": 3.5718, "lr": 4.796479647964797e-06, "epoch": 0.19196919691969197, "percentage": 0.96, "elapsed_time": "0:03:59", "remaining_time": "6:52:43", "throughput": 1536.81, "total_tokens": 368832} {"current_steps": 1750, "total_steps": 181800, "loss": 3.4523, "lr": 4.810231023102311e-06, "epoch": 0.1925192519251925, "percentage": 0.96, "elapsed_time": "0:04:00", "remaining_time": "6:52:43", "throughput": 1536.8, "total_tokens": 369888} {"current_steps": 1755, "total_steps": 181800, "loss": 3.5159, "lr": 4.8239823982398245e-06, "epoch": 0.19306930693069307, "percentage": 0.97, "elapsed_time": "0:04:01", "remaining_time": "6:52:42", "throughput": 1536.53, "total_tokens": 370880} {"current_steps": 1760, "total_steps": 181800, "loss": 3.41, "lr": 4.837733773377338e-06, "epoch": 0.1936193619361936, "percentage": 0.97, "elapsed_time": "0:04:02", "remaining_time": "6:52:41", "throughput": 1536.42, "total_tokens": 371904} {"current_steps": 1765, "total_steps": 181800, "loss": 3.482, "lr": 4.851485148514852e-06, "epoch": 0.19416941694169418, "percentage": 0.97, "elapsed_time": "0:04:02", "remaining_time": "6:52:40", "throughput": 1536.45, "total_tokens": 372960} {"current_steps": 1770, "total_steps": 181800, "loss": 3.4855, "lr": 4.865236523652365e-06, "epoch": 0.19471947194719472, "percentage": 0.97, "elapsed_time": "0:04:03", "remaining_time": "6:52:39", "throughput": 1536.6, "total_tokens": 374048} {"current_steps": 1775, "total_steps": 181800, "loss": 3.4263, "lr": 4.8789878987898795e-06, "epoch": 0.19526952695269528, "percentage": 0.98, "elapsed_time": "0:04:04", "remaining_time": "6:52:38", "throughput": 1536.61, "total_tokens": 375104} {"current_steps": 1780, "total_steps": 181800, "loss": 3.4421, "lr": 4.892739273927393e-06, "epoch": 0.19581958195819582, "percentage": 0.98, "elapsed_time": "0:04:04", "remaining_time": "6:52:38", "throughput": 1536.84, "total_tokens": 376224} {"current_steps": 1785, "total_steps": 181800, "loss": 3.4474, "lr": 4.906490649064906e-06, "epoch": 0.19636963696369636, "percentage": 0.98, "elapsed_time": "0:04:05", "remaining_time": "6:52:37", "throughput": 1537.07, "total_tokens": 377344} {"current_steps": 1790, "total_steps": 181800, "loss": 3.3859, "lr": 4.9202420242024204e-06, "epoch": 0.19691969196919692, "percentage": 0.98, "elapsed_time": "0:04:06", "remaining_time": "6:52:36", "throughput": 1536.96, "total_tokens": 378368} {"current_steps": 1795, "total_steps": 181800, "loss": 3.4431, "lr": 4.933993399339934e-06, "epoch": 0.19746974697469746, "percentage": 0.99, "elapsed_time": "0:04:06", "remaining_time": "6:52:35", "throughput": 1536.98, "total_tokens": 379424} {"current_steps": 1800, "total_steps": 181800, "loss": 3.4122, "lr": 4.947744774477448e-06, "epoch": 0.19801980198019803, "percentage": 0.99, "elapsed_time": "0:04:07", "remaining_time": "6:52:35", "throughput": 1536.84, "total_tokens": 380448} {"current_steps": 1805, "total_steps": 181800, "loss": 3.4009, "lr": 4.961496149614961e-06, "epoch": 0.19856985698569857, "percentage": 0.99, "elapsed_time": "0:04:08", "remaining_time": "6:52:34", "throughput": 1537.09, "total_tokens": 381568} {"current_steps": 1810, "total_steps": 181800, "loss": 3.3777, "lr": 4.9752475247524755e-06, "epoch": 0.19911991199119913, "percentage": 1.0, "elapsed_time": "0:04:08", "remaining_time": "6:52:33", "throughput": 1537.34, "total_tokens": 382688} {"current_steps": 1815, "total_steps": 181800, "loss": 3.4004, "lr": 4.988998899889989e-06, "epoch": 0.19966996699669967, "percentage": 1.0, "elapsed_time": "0:04:09", "remaining_time": "6:52:33", "throughput": 1537.6, "total_tokens": 383808} {"current_steps": 1820, "total_steps": 181800, "loss": 3.3696, "lr": 5.002750275027502e-06, "epoch": 0.2002200220022002, "percentage": 1.0, "elapsed_time": "0:04:10", "remaining_time": "6:52:32", "throughput": 1537.84, "total_tokens": 384928} {"current_steps": 1825, "total_steps": 181800, "loss": 3.3638, "lr": 5.0165016501650164e-06, "epoch": 0.20077007700770078, "percentage": 1.0, "elapsed_time": "0:04:10", "remaining_time": "6:52:31", "throughput": 1537.58, "total_tokens": 385920} {"current_steps": 1830, "total_steps": 181800, "loss": 3.4051, "lr": 5.030253025302531e-06, "epoch": 0.20132013201320131, "percentage": 1.01, "elapsed_time": "0:04:11", "remaining_time": "6:52:31", "throughput": 1537.32, "total_tokens": 386912} {"current_steps": 1835, "total_steps": 181800, "loss": 3.3815, "lr": 5.044004400440045e-06, "epoch": 0.20187018701870188, "percentage": 1.01, "elapsed_time": "0:04:12", "remaining_time": "6:52:30", "throughput": 1537.32, "total_tokens": 387968} {"current_steps": 1840, "total_steps": 181800, "loss": 3.3589, "lr": 5.057755775577558e-06, "epoch": 0.20242024202420242, "percentage": 1.01, "elapsed_time": "0:04:13", "remaining_time": "6:52:29", "throughput": 1537.32, "total_tokens": 389024} {"current_steps": 1845, "total_steps": 181800, "loss": 3.3309, "lr": 5.071507150715072e-06, "epoch": 0.20297029702970298, "percentage": 1.01, "elapsed_time": "0:04:13", "remaining_time": "6:52:28", "throughput": 1537.2, "total_tokens": 390048} {"current_steps": 1850, "total_steps": 181800, "loss": 3.3234, "lr": 5.085258525852586e-06, "epoch": 0.20352035203520352, "percentage": 1.02, "elapsed_time": "0:04:14", "remaining_time": "6:52:28", "throughput": 1536.83, "total_tokens": 391008} {"current_steps": 1855, "total_steps": 181800, "loss": 3.3752, "lr": 5.099009900990099e-06, "epoch": 0.20407040704070406, "percentage": 1.02, "elapsed_time": "0:04:15", "remaining_time": "6:52:26", "throughput": 1536.98, "total_tokens": 392096} {"current_steps": 1860, "total_steps": 181800, "loss": 3.303, "lr": 5.112761276127613e-06, "epoch": 0.20462046204620463, "percentage": 1.02, "elapsed_time": "0:04:15", "remaining_time": "6:52:26", "throughput": 1537.11, "total_tokens": 393184} {"current_steps": 1865, "total_steps": 181800, "loss": 3.3045, "lr": 5.126512651265127e-06, "epoch": 0.20517051705170516, "percentage": 1.03, "elapsed_time": "0:04:16", "remaining_time": "6:52:24", "throughput": 1537.27, "total_tokens": 394272} {"current_steps": 1870, "total_steps": 181800, "loss": 3.2605, "lr": 5.140264026402641e-06, "epoch": 0.20572057205720573, "percentage": 1.03, "elapsed_time": "0:04:17", "remaining_time": "6:52:23", "throughput": 1537.27, "total_tokens": 395328} {"current_steps": 1875, "total_steps": 181800, "loss": 3.3112, "lr": 5.154015401540154e-06, "epoch": 0.20627062706270627, "percentage": 1.03, "elapsed_time": "0:04:17", "remaining_time": "6:52:23", "throughput": 1537.27, "total_tokens": 396384} {"current_steps": 1880, "total_steps": 181800, "loss": 3.2632, "lr": 5.167766776677668e-06, "epoch": 0.2068206820682068, "percentage": 1.03, "elapsed_time": "0:04:18", "remaining_time": "6:52:22", "throughput": 1537.4, "total_tokens": 397472} {"current_steps": 1885, "total_steps": 181800, "loss": 3.2373, "lr": 5.181518151815182e-06, "epoch": 0.20737073707370737, "percentage": 1.04, "elapsed_time": "0:04:19", "remaining_time": "6:52:21", "throughput": 1537.4, "total_tokens": 398528} {"current_steps": 1890, "total_steps": 181800, "loss": 3.2612, "lr": 5.195269526952695e-06, "epoch": 0.2079207920792079, "percentage": 1.04, "elapsed_time": "0:04:19", "remaining_time": "6:52:20", "throughput": 1537.28, "total_tokens": 399552} {"current_steps": 1895, "total_steps": 181800, "loss": 3.2957, "lr": 5.209020902090209e-06, "epoch": 0.20847084708470848, "percentage": 1.04, "elapsed_time": "0:04:20", "remaining_time": "6:52:20", "throughput": 1537.16, "total_tokens": 400576} {"current_steps": 1900, "total_steps": 181800, "loss": 3.29, "lr": 5.222772277227723e-06, "epoch": 0.20902090209020902, "percentage": 1.05, "elapsed_time": "0:04:21", "remaining_time": "6:52:19", "throughput": 1537.03, "total_tokens": 401600} {"current_steps": 1905, "total_steps": 181800, "loss": 3.1994, "lr": 5.236523652365237e-06, "epoch": 0.20957095709570958, "percentage": 1.05, "elapsed_time": "0:04:21", "remaining_time": "6:52:18", "throughput": 1537.05, "total_tokens": 402656} {"current_steps": 1910, "total_steps": 181800, "loss": 3.2617, "lr": 5.25027502750275e-06, "epoch": 0.21012101210121012, "percentage": 1.05, "elapsed_time": "0:04:22", "remaining_time": "6:52:16", "throughput": 1536.84, "total_tokens": 403648} {"current_steps": 1915, "total_steps": 181800, "loss": 3.1986, "lr": 5.264026402640264e-06, "epoch": 0.21067106710671066, "percentage": 1.05, "elapsed_time": "0:04:23", "remaining_time": "6:52:15", "throughput": 1536.77, "total_tokens": 404672} {"current_steps": 1920, "total_steps": 181800, "loss": 3.1861, "lr": 5.277777777777778e-06, "epoch": 0.21122112211221122, "percentage": 1.06, "elapsed_time": "0:04:24", "remaining_time": "6:52:14", "throughput": 1536.56, "total_tokens": 405664} {"current_steps": 1925, "total_steps": 181800, "loss": 3.1647, "lr": 5.291529152915292e-06, "epoch": 0.21177117711771176, "percentage": 1.06, "elapsed_time": "0:04:24", "remaining_time": "6:52:13", "throughput": 1536.58, "total_tokens": 406720} {"current_steps": 1930, "total_steps": 181800, "loss": 3.245, "lr": 5.305280528052805e-06, "epoch": 0.21232123212321233, "percentage": 1.06, "elapsed_time": "0:04:25", "remaining_time": "6:52:11", "throughput": 1536.63, "total_tokens": 407776} {"current_steps": 1935, "total_steps": 181800, "loss": 3.2043, "lr": 5.3190319031903194e-06, "epoch": 0.21287128712871287, "percentage": 1.06, "elapsed_time": "0:04:26", "remaining_time": "6:52:10", "throughput": 1536.68, "total_tokens": 408832} {"current_steps": 1940, "total_steps": 181800, "loss": 3.1628, "lr": 5.332783278327834e-06, "epoch": 0.21342134213421343, "percentage": 1.07, "elapsed_time": "0:04:26", "remaining_time": "6:52:08", "throughput": 1536.73, "total_tokens": 409888} {"current_steps": 1945, "total_steps": 181800, "loss": 3.2212, "lr": 5.346534653465347e-06, "epoch": 0.21397139713971397, "percentage": 1.07, "elapsed_time": "0:04:27", "remaining_time": "6:52:07", "throughput": 1536.77, "total_tokens": 410944} {"current_steps": 1950, "total_steps": 181800, "loss": 3.1492, "lr": 5.360286028602861e-06, "epoch": 0.2145214521452145, "percentage": 1.07, "elapsed_time": "0:04:28", "remaining_time": "6:52:05", "throughput": 1537.17, "total_tokens": 412096} {"current_steps": 1955, "total_steps": 181800, "loss": 3.1062, "lr": 5.3740374037403745e-06, "epoch": 0.21507150715071507, "percentage": 1.08, "elapsed_time": "0:04:28", "remaining_time": "6:52:04", "throughput": 1537.3, "total_tokens": 413184} {"current_steps": 1960, "total_steps": 181800, "loss": 3.1718, "lr": 5.387788778877888e-06, "epoch": 0.2156215621562156, "percentage": 1.08, "elapsed_time": "0:04:29", "remaining_time": "6:52:03", "throughput": 1537.08, "total_tokens": 414176} {"current_steps": 1965, "total_steps": 181800, "loss": 3.1644, "lr": 5.401540154015402e-06, "epoch": 0.21617161716171618, "percentage": 1.08, "elapsed_time": "0:04:30", "remaining_time": "6:52:02", "throughput": 1536.98, "total_tokens": 415200} {"current_steps": 1970, "total_steps": 181800, "loss": 3.1487, "lr": 5.415291529152915e-06, "epoch": 0.21672167216721672, "percentage": 1.08, "elapsed_time": "0:04:30", "remaining_time": "6:52:01", "throughput": 1537.0, "total_tokens": 416256} {"current_steps": 1975, "total_steps": 181800, "loss": 3.0632, "lr": 5.42904290429043e-06, "epoch": 0.21727172717271728, "percentage": 1.09, "elapsed_time": "0:04:31", "remaining_time": "6:52:00", "throughput": 1536.9, "total_tokens": 417280} {"current_steps": 1980, "total_steps": 181800, "loss": 3.1184, "lr": 5.442794279427943e-06, "epoch": 0.21782178217821782, "percentage": 1.09, "elapsed_time": "0:04:32", "remaining_time": "6:51:59", "throughput": 1536.81, "total_tokens": 418304} {"current_steps": 1985, "total_steps": 181800, "loss": 3.0706, "lr": 5.456545654565457e-06, "epoch": 0.21837183718371836, "percentage": 1.09, "elapsed_time": "0:04:32", "remaining_time": "6:51:58", "throughput": 1537.21, "total_tokens": 419456} {"current_steps": 1990, "total_steps": 181800, "loss": 3.1104, "lr": 5.4702970297029705e-06, "epoch": 0.21892189218921893, "percentage": 1.09, "elapsed_time": "0:04:33", "remaining_time": "6:51:56", "throughput": 1537.49, "total_tokens": 420576} {"current_steps": 1995, "total_steps": 181800, "loss": 3.1684, "lr": 5.484048404840484e-06, "epoch": 0.21947194719471946, "percentage": 1.1, "elapsed_time": "0:04:34", "remaining_time": "6:51:55", "throughput": 1537.64, "total_tokens": 421664} {"current_steps": 2000, "total_steps": 181800, "loss": 3.139, "lr": 5.497799779977998e-06, "epoch": 0.22002200220022003, "percentage": 1.1, "elapsed_time": "0:04:34", "remaining_time": "6:51:54", "throughput": 1537.55, "total_tokens": 422688} {"current_steps": 2005, "total_steps": 181800, "loss": 2.959, "lr": 5.511551155115511e-06, "epoch": 0.22057205720572057, "percentage": 1.1, "elapsed_time": "0:04:35", "remaining_time": "6:51:53", "throughput": 1537.46, "total_tokens": 423712} {"current_steps": 2010, "total_steps": 181800, "loss": 2.9825, "lr": 5.525302530253026e-06, "epoch": 0.22112211221122113, "percentage": 1.11, "elapsed_time": "0:04:36", "remaining_time": "6:51:52", "throughput": 1537.61, "total_tokens": 424800} {"current_steps": 2015, "total_steps": 181800, "loss": 2.9748, "lr": 5.539053905390539e-06, "epoch": 0.22167216721672167, "percentage": 1.11, "elapsed_time": "0:04:36", "remaining_time": "6:51:50", "throughput": 1537.88, "total_tokens": 425920} {"current_steps": 2020, "total_steps": 181800, "loss": 3.0094, "lr": 5.552805280528053e-06, "epoch": 0.2222222222222222, "percentage": 1.11, "elapsed_time": "0:04:37", "remaining_time": "6:51:49", "throughput": 1538.15, "total_tokens": 427040} {"current_steps": 2025, "total_steps": 181800, "loss": 3.0871, "lr": 5.5665566556655665e-06, "epoch": 0.22277227722772278, "percentage": 1.11, "elapsed_time": "0:04:38", "remaining_time": "6:51:47", "throughput": 1538.3, "total_tokens": 428128} {"current_steps": 2030, "total_steps": 181800, "loss": 2.9765, "lr": 5.580308030803081e-06, "epoch": 0.22332233223322331, "percentage": 1.12, "elapsed_time": "0:04:38", "remaining_time": "6:51:46", "throughput": 1538.45, "total_tokens": 429216} {"current_steps": 2035, "total_steps": 181800, "loss": 3.0701, "lr": 5.594059405940594e-06, "epoch": 0.22387238723872388, "percentage": 1.12, "elapsed_time": "0:04:39", "remaining_time": "6:51:45", "throughput": 1538.71, "total_tokens": 430336} {"current_steps": 2040, "total_steps": 181800, "loss": 3.0517, "lr": 5.607810781078108e-06, "epoch": 0.22442244224422442, "percentage": 1.12, "elapsed_time": "0:04:40", "remaining_time": "6:51:44", "throughput": 1538.85, "total_tokens": 431424} {"current_steps": 2045, "total_steps": 181800, "loss": 3.0606, "lr": 5.6215621562156224e-06, "epoch": 0.22497249724972498, "percentage": 1.12, "elapsed_time": "0:04:41", "remaining_time": "6:51:42", "throughput": 1538.77, "total_tokens": 432448} {"current_steps": 2050, "total_steps": 181800, "loss": 3.0122, "lr": 5.635313531353136e-06, "epoch": 0.22552255225522552, "percentage": 1.13, "elapsed_time": "0:04:41", "remaining_time": "6:51:41", "throughput": 1538.79, "total_tokens": 433504} {"current_steps": 2055, "total_steps": 181800, "loss": 2.9753, "lr": 5.64906490649065e-06, "epoch": 0.22607260726072606, "percentage": 1.13, "elapsed_time": "0:04:42", "remaining_time": "6:51:40", "throughput": 1538.93, "total_tokens": 434592} {"current_steps": 2060, "total_steps": 181800, "loss": 3.0, "lr": 5.662816281628163e-06, "epoch": 0.22662266226622663, "percentage": 1.13, "elapsed_time": "0:04:43", "remaining_time": "6:51:39", "throughput": 1539.18, "total_tokens": 435712} {"current_steps": 2065, "total_steps": 181800, "loss": 2.9661, "lr": 5.676567656765677e-06, "epoch": 0.22717271727172716, "percentage": 1.14, "elapsed_time": "0:04:43", "remaining_time": "6:51:38", "throughput": 1539.32, "total_tokens": 436800} {"current_steps": 2070, "total_steps": 181800, "loss": 2.9543, "lr": 5.690319031903191e-06, "epoch": 0.22772277227722773, "percentage": 1.14, "elapsed_time": "0:04:44", "remaining_time": "6:51:37", "throughput": 1539.23, "total_tokens": 437824} {"current_steps": 2075, "total_steps": 181800, "loss": 2.968, "lr": 5.704070407040704e-06, "epoch": 0.22827282728272827, "percentage": 1.14, "elapsed_time": "0:04:45", "remaining_time": "6:51:36", "throughput": 1539.23, "total_tokens": 438880} {"current_steps": 2080, "total_steps": 181800, "loss": 2.9104, "lr": 5.7178217821782184e-06, "epoch": 0.22882288228822883, "percentage": 1.14, "elapsed_time": "0:04:45", "remaining_time": "6:51:35", "throughput": 1539.35, "total_tokens": 439968} {"current_steps": 2085, "total_steps": 181800, "loss": 2.9433, "lr": 5.731573157315732e-06, "epoch": 0.22937293729372937, "percentage": 1.15, "elapsed_time": "0:04:46", "remaining_time": "6:51:34", "throughput": 1539.27, "total_tokens": 440992} {"current_steps": 2090, "total_steps": 181800, "loss": 2.9571, "lr": 5.745324532453246e-06, "epoch": 0.2299229922992299, "percentage": 1.15, "elapsed_time": "0:04:47", "remaining_time": "6:51:33", "throughput": 1539.39, "total_tokens": 442080} {"current_steps": 2095, "total_steps": 181800, "loss": 2.9133, "lr": 5.759075907590759e-06, "epoch": 0.23047304730473048, "percentage": 1.15, "elapsed_time": "0:04:47", "remaining_time": "6:51:32", "throughput": 1539.41, "total_tokens": 443136} {"current_steps": 2100, "total_steps": 181800, "loss": 2.8893, "lr": 5.772827282728273e-06, "epoch": 0.23102310231023102, "percentage": 1.16, "elapsed_time": "0:04:48", "remaining_time": "6:51:31", "throughput": 1539.42, "total_tokens": 444192} {"current_steps": 2105, "total_steps": 181800, "loss": 2.8613, "lr": 5.786578657865787e-06, "epoch": 0.23157315731573158, "percentage": 1.16, "elapsed_time": "0:04:49", "remaining_time": "6:51:30", "throughput": 1539.33, "total_tokens": 445216} {"current_steps": 2110, "total_steps": 181800, "loss": 2.8623, "lr": 5.8003300330033e-06, "epoch": 0.23212321232123212, "percentage": 1.16, "elapsed_time": "0:04:49", "remaining_time": "6:51:28", "throughput": 1539.02, "total_tokens": 446176} {"current_steps": 2115, "total_steps": 181800, "loss": 2.8415, "lr": 5.814081408140814e-06, "epoch": 0.23267326732673269, "percentage": 1.16, "elapsed_time": "0:04:50", "remaining_time": "6:51:28", "throughput": 1539.25, "total_tokens": 447296} {"current_steps": 2120, "total_steps": 181800, "loss": 2.7846, "lr": 5.827832783278328e-06, "epoch": 0.23322332233223322, "percentage": 1.17, "elapsed_time": "0:04:51", "remaining_time": "6:51:26", "throughput": 1539.16, "total_tokens": 448320} {"current_steps": 2125, "total_steps": 181800, "loss": 2.8654, "lr": 5.841584158415842e-06, "epoch": 0.23377337733773376, "percentage": 1.17, "elapsed_time": "0:04:51", "remaining_time": "6:51:26", "throughput": 1539.17, "total_tokens": 449376} {"current_steps": 2130, "total_steps": 181800, "loss": 2.7838, "lr": 5.855335533553355e-06, "epoch": 0.23432343234323433, "percentage": 1.17, "elapsed_time": "0:04:52", "remaining_time": "6:51:24", "throughput": 1539.19, "total_tokens": 450432} {"current_steps": 2135, "total_steps": 181800, "loss": 2.8624, "lr": 5.8690869086908695e-06, "epoch": 0.23487348734873487, "percentage": 1.17, "elapsed_time": "0:04:53", "remaining_time": "6:51:23", "throughput": 1539.32, "total_tokens": 451520} {"current_steps": 2140, "total_steps": 181800, "loss": 2.839, "lr": 5.882838283828383e-06, "epoch": 0.23542354235423543, "percentage": 1.18, "elapsed_time": "0:04:54", "remaining_time": "6:51:22", "throughput": 1539.45, "total_tokens": 452608} {"current_steps": 2145, "total_steps": 181800, "loss": 2.7613, "lr": 5.896589658965897e-06, "epoch": 0.23597359735973597, "percentage": 1.18, "elapsed_time": "0:04:54", "remaining_time": "6:51:21", "throughput": 1539.26, "total_tokens": 453600} {"current_steps": 2150, "total_steps": 181800, "loss": 2.852, "lr": 5.910341034103411e-06, "epoch": 0.23652365236523654, "percentage": 1.18, "elapsed_time": "0:04:55", "remaining_time": "6:51:20", "throughput": 1539.3, "total_tokens": 454656} {"current_steps": 2155, "total_steps": 181800, "loss": 2.7968, "lr": 5.924092409240925e-06, "epoch": 0.23707370737073707, "percentage": 1.19, "elapsed_time": "0:04:56", "remaining_time": "6:51:19", "throughput": 1539.32, "total_tokens": 455712} {"current_steps": 2160, "total_steps": 181800, "loss": 2.7158, "lr": 5.937843784378439e-06, "epoch": 0.2376237623762376, "percentage": 1.19, "elapsed_time": "0:04:56", "remaining_time": "6:51:18", "throughput": 1539.34, "total_tokens": 456768} {"current_steps": 2165, "total_steps": 181800, "loss": 2.7288, "lr": 5.951595159515952e-06, "epoch": 0.23817381738173818, "percentage": 1.19, "elapsed_time": "0:04:57", "remaining_time": "6:51:16", "throughput": 1539.16, "total_tokens": 457760} {"current_steps": 2170, "total_steps": 181800, "loss": 2.7407, "lr": 5.9653465346534655e-06, "epoch": 0.23872387238723872, "percentage": 1.19, "elapsed_time": "0:04:58", "remaining_time": "6:51:20", "throughput": 1538.74, "total_tokens": 458784} {"current_steps": 2175, "total_steps": 181800, "loss": 2.687, "lr": 5.97909790979098e-06, "epoch": 0.23927392739273928, "percentage": 1.2, "elapsed_time": "0:04:58", "remaining_time": "6:51:19", "throughput": 1538.76, "total_tokens": 459840} {"current_steps": 2180, "total_steps": 181800, "loss": 2.6808, "lr": 5.992849284928493e-06, "epoch": 0.23982398239823982, "percentage": 1.2, "elapsed_time": "0:04:59", "remaining_time": "6:51:18", "throughput": 1538.79, "total_tokens": 460896} {"current_steps": 2185, "total_steps": 181800, "loss": 2.7467, "lr": 6.006600660066007e-06, "epoch": 0.2403740374037404, "percentage": 1.2, "elapsed_time": "0:05:00", "remaining_time": "6:51:17", "throughput": 1538.79, "total_tokens": 461952} {"current_steps": 2190, "total_steps": 181800, "loss": 2.6846, "lr": 6.020352035203521e-06, "epoch": 0.24092409240924093, "percentage": 1.2, "elapsed_time": "0:05:00", "remaining_time": "6:51:17", "throughput": 1538.9, "total_tokens": 463040} {"current_steps": 2195, "total_steps": 181800, "loss": 2.7228, "lr": 6.034103410341034e-06, "epoch": 0.24147414741474146, "percentage": 1.21, "elapsed_time": "0:05:01", "remaining_time": "6:51:16", "throughput": 1538.81, "total_tokens": 464064} {"current_steps": 2200, "total_steps": 181800, "loss": 2.5919, "lr": 6.047854785478548e-06, "epoch": 0.24202420242024203, "percentage": 1.21, "elapsed_time": "0:05:02", "remaining_time": "6:51:15", "throughput": 1539.04, "total_tokens": 465184} {"current_steps": 2205, "total_steps": 181800, "loss": 2.6287, "lr": 6.0616061606160615e-06, "epoch": 0.24257425742574257, "percentage": 1.21, "elapsed_time": "0:05:02", "remaining_time": "6:51:14", "throughput": 1539.05, "total_tokens": 466240} {"current_steps": 2210, "total_steps": 181800, "loss": 2.6169, "lr": 6.075357535753576e-06, "epoch": 0.24312431243124313, "percentage": 1.22, "elapsed_time": "0:05:03", "remaining_time": "6:51:13", "throughput": 1538.96, "total_tokens": 467264} {"current_steps": 2215, "total_steps": 181800, "loss": 2.6332, "lr": 6.089108910891089e-06, "epoch": 0.24367436743674367, "percentage": 1.22, "elapsed_time": "0:05:04", "remaining_time": "6:51:12", "throughput": 1538.98, "total_tokens": 468320} {"current_steps": 2220, "total_steps": 181800, "loss": 2.6706, "lr": 6.102860286028603e-06, "epoch": 0.24422442244224424, "percentage": 1.22, "elapsed_time": "0:05:04", "remaining_time": "6:51:10", "throughput": 1539.01, "total_tokens": 469376} {"current_steps": 2225, "total_steps": 181800, "loss": 2.6522, "lr": 6.1166116611661166e-06, "epoch": 0.24477447744774478, "percentage": 1.22, "elapsed_time": "0:05:05", "remaining_time": "6:51:10", "throughput": 1539.11, "total_tokens": 470464} {"current_steps": 2230, "total_steps": 181800, "loss": 2.6172, "lr": 6.13036303630363e-06, "epoch": 0.24532453245324531, "percentage": 1.23, "elapsed_time": "0:05:06", "remaining_time": "6:51:08", "throughput": 1539.25, "total_tokens": 471552} {"current_steps": 2235, "total_steps": 181800, "loss": 2.6658, "lr": 6.144114411441144e-06, "epoch": 0.24587458745874588, "percentage": 1.23, "elapsed_time": "0:05:07", "remaining_time": "6:51:07", "throughput": 1539.48, "total_tokens": 472672} {"current_steps": 2240, "total_steps": 181800, "loss": 2.6149, "lr": 6.157865786578658e-06, "epoch": 0.24642464246424642, "percentage": 1.23, "elapsed_time": "0:05:07", "remaining_time": "6:51:06", "throughput": 1539.29, "total_tokens": 473664} {"current_steps": 2245, "total_steps": 181800, "loss": 2.5302, "lr": 6.171617161716172e-06, "epoch": 0.24697469746974698, "percentage": 1.23, "elapsed_time": "0:05:08", "remaining_time": "6:51:05", "throughput": 1539.52, "total_tokens": 474784} {"current_steps": 2250, "total_steps": 181800, "loss": 2.5069, "lr": 6.185368536853686e-06, "epoch": 0.24752475247524752, "percentage": 1.24, "elapsed_time": "0:05:09", "remaining_time": "6:51:04", "throughput": 1539.43, "total_tokens": 475808} {"current_steps": 2255, "total_steps": 181800, "loss": 2.5469, "lr": 6.1991199119912e-06, "epoch": 0.2480748074807481, "percentage": 1.24, "elapsed_time": "0:05:09", "remaining_time": "6:51:03", "throughput": 1539.66, "total_tokens": 476928} {"current_steps": 2260, "total_steps": 181800, "loss": 2.5927, "lr": 6.212871287128713e-06, "epoch": 0.24862486248624863, "percentage": 1.24, "elapsed_time": "0:05:10", "remaining_time": "6:51:02", "throughput": 1539.66, "total_tokens": 477984} {"current_steps": 2265, "total_steps": 181800, "loss": 2.5135, "lr": 6.226622662266227e-06, "epoch": 0.24917491749174916, "percentage": 1.25, "elapsed_time": "0:05:11", "remaining_time": "6:51:01", "throughput": 1539.68, "total_tokens": 479040} {"current_steps": 2270, "total_steps": 181800, "loss": 2.4856, "lr": 6.240374037403741e-06, "epoch": 0.24972497249724973, "percentage": 1.25, "elapsed_time": "0:05:11", "remaining_time": "6:51:00", "throughput": 1539.91, "total_tokens": 480160} {"current_steps": 2275, "total_steps": 181800, "loss": 2.4731, "lr": 6.254125412541255e-06, "epoch": 0.25027502750275027, "percentage": 1.25, "elapsed_time": "0:05:12", "remaining_time": "6:50:59", "throughput": 1539.94, "total_tokens": 481216} {"current_steps": 2280, "total_steps": 181800, "loss": 2.4549, "lr": 6.2678767876787685e-06, "epoch": 0.2508250825082508, "percentage": 1.25, "elapsed_time": "0:05:13", "remaining_time": "6:50:58", "throughput": 1539.96, "total_tokens": 482272} {"current_steps": 2285, "total_steps": 181800, "loss": 2.4699, "lr": 6.281628162816282e-06, "epoch": 0.2513751375137514, "percentage": 1.26, "elapsed_time": "0:05:13", "remaining_time": "6:50:56", "throughput": 1540.0, "total_tokens": 483328} {"current_steps": 2290, "total_steps": 181800, "loss": 2.4472, "lr": 6.295379537953795e-06, "epoch": 0.25192519251925194, "percentage": 1.26, "elapsed_time": "0:05:14", "remaining_time": "6:50:55", "throughput": 1540.33, "total_tokens": 484480} {"current_steps": 2295, "total_steps": 181800, "loss": 2.4857, "lr": 6.30913091309131e-06, "epoch": 0.2524752475247525, "percentage": 1.26, "elapsed_time": "0:05:15", "remaining_time": "6:50:54", "throughput": 1540.55, "total_tokens": 485600} {"current_steps": 2300, "total_steps": 181800, "loss": 2.3885, "lr": 6.322882288228824e-06, "epoch": 0.253025302530253, "percentage": 1.27, "elapsed_time": "0:05:15", "remaining_time": "6:50:53", "throughput": 1540.45, "total_tokens": 486624} {"current_steps": 2305, "total_steps": 181800, "loss": 2.3375, "lr": 6.336633663366337e-06, "epoch": 0.25357535753575355, "percentage": 1.27, "elapsed_time": "0:05:16", "remaining_time": "6:50:52", "throughput": 1540.57, "total_tokens": 487712} {"current_steps": 2310, "total_steps": 181800, "loss": 2.3505, "lr": 6.35038503850385e-06, "epoch": 0.25412541254125415, "percentage": 1.27, "elapsed_time": "0:05:17", "remaining_time": "6:50:51", "throughput": 1540.57, "total_tokens": 488768} {"current_steps": 2315, "total_steps": 181800, "loss": 2.3711, "lr": 6.364136413641364e-06, "epoch": 0.2546754675467547, "percentage": 1.27, "elapsed_time": "0:05:17", "remaining_time": "6:50:50", "throughput": 1540.69, "total_tokens": 489856} {"current_steps": 2320, "total_steps": 181800, "loss": 2.3953, "lr": 6.377887788778879e-06, "epoch": 0.2552255225522552, "percentage": 1.28, "elapsed_time": "0:05:18", "remaining_time": "6:50:49", "throughput": 1540.51, "total_tokens": 490848} {"current_steps": 2325, "total_steps": 181800, "loss": 2.3881, "lr": 6.391639163916392e-06, "epoch": 0.25577557755775576, "percentage": 1.28, "elapsed_time": "0:05:19", "remaining_time": "6:50:48", "throughput": 1540.52, "total_tokens": 491904} {"current_steps": 2330, "total_steps": 181800, "loss": 2.3054, "lr": 6.405390539053905e-06, "epoch": 0.2563256325632563, "percentage": 1.28, "elapsed_time": "0:05:19", "remaining_time": "6:50:47", "throughput": 1540.84, "total_tokens": 493056} {"current_steps": 2335, "total_steps": 181800, "loss": 2.2839, "lr": 6.419141914191419e-06, "epoch": 0.2568756875687569, "percentage": 1.28, "elapsed_time": "0:05:20", "remaining_time": "6:50:46", "throughput": 1540.84, "total_tokens": 494112} {"current_steps": 2340, "total_steps": 181800, "loss": 2.2671, "lr": 6.432893289328933e-06, "epoch": 0.25742574257425743, "percentage": 1.29, "elapsed_time": "0:05:21", "remaining_time": "6:50:45", "throughput": 1540.86, "total_tokens": 495168} {"current_steps": 2345, "total_steps": 181800, "loss": 2.2827, "lr": 6.446644664466447e-06, "epoch": 0.25797579757975797, "percentage": 1.29, "elapsed_time": "0:05:22", "remaining_time": "6:50:44", "throughput": 1540.89, "total_tokens": 496224} {"current_steps": 2350, "total_steps": 181800, "loss": 2.2421, "lr": 6.4603960396039605e-06, "epoch": 0.2585258525852585, "percentage": 1.29, "elapsed_time": "0:05:22", "remaining_time": "6:50:43", "throughput": 1540.83, "total_tokens": 497248} {"current_steps": 2355, "total_steps": 181800, "loss": 2.229, "lr": 6.474147414741475e-06, "epoch": 0.2590759075907591, "percentage": 1.3, "elapsed_time": "0:05:23", "remaining_time": "6:50:41", "throughput": 1540.65, "total_tokens": 498240} {"current_steps": 2360, "total_steps": 181800, "loss": 2.2353, "lr": 6.487898789878988e-06, "epoch": 0.25962596259625964, "percentage": 1.3, "elapsed_time": "0:05:24", "remaining_time": "6:50:41", "throughput": 1540.66, "total_tokens": 499296} {"current_steps": 2365, "total_steps": 181800, "loss": 2.2008, "lr": 6.501650165016503e-06, "epoch": 0.2601760176017602, "percentage": 1.3, "elapsed_time": "0:05:24", "remaining_time": "6:50:40", "throughput": 1540.56, "total_tokens": 500320} {"current_steps": 2370, "total_steps": 181800, "loss": 2.0867, "lr": 6.515401540154016e-06, "epoch": 0.2607260726072607, "percentage": 1.3, "elapsed_time": "0:05:25", "remaining_time": "6:50:39", "throughput": 1540.57, "total_tokens": 501376} {"current_steps": 2375, "total_steps": 181800, "loss": 2.225, "lr": 6.52915291529153e-06, "epoch": 0.26127612761276126, "percentage": 1.31, "elapsed_time": "0:05:26", "remaining_time": "6:50:38", "throughput": 1540.48, "total_tokens": 502400} {"current_steps": 2380, "total_steps": 181800, "loss": 2.2374, "lr": 6.542904290429043e-06, "epoch": 0.26182618261826185, "percentage": 1.31, "elapsed_time": "0:05:26", "remaining_time": "6:50:37", "throughput": 1540.8, "total_tokens": 503552} {"current_steps": 2385, "total_steps": 181800, "loss": 2.196, "lr": 6.5566556655665565e-06, "epoch": 0.2623762376237624, "percentage": 1.31, "elapsed_time": "0:05:27", "remaining_time": "6:50:36", "throughput": 1540.92, "total_tokens": 504640} {"current_steps": 2390, "total_steps": 181800, "loss": 2.1668, "lr": 6.5704070407040715e-06, "epoch": 0.2629262926292629, "percentage": 1.31, "elapsed_time": "0:05:28", "remaining_time": "6:50:34", "throughput": 1540.95, "total_tokens": 505696} {"current_steps": 2395, "total_steps": 181800, "loss": 2.2206, "lr": 6.584158415841585e-06, "epoch": 0.26347634763476346, "percentage": 1.32, "elapsed_time": "0:05:28", "remaining_time": "6:50:33", "throughput": 1541.17, "total_tokens": 506816} {"current_steps": 2400, "total_steps": 181800, "loss": 2.1025, "lr": 6.597909790979098e-06, "epoch": 0.264026402640264, "percentage": 1.32, "elapsed_time": "0:05:29", "remaining_time": "6:50:32", "throughput": 1541.0, "total_tokens": 507808} {"current_steps": 2405, "total_steps": 181800, "loss": 2.1657, "lr": 6.6116611661166116e-06, "epoch": 0.2645764576457646, "percentage": 1.32, "elapsed_time": "0:05:30", "remaining_time": "6:50:31", "throughput": 1541.01, "total_tokens": 508864} {"current_steps": 2410, "total_steps": 181800, "loss": 2.0244, "lr": 6.625412541254125e-06, "epoch": 0.26512651265126513, "percentage": 1.33, "elapsed_time": "0:05:30", "remaining_time": "6:50:30", "throughput": 1541.11, "total_tokens": 509952} {"current_steps": 2415, "total_steps": 181800, "loss": 2.0603, "lr": 6.63916391639164e-06, "epoch": 0.26567656765676567, "percentage": 1.33, "elapsed_time": "0:05:31", "remaining_time": "6:50:44", "throughput": 1540.17, "total_tokens": 511008} {"current_steps": 2420, "total_steps": 181800, "loss": 1.989, "lr": 6.652915291529153e-06, "epoch": 0.2662266226622662, "percentage": 1.33, "elapsed_time": "0:05:32", "remaining_time": "6:50:43", "throughput": 1540.1, "total_tokens": 512032} {"current_steps": 2425, "total_steps": 181800, "loss": 2.0054, "lr": 6.666666666666667e-06, "epoch": 0.2667766776677668, "percentage": 1.33, "elapsed_time": "0:05:33", "remaining_time": "6:50:42", "throughput": 1540.12, "total_tokens": 513088} {"current_steps": 2430, "total_steps": 181800, "loss": 1.9166, "lr": 6.68041804180418e-06, "epoch": 0.26732673267326734, "percentage": 1.34, "elapsed_time": "0:05:33", "remaining_time": "6:50:41", "throughput": 1540.24, "total_tokens": 514176} {"current_steps": 2435, "total_steps": 181800, "loss": 1.9873, "lr": 6.694169416941694e-06, "epoch": 0.2678767876787679, "percentage": 1.34, "elapsed_time": "0:05:34", "remaining_time": "6:50:40", "throughput": 1540.17, "total_tokens": 515200} {"current_steps": 2440, "total_steps": 181800, "loss": 1.9823, "lr": 6.707920792079208e-06, "epoch": 0.2684268426842684, "percentage": 1.34, "elapsed_time": "0:05:35", "remaining_time": "6:50:39", "throughput": 1540.19, "total_tokens": 516256} {"current_steps": 2445, "total_steps": 181800, "loss": 1.8981, "lr": 6.721672167216722e-06, "epoch": 0.26897689768976896, "percentage": 1.34, "elapsed_time": "0:05:35", "remaining_time": "6:50:38", "throughput": 1540.21, "total_tokens": 517312} {"current_steps": 2450, "total_steps": 181800, "loss": 2.0438, "lr": 6.735423542354236e-06, "epoch": 0.26952695269526955, "percentage": 1.35, "elapsed_time": "0:05:36", "remaining_time": "6:50:37", "throughput": 1540.23, "total_tokens": 518368} {"current_steps": 2455, "total_steps": 181800, "loss": 1.91, "lr": 6.749174917491749e-06, "epoch": 0.2700770077007701, "percentage": 1.35, "elapsed_time": "0:05:37", "remaining_time": "6:50:35", "throughput": 1540.25, "total_tokens": 519424} {"current_steps": 2460, "total_steps": 181800, "loss": 1.8832, "lr": 6.7629262926292635e-06, "epoch": 0.2706270627062706, "percentage": 1.35, "elapsed_time": "0:05:37", "remaining_time": "6:50:34", "throughput": 1540.38, "total_tokens": 520512} {"current_steps": 2465, "total_steps": 181800, "loss": 1.8601, "lr": 6.776677667766778e-06, "epoch": 0.27117711771177117, "percentage": 1.36, "elapsed_time": "0:05:38", "remaining_time": "6:50:33", "throughput": 1540.22, "total_tokens": 521504} {"current_steps": 2470, "total_steps": 181800, "loss": 1.8649, "lr": 6.790429042904291e-06, "epoch": 0.2717271727172717, "percentage": 1.36, "elapsed_time": "0:05:39", "remaining_time": "6:50:32", "throughput": 1540.13, "total_tokens": 522528} {"current_steps": 2475, "total_steps": 181800, "loss": 1.9403, "lr": 6.804180418041804e-06, "epoch": 0.2722772277227723, "percentage": 1.36, "elapsed_time": "0:05:39", "remaining_time": "6:50:31", "throughput": 1540.22, "total_tokens": 523616} {"current_steps": 2480, "total_steps": 181800, "loss": 1.8821, "lr": 6.817931793179318e-06, "epoch": 0.27282728272827284, "percentage": 1.36, "elapsed_time": "0:05:40", "remaining_time": "6:50:30", "throughput": 1540.22, "total_tokens": 524672} {"current_steps": 2485, "total_steps": 181800, "loss": 1.796, "lr": 6.831683168316833e-06, "epoch": 0.2733773377337734, "percentage": 1.37, "elapsed_time": "0:05:41", "remaining_time": "6:50:30", "throughput": 1540.14, "total_tokens": 525696} {"current_steps": 2490, "total_steps": 181800, "loss": 1.7677, "lr": 6.845434543454346e-06, "epoch": 0.2739273927392739, "percentage": 1.37, "elapsed_time": "0:05:42", "remaining_time": "6:50:29", "throughput": 1540.24, "total_tokens": 526784} {"current_steps": 2495, "total_steps": 181800, "loss": 1.8677, "lr": 6.8591859185918595e-06, "epoch": 0.27447744774477445, "percentage": 1.37, "elapsed_time": "0:05:42", "remaining_time": "6:50:28", "throughput": 1540.07, "total_tokens": 527776} {"current_steps": 2500, "total_steps": 181800, "loss": 1.8275, "lr": 6.872937293729373e-06, "epoch": 0.27502750275027504, "percentage": 1.38, "elapsed_time": "0:05:43", "remaining_time": "6:50:27", "throughput": 1540.08, "total_tokens": 528832} {"current_steps": 2505, "total_steps": 181800, "loss": 1.7764, "lr": 6.886688668866886e-06, "epoch": 0.2755775577557756, "percentage": 1.38, "elapsed_time": "0:05:44", "remaining_time": "6:50:26", "throughput": 1540.18, "total_tokens": 529920} {"current_steps": 2510, "total_steps": 181800, "loss": 1.7844, "lr": 6.900440044004401e-06, "epoch": 0.2761276127612761, "percentage": 1.38, "elapsed_time": "0:05:44", "remaining_time": "6:50:25", "throughput": 1540.1, "total_tokens": 530944} {"current_steps": 2515, "total_steps": 181800, "loss": 1.6817, "lr": 6.9141914191419146e-06, "epoch": 0.27667766776677666, "percentage": 1.38, "elapsed_time": "0:05:45", "remaining_time": "6:50:24", "throughput": 1540.18, "total_tokens": 532032} {"current_steps": 2520, "total_steps": 181800, "loss": 1.7105, "lr": 6.927942794279428e-06, "epoch": 0.27722772277227725, "percentage": 1.39, "elapsed_time": "0:05:46", "remaining_time": "6:50:23", "throughput": 1540.28, "total_tokens": 533120} {"current_steps": 2525, "total_steps": 181800, "loss": 1.6749, "lr": 6.941694169416941e-06, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:05:46", "remaining_time": "6:50:23", "throughput": 1540.36, "total_tokens": 534208} {"current_steps": 2530, "total_steps": 181800, "loss": 1.7482, "lr": 6.955445544554456e-06, "epoch": 0.27832783278327833, "percentage": 1.39, "elapsed_time": "0:05:47", "remaining_time": "6:50:22", "throughput": 1540.28, "total_tokens": 535232} {"current_steps": 2535, "total_steps": 181800, "loss": 1.6794, "lr": 6.96919691969197e-06, "epoch": 0.27887788778877887, "percentage": 1.39, "elapsed_time": "0:05:48", "remaining_time": "6:50:21", "throughput": 1540.29, "total_tokens": 536288} {"current_steps": 2540, "total_steps": 181800, "loss": 1.7517, "lr": 6.982948294829483e-06, "epoch": 0.2794279427942794, "percentage": 1.4, "elapsed_time": "0:05:48", "remaining_time": "6:50:20", "throughput": 1540.39, "total_tokens": 537376} {"current_steps": 2545, "total_steps": 181800, "loss": 1.6997, "lr": 6.996699669966996e-06, "epoch": 0.27997799779978, "percentage": 1.4, "elapsed_time": "0:05:49", "remaining_time": "6:50:19", "throughput": 1540.4, "total_tokens": 538432} {"current_steps": 2550, "total_steps": 181800, "loss": 1.652, "lr": 7.0104510451045105e-06, "epoch": 0.28052805280528054, "percentage": 1.4, "elapsed_time": "0:05:50", "remaining_time": "6:50:18", "throughput": 1540.5, "total_tokens": 539520} {"current_steps": 2555, "total_steps": 181800, "loss": 1.629, "lr": 7.024202420242025e-06, "epoch": 0.2810781078107811, "percentage": 1.41, "elapsed_time": "0:05:50", "remaining_time": "6:50:17", "throughput": 1540.5, "total_tokens": 540576} {"current_steps": 2560, "total_steps": 181800, "loss": 1.5845, "lr": 7.037953795379539e-06, "epoch": 0.2816281628162816, "percentage": 1.41, "elapsed_time": "0:05:51", "remaining_time": "6:50:17", "throughput": 1540.51, "total_tokens": 541632} {"current_steps": 2565, "total_steps": 181800, "loss": 1.5555, "lr": 7.051705170517052e-06, "epoch": 0.28217821782178215, "percentage": 1.41, "elapsed_time": "0:05:52", "remaining_time": "6:50:16", "throughput": 1540.52, "total_tokens": 542688} {"current_steps": 2570, "total_steps": 181800, "loss": 1.6028, "lr": 7.065456545654566e-06, "epoch": 0.28272827282728275, "percentage": 1.41, "elapsed_time": "0:05:52", "remaining_time": "6:50:14", "throughput": 1540.55, "total_tokens": 543744} {"current_steps": 2575, "total_steps": 181800, "loss": 1.4914, "lr": 7.079207920792079e-06, "epoch": 0.2832783278327833, "percentage": 1.42, "elapsed_time": "0:05:53", "remaining_time": "6:50:13", "throughput": 1540.39, "total_tokens": 544736} {"current_steps": 2580, "total_steps": 181800, "loss": 1.5389, "lr": 7.092959295929594e-06, "epoch": 0.2838283828382838, "percentage": 1.42, "elapsed_time": "0:05:54", "remaining_time": "6:50:12", "throughput": 1540.51, "total_tokens": 545824} {"current_steps": 2585, "total_steps": 181800, "loss": 1.5166, "lr": 7.106710671067107e-06, "epoch": 0.28437843784378436, "percentage": 1.42, "elapsed_time": "0:05:54", "remaining_time": "6:50:11", "throughput": 1540.54, "total_tokens": 546880} {"current_steps": 2590, "total_steps": 181800, "loss": 1.5438, "lr": 7.120462046204621e-06, "epoch": 0.28492849284928495, "percentage": 1.42, "elapsed_time": "0:05:55", "remaining_time": "6:50:10", "throughput": 1540.75, "total_tokens": 548000} {"current_steps": 2595, "total_steps": 181800, "loss": 1.4628, "lr": 7.134213421342134e-06, "epoch": 0.2854785478547855, "percentage": 1.43, "elapsed_time": "0:05:56", "remaining_time": "6:50:09", "throughput": 1540.93, "total_tokens": 549120} {"current_steps": 2600, "total_steps": 181800, "loss": 1.4825, "lr": 7.147964796479649e-06, "epoch": 0.28602860286028603, "percentage": 1.43, "elapsed_time": "0:05:57", "remaining_time": "6:50:08", "throughput": 1541.03, "total_tokens": 550208} {"current_steps": 2605, "total_steps": 181800, "loss": 1.4593, "lr": 7.1617161716171625e-06, "epoch": 0.28657865786578657, "percentage": 1.43, "elapsed_time": "0:05:57", "remaining_time": "6:50:07", "throughput": 1541.05, "total_tokens": 551264} {"current_steps": 2610, "total_steps": 181800, "loss": 1.587, "lr": 7.175467546754676e-06, "epoch": 0.2871287128712871, "percentage": 1.44, "elapsed_time": "0:05:58", "remaining_time": "6:50:06", "throughput": 1541.06, "total_tokens": 552320} {"current_steps": 2615, "total_steps": 181800, "loss": 1.4495, "lr": 7.189218921892189e-06, "epoch": 0.2876787678767877, "percentage": 1.44, "elapsed_time": "0:05:59", "remaining_time": "6:50:05", "throughput": 1540.89, "total_tokens": 553312} {"current_steps": 2620, "total_steps": 181800, "loss": 1.5797, "lr": 7.2029702970297025e-06, "epoch": 0.28822882288228824, "percentage": 1.44, "elapsed_time": "0:05:59", "remaining_time": "6:50:04", "throughput": 1540.9, "total_tokens": 554368} {"current_steps": 2625, "total_steps": 181800, "loss": 1.412, "lr": 7.2167216721672176e-06, "epoch": 0.2887788778877888, "percentage": 1.44, "elapsed_time": "0:06:00", "remaining_time": "6:50:03", "throughput": 1540.81, "total_tokens": 555392} {"current_steps": 2630, "total_steps": 181800, "loss": 1.4025, "lr": 7.230473047304731e-06, "epoch": 0.2893289328932893, "percentage": 1.45, "elapsed_time": "0:06:01", "remaining_time": "6:50:02", "throughput": 1540.66, "total_tokens": 556384} {"current_steps": 2635, "total_steps": 181800, "loss": 1.2972, "lr": 7.244224422442244e-06, "epoch": 0.28987898789878985, "percentage": 1.45, "elapsed_time": "0:06:01", "remaining_time": "6:50:01", "throughput": 1540.78, "total_tokens": 557472} {"current_steps": 2640, "total_steps": 181800, "loss": 1.372, "lr": 7.257975797579758e-06, "epoch": 0.29042904290429045, "percentage": 1.45, "elapsed_time": "0:06:02", "remaining_time": "6:50:00", "throughput": 1540.8, "total_tokens": 558528} {"current_steps": 2645, "total_steps": 181800, "loss": 1.3402, "lr": 7.271727172717272e-06, "epoch": 0.290979097909791, "percentage": 1.45, "elapsed_time": "0:06:03", "remaining_time": "6:49:58", "throughput": 1540.65, "total_tokens": 559520} {"current_steps": 2650, "total_steps": 181800, "loss": 1.3813, "lr": 7.285478547854786e-06, "epoch": 0.2915291529152915, "percentage": 1.46, "elapsed_time": "0:06:03", "remaining_time": "6:49:57", "throughput": 1540.49, "total_tokens": 560512} {"current_steps": 2655, "total_steps": 181800, "loss": 1.3375, "lr": 7.299229922992299e-06, "epoch": 0.29207920792079206, "percentage": 1.46, "elapsed_time": "0:06:04", "remaining_time": "6:49:56", "throughput": 1540.51, "total_tokens": 561568} {"current_steps": 2660, "total_steps": 181800, "loss": 1.2308, "lr": 7.3129812981298136e-06, "epoch": 0.29262926292629265, "percentage": 1.46, "elapsed_time": "0:06:05", "remaining_time": "6:49:55", "throughput": 1540.28, "total_tokens": 562528} {"current_steps": 2665, "total_steps": 181800, "loss": 1.3154, "lr": 7.326732673267327e-06, "epoch": 0.2931793179317932, "percentage": 1.47, "elapsed_time": "0:06:05", "remaining_time": "6:49:54", "throughput": 1540.22, "total_tokens": 563552} {"current_steps": 2670, "total_steps": 181800, "loss": 1.2789, "lr": 7.340484048404841e-06, "epoch": 0.29372937293729373, "percentage": 1.47, "elapsed_time": "0:06:06", "remaining_time": "6:49:53", "throughput": 1540.15, "total_tokens": 564576} {"current_steps": 2675, "total_steps": 181800, "loss": 1.2558, "lr": 7.354235423542355e-06, "epoch": 0.29427942794279427, "percentage": 1.47, "elapsed_time": "0:06:07", "remaining_time": "6:49:52", "throughput": 1540.33, "total_tokens": 565696} {"current_steps": 2680, "total_steps": 181800, "loss": 1.2033, "lr": 7.367986798679869e-06, "epoch": 0.2948294829482948, "percentage": 1.47, "elapsed_time": "0:06:07", "remaining_time": "6:49:51", "throughput": 1540.18, "total_tokens": 566688} {"current_steps": 2685, "total_steps": 181800, "loss": 1.1678, "lr": 7.381738173817382e-06, "epoch": 0.2953795379537954, "percentage": 1.48, "elapsed_time": "0:06:08", "remaining_time": "6:49:50", "throughput": 1540.1, "total_tokens": 567712} {"current_steps": 2690, "total_steps": 181800, "loss": 1.1604, "lr": 7.395489548954895e-06, "epoch": 0.29592959295929594, "percentage": 1.48, "elapsed_time": "0:06:09", "remaining_time": "6:49:49", "throughput": 1540.38, "total_tokens": 568864} {"current_steps": 2695, "total_steps": 181800, "loss": 1.1496, "lr": 7.40924092409241e-06, "epoch": 0.2964796479647965, "percentage": 1.48, "elapsed_time": "0:06:09", "remaining_time": "6:49:48", "throughput": 1540.31, "total_tokens": 569888} {"current_steps": 2700, "total_steps": 181800, "loss": 1.2195, "lr": 7.422992299229924e-06, "epoch": 0.297029702970297, "percentage": 1.49, "elapsed_time": "0:06:10", "remaining_time": "6:49:47", "throughput": 1540.31, "total_tokens": 570944} {"current_steps": 2705, "total_steps": 181800, "loss": 1.1571, "lr": 7.436743674367437e-06, "epoch": 0.29757975797579755, "percentage": 1.49, "elapsed_time": "0:06:11", "remaining_time": "6:49:46", "throughput": 1540.33, "total_tokens": 572000} {"current_steps": 2710, "total_steps": 181800, "loss": 1.1751, "lr": 7.4504950495049504e-06, "epoch": 0.29812981298129815, "percentage": 1.49, "elapsed_time": "0:06:12", "remaining_time": "6:49:45", "throughput": 1540.17, "total_tokens": 572992} {"current_steps": 2715, "total_steps": 181800, "loss": 1.0753, "lr": 7.464246424642464e-06, "epoch": 0.2986798679867987, "percentage": 1.49, "elapsed_time": "0:06:12", "remaining_time": "6:49:44", "throughput": 1540.19, "total_tokens": 574048} {"current_steps": 2720, "total_steps": 181800, "loss": 1.108, "lr": 7.477997799779979e-06, "epoch": 0.2992299229922992, "percentage": 1.5, "elapsed_time": "0:06:13", "remaining_time": "6:49:43", "throughput": 1540.3, "total_tokens": 575136} {"current_steps": 2725, "total_steps": 181800, "loss": 1.0868, "lr": 7.491749174917492e-06, "epoch": 0.29977997799779976, "percentage": 1.5, "elapsed_time": "0:06:14", "remaining_time": "6:49:42", "throughput": 1540.24, "total_tokens": 576160} {"current_steps": 2730, "total_steps": 181800, "loss": 1.1336, "lr": 7.5055005500550055e-06, "epoch": 0.30033003300330036, "percentage": 1.5, "elapsed_time": "0:06:14", "remaining_time": "6:49:41", "throughput": 1540.17, "total_tokens": 577184} {"current_steps": 2735, "total_steps": 181800, "loss": 1.1232, "lr": 7.519251925192519e-06, "epoch": 0.3008800880088009, "percentage": 1.5, "elapsed_time": "0:06:15", "remaining_time": "6:49:40", "throughput": 1540.09, "total_tokens": 578208} {"current_steps": 2740, "total_steps": 181800, "loss": 1.0396, "lr": 7.533003300330034e-06, "epoch": 0.30143014301430143, "percentage": 1.51, "elapsed_time": "0:06:16", "remaining_time": "6:49:39", "throughput": 1540.19, "total_tokens": 579296} {"current_steps": 2745, "total_steps": 181800, "loss": 1.0207, "lr": 7.546754675467547e-06, "epoch": 0.30198019801980197, "percentage": 1.51, "elapsed_time": "0:06:16", "remaining_time": "6:49:38", "throughput": 1540.13, "total_tokens": 580320} {"current_steps": 2750, "total_steps": 181800, "loss": 1.0337, "lr": 7.560506050605061e-06, "epoch": 0.3025302530253025, "percentage": 1.51, "elapsed_time": "0:06:17", "remaining_time": "6:49:37", "throughput": 1540.07, "total_tokens": 581344} {"current_steps": 2755, "total_steps": 181800, "loss": 1.0657, "lr": 7.574257425742575e-06, "epoch": 0.3030803080308031, "percentage": 1.52, "elapsed_time": "0:06:18", "remaining_time": "6:49:36", "throughput": 1540.01, "total_tokens": 582368} {"current_steps": 2760, "total_steps": 181800, "loss": 0.9606, "lr": 7.588008800880088e-06, "epoch": 0.30363036303630364, "percentage": 1.52, "elapsed_time": "0:06:18", "remaining_time": "6:49:35", "throughput": 1540.03, "total_tokens": 583424} {"current_steps": 2765, "total_steps": 181800, "loss": 0.9683, "lr": 7.601760176017602e-06, "epoch": 0.3041804180418042, "percentage": 1.52, "elapsed_time": "0:06:19", "remaining_time": "6:49:34", "throughput": 1540.13, "total_tokens": 584512} {"current_steps": 2770, "total_steps": 181800, "loss": 0.9246, "lr": 7.6155115511551166e-06, "epoch": 0.3047304730473047, "percentage": 1.52, "elapsed_time": "0:06:20", "remaining_time": "6:49:33", "throughput": 1540.06, "total_tokens": 585536} {"current_steps": 2775, "total_steps": 181800, "loss": 0.9631, "lr": 7.62926292629263e-06, "epoch": 0.30528052805280526, "percentage": 1.53, "elapsed_time": "0:06:20", "remaining_time": "6:49:32", "throughput": 1540.16, "total_tokens": 586624} {"current_steps": 2780, "total_steps": 181800, "loss": 0.9781, "lr": 7.643014301430143e-06, "epoch": 0.30583058305830585, "percentage": 1.53, "elapsed_time": "0:06:21", "remaining_time": "6:49:31", "throughput": 1540.25, "total_tokens": 587712} {"current_steps": 2785, "total_steps": 181800, "loss": 0.9028, "lr": 7.656765676567657e-06, "epoch": 0.3063806380638064, "percentage": 1.53, "elapsed_time": "0:06:22", "remaining_time": "6:49:30", "throughput": 1540.18, "total_tokens": 588736} {"current_steps": 2790, "total_steps": 181800, "loss": 0.7857, "lr": 7.670517051705172e-06, "epoch": 0.3069306930693069, "percentage": 1.53, "elapsed_time": "0:06:22", "remaining_time": "6:49:29", "throughput": 1540.18, "total_tokens": 589792} {"current_steps": 2795, "total_steps": 181800, "loss": 0.9243, "lr": 7.684268426842685e-06, "epoch": 0.30748074807480746, "percentage": 1.54, "elapsed_time": "0:06:23", "remaining_time": "6:49:28", "throughput": 1540.36, "total_tokens": 590912} {"current_steps": 2800, "total_steps": 181800, "loss": 0.8511, "lr": 7.698019801980198e-06, "epoch": 0.30803080308030806, "percentage": 1.54, "elapsed_time": "0:06:24", "remaining_time": "6:49:27", "throughput": 1540.37, "total_tokens": 591968} {"current_steps": 2805, "total_steps": 181800, "loss": 0.8741, "lr": 7.711771177117712e-06, "epoch": 0.3085808580858086, "percentage": 1.54, "elapsed_time": "0:06:24", "remaining_time": "6:49:26", "throughput": 1540.4, "total_tokens": 593024} {"current_steps": 2810, "total_steps": 181800, "loss": 0.7625, "lr": 7.725522552255227e-06, "epoch": 0.30913091309130913, "percentage": 1.55, "elapsed_time": "0:06:25", "remaining_time": "6:49:25", "throughput": 1540.34, "total_tokens": 594048} {"current_steps": 2815, "total_steps": 181800, "loss": 0.8602, "lr": 7.73927392739274e-06, "epoch": 0.3096809680968097, "percentage": 1.55, "elapsed_time": "0:06:26", "remaining_time": "6:49:24", "throughput": 1540.27, "total_tokens": 595072} {"current_steps": 2820, "total_steps": 181800, "loss": 0.8144, "lr": 7.753025302530253e-06, "epoch": 0.3102310231023102, "percentage": 1.55, "elapsed_time": "0:06:27", "remaining_time": "6:49:23", "throughput": 1540.21, "total_tokens": 596096} {"current_steps": 2825, "total_steps": 181800, "loss": 0.8549, "lr": 7.766776677667767e-06, "epoch": 0.3107810781078108, "percentage": 1.55, "elapsed_time": "0:06:27", "remaining_time": "6:49:22", "throughput": 1540.32, "total_tokens": 597184} {"current_steps": 2830, "total_steps": 181800, "loss": 0.7722, "lr": 7.78052805280528e-06, "epoch": 0.31133113311331134, "percentage": 1.56, "elapsed_time": "0:06:28", "remaining_time": "6:49:21", "throughput": 1540.35, "total_tokens": 598240} {"current_steps": 2835, "total_steps": 181800, "loss": 0.7661, "lr": 7.794279427942795e-06, "epoch": 0.3118811881188119, "percentage": 1.56, "elapsed_time": "0:06:29", "remaining_time": "6:49:20", "throughput": 1540.46, "total_tokens": 599328} {"current_steps": 2840, "total_steps": 181800, "loss": 0.7026, "lr": 7.808030803080309e-06, "epoch": 0.3124312431243124, "percentage": 1.56, "elapsed_time": "0:06:29", "remaining_time": "6:49:19", "throughput": 1540.46, "total_tokens": 600384} {"current_steps": 2845, "total_steps": 181800, "loss": 0.7485, "lr": 7.821782178217822e-06, "epoch": 0.31298129812981296, "percentage": 1.56, "elapsed_time": "0:06:30", "remaining_time": "6:49:18", "throughput": 1540.53, "total_tokens": 601472} {"current_steps": 2850, "total_steps": 181800, "loss": 0.7902, "lr": 7.835533553355335e-06, "epoch": 0.31353135313531355, "percentage": 1.57, "elapsed_time": "0:06:31", "remaining_time": "6:49:17", "throughput": 1540.63, "total_tokens": 602560} {"current_steps": 2855, "total_steps": 181800, "loss": 0.6858, "lr": 7.849284928492849e-06, "epoch": 0.3140814081408141, "percentage": 1.57, "elapsed_time": "0:06:31", "remaining_time": "6:49:16", "throughput": 1540.57, "total_tokens": 603584} {"current_steps": 2860, "total_steps": 181800, "loss": 0.7011, "lr": 7.863036303630364e-06, "epoch": 0.3146314631463146, "percentage": 1.57, "elapsed_time": "0:06:32", "remaining_time": "6:49:15", "throughput": 1540.59, "total_tokens": 604640} {"current_steps": 2865, "total_steps": 181800, "loss": 0.6309, "lr": 7.876787678767877e-06, "epoch": 0.31518151815181517, "percentage": 1.58, "elapsed_time": "0:06:33", "remaining_time": "6:49:14", "throughput": 1540.76, "total_tokens": 605760} {"current_steps": 2870, "total_steps": 181800, "loss": 0.6317, "lr": 7.89053905390539e-06, "epoch": 0.31573157315731576, "percentage": 1.58, "elapsed_time": "0:06:33", "remaining_time": "6:49:13", "throughput": 1540.86, "total_tokens": 606848} {"current_steps": 2875, "total_steps": 181800, "loss": 0.6261, "lr": 7.904290429042904e-06, "epoch": 0.3162816281628163, "percentage": 1.58, "elapsed_time": "0:06:34", "remaining_time": "6:49:12", "throughput": 1540.89, "total_tokens": 607904} {"current_steps": 2880, "total_steps": 181800, "loss": 0.6798, "lr": 7.918041804180417e-06, "epoch": 0.31683168316831684, "percentage": 1.58, "elapsed_time": "0:06:35", "remaining_time": "6:49:11", "throughput": 1540.99, "total_tokens": 608992} {"current_steps": 2885, "total_steps": 181800, "loss": 0.6284, "lr": 7.931793179317932e-06, "epoch": 0.3173817381738174, "percentage": 1.59, "elapsed_time": "0:06:35", "remaining_time": "6:49:10", "throughput": 1540.92, "total_tokens": 610016} {"current_steps": 2890, "total_steps": 181800, "loss": 0.6523, "lr": 7.945544554455445e-06, "epoch": 0.3179317931793179, "percentage": 1.59, "elapsed_time": "0:06:36", "remaining_time": "6:49:09", "throughput": 1540.95, "total_tokens": 611072} {"current_steps": 2895, "total_steps": 181800, "loss": 0.6137, "lr": 7.959295929592959e-06, "epoch": 0.3184818481848185, "percentage": 1.59, "elapsed_time": "0:06:37", "remaining_time": "6:49:08", "throughput": 1541.04, "total_tokens": 612160} {"current_steps": 2900, "total_steps": 181800, "loss": 0.8761, "lr": 7.973047304730472e-06, "epoch": 0.31903190319031904, "percentage": 1.6, "elapsed_time": "0:06:37", "remaining_time": "6:49:07", "throughput": 1541.05, "total_tokens": 613216} {"current_steps": 2905, "total_steps": 181800, "loss": 0.6466, "lr": 7.986798679867987e-06, "epoch": 0.3195819581958196, "percentage": 1.6, "elapsed_time": "0:06:38", "remaining_time": "6:49:06", "throughput": 1541.14, "total_tokens": 614304} {"current_steps": 2910, "total_steps": 181800, "loss": 0.6578, "lr": 8.0005500550055e-06, "epoch": 0.3201320132013201, "percentage": 1.6, "elapsed_time": "0:06:39", "remaining_time": "6:49:05", "throughput": 1541.16, "total_tokens": 615360} {"current_steps": 2915, "total_steps": 181800, "loss": 0.555, "lr": 8.014301430143016e-06, "epoch": 0.32068206820682066, "percentage": 1.6, "elapsed_time": "0:06:39", "remaining_time": "6:49:04", "throughput": 1541.18, "total_tokens": 616416} {"current_steps": 2920, "total_steps": 181800, "loss": 0.6429, "lr": 8.028052805280529e-06, "epoch": 0.32123212321232125, "percentage": 1.61, "elapsed_time": "0:06:40", "remaining_time": "6:49:03", "throughput": 1541.2, "total_tokens": 617472} {"current_steps": 2925, "total_steps": 181800, "loss": 0.563, "lr": 8.041804180418042e-06, "epoch": 0.3217821782178218, "percentage": 1.61, "elapsed_time": "0:06:41", "remaining_time": "6:49:02", "throughput": 1541.22, "total_tokens": 618528} {"current_steps": 2930, "total_steps": 181800, "loss": 0.5662, "lr": 8.055555555555557e-06, "epoch": 0.32233223322332233, "percentage": 1.61, "elapsed_time": "0:06:42", "remaining_time": "6:49:01", "throughput": 1541.4, "total_tokens": 619648} {"current_steps": 2935, "total_steps": 181800, "loss": 0.6746, "lr": 8.06930693069307e-06, "epoch": 0.32288228822882287, "percentage": 1.61, "elapsed_time": "0:06:42", "remaining_time": "6:49:00", "throughput": 1541.42, "total_tokens": 620704} {"current_steps": 2940, "total_steps": 181800, "loss": 0.5746, "lr": 8.083058305830584e-06, "epoch": 0.3234323432343234, "percentage": 1.62, "elapsed_time": "0:06:43", "remaining_time": "6:48:59", "throughput": 1541.45, "total_tokens": 621760} {"current_steps": 2945, "total_steps": 181800, "loss": 0.4847, "lr": 8.096809680968097e-06, "epoch": 0.323982398239824, "percentage": 1.62, "elapsed_time": "0:06:44", "remaining_time": "6:48:58", "throughput": 1541.63, "total_tokens": 622880} {"current_steps": 2950, "total_steps": 181800, "loss": 0.578, "lr": 8.11056105610561e-06, "epoch": 0.32453245324532454, "percentage": 1.62, "elapsed_time": "0:06:44", "remaining_time": "6:48:57", "throughput": 1541.56, "total_tokens": 623904} {"current_steps": 2955, "total_steps": 181800, "loss": 0.4722, "lr": 8.124312431243126e-06, "epoch": 0.3250825082508251, "percentage": 1.63, "elapsed_time": "0:06:45", "remaining_time": "6:48:56", "throughput": 1541.79, "total_tokens": 625056} {"current_steps": 2960, "total_steps": 181800, "loss": 0.4901, "lr": 8.138063806380639e-06, "epoch": 0.3256325632563256, "percentage": 1.63, "elapsed_time": "0:06:46", "remaining_time": "6:48:55", "throughput": 1541.95, "total_tokens": 626176} {"current_steps": 2965, "total_steps": 181800, "loss": 0.437, "lr": 8.151815181518152e-06, "epoch": 0.3261826182618262, "percentage": 1.63, "elapsed_time": "0:06:46", "remaining_time": "6:48:54", "throughput": 1541.89, "total_tokens": 627200} {"current_steps": 2970, "total_steps": 181800, "loss": 0.4396, "lr": 8.165566556655666e-06, "epoch": 0.32673267326732675, "percentage": 1.63, "elapsed_time": "0:06:47", "remaining_time": "6:48:53", "throughput": 1541.9, "total_tokens": 628256} {"current_steps": 2975, "total_steps": 181800, "loss": 0.4583, "lr": 8.17931793179318e-06, "epoch": 0.3272827282728273, "percentage": 1.64, "elapsed_time": "0:06:48", "remaining_time": "6:48:52", "throughput": 1542.06, "total_tokens": 629376} {"current_steps": 2980, "total_steps": 181800, "loss": 0.4615, "lr": 8.193069306930694e-06, "epoch": 0.3278327832783278, "percentage": 1.64, "elapsed_time": "0:06:48", "remaining_time": "6:48:52", "throughput": 1542.06, "total_tokens": 630432} {"current_steps": 2985, "total_steps": 181800, "loss": 0.429, "lr": 8.206820682068208e-06, "epoch": 0.32838283828382836, "percentage": 1.64, "elapsed_time": "0:06:49", "remaining_time": "6:48:51", "throughput": 1542.14, "total_tokens": 631520} {"current_steps": 2990, "total_steps": 181800, "loss": 0.5213, "lr": 8.220572057205721e-06, "epoch": 0.32893289328932895, "percentage": 1.64, "elapsed_time": "0:06:50", "remaining_time": "6:48:50", "throughput": 1542.22, "total_tokens": 632608} {"current_steps": 2995, "total_steps": 181800, "loss": 0.4118, "lr": 8.234323432343234e-06, "epoch": 0.3294829482948295, "percentage": 1.65, "elapsed_time": "0:06:50", "remaining_time": "6:48:49", "throughput": 1542.22, "total_tokens": 633664} {"current_steps": 3000, "total_steps": 181800, "loss": 0.4487, "lr": 8.24807480748075e-06, "epoch": 0.33003300330033003, "percentage": 1.65, "elapsed_time": "0:06:51", "remaining_time": "6:48:48", "throughput": 1542.15, "total_tokens": 634688} {"current_steps": 3005, "total_steps": 181800, "loss": 0.3846, "lr": 8.261826182618263e-06, "epoch": 0.33058305830583057, "percentage": 1.65, "elapsed_time": "0:06:52", "remaining_time": "6:48:48", "throughput": 1542.16, "total_tokens": 635744} {"current_steps": 3010, "total_steps": 181800, "loss": 0.4454, "lr": 8.275577557755776e-06, "epoch": 0.3311331133113311, "percentage": 1.66, "elapsed_time": "0:06:52", "remaining_time": "6:48:47", "throughput": 1542.32, "total_tokens": 636864} {"current_steps": 3015, "total_steps": 181800, "loss": 0.4078, "lr": 8.28932893289329e-06, "epoch": 0.3316831683168317, "percentage": 1.66, "elapsed_time": "0:06:53", "remaining_time": "6:48:46", "throughput": 1542.24, "total_tokens": 637888} {"current_steps": 3020, "total_steps": 181800, "loss": 0.4164, "lr": 8.303080308030803e-06, "epoch": 0.33223322332233224, "percentage": 1.66, "elapsed_time": "0:06:54", "remaining_time": "6:48:45", "throughput": 1542.24, "total_tokens": 638944} {"current_steps": 3025, "total_steps": 181800, "loss": 0.3808, "lr": 8.316831683168318e-06, "epoch": 0.3327832783278328, "percentage": 1.66, "elapsed_time": "0:06:54", "remaining_time": "6:48:44", "throughput": 1542.25, "total_tokens": 640000} {"current_steps": 3030, "total_steps": 181800, "loss": 0.3876, "lr": 8.330583058305831e-06, "epoch": 0.3333333333333333, "percentage": 1.67, "elapsed_time": "0:06:55", "remaining_time": "6:48:43", "throughput": 1542.2, "total_tokens": 641024} {"current_steps": 3035, "total_steps": 181800, "loss": 0.3917, "lr": 8.344334433443344e-06, "epoch": 0.3338833883388339, "percentage": 1.67, "elapsed_time": "0:06:56", "remaining_time": "6:48:42", "throughput": 1542.22, "total_tokens": 642080} {"current_steps": 3040, "total_steps": 181800, "loss": 0.4059, "lr": 8.358085808580858e-06, "epoch": 0.33443344334433445, "percentage": 1.67, "elapsed_time": "0:06:57", "remaining_time": "6:48:41", "throughput": 1542.17, "total_tokens": 643104} {"current_steps": 3045, "total_steps": 181800, "loss": 0.3461, "lr": 8.371837183718373e-06, "epoch": 0.334983498349835, "percentage": 1.67, "elapsed_time": "0:06:57", "remaining_time": "6:48:40", "throughput": 1542.11, "total_tokens": 644128} {"current_steps": 3050, "total_steps": 181800, "loss": 0.3527, "lr": 8.385588558855886e-06, "epoch": 0.3355335533553355, "percentage": 1.68, "elapsed_time": "0:06:58", "remaining_time": "6:48:39", "throughput": 1542.21, "total_tokens": 645216} {"current_steps": 3055, "total_steps": 181800, "loss": 0.3504, "lr": 8.3993399339934e-06, "epoch": 0.33608360836083606, "percentage": 1.68, "elapsed_time": "0:06:59", "remaining_time": "6:48:38", "throughput": 1542.23, "total_tokens": 646272} {"current_steps": 3060, "total_steps": 181800, "loss": 0.3562, "lr": 8.413091309130913e-06, "epoch": 0.33663366336633666, "percentage": 1.68, "elapsed_time": "0:06:59", "remaining_time": "6:48:37", "throughput": 1542.38, "total_tokens": 647392} {"current_steps": 3065, "total_steps": 181800, "loss": 0.3597, "lr": 8.426842684268426e-06, "epoch": 0.3371837183718372, "percentage": 1.69, "elapsed_time": "0:07:00", "remaining_time": "6:48:36", "throughput": 1542.39, "total_tokens": 648448} {"current_steps": 3070, "total_steps": 181800, "loss": 0.3851, "lr": 8.440594059405941e-06, "epoch": 0.33773377337733773, "percentage": 1.69, "elapsed_time": "0:07:01", "remaining_time": "6:48:35", "throughput": 1542.31, "total_tokens": 649472} {"current_steps": 3075, "total_steps": 181800, "loss": 0.3497, "lr": 8.454345434543455e-06, "epoch": 0.33828382838283827, "percentage": 1.69, "elapsed_time": "0:07:01", "remaining_time": "6:48:34", "throughput": 1542.17, "total_tokens": 650464} {"current_steps": 3080, "total_steps": 181800, "loss": 0.3589, "lr": 8.468096809680968e-06, "epoch": 0.3388338833883388, "percentage": 1.69, "elapsed_time": "0:07:02", "remaining_time": "6:48:34", "throughput": 1542.18, "total_tokens": 651520} {"current_steps": 3085, "total_steps": 181800, "loss": 0.3994, "lr": 8.481848184818481e-06, "epoch": 0.3393839383938394, "percentage": 1.7, "elapsed_time": "0:07:03", "remaining_time": "6:48:33", "throughput": 1542.27, "total_tokens": 652608} {"current_steps": 3090, "total_steps": 181800, "loss": 0.2968, "lr": 8.495599559955995e-06, "epoch": 0.33993399339933994, "percentage": 1.7, "elapsed_time": "0:07:03", "remaining_time": "6:48:31", "throughput": 1542.15, "total_tokens": 653600} {"current_steps": 3095, "total_steps": 181800, "loss": 0.2758, "lr": 8.50935093509351e-06, "epoch": 0.3404840484048405, "percentage": 1.7, "elapsed_time": "0:07:04", "remaining_time": "6:48:30", "throughput": 1542.17, "total_tokens": 654656} {"current_steps": 3100, "total_steps": 181800, "loss": 0.3051, "lr": 8.523102310231023e-06, "epoch": 0.341034103410341, "percentage": 1.71, "elapsed_time": "0:07:05", "remaining_time": "6:48:29", "throughput": 1542.18, "total_tokens": 655712} {"current_steps": 3105, "total_steps": 181800, "loss": 0.3585, "lr": 8.536853685368536e-06, "epoch": 0.3415841584158416, "percentage": 1.71, "elapsed_time": "0:07:05", "remaining_time": "6:48:29", "throughput": 1542.1, "total_tokens": 656736} {"current_steps": 3110, "total_steps": 181800, "loss": 0.4152, "lr": 8.550605060506051e-06, "epoch": 0.34213421342134215, "percentage": 1.71, "elapsed_time": "0:07:06", "remaining_time": "6:48:28", "throughput": 1542.19, "total_tokens": 657824} {"current_steps": 3115, "total_steps": 181800, "loss": 0.3339, "lr": 8.564356435643565e-06, "epoch": 0.3426842684268427, "percentage": 1.71, "elapsed_time": "0:07:07", "remaining_time": "6:48:27", "throughput": 1542.35, "total_tokens": 658944} {"current_steps": 3120, "total_steps": 181800, "loss": 0.3278, "lr": 8.578107810781078e-06, "epoch": 0.3432343234323432, "percentage": 1.72, "elapsed_time": "0:07:07", "remaining_time": "6:48:26", "throughput": 1542.43, "total_tokens": 660032} {"current_steps": 3125, "total_steps": 181800, "loss": 0.3231, "lr": 8.591859185918593e-06, "epoch": 0.34378437843784376, "percentage": 1.72, "elapsed_time": "0:07:08", "remaining_time": "6:48:25", "throughput": 1542.44, "total_tokens": 661088} {"current_steps": 3130, "total_steps": 181800, "loss": 0.3111, "lr": 8.605610561056107e-06, "epoch": 0.34433443344334436, "percentage": 1.72, "elapsed_time": "0:07:09", "remaining_time": "6:48:24", "throughput": 1542.37, "total_tokens": 662112} {"current_steps": 3135, "total_steps": 181800, "loss": 0.3227, "lr": 8.61936193619362e-06, "epoch": 0.3448844884488449, "percentage": 1.72, "elapsed_time": "0:07:09", "remaining_time": "6:48:23", "throughput": 1542.16, "total_tokens": 663072} {"current_steps": 3140, "total_steps": 181800, "loss": 0.3327, "lr": 8.633113311331135e-06, "epoch": 0.34543454345434543, "percentage": 1.73, "elapsed_time": "0:07:10", "remaining_time": "6:48:22", "throughput": 1542.17, "total_tokens": 664128} {"current_steps": 3145, "total_steps": 181800, "loss": 0.3382, "lr": 8.646864686468648e-06, "epoch": 0.34598459845984597, "percentage": 1.73, "elapsed_time": "0:07:11", "remaining_time": "6:48:22", "throughput": 1542.17, "total_tokens": 665184} {"current_steps": 3150, "total_steps": 181800, "loss": 0.3481, "lr": 8.660616061606162e-06, "epoch": 0.3465346534653465, "percentage": 1.73, "elapsed_time": "0:07:12", "remaining_time": "6:48:21", "throughput": 1542.17, "total_tokens": 666240} {"current_steps": 3155, "total_steps": 181800, "loss": 0.2863, "lr": 8.674367436743675e-06, "epoch": 0.3470847084708471, "percentage": 1.74, "elapsed_time": "0:07:12", "remaining_time": "6:48:20", "throughput": 1542.02, "total_tokens": 667232} {"current_steps": 3160, "total_steps": 181800, "loss": 0.3084, "lr": 8.688118811881188e-06, "epoch": 0.34763476347634764, "percentage": 1.74, "elapsed_time": "0:07:13", "remaining_time": "6:48:19", "throughput": 1542.1, "total_tokens": 668320} {"current_steps": 3165, "total_steps": 181800, "loss": 0.3105, "lr": 8.701870187018703e-06, "epoch": 0.3481848184818482, "percentage": 1.74, "elapsed_time": "0:07:14", "remaining_time": "6:48:19", "throughput": 1542.03, "total_tokens": 669344} {"current_steps": 3170, "total_steps": 181800, "loss": 0.3099, "lr": 8.715621562156217e-06, "epoch": 0.3487348734873487, "percentage": 1.74, "elapsed_time": "0:07:14", "remaining_time": "6:48:18", "throughput": 1542.03, "total_tokens": 670400} {"current_steps": 3175, "total_steps": 181800, "loss": 0.2605, "lr": 8.72937293729373e-06, "epoch": 0.3492849284928493, "percentage": 1.75, "elapsed_time": "0:07:15", "remaining_time": "6:48:17", "throughput": 1542.09, "total_tokens": 671488} {"current_steps": 3180, "total_steps": 181800, "loss": 0.3088, "lr": 8.743124312431243e-06, "epoch": 0.34983498349834985, "percentage": 1.75, "elapsed_time": "0:07:16", "remaining_time": "6:48:16", "throughput": 1542.17, "total_tokens": 672576} {"current_steps": 3185, "total_steps": 181800, "loss": 0.3299, "lr": 8.756875687568758e-06, "epoch": 0.3503850385038504, "percentage": 1.75, "elapsed_time": "0:07:16", "remaining_time": "6:48:16", "throughput": 1542.32, "total_tokens": 673696} {"current_steps": 3190, "total_steps": 181800, "loss": 0.3005, "lr": 8.770627062706272e-06, "epoch": 0.3509350935093509, "percentage": 1.75, "elapsed_time": "0:07:17", "remaining_time": "6:48:15", "throughput": 1542.18, "total_tokens": 674688} {"current_steps": 3195, "total_steps": 181800, "loss": 0.3118, "lr": 8.784378437843785e-06, "epoch": 0.35148514851485146, "percentage": 1.76, "elapsed_time": "0:07:18", "remaining_time": "6:48:14", "throughput": 1542.19, "total_tokens": 675744} {"current_steps": 3200, "total_steps": 181800, "loss": 0.287, "lr": 8.798129812981298e-06, "epoch": 0.35203520352035206, "percentage": 1.76, "elapsed_time": "0:07:18", "remaining_time": "6:48:13", "throughput": 1542.2, "total_tokens": 676800} {"current_steps": 3205, "total_steps": 181800, "loss": 0.3063, "lr": 8.811881188118812e-06, "epoch": 0.3525852585258526, "percentage": 1.76, "elapsed_time": "0:07:19", "remaining_time": "6:48:12", "throughput": 1542.21, "total_tokens": 677856} {"current_steps": 3210, "total_steps": 181800, "loss": 0.2879, "lr": 8.825632563256327e-06, "epoch": 0.35313531353135313, "percentage": 1.77, "elapsed_time": "0:07:20", "remaining_time": "6:48:11", "throughput": 1542.22, "total_tokens": 678912} {"current_steps": 3215, "total_steps": 181800, "loss": 0.3203, "lr": 8.83938393839384e-06, "epoch": 0.3536853685368537, "percentage": 1.77, "elapsed_time": "0:07:20", "remaining_time": "6:48:10", "throughput": 1542.08, "total_tokens": 679904} {"current_steps": 3220, "total_steps": 181800, "loss": 0.238, "lr": 8.853135313531354e-06, "epoch": 0.3542354235423542, "percentage": 1.77, "elapsed_time": "0:07:21", "remaining_time": "6:48:09", "throughput": 1542.24, "total_tokens": 681024} {"current_steps": 3225, "total_steps": 181800, "loss": 0.2871, "lr": 8.866886688668867e-06, "epoch": 0.3547854785478548, "percentage": 1.77, "elapsed_time": "0:07:22", "remaining_time": "6:48:09", "throughput": 1542.24, "total_tokens": 682080} {"current_steps": 3230, "total_steps": 181800, "loss": 0.2781, "lr": 8.88063806380638e-06, "epoch": 0.35533553355335534, "percentage": 1.78, "elapsed_time": "0:07:22", "remaining_time": "6:48:08", "throughput": 1542.25, "total_tokens": 683136} {"current_steps": 3235, "total_steps": 181800, "loss": 0.2966, "lr": 8.894389438943895e-06, "epoch": 0.3558855885588559, "percentage": 1.78, "elapsed_time": "0:07:23", "remaining_time": "6:48:07", "throughput": 1542.39, "total_tokens": 684256} {"current_steps": 3240, "total_steps": 181800, "loss": 0.3019, "lr": 8.908140814081409e-06, "epoch": 0.3564356435643564, "percentage": 1.78, "elapsed_time": "0:07:24", "remaining_time": "6:48:06", "throughput": 1542.47, "total_tokens": 685344} {"current_steps": 3245, "total_steps": 181800, "loss": 0.3064, "lr": 8.921892189218922e-06, "epoch": 0.356985698569857, "percentage": 1.78, "elapsed_time": "0:07:24", "remaining_time": "6:48:05", "throughput": 1542.27, "total_tokens": 686304} {"current_steps": 3250, "total_steps": 181800, "loss": 0.2754, "lr": 8.935643564356435e-06, "epoch": 0.35753575357535755, "percentage": 1.79, "elapsed_time": "0:07:25", "remaining_time": "6:48:04", "throughput": 1542.22, "total_tokens": 687328} {"current_steps": 3255, "total_steps": 181800, "loss": 0.3464, "lr": 8.949394939493949e-06, "epoch": 0.3580858085808581, "percentage": 1.79, "elapsed_time": "0:07:26", "remaining_time": "6:48:03", "throughput": 1542.1, "total_tokens": 688320} {"current_steps": 3260, "total_steps": 181800, "loss": 0.2833, "lr": 8.963146314631464e-06, "epoch": 0.3586358635863586, "percentage": 1.79, "elapsed_time": "0:07:27", "remaining_time": "6:48:02", "throughput": 1542.11, "total_tokens": 689376} {"current_steps": 3265, "total_steps": 181800, "loss": 0.2739, "lr": 8.976897689768977e-06, "epoch": 0.35918591859185917, "percentage": 1.8, "elapsed_time": "0:07:27", "remaining_time": "6:48:01", "throughput": 1541.91, "total_tokens": 690336} {"current_steps": 3270, "total_steps": 181800, "loss": 0.3136, "lr": 8.99064906490649e-06, "epoch": 0.35973597359735976, "percentage": 1.8, "elapsed_time": "0:07:28", "remaining_time": "6:48:00", "throughput": 1542.07, "total_tokens": 691456} {"current_steps": 3275, "total_steps": 181800, "loss": 0.2613, "lr": 9.004400440044004e-06, "epoch": 0.3602860286028603, "percentage": 1.8, "elapsed_time": "0:07:29", "remaining_time": "6:47:59", "throughput": 1542.08, "total_tokens": 692512} {"current_steps": 3280, "total_steps": 181800, "loss": 0.2624, "lr": 9.018151815181519e-06, "epoch": 0.36083608360836084, "percentage": 1.8, "elapsed_time": "0:07:29", "remaining_time": "6:47:58", "throughput": 1542.03, "total_tokens": 693536} {"current_steps": 3285, "total_steps": 181800, "loss": 0.2534, "lr": 9.031903190319032e-06, "epoch": 0.3613861386138614, "percentage": 1.81, "elapsed_time": "0:07:30", "remaining_time": "6:47:58", "throughput": 1542.02, "total_tokens": 694592} {"current_steps": 3290, "total_steps": 181800, "loss": 0.2832, "lr": 9.045654565456546e-06, "epoch": 0.3619361936193619, "percentage": 1.81, "elapsed_time": "0:07:31", "remaining_time": "6:47:57", "throughput": 1542.03, "total_tokens": 695648} {"current_steps": 3295, "total_steps": 181800, "loss": 0.278, "lr": 9.059405940594059e-06, "epoch": 0.3624862486248625, "percentage": 1.81, "elapsed_time": "0:07:31", "remaining_time": "6:47:56", "throughput": 1542.18, "total_tokens": 696768} {"current_steps": 3300, "total_steps": 181800, "loss": 0.2616, "lr": 9.073157315731572e-06, "epoch": 0.36303630363036304, "percentage": 1.82, "elapsed_time": "0:07:32", "remaining_time": "6:47:55", "throughput": 1542.18, "total_tokens": 697824} {"current_steps": 3305, "total_steps": 181800, "loss": 0.2972, "lr": 9.086908690869087e-06, "epoch": 0.3635863586358636, "percentage": 1.82, "elapsed_time": "0:07:33", "remaining_time": "6:47:54", "throughput": 1542.26, "total_tokens": 698912} {"current_steps": 3310, "total_steps": 181800, "loss": 0.2441, "lr": 9.1006600660066e-06, "epoch": 0.3641364136413641, "percentage": 1.82, "elapsed_time": "0:07:33", "remaining_time": "6:47:53", "throughput": 1542.13, "total_tokens": 699904} {"current_steps": 3315, "total_steps": 181800, "loss": 0.2372, "lr": 9.114411441144114e-06, "epoch": 0.36468646864686466, "percentage": 1.82, "elapsed_time": "0:07:34", "remaining_time": "6:47:52", "throughput": 1542.08, "total_tokens": 700928} {"current_steps": 3320, "total_steps": 181800, "loss": 0.2682, "lr": 9.128162816281629e-06, "epoch": 0.36523652365236525, "percentage": 1.83, "elapsed_time": "0:07:35", "remaining_time": "6:47:51", "throughput": 1542.03, "total_tokens": 701952} {"current_steps": 3325, "total_steps": 181800, "loss": 0.2493, "lr": 9.141914191419142e-06, "epoch": 0.3657865786578658, "percentage": 1.83, "elapsed_time": "0:07:35", "remaining_time": "6:47:50", "throughput": 1541.98, "total_tokens": 702976} {"current_steps": 3330, "total_steps": 181800, "loss": 0.2437, "lr": 9.155665566556656e-06, "epoch": 0.36633663366336633, "percentage": 1.83, "elapsed_time": "0:07:36", "remaining_time": "6:47:49", "throughput": 1542.07, "total_tokens": 704064} {"current_steps": 3335, "total_steps": 181800, "loss": 0.2285, "lr": 9.16941694169417e-06, "epoch": 0.36688668866886687, "percentage": 1.83, "elapsed_time": "0:07:37", "remaining_time": "6:47:48", "throughput": 1542.16, "total_tokens": 705152} {"current_steps": 3340, "total_steps": 181800, "loss": 0.2799, "lr": 9.183168316831684e-06, "epoch": 0.36743674367436746, "percentage": 1.84, "elapsed_time": "0:07:37", "remaining_time": "6:47:47", "throughput": 1542.24, "total_tokens": 706240} {"current_steps": 3345, "total_steps": 181800, "loss": 0.2595, "lr": 9.196919691969197e-06, "epoch": 0.367986798679868, "percentage": 1.84, "elapsed_time": "0:07:38", "remaining_time": "6:47:48", "throughput": 1542.03, "total_tokens": 707232} {"current_steps": 3350, "total_steps": 181800, "loss": 0.2558, "lr": 9.210671067106713e-06, "epoch": 0.36853685368536854, "percentage": 1.84, "elapsed_time": "0:07:39", "remaining_time": "6:47:47", "throughput": 1542.19, "total_tokens": 708352} {"current_steps": 3355, "total_steps": 181800, "loss": 0.2555, "lr": 9.224422442244226e-06, "epoch": 0.3690869086908691, "percentage": 1.85, "elapsed_time": "0:07:39", "remaining_time": "6:47:45", "throughput": 1542.22, "total_tokens": 709408} {"current_steps": 3360, "total_steps": 181800, "loss": 0.2582, "lr": 9.23817381738174e-06, "epoch": 0.3696369636963696, "percentage": 1.85, "elapsed_time": "0:07:40", "remaining_time": "6:47:44", "throughput": 1542.3, "total_tokens": 710496} {"current_steps": 3365, "total_steps": 181800, "loss": 0.2983, "lr": 9.251925192519253e-06, "epoch": 0.3701870187018702, "percentage": 1.85, "elapsed_time": "0:07:41", "remaining_time": "6:47:43", "throughput": 1542.46, "total_tokens": 711616} {"current_steps": 3370, "total_steps": 181800, "loss": 0.2643, "lr": 9.265676567656766e-06, "epoch": 0.37073707370737075, "percentage": 1.85, "elapsed_time": "0:07:42", "remaining_time": "6:47:42", "throughput": 1542.49, "total_tokens": 712672} {"current_steps": 3375, "total_steps": 181800, "loss": 0.2558, "lr": 9.279427942794281e-06, "epoch": 0.3712871287128713, "percentage": 1.86, "elapsed_time": "0:07:42", "remaining_time": "6:47:41", "throughput": 1542.58, "total_tokens": 713760} {"current_steps": 3380, "total_steps": 181800, "loss": 0.2366, "lr": 9.293179317931794e-06, "epoch": 0.3718371837183718, "percentage": 1.86, "elapsed_time": "0:07:43", "remaining_time": "6:47:40", "throughput": 1542.81, "total_tokens": 714912} {"current_steps": 3385, "total_steps": 181800, "loss": 0.2606, "lr": 9.306930693069308e-06, "epoch": 0.37238723872387236, "percentage": 1.86, "elapsed_time": "0:07:44", "remaining_time": "6:47:39", "throughput": 1542.83, "total_tokens": 715968} {"current_steps": 3390, "total_steps": 181800, "loss": 0.2598, "lr": 9.320682068206821e-06, "epoch": 0.37293729372937295, "percentage": 1.86, "elapsed_time": "0:07:44", "remaining_time": "6:47:38", "throughput": 1542.84, "total_tokens": 717024} {"current_steps": 3395, "total_steps": 181800, "loss": 0.2566, "lr": 9.334433443344334e-06, "epoch": 0.3734873487348735, "percentage": 1.87, "elapsed_time": "0:07:45", "remaining_time": "6:47:37", "throughput": 1542.92, "total_tokens": 718112} {"current_steps": 3400, "total_steps": 181800, "loss": 0.2206, "lr": 9.34818481848185e-06, "epoch": 0.37403740374037403, "percentage": 1.87, "elapsed_time": "0:07:46", "remaining_time": "6:47:36", "throughput": 1543.07, "total_tokens": 719232} {"current_steps": 3405, "total_steps": 181800, "loss": 0.2264, "lr": 9.361936193619363e-06, "epoch": 0.37458745874587457, "percentage": 1.87, "elapsed_time": "0:07:46", "remaining_time": "6:47:35", "throughput": 1543.09, "total_tokens": 720288} {"current_steps": 3410, "total_steps": 181800, "loss": 0.2654, "lr": 9.375687568756876e-06, "epoch": 0.37513751375137516, "percentage": 1.88, "elapsed_time": "0:07:47", "remaining_time": "6:47:34", "throughput": 1543.04, "total_tokens": 721312} {"current_steps": 3415, "total_steps": 181800, "loss": 0.2792, "lr": 9.38943894389439e-06, "epoch": 0.3756875687568757, "percentage": 1.88, "elapsed_time": "0:07:48", "remaining_time": "6:47:33", "throughput": 1543.12, "total_tokens": 722400} {"current_steps": 3420, "total_steps": 181800, "loss": 0.2869, "lr": 9.403190319031905e-06, "epoch": 0.37623762376237624, "percentage": 1.88, "elapsed_time": "0:07:48", "remaining_time": "6:47:32", "throughput": 1543.01, "total_tokens": 723392} {"current_steps": 3425, "total_steps": 181800, "loss": 0.2778, "lr": 9.416941694169418e-06, "epoch": 0.3767876787678768, "percentage": 1.88, "elapsed_time": "0:07:49", "remaining_time": "6:47:31", "throughput": 1543.02, "total_tokens": 724448} {"current_steps": 3430, "total_steps": 181800, "loss": 0.3045, "lr": 9.430693069306931e-06, "epoch": 0.3773377337733773, "percentage": 1.89, "elapsed_time": "0:07:50", "remaining_time": "6:47:30", "throughput": 1542.9, "total_tokens": 725440} {"current_steps": 3435, "total_steps": 181800, "loss": 0.2424, "lr": 9.444444444444445e-06, "epoch": 0.3778877887788779, "percentage": 1.89, "elapsed_time": "0:07:50", "remaining_time": "6:47:29", "throughput": 1542.92, "total_tokens": 726496} {"current_steps": 3440, "total_steps": 181800, "loss": 0.2361, "lr": 9.458195819581958e-06, "epoch": 0.37843784378437845, "percentage": 1.89, "elapsed_time": "0:07:51", "remaining_time": "6:47:28", "throughput": 1542.8, "total_tokens": 727488} {"current_steps": 3445, "total_steps": 181800, "loss": 0.2561, "lr": 9.471947194719473e-06, "epoch": 0.378987898789879, "percentage": 1.89, "elapsed_time": "0:07:52", "remaining_time": "6:47:27", "throughput": 1542.82, "total_tokens": 728544} {"current_steps": 3450, "total_steps": 181800, "loss": 0.3059, "lr": 9.485698569856986e-06, "epoch": 0.3795379537953795, "percentage": 1.9, "elapsed_time": "0:07:52", "remaining_time": "6:47:26", "throughput": 1542.75, "total_tokens": 729568} {"current_steps": 3455, "total_steps": 181800, "loss": 0.2235, "lr": 9.4994499449945e-06, "epoch": 0.38008800880088006, "percentage": 1.9, "elapsed_time": "0:07:53", "remaining_time": "6:47:26", "throughput": 1542.56, "total_tokens": 730528} {"current_steps": 3460, "total_steps": 181800, "loss": 0.2373, "lr": 9.513201320132013e-06, "epoch": 0.38063806380638066, "percentage": 1.9, "elapsed_time": "0:07:54", "remaining_time": "6:47:25", "throughput": 1542.64, "total_tokens": 731616} {"current_steps": 3465, "total_steps": 181800, "loss": 0.3002, "lr": 9.526952695269526e-06, "epoch": 0.3811881188118812, "percentage": 1.91, "elapsed_time": "0:07:54", "remaining_time": "6:47:24", "throughput": 1542.92, "total_tokens": 732800} {"current_steps": 3470, "total_steps": 181800, "loss": 0.2555, "lr": 9.540704070407041e-06, "epoch": 0.38173817381738173, "percentage": 1.91, "elapsed_time": "0:07:55", "remaining_time": "6:47:23", "throughput": 1542.8, "total_tokens": 733792} {"current_steps": 3475, "total_steps": 181800, "loss": 0.2151, "lr": 9.554455445544555e-06, "epoch": 0.38228822882288227, "percentage": 1.91, "elapsed_time": "0:07:56", "remaining_time": "6:47:22", "throughput": 1542.69, "total_tokens": 734784} {"current_steps": 3480, "total_steps": 181800, "loss": 0.2492, "lr": 9.568206820682068e-06, "epoch": 0.38283828382838286, "percentage": 1.91, "elapsed_time": "0:07:56", "remaining_time": "6:47:21", "throughput": 1542.97, "total_tokens": 735968} {"current_steps": 3485, "total_steps": 181800, "loss": 0.3092, "lr": 9.581958195819581e-06, "epoch": 0.3833883388338834, "percentage": 1.92, "elapsed_time": "0:07:57", "remaining_time": "6:47:20", "throughput": 1542.78, "total_tokens": 736928} {"current_steps": 3490, "total_steps": 181800, "loss": 0.2751, "lr": 9.595709570957096e-06, "epoch": 0.38393839383938394, "percentage": 1.92, "elapsed_time": "0:07:58", "remaining_time": "6:47:19", "throughput": 1542.67, "total_tokens": 737920} {"current_steps": 3495, "total_steps": 181800, "loss": 0.2719, "lr": 9.60946094609461e-06, "epoch": 0.3844884488448845, "percentage": 1.92, "elapsed_time": "0:07:59", "remaining_time": "6:47:18", "throughput": 1542.75, "total_tokens": 739008} {"current_steps": 3500, "total_steps": 181800, "loss": 0.268, "lr": 9.623212321232123e-06, "epoch": 0.385038503850385, "percentage": 1.93, "elapsed_time": "0:07:59", "remaining_time": "6:47:17", "throughput": 1542.88, "total_tokens": 740128} {"current_steps": 3505, "total_steps": 181800, "loss": 0.2663, "lr": 9.636963696369637e-06, "epoch": 0.3855885588558856, "percentage": 1.93, "elapsed_time": "0:08:00", "remaining_time": "6:47:16", "throughput": 1543.02, "total_tokens": 741248} {"current_steps": 3510, "total_steps": 181800, "loss": 0.2475, "lr": 9.65071507150715e-06, "epoch": 0.38613861386138615, "percentage": 1.93, "elapsed_time": "0:08:01", "remaining_time": "6:47:15", "throughput": 1543.03, "total_tokens": 742304} {"current_steps": 3515, "total_steps": 181800, "loss": 0.2469, "lr": 9.664466446644665e-06, "epoch": 0.3866886688668867, "percentage": 1.93, "elapsed_time": "0:08:01", "remaining_time": "6:47:14", "throughput": 1542.91, "total_tokens": 743296} {"current_steps": 3520, "total_steps": 181800, "loss": 0.2194, "lr": 9.678217821782178e-06, "epoch": 0.3872387238723872, "percentage": 1.94, "elapsed_time": "0:08:02", "remaining_time": "6:47:13", "throughput": 1542.8, "total_tokens": 744288} {"current_steps": 3525, "total_steps": 181800, "loss": 0.2816, "lr": 9.691969196919692e-06, "epoch": 0.38778877887788776, "percentage": 1.94, "elapsed_time": "0:08:03", "remaining_time": "6:47:12", "throughput": 1542.88, "total_tokens": 745376} {"current_steps": 3530, "total_steps": 181800, "loss": 0.2383, "lr": 9.705720572057207e-06, "epoch": 0.38833883388338836, "percentage": 1.94, "elapsed_time": "0:08:03", "remaining_time": "6:47:11", "throughput": 1542.97, "total_tokens": 746464} {"current_steps": 3535, "total_steps": 181800, "loss": 0.2614, "lr": 9.71947194719472e-06, "epoch": 0.3888888888888889, "percentage": 1.94, "elapsed_time": "0:08:04", "remaining_time": "6:47:10", "throughput": 1542.99, "total_tokens": 747520} {"current_steps": 3540, "total_steps": 181800, "loss": 0.2176, "lr": 9.733223322332233e-06, "epoch": 0.38943894389438943, "percentage": 1.95, "elapsed_time": "0:08:05", "remaining_time": "6:47:09", "throughput": 1542.94, "total_tokens": 748544} {"current_steps": 3545, "total_steps": 181800, "loss": 0.2199, "lr": 9.746974697469748e-06, "epoch": 0.38998899889988997, "percentage": 1.95, "elapsed_time": "0:08:05", "remaining_time": "6:47:08", "throughput": 1542.96, "total_tokens": 749600} {"current_steps": 3550, "total_steps": 181800, "loss": 0.2181, "lr": 9.760726072607262e-06, "epoch": 0.39053905390539057, "percentage": 1.95, "elapsed_time": "0:08:06", "remaining_time": "6:47:07", "throughput": 1543.05, "total_tokens": 750688} {"current_steps": 3555, "total_steps": 181800, "loss": 0.2457, "lr": 9.774477447744775e-06, "epoch": 0.3910891089108911, "percentage": 1.96, "elapsed_time": "0:08:07", "remaining_time": "6:47:06", "throughput": 1543.0, "total_tokens": 751712} {"current_steps": 3560, "total_steps": 181800, "loss": 0.2148, "lr": 9.78822882288229e-06, "epoch": 0.39163916391639164, "percentage": 1.96, "elapsed_time": "0:08:07", "remaining_time": "6:47:05", "throughput": 1543.08, "total_tokens": 752800} {"current_steps": 3565, "total_steps": 181800, "loss": 0.2632, "lr": 9.801980198019804e-06, "epoch": 0.3921892189218922, "percentage": 1.96, "elapsed_time": "0:08:08", "remaining_time": "6:47:04", "throughput": 1543.08, "total_tokens": 753856} {"current_steps": 3570, "total_steps": 181800, "loss": 0.2203, "lr": 9.815731573157317e-06, "epoch": 0.3927392739273927, "percentage": 1.96, "elapsed_time": "0:08:09", "remaining_time": "6:47:04", "throughput": 1542.94, "total_tokens": 754848} {"current_steps": 3575, "total_steps": 181800, "loss": 0.2416, "lr": 9.82948294829483e-06, "epoch": 0.3932893289328933, "percentage": 1.97, "elapsed_time": "0:08:09", "remaining_time": "6:47:03", "throughput": 1542.88, "total_tokens": 755872} {"current_steps": 3580, "total_steps": 181800, "loss": 0.2858, "lr": 9.843234323432344e-06, "epoch": 0.39383938393839385, "percentage": 1.97, "elapsed_time": "0:08:10", "remaining_time": "6:47:02", "throughput": 1542.81, "total_tokens": 756896} {"current_steps": 3585, "total_steps": 181800, "loss": 0.279, "lr": 9.856985698569859e-06, "epoch": 0.3943894389438944, "percentage": 1.97, "elapsed_time": "0:08:11", "remaining_time": "6:47:02", "throughput": 1542.94, "total_tokens": 758016} {"current_steps": 3590, "total_steps": 181800, "loss": 0.2435, "lr": 9.870737073707372e-06, "epoch": 0.3949394939493949, "percentage": 1.97, "elapsed_time": "0:08:11", "remaining_time": "6:47:01", "throughput": 1542.82, "total_tokens": 759008} {"current_steps": 3595, "total_steps": 181800, "loss": 0.2565, "lr": 9.884488448844885e-06, "epoch": 0.39548954895489546, "percentage": 1.98, "elapsed_time": "0:08:12", "remaining_time": "6:47:00", "throughput": 1542.76, "total_tokens": 760032} {"current_steps": 3600, "total_steps": 181800, "loss": 0.2333, "lr": 9.898239823982399e-06, "epoch": 0.39603960396039606, "percentage": 1.98, "elapsed_time": "0:08:13", "remaining_time": "6:46:59", "throughput": 1542.9, "total_tokens": 761152} {"current_steps": 3605, "total_steps": 181800, "loss": 0.2394, "lr": 9.911991199119912e-06, "epoch": 0.3965896589658966, "percentage": 1.98, "elapsed_time": "0:08:14", "remaining_time": "6:46:58", "throughput": 1542.79, "total_tokens": 762144} {"current_steps": 3610, "total_steps": 181800, "loss": 0.2184, "lr": 9.925742574257427e-06, "epoch": 0.39713971397139713, "percentage": 1.99, "elapsed_time": "0:08:14", "remaining_time": "6:46:57", "throughput": 1542.87, "total_tokens": 763232} {"current_steps": 3615, "total_steps": 181800, "loss": 0.2512, "lr": 9.93949394939494e-06, "epoch": 0.3976897689768977, "percentage": 1.99, "elapsed_time": "0:08:15", "remaining_time": "6:46:56", "throughput": 1542.8, "total_tokens": 764256} {"current_steps": 3620, "total_steps": 181800, "loss": 0.2473, "lr": 9.953245324532454e-06, "epoch": 0.39823982398239827, "percentage": 1.99, "elapsed_time": "0:08:16", "remaining_time": "6:46:56", "throughput": 1542.74, "total_tokens": 765280} {"current_steps": 3625, "total_steps": 181800, "loss": 0.2785, "lr": 9.966996699669967e-06, "epoch": 0.3987898789878988, "percentage": 1.99, "elapsed_time": "0:08:16", "remaining_time": "6:46:55", "throughput": 1542.81, "total_tokens": 766368} {"current_steps": 3630, "total_steps": 181800, "loss": 0.2432, "lr": 9.980748074807482e-06, "epoch": 0.39933993399339934, "percentage": 2.0, "elapsed_time": "0:08:17", "remaining_time": "6:46:54", "throughput": 1542.82, "total_tokens": 767424} {"current_steps": 3635, "total_steps": 181800, "loss": 0.3108, "lr": 9.994499449944995e-06, "epoch": 0.3998899889988999, "percentage": 2.0, "elapsed_time": "0:08:18", "remaining_time": "6:46:53", "throughput": 1542.95, "total_tokens": 768544} {"current_steps": 3640, "total_steps": 181800, "loss": 0.2457, "lr": 1.0008250825082509e-05, "epoch": 0.4004400440044004, "percentage": 2.0, "elapsed_time": "0:08:18", "remaining_time": "6:46:52", "throughput": 1543.03, "total_tokens": 769632} {"current_steps": 3645, "total_steps": 181800, "loss": 0.2309, "lr": 1.0022002200220022e-05, "epoch": 0.400990099009901, "percentage": 2.0, "elapsed_time": "0:08:19", "remaining_time": "6:46:52", "throughput": 1543.22, "total_tokens": 770784} {"current_steps": 3650, "total_steps": 181800, "loss": 0.2474, "lr": 1.0035753575357536e-05, "epoch": 0.40154015401540155, "percentage": 2.01, "elapsed_time": "0:08:20", "remaining_time": "6:46:51", "throughput": 1543.23, "total_tokens": 771840} {"current_steps": 3655, "total_steps": 181800, "loss": 0.2457, "lr": 1.004950495049505e-05, "epoch": 0.4020902090209021, "percentage": 2.01, "elapsed_time": "0:08:20", "remaining_time": "6:46:50", "throughput": 1543.31, "total_tokens": 772928} {"current_steps": 3660, "total_steps": 181800, "loss": 0.2548, "lr": 1.0063256325632564e-05, "epoch": 0.40264026402640263, "percentage": 2.01, "elapsed_time": "0:08:21", "remaining_time": "6:46:49", "throughput": 1543.44, "total_tokens": 774048} {"current_steps": 3665, "total_steps": 181800, "loss": 0.3075, "lr": 1.0077007700770077e-05, "epoch": 0.40319031903190317, "percentage": 2.02, "elapsed_time": "0:08:22", "remaining_time": "6:46:48", "throughput": 1543.45, "total_tokens": 775104} {"current_steps": 3670, "total_steps": 181800, "loss": 0.2344, "lr": 1.009075907590759e-05, "epoch": 0.40374037403740376, "percentage": 2.02, "elapsed_time": "0:08:22", "remaining_time": "6:46:47", "throughput": 1543.45, "total_tokens": 776160} {"current_steps": 3675, "total_steps": 181800, "loss": 0.2683, "lr": 1.0104510451045104e-05, "epoch": 0.4042904290429043, "percentage": 2.02, "elapsed_time": "0:08:23", "remaining_time": "6:46:47", "throughput": 1543.45, "total_tokens": 777216} {"current_steps": 3680, "total_steps": 181800, "loss": 0.3293, "lr": 1.0118261826182619e-05, "epoch": 0.40484048404840484, "percentage": 2.02, "elapsed_time": "0:08:24", "remaining_time": "6:46:46", "throughput": 1543.45, "total_tokens": 778272} {"current_steps": 3685, "total_steps": 181800, "loss": 0.2476, "lr": 1.0132013201320132e-05, "epoch": 0.4053905390539054, "percentage": 2.03, "elapsed_time": "0:08:24", "remaining_time": "6:46:45", "throughput": 1543.45, "total_tokens": 779328} {"current_steps": 3690, "total_steps": 181800, "loss": 0.2516, "lr": 1.0145764576457646e-05, "epoch": 0.40594059405940597, "percentage": 2.03, "elapsed_time": "0:08:25", "remaining_time": "6:46:44", "throughput": 1543.65, "total_tokens": 780480} {"current_steps": 3695, "total_steps": 181800, "loss": 0.2229, "lr": 1.0159515951595159e-05, "epoch": 0.4064906490649065, "percentage": 2.03, "elapsed_time": "0:08:26", "remaining_time": "6:46:44", "throughput": 1543.84, "total_tokens": 781632} {"current_steps": 3700, "total_steps": 181800, "loss": 0.2129, "lr": 1.0173267326732672e-05, "epoch": 0.40704070407040704, "percentage": 2.04, "elapsed_time": "0:08:26", "remaining_time": "6:46:43", "throughput": 1543.9, "total_tokens": 782720} {"current_steps": 3705, "total_steps": 181800, "loss": 0.2281, "lr": 1.0187018701870187e-05, "epoch": 0.4075907590759076, "percentage": 2.04, "elapsed_time": "0:08:27", "remaining_time": "6:46:42", "throughput": 1543.78, "total_tokens": 783712} {"current_steps": 3710, "total_steps": 181800, "loss": 0.2085, "lr": 1.02007700770077e-05, "epoch": 0.4081408140814081, "percentage": 2.04, "elapsed_time": "0:08:28", "remaining_time": "6:46:41", "throughput": 1543.79, "total_tokens": 784768} {"current_steps": 3715, "total_steps": 181800, "loss": 0.2457, "lr": 1.0214521452145214e-05, "epoch": 0.4086908690869087, "percentage": 2.04, "elapsed_time": "0:08:29", "remaining_time": "6:46:40", "throughput": 1543.93, "total_tokens": 785888} {"current_steps": 3720, "total_steps": 181800, "loss": 0.2548, "lr": 1.0228272827282728e-05, "epoch": 0.40924092409240925, "percentage": 2.05, "elapsed_time": "0:08:29", "remaining_time": "6:46:39", "throughput": 1543.93, "total_tokens": 786944} {"current_steps": 3725, "total_steps": 181800, "loss": 0.2006, "lr": 1.0242024202420243e-05, "epoch": 0.4097909790979098, "percentage": 2.05, "elapsed_time": "0:08:30", "remaining_time": "6:46:39", "throughput": 1544.06, "total_tokens": 788064} {"current_steps": 3730, "total_steps": 181800, "loss": 0.2259, "lr": 1.0255775577557756e-05, "epoch": 0.41034103410341033, "percentage": 2.05, "elapsed_time": "0:08:31", "remaining_time": "6:46:38", "throughput": 1544.0, "total_tokens": 789088} {"current_steps": 3735, "total_steps": 181800, "loss": 0.273, "lr": 1.026952695269527e-05, "epoch": 0.41089108910891087, "percentage": 2.05, "elapsed_time": "0:08:31", "remaining_time": "6:46:37", "throughput": 1544.01, "total_tokens": 790144} {"current_steps": 3740, "total_steps": 181800, "loss": 0.2234, "lr": 1.0283278327832784e-05, "epoch": 0.41144114411441146, "percentage": 2.06, "elapsed_time": "0:08:32", "remaining_time": "6:46:36", "throughput": 1543.89, "total_tokens": 791136} {"current_steps": 3745, "total_steps": 181800, "loss": 0.2679, "lr": 1.0297029702970298e-05, "epoch": 0.411991199119912, "percentage": 2.06, "elapsed_time": "0:08:33", "remaining_time": "6:46:35", "throughput": 1543.83, "total_tokens": 792160} {"current_steps": 3750, "total_steps": 181800, "loss": 0.2831, "lr": 1.0310781078107811e-05, "epoch": 0.41254125412541254, "percentage": 2.06, "elapsed_time": "0:08:33", "remaining_time": "6:46:35", "throughput": 1543.82, "total_tokens": 793216} {"current_steps": 3755, "total_steps": 181800, "loss": 0.2515, "lr": 1.0324532453245326e-05, "epoch": 0.4130913091309131, "percentage": 2.07, "elapsed_time": "0:08:34", "remaining_time": "6:46:34", "throughput": 1543.82, "total_tokens": 794272} {"current_steps": 3760, "total_steps": 181800, "loss": 0.2445, "lr": 1.033828382838284e-05, "epoch": 0.4136413641364136, "percentage": 2.07, "elapsed_time": "0:08:35", "remaining_time": "6:46:33", "throughput": 1543.82, "total_tokens": 795328} {"current_steps": 3765, "total_steps": 181800, "loss": 0.2439, "lr": 1.0352035203520353e-05, "epoch": 0.4141914191419142, "percentage": 2.07, "elapsed_time": "0:08:35", "remaining_time": "6:46:32", "throughput": 1543.77, "total_tokens": 796352} {"current_steps": 3770, "total_steps": 181800, "loss": 0.2324, "lr": 1.0365786578657866e-05, "epoch": 0.41474147414741475, "percentage": 2.07, "elapsed_time": "0:08:36", "remaining_time": "6:46:31", "throughput": 1543.72, "total_tokens": 797376} {"current_steps": 3775, "total_steps": 181800, "loss": 0.2032, "lr": 1.0379537953795381e-05, "epoch": 0.4152915291529153, "percentage": 2.08, "elapsed_time": "0:08:37", "remaining_time": "6:46:31", "throughput": 1543.73, "total_tokens": 798432} {"current_steps": 3780, "total_steps": 181800, "loss": 0.1799, "lr": 1.0393289328932894e-05, "epoch": 0.4158415841584158, "percentage": 2.08, "elapsed_time": "0:08:37", "remaining_time": "6:46:30", "throughput": 1543.87, "total_tokens": 799552} {"current_steps": 3785, "total_steps": 181800, "loss": 0.2504, "lr": 1.0407040704070408e-05, "epoch": 0.4163916391639164, "percentage": 2.08, "elapsed_time": "0:08:38", "remaining_time": "6:46:29", "throughput": 1543.81, "total_tokens": 800576} {"current_steps": 3790, "total_steps": 181800, "loss": 0.2381, "lr": 1.0420792079207921e-05, "epoch": 0.41694169416941695, "percentage": 2.08, "elapsed_time": "0:08:39", "remaining_time": "6:46:28", "throughput": 1543.88, "total_tokens": 801664} {"current_steps": 3795, "total_steps": 181800, "loss": 0.2609, "lr": 1.0434543454345436e-05, "epoch": 0.4174917491749175, "percentage": 2.09, "elapsed_time": "0:08:39", "remaining_time": "6:46:27", "throughput": 1543.71, "total_tokens": 802624} {"current_steps": 3800, "total_steps": 181800, "loss": 0.2648, "lr": 1.044829482948295e-05, "epoch": 0.41804180418041803, "percentage": 2.09, "elapsed_time": "0:08:40", "remaining_time": "6:46:26", "throughput": 1543.73, "total_tokens": 803680} {"current_steps": 3805, "total_steps": 181800, "loss": 0.202, "lr": 1.0462046204620463e-05, "epoch": 0.41859185918591857, "percentage": 2.09, "elapsed_time": "0:08:41", "remaining_time": "6:46:25", "throughput": 1543.8, "total_tokens": 804768} {"current_steps": 3810, "total_steps": 181800, "loss": 0.2314, "lr": 1.0475797579757976e-05, "epoch": 0.41914191419141916, "percentage": 2.1, "elapsed_time": "0:08:41", "remaining_time": "6:46:24", "throughput": 1543.68, "total_tokens": 805760} {"current_steps": 3815, "total_steps": 181800, "loss": 0.2481, "lr": 1.048954895489549e-05, "epoch": 0.4196919691969197, "percentage": 2.1, "elapsed_time": "0:08:42", "remaining_time": "6:46:23", "throughput": 1543.69, "total_tokens": 806816} {"current_steps": 3820, "total_steps": 181800, "loss": 0.2521, "lr": 1.0503300330033005e-05, "epoch": 0.42024202420242024, "percentage": 2.1, "elapsed_time": "0:08:43", "remaining_time": "6:46:22", "throughput": 1543.64, "total_tokens": 807840} {"current_steps": 3825, "total_steps": 181800, "loss": 0.2173, "lr": 1.0517051705170518e-05, "epoch": 0.4207920792079208, "percentage": 2.1, "elapsed_time": "0:08:44", "remaining_time": "6:46:22", "throughput": 1543.59, "total_tokens": 808864} {"current_steps": 3830, "total_steps": 181800, "loss": 0.2431, "lr": 1.0530803080308031e-05, "epoch": 0.4213421342134213, "percentage": 2.11, "elapsed_time": "0:08:44", "remaining_time": "6:46:21", "throughput": 1543.61, "total_tokens": 809920} {"current_steps": 3835, "total_steps": 181800, "loss": 0.2187, "lr": 1.0544554455445545e-05, "epoch": 0.4218921892189219, "percentage": 2.11, "elapsed_time": "0:08:45", "remaining_time": "6:46:20", "throughput": 1543.67, "total_tokens": 811008} {"current_steps": 3840, "total_steps": 181800, "loss": 0.2357, "lr": 1.0558305830583058e-05, "epoch": 0.42244224422442245, "percentage": 2.11, "elapsed_time": "0:08:46", "remaining_time": "6:46:19", "throughput": 1543.55, "total_tokens": 812000} {"current_steps": 3845, "total_steps": 181800, "loss": 0.2413, "lr": 1.0572057205720573e-05, "epoch": 0.422992299229923, "percentage": 2.11, "elapsed_time": "0:08:46", "remaining_time": "6:46:18", "throughput": 1543.61, "total_tokens": 813088} {"current_steps": 3850, "total_steps": 181800, "loss": 0.2116, "lr": 1.0585808580858086e-05, "epoch": 0.4235423542354235, "percentage": 2.12, "elapsed_time": "0:08:47", "remaining_time": "6:46:17", "throughput": 1543.5, "total_tokens": 814080} {"current_steps": 3855, "total_steps": 181800, "loss": 0.2363, "lr": 1.05995599559956e-05, "epoch": 0.4240924092409241, "percentage": 2.12, "elapsed_time": "0:08:48", "remaining_time": "6:46:17", "throughput": 1543.44, "total_tokens": 815104} {"current_steps": 3860, "total_steps": 181800, "loss": 0.2086, "lr": 1.0613311331133113e-05, "epoch": 0.42464246424642466, "percentage": 2.12, "elapsed_time": "0:08:48", "remaining_time": "6:46:16", "throughput": 1543.33, "total_tokens": 816096} {"current_steps": 3865, "total_steps": 181800, "loss": 0.2407, "lr": 1.0627062706270628e-05, "epoch": 0.4251925192519252, "percentage": 2.13, "elapsed_time": "0:08:49", "remaining_time": "6:46:15", "throughput": 1543.27, "total_tokens": 817120} {"current_steps": 3870, "total_steps": 181800, "loss": 0.24, "lr": 1.0640814081408142e-05, "epoch": 0.42574257425742573, "percentage": 2.13, "elapsed_time": "0:08:50", "remaining_time": "6:46:14", "throughput": 1543.28, "total_tokens": 818176} {"current_steps": 3875, "total_steps": 181800, "loss": 0.2316, "lr": 1.0654565456545655e-05, "epoch": 0.42629262926292627, "percentage": 2.13, "elapsed_time": "0:08:50", "remaining_time": "6:46:13", "throughput": 1543.17, "total_tokens": 819168} {"current_steps": 3880, "total_steps": 181800, "loss": 0.2362, "lr": 1.0668316831683168e-05, "epoch": 0.42684268426842686, "percentage": 2.13, "elapsed_time": "0:08:51", "remaining_time": "6:46:13", "throughput": 1543.24, "total_tokens": 820256} {"current_steps": 3885, "total_steps": 181800, "loss": 0.2349, "lr": 1.0682068206820682e-05, "epoch": 0.4273927392739274, "percentage": 2.14, "elapsed_time": "0:08:52", "remaining_time": "6:46:12", "throughput": 1543.26, "total_tokens": 821312} {"current_steps": 3890, "total_steps": 181800, "loss": 0.209, "lr": 1.0695819581958197e-05, "epoch": 0.42794279427942794, "percentage": 2.14, "elapsed_time": "0:08:52", "remaining_time": "6:46:11", "throughput": 1543.22, "total_tokens": 822336} {"current_steps": 3895, "total_steps": 181800, "loss": 0.2418, "lr": 1.070957095709571e-05, "epoch": 0.4284928492849285, "percentage": 2.14, "elapsed_time": "0:08:53", "remaining_time": "6:46:10", "throughput": 1543.16, "total_tokens": 823360} {"current_steps": 3900, "total_steps": 181800, "loss": 0.2313, "lr": 1.0723322332233223e-05, "epoch": 0.429042904290429, "percentage": 2.15, "elapsed_time": "0:08:54", "remaining_time": "6:46:09", "throughput": 1543.17, "total_tokens": 824416} {"current_steps": 3905, "total_steps": 181800, "loss": 0.3061, "lr": 1.0737073707370737e-05, "epoch": 0.4295929592959296, "percentage": 2.15, "elapsed_time": "0:08:54", "remaining_time": "6:46:08", "throughput": 1543.06, "total_tokens": 825408} {"current_steps": 3910, "total_steps": 181800, "loss": 0.187, "lr": 1.075082508250825e-05, "epoch": 0.43014301430143015, "percentage": 2.15, "elapsed_time": "0:08:55", "remaining_time": "6:46:07", "throughput": 1543.07, "total_tokens": 826464} {"current_steps": 3915, "total_steps": 181800, "loss": 0.2162, "lr": 1.0764576457645765e-05, "epoch": 0.4306930693069307, "percentage": 2.15, "elapsed_time": "0:08:56", "remaining_time": "6:46:06", "throughput": 1543.2, "total_tokens": 827584} {"current_steps": 3920, "total_steps": 181800, "loss": 0.2495, "lr": 1.0778327832783278e-05, "epoch": 0.4312431243124312, "percentage": 2.16, "elapsed_time": "0:08:56", "remaining_time": "6:46:05", "throughput": 1543.21, "total_tokens": 828640} {"current_steps": 3925, "total_steps": 181800, "loss": 0.2102, "lr": 1.0792079207920792e-05, "epoch": 0.4317931793179318, "percentage": 2.16, "elapsed_time": "0:08:57", "remaining_time": "6:46:04", "throughput": 1543.28, "total_tokens": 829728} {"current_steps": 3930, "total_steps": 181800, "loss": 0.2115, "lr": 1.0805830583058305e-05, "epoch": 0.43234323432343236, "percentage": 2.16, "elapsed_time": "0:08:58", "remaining_time": "6:46:04", "throughput": 1543.24, "total_tokens": 830752} {"current_steps": 3935, "total_steps": 181800, "loss": 0.2477, "lr": 1.081958195819582e-05, "epoch": 0.4328932893289329, "percentage": 2.16, "elapsed_time": "0:08:58", "remaining_time": "6:46:03", "throughput": 1543.25, "total_tokens": 831808} {"current_steps": 3940, "total_steps": 181800, "loss": 0.2068, "lr": 1.0833333333333334e-05, "epoch": 0.43344334433443343, "percentage": 2.17, "elapsed_time": "0:08:59", "remaining_time": "6:46:02", "throughput": 1543.38, "total_tokens": 832928} {"current_steps": 3945, "total_steps": 181800, "loss": 0.2205, "lr": 1.0847084708470847e-05, "epoch": 0.43399339933993397, "percentage": 2.17, "elapsed_time": "0:09:00", "remaining_time": "6:46:01", "throughput": 1543.38, "total_tokens": 833984} {"current_steps": 3950, "total_steps": 181800, "loss": 0.2831, "lr": 1.0860836083608362e-05, "epoch": 0.43454345434543457, "percentage": 2.17, "elapsed_time": "0:09:01", "remaining_time": "6:46:00", "throughput": 1543.34, "total_tokens": 835008} {"current_steps": 3955, "total_steps": 181800, "loss": 0.2293, "lr": 1.0874587458745875e-05, "epoch": 0.4350935093509351, "percentage": 2.18, "elapsed_time": "0:09:01", "remaining_time": "6:45:59", "throughput": 1543.29, "total_tokens": 836032} {"current_steps": 3960, "total_steps": 181800, "loss": 0.2203, "lr": 1.0888338833883389e-05, "epoch": 0.43564356435643564, "percentage": 2.18, "elapsed_time": "0:09:02", "remaining_time": "6:45:58", "throughput": 1543.24, "total_tokens": 837056} {"current_steps": 3965, "total_steps": 181800, "loss": 0.1866, "lr": 1.0902090209020904e-05, "epoch": 0.4361936193619362, "percentage": 2.18, "elapsed_time": "0:09:03", "remaining_time": "6:45:57", "throughput": 1543.25, "total_tokens": 838112} {"current_steps": 3970, "total_steps": 181800, "loss": 0.2025, "lr": 1.0915841584158417e-05, "epoch": 0.4367436743674367, "percentage": 2.18, "elapsed_time": "0:09:03", "remaining_time": "6:45:56", "throughput": 1543.14, "total_tokens": 839104} {"current_steps": 3975, "total_steps": 181800, "loss": 0.2611, "lr": 1.092959295929593e-05, "epoch": 0.4372937293729373, "percentage": 2.19, "elapsed_time": "0:09:04", "remaining_time": "6:45:56", "throughput": 1543.21, "total_tokens": 840192} {"current_steps": 3980, "total_steps": 181800, "loss": 0.2008, "lr": 1.0943344334433444e-05, "epoch": 0.43784378437843785, "percentage": 2.19, "elapsed_time": "0:09:05", "remaining_time": "6:45:55", "throughput": 1543.1, "total_tokens": 841184} {"current_steps": 3985, "total_steps": 181800, "loss": 0.2103, "lr": 1.0957095709570959e-05, "epoch": 0.4383938393839384, "percentage": 2.19, "elapsed_time": "0:09:05", "remaining_time": "6:45:54", "throughput": 1542.98, "total_tokens": 842176} {"current_steps": 3990, "total_steps": 181800, "loss": 0.2208, "lr": 1.0970847084708472e-05, "epoch": 0.4389438943894389, "percentage": 2.19, "elapsed_time": "0:09:06", "remaining_time": "6:45:53", "throughput": 1542.99, "total_tokens": 843232} {"current_steps": 3995, "total_steps": 181800, "loss": 0.2542, "lr": 1.0984598459845985e-05, "epoch": 0.4394939493949395, "percentage": 2.2, "elapsed_time": "0:09:07", "remaining_time": "6:45:53", "throughput": 1542.99, "total_tokens": 844288} {"current_steps": 4000, "total_steps": 181800, "loss": 0.2269, "lr": 1.0998349834983499e-05, "epoch": 0.44004400440044006, "percentage": 2.2, "elapsed_time": "0:09:07", "remaining_time": "6:45:52", "throughput": 1543.12, "total_tokens": 845408} {"current_steps": 4005, "total_steps": 181800, "loss": 0.2126, "lr": 1.1012101210121014e-05, "epoch": 0.4405940594059406, "percentage": 2.2, "elapsed_time": "0:09:08", "remaining_time": "6:45:51", "throughput": 1543.0, "total_tokens": 846400} {"current_steps": 4010, "total_steps": 181800, "loss": 0.2281, "lr": 1.1025852585258527e-05, "epoch": 0.44114411441144114, "percentage": 2.21, "elapsed_time": "0:09:09", "remaining_time": "6:45:50", "throughput": 1542.89, "total_tokens": 847392} {"current_steps": 4015, "total_steps": 181800, "loss": 0.2436, "lr": 1.103960396039604e-05, "epoch": 0.4416941694169417, "percentage": 2.21, "elapsed_time": "0:09:09", "remaining_time": "6:45:49", "throughput": 1542.9, "total_tokens": 848448} {"current_steps": 4020, "total_steps": 181800, "loss": 0.276, "lr": 1.1053355335533554e-05, "epoch": 0.44224422442244227, "percentage": 2.21, "elapsed_time": "0:09:10", "remaining_time": "6:45:49", "throughput": 1542.91, "total_tokens": 849504} {"current_steps": 4025, "total_steps": 181800, "loss": 0.1978, "lr": 1.1067106710671067e-05, "epoch": 0.4427942794279428, "percentage": 2.21, "elapsed_time": "0:09:11", "remaining_time": "6:45:48", "throughput": 1542.8, "total_tokens": 850496} {"current_steps": 4030, "total_steps": 181800, "loss": 0.2405, "lr": 1.1080858085808582e-05, "epoch": 0.44334433443344334, "percentage": 2.22, "elapsed_time": "0:09:11", "remaining_time": "6:45:47", "throughput": 1542.75, "total_tokens": 851520} {"current_steps": 4035, "total_steps": 181800, "loss": 0.2121, "lr": 1.1094609460946096e-05, "epoch": 0.4438943894389439, "percentage": 2.22, "elapsed_time": "0:09:12", "remaining_time": "6:45:46", "throughput": 1542.71, "total_tokens": 852544} {"current_steps": 4040, "total_steps": 181800, "loss": 0.2277, "lr": 1.1108360836083609e-05, "epoch": 0.4444444444444444, "percentage": 2.22, "elapsed_time": "0:09:13", "remaining_time": "6:45:45", "throughput": 1542.72, "total_tokens": 853600} {"current_steps": 4045, "total_steps": 181800, "loss": 0.1839, "lr": 1.1122112211221122e-05, "epoch": 0.444994499449945, "percentage": 2.22, "elapsed_time": "0:09:13", "remaining_time": "6:45:44", "throughput": 1542.72, "total_tokens": 854656} {"current_steps": 4050, "total_steps": 181800, "loss": 0.3542, "lr": 1.1135863586358636e-05, "epoch": 0.44554455445544555, "percentage": 2.23, "elapsed_time": "0:09:14", "remaining_time": "6:45:44", "throughput": 1542.73, "total_tokens": 855712} {"current_steps": 4055, "total_steps": 181800, "loss": 0.1862, "lr": 1.114961496149615e-05, "epoch": 0.4460946094609461, "percentage": 2.23, "elapsed_time": "0:09:15", "remaining_time": "6:45:43", "throughput": 1542.59, "total_tokens": 856704} {"current_steps": 4060, "total_steps": 181800, "loss": 0.2158, "lr": 1.1163366336633664e-05, "epoch": 0.44664466446644663, "percentage": 2.23, "elapsed_time": "0:09:16", "remaining_time": "6:45:42", "throughput": 1542.59, "total_tokens": 857760} {"current_steps": 4065, "total_steps": 181800, "loss": 0.2148, "lr": 1.1177117711771177e-05, "epoch": 0.4471947194719472, "percentage": 2.24, "elapsed_time": "0:09:16", "remaining_time": "6:45:42", "throughput": 1542.66, "total_tokens": 858848} {"current_steps": 4070, "total_steps": 181800, "loss": 0.2392, "lr": 1.119086908690869e-05, "epoch": 0.44774477447744776, "percentage": 2.24, "elapsed_time": "0:09:17", "remaining_time": "6:45:41", "throughput": 1542.61, "total_tokens": 859872} {"current_steps": 4075, "total_steps": 181800, "loss": 0.2771, "lr": 1.1204620462046204e-05, "epoch": 0.4482948294829483, "percentage": 2.24, "elapsed_time": "0:09:18", "remaining_time": "6:45:40", "throughput": 1542.55, "total_tokens": 860896} {"current_steps": 4080, "total_steps": 181800, "loss": 0.2145, "lr": 1.121837183718372e-05, "epoch": 0.44884488448844884, "percentage": 2.24, "elapsed_time": "0:09:18", "remaining_time": "6:45:39", "throughput": 1542.62, "total_tokens": 861984} {"current_steps": 4085, "total_steps": 181800, "loss": 0.2065, "lr": 1.1232123212321233e-05, "epoch": 0.4493949394939494, "percentage": 2.25, "elapsed_time": "0:09:19", "remaining_time": "6:45:39", "throughput": 1542.45, "total_tokens": 862944} {"current_steps": 4090, "total_steps": 181800, "loss": 0.2342, "lr": 1.1245874587458746e-05, "epoch": 0.44994499449944997, "percentage": 2.25, "elapsed_time": "0:09:20", "remaining_time": "6:45:38", "throughput": 1542.4, "total_tokens": 863968} {"current_steps": 4095, "total_steps": 181800, "loss": 0.2033, "lr": 1.125962596259626e-05, "epoch": 0.4504950495049505, "percentage": 2.25, "elapsed_time": "0:09:20", "remaining_time": "6:45:37", "throughput": 1542.57, "total_tokens": 865120} {"current_steps": 4100, "total_steps": 181800, "loss": 0.2179, "lr": 1.1273377337733774e-05, "epoch": 0.45104510451045104, "percentage": 2.26, "elapsed_time": "0:09:21", "remaining_time": "6:45:36", "throughput": 1542.46, "total_tokens": 866112} {"current_steps": 4105, "total_steps": 181800, "loss": 0.2468, "lr": 1.1287128712871288e-05, "epoch": 0.4515951595159516, "percentage": 2.26, "elapsed_time": "0:09:22", "remaining_time": "6:45:35", "throughput": 1542.41, "total_tokens": 867136} {"current_steps": 4110, "total_steps": 181800, "loss": 0.2422, "lr": 1.1300880088008801e-05, "epoch": 0.4521452145214521, "percentage": 2.26, "elapsed_time": "0:09:22", "remaining_time": "6:45:35", "throughput": 1542.36, "total_tokens": 868160} {"current_steps": 4115, "total_steps": 181800, "loss": 0.2071, "lr": 1.1314631463146314e-05, "epoch": 0.4526952695269527, "percentage": 2.26, "elapsed_time": "0:09:23", "remaining_time": "6:45:34", "throughput": 1542.49, "total_tokens": 869280} {"current_steps": 4120, "total_steps": 181800, "loss": 0.2336, "lr": 1.1328382838283828e-05, "epoch": 0.45324532453245325, "percentage": 2.27, "elapsed_time": "0:09:24", "remaining_time": "6:45:33", "throughput": 1542.55, "total_tokens": 870368} {"current_steps": 4125, "total_steps": 181800, "loss": 0.2135, "lr": 1.1342134213421343e-05, "epoch": 0.4537953795379538, "percentage": 2.27, "elapsed_time": "0:09:24", "remaining_time": "6:45:32", "throughput": 1542.44, "total_tokens": 871360} {"current_steps": 4130, "total_steps": 181800, "loss": 0.2163, "lr": 1.1355885588558856e-05, "epoch": 0.45434543454345433, "percentage": 2.27, "elapsed_time": "0:09:25", "remaining_time": "6:45:31", "throughput": 1542.51, "total_tokens": 872448} {"current_steps": 4135, "total_steps": 181800, "loss": 0.2369, "lr": 1.136963696369637e-05, "epoch": 0.45489548954895487, "percentage": 2.27, "elapsed_time": "0:09:26", "remaining_time": "6:45:31", "throughput": 1542.57, "total_tokens": 873536} {"current_steps": 4140, "total_steps": 181800, "loss": 0.1754, "lr": 1.1383388338833883e-05, "epoch": 0.45544554455445546, "percentage": 2.28, "elapsed_time": "0:09:26", "remaining_time": "6:45:30", "throughput": 1542.58, "total_tokens": 874592} {"current_steps": 4145, "total_steps": 181800, "loss": 0.2005, "lr": 1.1397139713971398e-05, "epoch": 0.455995599559956, "percentage": 2.28, "elapsed_time": "0:09:27", "remaining_time": "6:45:29", "throughput": 1542.47, "total_tokens": 875584} {"current_steps": 4150, "total_steps": 181800, "loss": 0.2407, "lr": 1.1410891089108911e-05, "epoch": 0.45654565456545654, "percentage": 2.28, "elapsed_time": "0:09:28", "remaining_time": "6:45:28", "throughput": 1542.47, "total_tokens": 876640} {"current_steps": 4155, "total_steps": 181800, "loss": 0.1975, "lr": 1.1424642464246424e-05, "epoch": 0.4570957095709571, "percentage": 2.29, "elapsed_time": "0:09:29", "remaining_time": "6:45:28", "throughput": 1542.53, "total_tokens": 877728} {"current_steps": 4160, "total_steps": 181800, "loss": 0.2219, "lr": 1.143839383938394e-05, "epoch": 0.45764576457645767, "percentage": 2.29, "elapsed_time": "0:09:29", "remaining_time": "6:45:27", "throughput": 1542.48, "total_tokens": 878752} {"current_steps": 4165, "total_steps": 181800, "loss": 0.1903, "lr": 1.1452145214521453e-05, "epoch": 0.4581958195819582, "percentage": 2.29, "elapsed_time": "0:09:30", "remaining_time": "6:45:26", "throughput": 1542.35, "total_tokens": 879744} {"current_steps": 4170, "total_steps": 181800, "loss": 0.2411, "lr": 1.1465896589658966e-05, "epoch": 0.45874587458745875, "percentage": 2.29, "elapsed_time": "0:09:31", "remaining_time": "6:45:26", "throughput": 1542.36, "total_tokens": 880800} {"current_steps": 4175, "total_steps": 181800, "loss": 0.2671, "lr": 1.1479647964796481e-05, "epoch": 0.4592959295929593, "percentage": 2.3, "elapsed_time": "0:09:31", "remaining_time": "6:45:25", "throughput": 1542.32, "total_tokens": 881824} {"current_steps": 4180, "total_steps": 181800, "loss": 0.2186, "lr": 1.1493399339933995e-05, "epoch": 0.4598459845984598, "percentage": 2.3, "elapsed_time": "0:09:32", "remaining_time": "6:45:24", "throughput": 1542.28, "total_tokens": 882848} {"current_steps": 4185, "total_steps": 181800, "loss": 0.1855, "lr": 1.1507150715071508e-05, "epoch": 0.4603960396039604, "percentage": 2.3, "elapsed_time": "0:09:33", "remaining_time": "6:45:23", "throughput": 1542.12, "total_tokens": 883808} {"current_steps": 4190, "total_steps": 181800, "loss": 0.2064, "lr": 1.1520902090209021e-05, "epoch": 0.46094609460946095, "percentage": 2.3, "elapsed_time": "0:09:33", "remaining_time": "6:45:22", "throughput": 1542.08, "total_tokens": 884832} {"current_steps": 4195, "total_steps": 181800, "loss": 0.2675, "lr": 1.1534653465346536e-05, "epoch": 0.4614961496149615, "percentage": 2.31, "elapsed_time": "0:09:34", "remaining_time": "6:45:21", "throughput": 1542.04, "total_tokens": 885856} {"current_steps": 4200, "total_steps": 181800, "loss": 0.215, "lr": 1.154840484048405e-05, "epoch": 0.46204620462046203, "percentage": 2.31, "elapsed_time": "0:09:35", "remaining_time": "6:45:20", "throughput": 1542.0, "total_tokens": 886880} {"current_steps": 4205, "total_steps": 181800, "loss": 0.235, "lr": 1.1562156215621563e-05, "epoch": 0.46259625962596257, "percentage": 2.31, "elapsed_time": "0:09:35", "remaining_time": "6:45:19", "throughput": 1542.0, "total_tokens": 887936} {"current_steps": 4210, "total_steps": 181800, "loss": 0.2039, "lr": 1.1575907590759076e-05, "epoch": 0.46314631463146316, "percentage": 2.32, "elapsed_time": "0:09:36", "remaining_time": "6:45:19", "throughput": 1542.0, "total_tokens": 888992} {"current_steps": 4215, "total_steps": 181800, "loss": 0.2165, "lr": 1.158965896589659e-05, "epoch": 0.4636963696369637, "percentage": 2.32, "elapsed_time": "0:09:37", "remaining_time": "6:45:18", "throughput": 1542.01, "total_tokens": 890048} {"current_steps": 4220, "total_steps": 181800, "loss": 0.2522, "lr": 1.1603410341034105e-05, "epoch": 0.46424642464246424, "percentage": 2.32, "elapsed_time": "0:09:37", "remaining_time": "6:45:17", "throughput": 1542.03, "total_tokens": 891104} {"current_steps": 4225, "total_steps": 181800, "loss": 0.2161, "lr": 1.1617161716171618e-05, "epoch": 0.4647964796479648, "percentage": 2.32, "elapsed_time": "0:09:38", "remaining_time": "6:45:16", "throughput": 1542.09, "total_tokens": 892192} {"current_steps": 4230, "total_steps": 181800, "loss": 0.1669, "lr": 1.1630913091309132e-05, "epoch": 0.46534653465346537, "percentage": 2.33, "elapsed_time": "0:09:39", "remaining_time": "6:45:15", "throughput": 1542.05, "total_tokens": 893216} {"current_steps": 4235, "total_steps": 181800, "loss": 0.2088, "lr": 1.1644664466446645e-05, "epoch": 0.4658965896589659, "percentage": 2.33, "elapsed_time": "0:09:39", "remaining_time": "6:45:14", "throughput": 1542.06, "total_tokens": 894272} {"current_steps": 4240, "total_steps": 181800, "loss": 0.2242, "lr": 1.165841584158416e-05, "epoch": 0.46644664466446645, "percentage": 2.33, "elapsed_time": "0:09:40", "remaining_time": "6:45:14", "throughput": 1542.13, "total_tokens": 895360} {"current_steps": 4245, "total_steps": 181800, "loss": 0.2163, "lr": 1.1672167216721673e-05, "epoch": 0.466996699669967, "percentage": 2.33, "elapsed_time": "0:09:41", "remaining_time": "6:45:13", "throughput": 1542.13, "total_tokens": 896416} {"current_steps": 4250, "total_steps": 181800, "loss": 0.1936, "lr": 1.1685918591859187e-05, "epoch": 0.4675467546754675, "percentage": 2.34, "elapsed_time": "0:09:41", "remaining_time": "6:45:12", "throughput": 1542.08, "total_tokens": 897440} {"current_steps": 4255, "total_steps": 181800, "loss": 0.2392, "lr": 1.16996699669967e-05, "epoch": 0.4680968096809681, "percentage": 2.34, "elapsed_time": "0:09:42", "remaining_time": "6:45:11", "throughput": 1542.15, "total_tokens": 898528} {"current_steps": 4260, "total_steps": 181800, "loss": 0.2466, "lr": 1.1713421342134213e-05, "epoch": 0.46864686468646866, "percentage": 2.34, "elapsed_time": "0:09:43", "remaining_time": "6:45:10", "throughput": 1542.11, "total_tokens": 899552} {"current_steps": 4265, "total_steps": 181800, "loss": 0.2901, "lr": 1.1727172717271728e-05, "epoch": 0.4691969196919692, "percentage": 2.35, "elapsed_time": "0:09:44", "remaining_time": "6:45:09", "throughput": 1542.01, "total_tokens": 900544} {"current_steps": 4270, "total_steps": 181800, "loss": 0.2134, "lr": 1.1740924092409242e-05, "epoch": 0.46974697469746973, "percentage": 2.35, "elapsed_time": "0:09:44", "remaining_time": "6:45:09", "throughput": 1542.06, "total_tokens": 901632} {"current_steps": 4275, "total_steps": 181800, "loss": 0.2207, "lr": 1.1754675467546755e-05, "epoch": 0.47029702970297027, "percentage": 2.35, "elapsed_time": "0:09:45", "remaining_time": "6:45:08", "throughput": 1542.06, "total_tokens": 902688} {"current_steps": 4280, "total_steps": 181800, "loss": 0.2599, "lr": 1.1768426842684268e-05, "epoch": 0.47084708470847086, "percentage": 2.35, "elapsed_time": "0:09:46", "remaining_time": "6:45:07", "throughput": 1542.06, "total_tokens": 903744} {"current_steps": 4285, "total_steps": 181800, "loss": 0.2212, "lr": 1.1782178217821782e-05, "epoch": 0.4713971397139714, "percentage": 2.36, "elapsed_time": "0:09:46", "remaining_time": "6:45:07", "throughput": 1542.07, "total_tokens": 904800} {"current_steps": 4290, "total_steps": 181800, "loss": 0.2426, "lr": 1.1795929592959297e-05, "epoch": 0.47194719471947194, "percentage": 2.36, "elapsed_time": "0:09:47", "remaining_time": "6:45:06", "throughput": 1542.03, "total_tokens": 905824} {"current_steps": 4295, "total_steps": 181800, "loss": 0.215, "lr": 1.180968096809681e-05, "epoch": 0.4724972497249725, "percentage": 2.36, "elapsed_time": "0:09:48", "remaining_time": "6:45:05", "throughput": 1541.99, "total_tokens": 906848} {"current_steps": 4300, "total_steps": 181800, "loss": 0.2093, "lr": 1.1823432343234323e-05, "epoch": 0.4730473047304731, "percentage": 2.37, "elapsed_time": "0:09:48", "remaining_time": "6:45:04", "throughput": 1542.0, "total_tokens": 907904} {"current_steps": 4305, "total_steps": 181800, "loss": 0.2748, "lr": 1.1837183718371837e-05, "epoch": 0.4735973597359736, "percentage": 2.37, "elapsed_time": "0:09:49", "remaining_time": "6:45:03", "throughput": 1542.12, "total_tokens": 909024} {"current_steps": 4310, "total_steps": 181800, "loss": 0.2302, "lr": 1.1850935093509352e-05, "epoch": 0.47414741474147415, "percentage": 2.37, "elapsed_time": "0:09:50", "remaining_time": "6:45:02", "throughput": 1542.29, "total_tokens": 910176} {"current_steps": 4315, "total_steps": 181800, "loss": 0.2406, "lr": 1.1864686468646865e-05, "epoch": 0.4746974697469747, "percentage": 2.37, "elapsed_time": "0:09:50", "remaining_time": "6:45:01", "throughput": 1542.41, "total_tokens": 911296} {"current_steps": 4320, "total_steps": 181800, "loss": 0.2514, "lr": 1.1878437843784379e-05, "epoch": 0.4752475247524752, "percentage": 2.38, "elapsed_time": "0:09:51", "remaining_time": "6:45:01", "throughput": 1542.42, "total_tokens": 912352} {"current_steps": 4325, "total_steps": 181800, "loss": 0.2239, "lr": 1.1892189218921892e-05, "epoch": 0.4757975797579758, "percentage": 2.38, "elapsed_time": "0:09:52", "remaining_time": "6:45:00", "throughput": 1542.42, "total_tokens": 913408} {"current_steps": 4330, "total_steps": 181800, "loss": 0.2466, "lr": 1.1905940594059405e-05, "epoch": 0.47634763476347636, "percentage": 2.38, "elapsed_time": "0:09:52", "remaining_time": "6:44:59", "throughput": 1542.42, "total_tokens": 914464} {"current_steps": 4335, "total_steps": 181800, "loss": 0.2207, "lr": 1.191969196919692e-05, "epoch": 0.4768976897689769, "percentage": 2.38, "elapsed_time": "0:09:53", "remaining_time": "6:44:59", "throughput": 1542.47, "total_tokens": 915552} {"current_steps": 4340, "total_steps": 181800, "loss": 0.2219, "lr": 1.1933443344334434e-05, "epoch": 0.47744774477447743, "percentage": 2.39, "elapsed_time": "0:09:54", "remaining_time": "6:44:58", "throughput": 1542.54, "total_tokens": 916640} {"current_steps": 4345, "total_steps": 181800, "loss": 0.2235, "lr": 1.1947194719471947e-05, "epoch": 0.47799779977997797, "percentage": 2.39, "elapsed_time": "0:09:54", "remaining_time": "6:44:57", "throughput": 1542.55, "total_tokens": 917696} {"current_steps": 4350, "total_steps": 181800, "loss": 0.1864, "lr": 1.196094609460946e-05, "epoch": 0.47854785478547857, "percentage": 2.39, "elapsed_time": "0:09:55", "remaining_time": "6:44:56", "throughput": 1542.61, "total_tokens": 918784} {"current_steps": 4355, "total_steps": 181800, "loss": 0.219, "lr": 1.1974697469746975e-05, "epoch": 0.4790979097909791, "percentage": 2.4, "elapsed_time": "0:09:56", "remaining_time": "6:44:55", "throughput": 1542.51, "total_tokens": 919776} {"current_steps": 4360, "total_steps": 181800, "loss": 0.2206, "lr": 1.1988448844884489e-05, "epoch": 0.47964796479647964, "percentage": 2.4, "elapsed_time": "0:09:56", "remaining_time": "6:44:54", "throughput": 1542.63, "total_tokens": 920896} {"current_steps": 4365, "total_steps": 181800, "loss": 0.1736, "lr": 1.2002200220022004e-05, "epoch": 0.4801980198019802, "percentage": 2.4, "elapsed_time": "0:09:57", "remaining_time": "6:44:53", "throughput": 1542.48, "total_tokens": 921856} {"current_steps": 4370, "total_steps": 181800, "loss": 0.2634, "lr": 1.2015951595159517e-05, "epoch": 0.4807480748074808, "percentage": 2.4, "elapsed_time": "0:09:58", "remaining_time": "6:44:53", "throughput": 1542.49, "total_tokens": 922912} {"current_steps": 4375, "total_steps": 181800, "loss": 0.2215, "lr": 1.202970297029703e-05, "epoch": 0.4812981298129813, "percentage": 2.41, "elapsed_time": "0:09:59", "remaining_time": "6:44:52", "throughput": 1542.5, "total_tokens": 923968} {"current_steps": 4380, "total_steps": 181800, "loss": 0.2437, "lr": 1.2043454345434546e-05, "epoch": 0.48184818481848185, "percentage": 2.41, "elapsed_time": "0:09:59", "remaining_time": "6:44:51", "throughput": 1542.49, "total_tokens": 925024} {"current_steps": 4385, "total_steps": 181800, "loss": 0.185, "lr": 1.2057205720572059e-05, "epoch": 0.4823982398239824, "percentage": 2.41, "elapsed_time": "0:10:00", "remaining_time": "6:44:51", "throughput": 1542.49, "total_tokens": 926080} {"current_steps": 4390, "total_steps": 181800, "loss": 0.2128, "lr": 1.2070957095709572e-05, "epoch": 0.4829482948294829, "percentage": 2.41, "elapsed_time": "0:10:01", "remaining_time": "6:44:50", "throughput": 1542.43, "total_tokens": 927104} {"current_steps": 4395, "total_steps": 181800, "loss": 0.2824, "lr": 1.2084708470847086e-05, "epoch": 0.4834983498349835, "percentage": 2.42, "elapsed_time": "0:10:01", "remaining_time": "6:44:49", "throughput": 1542.39, "total_tokens": 928128} {"current_steps": 4400, "total_steps": 181800, "loss": 0.2247, "lr": 1.2098459845984599e-05, "epoch": 0.48404840484048406, "percentage": 2.42, "elapsed_time": "0:10:02", "remaining_time": "6:44:48", "throughput": 1542.39, "total_tokens": 929184} {"current_steps": 4405, "total_steps": 181800, "loss": 0.2301, "lr": 1.2112211221122114e-05, "epoch": 0.4845984598459846, "percentage": 2.42, "elapsed_time": "0:10:03", "remaining_time": "6:44:48", "throughput": 1542.29, "total_tokens": 930176} {"current_steps": 4410, "total_steps": 181800, "loss": 0.2763, "lr": 1.2125962596259627e-05, "epoch": 0.48514851485148514, "percentage": 2.43, "elapsed_time": "0:10:03", "remaining_time": "6:44:47", "throughput": 1542.14, "total_tokens": 931136} {"current_steps": 4415, "total_steps": 181800, "loss": 0.2198, "lr": 1.213971397139714e-05, "epoch": 0.4856985698569857, "percentage": 2.43, "elapsed_time": "0:10:04", "remaining_time": "6:44:46", "throughput": 1542.04, "total_tokens": 932128} {"current_steps": 4420, "total_steps": 181800, "loss": 0.2191, "lr": 1.2153465346534654e-05, "epoch": 0.48624862486248627, "percentage": 2.43, "elapsed_time": "0:10:05", "remaining_time": "6:44:45", "throughput": 1542.04, "total_tokens": 933184} {"current_steps": 4425, "total_steps": 181800, "loss": 0.2204, "lr": 1.2167216721672167e-05, "epoch": 0.4867986798679868, "percentage": 2.43, "elapsed_time": "0:10:05", "remaining_time": "6:44:44", "throughput": 1542.05, "total_tokens": 934240} {"current_steps": 4430, "total_steps": 181800, "loss": 0.2738, "lr": 1.2180968096809682e-05, "epoch": 0.48734873487348734, "percentage": 2.44, "elapsed_time": "0:10:06", "remaining_time": "6:44:44", "throughput": 1542.12, "total_tokens": 935328} {"current_steps": 4435, "total_steps": 181800, "loss": 0.2015, "lr": 1.2194719471947196e-05, "epoch": 0.4878987898789879, "percentage": 2.44, "elapsed_time": "0:10:07", "remaining_time": "6:44:43", "throughput": 1542.13, "total_tokens": 936384} {"current_steps": 4440, "total_steps": 181800, "loss": 0.2654, "lr": 1.2208470847084709e-05, "epoch": 0.4884488448844885, "percentage": 2.44, "elapsed_time": "0:10:07", "remaining_time": "6:44:42", "throughput": 1542.09, "total_tokens": 937408} {"current_steps": 4445, "total_steps": 181800, "loss": 0.244, "lr": 1.2222222222222222e-05, "epoch": 0.488998899889989, "percentage": 2.44, "elapsed_time": "0:10:08", "remaining_time": "6:44:41", "throughput": 1542.06, "total_tokens": 938432} {"current_steps": 4450, "total_steps": 181800, "loss": 0.206, "lr": 1.2235973597359738e-05, "epoch": 0.48954895489548955, "percentage": 2.45, "elapsed_time": "0:10:09", "remaining_time": "6:44:40", "throughput": 1542.12, "total_tokens": 939520} {"current_steps": 4455, "total_steps": 181800, "loss": 0.1945, "lr": 1.2249724972497251e-05, "epoch": 0.4900990099009901, "percentage": 2.45, "elapsed_time": "0:10:09", "remaining_time": "6:44:39", "throughput": 1542.08, "total_tokens": 940544} {"current_steps": 4460, "total_steps": 181800, "loss": 0.1815, "lr": 1.2263476347634764e-05, "epoch": 0.49064906490649063, "percentage": 2.45, "elapsed_time": "0:10:10", "remaining_time": "6:44:38", "throughput": 1541.94, "total_tokens": 941504} {"current_steps": 4465, "total_steps": 181800, "loss": 0.211, "lr": 1.2277227722772278e-05, "epoch": 0.4911991199119912, "percentage": 2.46, "elapsed_time": "0:10:11", "remaining_time": "6:44:38", "throughput": 1541.94, "total_tokens": 942560} {"current_steps": 4470, "total_steps": 181800, "loss": 0.1854, "lr": 1.2290979097909791e-05, "epoch": 0.49174917491749176, "percentage": 2.46, "elapsed_time": "0:10:11", "remaining_time": "6:44:37", "throughput": 1542.06, "total_tokens": 943680} {"current_steps": 4475, "total_steps": 181800, "loss": 0.2478, "lr": 1.2304730473047306e-05, "epoch": 0.4922992299229923, "percentage": 2.46, "elapsed_time": "0:10:12", "remaining_time": "6:44:36", "throughput": 1542.11, "total_tokens": 944768} {"current_steps": 4480, "total_steps": 181800, "loss": 0.1839, "lr": 1.231848184818482e-05, "epoch": 0.49284928492849284, "percentage": 2.46, "elapsed_time": "0:10:13", "remaining_time": "6:44:35", "throughput": 1542.06, "total_tokens": 945792} {"current_steps": 4485, "total_steps": 181800, "loss": 0.2308, "lr": 1.2332233223322333e-05, "epoch": 0.4933993399339934, "percentage": 2.47, "elapsed_time": "0:10:14", "remaining_time": "6:44:34", "throughput": 1542.07, "total_tokens": 946848} {"current_steps": 4490, "total_steps": 181800, "loss": 0.2051, "lr": 1.2345984598459846e-05, "epoch": 0.49394939493949397, "percentage": 2.47, "elapsed_time": "0:10:14", "remaining_time": "6:44:34", "throughput": 1542.19, "total_tokens": 947968} {"current_steps": 4495, "total_steps": 181800, "loss": 0.2438, "lr": 1.235973597359736e-05, "epoch": 0.4944994499449945, "percentage": 2.47, "elapsed_time": "0:10:15", "remaining_time": "6:44:33", "throughput": 1542.23, "total_tokens": 949056} {"current_steps": 4500, "total_steps": 181800, "loss": 0.2471, "lr": 1.2373487348734874e-05, "epoch": 0.49504950495049505, "percentage": 2.48, "elapsed_time": "0:10:16", "remaining_time": "6:44:32", "throughput": 1542.29, "total_tokens": 950144} {"current_steps": 4505, "total_steps": 181800, "loss": 0.2108, "lr": 1.2387238723872388e-05, "epoch": 0.4955995599559956, "percentage": 2.48, "elapsed_time": "0:10:16", "remaining_time": "6:44:31", "throughput": 1542.3, "total_tokens": 951200} {"current_steps": 4510, "total_steps": 181800, "loss": 0.185, "lr": 1.2400990099009901e-05, "epoch": 0.4961496149614962, "percentage": 2.48, "elapsed_time": "0:10:17", "remaining_time": "6:44:31", "throughput": 1542.26, "total_tokens": 952224} {"current_steps": 4515, "total_steps": 181800, "loss": 0.229, "lr": 1.2414741474147414e-05, "epoch": 0.4966996699669967, "percentage": 2.48, "elapsed_time": "0:10:18", "remaining_time": "6:44:30", "throughput": 1542.27, "total_tokens": 953280} {"current_steps": 4520, "total_steps": 181800, "loss": 0.2064, "lr": 1.2428492849284928e-05, "epoch": 0.49724972497249725, "percentage": 2.49, "elapsed_time": "0:10:18", "remaining_time": "6:44:29", "throughput": 1542.33, "total_tokens": 954368} {"current_steps": 4525, "total_steps": 181800, "loss": 0.2152, "lr": 1.2442244224422443e-05, "epoch": 0.4977997799779978, "percentage": 2.49, "elapsed_time": "0:10:19", "remaining_time": "6:44:28", "throughput": 1542.34, "total_tokens": 955424} {"current_steps": 4530, "total_steps": 181800, "loss": 0.2186, "lr": 1.2455995599559956e-05, "epoch": 0.49834983498349833, "percentage": 2.49, "elapsed_time": "0:10:20", "remaining_time": "6:44:27", "throughput": 1542.25, "total_tokens": 956416} {"current_steps": 4535, "total_steps": 181800, "loss": 0.2308, "lr": 1.246974697469747e-05, "epoch": 0.4988998899889989, "percentage": 2.49, "elapsed_time": "0:10:20", "remaining_time": "6:44:26", "throughput": 1542.26, "total_tokens": 957472} {"current_steps": 4540, "total_steps": 181800, "loss": 0.2098, "lr": 1.2483498349834983e-05, "epoch": 0.49944994499449946, "percentage": 2.5, "elapsed_time": "0:10:21", "remaining_time": "6:44:25", "throughput": 1542.27, "total_tokens": 958528} {"current_steps": 4545, "total_steps": 181800, "loss": 0.2238, "lr": 1.2497249724972498e-05, "epoch": 0.5, "percentage": 2.5, "elapsed_time": "0:10:22", "remaining_time": "6:44:25", "throughput": 1542.29, "total_tokens": 959584} {"current_steps": 4550, "total_steps": 181800, "loss": 0.2371, "lr": 1.2511001100110011e-05, "epoch": 0.5005500550055005, "percentage": 2.5, "elapsed_time": "0:10:22", "remaining_time": "6:44:24", "throughput": 1542.3, "total_tokens": 960640} {"current_steps": 4555, "total_steps": 181800, "loss": 0.1665, "lr": 1.2524752475247525e-05, "epoch": 0.5011001100110011, "percentage": 2.51, "elapsed_time": "0:10:23", "remaining_time": "6:44:23", "throughput": 1542.36, "total_tokens": 961728} {"current_steps": 4560, "total_steps": 181800, "loss": 0.2218, "lr": 1.253850385038504e-05, "epoch": 0.5016501650165016, "percentage": 2.51, "elapsed_time": "0:10:24", "remaining_time": "6:44:22", "throughput": 1542.37, "total_tokens": 962784} {"current_steps": 4565, "total_steps": 181800, "loss": 0.2613, "lr": 1.2552255225522553e-05, "epoch": 0.5022002200220022, "percentage": 2.51, "elapsed_time": "0:10:24", "remaining_time": "6:44:21", "throughput": 1542.33, "total_tokens": 963808} {"current_steps": 4570, "total_steps": 181800, "loss": 0.2142, "lr": 1.2566006600660066e-05, "epoch": 0.5027502750275028, "percentage": 2.51, "elapsed_time": "0:10:25", "remaining_time": "6:44:21", "throughput": 1542.44, "total_tokens": 964928} {"current_steps": 4575, "total_steps": 181800, "loss": 0.2729, "lr": 1.257975797579758e-05, "epoch": 0.5033003300330033, "percentage": 2.52, "elapsed_time": "0:10:26", "remaining_time": "6:44:20", "throughput": 1542.53, "total_tokens": 966048} {"current_steps": 4580, "total_steps": 181800, "loss": 0.2015, "lr": 1.2593509350935095e-05, "epoch": 0.5038503850385039, "percentage": 2.52, "elapsed_time": "0:10:26", "remaining_time": "6:44:19", "throughput": 1542.43, "total_tokens": 967040} {"current_steps": 4585, "total_steps": 181800, "loss": 0.2061, "lr": 1.2607260726072608e-05, "epoch": 0.5044004400440044, "percentage": 2.52, "elapsed_time": "0:10:27", "remaining_time": "6:44:18", "throughput": 1542.38, "total_tokens": 968064} {"current_steps": 4590, "total_steps": 181800, "loss": 0.1941, "lr": 1.2621012101210123e-05, "epoch": 0.504950495049505, "percentage": 2.52, "elapsed_time": "0:10:28", "remaining_time": "6:44:18", "throughput": 1542.33, "total_tokens": 969088} {"current_steps": 4595, "total_steps": 181800, "loss": 0.224, "lr": 1.2634763476347637e-05, "epoch": 0.5055005500550055, "percentage": 2.53, "elapsed_time": "0:10:29", "remaining_time": "6:44:17", "throughput": 1542.28, "total_tokens": 970112} {"current_steps": 4600, "total_steps": 181800, "loss": 0.2146, "lr": 1.264851485148515e-05, "epoch": 0.506050605060506, "percentage": 2.53, "elapsed_time": "0:10:29", "remaining_time": "6:44:16", "throughput": 1542.23, "total_tokens": 971136} {"current_steps": 4605, "total_steps": 181800, "loss": 0.1998, "lr": 1.2662266226622663e-05, "epoch": 0.5066006600660066, "percentage": 2.53, "elapsed_time": "0:10:30", "remaining_time": "6:44:16", "throughput": 1542.18, "total_tokens": 972160} {"current_steps": 4610, "total_steps": 181800, "loss": 0.21, "lr": 1.2676017601760177e-05, "epoch": 0.5071507150715071, "percentage": 2.54, "elapsed_time": "0:10:31", "remaining_time": "6:44:15", "throughput": 1542.13, "total_tokens": 973184} {"current_steps": 4615, "total_steps": 181800, "loss": 0.214, "lr": 1.268976897689769e-05, "epoch": 0.5077007700770076, "percentage": 2.54, "elapsed_time": "0:10:31", "remaining_time": "6:44:14", "throughput": 1542.13, "total_tokens": 974240} {"current_steps": 4620, "total_steps": 181800, "loss": 0.2085, "lr": 1.2703520352035203e-05, "epoch": 0.5082508250825083, "percentage": 2.54, "elapsed_time": "0:10:32", "remaining_time": "6:44:14", "throughput": 1542.08, "total_tokens": 975264} {"current_steps": 4625, "total_steps": 181800, "loss": 0.1581, "lr": 1.2717271727172717e-05, "epoch": 0.5088008800880088, "percentage": 2.54, "elapsed_time": "0:10:33", "remaining_time": "6:44:13", "throughput": 1541.98, "total_tokens": 976256} {"current_steps": 4630, "total_steps": 181800, "loss": 0.171, "lr": 1.2731023102310233e-05, "epoch": 0.5093509350935094, "percentage": 2.55, "elapsed_time": "0:10:33", "remaining_time": "6:44:12", "throughput": 1541.88, "total_tokens": 977248} {"current_steps": 4635, "total_steps": 181800, "loss": 0.2049, "lr": 1.2744774477447747e-05, "epoch": 0.5099009900990099, "percentage": 2.55, "elapsed_time": "0:10:34", "remaining_time": "6:44:12", "throughput": 1541.93, "total_tokens": 978336} {"current_steps": 4640, "total_steps": 181800, "loss": 0.1842, "lr": 1.275852585258526e-05, "epoch": 0.5104510451045104, "percentage": 2.55, "elapsed_time": "0:10:35", "remaining_time": "6:44:11", "throughput": 1541.88, "total_tokens": 979360} {"current_steps": 4645, "total_steps": 181800, "loss": 0.2878, "lr": 1.2772277227722773e-05, "epoch": 0.511001100110011, "percentage": 2.56, "elapsed_time": "0:10:35", "remaining_time": "6:44:10", "throughput": 1541.89, "total_tokens": 980416} {"current_steps": 4650, "total_steps": 181800, "loss": 0.2171, "lr": 1.2786028602860287e-05, "epoch": 0.5115511551155115, "percentage": 2.56, "elapsed_time": "0:10:36", "remaining_time": "6:44:10", "throughput": 1541.89, "total_tokens": 981472} {"current_steps": 4655, "total_steps": 181800, "loss": 0.219, "lr": 1.27997799779978e-05, "epoch": 0.5121012101210121, "percentage": 2.56, "elapsed_time": "0:10:37", "remaining_time": "6:44:09", "throughput": 1542.0, "total_tokens": 982592} {"current_steps": 4660, "total_steps": 181800, "loss": 0.2219, "lr": 1.2813531353135313e-05, "epoch": 0.5126512651265126, "percentage": 2.56, "elapsed_time": "0:10:37", "remaining_time": "6:44:08", "throughput": 1542.01, "total_tokens": 983648} {"current_steps": 4665, "total_steps": 181800, "loss": 0.2326, "lr": 1.2827282728272827e-05, "epoch": 0.5132013201320133, "percentage": 2.57, "elapsed_time": "0:10:38", "remaining_time": "6:44:07", "throughput": 1541.93, "total_tokens": 984640} {"current_steps": 4670, "total_steps": 181800, "loss": 0.1822, "lr": 1.284103410341034e-05, "epoch": 0.5137513751375138, "percentage": 2.57, "elapsed_time": "0:10:39", "remaining_time": "6:44:06", "throughput": 1541.98, "total_tokens": 985728} {"current_steps": 4675, "total_steps": 181800, "loss": 0.2649, "lr": 1.2854785478547857e-05, "epoch": 0.5143014301430143, "percentage": 2.57, "elapsed_time": "0:10:39", "remaining_time": "6:44:05", "throughput": 1542.04, "total_tokens": 986816} {"current_steps": 4680, "total_steps": 181800, "loss": 0.1755, "lr": 1.286853685368537e-05, "epoch": 0.5148514851485149, "percentage": 2.57, "elapsed_time": "0:10:40", "remaining_time": "6:44:05", "throughput": 1542.09, "total_tokens": 987904} {"current_steps": 4685, "total_steps": 181800, "loss": 0.2204, "lr": 1.2882288228822884e-05, "epoch": 0.5154015401540154, "percentage": 2.58, "elapsed_time": "0:10:41", "remaining_time": "6:44:04", "throughput": 1542.05, "total_tokens": 988928} {"current_steps": 4690, "total_steps": 181800, "loss": 0.1823, "lr": 1.2896039603960397e-05, "epoch": 0.5159515951595159, "percentage": 2.58, "elapsed_time": "0:10:41", "remaining_time": "6:44:03", "throughput": 1541.96, "total_tokens": 989920} {"current_steps": 4695, "total_steps": 181800, "loss": 0.1869, "lr": 1.290979097909791e-05, "epoch": 0.5165016501650165, "percentage": 2.58, "elapsed_time": "0:10:42", "remaining_time": "6:44:02", "throughput": 1541.92, "total_tokens": 990944} {"current_steps": 4700, "total_steps": 181800, "loss": 0.2105, "lr": 1.2923542354235424e-05, "epoch": 0.517051705170517, "percentage": 2.59, "elapsed_time": "0:10:43", "remaining_time": "6:44:02", "throughput": 1541.82, "total_tokens": 991936} {"current_steps": 4705, "total_steps": 181800, "loss": 0.2041, "lr": 1.2937293729372937e-05, "epoch": 0.5176017601760176, "percentage": 2.59, "elapsed_time": "0:10:44", "remaining_time": "6:44:01", "throughput": 1541.83, "total_tokens": 992992} {"current_steps": 4710, "total_steps": 181800, "loss": 0.2218, "lr": 1.295104510451045e-05, "epoch": 0.5181518151815182, "percentage": 2.59, "elapsed_time": "0:10:44", "remaining_time": "6:44:00", "throughput": 1541.83, "total_tokens": 994048} {"current_steps": 4715, "total_steps": 181800, "loss": 0.3047, "lr": 1.2964796479647964e-05, "epoch": 0.5187018701870187, "percentage": 2.59, "elapsed_time": "0:10:45", "remaining_time": "6:43:59", "throughput": 1541.84, "total_tokens": 995104} {"current_steps": 4720, "total_steps": 181800, "loss": 0.2086, "lr": 1.297854785478548e-05, "epoch": 0.5192519251925193, "percentage": 2.6, "elapsed_time": "0:10:46", "remaining_time": "6:43:59", "throughput": 1541.89, "total_tokens": 996192} {"current_steps": 4725, "total_steps": 181800, "loss": 0.2449, "lr": 1.2992299229922994e-05, "epoch": 0.5198019801980198, "percentage": 2.6, "elapsed_time": "0:10:46", "remaining_time": "6:43:58", "throughput": 1541.86, "total_tokens": 997216} {"current_steps": 4730, "total_steps": 181800, "loss": 0.1869, "lr": 1.3006050605060507e-05, "epoch": 0.5203520352035204, "percentage": 2.6, "elapsed_time": "0:10:47", "remaining_time": "6:43:57", "throughput": 1541.77, "total_tokens": 998208} {"current_steps": 4735, "total_steps": 181800, "loss": 0.1899, "lr": 1.301980198019802e-05, "epoch": 0.5209020902090209, "percentage": 2.6, "elapsed_time": "0:10:48", "remaining_time": "6:43:56", "throughput": 1541.78, "total_tokens": 999264} {"current_steps": 4740, "total_steps": 181800, "loss": 0.2186, "lr": 1.3033553355335534e-05, "epoch": 0.5214521452145214, "percentage": 2.61, "elapsed_time": "0:10:48", "remaining_time": "6:43:55", "throughput": 1541.84, "total_tokens": 1000352} {"current_steps": 4745, "total_steps": 181800, "loss": 0.1943, "lr": 1.3047304730473047e-05, "epoch": 0.522002200220022, "percentage": 2.61, "elapsed_time": "0:10:49", "remaining_time": "6:43:54", "throughput": 1541.86, "total_tokens": 1001408} {"current_steps": 4750, "total_steps": 181800, "loss": 0.238, "lr": 1.306105610561056e-05, "epoch": 0.5225522552255225, "percentage": 2.61, "elapsed_time": "0:10:50", "remaining_time": "6:43:53", "throughput": 1541.97, "total_tokens": 1002528} {"current_steps": 4755, "total_steps": 181800, "loss": 0.2079, "lr": 1.3074807480748076e-05, "epoch": 0.523102310231023, "percentage": 2.62, "elapsed_time": "0:10:50", "remaining_time": "6:43:53", "throughput": 1541.93, "total_tokens": 1003552} {"current_steps": 4760, "total_steps": 181800, "loss": 0.2249, "lr": 1.3088558855885589e-05, "epoch": 0.5236523652365237, "percentage": 2.62, "elapsed_time": "0:10:51", "remaining_time": "6:43:52", "throughput": 1541.94, "total_tokens": 1004608} {"current_steps": 4765, "total_steps": 181800, "loss": 0.2556, "lr": 1.3102310231023102e-05, "epoch": 0.5242024202420242, "percentage": 2.62, "elapsed_time": "0:10:52", "remaining_time": "6:43:51", "throughput": 1541.95, "total_tokens": 1005664} {"current_steps": 4770, "total_steps": 181800, "loss": 0.2234, "lr": 1.3116061606160617e-05, "epoch": 0.5247524752475248, "percentage": 2.62, "elapsed_time": "0:10:52", "remaining_time": "6:43:50", "throughput": 1541.82, "total_tokens": 1006624} {"current_steps": 4775, "total_steps": 181800, "loss": 0.2038, "lr": 1.312981298129813e-05, "epoch": 0.5253025302530253, "percentage": 2.63, "elapsed_time": "0:10:53", "remaining_time": "6:43:49", "throughput": 1541.83, "total_tokens": 1007680} {"current_steps": 4780, "total_steps": 181800, "loss": 0.2052, "lr": 1.3143564356435644e-05, "epoch": 0.5258525852585259, "percentage": 2.63, "elapsed_time": "0:10:54", "remaining_time": "6:43:49", "throughput": 1541.78, "total_tokens": 1008704} {"current_steps": 4785, "total_steps": 181800, "loss": 0.1673, "lr": 1.3157315731573159e-05, "epoch": 0.5264026402640264, "percentage": 2.63, "elapsed_time": "0:10:54", "remaining_time": "6:43:48", "throughput": 1541.78, "total_tokens": 1009760} {"current_steps": 4790, "total_steps": 181800, "loss": 0.2099, "lr": 1.3171067106710672e-05, "epoch": 0.5269526952695269, "percentage": 2.63, "elapsed_time": "0:10:55", "remaining_time": "6:43:47", "throughput": 1541.78, "total_tokens": 1010816} {"current_steps": 4795, "total_steps": 181800, "loss": 0.2703, "lr": 1.3184818481848186e-05, "epoch": 0.5275027502750275, "percentage": 2.64, "elapsed_time": "0:10:56", "remaining_time": "6:43:46", "throughput": 1541.78, "total_tokens": 1011872} {"current_steps": 4800, "total_steps": 181800, "loss": 0.1851, "lr": 1.3198569856985699e-05, "epoch": 0.528052805280528, "percentage": 2.64, "elapsed_time": "0:10:56", "remaining_time": "6:43:46", "throughput": 1541.83, "total_tokens": 1012960} {"current_steps": 4805, "total_steps": 181800, "loss": 0.2234, "lr": 1.3212321232123212e-05, "epoch": 0.5286028602860287, "percentage": 2.64, "elapsed_time": "0:10:57", "remaining_time": "6:43:45", "throughput": 1541.83, "total_tokens": 1014016} {"current_steps": 4810, "total_steps": 181800, "loss": 0.177, "lr": 1.3226072607260726e-05, "epoch": 0.5291529152915292, "percentage": 2.65, "elapsed_time": "0:10:58", "remaining_time": "6:43:44", "throughput": 1541.79, "total_tokens": 1015040} {"current_steps": 4815, "total_steps": 181800, "loss": 0.193, "lr": 1.3239823982398243e-05, "epoch": 0.5297029702970297, "percentage": 2.65, "elapsed_time": "0:10:59", "remaining_time": "6:43:44", "throughput": 1541.74, "total_tokens": 1016064} {"current_steps": 4820, "total_steps": 181800, "loss": 0.1935, "lr": 1.3253575357535756e-05, "epoch": 0.5302530253025303, "percentage": 2.65, "elapsed_time": "0:10:59", "remaining_time": "6:43:43", "throughput": 1541.69, "total_tokens": 1017088} {"current_steps": 4825, "total_steps": 181800, "loss": 0.1904, "lr": 1.326732673267327e-05, "epoch": 0.5308030803080308, "percentage": 2.65, "elapsed_time": "0:11:00", "remaining_time": "6:43:42", "throughput": 1541.73, "total_tokens": 1018176} {"current_steps": 4830, "total_steps": 181800, "loss": 0.1808, "lr": 1.3281078107810783e-05, "epoch": 0.5313531353135313, "percentage": 2.66, "elapsed_time": "0:11:01", "remaining_time": "6:43:42", "throughput": 1541.64, "total_tokens": 1019168} {"current_steps": 4835, "total_steps": 181800, "loss": 0.2219, "lr": 1.3294829482948296e-05, "epoch": 0.5319031903190319, "percentage": 2.66, "elapsed_time": "0:11:01", "remaining_time": "6:43:41", "throughput": 1541.65, "total_tokens": 1020224} {"current_steps": 4840, "total_steps": 181800, "loss": 0.2138, "lr": 1.330858085808581e-05, "epoch": 0.5324532453245324, "percentage": 2.66, "elapsed_time": "0:11:02", "remaining_time": "6:43:40", "throughput": 1541.66, "total_tokens": 1021280} {"current_steps": 4845, "total_steps": 181800, "loss": 0.2506, "lr": 1.3322332233223323e-05, "epoch": 0.533003300330033, "percentage": 2.67, "elapsed_time": "0:11:03", "remaining_time": "6:43:39", "throughput": 1541.72, "total_tokens": 1022368} {"current_steps": 4850, "total_steps": 181800, "loss": 0.2782, "lr": 1.3336083608360836e-05, "epoch": 0.5335533553355336, "percentage": 2.67, "elapsed_time": "0:11:03", "remaining_time": "6:43:39", "throughput": 1541.73, "total_tokens": 1023424} {"current_steps": 4855, "total_steps": 181800, "loss": 0.2704, "lr": 1.334983498349835e-05, "epoch": 0.5341034103410341, "percentage": 2.67, "elapsed_time": "0:11:04", "remaining_time": "6:43:38", "throughput": 1541.69, "total_tokens": 1024448} {"current_steps": 4860, "total_steps": 181800, "loss": 0.2344, "lr": 1.3363586358635866e-05, "epoch": 0.5346534653465347, "percentage": 2.67, "elapsed_time": "0:11:05", "remaining_time": "6:43:37", "throughput": 1541.7, "total_tokens": 1025504} {"current_steps": 4865, "total_steps": 181800, "loss": 0.2394, "lr": 1.337733773377338e-05, "epoch": 0.5352035203520352, "percentage": 2.68, "elapsed_time": "0:11:05", "remaining_time": "6:43:36", "throughput": 1541.71, "total_tokens": 1026560} {"current_steps": 4870, "total_steps": 181800, "loss": 0.2348, "lr": 1.3391089108910893e-05, "epoch": 0.5357535753575358, "percentage": 2.68, "elapsed_time": "0:11:06", "remaining_time": "6:43:35", "throughput": 1541.76, "total_tokens": 1027648} {"current_steps": 4875, "total_steps": 181800, "loss": 0.1589, "lr": 1.3404840484048406e-05, "epoch": 0.5363036303630363, "percentage": 2.68, "elapsed_time": "0:11:07", "remaining_time": "6:43:35", "throughput": 1541.81, "total_tokens": 1028736} {"current_steps": 4880, "total_steps": 181800, "loss": 0.2196, "lr": 1.341859185918592e-05, "epoch": 0.5368536853685368, "percentage": 2.68, "elapsed_time": "0:11:07", "remaining_time": "6:43:34", "throughput": 1541.76, "total_tokens": 1029760} {"current_steps": 4885, "total_steps": 181800, "loss": 0.1765, "lr": 1.3432343234323433e-05, "epoch": 0.5374037403740374, "percentage": 2.69, "elapsed_time": "0:11:08", "remaining_time": "6:43:33", "throughput": 1541.81, "total_tokens": 1030848} {"current_steps": 4890, "total_steps": 181800, "loss": 0.1645, "lr": 1.3446094609460946e-05, "epoch": 0.5379537953795379, "percentage": 2.69, "elapsed_time": "0:11:09", "remaining_time": "6:43:32", "throughput": 1542.02, "total_tokens": 1032032} {"current_steps": 4895, "total_steps": 181800, "loss": 0.1946, "lr": 1.345984598459846e-05, "epoch": 0.5385038503850385, "percentage": 2.69, "elapsed_time": "0:11:09", "remaining_time": "6:43:32", "throughput": 1542.12, "total_tokens": 1033152} {"current_steps": 4900, "total_steps": 181800, "loss": 0.2239, "lr": 1.3473597359735973e-05, "epoch": 0.5390539053905391, "percentage": 2.7, "elapsed_time": "0:11:10", "remaining_time": "6:43:31", "throughput": 1542.08, "total_tokens": 1034176} {"current_steps": 4905, "total_steps": 181800, "loss": 0.2418, "lr": 1.3487348734873486e-05, "epoch": 0.5396039603960396, "percentage": 2.7, "elapsed_time": "0:11:11", "remaining_time": "6:43:30", "throughput": 1542.09, "total_tokens": 1035232} {"current_steps": 4910, "total_steps": 181800, "loss": 0.2079, "lr": 1.3501100110011003e-05, "epoch": 0.5401540154015402, "percentage": 2.7, "elapsed_time": "0:11:12", "remaining_time": "6:43:36", "throughput": 1541.79, "total_tokens": 1036352} {"current_steps": 4915, "total_steps": 181800, "loss": 0.1835, "lr": 1.3514851485148516e-05, "epoch": 0.5407040704070407, "percentage": 2.7, "elapsed_time": "0:11:12", "remaining_time": "6:43:35", "throughput": 1541.75, "total_tokens": 1037376} {"current_steps": 4920, "total_steps": 181800, "loss": 0.1891, "lr": 1.352860286028603e-05, "epoch": 0.5412541254125413, "percentage": 2.71, "elapsed_time": "0:11:13", "remaining_time": "6:43:34", "throughput": 1541.81, "total_tokens": 1038464} {"current_steps": 4925, "total_steps": 181800, "loss": 0.1731, "lr": 1.3542354235423543e-05, "epoch": 0.5418041804180418, "percentage": 2.71, "elapsed_time": "0:11:14", "remaining_time": "6:43:33", "throughput": 1541.73, "total_tokens": 1039456} {"current_steps": 4930, "total_steps": 181800, "loss": 0.1759, "lr": 1.3556105610561056e-05, "epoch": 0.5423542354235423, "percentage": 2.71, "elapsed_time": "0:11:14", "remaining_time": "6:43:32", "throughput": 1541.78, "total_tokens": 1040544} {"current_steps": 4935, "total_steps": 181800, "loss": 0.2171, "lr": 1.356985698569857e-05, "epoch": 0.5429042904290429, "percentage": 2.71, "elapsed_time": "0:11:15", "remaining_time": "6:43:32", "throughput": 1541.79, "total_tokens": 1041600} {"current_steps": 4940, "total_steps": 181800, "loss": 0.1964, "lr": 1.3583608360836083e-05, "epoch": 0.5434543454345434, "percentage": 2.72, "elapsed_time": "0:11:16", "remaining_time": "6:43:31", "throughput": 1541.94, "total_tokens": 1042752} {"current_steps": 4945, "total_steps": 181800, "loss": 0.1879, "lr": 1.3597359735973596e-05, "epoch": 0.5440044004400441, "percentage": 2.72, "elapsed_time": "0:11:16", "remaining_time": "6:43:30", "throughput": 1541.81, "total_tokens": 1043712} {"current_steps": 4950, "total_steps": 181800, "loss": 0.1637, "lr": 1.3611111111111111e-05, "epoch": 0.5445544554455446, "percentage": 2.72, "elapsed_time": "0:11:17", "remaining_time": "6:43:29", "throughput": 1541.82, "total_tokens": 1044768} {"current_steps": 4955, "total_steps": 181800, "loss": 0.207, "lr": 1.3624862486248626e-05, "epoch": 0.5451045104510451, "percentage": 2.73, "elapsed_time": "0:11:18", "remaining_time": "6:43:28", "throughput": 1541.82, "total_tokens": 1045824} {"current_steps": 4960, "total_steps": 181800, "loss": 0.2562, "lr": 1.363861386138614e-05, "epoch": 0.5456545654565457, "percentage": 2.73, "elapsed_time": "0:11:18", "remaining_time": "6:43:28", "throughput": 1541.82, "total_tokens": 1046880} {"current_steps": 4965, "total_steps": 181800, "loss": 0.2166, "lr": 1.3652365236523653e-05, "epoch": 0.5462046204620462, "percentage": 2.73, "elapsed_time": "0:11:19", "remaining_time": "6:43:27", "throughput": 1541.78, "total_tokens": 1047904} {"current_steps": 4970, "total_steps": 181800, "loss": 0.2262, "lr": 1.3666116611661167e-05, "epoch": 0.5467546754675467, "percentage": 2.73, "elapsed_time": "0:11:20", "remaining_time": "6:43:26", "throughput": 1541.77, "total_tokens": 1048960} {"current_steps": 4975, "total_steps": 181800, "loss": 0.2393, "lr": 1.367986798679868e-05, "epoch": 0.5473047304730473, "percentage": 2.74, "elapsed_time": "0:11:21", "remaining_time": "6:43:26", "throughput": 1541.72, "total_tokens": 1049984} {"current_steps": 4980, "total_steps": 181800, "loss": 0.1883, "lr": 1.3693619361936195e-05, "epoch": 0.5478547854785478, "percentage": 2.74, "elapsed_time": "0:11:21", "remaining_time": "6:43:25", "throughput": 1541.63, "total_tokens": 1050976} {"current_steps": 4985, "total_steps": 181800, "loss": 0.1922, "lr": 1.3707370737073708e-05, "epoch": 0.5484048404840484, "percentage": 2.74, "elapsed_time": "0:11:22", "remaining_time": "6:43:24", "throughput": 1541.64, "total_tokens": 1052032} {"current_steps": 4990, "total_steps": 181800, "loss": 0.2159, "lr": 1.3721122112211222e-05, "epoch": 0.5489548954895489, "percentage": 2.74, "elapsed_time": "0:11:23", "remaining_time": "6:43:23", "throughput": 1541.6, "total_tokens": 1053056} {"current_steps": 4995, "total_steps": 181800, "loss": 0.1769, "lr": 1.3734873487348735e-05, "epoch": 0.5495049504950495, "percentage": 2.75, "elapsed_time": "0:11:23", "remaining_time": "6:43:23", "throughput": 1541.51, "total_tokens": 1054048} {"current_steps": 5000, "total_steps": 181800, "loss": 0.2141, "lr": 1.3748624862486248e-05, "epoch": 0.5500550055005501, "percentage": 2.75, "elapsed_time": "0:11:24", "remaining_time": "6:43:22", "throughput": 1541.51, "total_tokens": 1055104} {"current_steps": 5005, "total_steps": 181800, "loss": 0.2045, "lr": 1.3762376237623763e-05, "epoch": 0.5506050605060506, "percentage": 2.75, "elapsed_time": "0:11:25", "remaining_time": "6:43:21", "throughput": 1541.58, "total_tokens": 1056192} {"current_steps": 5010, "total_steps": 181800, "loss": 0.2115, "lr": 1.3776127612761278e-05, "epoch": 0.5511551155115512, "percentage": 2.76, "elapsed_time": "0:11:25", "remaining_time": "6:43:20", "throughput": 1541.69, "total_tokens": 1057312} {"current_steps": 5015, "total_steps": 181800, "loss": 0.157, "lr": 1.3789878987898792e-05, "epoch": 0.5517051705170517, "percentage": 2.76, "elapsed_time": "0:11:26", "remaining_time": "6:43:19", "throughput": 1541.7, "total_tokens": 1058368} {"current_steps": 5020, "total_steps": 181800, "loss": 0.2347, "lr": 1.3803630363036305e-05, "epoch": 0.5522552255225522, "percentage": 2.76, "elapsed_time": "0:11:27", "remaining_time": "6:43:18", "throughput": 1541.72, "total_tokens": 1059424} {"current_steps": 5025, "total_steps": 181800, "loss": 0.2256, "lr": 1.3817381738173818e-05, "epoch": 0.5528052805280528, "percentage": 2.76, "elapsed_time": "0:11:27", "remaining_time": "6:43:17", "throughput": 1541.69, "total_tokens": 1060448} {"current_steps": 5030, "total_steps": 181800, "loss": 0.1938, "lr": 1.3831133113311332e-05, "epoch": 0.5533553355335533, "percentage": 2.77, "elapsed_time": "0:11:28", "remaining_time": "6:43:16", "throughput": 1541.66, "total_tokens": 1061472} {"current_steps": 5035, "total_steps": 181800, "loss": 0.242, "lr": 1.3844884488448845e-05, "epoch": 0.5539053905390539, "percentage": 2.77, "elapsed_time": "0:11:29", "remaining_time": "6:43:16", "throughput": 1541.54, "total_tokens": 1062432} {"current_steps": 5040, "total_steps": 181800, "loss": 0.2107, "lr": 1.3858635863586358e-05, "epoch": 0.5544554455445545, "percentage": 2.77, "elapsed_time": "0:11:29", "remaining_time": "6:43:15", "throughput": 1541.5, "total_tokens": 1063456} {"current_steps": 5045, "total_steps": 181800, "loss": 0.2417, "lr": 1.3872387238723872e-05, "epoch": 0.555005500550055, "percentage": 2.78, "elapsed_time": "0:11:30", "remaining_time": "6:43:14", "throughput": 1541.46, "total_tokens": 1064480} {"current_steps": 5050, "total_steps": 181800, "loss": 0.2262, "lr": 1.3886138613861389e-05, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:11:31", "remaining_time": "6:43:13", "throughput": 1541.46, "total_tokens": 1065536} {"current_steps": 5055, "total_steps": 181800, "loss": 0.1757, "lr": 1.3899889988998902e-05, "epoch": 0.5561056105610561, "percentage": 2.78, "elapsed_time": "0:11:31", "remaining_time": "6:43:12", "throughput": 1541.47, "total_tokens": 1066592} {"current_steps": 5060, "total_steps": 181800, "loss": 0.1798, "lr": 1.3913641364136415e-05, "epoch": 0.5566556655665567, "percentage": 2.78, "elapsed_time": "0:11:32", "remaining_time": "6:43:12", "throughput": 1541.44, "total_tokens": 1067616} {"current_steps": 5065, "total_steps": 181800, "loss": 0.2298, "lr": 1.3927392739273929e-05, "epoch": 0.5572057205720572, "percentage": 2.79, "elapsed_time": "0:11:33", "remaining_time": "6:43:11", "throughput": 1541.46, "total_tokens": 1068672} {"current_steps": 5070, "total_steps": 181800, "loss": 0.3145, "lr": 1.3941144114411442e-05, "epoch": 0.5577557755775577, "percentage": 2.79, "elapsed_time": "0:11:33", "remaining_time": "6:43:10", "throughput": 1541.42, "total_tokens": 1069696} {"current_steps": 5075, "total_steps": 181800, "loss": 0.2278, "lr": 1.3954895489548955e-05, "epoch": 0.5583058305830583, "percentage": 2.79, "elapsed_time": "0:11:34", "remaining_time": "6:43:09", "throughput": 1541.43, "total_tokens": 1070752} {"current_steps": 5080, "total_steps": 181800, "loss": 0.1968, "lr": 1.3968646864686469e-05, "epoch": 0.5588558855885588, "percentage": 2.79, "elapsed_time": "0:11:35", "remaining_time": "6:43:08", "throughput": 1541.49, "total_tokens": 1071840} {"current_steps": 5085, "total_steps": 181800, "loss": 0.1917, "lr": 1.3982398239823982e-05, "epoch": 0.5594059405940595, "percentage": 2.8, "elapsed_time": "0:11:36", "remaining_time": "6:43:07", "throughput": 1541.54, "total_tokens": 1072928} {"current_steps": 5090, "total_steps": 181800, "loss": 0.1991, "lr": 1.3996149614961495e-05, "epoch": 0.55995599559956, "percentage": 2.8, "elapsed_time": "0:11:36", "remaining_time": "6:43:07", "throughput": 1541.41, "total_tokens": 1073888} {"current_steps": 5095, "total_steps": 181800, "loss": 0.1853, "lr": 1.4009900990099012e-05, "epoch": 0.5605060506050605, "percentage": 2.8, "elapsed_time": "0:11:37", "remaining_time": "6:43:06", "throughput": 1541.42, "total_tokens": 1074944} {"current_steps": 5100, "total_steps": 181800, "loss": 0.2275, "lr": 1.4023652365236525e-05, "epoch": 0.5610561056105611, "percentage": 2.81, "elapsed_time": "0:11:38", "remaining_time": "6:43:05", "throughput": 1541.57, "total_tokens": 1076096} {"current_steps": 5105, "total_steps": 181800, "loss": 0.1966, "lr": 1.4037403740374039e-05, "epoch": 0.5616061606160616, "percentage": 2.81, "elapsed_time": "0:11:38", "remaining_time": "6:43:04", "throughput": 1541.49, "total_tokens": 1077088} {"current_steps": 5110, "total_steps": 181800, "loss": 0.2298, "lr": 1.4051155115511552e-05, "epoch": 0.5621562156215621, "percentage": 2.81, "elapsed_time": "0:11:39", "remaining_time": "6:43:03", "throughput": 1541.5, "total_tokens": 1078144} {"current_steps": 5115, "total_steps": 181800, "loss": 0.2317, "lr": 1.4064906490649066e-05, "epoch": 0.5627062706270627, "percentage": 2.81, "elapsed_time": "0:11:40", "remaining_time": "6:43:03", "throughput": 1541.51, "total_tokens": 1079200} {"current_steps": 5120, "total_steps": 181800, "loss": 0.2173, "lr": 1.4078657865786579e-05, "epoch": 0.5632563256325632, "percentage": 2.82, "elapsed_time": "0:11:40", "remaining_time": "6:43:02", "throughput": 1541.52, "total_tokens": 1080256} {"current_steps": 5125, "total_steps": 181800, "loss": 0.208, "lr": 1.4092409240924092e-05, "epoch": 0.5638063806380638, "percentage": 2.82, "elapsed_time": "0:11:41", "remaining_time": "6:43:01", "throughput": 1541.57, "total_tokens": 1081344} {"current_steps": 5130, "total_steps": 181800, "loss": 0.1764, "lr": 1.4106160616061606e-05, "epoch": 0.5643564356435643, "percentage": 2.82, "elapsed_time": "0:11:42", "remaining_time": "6:43:00", "throughput": 1541.59, "total_tokens": 1082400} {"current_steps": 5135, "total_steps": 181800, "loss": 0.2598, "lr": 1.4119911991199119e-05, "epoch": 0.564906490649065, "percentage": 2.82, "elapsed_time": "0:11:42", "remaining_time": "6:42:59", "throughput": 1541.69, "total_tokens": 1083520} {"current_steps": 5140, "total_steps": 181800, "loss": 0.3027, "lr": 1.4133663366336632e-05, "epoch": 0.5654565456545655, "percentage": 2.83, "elapsed_time": "0:11:43", "remaining_time": "6:42:58", "throughput": 1541.7, "total_tokens": 1084576} {"current_steps": 5145, "total_steps": 181800, "loss": 0.2028, "lr": 1.4147414741474149e-05, "epoch": 0.566006600660066, "percentage": 2.83, "elapsed_time": "0:11:44", "remaining_time": "6:42:57", "throughput": 1541.71, "total_tokens": 1085632} {"current_steps": 5150, "total_steps": 181800, "loss": 0.2465, "lr": 1.4161166116611662e-05, "epoch": 0.5665566556655666, "percentage": 2.83, "elapsed_time": "0:11:44", "remaining_time": "6:42:57", "throughput": 1541.68, "total_tokens": 1086656} {"current_steps": 5155, "total_steps": 181800, "loss": 0.1539, "lr": 1.4174917491749176e-05, "epoch": 0.5671067106710671, "percentage": 2.84, "elapsed_time": "0:11:45", "remaining_time": "6:42:56", "throughput": 1541.64, "total_tokens": 1087680} {"current_steps": 5160, "total_steps": 181800, "loss": 0.1973, "lr": 1.4188668866886689e-05, "epoch": 0.5676567656765676, "percentage": 2.84, "elapsed_time": "0:11:46", "remaining_time": "6:42:55", "throughput": 1541.6, "total_tokens": 1088704} {"current_steps": 5165, "total_steps": 181800, "loss": 0.1822, "lr": 1.4202420242024202e-05, "epoch": 0.5682068206820682, "percentage": 2.84, "elapsed_time": "0:11:46", "remaining_time": "6:42:54", "throughput": 1541.57, "total_tokens": 1089728} {"current_steps": 5170, "total_steps": 181800, "loss": 0.2519, "lr": 1.4216171617161716e-05, "epoch": 0.5687568756875687, "percentage": 2.84, "elapsed_time": "0:11:47", "remaining_time": "6:42:53", "throughput": 1541.63, "total_tokens": 1090816} {"current_steps": 5175, "total_steps": 181800, "loss": 0.2005, "lr": 1.422992299229923e-05, "epoch": 0.5693069306930693, "percentage": 2.85, "elapsed_time": "0:11:48", "remaining_time": "6:42:53", "throughput": 1541.63, "total_tokens": 1091872} {"current_steps": 5180, "total_steps": 181800, "loss": 0.2763, "lr": 1.4243674367436744e-05, "epoch": 0.5698569856985699, "percentage": 2.85, "elapsed_time": "0:11:48", "remaining_time": "6:42:52", "throughput": 1541.73, "total_tokens": 1092992} {"current_steps": 5185, "total_steps": 181800, "loss": 0.2195, "lr": 1.4257425742574257e-05, "epoch": 0.5704070407040704, "percentage": 2.85, "elapsed_time": "0:11:49", "remaining_time": "6:42:51", "throughput": 1541.69, "total_tokens": 1094016} {"current_steps": 5190, "total_steps": 181800, "loss": 0.181, "lr": 1.4271177117711773e-05, "epoch": 0.570957095709571, "percentage": 2.85, "elapsed_time": "0:11:50", "remaining_time": "6:42:50", "throughput": 1541.74, "total_tokens": 1095104} {"current_steps": 5195, "total_steps": 181800, "loss": 0.1786, "lr": 1.4284928492849286e-05, "epoch": 0.5715071507150715, "percentage": 2.86, "elapsed_time": "0:11:50", "remaining_time": "6:42:50", "throughput": 1541.7, "total_tokens": 1096128} {"current_steps": 5200, "total_steps": 181800, "loss": 0.1954, "lr": 1.42986798679868e-05, "epoch": 0.5720572057205721, "percentage": 2.86, "elapsed_time": "0:11:51", "remaining_time": "6:42:49", "throughput": 1541.66, "total_tokens": 1097152} {"current_steps": 5205, "total_steps": 181800, "loss": 0.2197, "lr": 1.4312431243124314e-05, "epoch": 0.5726072607260726, "percentage": 2.86, "elapsed_time": "0:11:52", "remaining_time": "6:42:48", "throughput": 1541.63, "total_tokens": 1098176} {"current_steps": 5210, "total_steps": 181800, "loss": 0.2128, "lr": 1.4326182618261828e-05, "epoch": 0.5731573157315731, "percentage": 2.87, "elapsed_time": "0:11:53", "remaining_time": "6:42:47", "throughput": 1541.54, "total_tokens": 1099168} {"current_steps": 5215, "total_steps": 181800, "loss": 0.2227, "lr": 1.4339933993399341e-05, "epoch": 0.5737073707370737, "percentage": 2.87, "elapsed_time": "0:11:53", "remaining_time": "6:42:47", "throughput": 1541.46, "total_tokens": 1100160} {"current_steps": 5220, "total_steps": 181800, "loss": 0.1984, "lr": 1.4353685368536854e-05, "epoch": 0.5742574257425742, "percentage": 2.87, "elapsed_time": "0:11:54", "remaining_time": "6:42:46", "throughput": 1541.42, "total_tokens": 1101184} {"current_steps": 5225, "total_steps": 181800, "loss": 0.1651, "lr": 1.4367436743674368e-05, "epoch": 0.5748074807480749, "percentage": 2.87, "elapsed_time": "0:11:55", "remaining_time": "6:42:45", "throughput": 1541.47, "total_tokens": 1102272} {"current_steps": 5230, "total_steps": 181800, "loss": 0.197, "lr": 1.4381188118811881e-05, "epoch": 0.5753575357535754, "percentage": 2.88, "elapsed_time": "0:11:55", "remaining_time": "6:42:44", "throughput": 1541.48, "total_tokens": 1103328} {"current_steps": 5235, "total_steps": 181800, "loss": 0.1808, "lr": 1.4394939493949398e-05, "epoch": 0.5759075907590759, "percentage": 2.88, "elapsed_time": "0:11:56", "remaining_time": "6:42:43", "throughput": 1541.49, "total_tokens": 1104384} {"current_steps": 5240, "total_steps": 181800, "loss": 0.1467, "lr": 1.4408690869086911e-05, "epoch": 0.5764576457645765, "percentage": 2.88, "elapsed_time": "0:11:57", "remaining_time": "6:42:43", "throughput": 1541.49, "total_tokens": 1105440} {"current_steps": 5245, "total_steps": 181800, "loss": 0.2214, "lr": 1.4422442244224424e-05, "epoch": 0.577007700770077, "percentage": 2.89, "elapsed_time": "0:11:57", "remaining_time": "6:42:42", "throughput": 1541.5, "total_tokens": 1106496} {"current_steps": 5250, "total_steps": 181800, "loss": 0.2024, "lr": 1.4436193619361938e-05, "epoch": 0.5775577557755776, "percentage": 2.89, "elapsed_time": "0:11:58", "remaining_time": "6:42:41", "throughput": 1541.51, "total_tokens": 1107552} {"current_steps": 5255, "total_steps": 181800, "loss": 0.185, "lr": 1.4449944994499451e-05, "epoch": 0.5781078107810781, "percentage": 2.89, "elapsed_time": "0:11:59", "remaining_time": "6:42:40", "throughput": 1541.57, "total_tokens": 1108640} {"current_steps": 5260, "total_steps": 181800, "loss": 0.2783, "lr": 1.4463696369636965e-05, "epoch": 0.5786578657865786, "percentage": 2.89, "elapsed_time": "0:11:59", "remaining_time": "6:42:40", "throughput": 1541.62, "total_tokens": 1109728} {"current_steps": 5265, "total_steps": 181800, "loss": 0.2579, "lr": 1.4477447744774478e-05, "epoch": 0.5792079207920792, "percentage": 2.9, "elapsed_time": "0:12:00", "remaining_time": "6:42:39", "throughput": 1541.61, "total_tokens": 1110784} {"current_steps": 5270, "total_steps": 181800, "loss": 0.17, "lr": 1.4491199119911991e-05, "epoch": 0.5797579757975797, "percentage": 2.9, "elapsed_time": "0:12:01", "remaining_time": "6:42:38", "throughput": 1541.61, "total_tokens": 1111840} {"current_steps": 5275, "total_steps": 181800, "loss": 0.2579, "lr": 1.4504950495049505e-05, "epoch": 0.5803080308030804, "percentage": 2.9, "elapsed_time": "0:12:01", "remaining_time": "6:42:38", "throughput": 1541.53, "total_tokens": 1112832} {"current_steps": 5280, "total_steps": 181800, "loss": 0.1946, "lr": 1.4518701870187018e-05, "epoch": 0.5808580858085809, "percentage": 2.9, "elapsed_time": "0:12:02", "remaining_time": "6:42:37", "throughput": 1541.58, "total_tokens": 1113920} {"current_steps": 5285, "total_steps": 181800, "loss": 0.2465, "lr": 1.4532453245324535e-05, "epoch": 0.5814081408140814, "percentage": 2.91, "elapsed_time": "0:12:03", "remaining_time": "6:42:36", "throughput": 1541.67, "total_tokens": 1115040} {"current_steps": 5290, "total_steps": 181800, "loss": 0.1703, "lr": 1.4546204620462048e-05, "epoch": 0.581958195819582, "percentage": 2.91, "elapsed_time": "0:12:03", "remaining_time": "6:42:35", "throughput": 1541.64, "total_tokens": 1116064} {"current_steps": 5295, "total_steps": 181800, "loss": 0.2361, "lr": 1.4559955995599561e-05, "epoch": 0.5825082508250825, "percentage": 2.91, "elapsed_time": "0:12:04", "remaining_time": "6:42:35", "throughput": 1541.64, "total_tokens": 1117120} {"current_steps": 5300, "total_steps": 181800, "loss": 0.2464, "lr": 1.4573707370737075e-05, "epoch": 0.583058305830583, "percentage": 2.92, "elapsed_time": "0:12:05", "remaining_time": "6:42:34", "throughput": 1541.65, "total_tokens": 1118176} {"current_steps": 5305, "total_steps": 181800, "loss": 0.2265, "lr": 1.4587458745874588e-05, "epoch": 0.5836083608360836, "percentage": 2.92, "elapsed_time": "0:12:05", "remaining_time": "6:42:33", "throughput": 1541.66, "total_tokens": 1119232} {"current_steps": 5310, "total_steps": 181800, "loss": 0.1717, "lr": 1.4601210121012101e-05, "epoch": 0.5841584158415841, "percentage": 2.92, "elapsed_time": "0:12:06", "remaining_time": "6:42:32", "throughput": 1541.71, "total_tokens": 1120320} {"current_steps": 5315, "total_steps": 181800, "loss": 0.2704, "lr": 1.4614961496149615e-05, "epoch": 0.5847084708470847, "percentage": 2.92, "elapsed_time": "0:12:07", "remaining_time": "6:42:31", "throughput": 1541.75, "total_tokens": 1121408} {"current_steps": 5320, "total_steps": 181800, "loss": 0.2142, "lr": 1.4628712871287128e-05, "epoch": 0.5852585258525853, "percentage": 2.93, "elapsed_time": "0:12:08", "remaining_time": "6:42:31", "throughput": 1541.8, "total_tokens": 1122496} {"current_steps": 5325, "total_steps": 181800, "loss": 0.2365, "lr": 1.4642464246424641e-05, "epoch": 0.5858085808580858, "percentage": 2.93, "elapsed_time": "0:12:08", "remaining_time": "6:42:30", "throughput": 1541.68, "total_tokens": 1123456} {"current_steps": 5330, "total_steps": 181800, "loss": 0.1808, "lr": 1.4656215621562158e-05, "epoch": 0.5863586358635864, "percentage": 2.93, "elapsed_time": "0:12:09", "remaining_time": "6:42:29", "throughput": 1541.68, "total_tokens": 1124512} {"current_steps": 5335, "total_steps": 181800, "loss": 0.2611, "lr": 1.4669966996699672e-05, "epoch": 0.5869086908690869, "percentage": 2.93, "elapsed_time": "0:12:10", "remaining_time": "6:42:28", "throughput": 1541.69, "total_tokens": 1125568} {"current_steps": 5340, "total_steps": 181800, "loss": 0.1813, "lr": 1.4683718371837185e-05, "epoch": 0.5874587458745875, "percentage": 2.94, "elapsed_time": "0:12:10", "remaining_time": "6:42:28", "throughput": 1541.7, "total_tokens": 1126624} {"current_steps": 5345, "total_steps": 181800, "loss": 0.216, "lr": 1.4697469746974698e-05, "epoch": 0.588008800880088, "percentage": 2.94, "elapsed_time": "0:12:11", "remaining_time": "6:42:27", "throughput": 1541.75, "total_tokens": 1127712} {"current_steps": 5350, "total_steps": 181800, "loss": 0.1769, "lr": 1.4711221122112212e-05, "epoch": 0.5885588558855885, "percentage": 2.94, "elapsed_time": "0:12:12", "remaining_time": "6:42:26", "throughput": 1541.72, "total_tokens": 1128736} {"current_steps": 5355, "total_steps": 181800, "loss": 0.1701, "lr": 1.4724972497249725e-05, "epoch": 0.5891089108910891, "percentage": 2.95, "elapsed_time": "0:12:12", "remaining_time": "6:42:25", "throughput": 1541.69, "total_tokens": 1129760} {"current_steps": 5360, "total_steps": 181800, "loss": 0.2204, "lr": 1.4738723872387238e-05, "epoch": 0.5896589658965896, "percentage": 2.95, "elapsed_time": "0:12:13", "remaining_time": "6:42:24", "throughput": 1541.78, "total_tokens": 1130880} {"current_steps": 5365, "total_steps": 181800, "loss": 0.1809, "lr": 1.4752475247524752e-05, "epoch": 0.5902090209020903, "percentage": 2.95, "elapsed_time": "0:12:14", "remaining_time": "6:42:24", "throughput": 1541.75, "total_tokens": 1131904} {"current_steps": 5370, "total_steps": 181800, "loss": 0.1967, "lr": 1.4766226622662267e-05, "epoch": 0.5907590759075908, "percentage": 2.95, "elapsed_time": "0:12:14", "remaining_time": "6:42:23", "throughput": 1541.75, "total_tokens": 1132960} {"current_steps": 5375, "total_steps": 181800, "loss": 0.1894, "lr": 1.477997799779978e-05, "epoch": 0.5913091309130913, "percentage": 2.96, "elapsed_time": "0:12:15", "remaining_time": "6:42:22", "throughput": 1541.66, "total_tokens": 1133952} {"current_steps": 5380, "total_steps": 181800, "loss": 0.1724, "lr": 1.4793729372937295e-05, "epoch": 0.5918591859185919, "percentage": 2.96, "elapsed_time": "0:12:16", "remaining_time": "6:42:22", "throughput": 1541.66, "total_tokens": 1135008} {"current_steps": 5385, "total_steps": 181800, "loss": 0.1931, "lr": 1.4807480748074808e-05, "epoch": 0.5924092409240924, "percentage": 2.96, "elapsed_time": "0:12:16", "remaining_time": "6:42:21", "throughput": 1541.62, "total_tokens": 1136032} {"current_steps": 5390, "total_steps": 181800, "loss": 0.199, "lr": 1.4821232123212322e-05, "epoch": 0.592959295929593, "percentage": 2.96, "elapsed_time": "0:12:17", "remaining_time": "6:42:20", "throughput": 1541.5, "total_tokens": 1136992} {"current_steps": 5395, "total_steps": 181800, "loss": 0.1809, "lr": 1.4834983498349835e-05, "epoch": 0.5935093509350935, "percentage": 2.97, "elapsed_time": "0:12:18", "remaining_time": "6:42:19", "throughput": 1541.59, "total_tokens": 1138112} {"current_steps": 5400, "total_steps": 181800, "loss": 0.1945, "lr": 1.484873487348735e-05, "epoch": 0.594059405940594, "percentage": 2.97, "elapsed_time": "0:12:18", "remaining_time": "6:42:19", "throughput": 1541.55, "total_tokens": 1139136} {"current_steps": 5405, "total_steps": 181800, "loss": 0.2104, "lr": 1.4862486248624863e-05, "epoch": 0.5946094609460946, "percentage": 2.97, "elapsed_time": "0:12:19", "remaining_time": "6:42:18", "throughput": 1541.47, "total_tokens": 1140128} {"current_steps": 5410, "total_steps": 181800, "loss": 0.2005, "lr": 1.4876237623762377e-05, "epoch": 0.5951595159515951, "percentage": 2.98, "elapsed_time": "0:12:20", "remaining_time": "6:42:17", "throughput": 1541.52, "total_tokens": 1141216} {"current_steps": 5415, "total_steps": 181800, "loss": 0.165, "lr": 1.488998899889989e-05, "epoch": 0.5957095709570958, "percentage": 2.98, "elapsed_time": "0:12:21", "remaining_time": "6:42:16", "throughput": 1541.53, "total_tokens": 1142272} {"current_steps": 5420, "total_steps": 181800, "loss": 0.2954, "lr": 1.4903740374037404e-05, "epoch": 0.5962596259625963, "percentage": 2.98, "elapsed_time": "0:12:21", "remaining_time": "6:42:16", "throughput": 1541.54, "total_tokens": 1143328} {"current_steps": 5425, "total_steps": 181800, "loss": 0.1527, "lr": 1.4917491749174919e-05, "epoch": 0.5968096809680968, "percentage": 2.98, "elapsed_time": "0:12:22", "remaining_time": "6:42:15", "throughput": 1541.46, "total_tokens": 1144320} {"current_steps": 5430, "total_steps": 181800, "loss": 0.1755, "lr": 1.4931243124312434e-05, "epoch": 0.5973597359735974, "percentage": 2.99, "elapsed_time": "0:12:23", "remaining_time": "6:42:14", "throughput": 1541.47, "total_tokens": 1145376} {"current_steps": 5435, "total_steps": 181800, "loss": 0.1564, "lr": 1.4944994499449947e-05, "epoch": 0.5979097909790979, "percentage": 2.99, "elapsed_time": "0:12:23", "remaining_time": "6:42:13", "throughput": 1541.44, "total_tokens": 1146400} {"current_steps": 5440, "total_steps": 181800, "loss": 0.2303, "lr": 1.495874587458746e-05, "epoch": 0.5984598459845984, "percentage": 2.99, "elapsed_time": "0:12:24", "remaining_time": "6:42:12", "throughput": 1541.36, "total_tokens": 1147392} {"current_steps": 5445, "total_steps": 181800, "loss": 0.2148, "lr": 1.4972497249724974e-05, "epoch": 0.599009900990099, "percentage": 3.0, "elapsed_time": "0:12:25", "remaining_time": "6:42:12", "throughput": 1541.37, "total_tokens": 1148448} {"current_steps": 5450, "total_steps": 181800, "loss": 0.1765, "lr": 1.4986248624862487e-05, "epoch": 0.5995599559955995, "percentage": 3.0, "elapsed_time": "0:12:25", "remaining_time": "6:42:11", "throughput": 1541.38, "total_tokens": 1149504} {"current_steps": 5455, "total_steps": 181800, "loss": 0.1444, "lr": 1.5e-05, "epoch": 0.6001100110011001, "percentage": 3.0, "elapsed_time": "0:12:26", "remaining_time": "6:42:10", "throughput": 1541.42, "total_tokens": 1150592} {"current_steps": 5460, "total_steps": 181800, "loss": 0.2077, "lr": 1.5013751375137514e-05, "epoch": 0.6006600660066007, "percentage": 3.0, "elapsed_time": "0:12:27", "remaining_time": "6:42:09", "throughput": 1541.44, "total_tokens": 1151648} {"current_steps": 5465, "total_steps": 181800, "loss": 0.2439, "lr": 1.5027502750275027e-05, "epoch": 0.6012101210121013, "percentage": 3.01, "elapsed_time": "0:12:27", "remaining_time": "6:42:08", "throughput": 1541.4, "total_tokens": 1152672} {"current_steps": 5470, "total_steps": 181800, "loss": 0.1915, "lr": 1.5041254125412544e-05, "epoch": 0.6017601760176018, "percentage": 3.01, "elapsed_time": "0:12:28", "remaining_time": "6:42:08", "throughput": 1541.41, "total_tokens": 1153728} {"current_steps": 5475, "total_steps": 181800, "loss": 0.2191, "lr": 1.5055005500550057e-05, "epoch": 0.6023102310231023, "percentage": 3.01, "elapsed_time": "0:12:29", "remaining_time": "6:42:07", "throughput": 1541.37, "total_tokens": 1154752} {"current_steps": 5480, "total_steps": 181800, "loss": 0.1883, "lr": 1.506875687568757e-05, "epoch": 0.6028602860286029, "percentage": 3.01, "elapsed_time": "0:12:29", "remaining_time": "6:42:06", "throughput": 1541.41, "total_tokens": 1155840} {"current_steps": 5485, "total_steps": 181800, "loss": 0.191, "lr": 1.5082508250825084e-05, "epoch": 0.6034103410341034, "percentage": 3.02, "elapsed_time": "0:12:30", "remaining_time": "6:42:06", "throughput": 1541.45, "total_tokens": 1156928} {"current_steps": 5490, "total_steps": 181800, "loss": 0.192, "lr": 1.5096259625962597e-05, "epoch": 0.6039603960396039, "percentage": 3.02, "elapsed_time": "0:12:31", "remaining_time": "6:42:05", "throughput": 1541.45, "total_tokens": 1157984} {"current_steps": 5495, "total_steps": 181800, "loss": 0.159, "lr": 1.511001100110011e-05, "epoch": 0.6045104510451045, "percentage": 3.02, "elapsed_time": "0:12:31", "remaining_time": "6:42:04", "throughput": 1541.5, "total_tokens": 1159072} {"current_steps": 5500, "total_steps": 181800, "loss": 0.2502, "lr": 1.5123762376237624e-05, "epoch": 0.605060506050605, "percentage": 3.03, "elapsed_time": "0:12:32", "remaining_time": "6:42:04", "throughput": 1541.54, "total_tokens": 1160160} {"current_steps": 5505, "total_steps": 181800, "loss": 0.18, "lr": 1.5137513751375137e-05, "epoch": 0.6056105610561056, "percentage": 3.03, "elapsed_time": "0:12:33", "remaining_time": "6:42:03", "throughput": 1541.59, "total_tokens": 1161248} {"current_steps": 5510, "total_steps": 181800, "loss": 0.216, "lr": 1.515126512651265e-05, "epoch": 0.6061606160616062, "percentage": 3.03, "elapsed_time": "0:12:33", "remaining_time": "6:42:02", "throughput": 1541.56, "total_tokens": 1162272} {"current_steps": 5515, "total_steps": 181800, "loss": 0.2164, "lr": 1.5165016501650164e-05, "epoch": 0.6067106710671067, "percentage": 3.03, "elapsed_time": "0:12:34", "remaining_time": "6:42:01", "throughput": 1541.53, "total_tokens": 1163296} {"current_steps": 5520, "total_steps": 181800, "loss": 0.1764, "lr": 1.517876787678768e-05, "epoch": 0.6072607260726073, "percentage": 3.04, "elapsed_time": "0:12:35", "remaining_time": "6:42:00", "throughput": 1541.53, "total_tokens": 1164352} {"current_steps": 5525, "total_steps": 181800, "loss": 0.1557, "lr": 1.5192519251925194e-05, "epoch": 0.6078107810781078, "percentage": 3.04, "elapsed_time": "0:12:36", "remaining_time": "6:42:00", "throughput": 1541.46, "total_tokens": 1165344} {"current_steps": 5530, "total_steps": 181800, "loss": 0.1782, "lr": 1.5206270627062707e-05, "epoch": 0.6083608360836084, "percentage": 3.04, "elapsed_time": "0:12:36", "remaining_time": "6:41:59", "throughput": 1541.51, "total_tokens": 1166432} {"current_steps": 5535, "total_steps": 181800, "loss": 0.2593, "lr": 1.522002200220022e-05, "epoch": 0.6089108910891089, "percentage": 3.04, "elapsed_time": "0:12:37", "remaining_time": "6:41:58", "throughput": 1541.48, "total_tokens": 1167456} {"current_steps": 5540, "total_steps": 181800, "loss": 0.188, "lr": 1.5233773377337734e-05, "epoch": 0.6094609460946094, "percentage": 3.05, "elapsed_time": "0:12:38", "remaining_time": "6:41:57", "throughput": 1541.49, "total_tokens": 1168512} {"current_steps": 5545, "total_steps": 181800, "loss": 0.1786, "lr": 1.5247524752475247e-05, "epoch": 0.61001100110011, "percentage": 3.05, "elapsed_time": "0:12:38", "remaining_time": "6:41:56", "throughput": 1541.54, "total_tokens": 1169600} {"current_steps": 5550, "total_steps": 181800, "loss": 0.1993, "lr": 1.526127612761276e-05, "epoch": 0.6105610561056105, "percentage": 3.05, "elapsed_time": "0:12:39", "remaining_time": "6:41:56", "throughput": 1541.51, "total_tokens": 1170624} {"current_steps": 5555, "total_steps": 181800, "loss": 0.2077, "lr": 1.5275027502750276e-05, "epoch": 0.6111111111111112, "percentage": 3.06, "elapsed_time": "0:12:40", "remaining_time": "6:41:55", "throughput": 1541.51, "total_tokens": 1171680} {"current_steps": 5560, "total_steps": 181800, "loss": 0.2179, "lr": 1.5288778877887787e-05, "epoch": 0.6116611661166117, "percentage": 3.06, "elapsed_time": "0:12:40", "remaining_time": "6:41:54", "throughput": 1541.46, "total_tokens": 1172704} {"current_steps": 5565, "total_steps": 181800, "loss": 0.1761, "lr": 1.5302530253025306e-05, "epoch": 0.6122112211221122, "percentage": 3.06, "elapsed_time": "0:12:41", "remaining_time": "6:41:54", "throughput": 1541.47, "total_tokens": 1173760} {"current_steps": 5570, "total_steps": 181800, "loss": 0.2402, "lr": 1.5316281628162818e-05, "epoch": 0.6127612761276128, "percentage": 3.06, "elapsed_time": "0:12:42", "remaining_time": "6:41:53", "throughput": 1541.51, "total_tokens": 1174848} {"current_steps": 5575, "total_steps": 181800, "loss": 0.1963, "lr": 1.5330033003300333e-05, "epoch": 0.6133113311331133, "percentage": 3.07, "elapsed_time": "0:12:42", "remaining_time": "6:41:52", "throughput": 1541.47, "total_tokens": 1175872} {"current_steps": 5580, "total_steps": 181800, "loss": 0.2026, "lr": 1.5343784378437844e-05, "epoch": 0.6138613861386139, "percentage": 3.07, "elapsed_time": "0:12:43", "remaining_time": "6:41:51", "throughput": 1541.4, "total_tokens": 1176864} {"current_steps": 5585, "total_steps": 181800, "loss": 0.1472, "lr": 1.535753575357536e-05, "epoch": 0.6144114411441144, "percentage": 3.07, "elapsed_time": "0:12:44", "remaining_time": "6:41:51", "throughput": 1541.49, "total_tokens": 1177984} {"current_steps": 5590, "total_steps": 181800, "loss": 0.1337, "lr": 1.537128712871287e-05, "epoch": 0.6149614961496149, "percentage": 3.07, "elapsed_time": "0:12:44", "remaining_time": "6:41:50", "throughput": 1541.52, "total_tokens": 1179072} {"current_steps": 5595, "total_steps": 181800, "loss": 0.2154, "lr": 1.5385038503850386e-05, "epoch": 0.6155115511551155, "percentage": 3.08, "elapsed_time": "0:12:45", "remaining_time": "6:41:50", "throughput": 1541.52, "total_tokens": 1180128} {"current_steps": 5600, "total_steps": 181800, "loss": 0.1967, "lr": 1.5398789878987898e-05, "epoch": 0.6160616061606161, "percentage": 3.08, "elapsed_time": "0:12:46", "remaining_time": "6:41:49", "throughput": 1541.53, "total_tokens": 1181184} {"current_steps": 5605, "total_steps": 181800, "loss": 0.18, "lr": 1.5412541254125413e-05, "epoch": 0.6166116611661167, "percentage": 3.08, "elapsed_time": "0:12:46", "remaining_time": "6:41:48", "throughput": 1541.5, "total_tokens": 1182208} {"current_steps": 5610, "total_steps": 181800, "loss": 0.231, "lr": 1.5426292629262928e-05, "epoch": 0.6171617161716172, "percentage": 3.09, "elapsed_time": "0:12:47", "remaining_time": "6:41:47", "throughput": 1541.51, "total_tokens": 1183264} {"current_steps": 5615, "total_steps": 181800, "loss": 0.1684, "lr": 1.5440044004400443e-05, "epoch": 0.6177117711771177, "percentage": 3.09, "elapsed_time": "0:12:48", "remaining_time": "6:41:46", "throughput": 1541.44, "total_tokens": 1184256} {"current_steps": 5620, "total_steps": 181800, "loss": 0.2998, "lr": 1.5453795379537954e-05, "epoch": 0.6182618261826183, "percentage": 3.09, "elapsed_time": "0:12:48", "remaining_time": "6:41:45", "throughput": 1541.4, "total_tokens": 1185280} {"current_steps": 5625, "total_steps": 181800, "loss": 0.164, "lr": 1.546754675467547e-05, "epoch": 0.6188118811881188, "percentage": 3.09, "elapsed_time": "0:12:49", "remaining_time": "6:41:45", "throughput": 1541.45, "total_tokens": 1186368} {"current_steps": 5630, "total_steps": 181800, "loss": 0.1761, "lr": 1.548129812981298e-05, "epoch": 0.6193619361936193, "percentage": 3.1, "elapsed_time": "0:12:50", "remaining_time": "6:41:44", "throughput": 1541.46, "total_tokens": 1187424} {"current_steps": 5635, "total_steps": 181800, "loss": 0.1651, "lr": 1.5495049504950496e-05, "epoch": 0.6199119911991199, "percentage": 3.1, "elapsed_time": "0:12:51", "remaining_time": "6:41:43", "throughput": 1541.43, "total_tokens": 1188448} {"current_steps": 5640, "total_steps": 181800, "loss": 0.1938, "lr": 1.5508800880088008e-05, "epoch": 0.6204620462046204, "percentage": 3.1, "elapsed_time": "0:12:51", "remaining_time": "6:41:42", "throughput": 1541.43, "total_tokens": 1189504} {"current_steps": 5645, "total_steps": 181800, "loss": 0.2028, "lr": 1.5522552255225523e-05, "epoch": 0.621012101210121, "percentage": 3.11, "elapsed_time": "0:12:52", "remaining_time": "6:41:42", "throughput": 1541.48, "total_tokens": 1190592} {"current_steps": 5650, "total_steps": 181800, "loss": 0.1461, "lr": 1.5536303630363035e-05, "epoch": 0.6215621562156216, "percentage": 3.11, "elapsed_time": "0:12:53", "remaining_time": "6:41:41", "throughput": 1541.48, "total_tokens": 1191648} {"current_steps": 5655, "total_steps": 181800, "loss": 0.2232, "lr": 1.555005500550055e-05, "epoch": 0.6221122112211221, "percentage": 3.11, "elapsed_time": "0:12:53", "remaining_time": "6:41:40", "throughput": 1541.48, "total_tokens": 1192704} {"current_steps": 5660, "total_steps": 181800, "loss": 0.1984, "lr": 1.5563806380638065e-05, "epoch": 0.6226622662266227, "percentage": 3.11, "elapsed_time": "0:12:54", "remaining_time": "6:41:40", "throughput": 1541.44, "total_tokens": 1193728} {"current_steps": 5665, "total_steps": 181800, "loss": 0.1674, "lr": 1.557755775577558e-05, "epoch": 0.6232123212321232, "percentage": 3.12, "elapsed_time": "0:12:55", "remaining_time": "6:41:39", "throughput": 1541.45, "total_tokens": 1194784} {"current_steps": 5670, "total_steps": 181800, "loss": 0.2033, "lr": 1.559130913091309e-05, "epoch": 0.6237623762376238, "percentage": 3.12, "elapsed_time": "0:12:55", "remaining_time": "6:41:38", "throughput": 1541.41, "total_tokens": 1195808} {"current_steps": 5675, "total_steps": 181800, "loss": 0.2098, "lr": 1.5605060506050606e-05, "epoch": 0.6243124312431243, "percentage": 3.12, "elapsed_time": "0:12:56", "remaining_time": "6:41:37", "throughput": 1541.41, "total_tokens": 1196864} {"current_steps": 5680, "total_steps": 181800, "loss": 0.2854, "lr": 1.5618811881188118e-05, "epoch": 0.6248624862486248, "percentage": 3.12, "elapsed_time": "0:12:57", "remaining_time": "6:41:37", "throughput": 1541.46, "total_tokens": 1197952} {"current_steps": 5685, "total_steps": 181800, "loss": 0.2379, "lr": 1.5632563256325633e-05, "epoch": 0.6254125412541254, "percentage": 3.13, "elapsed_time": "0:12:57", "remaining_time": "6:41:36", "throughput": 1541.42, "total_tokens": 1198976} {"current_steps": 5690, "total_steps": 181800, "loss": 0.2222, "lr": 1.5646314631463148e-05, "epoch": 0.6259625962596259, "percentage": 3.13, "elapsed_time": "0:12:58", "remaining_time": "6:41:35", "throughput": 1541.44, "total_tokens": 1200032} {"current_steps": 5695, "total_steps": 181800, "loss": 0.1755, "lr": 1.566006600660066e-05, "epoch": 0.6265126512651266, "percentage": 3.13, "elapsed_time": "0:12:59", "remaining_time": "6:41:34", "throughput": 1541.48, "total_tokens": 1201120} {"current_steps": 5700, "total_steps": 181800, "loss": 0.2469, "lr": 1.5673817381738175e-05, "epoch": 0.6270627062706271, "percentage": 3.14, "elapsed_time": "0:12:59", "remaining_time": "6:41:34", "throughput": 1541.44, "total_tokens": 1202144} {"current_steps": 5705, "total_steps": 181800, "loss": 0.2067, "lr": 1.568756875687569e-05, "epoch": 0.6276127612761276, "percentage": 3.14, "elapsed_time": "0:13:00", "remaining_time": "6:41:33", "throughput": 1541.44, "total_tokens": 1203200} {"current_steps": 5710, "total_steps": 181800, "loss": 0.2148, "lr": 1.57013201320132e-05, "epoch": 0.6281628162816282, "percentage": 3.14, "elapsed_time": "0:13:01", "remaining_time": "6:41:33", "throughput": 1541.52, "total_tokens": 1204320} {"current_steps": 5715, "total_steps": 181800, "loss": 0.2114, "lr": 1.5715071507150717e-05, "epoch": 0.6287128712871287, "percentage": 3.14, "elapsed_time": "0:13:01", "remaining_time": "6:41:32", "throughput": 1541.48, "total_tokens": 1205344} {"current_steps": 5720, "total_steps": 181800, "loss": 0.1495, "lr": 1.572882288228823e-05, "epoch": 0.6292629262926293, "percentage": 3.15, "elapsed_time": "0:13:02", "remaining_time": "6:41:31", "throughput": 1541.41, "total_tokens": 1206336} {"current_steps": 5725, "total_steps": 181800, "loss": 0.2295, "lr": 1.5742574257425743e-05, "epoch": 0.6298129812981298, "percentage": 3.15, "elapsed_time": "0:13:03", "remaining_time": "6:41:30", "throughput": 1541.41, "total_tokens": 1207392} {"current_steps": 5730, "total_steps": 181800, "loss": 0.1826, "lr": 1.575632563256326e-05, "epoch": 0.6303630363036303, "percentage": 3.15, "elapsed_time": "0:13:03", "remaining_time": "6:41:30", "throughput": 1541.3, "total_tokens": 1208352} {"current_steps": 5735, "total_steps": 181800, "loss": 0.1634, "lr": 1.577007700770077e-05, "epoch": 0.6309130913091309, "percentage": 3.15, "elapsed_time": "0:13:04", "remaining_time": "6:41:29", "throughput": 1541.31, "total_tokens": 1209408} {"current_steps": 5740, "total_steps": 181800, "loss": 0.1999, "lr": 1.5783828382838285e-05, "epoch": 0.6314631463146315, "percentage": 3.16, "elapsed_time": "0:13:05", "remaining_time": "6:41:28", "throughput": 1541.27, "total_tokens": 1210432} {"current_steps": 5745, "total_steps": 181800, "loss": 0.205, "lr": 1.5797579757975797e-05, "epoch": 0.6320132013201321, "percentage": 3.16, "elapsed_time": "0:13:06", "remaining_time": "6:41:27", "throughput": 1541.32, "total_tokens": 1211520} {"current_steps": 5750, "total_steps": 181800, "loss": 0.1613, "lr": 1.5811331133113312e-05, "epoch": 0.6325632563256326, "percentage": 3.16, "elapsed_time": "0:13:06", "remaining_time": "6:41:26", "throughput": 1541.37, "total_tokens": 1212608} {"current_steps": 5755, "total_steps": 181800, "loss": 0.2279, "lr": 1.5825082508250827e-05, "epoch": 0.6331133113311331, "percentage": 3.17, "elapsed_time": "0:13:07", "remaining_time": "6:41:26", "throughput": 1541.29, "total_tokens": 1213600} {"current_steps": 5760, "total_steps": 181800, "loss": 0.1983, "lr": 1.5838833883388342e-05, "epoch": 0.6336633663366337, "percentage": 3.17, "elapsed_time": "0:13:08", "remaining_time": "6:41:25", "throughput": 1541.3, "total_tokens": 1214656} {"current_steps": 5765, "total_steps": 181800, "loss": 0.1449, "lr": 1.5852585258525853e-05, "epoch": 0.6342134213421342, "percentage": 3.17, "elapsed_time": "0:13:08", "remaining_time": "6:41:24", "throughput": 1541.31, "total_tokens": 1215712} {"current_steps": 5770, "total_steps": 181800, "loss": 0.2196, "lr": 1.586633663366337e-05, "epoch": 0.6347634763476347, "percentage": 3.17, "elapsed_time": "0:13:09", "remaining_time": "6:41:23", "throughput": 1541.32, "total_tokens": 1216768} {"current_steps": 5775, "total_steps": 181800, "loss": 0.1994, "lr": 1.588008800880088e-05, "epoch": 0.6353135313531353, "percentage": 3.18, "elapsed_time": "0:13:10", "remaining_time": "6:41:23", "throughput": 1541.37, "total_tokens": 1217856} {"current_steps": 5780, "total_steps": 181800, "loss": 0.1602, "lr": 1.5893839383938395e-05, "epoch": 0.6358635863586358, "percentage": 3.18, "elapsed_time": "0:13:10", "remaining_time": "6:41:22", "throughput": 1541.34, "total_tokens": 1218880} {"current_steps": 5785, "total_steps": 181800, "loss": 0.1745, "lr": 1.5907590759075907e-05, "epoch": 0.6364136413641364, "percentage": 3.18, "elapsed_time": "0:13:11", "remaining_time": "6:41:21", "throughput": 1541.3, "total_tokens": 1219904} {"current_steps": 5790, "total_steps": 181800, "loss": 0.2132, "lr": 1.5921342134213422e-05, "epoch": 0.636963696369637, "percentage": 3.18, "elapsed_time": "0:13:12", "remaining_time": "6:41:20", "throughput": 1541.26, "total_tokens": 1220928} {"current_steps": 5795, "total_steps": 181800, "loss": 0.1917, "lr": 1.5935093509350934e-05, "epoch": 0.6375137513751375, "percentage": 3.19, "elapsed_time": "0:13:12", "remaining_time": "6:41:20", "throughput": 1541.23, "total_tokens": 1221952} {"current_steps": 5800, "total_steps": 181800, "loss": 0.2264, "lr": 1.5948844884488452e-05, "epoch": 0.6380638063806381, "percentage": 3.19, "elapsed_time": "0:13:13", "remaining_time": "6:41:19", "throughput": 1541.24, "total_tokens": 1223008} {"current_steps": 5805, "total_steps": 181800, "loss": 0.2135, "lr": 1.5962596259625964e-05, "epoch": 0.6386138613861386, "percentage": 3.19, "elapsed_time": "0:13:14", "remaining_time": "6:41:18", "throughput": 1541.21, "total_tokens": 1224032} {"current_steps": 5810, "total_steps": 181800, "loss": 0.2177, "lr": 1.597634763476348e-05, "epoch": 0.6391639163916392, "percentage": 3.2, "elapsed_time": "0:13:14", "remaining_time": "6:41:17", "throughput": 1541.18, "total_tokens": 1225056} {"current_steps": 5815, "total_steps": 181800, "loss": 0.1819, "lr": 1.599009900990099e-05, "epoch": 0.6397139713971397, "percentage": 3.2, "elapsed_time": "0:13:15", "remaining_time": "6:41:16", "throughput": 1541.27, "total_tokens": 1226176} {"current_steps": 5820, "total_steps": 181800, "loss": 0.1804, "lr": 1.6003850385038505e-05, "epoch": 0.6402640264026402, "percentage": 3.2, "elapsed_time": "0:13:16", "remaining_time": "6:41:16", "throughput": 1541.27, "total_tokens": 1227232} {"current_steps": 5825, "total_steps": 181800, "loss": 0.2758, "lr": 1.6017601760176017e-05, "epoch": 0.6408140814081408, "percentage": 3.2, "elapsed_time": "0:13:16", "remaining_time": "6:41:15", "throughput": 1541.24, "total_tokens": 1228256} {"current_steps": 5830, "total_steps": 181800, "loss": 0.2222, "lr": 1.6031353135313532e-05, "epoch": 0.6413641364136413, "percentage": 3.21, "elapsed_time": "0:13:17", "remaining_time": "6:41:14", "throughput": 1541.29, "total_tokens": 1229344} {"current_steps": 5835, "total_steps": 181800, "loss": 0.2243, "lr": 1.6045104510451044e-05, "epoch": 0.641914191419142, "percentage": 3.21, "elapsed_time": "0:13:18", "remaining_time": "6:41:14", "throughput": 1541.33, "total_tokens": 1230432} {"current_steps": 5840, "total_steps": 181800, "loss": 0.1869, "lr": 1.605885588558856e-05, "epoch": 0.6424642464246425, "percentage": 3.21, "elapsed_time": "0:13:18", "remaining_time": "6:41:13", "throughput": 1541.33, "total_tokens": 1231488} {"current_steps": 5845, "total_steps": 181800, "loss": 0.2112, "lr": 1.6072607260726074e-05, "epoch": 0.643014301430143, "percentage": 3.22, "elapsed_time": "0:13:19", "remaining_time": "6:41:12", "throughput": 1541.3, "total_tokens": 1232512} {"current_steps": 5850, "total_steps": 181800, "loss": 0.1976, "lr": 1.608635863586359e-05, "epoch": 0.6435643564356436, "percentage": 3.22, "elapsed_time": "0:13:20", "remaining_time": "6:41:11", "throughput": 1541.39, "total_tokens": 1233632} {"current_steps": 5855, "total_steps": 181800, "loss": 0.2247, "lr": 1.61001100110011e-05, "epoch": 0.6441144114411441, "percentage": 3.22, "elapsed_time": "0:13:21", "remaining_time": "6:41:10", "throughput": 1541.32, "total_tokens": 1234624} {"current_steps": 5860, "total_steps": 181800, "loss": 0.1641, "lr": 1.6113861386138616e-05, "epoch": 0.6446644664466447, "percentage": 3.22, "elapsed_time": "0:13:21", "remaining_time": "6:41:10", "throughput": 1541.33, "total_tokens": 1235680} {"current_steps": 5865, "total_steps": 181800, "loss": 0.2056, "lr": 1.6127612761276127e-05, "epoch": 0.6452145214521452, "percentage": 3.23, "elapsed_time": "0:13:22", "remaining_time": "6:41:09", "throughput": 1541.38, "total_tokens": 1236768} {"current_steps": 5870, "total_steps": 181800, "loss": 0.2324, "lr": 1.6141364136413642e-05, "epoch": 0.6457645764576457, "percentage": 3.23, "elapsed_time": "0:13:23", "remaining_time": "6:41:08", "throughput": 1541.43, "total_tokens": 1237856} {"current_steps": 5875, "total_steps": 181800, "loss": 0.2108, "lr": 1.6155115511551154e-05, "epoch": 0.6463146314631463, "percentage": 3.23, "elapsed_time": "0:13:23", "remaining_time": "6:41:07", "throughput": 1541.4, "total_tokens": 1238880} {"current_steps": 5880, "total_steps": 181800, "loss": 0.2148, "lr": 1.616886688668867e-05, "epoch": 0.6468646864686468, "percentage": 3.23, "elapsed_time": "0:13:24", "remaining_time": "6:41:07", "throughput": 1541.44, "total_tokens": 1239968} {"current_steps": 5885, "total_steps": 181800, "loss": 0.167, "lr": 1.6182618261826184e-05, "epoch": 0.6474147414741475, "percentage": 3.24, "elapsed_time": "0:13:25", "remaining_time": "6:41:06", "throughput": 1541.44, "total_tokens": 1241024} {"current_steps": 5890, "total_steps": 181800, "loss": 0.2188, "lr": 1.6196369636963696e-05, "epoch": 0.647964796479648, "percentage": 3.24, "elapsed_time": "0:13:25", "remaining_time": "6:41:05", "throughput": 1541.41, "total_tokens": 1242048} {"current_steps": 5895, "total_steps": 181800, "loss": 0.2575, "lr": 1.621012101210121e-05, "epoch": 0.6485148514851485, "percentage": 3.24, "elapsed_time": "0:13:26", "remaining_time": "6:41:04", "throughput": 1541.33, "total_tokens": 1243040} {"current_steps": 5900, "total_steps": 181800, "loss": 0.2248, "lr": 1.6223872387238726e-05, "epoch": 0.6490649064906491, "percentage": 3.25, "elapsed_time": "0:13:27", "remaining_time": "6:41:04", "throughput": 1541.29, "total_tokens": 1244064} {"current_steps": 5905, "total_steps": 181800, "loss": 0.2112, "lr": 1.6237623762376237e-05, "epoch": 0.6496149614961496, "percentage": 3.25, "elapsed_time": "0:13:27", "remaining_time": "6:41:03", "throughput": 1541.25, "total_tokens": 1245088} {"current_steps": 5910, "total_steps": 181800, "loss": 0.2399, "lr": 1.6251375137513752e-05, "epoch": 0.6501650165016502, "percentage": 3.25, "elapsed_time": "0:13:28", "remaining_time": "6:41:02", "throughput": 1541.25, "total_tokens": 1246144} {"current_steps": 5915, "total_steps": 181800, "loss": 0.2382, "lr": 1.6265126512651267e-05, "epoch": 0.6507150715071507, "percentage": 3.25, "elapsed_time": "0:13:29", "remaining_time": "6:41:02", "throughput": 1541.3, "total_tokens": 1247232} {"current_steps": 5920, "total_steps": 181800, "loss": 0.2436, "lr": 1.627887788778878e-05, "epoch": 0.6512651265126512, "percentage": 3.26, "elapsed_time": "0:13:29", "remaining_time": "6:41:01", "throughput": 1541.31, "total_tokens": 1248288} {"current_steps": 5925, "total_steps": 181800, "loss": 0.218, "lr": 1.6292629262926294e-05, "epoch": 0.6518151815181518, "percentage": 3.26, "elapsed_time": "0:13:30", "remaining_time": "6:41:00", "throughput": 1541.35, "total_tokens": 1249376} {"current_steps": 5930, "total_steps": 181800, "loss": 0.2116, "lr": 1.6306380638063806e-05, "epoch": 0.6523652365236524, "percentage": 3.26, "elapsed_time": "0:13:31", "remaining_time": "6:40:59", "throughput": 1541.35, "total_tokens": 1250432} {"current_steps": 5935, "total_steps": 181800, "loss": 0.2064, "lr": 1.632013201320132e-05, "epoch": 0.652915291529153, "percentage": 3.26, "elapsed_time": "0:13:31", "remaining_time": "6:40:59", "throughput": 1541.43, "total_tokens": 1251552} {"current_steps": 5940, "total_steps": 181800, "loss": 0.1891, "lr": 1.6333883388338836e-05, "epoch": 0.6534653465346535, "percentage": 3.27, "elapsed_time": "0:13:32", "remaining_time": "6:40:58", "throughput": 1541.44, "total_tokens": 1252608} {"current_steps": 5945, "total_steps": 181800, "loss": 0.2024, "lr": 1.634763476347635e-05, "epoch": 0.654015401540154, "percentage": 3.27, "elapsed_time": "0:13:33", "remaining_time": "6:40:57", "throughput": 1541.44, "total_tokens": 1253664} {"current_steps": 5950, "total_steps": 181800, "loss": 0.2541, "lr": 1.6361386138613863e-05, "epoch": 0.6545654565456546, "percentage": 3.27, "elapsed_time": "0:13:33", "remaining_time": "6:40:57", "throughput": 1541.45, "total_tokens": 1254720} {"current_steps": 5955, "total_steps": 181800, "loss": 0.1756, "lr": 1.6375137513751378e-05, "epoch": 0.6551155115511551, "percentage": 3.28, "elapsed_time": "0:13:34", "remaining_time": "6:40:56", "throughput": 1541.57, "total_tokens": 1255872} {"current_steps": 5960, "total_steps": 181800, "loss": 0.163, "lr": 1.638888888888889e-05, "epoch": 0.6556655665566556, "percentage": 3.28, "elapsed_time": "0:13:35", "remaining_time": "6:40:55", "throughput": 1541.57, "total_tokens": 1256928} {"current_steps": 5965, "total_steps": 181800, "loss": 0.1761, "lr": 1.6402640264026404e-05, "epoch": 0.6562156215621562, "percentage": 3.28, "elapsed_time": "0:13:36", "remaining_time": "6:40:55", "throughput": 1541.46, "total_tokens": 1257888} {"current_steps": 5970, "total_steps": 181800, "loss": 0.2184, "lr": 1.6416391639163916e-05, "epoch": 0.6567656765676567, "percentage": 3.28, "elapsed_time": "0:13:36", "remaining_time": "6:40:54", "throughput": 1541.46, "total_tokens": 1258944} {"current_steps": 5975, "total_steps": 181800, "loss": 0.1969, "lr": 1.643014301430143e-05, "epoch": 0.6573157315731574, "percentage": 3.29, "elapsed_time": "0:13:37", "remaining_time": "6:40:53", "throughput": 1541.39, "total_tokens": 1259936} {"current_steps": 5980, "total_steps": 181800, "loss": 0.1987, "lr": 1.6443894389438943e-05, "epoch": 0.6578657865786579, "percentage": 3.29, "elapsed_time": "0:13:38", "remaining_time": "6:40:52", "throughput": 1541.4, "total_tokens": 1260992} {"current_steps": 5985, "total_steps": 181800, "loss": 0.1765, "lr": 1.645764576457646e-05, "epoch": 0.6584158415841584, "percentage": 3.29, "elapsed_time": "0:13:38", "remaining_time": "6:40:51", "throughput": 1541.37, "total_tokens": 1262016} {"current_steps": 5990, "total_steps": 181800, "loss": 0.2394, "lr": 1.6471397139713973e-05, "epoch": 0.658965896589659, "percentage": 3.29, "elapsed_time": "0:13:39", "remaining_time": "6:40:51", "throughput": 1541.38, "total_tokens": 1263072} {"current_steps": 5995, "total_steps": 181800, "loss": 0.1776, "lr": 1.6485148514851488e-05, "epoch": 0.6595159515951595, "percentage": 3.3, "elapsed_time": "0:13:40", "remaining_time": "6:40:50", "throughput": 1541.42, "total_tokens": 1264160} {"current_steps": 6000, "total_steps": 181800, "loss": 0.1726, "lr": 1.6498899889989e-05, "epoch": 0.6600660066006601, "percentage": 3.3, "elapsed_time": "0:13:40", "remaining_time": "6:40:49", "throughput": 1541.35, "total_tokens": 1265152} {"current_steps": 6005, "total_steps": 181800, "loss": 0.1892, "lr": 1.6512651265126515e-05, "epoch": 0.6606160616061606, "percentage": 3.3, "elapsed_time": "0:13:41", "remaining_time": "6:40:48", "throughput": 1541.35, "total_tokens": 1266208} {"current_steps": 6010, "total_steps": 181800, "loss": 0.2687, "lr": 1.6526402640264026e-05, "epoch": 0.6611661166116611, "percentage": 3.31, "elapsed_time": "0:13:42", "remaining_time": "6:40:48", "throughput": 1541.36, "total_tokens": 1267264} {"current_steps": 6015, "total_steps": 181800, "loss": 0.1772, "lr": 1.654015401540154e-05, "epoch": 0.6617161716171617, "percentage": 3.31, "elapsed_time": "0:13:42", "remaining_time": "6:40:47", "throughput": 1541.36, "total_tokens": 1268320} {"current_steps": 6020, "total_steps": 181800, "loss": 0.2516, "lr": 1.6553905390539053e-05, "epoch": 0.6622662266226622, "percentage": 3.31, "elapsed_time": "0:13:43", "remaining_time": "6:40:46", "throughput": 1541.29, "total_tokens": 1269312} {"current_steps": 6025, "total_steps": 181800, "loss": 0.2295, "lr": 1.6567656765676568e-05, "epoch": 0.6628162816281629, "percentage": 3.31, "elapsed_time": "0:13:44", "remaining_time": "6:40:45", "throughput": 1541.34, "total_tokens": 1270400} {"current_steps": 6030, "total_steps": 181800, "loss": 0.1775, "lr": 1.658140814081408e-05, "epoch": 0.6633663366336634, "percentage": 3.32, "elapsed_time": "0:13:44", "remaining_time": "6:40:45", "throughput": 1541.39, "total_tokens": 1271488} {"current_steps": 6035, "total_steps": 181800, "loss": 0.1989, "lr": 1.6595159515951598e-05, "epoch": 0.6639163916391639, "percentage": 3.32, "elapsed_time": "0:13:45", "remaining_time": "6:40:44", "throughput": 1541.39, "total_tokens": 1272544} {"current_steps": 6040, "total_steps": 181800, "loss": 0.191, "lr": 1.660891089108911e-05, "epoch": 0.6644664466446645, "percentage": 3.32, "elapsed_time": "0:13:46", "remaining_time": "6:40:43", "throughput": 1541.36, "total_tokens": 1273568} {"current_steps": 6045, "total_steps": 181800, "loss": 0.1867, "lr": 1.6622662266226625e-05, "epoch": 0.665016501650165, "percentage": 3.33, "elapsed_time": "0:13:46", "remaining_time": "6:40:42", "throughput": 1541.41, "total_tokens": 1274656} {"current_steps": 6050, "total_steps": 181800, "loss": 0.187, "lr": 1.6636413641364136e-05, "epoch": 0.6655665566556656, "percentage": 3.33, "elapsed_time": "0:13:47", "remaining_time": "6:40:42", "throughput": 1541.42, "total_tokens": 1275712} {"current_steps": 6055, "total_steps": 181800, "loss": 0.206, "lr": 1.665016501650165e-05, "epoch": 0.6661166116611661, "percentage": 3.33, "elapsed_time": "0:13:48", "remaining_time": "6:40:41", "throughput": 1541.39, "total_tokens": 1276736} {"current_steps": 6060, "total_steps": 181800, "loss": 0.1397, "lr": 1.6663916391639163e-05, "epoch": 0.6666666666666666, "percentage": 3.33, "elapsed_time": "0:13:48", "remaining_time": "6:40:40", "throughput": 1541.36, "total_tokens": 1277760} {"current_steps": 6065, "total_steps": 181800, "loss": 0.2564, "lr": 1.6677667766776678e-05, "epoch": 0.6672167216721672, "percentage": 3.34, "elapsed_time": "0:13:49", "remaining_time": "6:40:39", "throughput": 1541.37, "total_tokens": 1278816} {"current_steps": 6070, "total_steps": 181800, "loss": 0.1687, "lr": 1.669141914191419e-05, "epoch": 0.6677667766776678, "percentage": 3.34, "elapsed_time": "0:13:50", "remaining_time": "6:40:39", "throughput": 1541.37, "total_tokens": 1279872} {"current_steps": 6075, "total_steps": 181800, "loss": 0.1817, "lr": 1.6705170517051705e-05, "epoch": 0.6683168316831684, "percentage": 3.34, "elapsed_time": "0:13:51", "remaining_time": "6:40:38", "throughput": 1541.49, "total_tokens": 1281024} {"current_steps": 6080, "total_steps": 181800, "loss": 0.1869, "lr": 1.671892189218922e-05, "epoch": 0.6688668866886689, "percentage": 3.34, "elapsed_time": "0:13:51", "remaining_time": "6:40:37", "throughput": 1541.45, "total_tokens": 1282048} {"current_steps": 6085, "total_steps": 181800, "loss": 0.1697, "lr": 1.6732673267326735e-05, "epoch": 0.6694169416941694, "percentage": 3.35, "elapsed_time": "0:13:52", "remaining_time": "6:40:36", "throughput": 1541.46, "total_tokens": 1283104} {"current_steps": 6090, "total_steps": 181800, "loss": 0.1658, "lr": 1.6746424642464247e-05, "epoch": 0.66996699669967, "percentage": 3.35, "elapsed_time": "0:13:53", "remaining_time": "6:40:36", "throughput": 1541.47, "total_tokens": 1284160} {"current_steps": 6095, "total_steps": 181800, "loss": 0.1879, "lr": 1.676017601760176e-05, "epoch": 0.6705170517051705, "percentage": 3.35, "elapsed_time": "0:13:53", "remaining_time": "6:40:35", "throughput": 1541.4, "total_tokens": 1285152} {"current_steps": 6100, "total_steps": 181800, "loss": 0.1845, "lr": 1.6773927392739273e-05, "epoch": 0.671067106710671, "percentage": 3.36, "elapsed_time": "0:13:54", "remaining_time": "6:40:34", "throughput": 1541.45, "total_tokens": 1286240} {"current_steps": 6105, "total_steps": 181800, "loss": 0.1845, "lr": 1.678767876787679e-05, "epoch": 0.6716171617161716, "percentage": 3.36, "elapsed_time": "0:13:55", "remaining_time": "6:40:33", "throughput": 1541.49, "total_tokens": 1287328} {"current_steps": 6110, "total_steps": 181800, "loss": 0.1663, "lr": 1.6801430143014303e-05, "epoch": 0.6721672167216721, "percentage": 3.36, "elapsed_time": "0:13:55", "remaining_time": "6:40:33", "throughput": 1541.53, "total_tokens": 1288416} {"current_steps": 6115, "total_steps": 181800, "loss": 0.1348, "lr": 1.6815181518151815e-05, "epoch": 0.6727172717271728, "percentage": 3.36, "elapsed_time": "0:13:56", "remaining_time": "6:40:32", "throughput": 1541.61, "total_tokens": 1289536} {"current_steps": 6120, "total_steps": 181800, "loss": 0.2061, "lr": 1.682893289328933e-05, "epoch": 0.6732673267326733, "percentage": 3.37, "elapsed_time": "0:13:57", "remaining_time": "6:40:31", "throughput": 1541.62, "total_tokens": 1290592} {"current_steps": 6125, "total_steps": 181800, "loss": 0.1968, "lr": 1.6842684268426842e-05, "epoch": 0.6738173817381738, "percentage": 3.37, "elapsed_time": "0:13:57", "remaining_time": "6:40:30", "throughput": 1541.58, "total_tokens": 1291616} {"current_steps": 6130, "total_steps": 181800, "loss": 0.1733, "lr": 1.6856435643564357e-05, "epoch": 0.6743674367436744, "percentage": 3.37, "elapsed_time": "0:13:58", "remaining_time": "6:40:30", "throughput": 1541.58, "total_tokens": 1292672} {"current_steps": 6135, "total_steps": 181800, "loss": 0.244, "lr": 1.6870187018701872e-05, "epoch": 0.6749174917491749, "percentage": 3.37, "elapsed_time": "0:13:59", "remaining_time": "6:40:29", "throughput": 1541.59, "total_tokens": 1293728} {"current_steps": 6140, "total_steps": 181800, "loss": 0.108, "lr": 1.6883938393839387e-05, "epoch": 0.6754675467546755, "percentage": 3.38, "elapsed_time": "0:13:59", "remaining_time": "6:40:28", "throughput": 1541.59, "total_tokens": 1294784} {"current_steps": 6145, "total_steps": 181800, "loss": 0.1538, "lr": 1.68976897689769e-05, "epoch": 0.676017601760176, "percentage": 3.38, "elapsed_time": "0:14:00", "remaining_time": "6:40:31", "throughput": 1541.42, "total_tokens": 1295872} {"current_steps": 6150, "total_steps": 181800, "loss": 0.1218, "lr": 1.6911441144114414e-05, "epoch": 0.6765676567656765, "percentage": 3.38, "elapsed_time": "0:14:01", "remaining_time": "6:40:30", "throughput": 1541.39, "total_tokens": 1296896} {"current_steps": 6155, "total_steps": 181800, "loss": 0.1901, "lr": 1.6925192519251925e-05, "epoch": 0.6771177117711771, "percentage": 3.39, "elapsed_time": "0:14:02", "remaining_time": "6:40:29", "throughput": 1541.39, "total_tokens": 1297952} {"current_steps": 6160, "total_steps": 181800, "loss": 0.2241, "lr": 1.693894389438944e-05, "epoch": 0.6776677667766776, "percentage": 3.39, "elapsed_time": "0:14:02", "remaining_time": "6:40:29", "throughput": 1541.36, "total_tokens": 1298976} {"current_steps": 6165, "total_steps": 181800, "loss": 0.187, "lr": 1.6952695269526952e-05, "epoch": 0.6782178217821783, "percentage": 3.39, "elapsed_time": "0:14:03", "remaining_time": "6:40:28", "throughput": 1541.44, "total_tokens": 1300096} {"current_steps": 6170, "total_steps": 181800, "loss": 0.2302, "lr": 1.6966446644664467e-05, "epoch": 0.6787678767876788, "percentage": 3.39, "elapsed_time": "0:14:04", "remaining_time": "6:40:27", "throughput": 1541.44, "total_tokens": 1301152} {"current_steps": 6175, "total_steps": 181800, "loss": 0.2025, "lr": 1.6980198019801982e-05, "epoch": 0.6793179317931793, "percentage": 3.4, "elapsed_time": "0:14:04", "remaining_time": "6:40:26", "throughput": 1541.42, "total_tokens": 1302176} {"current_steps": 6180, "total_steps": 181800, "loss": 0.1512, "lr": 1.6993949394939497e-05, "epoch": 0.6798679867986799, "percentage": 3.4, "elapsed_time": "0:14:05", "remaining_time": "6:40:26", "throughput": 1541.42, "total_tokens": 1303232} {"current_steps": 6185, "total_steps": 181800, "loss": 0.1704, "lr": 1.700770077007701e-05, "epoch": 0.6804180418041804, "percentage": 3.4, "elapsed_time": "0:14:06", "remaining_time": "6:40:25", "throughput": 1541.47, "total_tokens": 1304320} {"current_steps": 6190, "total_steps": 181800, "loss": 0.1779, "lr": 1.7021452145214524e-05, "epoch": 0.680968096809681, "percentage": 3.4, "elapsed_time": "0:14:06", "remaining_time": "6:40:24", "throughput": 1541.41, "total_tokens": 1305312} {"current_steps": 6195, "total_steps": 181800, "loss": 0.2112, "lr": 1.7035203520352035e-05, "epoch": 0.6815181518151815, "percentage": 3.41, "elapsed_time": "0:14:07", "remaining_time": "6:40:23", "throughput": 1541.34, "total_tokens": 1306304} {"current_steps": 6200, "total_steps": 181800, "loss": 0.1721, "lr": 1.704895489548955e-05, "epoch": 0.682068206820682, "percentage": 3.41, "elapsed_time": "0:14:08", "remaining_time": "6:40:22", "throughput": 1541.31, "total_tokens": 1307328} {"current_steps": 6205, "total_steps": 181800, "loss": 0.2186, "lr": 1.7062706270627062e-05, "epoch": 0.6826182618261826, "percentage": 3.41, "elapsed_time": "0:14:08", "remaining_time": "6:40:22", "throughput": 1541.33, "total_tokens": 1308384} {"current_steps": 6210, "total_steps": 181800, "loss": 0.1838, "lr": 1.7076457645764577e-05, "epoch": 0.6831683168316832, "percentage": 3.42, "elapsed_time": "0:14:09", "remaining_time": "6:40:21", "throughput": 1541.34, "total_tokens": 1309440} {"current_steps": 6215, "total_steps": 181800, "loss": 0.1434, "lr": 1.709020902090209e-05, "epoch": 0.6837183718371838, "percentage": 3.42, "elapsed_time": "0:14:10", "remaining_time": "6:40:20", "throughput": 1541.39, "total_tokens": 1310528} {"current_steps": 6220, "total_steps": 181800, "loss": 0.2299, "lr": 1.7103960396039607e-05, "epoch": 0.6842684268426843, "percentage": 3.42, "elapsed_time": "0:14:10", "remaining_time": "6:40:19", "throughput": 1541.4, "total_tokens": 1311584} {"current_steps": 6225, "total_steps": 181800, "loss": 0.1855, "lr": 1.711771177117712e-05, "epoch": 0.6848184818481848, "percentage": 3.42, "elapsed_time": "0:14:11", "remaining_time": "6:40:18", "throughput": 1541.41, "total_tokens": 1312640} {"current_steps": 6230, "total_steps": 181800, "loss": 0.1552, "lr": 1.7131463146314634e-05, "epoch": 0.6853685368536854, "percentage": 3.43, "elapsed_time": "0:14:12", "remaining_time": "6:40:18", "throughput": 1541.41, "total_tokens": 1313696} {"current_steps": 6235, "total_steps": 181800, "loss": 0.1992, "lr": 1.7145214521452146e-05, "epoch": 0.6859185918591859, "percentage": 3.43, "elapsed_time": "0:14:12", "remaining_time": "6:40:17", "throughput": 1541.45, "total_tokens": 1314784} {"current_steps": 6240, "total_steps": 181800, "loss": 0.2354, "lr": 1.715896589658966e-05, "epoch": 0.6864686468646864, "percentage": 3.43, "elapsed_time": "0:14:13", "remaining_time": "6:40:16", "throughput": 1541.49, "total_tokens": 1315872} {"current_steps": 6245, "total_steps": 181800, "loss": 0.2047, "lr": 1.7172717271727172e-05, "epoch": 0.687018701870187, "percentage": 3.44, "elapsed_time": "0:14:14", "remaining_time": "6:40:15", "throughput": 1541.54, "total_tokens": 1316960} {"current_steps": 6250, "total_steps": 181800, "loss": 0.1645, "lr": 1.7186468646864687e-05, "epoch": 0.6875687568756875, "percentage": 3.44, "elapsed_time": "0:14:15", "remaining_time": "6:40:15", "throughput": 1541.54, "total_tokens": 1318016} {"current_steps": 6255, "total_steps": 181800, "loss": 0.2362, "lr": 1.72002200220022e-05, "epoch": 0.6881188118811881, "percentage": 3.44, "elapsed_time": "0:14:15", "remaining_time": "6:40:14", "throughput": 1541.54, "total_tokens": 1319072} {"current_steps": 6260, "total_steps": 181800, "loss": 0.1821, "lr": 1.7213971397139714e-05, "epoch": 0.6886688668866887, "percentage": 3.44, "elapsed_time": "0:14:16", "remaining_time": "6:40:13", "throughput": 1541.54, "total_tokens": 1320128} {"current_steps": 6265, "total_steps": 181800, "loss": 0.2023, "lr": 1.7227722772277226e-05, "epoch": 0.6892189218921893, "percentage": 3.45, "elapsed_time": "0:14:17", "remaining_time": "6:40:13", "throughput": 1541.54, "total_tokens": 1321184} {"current_steps": 6270, "total_steps": 181800, "loss": 0.1799, "lr": 1.7241474147414744e-05, "epoch": 0.6897689768976898, "percentage": 3.45, "elapsed_time": "0:14:17", "remaining_time": "6:40:12", "throughput": 1541.55, "total_tokens": 1322240} {"current_steps": 6275, "total_steps": 181800, "loss": 0.1476, "lr": 1.7255225522552256e-05, "epoch": 0.6903190319031903, "percentage": 3.45, "elapsed_time": "0:14:18", "remaining_time": "6:40:11", "throughput": 1541.55, "total_tokens": 1323296} {"current_steps": 6280, "total_steps": 181800, "loss": 0.1937, "lr": 1.726897689768977e-05, "epoch": 0.6908690869086909, "percentage": 3.45, "elapsed_time": "0:14:19", "remaining_time": "6:40:11", "throughput": 1541.52, "total_tokens": 1324320} {"current_steps": 6285, "total_steps": 181800, "loss": 0.2031, "lr": 1.7282728272827282e-05, "epoch": 0.6914191419141914, "percentage": 3.46, "elapsed_time": "0:14:19", "remaining_time": "6:40:10", "throughput": 1541.56, "total_tokens": 1325408} {"current_steps": 6290, "total_steps": 181800, "loss": 0.1691, "lr": 1.7296479647964798e-05, "epoch": 0.6919691969196919, "percentage": 3.46, "elapsed_time": "0:14:20", "remaining_time": "6:40:09", "throughput": 1541.6, "total_tokens": 1326496} {"current_steps": 6295, "total_steps": 181800, "loss": 0.3523, "lr": 1.731023102310231e-05, "epoch": 0.6925192519251925, "percentage": 3.46, "elapsed_time": "0:14:21", "remaining_time": "6:40:08", "throughput": 1541.64, "total_tokens": 1327584} {"current_steps": 6300, "total_steps": 181800, "loss": 0.1683, "lr": 1.7323982398239824e-05, "epoch": 0.693069306930693, "percentage": 3.47, "elapsed_time": "0:14:21", "remaining_time": "6:40:08", "throughput": 1541.65, "total_tokens": 1328640} {"current_steps": 6305, "total_steps": 181800, "loss": 0.1608, "lr": 1.733773377337734e-05, "epoch": 0.6936193619361937, "percentage": 3.47, "elapsed_time": "0:14:22", "remaining_time": "6:40:07", "throughput": 1541.69, "total_tokens": 1329728} {"current_steps": 6310, "total_steps": 181800, "loss": 0.2572, "lr": 1.735148514851485e-05, "epoch": 0.6941694169416942, "percentage": 3.47, "elapsed_time": "0:14:23", "remaining_time": "6:40:06", "throughput": 1541.74, "total_tokens": 1330816} {"current_steps": 6315, "total_steps": 181800, "loss": 0.1935, "lr": 1.7365236523652366e-05, "epoch": 0.6947194719471947, "percentage": 3.47, "elapsed_time": "0:14:23", "remaining_time": "6:40:05", "throughput": 1541.74, "total_tokens": 1331872} {"current_steps": 6320, "total_steps": 181800, "loss": 0.1793, "lr": 1.737898789878988e-05, "epoch": 0.6952695269526953, "percentage": 3.48, "elapsed_time": "0:14:24", "remaining_time": "6:40:05", "throughput": 1541.72, "total_tokens": 1332896} {"current_steps": 6325, "total_steps": 181800, "loss": 0.2187, "lr": 1.7392739273927393e-05, "epoch": 0.6958195819581958, "percentage": 3.48, "elapsed_time": "0:14:25", "remaining_time": "6:40:04", "throughput": 1541.73, "total_tokens": 1333952} {"current_steps": 6330, "total_steps": 181800, "loss": 0.1611, "lr": 1.7406490649064908e-05, "epoch": 0.6963696369636964, "percentage": 3.48, "elapsed_time": "0:14:25", "remaining_time": "6:40:03", "throughput": 1541.77, "total_tokens": 1335040} {"current_steps": 6335, "total_steps": 181800, "loss": 0.1242, "lr": 1.7420242024202423e-05, "epoch": 0.6969196919691969, "percentage": 3.48, "elapsed_time": "0:14:26", "remaining_time": "6:40:02", "throughput": 1541.78, "total_tokens": 1336096} {"current_steps": 6340, "total_steps": 181800, "loss": 0.1944, "lr": 1.7433993399339934e-05, "epoch": 0.6974697469746974, "percentage": 3.49, "elapsed_time": "0:14:27", "remaining_time": "6:40:01", "throughput": 1541.79, "total_tokens": 1337152} {"current_steps": 6345, "total_steps": 181800, "loss": 0.1615, "lr": 1.744774477447745e-05, "epoch": 0.698019801980198, "percentage": 3.49, "elapsed_time": "0:14:27", "remaining_time": "6:40:00", "throughput": 1541.88, "total_tokens": 1338272} {"current_steps": 6350, "total_steps": 181800, "loss": 0.1678, "lr": 1.746149614961496e-05, "epoch": 0.6985698569856986, "percentage": 3.49, "elapsed_time": "0:14:28", "remaining_time": "6:40:00", "throughput": 1541.84, "total_tokens": 1339296} {"current_steps": 6355, "total_steps": 181800, "loss": 0.1572, "lr": 1.7475247524752476e-05, "epoch": 0.6991199119911992, "percentage": 3.5, "elapsed_time": "0:14:29", "remaining_time": "6:39:59", "throughput": 1541.81, "total_tokens": 1340320} {"current_steps": 6360, "total_steps": 181800, "loss": 0.203, "lr": 1.748899889988999e-05, "epoch": 0.6996699669966997, "percentage": 3.5, "elapsed_time": "0:14:29", "remaining_time": "6:39:58", "throughput": 1541.85, "total_tokens": 1341408} {"current_steps": 6365, "total_steps": 181800, "loss": 0.1814, "lr": 1.7502750275027506e-05, "epoch": 0.7002200220022002, "percentage": 3.5, "elapsed_time": "0:14:30", "remaining_time": "6:39:58", "throughput": 1541.81, "total_tokens": 1342432} {"current_steps": 6370, "total_steps": 181800, "loss": 0.2677, "lr": 1.7516501650165018e-05, "epoch": 0.7007700770077008, "percentage": 3.5, "elapsed_time": "0:14:31", "remaining_time": "6:39:57", "throughput": 1541.78, "total_tokens": 1343456} {"current_steps": 6375, "total_steps": 181800, "loss": 0.1672, "lr": 1.7530253025302533e-05, "epoch": 0.7013201320132013, "percentage": 3.51, "elapsed_time": "0:14:32", "remaining_time": "6:39:56", "throughput": 1541.79, "total_tokens": 1344512} {"current_steps": 6380, "total_steps": 181800, "loss": 0.1529, "lr": 1.7544004400440045e-05, "epoch": 0.7018701870187019, "percentage": 3.51, "elapsed_time": "0:14:32", "remaining_time": "6:39:55", "throughput": 1541.72, "total_tokens": 1345504} {"current_steps": 6385, "total_steps": 181800, "loss": 0.1816, "lr": 1.755775577557756e-05, "epoch": 0.7024202420242024, "percentage": 3.51, "elapsed_time": "0:14:33", "remaining_time": "6:39:55", "throughput": 1541.72, "total_tokens": 1346560} {"current_steps": 6390, "total_steps": 181800, "loss": 0.2441, "lr": 1.757150715071507e-05, "epoch": 0.7029702970297029, "percentage": 3.51, "elapsed_time": "0:14:34", "remaining_time": "6:39:54", "throughput": 1541.77, "total_tokens": 1347648} {"current_steps": 6395, "total_steps": 181800, "loss": 0.1423, "lr": 1.7585258525852586e-05, "epoch": 0.7035203520352035, "percentage": 3.52, "elapsed_time": "0:14:34", "remaining_time": "6:39:53", "throughput": 1541.77, "total_tokens": 1348704} {"current_steps": 6400, "total_steps": 181800, "loss": 0.1684, "lr": 1.7599009900990098e-05, "epoch": 0.7040704070407041, "percentage": 3.52, "elapsed_time": "0:14:35", "remaining_time": "6:39:53", "throughput": 1541.85, "total_tokens": 1349824} {"current_steps": 6405, "total_steps": 181800, "loss": 0.138, "lr": 1.7612761276127613e-05, "epoch": 0.7046204620462047, "percentage": 3.52, "elapsed_time": "0:14:36", "remaining_time": "6:39:52", "throughput": 1541.78, "total_tokens": 1350816} {"current_steps": 6410, "total_steps": 181800, "loss": 0.2768, "lr": 1.7626512651265128e-05, "epoch": 0.7051705170517052, "percentage": 3.53, "elapsed_time": "0:14:36", "remaining_time": "6:39:51", "throughput": 1541.76, "total_tokens": 1351840} {"current_steps": 6415, "total_steps": 181800, "loss": 0.1551, "lr": 1.7640264026402643e-05, "epoch": 0.7057205720572057, "percentage": 3.53, "elapsed_time": "0:14:37", "remaining_time": "6:39:50", "throughput": 1541.76, "total_tokens": 1352896} {"current_steps": 6420, "total_steps": 181800, "loss": 0.1801, "lr": 1.7654015401540155e-05, "epoch": 0.7062706270627063, "percentage": 3.53, "elapsed_time": "0:14:38", "remaining_time": "6:39:49", "throughput": 1541.85, "total_tokens": 1354016} {"current_steps": 6425, "total_steps": 181800, "loss": 0.1614, "lr": 1.766776677667767e-05, "epoch": 0.7068206820682068, "percentage": 3.53, "elapsed_time": "0:14:38", "remaining_time": "6:39:49", "throughput": 1541.89, "total_tokens": 1355104} {"current_steps": 6430, "total_steps": 181800, "loss": 0.1951, "lr": 1.768151815181518e-05, "epoch": 0.7073707370737073, "percentage": 3.54, "elapsed_time": "0:14:39", "remaining_time": "6:39:48", "throughput": 1541.87, "total_tokens": 1356128} {"current_steps": 6435, "total_steps": 181800, "loss": 0.1501, "lr": 1.7695269526952696e-05, "epoch": 0.7079207920792079, "percentage": 3.54, "elapsed_time": "0:14:40", "remaining_time": "6:39:47", "throughput": 1541.88, "total_tokens": 1357184} {"current_steps": 6440, "total_steps": 181800, "loss": 0.1305, "lr": 1.7709020902090208e-05, "epoch": 0.7084708470847084, "percentage": 3.54, "elapsed_time": "0:14:40", "remaining_time": "6:39:46", "throughput": 1541.85, "total_tokens": 1358208} {"current_steps": 6445, "total_steps": 181800, "loss": 0.2515, "lr": 1.7722772277227723e-05, "epoch": 0.7090209020902091, "percentage": 3.55, "elapsed_time": "0:14:41", "remaining_time": "6:39:45", "throughput": 1541.82, "total_tokens": 1359232} {"current_steps": 6450, "total_steps": 181800, "loss": 0.1766, "lr": 1.7736523652365235e-05, "epoch": 0.7095709570957096, "percentage": 3.55, "elapsed_time": "0:14:42", "remaining_time": "6:39:44", "throughput": 1541.83, "total_tokens": 1360288} {"current_steps": 6455, "total_steps": 181800, "loss": 0.1804, "lr": 1.7750275027502753e-05, "epoch": 0.7101210121012101, "percentage": 3.55, "elapsed_time": "0:14:42", "remaining_time": "6:39:44", "throughput": 1541.84, "total_tokens": 1361344} {"current_steps": 6460, "total_steps": 181800, "loss": 0.1666, "lr": 1.7764026402640265e-05, "epoch": 0.7106710671067107, "percentage": 3.55, "elapsed_time": "0:14:43", "remaining_time": "6:39:43", "throughput": 1541.89, "total_tokens": 1362432} {"current_steps": 6465, "total_steps": 181800, "loss": 0.1728, "lr": 1.777777777777778e-05, "epoch": 0.7112211221122112, "percentage": 3.56, "elapsed_time": "0:14:44", "remaining_time": "6:39:42", "throughput": 1541.9, "total_tokens": 1363488} {"current_steps": 6470, "total_steps": 181800, "loss": 0.1601, "lr": 1.779152915291529e-05, "epoch": 0.7117711771177118, "percentage": 3.56, "elapsed_time": "0:14:44", "remaining_time": "6:39:41", "throughput": 1541.98, "total_tokens": 1364608} {"current_steps": 6475, "total_steps": 181800, "loss": 0.196, "lr": 1.7805280528052807e-05, "epoch": 0.7123212321232123, "percentage": 3.56, "elapsed_time": "0:14:45", "remaining_time": "6:39:41", "throughput": 1541.9, "total_tokens": 1365600} {"current_steps": 6480, "total_steps": 181800, "loss": 0.1712, "lr": 1.781903190319032e-05, "epoch": 0.7128712871287128, "percentage": 3.56, "elapsed_time": "0:14:46", "remaining_time": "6:39:40", "throughput": 1541.87, "total_tokens": 1366624} {"current_steps": 6485, "total_steps": 181800, "loss": 0.2421, "lr": 1.7832783278327833e-05, "epoch": 0.7134213421342134, "percentage": 3.57, "elapsed_time": "0:14:47", "remaining_time": "6:39:39", "throughput": 1541.81, "total_tokens": 1367616} {"current_steps": 6490, "total_steps": 181800, "loss": 0.1633, "lr": 1.7846534653465345e-05, "epoch": 0.713971397139714, "percentage": 3.57, "elapsed_time": "0:14:47", "remaining_time": "6:39:38", "throughput": 1541.9, "total_tokens": 1368736} {"current_steps": 6495, "total_steps": 181800, "loss": 0.2204, "lr": 1.786028602860286e-05, "epoch": 0.7145214521452146, "percentage": 3.57, "elapsed_time": "0:14:48", "remaining_time": "6:39:38", "throughput": 1541.9, "total_tokens": 1369792} {"current_steps": 6500, "total_steps": 181800, "loss": 0.2101, "lr": 1.7874037403740375e-05, "epoch": 0.7150715071507151, "percentage": 3.58, "elapsed_time": "0:14:49", "remaining_time": "6:39:37", "throughput": 1541.94, "total_tokens": 1370880} {"current_steps": 6505, "total_steps": 181800, "loss": 0.2164, "lr": 1.788778877887789e-05, "epoch": 0.7156215621562156, "percentage": 3.58, "elapsed_time": "0:14:49", "remaining_time": "6:39:36", "throughput": 1541.98, "total_tokens": 1371968} {"current_steps": 6510, "total_steps": 181800, "loss": 0.2181, "lr": 1.7901540154015402e-05, "epoch": 0.7161716171617162, "percentage": 3.58, "elapsed_time": "0:14:50", "remaining_time": "6:39:35", "throughput": 1542.05, "total_tokens": 1373088} {"current_steps": 6515, "total_steps": 181800, "loss": 0.1697, "lr": 1.7915291529152917e-05, "epoch": 0.7167216721672167, "percentage": 3.58, "elapsed_time": "0:14:51", "remaining_time": "6:39:35", "throughput": 1542.02, "total_tokens": 1374112} {"current_steps": 6520, "total_steps": 181800, "loss": 0.2059, "lr": 1.792904290429043e-05, "epoch": 0.7172717271727173, "percentage": 3.59, "elapsed_time": "0:14:51", "remaining_time": "6:39:34", "throughput": 1542.07, "total_tokens": 1375200} {"current_steps": 6525, "total_steps": 181800, "loss": 0.1715, "lr": 1.7942794279427944e-05, "epoch": 0.7178217821782178, "percentage": 3.59, "elapsed_time": "0:14:52", "remaining_time": "6:39:33", "throughput": 1542.03, "total_tokens": 1376224} {"current_steps": 6530, "total_steps": 181800, "loss": 0.2316, "lr": 1.795654565456546e-05, "epoch": 0.7183718371837183, "percentage": 3.59, "elapsed_time": "0:14:53", "remaining_time": "6:39:32", "throughput": 1542.11, "total_tokens": 1377344} {"current_steps": 6535, "total_steps": 181800, "loss": 0.2082, "lr": 1.797029702970297e-05, "epoch": 0.7189218921892189, "percentage": 3.59, "elapsed_time": "0:14:53", "remaining_time": "6:39:32", "throughput": 1542.11, "total_tokens": 1378400} {"current_steps": 6540, "total_steps": 181800, "loss": 0.2458, "lr": 1.7984048404840485e-05, "epoch": 0.7194719471947195, "percentage": 3.6, "elapsed_time": "0:14:54", "remaining_time": "6:39:31", "throughput": 1542.19, "total_tokens": 1379520} {"current_steps": 6545, "total_steps": 181800, "loss": 0.202, "lr": 1.7997799779977997e-05, "epoch": 0.7200220022002201, "percentage": 3.6, "elapsed_time": "0:14:55", "remaining_time": "6:39:30", "throughput": 1542.16, "total_tokens": 1380544} {"current_steps": 6550, "total_steps": 181800, "loss": 0.178, "lr": 1.8011551155115512e-05, "epoch": 0.7205720572057206, "percentage": 3.6, "elapsed_time": "0:14:55", "remaining_time": "6:39:30", "throughput": 1542.16, "total_tokens": 1381600} {"current_steps": 6555, "total_steps": 181800, "loss": 0.1612, "lr": 1.8025302530253027e-05, "epoch": 0.7211221122112211, "percentage": 3.61, "elapsed_time": "0:14:56", "remaining_time": "6:39:29", "throughput": 1542.2, "total_tokens": 1382688} {"current_steps": 6560, "total_steps": 181800, "loss": 0.2209, "lr": 1.8039053905390542e-05, "epoch": 0.7216721672167217, "percentage": 3.61, "elapsed_time": "0:14:57", "remaining_time": "6:39:28", "throughput": 1542.24, "total_tokens": 1383776} {"current_steps": 6565, "total_steps": 181800, "loss": 0.168, "lr": 1.8052805280528054e-05, "epoch": 0.7222222222222222, "percentage": 3.61, "elapsed_time": "0:14:57", "remaining_time": "6:39:27", "throughput": 1542.14, "total_tokens": 1384736} {"current_steps": 6570, "total_steps": 181800, "loss": 0.1895, "lr": 1.806655665566557e-05, "epoch": 0.7227722772277227, "percentage": 3.61, "elapsed_time": "0:14:58", "remaining_time": "6:39:27", "throughput": 1542.12, "total_tokens": 1385760} {"current_steps": 6575, "total_steps": 181800, "loss": 0.305, "lr": 1.808030803080308e-05, "epoch": 0.7233223322332233, "percentage": 3.62, "elapsed_time": "0:14:59", "remaining_time": "6:39:26", "throughput": 1542.12, "total_tokens": 1386816} {"current_steps": 6580, "total_steps": 181800, "loss": 0.1997, "lr": 1.8094059405940595e-05, "epoch": 0.7238723872387238, "percentage": 3.62, "elapsed_time": "0:14:59", "remaining_time": "6:39:25", "throughput": 1542.12, "total_tokens": 1387872} {"current_steps": 6585, "total_steps": 181800, "loss": 0.1929, "lr": 1.8107810781078107e-05, "epoch": 0.7244224422442245, "percentage": 3.62, "elapsed_time": "0:15:00", "remaining_time": "6:39:25", "throughput": 1542.08, "total_tokens": 1388896} {"current_steps": 6590, "total_steps": 181800, "loss": 0.1612, "lr": 1.8121562156215622e-05, "epoch": 0.724972497249725, "percentage": 3.62, "elapsed_time": "0:15:01", "remaining_time": "6:39:24", "throughput": 1542.15, "total_tokens": 1390016} {"current_steps": 6595, "total_steps": 181800, "loss": 0.2277, "lr": 1.8135313531353137e-05, "epoch": 0.7255225522552256, "percentage": 3.63, "elapsed_time": "0:15:02", "remaining_time": "6:39:23", "throughput": 1542.15, "total_tokens": 1391072} {"current_steps": 6600, "total_steps": 181800, "loss": 0.2162, "lr": 1.8149064906490652e-05, "epoch": 0.7260726072607261, "percentage": 3.63, "elapsed_time": "0:15:02", "remaining_time": "6:39:22", "throughput": 1542.16, "total_tokens": 1392128} {"current_steps": 6605, "total_steps": 181800, "loss": 0.3241, "lr": 1.8162816281628164e-05, "epoch": 0.7266226622662266, "percentage": 3.63, "elapsed_time": "0:15:03", "remaining_time": "6:39:22", "throughput": 1542.19, "total_tokens": 1393216} {"current_steps": 6610, "total_steps": 181800, "loss": 0.2, "lr": 1.817656765676568e-05, "epoch": 0.7271727172717272, "percentage": 3.64, "elapsed_time": "0:15:04", "remaining_time": "6:39:21", "throughput": 1542.23, "total_tokens": 1394304} {"current_steps": 6615, "total_steps": 181800, "loss": 0.1418, "lr": 1.819031903190319e-05, "epoch": 0.7277227722772277, "percentage": 3.64, "elapsed_time": "0:15:04", "remaining_time": "6:39:20", "throughput": 1542.27, "total_tokens": 1395392} {"current_steps": 6620, "total_steps": 181800, "loss": 0.14, "lr": 1.8204070407040706e-05, "epoch": 0.7282728272827282, "percentage": 3.64, "elapsed_time": "0:15:05", "remaining_time": "6:39:20", "throughput": 1542.31, "total_tokens": 1396480} {"current_steps": 6625, "total_steps": 181800, "loss": 0.1661, "lr": 1.8217821782178217e-05, "epoch": 0.7288228822882288, "percentage": 3.64, "elapsed_time": "0:15:06", "remaining_time": "6:39:19", "throughput": 1542.32, "total_tokens": 1397536} {"current_steps": 6630, "total_steps": 181800, "loss": 0.1748, "lr": 1.8231573157315732e-05, "epoch": 0.7293729372937293, "percentage": 3.65, "elapsed_time": "0:15:06", "remaining_time": "6:39:18", "throughput": 1542.37, "total_tokens": 1398624} {"current_steps": 6635, "total_steps": 181800, "loss": 0.1567, "lr": 1.8245324532453244e-05, "epoch": 0.72992299229923, "percentage": 3.65, "elapsed_time": "0:15:07", "remaining_time": "6:39:17", "throughput": 1542.41, "total_tokens": 1399712} {"current_steps": 6640, "total_steps": 181800, "loss": 0.252, "lr": 1.825907590759076e-05, "epoch": 0.7304730473047305, "percentage": 3.65, "elapsed_time": "0:15:08", "remaining_time": "6:39:16", "throughput": 1542.42, "total_tokens": 1400768} {"current_steps": 6645, "total_steps": 181800, "loss": 0.1744, "lr": 1.8272827282728274e-05, "epoch": 0.731023102310231, "percentage": 3.66, "elapsed_time": "0:15:08", "remaining_time": "6:39:16", "throughput": 1542.43, "total_tokens": 1401824} {"current_steps": 6650, "total_steps": 181800, "loss": 0.1749, "lr": 1.828657865786579e-05, "epoch": 0.7315731573157316, "percentage": 3.66, "elapsed_time": "0:15:09", "remaining_time": "6:39:15", "throughput": 1542.48, "total_tokens": 1402912} {"current_steps": 6655, "total_steps": 181800, "loss": 0.171, "lr": 1.83003300330033e-05, "epoch": 0.7321232123212321, "percentage": 3.66, "elapsed_time": "0:15:10", "remaining_time": "6:39:14", "throughput": 1542.42, "total_tokens": 1403904} {"current_steps": 6660, "total_steps": 181800, "loss": 0.1637, "lr": 1.8314081408140816e-05, "epoch": 0.7326732673267327, "percentage": 3.66, "elapsed_time": "0:15:10", "remaining_time": "6:39:13", "throughput": 1542.46, "total_tokens": 1404992} {"current_steps": 6665, "total_steps": 181800, "loss": 0.1631, "lr": 1.8327832783278328e-05, "epoch": 0.7332233223322332, "percentage": 3.67, "elapsed_time": "0:15:11", "remaining_time": "6:39:12", "throughput": 1542.5, "total_tokens": 1406080} {"current_steps": 6670, "total_steps": 181800, "loss": 0.1751, "lr": 1.8341584158415843e-05, "epoch": 0.7337733773377337, "percentage": 3.67, "elapsed_time": "0:15:12", "remaining_time": "6:39:12", "throughput": 1542.5, "total_tokens": 1407136} {"current_steps": 6675, "total_steps": 181800, "loss": 0.128, "lr": 1.8355335533553354e-05, "epoch": 0.7343234323432343, "percentage": 3.67, "elapsed_time": "0:15:12", "remaining_time": "6:39:11", "throughput": 1542.51, "total_tokens": 1408192} {"current_steps": 6680, "total_steps": 181800, "loss": 0.1719, "lr": 1.836908690869087e-05, "epoch": 0.7348734873487349, "percentage": 3.67, "elapsed_time": "0:15:13", "remaining_time": "6:39:10", "throughput": 1542.44, "total_tokens": 1409184} {"current_steps": 6685, "total_steps": 181800, "loss": 0.2397, "lr": 1.838283828382838e-05, "epoch": 0.7354235423542355, "percentage": 3.68, "elapsed_time": "0:15:14", "remaining_time": "6:39:09", "throughput": 1542.45, "total_tokens": 1410240} {"current_steps": 6690, "total_steps": 181800, "loss": 0.1982, "lr": 1.83965896589659e-05, "epoch": 0.735973597359736, "percentage": 3.68, "elapsed_time": "0:15:14", "remaining_time": "6:39:09", "throughput": 1542.45, "total_tokens": 1411296} {"current_steps": 6695, "total_steps": 181800, "loss": 0.2224, "lr": 1.841034103410341e-05, "epoch": 0.7365236523652365, "percentage": 3.68, "elapsed_time": "0:15:15", "remaining_time": "6:39:08", "throughput": 1542.41, "total_tokens": 1412320} {"current_steps": 6700, "total_steps": 181800, "loss": 0.1438, "lr": 1.8424092409240926e-05, "epoch": 0.7370737073707371, "percentage": 3.69, "elapsed_time": "0:15:16", "remaining_time": "6:39:07", "throughput": 1542.41, "total_tokens": 1413376} {"current_steps": 6705, "total_steps": 181800, "loss": 0.1887, "lr": 1.8437843784378438e-05, "epoch": 0.7376237623762376, "percentage": 3.69, "elapsed_time": "0:15:17", "remaining_time": "6:39:07", "throughput": 1542.35, "total_tokens": 1414368} {"current_steps": 6710, "total_steps": 181800, "loss": 0.1914, "lr": 1.8451595159515953e-05, "epoch": 0.7381738173817382, "percentage": 3.69, "elapsed_time": "0:15:17", "remaining_time": "6:39:06", "throughput": 1542.39, "total_tokens": 1415456} {"current_steps": 6715, "total_steps": 181800, "loss": 0.1972, "lr": 1.8465346534653464e-05, "epoch": 0.7387238723872387, "percentage": 3.69, "elapsed_time": "0:15:18", "remaining_time": "6:39:05", "throughput": 1542.46, "total_tokens": 1416576} {"current_steps": 6720, "total_steps": 181800, "loss": 0.1528, "lr": 1.847909790979098e-05, "epoch": 0.7392739273927392, "percentage": 3.7, "elapsed_time": "0:15:19", "remaining_time": "6:39:05", "throughput": 1542.46, "total_tokens": 1417632} {"current_steps": 6725, "total_steps": 181800, "loss": 0.2081, "lr": 1.8492849284928494e-05, "epoch": 0.7398239823982399, "percentage": 3.7, "elapsed_time": "0:15:19", "remaining_time": "6:39:04", "throughput": 1542.37, "total_tokens": 1418592} {"current_steps": 6730, "total_steps": 181800, "loss": 0.2025, "lr": 1.8506600660066006e-05, "epoch": 0.7403740374037404, "percentage": 3.7, "elapsed_time": "0:15:20", "remaining_time": "6:39:03", "throughput": 1542.44, "total_tokens": 1419712} {"current_steps": 6735, "total_steps": 181800, "loss": 0.2201, "lr": 1.852035203520352e-05, "epoch": 0.740924092409241, "percentage": 3.7, "elapsed_time": "0:15:21", "remaining_time": "6:39:02", "throughput": 1542.52, "total_tokens": 1420832} {"current_steps": 6740, "total_steps": 181800, "loss": 0.1469, "lr": 1.8534103410341036e-05, "epoch": 0.7414741474147415, "percentage": 3.71, "elapsed_time": "0:15:21", "remaining_time": "6:39:01", "throughput": 1542.56, "total_tokens": 1421920} {"current_steps": 6745, "total_steps": 181800, "loss": 0.1674, "lr": 1.8547854785478548e-05, "epoch": 0.742024202420242, "percentage": 3.71, "elapsed_time": "0:15:22", "remaining_time": "6:39:01", "throughput": 1542.6, "total_tokens": 1423008} {"current_steps": 6750, "total_steps": 181800, "loss": 0.1979, "lr": 1.8561606160616063e-05, "epoch": 0.7425742574257426, "percentage": 3.71, "elapsed_time": "0:15:23", "remaining_time": "6:39:00", "throughput": 1542.53, "total_tokens": 1424000} {"current_steps": 6755, "total_steps": 181800, "loss": 0.1227, "lr": 1.8575357535753578e-05, "epoch": 0.7431243124312431, "percentage": 3.72, "elapsed_time": "0:15:23", "remaining_time": "6:38:59", "throughput": 1542.46, "total_tokens": 1424992} {"current_steps": 6760, "total_steps": 181800, "loss": 0.2074, "lr": 1.858910891089109e-05, "epoch": 0.7436743674367436, "percentage": 3.72, "elapsed_time": "0:15:24", "remaining_time": "6:38:59", "throughput": 1542.43, "total_tokens": 1426016} {"current_steps": 6765, "total_steps": 181800, "loss": 0.1392, "lr": 1.8602860286028605e-05, "epoch": 0.7442244224422442, "percentage": 3.72, "elapsed_time": "0:15:25", "remaining_time": "6:38:58", "throughput": 1542.36, "total_tokens": 1427008} {"current_steps": 6770, "total_steps": 181800, "loss": 0.1553, "lr": 1.8616611661166116e-05, "epoch": 0.7447744774477447, "percentage": 3.72, "elapsed_time": "0:15:25", "remaining_time": "6:38:57", "throughput": 1542.4, "total_tokens": 1428096} {"current_steps": 6775, "total_steps": 181800, "loss": 0.2236, "lr": 1.863036303630363e-05, "epoch": 0.7453245324532454, "percentage": 3.73, "elapsed_time": "0:15:26", "remaining_time": "6:38:57", "throughput": 1542.47, "total_tokens": 1429216} {"current_steps": 6780, "total_steps": 181800, "loss": 0.1755, "lr": 1.8644114411441143e-05, "epoch": 0.7458745874587459, "percentage": 3.73, "elapsed_time": "0:15:27", "remaining_time": "6:38:56", "throughput": 1542.46, "total_tokens": 1430272} {"current_steps": 6785, "total_steps": 181800, "loss": 0.1944, "lr": 1.865786578657866e-05, "epoch": 0.7464246424642464, "percentage": 3.73, "elapsed_time": "0:15:27", "remaining_time": "6:38:55", "throughput": 1542.43, "total_tokens": 1431296} {"current_steps": 6790, "total_steps": 181800, "loss": 0.2115, "lr": 1.8671617161716173e-05, "epoch": 0.746974697469747, "percentage": 3.73, "elapsed_time": "0:15:28", "remaining_time": "6:38:55", "throughput": 1542.47, "total_tokens": 1432384} {"current_steps": 6795, "total_steps": 181800, "loss": 0.1885, "lr": 1.8685368536853688e-05, "epoch": 0.7475247524752475, "percentage": 3.74, "elapsed_time": "0:15:29", "remaining_time": "6:38:54", "throughput": 1542.47, "total_tokens": 1433440} {"current_steps": 6800, "total_steps": 181800, "loss": 0.1841, "lr": 1.86991199119912e-05, "epoch": 0.7480748074807481, "percentage": 3.74, "elapsed_time": "0:15:29", "remaining_time": "6:38:53", "throughput": 1542.41, "total_tokens": 1434432} {"current_steps": 6805, "total_steps": 181800, "loss": 0.1399, "lr": 1.8712871287128715e-05, "epoch": 0.7486248624862486, "percentage": 3.74, "elapsed_time": "0:15:30", "remaining_time": "6:38:53", "throughput": 1542.41, "total_tokens": 1435488} {"current_steps": 6810, "total_steps": 181800, "loss": 0.2109, "lr": 1.8726622662266227e-05, "epoch": 0.7491749174917491, "percentage": 3.75, "elapsed_time": "0:15:31", "remaining_time": "6:38:52", "throughput": 1542.37, "total_tokens": 1436512} {"current_steps": 6815, "total_steps": 181800, "loss": 0.1586, "lr": 1.874037403740374e-05, "epoch": 0.7497249724972497, "percentage": 3.75, "elapsed_time": "0:15:32", "remaining_time": "6:38:51", "throughput": 1542.3, "total_tokens": 1437504} {"current_steps": 6820, "total_steps": 181800, "loss": 0.122, "lr": 1.8754125412541253e-05, "epoch": 0.7502750275027503, "percentage": 3.75, "elapsed_time": "0:15:32", "remaining_time": "6:38:51", "throughput": 1542.34, "total_tokens": 1438592} {"current_steps": 6825, "total_steps": 181800, "loss": 0.155, "lr": 1.8767876787678768e-05, "epoch": 0.7508250825082509, "percentage": 3.75, "elapsed_time": "0:15:33", "remaining_time": "6:38:50", "throughput": 1542.34, "total_tokens": 1439648} {"current_steps": 6830, "total_steps": 181800, "loss": 0.1955, "lr": 1.8781628162816283e-05, "epoch": 0.7513751375137514, "percentage": 3.76, "elapsed_time": "0:15:34", "remaining_time": "6:38:49", "throughput": 1542.28, "total_tokens": 1440640} {"current_steps": 6835, "total_steps": 181800, "loss": 0.1462, "lr": 1.87953795379538e-05, "epoch": 0.7519251925192519, "percentage": 3.76, "elapsed_time": "0:15:34", "remaining_time": "6:38:48", "throughput": 1542.28, "total_tokens": 1441696} {"current_steps": 6840, "total_steps": 181800, "loss": 0.2292, "lr": 1.880913091309131e-05, "epoch": 0.7524752475247525, "percentage": 3.76, "elapsed_time": "0:15:35", "remaining_time": "6:38:48", "throughput": 1542.25, "total_tokens": 1442720} {"current_steps": 6845, "total_steps": 181800, "loss": 0.2, "lr": 1.8822882288228825e-05, "epoch": 0.753025302530253, "percentage": 3.77, "elapsed_time": "0:15:36", "remaining_time": "6:38:47", "throughput": 1542.22, "total_tokens": 1443744} {"current_steps": 6850, "total_steps": 181800, "loss": 0.1511, "lr": 1.8836633663366337e-05, "epoch": 0.7535753575357536, "percentage": 3.77, "elapsed_time": "0:15:36", "remaining_time": "6:38:46", "throughput": 1542.37, "total_tokens": 1444928} {"current_steps": 6855, "total_steps": 181800, "loss": 0.1977, "lr": 1.8850385038503852e-05, "epoch": 0.7541254125412541, "percentage": 3.77, "elapsed_time": "0:15:37", "remaining_time": "6:38:45", "throughput": 1542.44, "total_tokens": 1446048} {"current_steps": 6860, "total_steps": 181800, "loss": 0.1274, "lr": 1.8864136413641363e-05, "epoch": 0.7546754675467546, "percentage": 3.77, "elapsed_time": "0:15:38", "remaining_time": "6:38:45", "throughput": 1542.39, "total_tokens": 1447040} {"current_steps": 6865, "total_steps": 181800, "loss": 0.2516, "lr": 1.887788778877888e-05, "epoch": 0.7552255225522553, "percentage": 3.78, "elapsed_time": "0:15:38", "remaining_time": "6:38:44", "throughput": 1542.39, "total_tokens": 1448096} {"current_steps": 6870, "total_steps": 181800, "loss": 0.2188, "lr": 1.889163916391639e-05, "epoch": 0.7557755775577558, "percentage": 3.78, "elapsed_time": "0:15:39", "remaining_time": "6:38:43", "throughput": 1542.44, "total_tokens": 1449184} {"current_steps": 6875, "total_steps": 181800, "loss": 0.1195, "lr": 1.890539053905391e-05, "epoch": 0.7563256325632564, "percentage": 3.78, "elapsed_time": "0:15:40", "remaining_time": "6:38:42", "throughput": 1542.45, "total_tokens": 1450240} {"current_steps": 6880, "total_steps": 181800, "loss": 0.159, "lr": 1.891914191419142e-05, "epoch": 0.7568756875687569, "percentage": 3.78, "elapsed_time": "0:15:40", "remaining_time": "6:38:41", "throughput": 1542.45, "total_tokens": 1451296} {"current_steps": 6885, "total_steps": 181800, "loss": 0.2173, "lr": 1.8932893289328935e-05, "epoch": 0.7574257425742574, "percentage": 3.79, "elapsed_time": "0:15:41", "remaining_time": "6:38:41", "throughput": 1542.45, "total_tokens": 1452352} {"current_steps": 6890, "total_steps": 181800, "loss": 0.1984, "lr": 1.8946644664466447e-05, "epoch": 0.757975797579758, "percentage": 3.79, "elapsed_time": "0:15:42", "remaining_time": "6:38:40", "throughput": 1542.45, "total_tokens": 1453408} {"current_steps": 6895, "total_steps": 181800, "loss": 0.1539, "lr": 1.8960396039603962e-05, "epoch": 0.7585258525852585, "percentage": 3.79, "elapsed_time": "0:15:42", "remaining_time": "6:38:39", "throughput": 1542.59, "total_tokens": 1454592} {"current_steps": 6900, "total_steps": 181800, "loss": 0.2109, "lr": 1.8974147414741474e-05, "epoch": 0.759075907590759, "percentage": 3.8, "elapsed_time": "0:15:43", "remaining_time": "6:38:39", "throughput": 1542.53, "total_tokens": 1455584} {"current_steps": 6905, "total_steps": 181800, "loss": 0.1882, "lr": 1.898789878987899e-05, "epoch": 0.7596259625962596, "percentage": 3.8, "elapsed_time": "0:15:44", "remaining_time": "6:38:38", "throughput": 1542.5, "total_tokens": 1456608} {"current_steps": 6910, "total_steps": 181800, "loss": 0.1257, "lr": 1.90016501650165e-05, "epoch": 0.7601760176017601, "percentage": 3.8, "elapsed_time": "0:15:44", "remaining_time": "6:38:37", "throughput": 1542.61, "total_tokens": 1457760} {"current_steps": 6915, "total_steps": 181800, "loss": 0.1835, "lr": 1.9015401540154015e-05, "epoch": 0.7607260726072608, "percentage": 3.8, "elapsed_time": "0:15:45", "remaining_time": "6:38:36", "throughput": 1542.54, "total_tokens": 1458752} {"current_steps": 6920, "total_steps": 181800, "loss": 0.1837, "lr": 1.902915291529153e-05, "epoch": 0.7612761276127613, "percentage": 3.81, "elapsed_time": "0:15:46", "remaining_time": "6:38:36", "throughput": 1542.55, "total_tokens": 1459808} {"current_steps": 6925, "total_steps": 181800, "loss": 0.228, "lr": 1.9042904290429045e-05, "epoch": 0.7618261826182618, "percentage": 3.81, "elapsed_time": "0:15:47", "remaining_time": "6:38:35", "throughput": 1542.52, "total_tokens": 1460832} {"current_steps": 6930, "total_steps": 181800, "loss": 0.2429, "lr": 1.9056655665566557e-05, "epoch": 0.7623762376237624, "percentage": 3.81, "elapsed_time": "0:15:47", "remaining_time": "6:38:34", "throughput": 1542.53, "total_tokens": 1461888} {"current_steps": 6935, "total_steps": 181800, "loss": 0.1314, "lr": 1.9070407040704072e-05, "epoch": 0.7629262926292629, "percentage": 3.81, "elapsed_time": "0:15:48", "remaining_time": "6:38:33", "throughput": 1542.5, "total_tokens": 1462912} {"current_steps": 6940, "total_steps": 181800, "loss": 0.1138, "lr": 1.9084158415841584e-05, "epoch": 0.7634763476347635, "percentage": 3.82, "elapsed_time": "0:15:49", "remaining_time": "6:38:33", "throughput": 1542.48, "total_tokens": 1463936} {"current_steps": 6945, "total_steps": 181800, "loss": 0.1679, "lr": 1.90979097909791e-05, "epoch": 0.764026402640264, "percentage": 3.82, "elapsed_time": "0:15:49", "remaining_time": "6:38:32", "throughput": 1542.48, "total_tokens": 1464992} {"current_steps": 6950, "total_steps": 181800, "loss": 0.1818, "lr": 1.9111661166116614e-05, "epoch": 0.7645764576457645, "percentage": 3.82, "elapsed_time": "0:15:50", "remaining_time": "6:38:31", "throughput": 1542.49, "total_tokens": 1466048} {"current_steps": 6955, "total_steps": 181800, "loss": 0.2296, "lr": 1.9125412541254126e-05, "epoch": 0.7651265126512651, "percentage": 3.83, "elapsed_time": "0:15:51", "remaining_time": "6:38:30", "throughput": 1542.46, "total_tokens": 1467072} {"current_steps": 6960, "total_steps": 181800, "loss": 0.1391, "lr": 1.913916391639164e-05, "epoch": 0.7656765676567657, "percentage": 3.83, "elapsed_time": "0:15:51", "remaining_time": "6:38:30", "throughput": 1542.4, "total_tokens": 1468064} {"current_steps": 6965, "total_steps": 181800, "loss": 0.221, "lr": 1.9152915291529152e-05, "epoch": 0.7662266226622663, "percentage": 3.83, "elapsed_time": "0:15:52", "remaining_time": "6:38:29", "throughput": 1542.43, "total_tokens": 1469152} {"current_steps": 6970, "total_steps": 181800, "loss": 0.1995, "lr": 1.9166666666666667e-05, "epoch": 0.7667766776677668, "percentage": 3.83, "elapsed_time": "0:15:53", "remaining_time": "6:38:28", "throughput": 1542.43, "total_tokens": 1470208} {"current_steps": 6975, "total_steps": 181800, "loss": 0.2002, "lr": 1.9180418041804182e-05, "epoch": 0.7673267326732673, "percentage": 3.84, "elapsed_time": "0:15:53", "remaining_time": "6:38:27", "throughput": 1542.47, "total_tokens": 1471296} {"current_steps": 6980, "total_steps": 181800, "loss": 0.1496, "lr": 1.9194169416941697e-05, "epoch": 0.7678767876787679, "percentage": 3.84, "elapsed_time": "0:15:54", "remaining_time": "6:38:27", "throughput": 1542.5, "total_tokens": 1472384} {"current_steps": 6985, "total_steps": 181800, "loss": 0.1795, "lr": 1.920792079207921e-05, "epoch": 0.7684268426842684, "percentage": 3.84, "elapsed_time": "0:15:55", "remaining_time": "6:38:26", "throughput": 1542.51, "total_tokens": 1473440} {"current_steps": 6990, "total_steps": 181800, "loss": 0.1857, "lr": 1.9221672167216724e-05, "epoch": 0.768976897689769, "percentage": 3.84, "elapsed_time": "0:15:55", "remaining_time": "6:38:25", "throughput": 1542.47, "total_tokens": 1474464} {"current_steps": 6995, "total_steps": 181800, "loss": 0.1856, "lr": 1.9235423542354236e-05, "epoch": 0.7695269526952695, "percentage": 3.85, "elapsed_time": "0:15:56", "remaining_time": "6:38:25", "throughput": 1542.48, "total_tokens": 1475520} {"current_steps": 7000, "total_steps": 181800, "loss": 0.1862, "lr": 1.924917491749175e-05, "epoch": 0.77007700770077, "percentage": 3.85, "elapsed_time": "0:15:57", "remaining_time": "6:38:24", "throughput": 1542.44, "total_tokens": 1476544} {"current_steps": 7005, "total_steps": 181800, "loss": 0.1437, "lr": 1.9262926292629262e-05, "epoch": 0.7706270627062707, "percentage": 3.85, "elapsed_time": "0:15:57", "remaining_time": "6:38:23", "throughput": 1542.45, "total_tokens": 1477600} {"current_steps": 7010, "total_steps": 181800, "loss": 0.2175, "lr": 1.9276677667766777e-05, "epoch": 0.7711771177117712, "percentage": 3.86, "elapsed_time": "0:15:58", "remaining_time": "6:38:23", "throughput": 1542.42, "total_tokens": 1478624} {"current_steps": 7015, "total_steps": 181800, "loss": 0.2498, "lr": 1.929042904290429e-05, "epoch": 0.7717271727172718, "percentage": 3.86, "elapsed_time": "0:15:59", "remaining_time": "6:38:22", "throughput": 1542.46, "total_tokens": 1479712} {"current_steps": 7020, "total_steps": 181800, "loss": 0.2222, "lr": 1.9304180418041808e-05, "epoch": 0.7722772277227723, "percentage": 3.86, "elapsed_time": "0:16:00", "remaining_time": "6:38:21", "throughput": 1542.46, "total_tokens": 1480768} {"current_steps": 7025, "total_steps": 181800, "loss": 0.1392, "lr": 1.931793179317932e-05, "epoch": 0.7728272827282728, "percentage": 3.86, "elapsed_time": "0:16:00", "remaining_time": "6:38:20", "throughput": 1542.5, "total_tokens": 1481856} {"current_steps": 7030, "total_steps": 181800, "loss": 0.1931, "lr": 1.9331683168316834e-05, "epoch": 0.7733773377337734, "percentage": 3.87, "elapsed_time": "0:16:01", "remaining_time": "6:38:20", "throughput": 1542.5, "total_tokens": 1482912} {"current_steps": 7035, "total_steps": 181800, "loss": 0.2108, "lr": 1.9345434543454346e-05, "epoch": 0.7739273927392739, "percentage": 3.87, "elapsed_time": "0:16:02", "remaining_time": "6:38:19", "throughput": 1542.47, "total_tokens": 1483936} {"current_steps": 7040, "total_steps": 181800, "loss": 0.133, "lr": 1.935918591859186e-05, "epoch": 0.7744774477447744, "percentage": 3.87, "elapsed_time": "0:16:02", "remaining_time": "6:38:18", "throughput": 1542.45, "total_tokens": 1484960} {"current_steps": 7045, "total_steps": 181800, "loss": 0.1363, "lr": 1.9372937293729373e-05, "epoch": 0.775027502750275, "percentage": 3.88, "elapsed_time": "0:16:03", "remaining_time": "6:38:17", "throughput": 1542.42, "total_tokens": 1485984} {"current_steps": 7050, "total_steps": 181800, "loss": 0.1675, "lr": 1.9386688668866888e-05, "epoch": 0.7755775577557755, "percentage": 3.88, "elapsed_time": "0:16:04", "remaining_time": "6:38:17", "throughput": 1542.42, "total_tokens": 1487040} {"current_steps": 7055, "total_steps": 181800, "loss": 0.1405, "lr": 1.94004400440044e-05, "epoch": 0.7761276127612762, "percentage": 3.88, "elapsed_time": "0:16:04", "remaining_time": "6:38:16", "throughput": 1542.43, "total_tokens": 1488096} {"current_steps": 7060, "total_steps": 181800, "loss": 0.1624, "lr": 1.9414191419141914e-05, "epoch": 0.7766776677667767, "percentage": 3.88, "elapsed_time": "0:16:05", "remaining_time": "6:38:15", "throughput": 1542.4, "total_tokens": 1489120} {"current_steps": 7065, "total_steps": 181800, "loss": 0.205, "lr": 1.942794279427943e-05, "epoch": 0.7772277227722773, "percentage": 3.89, "elapsed_time": "0:16:06", "remaining_time": "6:38:14", "throughput": 1542.44, "total_tokens": 1490208} {"current_steps": 7070, "total_steps": 181800, "loss": 0.1933, "lr": 1.9441694169416944e-05, "epoch": 0.7777777777777778, "percentage": 3.89, "elapsed_time": "0:16:06", "remaining_time": "6:38:14", "throughput": 1542.41, "total_tokens": 1491232} {"current_steps": 7075, "total_steps": 181800, "loss": 0.2592, "lr": 1.9455445544554456e-05, "epoch": 0.7783278327832783, "percentage": 3.89, "elapsed_time": "0:16:07", "remaining_time": "6:38:13", "throughput": 1542.45, "total_tokens": 1492320} {"current_steps": 7080, "total_steps": 181800, "loss": 0.1233, "lr": 1.946919691969197e-05, "epoch": 0.7788778877887789, "percentage": 3.89, "elapsed_time": "0:16:08", "remaining_time": "6:38:12", "throughput": 1542.42, "total_tokens": 1493344} {"current_steps": 7085, "total_steps": 181800, "loss": 0.1885, "lr": 1.9482948294829483e-05, "epoch": 0.7794279427942794, "percentage": 3.9, "elapsed_time": "0:16:08", "remaining_time": "6:38:12", "throughput": 1542.42, "total_tokens": 1494400} {"current_steps": 7090, "total_steps": 181800, "loss": 0.1865, "lr": 1.9496699669966998e-05, "epoch": 0.7799779977997799, "percentage": 3.9, "elapsed_time": "0:16:09", "remaining_time": "6:38:11", "throughput": 1542.42, "total_tokens": 1495456} {"current_steps": 7095, "total_steps": 181800, "loss": 0.2665, "lr": 1.951045104510451e-05, "epoch": 0.7805280528052805, "percentage": 3.9, "elapsed_time": "0:16:10", "remaining_time": "6:38:10", "throughput": 1542.39, "total_tokens": 1496480} {"current_steps": 7100, "total_steps": 181800, "loss": 0.2585, "lr": 1.9524202420242024e-05, "epoch": 0.7810781078107811, "percentage": 3.91, "elapsed_time": "0:16:10", "remaining_time": "6:38:10", "throughput": 1542.36, "total_tokens": 1497504} {"current_steps": 7105, "total_steps": 181800, "loss": 0.1773, "lr": 1.9537953795379536e-05, "epoch": 0.7816281628162817, "percentage": 3.91, "elapsed_time": "0:16:11", "remaining_time": "6:38:09", "throughput": 1542.36, "total_tokens": 1498560} {"current_steps": 7110, "total_steps": 181800, "loss": 0.1931, "lr": 1.9551705170517055e-05, "epoch": 0.7821782178217822, "percentage": 3.91, "elapsed_time": "0:16:12", "remaining_time": "6:38:08", "throughput": 1542.3, "total_tokens": 1499552} {"current_steps": 7115, "total_steps": 181800, "loss": 0.1463, "lr": 1.9565456545654566e-05, "epoch": 0.7827282728272827, "percentage": 3.91, "elapsed_time": "0:16:12", "remaining_time": "6:38:07", "throughput": 1542.28, "total_tokens": 1500576} {"current_steps": 7120, "total_steps": 181800, "loss": 0.1734, "lr": 1.957920792079208e-05, "epoch": 0.7832783278327833, "percentage": 3.92, "elapsed_time": "0:16:13", "remaining_time": "6:38:07", "throughput": 1542.28, "total_tokens": 1501632} {"current_steps": 7125, "total_steps": 181800, "loss": 0.125, "lr": 1.9592959295929593e-05, "epoch": 0.7838283828382838, "percentage": 3.92, "elapsed_time": "0:16:14", "remaining_time": "6:38:06", "throughput": 1542.25, "total_tokens": 1502656} {"current_steps": 7130, "total_steps": 181800, "loss": 0.141, "lr": 1.9606710671067108e-05, "epoch": 0.7843784378437844, "percentage": 3.92, "elapsed_time": "0:16:15", "remaining_time": "6:38:05", "throughput": 1542.25, "total_tokens": 1503712} {"current_steps": 7135, "total_steps": 181800, "loss": 0.1912, "lr": 1.962046204620462e-05, "epoch": 0.7849284928492849, "percentage": 3.92, "elapsed_time": "0:16:15", "remaining_time": "6:38:05", "throughput": 1542.32, "total_tokens": 1504832} {"current_steps": 7140, "total_steps": 181800, "loss": 0.1448, "lr": 1.9634213421342135e-05, "epoch": 0.7854785478547854, "percentage": 3.93, "elapsed_time": "0:16:16", "remaining_time": "6:38:04", "throughput": 1542.3, "total_tokens": 1505856} {"current_steps": 7145, "total_steps": 181800, "loss": 0.1242, "lr": 1.964796479647965e-05, "epoch": 0.786028602860286, "percentage": 3.93, "elapsed_time": "0:16:17", "remaining_time": "6:38:03", "throughput": 1542.3, "total_tokens": 1506912} {"current_steps": 7150, "total_steps": 181800, "loss": 0.1879, "lr": 1.966171617161716e-05, "epoch": 0.7865786578657866, "percentage": 3.93, "elapsed_time": "0:16:17", "remaining_time": "6:38:02", "throughput": 1542.37, "total_tokens": 1508032} {"current_steps": 7155, "total_steps": 181800, "loss": 0.1533, "lr": 1.9675467546754676e-05, "epoch": 0.7871287128712872, "percentage": 3.94, "elapsed_time": "0:16:18", "remaining_time": "6:38:01", "throughput": 1542.35, "total_tokens": 1509056} {"current_steps": 7160, "total_steps": 181800, "loss": 0.1459, "lr": 1.968921892189219e-05, "epoch": 0.7876787678767877, "percentage": 3.94, "elapsed_time": "0:16:19", "remaining_time": "6:38:01", "throughput": 1542.35, "total_tokens": 1510112} {"current_steps": 7165, "total_steps": 181800, "loss": 0.1734, "lr": 1.9702970297029703e-05, "epoch": 0.7882288228822882, "percentage": 3.94, "elapsed_time": "0:16:19", "remaining_time": "6:38:00", "throughput": 1542.36, "total_tokens": 1511168} {"current_steps": 7170, "total_steps": 181800, "loss": 0.1962, "lr": 1.9716721672167218e-05, "epoch": 0.7887788778877888, "percentage": 3.94, "elapsed_time": "0:16:20", "remaining_time": "6:37:59", "throughput": 1542.39, "total_tokens": 1512256} {"current_steps": 7175, "total_steps": 181800, "loss": 0.1992, "lr": 1.9730473047304733e-05, "epoch": 0.7893289328932893, "percentage": 3.95, "elapsed_time": "0:16:21", "remaining_time": "6:37:59", "throughput": 1542.43, "total_tokens": 1513344} {"current_steps": 7180, "total_steps": 181800, "loss": 0.2343, "lr": 1.9744224422442245e-05, "epoch": 0.7898789878987899, "percentage": 3.95, "elapsed_time": "0:16:21", "remaining_time": "6:37:58", "throughput": 1542.43, "total_tokens": 1514400} {"current_steps": 7185, "total_steps": 181800, "loss": 0.2825, "lr": 1.975797579757976e-05, "epoch": 0.7904290429042904, "percentage": 3.95, "elapsed_time": "0:16:22", "remaining_time": "6:37:57", "throughput": 1542.4, "total_tokens": 1515424} {"current_steps": 7190, "total_steps": 181800, "loss": 0.1814, "lr": 1.977172717271727e-05, "epoch": 0.7909790979097909, "percentage": 3.95, "elapsed_time": "0:16:23", "remaining_time": "6:37:56", "throughput": 1542.37, "total_tokens": 1516448} {"current_steps": 7195, "total_steps": 181800, "loss": 0.2238, "lr": 1.9785478547854787e-05, "epoch": 0.7915291529152916, "percentage": 3.96, "elapsed_time": "0:16:23", "remaining_time": "6:37:56", "throughput": 1542.34, "total_tokens": 1517472} {"current_steps": 7200, "total_steps": 181800, "loss": 0.147, "lr": 1.9799229922992298e-05, "epoch": 0.7920792079207921, "percentage": 3.96, "elapsed_time": "0:16:24", "remaining_time": "6:37:55", "throughput": 1542.32, "total_tokens": 1518496} {"current_steps": 7205, "total_steps": 181800, "loss": 0.2012, "lr": 1.9812981298129817e-05, "epoch": 0.7926292629262927, "percentage": 3.96, "elapsed_time": "0:16:25", "remaining_time": "6:37:54", "throughput": 1542.29, "total_tokens": 1519520} {"current_steps": 7210, "total_steps": 181800, "loss": 0.1916, "lr": 1.982673267326733e-05, "epoch": 0.7931793179317932, "percentage": 3.97, "elapsed_time": "0:16:25", "remaining_time": "6:37:53", "throughput": 1542.33, "total_tokens": 1520608} {"current_steps": 7215, "total_steps": 181800, "loss": 0.1898, "lr": 1.9840484048404843e-05, "epoch": 0.7937293729372937, "percentage": 3.97, "elapsed_time": "0:16:26", "remaining_time": "6:37:53", "throughput": 1542.34, "total_tokens": 1521664} {"current_steps": 7220, "total_steps": 181800, "loss": 0.1442, "lr": 1.9854235423542355e-05, "epoch": 0.7942794279427943, "percentage": 3.97, "elapsed_time": "0:16:27", "remaining_time": "6:37:52", "throughput": 1542.31, "total_tokens": 1522688} {"current_steps": 7225, "total_steps": 181800, "loss": 0.1792, "lr": 1.986798679867987e-05, "epoch": 0.7948294829482948, "percentage": 3.97, "elapsed_time": "0:16:27", "remaining_time": "6:37:51", "throughput": 1542.34, "total_tokens": 1523776} {"current_steps": 7230, "total_steps": 181800, "loss": 0.1811, "lr": 1.9881738173817382e-05, "epoch": 0.7953795379537953, "percentage": 3.98, "elapsed_time": "0:16:28", "remaining_time": "6:37:50", "throughput": 1542.38, "total_tokens": 1524864} {"current_steps": 7235, "total_steps": 181800, "loss": 0.2024, "lr": 1.9895489548954897e-05, "epoch": 0.7959295929592959, "percentage": 3.98, "elapsed_time": "0:16:29", "remaining_time": "6:37:50", "throughput": 1542.36, "total_tokens": 1525888} {"current_steps": 7240, "total_steps": 181800, "loss": 0.1365, "lr": 1.990924092409241e-05, "epoch": 0.7964796479647965, "percentage": 3.98, "elapsed_time": "0:16:30", "remaining_time": "6:37:49", "throughput": 1542.39, "total_tokens": 1526976} {"current_steps": 7245, "total_steps": 181800, "loss": 0.1461, "lr": 1.9922992299229923e-05, "epoch": 0.7970297029702971, "percentage": 3.99, "elapsed_time": "0:16:30", "remaining_time": "6:37:48", "throughput": 1542.33, "total_tokens": 1527968} {"current_steps": 7250, "total_steps": 181800, "loss": 0.1559, "lr": 1.993674367436744e-05, "epoch": 0.7975797579757976, "percentage": 3.99, "elapsed_time": "0:16:31", "remaining_time": "6:37:48", "throughput": 1542.3, "total_tokens": 1528992} {"current_steps": 7255, "total_steps": 181800, "loss": 0.138, "lr": 1.9950495049504954e-05, "epoch": 0.7981298129812981, "percentage": 3.99, "elapsed_time": "0:16:32", "remaining_time": "6:37:47", "throughput": 1542.27, "total_tokens": 1530016} {"current_steps": 7260, "total_steps": 181800, "loss": 0.1559, "lr": 1.9964246424642465e-05, "epoch": 0.7986798679867987, "percentage": 3.99, "elapsed_time": "0:16:32", "remaining_time": "6:37:46", "throughput": 1542.31, "total_tokens": 1531104} {"current_steps": 7265, "total_steps": 181800, "loss": 0.1827, "lr": 1.997799779977998e-05, "epoch": 0.7992299229922992, "percentage": 4.0, "elapsed_time": "0:16:33", "remaining_time": "6:37:45", "throughput": 1542.35, "total_tokens": 1532192} {"current_steps": 7270, "total_steps": 181800, "loss": 0.2096, "lr": 1.9991749174917492e-05, "epoch": 0.7997799779977998, "percentage": 4.0, "elapsed_time": "0:16:34", "remaining_time": "6:37:45", "throughput": 1542.32, "total_tokens": 1533216} {"current_steps": 7275, "total_steps": 181800, "loss": 0.1143, "lr": 2.0005500550055007e-05, "epoch": 0.8003300330033003, "percentage": 4.0, "elapsed_time": "0:16:34", "remaining_time": "6:37:44", "throughput": 1542.29, "total_tokens": 1534240} {"current_steps": 7280, "total_steps": 181800, "loss": 0.1749, "lr": 2.001925192519252e-05, "epoch": 0.8008800880088008, "percentage": 4.0, "elapsed_time": "0:16:35", "remaining_time": "6:37:43", "throughput": 1542.29, "total_tokens": 1535296} {"current_steps": 7285, "total_steps": 181800, "loss": 0.1901, "lr": 2.0033003300330034e-05, "epoch": 0.8014301430143014, "percentage": 4.01, "elapsed_time": "0:16:36", "remaining_time": "6:37:43", "throughput": 1542.36, "total_tokens": 1536416} {"current_steps": 7290, "total_steps": 181800, "loss": 0.2037, "lr": 2.0046754675467545e-05, "epoch": 0.801980198019802, "percentage": 4.01, "elapsed_time": "0:16:36", "remaining_time": "6:37:42", "throughput": 1542.36, "total_tokens": 1537472} {"current_steps": 7295, "total_steps": 181800, "loss": 0.1503, "lr": 2.006050605060506e-05, "epoch": 0.8025302530253026, "percentage": 4.01, "elapsed_time": "0:16:37", "remaining_time": "6:37:41", "throughput": 1542.29, "total_tokens": 1538464} {"current_steps": 7300, "total_steps": 181800, "loss": 0.1471, "lr": 2.0074257425742575e-05, "epoch": 0.8030803080308031, "percentage": 4.02, "elapsed_time": "0:16:38", "remaining_time": "6:37:41", "throughput": 1542.26, "total_tokens": 1539488} {"current_steps": 7305, "total_steps": 181800, "loss": 0.149, "lr": 2.008800880088009e-05, "epoch": 0.8036303630363036, "percentage": 4.02, "elapsed_time": "0:16:38", "remaining_time": "6:37:40", "throughput": 1542.3, "total_tokens": 1540576} {"current_steps": 7310, "total_steps": 181800, "loss": 0.1716, "lr": 2.0101760176017602e-05, "epoch": 0.8041804180418042, "percentage": 4.02, "elapsed_time": "0:16:39", "remaining_time": "6:37:39", "throughput": 1542.3, "total_tokens": 1541632} {"current_steps": 7315, "total_steps": 181800, "loss": 0.1925, "lr": 2.0115511551155117e-05, "epoch": 0.8047304730473047, "percentage": 4.02, "elapsed_time": "0:16:40", "remaining_time": "6:37:38", "throughput": 1542.27, "total_tokens": 1542656} {"current_steps": 7320, "total_steps": 181800, "loss": 0.2069, "lr": 2.012926292629263e-05, "epoch": 0.8052805280528053, "percentage": 4.03, "elapsed_time": "0:16:40", "remaining_time": "6:37:38", "throughput": 1542.31, "total_tokens": 1543744} {"current_steps": 7325, "total_steps": 181800, "loss": 0.1135, "lr": 2.0143014301430144e-05, "epoch": 0.8058305830583058, "percentage": 4.03, "elapsed_time": "0:16:41", "remaining_time": "6:37:37", "throughput": 1542.41, "total_tokens": 1544896} {"current_steps": 7330, "total_steps": 181800, "loss": 0.1567, "lr": 2.0156765676567656e-05, "epoch": 0.8063806380638063, "percentage": 4.03, "elapsed_time": "0:16:42", "remaining_time": "6:37:36", "throughput": 1542.38, "total_tokens": 1545920} {"current_steps": 7335, "total_steps": 181800, "loss": 0.1673, "lr": 2.017051705170517e-05, "epoch": 0.806930693069307, "percentage": 4.03, "elapsed_time": "0:16:42", "remaining_time": "6:37:36", "throughput": 1542.45, "total_tokens": 1547040} {"current_steps": 7340, "total_steps": 181800, "loss": 0.1745, "lr": 2.0184268426842686e-05, "epoch": 0.8074807480748075, "percentage": 4.04, "elapsed_time": "0:16:43", "remaining_time": "6:37:35", "throughput": 1542.49, "total_tokens": 1548128} {"current_steps": 7345, "total_steps": 181800, "loss": 0.2022, "lr": 2.01980198019802e-05, "epoch": 0.8080308030803081, "percentage": 4.04, "elapsed_time": "0:16:44", "remaining_time": "6:37:34", "throughput": 1542.52, "total_tokens": 1549216} {"current_steps": 7350, "total_steps": 181800, "loss": 0.1586, "lr": 2.0211771177117712e-05, "epoch": 0.8085808580858086, "percentage": 4.04, "elapsed_time": "0:16:45", "remaining_time": "6:37:34", "throughput": 1542.48, "total_tokens": 1550240} {"current_steps": 7355, "total_steps": 181800, "loss": 0.184, "lr": 2.0225522552255227e-05, "epoch": 0.8091309130913091, "percentage": 4.05, "elapsed_time": "0:16:45", "remaining_time": "6:37:33", "throughput": 1542.45, "total_tokens": 1551264} {"current_steps": 7360, "total_steps": 181800, "loss": 0.1682, "lr": 2.023927392739274e-05, "epoch": 0.8096809680968097, "percentage": 4.05, "elapsed_time": "0:16:46", "remaining_time": "6:37:32", "throughput": 1542.42, "total_tokens": 1552288} {"current_steps": 7365, "total_steps": 181800, "loss": 0.2273, "lr": 2.0253025302530254e-05, "epoch": 0.8102310231023102, "percentage": 4.05, "elapsed_time": "0:16:47", "remaining_time": "6:37:32", "throughput": 1542.42, "total_tokens": 1553344} {"current_steps": 7370, "total_steps": 181800, "loss": 0.1351, "lr": 2.026677667766777e-05, "epoch": 0.8107810781078107, "percentage": 4.05, "elapsed_time": "0:16:47", "remaining_time": "6:37:31", "throughput": 1542.46, "total_tokens": 1554432} {"current_steps": 7375, "total_steps": 181800, "loss": 0.1702, "lr": 2.028052805280528e-05, "epoch": 0.8113311331133113, "percentage": 4.06, "elapsed_time": "0:16:48", "remaining_time": "6:37:30", "throughput": 1542.43, "total_tokens": 1555456} {"current_steps": 7380, "total_steps": 181800, "loss": 0.2731, "lr": 2.0294279427942796e-05, "epoch": 0.8118811881188119, "percentage": 4.06, "elapsed_time": "0:16:49", "remaining_time": "6:37:29", "throughput": 1542.46, "total_tokens": 1556544} {"current_steps": 7385, "total_steps": 181800, "loss": 0.1443, "lr": 2.0308030803080307e-05, "epoch": 0.8124312431243125, "percentage": 4.06, "elapsed_time": "0:16:49", "remaining_time": "6:37:33", "throughput": 1542.19, "total_tokens": 1557600} {"current_steps": 7390, "total_steps": 181800, "loss": 0.207, "lr": 2.0321782178217822e-05, "epoch": 0.812981298129813, "percentage": 4.06, "elapsed_time": "0:16:50", "remaining_time": "6:37:32", "throughput": 1542.16, "total_tokens": 1558624} {"current_steps": 7395, "total_steps": 181800, "loss": 0.2583, "lr": 2.0335533553355338e-05, "epoch": 0.8135313531353136, "percentage": 4.07, "elapsed_time": "0:16:51", "remaining_time": "6:37:32", "throughput": 1542.16, "total_tokens": 1559680} {"current_steps": 7400, "total_steps": 181800, "loss": 0.1883, "lr": 2.0349284928492853e-05, "epoch": 0.8140814081408141, "percentage": 4.07, "elapsed_time": "0:16:52", "remaining_time": "6:37:31", "throughput": 1542.19, "total_tokens": 1560768} {"current_steps": 7405, "total_steps": 181800, "loss": 0.1129, "lr": 2.0363036303630364e-05, "epoch": 0.8146314631463146, "percentage": 4.07, "elapsed_time": "0:16:52", "remaining_time": "6:37:30", "throughput": 1542.2, "total_tokens": 1561824} {"current_steps": 7410, "total_steps": 181800, "loss": 0.1688, "lr": 2.037678767876788e-05, "epoch": 0.8151815181518152, "percentage": 4.08, "elapsed_time": "0:16:53", "remaining_time": "6:37:30", "throughput": 1542.2, "total_tokens": 1562880} {"current_steps": 7415, "total_steps": 181800, "loss": 0.2646, "lr": 2.039053905390539e-05, "epoch": 0.8157315731573157, "percentage": 4.08, "elapsed_time": "0:16:54", "remaining_time": "6:37:29", "throughput": 1542.2, "total_tokens": 1563936} {"current_steps": 7420, "total_steps": 181800, "loss": 0.131, "lr": 2.0404290429042906e-05, "epoch": 0.8162816281628162, "percentage": 4.08, "elapsed_time": "0:16:54", "remaining_time": "6:37:28", "throughput": 1542.17, "total_tokens": 1564960} {"current_steps": 7425, "total_steps": 181800, "loss": 0.2209, "lr": 2.0418041804180418e-05, "epoch": 0.8168316831683168, "percentage": 4.08, "elapsed_time": "0:16:55", "remaining_time": "6:37:27", "throughput": 1542.15, "total_tokens": 1565984} {"current_steps": 7430, "total_steps": 181800, "loss": 0.1337, "lr": 2.0431793179317933e-05, "epoch": 0.8173817381738174, "percentage": 4.09, "elapsed_time": "0:16:56", "remaining_time": "6:37:27", "throughput": 1542.12, "total_tokens": 1567008} {"current_steps": 7435, "total_steps": 181800, "loss": 0.1909, "lr": 2.0445544554455444e-05, "epoch": 0.817931793179318, "percentage": 4.09, "elapsed_time": "0:16:56", "remaining_time": "6:37:26", "throughput": 1542.13, "total_tokens": 1568064} {"current_steps": 7440, "total_steps": 181800, "loss": 0.1756, "lr": 2.0459295929592963e-05, "epoch": 0.8184818481848185, "percentage": 4.09, "elapsed_time": "0:16:57", "remaining_time": "6:37:25", "throughput": 1542.19, "total_tokens": 1569184} {"current_steps": 7445, "total_steps": 181800, "loss": 0.1721, "lr": 2.0473047304730474e-05, "epoch": 0.819031903190319, "percentage": 4.1, "elapsed_time": "0:16:58", "remaining_time": "6:37:24", "throughput": 1542.29, "total_tokens": 1570336} {"current_steps": 7450, "total_steps": 181800, "loss": 0.2039, "lr": 2.048679867986799e-05, "epoch": 0.8195819581958196, "percentage": 4.1, "elapsed_time": "0:16:58", "remaining_time": "6:37:24", "throughput": 1542.23, "total_tokens": 1571328} {"current_steps": 7455, "total_steps": 181800, "loss": 0.1913, "lr": 2.05005500550055e-05, "epoch": 0.8201320132013201, "percentage": 4.1, "elapsed_time": "0:16:59", "remaining_time": "6:37:23", "throughput": 1542.3, "total_tokens": 1572448} {"current_steps": 7460, "total_steps": 181800, "loss": 0.1556, "lr": 2.0514301430143016e-05, "epoch": 0.8206820682068207, "percentage": 4.1, "elapsed_time": "0:17:00", "remaining_time": "6:37:22", "throughput": 1542.36, "total_tokens": 1573568} {"current_steps": 7465, "total_steps": 181800, "loss": 0.1512, "lr": 2.0528052805280528e-05, "epoch": 0.8212321232123212, "percentage": 4.11, "elapsed_time": "0:17:00", "remaining_time": "6:37:22", "throughput": 1542.33, "total_tokens": 1574592} {"current_steps": 7470, "total_steps": 181800, "loss": 0.1376, "lr": 2.0541804180418043e-05, "epoch": 0.8217821782178217, "percentage": 4.11, "elapsed_time": "0:17:01", "remaining_time": "6:37:21", "throughput": 1542.36, "total_tokens": 1575680} {"current_steps": 7475, "total_steps": 181800, "loss": 0.122, "lr": 2.0555555555555555e-05, "epoch": 0.8223322332233224, "percentage": 4.11, "elapsed_time": "0:17:02", "remaining_time": "6:37:20", "throughput": 1542.37, "total_tokens": 1576736} {"current_steps": 7480, "total_steps": 181800, "loss": 0.1956, "lr": 2.056930693069307e-05, "epoch": 0.8228822882288229, "percentage": 4.11, "elapsed_time": "0:17:02", "remaining_time": "6:37:20", "throughput": 1542.34, "total_tokens": 1577760} {"current_steps": 7485, "total_steps": 181800, "loss": 0.1631, "lr": 2.0583058305830585e-05, "epoch": 0.8234323432343235, "percentage": 4.12, "elapsed_time": "0:17:03", "remaining_time": "6:37:19", "throughput": 1542.34, "total_tokens": 1578816} {"current_steps": 7490, "total_steps": 181800, "loss": 0.1791, "lr": 2.05968096809681e-05, "epoch": 0.823982398239824, "percentage": 4.12, "elapsed_time": "0:17:04", "remaining_time": "6:37:18", "throughput": 1542.38, "total_tokens": 1579904} {"current_steps": 7495, "total_steps": 181800, "loss": 0.2069, "lr": 2.061056105610561e-05, "epoch": 0.8245324532453245, "percentage": 4.12, "elapsed_time": "0:17:05", "remaining_time": "6:37:17", "throughput": 1542.45, "total_tokens": 1581024} {"current_steps": 7500, "total_steps": 181800, "loss": 0.1297, "lr": 2.0624312431243126e-05, "epoch": 0.8250825082508251, "percentage": 4.13, "elapsed_time": "0:17:05", "remaining_time": "6:37:17", "throughput": 1542.43, "total_tokens": 1582048} {"current_steps": 7505, "total_steps": 181800, "loss": 0.2384, "lr": 2.0638063806380638e-05, "epoch": 0.8256325632563256, "percentage": 4.13, "elapsed_time": "0:17:06", "remaining_time": "6:37:16", "throughput": 1542.46, "total_tokens": 1583136} {"current_steps": 7510, "total_steps": 181800, "loss": 0.1583, "lr": 2.0651815181518153e-05, "epoch": 0.8261826182618262, "percentage": 4.13, "elapsed_time": "0:17:07", "remaining_time": "6:37:15", "throughput": 1542.38, "total_tokens": 1584096} {"current_steps": 7515, "total_steps": 181800, "loss": 0.1699, "lr": 2.0665566556655665e-05, "epoch": 0.8267326732673267, "percentage": 4.13, "elapsed_time": "0:17:07", "remaining_time": "6:37:14", "throughput": 1542.35, "total_tokens": 1585120} {"current_steps": 7520, "total_steps": 181800, "loss": 0.1424, "lr": 2.067931793179318e-05, "epoch": 0.8272827282728272, "percentage": 4.14, "elapsed_time": "0:17:08", "remaining_time": "6:37:13", "throughput": 1542.33, "total_tokens": 1586144} {"current_steps": 7525, "total_steps": 181800, "loss": 0.1907, "lr": 2.069306930693069e-05, "epoch": 0.8278327832783279, "percentage": 4.14, "elapsed_time": "0:17:09", "remaining_time": "6:37:13", "throughput": 1542.28, "total_tokens": 1587136} {"current_steps": 7530, "total_steps": 181800, "loss": 0.175, "lr": 2.0706820682068206e-05, "epoch": 0.8283828382838284, "percentage": 4.14, "elapsed_time": "0:17:09", "remaining_time": "6:37:12", "throughput": 1542.28, "total_tokens": 1588192} {"current_steps": 7535, "total_steps": 181800, "loss": 0.1614, "lr": 2.072057205720572e-05, "epoch": 0.828932893289329, "percentage": 4.14, "elapsed_time": "0:17:10", "remaining_time": "6:37:11", "throughput": 1542.26, "total_tokens": 1589216} {"current_steps": 7540, "total_steps": 181800, "loss": 0.1616, "lr": 2.0734323432343237e-05, "epoch": 0.8294829482948295, "percentage": 4.15, "elapsed_time": "0:17:11", "remaining_time": "6:37:10", "throughput": 1542.3, "total_tokens": 1590304} {"current_steps": 7545, "total_steps": 181800, "loss": 0.1279, "lr": 2.0748074807480748e-05, "epoch": 0.83003300330033, "percentage": 4.15, "elapsed_time": "0:17:11", "remaining_time": "6:37:10", "throughput": 1542.4, "total_tokens": 1591456} {"current_steps": 7550, "total_steps": 181800, "loss": 0.1636, "lr": 2.0761826182618263e-05, "epoch": 0.8305830583058306, "percentage": 4.15, "elapsed_time": "0:17:12", "remaining_time": "6:37:09", "throughput": 1542.47, "total_tokens": 1592576} {"current_steps": 7555, "total_steps": 181800, "loss": 0.1366, "lr": 2.0775577557755775e-05, "epoch": 0.8311331133113311, "percentage": 4.16, "elapsed_time": "0:17:13", "remaining_time": "6:37:08", "throughput": 1542.5, "total_tokens": 1593664} {"current_steps": 7560, "total_steps": 181800, "loss": 0.2668, "lr": 2.078932893289329e-05, "epoch": 0.8316831683168316, "percentage": 4.16, "elapsed_time": "0:17:13", "remaining_time": "6:37:07", "throughput": 1542.48, "total_tokens": 1594688} {"current_steps": 7565, "total_steps": 181800, "loss": 0.1989, "lr": 2.0803080308030805e-05, "epoch": 0.8322332233223322, "percentage": 4.16, "elapsed_time": "0:17:14", "remaining_time": "6:37:06", "throughput": 1542.46, "total_tokens": 1595712} {"current_steps": 7570, "total_steps": 181800, "loss": 0.0973, "lr": 2.0816831683168317e-05, "epoch": 0.8327832783278328, "percentage": 4.16, "elapsed_time": "0:17:15", "remaining_time": "6:37:06", "throughput": 1542.47, "total_tokens": 1596768} {"current_steps": 7575, "total_steps": 181800, "loss": 0.163, "lr": 2.083058305830583e-05, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:17:15", "remaining_time": "6:37:05", "throughput": 1542.5, "total_tokens": 1597856} {"current_steps": 7580, "total_steps": 181800, "loss": 0.1434, "lr": 2.0844334433443347e-05, "epoch": 0.8338833883388339, "percentage": 4.17, "elapsed_time": "0:17:16", "remaining_time": "6:37:04", "throughput": 1542.54, "total_tokens": 1598944} {"current_steps": 7585, "total_steps": 181800, "loss": 0.1799, "lr": 2.085808580858086e-05, "epoch": 0.8344334433443344, "percentage": 4.17, "elapsed_time": "0:17:17", "remaining_time": "6:37:03", "throughput": 1542.49, "total_tokens": 1599936} {"current_steps": 7590, "total_steps": 181800, "loss": 0.1708, "lr": 2.0871837183718373e-05, "epoch": 0.834983498349835, "percentage": 4.17, "elapsed_time": "0:17:17", "remaining_time": "6:37:03", "throughput": 1542.49, "total_tokens": 1600992} {"current_steps": 7595, "total_steps": 181800, "loss": 0.1145, "lr": 2.088558855885589e-05, "epoch": 0.8355335533553355, "percentage": 4.18, "elapsed_time": "0:17:18", "remaining_time": "6:37:02", "throughput": 1542.47, "total_tokens": 1602016} {"current_steps": 7600, "total_steps": 181800, "loss": 0.1405, "lr": 2.08993399339934e-05, "epoch": 0.8360836083608361, "percentage": 4.18, "elapsed_time": "0:17:19", "remaining_time": "6:37:01", "throughput": 1542.44, "total_tokens": 1603040} {"current_steps": 7605, "total_steps": 181800, "loss": 0.1676, "lr": 2.0913091309130915e-05, "epoch": 0.8366336633663366, "percentage": 4.18, "elapsed_time": "0:17:19", "remaining_time": "6:37:00", "throughput": 1542.42, "total_tokens": 1604064} {"current_steps": 7610, "total_steps": 181800, "loss": 0.2007, "lr": 2.0926842684268427e-05, "epoch": 0.8371837183718371, "percentage": 4.19, "elapsed_time": "0:17:20", "remaining_time": "6:37:00", "throughput": 1542.42, "total_tokens": 1605120} {"current_steps": 7615, "total_steps": 181800, "loss": 0.1521, "lr": 2.0940594059405942e-05, "epoch": 0.8377337733773378, "percentage": 4.19, "elapsed_time": "0:17:21", "remaining_time": "6:36:59", "throughput": 1542.43, "total_tokens": 1606176} {"current_steps": 7620, "total_steps": 181800, "loss": 0.1698, "lr": 2.0954345434543454e-05, "epoch": 0.8382838283828383, "percentage": 4.19, "elapsed_time": "0:17:22", "remaining_time": "6:36:58", "throughput": 1542.44, "total_tokens": 1607232} {"current_steps": 7625, "total_steps": 181800, "loss": 0.1868, "lr": 2.0968096809680972e-05, "epoch": 0.8388338833883389, "percentage": 4.19, "elapsed_time": "0:17:22", "remaining_time": "6:36:57", "throughput": 1542.41, "total_tokens": 1608256} {"current_steps": 7630, "total_steps": 181800, "loss": 0.139, "lr": 2.0981848184818484e-05, "epoch": 0.8393839383938394, "percentage": 4.2, "elapsed_time": "0:17:23", "remaining_time": "6:36:56", "throughput": 1542.42, "total_tokens": 1609312} {"current_steps": 7635, "total_steps": 181800, "loss": 0.3035, "lr": 2.0995599559956e-05, "epoch": 0.8399339933993399, "percentage": 4.2, "elapsed_time": "0:17:24", "remaining_time": "6:36:56", "throughput": 1542.45, "total_tokens": 1610400} {"current_steps": 7640, "total_steps": 181800, "loss": 0.1543, "lr": 2.100935093509351e-05, "epoch": 0.8404840484048405, "percentage": 4.2, "elapsed_time": "0:17:24", "remaining_time": "6:36:55", "throughput": 1542.51, "total_tokens": 1611520} {"current_steps": 7645, "total_steps": 181800, "loss": 0.1199, "lr": 2.1023102310231025e-05, "epoch": 0.841034103410341, "percentage": 4.21, "elapsed_time": "0:17:25", "remaining_time": "6:36:54", "throughput": 1542.51, "total_tokens": 1612576} {"current_steps": 7650, "total_steps": 181800, "loss": 0.2249, "lr": 2.1036853685368537e-05, "epoch": 0.8415841584158416, "percentage": 4.21, "elapsed_time": "0:17:26", "remaining_time": "6:36:54", "throughput": 1542.55, "total_tokens": 1613664} {"current_steps": 7655, "total_steps": 181800, "loss": 0.1306, "lr": 2.1050605060506052e-05, "epoch": 0.8421342134213421, "percentage": 4.21, "elapsed_time": "0:17:26", "remaining_time": "6:36:53", "throughput": 1542.56, "total_tokens": 1614720} {"current_steps": 7660, "total_steps": 181800, "loss": 0.1483, "lr": 2.1064356435643564e-05, "epoch": 0.8426842684268426, "percentage": 4.21, "elapsed_time": "0:17:27", "remaining_time": "6:36:52", "throughput": 1542.62, "total_tokens": 1615840} {"current_steps": 7665, "total_steps": 181800, "loss": 0.1215, "lr": 2.107810781078108e-05, "epoch": 0.8432343234323433, "percentage": 4.22, "elapsed_time": "0:17:28", "remaining_time": "6:36:51", "throughput": 1542.69, "total_tokens": 1616960} {"current_steps": 7670, "total_steps": 181800, "loss": 0.1797, "lr": 2.109185918591859e-05, "epoch": 0.8437843784378438, "percentage": 4.22, "elapsed_time": "0:17:28", "remaining_time": "6:36:51", "throughput": 1542.67, "total_tokens": 1617984} {"current_steps": 7675, "total_steps": 181800, "loss": 0.227, "lr": 2.110561056105611e-05, "epoch": 0.8443344334433444, "percentage": 4.22, "elapsed_time": "0:17:29", "remaining_time": "6:36:50", "throughput": 1542.67, "total_tokens": 1619040} {"current_steps": 7680, "total_steps": 181800, "loss": 0.205, "lr": 2.111936193619362e-05, "epoch": 0.8448844884488449, "percentage": 4.22, "elapsed_time": "0:17:30", "remaining_time": "6:36:49", "throughput": 1542.7, "total_tokens": 1620128} {"current_steps": 7685, "total_steps": 181800, "loss": 0.1573, "lr": 2.1133113311331136e-05, "epoch": 0.8454345434543454, "percentage": 4.23, "elapsed_time": "0:17:30", "remaining_time": "6:36:49", "throughput": 1542.67, "total_tokens": 1621152} {"current_steps": 7690, "total_steps": 181800, "loss": 0.1507, "lr": 2.1146864686468647e-05, "epoch": 0.845984598459846, "percentage": 4.23, "elapsed_time": "0:17:31", "remaining_time": "6:36:48", "throughput": 1542.67, "total_tokens": 1622208} {"current_steps": 7695, "total_steps": 181800, "loss": 0.0957, "lr": 2.1160616061606162e-05, "epoch": 0.8465346534653465, "percentage": 4.23, "elapsed_time": "0:17:32", "remaining_time": "6:36:47", "throughput": 1542.76, "total_tokens": 1623360} {"current_steps": 7700, "total_steps": 181800, "loss": 0.2192, "lr": 2.1174367436743674e-05, "epoch": 0.847084708470847, "percentage": 4.24, "elapsed_time": "0:17:32", "remaining_time": "6:36:47", "throughput": 1542.79, "total_tokens": 1624448} {"current_steps": 7705, "total_steps": 181800, "loss": 0.1469, "lr": 2.118811881188119e-05, "epoch": 0.8476347634763476, "percentage": 4.24, "elapsed_time": "0:17:33", "remaining_time": "6:36:46", "throughput": 1542.8, "total_tokens": 1625504} {"current_steps": 7710, "total_steps": 181800, "loss": 0.1603, "lr": 2.12018701870187e-05, "epoch": 0.8481848184818482, "percentage": 4.24, "elapsed_time": "0:17:34", "remaining_time": "6:36:45", "throughput": 1542.92, "total_tokens": 1626688} {"current_steps": 7715, "total_steps": 181800, "loss": 0.1773, "lr": 2.1215621562156216e-05, "epoch": 0.8487348734873488, "percentage": 4.24, "elapsed_time": "0:17:34", "remaining_time": "6:36:44", "throughput": 1542.89, "total_tokens": 1627712} {"current_steps": 7720, "total_steps": 181800, "loss": 0.1641, "lr": 2.122937293729373e-05, "epoch": 0.8492849284928493, "percentage": 4.25, "elapsed_time": "0:17:35", "remaining_time": "6:36:44", "throughput": 1542.84, "total_tokens": 1628704} {"current_steps": 7725, "total_steps": 181800, "loss": 0.1752, "lr": 2.1243124312431246e-05, "epoch": 0.8498349834983498, "percentage": 4.25, "elapsed_time": "0:17:36", "remaining_time": "6:36:43", "throughput": 1542.9, "total_tokens": 1629824} {"current_steps": 7730, "total_steps": 181800, "loss": 0.1749, "lr": 2.1256875687568757e-05, "epoch": 0.8503850385038504, "percentage": 4.25, "elapsed_time": "0:17:37", "remaining_time": "6:36:42", "throughput": 1542.91, "total_tokens": 1630880} {"current_steps": 7735, "total_steps": 181800, "loss": 0.1967, "lr": 2.1270627062706272e-05, "epoch": 0.8509350935093509, "percentage": 4.25, "elapsed_time": "0:17:37", "remaining_time": "6:36:41", "throughput": 1542.88, "total_tokens": 1631904} {"current_steps": 7740, "total_steps": 181800, "loss": 0.2153, "lr": 2.1284378437843784e-05, "epoch": 0.8514851485148515, "percentage": 4.26, "elapsed_time": "0:17:38", "remaining_time": "6:36:41", "throughput": 1542.92, "total_tokens": 1632992} {"current_steps": 7745, "total_steps": 181800, "loss": 0.1636, "lr": 2.12981298129813e-05, "epoch": 0.852035203520352, "percentage": 4.26, "elapsed_time": "0:17:39", "remaining_time": "6:36:40", "throughput": 1542.95, "total_tokens": 1634080} {"current_steps": 7750, "total_steps": 181800, "loss": 0.2781, "lr": 2.131188118811881e-05, "epoch": 0.8525852585258525, "percentage": 4.26, "elapsed_time": "0:17:39", "remaining_time": "6:36:39", "throughput": 1542.93, "total_tokens": 1635104} {"current_steps": 7755, "total_steps": 181800, "loss": 0.1371, "lr": 2.1325632563256326e-05, "epoch": 0.8531353135313532, "percentage": 4.27, "elapsed_time": "0:17:40", "remaining_time": "6:36:39", "throughput": 1542.86, "total_tokens": 1636096} {"current_steps": 7760, "total_steps": 181800, "loss": 0.0917, "lr": 2.133938393839384e-05, "epoch": 0.8536853685368537, "percentage": 4.27, "elapsed_time": "0:17:41", "remaining_time": "6:36:38", "throughput": 1542.77, "total_tokens": 1637056} {"current_steps": 7765, "total_steps": 181800, "loss": 0.1922, "lr": 2.1353135313531356e-05, "epoch": 0.8542354235423543, "percentage": 4.27, "elapsed_time": "0:17:41", "remaining_time": "6:36:37", "throughput": 1542.84, "total_tokens": 1638176} {"current_steps": 7770, "total_steps": 181800, "loss": 0.1594, "lr": 2.1366886688668868e-05, "epoch": 0.8547854785478548, "percentage": 4.27, "elapsed_time": "0:17:42", "remaining_time": "6:36:36", "throughput": 1542.85, "total_tokens": 1639232} {"current_steps": 7775, "total_steps": 181800, "loss": 0.1881, "lr": 2.1380638063806383e-05, "epoch": 0.8553355335533553, "percentage": 4.28, "elapsed_time": "0:17:43", "remaining_time": "6:36:36", "throughput": 1542.88, "total_tokens": 1640320} {"current_steps": 7780, "total_steps": 181800, "loss": 0.1637, "lr": 2.1394389438943894e-05, "epoch": 0.8558855885588559, "percentage": 4.28, "elapsed_time": "0:17:43", "remaining_time": "6:36:35", "throughput": 1542.86, "total_tokens": 1641344} {"current_steps": 7785, "total_steps": 181800, "loss": 0.1808, "lr": 2.140814081408141e-05, "epoch": 0.8564356435643564, "percentage": 4.28, "elapsed_time": "0:17:44", "remaining_time": "6:36:34", "throughput": 1542.92, "total_tokens": 1642464} {"current_steps": 7790, "total_steps": 181800, "loss": 0.2396, "lr": 2.1421892189218924e-05, "epoch": 0.856985698569857, "percentage": 4.28, "elapsed_time": "0:17:45", "remaining_time": "6:36:33", "throughput": 1542.95, "total_tokens": 1643552} {"current_steps": 7795, "total_steps": 181800, "loss": 0.1472, "lr": 2.1435643564356436e-05, "epoch": 0.8575357535753575, "percentage": 4.29, "elapsed_time": "0:17:45", "remaining_time": "6:36:33", "throughput": 1542.95, "total_tokens": 1644608} {"current_steps": 7800, "total_steps": 181800, "loss": 0.2181, "lr": 2.144939493949395e-05, "epoch": 0.858085808580858, "percentage": 4.29, "elapsed_time": "0:17:46", "remaining_time": "6:36:32", "throughput": 1542.95, "total_tokens": 1645664} {"current_steps": 7805, "total_steps": 181800, "loss": 0.155, "lr": 2.1463146314631463e-05, "epoch": 0.8586358635863587, "percentage": 4.29, "elapsed_time": "0:17:47", "remaining_time": "6:36:32", "throughput": 1542.92, "total_tokens": 1646688} {"current_steps": 7810, "total_steps": 181800, "loss": 0.1809, "lr": 2.1476897689768978e-05, "epoch": 0.8591859185918592, "percentage": 4.3, "elapsed_time": "0:17:47", "remaining_time": "6:36:31", "throughput": 1542.89, "total_tokens": 1647712} {"current_steps": 7815, "total_steps": 181800, "loss": 0.1691, "lr": 2.1490649064906493e-05, "epoch": 0.8597359735973598, "percentage": 4.3, "elapsed_time": "0:17:48", "remaining_time": "6:36:30", "throughput": 1542.84, "total_tokens": 1648704} {"current_steps": 7820, "total_steps": 181800, "loss": 0.1402, "lr": 2.1504400440044008e-05, "epoch": 0.8602860286028603, "percentage": 4.3, "elapsed_time": "0:17:49", "remaining_time": "6:36:29", "throughput": 1542.81, "total_tokens": 1649728} {"current_steps": 7825, "total_steps": 181800, "loss": 0.1356, "lr": 2.151815181518152e-05, "epoch": 0.8608360836083608, "percentage": 4.3, "elapsed_time": "0:17:49", "remaining_time": "6:36:29", "throughput": 1542.81, "total_tokens": 1650784} {"current_steps": 7830, "total_steps": 181800, "loss": 0.1571, "lr": 2.1531903190319035e-05, "epoch": 0.8613861386138614, "percentage": 4.31, "elapsed_time": "0:17:50", "remaining_time": "6:36:28", "throughput": 1542.85, "total_tokens": 1651872} {"current_steps": 7835, "total_steps": 181800, "loss": 0.1506, "lr": 2.1545654565456546e-05, "epoch": 0.8619361936193619, "percentage": 4.31, "elapsed_time": "0:17:51", "remaining_time": "6:36:27", "throughput": 1542.82, "total_tokens": 1652896} {"current_steps": 7840, "total_steps": 181800, "loss": 0.1626, "lr": 2.155940594059406e-05, "epoch": 0.8624862486248625, "percentage": 4.31, "elapsed_time": "0:17:52", "remaining_time": "6:36:26", "throughput": 1542.83, "total_tokens": 1653952} {"current_steps": 7845, "total_steps": 181800, "loss": 0.2294, "lr": 2.1573157315731573e-05, "epoch": 0.863036303630363, "percentage": 4.32, "elapsed_time": "0:17:52", "remaining_time": "6:36:26", "throughput": 1542.8, "total_tokens": 1654976} {"current_steps": 7850, "total_steps": 181800, "loss": 0.1751, "lr": 2.1586908690869088e-05, "epoch": 0.8635863586358636, "percentage": 4.32, "elapsed_time": "0:17:53", "remaining_time": "6:36:25", "throughput": 1542.84, "total_tokens": 1656064} {"current_steps": 7855, "total_steps": 181800, "loss": 0.1601, "lr": 2.16006600660066e-05, "epoch": 0.8641364136413642, "percentage": 4.32, "elapsed_time": "0:17:54", "remaining_time": "6:36:24", "throughput": 1542.84, "total_tokens": 1657120} {"current_steps": 7860, "total_steps": 181800, "loss": 0.1724, "lr": 2.1614411441144118e-05, "epoch": 0.8646864686468647, "percentage": 4.32, "elapsed_time": "0:17:54", "remaining_time": "6:36:24", "throughput": 1542.81, "total_tokens": 1658144} {"current_steps": 7865, "total_steps": 181800, "loss": 0.1887, "lr": 2.162816281628163e-05, "epoch": 0.8652365236523653, "percentage": 4.33, "elapsed_time": "0:17:55", "remaining_time": "6:36:23", "throughput": 1542.76, "total_tokens": 1659136} {"current_steps": 7870, "total_steps": 181800, "loss": 0.2408, "lr": 2.1641914191419145e-05, "epoch": 0.8657865786578658, "percentage": 4.33, "elapsed_time": "0:17:56", "remaining_time": "6:36:22", "throughput": 1542.76, "total_tokens": 1660192} {"current_steps": 7875, "total_steps": 181800, "loss": 0.1625, "lr": 2.1655665566556656e-05, "epoch": 0.8663366336633663, "percentage": 4.33, "elapsed_time": "0:17:56", "remaining_time": "6:36:21", "throughput": 1542.79, "total_tokens": 1661280} {"current_steps": 7880, "total_steps": 181800, "loss": 0.1314, "lr": 2.166941694169417e-05, "epoch": 0.8668866886688669, "percentage": 4.33, "elapsed_time": "0:17:57", "remaining_time": "6:36:21", "throughput": 1542.79, "total_tokens": 1662336} {"current_steps": 7885, "total_steps": 181800, "loss": 0.1246, "lr": 2.1683168316831683e-05, "epoch": 0.8674367436743674, "percentage": 4.34, "elapsed_time": "0:17:58", "remaining_time": "6:36:20", "throughput": 1542.8, "total_tokens": 1663392} {"current_steps": 7890, "total_steps": 181800, "loss": 0.2847, "lr": 2.1696919691969198e-05, "epoch": 0.8679867986798679, "percentage": 4.34, "elapsed_time": "0:17:58", "remaining_time": "6:36:19", "throughput": 1542.77, "total_tokens": 1664416} {"current_steps": 7895, "total_steps": 181800, "loss": 0.2766, "lr": 2.171067106710671e-05, "epoch": 0.8685368536853685, "percentage": 4.34, "elapsed_time": "0:17:59", "remaining_time": "6:36:19", "throughput": 1542.81, "total_tokens": 1665504} {"current_steps": 7900, "total_steps": 181800, "loss": 0.1321, "lr": 2.1724422442244225e-05, "epoch": 0.8690869086908691, "percentage": 4.35, "elapsed_time": "0:18:00", "remaining_time": "6:36:18", "throughput": 1542.84, "total_tokens": 1666592} {"current_steps": 7905, "total_steps": 181800, "loss": 0.2414, "lr": 2.1738173817381736e-05, "epoch": 0.8696369636963697, "percentage": 4.35, "elapsed_time": "0:18:00", "remaining_time": "6:36:17", "throughput": 1542.87, "total_tokens": 1667680} {"current_steps": 7910, "total_steps": 181800, "loss": 0.2429, "lr": 2.1751925192519255e-05, "epoch": 0.8701870187018702, "percentage": 4.35, "elapsed_time": "0:18:01", "remaining_time": "6:36:16", "throughput": 1542.87, "total_tokens": 1668736} {"current_steps": 7915, "total_steps": 181800, "loss": 0.1747, "lr": 2.1765676567656767e-05, "epoch": 0.8707370737073707, "percentage": 4.35, "elapsed_time": "0:18:02", "remaining_time": "6:36:16", "throughput": 1542.9, "total_tokens": 1669824} {"current_steps": 7920, "total_steps": 181800, "loss": 0.1283, "lr": 2.177942794279428e-05, "epoch": 0.8712871287128713, "percentage": 4.36, "elapsed_time": "0:18:02", "remaining_time": "6:36:15", "throughput": 1542.91, "total_tokens": 1670880} {"current_steps": 7925, "total_steps": 181800, "loss": 0.1486, "lr": 2.1793179317931793e-05, "epoch": 0.8718371837183718, "percentage": 4.36, "elapsed_time": "0:18:03", "remaining_time": "6:36:14", "throughput": 1542.91, "total_tokens": 1671936} {"current_steps": 7930, "total_steps": 181800, "loss": 0.1557, "lr": 2.1806930693069308e-05, "epoch": 0.8723872387238724, "percentage": 4.36, "elapsed_time": "0:18:04", "remaining_time": "6:36:14", "throughput": 1542.85, "total_tokens": 1672928} {"current_steps": 7935, "total_steps": 181800, "loss": 0.1314, "lr": 2.182068206820682e-05, "epoch": 0.8729372937293729, "percentage": 4.36, "elapsed_time": "0:18:04", "remaining_time": "6:36:13", "throughput": 1542.86, "total_tokens": 1673984} {"current_steps": 7940, "total_steps": 181800, "loss": 0.132, "lr": 2.1834433443344335e-05, "epoch": 0.8734873487348734, "percentage": 4.37, "elapsed_time": "0:18:05", "remaining_time": "6:36:12", "throughput": 1542.86, "total_tokens": 1675040} {"current_steps": 7945, "total_steps": 181800, "loss": 0.1904, "lr": 2.1848184818481847e-05, "epoch": 0.8740374037403741, "percentage": 4.37, "elapsed_time": "0:18:06", "remaining_time": "6:36:11", "throughput": 1542.86, "total_tokens": 1676096} {"current_steps": 7950, "total_steps": 181800, "loss": 0.1386, "lr": 2.186193619361936e-05, "epoch": 0.8745874587458746, "percentage": 4.37, "elapsed_time": "0:18:07", "remaining_time": "6:36:11", "throughput": 1542.9, "total_tokens": 1677184} {"current_steps": 7955, "total_steps": 181800, "loss": 0.1777, "lr": 2.1875687568756877e-05, "epoch": 0.8751375137513752, "percentage": 4.38, "elapsed_time": "0:18:07", "remaining_time": "6:36:10", "throughput": 1542.96, "total_tokens": 1678304} {"current_steps": 7960, "total_steps": 181800, "loss": 0.1213, "lr": 2.1889438943894392e-05, "epoch": 0.8756875687568757, "percentage": 4.38, "elapsed_time": "0:18:08", "remaining_time": "6:36:09", "throughput": 1542.96, "total_tokens": 1679360} {"current_steps": 7965, "total_steps": 181800, "loss": 0.1816, "lr": 2.1903190319031903e-05, "epoch": 0.8762376237623762, "percentage": 4.38, "elapsed_time": "0:18:09", "remaining_time": "6:36:09", "throughput": 1542.93, "total_tokens": 1680384} {"current_steps": 7970, "total_steps": 181800, "loss": 0.1592, "lr": 2.191694169416942e-05, "epoch": 0.8767876787678768, "percentage": 4.38, "elapsed_time": "0:18:09", "remaining_time": "6:36:08", "throughput": 1542.94, "total_tokens": 1681440} {"current_steps": 7975, "total_steps": 181800, "loss": 0.1487, "lr": 2.193069306930693e-05, "epoch": 0.8773377337733773, "percentage": 4.39, "elapsed_time": "0:18:10", "remaining_time": "6:36:07", "throughput": 1542.91, "total_tokens": 1682464} {"current_steps": 7980, "total_steps": 181800, "loss": 0.1956, "lr": 2.1944444444444445e-05, "epoch": 0.8778877887788779, "percentage": 4.39, "elapsed_time": "0:18:11", "remaining_time": "6:36:06", "throughput": 1542.94, "total_tokens": 1683552} {"current_steps": 7985, "total_steps": 181800, "loss": 0.183, "lr": 2.195819581958196e-05, "epoch": 0.8784378437843784, "percentage": 4.39, "elapsed_time": "0:18:11", "remaining_time": "6:36:06", "throughput": 1542.92, "total_tokens": 1684576} {"current_steps": 7990, "total_steps": 181800, "loss": 0.0607, "lr": 2.1971947194719472e-05, "epoch": 0.878987898789879, "percentage": 4.39, "elapsed_time": "0:18:12", "remaining_time": "6:36:05", "throughput": 1542.95, "total_tokens": 1685664} {"current_steps": 7995, "total_steps": 181800, "loss": 0.139, "lr": 2.1985698569856987e-05, "epoch": 0.8795379537953796, "percentage": 4.4, "elapsed_time": "0:18:13", "remaining_time": "6:36:04", "throughput": 1542.96, "total_tokens": 1686720} {"current_steps": 8000, "total_steps": 181800, "loss": 0.2205, "lr": 2.1999449944994502e-05, "epoch": 0.8800880088008801, "percentage": 4.4, "elapsed_time": "0:18:13", "remaining_time": "6:36:03", "throughput": 1542.93, "total_tokens": 1687744} {"current_steps": 8005, "total_steps": 181800, "loss": 0.1633, "lr": 2.2013201320132017e-05, "epoch": 0.8806380638063807, "percentage": 4.4, "elapsed_time": "0:18:14", "remaining_time": "6:36:03", "throughput": 1542.94, "total_tokens": 1688800} {"current_steps": 8010, "total_steps": 181800, "loss": 0.1965, "lr": 2.202695269526953e-05, "epoch": 0.8811881188118812, "percentage": 4.41, "elapsed_time": "0:18:15", "remaining_time": "6:36:02", "throughput": 1542.94, "total_tokens": 1689856} {"current_steps": 8015, "total_steps": 181800, "loss": 0.2205, "lr": 2.2040704070407044e-05, "epoch": 0.8817381738173817, "percentage": 4.41, "elapsed_time": "0:18:15", "remaining_time": "6:36:01", "throughput": 1542.94, "total_tokens": 1690912} {"current_steps": 8020, "total_steps": 181800, "loss": 0.1862, "lr": 2.2054455445544555e-05, "epoch": 0.8822882288228823, "percentage": 4.41, "elapsed_time": "0:18:16", "remaining_time": "6:36:01", "throughput": 1542.91, "total_tokens": 1691936} {"current_steps": 8025, "total_steps": 181800, "loss": 0.2822, "lr": 2.206820682068207e-05, "epoch": 0.8828382838283828, "percentage": 4.41, "elapsed_time": "0:18:17", "remaining_time": "6:36:00", "throughput": 1542.89, "total_tokens": 1692960} {"current_steps": 8030, "total_steps": 181800, "loss": 0.1285, "lr": 2.2081958195819582e-05, "epoch": 0.8833883388338833, "percentage": 4.42, "elapsed_time": "0:18:17", "remaining_time": "6:35:59", "throughput": 1542.89, "total_tokens": 1694016} {"current_steps": 8035, "total_steps": 181800, "loss": 0.1096, "lr": 2.2095709570957097e-05, "epoch": 0.8839383938393839, "percentage": 4.42, "elapsed_time": "0:18:18", "remaining_time": "6:35:58", "throughput": 1542.93, "total_tokens": 1695104} {"current_steps": 8040, "total_steps": 181800, "loss": 0.0902, "lr": 2.210946094609461e-05, "epoch": 0.8844884488448845, "percentage": 4.42, "elapsed_time": "0:18:19", "remaining_time": "6:35:58", "throughput": 1542.96, "total_tokens": 1696192} {"current_steps": 8045, "total_steps": 181800, "loss": 0.1815, "lr": 2.2123212321232124e-05, "epoch": 0.8850385038503851, "percentage": 4.43, "elapsed_time": "0:18:19", "remaining_time": "6:35:57", "throughput": 1543.0, "total_tokens": 1697280} {"current_steps": 8050, "total_steps": 181800, "loss": 0.1593, "lr": 2.213696369636964e-05, "epoch": 0.8855885588558856, "percentage": 4.43, "elapsed_time": "0:18:20", "remaining_time": "6:35:56", "throughput": 1542.92, "total_tokens": 1698240} {"current_steps": 8055, "total_steps": 181800, "loss": 0.1418, "lr": 2.2150715071507154e-05, "epoch": 0.8861386138613861, "percentage": 4.43, "elapsed_time": "0:18:21", "remaining_time": "6:35:55", "throughput": 1542.98, "total_tokens": 1699360} {"current_steps": 8060, "total_steps": 181800, "loss": 0.1428, "lr": 2.2164466446644666e-05, "epoch": 0.8866886688668867, "percentage": 4.43, "elapsed_time": "0:18:22", "remaining_time": "6:35:55", "throughput": 1542.98, "total_tokens": 1700416} {"current_steps": 8065, "total_steps": 181800, "loss": 0.1234, "lr": 2.217821782178218e-05, "epoch": 0.8872387238723872, "percentage": 4.44, "elapsed_time": "0:18:22", "remaining_time": "6:35:54", "throughput": 1543.01, "total_tokens": 1701504} {"current_steps": 8070, "total_steps": 181800, "loss": 0.1199, "lr": 2.2191969196919692e-05, "epoch": 0.8877887788778878, "percentage": 4.44, "elapsed_time": "0:18:23", "remaining_time": "6:35:53", "throughput": 1543.01, "total_tokens": 1702560} {"current_steps": 8075, "total_steps": 181800, "loss": 0.1598, "lr": 2.2205720572057207e-05, "epoch": 0.8883388338833883, "percentage": 4.44, "elapsed_time": "0:18:24", "remaining_time": "6:35:53", "throughput": 1542.98, "total_tokens": 1703584} {"current_steps": 8080, "total_steps": 181800, "loss": 0.1581, "lr": 2.221947194719472e-05, "epoch": 0.8888888888888888, "percentage": 4.44, "elapsed_time": "0:18:24", "remaining_time": "6:35:52", "throughput": 1542.93, "total_tokens": 1704576} {"current_steps": 8085, "total_steps": 181800, "loss": 0.2066, "lr": 2.2233223322332234e-05, "epoch": 0.8894389438943895, "percentage": 4.45, "elapsed_time": "0:18:25", "remaining_time": "6:35:51", "throughput": 1543.01, "total_tokens": 1705728} {"current_steps": 8090, "total_steps": 181800, "loss": 0.1238, "lr": 2.2246974697469746e-05, "epoch": 0.88998899889989, "percentage": 4.45, "elapsed_time": "0:18:26", "remaining_time": "6:35:51", "throughput": 1543.01, "total_tokens": 1706784} {"current_steps": 8095, "total_steps": 181800, "loss": 0.0988, "lr": 2.2260726072607264e-05, "epoch": 0.8905390539053906, "percentage": 4.45, "elapsed_time": "0:18:26", "remaining_time": "6:35:50", "throughput": 1543.1, "total_tokens": 1707936} {"current_steps": 8100, "total_steps": 181800, "loss": 0.2002, "lr": 2.2274477447744776e-05, "epoch": 0.8910891089108911, "percentage": 4.46, "elapsed_time": "0:18:27", "remaining_time": "6:35:49", "throughput": 1543.16, "total_tokens": 1709056} {"current_steps": 8105, "total_steps": 181800, "loss": 0.131, "lr": 2.228822882288229e-05, "epoch": 0.8916391639163916, "percentage": 4.46, "elapsed_time": "0:18:28", "remaining_time": "6:35:49", "throughput": 1543.2, "total_tokens": 1710144} {"current_steps": 8110, "total_steps": 181800, "loss": 0.2188, "lr": 2.2301980198019802e-05, "epoch": 0.8921892189218922, "percentage": 4.46, "elapsed_time": "0:18:28", "remaining_time": "6:35:48", "throughput": 1543.23, "total_tokens": 1711232} {"current_steps": 8115, "total_steps": 181800, "loss": 0.1154, "lr": 2.2315731573157317e-05, "epoch": 0.8927392739273927, "percentage": 4.46, "elapsed_time": "0:18:29", "remaining_time": "6:35:47", "throughput": 1543.27, "total_tokens": 1712320} {"current_steps": 8120, "total_steps": 181800, "loss": 0.2318, "lr": 2.232948294829483e-05, "epoch": 0.8932893289328933, "percentage": 4.47, "elapsed_time": "0:18:30", "remaining_time": "6:35:46", "throughput": 1543.27, "total_tokens": 1713376} {"current_steps": 8125, "total_steps": 181800, "loss": 0.1741, "lr": 2.2343234323432344e-05, "epoch": 0.8938393839383938, "percentage": 4.47, "elapsed_time": "0:18:30", "remaining_time": "6:35:46", "throughput": 1543.27, "total_tokens": 1714432} {"current_steps": 8130, "total_steps": 181800, "loss": 0.1954, "lr": 2.2356985698569856e-05, "epoch": 0.8943894389438944, "percentage": 4.47, "elapsed_time": "0:18:31", "remaining_time": "6:35:45", "throughput": 1543.18, "total_tokens": 1715392} {"current_steps": 8135, "total_steps": 181800, "loss": 0.1646, "lr": 2.237073707370737e-05, "epoch": 0.894939493949395, "percentage": 4.47, "elapsed_time": "0:18:32", "remaining_time": "6:35:44", "throughput": 1543.1, "total_tokens": 1716352} {"current_steps": 8140, "total_steps": 181800, "loss": 0.1587, "lr": 2.2384488448844886e-05, "epoch": 0.8954895489548955, "percentage": 4.48, "elapsed_time": "0:18:32", "remaining_time": "6:35:44", "throughput": 1543.07, "total_tokens": 1717376} {"current_steps": 8145, "total_steps": 181800, "loss": 0.098, "lr": 2.23982398239824e-05, "epoch": 0.8960396039603961, "percentage": 4.48, "elapsed_time": "0:18:33", "remaining_time": "6:35:43", "throughput": 1543.13, "total_tokens": 1718496} {"current_steps": 8150, "total_steps": 181800, "loss": 0.1612, "lr": 2.2411991199119913e-05, "epoch": 0.8965896589658966, "percentage": 4.48, "elapsed_time": "0:18:34", "remaining_time": "6:35:42", "throughput": 1543.13, "total_tokens": 1719552} {"current_steps": 8155, "total_steps": 181800, "loss": 0.1375, "lr": 2.2425742574257428e-05, "epoch": 0.8971397139713971, "percentage": 4.49, "elapsed_time": "0:18:35", "remaining_time": "6:35:41", "throughput": 1543.16, "total_tokens": 1720640} {"current_steps": 8160, "total_steps": 181800, "loss": 0.1069, "lr": 2.243949394939494e-05, "epoch": 0.8976897689768977, "percentage": 4.49, "elapsed_time": "0:18:35", "remaining_time": "6:35:41", "throughput": 1543.2, "total_tokens": 1721728} {"current_steps": 8165, "total_steps": 181800, "loss": 0.1962, "lr": 2.2453245324532454e-05, "epoch": 0.8982398239823982, "percentage": 4.49, "elapsed_time": "0:18:36", "remaining_time": "6:35:40", "throughput": 1543.17, "total_tokens": 1722752} {"current_steps": 8170, "total_steps": 181800, "loss": 0.223, "lr": 2.2466996699669966e-05, "epoch": 0.8987898789878987, "percentage": 4.49, "elapsed_time": "0:18:37", "remaining_time": "6:35:39", "throughput": 1543.24, "total_tokens": 1723872} {"current_steps": 8175, "total_steps": 181800, "loss": 0.15, "lr": 2.248074807480748e-05, "epoch": 0.8993399339933993, "percentage": 4.5, "elapsed_time": "0:18:37", "remaining_time": "6:35:38", "throughput": 1543.22, "total_tokens": 1724896} {"current_steps": 8180, "total_steps": 181800, "loss": 0.2364, "lr": 2.2494499449944996e-05, "epoch": 0.8998899889988999, "percentage": 4.5, "elapsed_time": "0:18:38", "remaining_time": "6:35:38", "throughput": 1543.25, "total_tokens": 1725984} {"current_steps": 8185, "total_steps": 181800, "loss": 0.1294, "lr": 2.2508250825082508e-05, "epoch": 0.9004400440044005, "percentage": 4.5, "elapsed_time": "0:18:39", "remaining_time": "6:35:37", "throughput": 1543.25, "total_tokens": 1727040} {"current_steps": 8190, "total_steps": 181800, "loss": 0.1285, "lr": 2.2522002200220023e-05, "epoch": 0.900990099009901, "percentage": 4.5, "elapsed_time": "0:18:39", "remaining_time": "6:35:36", "throughput": 1543.23, "total_tokens": 1728064} {"current_steps": 8195, "total_steps": 181800, "loss": 0.1926, "lr": 2.2535753575357538e-05, "epoch": 0.9015401540154016, "percentage": 4.51, "elapsed_time": "0:18:40", "remaining_time": "6:35:35", "throughput": 1543.21, "total_tokens": 1729088} {"current_steps": 8200, "total_steps": 181800, "loss": 0.1864, "lr": 2.2549504950495053e-05, "epoch": 0.9020902090209021, "percentage": 4.51, "elapsed_time": "0:18:41", "remaining_time": "6:35:35", "throughput": 1543.27, "total_tokens": 1730208} {"current_steps": 8205, "total_steps": 181800, "loss": 0.1633, "lr": 2.2563256325632565e-05, "epoch": 0.9026402640264026, "percentage": 4.51, "elapsed_time": "0:18:41", "remaining_time": "6:35:34", "throughput": 1543.21, "total_tokens": 1731200} {"current_steps": 8210, "total_steps": 181800, "loss": 0.1923, "lr": 2.257700770077008e-05, "epoch": 0.9031903190319032, "percentage": 4.52, "elapsed_time": "0:18:42", "remaining_time": "6:35:33", "throughput": 1543.18, "total_tokens": 1732224} {"current_steps": 8215, "total_steps": 181800, "loss": 0.1535, "lr": 2.259075907590759e-05, "epoch": 0.9037403740374037, "percentage": 4.52, "elapsed_time": "0:18:43", "remaining_time": "6:35:33", "throughput": 1543.18, "total_tokens": 1733280} {"current_steps": 8220, "total_steps": 181800, "loss": 0.1386, "lr": 2.2604510451045106e-05, "epoch": 0.9042904290429042, "percentage": 4.52, "elapsed_time": "0:18:43", "remaining_time": "6:35:32", "throughput": 1543.19, "total_tokens": 1734336} {"current_steps": 8225, "total_steps": 181800, "loss": 0.1439, "lr": 2.2618261826182618e-05, "epoch": 0.9048404840484049, "percentage": 4.52, "elapsed_time": "0:18:44", "remaining_time": "6:35:31", "throughput": 1543.16, "total_tokens": 1735360} {"current_steps": 8230, "total_steps": 181800, "loss": 0.1476, "lr": 2.2632013201320133e-05, "epoch": 0.9053905390539054, "percentage": 4.53, "elapsed_time": "0:18:45", "remaining_time": "6:35:31", "throughput": 1543.19, "total_tokens": 1736448} {"current_steps": 8235, "total_steps": 181800, "loss": 0.1363, "lr": 2.2645764576457648e-05, "epoch": 0.905940594059406, "percentage": 4.53, "elapsed_time": "0:18:45", "remaining_time": "6:35:30", "throughput": 1543.21, "total_tokens": 1737536} {"current_steps": 8240, "total_steps": 181800, "loss": 0.1103, "lr": 2.2659515951595163e-05, "epoch": 0.9064906490649065, "percentage": 4.53, "elapsed_time": "0:18:46", "remaining_time": "6:35:29", "throughput": 1543.16, "total_tokens": 1738528} {"current_steps": 8245, "total_steps": 181800, "loss": 0.191, "lr": 2.2673267326732675e-05, "epoch": 0.907040704070407, "percentage": 4.54, "elapsed_time": "0:18:47", "remaining_time": "6:35:28", "throughput": 1543.17, "total_tokens": 1739584} {"current_steps": 8250, "total_steps": 181800, "loss": 0.1412, "lr": 2.268701870187019e-05, "epoch": 0.9075907590759076, "percentage": 4.54, "elapsed_time": "0:18:47", "remaining_time": "6:35:28", "throughput": 1543.15, "total_tokens": 1740608} {"current_steps": 8255, "total_steps": 181800, "loss": 0.1994, "lr": 2.27007700770077e-05, "epoch": 0.9081408140814081, "percentage": 4.54, "elapsed_time": "0:18:48", "remaining_time": "6:35:27", "throughput": 1543.15, "total_tokens": 1741664} {"current_steps": 8260, "total_steps": 181800, "loss": 0.0931, "lr": 2.2714521452145216e-05, "epoch": 0.9086908690869087, "percentage": 4.54, "elapsed_time": "0:18:49", "remaining_time": "6:35:26", "throughput": 1543.1, "total_tokens": 1742656} {"current_steps": 8265, "total_steps": 181800, "loss": 0.2828, "lr": 2.2728272827282728e-05, "epoch": 0.9092409240924092, "percentage": 4.55, "elapsed_time": "0:18:50", "remaining_time": "6:35:25", "throughput": 1543.05, "total_tokens": 1743648} {"current_steps": 8270, "total_steps": 181800, "loss": 0.1657, "lr": 2.2742024202420243e-05, "epoch": 0.9097909790979097, "percentage": 4.55, "elapsed_time": "0:18:50", "remaining_time": "6:35:25", "throughput": 1543.06, "total_tokens": 1744704} {"current_steps": 8275, "total_steps": 181800, "loss": 0.1117, "lr": 2.2755775577557755e-05, "epoch": 0.9103410341034104, "percentage": 4.55, "elapsed_time": "0:18:51", "remaining_time": "6:35:24", "throughput": 1543.06, "total_tokens": 1745760} {"current_steps": 8280, "total_steps": 181800, "loss": 0.1796, "lr": 2.276952695269527e-05, "epoch": 0.9108910891089109, "percentage": 4.55, "elapsed_time": "0:18:52", "remaining_time": "6:35:23", "throughput": 1543.13, "total_tokens": 1746880} {"current_steps": 8285, "total_steps": 181800, "loss": 0.1253, "lr": 2.2783278327832785e-05, "epoch": 0.9114411441144115, "percentage": 4.56, "elapsed_time": "0:18:52", "remaining_time": "6:35:22", "throughput": 1543.16, "total_tokens": 1747968} {"current_steps": 8290, "total_steps": 181800, "loss": 0.1694, "lr": 2.27970297029703e-05, "epoch": 0.911991199119912, "percentage": 4.56, "elapsed_time": "0:18:53", "remaining_time": "6:35:22", "throughput": 1543.14, "total_tokens": 1748992} {"current_steps": 8295, "total_steps": 181800, "loss": 0.1241, "lr": 2.281078107810781e-05, "epoch": 0.9125412541254125, "percentage": 4.56, "elapsed_time": "0:18:54", "remaining_time": "6:35:21", "throughput": 1543.14, "total_tokens": 1750048} {"current_steps": 8300, "total_steps": 181800, "loss": 0.2002, "lr": 2.2824532453245327e-05, "epoch": 0.9130913091309131, "percentage": 4.57, "elapsed_time": "0:18:54", "remaining_time": "6:35:20", "throughput": 1543.12, "total_tokens": 1751072} {"current_steps": 8305, "total_steps": 181800, "loss": 0.2038, "lr": 2.2838283828382838e-05, "epoch": 0.9136413641364136, "percentage": 4.57, "elapsed_time": "0:18:55", "remaining_time": "6:35:19", "throughput": 1543.09, "total_tokens": 1752096} {"current_steps": 8310, "total_steps": 181800, "loss": 0.1867, "lr": 2.2852035203520353e-05, "epoch": 0.9141914191419142, "percentage": 4.57, "elapsed_time": "0:18:56", "remaining_time": "6:35:19", "throughput": 1543.09, "total_tokens": 1753152} {"current_steps": 8315, "total_steps": 181800, "loss": 0.1267, "lr": 2.2865786578657865e-05, "epoch": 0.9147414741474147, "percentage": 4.57, "elapsed_time": "0:18:56", "remaining_time": "6:35:18", "throughput": 1543.12, "total_tokens": 1754240} {"current_steps": 8320, "total_steps": 181800, "loss": 0.1535, "lr": 2.287953795379538e-05, "epoch": 0.9152915291529153, "percentage": 4.58, "elapsed_time": "0:18:57", "remaining_time": "6:35:17", "throughput": 1543.15, "total_tokens": 1755328} {"current_steps": 8325, "total_steps": 181800, "loss": 0.1204, "lr": 2.289328932893289e-05, "epoch": 0.9158415841584159, "percentage": 4.58, "elapsed_time": "0:18:58", "remaining_time": "6:35:17", "throughput": 1543.15, "total_tokens": 1756384} {"current_steps": 8330, "total_steps": 181800, "loss": 0.1453, "lr": 2.290704070407041e-05, "epoch": 0.9163916391639164, "percentage": 4.58, "elapsed_time": "0:18:58", "remaining_time": "6:35:16", "throughput": 1543.1, "total_tokens": 1757376} {"current_steps": 8335, "total_steps": 181800, "loss": 0.1434, "lr": 2.2920792079207922e-05, "epoch": 0.916941694169417, "percentage": 4.58, "elapsed_time": "0:18:59", "remaining_time": "6:35:15", "throughput": 1543.1, "total_tokens": 1758432} {"current_steps": 8340, "total_steps": 181800, "loss": 0.1387, "lr": 2.2934543454345437e-05, "epoch": 0.9174917491749175, "percentage": 4.59, "elapsed_time": "0:19:00", "remaining_time": "6:35:14", "throughput": 1543.05, "total_tokens": 1759424} {"current_steps": 8345, "total_steps": 181800, "loss": 0.1771, "lr": 2.294829482948295e-05, "epoch": 0.918041804180418, "percentage": 4.59, "elapsed_time": "0:19:00", "remaining_time": "6:35:14", "throughput": 1543.05, "total_tokens": 1760480} {"current_steps": 8350, "total_steps": 181800, "loss": 0.1107, "lr": 2.2962046204620464e-05, "epoch": 0.9185918591859186, "percentage": 4.59, "elapsed_time": "0:19:01", "remaining_time": "6:35:13", "throughput": 1543.06, "total_tokens": 1761536} {"current_steps": 8355, "total_steps": 181800, "loss": 0.1482, "lr": 2.2975797579757975e-05, "epoch": 0.9191419141914191, "percentage": 4.6, "elapsed_time": "0:19:02", "remaining_time": "6:35:12", "throughput": 1543.09, "total_tokens": 1762624} {"current_steps": 8360, "total_steps": 181800, "loss": 0.2177, "lr": 2.298954895489549e-05, "epoch": 0.9196919691969196, "percentage": 4.6, "elapsed_time": "0:19:02", "remaining_time": "6:35:12", "throughput": 1543.07, "total_tokens": 1763648} {"current_steps": 8365, "total_steps": 181800, "loss": 0.1352, "lr": 2.3003300330033002e-05, "epoch": 0.9202420242024203, "percentage": 4.6, "elapsed_time": "0:19:03", "remaining_time": "6:35:11", "throughput": 1543.04, "total_tokens": 1764672} {"current_steps": 8370, "total_steps": 181800, "loss": 0.2162, "lr": 2.3017051705170517e-05, "epoch": 0.9207920792079208, "percentage": 4.6, "elapsed_time": "0:19:04", "remaining_time": "6:35:10", "throughput": 1543.05, "total_tokens": 1765728} {"current_steps": 8375, "total_steps": 181800, "loss": 0.0892, "lr": 2.3030803080308032e-05, "epoch": 0.9213421342134214, "percentage": 4.61, "elapsed_time": "0:19:04", "remaining_time": "6:35:09", "throughput": 1543.05, "total_tokens": 1766784} {"current_steps": 8380, "total_steps": 181800, "loss": 0.1746, "lr": 2.3044554455445547e-05, "epoch": 0.9218921892189219, "percentage": 4.61, "elapsed_time": "0:19:05", "remaining_time": "6:35:09", "throughput": 1543.1, "total_tokens": 1767904} {"current_steps": 8385, "total_steps": 181800, "loss": 0.196, "lr": 2.305830583058306e-05, "epoch": 0.9224422442244224, "percentage": 4.61, "elapsed_time": "0:19:06", "remaining_time": "6:35:08", "throughput": 1543.08, "total_tokens": 1768928} {"current_steps": 8390, "total_steps": 181800, "loss": 0.0958, "lr": 2.3072057205720574e-05, "epoch": 0.922992299229923, "percentage": 4.61, "elapsed_time": "0:19:07", "remaining_time": "6:35:07", "throughput": 1543.11, "total_tokens": 1770016} {"current_steps": 8395, "total_steps": 181800, "loss": 0.1065, "lr": 2.308580858085809e-05, "epoch": 0.9235423542354235, "percentage": 4.62, "elapsed_time": "0:19:07", "remaining_time": "6:35:07", "throughput": 1543.09, "total_tokens": 1771040} {"current_steps": 8400, "total_steps": 181800, "loss": 0.1179, "lr": 2.30995599559956e-05, "epoch": 0.9240924092409241, "percentage": 4.62, "elapsed_time": "0:19:08", "remaining_time": "6:35:06", "throughput": 1543.1, "total_tokens": 1772096} {"current_steps": 8405, "total_steps": 181800, "loss": 0.2196, "lr": 2.3113311331133115e-05, "epoch": 0.9246424642464246, "percentage": 4.62, "elapsed_time": "0:19:09", "remaining_time": "6:35:05", "throughput": 1543.13, "total_tokens": 1773184} {"current_steps": 8410, "total_steps": 181800, "loss": 0.1196, "lr": 2.3127062706270627e-05, "epoch": 0.9251925192519251, "percentage": 4.63, "elapsed_time": "0:19:09", "remaining_time": "6:35:04", "throughput": 1543.13, "total_tokens": 1774240} {"current_steps": 8415, "total_steps": 181800, "loss": 0.1255, "lr": 2.3140814081408142e-05, "epoch": 0.9257425742574258, "percentage": 4.63, "elapsed_time": "0:19:10", "remaining_time": "6:35:04", "throughput": 1543.19, "total_tokens": 1775360} {"current_steps": 8420, "total_steps": 181800, "loss": 0.1272, "lr": 2.3154565456545654e-05, "epoch": 0.9262926292629263, "percentage": 4.63, "elapsed_time": "0:19:11", "remaining_time": "6:35:03", "throughput": 1543.25, "total_tokens": 1776480} {"current_steps": 8425, "total_steps": 181800, "loss": 0.1082, "lr": 2.3168316831683172e-05, "epoch": 0.9268426842684269, "percentage": 4.63, "elapsed_time": "0:19:11", "remaining_time": "6:35:02", "throughput": 1543.25, "total_tokens": 1777536} {"current_steps": 8430, "total_steps": 181800, "loss": 0.1787, "lr": 2.3182068206820684e-05, "epoch": 0.9273927392739274, "percentage": 4.64, "elapsed_time": "0:19:12", "remaining_time": "6:35:02", "throughput": 1543.28, "total_tokens": 1778624} {"current_steps": 8435, "total_steps": 181800, "loss": 0.2179, "lr": 2.31958195819582e-05, "epoch": 0.9279427942794279, "percentage": 4.64, "elapsed_time": "0:19:13", "remaining_time": "6:35:01", "throughput": 1543.23, "total_tokens": 1779616} {"current_steps": 8440, "total_steps": 181800, "loss": 0.1785, "lr": 2.320957095709571e-05, "epoch": 0.9284928492849285, "percentage": 4.64, "elapsed_time": "0:19:13", "remaining_time": "6:35:00", "throughput": 1543.23, "total_tokens": 1780672} {"current_steps": 8445, "total_steps": 181800, "loss": 0.1646, "lr": 2.3223322332233226e-05, "epoch": 0.929042904290429, "percentage": 4.65, "elapsed_time": "0:19:14", "remaining_time": "6:34:59", "throughput": 1543.29, "total_tokens": 1781792} {"current_steps": 8450, "total_steps": 181800, "loss": 0.1669, "lr": 2.3237073707370737e-05, "epoch": 0.9295929592959296, "percentage": 4.65, "elapsed_time": "0:19:15", "remaining_time": "6:34:59", "throughput": 1543.26, "total_tokens": 1782816} {"current_steps": 8455, "total_steps": 181800, "loss": 0.2027, "lr": 2.3250825082508252e-05, "epoch": 0.9301430143014301, "percentage": 4.65, "elapsed_time": "0:19:15", "remaining_time": "6:34:58", "throughput": 1543.31, "total_tokens": 1783936} {"current_steps": 8460, "total_steps": 181800, "loss": 0.2536, "lr": 2.3264576457645764e-05, "epoch": 0.9306930693069307, "percentage": 4.65, "elapsed_time": "0:19:16", "remaining_time": "6:34:57", "throughput": 1543.32, "total_tokens": 1784992} {"current_steps": 8465, "total_steps": 181800, "loss": 0.1392, "lr": 2.327832783278328e-05, "epoch": 0.9312431243124313, "percentage": 4.66, "elapsed_time": "0:19:17", "remaining_time": "6:34:57", "throughput": 1543.37, "total_tokens": 1786112} {"current_steps": 8470, "total_steps": 181800, "loss": 0.2024, "lr": 2.3292079207920794e-05, "epoch": 0.9317931793179318, "percentage": 4.66, "elapsed_time": "0:19:17", "remaining_time": "6:34:56", "throughput": 1543.34, "total_tokens": 1787136} {"current_steps": 8475, "total_steps": 181800, "loss": 0.1558, "lr": 2.330583058305831e-05, "epoch": 0.9323432343234324, "percentage": 4.66, "elapsed_time": "0:19:18", "remaining_time": "6:34:55", "throughput": 1543.32, "total_tokens": 1788160} {"current_steps": 8480, "total_steps": 181800, "loss": 0.1335, "lr": 2.331958195819582e-05, "epoch": 0.9328932893289329, "percentage": 4.66, "elapsed_time": "0:19:19", "remaining_time": "6:34:55", "throughput": 1543.28, "total_tokens": 1789184} {"current_steps": 8485, "total_steps": 181800, "loss": 0.1684, "lr": 2.3333333333333336e-05, "epoch": 0.9334433443344334, "percentage": 4.67, "elapsed_time": "0:19:20", "remaining_time": "6:34:54", "throughput": 1543.22, "total_tokens": 1790176} {"current_steps": 8490, "total_steps": 181800, "loss": 0.1348, "lr": 2.3347084708470847e-05, "epoch": 0.933993399339934, "percentage": 4.67, "elapsed_time": "0:19:20", "remaining_time": "6:34:54", "throughput": 1543.22, "total_tokens": 1791232} {"current_steps": 8495, "total_steps": 181800, "loss": 0.2593, "lr": 2.3360836083608363e-05, "epoch": 0.9345434543454345, "percentage": 4.67, "elapsed_time": "0:19:21", "remaining_time": "6:34:53", "throughput": 1543.17, "total_tokens": 1792224} {"current_steps": 8500, "total_steps": 181800, "loss": 0.1383, "lr": 2.3374587458745874e-05, "epoch": 0.935093509350935, "percentage": 4.68, "elapsed_time": "0:19:22", "remaining_time": "6:34:52", "throughput": 1543.14, "total_tokens": 1793248} {"current_steps": 8505, "total_steps": 181800, "loss": 0.1257, "lr": 2.338833883388339e-05, "epoch": 0.9356435643564357, "percentage": 4.68, "elapsed_time": "0:19:22", "remaining_time": "6:34:51", "throughput": 1543.17, "total_tokens": 1794336} {"current_steps": 8510, "total_steps": 181800, "loss": 0.1125, "lr": 2.34020902090209e-05, "epoch": 0.9361936193619362, "percentage": 4.68, "elapsed_time": "0:19:23", "remaining_time": "6:34:51", "throughput": 1543.2, "total_tokens": 1795424} {"current_steps": 8515, "total_steps": 181800, "loss": 0.119, "lr": 2.341584158415842e-05, "epoch": 0.9367436743674368, "percentage": 4.68, "elapsed_time": "0:19:24", "remaining_time": "6:34:50", "throughput": 1543.2, "total_tokens": 1796480} {"current_steps": 8520, "total_steps": 181800, "loss": 0.177, "lr": 2.342959295929593e-05, "epoch": 0.9372937293729373, "percentage": 4.69, "elapsed_time": "0:19:24", "remaining_time": "6:34:49", "throughput": 1543.26, "total_tokens": 1797600} {"current_steps": 8525, "total_steps": 181800, "loss": 0.128, "lr": 2.3443344334433446e-05, "epoch": 0.9378437843784379, "percentage": 4.69, "elapsed_time": "0:19:25", "remaining_time": "6:34:49", "throughput": 1543.26, "total_tokens": 1798656} {"current_steps": 8530, "total_steps": 181800, "loss": 0.188, "lr": 2.3457095709570958e-05, "epoch": 0.9383938393839384, "percentage": 4.69, "elapsed_time": "0:19:26", "remaining_time": "6:34:48", "throughput": 1543.29, "total_tokens": 1799744} {"current_steps": 8535, "total_steps": 181800, "loss": 0.1771, "lr": 2.3470847084708473e-05, "epoch": 0.9389438943894389, "percentage": 4.69, "elapsed_time": "0:19:26", "remaining_time": "6:34:47", "throughput": 1543.27, "total_tokens": 1800768} {"current_steps": 8540, "total_steps": 181800, "loss": 0.1428, "lr": 2.3484598459845984e-05, "epoch": 0.9394939493949395, "percentage": 4.7, "elapsed_time": "0:19:27", "remaining_time": "6:34:47", "throughput": 1543.24, "total_tokens": 1801792} {"current_steps": 8545, "total_steps": 181800, "loss": 0.1564, "lr": 2.34983498349835e-05, "epoch": 0.94004400440044, "percentage": 4.7, "elapsed_time": "0:19:28", "remaining_time": "6:34:46", "throughput": 1543.25, "total_tokens": 1802848} {"current_steps": 8550, "total_steps": 181800, "loss": 0.1879, "lr": 2.351210121012101e-05, "epoch": 0.9405940594059405, "percentage": 4.7, "elapsed_time": "0:19:28", "remaining_time": "6:34:45", "throughput": 1543.19, "total_tokens": 1803840} {"current_steps": 8555, "total_steps": 181800, "loss": 0.2032, "lr": 2.3525852585258526e-05, "epoch": 0.9411441144114412, "percentage": 4.71, "elapsed_time": "0:19:29", "remaining_time": "6:34:44", "throughput": 1543.22, "total_tokens": 1804928} {"current_steps": 8560, "total_steps": 181800, "loss": 0.1361, "lr": 2.3539603960396038e-05, "epoch": 0.9416941694169417, "percentage": 4.71, "elapsed_time": "0:19:30", "remaining_time": "6:34:44", "throughput": 1543.14, "total_tokens": 1805888} {"current_steps": 8565, "total_steps": 181800, "loss": 0.2536, "lr": 2.3553355335533556e-05, "epoch": 0.9422442244224423, "percentage": 4.71, "elapsed_time": "0:19:30", "remaining_time": "6:34:43", "throughput": 1543.19, "total_tokens": 1807008} {"current_steps": 8570, "total_steps": 181800, "loss": 0.0984, "lr": 2.3567106710671068e-05, "epoch": 0.9427942794279428, "percentage": 4.71, "elapsed_time": "0:19:31", "remaining_time": "6:34:42", "throughput": 1543.14, "total_tokens": 1808000} {"current_steps": 8575, "total_steps": 181800, "loss": 0.1411, "lr": 2.3580858085808583e-05, "epoch": 0.9433443344334433, "percentage": 4.72, "elapsed_time": "0:19:32", "remaining_time": "6:34:42", "throughput": 1543.17, "total_tokens": 1809088} {"current_steps": 8580, "total_steps": 181800, "loss": 0.2231, "lr": 2.3594609460946095e-05, "epoch": 0.9438943894389439, "percentage": 4.72, "elapsed_time": "0:19:33", "remaining_time": "6:34:41", "throughput": 1543.23, "total_tokens": 1810208} {"current_steps": 8585, "total_steps": 181800, "loss": 0.2067, "lr": 2.360836083608361e-05, "epoch": 0.9444444444444444, "percentage": 4.72, "elapsed_time": "0:19:33", "remaining_time": "6:34:40", "throughput": 1543.23, "total_tokens": 1811264} {"current_steps": 8590, "total_steps": 181800, "loss": 0.1447, "lr": 2.3622112211221125e-05, "epoch": 0.944994499449945, "percentage": 4.72, "elapsed_time": "0:19:34", "remaining_time": "6:34:40", "throughput": 1543.28, "total_tokens": 1812384} {"current_steps": 8595, "total_steps": 181800, "loss": 0.1791, "lr": 2.3635863586358636e-05, "epoch": 0.9455445544554455, "percentage": 4.73, "elapsed_time": "0:19:35", "remaining_time": "6:34:39", "throughput": 1543.31, "total_tokens": 1813472} {"current_steps": 8600, "total_steps": 181800, "loss": 0.1014, "lr": 2.364961496149615e-05, "epoch": 0.9460946094609461, "percentage": 4.73, "elapsed_time": "0:19:35", "remaining_time": "6:34:38", "throughput": 1543.37, "total_tokens": 1814592} {"current_steps": 8605, "total_steps": 181800, "loss": 0.2286, "lr": 2.3663366336633663e-05, "epoch": 0.9466446644664467, "percentage": 4.73, "elapsed_time": "0:19:36", "remaining_time": "6:34:37", "throughput": 1543.32, "total_tokens": 1815584} {"current_steps": 8610, "total_steps": 181800, "loss": 0.1232, "lr": 2.3677117711771178e-05, "epoch": 0.9471947194719472, "percentage": 4.74, "elapsed_time": "0:19:37", "remaining_time": "6:34:37", "throughput": 1543.32, "total_tokens": 1816640} {"current_steps": 8615, "total_steps": 181800, "loss": 0.1435, "lr": 2.3690869086908693e-05, "epoch": 0.9477447744774478, "percentage": 4.74, "elapsed_time": "0:19:37", "remaining_time": "6:34:36", "throughput": 1543.32, "total_tokens": 1817696} {"current_steps": 8620, "total_steps": 181800, "loss": 0.1615, "lr": 2.3704620462046208e-05, "epoch": 0.9482948294829483, "percentage": 4.74, "elapsed_time": "0:19:38", "remaining_time": "6:34:35", "throughput": 1543.41, "total_tokens": 1818848} {"current_steps": 8625, "total_steps": 181800, "loss": 0.1345, "lr": 2.371837183718372e-05, "epoch": 0.9488448844884488, "percentage": 4.74, "elapsed_time": "0:19:39", "remaining_time": "6:34:35", "throughput": 1543.45, "total_tokens": 1819936} {"current_steps": 8630, "total_steps": 181800, "loss": 0.1439, "lr": 2.3732123212321235e-05, "epoch": 0.9493949394939494, "percentage": 4.75, "elapsed_time": "0:19:39", "remaining_time": "6:34:34", "throughput": 1543.48, "total_tokens": 1821024} {"current_steps": 8635, "total_steps": 181800, "loss": 0.1115, "lr": 2.3745874587458746e-05, "epoch": 0.9499449944994499, "percentage": 4.75, "elapsed_time": "0:19:40", "remaining_time": "6:34:33", "throughput": 1543.46, "total_tokens": 1822048} {"current_steps": 8640, "total_steps": 181800, "loss": 0.1842, "lr": 2.375962596259626e-05, "epoch": 0.9504950495049505, "percentage": 4.75, "elapsed_time": "0:19:41", "remaining_time": "6:34:32", "throughput": 1543.51, "total_tokens": 1823168} {"current_steps": 8645, "total_steps": 181800, "loss": 0.1158, "lr": 2.3773377337733773e-05, "epoch": 0.9510451045104511, "percentage": 4.76, "elapsed_time": "0:19:41", "remaining_time": "6:34:32", "throughput": 1543.54, "total_tokens": 1824256} {"current_steps": 8650, "total_steps": 181800, "loss": 0.1798, "lr": 2.3787128712871288e-05, "epoch": 0.9515951595159516, "percentage": 4.76, "elapsed_time": "0:19:42", "remaining_time": "6:34:31", "throughput": 1543.6, "total_tokens": 1825376} {"current_steps": 8655, "total_steps": 181800, "loss": 0.1514, "lr": 2.38008800880088e-05, "epoch": 0.9521452145214522, "percentage": 4.76, "elapsed_time": "0:19:43", "remaining_time": "6:34:30", "throughput": 1543.57, "total_tokens": 1826400} {"current_steps": 8660, "total_steps": 181800, "loss": 0.1923, "lr": 2.3814631463146318e-05, "epoch": 0.9526952695269527, "percentage": 4.76, "elapsed_time": "0:19:43", "remaining_time": "6:34:29", "throughput": 1543.63, "total_tokens": 1827520} {"current_steps": 8665, "total_steps": 181800, "loss": 0.155, "lr": 2.382838283828383e-05, "epoch": 0.9532453245324533, "percentage": 4.77, "elapsed_time": "0:19:44", "remaining_time": "6:34:29", "throughput": 1543.61, "total_tokens": 1828544} {"current_steps": 8670, "total_steps": 181800, "loss": 0.1654, "lr": 2.3842134213421345e-05, "epoch": 0.9537953795379538, "percentage": 4.77, "elapsed_time": "0:19:45", "remaining_time": "6:34:28", "throughput": 1543.58, "total_tokens": 1829568} {"current_steps": 8675, "total_steps": 181800, "loss": 0.1641, "lr": 2.3855885588558857e-05, "epoch": 0.9543454345434543, "percentage": 4.77, "elapsed_time": "0:19:45", "remaining_time": "6:34:27", "throughput": 1543.61, "total_tokens": 1830656} {"current_steps": 8680, "total_steps": 181800, "loss": 0.1277, "lr": 2.386963696369637e-05, "epoch": 0.9548954895489549, "percentage": 4.77, "elapsed_time": "0:19:46", "remaining_time": "6:34:27", "throughput": 1543.59, "total_tokens": 1831680} {"current_steps": 8685, "total_steps": 181800, "loss": 0.1476, "lr": 2.3883388338833883e-05, "epoch": 0.9554455445544554, "percentage": 4.78, "elapsed_time": "0:19:47", "remaining_time": "6:34:26", "throughput": 1543.59, "total_tokens": 1832736} {"current_steps": 8690, "total_steps": 181800, "loss": 0.1083, "lr": 2.38971397139714e-05, "epoch": 0.9559955995599559, "percentage": 4.78, "elapsed_time": "0:19:47", "remaining_time": "6:34:25", "throughput": 1543.65, "total_tokens": 1833856} {"current_steps": 8695, "total_steps": 181800, "loss": 0.1276, "lr": 2.391089108910891e-05, "epoch": 0.9565456545654566, "percentage": 4.78, "elapsed_time": "0:19:48", "remaining_time": "6:34:24", "throughput": 1543.61, "total_tokens": 1834848} {"current_steps": 8700, "total_steps": 181800, "loss": 0.1852, "lr": 2.3924642464246425e-05, "epoch": 0.9570957095709571, "percentage": 4.79, "elapsed_time": "0:19:49", "remaining_time": "6:34:24", "throughput": 1543.64, "total_tokens": 1835936} {"current_steps": 8705, "total_steps": 181800, "loss": 0.084, "lr": 2.393839383938394e-05, "epoch": 0.9576457645764577, "percentage": 4.79, "elapsed_time": "0:19:50", "remaining_time": "6:34:23", "throughput": 1543.65, "total_tokens": 1836992} {"current_steps": 8710, "total_steps": 181800, "loss": 0.1194, "lr": 2.3952145214521455e-05, "epoch": 0.9581958195819582, "percentage": 4.79, "elapsed_time": "0:19:50", "remaining_time": "6:34:22", "throughput": 1543.6, "total_tokens": 1837984} {"current_steps": 8715, "total_steps": 181800, "loss": 0.1146, "lr": 2.3965896589658967e-05, "epoch": 0.9587458745874587, "percentage": 4.79, "elapsed_time": "0:19:51", "remaining_time": "6:34:21", "throughput": 1543.6, "total_tokens": 1839040} {"current_steps": 8720, "total_steps": 181800, "loss": 0.1092, "lr": 2.3979647964796482e-05, "epoch": 0.9592959295929593, "percentage": 4.8, "elapsed_time": "0:19:52", "remaining_time": "6:34:21", "throughput": 1543.64, "total_tokens": 1840128} {"current_steps": 8725, "total_steps": 181800, "loss": 0.1236, "lr": 2.3993399339933994e-05, "epoch": 0.9598459845984598, "percentage": 4.8, "elapsed_time": "0:19:52", "remaining_time": "6:34:20", "throughput": 1543.62, "total_tokens": 1841152} {"current_steps": 8730, "total_steps": 181800, "loss": 0.1863, "lr": 2.400715071507151e-05, "epoch": 0.9603960396039604, "percentage": 4.8, "elapsed_time": "0:19:53", "remaining_time": "6:34:19", "throughput": 1543.68, "total_tokens": 1842272} {"current_steps": 8735, "total_steps": 181800, "loss": 0.1904, "lr": 2.402090209020902e-05, "epoch": 0.9609460946094609, "percentage": 4.8, "elapsed_time": "0:19:54", "remaining_time": "6:34:18", "throughput": 1543.65, "total_tokens": 1843296} {"current_steps": 8740, "total_steps": 181800, "loss": 0.2329, "lr": 2.4034653465346535e-05, "epoch": 0.9614961496149615, "percentage": 4.81, "elapsed_time": "0:19:54", "remaining_time": "6:34:18", "throughput": 1543.66, "total_tokens": 1844352} {"current_steps": 8745, "total_steps": 181800, "loss": 0.0991, "lr": 2.4048404840484047e-05, "epoch": 0.9620462046204621, "percentage": 4.81, "elapsed_time": "0:19:55", "remaining_time": "6:34:17", "throughput": 1543.66, "total_tokens": 1845408} {"current_steps": 8750, "total_steps": 181800, "loss": 0.1412, "lr": 2.4062156215621565e-05, "epoch": 0.9625962596259626, "percentage": 4.81, "elapsed_time": "0:19:56", "remaining_time": "6:34:16", "throughput": 1543.61, "total_tokens": 1846400} {"current_steps": 8755, "total_steps": 181800, "loss": 0.1464, "lr": 2.4075907590759077e-05, "epoch": 0.9631463146314632, "percentage": 4.82, "elapsed_time": "0:19:56", "remaining_time": "6:34:15", "throughput": 1543.62, "total_tokens": 1847456} {"current_steps": 8760, "total_steps": 181800, "loss": 0.094, "lr": 2.4089658965896592e-05, "epoch": 0.9636963696369637, "percentage": 4.82, "elapsed_time": "0:19:57", "remaining_time": "6:34:15", "throughput": 1543.54, "total_tokens": 1848416} {"current_steps": 8765, "total_steps": 181800, "loss": 0.2057, "lr": 2.4103410341034104e-05, "epoch": 0.9642464246424642, "percentage": 4.82, "elapsed_time": "0:19:58", "remaining_time": "6:34:14", "throughput": 1543.55, "total_tokens": 1849472} {"current_steps": 8770, "total_steps": 181800, "loss": 0.1876, "lr": 2.411716171617162e-05, "epoch": 0.9647964796479648, "percentage": 4.82, "elapsed_time": "0:19:58", "remaining_time": "6:34:13", "throughput": 1543.55, "total_tokens": 1850528} {"current_steps": 8775, "total_steps": 181800, "loss": 0.2074, "lr": 2.413091309130913e-05, "epoch": 0.9653465346534653, "percentage": 4.83, "elapsed_time": "0:19:59", "remaining_time": "6:34:12", "throughput": 1543.63, "total_tokens": 1851680} {"current_steps": 8780, "total_steps": 181800, "loss": 0.1608, "lr": 2.4144664466446645e-05, "epoch": 0.9658965896589659, "percentage": 4.83, "elapsed_time": "0:20:00", "remaining_time": "6:34:12", "throughput": 1543.58, "total_tokens": 1852672} {"current_steps": 8785, "total_steps": 181800, "loss": 0.1326, "lr": 2.415841584158416e-05, "epoch": 0.9664466446644664, "percentage": 4.83, "elapsed_time": "0:20:00", "remaining_time": "6:34:11", "throughput": 1543.55, "total_tokens": 1853696} {"current_steps": 8790, "total_steps": 181800, "loss": 0.1456, "lr": 2.4172167216721672e-05, "epoch": 0.966996699669967, "percentage": 4.83, "elapsed_time": "0:20:01", "remaining_time": "6:34:10", "throughput": 1543.5, "total_tokens": 1854688} {"current_steps": 8795, "total_steps": 181800, "loss": 0.1612, "lr": 2.4185918591859187e-05, "epoch": 0.9675467546754676, "percentage": 4.84, "elapsed_time": "0:20:02", "remaining_time": "6:34:10", "throughput": 1543.48, "total_tokens": 1855712} {"current_steps": 8800, "total_steps": 181800, "loss": 0.1775, "lr": 2.4199669966996702e-05, "epoch": 0.9680968096809681, "percentage": 4.84, "elapsed_time": "0:20:02", "remaining_time": "6:34:09", "throughput": 1543.54, "total_tokens": 1856832} {"current_steps": 8805, "total_steps": 181800, "loss": 0.1306, "lr": 2.4213421342134214e-05, "epoch": 0.9686468646864687, "percentage": 4.84, "elapsed_time": "0:20:03", "remaining_time": "6:34:08", "throughput": 1543.57, "total_tokens": 1857920} {"current_steps": 8810, "total_steps": 181800, "loss": 0.1737, "lr": 2.422717271727173e-05, "epoch": 0.9691969196919692, "percentage": 4.85, "elapsed_time": "0:20:04", "remaining_time": "6:34:07", "throughput": 1543.55, "total_tokens": 1858944} {"current_steps": 8815, "total_steps": 181800, "loss": 0.3482, "lr": 2.4240924092409244e-05, "epoch": 0.9697469746974697, "percentage": 4.85, "elapsed_time": "0:20:05", "remaining_time": "6:34:07", "throughput": 1543.56, "total_tokens": 1860000} {"current_steps": 8820, "total_steps": 181800, "loss": 0.1414, "lr": 2.4254675467546756e-05, "epoch": 0.9702970297029703, "percentage": 4.85, "elapsed_time": "0:20:05", "remaining_time": "6:34:06", "throughput": 1543.56, "total_tokens": 1861056} {"current_steps": 8825, "total_steps": 181800, "loss": 0.1083, "lr": 2.426842684268427e-05, "epoch": 0.9708470847084708, "percentage": 4.85, "elapsed_time": "0:20:06", "remaining_time": "6:34:05", "throughput": 1543.54, "total_tokens": 1862080} {"current_steps": 8830, "total_steps": 181800, "loss": 0.1009, "lr": 2.4282178217821782e-05, "epoch": 0.9713971397139713, "percentage": 4.86, "elapsed_time": "0:20:07", "remaining_time": "6:34:04", "throughput": 1543.52, "total_tokens": 1863104} {"current_steps": 8835, "total_steps": 181800, "loss": 0.1378, "lr": 2.4295929592959297e-05, "epoch": 0.971947194719472, "percentage": 4.86, "elapsed_time": "0:20:07", "remaining_time": "6:34:03", "throughput": 1543.5, "total_tokens": 1864128} {"current_steps": 8840, "total_steps": 181800, "loss": 0.1537, "lr": 2.430968096809681e-05, "epoch": 0.9724972497249725, "percentage": 4.86, "elapsed_time": "0:20:08", "remaining_time": "6:34:03", "throughput": 1543.51, "total_tokens": 1865184} {"current_steps": 8845, "total_steps": 181800, "loss": 0.1528, "lr": 2.4323432343234327e-05, "epoch": 0.9730473047304731, "percentage": 4.87, "elapsed_time": "0:20:09", "remaining_time": "6:34:02", "throughput": 1543.52, "total_tokens": 1866240} {"current_steps": 8850, "total_steps": 181800, "loss": 0.1423, "lr": 2.433718371837184e-05, "epoch": 0.9735973597359736, "percentage": 4.87, "elapsed_time": "0:20:09", "remaining_time": "6:34:01", "throughput": 1543.57, "total_tokens": 1867360} {"current_steps": 8855, "total_steps": 181800, "loss": 0.1352, "lr": 2.4350935093509354e-05, "epoch": 0.9741474147414741, "percentage": 4.87, "elapsed_time": "0:20:10", "remaining_time": "6:34:00", "throughput": 1543.63, "total_tokens": 1868480} {"current_steps": 8860, "total_steps": 181800, "loss": 0.0936, "lr": 2.4364686468646866e-05, "epoch": 0.9746974697469747, "percentage": 4.87, "elapsed_time": "0:20:11", "remaining_time": "6:34:00", "throughput": 1543.56, "total_tokens": 1869440} {"current_steps": 8865, "total_steps": 181800, "loss": 0.1572, "lr": 2.437843784378438e-05, "epoch": 0.9752475247524752, "percentage": 4.88, "elapsed_time": "0:20:11", "remaining_time": "6:33:59", "throughput": 1543.57, "total_tokens": 1870496} {"current_steps": 8870, "total_steps": 181800, "loss": 0.1523, "lr": 2.4392189218921893e-05, "epoch": 0.9757975797579758, "percentage": 4.88, "elapsed_time": "0:20:12", "remaining_time": "6:33:58", "throughput": 1543.63, "total_tokens": 1871616} {"current_steps": 8875, "total_steps": 181800, "loss": 0.1487, "lr": 2.4405940594059408e-05, "epoch": 0.9763476347634763, "percentage": 4.88, "elapsed_time": "0:20:13", "remaining_time": "6:33:57", "throughput": 1543.63, "total_tokens": 1872672} {"current_steps": 8880, "total_steps": 181800, "loss": 0.1023, "lr": 2.441969196919692e-05, "epoch": 0.976897689768977, "percentage": 4.88, "elapsed_time": "0:20:13", "remaining_time": "6:33:57", "throughput": 1543.66, "total_tokens": 1873760} {"current_steps": 8885, "total_steps": 181800, "loss": 0.1467, "lr": 2.4433443344334434e-05, "epoch": 0.9774477447744775, "percentage": 4.89, "elapsed_time": "0:20:14", "remaining_time": "6:33:56", "throughput": 1543.64, "total_tokens": 1874784} {"current_steps": 8890, "total_steps": 181800, "loss": 0.1531, "lr": 2.444719471947195e-05, "epoch": 0.977997799779978, "percentage": 4.89, "elapsed_time": "0:20:15", "remaining_time": "6:33:55", "throughput": 1543.62, "total_tokens": 1875808} {"current_steps": 8895, "total_steps": 181800, "loss": 0.2164, "lr": 2.4460946094609464e-05, "epoch": 0.9785478547854786, "percentage": 4.89, "elapsed_time": "0:20:15", "remaining_time": "6:33:54", "throughput": 1543.59, "total_tokens": 1876832} {"current_steps": 8900, "total_steps": 181800, "loss": 0.1236, "lr": 2.4474697469746976e-05, "epoch": 0.9790979097909791, "percentage": 4.9, "elapsed_time": "0:20:16", "remaining_time": "6:33:54", "throughput": 1543.51, "total_tokens": 1877792} {"current_steps": 8905, "total_steps": 181800, "loss": 0.1824, "lr": 2.448844884488449e-05, "epoch": 0.9796479647964796, "percentage": 4.9, "elapsed_time": "0:20:17", "remaining_time": "6:33:53", "throughput": 1543.54, "total_tokens": 1878880} {"current_steps": 8910, "total_steps": 181800, "loss": 0.116, "lr": 2.4502200220022003e-05, "epoch": 0.9801980198019802, "percentage": 4.9, "elapsed_time": "0:20:17", "remaining_time": "6:33:52", "throughput": 1543.54, "total_tokens": 1879936} {"current_steps": 8915, "total_steps": 181800, "loss": 0.1804, "lr": 2.4515951595159518e-05, "epoch": 0.9807480748074807, "percentage": 4.9, "elapsed_time": "0:20:18", "remaining_time": "6:33:52", "throughput": 1543.55, "total_tokens": 1880992} {"current_steps": 8920, "total_steps": 181800, "loss": 0.1723, "lr": 2.452970297029703e-05, "epoch": 0.9812981298129813, "percentage": 4.91, "elapsed_time": "0:20:19", "remaining_time": "6:33:51", "throughput": 1543.55, "total_tokens": 1882048} {"current_steps": 8925, "total_steps": 181800, "loss": 0.1472, "lr": 2.4543454345434544e-05, "epoch": 0.9818481848184818, "percentage": 4.91, "elapsed_time": "0:20:19", "remaining_time": "6:33:50", "throughput": 1543.55, "total_tokens": 1883104} {"current_steps": 8930, "total_steps": 181800, "loss": 0.143, "lr": 2.4557205720572056e-05, "epoch": 0.9823982398239824, "percentage": 4.91, "elapsed_time": "0:20:20", "remaining_time": "6:33:49", "throughput": 1543.61, "total_tokens": 1884224} {"current_steps": 8935, "total_steps": 181800, "loss": 0.1166, "lr": 2.457095709570957e-05, "epoch": 0.982948294829483, "percentage": 4.91, "elapsed_time": "0:20:21", "remaining_time": "6:33:49", "throughput": 1543.59, "total_tokens": 1885248} {"current_steps": 8940, "total_steps": 181800, "loss": 0.1548, "lr": 2.4584708470847086e-05, "epoch": 0.9834983498349835, "percentage": 4.92, "elapsed_time": "0:20:22", "remaining_time": "6:33:48", "throughput": 1543.59, "total_tokens": 1886304} {"current_steps": 8945, "total_steps": 181800, "loss": 0.142, "lr": 2.45984598459846e-05, "epoch": 0.9840484048404841, "percentage": 4.92, "elapsed_time": "0:20:22", "remaining_time": "6:33:47", "throughput": 1543.59, "total_tokens": 1887360} {"current_steps": 8950, "total_steps": 181800, "loss": 0.1659, "lr": 2.4612211221122113e-05, "epoch": 0.9845984598459846, "percentage": 4.92, "elapsed_time": "0:20:23", "remaining_time": "6:33:47", "throughput": 1543.6, "total_tokens": 1888416} {"current_steps": 8955, "total_steps": 181800, "loss": 0.164, "lr": 2.4625962596259628e-05, "epoch": 0.9851485148514851, "percentage": 4.93, "elapsed_time": "0:20:24", "remaining_time": "6:33:46", "throughput": 1543.6, "total_tokens": 1889472} {"current_steps": 8960, "total_steps": 181800, "loss": 0.085, "lr": 2.463971397139714e-05, "epoch": 0.9856985698569857, "percentage": 4.93, "elapsed_time": "0:20:24", "remaining_time": "6:33:45", "throughput": 1543.65, "total_tokens": 1890592} {"current_steps": 8965, "total_steps": 181800, "loss": 0.1501, "lr": 2.4653465346534655e-05, "epoch": 0.9862486248624862, "percentage": 4.93, "elapsed_time": "0:20:25", "remaining_time": "6:33:45", "throughput": 1543.65, "total_tokens": 1891648} {"current_steps": 8970, "total_steps": 181800, "loss": 0.2722, "lr": 2.4667216721672166e-05, "epoch": 0.9867986798679867, "percentage": 4.93, "elapsed_time": "0:20:26", "remaining_time": "6:33:44", "throughput": 1543.63, "total_tokens": 1892672} {"current_steps": 8975, "total_steps": 181800, "loss": 0.2288, "lr": 2.468096809680968e-05, "epoch": 0.9873487348734874, "percentage": 4.94, "elapsed_time": "0:20:26", "remaining_time": "6:33:43", "throughput": 1543.65, "total_tokens": 1893760} {"current_steps": 8980, "total_steps": 181800, "loss": 0.1207, "lr": 2.4694719471947196e-05, "epoch": 0.9878987898789879, "percentage": 4.94, "elapsed_time": "0:20:27", "remaining_time": "6:33:43", "throughput": 1543.65, "total_tokens": 1894816} {"current_steps": 8985, "total_steps": 181800, "loss": 0.099, "lr": 2.470847084708471e-05, "epoch": 0.9884488448844885, "percentage": 4.94, "elapsed_time": "0:20:28", "remaining_time": "6:33:42", "throughput": 1543.68, "total_tokens": 1895904} {"current_steps": 8990, "total_steps": 181800, "loss": 0.1504, "lr": 2.4722222222222223e-05, "epoch": 0.988998899889989, "percentage": 4.94, "elapsed_time": "0:20:28", "remaining_time": "6:33:41", "throughput": 1543.71, "total_tokens": 1896992} {"current_steps": 8995, "total_steps": 181800, "loss": 0.1341, "lr": 2.4735973597359738e-05, "epoch": 0.9895489548954896, "percentage": 4.95, "elapsed_time": "0:20:29", "remaining_time": "6:33:40", "throughput": 1543.68, "total_tokens": 1898016} {"current_steps": 9000, "total_steps": 181800, "loss": 0.1564, "lr": 2.474972497249725e-05, "epoch": 0.9900990099009901, "percentage": 4.95, "elapsed_time": "0:20:30", "remaining_time": "6:33:40", "throughput": 1543.71, "total_tokens": 1899104} {"current_steps": 9005, "total_steps": 181800, "loss": 0.2735, "lr": 2.4763476347634765e-05, "epoch": 0.9906490649064906, "percentage": 4.95, "elapsed_time": "0:20:30", "remaining_time": "6:33:39", "throughput": 1543.68, "total_tokens": 1900128} {"current_steps": 9010, "total_steps": 181800, "loss": 0.1269, "lr": 2.477722772277228e-05, "epoch": 0.9911991199119912, "percentage": 4.96, "elapsed_time": "0:20:31", "remaining_time": "6:33:38", "throughput": 1543.68, "total_tokens": 1901184} {"current_steps": 9015, "total_steps": 181800, "loss": 0.1358, "lr": 2.479097909790979e-05, "epoch": 0.9917491749174917, "percentage": 4.96, "elapsed_time": "0:20:32", "remaining_time": "6:33:38", "throughput": 1543.71, "total_tokens": 1902272} {"current_steps": 9020, "total_steps": 181800, "loss": 0.1744, "lr": 2.4804730473047307e-05, "epoch": 0.9922992299229924, "percentage": 4.96, "elapsed_time": "0:20:32", "remaining_time": "6:33:37", "throughput": 1543.66, "total_tokens": 1903264} {"current_steps": 9025, "total_steps": 181800, "loss": 0.2435, "lr": 2.4818481848184818e-05, "epoch": 0.9928492849284929, "percentage": 4.96, "elapsed_time": "0:20:33", "remaining_time": "6:33:36", "throughput": 1543.64, "total_tokens": 1904288} {"current_steps": 9030, "total_steps": 181800, "loss": 0.1316, "lr": 2.4832233223322333e-05, "epoch": 0.9933993399339934, "percentage": 4.97, "elapsed_time": "0:20:34", "remaining_time": "6:33:36", "throughput": 1543.69, "total_tokens": 1905408} {"current_steps": 9035, "total_steps": 181800, "loss": 0.1161, "lr": 2.4845984598459848e-05, "epoch": 0.993949394939494, "percentage": 4.97, "elapsed_time": "0:20:35", "remaining_time": "6:33:35", "throughput": 1543.69, "total_tokens": 1906464} {"current_steps": 9040, "total_steps": 181800, "loss": 0.1216, "lr": 2.4859735973597363e-05, "epoch": 0.9944994499449945, "percentage": 4.97, "elapsed_time": "0:20:35", "remaining_time": "6:33:34", "throughput": 1543.72, "total_tokens": 1907552} {"current_steps": 9045, "total_steps": 181800, "loss": 0.1767, "lr": 2.4873487348734875e-05, "epoch": 0.995049504950495, "percentage": 4.98, "elapsed_time": "0:20:36", "remaining_time": "6:33:33", "throughput": 1543.7, "total_tokens": 1908576} {"current_steps": 9050, "total_steps": 181800, "loss": 0.114, "lr": 2.488723872387239e-05, "epoch": 0.9955995599559956, "percentage": 4.98, "elapsed_time": "0:20:37", "remaining_time": "6:33:33", "throughput": 1543.73, "total_tokens": 1909664} {"current_steps": 9055, "total_steps": 181800, "loss": 0.1277, "lr": 2.49009900990099e-05, "epoch": 0.9961496149614961, "percentage": 4.98, "elapsed_time": "0:20:37", "remaining_time": "6:33:32", "throughput": 1543.73, "total_tokens": 1910720} {"current_steps": 9060, "total_steps": 181800, "loss": 0.1353, "lr": 2.4914741474147417e-05, "epoch": 0.9966996699669967, "percentage": 4.98, "elapsed_time": "0:20:38", "remaining_time": "6:33:31", "throughput": 1543.79, "total_tokens": 1911840} {"current_steps": 9065, "total_steps": 181800, "loss": 0.1905, "lr": 2.492849284928493e-05, "epoch": 0.9972497249724972, "percentage": 4.99, "elapsed_time": "0:20:39", "remaining_time": "6:33:31", "throughput": 1543.79, "total_tokens": 1912896} {"current_steps": 9070, "total_steps": 181800, "loss": 0.1231, "lr": 2.4942244224422443e-05, "epoch": 0.9977997799779978, "percentage": 4.99, "elapsed_time": "0:20:39", "remaining_time": "6:33:30", "throughput": 1543.79, "total_tokens": 1913952} {"current_steps": 9075, "total_steps": 181800, "loss": 0.202, "lr": 2.4955995599559955e-05, "epoch": 0.9983498349834984, "percentage": 4.99, "elapsed_time": "0:20:40", "remaining_time": "6:33:29", "throughput": 1543.79, "total_tokens": 1915008} {"current_steps": 9080, "total_steps": 181800, "loss": 0.1503, "lr": 2.4969746974697474e-05, "epoch": 0.9988998899889989, "percentage": 4.99, "elapsed_time": "0:20:41", "remaining_time": "6:33:29", "throughput": 1543.79, "total_tokens": 1916064} {"current_steps": 9085, "total_steps": 181800, "loss": 0.1237, "lr": 2.4983498349834985e-05, "epoch": 0.9994499449944995, "percentage": 5.0, "elapsed_time": "0:20:41", "remaining_time": "6:33:28", "throughput": 1543.73, "total_tokens": 1917056} {"current_steps": 9090, "total_steps": 181800, "loss": 0.1899, "lr": 2.49972497249725e-05, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:20:42", "remaining_time": "6:33:28", "throughput": 1543.56, "total_tokens": 1917952} {"current_steps": 9090, "total_steps": 181800, "eval_loss": 0.1525431126356125, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:21:19", "remaining_time": "6:45:11", "throughput": 1498.93, "total_tokens": 1917952} {"current_steps": 9095, "total_steps": 181800, "loss": 0.1441, "lr": 2.501100110011001e-05, "epoch": 1.0005500550055006, "percentage": 5.0, "elapsed_time": "0:21:21", "remaining_time": "6:45:28", "throughput": 1497.82, "total_tokens": 1919008} {"current_steps": 9100, "total_steps": 181800, "loss": 0.2141, "lr": 2.5024752475247527e-05, "epoch": 1.001100110011001, "percentage": 5.01, "elapsed_time": "0:21:21", "remaining_time": "6:45:27", "throughput": 1497.8, "total_tokens": 1920032} {"current_steps": 9105, "total_steps": 181800, "loss": 0.1107, "lr": 2.5038503850385042e-05, "epoch": 1.0016501650165017, "percentage": 5.01, "elapsed_time": "0:21:22", "remaining_time": "6:45:27", "throughput": 1497.78, "total_tokens": 1921056} {"current_steps": 9110, "total_steps": 181800, "loss": 0.1215, "lr": 2.5052255225522554e-05, "epoch": 1.0022002200220022, "percentage": 5.01, "elapsed_time": "0:21:23", "remaining_time": "6:45:26", "throughput": 1497.79, "total_tokens": 1922112} {"current_steps": 9115, "total_steps": 181800, "loss": 0.1231, "lr": 2.506600660066007e-05, "epoch": 1.0027502750275028, "percentage": 5.01, "elapsed_time": "0:21:23", "remaining_time": "6:45:25", "throughput": 1497.77, "total_tokens": 1923136} {"current_steps": 9120, "total_steps": 181800, "loss": 0.1442, "lr": 2.507975797579758e-05, "epoch": 1.0033003300330032, "percentage": 5.02, "elapsed_time": "0:21:24", "remaining_time": "6:45:24", "throughput": 1497.75, "total_tokens": 1924160} {"current_steps": 9125, "total_steps": 181800, "loss": 0.1169, "lr": 2.5093509350935095e-05, "epoch": 1.0038503850385039, "percentage": 5.02, "elapsed_time": "0:21:25", "remaining_time": "6:45:23", "throughput": 1497.79, "total_tokens": 1925248} {"current_steps": 9130, "total_steps": 181800, "loss": 0.1193, "lr": 2.5107260726072607e-05, "epoch": 1.0044004400440043, "percentage": 5.02, "elapsed_time": "0:21:26", "remaining_time": "6:45:23", "throughput": 1497.74, "total_tokens": 1926240} {"current_steps": 9135, "total_steps": 181800, "loss": 0.1904, "lr": 2.5121012101210122e-05, "epoch": 1.004950495049505, "percentage": 5.02, "elapsed_time": "0:21:26", "remaining_time": "6:45:22", "throughput": 1497.75, "total_tokens": 1927296} {"current_steps": 9140, "total_steps": 181800, "loss": 0.1372, "lr": 2.5134763476347634e-05, "epoch": 1.0055005500550056, "percentage": 5.03, "elapsed_time": "0:21:27", "remaining_time": "6:45:21", "throughput": 1497.73, "total_tokens": 1928320} {"current_steps": 9145, "total_steps": 181800, "loss": 0.1699, "lr": 2.514851485148515e-05, "epoch": 1.006050605060506, "percentage": 5.03, "elapsed_time": "0:21:28", "remaining_time": "6:45:20", "throughput": 1497.76, "total_tokens": 1929408} {"current_steps": 9150, "total_steps": 181800, "loss": 0.1728, "lr": 2.5162266226622667e-05, "epoch": 1.0066006600660067, "percentage": 5.03, "elapsed_time": "0:21:28", "remaining_time": "6:45:19", "throughput": 1497.79, "total_tokens": 1930496} {"current_steps": 9155, "total_steps": 181800, "loss": 0.1215, "lr": 2.5176017601760175e-05, "epoch": 1.007150715071507, "percentage": 5.04, "elapsed_time": "0:21:29", "remaining_time": "6:45:19", "throughput": 1497.81, "total_tokens": 1931584} {"current_steps": 9160, "total_steps": 181800, "loss": 0.1534, "lr": 2.5189768976897694e-05, "epoch": 1.0077007700770078, "percentage": 5.04, "elapsed_time": "0:21:30", "remaining_time": "6:45:18", "throughput": 1497.76, "total_tokens": 1932576} {"current_steps": 9165, "total_steps": 181800, "loss": 0.1473, "lr": 2.5203520352035202e-05, "epoch": 1.0082508250825082, "percentage": 5.04, "elapsed_time": "0:21:31", "remaining_time": "6:45:17", "throughput": 1497.74, "total_tokens": 1933600} {"current_steps": 9170, "total_steps": 181800, "loss": 0.1146, "lr": 2.521727172717272e-05, "epoch": 1.0088008800880088, "percentage": 5.04, "elapsed_time": "0:21:31", "remaining_time": "6:45:16", "throughput": 1497.71, "total_tokens": 1934592} {"current_steps": 9175, "total_steps": 181800, "loss": 0.1122, "lr": 2.5231023102310232e-05, "epoch": 1.0093509350935093, "percentage": 5.05, "elapsed_time": "0:21:32", "remaining_time": "6:45:16", "throughput": 1497.67, "total_tokens": 1935584} {"current_steps": 9180, "total_steps": 181800, "loss": 0.142, "lr": 2.5244774477447747e-05, "epoch": 1.00990099009901, "percentage": 5.05, "elapsed_time": "0:21:33", "remaining_time": "6:45:15", "throughput": 1497.69, "total_tokens": 1936640} {"current_steps": 9185, "total_steps": 181800, "loss": 0.0961, "lr": 2.525852585258526e-05, "epoch": 1.0104510451045106, "percentage": 5.05, "elapsed_time": "0:21:33", "remaining_time": "6:45:14", "throughput": 1497.67, "total_tokens": 1937664} {"current_steps": 9190, "total_steps": 181800, "loss": 0.1724, "lr": 2.5272277227722774e-05, "epoch": 1.011001100110011, "percentage": 5.06, "elapsed_time": "0:21:34", "remaining_time": "6:45:13", "throughput": 1497.68, "total_tokens": 1938720} {"current_steps": 9195, "total_steps": 181800, "loss": 0.0956, "lr": 2.528602860286029e-05, "epoch": 1.0115511551155116, "percentage": 5.06, "elapsed_time": "0:21:35", "remaining_time": "6:45:12", "throughput": 1497.66, "total_tokens": 1939744} {"current_steps": 9200, "total_steps": 181800, "loss": 0.1617, "lr": 2.52997799779978e-05, "epoch": 1.012101210121012, "percentage": 5.06, "elapsed_time": "0:21:35", "remaining_time": "6:45:11", "throughput": 1497.72, "total_tokens": 1940864} {"current_steps": 9205, "total_steps": 181800, "loss": 0.151, "lr": 2.5313531353135316e-05, "epoch": 1.0126512651265127, "percentage": 5.06, "elapsed_time": "0:21:36", "remaining_time": "6:45:10", "throughput": 1497.71, "total_tokens": 1941888} {"current_steps": 9210, "total_steps": 181800, "loss": 0.1217, "lr": 2.5327282728272827e-05, "epoch": 1.0132013201320131, "percentage": 5.07, "elapsed_time": "0:21:37", "remaining_time": "6:45:10", "throughput": 1497.69, "total_tokens": 1942912} {"current_steps": 9215, "total_steps": 181800, "loss": 0.1718, "lr": 2.5341034103410342e-05, "epoch": 1.0137513751375138, "percentage": 5.07, "elapsed_time": "0:21:37", "remaining_time": "6:45:09", "throughput": 1497.7, "total_tokens": 1943968} {"current_steps": 9220, "total_steps": 181800, "loss": 0.1622, "lr": 2.5354785478547854e-05, "epoch": 1.0143014301430142, "percentage": 5.07, "elapsed_time": "0:21:38", "remaining_time": "6:45:08", "throughput": 1497.68, "total_tokens": 1944992} {"current_steps": 9225, "total_steps": 181800, "loss": 0.0898, "lr": 2.536853685368537e-05, "epoch": 1.0148514851485149, "percentage": 5.07, "elapsed_time": "0:21:39", "remaining_time": "6:45:07", "throughput": 1497.69, "total_tokens": 1946048} {"current_steps": 9230, "total_steps": 181800, "loss": 0.1678, "lr": 2.538228822882288e-05, "epoch": 1.0154015401540153, "percentage": 5.08, "elapsed_time": "0:21:40", "remaining_time": "6:45:06", "throughput": 1497.63, "total_tokens": 1947008} {"current_steps": 9235, "total_steps": 181800, "loss": 0.109, "lr": 2.53960396039604e-05, "epoch": 1.015951595159516, "percentage": 5.08, "elapsed_time": "0:21:40", "remaining_time": "6:45:05", "throughput": 1497.62, "total_tokens": 1948032} {"current_steps": 9240, "total_steps": 181800, "loss": 0.1356, "lr": 2.5409790979097907e-05, "epoch": 1.0165016501650166, "percentage": 5.08, "elapsed_time": "0:21:41", "remaining_time": "6:45:05", "throughput": 1497.6, "total_tokens": 1949056} {"current_steps": 9245, "total_steps": 181800, "loss": 0.1901, "lr": 2.5423542354235426e-05, "epoch": 1.017051705170517, "percentage": 5.09, "elapsed_time": "0:21:42", "remaining_time": "6:45:04", "throughput": 1497.61, "total_tokens": 1950112} {"current_steps": 9250, "total_steps": 181800, "loss": 0.2654, "lr": 2.543729372937294e-05, "epoch": 1.0176017601760177, "percentage": 5.09, "elapsed_time": "0:21:42", "remaining_time": "6:45:03", "throughput": 1497.64, "total_tokens": 1951200} {"current_steps": 9255, "total_steps": 181800, "loss": 0.1453, "lr": 2.5451045104510453e-05, "epoch": 1.018151815181518, "percentage": 5.09, "elapsed_time": "0:21:43", "remaining_time": "6:45:02", "throughput": 1497.63, "total_tokens": 1952224} {"current_steps": 9260, "total_steps": 181800, "loss": 0.1189, "lr": 2.5464796479647968e-05, "epoch": 1.0187018701870187, "percentage": 5.09, "elapsed_time": "0:21:44", "remaining_time": "6:45:01", "throughput": 1497.66, "total_tokens": 1953312} {"current_steps": 9265, "total_steps": 181800, "loss": 0.1221, "lr": 2.547854785478548e-05, "epoch": 1.0192519251925192, "percentage": 5.1, "elapsed_time": "0:21:44", "remaining_time": "6:45:00", "throughput": 1497.65, "total_tokens": 1954336} {"current_steps": 9270, "total_steps": 181800, "loss": 0.1475, "lr": 2.5492299229922994e-05, "epoch": 1.0198019801980198, "percentage": 5.1, "elapsed_time": "0:21:45", "remaining_time": "6:45:00", "throughput": 1497.66, "total_tokens": 1955392} {"current_steps": 9275, "total_steps": 181800, "loss": 0.1648, "lr": 2.5506050605060506e-05, "epoch": 1.0203520352035202, "percentage": 5.1, "elapsed_time": "0:21:46", "remaining_time": "6:44:59", "throughput": 1497.64, "total_tokens": 1956416} {"current_steps": 9280, "total_steps": 181800, "loss": 0.1167, "lr": 2.551980198019802e-05, "epoch": 1.020902090209021, "percentage": 5.1, "elapsed_time": "0:21:47", "remaining_time": "6:44:58", "throughput": 1497.61, "total_tokens": 1957408} {"current_steps": 9285, "total_steps": 181800, "loss": 0.1434, "lr": 2.5533553355335533e-05, "epoch": 1.0214521452145215, "percentage": 5.11, "elapsed_time": "0:21:47", "remaining_time": "6:44:57", "throughput": 1497.62, "total_tokens": 1958464} {"current_steps": 9290, "total_steps": 181800, "loss": 0.143, "lr": 2.5547304730473048e-05, "epoch": 1.022002200220022, "percentage": 5.11, "elapsed_time": "0:21:48", "remaining_time": "6:44:56", "throughput": 1497.66, "total_tokens": 1959552} {"current_steps": 9295, "total_steps": 181800, "loss": 0.1212, "lr": 2.5561056105610566e-05, "epoch": 1.0225522552255226, "percentage": 5.11, "elapsed_time": "0:21:49", "remaining_time": "6:44:55", "throughput": 1497.63, "total_tokens": 1960544} {"current_steps": 9300, "total_steps": 181800, "loss": 0.1466, "lr": 2.5574807480748074e-05, "epoch": 1.023102310231023, "percentage": 5.12, "elapsed_time": "0:21:49", "remaining_time": "6:44:54", "throughput": 1497.64, "total_tokens": 1961600} {"current_steps": 9305, "total_steps": 181800, "loss": 0.1816, "lr": 2.5588558855885593e-05, "epoch": 1.0236523652365237, "percentage": 5.12, "elapsed_time": "0:21:50", "remaining_time": "6:44:53", "throughput": 1497.68, "total_tokens": 1962688} {"current_steps": 9310, "total_steps": 181800, "loss": 0.18, "lr": 2.56023102310231e-05, "epoch": 1.0242024202420241, "percentage": 5.12, "elapsed_time": "0:21:51", "remaining_time": "6:44:52", "throughput": 1497.7, "total_tokens": 1963744} {"current_steps": 9315, "total_steps": 181800, "loss": 0.1223, "lr": 2.561606160616062e-05, "epoch": 1.0247524752475248, "percentage": 5.12, "elapsed_time": "0:21:51", "remaining_time": "6:44:51", "throughput": 1497.74, "total_tokens": 1964832} {"current_steps": 9320, "total_steps": 181800, "loss": 0.1446, "lr": 2.5629812981298128e-05, "epoch": 1.0253025302530252, "percentage": 5.13, "elapsed_time": "0:21:52", "remaining_time": "6:44:50", "throughput": 1497.77, "total_tokens": 1965920} {"current_steps": 9325, "total_steps": 181800, "loss": 0.1651, "lr": 2.5643564356435646e-05, "epoch": 1.0258525852585259, "percentage": 5.13, "elapsed_time": "0:21:53", "remaining_time": "6:44:49", "throughput": 1497.74, "total_tokens": 1966912} {"current_steps": 9330, "total_steps": 181800, "loss": 0.1039, "lr": 2.5657315731573155e-05, "epoch": 1.0264026402640265, "percentage": 5.13, "elapsed_time": "0:21:53", "remaining_time": "6:44:49", "throughput": 1497.84, "total_tokens": 1968096} {"current_steps": 9335, "total_steps": 181800, "loss": 0.1932, "lr": 2.5671067106710673e-05, "epoch": 1.026952695269527, "percentage": 5.13, "elapsed_time": "0:21:54", "remaining_time": "6:44:48", "throughput": 1497.91, "total_tokens": 1969216} {"current_steps": 9340, "total_steps": 181800, "loss": 0.102, "lr": 2.5684818481848188e-05, "epoch": 1.0275027502750276, "percentage": 5.14, "elapsed_time": "0:21:55", "remaining_time": "6:44:47", "throughput": 1497.94, "total_tokens": 1970304} {"current_steps": 9345, "total_steps": 181800, "loss": 0.1541, "lr": 2.56985698569857e-05, "epoch": 1.028052805280528, "percentage": 5.14, "elapsed_time": "0:21:56", "remaining_time": "6:44:46", "throughput": 1497.95, "total_tokens": 1971360} {"current_steps": 9350, "total_steps": 181800, "loss": 0.1555, "lr": 2.5712321232123215e-05, "epoch": 1.0286028602860287, "percentage": 5.14, "elapsed_time": "0:21:56", "remaining_time": "6:44:45", "throughput": 1497.96, "total_tokens": 1972416} {"current_steps": 9355, "total_steps": 181800, "loss": 0.0957, "lr": 2.5726072607260726e-05, "epoch": 1.029152915291529, "percentage": 5.15, "elapsed_time": "0:21:57", "remaining_time": "6:44:44", "throughput": 1497.95, "total_tokens": 1973440} {"current_steps": 9360, "total_steps": 181800, "loss": 0.1881, "lr": 2.573982398239824e-05, "epoch": 1.0297029702970297, "percentage": 5.15, "elapsed_time": "0:21:58", "remaining_time": "6:44:43", "throughput": 1497.91, "total_tokens": 1974432} {"current_steps": 9365, "total_steps": 181800, "loss": 0.2523, "lr": 2.5753575357535753e-05, "epoch": 1.0302530253025302, "percentage": 5.15, "elapsed_time": "0:21:58", "remaining_time": "6:44:43", "throughput": 1497.92, "total_tokens": 1975488} {"current_steps": 9370, "total_steps": 181800, "loss": 0.16, "lr": 2.5767326732673268e-05, "epoch": 1.0308030803080308, "percentage": 5.15, "elapsed_time": "0:21:59", "remaining_time": "6:44:42", "throughput": 1497.95, "total_tokens": 1976576} {"current_steps": 9375, "total_steps": 181800, "loss": 0.0999, "lr": 2.578107810781078e-05, "epoch": 1.0313531353135315, "percentage": 5.16, "elapsed_time": "0:22:00", "remaining_time": "6:44:41", "throughput": 1497.96, "total_tokens": 1977632} {"current_steps": 9380, "total_steps": 181800, "loss": 0.1711, "lr": 2.5794829482948295e-05, "epoch": 1.0319031903190319, "percentage": 5.16, "elapsed_time": "0:22:00", "remaining_time": "6:44:40", "throughput": 1497.99, "total_tokens": 1978720} {"current_steps": 9385, "total_steps": 181800, "loss": 0.2065, "lr": 2.5808580858085813e-05, "epoch": 1.0324532453245325, "percentage": 5.16, "elapsed_time": "0:22:01", "remaining_time": "6:44:39", "throughput": 1497.97, "total_tokens": 1979744} {"current_steps": 9390, "total_steps": 181800, "loss": 0.173, "lr": 2.582233223322332e-05, "epoch": 1.033003300330033, "percentage": 5.17, "elapsed_time": "0:22:02", "remaining_time": "6:44:38", "throughput": 1498.01, "total_tokens": 1980832} {"current_steps": 9395, "total_steps": 181800, "loss": 0.1873, "lr": 2.583608360836084e-05, "epoch": 1.0335533553355336, "percentage": 5.17, "elapsed_time": "0:22:03", "remaining_time": "6:44:38", "throughput": 1498.02, "total_tokens": 1981888} {"current_steps": 9400, "total_steps": 181800, "loss": 0.1223, "lr": 2.584983498349835e-05, "epoch": 1.034103410341034, "percentage": 5.17, "elapsed_time": "0:22:03", "remaining_time": "6:44:37", "throughput": 1498.03, "total_tokens": 1982944} {"current_steps": 9405, "total_steps": 181800, "loss": 0.2223, "lr": 2.5863586358635867e-05, "epoch": 1.0346534653465347, "percentage": 5.17, "elapsed_time": "0:22:04", "remaining_time": "6:44:36", "throughput": 1498.04, "total_tokens": 1984000} {"current_steps": 9410, "total_steps": 181800, "loss": 0.1244, "lr": 2.587733773377338e-05, "epoch": 1.0352035203520351, "percentage": 5.18, "elapsed_time": "0:22:05", "remaining_time": "6:44:35", "throughput": 1498.03, "total_tokens": 1985024} {"current_steps": 9415, "total_steps": 181800, "loss": 0.187, "lr": 2.5891089108910893e-05, "epoch": 1.0357535753575358, "percentage": 5.18, "elapsed_time": "0:22:05", "remaining_time": "6:44:34", "throughput": 1498.04, "total_tokens": 1986080} {"current_steps": 9420, "total_steps": 181800, "loss": 0.0862, "lr": 2.5904840484048405e-05, "epoch": 1.0363036303630364, "percentage": 5.18, "elapsed_time": "0:22:06", "remaining_time": "6:44:33", "throughput": 1498.03, "total_tokens": 1987104} {"current_steps": 9425, "total_steps": 181800, "loss": 0.1237, "lr": 2.591859185918592e-05, "epoch": 1.0368536853685368, "percentage": 5.18, "elapsed_time": "0:22:07", "remaining_time": "6:44:32", "throughput": 1498.06, "total_tokens": 1988192} {"current_steps": 9430, "total_steps": 181800, "loss": 0.0969, "lr": 2.5932343234323435e-05, "epoch": 1.0374037403740375, "percentage": 5.19, "elapsed_time": "0:22:07", "remaining_time": "6:44:32", "throughput": 1498.04, "total_tokens": 1989216} {"current_steps": 9435, "total_steps": 181800, "loss": 0.1341, "lr": 2.5946094609460947e-05, "epoch": 1.037953795379538, "percentage": 5.19, "elapsed_time": "0:22:08", "remaining_time": "6:44:31", "throughput": 1498.05, "total_tokens": 1990272} {"current_steps": 9440, "total_steps": 181800, "loss": 0.2467, "lr": 2.5959845984598462e-05, "epoch": 1.0385038503850386, "percentage": 5.19, "elapsed_time": "0:22:09", "remaining_time": "6:44:30", "throughput": 1498.02, "total_tokens": 1991264} {"current_steps": 9445, "total_steps": 181800, "loss": 0.1097, "lr": 2.5973597359735973e-05, "epoch": 1.039053905390539, "percentage": 5.2, "elapsed_time": "0:22:09", "remaining_time": "6:44:29", "throughput": 1498.0, "total_tokens": 1992288} {"current_steps": 9450, "total_steps": 181800, "loss": 0.1311, "lr": 2.598734873487349e-05, "epoch": 1.0396039603960396, "percentage": 5.2, "elapsed_time": "0:22:10", "remaining_time": "6:44:28", "throughput": 1498.02, "total_tokens": 1993344} {"current_steps": 9455, "total_steps": 181800, "loss": 0.1569, "lr": 2.6001100110011e-05, "epoch": 1.04015401540154, "percentage": 5.2, "elapsed_time": "0:22:11", "remaining_time": "6:44:27", "throughput": 1498.08, "total_tokens": 1994464} {"current_steps": 9460, "total_steps": 181800, "loss": 0.1076, "lr": 2.601485148514852e-05, "epoch": 1.0407040704070407, "percentage": 5.2, "elapsed_time": "0:22:12", "remaining_time": "6:44:26", "throughput": 1498.14, "total_tokens": 1995584} {"current_steps": 9465, "total_steps": 181800, "loss": 0.1158, "lr": 2.6028602860286027e-05, "epoch": 1.0412541254125411, "percentage": 5.21, "elapsed_time": "0:22:12", "remaining_time": "6:44:25", "throughput": 1498.15, "total_tokens": 1996640} {"current_steps": 9470, "total_steps": 181800, "loss": 0.1151, "lr": 2.6042354235423545e-05, "epoch": 1.0418041804180418, "percentage": 5.21, "elapsed_time": "0:22:13", "remaining_time": "6:44:25", "throughput": 1498.16, "total_tokens": 1997696} {"current_steps": 9475, "total_steps": 181800, "loss": 0.1794, "lr": 2.6056105610561054e-05, "epoch": 1.0423542354235424, "percentage": 5.21, "elapsed_time": "0:22:14", "remaining_time": "6:44:24", "throughput": 1498.15, "total_tokens": 1998720} {"current_steps": 9480, "total_steps": 181800, "loss": 0.1214, "lr": 2.6069856985698572e-05, "epoch": 1.0429042904290429, "percentage": 5.21, "elapsed_time": "0:22:14", "remaining_time": "6:44:23", "throughput": 1498.21, "total_tokens": 1999840} {"current_steps": 9485, "total_steps": 181800, "loss": 0.1654, "lr": 2.6083608360836087e-05, "epoch": 1.0434543454345435, "percentage": 5.22, "elapsed_time": "0:22:15", "remaining_time": "6:44:22", "throughput": 1498.17, "total_tokens": 2000832} {"current_steps": 9490, "total_steps": 181800, "loss": 0.14, "lr": 2.60973597359736e-05, "epoch": 1.044004400440044, "percentage": 5.22, "elapsed_time": "0:22:16", "remaining_time": "6:44:21", "throughput": 1498.22, "total_tokens": 2001952} {"current_steps": 9495, "total_steps": 181800, "loss": 0.1604, "lr": 2.6111111111111114e-05, "epoch": 1.0445544554455446, "percentage": 5.22, "elapsed_time": "0:22:16", "remaining_time": "6:44:20", "throughput": 1498.21, "total_tokens": 2002976} {"current_steps": 9500, "total_steps": 181800, "loss": 0.155, "lr": 2.6124862486248625e-05, "epoch": 1.045104510451045, "percentage": 5.23, "elapsed_time": "0:22:17", "remaining_time": "6:44:19", "throughput": 1498.2, "total_tokens": 2004000} {"current_steps": 9505, "total_steps": 181800, "loss": 0.1591, "lr": 2.613861386138614e-05, "epoch": 1.0456545654565457, "percentage": 5.23, "elapsed_time": "0:22:18", "remaining_time": "6:44:19", "throughput": 1498.24, "total_tokens": 2005088} {"current_steps": 9510, "total_steps": 181800, "loss": 0.1562, "lr": 2.6152365236523652e-05, "epoch": 1.046204620462046, "percentage": 5.23, "elapsed_time": "0:22:18", "remaining_time": "6:44:18", "throughput": 1498.25, "total_tokens": 2006144} {"current_steps": 9515, "total_steps": 181800, "loss": 0.1213, "lr": 2.6166116611661167e-05, "epoch": 1.0467546754675467, "percentage": 5.23, "elapsed_time": "0:22:19", "remaining_time": "6:44:17", "throughput": 1498.27, "total_tokens": 2007200} {"current_steps": 9520, "total_steps": 181800, "loss": 0.1071, "lr": 2.617986798679868e-05, "epoch": 1.0473047304730474, "percentage": 5.24, "elapsed_time": "0:22:20", "remaining_time": "6:44:16", "throughput": 1498.3, "total_tokens": 2008288} {"current_steps": 9525, "total_steps": 181800, "loss": 0.0919, "lr": 2.6193619361936194e-05, "epoch": 1.0478547854785478, "percentage": 5.24, "elapsed_time": "0:22:21", "remaining_time": "6:44:15", "throughput": 1498.31, "total_tokens": 2009344} {"current_steps": 9530, "total_steps": 181800, "loss": 0.2554, "lr": 2.6207370737073712e-05, "epoch": 1.0484048404840485, "percentage": 5.24, "elapsed_time": "0:22:21", "remaining_time": "6:44:14", "throughput": 1498.34, "total_tokens": 2010432} {"current_steps": 9535, "total_steps": 181800, "loss": 0.13, "lr": 2.622112211221122e-05, "epoch": 1.048954895489549, "percentage": 5.24, "elapsed_time": "0:22:22", "remaining_time": "6:44:13", "throughput": 1498.29, "total_tokens": 2011392} {"current_steps": 9540, "total_steps": 181800, "loss": 0.1608, "lr": 2.623487348734874e-05, "epoch": 1.0495049504950495, "percentage": 5.25, "elapsed_time": "0:22:23", "remaining_time": "6:44:12", "throughput": 1498.27, "total_tokens": 2012416} {"current_steps": 9545, "total_steps": 181800, "loss": 0.1673, "lr": 2.6248624862486247e-05, "epoch": 1.05005500550055, "percentage": 5.25, "elapsed_time": "0:22:23", "remaining_time": "6:44:12", "throughput": 1498.26, "total_tokens": 2013440} {"current_steps": 9550, "total_steps": 181800, "loss": 0.0955, "lr": 2.6262376237623766e-05, "epoch": 1.0506050605060506, "percentage": 5.25, "elapsed_time": "0:22:24", "remaining_time": "6:44:11", "throughput": 1498.24, "total_tokens": 2014464} {"current_steps": 9555, "total_steps": 181800, "loss": 0.0642, "lr": 2.6276127612761274e-05, "epoch": 1.051155115511551, "percentage": 5.26, "elapsed_time": "0:22:25", "remaining_time": "6:44:10", "throughput": 1498.3, "total_tokens": 2015584} {"current_steps": 9560, "total_steps": 181800, "loss": 0.1649, "lr": 2.6289878987898792e-05, "epoch": 1.0517051705170517, "percentage": 5.26, "elapsed_time": "0:22:25", "remaining_time": "6:44:09", "throughput": 1498.27, "total_tokens": 2016576} {"current_steps": 9565, "total_steps": 181800, "loss": 0.0999, "lr": 2.6303630363036304e-05, "epoch": 1.0522552255225524, "percentage": 5.26, "elapsed_time": "0:22:26", "remaining_time": "6:44:08", "throughput": 1498.23, "total_tokens": 2017568} {"current_steps": 9570, "total_steps": 181800, "loss": 0.0807, "lr": 2.631738173817382e-05, "epoch": 1.0528052805280528, "percentage": 5.26, "elapsed_time": "0:22:27", "remaining_time": "6:44:07", "throughput": 1498.26, "total_tokens": 2018656} {"current_steps": 9575, "total_steps": 181800, "loss": 0.2081, "lr": 2.6331133113311334e-05, "epoch": 1.0533553355335534, "percentage": 5.27, "elapsed_time": "0:22:28", "remaining_time": "6:44:06", "throughput": 1498.25, "total_tokens": 2019680} {"current_steps": 9580, "total_steps": 181800, "loss": 0.115, "lr": 2.6344884488448846e-05, "epoch": 1.0539053905390539, "percentage": 5.27, "elapsed_time": "0:22:28", "remaining_time": "6:44:05", "throughput": 1498.26, "total_tokens": 2020736} {"current_steps": 9585, "total_steps": 181800, "loss": 0.1648, "lr": 2.635863586358636e-05, "epoch": 1.0544554455445545, "percentage": 5.27, "elapsed_time": "0:22:29", "remaining_time": "6:44:05", "throughput": 1498.27, "total_tokens": 2021792} {"current_steps": 9590, "total_steps": 181800, "loss": 0.0961, "lr": 2.6372387238723872e-05, "epoch": 1.055005500550055, "percentage": 5.28, "elapsed_time": "0:22:30", "remaining_time": "6:44:04", "throughput": 1498.3, "total_tokens": 2022880} {"current_steps": 9595, "total_steps": 181800, "loss": 0.2458, "lr": 2.6386138613861387e-05, "epoch": 1.0555555555555556, "percentage": 5.28, "elapsed_time": "0:22:30", "remaining_time": "6:44:03", "throughput": 1498.29, "total_tokens": 2023904} {"current_steps": 9600, "total_steps": 181800, "loss": 0.2176, "lr": 2.63998899889989e-05, "epoch": 1.056105610561056, "percentage": 5.28, "elapsed_time": "0:22:31", "remaining_time": "6:44:02", "throughput": 1498.32, "total_tokens": 2024992} {"current_steps": 9605, "total_steps": 181800, "loss": 0.2774, "lr": 2.6413641364136414e-05, "epoch": 1.0566556655665567, "percentage": 5.28, "elapsed_time": "0:22:32", "remaining_time": "6:44:01", "throughput": 1498.33, "total_tokens": 2026048} {"current_steps": 9610, "total_steps": 181800, "loss": 0.2001, "lr": 2.6427392739273926e-05, "epoch": 1.0572057205720573, "percentage": 5.29, "elapsed_time": "0:22:32", "remaining_time": "6:44:00", "throughput": 1498.3, "total_tokens": 2027040} {"current_steps": 9615, "total_steps": 181800, "loss": 0.1194, "lr": 2.644114411441144e-05, "epoch": 1.0577557755775577, "percentage": 5.29, "elapsed_time": "0:22:33", "remaining_time": "6:44:00", "throughput": 1498.33, "total_tokens": 2028128} {"current_steps": 9620, "total_steps": 181800, "loss": 0.1606, "lr": 2.645489548954896e-05, "epoch": 1.0583058305830584, "percentage": 5.29, "elapsed_time": "0:22:34", "remaining_time": "6:43:59", "throughput": 1498.35, "total_tokens": 2029184} {"current_steps": 9625, "total_steps": 181800, "loss": 0.1518, "lr": 2.646864686468647e-05, "epoch": 1.0588558855885588, "percentage": 5.29, "elapsed_time": "0:22:34", "remaining_time": "6:43:58", "throughput": 1498.41, "total_tokens": 2030304} {"current_steps": 9630, "total_steps": 181800, "loss": 0.2569, "lr": 2.6482398239823986e-05, "epoch": 1.0594059405940595, "percentage": 5.3, "elapsed_time": "0:22:35", "remaining_time": "6:43:57", "throughput": 1498.47, "total_tokens": 2031424} {"current_steps": 9635, "total_steps": 181800, "loss": 0.0634, "lr": 2.6496149614961498e-05, "epoch": 1.0599559955995599, "percentage": 5.3, "elapsed_time": "0:22:36", "remaining_time": "6:43:56", "throughput": 1498.41, "total_tokens": 2032384} {"current_steps": 9640, "total_steps": 181800, "loss": 0.1438, "lr": 2.6509900990099013e-05, "epoch": 1.0605060506050605, "percentage": 5.3, "elapsed_time": "0:22:37", "remaining_time": "6:43:55", "throughput": 1498.45, "total_tokens": 2033472} {"current_steps": 9645, "total_steps": 181800, "loss": 0.1682, "lr": 2.6523652365236524e-05, "epoch": 1.061056105610561, "percentage": 5.31, "elapsed_time": "0:22:37", "remaining_time": "6:43:54", "throughput": 1498.44, "total_tokens": 2034496} {"current_steps": 9650, "total_steps": 181800, "loss": 0.1692, "lr": 2.653740374037404e-05, "epoch": 1.0616061606160616, "percentage": 5.31, "elapsed_time": "0:22:38", "remaining_time": "6:43:53", "throughput": 1498.45, "total_tokens": 2035552} {"current_steps": 9655, "total_steps": 181800, "loss": 0.1286, "lr": 2.655115511551155e-05, "epoch": 1.0621562156215623, "percentage": 5.31, "elapsed_time": "0:22:39", "remaining_time": "6:43:52", "throughput": 1498.44, "total_tokens": 2036576} {"current_steps": 9660, "total_steps": 181800, "loss": 0.1918, "lr": 2.6564906490649066e-05, "epoch": 1.0627062706270627, "percentage": 5.31, "elapsed_time": "0:22:39", "remaining_time": "6:43:51", "throughput": 1498.48, "total_tokens": 2037664} {"current_steps": 9665, "total_steps": 181800, "loss": 0.1683, "lr": 2.657865786578658e-05, "epoch": 1.0632563256325633, "percentage": 5.32, "elapsed_time": "0:22:40", "remaining_time": "6:43:51", "throughput": 1498.44, "total_tokens": 2038656} {"current_steps": 9670, "total_steps": 181800, "loss": 0.0944, "lr": 2.6592409240924093e-05, "epoch": 1.0638063806380638, "percentage": 5.32, "elapsed_time": "0:22:41", "remaining_time": "6:43:50", "throughput": 1498.47, "total_tokens": 2039744} {"current_steps": 9675, "total_steps": 181800, "loss": 0.0859, "lr": 2.6606160616061608e-05, "epoch": 1.0643564356435644, "percentage": 5.32, "elapsed_time": "0:22:41", "remaining_time": "6:43:49", "throughput": 1498.44, "total_tokens": 2040736} {"current_steps": 9680, "total_steps": 181800, "loss": 0.1467, "lr": 2.661991199119912e-05, "epoch": 1.0649064906490648, "percentage": 5.32, "elapsed_time": "0:22:42", "remaining_time": "6:43:48", "throughput": 1498.4, "total_tokens": 2041728} {"current_steps": 9685, "total_steps": 181800, "loss": 0.179, "lr": 2.6633663366336638e-05, "epoch": 1.0654565456545655, "percentage": 5.33, "elapsed_time": "0:22:43", "remaining_time": "6:43:47", "throughput": 1498.36, "total_tokens": 2042720} {"current_steps": 9690, "total_steps": 181800, "loss": 0.0855, "lr": 2.6647414741474146e-05, "epoch": 1.066006600660066, "percentage": 5.33, "elapsed_time": "0:22:43", "remaining_time": "6:43:46", "throughput": 1498.4, "total_tokens": 2043808} {"current_steps": 9695, "total_steps": 181800, "loss": 0.1673, "lr": 2.6661166116611665e-05, "epoch": 1.0665566556655666, "percentage": 5.33, "elapsed_time": "0:22:44", "remaining_time": "6:43:45", "throughput": 1498.38, "total_tokens": 2044832} {"current_steps": 9700, "total_steps": 181800, "loss": 0.1448, "lr": 2.6674917491749173e-05, "epoch": 1.0671067106710672, "percentage": 5.34, "elapsed_time": "0:22:45", "remaining_time": "6:43:45", "throughput": 1498.42, "total_tokens": 2045920} {"current_steps": 9705, "total_steps": 181800, "loss": 0.1232, "lr": 2.668866886688669e-05, "epoch": 1.0676567656765676, "percentage": 5.34, "elapsed_time": "0:22:46", "remaining_time": "6:43:44", "throughput": 1498.4, "total_tokens": 2046944} {"current_steps": 9710, "total_steps": 181800, "loss": 0.105, "lr": 2.6702420242024206e-05, "epoch": 1.0682068206820683, "percentage": 5.34, "elapsed_time": "0:22:46", "remaining_time": "6:43:43", "throughput": 1498.41, "total_tokens": 2048000} {"current_steps": 9715, "total_steps": 181800, "loss": 0.144, "lr": 2.6716171617161718e-05, "epoch": 1.0687568756875687, "percentage": 5.34, "elapsed_time": "0:22:47", "remaining_time": "6:43:42", "throughput": 1498.42, "total_tokens": 2049056} {"current_steps": 9720, "total_steps": 181800, "loss": 0.0957, "lr": 2.6729922992299233e-05, "epoch": 1.0693069306930694, "percentage": 5.35, "elapsed_time": "0:22:48", "remaining_time": "6:43:41", "throughput": 1498.48, "total_tokens": 2050176} {"current_steps": 9725, "total_steps": 181800, "loss": 0.0685, "lr": 2.6743674367436745e-05, "epoch": 1.0698569856985698, "percentage": 5.35, "elapsed_time": "0:22:48", "remaining_time": "6:43:40", "throughput": 1498.53, "total_tokens": 2051296} {"current_steps": 9730, "total_steps": 181800, "loss": 0.105, "lr": 2.675742574257426e-05, "epoch": 1.0704070407040704, "percentage": 5.35, "elapsed_time": "0:22:49", "remaining_time": "6:43:39", "throughput": 1498.55, "total_tokens": 2052352} {"current_steps": 9735, "total_steps": 181800, "loss": 0.0587, "lr": 2.677117711771177e-05, "epoch": 1.0709570957095709, "percentage": 5.35, "elapsed_time": "0:22:50", "remaining_time": "6:43:39", "throughput": 1498.56, "total_tokens": 2053408} {"current_steps": 9740, "total_steps": 181800, "loss": 0.3374, "lr": 2.6784928492849286e-05, "epoch": 1.0715071507150715, "percentage": 5.36, "elapsed_time": "0:22:50", "remaining_time": "6:43:38", "throughput": 1498.52, "total_tokens": 2054400} {"current_steps": 9745, "total_steps": 181800, "loss": 0.0861, "lr": 2.6798679867986798e-05, "epoch": 1.0720572057205722, "percentage": 5.36, "elapsed_time": "0:22:51", "remaining_time": "6:43:37", "throughput": 1498.55, "total_tokens": 2055488} {"current_steps": 9750, "total_steps": 181800, "loss": 0.1447, "lr": 2.6812431243124313e-05, "epoch": 1.0726072607260726, "percentage": 5.36, "elapsed_time": "0:22:52", "remaining_time": "6:43:36", "throughput": 1498.56, "total_tokens": 2056544} {"current_steps": 9755, "total_steps": 181800, "loss": 0.1252, "lr": 2.6826182618261825e-05, "epoch": 1.0731573157315732, "percentage": 5.37, "elapsed_time": "0:22:53", "remaining_time": "6:43:35", "throughput": 1498.56, "total_tokens": 2057600} {"current_steps": 9760, "total_steps": 181800, "loss": 0.1383, "lr": 2.683993399339934e-05, "epoch": 1.0737073707370737, "percentage": 5.37, "elapsed_time": "0:22:53", "remaining_time": "6:43:35", "throughput": 1498.57, "total_tokens": 2058656} {"current_steps": 9765, "total_steps": 181800, "loss": 0.1372, "lr": 2.685368536853686e-05, "epoch": 1.0742574257425743, "percentage": 5.37, "elapsed_time": "0:22:54", "remaining_time": "6:43:34", "throughput": 1498.56, "total_tokens": 2059680} {"current_steps": 9770, "total_steps": 181800, "loss": 0.1071, "lr": 2.6867436743674367e-05, "epoch": 1.0748074807480748, "percentage": 5.37, "elapsed_time": "0:22:55", "remaining_time": "6:43:33", "throughput": 1498.57, "total_tokens": 2060736} {"current_steps": 9775, "total_steps": 181800, "loss": 0.2307, "lr": 2.6881188118811885e-05, "epoch": 1.0753575357535754, "percentage": 5.38, "elapsed_time": "0:22:55", "remaining_time": "6:43:32", "throughput": 1498.58, "total_tokens": 2061792} {"current_steps": 9780, "total_steps": 181800, "loss": 0.1645, "lr": 2.6894939493949393e-05, "epoch": 1.0759075907590758, "percentage": 5.38, "elapsed_time": "0:22:56", "remaining_time": "6:43:31", "throughput": 1498.54, "total_tokens": 2062784} {"current_steps": 9785, "total_steps": 181800, "loss": 0.1692, "lr": 2.6908690869086912e-05, "epoch": 1.0764576457645765, "percentage": 5.38, "elapsed_time": "0:22:57", "remaining_time": "6:43:30", "throughput": 1498.5, "total_tokens": 2063776} {"current_steps": 9790, "total_steps": 181800, "loss": 0.085, "lr": 2.6922442244224423e-05, "epoch": 1.0770077007700771, "percentage": 5.39, "elapsed_time": "0:22:57", "remaining_time": "6:43:29", "throughput": 1498.54, "total_tokens": 2064864} {"current_steps": 9795, "total_steps": 181800, "loss": 0.1948, "lr": 2.693619361936194e-05, "epoch": 1.0775577557755776, "percentage": 5.39, "elapsed_time": "0:22:58", "remaining_time": "6:43:29", "throughput": 1498.55, "total_tokens": 2065920} {"current_steps": 9800, "total_steps": 181800, "loss": 0.2375, "lr": 2.694994499449945e-05, "epoch": 1.0781078107810782, "percentage": 5.39, "elapsed_time": "0:22:59", "remaining_time": "6:43:28", "throughput": 1498.56, "total_tokens": 2066976} {"current_steps": 9805, "total_steps": 181800, "loss": 0.1552, "lr": 2.6963696369636965e-05, "epoch": 1.0786578657865786, "percentage": 5.39, "elapsed_time": "0:23:00", "remaining_time": "6:43:27", "throughput": 1498.61, "total_tokens": 2068096} {"current_steps": 9810, "total_steps": 181800, "loss": 0.0874, "lr": 2.697744774477448e-05, "epoch": 1.0792079207920793, "percentage": 5.4, "elapsed_time": "0:23:00", "remaining_time": "6:43:26", "throughput": 1498.64, "total_tokens": 2069184} {"current_steps": 9815, "total_steps": 181800, "loss": 0.2328, "lr": 2.6991199119911992e-05, "epoch": 1.0797579757975797, "percentage": 5.4, "elapsed_time": "0:23:01", "remaining_time": "6:43:25", "throughput": 1498.65, "total_tokens": 2070240} {"current_steps": 9820, "total_steps": 181800, "loss": 0.2146, "lr": 2.7004950495049507e-05, "epoch": 1.0803080308030804, "percentage": 5.4, "elapsed_time": "0:23:02", "remaining_time": "6:43:25", "throughput": 1498.68, "total_tokens": 2071328} {"current_steps": 9825, "total_steps": 181800, "loss": 0.0781, "lr": 2.701870187018702e-05, "epoch": 1.0808580858085808, "percentage": 5.4, "elapsed_time": "0:23:02", "remaining_time": "6:43:24", "throughput": 1498.67, "total_tokens": 2072352} {"current_steps": 9830, "total_steps": 181800, "loss": 0.154, "lr": 2.7032453245324534e-05, "epoch": 1.0814081408140814, "percentage": 5.41, "elapsed_time": "0:23:03", "remaining_time": "6:43:23", "throughput": 1498.65, "total_tokens": 2073376} {"current_steps": 9835, "total_steps": 181800, "loss": 0.2116, "lr": 2.7046204620462045e-05, "epoch": 1.0819581958195819, "percentage": 5.41, "elapsed_time": "0:23:04", "remaining_time": "6:43:22", "throughput": 1498.64, "total_tokens": 2074400} {"current_steps": 9840, "total_steps": 181800, "loss": 0.1007, "lr": 2.705995599559956e-05, "epoch": 1.0825082508250825, "percentage": 5.41, "elapsed_time": "0:23:04", "remaining_time": "6:43:21", "throughput": 1498.74, "total_tokens": 2075584} {"current_steps": 9845, "total_steps": 181800, "loss": 0.2038, "lr": 2.7073707370737072e-05, "epoch": 1.0830583058305832, "percentage": 5.42, "elapsed_time": "0:23:05", "remaining_time": "6:43:21", "throughput": 1498.76, "total_tokens": 2076672} {"current_steps": 9850, "total_steps": 181800, "loss": 0.1716, "lr": 2.708745874587459e-05, "epoch": 1.0836083608360836, "percentage": 5.42, "elapsed_time": "0:23:06", "remaining_time": "6:43:20", "throughput": 1498.75, "total_tokens": 2077696} {"current_steps": 9855, "total_steps": 181800, "loss": 0.1416, "lr": 2.7101210121012105e-05, "epoch": 1.0841584158415842, "percentage": 5.42, "elapsed_time": "0:23:06", "remaining_time": "6:43:19", "throughput": 1498.78, "total_tokens": 2078784} {"current_steps": 9860, "total_steps": 181800, "loss": 0.1194, "lr": 2.7114961496149617e-05, "epoch": 1.0847084708470847, "percentage": 5.42, "elapsed_time": "0:23:07", "remaining_time": "6:43:18", "throughput": 1498.77, "total_tokens": 2079808} {"current_steps": 9865, "total_steps": 181800, "loss": 0.1457, "lr": 2.7128712871287132e-05, "epoch": 1.0852585258525853, "percentage": 5.43, "elapsed_time": "0:23:08", "remaining_time": "6:43:21", "throughput": 1498.55, "total_tokens": 2080896} {"current_steps": 9870, "total_steps": 181800, "loss": 0.1338, "lr": 2.7142464246424644e-05, "epoch": 1.0858085808580857, "percentage": 5.43, "elapsed_time": "0:23:09", "remaining_time": "6:43:20", "throughput": 1498.56, "total_tokens": 2081952} {"current_steps": 9875, "total_steps": 181800, "loss": 0.14, "lr": 2.715621562156216e-05, "epoch": 1.0863586358635864, "percentage": 5.43, "elapsed_time": "0:23:09", "remaining_time": "6:43:20", "throughput": 1498.61, "total_tokens": 2083072} {"current_steps": 9880, "total_steps": 181800, "loss": 0.2069, "lr": 2.716996699669967e-05, "epoch": 1.0869086908690868, "percentage": 5.43, "elapsed_time": "0:23:10", "remaining_time": "6:43:19", "throughput": 1498.6, "total_tokens": 2084096} {"current_steps": 9885, "total_steps": 181800, "loss": 0.273, "lr": 2.7183718371837185e-05, "epoch": 1.0874587458745875, "percentage": 5.44, "elapsed_time": "0:23:11", "remaining_time": "6:43:18", "throughput": 1498.63, "total_tokens": 2085184} {"current_steps": 9890, "total_steps": 181800, "loss": 0.0989, "lr": 2.7197469746974697e-05, "epoch": 1.0880088008800881, "percentage": 5.44, "elapsed_time": "0:23:12", "remaining_time": "6:43:17", "throughput": 1498.7, "total_tokens": 2086336} {"current_steps": 9895, "total_steps": 181800, "loss": 0.1105, "lr": 2.7211221122112212e-05, "epoch": 1.0885588558855885, "percentage": 5.44, "elapsed_time": "0:23:12", "remaining_time": "6:43:16", "throughput": 1498.68, "total_tokens": 2087360} {"current_steps": 9900, "total_steps": 181800, "loss": 0.0728, "lr": 2.7224972497249727e-05, "epoch": 1.0891089108910892, "percentage": 5.45, "elapsed_time": "0:23:13", "remaining_time": "6:43:16", "throughput": 1498.67, "total_tokens": 2088384} {"current_steps": 9905, "total_steps": 181800, "loss": 0.1104, "lr": 2.723872387238724e-05, "epoch": 1.0896589658965896, "percentage": 5.45, "elapsed_time": "0:23:14", "remaining_time": "6:43:15", "throughput": 1498.66, "total_tokens": 2089408} {"current_steps": 9910, "total_steps": 181800, "loss": 0.122, "lr": 2.7252475247524757e-05, "epoch": 1.0902090209020903, "percentage": 5.45, "elapsed_time": "0:23:14", "remaining_time": "6:43:14", "throughput": 1498.67, "total_tokens": 2090464} {"current_steps": 9915, "total_steps": 181800, "loss": 0.1442, "lr": 2.7266226622662266e-05, "epoch": 1.0907590759075907, "percentage": 5.45, "elapsed_time": "0:23:15", "remaining_time": "6:43:13", "throughput": 1498.7, "total_tokens": 2091552} {"current_steps": 9920, "total_steps": 181800, "loss": 0.1907, "lr": 2.7279977997799784e-05, "epoch": 1.0913091309130913, "percentage": 5.46, "elapsed_time": "0:23:16", "remaining_time": "6:43:12", "throughput": 1498.69, "total_tokens": 2092576} {"current_steps": 9925, "total_steps": 181800, "loss": 0.1563, "lr": 2.7293729372937292e-05, "epoch": 1.0918591859185918, "percentage": 5.46, "elapsed_time": "0:23:16", "remaining_time": "6:43:11", "throughput": 1498.72, "total_tokens": 2093664} {"current_steps": 9930, "total_steps": 181800, "loss": 0.0541, "lr": 2.730748074807481e-05, "epoch": 1.0924092409240924, "percentage": 5.46, "elapsed_time": "0:23:17", "remaining_time": "6:43:10", "throughput": 1498.73, "total_tokens": 2094720} {"current_steps": 9935, "total_steps": 181800, "loss": 0.1018, "lr": 2.732123212321232e-05, "epoch": 1.0929592959295928, "percentage": 5.46, "elapsed_time": "0:23:18", "remaining_time": "6:43:10", "throughput": 1498.74, "total_tokens": 2095776} {"current_steps": 9940, "total_steps": 181800, "loss": 0.0963, "lr": 2.7334983498349837e-05, "epoch": 1.0935093509350935, "percentage": 5.47, "elapsed_time": "0:23:19", "remaining_time": "6:43:09", "throughput": 1498.79, "total_tokens": 2096896} {"current_steps": 9945, "total_steps": 181800, "loss": 0.1598, "lr": 2.7348734873487352e-05, "epoch": 1.0940594059405941, "percentage": 5.47, "elapsed_time": "0:23:19", "remaining_time": "6:43:08", "throughput": 1498.78, "total_tokens": 2097920} {"current_steps": 9950, "total_steps": 181800, "loss": 0.1023, "lr": 2.7362486248624864e-05, "epoch": 1.0946094609460946, "percentage": 5.47, "elapsed_time": "0:23:20", "remaining_time": "6:43:07", "throughput": 1498.79, "total_tokens": 2098976} {"current_steps": 9955, "total_steps": 181800, "loss": 0.1585, "lr": 2.737623762376238e-05, "epoch": 1.0951595159515952, "percentage": 5.48, "elapsed_time": "0:23:21", "remaining_time": "6:43:06", "throughput": 1498.8, "total_tokens": 2100032} {"current_steps": 9960, "total_steps": 181800, "loss": 0.1963, "lr": 2.738998899889989e-05, "epoch": 1.0957095709570956, "percentage": 5.48, "elapsed_time": "0:23:21", "remaining_time": "6:43:05", "throughput": 1498.77, "total_tokens": 2101024} {"current_steps": 9965, "total_steps": 181800, "loss": 0.1526, "lr": 2.7403740374037406e-05, "epoch": 1.0962596259625963, "percentage": 5.48, "elapsed_time": "0:23:22", "remaining_time": "6:43:04", "throughput": 1498.76, "total_tokens": 2102048} {"current_steps": 9970, "total_steps": 181800, "loss": 0.1206, "lr": 2.7417491749174917e-05, "epoch": 1.0968096809680967, "percentage": 5.48, "elapsed_time": "0:23:23", "remaining_time": "6:43:04", "throughput": 1498.8, "total_tokens": 2103136} {"current_steps": 9975, "total_steps": 181800, "loss": 0.0929, "lr": 2.7431243124312433e-05, "epoch": 1.0973597359735974, "percentage": 5.49, "elapsed_time": "0:23:23", "remaining_time": "6:43:03", "throughput": 1498.81, "total_tokens": 2104192} {"current_steps": 9980, "total_steps": 181800, "loss": 0.1557, "lr": 2.7444994499449944e-05, "epoch": 1.0979097909790978, "percentage": 5.49, "elapsed_time": "0:23:24", "remaining_time": "6:43:02", "throughput": 1498.84, "total_tokens": 2105280} {"current_steps": 9985, "total_steps": 181800, "loss": 0.107, "lr": 2.745874587458746e-05, "epoch": 1.0984598459845984, "percentage": 5.49, "elapsed_time": "0:23:25", "remaining_time": "6:43:01", "throughput": 1498.87, "total_tokens": 2106368} {"current_steps": 9990, "total_steps": 181800, "loss": 0.1889, "lr": 2.747249724972497e-05, "epoch": 1.099009900990099, "percentage": 5.5, "elapsed_time": "0:23:25", "remaining_time": "6:43:00", "throughput": 1498.84, "total_tokens": 2107360} {"current_steps": 9995, "total_steps": 181800, "loss": 0.1003, "lr": 2.7486248624862486e-05, "epoch": 1.0995599559955995, "percentage": 5.5, "elapsed_time": "0:23:26", "remaining_time": "6:42:59", "throughput": 1498.89, "total_tokens": 2108480} {"current_steps": 10000, "total_steps": 181800, "loss": 0.2157, "lr": 2.7500000000000004e-05, "epoch": 1.1001100110011002, "percentage": 5.5, "elapsed_time": "0:23:27", "remaining_time": "6:42:58", "throughput": 1498.88, "total_tokens": 2109504} {"current_steps": 10005, "total_steps": 181800, "loss": 0.164, "lr": 2.7513751375137513e-05, "epoch": 1.1006600660066006, "percentage": 5.5, "elapsed_time": "0:23:28", "remaining_time": "6:42:58", "throughput": 1498.91, "total_tokens": 2110592} {"current_steps": 10010, "total_steps": 181800, "loss": 0.0827, "lr": 2.752750275027503e-05, "epoch": 1.1012101210121013, "percentage": 5.51, "elapsed_time": "0:23:28", "remaining_time": "6:42:57", "throughput": 1498.92, "total_tokens": 2111648} {"current_steps": 10015, "total_steps": 181800, "loss": 0.0975, "lr": 2.7541254125412543e-05, "epoch": 1.1017601760176017, "percentage": 5.51, "elapsed_time": "0:23:29", "remaining_time": "6:42:56", "throughput": 1498.89, "total_tokens": 2112640} {"current_steps": 10020, "total_steps": 181800, "loss": 0.1352, "lr": 2.7555005500550058e-05, "epoch": 1.1023102310231023, "percentage": 5.51, "elapsed_time": "0:23:30", "remaining_time": "6:42:55", "throughput": 1498.89, "total_tokens": 2113696} {"current_steps": 10025, "total_steps": 181800, "loss": 0.0813, "lr": 2.756875687568757e-05, "epoch": 1.1028602860286028, "percentage": 5.51, "elapsed_time": "0:23:30", "remaining_time": "6:42:54", "throughput": 1498.9, "total_tokens": 2114752} {"current_steps": 10030, "total_steps": 181800, "loss": 0.1609, "lr": 2.7582508250825084e-05, "epoch": 1.1034103410341034, "percentage": 5.52, "elapsed_time": "0:23:31", "remaining_time": "6:42:53", "throughput": 1498.92, "total_tokens": 2115808} {"current_steps": 10035, "total_steps": 181800, "loss": 0.1171, "lr": 2.7596259625962596e-05, "epoch": 1.103960396039604, "percentage": 5.52, "elapsed_time": "0:23:32", "remaining_time": "6:42:52", "throughput": 1498.93, "total_tokens": 2116864} {"current_steps": 10040, "total_steps": 181800, "loss": 0.1837, "lr": 2.761001100110011e-05, "epoch": 1.1045104510451045, "percentage": 5.52, "elapsed_time": "0:23:32", "remaining_time": "6:42:52", "throughput": 1498.94, "total_tokens": 2117920} {"current_steps": 10045, "total_steps": 181800, "loss": 0.0617, "lr": 2.7623762376237626e-05, "epoch": 1.1050605060506051, "percentage": 5.53, "elapsed_time": "0:23:33", "remaining_time": "6:42:51", "throughput": 1498.93, "total_tokens": 2118944} {"current_steps": 10050, "total_steps": 181800, "loss": 0.1004, "lr": 2.7637513751375138e-05, "epoch": 1.1056105610561056, "percentage": 5.53, "elapsed_time": "0:23:34", "remaining_time": "6:42:50", "throughput": 1498.9, "total_tokens": 2119936} {"current_steps": 10055, "total_steps": 181800, "loss": 0.0832, "lr": 2.7651265126512653e-05, "epoch": 1.1061606160616062, "percentage": 5.53, "elapsed_time": "0:23:35", "remaining_time": "6:42:49", "throughput": 1498.96, "total_tokens": 2121056} {"current_steps": 10060, "total_steps": 181800, "loss": 0.1527, "lr": 2.7665016501650165e-05, "epoch": 1.1067106710671066, "percentage": 5.53, "elapsed_time": "0:23:35", "remaining_time": "6:42:48", "throughput": 1498.99, "total_tokens": 2122144} {"current_steps": 10065, "total_steps": 181800, "loss": 0.0896, "lr": 2.767876787678768e-05, "epoch": 1.1072607260726073, "percentage": 5.54, "elapsed_time": "0:23:36", "remaining_time": "6:42:47", "throughput": 1499.0, "total_tokens": 2123200} {"current_steps": 10070, "total_steps": 181800, "loss": 0.1465, "lr": 2.769251925192519e-05, "epoch": 1.1078107810781077, "percentage": 5.54, "elapsed_time": "0:23:37", "remaining_time": "6:42:46", "throughput": 1499.01, "total_tokens": 2124256} {"current_steps": 10075, "total_steps": 181800, "loss": 0.1076, "lr": 2.770627062706271e-05, "epoch": 1.1083608360836084, "percentage": 5.54, "elapsed_time": "0:23:37", "remaining_time": "6:42:45", "throughput": 1499.06, "total_tokens": 2125376} {"current_steps": 10080, "total_steps": 181800, "loss": 0.1215, "lr": 2.7720022002200218e-05, "epoch": 1.108910891089109, "percentage": 5.54, "elapsed_time": "0:23:38", "remaining_time": "6:42:45", "throughput": 1499.1, "total_tokens": 2126464} {"current_steps": 10085, "total_steps": 181800, "loss": 0.0992, "lr": 2.7733773377337736e-05, "epoch": 1.1094609460946094, "percentage": 5.55, "elapsed_time": "0:23:39", "remaining_time": "6:42:44", "throughput": 1499.11, "total_tokens": 2127520} {"current_steps": 10090, "total_steps": 181800, "loss": 0.124, "lr": 2.774752475247525e-05, "epoch": 1.11001100110011, "percentage": 5.55, "elapsed_time": "0:23:39", "remaining_time": "6:42:43", "throughput": 1499.12, "total_tokens": 2128576} {"current_steps": 10095, "total_steps": 181800, "loss": 0.2153, "lr": 2.7761276127612763e-05, "epoch": 1.1105610561056105, "percentage": 5.55, "elapsed_time": "0:23:40", "remaining_time": "6:42:42", "throughput": 1499.17, "total_tokens": 2129696} {"current_steps": 10100, "total_steps": 181800, "loss": 0.1205, "lr": 2.7775027502750278e-05, "epoch": 1.1111111111111112, "percentage": 5.56, "elapsed_time": "0:23:41", "remaining_time": "6:42:41", "throughput": 1499.18, "total_tokens": 2130752} {"current_steps": 10105, "total_steps": 181800, "loss": 0.1938, "lr": 2.778877887788779e-05, "epoch": 1.1116611661166116, "percentage": 5.56, "elapsed_time": "0:23:41", "remaining_time": "6:42:40", "throughput": 1499.28, "total_tokens": 2131936} {"current_steps": 10110, "total_steps": 181800, "loss": 0.2512, "lr": 2.7802530253025305e-05, "epoch": 1.1122112211221122, "percentage": 5.56, "elapsed_time": "0:23:42", "remaining_time": "6:42:39", "throughput": 1499.32, "total_tokens": 2133024} {"current_steps": 10115, "total_steps": 181800, "loss": 0.0786, "lr": 2.7816281628162816e-05, "epoch": 1.1127612761276127, "percentage": 5.56, "elapsed_time": "0:23:43", "remaining_time": "6:42:39", "throughput": 1499.39, "total_tokens": 2134176} {"current_steps": 10120, "total_steps": 181800, "loss": 0.0715, "lr": 2.783003300330033e-05, "epoch": 1.1133113311331133, "percentage": 5.57, "elapsed_time": "0:23:44", "remaining_time": "6:42:38", "throughput": 1499.43, "total_tokens": 2135264} {"current_steps": 10125, "total_steps": 181800, "loss": 0.1659, "lr": 2.7843784378437843e-05, "epoch": 1.113861386138614, "percentage": 5.57, "elapsed_time": "0:23:44", "remaining_time": "6:42:37", "throughput": 1499.39, "total_tokens": 2136256} {"current_steps": 10130, "total_steps": 181800, "loss": 0.1426, "lr": 2.7857535753575358e-05, "epoch": 1.1144114411441144, "percentage": 5.57, "elapsed_time": "0:23:45", "remaining_time": "6:42:36", "throughput": 1499.4, "total_tokens": 2137312} {"current_steps": 10135, "total_steps": 181800, "loss": 0.2792, "lr": 2.7871287128712877e-05, "epoch": 1.114961496149615, "percentage": 5.57, "elapsed_time": "0:23:46", "remaining_time": "6:42:35", "throughput": 1499.48, "total_tokens": 2138464} {"current_steps": 10140, "total_steps": 181800, "loss": 0.1116, "lr": 2.7885038503850385e-05, "epoch": 1.1155115511551155, "percentage": 5.58, "elapsed_time": "0:23:46", "remaining_time": "6:42:34", "throughput": 1499.47, "total_tokens": 2139488} {"current_steps": 10145, "total_steps": 181800, "loss": 0.1815, "lr": 2.7898789878987903e-05, "epoch": 1.1160616061606161, "percentage": 5.58, "elapsed_time": "0:23:47", "remaining_time": "6:42:33", "throughput": 1499.43, "total_tokens": 2140480} {"current_steps": 10150, "total_steps": 181800, "loss": 0.1854, "lr": 2.791254125412541e-05, "epoch": 1.1166116611661165, "percentage": 5.58, "elapsed_time": "0:23:48", "remaining_time": "6:42:33", "throughput": 1499.42, "total_tokens": 2141504} {"current_steps": 10155, "total_steps": 181800, "loss": 0.1196, "lr": 2.792629262926293e-05, "epoch": 1.1171617161716172, "percentage": 5.59, "elapsed_time": "0:23:48", "remaining_time": "6:42:32", "throughput": 1499.43, "total_tokens": 2142560} {"current_steps": 10160, "total_steps": 181800, "loss": 0.1507, "lr": 2.794004400440044e-05, "epoch": 1.1177117711771176, "percentage": 5.59, "elapsed_time": "0:23:49", "remaining_time": "6:42:31", "throughput": 1499.44, "total_tokens": 2143616} {"current_steps": 10165, "total_steps": 181800, "loss": 0.1305, "lr": 2.7953795379537957e-05, "epoch": 1.1182618261826183, "percentage": 5.59, "elapsed_time": "0:23:50", "remaining_time": "6:42:30", "throughput": 1499.43, "total_tokens": 2144640} {"current_steps": 10170, "total_steps": 181800, "loss": 0.145, "lr": 2.7967546754675465e-05, "epoch": 1.118811881188119, "percentage": 5.59, "elapsed_time": "0:23:50", "remaining_time": "6:42:29", "throughput": 1499.44, "total_tokens": 2145696} {"current_steps": 10175, "total_steps": 181800, "loss": 0.1472, "lr": 2.7981298129812983e-05, "epoch": 1.1193619361936193, "percentage": 5.6, "elapsed_time": "0:23:51", "remaining_time": "6:42:28", "throughput": 1499.48, "total_tokens": 2146784} {"current_steps": 10180, "total_steps": 181800, "loss": 0.1369, "lr": 2.79950495049505e-05, "epoch": 1.11991199119912, "percentage": 5.6, "elapsed_time": "0:23:52", "remaining_time": "6:42:27", "throughput": 1499.43, "total_tokens": 2147744} {"current_steps": 10185, "total_steps": 181800, "loss": 0.1168, "lr": 2.800880088008801e-05, "epoch": 1.1204620462046204, "percentage": 5.6, "elapsed_time": "0:23:53", "remaining_time": "6:42:26", "throughput": 1499.51, "total_tokens": 2148896} {"current_steps": 10190, "total_steps": 181800, "loss": 0.0881, "lr": 2.8022552255225525e-05, "epoch": 1.121012101210121, "percentage": 5.61, "elapsed_time": "0:23:53", "remaining_time": "6:42:26", "throughput": 1499.52, "total_tokens": 2149952} {"current_steps": 10195, "total_steps": 181800, "loss": 0.115, "lr": 2.8036303630363037e-05, "epoch": 1.1215621562156215, "percentage": 5.61, "elapsed_time": "0:23:54", "remaining_time": "6:42:25", "throughput": 1499.5, "total_tokens": 2150976} {"current_steps": 10200, "total_steps": 181800, "loss": 0.1522, "lr": 2.8050055005500552e-05, "epoch": 1.1221122112211221, "percentage": 5.61, "elapsed_time": "0:23:55", "remaining_time": "6:42:24", "throughput": 1499.49, "total_tokens": 2152000} {"current_steps": 10205, "total_steps": 181800, "loss": 0.0775, "lr": 2.8063806380638064e-05, "epoch": 1.1226622662266226, "percentage": 5.61, "elapsed_time": "0:23:55", "remaining_time": "6:42:23", "throughput": 1499.5, "total_tokens": 2153056} {"current_steps": 10210, "total_steps": 181800, "loss": 0.159, "lr": 2.807755775577558e-05, "epoch": 1.1232123212321232, "percentage": 5.62, "elapsed_time": "0:23:56", "remaining_time": "6:42:22", "throughput": 1499.53, "total_tokens": 2154144} {"current_steps": 10215, "total_steps": 181800, "loss": 0.1337, "lr": 2.809130913091309e-05, "epoch": 1.1237623762376239, "percentage": 5.62, "elapsed_time": "0:23:57", "remaining_time": "6:42:21", "throughput": 1499.52, "total_tokens": 2155168} {"current_steps": 10220, "total_steps": 181800, "loss": 0.2224, "lr": 2.8105060506050605e-05, "epoch": 1.1243124312431243, "percentage": 5.62, "elapsed_time": "0:23:57", "remaining_time": "6:42:20", "throughput": 1499.48, "total_tokens": 2156160} {"current_steps": 10225, "total_steps": 181800, "loss": 0.1302, "lr": 2.8118811881188124e-05, "epoch": 1.124862486248625, "percentage": 5.62, "elapsed_time": "0:23:58", "remaining_time": "6:42:20", "throughput": 1499.45, "total_tokens": 2157152} {"current_steps": 10230, "total_steps": 181800, "loss": 0.1775, "lr": 2.8132563256325632e-05, "epoch": 1.1254125412541254, "percentage": 5.63, "elapsed_time": "0:23:59", "remaining_time": "6:42:19", "throughput": 1499.46, "total_tokens": 2158208} {"current_steps": 10235, "total_steps": 181800, "loss": 0.1819, "lr": 2.814631463146315e-05, "epoch": 1.125962596259626, "percentage": 5.63, "elapsed_time": "0:24:00", "remaining_time": "6:42:18", "throughput": 1499.45, "total_tokens": 2159232} {"current_steps": 10240, "total_steps": 181800, "loss": 0.1105, "lr": 2.8160066006600662e-05, "epoch": 1.1265126512651265, "percentage": 5.63, "elapsed_time": "0:24:00", "remaining_time": "6:42:17", "throughput": 1499.48, "total_tokens": 2160320} {"current_steps": 10245, "total_steps": 181800, "loss": 0.1824, "lr": 2.8173817381738177e-05, "epoch": 1.127062706270627, "percentage": 5.64, "elapsed_time": "0:24:01", "remaining_time": "6:42:16", "throughput": 1499.56, "total_tokens": 2161472} {"current_steps": 10250, "total_steps": 181800, "loss": 0.1046, "lr": 2.818756875687569e-05, "epoch": 1.1276127612761275, "percentage": 5.64, "elapsed_time": "0:24:02", "remaining_time": "6:42:15", "throughput": 1499.55, "total_tokens": 2162496} {"current_steps": 10255, "total_steps": 181800, "loss": 0.1589, "lr": 2.8201320132013204e-05, "epoch": 1.1281628162816282, "percentage": 5.64, "elapsed_time": "0:24:02", "remaining_time": "6:42:14", "throughput": 1499.51, "total_tokens": 2163488} {"current_steps": 10260, "total_steps": 181800, "loss": 0.1103, "lr": 2.8215071507150715e-05, "epoch": 1.1287128712871288, "percentage": 5.64, "elapsed_time": "0:24:03", "remaining_time": "6:42:14", "throughput": 1499.53, "total_tokens": 2164544} {"current_steps": 10265, "total_steps": 181800, "loss": 0.134, "lr": 2.822882288228823e-05, "epoch": 1.1292629262926293, "percentage": 5.65, "elapsed_time": "0:24:04", "remaining_time": "6:42:13", "throughput": 1499.53, "total_tokens": 2165600} {"current_steps": 10270, "total_steps": 181800, "loss": 0.1712, "lr": 2.8242574257425742e-05, "epoch": 1.12981298129813, "percentage": 5.65, "elapsed_time": "0:24:04", "remaining_time": "6:42:12", "throughput": 1499.52, "total_tokens": 2166624} {"current_steps": 10275, "total_steps": 181800, "loss": 0.0576, "lr": 2.8256325632563257e-05, "epoch": 1.1303630363036303, "percentage": 5.65, "elapsed_time": "0:24:05", "remaining_time": "6:42:11", "throughput": 1499.5, "total_tokens": 2167648} {"current_steps": 10280, "total_steps": 181800, "loss": 0.2023, "lr": 2.8270077007700772e-05, "epoch": 1.130913091309131, "percentage": 5.65, "elapsed_time": "0:24:06", "remaining_time": "6:42:10", "throughput": 1499.51, "total_tokens": 2168704} {"current_steps": 10285, "total_steps": 181800, "loss": 0.0831, "lr": 2.8283828382838284e-05, "epoch": 1.1314631463146314, "percentage": 5.66, "elapsed_time": "0:24:06", "remaining_time": "6:42:10", "throughput": 1499.52, "total_tokens": 2169760} {"current_steps": 10290, "total_steps": 181800, "loss": 0.2061, "lr": 2.82975797579758e-05, "epoch": 1.132013201320132, "percentage": 5.66, "elapsed_time": "0:24:07", "remaining_time": "6:42:09", "throughput": 1499.53, "total_tokens": 2170816} {"current_steps": 10295, "total_steps": 181800, "loss": 0.1227, "lr": 2.831133113311331e-05, "epoch": 1.1325632563256325, "percentage": 5.66, "elapsed_time": "0:24:08", "remaining_time": "6:42:08", "throughput": 1499.54, "total_tokens": 2171872} {"current_steps": 10300, "total_steps": 181800, "loss": 0.0933, "lr": 2.832508250825083e-05, "epoch": 1.1331133113311331, "percentage": 5.67, "elapsed_time": "0:24:09", "remaining_time": "6:42:07", "throughput": 1499.53, "total_tokens": 2172896} {"current_steps": 10305, "total_steps": 181800, "loss": 0.1561, "lr": 2.8338833883388337e-05, "epoch": 1.1336633663366338, "percentage": 5.67, "elapsed_time": "0:24:09", "remaining_time": "6:42:06", "throughput": 1499.56, "total_tokens": 2173984} {"current_steps": 10310, "total_steps": 181800, "loss": 0.3685, "lr": 2.8352585258525856e-05, "epoch": 1.1342134213421342, "percentage": 5.67, "elapsed_time": "0:24:10", "remaining_time": "6:42:05", "throughput": 1499.6, "total_tokens": 2175072} {"current_steps": 10315, "total_steps": 181800, "loss": 0.1454, "lr": 2.8366336633663364e-05, "epoch": 1.1347634763476349, "percentage": 5.67, "elapsed_time": "0:24:11", "remaining_time": "6:42:04", "throughput": 1499.61, "total_tokens": 2176128} {"current_steps": 10320, "total_steps": 181800, "loss": 0.1603, "lr": 2.8380088008800882e-05, "epoch": 1.1353135313531353, "percentage": 5.68, "elapsed_time": "0:24:11", "remaining_time": "6:42:04", "throughput": 1499.61, "total_tokens": 2177184} {"current_steps": 10325, "total_steps": 181800, "loss": 0.065, "lr": 2.8393839383938397e-05, "epoch": 1.135863586358636, "percentage": 5.68, "elapsed_time": "0:24:12", "remaining_time": "6:42:03", "throughput": 1499.69, "total_tokens": 2178336} {"current_steps": 10330, "total_steps": 181800, "loss": 0.1384, "lr": 2.840759075907591e-05, "epoch": 1.1364136413641364, "percentage": 5.68, "elapsed_time": "0:24:13", "remaining_time": "6:42:02", "throughput": 1499.68, "total_tokens": 2179360} {"current_steps": 10335, "total_steps": 181800, "loss": 0.1497, "lr": 2.8421342134213424e-05, "epoch": 1.136963696369637, "percentage": 5.68, "elapsed_time": "0:24:13", "remaining_time": "6:42:01", "throughput": 1499.71, "total_tokens": 2180448} {"current_steps": 10340, "total_steps": 181800, "loss": 0.1447, "lr": 2.8435093509350936e-05, "epoch": 1.1375137513751374, "percentage": 5.69, "elapsed_time": "0:24:14", "remaining_time": "6:42:00", "throughput": 1499.68, "total_tokens": 2181440} {"current_steps": 10345, "total_steps": 181800, "loss": 0.1263, "lr": 2.844884488448845e-05, "epoch": 1.138063806380638, "percentage": 5.69, "elapsed_time": "0:24:15", "remaining_time": "6:41:59", "throughput": 1499.71, "total_tokens": 2182528} {"current_steps": 10350, "total_steps": 181800, "loss": 0.069, "lr": 2.8462596259625963e-05, "epoch": 1.1386138613861387, "percentage": 5.69, "elapsed_time": "0:24:16", "remaining_time": "6:41:58", "throughput": 1499.69, "total_tokens": 2183552} {"current_steps": 10355, "total_steps": 181800, "loss": 0.1756, "lr": 2.8476347634763478e-05, "epoch": 1.1391639163916392, "percentage": 5.7, "elapsed_time": "0:24:16", "remaining_time": "6:41:58", "throughput": 1499.72, "total_tokens": 2184640} {"current_steps": 10360, "total_steps": 181800, "loss": 0.1006, "lr": 2.849009900990099e-05, "epoch": 1.1397139713971396, "percentage": 5.7, "elapsed_time": "0:24:17", "remaining_time": "6:41:57", "throughput": 1499.78, "total_tokens": 2185760} {"current_steps": 10365, "total_steps": 181800, "loss": 0.113, "lr": 2.8503850385038504e-05, "epoch": 1.1402640264026402, "percentage": 5.7, "elapsed_time": "0:24:18", "remaining_time": "6:41:56", "throughput": 1499.81, "total_tokens": 2186848} {"current_steps": 10370, "total_steps": 181800, "loss": 0.1436, "lr": 2.8517601760176023e-05, "epoch": 1.140814081408141, "percentage": 5.7, "elapsed_time": "0:24:18", "remaining_time": "6:41:55", "throughput": 1499.82, "total_tokens": 2187904} {"current_steps": 10375, "total_steps": 181800, "loss": 0.1186, "lr": 2.853135313531353e-05, "epoch": 1.1413641364136413, "percentage": 5.71, "elapsed_time": "0:24:19", "remaining_time": "6:41:54", "throughput": 1499.83, "total_tokens": 2188960} {"current_steps": 10380, "total_steps": 181800, "loss": 0.1423, "lr": 2.854510451045105e-05, "epoch": 1.141914191419142, "percentage": 5.71, "elapsed_time": "0:24:20", "remaining_time": "6:41:53", "throughput": 1499.86, "total_tokens": 2190048} {"current_steps": 10385, "total_steps": 181800, "loss": 0.0938, "lr": 2.8558855885588558e-05, "epoch": 1.1424642464246424, "percentage": 5.71, "elapsed_time": "0:24:20", "remaining_time": "6:41:53", "throughput": 1499.89, "total_tokens": 2191136} {"current_steps": 10390, "total_steps": 181800, "loss": 0.0574, "lr": 2.8572607260726076e-05, "epoch": 1.143014301430143, "percentage": 5.72, "elapsed_time": "0:24:21", "remaining_time": "6:41:52", "throughput": 1499.87, "total_tokens": 2192160} {"current_steps": 10395, "total_steps": 181800, "loss": 0.1261, "lr": 2.8586358635863584e-05, "epoch": 1.1435643564356435, "percentage": 5.72, "elapsed_time": "0:24:22", "remaining_time": "6:41:51", "throughput": 1499.88, "total_tokens": 2193216} {"current_steps": 10400, "total_steps": 181800, "loss": 0.136, "lr": 2.8600110011001103e-05, "epoch": 1.1441144114411441, "percentage": 5.72, "elapsed_time": "0:24:22", "remaining_time": "6:41:50", "throughput": 1499.91, "total_tokens": 2194304} {"current_steps": 10405, "total_steps": 181800, "loss": 0.0694, "lr": 2.8613861386138614e-05, "epoch": 1.1446644664466445, "percentage": 5.72, "elapsed_time": "0:24:23", "remaining_time": "6:41:49", "throughput": 1499.94, "total_tokens": 2195392} {"current_steps": 10410, "total_steps": 181800, "loss": 0.2092, "lr": 2.862761276127613e-05, "epoch": 1.1452145214521452, "percentage": 5.73, "elapsed_time": "0:24:24", "remaining_time": "6:41:48", "throughput": 1499.99, "total_tokens": 2196512} {"current_steps": 10415, "total_steps": 181800, "loss": 0.1101, "lr": 2.8641364136413645e-05, "epoch": 1.1457645764576458, "percentage": 5.73, "elapsed_time": "0:24:25", "remaining_time": "6:41:48", "throughput": 1500.04, "total_tokens": 2197632} {"current_steps": 10420, "total_steps": 181800, "loss": 0.1857, "lr": 2.8655115511551156e-05, "epoch": 1.1463146314631463, "percentage": 5.73, "elapsed_time": "0:24:25", "remaining_time": "6:41:47", "throughput": 1500.12, "total_tokens": 2198784} {"current_steps": 10425, "total_steps": 181800, "loss": 0.1029, "lr": 2.866886688668867e-05, "epoch": 1.146864686468647, "percentage": 5.73, "elapsed_time": "0:24:26", "remaining_time": "6:41:46", "throughput": 1500.06, "total_tokens": 2199744} {"current_steps": 10430, "total_steps": 181800, "loss": 0.1661, "lr": 2.8682618261826183e-05, "epoch": 1.1474147414741473, "percentage": 5.74, "elapsed_time": "0:24:27", "remaining_time": "6:41:45", "throughput": 1500.03, "total_tokens": 2200736} {"current_steps": 10435, "total_steps": 181800, "loss": 0.1774, "lr": 2.8696369636963698e-05, "epoch": 1.147964796479648, "percentage": 5.74, "elapsed_time": "0:24:27", "remaining_time": "6:41:44", "throughput": 1500.0, "total_tokens": 2201728} {"current_steps": 10440, "total_steps": 181800, "loss": 0.144, "lr": 2.871012101210121e-05, "epoch": 1.1485148514851484, "percentage": 5.74, "elapsed_time": "0:24:28", "remaining_time": "6:41:43", "throughput": 1499.99, "total_tokens": 2202752} {"current_steps": 10445, "total_steps": 181800, "loss": 0.1616, "lr": 2.8723872387238725e-05, "epoch": 1.149064906490649, "percentage": 5.75, "elapsed_time": "0:24:29", "remaining_time": "6:41:43", "throughput": 1500.04, "total_tokens": 2203872} {"current_steps": 10450, "total_steps": 181800, "loss": 0.1244, "lr": 2.8737623762376236e-05, "epoch": 1.1496149614961495, "percentage": 5.75, "elapsed_time": "0:24:29", "remaining_time": "6:41:42", "throughput": 1500.03, "total_tokens": 2204896} {"current_steps": 10455, "total_steps": 181800, "loss": 0.1273, "lr": 2.875137513751375e-05, "epoch": 1.1501650165016502, "percentage": 5.75, "elapsed_time": "0:24:30", "remaining_time": "6:41:41", "throughput": 1499.99, "total_tokens": 2205888} {"current_steps": 10460, "total_steps": 181800, "loss": 0.2014, "lr": 2.876512651265127e-05, "epoch": 1.1507150715071508, "percentage": 5.75, "elapsed_time": "0:24:31", "remaining_time": "6:41:40", "throughput": 1499.98, "total_tokens": 2206912} {"current_steps": 10465, "total_steps": 181800, "loss": 0.0756, "lr": 2.877887788778878e-05, "epoch": 1.1512651265126512, "percentage": 5.76, "elapsed_time": "0:24:31", "remaining_time": "6:41:39", "throughput": 1499.99, "total_tokens": 2207968} {"current_steps": 10470, "total_steps": 181800, "loss": 0.1454, "lr": 2.8792629262926296e-05, "epoch": 1.1518151815181519, "percentage": 5.76, "elapsed_time": "0:24:32", "remaining_time": "6:41:38", "throughput": 1499.98, "total_tokens": 2208992} {"current_steps": 10475, "total_steps": 181800, "loss": 0.1299, "lr": 2.8806380638063808e-05, "epoch": 1.1523652365236523, "percentage": 5.76, "elapsed_time": "0:24:33", "remaining_time": "6:41:37", "throughput": 1499.99, "total_tokens": 2210048} {"current_steps": 10480, "total_steps": 181800, "loss": 0.1294, "lr": 2.8820132013201323e-05, "epoch": 1.152915291529153, "percentage": 5.76, "elapsed_time": "0:24:34", "remaining_time": "6:41:37", "throughput": 1500.02, "total_tokens": 2211136} {"current_steps": 10485, "total_steps": 181800, "loss": 0.1596, "lr": 2.8833883388338835e-05, "epoch": 1.1534653465346534, "percentage": 5.77, "elapsed_time": "0:24:34", "remaining_time": "6:41:36", "throughput": 1500.01, "total_tokens": 2212160} {"current_steps": 10490, "total_steps": 181800, "loss": 0.0493, "lr": 2.884763476347635e-05, "epoch": 1.154015401540154, "percentage": 5.77, "elapsed_time": "0:24:35", "remaining_time": "6:41:35", "throughput": 1500.0, "total_tokens": 2213184} {"current_steps": 10495, "total_steps": 181800, "loss": 0.0731, "lr": 2.886138613861386e-05, "epoch": 1.1545654565456545, "percentage": 5.77, "elapsed_time": "0:24:36", "remaining_time": "6:41:34", "throughput": 1499.98, "total_tokens": 2214208} {"current_steps": 10500, "total_steps": 181800, "loss": 0.0666, "lr": 2.8875137513751377e-05, "epoch": 1.155115511551155, "percentage": 5.78, "elapsed_time": "0:24:36", "remaining_time": "6:41:33", "throughput": 1499.95, "total_tokens": 2215200} {"current_steps": 10505, "total_steps": 181800, "loss": 0.1276, "lr": 2.8888888888888888e-05, "epoch": 1.1556655665566558, "percentage": 5.78, "elapsed_time": "0:24:37", "remaining_time": "6:41:32", "throughput": 1500.0, "total_tokens": 2216320} {"current_steps": 10510, "total_steps": 181800, "loss": 0.1689, "lr": 2.8902640264026403e-05, "epoch": 1.1562156215621562, "percentage": 5.78, "elapsed_time": "0:24:38", "remaining_time": "6:41:32", "throughput": 1500.01, "total_tokens": 2217376} {"current_steps": 10515, "total_steps": 181800, "loss": 0.1356, "lr": 2.8916391639163922e-05, "epoch": 1.1567656765676568, "percentage": 5.78, "elapsed_time": "0:24:38", "remaining_time": "6:41:31", "throughput": 1500.0, "total_tokens": 2218400} {"current_steps": 10520, "total_steps": 181800, "loss": 0.1384, "lr": 2.893014301430143e-05, "epoch": 1.1573157315731573, "percentage": 5.79, "elapsed_time": "0:24:39", "remaining_time": "6:41:30", "throughput": 1500.03, "total_tokens": 2219488} {"current_steps": 10525, "total_steps": 181800, "loss": 0.1169, "lr": 2.894389438943895e-05, "epoch": 1.157865786578658, "percentage": 5.79, "elapsed_time": "0:24:40", "remaining_time": "6:41:29", "throughput": 1500.0, "total_tokens": 2220480} {"current_steps": 10530, "total_steps": 181800, "loss": 0.1371, "lr": 2.8957645764576457e-05, "epoch": 1.1584158415841583, "percentage": 5.79, "elapsed_time": "0:24:41", "remaining_time": "6:41:28", "throughput": 1500.01, "total_tokens": 2221536} {"current_steps": 10535, "total_steps": 181800, "loss": 0.1259, "lr": 2.8971397139713975e-05, "epoch": 1.158965896589659, "percentage": 5.79, "elapsed_time": "0:24:41", "remaining_time": "6:41:27", "throughput": 1499.98, "total_tokens": 2222528} {"current_steps": 10540, "total_steps": 181800, "loss": 0.1039, "lr": 2.8985148514851483e-05, "epoch": 1.1595159515951594, "percentage": 5.8, "elapsed_time": "0:24:42", "remaining_time": "6:41:26", "throughput": 1500.03, "total_tokens": 2223648} {"current_steps": 10545, "total_steps": 181800, "loss": 0.1078, "lr": 2.8998899889989002e-05, "epoch": 1.16006600660066, "percentage": 5.8, "elapsed_time": "0:24:43", "remaining_time": "6:41:25", "throughput": 1500.02, "total_tokens": 2224672} {"current_steps": 10550, "total_steps": 181800, "loss": 0.0817, "lr": 2.901265126512651e-05, "epoch": 1.1606160616061607, "percentage": 5.8, "elapsed_time": "0:24:43", "remaining_time": "6:41:25", "throughput": 1500.03, "total_tokens": 2225728} {"current_steps": 10555, "total_steps": 181800, "loss": 0.1766, "lr": 2.902640264026403e-05, "epoch": 1.1611661166116611, "percentage": 5.81, "elapsed_time": "0:24:44", "remaining_time": "6:41:24", "throughput": 1500.04, "total_tokens": 2226784} {"current_steps": 10560, "total_steps": 181800, "loss": 0.0975, "lr": 2.9040154015401544e-05, "epoch": 1.1617161716171618, "percentage": 5.81, "elapsed_time": "0:24:45", "remaining_time": "6:41:23", "throughput": 1500.07, "total_tokens": 2227872} {"current_steps": 10565, "total_steps": 181800, "loss": 0.126, "lr": 2.9053905390539055e-05, "epoch": 1.1622662266226622, "percentage": 5.81, "elapsed_time": "0:24:45", "remaining_time": "6:41:22", "throughput": 1500.03, "total_tokens": 2228864} {"current_steps": 10570, "total_steps": 181800, "loss": 0.1157, "lr": 2.906765676567657e-05, "epoch": 1.1628162816281629, "percentage": 5.81, "elapsed_time": "0:24:46", "remaining_time": "6:41:21", "throughput": 1500.04, "total_tokens": 2229920} {"current_steps": 10575, "total_steps": 181800, "loss": 0.1391, "lr": 2.9081408140814082e-05, "epoch": 1.1633663366336633, "percentage": 5.82, "elapsed_time": "0:24:47", "remaining_time": "6:41:20", "throughput": 1500.08, "total_tokens": 2231008} {"current_steps": 10580, "total_steps": 181800, "loss": 0.1078, "lr": 2.9095159515951597e-05, "epoch": 1.163916391639164, "percentage": 5.82, "elapsed_time": "0:24:47", "remaining_time": "6:41:20", "throughput": 1500.09, "total_tokens": 2232064} {"current_steps": 10585, "total_steps": 181800, "loss": 0.0441, "lr": 2.910891089108911e-05, "epoch": 1.1644664466446644, "percentage": 5.82, "elapsed_time": "0:24:48", "remaining_time": "6:41:19", "throughput": 1500.12, "total_tokens": 2233152} {"current_steps": 10590, "total_steps": 181800, "loss": 0.1226, "lr": 2.9122662266226624e-05, "epoch": 1.165016501650165, "percentage": 5.83, "elapsed_time": "0:24:49", "remaining_time": "6:41:18", "throughput": 1500.11, "total_tokens": 2234176} {"current_steps": 10595, "total_steps": 181800, "loss": 0.0684, "lr": 2.9136413641364135e-05, "epoch": 1.1655665566556657, "percentage": 5.83, "elapsed_time": "0:24:50", "remaining_time": "6:41:17", "throughput": 1500.14, "total_tokens": 2235264} {"current_steps": 10600, "total_steps": 181800, "loss": 0.155, "lr": 2.915016501650165e-05, "epoch": 1.166116611661166, "percentage": 5.83, "elapsed_time": "0:24:50", "remaining_time": "6:41:16", "throughput": 1500.17, "total_tokens": 2236352} {"current_steps": 10605, "total_steps": 181800, "loss": 0.1045, "lr": 2.916391639163917e-05, "epoch": 1.1666666666666667, "percentage": 5.83, "elapsed_time": "0:24:51", "remaining_time": "6:41:15", "throughput": 1500.22, "total_tokens": 2237472} {"current_steps": 10610, "total_steps": 181800, "loss": 0.2078, "lr": 2.9177667766776677e-05, "epoch": 1.1672167216721672, "percentage": 5.84, "elapsed_time": "0:24:52", "remaining_time": "6:41:15", "throughput": 1500.23, "total_tokens": 2238528} {"current_steps": 10615, "total_steps": 181800, "loss": 0.0542, "lr": 2.9191419141914195e-05, "epoch": 1.1677667766776678, "percentage": 5.84, "elapsed_time": "0:24:52", "remaining_time": "6:41:14", "throughput": 1500.26, "total_tokens": 2239616} {"current_steps": 10620, "total_steps": 181800, "loss": 0.1632, "lr": 2.9205170517051704e-05, "epoch": 1.1683168316831682, "percentage": 5.84, "elapsed_time": "0:24:53", "remaining_time": "6:41:13", "throughput": 1500.25, "total_tokens": 2240640} {"current_steps": 10625, "total_steps": 181800, "loss": 0.1756, "lr": 2.9218921892189222e-05, "epoch": 1.168866886688669, "percentage": 5.84, "elapsed_time": "0:24:54", "remaining_time": "6:41:12", "throughput": 1500.24, "total_tokens": 2241664} {"current_steps": 10630, "total_steps": 181800, "loss": 0.2022, "lr": 2.9232673267326734e-05, "epoch": 1.1694169416941693, "percentage": 5.85, "elapsed_time": "0:24:54", "remaining_time": "6:41:11", "throughput": 1500.24, "total_tokens": 2242720} {"current_steps": 10635, "total_steps": 181800, "loss": 0.1507, "lr": 2.924642464246425e-05, "epoch": 1.16996699669967, "percentage": 5.85, "elapsed_time": "0:24:55", "remaining_time": "6:41:10", "throughput": 1500.28, "total_tokens": 2243808} {"current_steps": 10640, "total_steps": 181800, "loss": 0.0995, "lr": 2.926017601760176e-05, "epoch": 1.1705170517051706, "percentage": 5.85, "elapsed_time": "0:24:56", "remaining_time": "6:41:10", "throughput": 1500.28, "total_tokens": 2244864} {"current_steps": 10645, "total_steps": 181800, "loss": 0.1707, "lr": 2.9273927392739276e-05, "epoch": 1.171067106710671, "percentage": 5.86, "elapsed_time": "0:24:56", "remaining_time": "6:41:09", "throughput": 1500.29, "total_tokens": 2245920} {"current_steps": 10650, "total_steps": 181800, "loss": 0.2044, "lr": 2.928767876787679e-05, "epoch": 1.1716171617161717, "percentage": 5.86, "elapsed_time": "0:24:57", "remaining_time": "6:41:08", "throughput": 1500.3, "total_tokens": 2246976} {"current_steps": 10655, "total_steps": 181800, "loss": 0.0671, "lr": 2.9301430143014302e-05, "epoch": 1.1721672167216721, "percentage": 5.86, "elapsed_time": "0:24:58", "remaining_time": "6:41:07", "throughput": 1500.33, "total_tokens": 2248064} {"current_steps": 10660, "total_steps": 181800, "loss": 0.1591, "lr": 2.9315181518151817e-05, "epoch": 1.1727172717271728, "percentage": 5.86, "elapsed_time": "0:24:59", "remaining_time": "6:41:06", "throughput": 1500.36, "total_tokens": 2249152} {"current_steps": 10665, "total_steps": 181800, "loss": 0.0808, "lr": 2.932893289328933e-05, "epoch": 1.1732673267326732, "percentage": 5.87, "elapsed_time": "0:24:59", "remaining_time": "6:41:05", "throughput": 1500.39, "total_tokens": 2250240} {"current_steps": 10670, "total_steps": 181800, "loss": 0.0962, "lr": 2.9342684268426844e-05, "epoch": 1.1738173817381738, "percentage": 5.87, "elapsed_time": "0:25:00", "remaining_time": "6:41:05", "throughput": 1500.42, "total_tokens": 2251328} {"current_steps": 10675, "total_steps": 181800, "loss": 0.2093, "lr": 2.9356435643564356e-05, "epoch": 1.1743674367436743, "percentage": 5.87, "elapsed_time": "0:25:01", "remaining_time": "6:41:04", "throughput": 1500.4, "total_tokens": 2252352} {"current_steps": 10680, "total_steps": 181800, "loss": 0.0745, "lr": 2.937018701870187e-05, "epoch": 1.174917491749175, "percentage": 5.87, "elapsed_time": "0:25:01", "remaining_time": "6:41:03", "throughput": 1500.41, "total_tokens": 2253408} {"current_steps": 10685, "total_steps": 181800, "loss": 0.0806, "lr": 2.9383938393839382e-05, "epoch": 1.1754675467546756, "percentage": 5.88, "elapsed_time": "0:25:02", "remaining_time": "6:41:02", "throughput": 1500.42, "total_tokens": 2254464} {"current_steps": 10690, "total_steps": 181800, "loss": 0.0593, "lr": 2.93976897689769e-05, "epoch": 1.176017601760176, "percentage": 5.88, "elapsed_time": "0:25:03", "remaining_time": "6:41:01", "throughput": 1500.45, "total_tokens": 2255552} {"current_steps": 10695, "total_steps": 181800, "loss": 0.1073, "lr": 2.9411441144114416e-05, "epoch": 1.1765676567656767, "percentage": 5.88, "elapsed_time": "0:25:03", "remaining_time": "6:41:01", "throughput": 1500.41, "total_tokens": 2256544} {"current_steps": 10700, "total_steps": 181800, "loss": 0.114, "lr": 2.9425192519251928e-05, "epoch": 1.177117711771177, "percentage": 5.89, "elapsed_time": "0:25:04", "remaining_time": "6:41:00", "throughput": 1500.45, "total_tokens": 2257632} {"current_steps": 10705, "total_steps": 181800, "loss": 0.1169, "lr": 2.9438943894389443e-05, "epoch": 1.1776677667766777, "percentage": 5.89, "elapsed_time": "0:25:05", "remaining_time": "6:40:59", "throughput": 1500.47, "total_tokens": 2258720} {"current_steps": 10710, "total_steps": 181800, "loss": 0.1805, "lr": 2.9452695269526954e-05, "epoch": 1.1782178217821782, "percentage": 5.89, "elapsed_time": "0:25:06", "remaining_time": "6:40:58", "throughput": 1500.48, "total_tokens": 2259776} {"current_steps": 10715, "total_steps": 181800, "loss": 0.1803, "lr": 2.946644664466447e-05, "epoch": 1.1787678767876788, "percentage": 5.89, "elapsed_time": "0:25:06", "remaining_time": "6:40:57", "throughput": 1500.53, "total_tokens": 2260896} {"current_steps": 10720, "total_steps": 181800, "loss": 0.1051, "lr": 2.948019801980198e-05, "epoch": 1.1793179317931792, "percentage": 5.9, "elapsed_time": "0:25:07", "remaining_time": "6:40:56", "throughput": 1500.56, "total_tokens": 2261984} {"current_steps": 10725, "total_steps": 181800, "loss": 0.1478, "lr": 2.9493949394939496e-05, "epoch": 1.1798679867986799, "percentage": 5.9, "elapsed_time": "0:25:08", "remaining_time": "6:40:56", "throughput": 1500.59, "total_tokens": 2263072} {"current_steps": 10730, "total_steps": 181800, "loss": 0.1503, "lr": 2.9507700770077008e-05, "epoch": 1.1804180418041805, "percentage": 5.9, "elapsed_time": "0:25:08", "remaining_time": "6:40:55", "throughput": 1500.58, "total_tokens": 2264096} {"current_steps": 10735, "total_steps": 181800, "loss": 0.1559, "lr": 2.9521452145214523e-05, "epoch": 1.180968096809681, "percentage": 5.9, "elapsed_time": "0:25:09", "remaining_time": "6:40:54", "throughput": 1500.59, "total_tokens": 2265152} {"current_steps": 10740, "total_steps": 181800, "loss": 0.1314, "lr": 2.9535203520352034e-05, "epoch": 1.1815181518151816, "percentage": 5.91, "elapsed_time": "0:25:10", "remaining_time": "6:40:53", "throughput": 1500.57, "total_tokens": 2266176} {"current_steps": 10745, "total_steps": 181800, "loss": 0.1835, "lr": 2.954895489548955e-05, "epoch": 1.182068206820682, "percentage": 5.91, "elapsed_time": "0:25:10", "remaining_time": "6:40:52", "throughput": 1500.56, "total_tokens": 2267200} {"current_steps": 10750, "total_steps": 181800, "loss": 0.1816, "lr": 2.9562706270627068e-05, "epoch": 1.1826182618261827, "percentage": 5.91, "elapsed_time": "0:25:11", "remaining_time": "6:40:52", "throughput": 1500.57, "total_tokens": 2268256} {"current_steps": 10755, "total_steps": 181800, "loss": 0.0884, "lr": 2.9576457645764576e-05, "epoch": 1.183168316831683, "percentage": 5.92, "elapsed_time": "0:25:12", "remaining_time": "6:40:51", "throughput": 1500.58, "total_tokens": 2269312} {"current_steps": 10760, "total_steps": 181800, "loss": 0.1368, "lr": 2.9590209020902094e-05, "epoch": 1.1837183718371838, "percentage": 5.92, "elapsed_time": "0:25:12", "remaining_time": "6:40:50", "throughput": 1500.61, "total_tokens": 2270400} {"current_steps": 10765, "total_steps": 181800, "loss": 0.1518, "lr": 2.9603960396039603e-05, "epoch": 1.1842684268426842, "percentage": 5.92, "elapsed_time": "0:25:13", "remaining_time": "6:40:49", "throughput": 1500.58, "total_tokens": 2271392} {"current_steps": 10770, "total_steps": 181800, "loss": 0.1102, "lr": 2.961771177117712e-05, "epoch": 1.1848184818481848, "percentage": 5.92, "elapsed_time": "0:25:14", "remaining_time": "6:40:48", "throughput": 1500.59, "total_tokens": 2272448} {"current_steps": 10775, "total_steps": 181800, "loss": 0.1159, "lr": 2.963146314631463e-05, "epoch": 1.1853685368536855, "percentage": 5.93, "elapsed_time": "0:25:15", "remaining_time": "6:40:47", "throughput": 1500.6, "total_tokens": 2273504} {"current_steps": 10780, "total_steps": 181800, "loss": 0.0706, "lr": 2.9645214521452148e-05, "epoch": 1.185918591859186, "percentage": 5.93, "elapsed_time": "0:25:15", "remaining_time": "6:40:46", "throughput": 1500.63, "total_tokens": 2274592} {"current_steps": 10785, "total_steps": 181800, "loss": 0.1278, "lr": 2.9658965896589656e-05, "epoch": 1.1864686468646866, "percentage": 5.93, "elapsed_time": "0:25:16", "remaining_time": "6:40:46", "throughput": 1500.64, "total_tokens": 2275648} {"current_steps": 10790, "total_steps": 181800, "loss": 0.0331, "lr": 2.9672717271727175e-05, "epoch": 1.187018701870187, "percentage": 5.94, "elapsed_time": "0:25:17", "remaining_time": "6:40:45", "throughput": 1500.66, "total_tokens": 2276736} {"current_steps": 10795, "total_steps": 181800, "loss": 0.1231, "lr": 2.968646864686469e-05, "epoch": 1.1875687568756876, "percentage": 5.94, "elapsed_time": "0:25:17", "remaining_time": "6:40:44", "throughput": 1500.71, "total_tokens": 2277856} {"current_steps": 10800, "total_steps": 181800, "loss": 0.1493, "lr": 2.97002200220022e-05, "epoch": 1.188118811881188, "percentage": 5.94, "elapsed_time": "0:25:18", "remaining_time": "6:40:43", "throughput": 1500.74, "total_tokens": 2278944} {"current_steps": 10805, "total_steps": 181800, "loss": 0.1228, "lr": 2.9713971397139716e-05, "epoch": 1.1886688668866887, "percentage": 5.94, "elapsed_time": "0:25:19", "remaining_time": "6:40:43", "throughput": 1500.69, "total_tokens": 2279936} {"current_steps": 10810, "total_steps": 181800, "loss": 0.2039, "lr": 2.9727722772277228e-05, "epoch": 1.1892189218921891, "percentage": 5.95, "elapsed_time": "0:25:19", "remaining_time": "6:40:42", "throughput": 1500.68, "total_tokens": 2280960} {"current_steps": 10815, "total_steps": 181800, "loss": 0.1282, "lr": 2.9741474147414743e-05, "epoch": 1.1897689768976898, "percentage": 5.95, "elapsed_time": "0:25:20", "remaining_time": "6:40:41", "throughput": 1500.71, "total_tokens": 2282048} {"current_steps": 10820, "total_steps": 181800, "loss": 0.1724, "lr": 2.9755225522552255e-05, "epoch": 1.1903190319031904, "percentage": 5.95, "elapsed_time": "0:25:21", "remaining_time": "6:40:40", "throughput": 1500.66, "total_tokens": 2283008} {"current_steps": 10825, "total_steps": 181800, "loss": 0.1537, "lr": 2.976897689768977e-05, "epoch": 1.1908690869086909, "percentage": 5.95, "elapsed_time": "0:25:22", "remaining_time": "6:40:39", "throughput": 1500.72, "total_tokens": 2284128} {"current_steps": 10830, "total_steps": 181800, "loss": 0.1182, "lr": 2.978272827282728e-05, "epoch": 1.1914191419141915, "percentage": 5.96, "elapsed_time": "0:25:22", "remaining_time": "6:40:38", "throughput": 1500.71, "total_tokens": 2285152} {"current_steps": 10835, "total_steps": 181800, "loss": 0.1346, "lr": 2.9796479647964796e-05, "epoch": 1.191969196919692, "percentage": 5.96, "elapsed_time": "0:25:23", "remaining_time": "6:40:37", "throughput": 1500.72, "total_tokens": 2286208} {"current_steps": 10840, "total_steps": 181800, "loss": 0.1227, "lr": 2.9810231023102315e-05, "epoch": 1.1925192519251926, "percentage": 5.96, "elapsed_time": "0:25:24", "remaining_time": "6:40:37", "throughput": 1500.75, "total_tokens": 2287296} {"current_steps": 10845, "total_steps": 181800, "loss": 0.081, "lr": 2.9823982398239823e-05, "epoch": 1.193069306930693, "percentage": 5.97, "elapsed_time": "0:25:24", "remaining_time": "6:40:36", "throughput": 1500.71, "total_tokens": 2288288} {"current_steps": 10850, "total_steps": 181800, "loss": 0.1271, "lr": 2.983773377337734e-05, "epoch": 1.1936193619361937, "percentage": 5.97, "elapsed_time": "0:25:25", "remaining_time": "6:40:35", "throughput": 1500.66, "total_tokens": 2289248} {"current_steps": 10855, "total_steps": 181800, "loss": 0.1477, "lr": 2.9851485148514853e-05, "epoch": 1.194169416941694, "percentage": 5.97, "elapsed_time": "0:25:26", "remaining_time": "6:40:34", "throughput": 1500.62, "total_tokens": 2290240} {"current_steps": 10860, "total_steps": 181800, "loss": 0.1586, "lr": 2.9865236523652368e-05, "epoch": 1.1947194719471947, "percentage": 5.97, "elapsed_time": "0:25:26", "remaining_time": "6:40:33", "throughput": 1500.67, "total_tokens": 2291360} {"current_steps": 10865, "total_steps": 181800, "loss": 0.1409, "lr": 2.987898789878988e-05, "epoch": 1.1952695269526954, "percentage": 5.98, "elapsed_time": "0:25:27", "remaining_time": "6:40:32", "throughput": 1500.72, "total_tokens": 2292480} {"current_steps": 10870, "total_steps": 181800, "loss": 0.1234, "lr": 2.9892739273927395e-05, "epoch": 1.1958195819581958, "percentage": 5.98, "elapsed_time": "0:25:28", "remaining_time": "6:40:32", "throughput": 1500.71, "total_tokens": 2293504} {"current_steps": 10875, "total_steps": 181800, "loss": 0.1146, "lr": 2.9906490649064907e-05, "epoch": 1.1963696369636962, "percentage": 5.98, "elapsed_time": "0:25:28", "remaining_time": "6:40:31", "throughput": 1500.7, "total_tokens": 2294528} {"current_steps": 10880, "total_steps": 181800, "loss": 0.1826, "lr": 2.992024202420242e-05, "epoch": 1.196919691969197, "percentage": 5.98, "elapsed_time": "0:25:29", "remaining_time": "6:40:30", "throughput": 1500.73, "total_tokens": 2295616} {"current_steps": 10885, "total_steps": 181800, "loss": 0.1326, "lr": 2.9933993399339937e-05, "epoch": 1.1974697469746975, "percentage": 5.99, "elapsed_time": "0:25:30", "remaining_time": "6:40:29", "throughput": 1500.78, "total_tokens": 2296736} {"current_steps": 10890, "total_steps": 181800, "loss": 0.1107, "lr": 2.994774477447745e-05, "epoch": 1.198019801980198, "percentage": 5.99, "elapsed_time": "0:25:31", "remaining_time": "6:40:28", "throughput": 1500.8, "total_tokens": 2297824} {"current_steps": 10895, "total_steps": 181800, "loss": 0.1325, "lr": 2.9961496149614963e-05, "epoch": 1.1985698569856986, "percentage": 5.99, "elapsed_time": "0:25:31", "remaining_time": "6:40:28", "throughput": 1500.81, "total_tokens": 2298880} {"current_steps": 10900, "total_steps": 181800, "loss": 0.097, "lr": 2.9975247524752475e-05, "epoch": 1.199119911991199, "percentage": 6.0, "elapsed_time": "0:25:32", "remaining_time": "6:40:27", "throughput": 1500.84, "total_tokens": 2299968} {"current_steps": 10905, "total_steps": 181800, "loss": 0.1536, "lr": 2.9988998899889993e-05, "epoch": 1.1996699669966997, "percentage": 6.0, "elapsed_time": "0:25:33", "remaining_time": "6:40:26", "throughput": 1500.85, "total_tokens": 2301024} {"current_steps": 10910, "total_steps": 181800, "loss": 0.1318, "lr": 3.0002750275027502e-05, "epoch": 1.2002200220022001, "percentage": 6.0, "elapsed_time": "0:25:33", "remaining_time": "6:40:25", "throughput": 1500.83, "total_tokens": 2302048} {"current_steps": 10915, "total_steps": 181800, "loss": 0.0867, "lr": 3.001650165016502e-05, "epoch": 1.2007700770077008, "percentage": 6.0, "elapsed_time": "0:25:34", "remaining_time": "6:40:24", "throughput": 1500.82, "total_tokens": 2303072} {"current_steps": 10920, "total_steps": 181800, "loss": 0.0809, "lr": 3.003025302530253e-05, "epoch": 1.2013201320132012, "percentage": 6.01, "elapsed_time": "0:25:35", "remaining_time": "6:40:23", "throughput": 1500.85, "total_tokens": 2304160} {"current_steps": 10925, "total_steps": 181800, "loss": 0.0964, "lr": 3.0044004400440047e-05, "epoch": 1.2018701870187019, "percentage": 6.01, "elapsed_time": "0:25:35", "remaining_time": "6:40:23", "throughput": 1500.84, "total_tokens": 2305184} {"current_steps": 10930, "total_steps": 181800, "loss": 0.0736, "lr": 3.0057755775577562e-05, "epoch": 1.2024202420242025, "percentage": 6.01, "elapsed_time": "0:25:36", "remaining_time": "6:40:22", "throughput": 1500.8, "total_tokens": 2306176} {"current_steps": 10935, "total_steps": 181800, "loss": 0.0725, "lr": 3.0071507150715074e-05, "epoch": 1.202970297029703, "percentage": 6.01, "elapsed_time": "0:25:37", "remaining_time": "6:40:21", "throughput": 1500.81, "total_tokens": 2307232} {"current_steps": 10940, "total_steps": 181800, "loss": 0.064, "lr": 3.008525852585259e-05, "epoch": 1.2035203520352036, "percentage": 6.02, "elapsed_time": "0:25:38", "remaining_time": "6:40:20", "throughput": 1500.84, "total_tokens": 2308320} {"current_steps": 10945, "total_steps": 181800, "loss": 0.0833, "lr": 3.00990099009901e-05, "epoch": 1.204070407040704, "percentage": 6.02, "elapsed_time": "0:25:38", "remaining_time": "6:40:19", "throughput": 1500.82, "total_tokens": 2309344} {"current_steps": 10950, "total_steps": 181800, "loss": 0.1547, "lr": 3.0112761276127615e-05, "epoch": 1.2046204620462047, "percentage": 6.02, "elapsed_time": "0:25:39", "remaining_time": "6:40:19", "throughput": 1500.81, "total_tokens": 2310368} {"current_steps": 10955, "total_steps": 181800, "loss": 0.1934, "lr": 3.0126512651265127e-05, "epoch": 1.205170517051705, "percentage": 6.03, "elapsed_time": "0:25:40", "remaining_time": "6:40:18", "throughput": 1500.78, "total_tokens": 2311360} {"current_steps": 10960, "total_steps": 181800, "loss": 0.1172, "lr": 3.0140264026402642e-05, "epoch": 1.2057205720572057, "percentage": 6.03, "elapsed_time": "0:25:40", "remaining_time": "6:40:17", "throughput": 1500.78, "total_tokens": 2312416} {"current_steps": 10965, "total_steps": 181800, "loss": 0.1503, "lr": 3.0154015401540154e-05, "epoch": 1.2062706270627062, "percentage": 6.03, "elapsed_time": "0:25:41", "remaining_time": "6:40:16", "throughput": 1500.75, "total_tokens": 2313408} {"current_steps": 10970, "total_steps": 181800, "loss": 0.1558, "lr": 3.016776677667767e-05, "epoch": 1.2068206820682068, "percentage": 6.03, "elapsed_time": "0:25:42", "remaining_time": "6:40:15", "throughput": 1500.71, "total_tokens": 2314400} {"current_steps": 10975, "total_steps": 181800, "loss": 0.1192, "lr": 3.0181518151815187e-05, "epoch": 1.2073707370737075, "percentage": 6.04, "elapsed_time": "0:25:42", "remaining_time": "6:40:15", "throughput": 1500.7, "total_tokens": 2315424} {"current_steps": 10980, "total_steps": 181800, "loss": 0.1587, "lr": 3.0195269526952695e-05, "epoch": 1.2079207920792079, "percentage": 6.04, "elapsed_time": "0:25:43", "remaining_time": "6:40:14", "throughput": 1500.77, "total_tokens": 2316576} {"current_steps": 10985, "total_steps": 181800, "loss": 0.1606, "lr": 3.0209020902090214e-05, "epoch": 1.2084708470847085, "percentage": 6.04, "elapsed_time": "0:25:44", "remaining_time": "6:40:13", "throughput": 1500.8, "total_tokens": 2317664} {"current_steps": 10990, "total_steps": 181800, "loss": 0.1246, "lr": 3.0222772277227722e-05, "epoch": 1.209020902090209, "percentage": 6.05, "elapsed_time": "0:25:44", "remaining_time": "6:40:12", "throughput": 1500.79, "total_tokens": 2318688} {"current_steps": 10995, "total_steps": 181800, "loss": 0.1006, "lr": 3.023652365236524e-05, "epoch": 1.2095709570957096, "percentage": 6.05, "elapsed_time": "0:25:45", "remaining_time": "6:40:11", "throughput": 1500.82, "total_tokens": 2319776} {"current_steps": 11000, "total_steps": 181800, "loss": 0.2938, "lr": 3.025027502750275e-05, "epoch": 1.21012101210121, "percentage": 6.05, "elapsed_time": "0:25:46", "remaining_time": "6:40:10", "throughput": 1500.86, "total_tokens": 2320896} {"current_steps": 11005, "total_steps": 181800, "loss": 0.1637, "lr": 3.0264026402640267e-05, "epoch": 1.2106710671067107, "percentage": 6.05, "elapsed_time": "0:25:47", "remaining_time": "6:40:10", "throughput": 1500.91, "total_tokens": 2322016} {"current_steps": 11010, "total_steps": 181800, "loss": 0.1138, "lr": 3.0277777777777776e-05, "epoch": 1.2112211221122111, "percentage": 6.06, "elapsed_time": "0:25:47", "remaining_time": "6:40:09", "throughput": 1500.92, "total_tokens": 2323072} {"current_steps": 11015, "total_steps": 181800, "loss": 0.1686, "lr": 3.0291529152915294e-05, "epoch": 1.2117711771177118, "percentage": 6.06, "elapsed_time": "0:25:48", "remaining_time": "6:40:08", "throughput": 1500.91, "total_tokens": 2324096} {"current_steps": 11020, "total_steps": 181800, "loss": 0.1371, "lr": 3.0305280528052806e-05, "epoch": 1.2123212321232124, "percentage": 6.06, "elapsed_time": "0:25:49", "remaining_time": "6:40:07", "throughput": 1500.89, "total_tokens": 2325120} {"current_steps": 11025, "total_steps": 181800, "loss": 0.1086, "lr": 3.031903190319032e-05, "epoch": 1.2128712871287128, "percentage": 6.06, "elapsed_time": "0:25:49", "remaining_time": "6:40:06", "throughput": 1500.88, "total_tokens": 2326144} {"current_steps": 11030, "total_steps": 181800, "loss": 0.1489, "lr": 3.0332783278327836e-05, "epoch": 1.2134213421342135, "percentage": 6.07, "elapsed_time": "0:25:50", "remaining_time": "6:40:06", "throughput": 1500.95, "total_tokens": 2327296} {"current_steps": 11035, "total_steps": 181800, "loss": 0.1344, "lr": 3.0346534653465347e-05, "epoch": 1.213971397139714, "percentage": 6.07, "elapsed_time": "0:25:51", "remaining_time": "6:40:05", "throughput": 1500.97, "total_tokens": 2328384} {"current_steps": 11040, "total_steps": 181800, "loss": 0.2015, "lr": 3.0360286028602862e-05, "epoch": 1.2145214521452146, "percentage": 6.07, "elapsed_time": "0:25:51", "remaining_time": "6:40:04", "throughput": 1500.96, "total_tokens": 2329408} {"current_steps": 11045, "total_steps": 181800, "loss": 0.1002, "lr": 3.0374037403740374e-05, "epoch": 1.215071507150715, "percentage": 6.08, "elapsed_time": "0:25:52", "remaining_time": "6:40:03", "throughput": 1500.97, "total_tokens": 2330464} {"current_steps": 11050, "total_steps": 181800, "loss": 0.1376, "lr": 3.038778877887789e-05, "epoch": 1.2156215621562156, "percentage": 6.08, "elapsed_time": "0:25:53", "remaining_time": "6:40:02", "throughput": 1500.95, "total_tokens": 2331488} {"current_steps": 11055, "total_steps": 181800, "loss": 0.1531, "lr": 3.04015401540154e-05, "epoch": 1.216171617161716, "percentage": 6.08, "elapsed_time": "0:25:54", "remaining_time": "6:40:02", "throughput": 1501.0, "total_tokens": 2332608} {"current_steps": 11060, "total_steps": 181800, "loss": 0.1927, "lr": 3.0415291529152916e-05, "epoch": 1.2167216721672167, "percentage": 6.08, "elapsed_time": "0:25:54", "remaining_time": "6:40:01", "throughput": 1501.07, "total_tokens": 2333760} {"current_steps": 11065, "total_steps": 181800, "loss": 0.2436, "lr": 3.0429042904290427e-05, "epoch": 1.2172717271727174, "percentage": 6.09, "elapsed_time": "0:25:55", "remaining_time": "6:40:00", "throughput": 1501.06, "total_tokens": 2334784} {"current_steps": 11070, "total_steps": 181800, "loss": 0.11, "lr": 3.0442794279427942e-05, "epoch": 1.2178217821782178, "percentage": 6.09, "elapsed_time": "0:25:56", "remaining_time": "6:39:59", "throughput": 1501.04, "total_tokens": 2335808} {"current_steps": 11075, "total_steps": 181800, "loss": 0.1592, "lr": 3.045654565456546e-05, "epoch": 1.2183718371837184, "percentage": 6.09, "elapsed_time": "0:25:56", "remaining_time": "6:39:58", "throughput": 1501.05, "total_tokens": 2336864} {"current_steps": 11080, "total_steps": 181800, "loss": 0.1563, "lr": 3.0470297029702973e-05, "epoch": 1.2189218921892189, "percentage": 6.09, "elapsed_time": "0:25:57", "remaining_time": "6:39:58", "throughput": 1501.02, "total_tokens": 2337856} {"current_steps": 11085, "total_steps": 181800, "loss": 0.1315, "lr": 3.0484048404840488e-05, "epoch": 1.2194719471947195, "percentage": 6.1, "elapsed_time": "0:25:58", "remaining_time": "6:39:57", "throughput": 1501.03, "total_tokens": 2338912} {"current_steps": 11090, "total_steps": 181800, "loss": 0.1696, "lr": 3.0497799779978e-05, "epoch": 1.22002200220022, "percentage": 6.1, "elapsed_time": "0:25:58", "remaining_time": "6:39:56", "throughput": 1501.04, "total_tokens": 2339968} {"current_steps": 11095, "total_steps": 181800, "loss": 0.2069, "lr": 3.0511551155115514e-05, "epoch": 1.2205720572057206, "percentage": 6.1, "elapsed_time": "0:25:59", "remaining_time": "6:39:55", "throughput": 1501.09, "total_tokens": 2341120} {"current_steps": 11100, "total_steps": 181800, "loss": 0.0666, "lr": 3.052530253025302e-05, "epoch": 1.221122112211221, "percentage": 6.11, "elapsed_time": "0:26:00", "remaining_time": "6:39:55", "throughput": 1501.07, "total_tokens": 2342144} {"current_steps": 11105, "total_steps": 181800, "loss": 0.1248, "lr": 3.053905390539054e-05, "epoch": 1.2216721672167217, "percentage": 6.11, "elapsed_time": "0:26:01", "remaining_time": "6:39:54", "throughput": 1501.05, "total_tokens": 2343168} {"current_steps": 11110, "total_steps": 181800, "loss": 0.1288, "lr": 3.055280528052805e-05, "epoch": 1.2222222222222223, "percentage": 6.11, "elapsed_time": "0:26:01", "remaining_time": "6:39:53", "throughput": 1501.08, "total_tokens": 2344256} {"current_steps": 11115, "total_steps": 181800, "loss": 0.3287, "lr": 3.056655665566557e-05, "epoch": 1.2227722772277227, "percentage": 6.11, "elapsed_time": "0:26:02", "remaining_time": "6:39:52", "throughput": 1501.07, "total_tokens": 2345280} {"current_steps": 11120, "total_steps": 181800, "loss": 0.1318, "lr": 3.058030803080308e-05, "epoch": 1.2233223322332234, "percentage": 6.12, "elapsed_time": "0:26:03", "remaining_time": "6:39:51", "throughput": 1501.04, "total_tokens": 2346272} {"current_steps": 11125, "total_steps": 181800, "loss": 0.0764, "lr": 3.0594059405940594e-05, "epoch": 1.2238723872387238, "percentage": 6.12, "elapsed_time": "0:26:03", "remaining_time": "6:39:51", "throughput": 1501.03, "total_tokens": 2347296} {"current_steps": 11130, "total_steps": 181800, "loss": 0.1047, "lr": 3.060781078107811e-05, "epoch": 1.2244224422442245, "percentage": 6.12, "elapsed_time": "0:26:04", "remaining_time": "6:39:50", "throughput": 1501.04, "total_tokens": 2348352} {"current_steps": 11135, "total_steps": 181800, "loss": 0.192, "lr": 3.0621562156215624e-05, "epoch": 1.224972497249725, "percentage": 6.12, "elapsed_time": "0:26:05", "remaining_time": "6:39:49", "throughput": 1501.07, "total_tokens": 2349440} {"current_steps": 11140, "total_steps": 181800, "loss": 0.2605, "lr": 3.0635313531353136e-05, "epoch": 1.2255225522552256, "percentage": 6.13, "elapsed_time": "0:26:05", "remaining_time": "6:39:48", "throughput": 1501.12, "total_tokens": 2350560} {"current_steps": 11145, "total_steps": 181800, "loss": 0.237, "lr": 3.064906490649065e-05, "epoch": 1.226072607260726, "percentage": 6.13, "elapsed_time": "0:26:06", "remaining_time": "6:39:47", "throughput": 1501.12, "total_tokens": 2351616} {"current_steps": 11150, "total_steps": 181800, "loss": 0.1101, "lr": 3.0662816281628166e-05, "epoch": 1.2266226622662266, "percentage": 6.13, "elapsed_time": "0:26:07", "remaining_time": "6:39:46", "throughput": 1501.15, "total_tokens": 2352704} {"current_steps": 11155, "total_steps": 181800, "loss": 0.1032, "lr": 3.067656765676568e-05, "epoch": 1.2271727172717273, "percentage": 6.14, "elapsed_time": "0:26:07", "remaining_time": "6:39:45", "throughput": 1501.14, "total_tokens": 2353728} {"current_steps": 11160, "total_steps": 181800, "loss": 0.1316, "lr": 3.069031903190319e-05, "epoch": 1.2277227722772277, "percentage": 6.14, "elapsed_time": "0:26:08", "remaining_time": "6:39:45", "throughput": 1501.16, "total_tokens": 2354784} {"current_steps": 11165, "total_steps": 181800, "loss": 0.0913, "lr": 3.070407040704071e-05, "epoch": 1.2282728272827284, "percentage": 6.14, "elapsed_time": "0:26:09", "remaining_time": "6:39:44", "throughput": 1501.12, "total_tokens": 2355776} {"current_steps": 11170, "total_steps": 181800, "loss": 0.0858, "lr": 3.071782178217822e-05, "epoch": 1.2288228822882288, "percentage": 6.14, "elapsed_time": "0:26:10", "remaining_time": "6:39:43", "throughput": 1501.09, "total_tokens": 2356768} {"current_steps": 11175, "total_steps": 181800, "loss": 0.1105, "lr": 3.073157315731574e-05, "epoch": 1.2293729372937294, "percentage": 6.15, "elapsed_time": "0:26:10", "remaining_time": "6:39:42", "throughput": 1501.1, "total_tokens": 2357824} {"current_steps": 11180, "total_steps": 181800, "loss": 0.2521, "lr": 3.074532453245324e-05, "epoch": 1.2299229922992299, "percentage": 6.15, "elapsed_time": "0:26:11", "remaining_time": "6:39:41", "throughput": 1501.07, "total_tokens": 2358816} {"current_steps": 11185, "total_steps": 181800, "loss": 0.1233, "lr": 3.075907590759076e-05, "epoch": 1.2304730473047305, "percentage": 6.15, "elapsed_time": "0:26:12", "remaining_time": "6:39:40", "throughput": 1501.02, "total_tokens": 2359776} {"current_steps": 11190, "total_steps": 181800, "loss": 0.1235, "lr": 3.077282728272827e-05, "epoch": 1.231023102310231, "percentage": 6.16, "elapsed_time": "0:26:12", "remaining_time": "6:39:40", "throughput": 1501.05, "total_tokens": 2360864} {"current_steps": 11195, "total_steps": 181800, "loss": 0.1583, "lr": 3.078657865786579e-05, "epoch": 1.2315731573157316, "percentage": 6.16, "elapsed_time": "0:26:13", "remaining_time": "6:39:39", "throughput": 1501.1, "total_tokens": 2361984} {"current_steps": 11200, "total_steps": 181800, "loss": 0.149, "lr": 3.0800330033003296e-05, "epoch": 1.2321232123212322, "percentage": 6.16, "elapsed_time": "0:26:14", "remaining_time": "6:39:38", "throughput": 1501.15, "total_tokens": 2363104} {"current_steps": 11205, "total_steps": 181800, "loss": 0.2058, "lr": 3.0814081408140815e-05, "epoch": 1.2326732673267327, "percentage": 6.16, "elapsed_time": "0:26:14", "remaining_time": "6:39:37", "throughput": 1501.19, "total_tokens": 2364224} {"current_steps": 11210, "total_steps": 181800, "loss": 0.0879, "lr": 3.082783278327833e-05, "epoch": 1.2332233223322333, "percentage": 6.17, "elapsed_time": "0:26:15", "remaining_time": "6:39:36", "throughput": 1501.2, "total_tokens": 2365280} {"current_steps": 11215, "total_steps": 181800, "loss": 0.106, "lr": 3.0841584158415845e-05, "epoch": 1.2337733773377337, "percentage": 6.17, "elapsed_time": "0:26:16", "remaining_time": "6:39:36", "throughput": 1501.25, "total_tokens": 2366400} {"current_steps": 11220, "total_steps": 181800, "loss": 0.1499, "lr": 3.0855335533553357e-05, "epoch": 1.2343234323432344, "percentage": 6.17, "elapsed_time": "0:26:16", "remaining_time": "6:39:35", "throughput": 1501.26, "total_tokens": 2367456} {"current_steps": 11225, "total_steps": 181800, "loss": 0.1464, "lr": 3.086908690869087e-05, "epoch": 1.2348734873487348, "percentage": 6.17, "elapsed_time": "0:26:17", "remaining_time": "6:39:34", "throughput": 1501.33, "total_tokens": 2368608} {"current_steps": 11230, "total_steps": 181800, "loss": 0.165, "lr": 3.0882838283828387e-05, "epoch": 1.2354235423542355, "percentage": 6.18, "elapsed_time": "0:26:18", "remaining_time": "6:39:33", "throughput": 1501.32, "total_tokens": 2369632} {"current_steps": 11235, "total_steps": 181800, "loss": 0.1024, "lr": 3.08965896589659e-05, "epoch": 1.2359735973597359, "percentage": 6.18, "elapsed_time": "0:26:19", "remaining_time": "6:39:32", "throughput": 1501.34, "total_tokens": 2370720} {"current_steps": 11240, "total_steps": 181800, "loss": 0.0763, "lr": 3.091034103410341e-05, "epoch": 1.2365236523652365, "percentage": 6.18, "elapsed_time": "0:26:19", "remaining_time": "6:39:31", "throughput": 1501.33, "total_tokens": 2371744} {"current_steps": 11245, "total_steps": 181800, "loss": 0.2163, "lr": 3.092409240924092e-05, "epoch": 1.2370737073707372, "percentage": 6.19, "elapsed_time": "0:26:20", "remaining_time": "6:39:31", "throughput": 1501.32, "total_tokens": 2372768} {"current_steps": 11250, "total_steps": 181800, "loss": 0.1466, "lr": 3.093784378437844e-05, "epoch": 1.2376237623762376, "percentage": 6.19, "elapsed_time": "0:26:21", "remaining_time": "6:39:30", "throughput": 1501.3, "total_tokens": 2373792} {"current_steps": 11255, "total_steps": 181800, "loss": 0.1401, "lr": 3.095159515951595e-05, "epoch": 1.2381738173817383, "percentage": 6.19, "elapsed_time": "0:26:21", "remaining_time": "6:39:29", "throughput": 1501.31, "total_tokens": 2374848} {"current_steps": 11260, "total_steps": 181800, "loss": 0.1587, "lr": 3.096534653465346e-05, "epoch": 1.2387238723872387, "percentage": 6.19, "elapsed_time": "0:26:22", "remaining_time": "6:39:28", "throughput": 1501.3, "total_tokens": 2375872} {"current_steps": 11265, "total_steps": 181800, "loss": 0.118, "lr": 3.097909790979098e-05, "epoch": 1.2392739273927393, "percentage": 6.2, "elapsed_time": "0:26:23", "remaining_time": "6:39:27", "throughput": 1501.33, "total_tokens": 2376960} {"current_steps": 11270, "total_steps": 181800, "loss": 0.0869, "lr": 3.0992849284928493e-05, "epoch": 1.2398239823982398, "percentage": 6.2, "elapsed_time": "0:26:23", "remaining_time": "6:39:26", "throughput": 1501.34, "total_tokens": 2378016} {"current_steps": 11275, "total_steps": 181800, "loss": 0.1053, "lr": 3.100660066006601e-05, "epoch": 1.2403740374037404, "percentage": 6.2, "elapsed_time": "0:26:24", "remaining_time": "6:39:26", "throughput": 1501.37, "total_tokens": 2379104} {"current_steps": 11280, "total_steps": 181800, "loss": 0.0432, "lr": 3.1020352035203523e-05, "epoch": 1.2409240924092408, "percentage": 6.2, "elapsed_time": "0:26:25", "remaining_time": "6:39:25", "throughput": 1501.4, "total_tokens": 2380192} {"current_steps": 11285, "total_steps": 181800, "loss": 0.1017, "lr": 3.1034103410341035e-05, "epoch": 1.2414741474147415, "percentage": 6.21, "elapsed_time": "0:26:26", "remaining_time": "6:39:24", "throughput": 1501.39, "total_tokens": 2381216} {"current_steps": 11290, "total_steps": 181800, "loss": 0.1382, "lr": 3.104785478547855e-05, "epoch": 1.2420242024202421, "percentage": 6.21, "elapsed_time": "0:26:26", "remaining_time": "6:39:23", "throughput": 1501.42, "total_tokens": 2382304} {"current_steps": 11295, "total_steps": 181800, "loss": 0.1473, "lr": 3.1061606160616065e-05, "epoch": 1.2425742574257426, "percentage": 6.21, "elapsed_time": "0:26:27", "remaining_time": "6:39:22", "throughput": 1501.46, "total_tokens": 2383424} {"current_steps": 11300, "total_steps": 181800, "loss": 0.1049, "lr": 3.107535753575358e-05, "epoch": 1.2431243124312432, "percentage": 6.22, "elapsed_time": "0:26:28", "remaining_time": "6:39:21", "throughput": 1501.47, "total_tokens": 2384480} {"current_steps": 11305, "total_steps": 181800, "loss": 0.1443, "lr": 3.108910891089109e-05, "epoch": 1.2436743674367436, "percentage": 6.22, "elapsed_time": "0:26:28", "remaining_time": "6:39:21", "throughput": 1501.44, "total_tokens": 2385472} {"current_steps": 11310, "total_steps": 181800, "loss": 0.1382, "lr": 3.110286028602861e-05, "epoch": 1.2442244224422443, "percentage": 6.22, "elapsed_time": "0:26:29", "remaining_time": "6:39:20", "throughput": 1501.45, "total_tokens": 2386528} {"current_steps": 11315, "total_steps": 181800, "loss": 0.0959, "lr": 3.111661166116612e-05, "epoch": 1.2447744774477447, "percentage": 6.22, "elapsed_time": "0:26:30", "remaining_time": "6:39:19", "throughput": 1501.48, "total_tokens": 2387616} {"current_steps": 11320, "total_steps": 181800, "loss": 0.145, "lr": 3.113036303630363e-05, "epoch": 1.2453245324532454, "percentage": 6.23, "elapsed_time": "0:26:30", "remaining_time": "6:39:18", "throughput": 1501.44, "total_tokens": 2388608} {"current_steps": 11325, "total_steps": 181800, "loss": 0.0418, "lr": 3.114411441144114e-05, "epoch": 1.2458745874587458, "percentage": 6.23, "elapsed_time": "0:26:31", "remaining_time": "6:39:18", "throughput": 1501.44, "total_tokens": 2389664} {"current_steps": 11330, "total_steps": 181800, "loss": 0.0847, "lr": 3.115786578657866e-05, "epoch": 1.2464246424642464, "percentage": 6.23, "elapsed_time": "0:26:32", "remaining_time": "6:39:17", "throughput": 1501.4, "total_tokens": 2390656} {"current_steps": 11335, "total_steps": 181800, "loss": 0.2043, "lr": 3.117161716171617e-05, "epoch": 1.246974697469747, "percentage": 6.23, "elapsed_time": "0:26:32", "remaining_time": "6:39:16", "throughput": 1501.43, "total_tokens": 2391744} {"current_steps": 11340, "total_steps": 181800, "loss": 0.078, "lr": 3.118536853685369e-05, "epoch": 1.2475247524752475, "percentage": 6.24, "elapsed_time": "0:26:33", "remaining_time": "6:39:15", "throughput": 1501.44, "total_tokens": 2392800} {"current_steps": 11345, "total_steps": 181800, "loss": 0.1546, "lr": 3.1199119911991195e-05, "epoch": 1.2480748074807482, "percentage": 6.24, "elapsed_time": "0:26:34", "remaining_time": "6:39:14", "throughput": 1501.44, "total_tokens": 2393856} {"current_steps": 11350, "total_steps": 181800, "loss": 0.0736, "lr": 3.1212871287128714e-05, "epoch": 1.2486248624862486, "percentage": 6.24, "elapsed_time": "0:26:35", "remaining_time": "6:39:14", "throughput": 1501.47, "total_tokens": 2394944} {"current_steps": 11355, "total_steps": 181800, "loss": 0.1536, "lr": 3.122662266226623e-05, "epoch": 1.2491749174917492, "percentage": 6.25, "elapsed_time": "0:26:35", "remaining_time": "6:39:13", "throughput": 1501.45, "total_tokens": 2395968} {"current_steps": 11360, "total_steps": 181800, "loss": 0.0855, "lr": 3.1240374037403744e-05, "epoch": 1.2497249724972497, "percentage": 6.25, "elapsed_time": "0:26:36", "remaining_time": "6:39:12", "throughput": 1501.44, "total_tokens": 2396992} {"current_steps": 11365, "total_steps": 181800, "loss": 0.066, "lr": 3.1254125412541256e-05, "epoch": 1.2502750275027503, "percentage": 6.25, "elapsed_time": "0:26:37", "remaining_time": "6:39:11", "throughput": 1501.46, "total_tokens": 2398080} {"current_steps": 11370, "total_steps": 181800, "loss": 0.1397, "lr": 3.126787678767877e-05, "epoch": 1.2508250825082508, "percentage": 6.25, "elapsed_time": "0:26:37", "remaining_time": "6:39:10", "throughput": 1501.51, "total_tokens": 2399200} {"current_steps": 11375, "total_steps": 181800, "loss": 0.1416, "lr": 3.1281628162816286e-05, "epoch": 1.2513751375137514, "percentage": 6.26, "elapsed_time": "0:26:38", "remaining_time": "6:39:10", "throughput": 1501.5, "total_tokens": 2400224} {"current_steps": 11380, "total_steps": 181800, "loss": 0.0871, "lr": 3.12953795379538e-05, "epoch": 1.251925192519252, "percentage": 6.26, "elapsed_time": "0:26:39", "remaining_time": "6:39:09", "throughput": 1501.47, "total_tokens": 2401216} {"current_steps": 11385, "total_steps": 181800, "loss": 0.1569, "lr": 3.130913091309131e-05, "epoch": 1.2524752475247525, "percentage": 6.26, "elapsed_time": "0:26:39", "remaining_time": "6:39:08", "throughput": 1501.47, "total_tokens": 2402240} {"current_steps": 11390, "total_steps": 181800, "loss": 0.1231, "lr": 3.132288228822882e-05, "epoch": 1.253025302530253, "percentage": 6.27, "elapsed_time": "0:26:40", "remaining_time": "6:39:07", "throughput": 1501.54, "total_tokens": 2403392} {"current_steps": 11395, "total_steps": 181800, "loss": 0.1828, "lr": 3.133663366336634e-05, "epoch": 1.2535753575357536, "percentage": 6.27, "elapsed_time": "0:26:41", "remaining_time": "6:39:06", "throughput": 1501.56, "total_tokens": 2404480} {"current_steps": 11400, "total_steps": 181800, "loss": 0.1157, "lr": 3.135038503850386e-05, "epoch": 1.2541254125412542, "percentage": 6.27, "elapsed_time": "0:26:42", "remaining_time": "6:39:06", "throughput": 1501.58, "total_tokens": 2405568} {"current_steps": 11405, "total_steps": 181800, "loss": 0.1473, "lr": 3.136413641364136e-05, "epoch": 1.2546754675467546, "percentage": 6.27, "elapsed_time": "0:26:42", "remaining_time": "6:39:05", "throughput": 1501.63, "total_tokens": 2406688} {"current_steps": 11410, "total_steps": 181800, "loss": 0.1068, "lr": 3.137788778877888e-05, "epoch": 1.2552255225522553, "percentage": 6.28, "elapsed_time": "0:26:43", "remaining_time": "6:39:04", "throughput": 1501.63, "total_tokens": 2407744} {"current_steps": 11415, "total_steps": 181800, "loss": 0.1511, "lr": 3.139163916391639e-05, "epoch": 1.2557755775577557, "percentage": 6.28, "elapsed_time": "0:26:44", "remaining_time": "6:39:03", "throughput": 1501.64, "total_tokens": 2408800} {"current_steps": 11420, "total_steps": 181800, "loss": 0.1255, "lr": 3.140539053905391e-05, "epoch": 1.2563256325632564, "percentage": 6.28, "elapsed_time": "0:26:44", "remaining_time": "6:39:02", "throughput": 1501.66, "total_tokens": 2409888} {"current_steps": 11425, "total_steps": 181800, "loss": 0.0921, "lr": 3.1419141914191416e-05, "epoch": 1.256875687568757, "percentage": 6.28, "elapsed_time": "0:26:45", "remaining_time": "6:39:02", "throughput": 1501.67, "total_tokens": 2410944} {"current_steps": 11430, "total_steps": 181800, "loss": 0.1161, "lr": 3.1432893289328934e-05, "epoch": 1.2574257425742574, "percentage": 6.29, "elapsed_time": "0:26:46", "remaining_time": "6:39:01", "throughput": 1501.67, "total_tokens": 2412000} {"current_steps": 11435, "total_steps": 181800, "loss": 0.2658, "lr": 3.1446644664466446e-05, "epoch": 1.2579757975797579, "percentage": 6.29, "elapsed_time": "0:26:46", "remaining_time": "6:39:00", "throughput": 1501.66, "total_tokens": 2413024} {"current_steps": 11440, "total_steps": 181800, "loss": 0.1978, "lr": 3.1460396039603964e-05, "epoch": 1.2585258525852585, "percentage": 6.29, "elapsed_time": "0:26:47", "remaining_time": "6:38:59", "throughput": 1501.71, "total_tokens": 2414144} {"current_steps": 11445, "total_steps": 181800, "loss": 0.1473, "lr": 3.1474147414741476e-05, "epoch": 1.2590759075907592, "percentage": 6.3, "elapsed_time": "0:26:48", "remaining_time": "6:38:58", "throughput": 1501.7, "total_tokens": 2415168} {"current_steps": 11450, "total_steps": 181800, "loss": 0.1196, "lr": 3.148789878987899e-05, "epoch": 1.2596259625962596, "percentage": 6.3, "elapsed_time": "0:26:48", "remaining_time": "6:38:58", "throughput": 1501.73, "total_tokens": 2416256} {"current_steps": 11455, "total_steps": 181800, "loss": 0.1354, "lr": 3.1501650165016506e-05, "epoch": 1.2601760176017602, "percentage": 6.3, "elapsed_time": "0:26:49", "remaining_time": "6:38:57", "throughput": 1501.72, "total_tokens": 2417280} {"current_steps": 11460, "total_steps": 181800, "loss": 0.1432, "lr": 3.151540154015402e-05, "epoch": 1.2607260726072607, "percentage": 6.3, "elapsed_time": "0:26:50", "remaining_time": "6:38:56", "throughput": 1501.71, "total_tokens": 2418304} {"current_steps": 11465, "total_steps": 181800, "loss": 0.0807, "lr": 3.152915291529153e-05, "epoch": 1.2612761276127613, "percentage": 6.31, "elapsed_time": "0:26:51", "remaining_time": "6:38:55", "throughput": 1501.69, "total_tokens": 2419328} {"current_steps": 11470, "total_steps": 181800, "loss": 0.0605, "lr": 3.154290429042904e-05, "epoch": 1.261826182618262, "percentage": 6.31, "elapsed_time": "0:26:51", "remaining_time": "6:38:54", "throughput": 1501.7, "total_tokens": 2420384} {"current_steps": 11475, "total_steps": 181800, "loss": 0.0835, "lr": 3.155665566556656e-05, "epoch": 1.2623762376237624, "percentage": 6.31, "elapsed_time": "0:26:52", "remaining_time": "6:38:53", "throughput": 1501.71, "total_tokens": 2421440} {"current_steps": 11480, "total_steps": 181800, "loss": 0.1775, "lr": 3.157040704070407e-05, "epoch": 1.2629262926292628, "percentage": 6.31, "elapsed_time": "0:26:53", "remaining_time": "6:38:53", "throughput": 1501.7, "total_tokens": 2422464} {"current_steps": 11485, "total_steps": 181800, "loss": 0.0957, "lr": 3.158415841584158e-05, "epoch": 1.2634763476347635, "percentage": 6.32, "elapsed_time": "0:26:53", "remaining_time": "6:38:52", "throughput": 1501.7, "total_tokens": 2423520} {"current_steps": 11490, "total_steps": 181800, "loss": 0.1352, "lr": 3.1597909790979094e-05, "epoch": 1.2640264026402641, "percentage": 6.32, "elapsed_time": "0:26:54", "remaining_time": "6:38:51", "throughput": 1501.77, "total_tokens": 2424672} {"current_steps": 11495, "total_steps": 181800, "loss": 0.1318, "lr": 3.161166116611661e-05, "epoch": 1.2645764576457645, "percentage": 6.32, "elapsed_time": "0:26:55", "remaining_time": "6:38:50", "throughput": 1501.76, "total_tokens": 2425696} {"current_steps": 11500, "total_steps": 181800, "loss": 0.1442, "lr": 3.162541254125413e-05, "epoch": 1.2651265126512652, "percentage": 6.33, "elapsed_time": "0:26:55", "remaining_time": "6:38:49", "throughput": 1501.71, "total_tokens": 2426656} {"current_steps": 11505, "total_steps": 181800, "loss": 0.0918, "lr": 3.163916391639164e-05, "epoch": 1.2656765676567656, "percentage": 6.33, "elapsed_time": "0:26:56", "remaining_time": "6:38:48", "throughput": 1501.76, "total_tokens": 2427776} {"current_steps": 11510, "total_steps": 181800, "loss": 0.0398, "lr": 3.1652915291529154e-05, "epoch": 1.2662266226622663, "percentage": 6.33, "elapsed_time": "0:26:57", "remaining_time": "6:38:48", "throughput": 1501.77, "total_tokens": 2428832} {"current_steps": 11515, "total_steps": 181800, "loss": 0.1654, "lr": 3.1666666666666666e-05, "epoch": 1.266776677667767, "percentage": 6.33, "elapsed_time": "0:26:58", "remaining_time": "6:38:47", "throughput": 1501.78, "total_tokens": 2429888} {"current_steps": 11520, "total_steps": 181800, "loss": 0.243, "lr": 3.1680418041804185e-05, "epoch": 1.2673267326732673, "percentage": 6.34, "elapsed_time": "0:26:58", "remaining_time": "6:38:46", "throughput": 1501.81, "total_tokens": 2430976} {"current_steps": 11525, "total_steps": 181800, "loss": 0.19, "lr": 3.1694169416941696e-05, "epoch": 1.2678767876787678, "percentage": 6.34, "elapsed_time": "0:26:59", "remaining_time": "6:38:45", "throughput": 1501.82, "total_tokens": 2432032} {"current_steps": 11530, "total_steps": 181800, "loss": 0.086, "lr": 3.170792079207921e-05, "epoch": 1.2684268426842684, "percentage": 6.34, "elapsed_time": "0:27:00", "remaining_time": "6:38:44", "throughput": 1501.85, "total_tokens": 2433120} {"current_steps": 11535, "total_steps": 181800, "loss": 0.0658, "lr": 3.172167216721672e-05, "epoch": 1.268976897689769, "percentage": 6.34, "elapsed_time": "0:27:00", "remaining_time": "6:38:43", "throughput": 1501.89, "total_tokens": 2434240} {"current_steps": 11540, "total_steps": 181800, "loss": 0.0875, "lr": 3.173542354235424e-05, "epoch": 1.2695269526952695, "percentage": 6.35, "elapsed_time": "0:27:01", "remaining_time": "6:38:43", "throughput": 1501.9, "total_tokens": 2435296} {"current_steps": 11545, "total_steps": 181800, "loss": 0.1147, "lr": 3.174917491749175e-05, "epoch": 1.2700770077007701, "percentage": 6.35, "elapsed_time": "0:27:02", "remaining_time": "6:38:42", "throughput": 1501.93, "total_tokens": 2436384} {"current_steps": 11550, "total_steps": 181800, "loss": 0.0591, "lr": 3.176292629262926e-05, "epoch": 1.2706270627062706, "percentage": 6.35, "elapsed_time": "0:27:02", "remaining_time": "6:38:41", "throughput": 1501.91, "total_tokens": 2437408} {"current_steps": 11555, "total_steps": 181800, "loss": 0.0593, "lr": 3.177667766776678e-05, "epoch": 1.2711771177117712, "percentage": 6.36, "elapsed_time": "0:27:03", "remaining_time": "6:38:40", "throughput": 1501.92, "total_tokens": 2438464} {"current_steps": 11560, "total_steps": 181800, "loss": 0.1646, "lr": 3.179042904290429e-05, "epoch": 1.2717271727172716, "percentage": 6.36, "elapsed_time": "0:27:04", "remaining_time": "6:38:39", "throughput": 1501.9, "total_tokens": 2439488} {"current_steps": 11565, "total_steps": 181800, "loss": 0.1821, "lr": 3.180418041804181e-05, "epoch": 1.2722772277227723, "percentage": 6.36, "elapsed_time": "0:27:04", "remaining_time": "6:38:39", "throughput": 1501.91, "total_tokens": 2440544} {"current_steps": 11570, "total_steps": 181800, "loss": 0.1753, "lr": 3.1817931793179315e-05, "epoch": 1.2728272827282727, "percentage": 6.36, "elapsed_time": "0:27:05", "remaining_time": "6:38:38", "throughput": 1501.91, "total_tokens": 2441600} {"current_steps": 11575, "total_steps": 181800, "loss": 0.1107, "lr": 3.183168316831683e-05, "epoch": 1.2733773377337734, "percentage": 6.37, "elapsed_time": "0:27:06", "remaining_time": "6:38:37", "throughput": 1501.92, "total_tokens": 2442656} {"current_steps": 11580, "total_steps": 181800, "loss": 0.1464, "lr": 3.1845434543454345e-05, "epoch": 1.273927392739274, "percentage": 6.37, "elapsed_time": "0:27:07", "remaining_time": "6:38:36", "throughput": 1501.91, "total_tokens": 2443680} {"current_steps": 11585, "total_steps": 181800, "loss": 0.0851, "lr": 3.185918591859186e-05, "epoch": 1.2744774477447744, "percentage": 6.37, "elapsed_time": "0:27:07", "remaining_time": "6:38:36", "throughput": 1501.91, "total_tokens": 2444736} {"current_steps": 11590, "total_steps": 181800, "loss": 0.2091, "lr": 3.1872937293729375e-05, "epoch": 1.275027502750275, "percentage": 6.38, "elapsed_time": "0:27:08", "remaining_time": "6:38:35", "throughput": 1501.94, "total_tokens": 2445824} {"current_steps": 11595, "total_steps": 181800, "loss": 0.0661, "lr": 3.1886688668866887e-05, "epoch": 1.2755775577557755, "percentage": 6.38, "elapsed_time": "0:27:09", "remaining_time": "6:38:34", "throughput": 1501.91, "total_tokens": 2446816} {"current_steps": 11600, "total_steps": 181800, "loss": 0.1152, "lr": 3.1900440044004405e-05, "epoch": 1.2761276127612762, "percentage": 6.38, "elapsed_time": "0:27:09", "remaining_time": "6:38:33", "throughput": 1501.93, "total_tokens": 2447904} {"current_steps": 11605, "total_steps": 181800, "loss": 0.1476, "lr": 3.1914191419141917e-05, "epoch": 1.2766776677667766, "percentage": 6.38, "elapsed_time": "0:27:10", "remaining_time": "6:38:32", "throughput": 1501.94, "total_tokens": 2448960} {"current_steps": 11610, "total_steps": 181800, "loss": 0.1942, "lr": 3.192794279427943e-05, "epoch": 1.2772277227722773, "percentage": 6.39, "elapsed_time": "0:27:11", "remaining_time": "6:38:31", "throughput": 1501.95, "total_tokens": 2450016} {"current_steps": 11615, "total_steps": 181800, "loss": 0.1212, "lr": 3.194169416941694e-05, "epoch": 1.2777777777777777, "percentage": 6.39, "elapsed_time": "0:27:11", "remaining_time": "6:38:31", "throughput": 1501.96, "total_tokens": 2451072} {"current_steps": 11620, "total_steps": 181800, "loss": 0.1887, "lr": 3.195544554455446e-05, "epoch": 1.2783278327832783, "percentage": 6.39, "elapsed_time": "0:27:12", "remaining_time": "6:38:30", "throughput": 1501.97, "total_tokens": 2452128} {"current_steps": 11625, "total_steps": 181800, "loss": 0.1341, "lr": 3.196919691969197e-05, "epoch": 1.278877887788779, "percentage": 6.39, "elapsed_time": "0:27:13", "remaining_time": "6:38:29", "throughput": 1502.0, "total_tokens": 2453216} {"current_steps": 11630, "total_steps": 181800, "loss": 0.0838, "lr": 3.198294829482948e-05, "epoch": 1.2794279427942794, "percentage": 6.4, "elapsed_time": "0:27:13", "remaining_time": "6:38:28", "throughput": 1502.03, "total_tokens": 2454304} {"current_steps": 11635, "total_steps": 181800, "loss": 0.0938, "lr": 3.1996699669967e-05, "epoch": 1.27997799779978, "percentage": 6.4, "elapsed_time": "0:27:14", "remaining_time": "6:38:28", "throughput": 1501.99, "total_tokens": 2455392} {"current_steps": 11640, "total_steps": 181800, "loss": 0.1085, "lr": 3.201045104510451e-05, "epoch": 1.2805280528052805, "percentage": 6.4, "elapsed_time": "0:27:15", "remaining_time": "6:38:27", "throughput": 1502.04, "total_tokens": 2456512} {"current_steps": 11645, "total_steps": 181800, "loss": 0.1425, "lr": 3.202420242024203e-05, "epoch": 1.2810781078107811, "percentage": 6.41, "elapsed_time": "0:27:16", "remaining_time": "6:38:27", "throughput": 1502.01, "total_tokens": 2457504} {"current_steps": 11650, "total_steps": 181800, "loss": 0.1287, "lr": 3.2037953795379535e-05, "epoch": 1.2816281628162816, "percentage": 6.41, "elapsed_time": "0:27:16", "remaining_time": "6:38:26", "throughput": 1502.02, "total_tokens": 2458592} {"current_steps": 11655, "total_steps": 181800, "loss": 0.0944, "lr": 3.2051705170517053e-05, "epoch": 1.2821782178217822, "percentage": 6.41, "elapsed_time": "0:27:17", "remaining_time": "6:38:25", "throughput": 1502.01, "total_tokens": 2459616} {"current_steps": 11660, "total_steps": 181800, "loss": 0.1404, "lr": 3.2065456545654565e-05, "epoch": 1.2827282728272826, "percentage": 6.41, "elapsed_time": "0:27:18", "remaining_time": "6:38:24", "throughput": 1502.04, "total_tokens": 2460704} {"current_steps": 11665, "total_steps": 181800, "loss": 0.1363, "lr": 3.2079207920792084e-05, "epoch": 1.2832783278327833, "percentage": 6.42, "elapsed_time": "0:27:18", "remaining_time": "6:38:23", "throughput": 1502.06, "total_tokens": 2461760} {"current_steps": 11670, "total_steps": 181800, "loss": 0.1605, "lr": 3.2092959295929595e-05, "epoch": 1.283828382838284, "percentage": 6.42, "elapsed_time": "0:27:19", "remaining_time": "6:38:22", "throughput": 1502.07, "total_tokens": 2462816} {"current_steps": 11675, "total_steps": 181800, "loss": 0.0754, "lr": 3.210671067106711e-05, "epoch": 1.2843784378437844, "percentage": 6.42, "elapsed_time": "0:27:20", "remaining_time": "6:38:21", "throughput": 1502.13, "total_tokens": 2463936} {"current_steps": 11680, "total_steps": 181800, "loss": 0.1045, "lr": 3.2120462046204625e-05, "epoch": 1.284928492849285, "percentage": 6.42, "elapsed_time": "0:27:20", "remaining_time": "6:38:21", "throughput": 1502.1, "total_tokens": 2464928} {"current_steps": 11685, "total_steps": 181800, "loss": 0.1292, "lr": 3.213421342134214e-05, "epoch": 1.2854785478547854, "percentage": 6.43, "elapsed_time": "0:27:21", "remaining_time": "6:38:20", "throughput": 1502.13, "total_tokens": 2466016} {"current_steps": 11690, "total_steps": 181800, "loss": 0.0814, "lr": 3.214796479647965e-05, "epoch": 1.286028602860286, "percentage": 6.43, "elapsed_time": "0:27:22", "remaining_time": "6:38:19", "throughput": 1502.2, "total_tokens": 2467168} {"current_steps": 11695, "total_steps": 181800, "loss": 0.1535, "lr": 3.216171617161716e-05, "epoch": 1.2865786578657865, "percentage": 6.43, "elapsed_time": "0:27:23", "remaining_time": "6:38:18", "throughput": 1502.19, "total_tokens": 2468192} {"current_steps": 11700, "total_steps": 181800, "loss": 0.0981, "lr": 3.217546754675468e-05, "epoch": 1.2871287128712872, "percentage": 6.44, "elapsed_time": "0:27:23", "remaining_time": "6:38:17", "throughput": 1502.2, "total_tokens": 2469248} {"current_steps": 11705, "total_steps": 181800, "loss": 0.1011, "lr": 3.218921892189219e-05, "epoch": 1.2876787678767876, "percentage": 6.44, "elapsed_time": "0:27:24", "remaining_time": "6:38:16", "throughput": 1502.2, "total_tokens": 2470272} {"current_steps": 11710, "total_steps": 181800, "loss": 0.0501, "lr": 3.22029702970297e-05, "epoch": 1.2882288228822882, "percentage": 6.44, "elapsed_time": "0:27:25", "remaining_time": "6:38:15", "throughput": 1502.17, "total_tokens": 2471264} {"current_steps": 11715, "total_steps": 181800, "loss": 0.1245, "lr": 3.2216721672167214e-05, "epoch": 1.2887788778877889, "percentage": 6.44, "elapsed_time": "0:27:25", "remaining_time": "6:38:14", "throughput": 1502.22, "total_tokens": 2472384} {"current_steps": 11720, "total_steps": 181800, "loss": 0.2227, "lr": 3.223047304730473e-05, "epoch": 1.2893289328932893, "percentage": 6.45, "elapsed_time": "0:27:26", "remaining_time": "6:38:14", "throughput": 1502.25, "total_tokens": 2473472} {"current_steps": 11725, "total_steps": 181800, "loss": 0.0872, "lr": 3.224422442244225e-05, "epoch": 1.2898789878987897, "percentage": 6.45, "elapsed_time": "0:27:27", "remaining_time": "6:38:13", "throughput": 1502.29, "total_tokens": 2474560} {"current_steps": 11730, "total_steps": 181800, "loss": 0.1204, "lr": 3.225797579757976e-05, "epoch": 1.2904290429042904, "percentage": 6.45, "elapsed_time": "0:27:27", "remaining_time": "6:38:12", "throughput": 1502.3, "total_tokens": 2475616} {"current_steps": 11735, "total_steps": 181800, "loss": 0.0564, "lr": 3.2271727172717274e-05, "epoch": 1.290979097909791, "percentage": 6.45, "elapsed_time": "0:27:28", "remaining_time": "6:38:11", "throughput": 1502.27, "total_tokens": 2476608} {"current_steps": 11740, "total_steps": 181800, "loss": 0.1617, "lr": 3.2285478547854786e-05, "epoch": 1.2915291529152915, "percentage": 6.46, "elapsed_time": "0:27:29", "remaining_time": "6:38:10", "throughput": 1502.29, "total_tokens": 2477664} {"current_steps": 11745, "total_steps": 181800, "loss": 0.0784, "lr": 3.2299229922992304e-05, "epoch": 1.2920792079207921, "percentage": 6.46, "elapsed_time": "0:27:29", "remaining_time": "6:38:09", "throughput": 1502.3, "total_tokens": 2478720} {"current_steps": 11750, "total_steps": 181800, "loss": 0.1089, "lr": 3.2312981298129816e-05, "epoch": 1.2926292629262925, "percentage": 6.46, "elapsed_time": "0:27:30", "remaining_time": "6:38:08", "throughput": 1502.31, "total_tokens": 2479776} {"current_steps": 11755, "total_steps": 181800, "loss": 0.1937, "lr": 3.232673267326733e-05, "epoch": 1.2931793179317932, "percentage": 6.47, "elapsed_time": "0:27:31", "remaining_time": "6:38:07", "throughput": 1502.3, "total_tokens": 2480800} {"current_steps": 11760, "total_steps": 181800, "loss": 0.2332, "lr": 3.234048404840484e-05, "epoch": 1.2937293729372938, "percentage": 6.47, "elapsed_time": "0:27:32", "remaining_time": "6:38:06", "throughput": 1502.29, "total_tokens": 2481824} {"current_steps": 11765, "total_steps": 181800, "loss": 0.0538, "lr": 3.235423542354236e-05, "epoch": 1.2942794279427943, "percentage": 6.47, "elapsed_time": "0:27:32", "remaining_time": "6:38:06", "throughput": 1502.33, "total_tokens": 2482912} {"current_steps": 11770, "total_steps": 181800, "loss": 0.1358, "lr": 3.236798679867987e-05, "epoch": 1.2948294829482947, "percentage": 6.47, "elapsed_time": "0:27:33", "remaining_time": "6:38:05", "throughput": 1502.3, "total_tokens": 2483904} {"current_steps": 11775, "total_steps": 181800, "loss": 0.122, "lr": 3.238173817381738e-05, "epoch": 1.2953795379537953, "percentage": 6.48, "elapsed_time": "0:27:34", "remaining_time": "6:38:04", "throughput": 1502.29, "total_tokens": 2484928} {"current_steps": 11780, "total_steps": 181800, "loss": 0.1639, "lr": 3.23954895489549e-05, "epoch": 1.295929592959296, "percentage": 6.48, "elapsed_time": "0:27:34", "remaining_time": "6:38:03", "throughput": 1502.37, "total_tokens": 2486080} {"current_steps": 11785, "total_steps": 181800, "loss": 0.1389, "lr": 3.240924092409241e-05, "epoch": 1.2964796479647964, "percentage": 6.48, "elapsed_time": "0:27:35", "remaining_time": "6:38:02", "throughput": 1502.36, "total_tokens": 2487104} {"current_steps": 11790, "total_steps": 181800, "loss": 0.0944, "lr": 3.242299229922993e-05, "epoch": 1.297029702970297, "percentage": 6.49, "elapsed_time": "0:27:36", "remaining_time": "6:38:01", "throughput": 1502.35, "total_tokens": 2488128} {"current_steps": 11795, "total_steps": 181800, "loss": 0.1295, "lr": 3.2436743674367434e-05, "epoch": 1.2975797579757975, "percentage": 6.49, "elapsed_time": "0:27:36", "remaining_time": "6:38:00", "throughput": 1502.37, "total_tokens": 2489184} {"current_steps": 11800, "total_steps": 181800, "loss": 0.1237, "lr": 3.245049504950495e-05, "epoch": 1.2981298129812981, "percentage": 6.49, "elapsed_time": "0:27:37", "remaining_time": "6:37:59", "throughput": 1502.44, "total_tokens": 2490336} {"current_steps": 11805, "total_steps": 181800, "loss": 0.2201, "lr": 3.2464246424642464e-05, "epoch": 1.2986798679867988, "percentage": 6.49, "elapsed_time": "0:27:38", "remaining_time": "6:37:58", "throughput": 1502.52, "total_tokens": 2491488} {"current_steps": 11810, "total_steps": 181800, "loss": 0.165, "lr": 3.247799779977998e-05, "epoch": 1.2992299229922992, "percentage": 6.5, "elapsed_time": "0:27:38", "remaining_time": "6:37:57", "throughput": 1502.49, "total_tokens": 2492480} {"current_steps": 11815, "total_steps": 181800, "loss": 0.1169, "lr": 3.249174917491749e-05, "epoch": 1.2997799779977997, "percentage": 6.5, "elapsed_time": "0:27:39", "remaining_time": "6:37:56", "throughput": 1502.53, "total_tokens": 2493568} {"current_steps": 11820, "total_steps": 181800, "loss": 0.2354, "lr": 3.2505500550055006e-05, "epoch": 1.3003300330033003, "percentage": 6.5, "elapsed_time": "0:27:40", "remaining_time": "6:37:55", "throughput": 1502.56, "total_tokens": 2494656} {"current_steps": 11825, "total_steps": 181800, "loss": 0.2152, "lr": 3.2519251925192524e-05, "epoch": 1.300880088008801, "percentage": 6.5, "elapsed_time": "0:27:40", "remaining_time": "6:37:54", "throughput": 1502.56, "total_tokens": 2495680} {"current_steps": 11830, "total_steps": 181800, "loss": 0.1176, "lr": 3.2533003300330036e-05, "epoch": 1.3014301430143014, "percentage": 6.51, "elapsed_time": "0:27:41", "remaining_time": "6:37:53", "throughput": 1502.56, "total_tokens": 2496704} {"current_steps": 11835, "total_steps": 181800, "loss": 0.1235, "lr": 3.254675467546755e-05, "epoch": 1.301980198019802, "percentage": 6.51, "elapsed_time": "0:27:42", "remaining_time": "6:37:53", "throughput": 1502.61, "total_tokens": 2497824} {"current_steps": 11840, "total_steps": 181800, "loss": 0.0427, "lr": 3.256050605060506e-05, "epoch": 1.3025302530253025, "percentage": 6.51, "elapsed_time": "0:27:43", "remaining_time": "6:37:52", "throughput": 1502.64, "total_tokens": 2498912} {"current_steps": 11845, "total_steps": 181800, "loss": 0.1156, "lr": 3.257425742574258e-05, "epoch": 1.303080308030803, "percentage": 6.52, "elapsed_time": "0:27:43", "remaining_time": "6:37:51", "throughput": 1502.69, "total_tokens": 2500032} {"current_steps": 11850, "total_steps": 181800, "loss": 0.1877, "lr": 3.258800880088009e-05, "epoch": 1.3036303630363038, "percentage": 6.52, "elapsed_time": "0:27:44", "remaining_time": "6:37:50", "throughput": 1502.71, "total_tokens": 2501088} {"current_steps": 11855, "total_steps": 181800, "loss": 0.1436, "lr": 3.26017601760176e-05, "epoch": 1.3041804180418042, "percentage": 6.52, "elapsed_time": "0:27:45", "remaining_time": "6:37:49", "throughput": 1502.72, "total_tokens": 2502144} {"current_steps": 11860, "total_steps": 181800, "loss": 0.0741, "lr": 3.261551155115511e-05, "epoch": 1.3047304730473046, "percentage": 6.52, "elapsed_time": "0:27:45", "remaining_time": "6:37:48", "throughput": 1502.7, "total_tokens": 2503168} {"current_steps": 11865, "total_steps": 181800, "loss": 0.19, "lr": 3.262926292629263e-05, "epoch": 1.3052805280528053, "percentage": 6.53, "elapsed_time": "0:27:46", "remaining_time": "6:37:47", "throughput": 1502.7, "total_tokens": 2504192} {"current_steps": 11870, "total_steps": 181800, "loss": 0.0797, "lr": 3.264301430143015e-05, "epoch": 1.305830583058306, "percentage": 6.53, "elapsed_time": "0:27:47", "remaining_time": "6:37:46", "throughput": 1502.69, "total_tokens": 2505216} {"current_steps": 11875, "total_steps": 181800, "loss": 0.1429, "lr": 3.2656765676567654e-05, "epoch": 1.3063806380638063, "percentage": 6.53, "elapsed_time": "0:27:47", "remaining_time": "6:37:45", "throughput": 1502.7, "total_tokens": 2506272} {"current_steps": 11880, "total_steps": 181800, "loss": 0.0559, "lr": 3.267051705170517e-05, "epoch": 1.306930693069307, "percentage": 6.53, "elapsed_time": "0:27:48", "remaining_time": "6:37:45", "throughput": 1502.74, "total_tokens": 2507360} {"current_steps": 11885, "total_steps": 181800, "loss": 0.1817, "lr": 3.2684268426842685e-05, "epoch": 1.3074807480748074, "percentage": 6.54, "elapsed_time": "0:27:49", "remaining_time": "6:37:44", "throughput": 1502.75, "total_tokens": 2508416} {"current_steps": 11890, "total_steps": 181800, "loss": 0.0615, "lr": 3.26980198019802e-05, "epoch": 1.308030803080308, "percentage": 6.54, "elapsed_time": "0:27:49", "remaining_time": "6:37:43", "throughput": 1502.74, "total_tokens": 2509440} {"current_steps": 11895, "total_steps": 181800, "loss": 0.1059, "lr": 3.2711771177117715e-05, "epoch": 1.3085808580858087, "percentage": 6.54, "elapsed_time": "0:27:50", "remaining_time": "6:37:42", "throughput": 1502.76, "total_tokens": 2510496} {"current_steps": 11900, "total_steps": 181800, "loss": 0.0749, "lr": 3.2725522552255226e-05, "epoch": 1.3091309130913091, "percentage": 6.55, "elapsed_time": "0:27:51", "remaining_time": "6:37:41", "throughput": 1502.73, "total_tokens": 2511488} {"current_steps": 11905, "total_steps": 181800, "loss": 0.0674, "lr": 3.273927392739274e-05, "epoch": 1.3096809680968096, "percentage": 6.55, "elapsed_time": "0:27:51", "remaining_time": "6:37:40", "throughput": 1502.75, "total_tokens": 2512544} {"current_steps": 11910, "total_steps": 181800, "loss": 0.1395, "lr": 3.2753025302530256e-05, "epoch": 1.3102310231023102, "percentage": 6.55, "elapsed_time": "0:27:52", "remaining_time": "6:37:39", "throughput": 1502.76, "total_tokens": 2513600} {"current_steps": 11915, "total_steps": 181800, "loss": 0.2117, "lr": 3.276677667766777e-05, "epoch": 1.3107810781078109, "percentage": 6.55, "elapsed_time": "0:27:53", "remaining_time": "6:37:38", "throughput": 1502.75, "total_tokens": 2514624} {"current_steps": 11920, "total_steps": 181800, "loss": 0.0757, "lr": 3.278052805280528e-05, "epoch": 1.3113311331133113, "percentage": 6.56, "elapsed_time": "0:27:54", "remaining_time": "6:37:37", "throughput": 1502.78, "total_tokens": 2515712} {"current_steps": 11925, "total_steps": 181800, "loss": 0.1244, "lr": 3.27942794279428e-05, "epoch": 1.311881188118812, "percentage": 6.56, "elapsed_time": "0:27:54", "remaining_time": "6:37:37", "throughput": 1502.79, "total_tokens": 2516768} {"current_steps": 11930, "total_steps": 181800, "loss": 0.1736, "lr": 3.280803080308031e-05, "epoch": 1.3124312431243124, "percentage": 6.56, "elapsed_time": "0:27:55", "remaining_time": "6:37:36", "throughput": 1502.8, "total_tokens": 2517824} {"current_steps": 11935, "total_steps": 181800, "loss": 0.0705, "lr": 3.282178217821782e-05, "epoch": 1.312981298129813, "percentage": 6.56, "elapsed_time": "0:27:56", "remaining_time": "6:37:35", "throughput": 1502.84, "total_tokens": 2518912} {"current_steps": 11940, "total_steps": 181800, "loss": 0.1326, "lr": 3.283553355335533e-05, "epoch": 1.3135313531353137, "percentage": 6.57, "elapsed_time": "0:27:56", "remaining_time": "6:37:34", "throughput": 1502.85, "total_tokens": 2519968} {"current_steps": 11945, "total_steps": 181800, "loss": 0.0789, "lr": 3.284928492849285e-05, "epoch": 1.314081408140814, "percentage": 6.57, "elapsed_time": "0:27:57", "remaining_time": "6:37:33", "throughput": 1502.87, "total_tokens": 2521024} {"current_steps": 11950, "total_steps": 181800, "loss": 0.116, "lr": 3.286303630363036e-05, "epoch": 1.3146314631463145, "percentage": 6.57, "elapsed_time": "0:27:58", "remaining_time": "6:37:32", "throughput": 1502.86, "total_tokens": 2522048} {"current_steps": 11955, "total_steps": 181800, "loss": 0.1173, "lr": 3.287678767876788e-05, "epoch": 1.3151815181518152, "percentage": 6.58, "elapsed_time": "0:27:58", "remaining_time": "6:37:31", "throughput": 1502.88, "total_tokens": 2523104} {"current_steps": 11960, "total_steps": 181800, "loss": 0.1888, "lr": 3.289053905390539e-05, "epoch": 1.3157315731573158, "percentage": 6.58, "elapsed_time": "0:27:59", "remaining_time": "6:37:30", "throughput": 1502.89, "total_tokens": 2524160} {"current_steps": 11965, "total_steps": 181800, "loss": 0.2433, "lr": 3.2904290429042905e-05, "epoch": 1.3162816281628162, "percentage": 6.58, "elapsed_time": "0:28:00", "remaining_time": "6:37:29", "throughput": 1502.92, "total_tokens": 2525248} {"current_steps": 11970, "total_steps": 181800, "loss": 0.0737, "lr": 3.291804180418042e-05, "epoch": 1.316831683168317, "percentage": 6.58, "elapsed_time": "0:28:00", "remaining_time": "6:37:28", "throughput": 1502.93, "total_tokens": 2526304} {"current_steps": 11975, "total_steps": 181800, "loss": 0.1612, "lr": 3.2931793179317935e-05, "epoch": 1.3173817381738173, "percentage": 6.59, "elapsed_time": "0:28:01", "remaining_time": "6:37:27", "throughput": 1502.95, "total_tokens": 2527360} {"current_steps": 11980, "total_steps": 181800, "loss": 0.114, "lr": 3.294554455445545e-05, "epoch": 1.317931793179318, "percentage": 6.59, "elapsed_time": "0:28:02", "remaining_time": "6:37:26", "throughput": 1502.96, "total_tokens": 2528416} {"current_steps": 11985, "total_steps": 181800, "loss": 0.1666, "lr": 3.295929592959296e-05, "epoch": 1.3184818481848186, "percentage": 6.59, "elapsed_time": "0:28:02", "remaining_time": "6:37:26", "throughput": 1502.95, "total_tokens": 2529440} {"current_steps": 11990, "total_steps": 181800, "loss": 0.198, "lr": 3.297304730473048e-05, "epoch": 1.319031903190319, "percentage": 6.6, "elapsed_time": "0:28:03", "remaining_time": "6:37:25", "throughput": 1502.93, "total_tokens": 2530432} {"current_steps": 11995, "total_steps": 181800, "loss": 0.1719, "lr": 3.298679867986799e-05, "epoch": 1.3195819581958195, "percentage": 6.6, "elapsed_time": "0:28:04", "remaining_time": "6:37:24", "throughput": 1502.9, "total_tokens": 2531424} {"current_steps": 12000, "total_steps": 181800, "loss": 0.1722, "lr": 3.30005500550055e-05, "epoch": 1.3201320132013201, "percentage": 6.6, "elapsed_time": "0:28:05", "remaining_time": "6:37:23", "throughput": 1502.91, "total_tokens": 2532480} {"current_steps": 12005, "total_steps": 181800, "loss": 0.0628, "lr": 3.301430143014301e-05, "epoch": 1.3206820682068208, "percentage": 6.6, "elapsed_time": "0:28:05", "remaining_time": "6:37:22", "throughput": 1502.94, "total_tokens": 2533568} {"current_steps": 12010, "total_steps": 181800, "loss": 0.1378, "lr": 3.302805280528053e-05, "epoch": 1.3212321232123212, "percentage": 6.61, "elapsed_time": "0:28:06", "remaining_time": "6:37:21", "throughput": 1502.91, "total_tokens": 2534560} {"current_steps": 12015, "total_steps": 181800, "loss": 0.124, "lr": 3.304180418041805e-05, "epoch": 1.3217821782178218, "percentage": 6.61, "elapsed_time": "0:28:07", "remaining_time": "6:37:20", "throughput": 1502.91, "total_tokens": 2535584} {"current_steps": 12020, "total_steps": 181800, "loss": 0.0797, "lr": 3.3055555555555553e-05, "epoch": 1.3223322332233223, "percentage": 6.61, "elapsed_time": "0:28:07", "remaining_time": "6:37:19", "throughput": 1502.88, "total_tokens": 2536576} {"current_steps": 12025, "total_steps": 181800, "loss": 0.1425, "lr": 3.306930693069307e-05, "epoch": 1.322882288228823, "percentage": 6.61, "elapsed_time": "0:28:08", "remaining_time": "6:37:19", "throughput": 1502.85, "total_tokens": 2537568} {"current_steps": 12030, "total_steps": 181800, "loss": 0.0743, "lr": 3.3083058305830583e-05, "epoch": 1.3234323432343233, "percentage": 6.62, "elapsed_time": "0:28:09", "remaining_time": "6:37:18", "throughput": 1502.85, "total_tokens": 2538592} {"current_steps": 12035, "total_steps": 181800, "loss": 0.1742, "lr": 3.30968096809681e-05, "epoch": 1.323982398239824, "percentage": 6.62, "elapsed_time": "0:28:09", "remaining_time": "6:37:17", "throughput": 1502.88, "total_tokens": 2539680} {"current_steps": 12040, "total_steps": 181800, "loss": 0.0733, "lr": 3.311056105610561e-05, "epoch": 1.3245324532453244, "percentage": 6.62, "elapsed_time": "0:28:10", "remaining_time": "6:37:16", "throughput": 1502.89, "total_tokens": 2540736} {"current_steps": 12045, "total_steps": 181800, "loss": 0.1177, "lr": 3.3124312431243125e-05, "epoch": 1.325082508250825, "percentage": 6.63, "elapsed_time": "0:28:11", "remaining_time": "6:37:15", "throughput": 1502.92, "total_tokens": 2541824} {"current_steps": 12050, "total_steps": 181800, "loss": 0.1418, "lr": 3.313806380638064e-05, "epoch": 1.3256325632563257, "percentage": 6.63, "elapsed_time": "0:28:11", "remaining_time": "6:37:14", "throughput": 1502.95, "total_tokens": 2542912} {"current_steps": 12055, "total_steps": 181800, "loss": 0.1121, "lr": 3.3151815181518155e-05, "epoch": 1.3261826182618262, "percentage": 6.63, "elapsed_time": "0:28:12", "remaining_time": "6:37:13", "throughput": 1503.02, "total_tokens": 2544064} {"current_steps": 12060, "total_steps": 181800, "loss": 0.0599, "lr": 3.316556655665567e-05, "epoch": 1.3267326732673268, "percentage": 6.63, "elapsed_time": "0:28:13", "remaining_time": "6:37:12", "throughput": 1503.02, "total_tokens": 2545088} {"current_steps": 12065, "total_steps": 181800, "loss": 0.1037, "lr": 3.317931793179318e-05, "epoch": 1.3272827282728272, "percentage": 6.64, "elapsed_time": "0:28:14", "remaining_time": "6:37:11", "throughput": 1503.03, "total_tokens": 2546144} {"current_steps": 12070, "total_steps": 181800, "loss": 0.0337, "lr": 3.31930693069307e-05, "epoch": 1.3278327832783279, "percentage": 6.64, "elapsed_time": "0:28:14", "remaining_time": "6:37:11", "throughput": 1503.01, "total_tokens": 2547136} {"current_steps": 12075, "total_steps": 181800, "loss": 0.0681, "lr": 3.320682068206821e-05, "epoch": 1.3283828382838283, "percentage": 6.64, "elapsed_time": "0:28:15", "remaining_time": "6:37:10", "throughput": 1503.0, "total_tokens": 2548160} {"current_steps": 12080, "total_steps": 181800, "loss": 0.0642, "lr": 3.322057205720572e-05, "epoch": 1.328932893289329, "percentage": 6.64, "elapsed_time": "0:28:16", "remaining_time": "6:37:09", "throughput": 1503.01, "total_tokens": 2549216} {"current_steps": 12085, "total_steps": 181800, "loss": 0.0968, "lr": 3.323432343234323e-05, "epoch": 1.3294829482948294, "percentage": 6.65, "elapsed_time": "0:28:16", "remaining_time": "6:37:08", "throughput": 1503.0, "total_tokens": 2550240} {"current_steps": 12090, "total_steps": 181800, "loss": 0.1177, "lr": 3.324807480748075e-05, "epoch": 1.33003300330033, "percentage": 6.65, "elapsed_time": "0:28:17", "remaining_time": "6:37:07", "throughput": 1503.01, "total_tokens": 2551296} {"current_steps": 12095, "total_steps": 181800, "loss": 0.1631, "lr": 3.326182618261826e-05, "epoch": 1.3305830583058307, "percentage": 6.65, "elapsed_time": "0:28:18", "remaining_time": "6:37:06", "throughput": 1503.02, "total_tokens": 2552352} {"current_steps": 12100, "total_steps": 181800, "loss": 0.0775, "lr": 3.3275577557755774e-05, "epoch": 1.331133113311331, "percentage": 6.66, "elapsed_time": "0:28:18", "remaining_time": "6:37:05", "throughput": 1503.01, "total_tokens": 2553376} {"current_steps": 12105, "total_steps": 181800, "loss": 0.0928, "lr": 3.328932893289329e-05, "epoch": 1.3316831683168318, "percentage": 6.66, "elapsed_time": "0:28:19", "remaining_time": "6:37:04", "throughput": 1503.01, "total_tokens": 2554400} {"current_steps": 12110, "total_steps": 181800, "loss": 0.0857, "lr": 3.3303080308030804e-05, "epoch": 1.3322332233223322, "percentage": 6.66, "elapsed_time": "0:28:20", "remaining_time": "6:37:04", "throughput": 1503.02, "total_tokens": 2555456} {"current_steps": 12115, "total_steps": 181800, "loss": 0.0621, "lr": 3.331683168316832e-05, "epoch": 1.3327832783278328, "percentage": 6.66, "elapsed_time": "0:28:20", "remaining_time": "6:37:03", "throughput": 1503.09, "total_tokens": 2556608} {"current_steps": 12120, "total_steps": 181800, "loss": 0.2577, "lr": 3.3330583058305834e-05, "epoch": 1.3333333333333333, "percentage": 6.67, "elapsed_time": "0:28:21", "remaining_time": "6:37:02", "throughput": 1503.12, "total_tokens": 2557696} {"current_steps": 12125, "total_steps": 181800, "loss": 0.1216, "lr": 3.3344334433443346e-05, "epoch": 1.333883388338834, "percentage": 6.67, "elapsed_time": "0:28:22", "remaining_time": "6:37:01", "throughput": 1503.17, "total_tokens": 2558816} {"current_steps": 12130, "total_steps": 181800, "loss": 0.0755, "lr": 3.335808580858086e-05, "epoch": 1.3344334433443343, "percentage": 6.67, "elapsed_time": "0:28:22", "remaining_time": "6:37:00", "throughput": 1503.15, "total_tokens": 2559808} {"current_steps": 12135, "total_steps": 181800, "loss": 0.1391, "lr": 3.3371837183718376e-05, "epoch": 1.334983498349835, "percentage": 6.67, "elapsed_time": "0:28:23", "remaining_time": "6:36:59", "throughput": 1503.16, "total_tokens": 2560864} {"current_steps": 12140, "total_steps": 181800, "loss": 0.1217, "lr": 3.338558855885589e-05, "epoch": 1.3355335533553356, "percentage": 6.68, "elapsed_time": "0:28:24", "remaining_time": "6:36:58", "throughput": 1503.18, "total_tokens": 2561952} {"current_steps": 12145, "total_steps": 181800, "loss": 0.1245, "lr": 3.33993399339934e-05, "epoch": 1.336083608360836, "percentage": 6.68, "elapsed_time": "0:28:25", "remaining_time": "6:36:57", "throughput": 1503.2, "total_tokens": 2563008} {"current_steps": 12150, "total_steps": 181800, "loss": 0.1005, "lr": 3.341309130913092e-05, "epoch": 1.3366336633663367, "percentage": 6.68, "elapsed_time": "0:28:25", "remaining_time": "6:36:57", "throughput": 1503.19, "total_tokens": 2564032} {"current_steps": 12155, "total_steps": 181800, "loss": 0.0999, "lr": 3.342684268426843e-05, "epoch": 1.3371837183718371, "percentage": 6.69, "elapsed_time": "0:28:26", "remaining_time": "6:36:56", "throughput": 1503.2, "total_tokens": 2565088} {"current_steps": 12160, "total_steps": 181800, "loss": 0.1125, "lr": 3.344059405940595e-05, "epoch": 1.3377337733773378, "percentage": 6.69, "elapsed_time": "0:28:27", "remaining_time": "6:36:55", "throughput": 1503.21, "total_tokens": 2566144} {"current_steps": 12165, "total_steps": 181800, "loss": 0.0958, "lr": 3.345434543454345e-05, "epoch": 1.3382838283828382, "percentage": 6.69, "elapsed_time": "0:28:27", "remaining_time": "6:36:54", "throughput": 1503.23, "total_tokens": 2567200} {"current_steps": 12170, "total_steps": 181800, "loss": 0.1217, "lr": 3.346809680968097e-05, "epoch": 1.3388338833883389, "percentage": 6.69, "elapsed_time": "0:28:28", "remaining_time": "6:36:53", "throughput": 1503.26, "total_tokens": 2568288} {"current_steps": 12175, "total_steps": 181800, "loss": 0.0501, "lr": 3.348184818481848e-05, "epoch": 1.3393839383938393, "percentage": 6.7, "elapsed_time": "0:28:29", "remaining_time": "6:36:52", "throughput": 1503.31, "total_tokens": 2569408} {"current_steps": 12180, "total_steps": 181800, "loss": 0.1368, "lr": 3.3495599559956e-05, "epoch": 1.33993399339934, "percentage": 6.7, "elapsed_time": "0:28:29", "remaining_time": "6:36:51", "throughput": 1503.34, "total_tokens": 2570496} {"current_steps": 12185, "total_steps": 181800, "loss": 0.0593, "lr": 3.3509350935093506e-05, "epoch": 1.3404840484048406, "percentage": 6.7, "elapsed_time": "0:28:30", "remaining_time": "6:36:50", "throughput": 1503.34, "total_tokens": 2571520} {"current_steps": 12190, "total_steps": 181800, "loss": 0.1241, "lr": 3.3523102310231024e-05, "epoch": 1.341034103410341, "percentage": 6.71, "elapsed_time": "0:28:31", "remaining_time": "6:36:49", "throughput": 1503.35, "total_tokens": 2572576} {"current_steps": 12195, "total_steps": 181800, "loss": 0.103, "lr": 3.353685368536854e-05, "epoch": 1.3415841584158417, "percentage": 6.71, "elapsed_time": "0:28:31", "remaining_time": "6:36:48", "throughput": 1503.36, "total_tokens": 2573632} {"current_steps": 12200, "total_steps": 181800, "loss": 0.0832, "lr": 3.3550605060506054e-05, "epoch": 1.342134213421342, "percentage": 6.71, "elapsed_time": "0:28:32", "remaining_time": "6:36:48", "throughput": 1503.41, "total_tokens": 2574752} {"current_steps": 12205, "total_steps": 181800, "loss": 0.155, "lr": 3.3564356435643566e-05, "epoch": 1.3426842684268427, "percentage": 6.71, "elapsed_time": "0:28:33", "remaining_time": "6:36:47", "throughput": 1503.43, "total_tokens": 2575808} {"current_steps": 12210, "total_steps": 181800, "loss": 0.0964, "lr": 3.357810781078108e-05, "epoch": 1.3432343234323432, "percentage": 6.72, "elapsed_time": "0:28:33", "remaining_time": "6:36:46", "throughput": 1503.44, "total_tokens": 2576864} {"current_steps": 12215, "total_steps": 181800, "loss": 0.1151, "lr": 3.3591859185918596e-05, "epoch": 1.3437843784378438, "percentage": 6.72, "elapsed_time": "0:28:34", "remaining_time": "6:36:45", "throughput": 1503.47, "total_tokens": 2577952} {"current_steps": 12220, "total_steps": 181800, "loss": 0.101, "lr": 3.360561056105611e-05, "epoch": 1.3443344334433442, "percentage": 6.72, "elapsed_time": "0:28:35", "remaining_time": "6:36:44", "throughput": 1503.47, "total_tokens": 2578976} {"current_steps": 12225, "total_steps": 181800, "loss": 0.1069, "lr": 3.361936193619362e-05, "epoch": 1.344884488448845, "percentage": 6.72, "elapsed_time": "0:28:36", "remaining_time": "6:36:43", "throughput": 1503.48, "total_tokens": 2580032} {"current_steps": 12230, "total_steps": 181800, "loss": 0.1132, "lr": 3.363311331133113e-05, "epoch": 1.3454345434543455, "percentage": 6.73, "elapsed_time": "0:28:36", "remaining_time": "6:36:42", "throughput": 1503.48, "total_tokens": 2581056} {"current_steps": 12235, "total_steps": 181800, "loss": 0.1132, "lr": 3.364686468646865e-05, "epoch": 1.345984598459846, "percentage": 6.73, "elapsed_time": "0:28:37", "remaining_time": "6:36:41", "throughput": 1503.49, "total_tokens": 2582112} {"current_steps": 12240, "total_steps": 181800, "loss": 0.2294, "lr": 3.366061606160617e-05, "epoch": 1.3465346534653464, "percentage": 6.73, "elapsed_time": "0:28:38", "remaining_time": "6:36:40", "throughput": 1503.5, "total_tokens": 2583168} {"current_steps": 12245, "total_steps": 181800, "loss": 0.1149, "lr": 3.367436743674367e-05, "epoch": 1.347084708470847, "percentage": 6.74, "elapsed_time": "0:28:38", "remaining_time": "6:36:39", "throughput": 1503.48, "total_tokens": 2584160} {"current_steps": 12250, "total_steps": 181800, "loss": 0.1048, "lr": 3.368811881188119e-05, "epoch": 1.3476347634763477, "percentage": 6.74, "elapsed_time": "0:28:39", "remaining_time": "6:36:38", "throughput": 1503.45, "total_tokens": 2585152} {"current_steps": 12255, "total_steps": 181800, "loss": 0.0923, "lr": 3.37018701870187e-05, "epoch": 1.3481848184818481, "percentage": 6.74, "elapsed_time": "0:28:40", "remaining_time": "6:36:38", "throughput": 1503.49, "total_tokens": 2586240} {"current_steps": 12260, "total_steps": 181800, "loss": 0.3684, "lr": 3.371562156215622e-05, "epoch": 1.3487348734873488, "percentage": 6.74, "elapsed_time": "0:28:40", "remaining_time": "6:36:37", "throughput": 1503.5, "total_tokens": 2587296} {"current_steps": 12265, "total_steps": 181800, "loss": 0.2201, "lr": 3.3729372937293726e-05, "epoch": 1.3492849284928492, "percentage": 6.75, "elapsed_time": "0:28:41", "remaining_time": "6:36:36", "throughput": 1503.51, "total_tokens": 2588352} {"current_steps": 12270, "total_steps": 181800, "loss": 0.0963, "lr": 3.3743124312431245e-05, "epoch": 1.3498349834983498, "percentage": 6.75, "elapsed_time": "0:28:42", "remaining_time": "6:36:35", "throughput": 1503.53, "total_tokens": 2589408} {"current_steps": 12275, "total_steps": 181800, "loss": 0.1259, "lr": 3.3756875687568756e-05, "epoch": 1.3503850385038505, "percentage": 6.75, "elapsed_time": "0:28:42", "remaining_time": "6:36:34", "throughput": 1503.51, "total_tokens": 2590400} {"current_steps": 12280, "total_steps": 181800, "loss": 0.1835, "lr": 3.3770627062706275e-05, "epoch": 1.350935093509351, "percentage": 6.75, "elapsed_time": "0:28:43", "remaining_time": "6:36:33", "throughput": 1503.5, "total_tokens": 2591424} {"current_steps": 12285, "total_steps": 181800, "loss": 0.0434, "lr": 3.3784378437843786e-05, "epoch": 1.3514851485148514, "percentage": 6.76, "elapsed_time": "0:28:44", "remaining_time": "6:36:32", "throughput": 1503.52, "total_tokens": 2592480} {"current_steps": 12290, "total_steps": 181800, "loss": 0.1522, "lr": 3.37981298129813e-05, "epoch": 1.352035203520352, "percentage": 6.76, "elapsed_time": "0:28:44", "remaining_time": "6:36:31", "throughput": 1503.53, "total_tokens": 2593536} {"current_steps": 12295, "total_steps": 181800, "loss": 0.1156, "lr": 3.3811881188118816e-05, "epoch": 1.3525852585258527, "percentage": 6.76, "elapsed_time": "0:28:45", "remaining_time": "6:36:30", "throughput": 1503.52, "total_tokens": 2594560} {"current_steps": 12300, "total_steps": 181800, "loss": 0.1834, "lr": 3.382563256325633e-05, "epoch": 1.353135313531353, "percentage": 6.77, "elapsed_time": "0:28:46", "remaining_time": "6:36:29", "throughput": 1503.55, "total_tokens": 2595648} {"current_steps": 12305, "total_steps": 181800, "loss": 0.1081, "lr": 3.383938393839384e-05, "epoch": 1.3536853685368537, "percentage": 6.77, "elapsed_time": "0:28:47", "remaining_time": "6:36:29", "throughput": 1503.53, "total_tokens": 2596672} {"current_steps": 12310, "total_steps": 181800, "loss": 0.1011, "lr": 3.385313531353135e-05, "epoch": 1.3542354235423542, "percentage": 6.77, "elapsed_time": "0:28:47", "remaining_time": "6:36:28", "throughput": 1503.53, "total_tokens": 2597696} {"current_steps": 12315, "total_steps": 181800, "loss": 0.0432, "lr": 3.386688668866887e-05, "epoch": 1.3547854785478548, "percentage": 6.77, "elapsed_time": "0:28:48", "remaining_time": "6:36:27", "throughput": 1503.5, "total_tokens": 2598688} {"current_steps": 12320, "total_steps": 181800, "loss": 0.1398, "lr": 3.388063806380638e-05, "epoch": 1.3553355335533555, "percentage": 6.78, "elapsed_time": "0:28:49", "remaining_time": "6:36:26", "throughput": 1503.55, "total_tokens": 2599808} {"current_steps": 12325, "total_steps": 181800, "loss": 0.1624, "lr": 3.389438943894389e-05, "epoch": 1.3558855885588559, "percentage": 6.78, "elapsed_time": "0:28:49", "remaining_time": "6:36:25", "throughput": 1503.58, "total_tokens": 2600896} {"current_steps": 12330, "total_steps": 181800, "loss": 0.1375, "lr": 3.3908140814081405e-05, "epoch": 1.3564356435643563, "percentage": 6.78, "elapsed_time": "0:28:50", "remaining_time": "6:36:24", "throughput": 1503.58, "total_tokens": 2601920} {"current_steps": 12335, "total_steps": 181800, "loss": 0.1541, "lr": 3.392189218921892e-05, "epoch": 1.356985698569857, "percentage": 6.78, "elapsed_time": "0:28:51", "remaining_time": "6:36:23", "throughput": 1503.57, "total_tokens": 2602944} {"current_steps": 12340, "total_steps": 181800, "loss": 0.142, "lr": 3.393564356435644e-05, "epoch": 1.3575357535753576, "percentage": 6.79, "elapsed_time": "0:28:52", "remaining_time": "6:36:25", "throughput": 1503.44, "total_tokens": 2604032} {"current_steps": 12345, "total_steps": 181800, "loss": 0.2076, "lr": 3.394939493949395e-05, "epoch": 1.358085808580858, "percentage": 6.79, "elapsed_time": "0:28:52", "remaining_time": "6:36:24", "throughput": 1503.47, "total_tokens": 2605120} {"current_steps": 12350, "total_steps": 181800, "loss": 0.1048, "lr": 3.3963146314631465e-05, "epoch": 1.3586358635863587, "percentage": 6.79, "elapsed_time": "0:28:53", "remaining_time": "6:36:23", "throughput": 1503.46, "total_tokens": 2606144} {"current_steps": 12355, "total_steps": 181800, "loss": 0.0657, "lr": 3.397689768976898e-05, "epoch": 1.359185918591859, "percentage": 6.8, "elapsed_time": "0:28:54", "remaining_time": "6:36:22", "throughput": 1503.46, "total_tokens": 2607168} {"current_steps": 12360, "total_steps": 181800, "loss": 0.1394, "lr": 3.3990649064906495e-05, "epoch": 1.3597359735973598, "percentage": 6.8, "elapsed_time": "0:28:54", "remaining_time": "6:36:21", "throughput": 1503.47, "total_tokens": 2608224} {"current_steps": 12365, "total_steps": 181800, "loss": 0.1252, "lr": 3.400440044004401e-05, "epoch": 1.3602860286028604, "percentage": 6.8, "elapsed_time": "0:28:55", "remaining_time": "6:36:21", "throughput": 1503.47, "total_tokens": 2609248} {"current_steps": 12370, "total_steps": 181800, "loss": 0.1126, "lr": 3.401815181518152e-05, "epoch": 1.3608360836083608, "percentage": 6.8, "elapsed_time": "0:28:56", "remaining_time": "6:36:20", "throughput": 1503.48, "total_tokens": 2610304} {"current_steps": 12375, "total_steps": 181800, "loss": 0.0865, "lr": 3.403190319031903e-05, "epoch": 1.3613861386138613, "percentage": 6.81, "elapsed_time": "0:28:56", "remaining_time": "6:36:19", "throughput": 1503.46, "total_tokens": 2611296} {"current_steps": 12380, "total_steps": 181800, "loss": 0.1425, "lr": 3.404565456545655e-05, "epoch": 1.361936193619362, "percentage": 6.81, "elapsed_time": "0:28:57", "remaining_time": "6:36:18", "throughput": 1503.45, "total_tokens": 2612320} {"current_steps": 12385, "total_steps": 181800, "loss": 0.09, "lr": 3.405940594059407e-05, "epoch": 1.3624862486248626, "percentage": 6.81, "elapsed_time": "0:28:58", "remaining_time": "6:36:17", "throughput": 1503.52, "total_tokens": 2613472} {"current_steps": 12390, "total_steps": 181800, "loss": 0.1342, "lr": 3.407315731573157e-05, "epoch": 1.363036303630363, "percentage": 6.82, "elapsed_time": "0:28:58", "remaining_time": "6:36:16", "throughput": 1503.54, "total_tokens": 2614560} {"current_steps": 12395, "total_steps": 181800, "loss": 0.1097, "lr": 3.408690869086909e-05, "epoch": 1.3635863586358636, "percentage": 6.82, "elapsed_time": "0:28:59", "remaining_time": "6:36:15", "throughput": 1503.57, "total_tokens": 2615648} {"current_steps": 12400, "total_steps": 181800, "loss": 0.1012, "lr": 3.41006600660066e-05, "epoch": 1.364136413641364, "percentage": 6.82, "elapsed_time": "0:29:00", "remaining_time": "6:36:14", "throughput": 1503.6, "total_tokens": 2616736} {"current_steps": 12405, "total_steps": 181800, "loss": 0.2005, "lr": 3.411441144114412e-05, "epoch": 1.3646864686468647, "percentage": 6.82, "elapsed_time": "0:29:01", "remaining_time": "6:36:14", "throughput": 1503.59, "total_tokens": 2617760} {"current_steps": 12410, "total_steps": 181800, "loss": 0.1228, "lr": 3.4128162816281625e-05, "epoch": 1.3652365236523654, "percentage": 6.83, "elapsed_time": "0:29:01", "remaining_time": "6:36:13", "throughput": 1503.6, "total_tokens": 2618816} {"current_steps": 12415, "total_steps": 181800, "loss": 0.1686, "lr": 3.4141914191419144e-05, "epoch": 1.3657865786578658, "percentage": 6.83, "elapsed_time": "0:29:02", "remaining_time": "6:36:12", "throughput": 1503.6, "total_tokens": 2619840} {"current_steps": 12420, "total_steps": 181800, "loss": 0.0829, "lr": 3.4155665566556655e-05, "epoch": 1.3663366336633662, "percentage": 6.83, "elapsed_time": "0:29:03", "remaining_time": "6:36:11", "throughput": 1503.59, "total_tokens": 2620864} {"current_steps": 12425, "total_steps": 181800, "loss": 0.0982, "lr": 3.4169416941694174e-05, "epoch": 1.3668866886688669, "percentage": 6.83, "elapsed_time": "0:29:03", "remaining_time": "6:36:10", "throughput": 1503.58, "total_tokens": 2621888} {"current_steps": 12430, "total_steps": 181800, "loss": 0.2518, "lr": 3.4183168316831685e-05, "epoch": 1.3674367436743675, "percentage": 6.84, "elapsed_time": "0:29:04", "remaining_time": "6:36:09", "throughput": 1503.56, "total_tokens": 2622880} {"current_steps": 12435, "total_steps": 181800, "loss": 0.0459, "lr": 3.41969196919692e-05, "epoch": 1.367986798679868, "percentage": 6.84, "elapsed_time": "0:29:05", "remaining_time": "6:36:08", "throughput": 1503.55, "total_tokens": 2623904} {"current_steps": 12440, "total_steps": 181800, "loss": 0.0994, "lr": 3.4210671067106715e-05, "epoch": 1.3685368536853686, "percentage": 6.84, "elapsed_time": "0:29:05", "remaining_time": "6:36:07", "throughput": 1503.57, "total_tokens": 2624960} {"current_steps": 12445, "total_steps": 181800, "loss": 0.1376, "lr": 3.422442244224423e-05, "epoch": 1.369086908690869, "percentage": 6.85, "elapsed_time": "0:29:06", "remaining_time": "6:36:06", "throughput": 1503.6, "total_tokens": 2626048} {"current_steps": 12450, "total_steps": 181800, "loss": 0.1472, "lr": 3.423817381738174e-05, "epoch": 1.3696369636963697, "percentage": 6.85, "elapsed_time": "0:29:07", "remaining_time": "6:36:06", "throughput": 1503.58, "total_tokens": 2627040} {"current_steps": 12455, "total_steps": 181800, "loss": 0.049, "lr": 3.425192519251925e-05, "epoch": 1.3701870187018703, "percentage": 6.85, "elapsed_time": "0:29:07", "remaining_time": "6:36:05", "throughput": 1503.59, "total_tokens": 2628096} {"current_steps": 12460, "total_steps": 181800, "loss": 0.1906, "lr": 3.426567656765677e-05, "epoch": 1.3707370737073707, "percentage": 6.85, "elapsed_time": "0:29:08", "remaining_time": "6:36:04", "throughput": 1503.57, "total_tokens": 2629088} {"current_steps": 12465, "total_steps": 181800, "loss": 0.0863, "lr": 3.427942794279428e-05, "epoch": 1.3712871287128712, "percentage": 6.86, "elapsed_time": "0:29:09", "remaining_time": "6:36:03", "throughput": 1503.64, "total_tokens": 2630240} {"current_steps": 12470, "total_steps": 181800, "loss": 0.1153, "lr": 3.429317931793179e-05, "epoch": 1.3718371837183718, "percentage": 6.86, "elapsed_time": "0:29:09", "remaining_time": "6:36:02", "throughput": 1503.69, "total_tokens": 2631360} {"current_steps": 12475, "total_steps": 181800, "loss": 0.1746, "lr": 3.430693069306931e-05, "epoch": 1.3723872387238725, "percentage": 6.86, "elapsed_time": "0:29:10", "remaining_time": "6:36:01", "throughput": 1503.7, "total_tokens": 2632416} {"current_steps": 12480, "total_steps": 181800, "loss": 0.1015, "lr": 3.432068206820682e-05, "epoch": 1.372937293729373, "percentage": 6.86, "elapsed_time": "0:29:11", "remaining_time": "6:36:00", "throughput": 1503.69, "total_tokens": 2633440} {"current_steps": 12485, "total_steps": 181800, "loss": 0.0863, "lr": 3.433443344334434e-05, "epoch": 1.3734873487348735, "percentage": 6.87, "elapsed_time": "0:29:12", "remaining_time": "6:35:59", "throughput": 1503.66, "total_tokens": 2634432} {"current_steps": 12490, "total_steps": 181800, "loss": 0.1453, "lr": 3.4348184818481846e-05, "epoch": 1.374037403740374, "percentage": 6.87, "elapsed_time": "0:29:12", "remaining_time": "6:35:58", "throughput": 1503.69, "total_tokens": 2635520} {"current_steps": 12495, "total_steps": 181800, "loss": 0.0726, "lr": 3.4361936193619364e-05, "epoch": 1.3745874587458746, "percentage": 6.87, "elapsed_time": "0:29:13", "remaining_time": "6:35:58", "throughput": 1503.71, "total_tokens": 2636576} {"current_steps": 12500, "total_steps": 181800, "loss": 0.1544, "lr": 3.4375687568756876e-05, "epoch": 1.3751375137513753, "percentage": 6.88, "elapsed_time": "0:29:14", "remaining_time": "6:35:57", "throughput": 1503.68, "total_tokens": 2637568} {"current_steps": 12505, "total_steps": 181800, "loss": 0.1731, "lr": 3.4389438943894394e-05, "epoch": 1.3756875687568757, "percentage": 6.88, "elapsed_time": "0:29:14", "remaining_time": "6:35:56", "throughput": 1503.71, "total_tokens": 2638656} {"current_steps": 12510, "total_steps": 181800, "loss": 0.134, "lr": 3.4403190319031906e-05, "epoch": 1.3762376237623761, "percentage": 6.88, "elapsed_time": "0:29:15", "remaining_time": "6:35:55", "throughput": 1503.68, "total_tokens": 2639648} {"current_steps": 12515, "total_steps": 181800, "loss": 0.069, "lr": 3.441694169416942e-05, "epoch": 1.3767876787678768, "percentage": 6.88, "elapsed_time": "0:29:16", "remaining_time": "6:35:54", "throughput": 1503.68, "total_tokens": 2640672} {"current_steps": 12520, "total_steps": 181800, "loss": 0.1117, "lr": 3.443069306930693e-05, "epoch": 1.3773377337733774, "percentage": 6.89, "elapsed_time": "0:29:16", "remaining_time": "6:35:53", "throughput": 1503.67, "total_tokens": 2641696} {"current_steps": 12525, "total_steps": 181800, "loss": 0.062, "lr": 3.444444444444445e-05, "epoch": 1.3778877887788779, "percentage": 6.89, "elapsed_time": "0:29:17", "remaining_time": "6:35:52", "throughput": 1503.71, "total_tokens": 2642816} {"current_steps": 12530, "total_steps": 181800, "loss": 0.093, "lr": 3.445819581958196e-05, "epoch": 1.3784378437843785, "percentage": 6.89, "elapsed_time": "0:29:18", "remaining_time": "6:35:52", "throughput": 1503.67, "total_tokens": 2643776} {"current_steps": 12535, "total_steps": 181800, "loss": 0.2125, "lr": 3.447194719471947e-05, "epoch": 1.378987898789879, "percentage": 6.89, "elapsed_time": "0:29:18", "remaining_time": "6:35:51", "throughput": 1503.66, "total_tokens": 2644800} {"current_steps": 12540, "total_steps": 181800, "loss": 0.1189, "lr": 3.448569856985699e-05, "epoch": 1.3795379537953796, "percentage": 6.9, "elapsed_time": "0:29:19", "remaining_time": "6:35:50", "throughput": 1503.67, "total_tokens": 2645856} {"current_steps": 12545, "total_steps": 181800, "loss": 0.0797, "lr": 3.44994499449945e-05, "epoch": 1.38008800880088, "percentage": 6.9, "elapsed_time": "0:29:20", "remaining_time": "6:35:49", "throughput": 1503.7, "total_tokens": 2646944} {"current_steps": 12550, "total_steps": 181800, "loss": 0.1082, "lr": 3.451320132013202e-05, "epoch": 1.3806380638063807, "percentage": 6.9, "elapsed_time": "0:29:20", "remaining_time": "6:35:48", "throughput": 1503.72, "total_tokens": 2648000} {"current_steps": 12555, "total_steps": 181800, "loss": 0.1178, "lr": 3.4526952695269524e-05, "epoch": 1.381188118811881, "percentage": 6.91, "elapsed_time": "0:29:21", "remaining_time": "6:35:47", "throughput": 1503.73, "total_tokens": 2649056} {"current_steps": 12560, "total_steps": 181800, "loss": 0.1173, "lr": 3.454070407040704e-05, "epoch": 1.3817381738173817, "percentage": 6.91, "elapsed_time": "0:29:22", "remaining_time": "6:35:46", "throughput": 1503.74, "total_tokens": 2650112} {"current_steps": 12565, "total_steps": 181800, "loss": 0.094, "lr": 3.4554455445544554e-05, "epoch": 1.3822882288228824, "percentage": 6.91, "elapsed_time": "0:29:23", "remaining_time": "6:35:45", "throughput": 1503.75, "total_tokens": 2651168} {"current_steps": 12570, "total_steps": 181800, "loss": 0.1334, "lr": 3.456820682068207e-05, "epoch": 1.3828382838283828, "percentage": 6.91, "elapsed_time": "0:29:23", "remaining_time": "6:35:45", "throughput": 1503.76, "total_tokens": 2652224} {"current_steps": 12575, "total_steps": 181800, "loss": 0.1813, "lr": 3.4581958195819584e-05, "epoch": 1.3833883388338835, "percentage": 6.92, "elapsed_time": "0:29:24", "remaining_time": "6:35:44", "throughput": 1503.75, "total_tokens": 2653248} {"current_steps": 12580, "total_steps": 181800, "loss": 0.1152, "lr": 3.4595709570957096e-05, "epoch": 1.3839383938393839, "percentage": 6.92, "elapsed_time": "0:29:25", "remaining_time": "6:35:43", "throughput": 1503.75, "total_tokens": 2654272} {"current_steps": 12585, "total_steps": 181800, "loss": 0.114, "lr": 3.4609460946094614e-05, "epoch": 1.3844884488448845, "percentage": 6.92, "elapsed_time": "0:29:25", "remaining_time": "6:35:42", "throughput": 1503.76, "total_tokens": 2655328} {"current_steps": 12590, "total_steps": 181800, "loss": 0.0969, "lr": 3.4623212321232126e-05, "epoch": 1.385038503850385, "percentage": 6.93, "elapsed_time": "0:29:26", "remaining_time": "6:35:41", "throughput": 1503.79, "total_tokens": 2656416} {"current_steps": 12595, "total_steps": 181800, "loss": 0.0669, "lr": 3.463696369636964e-05, "epoch": 1.3855885588558856, "percentage": 6.93, "elapsed_time": "0:29:27", "remaining_time": "6:35:40", "throughput": 1503.78, "total_tokens": 2657440} {"current_steps": 12600, "total_steps": 181800, "loss": 0.2301, "lr": 3.465071507150715e-05, "epoch": 1.386138613861386, "percentage": 6.93, "elapsed_time": "0:29:27", "remaining_time": "6:35:39", "throughput": 1503.82, "total_tokens": 2658560} {"current_steps": 12605, "total_steps": 181800, "loss": 0.0777, "lr": 3.466446644664467e-05, "epoch": 1.3866886688668867, "percentage": 6.93, "elapsed_time": "0:29:28", "remaining_time": "6:35:39", "throughput": 1503.8, "total_tokens": 2659552} {"current_steps": 12610, "total_steps": 181800, "loss": 0.1061, "lr": 3.467821782178218e-05, "epoch": 1.3872387238723873, "percentage": 6.94, "elapsed_time": "0:29:29", "remaining_time": "6:35:38", "throughput": 1503.84, "total_tokens": 2660672} {"current_steps": 12615, "total_steps": 181800, "loss": 0.1286, "lr": 3.469196919691969e-05, "epoch": 1.3877887788778878, "percentage": 6.94, "elapsed_time": "0:29:29", "remaining_time": "6:35:37", "throughput": 1503.82, "total_tokens": 2661664} {"current_steps": 12620, "total_steps": 181800, "loss": 0.1352, "lr": 3.470572057205721e-05, "epoch": 1.3883388338833884, "percentage": 6.94, "elapsed_time": "0:29:30", "remaining_time": "6:35:36", "throughput": 1503.78, "total_tokens": 2662624} {"current_steps": 12625, "total_steps": 181800, "loss": 0.1576, "lr": 3.471947194719472e-05, "epoch": 1.3888888888888888, "percentage": 6.94, "elapsed_time": "0:29:31", "remaining_time": "6:35:35", "throughput": 1503.79, "total_tokens": 2663680} {"current_steps": 12630, "total_steps": 181800, "loss": 0.0931, "lr": 3.473322332233224e-05, "epoch": 1.3894389438943895, "percentage": 6.95, "elapsed_time": "0:29:32", "remaining_time": "6:35:34", "throughput": 1503.78, "total_tokens": 2664704} {"current_steps": 12635, "total_steps": 181800, "loss": 0.161, "lr": 3.4746974697469745e-05, "epoch": 1.38998899889989, "percentage": 6.95, "elapsed_time": "0:29:32", "remaining_time": "6:35:33", "throughput": 1503.79, "total_tokens": 2665760} {"current_steps": 12640, "total_steps": 181800, "loss": 0.1902, "lr": 3.476072607260726e-05, "epoch": 1.3905390539053906, "percentage": 6.95, "elapsed_time": "0:29:33", "remaining_time": "6:35:33", "throughput": 1503.84, "total_tokens": 2666880} {"current_steps": 12645, "total_steps": 181800, "loss": 0.0956, "lr": 3.4774477447744775e-05, "epoch": 1.391089108910891, "percentage": 6.96, "elapsed_time": "0:29:34", "remaining_time": "6:35:32", "throughput": 1503.83, "total_tokens": 2667904} {"current_steps": 12650, "total_steps": 181800, "loss": 0.1192, "lr": 3.478822882288229e-05, "epoch": 1.3916391639163916, "percentage": 6.96, "elapsed_time": "0:29:34", "remaining_time": "6:35:31", "throughput": 1503.88, "total_tokens": 2669024} {"current_steps": 12655, "total_steps": 181800, "loss": 0.0388, "lr": 3.48019801980198e-05, "epoch": 1.3921892189218923, "percentage": 6.96, "elapsed_time": "0:29:35", "remaining_time": "6:35:30", "throughput": 1503.91, "total_tokens": 2670112} {"current_steps": 12660, "total_steps": 181800, "loss": 0.1244, "lr": 3.4815731573157316e-05, "epoch": 1.3927392739273927, "percentage": 6.96, "elapsed_time": "0:29:36", "remaining_time": "6:35:29", "throughput": 1503.9, "total_tokens": 2671136} {"current_steps": 12665, "total_steps": 181800, "loss": 0.1816, "lr": 3.4829482948294835e-05, "epoch": 1.3932893289328934, "percentage": 6.97, "elapsed_time": "0:29:36", "remaining_time": "6:35:28", "throughput": 1503.87, "total_tokens": 2672128} {"current_steps": 12670, "total_steps": 181800, "loss": 0.1183, "lr": 3.4843234323432346e-05, "epoch": 1.3938393839383938, "percentage": 6.97, "elapsed_time": "0:29:37", "remaining_time": "6:35:27", "throughput": 1503.85, "total_tokens": 2673120} {"current_steps": 12675, "total_steps": 181800, "loss": 0.065, "lr": 3.485698569856986e-05, "epoch": 1.3943894389438944, "percentage": 6.97, "elapsed_time": "0:29:38", "remaining_time": "6:35:26", "throughput": 1503.88, "total_tokens": 2674208} {"current_steps": 12680, "total_steps": 181800, "loss": 0.1738, "lr": 3.487073707370737e-05, "epoch": 1.3949394939493949, "percentage": 6.97, "elapsed_time": "0:29:38", "remaining_time": "6:35:26", "throughput": 1503.89, "total_tokens": 2675264} {"current_steps": 12685, "total_steps": 181800, "loss": 0.1898, "lr": 3.488448844884489e-05, "epoch": 1.3954895489548955, "percentage": 6.98, "elapsed_time": "0:29:39", "remaining_time": "6:35:25", "throughput": 1503.86, "total_tokens": 2676256} {"current_steps": 12690, "total_steps": 181800, "loss": 0.1636, "lr": 3.48982398239824e-05, "epoch": 1.396039603960396, "percentage": 6.98, "elapsed_time": "0:29:40", "remaining_time": "6:35:24", "throughput": 1503.87, "total_tokens": 2677312} {"current_steps": 12695, "total_steps": 181800, "loss": 0.182, "lr": 3.491199119911991e-05, "epoch": 1.3965896589658966, "percentage": 6.98, "elapsed_time": "0:29:40", "remaining_time": "6:35:23", "throughput": 1503.88, "total_tokens": 2678368} {"current_steps": 12700, "total_steps": 181800, "loss": 0.1003, "lr": 3.492574257425742e-05, "epoch": 1.3971397139713972, "percentage": 6.99, "elapsed_time": "0:29:41", "remaining_time": "6:35:22", "throughput": 1503.91, "total_tokens": 2679456} {"current_steps": 12705, "total_steps": 181800, "loss": 0.163, "lr": 3.493949394939494e-05, "epoch": 1.3976897689768977, "percentage": 6.99, "elapsed_time": "0:29:42", "remaining_time": "6:35:21", "throughput": 1503.94, "total_tokens": 2680544} {"current_steps": 12710, "total_steps": 181800, "loss": 0.2481, "lr": 3.495324532453246e-05, "epoch": 1.3982398239823983, "percentage": 6.99, "elapsed_time": "0:29:43", "remaining_time": "6:35:21", "throughput": 1503.93, "total_tokens": 2681568} {"current_steps": 12715, "total_steps": 181800, "loss": 0.1304, "lr": 3.4966996699669965e-05, "epoch": 1.3987898789878987, "percentage": 6.99, "elapsed_time": "0:29:43", "remaining_time": "6:35:20", "throughput": 1503.96, "total_tokens": 2682656} {"current_steps": 12720, "total_steps": 181800, "loss": 0.0814, "lr": 3.498074807480748e-05, "epoch": 1.3993399339933994, "percentage": 7.0, "elapsed_time": "0:29:44", "remaining_time": "6:35:19", "throughput": 1503.95, "total_tokens": 2683680} {"current_steps": 12725, "total_steps": 181800, "loss": 0.1664, "lr": 3.4994499449944995e-05, "epoch": 1.3998899889988998, "percentage": 7.0, "elapsed_time": "0:29:45", "remaining_time": "6:35:18", "throughput": 1503.94, "total_tokens": 2684704} {"current_steps": 12730, "total_steps": 181800, "loss": 0.1191, "lr": 3.5008250825082513e-05, "epoch": 1.4004400440044005, "percentage": 7.0, "elapsed_time": "0:29:45", "remaining_time": "6:35:17", "throughput": 1503.97, "total_tokens": 2685792} {"current_steps": 12735, "total_steps": 181800, "loss": 0.1252, "lr": 3.5022002200220025e-05, "epoch": 1.400990099009901, "percentage": 7.0, "elapsed_time": "0:29:46", "remaining_time": "6:35:16", "throughput": 1503.98, "total_tokens": 2686848} {"current_steps": 12740, "total_steps": 181800, "loss": 0.1717, "lr": 3.503575357535754e-05, "epoch": 1.4015401540154016, "percentage": 7.01, "elapsed_time": "0:29:47", "remaining_time": "6:35:15", "throughput": 1504.0, "total_tokens": 2687904} {"current_steps": 12745, "total_steps": 181800, "loss": 0.1242, "lr": 3.504950495049505e-05, "epoch": 1.4020902090209022, "percentage": 7.01, "elapsed_time": "0:29:47", "remaining_time": "6:35:14", "throughput": 1504.03, "total_tokens": 2688992} {"current_steps": 12750, "total_steps": 181800, "loss": 0.0544, "lr": 3.506325632563257e-05, "epoch": 1.4026402640264026, "percentage": 7.01, "elapsed_time": "0:29:48", "remaining_time": "6:35:14", "throughput": 1504.06, "total_tokens": 2690080} {"current_steps": 12755, "total_steps": 181800, "loss": 0.0963, "lr": 3.507700770077008e-05, "epoch": 1.403190319031903, "percentage": 7.02, "elapsed_time": "0:29:49", "remaining_time": "6:35:13", "throughput": 1504.11, "total_tokens": 2691200} {"current_steps": 12760, "total_steps": 181800, "loss": 0.187, "lr": 3.509075907590759e-05, "epoch": 1.4037403740374037, "percentage": 7.02, "elapsed_time": "0:29:49", "remaining_time": "6:35:12", "throughput": 1504.1, "total_tokens": 2692224} {"current_steps": 12765, "total_steps": 181800, "loss": 0.0878, "lr": 3.510451045104511e-05, "epoch": 1.4042904290429044, "percentage": 7.02, "elapsed_time": "0:29:50", "remaining_time": "6:35:11", "throughput": 1504.11, "total_tokens": 2693280} {"current_steps": 12770, "total_steps": 181800, "loss": 0.1146, "lr": 3.511826182618262e-05, "epoch": 1.4048404840484048, "percentage": 7.02, "elapsed_time": "0:29:51", "remaining_time": "6:35:10", "throughput": 1504.14, "total_tokens": 2694368} {"current_steps": 12775, "total_steps": 181800, "loss": 0.0734, "lr": 3.513201320132014e-05, "epoch": 1.4053905390539054, "percentage": 7.03, "elapsed_time": "0:29:51", "remaining_time": "6:35:09", "throughput": 1504.14, "total_tokens": 2695392} {"current_steps": 12780, "total_steps": 181800, "loss": 0.0656, "lr": 3.5145764576457644e-05, "epoch": 1.4059405940594059, "percentage": 7.03, "elapsed_time": "0:29:52", "remaining_time": "6:35:08", "throughput": 1504.14, "total_tokens": 2696416} {"current_steps": 12785, "total_steps": 181800, "loss": 0.131, "lr": 3.515951595159516e-05, "epoch": 1.4064906490649065, "percentage": 7.03, "elapsed_time": "0:29:53", "remaining_time": "6:35:07", "throughput": 1504.15, "total_tokens": 2697472} {"current_steps": 12790, "total_steps": 181800, "loss": 0.0566, "lr": 3.5173267326732674e-05, "epoch": 1.4070407040704072, "percentage": 7.04, "elapsed_time": "0:29:54", "remaining_time": "6:35:06", "throughput": 1504.11, "total_tokens": 2698432} {"current_steps": 12795, "total_steps": 181800, "loss": 0.2395, "lr": 3.518701870187019e-05, "epoch": 1.4075907590759076, "percentage": 7.04, "elapsed_time": "0:29:54", "remaining_time": "6:35:05", "throughput": 1504.11, "total_tokens": 2699456} {"current_steps": 12800, "total_steps": 181800, "loss": 0.1216, "lr": 3.52007700770077e-05, "epoch": 1.408140814081408, "percentage": 7.04, "elapsed_time": "0:29:55", "remaining_time": "6:35:05", "throughput": 1504.12, "total_tokens": 2700512} {"current_steps": 12805, "total_steps": 181800, "loss": 0.1194, "lr": 3.5214521452145215e-05, "epoch": 1.4086908690869087, "percentage": 7.04, "elapsed_time": "0:29:56", "remaining_time": "6:35:04", "throughput": 1504.11, "total_tokens": 2701536} {"current_steps": 12810, "total_steps": 181800, "loss": 0.0677, "lr": 3.5228272827282734e-05, "epoch": 1.4092409240924093, "percentage": 7.05, "elapsed_time": "0:29:56", "remaining_time": "6:35:03", "throughput": 1504.14, "total_tokens": 2702624} {"current_steps": 12815, "total_steps": 181800, "loss": 0.0777, "lr": 3.5242024202420245e-05, "epoch": 1.4097909790979097, "percentage": 7.05, "elapsed_time": "0:29:57", "remaining_time": "6:35:02", "throughput": 1504.17, "total_tokens": 2703712} {"current_steps": 12820, "total_steps": 181800, "loss": 0.1118, "lr": 3.525577557755776e-05, "epoch": 1.4103410341034104, "percentage": 7.05, "elapsed_time": "0:29:58", "remaining_time": "6:35:01", "throughput": 1504.15, "total_tokens": 2704704} {"current_steps": 12825, "total_steps": 181800, "loss": 0.1028, "lr": 3.526952695269527e-05, "epoch": 1.4108910891089108, "percentage": 7.05, "elapsed_time": "0:29:58", "remaining_time": "6:35:00", "throughput": 1504.16, "total_tokens": 2705760} {"current_steps": 12830, "total_steps": 181800, "loss": 0.073, "lr": 3.528327832783279e-05, "epoch": 1.4114411441144115, "percentage": 7.06, "elapsed_time": "0:29:59", "remaining_time": "6:34:59", "throughput": 1504.14, "total_tokens": 2706752} {"current_steps": 12835, "total_steps": 181800, "loss": 0.0592, "lr": 3.52970297029703e-05, "epoch": 1.411991199119912, "percentage": 7.06, "elapsed_time": "0:30:00", "remaining_time": "6:34:58", "throughput": 1504.15, "total_tokens": 2707808} {"current_steps": 12840, "total_steps": 181800, "loss": 0.0552, "lr": 3.531078107810781e-05, "epoch": 1.4125412541254125, "percentage": 7.06, "elapsed_time": "0:30:00", "remaining_time": "6:34:58", "throughput": 1504.12, "total_tokens": 2708800} {"current_steps": 12845, "total_steps": 181800, "loss": 0.0496, "lr": 3.532453245324532e-05, "epoch": 1.413091309130913, "percentage": 7.07, "elapsed_time": "0:30:01", "remaining_time": "6:34:57", "throughput": 1504.13, "total_tokens": 2709856} {"current_steps": 12850, "total_steps": 181800, "loss": 0.064, "lr": 3.533828382838284e-05, "epoch": 1.4136413641364136, "percentage": 7.07, "elapsed_time": "0:30:02", "remaining_time": "6:34:56", "throughput": 1504.14, "total_tokens": 2710912} {"current_steps": 12855, "total_steps": 181800, "loss": 0.0622, "lr": 3.535203520352036e-05, "epoch": 1.4141914191419143, "percentage": 7.07, "elapsed_time": "0:30:02", "remaining_time": "6:34:55", "throughput": 1504.13, "total_tokens": 2711936} {"current_steps": 12860, "total_steps": 181800, "loss": 0.1306, "lr": 3.5365786578657864e-05, "epoch": 1.4147414741474147, "percentage": 7.07, "elapsed_time": "0:30:03", "remaining_time": "6:34:54", "throughput": 1504.18, "total_tokens": 2713056} {"current_steps": 12865, "total_steps": 181800, "loss": 0.131, "lr": 3.537953795379538e-05, "epoch": 1.4152915291529153, "percentage": 7.08, "elapsed_time": "0:30:04", "remaining_time": "6:34:53", "throughput": 1504.24, "total_tokens": 2714208} {"current_steps": 12870, "total_steps": 181800, "loss": 0.1767, "lr": 3.5393289328932894e-05, "epoch": 1.4158415841584158, "percentage": 7.08, "elapsed_time": "0:30:05", "remaining_time": "6:34:52", "throughput": 1504.27, "total_tokens": 2715296} {"current_steps": 12875, "total_steps": 181800, "loss": 0.0883, "lr": 3.540704070407041e-05, "epoch": 1.4163916391639164, "percentage": 7.08, "elapsed_time": "0:30:05", "remaining_time": "6:34:52", "throughput": 1504.3, "total_tokens": 2716384} {"current_steps": 12880, "total_steps": 181800, "loss": 0.0713, "lr": 3.542079207920792e-05, "epoch": 1.416941694169417, "percentage": 7.08, "elapsed_time": "0:30:06", "remaining_time": "6:34:51", "throughput": 1504.3, "total_tokens": 2717408} {"current_steps": 12885, "total_steps": 181800, "loss": 0.0802, "lr": 3.5434543454345436e-05, "epoch": 1.4174917491749175, "percentage": 7.09, "elapsed_time": "0:30:07", "remaining_time": "6:34:50", "throughput": 1504.31, "total_tokens": 2718464} {"current_steps": 12890, "total_steps": 181800, "loss": 0.0576, "lr": 3.544829482948295e-05, "epoch": 1.418041804180418, "percentage": 7.09, "elapsed_time": "0:30:07", "remaining_time": "6:34:49", "throughput": 1504.34, "total_tokens": 2719552} {"current_steps": 12895, "total_steps": 181800, "loss": 0.0449, "lr": 3.5462046204620466e-05, "epoch": 1.4185918591859186, "percentage": 7.09, "elapsed_time": "0:30:08", "remaining_time": "6:34:48", "throughput": 1504.35, "total_tokens": 2720608} {"current_steps": 12900, "total_steps": 181800, "loss": 0.1143, "lr": 3.547579757975798e-05, "epoch": 1.4191419141914192, "percentage": 7.1, "elapsed_time": "0:30:09", "remaining_time": "6:34:47", "throughput": 1504.36, "total_tokens": 2721664} {"current_steps": 12905, "total_steps": 181800, "loss": 0.0595, "lr": 3.548954895489549e-05, "epoch": 1.4196919691969196, "percentage": 7.1, "elapsed_time": "0:30:09", "remaining_time": "6:34:46", "throughput": 1504.36, "total_tokens": 2722688} {"current_steps": 12910, "total_steps": 181800, "loss": 0.1587, "lr": 3.550330033003301e-05, "epoch": 1.4202420242024203, "percentage": 7.1, "elapsed_time": "0:30:10", "remaining_time": "6:34:45", "throughput": 1504.4, "total_tokens": 2723808} {"current_steps": 12915, "total_steps": 181800, "loss": 0.0427, "lr": 3.551705170517052e-05, "epoch": 1.4207920792079207, "percentage": 7.1, "elapsed_time": "0:30:11", "remaining_time": "6:34:45", "throughput": 1504.43, "total_tokens": 2724896} {"current_steps": 12920, "total_steps": 181800, "loss": 0.1105, "lr": 3.553080308030803e-05, "epoch": 1.4213421342134214, "percentage": 7.11, "elapsed_time": "0:30:11", "remaining_time": "6:34:44", "throughput": 1504.43, "total_tokens": 2725920} {"current_steps": 12925, "total_steps": 181800, "loss": 0.0782, "lr": 3.554455445544554e-05, "epoch": 1.421892189218922, "percentage": 7.11, "elapsed_time": "0:30:12", "remaining_time": "6:34:43", "throughput": 1504.44, "total_tokens": 2726976} {"current_steps": 12930, "total_steps": 181800, "loss": 0.1033, "lr": 3.555830583058306e-05, "epoch": 1.4224422442244224, "percentage": 7.11, "elapsed_time": "0:30:13", "remaining_time": "6:34:42", "throughput": 1504.44, "total_tokens": 2728032} {"current_steps": 12935, "total_steps": 181800, "loss": 0.1918, "lr": 3.557205720572057e-05, "epoch": 1.4229922992299229, "percentage": 7.11, "elapsed_time": "0:30:14", "remaining_time": "6:34:41", "throughput": 1504.44, "total_tokens": 2729056} {"current_steps": 12940, "total_steps": 181800, "loss": 0.1827, "lr": 3.558580858085809e-05, "epoch": 1.4235423542354235, "percentage": 7.12, "elapsed_time": "0:30:14", "remaining_time": "6:34:40", "throughput": 1504.45, "total_tokens": 2730112} {"current_steps": 12945, "total_steps": 181800, "loss": 0.0611, "lr": 3.55995599559956e-05, "epoch": 1.4240924092409242, "percentage": 7.12, "elapsed_time": "0:30:15", "remaining_time": "6:34:39", "throughput": 1504.48, "total_tokens": 2731200} {"current_steps": 12950, "total_steps": 181800, "loss": 0.1164, "lr": 3.5613311331133114e-05, "epoch": 1.4246424642464246, "percentage": 7.12, "elapsed_time": "0:30:16", "remaining_time": "6:34:38", "throughput": 1504.47, "total_tokens": 2732224} {"current_steps": 12955, "total_steps": 181800, "loss": 0.2333, "lr": 3.562706270627063e-05, "epoch": 1.4251925192519252, "percentage": 7.13, "elapsed_time": "0:30:16", "remaining_time": "6:34:38", "throughput": 1504.47, "total_tokens": 2733248} {"current_steps": 12960, "total_steps": 181800, "loss": 0.085, "lr": 3.5640814081408144e-05, "epoch": 1.4257425742574257, "percentage": 7.13, "elapsed_time": "0:30:17", "remaining_time": "6:34:37", "throughput": 1504.5, "total_tokens": 2734336} {"current_steps": 12965, "total_steps": 181800, "loss": 0.1161, "lr": 3.5654565456545656e-05, "epoch": 1.4262926292629263, "percentage": 7.13, "elapsed_time": "0:30:18", "remaining_time": "6:34:36", "throughput": 1504.53, "total_tokens": 2735424} {"current_steps": 12970, "total_steps": 181800, "loss": 0.1592, "lr": 3.566831683168317e-05, "epoch": 1.426842684268427, "percentage": 7.13, "elapsed_time": "0:30:18", "remaining_time": "6:34:35", "throughput": 1504.54, "total_tokens": 2736480} {"current_steps": 12975, "total_steps": 181800, "loss": 0.1057, "lr": 3.5682068206820686e-05, "epoch": 1.4273927392739274, "percentage": 7.14, "elapsed_time": "0:30:19", "remaining_time": "6:34:34", "throughput": 1504.52, "total_tokens": 2737472} {"current_steps": 12980, "total_steps": 181800, "loss": 0.0959, "lr": 3.56958195819582e-05, "epoch": 1.4279427942794278, "percentage": 7.14, "elapsed_time": "0:30:20", "remaining_time": "6:34:33", "throughput": 1504.57, "total_tokens": 2738592} {"current_steps": 12985, "total_steps": 181800, "loss": 0.1354, "lr": 3.570957095709571e-05, "epoch": 1.4284928492849285, "percentage": 7.14, "elapsed_time": "0:30:20", "remaining_time": "6:34:32", "throughput": 1504.57, "total_tokens": 2739616} {"current_steps": 12990, "total_steps": 181800, "loss": 0.0273, "lr": 3.572332233223323e-05, "epoch": 1.4290429042904291, "percentage": 7.15, "elapsed_time": "0:30:21", "remaining_time": "6:34:31", "throughput": 1504.54, "total_tokens": 2740608} {"current_steps": 12995, "total_steps": 181800, "loss": 0.0605, "lr": 3.573707370737074e-05, "epoch": 1.4295929592959296, "percentage": 7.15, "elapsed_time": "0:30:22", "remaining_time": "6:34:30", "throughput": 1504.59, "total_tokens": 2741728} {"current_steps": 13000, "total_steps": 181800, "loss": 0.1312, "lr": 3.575082508250826e-05, "epoch": 1.4301430143014302, "percentage": 7.15, "elapsed_time": "0:30:22", "remaining_time": "6:34:30", "throughput": 1504.58, "total_tokens": 2742752} {"current_steps": 13005, "total_steps": 181800, "loss": 0.0864, "lr": 3.576457645764576e-05, "epoch": 1.4306930693069306, "percentage": 7.15, "elapsed_time": "0:30:23", "remaining_time": "6:34:29", "throughput": 1504.59, "total_tokens": 2743808} {"current_steps": 13010, "total_steps": 181800, "loss": 0.0481, "lr": 3.577832783278328e-05, "epoch": 1.4312431243124313, "percentage": 7.16, "elapsed_time": "0:30:24", "remaining_time": "6:34:28", "throughput": 1504.6, "total_tokens": 2744864} {"current_steps": 13015, "total_steps": 181800, "loss": 0.1465, "lr": 3.579207920792079e-05, "epoch": 1.431793179317932, "percentage": 7.16, "elapsed_time": "0:30:25", "remaining_time": "6:34:27", "throughput": 1504.58, "total_tokens": 2745856} {"current_steps": 13020, "total_steps": 181800, "loss": 0.0456, "lr": 3.580583058305831e-05, "epoch": 1.4323432343234324, "percentage": 7.16, "elapsed_time": "0:30:25", "remaining_time": "6:34:26", "throughput": 1504.55, "total_tokens": 2746848} {"current_steps": 13025, "total_steps": 181800, "loss": 0.1513, "lr": 3.5819581958195816e-05, "epoch": 1.4328932893289328, "percentage": 7.16, "elapsed_time": "0:30:26", "remaining_time": "6:34:25", "throughput": 1504.56, "total_tokens": 2747904} {"current_steps": 13030, "total_steps": 181800, "loss": 0.0646, "lr": 3.5833333333333335e-05, "epoch": 1.4334433443344334, "percentage": 7.17, "elapsed_time": "0:30:27", "remaining_time": "6:34:24", "throughput": 1504.54, "total_tokens": 2748896} {"current_steps": 13035, "total_steps": 181800, "loss": 0.0477, "lr": 3.5847084708470846e-05, "epoch": 1.433993399339934, "percentage": 7.17, "elapsed_time": "0:30:27", "remaining_time": "6:34:24", "throughput": 1504.53, "total_tokens": 2749920} {"current_steps": 13040, "total_steps": 181800, "loss": 0.1264, "lr": 3.5860836083608365e-05, "epoch": 1.4345434543454345, "percentage": 7.17, "elapsed_time": "0:30:28", "remaining_time": "6:34:23", "throughput": 1504.53, "total_tokens": 2750944} {"current_steps": 13045, "total_steps": 181800, "loss": 0.1808, "lr": 3.5874587458745876e-05, "epoch": 1.4350935093509352, "percentage": 7.18, "elapsed_time": "0:30:29", "remaining_time": "6:34:22", "throughput": 1504.54, "total_tokens": 2752000} {"current_steps": 13050, "total_steps": 181800, "loss": 0.0638, "lr": 3.588833883388339e-05, "epoch": 1.4356435643564356, "percentage": 7.18, "elapsed_time": "0:30:29", "remaining_time": "6:34:21", "throughput": 1504.57, "total_tokens": 2753088} {"current_steps": 13055, "total_steps": 181800, "loss": 0.0568, "lr": 3.5902090209020907e-05, "epoch": 1.4361936193619362, "percentage": 7.18, "elapsed_time": "0:30:30", "remaining_time": "6:34:20", "throughput": 1504.6, "total_tokens": 2754176} {"current_steps": 13060, "total_steps": 181800, "loss": 0.1636, "lr": 3.591584158415842e-05, "epoch": 1.4367436743674367, "percentage": 7.18, "elapsed_time": "0:30:31", "remaining_time": "6:34:19", "throughput": 1504.62, "total_tokens": 2755264} {"current_steps": 13065, "total_steps": 181800, "loss": 0.1276, "lr": 3.592959295929593e-05, "epoch": 1.4372937293729373, "percentage": 7.19, "elapsed_time": "0:30:31", "remaining_time": "6:34:18", "throughput": 1504.64, "total_tokens": 2756320} {"current_steps": 13070, "total_steps": 181800, "loss": 0.1169, "lr": 3.594334433443344e-05, "epoch": 1.4378437843784377, "percentage": 7.19, "elapsed_time": "0:30:32", "remaining_time": "6:34:18", "throughput": 1504.68, "total_tokens": 2757440} {"current_steps": 13075, "total_steps": 181800, "loss": 0.0692, "lr": 3.595709570957096e-05, "epoch": 1.4383938393839384, "percentage": 7.19, "elapsed_time": "0:30:33", "remaining_time": "6:34:17", "throughput": 1504.7, "total_tokens": 2758496} {"current_steps": 13080, "total_steps": 181800, "loss": 0.0885, "lr": 3.597084708470847e-05, "epoch": 1.438943894389439, "percentage": 7.19, "elapsed_time": "0:30:33", "remaining_time": "6:34:16", "throughput": 1504.71, "total_tokens": 2759552} {"current_steps": 13085, "total_steps": 181800, "loss": 0.1323, "lr": 3.598459845984598e-05, "epoch": 1.4394939493949395, "percentage": 7.2, "elapsed_time": "0:30:34", "remaining_time": "6:34:15", "throughput": 1504.76, "total_tokens": 2760672} {"current_steps": 13090, "total_steps": 181800, "loss": 0.0932, "lr": 3.59983498349835e-05, "epoch": 1.4400440044004401, "percentage": 7.2, "elapsed_time": "0:30:35", "remaining_time": "6:34:14", "throughput": 1504.73, "total_tokens": 2761664} {"current_steps": 13095, "total_steps": 181800, "loss": 0.2093, "lr": 3.601210121012101e-05, "epoch": 1.4405940594059405, "percentage": 7.2, "elapsed_time": "0:30:36", "remaining_time": "6:34:13", "throughput": 1504.73, "total_tokens": 2762688} {"current_steps": 13100, "total_steps": 181800, "loss": 0.0781, "lr": 3.602585258525853e-05, "epoch": 1.4411441144114412, "percentage": 7.21, "elapsed_time": "0:30:36", "remaining_time": "6:34:12", "throughput": 1504.71, "total_tokens": 2763680} {"current_steps": 13105, "total_steps": 181800, "loss": 0.0602, "lr": 3.603960396039604e-05, "epoch": 1.4416941694169416, "percentage": 7.21, "elapsed_time": "0:30:37", "remaining_time": "6:34:11", "throughput": 1504.68, "total_tokens": 2764672} {"current_steps": 13110, "total_steps": 181800, "loss": 0.0965, "lr": 3.6053355335533555e-05, "epoch": 1.4422442244224423, "percentage": 7.21, "elapsed_time": "0:30:38", "remaining_time": "6:34:10", "throughput": 1504.73, "total_tokens": 2765792} {"current_steps": 13115, "total_steps": 181800, "loss": 0.2633, "lr": 3.606710671067107e-05, "epoch": 1.4427942794279427, "percentage": 7.21, "elapsed_time": "0:30:38", "remaining_time": "6:34:10", "throughput": 1504.72, "total_tokens": 2766816} {"current_steps": 13120, "total_steps": 181800, "loss": 0.0516, "lr": 3.6080858085808585e-05, "epoch": 1.4433443344334433, "percentage": 7.22, "elapsed_time": "0:30:39", "remaining_time": "6:34:09", "throughput": 1504.74, "total_tokens": 2767872} {"current_steps": 13125, "total_steps": 181800, "loss": 0.1175, "lr": 3.60946094609461e-05, "epoch": 1.443894389438944, "percentage": 7.22, "elapsed_time": "0:30:40", "remaining_time": "6:34:08", "throughput": 1504.75, "total_tokens": 2768928} {"current_steps": 13130, "total_steps": 181800, "loss": 0.0634, "lr": 3.610836083608361e-05, "epoch": 1.4444444444444444, "percentage": 7.22, "elapsed_time": "0:30:40", "remaining_time": "6:34:07", "throughput": 1504.74, "total_tokens": 2769952} {"current_steps": 13135, "total_steps": 181800, "loss": 0.1132, "lr": 3.612211221122113e-05, "epoch": 1.444994499449945, "percentage": 7.22, "elapsed_time": "0:30:41", "remaining_time": "6:34:06", "throughput": 1504.73, "total_tokens": 2770976} {"current_steps": 13140, "total_steps": 181800, "loss": 0.1672, "lr": 3.613586358635864e-05, "epoch": 1.4455445544554455, "percentage": 7.23, "elapsed_time": "0:30:42", "remaining_time": "6:34:05", "throughput": 1504.74, "total_tokens": 2772032} {"current_steps": 13145, "total_steps": 181800, "loss": 0.0564, "lr": 3.614961496149615e-05, "epoch": 1.4460946094609461, "percentage": 7.23, "elapsed_time": "0:30:42", "remaining_time": "6:34:04", "throughput": 1504.75, "total_tokens": 2773088} {"current_steps": 13150, "total_steps": 181800, "loss": 0.0875, "lr": 3.616336633663366e-05, "epoch": 1.4466446644664466, "percentage": 7.23, "elapsed_time": "0:30:43", "remaining_time": "6:34:04", "throughput": 1504.78, "total_tokens": 2774176} {"current_steps": 13155, "total_steps": 181800, "loss": 0.115, "lr": 3.617711771177118e-05, "epoch": 1.4471947194719472, "percentage": 7.24, "elapsed_time": "0:30:44", "remaining_time": "6:34:03", "throughput": 1504.76, "total_tokens": 2775168} {"current_steps": 13160, "total_steps": 181800, "loss": 0.0769, "lr": 3.619086908690869e-05, "epoch": 1.4477447744774476, "percentage": 7.24, "elapsed_time": "0:30:44", "remaining_time": "6:34:02", "throughput": 1504.75, "total_tokens": 2776192} {"current_steps": 13165, "total_steps": 181800, "loss": 0.1066, "lr": 3.620462046204621e-05, "epoch": 1.4482948294829483, "percentage": 7.24, "elapsed_time": "0:30:45", "remaining_time": "6:34:01", "throughput": 1504.73, "total_tokens": 2777184} {"current_steps": 13170, "total_steps": 181800, "loss": 0.1086, "lr": 3.6218371837183715e-05, "epoch": 1.448844884488449, "percentage": 7.24, "elapsed_time": "0:30:46", "remaining_time": "6:34:00", "throughput": 1504.74, "total_tokens": 2778240} {"current_steps": 13175, "total_steps": 181800, "loss": 0.0445, "lr": 3.6232123212321234e-05, "epoch": 1.4493949394939494, "percentage": 7.25, "elapsed_time": "0:30:47", "remaining_time": "6:33:59", "throughput": 1504.75, "total_tokens": 2779296} {"current_steps": 13180, "total_steps": 181800, "loss": 0.0952, "lr": 3.624587458745875e-05, "epoch": 1.44994499449945, "percentage": 7.25, "elapsed_time": "0:30:47", "remaining_time": "6:33:58", "throughput": 1504.75, "total_tokens": 2780320} {"current_steps": 13185, "total_steps": 181800, "loss": 0.1317, "lr": 3.6259625962596264e-05, "epoch": 1.4504950495049505, "percentage": 7.25, "elapsed_time": "0:30:48", "remaining_time": "6:33:57", "throughput": 1504.79, "total_tokens": 2781440} {"current_steps": 13190, "total_steps": 181800, "loss": 0.0862, "lr": 3.6273377337733775e-05, "epoch": 1.451045104510451, "percentage": 7.26, "elapsed_time": "0:30:49", "remaining_time": "6:33:56", "throughput": 1504.79, "total_tokens": 2782464} {"current_steps": 13195, "total_steps": 181800, "loss": 0.1145, "lr": 3.628712871287129e-05, "epoch": 1.4515951595159515, "percentage": 7.26, "elapsed_time": "0:30:49", "remaining_time": "6:33:56", "throughput": 1504.79, "total_tokens": 2783488} {"current_steps": 13200, "total_steps": 181800, "loss": 0.1708, "lr": 3.6300880088008806e-05, "epoch": 1.4521452145214522, "percentage": 7.26, "elapsed_time": "0:30:50", "remaining_time": "6:33:55", "throughput": 1504.82, "total_tokens": 2784576} {"current_steps": 13205, "total_steps": 181800, "loss": 0.0995, "lr": 3.631463146314632e-05, "epoch": 1.4526952695269526, "percentage": 7.26, "elapsed_time": "0:30:51", "remaining_time": "6:33:54", "throughput": 1504.83, "total_tokens": 2785632} {"current_steps": 13210, "total_steps": 181800, "loss": 0.1333, "lr": 3.632838283828383e-05, "epoch": 1.4532453245324533, "percentage": 7.27, "elapsed_time": "0:30:51", "remaining_time": "6:33:53", "throughput": 1504.8, "total_tokens": 2786624} {"current_steps": 13215, "total_steps": 181800, "loss": 0.1182, "lr": 3.634213421342134e-05, "epoch": 1.453795379537954, "percentage": 7.27, "elapsed_time": "0:30:52", "remaining_time": "6:33:52", "throughput": 1504.83, "total_tokens": 2787712} {"current_steps": 13220, "total_steps": 181800, "loss": 0.0669, "lr": 3.635588558855886e-05, "epoch": 1.4543454345434543, "percentage": 7.27, "elapsed_time": "0:30:53", "remaining_time": "6:33:51", "throughput": 1504.85, "total_tokens": 2788768} {"current_steps": 13225, "total_steps": 181800, "loss": 0.0832, "lr": 3.636963696369638e-05, "epoch": 1.4548954895489548, "percentage": 7.27, "elapsed_time": "0:30:53", "remaining_time": "6:33:50", "throughput": 1504.84, "total_tokens": 2789792} {"current_steps": 13230, "total_steps": 181800, "loss": 0.1374, "lr": 3.638338833883388e-05, "epoch": 1.4554455445544554, "percentage": 7.28, "elapsed_time": "0:30:54", "remaining_time": "6:33:49", "throughput": 1504.87, "total_tokens": 2790880} {"current_steps": 13235, "total_steps": 181800, "loss": 0.072, "lr": 3.63971397139714e-05, "epoch": 1.455995599559956, "percentage": 7.28, "elapsed_time": "0:30:55", "remaining_time": "6:33:49", "throughput": 1504.85, "total_tokens": 2791872} {"current_steps": 13240, "total_steps": 181800, "loss": 0.1677, "lr": 3.641089108910891e-05, "epoch": 1.4565456545654565, "percentage": 7.28, "elapsed_time": "0:30:55", "remaining_time": "6:33:48", "throughput": 1504.82, "total_tokens": 2792864} {"current_steps": 13245, "total_steps": 181800, "loss": 0.1619, "lr": 3.642464246424643e-05, "epoch": 1.4570957095709571, "percentage": 7.29, "elapsed_time": "0:30:56", "remaining_time": "6:33:47", "throughput": 1504.84, "total_tokens": 2793920} {"current_steps": 13250, "total_steps": 181800, "loss": 0.0929, "lr": 3.6438393839383936e-05, "epoch": 1.4576457645764576, "percentage": 7.29, "elapsed_time": "0:30:57", "remaining_time": "6:33:46", "throughput": 1504.87, "total_tokens": 2795008} {"current_steps": 13255, "total_steps": 181800, "loss": 0.1176, "lr": 3.6452145214521454e-05, "epoch": 1.4581958195819582, "percentage": 7.29, "elapsed_time": "0:30:58", "remaining_time": "6:33:45", "throughput": 1504.88, "total_tokens": 2796064} {"current_steps": 13260, "total_steps": 181800, "loss": 0.0422, "lr": 3.6465896589658966e-05, "epoch": 1.4587458745874589, "percentage": 7.29, "elapsed_time": "0:30:58", "remaining_time": "6:33:44", "throughput": 1504.89, "total_tokens": 2797120} {"current_steps": 13265, "total_steps": 181800, "loss": 0.0738, "lr": 3.6479647964796484e-05, "epoch": 1.4592959295929593, "percentage": 7.3, "elapsed_time": "0:30:59", "remaining_time": "6:33:43", "throughput": 1504.9, "total_tokens": 2798176} {"current_steps": 13270, "total_steps": 181800, "loss": 0.0939, "lr": 3.649339933993399e-05, "epoch": 1.4598459845984597, "percentage": 7.3, "elapsed_time": "0:31:00", "remaining_time": "6:33:42", "throughput": 1504.88, "total_tokens": 2799168} {"current_steps": 13275, "total_steps": 181800, "loss": 0.114, "lr": 3.650715071507151e-05, "epoch": 1.4603960396039604, "percentage": 7.3, "elapsed_time": "0:31:00", "remaining_time": "6:33:42", "throughput": 1504.87, "total_tokens": 2800192} {"current_steps": 13280, "total_steps": 181800, "loss": 0.1653, "lr": 3.6520902090209026e-05, "epoch": 1.460946094609461, "percentage": 7.3, "elapsed_time": "0:31:01", "remaining_time": "6:33:41", "throughput": 1504.9, "total_tokens": 2801280} {"current_steps": 13285, "total_steps": 181800, "loss": 0.1178, "lr": 3.653465346534654e-05, "epoch": 1.4614961496149614, "percentage": 7.31, "elapsed_time": "0:31:02", "remaining_time": "6:33:40", "throughput": 1504.91, "total_tokens": 2802336} {"current_steps": 13290, "total_steps": 181800, "loss": 0.1086, "lr": 3.654840484048405e-05, "epoch": 1.462046204620462, "percentage": 7.31, "elapsed_time": "0:31:02", "remaining_time": "6:33:39", "throughput": 1504.89, "total_tokens": 2803328} {"current_steps": 13295, "total_steps": 181800, "loss": 0.1185, "lr": 3.656215621562156e-05, "epoch": 1.4625962596259625, "percentage": 7.31, "elapsed_time": "0:31:03", "remaining_time": "6:33:38", "throughput": 1504.88, "total_tokens": 2804352} {"current_steps": 13300, "total_steps": 181800, "loss": 0.1012, "lr": 3.657590759075908e-05, "epoch": 1.4631463146314632, "percentage": 7.32, "elapsed_time": "0:31:04", "remaining_time": "6:33:37", "throughput": 1504.92, "total_tokens": 2805472} {"current_steps": 13305, "total_steps": 181800, "loss": 0.1026, "lr": 3.658965896589659e-05, "epoch": 1.4636963696369638, "percentage": 7.32, "elapsed_time": "0:31:04", "remaining_time": "6:33:36", "throughput": 1504.9, "total_tokens": 2806464} {"current_steps": 13310, "total_steps": 181800, "loss": 0.1002, "lr": 3.66034103410341e-05, "epoch": 1.4642464246424642, "percentage": 7.32, "elapsed_time": "0:31:05", "remaining_time": "6:33:36", "throughput": 1504.93, "total_tokens": 2807552} {"current_steps": 13315, "total_steps": 181800, "loss": 0.1649, "lr": 3.6617161716171614e-05, "epoch": 1.4647964796479647, "percentage": 7.32, "elapsed_time": "0:31:06", "remaining_time": "6:33:35", "throughput": 1504.98, "total_tokens": 2808672} {"current_steps": 13320, "total_steps": 181800, "loss": 0.0578, "lr": 3.663091309130913e-05, "epoch": 1.4653465346534653, "percentage": 7.33, "elapsed_time": "0:31:06", "remaining_time": "6:33:34", "throughput": 1504.97, "total_tokens": 2809696} {"current_steps": 13325, "total_steps": 181800, "loss": 0.1217, "lr": 3.664466446644665e-05, "epoch": 1.465896589658966, "percentage": 7.33, "elapsed_time": "0:31:07", "remaining_time": "6:33:33", "throughput": 1504.96, "total_tokens": 2810720} {"current_steps": 13330, "total_steps": 181800, "loss": 0.0732, "lr": 3.665841584158416e-05, "epoch": 1.4664466446644664, "percentage": 7.33, "elapsed_time": "0:31:08", "remaining_time": "6:33:32", "throughput": 1505.01, "total_tokens": 2811840} {"current_steps": 13335, "total_steps": 181800, "loss": 0.0797, "lr": 3.6672167216721674e-05, "epoch": 1.466996699669967, "percentage": 7.33, "elapsed_time": "0:31:09", "remaining_time": "6:33:31", "throughput": 1505.01, "total_tokens": 2812864} {"current_steps": 13340, "total_steps": 181800, "loss": 0.1024, "lr": 3.6685918591859186e-05, "epoch": 1.4675467546754675, "percentage": 7.34, "elapsed_time": "0:31:09", "remaining_time": "6:33:30", "throughput": 1505.02, "total_tokens": 2813920} {"current_steps": 13345, "total_steps": 181800, "loss": 0.1605, "lr": 3.6699669966996705e-05, "epoch": 1.4680968096809681, "percentage": 7.34, "elapsed_time": "0:31:10", "remaining_time": "6:33:29", "throughput": 1505.0, "total_tokens": 2814912} {"current_steps": 13350, "total_steps": 181800, "loss": 0.1275, "lr": 3.6713421342134216e-05, "epoch": 1.4686468646864688, "percentage": 7.34, "elapsed_time": "0:31:11", "remaining_time": "6:33:29", "throughput": 1505.06, "total_tokens": 2816064} {"current_steps": 13355, "total_steps": 181800, "loss": 0.1228, "lr": 3.672717271727173e-05, "epoch": 1.4691969196919692, "percentage": 7.35, "elapsed_time": "0:31:11", "remaining_time": "6:33:28", "throughput": 1505.11, "total_tokens": 2817184} {"current_steps": 13360, "total_steps": 181800, "loss": 0.1862, "lr": 3.674092409240924e-05, "epoch": 1.4697469746974696, "percentage": 7.35, "elapsed_time": "0:31:12", "remaining_time": "6:33:27", "throughput": 1505.12, "total_tokens": 2818240} {"current_steps": 13365, "total_steps": 181800, "loss": 0.1066, "lr": 3.675467546754676e-05, "epoch": 1.4702970297029703, "percentage": 7.35, "elapsed_time": "0:31:13", "remaining_time": "6:33:26", "throughput": 1505.11, "total_tokens": 2819264} {"current_steps": 13370, "total_steps": 181800, "loss": 0.0836, "lr": 3.676842684268427e-05, "epoch": 1.470847084708471, "percentage": 7.35, "elapsed_time": "0:31:13", "remaining_time": "6:33:25", "throughput": 1505.14, "total_tokens": 2820352} {"current_steps": 13375, "total_steps": 181800, "loss": 0.1667, "lr": 3.678217821782178e-05, "epoch": 1.4713971397139713, "percentage": 7.36, "elapsed_time": "0:31:14", "remaining_time": "6:33:24", "throughput": 1505.12, "total_tokens": 2821344} {"current_steps": 13380, "total_steps": 181800, "loss": 0.1718, "lr": 3.67959295929593e-05, "epoch": 1.471947194719472, "percentage": 7.36, "elapsed_time": "0:31:15", "remaining_time": "6:33:23", "throughput": 1505.11, "total_tokens": 2822368} {"current_steps": 13385, "total_steps": 181800, "loss": 0.1296, "lr": 3.680968096809681e-05, "epoch": 1.4724972497249724, "percentage": 7.36, "elapsed_time": "0:31:15", "remaining_time": "6:33:22", "throughput": 1505.12, "total_tokens": 2823424} {"current_steps": 13390, "total_steps": 181800, "loss": 0.082, "lr": 3.682343234323433e-05, "epoch": 1.473047304730473, "percentage": 7.37, "elapsed_time": "0:31:16", "remaining_time": "6:33:22", "throughput": 1505.15, "total_tokens": 2824512} {"current_steps": 13395, "total_steps": 181800, "loss": 0.0996, "lr": 3.6837183718371835e-05, "epoch": 1.4735973597359737, "percentage": 7.37, "elapsed_time": "0:31:17", "remaining_time": "6:33:21", "throughput": 1505.16, "total_tokens": 2825568} {"current_steps": 13400, "total_steps": 181800, "loss": 0.0477, "lr": 3.685093509350935e-05, "epoch": 1.4741474147414741, "percentage": 7.37, "elapsed_time": "0:31:17", "remaining_time": "6:33:20", "throughput": 1505.12, "total_tokens": 2826528} {"current_steps": 13405, "total_steps": 181800, "loss": 0.0902, "lr": 3.6864686468646865e-05, "epoch": 1.4746974697469746, "percentage": 7.37, "elapsed_time": "0:31:18", "remaining_time": "6:33:19", "throughput": 1505.16, "total_tokens": 2827648} {"current_steps": 13410, "total_steps": 181800, "loss": 0.1316, "lr": 3.687843784378438e-05, "epoch": 1.4752475247524752, "percentage": 7.38, "elapsed_time": "0:31:19", "remaining_time": "6:33:18", "throughput": 1505.15, "total_tokens": 2828672} {"current_steps": 13415, "total_steps": 181800, "loss": 0.1643, "lr": 3.6892189218921895e-05, "epoch": 1.4757975797579759, "percentage": 7.38, "elapsed_time": "0:31:20", "remaining_time": "6:33:17", "throughput": 1505.18, "total_tokens": 2829760} {"current_steps": 13420, "total_steps": 181800, "loss": 0.1419, "lr": 3.6905940594059406e-05, "epoch": 1.4763476347634763, "percentage": 7.38, "elapsed_time": "0:31:20", "remaining_time": "6:33:17", "throughput": 1505.18, "total_tokens": 2830784} {"current_steps": 13425, "total_steps": 181800, "loss": 0.0825, "lr": 3.6919691969196925e-05, "epoch": 1.476897689768977, "percentage": 7.38, "elapsed_time": "0:31:21", "remaining_time": "6:33:16", "throughput": 1505.15, "total_tokens": 2831776} {"current_steps": 13430, "total_steps": 181800, "loss": 0.1164, "lr": 3.6933443344334437e-05, "epoch": 1.4774477447744774, "percentage": 7.39, "elapsed_time": "0:31:22", "remaining_time": "6:33:15", "throughput": 1505.15, "total_tokens": 2832800} {"current_steps": 13435, "total_steps": 181800, "loss": 0.1161, "lr": 3.694719471947195e-05, "epoch": 1.477997799779978, "percentage": 7.39, "elapsed_time": "0:31:22", "remaining_time": "6:33:14", "throughput": 1505.16, "total_tokens": 2833856} {"current_steps": 13440, "total_steps": 181800, "loss": 0.1757, "lr": 3.696094609460946e-05, "epoch": 1.4785478547854787, "percentage": 7.39, "elapsed_time": "0:31:23", "remaining_time": "6:33:13", "throughput": 1505.14, "total_tokens": 2834848} {"current_steps": 13445, "total_steps": 181800, "loss": 0.1797, "lr": 3.697469746974698e-05, "epoch": 1.479097909790979, "percentage": 7.4, "elapsed_time": "0:31:24", "remaining_time": "6:33:12", "throughput": 1505.18, "total_tokens": 2835968} {"current_steps": 13450, "total_steps": 181800, "loss": 0.0903, "lr": 3.698844884488449e-05, "epoch": 1.4796479647964795, "percentage": 7.4, "elapsed_time": "0:31:24", "remaining_time": "6:33:11", "throughput": 1505.2, "total_tokens": 2837024} {"current_steps": 13455, "total_steps": 181800, "loss": 0.1097, "lr": 3.7002200220022e-05, "epoch": 1.4801980198019802, "percentage": 7.4, "elapsed_time": "0:31:25", "remaining_time": "6:33:10", "throughput": 1505.24, "total_tokens": 2838144} {"current_steps": 13460, "total_steps": 181800, "loss": 0.2211, "lr": 3.701595159515952e-05, "epoch": 1.4807480748074808, "percentage": 7.4, "elapsed_time": "0:31:26", "remaining_time": "6:33:10", "throughput": 1505.25, "total_tokens": 2839200} {"current_steps": 13465, "total_steps": 181800, "loss": 0.158, "lr": 3.702970297029703e-05, "epoch": 1.4812981298129813, "percentage": 7.41, "elapsed_time": "0:31:26", "remaining_time": "6:33:09", "throughput": 1505.26, "total_tokens": 2840256} {"current_steps": 13470, "total_steps": 181800, "loss": 0.1678, "lr": 3.704345434543455e-05, "epoch": 1.481848184818482, "percentage": 7.41, "elapsed_time": "0:31:27", "remaining_time": "6:33:08", "throughput": 1505.31, "total_tokens": 2841376} {"current_steps": 13475, "total_steps": 181800, "loss": 0.0946, "lr": 3.7057205720572055e-05, "epoch": 1.4823982398239823, "percentage": 7.41, "elapsed_time": "0:31:28", "remaining_time": "6:33:07", "throughput": 1505.3, "total_tokens": 2842400} {"current_steps": 13480, "total_steps": 181800, "loss": 0.1894, "lr": 3.7070957095709573e-05, "epoch": 1.482948294829483, "percentage": 7.41, "elapsed_time": "0:31:28", "remaining_time": "6:33:06", "throughput": 1505.28, "total_tokens": 2843392} {"current_steps": 13485, "total_steps": 181800, "loss": 0.1451, "lr": 3.7084708470847085e-05, "epoch": 1.4834983498349836, "percentage": 7.42, "elapsed_time": "0:31:29", "remaining_time": "6:33:05", "throughput": 1505.28, "total_tokens": 2844416} {"current_steps": 13490, "total_steps": 181800, "loss": 0.1232, "lr": 3.7098459845984604e-05, "epoch": 1.484048404840484, "percentage": 7.42, "elapsed_time": "0:31:30", "remaining_time": "6:33:04", "throughput": 1505.31, "total_tokens": 2845504} {"current_steps": 13495, "total_steps": 181800, "loss": 0.0658, "lr": 3.7112211221122115e-05, "epoch": 1.4845984598459845, "percentage": 7.42, "elapsed_time": "0:31:31", "remaining_time": "6:33:03", "throughput": 1505.32, "total_tokens": 2846560} {"current_steps": 13500, "total_steps": 181800, "loss": 0.0726, "lr": 3.712596259625963e-05, "epoch": 1.4851485148514851, "percentage": 7.43, "elapsed_time": "0:31:31", "remaining_time": "6:33:03", "throughput": 1505.34, "total_tokens": 2847648} {"current_steps": 13505, "total_steps": 181800, "loss": 0.1296, "lr": 3.7139713971397145e-05, "epoch": 1.4856985698569858, "percentage": 7.43, "elapsed_time": "0:31:32", "remaining_time": "6:33:02", "throughput": 1505.39, "total_tokens": 2848768} {"current_steps": 13510, "total_steps": 181800, "loss": 0.1224, "lr": 3.715346534653466e-05, "epoch": 1.4862486248624862, "percentage": 7.43, "elapsed_time": "0:31:33", "remaining_time": "6:33:01", "throughput": 1505.39, "total_tokens": 2849792} {"current_steps": 13515, "total_steps": 181800, "loss": 0.1015, "lr": 3.716721672167217e-05, "epoch": 1.4867986798679869, "percentage": 7.43, "elapsed_time": "0:31:33", "remaining_time": "6:33:00", "throughput": 1505.41, "total_tokens": 2850880} {"current_steps": 13520, "total_steps": 181800, "loss": 0.1308, "lr": 3.718096809680968e-05, "epoch": 1.4873487348734873, "percentage": 7.44, "elapsed_time": "0:31:34", "remaining_time": "6:32:59", "throughput": 1505.42, "total_tokens": 2851936} {"current_steps": 13525, "total_steps": 181800, "loss": 0.0745, "lr": 3.71947194719472e-05, "epoch": 1.487898789878988, "percentage": 7.44, "elapsed_time": "0:31:35", "remaining_time": "6:32:58", "throughput": 1505.4, "total_tokens": 2852928} {"current_steps": 13530, "total_steps": 181800, "loss": 0.2813, "lr": 3.720847084708471e-05, "epoch": 1.4884488448844886, "percentage": 7.44, "elapsed_time": "0:31:35", "remaining_time": "6:32:57", "throughput": 1505.41, "total_tokens": 2853984} {"current_steps": 13535, "total_steps": 181800, "loss": 0.0818, "lr": 3.722222222222222e-05, "epoch": 1.488998899889989, "percentage": 7.44, "elapsed_time": "0:31:36", "remaining_time": "6:32:57", "throughput": 1505.42, "total_tokens": 2855040} {"current_steps": 13540, "total_steps": 181800, "loss": 0.1641, "lr": 3.7235973597359734e-05, "epoch": 1.4895489548954894, "percentage": 7.45, "elapsed_time": "0:31:37", "remaining_time": "6:32:56", "throughput": 1505.4, "total_tokens": 2856032} {"current_steps": 13545, "total_steps": 181800, "loss": 0.1738, "lr": 3.724972497249725e-05, "epoch": 1.49009900990099, "percentage": 7.45, "elapsed_time": "0:31:37", "remaining_time": "6:32:55", "throughput": 1505.41, "total_tokens": 2857088} {"current_steps": 13550, "total_steps": 181800, "loss": 0.0644, "lr": 3.7263476347634764e-05, "epoch": 1.4906490649064907, "percentage": 7.45, "elapsed_time": "0:31:38", "remaining_time": "6:32:54", "throughput": 1505.44, "total_tokens": 2858176} {"current_steps": 13555, "total_steps": 181800, "loss": 0.0949, "lr": 3.727722772277228e-05, "epoch": 1.4911991199119912, "percentage": 7.46, "elapsed_time": "0:31:39", "remaining_time": "6:32:53", "throughput": 1505.45, "total_tokens": 2859232} {"current_steps": 13560, "total_steps": 181800, "loss": 0.1078, "lr": 3.7290979097909794e-05, "epoch": 1.4917491749174918, "percentage": 7.46, "elapsed_time": "0:31:39", "remaining_time": "6:32:52", "throughput": 1505.47, "total_tokens": 2860288} {"current_steps": 13565, "total_steps": 181800, "loss": 0.0525, "lr": 3.7304730473047305e-05, "epoch": 1.4922992299229922, "percentage": 7.46, "elapsed_time": "0:31:40", "remaining_time": "6:32:51", "throughput": 1505.46, "total_tokens": 2861312} {"current_steps": 13570, "total_steps": 181800, "loss": 0.078, "lr": 3.7318481848184824e-05, "epoch": 1.492849284928493, "percentage": 7.46, "elapsed_time": "0:31:41", "remaining_time": "6:32:50", "throughput": 1505.47, "total_tokens": 2862368} {"current_steps": 13575, "total_steps": 181800, "loss": 0.1823, "lr": 3.7332233223322336e-05, "epoch": 1.4933993399339933, "percentage": 7.47, "elapsed_time": "0:31:42", "remaining_time": "6:32:50", "throughput": 1505.46, "total_tokens": 2863392} {"current_steps": 13580, "total_steps": 181800, "loss": 0.0892, "lr": 3.734598459845985e-05, "epoch": 1.493949394939494, "percentage": 7.47, "elapsed_time": "0:31:42", "remaining_time": "6:32:49", "throughput": 1505.49, "total_tokens": 2864480} {"current_steps": 13585, "total_steps": 181800, "loss": 0.1038, "lr": 3.735973597359736e-05, "epoch": 1.4944994499449944, "percentage": 7.47, "elapsed_time": "0:31:43", "remaining_time": "6:32:48", "throughput": 1505.48, "total_tokens": 2865504} {"current_steps": 13590, "total_steps": 181800, "loss": 0.0485, "lr": 3.737348734873488e-05, "epoch": 1.495049504950495, "percentage": 7.48, "elapsed_time": "0:31:44", "remaining_time": "6:32:47", "throughput": 1505.49, "total_tokens": 2866560} {"current_steps": 13595, "total_steps": 181800, "loss": 0.1613, "lr": 3.738723872387239e-05, "epoch": 1.4955995599559957, "percentage": 7.48, "elapsed_time": "0:31:44", "remaining_time": "6:32:46", "throughput": 1505.53, "total_tokens": 2867680} {"current_steps": 13600, "total_steps": 181800, "loss": 0.1406, "lr": 3.74009900990099e-05, "epoch": 1.4961496149614961, "percentage": 7.48, "elapsed_time": "0:31:45", "remaining_time": "6:32:45", "throughput": 1505.54, "total_tokens": 2868736} {"current_steps": 13605, "total_steps": 181800, "loss": 0.0524, "lr": 3.741474147414742e-05, "epoch": 1.4966996699669968, "percentage": 7.48, "elapsed_time": "0:31:46", "remaining_time": "6:32:45", "throughput": 1505.56, "total_tokens": 2869824} {"current_steps": 13610, "total_steps": 181800, "loss": 0.1474, "lr": 3.742849284928493e-05, "epoch": 1.4972497249724972, "percentage": 7.49, "elapsed_time": "0:31:46", "remaining_time": "6:32:44", "throughput": 1505.59, "total_tokens": 2870912} {"current_steps": 13615, "total_steps": 181800, "loss": 0.0661, "lr": 3.744224422442245e-05, "epoch": 1.4977997799779978, "percentage": 7.49, "elapsed_time": "0:31:47", "remaining_time": "6:32:43", "throughput": 1505.59, "total_tokens": 2871936} {"current_steps": 13620, "total_steps": 181800, "loss": 0.0462, "lr": 3.7455995599559954e-05, "epoch": 1.4983498349834983, "percentage": 7.49, "elapsed_time": "0:31:48", "remaining_time": "6:32:42", "throughput": 1505.61, "total_tokens": 2873024} {"current_steps": 13625, "total_steps": 181800, "loss": 0.152, "lr": 3.746974697469747e-05, "epoch": 1.498899889988999, "percentage": 7.49, "elapsed_time": "0:31:48", "remaining_time": "6:32:41", "throughput": 1505.61, "total_tokens": 2874048} {"current_steps": 13630, "total_steps": 181800, "loss": 0.0987, "lr": 3.7483498349834984e-05, "epoch": 1.4994499449944994, "percentage": 7.5, "elapsed_time": "0:31:49", "remaining_time": "6:32:40", "throughput": 1505.63, "total_tokens": 2875136} {"current_steps": 13635, "total_steps": 181800, "loss": 0.2171, "lr": 3.74972497249725e-05, "epoch": 1.5, "percentage": 7.5, "elapsed_time": "0:31:50", "remaining_time": "6:32:40", "throughput": 1505.66, "total_tokens": 2876224} {"current_steps": 13640, "total_steps": 181800, "loss": 0.0821, "lr": 3.751100110011001e-05, "epoch": 1.5005500550055006, "percentage": 7.5, "elapsed_time": "0:31:50", "remaining_time": "6:32:39", "throughput": 1505.65, "total_tokens": 2877248} {"current_steps": 13645, "total_steps": 181800, "loss": 0.1127, "lr": 3.7524752475247526e-05, "epoch": 1.501100110011001, "percentage": 7.51, "elapsed_time": "0:31:51", "remaining_time": "6:32:38", "throughput": 1505.68, "total_tokens": 2878336} {"current_steps": 13650, "total_steps": 181800, "loss": 0.1198, "lr": 3.7538503850385044e-05, "epoch": 1.5016501650165015, "percentage": 7.51, "elapsed_time": "0:31:52", "remaining_time": "6:32:37", "throughput": 1505.67, "total_tokens": 2879360} {"current_steps": 13655, "total_steps": 181800, "loss": 0.094, "lr": 3.7552255225522556e-05, "epoch": 1.5022002200220022, "percentage": 7.51, "elapsed_time": "0:31:53", "remaining_time": "6:32:36", "throughput": 1505.68, "total_tokens": 2880416} {"current_steps": 13660, "total_steps": 181800, "loss": 0.1136, "lr": 3.756600660066007e-05, "epoch": 1.5027502750275028, "percentage": 7.51, "elapsed_time": "0:31:53", "remaining_time": "6:32:35", "throughput": 1505.71, "total_tokens": 2881504} {"current_steps": 13665, "total_steps": 181800, "loss": 0.0597, "lr": 3.757975797579758e-05, "epoch": 1.5033003300330035, "percentage": 7.52, "elapsed_time": "0:31:54", "remaining_time": "6:32:35", "throughput": 1505.7, "total_tokens": 2882528} {"current_steps": 13670, "total_steps": 181800, "loss": 0.0695, "lr": 3.75935093509351e-05, "epoch": 1.5038503850385039, "percentage": 7.52, "elapsed_time": "0:31:55", "remaining_time": "6:32:34", "throughput": 1505.73, "total_tokens": 2883616} {"current_steps": 13675, "total_steps": 181800, "loss": 0.1347, "lr": 3.760726072607261e-05, "epoch": 1.5044004400440043, "percentage": 7.52, "elapsed_time": "0:31:55", "remaining_time": "6:32:33", "throughput": 1505.78, "total_tokens": 2884736} {"current_steps": 13680, "total_steps": 181800, "loss": 0.0694, "lr": 3.762101210121012e-05, "epoch": 1.504950495049505, "percentage": 7.52, "elapsed_time": "0:31:56", "remaining_time": "6:32:32", "throughput": 1505.77, "total_tokens": 2885760} {"current_steps": 13685, "total_steps": 181800, "loss": 0.1048, "lr": 3.763476347634763e-05, "epoch": 1.5055005500550056, "percentage": 7.53, "elapsed_time": "0:31:57", "remaining_time": "6:32:31", "throughput": 1505.8, "total_tokens": 2886848} {"current_steps": 13690, "total_steps": 181800, "loss": 0.1222, "lr": 3.764851485148515e-05, "epoch": 1.506050605060506, "percentage": 7.53, "elapsed_time": "0:31:57", "remaining_time": "6:32:30", "throughput": 1505.8, "total_tokens": 2887904} {"current_steps": 13695, "total_steps": 181800, "loss": 0.0989, "lr": 3.766226622662267e-05, "epoch": 1.5066006600660065, "percentage": 7.53, "elapsed_time": "0:31:58", "remaining_time": "6:32:29", "throughput": 1505.85, "total_tokens": 2889024} {"current_steps": 13700, "total_steps": 181800, "loss": 0.1493, "lr": 3.7676017601760174e-05, "epoch": 1.507150715071507, "percentage": 7.54, "elapsed_time": "0:31:59", "remaining_time": "6:32:29", "throughput": 1505.86, "total_tokens": 2890080} {"current_steps": 13705, "total_steps": 181800, "loss": 0.1124, "lr": 3.768976897689769e-05, "epoch": 1.5077007700770078, "percentage": 7.54, "elapsed_time": "0:31:59", "remaining_time": "6:32:28", "throughput": 1505.85, "total_tokens": 2891104} {"current_steps": 13710, "total_steps": 181800, "loss": 0.0848, "lr": 3.7703520352035204e-05, "epoch": 1.5082508250825084, "percentage": 7.54, "elapsed_time": "0:32:00", "remaining_time": "6:32:27", "throughput": 1505.84, "total_tokens": 2892128} {"current_steps": 13715, "total_steps": 181800, "loss": 0.0723, "lr": 3.771727172717272e-05, "epoch": 1.5088008800880088, "percentage": 7.54, "elapsed_time": "0:32:01", "remaining_time": "6:32:26", "throughput": 1505.81, "total_tokens": 2893120} {"current_steps": 13720, "total_steps": 181800, "loss": 0.1018, "lr": 3.7731023102310235e-05, "epoch": 1.5093509350935093, "percentage": 7.55, "elapsed_time": "0:32:01", "remaining_time": "6:32:25", "throughput": 1505.82, "total_tokens": 2894176} {"current_steps": 13725, "total_steps": 181800, "loss": 0.1281, "lr": 3.7744774477447746e-05, "epoch": 1.50990099009901, "percentage": 7.55, "elapsed_time": "0:32:02", "remaining_time": "6:32:24", "throughput": 1505.86, "total_tokens": 2895296} {"current_steps": 13730, "total_steps": 181800, "loss": 0.0686, "lr": 3.775852585258526e-05, "epoch": 1.5104510451045106, "percentage": 7.55, "elapsed_time": "0:32:03", "remaining_time": "6:32:24", "throughput": 1505.88, "total_tokens": 2896352} {"current_steps": 13735, "total_steps": 181800, "loss": 0.1157, "lr": 3.7772277227722776e-05, "epoch": 1.511001100110011, "percentage": 7.56, "elapsed_time": "0:32:04", "remaining_time": "6:32:23", "throughput": 1505.89, "total_tokens": 2897408} {"current_steps": 13740, "total_steps": 181800, "loss": 0.1589, "lr": 3.778602860286029e-05, "epoch": 1.5115511551155114, "percentage": 7.56, "elapsed_time": "0:32:04", "remaining_time": "6:32:22", "throughput": 1505.93, "total_tokens": 2898528} {"current_steps": 13745, "total_steps": 181800, "loss": 0.2401, "lr": 3.77997799779978e-05, "epoch": 1.512101210121012, "percentage": 7.56, "elapsed_time": "0:32:05", "remaining_time": "6:32:21", "throughput": 1505.96, "total_tokens": 2899616} {"current_steps": 13750, "total_steps": 181800, "loss": 0.0881, "lr": 3.781353135313532e-05, "epoch": 1.5126512651265127, "percentage": 7.56, "elapsed_time": "0:32:06", "remaining_time": "6:32:20", "throughput": 1505.94, "total_tokens": 2900608} {"current_steps": 13755, "total_steps": 181800, "loss": 0.1028, "lr": 3.782728272827283e-05, "epoch": 1.5132013201320134, "percentage": 7.57, "elapsed_time": "0:32:06", "remaining_time": "6:32:19", "throughput": 1505.91, "total_tokens": 2901600} {"current_steps": 13760, "total_steps": 181800, "loss": 0.1439, "lr": 3.784103410341034e-05, "epoch": 1.5137513751375138, "percentage": 7.57, "elapsed_time": "0:32:07", "remaining_time": "6:32:18", "throughput": 1505.89, "total_tokens": 2902592} {"current_steps": 13765, "total_steps": 181800, "loss": 0.107, "lr": 3.785478547854785e-05, "epoch": 1.5143014301430142, "percentage": 7.57, "elapsed_time": "0:32:08", "remaining_time": "6:32:18", "throughput": 1505.9, "total_tokens": 2903648} {"current_steps": 13770, "total_steps": 181800, "loss": 0.0919, "lr": 3.786853685368537e-05, "epoch": 1.5148514851485149, "percentage": 7.57, "elapsed_time": "0:32:08", "remaining_time": "6:32:17", "throughput": 1505.91, "total_tokens": 2904704} {"current_steps": 13775, "total_steps": 181800, "loss": 0.0757, "lr": 3.788228822882288e-05, "epoch": 1.5154015401540155, "percentage": 7.58, "elapsed_time": "0:32:09", "remaining_time": "6:32:16", "throughput": 1505.9, "total_tokens": 2905728} {"current_steps": 13780, "total_steps": 181800, "loss": 0.032, "lr": 3.78960396039604e-05, "epoch": 1.515951595159516, "percentage": 7.58, "elapsed_time": "0:32:10", "remaining_time": "6:32:15", "throughput": 1505.92, "total_tokens": 2906784} {"current_steps": 13785, "total_steps": 181800, "loss": 0.0442, "lr": 3.7909790979097906e-05, "epoch": 1.5165016501650164, "percentage": 7.58, "elapsed_time": "0:32:10", "remaining_time": "6:32:14", "throughput": 1505.93, "total_tokens": 2907840} {"current_steps": 13790, "total_steps": 181800, "loss": 0.0403, "lr": 3.7923542354235425e-05, "epoch": 1.517051705170517, "percentage": 7.59, "elapsed_time": "0:32:11", "remaining_time": "6:32:13", "throughput": 1505.96, "total_tokens": 2908928} {"current_steps": 13795, "total_steps": 181800, "loss": 0.1594, "lr": 3.793729372937294e-05, "epoch": 1.5176017601760177, "percentage": 7.59, "elapsed_time": "0:32:12", "remaining_time": "6:32:12", "throughput": 1505.97, "total_tokens": 2909984} {"current_steps": 13800, "total_steps": 181800, "loss": 0.1004, "lr": 3.7951045104510455e-05, "epoch": 1.5181518151815183, "percentage": 7.59, "elapsed_time": "0:32:12", "remaining_time": "6:32:12", "throughput": 1505.94, "total_tokens": 2910976} {"current_steps": 13805, "total_steps": 181800, "loss": 0.1813, "lr": 3.7964796479647967e-05, "epoch": 1.5187018701870187, "percentage": 7.59, "elapsed_time": "0:32:13", "remaining_time": "6:32:11", "throughput": 1505.95, "total_tokens": 2912032} {"current_steps": 13810, "total_steps": 181800, "loss": 0.0734, "lr": 3.797854785478548e-05, "epoch": 1.5192519251925192, "percentage": 7.6, "elapsed_time": "0:32:14", "remaining_time": "6:32:10", "throughput": 1505.97, "total_tokens": 2913088} {"current_steps": 13815, "total_steps": 181800, "loss": 0.2254, "lr": 3.7992299229923e-05, "epoch": 1.5198019801980198, "percentage": 7.6, "elapsed_time": "0:32:15", "remaining_time": "6:32:09", "throughput": 1505.97, "total_tokens": 2914144} {"current_steps": 13820, "total_steps": 181800, "loss": 0.1232, "lr": 3.800605060506051e-05, "epoch": 1.5203520352035205, "percentage": 7.6, "elapsed_time": "0:32:15", "remaining_time": "6:32:08", "throughput": 1506.0, "total_tokens": 2915232} {"current_steps": 13825, "total_steps": 181800, "loss": 0.1099, "lr": 3.801980198019802e-05, "epoch": 1.520902090209021, "percentage": 7.6, "elapsed_time": "0:32:16", "remaining_time": "6:32:07", "throughput": 1506.01, "total_tokens": 2916288} {"current_steps": 13830, "total_steps": 181800, "loss": 0.1241, "lr": 3.803355335533553e-05, "epoch": 1.5214521452145213, "percentage": 7.61, "elapsed_time": "0:32:17", "remaining_time": "6:32:07", "throughput": 1506.03, "total_tokens": 2917376} {"current_steps": 13835, "total_steps": 181800, "loss": 0.1446, "lr": 3.804730473047305e-05, "epoch": 1.522002200220022, "percentage": 7.61, "elapsed_time": "0:32:17", "remaining_time": "6:32:06", "throughput": 1506.04, "total_tokens": 2918432} {"current_steps": 13840, "total_steps": 181800, "loss": 0.1155, "lr": 3.806105610561057e-05, "epoch": 1.5225522552255226, "percentage": 7.61, "elapsed_time": "0:32:18", "remaining_time": "6:32:05", "throughput": 1506.09, "total_tokens": 2919552} {"current_steps": 13845, "total_steps": 181800, "loss": 0.14, "lr": 3.807480748074807e-05, "epoch": 1.523102310231023, "percentage": 7.62, "elapsed_time": "0:32:19", "remaining_time": "6:32:04", "throughput": 1506.11, "total_tokens": 2920640} {"current_steps": 13850, "total_steps": 181800, "loss": 0.11, "lr": 3.808855885588559e-05, "epoch": 1.5236523652365237, "percentage": 7.62, "elapsed_time": "0:32:19", "remaining_time": "6:32:03", "throughput": 1506.12, "total_tokens": 2921696} {"current_steps": 13855, "total_steps": 181800, "loss": 0.0856, "lr": 3.8102310231023103e-05, "epoch": 1.5242024202420241, "percentage": 7.62, "elapsed_time": "0:32:20", "remaining_time": "6:32:02", "throughput": 1506.12, "total_tokens": 2922720} {"current_steps": 13860, "total_steps": 181800, "loss": 0.1189, "lr": 3.811606160616062e-05, "epoch": 1.5247524752475248, "percentage": 7.62, "elapsed_time": "0:32:21", "remaining_time": "6:32:01", "throughput": 1506.13, "total_tokens": 2923776} {"current_steps": 13865, "total_steps": 181800, "loss": 0.0378, "lr": 3.812981298129813e-05, "epoch": 1.5253025302530254, "percentage": 7.63, "elapsed_time": "0:32:21", "remaining_time": "6:32:01", "throughput": 1506.11, "total_tokens": 2924768} {"current_steps": 13870, "total_steps": 181800, "loss": 0.0688, "lr": 3.8143564356435645e-05, "epoch": 1.5258525852585259, "percentage": 7.63, "elapsed_time": "0:32:22", "remaining_time": "6:32:00", "throughput": 1506.14, "total_tokens": 2925856} {"current_steps": 13875, "total_steps": 181800, "loss": 0.1236, "lr": 3.815731573157316e-05, "epoch": 1.5264026402640263, "percentage": 7.63, "elapsed_time": "0:32:23", "remaining_time": "6:31:59", "throughput": 1506.18, "total_tokens": 2926976} {"current_steps": 13880, "total_steps": 181800, "loss": 0.155, "lr": 3.8171067106710675e-05, "epoch": 1.526952695269527, "percentage": 7.63, "elapsed_time": "0:32:23", "remaining_time": "6:31:58", "throughput": 1506.17, "total_tokens": 2928000} {"current_steps": 13885, "total_steps": 181800, "loss": 0.041, "lr": 3.818481848184819e-05, "epoch": 1.5275027502750276, "percentage": 7.64, "elapsed_time": "0:32:24", "remaining_time": "6:31:57", "throughput": 1506.18, "total_tokens": 2929056} {"current_steps": 13890, "total_steps": 181800, "loss": 0.1448, "lr": 3.81985698569857e-05, "epoch": 1.528052805280528, "percentage": 7.64, "elapsed_time": "0:32:25", "remaining_time": "6:31:56", "throughput": 1506.24, "total_tokens": 2930208} {"current_steps": 13895, "total_steps": 181800, "loss": 0.0381, "lr": 3.821232123212322e-05, "epoch": 1.5286028602860287, "percentage": 7.64, "elapsed_time": "0:32:26", "remaining_time": "6:31:55", "throughput": 1506.22, "total_tokens": 2931200} {"current_steps": 13900, "total_steps": 181800, "loss": 0.2064, "lr": 3.822607260726073e-05, "epoch": 1.529152915291529, "percentage": 7.65, "elapsed_time": "0:32:26", "remaining_time": "6:31:55", "throughput": 1506.25, "total_tokens": 2932288} {"current_steps": 13905, "total_steps": 181800, "loss": 0.1222, "lr": 3.823982398239824e-05, "epoch": 1.5297029702970297, "percentage": 7.65, "elapsed_time": "0:32:27", "remaining_time": "6:31:54", "throughput": 1506.22, "total_tokens": 2933280} {"current_steps": 13910, "total_steps": 181800, "loss": 0.1395, "lr": 3.825357535753575e-05, "epoch": 1.5302530253025304, "percentage": 7.65, "elapsed_time": "0:32:28", "remaining_time": "6:31:53", "throughput": 1506.23, "total_tokens": 2934336} {"current_steps": 13915, "total_steps": 181800, "loss": 0.07, "lr": 3.826732673267327e-05, "epoch": 1.5308030803080308, "percentage": 7.65, "elapsed_time": "0:32:28", "remaining_time": "6:31:52", "throughput": 1506.23, "total_tokens": 2935360} {"current_steps": 13920, "total_steps": 181800, "loss": 0.1465, "lr": 3.828107810781078e-05, "epoch": 1.5313531353135312, "percentage": 7.66, "elapsed_time": "0:32:29", "remaining_time": "6:31:51", "throughput": 1506.21, "total_tokens": 2936352} {"current_steps": 13925, "total_steps": 181800, "loss": 0.0595, "lr": 3.8294829482948294e-05, "epoch": 1.5319031903190319, "percentage": 7.66, "elapsed_time": "0:32:30", "remaining_time": "6:31:50", "throughput": 1506.22, "total_tokens": 2937408} {"current_steps": 13930, "total_steps": 181800, "loss": 0.0927, "lr": 3.830858085808581e-05, "epoch": 1.5324532453245325, "percentage": 7.66, "elapsed_time": "0:32:30", "remaining_time": "6:31:50", "throughput": 1506.27, "total_tokens": 2938560} {"current_steps": 13935, "total_steps": 181800, "loss": 0.0974, "lr": 3.8322332233223324e-05, "epoch": 1.533003300330033, "percentage": 7.67, "elapsed_time": "0:32:31", "remaining_time": "6:31:49", "throughput": 1506.27, "total_tokens": 2939584} {"current_steps": 13940, "total_steps": 181800, "loss": 0.0925, "lr": 3.833608360836084e-05, "epoch": 1.5335533553355336, "percentage": 7.67, "elapsed_time": "0:32:32", "remaining_time": "6:31:48", "throughput": 1506.28, "total_tokens": 2940640} {"current_steps": 13945, "total_steps": 181800, "loss": 0.1003, "lr": 3.8349834983498354e-05, "epoch": 1.534103410341034, "percentage": 7.67, "elapsed_time": "0:32:32", "remaining_time": "6:31:47", "throughput": 1506.27, "total_tokens": 2941664} {"current_steps": 13950, "total_steps": 181800, "loss": 0.0819, "lr": 3.8363586358635866e-05, "epoch": 1.5346534653465347, "percentage": 7.67, "elapsed_time": "0:32:33", "remaining_time": "6:31:46", "throughput": 1506.28, "total_tokens": 2942720} {"current_steps": 13955, "total_steps": 181800, "loss": 0.1675, "lr": 3.837733773377338e-05, "epoch": 1.5352035203520353, "percentage": 7.68, "elapsed_time": "0:32:34", "remaining_time": "6:31:45", "throughput": 1506.28, "total_tokens": 2943744} {"current_steps": 13960, "total_steps": 181800, "loss": 0.0868, "lr": 3.8391089108910896e-05, "epoch": 1.5357535753575358, "percentage": 7.68, "elapsed_time": "0:32:34", "remaining_time": "6:31:44", "throughput": 1506.24, "total_tokens": 2944704} {"current_steps": 13965, "total_steps": 181800, "loss": 0.1131, "lr": 3.840484048404841e-05, "epoch": 1.5363036303630362, "percentage": 7.68, "elapsed_time": "0:32:35", "remaining_time": "6:31:43", "throughput": 1506.25, "total_tokens": 2945760} {"current_steps": 13970, "total_steps": 181800, "loss": 0.1625, "lr": 3.841859185918592e-05, "epoch": 1.5368536853685368, "percentage": 7.68, "elapsed_time": "0:32:36", "remaining_time": "6:31:43", "throughput": 1506.21, "total_tokens": 2946720} {"current_steps": 13975, "total_steps": 181800, "loss": 0.1357, "lr": 3.843234323432344e-05, "epoch": 1.5374037403740375, "percentage": 7.69, "elapsed_time": "0:32:37", "remaining_time": "6:31:42", "throughput": 1506.22, "total_tokens": 2947776} {"current_steps": 13980, "total_steps": 181800, "loss": 0.1629, "lr": 3.844609460946095e-05, "epoch": 1.537953795379538, "percentage": 7.69, "elapsed_time": "0:32:37", "remaining_time": "6:31:41", "throughput": 1506.22, "total_tokens": 2948800} {"current_steps": 13985, "total_steps": 181800, "loss": 0.0971, "lr": 3.845984598459846e-05, "epoch": 1.5385038503850383, "percentage": 7.69, "elapsed_time": "0:32:38", "remaining_time": "6:31:40", "throughput": 1506.21, "total_tokens": 2949824} {"current_steps": 13990, "total_steps": 181800, "loss": 0.0501, "lr": 3.847359735973597e-05, "epoch": 1.539053905390539, "percentage": 7.7, "elapsed_time": "0:32:39", "remaining_time": "6:31:39", "throughput": 1506.24, "total_tokens": 2950912} {"current_steps": 13995, "total_steps": 181800, "loss": 0.1803, "lr": 3.848734873487349e-05, "epoch": 1.5396039603960396, "percentage": 7.7, "elapsed_time": "0:32:39", "remaining_time": "6:31:38", "throughput": 1506.25, "total_tokens": 2951968} {"current_steps": 14000, "total_steps": 181800, "loss": 0.1319, "lr": 3.8501100110011e-05, "epoch": 1.5401540154015403, "percentage": 7.7, "elapsed_time": "0:32:40", "remaining_time": "6:31:38", "throughput": 1506.26, "total_tokens": 2953024} {"current_steps": 14005, "total_steps": 181800, "loss": 0.1371, "lr": 3.851485148514852e-05, "epoch": 1.5407040704070407, "percentage": 7.7, "elapsed_time": "0:32:41", "remaining_time": "6:31:37", "throughput": 1506.25, "total_tokens": 2954048} {"current_steps": 14010, "total_steps": 181800, "loss": 0.0874, "lr": 3.8528602860286026e-05, "epoch": 1.5412541254125411, "percentage": 7.71, "elapsed_time": "0:32:41", "remaining_time": "6:31:36", "throughput": 1506.23, "total_tokens": 2955040} {"current_steps": 14015, "total_steps": 181800, "loss": 0.0554, "lr": 3.8542354235423544e-05, "epoch": 1.5418041804180418, "percentage": 7.71, "elapsed_time": "0:32:42", "remaining_time": "6:31:35", "throughput": 1506.23, "total_tokens": 2956064} {"current_steps": 14020, "total_steps": 181800, "loss": 0.0997, "lr": 3.8556105610561056e-05, "epoch": 1.5423542354235424, "percentage": 7.71, "elapsed_time": "0:32:43", "remaining_time": "6:31:34", "throughput": 1506.26, "total_tokens": 2957152} {"current_steps": 14025, "total_steps": 181800, "loss": 0.0894, "lr": 3.8569856985698574e-05, "epoch": 1.5429042904290429, "percentage": 7.71, "elapsed_time": "0:32:43", "remaining_time": "6:31:33", "throughput": 1506.27, "total_tokens": 2958208} {"current_steps": 14030, "total_steps": 181800, "loss": 0.1177, "lr": 3.8583608360836086e-05, "epoch": 1.5434543454345433, "percentage": 7.72, "elapsed_time": "0:32:44", "remaining_time": "6:31:32", "throughput": 1506.25, "total_tokens": 2959200} {"current_steps": 14035, "total_steps": 181800, "loss": 0.2155, "lr": 3.85973597359736e-05, "epoch": 1.544004400440044, "percentage": 7.72, "elapsed_time": "0:32:45", "remaining_time": "6:31:32", "throughput": 1506.25, "total_tokens": 2960256} {"current_steps": 14040, "total_steps": 181800, "loss": 0.1085, "lr": 3.8611111111111116e-05, "epoch": 1.5445544554455446, "percentage": 7.72, "elapsed_time": "0:32:46", "remaining_time": "6:31:31", "throughput": 1506.26, "total_tokens": 2961312} {"current_steps": 14045, "total_steps": 181800, "loss": 0.1934, "lr": 3.862486248624863e-05, "epoch": 1.5451045104510452, "percentage": 7.73, "elapsed_time": "0:32:46", "remaining_time": "6:31:30", "throughput": 1506.28, "total_tokens": 2962400} {"current_steps": 14050, "total_steps": 181800, "loss": 0.0603, "lr": 3.863861386138614e-05, "epoch": 1.5456545654565457, "percentage": 7.73, "elapsed_time": "0:32:47", "remaining_time": "6:31:29", "throughput": 1506.31, "total_tokens": 2963488} {"current_steps": 14055, "total_steps": 181800, "loss": 0.1987, "lr": 3.865236523652365e-05, "epoch": 1.546204620462046, "percentage": 7.73, "elapsed_time": "0:32:48", "remaining_time": "6:31:28", "throughput": 1506.27, "total_tokens": 2964448} {"current_steps": 14060, "total_steps": 181800, "loss": 0.0604, "lr": 3.866611661166117e-05, "epoch": 1.5467546754675467, "percentage": 7.73, "elapsed_time": "0:32:48", "remaining_time": "6:31:27", "throughput": 1506.31, "total_tokens": 2965568} {"current_steps": 14065, "total_steps": 181800, "loss": 0.1271, "lr": 3.867986798679868e-05, "epoch": 1.5473047304730474, "percentage": 7.74, "elapsed_time": "0:32:49", "remaining_time": "6:31:27", "throughput": 1506.32, "total_tokens": 2966624} {"current_steps": 14070, "total_steps": 181800, "loss": 0.1164, "lr": 3.869361936193619e-05, "epoch": 1.5478547854785478, "percentage": 7.74, "elapsed_time": "0:32:50", "remaining_time": "6:31:26", "throughput": 1506.32, "total_tokens": 2967648} {"current_steps": 14075, "total_steps": 181800, "loss": 0.0243, "lr": 3.870737073707371e-05, "epoch": 1.5484048404840483, "percentage": 7.74, "elapsed_time": "0:32:50", "remaining_time": "6:31:25", "throughput": 1506.31, "total_tokens": 2968672} {"current_steps": 14080, "total_steps": 181800, "loss": 0.0485, "lr": 3.872112211221122e-05, "epoch": 1.548954895489549, "percentage": 7.74, "elapsed_time": "0:32:51", "remaining_time": "6:31:24", "throughput": 1506.31, "total_tokens": 2969696} {"current_steps": 14085, "total_steps": 181800, "loss": 0.0624, "lr": 3.873487348734874e-05, "epoch": 1.5495049504950495, "percentage": 7.75, "elapsed_time": "0:32:52", "remaining_time": "6:31:23", "throughput": 1506.31, "total_tokens": 2970720} {"current_steps": 14090, "total_steps": 181800, "loss": 0.1409, "lr": 3.8748624862486246e-05, "epoch": 1.5500550055005502, "percentage": 7.75, "elapsed_time": "0:32:52", "remaining_time": "6:31:22", "throughput": 1506.3, "total_tokens": 2971744} {"current_steps": 14095, "total_steps": 181800, "loss": 0.0542, "lr": 3.8762376237623765e-05, "epoch": 1.5506050605060506, "percentage": 7.75, "elapsed_time": "0:32:53", "remaining_time": "6:31:21", "throughput": 1506.3, "total_tokens": 2972768} {"current_steps": 14100, "total_steps": 181800, "loss": 0.1114, "lr": 3.8776127612761276e-05, "epoch": 1.551155115511551, "percentage": 7.76, "elapsed_time": "0:32:54", "remaining_time": "6:31:20", "throughput": 1506.27, "total_tokens": 2973760} {"current_steps": 14105, "total_steps": 181800, "loss": 0.1179, "lr": 3.8789878987898795e-05, "epoch": 1.5517051705170517, "percentage": 7.76, "elapsed_time": "0:32:54", "remaining_time": "6:31:20", "throughput": 1506.27, "total_tokens": 2974784} {"current_steps": 14110, "total_steps": 181800, "loss": 0.0798, "lr": 3.8803630363036306e-05, "epoch": 1.5522552255225524, "percentage": 7.76, "elapsed_time": "0:32:55", "remaining_time": "6:31:19", "throughput": 1506.27, "total_tokens": 2975840} {"current_steps": 14115, "total_steps": 181800, "loss": 0.145, "lr": 3.881738173817382e-05, "epoch": 1.5528052805280528, "percentage": 7.76, "elapsed_time": "0:32:56", "remaining_time": "6:31:18", "throughput": 1506.25, "total_tokens": 2976832} {"current_steps": 14120, "total_steps": 181800, "loss": 0.0852, "lr": 3.8831133113311336e-05, "epoch": 1.5533553355335532, "percentage": 7.77, "elapsed_time": "0:32:57", "remaining_time": "6:31:17", "throughput": 1506.21, "total_tokens": 2977792} {"current_steps": 14125, "total_steps": 181800, "loss": 0.1056, "lr": 3.884488448844885e-05, "epoch": 1.5539053905390539, "percentage": 7.77, "elapsed_time": "0:32:57", "remaining_time": "6:31:16", "throughput": 1506.19, "total_tokens": 2978784} {"current_steps": 14130, "total_steps": 181800, "loss": 0.0335, "lr": 3.885863586358636e-05, "epoch": 1.5544554455445545, "percentage": 7.77, "elapsed_time": "0:32:58", "remaining_time": "6:31:15", "throughput": 1506.2, "total_tokens": 2979840} {"current_steps": 14135, "total_steps": 181800, "loss": 0.0765, "lr": 3.887238723872387e-05, "epoch": 1.5550055005500552, "percentage": 7.78, "elapsed_time": "0:32:59", "remaining_time": "6:31:15", "throughput": 1506.23, "total_tokens": 2980928} {"current_steps": 14140, "total_steps": 181800, "loss": 0.0847, "lr": 3.888613861386139e-05, "epoch": 1.5555555555555556, "percentage": 7.78, "elapsed_time": "0:32:59", "remaining_time": "6:31:14", "throughput": 1506.25, "total_tokens": 2982016} {"current_steps": 14145, "total_steps": 181800, "loss": 0.0684, "lr": 3.88998899889989e-05, "epoch": 1.556105610561056, "percentage": 7.78, "elapsed_time": "0:33:00", "remaining_time": "6:31:13", "throughput": 1506.29, "total_tokens": 2983136} {"current_steps": 14150, "total_steps": 181800, "loss": 0.2593, "lr": 3.891364136413641e-05, "epoch": 1.5566556655665567, "percentage": 7.78, "elapsed_time": "0:33:01", "remaining_time": "6:31:12", "throughput": 1506.3, "total_tokens": 2984192} {"current_steps": 14155, "total_steps": 181800, "loss": 0.0653, "lr": 3.8927392739273925e-05, "epoch": 1.5572057205720573, "percentage": 7.79, "elapsed_time": "0:33:01", "remaining_time": "6:31:11", "throughput": 1506.33, "total_tokens": 2985280} {"current_steps": 14160, "total_steps": 181800, "loss": 0.1026, "lr": 3.894114411441144e-05, "epoch": 1.5577557755775577, "percentage": 7.79, "elapsed_time": "0:33:02", "remaining_time": "6:31:10", "throughput": 1506.37, "total_tokens": 2986400} {"current_steps": 14165, "total_steps": 181800, "loss": 0.0408, "lr": 3.895489548954896e-05, "epoch": 1.5583058305830582, "percentage": 7.79, "elapsed_time": "0:33:03", "remaining_time": "6:31:10", "throughput": 1506.39, "total_tokens": 2987456} {"current_steps": 14170, "total_steps": 181800, "loss": 0.0333, "lr": 3.896864686468647e-05, "epoch": 1.5588558855885588, "percentage": 7.79, "elapsed_time": "0:33:03", "remaining_time": "6:31:09", "throughput": 1506.36, "total_tokens": 2988448} {"current_steps": 14175, "total_steps": 181800, "loss": 0.0753, "lr": 3.8982398239823985e-05, "epoch": 1.5594059405940595, "percentage": 7.8, "elapsed_time": "0:33:04", "remaining_time": "6:31:08", "throughput": 1506.37, "total_tokens": 2989504} {"current_steps": 14180, "total_steps": 181800, "loss": 0.1367, "lr": 3.8996149614961497e-05, "epoch": 1.55995599559956, "percentage": 7.8, "elapsed_time": "0:33:05", "remaining_time": "6:31:07", "throughput": 1506.37, "total_tokens": 2990528} {"current_steps": 14185, "total_steps": 181800, "loss": 0.0398, "lr": 3.9009900990099015e-05, "epoch": 1.5605060506050605, "percentage": 7.8, "elapsed_time": "0:33:05", "remaining_time": "6:31:06", "throughput": 1506.36, "total_tokens": 2991552} {"current_steps": 14190, "total_steps": 181800, "loss": 0.0404, "lr": 3.902365236523653e-05, "epoch": 1.561056105610561, "percentage": 7.81, "elapsed_time": "0:33:06", "remaining_time": "6:31:05", "throughput": 1506.35, "total_tokens": 2992576} {"current_steps": 14195, "total_steps": 181800, "loss": 0.08, "lr": 3.903740374037404e-05, "epoch": 1.5616061606160616, "percentage": 7.81, "elapsed_time": "0:33:07", "remaining_time": "6:31:05", "throughput": 1506.39, "total_tokens": 2993696} {"current_steps": 14200, "total_steps": 181800, "loss": 0.1692, "lr": 3.905115511551155e-05, "epoch": 1.5621562156215623, "percentage": 7.81, "elapsed_time": "0:33:08", "remaining_time": "6:31:04", "throughput": 1506.43, "total_tokens": 2994816} {"current_steps": 14205, "total_steps": 181800, "loss": 0.2223, "lr": 3.906490649064907e-05, "epoch": 1.5627062706270627, "percentage": 7.81, "elapsed_time": "0:33:08", "remaining_time": "6:31:03", "throughput": 1506.44, "total_tokens": 2995872} {"current_steps": 14210, "total_steps": 181800, "loss": 0.1292, "lr": 3.907865786578658e-05, "epoch": 1.5632563256325631, "percentage": 7.82, "elapsed_time": "0:33:09", "remaining_time": "6:31:02", "throughput": 1506.45, "total_tokens": 2996928} {"current_steps": 14215, "total_steps": 181800, "loss": 0.052, "lr": 3.909240924092409e-05, "epoch": 1.5638063806380638, "percentage": 7.82, "elapsed_time": "0:33:10", "remaining_time": "6:31:01", "throughput": 1506.47, "total_tokens": 2998016} {"current_steps": 14220, "total_steps": 181800, "loss": 0.1073, "lr": 3.910616061606161e-05, "epoch": 1.5643564356435644, "percentage": 7.82, "elapsed_time": "0:33:10", "remaining_time": "6:31:01", "throughput": 1506.49, "total_tokens": 2999104} {"current_steps": 14225, "total_steps": 181800, "loss": 0.1885, "lr": 3.911991199119912e-05, "epoch": 1.564906490649065, "percentage": 7.82, "elapsed_time": "0:33:11", "remaining_time": "6:31:00", "throughput": 1506.53, "total_tokens": 3000224} {"current_steps": 14230, "total_steps": 181800, "loss": 0.0659, "lr": 3.913366336633664e-05, "epoch": 1.5654565456545655, "percentage": 7.83, "elapsed_time": "0:33:12", "remaining_time": "6:30:59", "throughput": 1506.51, "total_tokens": 3001216} {"current_steps": 14235, "total_steps": 181800, "loss": 0.1336, "lr": 3.9147414741474145e-05, "epoch": 1.566006600660066, "percentage": 7.83, "elapsed_time": "0:33:12", "remaining_time": "6:30:58", "throughput": 1506.52, "total_tokens": 3002272} {"current_steps": 14240, "total_steps": 181800, "loss": 0.0837, "lr": 3.9161166116611664e-05, "epoch": 1.5665566556655666, "percentage": 7.83, "elapsed_time": "0:33:13", "remaining_time": "6:30:57", "throughput": 1506.52, "total_tokens": 3003296} {"current_steps": 14245, "total_steps": 181800, "loss": 0.1288, "lr": 3.9174917491749175e-05, "epoch": 1.5671067106710672, "percentage": 7.84, "elapsed_time": "0:33:14", "remaining_time": "6:30:56", "throughput": 1506.51, "total_tokens": 3004320} {"current_steps": 14250, "total_steps": 181800, "loss": 0.0764, "lr": 3.9188668866886694e-05, "epoch": 1.5676567656765676, "percentage": 7.84, "elapsed_time": "0:33:14", "remaining_time": "6:30:55", "throughput": 1506.55, "total_tokens": 3005440} {"current_steps": 14255, "total_steps": 181800, "loss": 0.1543, "lr": 3.9202420242024205e-05, "epoch": 1.568206820682068, "percentage": 7.84, "elapsed_time": "0:33:15", "remaining_time": "6:30:55", "throughput": 1506.56, "total_tokens": 3006496} {"current_steps": 14260, "total_steps": 181800, "loss": 0.0528, "lr": 3.921617161716172e-05, "epoch": 1.5687568756875687, "percentage": 7.84, "elapsed_time": "0:33:16", "remaining_time": "6:30:54", "throughput": 1506.6, "total_tokens": 3007616} {"current_steps": 14265, "total_steps": 181800, "loss": 0.1428, "lr": 3.9229922992299235e-05, "epoch": 1.5693069306930694, "percentage": 7.85, "elapsed_time": "0:33:16", "remaining_time": "6:30:53", "throughput": 1506.59, "total_tokens": 3008640} {"current_steps": 14270, "total_steps": 181800, "loss": 0.1072, "lr": 3.924367436743675e-05, "epoch": 1.56985698569857, "percentage": 7.85, "elapsed_time": "0:33:17", "remaining_time": "6:30:52", "throughput": 1506.61, "total_tokens": 3009728} {"current_steps": 14275, "total_steps": 181800, "loss": 0.1094, "lr": 3.925742574257426e-05, "epoch": 1.5704070407040704, "percentage": 7.85, "elapsed_time": "0:33:18", "remaining_time": "6:30:51", "throughput": 1506.6, "total_tokens": 3010752} {"current_steps": 14280, "total_steps": 181800, "loss": 0.0548, "lr": 3.927117711771177e-05, "epoch": 1.5709570957095709, "percentage": 7.85, "elapsed_time": "0:33:19", "remaining_time": "6:30:51", "throughput": 1506.6, "total_tokens": 3011776} {"current_steps": 14285, "total_steps": 181800, "loss": 0.1599, "lr": 3.928492849284929e-05, "epoch": 1.5715071507150715, "percentage": 7.86, "elapsed_time": "0:33:19", "remaining_time": "6:30:50", "throughput": 1506.65, "total_tokens": 3012928} {"current_steps": 14290, "total_steps": 181800, "loss": 0.1678, "lr": 3.92986798679868e-05, "epoch": 1.5720572057205722, "percentage": 7.86, "elapsed_time": "0:33:20", "remaining_time": "6:30:49", "throughput": 1506.63, "total_tokens": 3013920} {"current_steps": 14295, "total_steps": 181800, "loss": 0.0981, "lr": 3.931243124312431e-05, "epoch": 1.5726072607260726, "percentage": 7.86, "elapsed_time": "0:33:21", "remaining_time": "6:30:48", "throughput": 1506.64, "total_tokens": 3014976} {"current_steps": 14300, "total_steps": 181800, "loss": 0.0683, "lr": 3.9326182618261824e-05, "epoch": 1.573157315731573, "percentage": 7.87, "elapsed_time": "0:33:21", "remaining_time": "6:30:47", "throughput": 1506.67, "total_tokens": 3016064} {"current_steps": 14305, "total_steps": 181800, "loss": 0.0408, "lr": 3.933993399339934e-05, "epoch": 1.5737073707370737, "percentage": 7.87, "elapsed_time": "0:33:22", "remaining_time": "6:30:46", "throughput": 1506.69, "total_tokens": 3017152} {"current_steps": 14310, "total_steps": 181800, "loss": 0.163, "lr": 3.935368536853686e-05, "epoch": 1.5742574257425743, "percentage": 7.87, "elapsed_time": "0:33:23", "remaining_time": "6:30:46", "throughput": 1506.7, "total_tokens": 3018208} {"current_steps": 14315, "total_steps": 181800, "loss": 0.0843, "lr": 3.9367436743674365e-05, "epoch": 1.574807480748075, "percentage": 7.87, "elapsed_time": "0:33:23", "remaining_time": "6:30:45", "throughput": 1506.73, "total_tokens": 3019296} {"current_steps": 14320, "total_steps": 181800, "loss": 0.0374, "lr": 3.9381188118811884e-05, "epoch": 1.5753575357535754, "percentage": 7.88, "elapsed_time": "0:33:24", "remaining_time": "6:30:44", "throughput": 1506.72, "total_tokens": 3020320} {"current_steps": 14325, "total_steps": 181800, "loss": 0.1553, "lr": 3.9394939493949396e-05, "epoch": 1.5759075907590758, "percentage": 7.88, "elapsed_time": "0:33:25", "remaining_time": "6:30:43", "throughput": 1506.71, "total_tokens": 3021344} {"current_steps": 14330, "total_steps": 181800, "loss": 0.0615, "lr": 3.9408690869086914e-05, "epoch": 1.5764576457645765, "percentage": 7.88, "elapsed_time": "0:33:25", "remaining_time": "6:30:42", "throughput": 1506.7, "total_tokens": 3022368} {"current_steps": 14335, "total_steps": 181800, "loss": 0.034, "lr": 3.9422442244224426e-05, "epoch": 1.5770077007700771, "percentage": 7.89, "elapsed_time": "0:33:26", "remaining_time": "6:30:41", "throughput": 1506.73, "total_tokens": 3023456} {"current_steps": 14340, "total_steps": 181800, "loss": 0.1386, "lr": 3.943619361936194e-05, "epoch": 1.5775577557755776, "percentage": 7.89, "elapsed_time": "0:33:27", "remaining_time": "6:30:41", "throughput": 1506.74, "total_tokens": 3024512} {"current_steps": 14345, "total_steps": 181800, "loss": 0.1475, "lr": 3.944994499449945e-05, "epoch": 1.578107810781078, "percentage": 7.89, "elapsed_time": "0:33:28", "remaining_time": "6:30:40", "throughput": 1506.77, "total_tokens": 3025600} {"current_steps": 14350, "total_steps": 181800, "loss": 0.1562, "lr": 3.946369636963697e-05, "epoch": 1.5786578657865786, "percentage": 7.89, "elapsed_time": "0:33:28", "remaining_time": "6:30:39", "throughput": 1506.79, "total_tokens": 3026688} {"current_steps": 14355, "total_steps": 181800, "loss": 0.0525, "lr": 3.947744774477448e-05, "epoch": 1.5792079207920793, "percentage": 7.9, "elapsed_time": "0:33:29", "remaining_time": "6:30:38", "throughput": 1506.84, "total_tokens": 3027808} {"current_steps": 14360, "total_steps": 181800, "loss": 0.048, "lr": 3.949119911991199e-05, "epoch": 1.5797579757975797, "percentage": 7.9, "elapsed_time": "0:33:30", "remaining_time": "6:30:37", "throughput": 1506.83, "total_tokens": 3028832} {"current_steps": 14365, "total_steps": 181800, "loss": 0.0498, "lr": 3.950495049504951e-05, "epoch": 1.5803080308030804, "percentage": 7.9, "elapsed_time": "0:33:30", "remaining_time": "6:30:36", "throughput": 1506.82, "total_tokens": 3029856} {"current_steps": 14370, "total_steps": 181800, "loss": 0.2444, "lr": 3.951870187018702e-05, "epoch": 1.5808580858085808, "percentage": 7.9, "elapsed_time": "0:33:31", "remaining_time": "6:30:36", "throughput": 1506.82, "total_tokens": 3030912} {"current_steps": 14375, "total_steps": 181800, "loss": 0.1168, "lr": 3.953245324532453e-05, "epoch": 1.5814081408140814, "percentage": 7.91, "elapsed_time": "0:33:32", "remaining_time": "6:30:35", "throughput": 1506.83, "total_tokens": 3031968} {"current_steps": 14380, "total_steps": 181800, "loss": 0.1072, "lr": 3.9546204620462044e-05, "epoch": 1.581958195819582, "percentage": 7.91, "elapsed_time": "0:33:32", "remaining_time": "6:30:34", "throughput": 1506.86, "total_tokens": 3033056} {"current_steps": 14385, "total_steps": 181800, "loss": 0.0815, "lr": 3.955995599559956e-05, "epoch": 1.5825082508250825, "percentage": 7.91, "elapsed_time": "0:33:33", "remaining_time": "6:30:33", "throughput": 1506.85, "total_tokens": 3034080} {"current_steps": 14390, "total_steps": 181800, "loss": 0.0734, "lr": 3.9573707370737074e-05, "epoch": 1.583058305830583, "percentage": 7.92, "elapsed_time": "0:33:34", "remaining_time": "6:30:32", "throughput": 1506.88, "total_tokens": 3035168} {"current_steps": 14395, "total_steps": 181800, "loss": 0.1022, "lr": 3.958745874587459e-05, "epoch": 1.5836083608360836, "percentage": 7.92, "elapsed_time": "0:33:34", "remaining_time": "6:30:32", "throughput": 1506.9, "total_tokens": 3036256} {"current_steps": 14400, "total_steps": 181800, "loss": 0.1597, "lr": 3.9601210121012104e-05, "epoch": 1.5841584158415842, "percentage": 7.92, "elapsed_time": "0:33:35", "remaining_time": "6:30:31", "throughput": 1506.89, "total_tokens": 3037280} {"current_steps": 14405, "total_steps": 181800, "loss": 0.2251, "lr": 3.9614961496149616e-05, "epoch": 1.5847084708470847, "percentage": 7.92, "elapsed_time": "0:33:36", "remaining_time": "6:30:30", "throughput": 1506.89, "total_tokens": 3038304} {"current_steps": 14410, "total_steps": 181800, "loss": 0.054, "lr": 3.9628712871287134e-05, "epoch": 1.5852585258525853, "percentage": 7.93, "elapsed_time": "0:33:36", "remaining_time": "6:30:29", "throughput": 1506.86, "total_tokens": 3039296} {"current_steps": 14415, "total_steps": 181800, "loss": 0.0799, "lr": 3.9642464246424646e-05, "epoch": 1.5858085808580857, "percentage": 7.93, "elapsed_time": "0:33:37", "remaining_time": "6:30:28", "throughput": 1506.87, "total_tokens": 3040352} {"current_steps": 14420, "total_steps": 181800, "loss": 0.0885, "lr": 3.965621562156216e-05, "epoch": 1.5863586358635864, "percentage": 7.93, "elapsed_time": "0:33:38", "remaining_time": "6:30:27", "throughput": 1506.88, "total_tokens": 3041408} {"current_steps": 14425, "total_steps": 181800, "loss": 0.0698, "lr": 3.966996699669967e-05, "epoch": 1.586908690869087, "percentage": 7.93, "elapsed_time": "0:33:39", "remaining_time": "6:30:27", "throughput": 1506.87, "total_tokens": 3042432} {"current_steps": 14430, "total_steps": 181800, "loss": 0.1189, "lr": 3.968371837183719e-05, "epoch": 1.5874587458745875, "percentage": 7.94, "elapsed_time": "0:33:39", "remaining_time": "6:30:26", "throughput": 1506.83, "total_tokens": 3043392} {"current_steps": 14435, "total_steps": 181800, "loss": 0.1405, "lr": 3.96974697469747e-05, "epoch": 1.588008800880088, "percentage": 7.94, "elapsed_time": "0:33:40", "remaining_time": "6:30:25", "throughput": 1506.81, "total_tokens": 3044384} {"current_steps": 14440, "total_steps": 181800, "loss": 0.141, "lr": 3.971122112211221e-05, "epoch": 1.5885588558855885, "percentage": 7.94, "elapsed_time": "0:33:41", "remaining_time": "6:30:24", "throughput": 1506.79, "total_tokens": 3045376} {"current_steps": 14445, "total_steps": 181800, "loss": 0.1807, "lr": 3.972497249724973e-05, "epoch": 1.5891089108910892, "percentage": 7.95, "elapsed_time": "0:33:41", "remaining_time": "6:30:23", "throughput": 1506.78, "total_tokens": 3046400} {"current_steps": 14450, "total_steps": 181800, "loss": 0.0921, "lr": 3.973872387238724e-05, "epoch": 1.5896589658965896, "percentage": 7.95, "elapsed_time": "0:33:42", "remaining_time": "6:30:22", "throughput": 1506.81, "total_tokens": 3047488} {"current_steps": 14455, "total_steps": 181800, "loss": 0.1063, "lr": 3.975247524752476e-05, "epoch": 1.5902090209020903, "percentage": 7.95, "elapsed_time": "0:33:43", "remaining_time": "6:30:22", "throughput": 1506.8, "total_tokens": 3048512} {"current_steps": 14460, "total_steps": 181800, "loss": 0.0871, "lr": 3.9766226622662264e-05, "epoch": 1.5907590759075907, "percentage": 7.95, "elapsed_time": "0:33:43", "remaining_time": "6:30:21", "throughput": 1506.83, "total_tokens": 3049600} {"current_steps": 14465, "total_steps": 181800, "loss": 0.044, "lr": 3.977997799779978e-05, "epoch": 1.5913091309130913, "percentage": 7.96, "elapsed_time": "0:33:44", "remaining_time": "6:30:20", "throughput": 1506.84, "total_tokens": 3050656} {"current_steps": 14470, "total_steps": 181800, "loss": 0.1428, "lr": 3.9793729372937295e-05, "epoch": 1.591859185918592, "percentage": 7.96, "elapsed_time": "0:33:45", "remaining_time": "6:30:19", "throughput": 1506.86, "total_tokens": 3051744} {"current_steps": 14475, "total_steps": 181800, "loss": 0.04, "lr": 3.980748074807481e-05, "epoch": 1.5924092409240924, "percentage": 7.96, "elapsed_time": "0:33:45", "remaining_time": "6:30:18", "throughput": 1506.84, "total_tokens": 3052736} {"current_steps": 14480, "total_steps": 181800, "loss": 0.1603, "lr": 3.982123212321232e-05, "epoch": 1.5929592959295928, "percentage": 7.96, "elapsed_time": "0:33:46", "remaining_time": "6:30:18", "throughput": 1506.86, "total_tokens": 3053824} {"current_steps": 14485, "total_steps": 181800, "loss": 0.1172, "lr": 3.9834983498349836e-05, "epoch": 1.5935093509350935, "percentage": 7.97, "elapsed_time": "0:33:47", "remaining_time": "6:30:17", "throughput": 1506.87, "total_tokens": 3054880} {"current_steps": 14490, "total_steps": 181800, "loss": 0.1219, "lr": 3.9848734873487355e-05, "epoch": 1.5940594059405941, "percentage": 7.97, "elapsed_time": "0:33:47", "remaining_time": "6:30:16", "throughput": 1506.88, "total_tokens": 3055936} {"current_steps": 14495, "total_steps": 181800, "loss": 0.0863, "lr": 3.9862486248624866e-05, "epoch": 1.5946094609460946, "percentage": 7.97, "elapsed_time": "0:33:48", "remaining_time": "6:30:15", "throughput": 1506.88, "total_tokens": 3056992} {"current_steps": 14500, "total_steps": 181800, "loss": 0.0715, "lr": 3.987623762376238e-05, "epoch": 1.595159515951595, "percentage": 7.98, "elapsed_time": "0:33:49", "remaining_time": "6:30:14", "throughput": 1506.89, "total_tokens": 3058048} {"current_steps": 14505, "total_steps": 181800, "loss": 0.1661, "lr": 3.988998899889989e-05, "epoch": 1.5957095709570956, "percentage": 7.98, "elapsed_time": "0:33:50", "remaining_time": "6:30:13", "throughput": 1506.89, "total_tokens": 3059072} {"current_steps": 14510, "total_steps": 181800, "loss": 0.2095, "lr": 3.990374037403741e-05, "epoch": 1.5962596259625963, "percentage": 7.98, "elapsed_time": "0:33:50", "remaining_time": "6:30:13", "throughput": 1506.94, "total_tokens": 3060224} {"current_steps": 14515, "total_steps": 181800, "loss": 0.1146, "lr": 3.991749174917492e-05, "epoch": 1.596809680968097, "percentage": 7.98, "elapsed_time": "0:33:51", "remaining_time": "6:30:12", "throughput": 1506.97, "total_tokens": 3061312} {"current_steps": 14520, "total_steps": 181800, "loss": 0.0467, "lr": 3.993124312431243e-05, "epoch": 1.5973597359735974, "percentage": 7.99, "elapsed_time": "0:33:52", "remaining_time": "6:30:11", "throughput": 1506.98, "total_tokens": 3062368} {"current_steps": 14525, "total_steps": 181800, "loss": 0.1413, "lr": 3.994499449944994e-05, "epoch": 1.5979097909790978, "percentage": 7.99, "elapsed_time": "0:33:52", "remaining_time": "6:30:10", "throughput": 1506.97, "total_tokens": 3063392} {"current_steps": 14530, "total_steps": 181800, "loss": 0.1035, "lr": 3.995874587458746e-05, "epoch": 1.5984598459845984, "percentage": 7.99, "elapsed_time": "0:33:53", "remaining_time": "6:30:09", "throughput": 1506.94, "total_tokens": 3064384} {"current_steps": 14535, "total_steps": 181800, "loss": 0.0723, "lr": 3.997249724972497e-05, "epoch": 1.599009900990099, "percentage": 8.0, "elapsed_time": "0:33:54", "remaining_time": "6:30:09", "throughput": 1506.92, "total_tokens": 3065376} {"current_steps": 14540, "total_steps": 181800, "loss": 0.05, "lr": 3.9986248624862485e-05, "epoch": 1.5995599559955995, "percentage": 8.0, "elapsed_time": "0:33:54", "remaining_time": "6:30:08", "throughput": 1506.94, "total_tokens": 3066464} {"current_steps": 14545, "total_steps": 181800, "loss": 0.0599, "lr": 4e-05, "epoch": 1.6001100110011, "percentage": 8.0, "elapsed_time": "0:33:55", "remaining_time": "6:30:07", "throughput": 1506.9, "total_tokens": 3067424} {"current_steps": 14550, "total_steps": 181800, "loss": 0.0393, "lr": 4.0013751375137515e-05, "epoch": 1.6006600660066006, "percentage": 8.0, "elapsed_time": "0:33:56", "remaining_time": "6:30:06", "throughput": 1506.93, "total_tokens": 3068512} {"current_steps": 14555, "total_steps": 181800, "loss": 0.1203, "lr": 4.002750275027503e-05, "epoch": 1.6012101210121013, "percentage": 8.01, "elapsed_time": "0:33:56", "remaining_time": "6:30:05", "throughput": 1506.94, "total_tokens": 3069568} {"current_steps": 14560, "total_steps": 181800, "loss": 0.0729, "lr": 4.0041254125412545e-05, "epoch": 1.601760176017602, "percentage": 8.01, "elapsed_time": "0:33:57", "remaining_time": "6:30:04", "throughput": 1506.94, "total_tokens": 3070624} {"current_steps": 14565, "total_steps": 181800, "loss": 0.0813, "lr": 4.005500550055006e-05, "epoch": 1.6023102310231023, "percentage": 8.01, "elapsed_time": "0:33:58", "remaining_time": "6:30:04", "throughput": 1506.97, "total_tokens": 3071712} {"current_steps": 14570, "total_steps": 181800, "loss": 0.0806, "lr": 4.006875687568757e-05, "epoch": 1.6028602860286028, "percentage": 8.01, "elapsed_time": "0:33:59", "remaining_time": "6:30:03", "throughput": 1506.97, "total_tokens": 3072768} {"current_steps": 14575, "total_steps": 181800, "loss": 0.0844, "lr": 4.008250825082509e-05, "epoch": 1.6034103410341034, "percentage": 8.02, "elapsed_time": "0:33:59", "remaining_time": "6:30:02", "throughput": 1506.97, "total_tokens": 3073792} {"current_steps": 14580, "total_steps": 181800, "loss": 0.0576, "lr": 4.00962596259626e-05, "epoch": 1.603960396039604, "percentage": 8.02, "elapsed_time": "0:34:00", "remaining_time": "6:30:01", "throughput": 1506.99, "total_tokens": 3074880} {"current_steps": 14585, "total_steps": 181800, "loss": 0.1481, "lr": 4.011001100110011e-05, "epoch": 1.6045104510451045, "percentage": 8.02, "elapsed_time": "0:34:01", "remaining_time": "6:30:00", "throughput": 1507.03, "total_tokens": 3076000} {"current_steps": 14590, "total_steps": 181800, "loss": 0.0749, "lr": 4.012376237623763e-05, "epoch": 1.605060506050605, "percentage": 8.03, "elapsed_time": "0:34:01", "remaining_time": "6:30:00", "throughput": 1507.04, "total_tokens": 3077056} {"current_steps": 14595, "total_steps": 181800, "loss": 0.1352, "lr": 4.013751375137514e-05, "epoch": 1.6056105610561056, "percentage": 8.03, "elapsed_time": "0:34:02", "remaining_time": "6:29:59", "throughput": 1507.07, "total_tokens": 3078144} {"current_steps": 14600, "total_steps": 181800, "loss": 0.0815, "lr": 4.015126512651265e-05, "epoch": 1.6061606160616062, "percentage": 8.03, "elapsed_time": "0:34:03", "remaining_time": "6:29:58", "throughput": 1507.08, "total_tokens": 3079200} {"current_steps": 14605, "total_steps": 181800, "loss": 0.1311, "lr": 4.0165016501650163e-05, "epoch": 1.6067106710671069, "percentage": 8.03, "elapsed_time": "0:34:03", "remaining_time": "6:29:57", "throughput": 1507.09, "total_tokens": 3080256} {"current_steps": 14610, "total_steps": 181800, "loss": 0.0938, "lr": 4.017876787678768e-05, "epoch": 1.6072607260726073, "percentage": 8.04, "elapsed_time": "0:34:04", "remaining_time": "6:29:56", "throughput": 1507.12, "total_tokens": 3081376} {"current_steps": 14615, "total_steps": 181800, "loss": 0.0842, "lr": 4.0192519251925194e-05, "epoch": 1.6078107810781077, "percentage": 8.04, "elapsed_time": "0:34:05", "remaining_time": "6:29:55", "throughput": 1507.15, "total_tokens": 3082464} {"current_steps": 14620, "total_steps": 181800, "loss": 0.2538, "lr": 4.020627062706271e-05, "epoch": 1.6083608360836084, "percentage": 8.04, "elapsed_time": "0:34:05", "remaining_time": "6:29:55", "throughput": 1507.12, "total_tokens": 3083456} {"current_steps": 14625, "total_steps": 181800, "loss": 0.0847, "lr": 4.022002200220022e-05, "epoch": 1.608910891089109, "percentage": 8.04, "elapsed_time": "0:34:06", "remaining_time": "6:29:54", "throughput": 1507.13, "total_tokens": 3084512} {"current_steps": 14630, "total_steps": 181800, "loss": 0.0381, "lr": 4.0233773377337735e-05, "epoch": 1.6094609460946094, "percentage": 8.05, "elapsed_time": "0:34:07", "remaining_time": "6:29:53", "throughput": 1507.15, "total_tokens": 3085568} {"current_steps": 14635, "total_steps": 181800, "loss": 0.2321, "lr": 4.0247524752475254e-05, "epoch": 1.6100110011001099, "percentage": 8.05, "elapsed_time": "0:34:07", "remaining_time": "6:29:52", "throughput": 1507.14, "total_tokens": 3086592} {"current_steps": 14640, "total_steps": 181800, "loss": 0.1473, "lr": 4.0261276127612765e-05, "epoch": 1.6105610561056105, "percentage": 8.05, "elapsed_time": "0:34:08", "remaining_time": "6:29:51", "throughput": 1507.16, "total_tokens": 3087680} {"current_steps": 14645, "total_steps": 181800, "loss": 0.0553, "lr": 4.027502750275028e-05, "epoch": 1.6111111111111112, "percentage": 8.06, "elapsed_time": "0:34:09", "remaining_time": "6:29:50", "throughput": 1507.17, "total_tokens": 3088736} {"current_steps": 14650, "total_steps": 181800, "loss": 0.1092, "lr": 4.028877887788779e-05, "epoch": 1.6116611661166118, "percentage": 8.06, "elapsed_time": "0:34:10", "remaining_time": "6:29:50", "throughput": 1507.18, "total_tokens": 3089792} {"current_steps": 14655, "total_steps": 181800, "loss": 0.1263, "lr": 4.030253025302531e-05, "epoch": 1.6122112211221122, "percentage": 8.06, "elapsed_time": "0:34:10", "remaining_time": "6:29:49", "throughput": 1507.17, "total_tokens": 3090816} {"current_steps": 14660, "total_steps": 181800, "loss": 0.0389, "lr": 4.031628162816282e-05, "epoch": 1.6127612761276127, "percentage": 8.06, "elapsed_time": "0:34:11", "remaining_time": "6:29:48", "throughput": 1507.18, "total_tokens": 3091872} {"current_steps": 14665, "total_steps": 181800, "loss": 0.0845, "lr": 4.033003300330033e-05, "epoch": 1.6133113311331133, "percentage": 8.07, "elapsed_time": "0:34:12", "remaining_time": "6:29:47", "throughput": 1507.2, "total_tokens": 3092960} {"current_steps": 14670, "total_steps": 181800, "loss": 0.1298, "lr": 4.034378437843784e-05, "epoch": 1.613861386138614, "percentage": 8.07, "elapsed_time": "0:34:12", "remaining_time": "6:29:46", "throughput": 1507.2, "total_tokens": 3093984} {"current_steps": 14675, "total_steps": 181800, "loss": 0.0611, "lr": 4.035753575357536e-05, "epoch": 1.6144114411441144, "percentage": 8.07, "elapsed_time": "0:34:13", "remaining_time": "6:29:46", "throughput": 1507.19, "total_tokens": 3095008} {"current_steps": 14680, "total_steps": 181800, "loss": 0.0426, "lr": 4.037128712871288e-05, "epoch": 1.6149614961496148, "percentage": 8.07, "elapsed_time": "0:34:14", "remaining_time": "6:29:45", "throughput": 1507.2, "total_tokens": 3096064} {"current_steps": 14685, "total_steps": 181800, "loss": 0.0962, "lr": 4.0385038503850384e-05, "epoch": 1.6155115511551155, "percentage": 8.08, "elapsed_time": "0:34:14", "remaining_time": "6:29:44", "throughput": 1507.19, "total_tokens": 3097088} {"current_steps": 14690, "total_steps": 181800, "loss": 0.0576, "lr": 4.03987898789879e-05, "epoch": 1.6160616061606161, "percentage": 8.08, "elapsed_time": "0:34:15", "remaining_time": "6:29:43", "throughput": 1507.2, "total_tokens": 3098144} {"current_steps": 14695, "total_steps": 181800, "loss": 0.0936, "lr": 4.0412541254125414e-05, "epoch": 1.6166116611661168, "percentage": 8.08, "elapsed_time": "0:34:16", "remaining_time": "6:29:42", "throughput": 1507.19, "total_tokens": 3099168} {"current_steps": 14700, "total_steps": 181800, "loss": 0.1171, "lr": 4.042629262926293e-05, "epoch": 1.6171617161716172, "percentage": 8.09, "elapsed_time": "0:34:16", "remaining_time": "6:29:41", "throughput": 1507.23, "total_tokens": 3100288} {"current_steps": 14705, "total_steps": 181800, "loss": 0.0656, "lr": 4.044004400440044e-05, "epoch": 1.6177117711771176, "percentage": 8.09, "elapsed_time": "0:34:17", "remaining_time": "6:29:41", "throughput": 1507.24, "total_tokens": 3101344} {"current_steps": 14710, "total_steps": 181800, "loss": 0.1076, "lr": 4.0453795379537956e-05, "epoch": 1.6182618261826183, "percentage": 8.09, "elapsed_time": "0:34:18", "remaining_time": "6:29:40", "throughput": 1507.25, "total_tokens": 3102400} {"current_steps": 14715, "total_steps": 181800, "loss": 0.1105, "lr": 4.046754675467547e-05, "epoch": 1.618811881188119, "percentage": 8.09, "elapsed_time": "0:34:19", "remaining_time": "6:29:39", "throughput": 1507.27, "total_tokens": 3103488} {"current_steps": 14720, "total_steps": 181800, "loss": 0.0664, "lr": 4.0481298129812986e-05, "epoch": 1.6193619361936193, "percentage": 8.1, "elapsed_time": "0:34:19", "remaining_time": "6:29:38", "throughput": 1507.26, "total_tokens": 3104512} {"current_steps": 14725, "total_steps": 181800, "loss": 0.1631, "lr": 4.04950495049505e-05, "epoch": 1.6199119911991198, "percentage": 8.1, "elapsed_time": "0:34:20", "remaining_time": "6:29:37", "throughput": 1507.25, "total_tokens": 3105536} {"current_steps": 14730, "total_steps": 181800, "loss": 0.1873, "lr": 4.050880088008801e-05, "epoch": 1.6204620462046204, "percentage": 8.1, "elapsed_time": "0:34:21", "remaining_time": "6:29:37", "throughput": 1507.23, "total_tokens": 3106528} {"current_steps": 14735, "total_steps": 181800, "loss": 0.1741, "lr": 4.052255225522553e-05, "epoch": 1.621012101210121, "percentage": 8.11, "elapsed_time": "0:34:21", "remaining_time": "6:29:36", "throughput": 1507.24, "total_tokens": 3107584} {"current_steps": 14740, "total_steps": 181800, "loss": 0.1394, "lr": 4.053630363036304e-05, "epoch": 1.6215621562156217, "percentage": 8.11, "elapsed_time": "0:34:22", "remaining_time": "6:29:35", "throughput": 1507.28, "total_tokens": 3108704} {"current_steps": 14745, "total_steps": 181800, "loss": 0.0377, "lr": 4.055005500550055e-05, "epoch": 1.6221122112211221, "percentage": 8.11, "elapsed_time": "0:34:23", "remaining_time": "6:29:34", "throughput": 1507.29, "total_tokens": 3109760} {"current_steps": 14750, "total_steps": 181800, "loss": 0.0499, "lr": 4.056380638063806e-05, "epoch": 1.6226622662266226, "percentage": 8.11, "elapsed_time": "0:34:23", "remaining_time": "6:29:33", "throughput": 1507.29, "total_tokens": 3110816} {"current_steps": 14755, "total_steps": 181800, "loss": 0.0868, "lr": 4.057755775577558e-05, "epoch": 1.6232123212321232, "percentage": 8.12, "elapsed_time": "0:34:24", "remaining_time": "6:29:33", "throughput": 1507.27, "total_tokens": 3111808} {"current_steps": 14760, "total_steps": 181800, "loss": 0.1673, "lr": 4.059130913091309e-05, "epoch": 1.6237623762376239, "percentage": 8.12, "elapsed_time": "0:34:25", "remaining_time": "6:29:32", "throughput": 1507.31, "total_tokens": 3112928} {"current_steps": 14765, "total_steps": 181800, "loss": 0.0789, "lr": 4.0605060506050604e-05, "epoch": 1.6243124312431243, "percentage": 8.12, "elapsed_time": "0:34:25", "remaining_time": "6:29:31", "throughput": 1507.35, "total_tokens": 3114048} {"current_steps": 14770, "total_steps": 181800, "loss": 0.0789, "lr": 4.061881188118812e-05, "epoch": 1.6248624862486247, "percentage": 8.12, "elapsed_time": "0:34:26", "remaining_time": "6:29:30", "throughput": 1507.38, "total_tokens": 3115136} {"current_steps": 14775, "total_steps": 181800, "loss": 0.1661, "lr": 4.0632563256325634e-05, "epoch": 1.6254125412541254, "percentage": 8.13, "elapsed_time": "0:34:27", "remaining_time": "6:29:29", "throughput": 1507.39, "total_tokens": 3116192} {"current_steps": 14780, "total_steps": 181800, "loss": 0.1776, "lr": 4.064631463146315e-05, "epoch": 1.625962596259626, "percentage": 8.13, "elapsed_time": "0:34:27", "remaining_time": "6:29:28", "throughput": 1507.4, "total_tokens": 3117248} {"current_steps": 14785, "total_steps": 181800, "loss": 0.0809, "lr": 4.0660066006600664e-05, "epoch": 1.6265126512651267, "percentage": 8.13, "elapsed_time": "0:34:28", "remaining_time": "6:29:28", "throughput": 1507.4, "total_tokens": 3118304} {"current_steps": 14790, "total_steps": 181800, "loss": 0.1556, "lr": 4.0673817381738176e-05, "epoch": 1.627062706270627, "percentage": 8.14, "elapsed_time": "0:34:29", "remaining_time": "6:29:27", "throughput": 1507.42, "total_tokens": 3119392} {"current_steps": 14795, "total_steps": 181800, "loss": 0.0971, "lr": 4.068756875687569e-05, "epoch": 1.6276127612761275, "percentage": 8.14, "elapsed_time": "0:34:30", "remaining_time": "6:29:26", "throughput": 1507.48, "total_tokens": 3120544} {"current_steps": 14800, "total_steps": 181800, "loss": 0.0986, "lr": 4.0701320132013206e-05, "epoch": 1.6281628162816282, "percentage": 8.14, "elapsed_time": "0:34:30", "remaining_time": "6:29:25", "throughput": 1507.49, "total_tokens": 3121600} {"current_steps": 14805, "total_steps": 181800, "loss": 0.1072, "lr": 4.071507150715072e-05, "epoch": 1.6287128712871288, "percentage": 8.14, "elapsed_time": "0:34:31", "remaining_time": "6:29:24", "throughput": 1507.49, "total_tokens": 3122656} {"current_steps": 14810, "total_steps": 181800, "loss": 0.0566, "lr": 4.072882288228823e-05, "epoch": 1.6292629262926293, "percentage": 8.15, "elapsed_time": "0:34:32", "remaining_time": "6:29:24", "throughput": 1507.51, "total_tokens": 3123712} {"current_steps": 14815, "total_steps": 181800, "loss": 0.042, "lr": 4.074257425742574e-05, "epoch": 1.6298129812981297, "percentage": 8.15, "elapsed_time": "0:34:32", "remaining_time": "6:29:23", "throughput": 1507.5, "total_tokens": 3124736} {"current_steps": 14820, "total_steps": 181800, "loss": 0.2045, "lr": 4.075632563256326e-05, "epoch": 1.6303630363036303, "percentage": 8.15, "elapsed_time": "0:34:33", "remaining_time": "6:29:22", "throughput": 1507.48, "total_tokens": 3125728} {"current_steps": 14825, "total_steps": 181800, "loss": 0.1253, "lr": 4.077007700770077e-05, "epoch": 1.630913091309131, "percentage": 8.15, "elapsed_time": "0:34:34", "remaining_time": "6:29:21", "throughput": 1507.51, "total_tokens": 3126816} {"current_steps": 14830, "total_steps": 181800, "loss": 0.1046, "lr": 4.078382838283828e-05, "epoch": 1.6314631463146316, "percentage": 8.16, "elapsed_time": "0:34:34", "remaining_time": "6:29:20", "throughput": 1507.53, "total_tokens": 3127904} {"current_steps": 14835, "total_steps": 181800, "loss": 0.0831, "lr": 4.07975797579758e-05, "epoch": 1.632013201320132, "percentage": 8.16, "elapsed_time": "0:34:35", "remaining_time": "6:29:19", "throughput": 1507.54, "total_tokens": 3128960} {"current_steps": 14840, "total_steps": 181800, "loss": 0.1523, "lr": 4.081133113311331e-05, "epoch": 1.6325632563256325, "percentage": 8.16, "elapsed_time": "0:34:36", "remaining_time": "6:29:18", "throughput": 1507.53, "total_tokens": 3129984} {"current_steps": 14845, "total_steps": 181800, "loss": 0.1265, "lr": 4.082508250825083e-05, "epoch": 1.6331133113311331, "percentage": 8.17, "elapsed_time": "0:34:36", "remaining_time": "6:29:18", "throughput": 1507.54, "total_tokens": 3131040} {"current_steps": 14850, "total_steps": 181800, "loss": 0.1154, "lr": 4.0838833883388336e-05, "epoch": 1.6336633663366338, "percentage": 8.17, "elapsed_time": "0:34:37", "remaining_time": "6:29:17", "throughput": 1507.55, "total_tokens": 3132096} {"current_steps": 14855, "total_steps": 181800, "loss": 0.0574, "lr": 4.0852585258525855e-05, "epoch": 1.6342134213421342, "percentage": 8.17, "elapsed_time": "0:34:38", "remaining_time": "6:29:16", "throughput": 1507.56, "total_tokens": 3133152} {"current_steps": 14860, "total_steps": 181800, "loss": 0.0502, "lr": 4.0866336633663366e-05, "epoch": 1.6347634763476346, "percentage": 8.17, "elapsed_time": "0:34:38", "remaining_time": "6:29:15", "throughput": 1507.59, "total_tokens": 3134272} {"current_steps": 14865, "total_steps": 181800, "loss": 0.1256, "lr": 4.0880088008800885e-05, "epoch": 1.6353135313531353, "percentage": 8.18, "elapsed_time": "0:34:39", "remaining_time": "6:29:14", "throughput": 1507.62, "total_tokens": 3135360} {"current_steps": 14870, "total_steps": 181800, "loss": 0.1097, "lr": 4.0893839383938396e-05, "epoch": 1.635863586358636, "percentage": 8.18, "elapsed_time": "0:34:40", "remaining_time": "6:29:16", "throughput": 1507.52, "total_tokens": 3136480} {"current_steps": 14875, "total_steps": 181800, "loss": 0.0715, "lr": 4.090759075907591e-05, "epoch": 1.6364136413641364, "percentage": 8.18, "elapsed_time": "0:34:41", "remaining_time": "6:29:15", "throughput": 1507.51, "total_tokens": 3137504} {"current_steps": 14880, "total_steps": 181800, "loss": 0.1592, "lr": 4.0921342134213426e-05, "epoch": 1.636963696369637, "percentage": 8.18, "elapsed_time": "0:34:41", "remaining_time": "6:29:14", "throughput": 1507.52, "total_tokens": 3138560} {"current_steps": 14885, "total_steps": 181800, "loss": 0.0425, "lr": 4.093509350935094e-05, "epoch": 1.6375137513751374, "percentage": 8.19, "elapsed_time": "0:34:42", "remaining_time": "6:29:13", "throughput": 1507.54, "total_tokens": 3139648} {"current_steps": 14890, "total_steps": 181800, "loss": 0.0749, "lr": 4.094884488448845e-05, "epoch": 1.638063806380638, "percentage": 8.19, "elapsed_time": "0:34:43", "remaining_time": "6:29:12", "throughput": 1507.55, "total_tokens": 3140704} {"current_steps": 14895, "total_steps": 181800, "loss": 0.1128, "lr": 4.096259625962596e-05, "epoch": 1.6386138613861387, "percentage": 8.19, "elapsed_time": "0:34:43", "remaining_time": "6:29:12", "throughput": 1507.56, "total_tokens": 3141760} {"current_steps": 14900, "total_steps": 181800, "loss": 0.103, "lr": 4.097634763476348e-05, "epoch": 1.6391639163916392, "percentage": 8.2, "elapsed_time": "0:34:44", "remaining_time": "6:29:11", "throughput": 1507.54, "total_tokens": 3142752} {"current_steps": 14905, "total_steps": 181800, "loss": 0.1108, "lr": 4.099009900990099e-05, "epoch": 1.6397139713971396, "percentage": 8.2, "elapsed_time": "0:34:45", "remaining_time": "6:29:10", "throughput": 1507.54, "total_tokens": 3143808} {"current_steps": 14910, "total_steps": 181800, "loss": 0.0832, "lr": 4.10038503850385e-05, "epoch": 1.6402640264026402, "percentage": 8.2, "elapsed_time": "0:34:46", "remaining_time": "6:29:09", "throughput": 1507.55, "total_tokens": 3144864} {"current_steps": 14915, "total_steps": 181800, "loss": 0.1163, "lr": 4.101760176017602e-05, "epoch": 1.640814081408141, "percentage": 8.2, "elapsed_time": "0:34:46", "remaining_time": "6:29:08", "throughput": 1507.55, "total_tokens": 3145888} {"current_steps": 14920, "total_steps": 181800, "loss": 0.1447, "lr": 4.103135313531353e-05, "epoch": 1.6413641364136413, "percentage": 8.21, "elapsed_time": "0:34:47", "remaining_time": "6:29:08", "throughput": 1507.53, "total_tokens": 3146880} {"current_steps": 14925, "total_steps": 181800, "loss": 0.0814, "lr": 4.104510451045105e-05, "epoch": 1.641914191419142, "percentage": 8.21, "elapsed_time": "0:34:48", "remaining_time": "6:29:07", "throughput": 1507.54, "total_tokens": 3147936} {"current_steps": 14930, "total_steps": 181800, "loss": 0.1023, "lr": 4.1058855885588557e-05, "epoch": 1.6424642464246424, "percentage": 8.21, "elapsed_time": "0:34:48", "remaining_time": "6:29:06", "throughput": 1507.6, "total_tokens": 3149088} {"current_steps": 14935, "total_steps": 181800, "loss": 0.0584, "lr": 4.1072607260726075e-05, "epoch": 1.643014301430143, "percentage": 8.22, "elapsed_time": "0:34:49", "remaining_time": "6:29:05", "throughput": 1507.62, "total_tokens": 3150176} {"current_steps": 14940, "total_steps": 181800, "loss": 0.1354, "lr": 4.108635863586359e-05, "epoch": 1.6435643564356437, "percentage": 8.22, "elapsed_time": "0:34:50", "remaining_time": "6:29:04", "throughput": 1507.68, "total_tokens": 3151328} {"current_steps": 14945, "total_steps": 181800, "loss": 0.0752, "lr": 4.1100110011001105e-05, "epoch": 1.6441144114411441, "percentage": 8.22, "elapsed_time": "0:34:50", "remaining_time": "6:29:03", "throughput": 1507.69, "total_tokens": 3152384} {"current_steps": 14950, "total_steps": 181800, "loss": 0.1351, "lr": 4.111386138613862e-05, "epoch": 1.6446644664466445, "percentage": 8.22, "elapsed_time": "0:34:51", "remaining_time": "6:29:02", "throughput": 1507.73, "total_tokens": 3153504} {"current_steps": 14955, "total_steps": 181800, "loss": 0.1925, "lr": 4.112761276127613e-05, "epoch": 1.6452145214521452, "percentage": 8.23, "elapsed_time": "0:34:52", "remaining_time": "6:29:02", "throughput": 1507.74, "total_tokens": 3154560} {"current_steps": 14960, "total_steps": 181800, "loss": 0.0948, "lr": 4.114136413641365e-05, "epoch": 1.6457645764576458, "percentage": 8.23, "elapsed_time": "0:34:52", "remaining_time": "6:29:01", "throughput": 1507.75, "total_tokens": 3155616} {"current_steps": 14965, "total_steps": 181800, "loss": 0.1161, "lr": 4.115511551155116e-05, "epoch": 1.6463146314631463, "percentage": 8.23, "elapsed_time": "0:34:53", "remaining_time": "6:29:00", "throughput": 1507.78, "total_tokens": 3156704} {"current_steps": 14970, "total_steps": 181800, "loss": 0.032, "lr": 4.116886688668867e-05, "epoch": 1.6468646864686467, "percentage": 8.23, "elapsed_time": "0:34:54", "remaining_time": "6:28:59", "throughput": 1507.77, "total_tokens": 3157728} {"current_steps": 14975, "total_steps": 181800, "loss": 0.1039, "lr": 4.118261826182618e-05, "epoch": 1.6474147414741473, "percentage": 8.24, "elapsed_time": "0:34:54", "remaining_time": "6:28:58", "throughput": 1507.77, "total_tokens": 3158752} {"current_steps": 14980, "total_steps": 181800, "loss": 0.0883, "lr": 4.11963696369637e-05, "epoch": 1.647964796479648, "percentage": 8.24, "elapsed_time": "0:34:55", "remaining_time": "6:28:57", "throughput": 1507.76, "total_tokens": 3159776} {"current_steps": 14985, "total_steps": 181800, "loss": 0.1227, "lr": 4.121012101210121e-05, "epoch": 1.6485148514851486, "percentage": 8.24, "elapsed_time": "0:34:56", "remaining_time": "6:28:56", "throughput": 1507.77, "total_tokens": 3160832} {"current_steps": 14990, "total_steps": 181800, "loss": 0.1196, "lr": 4.1223872387238724e-05, "epoch": 1.649064906490649, "percentage": 8.25, "elapsed_time": "0:34:57", "remaining_time": "6:28:56", "throughput": 1507.8, "total_tokens": 3161920} {"current_steps": 14995, "total_steps": 181800, "loss": 0.1516, "lr": 4.1237623762376235e-05, "epoch": 1.6496149614961495, "percentage": 8.25, "elapsed_time": "0:34:57", "remaining_time": "6:28:55", "throughput": 1507.86, "total_tokens": 3163072} {"current_steps": 15000, "total_steps": 181800, "loss": 0.0488, "lr": 4.1251375137513754e-05, "epoch": 1.6501650165016502, "percentage": 8.25, "elapsed_time": "0:34:58", "remaining_time": "6:28:54", "throughput": 1507.88, "total_tokens": 3164160} {"current_steps": 15005, "total_steps": 181800, "loss": 0.1238, "lr": 4.126512651265127e-05, "epoch": 1.6507150715071508, "percentage": 8.25, "elapsed_time": "0:34:59", "remaining_time": "6:28:53", "throughput": 1507.89, "total_tokens": 3165216} {"current_steps": 15010, "total_steps": 181800, "loss": 0.0862, "lr": 4.1278877887788784e-05, "epoch": 1.6512651265126512, "percentage": 8.26, "elapsed_time": "0:34:59", "remaining_time": "6:28:52", "throughput": 1507.92, "total_tokens": 3166304} {"current_steps": 15015, "total_steps": 181800, "loss": 0.0874, "lr": 4.1292629262926295e-05, "epoch": 1.6518151815181517, "percentage": 8.26, "elapsed_time": "0:35:00", "remaining_time": "6:28:51", "throughput": 1507.93, "total_tokens": 3167360} {"current_steps": 15020, "total_steps": 181800, "loss": 0.0781, "lr": 4.130638063806381e-05, "epoch": 1.6523652365236523, "percentage": 8.26, "elapsed_time": "0:35:01", "remaining_time": "6:28:51", "throughput": 1507.97, "total_tokens": 3168480} {"current_steps": 15025, "total_steps": 181800, "loss": 0.1461, "lr": 4.1320132013201325e-05, "epoch": 1.652915291529153, "percentage": 8.26, "elapsed_time": "0:35:01", "remaining_time": "6:28:50", "throughput": 1507.99, "total_tokens": 3169568} {"current_steps": 15030, "total_steps": 181800, "loss": 0.175, "lr": 4.133388338833884e-05, "epoch": 1.6534653465346536, "percentage": 8.27, "elapsed_time": "0:35:02", "remaining_time": "6:28:49", "throughput": 1507.98, "total_tokens": 3170592} {"current_steps": 15035, "total_steps": 181800, "loss": 0.1653, "lr": 4.134763476347635e-05, "epoch": 1.654015401540154, "percentage": 8.27, "elapsed_time": "0:35:03", "remaining_time": "6:28:48", "throughput": 1507.99, "total_tokens": 3171648} {"current_steps": 15040, "total_steps": 181800, "loss": 0.0767, "lr": 4.136138613861386e-05, "epoch": 1.6545654565456545, "percentage": 8.27, "elapsed_time": "0:35:03", "remaining_time": "6:28:47", "throughput": 1508.01, "total_tokens": 3172736} {"current_steps": 15045, "total_steps": 181800, "loss": 0.0897, "lr": 4.137513751375138e-05, "epoch": 1.655115511551155, "percentage": 8.28, "elapsed_time": "0:35:04", "remaining_time": "6:28:46", "throughput": 1508.03, "total_tokens": 3173792} {"current_steps": 15050, "total_steps": 181800, "loss": 0.1199, "lr": 4.138888888888889e-05, "epoch": 1.6556655665566558, "percentage": 8.28, "elapsed_time": "0:35:05", "remaining_time": "6:28:46", "throughput": 1508.05, "total_tokens": 3174880} {"current_steps": 15055, "total_steps": 181800, "loss": 0.1396, "lr": 4.14026402640264e-05, "epoch": 1.6562156215621562, "percentage": 8.28, "elapsed_time": "0:35:05", "remaining_time": "6:28:45", "throughput": 1508.07, "total_tokens": 3175968} {"current_steps": 15060, "total_steps": 181800, "loss": 0.0655, "lr": 4.141639163916392e-05, "epoch": 1.6567656765676566, "percentage": 8.28, "elapsed_time": "0:35:06", "remaining_time": "6:28:44", "throughput": 1508.1, "total_tokens": 3177056} {"current_steps": 15065, "total_steps": 181800, "loss": 0.1099, "lr": 4.143014301430143e-05, "epoch": 1.6573157315731573, "percentage": 8.29, "elapsed_time": "0:35:07", "remaining_time": "6:28:43", "throughput": 1508.12, "total_tokens": 3178144} {"current_steps": 15070, "total_steps": 181800, "loss": 0.0689, "lr": 4.144389438943895e-05, "epoch": 1.657865786578658, "percentage": 8.29, "elapsed_time": "0:35:08", "remaining_time": "6:28:42", "throughput": 1508.12, "total_tokens": 3179168} {"current_steps": 15075, "total_steps": 181800, "loss": 0.129, "lr": 4.1457645764576456e-05, "epoch": 1.6584158415841586, "percentage": 8.29, "elapsed_time": "0:35:08", "remaining_time": "6:28:41", "throughput": 1508.13, "total_tokens": 3180224} {"current_steps": 15080, "total_steps": 181800, "loss": 0.1117, "lr": 4.1471397139713974e-05, "epoch": 1.658965896589659, "percentage": 8.29, "elapsed_time": "0:35:09", "remaining_time": "6:28:40", "throughput": 1508.12, "total_tokens": 3181248} {"current_steps": 15085, "total_steps": 181800, "loss": 0.1607, "lr": 4.1485148514851486e-05, "epoch": 1.6595159515951594, "percentage": 8.3, "elapsed_time": "0:35:10", "remaining_time": "6:28:40", "throughput": 1508.15, "total_tokens": 3182336} {"current_steps": 15090, "total_steps": 181800, "loss": 0.1467, "lr": 4.1498899889989004e-05, "epoch": 1.66006600660066, "percentage": 8.3, "elapsed_time": "0:35:10", "remaining_time": "6:28:39", "throughput": 1508.16, "total_tokens": 3183392} {"current_steps": 15095, "total_steps": 181800, "loss": 0.1342, "lr": 4.151265126512651e-05, "epoch": 1.6606160616061607, "percentage": 8.3, "elapsed_time": "0:35:11", "remaining_time": "6:28:38", "throughput": 1508.18, "total_tokens": 3184480} {"current_steps": 15100, "total_steps": 181800, "loss": 0.1086, "lr": 4.152640264026403e-05, "epoch": 1.6611661166116611, "percentage": 8.31, "elapsed_time": "0:35:12", "remaining_time": "6:28:37", "throughput": 1508.16, "total_tokens": 3185472} {"current_steps": 15105, "total_steps": 181800, "loss": 0.1007, "lr": 4.1540154015401546e-05, "epoch": 1.6617161716171616, "percentage": 8.31, "elapsed_time": "0:35:12", "remaining_time": "6:28:36", "throughput": 1508.17, "total_tokens": 3186528} {"current_steps": 15110, "total_steps": 181800, "loss": 0.1539, "lr": 4.155390539053906e-05, "epoch": 1.6622662266226622, "percentage": 8.31, "elapsed_time": "0:35:13", "remaining_time": "6:28:35", "throughput": 1508.15, "total_tokens": 3187520} {"current_steps": 15115, "total_steps": 181800, "loss": 0.1052, "lr": 4.156765676567657e-05, "epoch": 1.6628162816281629, "percentage": 8.31, "elapsed_time": "0:35:14", "remaining_time": "6:28:35", "throughput": 1508.14, "total_tokens": 3188544} {"current_steps": 15120, "total_steps": 181800, "loss": 0.0939, "lr": 4.158140814081408e-05, "epoch": 1.6633663366336635, "percentage": 8.32, "elapsed_time": "0:35:14", "remaining_time": "6:28:34", "throughput": 1508.17, "total_tokens": 3189632} {"current_steps": 15125, "total_steps": 181800, "loss": 0.0966, "lr": 4.15951595159516e-05, "epoch": 1.663916391639164, "percentage": 8.32, "elapsed_time": "0:35:15", "remaining_time": "6:28:33", "throughput": 1508.17, "total_tokens": 3190688} {"current_steps": 15130, "total_steps": 181800, "loss": 0.1782, "lr": 4.160891089108911e-05, "epoch": 1.6644664466446644, "percentage": 8.32, "elapsed_time": "0:35:16", "remaining_time": "6:28:32", "throughput": 1508.17, "total_tokens": 3191712} {"current_steps": 15135, "total_steps": 181800, "loss": 0.0757, "lr": 4.162266226622662e-05, "epoch": 1.665016501650165, "percentage": 8.33, "elapsed_time": "0:35:16", "remaining_time": "6:28:31", "throughput": 1508.16, "total_tokens": 3192736} {"current_steps": 15140, "total_steps": 181800, "loss": 0.0851, "lr": 4.1636413641364134e-05, "epoch": 1.6655665566556657, "percentage": 8.33, "elapsed_time": "0:35:17", "remaining_time": "6:28:31", "throughput": 1508.14, "total_tokens": 3193728} {"current_steps": 15145, "total_steps": 181800, "loss": 0.1163, "lr": 4.165016501650165e-05, "epoch": 1.666116611661166, "percentage": 8.33, "elapsed_time": "0:35:18", "remaining_time": "6:28:30", "throughput": 1508.14, "total_tokens": 3194784} {"current_steps": 15150, "total_steps": 181800, "loss": 0.1196, "lr": 4.166391639163917e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:35:19", "remaining_time": "6:28:29", "throughput": 1508.15, "total_tokens": 3195840} {"current_steps": 15155, "total_steps": 181800, "loss": 0.1893, "lr": 4.1677667766776676e-05, "epoch": 1.6672167216721672, "percentage": 8.34, "elapsed_time": "0:35:19", "remaining_time": "6:28:28", "throughput": 1508.17, "total_tokens": 3196928} {"current_steps": 15160, "total_steps": 181800, "loss": 0.1531, "lr": 4.1691419141914194e-05, "epoch": 1.6677667766776678, "percentage": 8.34, "elapsed_time": "0:35:20", "remaining_time": "6:28:27", "throughput": 1508.2, "total_tokens": 3198016} {"current_steps": 15165, "total_steps": 181800, "loss": 0.0576, "lr": 4.1705170517051706e-05, "epoch": 1.6683168316831685, "percentage": 8.34, "elapsed_time": "0:35:21", "remaining_time": "6:28:27", "throughput": 1508.21, "total_tokens": 3199072} {"current_steps": 15170, "total_steps": 181800, "loss": 0.1697, "lr": 4.1718921892189224e-05, "epoch": 1.668866886688669, "percentage": 8.34, "elapsed_time": "0:35:21", "remaining_time": "6:28:26", "throughput": 1508.22, "total_tokens": 3200128} {"current_steps": 15175, "total_steps": 181800, "loss": 0.079, "lr": 4.1732673267326736e-05, "epoch": 1.6694169416941693, "percentage": 8.35, "elapsed_time": "0:35:22", "remaining_time": "6:28:25", "throughput": 1508.19, "total_tokens": 3201120} {"current_steps": 15180, "total_steps": 181800, "loss": 0.0825, "lr": 4.174642464246425e-05, "epoch": 1.66996699669967, "percentage": 8.35, "elapsed_time": "0:35:23", "remaining_time": "6:28:24", "throughput": 1508.17, "total_tokens": 3202112} {"current_steps": 15185, "total_steps": 181800, "loss": 0.0978, "lr": 4.176017601760176e-05, "epoch": 1.6705170517051706, "percentage": 8.35, "elapsed_time": "0:35:23", "remaining_time": "6:28:23", "throughput": 1508.17, "total_tokens": 3203136} {"current_steps": 15190, "total_steps": 181800, "loss": 0.0208, "lr": 4.177392739273928e-05, "epoch": 1.671067106710671, "percentage": 8.36, "elapsed_time": "0:35:24", "remaining_time": "6:28:22", "throughput": 1508.19, "total_tokens": 3204224} {"current_steps": 15195, "total_steps": 181800, "loss": 0.1143, "lr": 4.178767876787679e-05, "epoch": 1.6716171617161715, "percentage": 8.36, "elapsed_time": "0:35:25", "remaining_time": "6:28:22", "throughput": 1508.23, "total_tokens": 3205344} {"current_steps": 15200, "total_steps": 181800, "loss": 0.0981, "lr": 4.18014301430143e-05, "epoch": 1.6721672167216721, "percentage": 8.36, "elapsed_time": "0:35:25", "remaining_time": "6:28:21", "throughput": 1508.2, "total_tokens": 3206336} {"current_steps": 15205, "total_steps": 181800, "loss": 0.0809, "lr": 4.181518151815182e-05, "epoch": 1.6727172717271728, "percentage": 8.36, "elapsed_time": "0:35:26", "remaining_time": "6:28:20", "throughput": 1508.24, "total_tokens": 3207456} {"current_steps": 15210, "total_steps": 181800, "loss": 0.0666, "lr": 4.182893289328933e-05, "epoch": 1.6732673267326734, "percentage": 8.37, "elapsed_time": "0:35:27", "remaining_time": "6:28:19", "throughput": 1508.24, "total_tokens": 3208480} {"current_steps": 15215, "total_steps": 181800, "loss": 0.1273, "lr": 4.184268426842684e-05, "epoch": 1.6738173817381738, "percentage": 8.37, "elapsed_time": "0:35:27", "remaining_time": "6:28:18", "throughput": 1508.25, "total_tokens": 3209536} {"current_steps": 15220, "total_steps": 181800, "loss": 0.0737, "lr": 4.1856435643564355e-05, "epoch": 1.6743674367436743, "percentage": 8.37, "elapsed_time": "0:35:28", "remaining_time": "6:28:17", "throughput": 1508.26, "total_tokens": 3210592} {"current_steps": 15225, "total_steps": 181800, "loss": 0.0967, "lr": 4.187018701870187e-05, "epoch": 1.674917491749175, "percentage": 8.37, "elapsed_time": "0:35:29", "remaining_time": "6:28:17", "throughput": 1508.24, "total_tokens": 3211584} {"current_steps": 15230, "total_steps": 181800, "loss": 0.1702, "lr": 4.1883938393839385e-05, "epoch": 1.6754675467546756, "percentage": 8.38, "elapsed_time": "0:35:30", "remaining_time": "6:28:16", "throughput": 1508.25, "total_tokens": 3212640} {"current_steps": 15235, "total_steps": 181800, "loss": 0.0709, "lr": 4.18976897689769e-05, "epoch": 1.676017601760176, "percentage": 8.38, "elapsed_time": "0:35:30", "remaining_time": "6:28:15", "throughput": 1508.24, "total_tokens": 3213664} {"current_steps": 15240, "total_steps": 181800, "loss": 0.0658, "lr": 4.1911441144114415e-05, "epoch": 1.6765676567656764, "percentage": 8.38, "elapsed_time": "0:35:31", "remaining_time": "6:28:14", "throughput": 1508.28, "total_tokens": 3214784} {"current_steps": 15245, "total_steps": 181800, "loss": 0.0448, "lr": 4.1925192519251926e-05, "epoch": 1.677117711771177, "percentage": 8.39, "elapsed_time": "0:35:32", "remaining_time": "6:28:13", "throughput": 1508.3, "total_tokens": 3215872} {"current_steps": 15250, "total_steps": 181800, "loss": 0.037, "lr": 4.1938943894389445e-05, "epoch": 1.6776677667766777, "percentage": 8.39, "elapsed_time": "0:35:32", "remaining_time": "6:28:13", "throughput": 1508.29, "total_tokens": 3216896} {"current_steps": 15255, "total_steps": 181800, "loss": 0.0811, "lr": 4.1952695269526956e-05, "epoch": 1.6782178217821784, "percentage": 8.39, "elapsed_time": "0:35:33", "remaining_time": "6:28:12", "throughput": 1508.28, "total_tokens": 3217920} {"current_steps": 15260, "total_steps": 181800, "loss": 0.0625, "lr": 4.196644664466447e-05, "epoch": 1.6787678767876788, "percentage": 8.39, "elapsed_time": "0:35:34", "remaining_time": "6:28:11", "throughput": 1508.28, "total_tokens": 3218944} {"current_steps": 15265, "total_steps": 181800, "loss": 0.1784, "lr": 4.198019801980198e-05, "epoch": 1.6793179317931792, "percentage": 8.4, "elapsed_time": "0:35:34", "remaining_time": "6:28:10", "throughput": 1508.24, "total_tokens": 3219904} {"current_steps": 15270, "total_steps": 181800, "loss": 0.1247, "lr": 4.19939493949395e-05, "epoch": 1.6798679867986799, "percentage": 8.4, "elapsed_time": "0:35:35", "remaining_time": "6:28:09", "throughput": 1508.29, "total_tokens": 3221056} {"current_steps": 15275, "total_steps": 181800, "loss": 0.1465, "lr": 4.200770077007701e-05, "epoch": 1.6804180418041805, "percentage": 8.4, "elapsed_time": "0:35:36", "remaining_time": "6:28:08", "throughput": 1508.29, "total_tokens": 3222080} {"current_steps": 15280, "total_steps": 181800, "loss": 0.1757, "lr": 4.202145214521452e-05, "epoch": 1.680968096809681, "percentage": 8.4, "elapsed_time": "0:35:36", "remaining_time": "6:28:08", "throughput": 1508.34, "total_tokens": 3223232} {"current_steps": 15285, "total_steps": 181800, "loss": 0.0758, "lr": 4.203520352035203e-05, "epoch": 1.6815181518151814, "percentage": 8.41, "elapsed_time": "0:35:37", "remaining_time": "6:28:07", "throughput": 1508.34, "total_tokens": 3224256} {"current_steps": 15290, "total_steps": 181800, "loss": 0.0778, "lr": 4.204895489548955e-05, "epoch": 1.682068206820682, "percentage": 8.41, "elapsed_time": "0:35:38", "remaining_time": "6:28:06", "throughput": 1508.35, "total_tokens": 3225312} {"current_steps": 15295, "total_steps": 181800, "loss": 0.0783, "lr": 4.206270627062707e-05, "epoch": 1.6826182618261827, "percentage": 8.41, "elapsed_time": "0:35:38", "remaining_time": "6:28:05", "throughput": 1508.36, "total_tokens": 3226368} {"current_steps": 15300, "total_steps": 181800, "loss": 0.0702, "lr": 4.2076457645764575e-05, "epoch": 1.6831683168316833, "percentage": 8.42, "elapsed_time": "0:35:39", "remaining_time": "6:28:04", "throughput": 1508.37, "total_tokens": 3227424} {"current_steps": 15305, "total_steps": 181800, "loss": 0.0808, "lr": 4.209020902090209e-05, "epoch": 1.6837183718371838, "percentage": 8.42, "elapsed_time": "0:35:40", "remaining_time": "6:28:03", "throughput": 1508.39, "total_tokens": 3228512} {"current_steps": 15310, "total_steps": 181800, "loss": 0.096, "lr": 4.2103960396039605e-05, "epoch": 1.6842684268426842, "percentage": 8.42, "elapsed_time": "0:35:41", "remaining_time": "6:28:03", "throughput": 1508.37, "total_tokens": 3229504} {"current_steps": 15315, "total_steps": 181800, "loss": 0.1444, "lr": 4.2117711771177123e-05, "epoch": 1.6848184818481848, "percentage": 8.42, "elapsed_time": "0:35:41", "remaining_time": "6:28:02", "throughput": 1508.38, "total_tokens": 3230560} {"current_steps": 15320, "total_steps": 181800, "loss": 0.0891, "lr": 4.213146314631463e-05, "epoch": 1.6853685368536855, "percentage": 8.43, "elapsed_time": "0:35:42", "remaining_time": "6:28:01", "throughput": 1508.4, "total_tokens": 3231648} {"current_steps": 15325, "total_steps": 181800, "loss": 0.255, "lr": 4.214521452145215e-05, "epoch": 1.685918591859186, "percentage": 8.43, "elapsed_time": "0:35:43", "remaining_time": "6:28:00", "throughput": 1508.41, "total_tokens": 3232704} {"current_steps": 15330, "total_steps": 181800, "loss": 0.125, "lr": 4.215896589658966e-05, "epoch": 1.6864686468646863, "percentage": 8.43, "elapsed_time": "0:35:43", "remaining_time": "6:27:59", "throughput": 1508.44, "total_tokens": 3233824} {"current_steps": 15335, "total_steps": 181800, "loss": 0.0861, "lr": 4.217271727172718e-05, "epoch": 1.687018701870187, "percentage": 8.44, "elapsed_time": "0:35:44", "remaining_time": "6:27:59", "throughput": 1508.44, "total_tokens": 3234848} {"current_steps": 15340, "total_steps": 181800, "loss": 0.0509, "lr": 4.218646864686469e-05, "epoch": 1.6875687568756876, "percentage": 8.44, "elapsed_time": "0:35:45", "remaining_time": "6:27:58", "throughput": 1508.48, "total_tokens": 3235968} {"current_steps": 15345, "total_steps": 181800, "loss": 0.0621, "lr": 4.22002200220022e-05, "epoch": 1.688118811881188, "percentage": 8.44, "elapsed_time": "0:35:45", "remaining_time": "6:27:57", "throughput": 1508.48, "total_tokens": 3237024} {"current_steps": 15350, "total_steps": 181800, "loss": 0.1092, "lr": 4.221397139713972e-05, "epoch": 1.6886688668866887, "percentage": 8.44, "elapsed_time": "0:35:46", "remaining_time": "6:27:56", "throughput": 1508.51, "total_tokens": 3238112} {"current_steps": 15355, "total_steps": 181800, "loss": 0.1167, "lr": 4.222772277227723e-05, "epoch": 1.6892189218921891, "percentage": 8.45, "elapsed_time": "0:35:47", "remaining_time": "6:27:55", "throughput": 1508.5, "total_tokens": 3239136} {"current_steps": 15360, "total_steps": 181800, "loss": 0.1094, "lr": 4.224147414741474e-05, "epoch": 1.6897689768976898, "percentage": 8.45, "elapsed_time": "0:35:47", "remaining_time": "6:27:54", "throughput": 1508.49, "total_tokens": 3240160} {"current_steps": 15365, "total_steps": 181800, "loss": 0.0845, "lr": 4.2255225522552254e-05, "epoch": 1.6903190319031904, "percentage": 8.45, "elapsed_time": "0:35:48", "remaining_time": "6:27:54", "throughput": 1508.53, "total_tokens": 3241280} {"current_steps": 15370, "total_steps": 181800, "loss": 0.1051, "lr": 4.226897689768977e-05, "epoch": 1.6908690869086909, "percentage": 8.45, "elapsed_time": "0:35:49", "remaining_time": "6:27:53", "throughput": 1508.53, "total_tokens": 3242304} {"current_steps": 15375, "total_steps": 181800, "loss": 0.0448, "lr": 4.2282728272827284e-05, "epoch": 1.6914191419141913, "percentage": 8.46, "elapsed_time": "0:35:50", "remaining_time": "6:27:52", "throughput": 1508.52, "total_tokens": 3243328} {"current_steps": 15380, "total_steps": 181800, "loss": 0.16, "lr": 4.2296479647964795e-05, "epoch": 1.691969196919692, "percentage": 8.46, "elapsed_time": "0:35:50", "remaining_time": "6:27:51", "throughput": 1508.53, "total_tokens": 3244384} {"current_steps": 15385, "total_steps": 181800, "loss": 0.0777, "lr": 4.2310231023102314e-05, "epoch": 1.6925192519251926, "percentage": 8.46, "elapsed_time": "0:35:51", "remaining_time": "6:27:50", "throughput": 1508.56, "total_tokens": 3245472} {"current_steps": 15390, "total_steps": 181800, "loss": 0.1364, "lr": 4.2323982398239825e-05, "epoch": 1.693069306930693, "percentage": 8.47, "elapsed_time": "0:35:52", "remaining_time": "6:27:49", "throughput": 1508.57, "total_tokens": 3246528} {"current_steps": 15395, "total_steps": 181800, "loss": 0.1249, "lr": 4.2337733773377344e-05, "epoch": 1.6936193619361937, "percentage": 8.47, "elapsed_time": "0:35:52", "remaining_time": "6:27:49", "throughput": 1508.59, "total_tokens": 3247616} {"current_steps": 15400, "total_steps": 181800, "loss": 0.097, "lr": 4.2351485148514855e-05, "epoch": 1.694169416941694, "percentage": 8.47, "elapsed_time": "0:35:53", "remaining_time": "6:27:48", "throughput": 1508.63, "total_tokens": 3248736} {"current_steps": 15405, "total_steps": 181800, "loss": 0.0702, "lr": 4.236523652365237e-05, "epoch": 1.6947194719471947, "percentage": 8.47, "elapsed_time": "0:35:54", "remaining_time": "6:27:47", "throughput": 1508.66, "total_tokens": 3249824} {"current_steps": 15410, "total_steps": 181800, "loss": 0.0641, "lr": 4.237898789878988e-05, "epoch": 1.6952695269526954, "percentage": 8.48, "elapsed_time": "0:35:54", "remaining_time": "6:27:46", "throughput": 1508.66, "total_tokens": 3250880} {"current_steps": 15415, "total_steps": 181800, "loss": 0.1009, "lr": 4.23927392739274e-05, "epoch": 1.6958195819581958, "percentage": 8.48, "elapsed_time": "0:35:55", "remaining_time": "6:27:45", "throughput": 1508.64, "total_tokens": 3251872} {"current_steps": 15420, "total_steps": 181800, "loss": 0.0189, "lr": 4.240649064906491e-05, "epoch": 1.6963696369636962, "percentage": 8.48, "elapsed_time": "0:35:56", "remaining_time": "6:27:44", "throughput": 1508.65, "total_tokens": 3252928} {"current_steps": 15425, "total_steps": 181800, "loss": 0.0311, "lr": 4.242024202420242e-05, "epoch": 1.696919691969197, "percentage": 8.48, "elapsed_time": "0:35:56", "remaining_time": "6:27:44", "throughput": 1508.66, "total_tokens": 3253984} {"current_steps": 15430, "total_steps": 181800, "loss": 0.0716, "lr": 4.243399339933994e-05, "epoch": 1.6974697469746975, "percentage": 8.49, "elapsed_time": "0:35:57", "remaining_time": "6:27:43", "throughput": 1508.66, "total_tokens": 3255008} {"current_steps": 15435, "total_steps": 181800, "loss": 0.1489, "lr": 4.244774477447745e-05, "epoch": 1.698019801980198, "percentage": 8.49, "elapsed_time": "0:35:58", "remaining_time": "6:27:42", "throughput": 1508.68, "total_tokens": 3256096} {"current_steps": 15440, "total_steps": 181800, "loss": 0.0899, "lr": 4.246149614961496e-05, "epoch": 1.6985698569856986, "percentage": 8.49, "elapsed_time": "0:35:58", "remaining_time": "6:27:41", "throughput": 1508.7, "total_tokens": 3257184} {"current_steps": 15445, "total_steps": 181800, "loss": 0.1473, "lr": 4.2475247524752474e-05, "epoch": 1.699119911991199, "percentage": 8.5, "elapsed_time": "0:35:59", "remaining_time": "6:27:40", "throughput": 1508.7, "total_tokens": 3258208} {"current_steps": 15450, "total_steps": 181800, "loss": 0.164, "lr": 4.248899889988999e-05, "epoch": 1.6996699669966997, "percentage": 8.5, "elapsed_time": "0:36:00", "remaining_time": "6:27:40", "throughput": 1508.73, "total_tokens": 3259328} {"current_steps": 15455, "total_steps": 181800, "loss": 0.0794, "lr": 4.2502750275027504e-05, "epoch": 1.7002200220022003, "percentage": 8.5, "elapsed_time": "0:36:00", "remaining_time": "6:27:39", "throughput": 1508.76, "total_tokens": 3260416} {"current_steps": 15460, "total_steps": 181800, "loss": 0.1657, "lr": 4.251650165016502e-05, "epoch": 1.7007700770077008, "percentage": 8.5, "elapsed_time": "0:36:01", "remaining_time": "6:27:38", "throughput": 1508.79, "total_tokens": 3261536} {"current_steps": 15465, "total_steps": 181800, "loss": 0.0496, "lr": 4.253025302530253e-05, "epoch": 1.7013201320132012, "percentage": 8.51, "elapsed_time": "0:36:02", "remaining_time": "6:27:37", "throughput": 1508.86, "total_tokens": 3262720} {"current_steps": 15470, "total_steps": 181800, "loss": 0.0474, "lr": 4.2544004400440046e-05, "epoch": 1.7018701870187019, "percentage": 8.51, "elapsed_time": "0:36:03", "remaining_time": "6:27:36", "throughput": 1508.89, "total_tokens": 3263808} {"current_steps": 15475, "total_steps": 181800, "loss": 0.122, "lr": 4.2557755775577564e-05, "epoch": 1.7024202420242025, "percentage": 8.51, "elapsed_time": "0:36:03", "remaining_time": "6:27:35", "throughput": 1508.87, "total_tokens": 3264800} {"current_steps": 15480, "total_steps": 181800, "loss": 0.0354, "lr": 4.2571507150715076e-05, "epoch": 1.702970297029703, "percentage": 8.51, "elapsed_time": "0:36:04", "remaining_time": "6:27:35", "throughput": 1508.92, "total_tokens": 3265952} {"current_steps": 15485, "total_steps": 181800, "loss": 0.1348, "lr": 4.258525852585259e-05, "epoch": 1.7035203520352034, "percentage": 8.52, "elapsed_time": "0:36:05", "remaining_time": "6:27:34", "throughput": 1508.92, "total_tokens": 3266976} {"current_steps": 15490, "total_steps": 181800, "loss": 0.1244, "lr": 4.25990099009901e-05, "epoch": 1.704070407040704, "percentage": 8.52, "elapsed_time": "0:36:05", "remaining_time": "6:27:33", "throughput": 1508.9, "total_tokens": 3267968} {"current_steps": 15495, "total_steps": 181800, "loss": 0.0716, "lr": 4.261276127612762e-05, "epoch": 1.7046204620462047, "percentage": 8.52, "elapsed_time": "0:36:06", "remaining_time": "6:27:32", "throughput": 1508.92, "total_tokens": 3269056} {"current_steps": 15500, "total_steps": 181800, "loss": 0.0842, "lr": 4.262651265126513e-05, "epoch": 1.7051705170517053, "percentage": 8.53, "elapsed_time": "0:36:07", "remaining_time": "6:27:31", "throughput": 1508.91, "total_tokens": 3270080} {"current_steps": 15505, "total_steps": 181800, "loss": 0.1819, "lr": 4.264026402640264e-05, "epoch": 1.7057205720572057, "percentage": 8.53, "elapsed_time": "0:36:07", "remaining_time": "6:27:30", "throughput": 1508.91, "total_tokens": 3271104} {"current_steps": 15510, "total_steps": 181800, "loss": 0.0481, "lr": 4.265401540154015e-05, "epoch": 1.7062706270627062, "percentage": 8.53, "elapsed_time": "0:36:08", "remaining_time": "6:27:30", "throughput": 1508.9, "total_tokens": 3272128} {"current_steps": 15515, "total_steps": 181800, "loss": 0.1731, "lr": 4.266776677667767e-05, "epoch": 1.7068206820682068, "percentage": 8.53, "elapsed_time": "0:36:09", "remaining_time": "6:27:29", "throughput": 1508.93, "total_tokens": 3273248} {"current_steps": 15520, "total_steps": 181800, "loss": 0.186, "lr": 4.268151815181519e-05, "epoch": 1.7073707370737075, "percentage": 8.54, "elapsed_time": "0:36:09", "remaining_time": "6:27:28", "throughput": 1508.93, "total_tokens": 3274272} {"current_steps": 15525, "total_steps": 181800, "loss": 0.078, "lr": 4.2695269526952694e-05, "epoch": 1.7079207920792079, "percentage": 8.54, "elapsed_time": "0:36:10", "remaining_time": "6:27:27", "throughput": 1508.89, "total_tokens": 3275232} {"current_steps": 15530, "total_steps": 181800, "loss": 0.0898, "lr": 4.270902090209021e-05, "epoch": 1.7084708470847083, "percentage": 8.54, "elapsed_time": "0:36:11", "remaining_time": "6:27:26", "throughput": 1508.88, "total_tokens": 3276256} {"current_steps": 15535, "total_steps": 181800, "loss": 0.2946, "lr": 4.2722772277227724e-05, "epoch": 1.709020902090209, "percentage": 8.55, "elapsed_time": "0:36:11", "remaining_time": "6:27:26", "throughput": 1508.88, "total_tokens": 3277280} {"current_steps": 15540, "total_steps": 181800, "loss": 0.108, "lr": 4.273652365236524e-05, "epoch": 1.7095709570957096, "percentage": 8.55, "elapsed_time": "0:36:12", "remaining_time": "6:27:25", "throughput": 1508.86, "total_tokens": 3278272} {"current_steps": 15545, "total_steps": 181800, "loss": 0.0837, "lr": 4.275027502750275e-05, "epoch": 1.7101210121012103, "percentage": 8.55, "elapsed_time": "0:36:13", "remaining_time": "6:27:24", "throughput": 1508.88, "total_tokens": 3279360} {"current_steps": 15550, "total_steps": 181800, "loss": 0.0643, "lr": 4.2764026402640266e-05, "epoch": 1.7106710671067107, "percentage": 8.55, "elapsed_time": "0:36:14", "remaining_time": "6:27:23", "throughput": 1508.91, "total_tokens": 3280448} {"current_steps": 15555, "total_steps": 181800, "loss": 0.0944, "lr": 4.277777777777778e-05, "epoch": 1.7112211221122111, "percentage": 8.56, "elapsed_time": "0:36:14", "remaining_time": "6:27:22", "throughput": 1508.9, "total_tokens": 3281472} {"current_steps": 15560, "total_steps": 181800, "loss": 0.072, "lr": 4.2791529152915296e-05, "epoch": 1.7117711771177118, "percentage": 8.56, "elapsed_time": "0:36:15", "remaining_time": "6:27:21", "throughput": 1508.91, "total_tokens": 3282528} {"current_steps": 15565, "total_steps": 181800, "loss": 0.1411, "lr": 4.280528052805281e-05, "epoch": 1.7123212321232124, "percentage": 8.56, "elapsed_time": "0:36:16", "remaining_time": "6:27:21", "throughput": 1508.92, "total_tokens": 3283584} {"current_steps": 15570, "total_steps": 181800, "loss": 0.1073, "lr": 4.281903190319032e-05, "epoch": 1.7128712871287128, "percentage": 8.56, "elapsed_time": "0:36:16", "remaining_time": "6:27:20", "throughput": 1508.91, "total_tokens": 3284608} {"current_steps": 15575, "total_steps": 181800, "loss": 0.0272, "lr": 4.283278327832784e-05, "epoch": 1.7134213421342133, "percentage": 8.57, "elapsed_time": "0:36:17", "remaining_time": "6:27:19", "throughput": 1508.89, "total_tokens": 3285600} {"current_steps": 15580, "total_steps": 181800, "loss": 0.0671, "lr": 4.284653465346535e-05, "epoch": 1.713971397139714, "percentage": 8.57, "elapsed_time": "0:36:18", "remaining_time": "6:27:18", "throughput": 1508.92, "total_tokens": 3286688} {"current_steps": 15585, "total_steps": 181800, "loss": 0.0995, "lr": 4.286028602860286e-05, "epoch": 1.7145214521452146, "percentage": 8.57, "elapsed_time": "0:36:18", "remaining_time": "6:27:17", "throughput": 1508.95, "total_tokens": 3287808} {"current_steps": 15590, "total_steps": 181800, "loss": 0.0878, "lr": 4.287403740374037e-05, "epoch": 1.7150715071507152, "percentage": 8.58, "elapsed_time": "0:36:19", "remaining_time": "6:27:16", "throughput": 1508.97, "total_tokens": 3288864} {"current_steps": 15595, "total_steps": 181800, "loss": 0.1534, "lr": 4.288778877887789e-05, "epoch": 1.7156215621562156, "percentage": 8.58, "elapsed_time": "0:36:20", "remaining_time": "6:27:16", "throughput": 1508.98, "total_tokens": 3289920} {"current_steps": 15600, "total_steps": 181800, "loss": 0.0287, "lr": 4.29015401540154e-05, "epoch": 1.716171617161716, "percentage": 8.58, "elapsed_time": "0:36:20", "remaining_time": "6:27:15", "throughput": 1508.98, "total_tokens": 3290976} {"current_steps": 15605, "total_steps": 181800, "loss": 0.1828, "lr": 4.2915291529152915e-05, "epoch": 1.7167216721672167, "percentage": 8.58, "elapsed_time": "0:36:21", "remaining_time": "6:27:14", "throughput": 1508.98, "total_tokens": 3292000} {"current_steps": 15610, "total_steps": 181800, "loss": 0.1251, "lr": 4.2929042904290426e-05, "epoch": 1.7172717271727174, "percentage": 8.59, "elapsed_time": "0:36:22", "remaining_time": "6:27:13", "throughput": 1508.99, "total_tokens": 3293056} {"current_steps": 15615, "total_steps": 181800, "loss": 0.1131, "lr": 4.2942794279427945e-05, "epoch": 1.7178217821782178, "percentage": 8.59, "elapsed_time": "0:36:22", "remaining_time": "6:27:12", "throughput": 1508.98, "total_tokens": 3294080} {"current_steps": 15620, "total_steps": 181800, "loss": 0.1737, "lr": 4.295654565456546e-05, "epoch": 1.7183718371837182, "percentage": 8.59, "elapsed_time": "0:36:23", "remaining_time": "6:27:11", "throughput": 1508.99, "total_tokens": 3295136} {"current_steps": 15625, "total_steps": 181800, "loss": 0.1018, "lr": 4.2970297029702975e-05, "epoch": 1.7189218921892189, "percentage": 8.59, "elapsed_time": "0:36:24", "remaining_time": "6:27:11", "throughput": 1509.04, "total_tokens": 3296288} {"current_steps": 15630, "total_steps": 181800, "loss": 0.038, "lr": 4.2984048404840487e-05, "epoch": 1.7194719471947195, "percentage": 8.6, "elapsed_time": "0:36:25", "remaining_time": "6:27:10", "throughput": 1509.05, "total_tokens": 3297344} {"current_steps": 15635, "total_steps": 181800, "loss": 0.0741, "lr": 4.2997799779978e-05, "epoch": 1.7200220022002202, "percentage": 8.6, "elapsed_time": "0:36:25", "remaining_time": "6:27:09", "throughput": 1509.08, "total_tokens": 3298432} {"current_steps": 15640, "total_steps": 181800, "loss": 0.0639, "lr": 4.3011551155115517e-05, "epoch": 1.7205720572057206, "percentage": 8.6, "elapsed_time": "0:36:26", "remaining_time": "6:27:08", "throughput": 1509.06, "total_tokens": 3299424} {"current_steps": 15645, "total_steps": 181800, "loss": 0.0746, "lr": 4.302530253025303e-05, "epoch": 1.721122112211221, "percentage": 8.61, "elapsed_time": "0:36:27", "remaining_time": "6:27:07", "throughput": 1509.06, "total_tokens": 3300480} {"current_steps": 15650, "total_steps": 181800, "loss": 0.1, "lr": 4.303905390539054e-05, "epoch": 1.7216721672167217, "percentage": 8.61, "elapsed_time": "0:36:27", "remaining_time": "6:27:06", "throughput": 1509.06, "total_tokens": 3301504} {"current_steps": 15655, "total_steps": 181800, "loss": 0.0596, "lr": 4.305280528052805e-05, "epoch": 1.7222222222222223, "percentage": 8.61, "elapsed_time": "0:36:28", "remaining_time": "6:27:06", "throughput": 1509.11, "total_tokens": 3302656} {"current_steps": 15660, "total_steps": 181800, "loss": 0.0758, "lr": 4.306655665566557e-05, "epoch": 1.7227722772277227, "percentage": 8.61, "elapsed_time": "0:36:29", "remaining_time": "6:27:05", "throughput": 1509.12, "total_tokens": 3303712} {"current_steps": 15665, "total_steps": 181800, "loss": 0.0311, "lr": 4.308030803080308e-05, "epoch": 1.7233223322332232, "percentage": 8.62, "elapsed_time": "0:36:29", "remaining_time": "6:27:04", "throughput": 1509.14, "total_tokens": 3304800} {"current_steps": 15670, "total_steps": 181800, "loss": 0.0817, "lr": 4.309405940594059e-05, "epoch": 1.7238723872387238, "percentage": 8.62, "elapsed_time": "0:36:30", "remaining_time": "6:27:03", "throughput": 1509.12, "total_tokens": 3305792} {"current_steps": 15675, "total_steps": 181800, "loss": 0.105, "lr": 4.310781078107811e-05, "epoch": 1.7244224422442245, "percentage": 8.62, "elapsed_time": "0:36:31", "remaining_time": "6:27:02", "throughput": 1509.13, "total_tokens": 3306848} {"current_steps": 15680, "total_steps": 181800, "loss": 0.0245, "lr": 4.3121562156215623e-05, "epoch": 1.7249724972497251, "percentage": 8.62, "elapsed_time": "0:36:31", "remaining_time": "6:27:01", "throughput": 1509.13, "total_tokens": 3307872} {"current_steps": 15685, "total_steps": 181800, "loss": 0.2154, "lr": 4.313531353135314e-05, "epoch": 1.7255225522552256, "percentage": 8.63, "elapsed_time": "0:36:32", "remaining_time": "6:27:01", "throughput": 1509.14, "total_tokens": 3308928} {"current_steps": 15690, "total_steps": 181800, "loss": 0.1612, "lr": 4.314906490649065e-05, "epoch": 1.726072607260726, "percentage": 8.63, "elapsed_time": "0:36:33", "remaining_time": "6:27:00", "throughput": 1509.14, "total_tokens": 3309984} {"current_steps": 15695, "total_steps": 181800, "loss": 0.1603, "lr": 4.3162816281628165e-05, "epoch": 1.7266226622662266, "percentage": 8.63, "elapsed_time": "0:36:33", "remaining_time": "6:26:59", "throughput": 1509.15, "total_tokens": 3311040} {"current_steps": 15700, "total_steps": 181800, "loss": 0.0787, "lr": 4.317656765676568e-05, "epoch": 1.7271727172717273, "percentage": 8.64, "elapsed_time": "0:36:34", "remaining_time": "6:26:58", "throughput": 1509.2, "total_tokens": 3312192} {"current_steps": 15705, "total_steps": 181800, "loss": 0.0351, "lr": 4.3190319031903195e-05, "epoch": 1.7277227722772277, "percentage": 8.64, "elapsed_time": "0:36:35", "remaining_time": "6:26:57", "throughput": 1509.2, "total_tokens": 3313216} {"current_steps": 15710, "total_steps": 181800, "loss": 0.1661, "lr": 4.320407040704071e-05, "epoch": 1.7282728272827281, "percentage": 8.64, "elapsed_time": "0:36:36", "remaining_time": "6:26:57", "throughput": 1509.19, "total_tokens": 3314240} {"current_steps": 15715, "total_steps": 181800, "loss": 0.0399, "lr": 4.321782178217822e-05, "epoch": 1.7288228822882288, "percentage": 8.64, "elapsed_time": "0:36:36", "remaining_time": "6:26:56", "throughput": 1509.2, "total_tokens": 3315296} {"current_steps": 15720, "total_steps": 181800, "loss": 0.1276, "lr": 4.323157315731574e-05, "epoch": 1.7293729372937294, "percentage": 8.65, "elapsed_time": "0:36:37", "remaining_time": "6:26:55", "throughput": 1509.17, "total_tokens": 3316288} {"current_steps": 15725, "total_steps": 181800, "loss": 0.1156, "lr": 4.324532453245325e-05, "epoch": 1.72992299229923, "percentage": 8.65, "elapsed_time": "0:36:38", "remaining_time": "6:26:54", "throughput": 1509.2, "total_tokens": 3317376} {"current_steps": 15730, "total_steps": 181800, "loss": 0.0942, "lr": 4.325907590759076e-05, "epoch": 1.7304730473047305, "percentage": 8.65, "elapsed_time": "0:36:38", "remaining_time": "6:26:53", "throughput": 1509.22, "total_tokens": 3318464} {"current_steps": 15735, "total_steps": 181800, "loss": 0.0444, "lr": 4.327282728272827e-05, "epoch": 1.731023102310231, "percentage": 8.66, "elapsed_time": "0:36:39", "remaining_time": "6:26:52", "throughput": 1509.23, "total_tokens": 3319520} {"current_steps": 15740, "total_steps": 181800, "loss": 0.0969, "lr": 4.328657865786579e-05, "epoch": 1.7315731573157316, "percentage": 8.66, "elapsed_time": "0:36:40", "remaining_time": "6:26:52", "throughput": 1509.24, "total_tokens": 3320576} {"current_steps": 15745, "total_steps": 181800, "loss": 0.0783, "lr": 4.33003300330033e-05, "epoch": 1.7321232123212322, "percentage": 8.66, "elapsed_time": "0:36:40", "remaining_time": "6:26:51", "throughput": 1509.21, "total_tokens": 3321536} {"current_steps": 15750, "total_steps": 181800, "loss": 0.1781, "lr": 4.3314081408140814e-05, "epoch": 1.7326732673267327, "percentage": 8.66, "elapsed_time": "0:36:41", "remaining_time": "6:26:50", "throughput": 1509.22, "total_tokens": 3322592} {"current_steps": 15755, "total_steps": 181800, "loss": 0.1997, "lr": 4.332783278327833e-05, "epoch": 1.733223322332233, "percentage": 8.67, "elapsed_time": "0:36:42", "remaining_time": "6:26:49", "throughput": 1509.25, "total_tokens": 3323712} {"current_steps": 15760, "total_steps": 181800, "loss": 0.0422, "lr": 4.3341584158415844e-05, "epoch": 1.7337733773377337, "percentage": 8.67, "elapsed_time": "0:36:42", "remaining_time": "6:26:48", "throughput": 1509.26, "total_tokens": 3324768} {"current_steps": 15765, "total_steps": 181800, "loss": 0.0793, "lr": 4.335533553355336e-05, "epoch": 1.7343234323432344, "percentage": 8.67, "elapsed_time": "0:36:43", "remaining_time": "6:26:48", "throughput": 1509.27, "total_tokens": 3325824} {"current_steps": 15770, "total_steps": 181800, "loss": 0.0469, "lr": 4.336908690869087e-05, "epoch": 1.734873487348735, "percentage": 8.67, "elapsed_time": "0:36:44", "remaining_time": "6:26:47", "throughput": 1509.27, "total_tokens": 3326880} {"current_steps": 15775, "total_steps": 181800, "loss": 0.0799, "lr": 4.3382838283828386e-05, "epoch": 1.7354235423542355, "percentage": 8.68, "elapsed_time": "0:36:44", "remaining_time": "6:26:46", "throughput": 1509.26, "total_tokens": 3327904} {"current_steps": 15780, "total_steps": 181800, "loss": 0.1298, "lr": 4.33965896589659e-05, "epoch": 1.7359735973597359, "percentage": 8.68, "elapsed_time": "0:36:45", "remaining_time": "6:26:45", "throughput": 1509.27, "total_tokens": 3328960} {"current_steps": 15785, "total_steps": 181800, "loss": 0.0966, "lr": 4.3410341034103416e-05, "epoch": 1.7365236523652365, "percentage": 8.68, "elapsed_time": "0:36:46", "remaining_time": "6:26:44", "throughput": 1509.27, "total_tokens": 3330016} {"current_steps": 15790, "total_steps": 181800, "loss": 0.0648, "lr": 4.342409240924093e-05, "epoch": 1.7370737073707372, "percentage": 8.69, "elapsed_time": "0:36:47", "remaining_time": "6:26:44", "throughput": 1509.26, "total_tokens": 3331040} {"current_steps": 15795, "total_steps": 181800, "loss": 0.0946, "lr": 4.343784378437844e-05, "epoch": 1.7376237623762376, "percentage": 8.69, "elapsed_time": "0:36:47", "remaining_time": "6:26:43", "throughput": 1509.29, "total_tokens": 3332128} {"current_steps": 15800, "total_steps": 181800, "loss": 0.0508, "lr": 4.345159515951595e-05, "epoch": 1.738173817381738, "percentage": 8.69, "elapsed_time": "0:36:48", "remaining_time": "6:26:42", "throughput": 1509.31, "total_tokens": 3333216} {"current_steps": 15805, "total_steps": 181800, "loss": 0.0781, "lr": 4.346534653465347e-05, "epoch": 1.7387238723872387, "percentage": 8.69, "elapsed_time": "0:36:49", "remaining_time": "6:26:41", "throughput": 1509.31, "total_tokens": 3334240} {"current_steps": 15810, "total_steps": 181800, "loss": 0.0844, "lr": 4.347909790979098e-05, "epoch": 1.7392739273927393, "percentage": 8.7, "elapsed_time": "0:36:49", "remaining_time": "6:26:40", "throughput": 1509.33, "total_tokens": 3335328} {"current_steps": 15815, "total_steps": 181800, "loss": 0.1554, "lr": 4.349284928492849e-05, "epoch": 1.73982398239824, "percentage": 8.7, "elapsed_time": "0:36:50", "remaining_time": "6:26:40", "throughput": 1509.3, "total_tokens": 3336288} {"current_steps": 15820, "total_steps": 181800, "loss": 0.0687, "lr": 4.350660066006601e-05, "epoch": 1.7403740374037404, "percentage": 8.7, "elapsed_time": "0:36:51", "remaining_time": "6:26:39", "throughput": 1509.3, "total_tokens": 3337344} {"current_steps": 15825, "total_steps": 181800, "loss": 0.0484, "lr": 4.352035203520352e-05, "epoch": 1.7409240924092408, "percentage": 8.7, "elapsed_time": "0:36:51", "remaining_time": "6:26:38", "throughput": 1509.3, "total_tokens": 3338368} {"current_steps": 15830, "total_steps": 181800, "loss": 0.0466, "lr": 4.3534103410341034e-05, "epoch": 1.7414741474147415, "percentage": 8.71, "elapsed_time": "0:36:52", "remaining_time": "6:26:37", "throughput": 1509.31, "total_tokens": 3339424} {"current_steps": 15835, "total_steps": 181800, "loss": 0.0742, "lr": 4.3547854785478546e-05, "epoch": 1.7420242024202421, "percentage": 8.71, "elapsed_time": "0:36:53", "remaining_time": "6:26:36", "throughput": 1509.33, "total_tokens": 3340512} {"current_steps": 15840, "total_steps": 181800, "loss": 0.0491, "lr": 4.3561606160616064e-05, "epoch": 1.7425742574257426, "percentage": 8.71, "elapsed_time": "0:36:53", "remaining_time": "6:26:35", "throughput": 1509.34, "total_tokens": 3341568} {"current_steps": 15845, "total_steps": 181800, "loss": 0.1068, "lr": 4.3575357535753576e-05, "epoch": 1.743124312431243, "percentage": 8.72, "elapsed_time": "0:36:54", "remaining_time": "6:26:35", "throughput": 1509.38, "total_tokens": 3342688} {"current_steps": 15850, "total_steps": 181800, "loss": 0.0781, "lr": 4.3589108910891094e-05, "epoch": 1.7436743674367436, "percentage": 8.72, "elapsed_time": "0:36:55", "remaining_time": "6:26:34", "throughput": 1509.35, "total_tokens": 3343680} {"current_steps": 15855, "total_steps": 181800, "loss": 0.1217, "lr": 4.3602860286028606e-05, "epoch": 1.7442244224422443, "percentage": 8.72, "elapsed_time": "0:36:55", "remaining_time": "6:26:33", "throughput": 1509.36, "total_tokens": 3344736} {"current_steps": 15860, "total_steps": 181800, "loss": 0.2101, "lr": 4.361661166116612e-05, "epoch": 1.7447744774477447, "percentage": 8.72, "elapsed_time": "0:36:56", "remaining_time": "6:26:32", "throughput": 1509.35, "total_tokens": 3345760} {"current_steps": 15865, "total_steps": 181800, "loss": 0.0675, "lr": 4.3630363036303636e-05, "epoch": 1.7453245324532454, "percentage": 8.73, "elapsed_time": "0:36:57", "remaining_time": "6:26:31", "throughput": 1509.36, "total_tokens": 3346816} {"current_steps": 15870, "total_steps": 181800, "loss": 0.152, "lr": 4.364411441144115e-05, "epoch": 1.7458745874587458, "percentage": 8.73, "elapsed_time": "0:36:58", "remaining_time": "6:26:31", "throughput": 1509.37, "total_tokens": 3347872} {"current_steps": 15875, "total_steps": 181800, "loss": 0.1121, "lr": 4.365786578657866e-05, "epoch": 1.7464246424642464, "percentage": 8.73, "elapsed_time": "0:36:58", "remaining_time": "6:26:30", "throughput": 1509.38, "total_tokens": 3348928} {"current_steps": 15880, "total_steps": 181800, "loss": 0.0526, "lr": 4.367161716171617e-05, "epoch": 1.746974697469747, "percentage": 8.73, "elapsed_time": "0:36:59", "remaining_time": "6:26:29", "throughput": 1509.41, "total_tokens": 3350048} {"current_steps": 15885, "total_steps": 181800, "loss": 0.1025, "lr": 4.368536853685369e-05, "epoch": 1.7475247524752475, "percentage": 8.74, "elapsed_time": "0:37:00", "remaining_time": "6:26:28", "throughput": 1509.39, "total_tokens": 3351040} {"current_steps": 15890, "total_steps": 181800, "loss": 0.0412, "lr": 4.36991199119912e-05, "epoch": 1.748074807480748, "percentage": 8.74, "elapsed_time": "0:37:00", "remaining_time": "6:26:27", "throughput": 1509.39, "total_tokens": 3352096} {"current_steps": 15895, "total_steps": 181800, "loss": 0.0802, "lr": 4.371287128712871e-05, "epoch": 1.7486248624862486, "percentage": 8.74, "elapsed_time": "0:37:01", "remaining_time": "6:26:27", "throughput": 1509.42, "total_tokens": 3353184} {"current_steps": 15900, "total_steps": 181800, "loss": 0.0389, "lr": 4.372662266226623e-05, "epoch": 1.7491749174917492, "percentage": 8.75, "elapsed_time": "0:37:02", "remaining_time": "6:26:26", "throughput": 1509.44, "total_tokens": 3354272} {"current_steps": 15905, "total_steps": 181800, "loss": 0.1421, "lr": 4.374037403740374e-05, "epoch": 1.7497249724972497, "percentage": 8.75, "elapsed_time": "0:37:02", "remaining_time": "6:26:25", "throughput": 1509.45, "total_tokens": 3355328} {"current_steps": 15910, "total_steps": 181800, "loss": 0.0354, "lr": 4.375412541254126e-05, "epoch": 1.7502750275027503, "percentage": 8.75, "elapsed_time": "0:37:03", "remaining_time": "6:26:24", "throughput": 1509.47, "total_tokens": 3356416} {"current_steps": 15915, "total_steps": 181800, "loss": 0.1136, "lr": 4.3767876787678766e-05, "epoch": 1.7508250825082508, "percentage": 8.75, "elapsed_time": "0:37:04", "remaining_time": "6:26:23", "throughput": 1509.47, "total_tokens": 3357440} {"current_steps": 15920, "total_steps": 181800, "loss": 0.1453, "lr": 4.3781628162816284e-05, "epoch": 1.7513751375137514, "percentage": 8.76, "elapsed_time": "0:37:04", "remaining_time": "6:26:23", "throughput": 1509.5, "total_tokens": 3358560} {"current_steps": 15925, "total_steps": 181800, "loss": 0.0781, "lr": 4.3795379537953796e-05, "epoch": 1.751925192519252, "percentage": 8.76, "elapsed_time": "0:37:05", "remaining_time": "6:26:22", "throughput": 1509.52, "total_tokens": 3359648} {"current_steps": 15930, "total_steps": 181800, "loss": 0.1173, "lr": 4.3809130913091315e-05, "epoch": 1.7524752475247525, "percentage": 8.76, "elapsed_time": "0:37:06", "remaining_time": "6:26:21", "throughput": 1509.52, "total_tokens": 3360672} {"current_steps": 15935, "total_steps": 181800, "loss": 0.1526, "lr": 4.382288228822882e-05, "epoch": 1.753025302530253, "percentage": 8.77, "elapsed_time": "0:37:07", "remaining_time": "6:26:20", "throughput": 1509.51, "total_tokens": 3361696} {"current_steps": 15940, "total_steps": 181800, "loss": 0.1671, "lr": 4.383663366336634e-05, "epoch": 1.7535753575357536, "percentage": 8.77, "elapsed_time": "0:37:07", "remaining_time": "6:26:19", "throughput": 1509.51, "total_tokens": 3362720} {"current_steps": 15945, "total_steps": 181800, "loss": 0.0469, "lr": 4.3850385038503856e-05, "epoch": 1.7541254125412542, "percentage": 8.77, "elapsed_time": "0:37:08", "remaining_time": "6:26:18", "throughput": 1509.51, "total_tokens": 3363776} {"current_steps": 15950, "total_steps": 181800, "loss": 0.103, "lr": 4.386413641364137e-05, "epoch": 1.7546754675467546, "percentage": 8.77, "elapsed_time": "0:37:09", "remaining_time": "6:26:18", "throughput": 1509.52, "total_tokens": 3364832} {"current_steps": 15955, "total_steps": 181800, "loss": 0.1147, "lr": 4.387788778877888e-05, "epoch": 1.7552255225522553, "percentage": 8.78, "elapsed_time": "0:37:09", "remaining_time": "6:26:17", "throughput": 1509.52, "total_tokens": 3365856} {"current_steps": 15960, "total_steps": 181800, "loss": 0.0925, "lr": 4.389163916391639e-05, "epoch": 1.7557755775577557, "percentage": 8.78, "elapsed_time": "0:37:10", "remaining_time": "6:26:16", "throughput": 1509.56, "total_tokens": 3366976} {"current_steps": 15965, "total_steps": 181800, "loss": 0.0673, "lr": 4.390539053905391e-05, "epoch": 1.7563256325632564, "percentage": 8.78, "elapsed_time": "0:37:11", "remaining_time": "6:26:15", "throughput": 1509.57, "total_tokens": 3368032} {"current_steps": 15970, "total_steps": 181800, "loss": 0.0467, "lr": 4.391914191419142e-05, "epoch": 1.756875687568757, "percentage": 8.78, "elapsed_time": "0:37:11", "remaining_time": "6:26:14", "throughput": 1509.58, "total_tokens": 3369088} {"current_steps": 15975, "total_steps": 181800, "loss": 0.0313, "lr": 4.393289328932893e-05, "epoch": 1.7574257425742574, "percentage": 8.79, "elapsed_time": "0:37:12", "remaining_time": "6:26:14", "throughput": 1509.58, "total_tokens": 3370144} {"current_steps": 15980, "total_steps": 181800, "loss": 0.1423, "lr": 4.3946644664466445e-05, "epoch": 1.7579757975797579, "percentage": 8.79, "elapsed_time": "0:37:13", "remaining_time": "6:26:13", "throughput": 1509.59, "total_tokens": 3371200} {"current_steps": 15985, "total_steps": 181800, "loss": 0.1139, "lr": 4.396039603960396e-05, "epoch": 1.7585258525852585, "percentage": 8.79, "elapsed_time": "0:37:13", "remaining_time": "6:26:12", "throughput": 1509.6, "total_tokens": 3372256} {"current_steps": 15990, "total_steps": 181800, "loss": 0.125, "lr": 4.397414741474148e-05, "epoch": 1.7590759075907592, "percentage": 8.8, "elapsed_time": "0:37:14", "remaining_time": "6:26:11", "throughput": 1509.59, "total_tokens": 3373280} {"current_steps": 15995, "total_steps": 181800, "loss": 0.0931, "lr": 4.3987898789878986e-05, "epoch": 1.7596259625962596, "percentage": 8.8, "elapsed_time": "0:37:15", "remaining_time": "6:26:10", "throughput": 1509.59, "total_tokens": 3374336} {"current_steps": 16000, "total_steps": 181800, "loss": 0.188, "lr": 4.4001650165016505e-05, "epoch": 1.76017601760176, "percentage": 8.8, "elapsed_time": "0:37:15", "remaining_time": "6:26:10", "throughput": 1509.59, "total_tokens": 3375360} {"current_steps": 16005, "total_steps": 181800, "loss": 0.0691, "lr": 4.4015401540154017e-05, "epoch": 1.7607260726072607, "percentage": 8.8, "elapsed_time": "0:37:16", "remaining_time": "6:26:09", "throughput": 1509.59, "total_tokens": 3376416} {"current_steps": 16010, "total_steps": 181800, "loss": 0.0674, "lr": 4.4029152915291535e-05, "epoch": 1.7612761276127613, "percentage": 8.81, "elapsed_time": "0:37:17", "remaining_time": "6:26:08", "throughput": 1509.6, "total_tokens": 3377472} {"current_steps": 16015, "total_steps": 181800, "loss": 0.1047, "lr": 4.4042904290429047e-05, "epoch": 1.761826182618262, "percentage": 8.81, "elapsed_time": "0:37:18", "remaining_time": "6:26:07", "throughput": 1509.61, "total_tokens": 3378528} {"current_steps": 16020, "total_steps": 181800, "loss": 0.0659, "lr": 4.405665566556656e-05, "epoch": 1.7623762376237624, "percentage": 8.81, "elapsed_time": "0:37:18", "remaining_time": "6:26:06", "throughput": 1509.65, "total_tokens": 3379648} {"current_steps": 16025, "total_steps": 181800, "loss": 0.0176, "lr": 4.407040704070407e-05, "epoch": 1.7629262926292628, "percentage": 8.81, "elapsed_time": "0:37:19", "remaining_time": "6:26:05", "throughput": 1509.68, "total_tokens": 3380768} {"current_steps": 16030, "total_steps": 181800, "loss": 0.1086, "lr": 4.408415841584159e-05, "epoch": 1.7634763476347635, "percentage": 8.82, "elapsed_time": "0:37:20", "remaining_time": "6:26:05", "throughput": 1509.74, "total_tokens": 3381920} {"current_steps": 16035, "total_steps": 181800, "loss": 0.2656, "lr": 4.40979097909791e-05, "epoch": 1.7640264026402641, "percentage": 8.82, "elapsed_time": "0:37:20", "remaining_time": "6:26:04", "throughput": 1509.75, "total_tokens": 3382976} {"current_steps": 16040, "total_steps": 181800, "loss": 0.0538, "lr": 4.411166116611661e-05, "epoch": 1.7645764576457645, "percentage": 8.82, "elapsed_time": "0:37:21", "remaining_time": "6:26:03", "throughput": 1509.78, "total_tokens": 3384096} {"current_steps": 16045, "total_steps": 181800, "loss": 0.0868, "lr": 4.412541254125413e-05, "epoch": 1.765126512651265, "percentage": 8.83, "elapsed_time": "0:37:22", "remaining_time": "6:26:02", "throughput": 1509.78, "total_tokens": 3385120} {"current_steps": 16050, "total_steps": 181800, "loss": 0.0888, "lr": 4.413916391639164e-05, "epoch": 1.7656765676567656, "percentage": 8.83, "elapsed_time": "0:37:22", "remaining_time": "6:26:01", "throughput": 1509.8, "total_tokens": 3386208} {"current_steps": 16055, "total_steps": 181800, "loss": 0.0617, "lr": 4.4152915291529153e-05, "epoch": 1.7662266226622663, "percentage": 8.83, "elapsed_time": "0:37:23", "remaining_time": "6:26:01", "throughput": 1509.79, "total_tokens": 3387232} {"current_steps": 16060, "total_steps": 181800, "loss": 0.044, "lr": 4.4166666666666665e-05, "epoch": 1.766776677667767, "percentage": 8.83, "elapsed_time": "0:37:24", "remaining_time": "6:26:00", "throughput": 1509.78, "total_tokens": 3388256} {"current_steps": 16065, "total_steps": 181800, "loss": 0.091, "lr": 4.4180418041804183e-05, "epoch": 1.7673267326732673, "percentage": 8.84, "elapsed_time": "0:37:24", "remaining_time": "6:25:59", "throughput": 1509.81, "total_tokens": 3389344} {"current_steps": 16070, "total_steps": 181800, "loss": 0.1157, "lr": 4.4194169416941695e-05, "epoch": 1.7678767876787678, "percentage": 8.84, "elapsed_time": "0:37:25", "remaining_time": "6:25:58", "throughput": 1509.81, "total_tokens": 3390400} {"current_steps": 16075, "total_steps": 181800, "loss": 0.0993, "lr": 4.4207920792079214e-05, "epoch": 1.7684268426842684, "percentage": 8.84, "elapsed_time": "0:37:26", "remaining_time": "6:25:57", "throughput": 1509.82, "total_tokens": 3391456} {"current_steps": 16080, "total_steps": 181800, "loss": 0.0653, "lr": 4.422167216721672e-05, "epoch": 1.768976897689769, "percentage": 8.84, "elapsed_time": "0:37:26", "remaining_time": "6:25:57", "throughput": 1509.86, "total_tokens": 3392576} {"current_steps": 16085, "total_steps": 181800, "loss": 0.0404, "lr": 4.423542354235424e-05, "epoch": 1.7695269526952695, "percentage": 8.85, "elapsed_time": "0:37:27", "remaining_time": "6:25:56", "throughput": 1509.89, "total_tokens": 3393696} {"current_steps": 16090, "total_steps": 181800, "loss": 0.149, "lr": 4.4249174917491755e-05, "epoch": 1.77007700770077, "percentage": 8.85, "elapsed_time": "0:37:28", "remaining_time": "6:25:55", "throughput": 1509.87, "total_tokens": 3394688} {"current_steps": 16095, "total_steps": 181800, "loss": 0.0969, "lr": 4.426292629262927e-05, "epoch": 1.7706270627062706, "percentage": 8.85, "elapsed_time": "0:37:29", "remaining_time": "6:25:54", "throughput": 1509.87, "total_tokens": 3395712} {"current_steps": 16100, "total_steps": 181800, "loss": 0.3359, "lr": 4.427667766776678e-05, "epoch": 1.7711771177117712, "percentage": 8.86, "elapsed_time": "0:37:29", "remaining_time": "6:25:53", "throughput": 1509.87, "total_tokens": 3396768} {"current_steps": 16105, "total_steps": 181800, "loss": 0.1173, "lr": 4.429042904290429e-05, "epoch": 1.7717271727172719, "percentage": 8.86, "elapsed_time": "0:37:30", "remaining_time": "6:25:53", "throughput": 1509.86, "total_tokens": 3397792} {"current_steps": 16110, "total_steps": 181800, "loss": 0.0602, "lr": 4.430418041804181e-05, "epoch": 1.7722772277227723, "percentage": 8.86, "elapsed_time": "0:37:31", "remaining_time": "6:25:52", "throughput": 1509.87, "total_tokens": 3398848} {"current_steps": 16115, "total_steps": 181800, "loss": 0.096, "lr": 4.431793179317932e-05, "epoch": 1.7728272827282727, "percentage": 8.86, "elapsed_time": "0:37:31", "remaining_time": "6:25:51", "throughput": 1509.91, "total_tokens": 3399968} {"current_steps": 16120, "total_steps": 181800, "loss": 0.0383, "lr": 4.433168316831683e-05, "epoch": 1.7733773377337734, "percentage": 8.87, "elapsed_time": "0:37:32", "remaining_time": "6:25:50", "throughput": 1509.91, "total_tokens": 3401024} {"current_steps": 16125, "total_steps": 181800, "loss": 0.1227, "lr": 4.4345434543454344e-05, "epoch": 1.773927392739274, "percentage": 8.87, "elapsed_time": "0:37:33", "remaining_time": "6:25:49", "throughput": 1509.91, "total_tokens": 3402048} {"current_steps": 16130, "total_steps": 181800, "loss": 0.1327, "lr": 4.435918591859186e-05, "epoch": 1.7744774477447744, "percentage": 8.87, "elapsed_time": "0:37:33", "remaining_time": "6:25:48", "throughput": 1509.93, "total_tokens": 3403136} {"current_steps": 16135, "total_steps": 181800, "loss": 0.0713, "lr": 4.437293729372938e-05, "epoch": 1.7750275027502749, "percentage": 8.88, "elapsed_time": "0:37:34", "remaining_time": "6:25:48", "throughput": 1509.94, "total_tokens": 3404192} {"current_steps": 16140, "total_steps": 181800, "loss": 0.1193, "lr": 4.4386688668866885e-05, "epoch": 1.7755775577557755, "percentage": 8.88, "elapsed_time": "0:37:35", "remaining_time": "6:25:47", "throughput": 1509.95, "total_tokens": 3405248} {"current_steps": 16145, "total_steps": 181800, "loss": 0.1009, "lr": 4.4400440044004404e-05, "epoch": 1.7761276127612762, "percentage": 8.88, "elapsed_time": "0:37:35", "remaining_time": "6:25:46", "throughput": 1509.96, "total_tokens": 3406304} {"current_steps": 16150, "total_steps": 181800, "loss": 0.1137, "lr": 4.4414191419141916e-05, "epoch": 1.7766776677667768, "percentage": 8.88, "elapsed_time": "0:37:36", "remaining_time": "6:25:45", "throughput": 1509.96, "total_tokens": 3407360} {"current_steps": 16155, "total_steps": 181800, "loss": 0.0789, "lr": 4.4427942794279434e-05, "epoch": 1.7772277227722773, "percentage": 8.89, "elapsed_time": "0:37:37", "remaining_time": "6:25:44", "throughput": 1510.0, "total_tokens": 3408480} {"current_steps": 16160, "total_steps": 181800, "loss": 0.1304, "lr": 4.444169416941694e-05, "epoch": 1.7777777777777777, "percentage": 8.89, "elapsed_time": "0:37:37", "remaining_time": "6:25:44", "throughput": 1510.0, "total_tokens": 3409504} {"current_steps": 16165, "total_steps": 181800, "loss": 0.1279, "lr": 4.445544554455446e-05, "epoch": 1.7783278327832783, "percentage": 8.89, "elapsed_time": "0:37:38", "remaining_time": "6:25:43", "throughput": 1510.0, "total_tokens": 3410560} {"current_steps": 16170, "total_steps": 181800, "loss": 0.1667, "lr": 4.446919691969197e-05, "epoch": 1.778877887788779, "percentage": 8.89, "elapsed_time": "0:37:39", "remaining_time": "6:25:42", "throughput": 1510.01, "total_tokens": 3411616} {"current_steps": 16175, "total_steps": 181800, "loss": 0.0736, "lr": 4.448294829482949e-05, "epoch": 1.7794279427942794, "percentage": 8.9, "elapsed_time": "0:37:40", "remaining_time": "6:25:41", "throughput": 1509.99, "total_tokens": 3412608} {"current_steps": 16180, "total_steps": 181800, "loss": 0.1259, "lr": 4.4496699669967e-05, "epoch": 1.7799779977997798, "percentage": 8.9, "elapsed_time": "0:37:40", "remaining_time": "6:25:40", "throughput": 1510.0, "total_tokens": 3413664} {"current_steps": 16185, "total_steps": 181800, "loss": 0.0759, "lr": 4.451045104510451e-05, "epoch": 1.7805280528052805, "percentage": 8.9, "elapsed_time": "0:37:41", "remaining_time": "6:25:39", "throughput": 1509.99, "total_tokens": 3414688} {"current_steps": 16190, "total_steps": 181800, "loss": 0.0448, "lr": 4.452420242024203e-05, "epoch": 1.7810781078107811, "percentage": 8.91, "elapsed_time": "0:37:42", "remaining_time": "6:25:39", "throughput": 1510.0, "total_tokens": 3415744} {"current_steps": 16195, "total_steps": 181800, "loss": 0.0294, "lr": 4.453795379537954e-05, "epoch": 1.7816281628162818, "percentage": 8.91, "elapsed_time": "0:37:42", "remaining_time": "6:25:38", "throughput": 1510.01, "total_tokens": 3416800} {"current_steps": 16200, "total_steps": 181800, "loss": 0.0495, "lr": 4.455170517051705e-05, "epoch": 1.7821782178217822, "percentage": 8.91, "elapsed_time": "0:37:43", "remaining_time": "6:25:37", "throughput": 1510.05, "total_tokens": 3417920} {"current_steps": 16205, "total_steps": 181800, "loss": 0.162, "lr": 4.4565456545654564e-05, "epoch": 1.7827282728272826, "percentage": 8.91, "elapsed_time": "0:37:44", "remaining_time": "6:25:36", "throughput": 1510.07, "total_tokens": 3419008} {"current_steps": 16210, "total_steps": 181800, "loss": 0.0847, "lr": 4.457920792079208e-05, "epoch": 1.7832783278327833, "percentage": 8.92, "elapsed_time": "0:37:44", "remaining_time": "6:25:35", "throughput": 1510.08, "total_tokens": 3420064} {"current_steps": 16215, "total_steps": 181800, "loss": 0.0916, "lr": 4.4592959295929594e-05, "epoch": 1.783828382838284, "percentage": 8.92, "elapsed_time": "0:37:45", "remaining_time": "6:25:35", "throughput": 1510.06, "total_tokens": 3421056} {"current_steps": 16220, "total_steps": 181800, "loss": 0.173, "lr": 4.4606710671067106e-05, "epoch": 1.7843784378437844, "percentage": 8.92, "elapsed_time": "0:37:46", "remaining_time": "6:25:34", "throughput": 1510.05, "total_tokens": 3422080} {"current_steps": 16225, "total_steps": 181800, "loss": 0.2266, "lr": 4.4620462046204624e-05, "epoch": 1.7849284928492848, "percentage": 8.92, "elapsed_time": "0:37:46", "remaining_time": "6:25:33", "throughput": 1510.1, "total_tokens": 3423232} {"current_steps": 16230, "total_steps": 181800, "loss": 0.0771, "lr": 4.4634213421342136e-05, "epoch": 1.7854785478547854, "percentage": 8.93, "elapsed_time": "0:37:47", "remaining_time": "6:25:32", "throughput": 1510.12, "total_tokens": 3424320} {"current_steps": 16235, "total_steps": 181800, "loss": 0.1442, "lr": 4.4647964796479654e-05, "epoch": 1.786028602860286, "percentage": 8.93, "elapsed_time": "0:37:48", "remaining_time": "6:25:31", "throughput": 1510.11, "total_tokens": 3425344} {"current_steps": 16240, "total_steps": 181800, "loss": 0.1999, "lr": 4.4661716171617166e-05, "epoch": 1.7865786578657867, "percentage": 8.93, "elapsed_time": "0:37:48", "remaining_time": "6:25:31", "throughput": 1510.12, "total_tokens": 3426400} {"current_steps": 16245, "total_steps": 181800, "loss": 0.0966, "lr": 4.467546754675468e-05, "epoch": 1.7871287128712872, "percentage": 8.94, "elapsed_time": "0:37:49", "remaining_time": "6:25:30", "throughput": 1510.14, "total_tokens": 3427488} {"current_steps": 16250, "total_steps": 181800, "loss": 0.1639, "lr": 4.468921892189219e-05, "epoch": 1.7876787678767876, "percentage": 8.94, "elapsed_time": "0:37:50", "remaining_time": "6:25:29", "throughput": 1510.15, "total_tokens": 3428544} {"current_steps": 16255, "total_steps": 181800, "loss": 0.1261, "lr": 4.470297029702971e-05, "epoch": 1.7882288228822882, "percentage": 8.94, "elapsed_time": "0:37:51", "remaining_time": "6:25:28", "throughput": 1510.16, "total_tokens": 3429600} {"current_steps": 16260, "total_steps": 181800, "loss": 0.039, "lr": 4.471672167216722e-05, "epoch": 1.7887788778877889, "percentage": 8.94, "elapsed_time": "0:37:51", "remaining_time": "6:25:27", "throughput": 1510.17, "total_tokens": 3430656} {"current_steps": 16265, "total_steps": 181800, "loss": 0.1622, "lr": 4.473047304730473e-05, "epoch": 1.7893289328932893, "percentage": 8.95, "elapsed_time": "0:37:52", "remaining_time": "6:25:27", "throughput": 1510.16, "total_tokens": 3431680} {"current_steps": 16270, "total_steps": 181800, "loss": 0.076, "lr": 4.474422442244225e-05, "epoch": 1.7898789878987897, "percentage": 8.95, "elapsed_time": "0:37:53", "remaining_time": "6:25:26", "throughput": 1510.17, "total_tokens": 3432736} {"current_steps": 16275, "total_steps": 181800, "loss": 0.0787, "lr": 4.475797579757976e-05, "epoch": 1.7904290429042904, "percentage": 8.95, "elapsed_time": "0:37:53", "remaining_time": "6:25:25", "throughput": 1510.19, "total_tokens": 3433824} {"current_steps": 16280, "total_steps": 181800, "loss": 0.0468, "lr": 4.477172717271727e-05, "epoch": 1.790979097909791, "percentage": 8.95, "elapsed_time": "0:37:54", "remaining_time": "6:25:24", "throughput": 1510.19, "total_tokens": 3434848} {"current_steps": 16285, "total_steps": 181800, "loss": 0.077, "lr": 4.4785478547854784e-05, "epoch": 1.7915291529152917, "percentage": 8.96, "elapsed_time": "0:37:55", "remaining_time": "6:25:23", "throughput": 1510.2, "total_tokens": 3435904} {"current_steps": 16290, "total_steps": 181800, "loss": 0.1279, "lr": 4.47992299229923e-05, "epoch": 1.7920792079207921, "percentage": 8.96, "elapsed_time": "0:37:55", "remaining_time": "6:25:22", "throughput": 1510.25, "total_tokens": 3437056} {"current_steps": 16295, "total_steps": 181800, "loss": 0.0537, "lr": 4.4812981298129815e-05, "epoch": 1.7926292629262925, "percentage": 8.96, "elapsed_time": "0:37:56", "remaining_time": "6:25:22", "throughput": 1510.27, "total_tokens": 3438144} {"current_steps": 16300, "total_steps": 181800, "loss": 0.0193, "lr": 4.482673267326733e-05, "epoch": 1.7931793179317932, "percentage": 8.97, "elapsed_time": "0:37:57", "remaining_time": "6:25:21", "throughput": 1510.26, "total_tokens": 3439168} {"current_steps": 16305, "total_steps": 181800, "loss": 0.042, "lr": 4.484048404840484e-05, "epoch": 1.7937293729372938, "percentage": 8.97, "elapsed_time": "0:37:57", "remaining_time": "6:25:20", "throughput": 1510.27, "total_tokens": 3440224} {"current_steps": 16310, "total_steps": 181800, "loss": 0.1724, "lr": 4.4854235423542356e-05, "epoch": 1.7942794279427943, "percentage": 8.97, "elapsed_time": "0:37:58", "remaining_time": "6:25:19", "throughput": 1510.28, "total_tokens": 3441312} {"current_steps": 16315, "total_steps": 181800, "loss": 0.0721, "lr": 4.486798679867987e-05, "epoch": 1.7948294829482947, "percentage": 8.97, "elapsed_time": "0:37:59", "remaining_time": "6:25:18", "throughput": 1510.29, "total_tokens": 3442368} {"current_steps": 16320, "total_steps": 181800, "loss": 0.0489, "lr": 4.4881738173817386e-05, "epoch": 1.7953795379537953, "percentage": 8.98, "elapsed_time": "0:37:59", "remaining_time": "6:25:18", "throughput": 1510.31, "total_tokens": 3443456} {"current_steps": 16325, "total_steps": 181800, "loss": 0.1056, "lr": 4.48954895489549e-05, "epoch": 1.795929592959296, "percentage": 8.98, "elapsed_time": "0:38:00", "remaining_time": "6:25:17", "throughput": 1510.3, "total_tokens": 3444480} {"current_steps": 16330, "total_steps": 181800, "loss": 0.0657, "lr": 4.490924092409241e-05, "epoch": 1.7964796479647966, "percentage": 8.98, "elapsed_time": "0:38:01", "remaining_time": "6:25:16", "throughput": 1510.31, "total_tokens": 3445536} {"current_steps": 16335, "total_steps": 181800, "loss": 0.0574, "lr": 4.492299229922993e-05, "epoch": 1.797029702970297, "percentage": 8.99, "elapsed_time": "0:38:02", "remaining_time": "6:25:15", "throughput": 1510.31, "total_tokens": 3446592} {"current_steps": 16340, "total_steps": 181800, "loss": 0.1406, "lr": 4.493674367436744e-05, "epoch": 1.7975797579757975, "percentage": 8.99, "elapsed_time": "0:38:02", "remaining_time": "6:25:15", "throughput": 1510.33, "total_tokens": 3447680} {"current_steps": 16345, "total_steps": 181800, "loss": 0.1042, "lr": 4.495049504950495e-05, "epoch": 1.7981298129812981, "percentage": 8.99, "elapsed_time": "0:38:03", "remaining_time": "6:25:14", "throughput": 1510.33, "total_tokens": 3448704} {"current_steps": 16350, "total_steps": 181800, "loss": 0.1885, "lr": 4.496424642464246e-05, "epoch": 1.7986798679867988, "percentage": 8.99, "elapsed_time": "0:38:04", "remaining_time": "6:25:13", "throughput": 1510.34, "total_tokens": 3449760} {"current_steps": 16355, "total_steps": 181800, "loss": 0.1382, "lr": 4.497799779977998e-05, "epoch": 1.7992299229922992, "percentage": 9.0, "elapsed_time": "0:38:04", "remaining_time": "6:25:12", "throughput": 1510.34, "total_tokens": 3450816} {"current_steps": 16360, "total_steps": 181800, "loss": 0.059, "lr": 4.499174917491749e-05, "epoch": 1.7997799779977997, "percentage": 9.0, "elapsed_time": "0:38:05", "remaining_time": "6:25:11", "throughput": 1510.38, "total_tokens": 3451936} {"current_steps": 16365, "total_steps": 181800, "loss": 0.0508, "lr": 4.5005500550055005e-05, "epoch": 1.8003300330033003, "percentage": 9.0, "elapsed_time": "0:38:06", "remaining_time": "6:25:10", "throughput": 1510.37, "total_tokens": 3452960} {"current_steps": 16370, "total_steps": 181800, "loss": 0.1061, "lr": 4.501925192519252e-05, "epoch": 1.800880088008801, "percentage": 9.0, "elapsed_time": "0:38:06", "remaining_time": "6:25:10", "throughput": 1510.35, "total_tokens": 3453952} {"current_steps": 16375, "total_steps": 181800, "loss": 0.0514, "lr": 4.5033003300330035e-05, "epoch": 1.8014301430143014, "percentage": 9.01, "elapsed_time": "0:38:07", "remaining_time": "6:25:09", "throughput": 1510.36, "total_tokens": 3455008} {"current_steps": 16380, "total_steps": 181800, "loss": 0.1028, "lr": 4.504675467546755e-05, "epoch": 1.801980198019802, "percentage": 9.01, "elapsed_time": "0:38:08", "remaining_time": "6:25:08", "throughput": 1510.37, "total_tokens": 3456064} {"current_steps": 16385, "total_steps": 181800, "loss": 0.07, "lr": 4.506050605060506e-05, "epoch": 1.8025302530253025, "percentage": 9.01, "elapsed_time": "0:38:08", "remaining_time": "6:25:07", "throughput": 1510.37, "total_tokens": 3457120} {"current_steps": 16390, "total_steps": 181800, "loss": 0.1525, "lr": 4.507425742574258e-05, "epoch": 1.803080308030803, "percentage": 9.02, "elapsed_time": "0:38:09", "remaining_time": "6:25:07", "throughput": 1510.37, "total_tokens": 3458176} {"current_steps": 16395, "total_steps": 181800, "loss": 0.0422, "lr": 4.508800880088009e-05, "epoch": 1.8036303630363038, "percentage": 9.02, "elapsed_time": "0:38:10", "remaining_time": "6:25:06", "throughput": 1510.38, "total_tokens": 3459232} {"current_steps": 16400, "total_steps": 181800, "loss": 0.0798, "lr": 4.510176017601761e-05, "epoch": 1.8041804180418042, "percentage": 9.02, "elapsed_time": "0:38:10", "remaining_time": "6:25:05", "throughput": 1510.37, "total_tokens": 3460256} {"current_steps": 16405, "total_steps": 181800, "loss": 0.0819, "lr": 4.511551155115512e-05, "epoch": 1.8047304730473046, "percentage": 9.02, "elapsed_time": "0:38:11", "remaining_time": "6:25:04", "throughput": 1510.37, "total_tokens": 3461280} {"current_steps": 16410, "total_steps": 181800, "loss": 0.0803, "lr": 4.512926292629263e-05, "epoch": 1.8052805280528053, "percentage": 9.03, "elapsed_time": "0:38:12", "remaining_time": "6:25:03", "throughput": 1510.39, "total_tokens": 3462368} {"current_steps": 16415, "total_steps": 181800, "loss": 0.152, "lr": 4.514301430143015e-05, "epoch": 1.805830583058306, "percentage": 9.03, "elapsed_time": "0:38:13", "remaining_time": "6:25:03", "throughput": 1510.39, "total_tokens": 3463392} {"current_steps": 16420, "total_steps": 181800, "loss": 0.1999, "lr": 4.515676567656766e-05, "epoch": 1.8063806380638063, "percentage": 9.03, "elapsed_time": "0:38:13", "remaining_time": "6:25:02", "throughput": 1510.4, "total_tokens": 3464448} {"current_steps": 16425, "total_steps": 181800, "loss": 0.1557, "lr": 4.517051705170517e-05, "epoch": 1.806930693069307, "percentage": 9.03, "elapsed_time": "0:38:14", "remaining_time": "6:25:01", "throughput": 1510.42, "total_tokens": 3465536} {"current_steps": 16430, "total_steps": 181800, "loss": 0.091, "lr": 4.5184268426842683e-05, "epoch": 1.8074807480748074, "percentage": 9.04, "elapsed_time": "0:38:15", "remaining_time": "6:25:00", "throughput": 1510.41, "total_tokens": 3466560} {"current_steps": 16435, "total_steps": 181800, "loss": 0.1766, "lr": 4.51980198019802e-05, "epoch": 1.808030803080308, "percentage": 9.04, "elapsed_time": "0:38:15", "remaining_time": "6:24:59", "throughput": 1510.41, "total_tokens": 3467584} {"current_steps": 16440, "total_steps": 181800, "loss": 0.098, "lr": 4.5211771177117713e-05, "epoch": 1.8085808580858087, "percentage": 9.04, "elapsed_time": "0:38:16", "remaining_time": "6:24:58", "throughput": 1510.41, "total_tokens": 3468640} {"current_steps": 16445, "total_steps": 181800, "loss": 0.0567, "lr": 4.5225522552255225e-05, "epoch": 1.8091309130913091, "percentage": 9.05, "elapsed_time": "0:38:17", "remaining_time": "6:24:58", "throughput": 1510.43, "total_tokens": 3469728} {"current_steps": 16450, "total_steps": 181800, "loss": 0.0286, "lr": 4.523927392739274e-05, "epoch": 1.8096809680968096, "percentage": 9.05, "elapsed_time": "0:38:17", "remaining_time": "6:24:57", "throughput": 1510.44, "total_tokens": 3470784} {"current_steps": 16455, "total_steps": 181800, "loss": 0.1027, "lr": 4.5253025302530255e-05, "epoch": 1.8102310231023102, "percentage": 9.05, "elapsed_time": "0:38:18", "remaining_time": "6:24:56", "throughput": 1510.41, "total_tokens": 3471744} {"current_steps": 16460, "total_steps": 181800, "loss": 0.0449, "lr": 4.5266776677667774e-05, "epoch": 1.8107810781078109, "percentage": 9.05, "elapsed_time": "0:38:19", "remaining_time": "6:24:55", "throughput": 1510.41, "total_tokens": 3472800} {"current_steps": 16465, "total_steps": 181800, "loss": 0.1005, "lr": 4.5280528052805285e-05, "epoch": 1.8113311331133113, "percentage": 9.06, "elapsed_time": "0:38:19", "remaining_time": "6:24:54", "throughput": 1510.41, "total_tokens": 3473824} {"current_steps": 16470, "total_steps": 181800, "loss": 0.0688, "lr": 4.52942794279428e-05, "epoch": 1.811881188118812, "percentage": 9.06, "elapsed_time": "0:38:20", "remaining_time": "6:24:54", "throughput": 1510.45, "total_tokens": 3474944} {"current_steps": 16475, "total_steps": 181800, "loss": 0.1261, "lr": 4.530803080308031e-05, "epoch": 1.8124312431243124, "percentage": 9.06, "elapsed_time": "0:38:21", "remaining_time": "6:24:56", "throughput": 1510.26, "total_tokens": 3476000} {"current_steps": 16480, "total_steps": 181800, "loss": 0.0425, "lr": 4.532178217821783e-05, "epoch": 1.812981298129813, "percentage": 9.06, "elapsed_time": "0:38:22", "remaining_time": "6:24:55", "throughput": 1510.28, "total_tokens": 3477088} {"current_steps": 16485, "total_steps": 181800, "loss": 0.1014, "lr": 4.533553355335534e-05, "epoch": 1.8135313531353137, "percentage": 9.07, "elapsed_time": "0:38:22", "remaining_time": "6:24:54", "throughput": 1510.29, "total_tokens": 3478144} {"current_steps": 16490, "total_steps": 181800, "loss": 0.0365, "lr": 4.534928492849285e-05, "epoch": 1.814081408140814, "percentage": 9.07, "elapsed_time": "0:38:23", "remaining_time": "6:24:53", "throughput": 1510.29, "total_tokens": 3479200} {"current_steps": 16495, "total_steps": 181800, "loss": 0.1021, "lr": 4.536303630363036e-05, "epoch": 1.8146314631463145, "percentage": 9.07, "elapsed_time": "0:38:24", "remaining_time": "6:24:53", "throughput": 1510.29, "total_tokens": 3480224} {"current_steps": 16500, "total_steps": 181800, "loss": 0.0775, "lr": 4.537678767876788e-05, "epoch": 1.8151815181518152, "percentage": 9.08, "elapsed_time": "0:38:25", "remaining_time": "6:24:52", "throughput": 1510.27, "total_tokens": 3481216} {"current_steps": 16505, "total_steps": 181800, "loss": 0.0578, "lr": 4.539053905390539e-05, "epoch": 1.8157315731573158, "percentage": 9.08, "elapsed_time": "0:38:25", "remaining_time": "6:24:51", "throughput": 1510.29, "total_tokens": 3482304} {"current_steps": 16510, "total_steps": 181800, "loss": 0.1302, "lr": 4.5404290429042904e-05, "epoch": 1.8162816281628162, "percentage": 9.08, "elapsed_time": "0:38:26", "remaining_time": "6:24:50", "throughput": 1510.28, "total_tokens": 3483328} {"current_steps": 16515, "total_steps": 181800, "loss": 0.0254, "lr": 4.541804180418042e-05, "epoch": 1.8168316831683167, "percentage": 9.08, "elapsed_time": "0:38:27", "remaining_time": "6:24:49", "throughput": 1510.27, "total_tokens": 3484352} {"current_steps": 16520, "total_steps": 181800, "loss": 0.0348, "lr": 4.5431793179317934e-05, "epoch": 1.8173817381738173, "percentage": 9.09, "elapsed_time": "0:38:27", "remaining_time": "6:24:49", "throughput": 1510.32, "total_tokens": 3485504} {"current_steps": 16525, "total_steps": 181800, "loss": 0.0792, "lr": 4.544554455445545e-05, "epoch": 1.817931793179318, "percentage": 9.09, "elapsed_time": "0:38:28", "remaining_time": "6:24:48", "throughput": 1510.31, "total_tokens": 3486528} {"current_steps": 16530, "total_steps": 181800, "loss": 0.0669, "lr": 4.545929592959296e-05, "epoch": 1.8184818481848186, "percentage": 9.09, "elapsed_time": "0:38:29", "remaining_time": "6:24:47", "throughput": 1510.31, "total_tokens": 3487552} {"current_steps": 16535, "total_steps": 181800, "loss": 0.1934, "lr": 4.5473047304730476e-05, "epoch": 1.819031903190319, "percentage": 9.1, "elapsed_time": "0:38:29", "remaining_time": "6:24:46", "throughput": 1510.34, "total_tokens": 3488672} {"current_steps": 16540, "total_steps": 181800, "loss": 0.0937, "lr": 4.548679867986799e-05, "epoch": 1.8195819581958195, "percentage": 9.1, "elapsed_time": "0:38:30", "remaining_time": "6:24:45", "throughput": 1510.34, "total_tokens": 3489728} {"current_steps": 16545, "total_steps": 181800, "loss": 0.0448, "lr": 4.5500550055005506e-05, "epoch": 1.8201320132013201, "percentage": 9.1, "elapsed_time": "0:38:31", "remaining_time": "6:24:45", "throughput": 1510.32, "total_tokens": 3490720} {"current_steps": 16550, "total_steps": 181800, "loss": 0.0607, "lr": 4.551430143014301e-05, "epoch": 1.8206820682068208, "percentage": 9.1, "elapsed_time": "0:38:31", "remaining_time": "6:24:44", "throughput": 1510.31, "total_tokens": 3491744} {"current_steps": 16555, "total_steps": 181800, "loss": 0.0948, "lr": 4.552805280528053e-05, "epoch": 1.8212321232123212, "percentage": 9.11, "elapsed_time": "0:38:32", "remaining_time": "6:24:43", "throughput": 1510.33, "total_tokens": 3492832} {"current_steps": 16560, "total_steps": 181800, "loss": 0.138, "lr": 4.554180418041805e-05, "epoch": 1.8217821782178216, "percentage": 9.11, "elapsed_time": "0:38:33", "remaining_time": "6:24:42", "throughput": 1510.35, "total_tokens": 3493920} {"current_steps": 16565, "total_steps": 181800, "loss": 0.1292, "lr": 4.555555555555556e-05, "epoch": 1.8223322332233223, "percentage": 9.11, "elapsed_time": "0:38:33", "remaining_time": "6:24:42", "throughput": 1510.35, "total_tokens": 3494944} {"current_steps": 16570, "total_steps": 181800, "loss": 0.1289, "lr": 4.556930693069307e-05, "epoch": 1.822882288228823, "percentage": 9.11, "elapsed_time": "0:38:34", "remaining_time": "6:24:41", "throughput": 1510.34, "total_tokens": 3495968} {"current_steps": 16575, "total_steps": 181800, "loss": 0.14, "lr": 4.558305830583058e-05, "epoch": 1.8234323432343236, "percentage": 9.12, "elapsed_time": "0:38:35", "remaining_time": "6:24:40", "throughput": 1510.35, "total_tokens": 3497024} {"current_steps": 16580, "total_steps": 181800, "loss": 0.0555, "lr": 4.55968096809681e-05, "epoch": 1.823982398239824, "percentage": 9.12, "elapsed_time": "0:38:36", "remaining_time": "6:24:39", "throughput": 1510.35, "total_tokens": 3498048} {"current_steps": 16585, "total_steps": 181800, "loss": 0.1084, "lr": 4.561056105610561e-05, "epoch": 1.8245324532453244, "percentage": 9.12, "elapsed_time": "0:38:36", "remaining_time": "6:24:38", "throughput": 1510.33, "total_tokens": 3499040} {"current_steps": 16590, "total_steps": 181800, "loss": 0.0394, "lr": 4.5624312431243124e-05, "epoch": 1.825082508250825, "percentage": 9.13, "elapsed_time": "0:38:37", "remaining_time": "6:24:37", "throughput": 1510.35, "total_tokens": 3500128} {"current_steps": 16595, "total_steps": 181800, "loss": 0.1399, "lr": 4.5638063806380636e-05, "epoch": 1.8256325632563257, "percentage": 9.13, "elapsed_time": "0:38:38", "remaining_time": "6:24:37", "throughput": 1510.34, "total_tokens": 3501152} {"current_steps": 16600, "total_steps": 181800, "loss": 0.0786, "lr": 4.5651815181518154e-05, "epoch": 1.8261826182618262, "percentage": 9.13, "elapsed_time": "0:38:38", "remaining_time": "6:24:36", "throughput": 1510.33, "total_tokens": 3502176} {"current_steps": 16605, "total_steps": 181800, "loss": 0.1009, "lr": 4.566556655665567e-05, "epoch": 1.8267326732673266, "percentage": 9.13, "elapsed_time": "0:38:39", "remaining_time": "6:24:35", "throughput": 1510.34, "total_tokens": 3503232} {"current_steps": 16610, "total_steps": 181800, "loss": 0.0889, "lr": 4.567931793179318e-05, "epoch": 1.8272827282728272, "percentage": 9.14, "elapsed_time": "0:38:40", "remaining_time": "6:24:34", "throughput": 1510.36, "total_tokens": 3504320} {"current_steps": 16615, "total_steps": 181800, "loss": 0.0889, "lr": 4.5693069306930696e-05, "epoch": 1.8278327832783279, "percentage": 9.14, "elapsed_time": "0:38:40", "remaining_time": "6:24:33", "throughput": 1510.37, "total_tokens": 3505376} {"current_steps": 16620, "total_steps": 181800, "loss": 0.0564, "lr": 4.570682068206821e-05, "epoch": 1.8283828382838285, "percentage": 9.14, "elapsed_time": "0:38:41", "remaining_time": "6:24:33", "throughput": 1510.39, "total_tokens": 3506464} {"current_steps": 16625, "total_steps": 181800, "loss": 0.0478, "lr": 4.5720572057205726e-05, "epoch": 1.828932893289329, "percentage": 9.14, "elapsed_time": "0:38:42", "remaining_time": "6:24:32", "throughput": 1510.39, "total_tokens": 3507520} {"current_steps": 16630, "total_steps": 181800, "loss": 0.0997, "lr": 4.573432343234324e-05, "epoch": 1.8294829482948294, "percentage": 9.15, "elapsed_time": "0:38:42", "remaining_time": "6:24:31", "throughput": 1510.4, "total_tokens": 3508576} {"current_steps": 16635, "total_steps": 181800, "loss": 0.1426, "lr": 4.574807480748075e-05, "epoch": 1.83003300330033, "percentage": 9.15, "elapsed_time": "0:38:43", "remaining_time": "6:24:30", "throughput": 1510.39, "total_tokens": 3509600} {"current_steps": 16640, "total_steps": 181800, "loss": 0.0775, "lr": 4.576182618261826e-05, "epoch": 1.8305830583058307, "percentage": 9.15, "elapsed_time": "0:38:44", "remaining_time": "6:24:29", "throughput": 1510.37, "total_tokens": 3510592} {"current_steps": 16645, "total_steps": 181800, "loss": 0.1279, "lr": 4.577557755775578e-05, "epoch": 1.831133113311331, "percentage": 9.16, "elapsed_time": "0:38:45", "remaining_time": "6:24:29", "throughput": 1510.38, "total_tokens": 3511648} {"current_steps": 16650, "total_steps": 181800, "loss": 0.0788, "lr": 4.578932893289329e-05, "epoch": 1.8316831683168315, "percentage": 9.16, "elapsed_time": "0:38:45", "remaining_time": "6:24:28", "throughput": 1510.38, "total_tokens": 3512704} {"current_steps": 16655, "total_steps": 181800, "loss": 0.0585, "lr": 4.58030803080308e-05, "epoch": 1.8322332233223322, "percentage": 9.16, "elapsed_time": "0:38:46", "remaining_time": "6:24:27", "throughput": 1510.4, "total_tokens": 3513792} {"current_steps": 16660, "total_steps": 181800, "loss": 0.1416, "lr": 4.581683168316832e-05, "epoch": 1.8327832783278328, "percentage": 9.16, "elapsed_time": "0:38:47", "remaining_time": "6:24:26", "throughput": 1510.39, "total_tokens": 3514816} {"current_steps": 16665, "total_steps": 181800, "loss": 0.0531, "lr": 4.583058305830583e-05, "epoch": 1.8333333333333335, "percentage": 9.17, "elapsed_time": "0:38:47", "remaining_time": "6:24:26", "throughput": 1510.39, "total_tokens": 3515840} {"current_steps": 16670, "total_steps": 181800, "loss": 0.2752, "lr": 4.5844334433443345e-05, "epoch": 1.833883388338834, "percentage": 9.17, "elapsed_time": "0:38:48", "remaining_time": "6:24:25", "throughput": 1510.37, "total_tokens": 3516832} {"current_steps": 16675, "total_steps": 181800, "loss": 0.1556, "lr": 4.5858085808580856e-05, "epoch": 1.8344334433443343, "percentage": 9.17, "elapsed_time": "0:38:49", "remaining_time": "6:24:24", "throughput": 1510.36, "total_tokens": 3517856} {"current_steps": 16680, "total_steps": 181800, "loss": 0.168, "lr": 4.5871837183718375e-05, "epoch": 1.834983498349835, "percentage": 9.17, "elapsed_time": "0:38:49", "remaining_time": "6:24:23", "throughput": 1510.38, "total_tokens": 3518944} {"current_steps": 16685, "total_steps": 181800, "loss": 0.1359, "lr": 4.5885588558855886e-05, "epoch": 1.8355335533553356, "percentage": 9.18, "elapsed_time": "0:38:50", "remaining_time": "6:24:23", "throughput": 1510.41, "total_tokens": 3520064} {"current_steps": 16690, "total_steps": 181800, "loss": 0.0646, "lr": 4.5899339933993405e-05, "epoch": 1.836083608360836, "percentage": 9.18, "elapsed_time": "0:38:51", "remaining_time": "6:24:22", "throughput": 1510.45, "total_tokens": 3521184} {"current_steps": 16695, "total_steps": 181800, "loss": 0.0473, "lr": 4.5913091309130916e-05, "epoch": 1.8366336633663365, "percentage": 9.18, "elapsed_time": "0:38:51", "remaining_time": "6:24:21", "throughput": 1510.48, "total_tokens": 3522304} {"current_steps": 16700, "total_steps": 181800, "loss": 0.0616, "lr": 4.592684268426843e-05, "epoch": 1.8371837183718371, "percentage": 9.19, "elapsed_time": "0:38:52", "remaining_time": "6:24:20", "throughput": 1510.49, "total_tokens": 3523360} {"current_steps": 16705, "total_steps": 181800, "loss": 0.0585, "lr": 4.5940594059405946e-05, "epoch": 1.8377337733773378, "percentage": 9.19, "elapsed_time": "0:38:53", "remaining_time": "6:24:19", "throughput": 1510.5, "total_tokens": 3524416} {"current_steps": 16710, "total_steps": 181800, "loss": 0.0293, "lr": 4.595434543454346e-05, "epoch": 1.8382838283828384, "percentage": 9.19, "elapsed_time": "0:38:53", "remaining_time": "6:24:18", "throughput": 1510.51, "total_tokens": 3525472} {"current_steps": 16715, "total_steps": 181800, "loss": 0.1046, "lr": 4.596809680968097e-05, "epoch": 1.8388338833883389, "percentage": 9.19, "elapsed_time": "0:38:54", "remaining_time": "6:24:18", "throughput": 1510.51, "total_tokens": 3526528} {"current_steps": 16720, "total_steps": 181800, "loss": 0.0968, "lr": 4.598184818481848e-05, "epoch": 1.8393839383938393, "percentage": 9.2, "elapsed_time": "0:38:55", "remaining_time": "6:24:17", "throughput": 1510.52, "total_tokens": 3527584} {"current_steps": 16725, "total_steps": 181800, "loss": 0.0818, "lr": 4.5995599559956e-05, "epoch": 1.83993399339934, "percentage": 9.2, "elapsed_time": "0:38:56", "remaining_time": "6:24:16", "throughput": 1510.54, "total_tokens": 3528672} {"current_steps": 16730, "total_steps": 181800, "loss": 0.0775, "lr": 4.600935093509351e-05, "epoch": 1.8404840484048406, "percentage": 9.2, "elapsed_time": "0:38:56", "remaining_time": "6:24:15", "throughput": 1510.56, "total_tokens": 3529760} {"current_steps": 16735, "total_steps": 181800, "loss": 0.041, "lr": 4.602310231023102e-05, "epoch": 1.841034103410341, "percentage": 9.21, "elapsed_time": "0:38:57", "remaining_time": "6:24:14", "throughput": 1510.58, "total_tokens": 3530848} {"current_steps": 16740, "total_steps": 181800, "loss": 0.0612, "lr": 4.603685368536854e-05, "epoch": 1.8415841584158414, "percentage": 9.21, "elapsed_time": "0:38:58", "remaining_time": "6:24:14", "throughput": 1510.58, "total_tokens": 3531872} {"current_steps": 16745, "total_steps": 181800, "loss": 0.1, "lr": 4.605060506050605e-05, "epoch": 1.842134213421342, "percentage": 9.21, "elapsed_time": "0:38:58", "remaining_time": "6:24:13", "throughput": 1510.56, "total_tokens": 3532864} {"current_steps": 16750, "total_steps": 181800, "loss": 0.0841, "lr": 4.606435643564357e-05, "epoch": 1.8426842684268427, "percentage": 9.21, "elapsed_time": "0:38:59", "remaining_time": "6:24:12", "throughput": 1510.54, "total_tokens": 3533856} {"current_steps": 16755, "total_steps": 181800, "loss": 0.0753, "lr": 4.6078107810781077e-05, "epoch": 1.8432343234323434, "percentage": 9.22, "elapsed_time": "0:39:00", "remaining_time": "6:24:11", "throughput": 1510.55, "total_tokens": 3534944} {"current_steps": 16760, "total_steps": 181800, "loss": 0.0618, "lr": 4.6091859185918595e-05, "epoch": 1.8437843784378438, "percentage": 9.22, "elapsed_time": "0:39:00", "remaining_time": "6:24:11", "throughput": 1510.56, "total_tokens": 3536000} {"current_steps": 16765, "total_steps": 181800, "loss": 0.0599, "lr": 4.610561056105611e-05, "epoch": 1.8443344334433442, "percentage": 9.22, "elapsed_time": "0:39:01", "remaining_time": "6:24:10", "throughput": 1510.58, "total_tokens": 3537088} {"current_steps": 16770, "total_steps": 181800, "loss": 0.109, "lr": 4.6119361936193625e-05, "epoch": 1.844884488448845, "percentage": 9.22, "elapsed_time": "0:39:02", "remaining_time": "6:24:09", "throughput": 1510.58, "total_tokens": 3538144} {"current_steps": 16775, "total_steps": 181800, "loss": 0.157, "lr": 4.613311331133113e-05, "epoch": 1.8454345434543455, "percentage": 9.23, "elapsed_time": "0:39:02", "remaining_time": "6:24:08", "throughput": 1510.6, "total_tokens": 3539232} {"current_steps": 16780, "total_steps": 181800, "loss": 0.1457, "lr": 4.614686468646865e-05, "epoch": 1.845984598459846, "percentage": 9.23, "elapsed_time": "0:39:03", "remaining_time": "6:24:07", "throughput": 1510.65, "total_tokens": 3540384} {"current_steps": 16785, "total_steps": 181800, "loss": 0.1929, "lr": 4.616061606160617e-05, "epoch": 1.8465346534653464, "percentage": 9.23, "elapsed_time": "0:39:04", "remaining_time": "6:24:07", "throughput": 1510.67, "total_tokens": 3541472} {"current_steps": 16790, "total_steps": 181800, "loss": 0.1067, "lr": 4.617436743674368e-05, "epoch": 1.847084708470847, "percentage": 9.24, "elapsed_time": "0:39:04", "remaining_time": "6:24:06", "throughput": 1510.68, "total_tokens": 3542528} {"current_steps": 16795, "total_steps": 181800, "loss": 0.0871, "lr": 4.618811881188119e-05, "epoch": 1.8476347634763477, "percentage": 9.24, "elapsed_time": "0:39:05", "remaining_time": "6:24:05", "throughput": 1510.67, "total_tokens": 3543552} {"current_steps": 16800, "total_steps": 181800, "loss": 0.1924, "lr": 4.62018701870187e-05, "epoch": 1.8481848184818483, "percentage": 9.24, "elapsed_time": "0:39:06", "remaining_time": "6:24:04", "throughput": 1510.68, "total_tokens": 3544608} {"current_steps": 16805, "total_steps": 181800, "loss": 0.0772, "lr": 4.621562156215622e-05, "epoch": 1.8487348734873488, "percentage": 9.24, "elapsed_time": "0:39:07", "remaining_time": "6:24:03", "throughput": 1510.68, "total_tokens": 3545632} {"current_steps": 16810, "total_steps": 181800, "loss": 0.0855, "lr": 4.622937293729373e-05, "epoch": 1.8492849284928492, "percentage": 9.25, "elapsed_time": "0:39:07", "remaining_time": "6:24:02", "throughput": 1510.7, "total_tokens": 3546720} {"current_steps": 16815, "total_steps": 181800, "loss": 0.0289, "lr": 4.6243124312431244e-05, "epoch": 1.8498349834983498, "percentage": 9.25, "elapsed_time": "0:39:08", "remaining_time": "6:24:02", "throughput": 1510.72, "total_tokens": 3547808} {"current_steps": 16820, "total_steps": 181800, "loss": 0.0716, "lr": 4.6256875687568755e-05, "epoch": 1.8503850385038505, "percentage": 9.25, "elapsed_time": "0:39:09", "remaining_time": "6:24:01", "throughput": 1510.71, "total_tokens": 3548832} {"current_steps": 16825, "total_steps": 181800, "loss": 0.0836, "lr": 4.6270627062706274e-05, "epoch": 1.850935093509351, "percentage": 9.25, "elapsed_time": "0:39:09", "remaining_time": "6:24:00", "throughput": 1510.72, "total_tokens": 3549888} {"current_steps": 16830, "total_steps": 181800, "loss": 0.1574, "lr": 4.6284378437843785e-05, "epoch": 1.8514851485148514, "percentage": 9.26, "elapsed_time": "0:39:10", "remaining_time": "6:23:59", "throughput": 1510.73, "total_tokens": 3550944} {"current_steps": 16835, "total_steps": 181800, "loss": 0.1218, "lr": 4.62981298129813e-05, "epoch": 1.852035203520352, "percentage": 9.26, "elapsed_time": "0:39:11", "remaining_time": "6:23:59", "throughput": 1510.72, "total_tokens": 3551968} {"current_steps": 16840, "total_steps": 181800, "loss": 0.1272, "lr": 4.6311881188118815e-05, "epoch": 1.8525852585258527, "percentage": 9.26, "elapsed_time": "0:39:11", "remaining_time": "6:23:58", "throughput": 1510.7, "total_tokens": 3552960} {"current_steps": 16845, "total_steps": 181800, "loss": 0.0692, "lr": 4.632563256325633e-05, "epoch": 1.8531353135313533, "percentage": 9.27, "elapsed_time": "0:39:12", "remaining_time": "6:23:57", "throughput": 1510.7, "total_tokens": 3554016} {"current_steps": 16850, "total_steps": 181800, "loss": 0.1358, "lr": 4.6339383938393845e-05, "epoch": 1.8536853685368537, "percentage": 9.27, "elapsed_time": "0:39:13", "remaining_time": "6:23:56", "throughput": 1510.71, "total_tokens": 3555072} {"current_steps": 16855, "total_steps": 181800, "loss": 0.1095, "lr": 4.635313531353136e-05, "epoch": 1.8542354235423542, "percentage": 9.27, "elapsed_time": "0:39:13", "remaining_time": "6:23:55", "throughput": 1510.73, "total_tokens": 3556160} {"current_steps": 16860, "total_steps": 181800, "loss": 0.1386, "lr": 4.636688668866887e-05, "epoch": 1.8547854785478548, "percentage": 9.27, "elapsed_time": "0:39:14", "remaining_time": "6:23:55", "throughput": 1510.71, "total_tokens": 3557152} {"current_steps": 16865, "total_steps": 181800, "loss": 0.1139, "lr": 4.638063806380638e-05, "epoch": 1.8553355335533555, "percentage": 9.28, "elapsed_time": "0:39:15", "remaining_time": "6:23:54", "throughput": 1510.71, "total_tokens": 3558208} {"current_steps": 16870, "total_steps": 181800, "loss": 0.1469, "lr": 4.63943894389439e-05, "epoch": 1.8558855885588559, "percentage": 9.28, "elapsed_time": "0:39:16", "remaining_time": "6:23:53", "throughput": 1510.71, "total_tokens": 3559232} {"current_steps": 16875, "total_steps": 181800, "loss": 0.0869, "lr": 4.640814081408141e-05, "epoch": 1.8564356435643563, "percentage": 9.28, "elapsed_time": "0:39:16", "remaining_time": "6:23:52", "throughput": 1510.73, "total_tokens": 3560320} {"current_steps": 16880, "total_steps": 181800, "loss": 0.0666, "lr": 4.642189218921892e-05, "epoch": 1.856985698569857, "percentage": 9.28, "elapsed_time": "0:39:17", "remaining_time": "6:23:51", "throughput": 1510.76, "total_tokens": 3561440} {"current_steps": 16885, "total_steps": 181800, "loss": 0.1696, "lr": 4.643564356435644e-05, "epoch": 1.8575357535753576, "percentage": 9.29, "elapsed_time": "0:39:18", "remaining_time": "6:23:51", "throughput": 1510.77, "total_tokens": 3562496} {"current_steps": 16890, "total_steps": 181800, "loss": 0.1386, "lr": 4.644939493949395e-05, "epoch": 1.858085808580858, "percentage": 9.29, "elapsed_time": "0:39:18", "remaining_time": "6:23:50", "throughput": 1510.82, "total_tokens": 3563648} {"current_steps": 16895, "total_steps": 181800, "loss": 0.0749, "lr": 4.6463146314631464e-05, "epoch": 1.8586358635863587, "percentage": 9.29, "elapsed_time": "0:39:19", "remaining_time": "6:23:49", "throughput": 1510.8, "total_tokens": 3564640} {"current_steps": 16900, "total_steps": 181800, "loss": 0.0371, "lr": 4.6476897689768976e-05, "epoch": 1.859185918591859, "percentage": 9.3, "elapsed_time": "0:39:20", "remaining_time": "6:23:48", "throughput": 1510.81, "total_tokens": 3565696} {"current_steps": 16905, "total_steps": 181800, "loss": 0.07, "lr": 4.6490649064906494e-05, "epoch": 1.8597359735973598, "percentage": 9.3, "elapsed_time": "0:39:20", "remaining_time": "6:23:47", "throughput": 1510.8, "total_tokens": 3566720} {"current_steps": 16910, "total_steps": 181800, "loss": 0.1506, "lr": 4.6504400440044006e-05, "epoch": 1.8602860286028604, "percentage": 9.3, "elapsed_time": "0:39:21", "remaining_time": "6:23:47", "throughput": 1510.81, "total_tokens": 3567776} {"current_steps": 16915, "total_steps": 181800, "loss": 0.0943, "lr": 4.6518151815181524e-05, "epoch": 1.8608360836083608, "percentage": 9.3, "elapsed_time": "0:39:22", "remaining_time": "6:23:46", "throughput": 1510.83, "total_tokens": 3568864} {"current_steps": 16920, "total_steps": 181800, "loss": 0.2302, "lr": 4.653190319031903e-05, "epoch": 1.8613861386138613, "percentage": 9.31, "elapsed_time": "0:39:22", "remaining_time": "6:23:45", "throughput": 1510.85, "total_tokens": 3569952} {"current_steps": 16925, "total_steps": 181800, "loss": 0.073, "lr": 4.654565456545655e-05, "epoch": 1.861936193619362, "percentage": 9.31, "elapsed_time": "0:39:23", "remaining_time": "6:23:44", "throughput": 1510.88, "total_tokens": 3571072} {"current_steps": 16930, "total_steps": 181800, "loss": 0.0551, "lr": 4.6559405940594066e-05, "epoch": 1.8624862486248626, "percentage": 9.31, "elapsed_time": "0:39:24", "remaining_time": "6:23:43", "throughput": 1510.93, "total_tokens": 3572224} {"current_steps": 16935, "total_steps": 181800, "loss": 0.0938, "lr": 4.657315731573158e-05, "epoch": 1.863036303630363, "percentage": 9.32, "elapsed_time": "0:39:24", "remaining_time": "6:23:43", "throughput": 1510.93, "total_tokens": 3573248} {"current_steps": 16940, "total_steps": 181800, "loss": 0.0862, "lr": 4.658690869086909e-05, "epoch": 1.8635863586358636, "percentage": 9.32, "elapsed_time": "0:39:25", "remaining_time": "6:23:42", "throughput": 1510.92, "total_tokens": 3574272} {"current_steps": 16945, "total_steps": 181800, "loss": 0.1688, "lr": 4.66006600660066e-05, "epoch": 1.864136413641364, "percentage": 9.32, "elapsed_time": "0:39:26", "remaining_time": "6:23:41", "throughput": 1510.91, "total_tokens": 3575296} {"current_steps": 16950, "total_steps": 181800, "loss": 0.0806, "lr": 4.661441144114412e-05, "epoch": 1.8646864686468647, "percentage": 9.32, "elapsed_time": "0:39:26", "remaining_time": "6:23:40", "throughput": 1510.94, "total_tokens": 3576384} {"current_steps": 16955, "total_steps": 181800, "loss": 0.101, "lr": 4.662816281628163e-05, "epoch": 1.8652365236523654, "percentage": 9.33, "elapsed_time": "0:39:27", "remaining_time": "6:23:39", "throughput": 1510.93, "total_tokens": 3577408} {"current_steps": 16960, "total_steps": 181800, "loss": 0.0766, "lr": 4.664191419141914e-05, "epoch": 1.8657865786578658, "percentage": 9.33, "elapsed_time": "0:39:28", "remaining_time": "6:23:39", "throughput": 1510.91, "total_tokens": 3578400} {"current_steps": 16965, "total_steps": 181800, "loss": 0.0878, "lr": 4.6655665566556654e-05, "epoch": 1.8663366336633662, "percentage": 9.33, "elapsed_time": "0:39:29", "remaining_time": "6:23:38", "throughput": 1510.9, "total_tokens": 3579424} {"current_steps": 16970, "total_steps": 181800, "loss": 0.1034, "lr": 4.666941694169417e-05, "epoch": 1.8668866886688669, "percentage": 9.33, "elapsed_time": "0:39:29", "remaining_time": "6:23:37", "throughput": 1510.91, "total_tokens": 3580480} {"current_steps": 16975, "total_steps": 181800, "loss": 0.1171, "lr": 4.668316831683169e-05, "epoch": 1.8674367436743675, "percentage": 9.34, "elapsed_time": "0:39:30", "remaining_time": "6:23:36", "throughput": 1510.91, "total_tokens": 3581536} {"current_steps": 16980, "total_steps": 181800, "loss": 0.1127, "lr": 4.6696919691969196e-05, "epoch": 1.867986798679868, "percentage": 9.34, "elapsed_time": "0:39:31", "remaining_time": "6:23:35", "throughput": 1510.94, "total_tokens": 3582656} {"current_steps": 16985, "total_steps": 181800, "loss": 0.0812, "lr": 4.6710671067106714e-05, "epoch": 1.8685368536853684, "percentage": 9.34, "elapsed_time": "0:39:31", "remaining_time": "6:23:35", "throughput": 1510.95, "total_tokens": 3583712} {"current_steps": 16990, "total_steps": 181800, "loss": 0.0456, "lr": 4.6724422442244226e-05, "epoch": 1.869086908690869, "percentage": 9.35, "elapsed_time": "0:39:32", "remaining_time": "6:23:34", "throughput": 1510.97, "total_tokens": 3584800} {"current_steps": 16995, "total_steps": 181800, "loss": 0.0887, "lr": 4.6738173817381744e-05, "epoch": 1.8696369636963697, "percentage": 9.35, "elapsed_time": "0:39:33", "remaining_time": "6:23:33", "throughput": 1510.97, "total_tokens": 3585856} {"current_steps": 17000, "total_steps": 181800, "loss": 0.0327, "lr": 4.675192519251925e-05, "epoch": 1.8701870187018703, "percentage": 9.35, "elapsed_time": "0:39:33", "remaining_time": "6:23:32", "throughput": 1510.97, "total_tokens": 3586880} {"current_steps": 17005, "total_steps": 181800, "loss": 0.0862, "lr": 4.676567656765677e-05, "epoch": 1.8707370737073707, "percentage": 9.35, "elapsed_time": "0:39:34", "remaining_time": "6:23:32", "throughput": 1510.97, "total_tokens": 3587936} {"current_steps": 17010, "total_steps": 181800, "loss": 0.1017, "lr": 4.677942794279428e-05, "epoch": 1.8712871287128712, "percentage": 9.36, "elapsed_time": "0:39:35", "remaining_time": "6:23:31", "throughput": 1510.95, "total_tokens": 3588928} {"current_steps": 17015, "total_steps": 181800, "loss": 0.0548, "lr": 4.67931793179318e-05, "epoch": 1.8718371837183718, "percentage": 9.36, "elapsed_time": "0:39:35", "remaining_time": "6:23:30", "throughput": 1510.96, "total_tokens": 3589984} {"current_steps": 17020, "total_steps": 181800, "loss": 0.06, "lr": 4.680693069306931e-05, "epoch": 1.8723872387238725, "percentage": 9.36, "elapsed_time": "0:39:36", "remaining_time": "6:23:29", "throughput": 1510.97, "total_tokens": 3591040} {"current_steps": 17025, "total_steps": 181800, "loss": 0.1385, "lr": 4.682068206820682e-05, "epoch": 1.872937293729373, "percentage": 9.36, "elapsed_time": "0:39:37", "remaining_time": "6:23:28", "throughput": 1510.95, "total_tokens": 3592032} {"current_steps": 17030, "total_steps": 181800, "loss": 0.0356, "lr": 4.683443344334434e-05, "epoch": 1.8734873487348733, "percentage": 9.37, "elapsed_time": "0:39:38", "remaining_time": "6:23:27", "throughput": 1510.93, "total_tokens": 3593024} {"current_steps": 17035, "total_steps": 181800, "loss": 0.0582, "lr": 4.684818481848185e-05, "epoch": 1.874037403740374, "percentage": 9.37, "elapsed_time": "0:39:38", "remaining_time": "6:23:27", "throughput": 1510.91, "total_tokens": 3594016} {"current_steps": 17040, "total_steps": 181800, "loss": 0.0624, "lr": 4.686193619361936e-05, "epoch": 1.8745874587458746, "percentage": 9.37, "elapsed_time": "0:39:39", "remaining_time": "6:23:26", "throughput": 1510.93, "total_tokens": 3595104} {"current_steps": 17045, "total_steps": 181800, "loss": 0.1257, "lr": 4.6875687568756875e-05, "epoch": 1.8751375137513753, "percentage": 9.38, "elapsed_time": "0:39:40", "remaining_time": "6:23:25", "throughput": 1510.96, "total_tokens": 3596224} {"current_steps": 17050, "total_steps": 181800, "loss": 0.0596, "lr": 4.688943894389439e-05, "epoch": 1.8756875687568757, "percentage": 9.38, "elapsed_time": "0:39:40", "remaining_time": "6:23:24", "throughput": 1510.96, "total_tokens": 3597248} {"current_steps": 17055, "total_steps": 181800, "loss": 0.0415, "lr": 4.6903190319031905e-05, "epoch": 1.8762376237623761, "percentage": 9.38, "elapsed_time": "0:39:41", "remaining_time": "6:23:24", "throughput": 1510.92, "total_tokens": 3598208} {"current_steps": 17060, "total_steps": 181800, "loss": 0.0541, "lr": 4.6916941694169416e-05, "epoch": 1.8767876787678768, "percentage": 9.38, "elapsed_time": "0:39:42", "remaining_time": "6:23:23", "throughput": 1510.92, "total_tokens": 3599232} {"current_steps": 17065, "total_steps": 181800, "loss": 0.2048, "lr": 4.693069306930693e-05, "epoch": 1.8773377337733774, "percentage": 9.39, "elapsed_time": "0:39:42", "remaining_time": "6:23:22", "throughput": 1510.94, "total_tokens": 3600320} {"current_steps": 17070, "total_steps": 181800, "loss": 0.1467, "lr": 4.6944444444444446e-05, "epoch": 1.8778877887788779, "percentage": 9.39, "elapsed_time": "0:39:43", "remaining_time": "6:23:21", "throughput": 1510.95, "total_tokens": 3601408} {"current_steps": 17075, "total_steps": 181800, "loss": 0.054, "lr": 4.6958195819581965e-05, "epoch": 1.8784378437843783, "percentage": 9.39, "elapsed_time": "0:39:44", "remaining_time": "6:23:20", "throughput": 1510.96, "total_tokens": 3602464} {"current_steps": 17080, "total_steps": 181800, "loss": 0.0868, "lr": 4.6971947194719476e-05, "epoch": 1.878987898789879, "percentage": 9.39, "elapsed_time": "0:39:44", "remaining_time": "6:23:20", "throughput": 1510.97, "total_tokens": 3603520} {"current_steps": 17085, "total_steps": 181800, "loss": 0.0367, "lr": 4.698569856985699e-05, "epoch": 1.8795379537953796, "percentage": 9.4, "elapsed_time": "0:39:45", "remaining_time": "6:23:19", "throughput": 1510.99, "total_tokens": 3604608} {"current_steps": 17090, "total_steps": 181800, "loss": 0.0951, "lr": 4.69994499449945e-05, "epoch": 1.8800880088008802, "percentage": 9.4, "elapsed_time": "0:39:46", "remaining_time": "6:23:18", "throughput": 1510.99, "total_tokens": 3605664} {"current_steps": 17095, "total_steps": 181800, "loss": 0.1219, "lr": 4.701320132013202e-05, "epoch": 1.8806380638063807, "percentage": 9.4, "elapsed_time": "0:39:46", "remaining_time": "6:23:17", "throughput": 1510.99, "total_tokens": 3606688} {"current_steps": 17100, "total_steps": 181800, "loss": 0.0727, "lr": 4.702695269526953e-05, "epoch": 1.881188118811881, "percentage": 9.41, "elapsed_time": "0:39:47", "remaining_time": "6:23:16", "throughput": 1510.99, "total_tokens": 3607744} {"current_steps": 17105, "total_steps": 181800, "loss": 0.0723, "lr": 4.704070407040704e-05, "epoch": 1.8817381738173817, "percentage": 9.41, "elapsed_time": "0:39:48", "remaining_time": "6:23:16", "throughput": 1511.02, "total_tokens": 3608832} {"current_steps": 17110, "total_steps": 181800, "loss": 0.0359, "lr": 4.705445544554455e-05, "epoch": 1.8822882288228824, "percentage": 9.41, "elapsed_time": "0:39:49", "remaining_time": "6:23:15", "throughput": 1511.0, "total_tokens": 3609824} {"current_steps": 17115, "total_steps": 181800, "loss": 0.0789, "lr": 4.706820682068207e-05, "epoch": 1.8828382838283828, "percentage": 9.41, "elapsed_time": "0:39:49", "remaining_time": "6:23:14", "throughput": 1511.01, "total_tokens": 3610880} {"current_steps": 17120, "total_steps": 181800, "loss": 0.1334, "lr": 4.708195819581958e-05, "epoch": 1.8833883388338832, "percentage": 9.42, "elapsed_time": "0:39:50", "remaining_time": "6:23:13", "throughput": 1511.0, "total_tokens": 3611904} {"current_steps": 17125, "total_steps": 181800, "loss": 0.0741, "lr": 4.7095709570957095e-05, "epoch": 1.8839383938393839, "percentage": 9.42, "elapsed_time": "0:39:51", "remaining_time": "6:23:12", "throughput": 1510.98, "total_tokens": 3612896} {"current_steps": 17130, "total_steps": 181800, "loss": 0.0501, "lr": 4.710946094609461e-05, "epoch": 1.8844884488448845, "percentage": 9.42, "elapsed_time": "0:39:51", "remaining_time": "6:23:12", "throughput": 1510.95, "total_tokens": 3613856} {"current_steps": 17135, "total_steps": 181800, "loss": 0.0548, "lr": 4.7123212321232125e-05, "epoch": 1.8850385038503852, "percentage": 9.43, "elapsed_time": "0:39:52", "remaining_time": "6:23:11", "throughput": 1510.97, "total_tokens": 3614944} {"current_steps": 17140, "total_steps": 181800, "loss": 0.0483, "lr": 4.7136963696369643e-05, "epoch": 1.8855885588558856, "percentage": 9.43, "elapsed_time": "0:39:53", "remaining_time": "6:23:10", "throughput": 1510.99, "total_tokens": 3616032} {"current_steps": 17145, "total_steps": 181800, "loss": 0.0593, "lr": 4.715071507150715e-05, "epoch": 1.886138613861386, "percentage": 9.43, "elapsed_time": "0:39:53", "remaining_time": "6:23:09", "throughput": 1510.99, "total_tokens": 3617056} {"current_steps": 17150, "total_steps": 181800, "loss": 0.1037, "lr": 4.716446644664467e-05, "epoch": 1.8866886688668867, "percentage": 9.43, "elapsed_time": "0:39:54", "remaining_time": "6:23:08", "throughput": 1511.02, "total_tokens": 3618176} {"current_steps": 17155, "total_steps": 181800, "loss": 0.1836, "lr": 4.717821782178218e-05, "epoch": 1.8872387238723873, "percentage": 9.44, "elapsed_time": "0:39:55", "remaining_time": "6:23:08", "throughput": 1511.03, "total_tokens": 3619232} {"current_steps": 17160, "total_steps": 181800, "loss": 0.0979, "lr": 4.71919691969197e-05, "epoch": 1.8877887788778878, "percentage": 9.44, "elapsed_time": "0:39:55", "remaining_time": "6:23:07", "throughput": 1511.05, "total_tokens": 3620320} {"current_steps": 17165, "total_steps": 181800, "loss": 0.1946, "lr": 4.720572057205721e-05, "epoch": 1.8883388338833882, "percentage": 9.44, "elapsed_time": "0:39:56", "remaining_time": "6:23:06", "throughput": 1511.06, "total_tokens": 3621376} {"current_steps": 17170, "total_steps": 181800, "loss": 0.0571, "lr": 4.721947194719472e-05, "epoch": 1.8888888888888888, "percentage": 9.44, "elapsed_time": "0:39:57", "remaining_time": "6:23:05", "throughput": 1511.04, "total_tokens": 3622368} {"current_steps": 17175, "total_steps": 181800, "loss": 0.1728, "lr": 4.723322332233224e-05, "epoch": 1.8894389438943895, "percentage": 9.45, "elapsed_time": "0:39:57", "remaining_time": "6:23:04", "throughput": 1511.03, "total_tokens": 3623392} {"current_steps": 17180, "total_steps": 181800, "loss": 0.0292, "lr": 4.724697469746975e-05, "epoch": 1.8899889988998901, "percentage": 9.45, "elapsed_time": "0:39:58", "remaining_time": "6:23:03", "throughput": 1511.03, "total_tokens": 3624416} {"current_steps": 17185, "total_steps": 181800, "loss": 0.101, "lr": 4.726072607260726e-05, "epoch": 1.8905390539053906, "percentage": 9.45, "elapsed_time": "0:39:59", "remaining_time": "6:23:03", "throughput": 1511.02, "total_tokens": 3625440} {"current_steps": 17190, "total_steps": 181800, "loss": 0.1163, "lr": 4.7274477447744774e-05, "epoch": 1.891089108910891, "percentage": 9.46, "elapsed_time": "0:40:00", "remaining_time": "6:23:02", "throughput": 1511.03, "total_tokens": 3626496} {"current_steps": 17195, "total_steps": 181800, "loss": 0.2327, "lr": 4.728822882288229e-05, "epoch": 1.8916391639163916, "percentage": 9.46, "elapsed_time": "0:40:00", "remaining_time": "6:23:01", "throughput": 1510.99, "total_tokens": 3627456} {"current_steps": 17200, "total_steps": 181800, "loss": 0.088, "lr": 4.7301980198019804e-05, "epoch": 1.8921892189218923, "percentage": 9.46, "elapsed_time": "0:40:01", "remaining_time": "6:23:00", "throughput": 1510.99, "total_tokens": 3628480} {"current_steps": 17205, "total_steps": 181800, "loss": 0.1211, "lr": 4.7315731573157315e-05, "epoch": 1.8927392739273927, "percentage": 9.46, "elapsed_time": "0:40:02", "remaining_time": "6:22:59", "throughput": 1510.98, "total_tokens": 3629504} {"current_steps": 17210, "total_steps": 181800, "loss": 0.0697, "lr": 4.7329482948294834e-05, "epoch": 1.8932893289328931, "percentage": 9.47, "elapsed_time": "0:40:02", "remaining_time": "6:22:59", "throughput": 1511.0, "total_tokens": 3630592} {"current_steps": 17215, "total_steps": 181800, "loss": 0.0688, "lr": 4.7343234323432345e-05, "epoch": 1.8938393839383938, "percentage": 9.47, "elapsed_time": "0:40:03", "remaining_time": "6:22:58", "throughput": 1511.03, "total_tokens": 3631712} {"current_steps": 17220, "total_steps": 181800, "loss": 0.1153, "lr": 4.7356985698569864e-05, "epoch": 1.8943894389438944, "percentage": 9.47, "elapsed_time": "0:40:04", "remaining_time": "6:22:57", "throughput": 1511.04, "total_tokens": 3632768} {"current_steps": 17225, "total_steps": 181800, "loss": 0.1135, "lr": 4.737073707370737e-05, "epoch": 1.894939493949395, "percentage": 9.47, "elapsed_time": "0:40:04", "remaining_time": "6:22:56", "throughput": 1511.06, "total_tokens": 3633856} {"current_steps": 17230, "total_steps": 181800, "loss": 0.0581, "lr": 4.738448844884489e-05, "epoch": 1.8954895489548955, "percentage": 9.48, "elapsed_time": "0:40:05", "remaining_time": "6:22:56", "throughput": 1511.08, "total_tokens": 3634944} {"current_steps": 17235, "total_steps": 181800, "loss": 0.0371, "lr": 4.73982398239824e-05, "epoch": 1.896039603960396, "percentage": 9.48, "elapsed_time": "0:40:06", "remaining_time": "6:22:55", "throughput": 1511.07, "total_tokens": 3635968} {"current_steps": 17240, "total_steps": 181800, "loss": 0.0792, "lr": 4.741199119911992e-05, "epoch": 1.8965896589658966, "percentage": 9.48, "elapsed_time": "0:40:06", "remaining_time": "6:22:54", "throughput": 1511.09, "total_tokens": 3637056} {"current_steps": 17245, "total_steps": 181800, "loss": 0.0602, "lr": 4.742574257425743e-05, "epoch": 1.8971397139713972, "percentage": 9.49, "elapsed_time": "0:40:07", "remaining_time": "6:22:53", "throughput": 1511.09, "total_tokens": 3638080} {"current_steps": 17250, "total_steps": 181800, "loss": 0.0776, "lr": 4.743949394939494e-05, "epoch": 1.8976897689768977, "percentage": 9.49, "elapsed_time": "0:40:08", "remaining_time": "6:22:52", "throughput": 1511.08, "total_tokens": 3639104} {"current_steps": 17255, "total_steps": 181800, "loss": 0.0903, "lr": 4.745324532453246e-05, "epoch": 1.898239823982398, "percentage": 9.49, "elapsed_time": "0:40:08", "remaining_time": "6:22:52", "throughput": 1511.13, "total_tokens": 3640256} {"current_steps": 17260, "total_steps": 181800, "loss": 0.0645, "lr": 4.746699669966997e-05, "epoch": 1.8987898789878987, "percentage": 9.49, "elapsed_time": "0:40:09", "remaining_time": "6:22:51", "throughput": 1511.12, "total_tokens": 3641280} {"current_steps": 17265, "total_steps": 181800, "loss": 0.0342, "lr": 4.748074807480748e-05, "epoch": 1.8993399339933994, "percentage": 9.5, "elapsed_time": "0:40:10", "remaining_time": "6:22:50", "throughput": 1511.13, "total_tokens": 3642336} {"current_steps": 17270, "total_steps": 181800, "loss": 0.1466, "lr": 4.7494499449944994e-05, "epoch": 1.8998899889989, "percentage": 9.5, "elapsed_time": "0:40:11", "remaining_time": "6:22:49", "throughput": 1511.14, "total_tokens": 3643392} {"current_steps": 17275, "total_steps": 181800, "loss": 0.185, "lr": 4.750825082508251e-05, "epoch": 1.9004400440044005, "percentage": 9.5, "elapsed_time": "0:40:11", "remaining_time": "6:22:48", "throughput": 1511.16, "total_tokens": 3644480} {"current_steps": 17280, "total_steps": 181800, "loss": 0.1149, "lr": 4.7522002200220024e-05, "epoch": 1.900990099009901, "percentage": 9.5, "elapsed_time": "0:40:12", "remaining_time": "6:22:48", "throughput": 1511.18, "total_tokens": 3645568} {"current_steps": 17285, "total_steps": 181800, "loss": 0.0728, "lr": 4.7535753575357536e-05, "epoch": 1.9015401540154016, "percentage": 9.51, "elapsed_time": "0:40:13", "remaining_time": "6:22:47", "throughput": 1511.17, "total_tokens": 3646592} {"current_steps": 17290, "total_steps": 181800, "loss": 0.0885, "lr": 4.754950495049505e-05, "epoch": 1.9020902090209022, "percentage": 9.51, "elapsed_time": "0:40:13", "remaining_time": "6:22:46", "throughput": 1511.16, "total_tokens": 3647616} {"current_steps": 17295, "total_steps": 181800, "loss": 0.0483, "lr": 4.7563256325632566e-05, "epoch": 1.9026402640264026, "percentage": 9.51, "elapsed_time": "0:40:14", "remaining_time": "6:22:45", "throughput": 1511.18, "total_tokens": 3648704} {"current_steps": 17300, "total_steps": 181800, "loss": 0.1263, "lr": 4.757700770077008e-05, "epoch": 1.903190319031903, "percentage": 9.52, "elapsed_time": "0:40:15", "remaining_time": "6:22:45", "throughput": 1511.2, "total_tokens": 3649792} {"current_steps": 17305, "total_steps": 181800, "loss": 0.1289, "lr": 4.7590759075907596e-05, "epoch": 1.9037403740374037, "percentage": 9.52, "elapsed_time": "0:40:15", "remaining_time": "6:22:44", "throughput": 1511.22, "total_tokens": 3650880} {"current_steps": 17310, "total_steps": 181800, "loss": 0.0786, "lr": 4.760451045104511e-05, "epoch": 1.9042904290429044, "percentage": 9.52, "elapsed_time": "0:40:16", "remaining_time": "6:22:43", "throughput": 1511.25, "total_tokens": 3652000} {"current_steps": 17315, "total_steps": 181800, "loss": 0.0298, "lr": 4.761826182618262e-05, "epoch": 1.904840484048405, "percentage": 9.52, "elapsed_time": "0:40:17", "remaining_time": "6:22:42", "throughput": 1511.24, "total_tokens": 3653024} {"current_steps": 17320, "total_steps": 181800, "loss": 0.0533, "lr": 4.763201320132014e-05, "epoch": 1.9053905390539054, "percentage": 9.53, "elapsed_time": "0:40:17", "remaining_time": "6:22:41", "throughput": 1511.28, "total_tokens": 3654144} {"current_steps": 17325, "total_steps": 181800, "loss": 0.0402, "lr": 4.764576457645765e-05, "epoch": 1.9059405940594059, "percentage": 9.53, "elapsed_time": "0:40:18", "remaining_time": "6:22:41", "throughput": 1511.27, "total_tokens": 3655168} {"current_steps": 17330, "total_steps": 181800, "loss": 0.1809, "lr": 4.765951595159516e-05, "epoch": 1.9064906490649065, "percentage": 9.53, "elapsed_time": "0:40:19", "remaining_time": "6:22:40", "throughput": 1511.25, "total_tokens": 3656160} {"current_steps": 17335, "total_steps": 181800, "loss": 0.0435, "lr": 4.767326732673267e-05, "epoch": 1.9070407040704072, "percentage": 9.54, "elapsed_time": "0:40:19", "remaining_time": "6:22:39", "throughput": 1511.29, "total_tokens": 3657312} {"current_steps": 17340, "total_steps": 181800, "loss": 0.0507, "lr": 4.768701870187019e-05, "epoch": 1.9075907590759076, "percentage": 9.54, "elapsed_time": "0:40:20", "remaining_time": "6:22:38", "throughput": 1511.31, "total_tokens": 3658400} {"current_steps": 17345, "total_steps": 181800, "loss": 0.044, "lr": 4.77007700770077e-05, "epoch": 1.908140814081408, "percentage": 9.54, "elapsed_time": "0:40:21", "remaining_time": "6:22:37", "throughput": 1511.31, "total_tokens": 3659424} {"current_steps": 17350, "total_steps": 181800, "loss": 0.1308, "lr": 4.7714521452145214e-05, "epoch": 1.9086908690869087, "percentage": 9.54, "elapsed_time": "0:40:22", "remaining_time": "6:22:37", "throughput": 1511.34, "total_tokens": 3660544} {"current_steps": 17355, "total_steps": 181800, "loss": 0.0812, "lr": 4.772827282728273e-05, "epoch": 1.9092409240924093, "percentage": 9.55, "elapsed_time": "0:40:22", "remaining_time": "6:22:36", "throughput": 1511.35, "total_tokens": 3661600} {"current_steps": 17360, "total_steps": 181800, "loss": 0.2425, "lr": 4.7742024202420244e-05, "epoch": 1.9097909790979097, "percentage": 9.55, "elapsed_time": "0:40:23", "remaining_time": "6:22:35", "throughput": 1511.36, "total_tokens": 3662656} {"current_steps": 17365, "total_steps": 181800, "loss": 0.016, "lr": 4.775577557755776e-05, "epoch": 1.9103410341034104, "percentage": 9.55, "elapsed_time": "0:40:24", "remaining_time": "6:22:34", "throughput": 1511.36, "total_tokens": 3663712} {"current_steps": 17370, "total_steps": 181800, "loss": 0.1259, "lr": 4.776952695269527e-05, "epoch": 1.9108910891089108, "percentage": 9.55, "elapsed_time": "0:40:24", "remaining_time": "6:22:33", "throughput": 1511.36, "total_tokens": 3664736} {"current_steps": 17375, "total_steps": 181800, "loss": 0.1592, "lr": 4.7783278327832786e-05, "epoch": 1.9114411441144115, "percentage": 9.56, "elapsed_time": "0:40:25", "remaining_time": "6:22:33", "throughput": 1511.4, "total_tokens": 3665888} {"current_steps": 17380, "total_steps": 181800, "loss": 0.1296, "lr": 4.77970297029703e-05, "epoch": 1.911991199119912, "percentage": 9.56, "elapsed_time": "0:40:26", "remaining_time": "6:22:32", "throughput": 1511.39, "total_tokens": 3666912} {"current_steps": 17385, "total_steps": 181800, "loss": 0.1453, "lr": 4.7810781078107816e-05, "epoch": 1.9125412541254125, "percentage": 9.56, "elapsed_time": "0:40:26", "remaining_time": "6:22:31", "throughput": 1511.39, "total_tokens": 3667936} {"current_steps": 17390, "total_steps": 181800, "loss": 0.1544, "lr": 4.782453245324532e-05, "epoch": 1.913091309130913, "percentage": 9.57, "elapsed_time": "0:40:27", "remaining_time": "6:22:30", "throughput": 1511.42, "total_tokens": 3669056} {"current_steps": 17395, "total_steps": 181800, "loss": 0.065, "lr": 4.783828382838284e-05, "epoch": 1.9136413641364136, "percentage": 9.57, "elapsed_time": "0:40:28", "remaining_time": "6:22:31", "throughput": 1511.3, "total_tokens": 3670112} {"current_steps": 17400, "total_steps": 181800, "loss": 0.1262, "lr": 4.785203520352036e-05, "epoch": 1.9141914191419143, "percentage": 9.57, "elapsed_time": "0:40:29", "remaining_time": "6:22:31", "throughput": 1511.29, "total_tokens": 3671104} {"current_steps": 17405, "total_steps": 181800, "loss": 0.0887, "lr": 4.786578657865787e-05, "epoch": 1.9147414741474147, "percentage": 9.57, "elapsed_time": "0:40:29", "remaining_time": "6:22:30", "throughput": 1511.28, "total_tokens": 3672128} {"current_steps": 17410, "total_steps": 181800, "loss": 0.0737, "lr": 4.787953795379538e-05, "epoch": 1.9152915291529153, "percentage": 9.58, "elapsed_time": "0:40:30", "remaining_time": "6:22:29", "throughput": 1511.31, "total_tokens": 3673248} {"current_steps": 17415, "total_steps": 181800, "loss": 0.1805, "lr": 4.789328932893289e-05, "epoch": 1.9158415841584158, "percentage": 9.58, "elapsed_time": "0:40:31", "remaining_time": "6:22:28", "throughput": 1511.29, "total_tokens": 3674240} {"current_steps": 17420, "total_steps": 181800, "loss": 0.1965, "lr": 4.790704070407041e-05, "epoch": 1.9163916391639164, "percentage": 9.58, "elapsed_time": "0:40:31", "remaining_time": "6:22:27", "throughput": 1511.34, "total_tokens": 3675392} {"current_steps": 17425, "total_steps": 181800, "loss": 0.1204, "lr": 4.792079207920792e-05, "epoch": 1.916941694169417, "percentage": 9.58, "elapsed_time": "0:40:32", "remaining_time": "6:22:27", "throughput": 1511.38, "total_tokens": 3676544} {"current_steps": 17430, "total_steps": 181800, "loss": 0.0447, "lr": 4.7934543454345435e-05, "epoch": 1.9174917491749175, "percentage": 9.59, "elapsed_time": "0:40:33", "remaining_time": "6:22:26", "throughput": 1511.38, "total_tokens": 3677568} {"current_steps": 17435, "total_steps": 181800, "loss": 0.1089, "lr": 4.7948294829482946e-05, "epoch": 1.918041804180418, "percentage": 9.59, "elapsed_time": "0:40:33", "remaining_time": "6:22:25", "throughput": 1511.37, "total_tokens": 3678592} {"current_steps": 17440, "total_steps": 181800, "loss": 0.0662, "lr": 4.7962046204620465e-05, "epoch": 1.9185918591859186, "percentage": 9.59, "elapsed_time": "0:40:34", "remaining_time": "6:22:24", "throughput": 1511.36, "total_tokens": 3679616} {"current_steps": 17445, "total_steps": 181800, "loss": 0.1697, "lr": 4.797579757975798e-05, "epoch": 1.9191419141914192, "percentage": 9.6, "elapsed_time": "0:40:35", "remaining_time": "6:22:23", "throughput": 1511.33, "total_tokens": 3680576} {"current_steps": 17450, "total_steps": 181800, "loss": 0.1097, "lr": 4.798954895489549e-05, "epoch": 1.9196919691969196, "percentage": 9.6, "elapsed_time": "0:40:36", "remaining_time": "6:22:23", "throughput": 1511.33, "total_tokens": 3681632} {"current_steps": 17455, "total_steps": 181800, "loss": 0.0402, "lr": 4.8003300330033006e-05, "epoch": 1.9202420242024203, "percentage": 9.6, "elapsed_time": "0:40:36", "remaining_time": "6:22:22", "throughput": 1511.33, "total_tokens": 3682656} {"current_steps": 17460, "total_steps": 181800, "loss": 0.1321, "lr": 4.801705170517052e-05, "epoch": 1.9207920792079207, "percentage": 9.6, "elapsed_time": "0:40:37", "remaining_time": "6:22:21", "throughput": 1511.32, "total_tokens": 3683680} {"current_steps": 17465, "total_steps": 181800, "loss": 0.0641, "lr": 4.8030803080308037e-05, "epoch": 1.9213421342134214, "percentage": 9.61, "elapsed_time": "0:40:38", "remaining_time": "6:22:20", "throughput": 1511.32, "total_tokens": 3684704} {"current_steps": 17470, "total_steps": 181800, "loss": 0.1078, "lr": 4.804455445544555e-05, "epoch": 1.921892189218922, "percentage": 9.61, "elapsed_time": "0:40:38", "remaining_time": "6:22:20", "throughput": 1511.31, "total_tokens": 3685728} {"current_steps": 17475, "total_steps": 181800, "loss": 0.0705, "lr": 4.805830583058306e-05, "epoch": 1.9224422442244224, "percentage": 9.61, "elapsed_time": "0:40:39", "remaining_time": "6:22:19", "throughput": 1511.32, "total_tokens": 3686784} {"current_steps": 17480, "total_steps": 181800, "loss": 0.0761, "lr": 4.807205720572057e-05, "epoch": 1.9229922992299229, "percentage": 9.61, "elapsed_time": "0:40:40", "remaining_time": "6:22:18", "throughput": 1511.31, "total_tokens": 3687808} {"current_steps": 17485, "total_steps": 181800, "loss": 0.088, "lr": 4.808580858085809e-05, "epoch": 1.9235423542354235, "percentage": 9.62, "elapsed_time": "0:40:40", "remaining_time": "6:22:17", "throughput": 1511.3, "total_tokens": 3688832} {"current_steps": 17490, "total_steps": 181800, "loss": 0.119, "lr": 4.80995599559956e-05, "epoch": 1.9240924092409242, "percentage": 9.62, "elapsed_time": "0:40:41", "remaining_time": "6:22:16", "throughput": 1511.33, "total_tokens": 3689920} {"current_steps": 17495, "total_steps": 181800, "loss": 0.1074, "lr": 4.811331133113311e-05, "epoch": 1.9246424642464246, "percentage": 9.62, "elapsed_time": "0:40:42", "remaining_time": "6:22:16", "throughput": 1511.35, "total_tokens": 3691008} {"current_steps": 17500, "total_steps": 181800, "loss": 0.1044, "lr": 4.812706270627063e-05, "epoch": 1.925192519251925, "percentage": 9.63, "elapsed_time": "0:40:42", "remaining_time": "6:22:15", "throughput": 1511.37, "total_tokens": 3692096} {"current_steps": 17505, "total_steps": 181800, "loss": 0.0598, "lr": 4.814081408140814e-05, "epoch": 1.9257425742574257, "percentage": 9.63, "elapsed_time": "0:40:43", "remaining_time": "6:22:14", "throughput": 1511.39, "total_tokens": 3693184} {"current_steps": 17510, "total_steps": 181800, "loss": 0.1525, "lr": 4.8154565456545655e-05, "epoch": 1.9262926292629263, "percentage": 9.63, "elapsed_time": "0:40:44", "remaining_time": "6:22:13", "throughput": 1511.4, "total_tokens": 3694240} {"current_steps": 17515, "total_steps": 181800, "loss": 0.1191, "lr": 4.816831683168317e-05, "epoch": 1.926842684268427, "percentage": 9.63, "elapsed_time": "0:40:44", "remaining_time": "6:22:12", "throughput": 1511.41, "total_tokens": 3695328} {"current_steps": 17520, "total_steps": 181800, "loss": 0.0399, "lr": 4.8182068206820685e-05, "epoch": 1.9273927392739274, "percentage": 9.64, "elapsed_time": "0:40:45", "remaining_time": "6:22:12", "throughput": 1511.45, "total_tokens": 3696448} {"current_steps": 17525, "total_steps": 181800, "loss": 0.0732, "lr": 4.81958195819582e-05, "epoch": 1.9279427942794278, "percentage": 9.64, "elapsed_time": "0:40:46", "remaining_time": "6:22:11", "throughput": 1511.47, "total_tokens": 3697536} {"current_steps": 17530, "total_steps": 181800, "loss": 0.0293, "lr": 4.8209570957095715e-05, "epoch": 1.9284928492849285, "percentage": 9.64, "elapsed_time": "0:40:47", "remaining_time": "6:22:10", "throughput": 1511.49, "total_tokens": 3698624} {"current_steps": 17535, "total_steps": 181800, "loss": 0.1319, "lr": 4.822332233223323e-05, "epoch": 1.9290429042904291, "percentage": 9.65, "elapsed_time": "0:40:47", "remaining_time": "6:22:09", "throughput": 1511.48, "total_tokens": 3699648} {"current_steps": 17540, "total_steps": 181800, "loss": 0.0651, "lr": 4.823707370737074e-05, "epoch": 1.9295929592959296, "percentage": 9.65, "elapsed_time": "0:40:48", "remaining_time": "6:22:08", "throughput": 1511.51, "total_tokens": 3700768} {"current_steps": 17545, "total_steps": 181800, "loss": 0.1382, "lr": 4.825082508250826e-05, "epoch": 1.93014301430143, "percentage": 9.65, "elapsed_time": "0:40:49", "remaining_time": "6:22:08", "throughput": 1511.52, "total_tokens": 3701824} {"current_steps": 17550, "total_steps": 181800, "loss": 0.0431, "lr": 4.826457645764577e-05, "epoch": 1.9306930693069306, "percentage": 9.65, "elapsed_time": "0:40:49", "remaining_time": "6:22:07", "throughput": 1511.52, "total_tokens": 3702848} {"current_steps": 17555, "total_steps": 181800, "loss": 0.0243, "lr": 4.827832783278328e-05, "epoch": 1.9312431243124313, "percentage": 9.66, "elapsed_time": "0:40:50", "remaining_time": "6:22:06", "throughput": 1511.55, "total_tokens": 3703968} {"current_steps": 17560, "total_steps": 181800, "loss": 0.0789, "lr": 4.829207920792079e-05, "epoch": 1.931793179317932, "percentage": 9.66, "elapsed_time": "0:40:51", "remaining_time": "6:22:05", "throughput": 1511.54, "total_tokens": 3704992} {"current_steps": 17565, "total_steps": 181800, "loss": 0.0784, "lr": 4.830583058305831e-05, "epoch": 1.9323432343234324, "percentage": 9.66, "elapsed_time": "0:40:51", "remaining_time": "6:22:04", "throughput": 1511.56, "total_tokens": 3706080} {"current_steps": 17570, "total_steps": 181800, "loss": 0.0944, "lr": 4.831958195819582e-05, "epoch": 1.9328932893289328, "percentage": 9.66, "elapsed_time": "0:40:52", "remaining_time": "6:22:03", "throughput": 1511.59, "total_tokens": 3707168} {"current_steps": 17575, "total_steps": 181800, "loss": 0.0991, "lr": 4.8333333333333334e-05, "epoch": 1.9334433443344334, "percentage": 9.67, "elapsed_time": "0:40:53", "remaining_time": "6:22:03", "throughput": 1511.59, "total_tokens": 3708224} {"current_steps": 17580, "total_steps": 181800, "loss": 0.0855, "lr": 4.8347084708470845e-05, "epoch": 1.933993399339934, "percentage": 9.67, "elapsed_time": "0:40:53", "remaining_time": "6:22:02", "throughput": 1511.61, "total_tokens": 3709312} {"current_steps": 17585, "total_steps": 181800, "loss": 0.095, "lr": 4.8360836083608364e-05, "epoch": 1.9345434543454345, "percentage": 9.67, "elapsed_time": "0:40:54", "remaining_time": "6:22:01", "throughput": 1511.6, "total_tokens": 3710336} {"current_steps": 17590, "total_steps": 181800, "loss": 0.0445, "lr": 4.837458745874588e-05, "epoch": 1.935093509350935, "percentage": 9.68, "elapsed_time": "0:40:55", "remaining_time": "6:22:00", "throughput": 1511.61, "total_tokens": 3711392} {"current_steps": 17595, "total_steps": 181800, "loss": 0.1182, "lr": 4.838833883388339e-05, "epoch": 1.9356435643564356, "percentage": 9.68, "elapsed_time": "0:40:55", "remaining_time": "6:22:00", "throughput": 1511.61, "total_tokens": 3712448} {"current_steps": 17600, "total_steps": 181800, "loss": 0.0817, "lr": 4.8402090209020905e-05, "epoch": 1.9361936193619362, "percentage": 9.68, "elapsed_time": "0:40:56", "remaining_time": "6:21:59", "throughput": 1511.62, "total_tokens": 3713504} {"current_steps": 17605, "total_steps": 181800, "loss": 0.1057, "lr": 4.841584158415842e-05, "epoch": 1.9367436743674369, "percentage": 9.68, "elapsed_time": "0:40:57", "remaining_time": "6:21:58", "throughput": 1511.6, "total_tokens": 3714496} {"current_steps": 17610, "total_steps": 181800, "loss": 0.0639, "lr": 4.8429592959295936e-05, "epoch": 1.9372937293729373, "percentage": 9.69, "elapsed_time": "0:40:58", "remaining_time": "6:21:57", "throughput": 1511.6, "total_tokens": 3715520} {"current_steps": 17615, "total_steps": 181800, "loss": 0.0517, "lr": 4.844334433443344e-05, "epoch": 1.9378437843784377, "percentage": 9.69, "elapsed_time": "0:40:58", "remaining_time": "6:21:56", "throughput": 1511.59, "total_tokens": 3716544} {"current_steps": 17620, "total_steps": 181800, "loss": 0.0855, "lr": 4.845709570957096e-05, "epoch": 1.9383938393839384, "percentage": 9.69, "elapsed_time": "0:40:59", "remaining_time": "6:21:56", "throughput": 1511.59, "total_tokens": 3717568} {"current_steps": 17625, "total_steps": 181800, "loss": 0.0678, "lr": 4.847084708470847e-05, "epoch": 1.938943894389439, "percentage": 9.69, "elapsed_time": "0:41:00", "remaining_time": "6:21:55", "throughput": 1511.55, "total_tokens": 3718528} {"current_steps": 17630, "total_steps": 181800, "loss": 0.1321, "lr": 4.848459845984599e-05, "epoch": 1.9394939493949395, "percentage": 9.7, "elapsed_time": "0:41:00", "remaining_time": "6:21:54", "throughput": 1511.55, "total_tokens": 3719552} {"current_steps": 17635, "total_steps": 181800, "loss": 0.2151, "lr": 4.84983498349835e-05, "epoch": 1.94004400440044, "percentage": 9.7, "elapsed_time": "0:41:01", "remaining_time": "6:21:53", "throughput": 1511.57, "total_tokens": 3720640} {"current_steps": 17640, "total_steps": 181800, "loss": 0.069, "lr": 4.851210121012101e-05, "epoch": 1.9405940594059405, "percentage": 9.7, "elapsed_time": "0:41:02", "remaining_time": "6:21:52", "throughput": 1511.6, "total_tokens": 3721760} {"current_steps": 17645, "total_steps": 181800, "loss": 0.0468, "lr": 4.852585258525853e-05, "epoch": 1.9411441144114412, "percentage": 9.71, "elapsed_time": "0:41:02", "remaining_time": "6:21:52", "throughput": 1511.59, "total_tokens": 3722784} {"current_steps": 17650, "total_steps": 181800, "loss": 0.0337, "lr": 4.853960396039604e-05, "epoch": 1.9416941694169418, "percentage": 9.71, "elapsed_time": "0:41:03", "remaining_time": "6:21:51", "throughput": 1511.6, "total_tokens": 3723840} {"current_steps": 17655, "total_steps": 181800, "loss": 0.0825, "lr": 4.8553355335533554e-05, "epoch": 1.9422442244224423, "percentage": 9.71, "elapsed_time": "0:41:04", "remaining_time": "6:21:50", "throughput": 1511.61, "total_tokens": 3724896} {"current_steps": 17660, "total_steps": 181800, "loss": 0.1311, "lr": 4.8567106710671066e-05, "epoch": 1.9427942794279427, "percentage": 9.71, "elapsed_time": "0:41:04", "remaining_time": "6:21:49", "throughput": 1511.65, "total_tokens": 3726048} {"current_steps": 17665, "total_steps": 181800, "loss": 0.2119, "lr": 4.8580858085808584e-05, "epoch": 1.9433443344334433, "percentage": 9.72, "elapsed_time": "0:41:05", "remaining_time": "6:21:48", "throughput": 1511.66, "total_tokens": 3727104} {"current_steps": 17670, "total_steps": 181800, "loss": 0.059, "lr": 4.8594609460946096e-05, "epoch": 1.943894389438944, "percentage": 9.72, "elapsed_time": "0:41:06", "remaining_time": "6:21:48", "throughput": 1511.65, "total_tokens": 3728128} {"current_steps": 17675, "total_steps": 181800, "loss": 0.2099, "lr": 4.860836083608361e-05, "epoch": 1.9444444444444444, "percentage": 9.72, "elapsed_time": "0:41:06", "remaining_time": "6:21:47", "throughput": 1511.66, "total_tokens": 3729184} {"current_steps": 17680, "total_steps": 181800, "loss": 0.08, "lr": 4.8622112211221126e-05, "epoch": 1.9449944994499448, "percentage": 9.72, "elapsed_time": "0:41:07", "remaining_time": "6:21:46", "throughput": 1511.66, "total_tokens": 3730208} {"current_steps": 17685, "total_steps": 181800, "loss": 0.0797, "lr": 4.863586358635864e-05, "epoch": 1.9455445544554455, "percentage": 9.73, "elapsed_time": "0:41:08", "remaining_time": "6:21:45", "throughput": 1511.68, "total_tokens": 3731296} {"current_steps": 17690, "total_steps": 181800, "loss": 0.1519, "lr": 4.8649614961496156e-05, "epoch": 1.9460946094609461, "percentage": 9.73, "elapsed_time": "0:41:09", "remaining_time": "6:21:44", "throughput": 1511.71, "total_tokens": 3732416} {"current_steps": 17695, "total_steps": 181800, "loss": 0.0315, "lr": 4.866336633663367e-05, "epoch": 1.9466446644664468, "percentage": 9.73, "elapsed_time": "0:41:09", "remaining_time": "6:21:44", "throughput": 1511.72, "total_tokens": 3733472} {"current_steps": 17700, "total_steps": 181800, "loss": 0.0988, "lr": 4.867711771177118e-05, "epoch": 1.9471947194719472, "percentage": 9.74, "elapsed_time": "0:41:10", "remaining_time": "6:21:43", "throughput": 1511.74, "total_tokens": 3734560} {"current_steps": 17705, "total_steps": 181800, "loss": 0.0586, "lr": 4.869086908690869e-05, "epoch": 1.9477447744774476, "percentage": 9.74, "elapsed_time": "0:41:11", "remaining_time": "6:21:42", "throughput": 1511.74, "total_tokens": 3735616} {"current_steps": 17710, "total_steps": 181800, "loss": 0.0915, "lr": 4.870462046204621e-05, "epoch": 1.9482948294829483, "percentage": 9.74, "elapsed_time": "0:41:11", "remaining_time": "6:21:41", "throughput": 1511.75, "total_tokens": 3736672} {"current_steps": 17715, "total_steps": 181800, "loss": 0.0955, "lr": 4.871837183718372e-05, "epoch": 1.948844884488449, "percentage": 9.74, "elapsed_time": "0:41:12", "remaining_time": "6:21:40", "throughput": 1511.74, "total_tokens": 3737696} {"current_steps": 17720, "total_steps": 181800, "loss": 0.0839, "lr": 4.873212321232123e-05, "epoch": 1.9493949394939494, "percentage": 9.75, "elapsed_time": "0:41:13", "remaining_time": "6:21:40", "throughput": 1511.72, "total_tokens": 3738688} {"current_steps": 17725, "total_steps": 181800, "loss": 0.0521, "lr": 4.874587458745875e-05, "epoch": 1.9499449944994498, "percentage": 9.75, "elapsed_time": "0:41:13", "remaining_time": "6:21:39", "throughput": 1511.73, "total_tokens": 3739744} {"current_steps": 17730, "total_steps": 181800, "loss": 0.0901, "lr": 4.875962596259626e-05, "epoch": 1.9504950495049505, "percentage": 9.75, "elapsed_time": "0:41:14", "remaining_time": "6:21:38", "throughput": 1511.72, "total_tokens": 3740768} {"current_steps": 17735, "total_steps": 181800, "loss": 0.0264, "lr": 4.8773377337733774e-05, "epoch": 1.951045104510451, "percentage": 9.76, "elapsed_time": "0:41:15", "remaining_time": "6:21:37", "throughput": 1511.73, "total_tokens": 3741824} {"current_steps": 17740, "total_steps": 181800, "loss": 0.1112, "lr": 4.8787128712871286e-05, "epoch": 1.9515951595159517, "percentage": 9.76, "elapsed_time": "0:41:15", "remaining_time": "6:21:37", "throughput": 1511.73, "total_tokens": 3742880} {"current_steps": 17745, "total_steps": 181800, "loss": 0.0362, "lr": 4.8800880088008804e-05, "epoch": 1.9521452145214522, "percentage": 9.76, "elapsed_time": "0:41:16", "remaining_time": "6:21:36", "throughput": 1511.78, "total_tokens": 3744032} {"current_steps": 17750, "total_steps": 181800, "loss": 0.1021, "lr": 4.8814631463146316e-05, "epoch": 1.9526952695269526, "percentage": 9.76, "elapsed_time": "0:41:17", "remaining_time": "6:21:35", "throughput": 1511.8, "total_tokens": 3745120} {"current_steps": 17755, "total_steps": 181800, "loss": 0.0682, "lr": 4.8828382838283835e-05, "epoch": 1.9532453245324533, "percentage": 9.77, "elapsed_time": "0:41:17", "remaining_time": "6:21:34", "throughput": 1511.79, "total_tokens": 3746144} {"current_steps": 17760, "total_steps": 181800, "loss": 0.0575, "lr": 4.884213421342134e-05, "epoch": 1.953795379537954, "percentage": 9.77, "elapsed_time": "0:41:18", "remaining_time": "6:21:33", "throughput": 1511.78, "total_tokens": 3747168} {"current_steps": 17765, "total_steps": 181800, "loss": 0.0575, "lr": 4.885588558855886e-05, "epoch": 1.9543454345434543, "percentage": 9.77, "elapsed_time": "0:41:19", "remaining_time": "6:21:33", "throughput": 1511.78, "total_tokens": 3748192} {"current_steps": 17770, "total_steps": 181800, "loss": 0.1063, "lr": 4.8869636963696376e-05, "epoch": 1.9548954895489548, "percentage": 9.77, "elapsed_time": "0:41:20", "remaining_time": "6:21:32", "throughput": 1511.81, "total_tokens": 3749312} {"current_steps": 17775, "total_steps": 181800, "loss": 0.094, "lr": 4.888338833883389e-05, "epoch": 1.9554455445544554, "percentage": 9.78, "elapsed_time": "0:41:20", "remaining_time": "6:21:31", "throughput": 1511.8, "total_tokens": 3750336} {"current_steps": 17780, "total_steps": 181800, "loss": 0.1145, "lr": 4.88971397139714e-05, "epoch": 1.955995599559956, "percentage": 9.78, "elapsed_time": "0:41:21", "remaining_time": "6:21:30", "throughput": 1511.8, "total_tokens": 3751360} {"current_steps": 17785, "total_steps": 181800, "loss": 0.0943, "lr": 4.891089108910891e-05, "epoch": 1.9565456545654567, "percentage": 9.78, "elapsed_time": "0:41:22", "remaining_time": "6:21:29", "throughput": 1511.82, "total_tokens": 3752448} {"current_steps": 17790, "total_steps": 181800, "loss": 0.0838, "lr": 4.892464246424643e-05, "epoch": 1.9570957095709571, "percentage": 9.79, "elapsed_time": "0:41:22", "remaining_time": "6:21:29", "throughput": 1511.82, "total_tokens": 3753504} {"current_steps": 17795, "total_steps": 181800, "loss": 0.0898, "lr": 4.893839383938394e-05, "epoch": 1.9576457645764576, "percentage": 9.79, "elapsed_time": "0:41:23", "remaining_time": "6:21:28", "throughput": 1511.84, "total_tokens": 3754592} {"current_steps": 17800, "total_steps": 181800, "loss": 0.1046, "lr": 4.895214521452145e-05, "epoch": 1.9581958195819582, "percentage": 9.79, "elapsed_time": "0:41:24", "remaining_time": "6:21:27", "throughput": 1511.86, "total_tokens": 3755680} {"current_steps": 17805, "total_steps": 181800, "loss": 0.1057, "lr": 4.8965896589658965e-05, "epoch": 1.9587458745874589, "percentage": 9.79, "elapsed_time": "0:41:24", "remaining_time": "6:21:26", "throughput": 1511.85, "total_tokens": 3756672} {"current_steps": 17810, "total_steps": 181800, "loss": 0.1527, "lr": 4.897964796479648e-05, "epoch": 1.9592959295929593, "percentage": 9.8, "elapsed_time": "0:41:25", "remaining_time": "6:21:25", "throughput": 1511.84, "total_tokens": 3757696} {"current_steps": 17815, "total_steps": 181800, "loss": 0.074, "lr": 4.8993399339933995e-05, "epoch": 1.9598459845984597, "percentage": 9.8, "elapsed_time": "0:41:26", "remaining_time": "6:21:25", "throughput": 1511.83, "total_tokens": 3758720} {"current_steps": 17820, "total_steps": 181800, "loss": 0.0496, "lr": 4.9007150715071506e-05, "epoch": 1.9603960396039604, "percentage": 9.8, "elapsed_time": "0:41:26", "remaining_time": "6:21:24", "throughput": 1511.85, "total_tokens": 3759808} {"current_steps": 17825, "total_steps": 181800, "loss": 0.1746, "lr": 4.9020902090209025e-05, "epoch": 1.960946094609461, "percentage": 9.8, "elapsed_time": "0:41:27", "remaining_time": "6:21:23", "throughput": 1511.86, "total_tokens": 3760864} {"current_steps": 17830, "total_steps": 181800, "loss": 0.0585, "lr": 4.9034653465346536e-05, "epoch": 1.9614961496149617, "percentage": 9.81, "elapsed_time": "0:41:28", "remaining_time": "6:21:22", "throughput": 1511.84, "total_tokens": 3761856} {"current_steps": 17835, "total_steps": 181800, "loss": 0.1473, "lr": 4.9048404840484055e-05, "epoch": 1.962046204620462, "percentage": 9.81, "elapsed_time": "0:41:28", "remaining_time": "6:21:22", "throughput": 1511.84, "total_tokens": 3762912} {"current_steps": 17840, "total_steps": 181800, "loss": 0.1265, "lr": 4.906215621562156e-05, "epoch": 1.9625962596259625, "percentage": 9.81, "elapsed_time": "0:41:29", "remaining_time": "6:21:21", "throughput": 1511.86, "total_tokens": 3764000} {"current_steps": 17845, "total_steps": 181800, "loss": 0.2273, "lr": 4.907590759075908e-05, "epoch": 1.9631463146314632, "percentage": 9.82, "elapsed_time": "0:41:30", "remaining_time": "6:21:20", "throughput": 1511.85, "total_tokens": 3765024} {"current_steps": 17850, "total_steps": 181800, "loss": 0.0794, "lr": 4.908965896589659e-05, "epoch": 1.9636963696369638, "percentage": 9.82, "elapsed_time": "0:41:31", "remaining_time": "6:21:19", "throughput": 1511.84, "total_tokens": 3766048} {"current_steps": 17855, "total_steps": 181800, "loss": 0.0986, "lr": 4.910341034103411e-05, "epoch": 1.9642464246424642, "percentage": 9.82, "elapsed_time": "0:41:31", "remaining_time": "6:21:19", "throughput": 1511.83, "total_tokens": 3767072} {"current_steps": 17860, "total_steps": 181800, "loss": 0.1494, "lr": 4.911716171617162e-05, "epoch": 1.9647964796479647, "percentage": 9.82, "elapsed_time": "0:41:32", "remaining_time": "6:21:18", "throughput": 1511.85, "total_tokens": 3768160} {"current_steps": 17865, "total_steps": 181800, "loss": 0.1123, "lr": 4.913091309130913e-05, "epoch": 1.9653465346534653, "percentage": 9.83, "elapsed_time": "0:41:33", "remaining_time": "6:21:17", "throughput": 1511.86, "total_tokens": 3769216} {"current_steps": 17870, "total_steps": 181800, "loss": 0.1239, "lr": 4.914466446644665e-05, "epoch": 1.965896589658966, "percentage": 9.83, "elapsed_time": "0:41:33", "remaining_time": "6:21:16", "throughput": 1511.88, "total_tokens": 3770304} {"current_steps": 17875, "total_steps": 181800, "loss": 0.1947, "lr": 4.915841584158416e-05, "epoch": 1.9664466446644664, "percentage": 9.83, "elapsed_time": "0:41:34", "remaining_time": "6:21:15", "throughput": 1511.9, "total_tokens": 3771392} {"current_steps": 17880, "total_steps": 181800, "loss": 0.0784, "lr": 4.917216721672167e-05, "epoch": 1.966996699669967, "percentage": 9.83, "elapsed_time": "0:41:35", "remaining_time": "6:21:15", "throughput": 1511.88, "total_tokens": 3772384} {"current_steps": 17885, "total_steps": 181800, "loss": 0.06, "lr": 4.9185918591859185e-05, "epoch": 1.9675467546754675, "percentage": 9.84, "elapsed_time": "0:41:35", "remaining_time": "6:21:14", "throughput": 1511.89, "total_tokens": 3773472} {"current_steps": 17890, "total_steps": 181800, "loss": 0.0918, "lr": 4.9199669966996703e-05, "epoch": 1.9680968096809681, "percentage": 9.84, "elapsed_time": "0:41:36", "remaining_time": "6:21:13", "throughput": 1511.9, "total_tokens": 3774528} {"current_steps": 17895, "total_steps": 181800, "loss": 0.0524, "lr": 4.9213421342134215e-05, "epoch": 1.9686468646864688, "percentage": 9.84, "elapsed_time": "0:41:37", "remaining_time": "6:21:12", "throughput": 1511.91, "total_tokens": 3775584} {"current_steps": 17900, "total_steps": 181800, "loss": 0.1063, "lr": 4.922717271727173e-05, "epoch": 1.9691969196919692, "percentage": 9.85, "elapsed_time": "0:41:37", "remaining_time": "6:21:11", "throughput": 1511.93, "total_tokens": 3776672} {"current_steps": 17905, "total_steps": 181800, "loss": 0.0689, "lr": 4.924092409240924e-05, "epoch": 1.9697469746974696, "percentage": 9.85, "elapsed_time": "0:41:38", "remaining_time": "6:21:11", "throughput": 1511.92, "total_tokens": 3777696} {"current_steps": 17910, "total_steps": 181800, "loss": 0.0709, "lr": 4.925467546754676e-05, "epoch": 1.9702970297029703, "percentage": 9.85, "elapsed_time": "0:41:39", "remaining_time": "6:21:10", "throughput": 1511.93, "total_tokens": 3778752} {"current_steps": 17915, "total_steps": 181800, "loss": 0.0681, "lr": 4.9268426842684275e-05, "epoch": 1.970847084708471, "percentage": 9.85, "elapsed_time": "0:41:39", "remaining_time": "6:21:09", "throughput": 1511.94, "total_tokens": 3779808} {"current_steps": 17920, "total_steps": 181800, "loss": 0.0457, "lr": 4.928217821782179e-05, "epoch": 1.9713971397139713, "percentage": 9.86, "elapsed_time": "0:41:40", "remaining_time": "6:21:08", "throughput": 1511.93, "total_tokens": 3780832} {"current_steps": 17925, "total_steps": 181800, "loss": 0.0888, "lr": 4.92959295929593e-05, "epoch": 1.971947194719472, "percentage": 9.86, "elapsed_time": "0:41:41", "remaining_time": "6:21:07", "throughput": 1511.93, "total_tokens": 3781856} {"current_steps": 17930, "total_steps": 181800, "loss": 0.1828, "lr": 4.930968096809681e-05, "epoch": 1.9724972497249724, "percentage": 9.86, "elapsed_time": "0:41:42", "remaining_time": "6:21:07", "throughput": 1511.96, "total_tokens": 3782976} {"current_steps": 17935, "total_steps": 181800, "loss": 0.1982, "lr": 4.932343234323433e-05, "epoch": 1.973047304730473, "percentage": 9.87, "elapsed_time": "0:41:42", "remaining_time": "6:21:06", "throughput": 1511.95, "total_tokens": 3784000} {"current_steps": 17940, "total_steps": 181800, "loss": 0.0656, "lr": 4.933718371837184e-05, "epoch": 1.9735973597359737, "percentage": 9.87, "elapsed_time": "0:41:43", "remaining_time": "6:21:05", "throughput": 1511.96, "total_tokens": 3785056} {"current_steps": 17945, "total_steps": 181800, "loss": 0.0822, "lr": 4.935093509350935e-05, "epoch": 1.9741474147414741, "percentage": 9.87, "elapsed_time": "0:41:44", "remaining_time": "6:21:04", "throughput": 1511.95, "total_tokens": 3786080} {"current_steps": 17950, "total_steps": 181800, "loss": 0.1856, "lr": 4.9364686468646864e-05, "epoch": 1.9746974697469746, "percentage": 9.87, "elapsed_time": "0:41:44", "remaining_time": "6:21:04", "throughput": 1511.96, "total_tokens": 3787136} {"current_steps": 17955, "total_steps": 181800, "loss": 0.0259, "lr": 4.937843784378438e-05, "epoch": 1.9752475247524752, "percentage": 9.88, "elapsed_time": "0:41:45", "remaining_time": "6:21:03", "throughput": 1511.97, "total_tokens": 3788224} {"current_steps": 17960, "total_steps": 181800, "loss": 0.0562, "lr": 4.9392189218921894e-05, "epoch": 1.9757975797579759, "percentage": 9.88, "elapsed_time": "0:41:46", "remaining_time": "6:21:02", "throughput": 1512.02, "total_tokens": 3789376} {"current_steps": 17965, "total_steps": 181800, "loss": 0.1526, "lr": 4.9405940594059405e-05, "epoch": 1.9763476347634763, "percentage": 9.88, "elapsed_time": "0:41:46", "remaining_time": "6:21:01", "throughput": 1512.02, "total_tokens": 3790432} {"current_steps": 17970, "total_steps": 181800, "loss": 0.0501, "lr": 4.9419691969196924e-05, "epoch": 1.976897689768977, "percentage": 9.88, "elapsed_time": "0:41:47", "remaining_time": "6:21:00", "throughput": 1512.04, "total_tokens": 3791520} {"current_steps": 17975, "total_steps": 181800, "loss": 0.0279, "lr": 4.9433443344334435e-05, "epoch": 1.9774477447744774, "percentage": 9.89, "elapsed_time": "0:41:48", "remaining_time": "6:21:00", "throughput": 1512.06, "total_tokens": 3792608} {"current_steps": 17980, "total_steps": 181800, "loss": 0.1686, "lr": 4.9447194719471954e-05, "epoch": 1.977997799779978, "percentage": 9.89, "elapsed_time": "0:41:48", "remaining_time": "6:20:59", "throughput": 1512.04, "total_tokens": 3793600} {"current_steps": 17985, "total_steps": 181800, "loss": 0.1036, "lr": 4.946094609460946e-05, "epoch": 1.9785478547854787, "percentage": 9.89, "elapsed_time": "0:41:49", "remaining_time": "6:20:58", "throughput": 1512.03, "total_tokens": 3794592} {"current_steps": 17990, "total_steps": 181800, "loss": 0.1287, "lr": 4.947469746974698e-05, "epoch": 1.979097909790979, "percentage": 9.9, "elapsed_time": "0:41:50", "remaining_time": "6:20:57", "throughput": 1512.01, "total_tokens": 3795584} {"current_steps": 17995, "total_steps": 181800, "loss": 0.0835, "lr": 4.948844884488449e-05, "epoch": 1.9796479647964795, "percentage": 9.9, "elapsed_time": "0:41:50", "remaining_time": "6:20:56", "throughput": 1512.01, "total_tokens": 3796640} {"current_steps": 18000, "total_steps": 181800, "loss": 0.1158, "lr": 4.950220022002201e-05, "epoch": 1.9801980198019802, "percentage": 9.9, "elapsed_time": "0:41:51", "remaining_time": "6:20:56", "throughput": 1512.03, "total_tokens": 3797728} {"current_steps": 18005, "total_steps": 181800, "loss": 0.0624, "lr": 4.951595159515952e-05, "epoch": 1.9807480748074808, "percentage": 9.9, "elapsed_time": "0:41:52", "remaining_time": "6:20:55", "throughput": 1512.04, "total_tokens": 3798784} {"current_steps": 18010, "total_steps": 181800, "loss": 0.0603, "lr": 4.952970297029703e-05, "epoch": 1.9812981298129813, "percentage": 9.91, "elapsed_time": "0:41:53", "remaining_time": "6:20:54", "throughput": 1512.03, "total_tokens": 3799808} {"current_steps": 18015, "total_steps": 181800, "loss": 0.0522, "lr": 4.954345434543455e-05, "epoch": 1.9818481848184817, "percentage": 9.91, "elapsed_time": "0:41:53", "remaining_time": "6:20:53", "throughput": 1512.06, "total_tokens": 3800928} {"current_steps": 18020, "total_steps": 181800, "loss": 0.0355, "lr": 4.955720572057206e-05, "epoch": 1.9823982398239823, "percentage": 9.91, "elapsed_time": "0:41:54", "remaining_time": "6:20:53", "throughput": 1512.08, "total_tokens": 3802016} {"current_steps": 18025, "total_steps": 181800, "loss": 0.015, "lr": 4.957095709570957e-05, "epoch": 1.982948294829483, "percentage": 9.91, "elapsed_time": "0:41:55", "remaining_time": "6:20:52", "throughput": 1512.06, "total_tokens": 3803008} {"current_steps": 18030, "total_steps": 181800, "loss": 0.0917, "lr": 4.9584708470847084e-05, "epoch": 1.9834983498349836, "percentage": 9.92, "elapsed_time": "0:41:55", "remaining_time": "6:20:51", "throughput": 1512.08, "total_tokens": 3804096} {"current_steps": 18035, "total_steps": 181800, "loss": 0.1326, "lr": 4.95984598459846e-05, "epoch": 1.984048404840484, "percentage": 9.92, "elapsed_time": "0:41:56", "remaining_time": "6:20:50", "throughput": 1512.08, "total_tokens": 3805120} {"current_steps": 18040, "total_steps": 181800, "loss": 0.1255, "lr": 4.9612211221122114e-05, "epoch": 1.9845984598459845, "percentage": 9.92, "elapsed_time": "0:41:57", "remaining_time": "6:20:49", "throughput": 1512.08, "total_tokens": 3806176} {"current_steps": 18045, "total_steps": 181800, "loss": 0.0984, "lr": 4.9625962596259626e-05, "epoch": 1.9851485148514851, "percentage": 9.93, "elapsed_time": "0:41:57", "remaining_time": "6:20:49", "throughput": 1512.1, "total_tokens": 3807264} {"current_steps": 18050, "total_steps": 181800, "loss": 0.0992, "lr": 4.9639713971397144e-05, "epoch": 1.9856985698569858, "percentage": 9.93, "elapsed_time": "0:41:58", "remaining_time": "6:20:48", "throughput": 1512.11, "total_tokens": 3808320} {"current_steps": 18055, "total_steps": 181800, "loss": 0.07, "lr": 4.9653465346534656e-05, "epoch": 1.9862486248624862, "percentage": 9.93, "elapsed_time": "0:41:59", "remaining_time": "6:20:47", "throughput": 1512.13, "total_tokens": 3809408} {"current_steps": 18060, "total_steps": 181800, "loss": 0.1033, "lr": 4.9667216721672174e-05, "epoch": 1.9867986798679866, "percentage": 9.93, "elapsed_time": "0:41:59", "remaining_time": "6:20:46", "throughput": 1512.16, "total_tokens": 3810528} {"current_steps": 18065, "total_steps": 181800, "loss": 0.1465, "lr": 4.968096809680968e-05, "epoch": 1.9873487348734873, "percentage": 9.94, "elapsed_time": "0:42:00", "remaining_time": "6:20:46", "throughput": 1512.16, "total_tokens": 3811584} {"current_steps": 18070, "total_steps": 181800, "loss": 0.0334, "lr": 4.96947194719472e-05, "epoch": 1.987898789878988, "percentage": 9.94, "elapsed_time": "0:42:01", "remaining_time": "6:20:45", "throughput": 1512.19, "total_tokens": 3812704} {"current_steps": 18075, "total_steps": 181800, "loss": 0.1226, "lr": 4.970847084708471e-05, "epoch": 1.9884488448844886, "percentage": 9.94, "elapsed_time": "0:42:01", "remaining_time": "6:20:44", "throughput": 1512.2, "total_tokens": 3813760} {"current_steps": 18080, "total_steps": 181800, "loss": 0.0446, "lr": 4.972222222222223e-05, "epoch": 1.988998899889989, "percentage": 9.94, "elapsed_time": "0:42:02", "remaining_time": "6:20:43", "throughput": 1512.19, "total_tokens": 3814784} {"current_steps": 18085, "total_steps": 181800, "loss": 0.1042, "lr": 4.973597359735974e-05, "epoch": 1.9895489548954894, "percentage": 9.95, "elapsed_time": "0:42:03", "remaining_time": "6:20:42", "throughput": 1512.21, "total_tokens": 3815872} {"current_steps": 18090, "total_steps": 181800, "loss": 0.1725, "lr": 4.974972497249725e-05, "epoch": 1.99009900990099, "percentage": 9.95, "elapsed_time": "0:42:04", "remaining_time": "6:20:42", "throughput": 1512.24, "total_tokens": 3816992} {"current_steps": 18095, "total_steps": 181800, "loss": 0.056, "lr": 4.976347634763476e-05, "epoch": 1.9906490649064907, "percentage": 9.95, "elapsed_time": "0:42:04", "remaining_time": "6:20:41", "throughput": 1512.26, "total_tokens": 3818080} {"current_steps": 18100, "total_steps": 181800, "loss": 0.1797, "lr": 4.977722772277228e-05, "epoch": 1.9911991199119912, "percentage": 9.96, "elapsed_time": "0:42:05", "remaining_time": "6:20:40", "throughput": 1512.26, "total_tokens": 3819136} {"current_steps": 18105, "total_steps": 181800, "loss": 0.0951, "lr": 4.979097909790979e-05, "epoch": 1.9917491749174916, "percentage": 9.96, "elapsed_time": "0:42:06", "remaining_time": "6:20:39", "throughput": 1512.24, "total_tokens": 3820128} {"current_steps": 18110, "total_steps": 181800, "loss": 0.0437, "lr": 4.9804730473047304e-05, "epoch": 1.9922992299229922, "percentage": 9.96, "elapsed_time": "0:42:06", "remaining_time": "6:20:39", "throughput": 1512.23, "total_tokens": 3821152} {"current_steps": 18115, "total_steps": 181800, "loss": 0.1119, "lr": 4.981848184818482e-05, "epoch": 1.992849284928493, "percentage": 9.96, "elapsed_time": "0:42:07", "remaining_time": "6:20:38", "throughput": 1512.22, "total_tokens": 3822176} {"current_steps": 18120, "total_steps": 181800, "loss": 0.0682, "lr": 4.9832233223322334e-05, "epoch": 1.9933993399339935, "percentage": 9.97, "elapsed_time": "0:42:08", "remaining_time": "6:20:37", "throughput": 1512.23, "total_tokens": 3823232} {"current_steps": 18125, "total_steps": 181800, "loss": 0.0335, "lr": 4.9845984598459846e-05, "epoch": 1.993949394939494, "percentage": 9.97, "elapsed_time": "0:42:08", "remaining_time": "6:20:36", "throughput": 1512.24, "total_tokens": 3824288} {"current_steps": 18130, "total_steps": 181800, "loss": 0.0458, "lr": 4.985973597359736e-05, "epoch": 1.9944994499449944, "percentage": 9.97, "elapsed_time": "0:42:09", "remaining_time": "6:20:35", "throughput": 1512.22, "total_tokens": 3825280} {"current_steps": 18135, "total_steps": 181800, "loss": 0.1288, "lr": 4.9873487348734876e-05, "epoch": 1.995049504950495, "percentage": 9.98, "elapsed_time": "0:42:10", "remaining_time": "6:20:35", "throughput": 1512.23, "total_tokens": 3826336} {"current_steps": 18140, "total_steps": 181800, "loss": 0.057, "lr": 4.988723872387239e-05, "epoch": 1.9955995599559957, "percentage": 9.98, "elapsed_time": "0:42:10", "remaining_time": "6:20:34", "throughput": 1512.22, "total_tokens": 3827360} {"current_steps": 18145, "total_steps": 181800, "loss": 0.1402, "lr": 4.9900990099009906e-05, "epoch": 1.9961496149614961, "percentage": 9.98, "elapsed_time": "0:42:11", "remaining_time": "6:20:33", "throughput": 1512.24, "total_tokens": 3828448} {"current_steps": 18150, "total_steps": 181800, "loss": 0.1363, "lr": 4.991474147414742e-05, "epoch": 1.9966996699669965, "percentage": 9.98, "elapsed_time": "0:42:12", "remaining_time": "6:20:32", "throughput": 1512.26, "total_tokens": 3829536} {"current_steps": 18155, "total_steps": 181800, "loss": 0.0527, "lr": 4.992849284928493e-05, "epoch": 1.9972497249724972, "percentage": 9.99, "elapsed_time": "0:42:13", "remaining_time": "6:20:32", "throughput": 1512.25, "total_tokens": 3830560} {"current_steps": 18160, "total_steps": 181800, "loss": 0.0365, "lr": 4.994224422442245e-05, "epoch": 1.9977997799779978, "percentage": 9.99, "elapsed_time": "0:42:13", "remaining_time": "6:20:31", "throughput": 1512.26, "total_tokens": 3831616} {"current_steps": 18165, "total_steps": 181800, "loss": 0.1002, "lr": 4.995599559955996e-05, "epoch": 1.9983498349834985, "percentage": 9.99, "elapsed_time": "0:42:14", "remaining_time": "6:20:30", "throughput": 1512.26, "total_tokens": 3832672} {"current_steps": 18170, "total_steps": 181800, "loss": 0.1342, "lr": 4.996974697469747e-05, "epoch": 1.998899889988999, "percentage": 9.99, "elapsed_time": "0:42:15", "remaining_time": "6:20:29", "throughput": 1512.29, "total_tokens": 3833792} {"current_steps": 18175, "total_steps": 181800, "loss": 0.1057, "lr": 4.998349834983498e-05, "epoch": 1.9994499449944994, "percentage": 10.0, "elapsed_time": "0:42:15", "remaining_time": "6:20:29", "throughput": 1512.32, "total_tokens": 3834912} {"current_steps": 18180, "total_steps": 181800, "loss": 0.0784, "lr": 4.99972497249725e-05, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:42:16", "remaining_time": "6:20:28", "throughput": 1512.25, "total_tokens": 3835840} {"current_steps": 18180, "total_steps": 181800, "eval_loss": 0.09340229630470276, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:42:53", "remaining_time": "6:26:01", "throughput": 1490.51, "total_tokens": 3835840} {"current_steps": 18185, "total_steps": 181800, "loss": 0.0653, "lr": 4.999999992626784e-05, "epoch": 2.0005500550055006, "percentage": 10.0, "elapsed_time": "0:42:55", "remaining_time": "6:26:09", "throughput": 1489.94, "total_tokens": 3836896} {"current_steps": 18190, "total_steps": 181800, "loss": 0.0641, "lr": 4.999999962673094e-05, "epoch": 2.0011001100110013, "percentage": 10.01, "elapsed_time": "0:42:55", "remaining_time": "6:26:08", "throughput": 1489.97, "total_tokens": 3837984} {"current_steps": 18195, "total_steps": 181800, "loss": 0.0502, "lr": 4.9999999096781035e-05, "epoch": 2.0016501650165015, "percentage": 10.01, "elapsed_time": "0:42:56", "remaining_time": "6:26:07", "throughput": 1489.99, "total_tokens": 3839072} {"current_steps": 18200, "total_steps": 181800, "loss": 0.0714, "lr": 4.999999833641813e-05, "epoch": 2.002200220022002, "percentage": 10.01, "elapsed_time": "0:42:57", "remaining_time": "6:26:07", "throughput": 1489.99, "total_tokens": 3840096} {"current_steps": 18205, "total_steps": 181800, "loss": 0.1867, "lr": 4.9999997345642244e-05, "epoch": 2.002750275027503, "percentage": 10.01, "elapsed_time": "0:42:57", "remaining_time": "6:26:06", "throughput": 1489.96, "total_tokens": 3841056} {"current_steps": 18210, "total_steps": 181800, "loss": 0.0723, "lr": 4.999999612445338e-05, "epoch": 2.0033003300330035, "percentage": 10.02, "elapsed_time": "0:42:58", "remaining_time": "6:26:05", "throughput": 1489.98, "total_tokens": 3842144} {"current_steps": 18215, "total_steps": 181800, "loss": 0.1006, "lr": 4.999999467285154e-05, "epoch": 2.0038503850385037, "percentage": 10.02, "elapsed_time": "0:42:59", "remaining_time": "6:26:04", "throughput": 1489.99, "total_tokens": 3843200} {"current_steps": 18220, "total_steps": 181800, "loss": 0.0916, "lr": 4.999999299083675e-05, "epoch": 2.0044004400440043, "percentage": 10.02, "elapsed_time": "0:43:00", "remaining_time": "6:26:03", "throughput": 1490.0, "total_tokens": 3844256} {"current_steps": 18225, "total_steps": 181800, "loss": 0.1277, "lr": 4.999999107840901e-05, "epoch": 2.004950495049505, "percentage": 10.02, "elapsed_time": "0:43:00", "remaining_time": "6:26:02", "throughput": 1490.02, "total_tokens": 3845344} {"current_steps": 18230, "total_steps": 181800, "loss": 0.1434, "lr": 4.9999988935568364e-05, "epoch": 2.0055005500550056, "percentage": 10.03, "elapsed_time": "0:43:01", "remaining_time": "6:26:02", "throughput": 1490.01, "total_tokens": 3846336} {"current_steps": 18235, "total_steps": 181800, "loss": 0.1306, "lr": 4.999998656231481e-05, "epoch": 2.0060506050605063, "percentage": 10.03, "elapsed_time": "0:43:02", "remaining_time": "6:26:01", "throughput": 1490.01, "total_tokens": 3847392} {"current_steps": 18240, "total_steps": 181800, "loss": 0.0953, "lr": 4.999998395864838e-05, "epoch": 2.0066006600660065, "percentage": 10.03, "elapsed_time": "0:43:02", "remaining_time": "6:26:00", "throughput": 1490.04, "total_tokens": 3848480} {"current_steps": 18245, "total_steps": 181800, "loss": 0.0398, "lr": 4.999998112456909e-05, "epoch": 2.007150715071507, "percentage": 10.04, "elapsed_time": "0:43:03", "remaining_time": "6:25:59", "throughput": 1490.05, "total_tokens": 3849536} {"current_steps": 18250, "total_steps": 181800, "loss": 0.1151, "lr": 4.9999978060076966e-05, "epoch": 2.0077007700770078, "percentage": 10.04, "elapsed_time": "0:43:04", "remaining_time": "6:25:58", "throughput": 1490.04, "total_tokens": 3850560} {"current_steps": 18255, "total_steps": 181800, "loss": 0.022, "lr": 4.999997476517205e-05, "epoch": 2.0082508250825084, "percentage": 10.04, "elapsed_time": "0:43:04", "remaining_time": "6:25:57", "throughput": 1490.08, "total_tokens": 3851680} {"current_steps": 18260, "total_steps": 181800, "loss": 0.0507, "lr": 4.999997123985436e-05, "epoch": 2.0088008800880086, "percentage": 10.04, "elapsed_time": "0:43:05", "remaining_time": "6:25:56", "throughput": 1490.06, "total_tokens": 3852672} {"current_steps": 18265, "total_steps": 181800, "loss": 0.0665, "lr": 4.999996748412392e-05, "epoch": 2.0093509350935093, "percentage": 10.05, "elapsed_time": "0:43:06", "remaining_time": "6:25:56", "throughput": 1490.11, "total_tokens": 3853824} {"current_steps": 18270, "total_steps": 181800, "loss": 0.1209, "lr": 4.999996349798079e-05, "epoch": 2.00990099009901, "percentage": 10.05, "elapsed_time": "0:43:06", "remaining_time": "6:25:55", "throughput": 1490.11, "total_tokens": 3854848} {"current_steps": 18275, "total_steps": 181800, "loss": 0.0533, "lr": 4.999995928142499e-05, "epoch": 2.0104510451045106, "percentage": 10.05, "elapsed_time": "0:43:07", "remaining_time": "6:25:54", "throughput": 1490.12, "total_tokens": 3855904} {"current_steps": 18280, "total_steps": 181800, "loss": 0.0955, "lr": 4.999995483445655e-05, "epoch": 2.011001100110011, "percentage": 10.06, "elapsed_time": "0:43:08", "remaining_time": "6:25:53", "throughput": 1490.11, "total_tokens": 3856928} {"current_steps": 18285, "total_steps": 181800, "loss": 0.0647, "lr": 4.999995015707554e-05, "epoch": 2.0115511551155114, "percentage": 10.06, "elapsed_time": "0:43:09", "remaining_time": "6:25:52", "throughput": 1490.11, "total_tokens": 3857952} {"current_steps": 18290, "total_steps": 181800, "loss": 0.0404, "lr": 4.999994524928198e-05, "epoch": 2.012101210121012, "percentage": 10.06, "elapsed_time": "0:43:09", "remaining_time": "6:25:51", "throughput": 1490.14, "total_tokens": 3859072} {"current_steps": 18295, "total_steps": 181800, "loss": 0.0852, "lr": 4.999994011107591e-05, "epoch": 2.0126512651265127, "percentage": 10.06, "elapsed_time": "0:43:10", "remaining_time": "6:25:51", "throughput": 1490.16, "total_tokens": 3860160} {"current_steps": 18300, "total_steps": 181800, "loss": 0.0854, "lr": 4.99999347424574e-05, "epoch": 2.0132013201320134, "percentage": 10.07, "elapsed_time": "0:43:11", "remaining_time": "6:25:50", "throughput": 1490.17, "total_tokens": 3861216} {"current_steps": 18305, "total_steps": 181800, "loss": 0.0576, "lr": 4.9999929143426484e-05, "epoch": 2.0137513751375136, "percentage": 10.07, "elapsed_time": "0:43:11", "remaining_time": "6:25:49", "throughput": 1490.17, "total_tokens": 3862272} {"current_steps": 18310, "total_steps": 181800, "loss": 0.0867, "lr": 4.999992331398321e-05, "epoch": 2.014301430143014, "percentage": 10.07, "elapsed_time": "0:43:12", "remaining_time": "6:25:48", "throughput": 1490.19, "total_tokens": 3863360} {"current_steps": 18315, "total_steps": 181800, "loss": 0.0762, "lr": 4.999991725412765e-05, "epoch": 2.014851485148515, "percentage": 10.07, "elapsed_time": "0:43:13", "remaining_time": "6:25:48", "throughput": 1490.17, "total_tokens": 3864416} {"current_steps": 18320, "total_steps": 181800, "loss": 0.1531, "lr": 4.999991096385984e-05, "epoch": 2.0154015401540155, "percentage": 10.08, "elapsed_time": "0:43:14", "remaining_time": "6:25:48", "throughput": 1490.11, "total_tokens": 3865440} {"current_steps": 18325, "total_steps": 181800, "loss": 0.1021, "lr": 4.9999904443179855e-05, "epoch": 2.015951595159516, "percentage": 10.08, "elapsed_time": "0:43:14", "remaining_time": "6:25:47", "throughput": 1490.11, "total_tokens": 3866496} {"current_steps": 18330, "total_steps": 181800, "loss": 0.0643, "lr": 4.999989769208774e-05, "epoch": 2.0165016501650164, "percentage": 10.08, "elapsed_time": "0:43:15", "remaining_time": "6:25:46", "throughput": 1490.11, "total_tokens": 3867520} {"current_steps": 18335, "total_steps": 181800, "loss": 0.0579, "lr": 4.999989071058357e-05, "epoch": 2.017051705170517, "percentage": 10.09, "elapsed_time": "0:43:16", "remaining_time": "6:25:46", "throughput": 1490.11, "total_tokens": 3868576} {"current_steps": 18340, "total_steps": 181800, "loss": 0.095, "lr": 4.99998834986674e-05, "epoch": 2.0176017601760177, "percentage": 10.09, "elapsed_time": "0:43:16", "remaining_time": "6:25:45", "throughput": 1490.12, "total_tokens": 3869632} {"current_steps": 18345, "total_steps": 181800, "loss": 0.1284, "lr": 4.99998760563393e-05, "epoch": 2.0181518151815183, "percentage": 10.09, "elapsed_time": "0:43:17", "remaining_time": "6:25:44", "throughput": 1490.09, "total_tokens": 3870592} {"current_steps": 18350, "total_steps": 181800, "loss": 0.0602, "lr": 4.9999868383599336e-05, "epoch": 2.0187018701870185, "percentage": 10.09, "elapsed_time": "0:43:18", "remaining_time": "6:25:43", "throughput": 1490.11, "total_tokens": 3871680} {"current_steps": 18355, "total_steps": 181800, "loss": 0.0326, "lr": 4.9999860480447583e-05, "epoch": 2.019251925192519, "percentage": 10.1, "elapsed_time": "0:43:18", "remaining_time": "6:25:42", "throughput": 1490.11, "total_tokens": 3872704} {"current_steps": 18360, "total_steps": 181800, "loss": 0.1313, "lr": 4.999985234688411e-05, "epoch": 2.01980198019802, "percentage": 10.1, "elapsed_time": "0:43:19", "remaining_time": "6:25:41", "throughput": 1490.11, "total_tokens": 3873728} {"current_steps": 18365, "total_steps": 181800, "loss": 0.0945, "lr": 4.9999843982909e-05, "epoch": 2.0203520352035205, "percentage": 10.1, "elapsed_time": "0:43:20", "remaining_time": "6:25:40", "throughput": 1490.11, "total_tokens": 3874752} {"current_steps": 18370, "total_steps": 181800, "loss": 0.0448, "lr": 4.999983538852232e-05, "epoch": 2.020902090209021, "percentage": 10.1, "elapsed_time": "0:43:21", "remaining_time": "6:25:40", "throughput": 1490.12, "total_tokens": 3875808} {"current_steps": 18375, "total_steps": 181800, "loss": 0.0413, "lr": 4.999982656372416e-05, "epoch": 2.0214521452145213, "percentage": 10.11, "elapsed_time": "0:43:21", "remaining_time": "6:25:39", "throughput": 1490.13, "total_tokens": 3876864} {"current_steps": 18380, "total_steps": 181800, "loss": 0.048, "lr": 4.999981750851459e-05, "epoch": 2.022002200220022, "percentage": 10.11, "elapsed_time": "0:43:22", "remaining_time": "6:25:38", "throughput": 1490.14, "total_tokens": 3877920} {"current_steps": 18385, "total_steps": 181800, "loss": 0.0331, "lr": 4.9999808222893695e-05, "epoch": 2.0225522552255226, "percentage": 10.11, "elapsed_time": "0:43:23", "remaining_time": "6:25:37", "throughput": 1490.13, "total_tokens": 3878912} {"current_steps": 18390, "total_steps": 181800, "loss": 0.0559, "lr": 4.999979870686157e-05, "epoch": 2.0231023102310233, "percentage": 10.12, "elapsed_time": "0:43:23", "remaining_time": "6:25:36", "throughput": 1490.14, "total_tokens": 3879968} {"current_steps": 18395, "total_steps": 181800, "loss": 0.0365, "lr": 4.9999788960418284e-05, "epoch": 2.0236523652365235, "percentage": 10.12, "elapsed_time": "0:43:24", "remaining_time": "6:25:35", "throughput": 1490.15, "total_tokens": 3881024} {"current_steps": 18400, "total_steps": 181800, "loss": 0.1271, "lr": 4.999977898356395e-05, "epoch": 2.024202420242024, "percentage": 10.12, "elapsed_time": "0:43:25", "remaining_time": "6:25:34", "throughput": 1490.19, "total_tokens": 3882144} {"current_steps": 18405, "total_steps": 181800, "loss": 0.0931, "lr": 4.999976877629865e-05, "epoch": 2.0247524752475248, "percentage": 10.12, "elapsed_time": "0:43:25", "remaining_time": "6:25:33", "throughput": 1490.21, "total_tokens": 3883232} {"current_steps": 18410, "total_steps": 181800, "loss": 0.1083, "lr": 4.999975833862247e-05, "epoch": 2.0253025302530254, "percentage": 10.13, "elapsed_time": "0:43:26", "remaining_time": "6:25:33", "throughput": 1490.21, "total_tokens": 3884256} {"current_steps": 18415, "total_steps": 181800, "loss": 0.1175, "lr": 4.999974767053552e-05, "epoch": 2.0258525852585256, "percentage": 10.13, "elapsed_time": "0:43:27", "remaining_time": "6:25:32", "throughput": 1490.22, "total_tokens": 3885312} {"current_steps": 18420, "total_steps": 181800, "loss": 0.0245, "lr": 4.9999736772037884e-05, "epoch": 2.0264026402640263, "percentage": 10.13, "elapsed_time": "0:43:27", "remaining_time": "6:25:31", "throughput": 1490.23, "total_tokens": 3886368} {"current_steps": 18425, "total_steps": 181800, "loss": 0.1017, "lr": 4.999972564312968e-05, "epoch": 2.026952695269527, "percentage": 10.13, "elapsed_time": "0:43:28", "remaining_time": "6:25:30", "throughput": 1490.27, "total_tokens": 3887488} {"current_steps": 18430, "total_steps": 181800, "loss": 0.0914, "lr": 4.999971428381099e-05, "epoch": 2.0275027502750276, "percentage": 10.14, "elapsed_time": "0:43:29", "remaining_time": "6:25:29", "throughput": 1490.28, "total_tokens": 3888544} {"current_steps": 18435, "total_steps": 181800, "loss": 0.0163, "lr": 4.999970269408194e-05, "epoch": 2.0280528052805282, "percentage": 10.14, "elapsed_time": "0:43:29", "remaining_time": "6:25:28", "throughput": 1490.3, "total_tokens": 3889632} {"current_steps": 18440, "total_steps": 181800, "loss": 0.1672, "lr": 4.999969087394262e-05, "epoch": 2.0286028602860284, "percentage": 10.14, "elapsed_time": "0:43:30", "remaining_time": "6:25:27", "throughput": 1490.28, "total_tokens": 3890624} {"current_steps": 18445, "total_steps": 181800, "loss": 0.0571, "lr": 4.999967882339315e-05, "epoch": 2.029152915291529, "percentage": 10.15, "elapsed_time": "0:43:31", "remaining_time": "6:25:26", "throughput": 1490.32, "total_tokens": 3891744} {"current_steps": 18450, "total_steps": 181800, "loss": 0.0411, "lr": 4.9999666542433633e-05, "epoch": 2.0297029702970297, "percentage": 10.15, "elapsed_time": "0:43:32", "remaining_time": "6:25:26", "throughput": 1490.35, "total_tokens": 3892864} {"current_steps": 18455, "total_steps": 181800, "loss": 0.0731, "lr": 4.9999654031064184e-05, "epoch": 2.0302530253025304, "percentage": 10.15, "elapsed_time": "0:43:32", "remaining_time": "6:25:25", "throughput": 1490.37, "total_tokens": 3893920} {"current_steps": 18460, "total_steps": 181800, "loss": 0.0834, "lr": 4.999964128928493e-05, "epoch": 2.0308030803080306, "percentage": 10.15, "elapsed_time": "0:43:33", "remaining_time": "6:25:24", "throughput": 1490.39, "total_tokens": 3895008} {"current_steps": 18465, "total_steps": 181800, "loss": 0.0933, "lr": 4.9999628317095964e-05, "epoch": 2.0313531353135312, "percentage": 10.16, "elapsed_time": "0:43:34", "remaining_time": "6:25:23", "throughput": 1490.4, "total_tokens": 3896064} {"current_steps": 18470, "total_steps": 181800, "loss": 0.0282, "lr": 4.9999615114497424e-05, "epoch": 2.031903190319032, "percentage": 10.16, "elapsed_time": "0:43:34", "remaining_time": "6:25:22", "throughput": 1490.41, "total_tokens": 3897120} {"current_steps": 18475, "total_steps": 181800, "loss": 0.0817, "lr": 4.9999601681489435e-05, "epoch": 2.0324532453245325, "percentage": 10.16, "elapsed_time": "0:43:35", "remaining_time": "6:25:21", "throughput": 1490.4, "total_tokens": 3898112} {"current_steps": 18480, "total_steps": 181800, "loss": 0.1729, "lr": 4.999958801807211e-05, "epoch": 2.033003300330033, "percentage": 10.17, "elapsed_time": "0:43:36", "remaining_time": "6:25:20", "throughput": 1490.39, "total_tokens": 3899136} {"current_steps": 18485, "total_steps": 181800, "loss": 0.0844, "lr": 4.9999574124245575e-05, "epoch": 2.0335533553355334, "percentage": 10.17, "elapsed_time": "0:43:36", "remaining_time": "6:25:20", "throughput": 1490.38, "total_tokens": 3900128} {"current_steps": 18490, "total_steps": 181800, "loss": 0.0604, "lr": 4.999956000000996e-05, "epoch": 2.034103410341034, "percentage": 10.17, "elapsed_time": "0:43:37", "remaining_time": "6:25:19", "throughput": 1490.38, "total_tokens": 3901152} {"current_steps": 18495, "total_steps": 181800, "loss": 0.138, "lr": 4.99995456453654e-05, "epoch": 2.0346534653465347, "percentage": 10.17, "elapsed_time": "0:43:38", "remaining_time": "6:25:18", "throughput": 1490.4, "total_tokens": 3902240} {"current_steps": 18500, "total_steps": 181800, "loss": 0.1289, "lr": 4.999953106031202e-05, "epoch": 2.0352035203520353, "percentage": 10.18, "elapsed_time": "0:43:38", "remaining_time": "6:25:17", "throughput": 1490.42, "total_tokens": 3903328} {"current_steps": 18505, "total_steps": 181800, "loss": 0.0809, "lr": 4.9999516244849956e-05, "epoch": 2.0357535753575355, "percentage": 10.18, "elapsed_time": "0:43:39", "remaining_time": "6:25:16", "throughput": 1490.42, "total_tokens": 3904352} {"current_steps": 18510, "total_steps": 181800, "loss": 0.0658, "lr": 4.999950119897935e-05, "epoch": 2.036303630363036, "percentage": 10.18, "elapsed_time": "0:43:40", "remaining_time": "6:25:15", "throughput": 1490.43, "total_tokens": 3905408} {"current_steps": 18515, "total_steps": 181800, "loss": 0.1679, "lr": 4.999948592270034e-05, "epoch": 2.036853685368537, "percentage": 10.18, "elapsed_time": "0:43:41", "remaining_time": "6:25:14", "throughput": 1490.44, "total_tokens": 3906464} {"current_steps": 18520, "total_steps": 181800, "loss": 0.0485, "lr": 4.999947041601306e-05, "epoch": 2.0374037403740375, "percentage": 10.19, "elapsed_time": "0:43:41", "remaining_time": "6:25:13", "throughput": 1490.48, "total_tokens": 3907584} {"current_steps": 18525, "total_steps": 181800, "loss": 0.0758, "lr": 4.9999454678917665e-05, "epoch": 2.037953795379538, "percentage": 10.19, "elapsed_time": "0:43:42", "remaining_time": "6:25:13", "throughput": 1490.5, "total_tokens": 3908672} {"current_steps": 18530, "total_steps": 181800, "loss": 0.0342, "lr": 4.9999438711414284e-05, "epoch": 2.0385038503850383, "percentage": 10.19, "elapsed_time": "0:43:43", "remaining_time": "6:25:12", "throughput": 1490.52, "total_tokens": 3909760} {"current_steps": 18535, "total_steps": 181800, "loss": 0.0853, "lr": 4.999942251350307e-05, "epoch": 2.039053905390539, "percentage": 10.2, "elapsed_time": "0:43:43", "remaining_time": "6:25:11", "throughput": 1490.53, "total_tokens": 3910816} {"current_steps": 18540, "total_steps": 181800, "loss": 0.3095, "lr": 4.999940608518418e-05, "epoch": 2.0396039603960396, "percentage": 10.2, "elapsed_time": "0:43:44", "remaining_time": "6:25:10", "throughput": 1490.53, "total_tokens": 3911840} {"current_steps": 18545, "total_steps": 181800, "loss": 0.1597, "lr": 4.999938942645776e-05, "epoch": 2.0401540154015403, "percentage": 10.2, "elapsed_time": "0:43:45", "remaining_time": "6:25:09", "throughput": 1490.53, "total_tokens": 3912864} {"current_steps": 18550, "total_steps": 181800, "loss": 0.058, "lr": 4.999937253732397e-05, "epoch": 2.0407040704070405, "percentage": 10.2, "elapsed_time": "0:43:45", "remaining_time": "6:25:08", "throughput": 1490.54, "total_tokens": 3913920} {"current_steps": 18555, "total_steps": 181800, "loss": 0.1793, "lr": 4.999935541778295e-05, "epoch": 2.041254125412541, "percentage": 10.21, "elapsed_time": "0:43:46", "remaining_time": "6:25:07", "throughput": 1490.56, "total_tokens": 3915008} {"current_steps": 18560, "total_steps": 181800, "loss": 0.0696, "lr": 4.999933806783487e-05, "epoch": 2.041804180418042, "percentage": 10.21, "elapsed_time": "0:43:47", "remaining_time": "6:25:07", "throughput": 1490.58, "total_tokens": 3916096} {"current_steps": 18565, "total_steps": 181800, "loss": 0.09, "lr": 4.9999320487479884e-05, "epoch": 2.0423542354235424, "percentage": 10.21, "elapsed_time": "0:43:47", "remaining_time": "6:25:06", "throughput": 1490.56, "total_tokens": 3917056} {"current_steps": 18570, "total_steps": 181800, "loss": 0.1294, "lr": 4.999930267671816e-05, "epoch": 2.042904290429043, "percentage": 10.21, "elapsed_time": "0:43:48", "remaining_time": "6:25:05", "throughput": 1490.58, "total_tokens": 3918144} {"current_steps": 18575, "total_steps": 181800, "loss": 0.1667, "lr": 4.999928463554986e-05, "epoch": 2.0434543454345433, "percentage": 10.22, "elapsed_time": "0:43:49", "remaining_time": "6:25:04", "throughput": 1490.6, "total_tokens": 3919232} {"current_steps": 18580, "total_steps": 181800, "loss": 0.1573, "lr": 4.999926636397515e-05, "epoch": 2.044004400440044, "percentage": 10.22, "elapsed_time": "0:43:49", "remaining_time": "6:25:03", "throughput": 1490.6, "total_tokens": 3920256} {"current_steps": 18585, "total_steps": 181800, "loss": 0.0406, "lr": 4.9999247861994194e-05, "epoch": 2.0445544554455446, "percentage": 10.22, "elapsed_time": "0:43:50", "remaining_time": "6:25:02", "throughput": 1490.64, "total_tokens": 3921376} {"current_steps": 18590, "total_steps": 181800, "loss": 0.0892, "lr": 4.999922912960717e-05, "epoch": 2.0451045104510452, "percentage": 10.23, "elapsed_time": "0:43:51", "remaining_time": "6:25:01", "throughput": 1490.65, "total_tokens": 3922432} {"current_steps": 18595, "total_steps": 181800, "loss": 0.063, "lr": 4.9999210166814236e-05, "epoch": 2.0456545654565454, "percentage": 10.23, "elapsed_time": "0:43:52", "remaining_time": "6:25:01", "throughput": 1490.66, "total_tokens": 3923488} {"current_steps": 18600, "total_steps": 181800, "loss": 0.0674, "lr": 4.999919097361559e-05, "epoch": 2.046204620462046, "percentage": 10.23, "elapsed_time": "0:43:52", "remaining_time": "6:25:00", "throughput": 1490.66, "total_tokens": 3924512} {"current_steps": 18605, "total_steps": 181800, "loss": 0.0307, "lr": 4.999917155001139e-05, "epoch": 2.0467546754675467, "percentage": 10.23, "elapsed_time": "0:43:53", "remaining_time": "6:24:59", "throughput": 1490.68, "total_tokens": 3925600} {"current_steps": 18610, "total_steps": 181800, "loss": 0.144, "lr": 4.9999151896001826e-05, "epoch": 2.0473047304730474, "percentage": 10.24, "elapsed_time": "0:43:54", "remaining_time": "6:24:58", "throughput": 1490.7, "total_tokens": 3926656} {"current_steps": 18615, "total_steps": 181800, "loss": 0.099, "lr": 4.999913201158707e-05, "epoch": 2.047854785478548, "percentage": 10.24, "elapsed_time": "0:43:54", "remaining_time": "6:24:57", "throughput": 1490.72, "total_tokens": 3927744} {"current_steps": 18620, "total_steps": 181800, "loss": 0.0487, "lr": 4.999911189676732e-05, "epoch": 2.0484048404840483, "percentage": 10.24, "elapsed_time": "0:43:55", "remaining_time": "6:24:56", "throughput": 1490.71, "total_tokens": 3928736} {"current_steps": 18625, "total_steps": 181800, "loss": 0.0677, "lr": 4.999909155154274e-05, "epoch": 2.048954895489549, "percentage": 10.24, "elapsed_time": "0:43:56", "remaining_time": "6:24:55", "throughput": 1490.71, "total_tokens": 3929760} {"current_steps": 18630, "total_steps": 181800, "loss": 0.0524, "lr": 4.999907097591353e-05, "epoch": 2.0495049504950495, "percentage": 10.25, "elapsed_time": "0:43:56", "remaining_time": "6:24:54", "throughput": 1490.72, "total_tokens": 3930816} {"current_steps": 18635, "total_steps": 181800, "loss": 0.1376, "lr": 4.999905016987989e-05, "epoch": 2.05005500550055, "percentage": 10.25, "elapsed_time": "0:43:57", "remaining_time": "6:24:53", "throughput": 1490.75, "total_tokens": 3931904} {"current_steps": 18640, "total_steps": 181800, "loss": 0.1098, "lr": 4.999902913344199e-05, "epoch": 2.0506050605060504, "percentage": 10.25, "elapsed_time": "0:43:58", "remaining_time": "6:24:52", "throughput": 1490.74, "total_tokens": 3932896} {"current_steps": 18645, "total_steps": 181800, "loss": 0.0655, "lr": 4.999900786660003e-05, "epoch": 2.051155115511551, "percentage": 10.26, "elapsed_time": "0:43:58", "remaining_time": "6:24:52", "throughput": 1490.76, "total_tokens": 3933984} {"current_steps": 18650, "total_steps": 181800, "loss": 0.0535, "lr": 4.9998986369354214e-05, "epoch": 2.0517051705170517, "percentage": 10.26, "elapsed_time": "0:43:59", "remaining_time": "6:24:51", "throughput": 1490.78, "total_tokens": 3935072} {"current_steps": 18655, "total_steps": 181800, "loss": 0.21, "lr": 4.999896464170475e-05, "epoch": 2.0522552255225524, "percentage": 10.26, "elapsed_time": "0:44:00", "remaining_time": "6:24:50", "throughput": 1490.8, "total_tokens": 3936160} {"current_steps": 18660, "total_steps": 181800, "loss": 0.037, "lr": 4.9998942683651806e-05, "epoch": 2.052805280528053, "percentage": 10.26, "elapsed_time": "0:44:00", "remaining_time": "6:24:49", "throughput": 1490.82, "total_tokens": 3937216} {"current_steps": 18665, "total_steps": 181800, "loss": 0.1132, "lr": 4.999892049519561e-05, "epoch": 2.053355335533553, "percentage": 10.27, "elapsed_time": "0:44:01", "remaining_time": "6:24:48", "throughput": 1490.8, "total_tokens": 3938208} {"current_steps": 18670, "total_steps": 181800, "loss": 0.0206, "lr": 4.9998898076336365e-05, "epoch": 2.053905390539054, "percentage": 10.27, "elapsed_time": "0:44:02", "remaining_time": "6:24:47", "throughput": 1490.8, "total_tokens": 3939232} {"current_steps": 18675, "total_steps": 181800, "loss": 0.1663, "lr": 4.999887542707427e-05, "epoch": 2.0544554455445545, "percentage": 10.27, "elapsed_time": "0:44:03", "remaining_time": "6:24:46", "throughput": 1490.81, "total_tokens": 3940288} {"current_steps": 18680, "total_steps": 181800, "loss": 0.0424, "lr": 4.9998852547409525e-05, "epoch": 2.055005500550055, "percentage": 10.28, "elapsed_time": "0:44:03", "remaining_time": "6:24:45", "throughput": 1490.84, "total_tokens": 3941376} {"current_steps": 18685, "total_steps": 181800, "loss": 0.0309, "lr": 4.999882943734237e-05, "epoch": 2.0555555555555554, "percentage": 10.28, "elapsed_time": "0:44:04", "remaining_time": "6:24:45", "throughput": 1490.85, "total_tokens": 3942432} {"current_steps": 18690, "total_steps": 181800, "loss": 0.0985, "lr": 4.999880609687298e-05, "epoch": 2.056105610561056, "percentage": 10.28, "elapsed_time": "0:44:05", "remaining_time": "6:24:44", "throughput": 1490.83, "total_tokens": 3943424} {"current_steps": 18695, "total_steps": 181800, "loss": 0.0331, "lr": 4.9998782526001596e-05, "epoch": 2.0566556655665567, "percentage": 10.28, "elapsed_time": "0:44:05", "remaining_time": "6:24:43", "throughput": 1490.83, "total_tokens": 3944448} {"current_steps": 18700, "total_steps": 181800, "loss": 0.1107, "lr": 4.9998758724728435e-05, "epoch": 2.0572057205720573, "percentage": 10.29, "elapsed_time": "0:44:06", "remaining_time": "6:24:42", "throughput": 1490.84, "total_tokens": 3945504} {"current_steps": 18705, "total_steps": 181800, "loss": 0.1523, "lr": 4.999873469305371e-05, "epoch": 2.057755775577558, "percentage": 10.29, "elapsed_time": "0:44:07", "remaining_time": "6:24:41", "throughput": 1490.89, "total_tokens": 3946656} {"current_steps": 18710, "total_steps": 181800, "loss": 0.1746, "lr": 4.9998710430977635e-05, "epoch": 2.058305830583058, "percentage": 10.29, "elapsed_time": "0:44:07", "remaining_time": "6:24:40", "throughput": 1490.86, "total_tokens": 3947616} {"current_steps": 18715, "total_steps": 181800, "loss": 0.1102, "lr": 4.999868593850045e-05, "epoch": 2.058855885588559, "percentage": 10.29, "elapsed_time": "0:44:08", "remaining_time": "6:24:39", "throughput": 1490.88, "total_tokens": 3948672} {"current_steps": 18720, "total_steps": 181800, "loss": 0.0468, "lr": 4.999866121562237e-05, "epoch": 2.0594059405940595, "percentage": 10.3, "elapsed_time": "0:44:09", "remaining_time": "6:24:38", "throughput": 1490.9, "total_tokens": 3949760} {"current_steps": 18725, "total_steps": 181800, "loss": 0.0351, "lr": 4.9998636262343625e-05, "epoch": 2.05995599559956, "percentage": 10.3, "elapsed_time": "0:44:09", "remaining_time": "6:24:38", "throughput": 1490.89, "total_tokens": 3950752} {"current_steps": 18730, "total_steps": 181800, "loss": 0.0765, "lr": 4.999861107866444e-05, "epoch": 2.0605060506050603, "percentage": 10.3, "elapsed_time": "0:44:10", "remaining_time": "6:24:37", "throughput": 1490.89, "total_tokens": 3951776} {"current_steps": 18735, "total_steps": 181800, "loss": 0.0802, "lr": 4.999858566458506e-05, "epoch": 2.061056105610561, "percentage": 10.31, "elapsed_time": "0:44:11", "remaining_time": "6:24:36", "throughput": 1490.9, "total_tokens": 3952832} {"current_steps": 18740, "total_steps": 181800, "loss": 0.0265, "lr": 4.9998560020105706e-05, "epoch": 2.0616061606160616, "percentage": 10.31, "elapsed_time": "0:44:12", "remaining_time": "6:24:35", "throughput": 1490.92, "total_tokens": 3953920} {"current_steps": 18745, "total_steps": 181800, "loss": 0.1585, "lr": 4.999853414522662e-05, "epoch": 2.0621562156215623, "percentage": 10.31, "elapsed_time": "0:44:12", "remaining_time": "6:24:34", "throughput": 1490.94, "total_tokens": 3955008} {"current_steps": 18750, "total_steps": 181800, "loss": 0.1019, "lr": 4.999850803994805e-05, "epoch": 2.062706270627063, "percentage": 10.31, "elapsed_time": "0:44:13", "remaining_time": "6:24:33", "throughput": 1490.96, "total_tokens": 3956096} {"current_steps": 18755, "total_steps": 181800, "loss": 0.0989, "lr": 4.999848170427021e-05, "epoch": 2.063256325632563, "percentage": 10.32, "elapsed_time": "0:44:14", "remaining_time": "6:24:32", "throughput": 1490.97, "total_tokens": 3957152} {"current_steps": 18760, "total_steps": 181800, "loss": 0.0331, "lr": 4.999845513819337e-05, "epoch": 2.0638063806380638, "percentage": 10.32, "elapsed_time": "0:44:14", "remaining_time": "6:24:32", "throughput": 1490.98, "total_tokens": 3958208} {"current_steps": 18765, "total_steps": 181800, "loss": 0.0442, "lr": 4.9998428341717765e-05, "epoch": 2.0643564356435644, "percentage": 10.32, "elapsed_time": "0:44:15", "remaining_time": "6:24:31", "throughput": 1491.0, "total_tokens": 3959264} {"current_steps": 18770, "total_steps": 181800, "loss": 0.1188, "lr": 4.999840131484363e-05, "epoch": 2.064906490649065, "percentage": 10.32, "elapsed_time": "0:44:16", "remaining_time": "6:24:30", "throughput": 1491.02, "total_tokens": 3960352} {"current_steps": 18775, "total_steps": 181800, "loss": 0.0447, "lr": 4.999837405757124e-05, "epoch": 2.0654565456545653, "percentage": 10.33, "elapsed_time": "0:44:16", "remaining_time": "6:24:29", "throughput": 1491.04, "total_tokens": 3961440} {"current_steps": 18780, "total_steps": 181800, "loss": 0.0578, "lr": 4.999834656990082e-05, "epoch": 2.066006600660066, "percentage": 10.33, "elapsed_time": "0:44:17", "remaining_time": "6:24:28", "throughput": 1491.04, "total_tokens": 3962464} {"current_steps": 18785, "total_steps": 181800, "loss": 0.0308, "lr": 4.999831885183265e-05, "epoch": 2.0665566556655666, "percentage": 10.33, "elapsed_time": "0:44:18", "remaining_time": "6:24:27", "throughput": 1491.06, "total_tokens": 3963552} {"current_steps": 18790, "total_steps": 181800, "loss": 0.0744, "lr": 4.9998290903366965e-05, "epoch": 2.067106710671067, "percentage": 10.34, "elapsed_time": "0:44:18", "remaining_time": "6:24:26", "throughput": 1491.1, "total_tokens": 3964704} {"current_steps": 18795, "total_steps": 181800, "loss": 0.1464, "lr": 4.999826272450402e-05, "epoch": 2.067656765676568, "percentage": 10.34, "elapsed_time": "0:44:19", "remaining_time": "6:24:26", "throughput": 1491.09, "total_tokens": 3965696} {"current_steps": 18800, "total_steps": 181800, "loss": 0.0449, "lr": 4.9998234315244085e-05, "epoch": 2.068206820682068, "percentage": 10.34, "elapsed_time": "0:44:20", "remaining_time": "6:24:25", "throughput": 1491.07, "total_tokens": 3966688} {"current_steps": 18805, "total_steps": 181800, "loss": 0.1071, "lr": 4.999820567558742e-05, "epoch": 2.0687568756875687, "percentage": 10.34, "elapsed_time": "0:44:20", "remaining_time": "6:24:24", "throughput": 1491.07, "total_tokens": 3967712} {"current_steps": 18810, "total_steps": 181800, "loss": 0.0663, "lr": 4.999817680553429e-05, "epoch": 2.0693069306930694, "percentage": 10.35, "elapsed_time": "0:44:21", "remaining_time": "6:24:23", "throughput": 1491.06, "total_tokens": 3968704} {"current_steps": 18815, "total_steps": 181800, "loss": 0.0365, "lr": 4.9998147705084964e-05, "epoch": 2.06985698569857, "percentage": 10.35, "elapsed_time": "0:44:22", "remaining_time": "6:24:22", "throughput": 1491.07, "total_tokens": 3969760} {"current_steps": 18820, "total_steps": 181800, "loss": 0.0683, "lr": 4.99981183742397e-05, "epoch": 2.0704070407040702, "percentage": 10.35, "elapsed_time": "0:44:23", "remaining_time": "6:24:21", "throughput": 1491.08, "total_tokens": 3970816} {"current_steps": 18825, "total_steps": 181800, "loss": 0.0941, "lr": 4.9998088812998776e-05, "epoch": 2.070957095709571, "percentage": 10.35, "elapsed_time": "0:44:23", "remaining_time": "6:24:20", "throughput": 1491.09, "total_tokens": 3971872} {"current_steps": 18830, "total_steps": 181800, "loss": 0.1065, "lr": 4.999805902136246e-05, "epoch": 2.0715071507150715, "percentage": 10.36, "elapsed_time": "0:44:24", "remaining_time": "6:24:20", "throughput": 1491.08, "total_tokens": 3972864} {"current_steps": 18835, "total_steps": 181800, "loss": 0.059, "lr": 4.999802899933104e-05, "epoch": 2.072057205720572, "percentage": 10.36, "elapsed_time": "0:44:25", "remaining_time": "6:24:19", "throughput": 1491.08, "total_tokens": 3973888} {"current_steps": 18840, "total_steps": 181800, "loss": 0.0483, "lr": 4.9997998746904775e-05, "epoch": 2.072607260726073, "percentage": 10.36, "elapsed_time": "0:44:25", "remaining_time": "6:24:18", "throughput": 1491.07, "total_tokens": 3974880} {"current_steps": 18845, "total_steps": 181800, "loss": 0.2231, "lr": 4.999796826408395e-05, "epoch": 2.073157315731573, "percentage": 10.37, "elapsed_time": "0:44:26", "remaining_time": "6:24:17", "throughput": 1491.07, "total_tokens": 3975904} {"current_steps": 18850, "total_steps": 181800, "loss": 0.1012, "lr": 4.9997937550868845e-05, "epoch": 2.0737073707370737, "percentage": 10.37, "elapsed_time": "0:44:27", "remaining_time": "6:24:16", "throughput": 1491.06, "total_tokens": 3976896} {"current_steps": 18855, "total_steps": 181800, "loss": 0.0949, "lr": 4.999790660725975e-05, "epoch": 2.0742574257425743, "percentage": 10.37, "elapsed_time": "0:44:27", "remaining_time": "6:24:15", "throughput": 1491.05, "total_tokens": 3977888} {"current_steps": 18860, "total_steps": 181800, "loss": 0.082, "lr": 4.9997875433256935e-05, "epoch": 2.074807480748075, "percentage": 10.37, "elapsed_time": "0:44:28", "remaining_time": "6:24:14", "throughput": 1491.06, "total_tokens": 3978944} {"current_steps": 18865, "total_steps": 181800, "loss": 0.1554, "lr": 4.999784402886071e-05, "epoch": 2.075357535753575, "percentage": 10.38, "elapsed_time": "0:44:29", "remaining_time": "6:24:13", "throughput": 1491.09, "total_tokens": 3980064} {"current_steps": 18870, "total_steps": 181800, "loss": 0.1084, "lr": 4.999781239407134e-05, "epoch": 2.075907590759076, "percentage": 10.38, "elapsed_time": "0:44:29", "remaining_time": "6:24:12", "throughput": 1491.08, "total_tokens": 3981056} {"current_steps": 18875, "total_steps": 181800, "loss": 0.1242, "lr": 4.999778052888914e-05, "epoch": 2.0764576457645765, "percentage": 10.38, "elapsed_time": "0:44:30", "remaining_time": "6:24:12", "throughput": 1491.08, "total_tokens": 3982080} {"current_steps": 18880, "total_steps": 181800, "loss": 0.0211, "lr": 4.9997748433314384e-05, "epoch": 2.077007700770077, "percentage": 10.39, "elapsed_time": "0:44:31", "remaining_time": "6:24:11", "throughput": 1491.1, "total_tokens": 3983168} {"current_steps": 18885, "total_steps": 181800, "loss": 0.1208, "lr": 4.999771610734737e-05, "epoch": 2.0775577557755778, "percentage": 10.39, "elapsed_time": "0:44:31", "remaining_time": "6:24:10", "throughput": 1491.09, "total_tokens": 3984160} {"current_steps": 18890, "total_steps": 181800, "loss": 0.0294, "lr": 4.999768355098842e-05, "epoch": 2.078107810781078, "percentage": 10.39, "elapsed_time": "0:44:32", "remaining_time": "6:24:09", "throughput": 1491.11, "total_tokens": 3985248} {"current_steps": 18895, "total_steps": 181800, "loss": 0.086, "lr": 4.99976507642378e-05, "epoch": 2.0786578657865786, "percentage": 10.39, "elapsed_time": "0:44:33", "remaining_time": "6:24:08", "throughput": 1491.12, "total_tokens": 3986304} {"current_steps": 18900, "total_steps": 181800, "loss": 0.0429, "lr": 4.999761774709583e-05, "epoch": 2.0792079207920793, "percentage": 10.4, "elapsed_time": "0:44:34", "remaining_time": "6:24:07", "throughput": 1491.13, "total_tokens": 3987360} {"current_steps": 18905, "total_steps": 181800, "loss": 0.067, "lr": 4.9997584499562814e-05, "epoch": 2.07975797579758, "percentage": 10.4, "elapsed_time": "0:44:34", "remaining_time": "6:24:06", "throughput": 1491.12, "total_tokens": 3988352} {"current_steps": 18910, "total_steps": 181800, "loss": 0.0981, "lr": 4.999755102163906e-05, "epoch": 2.08030803080308, "percentage": 10.4, "elapsed_time": "0:44:35", "remaining_time": "6:24:05", "throughput": 1491.13, "total_tokens": 3989408} {"current_steps": 18915, "total_steps": 181800, "loss": 0.0525, "lr": 4.999751731332487e-05, "epoch": 2.080858085808581, "percentage": 10.4, "elapsed_time": "0:44:36", "remaining_time": "6:24:05", "throughput": 1491.15, "total_tokens": 3990464} {"current_steps": 18920, "total_steps": 181800, "loss": 0.0415, "lr": 4.9997483374620565e-05, "epoch": 2.0814081408140814, "percentage": 10.41, "elapsed_time": "0:44:36", "remaining_time": "6:24:04", "throughput": 1491.16, "total_tokens": 3991520} {"current_steps": 18925, "total_steps": 181800, "loss": 0.0656, "lr": 4.9997449205526443e-05, "epoch": 2.081958195819582, "percentage": 10.41, "elapsed_time": "0:44:37", "remaining_time": "6:24:03", "throughput": 1491.17, "total_tokens": 3992576} {"current_steps": 18930, "total_steps": 181800, "loss": 0.0378, "lr": 4.999741480604283e-05, "epoch": 2.0825082508250823, "percentage": 10.41, "elapsed_time": "0:44:38", "remaining_time": "6:24:02", "throughput": 1491.17, "total_tokens": 3993600} {"current_steps": 18935, "total_steps": 181800, "loss": 0.1268, "lr": 4.9997380176170034e-05, "epoch": 2.083058305830583, "percentage": 10.42, "elapsed_time": "0:44:38", "remaining_time": "6:24:01", "throughput": 1491.16, "total_tokens": 3994592} {"current_steps": 18940, "total_steps": 181800, "loss": 0.1917, "lr": 4.9997345315908384e-05, "epoch": 2.0836083608360836, "percentage": 10.42, "elapsed_time": "0:44:39", "remaining_time": "6:24:00", "throughput": 1491.17, "total_tokens": 3995648} {"current_steps": 18945, "total_steps": 181800, "loss": 0.1973, "lr": 4.99973102252582e-05, "epoch": 2.0841584158415842, "percentage": 10.42, "elapsed_time": "0:44:40", "remaining_time": "6:23:59", "throughput": 1491.17, "total_tokens": 3996672} {"current_steps": 18950, "total_steps": 181800, "loss": 0.0939, "lr": 4.999727490421979e-05, "epoch": 2.084708470847085, "percentage": 10.42, "elapsed_time": "0:44:40", "remaining_time": "6:23:58", "throughput": 1491.17, "total_tokens": 3997696} {"current_steps": 18955, "total_steps": 181800, "loss": 0.079, "lr": 4.9997239352793515e-05, "epoch": 2.085258525852585, "percentage": 10.43, "elapsed_time": "0:44:41", "remaining_time": "6:23:58", "throughput": 1491.19, "total_tokens": 3998784} {"current_steps": 18960, "total_steps": 181800, "loss": 0.0668, "lr": 4.9997203570979656e-05, "epoch": 2.0858085808580857, "percentage": 10.43, "elapsed_time": "0:44:42", "remaining_time": "6:23:57", "throughput": 1491.2, "total_tokens": 3999840} {"current_steps": 18965, "total_steps": 181800, "loss": 0.0429, "lr": 4.999716755877858e-05, "epoch": 2.0863586358635864, "percentage": 10.43, "elapsed_time": "0:44:42", "remaining_time": "6:23:56", "throughput": 1491.2, "total_tokens": 4000864} {"current_steps": 18970, "total_steps": 181800, "loss": 0.0896, "lr": 4.9997131316190604e-05, "epoch": 2.086908690869087, "percentage": 10.43, "elapsed_time": "0:44:43", "remaining_time": "6:23:55", "throughput": 1491.22, "total_tokens": 4001952} {"current_steps": 18975, "total_steps": 181800, "loss": 0.1351, "lr": 4.999709484321606e-05, "epoch": 2.0874587458745877, "percentage": 10.44, "elapsed_time": "0:44:44", "remaining_time": "6:23:54", "throughput": 1491.25, "total_tokens": 4003040} {"current_steps": 18980, "total_steps": 181800, "loss": 0.1343, "lr": 4.999705813985529e-05, "epoch": 2.088008800880088, "percentage": 10.44, "elapsed_time": "0:44:45", "remaining_time": "6:23:53", "throughput": 1491.28, "total_tokens": 4004160} {"current_steps": 18985, "total_steps": 181800, "loss": 0.1485, "lr": 4.999702120610863e-05, "epoch": 2.0885588558855885, "percentage": 10.44, "elapsed_time": "0:44:45", "remaining_time": "6:23:52", "throughput": 1491.3, "total_tokens": 4005248} {"current_steps": 18990, "total_steps": 181800, "loss": 0.0935, "lr": 4.999698404197642e-05, "epoch": 2.089108910891089, "percentage": 10.45, "elapsed_time": "0:44:46", "remaining_time": "6:23:52", "throughput": 1491.3, "total_tokens": 4006272} {"current_steps": 18995, "total_steps": 181800, "loss": 0.0557, "lr": 4.9996946647458996e-05, "epoch": 2.08965896589659, "percentage": 10.45, "elapsed_time": "0:44:47", "remaining_time": "6:23:51", "throughput": 1491.3, "total_tokens": 4007296} {"current_steps": 19000, "total_steps": 181800, "loss": 0.0912, "lr": 4.999690902255672e-05, "epoch": 2.09020902090209, "percentage": 10.45, "elapsed_time": "0:44:47", "remaining_time": "6:23:50", "throughput": 1491.3, "total_tokens": 4008320} {"current_steps": 19005, "total_steps": 181800, "loss": 0.0693, "lr": 4.999687116726992e-05, "epoch": 2.0907590759075907, "percentage": 10.45, "elapsed_time": "0:44:48", "remaining_time": "6:23:49", "throughput": 1491.31, "total_tokens": 4009376} {"current_steps": 19010, "total_steps": 181800, "loss": 0.0543, "lr": 4.999683308159896e-05, "epoch": 2.0913091309130913, "percentage": 10.46, "elapsed_time": "0:44:49", "remaining_time": "6:23:48", "throughput": 1491.35, "total_tokens": 4010496} {"current_steps": 19015, "total_steps": 181800, "loss": 0.0687, "lr": 4.999679476554418e-05, "epoch": 2.091859185918592, "percentage": 10.46, "elapsed_time": "0:44:49", "remaining_time": "6:23:47", "throughput": 1491.37, "total_tokens": 4011584} {"current_steps": 19020, "total_steps": 181800, "loss": 0.0884, "lr": 4.999675621910594e-05, "epoch": 2.092409240924092, "percentage": 10.46, "elapsed_time": "0:44:50", "remaining_time": "6:23:46", "throughput": 1491.4, "total_tokens": 4012672} {"current_steps": 19025, "total_steps": 181800, "loss": 0.0342, "lr": 4.999671744228459e-05, "epoch": 2.092959295929593, "percentage": 10.46, "elapsed_time": "0:44:51", "remaining_time": "6:23:45", "throughput": 1491.4, "total_tokens": 4013696} {"current_steps": 19030, "total_steps": 181800, "loss": 0.1097, "lr": 4.999667843508049e-05, "epoch": 2.0935093509350935, "percentage": 10.47, "elapsed_time": "0:44:51", "remaining_time": "6:23:44", "throughput": 1491.41, "total_tokens": 4014752} {"current_steps": 19035, "total_steps": 181800, "loss": 0.1103, "lr": 4.9996639197494e-05, "epoch": 2.094059405940594, "percentage": 10.47, "elapsed_time": "0:44:52", "remaining_time": "6:23:44", "throughput": 1491.44, "total_tokens": 4015872} {"current_steps": 19040, "total_steps": 181800, "loss": 0.0307, "lr": 4.999659972952548e-05, "epoch": 2.094609460946095, "percentage": 10.47, "elapsed_time": "0:44:53", "remaining_time": "6:23:43", "throughput": 1491.45, "total_tokens": 4016928} {"current_steps": 19045, "total_steps": 181800, "loss": 0.0852, "lr": 4.99965600311753e-05, "epoch": 2.095159515951595, "percentage": 10.48, "elapsed_time": "0:44:53", "remaining_time": "6:23:42", "throughput": 1491.46, "total_tokens": 4017984} {"current_steps": 19050, "total_steps": 181800, "loss": 0.157, "lr": 4.999652010244382e-05, "epoch": 2.0957095709570956, "percentage": 10.48, "elapsed_time": "0:44:54", "remaining_time": "6:23:41", "throughput": 1491.47, "total_tokens": 4019040} {"current_steps": 19055, "total_steps": 181800, "loss": 0.0585, "lr": 4.9996479943331395e-05, "epoch": 2.0962596259625963, "percentage": 10.48, "elapsed_time": "0:44:55", "remaining_time": "6:23:40", "throughput": 1491.47, "total_tokens": 4020064} {"current_steps": 19060, "total_steps": 181800, "loss": 0.0462, "lr": 4.999643955383842e-05, "epoch": 2.096809680968097, "percentage": 10.48, "elapsed_time": "0:44:56", "remaining_time": "6:23:39", "throughput": 1491.47, "total_tokens": 4021088} {"current_steps": 19065, "total_steps": 181800, "loss": 0.076, "lr": 4.999639893396526e-05, "epoch": 2.097359735973597, "percentage": 10.49, "elapsed_time": "0:44:56", "remaining_time": "6:23:38", "throughput": 1491.48, "total_tokens": 4022144} {"current_steps": 19070, "total_steps": 181800, "loss": 0.0619, "lr": 4.999635808371228e-05, "epoch": 2.097909790979098, "percentage": 10.49, "elapsed_time": "0:44:57", "remaining_time": "6:23:37", "throughput": 1491.51, "total_tokens": 4023232} {"current_steps": 19075, "total_steps": 181800, "loss": 0.1622, "lr": 4.999631700307986e-05, "epoch": 2.0984598459845984, "percentage": 10.49, "elapsed_time": "0:44:58", "remaining_time": "6:23:37", "throughput": 1491.53, "total_tokens": 4024320} {"current_steps": 19080, "total_steps": 181800, "loss": 0.1085, "lr": 4.999627569206839e-05, "epoch": 2.099009900990099, "percentage": 10.5, "elapsed_time": "0:44:58", "remaining_time": "6:23:36", "throughput": 1491.53, "total_tokens": 4025344} {"current_steps": 19085, "total_steps": 181800, "loss": 0.1236, "lr": 4.999623415067823e-05, "epoch": 2.0995599559955997, "percentage": 10.5, "elapsed_time": "0:44:59", "remaining_time": "6:23:35", "throughput": 1491.52, "total_tokens": 4026336} {"current_steps": 19090, "total_steps": 181800, "loss": 0.1494, "lr": 4.9996192378909786e-05, "epoch": 2.1001100110011, "percentage": 10.5, "elapsed_time": "0:45:00", "remaining_time": "6:23:34", "throughput": 1491.54, "total_tokens": 4027424} {"current_steps": 19095, "total_steps": 181800, "loss": 0.1167, "lr": 4.999615037676342e-05, "epoch": 2.1006600660066006, "percentage": 10.5, "elapsed_time": "0:45:00", "remaining_time": "6:23:33", "throughput": 1491.55, "total_tokens": 4028480} {"current_steps": 19100, "total_steps": 181800, "loss": 0.1488, "lr": 4.999610814423954e-05, "epoch": 2.1012101210121013, "percentage": 10.51, "elapsed_time": "0:45:01", "remaining_time": "6:23:32", "throughput": 1491.57, "total_tokens": 4029568} {"current_steps": 19105, "total_steps": 181800, "loss": 0.0303, "lr": 4.9996065681338515e-05, "epoch": 2.101760176017602, "percentage": 10.51, "elapsed_time": "0:45:02", "remaining_time": "6:23:31", "throughput": 1491.58, "total_tokens": 4030624} {"current_steps": 19110, "total_steps": 181800, "loss": 0.0942, "lr": 4.9996022988060755e-05, "epoch": 2.102310231023102, "percentage": 10.51, "elapsed_time": "0:45:02", "remaining_time": "6:23:31", "throughput": 1491.57, "total_tokens": 4031648} {"current_steps": 19115, "total_steps": 181800, "loss": 0.0218, "lr": 4.999598006440664e-05, "epoch": 2.1028602860286028, "percentage": 10.51, "elapsed_time": "0:45:03", "remaining_time": "6:23:30", "throughput": 1491.56, "total_tokens": 4032640} {"current_steps": 19120, "total_steps": 181800, "loss": 0.1, "lr": 4.999593691037657e-05, "epoch": 2.1034103410341034, "percentage": 10.52, "elapsed_time": "0:45:04", "remaining_time": "6:23:29", "throughput": 1491.58, "total_tokens": 4033728} {"current_steps": 19125, "total_steps": 181800, "loss": 0.0923, "lr": 4.999589352597095e-05, "epoch": 2.103960396039604, "percentage": 10.52, "elapsed_time": "0:45:05", "remaining_time": "6:23:28", "throughput": 1491.58, "total_tokens": 4034752} {"current_steps": 19130, "total_steps": 181800, "loss": 0.1144, "lr": 4.999584991119017e-05, "epoch": 2.1045104510451047, "percentage": 10.52, "elapsed_time": "0:45:05", "remaining_time": "6:23:27", "throughput": 1491.58, "total_tokens": 4035776} {"current_steps": 19135, "total_steps": 181800, "loss": 0.1195, "lr": 4.999580606603463e-05, "epoch": 2.105060506050605, "percentage": 10.53, "elapsed_time": "0:45:06", "remaining_time": "6:23:26", "throughput": 1491.6, "total_tokens": 4036832} {"current_steps": 19140, "total_steps": 181800, "loss": 0.1595, "lr": 4.999576199050475e-05, "epoch": 2.1056105610561056, "percentage": 10.53, "elapsed_time": "0:45:07", "remaining_time": "6:23:25", "throughput": 1491.58, "total_tokens": 4037824} {"current_steps": 19145, "total_steps": 181800, "loss": 0.0761, "lr": 4.999571768460093e-05, "epoch": 2.106160616061606, "percentage": 10.53, "elapsed_time": "0:45:07", "remaining_time": "6:23:25", "throughput": 1491.58, "total_tokens": 4038848} {"current_steps": 19150, "total_steps": 181800, "loss": 0.0363, "lr": 4.9995673148323566e-05, "epoch": 2.106710671067107, "percentage": 10.53, "elapsed_time": "0:45:08", "remaining_time": "6:23:24", "throughput": 1491.58, "total_tokens": 4039872} {"current_steps": 19155, "total_steps": 181800, "loss": 0.0481, "lr": 4.999562838167307e-05, "epoch": 2.107260726072607, "percentage": 10.54, "elapsed_time": "0:45:09", "remaining_time": "6:23:23", "throughput": 1491.59, "total_tokens": 4040928} {"current_steps": 19160, "total_steps": 181800, "loss": 0.0551, "lr": 4.999558338464987e-05, "epoch": 2.1078107810781077, "percentage": 10.54, "elapsed_time": "0:45:09", "remaining_time": "6:23:22", "throughput": 1491.6, "total_tokens": 4041984} {"current_steps": 19165, "total_steps": 181800, "loss": 0.0709, "lr": 4.999553815725437e-05, "epoch": 2.1083608360836084, "percentage": 10.54, "elapsed_time": "0:45:10", "remaining_time": "6:23:21", "throughput": 1491.64, "total_tokens": 4043104} {"current_steps": 19170, "total_steps": 181800, "loss": 0.0669, "lr": 4.999549269948699e-05, "epoch": 2.108910891089109, "percentage": 10.54, "elapsed_time": "0:45:11", "remaining_time": "6:23:20", "throughput": 1491.67, "total_tokens": 4044224} {"current_steps": 19175, "total_steps": 181800, "loss": 0.1023, "lr": 4.999544701134815e-05, "epoch": 2.1094609460946097, "percentage": 10.55, "elapsed_time": "0:45:11", "remaining_time": "6:23:19", "throughput": 1491.69, "total_tokens": 4045312} {"current_steps": 19180, "total_steps": 181800, "loss": 0.1232, "lr": 4.9995401092838255e-05, "epoch": 2.11001100110011, "percentage": 10.55, "elapsed_time": "0:45:12", "remaining_time": "6:23:18", "throughput": 1491.68, "total_tokens": 4046304} {"current_steps": 19185, "total_steps": 181800, "loss": 0.0691, "lr": 4.9995354943957755e-05, "epoch": 2.1105610561056105, "percentage": 10.55, "elapsed_time": "0:45:13", "remaining_time": "6:23:18", "throughput": 1491.69, "total_tokens": 4047360} {"current_steps": 19190, "total_steps": 181800, "loss": 0.1534, "lr": 4.999530856470706e-05, "epoch": 2.111111111111111, "percentage": 10.56, "elapsed_time": "0:45:13", "remaining_time": "6:23:17", "throughput": 1491.7, "total_tokens": 4048416} {"current_steps": 19195, "total_steps": 181800, "loss": 0.13, "lr": 4.99952619550866e-05, "epoch": 2.111661166116612, "percentage": 10.56, "elapsed_time": "0:45:14", "remaining_time": "6:23:16", "throughput": 1491.7, "total_tokens": 4049440} {"current_steps": 19200, "total_steps": 181800, "loss": 0.0466, "lr": 4.999521511509681e-05, "epoch": 2.112211221122112, "percentage": 10.56, "elapsed_time": "0:45:15", "remaining_time": "6:23:15", "throughput": 1491.7, "total_tokens": 4050464} {"current_steps": 19205, "total_steps": 181800, "loss": 0.1253, "lr": 4.99951680447381e-05, "epoch": 2.1127612761276127, "percentage": 10.56, "elapsed_time": "0:45:16", "remaining_time": "6:23:14", "throughput": 1491.68, "total_tokens": 4051424} {"current_steps": 19210, "total_steps": 181800, "loss": 0.0401, "lr": 4.999512074401094e-05, "epoch": 2.1133113311331133, "percentage": 10.57, "elapsed_time": "0:45:16", "remaining_time": "6:23:13", "throughput": 1491.69, "total_tokens": 4052480} {"current_steps": 19215, "total_steps": 181800, "loss": 0.0847, "lr": 4.9995073212915736e-05, "epoch": 2.113861386138614, "percentage": 10.57, "elapsed_time": "0:45:17", "remaining_time": "6:23:12", "throughput": 1491.69, "total_tokens": 4053504} {"current_steps": 19220, "total_steps": 181800, "loss": 0.0603, "lr": 4.9995025451452935e-05, "epoch": 2.1144114411441146, "percentage": 10.57, "elapsed_time": "0:45:18", "remaining_time": "6:23:11", "throughput": 1491.67, "total_tokens": 4054496} {"current_steps": 19225, "total_steps": 181800, "loss": 0.1222, "lr": 4.9994977459622976e-05, "epoch": 2.114961496149615, "percentage": 10.57, "elapsed_time": "0:45:18", "remaining_time": "6:23:11", "throughput": 1491.67, "total_tokens": 4055520} {"current_steps": 19230, "total_steps": 181800, "loss": 0.0622, "lr": 4.999492923742631e-05, "epoch": 2.1155115511551155, "percentage": 10.58, "elapsed_time": "0:45:19", "remaining_time": "6:23:10", "throughput": 1491.67, "total_tokens": 4056544} {"current_steps": 19235, "total_steps": 181800, "loss": 0.2685, "lr": 4.9994880784863375e-05, "epoch": 2.116061606160616, "percentage": 10.58, "elapsed_time": "0:45:20", "remaining_time": "6:23:09", "throughput": 1491.68, "total_tokens": 4057600} {"current_steps": 19240, "total_steps": 181800, "loss": 0.1908, "lr": 4.9994832101934607e-05, "epoch": 2.1166116611661168, "percentage": 10.58, "elapsed_time": "0:45:20", "remaining_time": "6:23:08", "throughput": 1491.69, "total_tokens": 4058656} {"current_steps": 19245, "total_steps": 181800, "loss": 0.0704, "lr": 4.9994783188640476e-05, "epoch": 2.117161716171617, "percentage": 10.59, "elapsed_time": "0:45:21", "remaining_time": "6:23:07", "throughput": 1491.7, "total_tokens": 4059712} {"current_steps": 19250, "total_steps": 181800, "loss": 0.0546, "lr": 4.999473404498142e-05, "epoch": 2.1177117711771176, "percentage": 10.59, "elapsed_time": "0:45:22", "remaining_time": "6:23:06", "throughput": 1491.69, "total_tokens": 4060704} {"current_steps": 19255, "total_steps": 181800, "loss": 0.0623, "lr": 4.999468467095789e-05, "epoch": 2.1182618261826183, "percentage": 10.59, "elapsed_time": "0:45:22", "remaining_time": "6:23:06", "throughput": 1491.71, "total_tokens": 4061792} {"current_steps": 19260, "total_steps": 181800, "loss": 0.0611, "lr": 4.999463506657035e-05, "epoch": 2.118811881188119, "percentage": 10.59, "elapsed_time": "0:45:23", "remaining_time": "6:23:05", "throughput": 1491.75, "total_tokens": 4062944} {"current_steps": 19265, "total_steps": 181800, "loss": 0.0441, "lr": 4.9994585231819246e-05, "epoch": 2.1193619361936196, "percentage": 10.6, "elapsed_time": "0:45:24", "remaining_time": "6:23:04", "throughput": 1491.75, "total_tokens": 4063968} {"current_steps": 19270, "total_steps": 181800, "loss": 0.0376, "lr": 4.999453516670505e-05, "epoch": 2.1199119911991198, "percentage": 10.6, "elapsed_time": "0:45:24", "remaining_time": "6:23:03", "throughput": 1491.77, "total_tokens": 4065056} {"current_steps": 19275, "total_steps": 181800, "loss": 0.0285, "lr": 4.9994484871228206e-05, "epoch": 2.1204620462046204, "percentage": 10.6, "elapsed_time": "0:45:25", "remaining_time": "6:23:02", "throughput": 1491.79, "total_tokens": 4066144} {"current_steps": 19280, "total_steps": 181800, "loss": 0.0361, "lr": 4.999443434538921e-05, "epoch": 2.121012101210121, "percentage": 10.61, "elapsed_time": "0:45:26", "remaining_time": "6:23:01", "throughput": 1491.82, "total_tokens": 4067264} {"current_steps": 19285, "total_steps": 181800, "loss": 0.0715, "lr": 4.9994383589188485e-05, "epoch": 2.1215621562156217, "percentage": 10.61, "elapsed_time": "0:45:27", "remaining_time": "6:23:00", "throughput": 1491.83, "total_tokens": 4068320} {"current_steps": 19290, "total_steps": 181800, "loss": 0.029, "lr": 4.999433260262653e-05, "epoch": 2.122112211221122, "percentage": 10.61, "elapsed_time": "0:45:27", "remaining_time": "6:23:00", "throughput": 1491.85, "total_tokens": 4069408} {"current_steps": 19295, "total_steps": 181800, "loss": 0.0923, "lr": 4.99942813857038e-05, "epoch": 2.1226622662266226, "percentage": 10.61, "elapsed_time": "0:45:28", "remaining_time": "6:22:59", "throughput": 1491.86, "total_tokens": 4070464} {"current_steps": 19300, "total_steps": 181800, "loss": 0.0347, "lr": 4.999422993842078e-05, "epoch": 2.1232123212321232, "percentage": 10.62, "elapsed_time": "0:45:29", "remaining_time": "6:22:58", "throughput": 1491.86, "total_tokens": 4071488} {"current_steps": 19305, "total_steps": 181800, "loss": 0.0541, "lr": 4.999417826077793e-05, "epoch": 2.123762376237624, "percentage": 10.62, "elapsed_time": "0:45:29", "remaining_time": "6:22:57", "throughput": 1491.88, "total_tokens": 4072576} {"current_steps": 19310, "total_steps": 181800, "loss": 0.0917, "lr": 4.9994126352775725e-05, "epoch": 2.1243124312431245, "percentage": 10.62, "elapsed_time": "0:45:30", "remaining_time": "6:22:56", "throughput": 1491.89, "total_tokens": 4073632} {"current_steps": 19315, "total_steps": 181800, "loss": 0.12, "lr": 4.9994074214414666e-05, "epoch": 2.1248624862486247, "percentage": 10.62, "elapsed_time": "0:45:31", "remaining_time": "6:22:55", "throughput": 1491.91, "total_tokens": 4074720} {"current_steps": 19320, "total_steps": 181800, "loss": 0.0923, "lr": 4.9994021845695205e-05, "epoch": 2.1254125412541254, "percentage": 10.63, "elapsed_time": "0:45:31", "remaining_time": "6:22:55", "throughput": 1491.92, "total_tokens": 4075776} {"current_steps": 19325, "total_steps": 181800, "loss": 0.0692, "lr": 4.999396924661784e-05, "epoch": 2.125962596259626, "percentage": 10.63, "elapsed_time": "0:45:32", "remaining_time": "6:22:54", "throughput": 1491.94, "total_tokens": 4076864} {"current_steps": 19330, "total_steps": 181800, "loss": 0.0565, "lr": 4.999391641718306e-05, "epoch": 2.1265126512651267, "percentage": 10.63, "elapsed_time": "0:45:33", "remaining_time": "6:22:53", "throughput": 1491.96, "total_tokens": 4077952} {"current_steps": 19335, "total_steps": 181800, "loss": 0.1594, "lr": 4.9993863357391344e-05, "epoch": 2.127062706270627, "percentage": 10.64, "elapsed_time": "0:45:33", "remaining_time": "6:22:52", "throughput": 1491.97, "total_tokens": 4079008} {"current_steps": 19340, "total_steps": 181800, "loss": 0.1634, "lr": 4.9993810067243184e-05, "epoch": 2.1276127612761275, "percentage": 10.64, "elapsed_time": "0:45:34", "remaining_time": "6:22:51", "throughput": 1491.99, "total_tokens": 4080096} {"current_steps": 19345, "total_steps": 181800, "loss": 0.0221, "lr": 4.999375654673907e-05, "epoch": 2.128162816281628, "percentage": 10.64, "elapsed_time": "0:45:35", "remaining_time": "6:22:50", "throughput": 1492.01, "total_tokens": 4081184} {"current_steps": 19350, "total_steps": 181800, "loss": 0.0879, "lr": 4.999370279587949e-05, "epoch": 2.128712871287129, "percentage": 10.64, "elapsed_time": "0:45:36", "remaining_time": "6:22:50", "throughput": 1492.01, "total_tokens": 4082240} {"current_steps": 19355, "total_steps": 181800, "loss": 0.0239, "lr": 4.999364881466495e-05, "epoch": 2.129262926292629, "percentage": 10.65, "elapsed_time": "0:45:36", "remaining_time": "6:22:49", "throughput": 1492.04, "total_tokens": 4083328} {"current_steps": 19360, "total_steps": 181800, "loss": 0.1226, "lr": 4.999359460309594e-05, "epoch": 2.1298129812981297, "percentage": 10.65, "elapsed_time": "0:45:37", "remaining_time": "6:22:48", "throughput": 1492.03, "total_tokens": 4084320} {"current_steps": 19365, "total_steps": 181800, "loss": 0.1353, "lr": 4.999354016117296e-05, "epoch": 2.1303630363036303, "percentage": 10.65, "elapsed_time": "0:45:38", "remaining_time": "6:22:47", "throughput": 1492.01, "total_tokens": 4085312} {"current_steps": 19370, "total_steps": 181800, "loss": 0.0273, "lr": 4.9993485488896515e-05, "epoch": 2.130913091309131, "percentage": 10.65, "elapsed_time": "0:45:38", "remaining_time": "6:22:46", "throughput": 1492.06, "total_tokens": 4086464} {"current_steps": 19375, "total_steps": 181800, "loss": 0.1085, "lr": 4.99934305862671e-05, "epoch": 2.1314631463146316, "percentage": 10.66, "elapsed_time": "0:45:39", "remaining_time": "6:22:45", "throughput": 1492.09, "total_tokens": 4087584} {"current_steps": 19380, "total_steps": 181800, "loss": 0.0638, "lr": 4.999337545328524e-05, "epoch": 2.132013201320132, "percentage": 10.66, "elapsed_time": "0:45:40", "remaining_time": "6:22:45", "throughput": 1492.08, "total_tokens": 4088576} {"current_steps": 19385, "total_steps": 181800, "loss": 0.1746, "lr": 4.9993320089951425e-05, "epoch": 2.1325632563256325, "percentage": 10.66, "elapsed_time": "0:45:40", "remaining_time": "6:22:44", "throughput": 1492.08, "total_tokens": 4089632} {"current_steps": 19390, "total_steps": 181800, "loss": 0.0959, "lr": 4.999326449626617e-05, "epoch": 2.133113311331133, "percentage": 10.67, "elapsed_time": "0:45:41", "remaining_time": "6:22:43", "throughput": 1492.09, "total_tokens": 4090688} {"current_steps": 19395, "total_steps": 181800, "loss": 0.0471, "lr": 4.9993208672229995e-05, "epoch": 2.133663366336634, "percentage": 10.67, "elapsed_time": "0:45:42", "remaining_time": "6:22:42", "throughput": 1492.13, "total_tokens": 4091808} {"current_steps": 19400, "total_steps": 181800, "loss": 0.0683, "lr": 4.9993152617843406e-05, "epoch": 2.1342134213421344, "percentage": 10.67, "elapsed_time": "0:45:42", "remaining_time": "6:22:41", "throughput": 1492.12, "total_tokens": 4092832} {"current_steps": 19405, "total_steps": 181800, "loss": 0.0402, "lr": 4.999309633310692e-05, "epoch": 2.1347634763476346, "percentage": 10.67, "elapsed_time": "0:45:43", "remaining_time": "6:22:40", "throughput": 1492.15, "total_tokens": 4093920} {"current_steps": 19410, "total_steps": 181800, "loss": 0.035, "lr": 4.999303981802106e-05, "epoch": 2.1353135313531353, "percentage": 10.68, "elapsed_time": "0:45:44", "remaining_time": "6:22:39", "throughput": 1492.16, "total_tokens": 4094976} {"current_steps": 19415, "total_steps": 181800, "loss": 0.078, "lr": 4.999298307258635e-05, "epoch": 2.135863586358636, "percentage": 10.68, "elapsed_time": "0:45:45", "remaining_time": "6:22:39", "throughput": 1492.18, "total_tokens": 4096064} {"current_steps": 19420, "total_steps": 181800, "loss": 0.0136, "lr": 4.9992926096803294e-05, "epoch": 2.1364136413641366, "percentage": 10.68, "elapsed_time": "0:45:45", "remaining_time": "6:22:38", "throughput": 1492.17, "total_tokens": 4097056} {"current_steps": 19425, "total_steps": 181800, "loss": 0.0632, "lr": 4.9992868890672437e-05, "epoch": 2.136963696369637, "percentage": 10.68, "elapsed_time": "0:45:46", "remaining_time": "6:22:37", "throughput": 1492.19, "total_tokens": 4098144} {"current_steps": 19430, "total_steps": 181800, "loss": 0.0898, "lr": 4.999281145419431e-05, "epoch": 2.1375137513751374, "percentage": 10.69, "elapsed_time": "0:45:47", "remaining_time": "6:22:36", "throughput": 1492.2, "total_tokens": 4099200} {"current_steps": 19435, "total_steps": 181800, "loss": 0.1143, "lr": 4.999275378736942e-05, "epoch": 2.138063806380638, "percentage": 10.69, "elapsed_time": "0:45:47", "remaining_time": "6:22:35", "throughput": 1492.22, "total_tokens": 4100288} {"current_steps": 19440, "total_steps": 181800, "loss": 0.1199, "lr": 4.999269589019832e-05, "epoch": 2.1386138613861387, "percentage": 10.69, "elapsed_time": "0:45:48", "remaining_time": "6:22:34", "throughput": 1492.24, "total_tokens": 4101376} {"current_steps": 19445, "total_steps": 181800, "loss": 0.0127, "lr": 4.9992637762681525e-05, "epoch": 2.139163916391639, "percentage": 10.7, "elapsed_time": "0:45:49", "remaining_time": "6:22:33", "throughput": 1492.25, "total_tokens": 4102432} {"current_steps": 19450, "total_steps": 181800, "loss": 0.1006, "lr": 4.999257940481959e-05, "epoch": 2.1397139713971396, "percentage": 10.7, "elapsed_time": "0:45:49", "remaining_time": "6:22:33", "throughput": 1492.27, "total_tokens": 4103488} {"current_steps": 19455, "total_steps": 181800, "loss": 0.0164, "lr": 4.999252081661304e-05, "epoch": 2.1402640264026402, "percentage": 10.7, "elapsed_time": "0:45:50", "remaining_time": "6:22:32", "throughput": 1492.28, "total_tokens": 4104544} {"current_steps": 19460, "total_steps": 181800, "loss": 0.1318, "lr": 4.999246199806242e-05, "epoch": 2.140814081408141, "percentage": 10.7, "elapsed_time": "0:45:51", "remaining_time": "6:22:31", "throughput": 1492.29, "total_tokens": 4105600} {"current_steps": 19465, "total_steps": 181800, "loss": 0.0556, "lr": 4.9992402949168266e-05, "epoch": 2.1413641364136415, "percentage": 10.71, "elapsed_time": "0:45:51", "remaining_time": "6:22:30", "throughput": 1492.31, "total_tokens": 4106688} {"current_steps": 19470, "total_steps": 181800, "loss": 0.0372, "lr": 4.999234366993113e-05, "epoch": 2.1419141914191417, "percentage": 10.71, "elapsed_time": "0:45:52", "remaining_time": "6:22:29", "throughput": 1492.33, "total_tokens": 4107776} {"current_steps": 19475, "total_steps": 181800, "loss": 0.0575, "lr": 4.999228416035155e-05, "epoch": 2.1424642464246424, "percentage": 10.71, "elapsed_time": "0:45:53", "remaining_time": "6:22:28", "throughput": 1492.37, "total_tokens": 4108896} {"current_steps": 19480, "total_steps": 181800, "loss": 0.0306, "lr": 4.999222442043009e-05, "epoch": 2.143014301430143, "percentage": 10.72, "elapsed_time": "0:45:53", "remaining_time": "6:22:27", "throughput": 1492.38, "total_tokens": 4109952} {"current_steps": 19485, "total_steps": 181800, "loss": 0.1508, "lr": 4.999216445016728e-05, "epoch": 2.1435643564356437, "percentage": 10.72, "elapsed_time": "0:45:54", "remaining_time": "6:22:26", "throughput": 1492.38, "total_tokens": 4110976} {"current_steps": 19490, "total_steps": 181800, "loss": 0.0375, "lr": 4.999210424956368e-05, "epoch": 2.1441144114411443, "percentage": 10.72, "elapsed_time": "0:45:55", "remaining_time": "6:22:26", "throughput": 1492.38, "total_tokens": 4112000} {"current_steps": 19495, "total_steps": 181800, "loss": 0.0481, "lr": 4.999204381861985e-05, "epoch": 2.1446644664466445, "percentage": 10.72, "elapsed_time": "0:45:56", "remaining_time": "6:22:25", "throughput": 1492.38, "total_tokens": 4113024} {"current_steps": 19500, "total_steps": 181800, "loss": 0.0431, "lr": 4.9991983157336355e-05, "epoch": 2.145214521452145, "percentage": 10.73, "elapsed_time": "0:45:56", "remaining_time": "6:22:24", "throughput": 1492.37, "total_tokens": 4114016} {"current_steps": 19505, "total_steps": 181800, "loss": 0.0773, "lr": 4.999192226571373e-05, "epoch": 2.145764576457646, "percentage": 10.73, "elapsed_time": "0:45:57", "remaining_time": "6:22:23", "throughput": 1492.37, "total_tokens": 4115040} {"current_steps": 19510, "total_steps": 181800, "loss": 0.0913, "lr": 4.999186114375256e-05, "epoch": 2.1463146314631465, "percentage": 10.73, "elapsed_time": "0:45:58", "remaining_time": "6:22:22", "throughput": 1492.38, "total_tokens": 4116096} {"current_steps": 19515, "total_steps": 181800, "loss": 0.0982, "lr": 4.999179979145339e-05, "epoch": 2.1468646864686467, "percentage": 10.73, "elapsed_time": "0:45:58", "remaining_time": "6:22:21", "throughput": 1492.39, "total_tokens": 4117152} {"current_steps": 19520, "total_steps": 181800, "loss": 0.0593, "lr": 4.99917382088168e-05, "epoch": 2.1474147414741473, "percentage": 10.74, "elapsed_time": "0:45:59", "remaining_time": "6:22:20", "throughput": 1492.4, "total_tokens": 4118208} {"current_steps": 19525, "total_steps": 181800, "loss": 0.0308, "lr": 4.9991676395843344e-05, "epoch": 2.147964796479648, "percentage": 10.74, "elapsed_time": "0:46:00", "remaining_time": "6:22:19", "throughput": 1492.4, "total_tokens": 4119232} {"current_steps": 19530, "total_steps": 181800, "loss": 0.0736, "lr": 4.999161435253361e-05, "epoch": 2.1485148514851486, "percentage": 10.74, "elapsed_time": "0:46:00", "remaining_time": "6:22:19", "throughput": 1492.41, "total_tokens": 4120288} {"current_steps": 19535, "total_steps": 181800, "loss": 0.0383, "lr": 4.999155207888815e-05, "epoch": 2.149064906490649, "percentage": 10.75, "elapsed_time": "0:46:01", "remaining_time": "6:22:18", "throughput": 1492.38, "total_tokens": 4121248} {"current_steps": 19540, "total_steps": 181800, "loss": 0.0767, "lr": 4.999148957490755e-05, "epoch": 2.1496149614961495, "percentage": 10.75, "elapsed_time": "0:46:02", "remaining_time": "6:22:17", "throughput": 1492.37, "total_tokens": 4122240} {"current_steps": 19545, "total_steps": 181800, "loss": 0.1043, "lr": 4.999142684059238e-05, "epoch": 2.15016501650165, "percentage": 10.75, "elapsed_time": "0:46:02", "remaining_time": "6:22:16", "throughput": 1492.36, "total_tokens": 4123264} {"current_steps": 19550, "total_steps": 181800, "loss": 0.0938, "lr": 4.999136387594322e-05, "epoch": 2.150715071507151, "percentage": 10.75, "elapsed_time": "0:46:03", "remaining_time": "6:22:15", "throughput": 1492.37, "total_tokens": 4124320} {"current_steps": 19555, "total_steps": 181800, "loss": 0.2002, "lr": 4.999130068096065e-05, "epoch": 2.1512651265126514, "percentage": 10.76, "elapsed_time": "0:46:04", "remaining_time": "6:22:14", "throughput": 1492.37, "total_tokens": 4125344} {"current_steps": 19560, "total_steps": 181800, "loss": 0.1017, "lr": 4.999123725564526e-05, "epoch": 2.1518151815181517, "percentage": 10.76, "elapsed_time": "0:46:04", "remaining_time": "6:22:14", "throughput": 1492.39, "total_tokens": 4126432} {"current_steps": 19565, "total_steps": 181800, "loss": 0.1346, "lr": 4.999117359999763e-05, "epoch": 2.1523652365236523, "percentage": 10.76, "elapsed_time": "0:46:05", "remaining_time": "6:22:13", "throughput": 1492.41, "total_tokens": 4127488} {"current_steps": 19570, "total_steps": 181800, "loss": 0.1501, "lr": 4.999110971401834e-05, "epoch": 2.152915291529153, "percentage": 10.76, "elapsed_time": "0:46:06", "remaining_time": "6:22:12", "throughput": 1492.43, "total_tokens": 4128576} {"current_steps": 19575, "total_steps": 181800, "loss": 0.1225, "lr": 4.999104559770797e-05, "epoch": 2.1534653465346536, "percentage": 10.77, "elapsed_time": "0:46:07", "remaining_time": "6:22:11", "throughput": 1492.45, "total_tokens": 4129664} {"current_steps": 19580, "total_steps": 181800, "loss": 0.0464, "lr": 4.999098125106715e-05, "epoch": 2.1540154015401543, "percentage": 10.77, "elapsed_time": "0:46:07", "remaining_time": "6:22:10", "throughput": 1492.45, "total_tokens": 4130688} {"current_steps": 19585, "total_steps": 181800, "loss": 0.1451, "lr": 4.999091667409643e-05, "epoch": 2.1545654565456545, "percentage": 10.77, "elapsed_time": "0:46:08", "remaining_time": "6:22:09", "throughput": 1492.43, "total_tokens": 4131680} {"current_steps": 19590, "total_steps": 181800, "loss": 0.0835, "lr": 4.999085186679643e-05, "epoch": 2.155115511551155, "percentage": 10.78, "elapsed_time": "0:46:09", "remaining_time": "6:22:08", "throughput": 1492.44, "total_tokens": 4132736} {"current_steps": 19595, "total_steps": 181800, "loss": 0.213, "lr": 4.999078682916774e-05, "epoch": 2.1556655665566558, "percentage": 10.78, "elapsed_time": "0:46:09", "remaining_time": "6:22:08", "throughput": 1492.47, "total_tokens": 4133824} {"current_steps": 19600, "total_steps": 181800, "loss": 0.0601, "lr": 4.9990721561210956e-05, "epoch": 2.1562156215621564, "percentage": 10.78, "elapsed_time": "0:46:10", "remaining_time": "6:22:07", "throughput": 1492.47, "total_tokens": 4134880} {"current_steps": 19605, "total_steps": 181800, "loss": 0.1424, "lr": 4.999065606292669e-05, "epoch": 2.1567656765676566, "percentage": 10.78, "elapsed_time": "0:46:11", "remaining_time": "6:22:06", "throughput": 1492.47, "total_tokens": 4135904} {"current_steps": 19610, "total_steps": 181800, "loss": 0.0542, "lr": 4.999059033431554e-05, "epoch": 2.1573157315731573, "percentage": 10.79, "elapsed_time": "0:46:11", "remaining_time": "6:22:05", "throughput": 1492.48, "total_tokens": 4136960} {"current_steps": 19615, "total_steps": 181800, "loss": 0.1746, "lr": 4.9990524375378095e-05, "epoch": 2.157865786578658, "percentage": 10.79, "elapsed_time": "0:46:12", "remaining_time": "6:22:04", "throughput": 1492.47, "total_tokens": 4137952} {"current_steps": 19620, "total_steps": 181800, "loss": 0.0304, "lr": 4.9990458186114985e-05, "epoch": 2.1584158415841586, "percentage": 10.79, "elapsed_time": "0:46:13", "remaining_time": "6:22:03", "throughput": 1492.49, "total_tokens": 4139040} {"current_steps": 19625, "total_steps": 181800, "loss": 0.0923, "lr": 4.999039176652682e-05, "epoch": 2.1589658965896588, "percentage": 10.79, "elapsed_time": "0:46:13", "remaining_time": "6:22:02", "throughput": 1492.49, "total_tokens": 4140064} {"current_steps": 19630, "total_steps": 181800, "loss": 0.1281, "lr": 4.99903251166142e-05, "epoch": 2.1595159515951594, "percentage": 10.8, "elapsed_time": "0:46:14", "remaining_time": "6:22:02", "throughput": 1492.5, "total_tokens": 4141120} {"current_steps": 19635, "total_steps": 181800, "loss": 0.1189, "lr": 4.999025823637775e-05, "epoch": 2.16006600660066, "percentage": 10.8, "elapsed_time": "0:46:15", "remaining_time": "6:22:01", "throughput": 1492.5, "total_tokens": 4142176} {"current_steps": 19640, "total_steps": 181800, "loss": 0.0989, "lr": 4.9990191125818074e-05, "epoch": 2.1606160616061607, "percentage": 10.8, "elapsed_time": "0:46:16", "remaining_time": "6:22:00", "throughput": 1492.5, "total_tokens": 4143200} {"current_steps": 19645, "total_steps": 181800, "loss": 0.0252, "lr": 4.999012378493581e-05, "epoch": 2.1611661166116614, "percentage": 10.81, "elapsed_time": "0:46:16", "remaining_time": "6:21:59", "throughput": 1492.5, "total_tokens": 4144224} {"current_steps": 19650, "total_steps": 181800, "loss": 0.0579, "lr": 4.999005621373155e-05, "epoch": 2.1617161716171616, "percentage": 10.81, "elapsed_time": "0:46:17", "remaining_time": "6:21:58", "throughput": 1492.48, "total_tokens": 4145216} {"current_steps": 19655, "total_steps": 181800, "loss": 0.0166, "lr": 4.998998841220595e-05, "epoch": 2.162266226622662, "percentage": 10.81, "elapsed_time": "0:46:18", "remaining_time": "6:21:57", "throughput": 1492.51, "total_tokens": 4146304} {"current_steps": 19660, "total_steps": 181800, "loss": 0.097, "lr": 4.9989920380359605e-05, "epoch": 2.162816281628163, "percentage": 10.81, "elapsed_time": "0:46:18", "remaining_time": "6:21:57", "throughput": 1492.53, "total_tokens": 4147392} {"current_steps": 19665, "total_steps": 181800, "loss": 0.0733, "lr": 4.998985211819316e-05, "epoch": 2.1633663366336635, "percentage": 10.82, "elapsed_time": "0:46:19", "remaining_time": "6:21:56", "throughput": 1492.55, "total_tokens": 4148480} {"current_steps": 19670, "total_steps": 181800, "loss": 0.0164, "lr": 4.9989783625707243e-05, "epoch": 2.1639163916391637, "percentage": 10.82, "elapsed_time": "0:46:20", "remaining_time": "6:21:55", "throughput": 1492.54, "total_tokens": 4149472} {"current_steps": 19675, "total_steps": 181800, "loss": 0.0652, "lr": 4.998971490290247e-05, "epoch": 2.1644664466446644, "percentage": 10.82, "elapsed_time": "0:46:20", "remaining_time": "6:21:54", "throughput": 1492.53, "total_tokens": 4150464} {"current_steps": 19680, "total_steps": 181800, "loss": 0.0854, "lr": 4.9989645949779504e-05, "epoch": 2.165016501650165, "percentage": 10.83, "elapsed_time": "0:46:21", "remaining_time": "6:21:53", "throughput": 1492.55, "total_tokens": 4151552} {"current_steps": 19685, "total_steps": 181800, "loss": 0.0257, "lr": 4.998957676633895e-05, "epoch": 2.1655665566556657, "percentage": 10.83, "elapsed_time": "0:46:22", "remaining_time": "6:21:52", "throughput": 1492.55, "total_tokens": 4152576} {"current_steps": 19690, "total_steps": 181800, "loss": 0.1007, "lr": 4.998950735258146e-05, "epoch": 2.1661166116611663, "percentage": 10.83, "elapsed_time": "0:46:22", "remaining_time": "6:21:51", "throughput": 1492.57, "total_tokens": 4153664} {"current_steps": 19695, "total_steps": 181800, "loss": 0.0429, "lr": 4.9989437708507675e-05, "epoch": 2.1666666666666665, "percentage": 10.83, "elapsed_time": "0:46:23", "remaining_time": "6:21:51", "throughput": 1492.56, "total_tokens": 4154688} {"current_steps": 19700, "total_steps": 181800, "loss": 0.0925, "lr": 4.9989367834118225e-05, "epoch": 2.167216721672167, "percentage": 10.84, "elapsed_time": "0:46:24", "remaining_time": "6:21:50", "throughput": 1492.56, "total_tokens": 4155712} {"current_steps": 19705, "total_steps": 181800, "loss": 0.1361, "lr": 4.9989297729413774e-05, "epoch": 2.167766776677668, "percentage": 10.84, "elapsed_time": "0:46:24", "remaining_time": "6:21:49", "throughput": 1492.59, "total_tokens": 4156832} {"current_steps": 19710, "total_steps": 181800, "loss": 0.1149, "lr": 4.998922739439495e-05, "epoch": 2.1683168316831685, "percentage": 10.84, "elapsed_time": "0:46:25", "remaining_time": "6:21:48", "throughput": 1492.58, "total_tokens": 4157824} {"current_steps": 19715, "total_steps": 181800, "loss": 0.0425, "lr": 4.998915682906241e-05, "epoch": 2.1688668866886687, "percentage": 10.84, "elapsed_time": "0:46:26", "remaining_time": "6:21:47", "throughput": 1492.61, "total_tokens": 4158944} {"current_steps": 19720, "total_steps": 181800, "loss": 0.0263, "lr": 4.9989086033416806e-05, "epoch": 2.1694169416941693, "percentage": 10.85, "elapsed_time": "0:46:27", "remaining_time": "6:21:46", "throughput": 1492.63, "total_tokens": 4160032} {"current_steps": 19725, "total_steps": 181800, "loss": 0.0534, "lr": 4.998901500745878e-05, "epoch": 2.16996699669967, "percentage": 10.85, "elapsed_time": "0:46:27", "remaining_time": "6:21:46", "throughput": 1492.64, "total_tokens": 4161088} {"current_steps": 19730, "total_steps": 181800, "loss": 0.1439, "lr": 4.9988943751189e-05, "epoch": 2.1705170517051706, "percentage": 10.85, "elapsed_time": "0:46:28", "remaining_time": "6:21:45", "throughput": 1492.63, "total_tokens": 4162080} {"current_steps": 19735, "total_steps": 181800, "loss": 0.082, "lr": 4.9988872264608114e-05, "epoch": 2.1710671067106713, "percentage": 10.86, "elapsed_time": "0:46:29", "remaining_time": "6:21:44", "throughput": 1492.65, "total_tokens": 4163168} {"current_steps": 19740, "total_steps": 181800, "loss": 0.068, "lr": 4.9988800547716784e-05, "epoch": 2.1716171617161715, "percentage": 10.86, "elapsed_time": "0:46:29", "remaining_time": "6:21:43", "throughput": 1492.65, "total_tokens": 4164224} {"current_steps": 19745, "total_steps": 181800, "loss": 0.0187, "lr": 4.9988728600515664e-05, "epoch": 2.172167216721672, "percentage": 10.86, "elapsed_time": "0:46:30", "remaining_time": "6:21:42", "throughput": 1492.67, "total_tokens": 4165312} {"current_steps": 19750, "total_steps": 181800, "loss": 0.059, "lr": 4.998865642300543e-05, "epoch": 2.1727172717271728, "percentage": 10.86, "elapsed_time": "0:46:31", "remaining_time": "6:21:41", "throughput": 1492.66, "total_tokens": 4166304} {"current_steps": 19755, "total_steps": 181800, "loss": 0.1303, "lr": 4.998858401518674e-05, "epoch": 2.1732673267326734, "percentage": 10.87, "elapsed_time": "0:46:31", "remaining_time": "6:21:41", "throughput": 1492.65, "total_tokens": 4167296} {"current_steps": 19760, "total_steps": 181800, "loss": 0.1291, "lr": 4.998851137706026e-05, "epoch": 2.1738173817381736, "percentage": 10.87, "elapsed_time": "0:46:32", "remaining_time": "6:21:40", "throughput": 1492.63, "total_tokens": 4168288} {"current_steps": 19765, "total_steps": 181800, "loss": 0.0374, "lr": 4.9988438508626664e-05, "epoch": 2.1743674367436743, "percentage": 10.87, "elapsed_time": "0:46:33", "remaining_time": "6:21:39", "throughput": 1492.63, "total_tokens": 4169312} {"current_steps": 19770, "total_steps": 181800, "loss": 0.125, "lr": 4.998836540988662e-05, "epoch": 2.174917491749175, "percentage": 10.87, "elapsed_time": "0:46:33", "remaining_time": "6:21:38", "throughput": 1492.65, "total_tokens": 4170400} {"current_steps": 19775, "total_steps": 181800, "loss": 0.1088, "lr": 4.998829208084079e-05, "epoch": 2.1754675467546756, "percentage": 10.88, "elapsed_time": "0:46:34", "remaining_time": "6:21:37", "throughput": 1492.67, "total_tokens": 4171488} {"current_steps": 19780, "total_steps": 181800, "loss": 0.0722, "lr": 4.998821852148988e-05, "epoch": 2.1760176017601762, "percentage": 10.88, "elapsed_time": "0:46:35", "remaining_time": "6:21:36", "throughput": 1492.7, "total_tokens": 4172608} {"current_steps": 19785, "total_steps": 181800, "loss": 0.0337, "lr": 4.998814473183454e-05, "epoch": 2.1765676567656764, "percentage": 10.88, "elapsed_time": "0:46:36", "remaining_time": "6:21:36", "throughput": 1492.71, "total_tokens": 4173664} {"current_steps": 19790, "total_steps": 181800, "loss": 0.118, "lr": 4.9988070711875465e-05, "epoch": 2.177117711771177, "percentage": 10.89, "elapsed_time": "0:46:36", "remaining_time": "6:21:35", "throughput": 1492.72, "total_tokens": 4174720} {"current_steps": 19795, "total_steps": 181800, "loss": 0.041, "lr": 4.998799646161334e-05, "epoch": 2.1776677667766777, "percentage": 10.89, "elapsed_time": "0:46:37", "remaining_time": "6:21:34", "throughput": 1492.71, "total_tokens": 4175712} {"current_steps": 19800, "total_steps": 181800, "loss": 0.0828, "lr": 4.998792198104883e-05, "epoch": 2.1782178217821784, "percentage": 10.89, "elapsed_time": "0:46:38", "remaining_time": "6:21:33", "throughput": 1492.74, "total_tokens": 4176832} {"current_steps": 19805, "total_steps": 181800, "loss": 0.0346, "lr": 4.998784727018264e-05, "epoch": 2.1787678767876786, "percentage": 10.89, "elapsed_time": "0:46:38", "remaining_time": "6:21:32", "throughput": 1492.77, "total_tokens": 4177952} {"current_steps": 19810, "total_steps": 181800, "loss": 0.1562, "lr": 4.9987772329015447e-05, "epoch": 2.1793179317931792, "percentage": 10.9, "elapsed_time": "0:46:39", "remaining_time": "6:21:31", "throughput": 1492.78, "total_tokens": 4179008} {"current_steps": 19815, "total_steps": 181800, "loss": 0.1394, "lr": 4.998769715754795e-05, "epoch": 2.17986798679868, "percentage": 10.9, "elapsed_time": "0:46:40", "remaining_time": "6:21:30", "throughput": 1492.8, "total_tokens": 4180096} {"current_steps": 19820, "total_steps": 181800, "loss": 0.2106, "lr": 4.9987621755780834e-05, "epoch": 2.1804180418041805, "percentage": 10.9, "elapsed_time": "0:46:40", "remaining_time": "6:21:30", "throughput": 1492.8, "total_tokens": 4181120} {"current_steps": 19825, "total_steps": 181800, "loss": 0.0973, "lr": 4.998754612371481e-05, "epoch": 2.180968096809681, "percentage": 10.9, "elapsed_time": "0:46:41", "remaining_time": "6:21:29", "throughput": 1492.81, "total_tokens": 4182176} {"current_steps": 19830, "total_steps": 181800, "loss": 0.1207, "lr": 4.998747026135055e-05, "epoch": 2.1815181518151814, "percentage": 10.91, "elapsed_time": "0:46:42", "remaining_time": "6:21:28", "throughput": 1492.85, "total_tokens": 4183296} {"current_steps": 19835, "total_steps": 181800, "loss": 0.1354, "lr": 4.998739416868877e-05, "epoch": 2.182068206820682, "percentage": 10.91, "elapsed_time": "0:46:42", "remaining_time": "6:21:27", "throughput": 1492.84, "total_tokens": 4184320} {"current_steps": 19840, "total_steps": 181800, "loss": 0.1074, "lr": 4.998731784573018e-05, "epoch": 2.1826182618261827, "percentage": 10.91, "elapsed_time": "0:46:43", "remaining_time": "6:21:26", "throughput": 1492.82, "total_tokens": 4185280} {"current_steps": 19845, "total_steps": 181800, "loss": 0.1604, "lr": 4.9987241292475456e-05, "epoch": 2.1831683168316833, "percentage": 10.92, "elapsed_time": "0:46:44", "remaining_time": "6:21:25", "throughput": 1492.84, "total_tokens": 4186368} {"current_steps": 19850, "total_steps": 181800, "loss": 0.0632, "lr": 4.998716450892533e-05, "epoch": 2.1837183718371835, "percentage": 10.92, "elapsed_time": "0:46:44", "remaining_time": "6:21:25", "throughput": 1492.85, "total_tokens": 4187424} {"current_steps": 19855, "total_steps": 181800, "loss": 0.0251, "lr": 4.9987087495080484e-05, "epoch": 2.184268426842684, "percentage": 10.92, "elapsed_time": "0:46:45", "remaining_time": "6:21:24", "throughput": 1492.85, "total_tokens": 4188480} {"current_steps": 19860, "total_steps": 181800, "loss": 0.0594, "lr": 4.998701025094166e-05, "epoch": 2.184818481848185, "percentage": 10.92, "elapsed_time": "0:46:46", "remaining_time": "6:21:25", "throughput": 1492.74, "total_tokens": 4189536} {"current_steps": 19865, "total_steps": 181800, "loss": 0.1316, "lr": 4.998693277650954e-05, "epoch": 2.1853685368536855, "percentage": 10.93, "elapsed_time": "0:46:47", "remaining_time": "6:21:24", "throughput": 1492.75, "total_tokens": 4190592} {"current_steps": 19870, "total_steps": 181800, "loss": 0.066, "lr": 4.998685507178486e-05, "epoch": 2.1859185918591857, "percentage": 10.93, "elapsed_time": "0:46:47", "remaining_time": "6:21:23", "throughput": 1492.76, "total_tokens": 4191648} {"current_steps": 19875, "total_steps": 181800, "loss": 0.0473, "lr": 4.998677713676833e-05, "epoch": 2.1864686468646863, "percentage": 10.93, "elapsed_time": "0:46:48", "remaining_time": "6:21:22", "throughput": 1492.76, "total_tokens": 4192672} {"current_steps": 19880, "total_steps": 181800, "loss": 0.0547, "lr": 4.998669897146065e-05, "epoch": 2.187018701870187, "percentage": 10.94, "elapsed_time": "0:46:49", "remaining_time": "6:21:21", "throughput": 1492.75, "total_tokens": 4193664} {"current_steps": 19885, "total_steps": 181800, "loss": 0.0774, "lr": 4.998662057586256e-05, "epoch": 2.1875687568756876, "percentage": 10.94, "elapsed_time": "0:46:50", "remaining_time": "6:21:20", "throughput": 1492.75, "total_tokens": 4194688} {"current_steps": 19890, "total_steps": 181800, "loss": 0.1189, "lr": 4.9986541949974784e-05, "epoch": 2.1881188118811883, "percentage": 10.94, "elapsed_time": "0:46:50", "remaining_time": "6:21:20", "throughput": 1492.77, "total_tokens": 4195776} {"current_steps": 19895, "total_steps": 181800, "loss": 0.1007, "lr": 4.9986463093798035e-05, "epoch": 2.1886688668866885, "percentage": 10.94, "elapsed_time": "0:46:51", "remaining_time": "6:21:19", "throughput": 1492.78, "total_tokens": 4196832} {"current_steps": 19900, "total_steps": 181800, "loss": 0.1023, "lr": 4.9986384007333045e-05, "epoch": 2.189218921892189, "percentage": 10.95, "elapsed_time": "0:46:52", "remaining_time": "6:21:18", "throughput": 1492.83, "total_tokens": 4197984} {"current_steps": 19905, "total_steps": 181800, "loss": 0.0511, "lr": 4.998630469058055e-05, "epoch": 2.18976897689769, "percentage": 10.95, "elapsed_time": "0:46:52", "remaining_time": "6:21:17", "throughput": 1492.84, "total_tokens": 4199040} {"current_steps": 19910, "total_steps": 181800, "loss": 0.1976, "lr": 4.998622514354127e-05, "epoch": 2.1903190319031904, "percentage": 10.95, "elapsed_time": "0:46:53", "remaining_time": "6:21:16", "throughput": 1492.86, "total_tokens": 4200128} {"current_steps": 19915, "total_steps": 181800, "loss": 0.0342, "lr": 4.9986145366215944e-05, "epoch": 2.190869086908691, "percentage": 10.95, "elapsed_time": "0:46:54", "remaining_time": "6:21:15", "throughput": 1492.87, "total_tokens": 4201184} {"current_steps": 19920, "total_steps": 181800, "loss": 0.0875, "lr": 4.99860653586053e-05, "epoch": 2.1914191419141913, "percentage": 10.96, "elapsed_time": "0:46:54", "remaining_time": "6:21:14", "throughput": 1492.88, "total_tokens": 4202240} {"current_steps": 19925, "total_steps": 181800, "loss": 0.0662, "lr": 4.998598512071009e-05, "epoch": 2.191969196919692, "percentage": 10.96, "elapsed_time": "0:46:55", "remaining_time": "6:21:14", "throughput": 1492.89, "total_tokens": 4203296} {"current_steps": 19930, "total_steps": 181800, "loss": 0.1133, "lr": 4.998590465253104e-05, "epoch": 2.1925192519251926, "percentage": 10.96, "elapsed_time": "0:46:56", "remaining_time": "6:21:13", "throughput": 1492.9, "total_tokens": 4204352} {"current_steps": 19935, "total_steps": 181800, "loss": 0.1105, "lr": 4.998582395406889e-05, "epoch": 2.1930693069306932, "percentage": 10.97, "elapsed_time": "0:46:56", "remaining_time": "6:21:12", "throughput": 1492.93, "total_tokens": 4205472} {"current_steps": 19940, "total_steps": 181800, "loss": 0.0419, "lr": 4.99857430253244e-05, "epoch": 2.1936193619361934, "percentage": 10.97, "elapsed_time": "0:46:57", "remaining_time": "6:21:11", "throughput": 1492.94, "total_tokens": 4206528} {"current_steps": 19945, "total_steps": 181800, "loss": 0.1226, "lr": 4.9985661866298296e-05, "epoch": 2.194169416941694, "percentage": 10.97, "elapsed_time": "0:46:58", "remaining_time": "6:21:10", "throughput": 1492.95, "total_tokens": 4207584} {"current_steps": 19950, "total_steps": 181800, "loss": 0.0224, "lr": 4.998558047699135e-05, "epoch": 2.1947194719471947, "percentage": 10.97, "elapsed_time": "0:46:58", "remaining_time": "6:21:09", "throughput": 1492.96, "total_tokens": 4208640} {"current_steps": 19955, "total_steps": 181800, "loss": 0.0316, "lr": 4.998549885740428e-05, "epoch": 2.1952695269526954, "percentage": 10.98, "elapsed_time": "0:46:59", "remaining_time": "6:21:08", "throughput": 1492.95, "total_tokens": 4209632} {"current_steps": 19960, "total_steps": 181800, "loss": 0.0527, "lr": 4.998541700753787e-05, "epoch": 2.1958195819581956, "percentage": 10.98, "elapsed_time": "0:47:00", "remaining_time": "6:21:08", "throughput": 1492.94, "total_tokens": 4210624} {"current_steps": 19965, "total_steps": 181800, "loss": 0.0458, "lr": 4.998533492739286e-05, "epoch": 2.1963696369636962, "percentage": 10.98, "elapsed_time": "0:47:01", "remaining_time": "6:21:07", "throughput": 1492.95, "total_tokens": 4211680} {"current_steps": 19970, "total_steps": 181800, "loss": 0.0675, "lr": 4.998525261697e-05, "epoch": 2.196919691969197, "percentage": 10.98, "elapsed_time": "0:47:01", "remaining_time": "6:21:06", "throughput": 1492.98, "total_tokens": 4212800} {"current_steps": 19975, "total_steps": 181800, "loss": 0.1697, "lr": 4.998517007627006e-05, "epoch": 2.1974697469746975, "percentage": 10.99, "elapsed_time": "0:47:02", "remaining_time": "6:21:05", "throughput": 1492.98, "total_tokens": 4213824} {"current_steps": 19980, "total_steps": 181800, "loss": 0.0926, "lr": 4.9985087305293796e-05, "epoch": 2.198019801980198, "percentage": 10.99, "elapsed_time": "0:47:03", "remaining_time": "6:21:04", "throughput": 1493.0, "total_tokens": 4214912} {"current_steps": 19985, "total_steps": 181800, "loss": 0.1352, "lr": 4.998500430404197e-05, "epoch": 2.1985698569856984, "percentage": 10.99, "elapsed_time": "0:47:03", "remaining_time": "6:21:03", "throughput": 1493.03, "total_tokens": 4216032} {"current_steps": 19990, "total_steps": 181800, "loss": 0.1154, "lr": 4.9984921072515345e-05, "epoch": 2.199119911991199, "percentage": 11.0, "elapsed_time": "0:47:04", "remaining_time": "6:21:02", "throughput": 1493.03, "total_tokens": 4217056} {"current_steps": 19995, "total_steps": 181800, "loss": 0.0939, "lr": 4.9984837610714696e-05, "epoch": 2.1996699669966997, "percentage": 11.0, "elapsed_time": "0:47:05", "remaining_time": "6:21:02", "throughput": 1493.03, "total_tokens": 4218080} {"current_steps": 20000, "total_steps": 181800, "loss": 0.0687, "lr": 4.9984753918640795e-05, "epoch": 2.2002200220022003, "percentage": 11.0, "elapsed_time": "0:47:05", "remaining_time": "6:21:01", "throughput": 1493.03, "total_tokens": 4219104} {"current_steps": 20005, "total_steps": 181800, "loss": 0.0675, "lr": 4.9984669996294394e-05, "epoch": 2.200770077007701, "percentage": 11.0, "elapsed_time": "0:47:06", "remaining_time": "6:21:00", "throughput": 1493.06, "total_tokens": 4220224} {"current_steps": 20010, "total_steps": 181800, "loss": 0.0797, "lr": 4.998458584367628e-05, "epoch": 2.201320132013201, "percentage": 11.01, "elapsed_time": "0:47:07", "remaining_time": "6:20:59", "throughput": 1493.08, "total_tokens": 4221312} {"current_steps": 20015, "total_steps": 181800, "loss": 0.053, "lr": 4.998450146078723e-05, "epoch": 2.201870187018702, "percentage": 11.01, "elapsed_time": "0:47:07", "remaining_time": "6:20:58", "throughput": 1493.09, "total_tokens": 4222368} {"current_steps": 20020, "total_steps": 181800, "loss": 0.1045, "lr": 4.9984416847628024e-05, "epoch": 2.2024202420242025, "percentage": 11.01, "elapsed_time": "0:47:08", "remaining_time": "6:20:57", "throughput": 1493.09, "total_tokens": 4223392} {"current_steps": 20025, "total_steps": 181800, "loss": 0.0524, "lr": 4.998433200419943e-05, "epoch": 2.202970297029703, "percentage": 11.01, "elapsed_time": "0:47:09", "remaining_time": "6:20:57", "throughput": 1493.09, "total_tokens": 4224416} {"current_steps": 20030, "total_steps": 181800, "loss": 0.0303, "lr": 4.998424693050223e-05, "epoch": 2.2035203520352034, "percentage": 11.02, "elapsed_time": "0:47:09", "remaining_time": "6:20:56", "throughput": 1493.1, "total_tokens": 4225472} {"current_steps": 20035, "total_steps": 181800, "loss": 0.0397, "lr": 4.998416162653723e-05, "epoch": 2.204070407040704, "percentage": 11.02, "elapsed_time": "0:47:10", "remaining_time": "6:20:55", "throughput": 1493.12, "total_tokens": 4226560} {"current_steps": 20040, "total_steps": 181800, "loss": 0.084, "lr": 4.998407609230519e-05, "epoch": 2.2046204620462047, "percentage": 11.02, "elapsed_time": "0:47:11", "remaining_time": "6:20:54", "throughput": 1493.13, "total_tokens": 4227616} {"current_steps": 20045, "total_steps": 181800, "loss": 0.0877, "lr": 4.9983990327806915e-05, "epoch": 2.2051705170517053, "percentage": 11.03, "elapsed_time": "0:47:12", "remaining_time": "6:20:53", "throughput": 1493.13, "total_tokens": 4228640} {"current_steps": 20050, "total_steps": 181800, "loss": 0.0749, "lr": 4.998390433304318e-05, "epoch": 2.2057205720572055, "percentage": 11.03, "elapsed_time": "0:47:12", "remaining_time": "6:20:52", "throughput": 1493.14, "total_tokens": 4229696} {"current_steps": 20055, "total_steps": 181800, "loss": 0.1016, "lr": 4.9983818108014804e-05, "epoch": 2.206270627062706, "percentage": 11.03, "elapsed_time": "0:47:13", "remaining_time": "6:20:51", "throughput": 1493.14, "total_tokens": 4230720} {"current_steps": 20060, "total_steps": 181800, "loss": 0.0877, "lr": 4.998373165272255e-05, "epoch": 2.206820682068207, "percentage": 11.03, "elapsed_time": "0:47:14", "remaining_time": "6:20:51", "throughput": 1493.14, "total_tokens": 4231744} {"current_steps": 20065, "total_steps": 181800, "loss": 0.0797, "lr": 4.998364496716724e-05, "epoch": 2.2073707370737075, "percentage": 11.04, "elapsed_time": "0:47:14", "remaining_time": "6:20:50", "throughput": 1493.16, "total_tokens": 4232832} {"current_steps": 20070, "total_steps": 181800, "loss": 0.0635, "lr": 4.998355805134966e-05, "epoch": 2.207920792079208, "percentage": 11.04, "elapsed_time": "0:47:15", "remaining_time": "6:20:49", "throughput": 1493.16, "total_tokens": 4233856} {"current_steps": 20075, "total_steps": 181800, "loss": 0.2158, "lr": 4.99834709052706e-05, "epoch": 2.2084708470847083, "percentage": 11.04, "elapsed_time": "0:47:16", "remaining_time": "6:20:48", "throughput": 1493.16, "total_tokens": 4234880} {"current_steps": 20080, "total_steps": 181800, "loss": 0.0911, "lr": 4.9983383528930896e-05, "epoch": 2.209020902090209, "percentage": 11.05, "elapsed_time": "0:47:16", "remaining_time": "6:20:47", "throughput": 1493.18, "total_tokens": 4235968} {"current_steps": 20085, "total_steps": 181800, "loss": 0.0434, "lr": 4.9983295922331316e-05, "epoch": 2.2095709570957096, "percentage": 11.05, "elapsed_time": "0:47:17", "remaining_time": "6:20:46", "throughput": 1493.19, "total_tokens": 4237024} {"current_steps": 20090, "total_steps": 181800, "loss": 0.1377, "lr": 4.99832080854727e-05, "epoch": 2.2101210121012103, "percentage": 11.05, "elapsed_time": "0:47:18", "remaining_time": "6:20:45", "throughput": 1493.19, "total_tokens": 4238048} {"current_steps": 20095, "total_steps": 181800, "loss": 0.0082, "lr": 4.998312001835584e-05, "epoch": 2.2106710671067105, "percentage": 11.05, "elapsed_time": "0:47:18", "remaining_time": "6:20:45", "throughput": 1493.21, "total_tokens": 4239136} {"current_steps": 20100, "total_steps": 181800, "loss": 0.0644, "lr": 4.998303172098155e-05, "epoch": 2.211221122112211, "percentage": 11.06, "elapsed_time": "0:47:19", "remaining_time": "6:20:44", "throughput": 1493.2, "total_tokens": 4240128} {"current_steps": 20105, "total_steps": 181800, "loss": 0.1195, "lr": 4.998294319335065e-05, "epoch": 2.2117711771177118, "percentage": 11.06, "elapsed_time": "0:47:20", "remaining_time": "6:20:43", "throughput": 1493.21, "total_tokens": 4241184} {"current_steps": 20110, "total_steps": 181800, "loss": 0.0363, "lr": 4.998285443546394e-05, "epoch": 2.2123212321232124, "percentage": 11.06, "elapsed_time": "0:47:21", "remaining_time": "6:20:42", "throughput": 1493.23, "total_tokens": 4242272} {"current_steps": 20115, "total_steps": 181800, "loss": 0.0683, "lr": 4.9982765447322256e-05, "epoch": 2.212871287128713, "percentage": 11.06, "elapsed_time": "0:47:21", "remaining_time": "6:20:41", "throughput": 1493.24, "total_tokens": 4243328} {"current_steps": 20120, "total_steps": 181800, "loss": 0.0444, "lr": 4.998267622892641e-05, "epoch": 2.2134213421342133, "percentage": 11.07, "elapsed_time": "0:47:22", "remaining_time": "6:20:40", "throughput": 1493.25, "total_tokens": 4244384} {"current_steps": 20125, "total_steps": 181800, "loss": 0.112, "lr": 4.998258678027722e-05, "epoch": 2.213971397139714, "percentage": 11.07, "elapsed_time": "0:47:23", "remaining_time": "6:20:39", "throughput": 1493.26, "total_tokens": 4245440} {"current_steps": 20130, "total_steps": 181800, "loss": 0.0269, "lr": 4.998249710137552e-05, "epoch": 2.2145214521452146, "percentage": 11.07, "elapsed_time": "0:47:23", "remaining_time": "6:20:39", "throughput": 1493.26, "total_tokens": 4246464} {"current_steps": 20135, "total_steps": 181800, "loss": 0.0769, "lr": 4.998240719222214e-05, "epoch": 2.215071507150715, "percentage": 11.08, "elapsed_time": "0:47:24", "remaining_time": "6:20:38", "throughput": 1493.27, "total_tokens": 4247520} {"current_steps": 20140, "total_steps": 181800, "loss": 0.176, "lr": 4.998231705281788e-05, "epoch": 2.2156215621562154, "percentage": 11.08, "elapsed_time": "0:47:25", "remaining_time": "6:20:37", "throughput": 1493.28, "total_tokens": 4248576} {"current_steps": 20145, "total_steps": 181800, "loss": 0.0394, "lr": 4.998222668316361e-05, "epoch": 2.216171617161716, "percentage": 11.08, "elapsed_time": "0:47:25", "remaining_time": "6:20:36", "throughput": 1493.29, "total_tokens": 4249632} {"current_steps": 20150, "total_steps": 181800, "loss": 0.064, "lr": 4.9982136083260136e-05, "epoch": 2.2167216721672167, "percentage": 11.08, "elapsed_time": "0:47:26", "remaining_time": "6:20:35", "throughput": 1493.33, "total_tokens": 4250752} {"current_steps": 20155, "total_steps": 181800, "loss": 0.1191, "lr": 4.99820452531083e-05, "epoch": 2.2172717271727174, "percentage": 11.09, "elapsed_time": "0:47:27", "remaining_time": "6:20:34", "throughput": 1493.32, "total_tokens": 4251776} {"current_steps": 20160, "total_steps": 181800, "loss": 0.0506, "lr": 4.9981954192708945e-05, "epoch": 2.217821782178218, "percentage": 11.09, "elapsed_time": "0:47:27", "remaining_time": "6:20:33", "throughput": 1493.33, "total_tokens": 4252832} {"current_steps": 20165, "total_steps": 181800, "loss": 0.0576, "lr": 4.99818629020629e-05, "epoch": 2.218371837183718, "percentage": 11.09, "elapsed_time": "0:47:28", "remaining_time": "6:20:33", "throughput": 1493.32, "total_tokens": 4253824} {"current_steps": 20170, "total_steps": 181800, "loss": 0.0506, "lr": 4.998177138117102e-05, "epoch": 2.218921892189219, "percentage": 11.09, "elapsed_time": "0:47:29", "remaining_time": "6:20:32", "throughput": 1493.32, "total_tokens": 4254848} {"current_steps": 20175, "total_steps": 181800, "loss": 0.1389, "lr": 4.998167963003414e-05, "epoch": 2.2194719471947195, "percentage": 11.1, "elapsed_time": "0:47:29", "remaining_time": "6:20:31", "throughput": 1493.33, "total_tokens": 4255904} {"current_steps": 20180, "total_steps": 181800, "loss": 0.0924, "lr": 4.99815876486531e-05, "epoch": 2.22002200220022, "percentage": 11.1, "elapsed_time": "0:47:30", "remaining_time": "6:20:30", "throughput": 1493.34, "total_tokens": 4256960} {"current_steps": 20185, "total_steps": 181800, "loss": 0.158, "lr": 4.998149543702876e-05, "epoch": 2.2205720572057204, "percentage": 11.1, "elapsed_time": "0:47:31", "remaining_time": "6:20:29", "throughput": 1493.38, "total_tokens": 4258112} {"current_steps": 20190, "total_steps": 181800, "loss": 0.055, "lr": 4.9981402995161955e-05, "epoch": 2.221122112211221, "percentage": 11.11, "elapsed_time": "0:47:32", "remaining_time": "6:20:28", "throughput": 1493.4, "total_tokens": 4259200} {"current_steps": 20195, "total_steps": 181800, "loss": 0.1137, "lr": 4.998131032305355e-05, "epoch": 2.2216721672167217, "percentage": 11.11, "elapsed_time": "0:47:32", "remaining_time": "6:20:28", "throughput": 1493.43, "total_tokens": 4260320} {"current_steps": 20200, "total_steps": 181800, "loss": 0.0503, "lr": 4.9981217420704394e-05, "epoch": 2.2222222222222223, "percentage": 11.11, "elapsed_time": "0:47:33", "remaining_time": "6:20:27", "throughput": 1493.43, "total_tokens": 4261344} {"current_steps": 20205, "total_steps": 181800, "loss": 0.1625, "lr": 4.998112428811536e-05, "epoch": 2.222772277227723, "percentage": 11.11, "elapsed_time": "0:47:34", "remaining_time": "6:20:26", "throughput": 1493.44, "total_tokens": 4262400} {"current_steps": 20210, "total_steps": 181800, "loss": 0.0683, "lr": 4.998103092528727e-05, "epoch": 2.223322332233223, "percentage": 11.12, "elapsed_time": "0:47:34", "remaining_time": "6:20:25", "throughput": 1493.44, "total_tokens": 4263424} {"current_steps": 20215, "total_steps": 181800, "loss": 0.0828, "lr": 4.998093733222101e-05, "epoch": 2.223872387238724, "percentage": 11.12, "elapsed_time": "0:47:35", "remaining_time": "6:20:24", "throughput": 1493.45, "total_tokens": 4264480} {"current_steps": 20220, "total_steps": 181800, "loss": 0.0735, "lr": 4.9980843508917444e-05, "epoch": 2.2244224422442245, "percentage": 11.12, "elapsed_time": "0:47:36", "remaining_time": "6:20:23", "throughput": 1493.45, "total_tokens": 4265504} {"current_steps": 20225, "total_steps": 181800, "loss": 0.0328, "lr": 4.998074945537742e-05, "epoch": 2.224972497249725, "percentage": 11.12, "elapsed_time": "0:47:36", "remaining_time": "6:20:22", "throughput": 1493.45, "total_tokens": 4266528} {"current_steps": 20230, "total_steps": 181800, "loss": 0.1171, "lr": 4.9980655171601825e-05, "epoch": 2.2255225522552253, "percentage": 11.13, "elapsed_time": "0:47:37", "remaining_time": "6:20:22", "throughput": 1493.49, "total_tokens": 4267680} {"current_steps": 20235, "total_steps": 181800, "loss": 0.0487, "lr": 4.998056065759151e-05, "epoch": 2.226072607260726, "percentage": 11.13, "elapsed_time": "0:47:38", "remaining_time": "6:20:21", "throughput": 1493.5, "total_tokens": 4268736} {"current_steps": 20240, "total_steps": 181800, "loss": 0.1374, "lr": 4.9980465913347365e-05, "epoch": 2.2266226622662266, "percentage": 11.13, "elapsed_time": "0:47:38", "remaining_time": "6:20:20", "throughput": 1493.5, "total_tokens": 4269760} {"current_steps": 20245, "total_steps": 181800, "loss": 0.1061, "lr": 4.998037093887025e-05, "epoch": 2.2271727172717273, "percentage": 11.14, "elapsed_time": "0:47:39", "remaining_time": "6:20:19", "throughput": 1493.54, "total_tokens": 4270912} {"current_steps": 20250, "total_steps": 181800, "loss": 0.0937, "lr": 4.998027573416103e-05, "epoch": 2.227722772277228, "percentage": 11.14, "elapsed_time": "0:47:40", "remaining_time": "6:20:18", "throughput": 1493.59, "total_tokens": 4272096} {"current_steps": 20255, "total_steps": 181800, "loss": 0.0702, "lr": 4.998018029922061e-05, "epoch": 2.228272827282728, "percentage": 11.14, "elapsed_time": "0:47:40", "remaining_time": "6:20:17", "throughput": 1493.6, "total_tokens": 4273152} {"current_steps": 20260, "total_steps": 181800, "loss": 0.0672, "lr": 4.998008463404985e-05, "epoch": 2.228822882288229, "percentage": 11.14, "elapsed_time": "0:47:41", "remaining_time": "6:20:16", "throughput": 1493.6, "total_tokens": 4274176} {"current_steps": 20265, "total_steps": 181800, "loss": 0.0872, "lr": 4.997998873864963e-05, "epoch": 2.2293729372937294, "percentage": 11.15, "elapsed_time": "0:47:42", "remaining_time": "6:20:16", "throughput": 1493.62, "total_tokens": 4275264} {"current_steps": 20270, "total_steps": 181800, "loss": 0.1471, "lr": 4.997989261302085e-05, "epoch": 2.22992299229923, "percentage": 11.15, "elapsed_time": "0:47:43", "remaining_time": "6:20:15", "throughput": 1493.64, "total_tokens": 4276352} {"current_steps": 20275, "total_steps": 181800, "loss": 0.1787, "lr": 4.997979625716438e-05, "epoch": 2.2304730473047303, "percentage": 11.15, "elapsed_time": "0:47:43", "remaining_time": "6:20:14", "throughput": 1493.65, "total_tokens": 4277408} {"current_steps": 20280, "total_steps": 181800, "loss": 0.1104, "lr": 4.997969967108111e-05, "epoch": 2.231023102310231, "percentage": 11.16, "elapsed_time": "0:47:44", "remaining_time": "6:20:13", "throughput": 1493.67, "total_tokens": 4278496} {"current_steps": 20285, "total_steps": 181800, "loss": 0.0165, "lr": 4.997960285477195e-05, "epoch": 2.2315731573157316, "percentage": 11.16, "elapsed_time": "0:47:45", "remaining_time": "6:20:12", "throughput": 1493.67, "total_tokens": 4279520} {"current_steps": 20290, "total_steps": 181800, "loss": 0.0477, "lr": 4.997950580823777e-05, "epoch": 2.2321232123212322, "percentage": 11.16, "elapsed_time": "0:47:45", "remaining_time": "6:20:11", "throughput": 1493.68, "total_tokens": 4280576} {"current_steps": 20295, "total_steps": 181800, "loss": 0.136, "lr": 4.997940853147947e-05, "epoch": 2.232673267326733, "percentage": 11.16, "elapsed_time": "0:47:46", "remaining_time": "6:20:11", "throughput": 1493.7, "total_tokens": 4281664} {"current_steps": 20300, "total_steps": 181800, "loss": 0.0606, "lr": 4.997931102449794e-05, "epoch": 2.233223322332233, "percentage": 11.17, "elapsed_time": "0:47:47", "remaining_time": "6:20:10", "throughput": 1493.7, "total_tokens": 4282688} {"current_steps": 20305, "total_steps": 181800, "loss": 0.0487, "lr": 4.99792132872941e-05, "epoch": 2.2337733773377337, "percentage": 11.17, "elapsed_time": "0:47:47", "remaining_time": "6:20:09", "throughput": 1493.7, "total_tokens": 4283712} {"current_steps": 20310, "total_steps": 181800, "loss": 0.0564, "lr": 4.997911531986883e-05, "epoch": 2.2343234323432344, "percentage": 11.17, "elapsed_time": "0:47:48", "remaining_time": "6:20:08", "throughput": 1493.7, "total_tokens": 4284736} {"current_steps": 20315, "total_steps": 181800, "loss": 0.0292, "lr": 4.9979017122223036e-05, "epoch": 2.234873487348735, "percentage": 11.17, "elapsed_time": "0:47:49", "remaining_time": "6:20:07", "throughput": 1493.71, "total_tokens": 4285792} {"current_steps": 20320, "total_steps": 181800, "loss": 0.0504, "lr": 4.9978918694357636e-05, "epoch": 2.2354235423542352, "percentage": 11.18, "elapsed_time": "0:47:49", "remaining_time": "6:20:06", "throughput": 1493.72, "total_tokens": 4286848} {"current_steps": 20325, "total_steps": 181800, "loss": 0.0894, "lr": 4.997882003627353e-05, "epoch": 2.235973597359736, "percentage": 11.18, "elapsed_time": "0:47:50", "remaining_time": "6:20:05", "throughput": 1493.71, "total_tokens": 4287840} {"current_steps": 20330, "total_steps": 181800, "loss": 0.0355, "lr": 4.997872114797162e-05, "epoch": 2.2365236523652365, "percentage": 11.18, "elapsed_time": "0:47:51", "remaining_time": "6:20:05", "throughput": 1493.69, "total_tokens": 4288800} {"current_steps": 20335, "total_steps": 181800, "loss": 0.0655, "lr": 4.997862202945282e-05, "epoch": 2.237073707370737, "percentage": 11.19, "elapsed_time": "0:47:51", "remaining_time": "6:20:04", "throughput": 1493.71, "total_tokens": 4289888} {"current_steps": 20340, "total_steps": 181800, "loss": 0.0934, "lr": 4.997852268071805e-05, "epoch": 2.237623762376238, "percentage": 11.19, "elapsed_time": "0:47:52", "remaining_time": "6:20:03", "throughput": 1493.73, "total_tokens": 4290976} {"current_steps": 20345, "total_steps": 181800, "loss": 0.0444, "lr": 4.997842310176822e-05, "epoch": 2.238173817381738, "percentage": 11.19, "elapsed_time": "0:47:53", "remaining_time": "6:20:02", "throughput": 1493.74, "total_tokens": 4292032} {"current_steps": 20350, "total_steps": 181800, "loss": 0.0663, "lr": 4.997832329260426e-05, "epoch": 2.2387238723872387, "percentage": 11.19, "elapsed_time": "0:47:54", "remaining_time": "6:20:01", "throughput": 1493.75, "total_tokens": 4293088} {"current_steps": 20355, "total_steps": 181800, "loss": 0.0547, "lr": 4.997822325322708e-05, "epoch": 2.2392739273927393, "percentage": 11.2, "elapsed_time": "0:47:54", "remaining_time": "6:20:00", "throughput": 1493.75, "total_tokens": 4294112} {"current_steps": 20360, "total_steps": 181800, "loss": 0.0517, "lr": 4.9978122983637585e-05, "epoch": 2.23982398239824, "percentage": 11.2, "elapsed_time": "0:47:55", "remaining_time": "6:19:59", "throughput": 1493.77, "total_tokens": 4295200} {"current_steps": 20365, "total_steps": 181800, "loss": 0.0462, "lr": 4.997802248383673e-05, "epoch": 2.24037403740374, "percentage": 11.2, "elapsed_time": "0:47:56", "remaining_time": "6:19:59", "throughput": 1493.77, "total_tokens": 4296224} {"current_steps": 20370, "total_steps": 181800, "loss": 0.1005, "lr": 4.997792175382542e-05, "epoch": 2.240924092409241, "percentage": 11.2, "elapsed_time": "0:47:56", "remaining_time": "6:19:58", "throughput": 1493.78, "total_tokens": 4297280} {"current_steps": 20375, "total_steps": 181800, "loss": 0.0534, "lr": 4.99778207936046e-05, "epoch": 2.2414741474147415, "percentage": 11.21, "elapsed_time": "0:47:57", "remaining_time": "6:19:57", "throughput": 1493.79, "total_tokens": 4298336} {"current_steps": 20380, "total_steps": 181800, "loss": 0.1389, "lr": 4.9977719603175184e-05, "epoch": 2.242024202420242, "percentage": 11.21, "elapsed_time": "0:47:58", "remaining_time": "6:19:56", "throughput": 1493.82, "total_tokens": 4299456} {"current_steps": 20385, "total_steps": 181800, "loss": 0.1131, "lr": 4.997761818253811e-05, "epoch": 2.2425742574257423, "percentage": 11.21, "elapsed_time": "0:47:58", "remaining_time": "6:19:55", "throughput": 1493.82, "total_tokens": 4300480} {"current_steps": 20390, "total_steps": 181800, "loss": 0.083, "lr": 4.9977516531694315e-05, "epoch": 2.243124312431243, "percentage": 11.22, "elapsed_time": "0:47:59", "remaining_time": "6:19:54", "throughput": 1493.81, "total_tokens": 4301472} {"current_steps": 20395, "total_steps": 181800, "loss": 0.0876, "lr": 4.9977414650644745e-05, "epoch": 2.2436743674367436, "percentage": 11.22, "elapsed_time": "0:48:00", "remaining_time": "6:19:53", "throughput": 1493.8, "total_tokens": 4302496} {"current_steps": 20400, "total_steps": 181800, "loss": 0.0667, "lr": 4.997731253939032e-05, "epoch": 2.2442244224422443, "percentage": 11.22, "elapsed_time": "0:48:00", "remaining_time": "6:19:53", "throughput": 1493.82, "total_tokens": 4303584} {"current_steps": 20405, "total_steps": 181800, "loss": 0.0391, "lr": 4.9977210197931997e-05, "epoch": 2.244774477447745, "percentage": 11.22, "elapsed_time": "0:48:01", "remaining_time": "6:19:52", "throughput": 1493.85, "total_tokens": 4304704} {"current_steps": 20410, "total_steps": 181800, "loss": 0.1096, "lr": 4.997710762627071e-05, "epoch": 2.245324532453245, "percentage": 11.23, "elapsed_time": "0:48:02", "remaining_time": "6:19:51", "throughput": 1493.85, "total_tokens": 4305728} {"current_steps": 20415, "total_steps": 181800, "loss": 0.0267, "lr": 4.99770048244074e-05, "epoch": 2.245874587458746, "percentage": 11.23, "elapsed_time": "0:48:02", "remaining_time": "6:19:50", "throughput": 1493.85, "total_tokens": 4306752} {"current_steps": 20420, "total_steps": 181800, "loss": 0.1567, "lr": 4.9976901792343034e-05, "epoch": 2.2464246424642464, "percentage": 11.23, "elapsed_time": "0:48:03", "remaining_time": "6:19:49", "throughput": 1493.85, "total_tokens": 4307776} {"current_steps": 20425, "total_steps": 181800, "loss": 0.0592, "lr": 4.997679853007854e-05, "epoch": 2.246974697469747, "percentage": 11.23, "elapsed_time": "0:48:04", "remaining_time": "6:19:48", "throughput": 1493.86, "total_tokens": 4308832} {"current_steps": 20430, "total_steps": 181800, "loss": 0.1172, "lr": 4.997669503761488e-05, "epoch": 2.2475247524752477, "percentage": 11.24, "elapsed_time": "0:48:05", "remaining_time": "6:19:48", "throughput": 1493.87, "total_tokens": 4309888} {"current_steps": 20435, "total_steps": 181800, "loss": 0.0653, "lr": 4.9976591314953014e-05, "epoch": 2.248074807480748, "percentage": 11.24, "elapsed_time": "0:48:05", "remaining_time": "6:19:47", "throughput": 1493.88, "total_tokens": 4310944} {"current_steps": 20440, "total_steps": 181800, "loss": 0.0737, "lr": 4.997648736209389e-05, "epoch": 2.2486248624862486, "percentage": 11.24, "elapsed_time": "0:48:06", "remaining_time": "6:19:46", "throughput": 1493.9, "total_tokens": 4312032} {"current_steps": 20445, "total_steps": 181800, "loss": 0.1709, "lr": 4.9976383179038464e-05, "epoch": 2.2491749174917492, "percentage": 11.25, "elapsed_time": "0:48:07", "remaining_time": "6:19:45", "throughput": 1493.91, "total_tokens": 4313088} {"current_steps": 20450, "total_steps": 181800, "loss": 0.0504, "lr": 4.997627876578769e-05, "epoch": 2.24972497249725, "percentage": 11.25, "elapsed_time": "0:48:07", "remaining_time": "6:19:44", "throughput": 1493.9, "total_tokens": 4314112} {"current_steps": 20455, "total_steps": 181800, "loss": 0.0772, "lr": 4.997617412234255e-05, "epoch": 2.25027502750275, "percentage": 11.25, "elapsed_time": "0:48:08", "remaining_time": "6:19:43", "throughput": 1493.9, "total_tokens": 4315136} {"current_steps": 20460, "total_steps": 181800, "loss": 0.0746, "lr": 4.9976069248704e-05, "epoch": 2.2508250825082508, "percentage": 11.25, "elapsed_time": "0:48:09", "remaining_time": "6:19:43", "throughput": 1493.92, "total_tokens": 4316224} {"current_steps": 20465, "total_steps": 181800, "loss": 0.0311, "lr": 4.9975964144873e-05, "epoch": 2.2513751375137514, "percentage": 11.26, "elapsed_time": "0:48:09", "remaining_time": "6:19:42", "throughput": 1493.92, "total_tokens": 4317248} {"current_steps": 20470, "total_steps": 181800, "loss": 0.0815, "lr": 4.997585881085052e-05, "epoch": 2.251925192519252, "percentage": 11.26, "elapsed_time": "0:48:10", "remaining_time": "6:19:41", "throughput": 1493.93, "total_tokens": 4318304} {"current_steps": 20475, "total_steps": 181800, "loss": 0.1036, "lr": 4.997575324663754e-05, "epoch": 2.2524752475247523, "percentage": 11.26, "elapsed_time": "0:48:11", "remaining_time": "6:19:40", "throughput": 1493.95, "total_tokens": 4319392} {"current_steps": 20480, "total_steps": 181800, "loss": 0.1084, "lr": 4.997564745223502e-05, "epoch": 2.253025302530253, "percentage": 11.27, "elapsed_time": "0:48:11", "remaining_time": "6:19:39", "throughput": 1493.93, "total_tokens": 4320384} {"current_steps": 20485, "total_steps": 181800, "loss": 0.0705, "lr": 4.9975541427643945e-05, "epoch": 2.2535753575357536, "percentage": 11.27, "elapsed_time": "0:48:12", "remaining_time": "6:19:38", "throughput": 1493.96, "total_tokens": 4321472} {"current_steps": 20490, "total_steps": 181800, "loss": 0.0612, "lr": 4.9975435172865294e-05, "epoch": 2.254125412541254, "percentage": 11.27, "elapsed_time": "0:48:13", "remaining_time": "6:19:38", "throughput": 1493.99, "total_tokens": 4322592} {"current_steps": 20495, "total_steps": 181800, "loss": 0.0567, "lr": 4.997532868790003e-05, "epoch": 2.254675467546755, "percentage": 11.27, "elapsed_time": "0:48:14", "remaining_time": "6:19:37", "throughput": 1494.01, "total_tokens": 4323680} {"current_steps": 20500, "total_steps": 181800, "loss": 0.0714, "lr": 4.997522197274915e-05, "epoch": 2.255225522552255, "percentage": 11.28, "elapsed_time": "0:48:14", "remaining_time": "6:19:36", "throughput": 1494.0, "total_tokens": 4324672} {"current_steps": 20505, "total_steps": 181800, "loss": 0.1012, "lr": 4.997511502741364e-05, "epoch": 2.2557755775577557, "percentage": 11.28, "elapsed_time": "0:48:15", "remaining_time": "6:19:35", "throughput": 1493.99, "total_tokens": 4325664} {"current_steps": 20510, "total_steps": 181800, "loss": 0.0802, "lr": 4.997500785189448e-05, "epoch": 2.2563256325632564, "percentage": 11.28, "elapsed_time": "0:48:16", "remaining_time": "6:19:34", "throughput": 1494.01, "total_tokens": 4326752} {"current_steps": 20515, "total_steps": 181800, "loss": 0.1359, "lr": 4.997490044619265e-05, "epoch": 2.256875687568757, "percentage": 11.28, "elapsed_time": "0:48:16", "remaining_time": "6:19:33", "throughput": 1493.98, "total_tokens": 4327712} {"current_steps": 20520, "total_steps": 181800, "loss": 0.0872, "lr": 4.997479281030915e-05, "epoch": 2.2574257425742577, "percentage": 11.29, "elapsed_time": "0:48:17", "remaining_time": "6:19:32", "throughput": 1493.97, "total_tokens": 4328704} {"current_steps": 20525, "total_steps": 181800, "loss": 0.0984, "lr": 4.9974684944244964e-05, "epoch": 2.257975797579758, "percentage": 11.29, "elapsed_time": "0:48:18", "remaining_time": "6:19:32", "throughput": 1493.97, "total_tokens": 4329728} {"current_steps": 20530, "total_steps": 181800, "loss": 0.1377, "lr": 4.99745768480011e-05, "epoch": 2.2585258525852585, "percentage": 11.29, "elapsed_time": "0:48:18", "remaining_time": "6:19:31", "throughput": 1493.98, "total_tokens": 4330784} {"current_steps": 20535, "total_steps": 181800, "loss": 0.1259, "lr": 4.9974468521578535e-05, "epoch": 2.259075907590759, "percentage": 11.3, "elapsed_time": "0:48:19", "remaining_time": "6:19:30", "throughput": 1494.0, "total_tokens": 4331872} {"current_steps": 20540, "total_steps": 181800, "loss": 0.0381, "lr": 4.997435996497828e-05, "epoch": 2.25962596259626, "percentage": 11.3, "elapsed_time": "0:48:20", "remaining_time": "6:19:29", "throughput": 1494.02, "total_tokens": 4332960} {"current_steps": 20545, "total_steps": 181800, "loss": 0.107, "lr": 4.997425117820134e-05, "epoch": 2.26017601760176, "percentage": 11.3, "elapsed_time": "0:48:20", "remaining_time": "6:19:28", "throughput": 1494.01, "total_tokens": 4333952} {"current_steps": 20550, "total_steps": 181800, "loss": 0.078, "lr": 4.997414216124871e-05, "epoch": 2.2607260726072607, "percentage": 11.3, "elapsed_time": "0:48:21", "remaining_time": "6:19:27", "throughput": 1493.99, "total_tokens": 4334944} {"current_steps": 20555, "total_steps": 181800, "loss": 0.0292, "lr": 4.9974032914121386e-05, "epoch": 2.2612761276127613, "percentage": 11.31, "elapsed_time": "0:48:22", "remaining_time": "6:19:27", "throughput": 1494.01, "total_tokens": 4336032} {"current_steps": 20560, "total_steps": 181800, "loss": 0.0237, "lr": 4.997392343682039e-05, "epoch": 2.261826182618262, "percentage": 11.31, "elapsed_time": "0:48:22", "remaining_time": "6:19:26", "throughput": 1494.01, "total_tokens": 4337056} {"current_steps": 20565, "total_steps": 181800, "loss": 0.1142, "lr": 4.997381372934673e-05, "epoch": 2.262376237623762, "percentage": 11.31, "elapsed_time": "0:48:23", "remaining_time": "6:19:25", "throughput": 1494.02, "total_tokens": 4338112} {"current_steps": 20570, "total_steps": 181800, "loss": 0.0848, "lr": 4.99737037917014e-05, "epoch": 2.262926292629263, "percentage": 11.31, "elapsed_time": "0:48:24", "remaining_time": "6:19:24", "throughput": 1494.02, "total_tokens": 4339136} {"current_steps": 20575, "total_steps": 181800, "loss": 0.0882, "lr": 4.997359362388544e-05, "epoch": 2.2634763476347635, "percentage": 11.32, "elapsed_time": "0:48:25", "remaining_time": "6:19:23", "throughput": 1494.03, "total_tokens": 4340192} {"current_steps": 20580, "total_steps": 181800, "loss": 0.0738, "lr": 4.9973483225899844e-05, "epoch": 2.264026402640264, "percentage": 11.32, "elapsed_time": "0:48:25", "remaining_time": "6:19:22", "throughput": 1494.04, "total_tokens": 4341248} {"current_steps": 20585, "total_steps": 181800, "loss": 0.1401, "lr": 4.997337259774564e-05, "epoch": 2.2645764576457648, "percentage": 11.32, "elapsed_time": "0:48:26", "remaining_time": "6:19:21", "throughput": 1494.04, "total_tokens": 4342272} {"current_steps": 20590, "total_steps": 181800, "loss": 0.1371, "lr": 4.997326173942384e-05, "epoch": 2.265126512651265, "percentage": 11.33, "elapsed_time": "0:48:27", "remaining_time": "6:19:21", "throughput": 1494.05, "total_tokens": 4343328} {"current_steps": 20595, "total_steps": 181800, "loss": 0.0707, "lr": 4.997315065093546e-05, "epoch": 2.2656765676567656, "percentage": 11.33, "elapsed_time": "0:48:27", "remaining_time": "6:19:20", "throughput": 1494.05, "total_tokens": 4344352} {"current_steps": 20600, "total_steps": 181800, "loss": 0.018, "lr": 4.997303933228155e-05, "epoch": 2.2662266226622663, "percentage": 11.33, "elapsed_time": "0:48:28", "remaining_time": "6:19:19", "throughput": 1494.07, "total_tokens": 4345440} {"current_steps": 20605, "total_steps": 181800, "loss": 0.0904, "lr": 4.997292778346312e-05, "epoch": 2.266776677667767, "percentage": 11.33, "elapsed_time": "0:48:29", "remaining_time": "6:19:18", "throughput": 1494.1, "total_tokens": 4346560} {"current_steps": 20610, "total_steps": 181800, "loss": 0.0816, "lr": 4.9972816004481185e-05, "epoch": 2.2673267326732676, "percentage": 11.34, "elapsed_time": "0:48:29", "remaining_time": "6:19:17", "throughput": 1494.11, "total_tokens": 4347616} {"current_steps": 20615, "total_steps": 181800, "loss": 0.122, "lr": 4.99727039953368e-05, "epoch": 2.2678767876787678, "percentage": 11.34, "elapsed_time": "0:48:30", "remaining_time": "6:19:16", "throughput": 1494.12, "total_tokens": 4348672} {"current_steps": 20620, "total_steps": 181800, "loss": 0.1476, "lr": 4.997259175603098e-05, "epoch": 2.2684268426842684, "percentage": 11.34, "elapsed_time": "0:48:31", "remaining_time": "6:19:16", "throughput": 1494.12, "total_tokens": 4349696} {"current_steps": 20625, "total_steps": 181800, "loss": 0.037, "lr": 4.9972479286564764e-05, "epoch": 2.268976897689769, "percentage": 11.34, "elapsed_time": "0:48:31", "remaining_time": "6:19:15", "throughput": 1494.11, "total_tokens": 4350688} {"current_steps": 20630, "total_steps": 181800, "loss": 0.0259, "lr": 4.997236658693919e-05, "epoch": 2.2695269526952697, "percentage": 11.35, "elapsed_time": "0:48:32", "remaining_time": "6:19:14", "throughput": 1494.12, "total_tokens": 4351744} {"current_steps": 20635, "total_steps": 181800, "loss": 0.0498, "lr": 4.99722536571553e-05, "epoch": 2.27007700770077, "percentage": 11.35, "elapsed_time": "0:48:33", "remaining_time": "6:19:13", "throughput": 1494.13, "total_tokens": 4352800} {"current_steps": 20640, "total_steps": 181800, "loss": 0.1356, "lr": 4.9972140497214125e-05, "epoch": 2.2706270627062706, "percentage": 11.35, "elapsed_time": "0:48:33", "remaining_time": "6:19:12", "throughput": 1494.15, "total_tokens": 4353888} {"current_steps": 20645, "total_steps": 181800, "loss": 0.1122, "lr": 4.997202710711672e-05, "epoch": 2.271177117711771, "percentage": 11.36, "elapsed_time": "0:48:34", "remaining_time": "6:19:11", "throughput": 1494.16, "total_tokens": 4354944} {"current_steps": 20650, "total_steps": 181800, "loss": 0.0812, "lr": 4.997191348686412e-05, "epoch": 2.271727172717272, "percentage": 11.36, "elapsed_time": "0:48:35", "remaining_time": "6:19:10", "throughput": 1494.16, "total_tokens": 4355968} {"current_steps": 20655, "total_steps": 181800, "loss": 0.0474, "lr": 4.997179963645737e-05, "epoch": 2.272277227722772, "percentage": 11.36, "elapsed_time": "0:48:36", "remaining_time": "6:19:09", "throughput": 1494.15, "total_tokens": 4356960} {"current_steps": 20660, "total_steps": 181800, "loss": 0.052, "lr": 4.997168555589753e-05, "epoch": 2.2728272827282727, "percentage": 11.36, "elapsed_time": "0:48:36", "remaining_time": "6:19:09", "throughput": 1494.15, "total_tokens": 4357984} {"current_steps": 20665, "total_steps": 181800, "loss": 0.1029, "lr": 4.9971571245185655e-05, "epoch": 2.2733773377337734, "percentage": 11.37, "elapsed_time": "0:48:37", "remaining_time": "6:19:08", "throughput": 1494.14, "total_tokens": 4358976} {"current_steps": 20670, "total_steps": 181800, "loss": 0.0791, "lr": 4.9971456704322784e-05, "epoch": 2.273927392739274, "percentage": 11.37, "elapsed_time": "0:48:38", "remaining_time": "6:19:07", "throughput": 1494.14, "total_tokens": 4360000} {"current_steps": 20675, "total_steps": 181800, "loss": 0.0551, "lr": 4.997134193330998e-05, "epoch": 2.2744774477447747, "percentage": 11.37, "elapsed_time": "0:48:38", "remaining_time": "6:19:06", "throughput": 1494.15, "total_tokens": 4361056} {"current_steps": 20680, "total_steps": 181800, "loss": 0.0342, "lr": 4.99712269321483e-05, "epoch": 2.275027502750275, "percentage": 11.38, "elapsed_time": "0:48:39", "remaining_time": "6:19:05", "throughput": 1494.17, "total_tokens": 4362144} {"current_steps": 20685, "total_steps": 181800, "loss": 0.0192, "lr": 4.9971111700838805e-05, "epoch": 2.2755775577557755, "percentage": 11.38, "elapsed_time": "0:48:40", "remaining_time": "6:19:04", "throughput": 1494.2, "total_tokens": 4363264} {"current_steps": 20690, "total_steps": 181800, "loss": 0.201, "lr": 4.997099623938255e-05, "epoch": 2.276127612761276, "percentage": 11.38, "elapsed_time": "0:48:40", "remaining_time": "6:19:04", "throughput": 1494.22, "total_tokens": 4364352} {"current_steps": 20695, "total_steps": 181800, "loss": 0.1172, "lr": 4.997088054778061e-05, "epoch": 2.276677667766777, "percentage": 11.38, "elapsed_time": "0:48:41", "remaining_time": "6:19:03", "throughput": 1494.25, "total_tokens": 4365472} {"current_steps": 20700, "total_steps": 181800, "loss": 0.0327, "lr": 4.9970764626034036e-05, "epoch": 2.2772277227722775, "percentage": 11.39, "elapsed_time": "0:48:42", "remaining_time": "6:19:02", "throughput": 1494.23, "total_tokens": 4366464} {"current_steps": 20705, "total_steps": 181800, "loss": 0.028, "lr": 4.997064847414392e-05, "epoch": 2.2777777777777777, "percentage": 11.39, "elapsed_time": "0:48:42", "remaining_time": "6:19:01", "throughput": 1494.24, "total_tokens": 4367520} {"current_steps": 20710, "total_steps": 181800, "loss": 0.0463, "lr": 4.997053209211131e-05, "epoch": 2.2783278327832783, "percentage": 11.39, "elapsed_time": "0:48:43", "remaining_time": "6:19:00", "throughput": 1494.24, "total_tokens": 4368544} {"current_steps": 20715, "total_steps": 181800, "loss": 0.0972, "lr": 4.997041547993729e-05, "epoch": 2.278877887788779, "percentage": 11.39, "elapsed_time": "0:48:44", "remaining_time": "6:18:59", "throughput": 1494.25, "total_tokens": 4369600} {"current_steps": 20720, "total_steps": 181800, "loss": 0.0512, "lr": 4.9970298637622936e-05, "epoch": 2.279427942794279, "percentage": 11.4, "elapsed_time": "0:48:44", "remaining_time": "6:18:59", "throughput": 1494.26, "total_tokens": 4370656} {"current_steps": 20725, "total_steps": 181800, "loss": 0.2009, "lr": 4.997018156516933e-05, "epoch": 2.27997799779978, "percentage": 11.4, "elapsed_time": "0:48:45", "remaining_time": "6:18:58", "throughput": 1494.28, "total_tokens": 4371744} {"current_steps": 20730, "total_steps": 181800, "loss": 0.0819, "lr": 4.997006426257752e-05, "epoch": 2.2805280528052805, "percentage": 11.4, "elapsed_time": "0:48:46", "remaining_time": "6:18:57", "throughput": 1494.29, "total_tokens": 4372800} {"current_steps": 20735, "total_steps": 181800, "loss": 0.0788, "lr": 4.9969946729848626e-05, "epoch": 2.281078107810781, "percentage": 11.41, "elapsed_time": "0:48:47", "remaining_time": "6:18:56", "throughput": 1494.27, "total_tokens": 4373792} {"current_steps": 20740, "total_steps": 181800, "loss": 0.0796, "lr": 4.996982896698371e-05, "epoch": 2.281628162816282, "percentage": 11.41, "elapsed_time": "0:48:47", "remaining_time": "6:18:55", "throughput": 1494.27, "total_tokens": 4374816} {"current_steps": 20745, "total_steps": 181800, "loss": 0.074, "lr": 4.9969710973983865e-05, "epoch": 2.282178217821782, "percentage": 11.41, "elapsed_time": "0:48:48", "remaining_time": "6:18:54", "throughput": 1494.28, "total_tokens": 4375872} {"current_steps": 20750, "total_steps": 181800, "loss": 0.1029, "lr": 4.996959275085017e-05, "epoch": 2.2827282728272826, "percentage": 11.41, "elapsed_time": "0:48:49", "remaining_time": "6:18:54", "throughput": 1494.29, "total_tokens": 4376928} {"current_steps": 20755, "total_steps": 181800, "loss": 0.0432, "lr": 4.996947429758373e-05, "epoch": 2.2832783278327833, "percentage": 11.42, "elapsed_time": "0:48:49", "remaining_time": "6:18:53", "throughput": 1494.28, "total_tokens": 4377920} {"current_steps": 20760, "total_steps": 181800, "loss": 0.035, "lr": 4.9969355614185616e-05, "epoch": 2.283828382838284, "percentage": 11.42, "elapsed_time": "0:48:50", "remaining_time": "6:18:52", "throughput": 1494.28, "total_tokens": 4378976} {"current_steps": 20765, "total_steps": 181800, "loss": 0.0699, "lr": 4.9969236700656934e-05, "epoch": 2.2843784378437846, "percentage": 11.42, "elapsed_time": "0:48:51", "remaining_time": "6:18:51", "throughput": 1494.33, "total_tokens": 4380128} {"current_steps": 20770, "total_steps": 181800, "loss": 0.1382, "lr": 4.9969117556998785e-05, "epoch": 2.284928492849285, "percentage": 11.42, "elapsed_time": "0:48:51", "remaining_time": "6:18:50", "throughput": 1494.34, "total_tokens": 4381184} {"current_steps": 20775, "total_steps": 181800, "loss": 0.0441, "lr": 4.9968998183212254e-05, "epoch": 2.2854785478547854, "percentage": 11.43, "elapsed_time": "0:48:52", "remaining_time": "6:18:49", "throughput": 1494.36, "total_tokens": 4382272} {"current_steps": 20780, "total_steps": 181800, "loss": 0.1171, "lr": 4.996887857929845e-05, "epoch": 2.286028602860286, "percentage": 11.43, "elapsed_time": "0:48:53", "remaining_time": "6:18:49", "throughput": 1494.37, "total_tokens": 4383328} {"current_steps": 20785, "total_steps": 181800, "loss": 0.0836, "lr": 4.996875874525848e-05, "epoch": 2.2865786578657867, "percentage": 11.43, "elapsed_time": "0:48:53", "remaining_time": "6:18:48", "throughput": 1494.38, "total_tokens": 4384384} {"current_steps": 20790, "total_steps": 181800, "loss": 0.1838, "lr": 4.996863868109344e-05, "epoch": 2.287128712871287, "percentage": 11.44, "elapsed_time": "0:48:54", "remaining_time": "6:18:47", "throughput": 1494.4, "total_tokens": 4385472} {"current_steps": 20795, "total_steps": 181800, "loss": 0.0376, "lr": 4.996851838680443e-05, "epoch": 2.2876787678767876, "percentage": 11.44, "elapsed_time": "0:48:55", "remaining_time": "6:18:46", "throughput": 1494.42, "total_tokens": 4386560} {"current_steps": 20800, "total_steps": 181800, "loss": 0.0694, "lr": 4.996839786239257e-05, "epoch": 2.2882288228822882, "percentage": 11.44, "elapsed_time": "0:48:55", "remaining_time": "6:18:45", "throughput": 1494.44, "total_tokens": 4387648} {"current_steps": 20805, "total_steps": 181800, "loss": 0.086, "lr": 4.996827710785897e-05, "epoch": 2.288778877887789, "percentage": 11.44, "elapsed_time": "0:48:56", "remaining_time": "6:18:44", "throughput": 1494.46, "total_tokens": 4388736} {"current_steps": 20810, "total_steps": 181800, "loss": 0.1892, "lr": 4.9968156123204744e-05, "epoch": 2.289328932893289, "percentage": 11.45, "elapsed_time": "0:48:57", "remaining_time": "6:18:43", "throughput": 1494.49, "total_tokens": 4389856} {"current_steps": 20815, "total_steps": 181800, "loss": 0.0499, "lr": 4.9968034908431e-05, "epoch": 2.2898789878987897, "percentage": 11.45, "elapsed_time": "0:48:58", "remaining_time": "6:18:43", "throughput": 1494.52, "total_tokens": 4390944} {"current_steps": 20820, "total_steps": 181800, "loss": 0.0658, "lr": 4.9967913463538864e-05, "epoch": 2.2904290429042904, "percentage": 11.45, "elapsed_time": "0:48:58", "remaining_time": "6:18:42", "throughput": 1494.53, "total_tokens": 4392000} {"current_steps": 20825, "total_steps": 181800, "loss": 0.0899, "lr": 4.996779178852944e-05, "epoch": 2.290979097909791, "percentage": 11.45, "elapsed_time": "0:48:59", "remaining_time": "6:18:41", "throughput": 1494.5, "total_tokens": 4392960} {"current_steps": 20830, "total_steps": 181800, "loss": 0.0732, "lr": 4.9967669883403866e-05, "epoch": 2.2915291529152917, "percentage": 11.46, "elapsed_time": "0:49:00", "remaining_time": "6:18:40", "throughput": 1494.49, "total_tokens": 4393952} {"current_steps": 20835, "total_steps": 181800, "loss": 0.1262, "lr": 4.9967547748163264e-05, "epoch": 2.292079207920792, "percentage": 11.46, "elapsed_time": "0:49:00", "remaining_time": "6:18:39", "throughput": 1494.51, "total_tokens": 4395040} {"current_steps": 20840, "total_steps": 181800, "loss": 0.1187, "lr": 4.996742538280875e-05, "epoch": 2.2926292629262925, "percentage": 11.46, "elapsed_time": "0:49:01", "remaining_time": "6:18:38", "throughput": 1494.5, "total_tokens": 4396064} {"current_steps": 20845, "total_steps": 181800, "loss": 0.0968, "lr": 4.9967302787341455e-05, "epoch": 2.293179317931793, "percentage": 11.47, "elapsed_time": "0:49:02", "remaining_time": "6:18:38", "throughput": 1494.53, "total_tokens": 4397184} {"current_steps": 20850, "total_steps": 181800, "loss": 0.0707, "lr": 4.996717996176251e-05, "epoch": 2.293729372937294, "percentage": 11.47, "elapsed_time": "0:49:02", "remaining_time": "6:18:37", "throughput": 1494.53, "total_tokens": 4398208} {"current_steps": 20855, "total_steps": 181800, "loss": 0.0528, "lr": 4.996705690607305e-05, "epoch": 2.2942794279427945, "percentage": 11.47, "elapsed_time": "0:49:03", "remaining_time": "6:18:36", "throughput": 1494.54, "total_tokens": 4399264} {"current_steps": 20860, "total_steps": 181800, "loss": 0.0701, "lr": 4.996693362027421e-05, "epoch": 2.2948294829482947, "percentage": 11.47, "elapsed_time": "0:49:04", "remaining_time": "6:18:35", "throughput": 1494.55, "total_tokens": 4400320} {"current_steps": 20865, "total_steps": 181800, "loss": 0.1012, "lr": 4.996681010436712e-05, "epoch": 2.2953795379537953, "percentage": 11.48, "elapsed_time": "0:49:04", "remaining_time": "6:18:34", "throughput": 1494.54, "total_tokens": 4401344} {"current_steps": 20870, "total_steps": 181800, "loss": 0.0425, "lr": 4.996668635835292e-05, "epoch": 2.295929592959296, "percentage": 11.48, "elapsed_time": "0:49:05", "remaining_time": "6:18:33", "throughput": 1494.54, "total_tokens": 4402368} {"current_steps": 20875, "total_steps": 181800, "loss": 0.0726, "lr": 4.996656238223276e-05, "epoch": 2.2964796479647966, "percentage": 11.48, "elapsed_time": "0:49:06", "remaining_time": "6:18:33", "throughput": 1494.55, "total_tokens": 4403424} {"current_steps": 20880, "total_steps": 181800, "loss": 0.013, "lr": 4.996643817600777e-05, "epoch": 2.297029702970297, "percentage": 11.49, "elapsed_time": "0:49:07", "remaining_time": "6:18:32", "throughput": 1494.56, "total_tokens": 4404480} {"current_steps": 20885, "total_steps": 181800, "loss": 0.2096, "lr": 4.9966313739679096e-05, "epoch": 2.2975797579757975, "percentage": 11.49, "elapsed_time": "0:49:07", "remaining_time": "6:18:31", "throughput": 1494.57, "total_tokens": 4405536} {"current_steps": 20890, "total_steps": 181800, "loss": 0.0405, "lr": 4.9966189073247885e-05, "epoch": 2.298129812981298, "percentage": 11.49, "elapsed_time": "0:49:08", "remaining_time": "6:18:30", "throughput": 1494.58, "total_tokens": 4406592} {"current_steps": 20895, "total_steps": 181800, "loss": 0.0281, "lr": 4.99660641767153e-05, "epoch": 2.298679867986799, "percentage": 11.49, "elapsed_time": "0:49:09", "remaining_time": "6:18:29", "throughput": 1494.59, "total_tokens": 4407680} {"current_steps": 20900, "total_steps": 181800, "loss": 0.092, "lr": 4.996593905008248e-05, "epoch": 2.299229922992299, "percentage": 11.5, "elapsed_time": "0:49:09", "remaining_time": "6:18:29", "throughput": 1494.6, "total_tokens": 4408736} {"current_steps": 20905, "total_steps": 181800, "loss": 0.0108, "lr": 4.996581369335057e-05, "epoch": 2.2997799779977997, "percentage": 11.5, "elapsed_time": "0:49:10", "remaining_time": "6:18:28", "throughput": 1494.6, "total_tokens": 4409760} {"current_steps": 20910, "total_steps": 181800, "loss": 0.0935, "lr": 4.9965688106520745e-05, "epoch": 2.3003300330033003, "percentage": 11.5, "elapsed_time": "0:49:11", "remaining_time": "6:18:27", "throughput": 1494.6, "total_tokens": 4410784} {"current_steps": 20915, "total_steps": 181800, "loss": 0.0919, "lr": 4.9965562289594145e-05, "epoch": 2.300880088008801, "percentage": 11.5, "elapsed_time": "0:49:11", "remaining_time": "6:18:26", "throughput": 1494.62, "total_tokens": 4411872} {"current_steps": 20920, "total_steps": 181800, "loss": 0.0862, "lr": 4.996543624257194e-05, "epoch": 2.3014301430143016, "percentage": 11.51, "elapsed_time": "0:49:12", "remaining_time": "6:18:25", "throughput": 1494.6, "total_tokens": 4412864} {"current_steps": 20925, "total_steps": 181800, "loss": 0.1253, "lr": 4.996530996545529e-05, "epoch": 2.301980198019802, "percentage": 11.51, "elapsed_time": "0:49:13", "remaining_time": "6:18:24", "throughput": 1494.59, "total_tokens": 4413856} {"current_steps": 20930, "total_steps": 181800, "loss": 0.111, "lr": 4.9965183458245354e-05, "epoch": 2.3025302530253025, "percentage": 11.51, "elapsed_time": "0:49:13", "remaining_time": "6:18:24", "throughput": 1494.59, "total_tokens": 4414880} {"current_steps": 20935, "total_steps": 181800, "loss": 0.1087, "lr": 4.9965056720943304e-05, "epoch": 2.303080308030803, "percentage": 11.52, "elapsed_time": "0:49:14", "remaining_time": "6:18:23", "throughput": 1494.58, "total_tokens": 4415904} {"current_steps": 20940, "total_steps": 181800, "loss": 0.1444, "lr": 4.9964929753550304e-05, "epoch": 2.3036303630363038, "percentage": 11.52, "elapsed_time": "0:49:15", "remaining_time": "6:18:22", "throughput": 1494.59, "total_tokens": 4416960} {"current_steps": 20945, "total_steps": 181800, "loss": 0.1305, "lr": 4.9964802556067526e-05, "epoch": 2.3041804180418044, "percentage": 11.52, "elapsed_time": "0:49:15", "remaining_time": "6:18:21", "throughput": 1494.58, "total_tokens": 4417952} {"current_steps": 20950, "total_steps": 181800, "loss": 0.0546, "lr": 4.996467512849614e-05, "epoch": 2.3047304730473046, "percentage": 11.52, "elapsed_time": "0:49:16", "remaining_time": "6:18:20", "throughput": 1494.62, "total_tokens": 4419104} {"current_steps": 20955, "total_steps": 181800, "loss": 0.0401, "lr": 4.996454747083733e-05, "epoch": 2.3052805280528053, "percentage": 11.53, "elapsed_time": "0:49:17", "remaining_time": "6:18:19", "throughput": 1494.63, "total_tokens": 4420160} {"current_steps": 20960, "total_steps": 181800, "loss": 0.1505, "lr": 4.996441958309226e-05, "epoch": 2.305830583058306, "percentage": 11.53, "elapsed_time": "0:49:18", "remaining_time": "6:18:19", "throughput": 1494.63, "total_tokens": 4421184} {"current_steps": 20965, "total_steps": 181800, "loss": 0.1324, "lr": 4.9964291465262114e-05, "epoch": 2.3063806380638066, "percentage": 11.53, "elapsed_time": "0:49:18", "remaining_time": "6:18:18", "throughput": 1494.66, "total_tokens": 4422304} {"current_steps": 20970, "total_steps": 181800, "loss": 0.0617, "lr": 4.996416311734807e-05, "epoch": 2.3069306930693068, "percentage": 11.53, "elapsed_time": "0:49:19", "remaining_time": "6:18:17", "throughput": 1494.69, "total_tokens": 4423392} {"current_steps": 20975, "total_steps": 181800, "loss": 0.1334, "lr": 4.9964034539351324e-05, "epoch": 2.3074807480748074, "percentage": 11.54, "elapsed_time": "0:49:20", "remaining_time": "6:18:16", "throughput": 1494.69, "total_tokens": 4424448} {"current_steps": 20980, "total_steps": 181800, "loss": 0.0559, "lr": 4.996390573127304e-05, "epoch": 2.308030803080308, "percentage": 11.54, "elapsed_time": "0:49:20", "remaining_time": "6:18:15", "throughput": 1494.7, "total_tokens": 4425504} {"current_steps": 20985, "total_steps": 181800, "loss": 0.0602, "lr": 4.996377669311442e-05, "epoch": 2.3085808580858087, "percentage": 11.54, "elapsed_time": "0:49:21", "remaining_time": "6:18:14", "throughput": 1494.7, "total_tokens": 4426528} {"current_steps": 20990, "total_steps": 181800, "loss": 0.0557, "lr": 4.9963647424876645e-05, "epoch": 2.309130913091309, "percentage": 11.55, "elapsed_time": "0:49:22", "remaining_time": "6:18:13", "throughput": 1494.71, "total_tokens": 4427584} {"current_steps": 20995, "total_steps": 181800, "loss": 0.0383, "lr": 4.996351792656092e-05, "epoch": 2.3096809680968096, "percentage": 11.55, "elapsed_time": "0:49:22", "remaining_time": "6:18:13", "throughput": 1494.71, "total_tokens": 4428608} {"current_steps": 21000, "total_steps": 181800, "loss": 0.1274, "lr": 4.996338819816842e-05, "epoch": 2.31023102310231, "percentage": 11.55, "elapsed_time": "0:49:23", "remaining_time": "6:18:12", "throughput": 1494.71, "total_tokens": 4429664} {"current_steps": 21005, "total_steps": 181800, "loss": 0.1183, "lr": 4.996325823970035e-05, "epoch": 2.310781078107811, "percentage": 11.55, "elapsed_time": "0:49:24", "remaining_time": "6:18:11", "throughput": 1494.73, "total_tokens": 4430752} {"current_steps": 21010, "total_steps": 181800, "loss": 0.0519, "lr": 4.9963128051157916e-05, "epoch": 2.3113311331133115, "percentage": 11.56, "elapsed_time": "0:49:24", "remaining_time": "6:18:10", "throughput": 1494.74, "total_tokens": 4431808} {"current_steps": 21015, "total_steps": 181800, "loss": 0.0379, "lr": 4.99629976325423e-05, "epoch": 2.3118811881188117, "percentage": 11.56, "elapsed_time": "0:49:25", "remaining_time": "6:18:09", "throughput": 1494.73, "total_tokens": 4432800} {"current_steps": 21020, "total_steps": 181800, "loss": 0.0705, "lr": 4.996286698385472e-05, "epoch": 2.3124312431243124, "percentage": 11.56, "elapsed_time": "0:49:26", "remaining_time": "6:18:09", "throughput": 1494.74, "total_tokens": 4433856} {"current_steps": 21025, "total_steps": 181800, "loss": 0.0524, "lr": 4.9962736105096365e-05, "epoch": 2.312981298129813, "percentage": 11.56, "elapsed_time": "0:49:26", "remaining_time": "6:18:08", "throughput": 1494.76, "total_tokens": 4434944} {"current_steps": 21030, "total_steps": 181800, "loss": 0.1505, "lr": 4.9962604996268456e-05, "epoch": 2.3135313531353137, "percentage": 11.57, "elapsed_time": "0:49:27", "remaining_time": "6:18:07", "throughput": 1494.77, "total_tokens": 4436000} {"current_steps": 21035, "total_steps": 181800, "loss": 0.0403, "lr": 4.996247365737219e-05, "epoch": 2.3140814081408143, "percentage": 11.57, "elapsed_time": "0:49:28", "remaining_time": "6:18:06", "throughput": 1494.77, "total_tokens": 4437056} {"current_steps": 21040, "total_steps": 181800, "loss": 0.0826, "lr": 4.996234208840879e-05, "epoch": 2.3146314631463145, "percentage": 11.57, "elapsed_time": "0:49:29", "remaining_time": "6:18:05", "throughput": 1494.81, "total_tokens": 4438176} {"current_steps": 21045, "total_steps": 181800, "loss": 0.1677, "lr": 4.996221028937945e-05, "epoch": 2.315181518151815, "percentage": 11.58, "elapsed_time": "0:49:29", "remaining_time": "6:18:04", "throughput": 1494.82, "total_tokens": 4439264} {"current_steps": 21050, "total_steps": 181800, "loss": 0.0944, "lr": 4.9962078260285405e-05, "epoch": 2.315731573157316, "percentage": 11.58, "elapsed_time": "0:49:30", "remaining_time": "6:18:04", "throughput": 1494.82, "total_tokens": 4440288} {"current_steps": 21055, "total_steps": 181800, "loss": 0.1412, "lr": 4.9961946001127854e-05, "epoch": 2.3162816281628165, "percentage": 11.58, "elapsed_time": "0:49:31", "remaining_time": "6:18:03", "throughput": 1494.84, "total_tokens": 4441376} {"current_steps": 21060, "total_steps": 181800, "loss": 0.0543, "lr": 4.996181351190804e-05, "epoch": 2.3168316831683167, "percentage": 11.58, "elapsed_time": "0:49:31", "remaining_time": "6:18:02", "throughput": 1494.87, "total_tokens": 4442496} {"current_steps": 21065, "total_steps": 181800, "loss": 0.0162, "lr": 4.996168079262715e-05, "epoch": 2.3173817381738173, "percentage": 11.59, "elapsed_time": "0:49:32", "remaining_time": "6:18:01", "throughput": 1494.9, "total_tokens": 4443616} {"current_steps": 21070, "total_steps": 181800, "loss": 0.089, "lr": 4.996154784328644e-05, "epoch": 2.317931793179318, "percentage": 11.59, "elapsed_time": "0:49:33", "remaining_time": "6:18:00", "throughput": 1494.89, "total_tokens": 4444608} {"current_steps": 21075, "total_steps": 181800, "loss": 0.1311, "lr": 4.996141466388712e-05, "epoch": 2.3184818481848186, "percentage": 11.59, "elapsed_time": "0:49:33", "remaining_time": "6:17:59", "throughput": 1494.9, "total_tokens": 4445664} {"current_steps": 21080, "total_steps": 181800, "loss": 0.0262, "lr": 4.9961281254430415e-05, "epoch": 2.319031903190319, "percentage": 11.6, "elapsed_time": "0:49:34", "remaining_time": "6:17:59", "throughput": 1494.89, "total_tokens": 4446656} {"current_steps": 21085, "total_steps": 181800, "loss": 0.0874, "lr": 4.9961147614917555e-05, "epoch": 2.3195819581958195, "percentage": 11.6, "elapsed_time": "0:49:35", "remaining_time": "6:17:58", "throughput": 1494.92, "total_tokens": 4447776} {"current_steps": 21090, "total_steps": 181800, "loss": 0.0843, "lr": 4.996101374534978e-05, "epoch": 2.32013201320132, "percentage": 11.6, "elapsed_time": "0:49:35", "remaining_time": "6:17:57", "throughput": 1494.94, "total_tokens": 4448864} {"current_steps": 21095, "total_steps": 181800, "loss": 0.1055, "lr": 4.996087964572832e-05, "epoch": 2.3206820682068208, "percentage": 11.6, "elapsed_time": "0:49:36", "remaining_time": "6:17:56", "throughput": 1494.95, "total_tokens": 4449920} {"current_steps": 21100, "total_steps": 181800, "loss": 0.1192, "lr": 4.99607453160544e-05, "epoch": 2.3212321232123214, "percentage": 11.61, "elapsed_time": "0:49:37", "remaining_time": "6:17:55", "throughput": 1494.97, "total_tokens": 4451008} {"current_steps": 21105, "total_steps": 181800, "loss": 0.0335, "lr": 4.9960610756329276e-05, "epoch": 2.3217821782178216, "percentage": 11.61, "elapsed_time": "0:49:38", "remaining_time": "6:17:54", "throughput": 1494.96, "total_tokens": 4452000} {"current_steps": 21110, "total_steps": 181800, "loss": 0.1826, "lr": 4.996047596655418e-05, "epoch": 2.3223322332233223, "percentage": 11.61, "elapsed_time": "0:49:38", "remaining_time": "6:17:53", "throughput": 1494.97, "total_tokens": 4453056} {"current_steps": 21115, "total_steps": 181800, "loss": 0.0727, "lr": 4.996034094673035e-05, "epoch": 2.322882288228823, "percentage": 11.61, "elapsed_time": "0:49:39", "remaining_time": "6:17:53", "throughput": 1494.98, "total_tokens": 4454112} {"current_steps": 21120, "total_steps": 181800, "loss": 0.0559, "lr": 4.9960205696859044e-05, "epoch": 2.3234323432343236, "percentage": 11.62, "elapsed_time": "0:49:40", "remaining_time": "6:17:52", "throughput": 1494.99, "total_tokens": 4455168} {"current_steps": 21125, "total_steps": 181800, "loss": 0.0645, "lr": 4.996007021694148e-05, "epoch": 2.323982398239824, "percentage": 11.62, "elapsed_time": "0:49:40", "remaining_time": "6:17:51", "throughput": 1495.01, "total_tokens": 4456256} {"current_steps": 21130, "total_steps": 181800, "loss": 0.2083, "lr": 4.995993450697894e-05, "epoch": 2.3245324532453244, "percentage": 11.62, "elapsed_time": "0:49:41", "remaining_time": "6:17:50", "throughput": 1495.02, "total_tokens": 4457312} {"current_steps": 21135, "total_steps": 181800, "loss": 0.268, "lr": 4.995979856697266e-05, "epoch": 2.325082508250825, "percentage": 11.63, "elapsed_time": "0:49:42", "remaining_time": "6:17:49", "throughput": 1495.03, "total_tokens": 4458368} {"current_steps": 21140, "total_steps": 181800, "loss": 0.0856, "lr": 4.995966239692389e-05, "epoch": 2.3256325632563257, "percentage": 11.63, "elapsed_time": "0:49:42", "remaining_time": "6:17:48", "throughput": 1495.03, "total_tokens": 4459392} {"current_steps": 21145, "total_steps": 181800, "loss": 0.1384, "lr": 4.995952599683389e-05, "epoch": 2.3261826182618264, "percentage": 11.63, "elapsed_time": "0:49:43", "remaining_time": "6:17:47", "throughput": 1495.04, "total_tokens": 4460448} {"current_steps": 21150, "total_steps": 181800, "loss": 0.0326, "lr": 4.9959389366703925e-05, "epoch": 2.3267326732673266, "percentage": 11.63, "elapsed_time": "0:49:44", "remaining_time": "6:17:47", "throughput": 1495.05, "total_tokens": 4461504} {"current_steps": 21155, "total_steps": 181800, "loss": 0.1397, "lr": 4.995925250653524e-05, "epoch": 2.3272827282728272, "percentage": 11.64, "elapsed_time": "0:49:44", "remaining_time": "6:17:46", "throughput": 1495.05, "total_tokens": 4462528} {"current_steps": 21160, "total_steps": 181800, "loss": 0.0972, "lr": 4.9959115416329096e-05, "epoch": 2.327832783278328, "percentage": 11.64, "elapsed_time": "0:49:45", "remaining_time": "6:17:45", "throughput": 1495.07, "total_tokens": 4463616} {"current_steps": 21165, "total_steps": 181800, "loss": 0.0603, "lr": 4.995897809608676e-05, "epoch": 2.3283828382838285, "percentage": 11.64, "elapsed_time": "0:49:46", "remaining_time": "6:17:44", "throughput": 1495.07, "total_tokens": 4464640} {"current_steps": 21170, "total_steps": 181800, "loss": 0.0448, "lr": 4.99588405458095e-05, "epoch": 2.3289328932893287, "percentage": 11.64, "elapsed_time": "0:49:46", "remaining_time": "6:17:43", "throughput": 1495.08, "total_tokens": 4465696} {"current_steps": 21175, "total_steps": 181800, "loss": 0.0799, "lr": 4.995870276549859e-05, "epoch": 2.3294829482948294, "percentage": 11.65, "elapsed_time": "0:49:47", "remaining_time": "6:17:42", "throughput": 1495.06, "total_tokens": 4466656} {"current_steps": 21180, "total_steps": 181800, "loss": 0.0975, "lr": 4.9958564755155285e-05, "epoch": 2.33003300330033, "percentage": 11.65, "elapsed_time": "0:49:48", "remaining_time": "6:17:41", "throughput": 1495.05, "total_tokens": 4467648} {"current_steps": 21185, "total_steps": 181800, "loss": 0.0686, "lr": 4.995842651478086e-05, "epoch": 2.3305830583058307, "percentage": 11.65, "elapsed_time": "0:49:48", "remaining_time": "6:17:41", "throughput": 1495.04, "total_tokens": 4468640} {"current_steps": 21190, "total_steps": 181800, "loss": 0.0399, "lr": 4.995828804437661e-05, "epoch": 2.3311331133113313, "percentage": 11.66, "elapsed_time": "0:49:49", "remaining_time": "6:17:40", "throughput": 1495.03, "total_tokens": 4469664} {"current_steps": 21195, "total_steps": 181800, "loss": 0.064, "lr": 4.9958149343943786e-05, "epoch": 2.3316831683168315, "percentage": 11.66, "elapsed_time": "0:49:50", "remaining_time": "6:17:39", "throughput": 1495.07, "total_tokens": 4470784} {"current_steps": 21200, "total_steps": 181800, "loss": 0.0311, "lr": 4.995801041348368e-05, "epoch": 2.332233223322332, "percentage": 11.66, "elapsed_time": "0:49:51", "remaining_time": "6:17:38", "throughput": 1495.11, "total_tokens": 4471936} {"current_steps": 21205, "total_steps": 181800, "loss": 0.0592, "lr": 4.9957871252997566e-05, "epoch": 2.332783278327833, "percentage": 11.66, "elapsed_time": "0:49:51", "remaining_time": "6:17:37", "throughput": 1495.1, "total_tokens": 4472928} {"current_steps": 21210, "total_steps": 181800, "loss": 0.0522, "lr": 4.995773186248673e-05, "epoch": 2.3333333333333335, "percentage": 11.67, "elapsed_time": "0:49:52", "remaining_time": "6:17:36", "throughput": 1495.11, "total_tokens": 4473984} {"current_steps": 21215, "total_steps": 181800, "loss": 0.0675, "lr": 4.9957592241952457e-05, "epoch": 2.333883388338834, "percentage": 11.67, "elapsed_time": "0:49:53", "remaining_time": "6:17:36", "throughput": 1495.09, "total_tokens": 4474976} {"current_steps": 21220, "total_steps": 181800, "loss": 0.0843, "lr": 4.995745239139602e-05, "epoch": 2.3344334433443343, "percentage": 11.67, "elapsed_time": "0:49:53", "remaining_time": "6:17:35", "throughput": 1495.09, "total_tokens": 4476000} {"current_steps": 21225, "total_steps": 181800, "loss": 0.1511, "lr": 4.995731231081873e-05, "epoch": 2.334983498349835, "percentage": 11.67, "elapsed_time": "0:49:54", "remaining_time": "6:17:34", "throughput": 1495.1, "total_tokens": 4477056} {"current_steps": 21230, "total_steps": 181800, "loss": 0.1059, "lr": 4.995717200022187e-05, "epoch": 2.3355335533553356, "percentage": 11.68, "elapsed_time": "0:49:55", "remaining_time": "6:17:33", "throughput": 1495.11, "total_tokens": 4478112} {"current_steps": 21235, "total_steps": 181800, "loss": 0.0776, "lr": 4.9957031459606726e-05, "epoch": 2.336083608360836, "percentage": 11.68, "elapsed_time": "0:49:55", "remaining_time": "6:17:32", "throughput": 1495.13, "total_tokens": 4479200} {"current_steps": 21240, "total_steps": 181800, "loss": 0.0856, "lr": 4.99568906889746e-05, "epoch": 2.3366336633663365, "percentage": 11.68, "elapsed_time": "0:49:56", "remaining_time": "6:17:31", "throughput": 1495.11, "total_tokens": 4480160} {"current_steps": 21245, "total_steps": 181800, "loss": 0.0839, "lr": 4.9956749688326786e-05, "epoch": 2.337183718371837, "percentage": 11.69, "elapsed_time": "0:49:57", "remaining_time": "6:17:30", "throughput": 1495.1, "total_tokens": 4481152} {"current_steps": 21250, "total_steps": 181800, "loss": 0.0759, "lr": 4.99566084576646e-05, "epoch": 2.337733773377338, "percentage": 11.69, "elapsed_time": "0:49:57", "remaining_time": "6:17:30", "throughput": 1495.11, "total_tokens": 4482208} {"current_steps": 21255, "total_steps": 181800, "loss": 0.115, "lr": 4.995646699698931e-05, "epoch": 2.3382838283828384, "percentage": 11.69, "elapsed_time": "0:49:58", "remaining_time": "6:17:29", "throughput": 1495.11, "total_tokens": 4483232} {"current_steps": 21260, "total_steps": 181800, "loss": 0.1318, "lr": 4.995632530630224e-05, "epoch": 2.3388338833883386, "percentage": 11.69, "elapsed_time": "0:49:59", "remaining_time": "6:17:28", "throughput": 1495.12, "total_tokens": 4484288} {"current_steps": 21265, "total_steps": 181800, "loss": 0.0853, "lr": 4.99561833856047e-05, "epoch": 2.3393839383938393, "percentage": 11.7, "elapsed_time": "0:49:59", "remaining_time": "6:17:27", "throughput": 1495.14, "total_tokens": 4485376} {"current_steps": 21270, "total_steps": 181800, "loss": 0.0909, "lr": 4.9956041234898e-05, "epoch": 2.33993399339934, "percentage": 11.7, "elapsed_time": "0:50:00", "remaining_time": "6:17:26", "throughput": 1495.17, "total_tokens": 4486528} {"current_steps": 21275, "total_steps": 181800, "loss": 0.1158, "lr": 4.995589885418344e-05, "epoch": 2.3404840484048406, "percentage": 11.7, "elapsed_time": "0:50:01", "remaining_time": "6:17:26", "throughput": 1495.19, "total_tokens": 4487616} {"current_steps": 21280, "total_steps": 181800, "loss": 0.09, "lr": 4.9955756243462334e-05, "epoch": 2.3410341034103412, "percentage": 11.71, "elapsed_time": "0:50:02", "remaining_time": "6:17:25", "throughput": 1495.21, "total_tokens": 4488704} {"current_steps": 21285, "total_steps": 181800, "loss": 0.0151, "lr": 4.995561340273599e-05, "epoch": 2.3415841584158414, "percentage": 11.71, "elapsed_time": "0:50:02", "remaining_time": "6:17:24", "throughput": 1495.24, "total_tokens": 4489824} {"current_steps": 21290, "total_steps": 181800, "loss": 0.0983, "lr": 4.9955470332005735e-05, "epoch": 2.342134213421342, "percentage": 11.71, "elapsed_time": "0:50:03", "remaining_time": "6:17:23", "throughput": 1495.24, "total_tokens": 4490848} {"current_steps": 21295, "total_steps": 181800, "loss": 0.1629, "lr": 4.995532703127289e-05, "epoch": 2.3426842684268427, "percentage": 11.71, "elapsed_time": "0:50:04", "remaining_time": "6:17:22", "throughput": 1495.22, "total_tokens": 4491840} {"current_steps": 21300, "total_steps": 181800, "loss": 0.1486, "lr": 4.995518350053877e-05, "epoch": 2.3432343234323434, "percentage": 11.72, "elapsed_time": "0:50:04", "remaining_time": "6:17:21", "throughput": 1495.25, "total_tokens": 4492960} {"current_steps": 21305, "total_steps": 181800, "loss": 0.0219, "lr": 4.99550397398047e-05, "epoch": 2.3437843784378436, "percentage": 11.72, "elapsed_time": "0:50:05", "remaining_time": "6:17:21", "throughput": 1495.27, "total_tokens": 4494048} {"current_steps": 21310, "total_steps": 181800, "loss": 0.0467, "lr": 4.9954895749072e-05, "epoch": 2.3443344334433442, "percentage": 11.72, "elapsed_time": "0:50:06", "remaining_time": "6:17:20", "throughput": 1495.3, "total_tokens": 4495168} {"current_steps": 21315, "total_steps": 181800, "loss": 0.1058, "lr": 4.9954751528342e-05, "epoch": 2.344884488448845, "percentage": 11.72, "elapsed_time": "0:50:06", "remaining_time": "6:17:19", "throughput": 1495.3, "total_tokens": 4496192} {"current_steps": 21320, "total_steps": 181800, "loss": 0.09, "lr": 4.995460707761603e-05, "epoch": 2.3454345434543455, "percentage": 11.73, "elapsed_time": "0:50:07", "remaining_time": "6:17:18", "throughput": 1495.31, "total_tokens": 4497248} {"current_steps": 21325, "total_steps": 181800, "loss": 0.0264, "lr": 4.995446239689542e-05, "epoch": 2.3459845984598457, "percentage": 11.73, "elapsed_time": "0:50:08", "remaining_time": "6:17:17", "throughput": 1495.32, "total_tokens": 4498304} {"current_steps": 21330, "total_steps": 181800, "loss": 0.0815, "lr": 4.9954317486181506e-05, "epoch": 2.3465346534653464, "percentage": 11.73, "elapsed_time": "0:50:08", "remaining_time": "6:17:16", "throughput": 1495.32, "total_tokens": 4499328} {"current_steps": 21335, "total_steps": 181800, "loss": 0.2027, "lr": 4.995417234547562e-05, "epoch": 2.347084708470847, "percentage": 11.74, "elapsed_time": "0:50:09", "remaining_time": "6:17:15", "throughput": 1495.33, "total_tokens": 4500384} {"current_steps": 21340, "total_steps": 181800, "loss": 0.0373, "lr": 4.99540269747791e-05, "epoch": 2.3476347634763477, "percentage": 11.74, "elapsed_time": "0:50:10", "remaining_time": "6:17:15", "throughput": 1495.37, "total_tokens": 4501536} {"current_steps": 21345, "total_steps": 181800, "loss": 0.1932, "lr": 4.995388137409329e-05, "epoch": 2.3481848184818483, "percentage": 11.74, "elapsed_time": "0:50:11", "remaining_time": "6:17:14", "throughput": 1495.39, "total_tokens": 4502624} {"current_steps": 21350, "total_steps": 181800, "loss": 0.0508, "lr": 4.9953735543419535e-05, "epoch": 2.3487348734873486, "percentage": 11.74, "elapsed_time": "0:50:11", "remaining_time": "6:17:13", "throughput": 1495.39, "total_tokens": 4503648} {"current_steps": 21355, "total_steps": 181800, "loss": 0.0417, "lr": 4.995358948275917e-05, "epoch": 2.349284928492849, "percentage": 11.75, "elapsed_time": "0:50:12", "remaining_time": "6:17:12", "throughput": 1495.39, "total_tokens": 4504672} {"current_steps": 21360, "total_steps": 181800, "loss": 0.0153, "lr": 4.995344319211354e-05, "epoch": 2.34983498349835, "percentage": 11.75, "elapsed_time": "0:50:13", "remaining_time": "6:17:11", "throughput": 1495.42, "total_tokens": 4505792} {"current_steps": 21365, "total_steps": 181800, "loss": 0.0858, "lr": 4.9953296671484004e-05, "epoch": 2.3503850385038505, "percentage": 11.75, "elapsed_time": "0:50:13", "remaining_time": "6:17:11", "throughput": 1495.43, "total_tokens": 4506880} {"current_steps": 21370, "total_steps": 181800, "loss": 0.0353, "lr": 4.99531499208719e-05, "epoch": 2.350935093509351, "percentage": 11.75, "elapsed_time": "0:50:14", "remaining_time": "6:17:10", "throughput": 1495.43, "total_tokens": 4507904} {"current_steps": 21375, "total_steps": 181800, "loss": 0.0351, "lr": 4.995300294027859e-05, "epoch": 2.3514851485148514, "percentage": 11.76, "elapsed_time": "0:50:15", "remaining_time": "6:17:09", "throughput": 1495.42, "total_tokens": 4508896} {"current_steps": 21380, "total_steps": 181800, "loss": 0.063, "lr": 4.995285572970543e-05, "epoch": 2.352035203520352, "percentage": 11.76, "elapsed_time": "0:50:15", "remaining_time": "6:17:08", "throughput": 1495.41, "total_tokens": 4509920} {"current_steps": 21385, "total_steps": 181800, "loss": 0.1526, "lr": 4.995270828915377e-05, "epoch": 2.3525852585258527, "percentage": 11.76, "elapsed_time": "0:50:16", "remaining_time": "6:17:07", "throughput": 1495.41, "total_tokens": 4510944} {"current_steps": 21390, "total_steps": 181800, "loss": 0.0583, "lr": 4.995256061862497e-05, "epoch": 2.3531353135313533, "percentage": 11.77, "elapsed_time": "0:50:17", "remaining_time": "6:17:07", "throughput": 1495.43, "total_tokens": 4512032} {"current_steps": 21395, "total_steps": 181800, "loss": 0.0285, "lr": 4.9952412718120387e-05, "epoch": 2.3536853685368535, "percentage": 11.77, "elapsed_time": "0:50:17", "remaining_time": "6:17:06", "throughput": 1495.43, "total_tokens": 4513088} {"current_steps": 21400, "total_steps": 181800, "loss": 0.0943, "lr": 4.9952264587641394e-05, "epoch": 2.354235423542354, "percentage": 11.77, "elapsed_time": "0:50:18", "remaining_time": "6:17:05", "throughput": 1495.45, "total_tokens": 4514176} {"current_steps": 21405, "total_steps": 181800, "loss": 0.1125, "lr": 4.995211622718935e-05, "epoch": 2.354785478547855, "percentage": 11.77, "elapsed_time": "0:50:19", "remaining_time": "6:17:04", "throughput": 1495.47, "total_tokens": 4515264} {"current_steps": 21410, "total_steps": 181800, "loss": 0.1201, "lr": 4.9951967636765626e-05, "epoch": 2.3553355335533555, "percentage": 11.78, "elapsed_time": "0:50:19", "remaining_time": "6:17:03", "throughput": 1495.47, "total_tokens": 4516288} {"current_steps": 21415, "total_steps": 181800, "loss": 0.0694, "lr": 4.995181881637159e-05, "epoch": 2.3558855885588557, "percentage": 11.78, "elapsed_time": "0:50:20", "remaining_time": "6:17:02", "throughput": 1495.49, "total_tokens": 4517376} {"current_steps": 21420, "total_steps": 181800, "loss": 0.098, "lr": 4.9951669766008615e-05, "epoch": 2.3564356435643563, "percentage": 11.78, "elapsed_time": "0:50:21", "remaining_time": "6:17:02", "throughput": 1495.48, "total_tokens": 4518400} {"current_steps": 21425, "total_steps": 181800, "loss": 0.0439, "lr": 4.995152048567806e-05, "epoch": 2.356985698569857, "percentage": 11.78, "elapsed_time": "0:50:22", "remaining_time": "6:17:01", "throughput": 1495.48, "total_tokens": 4519424} {"current_steps": 21430, "total_steps": 181800, "loss": 0.0735, "lr": 4.995137097538133e-05, "epoch": 2.3575357535753576, "percentage": 11.79, "elapsed_time": "0:50:22", "remaining_time": "6:17:00", "throughput": 1495.5, "total_tokens": 4520512} {"current_steps": 21435, "total_steps": 181800, "loss": 0.0783, "lr": 4.995122123511977e-05, "epoch": 2.3580858085808583, "percentage": 11.79, "elapsed_time": "0:50:23", "remaining_time": "6:16:59", "throughput": 1495.51, "total_tokens": 4521568} {"current_steps": 21440, "total_steps": 181800, "loss": 0.1321, "lr": 4.9951071264894786e-05, "epoch": 2.3586358635863585, "percentage": 11.79, "elapsed_time": "0:50:24", "remaining_time": "6:16:58", "throughput": 1495.51, "total_tokens": 4522592} {"current_steps": 21445, "total_steps": 181800, "loss": 0.0451, "lr": 4.9950921064707754e-05, "epoch": 2.359185918591859, "percentage": 11.8, "elapsed_time": "0:50:24", "remaining_time": "6:16:58", "throughput": 1495.54, "total_tokens": 4523712} {"current_steps": 21450, "total_steps": 181800, "loss": 0.0737, "lr": 4.995077063456005e-05, "epoch": 2.3597359735973598, "percentage": 11.8, "elapsed_time": "0:50:25", "remaining_time": "6:16:57", "throughput": 1495.56, "total_tokens": 4524832} {"current_steps": 21455, "total_steps": 181800, "loss": 0.0645, "lr": 4.995061997445307e-05, "epoch": 2.3602860286028604, "percentage": 11.8, "elapsed_time": "0:50:26", "remaining_time": "6:16:56", "throughput": 1495.56, "total_tokens": 4525856} {"current_steps": 21460, "total_steps": 181800, "loss": 0.0632, "lr": 4.9950469084388196e-05, "epoch": 2.360836083608361, "percentage": 11.8, "elapsed_time": "0:50:26", "remaining_time": "6:16:55", "throughput": 1495.57, "total_tokens": 4526912} {"current_steps": 21465, "total_steps": 181800, "loss": 0.0926, "lr": 4.995031796436682e-05, "epoch": 2.3613861386138613, "percentage": 11.81, "elapsed_time": "0:50:27", "remaining_time": "6:16:54", "throughput": 1495.58, "total_tokens": 4527968} {"current_steps": 21470, "total_steps": 181800, "loss": 0.068, "lr": 4.9950166614390336e-05, "epoch": 2.361936193619362, "percentage": 11.81, "elapsed_time": "0:50:28", "remaining_time": "6:16:53", "throughput": 1495.59, "total_tokens": 4529024} {"current_steps": 21475, "total_steps": 181800, "loss": 0.0285, "lr": 4.995001503446014e-05, "epoch": 2.3624862486248626, "percentage": 11.81, "elapsed_time": "0:50:28", "remaining_time": "6:16:53", "throughput": 1495.59, "total_tokens": 4530048} {"current_steps": 21480, "total_steps": 181800, "loss": 0.0729, "lr": 4.994986322457763e-05, "epoch": 2.363036303630363, "percentage": 11.82, "elapsed_time": "0:50:29", "remaining_time": "6:16:52", "throughput": 1495.61, "total_tokens": 4531136} {"current_steps": 21485, "total_steps": 181800, "loss": 0.0443, "lr": 4.99497111847442e-05, "epoch": 2.3635863586358634, "percentage": 11.82, "elapsed_time": "0:50:30", "remaining_time": "6:16:51", "throughput": 1495.6, "total_tokens": 4532160} {"current_steps": 21490, "total_steps": 181800, "loss": 0.1806, "lr": 4.994955891496125e-05, "epoch": 2.364136413641364, "percentage": 11.82, "elapsed_time": "0:50:31", "remaining_time": "6:16:50", "throughput": 1495.61, "total_tokens": 4533216} {"current_steps": 21495, "total_steps": 181800, "loss": 0.0913, "lr": 4.994940641523019e-05, "epoch": 2.3646864686468647, "percentage": 11.82, "elapsed_time": "0:50:31", "remaining_time": "6:16:49", "throughput": 1495.63, "total_tokens": 4534304} {"current_steps": 21500, "total_steps": 181800, "loss": 0.1008, "lr": 4.994925368555242e-05, "epoch": 2.3652365236523654, "percentage": 11.83, "elapsed_time": "0:50:32", "remaining_time": "6:16:48", "throughput": 1495.63, "total_tokens": 4535328} {"current_steps": 21505, "total_steps": 181800, "loss": 0.0485, "lr": 4.994910072592936e-05, "epoch": 2.3657865786578656, "percentage": 11.83, "elapsed_time": "0:50:33", "remaining_time": "6:16:48", "throughput": 1495.66, "total_tokens": 4536448} {"current_steps": 21510, "total_steps": 181800, "loss": 0.0801, "lr": 4.99489475363624e-05, "epoch": 2.366336633663366, "percentage": 11.83, "elapsed_time": "0:50:33", "remaining_time": "6:16:47", "throughput": 1495.68, "total_tokens": 4537568} {"current_steps": 21515, "total_steps": 181800, "loss": 0.0649, "lr": 4.994879411685297e-05, "epoch": 2.366886688668867, "percentage": 11.83, "elapsed_time": "0:50:34", "remaining_time": "6:16:46", "throughput": 1495.69, "total_tokens": 4538624} {"current_steps": 21520, "total_steps": 181800, "loss": 0.0247, "lr": 4.994864046740247e-05, "epoch": 2.3674367436743675, "percentage": 11.84, "elapsed_time": "0:50:35", "remaining_time": "6:16:45", "throughput": 1495.72, "total_tokens": 4539744} {"current_steps": 21525, "total_steps": 181800, "loss": 0.023, "lr": 4.994848658801233e-05, "epoch": 2.367986798679868, "percentage": 11.84, "elapsed_time": "0:50:35", "remaining_time": "6:16:44", "throughput": 1495.75, "total_tokens": 4540864} {"current_steps": 21530, "total_steps": 181800, "loss": 0.0496, "lr": 4.994833247868396e-05, "epoch": 2.3685368536853684, "percentage": 11.84, "elapsed_time": "0:50:36", "remaining_time": "6:16:44", "throughput": 1495.75, "total_tokens": 4541888} {"current_steps": 21535, "total_steps": 181800, "loss": 0.1312, "lr": 4.9948178139418774e-05, "epoch": 2.369086908690869, "percentage": 11.85, "elapsed_time": "0:50:37", "remaining_time": "6:16:43", "throughput": 1495.76, "total_tokens": 4542944} {"current_steps": 21540, "total_steps": 181800, "loss": 0.0274, "lr": 4.99480235702182e-05, "epoch": 2.3696369636963697, "percentage": 11.85, "elapsed_time": "0:50:37", "remaining_time": "6:16:42", "throughput": 1495.75, "total_tokens": 4543968} {"current_steps": 21545, "total_steps": 181800, "loss": 0.0775, "lr": 4.994786877108367e-05, "epoch": 2.3701870187018703, "percentage": 11.85, "elapsed_time": "0:50:38", "remaining_time": "6:16:41", "throughput": 1495.75, "total_tokens": 4544992} {"current_steps": 21550, "total_steps": 181800, "loss": 0.0675, "lr": 4.994771374201661e-05, "epoch": 2.370737073707371, "percentage": 11.85, "elapsed_time": "0:50:39", "remaining_time": "6:16:40", "throughput": 1495.75, "total_tokens": 4546016} {"current_steps": 21555, "total_steps": 181800, "loss": 0.0616, "lr": 4.994755848301843e-05, "epoch": 2.371287128712871, "percentage": 11.86, "elapsed_time": "0:50:39", "remaining_time": "6:16:39", "throughput": 1495.77, "total_tokens": 4547104} {"current_steps": 21560, "total_steps": 181800, "loss": 0.0618, "lr": 4.994740299409058e-05, "epoch": 2.371837183718372, "percentage": 11.86, "elapsed_time": "0:50:40", "remaining_time": "6:16:39", "throughput": 1495.78, "total_tokens": 4548160} {"current_steps": 21565, "total_steps": 181800, "loss": 0.0853, "lr": 4.994724727523449e-05, "epoch": 2.3723872387238725, "percentage": 11.86, "elapsed_time": "0:50:41", "remaining_time": "6:16:38", "throughput": 1495.78, "total_tokens": 4549184} {"current_steps": 21570, "total_steps": 181800, "loss": 0.0971, "lr": 4.994709132645159e-05, "epoch": 2.372937293729373, "percentage": 11.86, "elapsed_time": "0:50:42", "remaining_time": "6:16:37", "throughput": 1495.78, "total_tokens": 4550208} {"current_steps": 21575, "total_steps": 181800, "loss": 0.0544, "lr": 4.9946935147743326e-05, "epoch": 2.3734873487348733, "percentage": 11.87, "elapsed_time": "0:50:42", "remaining_time": "6:16:36", "throughput": 1495.8, "total_tokens": 4551296} {"current_steps": 21580, "total_steps": 181800, "loss": 0.0426, "lr": 4.9946778739111125e-05, "epoch": 2.374037403740374, "percentage": 11.87, "elapsed_time": "0:50:43", "remaining_time": "6:16:35", "throughput": 1495.79, "total_tokens": 4552320} {"current_steps": 21585, "total_steps": 181800, "loss": 0.0976, "lr": 4.994662210055643e-05, "epoch": 2.3745874587458746, "percentage": 11.87, "elapsed_time": "0:50:44", "remaining_time": "6:16:34", "throughput": 1495.78, "total_tokens": 4553312} {"current_steps": 21590, "total_steps": 181800, "loss": 0.0479, "lr": 4.9946465232080696e-05, "epoch": 2.3751375137513753, "percentage": 11.88, "elapsed_time": "0:50:44", "remaining_time": "6:16:34", "throughput": 1495.81, "total_tokens": 4554432} {"current_steps": 21595, "total_steps": 181800, "loss": 0.0132, "lr": 4.994630813368537e-05, "epoch": 2.3756875687568755, "percentage": 11.88, "elapsed_time": "0:50:45", "remaining_time": "6:16:33", "throughput": 1495.82, "total_tokens": 4555488} {"current_steps": 21600, "total_steps": 181800, "loss": 0.0508, "lr": 4.9946150805371885e-05, "epoch": 2.376237623762376, "percentage": 11.88, "elapsed_time": "0:50:46", "remaining_time": "6:16:32", "throughput": 1495.83, "total_tokens": 4556544} {"current_steps": 21605, "total_steps": 181800, "loss": 0.0246, "lr": 4.9945993247141697e-05, "epoch": 2.3767876787678768, "percentage": 11.88, "elapsed_time": "0:50:46", "remaining_time": "6:16:31", "throughput": 1495.83, "total_tokens": 4557568} {"current_steps": 21610, "total_steps": 181800, "loss": 0.3121, "lr": 4.994583545899626e-05, "epoch": 2.3773377337733774, "percentage": 11.89, "elapsed_time": "0:50:47", "remaining_time": "6:16:30", "throughput": 1495.84, "total_tokens": 4558656} {"current_steps": 21615, "total_steps": 181800, "loss": 0.1117, "lr": 4.994567744093703e-05, "epoch": 2.377887788778878, "percentage": 11.89, "elapsed_time": "0:50:48", "remaining_time": "6:16:29", "throughput": 1495.86, "total_tokens": 4559744} {"current_steps": 21620, "total_steps": 181800, "loss": 0.1598, "lr": 4.994551919296546e-05, "epoch": 2.3784378437843783, "percentage": 11.89, "elapsed_time": "0:50:48", "remaining_time": "6:16:29", "throughput": 1495.87, "total_tokens": 4560800} {"current_steps": 21625, "total_steps": 181800, "loss": 0.1433, "lr": 4.994536071508301e-05, "epoch": 2.378987898789879, "percentage": 11.89, "elapsed_time": "0:50:49", "remaining_time": "6:16:28", "throughput": 1495.87, "total_tokens": 4561824} {"current_steps": 21630, "total_steps": 181800, "loss": 0.0424, "lr": 4.9945202007291134e-05, "epoch": 2.3795379537953796, "percentage": 11.9, "elapsed_time": "0:50:50", "remaining_time": "6:16:27", "throughput": 1495.87, "total_tokens": 4562848} {"current_steps": 21635, "total_steps": 181800, "loss": 0.0674, "lr": 4.9945043069591314e-05, "epoch": 2.3800880088008802, "percentage": 11.9, "elapsed_time": "0:50:50", "remaining_time": "6:16:26", "throughput": 1495.88, "total_tokens": 4563904} {"current_steps": 21640, "total_steps": 181800, "loss": 0.1001, "lr": 4.994488390198499e-05, "epoch": 2.380638063806381, "percentage": 11.9, "elapsed_time": "0:50:51", "remaining_time": "6:16:25", "throughput": 1495.88, "total_tokens": 4564928} {"current_steps": 21645, "total_steps": 181800, "loss": 0.0876, "lr": 4.994472450447365e-05, "epoch": 2.381188118811881, "percentage": 11.91, "elapsed_time": "0:50:52", "remaining_time": "6:16:24", "throughput": 1495.9, "total_tokens": 4566016} {"current_steps": 21650, "total_steps": 181800, "loss": 0.0669, "lr": 4.994456487705874e-05, "epoch": 2.3817381738173817, "percentage": 11.91, "elapsed_time": "0:50:53", "remaining_time": "6:16:24", "throughput": 1495.92, "total_tokens": 4567104} {"current_steps": 21655, "total_steps": 181800, "loss": 0.0532, "lr": 4.994440501974176e-05, "epoch": 2.3822882288228824, "percentage": 11.91, "elapsed_time": "0:50:53", "remaining_time": "6:16:23", "throughput": 1495.93, "total_tokens": 4568160} {"current_steps": 21660, "total_steps": 181800, "loss": 0.0306, "lr": 4.994424493252417e-05, "epoch": 2.382838283828383, "percentage": 11.91, "elapsed_time": "0:50:54", "remaining_time": "6:16:22", "throughput": 1495.92, "total_tokens": 4569184} {"current_steps": 21665, "total_steps": 181800, "loss": 0.087, "lr": 4.994408461540743e-05, "epoch": 2.3833883388338832, "percentage": 11.92, "elapsed_time": "0:50:55", "remaining_time": "6:16:21", "throughput": 1495.94, "total_tokens": 4570272} {"current_steps": 21670, "total_steps": 181800, "loss": 0.1254, "lr": 4.994392406839303e-05, "epoch": 2.383938393839384, "percentage": 11.92, "elapsed_time": "0:50:55", "remaining_time": "6:16:20", "throughput": 1495.94, "total_tokens": 4571296} {"current_steps": 21675, "total_steps": 181800, "loss": 0.0402, "lr": 4.994376329148246e-05, "epoch": 2.3844884488448845, "percentage": 11.92, "elapsed_time": "0:50:56", "remaining_time": "6:16:19", "throughput": 1495.93, "total_tokens": 4572288} {"current_steps": 21680, "total_steps": 181800, "loss": 0.0164, "lr": 4.99436022846772e-05, "epoch": 2.385038503850385, "percentage": 11.93, "elapsed_time": "0:50:57", "remaining_time": "6:16:19", "throughput": 1495.93, "total_tokens": 4573312} {"current_steps": 21685, "total_steps": 181800, "loss": 0.1228, "lr": 4.994344104797872e-05, "epoch": 2.3855885588558854, "percentage": 11.93, "elapsed_time": "0:50:57", "remaining_time": "6:16:18", "throughput": 1495.94, "total_tokens": 4574368} {"current_steps": 21690, "total_steps": 181800, "loss": 0.0593, "lr": 4.994327958138851e-05, "epoch": 2.386138613861386, "percentage": 11.93, "elapsed_time": "0:50:58", "remaining_time": "6:16:17", "throughput": 1495.95, "total_tokens": 4575424} {"current_steps": 21695, "total_steps": 181800, "loss": 0.0873, "lr": 4.9943117884908066e-05, "epoch": 2.3866886688668867, "percentage": 11.93, "elapsed_time": "0:50:59", "remaining_time": "6:16:16", "throughput": 1495.95, "total_tokens": 4576448} {"current_steps": 21700, "total_steps": 181800, "loss": 0.0864, "lr": 4.994295595853886e-05, "epoch": 2.3872387238723873, "percentage": 11.94, "elapsed_time": "0:50:59", "remaining_time": "6:16:15", "throughput": 1495.95, "total_tokens": 4577504} {"current_steps": 21705, "total_steps": 181800, "loss": 0.1453, "lr": 4.9942793802282414e-05, "epoch": 2.387788778877888, "percentage": 11.94, "elapsed_time": "0:51:00", "remaining_time": "6:16:14", "throughput": 1495.95, "total_tokens": 4578528} {"current_steps": 21710, "total_steps": 181800, "loss": 0.0825, "lr": 4.9942631416140196e-05, "epoch": 2.388338833883388, "percentage": 11.94, "elapsed_time": "0:51:01", "remaining_time": "6:16:14", "throughput": 1495.95, "total_tokens": 4579552} {"current_steps": 21715, "total_steps": 181800, "loss": 0.0934, "lr": 4.9942468800113716e-05, "epoch": 2.388888888888889, "percentage": 11.94, "elapsed_time": "0:51:01", "remaining_time": "6:16:13", "throughput": 1495.95, "total_tokens": 4580576} {"current_steps": 21720, "total_steps": 181800, "loss": 0.0396, "lr": 4.9942305954204474e-05, "epoch": 2.3894389438943895, "percentage": 11.95, "elapsed_time": "0:51:02", "remaining_time": "6:16:12", "throughput": 1495.96, "total_tokens": 4581664} {"current_steps": 21725, "total_steps": 181800, "loss": 0.1552, "lr": 4.9942142878413965e-05, "epoch": 2.38998899889989, "percentage": 11.95, "elapsed_time": "0:51:03", "remaining_time": "6:16:11", "throughput": 1495.98, "total_tokens": 4582752} {"current_steps": 21730, "total_steps": 181800, "loss": 0.129, "lr": 4.994197957274369e-05, "epoch": 2.390539053905391, "percentage": 11.95, "elapsed_time": "0:51:04", "remaining_time": "6:16:10", "throughput": 1495.99, "total_tokens": 4583808} {"current_steps": 21735, "total_steps": 181800, "loss": 0.2175, "lr": 4.994181603719516e-05, "epoch": 2.391089108910891, "percentage": 11.96, "elapsed_time": "0:51:04", "remaining_time": "6:16:09", "throughput": 1496.0, "total_tokens": 4584864} {"current_steps": 21740, "total_steps": 181800, "loss": 0.0486, "lr": 4.9941652271769876e-05, "epoch": 2.3916391639163916, "percentage": 11.96, "elapsed_time": "0:51:05", "remaining_time": "6:16:09", "throughput": 1496.01, "total_tokens": 4585920} {"current_steps": 21745, "total_steps": 181800, "loss": 0.0686, "lr": 4.9941488276469355e-05, "epoch": 2.3921892189218923, "percentage": 11.96, "elapsed_time": "0:51:06", "remaining_time": "6:16:08", "throughput": 1496.01, "total_tokens": 4586944} {"current_steps": 21750, "total_steps": 181800, "loss": 0.0882, "lr": 4.9941324051295104e-05, "epoch": 2.3927392739273925, "percentage": 11.96, "elapsed_time": "0:51:06", "remaining_time": "6:16:07", "throughput": 1496.02, "total_tokens": 4588000} {"current_steps": 21755, "total_steps": 181800, "loss": 0.1222, "lr": 4.994115959624864e-05, "epoch": 2.393289328932893, "percentage": 11.97, "elapsed_time": "0:51:07", "remaining_time": "6:16:06", "throughput": 1496.01, "total_tokens": 4589024} {"current_steps": 21760, "total_steps": 181800, "loss": 0.0507, "lr": 4.9940994911331474e-05, "epoch": 2.393839383938394, "percentage": 11.97, "elapsed_time": "0:51:08", "remaining_time": "6:16:05", "throughput": 1496.01, "total_tokens": 4590048} {"current_steps": 21765, "total_steps": 181800, "loss": 0.0917, "lr": 4.9940829996545125e-05, "epoch": 2.3943894389438944, "percentage": 11.97, "elapsed_time": "0:51:08", "remaining_time": "6:16:04", "throughput": 1496.02, "total_tokens": 4591104} {"current_steps": 21770, "total_steps": 181800, "loss": 0.084, "lr": 4.994066485189111e-05, "epoch": 2.394939493949395, "percentage": 11.97, "elapsed_time": "0:51:09", "remaining_time": "6:16:04", "throughput": 1496.02, "total_tokens": 4592128} {"current_steps": 21775, "total_steps": 181800, "loss": 0.2184, "lr": 4.994049947737096e-05, "epoch": 2.3954895489548953, "percentage": 11.98, "elapsed_time": "0:51:10", "remaining_time": "6:16:03", "throughput": 1496.01, "total_tokens": 4593120} {"current_steps": 21780, "total_steps": 181800, "loss": 0.0951, "lr": 4.994033387298619e-05, "epoch": 2.396039603960396, "percentage": 11.98, "elapsed_time": "0:51:10", "remaining_time": "6:16:02", "throughput": 1496.01, "total_tokens": 4594144} {"current_steps": 21785, "total_steps": 181800, "loss": 0.1187, "lr": 4.994016803873833e-05, "epoch": 2.3965896589658966, "percentage": 11.98, "elapsed_time": "0:51:11", "remaining_time": "6:16:01", "throughput": 1496.04, "total_tokens": 4595264} {"current_steps": 21790, "total_steps": 181800, "loss": 0.0942, "lr": 4.9940001974628915e-05, "epoch": 2.3971397139713972, "percentage": 11.99, "elapsed_time": "0:51:12", "remaining_time": "6:16:00", "throughput": 1496.06, "total_tokens": 4596352} {"current_steps": 21795, "total_steps": 181800, "loss": 0.0804, "lr": 4.993983568065946e-05, "epoch": 2.397689768976898, "percentage": 11.99, "elapsed_time": "0:51:12", "remaining_time": "6:15:59", "throughput": 1496.07, "total_tokens": 4597408} {"current_steps": 21800, "total_steps": 181800, "loss": 0.0356, "lr": 4.993966915683151e-05, "epoch": 2.398239823982398, "percentage": 11.99, "elapsed_time": "0:51:13", "remaining_time": "6:15:59", "throughput": 1496.08, "total_tokens": 4598464} {"current_steps": 21805, "total_steps": 181800, "loss": 0.0265, "lr": 4.99395024031466e-05, "epoch": 2.3987898789878987, "percentage": 11.99, "elapsed_time": "0:51:14", "remaining_time": "6:15:58", "throughput": 1496.08, "total_tokens": 4599488} {"current_steps": 21810, "total_steps": 181800, "loss": 0.0383, "lr": 4.993933541960627e-05, "epoch": 2.3993399339933994, "percentage": 12.0, "elapsed_time": "0:51:15", "remaining_time": "6:15:57", "throughput": 1496.09, "total_tokens": 4600544} {"current_steps": 21815, "total_steps": 181800, "loss": 0.1155, "lr": 4.993916820621204e-05, "epoch": 2.3998899889989, "percentage": 12.0, "elapsed_time": "0:51:15", "remaining_time": "6:15:56", "throughput": 1496.08, "total_tokens": 4601568} {"current_steps": 21820, "total_steps": 181800, "loss": 0.0783, "lr": 4.9939000762965474e-05, "epoch": 2.4004400440044003, "percentage": 12.0, "elapsed_time": "0:51:16", "remaining_time": "6:15:55", "throughput": 1496.09, "total_tokens": 4602624} {"current_steps": 21825, "total_steps": 181800, "loss": 0.0697, "lr": 4.9938833089868096e-05, "epoch": 2.400990099009901, "percentage": 12.0, "elapsed_time": "0:51:17", "remaining_time": "6:15:55", "throughput": 1496.1, "total_tokens": 4603680} {"current_steps": 21830, "total_steps": 181800, "loss": 0.0758, "lr": 4.993866518692146e-05, "epoch": 2.4015401540154016, "percentage": 12.01, "elapsed_time": "0:51:17", "remaining_time": "6:15:54", "throughput": 1496.12, "total_tokens": 4604800} {"current_steps": 21835, "total_steps": 181800, "loss": 0.0616, "lr": 4.993849705412712e-05, "epoch": 2.402090209020902, "percentage": 12.01, "elapsed_time": "0:51:18", "remaining_time": "6:15:53", "throughput": 1496.15, "total_tokens": 4605920} {"current_steps": 21840, "total_steps": 181800, "loss": 0.0917, "lr": 4.9938328691486615e-05, "epoch": 2.4026402640264024, "percentage": 12.01, "elapsed_time": "0:51:19", "remaining_time": "6:15:52", "throughput": 1496.17, "total_tokens": 4607008} {"current_steps": 21845, "total_steps": 181800, "loss": 0.0961, "lr": 4.993816009900151e-05, "epoch": 2.403190319031903, "percentage": 12.02, "elapsed_time": "0:51:19", "remaining_time": "6:15:51", "throughput": 1496.17, "total_tokens": 4608032} {"current_steps": 21850, "total_steps": 181800, "loss": 0.1407, "lr": 4.9937991276673335e-05, "epoch": 2.4037403740374037, "percentage": 12.02, "elapsed_time": "0:51:20", "remaining_time": "6:15:51", "throughput": 1496.15, "total_tokens": 4609024} {"current_steps": 21855, "total_steps": 181800, "loss": 0.078, "lr": 4.993782222450367e-05, "epoch": 2.4042904290429044, "percentage": 12.02, "elapsed_time": "0:51:21", "remaining_time": "6:15:50", "throughput": 1496.17, "total_tokens": 4610112} {"current_steps": 21860, "total_steps": 181800, "loss": 0.1208, "lr": 4.9937652942494065e-05, "epoch": 2.404840484048405, "percentage": 12.02, "elapsed_time": "0:51:21", "remaining_time": "6:15:49", "throughput": 1496.2, "total_tokens": 4611232} {"current_steps": 21865, "total_steps": 181800, "loss": 0.0848, "lr": 4.993748343064607e-05, "epoch": 2.405390539053905, "percentage": 12.03, "elapsed_time": "0:51:22", "remaining_time": "6:15:48", "throughput": 1496.19, "total_tokens": 4612256} {"current_steps": 21870, "total_steps": 181800, "loss": 0.1309, "lr": 4.993731368896126e-05, "epoch": 2.405940594059406, "percentage": 12.03, "elapsed_time": "0:51:23", "remaining_time": "6:15:47", "throughput": 1496.2, "total_tokens": 4613312} {"current_steps": 21875, "total_steps": 181800, "loss": 0.0573, "lr": 4.993714371744121e-05, "epoch": 2.4064906490649065, "percentage": 12.03, "elapsed_time": "0:51:24", "remaining_time": "6:15:46", "throughput": 1496.22, "total_tokens": 4614400} {"current_steps": 21880, "total_steps": 181800, "loss": 0.0829, "lr": 4.993697351608746e-05, "epoch": 2.407040704070407, "percentage": 12.04, "elapsed_time": "0:51:24", "remaining_time": "6:15:46", "throughput": 1496.22, "total_tokens": 4615424} {"current_steps": 21885, "total_steps": 181800, "loss": 0.1512, "lr": 4.993680308490158e-05, "epoch": 2.407590759075908, "percentage": 12.04, "elapsed_time": "0:51:25", "remaining_time": "6:15:45", "throughput": 1496.21, "total_tokens": 4616416} {"current_steps": 21890, "total_steps": 181800, "loss": 0.1515, "lr": 4.993663242388516e-05, "epoch": 2.408140814081408, "percentage": 12.04, "elapsed_time": "0:51:26", "remaining_time": "6:15:44", "throughput": 1496.22, "total_tokens": 4617504} {"current_steps": 21895, "total_steps": 181800, "loss": 0.0663, "lr": 4.993646153303978e-05, "epoch": 2.4086908690869087, "percentage": 12.04, "elapsed_time": "0:51:26", "remaining_time": "6:15:43", "throughput": 1496.22, "total_tokens": 4618528} {"current_steps": 21900, "total_steps": 181800, "loss": 0.1054, "lr": 4.993629041236698e-05, "epoch": 2.4092409240924093, "percentage": 12.05, "elapsed_time": "0:51:27", "remaining_time": "6:15:42", "throughput": 1496.22, "total_tokens": 4619552} {"current_steps": 21905, "total_steps": 181800, "loss": 0.0612, "lr": 4.993611906186837e-05, "epoch": 2.40979097909791, "percentage": 12.05, "elapsed_time": "0:51:28", "remaining_time": "6:15:42", "throughput": 1496.24, "total_tokens": 4620640} {"current_steps": 21910, "total_steps": 181800, "loss": 0.0499, "lr": 4.993594748154551e-05, "epoch": 2.41034103410341, "percentage": 12.05, "elapsed_time": "0:51:28", "remaining_time": "6:15:41", "throughput": 1496.26, "total_tokens": 4621760} {"current_steps": 21915, "total_steps": 181800, "loss": 0.0758, "lr": 4.993577567139999e-05, "epoch": 2.410891089108911, "percentage": 12.05, "elapsed_time": "0:51:29", "remaining_time": "6:15:40", "throughput": 1496.26, "total_tokens": 4622784} {"current_steps": 21920, "total_steps": 181800, "loss": 0.0596, "lr": 4.993560363143339e-05, "epoch": 2.4114411441144115, "percentage": 12.06, "elapsed_time": "0:51:30", "remaining_time": "6:15:39", "throughput": 1496.26, "total_tokens": 4623808} {"current_steps": 21925, "total_steps": 181800, "loss": 0.0602, "lr": 4.993543136164729e-05, "epoch": 2.411991199119912, "percentage": 12.06, "elapsed_time": "0:51:30", "remaining_time": "6:15:38", "throughput": 1496.24, "total_tokens": 4624800} {"current_steps": 21930, "total_steps": 181800, "loss": 0.0836, "lr": 4.9935258862043294e-05, "epoch": 2.4125412541254123, "percentage": 12.06, "elapsed_time": "0:51:31", "remaining_time": "6:15:38", "throughput": 1496.25, "total_tokens": 4625856} {"current_steps": 21935, "total_steps": 181800, "loss": 0.1279, "lr": 4.9935086132622975e-05, "epoch": 2.413091309130913, "percentage": 12.07, "elapsed_time": "0:51:32", "remaining_time": "6:15:37", "throughput": 1496.27, "total_tokens": 4626944} {"current_steps": 21940, "total_steps": 181800, "loss": 0.1224, "lr": 4.993491317338794e-05, "epoch": 2.4136413641364136, "percentage": 12.07, "elapsed_time": "0:51:33", "remaining_time": "6:15:36", "throughput": 1496.27, "total_tokens": 4627968} {"current_steps": 21945, "total_steps": 181800, "loss": 0.0442, "lr": 4.993473998433977e-05, "epoch": 2.4141914191419143, "percentage": 12.07, "elapsed_time": "0:51:33", "remaining_time": "6:15:35", "throughput": 1496.3, "total_tokens": 4629088} {"current_steps": 21950, "total_steps": 181800, "loss": 0.0963, "lr": 4.9934566565480065e-05, "epoch": 2.414741474147415, "percentage": 12.07, "elapsed_time": "0:51:34", "remaining_time": "6:15:34", "throughput": 1496.33, "total_tokens": 4630208} {"current_steps": 21955, "total_steps": 181800, "loss": 0.0606, "lr": 4.993439291681042e-05, "epoch": 2.415291529152915, "percentage": 12.08, "elapsed_time": "0:51:35", "remaining_time": "6:15:33", "throughput": 1496.31, "total_tokens": 4631200} {"current_steps": 21960, "total_steps": 181800, "loss": 0.1099, "lr": 4.9934219038332455e-05, "epoch": 2.4158415841584158, "percentage": 12.08, "elapsed_time": "0:51:35", "remaining_time": "6:15:33", "throughput": 1496.32, "total_tokens": 4632256} {"current_steps": 21965, "total_steps": 181800, "loss": 0.105, "lr": 4.993404493004775e-05, "epoch": 2.4163916391639164, "percentage": 12.08, "elapsed_time": "0:51:36", "remaining_time": "6:15:32", "throughput": 1496.35, "total_tokens": 4633376} {"current_steps": 21970, "total_steps": 181800, "loss": 0.0641, "lr": 4.993387059195792e-05, "epoch": 2.416941694169417, "percentage": 12.08, "elapsed_time": "0:51:37", "remaining_time": "6:15:31", "throughput": 1496.36, "total_tokens": 4634432} {"current_steps": 21975, "total_steps": 181800, "loss": 0.0474, "lr": 4.993369602406456e-05, "epoch": 2.4174917491749177, "percentage": 12.09, "elapsed_time": "0:51:37", "remaining_time": "6:15:30", "throughput": 1496.35, "total_tokens": 4635456} {"current_steps": 21980, "total_steps": 181800, "loss": 0.0624, "lr": 4.9933521226369294e-05, "epoch": 2.418041804180418, "percentage": 12.09, "elapsed_time": "0:51:38", "remaining_time": "6:15:29", "throughput": 1496.37, "total_tokens": 4636544} {"current_steps": 21985, "total_steps": 181800, "loss": 0.0646, "lr": 4.993334619887373e-05, "epoch": 2.4185918591859186, "percentage": 12.09, "elapsed_time": "0:51:39", "remaining_time": "6:15:29", "throughput": 1496.4, "total_tokens": 4637664} {"current_steps": 21990, "total_steps": 181800, "loss": 0.084, "lr": 4.993317094157948e-05, "epoch": 2.419141914191419, "percentage": 12.1, "elapsed_time": "0:51:39", "remaining_time": "6:15:28", "throughput": 1496.39, "total_tokens": 4638656} {"current_steps": 21995, "total_steps": 181800, "loss": 0.0674, "lr": 4.993299545448815e-05, "epoch": 2.41969196919692, "percentage": 12.1, "elapsed_time": "0:51:40", "remaining_time": "6:15:27", "throughput": 1496.4, "total_tokens": 4639712} {"current_steps": 22000, "total_steps": 181800, "loss": 0.0986, "lr": 4.993281973760137e-05, "epoch": 2.42024202420242, "percentage": 12.1, "elapsed_time": "0:51:41", "remaining_time": "6:15:26", "throughput": 1496.39, "total_tokens": 4640704} {"current_steps": 22005, "total_steps": 181800, "loss": 0.046, "lr": 4.993264379092075e-05, "epoch": 2.4207920792079207, "percentage": 12.1, "elapsed_time": "0:51:41", "remaining_time": "6:15:25", "throughput": 1496.4, "total_tokens": 4641760} {"current_steps": 22010, "total_steps": 181800, "loss": 0.0289, "lr": 4.993246761444792e-05, "epoch": 2.4213421342134214, "percentage": 12.11, "elapsed_time": "0:51:42", "remaining_time": "6:15:24", "throughput": 1496.39, "total_tokens": 4642752} {"current_steps": 22015, "total_steps": 181800, "loss": 0.127, "lr": 4.99322912081845e-05, "epoch": 2.421892189218922, "percentage": 12.11, "elapsed_time": "0:51:43", "remaining_time": "6:15:24", "throughput": 1496.39, "total_tokens": 4643808} {"current_steps": 22020, "total_steps": 181800, "loss": 0.0548, "lr": 4.993211457213212e-05, "epoch": 2.4224422442244222, "percentage": 12.11, "elapsed_time": "0:51:44", "remaining_time": "6:15:23", "throughput": 1496.41, "total_tokens": 4644896} {"current_steps": 22025, "total_steps": 181800, "loss": 0.0634, "lr": 4.993193770629239e-05, "epoch": 2.422992299229923, "percentage": 12.11, "elapsed_time": "0:51:44", "remaining_time": "6:15:22", "throughput": 1496.42, "total_tokens": 4645952} {"current_steps": 22030, "total_steps": 181800, "loss": 0.0828, "lr": 4.993176061066696e-05, "epoch": 2.4235423542354235, "percentage": 12.12, "elapsed_time": "0:51:45", "remaining_time": "6:15:21", "throughput": 1496.45, "total_tokens": 4647072} {"current_steps": 22035, "total_steps": 181800, "loss": 0.1612, "lr": 4.9931583285257456e-05, "epoch": 2.424092409240924, "percentage": 12.12, "elapsed_time": "0:51:46", "remaining_time": "6:15:20", "throughput": 1496.44, "total_tokens": 4648064} {"current_steps": 22040, "total_steps": 181800, "loss": 0.1469, "lr": 4.993140573006552e-05, "epoch": 2.424642464246425, "percentage": 12.12, "elapsed_time": "0:51:46", "remaining_time": "6:15:19", "throughput": 1496.43, "total_tokens": 4649056} {"current_steps": 22045, "total_steps": 181800, "loss": 0.0904, "lr": 4.9931227945092774e-05, "epoch": 2.425192519251925, "percentage": 12.13, "elapsed_time": "0:51:47", "remaining_time": "6:15:19", "throughput": 1496.44, "total_tokens": 4650144} {"current_steps": 22050, "total_steps": 181800, "loss": 0.1227, "lr": 4.9931049930340854e-05, "epoch": 2.4257425742574257, "percentage": 12.13, "elapsed_time": "0:51:48", "remaining_time": "6:15:18", "throughput": 1496.43, "total_tokens": 4651136} {"current_steps": 22055, "total_steps": 181800, "loss": 0.0225, "lr": 4.993087168581143e-05, "epoch": 2.4262926292629263, "percentage": 12.13, "elapsed_time": "0:51:48", "remaining_time": "6:15:17", "throughput": 1496.43, "total_tokens": 4652160} {"current_steps": 22060, "total_steps": 181800, "loss": 0.0531, "lr": 4.9930693211506106e-05, "epoch": 2.426842684268427, "percentage": 12.13, "elapsed_time": "0:51:49", "remaining_time": "6:15:16", "throughput": 1496.47, "total_tokens": 4653312} {"current_steps": 22065, "total_steps": 181800, "loss": 0.0635, "lr": 4.993051450742656e-05, "epoch": 2.4273927392739276, "percentage": 12.14, "elapsed_time": "0:51:50", "remaining_time": "6:15:15", "throughput": 1496.48, "total_tokens": 4654368} {"current_steps": 22070, "total_steps": 181800, "loss": 0.11, "lr": 4.993033557357442e-05, "epoch": 2.427942794279428, "percentage": 12.14, "elapsed_time": "0:51:50", "remaining_time": "6:15:14", "throughput": 1496.48, "total_tokens": 4655424} {"current_steps": 22075, "total_steps": 181800, "loss": 0.0592, "lr": 4.9930156409951334e-05, "epoch": 2.4284928492849285, "percentage": 12.14, "elapsed_time": "0:51:51", "remaining_time": "6:15:14", "throughput": 1496.5, "total_tokens": 4656512} {"current_steps": 22080, "total_steps": 181800, "loss": 0.0987, "lr": 4.992997701655896e-05, "epoch": 2.429042904290429, "percentage": 12.15, "elapsed_time": "0:51:52", "remaining_time": "6:15:13", "throughput": 1496.53, "total_tokens": 4657632} {"current_steps": 22085, "total_steps": 181800, "loss": 0.0817, "lr": 4.992979739339895e-05, "epoch": 2.4295929592959298, "percentage": 12.15, "elapsed_time": "0:51:52", "remaining_time": "6:15:12", "throughput": 1496.53, "total_tokens": 4658656} {"current_steps": 22090, "total_steps": 181800, "loss": 0.0965, "lr": 4.9929617540472964e-05, "epoch": 2.43014301430143, "percentage": 12.15, "elapsed_time": "0:51:53", "remaining_time": "6:15:11", "throughput": 1496.52, "total_tokens": 4659648} {"current_steps": 22095, "total_steps": 181800, "loss": 0.0472, "lr": 4.9929437457782654e-05, "epoch": 2.4306930693069306, "percentage": 12.15, "elapsed_time": "0:51:54", "remaining_time": "6:15:10", "throughput": 1496.54, "total_tokens": 4660736} {"current_steps": 22100, "total_steps": 181800, "loss": 0.0795, "lr": 4.992925714532969e-05, "epoch": 2.4312431243124313, "percentage": 12.16, "elapsed_time": "0:51:55", "remaining_time": "6:15:09", "throughput": 1496.56, "total_tokens": 4661824} {"current_steps": 22105, "total_steps": 181800, "loss": 0.0391, "lr": 4.992907660311571e-05, "epoch": 2.431793179317932, "percentage": 12.16, "elapsed_time": "0:51:55", "remaining_time": "6:15:09", "throughput": 1496.58, "total_tokens": 4662912} {"current_steps": 22110, "total_steps": 181800, "loss": 0.0552, "lr": 4.99288958311424e-05, "epoch": 2.432343234323432, "percentage": 12.16, "elapsed_time": "0:51:56", "remaining_time": "6:15:08", "throughput": 1496.59, "total_tokens": 4663968} {"current_steps": 22115, "total_steps": 181800, "loss": 0.0412, "lr": 4.992871482941142e-05, "epoch": 2.432893289328933, "percentage": 12.16, "elapsed_time": "0:51:57", "remaining_time": "6:15:07", "throughput": 1496.6, "total_tokens": 4665024} {"current_steps": 22120, "total_steps": 181800, "loss": 0.0879, "lr": 4.992853359792444e-05, "epoch": 2.4334433443344334, "percentage": 12.17, "elapsed_time": "0:51:57", "remaining_time": "6:15:06", "throughput": 1496.64, "total_tokens": 4666176} {"current_steps": 22125, "total_steps": 181800, "loss": 0.0371, "lr": 4.992835213668312e-05, "epoch": 2.433993399339934, "percentage": 12.17, "elapsed_time": "0:51:58", "remaining_time": "6:15:05", "throughput": 1496.64, "total_tokens": 4667232} {"current_steps": 22130, "total_steps": 181800, "loss": 0.0427, "lr": 4.9928170445689145e-05, "epoch": 2.4345434543454347, "percentage": 12.17, "elapsed_time": "0:51:59", "remaining_time": "6:15:05", "throughput": 1496.65, "total_tokens": 4668288} {"current_steps": 22135, "total_steps": 181800, "loss": 0.1042, "lr": 4.9927988524944184e-05, "epoch": 2.435093509350935, "percentage": 12.18, "elapsed_time": "0:51:59", "remaining_time": "6:15:04", "throughput": 1496.67, "total_tokens": 4669376} {"current_steps": 22140, "total_steps": 181800, "loss": 0.0666, "lr": 4.992780637444992e-05, "epoch": 2.4356435643564356, "percentage": 12.18, "elapsed_time": "0:52:00", "remaining_time": "6:15:03", "throughput": 1496.67, "total_tokens": 4670400} {"current_steps": 22145, "total_steps": 181800, "loss": 0.0759, "lr": 4.9927623994208014e-05, "epoch": 2.4361936193619362, "percentage": 12.18, "elapsed_time": "0:52:01", "remaining_time": "6:15:02", "throughput": 1496.67, "total_tokens": 4671456} {"current_steps": 22150, "total_steps": 181800, "loss": 0.0457, "lr": 4.992744138422017e-05, "epoch": 2.436743674367437, "percentage": 12.18, "elapsed_time": "0:52:01", "remaining_time": "6:15:01", "throughput": 1496.68, "total_tokens": 4672512} {"current_steps": 22155, "total_steps": 181800, "loss": 0.035, "lr": 4.9927258544488056e-05, "epoch": 2.4372937293729375, "percentage": 12.19, "elapsed_time": "0:52:02", "remaining_time": "6:15:00", "throughput": 1496.7, "total_tokens": 4673600} {"current_steps": 22160, "total_steps": 181800, "loss": 0.0723, "lr": 4.992707547501336e-05, "epoch": 2.4378437843784377, "percentage": 12.19, "elapsed_time": "0:52:03", "remaining_time": "6:15:00", "throughput": 1496.7, "total_tokens": 4674624} {"current_steps": 22165, "total_steps": 181800, "loss": 0.0862, "lr": 4.992689217579777e-05, "epoch": 2.4383938393839384, "percentage": 12.19, "elapsed_time": "0:52:03", "remaining_time": "6:14:59", "throughput": 1496.72, "total_tokens": 4675712} {"current_steps": 22170, "total_steps": 181800, "loss": 0.0708, "lr": 4.992670864684298e-05, "epoch": 2.438943894389439, "percentage": 12.19, "elapsed_time": "0:52:04", "remaining_time": "6:14:58", "throughput": 1496.74, "total_tokens": 4676800} {"current_steps": 22175, "total_steps": 181800, "loss": 0.0517, "lr": 4.9926524888150674e-05, "epoch": 2.4394939493949397, "percentage": 12.2, "elapsed_time": "0:52:05", "remaining_time": "6:14:57", "throughput": 1496.73, "total_tokens": 4677792} {"current_steps": 22180, "total_steps": 181800, "loss": 0.077, "lr": 4.992634089972255e-05, "epoch": 2.44004400440044, "percentage": 12.2, "elapsed_time": "0:52:06", "remaining_time": "6:14:56", "throughput": 1496.72, "total_tokens": 4678816} {"current_steps": 22185, "total_steps": 181800, "loss": 0.0418, "lr": 4.99261566815603e-05, "epoch": 2.4405940594059405, "percentage": 12.2, "elapsed_time": "0:52:06", "remaining_time": "6:14:55", "throughput": 1496.73, "total_tokens": 4679872} {"current_steps": 22190, "total_steps": 181800, "loss": 0.1502, "lr": 4.992597223366563e-05, "epoch": 2.441144114411441, "percentage": 12.21, "elapsed_time": "0:52:07", "remaining_time": "6:14:55", "throughput": 1496.73, "total_tokens": 4680896} {"current_steps": 22195, "total_steps": 181800, "loss": 0.0974, "lr": 4.992578755604023e-05, "epoch": 2.441694169416942, "percentage": 12.21, "elapsed_time": "0:52:08", "remaining_time": "6:14:54", "throughput": 1496.74, "total_tokens": 4681952} {"current_steps": 22200, "total_steps": 181800, "loss": 0.1053, "lr": 4.992560264868581e-05, "epoch": 2.442244224422442, "percentage": 12.21, "elapsed_time": "0:52:08", "remaining_time": "6:14:53", "throughput": 1496.75, "total_tokens": 4683008} {"current_steps": 22205, "total_steps": 181800, "loss": 0.0485, "lr": 4.9925417511604066e-05, "epoch": 2.4427942794279427, "percentage": 12.21, "elapsed_time": "0:52:09", "remaining_time": "6:14:52", "throughput": 1496.78, "total_tokens": 4684128} {"current_steps": 22210, "total_steps": 181800, "loss": 0.1033, "lr": 4.992523214479672e-05, "epoch": 2.4433443344334433, "percentage": 12.22, "elapsed_time": "0:52:10", "remaining_time": "6:14:51", "throughput": 1496.79, "total_tokens": 4685184} {"current_steps": 22215, "total_steps": 181800, "loss": 0.1306, "lr": 4.992504654826546e-05, "epoch": 2.443894389438944, "percentage": 12.22, "elapsed_time": "0:52:10", "remaining_time": "6:14:50", "throughput": 1496.8, "total_tokens": 4686240} {"current_steps": 22220, "total_steps": 181800, "loss": 0.0391, "lr": 4.992486072201201e-05, "epoch": 2.4444444444444446, "percentage": 12.22, "elapsed_time": "0:52:11", "remaining_time": "6:14:50", "throughput": 1496.79, "total_tokens": 4687232} {"current_steps": 22225, "total_steps": 181800, "loss": 0.0488, "lr": 4.9924674666038075e-05, "epoch": 2.444994499449945, "percentage": 12.22, "elapsed_time": "0:52:12", "remaining_time": "6:14:49", "throughput": 1496.79, "total_tokens": 4688288} {"current_steps": 22230, "total_steps": 181800, "loss": 0.0489, "lr": 4.992448838034537e-05, "epoch": 2.4455445544554455, "percentage": 12.23, "elapsed_time": "0:52:12", "remaining_time": "6:14:48", "throughput": 1496.78, "total_tokens": 4689280} {"current_steps": 22235, "total_steps": 181800, "loss": 0.0599, "lr": 4.992430186493563e-05, "epoch": 2.446094609460946, "percentage": 12.23, "elapsed_time": "0:52:13", "remaining_time": "6:14:47", "throughput": 1496.79, "total_tokens": 4690336} {"current_steps": 22240, "total_steps": 181800, "loss": 0.03, "lr": 4.992411511981055e-05, "epoch": 2.446644664466447, "percentage": 12.23, "elapsed_time": "0:52:14", "remaining_time": "6:14:46", "throughput": 1496.79, "total_tokens": 4691360} {"current_steps": 22245, "total_steps": 181800, "loss": 0.0456, "lr": 4.992392814497186e-05, "epoch": 2.4471947194719474, "percentage": 12.24, "elapsed_time": "0:52:14", "remaining_time": "6:14:45", "throughput": 1496.81, "total_tokens": 4692448} {"current_steps": 22250, "total_steps": 181800, "loss": 0.0767, "lr": 4.9923740940421285e-05, "epoch": 2.4477447744774476, "percentage": 12.24, "elapsed_time": "0:52:15", "remaining_time": "6:14:45", "throughput": 1496.81, "total_tokens": 4693472} {"current_steps": 22255, "total_steps": 181800, "loss": 0.0704, "lr": 4.9923553506160546e-05, "epoch": 2.4482948294829483, "percentage": 12.24, "elapsed_time": "0:52:16", "remaining_time": "6:14:44", "throughput": 1496.84, "total_tokens": 4694592} {"current_steps": 22260, "total_steps": 181800, "loss": 0.0348, "lr": 4.992336584219138e-05, "epoch": 2.448844884488449, "percentage": 12.24, "elapsed_time": "0:52:17", "remaining_time": "6:14:43", "throughput": 1496.85, "total_tokens": 4695648} {"current_steps": 22265, "total_steps": 181800, "loss": 0.0481, "lr": 4.992317794851551e-05, "epoch": 2.449394939493949, "percentage": 12.25, "elapsed_time": "0:52:17", "remaining_time": "6:14:42", "throughput": 1496.86, "total_tokens": 4696736} {"current_steps": 22270, "total_steps": 181800, "loss": 0.1014, "lr": 4.9922989825134665e-05, "epoch": 2.44994499449945, "percentage": 12.25, "elapsed_time": "0:52:18", "remaining_time": "6:14:41", "throughput": 1496.87, "total_tokens": 4697792} {"current_steps": 22275, "total_steps": 181800, "loss": 0.1721, "lr": 4.9922801472050586e-05, "epoch": 2.4504950495049505, "percentage": 12.25, "elapsed_time": "0:52:19", "remaining_time": "6:14:40", "throughput": 1496.91, "total_tokens": 4698944} {"current_steps": 22280, "total_steps": 181800, "loss": 0.0704, "lr": 4.9922612889264995e-05, "epoch": 2.451045104510451, "percentage": 12.26, "elapsed_time": "0:52:19", "remaining_time": "6:14:40", "throughput": 1496.93, "total_tokens": 4700032} {"current_steps": 22285, "total_steps": 181800, "loss": 0.0664, "lr": 4.992242407677965e-05, "epoch": 2.4515951595159517, "percentage": 12.26, "elapsed_time": "0:52:20", "remaining_time": "6:14:39", "throughput": 1496.94, "total_tokens": 4701088} {"current_steps": 22290, "total_steps": 181800, "loss": 0.1706, "lr": 4.992223503459628e-05, "epoch": 2.452145214521452, "percentage": 12.26, "elapsed_time": "0:52:21", "remaining_time": "6:14:38", "throughput": 1496.95, "total_tokens": 4702144} {"current_steps": 22295, "total_steps": 181800, "loss": 0.1134, "lr": 4.992204576271663e-05, "epoch": 2.4526952695269526, "percentage": 12.26, "elapsed_time": "0:52:21", "remaining_time": "6:14:37", "throughput": 1496.94, "total_tokens": 4703168} {"current_steps": 22300, "total_steps": 181800, "loss": 0.1741, "lr": 4.992185626114244e-05, "epoch": 2.4532453245324533, "percentage": 12.27, "elapsed_time": "0:52:22", "remaining_time": "6:14:36", "throughput": 1496.96, "total_tokens": 4704256} {"current_steps": 22305, "total_steps": 181800, "loss": 0.0405, "lr": 4.9921666529875454e-05, "epoch": 2.453795379537954, "percentage": 12.27, "elapsed_time": "0:52:23", "remaining_time": "6:14:36", "throughput": 1496.98, "total_tokens": 4705344} {"current_steps": 22310, "total_steps": 181800, "loss": 0.0664, "lr": 4.992147656891744e-05, "epoch": 2.4543454345434546, "percentage": 12.27, "elapsed_time": "0:52:23", "remaining_time": "6:14:35", "throughput": 1497.0, "total_tokens": 4706432} {"current_steps": 22315, "total_steps": 181800, "loss": 0.1289, "lr": 4.992128637827012e-05, "epoch": 2.4548954895489548, "percentage": 12.27, "elapsed_time": "0:52:24", "remaining_time": "6:14:34", "throughput": 1497.02, "total_tokens": 4707552} {"current_steps": 22320, "total_steps": 181800, "loss": 0.1413, "lr": 4.9921095957935274e-05, "epoch": 2.4554455445544554, "percentage": 12.28, "elapsed_time": "0:52:25", "remaining_time": "6:14:33", "throughput": 1497.03, "total_tokens": 4708608} {"current_steps": 22325, "total_steps": 181800, "loss": 0.069, "lr": 4.9920905307914635e-05, "epoch": 2.455995599559956, "percentage": 12.28, "elapsed_time": "0:52:25", "remaining_time": "6:14:32", "throughput": 1497.03, "total_tokens": 4709632} {"current_steps": 22330, "total_steps": 181800, "loss": 0.0216, "lr": 4.9920714428209974e-05, "epoch": 2.4565456545654567, "percentage": 12.28, "elapsed_time": "0:52:26", "remaining_time": "6:14:31", "throughput": 1497.02, "total_tokens": 4710624} {"current_steps": 22335, "total_steps": 181800, "loss": 0.0515, "lr": 4.9920523318823046e-05, "epoch": 2.457095709570957, "percentage": 12.29, "elapsed_time": "0:52:27", "remaining_time": "6:14:31", "throughput": 1497.04, "total_tokens": 4711712} {"current_steps": 22340, "total_steps": 181800, "loss": 0.0669, "lr": 4.992033197975561e-05, "epoch": 2.4576457645764576, "percentage": 12.29, "elapsed_time": "0:52:28", "remaining_time": "6:14:30", "throughput": 1497.07, "total_tokens": 4712832} {"current_steps": 22345, "total_steps": 181800, "loss": 0.0111, "lr": 4.992014041100944e-05, "epoch": 2.458195819581958, "percentage": 12.29, "elapsed_time": "0:52:28", "remaining_time": "6:14:29", "throughput": 1497.1, "total_tokens": 4713952} {"current_steps": 22350, "total_steps": 181800, "loss": 0.0462, "lr": 4.991994861258629e-05, "epoch": 2.458745874587459, "percentage": 12.29, "elapsed_time": "0:52:29", "remaining_time": "6:14:28", "throughput": 1497.1, "total_tokens": 4715008} {"current_steps": 22355, "total_steps": 181800, "loss": 0.1438, "lr": 4.991975658448793e-05, "epoch": 2.459295929592959, "percentage": 12.3, "elapsed_time": "0:52:30", "remaining_time": "6:14:27", "throughput": 1497.12, "total_tokens": 4716096} {"current_steps": 22360, "total_steps": 181800, "loss": 0.0256, "lr": 4.991956432671613e-05, "epoch": 2.4598459845984597, "percentage": 12.3, "elapsed_time": "0:52:30", "remaining_time": "6:14:27", "throughput": 1497.13, "total_tokens": 4717152} {"current_steps": 22365, "total_steps": 181800, "loss": 0.1019, "lr": 4.9919371839272664e-05, "epoch": 2.4603960396039604, "percentage": 12.3, "elapsed_time": "0:52:31", "remaining_time": "6:14:27", "throughput": 1497.05, "total_tokens": 4718208} {"current_steps": 22370, "total_steps": 181800, "loss": 0.0129, "lr": 4.991917912215931e-05, "epoch": 2.460946094609461, "percentage": 12.3, "elapsed_time": "0:52:32", "remaining_time": "6:14:26", "throughput": 1497.04, "total_tokens": 4719232} {"current_steps": 22375, "total_steps": 181800, "loss": 0.0623, "lr": 4.9918986175377836e-05, "epoch": 2.4614961496149617, "percentage": 12.31, "elapsed_time": "0:52:33", "remaining_time": "6:14:26", "throughput": 1497.06, "total_tokens": 4720320} {"current_steps": 22380, "total_steps": 181800, "loss": 0.0737, "lr": 4.991879299893002e-05, "epoch": 2.462046204620462, "percentage": 12.31, "elapsed_time": "0:52:33", "remaining_time": "6:14:25", "throughput": 1497.07, "total_tokens": 4721408} {"current_steps": 22385, "total_steps": 181800, "loss": 0.033, "lr": 4.991859959281765e-05, "epoch": 2.4625962596259625, "percentage": 12.31, "elapsed_time": "0:52:34", "remaining_time": "6:14:24", "throughput": 1497.07, "total_tokens": 4722432} {"current_steps": 22390, "total_steps": 181800, "loss": 0.1719, "lr": 4.99184059570425e-05, "epoch": 2.463146314631463, "percentage": 12.32, "elapsed_time": "0:52:35", "remaining_time": "6:14:23", "throughput": 1497.08, "total_tokens": 4723488} {"current_steps": 22395, "total_steps": 181800, "loss": 0.1021, "lr": 4.991821209160636e-05, "epoch": 2.463696369636964, "percentage": 12.32, "elapsed_time": "0:52:35", "remaining_time": "6:14:22", "throughput": 1497.08, "total_tokens": 4724512} {"current_steps": 22400, "total_steps": 181800, "loss": 0.0372, "lr": 4.9918017996511025e-05, "epoch": 2.4642464246424645, "percentage": 12.32, "elapsed_time": "0:52:36", "remaining_time": "6:14:21", "throughput": 1497.11, "total_tokens": 4725632} {"current_steps": 22405, "total_steps": 181800, "loss": 0.0391, "lr": 4.991782367175827e-05, "epoch": 2.4647964796479647, "percentage": 12.32, "elapsed_time": "0:52:37", "remaining_time": "6:14:21", "throughput": 1497.13, "total_tokens": 4726720} {"current_steps": 22410, "total_steps": 181800, "loss": 0.0763, "lr": 4.991762911734989e-05, "epoch": 2.4653465346534653, "percentage": 12.33, "elapsed_time": "0:52:37", "remaining_time": "6:14:20", "throughput": 1497.15, "total_tokens": 4727808} {"current_steps": 22415, "total_steps": 181800, "loss": 0.1242, "lr": 4.9917434333287675e-05, "epoch": 2.465896589658966, "percentage": 12.33, "elapsed_time": "0:52:38", "remaining_time": "6:14:19", "throughput": 1497.14, "total_tokens": 4728832} {"current_steps": 22420, "total_steps": 181800, "loss": 0.046, "lr": 4.9917239319573426e-05, "epoch": 2.4664466446644666, "percentage": 12.33, "elapsed_time": "0:52:39", "remaining_time": "6:14:18", "throughput": 1497.14, "total_tokens": 4729856} {"current_steps": 22425, "total_steps": 181800, "loss": 0.0287, "lr": 4.991704407620895e-05, "epoch": 2.466996699669967, "percentage": 12.33, "elapsed_time": "0:52:39", "remaining_time": "6:14:17", "throughput": 1497.14, "total_tokens": 4730912} {"current_steps": 22430, "total_steps": 181800, "loss": 0.1381, "lr": 4.991684860319602e-05, "epoch": 2.4675467546754675, "percentage": 12.34, "elapsed_time": "0:52:40", "remaining_time": "6:14:17", "throughput": 1497.13, "total_tokens": 4731904} {"current_steps": 22435, "total_steps": 181800, "loss": 0.0522, "lr": 4.9916652900536466e-05, "epoch": 2.468096809680968, "percentage": 12.34, "elapsed_time": "0:52:41", "remaining_time": "6:14:16", "throughput": 1497.13, "total_tokens": 4732928} {"current_steps": 22440, "total_steps": 181800, "loss": 0.0692, "lr": 4.991645696823207e-05, "epoch": 2.4686468646864688, "percentage": 12.34, "elapsed_time": "0:52:42", "remaining_time": "6:14:15", "throughput": 1497.14, "total_tokens": 4733984} {"current_steps": 22445, "total_steps": 181800, "loss": 0.0555, "lr": 4.9916260806284644e-05, "epoch": 2.469196919691969, "percentage": 12.35, "elapsed_time": "0:52:42", "remaining_time": "6:14:14", "throughput": 1497.13, "total_tokens": 4734976} {"current_steps": 22450, "total_steps": 181800, "loss": 0.0329, "lr": 4.9916064414696004e-05, "epoch": 2.4697469746974696, "percentage": 12.35, "elapsed_time": "0:52:43", "remaining_time": "6:14:13", "throughput": 1497.11, "total_tokens": 4735968} {"current_steps": 22455, "total_steps": 181800, "loss": 0.0735, "lr": 4.991586779346795e-05, "epoch": 2.4702970297029703, "percentage": 12.35, "elapsed_time": "0:52:44", "remaining_time": "6:14:12", "throughput": 1497.13, "total_tokens": 4737056} {"current_steps": 22460, "total_steps": 181800, "loss": 0.1281, "lr": 4.99156709426023e-05, "epoch": 2.470847084708471, "percentage": 12.35, "elapsed_time": "0:52:44", "remaining_time": "6:14:12", "throughput": 1497.15, "total_tokens": 4738144} {"current_steps": 22465, "total_steps": 181800, "loss": 0.0263, "lr": 4.991547386210087e-05, "epoch": 2.4713971397139716, "percentage": 12.36, "elapsed_time": "0:52:45", "remaining_time": "6:14:11", "throughput": 1497.17, "total_tokens": 4739232} {"current_steps": 22470, "total_steps": 181800, "loss": 0.1346, "lr": 4.991527655196547e-05, "epoch": 2.4719471947194718, "percentage": 12.36, "elapsed_time": "0:52:46", "remaining_time": "6:14:10", "throughput": 1497.2, "total_tokens": 4740352} {"current_steps": 22475, "total_steps": 181800, "loss": 0.0901, "lr": 4.991507901219792e-05, "epoch": 2.4724972497249724, "percentage": 12.36, "elapsed_time": "0:52:46", "remaining_time": "6:14:09", "throughput": 1497.21, "total_tokens": 4741408} {"current_steps": 22480, "total_steps": 181800, "loss": 0.0468, "lr": 4.991488124280004e-05, "epoch": 2.473047304730473, "percentage": 12.37, "elapsed_time": "0:52:47", "remaining_time": "6:14:08", "throughput": 1497.21, "total_tokens": 4742464} {"current_steps": 22485, "total_steps": 181800, "loss": 0.0462, "lr": 4.991468324377366e-05, "epoch": 2.4735973597359737, "percentage": 12.37, "elapsed_time": "0:52:48", "remaining_time": "6:14:08", "throughput": 1497.24, "total_tokens": 4743584} {"current_steps": 22490, "total_steps": 181800, "loss": 0.0246, "lr": 4.99144850151206e-05, "epoch": 2.4741474147414744, "percentage": 12.37, "elapsed_time": "0:52:48", "remaining_time": "6:14:07", "throughput": 1497.27, "total_tokens": 4744704} {"current_steps": 22495, "total_steps": 181800, "loss": 0.0686, "lr": 4.9914286556842684e-05, "epoch": 2.4746974697469746, "percentage": 12.37, "elapsed_time": "0:52:49", "remaining_time": "6:14:06", "throughput": 1497.28, "total_tokens": 4745760} {"current_steps": 22500, "total_steps": 181800, "loss": 0.0936, "lr": 4.991408786894175e-05, "epoch": 2.4752475247524752, "percentage": 12.38, "elapsed_time": "0:52:50", "remaining_time": "6:14:05", "throughput": 1497.29, "total_tokens": 4746816} {"current_steps": 22505, "total_steps": 181800, "loss": 0.106, "lr": 4.991388895141961e-05, "epoch": 2.475797579757976, "percentage": 12.38, "elapsed_time": "0:52:50", "remaining_time": "6:14:04", "throughput": 1497.32, "total_tokens": 4747968} {"current_steps": 22510, "total_steps": 181800, "loss": 0.1367, "lr": 4.991368980427812e-05, "epoch": 2.4763476347634765, "percentage": 12.38, "elapsed_time": "0:52:51", "remaining_time": "6:14:03", "throughput": 1497.34, "total_tokens": 4749056} {"current_steps": 22515, "total_steps": 181800, "loss": 0.1473, "lr": 4.9913490427519106e-05, "epoch": 2.4768976897689767, "percentage": 12.38, "elapsed_time": "0:52:52", "remaining_time": "6:14:03", "throughput": 1497.37, "total_tokens": 4750176} {"current_steps": 22520, "total_steps": 181800, "loss": 0.0117, "lr": 4.9913290821144396e-05, "epoch": 2.4774477447744774, "percentage": 12.39, "elapsed_time": "0:52:53", "remaining_time": "6:14:02", "throughput": 1497.36, "total_tokens": 4751200} {"current_steps": 22525, "total_steps": 181800, "loss": 0.1151, "lr": 4.991309098515585e-05, "epoch": 2.477997799779978, "percentage": 12.39, "elapsed_time": "0:52:53", "remaining_time": "6:14:01", "throughput": 1497.4, "total_tokens": 4752352} {"current_steps": 22530, "total_steps": 181800, "loss": 0.0674, "lr": 4.99128909195553e-05, "epoch": 2.4785478547854787, "percentage": 12.39, "elapsed_time": "0:52:54", "remaining_time": "6:14:00", "throughput": 1497.41, "total_tokens": 4753408} {"current_steps": 22535, "total_steps": 181800, "loss": 0.1041, "lr": 4.9912690624344584e-05, "epoch": 2.479097909790979, "percentage": 12.4, "elapsed_time": "0:52:55", "remaining_time": "6:13:59", "throughput": 1497.41, "total_tokens": 4754432} {"current_steps": 22540, "total_steps": 181800, "loss": 0.0578, "lr": 4.991249009952556e-05, "epoch": 2.4796479647964795, "percentage": 12.4, "elapsed_time": "0:52:55", "remaining_time": "6:13:59", "throughput": 1497.4, "total_tokens": 4755456} {"current_steps": 22545, "total_steps": 181800, "loss": 0.0541, "lr": 4.991228934510005e-05, "epoch": 2.48019801980198, "percentage": 12.4, "elapsed_time": "0:52:56", "remaining_time": "6:13:58", "throughput": 1497.41, "total_tokens": 4756512} {"current_steps": 22550, "total_steps": 181800, "loss": 0.0379, "lr": 4.9912088361069945e-05, "epoch": 2.480748074807481, "percentage": 12.4, "elapsed_time": "0:52:57", "remaining_time": "6:13:57", "throughput": 1497.43, "total_tokens": 4757600} {"current_steps": 22555, "total_steps": 181800, "loss": 0.0363, "lr": 4.991188714743706e-05, "epoch": 2.4812981298129815, "percentage": 12.41, "elapsed_time": "0:52:57", "remaining_time": "6:13:56", "throughput": 1497.46, "total_tokens": 4758720} {"current_steps": 22560, "total_steps": 181800, "loss": 0.0444, "lr": 4.991168570420327e-05, "epoch": 2.4818481848184817, "percentage": 12.41, "elapsed_time": "0:52:58", "remaining_time": "6:13:55", "throughput": 1497.46, "total_tokens": 4759776} {"current_steps": 22565, "total_steps": 181800, "loss": 0.083, "lr": 4.991148403137043e-05, "epoch": 2.4823982398239823, "percentage": 12.41, "elapsed_time": "0:52:59", "remaining_time": "6:13:55", "throughput": 1497.47, "total_tokens": 4760832} {"current_steps": 22570, "total_steps": 181800, "loss": 0.0868, "lr": 4.991128212894039e-05, "epoch": 2.482948294829483, "percentage": 12.41, "elapsed_time": "0:52:59", "remaining_time": "6:13:54", "throughput": 1497.47, "total_tokens": 4761856} {"current_steps": 22575, "total_steps": 181800, "loss": 0.1104, "lr": 4.9911079996915014e-05, "epoch": 2.4834983498349836, "percentage": 12.42, "elapsed_time": "0:53:00", "remaining_time": "6:13:53", "throughput": 1497.46, "total_tokens": 4762848} {"current_steps": 22580, "total_steps": 181800, "loss": 0.1115, "lr": 4.991087763529618e-05, "epoch": 2.4840484048404843, "percentage": 12.42, "elapsed_time": "0:53:01", "remaining_time": "6:13:52", "throughput": 1497.47, "total_tokens": 4763904} {"current_steps": 22585, "total_steps": 181800, "loss": 0.0756, "lr": 4.991067504408573e-05, "epoch": 2.4845984598459845, "percentage": 12.42, "elapsed_time": "0:53:01", "remaining_time": "6:13:51", "throughput": 1497.46, "total_tokens": 4764928} {"current_steps": 22590, "total_steps": 181800, "loss": 0.0196, "lr": 4.991047222328554e-05, "epoch": 2.485148514851485, "percentage": 12.43, "elapsed_time": "0:53:02", "remaining_time": "6:13:50", "throughput": 1497.47, "total_tokens": 4765984} {"current_steps": 22595, "total_steps": 181800, "loss": 0.0184, "lr": 4.991026917289748e-05, "epoch": 2.485698569856986, "percentage": 12.43, "elapsed_time": "0:53:03", "remaining_time": "6:13:50", "throughput": 1497.48, "total_tokens": 4767040} {"current_steps": 22600, "total_steps": 181800, "loss": 0.0539, "lr": 4.991006589292343e-05, "epoch": 2.4862486248624864, "percentage": 12.43, "elapsed_time": "0:53:04", "remaining_time": "6:13:49", "throughput": 1497.5, "total_tokens": 4768128} {"current_steps": 22605, "total_steps": 181800, "loss": 0.1007, "lr": 4.990986238336526e-05, "epoch": 2.4867986798679866, "percentage": 12.43, "elapsed_time": "0:53:04", "remaining_time": "6:13:48", "throughput": 1497.5, "total_tokens": 4769152} {"current_steps": 22610, "total_steps": 181800, "loss": 0.0262, "lr": 4.990965864422483e-05, "epoch": 2.4873487348734873, "percentage": 12.44, "elapsed_time": "0:53:05", "remaining_time": "6:13:47", "throughput": 1497.52, "total_tokens": 4770240} {"current_steps": 22615, "total_steps": 181800, "loss": 0.0808, "lr": 4.990945467550403e-05, "epoch": 2.487898789878988, "percentage": 12.44, "elapsed_time": "0:53:06", "remaining_time": "6:13:46", "throughput": 1497.53, "total_tokens": 4771296} {"current_steps": 22620, "total_steps": 181800, "loss": 0.0469, "lr": 4.9909250477204746e-05, "epoch": 2.4884488448844886, "percentage": 12.44, "elapsed_time": "0:53:06", "remaining_time": "6:13:45", "throughput": 1497.52, "total_tokens": 4772288} {"current_steps": 22625, "total_steps": 181800, "loss": 0.0647, "lr": 4.9909046049328846e-05, "epoch": 2.488998899889989, "percentage": 12.44, "elapsed_time": "0:53:07", "remaining_time": "6:13:45", "throughput": 1497.52, "total_tokens": 4773312} {"current_steps": 22630, "total_steps": 181800, "loss": 0.0795, "lr": 4.9908841391878225e-05, "epoch": 2.4895489548954894, "percentage": 12.45, "elapsed_time": "0:53:08", "remaining_time": "6:13:44", "throughput": 1497.55, "total_tokens": 4774432} {"current_steps": 22635, "total_steps": 181800, "loss": 0.1193, "lr": 4.990863650485476e-05, "epoch": 2.49009900990099, "percentage": 12.45, "elapsed_time": "0:53:08", "remaining_time": "6:13:43", "throughput": 1497.55, "total_tokens": 4775488} {"current_steps": 22640, "total_steps": 181800, "loss": 0.1857, "lr": 4.990843138826035e-05, "epoch": 2.4906490649064907, "percentage": 12.45, "elapsed_time": "0:53:09", "remaining_time": "6:13:42", "throughput": 1497.54, "total_tokens": 4776480} {"current_steps": 22645, "total_steps": 181800, "loss": 0.1205, "lr": 4.990822604209688e-05, "epoch": 2.4911991199119914, "percentage": 12.46, "elapsed_time": "0:53:10", "remaining_time": "6:13:41", "throughput": 1497.55, "total_tokens": 4777536} {"current_steps": 22650, "total_steps": 181800, "loss": 0.091, "lr": 4.990802046636624e-05, "epoch": 2.4917491749174916, "percentage": 12.46, "elapsed_time": "0:53:10", "remaining_time": "6:13:41", "throughput": 1497.56, "total_tokens": 4778592} {"current_steps": 22655, "total_steps": 181800, "loss": 0.0632, "lr": 4.990781466107033e-05, "epoch": 2.4922992299229922, "percentage": 12.46, "elapsed_time": "0:53:11", "remaining_time": "6:13:40", "throughput": 1497.57, "total_tokens": 4779680} {"current_steps": 22660, "total_steps": 181800, "loss": 0.0908, "lr": 4.990760862621104e-05, "epoch": 2.492849284928493, "percentage": 12.46, "elapsed_time": "0:53:12", "remaining_time": "6:13:39", "throughput": 1497.62, "total_tokens": 4780864} {"current_steps": 22665, "total_steps": 181800, "loss": 0.0322, "lr": 4.990740236179028e-05, "epoch": 2.4933993399339935, "percentage": 12.47, "elapsed_time": "0:53:12", "remaining_time": "6:13:38", "throughput": 1497.64, "total_tokens": 4781952} {"current_steps": 22670, "total_steps": 181800, "loss": 0.1321, "lr": 4.990719586780994e-05, "epoch": 2.493949394939494, "percentage": 12.47, "elapsed_time": "0:53:13", "remaining_time": "6:13:37", "throughput": 1497.65, "total_tokens": 4783008} {"current_steps": 22675, "total_steps": 181800, "loss": 0.0924, "lr": 4.990698914427193e-05, "epoch": 2.4944994499449944, "percentage": 12.47, "elapsed_time": "0:53:14", "remaining_time": "6:13:36", "throughput": 1497.66, "total_tokens": 4784064} {"current_steps": 22680, "total_steps": 181800, "loss": 0.0854, "lr": 4.990678219117815e-05, "epoch": 2.495049504950495, "percentage": 12.48, "elapsed_time": "0:53:15", "remaining_time": "6:13:36", "throughput": 1497.67, "total_tokens": 4785120} {"current_steps": 22685, "total_steps": 181800, "loss": 0.0775, "lr": 4.990657500853051e-05, "epoch": 2.4955995599559957, "percentage": 12.48, "elapsed_time": "0:53:15", "remaining_time": "6:13:35", "throughput": 1497.68, "total_tokens": 4786208} {"current_steps": 22690, "total_steps": 181800, "loss": 0.1333, "lr": 4.990636759633092e-05, "epoch": 2.4961496149614963, "percentage": 12.48, "elapsed_time": "0:53:16", "remaining_time": "6:13:34", "throughput": 1497.67, "total_tokens": 4787200} {"current_steps": 22695, "total_steps": 181800, "loss": 0.0464, "lr": 4.990615995458129e-05, "epoch": 2.4966996699669965, "percentage": 12.48, "elapsed_time": "0:53:17", "remaining_time": "6:13:33", "throughput": 1497.66, "total_tokens": 4788192} {"current_steps": 22700, "total_steps": 181800, "loss": 0.1386, "lr": 4.9905952083283534e-05, "epoch": 2.497249724972497, "percentage": 12.49, "elapsed_time": "0:53:17", "remaining_time": "6:13:32", "throughput": 1497.67, "total_tokens": 4789280} {"current_steps": 22705, "total_steps": 181800, "loss": 0.046, "lr": 4.990574398243957e-05, "epoch": 2.497799779977998, "percentage": 12.49, "elapsed_time": "0:53:18", "remaining_time": "6:13:32", "throughput": 1497.7, "total_tokens": 4790400} {"current_steps": 22710, "total_steps": 181800, "loss": 0.091, "lr": 4.990553565205132e-05, "epoch": 2.4983498349834985, "percentage": 12.49, "elapsed_time": "0:53:19", "remaining_time": "6:13:31", "throughput": 1497.7, "total_tokens": 4791424} {"current_steps": 22715, "total_steps": 181800, "loss": 0.1121, "lr": 4.990532709212069e-05, "epoch": 2.4988998899889987, "percentage": 12.49, "elapsed_time": "0:53:19", "remaining_time": "6:13:30", "throughput": 1497.73, "total_tokens": 4792544} {"current_steps": 22720, "total_steps": 181800, "loss": 0.2129, "lr": 4.990511830264961e-05, "epoch": 2.4994499449944994, "percentage": 12.5, "elapsed_time": "0:53:20", "remaining_time": "6:13:29", "throughput": 1497.74, "total_tokens": 4793600} {"current_steps": 22725, "total_steps": 181800, "loss": 0.0488, "lr": 4.990490928364001e-05, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:53:21", "remaining_time": "6:13:28", "throughput": 1497.74, "total_tokens": 4794624} {"current_steps": 22730, "total_steps": 181800, "loss": 0.1183, "lr": 4.990470003509382e-05, "epoch": 2.5005500550055006, "percentage": 12.5, "elapsed_time": "0:53:21", "remaining_time": "6:13:27", "throughput": 1497.74, "total_tokens": 4795648} {"current_steps": 22735, "total_steps": 181800, "loss": 0.065, "lr": 4.990449055701295e-05, "epoch": 2.5011001100110013, "percentage": 12.51, "elapsed_time": "0:53:22", "remaining_time": "6:13:27", "throughput": 1497.76, "total_tokens": 4796768} {"current_steps": 22740, "total_steps": 181800, "loss": 0.0536, "lr": 4.990428084939934e-05, "epoch": 2.5016501650165015, "percentage": 12.51, "elapsed_time": "0:53:23", "remaining_time": "6:13:26", "throughput": 1497.77, "total_tokens": 4797824} {"current_steps": 22745, "total_steps": 181800, "loss": 0.0676, "lr": 4.990407091225493e-05, "epoch": 2.502200220022002, "percentage": 12.51, "elapsed_time": "0:53:23", "remaining_time": "6:13:25", "throughput": 1497.79, "total_tokens": 4798912} {"current_steps": 22750, "total_steps": 181800, "loss": 0.0666, "lr": 4.990386074558164e-05, "epoch": 2.502750275027503, "percentage": 12.51, "elapsed_time": "0:53:24", "remaining_time": "6:13:24", "throughput": 1497.79, "total_tokens": 4799936} {"current_steps": 22755, "total_steps": 181800, "loss": 0.0391, "lr": 4.9903650349381424e-05, "epoch": 2.5033003300330035, "percentage": 12.52, "elapsed_time": "0:53:25", "remaining_time": "6:13:23", "throughput": 1497.79, "total_tokens": 4800992} {"current_steps": 22760, "total_steps": 181800, "loss": 0.0818, "lr": 4.990343972365621e-05, "epoch": 2.503850385038504, "percentage": 12.52, "elapsed_time": "0:53:26", "remaining_time": "6:13:23", "throughput": 1497.82, "total_tokens": 4802112} {"current_steps": 22765, "total_steps": 181800, "loss": 0.1029, "lr": 4.9903228868407936e-05, "epoch": 2.5044004400440043, "percentage": 12.52, "elapsed_time": "0:53:26", "remaining_time": "6:13:22", "throughput": 1497.82, "total_tokens": 4803136} {"current_steps": 22770, "total_steps": 181800, "loss": 0.0323, "lr": 4.990301778363856e-05, "epoch": 2.504950495049505, "percentage": 12.52, "elapsed_time": "0:53:27", "remaining_time": "6:13:21", "throughput": 1497.83, "total_tokens": 4804192} {"current_steps": 22775, "total_steps": 181800, "loss": 0.0534, "lr": 4.990280646935002e-05, "epoch": 2.5055005500550056, "percentage": 12.53, "elapsed_time": "0:53:28", "remaining_time": "6:13:20", "throughput": 1497.82, "total_tokens": 4805216} {"current_steps": 22780, "total_steps": 181800, "loss": 0.0965, "lr": 4.990259492554425e-05, "epoch": 2.506050605060506, "percentage": 12.53, "elapsed_time": "0:53:28", "remaining_time": "6:13:19", "throughput": 1497.84, "total_tokens": 4806304} {"current_steps": 22785, "total_steps": 181800, "loss": 0.0643, "lr": 4.990238315222322e-05, "epoch": 2.5066006600660065, "percentage": 12.53, "elapsed_time": "0:53:29", "remaining_time": "6:13:18", "throughput": 1497.87, "total_tokens": 4807424} {"current_steps": 22790, "total_steps": 181800, "loss": 0.1519, "lr": 4.9902171149388875e-05, "epoch": 2.507150715071507, "percentage": 12.54, "elapsed_time": "0:53:30", "remaining_time": "6:13:18", "throughput": 1497.87, "total_tokens": 4808480} {"current_steps": 22795, "total_steps": 181800, "loss": 0.0575, "lr": 4.9901958917043164e-05, "epoch": 2.5077007700770078, "percentage": 12.54, "elapsed_time": "0:53:30", "remaining_time": "6:13:17", "throughput": 1497.87, "total_tokens": 4809504} {"current_steps": 22800, "total_steps": 181800, "loss": 0.0974, "lr": 4.990174645518805e-05, "epoch": 2.5082508250825084, "percentage": 12.54, "elapsed_time": "0:53:31", "remaining_time": "6:13:16", "throughput": 1497.88, "total_tokens": 4810592} {"current_steps": 22805, "total_steps": 181800, "loss": 0.1053, "lr": 4.990153376382548e-05, "epoch": 2.5088008800880086, "percentage": 12.54, "elapsed_time": "0:53:32", "remaining_time": "6:13:15", "throughput": 1497.89, "total_tokens": 4811648} {"current_steps": 22810, "total_steps": 181800, "loss": 0.0625, "lr": 4.9901320842957436e-05, "epoch": 2.5093509350935093, "percentage": 12.55, "elapsed_time": "0:53:32", "remaining_time": "6:13:15", "throughput": 1497.91, "total_tokens": 4812736} {"current_steps": 22815, "total_steps": 181800, "loss": 0.0877, "lr": 4.9901107692585856e-05, "epoch": 2.50990099009901, "percentage": 12.55, "elapsed_time": "0:53:33", "remaining_time": "6:13:14", "throughput": 1497.9, "total_tokens": 4813728} {"current_steps": 22820, "total_steps": 181800, "loss": 0.0496, "lr": 4.990089431271272e-05, "epoch": 2.5104510451045106, "percentage": 12.55, "elapsed_time": "0:53:34", "remaining_time": "6:13:13", "throughput": 1497.92, "total_tokens": 4814816} {"current_steps": 22825, "total_steps": 181800, "loss": 0.0682, "lr": 4.990068070333999e-05, "epoch": 2.511001100110011, "percentage": 12.56, "elapsed_time": "0:53:35", "remaining_time": "6:13:12", "throughput": 1497.9, "total_tokens": 4815808} {"current_steps": 22830, "total_steps": 181800, "loss": 0.0776, "lr": 4.990046686446963e-05, "epoch": 2.5115511551155114, "percentage": 12.56, "elapsed_time": "0:53:35", "remaining_time": "6:13:11", "throughput": 1497.91, "total_tokens": 4816864} {"current_steps": 22835, "total_steps": 181800, "loss": 0.0739, "lr": 4.990025279610362e-05, "epoch": 2.512101210121012, "percentage": 12.56, "elapsed_time": "0:53:36", "remaining_time": "6:13:10", "throughput": 1497.91, "total_tokens": 4817888} {"current_steps": 22840, "total_steps": 181800, "loss": 0.061, "lr": 4.9900038498243926e-05, "epoch": 2.5126512651265127, "percentage": 12.56, "elapsed_time": "0:53:37", "remaining_time": "6:13:10", "throughput": 1497.93, "total_tokens": 4818976} {"current_steps": 22845, "total_steps": 181800, "loss": 0.1126, "lr": 4.9899823970892524e-05, "epoch": 2.5132013201320134, "percentage": 12.57, "elapsed_time": "0:53:37", "remaining_time": "6:13:09", "throughput": 1497.94, "total_tokens": 4820032} {"current_steps": 22850, "total_steps": 181800, "loss": 0.062, "lr": 4.989960921405139e-05, "epoch": 2.513751375137514, "percentage": 12.57, "elapsed_time": "0:53:38", "remaining_time": "6:13:08", "throughput": 1497.94, "total_tokens": 4821056} {"current_steps": 22855, "total_steps": 181800, "loss": 0.1136, "lr": 4.989939422772252e-05, "epoch": 2.514301430143014, "percentage": 12.57, "elapsed_time": "0:53:39", "remaining_time": "6:13:07", "throughput": 1497.97, "total_tokens": 4822176} {"current_steps": 22860, "total_steps": 181800, "loss": 0.0778, "lr": 4.989917901190787e-05, "epoch": 2.514851485148515, "percentage": 12.57, "elapsed_time": "0:53:39", "remaining_time": "6:13:06", "throughput": 1497.98, "total_tokens": 4823232} {"current_steps": 22865, "total_steps": 181800, "loss": 0.1064, "lr": 4.989896356660944e-05, "epoch": 2.5154015401540155, "percentage": 12.58, "elapsed_time": "0:53:40", "remaining_time": "6:13:05", "throughput": 1497.98, "total_tokens": 4824288} {"current_steps": 22870, "total_steps": 181800, "loss": 0.0517, "lr": 4.98987478918292e-05, "epoch": 2.5159515951595157, "percentage": 12.58, "elapsed_time": "0:53:41", "remaining_time": "6:13:05", "throughput": 1497.98, "total_tokens": 4825312} {"current_steps": 22875, "total_steps": 181800, "loss": 0.0113, "lr": 4.989853198756915e-05, "epoch": 2.5165016501650164, "percentage": 12.58, "elapsed_time": "0:53:41", "remaining_time": "6:13:04", "throughput": 1497.97, "total_tokens": 4826304} {"current_steps": 22880, "total_steps": 181800, "loss": 0.0481, "lr": 4.989831585383129e-05, "epoch": 2.517051705170517, "percentage": 12.59, "elapsed_time": "0:53:42", "remaining_time": "6:13:03", "throughput": 1497.98, "total_tokens": 4827360} {"current_steps": 22885, "total_steps": 181800, "loss": 0.0845, "lr": 4.989809949061759e-05, "epoch": 2.5176017601760177, "percentage": 12.59, "elapsed_time": "0:53:43", "remaining_time": "6:13:02", "throughput": 1497.99, "total_tokens": 4828448} {"current_steps": 22890, "total_steps": 181800, "loss": 0.1107, "lr": 4.989788289793006e-05, "epoch": 2.5181518151815183, "percentage": 12.59, "elapsed_time": "0:53:43", "remaining_time": "6:13:01", "throughput": 1498.0, "total_tokens": 4829504} {"current_steps": 22895, "total_steps": 181800, "loss": 0.0764, "lr": 4.989766607577069e-05, "epoch": 2.5187018701870185, "percentage": 12.59, "elapsed_time": "0:53:44", "remaining_time": "6:13:01", "throughput": 1498.01, "total_tokens": 4830560} {"current_steps": 22900, "total_steps": 181800, "loss": 0.0481, "lr": 4.989744902414147e-05, "epoch": 2.519251925192519, "percentage": 12.6, "elapsed_time": "0:53:45", "remaining_time": "6:13:00", "throughput": 1498.01, "total_tokens": 4831616} {"current_steps": 22905, "total_steps": 181800, "loss": 0.1037, "lr": 4.989723174304441e-05, "epoch": 2.51980198019802, "percentage": 12.6, "elapsed_time": "0:53:46", "remaining_time": "6:12:59", "throughput": 1498.02, "total_tokens": 4832672} {"current_steps": 22910, "total_steps": 181800, "loss": 0.0551, "lr": 4.9897014232481526e-05, "epoch": 2.5203520352035205, "percentage": 12.6, "elapsed_time": "0:53:46", "remaining_time": "6:12:58", "throughput": 1498.03, "total_tokens": 4833728} {"current_steps": 22915, "total_steps": 181800, "loss": 0.0945, "lr": 4.98967964924548e-05, "epoch": 2.520902090209021, "percentage": 12.6, "elapsed_time": "0:53:47", "remaining_time": "6:12:57", "throughput": 1498.04, "total_tokens": 4834816} {"current_steps": 22920, "total_steps": 181800, "loss": 0.0307, "lr": 4.9896578522966245e-05, "epoch": 2.5214521452145213, "percentage": 12.61, "elapsed_time": "0:53:48", "remaining_time": "6:12:57", "throughput": 1498.03, "total_tokens": 4835808} {"current_steps": 22925, "total_steps": 181800, "loss": 0.035, "lr": 4.9896360324017874e-05, "epoch": 2.522002200220022, "percentage": 12.61, "elapsed_time": "0:53:48", "remaining_time": "6:12:56", "throughput": 1498.05, "total_tokens": 4836896} {"current_steps": 22930, "total_steps": 181800, "loss": 0.1062, "lr": 4.98961418956117e-05, "epoch": 2.5225522552255226, "percentage": 12.61, "elapsed_time": "0:53:49", "remaining_time": "6:12:55", "throughput": 1498.07, "total_tokens": 4837984} {"current_steps": 22935, "total_steps": 181800, "loss": 0.0805, "lr": 4.989592323774973e-05, "epoch": 2.523102310231023, "percentage": 12.62, "elapsed_time": "0:53:50", "remaining_time": "6:12:54", "throughput": 1498.06, "total_tokens": 4839008} {"current_steps": 22940, "total_steps": 181800, "loss": 0.0512, "lr": 4.989570435043398e-05, "epoch": 2.523652365236524, "percentage": 12.62, "elapsed_time": "0:53:50", "remaining_time": "6:12:53", "throughput": 1498.07, "total_tokens": 4840064} {"current_steps": 22945, "total_steps": 181800, "loss": 0.1638, "lr": 4.9895485233666476e-05, "epoch": 2.524202420242024, "percentage": 12.62, "elapsed_time": "0:53:51", "remaining_time": "6:12:52", "throughput": 1498.1, "total_tokens": 4841184} {"current_steps": 22950, "total_steps": 181800, "loss": 0.0407, "lr": 4.989526588744923e-05, "epoch": 2.5247524752475248, "percentage": 12.62, "elapsed_time": "0:53:52", "remaining_time": "6:12:52", "throughput": 1498.1, "total_tokens": 4842208} {"current_steps": 22955, "total_steps": 181800, "loss": 0.0677, "lr": 4.989504631178426e-05, "epoch": 2.5253025302530254, "percentage": 12.63, "elapsed_time": "0:53:52", "remaining_time": "6:12:51", "throughput": 1498.1, "total_tokens": 4843264} {"current_steps": 22960, "total_steps": 181800, "loss": 0.0325, "lr": 4.989482650667359e-05, "epoch": 2.5258525852585256, "percentage": 12.63, "elapsed_time": "0:53:53", "remaining_time": "6:12:50", "throughput": 1498.1, "total_tokens": 4844288} {"current_steps": 22965, "total_steps": 181800, "loss": 0.0497, "lr": 4.9894606472119256e-05, "epoch": 2.5264026402640263, "percentage": 12.63, "elapsed_time": "0:53:54", "remaining_time": "6:12:49", "throughput": 1498.1, "total_tokens": 4845344} {"current_steps": 22970, "total_steps": 181800, "loss": 0.0645, "lr": 4.9894386208123276e-05, "epoch": 2.526952695269527, "percentage": 12.63, "elapsed_time": "0:53:55", "remaining_time": "6:12:49", "throughput": 1498.09, "total_tokens": 4846336} {"current_steps": 22975, "total_steps": 181800, "loss": 0.102, "lr": 4.989416571468768e-05, "epoch": 2.5275027502750276, "percentage": 12.64, "elapsed_time": "0:53:55", "remaining_time": "6:12:48", "throughput": 1498.11, "total_tokens": 4847424} {"current_steps": 22980, "total_steps": 181800, "loss": 0.0538, "lr": 4.9893944991814514e-05, "epoch": 2.5280528052805282, "percentage": 12.64, "elapsed_time": "0:53:56", "remaining_time": "6:12:47", "throughput": 1498.13, "total_tokens": 4848544} {"current_steps": 22985, "total_steps": 181800, "loss": 0.0855, "lr": 4.98937240395058e-05, "epoch": 2.5286028602860284, "percentage": 12.64, "elapsed_time": "0:53:57", "remaining_time": "6:12:46", "throughput": 1498.14, "total_tokens": 4849600} {"current_steps": 22990, "total_steps": 181800, "loss": 0.1154, "lr": 4.989350285776357e-05, "epoch": 2.529152915291529, "percentage": 12.65, "elapsed_time": "0:53:57", "remaining_time": "6:12:45", "throughput": 1498.13, "total_tokens": 4850592} {"current_steps": 22995, "total_steps": 181800, "loss": 0.1164, "lr": 4.989328144658987e-05, "epoch": 2.5297029702970297, "percentage": 12.65, "elapsed_time": "0:53:58", "remaining_time": "6:12:45", "throughput": 1498.14, "total_tokens": 4851680} {"current_steps": 23000, "total_steps": 181800, "loss": 0.0236, "lr": 4.989305980598674e-05, "epoch": 2.5302530253025304, "percentage": 12.65, "elapsed_time": "0:53:59", "remaining_time": "6:12:44", "throughput": 1498.14, "total_tokens": 4852704} {"current_steps": 23005, "total_steps": 181800, "loss": 0.0384, "lr": 4.989283793595623e-05, "epoch": 2.530803080308031, "percentage": 12.65, "elapsed_time": "0:53:59", "remaining_time": "6:12:43", "throughput": 1498.16, "total_tokens": 4853792} {"current_steps": 23010, "total_steps": 181800, "loss": 0.0543, "lr": 4.9892615836500375e-05, "epoch": 2.5313531353135312, "percentage": 12.66, "elapsed_time": "0:54:00", "remaining_time": "6:12:42", "throughput": 1498.16, "total_tokens": 4854848} {"current_steps": 23015, "total_steps": 181800, "loss": 0.1162, "lr": 4.989239350762122e-05, "epoch": 2.531903190319032, "percentage": 12.66, "elapsed_time": "0:54:01", "remaining_time": "6:12:41", "throughput": 1498.17, "total_tokens": 4855904} {"current_steps": 23020, "total_steps": 181800, "loss": 0.0283, "lr": 4.989217094932083e-05, "epoch": 2.5324532453245325, "percentage": 12.66, "elapsed_time": "0:54:01", "remaining_time": "6:12:41", "throughput": 1498.19, "total_tokens": 4856992} {"current_steps": 23025, "total_steps": 181800, "loss": 0.049, "lr": 4.989194816160123e-05, "epoch": 2.5330033003300327, "percentage": 12.67, "elapsed_time": "0:54:02", "remaining_time": "6:12:40", "throughput": 1498.2, "total_tokens": 4858080} {"current_steps": 23030, "total_steps": 181800, "loss": 0.076, "lr": 4.9891725144464495e-05, "epoch": 2.533553355335534, "percentage": 12.67, "elapsed_time": "0:54:03", "remaining_time": "6:12:39", "throughput": 1498.18, "total_tokens": 4859040} {"current_steps": 23035, "total_steps": 181800, "loss": 0.0698, "lr": 4.9891501897912676e-05, "epoch": 2.534103410341034, "percentage": 12.67, "elapsed_time": "0:54:03", "remaining_time": "6:12:38", "throughput": 1498.19, "total_tokens": 4860096} {"current_steps": 23040, "total_steps": 181800, "loss": 0.039, "lr": 4.989127842194782e-05, "epoch": 2.5346534653465347, "percentage": 12.67, "elapsed_time": "0:54:04", "remaining_time": "6:12:37", "throughput": 1498.2, "total_tokens": 4861152} {"current_steps": 23045, "total_steps": 181800, "loss": 0.0447, "lr": 4.9891054716572e-05, "epoch": 2.5352035203520353, "percentage": 12.68, "elapsed_time": "0:54:05", "remaining_time": "6:12:36", "throughput": 1498.22, "total_tokens": 4862272} {"current_steps": 23050, "total_steps": 181800, "loss": 0.1096, "lr": 4.989083078178727e-05, "epoch": 2.5357535753575355, "percentage": 12.68, "elapsed_time": "0:54:06", "remaining_time": "6:12:36", "throughput": 1498.24, "total_tokens": 4863360} {"current_steps": 23055, "total_steps": 181800, "loss": 0.1089, "lr": 4.9890606617595706e-05, "epoch": 2.536303630363036, "percentage": 12.68, "elapsed_time": "0:54:06", "remaining_time": "6:12:35", "throughput": 1498.24, "total_tokens": 4864384} {"current_steps": 23060, "total_steps": 181800, "loss": 0.0717, "lr": 4.989038222399936e-05, "epoch": 2.536853685368537, "percentage": 12.68, "elapsed_time": "0:54:07", "remaining_time": "6:12:34", "throughput": 1498.24, "total_tokens": 4865440} {"current_steps": 23065, "total_steps": 181800, "loss": 0.028, "lr": 4.989015760100029e-05, "epoch": 2.5374037403740375, "percentage": 12.69, "elapsed_time": "0:54:08", "remaining_time": "6:12:33", "throughput": 1498.25, "total_tokens": 4866496} {"current_steps": 23070, "total_steps": 181800, "loss": 0.0574, "lr": 4.9889932748600596e-05, "epoch": 2.537953795379538, "percentage": 12.69, "elapsed_time": "0:54:08", "remaining_time": "6:12:32", "throughput": 1498.28, "total_tokens": 4867616} {"current_steps": 23075, "total_steps": 181800, "loss": 0.1168, "lr": 4.988970766680233e-05, "epoch": 2.5385038503850383, "percentage": 12.69, "elapsed_time": "0:54:09", "remaining_time": "6:12:32", "throughput": 1498.29, "total_tokens": 4868704} {"current_steps": 23080, "total_steps": 181800, "loss": 0.0902, "lr": 4.9889482355607574e-05, "epoch": 2.539053905390539, "percentage": 12.7, "elapsed_time": "0:54:10", "remaining_time": "6:12:31", "throughput": 1498.33, "total_tokens": 4869856} {"current_steps": 23085, "total_steps": 181800, "loss": 0.0663, "lr": 4.9889256815018405e-05, "epoch": 2.5396039603960396, "percentage": 12.7, "elapsed_time": "0:54:10", "remaining_time": "6:12:30", "throughput": 1498.36, "total_tokens": 4870976} {"current_steps": 23090, "total_steps": 181800, "loss": 0.0826, "lr": 4.988903104503689e-05, "epoch": 2.5401540154015403, "percentage": 12.7, "elapsed_time": "0:54:11", "remaining_time": "6:12:29", "throughput": 1498.38, "total_tokens": 4872064} {"current_steps": 23095, "total_steps": 181800, "loss": 0.0833, "lr": 4.988880504566513e-05, "epoch": 2.540704070407041, "percentage": 12.7, "elapsed_time": "0:54:12", "remaining_time": "6:12:28", "throughput": 1498.38, "total_tokens": 4873120} {"current_steps": 23100, "total_steps": 181800, "loss": 0.1886, "lr": 4.9888578816905187e-05, "epoch": 2.541254125412541, "percentage": 12.71, "elapsed_time": "0:54:12", "remaining_time": "6:12:28", "throughput": 1498.39, "total_tokens": 4874176} {"current_steps": 23105, "total_steps": 181800, "loss": 0.0224, "lr": 4.988835235875916e-05, "epoch": 2.541804180418042, "percentage": 12.71, "elapsed_time": "0:54:13", "remaining_time": "6:12:27", "throughput": 1498.39, "total_tokens": 4875232} {"current_steps": 23110, "total_steps": 181800, "loss": 0.0605, "lr": 4.9888125671229134e-05, "epoch": 2.5423542354235424, "percentage": 12.71, "elapsed_time": "0:54:14", "remaining_time": "6:12:26", "throughput": 1498.38, "total_tokens": 4876224} {"current_steps": 23115, "total_steps": 181800, "loss": 0.074, "lr": 4.98878987543172e-05, "epoch": 2.5429042904290426, "percentage": 12.71, "elapsed_time": "0:54:15", "remaining_time": "6:12:25", "throughput": 1498.39, "total_tokens": 4877280} {"current_steps": 23120, "total_steps": 181800, "loss": 0.1004, "lr": 4.988767160802543e-05, "epoch": 2.5434543454345433, "percentage": 12.72, "elapsed_time": "0:54:15", "remaining_time": "6:12:24", "throughput": 1498.37, "total_tokens": 4878272} {"current_steps": 23125, "total_steps": 181800, "loss": 0.0339, "lr": 4.988744423235594e-05, "epoch": 2.544004400440044, "percentage": 12.72, "elapsed_time": "0:54:16", "remaining_time": "6:12:24", "throughput": 1498.39, "total_tokens": 4879360} {"current_steps": 23130, "total_steps": 181800, "loss": 0.0306, "lr": 4.988721662731083e-05, "epoch": 2.5445544554455446, "percentage": 12.72, "elapsed_time": "0:54:17", "remaining_time": "6:12:23", "throughput": 1498.39, "total_tokens": 4880384} {"current_steps": 23135, "total_steps": 181800, "loss": 0.032, "lr": 4.988698879289217e-05, "epoch": 2.5451045104510452, "percentage": 12.73, "elapsed_time": "0:54:17", "remaining_time": "6:12:22", "throughput": 1498.4, "total_tokens": 4881472} {"current_steps": 23140, "total_steps": 181800, "loss": 0.1044, "lr": 4.988676072910209e-05, "epoch": 2.5456545654565454, "percentage": 12.73, "elapsed_time": "0:54:18", "remaining_time": "6:12:21", "throughput": 1498.41, "total_tokens": 4882528} {"current_steps": 23145, "total_steps": 181800, "loss": 0.0622, "lr": 4.988653243594267e-05, "epoch": 2.546204620462046, "percentage": 12.73, "elapsed_time": "0:54:19", "remaining_time": "6:12:20", "throughput": 1498.39, "total_tokens": 4883488} {"current_steps": 23150, "total_steps": 181800, "loss": 0.0464, "lr": 4.988630391341602e-05, "epoch": 2.5467546754675467, "percentage": 12.73, "elapsed_time": "0:54:19", "remaining_time": "6:12:20", "throughput": 1498.39, "total_tokens": 4884512} {"current_steps": 23155, "total_steps": 181800, "loss": 0.1096, "lr": 4.988607516152426e-05, "epoch": 2.5473047304730474, "percentage": 12.74, "elapsed_time": "0:54:20", "remaining_time": "6:12:19", "throughput": 1498.4, "total_tokens": 4885600} {"current_steps": 23160, "total_steps": 181800, "loss": 0.1401, "lr": 4.988584618026948e-05, "epoch": 2.547854785478548, "percentage": 12.74, "elapsed_time": "0:54:21", "remaining_time": "6:12:18", "throughput": 1498.43, "total_tokens": 4886720} {"current_steps": 23165, "total_steps": 181800, "loss": 0.1238, "lr": 4.988561696965379e-05, "epoch": 2.5484048404840483, "percentage": 12.74, "elapsed_time": "0:54:21", "remaining_time": "6:12:17", "throughput": 1498.45, "total_tokens": 4887808} {"current_steps": 23170, "total_steps": 181800, "loss": 0.0677, "lr": 4.988538752967932e-05, "epoch": 2.548954895489549, "percentage": 12.74, "elapsed_time": "0:54:22", "remaining_time": "6:12:16", "throughput": 1498.46, "total_tokens": 4888864} {"current_steps": 23175, "total_steps": 181800, "loss": 0.0745, "lr": 4.988515786034817e-05, "epoch": 2.5495049504950495, "percentage": 12.75, "elapsed_time": "0:54:23", "remaining_time": "6:12:16", "throughput": 1498.48, "total_tokens": 4889984} {"current_steps": 23180, "total_steps": 181800, "loss": 0.0249, "lr": 4.9884927961662466e-05, "epoch": 2.55005500550055, "percentage": 12.75, "elapsed_time": "0:54:23", "remaining_time": "6:12:15", "throughput": 1498.48, "total_tokens": 4891008} {"current_steps": 23185, "total_steps": 181800, "loss": 0.0934, "lr": 4.988469783362432e-05, "epoch": 2.550605060506051, "percentage": 12.75, "elapsed_time": "0:54:24", "remaining_time": "6:12:14", "throughput": 1498.48, "total_tokens": 4892032} {"current_steps": 23190, "total_steps": 181800, "loss": 0.0274, "lr": 4.988446747623585e-05, "epoch": 2.551155115511551, "percentage": 12.76, "elapsed_time": "0:54:25", "remaining_time": "6:12:13", "throughput": 1498.5, "total_tokens": 4893152} {"current_steps": 23195, "total_steps": 181800, "loss": 0.0661, "lr": 4.988423688949918e-05, "epoch": 2.5517051705170517, "percentage": 12.76, "elapsed_time": "0:54:26", "remaining_time": "6:12:12", "throughput": 1498.54, "total_tokens": 4894304} {"current_steps": 23200, "total_steps": 181800, "loss": 0.0168, "lr": 4.988400607341645e-05, "epoch": 2.5522552255225524, "percentage": 12.76, "elapsed_time": "0:54:26", "remaining_time": "6:12:12", "throughput": 1498.54, "total_tokens": 4895328} {"current_steps": 23205, "total_steps": 181800, "loss": 0.0202, "lr": 4.9883775027989773e-05, "epoch": 2.5528052805280526, "percentage": 12.76, "elapsed_time": "0:54:27", "remaining_time": "6:12:11", "throughput": 1498.54, "total_tokens": 4896384} {"current_steps": 23210, "total_steps": 181800, "loss": 0.0288, "lr": 4.988354375322128e-05, "epoch": 2.553355335533553, "percentage": 12.77, "elapsed_time": "0:54:28", "remaining_time": "6:12:10", "throughput": 1498.54, "total_tokens": 4897408} {"current_steps": 23215, "total_steps": 181800, "loss": 0.1035, "lr": 4.9883312249113105e-05, "epoch": 2.553905390539054, "percentage": 12.77, "elapsed_time": "0:54:28", "remaining_time": "6:12:09", "throughput": 1498.53, "total_tokens": 4898400} {"current_steps": 23220, "total_steps": 181800, "loss": 0.0546, "lr": 4.988308051566738e-05, "epoch": 2.5544554455445545, "percentage": 12.77, "elapsed_time": "0:54:29", "remaining_time": "6:12:08", "throughput": 1498.53, "total_tokens": 4899424} {"current_steps": 23225, "total_steps": 181800, "loss": 0.1005, "lr": 4.988284855288625e-05, "epoch": 2.555005500550055, "percentage": 12.78, "elapsed_time": "0:54:30", "remaining_time": "6:12:08", "throughput": 1498.55, "total_tokens": 4900512} {"current_steps": 23230, "total_steps": 181800, "loss": 0.0405, "lr": 4.988261636077184e-05, "epoch": 2.5555555555555554, "percentage": 12.78, "elapsed_time": "0:54:30", "remaining_time": "6:12:07", "throughput": 1498.57, "total_tokens": 4901632} {"current_steps": 23235, "total_steps": 181800, "loss": 0.04, "lr": 4.988238393932629e-05, "epoch": 2.556105610561056, "percentage": 12.78, "elapsed_time": "0:54:31", "remaining_time": "6:12:06", "throughput": 1498.56, "total_tokens": 4902624} {"current_steps": 23240, "total_steps": 181800, "loss": 0.0538, "lr": 4.988215128855175e-05, "epoch": 2.5566556655665567, "percentage": 12.78, "elapsed_time": "0:54:32", "remaining_time": "6:12:05", "throughput": 1498.56, "total_tokens": 4903648} {"current_steps": 23245, "total_steps": 181800, "loss": 0.097, "lr": 4.9881918408450356e-05, "epoch": 2.5572057205720573, "percentage": 12.79, "elapsed_time": "0:54:32", "remaining_time": "6:12:04", "throughput": 1498.59, "total_tokens": 4904768} {"current_steps": 23250, "total_steps": 181800, "loss": 0.0643, "lr": 4.988168529902427e-05, "epoch": 2.557755775577558, "percentage": 12.79, "elapsed_time": "0:54:33", "remaining_time": "6:12:03", "throughput": 1498.61, "total_tokens": 4905856} {"current_steps": 23255, "total_steps": 181800, "loss": 0.0828, "lr": 4.988145196027563e-05, "epoch": 2.558305830583058, "percentage": 12.79, "elapsed_time": "0:54:34", "remaining_time": "6:12:03", "throughput": 1498.63, "total_tokens": 4906944} {"current_steps": 23260, "total_steps": 181800, "loss": 0.0558, "lr": 4.9881218392206574e-05, "epoch": 2.558855885588559, "percentage": 12.79, "elapsed_time": "0:54:34", "remaining_time": "6:12:02", "throughput": 1498.65, "total_tokens": 4908064} {"current_steps": 23265, "total_steps": 181800, "loss": 0.0336, "lr": 4.988098459481928e-05, "epoch": 2.5594059405940595, "percentage": 12.8, "elapsed_time": "0:54:35", "remaining_time": "6:12:01", "throughput": 1498.66, "total_tokens": 4909120} {"current_steps": 23270, "total_steps": 181800, "loss": 0.0607, "lr": 4.988075056811589e-05, "epoch": 2.55995599559956, "percentage": 12.8, "elapsed_time": "0:54:36", "remaining_time": "6:12:00", "throughput": 1498.65, "total_tokens": 4910112} {"current_steps": 23275, "total_steps": 181800, "loss": 0.0628, "lr": 4.988051631209855e-05, "epoch": 2.5605060506050608, "percentage": 12.8, "elapsed_time": "0:54:37", "remaining_time": "6:11:59", "throughput": 1498.66, "total_tokens": 4911168} {"current_steps": 23280, "total_steps": 181800, "loss": 0.0765, "lr": 4.988028182676944e-05, "epoch": 2.561056105610561, "percentage": 12.81, "elapsed_time": "0:54:37", "remaining_time": "6:11:58", "throughput": 1498.7, "total_tokens": 4912320} {"current_steps": 23285, "total_steps": 181800, "loss": 0.1276, "lr": 4.98800471121307e-05, "epoch": 2.5616061606160616, "percentage": 12.81, "elapsed_time": "0:54:38", "remaining_time": "6:11:58", "throughput": 1498.7, "total_tokens": 4913344} {"current_steps": 23290, "total_steps": 181800, "loss": 0.0221, "lr": 4.987981216818451e-05, "epoch": 2.5621562156215623, "percentage": 12.81, "elapsed_time": "0:54:39", "remaining_time": "6:11:57", "throughput": 1498.71, "total_tokens": 4914432} {"current_steps": 23295, "total_steps": 181800, "loss": 0.0558, "lr": 4.9879576994933035e-05, "epoch": 2.5627062706270625, "percentage": 12.81, "elapsed_time": "0:54:39", "remaining_time": "6:11:56", "throughput": 1498.72, "total_tokens": 4915488} {"current_steps": 23300, "total_steps": 181800, "loss": 0.1168, "lr": 4.9879341592378435e-05, "epoch": 2.563256325632563, "percentage": 12.82, "elapsed_time": "0:54:40", "remaining_time": "6:11:55", "throughput": 1498.72, "total_tokens": 4916512} {"current_steps": 23305, "total_steps": 181800, "loss": 0.0503, "lr": 4.9879105960522875e-05, "epoch": 2.5638063806380638, "percentage": 12.82, "elapsed_time": "0:54:41", "remaining_time": "6:11:54", "throughput": 1498.73, "total_tokens": 4917568} {"current_steps": 23310, "total_steps": 181800, "loss": 0.0782, "lr": 4.9878870099368544e-05, "epoch": 2.5643564356435644, "percentage": 12.82, "elapsed_time": "0:54:41", "remaining_time": "6:11:54", "throughput": 1498.73, "total_tokens": 4918624} {"current_steps": 23315, "total_steps": 181800, "loss": 0.1089, "lr": 4.9878634008917604e-05, "epoch": 2.564906490649065, "percentage": 12.82, "elapsed_time": "0:54:42", "remaining_time": "6:11:53", "throughput": 1498.73, "total_tokens": 4919648} {"current_steps": 23320, "total_steps": 181800, "loss": 0.1314, "lr": 4.987839768917222e-05, "epoch": 2.5654565456545653, "percentage": 12.83, "elapsed_time": "0:54:43", "remaining_time": "6:11:52", "throughput": 1498.73, "total_tokens": 4920672} {"current_steps": 23325, "total_steps": 181800, "loss": 0.0989, "lr": 4.9878161140134594e-05, "epoch": 2.566006600660066, "percentage": 12.83, "elapsed_time": "0:54:43", "remaining_time": "6:11:51", "throughput": 1498.75, "total_tokens": 4921760} {"current_steps": 23330, "total_steps": 181800, "loss": 0.0946, "lr": 4.9877924361806896e-05, "epoch": 2.5665566556655666, "percentage": 12.83, "elapsed_time": "0:54:44", "remaining_time": "6:11:50", "throughput": 1498.77, "total_tokens": 4922848} {"current_steps": 23335, "total_steps": 181800, "loss": 0.1639, "lr": 4.9877687354191295e-05, "epoch": 2.567106710671067, "percentage": 12.84, "elapsed_time": "0:54:45", "remaining_time": "6:11:50", "throughput": 1498.77, "total_tokens": 4923904} {"current_steps": 23340, "total_steps": 181800, "loss": 0.0399, "lr": 4.9877450117289995e-05, "epoch": 2.567656765676568, "percentage": 12.84, "elapsed_time": "0:54:45", "remaining_time": "6:11:49", "throughput": 1498.78, "total_tokens": 4924960} {"current_steps": 23345, "total_steps": 181800, "loss": 0.0726, "lr": 4.987721265110518e-05, "epoch": 2.568206820682068, "percentage": 12.84, "elapsed_time": "0:54:46", "remaining_time": "6:11:48", "throughput": 1498.79, "total_tokens": 4926016} {"current_steps": 23350, "total_steps": 181800, "loss": 0.0222, "lr": 4.987697495563902e-05, "epoch": 2.5687568756875687, "percentage": 12.84, "elapsed_time": "0:54:47", "remaining_time": "6:11:47", "throughput": 1498.79, "total_tokens": 4927040} {"current_steps": 23355, "total_steps": 181800, "loss": 0.1484, "lr": 4.987673703089373e-05, "epoch": 2.5693069306930694, "percentage": 12.85, "elapsed_time": "0:54:48", "remaining_time": "6:11:46", "throughput": 1498.81, "total_tokens": 4928128} {"current_steps": 23360, "total_steps": 181800, "loss": 0.0674, "lr": 4.987649887687149e-05, "epoch": 2.56985698569857, "percentage": 12.85, "elapsed_time": "0:54:48", "remaining_time": "6:11:45", "throughput": 1498.81, "total_tokens": 4929184} {"current_steps": 23365, "total_steps": 181800, "loss": 0.0176, "lr": 4.987626049357449e-05, "epoch": 2.5704070407040707, "percentage": 12.85, "elapsed_time": "0:54:49", "remaining_time": "6:11:45", "throughput": 1498.79, "total_tokens": 4930144} {"current_steps": 23370, "total_steps": 181800, "loss": 0.0199, "lr": 4.9876021881004944e-05, "epoch": 2.570957095709571, "percentage": 12.85, "elapsed_time": "0:54:50", "remaining_time": "6:11:44", "throughput": 1498.77, "total_tokens": 4931104} {"current_steps": 23375, "total_steps": 181800, "loss": 0.1786, "lr": 4.987578303916503e-05, "epoch": 2.5715071507150715, "percentage": 12.86, "elapsed_time": "0:54:50", "remaining_time": "6:11:43", "throughput": 1498.78, "total_tokens": 4932160} {"current_steps": 23380, "total_steps": 181800, "loss": 0.0455, "lr": 4.9875543968056965e-05, "epoch": 2.572057205720572, "percentage": 12.86, "elapsed_time": "0:54:51", "remaining_time": "6:11:42", "throughput": 1498.78, "total_tokens": 4933184} {"current_steps": 23385, "total_steps": 181800, "loss": 0.0543, "lr": 4.987530466768295e-05, "epoch": 2.5726072607260724, "percentage": 12.86, "elapsed_time": "0:54:52", "remaining_time": "6:11:41", "throughput": 1498.79, "total_tokens": 4934240} {"current_steps": 23390, "total_steps": 181800, "loss": 0.0797, "lr": 4.9875065138045185e-05, "epoch": 2.573157315731573, "percentage": 12.87, "elapsed_time": "0:54:52", "remaining_time": "6:11:40", "throughput": 1498.8, "total_tokens": 4935296} {"current_steps": 23395, "total_steps": 181800, "loss": 0.0528, "lr": 4.987482537914589e-05, "epoch": 2.5737073707370737, "percentage": 12.87, "elapsed_time": "0:54:53", "remaining_time": "6:11:40", "throughput": 1498.79, "total_tokens": 4936320} {"current_steps": 23400, "total_steps": 181800, "loss": 0.1739, "lr": 4.987458539098725e-05, "epoch": 2.5742574257425743, "percentage": 12.87, "elapsed_time": "0:54:54", "remaining_time": "6:11:39", "throughput": 1498.78, "total_tokens": 4937312} {"current_steps": 23405, "total_steps": 181800, "loss": 0.0815, "lr": 4.98743451735715e-05, "epoch": 2.574807480748075, "percentage": 12.87, "elapsed_time": "0:54:54", "remaining_time": "6:11:38", "throughput": 1498.79, "total_tokens": 4938368} {"current_steps": 23410, "total_steps": 181800, "loss": 0.0885, "lr": 4.987410472690085e-05, "epoch": 2.575357535753575, "percentage": 12.88, "elapsed_time": "0:54:55", "remaining_time": "6:11:37", "throughput": 1498.79, "total_tokens": 4939424} {"current_steps": 23415, "total_steps": 181800, "loss": 0.0633, "lr": 4.9873864050977504e-05, "epoch": 2.575907590759076, "percentage": 12.88, "elapsed_time": "0:54:56", "remaining_time": "6:11:36", "throughput": 1498.8, "total_tokens": 4940480} {"current_steps": 23420, "total_steps": 181800, "loss": 0.1843, "lr": 4.98736231458037e-05, "epoch": 2.5764576457645765, "percentage": 12.88, "elapsed_time": "0:54:56", "remaining_time": "6:11:36", "throughput": 1498.8, "total_tokens": 4941504} {"current_steps": 23425, "total_steps": 181800, "loss": 0.1024, "lr": 4.987338201138164e-05, "epoch": 2.577007700770077, "percentage": 12.89, "elapsed_time": "0:54:57", "remaining_time": "6:11:35", "throughput": 1498.82, "total_tokens": 4942592} {"current_steps": 23430, "total_steps": 181800, "loss": 0.0644, "lr": 4.987314064771356e-05, "epoch": 2.5775577557755778, "percentage": 12.89, "elapsed_time": "0:54:58", "remaining_time": "6:11:34", "throughput": 1498.83, "total_tokens": 4943680} {"current_steps": 23435, "total_steps": 181800, "loss": 0.0708, "lr": 4.987289905480166e-05, "epoch": 2.578107810781078, "percentage": 12.89, "elapsed_time": "0:54:59", "remaining_time": "6:11:33", "throughput": 1498.85, "total_tokens": 4944768} {"current_steps": 23440, "total_steps": 181800, "loss": 0.0967, "lr": 4.98726572326482e-05, "epoch": 2.5786578657865786, "percentage": 12.89, "elapsed_time": "0:54:59", "remaining_time": "6:11:32", "throughput": 1498.88, "total_tokens": 4945888} {"current_steps": 23445, "total_steps": 181800, "loss": 0.0451, "lr": 4.9872415181255396e-05, "epoch": 2.5792079207920793, "percentage": 12.9, "elapsed_time": "0:55:00", "remaining_time": "6:11:32", "throughput": 1498.88, "total_tokens": 4946912} {"current_steps": 23450, "total_steps": 181800, "loss": 0.0657, "lr": 4.987217290062547e-05, "epoch": 2.5797579757975795, "percentage": 12.9, "elapsed_time": "0:55:01", "remaining_time": "6:11:31", "throughput": 1498.9, "total_tokens": 4948032} {"current_steps": 23455, "total_steps": 181800, "loss": 0.0469, "lr": 4.9871930390760654e-05, "epoch": 2.5803080308030806, "percentage": 12.9, "elapsed_time": "0:55:01", "remaining_time": "6:11:30", "throughput": 1498.9, "total_tokens": 4949056} {"current_steps": 23460, "total_steps": 181800, "loss": 0.0481, "lr": 4.98716876516632e-05, "epoch": 2.580858085808581, "percentage": 12.9, "elapsed_time": "0:55:02", "remaining_time": "6:11:29", "throughput": 1498.9, "total_tokens": 4950080} {"current_steps": 23465, "total_steps": 181800, "loss": 0.0341, "lr": 4.987144468333533e-05, "epoch": 2.5814081408140814, "percentage": 12.91, "elapsed_time": "0:55:03", "remaining_time": "6:11:28", "throughput": 1498.91, "total_tokens": 4951136} {"current_steps": 23470, "total_steps": 181800, "loss": 0.1, "lr": 4.98712014857793e-05, "epoch": 2.581958195819582, "percentage": 12.91, "elapsed_time": "0:55:03", "remaining_time": "6:11:27", "throughput": 1498.91, "total_tokens": 4952160} {"current_steps": 23475, "total_steps": 181800, "loss": 0.1332, "lr": 4.987095805899733e-05, "epoch": 2.5825082508250823, "percentage": 12.91, "elapsed_time": "0:55:04", "remaining_time": "6:11:27", "throughput": 1498.91, "total_tokens": 4953216} {"current_steps": 23480, "total_steps": 181800, "loss": 0.1157, "lr": 4.987071440299168e-05, "epoch": 2.583058305830583, "percentage": 12.92, "elapsed_time": "0:55:05", "remaining_time": "6:11:26", "throughput": 1498.91, "total_tokens": 4954240} {"current_steps": 23485, "total_steps": 181800, "loss": 0.0355, "lr": 4.9870470517764584e-05, "epoch": 2.5836083608360836, "percentage": 12.92, "elapsed_time": "0:55:05", "remaining_time": "6:11:25", "throughput": 1498.93, "total_tokens": 4955328} {"current_steps": 23490, "total_steps": 181800, "loss": 0.0936, "lr": 4.9870226403318296e-05, "epoch": 2.5841584158415842, "percentage": 12.92, "elapsed_time": "0:55:06", "remaining_time": "6:11:24", "throughput": 1498.93, "total_tokens": 4956384} {"current_steps": 23495, "total_steps": 181800, "loss": 0.1657, "lr": 4.986998205965506e-05, "epoch": 2.584708470847085, "percentage": 12.92, "elapsed_time": "0:55:07", "remaining_time": "6:11:23", "throughput": 1498.94, "total_tokens": 4957440} {"current_steps": 23500, "total_steps": 181800, "loss": 0.1295, "lr": 4.9869737486777145e-05, "epoch": 2.585258525852585, "percentage": 12.93, "elapsed_time": "0:55:07", "remaining_time": "6:11:23", "throughput": 1498.95, "total_tokens": 4958496} {"current_steps": 23505, "total_steps": 181800, "loss": 0.1515, "lr": 4.986949268468679e-05, "epoch": 2.5858085808580857, "percentage": 12.93, "elapsed_time": "0:55:08", "remaining_time": "6:11:22", "throughput": 1498.96, "total_tokens": 4959552} {"current_steps": 23510, "total_steps": 181800, "loss": 0.0534, "lr": 4.9869247653386256e-05, "epoch": 2.5863586358635864, "percentage": 12.93, "elapsed_time": "0:55:09", "remaining_time": "6:11:21", "throughput": 1498.97, "total_tokens": 4960640} {"current_steps": 23515, "total_steps": 181800, "loss": 0.0413, "lr": 4.9869002392877786e-05, "epoch": 2.586908690869087, "percentage": 12.93, "elapsed_time": "0:55:10", "remaining_time": "6:11:20", "throughput": 1499.01, "total_tokens": 4961792} {"current_steps": 23520, "total_steps": 181800, "loss": 0.0587, "lr": 4.986875690316367e-05, "epoch": 2.5874587458745877, "percentage": 12.94, "elapsed_time": "0:55:10", "remaining_time": "6:11:19", "throughput": 1499.0, "total_tokens": 4962816} {"current_steps": 23525, "total_steps": 181800, "loss": 0.0312, "lr": 4.986851118424615e-05, "epoch": 2.588008800880088, "percentage": 12.94, "elapsed_time": "0:55:11", "remaining_time": "6:11:19", "throughput": 1499.01, "total_tokens": 4963872} {"current_steps": 23530, "total_steps": 181800, "loss": 0.0633, "lr": 4.986826523612749e-05, "epoch": 2.5885588558855885, "percentage": 12.94, "elapsed_time": "0:55:12", "remaining_time": "6:11:18", "throughput": 1499.02, "total_tokens": 4964928} {"current_steps": 23535, "total_steps": 181800, "loss": 0.1502, "lr": 4.986801905880997e-05, "epoch": 2.589108910891089, "percentage": 12.95, "elapsed_time": "0:55:12", "remaining_time": "6:11:17", "throughput": 1499.01, "total_tokens": 4965952} {"current_steps": 23540, "total_steps": 181800, "loss": 0.0236, "lr": 4.9867772652295845e-05, "epoch": 2.5896589658965894, "percentage": 12.95, "elapsed_time": "0:55:13", "remaining_time": "6:11:16", "throughput": 1499.02, "total_tokens": 4967008} {"current_steps": 23545, "total_steps": 181800, "loss": 0.0439, "lr": 4.986752601658739e-05, "epoch": 2.5902090209020905, "percentage": 12.95, "elapsed_time": "0:55:14", "remaining_time": "6:11:15", "throughput": 1499.05, "total_tokens": 4968128} {"current_steps": 23550, "total_steps": 181800, "loss": 0.0639, "lr": 4.986727915168689e-05, "epoch": 2.5907590759075907, "percentage": 12.95, "elapsed_time": "0:55:14", "remaining_time": "6:11:15", "throughput": 1499.05, "total_tokens": 4969152} {"current_steps": 23555, "total_steps": 181800, "loss": 0.1161, "lr": 4.986703205759661e-05, "epoch": 2.5913091309130913, "percentage": 12.96, "elapsed_time": "0:55:15", "remaining_time": "6:11:14", "throughput": 1499.05, "total_tokens": 4970208} {"current_steps": 23560, "total_steps": 181800, "loss": 0.0209, "lr": 4.986678473431882e-05, "epoch": 2.591859185918592, "percentage": 12.96, "elapsed_time": "0:55:16", "remaining_time": "6:11:13", "throughput": 1499.04, "total_tokens": 4971232} {"current_steps": 23565, "total_steps": 181800, "loss": 0.0447, "lr": 4.986653718185581e-05, "epoch": 2.592409240924092, "percentage": 12.96, "elapsed_time": "0:55:16", "remaining_time": "6:11:12", "throughput": 1499.04, "total_tokens": 4972256} {"current_steps": 23570, "total_steps": 181800, "loss": 0.0207, "lr": 4.9866289400209865e-05, "epoch": 2.592959295929593, "percentage": 12.96, "elapsed_time": "0:55:17", "remaining_time": "6:11:12", "throughput": 1499.04, "total_tokens": 4973312} {"current_steps": 23575, "total_steps": 181800, "loss": 0.0483, "lr": 4.9866041389383254e-05, "epoch": 2.5935093509350935, "percentage": 12.97, "elapsed_time": "0:55:18", "remaining_time": "6:11:11", "throughput": 1499.03, "total_tokens": 4974304} {"current_steps": 23580, "total_steps": 181800, "loss": 0.0073, "lr": 4.986579314937828e-05, "epoch": 2.594059405940594, "percentage": 12.97, "elapsed_time": "0:55:19", "remaining_time": "6:11:10", "throughput": 1499.04, "total_tokens": 4975360} {"current_steps": 23585, "total_steps": 181800, "loss": 0.137, "lr": 4.986554468019722e-05, "epoch": 2.594609460946095, "percentage": 12.97, "elapsed_time": "0:55:19", "remaining_time": "6:11:09", "throughput": 1499.04, "total_tokens": 4976416} {"current_steps": 23590, "total_steps": 181800, "loss": 0.0515, "lr": 4.986529598184236e-05, "epoch": 2.595159515951595, "percentage": 12.98, "elapsed_time": "0:55:20", "remaining_time": "6:11:08", "throughput": 1499.03, "total_tokens": 4977408} {"current_steps": 23595, "total_steps": 181800, "loss": 0.0313, "lr": 4.9865047054316e-05, "epoch": 2.5957095709570956, "percentage": 12.98, "elapsed_time": "0:55:21", "remaining_time": "6:11:08", "throughput": 1499.05, "total_tokens": 4978528} {"current_steps": 23600, "total_steps": 181800, "loss": 0.0639, "lr": 4.9864797897620434e-05, "epoch": 2.5962596259625963, "percentage": 12.98, "elapsed_time": "0:55:21", "remaining_time": "6:11:07", "throughput": 1499.06, "total_tokens": 4979584} {"current_steps": 23605, "total_steps": 181800, "loss": 0.0191, "lr": 4.9864548511757955e-05, "epoch": 2.596809680968097, "percentage": 12.98, "elapsed_time": "0:55:22", "remaining_time": "6:11:06", "throughput": 1499.08, "total_tokens": 4980672} {"current_steps": 23610, "total_steps": 181800, "loss": 0.0769, "lr": 4.986429889673087e-05, "epoch": 2.5973597359735976, "percentage": 12.99, "elapsed_time": "0:55:23", "remaining_time": "6:11:05", "throughput": 1499.07, "total_tokens": 4981696} {"current_steps": 23615, "total_steps": 181800, "loss": 0.0803, "lr": 4.986404905254147e-05, "epoch": 2.597909790979098, "percentage": 12.99, "elapsed_time": "0:55:23", "remaining_time": "6:11:04", "throughput": 1499.07, "total_tokens": 4982720} {"current_steps": 23620, "total_steps": 181800, "loss": 0.0292, "lr": 4.986379897919206e-05, "epoch": 2.5984598459845984, "percentage": 12.99, "elapsed_time": "0:55:24", "remaining_time": "6:11:04", "throughput": 1499.06, "total_tokens": 4983744} {"current_steps": 23625, "total_steps": 181800, "loss": 0.0953, "lr": 4.9863548676684944e-05, "epoch": 2.599009900990099, "percentage": 13.0, "elapsed_time": "0:55:25", "remaining_time": "6:11:03", "throughput": 1499.09, "total_tokens": 4984864} {"current_steps": 23630, "total_steps": 181800, "loss": 0.0284, "lr": 4.986329814502244e-05, "epoch": 2.5995599559955993, "percentage": 13.0, "elapsed_time": "0:55:25", "remaining_time": "6:11:02", "throughput": 1499.12, "total_tokens": 4985984} {"current_steps": 23635, "total_steps": 181800, "loss": 0.0392, "lr": 4.9863047384206835e-05, "epoch": 2.6001100110011, "percentage": 13.0, "elapsed_time": "0:55:26", "remaining_time": "6:11:01", "throughput": 1499.14, "total_tokens": 4987104} {"current_steps": 23640, "total_steps": 181800, "loss": 0.0259, "lr": 4.9862796394240456e-05, "epoch": 2.6006600660066006, "percentage": 13.0, "elapsed_time": "0:55:27", "remaining_time": "6:11:01", "throughput": 1499.15, "total_tokens": 4988160} {"current_steps": 23645, "total_steps": 181800, "loss": 0.0858, "lr": 4.9862545175125616e-05, "epoch": 2.6012101210121013, "percentage": 13.01, "elapsed_time": "0:55:28", "remaining_time": "6:11:00", "throughput": 1499.17, "total_tokens": 4989280} {"current_steps": 23650, "total_steps": 181800, "loss": 0.0285, "lr": 4.9862293726864626e-05, "epoch": 2.601760176017602, "percentage": 13.01, "elapsed_time": "0:55:28", "remaining_time": "6:10:59", "throughput": 1499.19, "total_tokens": 4990368} {"current_steps": 23655, "total_steps": 181800, "loss": 0.0158, "lr": 4.9862042049459805e-05, "epoch": 2.602310231023102, "percentage": 13.01, "elapsed_time": "0:55:29", "remaining_time": "6:10:58", "throughput": 1499.21, "total_tokens": 4991456} {"current_steps": 23660, "total_steps": 181800, "loss": 0.1158, "lr": 4.9861790142913476e-05, "epoch": 2.6028602860286028, "percentage": 13.01, "elapsed_time": "0:55:30", "remaining_time": "6:10:57", "throughput": 1499.22, "total_tokens": 4992544} {"current_steps": 23665, "total_steps": 181800, "loss": 0.0524, "lr": 4.986153800722795e-05, "epoch": 2.6034103410341034, "percentage": 13.02, "elapsed_time": "0:55:30", "remaining_time": "6:10:57", "throughput": 1499.23, "total_tokens": 4993600} {"current_steps": 23670, "total_steps": 181800, "loss": 0.1283, "lr": 4.9861285642405564e-05, "epoch": 2.603960396039604, "percentage": 13.02, "elapsed_time": "0:55:31", "remaining_time": "6:10:56", "throughput": 1499.24, "total_tokens": 4994656} {"current_steps": 23675, "total_steps": 181800, "loss": 0.1033, "lr": 4.986103304844864e-05, "epoch": 2.6045104510451047, "percentage": 13.02, "elapsed_time": "0:55:32", "remaining_time": "6:10:55", "throughput": 1499.26, "total_tokens": 4995776} {"current_steps": 23680, "total_steps": 181800, "loss": 0.0666, "lr": 4.986078022535949e-05, "epoch": 2.605060506050605, "percentage": 13.03, "elapsed_time": "0:55:32", "remaining_time": "6:10:54", "throughput": 1499.26, "total_tokens": 4996800} {"current_steps": 23685, "total_steps": 181800, "loss": 0.0695, "lr": 4.986052717314047e-05, "epoch": 2.6056105610561056, "percentage": 13.03, "elapsed_time": "0:55:33", "remaining_time": "6:10:53", "throughput": 1499.26, "total_tokens": 4997824} {"current_steps": 23690, "total_steps": 181800, "loss": 0.1188, "lr": 4.9860273891793896e-05, "epoch": 2.606160616061606, "percentage": 13.03, "elapsed_time": "0:55:34", "remaining_time": "6:10:53", "throughput": 1499.26, "total_tokens": 4998880} {"current_steps": 23695, "total_steps": 181800, "loss": 0.036, "lr": 4.986002038132211e-05, "epoch": 2.606710671067107, "percentage": 13.03, "elapsed_time": "0:55:34", "remaining_time": "6:10:52", "throughput": 1499.26, "total_tokens": 4999904} {"current_steps": 23700, "total_steps": 181800, "loss": 0.116, "lr": 4.985976664172745e-05, "epoch": 2.6072607260726075, "percentage": 13.04, "elapsed_time": "0:55:35", "remaining_time": "6:10:51", "throughput": 1499.26, "total_tokens": 5000928} {"current_steps": 23705, "total_steps": 181800, "loss": 0.1468, "lr": 4.9859512673012236e-05, "epoch": 2.6078107810781077, "percentage": 13.04, "elapsed_time": "0:55:36", "remaining_time": "6:10:50", "throughput": 1499.25, "total_tokens": 5001952} {"current_steps": 23710, "total_steps": 181800, "loss": 0.0963, "lr": 4.9859258475178826e-05, "epoch": 2.6083608360836084, "percentage": 13.04, "elapsed_time": "0:55:36", "remaining_time": "6:10:49", "throughput": 1499.26, "total_tokens": 5003008} {"current_steps": 23715, "total_steps": 181800, "loss": 0.0578, "lr": 4.9859004048229564e-05, "epoch": 2.608910891089109, "percentage": 13.04, "elapsed_time": "0:55:37", "remaining_time": "6:10:49", "throughput": 1499.27, "total_tokens": 5004064} {"current_steps": 23720, "total_steps": 181800, "loss": 0.0659, "lr": 4.985874939216679e-05, "epoch": 2.609460946094609, "percentage": 13.05, "elapsed_time": "0:55:38", "remaining_time": "6:10:48", "throughput": 1499.27, "total_tokens": 5005088} {"current_steps": 23725, "total_steps": 181800, "loss": 0.0342, "lr": 4.9858494506992845e-05, "epoch": 2.61001100110011, "percentage": 13.05, "elapsed_time": "0:55:39", "remaining_time": "6:10:47", "throughput": 1499.28, "total_tokens": 5006144} {"current_steps": 23730, "total_steps": 181800, "loss": 0.0504, "lr": 4.985823939271009e-05, "epoch": 2.6105610561056105, "percentage": 13.05, "elapsed_time": "0:55:39", "remaining_time": "6:10:46", "throughput": 1499.28, "total_tokens": 5007200} {"current_steps": 23735, "total_steps": 181800, "loss": 0.3178, "lr": 4.985798404932088e-05, "epoch": 2.611111111111111, "percentage": 13.06, "elapsed_time": "0:55:40", "remaining_time": "6:10:45", "throughput": 1499.3, "total_tokens": 5008288} {"current_steps": 23740, "total_steps": 181800, "loss": 0.1682, "lr": 4.985772847682755e-05, "epoch": 2.611661166116612, "percentage": 13.06, "elapsed_time": "0:55:41", "remaining_time": "6:10:44", "throughput": 1499.31, "total_tokens": 5009344} {"current_steps": 23745, "total_steps": 181800, "loss": 0.0881, "lr": 4.985747267523246e-05, "epoch": 2.612211221122112, "percentage": 13.06, "elapsed_time": "0:55:41", "remaining_time": "6:10:44", "throughput": 1499.32, "total_tokens": 5010400} {"current_steps": 23750, "total_steps": 181800, "loss": 0.028, "lr": 4.9857216644537976e-05, "epoch": 2.6127612761276127, "percentage": 13.06, "elapsed_time": "0:55:42", "remaining_time": "6:10:43", "throughput": 1499.34, "total_tokens": 5011520} {"current_steps": 23755, "total_steps": 181800, "loss": 0.1044, "lr": 4.985696038474645e-05, "epoch": 2.6133113311331133, "percentage": 13.07, "elapsed_time": "0:55:43", "remaining_time": "6:10:42", "throughput": 1499.35, "total_tokens": 5012576} {"current_steps": 23760, "total_steps": 181800, "loss": 0.0419, "lr": 4.985670389586026e-05, "epoch": 2.613861386138614, "percentage": 13.07, "elapsed_time": "0:55:43", "remaining_time": "6:10:41", "throughput": 1499.37, "total_tokens": 5013664} {"current_steps": 23765, "total_steps": 181800, "loss": 0.0504, "lr": 4.9856447177881745e-05, "epoch": 2.6144114411441146, "percentage": 13.07, "elapsed_time": "0:55:44", "remaining_time": "6:10:40", "throughput": 1499.37, "total_tokens": 5014688} {"current_steps": 23770, "total_steps": 181800, "loss": 0.1593, "lr": 4.9856190230813285e-05, "epoch": 2.614961496149615, "percentage": 13.07, "elapsed_time": "0:55:45", "remaining_time": "6:10:40", "throughput": 1499.38, "total_tokens": 5015776} {"current_steps": 23775, "total_steps": 181800, "loss": 0.0439, "lr": 4.985593305465725e-05, "epoch": 2.6155115511551155, "percentage": 13.08, "elapsed_time": "0:55:45", "remaining_time": "6:10:39", "throughput": 1499.4, "total_tokens": 5016864} {"current_steps": 23780, "total_steps": 181800, "loss": 0.0256, "lr": 4.9855675649416e-05, "epoch": 2.616061606160616, "percentage": 13.08, "elapsed_time": "0:55:46", "remaining_time": "6:10:38", "throughput": 1499.4, "total_tokens": 5017888} {"current_steps": 23785, "total_steps": 181800, "loss": 0.1392, "lr": 4.9855418015091924e-05, "epoch": 2.6166116611661168, "percentage": 13.08, "elapsed_time": "0:55:47", "remaining_time": "6:10:37", "throughput": 1499.4, "total_tokens": 5018944} {"current_steps": 23790, "total_steps": 181800, "loss": 0.1175, "lr": 4.9855160151687386e-05, "epoch": 2.6171617161716174, "percentage": 13.09, "elapsed_time": "0:55:47", "remaining_time": "6:10:36", "throughput": 1499.41, "total_tokens": 5020000} {"current_steps": 23795, "total_steps": 181800, "loss": 0.0895, "lr": 4.9854902059204765e-05, "epoch": 2.6177117711771176, "percentage": 13.09, "elapsed_time": "0:55:48", "remaining_time": "6:10:36", "throughput": 1499.43, "total_tokens": 5021088} {"current_steps": 23800, "total_steps": 181800, "loss": 0.0123, "lr": 4.9854643737646434e-05, "epoch": 2.6182618261826183, "percentage": 13.09, "elapsed_time": "0:55:49", "remaining_time": "6:10:35", "throughput": 1499.42, "total_tokens": 5022112} {"current_steps": 23805, "total_steps": 181800, "loss": 0.1009, "lr": 4.985438518701477e-05, "epoch": 2.618811881188119, "percentage": 13.09, "elapsed_time": "0:55:50", "remaining_time": "6:10:34", "throughput": 1499.43, "total_tokens": 5023168} {"current_steps": 23810, "total_steps": 181800, "loss": 0.1354, "lr": 4.9854126407312176e-05, "epoch": 2.619361936193619, "percentage": 13.1, "elapsed_time": "0:55:50", "remaining_time": "6:10:33", "throughput": 1499.44, "total_tokens": 5024224} {"current_steps": 23815, "total_steps": 181800, "loss": 0.045, "lr": 4.9853867398541026e-05, "epoch": 2.6199119911991198, "percentage": 13.1, "elapsed_time": "0:55:51", "remaining_time": "6:10:32", "throughput": 1499.45, "total_tokens": 5025312} {"current_steps": 23820, "total_steps": 181800, "loss": 0.0283, "lr": 4.98536081607037e-05, "epoch": 2.6204620462046204, "percentage": 13.1, "elapsed_time": "0:55:52", "remaining_time": "6:10:32", "throughput": 1499.45, "total_tokens": 5026336} {"current_steps": 23825, "total_steps": 181800, "loss": 0.0492, "lr": 4.98533486938026e-05, "epoch": 2.621012101210121, "percentage": 13.11, "elapsed_time": "0:55:52", "remaining_time": "6:10:31", "throughput": 1499.47, "total_tokens": 5027424} {"current_steps": 23830, "total_steps": 181800, "loss": 0.0234, "lr": 4.98530889978401e-05, "epoch": 2.6215621562156217, "percentage": 13.11, "elapsed_time": "0:55:53", "remaining_time": "6:10:30", "throughput": 1499.47, "total_tokens": 5028448} {"current_steps": 23835, "total_steps": 181800, "loss": 0.0665, "lr": 4.985282907281862e-05, "epoch": 2.622112211221122, "percentage": 13.11, "elapsed_time": "0:55:54", "remaining_time": "6:10:29", "throughput": 1499.47, "total_tokens": 5029504} {"current_steps": 23840, "total_steps": 181800, "loss": 0.0636, "lr": 4.985256891874053e-05, "epoch": 2.6226622662266226, "percentage": 13.11, "elapsed_time": "0:55:54", "remaining_time": "6:10:28", "throughput": 1499.47, "total_tokens": 5030528} {"current_steps": 23845, "total_steps": 181800, "loss": 0.1352, "lr": 4.985230853560824e-05, "epoch": 2.6232123212321232, "percentage": 13.12, "elapsed_time": "0:55:55", "remaining_time": "6:10:27", "throughput": 1499.48, "total_tokens": 5031584} {"current_steps": 23850, "total_steps": 181800, "loss": 0.0505, "lr": 4.9852047923424137e-05, "epoch": 2.623762376237624, "percentage": 13.12, "elapsed_time": "0:55:56", "remaining_time": "6:10:27", "throughput": 1499.48, "total_tokens": 5032608} {"current_steps": 23855, "total_steps": 181800, "loss": 0.0352, "lr": 4.985178708219065e-05, "epoch": 2.6243124312431245, "percentage": 13.12, "elapsed_time": "0:55:56", "remaining_time": "6:10:26", "throughput": 1499.52, "total_tokens": 5033792} {"current_steps": 23860, "total_steps": 181800, "loss": 0.0563, "lr": 4.985152601191016e-05, "epoch": 2.6248624862486247, "percentage": 13.12, "elapsed_time": "0:55:57", "remaining_time": "6:10:25", "throughput": 1499.52, "total_tokens": 5034816} {"current_steps": 23865, "total_steps": 181800, "loss": 0.0572, "lr": 4.985126471258508e-05, "epoch": 2.6254125412541254, "percentage": 13.13, "elapsed_time": "0:55:58", "remaining_time": "6:10:24", "throughput": 1499.53, "total_tokens": 5035872} {"current_steps": 23870, "total_steps": 181800, "loss": 0.1338, "lr": 4.985100318421781e-05, "epoch": 2.625962596259626, "percentage": 13.13, "elapsed_time": "0:55:58", "remaining_time": "6:10:23", "throughput": 1499.55, "total_tokens": 5036960} {"current_steps": 23875, "total_steps": 181800, "loss": 0.1519, "lr": 4.9850741426810774e-05, "epoch": 2.6265126512651267, "percentage": 13.13, "elapsed_time": "0:55:59", "remaining_time": "6:10:23", "throughput": 1499.53, "total_tokens": 5037952} {"current_steps": 23880, "total_steps": 181800, "loss": 0.0353, "lr": 4.985047944036638e-05, "epoch": 2.6270627062706273, "percentage": 13.14, "elapsed_time": "0:56:00", "remaining_time": "6:10:22", "throughput": 1499.55, "total_tokens": 5039040} {"current_steps": 23885, "total_steps": 181800, "loss": 0.0359, "lr": 4.985021722488704e-05, "epoch": 2.6276127612761275, "percentage": 13.14, "elapsed_time": "0:56:01", "remaining_time": "6:10:21", "throughput": 1499.54, "total_tokens": 5040032} {"current_steps": 23890, "total_steps": 181800, "loss": 0.0569, "lr": 4.9849954780375174e-05, "epoch": 2.628162816281628, "percentage": 13.14, "elapsed_time": "0:56:01", "remaining_time": "6:10:20", "throughput": 1499.54, "total_tokens": 5041056} {"current_steps": 23895, "total_steps": 181800, "loss": 0.0982, "lr": 4.98496921068332e-05, "epoch": 2.628712871287129, "percentage": 13.14, "elapsed_time": "0:56:02", "remaining_time": "6:10:19", "throughput": 1499.54, "total_tokens": 5042112} {"current_steps": 23900, "total_steps": 181800, "loss": 0.0787, "lr": 4.984942920426354e-05, "epoch": 2.629262926292629, "percentage": 13.15, "elapsed_time": "0:56:03", "remaining_time": "6:10:19", "throughput": 1499.54, "total_tokens": 5043136} {"current_steps": 23905, "total_steps": 181800, "loss": 0.0881, "lr": 4.984916607266861e-05, "epoch": 2.6298129812981297, "percentage": 13.15, "elapsed_time": "0:56:03", "remaining_time": "6:10:18", "throughput": 1499.55, "total_tokens": 5044224} {"current_steps": 23910, "total_steps": 181800, "loss": 0.0307, "lr": 4.9848902712050836e-05, "epoch": 2.6303630363036303, "percentage": 13.15, "elapsed_time": "0:56:04", "remaining_time": "6:10:17", "throughput": 1499.58, "total_tokens": 5045344} {"current_steps": 23915, "total_steps": 181800, "loss": 0.0719, "lr": 4.9848639122412655e-05, "epoch": 2.630913091309131, "percentage": 13.15, "elapsed_time": "0:56:05", "remaining_time": "6:10:16", "throughput": 1499.58, "total_tokens": 5046368} {"current_steps": 23920, "total_steps": 181800, "loss": 0.0983, "lr": 4.984837530375649e-05, "epoch": 2.6314631463146316, "percentage": 13.16, "elapsed_time": "0:56:05", "remaining_time": "6:10:15", "throughput": 1499.6, "total_tokens": 5047488} {"current_steps": 23925, "total_steps": 181800, "loss": 0.0938, "lr": 4.984811125608477e-05, "epoch": 2.632013201320132, "percentage": 13.16, "elapsed_time": "0:56:06", "remaining_time": "6:10:15", "throughput": 1499.6, "total_tokens": 5048512} {"current_steps": 23930, "total_steps": 181800, "loss": 0.0554, "lr": 4.9847846979399945e-05, "epoch": 2.6325632563256325, "percentage": 13.16, "elapsed_time": "0:56:07", "remaining_time": "6:10:14", "throughput": 1499.61, "total_tokens": 5049600} {"current_steps": 23935, "total_steps": 181800, "loss": 0.2616, "lr": 4.984758247370443e-05, "epoch": 2.633113311331133, "percentage": 13.17, "elapsed_time": "0:56:07", "remaining_time": "6:10:13", "throughput": 1499.61, "total_tokens": 5050624} {"current_steps": 23940, "total_steps": 181800, "loss": 0.0612, "lr": 4.9847317739000664e-05, "epoch": 2.633663366336634, "percentage": 13.17, "elapsed_time": "0:56:08", "remaining_time": "6:10:12", "throughput": 1499.65, "total_tokens": 5051776} {"current_steps": 23945, "total_steps": 181800, "loss": 0.1112, "lr": 4.98470527752911e-05, "epoch": 2.6342134213421344, "percentage": 13.17, "elapsed_time": "0:56:09", "remaining_time": "6:10:12", "throughput": 1499.64, "total_tokens": 5052800} {"current_steps": 23950, "total_steps": 181800, "loss": 0.0269, "lr": 4.984678758257817e-05, "epoch": 2.6347634763476346, "percentage": 13.17, "elapsed_time": "0:56:10", "remaining_time": "6:10:11", "throughput": 1499.65, "total_tokens": 5053856} {"current_steps": 23955, "total_steps": 181800, "loss": 0.0363, "lr": 4.9846522160864314e-05, "epoch": 2.6353135313531353, "percentage": 13.18, "elapsed_time": "0:56:10", "remaining_time": "6:10:10", "throughput": 1499.67, "total_tokens": 5054944} {"current_steps": 23960, "total_steps": 181800, "loss": 0.1599, "lr": 4.9846256510152003e-05, "epoch": 2.635863586358636, "percentage": 13.18, "elapsed_time": "0:56:11", "remaining_time": "6:10:09", "throughput": 1499.67, "total_tokens": 5056000} {"current_steps": 23965, "total_steps": 181800, "loss": 0.0314, "lr": 4.984599063044366e-05, "epoch": 2.636413641364136, "percentage": 13.18, "elapsed_time": "0:56:12", "remaining_time": "6:10:08", "throughput": 1499.69, "total_tokens": 5057088} {"current_steps": 23970, "total_steps": 181800, "loss": 0.059, "lr": 4.984572452174174e-05, "epoch": 2.6369636963696372, "percentage": 13.18, "elapsed_time": "0:56:12", "remaining_time": "6:10:08", "throughput": 1499.7, "total_tokens": 5058144} {"current_steps": 23975, "total_steps": 181800, "loss": 0.0658, "lr": 4.98454581840487e-05, "epoch": 2.6375137513751374, "percentage": 13.19, "elapsed_time": "0:56:13", "remaining_time": "6:10:07", "throughput": 1499.69, "total_tokens": 5059168} {"current_steps": 23980, "total_steps": 181800, "loss": 0.0983, "lr": 4.9845191617367e-05, "epoch": 2.638063806380638, "percentage": 13.19, "elapsed_time": "0:56:14", "remaining_time": "6:10:06", "throughput": 1499.68, "total_tokens": 5060160} {"current_steps": 23985, "total_steps": 181800, "loss": 0.0992, "lr": 4.9844924821699086e-05, "epoch": 2.6386138613861387, "percentage": 13.19, "elapsed_time": "0:56:14", "remaining_time": "6:10:05", "throughput": 1499.68, "total_tokens": 5061184} {"current_steps": 23990, "total_steps": 181800, "loss": 0.0228, "lr": 4.984465779704742e-05, "epoch": 2.639163916391639, "percentage": 13.2, "elapsed_time": "0:56:15", "remaining_time": "6:10:04", "throughput": 1499.69, "total_tokens": 5062272} {"current_steps": 23995, "total_steps": 181800, "loss": 0.0628, "lr": 4.984439054341447e-05, "epoch": 2.6397139713971396, "percentage": 13.2, "elapsed_time": "0:56:16", "remaining_time": "6:10:04", "throughput": 1499.73, "total_tokens": 5063424} {"current_steps": 24000, "total_steps": 181800, "loss": 0.0504, "lr": 4.98441230608027e-05, "epoch": 2.6402640264026402, "percentage": 13.2, "elapsed_time": "0:56:16", "remaining_time": "6:10:03", "throughput": 1499.73, "total_tokens": 5064480} {"current_steps": 24005, "total_steps": 181800, "loss": 0.0915, "lr": 4.984385534921455e-05, "epoch": 2.640814081408141, "percentage": 13.2, "elapsed_time": "0:56:17", "remaining_time": "6:10:02", "throughput": 1499.74, "total_tokens": 5065536} {"current_steps": 24010, "total_steps": 181800, "loss": 0.0486, "lr": 4.984358740865251e-05, "epoch": 2.6413641364136415, "percentage": 13.21, "elapsed_time": "0:56:18", "remaining_time": "6:10:01", "throughput": 1499.74, "total_tokens": 5066592} {"current_steps": 24015, "total_steps": 181800, "loss": 0.0593, "lr": 4.984331923911906e-05, "epoch": 2.6419141914191417, "percentage": 13.21, "elapsed_time": "0:56:18", "remaining_time": "6:10:00", "throughput": 1499.73, "total_tokens": 5067584} {"current_steps": 24020, "total_steps": 181800, "loss": 0.1363, "lr": 4.984305084061665e-05, "epoch": 2.6424642464246424, "percentage": 13.21, "elapsed_time": "0:56:19", "remaining_time": "6:10:00", "throughput": 1499.73, "total_tokens": 5068608} {"current_steps": 24025, "total_steps": 181800, "loss": 0.166, "lr": 4.9842782213147765e-05, "epoch": 2.643014301430143, "percentage": 13.22, "elapsed_time": "0:56:20", "remaining_time": "6:09:59", "throughput": 1499.72, "total_tokens": 5069632} {"current_steps": 24030, "total_steps": 181800, "loss": 0.0531, "lr": 4.984251335671487e-05, "epoch": 2.6435643564356437, "percentage": 13.22, "elapsed_time": "0:56:21", "remaining_time": "6:09:58", "throughput": 1499.74, "total_tokens": 5070720} {"current_steps": 24035, "total_steps": 181800, "loss": 0.0223, "lr": 4.984224427132045e-05, "epoch": 2.6441144114411443, "percentage": 13.22, "elapsed_time": "0:56:21", "remaining_time": "6:09:57", "throughput": 1499.75, "total_tokens": 5071776} {"current_steps": 24040, "total_steps": 181800, "loss": 0.0772, "lr": 4.9841974956967e-05, "epoch": 2.6446644664466445, "percentage": 13.22, "elapsed_time": "0:56:22", "remaining_time": "6:09:56", "throughput": 1499.75, "total_tokens": 5072832} {"current_steps": 24045, "total_steps": 181800, "loss": 0.0388, "lr": 4.984170541365697e-05, "epoch": 2.645214521452145, "percentage": 13.23, "elapsed_time": "0:56:23", "remaining_time": "6:09:56", "throughput": 1499.78, "total_tokens": 5073952} {"current_steps": 24050, "total_steps": 181800, "loss": 0.0563, "lr": 4.9841435641392866e-05, "epoch": 2.645764576457646, "percentage": 13.23, "elapsed_time": "0:56:23", "remaining_time": "6:09:55", "throughput": 1499.81, "total_tokens": 5075104} {"current_steps": 24055, "total_steps": 181800, "loss": 0.0697, "lr": 4.9841165640177165e-05, "epoch": 2.646314631463146, "percentage": 13.23, "elapsed_time": "0:56:24", "remaining_time": "6:09:54", "throughput": 1499.83, "total_tokens": 5076224} {"current_steps": 24060, "total_steps": 181800, "loss": 0.1125, "lr": 4.9840895410012375e-05, "epoch": 2.6468646864686467, "percentage": 13.23, "elapsed_time": "0:56:25", "remaining_time": "6:09:53", "throughput": 1499.84, "total_tokens": 5077280} {"current_steps": 24065, "total_steps": 181800, "loss": 0.0337, "lr": 4.984062495090096e-05, "epoch": 2.6474147414741473, "percentage": 13.24, "elapsed_time": "0:56:25", "remaining_time": "6:09:53", "throughput": 1499.85, "total_tokens": 5078336} {"current_steps": 24070, "total_steps": 181800, "loss": 0.0834, "lr": 4.984035426284543e-05, "epoch": 2.647964796479648, "percentage": 13.24, "elapsed_time": "0:56:26", "remaining_time": "6:09:52", "throughput": 1499.85, "total_tokens": 5079392} {"current_steps": 24075, "total_steps": 181800, "loss": 0.1349, "lr": 4.984008334584827e-05, "epoch": 2.6485148514851486, "percentage": 13.24, "elapsed_time": "0:56:27", "remaining_time": "6:09:51", "throughput": 1499.87, "total_tokens": 5080480} {"current_steps": 24080, "total_steps": 181800, "loss": 0.2407, "lr": 4.983981219991198e-05, "epoch": 2.649064906490649, "percentage": 13.25, "elapsed_time": "0:56:27", "remaining_time": "6:09:50", "throughput": 1499.85, "total_tokens": 5081472} {"current_steps": 24085, "total_steps": 181800, "loss": 0.0693, "lr": 4.9839540825039065e-05, "epoch": 2.6496149614961495, "percentage": 13.25, "elapsed_time": "0:56:28", "remaining_time": "6:09:49", "throughput": 1499.86, "total_tokens": 5082528} {"current_steps": 24090, "total_steps": 181800, "loss": 0.059, "lr": 4.983926922123202e-05, "epoch": 2.65016501650165, "percentage": 13.25, "elapsed_time": "0:56:29", "remaining_time": "6:09:49", "throughput": 1499.87, "total_tokens": 5083584} {"current_steps": 24095, "total_steps": 181800, "loss": 0.1272, "lr": 4.983899738849335e-05, "epoch": 2.650715071507151, "percentage": 13.25, "elapsed_time": "0:56:30", "remaining_time": "6:09:48", "throughput": 1499.86, "total_tokens": 5084608} {"current_steps": 24100, "total_steps": 181800, "loss": 0.0816, "lr": 4.983872532682556e-05, "epoch": 2.6512651265126514, "percentage": 13.26, "elapsed_time": "0:56:30", "remaining_time": "6:09:47", "throughput": 1499.86, "total_tokens": 5085664} {"current_steps": 24105, "total_steps": 181800, "loss": 0.0701, "lr": 4.9838453036231155e-05, "epoch": 2.6518151815181517, "percentage": 13.26, "elapsed_time": "0:56:31", "remaining_time": "6:09:46", "throughput": 1499.87, "total_tokens": 5086720} {"current_steps": 24110, "total_steps": 181800, "loss": 0.0384, "lr": 4.9838180516712655e-05, "epoch": 2.6523652365236523, "percentage": 13.26, "elapsed_time": "0:56:32", "remaining_time": "6:09:45", "throughput": 1499.87, "total_tokens": 5087744} {"current_steps": 24115, "total_steps": 181800, "loss": 0.0736, "lr": 4.983790776827255e-05, "epoch": 2.652915291529153, "percentage": 13.26, "elapsed_time": "0:56:32", "remaining_time": "6:09:45", "throughput": 1499.87, "total_tokens": 5088768} {"current_steps": 24120, "total_steps": 181800, "loss": 0.1238, "lr": 4.983763479091338e-05, "epoch": 2.6534653465346536, "percentage": 13.27, "elapsed_time": "0:56:33", "remaining_time": "6:09:44", "throughput": 1499.88, "total_tokens": 5089824} {"current_steps": 24125, "total_steps": 181800, "loss": 0.0595, "lr": 4.983736158463764e-05, "epoch": 2.6540154015401543, "percentage": 13.27, "elapsed_time": "0:56:34", "remaining_time": "6:09:43", "throughput": 1499.88, "total_tokens": 5090880} {"current_steps": 24130, "total_steps": 181800, "loss": 0.1341, "lr": 4.983708814944786e-05, "epoch": 2.6545654565456545, "percentage": 13.27, "elapsed_time": "0:56:34", "remaining_time": "6:09:42", "throughput": 1499.88, "total_tokens": 5091904} {"current_steps": 24135, "total_steps": 181800, "loss": 0.1058, "lr": 4.983681448534656e-05, "epoch": 2.655115511551155, "percentage": 13.28, "elapsed_time": "0:56:35", "remaining_time": "6:09:41", "throughput": 1499.88, "total_tokens": 5092928} {"current_steps": 24140, "total_steps": 181800, "loss": 0.0472, "lr": 4.983654059233626e-05, "epoch": 2.6556655665566558, "percentage": 13.28, "elapsed_time": "0:56:36", "remaining_time": "6:09:41", "throughput": 1499.87, "total_tokens": 5093952} {"current_steps": 24145, "total_steps": 181800, "loss": 0.0506, "lr": 4.983626647041947e-05, "epoch": 2.656215621562156, "percentage": 13.28, "elapsed_time": "0:56:36", "remaining_time": "6:09:40", "throughput": 1499.85, "total_tokens": 5094912} {"current_steps": 24150, "total_steps": 181800, "loss": 0.0497, "lr": 4.983599211959874e-05, "epoch": 2.6567656765676566, "percentage": 13.28, "elapsed_time": "0:56:37", "remaining_time": "6:09:39", "throughput": 1499.84, "total_tokens": 5095904} {"current_steps": 24155, "total_steps": 181800, "loss": 0.0537, "lr": 4.983571753987658e-05, "epoch": 2.6573157315731573, "percentage": 13.29, "elapsed_time": "0:56:38", "remaining_time": "6:09:38", "throughput": 1499.84, "total_tokens": 5096928} {"current_steps": 24160, "total_steps": 181800, "loss": 0.074, "lr": 4.983544273125554e-05, "epoch": 2.657865786578658, "percentage": 13.29, "elapsed_time": "0:56:39", "remaining_time": "6:09:37", "throughput": 1499.87, "total_tokens": 5098048} {"current_steps": 24165, "total_steps": 181800, "loss": 0.0642, "lr": 4.983516769373814e-05, "epoch": 2.6584158415841586, "percentage": 13.29, "elapsed_time": "0:56:39", "remaining_time": "6:09:37", "throughput": 1499.88, "total_tokens": 5099136} {"current_steps": 24170, "total_steps": 181800, "loss": 0.0266, "lr": 4.9834892427326907e-05, "epoch": 2.6589658965896588, "percentage": 13.29, "elapsed_time": "0:56:40", "remaining_time": "6:09:36", "throughput": 1499.89, "total_tokens": 5100192} {"current_steps": 24175, "total_steps": 181800, "loss": 0.0415, "lr": 4.983461693202439e-05, "epoch": 2.6595159515951594, "percentage": 13.3, "elapsed_time": "0:56:41", "remaining_time": "6:09:35", "throughput": 1499.92, "total_tokens": 5101312} {"current_steps": 24180, "total_steps": 181800, "loss": 0.2315, "lr": 4.983434120783314e-05, "epoch": 2.66006600660066, "percentage": 13.3, "elapsed_time": "0:56:41", "remaining_time": "6:09:34", "throughput": 1499.92, "total_tokens": 5102336} {"current_steps": 24185, "total_steps": 181800, "loss": 0.0601, "lr": 4.9834065254755664e-05, "epoch": 2.6606160616061607, "percentage": 13.3, "elapsed_time": "0:56:42", "remaining_time": "6:09:33", "throughput": 1499.93, "total_tokens": 5103424} {"current_steps": 24190, "total_steps": 181800, "loss": 0.0974, "lr": 4.9833789072794534e-05, "epoch": 2.6611661166116614, "percentage": 13.31, "elapsed_time": "0:56:43", "remaining_time": "6:09:33", "throughput": 1499.95, "total_tokens": 5104512} {"current_steps": 24195, "total_steps": 181800, "loss": 0.0739, "lr": 4.983351266195229e-05, "epoch": 2.6617161716171616, "percentage": 13.31, "elapsed_time": "0:56:43", "remaining_time": "6:09:32", "throughput": 1499.95, "total_tokens": 5105536} {"current_steps": 24200, "total_steps": 181800, "loss": 0.0205, "lr": 4.9833236022231465e-05, "epoch": 2.662266226622662, "percentage": 13.31, "elapsed_time": "0:56:44", "remaining_time": "6:09:31", "throughput": 1499.95, "total_tokens": 5106560} {"current_steps": 24205, "total_steps": 181800, "loss": 0.1303, "lr": 4.983295915363463e-05, "epoch": 2.662816281628163, "percentage": 13.31, "elapsed_time": "0:56:45", "remaining_time": "6:09:30", "throughput": 1499.95, "total_tokens": 5107616} {"current_steps": 24210, "total_steps": 181800, "loss": 0.0485, "lr": 4.983268205616433e-05, "epoch": 2.6633663366336635, "percentage": 13.32, "elapsed_time": "0:56:45", "remaining_time": "6:09:29", "throughput": 1499.96, "total_tokens": 5108672} {"current_steps": 24215, "total_steps": 181800, "loss": 0.0501, "lr": 4.98324047298231e-05, "epoch": 2.663916391639164, "percentage": 13.32, "elapsed_time": "0:56:46", "remaining_time": "6:09:28", "throughput": 1499.98, "total_tokens": 5109760} {"current_steps": 24220, "total_steps": 181800, "loss": 0.0932, "lr": 4.983212717461352e-05, "epoch": 2.6644664466446644, "percentage": 13.32, "elapsed_time": "0:56:47", "remaining_time": "6:09:28", "throughput": 1500.0, "total_tokens": 5110880} {"current_steps": 24225, "total_steps": 181800, "loss": 0.1024, "lr": 4.983184939053814e-05, "epoch": 2.665016501650165, "percentage": 13.33, "elapsed_time": "0:56:47", "remaining_time": "6:09:27", "throughput": 1500.0, "total_tokens": 5111904} {"current_steps": 24230, "total_steps": 181800, "loss": 0.1826, "lr": 4.9831571377599515e-05, "epoch": 2.6655665566556657, "percentage": 13.33, "elapsed_time": "0:56:48", "remaining_time": "6:09:26", "throughput": 1500.01, "total_tokens": 5112960} {"current_steps": 24235, "total_steps": 181800, "loss": 0.0582, "lr": 4.983129313580022e-05, "epoch": 2.666116611661166, "percentage": 13.33, "elapsed_time": "0:56:49", "remaining_time": "6:09:25", "throughput": 1500.05, "total_tokens": 5114112} {"current_steps": 24240, "total_steps": 181800, "loss": 0.0763, "lr": 4.98310146651428e-05, "epoch": 2.6666666666666665, "percentage": 13.33, "elapsed_time": "0:56:49", "remaining_time": "6:09:24", "throughput": 1500.05, "total_tokens": 5115168} {"current_steps": 24245, "total_steps": 181800, "loss": 0.0569, "lr": 4.983073596562985e-05, "epoch": 2.667216721672167, "percentage": 13.34, "elapsed_time": "0:56:50", "remaining_time": "6:09:24", "throughput": 1500.08, "total_tokens": 5116288} {"current_steps": 24250, "total_steps": 181800, "loss": 0.0558, "lr": 4.983045703726391e-05, "epoch": 2.667766776677668, "percentage": 13.34, "elapsed_time": "0:56:51", "remaining_time": "6:09:23", "throughput": 1500.08, "total_tokens": 5117312} {"current_steps": 24255, "total_steps": 181800, "loss": 0.065, "lr": 4.983017788004756e-05, "epoch": 2.6683168316831685, "percentage": 13.34, "elapsed_time": "0:56:52", "remaining_time": "6:09:22", "throughput": 1500.09, "total_tokens": 5118368} {"current_steps": 24260, "total_steps": 181800, "loss": 0.0205, "lr": 4.9829898493983384e-05, "epoch": 2.6688668866886687, "percentage": 13.34, "elapsed_time": "0:56:52", "remaining_time": "6:09:21", "throughput": 1500.11, "total_tokens": 5119488} {"current_steps": 24265, "total_steps": 181800, "loss": 0.1313, "lr": 4.9829618879073944e-05, "epoch": 2.6694169416941693, "percentage": 13.35, "elapsed_time": "0:56:53", "remaining_time": "6:09:20", "throughput": 1500.14, "total_tokens": 5120608} {"current_steps": 24270, "total_steps": 181800, "loss": 0.054, "lr": 4.9829339035321824e-05, "epoch": 2.66996699669967, "percentage": 13.35, "elapsed_time": "0:56:54", "remaining_time": "6:09:20", "throughput": 1500.14, "total_tokens": 5121664} {"current_steps": 24275, "total_steps": 181800, "loss": 0.1779, "lr": 4.982905896272959e-05, "epoch": 2.6705170517051706, "percentage": 13.35, "elapsed_time": "0:56:54", "remaining_time": "6:09:19", "throughput": 1500.13, "total_tokens": 5122656} {"current_steps": 24280, "total_steps": 181800, "loss": 0.0303, "lr": 4.9828778661299845e-05, "epoch": 2.6710671067106713, "percentage": 13.36, "elapsed_time": "0:56:55", "remaining_time": "6:09:18", "throughput": 1500.14, "total_tokens": 5123712} {"current_steps": 24285, "total_steps": 181800, "loss": 0.0699, "lr": 4.982849813103515e-05, "epoch": 2.6716171617161715, "percentage": 13.36, "elapsed_time": "0:56:56", "remaining_time": "6:09:17", "throughput": 1500.15, "total_tokens": 5124768} {"current_steps": 24290, "total_steps": 181800, "loss": 0.0797, "lr": 4.9828217371938115e-05, "epoch": 2.672167216721672, "percentage": 13.36, "elapsed_time": "0:56:56", "remaining_time": "6:09:16", "throughput": 1500.16, "total_tokens": 5125856} {"current_steps": 24295, "total_steps": 181800, "loss": 0.0367, "lr": 4.982793638401131e-05, "epoch": 2.6727172717271728, "percentage": 13.36, "elapsed_time": "0:56:57", "remaining_time": "6:09:16", "throughput": 1500.17, "total_tokens": 5126912} {"current_steps": 24300, "total_steps": 181800, "loss": 0.0408, "lr": 4.982765516725732e-05, "epoch": 2.6732673267326734, "percentage": 13.37, "elapsed_time": "0:56:58", "remaining_time": "6:09:15", "throughput": 1500.17, "total_tokens": 5127936} {"current_steps": 24305, "total_steps": 181800, "loss": 0.018, "lr": 4.9827373721678755e-05, "epoch": 2.673817381738174, "percentage": 13.37, "elapsed_time": "0:56:58", "remaining_time": "6:09:14", "throughput": 1500.17, "total_tokens": 5128992} {"current_steps": 24310, "total_steps": 181800, "loss": 0.0566, "lr": 4.9827092047278195e-05, "epoch": 2.6743674367436743, "percentage": 13.37, "elapsed_time": "0:56:59", "remaining_time": "6:09:13", "throughput": 1500.18, "total_tokens": 5130048} {"current_steps": 24315, "total_steps": 181800, "loss": 0.0634, "lr": 4.9826810144058244e-05, "epoch": 2.674917491749175, "percentage": 13.37, "elapsed_time": "0:57:00", "remaining_time": "6:09:12", "throughput": 1500.18, "total_tokens": 5131104} {"current_steps": 24320, "total_steps": 181800, "loss": 0.0539, "lr": 4.9826528012021496e-05, "epoch": 2.6754675467546756, "percentage": 13.38, "elapsed_time": "0:57:01", "remaining_time": "6:09:12", "throughput": 1500.21, "total_tokens": 5132224} {"current_steps": 24325, "total_steps": 181800, "loss": 0.02, "lr": 4.9826245651170555e-05, "epoch": 2.676017601760176, "percentage": 13.38, "elapsed_time": "0:57:01", "remaining_time": "6:09:11", "throughput": 1500.22, "total_tokens": 5133280} {"current_steps": 24330, "total_steps": 181800, "loss": 0.1023, "lr": 4.982596306150802e-05, "epoch": 2.6765676567656764, "percentage": 13.38, "elapsed_time": "0:57:02", "remaining_time": "6:09:10", "throughput": 1500.23, "total_tokens": 5134368} {"current_steps": 24335, "total_steps": 181800, "loss": 0.0418, "lr": 4.9825680243036485e-05, "epoch": 2.677117711771177, "percentage": 13.39, "elapsed_time": "0:57:03", "remaining_time": "6:09:09", "throughput": 1500.22, "total_tokens": 5135360} {"current_steps": 24340, "total_steps": 181800, "loss": 0.0293, "lr": 4.982539719575858e-05, "epoch": 2.6776677667766777, "percentage": 13.39, "elapsed_time": "0:57:03", "remaining_time": "6:09:08", "throughput": 1500.25, "total_tokens": 5136480} {"current_steps": 24345, "total_steps": 181800, "loss": 0.0661, "lr": 4.98251139196769e-05, "epoch": 2.6782178217821784, "percentage": 13.39, "elapsed_time": "0:57:04", "remaining_time": "6:09:08", "throughput": 1500.24, "total_tokens": 5137472} {"current_steps": 24350, "total_steps": 181800, "loss": 0.0565, "lr": 4.9824830414794053e-05, "epoch": 2.6787678767876786, "percentage": 13.39, "elapsed_time": "0:57:05", "remaining_time": "6:09:07", "throughput": 1500.23, "total_tokens": 5138464} {"current_steps": 24355, "total_steps": 181800, "loss": 0.1425, "lr": 4.982454668111266e-05, "epoch": 2.6793179317931792, "percentage": 13.4, "elapsed_time": "0:57:05", "remaining_time": "6:09:06", "throughput": 1500.22, "total_tokens": 5139488} {"current_steps": 24360, "total_steps": 181800, "loss": 0.0324, "lr": 4.982426271863533e-05, "epoch": 2.67986798679868, "percentage": 13.4, "elapsed_time": "0:57:06", "remaining_time": "6:09:05", "throughput": 1500.22, "total_tokens": 5140512} {"current_steps": 24365, "total_steps": 181800, "loss": 0.08, "lr": 4.982397852736468e-05, "epoch": 2.6804180418041805, "percentage": 13.4, "elapsed_time": "0:57:07", "remaining_time": "6:09:04", "throughput": 1500.23, "total_tokens": 5141568} {"current_steps": 24370, "total_steps": 181800, "loss": 0.1632, "lr": 4.982369410730334e-05, "epoch": 2.680968096809681, "percentage": 13.4, "elapsed_time": "0:57:07", "remaining_time": "6:09:04", "throughput": 1500.24, "total_tokens": 5142624} {"current_steps": 24375, "total_steps": 181800, "loss": 0.0531, "lr": 4.982340945845392e-05, "epoch": 2.6815181518151814, "percentage": 13.41, "elapsed_time": "0:57:08", "remaining_time": "6:09:03", "throughput": 1500.24, "total_tokens": 5143680} {"current_steps": 24380, "total_steps": 181800, "loss": 0.0651, "lr": 4.9823124580819037e-05, "epoch": 2.682068206820682, "percentage": 13.41, "elapsed_time": "0:57:09", "remaining_time": "6:09:02", "throughput": 1500.25, "total_tokens": 5144736} {"current_steps": 24385, "total_steps": 181800, "loss": 0.0459, "lr": 4.9822839474401334e-05, "epoch": 2.6826182618261827, "percentage": 13.41, "elapsed_time": "0:57:09", "remaining_time": "6:09:01", "throughput": 1500.26, "total_tokens": 5145792} {"current_steps": 24390, "total_steps": 181800, "loss": 0.0314, "lr": 4.982255413920343e-05, "epoch": 2.6831683168316833, "percentage": 13.42, "elapsed_time": "0:57:10", "remaining_time": "6:09:00", "throughput": 1500.25, "total_tokens": 5146816} {"current_steps": 24395, "total_steps": 181800, "loss": 0.1421, "lr": 4.982226857522796e-05, "epoch": 2.683718371837184, "percentage": 13.42, "elapsed_time": "0:57:11", "remaining_time": "6:09:00", "throughput": 1500.25, "total_tokens": 5147840} {"current_steps": 24400, "total_steps": 181800, "loss": 0.1289, "lr": 4.982198278247754e-05, "epoch": 2.684268426842684, "percentage": 13.42, "elapsed_time": "0:57:12", "remaining_time": "6:08:59", "throughput": 1500.26, "total_tokens": 5148896} {"current_steps": 24405, "total_steps": 181800, "loss": 0.2025, "lr": 4.982169676095483e-05, "epoch": 2.684818481848185, "percentage": 13.42, "elapsed_time": "0:57:12", "remaining_time": "6:08:58", "throughput": 1500.27, "total_tokens": 5149984} {"current_steps": 24410, "total_steps": 181800, "loss": 0.0769, "lr": 4.982141051066243e-05, "epoch": 2.6853685368536855, "percentage": 13.43, "elapsed_time": "0:57:13", "remaining_time": "6:08:57", "throughput": 1500.26, "total_tokens": 5150976} {"current_steps": 24415, "total_steps": 181800, "loss": 0.0346, "lr": 4.9821124031603025e-05, "epoch": 2.6859185918591857, "percentage": 13.43, "elapsed_time": "0:57:14", "remaining_time": "6:08:56", "throughput": 1500.27, "total_tokens": 5152032} {"current_steps": 24420, "total_steps": 181800, "loss": 0.0136, "lr": 4.9820837323779215e-05, "epoch": 2.6864686468646863, "percentage": 13.43, "elapsed_time": "0:57:14", "remaining_time": "6:08:56", "throughput": 1500.28, "total_tokens": 5153088} {"current_steps": 24425, "total_steps": 181800, "loss": 0.198, "lr": 4.9820550387193667e-05, "epoch": 2.687018701870187, "percentage": 13.44, "elapsed_time": "0:57:15", "remaining_time": "6:08:55", "throughput": 1500.28, "total_tokens": 5154144} {"current_steps": 24430, "total_steps": 181800, "loss": 0.037, "lr": 4.982026322184901e-05, "epoch": 2.6875687568756876, "percentage": 13.44, "elapsed_time": "0:57:16", "remaining_time": "6:08:54", "throughput": 1500.29, "total_tokens": 5155200} {"current_steps": 24435, "total_steps": 181800, "loss": 0.0504, "lr": 4.981997582774789e-05, "epoch": 2.6881188118811883, "percentage": 13.44, "elapsed_time": "0:57:16", "remaining_time": "6:08:53", "throughput": 1500.29, "total_tokens": 5156256} {"current_steps": 24440, "total_steps": 181800, "loss": 0.0899, "lr": 4.9819688204892974e-05, "epoch": 2.6886688668866885, "percentage": 13.44, "elapsed_time": "0:57:17", "remaining_time": "6:08:52", "throughput": 1500.3, "total_tokens": 5157312} {"current_steps": 24445, "total_steps": 181800, "loss": 0.058, "lr": 4.981940035328689e-05, "epoch": 2.689218921892189, "percentage": 13.45, "elapsed_time": "0:57:18", "remaining_time": "6:08:52", "throughput": 1500.31, "total_tokens": 5158368} {"current_steps": 24450, "total_steps": 181800, "loss": 0.0754, "lr": 4.981911227293231e-05, "epoch": 2.68976897689769, "percentage": 13.45, "elapsed_time": "0:57:18", "remaining_time": "6:08:51", "throughput": 1500.31, "total_tokens": 5159392} {"current_steps": 24455, "total_steps": 181800, "loss": 0.0928, "lr": 4.981882396383189e-05, "epoch": 2.6903190319031904, "percentage": 13.45, "elapsed_time": "0:57:19", "remaining_time": "6:08:50", "throughput": 1500.31, "total_tokens": 5160448} {"current_steps": 24460, "total_steps": 181800, "loss": 0.0892, "lr": 4.9818535425988265e-05, "epoch": 2.690869086908691, "percentage": 13.45, "elapsed_time": "0:57:20", "remaining_time": "6:08:49", "throughput": 1500.34, "total_tokens": 5161600} {"current_steps": 24465, "total_steps": 181800, "loss": 0.1562, "lr": 4.9818246659404114e-05, "epoch": 2.6914191419141913, "percentage": 13.46, "elapsed_time": "0:57:20", "remaining_time": "6:08:48", "throughput": 1500.35, "total_tokens": 5162656} {"current_steps": 24470, "total_steps": 181800, "loss": 0.175, "lr": 4.9817957664082096e-05, "epoch": 2.691969196919692, "percentage": 13.46, "elapsed_time": "0:57:21", "remaining_time": "6:08:48", "throughput": 1500.34, "total_tokens": 5163648} {"current_steps": 24475, "total_steps": 181800, "loss": 0.0418, "lr": 4.981766844002486e-05, "epoch": 2.6925192519251926, "percentage": 13.46, "elapsed_time": "0:57:22", "remaining_time": "6:08:47", "throughput": 1500.34, "total_tokens": 5164704} {"current_steps": 24480, "total_steps": 181800, "loss": 0.1169, "lr": 4.981737898723509e-05, "epoch": 2.693069306930693, "percentage": 13.47, "elapsed_time": "0:57:23", "remaining_time": "6:08:46", "throughput": 1500.34, "total_tokens": 5165728} {"current_steps": 24485, "total_steps": 181800, "loss": 0.0689, "lr": 4.9817089305715445e-05, "epoch": 2.693619361936194, "percentage": 13.47, "elapsed_time": "0:57:23", "remaining_time": "6:08:45", "throughput": 1500.33, "total_tokens": 5166752} {"current_steps": 24490, "total_steps": 181800, "loss": 0.16, "lr": 4.98167993954686e-05, "epoch": 2.694169416941694, "percentage": 13.47, "elapsed_time": "0:57:24", "remaining_time": "6:08:45", "throughput": 1500.33, "total_tokens": 5167776} {"current_steps": 24495, "total_steps": 181800, "loss": 0.0569, "lr": 4.981650925649722e-05, "epoch": 2.6947194719471947, "percentage": 13.47, "elapsed_time": "0:57:25", "remaining_time": "6:08:44", "throughput": 1500.34, "total_tokens": 5168832} {"current_steps": 24500, "total_steps": 181800, "loss": 0.0621, "lr": 4.981621888880398e-05, "epoch": 2.6952695269526954, "percentage": 13.48, "elapsed_time": "0:57:25", "remaining_time": "6:08:43", "throughput": 1500.32, "total_tokens": 5169824} {"current_steps": 24505, "total_steps": 181800, "loss": 0.1766, "lr": 4.981592829239156e-05, "epoch": 2.6958195819581956, "percentage": 13.48, "elapsed_time": "0:57:26", "remaining_time": "6:08:42", "throughput": 1500.34, "total_tokens": 5170912} {"current_steps": 24510, "total_steps": 181800, "loss": 0.1126, "lr": 4.981563746726264e-05, "epoch": 2.6963696369636962, "percentage": 13.48, "elapsed_time": "0:57:27", "remaining_time": "6:08:41", "throughput": 1500.34, "total_tokens": 5171936} {"current_steps": 24515, "total_steps": 181800, "loss": 0.1323, "lr": 4.981534641341989e-05, "epoch": 2.696919691969197, "percentage": 13.48, "elapsed_time": "0:57:27", "remaining_time": "6:08:41", "throughput": 1500.35, "total_tokens": 5173024} {"current_steps": 24520, "total_steps": 181800, "loss": 0.1109, "lr": 4.981505513086601e-05, "epoch": 2.6974697469746975, "percentage": 13.49, "elapsed_time": "0:57:28", "remaining_time": "6:08:40", "throughput": 1500.36, "total_tokens": 5174080} {"current_steps": 24525, "total_steps": 181800, "loss": 0.1228, "lr": 4.981476361960367e-05, "epoch": 2.698019801980198, "percentage": 13.49, "elapsed_time": "0:57:29", "remaining_time": "6:08:39", "throughput": 1500.35, "total_tokens": 5175072} {"current_steps": 24530, "total_steps": 181800, "loss": 0.0801, "lr": 4.981447187963556e-05, "epoch": 2.6985698569856984, "percentage": 13.49, "elapsed_time": "0:57:29", "remaining_time": "6:08:38", "throughput": 1500.36, "total_tokens": 5176128} {"current_steps": 24535, "total_steps": 181800, "loss": 0.0497, "lr": 4.981417991096436e-05, "epoch": 2.699119911991199, "percentage": 13.5, "elapsed_time": "0:57:30", "remaining_time": "6:08:37", "throughput": 1500.36, "total_tokens": 5177184} {"current_steps": 24540, "total_steps": 181800, "loss": 0.0244, "lr": 4.981388771359279e-05, "epoch": 2.6996699669966997, "percentage": 13.5, "elapsed_time": "0:57:31", "remaining_time": "6:08:37", "throughput": 1500.37, "total_tokens": 5178240} {"current_steps": 24545, "total_steps": 181800, "loss": 0.034, "lr": 4.981359528752351e-05, "epoch": 2.7002200220022003, "percentage": 13.5, "elapsed_time": "0:57:32", "remaining_time": "6:08:36", "throughput": 1500.37, "total_tokens": 5179296} {"current_steps": 24550, "total_steps": 181800, "loss": 0.0543, "lr": 4.981330263275924e-05, "epoch": 2.700770077007701, "percentage": 13.5, "elapsed_time": "0:57:32", "remaining_time": "6:08:35", "throughput": 1500.38, "total_tokens": 5180352} {"current_steps": 24555, "total_steps": 181800, "loss": 0.1908, "lr": 4.9813009749302655e-05, "epoch": 2.701320132013201, "percentage": 13.51, "elapsed_time": "0:57:33", "remaining_time": "6:08:34", "throughput": 1500.36, "total_tokens": 5181344} {"current_steps": 24560, "total_steps": 181800, "loss": 0.0931, "lr": 4.981271663715647e-05, "epoch": 2.701870187018702, "percentage": 13.51, "elapsed_time": "0:57:34", "remaining_time": "6:08:33", "throughput": 1500.38, "total_tokens": 5182432} {"current_steps": 24565, "total_steps": 181800, "loss": 0.0843, "lr": 4.9812423296323384e-05, "epoch": 2.7024202420242025, "percentage": 13.51, "elapsed_time": "0:57:34", "remaining_time": "6:08:33", "throughput": 1500.38, "total_tokens": 5183456} {"current_steps": 24570, "total_steps": 181800, "loss": 0.0984, "lr": 4.98121297268061e-05, "epoch": 2.7029702970297027, "percentage": 13.51, "elapsed_time": "0:57:35", "remaining_time": "6:08:32", "throughput": 1500.38, "total_tokens": 5184512} {"current_steps": 24575, "total_steps": 181800, "loss": 0.0325, "lr": 4.981183592860731e-05, "epoch": 2.7035203520352034, "percentage": 13.52, "elapsed_time": "0:57:36", "remaining_time": "6:08:31", "throughput": 1500.41, "total_tokens": 5185664} {"current_steps": 24580, "total_steps": 181800, "loss": 0.0685, "lr": 4.981154190172975e-05, "epoch": 2.704070407040704, "percentage": 13.52, "elapsed_time": "0:57:36", "remaining_time": "6:08:30", "throughput": 1500.43, "total_tokens": 5186752} {"current_steps": 24585, "total_steps": 181800, "loss": 0.067, "lr": 4.981124764617611e-05, "epoch": 2.7046204620462047, "percentage": 13.52, "elapsed_time": "0:57:37", "remaining_time": "6:08:30", "throughput": 1500.43, "total_tokens": 5187776} {"current_steps": 24590, "total_steps": 181800, "loss": 0.0293, "lr": 4.9810953161949094e-05, "epoch": 2.7051705170517053, "percentage": 13.53, "elapsed_time": "0:57:38", "remaining_time": "6:08:29", "throughput": 1500.44, "total_tokens": 5188864} {"current_steps": 24595, "total_steps": 181800, "loss": 0.0472, "lr": 4.981065844905144e-05, "epoch": 2.7057205720572055, "percentage": 13.53, "elapsed_time": "0:57:38", "remaining_time": "6:08:28", "throughput": 1500.46, "total_tokens": 5189952} {"current_steps": 24600, "total_steps": 181800, "loss": 0.0869, "lr": 4.9810363507485844e-05, "epoch": 2.706270627062706, "percentage": 13.53, "elapsed_time": "0:57:39", "remaining_time": "6:08:27", "throughput": 1500.46, "total_tokens": 5191008} {"current_steps": 24605, "total_steps": 181800, "loss": 0.1339, "lr": 4.981006833725504e-05, "epoch": 2.706820682068207, "percentage": 13.53, "elapsed_time": "0:57:40", "remaining_time": "6:08:26", "throughput": 1500.47, "total_tokens": 5192064} {"current_steps": 24610, "total_steps": 181800, "loss": 0.0552, "lr": 4.980977293836174e-05, "epoch": 2.7073707370737075, "percentage": 13.54, "elapsed_time": "0:57:40", "remaining_time": "6:08:26", "throughput": 1500.48, "total_tokens": 5193152} {"current_steps": 24615, "total_steps": 181800, "loss": 0.0443, "lr": 4.980947731080867e-05, "epoch": 2.707920792079208, "percentage": 13.54, "elapsed_time": "0:57:41", "remaining_time": "6:08:25", "throughput": 1500.51, "total_tokens": 5194272} {"current_steps": 24620, "total_steps": 181800, "loss": 0.1136, "lr": 4.980918145459855e-05, "epoch": 2.7084708470847083, "percentage": 13.54, "elapsed_time": "0:57:42", "remaining_time": "6:08:24", "throughput": 1500.51, "total_tokens": 5195328} {"current_steps": 24625, "total_steps": 181800, "loss": 0.0372, "lr": 4.980888536973411e-05, "epoch": 2.709020902090209, "percentage": 13.55, "elapsed_time": "0:57:43", "remaining_time": "6:08:23", "throughput": 1500.5, "total_tokens": 5196320} {"current_steps": 24630, "total_steps": 181800, "loss": 0.1191, "lr": 4.980858905621808e-05, "epoch": 2.7095709570957096, "percentage": 13.55, "elapsed_time": "0:57:43", "remaining_time": "6:08:22", "throughput": 1500.5, "total_tokens": 5197344} {"current_steps": 24635, "total_steps": 181800, "loss": 0.0643, "lr": 4.9808292514053176e-05, "epoch": 2.7101210121012103, "percentage": 13.55, "elapsed_time": "0:57:44", "remaining_time": "6:08:22", "throughput": 1500.49, "total_tokens": 5198336} {"current_steps": 24640, "total_steps": 181800, "loss": 0.1334, "lr": 4.980799574324216e-05, "epoch": 2.710671067106711, "percentage": 13.55, "elapsed_time": "0:57:45", "remaining_time": "6:08:21", "throughput": 1500.5, "total_tokens": 5199424} {"current_steps": 24645, "total_steps": 181800, "loss": 0.0592, "lr": 4.9807698743787744e-05, "epoch": 2.711221122112211, "percentage": 13.56, "elapsed_time": "0:57:45", "remaining_time": "6:08:20", "throughput": 1500.52, "total_tokens": 5200512} {"current_steps": 24650, "total_steps": 181800, "loss": 0.0476, "lr": 4.9807401515692675e-05, "epoch": 2.7117711771177118, "percentage": 13.56, "elapsed_time": "0:57:46", "remaining_time": "6:08:19", "throughput": 1500.51, "total_tokens": 5201536} {"current_steps": 24655, "total_steps": 181800, "loss": 0.1005, "lr": 4.9807104058959684e-05, "epoch": 2.7123212321232124, "percentage": 13.56, "elapsed_time": "0:57:47", "remaining_time": "6:08:19", "throughput": 1500.51, "total_tokens": 5202560} {"current_steps": 24660, "total_steps": 181800, "loss": 0.0805, "lr": 4.980680637359153e-05, "epoch": 2.7128712871287126, "percentage": 13.56, "elapsed_time": "0:57:47", "remaining_time": "6:08:18", "throughput": 1500.5, "total_tokens": 5203552} {"current_steps": 24665, "total_steps": 181800, "loss": 0.0446, "lr": 4.9806508459590936e-05, "epoch": 2.7134213421342133, "percentage": 13.57, "elapsed_time": "0:57:48", "remaining_time": "6:08:17", "throughput": 1500.51, "total_tokens": 5204608} {"current_steps": 24670, "total_steps": 181800, "loss": 0.0979, "lr": 4.9806210316960655e-05, "epoch": 2.713971397139714, "percentage": 13.57, "elapsed_time": "0:57:49", "remaining_time": "6:08:16", "throughput": 1500.5, "total_tokens": 5205632} {"current_steps": 24675, "total_steps": 181800, "loss": 0.059, "lr": 4.980591194570344e-05, "epoch": 2.7145214521452146, "percentage": 13.57, "elapsed_time": "0:57:49", "remaining_time": "6:08:15", "throughput": 1500.51, "total_tokens": 5206688} {"current_steps": 24680, "total_steps": 181800, "loss": 0.0614, "lr": 4.980561334582204e-05, "epoch": 2.715071507150715, "percentage": 13.58, "elapsed_time": "0:57:50", "remaining_time": "6:08:15", "throughput": 1500.5, "total_tokens": 5207680} {"current_steps": 24685, "total_steps": 181800, "loss": 0.0628, "lr": 4.980531451731921e-05, "epoch": 2.7156215621562154, "percentage": 13.58, "elapsed_time": "0:57:51", "remaining_time": "6:08:14", "throughput": 1500.48, "total_tokens": 5208640} {"current_steps": 24690, "total_steps": 181800, "loss": 0.1471, "lr": 4.980501546019769e-05, "epoch": 2.716171617161716, "percentage": 13.58, "elapsed_time": "0:57:52", "remaining_time": "6:08:13", "throughput": 1500.49, "total_tokens": 5209696} {"current_steps": 24695, "total_steps": 181800, "loss": 0.0389, "lr": 4.9804716174460244e-05, "epoch": 2.7167216721672167, "percentage": 13.58, "elapsed_time": "0:57:52", "remaining_time": "6:08:12", "throughput": 1500.51, "total_tokens": 5210816} {"current_steps": 24700, "total_steps": 181800, "loss": 0.1545, "lr": 4.980441666010963e-05, "epoch": 2.7172717271727174, "percentage": 13.59, "elapsed_time": "0:57:53", "remaining_time": "6:08:11", "throughput": 1500.53, "total_tokens": 5211904} {"current_steps": 24705, "total_steps": 181800, "loss": 0.0557, "lr": 4.980411691714862e-05, "epoch": 2.717821782178218, "percentage": 13.59, "elapsed_time": "0:57:54", "remaining_time": "6:08:10", "throughput": 1500.54, "total_tokens": 5212960} {"current_steps": 24710, "total_steps": 181800, "loss": 0.0455, "lr": 4.980381694557996e-05, "epoch": 2.718371837183718, "percentage": 13.59, "elapsed_time": "0:57:54", "remaining_time": "6:08:10", "throughput": 1500.57, "total_tokens": 5214112} {"current_steps": 24715, "total_steps": 181800, "loss": 0.1287, "lr": 4.980351674540642e-05, "epoch": 2.718921892189219, "percentage": 13.59, "elapsed_time": "0:57:55", "remaining_time": "6:08:09", "throughput": 1500.58, "total_tokens": 5215168} {"current_steps": 24720, "total_steps": 181800, "loss": 0.1067, "lr": 4.980321631663078e-05, "epoch": 2.7194719471947195, "percentage": 13.6, "elapsed_time": "0:57:56", "remaining_time": "6:08:08", "throughput": 1500.6, "total_tokens": 5216288} {"current_steps": 24725, "total_steps": 181800, "loss": 0.0592, "lr": 4.980291565925578e-05, "epoch": 2.72002200220022, "percentage": 13.6, "elapsed_time": "0:57:56", "remaining_time": "6:08:07", "throughput": 1500.61, "total_tokens": 5217344} {"current_steps": 24730, "total_steps": 181800, "loss": 0.0426, "lr": 4.9802614773284216e-05, "epoch": 2.720572057205721, "percentage": 13.6, "elapsed_time": "0:57:57", "remaining_time": "6:08:06", "throughput": 1500.61, "total_tokens": 5218368} {"current_steps": 24735, "total_steps": 181800, "loss": 0.1126, "lr": 4.980231365871885e-05, "epoch": 2.721122112211221, "percentage": 13.61, "elapsed_time": "0:57:58", "remaining_time": "6:08:06", "throughput": 1500.64, "total_tokens": 5219520} {"current_steps": 24740, "total_steps": 181800, "loss": 0.1145, "lr": 4.9802012315562465e-05, "epoch": 2.7216721672167217, "percentage": 13.61, "elapsed_time": "0:57:58", "remaining_time": "6:08:05", "throughput": 1500.64, "total_tokens": 5220544} {"current_steps": 24745, "total_steps": 181800, "loss": 0.0437, "lr": 4.980171074381783e-05, "epoch": 2.7222222222222223, "percentage": 13.61, "elapsed_time": "0:57:59", "remaining_time": "6:08:04", "throughput": 1500.65, "total_tokens": 5221632} {"current_steps": 24750, "total_steps": 181800, "loss": 0.1667, "lr": 4.980140894348773e-05, "epoch": 2.7227722772277225, "percentage": 13.61, "elapsed_time": "0:58:00", "remaining_time": "6:08:03", "throughput": 1500.66, "total_tokens": 5222688} {"current_steps": 24755, "total_steps": 181800, "loss": 0.0886, "lr": 4.9801106914574944e-05, "epoch": 2.723322332233223, "percentage": 13.62, "elapsed_time": "0:58:00", "remaining_time": "6:08:03", "throughput": 1500.64, "total_tokens": 5223680} {"current_steps": 24760, "total_steps": 181800, "loss": 0.1185, "lr": 4.9800804657082255e-05, "epoch": 2.723872387238724, "percentage": 13.62, "elapsed_time": "0:58:01", "remaining_time": "6:08:02", "throughput": 1500.65, "total_tokens": 5224736} {"current_steps": 24765, "total_steps": 181800, "loss": 0.0784, "lr": 4.980050217101245e-05, "epoch": 2.7244224422442245, "percentage": 13.62, "elapsed_time": "0:58:02", "remaining_time": "6:08:01", "throughput": 1500.65, "total_tokens": 5225792} {"current_steps": 24770, "total_steps": 181800, "loss": 0.1088, "lr": 4.980019945636832e-05, "epoch": 2.724972497249725, "percentage": 13.62, "elapsed_time": "0:58:03", "remaining_time": "6:08:00", "throughput": 1500.65, "total_tokens": 5226816} {"current_steps": 24775, "total_steps": 181800, "loss": 0.0367, "lr": 4.979989651315266e-05, "epoch": 2.7255225522552253, "percentage": 13.63, "elapsed_time": "0:58:03", "remaining_time": "6:08:00", "throughput": 1500.65, "total_tokens": 5227872} {"current_steps": 24780, "total_steps": 181800, "loss": 0.0423, "lr": 4.9799593341368234e-05, "epoch": 2.726072607260726, "percentage": 13.63, "elapsed_time": "0:58:04", "remaining_time": "6:07:59", "throughput": 1500.66, "total_tokens": 5228928} {"current_steps": 24785, "total_steps": 181800, "loss": 0.0177, "lr": 4.9799289941017866e-05, "epoch": 2.7266226622662266, "percentage": 13.63, "elapsed_time": "0:58:05", "remaining_time": "6:07:58", "throughput": 1500.67, "total_tokens": 5229984} {"current_steps": 24790, "total_steps": 181800, "loss": 0.0864, "lr": 4.979898631210434e-05, "epoch": 2.7271727172717273, "percentage": 13.64, "elapsed_time": "0:58:05", "remaining_time": "6:07:57", "throughput": 1500.67, "total_tokens": 5231040} {"current_steps": 24795, "total_steps": 181800, "loss": 0.1182, "lr": 4.9798682454630466e-05, "epoch": 2.727722772277228, "percentage": 13.64, "elapsed_time": "0:58:06", "remaining_time": "6:07:56", "throughput": 1500.68, "total_tokens": 5232096} {"current_steps": 24800, "total_steps": 181800, "loss": 0.0518, "lr": 4.979837836859903e-05, "epoch": 2.728272827282728, "percentage": 13.64, "elapsed_time": "0:58:07", "remaining_time": "6:07:55", "throughput": 1500.69, "total_tokens": 5233152} {"current_steps": 24805, "total_steps": 181800, "loss": 0.0538, "lr": 4.979807405401284e-05, "epoch": 2.728822882288229, "percentage": 13.64, "elapsed_time": "0:58:07", "remaining_time": "6:07:55", "throughput": 1500.69, "total_tokens": 5234176} {"current_steps": 24810, "total_steps": 181800, "loss": 0.0365, "lr": 4.9797769510874696e-05, "epoch": 2.7293729372937294, "percentage": 13.65, "elapsed_time": "0:58:08", "remaining_time": "6:07:54", "throughput": 1500.69, "total_tokens": 5235232} {"current_steps": 24815, "total_steps": 181800, "loss": 0.0566, "lr": 4.979746473918742e-05, "epoch": 2.72992299229923, "percentage": 13.65, "elapsed_time": "0:58:09", "remaining_time": "6:07:53", "throughput": 1500.69, "total_tokens": 5236256} {"current_steps": 24820, "total_steps": 181800, "loss": 0.0902, "lr": 4.9797159738953806e-05, "epoch": 2.7304730473047307, "percentage": 13.65, "elapsed_time": "0:58:09", "remaining_time": "6:07:52", "throughput": 1500.68, "total_tokens": 5237248} {"current_steps": 24825, "total_steps": 181800, "loss": 0.0611, "lr": 4.9796854510176664e-05, "epoch": 2.731023102310231, "percentage": 13.66, "elapsed_time": "0:58:10", "remaining_time": "6:07:52", "throughput": 1500.69, "total_tokens": 5238336} {"current_steps": 24830, "total_steps": 181800, "loss": 0.0548, "lr": 4.979654905285881e-05, "epoch": 2.7315731573157316, "percentage": 13.66, "elapsed_time": "0:58:11", "remaining_time": "6:07:51", "throughput": 1500.68, "total_tokens": 5239328} {"current_steps": 24835, "total_steps": 181800, "loss": 0.0437, "lr": 4.979624336700307e-05, "epoch": 2.7321232123212322, "percentage": 13.66, "elapsed_time": "0:58:11", "remaining_time": "6:07:50", "throughput": 1500.69, "total_tokens": 5240384} {"current_steps": 24840, "total_steps": 181800, "loss": 0.1548, "lr": 4.979593745261225e-05, "epoch": 2.7326732673267324, "percentage": 13.66, "elapsed_time": "0:58:12", "remaining_time": "6:07:49", "throughput": 1500.69, "total_tokens": 5241440} {"current_steps": 24845, "total_steps": 181800, "loss": 0.0297, "lr": 4.979563130968917e-05, "epoch": 2.733223322332233, "percentage": 13.67, "elapsed_time": "0:58:13", "remaining_time": "6:07:48", "throughput": 1500.7, "total_tokens": 5242496} {"current_steps": 24850, "total_steps": 181800, "loss": 0.1302, "lr": 4.9795324938236664e-05, "epoch": 2.7337733773377337, "percentage": 13.67, "elapsed_time": "0:58:14", "remaining_time": "6:07:48", "throughput": 1500.73, "total_tokens": 5243616} {"current_steps": 24855, "total_steps": 181800, "loss": 0.0773, "lr": 4.9795018338257535e-05, "epoch": 2.7343234323432344, "percentage": 13.67, "elapsed_time": "0:58:14", "remaining_time": "6:07:47", "throughput": 1500.74, "total_tokens": 5244704} {"current_steps": 24860, "total_steps": 181800, "loss": 0.0136, "lr": 4.9794711509754636e-05, "epoch": 2.734873487348735, "percentage": 13.67, "elapsed_time": "0:58:15", "remaining_time": "6:07:46", "throughput": 1500.75, "total_tokens": 5245760} {"current_steps": 24865, "total_steps": 181800, "loss": 0.178, "lr": 4.979440445273076e-05, "epoch": 2.7354235423542352, "percentage": 13.68, "elapsed_time": "0:58:16", "remaining_time": "6:07:46", "throughput": 1500.68, "total_tokens": 5246816} {"current_steps": 24870, "total_steps": 181800, "loss": 0.1387, "lr": 4.979409716718877e-05, "epoch": 2.735973597359736, "percentage": 13.68, "elapsed_time": "0:58:16", "remaining_time": "6:07:46", "throughput": 1500.68, "total_tokens": 5247840} {"current_steps": 24875, "total_steps": 181800, "loss": 0.0632, "lr": 4.9793789653131474e-05, "epoch": 2.7365236523652365, "percentage": 13.68, "elapsed_time": "0:58:17", "remaining_time": "6:07:45", "throughput": 1500.69, "total_tokens": 5248928} {"current_steps": 24880, "total_steps": 181800, "loss": 0.0461, "lr": 4.979348191056172e-05, "epoch": 2.737073707370737, "percentage": 13.69, "elapsed_time": "0:58:18", "remaining_time": "6:07:44", "throughput": 1500.7, "total_tokens": 5249984} {"current_steps": 24885, "total_steps": 181800, "loss": 0.0748, "lr": 4.979317393948234e-05, "epoch": 2.737623762376238, "percentage": 13.69, "elapsed_time": "0:58:19", "remaining_time": "6:07:43", "throughput": 1500.71, "total_tokens": 5251072} {"current_steps": 24890, "total_steps": 181800, "loss": 0.0328, "lr": 4.979286573989617e-05, "epoch": 2.738173817381738, "percentage": 13.69, "elapsed_time": "0:58:19", "remaining_time": "6:07:42", "throughput": 1500.71, "total_tokens": 5252096} {"current_steps": 24895, "total_steps": 181800, "loss": 0.0413, "lr": 4.979255731180605e-05, "epoch": 2.7387238723872387, "percentage": 13.69, "elapsed_time": "0:58:20", "remaining_time": "6:07:42", "throughput": 1500.71, "total_tokens": 5253120} {"current_steps": 24900, "total_steps": 181800, "loss": 0.1175, "lr": 4.9792248655214834e-05, "epoch": 2.7392739273927393, "percentage": 13.7, "elapsed_time": "0:58:21", "remaining_time": "6:07:41", "throughput": 1500.71, "total_tokens": 5254144} {"current_steps": 24905, "total_steps": 181800, "loss": 0.2012, "lr": 4.9791939770125364e-05, "epoch": 2.73982398239824, "percentage": 13.7, "elapsed_time": "0:58:21", "remaining_time": "6:07:40", "throughput": 1500.71, "total_tokens": 5255200} {"current_steps": 24910, "total_steps": 181800, "loss": 0.1404, "lr": 4.9791630656540463e-05, "epoch": 2.7403740374037406, "percentage": 13.7, "elapsed_time": "0:58:22", "remaining_time": "6:07:39", "throughput": 1500.7, "total_tokens": 5256192} {"current_steps": 24915, "total_steps": 181800, "loss": 0.0627, "lr": 4.979132131446301e-05, "epoch": 2.740924092409241, "percentage": 13.7, "elapsed_time": "0:58:23", "remaining_time": "6:07:38", "throughput": 1500.72, "total_tokens": 5257280} {"current_steps": 24920, "total_steps": 181800, "loss": 0.0723, "lr": 4.9791011743895846e-05, "epoch": 2.7414741474147415, "percentage": 13.71, "elapsed_time": "0:58:23", "remaining_time": "6:07:38", "throughput": 1500.71, "total_tokens": 5258272} {"current_steps": 24925, "total_steps": 181800, "loss": 0.0921, "lr": 4.979070194484182e-05, "epoch": 2.742024202420242, "percentage": 13.71, "elapsed_time": "0:58:24", "remaining_time": "6:07:37", "throughput": 1500.71, "total_tokens": 5259328} {"current_steps": 24930, "total_steps": 181800, "loss": 0.0812, "lr": 4.979039191730379e-05, "epoch": 2.7425742574257423, "percentage": 13.71, "elapsed_time": "0:58:25", "remaining_time": "6:07:36", "throughput": 1500.71, "total_tokens": 5260352} {"current_steps": 24935, "total_steps": 181800, "loss": 0.1035, "lr": 4.9790081661284616e-05, "epoch": 2.743124312431243, "percentage": 13.72, "elapsed_time": "0:58:25", "remaining_time": "6:07:35", "throughput": 1500.72, "total_tokens": 5261408} {"current_steps": 24940, "total_steps": 181800, "loss": 0.1587, "lr": 4.978977117678715e-05, "epoch": 2.7436743674367436, "percentage": 13.72, "elapsed_time": "0:58:26", "remaining_time": "6:07:34", "throughput": 1500.71, "total_tokens": 5262400} {"current_steps": 24945, "total_steps": 181800, "loss": 0.0676, "lr": 4.978946046381426e-05, "epoch": 2.7442244224422443, "percentage": 13.72, "elapsed_time": "0:58:27", "remaining_time": "6:07:34", "throughput": 1500.72, "total_tokens": 5263488} {"current_steps": 24950, "total_steps": 181800, "loss": 0.1241, "lr": 4.9789149522368805e-05, "epoch": 2.744774477447745, "percentage": 13.72, "elapsed_time": "0:58:27", "remaining_time": "6:07:33", "throughput": 1500.72, "total_tokens": 5264512} {"current_steps": 24955, "total_steps": 181800, "loss": 0.0492, "lr": 4.978883835245366e-05, "epoch": 2.745324532453245, "percentage": 13.73, "elapsed_time": "0:58:28", "remaining_time": "6:07:32", "throughput": 1500.72, "total_tokens": 5265536} {"current_steps": 24960, "total_steps": 181800, "loss": 0.0346, "lr": 4.9788526954071685e-05, "epoch": 2.745874587458746, "percentage": 13.73, "elapsed_time": "0:58:29", "remaining_time": "6:07:31", "throughput": 1500.73, "total_tokens": 5266624} {"current_steps": 24965, "total_steps": 181800, "loss": 0.0281, "lr": 4.9788215327225754e-05, "epoch": 2.7464246424642464, "percentage": 13.73, "elapsed_time": "0:58:30", "remaining_time": "6:07:30", "throughput": 1500.74, "total_tokens": 5267680} {"current_steps": 24970, "total_steps": 181800, "loss": 0.0754, "lr": 4.978790347191873e-05, "epoch": 2.746974697469747, "percentage": 13.73, "elapsed_time": "0:58:30", "remaining_time": "6:07:30", "throughput": 1500.73, "total_tokens": 5268704} {"current_steps": 24975, "total_steps": 181800, "loss": 0.11, "lr": 4.97875913881535e-05, "epoch": 2.7475247524752477, "percentage": 13.74, "elapsed_time": "0:58:31", "remaining_time": "6:07:29", "throughput": 1500.73, "total_tokens": 5269728} {"current_steps": 24980, "total_steps": 181800, "loss": 0.0746, "lr": 4.978727907593293e-05, "epoch": 2.748074807480748, "percentage": 13.74, "elapsed_time": "0:58:32", "remaining_time": "6:07:28", "throughput": 1500.73, "total_tokens": 5270784} {"current_steps": 24985, "total_steps": 181800, "loss": 0.0516, "lr": 4.97869665352599e-05, "epoch": 2.7486248624862486, "percentage": 13.74, "elapsed_time": "0:58:32", "remaining_time": "6:07:27", "throughput": 1500.74, "total_tokens": 5271840} {"current_steps": 24990, "total_steps": 181800, "loss": 0.0439, "lr": 4.97866537661373e-05, "epoch": 2.7491749174917492, "percentage": 13.75, "elapsed_time": "0:58:33", "remaining_time": "6:07:27", "throughput": 1500.75, "total_tokens": 5272928} {"current_steps": 24995, "total_steps": 181800, "loss": 0.1633, "lr": 4.978634076856801e-05, "epoch": 2.7497249724972495, "percentage": 13.75, "elapsed_time": "0:58:34", "remaining_time": "6:07:26", "throughput": 1500.76, "total_tokens": 5273984} {"current_steps": 25000, "total_steps": 181800, "loss": 0.0165, "lr": 4.97860275425549e-05, "epoch": 2.7502750275027505, "percentage": 13.75, "elapsed_time": "0:58:34", "remaining_time": "6:07:25", "throughput": 1500.75, "total_tokens": 5274976} {"current_steps": 25005, "total_steps": 181800, "loss": 0.0416, "lr": 4.978571408810088e-05, "epoch": 2.7508250825082508, "percentage": 13.75, "elapsed_time": "0:58:35", "remaining_time": "6:07:24", "throughput": 1500.75, "total_tokens": 5276000} {"current_steps": 25010, "total_steps": 181800, "loss": 0.1023, "lr": 4.978540040520882e-05, "epoch": 2.7513751375137514, "percentage": 13.76, "elapsed_time": "0:58:36", "remaining_time": "6:07:23", "throughput": 1500.76, "total_tokens": 5277088} {"current_steps": 25015, "total_steps": 181800, "loss": 0.0795, "lr": 4.978508649388161e-05, "epoch": 2.751925192519252, "percentage": 13.76, "elapsed_time": "0:58:36", "remaining_time": "6:07:22", "throughput": 1500.76, "total_tokens": 5278112} {"current_steps": 25020, "total_steps": 181800, "loss": 0.0851, "lr": 4.978477235412216e-05, "epoch": 2.7524752475247523, "percentage": 13.76, "elapsed_time": "0:58:37", "remaining_time": "6:07:22", "throughput": 1500.75, "total_tokens": 5279104} {"current_steps": 25025, "total_steps": 181800, "loss": 0.0662, "lr": 4.9784457985933354e-05, "epoch": 2.753025302530253, "percentage": 13.77, "elapsed_time": "0:58:38", "remaining_time": "6:07:21", "throughput": 1500.78, "total_tokens": 5280224} {"current_steps": 25030, "total_steps": 181800, "loss": 0.0458, "lr": 4.9784143389318095e-05, "epoch": 2.7535753575357536, "percentage": 13.77, "elapsed_time": "0:58:39", "remaining_time": "6:07:20", "throughput": 1500.78, "total_tokens": 5281248} {"current_steps": 25035, "total_steps": 181800, "loss": 0.1426, "lr": 4.9783828564279274e-05, "epoch": 2.754125412541254, "percentage": 13.77, "elapsed_time": "0:58:39", "remaining_time": "6:07:19", "throughput": 1500.79, "total_tokens": 5282336} {"current_steps": 25040, "total_steps": 181800, "loss": 0.0475, "lr": 4.97835135108198e-05, "epoch": 2.754675467546755, "percentage": 13.77, "elapsed_time": "0:58:40", "remaining_time": "6:07:18", "throughput": 1500.8, "total_tokens": 5283392} {"current_steps": 25045, "total_steps": 181800, "loss": 0.0427, "lr": 4.978319822894257e-05, "epoch": 2.755225522552255, "percentage": 13.78, "elapsed_time": "0:58:41", "remaining_time": "6:07:18", "throughput": 1500.79, "total_tokens": 5284384} {"current_steps": 25050, "total_steps": 181800, "loss": 0.0255, "lr": 4.97828827186505e-05, "epoch": 2.7557755775577557, "percentage": 13.78, "elapsed_time": "0:58:41", "remaining_time": "6:07:17", "throughput": 1500.79, "total_tokens": 5285440} {"current_steps": 25055, "total_steps": 181800, "loss": 0.1411, "lr": 4.9782566979946485e-05, "epoch": 2.7563256325632564, "percentage": 13.78, "elapsed_time": "0:58:42", "remaining_time": "6:07:16", "throughput": 1500.82, "total_tokens": 5286560} {"current_steps": 25060, "total_steps": 181800, "loss": 0.0729, "lr": 4.978225101283345e-05, "epoch": 2.756875687568757, "percentage": 13.78, "elapsed_time": "0:58:43", "remaining_time": "6:07:15", "throughput": 1500.83, "total_tokens": 5287648} {"current_steps": 25065, "total_steps": 181800, "loss": 0.0366, "lr": 4.978193481731429e-05, "epoch": 2.7574257425742577, "percentage": 13.79, "elapsed_time": "0:58:43", "remaining_time": "6:07:15", "throughput": 1500.84, "total_tokens": 5288704} {"current_steps": 25070, "total_steps": 181800, "loss": 0.0903, "lr": 4.978161839339194e-05, "epoch": 2.757975797579758, "percentage": 13.79, "elapsed_time": "0:58:44", "remaining_time": "6:07:14", "throughput": 1500.83, "total_tokens": 5289728} {"current_steps": 25075, "total_steps": 181800, "loss": 0.0295, "lr": 4.9781301741069295e-05, "epoch": 2.7585258525852585, "percentage": 13.79, "elapsed_time": "0:58:45", "remaining_time": "6:07:13", "throughput": 1500.85, "total_tokens": 5290816} {"current_steps": 25080, "total_steps": 181800, "loss": 0.0776, "lr": 4.978098486034929e-05, "epoch": 2.759075907590759, "percentage": 13.8, "elapsed_time": "0:58:45", "remaining_time": "6:07:12", "throughput": 1500.87, "total_tokens": 5291936} {"current_steps": 25085, "total_steps": 181800, "loss": 0.083, "lr": 4.9780667751234835e-05, "epoch": 2.7596259625962594, "percentage": 13.8, "elapsed_time": "0:58:46", "remaining_time": "6:07:11", "throughput": 1500.89, "total_tokens": 5293024} {"current_steps": 25090, "total_steps": 181800, "loss": 0.0947, "lr": 4.978035041372885e-05, "epoch": 2.76017601760176, "percentage": 13.8, "elapsed_time": "0:58:47", "remaining_time": "6:07:11", "throughput": 1500.88, "total_tokens": 5294048} {"current_steps": 25095, "total_steps": 181800, "loss": 0.0559, "lr": 4.9780032847834276e-05, "epoch": 2.7607260726072607, "percentage": 13.8, "elapsed_time": "0:58:47", "remaining_time": "6:07:10", "throughput": 1500.88, "total_tokens": 5295072} {"current_steps": 25100, "total_steps": 181800, "loss": 0.0413, "lr": 4.977971505355402e-05, "epoch": 2.7612761276127613, "percentage": 13.81, "elapsed_time": "0:58:48", "remaining_time": "6:07:09", "throughput": 1500.88, "total_tokens": 5296096} {"current_steps": 25105, "total_steps": 181800, "loss": 0.054, "lr": 4.9779397030891026e-05, "epoch": 2.761826182618262, "percentage": 13.81, "elapsed_time": "0:58:49", "remaining_time": "6:07:08", "throughput": 1500.91, "total_tokens": 5297248} {"current_steps": 25110, "total_steps": 181800, "loss": 0.0494, "lr": 4.9779078779848224e-05, "epoch": 2.762376237623762, "percentage": 13.81, "elapsed_time": "0:58:50", "remaining_time": "6:07:07", "throughput": 1500.9, "total_tokens": 5298240} {"current_steps": 25115, "total_steps": 181800, "loss": 0.0601, "lr": 4.977876030042854e-05, "epoch": 2.762926292629263, "percentage": 13.81, "elapsed_time": "0:58:50", "remaining_time": "6:07:07", "throughput": 1500.91, "total_tokens": 5299296} {"current_steps": 25120, "total_steps": 181800, "loss": 0.1209, "lr": 4.977844159263492e-05, "epoch": 2.7634763476347635, "percentage": 13.82, "elapsed_time": "0:58:51", "remaining_time": "6:07:06", "throughput": 1500.9, "total_tokens": 5300288} {"current_steps": 25125, "total_steps": 181800, "loss": 0.037, "lr": 4.9778122656470284e-05, "epoch": 2.764026402640264, "percentage": 13.82, "elapsed_time": "0:58:52", "remaining_time": "6:07:05", "throughput": 1500.9, "total_tokens": 5301312} {"current_steps": 25130, "total_steps": 181800, "loss": 0.2704, "lr": 4.977780349193758e-05, "epoch": 2.7645764576457648, "percentage": 13.82, "elapsed_time": "0:58:52", "remaining_time": "6:07:04", "throughput": 1500.89, "total_tokens": 5302336} {"current_steps": 25135, "total_steps": 181800, "loss": 0.0149, "lr": 4.977748409903975e-05, "epoch": 2.765126512651265, "percentage": 13.83, "elapsed_time": "0:58:53", "remaining_time": "6:07:03", "throughput": 1500.91, "total_tokens": 5303424} {"current_steps": 25140, "total_steps": 181800, "loss": 0.0951, "lr": 4.9777164477779745e-05, "epoch": 2.7656765676567656, "percentage": 13.83, "elapsed_time": "0:58:54", "remaining_time": "6:07:03", "throughput": 1500.9, "total_tokens": 5304448} {"current_steps": 25145, "total_steps": 181800, "loss": 0.0323, "lr": 4.97768446281605e-05, "epoch": 2.7662266226622663, "percentage": 13.83, "elapsed_time": "0:58:54", "remaining_time": "6:07:02", "throughput": 1500.88, "total_tokens": 5305408} {"current_steps": 25150, "total_steps": 181800, "loss": 0.0569, "lr": 4.9776524550184965e-05, "epoch": 2.766776677667767, "percentage": 13.83, "elapsed_time": "0:58:55", "remaining_time": "6:07:01", "throughput": 1500.89, "total_tokens": 5306464} {"current_steps": 25155, "total_steps": 181800, "loss": 0.0262, "lr": 4.97762042438561e-05, "epoch": 2.7673267326732676, "percentage": 13.84, "elapsed_time": "0:58:56", "remaining_time": "6:07:00", "throughput": 1500.9, "total_tokens": 5307552} {"current_steps": 25160, "total_steps": 181800, "loss": 0.1481, "lr": 4.977588370917684e-05, "epoch": 2.7678767876787678, "percentage": 13.84, "elapsed_time": "0:58:56", "remaining_time": "6:07:00", "throughput": 1500.91, "total_tokens": 5308608} {"current_steps": 25165, "total_steps": 181800, "loss": 0.0325, "lr": 4.9775562946150155e-05, "epoch": 2.7684268426842684, "percentage": 13.84, "elapsed_time": "0:58:57", "remaining_time": "6:06:59", "throughput": 1500.9, "total_tokens": 5309600} {"current_steps": 25170, "total_steps": 181800, "loss": 0.0326, "lr": 4.9775241954779e-05, "epoch": 2.768976897689769, "percentage": 13.84, "elapsed_time": "0:58:58", "remaining_time": "6:06:58", "throughput": 1500.9, "total_tokens": 5310656} {"current_steps": 25175, "total_steps": 181800, "loss": 0.0667, "lr": 4.977492073506632e-05, "epoch": 2.7695269526952693, "percentage": 13.85, "elapsed_time": "0:58:58", "remaining_time": "6:06:57", "throughput": 1500.9, "total_tokens": 5311680} {"current_steps": 25180, "total_steps": 181800, "loss": 0.1175, "lr": 4.977459928701508e-05, "epoch": 2.77007700770077, "percentage": 13.85, "elapsed_time": "0:58:59", "remaining_time": "6:06:56", "throughput": 1500.91, "total_tokens": 5312768} {"current_steps": 25185, "total_steps": 181800, "loss": 0.0439, "lr": 4.977427761062825e-05, "epoch": 2.7706270627062706, "percentage": 13.85, "elapsed_time": "0:59:00", "remaining_time": "6:06:56", "throughput": 1500.9, "total_tokens": 5313760} {"current_steps": 25190, "total_steps": 181800, "loss": 0.0842, "lr": 4.97739557059088e-05, "epoch": 2.771177117711771, "percentage": 13.86, "elapsed_time": "0:59:01", "remaining_time": "6:06:55", "throughput": 1500.92, "total_tokens": 5314848} {"current_steps": 25195, "total_steps": 181800, "loss": 0.1787, "lr": 4.977363357285968e-05, "epoch": 2.771727172717272, "percentage": 13.86, "elapsed_time": "0:59:01", "remaining_time": "6:06:54", "throughput": 1500.91, "total_tokens": 5315872} {"current_steps": 25200, "total_steps": 181800, "loss": 0.0802, "lr": 4.977331121148386e-05, "epoch": 2.772277227722772, "percentage": 13.86, "elapsed_time": "0:59:02", "remaining_time": "6:06:53", "throughput": 1500.91, "total_tokens": 5316896} {"current_steps": 25205, "total_steps": 181800, "loss": 0.0211, "lr": 4.9772988621784335e-05, "epoch": 2.7728272827282727, "percentage": 13.86, "elapsed_time": "0:59:03", "remaining_time": "6:06:52", "throughput": 1500.93, "total_tokens": 5317984} {"current_steps": 25210, "total_steps": 181800, "loss": 0.0837, "lr": 4.9772665803764054e-05, "epoch": 2.7733773377337734, "percentage": 13.87, "elapsed_time": "0:59:03", "remaining_time": "6:06:52", "throughput": 1500.92, "total_tokens": 5318976} {"current_steps": 25215, "total_steps": 181800, "loss": 0.1383, "lr": 4.9772342757425995e-05, "epoch": 2.773927392739274, "percentage": 13.87, "elapsed_time": "0:59:04", "remaining_time": "6:06:51", "throughput": 1500.93, "total_tokens": 5320064} {"current_steps": 25220, "total_steps": 181800, "loss": 0.0271, "lr": 4.977201948277313e-05, "epoch": 2.7744774477447747, "percentage": 13.87, "elapsed_time": "0:59:05", "remaining_time": "6:06:50", "throughput": 1500.93, "total_tokens": 5321088} {"current_steps": 25225, "total_steps": 181800, "loss": 0.1058, "lr": 4.977169597980847e-05, "epoch": 2.775027502750275, "percentage": 13.88, "elapsed_time": "0:59:05", "remaining_time": "6:06:49", "throughput": 1500.93, "total_tokens": 5322112} {"current_steps": 25230, "total_steps": 181800, "loss": 0.2017, "lr": 4.977137224853496e-05, "epoch": 2.7755775577557755, "percentage": 13.88, "elapsed_time": "0:59:06", "remaining_time": "6:06:48", "throughput": 1500.92, "total_tokens": 5323104} {"current_steps": 25235, "total_steps": 181800, "loss": 0.0845, "lr": 4.9771048288955606e-05, "epoch": 2.776127612761276, "percentage": 13.88, "elapsed_time": "0:59:07", "remaining_time": "6:06:48", "throughput": 1500.92, "total_tokens": 5324128} {"current_steps": 25240, "total_steps": 181800, "loss": 0.0624, "lr": 4.9770724101073386e-05, "epoch": 2.776677667766777, "percentage": 13.88, "elapsed_time": "0:59:07", "remaining_time": "6:06:47", "throughput": 1500.93, "total_tokens": 5325216} {"current_steps": 25245, "total_steps": 181800, "loss": 0.0195, "lr": 4.977039968489128e-05, "epoch": 2.7772277227722775, "percentage": 13.89, "elapsed_time": "0:59:08", "remaining_time": "6:06:46", "throughput": 1500.95, "total_tokens": 5326304} {"current_steps": 25250, "total_steps": 181800, "loss": 0.0734, "lr": 4.977007504041229e-05, "epoch": 2.7777777777777777, "percentage": 13.89, "elapsed_time": "0:59:09", "remaining_time": "6:06:45", "throughput": 1500.98, "total_tokens": 5327456} {"current_steps": 25255, "total_steps": 181800, "loss": 0.1037, "lr": 4.976975016763941e-05, "epoch": 2.7783278327832783, "percentage": 13.89, "elapsed_time": "0:59:09", "remaining_time": "6:06:44", "throughput": 1501.0, "total_tokens": 5328544} {"current_steps": 25260, "total_steps": 181800, "loss": 0.1184, "lr": 4.9769425066575624e-05, "epoch": 2.778877887788779, "percentage": 13.89, "elapsed_time": "0:59:10", "remaining_time": "6:06:44", "throughput": 1500.98, "total_tokens": 5329504} {"current_steps": 25265, "total_steps": 181800, "loss": 0.049, "lr": 4.9769099737223936e-05, "epoch": 2.779427942794279, "percentage": 13.9, "elapsed_time": "0:59:11", "remaining_time": "6:06:43", "throughput": 1501.0, "total_tokens": 5330592} {"current_steps": 25270, "total_steps": 181800, "loss": 0.0355, "lr": 4.976877417958734e-05, "epoch": 2.77997799779978, "percentage": 13.9, "elapsed_time": "0:59:12", "remaining_time": "6:06:42", "throughput": 1501.02, "total_tokens": 5331712} {"current_steps": 25275, "total_steps": 181800, "loss": 0.0213, "lr": 4.976844839366883e-05, "epoch": 2.7805280528052805, "percentage": 13.9, "elapsed_time": "0:59:12", "remaining_time": "6:06:41", "throughput": 1501.02, "total_tokens": 5332736} {"current_steps": 25280, "total_steps": 181800, "loss": 0.0446, "lr": 4.976812237947143e-05, "epoch": 2.781078107810781, "percentage": 13.91, "elapsed_time": "0:59:13", "remaining_time": "6:06:40", "throughput": 1501.02, "total_tokens": 5333792} {"current_steps": 25285, "total_steps": 181800, "loss": 0.0228, "lr": 4.976779613699812e-05, "epoch": 2.781628162816282, "percentage": 13.91, "elapsed_time": "0:59:14", "remaining_time": "6:06:40", "throughput": 1501.05, "total_tokens": 5334912} {"current_steps": 25290, "total_steps": 181800, "loss": 0.0679, "lr": 4.976746966625192e-05, "epoch": 2.782178217821782, "percentage": 13.91, "elapsed_time": "0:59:14", "remaining_time": "6:06:39", "throughput": 1501.06, "total_tokens": 5336000} {"current_steps": 25295, "total_steps": 181800, "loss": 0.0853, "lr": 4.9767142967235835e-05, "epoch": 2.7827282728272826, "percentage": 13.91, "elapsed_time": "0:59:15", "remaining_time": "6:06:38", "throughput": 1501.08, "total_tokens": 5337088} {"current_steps": 25300, "total_steps": 181800, "loss": 0.0249, "lr": 4.976681603995288e-05, "epoch": 2.7832783278327833, "percentage": 13.92, "elapsed_time": "0:59:16", "remaining_time": "6:06:37", "throughput": 1501.07, "total_tokens": 5338080} {"current_steps": 25305, "total_steps": 181800, "loss": 0.0722, "lr": 4.9766488884406066e-05, "epoch": 2.783828382838284, "percentage": 13.92, "elapsed_time": "0:59:16", "remaining_time": "6:06:36", "throughput": 1501.09, "total_tokens": 5339200} {"current_steps": 25310, "total_steps": 181800, "loss": 0.063, "lr": 4.976616150059841e-05, "epoch": 2.7843784378437846, "percentage": 13.92, "elapsed_time": "0:59:17", "remaining_time": "6:06:36", "throughput": 1501.11, "total_tokens": 5340288} {"current_steps": 25315, "total_steps": 181800, "loss": 0.1509, "lr": 4.976583388853292e-05, "epoch": 2.784928492849285, "percentage": 13.92, "elapsed_time": "0:59:18", "remaining_time": "6:06:35", "throughput": 1501.11, "total_tokens": 5341312} {"current_steps": 25320, "total_steps": 181800, "loss": 0.0343, "lr": 4.976550604821263e-05, "epoch": 2.7854785478547854, "percentage": 13.93, "elapsed_time": "0:59:18", "remaining_time": "6:06:34", "throughput": 1501.11, "total_tokens": 5342368} {"current_steps": 25325, "total_steps": 181800, "loss": 0.1798, "lr": 4.9765177979640556e-05, "epoch": 2.786028602860286, "percentage": 13.93, "elapsed_time": "0:59:19", "remaining_time": "6:06:33", "throughput": 1501.13, "total_tokens": 5343456} {"current_steps": 25330, "total_steps": 181800, "loss": 0.0611, "lr": 4.9764849682819716e-05, "epoch": 2.7865786578657867, "percentage": 13.93, "elapsed_time": "0:59:20", "remaining_time": "6:06:33", "throughput": 1501.13, "total_tokens": 5344512} {"current_steps": 25335, "total_steps": 181800, "loss": 0.0511, "lr": 4.976452115775314e-05, "epoch": 2.7871287128712874, "percentage": 13.94, "elapsed_time": "0:59:21", "remaining_time": "6:06:32", "throughput": 1501.15, "total_tokens": 5345600} {"current_steps": 25340, "total_steps": 181800, "loss": 0.1475, "lr": 4.976419240444385e-05, "epoch": 2.7876787678767876, "percentage": 13.94, "elapsed_time": "0:59:21", "remaining_time": "6:06:31", "throughput": 1501.14, "total_tokens": 5346592} {"current_steps": 25345, "total_steps": 181800, "loss": 0.0155, "lr": 4.976386342289489e-05, "epoch": 2.7882288228822882, "percentage": 13.94, "elapsed_time": "0:59:22", "remaining_time": "6:06:30", "throughput": 1501.15, "total_tokens": 5347680} {"current_steps": 25350, "total_steps": 181800, "loss": 0.0349, "lr": 4.976353421310929e-05, "epoch": 2.788778877887789, "percentage": 13.94, "elapsed_time": "0:59:23", "remaining_time": "6:06:29", "throughput": 1501.19, "total_tokens": 5348832} {"current_steps": 25355, "total_steps": 181800, "loss": 0.1222, "lr": 4.9763204775090064e-05, "epoch": 2.789328932893289, "percentage": 13.95, "elapsed_time": "0:59:23", "remaining_time": "6:06:29", "throughput": 1501.19, "total_tokens": 5349888} {"current_steps": 25360, "total_steps": 181800, "loss": 0.1283, "lr": 4.976287510884027e-05, "epoch": 2.7898789878987897, "percentage": 13.95, "elapsed_time": "0:59:24", "remaining_time": "6:06:28", "throughput": 1501.19, "total_tokens": 5350912} {"current_steps": 25365, "total_steps": 181800, "loss": 0.1039, "lr": 4.976254521436293e-05, "epoch": 2.7904290429042904, "percentage": 13.95, "elapsed_time": "0:59:25", "remaining_time": "6:06:27", "throughput": 1501.2, "total_tokens": 5351968} {"current_steps": 25370, "total_steps": 181800, "loss": 0.0892, "lr": 4.9762215091661105e-05, "epoch": 2.790979097909791, "percentage": 13.95, "elapsed_time": "0:59:25", "remaining_time": "6:06:26", "throughput": 1501.22, "total_tokens": 5353088} {"current_steps": 25375, "total_steps": 181800, "loss": 0.0658, "lr": 4.976188474073781e-05, "epoch": 2.7915291529152917, "percentage": 13.96, "elapsed_time": "0:59:26", "remaining_time": "6:06:25", "throughput": 1501.24, "total_tokens": 5354176} {"current_steps": 25380, "total_steps": 181800, "loss": 0.1372, "lr": 4.976155416159612e-05, "epoch": 2.792079207920792, "percentage": 13.96, "elapsed_time": "0:59:27", "remaining_time": "6:06:25", "throughput": 1501.25, "total_tokens": 5355264} {"current_steps": 25385, "total_steps": 181800, "loss": 0.0944, "lr": 4.976122335423906e-05, "epoch": 2.7926292629262925, "percentage": 13.96, "elapsed_time": "0:59:27", "remaining_time": "6:06:24", "throughput": 1501.25, "total_tokens": 5356288} {"current_steps": 25390, "total_steps": 181800, "loss": 0.0274, "lr": 4.976089231866969e-05, "epoch": 2.793179317931793, "percentage": 13.97, "elapsed_time": "0:59:28", "remaining_time": "6:06:23", "throughput": 1501.25, "total_tokens": 5357312} {"current_steps": 25395, "total_steps": 181800, "loss": 0.0555, "lr": 4.9760561054891055e-05, "epoch": 2.793729372937294, "percentage": 13.97, "elapsed_time": "0:59:29", "remaining_time": "6:06:22", "throughput": 1501.26, "total_tokens": 5358368} {"current_steps": 25400, "total_steps": 181800, "loss": 0.084, "lr": 4.9760229562906205e-05, "epoch": 2.7942794279427945, "percentage": 13.97, "elapsed_time": "0:59:29", "remaining_time": "6:06:21", "throughput": 1501.25, "total_tokens": 5359392} {"current_steps": 25405, "total_steps": 181800, "loss": 0.1185, "lr": 4.9759897842718205e-05, "epoch": 2.7948294829482947, "percentage": 13.97, "elapsed_time": "0:59:30", "remaining_time": "6:06:21", "throughput": 1501.25, "total_tokens": 5360416} {"current_steps": 25410, "total_steps": 181800, "loss": 0.035, "lr": 4.975956589433011e-05, "epoch": 2.7953795379537953, "percentage": 13.98, "elapsed_time": "0:59:31", "remaining_time": "6:06:20", "throughput": 1501.25, "total_tokens": 5361472} {"current_steps": 25415, "total_steps": 181800, "loss": 0.0937, "lr": 4.975923371774497e-05, "epoch": 2.795929592959296, "percentage": 13.98, "elapsed_time": "0:59:32", "remaining_time": "6:06:19", "throughput": 1501.26, "total_tokens": 5362528} {"current_steps": 25420, "total_steps": 181800, "loss": 0.0172, "lr": 4.975890131296586e-05, "epoch": 2.7964796479647966, "percentage": 13.98, "elapsed_time": "0:59:32", "remaining_time": "6:06:18", "throughput": 1501.27, "total_tokens": 5363584} {"current_steps": 25425, "total_steps": 181800, "loss": 0.0761, "lr": 4.9758568679995835e-05, "epoch": 2.7970297029702973, "percentage": 13.99, "elapsed_time": "0:59:33", "remaining_time": "6:06:17", "throughput": 1501.28, "total_tokens": 5364672} {"current_steps": 25430, "total_steps": 181800, "loss": 0.0393, "lr": 4.975823581883796e-05, "epoch": 2.7975797579757975, "percentage": 13.99, "elapsed_time": "0:59:34", "remaining_time": "6:06:17", "throughput": 1501.31, "total_tokens": 5365792} {"current_steps": 25435, "total_steps": 181800, "loss": 0.0646, "lr": 4.975790272949531e-05, "epoch": 2.798129812981298, "percentage": 13.99, "elapsed_time": "0:59:34", "remaining_time": "6:06:16", "throughput": 1501.31, "total_tokens": 5366848} {"current_steps": 25440, "total_steps": 181800, "loss": 0.0838, "lr": 4.975756941197095e-05, "epoch": 2.798679867986799, "percentage": 13.99, "elapsed_time": "0:59:35", "remaining_time": "6:06:15", "throughput": 1501.33, "total_tokens": 5367936} {"current_steps": 25445, "total_steps": 181800, "loss": 0.0426, "lr": 4.975723586626795e-05, "epoch": 2.799229922992299, "percentage": 14.0, "elapsed_time": "0:59:36", "remaining_time": "6:06:14", "throughput": 1501.35, "total_tokens": 5369056} {"current_steps": 25450, "total_steps": 181800, "loss": 0.0579, "lr": 4.975690209238939e-05, "epoch": 2.7997799779977997, "percentage": 14.0, "elapsed_time": "0:59:36", "remaining_time": "6:06:14", "throughput": 1501.36, "total_tokens": 5370144} {"current_steps": 25455, "total_steps": 181800, "loss": 0.0951, "lr": 4.975656809033834e-05, "epoch": 2.8003300330033003, "percentage": 14.0, "elapsed_time": "0:59:37", "remaining_time": "6:06:13", "throughput": 1501.39, "total_tokens": 5371264} {"current_steps": 25460, "total_steps": 181800, "loss": 0.0935, "lr": 4.9756233860117885e-05, "epoch": 2.800880088008801, "percentage": 14.0, "elapsed_time": "0:59:38", "remaining_time": "6:06:12", "throughput": 1501.4, "total_tokens": 5372352} {"current_steps": 25465, "total_steps": 181800, "loss": 0.1185, "lr": 4.97558994017311e-05, "epoch": 2.8014301430143016, "percentage": 14.01, "elapsed_time": "0:59:38", "remaining_time": "6:06:11", "throughput": 1501.41, "total_tokens": 5373408} {"current_steps": 25470, "total_steps": 181800, "loss": 0.0355, "lr": 4.9755564715181064e-05, "epoch": 2.801980198019802, "percentage": 14.01, "elapsed_time": "0:59:39", "remaining_time": "6:06:10", "throughput": 1501.43, "total_tokens": 5374496} {"current_steps": 25475, "total_steps": 181800, "loss": 0.0632, "lr": 4.975522980047087e-05, "epoch": 2.8025302530253025, "percentage": 14.01, "elapsed_time": "0:59:40", "remaining_time": "6:06:10", "throughput": 1501.43, "total_tokens": 5375552} {"current_steps": 25480, "total_steps": 181800, "loss": 0.1216, "lr": 4.97548946576036e-05, "epoch": 2.803080308030803, "percentage": 14.02, "elapsed_time": "0:59:40", "remaining_time": "6:06:09", "throughput": 1501.43, "total_tokens": 5376576} {"current_steps": 25485, "total_steps": 181800, "loss": 0.1802, "lr": 4.975455928658235e-05, "epoch": 2.8036303630363038, "percentage": 14.02, "elapsed_time": "0:59:41", "remaining_time": "6:06:08", "throughput": 1501.43, "total_tokens": 5377600} {"current_steps": 25490, "total_steps": 181800, "loss": 0.0723, "lr": 4.975422368741021e-05, "epoch": 2.8041804180418044, "percentage": 14.02, "elapsed_time": "0:59:42", "remaining_time": "6:06:07", "throughput": 1501.44, "total_tokens": 5378688} {"current_steps": 25495, "total_steps": 181800, "loss": 0.0164, "lr": 4.9753887860090254e-05, "epoch": 2.8047304730473046, "percentage": 14.02, "elapsed_time": "0:59:43", "remaining_time": "6:06:06", "throughput": 1501.46, "total_tokens": 5379776} {"current_steps": 25500, "total_steps": 181800, "loss": 0.1216, "lr": 4.9753551804625596e-05, "epoch": 2.8052805280528053, "percentage": 14.03, "elapsed_time": "0:59:43", "remaining_time": "6:06:06", "throughput": 1501.46, "total_tokens": 5380800} {"current_steps": 25505, "total_steps": 181800, "loss": 0.0423, "lr": 4.9753215521019335e-05, "epoch": 2.805830583058306, "percentage": 14.03, "elapsed_time": "0:59:44", "remaining_time": "6:06:05", "throughput": 1501.47, "total_tokens": 5381856} {"current_steps": 25510, "total_steps": 181800, "loss": 0.0982, "lr": 4.975287900927456e-05, "epoch": 2.806380638063806, "percentage": 14.03, "elapsed_time": "0:59:45", "remaining_time": "6:06:04", "throughput": 1501.46, "total_tokens": 5382880} {"current_steps": 25515, "total_steps": 181800, "loss": 0.0691, "lr": 4.9752542269394373e-05, "epoch": 2.806930693069307, "percentage": 14.03, "elapsed_time": "0:59:45", "remaining_time": "6:06:03", "throughput": 1501.48, "total_tokens": 5384000} {"current_steps": 25520, "total_steps": 181800, "loss": 0.0326, "lr": 4.975220530138189e-05, "epoch": 2.8074807480748074, "percentage": 14.04, "elapsed_time": "0:59:46", "remaining_time": "6:06:02", "throughput": 1501.48, "total_tokens": 5385024} {"current_steps": 25525, "total_steps": 181800, "loss": 0.0793, "lr": 4.9751868105240204e-05, "epoch": 2.808030803080308, "percentage": 14.04, "elapsed_time": "0:59:47", "remaining_time": "6:06:02", "throughput": 1501.49, "total_tokens": 5386112} {"current_steps": 25530, "total_steps": 181800, "loss": 0.0846, "lr": 4.9751530680972424e-05, "epoch": 2.8085808580858087, "percentage": 14.04, "elapsed_time": "0:59:47", "remaining_time": "6:06:01", "throughput": 1501.51, "total_tokens": 5387200} {"current_steps": 25535, "total_steps": 181800, "loss": 0.1173, "lr": 4.975119302858166e-05, "epoch": 2.809130913091309, "percentage": 14.05, "elapsed_time": "0:59:48", "remaining_time": "6:06:00", "throughput": 1501.52, "total_tokens": 5388256} {"current_steps": 25540, "total_steps": 181800, "loss": 0.108, "lr": 4.975085514807104e-05, "epoch": 2.8096809680968096, "percentage": 14.05, "elapsed_time": "0:59:49", "remaining_time": "6:05:59", "throughput": 1501.51, "total_tokens": 5389248} {"current_steps": 25545, "total_steps": 181800, "loss": 0.0882, "lr": 4.975051703944366e-05, "epoch": 2.81023102310231, "percentage": 14.05, "elapsed_time": "0:59:49", "remaining_time": "6:05:58", "throughput": 1501.51, "total_tokens": 5390272} {"current_steps": 25550, "total_steps": 181800, "loss": 0.0699, "lr": 4.975017870270263e-05, "epoch": 2.810781078107811, "percentage": 14.05, "elapsed_time": "0:59:50", "remaining_time": "6:05:58", "throughput": 1501.52, "total_tokens": 5391360} {"current_steps": 25555, "total_steps": 181800, "loss": 0.1604, "lr": 4.974984013785109e-05, "epoch": 2.8113311331133115, "percentage": 14.06, "elapsed_time": "0:59:51", "remaining_time": "6:05:57", "throughput": 1501.52, "total_tokens": 5392384} {"current_steps": 25560, "total_steps": 181800, "loss": 0.0394, "lr": 4.974950134489215e-05, "epoch": 2.8118811881188117, "percentage": 14.06, "elapsed_time": "0:59:51", "remaining_time": "6:05:56", "throughput": 1501.51, "total_tokens": 5393376} {"current_steps": 25565, "total_steps": 181800, "loss": 0.0743, "lr": 4.9749162323828926e-05, "epoch": 2.8124312431243124, "percentage": 14.06, "elapsed_time": "0:59:52", "remaining_time": "6:05:55", "throughput": 1501.51, "total_tokens": 5394400} {"current_steps": 25570, "total_steps": 181800, "loss": 0.0336, "lr": 4.9748823074664555e-05, "epoch": 2.812981298129813, "percentage": 14.06, "elapsed_time": "0:59:53", "remaining_time": "6:05:54", "throughput": 1501.5, "total_tokens": 5395424} {"current_steps": 25575, "total_steps": 181800, "loss": 0.0873, "lr": 4.974848359740215e-05, "epoch": 2.8135313531353137, "percentage": 14.07, "elapsed_time": "0:59:54", "remaining_time": "6:05:54", "throughput": 1501.49, "total_tokens": 5396416} {"current_steps": 25580, "total_steps": 181800, "loss": 0.0459, "lr": 4.974814389204485e-05, "epoch": 2.8140814081408143, "percentage": 14.07, "elapsed_time": "0:59:54", "remaining_time": "6:05:53", "throughput": 1501.52, "total_tokens": 5397536} {"current_steps": 25585, "total_steps": 181800, "loss": 0.1255, "lr": 4.9747803958595785e-05, "epoch": 2.8146314631463145, "percentage": 14.07, "elapsed_time": "0:59:55", "remaining_time": "6:05:52", "throughput": 1501.53, "total_tokens": 5398592} {"current_steps": 25590, "total_steps": 181800, "loss": 0.0742, "lr": 4.974746379705809e-05, "epoch": 2.815181518151815, "percentage": 14.08, "elapsed_time": "0:59:56", "remaining_time": "6:05:51", "throughput": 1501.52, "total_tokens": 5399616} {"current_steps": 25595, "total_steps": 181800, "loss": 0.2232, "lr": 4.974712340743489e-05, "epoch": 2.815731573157316, "percentage": 14.08, "elapsed_time": "0:59:56", "remaining_time": "6:05:50", "throughput": 1501.53, "total_tokens": 5400672} {"current_steps": 25600, "total_steps": 181800, "loss": 0.0442, "lr": 4.974678278972933e-05, "epoch": 2.816281628162816, "percentage": 14.08, "elapsed_time": "0:59:57", "remaining_time": "6:05:50", "throughput": 1501.51, "total_tokens": 5401632} {"current_steps": 25605, "total_steps": 181800, "loss": 0.0648, "lr": 4.974644194394454e-05, "epoch": 2.8168316831683167, "percentage": 14.08, "elapsed_time": "0:59:58", "remaining_time": "6:05:49", "throughput": 1501.51, "total_tokens": 5402688} {"current_steps": 25610, "total_steps": 181800, "loss": 0.0183, "lr": 4.9746100870083676e-05, "epoch": 2.8173817381738173, "percentage": 14.09, "elapsed_time": "0:59:58", "remaining_time": "6:05:48", "throughput": 1501.51, "total_tokens": 5403712} {"current_steps": 25615, "total_steps": 181800, "loss": 0.0438, "lr": 4.974575956814988e-05, "epoch": 2.817931793179318, "percentage": 14.09, "elapsed_time": "0:59:59", "remaining_time": "6:05:47", "throughput": 1501.52, "total_tokens": 5404768} {"current_steps": 25620, "total_steps": 181800, "loss": 0.0898, "lr": 4.974541803814629e-05, "epoch": 2.8184818481848186, "percentage": 14.09, "elapsed_time": "1:00:00", "remaining_time": "6:05:47", "throughput": 1501.51, "total_tokens": 5405792} {"current_steps": 25625, "total_steps": 181800, "loss": 0.0387, "lr": 4.974507628007605e-05, "epoch": 2.819031903190319, "percentage": 14.1, "elapsed_time": "1:00:00", "remaining_time": "6:05:46", "throughput": 1501.52, "total_tokens": 5406848} {"current_steps": 25630, "total_steps": 181800, "loss": 0.0718, "lr": 4.974473429394232e-05, "epoch": 2.8195819581958195, "percentage": 14.1, "elapsed_time": "1:00:01", "remaining_time": "6:05:45", "throughput": 1501.53, "total_tokens": 5407936} {"current_steps": 25635, "total_steps": 181800, "loss": 0.0398, "lr": 4.974439207974825e-05, "epoch": 2.82013201320132, "percentage": 14.1, "elapsed_time": "1:00:02", "remaining_time": "6:05:44", "throughput": 1501.55, "total_tokens": 5409024} {"current_steps": 25640, "total_steps": 181800, "loss": 0.0991, "lr": 4.9744049637496984e-05, "epoch": 2.8206820682068208, "percentage": 14.1, "elapsed_time": "1:00:02", "remaining_time": "6:05:43", "throughput": 1501.54, "total_tokens": 5410048} {"current_steps": 25645, "total_steps": 181800, "loss": 0.0678, "lr": 4.974370696719169e-05, "epoch": 2.8212321232123214, "percentage": 14.11, "elapsed_time": "1:00:03", "remaining_time": "6:05:43", "throughput": 1501.54, "total_tokens": 5411072} {"current_steps": 25650, "total_steps": 181800, "loss": 0.1935, "lr": 4.974336406883552e-05, "epoch": 2.8217821782178216, "percentage": 14.11, "elapsed_time": "1:00:04", "remaining_time": "6:05:42", "throughput": 1501.53, "total_tokens": 5412064} {"current_steps": 25655, "total_steps": 181800, "loss": 0.0332, "lr": 4.974302094243164e-05, "epoch": 2.8223322332233223, "percentage": 14.11, "elapsed_time": "1:00:05", "remaining_time": "6:05:41", "throughput": 1501.52, "total_tokens": 5413056} {"current_steps": 25660, "total_steps": 181800, "loss": 0.0608, "lr": 4.9742677587983205e-05, "epoch": 2.822882288228823, "percentage": 14.11, "elapsed_time": "1:00:05", "remaining_time": "6:05:40", "throughput": 1501.55, "total_tokens": 5414208} {"current_steps": 25665, "total_steps": 181800, "loss": 0.1347, "lr": 4.974233400549339e-05, "epoch": 2.8234323432343236, "percentage": 14.12, "elapsed_time": "1:00:06", "remaining_time": "6:05:40", "throughput": 1501.56, "total_tokens": 5415296} {"current_steps": 25670, "total_steps": 181800, "loss": 0.1426, "lr": 4.9741990194965346e-05, "epoch": 2.823982398239824, "percentage": 14.12, "elapsed_time": "1:00:07", "remaining_time": "6:05:39", "throughput": 1501.57, "total_tokens": 5416352} {"current_steps": 25675, "total_steps": 181800, "loss": 0.0591, "lr": 4.974164615640225e-05, "epoch": 2.8245324532453244, "percentage": 14.12, "elapsed_time": "1:00:07", "remaining_time": "6:05:38", "throughput": 1501.58, "total_tokens": 5417408} {"current_steps": 25680, "total_steps": 181800, "loss": 0.1007, "lr": 4.974130188980729e-05, "epoch": 2.825082508250825, "percentage": 14.13, "elapsed_time": "1:00:08", "remaining_time": "6:05:37", "throughput": 1501.59, "total_tokens": 5418496} {"current_steps": 25685, "total_steps": 181800, "loss": 0.013, "lr": 4.974095739518361e-05, "epoch": 2.8256325632563257, "percentage": 14.13, "elapsed_time": "1:00:09", "remaining_time": "6:05:36", "throughput": 1501.59, "total_tokens": 5419520} {"current_steps": 25690, "total_steps": 181800, "loss": 0.1244, "lr": 4.97406126725344e-05, "epoch": 2.826182618261826, "percentage": 14.13, "elapsed_time": "1:00:09", "remaining_time": "6:05:36", "throughput": 1501.59, "total_tokens": 5420576} {"current_steps": 25695, "total_steps": 181800, "loss": 0.0694, "lr": 4.9740267721862835e-05, "epoch": 2.8267326732673266, "percentage": 14.13, "elapsed_time": "1:00:10", "remaining_time": "6:05:35", "throughput": 1501.6, "total_tokens": 5421632} {"current_steps": 25700, "total_steps": 181800, "loss": 0.1158, "lr": 4.973992254317209e-05, "epoch": 2.8272827282728272, "percentage": 14.14, "elapsed_time": "1:00:11", "remaining_time": "6:05:34", "throughput": 1501.61, "total_tokens": 5422688} {"current_steps": 25705, "total_steps": 181800, "loss": 0.0169, "lr": 4.9739577136465354e-05, "epoch": 2.827832783278328, "percentage": 14.14, "elapsed_time": "1:00:11", "remaining_time": "6:05:33", "throughput": 1501.63, "total_tokens": 5423808} {"current_steps": 25710, "total_steps": 181800, "loss": 0.0365, "lr": 4.9739231501745805e-05, "epoch": 2.8283828382838285, "percentage": 14.14, "elapsed_time": "1:00:12", "remaining_time": "6:05:32", "throughput": 1501.63, "total_tokens": 5424832} {"current_steps": 25715, "total_steps": 181800, "loss": 0.097, "lr": 4.973888563901663e-05, "epoch": 2.8289328932893287, "percentage": 14.14, "elapsed_time": "1:00:13", "remaining_time": "6:05:32", "throughput": 1501.63, "total_tokens": 5425856} {"current_steps": 25720, "total_steps": 181800, "loss": 0.0537, "lr": 4.9738539548281017e-05, "epoch": 2.8294829482948294, "percentage": 14.15, "elapsed_time": "1:00:14", "remaining_time": "6:05:31", "throughput": 1501.63, "total_tokens": 5426912} {"current_steps": 25725, "total_steps": 181800, "loss": 0.0179, "lr": 4.973819322954216e-05, "epoch": 2.83003300330033, "percentage": 14.15, "elapsed_time": "1:00:14", "remaining_time": "6:05:30", "throughput": 1501.65, "total_tokens": 5428000} {"current_steps": 25730, "total_steps": 181800, "loss": 0.0978, "lr": 4.973784668280324e-05, "epoch": 2.8305830583058307, "percentage": 14.15, "elapsed_time": "1:00:15", "remaining_time": "6:05:29", "throughput": 1501.63, "total_tokens": 5428992} {"current_steps": 25735, "total_steps": 181800, "loss": 0.0682, "lr": 4.9737499908067465e-05, "epoch": 2.8311331133113313, "percentage": 14.16, "elapsed_time": "1:00:16", "remaining_time": "6:05:29", "throughput": 1501.64, "total_tokens": 5430048} {"current_steps": 25740, "total_steps": 181800, "loss": 0.0324, "lr": 4.973715290533801e-05, "epoch": 2.8316831683168315, "percentage": 14.16, "elapsed_time": "1:00:16", "remaining_time": "6:05:28", "throughput": 1501.65, "total_tokens": 5431136} {"current_steps": 25745, "total_steps": 181800, "loss": 0.0824, "lr": 4.9736805674618105e-05, "epoch": 2.832233223322332, "percentage": 14.16, "elapsed_time": "1:00:17", "remaining_time": "6:05:27", "throughput": 1501.66, "total_tokens": 5432192} {"current_steps": 25750, "total_steps": 181800, "loss": 0.1087, "lr": 4.973645821591092e-05, "epoch": 2.832783278327833, "percentage": 14.16, "elapsed_time": "1:00:18", "remaining_time": "6:05:26", "throughput": 1501.66, "total_tokens": 5433248} {"current_steps": 25755, "total_steps": 181800, "loss": 0.0646, "lr": 4.9736110529219674e-05, "epoch": 2.8333333333333335, "percentage": 14.17, "elapsed_time": "1:00:18", "remaining_time": "6:05:25", "throughput": 1501.67, "total_tokens": 5434304} {"current_steps": 25760, "total_steps": 181800, "loss": 0.063, "lr": 4.9735762614547565e-05, "epoch": 2.833883388338834, "percentage": 14.17, "elapsed_time": "1:00:19", "remaining_time": "6:05:25", "throughput": 1501.68, "total_tokens": 5435360} {"current_steps": 25765, "total_steps": 181800, "loss": 0.0925, "lr": 4.97354144718978e-05, "epoch": 2.8344334433443343, "percentage": 14.17, "elapsed_time": "1:00:20", "remaining_time": "6:05:24", "throughput": 1501.68, "total_tokens": 5436416} {"current_steps": 25770, "total_steps": 181800, "loss": 0.1701, "lr": 4.973506610127359e-05, "epoch": 2.834983498349835, "percentage": 14.17, "elapsed_time": "1:00:20", "remaining_time": "6:05:23", "throughput": 1501.67, "total_tokens": 5437408} {"current_steps": 25775, "total_steps": 181800, "loss": 0.1338, "lr": 4.973471750267814e-05, "epoch": 2.8355335533553356, "percentage": 14.18, "elapsed_time": "1:00:21", "remaining_time": "6:05:22", "throughput": 1501.68, "total_tokens": 5438496} {"current_steps": 25780, "total_steps": 181800, "loss": 0.1044, "lr": 4.973436867611467e-05, "epoch": 2.836083608360836, "percentage": 14.18, "elapsed_time": "1:00:22", "remaining_time": "6:05:21", "throughput": 1501.67, "total_tokens": 5439488} {"current_steps": 25785, "total_steps": 181800, "loss": 0.1273, "lr": 4.97340196215864e-05, "epoch": 2.8366336633663365, "percentage": 14.18, "elapsed_time": "1:00:22", "remaining_time": "6:05:21", "throughput": 1501.67, "total_tokens": 5440512} {"current_steps": 25790, "total_steps": 181800, "loss": 0.0401, "lr": 4.973367033909654e-05, "epoch": 2.837183718371837, "percentage": 14.19, "elapsed_time": "1:00:23", "remaining_time": "6:05:20", "throughput": 1501.67, "total_tokens": 5441536} {"current_steps": 25795, "total_steps": 181800, "loss": 0.0322, "lr": 4.97333208286483e-05, "epoch": 2.837733773377338, "percentage": 14.19, "elapsed_time": "1:00:24", "remaining_time": "6:05:19", "throughput": 1501.66, "total_tokens": 5442560} {"current_steps": 25800, "total_steps": 181800, "loss": 0.2041, "lr": 4.973297109024492e-05, "epoch": 2.8382838283828384, "percentage": 14.19, "elapsed_time": "1:00:25", "remaining_time": "6:05:18", "throughput": 1501.67, "total_tokens": 5443616} {"current_steps": 25805, "total_steps": 181800, "loss": 0.0909, "lr": 4.97326211238896e-05, "epoch": 2.8388338833883386, "percentage": 14.19, "elapsed_time": "1:00:25", "remaining_time": "6:05:18", "throughput": 1501.67, "total_tokens": 5444672} {"current_steps": 25810, "total_steps": 181800, "loss": 0.083, "lr": 4.973227092958559e-05, "epoch": 2.8393839383938393, "percentage": 14.2, "elapsed_time": "1:00:26", "remaining_time": "6:05:17", "throughput": 1501.7, "total_tokens": 5445792} {"current_steps": 25815, "total_steps": 181800, "loss": 0.0259, "lr": 4.97319205073361e-05, "epoch": 2.83993399339934, "percentage": 14.2, "elapsed_time": "1:00:27", "remaining_time": "6:05:16", "throughput": 1501.71, "total_tokens": 5446880} {"current_steps": 25820, "total_steps": 181800, "loss": 0.0633, "lr": 4.973156985714437e-05, "epoch": 2.8404840484048406, "percentage": 14.2, "elapsed_time": "1:00:27", "remaining_time": "6:05:15", "throughput": 1501.72, "total_tokens": 5447936} {"current_steps": 25825, "total_steps": 181800, "loss": 0.1331, "lr": 4.973121897901363e-05, "epoch": 2.8410341034103412, "percentage": 14.21, "elapsed_time": "1:00:28", "remaining_time": "6:05:14", "throughput": 1501.72, "total_tokens": 5448960} {"current_steps": 25830, "total_steps": 181800, "loss": 0.0232, "lr": 4.9730867872947105e-05, "epoch": 2.8415841584158414, "percentage": 14.21, "elapsed_time": "1:00:29", "remaining_time": "6:05:14", "throughput": 1501.72, "total_tokens": 5450016} {"current_steps": 25835, "total_steps": 181800, "loss": 0.0685, "lr": 4.973051653894805e-05, "epoch": 2.842134213421342, "percentage": 14.21, "elapsed_time": "1:00:29", "remaining_time": "6:05:13", "throughput": 1501.74, "total_tokens": 5451104} {"current_steps": 25840, "total_steps": 181800, "loss": 0.0274, "lr": 4.9730164977019676e-05, "epoch": 2.8426842684268427, "percentage": 14.21, "elapsed_time": "1:00:30", "remaining_time": "6:05:12", "throughput": 1501.75, "total_tokens": 5452192} {"current_steps": 25845, "total_steps": 181800, "loss": 0.0839, "lr": 4.972981318716525e-05, "epoch": 2.8432343234323434, "percentage": 14.22, "elapsed_time": "1:00:31", "remaining_time": "6:05:11", "throughput": 1501.75, "total_tokens": 5453216} {"current_steps": 25850, "total_steps": 181800, "loss": 0.0529, "lr": 4.9729461169387994e-05, "epoch": 2.843784378437844, "percentage": 14.22, "elapsed_time": "1:00:31", "remaining_time": "6:05:11", "throughput": 1501.75, "total_tokens": 5454240} {"current_steps": 25855, "total_steps": 181800, "loss": 0.0358, "lr": 4.9729108923691164e-05, "epoch": 2.8443344334433442, "percentage": 14.22, "elapsed_time": "1:00:32", "remaining_time": "6:05:10", "throughput": 1501.75, "total_tokens": 5455296} {"current_steps": 25860, "total_steps": 181800, "loss": 0.0376, "lr": 4.972875645007801e-05, "epoch": 2.844884488448845, "percentage": 14.22, "elapsed_time": "1:00:33", "remaining_time": "6:05:09", "throughput": 1501.76, "total_tokens": 5456352} {"current_steps": 25865, "total_steps": 181800, "loss": 0.1321, "lr": 4.972840374855176e-05, "epoch": 2.8454345434543455, "percentage": 14.23, "elapsed_time": "1:00:33", "remaining_time": "6:05:08", "throughput": 1501.78, "total_tokens": 5457472} {"current_steps": 25870, "total_steps": 181800, "loss": 0.0711, "lr": 4.972805081911569e-05, "epoch": 2.8459845984598457, "percentage": 14.23, "elapsed_time": "1:00:34", "remaining_time": "6:05:07", "throughput": 1501.78, "total_tokens": 5458496} {"current_steps": 25875, "total_steps": 181800, "loss": 0.0533, "lr": 4.972769766177303e-05, "epoch": 2.8465346534653464, "percentage": 14.23, "elapsed_time": "1:00:35", "remaining_time": "6:05:07", "throughput": 1501.78, "total_tokens": 5459520} {"current_steps": 25880, "total_steps": 181800, "loss": 0.0437, "lr": 4.972734427652705e-05, "epoch": 2.847084708470847, "percentage": 14.24, "elapsed_time": "1:00:36", "remaining_time": "6:05:06", "throughput": 1501.79, "total_tokens": 5460608} {"current_steps": 25885, "total_steps": 181800, "loss": 0.055, "lr": 4.972699066338101e-05, "epoch": 2.8476347634763477, "percentage": 14.24, "elapsed_time": "1:00:36", "remaining_time": "6:05:05", "throughput": 1501.81, "total_tokens": 5461728} {"current_steps": 25890, "total_steps": 181800, "loss": 0.0548, "lr": 4.972663682233816e-05, "epoch": 2.8481848184818483, "percentage": 14.24, "elapsed_time": "1:00:37", "remaining_time": "6:05:04", "throughput": 1501.8, "total_tokens": 5462720} {"current_steps": 25895, "total_steps": 181800, "loss": 0.0747, "lr": 4.9726282753401765e-05, "epoch": 2.8487348734873486, "percentage": 14.24, "elapsed_time": "1:00:38", "remaining_time": "6:05:03", "throughput": 1501.82, "total_tokens": 5463808} {"current_steps": 25900, "total_steps": 181800, "loss": 0.1654, "lr": 4.972592845657508e-05, "epoch": 2.849284928492849, "percentage": 14.25, "elapsed_time": "1:00:38", "remaining_time": "6:05:03", "throughput": 1501.82, "total_tokens": 5464832} {"current_steps": 25905, "total_steps": 181800, "loss": 0.1678, "lr": 4.972557393186138e-05, "epoch": 2.84983498349835, "percentage": 14.25, "elapsed_time": "1:00:39", "remaining_time": "6:05:02", "throughput": 1501.82, "total_tokens": 5465888} {"current_steps": 25910, "total_steps": 181800, "loss": 0.1218, "lr": 4.972521917926394e-05, "epoch": 2.8503850385038505, "percentage": 14.25, "elapsed_time": "1:00:40", "remaining_time": "6:05:01", "throughput": 1501.82, "total_tokens": 5466912} {"current_steps": 25915, "total_steps": 181800, "loss": 0.0574, "lr": 4.9724864198786006e-05, "epoch": 2.850935093509351, "percentage": 14.25, "elapsed_time": "1:00:40", "remaining_time": "6:05:00", "throughput": 1501.81, "total_tokens": 5467904} {"current_steps": 25920, "total_steps": 181800, "loss": 0.0764, "lr": 4.9724508990430865e-05, "epoch": 2.8514851485148514, "percentage": 14.26, "elapsed_time": "1:00:41", "remaining_time": "6:05:00", "throughput": 1501.8, "total_tokens": 5468928} {"current_steps": 25925, "total_steps": 181800, "loss": 0.0942, "lr": 4.972415355420179e-05, "epoch": 2.852035203520352, "percentage": 14.26, "elapsed_time": "1:00:42", "remaining_time": "6:04:59", "throughput": 1501.8, "total_tokens": 5469952} {"current_steps": 25930, "total_steps": 181800, "loss": 0.1048, "lr": 4.972379789010205e-05, "epoch": 2.8525852585258527, "percentage": 14.26, "elapsed_time": "1:00:42", "remaining_time": "6:04:58", "throughput": 1501.81, "total_tokens": 5471008} {"current_steps": 25935, "total_steps": 181800, "loss": 0.094, "lr": 4.9723441998134936e-05, "epoch": 2.8531353135313533, "percentage": 14.27, "elapsed_time": "1:00:43", "remaining_time": "6:04:57", "throughput": 1501.82, "total_tokens": 5472096} {"current_steps": 25940, "total_steps": 181800, "loss": 0.0879, "lr": 4.972308587830372e-05, "epoch": 2.853685368536854, "percentage": 14.27, "elapsed_time": "1:00:44", "remaining_time": "6:04:56", "throughput": 1501.83, "total_tokens": 5473152} {"current_steps": 25945, "total_steps": 181800, "loss": 0.0614, "lr": 4.9722729530611684e-05, "epoch": 2.854235423542354, "percentage": 14.27, "elapsed_time": "1:00:45", "remaining_time": "6:04:56", "throughput": 1501.84, "total_tokens": 5474240} {"current_steps": 25950, "total_steps": 181800, "loss": 0.0587, "lr": 4.972237295506211e-05, "epoch": 2.854785478547855, "percentage": 14.27, "elapsed_time": "1:00:45", "remaining_time": "6:04:55", "throughput": 1501.87, "total_tokens": 5475360} {"current_steps": 25955, "total_steps": 181800, "loss": 0.0417, "lr": 4.972201615165829e-05, "epoch": 2.8553355335533555, "percentage": 14.28, "elapsed_time": "1:00:46", "remaining_time": "6:04:54", "throughput": 1501.88, "total_tokens": 5476416} {"current_steps": 25960, "total_steps": 181800, "loss": 0.0277, "lr": 4.972165912040351e-05, "epoch": 2.8558855885588557, "percentage": 14.28, "elapsed_time": "1:00:47", "remaining_time": "6:04:53", "throughput": 1501.88, "total_tokens": 5477472} {"current_steps": 25965, "total_steps": 181800, "loss": 0.0287, "lr": 4.972130186130106e-05, "epoch": 2.8564356435643563, "percentage": 14.28, "elapsed_time": "1:00:47", "remaining_time": "6:04:52", "throughput": 1501.91, "total_tokens": 5478592} {"current_steps": 25970, "total_steps": 181800, "loss": 0.0479, "lr": 4.9720944374354235e-05, "epoch": 2.856985698569857, "percentage": 14.28, "elapsed_time": "1:00:48", "remaining_time": "6:04:52", "throughput": 1501.92, "total_tokens": 5479680} {"current_steps": 25975, "total_steps": 181800, "loss": 0.0272, "lr": 4.972058665956633e-05, "epoch": 2.8575357535753576, "percentage": 14.29, "elapsed_time": "1:00:49", "remaining_time": "6:04:51", "throughput": 1501.92, "total_tokens": 5480736} {"current_steps": 25980, "total_steps": 181800, "loss": 0.0957, "lr": 4.972022871694063e-05, "epoch": 2.8580858085808583, "percentage": 14.29, "elapsed_time": "1:00:49", "remaining_time": "6:04:50", "throughput": 1501.92, "total_tokens": 5481760} {"current_steps": 25985, "total_steps": 181800, "loss": 0.0642, "lr": 4.971987054648045e-05, "epoch": 2.8586358635863585, "percentage": 14.29, "elapsed_time": "1:00:50", "remaining_time": "6:04:49", "throughput": 1501.92, "total_tokens": 5482784} {"current_steps": 25990, "total_steps": 181800, "loss": 0.0953, "lr": 4.971951214818908e-05, "epoch": 2.859185918591859, "percentage": 14.3, "elapsed_time": "1:00:51", "remaining_time": "6:04:48", "throughput": 1501.93, "total_tokens": 5483872} {"current_steps": 25995, "total_steps": 181800, "loss": 0.0855, "lr": 4.9719153522069836e-05, "epoch": 2.8597359735973598, "percentage": 14.3, "elapsed_time": "1:00:51", "remaining_time": "6:04:48", "throughput": 1501.95, "total_tokens": 5484960} {"current_steps": 26000, "total_steps": 181800, "loss": 0.0302, "lr": 4.9718794668126015e-05, "epoch": 2.8602860286028604, "percentage": 14.3, "elapsed_time": "1:00:52", "remaining_time": "6:04:47", "throughput": 1501.96, "total_tokens": 5486016} {"current_steps": 26005, "total_steps": 181800, "loss": 0.0645, "lr": 4.971843558636092e-05, "epoch": 2.860836083608361, "percentage": 14.3, "elapsed_time": "1:00:53", "remaining_time": "6:04:46", "throughput": 1501.96, "total_tokens": 5487072} {"current_steps": 26010, "total_steps": 181800, "loss": 0.0852, "lr": 4.971807627677787e-05, "epoch": 2.8613861386138613, "percentage": 14.31, "elapsed_time": "1:00:53", "remaining_time": "6:04:45", "throughput": 1501.99, "total_tokens": 5488192} {"current_steps": 26015, "total_steps": 181800, "loss": 0.0728, "lr": 4.9717716739380166e-05, "epoch": 2.861936193619362, "percentage": 14.31, "elapsed_time": "1:00:54", "remaining_time": "6:04:45", "throughput": 1501.99, "total_tokens": 5489248} {"current_steps": 26020, "total_steps": 181800, "loss": 0.0504, "lr": 4.971735697417113e-05, "epoch": 2.8624862486248626, "percentage": 14.31, "elapsed_time": "1:00:55", "remaining_time": "6:04:44", "throughput": 1502.0, "total_tokens": 5490304} {"current_steps": 26025, "total_steps": 181800, "loss": 0.1129, "lr": 4.9716996981154076e-05, "epoch": 2.8630363036303628, "percentage": 14.32, "elapsed_time": "1:00:56", "remaining_time": "6:04:43", "throughput": 1502.0, "total_tokens": 5491360} {"current_steps": 26030, "total_steps": 181800, "loss": 0.0546, "lr": 4.9716636760332325e-05, "epoch": 2.863586358635864, "percentage": 14.32, "elapsed_time": "1:00:56", "remaining_time": "6:04:42", "throughput": 1502.01, "total_tokens": 5492416} {"current_steps": 26035, "total_steps": 181800, "loss": 0.0985, "lr": 4.9716276311709186e-05, "epoch": 2.864136413641364, "percentage": 14.32, "elapsed_time": "1:00:57", "remaining_time": "6:04:41", "throughput": 1502.02, "total_tokens": 5493504} {"current_steps": 26040, "total_steps": 181800, "loss": 0.0389, "lr": 4.971591563528799e-05, "epoch": 2.8646864686468647, "percentage": 14.32, "elapsed_time": "1:00:58", "remaining_time": "6:04:41", "throughput": 1502.03, "total_tokens": 5494560} {"current_steps": 26045, "total_steps": 181800, "loss": 0.0389, "lr": 4.971555473107206e-05, "epoch": 2.8652365236523654, "percentage": 14.33, "elapsed_time": "1:00:58", "remaining_time": "6:04:40", "throughput": 1502.03, "total_tokens": 5495584} {"current_steps": 26050, "total_steps": 181800, "loss": 0.0913, "lr": 4.9715193599064725e-05, "epoch": 2.8657865786578656, "percentage": 14.33, "elapsed_time": "1:00:59", "remaining_time": "6:04:39", "throughput": 1502.02, "total_tokens": 5496608} {"current_steps": 26055, "total_steps": 181800, "loss": 0.0306, "lr": 4.9714832239269306e-05, "epoch": 2.866336633663366, "percentage": 14.33, "elapsed_time": "1:01:00", "remaining_time": "6:04:38", "throughput": 1502.02, "total_tokens": 5497632} {"current_steps": 26060, "total_steps": 181800, "loss": 0.0156, "lr": 4.9714470651689136e-05, "epoch": 2.866886688668867, "percentage": 14.33, "elapsed_time": "1:01:00", "remaining_time": "6:04:37", "throughput": 1502.01, "total_tokens": 5498624} {"current_steps": 26065, "total_steps": 181800, "loss": 0.1553, "lr": 4.9714108836327556e-05, "epoch": 2.8674367436743675, "percentage": 14.34, "elapsed_time": "1:01:01", "remaining_time": "6:04:37", "throughput": 1501.99, "total_tokens": 5499584} {"current_steps": 26070, "total_steps": 181800, "loss": 0.0561, "lr": 4.971374679318789e-05, "epoch": 2.867986798679868, "percentage": 14.34, "elapsed_time": "1:01:02", "remaining_time": "6:04:36", "throughput": 1502.01, "total_tokens": 5500704} {"current_steps": 26075, "total_steps": 181800, "loss": 0.0585, "lr": 4.971338452227348e-05, "epoch": 2.8685368536853684, "percentage": 14.34, "elapsed_time": "1:01:02", "remaining_time": "6:04:35", "throughput": 1502.04, "total_tokens": 5501856} {"current_steps": 26080, "total_steps": 181800, "loss": 0.0699, "lr": 4.971302202358766e-05, "epoch": 2.869086908690869, "percentage": 14.35, "elapsed_time": "1:01:03", "remaining_time": "6:04:34", "throughput": 1502.04, "total_tokens": 5502880} {"current_steps": 26085, "total_steps": 181800, "loss": 0.0592, "lr": 4.971265929713378e-05, "epoch": 2.8696369636963697, "percentage": 14.35, "elapsed_time": "1:01:04", "remaining_time": "6:04:34", "throughput": 1502.04, "total_tokens": 5503936} {"current_steps": 26090, "total_steps": 181800, "loss": 0.0647, "lr": 4.9712296342915174e-05, "epoch": 2.8701870187018703, "percentage": 14.35, "elapsed_time": "1:01:04", "remaining_time": "6:04:33", "throughput": 1502.05, "total_tokens": 5504992} {"current_steps": 26095, "total_steps": 181800, "loss": 0.0355, "lr": 4.9711933160935194e-05, "epoch": 2.870737073707371, "percentage": 14.35, "elapsed_time": "1:01:05", "remaining_time": "6:04:32", "throughput": 1502.06, "total_tokens": 5506080} {"current_steps": 26100, "total_steps": 181800, "loss": 0.0771, "lr": 4.971156975119718e-05, "epoch": 2.871287128712871, "percentage": 14.36, "elapsed_time": "1:01:06", "remaining_time": "6:04:31", "throughput": 1502.07, "total_tokens": 5507168} {"current_steps": 26105, "total_steps": 181800, "loss": 0.1192, "lr": 4.971120611370449e-05, "epoch": 2.871837183718372, "percentage": 14.36, "elapsed_time": "1:01:07", "remaining_time": "6:04:31", "throughput": 1502.08, "total_tokens": 5508224} {"current_steps": 26110, "total_steps": 181800, "loss": 0.0434, "lr": 4.9710842248460466e-05, "epoch": 2.8723872387238725, "percentage": 14.36, "elapsed_time": "1:01:07", "remaining_time": "6:04:30", "throughput": 1502.07, "total_tokens": 5509248} {"current_steps": 26115, "total_steps": 181800, "loss": 0.0744, "lr": 4.9710478155468463e-05, "epoch": 2.8729372937293727, "percentage": 14.36, "elapsed_time": "1:01:08", "remaining_time": "6:04:29", "throughput": 1502.08, "total_tokens": 5510304} {"current_steps": 26120, "total_steps": 181800, "loss": 0.1002, "lr": 4.9710113834731846e-05, "epoch": 2.8734873487348733, "percentage": 14.37, "elapsed_time": "1:01:09", "remaining_time": "6:04:28", "throughput": 1502.07, "total_tokens": 5511296} {"current_steps": 26125, "total_steps": 181800, "loss": 0.0717, "lr": 4.970974928625397e-05, "epoch": 2.874037403740374, "percentage": 14.37, "elapsed_time": "1:01:09", "remaining_time": "6:04:27", "throughput": 1502.07, "total_tokens": 5512352} {"current_steps": 26130, "total_steps": 181800, "loss": 0.0732, "lr": 4.9709384510038184e-05, "epoch": 2.8745874587458746, "percentage": 14.37, "elapsed_time": "1:01:10", "remaining_time": "6:04:27", "throughput": 1502.08, "total_tokens": 5513408} {"current_steps": 26135, "total_steps": 181800, "loss": 0.1355, "lr": 4.970901950608786e-05, "epoch": 2.8751375137513753, "percentage": 14.38, "elapsed_time": "1:01:11", "remaining_time": "6:04:26", "throughput": 1502.08, "total_tokens": 5514464} {"current_steps": 26140, "total_steps": 181800, "loss": 0.0646, "lr": 4.970865427440636e-05, "epoch": 2.8756875687568755, "percentage": 14.38, "elapsed_time": "1:01:11", "remaining_time": "6:04:25", "throughput": 1502.08, "total_tokens": 5515520} {"current_steps": 26145, "total_steps": 181800, "loss": 0.0471, "lr": 4.970828881499705e-05, "epoch": 2.876237623762376, "percentage": 14.38, "elapsed_time": "1:01:12", "remaining_time": "6:04:24", "throughput": 1502.1, "total_tokens": 5516608} {"current_steps": 26150, "total_steps": 181800, "loss": 0.0872, "lr": 4.97079231278633e-05, "epoch": 2.8767876787678768, "percentage": 14.38, "elapsed_time": "1:01:13", "remaining_time": "6:04:24", "throughput": 1502.11, "total_tokens": 5517696} {"current_steps": 26155, "total_steps": 181800, "loss": 0.0379, "lr": 4.9707557213008485e-05, "epoch": 2.8773377337733774, "percentage": 14.39, "elapsed_time": "1:01:13", "remaining_time": "6:04:23", "throughput": 1502.12, "total_tokens": 5518752} {"current_steps": 26160, "total_steps": 181800, "loss": 0.134, "lr": 4.970719107043595e-05, "epoch": 2.877887788778878, "percentage": 14.39, "elapsed_time": "1:01:14", "remaining_time": "6:04:22", "throughput": 1502.11, "total_tokens": 5519776} {"current_steps": 26165, "total_steps": 181800, "loss": 0.0674, "lr": 4.9706824700149115e-05, "epoch": 2.8784378437843783, "percentage": 14.39, "elapsed_time": "1:01:15", "remaining_time": "6:04:21", "throughput": 1502.12, "total_tokens": 5520832} {"current_steps": 26170, "total_steps": 181800, "loss": 0.0311, "lr": 4.970645810215132e-05, "epoch": 2.878987898789879, "percentage": 14.39, "elapsed_time": "1:01:16", "remaining_time": "6:04:21", "throughput": 1502.12, "total_tokens": 5521888} {"current_steps": 26175, "total_steps": 181800, "loss": 0.095, "lr": 4.970609127644596e-05, "epoch": 2.8795379537953796, "percentage": 14.4, "elapsed_time": "1:01:16", "remaining_time": "6:04:20", "throughput": 1502.12, "total_tokens": 5522912} {"current_steps": 26180, "total_steps": 181800, "loss": 0.0436, "lr": 4.9705724223036406e-05, "epoch": 2.8800880088008802, "percentage": 14.4, "elapsed_time": "1:01:17", "remaining_time": "6:04:19", "throughput": 1502.1, "total_tokens": 5523904} {"current_steps": 26185, "total_steps": 181800, "loss": 0.0342, "lr": 4.970535694192605e-05, "epoch": 2.880638063806381, "percentage": 14.4, "elapsed_time": "1:01:18", "remaining_time": "6:04:18", "throughput": 1502.11, "total_tokens": 5524960} {"current_steps": 26190, "total_steps": 181800, "loss": 0.0193, "lr": 4.970498943311827e-05, "epoch": 2.881188118811881, "percentage": 14.41, "elapsed_time": "1:01:18", "remaining_time": "6:04:18", "throughput": 1502.11, "total_tokens": 5525984} {"current_steps": 26195, "total_steps": 181800, "loss": 0.0405, "lr": 4.970462169661646e-05, "epoch": 2.8817381738173817, "percentage": 14.41, "elapsed_time": "1:01:19", "remaining_time": "6:04:17", "throughput": 1502.12, "total_tokens": 5527072} {"current_steps": 26200, "total_steps": 181800, "loss": 0.0234, "lr": 4.970425373242401e-05, "epoch": 2.8822882288228824, "percentage": 14.41, "elapsed_time": "1:01:20", "remaining_time": "6:04:16", "throughput": 1502.11, "total_tokens": 5528064} {"current_steps": 26205, "total_steps": 181800, "loss": 0.0372, "lr": 4.97038855405443e-05, "epoch": 2.8828382838283826, "percentage": 14.41, "elapsed_time": "1:01:20", "remaining_time": "6:04:15", "throughput": 1502.11, "total_tokens": 5529120} {"current_steps": 26210, "total_steps": 181800, "loss": 0.045, "lr": 4.970351712098074e-05, "epoch": 2.8833883388338832, "percentage": 14.42, "elapsed_time": "1:01:21", "remaining_time": "6:04:14", "throughput": 1502.12, "total_tokens": 5530208} {"current_steps": 26215, "total_steps": 181800, "loss": 0.0412, "lr": 4.970314847373672e-05, "epoch": 2.883938393839384, "percentage": 14.42, "elapsed_time": "1:01:22", "remaining_time": "6:04:14", "throughput": 1502.12, "total_tokens": 5531232} {"current_steps": 26220, "total_steps": 181800, "loss": 0.0346, "lr": 4.970277959881562e-05, "epoch": 2.8844884488448845, "percentage": 14.42, "elapsed_time": "1:01:22", "remaining_time": "6:04:13", "throughput": 1502.14, "total_tokens": 5532352} {"current_steps": 26225, "total_steps": 181800, "loss": 0.0217, "lr": 4.970241049622086e-05, "epoch": 2.885038503850385, "percentage": 14.43, "elapsed_time": "1:01:23", "remaining_time": "6:04:12", "throughput": 1502.14, "total_tokens": 5533376} {"current_steps": 26230, "total_steps": 181800, "loss": 0.1167, "lr": 4.9702041165955837e-05, "epoch": 2.8855885588558854, "percentage": 14.43, "elapsed_time": "1:01:24", "remaining_time": "6:04:11", "throughput": 1502.16, "total_tokens": 5534464} {"current_steps": 26235, "total_steps": 181800, "loss": 0.157, "lr": 4.970167160802395e-05, "epoch": 2.886138613861386, "percentage": 14.43, "elapsed_time": "1:01:25", "remaining_time": "6:04:11", "throughput": 1502.17, "total_tokens": 5535552} {"current_steps": 26240, "total_steps": 181800, "loss": 0.0727, "lr": 4.970130182242861e-05, "epoch": 2.8866886688668867, "percentage": 14.43, "elapsed_time": "1:01:25", "remaining_time": "6:04:10", "throughput": 1502.17, "total_tokens": 5536576} {"current_steps": 26245, "total_steps": 181800, "loss": 0.0752, "lr": 4.9700931809173226e-05, "epoch": 2.8872387238723873, "percentage": 14.44, "elapsed_time": "1:01:26", "remaining_time": "6:04:09", "throughput": 1502.17, "total_tokens": 5537632} {"current_steps": 26250, "total_steps": 181800, "loss": 0.1301, "lr": 4.970056156826121e-05, "epoch": 2.887788778877888, "percentage": 14.44, "elapsed_time": "1:01:27", "remaining_time": "6:04:08", "throughput": 1502.18, "total_tokens": 5538688} {"current_steps": 26255, "total_steps": 181800, "loss": 0.0914, "lr": 4.970019109969597e-05, "epoch": 2.888338833883388, "percentage": 14.44, "elapsed_time": "1:01:27", "remaining_time": "6:04:07", "throughput": 1502.17, "total_tokens": 5539712} {"current_steps": 26260, "total_steps": 181800, "loss": 0.0663, "lr": 4.9699820403480915e-05, "epoch": 2.888888888888889, "percentage": 14.44, "elapsed_time": "1:01:28", "remaining_time": "6:04:07", "throughput": 1502.19, "total_tokens": 5540800} {"current_steps": 26265, "total_steps": 181800, "loss": 0.0558, "lr": 4.969944947961947e-05, "epoch": 2.8894389438943895, "percentage": 14.45, "elapsed_time": "1:01:29", "remaining_time": "6:04:06", "throughput": 1502.2, "total_tokens": 5541888} {"current_steps": 26270, "total_steps": 181800, "loss": 0.052, "lr": 4.969907832811505e-05, "epoch": 2.88998899889989, "percentage": 14.45, "elapsed_time": "1:01:29", "remaining_time": "6:04:05", "throughput": 1502.22, "total_tokens": 5542976} {"current_steps": 26275, "total_steps": 181800, "loss": 0.0756, "lr": 4.9698706948971074e-05, "epoch": 2.890539053905391, "percentage": 14.45, "elapsed_time": "1:01:30", "remaining_time": "6:04:04", "throughput": 1502.22, "total_tokens": 5544032} {"current_steps": 26280, "total_steps": 181800, "loss": 0.0437, "lr": 4.969833534219097e-05, "epoch": 2.891089108910891, "percentage": 14.46, "elapsed_time": "1:01:31", "remaining_time": "6:04:04", "throughput": 1502.22, "total_tokens": 5545056} {"current_steps": 26285, "total_steps": 181800, "loss": 0.0681, "lr": 4.969796350777817e-05, "epoch": 2.8916391639163916, "percentage": 14.46, "elapsed_time": "1:01:31", "remaining_time": "6:04:03", "throughput": 1502.22, "total_tokens": 5546112} {"current_steps": 26290, "total_steps": 181800, "loss": 0.0819, "lr": 4.969759144573608e-05, "epoch": 2.8921892189218923, "percentage": 14.46, "elapsed_time": "1:01:32", "remaining_time": "6:04:02", "throughput": 1502.23, "total_tokens": 5547200} {"current_steps": 26295, "total_steps": 181800, "loss": 0.0571, "lr": 4.969721915606814e-05, "epoch": 2.8927392739273925, "percentage": 14.46, "elapsed_time": "1:01:33", "remaining_time": "6:04:01", "throughput": 1502.24, "total_tokens": 5548256} {"current_steps": 26300, "total_steps": 181800, "loss": 0.0674, "lr": 4.9696846638777796e-05, "epoch": 2.893289328932893, "percentage": 14.47, "elapsed_time": "1:01:34", "remaining_time": "6:04:01", "throughput": 1502.25, "total_tokens": 5549344} {"current_steps": 26305, "total_steps": 181800, "loss": 0.0639, "lr": 4.9696473893868455e-05, "epoch": 2.893839383938394, "percentage": 14.47, "elapsed_time": "1:01:34", "remaining_time": "6:04:00", "throughput": 1502.25, "total_tokens": 5550368} {"current_steps": 26310, "total_steps": 181800, "loss": 0.0537, "lr": 4.969610092134357e-05, "epoch": 2.8943894389438944, "percentage": 14.47, "elapsed_time": "1:01:35", "remaining_time": "6:03:59", "throughput": 1502.24, "total_tokens": 5551360} {"current_steps": 26315, "total_steps": 181800, "loss": 0.0338, "lr": 4.969572772120656e-05, "epoch": 2.894939493949395, "percentage": 14.47, "elapsed_time": "1:01:36", "remaining_time": "6:03:58", "throughput": 1502.25, "total_tokens": 5552416} {"current_steps": 26320, "total_steps": 181800, "loss": 0.1816, "lr": 4.969535429346089e-05, "epoch": 2.8954895489548953, "percentage": 14.48, "elapsed_time": "1:01:36", "remaining_time": "6:03:57", "throughput": 1502.25, "total_tokens": 5553472} {"current_steps": 26325, "total_steps": 181800, "loss": 0.0393, "lr": 4.969498063810999e-05, "epoch": 2.896039603960396, "percentage": 14.48, "elapsed_time": "1:01:37", "remaining_time": "6:03:57", "throughput": 1502.24, "total_tokens": 5554464} {"current_steps": 26330, "total_steps": 181800, "loss": 0.0538, "lr": 4.96946067551573e-05, "epoch": 2.8965896589658966, "percentage": 14.48, "elapsed_time": "1:01:38", "remaining_time": "6:03:56", "throughput": 1502.23, "total_tokens": 5555456} {"current_steps": 26335, "total_steps": 181800, "loss": 0.0513, "lr": 4.969423264460627e-05, "epoch": 2.8971397139713972, "percentage": 14.49, "elapsed_time": "1:01:38", "remaining_time": "6:03:55", "throughput": 1502.22, "total_tokens": 5556448} {"current_steps": 26340, "total_steps": 181800, "loss": 0.0536, "lr": 4.969385830646035e-05, "epoch": 2.897689768976898, "percentage": 14.49, "elapsed_time": "1:01:39", "remaining_time": "6:03:54", "throughput": 1502.23, "total_tokens": 5557536} {"current_steps": 26345, "total_steps": 181800, "loss": 0.0487, "lr": 4.969348374072298e-05, "epoch": 2.898239823982398, "percentage": 14.49, "elapsed_time": "1:01:40", "remaining_time": "6:03:53", "throughput": 1502.24, "total_tokens": 5558592} {"current_steps": 26350, "total_steps": 181800, "loss": 0.032, "lr": 4.9693108947397626e-05, "epoch": 2.8987898789878987, "percentage": 14.49, "elapsed_time": "1:01:40", "remaining_time": "6:03:53", "throughput": 1502.25, "total_tokens": 5559680} {"current_steps": 26355, "total_steps": 181800, "loss": 0.0961, "lr": 4.969273392648773e-05, "epoch": 2.8993399339933994, "percentage": 14.5, "elapsed_time": "1:01:41", "remaining_time": "6:03:52", "throughput": 1502.28, "total_tokens": 5560800} {"current_steps": 26360, "total_steps": 181800, "loss": 0.0151, "lr": 4.9692358677996766e-05, "epoch": 2.8998899889989, "percentage": 14.5, "elapsed_time": "1:01:42", "remaining_time": "6:03:51", "throughput": 1502.28, "total_tokens": 5561856} {"current_steps": 26365, "total_steps": 181800, "loss": 0.0477, "lr": 4.9691983201928174e-05, "epoch": 2.9004400440044007, "percentage": 14.5, "elapsed_time": "1:01:42", "remaining_time": "6:03:50", "throughput": 1502.29, "total_tokens": 5562912} {"current_steps": 26370, "total_steps": 181800, "loss": 0.1292, "lr": 4.9691607498285417e-05, "epoch": 2.900990099009901, "percentage": 14.5, "elapsed_time": "1:01:43", "remaining_time": "6:03:50", "throughput": 1502.3, "total_tokens": 5564000} {"current_steps": 26375, "total_steps": 181800, "loss": 0.0596, "lr": 4.9691231567071964e-05, "epoch": 2.9015401540154016, "percentage": 14.51, "elapsed_time": "1:01:44", "remaining_time": "6:03:49", "throughput": 1502.29, "total_tokens": 5564992} {"current_steps": 26380, "total_steps": 181800, "loss": 0.0355, "lr": 4.969085540829128e-05, "epoch": 2.902090209020902, "percentage": 14.51, "elapsed_time": "1:01:45", "remaining_time": "6:03:48", "throughput": 1502.29, "total_tokens": 5566048} {"current_steps": 26385, "total_steps": 181800, "loss": 0.1384, "lr": 4.9690479021946824e-05, "epoch": 2.9026402640264024, "percentage": 14.51, "elapsed_time": "1:01:45", "remaining_time": "6:03:47", "throughput": 1502.28, "total_tokens": 5567040} {"current_steps": 26390, "total_steps": 181800, "loss": 0.0176, "lr": 4.969010240804207e-05, "epoch": 2.903190319031903, "percentage": 14.52, "elapsed_time": "1:01:46", "remaining_time": "6:03:46", "throughput": 1502.3, "total_tokens": 5568160} {"current_steps": 26395, "total_steps": 181800, "loss": 0.1247, "lr": 4.9689725566580496e-05, "epoch": 2.9037403740374037, "percentage": 14.52, "elapsed_time": "1:01:47", "remaining_time": "6:03:46", "throughput": 1502.31, "total_tokens": 5569216} {"current_steps": 26400, "total_steps": 181800, "loss": 0.0748, "lr": 4.968934849756557e-05, "epoch": 2.9042904290429044, "percentage": 14.52, "elapsed_time": "1:01:47", "remaining_time": "6:03:45", "throughput": 1502.33, "total_tokens": 5570304} {"current_steps": 26405, "total_steps": 181800, "loss": 0.1395, "lr": 4.9688971201000755e-05, "epoch": 2.904840484048405, "percentage": 14.52, "elapsed_time": "1:01:48", "remaining_time": "6:03:44", "throughput": 1502.34, "total_tokens": 5571392} {"current_steps": 26410, "total_steps": 181800, "loss": 0.0084, "lr": 4.968859367688955e-05, "epoch": 2.905390539053905, "percentage": 14.53, "elapsed_time": "1:01:49", "remaining_time": "6:03:43", "throughput": 1502.34, "total_tokens": 5572416} {"current_steps": 26415, "total_steps": 181800, "loss": 0.046, "lr": 4.968821592523542e-05, "epoch": 2.905940594059406, "percentage": 14.53, "elapsed_time": "1:01:49", "remaining_time": "6:03:43", "throughput": 1502.38, "total_tokens": 5573632} {"current_steps": 26420, "total_steps": 181800, "loss": 0.0768, "lr": 4.9687837946041846e-05, "epoch": 2.9064906490649065, "percentage": 14.53, "elapsed_time": "1:01:50", "remaining_time": "6:03:42", "throughput": 1502.39, "total_tokens": 5574688} {"current_steps": 26425, "total_steps": 181800, "loss": 0.069, "lr": 4.968745973931233e-05, "epoch": 2.907040704070407, "percentage": 14.54, "elapsed_time": "1:01:51", "remaining_time": "6:03:41", "throughput": 1502.4, "total_tokens": 5575744} {"current_steps": 26430, "total_steps": 181800, "loss": 0.073, "lr": 4.968708130505033e-05, "epoch": 2.907590759075908, "percentage": 14.54, "elapsed_time": "1:01:51", "remaining_time": "6:03:40", "throughput": 1502.41, "total_tokens": 5576832} {"current_steps": 26435, "total_steps": 181800, "loss": 0.0225, "lr": 4.968670264325935e-05, "epoch": 2.908140814081408, "percentage": 14.54, "elapsed_time": "1:01:52", "remaining_time": "6:03:39", "throughput": 1502.42, "total_tokens": 5577888} {"current_steps": 26440, "total_steps": 181800, "loss": 0.0261, "lr": 4.968632375394289e-05, "epoch": 2.9086908690869087, "percentage": 14.54, "elapsed_time": "1:01:53", "remaining_time": "6:03:39", "throughput": 1502.42, "total_tokens": 5578944} {"current_steps": 26445, "total_steps": 181800, "loss": 0.0511, "lr": 4.9685944637104415e-05, "epoch": 2.9092409240924093, "percentage": 14.55, "elapsed_time": "1:01:53", "remaining_time": "6:03:38", "throughput": 1502.44, "total_tokens": 5580032} {"current_steps": 26450, "total_steps": 181800, "loss": 0.0367, "lr": 4.9685565292747436e-05, "epoch": 2.9097909790979095, "percentage": 14.55, "elapsed_time": "1:01:54", "remaining_time": "6:03:37", "throughput": 1502.43, "total_tokens": 5581056} {"current_steps": 26455, "total_steps": 181800, "loss": 0.1127, "lr": 4.968518572087545e-05, "epoch": 2.9103410341034106, "percentage": 14.55, "elapsed_time": "1:01:55", "remaining_time": "6:03:36", "throughput": 1502.47, "total_tokens": 5582208} {"current_steps": 26460, "total_steps": 181800, "loss": 0.0623, "lr": 4.968480592149195e-05, "epoch": 2.910891089108911, "percentage": 14.55, "elapsed_time": "1:01:56", "remaining_time": "6:03:36", "throughput": 1502.47, "total_tokens": 5583264} {"current_steps": 26465, "total_steps": 181800, "loss": 0.0745, "lr": 4.968442589460044e-05, "epoch": 2.9114411441144115, "percentage": 14.56, "elapsed_time": "1:01:56", "remaining_time": "6:03:35", "throughput": 1502.47, "total_tokens": 5584288} {"current_steps": 26470, "total_steps": 181800, "loss": 0.0573, "lr": 4.9684045640204426e-05, "epoch": 2.911991199119912, "percentage": 14.56, "elapsed_time": "1:01:57", "remaining_time": "6:03:34", "throughput": 1502.48, "total_tokens": 5585376} {"current_steps": 26475, "total_steps": 181800, "loss": 0.0864, "lr": 4.96836651583074e-05, "epoch": 2.9125412541254123, "percentage": 14.56, "elapsed_time": "1:01:58", "remaining_time": "6:03:33", "throughput": 1502.52, "total_tokens": 5586528} {"current_steps": 26480, "total_steps": 181800, "loss": 0.0255, "lr": 4.968328444891288e-05, "epoch": 2.913091309130913, "percentage": 14.57, "elapsed_time": "1:01:58", "remaining_time": "6:03:32", "throughput": 1502.53, "total_tokens": 5587616} {"current_steps": 26485, "total_steps": 181800, "loss": 0.0396, "lr": 4.968290351202437e-05, "epoch": 2.9136413641364136, "percentage": 14.57, "elapsed_time": "1:01:59", "remaining_time": "6:03:32", "throughput": 1502.53, "total_tokens": 5588640} {"current_steps": 26490, "total_steps": 181800, "loss": 0.0481, "lr": 4.9682522347645386e-05, "epoch": 2.9141914191419143, "percentage": 14.57, "elapsed_time": "1:02:00", "remaining_time": "6:03:31", "throughput": 1502.51, "total_tokens": 5589600} {"current_steps": 26495, "total_steps": 181800, "loss": 0.0528, "lr": 4.9682140955779434e-05, "epoch": 2.914741474147415, "percentage": 14.57, "elapsed_time": "1:02:00", "remaining_time": "6:03:30", "throughput": 1502.51, "total_tokens": 5590624} {"current_steps": 26500, "total_steps": 181800, "loss": 0.083, "lr": 4.968175933643003e-05, "epoch": 2.915291529152915, "percentage": 14.58, "elapsed_time": "1:02:01", "remaining_time": "6:03:29", "throughput": 1502.52, "total_tokens": 5591712} {"current_steps": 26505, "total_steps": 181800, "loss": 0.0241, "lr": 4.96813774896007e-05, "epoch": 2.9158415841584158, "percentage": 14.58, "elapsed_time": "1:02:02", "remaining_time": "6:03:28", "throughput": 1502.52, "total_tokens": 5592768} {"current_steps": 26510, "total_steps": 181800, "loss": 0.0218, "lr": 4.9680995415294956e-05, "epoch": 2.9163916391639164, "percentage": 14.58, "elapsed_time": "1:02:02", "remaining_time": "6:03:28", "throughput": 1502.54, "total_tokens": 5593856} {"current_steps": 26515, "total_steps": 181800, "loss": 0.1281, "lr": 4.9680613113516315e-05, "epoch": 2.916941694169417, "percentage": 14.58, "elapsed_time": "1:02:03", "remaining_time": "6:03:27", "throughput": 1502.54, "total_tokens": 5594880} {"current_steps": 26520, "total_steps": 181800, "loss": 0.091, "lr": 4.968023058426832e-05, "epoch": 2.9174917491749177, "percentage": 14.59, "elapsed_time": "1:02:04", "remaining_time": "6:03:26", "throughput": 1502.53, "total_tokens": 5595904} {"current_steps": 26525, "total_steps": 181800, "loss": 0.164, "lr": 4.967984782755446e-05, "epoch": 2.918041804180418, "percentage": 14.59, "elapsed_time": "1:02:04", "remaining_time": "6:03:25", "throughput": 1502.54, "total_tokens": 5596960} {"current_steps": 26530, "total_steps": 181800, "loss": 0.0244, "lr": 4.96794648433783e-05, "epoch": 2.9185918591859186, "percentage": 14.59, "elapsed_time": "1:02:05", "remaining_time": "6:03:25", "throughput": 1502.54, "total_tokens": 5597984} {"current_steps": 26535, "total_steps": 181800, "loss": 0.0234, "lr": 4.9679081631743354e-05, "epoch": 2.919141914191419, "percentage": 14.6, "elapsed_time": "1:02:06", "remaining_time": "6:03:24", "throughput": 1502.55, "total_tokens": 5599072} {"current_steps": 26540, "total_steps": 181800, "loss": 0.1043, "lr": 4.967869819265315e-05, "epoch": 2.9196919691969194, "percentage": 14.6, "elapsed_time": "1:02:07", "remaining_time": "6:03:23", "throughput": 1502.56, "total_tokens": 5600128} {"current_steps": 26545, "total_steps": 181800, "loss": 0.0376, "lr": 4.967831452611124e-05, "epoch": 2.9202420242024205, "percentage": 14.6, "elapsed_time": "1:02:07", "remaining_time": "6:03:22", "throughput": 1502.56, "total_tokens": 5601152} {"current_steps": 26550, "total_steps": 181800, "loss": 0.0989, "lr": 4.967793063212113e-05, "epoch": 2.9207920792079207, "percentage": 14.6, "elapsed_time": "1:02:08", "remaining_time": "6:03:21", "throughput": 1502.56, "total_tokens": 5602208} {"current_steps": 26555, "total_steps": 181800, "loss": 0.1667, "lr": 4.967754651068638e-05, "epoch": 2.9213421342134214, "percentage": 14.61, "elapsed_time": "1:02:09", "remaining_time": "6:03:21", "throughput": 1502.58, "total_tokens": 5603296} {"current_steps": 26560, "total_steps": 181800, "loss": 0.0918, "lr": 4.967716216181052e-05, "epoch": 2.921892189218922, "percentage": 14.61, "elapsed_time": "1:02:09", "remaining_time": "6:03:20", "throughput": 1502.58, "total_tokens": 5604320} {"current_steps": 26565, "total_steps": 181800, "loss": 0.0643, "lr": 4.967677758549711e-05, "epoch": 2.9224422442244222, "percentage": 14.61, "elapsed_time": "1:02:10", "remaining_time": "6:03:19", "throughput": 1502.59, "total_tokens": 5605408} {"current_steps": 26570, "total_steps": 181800, "loss": 0.054, "lr": 4.9676392781749674e-05, "epoch": 2.922992299229923, "percentage": 14.61, "elapsed_time": "1:02:11", "remaining_time": "6:03:18", "throughput": 1502.6, "total_tokens": 5606464} {"current_steps": 26575, "total_steps": 181800, "loss": 0.0079, "lr": 4.9676007750571774e-05, "epoch": 2.9235423542354235, "percentage": 14.62, "elapsed_time": "1:02:11", "remaining_time": "6:03:17", "throughput": 1502.6, "total_tokens": 5607520} {"current_steps": 26580, "total_steps": 181800, "loss": 0.0317, "lr": 4.9675622491966944e-05, "epoch": 2.924092409240924, "percentage": 14.62, "elapsed_time": "1:02:12", "remaining_time": "6:03:17", "throughput": 1502.61, "total_tokens": 5608576} {"current_steps": 26585, "total_steps": 181800, "loss": 0.041, "lr": 4.967523700593875e-05, "epoch": 2.924642464246425, "percentage": 14.62, "elapsed_time": "1:02:13", "remaining_time": "6:03:16", "throughput": 1502.61, "total_tokens": 5609632} {"current_steps": 26590, "total_steps": 181800, "loss": 0.0716, "lr": 4.967485129249072e-05, "epoch": 2.925192519251925, "percentage": 14.63, "elapsed_time": "1:02:13", "remaining_time": "6:03:15", "throughput": 1502.63, "total_tokens": 5610720} {"current_steps": 26595, "total_steps": 181800, "loss": 0.0739, "lr": 4.967446535162644e-05, "epoch": 2.9257425742574257, "percentage": 14.63, "elapsed_time": "1:02:14", "remaining_time": "6:03:14", "throughput": 1502.63, "total_tokens": 5611776} {"current_steps": 26600, "total_steps": 181800, "loss": 0.0161, "lr": 4.967407918334945e-05, "epoch": 2.9262926292629263, "percentage": 14.63, "elapsed_time": "1:02:15", "remaining_time": "6:03:14", "throughput": 1502.62, "total_tokens": 5612768} {"current_steps": 26605, "total_steps": 181800, "loss": 0.0648, "lr": 4.9673692787663314e-05, "epoch": 2.926842684268427, "percentage": 14.63, "elapsed_time": "1:02:16", "remaining_time": "6:03:13", "throughput": 1502.61, "total_tokens": 5613792} {"current_steps": 26610, "total_steps": 181800, "loss": 0.0789, "lr": 4.9673306164571584e-05, "epoch": 2.9273927392739276, "percentage": 14.64, "elapsed_time": "1:02:16", "remaining_time": "6:03:12", "throughput": 1502.61, "total_tokens": 5614816} {"current_steps": 26615, "total_steps": 181800, "loss": 0.1427, "lr": 4.967291931407784e-05, "epoch": 2.927942794279428, "percentage": 14.64, "elapsed_time": "1:02:17", "remaining_time": "6:03:11", "throughput": 1502.61, "total_tokens": 5615872} {"current_steps": 26620, "total_steps": 181800, "loss": 0.0345, "lr": 4.9672532236185634e-05, "epoch": 2.9284928492849285, "percentage": 14.64, "elapsed_time": "1:02:18", "remaining_time": "6:03:10", "throughput": 1502.62, "total_tokens": 5616928} {"current_steps": 26625, "total_steps": 181800, "loss": 0.0816, "lr": 4.9672144930898535e-05, "epoch": 2.929042904290429, "percentage": 14.65, "elapsed_time": "1:02:18", "remaining_time": "6:03:10", "throughput": 1502.62, "total_tokens": 5617952} {"current_steps": 26630, "total_steps": 181800, "loss": 0.1372, "lr": 4.967175739822011e-05, "epoch": 2.9295929592959293, "percentage": 14.65, "elapsed_time": "1:02:19", "remaining_time": "6:03:09", "throughput": 1502.63, "total_tokens": 5619040} {"current_steps": 26635, "total_steps": 181800, "loss": 0.0453, "lr": 4.967136963815394e-05, "epoch": 2.93014301430143, "percentage": 14.65, "elapsed_time": "1:02:20", "remaining_time": "6:03:08", "throughput": 1502.65, "total_tokens": 5620128} {"current_steps": 26640, "total_steps": 181800, "loss": 0.0285, "lr": 4.96709816507036e-05, "epoch": 2.9306930693069306, "percentage": 14.65, "elapsed_time": "1:02:20", "remaining_time": "6:03:07", "throughput": 1502.66, "total_tokens": 5621184} {"current_steps": 26645, "total_steps": 181800, "loss": 0.1094, "lr": 4.967059343587266e-05, "epoch": 2.9312431243124313, "percentage": 14.66, "elapsed_time": "1:02:21", "remaining_time": "6:03:07", "throughput": 1502.69, "total_tokens": 5622336} {"current_steps": 26650, "total_steps": 181800, "loss": 0.0364, "lr": 4.967020499366469e-05, "epoch": 2.931793179317932, "percentage": 14.66, "elapsed_time": "1:02:22", "remaining_time": "6:03:06", "throughput": 1502.68, "total_tokens": 5623360} {"current_steps": 26655, "total_steps": 181800, "loss": 0.0852, "lr": 4.966981632408328e-05, "epoch": 2.932343234323432, "percentage": 14.66, "elapsed_time": "1:02:22", "remaining_time": "6:03:05", "throughput": 1502.69, "total_tokens": 5624448} {"current_steps": 26660, "total_steps": 181800, "loss": 0.02, "lr": 4.966942742713202e-05, "epoch": 2.932893289328933, "percentage": 14.66, "elapsed_time": "1:02:23", "remaining_time": "6:03:04", "throughput": 1502.71, "total_tokens": 5625536} {"current_steps": 26665, "total_steps": 181800, "loss": 0.026, "lr": 4.966903830281449e-05, "epoch": 2.9334433443344334, "percentage": 14.67, "elapsed_time": "1:02:24", "remaining_time": "6:03:04", "throughput": 1502.7, "total_tokens": 5626560} {"current_steps": 26670, "total_steps": 181800, "loss": 0.0735, "lr": 4.966864895113426e-05, "epoch": 2.933993399339934, "percentage": 14.67, "elapsed_time": "1:02:24", "remaining_time": "6:03:03", "throughput": 1502.68, "total_tokens": 5627520} {"current_steps": 26675, "total_steps": 181800, "loss": 0.0433, "lr": 4.966825937209493e-05, "epoch": 2.9345434543454347, "percentage": 14.67, "elapsed_time": "1:02:25", "remaining_time": "6:03:02", "throughput": 1502.7, "total_tokens": 5628640} {"current_steps": 26680, "total_steps": 181800, "loss": 0.1104, "lr": 4.966786956570009e-05, "epoch": 2.935093509350935, "percentage": 14.68, "elapsed_time": "1:02:26", "remaining_time": "6:03:01", "throughput": 1502.71, "total_tokens": 5629696} {"current_steps": 26685, "total_steps": 181800, "loss": 0.104, "lr": 4.9667479531953334e-05, "epoch": 2.9356435643564356, "percentage": 14.68, "elapsed_time": "1:02:27", "remaining_time": "6:03:00", "throughput": 1502.71, "total_tokens": 5630720} {"current_steps": 26690, "total_steps": 181800, "loss": 0.0768, "lr": 4.966708927085825e-05, "epoch": 2.9361936193619362, "percentage": 14.68, "elapsed_time": "1:02:27", "remaining_time": "6:03:00", "throughput": 1502.74, "total_tokens": 5631872} {"current_steps": 26695, "total_steps": 181800, "loss": 0.0898, "lr": 4.9666698782418446e-05, "epoch": 2.936743674367437, "percentage": 14.68, "elapsed_time": "1:02:28", "remaining_time": "6:02:59", "throughput": 1502.73, "total_tokens": 5632864} {"current_steps": 26700, "total_steps": 181800, "loss": 0.1246, "lr": 4.966630806663751e-05, "epoch": 2.9372937293729375, "percentage": 14.69, "elapsed_time": "1:02:29", "remaining_time": "6:02:58", "throughput": 1502.75, "total_tokens": 5633984} {"current_steps": 26705, "total_steps": 181800, "loss": 0.1029, "lr": 4.966591712351906e-05, "epoch": 2.9378437843784377, "percentage": 14.69, "elapsed_time": "1:02:29", "remaining_time": "6:02:57", "throughput": 1502.75, "total_tokens": 5635008} {"current_steps": 26710, "total_steps": 181800, "loss": 0.042, "lr": 4.966552595306668e-05, "epoch": 2.9383938393839384, "percentage": 14.69, "elapsed_time": "1:02:30", "remaining_time": "6:02:57", "throughput": 1502.75, "total_tokens": 5636064} {"current_steps": 26715, "total_steps": 181800, "loss": 0.0467, "lr": 4.966513455528399e-05, "epoch": 2.938943894389439, "percentage": 14.69, "elapsed_time": "1:02:31", "remaining_time": "6:02:56", "throughput": 1502.76, "total_tokens": 5637120} {"current_steps": 26720, "total_steps": 181800, "loss": 0.0198, "lr": 4.9664742930174585e-05, "epoch": 2.9394939493949392, "percentage": 14.7, "elapsed_time": "1:02:31", "remaining_time": "6:02:55", "throughput": 1502.76, "total_tokens": 5638176} {"current_steps": 26725, "total_steps": 181800, "loss": 0.0314, "lr": 4.966435107774208e-05, "epoch": 2.94004400440044, "percentage": 14.7, "elapsed_time": "1:02:32", "remaining_time": "6:02:54", "throughput": 1502.77, "total_tokens": 5639232} {"current_steps": 26730, "total_steps": 181800, "loss": 0.1451, "lr": 4.9663958997990084e-05, "epoch": 2.9405940594059405, "percentage": 14.7, "elapsed_time": "1:02:33", "remaining_time": "6:02:53", "throughput": 1502.77, "total_tokens": 5640288} {"current_steps": 26735, "total_steps": 181800, "loss": 0.0512, "lr": 4.966356669092222e-05, "epoch": 2.941144114411441, "percentage": 14.71, "elapsed_time": "1:02:33", "remaining_time": "6:02:53", "throughput": 1502.78, "total_tokens": 5641344} {"current_steps": 26740, "total_steps": 181800, "loss": 0.0911, "lr": 4.9663174156542095e-05, "epoch": 2.941694169416942, "percentage": 14.71, "elapsed_time": "1:02:34", "remaining_time": "6:02:52", "throughput": 1502.79, "total_tokens": 5642400} {"current_steps": 26745, "total_steps": 181800, "loss": 0.0794, "lr": 4.966278139485332e-05, "epoch": 2.942244224422442, "percentage": 14.71, "elapsed_time": "1:02:35", "remaining_time": "6:02:51", "throughput": 1502.79, "total_tokens": 5643456} {"current_steps": 26750, "total_steps": 181800, "loss": 0.0311, "lr": 4.966238840585953e-05, "epoch": 2.9427942794279427, "percentage": 14.71, "elapsed_time": "1:02:35", "remaining_time": "6:02:50", "throughput": 1502.78, "total_tokens": 5644448} {"current_steps": 26755, "total_steps": 181800, "loss": 0.0598, "lr": 4.966199518956433e-05, "epoch": 2.9433443344334433, "percentage": 14.72, "elapsed_time": "1:02:36", "remaining_time": "6:02:49", "throughput": 1502.8, "total_tokens": 5645536} {"current_steps": 26760, "total_steps": 181800, "loss": 0.1018, "lr": 4.966160174597137e-05, "epoch": 2.943894389438944, "percentage": 14.72, "elapsed_time": "1:02:37", "remaining_time": "6:02:49", "throughput": 1502.79, "total_tokens": 5646560} {"current_steps": 26765, "total_steps": 181800, "loss": 0.1277, "lr": 4.966120807508425e-05, "epoch": 2.9444444444444446, "percentage": 14.72, "elapsed_time": "1:02:38", "remaining_time": "6:02:48", "throughput": 1502.77, "total_tokens": 5647520} {"current_steps": 26770, "total_steps": 181800, "loss": 0.1207, "lr": 4.9660814176906614e-05, "epoch": 2.944994499449945, "percentage": 14.72, "elapsed_time": "1:02:38", "remaining_time": "6:02:47", "throughput": 1502.79, "total_tokens": 5648608} {"current_steps": 26775, "total_steps": 181800, "loss": 0.0321, "lr": 4.9660420051442084e-05, "epoch": 2.9455445544554455, "percentage": 14.73, "elapsed_time": "1:02:39", "remaining_time": "6:02:46", "throughput": 1502.79, "total_tokens": 5649664} {"current_steps": 26780, "total_steps": 181800, "loss": 0.0704, "lr": 4.96600256986943e-05, "epoch": 2.946094609460946, "percentage": 14.73, "elapsed_time": "1:02:40", "remaining_time": "6:02:46", "throughput": 1502.8, "total_tokens": 5650720} {"current_steps": 26785, "total_steps": 181800, "loss": 0.1292, "lr": 4.965963111866689e-05, "epoch": 2.946644664466447, "percentage": 14.73, "elapsed_time": "1:02:40", "remaining_time": "6:02:45", "throughput": 1502.81, "total_tokens": 5651776} {"current_steps": 26790, "total_steps": 181800, "loss": 0.0842, "lr": 4.965923631136349e-05, "epoch": 2.9471947194719474, "percentage": 14.74, "elapsed_time": "1:02:41", "remaining_time": "6:02:44", "throughput": 1502.8, "total_tokens": 5652768} {"current_steps": 26795, "total_steps": 181800, "loss": 0.0611, "lr": 4.9658841276787746e-05, "epoch": 2.9477447744774476, "percentage": 14.74, "elapsed_time": "1:02:42", "remaining_time": "6:02:43", "throughput": 1502.81, "total_tokens": 5653856} {"current_steps": 26800, "total_steps": 181800, "loss": 0.0588, "lr": 4.9658446014943285e-05, "epoch": 2.9482948294829483, "percentage": 14.74, "elapsed_time": "1:02:42", "remaining_time": "6:02:42", "throughput": 1502.83, "total_tokens": 5654944} {"current_steps": 26805, "total_steps": 181800, "loss": 0.0812, "lr": 4.965805052583377e-05, "epoch": 2.948844884488449, "percentage": 14.74, "elapsed_time": "1:02:43", "remaining_time": "6:02:42", "throughput": 1502.82, "total_tokens": 5655968} {"current_steps": 26810, "total_steps": 181800, "loss": 0.0348, "lr": 4.9657654809462826e-05, "epoch": 2.949394939493949, "percentage": 14.75, "elapsed_time": "1:02:44", "remaining_time": "6:02:41", "throughput": 1502.84, "total_tokens": 5657056} {"current_steps": 26815, "total_steps": 181800, "loss": 0.0811, "lr": 4.965725886583412e-05, "epoch": 2.94994499449945, "percentage": 14.75, "elapsed_time": "1:02:44", "remaining_time": "6:02:40", "throughput": 1502.85, "total_tokens": 5658144} {"current_steps": 26820, "total_steps": 181800, "loss": 0.0429, "lr": 4.965686269495129e-05, "epoch": 2.9504950495049505, "percentage": 14.75, "elapsed_time": "1:02:45", "remaining_time": "6:02:39", "throughput": 1502.84, "total_tokens": 5659136} {"current_steps": 26825, "total_steps": 181800, "loss": 0.1054, "lr": 4.9656466296817985e-05, "epoch": 2.951045104510451, "percentage": 14.76, "elapsed_time": "1:02:46", "remaining_time": "6:02:38", "throughput": 1502.84, "total_tokens": 5660160} {"current_steps": 26830, "total_steps": 181800, "loss": 0.0584, "lr": 4.9656069671437856e-05, "epoch": 2.9515951595159517, "percentage": 14.76, "elapsed_time": "1:02:46", "remaining_time": "6:02:38", "throughput": 1502.84, "total_tokens": 5661184} {"current_steps": 26835, "total_steps": 181800, "loss": 0.1664, "lr": 4.965567281881457e-05, "epoch": 2.952145214521452, "percentage": 14.76, "elapsed_time": "1:02:47", "remaining_time": "6:02:37", "throughput": 1502.85, "total_tokens": 5662240} {"current_steps": 26840, "total_steps": 181800, "loss": 0.0785, "lr": 4.965527573895178e-05, "epoch": 2.9526952695269526, "percentage": 14.76, "elapsed_time": "1:02:48", "remaining_time": "6:02:36", "throughput": 1502.86, "total_tokens": 5663328} {"current_steps": 26845, "total_steps": 181800, "loss": 0.1506, "lr": 4.965487843185314e-05, "epoch": 2.9532453245324533, "percentage": 14.77, "elapsed_time": "1:02:49", "remaining_time": "6:02:35", "throughput": 1502.86, "total_tokens": 5664352} {"current_steps": 26850, "total_steps": 181800, "loss": 0.0451, "lr": 4.9654480897522314e-05, "epoch": 2.953795379537954, "percentage": 14.77, "elapsed_time": "1:02:49", "remaining_time": "6:02:34", "throughput": 1502.86, "total_tokens": 5665376} {"current_steps": 26855, "total_steps": 181800, "loss": 0.0597, "lr": 4.965408313596297e-05, "epoch": 2.9543454345434546, "percentage": 14.77, "elapsed_time": "1:02:50", "remaining_time": "6:02:34", "throughput": 1502.85, "total_tokens": 5666368} {"current_steps": 26860, "total_steps": 181800, "loss": 0.0302, "lr": 4.965368514717877e-05, "epoch": 2.9548954895489548, "percentage": 14.77, "elapsed_time": "1:02:51", "remaining_time": "6:02:33", "throughput": 1502.85, "total_tokens": 5667424} {"current_steps": 26865, "total_steps": 181800, "loss": 0.0424, "lr": 4.9653286931173395e-05, "epoch": 2.9554455445544554, "percentage": 14.78, "elapsed_time": "1:02:51", "remaining_time": "6:02:32", "throughput": 1502.86, "total_tokens": 5668480} {"current_steps": 26870, "total_steps": 181800, "loss": 0.0361, "lr": 4.9652888487950494e-05, "epoch": 2.955995599559956, "percentage": 14.78, "elapsed_time": "1:02:52", "remaining_time": "6:02:31", "throughput": 1502.87, "total_tokens": 5669536} {"current_steps": 26875, "total_steps": 181800, "loss": 0.1005, "lr": 4.965248981751375e-05, "epoch": 2.9565456545654567, "percentage": 14.78, "elapsed_time": "1:02:53", "remaining_time": "6:02:30", "throughput": 1502.86, "total_tokens": 5670528} {"current_steps": 26880, "total_steps": 181800, "loss": 0.0928, "lr": 4.965209091986684e-05, "epoch": 2.9570957095709574, "percentage": 14.79, "elapsed_time": "1:02:53", "remaining_time": "6:02:30", "throughput": 1502.87, "total_tokens": 5671616} {"current_steps": 26885, "total_steps": 181800, "loss": 0.029, "lr": 4.9651691795013435e-05, "epoch": 2.9576457645764576, "percentage": 14.79, "elapsed_time": "1:02:54", "remaining_time": "6:02:29", "throughput": 1502.89, "total_tokens": 5672736} {"current_steps": 26890, "total_steps": 181800, "loss": 0.0224, "lr": 4.9651292442957216e-05, "epoch": 2.958195819581958, "percentage": 14.79, "elapsed_time": "1:02:55", "remaining_time": "6:02:28", "throughput": 1502.89, "total_tokens": 5673760} {"current_steps": 26895, "total_steps": 181800, "loss": 0.025, "lr": 4.9650892863701865e-05, "epoch": 2.958745874587459, "percentage": 14.79, "elapsed_time": "1:02:55", "remaining_time": "6:02:27", "throughput": 1502.89, "total_tokens": 5674784} {"current_steps": 26900, "total_steps": 181800, "loss": 0.0577, "lr": 4.9650493057251054e-05, "epoch": 2.959295929592959, "percentage": 14.8, "elapsed_time": "1:02:56", "remaining_time": "6:02:27", "throughput": 1502.88, "total_tokens": 5675808} {"current_steps": 26905, "total_steps": 181800, "loss": 0.1089, "lr": 4.965009302360849e-05, "epoch": 2.9598459845984597, "percentage": 14.8, "elapsed_time": "1:02:57", "remaining_time": "6:02:26", "throughput": 1502.89, "total_tokens": 5676864} {"current_steps": 26910, "total_steps": 181800, "loss": 0.0555, "lr": 4.9649692762777846e-05, "epoch": 2.9603960396039604, "percentage": 14.8, "elapsed_time": "1:02:57", "remaining_time": "6:02:25", "throughput": 1502.9, "total_tokens": 5677952} {"current_steps": 26915, "total_steps": 181800, "loss": 0.0437, "lr": 4.96492922747628e-05, "epoch": 2.960946094609461, "percentage": 14.8, "elapsed_time": "1:02:58", "remaining_time": "6:02:24", "throughput": 1502.91, "total_tokens": 5679008} {"current_steps": 26920, "total_steps": 181800, "loss": 0.0182, "lr": 4.964889155956707e-05, "epoch": 2.9614961496149617, "percentage": 14.81, "elapsed_time": "1:02:59", "remaining_time": "6:02:24", "throughput": 1502.91, "total_tokens": 5680064} {"current_steps": 26925, "total_steps": 181800, "loss": 0.0543, "lr": 4.964849061719432e-05, "epoch": 2.962046204620462, "percentage": 14.81, "elapsed_time": "1:03:00", "remaining_time": "6:02:23", "throughput": 1502.91, "total_tokens": 5681088} {"current_steps": 26930, "total_steps": 181800, "loss": 0.1465, "lr": 4.964808944764827e-05, "epoch": 2.9625962596259625, "percentage": 14.81, "elapsed_time": "1:03:00", "remaining_time": "6:02:22", "throughput": 1502.9, "total_tokens": 5682080} {"current_steps": 26935, "total_steps": 181800, "loss": 0.0462, "lr": 4.964768805093261e-05, "epoch": 2.963146314631463, "percentage": 14.82, "elapsed_time": "1:03:01", "remaining_time": "6:02:21", "throughput": 1502.92, "total_tokens": 5683200} {"current_steps": 26940, "total_steps": 181800, "loss": 0.0178, "lr": 4.9647286427051023e-05, "epoch": 2.963696369636964, "percentage": 14.82, "elapsed_time": "1:03:02", "remaining_time": "6:02:20", "throughput": 1502.93, "total_tokens": 5684288} {"current_steps": 26945, "total_steps": 181800, "loss": 0.0242, "lr": 4.964688457600723e-05, "epoch": 2.9642464246424645, "percentage": 14.82, "elapsed_time": "1:03:02", "remaining_time": "6:02:20", "throughput": 1502.94, "total_tokens": 5685344} {"current_steps": 26950, "total_steps": 181800, "loss": 0.1076, "lr": 4.964648249780493e-05, "epoch": 2.9647964796479647, "percentage": 14.82, "elapsed_time": "1:03:03", "remaining_time": "6:02:19", "throughput": 1502.95, "total_tokens": 5686432} {"current_steps": 26955, "total_steps": 181800, "loss": 0.0886, "lr": 4.964608019244783e-05, "epoch": 2.9653465346534653, "percentage": 14.83, "elapsed_time": "1:03:04", "remaining_time": "6:02:18", "throughput": 1502.96, "total_tokens": 5687488} {"current_steps": 26960, "total_steps": 181800, "loss": 0.0729, "lr": 4.964567765993963e-05, "epoch": 2.965896589658966, "percentage": 14.83, "elapsed_time": "1:03:04", "remaining_time": "6:02:17", "throughput": 1502.96, "total_tokens": 5688512} {"current_steps": 26965, "total_steps": 181800, "loss": 0.0412, "lr": 4.9645274900284045e-05, "epoch": 2.966446644664466, "percentage": 14.83, "elapsed_time": "1:03:05", "remaining_time": "6:02:17", "throughput": 1502.96, "total_tokens": 5689568} {"current_steps": 26970, "total_steps": 181800, "loss": 0.0581, "lr": 4.964487191348479e-05, "epoch": 2.9669966996699673, "percentage": 14.83, "elapsed_time": "1:03:06", "remaining_time": "6:02:16", "throughput": 1502.97, "total_tokens": 5690624} {"current_steps": 26975, "total_steps": 181800, "loss": 0.0372, "lr": 4.964446869954558e-05, "epoch": 2.9675467546754675, "percentage": 14.84, "elapsed_time": "1:03:06", "remaining_time": "6:02:15", "throughput": 1502.98, "total_tokens": 5691680} {"current_steps": 26980, "total_steps": 181800, "loss": 0.0426, "lr": 4.964406525847012e-05, "epoch": 2.968096809680968, "percentage": 14.84, "elapsed_time": "1:03:07", "remaining_time": "6:02:14", "throughput": 1503.0, "total_tokens": 5692800} {"current_steps": 26985, "total_steps": 181800, "loss": 0.1096, "lr": 4.964366159026213e-05, "epoch": 2.9686468646864688, "percentage": 14.84, "elapsed_time": "1:03:08", "remaining_time": "6:02:13", "throughput": 1502.99, "total_tokens": 5693792} {"current_steps": 26990, "total_steps": 181800, "loss": 0.0369, "lr": 4.964325769492535e-05, "epoch": 2.969196919691969, "percentage": 14.85, "elapsed_time": "1:03:09", "remaining_time": "6:02:13", "throughput": 1502.98, "total_tokens": 5694816} {"current_steps": 26995, "total_steps": 181800, "loss": 0.0996, "lr": 4.964285357246348e-05, "epoch": 2.9697469746974696, "percentage": 14.85, "elapsed_time": "1:03:09", "remaining_time": "6:02:12", "throughput": 1502.98, "total_tokens": 5695840} {"current_steps": 27000, "total_steps": 181800, "loss": 0.1279, "lr": 4.964244922288026e-05, "epoch": 2.9702970297029703, "percentage": 14.85, "elapsed_time": "1:03:10", "remaining_time": "6:02:11", "throughput": 1502.99, "total_tokens": 5696896} {"current_steps": 27005, "total_steps": 181800, "loss": 0.0484, "lr": 4.964204464617941e-05, "epoch": 2.970847084708471, "percentage": 14.85, "elapsed_time": "1:03:11", "remaining_time": "6:02:10", "throughput": 1503.0, "total_tokens": 5697984} {"current_steps": 27010, "total_steps": 181800, "loss": 0.0855, "lr": 4.964163984236465e-05, "epoch": 2.9713971397139716, "percentage": 14.86, "elapsed_time": "1:03:11", "remaining_time": "6:02:09", "throughput": 1502.98, "total_tokens": 5698944} {"current_steps": 27015, "total_steps": 181800, "loss": 0.0351, "lr": 4.964123481143973e-05, "epoch": 2.9719471947194718, "percentage": 14.86, "elapsed_time": "1:03:12", "remaining_time": "6:02:09", "throughput": 1502.98, "total_tokens": 5699968} {"current_steps": 27020, "total_steps": 181800, "loss": 0.0579, "lr": 4.9640829553408366e-05, "epoch": 2.9724972497249724, "percentage": 14.86, "elapsed_time": "1:03:13", "remaining_time": "6:02:08", "throughput": 1502.97, "total_tokens": 5700960} {"current_steps": 27025, "total_steps": 181800, "loss": 0.0642, "lr": 4.9640424068274304e-05, "epoch": 2.973047304730473, "percentage": 14.87, "elapsed_time": "1:03:13", "remaining_time": "6:02:07", "throughput": 1502.96, "total_tokens": 5701984} {"current_steps": 27030, "total_steps": 181800, "loss": 0.0509, "lr": 4.9640018356041275e-05, "epoch": 2.9735973597359737, "percentage": 14.87, "elapsed_time": "1:03:14", "remaining_time": "6:02:06", "throughput": 1502.98, "total_tokens": 5703072} {"current_steps": 27035, "total_steps": 181800, "loss": 0.1226, "lr": 4.963961241671302e-05, "epoch": 2.9741474147414744, "percentage": 14.87, "elapsed_time": "1:03:15", "remaining_time": "6:02:06", "throughput": 1502.97, "total_tokens": 5704064} {"current_steps": 27040, "total_steps": 181800, "loss": 0.0903, "lr": 4.963920625029328e-05, "epoch": 2.9746974697469746, "percentage": 14.87, "elapsed_time": "1:03:15", "remaining_time": "6:02:05", "throughput": 1502.96, "total_tokens": 5705088} {"current_steps": 27045, "total_steps": 181800, "loss": 0.0744, "lr": 4.963879985678581e-05, "epoch": 2.9752475247524752, "percentage": 14.88, "elapsed_time": "1:03:16", "remaining_time": "6:02:04", "throughput": 1502.98, "total_tokens": 5706176} {"current_steps": 27050, "total_steps": 181800, "loss": 0.1576, "lr": 4.963839323619433e-05, "epoch": 2.975797579757976, "percentage": 14.88, "elapsed_time": "1:03:17", "remaining_time": "6:02:03", "throughput": 1502.99, "total_tokens": 5707264} {"current_steps": 27055, "total_steps": 181800, "loss": 0.0775, "lr": 4.9637986388522605e-05, "epoch": 2.976347634763476, "percentage": 14.88, "elapsed_time": "1:03:17", "remaining_time": "6:02:02", "throughput": 1502.98, "total_tokens": 5708256} {"current_steps": 27060, "total_steps": 181800, "loss": 0.0792, "lr": 4.963757931377439e-05, "epoch": 2.976897689768977, "percentage": 14.88, "elapsed_time": "1:03:18", "remaining_time": "6:02:02", "throughput": 1502.99, "total_tokens": 5709344} {"current_steps": 27065, "total_steps": 181800, "loss": 0.0426, "lr": 4.963717201195342e-05, "epoch": 2.9774477447744774, "percentage": 14.89, "elapsed_time": "1:03:19", "remaining_time": "6:02:01", "throughput": 1502.98, "total_tokens": 5710336} {"current_steps": 27070, "total_steps": 181800, "loss": 0.0898, "lr": 4.963676448306346e-05, "epoch": 2.977997799779978, "percentage": 14.89, "elapsed_time": "1:03:20", "remaining_time": "6:02:00", "throughput": 1502.98, "total_tokens": 5711360} {"current_steps": 27075, "total_steps": 181800, "loss": 0.0404, "lr": 4.9636356727108265e-05, "epoch": 2.9785478547854787, "percentage": 14.89, "elapsed_time": "1:03:20", "remaining_time": "6:01:59", "throughput": 1502.99, "total_tokens": 5712416} {"current_steps": 27080, "total_steps": 181800, "loss": 0.1112, "lr": 4.9635948744091585e-05, "epoch": 2.979097909790979, "percentage": 14.9, "elapsed_time": "1:03:21", "remaining_time": "6:01:59", "throughput": 1502.98, "total_tokens": 5713408} {"current_steps": 27085, "total_steps": 181800, "loss": 0.021, "lr": 4.96355405340172e-05, "epoch": 2.9796479647964795, "percentage": 14.9, "elapsed_time": "1:03:22", "remaining_time": "6:01:58", "throughput": 1502.97, "total_tokens": 5714400} {"current_steps": 27090, "total_steps": 181800, "loss": 0.1546, "lr": 4.963513209688885e-05, "epoch": 2.98019801980198, "percentage": 14.9, "elapsed_time": "1:03:22", "remaining_time": "6:01:57", "throughput": 1502.96, "total_tokens": 5715424} {"current_steps": 27095, "total_steps": 181800, "loss": 0.1493, "lr": 4.963472343271031e-05, "epoch": 2.980748074807481, "percentage": 14.9, "elapsed_time": "1:03:23", "remaining_time": "6:01:56", "throughput": 1502.98, "total_tokens": 5716512} {"current_steps": 27100, "total_steps": 181800, "loss": 0.0388, "lr": 4.9634314541485346e-05, "epoch": 2.9812981298129815, "percentage": 14.91, "elapsed_time": "1:03:24", "remaining_time": "6:01:55", "throughput": 1502.97, "total_tokens": 5717536} {"current_steps": 27105, "total_steps": 181800, "loss": 0.0531, "lr": 4.963390542321773e-05, "epoch": 2.9818481848184817, "percentage": 14.91, "elapsed_time": "1:03:24", "remaining_time": "6:01:55", "throughput": 1503.0, "total_tokens": 5718656} {"current_steps": 27110, "total_steps": 181800, "loss": 0.0328, "lr": 4.9633496077911216e-05, "epoch": 2.9823982398239823, "percentage": 14.91, "elapsed_time": "1:03:25", "remaining_time": "6:01:54", "throughput": 1503.01, "total_tokens": 5719744} {"current_steps": 27115, "total_steps": 181800, "loss": 0.0933, "lr": 4.96330865055696e-05, "epoch": 2.982948294829483, "percentage": 14.91, "elapsed_time": "1:03:26", "remaining_time": "6:01:53", "throughput": 1503.01, "total_tokens": 5720800} {"current_steps": 27120, "total_steps": 181800, "loss": 0.0881, "lr": 4.963267670619664e-05, "epoch": 2.9834983498349836, "percentage": 14.92, "elapsed_time": "1:03:26", "remaining_time": "6:01:52", "throughput": 1503.01, "total_tokens": 5721824} {"current_steps": 27125, "total_steps": 181800, "loss": 0.0901, "lr": 4.963226667979612e-05, "epoch": 2.9840484048404843, "percentage": 14.92, "elapsed_time": "1:03:27", "remaining_time": "6:01:52", "throughput": 1503.03, "total_tokens": 5722944} {"current_steps": 27130, "total_steps": 181800, "loss": 0.0119, "lr": 4.9631856426371816e-05, "epoch": 2.9845984598459845, "percentage": 14.92, "elapsed_time": "1:03:28", "remaining_time": "6:01:51", "throughput": 1503.05, "total_tokens": 5724032} {"current_steps": 27135, "total_steps": 181800, "loss": 0.0493, "lr": 4.963144594592751e-05, "epoch": 2.985148514851485, "percentage": 14.93, "elapsed_time": "1:03:28", "remaining_time": "6:01:50", "throughput": 1503.04, "total_tokens": 5725056} {"current_steps": 27140, "total_steps": 181800, "loss": 0.0784, "lr": 4.9631035238467e-05, "epoch": 2.985698569856986, "percentage": 14.93, "elapsed_time": "1:03:29", "remaining_time": "6:01:49", "throughput": 1503.04, "total_tokens": 5726080} {"current_steps": 27145, "total_steps": 181800, "loss": 0.0344, "lr": 4.9630624303994044e-05, "epoch": 2.986248624862486, "percentage": 14.93, "elapsed_time": "1:03:30", "remaining_time": "6:01:48", "throughput": 1503.05, "total_tokens": 5727136} {"current_steps": 27150, "total_steps": 181800, "loss": 0.0544, "lr": 4.9630213142512447e-05, "epoch": 2.9867986798679866, "percentage": 14.93, "elapsed_time": "1:03:31", "remaining_time": "6:01:48", "throughput": 1503.04, "total_tokens": 5728160} {"current_steps": 27155, "total_steps": 181800, "loss": 0.0463, "lr": 4.9629801754025985e-05, "epoch": 2.9873487348734873, "percentage": 14.94, "elapsed_time": "1:03:31", "remaining_time": "6:01:47", "throughput": 1503.04, "total_tokens": 5729184} {"current_steps": 27160, "total_steps": 181800, "loss": 0.1245, "lr": 4.962939013853847e-05, "epoch": 2.987898789878988, "percentage": 14.94, "elapsed_time": "1:03:32", "remaining_time": "6:01:46", "throughput": 1503.03, "total_tokens": 5730208} {"current_steps": 27165, "total_steps": 181800, "loss": 0.0516, "lr": 4.962897829605368e-05, "epoch": 2.9884488448844886, "percentage": 14.94, "elapsed_time": "1:03:33", "remaining_time": "6:01:45", "throughput": 1503.03, "total_tokens": 5731232} {"current_steps": 27170, "total_steps": 181800, "loss": 0.0452, "lr": 4.962856622657541e-05, "epoch": 2.988998899889989, "percentage": 14.94, "elapsed_time": "1:03:33", "remaining_time": "6:01:45", "throughput": 1503.04, "total_tokens": 5732288} {"current_steps": 27175, "total_steps": 181800, "loss": 0.038, "lr": 4.962815393010747e-05, "epoch": 2.9895489548954894, "percentage": 14.95, "elapsed_time": "1:03:34", "remaining_time": "6:01:44", "throughput": 1503.04, "total_tokens": 5733344} {"current_steps": 27180, "total_steps": 181800, "loss": 0.0685, "lr": 4.962774140665366e-05, "epoch": 2.99009900990099, "percentage": 14.95, "elapsed_time": "1:03:35", "remaining_time": "6:01:43", "throughput": 1503.03, "total_tokens": 5734336} {"current_steps": 27185, "total_steps": 181800, "loss": 0.0558, "lr": 4.9627328656217764e-05, "epoch": 2.9906490649064907, "percentage": 14.95, "elapsed_time": "1:03:35", "remaining_time": "6:01:42", "throughput": 1503.04, "total_tokens": 5735424} {"current_steps": 27190, "total_steps": 181800, "loss": 0.0607, "lr": 4.9626915678803597e-05, "epoch": 2.9911991199119914, "percentage": 14.96, "elapsed_time": "1:03:36", "remaining_time": "6:01:42", "throughput": 1503.06, "total_tokens": 5736512} {"current_steps": 27195, "total_steps": 181800, "loss": 0.0357, "lr": 4.962650247441497e-05, "epoch": 2.9917491749174916, "percentage": 14.96, "elapsed_time": "1:03:37", "remaining_time": "6:01:41", "throughput": 1503.05, "total_tokens": 5737536} {"current_steps": 27200, "total_steps": 181800, "loss": 0.1342, "lr": 4.9626089043055687e-05, "epoch": 2.9922992299229922, "percentage": 14.96, "elapsed_time": "1:03:37", "remaining_time": "6:01:40", "throughput": 1503.06, "total_tokens": 5738592} {"current_steps": 27205, "total_steps": 181800, "loss": 0.0418, "lr": 4.9625675384729554e-05, "epoch": 2.992849284928493, "percentage": 14.96, "elapsed_time": "1:03:38", "remaining_time": "6:01:39", "throughput": 1503.07, "total_tokens": 5739648} {"current_steps": 27210, "total_steps": 181800, "loss": 0.1384, "lr": 4.962526149944039e-05, "epoch": 2.9933993399339935, "percentage": 14.97, "elapsed_time": "1:03:39", "remaining_time": "6:01:38", "throughput": 1503.06, "total_tokens": 5740640} {"current_steps": 27215, "total_steps": 181800, "loss": 0.031, "lr": 4.962484738719201e-05, "epoch": 2.993949394939494, "percentage": 14.97, "elapsed_time": "1:03:40", "remaining_time": "6:01:38", "throughput": 1503.07, "total_tokens": 5741728} {"current_steps": 27220, "total_steps": 181800, "loss": 0.0253, "lr": 4.9624433047988214e-05, "epoch": 2.9944994499449944, "percentage": 14.97, "elapsed_time": "1:03:40", "remaining_time": "6:01:37", "throughput": 1503.08, "total_tokens": 5742784} {"current_steps": 27225, "total_steps": 181800, "loss": 0.078, "lr": 4.962401848183285e-05, "epoch": 2.995049504950495, "percentage": 14.98, "elapsed_time": "1:03:41", "remaining_time": "6:01:36", "throughput": 1503.09, "total_tokens": 5743872} {"current_steps": 27230, "total_steps": 181800, "loss": 0.0525, "lr": 4.962360368872972e-05, "epoch": 2.9955995599559957, "percentage": 14.98, "elapsed_time": "1:03:42", "remaining_time": "6:01:35", "throughput": 1503.1, "total_tokens": 5744928} {"current_steps": 27235, "total_steps": 181800, "loss": 0.0404, "lr": 4.962318866868265e-05, "epoch": 2.996149614961496, "percentage": 14.98, "elapsed_time": "1:03:42", "remaining_time": "6:01:34", "throughput": 1503.1, "total_tokens": 5745984} {"current_steps": 27240, "total_steps": 181800, "loss": 0.0307, "lr": 4.962277342169546e-05, "epoch": 2.9966996699669965, "percentage": 14.98, "elapsed_time": "1:03:43", "remaining_time": "6:01:34", "throughput": 1503.11, "total_tokens": 5747040} {"current_steps": 27245, "total_steps": 181800, "loss": 0.0662, "lr": 4.962235794777199e-05, "epoch": 2.997249724972497, "percentage": 14.99, "elapsed_time": "1:03:44", "remaining_time": "6:01:33", "throughput": 1503.11, "total_tokens": 5748064} {"current_steps": 27250, "total_steps": 181800, "loss": 0.0255, "lr": 4.962194224691606e-05, "epoch": 2.997799779977998, "percentage": 14.99, "elapsed_time": "1:03:44", "remaining_time": "6:01:32", "throughput": 1503.11, "total_tokens": 5749120} {"current_steps": 27255, "total_steps": 181800, "loss": 0.0804, "lr": 4.96215263191315e-05, "epoch": 2.9983498349834985, "percentage": 14.99, "elapsed_time": "1:03:45", "remaining_time": "6:01:31", "throughput": 1503.11, "total_tokens": 5750176} {"current_steps": 27260, "total_steps": 181800, "loss": 0.0567, "lr": 4.9621110164422145e-05, "epoch": 2.9988998899889987, "percentage": 14.99, "elapsed_time": "1:03:46", "remaining_time": "6:01:31", "throughput": 1503.12, "total_tokens": 5751232} {"current_steps": 27265, "total_steps": 181800, "loss": 0.0275, "lr": 4.962069378279184e-05, "epoch": 2.9994499449944994, "percentage": 15.0, "elapsed_time": "1:03:46", "remaining_time": "6:01:30", "throughput": 1503.11, "total_tokens": 5752256} {"current_steps": 27270, "total_steps": 181800, "loss": 0.0395, "lr": 4.962027717424441e-05, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "1:03:47", "remaining_time": "6:01:29", "throughput": 1503.06, "total_tokens": 5753152} {"current_steps": 27270, "total_steps": 181800, "eval_loss": 0.07973591983318329, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "1:04:24", "remaining_time": "6:04:59", "throughput": 1488.66, "total_tokens": 5753152} {"current_steps": 27275, "total_steps": 181800, "loss": 0.0387, "lr": 4.9619860338783695e-05, "epoch": 3.0005500550055006, "percentage": 15.0, "elapsed_time": "1:04:26", "remaining_time": "6:05:04", "throughput": 1488.25, "total_tokens": 5754176} {"current_steps": 27280, "total_steps": 181800, "loss": 0.0607, "lr": 4.961944327641355e-05, "epoch": 3.0011001100110013, "percentage": 15.01, "elapsed_time": "1:04:27", "remaining_time": "6:05:04", "throughput": 1488.26, "total_tokens": 5755232} {"current_steps": 27285, "total_steps": 181800, "loss": 0.0206, "lr": 4.96190259871378e-05, "epoch": 3.0016501650165015, "percentage": 15.01, "elapsed_time": "1:04:27", "remaining_time": "6:05:03", "throughput": 1488.29, "total_tokens": 5756384} {"current_steps": 27290, "total_steps": 181800, "loss": 0.034, "lr": 4.96186084709603e-05, "epoch": 3.002200220022002, "percentage": 15.01, "elapsed_time": "1:04:28", "remaining_time": "6:05:02", "throughput": 1488.31, "total_tokens": 5757504} {"current_steps": 27295, "total_steps": 181800, "loss": 0.0389, "lr": 4.961819072788491e-05, "epoch": 3.002750275027503, "percentage": 15.01, "elapsed_time": "1:04:29", "remaining_time": "6:05:01", "throughput": 1488.33, "total_tokens": 5758624} {"current_steps": 27300, "total_steps": 181800, "loss": 0.0144, "lr": 4.961777275791546e-05, "epoch": 3.0033003300330035, "percentage": 15.02, "elapsed_time": "1:04:29", "remaining_time": "6:05:01", "throughput": 1488.34, "total_tokens": 5759712} {"current_steps": 27305, "total_steps": 181800, "loss": 0.1227, "lr": 4.961735456105582e-05, "epoch": 3.0038503850385037, "percentage": 15.02, "elapsed_time": "1:04:30", "remaining_time": "6:05:01", "throughput": 1488.25, "total_tokens": 5760768} {"current_steps": 27310, "total_steps": 181800, "loss": 0.0155, "lr": 4.961693613730983e-05, "epoch": 3.0044004400440043, "percentage": 15.02, "elapsed_time": "1:04:31", "remaining_time": "6:05:01", "throughput": 1488.27, "total_tokens": 5761920} {"current_steps": 27315, "total_steps": 181800, "loss": 0.118, "lr": 4.961651748668135e-05, "epoch": 3.004950495049505, "percentage": 15.02, "elapsed_time": "1:04:32", "remaining_time": "6:05:00", "throughput": 1488.24, "total_tokens": 5763008} {"current_steps": 27320, "total_steps": 181800, "loss": 0.0444, "lr": 4.9616098609174246e-05, "epoch": 3.0055005500550056, "percentage": 15.03, "elapsed_time": "1:04:33", "remaining_time": "6:05:00", "throughput": 1488.25, "total_tokens": 5764096} {"current_steps": 27325, "total_steps": 181800, "loss": 0.1804, "lr": 4.9615679504792364e-05, "epoch": 3.0060506050605063, "percentage": 15.03, "elapsed_time": "1:04:33", "remaining_time": "6:04:59", "throughput": 1488.27, "total_tokens": 5765216} {"current_steps": 27330, "total_steps": 181800, "loss": 0.0067, "lr": 4.961526017353958e-05, "epoch": 3.0066006600660065, "percentage": 15.03, "elapsed_time": "1:04:34", "remaining_time": "6:04:58", "throughput": 1488.3, "total_tokens": 5766336} {"current_steps": 27335, "total_steps": 181800, "loss": 0.107, "lr": 4.961484061541976e-05, "epoch": 3.007150715071507, "percentage": 15.04, "elapsed_time": "1:04:35", "remaining_time": "6:04:57", "throughput": 1488.29, "total_tokens": 5767360} {"current_steps": 27340, "total_steps": 181800, "loss": 0.0982, "lr": 4.961442083043676e-05, "epoch": 3.0077007700770078, "percentage": 15.04, "elapsed_time": "1:04:35", "remaining_time": "6:04:56", "throughput": 1488.32, "total_tokens": 5768480} {"current_steps": 27345, "total_steps": 181800, "loss": 0.0932, "lr": 4.9614000818594456e-05, "epoch": 3.0082508250825084, "percentage": 15.04, "elapsed_time": "1:04:36", "remaining_time": "6:04:56", "throughput": 1488.31, "total_tokens": 5769504} {"current_steps": 27350, "total_steps": 181800, "loss": 0.0372, "lr": 4.961358057989672e-05, "epoch": 3.0088008800880086, "percentage": 15.04, "elapsed_time": "1:04:37", "remaining_time": "6:04:55", "throughput": 1488.34, "total_tokens": 5770624} {"current_steps": 27355, "total_steps": 181800, "loss": 0.1357, "lr": 4.961316011434742e-05, "epoch": 3.0093509350935093, "percentage": 15.05, "elapsed_time": "1:04:37", "remaining_time": "6:04:54", "throughput": 1488.34, "total_tokens": 5771648} {"current_steps": 27360, "total_steps": 181800, "loss": 0.1483, "lr": 4.9612739421950425e-05, "epoch": 3.00990099009901, "percentage": 15.05, "elapsed_time": "1:04:38", "remaining_time": "6:04:53", "throughput": 1488.33, "total_tokens": 5772672} {"current_steps": 27365, "total_steps": 181800, "loss": 0.1967, "lr": 4.961231850270963e-05, "epoch": 3.0104510451045106, "percentage": 15.05, "elapsed_time": "1:04:39", "remaining_time": "6:04:52", "throughput": 1488.33, "total_tokens": 5773696} {"current_steps": 27370, "total_steps": 181800, "loss": 0.1124, "lr": 4.9611897356628915e-05, "epoch": 3.011001100110011, "percentage": 15.06, "elapsed_time": "1:04:39", "remaining_time": "6:04:52", "throughput": 1488.36, "total_tokens": 5774848} {"current_steps": 27375, "total_steps": 181800, "loss": 0.0186, "lr": 4.961147598371214e-05, "epoch": 3.0115511551155114, "percentage": 15.06, "elapsed_time": "1:04:40", "remaining_time": "6:04:51", "throughput": 1488.38, "total_tokens": 5775936} {"current_steps": 27380, "total_steps": 181800, "loss": 0.0303, "lr": 4.96110543839632e-05, "epoch": 3.012101210121012, "percentage": 15.06, "elapsed_time": "1:04:41", "remaining_time": "6:04:50", "throughput": 1488.38, "total_tokens": 5776960} {"current_steps": 27385, "total_steps": 181800, "loss": 0.1004, "lr": 4.961063255738598e-05, "epoch": 3.0126512651265127, "percentage": 15.06, "elapsed_time": "1:04:42", "remaining_time": "6:04:49", "throughput": 1488.37, "total_tokens": 5777984} {"current_steps": 27390, "total_steps": 181800, "loss": 0.0692, "lr": 4.9610210503984375e-05, "epoch": 3.0132013201320134, "percentage": 15.07, "elapsed_time": "1:04:42", "remaining_time": "6:04:48", "throughput": 1488.38, "total_tokens": 5779040} {"current_steps": 27395, "total_steps": 181800, "loss": 0.1187, "lr": 4.960978822376227e-05, "epoch": 3.0137513751375136, "percentage": 15.07, "elapsed_time": "1:04:43", "remaining_time": "6:04:48", "throughput": 1488.39, "total_tokens": 5780128} {"current_steps": 27400, "total_steps": 181800, "loss": 0.0383, "lr": 4.9609365716723546e-05, "epoch": 3.014301430143014, "percentage": 15.07, "elapsed_time": "1:04:44", "remaining_time": "6:04:47", "throughput": 1488.41, "total_tokens": 5781216} {"current_steps": 27405, "total_steps": 181800, "loss": 0.057, "lr": 4.960894298287212e-05, "epoch": 3.014851485148515, "percentage": 15.07, "elapsed_time": "1:04:44", "remaining_time": "6:04:46", "throughput": 1488.43, "total_tokens": 5782336} {"current_steps": 27410, "total_steps": 181800, "loss": 0.0548, "lr": 4.9608520022211866e-05, "epoch": 3.0154015401540155, "percentage": 15.08, "elapsed_time": "1:04:45", "remaining_time": "6:04:45", "throughput": 1488.43, "total_tokens": 5783360} {"current_steps": 27415, "total_steps": 181800, "loss": 0.0262, "lr": 4.96080968347467e-05, "epoch": 3.015951595159516, "percentage": 15.08, "elapsed_time": "1:04:46", "remaining_time": "6:04:44", "throughput": 1488.42, "total_tokens": 5784352} {"current_steps": 27420, "total_steps": 181800, "loss": 0.0332, "lr": 4.9607673420480507e-05, "epoch": 3.0165016501650164, "percentage": 15.08, "elapsed_time": "1:04:46", "remaining_time": "6:04:44", "throughput": 1488.44, "total_tokens": 5785440} {"current_steps": 27425, "total_steps": 181800, "loss": 0.1057, "lr": 4.960724977941719e-05, "epoch": 3.017051705170517, "percentage": 15.09, "elapsed_time": "1:04:47", "remaining_time": "6:04:43", "throughput": 1488.45, "total_tokens": 5786528} {"current_steps": 27430, "total_steps": 181800, "loss": 0.0235, "lr": 4.9606825911560665e-05, "epoch": 3.0176017601760177, "percentage": 15.09, "elapsed_time": "1:04:48", "remaining_time": "6:04:42", "throughput": 1488.46, "total_tokens": 5787584} {"current_steps": 27435, "total_steps": 181800, "loss": 0.0347, "lr": 4.960640181691484e-05, "epoch": 3.0181518151815183, "percentage": 15.09, "elapsed_time": "1:04:48", "remaining_time": "6:04:41", "throughput": 1488.48, "total_tokens": 5788704} {"current_steps": 27440, "total_steps": 181800, "loss": 0.1231, "lr": 4.960597749548361e-05, "epoch": 3.0187018701870185, "percentage": 15.09, "elapsed_time": "1:04:49", "remaining_time": "6:04:40", "throughput": 1488.49, "total_tokens": 5789760} {"current_steps": 27445, "total_steps": 181800, "loss": 0.1666, "lr": 4.9605552947270894e-05, "epoch": 3.019251925192519, "percentage": 15.1, "elapsed_time": "1:04:50", "remaining_time": "6:04:40", "throughput": 1488.49, "total_tokens": 5790784} {"current_steps": 27450, "total_steps": 181800, "loss": 0.094, "lr": 4.96051281722806e-05, "epoch": 3.01980198019802, "percentage": 15.1, "elapsed_time": "1:04:51", "remaining_time": "6:04:39", "throughput": 1488.49, "total_tokens": 5791808} {"current_steps": 27455, "total_steps": 181800, "loss": 0.0523, "lr": 4.960470317051665e-05, "epoch": 3.0203520352035205, "percentage": 15.1, "elapsed_time": "1:04:51", "remaining_time": "6:04:38", "throughput": 1488.5, "total_tokens": 5792896} {"current_steps": 27460, "total_steps": 181800, "loss": 0.0319, "lr": 4.9604277941982955e-05, "epoch": 3.020902090209021, "percentage": 15.1, "elapsed_time": "1:04:52", "remaining_time": "6:04:37", "throughput": 1488.49, "total_tokens": 5793888} {"current_steps": 27465, "total_steps": 181800, "loss": 0.1036, "lr": 4.960385248668344e-05, "epoch": 3.0214521452145213, "percentage": 15.11, "elapsed_time": "1:04:53", "remaining_time": "6:04:36", "throughput": 1488.51, "total_tokens": 5794976} {"current_steps": 27470, "total_steps": 181800, "loss": 0.031, "lr": 4.960342680462202e-05, "epoch": 3.022002200220022, "percentage": 15.11, "elapsed_time": "1:04:53", "remaining_time": "6:04:35", "throughput": 1488.5, "total_tokens": 5795968} {"current_steps": 27475, "total_steps": 181800, "loss": 0.1098, "lr": 4.9603000895802623e-05, "epoch": 3.0225522552255226, "percentage": 15.11, "elapsed_time": "1:04:54", "remaining_time": "6:04:35", "throughput": 1488.52, "total_tokens": 5797056} {"current_steps": 27480, "total_steps": 181800, "loss": 0.0556, "lr": 4.960257476022917e-05, "epoch": 3.0231023102310233, "percentage": 15.12, "elapsed_time": "1:04:55", "remaining_time": "6:04:34", "throughput": 1488.52, "total_tokens": 5798080} {"current_steps": 27485, "total_steps": 181800, "loss": 0.0312, "lr": 4.960214839790559e-05, "epoch": 3.0236523652365235, "percentage": 15.12, "elapsed_time": "1:04:55", "remaining_time": "6:04:33", "throughput": 1488.52, "total_tokens": 5799104} {"current_steps": 27490, "total_steps": 181800, "loss": 0.0335, "lr": 4.9601721808835814e-05, "epoch": 3.024202420242024, "percentage": 15.12, "elapsed_time": "1:04:56", "remaining_time": "6:04:32", "throughput": 1488.53, "total_tokens": 5800160} {"current_steps": 27495, "total_steps": 181800, "loss": 0.0542, "lr": 4.960129499302377e-05, "epoch": 3.0247524752475248, "percentage": 15.12, "elapsed_time": "1:04:57", "remaining_time": "6:04:31", "throughput": 1488.55, "total_tokens": 5801280} {"current_steps": 27500, "total_steps": 181800, "loss": 0.0625, "lr": 4.960086795047341e-05, "epoch": 3.0253025302530254, "percentage": 15.13, "elapsed_time": "1:04:57", "remaining_time": "6:04:31", "throughput": 1488.56, "total_tokens": 5802336} {"current_steps": 27505, "total_steps": 181800, "loss": 0.0068, "lr": 4.960044068118864e-05, "epoch": 3.0258525852585256, "percentage": 15.13, "elapsed_time": "1:04:58", "remaining_time": "6:04:30", "throughput": 1488.58, "total_tokens": 5803456} {"current_steps": 27510, "total_steps": 181800, "loss": 0.0748, "lr": 4.960001318517342e-05, "epoch": 3.0264026402640263, "percentage": 15.13, "elapsed_time": "1:04:59", "remaining_time": "6:04:29", "throughput": 1488.58, "total_tokens": 5804480} {"current_steps": 27515, "total_steps": 181800, "loss": 0.0841, "lr": 4.959958546243167e-05, "epoch": 3.026952695269527, "percentage": 15.13, "elapsed_time": "1:05:00", "remaining_time": "6:04:28", "throughput": 1488.59, "total_tokens": 5805536} {"current_steps": 27520, "total_steps": 181800, "loss": 0.0777, "lr": 4.959915751296736e-05, "epoch": 3.0275027502750276, "percentage": 15.14, "elapsed_time": "1:05:00", "remaining_time": "6:04:27", "throughput": 1488.59, "total_tokens": 5806560} {"current_steps": 27525, "total_steps": 181800, "loss": 0.0245, "lr": 4.959872933678441e-05, "epoch": 3.0280528052805282, "percentage": 15.14, "elapsed_time": "1:05:01", "remaining_time": "6:04:26", "throughput": 1488.59, "total_tokens": 5807584} {"current_steps": 27530, "total_steps": 181800, "loss": 0.0428, "lr": 4.959830093388678e-05, "epoch": 3.0286028602860284, "percentage": 15.14, "elapsed_time": "1:05:02", "remaining_time": "6:04:26", "throughput": 1488.61, "total_tokens": 5808672} {"current_steps": 27535, "total_steps": 181800, "loss": 0.0286, "lr": 4.959787230427842e-05, "epoch": 3.029152915291529, "percentage": 15.15, "elapsed_time": "1:05:02", "remaining_time": "6:04:25", "throughput": 1488.62, "total_tokens": 5809728} {"current_steps": 27540, "total_steps": 181800, "loss": 0.1415, "lr": 4.959744344796326e-05, "epoch": 3.0297029702970297, "percentage": 15.15, "elapsed_time": "1:05:03", "remaining_time": "6:04:24", "throughput": 1488.61, "total_tokens": 5810720} {"current_steps": 27545, "total_steps": 181800, "loss": 0.1026, "lr": 4.959701436494527e-05, "epoch": 3.0302530253025304, "percentage": 15.15, "elapsed_time": "1:05:04", "remaining_time": "6:04:23", "throughput": 1488.63, "total_tokens": 5811808} {"current_steps": 27550, "total_steps": 181800, "loss": 0.0537, "lr": 4.959658505522841e-05, "epoch": 3.0308030803080306, "percentage": 15.15, "elapsed_time": "1:05:04", "remaining_time": "6:04:22", "throughput": 1488.63, "total_tokens": 5812864} {"current_steps": 27555, "total_steps": 181800, "loss": 0.0346, "lr": 4.959615551881662e-05, "epoch": 3.0313531353135312, "percentage": 15.16, "elapsed_time": "1:05:05", "remaining_time": "6:04:21", "throughput": 1488.63, "total_tokens": 5813856} {"current_steps": 27560, "total_steps": 181800, "loss": 0.0529, "lr": 4.9595725755713877e-05, "epoch": 3.031903190319032, "percentage": 15.16, "elapsed_time": "1:05:06", "remaining_time": "6:04:21", "throughput": 1488.66, "total_tokens": 5815008} {"current_steps": 27565, "total_steps": 181800, "loss": 0.0479, "lr": 4.9595295765924124e-05, "epoch": 3.0324532453245325, "percentage": 15.16, "elapsed_time": "1:05:06", "remaining_time": "6:04:20", "throughput": 1488.69, "total_tokens": 5816160} {"current_steps": 27570, "total_steps": 181800, "loss": 0.1833, "lr": 4.959486554945133e-05, "epoch": 3.033003300330033, "percentage": 15.17, "elapsed_time": "1:05:07", "remaining_time": "6:04:19", "throughput": 1488.72, "total_tokens": 5817280} {"current_steps": 27575, "total_steps": 181800, "loss": 0.0655, "lr": 4.959443510629947e-05, "epoch": 3.0335533553355334, "percentage": 15.17, "elapsed_time": "1:05:08", "remaining_time": "6:04:18", "throughput": 1488.72, "total_tokens": 5818304} {"current_steps": 27580, "total_steps": 181800, "loss": 0.0395, "lr": 4.959400443647249e-05, "epoch": 3.034103410341034, "percentage": 15.17, "elapsed_time": "1:05:08", "remaining_time": "6:04:17", "throughput": 1488.72, "total_tokens": 5819328} {"current_steps": 27585, "total_steps": 181800, "loss": 0.0915, "lr": 4.959357353997438e-05, "epoch": 3.0346534653465347, "percentage": 15.17, "elapsed_time": "1:05:09", "remaining_time": "6:04:16", "throughput": 1488.73, "total_tokens": 5820384} {"current_steps": 27590, "total_steps": 181800, "loss": 0.0821, "lr": 4.9593142416809104e-05, "epoch": 3.0352035203520353, "percentage": 15.18, "elapsed_time": "1:05:10", "remaining_time": "6:04:16", "throughput": 1488.74, "total_tokens": 5821440} {"current_steps": 27595, "total_steps": 181800, "loss": 0.062, "lr": 4.9592711066980635e-05, "epoch": 3.0357535753575355, "percentage": 15.18, "elapsed_time": "1:05:11", "remaining_time": "6:04:15", "throughput": 1488.76, "total_tokens": 5822560} {"current_steps": 27600, "total_steps": 181800, "loss": 0.2575, "lr": 4.959227949049295e-05, "epoch": 3.036303630363036, "percentage": 15.18, "elapsed_time": "1:05:11", "remaining_time": "6:04:14", "throughput": 1488.79, "total_tokens": 5823680} {"current_steps": 27605, "total_steps": 181800, "loss": 0.049, "lr": 4.959184768735002e-05, "epoch": 3.036853685368537, "percentage": 15.18, "elapsed_time": "1:05:12", "remaining_time": "6:04:13", "throughput": 1488.79, "total_tokens": 5824736} {"current_steps": 27610, "total_steps": 181800, "loss": 0.0901, "lr": 4.959141565755584e-05, "epoch": 3.0374037403740375, "percentage": 15.19, "elapsed_time": "1:05:13", "remaining_time": "6:04:12", "throughput": 1488.8, "total_tokens": 5825792} {"current_steps": 27615, "total_steps": 181800, "loss": 0.0468, "lr": 4.959098340111438e-05, "epoch": 3.037953795379538, "percentage": 15.19, "elapsed_time": "1:05:13", "remaining_time": "6:04:12", "throughput": 1488.8, "total_tokens": 5826816} {"current_steps": 27620, "total_steps": 181800, "loss": 0.0095, "lr": 4.959055091802962e-05, "epoch": 3.0385038503850383, "percentage": 15.19, "elapsed_time": "1:05:14", "remaining_time": "6:04:11", "throughput": 1488.82, "total_tokens": 5827904} {"current_steps": 27625, "total_steps": 181800, "loss": 0.0444, "lr": 4.9590118208305555e-05, "epoch": 3.039053905390539, "percentage": 15.2, "elapsed_time": "1:05:15", "remaining_time": "6:04:10", "throughput": 1488.82, "total_tokens": 5828928} {"current_steps": 27630, "total_steps": 181800, "loss": 0.068, "lr": 4.9589685271946165e-05, "epoch": 3.0396039603960396, "percentage": 15.2, "elapsed_time": "1:05:15", "remaining_time": "6:04:09", "throughput": 1488.82, "total_tokens": 5829952} {"current_steps": 27635, "total_steps": 181800, "loss": 0.1055, "lr": 4.958925210895545e-05, "epoch": 3.0401540154015403, "percentage": 15.2, "elapsed_time": "1:05:16", "remaining_time": "6:04:08", "throughput": 1488.84, "total_tokens": 5831072} {"current_steps": 27640, "total_steps": 181800, "loss": 0.034, "lr": 4.95888187193374e-05, "epoch": 3.0407040704070405, "percentage": 15.2, "elapsed_time": "1:05:17", "remaining_time": "6:04:07", "throughput": 1488.85, "total_tokens": 5832128} {"current_steps": 27645, "total_steps": 181800, "loss": 0.024, "lr": 4.9588385103096005e-05, "epoch": 3.041254125412541, "percentage": 15.21, "elapsed_time": "1:05:17", "remaining_time": "6:04:07", "throughput": 1488.87, "total_tokens": 5833248} {"current_steps": 27650, "total_steps": 181800, "loss": 0.1324, "lr": 4.958795126023526e-05, "epoch": 3.041804180418042, "percentage": 15.21, "elapsed_time": "1:05:18", "remaining_time": "6:04:06", "throughput": 1488.88, "total_tokens": 5834304} {"current_steps": 27655, "total_steps": 181800, "loss": 0.0314, "lr": 4.958751719075917e-05, "epoch": 3.0423542354235424, "percentage": 15.21, "elapsed_time": "1:05:19", "remaining_time": "6:04:05", "throughput": 1488.88, "total_tokens": 5835328} {"current_steps": 27660, "total_steps": 181800, "loss": 0.1862, "lr": 4.958708289467173e-05, "epoch": 3.042904290429043, "percentage": 15.21, "elapsed_time": "1:05:19", "remaining_time": "6:04:04", "throughput": 1488.88, "total_tokens": 5836352} {"current_steps": 27665, "total_steps": 181800, "loss": 0.1177, "lr": 4.9586648371976947e-05, "epoch": 3.0434543454345433, "percentage": 15.22, "elapsed_time": "1:05:20", "remaining_time": "6:04:03", "throughput": 1488.9, "total_tokens": 5837440} {"current_steps": 27670, "total_steps": 181800, "loss": 0.0729, "lr": 4.958621362267882e-05, "epoch": 3.044004400440044, "percentage": 15.22, "elapsed_time": "1:05:21", "remaining_time": "6:04:02", "throughput": 1488.89, "total_tokens": 5838432} {"current_steps": 27675, "total_steps": 181800, "loss": 0.1184, "lr": 4.9585778646781364e-05, "epoch": 3.0445544554455446, "percentage": 15.22, "elapsed_time": "1:05:22", "remaining_time": "6:04:02", "throughput": 1488.91, "total_tokens": 5839520} {"current_steps": 27680, "total_steps": 181800, "loss": 0.0395, "lr": 4.958534344428858e-05, "epoch": 3.0451045104510452, "percentage": 15.23, "elapsed_time": "1:05:22", "remaining_time": "6:04:01", "throughput": 1488.92, "total_tokens": 5840576} {"current_steps": 27685, "total_steps": 181800, "loss": 0.0494, "lr": 4.958490801520449e-05, "epoch": 3.0456545654565454, "percentage": 15.23, "elapsed_time": "1:05:23", "remaining_time": "6:04:00", "throughput": 1488.91, "total_tokens": 5841568} {"current_steps": 27690, "total_steps": 181800, "loss": 0.0397, "lr": 4.95844723595331e-05, "epoch": 3.046204620462046, "percentage": 15.23, "elapsed_time": "1:05:24", "remaining_time": "6:03:59", "throughput": 1488.92, "total_tokens": 5842624} {"current_steps": 27695, "total_steps": 181800, "loss": 0.1071, "lr": 4.958403647727841e-05, "epoch": 3.0467546754675467, "percentage": 15.23, "elapsed_time": "1:05:24", "remaining_time": "6:03:58", "throughput": 1488.94, "total_tokens": 5843712} {"current_steps": 27700, "total_steps": 181800, "loss": 0.0613, "lr": 4.958360036844446e-05, "epoch": 3.0473047304730474, "percentage": 15.24, "elapsed_time": "1:05:25", "remaining_time": "6:03:57", "throughput": 1488.96, "total_tokens": 5844832} {"current_steps": 27705, "total_steps": 181800, "loss": 0.2558, "lr": 4.9583164033035266e-05, "epoch": 3.047854785478548, "percentage": 15.24, "elapsed_time": "1:05:26", "remaining_time": "6:03:57", "throughput": 1488.99, "total_tokens": 5845952} {"current_steps": 27710, "total_steps": 181800, "loss": 0.0985, "lr": 4.9582727471054845e-05, "epoch": 3.0484048404840483, "percentage": 15.24, "elapsed_time": "1:05:26", "remaining_time": "6:03:56", "throughput": 1488.98, "total_tokens": 5846976} {"current_steps": 27715, "total_steps": 181800, "loss": 0.023, "lr": 4.958229068250721e-05, "epoch": 3.048954895489549, "percentage": 15.24, "elapsed_time": "1:05:27", "remaining_time": "6:03:55", "throughput": 1488.99, "total_tokens": 5848032} {"current_steps": 27720, "total_steps": 181800, "loss": 0.0436, "lr": 4.9581853667396414e-05, "epoch": 3.0495049504950495, "percentage": 15.25, "elapsed_time": "1:05:28", "remaining_time": "6:03:54", "throughput": 1489.01, "total_tokens": 5849120} {"current_steps": 27725, "total_steps": 181800, "loss": 0.1164, "lr": 4.9581416425726454e-05, "epoch": 3.05005500550055, "percentage": 15.25, "elapsed_time": "1:05:28", "remaining_time": "6:03:53", "throughput": 1489.0, "total_tokens": 5850112} {"current_steps": 27730, "total_steps": 181800, "loss": 0.025, "lr": 4.958097895750139e-05, "epoch": 3.0506050605060504, "percentage": 15.25, "elapsed_time": "1:05:29", "remaining_time": "6:03:53", "throughput": 1489.01, "total_tokens": 5851200} {"current_steps": 27735, "total_steps": 181800, "loss": 0.0741, "lr": 4.958054126272522e-05, "epoch": 3.051155115511551, "percentage": 15.26, "elapsed_time": "1:05:30", "remaining_time": "6:03:52", "throughput": 1489.01, "total_tokens": 5852224} {"current_steps": 27740, "total_steps": 181800, "loss": 0.0789, "lr": 4.958010334140201e-05, "epoch": 3.0517051705170517, "percentage": 15.26, "elapsed_time": "1:05:30", "remaining_time": "6:03:51", "throughput": 1489.02, "total_tokens": 5853280} {"current_steps": 27745, "total_steps": 181800, "loss": 0.0455, "lr": 4.957966519353577e-05, "epoch": 3.0522552255225524, "percentage": 15.26, "elapsed_time": "1:05:31", "remaining_time": "6:03:50", "throughput": 1489.04, "total_tokens": 5854368} {"current_steps": 27750, "total_steps": 181800, "loss": 0.0659, "lr": 4.957922681913056e-05, "epoch": 3.052805280528053, "percentage": 15.26, "elapsed_time": "1:05:32", "remaining_time": "6:03:49", "throughput": 1489.04, "total_tokens": 5855392} {"current_steps": 27755, "total_steps": 181800, "loss": 0.0642, "lr": 4.9578788218190416e-05, "epoch": 3.053355335533553, "percentage": 15.27, "elapsed_time": "1:05:33", "remaining_time": "6:03:48", "throughput": 1489.03, "total_tokens": 5856384} {"current_steps": 27760, "total_steps": 181800, "loss": 0.0253, "lr": 4.9578349390719365e-05, "epoch": 3.053905390539054, "percentage": 15.27, "elapsed_time": "1:05:33", "remaining_time": "6:03:48", "throughput": 1489.03, "total_tokens": 5857408} {"current_steps": 27765, "total_steps": 181800, "loss": 0.0558, "lr": 4.957791033672146e-05, "epoch": 3.0544554455445545, "percentage": 15.27, "elapsed_time": "1:05:34", "remaining_time": "6:03:47", "throughput": 1489.04, "total_tokens": 5858464} {"current_steps": 27770, "total_steps": 181800, "loss": 0.0865, "lr": 4.957747105620075e-05, "epoch": 3.055005500550055, "percentage": 15.28, "elapsed_time": "1:05:35", "remaining_time": "6:03:46", "throughput": 1489.04, "total_tokens": 5859520} {"current_steps": 27775, "total_steps": 181800, "loss": 0.0624, "lr": 4.957703154916129e-05, "epoch": 3.0555555555555554, "percentage": 15.28, "elapsed_time": "1:05:35", "remaining_time": "6:03:45", "throughput": 1489.05, "total_tokens": 5860576} {"current_steps": 27780, "total_steps": 181800, "loss": 0.0916, "lr": 4.957659181560712e-05, "epoch": 3.056105610561056, "percentage": 15.28, "elapsed_time": "1:05:36", "remaining_time": "6:03:44", "throughput": 1489.06, "total_tokens": 5861632} {"current_steps": 27785, "total_steps": 181800, "loss": 0.0199, "lr": 4.9576151855542295e-05, "epoch": 3.0566556655665567, "percentage": 15.28, "elapsed_time": "1:05:37", "remaining_time": "6:03:44", "throughput": 1489.06, "total_tokens": 5862656} {"current_steps": 27790, "total_steps": 181800, "loss": 0.0693, "lr": 4.957571166897087e-05, "epoch": 3.0572057205720573, "percentage": 15.29, "elapsed_time": "1:05:37", "remaining_time": "6:03:43", "throughput": 1489.07, "total_tokens": 5863712} {"current_steps": 27795, "total_steps": 181800, "loss": 0.125, "lr": 4.957527125589691e-05, "epoch": 3.057755775577558, "percentage": 15.29, "elapsed_time": "1:05:38", "remaining_time": "6:03:42", "throughput": 1489.06, "total_tokens": 5864704} {"current_steps": 27800, "total_steps": 181800, "loss": 0.1394, "lr": 4.957483061632445e-05, "epoch": 3.058305830583058, "percentage": 15.29, "elapsed_time": "1:05:39", "remaining_time": "6:03:41", "throughput": 1489.06, "total_tokens": 5865728} {"current_steps": 27805, "total_steps": 181800, "loss": 0.0721, "lr": 4.957438975025759e-05, "epoch": 3.058855885588559, "percentage": 15.29, "elapsed_time": "1:05:39", "remaining_time": "6:03:40", "throughput": 1489.06, "total_tokens": 5866752} {"current_steps": 27810, "total_steps": 181800, "loss": 0.0791, "lr": 4.9573948657700356e-05, "epoch": 3.0594059405940595, "percentage": 15.3, "elapsed_time": "1:05:40", "remaining_time": "6:03:39", "throughput": 1489.07, "total_tokens": 5867808} {"current_steps": 27815, "total_steps": 181800, "loss": 0.038, "lr": 4.957350733865683e-05, "epoch": 3.05995599559956, "percentage": 15.3, "elapsed_time": "1:05:41", "remaining_time": "6:03:39", "throughput": 1489.07, "total_tokens": 5868832} {"current_steps": 27820, "total_steps": 181800, "loss": 0.0332, "lr": 4.957306579313109e-05, "epoch": 3.0605060506050603, "percentage": 15.3, "elapsed_time": "1:05:41", "remaining_time": "6:03:38", "throughput": 1489.07, "total_tokens": 5869856} {"current_steps": 27825, "total_steps": 181800, "loss": 0.0396, "lr": 4.957262402112718e-05, "epoch": 3.061056105610561, "percentage": 15.31, "elapsed_time": "1:05:42", "remaining_time": "6:03:37", "throughput": 1489.09, "total_tokens": 5870944} {"current_steps": 27830, "total_steps": 181800, "loss": 0.0775, "lr": 4.95721820226492e-05, "epoch": 3.0616061606160616, "percentage": 15.31, "elapsed_time": "1:05:43", "remaining_time": "6:03:36", "throughput": 1489.1, "total_tokens": 5872000} {"current_steps": 27835, "total_steps": 181800, "loss": 0.1335, "lr": 4.95717397977012e-05, "epoch": 3.0621562156215623, "percentage": 15.31, "elapsed_time": "1:05:44", "remaining_time": "6:03:35", "throughput": 1489.12, "total_tokens": 5873120} {"current_steps": 27840, "total_steps": 181800, "loss": 0.0131, "lr": 4.957129734628726e-05, "epoch": 3.062706270627063, "percentage": 15.31, "elapsed_time": "1:05:44", "remaining_time": "6:03:34", "throughput": 1489.12, "total_tokens": 5874144} {"current_steps": 27845, "total_steps": 181800, "loss": 0.0949, "lr": 4.957085466841147e-05, "epoch": 3.063256325632563, "percentage": 15.32, "elapsed_time": "1:05:45", "remaining_time": "6:03:34", "throughput": 1489.14, "total_tokens": 5875232} {"current_steps": 27850, "total_steps": 181800, "loss": 0.0761, "lr": 4.957041176407791e-05, "epoch": 3.0638063806380638, "percentage": 15.32, "elapsed_time": "1:05:46", "remaining_time": "6:03:33", "throughput": 1489.14, "total_tokens": 5876256} {"current_steps": 27855, "total_steps": 181800, "loss": 0.0323, "lr": 4.956996863329064e-05, "epoch": 3.0643564356435644, "percentage": 15.32, "elapsed_time": "1:05:46", "remaining_time": "6:03:32", "throughput": 1489.14, "total_tokens": 5877312} {"current_steps": 27860, "total_steps": 181800, "loss": 0.0847, "lr": 4.9569525276053766e-05, "epoch": 3.064906490649065, "percentage": 15.32, "elapsed_time": "1:05:47", "remaining_time": "6:03:31", "throughput": 1489.14, "total_tokens": 5878336} {"current_steps": 27865, "total_steps": 181800, "loss": 0.0838, "lr": 4.9569081692371366e-05, "epoch": 3.0654565456545653, "percentage": 15.33, "elapsed_time": "1:05:48", "remaining_time": "6:03:30", "throughput": 1489.16, "total_tokens": 5879424} {"current_steps": 27870, "total_steps": 181800, "loss": 0.0069, "lr": 4.956863788224753e-05, "epoch": 3.066006600660066, "percentage": 15.33, "elapsed_time": "1:05:48", "remaining_time": "6:03:30", "throughput": 1489.17, "total_tokens": 5880512} {"current_steps": 27875, "total_steps": 181800, "loss": 0.067, "lr": 4.956819384568635e-05, "epoch": 3.0665566556655666, "percentage": 15.33, "elapsed_time": "1:05:49", "remaining_time": "6:03:29", "throughput": 1489.17, "total_tokens": 5881504} {"current_steps": 27880, "total_steps": 181800, "loss": 0.1717, "lr": 4.956774958269191e-05, "epoch": 3.067106710671067, "percentage": 15.34, "elapsed_time": "1:05:50", "remaining_time": "6:03:28", "throughput": 1489.16, "total_tokens": 5882496} {"current_steps": 27885, "total_steps": 181800, "loss": 0.0345, "lr": 4.956730509326832e-05, "epoch": 3.067656765676568, "percentage": 15.34, "elapsed_time": "1:05:50", "remaining_time": "6:03:27", "throughput": 1489.17, "total_tokens": 5883584} {"current_steps": 27890, "total_steps": 181800, "loss": 0.0189, "lr": 4.956686037741966e-05, "epoch": 3.068206820682068, "percentage": 15.34, "elapsed_time": "1:05:51", "remaining_time": "6:03:26", "throughput": 1489.19, "total_tokens": 5884672} {"current_steps": 27895, "total_steps": 181800, "loss": 0.1615, "lr": 4.956641543515004e-05, "epoch": 3.0687568756875687, "percentage": 15.34, "elapsed_time": "1:05:52", "remaining_time": "6:03:25", "throughput": 1489.19, "total_tokens": 5885696} {"current_steps": 27900, "total_steps": 181800, "loss": 0.027, "lr": 4.956597026646356e-05, "epoch": 3.0693069306930694, "percentage": 15.35, "elapsed_time": "1:05:52", "remaining_time": "6:03:25", "throughput": 1489.2, "total_tokens": 5886784} {"current_steps": 27905, "total_steps": 181800, "loss": 0.0335, "lr": 4.956552487136431e-05, "epoch": 3.06985698569857, "percentage": 15.35, "elapsed_time": "1:05:53", "remaining_time": "6:03:24", "throughput": 1489.22, "total_tokens": 5887872} {"current_steps": 27910, "total_steps": 181800, "loss": 0.0365, "lr": 4.956507924985641e-05, "epoch": 3.0704070407040702, "percentage": 15.35, "elapsed_time": "1:05:54", "remaining_time": "6:03:23", "throughput": 1489.22, "total_tokens": 5888896} {"current_steps": 27915, "total_steps": 181800, "loss": 0.0544, "lr": 4.956463340194396e-05, "epoch": 3.070957095709571, "percentage": 15.35, "elapsed_time": "1:05:55", "remaining_time": "6:03:22", "throughput": 1489.21, "total_tokens": 5889888} {"current_steps": 27920, "total_steps": 181800, "loss": 0.0735, "lr": 4.956418732763107e-05, "epoch": 3.0715071507150715, "percentage": 15.36, "elapsed_time": "1:05:55", "remaining_time": "6:03:21", "throughput": 1489.21, "total_tokens": 5890912} {"current_steps": 27925, "total_steps": 181800, "loss": 0.0191, "lr": 4.9563741026921865e-05, "epoch": 3.072057205720572, "percentage": 15.36, "elapsed_time": "1:05:56", "remaining_time": "6:03:20", "throughput": 1489.23, "total_tokens": 5892000} {"current_steps": 27930, "total_steps": 181800, "loss": 0.0756, "lr": 4.956329449982043e-05, "epoch": 3.072607260726073, "percentage": 15.36, "elapsed_time": "1:05:57", "remaining_time": "6:03:20", "throughput": 1489.23, "total_tokens": 5893024} {"current_steps": 27935, "total_steps": 181800, "loss": 0.1937, "lr": 4.956284774633091e-05, "epoch": 3.073157315731573, "percentage": 15.37, "elapsed_time": "1:05:57", "remaining_time": "6:03:19", "throughput": 1489.23, "total_tokens": 5894048} {"current_steps": 27940, "total_steps": 181800, "loss": 0.0393, "lr": 4.95624007664574e-05, "epoch": 3.0737073707370737, "percentage": 15.37, "elapsed_time": "1:05:58", "remaining_time": "6:03:18", "throughput": 1489.24, "total_tokens": 5895104} {"current_steps": 27945, "total_steps": 181800, "loss": 0.147, "lr": 4.956195356020403e-05, "epoch": 3.0742574257425743, "percentage": 15.37, "elapsed_time": "1:05:59", "remaining_time": "6:03:17", "throughput": 1489.23, "total_tokens": 5896096} {"current_steps": 27950, "total_steps": 181800, "loss": 0.0353, "lr": 4.956150612757492e-05, "epoch": 3.074807480748075, "percentage": 15.37, "elapsed_time": "1:05:59", "remaining_time": "6:03:16", "throughput": 1489.22, "total_tokens": 5897088} {"current_steps": 27955, "total_steps": 181800, "loss": 0.0884, "lr": 4.9561058468574195e-05, "epoch": 3.075357535753575, "percentage": 15.38, "elapsed_time": "1:06:00", "remaining_time": "6:03:16", "throughput": 1489.24, "total_tokens": 5898208} {"current_steps": 27960, "total_steps": 181800, "loss": 0.0516, "lr": 4.956061058320598e-05, "epoch": 3.075907590759076, "percentage": 15.38, "elapsed_time": "1:06:01", "remaining_time": "6:03:15", "throughput": 1489.25, "total_tokens": 5899264} {"current_steps": 27965, "total_steps": 181800, "loss": 0.0752, "lr": 4.9560162471474405e-05, "epoch": 3.0764576457645765, "percentage": 15.38, "elapsed_time": "1:06:01", "remaining_time": "6:03:14", "throughput": 1489.27, "total_tokens": 5900352} {"current_steps": 27970, "total_steps": 181800, "loss": 0.0374, "lr": 4.955971413338359e-05, "epoch": 3.077007700770077, "percentage": 15.39, "elapsed_time": "1:06:02", "remaining_time": "6:03:13", "throughput": 1489.27, "total_tokens": 5901376} {"current_steps": 27975, "total_steps": 181800, "loss": 0.0425, "lr": 4.955926556893768e-05, "epoch": 3.0775577557755778, "percentage": 15.39, "elapsed_time": "1:06:03", "remaining_time": "6:03:12", "throughput": 1489.27, "total_tokens": 5902400} {"current_steps": 27980, "total_steps": 181800, "loss": 0.0474, "lr": 4.9558816778140804e-05, "epoch": 3.078107810781078, "percentage": 15.39, "elapsed_time": "1:06:03", "remaining_time": "6:03:11", "throughput": 1489.28, "total_tokens": 5903488} {"current_steps": 27985, "total_steps": 181800, "loss": 0.0678, "lr": 4.955836776099709e-05, "epoch": 3.0786578657865786, "percentage": 15.39, "elapsed_time": "1:06:04", "remaining_time": "6:03:11", "throughput": 1489.3, "total_tokens": 5904576} {"current_steps": 27990, "total_steps": 181800, "loss": 0.0565, "lr": 4.9557918517510694e-05, "epoch": 3.0792079207920793, "percentage": 15.4, "elapsed_time": "1:06:05", "remaining_time": "6:03:10", "throughput": 1489.3, "total_tokens": 5905600} {"current_steps": 27995, "total_steps": 181800, "loss": 0.0167, "lr": 4.955746904768574e-05, "epoch": 3.07975797579758, "percentage": 15.4, "elapsed_time": "1:06:06", "remaining_time": "6:03:09", "throughput": 1489.28, "total_tokens": 5906560} {"current_steps": 28000, "total_steps": 181800, "loss": 0.0592, "lr": 4.955701935152639e-05, "epoch": 3.08030803080308, "percentage": 15.4, "elapsed_time": "1:06:06", "remaining_time": "6:03:08", "throughput": 1489.27, "total_tokens": 5907552} {"current_steps": 28005, "total_steps": 181800, "loss": 0.0452, "lr": 4.955656942903677e-05, "epoch": 3.080858085808581, "percentage": 15.4, "elapsed_time": "1:06:07", "remaining_time": "6:03:07", "throughput": 1489.29, "total_tokens": 5908640} {"current_steps": 28010, "total_steps": 181800, "loss": 0.0275, "lr": 4.955611928022103e-05, "epoch": 3.0814081408140814, "percentage": 15.41, "elapsed_time": "1:06:08", "remaining_time": "6:03:07", "throughput": 1489.31, "total_tokens": 5909760} {"current_steps": 28015, "total_steps": 181800, "loss": 0.0886, "lr": 4.9555668905083317e-05, "epoch": 3.081958195819582, "percentage": 15.41, "elapsed_time": "1:06:08", "remaining_time": "6:03:06", "throughput": 1489.34, "total_tokens": 5910880} {"current_steps": 28020, "total_steps": 181800, "loss": 0.013, "lr": 4.9555218303627795e-05, "epoch": 3.0825082508250823, "percentage": 15.41, "elapsed_time": "1:06:09", "remaining_time": "6:03:05", "throughput": 1489.34, "total_tokens": 5911904} {"current_steps": 28025, "total_steps": 181800, "loss": 0.0802, "lr": 4.955476747585861e-05, "epoch": 3.083058305830583, "percentage": 15.42, "elapsed_time": "1:06:10", "remaining_time": "6:03:04", "throughput": 1489.35, "total_tokens": 5912960} {"current_steps": 28030, "total_steps": 181800, "loss": 0.057, "lr": 4.955431642177991e-05, "epoch": 3.0836083608360836, "percentage": 15.42, "elapsed_time": "1:06:10", "remaining_time": "6:03:03", "throughput": 1489.36, "total_tokens": 5914016} {"current_steps": 28035, "total_steps": 181800, "loss": 0.0306, "lr": 4.955386514139586e-05, "epoch": 3.0841584158415842, "percentage": 15.42, "elapsed_time": "1:06:11", "remaining_time": "6:03:02", "throughput": 1489.38, "total_tokens": 5915136} {"current_steps": 28040, "total_steps": 181800, "loss": 0.1282, "lr": 4.9553413634710615e-05, "epoch": 3.084708470847085, "percentage": 15.42, "elapsed_time": "1:06:12", "remaining_time": "6:03:02", "throughput": 1489.39, "total_tokens": 5916192} {"current_steps": 28045, "total_steps": 181800, "loss": 0.055, "lr": 4.955296190172834e-05, "epoch": 3.085258525852585, "percentage": 15.43, "elapsed_time": "1:06:12", "remaining_time": "6:03:01", "throughput": 1489.41, "total_tokens": 5917280} {"current_steps": 28050, "total_steps": 181800, "loss": 0.0649, "lr": 4.9552509942453196e-05, "epoch": 3.0858085808580857, "percentage": 15.43, "elapsed_time": "1:06:13", "remaining_time": "6:03:00", "throughput": 1489.43, "total_tokens": 5918400} {"current_steps": 28055, "total_steps": 181800, "loss": 0.1205, "lr": 4.9552057756889355e-05, "epoch": 3.0863586358635864, "percentage": 15.43, "elapsed_time": "1:06:14", "remaining_time": "6:02:59", "throughput": 1489.43, "total_tokens": 5919424} {"current_steps": 28060, "total_steps": 181800, "loss": 0.023, "lr": 4.9551605345040974e-05, "epoch": 3.086908690869087, "percentage": 15.43, "elapsed_time": "1:06:14", "remaining_time": "6:02:58", "throughput": 1489.44, "total_tokens": 5920480} {"current_steps": 28065, "total_steps": 181800, "loss": 0.0315, "lr": 4.955115270691223e-05, "epoch": 3.0874587458745877, "percentage": 15.44, "elapsed_time": "1:06:15", "remaining_time": "6:02:57", "throughput": 1489.45, "total_tokens": 5921536} {"current_steps": 28070, "total_steps": 181800, "loss": 0.1124, "lr": 4.955069984250729e-05, "epoch": 3.088008800880088, "percentage": 15.44, "elapsed_time": "1:06:16", "remaining_time": "6:02:57", "throughput": 1489.48, "total_tokens": 5922656} {"current_steps": 28075, "total_steps": 181800, "loss": 0.02, "lr": 4.955024675183033e-05, "epoch": 3.0885588558855885, "percentage": 15.44, "elapsed_time": "1:06:17", "remaining_time": "6:02:56", "throughput": 1489.48, "total_tokens": 5923712} {"current_steps": 28080, "total_steps": 181800, "loss": 0.0578, "lr": 4.9549793434885525e-05, "epoch": 3.089108910891089, "percentage": 15.45, "elapsed_time": "1:06:17", "remaining_time": "6:02:55", "throughput": 1489.49, "total_tokens": 5924768} {"current_steps": 28085, "total_steps": 181800, "loss": 0.0406, "lr": 4.9549339891677056e-05, "epoch": 3.08965896589659, "percentage": 15.45, "elapsed_time": "1:06:18", "remaining_time": "6:02:54", "throughput": 1489.49, "total_tokens": 5925792} {"current_steps": 28090, "total_steps": 181800, "loss": 0.0286, "lr": 4.95488861222091e-05, "epoch": 3.09020902090209, "percentage": 15.45, "elapsed_time": "1:06:19", "remaining_time": "6:02:53", "throughput": 1489.49, "total_tokens": 5926816} {"current_steps": 28095, "total_steps": 181800, "loss": 0.1401, "lr": 4.954843212648584e-05, "epoch": 3.0907590759075907, "percentage": 15.45, "elapsed_time": "1:06:19", "remaining_time": "6:02:52", "throughput": 1489.48, "total_tokens": 5927808} {"current_steps": 28100, "total_steps": 181800, "loss": 0.024, "lr": 4.954797790451146e-05, "epoch": 3.0913091309130913, "percentage": 15.46, "elapsed_time": "1:06:20", "remaining_time": "6:02:52", "throughput": 1489.51, "total_tokens": 5928928} {"current_steps": 28105, "total_steps": 181800, "loss": 0.0526, "lr": 4.9547523456290146e-05, "epoch": 3.091859185918592, "percentage": 15.46, "elapsed_time": "1:06:21", "remaining_time": "6:02:51", "throughput": 1489.52, "total_tokens": 5930016} {"current_steps": 28110, "total_steps": 181800, "loss": 0.0572, "lr": 4.954706878182609e-05, "epoch": 3.092409240924092, "percentage": 15.46, "elapsed_time": "1:06:21", "remaining_time": "6:02:50", "throughput": 1489.52, "total_tokens": 5931040} {"current_steps": 28115, "total_steps": 181800, "loss": 0.0363, "lr": 4.954661388112348e-05, "epoch": 3.092959295929593, "percentage": 15.46, "elapsed_time": "1:06:22", "remaining_time": "6:02:49", "throughput": 1489.53, "total_tokens": 5932096} {"current_steps": 28120, "total_steps": 181800, "loss": 0.0767, "lr": 4.954615875418651e-05, "epoch": 3.0935093509350935, "percentage": 15.47, "elapsed_time": "1:06:23", "remaining_time": "6:02:48", "throughput": 1489.53, "total_tokens": 5933120} {"current_steps": 28125, "total_steps": 181800, "loss": 0.082, "lr": 4.954570340101937e-05, "epoch": 3.094059405940594, "percentage": 15.47, "elapsed_time": "1:06:23", "remaining_time": "6:02:48", "throughput": 1489.54, "total_tokens": 5934208} {"current_steps": 28130, "total_steps": 181800, "loss": 0.1086, "lr": 4.9545247821626265e-05, "epoch": 3.094609460946095, "percentage": 15.47, "elapsed_time": "1:06:24", "remaining_time": "6:02:47", "throughput": 1489.54, "total_tokens": 5935232} {"current_steps": 28135, "total_steps": 181800, "loss": 0.1296, "lr": 4.954479201601138e-05, "epoch": 3.095159515951595, "percentage": 15.48, "elapsed_time": "1:06:25", "remaining_time": "6:02:46", "throughput": 1489.55, "total_tokens": 5936288} {"current_steps": 28140, "total_steps": 181800, "loss": 0.0844, "lr": 4.9544335984178933e-05, "epoch": 3.0957095709570956, "percentage": 15.48, "elapsed_time": "1:06:25", "remaining_time": "6:02:45", "throughput": 1489.55, "total_tokens": 5937312} {"current_steps": 28145, "total_steps": 181800, "loss": 0.1931, "lr": 4.954387972613311e-05, "epoch": 3.0962596259625963, "percentage": 15.48, "elapsed_time": "1:06:26", "remaining_time": "6:02:44", "throughput": 1489.55, "total_tokens": 5938336} {"current_steps": 28150, "total_steps": 181800, "loss": 0.1005, "lr": 4.954342324187814e-05, "epoch": 3.096809680968097, "percentage": 15.48, "elapsed_time": "1:06:27", "remaining_time": "6:02:44", "throughput": 1489.56, "total_tokens": 5939392} {"current_steps": 28155, "total_steps": 181800, "loss": 0.035, "lr": 4.95429665314182e-05, "epoch": 3.097359735973597, "percentage": 15.49, "elapsed_time": "1:06:28", "remaining_time": "6:02:43", "throughput": 1489.57, "total_tokens": 5940448} {"current_steps": 28160, "total_steps": 181800, "loss": 0.0798, "lr": 4.9542509594757526e-05, "epoch": 3.097909790979098, "percentage": 15.49, "elapsed_time": "1:06:28", "remaining_time": "6:02:42", "throughput": 1489.56, "total_tokens": 5941440} {"current_steps": 28165, "total_steps": 181800, "loss": 0.1201, "lr": 4.954205243190031e-05, "epoch": 3.0984598459845984, "percentage": 15.49, "elapsed_time": "1:06:29", "remaining_time": "6:02:41", "throughput": 1489.57, "total_tokens": 5942496} {"current_steps": 28170, "total_steps": 181800, "loss": 0.203, "lr": 4.9541595042850766e-05, "epoch": 3.099009900990099, "percentage": 15.5, "elapsed_time": "1:06:30", "remaining_time": "6:02:40", "throughput": 1489.59, "total_tokens": 5943616} {"current_steps": 28175, "total_steps": 181800, "loss": 0.0103, "lr": 4.9541137427613125e-05, "epoch": 3.0995599559955997, "percentage": 15.5, "elapsed_time": "1:06:30", "remaining_time": "6:02:39", "throughput": 1489.61, "total_tokens": 5944736} {"current_steps": 28180, "total_steps": 181800, "loss": 0.0251, "lr": 4.9540679586191605e-05, "epoch": 3.1001100110011, "percentage": 15.5, "elapsed_time": "1:06:31", "remaining_time": "6:02:39", "throughput": 1489.63, "total_tokens": 5945824} {"current_steps": 28185, "total_steps": 181800, "loss": 0.0232, "lr": 4.95402215185904e-05, "epoch": 3.1006600660066006, "percentage": 15.5, "elapsed_time": "1:06:32", "remaining_time": "6:02:38", "throughput": 1489.64, "total_tokens": 5946880} {"current_steps": 28190, "total_steps": 181800, "loss": 0.0458, "lr": 4.953976322481376e-05, "epoch": 3.1012101210121013, "percentage": 15.51, "elapsed_time": "1:06:32", "remaining_time": "6:02:37", "throughput": 1489.64, "total_tokens": 5947936} {"current_steps": 28195, "total_steps": 181800, "loss": 0.0374, "lr": 4.953930470486589e-05, "epoch": 3.101760176017602, "percentage": 15.51, "elapsed_time": "1:06:33", "remaining_time": "6:02:36", "throughput": 1489.63, "total_tokens": 5948896} {"current_steps": 28200, "total_steps": 181800, "loss": 0.0962, "lr": 4.9538845958751034e-05, "epoch": 3.102310231023102, "percentage": 15.51, "elapsed_time": "1:06:34", "remaining_time": "6:02:35", "throughput": 1489.64, "total_tokens": 5949984} {"current_steps": 28205, "total_steps": 181800, "loss": 0.0176, "lr": 4.95383869864734e-05, "epoch": 3.1028602860286028, "percentage": 15.51, "elapsed_time": "1:06:34", "remaining_time": "6:02:35", "throughput": 1489.67, "total_tokens": 5951104} {"current_steps": 28210, "total_steps": 181800, "loss": 0.0581, "lr": 4.9537927788037244e-05, "epoch": 3.1034103410341034, "percentage": 15.52, "elapsed_time": "1:06:35", "remaining_time": "6:02:34", "throughput": 1489.67, "total_tokens": 5952128} {"current_steps": 28215, "total_steps": 181800, "loss": 0.0948, "lr": 4.9537468363446764e-05, "epoch": 3.103960396039604, "percentage": 15.52, "elapsed_time": "1:06:36", "remaining_time": "6:02:33", "throughput": 1489.68, "total_tokens": 5953184} {"current_steps": 28220, "total_steps": 181800, "loss": 0.0814, "lr": 4.953700871270622e-05, "epoch": 3.1045104510451047, "percentage": 15.52, "elapsed_time": "1:06:36", "remaining_time": "6:02:32", "throughput": 1489.68, "total_tokens": 5954240} {"current_steps": 28225, "total_steps": 181800, "loss": 0.083, "lr": 4.953654883581984e-05, "epoch": 3.105060506050605, "percentage": 15.53, "elapsed_time": "1:06:37", "remaining_time": "6:02:31", "throughput": 1489.68, "total_tokens": 5955264} {"current_steps": 28230, "total_steps": 181800, "loss": 0.118, "lr": 4.953608873279186e-05, "epoch": 3.1056105610561056, "percentage": 15.53, "elapsed_time": "1:06:38", "remaining_time": "6:02:30", "throughput": 1489.71, "total_tokens": 5956384} {"current_steps": 28235, "total_steps": 181800, "loss": 0.0349, "lr": 4.9535628403626524e-05, "epoch": 3.106160616061606, "percentage": 15.53, "elapsed_time": "1:06:39", "remaining_time": "6:02:30", "throughput": 1489.7, "total_tokens": 5957408} {"current_steps": 28240, "total_steps": 181800, "loss": 0.0904, "lr": 4.953516784832808e-05, "epoch": 3.106710671067107, "percentage": 15.53, "elapsed_time": "1:06:39", "remaining_time": "6:02:29", "throughput": 1489.7, "total_tokens": 5958432} {"current_steps": 28245, "total_steps": 181800, "loss": 0.1109, "lr": 4.953470706690077e-05, "epoch": 3.107260726072607, "percentage": 15.54, "elapsed_time": "1:06:40", "remaining_time": "6:02:28", "throughput": 1489.7, "total_tokens": 5959456} {"current_steps": 28250, "total_steps": 181800, "loss": 0.035, "lr": 4.9534246059348824e-05, "epoch": 3.1078107810781077, "percentage": 15.54, "elapsed_time": "1:06:41", "remaining_time": "6:02:27", "throughput": 1489.73, "total_tokens": 5960576} {"current_steps": 28255, "total_steps": 181800, "loss": 0.042, "lr": 4.953378482567651e-05, "epoch": 3.1083608360836084, "percentage": 15.54, "elapsed_time": "1:06:41", "remaining_time": "6:02:26", "throughput": 1489.74, "total_tokens": 5961632} {"current_steps": 28260, "total_steps": 181800, "loss": 0.0758, "lr": 4.953332336588808e-05, "epoch": 3.108910891089109, "percentage": 15.54, "elapsed_time": "1:06:42", "remaining_time": "6:02:26", "throughput": 1489.74, "total_tokens": 5962688} {"current_steps": 28265, "total_steps": 181800, "loss": 0.0561, "lr": 4.953286167998777e-05, "epoch": 3.1094609460946097, "percentage": 15.55, "elapsed_time": "1:06:43", "remaining_time": "6:02:25", "throughput": 1489.76, "total_tokens": 5963776} {"current_steps": 28270, "total_steps": 181800, "loss": 0.1356, "lr": 4.9532399767979854e-05, "epoch": 3.11001100110011, "percentage": 15.55, "elapsed_time": "1:06:43", "remaining_time": "6:02:24", "throughput": 1489.76, "total_tokens": 5964800} {"current_steps": 28275, "total_steps": 181800, "loss": 0.0838, "lr": 4.953193762986859e-05, "epoch": 3.1105610561056105, "percentage": 15.55, "elapsed_time": "1:06:44", "remaining_time": "6:02:23", "throughput": 1489.76, "total_tokens": 5965824} {"current_steps": 28280, "total_steps": 181800, "loss": 0.0705, "lr": 4.953147526565821e-05, "epoch": 3.111111111111111, "percentage": 15.56, "elapsed_time": "1:06:45", "remaining_time": "6:02:22", "throughput": 1489.77, "total_tokens": 5966912} {"current_steps": 28285, "total_steps": 181800, "loss": 0.0565, "lr": 4.9531012675353006e-05, "epoch": 3.111661166116612, "percentage": 15.56, "elapsed_time": "1:06:45", "remaining_time": "6:02:21", "throughput": 1489.76, "total_tokens": 5967904} {"current_steps": 28290, "total_steps": 181800, "loss": 0.0392, "lr": 4.953054985895722e-05, "epoch": 3.112211221122112, "percentage": 15.56, "elapsed_time": "1:06:46", "remaining_time": "6:02:21", "throughput": 1489.78, "total_tokens": 5968992} {"current_steps": 28295, "total_steps": 181800, "loss": 0.0687, "lr": 4.953008681647513e-05, "epoch": 3.1127612761276127, "percentage": 15.56, "elapsed_time": "1:06:47", "remaining_time": "6:02:20", "throughput": 1489.79, "total_tokens": 5970048} {"current_steps": 28300, "total_steps": 181800, "loss": 0.0155, "lr": 4.952962354791101e-05, "epoch": 3.1133113311331133, "percentage": 15.57, "elapsed_time": "1:06:48", "remaining_time": "6:02:19", "throughput": 1489.79, "total_tokens": 5971104} {"current_steps": 28305, "total_steps": 181800, "loss": 0.108, "lr": 4.9529160053269106e-05, "epoch": 3.113861386138614, "percentage": 15.57, "elapsed_time": "1:06:48", "remaining_time": "6:02:18", "throughput": 1489.8, "total_tokens": 5972160} {"current_steps": 28310, "total_steps": 181800, "loss": 0.0627, "lr": 4.9528696332553715e-05, "epoch": 3.1144114411441146, "percentage": 15.57, "elapsed_time": "1:06:49", "remaining_time": "6:02:17", "throughput": 1489.82, "total_tokens": 5973280} {"current_steps": 28315, "total_steps": 181800, "loss": 0.0626, "lr": 4.952823238576909e-05, "epoch": 3.114961496149615, "percentage": 15.57, "elapsed_time": "1:06:50", "remaining_time": "6:02:17", "throughput": 1489.85, "total_tokens": 5974400} {"current_steps": 28320, "total_steps": 181800, "loss": 0.0807, "lr": 4.952776821291952e-05, "epoch": 3.1155115511551155, "percentage": 15.58, "elapsed_time": "1:06:50", "remaining_time": "6:02:16", "throughput": 1489.85, "total_tokens": 5975424} {"current_steps": 28325, "total_steps": 181800, "loss": 0.0679, "lr": 4.952730381400929e-05, "epoch": 3.116061606160616, "percentage": 15.58, "elapsed_time": "1:06:51", "remaining_time": "6:02:15", "throughput": 1489.85, "total_tokens": 5976480} {"current_steps": 28330, "total_steps": 181800, "loss": 0.07, "lr": 4.9526839189042665e-05, "epoch": 3.1166116611661168, "percentage": 15.58, "elapsed_time": "1:06:52", "remaining_time": "6:02:14", "throughput": 1489.85, "total_tokens": 5977472} {"current_steps": 28335, "total_steps": 181800, "loss": 0.1577, "lr": 4.952637433802393e-05, "epoch": 3.117161716171617, "percentage": 15.59, "elapsed_time": "1:06:52", "remaining_time": "6:02:13", "throughput": 1489.88, "total_tokens": 5978624} {"current_steps": 28340, "total_steps": 181800, "loss": 0.0833, "lr": 4.952590926095737e-05, "epoch": 3.1177117711771176, "percentage": 15.59, "elapsed_time": "1:06:53", "remaining_time": "6:02:13", "throughput": 1489.87, "total_tokens": 5979648} {"current_steps": 28345, "total_steps": 181800, "loss": 0.0313, "lr": 4.9525443957847276e-05, "epoch": 3.1182618261826183, "percentage": 15.59, "elapsed_time": "1:06:54", "remaining_time": "6:02:12", "throughput": 1489.88, "total_tokens": 5980704} {"current_steps": 28350, "total_steps": 181800, "loss": 0.0109, "lr": 4.9524978428697934e-05, "epoch": 3.118811881188119, "percentage": 15.59, "elapsed_time": "1:06:54", "remaining_time": "6:02:11", "throughput": 1489.88, "total_tokens": 5981728} {"current_steps": 28355, "total_steps": 181800, "loss": 0.0609, "lr": 4.952451267351362e-05, "epoch": 3.1193619361936196, "percentage": 15.6, "elapsed_time": "1:06:55", "remaining_time": "6:02:10", "throughput": 1489.88, "total_tokens": 5982752} {"current_steps": 28360, "total_steps": 181800, "loss": 0.0954, "lr": 4.952404669229866e-05, "epoch": 3.1199119911991198, "percentage": 15.6, "elapsed_time": "1:06:56", "remaining_time": "6:02:09", "throughput": 1489.88, "total_tokens": 5983776} {"current_steps": 28365, "total_steps": 181800, "loss": 0.1997, "lr": 4.952358048505732e-05, "epoch": 3.1204620462046204, "percentage": 15.6, "elapsed_time": "1:06:56", "remaining_time": "6:02:09", "throughput": 1489.9, "total_tokens": 5984864} {"current_steps": 28370, "total_steps": 181800, "loss": 0.022, "lr": 4.952311405179391e-05, "epoch": 3.121012101210121, "percentage": 15.61, "elapsed_time": "1:06:57", "remaining_time": "6:02:08", "throughput": 1489.9, "total_tokens": 5985920} {"current_steps": 28375, "total_steps": 181800, "loss": 0.0559, "lr": 4.9522647392512724e-05, "epoch": 3.1215621562156217, "percentage": 15.61, "elapsed_time": "1:06:58", "remaining_time": "6:02:07", "throughput": 1489.93, "total_tokens": 5987072} {"current_steps": 28380, "total_steps": 181800, "loss": 0.0388, "lr": 4.9522180507218064e-05, "epoch": 3.122112211221122, "percentage": 15.61, "elapsed_time": "1:06:59", "remaining_time": "6:02:06", "throughput": 1489.94, "total_tokens": 5988128} {"current_steps": 28385, "total_steps": 181800, "loss": 0.1056, "lr": 4.952171339591423e-05, "epoch": 3.1226622662266226, "percentage": 15.61, "elapsed_time": "1:06:59", "remaining_time": "6:02:05", "throughput": 1489.95, "total_tokens": 5989184} {"current_steps": 28390, "total_steps": 181800, "loss": 0.1067, "lr": 4.9521246058605534e-05, "epoch": 3.1232123212321232, "percentage": 15.62, "elapsed_time": "1:07:00", "remaining_time": "6:02:05", "throughput": 1489.96, "total_tokens": 5990272} {"current_steps": 28395, "total_steps": 181800, "loss": 0.0566, "lr": 4.9520778495296284e-05, "epoch": 3.123762376237624, "percentage": 15.62, "elapsed_time": "1:07:01", "remaining_time": "6:02:04", "throughput": 1489.97, "total_tokens": 5991328} {"current_steps": 28400, "total_steps": 181800, "loss": 0.052, "lr": 4.9520310705990775e-05, "epoch": 3.1243124312431245, "percentage": 15.62, "elapsed_time": "1:07:01", "remaining_time": "6:02:03", "throughput": 1489.97, "total_tokens": 5992352} {"current_steps": 28405, "total_steps": 181800, "loss": 0.071, "lr": 4.951984269069333e-05, "epoch": 3.1248624862486247, "percentage": 15.62, "elapsed_time": "1:07:02", "remaining_time": "6:02:02", "throughput": 1489.96, "total_tokens": 5993344} {"current_steps": 28410, "total_steps": 181800, "loss": 0.0769, "lr": 4.9519374449408266e-05, "epoch": 3.1254125412541254, "percentage": 15.63, "elapsed_time": "1:07:03", "remaining_time": "6:02:01", "throughput": 1489.96, "total_tokens": 5994400} {"current_steps": 28415, "total_steps": 181800, "loss": 0.0623, "lr": 4.951890598213989e-05, "epoch": 3.125962596259626, "percentage": 15.63, "elapsed_time": "1:07:03", "remaining_time": "6:02:01", "throughput": 1489.99, "total_tokens": 5995520} {"current_steps": 28420, "total_steps": 181800, "loss": 0.0615, "lr": 4.9518437288892524e-05, "epoch": 3.1265126512651267, "percentage": 15.63, "elapsed_time": "1:07:04", "remaining_time": "6:02:00", "throughput": 1490.0, "total_tokens": 5996608} {"current_steps": 28425, "total_steps": 181800, "loss": 0.0956, "lr": 4.951796836967049e-05, "epoch": 3.127062706270627, "percentage": 15.64, "elapsed_time": "1:07:05", "remaining_time": "6:01:59", "throughput": 1489.99, "total_tokens": 5997600} {"current_steps": 28430, "total_steps": 181800, "loss": 0.0846, "lr": 4.9517499224478095e-05, "epoch": 3.1276127612761275, "percentage": 15.64, "elapsed_time": "1:07:05", "remaining_time": "6:01:58", "throughput": 1490.01, "total_tokens": 5998688} {"current_steps": 28435, "total_steps": 181800, "loss": 0.1543, "lr": 4.9517029853319687e-05, "epoch": 3.128162816281628, "percentage": 15.64, "elapsed_time": "1:07:06", "remaining_time": "6:01:57", "throughput": 1490.02, "total_tokens": 5999776} {"current_steps": 28440, "total_steps": 181800, "loss": 0.0999, "lr": 4.951656025619957e-05, "epoch": 3.128712871287129, "percentage": 15.64, "elapsed_time": "1:07:07", "remaining_time": "6:01:56", "throughput": 1490.03, "total_tokens": 6000832} {"current_steps": 28445, "total_steps": 181800, "loss": 0.0767, "lr": 4.951609043312209e-05, "epoch": 3.129262926292629, "percentage": 15.65, "elapsed_time": "1:07:08", "remaining_time": "6:01:56", "throughput": 1490.02, "total_tokens": 6001824} {"current_steps": 28450, "total_steps": 181800, "loss": 0.0442, "lr": 4.951562038409157e-05, "epoch": 3.1298129812981297, "percentage": 15.65, "elapsed_time": "1:07:08", "remaining_time": "6:01:55", "throughput": 1490.04, "total_tokens": 6002912} {"current_steps": 28455, "total_steps": 181800, "loss": 0.1476, "lr": 4.951515010911233e-05, "epoch": 3.1303630363036303, "percentage": 15.65, "elapsed_time": "1:07:09", "remaining_time": "6:01:54", "throughput": 1490.05, "total_tokens": 6004000} {"current_steps": 28460, "total_steps": 181800, "loss": 0.0175, "lr": 4.9514679608188716e-05, "epoch": 3.130913091309131, "percentage": 15.65, "elapsed_time": "1:07:10", "remaining_time": "6:01:53", "throughput": 1490.05, "total_tokens": 6005024} {"current_steps": 28465, "total_steps": 181800, "loss": 0.0719, "lr": 4.9514208881325066e-05, "epoch": 3.1314631463146316, "percentage": 15.66, "elapsed_time": "1:07:10", "remaining_time": "6:01:52", "throughput": 1490.06, "total_tokens": 6006080} {"current_steps": 28470, "total_steps": 181800, "loss": 0.0257, "lr": 4.951373792852572e-05, "epoch": 3.132013201320132, "percentage": 15.66, "elapsed_time": "1:07:11", "remaining_time": "6:01:52", "throughput": 1490.06, "total_tokens": 6007104} {"current_steps": 28475, "total_steps": 181800, "loss": 0.0369, "lr": 4.951326674979501e-05, "epoch": 3.1325632563256325, "percentage": 15.66, "elapsed_time": "1:07:12", "remaining_time": "6:01:51", "throughput": 1490.07, "total_tokens": 6008160} {"current_steps": 28480, "total_steps": 181800, "loss": 0.0386, "lr": 4.951279534513728e-05, "epoch": 3.133113311331133, "percentage": 15.67, "elapsed_time": "1:07:12", "remaining_time": "6:01:50", "throughput": 1490.07, "total_tokens": 6009216} {"current_steps": 28485, "total_steps": 181800, "loss": 0.0296, "lr": 4.9512323714556886e-05, "epoch": 3.133663366336634, "percentage": 15.67, "elapsed_time": "1:07:13", "remaining_time": "6:01:49", "throughput": 1490.1, "total_tokens": 6010336} {"current_steps": 28490, "total_steps": 181800, "loss": 0.0314, "lr": 4.9511851858058154e-05, "epoch": 3.1342134213421344, "percentage": 15.67, "elapsed_time": "1:07:14", "remaining_time": "6:01:48", "throughput": 1490.11, "total_tokens": 6011424} {"current_steps": 28495, "total_steps": 181800, "loss": 0.0203, "lr": 4.951137977564546e-05, "epoch": 3.1347634763476346, "percentage": 15.67, "elapsed_time": "1:07:14", "remaining_time": "6:01:48", "throughput": 1490.11, "total_tokens": 6012448} {"current_steps": 28500, "total_steps": 181800, "loss": 0.0911, "lr": 4.9510907467323134e-05, "epoch": 3.1353135313531353, "percentage": 15.68, "elapsed_time": "1:07:15", "remaining_time": "6:01:47", "throughput": 1490.11, "total_tokens": 6013472} {"current_steps": 28505, "total_steps": 181800, "loss": 0.0415, "lr": 4.951043493309553e-05, "epoch": 3.135863586358636, "percentage": 15.68, "elapsed_time": "1:07:16", "remaining_time": "6:01:46", "throughput": 1490.12, "total_tokens": 6014528} {"current_steps": 28510, "total_steps": 181800, "loss": 0.0306, "lr": 4.9509962172967016e-05, "epoch": 3.1364136413641366, "percentage": 15.68, "elapsed_time": "1:07:16", "remaining_time": "6:01:45", "throughput": 1490.11, "total_tokens": 6015520} {"current_steps": 28515, "total_steps": 181800, "loss": 0.0592, "lr": 4.950948918694194e-05, "epoch": 3.136963696369637, "percentage": 15.68, "elapsed_time": "1:07:17", "remaining_time": "6:01:44", "throughput": 1490.11, "total_tokens": 6016544} {"current_steps": 28520, "total_steps": 181800, "loss": 0.1006, "lr": 4.9509015975024665e-05, "epoch": 3.1375137513751374, "percentage": 15.69, "elapsed_time": "1:07:18", "remaining_time": "6:01:43", "throughput": 1490.12, "total_tokens": 6017632} {"current_steps": 28525, "total_steps": 181800, "loss": 0.0567, "lr": 4.9508542537219544e-05, "epoch": 3.138063806380638, "percentage": 15.69, "elapsed_time": "1:07:19", "remaining_time": "6:01:43", "throughput": 1490.15, "total_tokens": 6018752} {"current_steps": 28530, "total_steps": 181800, "loss": 0.0137, "lr": 4.950806887353095e-05, "epoch": 3.1386138613861387, "percentage": 15.69, "elapsed_time": "1:07:19", "remaining_time": "6:01:42", "throughput": 1490.15, "total_tokens": 6019776} {"current_steps": 28535, "total_steps": 181800, "loss": 0.0465, "lr": 4.950759498396325e-05, "epoch": 3.139163916391639, "percentage": 15.7, "elapsed_time": "1:07:20", "remaining_time": "6:01:41", "throughput": 1490.17, "total_tokens": 6020896} {"current_steps": 28540, "total_steps": 181800, "loss": 0.0663, "lr": 4.95071208685208e-05, "epoch": 3.1397139713971396, "percentage": 15.7, "elapsed_time": "1:07:21", "remaining_time": "6:01:40", "throughput": 1490.18, "total_tokens": 6021952} {"current_steps": 28545, "total_steps": 181800, "loss": 0.1103, "lr": 4.950664652720798e-05, "epoch": 3.1402640264026402, "percentage": 15.7, "elapsed_time": "1:07:21", "remaining_time": "6:01:39", "throughput": 1490.21, "total_tokens": 6023104} {"current_steps": 28550, "total_steps": 181800, "loss": 0.0224, "lr": 4.950617196002916e-05, "epoch": 3.140814081408141, "percentage": 15.7, "elapsed_time": "1:07:22", "remaining_time": "6:01:39", "throughput": 1490.2, "total_tokens": 6024128} {"current_steps": 28555, "total_steps": 181800, "loss": 0.0127, "lr": 4.9505697166988705e-05, "epoch": 3.1413641364136415, "percentage": 15.71, "elapsed_time": "1:07:23", "remaining_time": "6:01:38", "throughput": 1490.2, "total_tokens": 6025152} {"current_steps": 28560, "total_steps": 181800, "loss": 0.0728, "lr": 4.9505222148091e-05, "epoch": 3.1419141914191417, "percentage": 15.71, "elapsed_time": "1:07:23", "remaining_time": "6:01:37", "throughput": 1490.22, "total_tokens": 6026240} {"current_steps": 28565, "total_steps": 181800, "loss": 0.0583, "lr": 4.9504746903340424e-05, "epoch": 3.1424642464246424, "percentage": 15.71, "elapsed_time": "1:07:24", "remaining_time": "6:01:36", "throughput": 1490.23, "total_tokens": 6027328} {"current_steps": 28570, "total_steps": 181800, "loss": 0.068, "lr": 4.9504271432741354e-05, "epoch": 3.143014301430143, "percentage": 15.72, "elapsed_time": "1:07:25", "remaining_time": "6:01:35", "throughput": 1490.24, "total_tokens": 6028384} {"current_steps": 28575, "total_steps": 181800, "loss": 0.0194, "lr": 4.9503795736298173e-05, "epoch": 3.1435643564356437, "percentage": 15.72, "elapsed_time": "1:07:25", "remaining_time": "6:01:35", "throughput": 1490.24, "total_tokens": 6029440} {"current_steps": 28580, "total_steps": 181800, "loss": 0.1352, "lr": 4.950331981401527e-05, "epoch": 3.1441144114411443, "percentage": 15.72, "elapsed_time": "1:07:26", "remaining_time": "6:01:34", "throughput": 1490.25, "total_tokens": 6030496} {"current_steps": 28585, "total_steps": 181800, "loss": 0.0399, "lr": 4.950284366589702e-05, "epoch": 3.1446644664466445, "percentage": 15.72, "elapsed_time": "1:07:27", "remaining_time": "6:01:33", "throughput": 1490.27, "total_tokens": 6031584} {"current_steps": 28590, "total_steps": 181800, "loss": 0.0216, "lr": 4.9502367291947814e-05, "epoch": 3.145214521452145, "percentage": 15.73, "elapsed_time": "1:07:28", "remaining_time": "6:01:32", "throughput": 1490.28, "total_tokens": 6032672} {"current_steps": 28595, "total_steps": 181800, "loss": 0.0505, "lr": 4.9501890692172055e-05, "epoch": 3.145764576457646, "percentage": 15.73, "elapsed_time": "1:07:28", "remaining_time": "6:01:31", "throughput": 1490.27, "total_tokens": 6033664} {"current_steps": 28600, "total_steps": 181800, "loss": 0.057, "lr": 4.950141386657412e-05, "epoch": 3.1463146314631465, "percentage": 15.73, "elapsed_time": "1:07:29", "remaining_time": "6:01:31", "throughput": 1490.29, "total_tokens": 6034752} {"current_steps": 28605, "total_steps": 181800, "loss": 0.1799, "lr": 4.950093681515842e-05, "epoch": 3.1468646864686467, "percentage": 15.73, "elapsed_time": "1:07:30", "remaining_time": "6:01:30", "throughput": 1490.29, "total_tokens": 6035776} {"current_steps": 28610, "total_steps": 181800, "loss": 0.0248, "lr": 4.9500459537929326e-05, "epoch": 3.1474147414741473, "percentage": 15.74, "elapsed_time": "1:07:30", "remaining_time": "6:01:29", "throughput": 1490.29, "total_tokens": 6036832} {"current_steps": 28615, "total_steps": 181800, "loss": 0.0993, "lr": 4.949998203489126e-05, "epoch": 3.147964796479648, "percentage": 15.74, "elapsed_time": "1:07:31", "remaining_time": "6:01:28", "throughput": 1490.32, "total_tokens": 6037952} {"current_steps": 28620, "total_steps": 181800, "loss": 0.1403, "lr": 4.949950430604862e-05, "epoch": 3.1485148514851486, "percentage": 15.74, "elapsed_time": "1:07:32", "remaining_time": "6:01:27", "throughput": 1490.33, "total_tokens": 6039040} {"current_steps": 28625, "total_steps": 181800, "loss": 0.0602, "lr": 4.94990263514058e-05, "epoch": 3.149064906490649, "percentage": 15.75, "elapsed_time": "1:07:32", "remaining_time": "6:01:27", "throughput": 1490.35, "total_tokens": 6040128} {"current_steps": 28630, "total_steps": 181800, "loss": 0.0692, "lr": 4.9498548170967216e-05, "epoch": 3.1496149614961495, "percentage": 15.75, "elapsed_time": "1:07:33", "remaining_time": "6:01:26", "throughput": 1490.37, "total_tokens": 6041248} {"current_steps": 28635, "total_steps": 181800, "loss": 0.0913, "lr": 4.949806976473727e-05, "epoch": 3.15016501650165, "percentage": 15.75, "elapsed_time": "1:07:34", "remaining_time": "6:01:25", "throughput": 1490.39, "total_tokens": 6042336} {"current_steps": 28640, "total_steps": 181800, "loss": 0.0373, "lr": 4.949759113272035e-05, "epoch": 3.150715071507151, "percentage": 15.75, "elapsed_time": "1:07:34", "remaining_time": "6:01:24", "throughput": 1490.4, "total_tokens": 6043424} {"current_steps": 28645, "total_steps": 181800, "loss": 0.0053, "lr": 4.949711227492091e-05, "epoch": 3.1512651265126514, "percentage": 15.76, "elapsed_time": "1:07:35", "remaining_time": "6:01:23", "throughput": 1490.4, "total_tokens": 6044448} {"current_steps": 28650, "total_steps": 181800, "loss": 0.0971, "lr": 4.949663319134333e-05, "epoch": 3.1518151815181517, "percentage": 15.76, "elapsed_time": "1:07:36", "remaining_time": "6:01:22", "throughput": 1490.41, "total_tokens": 6045504} {"current_steps": 28655, "total_steps": 181800, "loss": 0.0251, "lr": 4.9496153881992044e-05, "epoch": 3.1523652365236523, "percentage": 15.76, "elapsed_time": "1:07:36", "remaining_time": "6:01:22", "throughput": 1490.43, "total_tokens": 6046592} {"current_steps": 28660, "total_steps": 181800, "loss": 0.0248, "lr": 4.9495674346871454e-05, "epoch": 3.152915291529153, "percentage": 15.76, "elapsed_time": "1:07:37", "remaining_time": "6:01:21", "throughput": 1490.44, "total_tokens": 6047680} {"current_steps": 28665, "total_steps": 181800, "loss": 0.0145, "lr": 4.9495194585985996e-05, "epoch": 3.1534653465346536, "percentage": 15.77, "elapsed_time": "1:07:38", "remaining_time": "6:01:20", "throughput": 1490.46, "total_tokens": 6048768} {"current_steps": 28670, "total_steps": 181800, "loss": 0.0489, "lr": 4.949471459934008e-05, "epoch": 3.1540154015401543, "percentage": 15.77, "elapsed_time": "1:07:39", "remaining_time": "6:01:19", "throughput": 1490.47, "total_tokens": 6049824} {"current_steps": 28675, "total_steps": 181800, "loss": 0.1098, "lr": 4.949423438693813e-05, "epoch": 3.1545654565456545, "percentage": 15.77, "elapsed_time": "1:07:39", "remaining_time": "6:01:18", "throughput": 1490.47, "total_tokens": 6050848} {"current_steps": 28680, "total_steps": 181800, "loss": 0.0858, "lr": 4.9493753948784584e-05, "epoch": 3.155115511551155, "percentage": 15.78, "elapsed_time": "1:07:40", "remaining_time": "6:01:18", "throughput": 1490.48, "total_tokens": 6051936} {"current_steps": 28685, "total_steps": 181800, "loss": 0.0412, "lr": 4.9493273284883854e-05, "epoch": 3.1556655665566558, "percentage": 15.78, "elapsed_time": "1:07:41", "remaining_time": "6:01:17", "throughput": 1490.47, "total_tokens": 6052928} {"current_steps": 28690, "total_steps": 181800, "loss": 0.1528, "lr": 4.949279239524037e-05, "epoch": 3.1562156215621564, "percentage": 15.78, "elapsed_time": "1:07:41", "remaining_time": "6:01:16", "throughput": 1490.49, "total_tokens": 6054016} {"current_steps": 28695, "total_steps": 181800, "loss": 0.1065, "lr": 4.9492311279858585e-05, "epoch": 3.1567656765676566, "percentage": 15.78, "elapsed_time": "1:07:42", "remaining_time": "6:01:15", "throughput": 1490.49, "total_tokens": 6055040} {"current_steps": 28700, "total_steps": 181800, "loss": 0.0216, "lr": 4.949182993874292e-05, "epoch": 3.1573157315731573, "percentage": 15.79, "elapsed_time": "1:07:43", "remaining_time": "6:01:14", "throughput": 1490.5, "total_tokens": 6056096} {"current_steps": 28705, "total_steps": 181800, "loss": 0.0544, "lr": 4.94913483718978e-05, "epoch": 3.157865786578658, "percentage": 15.79, "elapsed_time": "1:07:43", "remaining_time": "6:01:13", "throughput": 1490.51, "total_tokens": 6057152} {"current_steps": 28710, "total_steps": 181800, "loss": 0.0619, "lr": 4.9490866579327674e-05, "epoch": 3.1584158415841586, "percentage": 15.79, "elapsed_time": "1:07:44", "remaining_time": "6:01:13", "throughput": 1490.52, "total_tokens": 6058240} {"current_steps": 28715, "total_steps": 181800, "loss": 0.0391, "lr": 4.9490384561036995e-05, "epoch": 3.1589658965896588, "percentage": 15.79, "elapsed_time": "1:07:45", "remaining_time": "6:01:12", "throughput": 1490.52, "total_tokens": 6059264} {"current_steps": 28720, "total_steps": 181800, "loss": 0.0998, "lr": 4.9489902317030176e-05, "epoch": 3.1595159515951594, "percentage": 15.8, "elapsed_time": "1:07:45", "remaining_time": "6:01:11", "throughput": 1490.52, "total_tokens": 6060256} {"current_steps": 28725, "total_steps": 181800, "loss": 0.0165, "lr": 4.948941984731169e-05, "epoch": 3.16006600660066, "percentage": 15.8, "elapsed_time": "1:07:46", "remaining_time": "6:01:10", "throughput": 1490.52, "total_tokens": 6061280} {"current_steps": 28730, "total_steps": 181800, "loss": 0.1208, "lr": 4.948893715188597e-05, "epoch": 3.1606160616061607, "percentage": 15.8, "elapsed_time": "1:07:47", "remaining_time": "6:01:09", "throughput": 1490.52, "total_tokens": 6062336} {"current_steps": 28735, "total_steps": 181800, "loss": 0.1295, "lr": 4.948845423075748e-05, "epoch": 3.1611661166116614, "percentage": 15.81, "elapsed_time": "1:07:47", "remaining_time": "6:01:09", "throughput": 1490.52, "total_tokens": 6063328} {"current_steps": 28740, "total_steps": 181800, "loss": 0.0279, "lr": 4.9487971083930637e-05, "epoch": 3.1617161716171616, "percentage": 15.81, "elapsed_time": "1:07:48", "remaining_time": "6:01:08", "throughput": 1490.52, "total_tokens": 6064352} {"current_steps": 28745, "total_steps": 181800, "loss": 0.0729, "lr": 4.948748771140993e-05, "epoch": 3.162266226622662, "percentage": 15.81, "elapsed_time": "1:07:49", "remaining_time": "6:01:07", "throughput": 1490.52, "total_tokens": 6065408} {"current_steps": 28750, "total_steps": 181800, "loss": 0.0693, "lr": 4.948700411319979e-05, "epoch": 3.162816281628163, "percentage": 15.81, "elapsed_time": "1:07:49", "remaining_time": "6:01:06", "throughput": 1490.54, "total_tokens": 6066496} {"current_steps": 28755, "total_steps": 181800, "loss": 0.0208, "lr": 4.948652028930468e-05, "epoch": 3.1633663366336635, "percentage": 15.82, "elapsed_time": "1:07:50", "remaining_time": "6:01:05", "throughput": 1490.56, "total_tokens": 6067616} {"current_steps": 28760, "total_steps": 181800, "loss": 0.0935, "lr": 4.948603623972907e-05, "epoch": 3.1639163916391637, "percentage": 15.82, "elapsed_time": "1:07:51", "remaining_time": "6:01:04", "throughput": 1490.57, "total_tokens": 6068672} {"current_steps": 28765, "total_steps": 181800, "loss": 0.109, "lr": 4.948555196447742e-05, "epoch": 3.1644664466446644, "percentage": 15.82, "elapsed_time": "1:07:52", "remaining_time": "6:01:04", "throughput": 1490.59, "total_tokens": 6069760} {"current_steps": 28770, "total_steps": 181800, "loss": 0.0748, "lr": 4.948506746355418e-05, "epoch": 3.165016501650165, "percentage": 15.83, "elapsed_time": "1:07:52", "remaining_time": "6:01:03", "throughput": 1490.6, "total_tokens": 6070816} {"current_steps": 28775, "total_steps": 181800, "loss": 0.0734, "lr": 4.9484582736963816e-05, "epoch": 3.1655665566556657, "percentage": 15.83, "elapsed_time": "1:07:53", "remaining_time": "6:01:02", "throughput": 1490.62, "total_tokens": 6071936} {"current_steps": 28780, "total_steps": 181800, "loss": 0.1004, "lr": 4.9484097784710805e-05, "epoch": 3.1661166116611663, "percentage": 15.83, "elapsed_time": "1:07:54", "remaining_time": "6:01:01", "throughput": 1490.63, "total_tokens": 6073024} {"current_steps": 28785, "total_steps": 181800, "loss": 0.1141, "lr": 4.948361260679961e-05, "epoch": 3.1666666666666665, "percentage": 15.83, "elapsed_time": "1:07:54", "remaining_time": "6:01:00", "throughput": 1490.63, "total_tokens": 6074048} {"current_steps": 28790, "total_steps": 181800, "loss": 0.0905, "lr": 4.9483127203234715e-05, "epoch": 3.167216721672167, "percentage": 15.84, "elapsed_time": "1:07:55", "remaining_time": "6:01:00", "throughput": 1490.63, "total_tokens": 6075072} {"current_steps": 28795, "total_steps": 181800, "loss": 0.1376, "lr": 4.9482641574020586e-05, "epoch": 3.167766776677668, "percentage": 15.84, "elapsed_time": "1:07:56", "remaining_time": "6:00:59", "throughput": 1490.62, "total_tokens": 6076064} {"current_steps": 28800, "total_steps": 181800, "loss": 0.051, "lr": 4.948215571916169e-05, "epoch": 3.1683168316831685, "percentage": 15.84, "elapsed_time": "1:07:56", "remaining_time": "6:00:58", "throughput": 1490.63, "total_tokens": 6077120} {"current_steps": 28805, "total_steps": 181800, "loss": 0.0763, "lr": 4.9481669638662516e-05, "epoch": 3.1688668866886687, "percentage": 15.84, "elapsed_time": "1:07:57", "remaining_time": "6:00:57", "throughput": 1490.63, "total_tokens": 6078144} {"current_steps": 28810, "total_steps": 181800, "loss": 0.0229, "lr": 4.9481183332527534e-05, "epoch": 3.1694169416941693, "percentage": 15.85, "elapsed_time": "1:07:58", "remaining_time": "6:00:56", "throughput": 1490.66, "total_tokens": 6079296} {"current_steps": 28815, "total_steps": 181800, "loss": 0.0196, "lr": 4.9480696800761236e-05, "epoch": 3.16996699669967, "percentage": 15.85, "elapsed_time": "1:07:58", "remaining_time": "6:00:55", "throughput": 1490.67, "total_tokens": 6080352} {"current_steps": 28820, "total_steps": 181800, "loss": 0.0536, "lr": 4.948021004336811e-05, "epoch": 3.1705170517051706, "percentage": 15.85, "elapsed_time": "1:07:59", "remaining_time": "6:00:55", "throughput": 1490.68, "total_tokens": 6081408} {"current_steps": 28825, "total_steps": 181800, "loss": 0.0909, "lr": 4.947972306035263e-05, "epoch": 3.1710671067106713, "percentage": 15.86, "elapsed_time": "1:08:00", "remaining_time": "6:00:54", "throughput": 1490.69, "total_tokens": 6082496} {"current_steps": 28830, "total_steps": 181800, "loss": 0.1469, "lr": 4.9479235851719284e-05, "epoch": 3.1716171617161715, "percentage": 15.86, "elapsed_time": "1:08:01", "remaining_time": "6:00:53", "throughput": 1490.7, "total_tokens": 6083584} {"current_steps": 28835, "total_steps": 181800, "loss": 0.0744, "lr": 4.947874841747258e-05, "epoch": 3.172167216721672, "percentage": 15.86, "elapsed_time": "1:08:01", "remaining_time": "6:00:52", "throughput": 1490.7, "total_tokens": 6084608} {"current_steps": 28840, "total_steps": 181800, "loss": 0.0518, "lr": 4.947826075761698e-05, "epoch": 3.1727172717271728, "percentage": 15.86, "elapsed_time": "1:08:02", "remaining_time": "6:00:51", "throughput": 1490.72, "total_tokens": 6085696} {"current_steps": 28845, "total_steps": 181800, "loss": 0.0483, "lr": 4.947777287215701e-05, "epoch": 3.1732673267326734, "percentage": 15.87, "elapsed_time": "1:08:03", "remaining_time": "6:00:51", "throughput": 1490.73, "total_tokens": 6086784} {"current_steps": 28850, "total_steps": 181800, "loss": 0.0684, "lr": 4.947728476109715e-05, "epoch": 3.1738173817381736, "percentage": 15.87, "elapsed_time": "1:08:03", "remaining_time": "6:00:50", "throughput": 1490.75, "total_tokens": 6087872} {"current_steps": 28855, "total_steps": 181800, "loss": 0.0601, "lr": 4.94767964244419e-05, "epoch": 3.1743674367436743, "percentage": 15.87, "elapsed_time": "1:08:04", "remaining_time": "6:00:49", "throughput": 1490.75, "total_tokens": 6088928} {"current_steps": 28860, "total_steps": 181800, "loss": 0.0304, "lr": 4.947630786219576e-05, "epoch": 3.174917491749175, "percentage": 15.87, "elapsed_time": "1:08:05", "remaining_time": "6:00:48", "throughput": 1490.75, "total_tokens": 6089952} {"current_steps": 28865, "total_steps": 181800, "loss": 0.1192, "lr": 4.947581907436324e-05, "epoch": 3.1754675467546756, "percentage": 15.88, "elapsed_time": "1:08:05", "remaining_time": "6:00:47", "throughput": 1490.76, "total_tokens": 6091008} {"current_steps": 28870, "total_steps": 181800, "loss": 0.0833, "lr": 4.947533006094884e-05, "epoch": 3.1760176017601762, "percentage": 15.88, "elapsed_time": "1:08:06", "remaining_time": "6:00:47", "throughput": 1490.78, "total_tokens": 6092096} {"current_steps": 28875, "total_steps": 181800, "loss": 0.0104, "lr": 4.9474840821957064e-05, "epoch": 3.1765676567656764, "percentage": 15.88, "elapsed_time": "1:08:07", "remaining_time": "6:00:46", "throughput": 1490.78, "total_tokens": 6093152} {"current_steps": 28880, "total_steps": 181800, "loss": 0.054, "lr": 4.947435135739242e-05, "epoch": 3.177117711771177, "percentage": 15.89, "elapsed_time": "1:08:07", "remaining_time": "6:00:45", "throughput": 1490.78, "total_tokens": 6094176} {"current_steps": 28885, "total_steps": 181800, "loss": 0.0286, "lr": 4.9473861667259434e-05, "epoch": 3.1776677667766777, "percentage": 15.89, "elapsed_time": "1:08:08", "remaining_time": "6:00:44", "throughput": 1490.8, "total_tokens": 6095296} {"current_steps": 28890, "total_steps": 181800, "loss": 0.0843, "lr": 4.9473371751562604e-05, "epoch": 3.1782178217821784, "percentage": 15.89, "elapsed_time": "1:08:09", "remaining_time": "6:00:43", "throughput": 1490.81, "total_tokens": 6096352} {"current_steps": 28895, "total_steps": 181800, "loss": 0.0705, "lr": 4.9472881610306456e-05, "epoch": 3.1787678767876786, "percentage": 15.89, "elapsed_time": "1:08:09", "remaining_time": "6:00:43", "throughput": 1490.82, "total_tokens": 6097408} {"current_steps": 28900, "total_steps": 181800, "loss": 0.0868, "lr": 4.947239124349549e-05, "epoch": 3.1793179317931792, "percentage": 15.9, "elapsed_time": "1:08:10", "remaining_time": "6:00:42", "throughput": 1490.81, "total_tokens": 6098400} {"current_steps": 28905, "total_steps": 181800, "loss": 0.0137, "lr": 4.947190065113424e-05, "epoch": 3.17986798679868, "percentage": 15.9, "elapsed_time": "1:08:11", "remaining_time": "6:00:41", "throughput": 1490.82, "total_tokens": 6099456} {"current_steps": 28910, "total_steps": 181800, "loss": 0.0324, "lr": 4.947140983322723e-05, "epoch": 3.1804180418041805, "percentage": 15.9, "elapsed_time": "1:08:12", "remaining_time": "6:00:40", "throughput": 1490.83, "total_tokens": 6100544} {"current_steps": 28915, "total_steps": 181800, "loss": 0.0569, "lr": 4.947091878977897e-05, "epoch": 3.180968096809681, "percentage": 15.9, "elapsed_time": "1:08:12", "remaining_time": "6:00:39", "throughput": 1490.83, "total_tokens": 6101568} {"current_steps": 28920, "total_steps": 181800, "loss": 0.0227, "lr": 4.947042752079401e-05, "epoch": 3.1815181518151814, "percentage": 15.91, "elapsed_time": "1:08:13", "remaining_time": "6:00:39", "throughput": 1490.85, "total_tokens": 6102656} {"current_steps": 28925, "total_steps": 181800, "loss": 0.0442, "lr": 4.946993602627684e-05, "epoch": 3.182068206820682, "percentage": 15.91, "elapsed_time": "1:08:14", "remaining_time": "6:00:38", "throughput": 1490.85, "total_tokens": 6103680} {"current_steps": 28930, "total_steps": 181800, "loss": 0.015, "lr": 4.946944430623203e-05, "epoch": 3.1826182618261827, "percentage": 15.91, "elapsed_time": "1:08:14", "remaining_time": "6:00:37", "throughput": 1490.85, "total_tokens": 6104704} {"current_steps": 28935, "total_steps": 181800, "loss": 0.024, "lr": 4.946895236066408e-05, "epoch": 3.1831683168316833, "percentage": 15.92, "elapsed_time": "1:08:15", "remaining_time": "6:00:36", "throughput": 1490.85, "total_tokens": 6105728} {"current_steps": 28940, "total_steps": 181800, "loss": 0.0949, "lr": 4.946846018957755e-05, "epoch": 3.1837183718371835, "percentage": 15.92, "elapsed_time": "1:08:16", "remaining_time": "6:00:35", "throughput": 1490.86, "total_tokens": 6106816} {"current_steps": 28945, "total_steps": 181800, "loss": 0.0645, "lr": 4.9467967792976956e-05, "epoch": 3.184268426842684, "percentage": 15.92, "elapsed_time": "1:08:16", "remaining_time": "6:00:34", "throughput": 1490.85, "total_tokens": 6107808} {"current_steps": 28950, "total_steps": 181800, "loss": 0.0719, "lr": 4.946747517086684e-05, "epoch": 3.184818481848185, "percentage": 15.92, "elapsed_time": "1:08:17", "remaining_time": "6:00:34", "throughput": 1490.87, "total_tokens": 6108896} {"current_steps": 28955, "total_steps": 181800, "loss": 0.0118, "lr": 4.946698232325175e-05, "epoch": 3.1853685368536855, "percentage": 15.93, "elapsed_time": "1:08:18", "remaining_time": "6:00:33", "throughput": 1490.87, "total_tokens": 6109920} {"current_steps": 28960, "total_steps": 181800, "loss": 0.0475, "lr": 4.9466489250136224e-05, "epoch": 3.1859185918591857, "percentage": 15.93, "elapsed_time": "1:08:18", "remaining_time": "6:00:32", "throughput": 1490.85, "total_tokens": 6110880} {"current_steps": 28965, "total_steps": 181800, "loss": 0.0365, "lr": 4.9465995951524805e-05, "epoch": 3.1864686468646863, "percentage": 15.93, "elapsed_time": "1:08:19", "remaining_time": "6:00:31", "throughput": 1490.86, "total_tokens": 6111936} {"current_steps": 28970, "total_steps": 181800, "loss": 0.055, "lr": 4.946550242742204e-05, "epoch": 3.187018701870187, "percentage": 15.94, "elapsed_time": "1:08:20", "remaining_time": "6:00:30", "throughput": 1490.87, "total_tokens": 6112992} {"current_steps": 28975, "total_steps": 181800, "loss": 0.0206, "lr": 4.946500867783249e-05, "epoch": 3.1875687568756876, "percentage": 15.94, "elapsed_time": "1:08:20", "remaining_time": "6:00:30", "throughput": 1490.88, "total_tokens": 6114080} {"current_steps": 28980, "total_steps": 181800, "loss": 0.1232, "lr": 4.9464514702760684e-05, "epoch": 3.1881188118811883, "percentage": 15.94, "elapsed_time": "1:08:21", "remaining_time": "6:00:29", "throughput": 1490.9, "total_tokens": 6115200} {"current_steps": 28985, "total_steps": 181800, "loss": 0.0526, "lr": 4.946402050221118e-05, "epoch": 3.1886688668866885, "percentage": 15.94, "elapsed_time": "1:08:22", "remaining_time": "6:00:28", "throughput": 1490.91, "total_tokens": 6116256} {"current_steps": 28990, "total_steps": 181800, "loss": 0.0665, "lr": 4.9463526076188556e-05, "epoch": 3.189218921892189, "percentage": 15.95, "elapsed_time": "1:08:23", "remaining_time": "6:00:27", "throughput": 1490.91, "total_tokens": 6117280} {"current_steps": 28995, "total_steps": 181800, "loss": 0.0893, "lr": 4.9463031424697335e-05, "epoch": 3.18976897689769, "percentage": 15.95, "elapsed_time": "1:08:23", "remaining_time": "6:00:26", "throughput": 1490.91, "total_tokens": 6118336} {"current_steps": 29000, "total_steps": 181800, "loss": 0.0257, "lr": 4.94625365477421e-05, "epoch": 3.1903190319031904, "percentage": 15.95, "elapsed_time": "1:08:24", "remaining_time": "6:00:26", "throughput": 1490.94, "total_tokens": 6119456} {"current_steps": 29005, "total_steps": 181800, "loss": 0.0067, "lr": 4.94620414453274e-05, "epoch": 3.190869086908691, "percentage": 15.95, "elapsed_time": "1:08:25", "remaining_time": "6:00:25", "throughput": 1490.93, "total_tokens": 6120448} {"current_steps": 29010, "total_steps": 181800, "loss": 0.0781, "lr": 4.94615461174578e-05, "epoch": 3.1914191419141913, "percentage": 15.96, "elapsed_time": "1:08:25", "remaining_time": "6:00:24", "throughput": 1490.94, "total_tokens": 6121536} {"current_steps": 29015, "total_steps": 181800, "loss": 0.0581, "lr": 4.946105056413788e-05, "epoch": 3.191969196919692, "percentage": 15.96, "elapsed_time": "1:08:26", "remaining_time": "6:00:23", "throughput": 1490.92, "total_tokens": 6122496} {"current_steps": 29020, "total_steps": 181800, "loss": 0.0425, "lr": 4.946055478537218e-05, "epoch": 3.1925192519251926, "percentage": 15.96, "elapsed_time": "1:08:27", "remaining_time": "6:00:22", "throughput": 1490.94, "total_tokens": 6123584} {"current_steps": 29025, "total_steps": 181800, "loss": 0.0224, "lr": 4.946005878116529e-05, "epoch": 3.1930693069306932, "percentage": 15.97, "elapsed_time": "1:08:27", "remaining_time": "6:00:22", "throughput": 1490.95, "total_tokens": 6124672} {"current_steps": 29030, "total_steps": 181800, "loss": 0.0844, "lr": 4.945956255152178e-05, "epoch": 3.1936193619361934, "percentage": 15.97, "elapsed_time": "1:08:28", "remaining_time": "6:00:21", "throughput": 1490.96, "total_tokens": 6125728} {"current_steps": 29035, "total_steps": 181800, "loss": 0.0135, "lr": 4.94590660964462e-05, "epoch": 3.194169416941694, "percentage": 15.97, "elapsed_time": "1:08:29", "remaining_time": "6:00:20", "throughput": 1490.96, "total_tokens": 6126752} {"current_steps": 29040, "total_steps": 181800, "loss": 0.0381, "lr": 4.945856941594317e-05, "epoch": 3.1947194719471947, "percentage": 15.97, "elapsed_time": "1:08:29", "remaining_time": "6:00:19", "throughput": 1491.0, "total_tokens": 6127936} {"current_steps": 29045, "total_steps": 181800, "loss": 0.0395, "lr": 4.945807251001723e-05, "epoch": 3.1952695269526954, "percentage": 15.98, "elapsed_time": "1:08:30", "remaining_time": "6:00:18", "throughput": 1491.01, "total_tokens": 6129024} {"current_steps": 29050, "total_steps": 181800, "loss": 0.0419, "lr": 4.9457575378672974e-05, "epoch": 3.1958195819581956, "percentage": 15.98, "elapsed_time": "1:08:31", "remaining_time": "6:00:18", "throughput": 1491.02, "total_tokens": 6130080} {"current_steps": 29055, "total_steps": 181800, "loss": 0.0827, "lr": 4.945707802191497e-05, "epoch": 3.1963696369636962, "percentage": 15.98, "elapsed_time": "1:08:32", "remaining_time": "6:00:17", "throughput": 1491.01, "total_tokens": 6131072} {"current_steps": 29060, "total_steps": 181800, "loss": 0.0483, "lr": 4.945658043974782e-05, "epoch": 3.196919691969197, "percentage": 15.98, "elapsed_time": "1:08:32", "remaining_time": "6:00:16", "throughput": 1491.01, "total_tokens": 6132128} {"current_steps": 29065, "total_steps": 181800, "loss": 0.0745, "lr": 4.9456082632176115e-05, "epoch": 3.1974697469746975, "percentage": 15.99, "elapsed_time": "1:08:33", "remaining_time": "6:00:15", "throughput": 1491.03, "total_tokens": 6133216} {"current_steps": 29070, "total_steps": 181800, "loss": 0.0865, "lr": 4.945558459920442e-05, "epoch": 3.198019801980198, "percentage": 15.99, "elapsed_time": "1:08:34", "remaining_time": "6:00:14", "throughput": 1491.03, "total_tokens": 6134240} {"current_steps": 29075, "total_steps": 181800, "loss": 0.0915, "lr": 4.945508634083734e-05, "epoch": 3.1985698569856984, "percentage": 15.99, "elapsed_time": "1:08:34", "remaining_time": "6:00:14", "throughput": 1491.04, "total_tokens": 6135296} {"current_steps": 29080, "total_steps": 181800, "loss": 0.0278, "lr": 4.945458785707946e-05, "epoch": 3.199119911991199, "percentage": 16.0, "elapsed_time": "1:08:35", "remaining_time": "6:00:13", "throughput": 1491.06, "total_tokens": 6136416} {"current_steps": 29085, "total_steps": 181800, "loss": 0.0486, "lr": 4.945408914793538e-05, "epoch": 3.1996699669966997, "percentage": 16.0, "elapsed_time": "1:08:36", "remaining_time": "6:00:12", "throughput": 1491.05, "total_tokens": 6137408} {"current_steps": 29090, "total_steps": 181800, "loss": 0.055, "lr": 4.9453590213409697e-05, "epoch": 3.2002200220022003, "percentage": 16.0, "elapsed_time": "1:08:36", "remaining_time": "6:00:11", "throughput": 1491.06, "total_tokens": 6138496} {"current_steps": 29095, "total_steps": 181800, "loss": 0.0353, "lr": 4.945309105350701e-05, "epoch": 3.200770077007701, "percentage": 16.0, "elapsed_time": "1:08:37", "remaining_time": "6:00:10", "throughput": 1491.08, "total_tokens": 6139584} {"current_steps": 29100, "total_steps": 181800, "loss": 0.2, "lr": 4.9452591668231905e-05, "epoch": 3.201320132013201, "percentage": 16.01, "elapsed_time": "1:08:38", "remaining_time": "6:00:10", "throughput": 1491.08, "total_tokens": 6140608} {"current_steps": 29105, "total_steps": 181800, "loss": 0.1517, "lr": 4.9452092057589e-05, "epoch": 3.201870187018702, "percentage": 16.01, "elapsed_time": "1:08:38", "remaining_time": "6:00:09", "throughput": 1491.08, "total_tokens": 6141632} {"current_steps": 29110, "total_steps": 181800, "loss": 0.0897, "lr": 4.945159222158291e-05, "epoch": 3.2024202420242025, "percentage": 16.01, "elapsed_time": "1:08:39", "remaining_time": "6:00:08", "throughput": 1491.07, "total_tokens": 6142656} {"current_steps": 29115, "total_steps": 181800, "loss": 0.0113, "lr": 4.9451092160218216e-05, "epoch": 3.202970297029703, "percentage": 16.01, "elapsed_time": "1:08:40", "remaining_time": "6:00:07", "throughput": 1491.08, "total_tokens": 6143712} {"current_steps": 29120, "total_steps": 181800, "loss": 0.0525, "lr": 4.945059187349954e-05, "epoch": 3.2035203520352034, "percentage": 16.02, "elapsed_time": "1:08:40", "remaining_time": "6:00:06", "throughput": 1491.09, "total_tokens": 6144800} {"current_steps": 29125, "total_steps": 181800, "loss": 0.1425, "lr": 4.945009136143149e-05, "epoch": 3.204070407040704, "percentage": 16.02, "elapsed_time": "1:08:41", "remaining_time": "6:00:06", "throughput": 1491.09, "total_tokens": 6145792} {"current_steps": 29130, "total_steps": 181800, "loss": 0.0708, "lr": 4.944959062401868e-05, "epoch": 3.2046204620462047, "percentage": 16.02, "elapsed_time": "1:08:42", "remaining_time": "6:00:05", "throughput": 1491.11, "total_tokens": 6146912} {"current_steps": 29135, "total_steps": 181800, "loss": 0.0463, "lr": 4.9449089661265724e-05, "epoch": 3.2051705170517053, "percentage": 16.03, "elapsed_time": "1:08:43", "remaining_time": "6:00:04", "throughput": 1491.1, "total_tokens": 6147904} {"current_steps": 29140, "total_steps": 181800, "loss": 0.1397, "lr": 4.944858847317724e-05, "epoch": 3.2057205720572055, "percentage": 16.03, "elapsed_time": "1:08:43", "remaining_time": "6:00:03", "throughput": 1491.11, "total_tokens": 6148992} {"current_steps": 29145, "total_steps": 181800, "loss": 0.0667, "lr": 4.944808705975785e-05, "epoch": 3.206270627062706, "percentage": 16.03, "elapsed_time": "1:08:44", "remaining_time": "6:00:02", "throughput": 1491.1, "total_tokens": 6149984} {"current_steps": 29150, "total_steps": 181800, "loss": 0.0352, "lr": 4.944758542101218e-05, "epoch": 3.206820682068207, "percentage": 16.03, "elapsed_time": "1:08:45", "remaining_time": "6:00:02", "throughput": 1491.12, "total_tokens": 6151072} {"current_steps": 29155, "total_steps": 181800, "loss": 0.0531, "lr": 4.9447083556944834e-05, "epoch": 3.2073707370737075, "percentage": 16.04, "elapsed_time": "1:08:45", "remaining_time": "6:00:01", "throughput": 1491.12, "total_tokens": 6152096} {"current_steps": 29160, "total_steps": 181800, "loss": 0.033, "lr": 4.9446581467560455e-05, "epoch": 3.207920792079208, "percentage": 16.04, "elapsed_time": "1:08:46", "remaining_time": "6:00:00", "throughput": 1491.14, "total_tokens": 6153216} {"current_steps": 29165, "total_steps": 181800, "loss": 0.0127, "lr": 4.944607915286367e-05, "epoch": 3.2084708470847083, "percentage": 16.04, "elapsed_time": "1:08:47", "remaining_time": "5:59:59", "throughput": 1491.14, "total_tokens": 6154240} {"current_steps": 29170, "total_steps": 181800, "loss": 0.1721, "lr": 4.944557661285909e-05, "epoch": 3.209020902090209, "percentage": 16.05, "elapsed_time": "1:08:47", "remaining_time": "5:59:58", "throughput": 1491.13, "total_tokens": 6155232} {"current_steps": 29175, "total_steps": 181800, "loss": 0.124, "lr": 4.944507384755137e-05, "epoch": 3.2095709570957096, "percentage": 16.05, "elapsed_time": "1:08:48", "remaining_time": "5:59:58", "throughput": 1491.14, "total_tokens": 6156288} {"current_steps": 29180, "total_steps": 181800, "loss": 0.1064, "lr": 4.944457085694514e-05, "epoch": 3.2101210121012103, "percentage": 16.05, "elapsed_time": "1:08:49", "remaining_time": "5:59:57", "throughput": 1491.15, "total_tokens": 6157344} {"current_steps": 29185, "total_steps": 181800, "loss": 0.072, "lr": 4.9444067641045024e-05, "epoch": 3.2106710671067105, "percentage": 16.05, "elapsed_time": "1:08:49", "remaining_time": "5:59:56", "throughput": 1491.13, "total_tokens": 6158304} {"current_steps": 29190, "total_steps": 181800, "loss": 0.0327, "lr": 4.9443564199855666e-05, "epoch": 3.211221122112211, "percentage": 16.06, "elapsed_time": "1:08:50", "remaining_time": "5:59:55", "throughput": 1491.12, "total_tokens": 6159296} {"current_steps": 29195, "total_steps": 181800, "loss": 0.0273, "lr": 4.94430605333817e-05, "epoch": 3.2117711771177118, "percentage": 16.06, "elapsed_time": "1:08:51", "remaining_time": "5:59:54", "throughput": 1491.13, "total_tokens": 6160352} {"current_steps": 29200, "total_steps": 181800, "loss": 0.0681, "lr": 4.944255664162778e-05, "epoch": 3.2123212321232124, "percentage": 16.06, "elapsed_time": "1:08:52", "remaining_time": "5:59:54", "throughput": 1491.14, "total_tokens": 6161440} {"current_steps": 29205, "total_steps": 181800, "loss": 0.094, "lr": 4.944205252459855e-05, "epoch": 3.212871287128713, "percentage": 16.06, "elapsed_time": "1:08:52", "remaining_time": "5:59:53", "throughput": 1491.16, "total_tokens": 6162528} {"current_steps": 29210, "total_steps": 181800, "loss": 0.1349, "lr": 4.9441548182298636e-05, "epoch": 3.2134213421342133, "percentage": 16.07, "elapsed_time": "1:08:53", "remaining_time": "5:59:52", "throughput": 1491.15, "total_tokens": 6163520} {"current_steps": 29215, "total_steps": 181800, "loss": 0.0103, "lr": 4.9441043614732705e-05, "epoch": 3.213971397139714, "percentage": 16.07, "elapsed_time": "1:08:54", "remaining_time": "5:59:51", "throughput": 1491.14, "total_tokens": 6164512} {"current_steps": 29220, "total_steps": 181800, "loss": 0.1286, "lr": 4.9440538821905416e-05, "epoch": 3.2145214521452146, "percentage": 16.07, "elapsed_time": "1:08:54", "remaining_time": "5:59:50", "throughput": 1491.14, "total_tokens": 6165536} {"current_steps": 29225, "total_steps": 181800, "loss": 0.0205, "lr": 4.94400338038214e-05, "epoch": 3.215071507150715, "percentage": 16.08, "elapsed_time": "1:08:55", "remaining_time": "5:59:50", "throughput": 1491.14, "total_tokens": 6166592} {"current_steps": 29230, "total_steps": 181800, "loss": 0.0646, "lr": 4.9439528560485316e-05, "epoch": 3.2156215621562154, "percentage": 16.08, "elapsed_time": "1:08:56", "remaining_time": "5:59:49", "throughput": 1491.14, "total_tokens": 6167616} {"current_steps": 29235, "total_steps": 181800, "loss": 0.0141, "lr": 4.943902309190182e-05, "epoch": 3.216171617161716, "percentage": 16.08, "elapsed_time": "1:08:56", "remaining_time": "5:59:48", "throughput": 1491.15, "total_tokens": 6168672} {"current_steps": 29240, "total_steps": 181800, "loss": 0.0761, "lr": 4.943851739807559e-05, "epoch": 3.2167216721672167, "percentage": 16.08, "elapsed_time": "1:08:57", "remaining_time": "5:59:47", "throughput": 1491.15, "total_tokens": 6169696} {"current_steps": 29245, "total_steps": 181800, "loss": 0.1185, "lr": 4.943801147901126e-05, "epoch": 3.2172717271727174, "percentage": 16.09, "elapsed_time": "1:08:58", "remaining_time": "5:59:46", "throughput": 1491.15, "total_tokens": 6170720} {"current_steps": 29250, "total_steps": 181800, "loss": 0.1035, "lr": 4.943750533471351e-05, "epoch": 3.217821782178218, "percentage": 16.09, "elapsed_time": "1:08:58", "remaining_time": "5:59:46", "throughput": 1491.15, "total_tokens": 6171776} {"current_steps": 29255, "total_steps": 181800, "loss": 0.066, "lr": 4.9436998965187e-05, "epoch": 3.218371837183718, "percentage": 16.09, "elapsed_time": "1:08:59", "remaining_time": "5:59:45", "throughput": 1491.17, "total_tokens": 6172864} {"current_steps": 29260, "total_steps": 181800, "loss": 0.0698, "lr": 4.943649237043639e-05, "epoch": 3.218921892189219, "percentage": 16.09, "elapsed_time": "1:09:00", "remaining_time": "5:59:44", "throughput": 1491.17, "total_tokens": 6173888} {"current_steps": 29265, "total_steps": 181800, "loss": 0.0134, "lr": 4.943598555046637e-05, "epoch": 3.2194719471947195, "percentage": 16.1, "elapsed_time": "1:09:00", "remaining_time": "5:59:43", "throughput": 1491.17, "total_tokens": 6174944} {"current_steps": 29270, "total_steps": 181800, "loss": 0.0548, "lr": 4.9435478505281585e-05, "epoch": 3.22002200220022, "percentage": 16.1, "elapsed_time": "1:09:01", "remaining_time": "5:59:42", "throughput": 1491.17, "total_tokens": 6175968} {"current_steps": 29275, "total_steps": 181800, "loss": 0.0683, "lr": 4.943497123488672e-05, "epoch": 3.2205720572057204, "percentage": 16.1, "elapsed_time": "1:09:02", "remaining_time": "5:59:42", "throughput": 1491.17, "total_tokens": 6176992} {"current_steps": 29280, "total_steps": 181800, "loss": 0.0496, "lr": 4.9434463739286454e-05, "epoch": 3.221122112211221, "percentage": 16.11, "elapsed_time": "1:09:03", "remaining_time": "5:59:41", "throughput": 1491.18, "total_tokens": 6178080} {"current_steps": 29285, "total_steps": 181800, "loss": 0.0277, "lr": 4.943395601848546e-05, "epoch": 3.2216721672167217, "percentage": 16.11, "elapsed_time": "1:09:03", "remaining_time": "5:59:40", "throughput": 1491.18, "total_tokens": 6179104} {"current_steps": 29290, "total_steps": 181800, "loss": 0.0604, "lr": 4.9433448072488414e-05, "epoch": 3.2222222222222223, "percentage": 16.11, "elapsed_time": "1:09:04", "remaining_time": "5:59:39", "throughput": 1491.2, "total_tokens": 6180224} {"current_steps": 29295, "total_steps": 181800, "loss": 0.075, "lr": 4.94329399013e-05, "epoch": 3.222772277227723, "percentage": 16.11, "elapsed_time": "1:09:05", "remaining_time": "5:59:38", "throughput": 1491.2, "total_tokens": 6181216} {"current_steps": 29300, "total_steps": 181800, "loss": 0.0214, "lr": 4.9432431504924915e-05, "epoch": 3.223322332233223, "percentage": 16.12, "elapsed_time": "1:09:05", "remaining_time": "5:59:38", "throughput": 1491.2, "total_tokens": 6182272} {"current_steps": 29305, "total_steps": 181800, "loss": 0.0547, "lr": 4.943192288336782e-05, "epoch": 3.223872387238724, "percentage": 16.12, "elapsed_time": "1:09:06", "remaining_time": "5:59:37", "throughput": 1491.2, "total_tokens": 6183296} {"current_steps": 29310, "total_steps": 181800, "loss": 0.1228, "lr": 4.9431414036633424e-05, "epoch": 3.2244224422442245, "percentage": 16.12, "elapsed_time": "1:09:07", "remaining_time": "5:59:36", "throughput": 1491.22, "total_tokens": 6184384} {"current_steps": 29315, "total_steps": 181800, "loss": 0.0374, "lr": 4.94309049647264e-05, "epoch": 3.224972497249725, "percentage": 16.12, "elapsed_time": "1:09:07", "remaining_time": "5:59:35", "throughput": 1491.23, "total_tokens": 6185472} {"current_steps": 29320, "total_steps": 181800, "loss": 0.1028, "lr": 4.9430395667651454e-05, "epoch": 3.2255225522552253, "percentage": 16.13, "elapsed_time": "1:09:08", "remaining_time": "5:59:34", "throughput": 1491.24, "total_tokens": 6186528} {"current_steps": 29325, "total_steps": 181800, "loss": 0.0317, "lr": 4.942988614541327e-05, "epoch": 3.226072607260726, "percentage": 16.13, "elapsed_time": "1:09:09", "remaining_time": "5:59:34", "throughput": 1491.25, "total_tokens": 6187616} {"current_steps": 29330, "total_steps": 181800, "loss": 0.0219, "lr": 4.942937639801655e-05, "epoch": 3.2266226622662266, "percentage": 16.13, "elapsed_time": "1:09:09", "remaining_time": "5:59:33", "throughput": 1491.27, "total_tokens": 6188704} {"current_steps": 29335, "total_steps": 181800, "loss": 0.2203, "lr": 4.942886642546599e-05, "epoch": 3.2271727172717273, "percentage": 16.14, "elapsed_time": "1:09:10", "remaining_time": "5:59:32", "throughput": 1491.27, "total_tokens": 6189728} {"current_steps": 29340, "total_steps": 181800, "loss": 0.1011, "lr": 4.9428356227766294e-05, "epoch": 3.227722772277228, "percentage": 16.14, "elapsed_time": "1:09:11", "remaining_time": "5:59:31", "throughput": 1491.27, "total_tokens": 6190752} {"current_steps": 29345, "total_steps": 181800, "loss": 0.0935, "lr": 4.942784580492216e-05, "epoch": 3.228272827282728, "percentage": 16.14, "elapsed_time": "1:09:12", "remaining_time": "5:59:30", "throughput": 1491.28, "total_tokens": 6191808} {"current_steps": 29350, "total_steps": 181800, "loss": 0.1468, "lr": 4.942733515693829e-05, "epoch": 3.228822882288229, "percentage": 16.14, "elapsed_time": "1:09:12", "remaining_time": "5:59:30", "throughput": 1491.28, "total_tokens": 6192864} {"current_steps": 29355, "total_steps": 181800, "loss": 0.0669, "lr": 4.942682428381939e-05, "epoch": 3.2293729372937294, "percentage": 16.15, "elapsed_time": "1:09:13", "remaining_time": "5:59:29", "throughput": 1491.28, "total_tokens": 6193888} {"current_steps": 29360, "total_steps": 181800, "loss": 0.0993, "lr": 4.9426313185570174e-05, "epoch": 3.22992299229923, "percentage": 16.15, "elapsed_time": "1:09:14", "remaining_time": "5:59:28", "throughput": 1491.28, "total_tokens": 6194880} {"current_steps": 29365, "total_steps": 181800, "loss": 0.0984, "lr": 4.942580186219535e-05, "epoch": 3.2304730473047303, "percentage": 16.15, "elapsed_time": "1:09:14", "remaining_time": "5:59:27", "throughput": 1491.28, "total_tokens": 6195936} {"current_steps": 29370, "total_steps": 181800, "loss": 0.1101, "lr": 4.9425290313699637e-05, "epoch": 3.231023102310231, "percentage": 16.16, "elapsed_time": "1:09:15", "remaining_time": "5:59:26", "throughput": 1491.29, "total_tokens": 6197024} {"current_steps": 29375, "total_steps": 181800, "loss": 0.0654, "lr": 4.942477854008774e-05, "epoch": 3.2315731573157316, "percentage": 16.16, "elapsed_time": "1:09:16", "remaining_time": "5:59:26", "throughput": 1491.29, "total_tokens": 6198048} {"current_steps": 29380, "total_steps": 181800, "loss": 0.0566, "lr": 4.942426654136437e-05, "epoch": 3.2321232123212322, "percentage": 16.16, "elapsed_time": "1:09:16", "remaining_time": "5:59:25", "throughput": 1491.3, "total_tokens": 6199136} {"current_steps": 29385, "total_steps": 181800, "loss": 0.0634, "lr": 4.942375431753427e-05, "epoch": 3.232673267326733, "percentage": 16.16, "elapsed_time": "1:09:17", "remaining_time": "5:59:24", "throughput": 1491.31, "total_tokens": 6200192} {"current_steps": 29390, "total_steps": 181800, "loss": 0.042, "lr": 4.942324186860214e-05, "epoch": 3.233223322332233, "percentage": 16.17, "elapsed_time": "1:09:18", "remaining_time": "5:59:23", "throughput": 1491.32, "total_tokens": 6201248} {"current_steps": 29395, "total_steps": 181800, "loss": 0.0948, "lr": 4.94227291945727e-05, "epoch": 3.2337733773377337, "percentage": 16.17, "elapsed_time": "1:09:18", "remaining_time": "5:59:22", "throughput": 1491.32, "total_tokens": 6202304} {"current_steps": 29400, "total_steps": 181800, "loss": 0.0836, "lr": 4.9422216295450696e-05, "epoch": 3.2343234323432344, "percentage": 16.17, "elapsed_time": "1:09:19", "remaining_time": "5:59:22", "throughput": 1491.33, "total_tokens": 6203360} {"current_steps": 29405, "total_steps": 181800, "loss": 0.0366, "lr": 4.942170317124084e-05, "epoch": 3.234873487348735, "percentage": 16.17, "elapsed_time": "1:09:20", "remaining_time": "5:59:21", "throughput": 1491.32, "total_tokens": 6204352} {"current_steps": 29410, "total_steps": 181800, "loss": 0.09, "lr": 4.942118982194787e-05, "epoch": 3.2354235423542352, "percentage": 16.18, "elapsed_time": "1:09:20", "remaining_time": "5:59:20", "throughput": 1491.31, "total_tokens": 6205312} {"current_steps": 29415, "total_steps": 181800, "loss": 0.0231, "lr": 4.94206762475765e-05, "epoch": 3.235973597359736, "percentage": 16.18, "elapsed_time": "1:09:21", "remaining_time": "5:59:19", "throughput": 1491.32, "total_tokens": 6206400} {"current_steps": 29420, "total_steps": 181800, "loss": 0.047, "lr": 4.942016244813148e-05, "epoch": 3.2365236523652365, "percentage": 16.18, "elapsed_time": "1:09:22", "remaining_time": "5:59:18", "throughput": 1491.33, "total_tokens": 6207488} {"current_steps": 29425, "total_steps": 181800, "loss": 0.0907, "lr": 4.941964842361755e-05, "epoch": 3.237073707370737, "percentage": 16.19, "elapsed_time": "1:09:23", "remaining_time": "5:59:18", "throughput": 1491.33, "total_tokens": 6208512} {"current_steps": 29430, "total_steps": 181800, "loss": 0.08, "lr": 4.941913417403943e-05, "epoch": 3.237623762376238, "percentage": 16.19, "elapsed_time": "1:09:23", "remaining_time": "5:59:17", "throughput": 1491.35, "total_tokens": 6209632} {"current_steps": 29435, "total_steps": 181800, "loss": 0.0438, "lr": 4.941861969940187e-05, "epoch": 3.238173817381738, "percentage": 16.19, "elapsed_time": "1:09:24", "remaining_time": "5:59:16", "throughput": 1491.35, "total_tokens": 6210656} {"current_steps": 29440, "total_steps": 181800, "loss": 0.1635, "lr": 4.9418104999709604e-05, "epoch": 3.2387238723872387, "percentage": 16.19, "elapsed_time": "1:09:25", "remaining_time": "5:59:15", "throughput": 1491.34, "total_tokens": 6211648} {"current_steps": 29445, "total_steps": 181800, "loss": 0.056, "lr": 4.941759007496738e-05, "epoch": 3.2392739273927393, "percentage": 16.2, "elapsed_time": "1:09:25", "remaining_time": "5:59:14", "throughput": 1491.36, "total_tokens": 6212768} {"current_steps": 29450, "total_steps": 181800, "loss": 0.0135, "lr": 4.941707492517995e-05, "epoch": 3.23982398239824, "percentage": 16.2, "elapsed_time": "1:09:26", "remaining_time": "5:59:14", "throughput": 1491.37, "total_tokens": 6213824} {"current_steps": 29455, "total_steps": 181800, "loss": 0.0788, "lr": 4.941655955035206e-05, "epoch": 3.24037403740374, "percentage": 16.2, "elapsed_time": "1:09:27", "remaining_time": "5:59:13", "throughput": 1491.39, "total_tokens": 6214912} {"current_steps": 29460, "total_steps": 181800, "loss": 0.1063, "lr": 4.9416043950488454e-05, "epoch": 3.240924092409241, "percentage": 16.2, "elapsed_time": "1:09:27", "remaining_time": "5:59:12", "throughput": 1491.39, "total_tokens": 6215968} {"current_steps": 29465, "total_steps": 181800, "loss": 0.0266, "lr": 4.941552812559389e-05, "epoch": 3.2414741474147415, "percentage": 16.21, "elapsed_time": "1:09:28", "remaining_time": "5:59:11", "throughput": 1491.39, "total_tokens": 6216992} {"current_steps": 29470, "total_steps": 181800, "loss": 0.0058, "lr": 4.941501207567311e-05, "epoch": 3.242024202420242, "percentage": 16.21, "elapsed_time": "1:09:29", "remaining_time": "5:59:10", "throughput": 1491.41, "total_tokens": 6218080} {"current_steps": 29475, "total_steps": 181800, "loss": 0.1369, "lr": 4.9414495800730886e-05, "epoch": 3.2425742574257423, "percentage": 16.21, "elapsed_time": "1:09:29", "remaining_time": "5:59:10", "throughput": 1491.41, "total_tokens": 6219136} {"current_steps": 29480, "total_steps": 181800, "loss": 0.0654, "lr": 4.9413979300771975e-05, "epoch": 3.243124312431243, "percentage": 16.22, "elapsed_time": "1:09:30", "remaining_time": "5:59:09", "throughput": 1491.44, "total_tokens": 6220256} {"current_steps": 29485, "total_steps": 181800, "loss": 0.0345, "lr": 4.941346257580112e-05, "epoch": 3.2436743674367436, "percentage": 16.22, "elapsed_time": "1:09:31", "remaining_time": "5:59:08", "throughput": 1491.46, "total_tokens": 6221376} {"current_steps": 29490, "total_steps": 181800, "loss": 0.0381, "lr": 4.9412945625823096e-05, "epoch": 3.2442244224422443, "percentage": 16.22, "elapsed_time": "1:09:32", "remaining_time": "5:59:07", "throughput": 1491.46, "total_tokens": 6222432} {"current_steps": 29495, "total_steps": 181800, "loss": 0.1208, "lr": 4.9412428450842676e-05, "epoch": 3.244774477447745, "percentage": 16.22, "elapsed_time": "1:09:32", "remaining_time": "5:59:06", "throughput": 1491.48, "total_tokens": 6223520} {"current_steps": 29500, "total_steps": 181800, "loss": 0.0975, "lr": 4.941191105086461e-05, "epoch": 3.245324532453245, "percentage": 16.23, "elapsed_time": "1:09:33", "remaining_time": "5:59:06", "throughput": 1491.49, "total_tokens": 6224576} {"current_steps": 29505, "total_steps": 181800, "loss": 0.0393, "lr": 4.941139342589367e-05, "epoch": 3.245874587458746, "percentage": 16.23, "elapsed_time": "1:09:34", "remaining_time": "5:59:05", "throughput": 1491.5, "total_tokens": 6225664} {"current_steps": 29510, "total_steps": 181800, "loss": 0.0804, "lr": 4.941087557593464e-05, "epoch": 3.2464246424642464, "percentage": 16.23, "elapsed_time": "1:09:34", "remaining_time": "5:59:04", "throughput": 1491.52, "total_tokens": 6226752} {"current_steps": 29515, "total_steps": 181800, "loss": 0.0754, "lr": 4.941035750099228e-05, "epoch": 3.246974697469747, "percentage": 16.23, "elapsed_time": "1:09:35", "remaining_time": "5:59:03", "throughput": 1491.51, "total_tokens": 6227744} {"current_steps": 29520, "total_steps": 181800, "loss": 0.0248, "lr": 4.940983920107137e-05, "epoch": 3.2475247524752477, "percentage": 16.24, "elapsed_time": "1:09:36", "remaining_time": "5:59:02", "throughput": 1491.5, "total_tokens": 6228768} {"current_steps": 29525, "total_steps": 181800, "loss": 0.0323, "lr": 4.940932067617668e-05, "epoch": 3.248074807480748, "percentage": 16.24, "elapsed_time": "1:09:36", "remaining_time": "5:59:02", "throughput": 1491.51, "total_tokens": 6229824} {"current_steps": 29530, "total_steps": 181800, "loss": 0.1076, "lr": 4.9408801926313e-05, "epoch": 3.2486248624862486, "percentage": 16.24, "elapsed_time": "1:09:37", "remaining_time": "5:59:01", "throughput": 1491.5, "total_tokens": 6230816} {"current_steps": 29535, "total_steps": 181800, "loss": 0.1004, "lr": 4.9408282951485096e-05, "epoch": 3.2491749174917492, "percentage": 16.25, "elapsed_time": "1:09:38", "remaining_time": "5:59:00", "throughput": 1491.51, "total_tokens": 6231904} {"current_steps": 29540, "total_steps": 181800, "loss": 0.0805, "lr": 4.9407763751697766e-05, "epoch": 3.24972497249725, "percentage": 16.25, "elapsed_time": "1:09:38", "remaining_time": "5:58:59", "throughput": 1491.51, "total_tokens": 6232928} {"current_steps": 29545, "total_steps": 181800, "loss": 0.0947, "lr": 4.940724432695579e-05, "epoch": 3.25027502750275, "percentage": 16.25, "elapsed_time": "1:09:39", "remaining_time": "5:58:58", "throughput": 1491.51, "total_tokens": 6233952} {"current_steps": 29550, "total_steps": 181800, "loss": 0.0452, "lr": 4.940672467726396e-05, "epoch": 3.2508250825082508, "percentage": 16.25, "elapsed_time": "1:09:40", "remaining_time": "5:58:58", "throughput": 1491.51, "total_tokens": 6234944} {"current_steps": 29555, "total_steps": 181800, "loss": 0.0999, "lr": 4.940620480262705e-05, "epoch": 3.2513751375137514, "percentage": 16.26, "elapsed_time": "1:09:40", "remaining_time": "5:58:57", "throughput": 1491.5, "total_tokens": 6235936} {"current_steps": 29560, "total_steps": 181800, "loss": 0.0709, "lr": 4.9405684703049865e-05, "epoch": 3.251925192519252, "percentage": 16.26, "elapsed_time": "1:09:41", "remaining_time": "5:58:56", "throughput": 1491.53, "total_tokens": 6237088} {"current_steps": 29565, "total_steps": 181800, "loss": 0.0848, "lr": 4.9405164378537195e-05, "epoch": 3.2524752475247523, "percentage": 16.26, "elapsed_time": "1:09:42", "remaining_time": "5:58:55", "throughput": 1491.54, "total_tokens": 6238176} {"current_steps": 29570, "total_steps": 181800, "loss": 0.0309, "lr": 4.9404643829093835e-05, "epoch": 3.253025302530253, "percentage": 16.27, "elapsed_time": "1:09:43", "remaining_time": "5:58:54", "throughput": 1491.54, "total_tokens": 6239200} {"current_steps": 29575, "total_steps": 181800, "loss": 0.0832, "lr": 4.940412305472459e-05, "epoch": 3.2535753575357536, "percentage": 16.27, "elapsed_time": "1:09:43", "remaining_time": "5:58:54", "throughput": 1491.56, "total_tokens": 6240288} {"current_steps": 29580, "total_steps": 181800, "loss": 0.0432, "lr": 4.940360205543424e-05, "epoch": 3.254125412541254, "percentage": 16.27, "elapsed_time": "1:09:44", "remaining_time": "5:58:53", "throughput": 1491.57, "total_tokens": 6241344} {"current_steps": 29585, "total_steps": 181800, "loss": 0.194, "lr": 4.940308083122761e-05, "epoch": 3.254675467546755, "percentage": 16.27, "elapsed_time": "1:09:45", "remaining_time": "5:58:52", "throughput": 1491.56, "total_tokens": 6242368} {"current_steps": 29590, "total_steps": 181800, "loss": 0.0173, "lr": 4.940255938210949e-05, "epoch": 3.255225522552255, "percentage": 16.28, "elapsed_time": "1:09:45", "remaining_time": "5:58:51", "throughput": 1491.56, "total_tokens": 6243392} {"current_steps": 29595, "total_steps": 181800, "loss": 0.0359, "lr": 4.9402037708084694e-05, "epoch": 3.2557755775577557, "percentage": 16.28, "elapsed_time": "1:09:46", "remaining_time": "5:58:50", "throughput": 1491.58, "total_tokens": 6244480} {"current_steps": 29600, "total_steps": 181800, "loss": 0.1682, "lr": 4.940151580915803e-05, "epoch": 3.2563256325632564, "percentage": 16.28, "elapsed_time": "1:09:47", "remaining_time": "5:58:50", "throughput": 1491.6, "total_tokens": 6245600} {"current_steps": 29605, "total_steps": 181800, "loss": 0.0328, "lr": 4.940099368533429e-05, "epoch": 3.256875687568757, "percentage": 16.28, "elapsed_time": "1:09:47", "remaining_time": "5:58:49", "throughput": 1491.61, "total_tokens": 6246656} {"current_steps": 29610, "total_steps": 181800, "loss": 0.074, "lr": 4.940047133661831e-05, "epoch": 3.2574257425742577, "percentage": 16.29, "elapsed_time": "1:09:48", "remaining_time": "5:58:48", "throughput": 1491.62, "total_tokens": 6247744} {"current_steps": 29615, "total_steps": 181800, "loss": 0.0524, "lr": 4.9399948763014894e-05, "epoch": 3.257975797579758, "percentage": 16.29, "elapsed_time": "1:09:49", "remaining_time": "5:58:47", "throughput": 1491.64, "total_tokens": 6248832} {"current_steps": 29620, "total_steps": 181800, "loss": 0.1581, "lr": 4.939942596452885e-05, "epoch": 3.2585258525852585, "percentage": 16.29, "elapsed_time": "1:09:49", "remaining_time": "5:58:46", "throughput": 1491.64, "total_tokens": 6249888} {"current_steps": 29625, "total_steps": 181800, "loss": 0.0765, "lr": 4.939890294116501e-05, "epoch": 3.259075907590759, "percentage": 16.3, "elapsed_time": "1:09:50", "remaining_time": "5:58:46", "throughput": 1491.64, "total_tokens": 6250912} {"current_steps": 29630, "total_steps": 181800, "loss": 0.0337, "lr": 4.9398379692928185e-05, "epoch": 3.25962596259626, "percentage": 16.3, "elapsed_time": "1:09:51", "remaining_time": "5:58:45", "throughput": 1491.64, "total_tokens": 6251936} {"current_steps": 29635, "total_steps": 181800, "loss": 0.0144, "lr": 4.939785621982321e-05, "epoch": 3.26017601760176, "percentage": 16.3, "elapsed_time": "1:09:52", "remaining_time": "5:58:44", "throughput": 1491.66, "total_tokens": 6253056} {"current_steps": 29640, "total_steps": 181800, "loss": 0.0224, "lr": 4.93973325218549e-05, "epoch": 3.2607260726072607, "percentage": 16.3, "elapsed_time": "1:09:52", "remaining_time": "5:58:43", "throughput": 1491.67, "total_tokens": 6254144} {"current_steps": 29645, "total_steps": 181800, "loss": 0.0605, "lr": 4.939680859902808e-05, "epoch": 3.2612761276127613, "percentage": 16.31, "elapsed_time": "1:09:53", "remaining_time": "5:58:42", "throughput": 1491.68, "total_tokens": 6255200} {"current_steps": 29650, "total_steps": 181800, "loss": 0.0418, "lr": 4.939628445134759e-05, "epoch": 3.261826182618262, "percentage": 16.31, "elapsed_time": "1:09:54", "remaining_time": "5:58:42", "throughput": 1491.69, "total_tokens": 6256288} {"current_steps": 29655, "total_steps": 181800, "loss": 0.0397, "lr": 4.9395760078818235e-05, "epoch": 3.262376237623762, "percentage": 16.31, "elapsed_time": "1:09:54", "remaining_time": "5:58:41", "throughput": 1491.69, "total_tokens": 6257312} {"current_steps": 29660, "total_steps": 181800, "loss": 0.0498, "lr": 4.939523548144488e-05, "epoch": 3.262926292629263, "percentage": 16.31, "elapsed_time": "1:09:55", "remaining_time": "5:58:40", "throughput": 1491.7, "total_tokens": 6258368} {"current_steps": 29665, "total_steps": 181800, "loss": 0.0357, "lr": 4.9394710659232343e-05, "epoch": 3.2634763476347635, "percentage": 16.32, "elapsed_time": "1:09:56", "remaining_time": "5:58:39", "throughput": 1491.7, "total_tokens": 6259392} {"current_steps": 29670, "total_steps": 181800, "loss": 0.0431, "lr": 4.939418561218546e-05, "epoch": 3.264026402640264, "percentage": 16.32, "elapsed_time": "1:09:56", "remaining_time": "5:58:38", "throughput": 1491.69, "total_tokens": 6260384} {"current_steps": 29675, "total_steps": 181800, "loss": 0.0214, "lr": 4.939366034030908e-05, "epoch": 3.2645764576457648, "percentage": 16.32, "elapsed_time": "1:09:57", "remaining_time": "5:58:38", "throughput": 1491.68, "total_tokens": 6261376} {"current_steps": 29680, "total_steps": 181800, "loss": 0.0534, "lr": 4.9393134843608027e-05, "epoch": 3.265126512651265, "percentage": 16.33, "elapsed_time": "1:09:58", "remaining_time": "5:58:37", "throughput": 1491.68, "total_tokens": 6262400} {"current_steps": 29685, "total_steps": 181800, "loss": 0.0152, "lr": 4.9392609122087165e-05, "epoch": 3.2656765676567656, "percentage": 16.33, "elapsed_time": "1:09:58", "remaining_time": "5:58:36", "throughput": 1491.69, "total_tokens": 6263488} {"current_steps": 29690, "total_steps": 181800, "loss": 0.06, "lr": 4.9392083175751325e-05, "epoch": 3.2662266226622663, "percentage": 16.33, "elapsed_time": "1:09:59", "remaining_time": "5:58:35", "throughput": 1491.7, "total_tokens": 6264544} {"current_steps": 29695, "total_steps": 181800, "loss": 0.0543, "lr": 4.939155700460536e-05, "epoch": 3.266776677667767, "percentage": 16.33, "elapsed_time": "1:10:00", "remaining_time": "5:58:34", "throughput": 1491.7, "total_tokens": 6265568} {"current_steps": 29700, "total_steps": 181800, "loss": 0.0579, "lr": 4.939103060865412e-05, "epoch": 3.2673267326732676, "percentage": 16.34, "elapsed_time": "1:10:00", "remaining_time": "5:58:34", "throughput": 1491.69, "total_tokens": 6266560} {"current_steps": 29705, "total_steps": 181800, "loss": 0.0697, "lr": 4.939050398790245e-05, "epoch": 3.2678767876787678, "percentage": 16.34, "elapsed_time": "1:10:01", "remaining_time": "5:58:33", "throughput": 1491.69, "total_tokens": 6267584} {"current_steps": 29710, "total_steps": 181800, "loss": 0.0943, "lr": 4.9389977142355214e-05, "epoch": 3.2684268426842684, "percentage": 16.34, "elapsed_time": "1:10:02", "remaining_time": "5:58:32", "throughput": 1491.69, "total_tokens": 6268608} {"current_steps": 29715, "total_steps": 181800, "loss": 0.0834, "lr": 4.9389450072017264e-05, "epoch": 3.268976897689769, "percentage": 16.34, "elapsed_time": "1:10:03", "remaining_time": "5:58:31", "throughput": 1491.69, "total_tokens": 6269632} {"current_steps": 29720, "total_steps": 181800, "loss": 0.0528, "lr": 4.938892277689344e-05, "epoch": 3.2695269526952697, "percentage": 16.35, "elapsed_time": "1:10:03", "remaining_time": "5:58:30", "throughput": 1491.71, "total_tokens": 6270752} {"current_steps": 29725, "total_steps": 181800, "loss": 0.1015, "lr": 4.938839525698863e-05, "epoch": 3.27007700770077, "percentage": 16.35, "elapsed_time": "1:10:04", "remaining_time": "5:58:30", "throughput": 1491.72, "total_tokens": 6271808} {"current_steps": 29730, "total_steps": 181800, "loss": 0.0438, "lr": 4.938786751230769e-05, "epoch": 3.2706270627062706, "percentage": 16.35, "elapsed_time": "1:10:05", "remaining_time": "5:58:29", "throughput": 1491.72, "total_tokens": 6272864} {"current_steps": 29735, "total_steps": 181800, "loss": 0.034, "lr": 4.938733954285547e-05, "epoch": 3.271177117711771, "percentage": 16.36, "elapsed_time": "1:10:05", "remaining_time": "5:58:28", "throughput": 1491.73, "total_tokens": 6273920} {"current_steps": 29740, "total_steps": 181800, "loss": 0.0276, "lr": 4.938681134863684e-05, "epoch": 3.271727172717272, "percentage": 16.36, "elapsed_time": "1:10:06", "remaining_time": "5:58:27", "throughput": 1491.74, "total_tokens": 6274976} {"current_steps": 29745, "total_steps": 181800, "loss": 0.0359, "lr": 4.938628292965668e-05, "epoch": 3.272277227722772, "percentage": 16.36, "elapsed_time": "1:10:07", "remaining_time": "5:58:26", "throughput": 1491.76, "total_tokens": 6276096} {"current_steps": 29750, "total_steps": 181800, "loss": 0.0208, "lr": 4.938575428591985e-05, "epoch": 3.2728272827282727, "percentage": 16.36, "elapsed_time": "1:10:07", "remaining_time": "5:58:26", "throughput": 1491.75, "total_tokens": 6277088} {"current_steps": 29755, "total_steps": 181800, "loss": 0.0579, "lr": 4.938522541743122e-05, "epoch": 3.2733773377337734, "percentage": 16.37, "elapsed_time": "1:10:08", "remaining_time": "5:58:25", "throughput": 1491.76, "total_tokens": 6278176} {"current_steps": 29760, "total_steps": 181800, "loss": 0.0343, "lr": 4.9384696324195664e-05, "epoch": 3.273927392739274, "percentage": 16.37, "elapsed_time": "1:10:09", "remaining_time": "5:58:24", "throughput": 1491.79, "total_tokens": 6279296} {"current_steps": 29765, "total_steps": 181800, "loss": 0.0398, "lr": 4.938416700621807e-05, "epoch": 3.2744774477447747, "percentage": 16.37, "elapsed_time": "1:10:09", "remaining_time": "5:58:23", "throughput": 1491.79, "total_tokens": 6280352} {"current_steps": 29770, "total_steps": 181800, "loss": 0.0671, "lr": 4.9383637463503314e-05, "epoch": 3.275027502750275, "percentage": 16.38, "elapsed_time": "1:10:10", "remaining_time": "5:58:22", "throughput": 1491.81, "total_tokens": 6281440} {"current_steps": 29775, "total_steps": 181800, "loss": 0.0153, "lr": 4.938310769605626e-05, "epoch": 3.2755775577557755, "percentage": 16.38, "elapsed_time": "1:10:11", "remaining_time": "5:58:22", "throughput": 1491.81, "total_tokens": 6282496} {"current_steps": 29780, "total_steps": 181800, "loss": 0.0912, "lr": 4.938257770388182e-05, "epoch": 3.276127612761276, "percentage": 16.38, "elapsed_time": "1:10:12", "remaining_time": "5:58:21", "throughput": 1491.81, "total_tokens": 6283520} {"current_steps": 29785, "total_steps": 181800, "loss": 0.1056, "lr": 4.9382047486984847e-05, "epoch": 3.276677667766777, "percentage": 16.38, "elapsed_time": "1:10:12", "remaining_time": "5:58:20", "throughput": 1491.84, "total_tokens": 6284672} {"current_steps": 29790, "total_steps": 181800, "loss": 0.0536, "lr": 4.938151704537024e-05, "epoch": 3.2772277227722775, "percentage": 16.39, "elapsed_time": "1:10:13", "remaining_time": "5:58:19", "throughput": 1491.84, "total_tokens": 6285664} {"current_steps": 29795, "total_steps": 181800, "loss": 0.0532, "lr": 4.9380986379042896e-05, "epoch": 3.2777777777777777, "percentage": 16.39, "elapsed_time": "1:10:14", "remaining_time": "5:58:18", "throughput": 1491.83, "total_tokens": 6286688} {"current_steps": 29800, "total_steps": 181800, "loss": 0.2417, "lr": 4.93804554880077e-05, "epoch": 3.2783278327832783, "percentage": 16.39, "elapsed_time": "1:10:14", "remaining_time": "5:58:18", "throughput": 1491.83, "total_tokens": 6287712} {"current_steps": 29805, "total_steps": 181800, "loss": 0.0313, "lr": 4.937992437226955e-05, "epoch": 3.278877887788779, "percentage": 16.39, "elapsed_time": "1:10:15", "remaining_time": "5:58:17", "throughput": 1491.85, "total_tokens": 6288800} {"current_steps": 29810, "total_steps": 181800, "loss": 0.0742, "lr": 4.937939303183332e-05, "epoch": 3.279427942794279, "percentage": 16.4, "elapsed_time": "1:10:16", "remaining_time": "5:58:16", "throughput": 1491.86, "total_tokens": 6289888} {"current_steps": 29815, "total_steps": 181800, "loss": 0.0489, "lr": 4.9378861466703935e-05, "epoch": 3.27997799779978, "percentage": 16.4, "elapsed_time": "1:10:17", "remaining_time": "5:58:16", "throughput": 1491.78, "total_tokens": 6290880} {"current_steps": 29820, "total_steps": 181800, "loss": 0.0722, "lr": 4.937832967688628e-05, "epoch": 3.2805280528052805, "percentage": 16.4, "elapsed_time": "1:10:17", "remaining_time": "5:58:15", "throughput": 1491.77, "total_tokens": 6291872} {"current_steps": 29825, "total_steps": 181800, "loss": 0.0436, "lr": 4.937779766238526e-05, "epoch": 3.281078107810781, "percentage": 16.41, "elapsed_time": "1:10:18", "remaining_time": "5:58:15", "throughput": 1491.78, "total_tokens": 6292928} {"current_steps": 29830, "total_steps": 181800, "loss": 0.0255, "lr": 4.937726542320577e-05, "epoch": 3.281628162816282, "percentage": 16.41, "elapsed_time": "1:10:19", "remaining_time": "5:58:14", "throughput": 1491.79, "total_tokens": 6294016} {"current_steps": 29835, "total_steps": 181800, "loss": 0.0626, "lr": 4.937673295935272e-05, "epoch": 3.282178217821782, "percentage": 16.41, "elapsed_time": "1:10:19", "remaining_time": "5:58:13", "throughput": 1491.79, "total_tokens": 6295040} {"current_steps": 29840, "total_steps": 181800, "loss": 0.0179, "lr": 4.937620027083103e-05, "epoch": 3.2827282728272826, "percentage": 16.41, "elapsed_time": "1:10:20", "remaining_time": "5:58:12", "throughput": 1491.8, "total_tokens": 6296096} {"current_steps": 29845, "total_steps": 181800, "loss": 0.0803, "lr": 4.937566735764559e-05, "epoch": 3.2832783278327833, "percentage": 16.42, "elapsed_time": "1:10:21", "remaining_time": "5:58:11", "throughput": 1491.81, "total_tokens": 6297152} {"current_steps": 29850, "total_steps": 181800, "loss": 0.0264, "lr": 4.937513421980133e-05, "epoch": 3.283828382838284, "percentage": 16.42, "elapsed_time": "1:10:21", "remaining_time": "5:58:11", "throughput": 1491.8, "total_tokens": 6298144} {"current_steps": 29855, "total_steps": 181800, "loss": 0.0641, "lr": 4.937460085730315e-05, "epoch": 3.2843784378437846, "percentage": 16.42, "elapsed_time": "1:10:22", "remaining_time": "5:58:10", "throughput": 1491.8, "total_tokens": 6299200} {"current_steps": 29860, "total_steps": 181800, "loss": 0.0356, "lr": 4.937406727015596e-05, "epoch": 3.284928492849285, "percentage": 16.42, "elapsed_time": "1:10:23", "remaining_time": "5:58:09", "throughput": 1491.81, "total_tokens": 6300256} {"current_steps": 29865, "total_steps": 181800, "loss": 0.0508, "lr": 4.9373533458364704e-05, "epoch": 3.2854785478547854, "percentage": 16.43, "elapsed_time": "1:10:23", "remaining_time": "5:58:08", "throughput": 1491.8, "total_tokens": 6301248} {"current_steps": 29870, "total_steps": 181800, "loss": 0.0058, "lr": 4.937299942193427e-05, "epoch": 3.286028602860286, "percentage": 16.43, "elapsed_time": "1:10:24", "remaining_time": "5:58:07", "throughput": 1491.82, "total_tokens": 6302336} {"current_steps": 29875, "total_steps": 181800, "loss": 0.1086, "lr": 4.937246516086961e-05, "epoch": 3.2865786578657867, "percentage": 16.43, "elapsed_time": "1:10:25", "remaining_time": "5:58:07", "throughput": 1491.82, "total_tokens": 6303392} {"current_steps": 29880, "total_steps": 181800, "loss": 0.019, "lr": 4.937193067517562e-05, "epoch": 3.287128712871287, "percentage": 16.44, "elapsed_time": "1:10:25", "remaining_time": "5:58:06", "throughput": 1491.83, "total_tokens": 6304448} {"current_steps": 29885, "total_steps": 181800, "loss": 0.0313, "lr": 4.9371395964857256e-05, "epoch": 3.2876787678767876, "percentage": 16.44, "elapsed_time": "1:10:26", "remaining_time": "5:58:05", "throughput": 1491.85, "total_tokens": 6305568} {"current_steps": 29890, "total_steps": 181800, "loss": 0.1421, "lr": 4.9370861029919425e-05, "epoch": 3.2882288228822882, "percentage": 16.44, "elapsed_time": "1:10:27", "remaining_time": "5:58:04", "throughput": 1491.85, "total_tokens": 6306592} {"current_steps": 29895, "total_steps": 181800, "loss": 0.1439, "lr": 4.937032587036705e-05, "epoch": 3.288778877887789, "percentage": 16.44, "elapsed_time": "1:10:28", "remaining_time": "5:58:03", "throughput": 1491.86, "total_tokens": 6307648} {"current_steps": 29900, "total_steps": 181800, "loss": 0.0639, "lr": 4.9369790486205086e-05, "epoch": 3.289328932893289, "percentage": 16.45, "elapsed_time": "1:10:28", "remaining_time": "5:58:03", "throughput": 1491.87, "total_tokens": 6308736} {"current_steps": 29905, "total_steps": 181800, "loss": 0.0959, "lr": 4.936925487743845e-05, "epoch": 3.2898789878987897, "percentage": 16.45, "elapsed_time": "1:10:29", "remaining_time": "5:58:02", "throughput": 1491.88, "total_tokens": 6309792} {"current_steps": 29910, "total_steps": 181800, "loss": 0.0635, "lr": 4.93687190440721e-05, "epoch": 3.2904290429042904, "percentage": 16.45, "elapsed_time": "1:10:30", "remaining_time": "5:58:01", "throughput": 1491.87, "total_tokens": 6310816} {"current_steps": 29915, "total_steps": 181800, "loss": 0.04, "lr": 4.936818298611094e-05, "epoch": 3.290979097909791, "percentage": 16.45, "elapsed_time": "1:10:30", "remaining_time": "5:58:00", "throughput": 1491.88, "total_tokens": 6311872} {"current_steps": 29920, "total_steps": 181800, "loss": 0.0323, "lr": 4.936764670355994e-05, "epoch": 3.2915291529152917, "percentage": 16.46, "elapsed_time": "1:10:31", "remaining_time": "5:58:00", "throughput": 1491.88, "total_tokens": 6312928} {"current_steps": 29925, "total_steps": 181800, "loss": 0.0593, "lr": 4.936711019642404e-05, "epoch": 3.292079207920792, "percentage": 16.46, "elapsed_time": "1:10:32", "remaining_time": "5:57:59", "throughput": 1491.88, "total_tokens": 6313952} {"current_steps": 29930, "total_steps": 181800, "loss": 0.0414, "lr": 4.936657346470816e-05, "epoch": 3.2926292629262925, "percentage": 16.46, "elapsed_time": "1:10:32", "remaining_time": "5:57:58", "throughput": 1491.87, "total_tokens": 6314944} {"current_steps": 29935, "total_steps": 181800, "loss": 0.0483, "lr": 4.936603650841728e-05, "epoch": 3.293179317931793, "percentage": 16.47, "elapsed_time": "1:10:33", "remaining_time": "5:57:57", "throughput": 1491.87, "total_tokens": 6315968} {"current_steps": 29940, "total_steps": 181800, "loss": 0.0659, "lr": 4.936549932755633e-05, "epoch": 3.293729372937294, "percentage": 16.47, "elapsed_time": "1:10:34", "remaining_time": "5:57:56", "throughput": 1491.85, "total_tokens": 6316928} {"current_steps": 29945, "total_steps": 181800, "loss": 0.0281, "lr": 4.936496192213027e-05, "epoch": 3.2942794279427945, "percentage": 16.47, "elapsed_time": "1:10:34", "remaining_time": "5:57:56", "throughput": 1491.86, "total_tokens": 6317984} {"current_steps": 29950, "total_steps": 181800, "loss": 0.0405, "lr": 4.936442429214404e-05, "epoch": 3.2948294829482947, "percentage": 16.47, "elapsed_time": "1:10:35", "remaining_time": "5:57:55", "throughput": 1491.87, "total_tokens": 6319040} {"current_steps": 29955, "total_steps": 181800, "loss": 0.0942, "lr": 4.93638864376026e-05, "epoch": 3.2953795379537953, "percentage": 16.48, "elapsed_time": "1:10:36", "remaining_time": "5:57:54", "throughput": 1491.87, "total_tokens": 6320064} {"current_steps": 29960, "total_steps": 181800, "loss": 0.0206, "lr": 4.936334835851092e-05, "epoch": 3.295929592959296, "percentage": 16.48, "elapsed_time": "1:10:37", "remaining_time": "5:57:53", "throughput": 1491.87, "total_tokens": 6321088} {"current_steps": 29965, "total_steps": 181800, "loss": 0.0443, "lr": 4.936281005487394e-05, "epoch": 3.2964796479647966, "percentage": 16.48, "elapsed_time": "1:10:37", "remaining_time": "5:57:52", "throughput": 1491.87, "total_tokens": 6322112} {"current_steps": 29970, "total_steps": 181800, "loss": 0.037, "lr": 4.936227152669663e-05, "epoch": 3.297029702970297, "percentage": 16.49, "elapsed_time": "1:10:38", "remaining_time": "5:57:52", "throughput": 1491.86, "total_tokens": 6323136} {"current_steps": 29975, "total_steps": 181800, "loss": 0.0542, "lr": 4.936173277398395e-05, "epoch": 3.2975797579757975, "percentage": 16.49, "elapsed_time": "1:10:39", "remaining_time": "5:57:51", "throughput": 1491.86, "total_tokens": 6324160} {"current_steps": 29980, "total_steps": 181800, "loss": 0.1548, "lr": 4.936119379674088e-05, "epoch": 3.298129812981298, "percentage": 16.49, "elapsed_time": "1:10:39", "remaining_time": "5:57:50", "throughput": 1491.88, "total_tokens": 6325248} {"current_steps": 29985, "total_steps": 181800, "loss": 0.0345, "lr": 4.9360654594972365e-05, "epoch": 3.298679867986799, "percentage": 16.49, "elapsed_time": "1:10:40", "remaining_time": "5:57:49", "throughput": 1491.87, "total_tokens": 6326240} {"current_steps": 29990, "total_steps": 181800, "loss": 0.044, "lr": 4.9360115168683396e-05, "epoch": 3.299229922992299, "percentage": 16.5, "elapsed_time": "1:10:41", "remaining_time": "5:57:48", "throughput": 1491.89, "total_tokens": 6327360} {"current_steps": 29995, "total_steps": 181800, "loss": 0.0332, "lr": 4.935957551787893e-05, "epoch": 3.2997799779977997, "percentage": 16.5, "elapsed_time": "1:10:41", "remaining_time": "5:57:48", "throughput": 1491.9, "total_tokens": 6328448} {"current_steps": 30000, "total_steps": 181800, "loss": 0.0653, "lr": 4.9359035642563946e-05, "epoch": 3.3003300330033003, "percentage": 16.5, "elapsed_time": "1:10:42", "remaining_time": "5:57:47", "throughput": 1491.91, "total_tokens": 6329504} {"current_steps": 30005, "total_steps": 181800, "loss": 0.0811, "lr": 4.935849554274342e-05, "epoch": 3.300880088008801, "percentage": 16.5, "elapsed_time": "1:10:43", "remaining_time": "5:57:46", "throughput": 1491.91, "total_tokens": 6330560} {"current_steps": 30010, "total_steps": 181800, "loss": 0.0936, "lr": 4.935795521842233e-05, "epoch": 3.3014301430143016, "percentage": 16.51, "elapsed_time": "1:10:43", "remaining_time": "5:57:45", "throughput": 1491.93, "total_tokens": 6331648} {"current_steps": 30015, "total_steps": 181800, "loss": 0.0388, "lr": 4.935741466960565e-05, "epoch": 3.301980198019802, "percentage": 16.51, "elapsed_time": "1:10:44", "remaining_time": "5:57:44", "throughput": 1491.94, "total_tokens": 6332736} {"current_steps": 30020, "total_steps": 181800, "loss": 0.0094, "lr": 4.935687389629837e-05, "epoch": 3.3025302530253025, "percentage": 16.51, "elapsed_time": "1:10:45", "remaining_time": "5:57:44", "throughput": 1491.95, "total_tokens": 6333824} {"current_steps": 30025, "total_steps": 181800, "loss": 0.0482, "lr": 4.935633289850547e-05, "epoch": 3.303080308030803, "percentage": 16.52, "elapsed_time": "1:10:46", "remaining_time": "5:57:43", "throughput": 1491.95, "total_tokens": 6334816} {"current_steps": 30030, "total_steps": 181800, "loss": 0.0129, "lr": 4.935579167623193e-05, "epoch": 3.3036303630363038, "percentage": 16.52, "elapsed_time": "1:10:46", "remaining_time": "5:57:42", "throughput": 1491.97, "total_tokens": 6335936} {"current_steps": 30035, "total_steps": 181800, "loss": 0.0617, "lr": 4.9355250229482755e-05, "epoch": 3.3041804180418044, "percentage": 16.52, "elapsed_time": "1:10:47", "remaining_time": "5:57:41", "throughput": 1491.98, "total_tokens": 6337024} {"current_steps": 30040, "total_steps": 181800, "loss": 0.0941, "lr": 4.935470855826292e-05, "epoch": 3.3047304730473046, "percentage": 16.52, "elapsed_time": "1:10:48", "remaining_time": "5:57:40", "throughput": 1492.0, "total_tokens": 6338112} {"current_steps": 30045, "total_steps": 181800, "loss": 0.0594, "lr": 4.935416666257743e-05, "epoch": 3.3052805280528053, "percentage": 16.53, "elapsed_time": "1:10:48", "remaining_time": "5:57:40", "throughput": 1492.0, "total_tokens": 6339168} {"current_steps": 30050, "total_steps": 181800, "loss": 0.0281, "lr": 4.935362454243127e-05, "epoch": 3.305830583058306, "percentage": 16.53, "elapsed_time": "1:10:49", "remaining_time": "5:57:39", "throughput": 1492.0, "total_tokens": 6340192} {"current_steps": 30055, "total_steps": 181800, "loss": 0.1429, "lr": 4.9353082197829435e-05, "epoch": 3.3063806380638066, "percentage": 16.53, "elapsed_time": "1:10:50", "remaining_time": "5:57:38", "throughput": 1492.0, "total_tokens": 6341216} {"current_steps": 30060, "total_steps": 181800, "loss": 0.132, "lr": 4.935253962877693e-05, "epoch": 3.3069306930693068, "percentage": 16.53, "elapsed_time": "1:10:50", "remaining_time": "5:57:37", "throughput": 1492.0, "total_tokens": 6342272} {"current_steps": 30065, "total_steps": 181800, "loss": 0.0996, "lr": 4.9351996835278746e-05, "epoch": 3.3074807480748074, "percentage": 16.54, "elapsed_time": "1:10:51", "remaining_time": "5:57:37", "throughput": 1492.01, "total_tokens": 6343328} {"current_steps": 30070, "total_steps": 181800, "loss": 0.0278, "lr": 4.93514538173399e-05, "epoch": 3.308030803080308, "percentage": 16.54, "elapsed_time": "1:10:52", "remaining_time": "5:57:36", "throughput": 1492.01, "total_tokens": 6344352} {"current_steps": 30075, "total_steps": 181800, "loss": 0.025, "lr": 4.9350910574965385e-05, "epoch": 3.3085808580858087, "percentage": 16.54, "elapsed_time": "1:10:52", "remaining_time": "5:57:35", "throughput": 1492.0, "total_tokens": 6345344} {"current_steps": 30080, "total_steps": 181800, "loss": 0.0554, "lr": 4.935036710816021e-05, "epoch": 3.309130913091309, "percentage": 16.55, "elapsed_time": "1:10:53", "remaining_time": "5:57:34", "throughput": 1491.99, "total_tokens": 6346304} {"current_steps": 30085, "total_steps": 181800, "loss": 0.1256, "lr": 4.93498234169294e-05, "epoch": 3.3096809680968096, "percentage": 16.55, "elapsed_time": "1:10:54", "remaining_time": "5:57:33", "throughput": 1492.0, "total_tokens": 6347360} {"current_steps": 30090, "total_steps": 181800, "loss": 0.011, "lr": 4.9349279501277935e-05, "epoch": 3.31023102310231, "percentage": 16.55, "elapsed_time": "1:10:54", "remaining_time": "5:57:32", "throughput": 1492.01, "total_tokens": 6348448} {"current_steps": 30095, "total_steps": 181800, "loss": 0.1107, "lr": 4.934873536121085e-05, "epoch": 3.310781078107811, "percentage": 16.55, "elapsed_time": "1:10:55", "remaining_time": "5:57:32", "throughput": 1492.02, "total_tokens": 6349536} {"current_steps": 30100, "total_steps": 181800, "loss": 0.0476, "lr": 4.9348190996733155e-05, "epoch": 3.3113311331133115, "percentage": 16.56, "elapsed_time": "1:10:56", "remaining_time": "5:57:31", "throughput": 1492.02, "total_tokens": 6350560} {"current_steps": 30105, "total_steps": 181800, "loss": 0.0764, "lr": 4.934764640784987e-05, "epoch": 3.3118811881188117, "percentage": 16.56, "elapsed_time": "1:10:57", "remaining_time": "5:57:30", "throughput": 1492.02, "total_tokens": 6351584} {"current_steps": 30110, "total_steps": 181800, "loss": 0.0291, "lr": 4.9347101594566005e-05, "epoch": 3.3124312431243124, "percentage": 16.56, "elapsed_time": "1:10:57", "remaining_time": "5:57:29", "throughput": 1492.03, "total_tokens": 6352640} {"current_steps": 30115, "total_steps": 181800, "loss": 0.0378, "lr": 4.9346556556886594e-05, "epoch": 3.312981298129813, "percentage": 16.56, "elapsed_time": "1:10:58", "remaining_time": "5:57:29", "throughput": 1492.06, "total_tokens": 6353792} {"current_steps": 30120, "total_steps": 181800, "loss": 0.051, "lr": 4.934601129481665e-05, "epoch": 3.3135313531353137, "percentage": 16.57, "elapsed_time": "1:10:59", "remaining_time": "5:57:28", "throughput": 1492.06, "total_tokens": 6354816} {"current_steps": 30125, "total_steps": 181800, "loss": 0.0671, "lr": 4.9345465808361205e-05, "epoch": 3.3140814081408143, "percentage": 16.57, "elapsed_time": "1:10:59", "remaining_time": "5:57:27", "throughput": 1492.06, "total_tokens": 6355872} {"current_steps": 30130, "total_steps": 181800, "loss": 0.068, "lr": 4.9344920097525284e-05, "epoch": 3.3146314631463145, "percentage": 16.57, "elapsed_time": "1:11:00", "remaining_time": "5:57:26", "throughput": 1492.06, "total_tokens": 6356896} {"current_steps": 30135, "total_steps": 181800, "loss": 0.0302, "lr": 4.934437416231391e-05, "epoch": 3.315181518151815, "percentage": 16.58, "elapsed_time": "1:11:01", "remaining_time": "5:57:25", "throughput": 1492.07, "total_tokens": 6357952} {"current_steps": 30140, "total_steps": 181800, "loss": 0.0381, "lr": 4.934382800273213e-05, "epoch": 3.315731573157316, "percentage": 16.58, "elapsed_time": "1:11:01", "remaining_time": "5:57:24", "throughput": 1492.09, "total_tokens": 6359072} {"current_steps": 30145, "total_steps": 181800, "loss": 0.1105, "lr": 4.9343281618784965e-05, "epoch": 3.3162816281628165, "percentage": 16.58, "elapsed_time": "1:11:02", "remaining_time": "5:57:24", "throughput": 1492.1, "total_tokens": 6360128} {"current_steps": 30150, "total_steps": 181800, "loss": 0.039, "lr": 4.9342735010477445e-05, "epoch": 3.3168316831683167, "percentage": 16.58, "elapsed_time": "1:11:03", "remaining_time": "5:57:23", "throughput": 1492.1, "total_tokens": 6361152} {"current_steps": 30155, "total_steps": 181800, "loss": 0.138, "lr": 4.934218817781463e-05, "epoch": 3.3173817381738173, "percentage": 16.59, "elapsed_time": "1:11:03", "remaining_time": "5:57:22", "throughput": 1492.11, "total_tokens": 6362208} {"current_steps": 30160, "total_steps": 181800, "loss": 0.0359, "lr": 4.934164112080154e-05, "epoch": 3.317931793179318, "percentage": 16.59, "elapsed_time": "1:11:04", "remaining_time": "5:57:21", "throughput": 1492.11, "total_tokens": 6363232} {"current_steps": 30165, "total_steps": 181800, "loss": 0.0073, "lr": 4.934109383944323e-05, "epoch": 3.3184818481848186, "percentage": 16.59, "elapsed_time": "1:11:05", "remaining_time": "5:57:20", "throughput": 1492.11, "total_tokens": 6364288} {"current_steps": 30170, "total_steps": 181800, "loss": 0.0497, "lr": 4.9340546333744736e-05, "epoch": 3.319031903190319, "percentage": 16.6, "elapsed_time": "1:11:05", "remaining_time": "5:57:20", "throughput": 1492.1, "total_tokens": 6365280} {"current_steps": 30175, "total_steps": 181800, "loss": 0.0189, "lr": 4.9339998603711105e-05, "epoch": 3.3195819581958195, "percentage": 16.6, "elapsed_time": "1:11:06", "remaining_time": "5:57:19", "throughput": 1492.11, "total_tokens": 6366336} {"current_steps": 30180, "total_steps": 181800, "loss": 0.0533, "lr": 4.9339450649347384e-05, "epoch": 3.32013201320132, "percentage": 16.6, "elapsed_time": "1:11:07", "remaining_time": "5:57:18", "throughput": 1492.11, "total_tokens": 6367360} {"current_steps": 30185, "total_steps": 181800, "loss": 0.0946, "lr": 4.933890247065863e-05, "epoch": 3.3206820682068208, "percentage": 16.6, "elapsed_time": "1:11:08", "remaining_time": "5:57:17", "throughput": 1492.09, "total_tokens": 6368320} {"current_steps": 30190, "total_steps": 181800, "loss": 0.1112, "lr": 4.933835406764989e-05, "epoch": 3.3212321232123214, "percentage": 16.61, "elapsed_time": "1:11:08", "remaining_time": "5:57:16", "throughput": 1492.12, "total_tokens": 6369440} {"current_steps": 30195, "total_steps": 181800, "loss": 0.021, "lr": 4.933780544032621e-05, "epoch": 3.3217821782178216, "percentage": 16.61, "elapsed_time": "1:11:09", "remaining_time": "5:57:16", "throughput": 1492.14, "total_tokens": 6370560} {"current_steps": 30200, "total_steps": 181800, "loss": 0.0167, "lr": 4.933725658869267e-05, "epoch": 3.3223322332233223, "percentage": 16.61, "elapsed_time": "1:11:10", "remaining_time": "5:57:15", "throughput": 1492.15, "total_tokens": 6371648} {"current_steps": 30205, "total_steps": 181800, "loss": 0.0497, "lr": 4.933670751275431e-05, "epoch": 3.322882288228823, "percentage": 16.61, "elapsed_time": "1:11:10", "remaining_time": "5:57:14", "throughput": 1492.16, "total_tokens": 6372736} {"current_steps": 30210, "total_steps": 181800, "loss": 0.0086, "lr": 4.933615821251619e-05, "epoch": 3.3234323432343236, "percentage": 16.62, "elapsed_time": "1:11:11", "remaining_time": "5:57:13", "throughput": 1492.17, "total_tokens": 6373792} {"current_steps": 30215, "total_steps": 181800, "loss": 0.1301, "lr": 4.933560868798338e-05, "epoch": 3.323982398239824, "percentage": 16.62, "elapsed_time": "1:11:12", "remaining_time": "5:57:13", "throughput": 1492.16, "total_tokens": 6374784} {"current_steps": 30220, "total_steps": 181800, "loss": 0.0534, "lr": 4.933505893916094e-05, "epoch": 3.3245324532453244, "percentage": 16.62, "elapsed_time": "1:11:12", "remaining_time": "5:57:12", "throughput": 1492.17, "total_tokens": 6375872} {"current_steps": 30225, "total_steps": 181800, "loss": 0.0508, "lr": 4.9334508966053946e-05, "epoch": 3.325082508250825, "percentage": 16.63, "elapsed_time": "1:11:13", "remaining_time": "5:57:11", "throughput": 1492.18, "total_tokens": 6376928} {"current_steps": 30230, "total_steps": 181800, "loss": 0.0054, "lr": 4.9333958768667455e-05, "epoch": 3.3256325632563257, "percentage": 16.63, "elapsed_time": "1:11:14", "remaining_time": "5:57:10", "throughput": 1492.18, "total_tokens": 6377952} {"current_steps": 30235, "total_steps": 181800, "loss": 0.0824, "lr": 4.9333408347006535e-05, "epoch": 3.3261826182618264, "percentage": 16.63, "elapsed_time": "1:11:14", "remaining_time": "5:57:09", "throughput": 1492.19, "total_tokens": 6379008} {"current_steps": 30240, "total_steps": 181800, "loss": 0.1372, "lr": 4.9332857701076274e-05, "epoch": 3.3267326732673266, "percentage": 16.63, "elapsed_time": "1:11:15", "remaining_time": "5:57:09", "throughput": 1492.18, "total_tokens": 6380032} {"current_steps": 30245, "total_steps": 181800, "loss": 0.1109, "lr": 4.933230683088174e-05, "epoch": 3.3272827282728272, "percentage": 16.64, "elapsed_time": "1:11:16", "remaining_time": "5:57:08", "throughput": 1492.2, "total_tokens": 6381120} {"current_steps": 30250, "total_steps": 181800, "loss": 0.059, "lr": 4.9331755736428006e-05, "epoch": 3.327832783278328, "percentage": 16.64, "elapsed_time": "1:11:17", "remaining_time": "5:57:07", "throughput": 1492.21, "total_tokens": 6382208} {"current_steps": 30255, "total_steps": 181800, "loss": 0.0588, "lr": 4.933120441772017e-05, "epoch": 3.3283828382838285, "percentage": 16.64, "elapsed_time": "1:11:17", "remaining_time": "5:57:06", "throughput": 1492.21, "total_tokens": 6383232} {"current_steps": 30260, "total_steps": 181800, "loss": 0.0518, "lr": 4.9330652874763275e-05, "epoch": 3.3289328932893287, "percentage": 16.64, "elapsed_time": "1:11:18", "remaining_time": "5:57:05", "throughput": 1492.21, "total_tokens": 6384256} {"current_steps": 30265, "total_steps": 181800, "loss": 0.1609, "lr": 4.9330101107562444e-05, "epoch": 3.3294829482948294, "percentage": 16.65, "elapsed_time": "1:11:19", "remaining_time": "5:57:05", "throughput": 1492.23, "total_tokens": 6385344} {"current_steps": 30270, "total_steps": 181800, "loss": 0.0113, "lr": 4.9329549116122745e-05, "epoch": 3.33003300330033, "percentage": 16.65, "elapsed_time": "1:11:19", "remaining_time": "5:57:04", "throughput": 1492.22, "total_tokens": 6386336} {"current_steps": 30275, "total_steps": 181800, "loss": 0.1329, "lr": 4.9328996900449254e-05, "epoch": 3.3305830583058307, "percentage": 16.65, "elapsed_time": "1:11:20", "remaining_time": "5:57:03", "throughput": 1492.23, "total_tokens": 6387424} {"current_steps": 30280, "total_steps": 181800, "loss": 0.1117, "lr": 4.932844446054709e-05, "epoch": 3.3311331133113313, "percentage": 16.66, "elapsed_time": "1:11:21", "remaining_time": "5:57:02", "throughput": 1492.22, "total_tokens": 6388416} {"current_steps": 30285, "total_steps": 181800, "loss": 0.0201, "lr": 4.9327891796421314e-05, "epoch": 3.3316831683168315, "percentage": 16.66, "elapsed_time": "1:11:21", "remaining_time": "5:57:01", "throughput": 1492.24, "total_tokens": 6389504} {"current_steps": 30290, "total_steps": 181800, "loss": 0.0856, "lr": 4.932733890807703e-05, "epoch": 3.332233223322332, "percentage": 16.66, "elapsed_time": "1:11:22", "remaining_time": "5:57:01", "throughput": 1492.25, "total_tokens": 6390560} {"current_steps": 30295, "total_steps": 181800, "loss": 0.0183, "lr": 4.932678579551935e-05, "epoch": 3.332783278327833, "percentage": 16.66, "elapsed_time": "1:11:23", "remaining_time": "5:57:00", "throughput": 1492.25, "total_tokens": 6391584} {"current_steps": 30300, "total_steps": 181800, "loss": 0.125, "lr": 4.9326232458753345e-05, "epoch": 3.3333333333333335, "percentage": 16.67, "elapsed_time": "1:11:23", "remaining_time": "5:56:59", "throughput": 1492.25, "total_tokens": 6392640} {"current_steps": 30305, "total_steps": 181800, "loss": 0.1215, "lr": 4.932567889778413e-05, "epoch": 3.333883388338834, "percentage": 16.67, "elapsed_time": "1:11:24", "remaining_time": "5:56:58", "throughput": 1492.26, "total_tokens": 6393696} {"current_steps": 30310, "total_steps": 181800, "loss": 0.0544, "lr": 4.932512511261681e-05, "epoch": 3.3344334433443343, "percentage": 16.67, "elapsed_time": "1:11:25", "remaining_time": "5:56:57", "throughput": 1492.25, "total_tokens": 6394688} {"current_steps": 30315, "total_steps": 181800, "loss": 0.1732, "lr": 4.932457110325649e-05, "epoch": 3.334983498349835, "percentage": 16.67, "elapsed_time": "1:11:25", "remaining_time": "5:56:57", "throughput": 1492.27, "total_tokens": 6395808} {"current_steps": 30320, "total_steps": 181800, "loss": 0.1007, "lr": 4.9324016869708264e-05, "epoch": 3.3355335533553356, "percentage": 16.68, "elapsed_time": "1:11:26", "remaining_time": "5:56:56", "throughput": 1492.27, "total_tokens": 6396832} {"current_steps": 30325, "total_steps": 181800, "loss": 0.0652, "lr": 4.932346241197725e-05, "epoch": 3.336083608360836, "percentage": 16.68, "elapsed_time": "1:11:27", "remaining_time": "5:56:55", "throughput": 1492.28, "total_tokens": 6397888} {"current_steps": 30330, "total_steps": 181800, "loss": 0.0224, "lr": 4.932290773006855e-05, "epoch": 3.3366336633663365, "percentage": 16.68, "elapsed_time": "1:11:28", "remaining_time": "5:56:54", "throughput": 1492.28, "total_tokens": 6398944} {"current_steps": 30335, "total_steps": 181800, "loss": 0.1465, "lr": 4.9322352823987284e-05, "epoch": 3.337183718371837, "percentage": 16.69, "elapsed_time": "1:11:28", "remaining_time": "5:56:53", "throughput": 1492.3, "total_tokens": 6400032} {"current_steps": 30340, "total_steps": 181800, "loss": 0.0596, "lr": 4.9321797693738555e-05, "epoch": 3.337733773377338, "percentage": 16.69, "elapsed_time": "1:11:29", "remaining_time": "5:56:53", "throughput": 1492.3, "total_tokens": 6401088} {"current_steps": 30345, "total_steps": 181800, "loss": 0.0327, "lr": 4.9321242339327504e-05, "epoch": 3.3382838283828384, "percentage": 16.69, "elapsed_time": "1:11:30", "remaining_time": "5:56:52", "throughput": 1492.31, "total_tokens": 6402144} {"current_steps": 30350, "total_steps": 181800, "loss": 0.0457, "lr": 4.932068676075922e-05, "epoch": 3.3388338833883386, "percentage": 16.69, "elapsed_time": "1:11:30", "remaining_time": "5:56:51", "throughput": 1492.31, "total_tokens": 6403200} {"current_steps": 30355, "total_steps": 181800, "loss": 0.1052, "lr": 4.9320130958038835e-05, "epoch": 3.3393839383938393, "percentage": 16.7, "elapsed_time": "1:11:31", "remaining_time": "5:56:50", "throughput": 1492.33, "total_tokens": 6404288} {"current_steps": 30360, "total_steps": 181800, "loss": 0.0477, "lr": 4.931957493117148e-05, "epoch": 3.33993399339934, "percentage": 16.7, "elapsed_time": "1:11:32", "remaining_time": "5:56:49", "throughput": 1492.33, "total_tokens": 6405312} {"current_steps": 30365, "total_steps": 181800, "loss": 0.0978, "lr": 4.931901868016227e-05, "epoch": 3.3404840484048406, "percentage": 16.7, "elapsed_time": "1:11:32", "remaining_time": "5:56:49", "throughput": 1492.35, "total_tokens": 6406432} {"current_steps": 30370, "total_steps": 181800, "loss": 0.032, "lr": 4.9318462205016324e-05, "epoch": 3.3410341034103412, "percentage": 16.71, "elapsed_time": "1:11:33", "remaining_time": "5:56:48", "throughput": 1492.36, "total_tokens": 6407520} {"current_steps": 30375, "total_steps": 181800, "loss": 0.1003, "lr": 4.931790550573879e-05, "epoch": 3.3415841584158414, "percentage": 16.71, "elapsed_time": "1:11:34", "remaining_time": "5:56:47", "throughput": 1492.36, "total_tokens": 6408544} {"current_steps": 30380, "total_steps": 181800, "loss": 0.1884, "lr": 4.931734858233479e-05, "epoch": 3.342134213421342, "percentage": 16.71, "elapsed_time": "1:11:34", "remaining_time": "5:56:46", "throughput": 1492.36, "total_tokens": 6409568} {"current_steps": 30385, "total_steps": 181800, "loss": 0.0637, "lr": 4.931679143480946e-05, "epoch": 3.3426842684268427, "percentage": 16.71, "elapsed_time": "1:11:35", "remaining_time": "5:56:45", "throughput": 1492.36, "total_tokens": 6410624} {"current_steps": 30390, "total_steps": 181800, "loss": 0.0602, "lr": 4.931623406316793e-05, "epoch": 3.3432343234323434, "percentage": 16.72, "elapsed_time": "1:11:36", "remaining_time": "5:56:45", "throughput": 1492.37, "total_tokens": 6411680} {"current_steps": 30395, "total_steps": 181800, "loss": 0.0421, "lr": 4.931567646741534e-05, "epoch": 3.3437843784378436, "percentage": 16.72, "elapsed_time": "1:11:36", "remaining_time": "5:56:44", "throughput": 1492.36, "total_tokens": 6412672} {"current_steps": 30400, "total_steps": 181800, "loss": 0.0211, "lr": 4.9315118647556824e-05, "epoch": 3.3443344334433442, "percentage": 16.72, "elapsed_time": "1:11:37", "remaining_time": "5:56:43", "throughput": 1492.38, "total_tokens": 6413792} {"current_steps": 30405, "total_steps": 181800, "loss": 0.2001, "lr": 4.931456060359753e-05, "epoch": 3.344884488448845, "percentage": 16.72, "elapsed_time": "1:11:38", "remaining_time": "5:56:42", "throughput": 1492.4, "total_tokens": 6414880} {"current_steps": 30410, "total_steps": 181800, "loss": 0.0394, "lr": 4.931400233554259e-05, "epoch": 3.3454345434543455, "percentage": 16.73, "elapsed_time": "1:11:39", "remaining_time": "5:56:42", "throughput": 1492.4, "total_tokens": 6415936} {"current_steps": 30415, "total_steps": 181800, "loss": 0.1082, "lr": 4.931344384339717e-05, "epoch": 3.3459845984598457, "percentage": 16.73, "elapsed_time": "1:11:39", "remaining_time": "5:56:41", "throughput": 1492.42, "total_tokens": 6417024} {"current_steps": 30420, "total_steps": 181800, "loss": 0.0635, "lr": 4.93128851271664e-05, "epoch": 3.3465346534653464, "percentage": 16.73, "elapsed_time": "1:11:40", "remaining_time": "5:56:40", "throughput": 1492.42, "total_tokens": 6418080} {"current_steps": 30425, "total_steps": 181800, "loss": 0.041, "lr": 4.931232618685543e-05, "epoch": 3.347084708470847, "percentage": 16.74, "elapsed_time": "1:11:41", "remaining_time": "5:56:39", "throughput": 1492.44, "total_tokens": 6419168} {"current_steps": 30430, "total_steps": 181800, "loss": 0.0275, "lr": 4.931176702246941e-05, "epoch": 3.3476347634763477, "percentage": 16.74, "elapsed_time": "1:11:41", "remaining_time": "5:56:38", "throughput": 1492.44, "total_tokens": 6420192} {"current_steps": 30435, "total_steps": 181800, "loss": 0.0547, "lr": 4.9311207634013515e-05, "epoch": 3.3481848184818483, "percentage": 16.74, "elapsed_time": "1:11:42", "remaining_time": "5:56:38", "throughput": 1492.44, "total_tokens": 6421216} {"current_steps": 30440, "total_steps": 181800, "loss": 0.0566, "lr": 4.931064802149288e-05, "epoch": 3.3487348734873486, "percentage": 16.74, "elapsed_time": "1:11:43", "remaining_time": "5:56:37", "throughput": 1492.44, "total_tokens": 6422272} {"current_steps": 30445, "total_steps": 181800, "loss": 0.0374, "lr": 4.931008818491266e-05, "epoch": 3.349284928492849, "percentage": 16.75, "elapsed_time": "1:11:43", "remaining_time": "5:56:36", "throughput": 1492.44, "total_tokens": 6423296} {"current_steps": 30450, "total_steps": 181800, "loss": 0.0589, "lr": 4.9309528124278025e-05, "epoch": 3.34983498349835, "percentage": 16.75, "elapsed_time": "1:11:44", "remaining_time": "5:56:35", "throughput": 1492.45, "total_tokens": 6424352} {"current_steps": 30455, "total_steps": 181800, "loss": 0.0344, "lr": 4.9308967839594136e-05, "epoch": 3.3503850385038505, "percentage": 16.75, "elapsed_time": "1:11:45", "remaining_time": "5:56:34", "throughput": 1492.44, "total_tokens": 6425344} {"current_steps": 30460, "total_steps": 181800, "loss": 0.0475, "lr": 4.9308407330866156e-05, "epoch": 3.350935093509351, "percentage": 16.75, "elapsed_time": "1:11:45", "remaining_time": "5:56:34", "throughput": 1492.46, "total_tokens": 6426464} {"current_steps": 30465, "total_steps": 181800, "loss": 0.0697, "lr": 4.930784659809925e-05, "epoch": 3.3514851485148514, "percentage": 16.76, "elapsed_time": "1:11:46", "remaining_time": "5:56:33", "throughput": 1492.46, "total_tokens": 6427488} {"current_steps": 30470, "total_steps": 181800, "loss": 0.0444, "lr": 4.9307285641298585e-05, "epoch": 3.352035203520352, "percentage": 16.76, "elapsed_time": "1:11:47", "remaining_time": "5:56:32", "throughput": 1492.46, "total_tokens": 6428512} {"current_steps": 30475, "total_steps": 181800, "loss": 0.0423, "lr": 4.9306724460469335e-05, "epoch": 3.3525852585258527, "percentage": 16.76, "elapsed_time": "1:11:48", "remaining_time": "5:56:31", "throughput": 1492.46, "total_tokens": 6429536} {"current_steps": 30480, "total_steps": 181800, "loss": 0.0185, "lr": 4.930616305561667e-05, "epoch": 3.3531353135313533, "percentage": 16.77, "elapsed_time": "1:11:48", "remaining_time": "5:56:30", "throughput": 1492.48, "total_tokens": 6430656} {"current_steps": 30485, "total_steps": 181800, "loss": 0.0364, "lr": 4.930560142674576e-05, "epoch": 3.3536853685368535, "percentage": 16.77, "elapsed_time": "1:11:49", "remaining_time": "5:56:30", "throughput": 1492.48, "total_tokens": 6431712} {"current_steps": 30490, "total_steps": 181800, "loss": 0.1195, "lr": 4.9305039573861776e-05, "epoch": 3.354235423542354, "percentage": 16.77, "elapsed_time": "1:11:50", "remaining_time": "5:56:29", "throughput": 1492.49, "total_tokens": 6432768} {"current_steps": 30495, "total_steps": 181800, "loss": 0.038, "lr": 4.9304477496969916e-05, "epoch": 3.354785478547855, "percentage": 16.77, "elapsed_time": "1:11:50", "remaining_time": "5:56:28", "throughput": 1492.5, "total_tokens": 6433856} {"current_steps": 30500, "total_steps": 181800, "loss": 0.0688, "lr": 4.930391519607534e-05, "epoch": 3.3553355335533555, "percentage": 16.78, "elapsed_time": "1:11:51", "remaining_time": "5:56:27", "throughput": 1492.52, "total_tokens": 6434976} {"current_steps": 30505, "total_steps": 181800, "loss": 0.0517, "lr": 4.930335267118326e-05, "epoch": 3.3558855885588557, "percentage": 16.78, "elapsed_time": "1:11:52", "remaining_time": "5:56:27", "throughput": 1492.52, "total_tokens": 6436000} {"current_steps": 30510, "total_steps": 181800, "loss": 0.0326, "lr": 4.930278992229882e-05, "epoch": 3.3564356435643563, "percentage": 16.78, "elapsed_time": "1:11:52", "remaining_time": "5:56:26", "throughput": 1492.53, "total_tokens": 6437088} {"current_steps": 30515, "total_steps": 181800, "loss": 0.0381, "lr": 4.930222694942723e-05, "epoch": 3.356985698569857, "percentage": 16.78, "elapsed_time": "1:11:53", "remaining_time": "5:56:25", "throughput": 1492.52, "total_tokens": 6438080} {"current_steps": 30520, "total_steps": 181800, "loss": 0.023, "lr": 4.9301663752573684e-05, "epoch": 3.3575357535753576, "percentage": 16.79, "elapsed_time": "1:11:54", "remaining_time": "5:56:24", "throughput": 1492.54, "total_tokens": 6439168} {"current_steps": 30525, "total_steps": 181800, "loss": 0.0263, "lr": 4.930110033174336e-05, "epoch": 3.3580858085808583, "percentage": 16.79, "elapsed_time": "1:11:54", "remaining_time": "5:56:23", "throughput": 1492.53, "total_tokens": 6440160} {"current_steps": 30530, "total_steps": 181800, "loss": 0.0917, "lr": 4.9300536686941455e-05, "epoch": 3.3586358635863585, "percentage": 16.79, "elapsed_time": "1:11:55", "remaining_time": "5:56:23", "throughput": 1492.55, "total_tokens": 6441280} {"current_steps": 30535, "total_steps": 181800, "loss": 0.0894, "lr": 4.929997281817317e-05, "epoch": 3.359185918591859, "percentage": 16.8, "elapsed_time": "1:11:56", "remaining_time": "5:56:22", "throughput": 1492.56, "total_tokens": 6442368} {"current_steps": 30540, "total_steps": 181800, "loss": 0.1072, "lr": 4.9299408725443685e-05, "epoch": 3.3597359735973598, "percentage": 16.8, "elapsed_time": "1:11:56", "remaining_time": "5:56:21", "throughput": 1492.58, "total_tokens": 6443456} {"current_steps": 30545, "total_steps": 181800, "loss": 0.0637, "lr": 4.9298844408758215e-05, "epoch": 3.3602860286028604, "percentage": 16.8, "elapsed_time": "1:11:57", "remaining_time": "5:56:20", "throughput": 1492.58, "total_tokens": 6444480} {"current_steps": 30550, "total_steps": 181800, "loss": 0.0611, "lr": 4.929827986812196e-05, "epoch": 3.360836083608361, "percentage": 16.8, "elapsed_time": "1:11:58", "remaining_time": "5:56:19", "throughput": 1492.59, "total_tokens": 6445568} {"current_steps": 30555, "total_steps": 181800, "loss": 0.1402, "lr": 4.929771510354011e-05, "epoch": 3.3613861386138613, "percentage": 16.81, "elapsed_time": "1:11:59", "remaining_time": "5:56:19", "throughput": 1492.6, "total_tokens": 6446656} {"current_steps": 30560, "total_steps": 181800, "loss": 0.0357, "lr": 4.9297150115017875e-05, "epoch": 3.361936193619362, "percentage": 16.81, "elapsed_time": "1:11:59", "remaining_time": "5:56:18", "throughput": 1492.61, "total_tokens": 6447712} {"current_steps": 30565, "total_steps": 181800, "loss": 0.1019, "lr": 4.929658490256048e-05, "epoch": 3.3624862486248626, "percentage": 16.81, "elapsed_time": "1:12:00", "remaining_time": "5:56:17", "throughput": 1492.6, "total_tokens": 6448736} {"current_steps": 30570, "total_steps": 181800, "loss": 0.1263, "lr": 4.9296019466173116e-05, "epoch": 3.363036303630363, "percentage": 16.82, "elapsed_time": "1:12:01", "remaining_time": "5:56:16", "throughput": 1492.6, "total_tokens": 6449760} {"current_steps": 30575, "total_steps": 181800, "loss": 0.0738, "lr": 4.9295453805860994e-05, "epoch": 3.3635863586358634, "percentage": 16.82, "elapsed_time": "1:12:01", "remaining_time": "5:56:15", "throughput": 1492.61, "total_tokens": 6450816} {"current_steps": 30580, "total_steps": 181800, "loss": 0.0388, "lr": 4.929488792162934e-05, "epoch": 3.364136413641364, "percentage": 16.82, "elapsed_time": "1:12:02", "remaining_time": "5:56:15", "throughput": 1492.62, "total_tokens": 6451904} {"current_steps": 30585, "total_steps": 181800, "loss": 0.0651, "lr": 4.929432181348336e-05, "epoch": 3.3646864686468647, "percentage": 16.82, "elapsed_time": "1:12:03", "remaining_time": "5:56:14", "throughput": 1492.63, "total_tokens": 6452960} {"current_steps": 30590, "total_steps": 181800, "loss": 0.0242, "lr": 4.929375548142827e-05, "epoch": 3.3652365236523654, "percentage": 16.83, "elapsed_time": "1:12:03", "remaining_time": "5:56:13", "throughput": 1492.65, "total_tokens": 6454080} {"current_steps": 30595, "total_steps": 181800, "loss": 0.0258, "lr": 4.9293188925469294e-05, "epoch": 3.3657865786578656, "percentage": 16.83, "elapsed_time": "1:12:04", "remaining_time": "5:56:12", "throughput": 1492.66, "total_tokens": 6455168} {"current_steps": 30600, "total_steps": 181800, "loss": 0.0634, "lr": 4.929262214561165e-05, "epoch": 3.366336633663366, "percentage": 16.83, "elapsed_time": "1:12:05", "remaining_time": "5:56:11", "throughput": 1492.66, "total_tokens": 6456160} {"current_steps": 30605, "total_steps": 181800, "loss": 0.0486, "lr": 4.929205514186057e-05, "epoch": 3.366886688668867, "percentage": 16.83, "elapsed_time": "1:12:05", "remaining_time": "5:56:11", "throughput": 1492.66, "total_tokens": 6457216} {"current_steps": 30610, "total_steps": 181800, "loss": 0.0797, "lr": 4.9291487914221266e-05, "epoch": 3.3674367436743675, "percentage": 16.84, "elapsed_time": "1:12:06", "remaining_time": "5:56:10", "throughput": 1492.66, "total_tokens": 6458240} {"current_steps": 30615, "total_steps": 181800, "loss": 0.208, "lr": 4.9290920462698985e-05, "epoch": 3.367986798679868, "percentage": 16.84, "elapsed_time": "1:12:07", "remaining_time": "5:56:09", "throughput": 1492.67, "total_tokens": 6459296} {"current_steps": 30620, "total_steps": 181800, "loss": 0.1496, "lr": 4.929035278729894e-05, "epoch": 3.3685368536853684, "percentage": 16.84, "elapsed_time": "1:12:08", "remaining_time": "5:56:08", "throughput": 1492.68, "total_tokens": 6460384} {"current_steps": 30625, "total_steps": 181800, "loss": 0.1159, "lr": 4.928978488802637e-05, "epoch": 3.369086908690869, "percentage": 16.85, "elapsed_time": "1:12:08", "remaining_time": "5:56:07", "throughput": 1492.68, "total_tokens": 6461408} {"current_steps": 30630, "total_steps": 181800, "loss": 0.0895, "lr": 4.9289216764886506e-05, "epoch": 3.3696369636963697, "percentage": 16.85, "elapsed_time": "1:12:09", "remaining_time": "5:56:07", "throughput": 1492.68, "total_tokens": 6462432} {"current_steps": 30635, "total_steps": 181800, "loss": 0.0511, "lr": 4.9288648417884584e-05, "epoch": 3.3701870187018703, "percentage": 16.85, "elapsed_time": "1:12:10", "remaining_time": "5:56:06", "throughput": 1492.68, "total_tokens": 6463424} {"current_steps": 30640, "total_steps": 181800, "loss": 0.094, "lr": 4.9288079847025855e-05, "epoch": 3.370737073707371, "percentage": 16.85, "elapsed_time": "1:12:10", "remaining_time": "5:56:05", "throughput": 1492.69, "total_tokens": 6464512} {"current_steps": 30645, "total_steps": 181800, "loss": 0.0832, "lr": 4.9287511052315535e-05, "epoch": 3.371287128712871, "percentage": 16.86, "elapsed_time": "1:12:11", "remaining_time": "5:56:04", "throughput": 1492.68, "total_tokens": 6465504} {"current_steps": 30650, "total_steps": 181800, "loss": 0.1089, "lr": 4.928694203375889e-05, "epoch": 3.371837183718372, "percentage": 16.86, "elapsed_time": "1:12:12", "remaining_time": "5:56:03", "throughput": 1492.7, "total_tokens": 6466592} {"current_steps": 30655, "total_steps": 181800, "loss": 0.0191, "lr": 4.928637279136115e-05, "epoch": 3.3723872387238725, "percentage": 16.86, "elapsed_time": "1:12:12", "remaining_time": "5:56:03", "throughput": 1492.7, "total_tokens": 6467648} {"current_steps": 30660, "total_steps": 181800, "loss": 0.111, "lr": 4.928580332512757e-05, "epoch": 3.372937293729373, "percentage": 16.86, "elapsed_time": "1:12:13", "remaining_time": "5:56:02", "throughput": 1492.71, "total_tokens": 6468704} {"current_steps": 30665, "total_steps": 181800, "loss": 0.0572, "lr": 4.928523363506339e-05, "epoch": 3.3734873487348733, "percentage": 16.87, "elapsed_time": "1:12:14", "remaining_time": "5:56:01", "throughput": 1492.71, "total_tokens": 6469760} {"current_steps": 30670, "total_steps": 181800, "loss": 0.0514, "lr": 4.9284663721173865e-05, "epoch": 3.374037403740374, "percentage": 16.87, "elapsed_time": "1:12:14", "remaining_time": "5:56:00", "throughput": 1492.72, "total_tokens": 6470848} {"current_steps": 30675, "total_steps": 181800, "loss": 0.0894, "lr": 4.928409358346425e-05, "epoch": 3.3745874587458746, "percentage": 16.87, "elapsed_time": "1:12:15", "remaining_time": "5:56:00", "throughput": 1492.74, "total_tokens": 6471936} {"current_steps": 30680, "total_steps": 181800, "loss": 0.0868, "lr": 4.9283523221939796e-05, "epoch": 3.3751375137513753, "percentage": 16.88, "elapsed_time": "1:12:16", "remaining_time": "5:55:59", "throughput": 1492.74, "total_tokens": 6472992} {"current_steps": 30685, "total_steps": 181800, "loss": 0.0484, "lr": 4.928295263660576e-05, "epoch": 3.3756875687568755, "percentage": 16.88, "elapsed_time": "1:12:16", "remaining_time": "5:55:58", "throughput": 1492.75, "total_tokens": 6474048} {"current_steps": 30690, "total_steps": 181800, "loss": 0.0853, "lr": 4.9282381827467397e-05, "epoch": 3.376237623762376, "percentage": 16.88, "elapsed_time": "1:12:17", "remaining_time": "5:55:57", "throughput": 1492.78, "total_tokens": 6475200} {"current_steps": 30695, "total_steps": 181800, "loss": 0.0668, "lr": 4.928181079452998e-05, "epoch": 3.3767876787678768, "percentage": 16.88, "elapsed_time": "1:12:18", "remaining_time": "5:55:56", "throughput": 1492.8, "total_tokens": 6476320} {"current_steps": 30700, "total_steps": 181800, "loss": 0.0773, "lr": 4.928123953779876e-05, "epoch": 3.3773377337733774, "percentage": 16.89, "elapsed_time": "1:12:19", "remaining_time": "5:55:56", "throughput": 1492.8, "total_tokens": 6477344} {"current_steps": 30705, "total_steps": 181800, "loss": 0.0592, "lr": 4.9280668057279014e-05, "epoch": 3.377887788778878, "percentage": 16.89, "elapsed_time": "1:12:19", "remaining_time": "5:55:55", "throughput": 1492.8, "total_tokens": 6478368} {"current_steps": 30710, "total_steps": 181800, "loss": 0.0699, "lr": 4.928009635297599e-05, "epoch": 3.3784378437843783, "percentage": 16.89, "elapsed_time": "1:12:20", "remaining_time": "5:55:54", "throughput": 1492.8, "total_tokens": 6479392} {"current_steps": 30715, "total_steps": 181800, "loss": 0.082, "lr": 4.9279524424894976e-05, "epoch": 3.378987898789879, "percentage": 16.89, "elapsed_time": "1:12:21", "remaining_time": "5:55:53", "throughput": 1492.8, "total_tokens": 6480448} {"current_steps": 30720, "total_steps": 181800, "loss": 0.02, "lr": 4.9278952273041236e-05, "epoch": 3.3795379537953796, "percentage": 16.9, "elapsed_time": "1:12:21", "remaining_time": "5:55:52", "throughput": 1492.81, "total_tokens": 6481504} {"current_steps": 30725, "total_steps": 181800, "loss": 0.0459, "lr": 4.927837989742004e-05, "epoch": 3.3800880088008802, "percentage": 16.9, "elapsed_time": "1:12:22", "remaining_time": "5:55:52", "throughput": 1492.83, "total_tokens": 6482624} {"current_steps": 30730, "total_steps": 181800, "loss": 0.0901, "lr": 4.927780729803667e-05, "epoch": 3.380638063806381, "percentage": 16.9, "elapsed_time": "1:12:23", "remaining_time": "5:55:51", "throughput": 1492.85, "total_tokens": 6483712} {"current_steps": 30735, "total_steps": 181800, "loss": 0.1331, "lr": 4.92772344748964e-05, "epoch": 3.381188118811881, "percentage": 16.91, "elapsed_time": "1:12:23", "remaining_time": "5:55:50", "throughput": 1492.87, "total_tokens": 6484832} {"current_steps": 30740, "total_steps": 181800, "loss": 0.1442, "lr": 4.9276661428004503e-05, "epoch": 3.3817381738173817, "percentage": 16.91, "elapsed_time": "1:12:24", "remaining_time": "5:55:49", "throughput": 1492.88, "total_tokens": 6485920} {"current_steps": 30745, "total_steps": 181800, "loss": 0.036, "lr": 4.927608815736627e-05, "epoch": 3.3822882288228824, "percentage": 16.91, "elapsed_time": "1:12:25", "remaining_time": "5:55:48", "throughput": 1492.9, "total_tokens": 6487008} {"current_steps": 30750, "total_steps": 181800, "loss": 0.0087, "lr": 4.927551466298698e-05, "epoch": 3.382838283828383, "percentage": 16.91, "elapsed_time": "1:12:25", "remaining_time": "5:55:48", "throughput": 1492.89, "total_tokens": 6488032} {"current_steps": 30755, "total_steps": 181800, "loss": 0.0697, "lr": 4.927494094487192e-05, "epoch": 3.3833883388338832, "percentage": 16.92, "elapsed_time": "1:12:26", "remaining_time": "5:55:47", "throughput": 1492.91, "total_tokens": 6489120} {"current_steps": 30760, "total_steps": 181800, "loss": 0.0419, "lr": 4.927436700302638e-05, "epoch": 3.383938393839384, "percentage": 16.92, "elapsed_time": "1:12:27", "remaining_time": "5:55:46", "throughput": 1492.93, "total_tokens": 6490240} {"current_steps": 30765, "total_steps": 181800, "loss": 0.0386, "lr": 4.927379283745565e-05, "epoch": 3.3844884488448845, "percentage": 16.92, "elapsed_time": "1:12:28", "remaining_time": "5:55:45", "throughput": 1492.94, "total_tokens": 6491328} {"current_steps": 30770, "total_steps": 181800, "loss": 0.0121, "lr": 4.9273218448165014e-05, "epoch": 3.385038503850385, "percentage": 16.93, "elapsed_time": "1:12:28", "remaining_time": "5:55:44", "throughput": 1492.94, "total_tokens": 6492320} {"current_steps": 30775, "total_steps": 181800, "loss": 0.0655, "lr": 4.927264383515977e-05, "epoch": 3.3855885588558854, "percentage": 16.93, "elapsed_time": "1:12:29", "remaining_time": "5:55:44", "throughput": 1492.95, "total_tokens": 6493408} {"current_steps": 30780, "total_steps": 181800, "loss": 0.0795, "lr": 4.927206899844522e-05, "epoch": 3.386138613861386, "percentage": 16.93, "elapsed_time": "1:12:30", "remaining_time": "5:55:43", "throughput": 1492.96, "total_tokens": 6494464} {"current_steps": 30785, "total_steps": 181800, "loss": 0.0226, "lr": 4.927149393802665e-05, "epoch": 3.3866886688668867, "percentage": 16.93, "elapsed_time": "1:12:30", "remaining_time": "5:55:42", "throughput": 1492.96, "total_tokens": 6495520} {"current_steps": 30790, "total_steps": 181800, "loss": 0.0156, "lr": 4.927091865390937e-05, "epoch": 3.3872387238723873, "percentage": 16.94, "elapsed_time": "1:12:31", "remaining_time": "5:55:41", "throughput": 1492.96, "total_tokens": 6496544} {"current_steps": 30795, "total_steps": 181800, "loss": 0.0773, "lr": 4.927034314609869e-05, "epoch": 3.387788778877888, "percentage": 16.94, "elapsed_time": "1:12:32", "remaining_time": "5:55:40", "throughput": 1492.96, "total_tokens": 6497568} {"current_steps": 30800, "total_steps": 181800, "loss": 0.0643, "lr": 4.926976741459989e-05, "epoch": 3.388338833883388, "percentage": 16.94, "elapsed_time": "1:12:32", "remaining_time": "5:55:40", "throughput": 1492.96, "total_tokens": 6498592} {"current_steps": 30805, "total_steps": 181800, "loss": 0.1055, "lr": 4.926919145941829e-05, "epoch": 3.388888888888889, "percentage": 16.94, "elapsed_time": "1:12:33", "remaining_time": "5:55:39", "throughput": 1492.95, "total_tokens": 6499584} {"current_steps": 30810, "total_steps": 181800, "loss": 0.0746, "lr": 4.9268615280559205e-05, "epoch": 3.3894389438943895, "percentage": 16.95, "elapsed_time": "1:12:34", "remaining_time": "5:55:38", "throughput": 1492.96, "total_tokens": 6500640} {"current_steps": 30815, "total_steps": 181800, "loss": 0.1679, "lr": 4.9268038878027937e-05, "epoch": 3.38998899889989, "percentage": 16.95, "elapsed_time": "1:12:34", "remaining_time": "5:55:37", "throughput": 1492.97, "total_tokens": 6501728} {"current_steps": 30820, "total_steps": 181800, "loss": 0.0954, "lr": 4.9267462251829785e-05, "epoch": 3.390539053905391, "percentage": 16.95, "elapsed_time": "1:12:35", "remaining_time": "5:55:36", "throughput": 1492.97, "total_tokens": 6502720} {"current_steps": 30825, "total_steps": 181800, "loss": 0.0279, "lr": 4.9266885401970097e-05, "epoch": 3.391089108910891, "percentage": 16.96, "elapsed_time": "1:12:36", "remaining_time": "5:55:36", "throughput": 1492.98, "total_tokens": 6503808} {"current_steps": 30830, "total_steps": 181800, "loss": 0.075, "lr": 4.926630832845416e-05, "epoch": 3.3916391639163916, "percentage": 16.96, "elapsed_time": "1:12:36", "remaining_time": "5:55:35", "throughput": 1492.98, "total_tokens": 6504832} {"current_steps": 30835, "total_steps": 181800, "loss": 0.1026, "lr": 4.926573103128731e-05, "epoch": 3.3921892189218923, "percentage": 16.96, "elapsed_time": "1:12:37", "remaining_time": "5:55:34", "throughput": 1492.98, "total_tokens": 6505856} {"current_steps": 30840, "total_steps": 181800, "loss": 0.0624, "lr": 4.926515351047486e-05, "epoch": 3.3927392739273925, "percentage": 16.96, "elapsed_time": "1:12:38", "remaining_time": "5:55:33", "throughput": 1492.99, "total_tokens": 6506912} {"current_steps": 30845, "total_steps": 181800, "loss": 0.1057, "lr": 4.926457576602213e-05, "epoch": 3.393289328932893, "percentage": 16.97, "elapsed_time": "1:12:39", "remaining_time": "5:55:32", "throughput": 1492.99, "total_tokens": 6507936} {"current_steps": 30850, "total_steps": 181800, "loss": 0.0758, "lr": 4.9263997797934445e-05, "epoch": 3.393839383938394, "percentage": 16.97, "elapsed_time": "1:12:39", "remaining_time": "5:55:32", "throughput": 1493.0, "total_tokens": 6509024} {"current_steps": 30855, "total_steps": 181800, "loss": 0.0531, "lr": 4.926341960621714e-05, "epoch": 3.3943894389438944, "percentage": 16.97, "elapsed_time": "1:12:40", "remaining_time": "5:55:31", "throughput": 1493.01, "total_tokens": 6510080} {"current_steps": 30860, "total_steps": 181800, "loss": 0.0305, "lr": 4.9262841190875545e-05, "epoch": 3.394939493949395, "percentage": 16.97, "elapsed_time": "1:12:41", "remaining_time": "5:55:30", "throughput": 1493.01, "total_tokens": 6511104} {"current_steps": 30865, "total_steps": 181800, "loss": 0.0176, "lr": 4.926226255191497e-05, "epoch": 3.3954895489548953, "percentage": 16.98, "elapsed_time": "1:12:41", "remaining_time": "5:55:29", "throughput": 1492.99, "total_tokens": 6512064} {"current_steps": 30870, "total_steps": 181800, "loss": 0.0535, "lr": 4.926168368934078e-05, "epoch": 3.396039603960396, "percentage": 16.98, "elapsed_time": "1:12:42", "remaining_time": "5:55:28", "throughput": 1493.01, "total_tokens": 6513152} {"current_steps": 30875, "total_steps": 181800, "loss": 0.0866, "lr": 4.926110460315828e-05, "epoch": 3.3965896589658966, "percentage": 16.98, "elapsed_time": "1:12:43", "remaining_time": "5:55:28", "throughput": 1493.02, "total_tokens": 6514240} {"current_steps": 30880, "total_steps": 181800, "loss": 0.1657, "lr": 4.9260525293372825e-05, "epoch": 3.3971397139713972, "percentage": 16.99, "elapsed_time": "1:12:43", "remaining_time": "5:55:27", "throughput": 1493.03, "total_tokens": 6515296} {"current_steps": 30885, "total_steps": 181800, "loss": 0.0406, "lr": 4.925994575998976e-05, "epoch": 3.397689768976898, "percentage": 16.99, "elapsed_time": "1:12:44", "remaining_time": "5:55:26", "throughput": 1493.04, "total_tokens": 6516352} {"current_steps": 30890, "total_steps": 181800, "loss": 0.0383, "lr": 4.92593660030144e-05, "epoch": 3.398239823982398, "percentage": 16.99, "elapsed_time": "1:12:45", "remaining_time": "5:55:25", "throughput": 1493.04, "total_tokens": 6517408} {"current_steps": 30895, "total_steps": 181800, "loss": 0.1194, "lr": 4.925878602245211e-05, "epoch": 3.3987898789878987, "percentage": 16.99, "elapsed_time": "1:12:45", "remaining_time": "5:55:24", "throughput": 1493.03, "total_tokens": 6518400} {"current_steps": 30900, "total_steps": 181800, "loss": 0.0922, "lr": 4.925820581830823e-05, "epoch": 3.3993399339933994, "percentage": 17.0, "elapsed_time": "1:12:46", "remaining_time": "5:55:24", "throughput": 1493.05, "total_tokens": 6519488} {"current_steps": 30905, "total_steps": 181800, "loss": 0.0656, "lr": 4.925762539058811e-05, "epoch": 3.3998899889989, "percentage": 17.0, "elapsed_time": "1:12:47", "remaining_time": "5:55:23", "throughput": 1493.05, "total_tokens": 6520544} {"current_steps": 30910, "total_steps": 181800, "loss": 0.0434, "lr": 4.92570447392971e-05, "epoch": 3.4004400440044003, "percentage": 17.0, "elapsed_time": "1:12:47", "remaining_time": "5:55:22", "throughput": 1493.06, "total_tokens": 6521600} {"current_steps": 30915, "total_steps": 181800, "loss": 0.0688, "lr": 4.9256463864440535e-05, "epoch": 3.400990099009901, "percentage": 17.0, "elapsed_time": "1:12:48", "remaining_time": "5:55:21", "throughput": 1493.05, "total_tokens": 6522592} {"current_steps": 30920, "total_steps": 181800, "loss": 0.0799, "lr": 4.9255882766023795e-05, "epoch": 3.4015401540154016, "percentage": 17.01, "elapsed_time": "1:12:49", "remaining_time": "5:55:20", "throughput": 1493.04, "total_tokens": 6523584} {"current_steps": 30925, "total_steps": 181800, "loss": 0.0572, "lr": 4.925530144405222e-05, "epoch": 3.402090209020902, "percentage": 17.01, "elapsed_time": "1:12:50", "remaining_time": "5:55:20", "throughput": 1493.04, "total_tokens": 6524576} {"current_steps": 30930, "total_steps": 181800, "loss": 0.0513, "lr": 4.925471989853117e-05, "epoch": 3.4026402640264024, "percentage": 17.01, "elapsed_time": "1:12:50", "remaining_time": "5:55:19", "throughput": 1493.06, "total_tokens": 6525696} {"current_steps": 30935, "total_steps": 181800, "loss": 0.0498, "lr": 4.9254138129466e-05, "epoch": 3.403190319031903, "percentage": 17.02, "elapsed_time": "1:12:51", "remaining_time": "5:55:18", "throughput": 1493.07, "total_tokens": 6526784} {"current_steps": 30940, "total_steps": 181800, "loss": 0.0323, "lr": 4.925355613686208e-05, "epoch": 3.4037403740374037, "percentage": 17.02, "elapsed_time": "1:12:52", "remaining_time": "5:55:17", "throughput": 1493.09, "total_tokens": 6527904} {"current_steps": 30945, "total_steps": 181800, "loss": 0.0103, "lr": 4.925297392072478e-05, "epoch": 3.4042904290429044, "percentage": 17.02, "elapsed_time": "1:12:52", "remaining_time": "5:55:16", "throughput": 1493.09, "total_tokens": 6528928} {"current_steps": 30950, "total_steps": 181800, "loss": 0.1354, "lr": 4.9252391481059445e-05, "epoch": 3.404840484048405, "percentage": 17.02, "elapsed_time": "1:12:53", "remaining_time": "5:55:16", "throughput": 1493.1, "total_tokens": 6529984} {"current_steps": 30955, "total_steps": 181800, "loss": 0.0777, "lr": 4.9251808817871456e-05, "epoch": 3.405390539053905, "percentage": 17.03, "elapsed_time": "1:12:54", "remaining_time": "5:55:15", "throughput": 1493.11, "total_tokens": 6531072} {"current_steps": 30960, "total_steps": 181800, "loss": 0.0478, "lr": 4.9251225931166184e-05, "epoch": 3.405940594059406, "percentage": 17.03, "elapsed_time": "1:12:54", "remaining_time": "5:55:14", "throughput": 1493.12, "total_tokens": 6532128} {"current_steps": 30965, "total_steps": 181800, "loss": 0.0956, "lr": 4.9250642820949e-05, "epoch": 3.4064906490649065, "percentage": 17.03, "elapsed_time": "1:12:55", "remaining_time": "5:55:13", "throughput": 1493.12, "total_tokens": 6533152} {"current_steps": 30970, "total_steps": 181800, "loss": 0.0212, "lr": 4.9250059487225283e-05, "epoch": 3.407040704070407, "percentage": 17.04, "elapsed_time": "1:12:56", "remaining_time": "5:55:12", "throughput": 1493.12, "total_tokens": 6534208} {"current_steps": 30975, "total_steps": 181800, "loss": 0.0697, "lr": 4.92494759300004e-05, "epoch": 3.407590759075908, "percentage": 17.04, "elapsed_time": "1:12:56", "remaining_time": "5:55:12", "throughput": 1493.12, "total_tokens": 6535232} {"current_steps": 30980, "total_steps": 181800, "loss": 0.0716, "lr": 4.924889214927973e-05, "epoch": 3.408140814081408, "percentage": 17.04, "elapsed_time": "1:12:57", "remaining_time": "5:55:11", "throughput": 1493.13, "total_tokens": 6536288} {"current_steps": 30985, "total_steps": 181800, "loss": 0.0868, "lr": 4.924830814506866e-05, "epoch": 3.4086908690869087, "percentage": 17.04, "elapsed_time": "1:12:58", "remaining_time": "5:55:10", "throughput": 1493.14, "total_tokens": 6537344} {"current_steps": 30990, "total_steps": 181800, "loss": 0.1135, "lr": 4.9247723917372565e-05, "epoch": 3.4092409240924093, "percentage": 17.05, "elapsed_time": "1:12:58", "remaining_time": "5:55:09", "throughput": 1493.14, "total_tokens": 6538400} {"current_steps": 30995, "total_steps": 181800, "loss": 0.0886, "lr": 4.924713946619684e-05, "epoch": 3.40979097909791, "percentage": 17.05, "elapsed_time": "1:12:59", "remaining_time": "5:55:08", "throughput": 1493.16, "total_tokens": 6539488} {"current_steps": 31000, "total_steps": 181800, "loss": 0.0153, "lr": 4.924655479154686e-05, "epoch": 3.41034103410341, "percentage": 17.05, "elapsed_time": "1:13:00", "remaining_time": "5:55:08", "throughput": 1493.17, "total_tokens": 6540544} {"current_steps": 31005, "total_steps": 181800, "loss": 0.0506, "lr": 4.924596989342802e-05, "epoch": 3.410891089108911, "percentage": 17.05, "elapsed_time": "1:13:01", "remaining_time": "5:55:07", "throughput": 1493.18, "total_tokens": 6541632} {"current_steps": 31010, "total_steps": 181800, "loss": 0.1286, "lr": 4.924538477184571e-05, "epoch": 3.4114411441144115, "percentage": 17.06, "elapsed_time": "1:13:01", "remaining_time": "5:55:06", "throughput": 1493.18, "total_tokens": 6542656} {"current_steps": 31015, "total_steps": 181800, "loss": 0.0494, "lr": 4.924479942680533e-05, "epoch": 3.411991199119912, "percentage": 17.06, "elapsed_time": "1:13:02", "remaining_time": "5:55:05", "throughput": 1493.19, "total_tokens": 6543744} {"current_steps": 31020, "total_steps": 181800, "loss": 0.0604, "lr": 4.924421385831227e-05, "epoch": 3.4125412541254123, "percentage": 17.06, "elapsed_time": "1:13:03", "remaining_time": "5:55:04", "throughput": 1493.18, "total_tokens": 6544736} {"current_steps": 31025, "total_steps": 181800, "loss": 0.0593, "lr": 4.924362806637191e-05, "epoch": 3.413091309130913, "percentage": 17.07, "elapsed_time": "1:13:03", "remaining_time": "5:55:04", "throughput": 1493.18, "total_tokens": 6545760} {"current_steps": 31030, "total_steps": 181800, "loss": 0.0408, "lr": 4.924304205098967e-05, "epoch": 3.4136413641364136, "percentage": 17.07, "elapsed_time": "1:13:04", "remaining_time": "5:55:03", "throughput": 1493.2, "total_tokens": 6546880} {"current_steps": 31035, "total_steps": 181800, "loss": 0.0691, "lr": 4.924245581217095e-05, "epoch": 3.4141914191419143, "percentage": 17.07, "elapsed_time": "1:13:05", "remaining_time": "5:55:02", "throughput": 1493.21, "total_tokens": 6547968} {"current_steps": 31040, "total_steps": 181800, "loss": 0.0352, "lr": 4.924186934992114e-05, "epoch": 3.414741474147415, "percentage": 17.07, "elapsed_time": "1:13:05", "remaining_time": "5:55:01", "throughput": 1493.22, "total_tokens": 6549024} {"current_steps": 31045, "total_steps": 181800, "loss": 0.0192, "lr": 4.924128266424565e-05, "epoch": 3.415291529152915, "percentage": 17.08, "elapsed_time": "1:13:06", "remaining_time": "5:55:01", "throughput": 1493.21, "total_tokens": 6550016} {"current_steps": 31050, "total_steps": 181800, "loss": 0.039, "lr": 4.9240695755149894e-05, "epoch": 3.4158415841584158, "percentage": 17.08, "elapsed_time": "1:13:07", "remaining_time": "5:55:00", "throughput": 1493.22, "total_tokens": 6551072} {"current_steps": 31055, "total_steps": 181800, "loss": 0.0354, "lr": 4.924010862263928e-05, "epoch": 3.4163916391639164, "percentage": 17.08, "elapsed_time": "1:13:07", "remaining_time": "5:54:59", "throughput": 1493.21, "total_tokens": 6552064} {"current_steps": 31060, "total_steps": 181800, "loss": 0.0169, "lr": 4.9239521266719216e-05, "epoch": 3.416941694169417, "percentage": 17.08, "elapsed_time": "1:13:08", "remaining_time": "5:54:58", "throughput": 1493.21, "total_tokens": 6553120} {"current_steps": 31065, "total_steps": 181800, "loss": 0.0674, "lr": 4.923893368739511e-05, "epoch": 3.4174917491749177, "percentage": 17.09, "elapsed_time": "1:13:09", "remaining_time": "5:54:57", "throughput": 1493.23, "total_tokens": 6554208} {"current_steps": 31070, "total_steps": 181800, "loss": 0.0181, "lr": 4.923834588467239e-05, "epoch": 3.418041804180418, "percentage": 17.09, "elapsed_time": "1:13:09", "remaining_time": "5:54:57", "throughput": 1493.23, "total_tokens": 6555264} {"current_steps": 31075, "total_steps": 181800, "loss": 0.0351, "lr": 4.923775785855646e-05, "epoch": 3.4185918591859186, "percentage": 17.09, "elapsed_time": "1:13:10", "remaining_time": "5:54:56", "throughput": 1493.24, "total_tokens": 6556320} {"current_steps": 31080, "total_steps": 181800, "loss": 0.0501, "lr": 4.9237169609052744e-05, "epoch": 3.419141914191419, "percentage": 17.1, "elapsed_time": "1:13:11", "remaining_time": "5:54:55", "throughput": 1493.24, "total_tokens": 6557344} {"current_steps": 31085, "total_steps": 181800, "loss": 0.0118, "lr": 4.9236581136166676e-05, "epoch": 3.41969196919692, "percentage": 17.1, "elapsed_time": "1:13:12", "remaining_time": "5:54:54", "throughput": 1493.24, "total_tokens": 6558368} {"current_steps": 31090, "total_steps": 181800, "loss": 0.0234, "lr": 4.923599243990367e-05, "epoch": 3.42024202420242, "percentage": 17.1, "elapsed_time": "1:13:12", "remaining_time": "5:54:53", "throughput": 1493.25, "total_tokens": 6559456} {"current_steps": 31095, "total_steps": 181800, "loss": 0.0943, "lr": 4.923540352026914e-05, "epoch": 3.4207920792079207, "percentage": 17.1, "elapsed_time": "1:13:13", "remaining_time": "5:54:53", "throughput": 1493.27, "total_tokens": 6560544} {"current_steps": 31100, "total_steps": 181800, "loss": 0.0813, "lr": 4.923481437726853e-05, "epoch": 3.4213421342134214, "percentage": 17.11, "elapsed_time": "1:13:14", "remaining_time": "5:54:52", "throughput": 1493.28, "total_tokens": 6561632} {"current_steps": 31105, "total_steps": 181800, "loss": 0.0311, "lr": 4.923422501090726e-05, "epoch": 3.421892189218922, "percentage": 17.11, "elapsed_time": "1:13:14", "remaining_time": "5:54:51", "throughput": 1493.29, "total_tokens": 6562720} {"current_steps": 31110, "total_steps": 181800, "loss": 0.1382, "lr": 4.9233635421190784e-05, "epoch": 3.4224422442244222, "percentage": 17.11, "elapsed_time": "1:13:15", "remaining_time": "5:54:50", "throughput": 1493.3, "total_tokens": 6563808} {"current_steps": 31115, "total_steps": 181800, "loss": 0.075, "lr": 4.92330456081245e-05, "epoch": 3.422992299229923, "percentage": 17.11, "elapsed_time": "1:13:16", "remaining_time": "5:54:50", "throughput": 1493.32, "total_tokens": 6564928} {"current_steps": 31120, "total_steps": 181800, "loss": 0.0359, "lr": 4.923245557171388e-05, "epoch": 3.4235423542354235, "percentage": 17.12, "elapsed_time": "1:13:16", "remaining_time": "5:54:49", "throughput": 1493.33, "total_tokens": 6565984} {"current_steps": 31125, "total_steps": 181800, "loss": 0.0846, "lr": 4.923186531196433e-05, "epoch": 3.424092409240924, "percentage": 17.12, "elapsed_time": "1:13:17", "remaining_time": "5:54:48", "throughput": 1493.34, "total_tokens": 6567040} {"current_steps": 31130, "total_steps": 181800, "loss": 0.125, "lr": 4.9231274828881315e-05, "epoch": 3.424642464246425, "percentage": 17.12, "elapsed_time": "1:13:18", "remaining_time": "5:54:47", "throughput": 1493.34, "total_tokens": 6568096} {"current_steps": 31135, "total_steps": 181800, "loss": 0.0717, "lr": 4.923068412247026e-05, "epoch": 3.425192519251925, "percentage": 17.13, "elapsed_time": "1:13:18", "remaining_time": "5:54:46", "throughput": 1493.34, "total_tokens": 6569088} {"current_steps": 31140, "total_steps": 181800, "loss": 0.2156, "lr": 4.923009319273662e-05, "epoch": 3.4257425742574257, "percentage": 17.13, "elapsed_time": "1:13:19", "remaining_time": "5:54:46", "throughput": 1493.36, "total_tokens": 6570208} {"current_steps": 31145, "total_steps": 181800, "loss": 0.0628, "lr": 4.922950203968583e-05, "epoch": 3.4262926292629263, "percentage": 17.13, "elapsed_time": "1:13:20", "remaining_time": "5:54:45", "throughput": 1493.36, "total_tokens": 6571264} {"current_steps": 31150, "total_steps": 181800, "loss": 0.0695, "lr": 4.922891066332336e-05, "epoch": 3.426842684268427, "percentage": 17.13, "elapsed_time": "1:13:20", "remaining_time": "5:54:44", "throughput": 1493.37, "total_tokens": 6572320} {"current_steps": 31155, "total_steps": 181800, "loss": 0.0258, "lr": 4.922831906365463e-05, "epoch": 3.4273927392739276, "percentage": 17.14, "elapsed_time": "1:13:21", "remaining_time": "5:54:43", "throughput": 1493.37, "total_tokens": 6573344} {"current_steps": 31160, "total_steps": 181800, "loss": 0.0258, "lr": 4.922772724068512e-05, "epoch": 3.427942794279428, "percentage": 17.14, "elapsed_time": "1:13:22", "remaining_time": "5:54:42", "throughput": 1493.38, "total_tokens": 6574432} {"current_steps": 31165, "total_steps": 181800, "loss": 0.066, "lr": 4.922713519442027e-05, "epoch": 3.4284928492849285, "percentage": 17.14, "elapsed_time": "1:13:23", "remaining_time": "5:54:42", "throughput": 1493.39, "total_tokens": 6575488} {"current_steps": 31170, "total_steps": 181800, "loss": 0.0072, "lr": 4.9226542924865546e-05, "epoch": 3.429042904290429, "percentage": 17.15, "elapsed_time": "1:13:23", "remaining_time": "5:54:41", "throughput": 1493.4, "total_tokens": 6576576} {"current_steps": 31175, "total_steps": 181800, "loss": 0.0373, "lr": 4.92259504320264e-05, "epoch": 3.4295929592959298, "percentage": 17.15, "elapsed_time": "1:13:24", "remaining_time": "5:54:40", "throughput": 1493.41, "total_tokens": 6577632} {"current_steps": 31180, "total_steps": 181800, "loss": 0.111, "lr": 4.922535771590829e-05, "epoch": 3.43014301430143, "percentage": 17.15, "elapsed_time": "1:13:25", "remaining_time": "5:54:39", "throughput": 1493.42, "total_tokens": 6578720} {"current_steps": 31185, "total_steps": 181800, "loss": 0.0435, "lr": 4.922476477651668e-05, "epoch": 3.4306930693069306, "percentage": 17.15, "elapsed_time": "1:13:25", "remaining_time": "5:54:38", "throughput": 1493.43, "total_tokens": 6579776} {"current_steps": 31190, "total_steps": 181800, "loss": 0.0699, "lr": 4.922417161385704e-05, "epoch": 3.4312431243124313, "percentage": 17.16, "elapsed_time": "1:13:26", "remaining_time": "5:54:38", "throughput": 1493.43, "total_tokens": 6580832} {"current_steps": 31195, "total_steps": 181800, "loss": 0.0365, "lr": 4.922357822793483e-05, "epoch": 3.431793179317932, "percentage": 17.16, "elapsed_time": "1:13:27", "remaining_time": "5:54:37", "throughput": 1493.44, "total_tokens": 6581888} {"current_steps": 31200, "total_steps": 181800, "loss": 0.0656, "lr": 4.922298461875553e-05, "epoch": 3.432343234323432, "percentage": 17.16, "elapsed_time": "1:13:27", "remaining_time": "5:54:36", "throughput": 1493.46, "total_tokens": 6582976} {"current_steps": 31205, "total_steps": 181800, "loss": 0.0256, "lr": 4.92223907863246e-05, "epoch": 3.432893289328933, "percentage": 17.16, "elapsed_time": "1:13:28", "remaining_time": "5:54:35", "throughput": 1493.47, "total_tokens": 6584064} {"current_steps": 31210, "total_steps": 181800, "loss": 0.0387, "lr": 4.9221796730647516e-05, "epoch": 3.4334433443344334, "percentage": 17.17, "elapsed_time": "1:13:29", "remaining_time": "5:54:34", "throughput": 1493.49, "total_tokens": 6585184} {"current_steps": 31215, "total_steps": 181800, "loss": 0.0283, "lr": 4.922120245172977e-05, "epoch": 3.433993399339934, "percentage": 17.17, "elapsed_time": "1:13:29", "remaining_time": "5:54:34", "throughput": 1493.51, "total_tokens": 6586304} {"current_steps": 31220, "total_steps": 181800, "loss": 0.1147, "lr": 4.92206079495768e-05, "epoch": 3.4345434543454347, "percentage": 17.17, "elapsed_time": "1:13:30", "remaining_time": "5:54:33", "throughput": 1493.52, "total_tokens": 6587360} {"current_steps": 31225, "total_steps": 181800, "loss": 0.0161, "lr": 4.9220013224194126e-05, "epoch": 3.435093509350935, "percentage": 17.18, "elapsed_time": "1:13:31", "remaining_time": "5:54:32", "throughput": 1493.53, "total_tokens": 6588416} {"current_steps": 31230, "total_steps": 181800, "loss": 0.1621, "lr": 4.9219418275587205e-05, "epoch": 3.4356435643564356, "percentage": 17.18, "elapsed_time": "1:13:32", "remaining_time": "5:54:31", "throughput": 1493.54, "total_tokens": 6589504} {"current_steps": 31235, "total_steps": 181800, "loss": 0.1073, "lr": 4.921882310376152e-05, "epoch": 3.4361936193619362, "percentage": 17.18, "elapsed_time": "1:13:32", "remaining_time": "5:54:30", "throughput": 1493.57, "total_tokens": 6590656} {"current_steps": 31240, "total_steps": 181800, "loss": 0.1033, "lr": 4.9218227708722573e-05, "epoch": 3.436743674367437, "percentage": 17.18, "elapsed_time": "1:13:33", "remaining_time": "5:54:30", "throughput": 1493.56, "total_tokens": 6591648} {"current_steps": 31245, "total_steps": 181800, "loss": 0.0232, "lr": 4.921763209047584e-05, "epoch": 3.4372937293729375, "percentage": 17.19, "elapsed_time": "1:13:34", "remaining_time": "5:54:29", "throughput": 1493.57, "total_tokens": 6592736} {"current_steps": 31250, "total_steps": 181800, "loss": 0.0118, "lr": 4.921703624902682e-05, "epoch": 3.4378437843784377, "percentage": 17.19, "elapsed_time": "1:13:34", "remaining_time": "5:54:28", "throughput": 1493.57, "total_tokens": 6593760} {"current_steps": 31255, "total_steps": 181800, "loss": 0.0574, "lr": 4.921644018438099e-05, "epoch": 3.4383938393839384, "percentage": 17.19, "elapsed_time": "1:13:35", "remaining_time": "5:54:27", "throughput": 1493.58, "total_tokens": 6594816} {"current_steps": 31260, "total_steps": 181800, "loss": 0.1075, "lr": 4.921584389654385e-05, "epoch": 3.438943894389439, "percentage": 17.19, "elapsed_time": "1:13:36", "remaining_time": "5:54:26", "throughput": 1493.58, "total_tokens": 6595840} {"current_steps": 31265, "total_steps": 181800, "loss": 0.0962, "lr": 4.92152473855209e-05, "epoch": 3.4394939493949397, "percentage": 17.2, "elapsed_time": "1:13:36", "remaining_time": "5:54:26", "throughput": 1493.58, "total_tokens": 6596864} {"current_steps": 31270, "total_steps": 181800, "loss": 0.1319, "lr": 4.921465065131763e-05, "epoch": 3.44004400440044, "percentage": 17.2, "elapsed_time": "1:13:37", "remaining_time": "5:54:25", "throughput": 1493.58, "total_tokens": 6597920} {"current_steps": 31275, "total_steps": 181800, "loss": 0.0476, "lr": 4.921405369393955e-05, "epoch": 3.4405940594059405, "percentage": 17.2, "elapsed_time": "1:13:38", "remaining_time": "5:54:24", "throughput": 1493.6, "total_tokens": 6599008} {"current_steps": 31280, "total_steps": 181800, "loss": 0.0502, "lr": 4.921345651339215e-05, "epoch": 3.441144114411441, "percentage": 17.21, "elapsed_time": "1:13:38", "remaining_time": "5:54:23", "throughput": 1493.6, "total_tokens": 6600064} {"current_steps": 31285, "total_steps": 181800, "loss": 0.0352, "lr": 4.921285910968094e-05, "epoch": 3.441694169416942, "percentage": 17.21, "elapsed_time": "1:13:39", "remaining_time": "5:54:23", "throughput": 1493.61, "total_tokens": 6601120} {"current_steps": 31290, "total_steps": 181800, "loss": 0.0811, "lr": 4.9212261482811426e-05, "epoch": 3.442244224422442, "percentage": 17.21, "elapsed_time": "1:13:40", "remaining_time": "5:54:22", "throughput": 1493.62, "total_tokens": 6602208} {"current_steps": 31295, "total_steps": 181800, "loss": 0.0425, "lr": 4.921166363278912e-05, "epoch": 3.4427942794279427, "percentage": 17.21, "elapsed_time": "1:13:40", "remaining_time": "5:54:21", "throughput": 1493.63, "total_tokens": 6603264} {"current_steps": 31300, "total_steps": 181800, "loss": 0.0378, "lr": 4.921106555961953e-05, "epoch": 3.4433443344334433, "percentage": 17.22, "elapsed_time": "1:13:41", "remaining_time": "5:54:20", "throughput": 1493.63, "total_tokens": 6604320} {"current_steps": 31305, "total_steps": 181800, "loss": 0.0928, "lr": 4.921046726330817e-05, "epoch": 3.443894389438944, "percentage": 17.22, "elapsed_time": "1:13:42", "remaining_time": "5:54:19", "throughput": 1493.63, "total_tokens": 6605344} {"current_steps": 31310, "total_steps": 181800, "loss": 0.1152, "lr": 4.920986874386054e-05, "epoch": 3.4444444444444446, "percentage": 17.22, "elapsed_time": "1:13:43", "remaining_time": "5:54:19", "throughput": 1493.65, "total_tokens": 6606464} {"current_steps": 31315, "total_steps": 181800, "loss": 0.0533, "lr": 4.920927000128217e-05, "epoch": 3.444994499449945, "percentage": 17.22, "elapsed_time": "1:13:43", "remaining_time": "5:54:18", "throughput": 1493.67, "total_tokens": 6607552} {"current_steps": 31320, "total_steps": 181800, "loss": 0.0217, "lr": 4.920867103557858e-05, "epoch": 3.4455445544554455, "percentage": 17.23, "elapsed_time": "1:13:44", "remaining_time": "5:54:17", "throughput": 1493.67, "total_tokens": 6608576} {"current_steps": 31325, "total_steps": 181800, "loss": 0.055, "lr": 4.920807184675528e-05, "epoch": 3.446094609460946, "percentage": 17.23, "elapsed_time": "1:13:45", "remaining_time": "5:54:16", "throughput": 1493.67, "total_tokens": 6609632} {"current_steps": 31330, "total_steps": 181800, "loss": 0.0426, "lr": 4.92074724348178e-05, "epoch": 3.446644664466447, "percentage": 17.23, "elapsed_time": "1:13:45", "remaining_time": "5:54:15", "throughput": 1493.69, "total_tokens": 6610752} {"current_steps": 31335, "total_steps": 181800, "loss": 0.0448, "lr": 4.920687279977166e-05, "epoch": 3.4471947194719474, "percentage": 17.24, "elapsed_time": "1:13:46", "remaining_time": "5:54:15", "throughput": 1493.69, "total_tokens": 6611776} {"current_steps": 31340, "total_steps": 181800, "loss": 0.0694, "lr": 4.920627294162239e-05, "epoch": 3.4477447744774476, "percentage": 17.24, "elapsed_time": "1:13:47", "remaining_time": "5:54:14", "throughput": 1493.7, "total_tokens": 6612864} {"current_steps": 31345, "total_steps": 181800, "loss": 0.1182, "lr": 4.920567286037552e-05, "epoch": 3.4482948294829483, "percentage": 17.24, "elapsed_time": "1:13:47", "remaining_time": "5:54:13", "throughput": 1493.72, "total_tokens": 6613952} {"current_steps": 31350, "total_steps": 181800, "loss": 0.0442, "lr": 4.920507255603658e-05, "epoch": 3.448844884488449, "percentage": 17.24, "elapsed_time": "1:13:48", "remaining_time": "5:54:12", "throughput": 1493.72, "total_tokens": 6614976} {"current_steps": 31355, "total_steps": 181800, "loss": 0.0334, "lr": 4.9204472028611096e-05, "epoch": 3.449394939493949, "percentage": 17.25, "elapsed_time": "1:13:49", "remaining_time": "5:54:11", "throughput": 1493.72, "total_tokens": 6616032} {"current_steps": 31360, "total_steps": 181800, "loss": 0.0393, "lr": 4.9203871278104605e-05, "epoch": 3.44994499449945, "percentage": 17.25, "elapsed_time": "1:13:49", "remaining_time": "5:54:11", "throughput": 1493.74, "total_tokens": 6617152} {"current_steps": 31365, "total_steps": 181800, "loss": 0.0771, "lr": 4.920327030452265e-05, "epoch": 3.4504950495049505, "percentage": 17.25, "elapsed_time": "1:13:50", "remaining_time": "5:54:10", "throughput": 1493.76, "total_tokens": 6618240} {"current_steps": 31370, "total_steps": 181800, "loss": 0.0437, "lr": 4.9202669107870775e-05, "epoch": 3.451045104510451, "percentage": 17.26, "elapsed_time": "1:13:51", "remaining_time": "5:54:09", "throughput": 1493.76, "total_tokens": 6619296} {"current_steps": 31375, "total_steps": 181800, "loss": 0.026, "lr": 4.920206768815451e-05, "epoch": 3.4515951595159517, "percentage": 17.26, "elapsed_time": "1:13:51", "remaining_time": "5:54:08", "throughput": 1493.77, "total_tokens": 6620352} {"current_steps": 31380, "total_steps": 181800, "loss": 0.0225, "lr": 4.920146604537939e-05, "epoch": 3.452145214521452, "percentage": 17.26, "elapsed_time": "1:13:52", "remaining_time": "5:54:07", "throughput": 1493.77, "total_tokens": 6621408} {"current_steps": 31385, "total_steps": 181800, "loss": 0.0654, "lr": 4.9200864179550975e-05, "epoch": 3.4526952695269526, "percentage": 17.26, "elapsed_time": "1:13:53", "remaining_time": "5:54:07", "throughput": 1493.77, "total_tokens": 6622432} {"current_steps": 31390, "total_steps": 181800, "loss": 0.0398, "lr": 4.920026209067481e-05, "epoch": 3.4532453245324533, "percentage": 17.27, "elapsed_time": "1:13:54", "remaining_time": "5:54:06", "throughput": 1493.79, "total_tokens": 6623520} {"current_steps": 31395, "total_steps": 181800, "loss": 0.0533, "lr": 4.919965977875644e-05, "epoch": 3.453795379537954, "percentage": 17.27, "elapsed_time": "1:13:54", "remaining_time": "5:54:05", "throughput": 1493.78, "total_tokens": 6624512} {"current_steps": 31400, "total_steps": 181800, "loss": 0.0119, "lr": 4.9199057243801416e-05, "epoch": 3.4543454345434546, "percentage": 17.27, "elapsed_time": "1:13:55", "remaining_time": "5:54:04", "throughput": 1493.77, "total_tokens": 6625504} {"current_steps": 31405, "total_steps": 181800, "loss": 0.0158, "lr": 4.91984544858153e-05, "epoch": 3.4548954895489548, "percentage": 17.27, "elapsed_time": "1:13:56", "remaining_time": "5:54:04", "throughput": 1493.77, "total_tokens": 6626560} {"current_steps": 31410, "total_steps": 181800, "loss": 0.0413, "lr": 4.9197851504803635e-05, "epoch": 3.4554455445544554, "percentage": 17.28, "elapsed_time": "1:13:56", "remaining_time": "5:54:03", "throughput": 1493.78, "total_tokens": 6627616} {"current_steps": 31415, "total_steps": 181800, "loss": 0.0285, "lr": 4.919724830077199e-05, "epoch": 3.455995599559956, "percentage": 17.28, "elapsed_time": "1:13:57", "remaining_time": "5:54:02", "throughput": 1493.81, "total_tokens": 6628768} {"current_steps": 31420, "total_steps": 181800, "loss": 0.1155, "lr": 4.9196644873725906e-05, "epoch": 3.4565456545654567, "percentage": 17.28, "elapsed_time": "1:13:58", "remaining_time": "5:54:01", "throughput": 1493.81, "total_tokens": 6629792} {"current_steps": 31425, "total_steps": 181800, "loss": 0.1337, "lr": 4.919604122367096e-05, "epoch": 3.457095709570957, "percentage": 17.29, "elapsed_time": "1:13:58", "remaining_time": "5:54:00", "throughput": 1493.81, "total_tokens": 6630848} {"current_steps": 31430, "total_steps": 181800, "loss": 0.1113, "lr": 4.919543735061273e-05, "epoch": 3.4576457645764576, "percentage": 17.29, "elapsed_time": "1:13:59", "remaining_time": "5:54:00", "throughput": 1493.82, "total_tokens": 6631904} {"current_steps": 31435, "total_steps": 181800, "loss": 0.072, "lr": 4.919483325455674e-05, "epoch": 3.458195819581958, "percentage": 17.29, "elapsed_time": "1:14:00", "remaining_time": "5:53:59", "throughput": 1493.83, "total_tokens": 6632992} {"current_steps": 31440, "total_steps": 181800, "loss": 0.0395, "lr": 4.9194228935508595e-05, "epoch": 3.458745874587459, "percentage": 17.29, "elapsed_time": "1:14:00", "remaining_time": "5:53:58", "throughput": 1493.83, "total_tokens": 6634016} {"current_steps": 31445, "total_steps": 181800, "loss": 0.0461, "lr": 4.919362439347385e-05, "epoch": 3.459295929592959, "percentage": 17.3, "elapsed_time": "1:14:01", "remaining_time": "5:53:57", "throughput": 1493.83, "total_tokens": 6635040} {"current_steps": 31450, "total_steps": 181800, "loss": 0.0169, "lr": 4.919301962845808e-05, "epoch": 3.4598459845984597, "percentage": 17.3, "elapsed_time": "1:14:02", "remaining_time": "5:53:57", "throughput": 1493.83, "total_tokens": 6636096} {"current_steps": 31455, "total_steps": 181800, "loss": 0.0322, "lr": 4.919241464046686e-05, "epoch": 3.4603960396039604, "percentage": 17.3, "elapsed_time": "1:14:03", "remaining_time": "5:53:56", "throughput": 1493.83, "total_tokens": 6637120} {"current_steps": 31460, "total_steps": 181800, "loss": 0.1329, "lr": 4.919180942950575e-05, "epoch": 3.460946094609461, "percentage": 17.3, "elapsed_time": "1:14:03", "remaining_time": "5:53:55", "throughput": 1493.83, "total_tokens": 6638144} {"current_steps": 31465, "total_steps": 181800, "loss": 0.0829, "lr": 4.9191203995580347e-05, "epoch": 3.4614961496149617, "percentage": 17.31, "elapsed_time": "1:14:04", "remaining_time": "5:53:54", "throughput": 1493.84, "total_tokens": 6639232} {"current_steps": 31470, "total_steps": 181800, "loss": 0.0472, "lr": 4.9190598338696225e-05, "epoch": 3.462046204620462, "percentage": 17.31, "elapsed_time": "1:14:05", "remaining_time": "5:53:53", "throughput": 1493.84, "total_tokens": 6640224} {"current_steps": 31475, "total_steps": 181800, "loss": 0.0899, "lr": 4.918999245885897e-05, "epoch": 3.4625962596259625, "percentage": 17.31, "elapsed_time": "1:14:05", "remaining_time": "5:53:53", "throughput": 1493.85, "total_tokens": 6641312} {"current_steps": 31480, "total_steps": 181800, "loss": 0.1008, "lr": 4.9189386356074154e-05, "epoch": 3.463146314631463, "percentage": 17.32, "elapsed_time": "1:14:06", "remaining_time": "5:53:52", "throughput": 1493.85, "total_tokens": 6642336} {"current_steps": 31485, "total_steps": 181800, "loss": 0.0626, "lr": 4.918878003034738e-05, "epoch": 3.463696369636964, "percentage": 17.32, "elapsed_time": "1:14:07", "remaining_time": "5:53:51", "throughput": 1493.86, "total_tokens": 6643424} {"current_steps": 31490, "total_steps": 181800, "loss": 0.0544, "lr": 4.9188173481684216e-05, "epoch": 3.4642464246424645, "percentage": 17.32, "elapsed_time": "1:14:07", "remaining_time": "5:53:50", "throughput": 1493.87, "total_tokens": 6644480} {"current_steps": 31495, "total_steps": 181800, "loss": 0.0553, "lr": 4.9187566710090275e-05, "epoch": 3.4647964796479647, "percentage": 17.32, "elapsed_time": "1:14:08", "remaining_time": "5:53:49", "throughput": 1493.87, "total_tokens": 6645536} {"current_steps": 31500, "total_steps": 181800, "loss": 0.119, "lr": 4.918695971557113e-05, "epoch": 3.4653465346534653, "percentage": 17.33, "elapsed_time": "1:14:09", "remaining_time": "5:53:49", "throughput": 1493.87, "total_tokens": 6646560} {"current_steps": 31505, "total_steps": 181800, "loss": 0.0801, "lr": 4.9186352498132395e-05, "epoch": 3.465896589658966, "percentage": 17.33, "elapsed_time": "1:14:09", "remaining_time": "5:53:48", "throughput": 1493.87, "total_tokens": 6647584} {"current_steps": 31510, "total_steps": 181800, "loss": 0.0732, "lr": 4.918574505777964e-05, "epoch": 3.4664466446644666, "percentage": 17.33, "elapsed_time": "1:14:10", "remaining_time": "5:53:47", "throughput": 1493.87, "total_tokens": 6648608} {"current_steps": 31515, "total_steps": 181800, "loss": 0.0346, "lr": 4.918513739451849e-05, "epoch": 3.466996699669967, "percentage": 17.33, "elapsed_time": "1:14:11", "remaining_time": "5:53:46", "throughput": 1493.87, "total_tokens": 6649632} {"current_steps": 31520, "total_steps": 181800, "loss": 0.1201, "lr": 4.9184529508354524e-05, "epoch": 3.4675467546754675, "percentage": 17.34, "elapsed_time": "1:14:11", "remaining_time": "5:53:45", "throughput": 1493.88, "total_tokens": 6650720} {"current_steps": 31525, "total_steps": 181800, "loss": 0.0304, "lr": 4.9183921399293363e-05, "epoch": 3.468096809680968, "percentage": 17.34, "elapsed_time": "1:14:12", "remaining_time": "5:53:45", "throughput": 1493.88, "total_tokens": 6651776} {"current_steps": 31530, "total_steps": 181800, "loss": 0.1203, "lr": 4.91833130673406e-05, "epoch": 3.4686468646864688, "percentage": 17.34, "elapsed_time": "1:14:13", "remaining_time": "5:53:44", "throughput": 1493.89, "total_tokens": 6652832} {"current_steps": 31535, "total_steps": 181800, "loss": 0.0759, "lr": 4.918270451250184e-05, "epoch": 3.469196919691969, "percentage": 17.35, "elapsed_time": "1:14:14", "remaining_time": "5:53:43", "throughput": 1493.9, "total_tokens": 6653920} {"current_steps": 31540, "total_steps": 181800, "loss": 0.0472, "lr": 4.918209573478271e-05, "epoch": 3.4697469746974696, "percentage": 17.35, "elapsed_time": "1:14:14", "remaining_time": "5:53:42", "throughput": 1493.9, "total_tokens": 6654944} {"current_steps": 31545, "total_steps": 181800, "loss": 0.0585, "lr": 4.918148673418879e-05, "epoch": 3.4702970297029703, "percentage": 17.35, "elapsed_time": "1:14:15", "remaining_time": "5:53:42", "throughput": 1493.9, "total_tokens": 6655968} {"current_steps": 31550, "total_steps": 181800, "loss": 0.0287, "lr": 4.918087751072572e-05, "epoch": 3.470847084708471, "percentage": 17.35, "elapsed_time": "1:14:16", "remaining_time": "5:53:41", "throughput": 1493.9, "total_tokens": 6657024} {"current_steps": 31555, "total_steps": 181800, "loss": 0.0128, "lr": 4.91802680643991e-05, "epoch": 3.4713971397139716, "percentage": 17.36, "elapsed_time": "1:14:16", "remaining_time": "5:53:40", "throughput": 1493.92, "total_tokens": 6658112} {"current_steps": 31560, "total_steps": 181800, "loss": 0.0251, "lr": 4.917965839521455e-05, "epoch": 3.4719471947194718, "percentage": 17.36, "elapsed_time": "1:14:17", "remaining_time": "5:53:39", "throughput": 1493.92, "total_tokens": 6659168} {"current_steps": 31565, "total_steps": 181800, "loss": 0.0928, "lr": 4.91790485031777e-05, "epoch": 3.4724972497249724, "percentage": 17.36, "elapsed_time": "1:14:18", "remaining_time": "5:53:39", "throughput": 1493.95, "total_tokens": 6660320} {"current_steps": 31570, "total_steps": 181800, "loss": 0.0162, "lr": 4.917843838829416e-05, "epoch": 3.473047304730473, "percentage": 17.37, "elapsed_time": "1:14:18", "remaining_time": "5:53:38", "throughput": 1493.95, "total_tokens": 6661376} {"current_steps": 31575, "total_steps": 181800, "loss": 0.0898, "lr": 4.917782805056955e-05, "epoch": 3.4735973597359737, "percentage": 17.37, "elapsed_time": "1:14:19", "remaining_time": "5:53:37", "throughput": 1493.96, "total_tokens": 6662432} {"current_steps": 31580, "total_steps": 181800, "loss": 0.1226, "lr": 4.917721749000951e-05, "epoch": 3.4741474147414744, "percentage": 17.37, "elapsed_time": "1:14:20", "remaining_time": "5:53:36", "throughput": 1493.96, "total_tokens": 6663488} {"current_steps": 31585, "total_steps": 181800, "loss": 0.1098, "lr": 4.9176606706619654e-05, "epoch": 3.4746974697469746, "percentage": 17.37, "elapsed_time": "1:14:20", "remaining_time": "5:53:35", "throughput": 1493.97, "total_tokens": 6664544} {"current_steps": 31590, "total_steps": 181800, "loss": 0.0307, "lr": 4.9175995700405606e-05, "epoch": 3.4752475247524752, "percentage": 17.38, "elapsed_time": "1:14:21", "remaining_time": "5:53:35", "throughput": 1493.99, "total_tokens": 6665664} {"current_steps": 31595, "total_steps": 181800, "loss": 0.0559, "lr": 4.917538447137302e-05, "epoch": 3.475797579757976, "percentage": 17.38, "elapsed_time": "1:14:22", "remaining_time": "5:53:34", "throughput": 1494.0, "total_tokens": 6666720} {"current_steps": 31600, "total_steps": 181800, "loss": 0.0957, "lr": 4.9174773019527506e-05, "epoch": 3.4763476347634765, "percentage": 17.38, "elapsed_time": "1:14:23", "remaining_time": "5:53:33", "throughput": 1494.01, "total_tokens": 6667808} {"current_steps": 31605, "total_steps": 181800, "loss": 0.0517, "lr": 4.917416134487472e-05, "epoch": 3.4768976897689767, "percentage": 17.38, "elapsed_time": "1:14:23", "remaining_time": "5:53:32", "throughput": 1494.03, "total_tokens": 6668928} {"current_steps": 31610, "total_steps": 181800, "loss": 0.067, "lr": 4.917354944742027e-05, "epoch": 3.4774477447744774, "percentage": 17.39, "elapsed_time": "1:14:24", "remaining_time": "5:53:31", "throughput": 1494.03, "total_tokens": 6669984} {"current_steps": 31615, "total_steps": 181800, "loss": 0.1089, "lr": 4.917293732716983e-05, "epoch": 3.477997799779978, "percentage": 17.39, "elapsed_time": "1:14:25", "remaining_time": "5:53:31", "throughput": 1494.03, "total_tokens": 6671008} {"current_steps": 31620, "total_steps": 181800, "loss": 0.0801, "lr": 4.917232498412903e-05, "epoch": 3.4785478547854787, "percentage": 17.39, "elapsed_time": "1:14:25", "remaining_time": "5:53:30", "throughput": 1494.04, "total_tokens": 6672096} {"current_steps": 31625, "total_steps": 181800, "loss": 0.0176, "lr": 4.9171712418303496e-05, "epoch": 3.479097909790979, "percentage": 17.4, "elapsed_time": "1:14:26", "remaining_time": "5:53:29", "throughput": 1494.03, "total_tokens": 6673088} {"current_steps": 31630, "total_steps": 181800, "loss": 0.1817, "lr": 4.9171099629698894e-05, "epoch": 3.4796479647964795, "percentage": 17.4, "elapsed_time": "1:14:27", "remaining_time": "5:53:28", "throughput": 1494.03, "total_tokens": 6674112} {"current_steps": 31635, "total_steps": 181800, "loss": 0.0301, "lr": 4.917048661832086e-05, "epoch": 3.48019801980198, "percentage": 17.4, "elapsed_time": "1:14:27", "remaining_time": "5:53:28", "throughput": 1494.04, "total_tokens": 6675200} {"current_steps": 31640, "total_steps": 181800, "loss": 0.0183, "lr": 4.916987338417505e-05, "epoch": 3.480748074807481, "percentage": 17.4, "elapsed_time": "1:14:28", "remaining_time": "5:53:27", "throughput": 1494.05, "total_tokens": 6676256} {"current_steps": 31645, "total_steps": 181800, "loss": 0.074, "lr": 4.916925992726712e-05, "epoch": 3.4812981298129815, "percentage": 17.41, "elapsed_time": "1:14:29", "remaining_time": "5:53:26", "throughput": 1494.04, "total_tokens": 6677248} {"current_steps": 31650, "total_steps": 181800, "loss": 0.0594, "lr": 4.916864624760272e-05, "epoch": 3.4818481848184817, "percentage": 17.41, "elapsed_time": "1:14:29", "remaining_time": "5:53:25", "throughput": 1494.05, "total_tokens": 6678336} {"current_steps": 31655, "total_steps": 181800, "loss": 0.0237, "lr": 4.9168032345187497e-05, "epoch": 3.4823982398239823, "percentage": 17.41, "elapsed_time": "1:14:30", "remaining_time": "5:53:24", "throughput": 1494.06, "total_tokens": 6679392} {"current_steps": 31660, "total_steps": 181800, "loss": 0.0359, "lr": 4.9167418220027124e-05, "epoch": 3.482948294829483, "percentage": 17.41, "elapsed_time": "1:14:31", "remaining_time": "5:53:24", "throughput": 1494.06, "total_tokens": 6680448} {"current_steps": 31665, "total_steps": 181800, "loss": 0.0699, "lr": 4.9166803872127254e-05, "epoch": 3.4834983498349836, "percentage": 17.42, "elapsed_time": "1:14:32", "remaining_time": "5:53:23", "throughput": 1494.09, "total_tokens": 6681568} {"current_steps": 31670, "total_steps": 181800, "loss": 0.0768, "lr": 4.9166189301493544e-05, "epoch": 3.4840484048404843, "percentage": 17.42, "elapsed_time": "1:14:32", "remaining_time": "5:53:22", "throughput": 1494.09, "total_tokens": 6682624} {"current_steps": 31675, "total_steps": 181800, "loss": 0.112, "lr": 4.916557450813166e-05, "epoch": 3.4845984598459845, "percentage": 17.42, "elapsed_time": "1:14:33", "remaining_time": "5:53:21", "throughput": 1494.1, "total_tokens": 6683680} {"current_steps": 31680, "total_steps": 181800, "loss": 0.0366, "lr": 4.916495949204728e-05, "epoch": 3.485148514851485, "percentage": 17.43, "elapsed_time": "1:14:34", "remaining_time": "5:53:21", "throughput": 1494.1, "total_tokens": 6684736} {"current_steps": 31685, "total_steps": 181800, "loss": 0.0715, "lr": 4.9164344253246066e-05, "epoch": 3.485698569856986, "percentage": 17.43, "elapsed_time": "1:14:34", "remaining_time": "5:53:20", "throughput": 1494.12, "total_tokens": 6685856} {"current_steps": 31690, "total_steps": 181800, "loss": 0.0427, "lr": 4.916372879173368e-05, "epoch": 3.4862486248624864, "percentage": 17.43, "elapsed_time": "1:14:35", "remaining_time": "5:53:19", "throughput": 1494.14, "total_tokens": 6686976} {"current_steps": 31695, "total_steps": 181800, "loss": 0.0178, "lr": 4.9163113107515795e-05, "epoch": 3.4867986798679866, "percentage": 17.43, "elapsed_time": "1:14:36", "remaining_time": "5:53:18", "throughput": 1494.14, "total_tokens": 6688000} {"current_steps": 31700, "total_steps": 181800, "loss": 0.0659, "lr": 4.9162497200598104e-05, "epoch": 3.4873487348734873, "percentage": 17.44, "elapsed_time": "1:14:36", "remaining_time": "5:53:17", "throughput": 1494.17, "total_tokens": 6689152} {"current_steps": 31705, "total_steps": 181800, "loss": 0.1267, "lr": 4.916188107098626e-05, "epoch": 3.487898789878988, "percentage": 17.44, "elapsed_time": "1:14:37", "remaining_time": "5:53:17", "throughput": 1494.17, "total_tokens": 6690208} {"current_steps": 31710, "total_steps": 181800, "loss": 0.1392, "lr": 4.916126471868595e-05, "epoch": 3.4884488448844886, "percentage": 17.44, "elapsed_time": "1:14:38", "remaining_time": "5:53:16", "throughput": 1494.19, "total_tokens": 6691296} {"current_steps": 31715, "total_steps": 181800, "loss": 0.0554, "lr": 4.916064814370287e-05, "epoch": 3.488998899889989, "percentage": 17.44, "elapsed_time": "1:14:38", "remaining_time": "5:53:15", "throughput": 1494.19, "total_tokens": 6692352} {"current_steps": 31720, "total_steps": 181800, "loss": 0.0578, "lr": 4.916003134604268e-05, "epoch": 3.4895489548954894, "percentage": 17.45, "elapsed_time": "1:14:39", "remaining_time": "5:53:14", "throughput": 1494.2, "total_tokens": 6693408} {"current_steps": 31725, "total_steps": 181800, "loss": 0.077, "lr": 4.915941432571108e-05, "epoch": 3.49009900990099, "percentage": 17.45, "elapsed_time": "1:14:40", "remaining_time": "5:53:13", "throughput": 1494.2, "total_tokens": 6694464} {"current_steps": 31730, "total_steps": 181800, "loss": 0.0598, "lr": 4.915879708271375e-05, "epoch": 3.4906490649064907, "percentage": 17.45, "elapsed_time": "1:14:40", "remaining_time": "5:53:13", "throughput": 1494.21, "total_tokens": 6695520} {"current_steps": 31735, "total_steps": 181800, "loss": 0.0296, "lr": 4.915817961705637e-05, "epoch": 3.4911991199119914, "percentage": 17.46, "elapsed_time": "1:14:41", "remaining_time": "5:53:12", "throughput": 1494.2, "total_tokens": 6696512} {"current_steps": 31740, "total_steps": 181800, "loss": 0.0239, "lr": 4.915756192874465e-05, "epoch": 3.4917491749174916, "percentage": 17.46, "elapsed_time": "1:14:42", "remaining_time": "5:53:11", "throughput": 1494.21, "total_tokens": 6697568} {"current_steps": 31745, "total_steps": 181800, "loss": 0.0306, "lr": 4.9156944017784274e-05, "epoch": 3.4922992299229922, "percentage": 17.46, "elapsed_time": "1:14:43", "remaining_time": "5:53:10", "throughput": 1494.21, "total_tokens": 6698624} {"current_steps": 31750, "total_steps": 181800, "loss": 0.0336, "lr": 4.915632588418093e-05, "epoch": 3.492849284928493, "percentage": 17.46, "elapsed_time": "1:14:43", "remaining_time": "5:53:10", "throughput": 1494.21, "total_tokens": 6699648} {"current_steps": 31755, "total_steps": 181800, "loss": 0.06, "lr": 4.915570752794033e-05, "epoch": 3.4933993399339935, "percentage": 17.47, "elapsed_time": "1:14:44", "remaining_time": "5:53:09", "throughput": 1494.22, "total_tokens": 6700736} {"current_steps": 31760, "total_steps": 181800, "loss": 0.0454, "lr": 4.915508894906816e-05, "epoch": 3.493949394939494, "percentage": 17.47, "elapsed_time": "1:14:45", "remaining_time": "5:53:08", "throughput": 1494.22, "total_tokens": 6701760} {"current_steps": 31765, "total_steps": 181800, "loss": 0.0152, "lr": 4.9154470147570124e-05, "epoch": 3.4944994499449944, "percentage": 17.47, "elapsed_time": "1:14:45", "remaining_time": "5:53:07", "throughput": 1494.23, "total_tokens": 6702848} {"current_steps": 31770, "total_steps": 181800, "loss": 0.0684, "lr": 4.915385112345193e-05, "epoch": 3.495049504950495, "percentage": 17.48, "elapsed_time": "1:14:46", "remaining_time": "5:53:06", "throughput": 1494.27, "total_tokens": 6704032} {"current_steps": 31775, "total_steps": 181800, "loss": 0.0602, "lr": 4.9153231876719284e-05, "epoch": 3.4955995599559957, "percentage": 17.48, "elapsed_time": "1:14:47", "remaining_time": "5:53:06", "throughput": 1494.29, "total_tokens": 6705152} {"current_steps": 31780, "total_steps": 181800, "loss": 0.0444, "lr": 4.915261240737789e-05, "epoch": 3.4961496149614963, "percentage": 17.48, "elapsed_time": "1:14:47", "remaining_time": "5:53:05", "throughput": 1494.3, "total_tokens": 6706240} {"current_steps": 31785, "total_steps": 181800, "loss": 0.1162, "lr": 4.915199271543345e-05, "epoch": 3.4966996699669965, "percentage": 17.48, "elapsed_time": "1:14:48", "remaining_time": "5:53:04", "throughput": 1494.31, "total_tokens": 6707296} {"current_steps": 31790, "total_steps": 181800, "loss": 0.0836, "lr": 4.915137280089168e-05, "epoch": 3.497249724972497, "percentage": 17.49, "elapsed_time": "1:14:49", "remaining_time": "5:53:03", "throughput": 1494.32, "total_tokens": 6708384} {"current_steps": 31795, "total_steps": 181800, "loss": 0.0408, "lr": 4.9150752663758307e-05, "epoch": 3.497799779977998, "percentage": 17.49, "elapsed_time": "1:14:49", "remaining_time": "5:53:02", "throughput": 1494.32, "total_tokens": 6709408} {"current_steps": 31800, "total_steps": 181800, "loss": 0.0477, "lr": 4.9150132304039024e-05, "epoch": 3.4983498349834985, "percentage": 17.49, "elapsed_time": "1:14:50", "remaining_time": "5:53:02", "throughput": 1494.33, "total_tokens": 6710496} {"current_steps": 31805, "total_steps": 181800, "loss": 0.0803, "lr": 4.914951172173957e-05, "epoch": 3.4988998899889987, "percentage": 17.49, "elapsed_time": "1:14:51", "remaining_time": "5:53:01", "throughput": 1494.34, "total_tokens": 6711552} {"current_steps": 31810, "total_steps": 181800, "loss": 0.0453, "lr": 4.914889091686565e-05, "epoch": 3.4994499449944994, "percentage": 17.5, "elapsed_time": "1:14:52", "remaining_time": "5:53:00", "throughput": 1494.34, "total_tokens": 6712608} {"current_steps": 31815, "total_steps": 181800, "loss": 0.1203, "lr": 4.914826988942299e-05, "epoch": 3.5, "percentage": 17.5, "elapsed_time": "1:14:52", "remaining_time": "5:52:59", "throughput": 1494.35, "total_tokens": 6713664} {"current_steps": 31820, "total_steps": 181800, "loss": 0.0726, "lr": 4.914764863941731e-05, "epoch": 3.5005500550055006, "percentage": 17.5, "elapsed_time": "1:14:53", "remaining_time": "5:52:59", "throughput": 1494.36, "total_tokens": 6714752} {"current_steps": 31825, "total_steps": 181800, "loss": 0.1413, "lr": 4.914702716685434e-05, "epoch": 3.5011001100110013, "percentage": 17.51, "elapsed_time": "1:14:54", "remaining_time": "5:52:58", "throughput": 1494.36, "total_tokens": 6715776} {"current_steps": 31830, "total_steps": 181800, "loss": 0.0611, "lr": 4.9146405471739816e-05, "epoch": 3.5016501650165015, "percentage": 17.51, "elapsed_time": "1:14:54", "remaining_time": "5:52:57", "throughput": 1494.36, "total_tokens": 6716800} {"current_steps": 31835, "total_steps": 181800, "loss": 0.0179, "lr": 4.9145783554079447e-05, "epoch": 3.502200220022002, "percentage": 17.51, "elapsed_time": "1:14:55", "remaining_time": "5:52:56", "throughput": 1494.37, "total_tokens": 6717888} {"current_steps": 31840, "total_steps": 181800, "loss": 0.0411, "lr": 4.914516141387899e-05, "epoch": 3.502750275027503, "percentage": 17.51, "elapsed_time": "1:14:56", "remaining_time": "5:52:55", "throughput": 1494.39, "total_tokens": 6719008} {"current_steps": 31845, "total_steps": 181800, "loss": 0.0834, "lr": 4.9144539051144165e-05, "epoch": 3.5033003300330035, "percentage": 17.52, "elapsed_time": "1:14:56", "remaining_time": "5:52:55", "throughput": 1494.4, "total_tokens": 6720064} {"current_steps": 31850, "total_steps": 181800, "loss": 0.0641, "lr": 4.9143916465880704e-05, "epoch": 3.503850385038504, "percentage": 17.52, "elapsed_time": "1:14:57", "remaining_time": "5:52:54", "throughput": 1494.43, "total_tokens": 6721216} {"current_steps": 31855, "total_steps": 181800, "loss": 0.1508, "lr": 4.914329365809435e-05, "epoch": 3.5044004400440043, "percentage": 17.52, "elapsed_time": "1:14:58", "remaining_time": "5:52:53", "throughput": 1494.44, "total_tokens": 6722304} {"current_steps": 31860, "total_steps": 181800, "loss": 0.0773, "lr": 4.9142670627790847e-05, "epoch": 3.504950495049505, "percentage": 17.52, "elapsed_time": "1:14:58", "remaining_time": "5:52:52", "throughput": 1494.44, "total_tokens": 6723328} {"current_steps": 31865, "total_steps": 181800, "loss": 0.0933, "lr": 4.914204737497593e-05, "epoch": 3.5055005500550056, "percentage": 17.53, "elapsed_time": "1:14:59", "remaining_time": "5:52:52", "throughput": 1494.45, "total_tokens": 6724416} {"current_steps": 31870, "total_steps": 181800, "loss": 0.0918, "lr": 4.914142389965535e-05, "epoch": 3.506050605060506, "percentage": 17.53, "elapsed_time": "1:15:00", "remaining_time": "5:52:51", "throughput": 1494.45, "total_tokens": 6725472} {"current_steps": 31875, "total_steps": 181800, "loss": 0.0793, "lr": 4.914080020183485e-05, "epoch": 3.5066006600660065, "percentage": 17.53, "elapsed_time": "1:15:00", "remaining_time": "5:52:50", "throughput": 1494.47, "total_tokens": 6726560} {"current_steps": 31880, "total_steps": 181800, "loss": 0.1245, "lr": 4.914017628152017e-05, "epoch": 3.507150715071507, "percentage": 17.54, "elapsed_time": "1:15:01", "remaining_time": "5:52:49", "throughput": 1494.47, "total_tokens": 6727584} {"current_steps": 31885, "total_steps": 181800, "loss": 0.0818, "lr": 4.9139552138717076e-05, "epoch": 3.5077007700770078, "percentage": 17.54, "elapsed_time": "1:15:02", "remaining_time": "5:52:48", "throughput": 1494.47, "total_tokens": 6728640} {"current_steps": 31890, "total_steps": 181800, "loss": 0.0598, "lr": 4.913892777343131e-05, "epoch": 3.5082508250825084, "percentage": 17.54, "elapsed_time": "1:15:03", "remaining_time": "5:52:48", "throughput": 1494.48, "total_tokens": 6729728} {"current_steps": 31895, "total_steps": 181800, "loss": 0.0474, "lr": 4.913830318566864e-05, "epoch": 3.5088008800880086, "percentage": 17.54, "elapsed_time": "1:15:03", "remaining_time": "5:52:47", "throughput": 1494.5, "total_tokens": 6730848} {"current_steps": 31900, "total_steps": 181800, "loss": 0.0118, "lr": 4.9137678375434806e-05, "epoch": 3.5093509350935093, "percentage": 17.55, "elapsed_time": "1:15:04", "remaining_time": "5:52:46", "throughput": 1494.51, "total_tokens": 6731904} {"current_steps": 31905, "total_steps": 181800, "loss": 0.0494, "lr": 4.913705334273557e-05, "epoch": 3.50990099009901, "percentage": 17.55, "elapsed_time": "1:15:05", "remaining_time": "5:52:45", "throughput": 1494.51, "total_tokens": 6732928} {"current_steps": 31910, "total_steps": 181800, "loss": 0.0618, "lr": 4.913642808757669e-05, "epoch": 3.5104510451045106, "percentage": 17.55, "elapsed_time": "1:15:05", "remaining_time": "5:52:44", "throughput": 1494.51, "total_tokens": 6733952} {"current_steps": 31915, "total_steps": 181800, "loss": 0.1197, "lr": 4.9135802609963947e-05, "epoch": 3.511001100110011, "percentage": 17.56, "elapsed_time": "1:15:06", "remaining_time": "5:52:44", "throughput": 1494.52, "total_tokens": 6735040} {"current_steps": 31920, "total_steps": 181800, "loss": 0.0825, "lr": 4.9135176909903085e-05, "epoch": 3.5115511551155114, "percentage": 17.56, "elapsed_time": "1:15:07", "remaining_time": "5:52:43", "throughput": 1494.53, "total_tokens": 6736096} {"current_steps": 31925, "total_steps": 181800, "loss": 0.0898, "lr": 4.913455098739988e-05, "epoch": 3.512101210121012, "percentage": 17.56, "elapsed_time": "1:15:07", "remaining_time": "5:52:42", "throughput": 1494.53, "total_tokens": 6737152} {"current_steps": 31930, "total_steps": 181800, "loss": 0.0239, "lr": 4.91339248424601e-05, "epoch": 3.5126512651265127, "percentage": 17.56, "elapsed_time": "1:15:08", "remaining_time": "5:52:41", "throughput": 1494.54, "total_tokens": 6738208} {"current_steps": 31935, "total_steps": 181800, "loss": 0.0315, "lr": 4.913329847508952e-05, "epoch": 3.5132013201320134, "percentage": 17.57, "elapsed_time": "1:15:09", "remaining_time": "5:52:41", "throughput": 1494.54, "total_tokens": 6739232} {"current_steps": 31940, "total_steps": 181800, "loss": 0.0403, "lr": 4.91326718852939e-05, "epoch": 3.513751375137514, "percentage": 17.57, "elapsed_time": "1:15:09", "remaining_time": "5:52:40", "throughput": 1494.55, "total_tokens": 6740320} {"current_steps": 31945, "total_steps": 181800, "loss": 0.0124, "lr": 4.913204507307903e-05, "epoch": 3.514301430143014, "percentage": 17.57, "elapsed_time": "1:15:10", "remaining_time": "5:52:39", "throughput": 1494.54, "total_tokens": 6741312} {"current_steps": 31950, "total_steps": 181800, "loss": 0.0502, "lr": 4.913141803845067e-05, "epoch": 3.514851485148515, "percentage": 17.57, "elapsed_time": "1:15:11", "remaining_time": "5:52:38", "throughput": 1494.54, "total_tokens": 6742336} {"current_steps": 31955, "total_steps": 181800, "loss": 0.0744, "lr": 4.913079078141462e-05, "epoch": 3.5154015401540155, "percentage": 17.58, "elapsed_time": "1:15:12", "remaining_time": "5:52:37", "throughput": 1494.54, "total_tokens": 6743392} {"current_steps": 31960, "total_steps": 181800, "loss": 0.0855, "lr": 4.913016330197664e-05, "epoch": 3.5159515951595157, "percentage": 17.58, "elapsed_time": "1:15:12", "remaining_time": "5:52:37", "throughput": 1494.53, "total_tokens": 6744352} {"current_steps": 31965, "total_steps": 181800, "loss": 0.0202, "lr": 4.912953560014254e-05, "epoch": 3.5165016501650164, "percentage": 17.58, "elapsed_time": "1:15:13", "remaining_time": "5:52:36", "throughput": 1494.54, "total_tokens": 6745440} {"current_steps": 31970, "total_steps": 181800, "loss": 0.0506, "lr": 4.912890767591808e-05, "epoch": 3.517051705170517, "percentage": 17.59, "elapsed_time": "1:15:14", "remaining_time": "5:52:35", "throughput": 1494.54, "total_tokens": 6746464} {"current_steps": 31975, "total_steps": 181800, "loss": 0.0788, "lr": 4.912827952930905e-05, "epoch": 3.5176017601760177, "percentage": 17.59, "elapsed_time": "1:15:14", "remaining_time": "5:52:34", "throughput": 1494.56, "total_tokens": 6747584} {"current_steps": 31980, "total_steps": 181800, "loss": 0.0656, "lr": 4.912765116032125e-05, "epoch": 3.5181518151815183, "percentage": 17.59, "elapsed_time": "1:15:15", "remaining_time": "5:52:34", "throughput": 1494.56, "total_tokens": 6748608} {"current_steps": 31985, "total_steps": 181800, "loss": 0.0433, "lr": 4.9127022568960466e-05, "epoch": 3.5187018701870185, "percentage": 17.59, "elapsed_time": "1:15:16", "remaining_time": "5:52:33", "throughput": 1494.56, "total_tokens": 6749664} {"current_steps": 31990, "total_steps": 181800, "loss": 0.0629, "lr": 4.91263937552325e-05, "epoch": 3.519251925192519, "percentage": 17.6, "elapsed_time": "1:15:16", "remaining_time": "5:52:32", "throughput": 1494.56, "total_tokens": 6750720} {"current_steps": 31995, "total_steps": 181800, "loss": 0.0903, "lr": 4.9125764719143134e-05, "epoch": 3.51980198019802, "percentage": 17.6, "elapsed_time": "1:15:17", "remaining_time": "5:52:31", "throughput": 1494.58, "total_tokens": 6751808} {"current_steps": 32000, "total_steps": 181800, "loss": 0.0202, "lr": 4.912513546069817e-05, "epoch": 3.5203520352035205, "percentage": 17.6, "elapsed_time": "1:15:18", "remaining_time": "5:52:30", "throughput": 1494.58, "total_tokens": 6752864} {"current_steps": 32005, "total_steps": 181800, "loss": 0.0473, "lr": 4.912450597990341e-05, "epoch": 3.520902090209021, "percentage": 17.6, "elapsed_time": "1:15:18", "remaining_time": "5:52:30", "throughput": 1494.6, "total_tokens": 6753984} {"current_steps": 32010, "total_steps": 181800, "loss": 0.0746, "lr": 4.9123876276764655e-05, "epoch": 3.5214521452145213, "percentage": 17.61, "elapsed_time": "1:15:19", "remaining_time": "5:52:29", "throughput": 1494.6, "total_tokens": 6755008} {"current_steps": 32015, "total_steps": 181800, "loss": 0.0269, "lr": 4.91232463512877e-05, "epoch": 3.522002200220022, "percentage": 17.61, "elapsed_time": "1:15:20", "remaining_time": "5:52:28", "throughput": 1494.61, "total_tokens": 6756096} {"current_steps": 32020, "total_steps": 181800, "loss": 0.1869, "lr": 4.912261620347837e-05, "epoch": 3.5225522552255226, "percentage": 17.61, "elapsed_time": "1:15:20", "remaining_time": "5:52:27", "throughput": 1494.62, "total_tokens": 6757184} {"current_steps": 32025, "total_steps": 181800, "loss": 0.1414, "lr": 4.9121985833342456e-05, "epoch": 3.523102310231023, "percentage": 17.62, "elapsed_time": "1:15:21", "remaining_time": "5:52:27", "throughput": 1494.64, "total_tokens": 6758304} {"current_steps": 32030, "total_steps": 181800, "loss": 0.031, "lr": 4.912135524088577e-05, "epoch": 3.523652365236524, "percentage": 17.62, "elapsed_time": "1:15:22", "remaining_time": "5:52:26", "throughput": 1494.65, "total_tokens": 6759360} {"current_steps": 32035, "total_steps": 181800, "loss": 0.1761, "lr": 4.912072442611414e-05, "epoch": 3.524202420242024, "percentage": 17.62, "elapsed_time": "1:15:23", "remaining_time": "5:52:25", "throughput": 1494.66, "total_tokens": 6760416} {"current_steps": 32040, "total_steps": 181800, "loss": 0.0596, "lr": 4.912009338903336e-05, "epoch": 3.5247524752475248, "percentage": 17.62, "elapsed_time": "1:15:23", "remaining_time": "5:52:24", "throughput": 1494.66, "total_tokens": 6761472} {"current_steps": 32045, "total_steps": 181800, "loss": 0.0894, "lr": 4.9119462129649254e-05, "epoch": 3.5253025302530254, "percentage": 17.63, "elapsed_time": "1:15:24", "remaining_time": "5:52:23", "throughput": 1494.65, "total_tokens": 6762432} {"current_steps": 32050, "total_steps": 181800, "loss": 0.0792, "lr": 4.911883064796763e-05, "epoch": 3.5258525852585256, "percentage": 17.63, "elapsed_time": "1:15:25", "remaining_time": "5:52:23", "throughput": 1494.64, "total_tokens": 6763456} {"current_steps": 32055, "total_steps": 181800, "loss": 0.0713, "lr": 4.911819894399433e-05, "epoch": 3.5264026402640263, "percentage": 17.63, "elapsed_time": "1:15:25", "remaining_time": "5:52:22", "throughput": 1494.65, "total_tokens": 6764512} {"current_steps": 32060, "total_steps": 181800, "loss": 0.0189, "lr": 4.911756701773516e-05, "epoch": 3.526952695269527, "percentage": 17.63, "elapsed_time": "1:15:26", "remaining_time": "5:52:21", "throughput": 1494.66, "total_tokens": 6765568} {"current_steps": 32065, "total_steps": 181800, "loss": 0.0834, "lr": 4.911693486919594e-05, "epoch": 3.5275027502750276, "percentage": 17.64, "elapsed_time": "1:15:27", "remaining_time": "5:52:20", "throughput": 1494.67, "total_tokens": 6766656} {"current_steps": 32070, "total_steps": 181800, "loss": 0.0442, "lr": 4.911630249838252e-05, "epoch": 3.5280528052805282, "percentage": 17.64, "elapsed_time": "1:15:27", "remaining_time": "5:52:19", "throughput": 1494.68, "total_tokens": 6767712} {"current_steps": 32075, "total_steps": 181800, "loss": 0.0213, "lr": 4.91156699053007e-05, "epoch": 3.5286028602860284, "percentage": 17.64, "elapsed_time": "1:15:28", "remaining_time": "5:52:19", "throughput": 1494.68, "total_tokens": 6768768} {"current_steps": 32080, "total_steps": 181800, "loss": 0.0333, "lr": 4.9115037089956316e-05, "epoch": 3.529152915291529, "percentage": 17.65, "elapsed_time": "1:15:29", "remaining_time": "5:52:18", "throughput": 1494.67, "total_tokens": 6769760} {"current_steps": 32085, "total_steps": 181800, "loss": 0.0563, "lr": 4.9114404052355225e-05, "epoch": 3.5297029702970297, "percentage": 17.65, "elapsed_time": "1:15:29", "remaining_time": "5:52:17", "throughput": 1494.67, "total_tokens": 6770784} {"current_steps": 32090, "total_steps": 181800, "loss": 0.0123, "lr": 4.9113770792503225e-05, "epoch": 3.5302530253025304, "percentage": 17.65, "elapsed_time": "1:15:30", "remaining_time": "5:52:16", "throughput": 1494.69, "total_tokens": 6771904} {"current_steps": 32095, "total_steps": 181800, "loss": 0.0875, "lr": 4.911313731040618e-05, "epoch": 3.530803080308031, "percentage": 17.65, "elapsed_time": "1:15:31", "remaining_time": "5:52:16", "throughput": 1494.69, "total_tokens": 6772928} {"current_steps": 32100, "total_steps": 181800, "loss": 0.1053, "lr": 4.911250360606992e-05, "epoch": 3.5313531353135312, "percentage": 17.66, "elapsed_time": "1:15:32", "remaining_time": "5:52:15", "throughput": 1494.7, "total_tokens": 6774016} {"current_steps": 32105, "total_steps": 181800, "loss": 0.211, "lr": 4.9111869679500274e-05, "epoch": 3.531903190319032, "percentage": 17.66, "elapsed_time": "1:15:32", "remaining_time": "5:52:14", "throughput": 1494.69, "total_tokens": 6775040} {"current_steps": 32110, "total_steps": 181800, "loss": 0.0336, "lr": 4.911123553070311e-05, "epoch": 3.5324532453245325, "percentage": 17.66, "elapsed_time": "1:15:33", "remaining_time": "5:52:13", "throughput": 1494.7, "total_tokens": 6776096} {"current_steps": 32115, "total_steps": 181800, "loss": 0.0128, "lr": 4.911060115968425e-05, "epoch": 3.5330033003300327, "percentage": 17.67, "elapsed_time": "1:15:34", "remaining_time": "5:52:13", "throughput": 1494.7, "total_tokens": 6777120} {"current_steps": 32120, "total_steps": 181800, "loss": 0.03, "lr": 4.910996656644955e-05, "epoch": 3.533553355335534, "percentage": 17.67, "elapsed_time": "1:15:34", "remaining_time": "5:52:12", "throughput": 1494.7, "total_tokens": 6778176} {"current_steps": 32125, "total_steps": 181800, "loss": 0.0724, "lr": 4.9109331751004855e-05, "epoch": 3.534103410341034, "percentage": 17.67, "elapsed_time": "1:15:35", "remaining_time": "5:52:11", "throughput": 1494.69, "total_tokens": 6779168} {"current_steps": 32130, "total_steps": 181800, "loss": 0.0807, "lr": 4.910869671335602e-05, "epoch": 3.5346534653465347, "percentage": 17.67, "elapsed_time": "1:15:36", "remaining_time": "5:52:10", "throughput": 1494.71, "total_tokens": 6780256} {"current_steps": 32135, "total_steps": 181800, "loss": 0.0169, "lr": 4.91080614535089e-05, "epoch": 3.5352035203520353, "percentage": 17.68, "elapsed_time": "1:15:36", "remaining_time": "5:52:09", "throughput": 1494.72, "total_tokens": 6781344} {"current_steps": 32140, "total_steps": 181800, "loss": 0.1022, "lr": 4.9107425971469336e-05, "epoch": 3.5357535753575355, "percentage": 17.68, "elapsed_time": "1:15:37", "remaining_time": "5:52:09", "throughput": 1494.73, "total_tokens": 6782432} {"current_steps": 32145, "total_steps": 181800, "loss": 0.0856, "lr": 4.91067902672432e-05, "epoch": 3.536303630363036, "percentage": 17.68, "elapsed_time": "1:15:38", "remaining_time": "5:52:08", "throughput": 1494.73, "total_tokens": 6783456} {"current_steps": 32150, "total_steps": 181800, "loss": 0.1126, "lr": 4.910615434083635e-05, "epoch": 3.536853685368537, "percentage": 17.68, "elapsed_time": "1:15:38", "remaining_time": "5:52:07", "throughput": 1494.73, "total_tokens": 6784480} {"current_steps": 32155, "total_steps": 181800, "loss": 0.0719, "lr": 4.9105518192254634e-05, "epoch": 3.5374037403740375, "percentage": 17.69, "elapsed_time": "1:15:39", "remaining_time": "5:52:06", "throughput": 1494.75, "total_tokens": 6785600} {"current_steps": 32160, "total_steps": 181800, "loss": 0.043, "lr": 4.910488182150393e-05, "epoch": 3.537953795379538, "percentage": 17.69, "elapsed_time": "1:15:40", "remaining_time": "5:52:05", "throughput": 1494.78, "total_tokens": 6786784} {"current_steps": 32165, "total_steps": 181800, "loss": 0.0507, "lr": 4.9104245228590096e-05, "epoch": 3.5385038503850383, "percentage": 17.69, "elapsed_time": "1:15:40", "remaining_time": "5:52:05", "throughput": 1494.8, "total_tokens": 6787904} {"current_steps": 32170, "total_steps": 181800, "loss": 0.1006, "lr": 4.9103608413518995e-05, "epoch": 3.539053905390539, "percentage": 17.7, "elapsed_time": "1:15:41", "remaining_time": "5:52:04", "throughput": 1494.8, "total_tokens": 6788928} {"current_steps": 32175, "total_steps": 181800, "loss": 0.1207, "lr": 4.910297137629651e-05, "epoch": 3.5396039603960396, "percentage": 17.7, "elapsed_time": "1:15:42", "remaining_time": "5:52:03", "throughput": 1494.8, "total_tokens": 6789952} {"current_steps": 32180, "total_steps": 181800, "loss": 0.034, "lr": 4.910233411692849e-05, "epoch": 3.5401540154015403, "percentage": 17.7, "elapsed_time": "1:15:43", "remaining_time": "5:52:02", "throughput": 1494.81, "total_tokens": 6791040} {"current_steps": 32185, "total_steps": 181800, "loss": 0.0271, "lr": 4.9101696635420834e-05, "epoch": 3.540704070407041, "percentage": 17.7, "elapsed_time": "1:15:43", "remaining_time": "5:52:02", "throughput": 1494.82, "total_tokens": 6792128} {"current_steps": 32190, "total_steps": 181800, "loss": 0.1947, "lr": 4.910105893177941e-05, "epoch": 3.541254125412541, "percentage": 17.71, "elapsed_time": "1:15:44", "remaining_time": "5:52:01", "throughput": 1494.82, "total_tokens": 6793152} {"current_steps": 32195, "total_steps": 181800, "loss": 0.073, "lr": 4.910042100601008e-05, "epoch": 3.541804180418042, "percentage": 17.71, "elapsed_time": "1:15:45", "remaining_time": "5:52:00", "throughput": 1494.84, "total_tokens": 6794272} {"current_steps": 32200, "total_steps": 181800, "loss": 0.0811, "lr": 4.9099782858118736e-05, "epoch": 3.5423542354235424, "percentage": 17.71, "elapsed_time": "1:15:45", "remaining_time": "5:51:59", "throughput": 1494.86, "total_tokens": 6795392} {"current_steps": 32205, "total_steps": 181800, "loss": 0.0884, "lr": 4.909914448811126e-05, "epoch": 3.5429042904290426, "percentage": 17.71, "elapsed_time": "1:15:46", "remaining_time": "5:51:58", "throughput": 1494.87, "total_tokens": 6796448} {"current_steps": 32210, "total_steps": 181800, "loss": 0.0507, "lr": 4.909850589599353e-05, "epoch": 3.5434543454345433, "percentage": 17.72, "elapsed_time": "1:15:47", "remaining_time": "5:51:58", "throughput": 1494.86, "total_tokens": 6797440} {"current_steps": 32215, "total_steps": 181800, "loss": 0.0418, "lr": 4.9097867081771435e-05, "epoch": 3.544004400440044, "percentage": 17.72, "elapsed_time": "1:15:47", "remaining_time": "5:51:57", "throughput": 1494.86, "total_tokens": 6798464} {"current_steps": 32220, "total_steps": 181800, "loss": 0.0631, "lr": 4.9097228045450864e-05, "epoch": 3.5445544554455446, "percentage": 17.72, "elapsed_time": "1:15:48", "remaining_time": "5:51:56", "throughput": 1494.87, "total_tokens": 6799520} {"current_steps": 32225, "total_steps": 181800, "loss": 0.0635, "lr": 4.9096588787037706e-05, "epoch": 3.5451045104510452, "percentage": 17.73, "elapsed_time": "1:15:49", "remaining_time": "5:51:55", "throughput": 1494.88, "total_tokens": 6800608} {"current_steps": 32230, "total_steps": 181800, "loss": 0.0366, "lr": 4.909594930653785e-05, "epoch": 3.5456545654565454, "percentage": 17.73, "elapsed_time": "1:15:49", "remaining_time": "5:51:55", "throughput": 1494.89, "total_tokens": 6801664} {"current_steps": 32235, "total_steps": 181800, "loss": 0.0156, "lr": 4.9095309603957194e-05, "epoch": 3.546204620462046, "percentage": 17.73, "elapsed_time": "1:15:50", "remaining_time": "5:51:54", "throughput": 1494.88, "total_tokens": 6802688} {"current_steps": 32240, "total_steps": 181800, "loss": 0.0542, "lr": 4.909466967930163e-05, "epoch": 3.5467546754675467, "percentage": 17.73, "elapsed_time": "1:15:51", "remaining_time": "5:51:53", "throughput": 1494.89, "total_tokens": 6803744} {"current_steps": 32245, "total_steps": 181800, "loss": 0.0783, "lr": 4.9094029532577055e-05, "epoch": 3.5473047304730474, "percentage": 17.74, "elapsed_time": "1:15:52", "remaining_time": "5:51:52", "throughput": 1494.91, "total_tokens": 6804864} {"current_steps": 32250, "total_steps": 181800, "loss": 0.0618, "lr": 4.909338916378937e-05, "epoch": 3.547854785478548, "percentage": 17.74, "elapsed_time": "1:15:52", "remaining_time": "5:51:51", "throughput": 1494.91, "total_tokens": 6805888} {"current_steps": 32255, "total_steps": 181800, "loss": 0.0811, "lr": 4.9092748572944486e-05, "epoch": 3.5484048404840483, "percentage": 17.74, "elapsed_time": "1:15:53", "remaining_time": "5:51:51", "throughput": 1494.93, "total_tokens": 6807008} {"current_steps": 32260, "total_steps": 181800, "loss": 0.0536, "lr": 4.90921077600483e-05, "epoch": 3.548954895489549, "percentage": 17.74, "elapsed_time": "1:15:54", "remaining_time": "5:51:50", "throughput": 1494.93, "total_tokens": 6808032} {"current_steps": 32265, "total_steps": 181800, "loss": 0.0567, "lr": 4.9091466725106704e-05, "epoch": 3.5495049504950495, "percentage": 17.75, "elapsed_time": "1:15:54", "remaining_time": "5:51:49", "throughput": 1494.94, "total_tokens": 6809120} {"current_steps": 32270, "total_steps": 181800, "loss": 0.0525, "lr": 4.909082546812563e-05, "epoch": 3.55005500550055, "percentage": 17.75, "elapsed_time": "1:15:55", "remaining_time": "5:51:48", "throughput": 1494.95, "total_tokens": 6810208} {"current_steps": 32275, "total_steps": 181800, "loss": 0.0445, "lr": 4.9090183989110974e-05, "epoch": 3.550605060506051, "percentage": 17.75, "elapsed_time": "1:15:56", "remaining_time": "5:51:47", "throughput": 1494.96, "total_tokens": 6811264} {"current_steps": 32280, "total_steps": 181800, "loss": 0.1337, "lr": 4.9089542288068654e-05, "epoch": 3.551155115511551, "percentage": 17.76, "elapsed_time": "1:15:56", "remaining_time": "5:51:47", "throughput": 1494.97, "total_tokens": 6812320} {"current_steps": 32285, "total_steps": 181800, "loss": 0.0393, "lr": 4.908890036500457e-05, "epoch": 3.5517051705170517, "percentage": 17.76, "elapsed_time": "1:15:57", "remaining_time": "5:51:46", "throughput": 1494.97, "total_tokens": 6813344} {"current_steps": 32290, "total_steps": 181800, "loss": 0.044, "lr": 4.908825821992467e-05, "epoch": 3.5522552255225524, "percentage": 17.76, "elapsed_time": "1:15:58", "remaining_time": "5:51:45", "throughput": 1494.96, "total_tokens": 6814368} {"current_steps": 32295, "total_steps": 181800, "loss": 0.0202, "lr": 4.908761585283485e-05, "epoch": 3.5528052805280526, "percentage": 17.76, "elapsed_time": "1:15:58", "remaining_time": "5:51:44", "throughput": 1494.97, "total_tokens": 6815424} {"current_steps": 32300, "total_steps": 181800, "loss": 0.1629, "lr": 4.908697326374102e-05, "epoch": 3.553355335533553, "percentage": 17.77, "elapsed_time": "1:15:59", "remaining_time": "5:51:43", "throughput": 1494.98, "total_tokens": 6816512} {"current_steps": 32305, "total_steps": 181800, "loss": 0.102, "lr": 4.908633045264912e-05, "epoch": 3.553905390539054, "percentage": 17.77, "elapsed_time": "1:16:00", "remaining_time": "5:51:43", "throughput": 1495.0, "total_tokens": 6817632} {"current_steps": 32310, "total_steps": 181800, "loss": 0.0273, "lr": 4.908568741956507e-05, "epoch": 3.5544554455445545, "percentage": 17.77, "elapsed_time": "1:16:00", "remaining_time": "5:51:42", "throughput": 1495.01, "total_tokens": 6818688} {"current_steps": 32315, "total_steps": 181800, "loss": 0.2097, "lr": 4.9085044164494803e-05, "epoch": 3.555005500550055, "percentage": 17.78, "elapsed_time": "1:16:01", "remaining_time": "5:51:41", "throughput": 1495.02, "total_tokens": 6819744} {"current_steps": 32320, "total_steps": 181800, "loss": 0.0635, "lr": 4.9084400687444236e-05, "epoch": 3.5555555555555554, "percentage": 17.78, "elapsed_time": "1:16:02", "remaining_time": "5:51:40", "throughput": 1495.01, "total_tokens": 6820768} {"current_steps": 32325, "total_steps": 181800, "loss": 0.2017, "lr": 4.9083756988419306e-05, "epoch": 3.556105610561056, "percentage": 17.78, "elapsed_time": "1:16:03", "remaining_time": "5:51:40", "throughput": 1494.96, "total_tokens": 6821824} {"current_steps": 32330, "total_steps": 181800, "loss": 0.0525, "lr": 4.9083113067425944e-05, "epoch": 3.5566556655665567, "percentage": 17.78, "elapsed_time": "1:16:03", "remaining_time": "5:51:40", "throughput": 1494.98, "total_tokens": 6822976} {"current_steps": 32335, "total_steps": 181800, "loss": 0.0714, "lr": 4.9082468924470084e-05, "epoch": 3.5572057205720573, "percentage": 17.79, "elapsed_time": "1:16:04", "remaining_time": "5:51:39", "throughput": 1495.0, "total_tokens": 6824064} {"current_steps": 32340, "total_steps": 181800, "loss": 0.0686, "lr": 4.908182455955766e-05, "epoch": 3.557755775577558, "percentage": 17.79, "elapsed_time": "1:16:05", "remaining_time": "5:51:38", "throughput": 1494.99, "total_tokens": 6825056} {"current_steps": 32345, "total_steps": 181800, "loss": 0.0938, "lr": 4.9081179972694625e-05, "epoch": 3.558305830583058, "percentage": 17.79, "elapsed_time": "1:16:05", "remaining_time": "5:51:37", "throughput": 1495.0, "total_tokens": 6826112} {"current_steps": 32350, "total_steps": 181800, "loss": 0.1329, "lr": 4.9080535163886904e-05, "epoch": 3.558855885588559, "percentage": 17.79, "elapsed_time": "1:16:06", "remaining_time": "5:51:36", "throughput": 1494.99, "total_tokens": 6827104} {"current_steps": 32355, "total_steps": 181800, "loss": 0.3146, "lr": 4.907989013314045e-05, "epoch": 3.5594059405940595, "percentage": 17.8, "elapsed_time": "1:16:07", "remaining_time": "5:51:36", "throughput": 1495.0, "total_tokens": 6828192} {"current_steps": 32360, "total_steps": 181800, "loss": 0.0237, "lr": 4.9079244880461194e-05, "epoch": 3.55995599559956, "percentage": 17.8, "elapsed_time": "1:16:08", "remaining_time": "5:51:35", "throughput": 1494.99, "total_tokens": 6829184} {"current_steps": 32365, "total_steps": 181800, "loss": 0.0332, "lr": 4.90785994058551e-05, "epoch": 3.5605060506050608, "percentage": 17.8, "elapsed_time": "1:16:08", "remaining_time": "5:51:34", "throughput": 1495.01, "total_tokens": 6830272} {"current_steps": 32370, "total_steps": 181800, "loss": 0.0711, "lr": 4.907795370932811e-05, "epoch": 3.561056105610561, "percentage": 17.81, "elapsed_time": "1:16:09", "remaining_time": "5:51:33", "throughput": 1495.01, "total_tokens": 6831296} {"current_steps": 32375, "total_steps": 181800, "loss": 0.0809, "lr": 4.907730779088616e-05, "epoch": 3.5616061606160616, "percentage": 17.81, "elapsed_time": "1:16:10", "remaining_time": "5:51:33", "throughput": 1495.01, "total_tokens": 6832352} {"current_steps": 32380, "total_steps": 181800, "loss": 0.0507, "lr": 4.9076661650535226e-05, "epoch": 3.5621562156215623, "percentage": 17.81, "elapsed_time": "1:16:10", "remaining_time": "5:51:32", "throughput": 1495.03, "total_tokens": 6833440} {"current_steps": 32385, "total_steps": 181800, "loss": 0.0486, "lr": 4.9076015288281264e-05, "epoch": 3.5627062706270625, "percentage": 17.81, "elapsed_time": "1:16:11", "remaining_time": "5:51:31", "throughput": 1495.05, "total_tokens": 6834592} {"current_steps": 32390, "total_steps": 181800, "loss": 0.0986, "lr": 4.907536870413021e-05, "epoch": 3.563256325632563, "percentage": 17.82, "elapsed_time": "1:16:12", "remaining_time": "5:51:30", "throughput": 1495.06, "total_tokens": 6835648} {"current_steps": 32395, "total_steps": 181800, "loss": 0.1383, "lr": 4.907472189808804e-05, "epoch": 3.5638063806380638, "percentage": 17.82, "elapsed_time": "1:16:12", "remaining_time": "5:51:29", "throughput": 1495.06, "total_tokens": 6836672} {"current_steps": 32400, "total_steps": 181800, "loss": 0.0666, "lr": 4.9074074870160715e-05, "epoch": 3.5643564356435644, "percentage": 17.82, "elapsed_time": "1:16:13", "remaining_time": "5:51:29", "throughput": 1495.06, "total_tokens": 6837696} {"current_steps": 32405, "total_steps": 181800, "loss": 0.111, "lr": 4.907342762035418e-05, "epoch": 3.564906490649065, "percentage": 17.82, "elapsed_time": "1:16:14", "remaining_time": "5:51:28", "throughput": 1495.06, "total_tokens": 6838752} {"current_steps": 32410, "total_steps": 181800, "loss": 0.0546, "lr": 4.907278014867442e-05, "epoch": 3.5654565456545653, "percentage": 17.83, "elapsed_time": "1:16:14", "remaining_time": "5:51:27", "throughput": 1495.08, "total_tokens": 6839840} {"current_steps": 32415, "total_steps": 181800, "loss": 0.0479, "lr": 4.9072132455127406e-05, "epoch": 3.566006600660066, "percentage": 17.83, "elapsed_time": "1:16:15", "remaining_time": "5:51:26", "throughput": 1495.07, "total_tokens": 6840832} {"current_steps": 32420, "total_steps": 181800, "loss": 0.0982, "lr": 4.907148453971909e-05, "epoch": 3.5665566556655666, "percentage": 17.83, "elapsed_time": "1:16:16", "remaining_time": "5:51:25", "throughput": 1495.07, "total_tokens": 6841888} {"current_steps": 32425, "total_steps": 181800, "loss": 0.1023, "lr": 4.9070836402455456e-05, "epoch": 3.567106710671067, "percentage": 17.84, "elapsed_time": "1:16:16", "remaining_time": "5:51:25", "throughput": 1495.08, "total_tokens": 6842944} {"current_steps": 32430, "total_steps": 181800, "loss": 0.0215, "lr": 4.907018804334247e-05, "epoch": 3.567656765676568, "percentage": 17.84, "elapsed_time": "1:16:17", "remaining_time": "5:51:24", "throughput": 1495.09, "total_tokens": 6844032} {"current_steps": 32435, "total_steps": 181800, "loss": 0.0294, "lr": 4.906953946238611e-05, "epoch": 3.568206820682068, "percentage": 17.84, "elapsed_time": "1:16:18", "remaining_time": "5:51:23", "throughput": 1495.1, "total_tokens": 6845120} {"current_steps": 32440, "total_steps": 181800, "loss": 0.028, "lr": 4.906889065959236e-05, "epoch": 3.5687568756875687, "percentage": 17.84, "elapsed_time": "1:16:19", "remaining_time": "5:51:22", "throughput": 1495.1, "total_tokens": 6846144} {"current_steps": 32445, "total_steps": 181800, "loss": 0.025, "lr": 4.906824163496719e-05, "epoch": 3.5693069306930694, "percentage": 17.85, "elapsed_time": "1:16:19", "remaining_time": "5:51:22", "throughput": 1495.12, "total_tokens": 6847232} {"current_steps": 32450, "total_steps": 181800, "loss": 0.117, "lr": 4.906759238851658e-05, "epoch": 3.56985698569857, "percentage": 17.85, "elapsed_time": "1:16:20", "remaining_time": "5:51:21", "throughput": 1495.12, "total_tokens": 6848288} {"current_steps": 32455, "total_steps": 181800, "loss": 0.0795, "lr": 4.906694292024653e-05, "epoch": 3.5704070407040707, "percentage": 17.85, "elapsed_time": "1:16:21", "remaining_time": "5:51:20", "throughput": 1495.11, "total_tokens": 6849280} {"current_steps": 32460, "total_steps": 181800, "loss": 0.1262, "lr": 4.9066293230163005e-05, "epoch": 3.570957095709571, "percentage": 17.85, "elapsed_time": "1:16:21", "remaining_time": "5:51:19", "throughput": 1495.1, "total_tokens": 6850240} {"current_steps": 32465, "total_steps": 181800, "loss": 0.0216, "lr": 4.906564331827202e-05, "epoch": 3.5715071507150715, "percentage": 17.86, "elapsed_time": "1:16:22", "remaining_time": "5:51:18", "throughput": 1495.09, "total_tokens": 6851232} {"current_steps": 32470, "total_steps": 181800, "loss": 0.0819, "lr": 4.906499318457953e-05, "epoch": 3.572057205720572, "percentage": 17.86, "elapsed_time": "1:16:23", "remaining_time": "5:51:18", "throughput": 1495.1, "total_tokens": 6852288} {"current_steps": 32475, "total_steps": 181800, "loss": 0.1921, "lr": 4.906434282909156e-05, "epoch": 3.5726072607260724, "percentage": 17.86, "elapsed_time": "1:16:23", "remaining_time": "5:51:17", "throughput": 1495.11, "total_tokens": 6853344} {"current_steps": 32480, "total_steps": 181800, "loss": 0.0256, "lr": 4.906369225181407e-05, "epoch": 3.573157315731573, "percentage": 17.87, "elapsed_time": "1:16:24", "remaining_time": "5:51:16", "throughput": 1495.11, "total_tokens": 6854400} {"current_steps": 32485, "total_steps": 181800, "loss": 0.0806, "lr": 4.9063041452753096e-05, "epoch": 3.5737073707370737, "percentage": 17.87, "elapsed_time": "1:16:25", "remaining_time": "5:51:15", "throughput": 1495.1, "total_tokens": 6855392} {"current_steps": 32490, "total_steps": 181800, "loss": 0.0502, "lr": 4.906239043191461e-05, "epoch": 3.5742574257425743, "percentage": 17.87, "elapsed_time": "1:16:25", "remaining_time": "5:51:14", "throughput": 1495.1, "total_tokens": 6856416} {"current_steps": 32495, "total_steps": 181800, "loss": 0.028, "lr": 4.906173918930461e-05, "epoch": 3.574807480748075, "percentage": 17.87, "elapsed_time": "1:16:26", "remaining_time": "5:51:14", "throughput": 1495.12, "total_tokens": 6857504} {"current_steps": 32500, "total_steps": 181800, "loss": 0.0943, "lr": 4.906108772492911e-05, "epoch": 3.575357535753575, "percentage": 17.88, "elapsed_time": "1:16:27", "remaining_time": "5:51:13", "throughput": 1495.11, "total_tokens": 6858496} {"current_steps": 32505, "total_steps": 181800, "loss": 0.0473, "lr": 4.906043603879411e-05, "epoch": 3.575907590759076, "percentage": 17.88, "elapsed_time": "1:16:27", "remaining_time": "5:51:12", "throughput": 1495.11, "total_tokens": 6859552} {"current_steps": 32510, "total_steps": 181800, "loss": 0.0536, "lr": 4.905978413090562e-05, "epoch": 3.5764576457645765, "percentage": 17.88, "elapsed_time": "1:16:28", "remaining_time": "5:51:11", "throughput": 1495.12, "total_tokens": 6860608} {"current_steps": 32515, "total_steps": 181800, "loss": 0.0511, "lr": 4.905913200126964e-05, "epoch": 3.577007700770077, "percentage": 17.89, "elapsed_time": "1:16:29", "remaining_time": "5:51:10", "throughput": 1495.12, "total_tokens": 6861632} {"current_steps": 32520, "total_steps": 181800, "loss": 0.0967, "lr": 4.905847964989219e-05, "epoch": 3.5775577557755778, "percentage": 17.89, "elapsed_time": "1:16:30", "remaining_time": "5:51:10", "throughput": 1495.13, "total_tokens": 6862720} {"current_steps": 32525, "total_steps": 181800, "loss": 0.055, "lr": 4.905782707677927e-05, "epoch": 3.578107810781078, "percentage": 17.89, "elapsed_time": "1:16:30", "remaining_time": "5:51:09", "throughput": 1495.14, "total_tokens": 6863808} {"current_steps": 32530, "total_steps": 181800, "loss": 0.1056, "lr": 4.905717428193691e-05, "epoch": 3.5786578657865786, "percentage": 17.89, "elapsed_time": "1:16:31", "remaining_time": "5:51:08", "throughput": 1495.15, "total_tokens": 6864864} {"current_steps": 32535, "total_steps": 181800, "loss": 0.0641, "lr": 4.905652126537111e-05, "epoch": 3.5792079207920793, "percentage": 17.9, "elapsed_time": "1:16:32", "remaining_time": "5:51:07", "throughput": 1495.15, "total_tokens": 6865920} {"current_steps": 32540, "total_steps": 181800, "loss": 0.0283, "lr": 4.90558680270879e-05, "epoch": 3.5797579757975795, "percentage": 17.9, "elapsed_time": "1:16:32", "remaining_time": "5:51:07", "throughput": 1495.15, "total_tokens": 6866944} {"current_steps": 32545, "total_steps": 181800, "loss": 0.0978, "lr": 4.905521456709331e-05, "epoch": 3.5803080308030806, "percentage": 17.9, "elapsed_time": "1:16:33", "remaining_time": "5:51:06", "throughput": 1495.15, "total_tokens": 6867968} {"current_steps": 32550, "total_steps": 181800, "loss": 0.0359, "lr": 4.9054560885393335e-05, "epoch": 3.580858085808581, "percentage": 17.9, "elapsed_time": "1:16:34", "remaining_time": "5:51:05", "throughput": 1495.16, "total_tokens": 6869024} {"current_steps": 32555, "total_steps": 181800, "loss": 0.0977, "lr": 4.9053906981994025e-05, "epoch": 3.5814081408140814, "percentage": 17.91, "elapsed_time": "1:16:34", "remaining_time": "5:51:04", "throughput": 1495.17, "total_tokens": 6870112} {"current_steps": 32560, "total_steps": 181800, "loss": 0.0157, "lr": 4.905325285690139e-05, "epoch": 3.581958195819582, "percentage": 17.91, "elapsed_time": "1:16:35", "remaining_time": "5:51:03", "throughput": 1495.18, "total_tokens": 6871200} {"current_steps": 32565, "total_steps": 181800, "loss": 0.0881, "lr": 4.905259851012146e-05, "epoch": 3.5825082508250823, "percentage": 17.91, "elapsed_time": "1:16:36", "remaining_time": "5:51:03", "throughput": 1495.19, "total_tokens": 6872288} {"current_steps": 32570, "total_steps": 181800, "loss": 0.0739, "lr": 4.9051943941660285e-05, "epoch": 3.583058305830583, "percentage": 17.92, "elapsed_time": "1:16:36", "remaining_time": "5:51:02", "throughput": 1495.19, "total_tokens": 6873312} {"current_steps": 32575, "total_steps": 181800, "loss": 0.0869, "lr": 4.905128915152387e-05, "epoch": 3.5836083608360836, "percentage": 17.92, "elapsed_time": "1:16:37", "remaining_time": "5:51:01", "throughput": 1495.21, "total_tokens": 6874432} {"current_steps": 32580, "total_steps": 181800, "loss": 0.0181, "lr": 4.905063413971827e-05, "epoch": 3.5841584158415842, "percentage": 17.92, "elapsed_time": "1:16:38", "remaining_time": "5:51:00", "throughput": 1495.22, "total_tokens": 6875488} {"current_steps": 32585, "total_steps": 181800, "loss": 0.0323, "lr": 4.9049978906249515e-05, "epoch": 3.584708470847085, "percentage": 17.92, "elapsed_time": "1:16:38", "remaining_time": "5:50:59", "throughput": 1495.22, "total_tokens": 6876512} {"current_steps": 32590, "total_steps": 181800, "loss": 0.0395, "lr": 4.904932345112364e-05, "epoch": 3.585258525852585, "percentage": 17.93, "elapsed_time": "1:16:39", "remaining_time": "5:50:59", "throughput": 1495.22, "total_tokens": 6877568} {"current_steps": 32595, "total_steps": 181800, "loss": 0.0568, "lr": 4.90486677743467e-05, "epoch": 3.5858085808580857, "percentage": 17.93, "elapsed_time": "1:16:40", "remaining_time": "5:50:58", "throughput": 1495.24, "total_tokens": 6878656} {"current_steps": 32600, "total_steps": 181800, "loss": 0.0513, "lr": 4.9048011875924725e-05, "epoch": 3.5863586358635864, "percentage": 17.93, "elapsed_time": "1:16:41", "remaining_time": "5:50:57", "throughput": 1495.26, "total_tokens": 6879808} {"current_steps": 32605, "total_steps": 181800, "loss": 0.1247, "lr": 4.9047355755863766e-05, "epoch": 3.586908690869087, "percentage": 17.93, "elapsed_time": "1:16:41", "remaining_time": "5:50:56", "throughput": 1495.26, "total_tokens": 6880832} {"current_steps": 32610, "total_steps": 181800, "loss": 0.046, "lr": 4.904669941416987e-05, "epoch": 3.5874587458745877, "percentage": 17.94, "elapsed_time": "1:16:42", "remaining_time": "5:50:56", "throughput": 1495.26, "total_tokens": 6881856} {"current_steps": 32615, "total_steps": 181800, "loss": 0.0814, "lr": 4.9046042850849074e-05, "epoch": 3.588008800880088, "percentage": 17.94, "elapsed_time": "1:16:43", "remaining_time": "5:50:55", "throughput": 1495.26, "total_tokens": 6882912} {"current_steps": 32620, "total_steps": 181800, "loss": 0.0152, "lr": 4.904538606590745e-05, "epoch": 3.5885588558855885, "percentage": 17.94, "elapsed_time": "1:16:43", "remaining_time": "5:50:54", "throughput": 1495.28, "total_tokens": 6884000} {"current_steps": 32625, "total_steps": 181800, "loss": 0.0368, "lr": 4.904472905935104e-05, "epoch": 3.589108910891089, "percentage": 17.95, "elapsed_time": "1:16:44", "remaining_time": "5:50:53", "throughput": 1495.28, "total_tokens": 6885056} {"current_steps": 32630, "total_steps": 181800, "loss": 0.0357, "lr": 4.904407183118589e-05, "epoch": 3.5896589658965894, "percentage": 17.95, "elapsed_time": "1:16:45", "remaining_time": "5:50:52", "throughput": 1495.29, "total_tokens": 6886112} {"current_steps": 32635, "total_steps": 181800, "loss": 0.0611, "lr": 4.904341438141807e-05, "epoch": 3.5902090209020905, "percentage": 17.95, "elapsed_time": "1:16:45", "remaining_time": "5:50:52", "throughput": 1495.29, "total_tokens": 6887136} {"current_steps": 32640, "total_steps": 181800, "loss": 0.0893, "lr": 4.904275671005364e-05, "epoch": 3.5907590759075907, "percentage": 17.95, "elapsed_time": "1:16:46", "remaining_time": "5:50:51", "throughput": 1495.29, "total_tokens": 6888160} {"current_steps": 32645, "total_steps": 181800, "loss": 0.0421, "lr": 4.904209881709866e-05, "epoch": 3.5913091309130913, "percentage": 17.96, "elapsed_time": "1:16:47", "remaining_time": "5:50:50", "throughput": 1495.3, "total_tokens": 6889248} {"current_steps": 32650, "total_steps": 181800, "loss": 0.0354, "lr": 4.90414407025592e-05, "epoch": 3.591859185918592, "percentage": 17.96, "elapsed_time": "1:16:47", "remaining_time": "5:50:49", "throughput": 1495.3, "total_tokens": 6890272} {"current_steps": 32655, "total_steps": 181800, "loss": 0.0854, "lr": 4.9040782366441304e-05, "epoch": 3.592409240924092, "percentage": 17.96, "elapsed_time": "1:16:48", "remaining_time": "5:50:49", "throughput": 1495.32, "total_tokens": 6891392} {"current_steps": 32660, "total_steps": 181800, "loss": 0.0066, "lr": 4.904012380875106e-05, "epoch": 3.592959295929593, "percentage": 17.96, "elapsed_time": "1:16:49", "remaining_time": "5:50:48", "throughput": 1495.31, "total_tokens": 6892384} {"current_steps": 32665, "total_steps": 181800, "loss": 0.0382, "lr": 4.903946502949452e-05, "epoch": 3.5935093509350935, "percentage": 17.97, "elapsed_time": "1:16:50", "remaining_time": "5:50:47", "throughput": 1495.32, "total_tokens": 6893472} {"current_steps": 32670, "total_steps": 181800, "loss": 0.0264, "lr": 4.9038806028677776e-05, "epoch": 3.594059405940594, "percentage": 17.97, "elapsed_time": "1:16:50", "remaining_time": "5:50:46", "throughput": 1495.32, "total_tokens": 6894496} {"current_steps": 32675, "total_steps": 181800, "loss": 0.0385, "lr": 4.9038146806306885e-05, "epoch": 3.594609460946095, "percentage": 17.97, "elapsed_time": "1:16:51", "remaining_time": "5:50:45", "throughput": 1495.33, "total_tokens": 6895552} {"current_steps": 32680, "total_steps": 181800, "loss": 0.1418, "lr": 4.903748736238793e-05, "epoch": 3.595159515951595, "percentage": 17.98, "elapsed_time": "1:16:52", "remaining_time": "5:50:45", "throughput": 1495.34, "total_tokens": 6896640} {"current_steps": 32685, "total_steps": 181800, "loss": 0.0216, "lr": 4.9036827696927e-05, "epoch": 3.5957095709570956, "percentage": 17.98, "elapsed_time": "1:16:52", "remaining_time": "5:50:44", "throughput": 1495.34, "total_tokens": 6897696} {"current_steps": 32690, "total_steps": 181800, "loss": 0.0336, "lr": 4.903616780993015e-05, "epoch": 3.5962596259625963, "percentage": 17.98, "elapsed_time": "1:16:53", "remaining_time": "5:50:43", "throughput": 1495.34, "total_tokens": 6898688} {"current_steps": 32695, "total_steps": 181800, "loss": 0.0146, "lr": 4.903550770140348e-05, "epoch": 3.596809680968097, "percentage": 17.98, "elapsed_time": "1:16:54", "remaining_time": "5:50:42", "throughput": 1495.34, "total_tokens": 6899744} {"current_steps": 32700, "total_steps": 181800, "loss": 0.0217, "lr": 4.903484737135306e-05, "epoch": 3.5973597359735976, "percentage": 17.99, "elapsed_time": "1:16:54", "remaining_time": "5:50:42", "throughput": 1495.34, "total_tokens": 6900768} {"current_steps": 32705, "total_steps": 181800, "loss": 0.1003, "lr": 4.9034186819785e-05, "epoch": 3.597909790979098, "percentage": 17.99, "elapsed_time": "1:16:55", "remaining_time": "5:50:41", "throughput": 1495.35, "total_tokens": 6901824} {"current_steps": 32710, "total_steps": 181800, "loss": 0.1292, "lr": 4.903352604670537e-05, "epoch": 3.5984598459845984, "percentage": 17.99, "elapsed_time": "1:16:56", "remaining_time": "5:50:40", "throughput": 1495.36, "total_tokens": 6902912} {"current_steps": 32715, "total_steps": 181800, "loss": 0.0327, "lr": 4.9032865052120255e-05, "epoch": 3.599009900990099, "percentage": 18.0, "elapsed_time": "1:16:56", "remaining_time": "5:50:39", "throughput": 1495.36, "total_tokens": 6903968} {"current_steps": 32720, "total_steps": 181800, "loss": 0.0084, "lr": 4.903220383603576e-05, "epoch": 3.5995599559955993, "percentage": 18.0, "elapsed_time": "1:16:57", "remaining_time": "5:50:38", "throughput": 1495.37, "total_tokens": 6905024} {"current_steps": 32725, "total_steps": 181800, "loss": 0.1069, "lr": 4.9031542398457974e-05, "epoch": 3.6001100110011, "percentage": 18.0, "elapsed_time": "1:16:58", "remaining_time": "5:50:38", "throughput": 1495.37, "total_tokens": 6906048} {"current_steps": 32730, "total_steps": 181800, "loss": 0.1121, "lr": 4.9030880739392993e-05, "epoch": 3.6006600660066006, "percentage": 18.0, "elapsed_time": "1:16:58", "remaining_time": "5:50:37", "throughput": 1495.37, "total_tokens": 6907072} {"current_steps": 32735, "total_steps": 181800, "loss": 0.0977, "lr": 4.903021885884691e-05, "epoch": 3.6012101210121013, "percentage": 18.01, "elapsed_time": "1:16:59", "remaining_time": "5:50:36", "throughput": 1495.38, "total_tokens": 6908160} {"current_steps": 32740, "total_steps": 181800, "loss": 0.0462, "lr": 4.902955675682584e-05, "epoch": 3.601760176017602, "percentage": 18.01, "elapsed_time": "1:17:00", "remaining_time": "5:50:35", "throughput": 1495.39, "total_tokens": 6909216} {"current_steps": 32745, "total_steps": 181800, "loss": 0.0328, "lr": 4.9028894433335874e-05, "epoch": 3.602310231023102, "percentage": 18.01, "elapsed_time": "1:17:01", "remaining_time": "5:50:34", "throughput": 1495.39, "total_tokens": 6910272} {"current_steps": 32750, "total_steps": 181800, "loss": 0.0314, "lr": 4.9028231888383114e-05, "epoch": 3.6028602860286028, "percentage": 18.01, "elapsed_time": "1:17:01", "remaining_time": "5:50:34", "throughput": 1495.38, "total_tokens": 6911264} {"current_steps": 32755, "total_steps": 181800, "loss": 0.0963, "lr": 4.902756912197367e-05, "epoch": 3.6034103410341034, "percentage": 18.02, "elapsed_time": "1:17:02", "remaining_time": "5:50:33", "throughput": 1495.4, "total_tokens": 6912384} {"current_steps": 32760, "total_steps": 181800, "loss": 0.0069, "lr": 4.902690613411365e-05, "epoch": 3.603960396039604, "percentage": 18.02, "elapsed_time": "1:17:03", "remaining_time": "5:50:32", "throughput": 1495.4, "total_tokens": 6913440} {"current_steps": 32765, "total_steps": 181800, "loss": 0.1283, "lr": 4.902624292480917e-05, "epoch": 3.6045104510451047, "percentage": 18.02, "elapsed_time": "1:17:03", "remaining_time": "5:50:31", "throughput": 1495.4, "total_tokens": 6914432} {"current_steps": 32770, "total_steps": 181800, "loss": 0.0267, "lr": 4.902557949406633e-05, "epoch": 3.605060506050605, "percentage": 18.03, "elapsed_time": "1:17:04", "remaining_time": "5:50:31", "throughput": 1495.4, "total_tokens": 6915456} {"current_steps": 32775, "total_steps": 181800, "loss": 0.1003, "lr": 4.902491584189126e-05, "epoch": 3.6056105610561056, "percentage": 18.03, "elapsed_time": "1:17:05", "remaining_time": "5:50:30", "throughput": 1495.41, "total_tokens": 6916544} {"current_steps": 32780, "total_steps": 181800, "loss": 0.0189, "lr": 4.902425196829007e-05, "epoch": 3.606160616061606, "percentage": 18.03, "elapsed_time": "1:17:05", "remaining_time": "5:50:29", "throughput": 1495.42, "total_tokens": 6917600} {"current_steps": 32785, "total_steps": 181800, "loss": 0.0747, "lr": 4.902358787326887e-05, "epoch": 3.606710671067107, "percentage": 18.03, "elapsed_time": "1:17:06", "remaining_time": "5:50:28", "throughput": 1495.41, "total_tokens": 6918624} {"current_steps": 32790, "total_steps": 181800, "loss": 0.0752, "lr": 4.90229235568338e-05, "epoch": 3.6072607260726075, "percentage": 18.04, "elapsed_time": "1:17:07", "remaining_time": "5:50:27", "throughput": 1495.43, "total_tokens": 6919744} {"current_steps": 32795, "total_steps": 181800, "loss": 0.2578, "lr": 4.902225901899096e-05, "epoch": 3.6078107810781077, "percentage": 18.04, "elapsed_time": "1:17:07", "remaining_time": "5:50:27", "throughput": 1495.44, "total_tokens": 6920800} {"current_steps": 32800, "total_steps": 181800, "loss": 0.0878, "lr": 4.90215942597465e-05, "epoch": 3.6083608360836084, "percentage": 18.04, "elapsed_time": "1:17:08", "remaining_time": "5:50:26", "throughput": 1495.47, "total_tokens": 6921952} {"current_steps": 32805, "total_steps": 181800, "loss": 0.0246, "lr": 4.9020929279106514e-05, "epoch": 3.608910891089109, "percentage": 18.04, "elapsed_time": "1:17:09", "remaining_time": "5:50:25", "throughput": 1495.48, "total_tokens": 6923040} {"current_steps": 32810, "total_steps": 181800, "loss": 0.0788, "lr": 4.902026407707716e-05, "epoch": 3.609460946094609, "percentage": 18.05, "elapsed_time": "1:17:09", "remaining_time": "5:50:24", "throughput": 1495.5, "total_tokens": 6924160} {"current_steps": 32815, "total_steps": 181800, "loss": 0.063, "lr": 4.901959865366456e-05, "epoch": 3.61001100110011, "percentage": 18.05, "elapsed_time": "1:17:10", "remaining_time": "5:50:23", "throughput": 1495.49, "total_tokens": 6925152} {"current_steps": 32820, "total_steps": 181800, "loss": 0.0763, "lr": 4.9018933008874835e-05, "epoch": 3.6105610561056105, "percentage": 18.05, "elapsed_time": "1:17:11", "remaining_time": "5:50:23", "throughput": 1495.52, "total_tokens": 6926304} {"current_steps": 32825, "total_steps": 181800, "loss": 0.1341, "lr": 4.9018267142714136e-05, "epoch": 3.611111111111111, "percentage": 18.06, "elapsed_time": "1:17:12", "remaining_time": "5:50:22", "throughput": 1495.52, "total_tokens": 6927328} {"current_steps": 32830, "total_steps": 181800, "loss": 0.0489, "lr": 4.901760105518859e-05, "epoch": 3.611661166116612, "percentage": 18.06, "elapsed_time": "1:17:12", "remaining_time": "5:50:21", "throughput": 1495.51, "total_tokens": 6928320} {"current_steps": 32835, "total_steps": 181800, "loss": 0.109, "lr": 4.9016934746304346e-05, "epoch": 3.612211221122112, "percentage": 18.06, "elapsed_time": "1:17:13", "remaining_time": "5:50:20", "throughput": 1495.53, "total_tokens": 6929408} {"current_steps": 32840, "total_steps": 181800, "loss": 0.0494, "lr": 4.9016268216067526e-05, "epoch": 3.6127612761276127, "percentage": 18.06, "elapsed_time": "1:17:14", "remaining_time": "5:50:19", "throughput": 1495.53, "total_tokens": 6930464} {"current_steps": 32845, "total_steps": 181800, "loss": 0.0653, "lr": 4.90156014644843e-05, "epoch": 3.6133113311331133, "percentage": 18.07, "elapsed_time": "1:17:14", "remaining_time": "5:50:19", "throughput": 1495.55, "total_tokens": 6931552} {"current_steps": 32850, "total_steps": 181800, "loss": 0.0601, "lr": 4.9014934491560796e-05, "epoch": 3.613861386138614, "percentage": 18.07, "elapsed_time": "1:17:15", "remaining_time": "5:50:18", "throughput": 1495.57, "total_tokens": 6932704} {"current_steps": 32855, "total_steps": 181800, "loss": 0.1024, "lr": 4.901426729730316e-05, "epoch": 3.6144114411441146, "percentage": 18.07, "elapsed_time": "1:17:16", "remaining_time": "5:50:17", "throughput": 1495.57, "total_tokens": 6933728} {"current_steps": 32860, "total_steps": 181800, "loss": 0.0706, "lr": 4.9013599881717556e-05, "epoch": 3.614961496149615, "percentage": 18.07, "elapsed_time": "1:17:16", "remaining_time": "5:50:16", "throughput": 1495.57, "total_tokens": 6934752} {"current_steps": 32865, "total_steps": 181800, "loss": 0.0456, "lr": 4.9012932244810113e-05, "epoch": 3.6155115511551155, "percentage": 18.08, "elapsed_time": "1:17:17", "remaining_time": "5:50:16", "throughput": 1495.58, "total_tokens": 6935840} {"current_steps": 32870, "total_steps": 181800, "loss": 0.0607, "lr": 4.9012264386586996e-05, "epoch": 3.616061606160616, "percentage": 18.08, "elapsed_time": "1:17:18", "remaining_time": "5:50:15", "throughput": 1495.58, "total_tokens": 6936864} {"current_steps": 32875, "total_steps": 181800, "loss": 0.0123, "lr": 4.901159630705436e-05, "epoch": 3.6166116611661168, "percentage": 18.08, "elapsed_time": "1:17:18", "remaining_time": "5:50:14", "throughput": 1495.59, "total_tokens": 6937920} {"current_steps": 32880, "total_steps": 181800, "loss": 0.0914, "lr": 4.901092800621837e-05, "epoch": 3.6171617161716174, "percentage": 18.09, "elapsed_time": "1:17:19", "remaining_time": "5:50:13", "throughput": 1495.6, "total_tokens": 6938976} {"current_steps": 32885, "total_steps": 181800, "loss": 0.0901, "lr": 4.901025948408518e-05, "epoch": 3.6177117711771176, "percentage": 18.09, "elapsed_time": "1:17:20", "remaining_time": "5:50:12", "throughput": 1495.6, "total_tokens": 6940000} {"current_steps": 32890, "total_steps": 181800, "loss": 0.1886, "lr": 4.900959074066094e-05, "epoch": 3.6182618261826183, "percentage": 18.09, "elapsed_time": "1:17:20", "remaining_time": "5:50:12", "throughput": 1495.6, "total_tokens": 6941056} {"current_steps": 32895, "total_steps": 181800, "loss": 0.0264, "lr": 4.9008921775951835e-05, "epoch": 3.618811881188119, "percentage": 18.09, "elapsed_time": "1:17:21", "remaining_time": "5:50:11", "throughput": 1495.6, "total_tokens": 6942080} {"current_steps": 32900, "total_steps": 181800, "loss": 0.0454, "lr": 4.900825258996401e-05, "epoch": 3.619361936193619, "percentage": 18.1, "elapsed_time": "1:17:22", "remaining_time": "5:50:10", "throughput": 1495.6, "total_tokens": 6943072} {"current_steps": 32905, "total_steps": 181800, "loss": 0.0239, "lr": 4.900758318270364e-05, "epoch": 3.6199119911991198, "percentage": 18.1, "elapsed_time": "1:17:23", "remaining_time": "5:50:09", "throughput": 1495.59, "total_tokens": 6944096} {"current_steps": 32910, "total_steps": 181800, "loss": 0.0969, "lr": 4.9006913554176905e-05, "epoch": 3.6204620462046204, "percentage": 18.1, "elapsed_time": "1:17:23", "remaining_time": "5:50:08", "throughput": 1495.61, "total_tokens": 6945184} {"current_steps": 32915, "total_steps": 181800, "loss": 0.027, "lr": 4.900624370438995e-05, "epoch": 3.621012101210121, "percentage": 18.11, "elapsed_time": "1:17:24", "remaining_time": "5:50:08", "throughput": 1495.61, "total_tokens": 6946208} {"current_steps": 32920, "total_steps": 181800, "loss": 0.0482, "lr": 4.900557363334898e-05, "epoch": 3.6215621562156217, "percentage": 18.11, "elapsed_time": "1:17:25", "remaining_time": "5:50:07", "throughput": 1495.61, "total_tokens": 6947264} {"current_steps": 32925, "total_steps": 181800, "loss": 0.0391, "lr": 4.900490334106016e-05, "epoch": 3.622112211221122, "percentage": 18.11, "elapsed_time": "1:17:25", "remaining_time": "5:50:06", "throughput": 1495.63, "total_tokens": 6948352} {"current_steps": 32930, "total_steps": 181800, "loss": 0.096, "lr": 4.9004232827529656e-05, "epoch": 3.6226622662266226, "percentage": 18.11, "elapsed_time": "1:17:26", "remaining_time": "5:50:05", "throughput": 1495.63, "total_tokens": 6949408} {"current_steps": 32935, "total_steps": 181800, "loss": 0.024, "lr": 4.9003562092763656e-05, "epoch": 3.6232123212321232, "percentage": 18.12, "elapsed_time": "1:17:27", "remaining_time": "5:50:04", "throughput": 1495.64, "total_tokens": 6950464} {"current_steps": 32940, "total_steps": 181800, "loss": 0.1232, "lr": 4.900289113676835e-05, "epoch": 3.623762376237624, "percentage": 18.12, "elapsed_time": "1:17:27", "remaining_time": "5:50:04", "throughput": 1495.65, "total_tokens": 6951552} {"current_steps": 32945, "total_steps": 181800, "loss": 0.0522, "lr": 4.9002219959549906e-05, "epoch": 3.6243124312431245, "percentage": 18.12, "elapsed_time": "1:17:28", "remaining_time": "5:50:03", "throughput": 1495.66, "total_tokens": 6952640} {"current_steps": 32950, "total_steps": 181800, "loss": 0.0978, "lr": 4.9001548561114516e-05, "epoch": 3.6248624862486247, "percentage": 18.12, "elapsed_time": "1:17:29", "remaining_time": "5:50:02", "throughput": 1495.68, "total_tokens": 6953760} {"current_steps": 32955, "total_steps": 181800, "loss": 0.0549, "lr": 4.900087694146838e-05, "epoch": 3.6254125412541254, "percentage": 18.13, "elapsed_time": "1:17:29", "remaining_time": "5:50:01", "throughput": 1495.69, "total_tokens": 6954848} {"current_steps": 32960, "total_steps": 181800, "loss": 0.0405, "lr": 4.9000205100617674e-05, "epoch": 3.625962596259626, "percentage": 18.13, "elapsed_time": "1:17:30", "remaining_time": "5:50:01", "throughput": 1495.71, "total_tokens": 6955968} {"current_steps": 32965, "total_steps": 181800, "loss": 0.0502, "lr": 4.899953303856859e-05, "epoch": 3.6265126512651267, "percentage": 18.13, "elapsed_time": "1:17:31", "remaining_time": "5:50:00", "throughput": 1495.72, "total_tokens": 6957024} {"current_steps": 32970, "total_steps": 181800, "loss": 0.047, "lr": 4.899886075532733e-05, "epoch": 3.6270627062706273, "percentage": 18.14, "elapsed_time": "1:17:31", "remaining_time": "5:49:59", "throughput": 1495.71, "total_tokens": 6958016} {"current_steps": 32975, "total_steps": 181800, "loss": 0.0476, "lr": 4.899818825090009e-05, "epoch": 3.6276127612761275, "percentage": 18.14, "elapsed_time": "1:17:32", "remaining_time": "5:49:58", "throughput": 1495.71, "total_tokens": 6959072} {"current_steps": 32980, "total_steps": 181800, "loss": 0.0811, "lr": 4.899751552529306e-05, "epoch": 3.628162816281628, "percentage": 18.14, "elapsed_time": "1:17:33", "remaining_time": "5:49:57", "throughput": 1495.71, "total_tokens": 6960096} {"current_steps": 32985, "total_steps": 181800, "loss": 0.0799, "lr": 4.8996842578512444e-05, "epoch": 3.628712871287129, "percentage": 18.14, "elapsed_time": "1:17:34", "remaining_time": "5:49:57", "throughput": 1495.71, "total_tokens": 6961120} {"current_steps": 32990, "total_steps": 181800, "loss": 0.0685, "lr": 4.8996169410564444e-05, "epoch": 3.629262926292629, "percentage": 18.15, "elapsed_time": "1:17:34", "remaining_time": "5:49:56", "throughput": 1495.71, "total_tokens": 6962144} {"current_steps": 32995, "total_steps": 181800, "loss": 0.0497, "lr": 4.899549602145527e-05, "epoch": 3.6298129812981297, "percentage": 18.15, "elapsed_time": "1:17:35", "remaining_time": "5:49:55", "throughput": 1495.73, "total_tokens": 6963264} {"current_steps": 33000, "total_steps": 181800, "loss": 0.012, "lr": 4.899482241119111e-05, "epoch": 3.6303630363036303, "percentage": 18.15, "elapsed_time": "1:17:36", "remaining_time": "5:49:54", "throughput": 1495.74, "total_tokens": 6964320} {"current_steps": 33005, "total_steps": 181800, "loss": 0.1509, "lr": 4.89941485797782e-05, "epoch": 3.630913091309131, "percentage": 18.15, "elapsed_time": "1:17:36", "remaining_time": "5:49:54", "throughput": 1495.74, "total_tokens": 6965376} {"current_steps": 33010, "total_steps": 181800, "loss": 0.0784, "lr": 4.899347452722273e-05, "epoch": 3.6314631463146316, "percentage": 18.16, "elapsed_time": "1:17:37", "remaining_time": "5:49:53", "throughput": 1495.74, "total_tokens": 6966400} {"current_steps": 33015, "total_steps": 181800, "loss": 0.1205, "lr": 4.8992800253530916e-05, "epoch": 3.632013201320132, "percentage": 18.16, "elapsed_time": "1:17:38", "remaining_time": "5:49:52", "throughput": 1495.74, "total_tokens": 6967424} {"current_steps": 33020, "total_steps": 181800, "loss": 0.1238, "lr": 4.899212575870898e-05, "epoch": 3.6325632563256325, "percentage": 18.16, "elapsed_time": "1:17:38", "remaining_time": "5:49:51", "throughput": 1495.73, "total_tokens": 6968416} {"current_steps": 33025, "total_steps": 181800, "loss": 0.1189, "lr": 4.8991451042763135e-05, "epoch": 3.633113311331133, "percentage": 18.17, "elapsed_time": "1:17:39", "remaining_time": "5:49:50", "throughput": 1495.72, "total_tokens": 6969408} {"current_steps": 33030, "total_steps": 181800, "loss": 0.052, "lr": 4.8990776105699594e-05, "epoch": 3.633663366336634, "percentage": 18.17, "elapsed_time": "1:17:40", "remaining_time": "5:49:50", "throughput": 1495.73, "total_tokens": 6970464} {"current_steps": 33035, "total_steps": 181800, "loss": 0.0723, "lr": 4.899010094752458e-05, "epoch": 3.6342134213421344, "percentage": 18.17, "elapsed_time": "1:17:40", "remaining_time": "5:49:49", "throughput": 1495.74, "total_tokens": 6971552} {"current_steps": 33040, "total_steps": 181800, "loss": 0.1005, "lr": 4.8989425568244315e-05, "epoch": 3.6347634763476346, "percentage": 18.17, "elapsed_time": "1:17:41", "remaining_time": "5:49:48", "throughput": 1495.75, "total_tokens": 6972640} {"current_steps": 33045, "total_steps": 181800, "loss": 0.088, "lr": 4.898874996786503e-05, "epoch": 3.6353135313531353, "percentage": 18.18, "elapsed_time": "1:17:42", "remaining_time": "5:49:47", "throughput": 1495.78, "total_tokens": 6973792} {"current_steps": 33050, "total_steps": 181800, "loss": 0.1703, "lr": 4.898807414639296e-05, "epoch": 3.635863586358636, "percentage": 18.18, "elapsed_time": "1:17:43", "remaining_time": "5:49:47", "throughput": 1495.78, "total_tokens": 6974848} {"current_steps": 33055, "total_steps": 181800, "loss": 0.0351, "lr": 4.8987398103834305e-05, "epoch": 3.636413641364136, "percentage": 18.18, "elapsed_time": "1:17:43", "remaining_time": "5:49:46", "throughput": 1495.79, "total_tokens": 6975904} {"current_steps": 33060, "total_steps": 181800, "loss": 0.0681, "lr": 4.898672184019532e-05, "epoch": 3.6369636963696372, "percentage": 18.18, "elapsed_time": "1:17:44", "remaining_time": "5:49:45", "throughput": 1495.82, "total_tokens": 6977056} {"current_steps": 33065, "total_steps": 181800, "loss": 0.0399, "lr": 4.8986045355482216e-05, "epoch": 3.6375137513751374, "percentage": 18.19, "elapsed_time": "1:17:45", "remaining_time": "5:49:44", "throughput": 1495.81, "total_tokens": 6978048} {"current_steps": 33070, "total_steps": 181800, "loss": 0.026, "lr": 4.898536864970126e-05, "epoch": 3.638063806380638, "percentage": 18.19, "elapsed_time": "1:17:45", "remaining_time": "5:49:43", "throughput": 1495.82, "total_tokens": 6979136} {"current_steps": 33075, "total_steps": 181800, "loss": 0.0523, "lr": 4.898469172285866e-05, "epoch": 3.6386138613861387, "percentage": 18.19, "elapsed_time": "1:17:46", "remaining_time": "5:49:43", "throughput": 1495.83, "total_tokens": 6980224} {"current_steps": 33080, "total_steps": 181800, "loss": 0.0552, "lr": 4.898401457496066e-05, "epoch": 3.639163916391639, "percentage": 18.2, "elapsed_time": "1:17:47", "remaining_time": "5:49:42", "throughput": 1495.84, "total_tokens": 6981312} {"current_steps": 33085, "total_steps": 181800, "loss": 0.0439, "lr": 4.898333720601352e-05, "epoch": 3.6397139713971396, "percentage": 18.2, "elapsed_time": "1:17:47", "remaining_time": "5:49:41", "throughput": 1495.85, "total_tokens": 6982368} {"current_steps": 33090, "total_steps": 181800, "loss": 0.1328, "lr": 4.898265961602346e-05, "epoch": 3.6402640264026402, "percentage": 18.2, "elapsed_time": "1:17:48", "remaining_time": "5:49:40", "throughput": 1495.86, "total_tokens": 6983456} {"current_steps": 33095, "total_steps": 181800, "loss": 0.0945, "lr": 4.8981981804996736e-05, "epoch": 3.640814081408141, "percentage": 18.2, "elapsed_time": "1:17:49", "remaining_time": "5:49:40", "throughput": 1495.87, "total_tokens": 6984544} {"current_steps": 33100, "total_steps": 181800, "loss": 0.07, "lr": 4.8981303772939594e-05, "epoch": 3.6413641364136415, "percentage": 18.21, "elapsed_time": "1:17:49", "remaining_time": "5:49:39", "throughput": 1495.88, "total_tokens": 6985600} {"current_steps": 33105, "total_steps": 181800, "loss": 0.0483, "lr": 4.8980625519858284e-05, "epoch": 3.6419141914191417, "percentage": 18.21, "elapsed_time": "1:17:50", "remaining_time": "5:49:38", "throughput": 1495.88, "total_tokens": 6986624} {"current_steps": 33110, "total_steps": 181800, "loss": 0.0731, "lr": 4.8979947045759055e-05, "epoch": 3.6424642464246424, "percentage": 18.21, "elapsed_time": "1:17:51", "remaining_time": "5:49:37", "throughput": 1495.88, "total_tokens": 6987648} {"current_steps": 33115, "total_steps": 181800, "loss": 0.0638, "lr": 4.897926835064816e-05, "epoch": 3.643014301430143, "percentage": 18.22, "elapsed_time": "1:17:51", "remaining_time": "5:49:36", "throughput": 1495.88, "total_tokens": 6988672} {"current_steps": 33120, "total_steps": 181800, "loss": 0.069, "lr": 4.8978589434531855e-05, "epoch": 3.6435643564356437, "percentage": 18.22, "elapsed_time": "1:17:52", "remaining_time": "5:49:36", "throughput": 1495.87, "total_tokens": 6989696} {"current_steps": 33125, "total_steps": 181800, "loss": 0.0876, "lr": 4.897791029741639e-05, "epoch": 3.6441144114411443, "percentage": 18.22, "elapsed_time": "1:17:53", "remaining_time": "5:49:35", "throughput": 1495.87, "total_tokens": 6990720} {"current_steps": 33130, "total_steps": 181800, "loss": 0.0552, "lr": 4.897723093930805e-05, "epoch": 3.6446644664466445, "percentage": 18.22, "elapsed_time": "1:17:54", "remaining_time": "5:49:34", "throughput": 1495.87, "total_tokens": 6991744} {"current_steps": 33135, "total_steps": 181800, "loss": 0.0572, "lr": 4.897655136021306e-05, "epoch": 3.645214521452145, "percentage": 18.23, "elapsed_time": "1:17:54", "remaining_time": "5:49:33", "throughput": 1495.87, "total_tokens": 6992768} {"current_steps": 33140, "total_steps": 181800, "loss": 0.1424, "lr": 4.897587156013771e-05, "epoch": 3.645764576457646, "percentage": 18.23, "elapsed_time": "1:17:55", "remaining_time": "5:49:33", "throughput": 1495.86, "total_tokens": 6993760} {"current_steps": 33145, "total_steps": 181800, "loss": 0.0465, "lr": 4.897519153908826e-05, "epoch": 3.646314631463146, "percentage": 18.23, "elapsed_time": "1:17:56", "remaining_time": "5:49:32", "throughput": 1495.87, "total_tokens": 6994816} {"current_steps": 33150, "total_steps": 181800, "loss": 0.068, "lr": 4.897451129707096e-05, "epoch": 3.6468646864686467, "percentage": 18.23, "elapsed_time": "1:17:56", "remaining_time": "5:49:31", "throughput": 1495.87, "total_tokens": 6995872} {"current_steps": 33155, "total_steps": 181800, "loss": 0.0158, "lr": 4.8973830834092104e-05, "epoch": 3.6474147414741473, "percentage": 18.24, "elapsed_time": "1:17:57", "remaining_time": "5:49:30", "throughput": 1495.88, "total_tokens": 6996928} {"current_steps": 33160, "total_steps": 181800, "loss": 0.0142, "lr": 4.897315015015795e-05, "epoch": 3.647964796479648, "percentage": 18.24, "elapsed_time": "1:17:58", "remaining_time": "5:49:29", "throughput": 1495.89, "total_tokens": 6998016} {"current_steps": 33165, "total_steps": 181800, "loss": 0.112, "lr": 4.8972469245274776e-05, "epoch": 3.6485148514851486, "percentage": 18.24, "elapsed_time": "1:17:58", "remaining_time": "5:49:29", "throughput": 1495.9, "total_tokens": 6999104} {"current_steps": 33170, "total_steps": 181800, "loss": 0.0144, "lr": 4.8971788119448855e-05, "epoch": 3.649064906490649, "percentage": 18.25, "elapsed_time": "1:17:59", "remaining_time": "5:49:28", "throughput": 1495.91, "total_tokens": 7000160} {"current_steps": 33175, "total_steps": 181800, "loss": 0.0376, "lr": 4.897110677268647e-05, "epoch": 3.6496149614961495, "percentage": 18.25, "elapsed_time": "1:18:00", "remaining_time": "5:49:27", "throughput": 1495.91, "total_tokens": 7001216} {"current_steps": 33180, "total_steps": 181800, "loss": 0.0144, "lr": 4.897042520499389e-05, "epoch": 3.65016501650165, "percentage": 18.25, "elapsed_time": "1:18:00", "remaining_time": "5:49:26", "throughput": 1495.92, "total_tokens": 7002272} {"current_steps": 33185, "total_steps": 181800, "loss": 0.1168, "lr": 4.8969743416377406e-05, "epoch": 3.650715071507151, "percentage": 18.25, "elapsed_time": "1:18:01", "remaining_time": "5:49:26", "throughput": 1495.92, "total_tokens": 7003328} {"current_steps": 33190, "total_steps": 181800, "loss": 0.0839, "lr": 4.89690614068433e-05, "epoch": 3.6512651265126514, "percentage": 18.26, "elapsed_time": "1:18:02", "remaining_time": "5:49:25", "throughput": 1495.93, "total_tokens": 7004384} {"current_steps": 33195, "total_steps": 181800, "loss": 0.1279, "lr": 4.8968379176397857e-05, "epoch": 3.6518151815181517, "percentage": 18.26, "elapsed_time": "1:18:02", "remaining_time": "5:49:24", "throughput": 1495.92, "total_tokens": 7005376} {"current_steps": 33200, "total_steps": 181800, "loss": 0.0186, "lr": 4.896769672504736e-05, "epoch": 3.6523652365236523, "percentage": 18.26, "elapsed_time": "1:18:03", "remaining_time": "5:49:23", "throughput": 1495.92, "total_tokens": 7006432} {"current_steps": 33205, "total_steps": 181800, "loss": 0.013, "lr": 4.8967014052798104e-05, "epoch": 3.652915291529153, "percentage": 18.26, "elapsed_time": "1:18:04", "remaining_time": "5:49:22", "throughput": 1495.92, "total_tokens": 7007456} {"current_steps": 33210, "total_steps": 181800, "loss": 0.0781, "lr": 4.8966331159656384e-05, "epoch": 3.6534653465346536, "percentage": 18.27, "elapsed_time": "1:18:05", "remaining_time": "5:49:22", "throughput": 1495.92, "total_tokens": 7008480} {"current_steps": 33215, "total_steps": 181800, "loss": 0.0571, "lr": 4.896564804562849e-05, "epoch": 3.6540154015401543, "percentage": 18.27, "elapsed_time": "1:18:05", "remaining_time": "5:49:21", "throughput": 1495.92, "total_tokens": 7009504} {"current_steps": 33220, "total_steps": 181800, "loss": 0.0595, "lr": 4.8964964710720705e-05, "epoch": 3.6545654565456545, "percentage": 18.27, "elapsed_time": "1:18:06", "remaining_time": "5:49:20", "throughput": 1495.92, "total_tokens": 7010560} {"current_steps": 33225, "total_steps": 181800, "loss": 0.0445, "lr": 4.896428115493935e-05, "epoch": 3.655115511551155, "percentage": 18.28, "elapsed_time": "1:18:07", "remaining_time": "5:49:19", "throughput": 1495.93, "total_tokens": 7011648} {"current_steps": 33230, "total_steps": 181800, "loss": 0.0398, "lr": 4.896359737829071e-05, "epoch": 3.6556655665566558, "percentage": 18.28, "elapsed_time": "1:18:07", "remaining_time": "5:49:19", "throughput": 1495.93, "total_tokens": 7012672} {"current_steps": 33235, "total_steps": 181800, "loss": 0.0683, "lr": 4.896291338078111e-05, "epoch": 3.656215621562156, "percentage": 18.28, "elapsed_time": "1:18:08", "remaining_time": "5:49:18", "throughput": 1495.92, "total_tokens": 7013664} {"current_steps": 33240, "total_steps": 181800, "loss": 0.0295, "lr": 4.8962229162416816e-05, "epoch": 3.6567656765676566, "percentage": 18.28, "elapsed_time": "1:18:09", "remaining_time": "5:49:17", "throughput": 1495.93, "total_tokens": 7014720} {"current_steps": 33245, "total_steps": 181800, "loss": 0.0171, "lr": 4.896154472320416e-05, "epoch": 3.6573157315731573, "percentage": 18.29, "elapsed_time": "1:18:09", "remaining_time": "5:49:16", "throughput": 1495.92, "total_tokens": 7015712} {"current_steps": 33250, "total_steps": 181800, "loss": 0.0378, "lr": 4.896086006314944e-05, "epoch": 3.657865786578658, "percentage": 18.29, "elapsed_time": "1:18:10", "remaining_time": "5:49:16", "throughput": 1495.91, "total_tokens": 7016736} {"current_steps": 33255, "total_steps": 181800, "loss": 0.0171, "lr": 4.8960175182258984e-05, "epoch": 3.6584158415841586, "percentage": 18.29, "elapsed_time": "1:18:11", "remaining_time": "5:49:15", "throughput": 1495.91, "total_tokens": 7017728} {"current_steps": 33260, "total_steps": 181800, "loss": 0.0601, "lr": 4.8959490080539074e-05, "epoch": 3.6589658965896588, "percentage": 18.29, "elapsed_time": "1:18:11", "remaining_time": "5:49:14", "throughput": 1495.91, "total_tokens": 7018784} {"current_steps": 33265, "total_steps": 181800, "loss": 0.071, "lr": 4.895880475799605e-05, "epoch": 3.6595159515951594, "percentage": 18.3, "elapsed_time": "1:18:12", "remaining_time": "5:49:13", "throughput": 1495.92, "total_tokens": 7019840} {"current_steps": 33270, "total_steps": 181800, "loss": 0.0114, "lr": 4.895811921463622e-05, "epoch": 3.66006600660066, "percentage": 18.3, "elapsed_time": "1:18:13", "remaining_time": "5:49:12", "throughput": 1495.92, "total_tokens": 7020896} {"current_steps": 33275, "total_steps": 181800, "loss": 0.0218, "lr": 4.8957433450465894e-05, "epoch": 3.6606160616061607, "percentage": 18.3, "elapsed_time": "1:18:14", "remaining_time": "5:49:12", "throughput": 1495.93, "total_tokens": 7021984} {"current_steps": 33280, "total_steps": 181800, "loss": 0.0695, "lr": 4.89567474654914e-05, "epoch": 3.6611661166116614, "percentage": 18.31, "elapsed_time": "1:18:14", "remaining_time": "5:49:11", "throughput": 1495.95, "total_tokens": 7023104} {"current_steps": 33285, "total_steps": 181800, "loss": 0.0469, "lr": 4.895606125971907e-05, "epoch": 3.6617161716171616, "percentage": 18.31, "elapsed_time": "1:18:15", "remaining_time": "5:49:10", "throughput": 1495.97, "total_tokens": 7024224} {"current_steps": 33290, "total_steps": 181800, "loss": 0.0864, "lr": 4.895537483315521e-05, "epoch": 3.662266226622662, "percentage": 18.31, "elapsed_time": "1:18:16", "remaining_time": "5:49:09", "throughput": 1495.98, "total_tokens": 7025280} {"current_steps": 33295, "total_steps": 181800, "loss": 0.0763, "lr": 4.8954688185806165e-05, "epoch": 3.662816281628163, "percentage": 18.31, "elapsed_time": "1:18:16", "remaining_time": "5:49:09", "throughput": 1495.97, "total_tokens": 7026304} {"current_steps": 33300, "total_steps": 181800, "loss": 0.1141, "lr": 4.8954001317678245e-05, "epoch": 3.6633663366336635, "percentage": 18.32, "elapsed_time": "1:18:17", "remaining_time": "5:49:08", "throughput": 1495.99, "total_tokens": 7027392} {"current_steps": 33305, "total_steps": 181800, "loss": 0.0453, "lr": 4.8953314228777795e-05, "epoch": 3.663916391639164, "percentage": 18.32, "elapsed_time": "1:18:18", "remaining_time": "5:49:07", "throughput": 1496.0, "total_tokens": 7028512} {"current_steps": 33310, "total_steps": 181800, "loss": 0.0778, "lr": 4.8952626919111135e-05, "epoch": 3.6644664466446644, "percentage": 18.32, "elapsed_time": "1:18:18", "remaining_time": "5:49:06", "throughput": 1496.01, "total_tokens": 7029568} {"current_steps": 33315, "total_steps": 181800, "loss": 0.0872, "lr": 4.89519393886846e-05, "epoch": 3.665016501650165, "percentage": 18.33, "elapsed_time": "1:18:19", "remaining_time": "5:49:05", "throughput": 1496.01, "total_tokens": 7030592} {"current_steps": 33320, "total_steps": 181800, "loss": 0.1477, "lr": 4.895125163750455e-05, "epoch": 3.6655665566556657, "percentage": 18.33, "elapsed_time": "1:18:20", "remaining_time": "5:49:05", "throughput": 1496.03, "total_tokens": 7031712} {"current_steps": 33325, "total_steps": 181800, "loss": 0.0756, "lr": 4.895056366557729e-05, "epoch": 3.666116611661166, "percentage": 18.33, "elapsed_time": "1:18:20", "remaining_time": "5:49:04", "throughput": 1496.04, "total_tokens": 7032768} {"current_steps": 33330, "total_steps": 181800, "loss": 0.0609, "lr": 4.894987547290919e-05, "epoch": 3.6666666666666665, "percentage": 18.33, "elapsed_time": "1:18:21", "remaining_time": "5:49:03", "throughput": 1496.04, "total_tokens": 7033824} {"current_steps": 33335, "total_steps": 181800, "loss": 0.0312, "lr": 4.894918705950657e-05, "epoch": 3.667216721672167, "percentage": 18.34, "elapsed_time": "1:18:22", "remaining_time": "5:49:02", "throughput": 1496.05, "total_tokens": 7034880} {"current_steps": 33340, "total_steps": 181800, "loss": 0.0446, "lr": 4.89484984253758e-05, "epoch": 3.667766776677668, "percentage": 18.34, "elapsed_time": "1:18:22", "remaining_time": "5:49:02", "throughput": 1496.03, "total_tokens": 7035840} {"current_steps": 33345, "total_steps": 181800, "loss": 0.0399, "lr": 4.894780957052319e-05, "epoch": 3.6683168316831685, "percentage": 18.34, "elapsed_time": "1:18:23", "remaining_time": "5:49:01", "throughput": 1496.05, "total_tokens": 7036960} {"current_steps": 33350, "total_steps": 181800, "loss": 0.0393, "lr": 4.894712049495513e-05, "epoch": 3.6688668866886687, "percentage": 18.34, "elapsed_time": "1:18:24", "remaining_time": "5:49:00", "throughput": 1496.07, "total_tokens": 7038080} {"current_steps": 33355, "total_steps": 181800, "loss": 0.0339, "lr": 4.894643119867794e-05, "epoch": 3.6694169416941693, "percentage": 18.35, "elapsed_time": "1:18:25", "remaining_time": "5:48:59", "throughput": 1496.09, "total_tokens": 7039200} {"current_steps": 33360, "total_steps": 181800, "loss": 0.0425, "lr": 4.8945741681697984e-05, "epoch": 3.66996699669967, "percentage": 18.35, "elapsed_time": "1:18:25", "remaining_time": "5:48:58", "throughput": 1496.1, "total_tokens": 7040288} {"current_steps": 33365, "total_steps": 181800, "loss": 0.069, "lr": 4.894505194402163e-05, "epoch": 3.6705170517051706, "percentage": 18.35, "elapsed_time": "1:18:26", "remaining_time": "5:48:58", "throughput": 1496.12, "total_tokens": 7041408} {"current_steps": 33370, "total_steps": 181800, "loss": 0.1241, "lr": 4.8944361985655214e-05, "epoch": 3.6710671067106713, "percentage": 18.36, "elapsed_time": "1:18:27", "remaining_time": "5:48:57", "throughput": 1496.13, "total_tokens": 7042464} {"current_steps": 33375, "total_steps": 181800, "loss": 0.0751, "lr": 4.89436718066051e-05, "epoch": 3.6716171617161715, "percentage": 18.36, "elapsed_time": "1:18:27", "remaining_time": "5:48:56", "throughput": 1496.11, "total_tokens": 7043424} {"current_steps": 33380, "total_steps": 181800, "loss": 0.087, "lr": 4.894298140687765e-05, "epoch": 3.672167216721672, "percentage": 18.36, "elapsed_time": "1:18:28", "remaining_time": "5:48:55", "throughput": 1496.12, "total_tokens": 7044480} {"current_steps": 33385, "total_steps": 181800, "loss": 0.0873, "lr": 4.894229078647924e-05, "epoch": 3.6727172717271728, "percentage": 18.36, "elapsed_time": "1:18:29", "remaining_time": "5:48:54", "throughput": 1496.11, "total_tokens": 7045472} {"current_steps": 33390, "total_steps": 181800, "loss": 0.0431, "lr": 4.8941599945416213e-05, "epoch": 3.6732673267326734, "percentage": 18.37, "elapsed_time": "1:18:29", "remaining_time": "5:48:54", "throughput": 1496.11, "total_tokens": 7046496} {"current_steps": 33395, "total_steps": 181800, "loss": 0.0815, "lr": 4.894090888369496e-05, "epoch": 3.673817381738174, "percentage": 18.37, "elapsed_time": "1:18:30", "remaining_time": "5:48:53", "throughput": 1496.12, "total_tokens": 7047584} {"current_steps": 33400, "total_steps": 181800, "loss": 0.0248, "lr": 4.8940217601321824e-05, "epoch": 3.6743674367436743, "percentage": 18.37, "elapsed_time": "1:18:31", "remaining_time": "5:48:52", "throughput": 1496.13, "total_tokens": 7048672} {"current_steps": 33405, "total_steps": 181800, "loss": 0.072, "lr": 4.89395260983032e-05, "epoch": 3.674917491749175, "percentage": 18.37, "elapsed_time": "1:18:31", "remaining_time": "5:48:51", "throughput": 1496.13, "total_tokens": 7049664} {"current_steps": 33410, "total_steps": 181800, "loss": 0.0583, "lr": 4.893883437464545e-05, "epoch": 3.6754675467546756, "percentage": 18.38, "elapsed_time": "1:18:32", "remaining_time": "5:48:51", "throughput": 1496.13, "total_tokens": 7050688} {"current_steps": 33415, "total_steps": 181800, "loss": 0.0152, "lr": 4.893814243035495e-05, "epoch": 3.676017601760176, "percentage": 18.38, "elapsed_time": "1:18:33", "remaining_time": "5:48:50", "throughput": 1496.12, "total_tokens": 7051712} {"current_steps": 33420, "total_steps": 181800, "loss": 0.0487, "lr": 4.8937450265438076e-05, "epoch": 3.6765676567656764, "percentage": 18.38, "elapsed_time": "1:18:34", "remaining_time": "5:48:49", "throughput": 1496.12, "total_tokens": 7052736} {"current_steps": 33425, "total_steps": 181800, "loss": 0.0226, "lr": 4.8936757879901205e-05, "epoch": 3.677117711771177, "percentage": 18.39, "elapsed_time": "1:18:34", "remaining_time": "5:48:48", "throughput": 1496.13, "total_tokens": 7053824} {"current_steps": 33430, "total_steps": 181800, "loss": 0.051, "lr": 4.893606527375073e-05, "epoch": 3.6776677667766777, "percentage": 18.39, "elapsed_time": "1:18:35", "remaining_time": "5:48:47", "throughput": 1496.14, "total_tokens": 7054880} {"current_steps": 33435, "total_steps": 181800, "loss": 0.0697, "lr": 4.8935372446993024e-05, "epoch": 3.6782178217821784, "percentage": 18.39, "elapsed_time": "1:18:36", "remaining_time": "5:48:47", "throughput": 1496.13, "total_tokens": 7055872} {"current_steps": 33440, "total_steps": 181800, "loss": 0.0784, "lr": 4.8934679399634475e-05, "epoch": 3.6787678767876786, "percentage": 18.39, "elapsed_time": "1:18:36", "remaining_time": "5:48:46", "throughput": 1496.15, "total_tokens": 7056992} {"current_steps": 33445, "total_steps": 181800, "loss": 0.0292, "lr": 4.8933986131681474e-05, "epoch": 3.6793179317931792, "percentage": 18.4, "elapsed_time": "1:18:37", "remaining_time": "5:48:45", "throughput": 1496.14, "total_tokens": 7057984} {"current_steps": 33450, "total_steps": 181800, "loss": 0.1198, "lr": 4.893329264314041e-05, "epoch": 3.67986798679868, "percentage": 18.4, "elapsed_time": "1:18:38", "remaining_time": "5:48:44", "throughput": 1496.14, "total_tokens": 7059008} {"current_steps": 33455, "total_steps": 181800, "loss": 0.1248, "lr": 4.893259893401766e-05, "epoch": 3.6804180418041805, "percentage": 18.4, "elapsed_time": "1:18:38", "remaining_time": "5:48:44", "throughput": 1496.14, "total_tokens": 7060064} {"current_steps": 33460, "total_steps": 181800, "loss": 0.0432, "lr": 4.893190500431964e-05, "epoch": 3.680968096809681, "percentage": 18.4, "elapsed_time": "1:18:39", "remaining_time": "5:48:43", "throughput": 1496.16, "total_tokens": 7061152} {"current_steps": 33465, "total_steps": 181800, "loss": 0.1099, "lr": 4.8931210854052734e-05, "epoch": 3.6815181518151814, "percentage": 18.41, "elapsed_time": "1:18:40", "remaining_time": "5:48:42", "throughput": 1496.18, "total_tokens": 7062272} {"current_steps": 33470, "total_steps": 181800, "loss": 0.0791, "lr": 4.893051648322334e-05, "epoch": 3.682068206820682, "percentage": 18.41, "elapsed_time": "1:18:40", "remaining_time": "5:48:41", "throughput": 1496.19, "total_tokens": 7063360} {"current_steps": 33475, "total_steps": 181800, "loss": 0.024, "lr": 4.892982189183786e-05, "epoch": 3.6826182618261827, "percentage": 18.41, "elapsed_time": "1:18:41", "remaining_time": "5:48:41", "throughput": 1496.2, "total_tokens": 7064448} {"current_steps": 33480, "total_steps": 181800, "loss": 0.0349, "lr": 4.8929127079902684e-05, "epoch": 3.6831683168316833, "percentage": 18.42, "elapsed_time": "1:18:42", "remaining_time": "5:48:40", "throughput": 1496.18, "total_tokens": 7065408} {"current_steps": 33485, "total_steps": 181800, "loss": 0.0363, "lr": 4.892843204742424e-05, "epoch": 3.683718371837184, "percentage": 18.42, "elapsed_time": "1:18:42", "remaining_time": "5:48:39", "throughput": 1496.18, "total_tokens": 7066400} {"current_steps": 33490, "total_steps": 181800, "loss": 0.1087, "lr": 4.8927736794408905e-05, "epoch": 3.684268426842684, "percentage": 18.42, "elapsed_time": "1:18:43", "remaining_time": "5:48:38", "throughput": 1496.19, "total_tokens": 7067520} {"current_steps": 33495, "total_steps": 181800, "loss": 0.0347, "lr": 4.892704132086312e-05, "epoch": 3.684818481848185, "percentage": 18.42, "elapsed_time": "1:18:44", "remaining_time": "5:48:37", "throughput": 1496.19, "total_tokens": 7068512} {"current_steps": 33500, "total_steps": 181800, "loss": 0.0862, "lr": 4.8926345626793264e-05, "epoch": 3.6853685368536855, "percentage": 18.43, "elapsed_time": "1:18:45", "remaining_time": "5:48:37", "throughput": 1496.19, "total_tokens": 7069568} {"current_steps": 33505, "total_steps": 181800, "loss": 0.0393, "lr": 4.8925649712205765e-05, "epoch": 3.6859185918591857, "percentage": 18.43, "elapsed_time": "1:18:45", "remaining_time": "5:48:36", "throughput": 1496.18, "total_tokens": 7070528} {"current_steps": 33510, "total_steps": 181800, "loss": 0.055, "lr": 4.892495357710703e-05, "epoch": 3.6864686468646863, "percentage": 18.43, "elapsed_time": "1:18:46", "remaining_time": "5:48:35", "throughput": 1496.17, "total_tokens": 7071520} {"current_steps": 33515, "total_steps": 181800, "loss": 0.0752, "lr": 4.892425722150348e-05, "epoch": 3.687018701870187, "percentage": 18.44, "elapsed_time": "1:18:47", "remaining_time": "5:48:34", "throughput": 1496.19, "total_tokens": 7072640} {"current_steps": 33520, "total_steps": 181800, "loss": 0.111, "lr": 4.8923560645401536e-05, "epoch": 3.6875687568756876, "percentage": 18.44, "elapsed_time": "1:18:47", "remaining_time": "5:48:34", "throughput": 1496.2, "total_tokens": 7073728} {"current_steps": 33525, "total_steps": 181800, "loss": 0.0283, "lr": 4.892286384880761e-05, "epoch": 3.6881188118811883, "percentage": 18.44, "elapsed_time": "1:18:48", "remaining_time": "5:48:33", "throughput": 1496.2, "total_tokens": 7074752} {"current_steps": 33530, "total_steps": 181800, "loss": 0.0098, "lr": 4.892216683172812e-05, "epoch": 3.6886688668866885, "percentage": 18.44, "elapsed_time": "1:18:49", "remaining_time": "5:48:32", "throughput": 1496.2, "total_tokens": 7075776} {"current_steps": 33535, "total_steps": 181800, "loss": 0.0201, "lr": 4.892146959416951e-05, "epoch": 3.689218921892189, "percentage": 18.45, "elapsed_time": "1:18:49", "remaining_time": "5:48:31", "throughput": 1496.21, "total_tokens": 7076896} {"current_steps": 33540, "total_steps": 181800, "loss": 0.0352, "lr": 4.892077213613818e-05, "epoch": 3.68976897689769, "percentage": 18.45, "elapsed_time": "1:18:50", "remaining_time": "5:48:30", "throughput": 1496.21, "total_tokens": 7077920} {"current_steps": 33545, "total_steps": 181800, "loss": 0.0653, "lr": 4.892007445764058e-05, "epoch": 3.6903190319031904, "percentage": 18.45, "elapsed_time": "1:18:51", "remaining_time": "5:48:30", "throughput": 1496.21, "total_tokens": 7078944} {"current_steps": 33550, "total_steps": 181800, "loss": 0.0308, "lr": 4.891937655868313e-05, "epoch": 3.690869086908691, "percentage": 18.45, "elapsed_time": "1:18:51", "remaining_time": "5:48:29", "throughput": 1496.22, "total_tokens": 7080000} {"current_steps": 33555, "total_steps": 181800, "loss": 0.0476, "lr": 4.8918678439272265e-05, "epoch": 3.6914191419141913, "percentage": 18.46, "elapsed_time": "1:18:52", "remaining_time": "5:48:28", "throughput": 1496.21, "total_tokens": 7080992} {"current_steps": 33560, "total_steps": 181800, "loss": 0.1007, "lr": 4.891798009941442e-05, "epoch": 3.691969196919692, "percentage": 18.46, "elapsed_time": "1:18:53", "remaining_time": "5:48:27", "throughput": 1496.22, "total_tokens": 7082048} {"current_steps": 33565, "total_steps": 181800, "loss": 0.0813, "lr": 4.891728153911602e-05, "epoch": 3.6925192519251926, "percentage": 18.46, "elapsed_time": "1:18:53", "remaining_time": "5:48:26", "throughput": 1496.23, "total_tokens": 7083136} {"current_steps": 33570, "total_steps": 181800, "loss": 0.0972, "lr": 4.8916582758383525e-05, "epoch": 3.693069306930693, "percentage": 18.47, "elapsed_time": "1:18:54", "remaining_time": "5:48:26", "throughput": 1496.23, "total_tokens": 7084160} {"current_steps": 33575, "total_steps": 181800, "loss": 0.0025, "lr": 4.891588375722335e-05, "epoch": 3.693619361936194, "percentage": 18.47, "elapsed_time": "1:18:55", "remaining_time": "5:48:25", "throughput": 1496.23, "total_tokens": 7085184} {"current_steps": 33580, "total_steps": 181800, "loss": 0.0151, "lr": 4.8915184535641964e-05, "epoch": 3.694169416941694, "percentage": 18.47, "elapsed_time": "1:18:56", "remaining_time": "5:48:24", "throughput": 1496.23, "total_tokens": 7086240} {"current_steps": 33585, "total_steps": 181800, "loss": 0.0293, "lr": 4.891448509364579e-05, "epoch": 3.6947194719471947, "percentage": 18.47, "elapsed_time": "1:18:56", "remaining_time": "5:48:23", "throughput": 1496.22, "total_tokens": 7087232} {"current_steps": 33590, "total_steps": 181800, "loss": 0.0933, "lr": 4.8913785431241283e-05, "epoch": 3.6952695269526954, "percentage": 18.48, "elapsed_time": "1:18:57", "remaining_time": "5:48:23", "throughput": 1496.24, "total_tokens": 7088352} {"current_steps": 33595, "total_steps": 181800, "loss": 0.0799, "lr": 4.891308554843489e-05, "epoch": 3.6958195819581956, "percentage": 18.48, "elapsed_time": "1:18:58", "remaining_time": "5:48:22", "throughput": 1496.23, "total_tokens": 7089312} {"current_steps": 33600, "total_steps": 181800, "loss": 0.0118, "lr": 4.8912385445233065e-05, "epoch": 3.6963696369636962, "percentage": 18.48, "elapsed_time": "1:18:58", "remaining_time": "5:48:21", "throughput": 1496.21, "total_tokens": 7090272} {"current_steps": 33605, "total_steps": 181800, "loss": 0.014, "lr": 4.891168512164225e-05, "epoch": 3.696919691969197, "percentage": 18.48, "elapsed_time": "1:18:59", "remaining_time": "5:48:20", "throughput": 1496.24, "total_tokens": 7091424} {"current_steps": 33610, "total_steps": 181800, "loss": 0.0595, "lr": 4.891098457766892e-05, "epoch": 3.6974697469746975, "percentage": 18.49, "elapsed_time": "1:19:00", "remaining_time": "5:48:20", "throughput": 1496.25, "total_tokens": 7092512} {"current_steps": 33615, "total_steps": 181800, "loss": 0.0347, "lr": 4.891028381331951e-05, "epoch": 3.698019801980198, "percentage": 18.49, "elapsed_time": "1:19:00", "remaining_time": "5:48:19", "throughput": 1496.25, "total_tokens": 7093536} {"current_steps": 33620, "total_steps": 181800, "loss": 0.0394, "lr": 4.890958282860049e-05, "epoch": 3.6985698569856984, "percentage": 18.49, "elapsed_time": "1:19:01", "remaining_time": "5:48:18", "throughput": 1496.24, "total_tokens": 7094560} {"current_steps": 33625, "total_steps": 181800, "loss": 0.0307, "lr": 4.890888162351831e-05, "epoch": 3.699119911991199, "percentage": 18.5, "elapsed_time": "1:19:02", "remaining_time": "5:48:17", "throughput": 1496.25, "total_tokens": 7095616} {"current_steps": 33630, "total_steps": 181800, "loss": 0.0197, "lr": 4.890818019807945e-05, "epoch": 3.6996699669966997, "percentage": 18.5, "elapsed_time": "1:19:02", "remaining_time": "5:48:16", "throughput": 1496.26, "total_tokens": 7096704} {"current_steps": 33635, "total_steps": 181800, "loss": 0.0802, "lr": 4.890747855229036e-05, "epoch": 3.7002200220022003, "percentage": 18.5, "elapsed_time": "1:19:03", "remaining_time": "5:48:16", "throughput": 1496.29, "total_tokens": 7097856} {"current_steps": 33640, "total_steps": 181800, "loss": 0.1205, "lr": 4.8906776686157516e-05, "epoch": 3.700770077007701, "percentage": 18.5, "elapsed_time": "1:19:04", "remaining_time": "5:48:15", "throughput": 1496.3, "total_tokens": 7098944} {"current_steps": 33645, "total_steps": 181800, "loss": 0.0244, "lr": 4.8906074599687385e-05, "epoch": 3.701320132013201, "percentage": 18.51, "elapsed_time": "1:19:05", "remaining_time": "5:48:14", "throughput": 1496.3, "total_tokens": 7100000} {"current_steps": 33650, "total_steps": 181800, "loss": 0.0193, "lr": 4.8905372292886434e-05, "epoch": 3.701870187018702, "percentage": 18.51, "elapsed_time": "1:19:05", "remaining_time": "5:48:13", "throughput": 1496.3, "total_tokens": 7101024} {"current_steps": 33655, "total_steps": 181800, "loss": 0.1252, "lr": 4.8904669765761133e-05, "epoch": 3.7024202420242025, "percentage": 18.51, "elapsed_time": "1:19:06", "remaining_time": "5:48:13", "throughput": 1496.31, "total_tokens": 7102080} {"current_steps": 33660, "total_steps": 181800, "loss": 0.0799, "lr": 4.890396701831796e-05, "epoch": 3.7029702970297027, "percentage": 18.51, "elapsed_time": "1:19:07", "remaining_time": "5:48:12", "throughput": 1496.31, "total_tokens": 7103104} {"current_steps": 33665, "total_steps": 181800, "loss": 0.1165, "lr": 4.89032640505634e-05, "epoch": 3.7035203520352034, "percentage": 18.52, "elapsed_time": "1:19:07", "remaining_time": "5:48:11", "throughput": 1496.33, "total_tokens": 7104224} {"current_steps": 33670, "total_steps": 181800, "loss": 0.0681, "lr": 4.890256086250393e-05, "epoch": 3.704070407040704, "percentage": 18.52, "elapsed_time": "1:19:08", "remaining_time": "5:48:10", "throughput": 1496.32, "total_tokens": 7105216} {"current_steps": 33675, "total_steps": 181800, "loss": 0.123, "lr": 4.8901857454146014e-05, "epoch": 3.7046204620462047, "percentage": 18.52, "elapsed_time": "1:19:09", "remaining_time": "5:48:09", "throughput": 1496.32, "total_tokens": 7106272} {"current_steps": 33680, "total_steps": 181800, "loss": 0.1475, "lr": 4.8901153825496155e-05, "epoch": 3.7051705170517053, "percentage": 18.53, "elapsed_time": "1:19:09", "remaining_time": "5:48:09", "throughput": 1496.31, "total_tokens": 7107264} {"current_steps": 33685, "total_steps": 181800, "loss": 0.0279, "lr": 4.890044997656082e-05, "epoch": 3.7057205720572055, "percentage": 18.53, "elapsed_time": "1:19:10", "remaining_time": "5:48:08", "throughput": 1496.32, "total_tokens": 7108320} {"current_steps": 33690, "total_steps": 181800, "loss": 0.0679, "lr": 4.8899745907346516e-05, "epoch": 3.706270627062706, "percentage": 18.53, "elapsed_time": "1:19:11", "remaining_time": "5:48:07", "throughput": 1496.32, "total_tokens": 7109376} {"current_steps": 33695, "total_steps": 181800, "loss": 0.0709, "lr": 4.889904161785972e-05, "epoch": 3.706820682068207, "percentage": 18.53, "elapsed_time": "1:19:11", "remaining_time": "5:48:06", "throughput": 1496.33, "total_tokens": 7110464} {"current_steps": 33700, "total_steps": 181800, "loss": 0.0285, "lr": 4.889833710810693e-05, "epoch": 3.7073707370737075, "percentage": 18.54, "elapsed_time": "1:19:12", "remaining_time": "5:48:06", "throughput": 1496.34, "total_tokens": 7111520} {"current_steps": 33705, "total_steps": 181800, "loss": 0.0952, "lr": 4.889763237809463e-05, "epoch": 3.707920792079208, "percentage": 18.54, "elapsed_time": "1:19:13", "remaining_time": "5:48:05", "throughput": 1496.33, "total_tokens": 7112544} {"current_steps": 33710, "total_steps": 181800, "loss": 0.0199, "lr": 4.889692742782932e-05, "epoch": 3.7084708470847083, "percentage": 18.54, "elapsed_time": "1:19:14", "remaining_time": "5:48:04", "throughput": 1496.35, "total_tokens": 7113632} {"current_steps": 33715, "total_steps": 181800, "loss": 0.0413, "lr": 4.889622225731749e-05, "epoch": 3.709020902090209, "percentage": 18.55, "elapsed_time": "1:19:14", "remaining_time": "5:48:03", "throughput": 1496.36, "total_tokens": 7114720} {"current_steps": 33720, "total_steps": 181800, "loss": 0.0606, "lr": 4.889551686656565e-05, "epoch": 3.7095709570957096, "percentage": 18.55, "elapsed_time": "1:19:15", "remaining_time": "5:48:03", "throughput": 1496.36, "total_tokens": 7115744} {"current_steps": 33725, "total_steps": 181800, "loss": 0.0618, "lr": 4.88948112555803e-05, "epoch": 3.7101210121012103, "percentage": 18.55, "elapsed_time": "1:19:16", "remaining_time": "5:48:02", "throughput": 1496.36, "total_tokens": 7116800} {"current_steps": 33730, "total_steps": 181800, "loss": 0.0556, "lr": 4.889410542436794e-05, "epoch": 3.710671067106711, "percentage": 18.55, "elapsed_time": "1:19:16", "remaining_time": "5:48:01", "throughput": 1496.36, "total_tokens": 7117824} {"current_steps": 33735, "total_steps": 181800, "loss": 0.0134, "lr": 4.889339937293508e-05, "epoch": 3.711221122112211, "percentage": 18.56, "elapsed_time": "1:19:17", "remaining_time": "5:48:00", "throughput": 1496.36, "total_tokens": 7118880} {"current_steps": 33740, "total_steps": 181800, "loss": 0.0515, "lr": 4.8892693101288215e-05, "epoch": 3.7117711771177118, "percentage": 18.56, "elapsed_time": "1:19:18", "remaining_time": "5:48:00", "throughput": 1496.37, "total_tokens": 7119936} {"current_steps": 33745, "total_steps": 181800, "loss": 0.1094, "lr": 4.8891986609433863e-05, "epoch": 3.7123212321232124, "percentage": 18.56, "elapsed_time": "1:19:18", "remaining_time": "5:47:59", "throughput": 1496.38, "total_tokens": 7121056} {"current_steps": 33750, "total_steps": 181800, "loss": 0.0608, "lr": 4.889127989737854e-05, "epoch": 3.7128712871287126, "percentage": 18.56, "elapsed_time": "1:19:19", "remaining_time": "5:47:58", "throughput": 1496.38, "total_tokens": 7122080} {"current_steps": 33755, "total_steps": 181800, "loss": 0.0629, "lr": 4.889057296512875e-05, "epoch": 3.7134213421342133, "percentage": 18.57, "elapsed_time": "1:19:20", "remaining_time": "5:47:57", "throughput": 1496.37, "total_tokens": 7123072} {"current_steps": 33760, "total_steps": 181800, "loss": 0.0178, "lr": 4.888986581269102e-05, "epoch": 3.713971397139714, "percentage": 18.57, "elapsed_time": "1:19:20", "remaining_time": "5:47:56", "throughput": 1496.37, "total_tokens": 7124096} {"current_steps": 33765, "total_steps": 181800, "loss": 0.0672, "lr": 4.888915844007185e-05, "epoch": 3.7145214521452146, "percentage": 18.57, "elapsed_time": "1:19:21", "remaining_time": "5:47:56", "throughput": 1496.38, "total_tokens": 7125184} {"current_steps": 33770, "total_steps": 181800, "loss": 0.0331, "lr": 4.8888450847277775e-05, "epoch": 3.715071507150715, "percentage": 18.58, "elapsed_time": "1:19:22", "remaining_time": "5:47:55", "throughput": 1496.39, "total_tokens": 7126240} {"current_steps": 33775, "total_steps": 181800, "loss": 0.0679, "lr": 4.888774303431531e-05, "epoch": 3.7156215621562154, "percentage": 18.58, "elapsed_time": "1:19:22", "remaining_time": "5:47:54", "throughput": 1496.39, "total_tokens": 7127296} {"current_steps": 33780, "total_steps": 181800, "loss": 0.1331, "lr": 4.8887035001190986e-05, "epoch": 3.716171617161716, "percentage": 18.58, "elapsed_time": "1:19:23", "remaining_time": "5:47:53", "throughput": 1496.4, "total_tokens": 7128352} {"current_steps": 33785, "total_steps": 181800, "loss": 0.0846, "lr": 4.888632674791131e-05, "epoch": 3.7167216721672167, "percentage": 18.58, "elapsed_time": "1:19:24", "remaining_time": "5:47:53", "throughput": 1496.4, "total_tokens": 7129376} {"current_steps": 33790, "total_steps": 181800, "loss": 0.0202, "lr": 4.888561827448284e-05, "epoch": 3.7172717271727174, "percentage": 18.59, "elapsed_time": "1:19:25", "remaining_time": "5:47:52", "throughput": 1496.4, "total_tokens": 7130432} {"current_steps": 33795, "total_steps": 181800, "loss": 0.109, "lr": 4.8884909580912076e-05, "epoch": 3.717821782178218, "percentage": 18.59, "elapsed_time": "1:19:25", "remaining_time": "5:47:51", "throughput": 1496.41, "total_tokens": 7131520} {"current_steps": 33800, "total_steps": 181800, "loss": 0.047, "lr": 4.888420066720556e-05, "epoch": 3.718371837183718, "percentage": 18.59, "elapsed_time": "1:19:26", "remaining_time": "5:47:50", "throughput": 1496.43, "total_tokens": 7132608} {"current_steps": 33805, "total_steps": 181800, "loss": 0.0198, "lr": 4.888349153336983e-05, "epoch": 3.718921892189219, "percentage": 18.59, "elapsed_time": "1:19:27", "remaining_time": "5:47:49", "throughput": 1496.41, "total_tokens": 7133568} {"current_steps": 33810, "total_steps": 181800, "loss": 0.1172, "lr": 4.888278217941142e-05, "epoch": 3.7194719471947195, "percentage": 18.6, "elapsed_time": "1:19:27", "remaining_time": "5:47:49", "throughput": 1496.41, "total_tokens": 7134592} {"current_steps": 33815, "total_steps": 181800, "loss": 0.0366, "lr": 4.888207260533687e-05, "epoch": 3.72002200220022, "percentage": 18.6, "elapsed_time": "1:19:28", "remaining_time": "5:47:48", "throughput": 1496.4, "total_tokens": 7135584} {"current_steps": 33820, "total_steps": 181800, "loss": 0.0907, "lr": 4.888136281115271e-05, "epoch": 3.720572057205721, "percentage": 18.6, "elapsed_time": "1:19:29", "remaining_time": "5:47:47", "throughput": 1496.4, "total_tokens": 7136640} {"current_steps": 33825, "total_steps": 181800, "loss": 0.0251, "lr": 4.8880652796865486e-05, "epoch": 3.721122112211221, "percentage": 18.61, "elapsed_time": "1:19:29", "remaining_time": "5:47:46", "throughput": 1496.41, "total_tokens": 7137696} {"current_steps": 33830, "total_steps": 181800, "loss": 0.0076, "lr": 4.887994256248175e-05, "epoch": 3.7216721672167217, "percentage": 18.61, "elapsed_time": "1:19:30", "remaining_time": "5:47:46", "throughput": 1496.41, "total_tokens": 7138752} {"current_steps": 33835, "total_steps": 181800, "loss": 0.0293, "lr": 4.887923210800804e-05, "epoch": 3.7222222222222223, "percentage": 18.61, "elapsed_time": "1:19:31", "remaining_time": "5:47:45", "throughput": 1496.42, "total_tokens": 7139840} {"current_steps": 33840, "total_steps": 181800, "loss": 0.0332, "lr": 4.887852143345091e-05, "epoch": 3.7227722772277225, "percentage": 18.61, "elapsed_time": "1:19:31", "remaining_time": "5:47:44", "throughput": 1496.42, "total_tokens": 7140832} {"current_steps": 33845, "total_steps": 181800, "loss": 0.1004, "lr": 4.8877810538816905e-05, "epoch": 3.723322332233223, "percentage": 18.62, "elapsed_time": "1:19:32", "remaining_time": "5:47:43", "throughput": 1496.41, "total_tokens": 7141824} {"current_steps": 33850, "total_steps": 181800, "loss": 0.021, "lr": 4.887709942411257e-05, "epoch": 3.723872387238724, "percentage": 18.62, "elapsed_time": "1:19:33", "remaining_time": "5:47:43", "throughput": 1496.41, "total_tokens": 7142880} {"current_steps": 33855, "total_steps": 181800, "loss": 0.0966, "lr": 4.887638808934447e-05, "epoch": 3.7244224422442245, "percentage": 18.62, "elapsed_time": "1:19:34", "remaining_time": "5:47:42", "throughput": 1496.43, "total_tokens": 7144000} {"current_steps": 33860, "total_steps": 181800, "loss": 0.0564, "lr": 4.8875676534519164e-05, "epoch": 3.724972497249725, "percentage": 18.62, "elapsed_time": "1:19:34", "remaining_time": "5:47:41", "throughput": 1496.46, "total_tokens": 7145152} {"current_steps": 33865, "total_steps": 181800, "loss": 0.0635, "lr": 4.8874964759643207e-05, "epoch": 3.7255225522552253, "percentage": 18.63, "elapsed_time": "1:19:35", "remaining_time": "5:47:40", "throughput": 1496.46, "total_tokens": 7146176} {"current_steps": 33870, "total_steps": 181800, "loss": 0.0636, "lr": 4.887425276472315e-05, "epoch": 3.726072607260726, "percentage": 18.63, "elapsed_time": "1:19:36", "remaining_time": "5:47:39", "throughput": 1496.45, "total_tokens": 7147200} {"current_steps": 33875, "total_steps": 181800, "loss": 0.01, "lr": 4.8873540549765564e-05, "epoch": 3.7266226622662266, "percentage": 18.63, "elapsed_time": "1:19:36", "remaining_time": "5:47:39", "throughput": 1496.46, "total_tokens": 7148256} {"current_steps": 33880, "total_steps": 181800, "loss": 0.031, "lr": 4.8872828114777004e-05, "epoch": 3.7271727172717273, "percentage": 18.64, "elapsed_time": "1:19:37", "remaining_time": "5:47:38", "throughput": 1496.49, "total_tokens": 7149408} {"current_steps": 33885, "total_steps": 181800, "loss": 0.0195, "lr": 4.8872115459764046e-05, "epoch": 3.727722772277228, "percentage": 18.64, "elapsed_time": "1:19:38", "remaining_time": "5:47:37", "throughput": 1496.48, "total_tokens": 7150432} {"current_steps": 33890, "total_steps": 181800, "loss": 0.0261, "lr": 4.887140258473325e-05, "epoch": 3.728272827282728, "percentage": 18.64, "elapsed_time": "1:19:38", "remaining_time": "5:47:36", "throughput": 1496.48, "total_tokens": 7151456} {"current_steps": 33895, "total_steps": 181800, "loss": 0.0781, "lr": 4.88706894896912e-05, "epoch": 3.728822882288229, "percentage": 18.64, "elapsed_time": "1:19:39", "remaining_time": "5:47:36", "throughput": 1496.49, "total_tokens": 7152544} {"current_steps": 33900, "total_steps": 181800, "loss": 0.0389, "lr": 4.886997617464446e-05, "epoch": 3.7293729372937294, "percentage": 18.65, "elapsed_time": "1:19:40", "remaining_time": "5:47:35", "throughput": 1496.49, "total_tokens": 7153568} {"current_steps": 33905, "total_steps": 181800, "loss": 0.097, "lr": 4.886926263959959e-05, "epoch": 3.72992299229923, "percentage": 18.65, "elapsed_time": "1:19:40", "remaining_time": "5:47:34", "throughput": 1496.49, "total_tokens": 7154560} {"current_steps": 33910, "total_steps": 181800, "loss": 0.028, "lr": 4.8868548884563194e-05, "epoch": 3.7304730473047307, "percentage": 18.65, "elapsed_time": "1:19:41", "remaining_time": "5:47:33", "throughput": 1496.48, "total_tokens": 7155584} {"current_steps": 33915, "total_steps": 181800, "loss": 0.0588, "lr": 4.886783490954183e-05, "epoch": 3.731023102310231, "percentage": 18.66, "elapsed_time": "1:19:42", "remaining_time": "5:47:32", "throughput": 1496.48, "total_tokens": 7156608} {"current_steps": 33920, "total_steps": 181800, "loss": 0.0072, "lr": 4.886712071454208e-05, "epoch": 3.7315731573157316, "percentage": 18.66, "elapsed_time": "1:19:42", "remaining_time": "5:47:32", "throughput": 1496.49, "total_tokens": 7157696} {"current_steps": 33925, "total_steps": 181800, "loss": 0.0526, "lr": 4.886640629957054e-05, "epoch": 3.7321232123212322, "percentage": 18.66, "elapsed_time": "1:19:43", "remaining_time": "5:47:31", "throughput": 1496.5, "total_tokens": 7158752} {"current_steps": 33930, "total_steps": 181800, "loss": 0.034, "lr": 4.8865691664633785e-05, "epoch": 3.7326732673267324, "percentage": 18.66, "elapsed_time": "1:19:44", "remaining_time": "5:47:30", "throughput": 1496.5, "total_tokens": 7159776} {"current_steps": 33935, "total_steps": 181800, "loss": 0.0043, "lr": 4.886497680973839e-05, "epoch": 3.733223322332233, "percentage": 18.67, "elapsed_time": "1:19:45", "remaining_time": "5:47:29", "throughput": 1496.51, "total_tokens": 7160864} {"current_steps": 33940, "total_steps": 181800, "loss": 0.0081, "lr": 4.886426173489097e-05, "epoch": 3.7337733773377337, "percentage": 18.67, "elapsed_time": "1:19:45", "remaining_time": "5:47:29", "throughput": 1496.53, "total_tokens": 7161984} {"current_steps": 33945, "total_steps": 181800, "loss": 0.0036, "lr": 4.8863546440098095e-05, "epoch": 3.7343234323432344, "percentage": 18.67, "elapsed_time": "1:19:46", "remaining_time": "5:47:28", "throughput": 1496.52, "total_tokens": 7163008} {"current_steps": 33950, "total_steps": 181800, "loss": 0.0626, "lr": 4.886283092536636e-05, "epoch": 3.734873487348735, "percentage": 18.67, "elapsed_time": "1:19:47", "remaining_time": "5:47:27", "throughput": 1496.52, "total_tokens": 7164000} {"current_steps": 33955, "total_steps": 181800, "loss": 0.0418, "lr": 4.886211519070237e-05, "epoch": 3.7354235423542352, "percentage": 18.68, "elapsed_time": "1:19:47", "remaining_time": "5:47:26", "throughput": 1496.53, "total_tokens": 7165088} {"current_steps": 33960, "total_steps": 181800, "loss": 0.0083, "lr": 4.88613992361127e-05, "epoch": 3.735973597359736, "percentage": 18.68, "elapsed_time": "1:19:48", "remaining_time": "5:47:26", "throughput": 1496.52, "total_tokens": 7166112} {"current_steps": 33965, "total_steps": 181800, "loss": 0.0256, "lr": 4.8860683061603986e-05, "epoch": 3.7365236523652365, "percentage": 18.68, "elapsed_time": "1:19:49", "remaining_time": "5:47:25", "throughput": 1496.52, "total_tokens": 7167136} {"current_steps": 33970, "total_steps": 181800, "loss": 0.0151, "lr": 4.885996666718279e-05, "epoch": 3.737073707370737, "percentage": 18.69, "elapsed_time": "1:19:49", "remaining_time": "5:47:24", "throughput": 1496.53, "total_tokens": 7168192} {"current_steps": 33975, "total_steps": 181800, "loss": 0.0754, "lr": 4.8859250052855735e-05, "epoch": 3.737623762376238, "percentage": 18.69, "elapsed_time": "1:19:50", "remaining_time": "5:47:23", "throughput": 1496.54, "total_tokens": 7169280} {"current_steps": 33980, "total_steps": 181800, "loss": 0.0133, "lr": 4.885853321862941e-05, "epoch": 3.738173817381738, "percentage": 18.69, "elapsed_time": "1:19:51", "remaining_time": "5:47:22", "throughput": 1496.54, "total_tokens": 7170304} {"current_steps": 33985, "total_steps": 181800, "loss": 0.1391, "lr": 4.885781616451045e-05, "epoch": 3.7387238723872387, "percentage": 18.69, "elapsed_time": "1:19:51", "remaining_time": "5:47:22", "throughput": 1496.53, "total_tokens": 7171296} {"current_steps": 33990, "total_steps": 181800, "loss": 0.0219, "lr": 4.8857098890505434e-05, "epoch": 3.7392739273927393, "percentage": 18.7, "elapsed_time": "1:19:52", "remaining_time": "5:47:21", "throughput": 1496.55, "total_tokens": 7172416} {"current_steps": 33995, "total_steps": 181800, "loss": 0.0776, "lr": 4.885638139662099e-05, "epoch": 3.73982398239824, "percentage": 18.7, "elapsed_time": "1:19:53", "remaining_time": "5:47:20", "throughput": 1496.55, "total_tokens": 7173440} {"current_steps": 34000, "total_steps": 181800, "loss": 0.0398, "lr": 4.885566368286373e-05, "epoch": 3.7403740374037406, "percentage": 18.7, "elapsed_time": "1:19:54", "remaining_time": "5:47:19", "throughput": 1496.56, "total_tokens": 7174528} {"current_steps": 34005, "total_steps": 181800, "loss": 0.0277, "lr": 4.885494574924026e-05, "epoch": 3.740924092409241, "percentage": 18.7, "elapsed_time": "1:19:54", "remaining_time": "5:47:19", "throughput": 1496.56, "total_tokens": 7175584} {"current_steps": 34010, "total_steps": 181800, "loss": 0.0353, "lr": 4.88542275957572e-05, "epoch": 3.7414741474147415, "percentage": 18.71, "elapsed_time": "1:19:55", "remaining_time": "5:47:18", "throughput": 1496.59, "total_tokens": 7176736} {"current_steps": 34015, "total_steps": 181800, "loss": 0.0566, "lr": 4.8853509222421176e-05, "epoch": 3.742024202420242, "percentage": 18.71, "elapsed_time": "1:19:56", "remaining_time": "5:47:17", "throughput": 1496.58, "total_tokens": 7177728} {"current_steps": 34020, "total_steps": 181800, "loss": 0.2071, "lr": 4.88527906292388e-05, "epoch": 3.7425742574257423, "percentage": 18.71, "elapsed_time": "1:19:56", "remaining_time": "5:47:16", "throughput": 1496.58, "total_tokens": 7178752} {"current_steps": 34025, "total_steps": 181800, "loss": 0.0188, "lr": 4.8852071816216696e-05, "epoch": 3.743124312431243, "percentage": 18.72, "elapsed_time": "1:19:57", "remaining_time": "5:47:15", "throughput": 1496.59, "total_tokens": 7179840} {"current_steps": 34030, "total_steps": 181800, "loss": 0.0717, "lr": 4.88513527833615e-05, "epoch": 3.7436743674367436, "percentage": 18.72, "elapsed_time": "1:19:58", "remaining_time": "5:47:15", "throughput": 1496.6, "total_tokens": 7180928} {"current_steps": 34035, "total_steps": 181800, "loss": 0.0324, "lr": 4.885063353067982e-05, "epoch": 3.7442244224422443, "percentage": 18.72, "elapsed_time": "1:19:58", "remaining_time": "5:47:14", "throughput": 1496.6, "total_tokens": 7181920} {"current_steps": 34040, "total_steps": 181800, "loss": 0.1981, "lr": 4.88499140581783e-05, "epoch": 3.744774477447745, "percentage": 18.72, "elapsed_time": "1:19:59", "remaining_time": "5:47:13", "throughput": 1496.6, "total_tokens": 7182976} {"current_steps": 34045, "total_steps": 181800, "loss": 0.0385, "lr": 4.884919436586357e-05, "epoch": 3.745324532453245, "percentage": 18.73, "elapsed_time": "1:20:00", "remaining_time": "5:47:12", "throughput": 1496.61, "total_tokens": 7184064} {"current_steps": 34050, "total_steps": 181800, "loss": 0.2335, "lr": 4.8848474453742255e-05, "epoch": 3.745874587458746, "percentage": 18.73, "elapsed_time": "1:20:00", "remaining_time": "5:47:12", "throughput": 1496.61, "total_tokens": 7185120} {"current_steps": 34055, "total_steps": 181800, "loss": 0.0694, "lr": 4.884775432182099e-05, "epoch": 3.7464246424642464, "percentage": 18.73, "elapsed_time": "1:20:01", "remaining_time": "5:47:11", "throughput": 1496.62, "total_tokens": 7186176} {"current_steps": 34060, "total_steps": 181800, "loss": 0.01, "lr": 4.8847033970106427e-05, "epoch": 3.746974697469747, "percentage": 18.73, "elapsed_time": "1:20:02", "remaining_time": "5:47:10", "throughput": 1496.62, "total_tokens": 7187200} {"current_steps": 34065, "total_steps": 181800, "loss": 0.0993, "lr": 4.884631339860519e-05, "epoch": 3.7475247524752477, "percentage": 18.74, "elapsed_time": "1:20:02", "remaining_time": "5:47:09", "throughput": 1496.64, "total_tokens": 7188320} {"current_steps": 34070, "total_steps": 181800, "loss": 0.0091, "lr": 4.8845592607323935e-05, "epoch": 3.748074807480748, "percentage": 18.74, "elapsed_time": "1:20:03", "remaining_time": "5:47:09", "throughput": 1496.64, "total_tokens": 7189376} {"current_steps": 34075, "total_steps": 181800, "loss": 0.0433, "lr": 4.8844871596269275e-05, "epoch": 3.7486248624862486, "percentage": 18.74, "elapsed_time": "1:20:04", "remaining_time": "5:47:08", "throughput": 1496.63, "total_tokens": 7190400} {"current_steps": 34080, "total_steps": 181800, "loss": 0.236, "lr": 4.8844150365447885e-05, "epoch": 3.7491749174917492, "percentage": 18.75, "elapsed_time": "1:20:05", "remaining_time": "5:47:07", "throughput": 1496.64, "total_tokens": 7191488} {"current_steps": 34085, "total_steps": 181800, "loss": 0.0194, "lr": 4.8843428914866406e-05, "epoch": 3.7497249724972495, "percentage": 18.75, "elapsed_time": "1:20:05", "remaining_time": "5:47:06", "throughput": 1496.66, "total_tokens": 7192576} {"current_steps": 34090, "total_steps": 181800, "loss": 0.0456, "lr": 4.8842707244531485e-05, "epoch": 3.7502750275027505, "percentage": 18.75, "elapsed_time": "1:20:06", "remaining_time": "5:47:06", "throughput": 1496.66, "total_tokens": 7193632} {"current_steps": 34095, "total_steps": 181800, "loss": 0.0807, "lr": 4.884198535444976e-05, "epoch": 3.7508250825082508, "percentage": 18.75, "elapsed_time": "1:20:07", "remaining_time": "5:47:05", "throughput": 1496.66, "total_tokens": 7194656} {"current_steps": 34100, "total_steps": 181800, "loss": 0.0201, "lr": 4.884126324462791e-05, "epoch": 3.7513751375137514, "percentage": 18.76, "elapsed_time": "1:20:07", "remaining_time": "5:47:04", "throughput": 1496.68, "total_tokens": 7195776} {"current_steps": 34105, "total_steps": 181800, "loss": 0.022, "lr": 4.8840540915072573e-05, "epoch": 3.751925192519252, "percentage": 18.76, "elapsed_time": "1:20:08", "remaining_time": "5:47:03", "throughput": 1496.69, "total_tokens": 7196864} {"current_steps": 34110, "total_steps": 181800, "loss": 0.1682, "lr": 4.883981836579041e-05, "epoch": 3.7524752475247523, "percentage": 18.76, "elapsed_time": "1:20:09", "remaining_time": "5:47:02", "throughput": 1496.68, "total_tokens": 7197856} {"current_steps": 34115, "total_steps": 181800, "loss": 0.0204, "lr": 4.883909559678808e-05, "epoch": 3.753025302530253, "percentage": 18.77, "elapsed_time": "1:20:09", "remaining_time": "5:47:02", "throughput": 1496.68, "total_tokens": 7198880} {"current_steps": 34120, "total_steps": 181800, "loss": 0.0376, "lr": 4.883837260807224e-05, "epoch": 3.7535753575357536, "percentage": 18.77, "elapsed_time": "1:20:10", "remaining_time": "5:47:01", "throughput": 1496.7, "total_tokens": 7200032} {"current_steps": 34125, "total_steps": 181800, "loss": 0.0206, "lr": 4.883764939964957e-05, "epoch": 3.754125412541254, "percentage": 18.77, "elapsed_time": "1:20:11", "remaining_time": "5:47:00", "throughput": 1496.69, "total_tokens": 7200992} {"current_steps": 34130, "total_steps": 181800, "loss": 0.0997, "lr": 4.8836925971526714e-05, "epoch": 3.754675467546755, "percentage": 18.77, "elapsed_time": "1:20:11", "remaining_time": "5:46:59", "throughput": 1496.69, "total_tokens": 7202016} {"current_steps": 34135, "total_steps": 181800, "loss": 0.0224, "lr": 4.883620232371035e-05, "epoch": 3.755225522552255, "percentage": 18.78, "elapsed_time": "1:20:12", "remaining_time": "5:46:59", "throughput": 1496.69, "total_tokens": 7203072} {"current_steps": 34140, "total_steps": 181800, "loss": 0.0568, "lr": 4.883547845620715e-05, "epoch": 3.7557755775577557, "percentage": 18.78, "elapsed_time": "1:20:13", "remaining_time": "5:46:58", "throughput": 1496.7, "total_tokens": 7204160} {"current_steps": 34145, "total_steps": 181800, "loss": 0.0726, "lr": 4.8834754369023784e-05, "epoch": 3.7563256325632564, "percentage": 18.78, "elapsed_time": "1:20:14", "remaining_time": "5:46:57", "throughput": 1496.72, "total_tokens": 7205280} {"current_steps": 34150, "total_steps": 181800, "loss": 0.0305, "lr": 4.883403006216692e-05, "epoch": 3.756875687568757, "percentage": 18.78, "elapsed_time": "1:20:14", "remaining_time": "5:46:56", "throughput": 1496.71, "total_tokens": 7206272} {"current_steps": 34155, "total_steps": 181800, "loss": 0.0346, "lr": 4.883330553564324e-05, "epoch": 3.7574257425742577, "percentage": 18.79, "elapsed_time": "1:20:15", "remaining_time": "5:46:56", "throughput": 1496.72, "total_tokens": 7207360} {"current_steps": 34160, "total_steps": 181800, "loss": 0.0144, "lr": 4.8832580789459416e-05, "epoch": 3.757975797579758, "percentage": 18.79, "elapsed_time": "1:20:16", "remaining_time": "5:46:55", "throughput": 1496.75, "total_tokens": 7208544} {"current_steps": 34165, "total_steps": 181800, "loss": 0.0544, "lr": 4.8831855823622135e-05, "epoch": 3.7585258525852585, "percentage": 18.79, "elapsed_time": "1:20:16", "remaining_time": "5:46:54", "throughput": 1496.78, "total_tokens": 7209696} {"current_steps": 34170, "total_steps": 181800, "loss": 0.0381, "lr": 4.883113063813807e-05, "epoch": 3.759075907590759, "percentage": 18.8, "elapsed_time": "1:20:17", "remaining_time": "5:46:53", "throughput": 1496.77, "total_tokens": 7210688} {"current_steps": 34175, "total_steps": 181800, "loss": 0.0336, "lr": 4.883040523301392e-05, "epoch": 3.7596259625962594, "percentage": 18.8, "elapsed_time": "1:20:18", "remaining_time": "5:46:52", "throughput": 1496.77, "total_tokens": 7211712} {"current_steps": 34180, "total_steps": 181800, "loss": 0.0663, "lr": 4.8829679608256345e-05, "epoch": 3.76017601760176, "percentage": 18.8, "elapsed_time": "1:20:18", "remaining_time": "5:46:52", "throughput": 1496.78, "total_tokens": 7212768} {"current_steps": 34185, "total_steps": 181800, "loss": 0.0297, "lr": 4.882895376387205e-05, "epoch": 3.7607260726072607, "percentage": 18.8, "elapsed_time": "1:20:19", "remaining_time": "5:46:51", "throughput": 1496.77, "total_tokens": 7213760} {"current_steps": 34190, "total_steps": 181800, "loss": 0.0539, "lr": 4.882822769986774e-05, "epoch": 3.7612761276127613, "percentage": 18.81, "elapsed_time": "1:20:20", "remaining_time": "5:46:50", "throughput": 1496.78, "total_tokens": 7214848} {"current_steps": 34195, "total_steps": 181800, "loss": 0.1274, "lr": 4.8827501416250065e-05, "epoch": 3.761826182618262, "percentage": 18.81, "elapsed_time": "1:20:20", "remaining_time": "5:46:49", "throughput": 1496.78, "total_tokens": 7215872} {"current_steps": 34200, "total_steps": 181800, "loss": 0.0605, "lr": 4.882677491302576e-05, "epoch": 3.762376237623762, "percentage": 18.81, "elapsed_time": "1:20:21", "remaining_time": "5:46:49", "throughput": 1496.77, "total_tokens": 7216864} {"current_steps": 34205, "total_steps": 181800, "loss": 0.1471, "lr": 4.882604819020149e-05, "epoch": 3.762926292629263, "percentage": 18.81, "elapsed_time": "1:20:22", "remaining_time": "5:46:48", "throughput": 1496.77, "total_tokens": 7217920} {"current_steps": 34210, "total_steps": 181800, "loss": 0.1043, "lr": 4.8825321247783984e-05, "epoch": 3.7634763476347635, "percentage": 18.82, "elapsed_time": "1:20:23", "remaining_time": "5:46:47", "throughput": 1496.77, "total_tokens": 7218944} {"current_steps": 34215, "total_steps": 181800, "loss": 0.0094, "lr": 4.882459408577991e-05, "epoch": 3.764026402640264, "percentage": 18.82, "elapsed_time": "1:20:23", "remaining_time": "5:46:46", "throughput": 1496.76, "total_tokens": 7219936} {"current_steps": 34220, "total_steps": 181800, "loss": 0.0499, "lr": 4.882386670419599e-05, "epoch": 3.7645764576457648, "percentage": 18.82, "elapsed_time": "1:20:24", "remaining_time": "5:46:46", "throughput": 1496.76, "total_tokens": 7220960} {"current_steps": 34225, "total_steps": 181800, "loss": 0.0328, "lr": 4.8823139103038926e-05, "epoch": 3.765126512651265, "percentage": 18.83, "elapsed_time": "1:20:25", "remaining_time": "5:46:45", "throughput": 1496.75, "total_tokens": 7221920} {"current_steps": 34230, "total_steps": 181800, "loss": 0.0923, "lr": 4.8822411282315416e-05, "epoch": 3.7656765676567656, "percentage": 18.83, "elapsed_time": "1:20:25", "remaining_time": "5:46:44", "throughput": 1496.75, "total_tokens": 7222944} {"current_steps": 34235, "total_steps": 181800, "loss": 0.0045, "lr": 4.882168324203217e-05, "epoch": 3.7662266226622663, "percentage": 18.83, "elapsed_time": "1:20:26", "remaining_time": "5:46:43", "throughput": 1496.76, "total_tokens": 7224032} {"current_steps": 34240, "total_steps": 181800, "loss": 0.1108, "lr": 4.8820954982195905e-05, "epoch": 3.766776677667767, "percentage": 18.83, "elapsed_time": "1:20:27", "remaining_time": "5:46:42", "throughput": 1496.76, "total_tokens": 7225088} {"current_steps": 34245, "total_steps": 181800, "loss": 0.0242, "lr": 4.882022650281333e-05, "epoch": 3.7673267326732676, "percentage": 18.84, "elapsed_time": "1:20:27", "remaining_time": "5:46:42", "throughput": 1496.76, "total_tokens": 7226112} {"current_steps": 34250, "total_steps": 181800, "loss": 0.0765, "lr": 4.881949780389115e-05, "epoch": 3.7678767876787678, "percentage": 18.84, "elapsed_time": "1:20:28", "remaining_time": "5:46:41", "throughput": 1496.75, "total_tokens": 7227072} {"current_steps": 34255, "total_steps": 181800, "loss": 0.1228, "lr": 4.881876888543609e-05, "epoch": 3.7684268426842684, "percentage": 18.84, "elapsed_time": "1:20:29", "remaining_time": "5:46:40", "throughput": 1496.76, "total_tokens": 7228160} {"current_steps": 34260, "total_steps": 181800, "loss": 0.0423, "lr": 4.881803974745487e-05, "epoch": 3.768976897689769, "percentage": 18.84, "elapsed_time": "1:20:29", "remaining_time": "5:46:39", "throughput": 1496.76, "total_tokens": 7229216} {"current_steps": 34265, "total_steps": 181800, "loss": 0.0367, "lr": 4.881731038995421e-05, "epoch": 3.7695269526952693, "percentage": 18.85, "elapsed_time": "1:20:30", "remaining_time": "5:46:39", "throughput": 1496.76, "total_tokens": 7230240} {"current_steps": 34270, "total_steps": 181800, "loss": 0.0243, "lr": 4.881658081294082e-05, "epoch": 3.77007700770077, "percentage": 18.85, "elapsed_time": "1:20:31", "remaining_time": "5:46:38", "throughput": 1496.78, "total_tokens": 7231360} {"current_steps": 34275, "total_steps": 181800, "loss": 0.0321, "lr": 4.8815851016421435e-05, "epoch": 3.7706270627062706, "percentage": 18.85, "elapsed_time": "1:20:31", "remaining_time": "5:46:37", "throughput": 1496.79, "total_tokens": 7232448} {"current_steps": 34280, "total_steps": 181800, "loss": 0.0481, "lr": 4.8815121000402785e-05, "epoch": 3.771177117711771, "percentage": 18.86, "elapsed_time": "1:20:32", "remaining_time": "5:46:36", "throughput": 1496.79, "total_tokens": 7233472} {"current_steps": 34285, "total_steps": 181800, "loss": 0.0076, "lr": 4.8814390764891586e-05, "epoch": 3.771727172717272, "percentage": 18.86, "elapsed_time": "1:20:33", "remaining_time": "5:46:36", "throughput": 1496.8, "total_tokens": 7234560} {"current_steps": 34290, "total_steps": 181800, "loss": 0.071, "lr": 4.881366030989458e-05, "epoch": 3.772277227722772, "percentage": 18.86, "elapsed_time": "1:20:34", "remaining_time": "5:46:35", "throughput": 1496.8, "total_tokens": 7235616} {"current_steps": 34295, "total_steps": 181800, "loss": 0.0731, "lr": 4.881292963541849e-05, "epoch": 3.7728272827282727, "percentage": 18.86, "elapsed_time": "1:20:34", "remaining_time": "5:46:34", "throughput": 1496.82, "total_tokens": 7236736} {"current_steps": 34300, "total_steps": 181800, "loss": 0.0846, "lr": 4.881219874147006e-05, "epoch": 3.7733773377337734, "percentage": 18.87, "elapsed_time": "1:20:35", "remaining_time": "5:46:33", "throughput": 1496.82, "total_tokens": 7237760} {"current_steps": 34305, "total_steps": 181800, "loss": 0.0728, "lr": 4.8811467628056006e-05, "epoch": 3.773927392739274, "percentage": 18.87, "elapsed_time": "1:20:36", "remaining_time": "5:46:32", "throughput": 1496.82, "total_tokens": 7238784} {"current_steps": 34310, "total_steps": 181800, "loss": 0.0642, "lr": 4.8810736295183096e-05, "epoch": 3.7744774477447747, "percentage": 18.87, "elapsed_time": "1:20:36", "remaining_time": "5:46:32", "throughput": 1496.83, "total_tokens": 7239872} {"current_steps": 34315, "total_steps": 181800, "loss": 0.0112, "lr": 4.881000474285805e-05, "epoch": 3.775027502750275, "percentage": 18.88, "elapsed_time": "1:20:37", "remaining_time": "5:46:31", "throughput": 1496.84, "total_tokens": 7240928} {"current_steps": 34320, "total_steps": 181800, "loss": 0.0279, "lr": 4.8809272971087614e-05, "epoch": 3.7755775577557755, "percentage": 18.88, "elapsed_time": "1:20:38", "remaining_time": "5:46:30", "throughput": 1496.84, "total_tokens": 7241952} {"current_steps": 34325, "total_steps": 181800, "loss": 0.1312, "lr": 4.880854097987853e-05, "epoch": 3.776127612761276, "percentage": 18.88, "elapsed_time": "1:20:38", "remaining_time": "5:46:29", "throughput": 1496.85, "total_tokens": 7243040} {"current_steps": 34330, "total_steps": 181800, "loss": 0.054, "lr": 4.880780876923756e-05, "epoch": 3.776677667766777, "percentage": 18.88, "elapsed_time": "1:20:39", "remaining_time": "5:46:29", "throughput": 1496.85, "total_tokens": 7244064} {"current_steps": 34335, "total_steps": 181800, "loss": 0.1226, "lr": 4.880707633917143e-05, "epoch": 3.7772277227722775, "percentage": 18.89, "elapsed_time": "1:20:40", "remaining_time": "5:46:28", "throughput": 1496.84, "total_tokens": 7245088} {"current_steps": 34340, "total_steps": 181800, "loss": 0.056, "lr": 4.8806343689686906e-05, "epoch": 3.7777777777777777, "percentage": 18.89, "elapsed_time": "1:20:40", "remaining_time": "5:46:27", "throughput": 1496.84, "total_tokens": 7246112} {"current_steps": 34345, "total_steps": 181800, "loss": 0.0615, "lr": 4.8805610820790735e-05, "epoch": 3.7783278327832783, "percentage": 18.89, "elapsed_time": "1:20:41", "remaining_time": "5:46:26", "throughput": 1496.83, "total_tokens": 7247104} {"current_steps": 34350, "total_steps": 181800, "loss": 0.0292, "lr": 4.880487773248967e-05, "epoch": 3.778877887788779, "percentage": 18.89, "elapsed_time": "1:20:42", "remaining_time": "5:46:25", "throughput": 1496.85, "total_tokens": 7248224} {"current_steps": 34355, "total_steps": 181800, "loss": 0.1392, "lr": 4.880414442479047e-05, "epoch": 3.779427942794279, "percentage": 18.9, "elapsed_time": "1:20:43", "remaining_time": "5:46:25", "throughput": 1496.85, "total_tokens": 7249248} {"current_steps": 34360, "total_steps": 181800, "loss": 0.0327, "lr": 4.88034108976999e-05, "epoch": 3.77997799779978, "percentage": 18.9, "elapsed_time": "1:20:43", "remaining_time": "5:46:24", "throughput": 1496.87, "total_tokens": 7250400} {"current_steps": 34365, "total_steps": 181800, "loss": 0.142, "lr": 4.88026771512247e-05, "epoch": 3.7805280528052805, "percentage": 18.9, "elapsed_time": "1:20:44", "remaining_time": "5:46:23", "throughput": 1496.88, "total_tokens": 7251456} {"current_steps": 34370, "total_steps": 181800, "loss": 0.1282, "lr": 4.880194318537166e-05, "epoch": 3.781078107810781, "percentage": 18.91, "elapsed_time": "1:20:45", "remaining_time": "5:46:22", "throughput": 1496.91, "total_tokens": 7252640} {"current_steps": 34375, "total_steps": 181800, "loss": 0.1586, "lr": 4.880120900014752e-05, "epoch": 3.781628162816282, "percentage": 18.91, "elapsed_time": "1:20:45", "remaining_time": "5:46:22", "throughput": 1496.92, "total_tokens": 7253728} {"current_steps": 34380, "total_steps": 181800, "loss": 0.0381, "lr": 4.880047459555907e-05, "epoch": 3.782178217821782, "percentage": 18.91, "elapsed_time": "1:20:46", "remaining_time": "5:46:21", "throughput": 1496.93, "total_tokens": 7254784} {"current_steps": 34385, "total_steps": 181800, "loss": 0.0824, "lr": 4.8799739971613055e-05, "epoch": 3.7827282728272826, "percentage": 18.91, "elapsed_time": "1:20:47", "remaining_time": "5:46:20", "throughput": 1496.92, "total_tokens": 7255776} {"current_steps": 34390, "total_steps": 181800, "loss": 0.0906, "lr": 4.8799005128316254e-05, "epoch": 3.7832783278327833, "percentage": 18.92, "elapsed_time": "1:20:47", "remaining_time": "5:46:19", "throughput": 1496.91, "total_tokens": 7256768} {"current_steps": 34395, "total_steps": 181800, "loss": 0.1864, "lr": 4.879827006567545e-05, "epoch": 3.783828382838284, "percentage": 18.92, "elapsed_time": "1:20:48", "remaining_time": "5:46:19", "throughput": 1496.9, "total_tokens": 7257728} {"current_steps": 34400, "total_steps": 181800, "loss": 0.1346, "lr": 4.8797534783697415e-05, "epoch": 3.7843784378437846, "percentage": 18.92, "elapsed_time": "1:20:49", "remaining_time": "5:46:18", "throughput": 1496.89, "total_tokens": 7258752} {"current_steps": 34405, "total_steps": 181800, "loss": 0.1137, "lr": 4.879679928238892e-05, "epoch": 3.784928492849285, "percentage": 18.92, "elapsed_time": "1:20:49", "remaining_time": "5:46:17", "throughput": 1496.89, "total_tokens": 7259776} {"current_steps": 34410, "total_steps": 181800, "loss": 0.009, "lr": 4.8796063561756734e-05, "epoch": 3.7854785478547854, "percentage": 18.93, "elapsed_time": "1:20:50", "remaining_time": "5:46:16", "throughput": 1496.88, "total_tokens": 7260736} {"current_steps": 34415, "total_steps": 181800, "loss": 0.0326, "lr": 4.8795327621807656e-05, "epoch": 3.786028602860286, "percentage": 18.93, "elapsed_time": "1:20:51", "remaining_time": "5:46:16", "throughput": 1496.88, "total_tokens": 7261792} {"current_steps": 34420, "total_steps": 181800, "loss": 0.0414, "lr": 4.879459146254846e-05, "epoch": 3.7865786578657867, "percentage": 18.93, "elapsed_time": "1:20:51", "remaining_time": "5:46:15", "throughput": 1496.89, "total_tokens": 7262848} {"current_steps": 34425, "total_steps": 181800, "loss": 0.0383, "lr": 4.8793855083985936e-05, "epoch": 3.7871287128712874, "percentage": 18.94, "elapsed_time": "1:20:52", "remaining_time": "5:46:14", "throughput": 1496.89, "total_tokens": 7263904} {"current_steps": 34430, "total_steps": 181800, "loss": 0.1571, "lr": 4.879311848612687e-05, "epoch": 3.7876787678767876, "percentage": 18.94, "elapsed_time": "1:20:53", "remaining_time": "5:46:13", "throughput": 1496.9, "total_tokens": 7264992} {"current_steps": 34435, "total_steps": 181800, "loss": 0.0726, "lr": 4.8792381668978035e-05, "epoch": 3.7882288228822882, "percentage": 18.94, "elapsed_time": "1:20:54", "remaining_time": "5:46:12", "throughput": 1496.9, "total_tokens": 7266016} {"current_steps": 34440, "total_steps": 181800, "loss": 0.0291, "lr": 4.8791644632546244e-05, "epoch": 3.788778877887789, "percentage": 18.94, "elapsed_time": "1:20:54", "remaining_time": "5:46:12", "throughput": 1496.9, "total_tokens": 7267040} {"current_steps": 34445, "total_steps": 181800, "loss": 0.0822, "lr": 4.879090737683828e-05, "epoch": 3.789328932893289, "percentage": 18.95, "elapsed_time": "1:20:55", "remaining_time": "5:46:11", "throughput": 1496.9, "total_tokens": 7268064} {"current_steps": 34450, "total_steps": 181800, "loss": 0.0287, "lr": 4.879016990186094e-05, "epoch": 3.7898789878987897, "percentage": 18.95, "elapsed_time": "1:20:56", "remaining_time": "5:46:10", "throughput": 1496.9, "total_tokens": 7269120} {"current_steps": 34455, "total_steps": 181800, "loss": 0.1049, "lr": 4.878943220762101e-05, "epoch": 3.7904290429042904, "percentage": 18.95, "elapsed_time": "1:20:56", "remaining_time": "5:46:09", "throughput": 1496.9, "total_tokens": 7270144} {"current_steps": 34460, "total_steps": 181800, "loss": 0.0225, "lr": 4.8788694294125306e-05, "epoch": 3.790979097909791, "percentage": 18.95, "elapsed_time": "1:20:57", "remaining_time": "5:46:09", "throughput": 1496.91, "total_tokens": 7271232} {"current_steps": 34465, "total_steps": 181800, "loss": 0.0217, "lr": 4.878795616138062e-05, "epoch": 3.7915291529152917, "percentage": 18.96, "elapsed_time": "1:20:58", "remaining_time": "5:46:08", "throughput": 1496.92, "total_tokens": 7272320} {"current_steps": 34470, "total_steps": 181800, "loss": 0.0796, "lr": 4.878721780939376e-05, "epoch": 3.792079207920792, "percentage": 18.96, "elapsed_time": "1:20:58", "remaining_time": "5:46:07", "throughput": 1496.92, "total_tokens": 7273376} {"current_steps": 34475, "total_steps": 181800, "loss": 0.0302, "lr": 4.878647923817152e-05, "epoch": 3.7926292629262925, "percentage": 18.96, "elapsed_time": "1:20:59", "remaining_time": "5:46:06", "throughput": 1496.93, "total_tokens": 7274432} {"current_steps": 34480, "total_steps": 181800, "loss": 0.0265, "lr": 4.878574044772073e-05, "epoch": 3.793179317931793, "percentage": 18.97, "elapsed_time": "1:21:00", "remaining_time": "5:46:06", "throughput": 1496.94, "total_tokens": 7275520} {"current_steps": 34485, "total_steps": 181800, "loss": 0.0356, "lr": 4.8785001438048175e-05, "epoch": 3.793729372937294, "percentage": 18.97, "elapsed_time": "1:21:00", "remaining_time": "5:46:05", "throughput": 1496.95, "total_tokens": 7276608} {"current_steps": 34490, "total_steps": 181800, "loss": 0.0181, "lr": 4.878426220916067e-05, "epoch": 3.7942794279427945, "percentage": 18.97, "elapsed_time": "1:21:01", "remaining_time": "5:46:04", "throughput": 1496.96, "total_tokens": 7277696} {"current_steps": 34495, "total_steps": 181800, "loss": 0.0389, "lr": 4.878352276106504e-05, "epoch": 3.7948294829482947, "percentage": 18.97, "elapsed_time": "1:21:02", "remaining_time": "5:46:03", "throughput": 1496.97, "total_tokens": 7278752} {"current_steps": 34500, "total_steps": 181800, "loss": 0.0336, "lr": 4.878278309376809e-05, "epoch": 3.7953795379537953, "percentage": 18.98, "elapsed_time": "1:21:03", "remaining_time": "5:46:03", "throughput": 1496.97, "total_tokens": 7279808} {"current_steps": 34505, "total_steps": 181800, "loss": 0.0504, "lr": 4.878204320727664e-05, "epoch": 3.795929592959296, "percentage": 18.98, "elapsed_time": "1:21:03", "remaining_time": "5:46:02", "throughput": 1496.97, "total_tokens": 7280832} {"current_steps": 34510, "total_steps": 181800, "loss": 0.045, "lr": 4.878130310159751e-05, "epoch": 3.7964796479647966, "percentage": 18.98, "elapsed_time": "1:21:04", "remaining_time": "5:46:01", "throughput": 1496.97, "total_tokens": 7281888} {"current_steps": 34515, "total_steps": 181800, "loss": 0.055, "lr": 4.8780562776737515e-05, "epoch": 3.7970297029702973, "percentage": 18.99, "elapsed_time": "1:21:05", "remaining_time": "5:46:00", "throughput": 1496.98, "total_tokens": 7282976} {"current_steps": 34520, "total_steps": 181800, "loss": 0.0054, "lr": 4.8779822232703495e-05, "epoch": 3.7975797579757975, "percentage": 18.99, "elapsed_time": "1:21:05", "remaining_time": "5:45:59", "throughput": 1496.99, "total_tokens": 7284064} {"current_steps": 34525, "total_steps": 181800, "loss": 0.1399, "lr": 4.8779081469502255e-05, "epoch": 3.798129812981298, "percentage": 18.99, "elapsed_time": "1:21:06", "remaining_time": "5:45:59", "throughput": 1497.01, "total_tokens": 7285184} {"current_steps": 34530, "total_steps": 181800, "loss": 0.0249, "lr": 4.877834048714064e-05, "epoch": 3.798679867986799, "percentage": 18.99, "elapsed_time": "1:21:07", "remaining_time": "5:45:58", "throughput": 1497.03, "total_tokens": 7286304} {"current_steps": 34535, "total_steps": 181800, "loss": 0.0322, "lr": 4.877759928562546e-05, "epoch": 3.799229922992299, "percentage": 19.0, "elapsed_time": "1:21:07", "remaining_time": "5:45:57", "throughput": 1497.04, "total_tokens": 7287392} {"current_steps": 34540, "total_steps": 181800, "loss": 0.1797, "lr": 4.8776857864963564e-05, "epoch": 3.7997799779977997, "percentage": 19.0, "elapsed_time": "1:21:08", "remaining_time": "5:45:56", "throughput": 1497.03, "total_tokens": 7288352} {"current_steps": 34545, "total_steps": 181800, "loss": 0.0651, "lr": 4.877611622516178e-05, "epoch": 3.8003300330033003, "percentage": 19.0, "elapsed_time": "1:21:09", "remaining_time": "5:45:56", "throughput": 1497.05, "total_tokens": 7289472} {"current_steps": 34550, "total_steps": 181800, "loss": 0.0914, "lr": 4.8775374366226936e-05, "epoch": 3.800880088008801, "percentage": 19.0, "elapsed_time": "1:21:09", "remaining_time": "5:45:55", "throughput": 1497.04, "total_tokens": 7290464} {"current_steps": 34555, "total_steps": 181800, "loss": 0.0089, "lr": 4.877463228816588e-05, "epoch": 3.8014301430143016, "percentage": 19.01, "elapsed_time": "1:21:10", "remaining_time": "5:45:54", "throughput": 1497.04, "total_tokens": 7291520} {"current_steps": 34560, "total_steps": 181800, "loss": 0.0797, "lr": 4.8773889990985445e-05, "epoch": 3.801980198019802, "percentage": 19.01, "elapsed_time": "1:21:11", "remaining_time": "5:45:53", "throughput": 1497.05, "total_tokens": 7292576} {"current_steps": 34565, "total_steps": 181800, "loss": 0.018, "lr": 4.8773147474692474e-05, "epoch": 3.8025302530253025, "percentage": 19.01, "elapsed_time": "1:21:11", "remaining_time": "5:45:53", "throughput": 1497.04, "total_tokens": 7293568} {"current_steps": 34570, "total_steps": 181800, "loss": 0.0142, "lr": 4.877240473929381e-05, "epoch": 3.803080308030803, "percentage": 19.02, "elapsed_time": "1:21:12", "remaining_time": "5:45:52", "throughput": 1497.05, "total_tokens": 7294656} {"current_steps": 34575, "total_steps": 181800, "loss": 0.0388, "lr": 4.87716617847963e-05, "epoch": 3.8036303630363038, "percentage": 19.02, "elapsed_time": "1:21:13", "remaining_time": "5:45:51", "throughput": 1497.06, "total_tokens": 7295744} {"current_steps": 34580, "total_steps": 181800, "loss": 0.0829, "lr": 4.8770918611206784e-05, "epoch": 3.8041804180418044, "percentage": 19.02, "elapsed_time": "1:21:14", "remaining_time": "5:45:50", "throughput": 1497.08, "total_tokens": 7296864} {"current_steps": 34585, "total_steps": 181800, "loss": 0.0442, "lr": 4.877017521853212e-05, "epoch": 3.8047304730473046, "percentage": 19.02, "elapsed_time": "1:21:14", "remaining_time": "5:45:49", "throughput": 1497.07, "total_tokens": 7297856} {"current_steps": 34590, "total_steps": 181800, "loss": 0.0885, "lr": 4.876943160677916e-05, "epoch": 3.8052805280528053, "percentage": 19.03, "elapsed_time": "1:21:15", "remaining_time": "5:45:49", "throughput": 1497.07, "total_tokens": 7298880} {"current_steps": 34595, "total_steps": 181800, "loss": 0.0289, "lr": 4.8768687775954744e-05, "epoch": 3.805830583058306, "percentage": 19.03, "elapsed_time": "1:21:16", "remaining_time": "5:45:48", "throughput": 1497.08, "total_tokens": 7299968} {"current_steps": 34600, "total_steps": 181800, "loss": 0.035, "lr": 4.8767943726065755e-05, "epoch": 3.806380638063806, "percentage": 19.03, "elapsed_time": "1:21:16", "remaining_time": "5:45:47", "throughput": 1497.08, "total_tokens": 7300992} {"current_steps": 34605, "total_steps": 181800, "loss": 0.0706, "lr": 4.876719945711902e-05, "epoch": 3.806930693069307, "percentage": 19.03, "elapsed_time": "1:21:17", "remaining_time": "5:45:46", "throughput": 1497.08, "total_tokens": 7302048} {"current_steps": 34610, "total_steps": 181800, "loss": 0.0205, "lr": 4.876645496912142e-05, "epoch": 3.8074807480748074, "percentage": 19.04, "elapsed_time": "1:21:18", "remaining_time": "5:45:46", "throughput": 1497.1, "total_tokens": 7303168} {"current_steps": 34615, "total_steps": 181800, "loss": 0.0635, "lr": 4.8765710262079814e-05, "epoch": 3.808030803080308, "percentage": 19.04, "elapsed_time": "1:21:18", "remaining_time": "5:45:45", "throughput": 1497.11, "total_tokens": 7304224} {"current_steps": 34620, "total_steps": 181800, "loss": 0.04, "lr": 4.8764965336001046e-05, "epoch": 3.8085808580858087, "percentage": 19.04, "elapsed_time": "1:21:19", "remaining_time": "5:45:44", "throughput": 1497.1, "total_tokens": 7305216} {"current_steps": 34625, "total_steps": 181800, "loss": 0.1149, "lr": 4.8764220190892005e-05, "epoch": 3.809130913091309, "percentage": 19.05, "elapsed_time": "1:21:20", "remaining_time": "5:45:43", "throughput": 1497.1, "total_tokens": 7306272} {"current_steps": 34630, "total_steps": 181800, "loss": 0.1293, "lr": 4.876347482675955e-05, "epoch": 3.8096809680968096, "percentage": 19.05, "elapsed_time": "1:21:20", "remaining_time": "5:45:43", "throughput": 1497.11, "total_tokens": 7307328} {"current_steps": 34635, "total_steps": 181800, "loss": 0.0912, "lr": 4.8762729243610544e-05, "epoch": 3.81023102310231, "percentage": 19.05, "elapsed_time": "1:21:21", "remaining_time": "5:45:42", "throughput": 1497.11, "total_tokens": 7308384} {"current_steps": 34640, "total_steps": 181800, "loss": 0.0985, "lr": 4.8761983441451866e-05, "epoch": 3.810781078107811, "percentage": 19.05, "elapsed_time": "1:21:22", "remaining_time": "5:45:41", "throughput": 1497.13, "total_tokens": 7309472} {"current_steps": 34645, "total_steps": 181800, "loss": 0.04, "lr": 4.8761237420290394e-05, "epoch": 3.8113311331133115, "percentage": 19.06, "elapsed_time": "1:21:23", "remaining_time": "5:45:40", "throughput": 1497.12, "total_tokens": 7310464} {"current_steps": 34650, "total_steps": 181800, "loss": 0.0283, "lr": 4.8760491180133e-05, "epoch": 3.8118811881188117, "percentage": 19.06, "elapsed_time": "1:21:23", "remaining_time": "5:45:39", "throughput": 1497.12, "total_tokens": 7311488} {"current_steps": 34655, "total_steps": 181800, "loss": 0.0961, "lr": 4.875974472098656e-05, "epoch": 3.8124312431243124, "percentage": 19.06, "elapsed_time": "1:21:24", "remaining_time": "5:45:39", "throughput": 1497.13, "total_tokens": 7312608} {"current_steps": 34660, "total_steps": 181800, "loss": 0.0635, "lr": 4.875899804285794e-05, "epoch": 3.812981298129813, "percentage": 19.06, "elapsed_time": "1:21:25", "remaining_time": "5:45:38", "throughput": 1497.13, "total_tokens": 7313600} {"current_steps": 34665, "total_steps": 181800, "loss": 0.0399, "lr": 4.875825114575405e-05, "epoch": 3.8135313531353137, "percentage": 19.07, "elapsed_time": "1:21:25", "remaining_time": "5:45:37", "throughput": 1497.12, "total_tokens": 7314592} {"current_steps": 34670, "total_steps": 181800, "loss": 0.0673, "lr": 4.8757504029681755e-05, "epoch": 3.8140814081408143, "percentage": 19.07, "elapsed_time": "1:21:26", "remaining_time": "5:45:36", "throughput": 1497.13, "total_tokens": 7315680} {"current_steps": 34675, "total_steps": 181800, "loss": 0.0866, "lr": 4.8756756694647946e-05, "epoch": 3.8146314631463145, "percentage": 19.07, "elapsed_time": "1:21:27", "remaining_time": "5:45:36", "throughput": 1497.14, "total_tokens": 7316768} {"current_steps": 34680, "total_steps": 181800, "loss": 0.0315, "lr": 4.8756009140659514e-05, "epoch": 3.815181518151815, "percentage": 19.08, "elapsed_time": "1:21:27", "remaining_time": "5:45:35", "throughput": 1497.15, "total_tokens": 7317824} {"current_steps": 34685, "total_steps": 181800, "loss": 0.0329, "lr": 4.875526136772334e-05, "epoch": 3.815731573157316, "percentage": 19.08, "elapsed_time": "1:21:28", "remaining_time": "5:45:34", "throughput": 1497.17, "total_tokens": 7318944} {"current_steps": 34690, "total_steps": 181800, "loss": 0.1027, "lr": 4.8754513375846324e-05, "epoch": 3.816281628162816, "percentage": 19.08, "elapsed_time": "1:21:29", "remaining_time": "5:45:33", "throughput": 1497.17, "total_tokens": 7320000} {"current_steps": 34695, "total_steps": 181800, "loss": 0.0713, "lr": 4.8753765165035356e-05, "epoch": 3.8168316831683167, "percentage": 19.08, "elapsed_time": "1:21:29", "remaining_time": "5:45:32", "throughput": 1497.18, "total_tokens": 7321056} {"current_steps": 34700, "total_steps": 181800, "loss": 0.1058, "lr": 4.875301673529733e-05, "epoch": 3.8173817381738173, "percentage": 19.09, "elapsed_time": "1:21:30", "remaining_time": "5:45:32", "throughput": 1497.18, "total_tokens": 7322112} {"current_steps": 34705, "total_steps": 181800, "loss": 0.0222, "lr": 4.875226808663915e-05, "epoch": 3.817931793179318, "percentage": 19.09, "elapsed_time": "1:21:31", "remaining_time": "5:45:31", "throughput": 1497.19, "total_tokens": 7323168} {"current_steps": 34710, "total_steps": 181800, "loss": 0.0403, "lr": 4.875151921906771e-05, "epoch": 3.8184818481848186, "percentage": 19.09, "elapsed_time": "1:21:31", "remaining_time": "5:45:30", "throughput": 1497.2, "total_tokens": 7324256} {"current_steps": 34715, "total_steps": 181800, "loss": 0.1808, "lr": 4.8750770132589915e-05, "epoch": 3.819031903190319, "percentage": 19.1, "elapsed_time": "1:21:32", "remaining_time": "5:45:29", "throughput": 1497.2, "total_tokens": 7325312} {"current_steps": 34720, "total_steps": 181800, "loss": 0.0559, "lr": 4.875002082721267e-05, "epoch": 3.8195819581958195, "percentage": 19.1, "elapsed_time": "1:21:33", "remaining_time": "5:45:29", "throughput": 1497.21, "total_tokens": 7326368} {"current_steps": 34725, "total_steps": 181800, "loss": 0.1275, "lr": 4.874927130294287e-05, "epoch": 3.82013201320132, "percentage": 19.1, "elapsed_time": "1:21:34", "remaining_time": "5:45:28", "throughput": 1497.19, "total_tokens": 7327328} {"current_steps": 34730, "total_steps": 181800, "loss": 0.0203, "lr": 4.874852155978744e-05, "epoch": 3.8206820682068208, "percentage": 19.1, "elapsed_time": "1:21:34", "remaining_time": "5:45:27", "throughput": 1497.19, "total_tokens": 7328352} {"current_steps": 34735, "total_steps": 181800, "loss": 0.0603, "lr": 4.874777159775329e-05, "epoch": 3.8212321232123214, "percentage": 19.11, "elapsed_time": "1:21:35", "remaining_time": "5:45:26", "throughput": 1497.2, "total_tokens": 7329440} {"current_steps": 34740, "total_steps": 181800, "loss": 0.0574, "lr": 4.874702141684732e-05, "epoch": 3.8217821782178216, "percentage": 19.11, "elapsed_time": "1:21:36", "remaining_time": "5:45:26", "throughput": 1497.2, "total_tokens": 7330432} {"current_steps": 34745, "total_steps": 181800, "loss": 0.0261, "lr": 4.874627101707644e-05, "epoch": 3.8223322332233223, "percentage": 19.11, "elapsed_time": "1:21:36", "remaining_time": "5:45:25", "throughput": 1497.21, "total_tokens": 7331552} {"current_steps": 34750, "total_steps": 181800, "loss": 0.0351, "lr": 4.874552039844758e-05, "epoch": 3.822882288228823, "percentage": 19.11, "elapsed_time": "1:21:37", "remaining_time": "5:45:25", "throughput": 1497.18, "total_tokens": 7332608} {"current_steps": 34755, "total_steps": 181800, "loss": 0.0343, "lr": 4.874476956096765e-05, "epoch": 3.8234323432343236, "percentage": 19.12, "elapsed_time": "1:21:38", "remaining_time": "5:45:24", "throughput": 1497.18, "total_tokens": 7333632} {"current_steps": 34760, "total_steps": 181800, "loss": 0.0514, "lr": 4.874401850464358e-05, "epoch": 3.823982398239824, "percentage": 19.12, "elapsed_time": "1:21:38", "remaining_time": "5:45:23", "throughput": 1497.2, "total_tokens": 7334752} {"current_steps": 34765, "total_steps": 181800, "loss": 0.0534, "lr": 4.874326722948228e-05, "epoch": 3.8245324532453244, "percentage": 19.12, "elapsed_time": "1:21:39", "remaining_time": "5:45:22", "throughput": 1497.2, "total_tokens": 7335808} {"current_steps": 34770, "total_steps": 181800, "loss": 0.1108, "lr": 4.874251573549068e-05, "epoch": 3.825082508250825, "percentage": 19.13, "elapsed_time": "1:21:40", "remaining_time": "5:45:21", "throughput": 1497.22, "total_tokens": 7336928} {"current_steps": 34775, "total_steps": 181800, "loss": 0.1569, "lr": 4.8741764022675705e-05, "epoch": 3.8256325632563257, "percentage": 19.13, "elapsed_time": "1:21:41", "remaining_time": "5:45:21", "throughput": 1497.21, "total_tokens": 7337888} {"current_steps": 34780, "total_steps": 181800, "loss": 0.0841, "lr": 4.874101209104428e-05, "epoch": 3.826182618261826, "percentage": 19.13, "elapsed_time": "1:21:41", "remaining_time": "5:45:20", "throughput": 1497.22, "total_tokens": 7338976} {"current_steps": 34785, "total_steps": 181800, "loss": 0.0422, "lr": 4.874025994060334e-05, "epoch": 3.8267326732673266, "percentage": 19.13, "elapsed_time": "1:21:42", "remaining_time": "5:45:19", "throughput": 1497.22, "total_tokens": 7340032} {"current_steps": 34790, "total_steps": 181800, "loss": 0.0635, "lr": 4.873950757135982e-05, "epoch": 3.8272827282728272, "percentage": 19.14, "elapsed_time": "1:21:43", "remaining_time": "5:45:18", "throughput": 1497.23, "total_tokens": 7341088} {"current_steps": 34795, "total_steps": 181800, "loss": 0.085, "lr": 4.873875498332065e-05, "epoch": 3.827832783278328, "percentage": 19.14, "elapsed_time": "1:21:43", "remaining_time": "5:45:18", "throughput": 1497.23, "total_tokens": 7342112} {"current_steps": 34800, "total_steps": 181800, "loss": 0.1611, "lr": 4.8738002176492764e-05, "epoch": 3.8283828382838285, "percentage": 19.14, "elapsed_time": "1:21:44", "remaining_time": "5:45:17", "throughput": 1497.24, "total_tokens": 7343200} {"current_steps": 34805, "total_steps": 181800, "loss": 0.0896, "lr": 4.87372491508831e-05, "epoch": 3.8289328932893287, "percentage": 19.14, "elapsed_time": "1:21:45", "remaining_time": "5:45:16", "throughput": 1497.24, "total_tokens": 7344256} {"current_steps": 34810, "total_steps": 181800, "loss": 0.0333, "lr": 4.87364959064986e-05, "epoch": 3.8294829482948294, "percentage": 19.15, "elapsed_time": "1:21:45", "remaining_time": "5:45:15", "throughput": 1497.24, "total_tokens": 7345280} {"current_steps": 34815, "total_steps": 181800, "loss": 0.0666, "lr": 4.8735742443346216e-05, "epoch": 3.83003300330033, "percentage": 19.15, "elapsed_time": "1:21:46", "remaining_time": "5:45:15", "throughput": 1497.25, "total_tokens": 7346368} {"current_steps": 34820, "total_steps": 181800, "loss": 0.0249, "lr": 4.8734988761432876e-05, "epoch": 3.8305830583058307, "percentage": 19.15, "elapsed_time": "1:21:47", "remaining_time": "5:45:15", "throughput": 1497.19, "total_tokens": 7347392} {"current_steps": 34825, "total_steps": 181800, "loss": 0.0863, "lr": 4.873423486076554e-05, "epoch": 3.8311331133113313, "percentage": 19.16, "elapsed_time": "1:21:48", "remaining_time": "5:45:14", "throughput": 1497.21, "total_tokens": 7348512} {"current_steps": 34830, "total_steps": 181800, "loss": 0.0443, "lr": 4.873348074135114e-05, "epoch": 3.8316831683168315, "percentage": 19.16, "elapsed_time": "1:21:48", "remaining_time": "5:45:13", "throughput": 1497.22, "total_tokens": 7349600} {"current_steps": 34835, "total_steps": 181800, "loss": 0.1112, "lr": 4.873272640319665e-05, "epoch": 3.832233223322332, "percentage": 19.16, "elapsed_time": "1:21:49", "remaining_time": "5:45:12", "throughput": 1497.24, "total_tokens": 7350720} {"current_steps": 34840, "total_steps": 181800, "loss": 0.0632, "lr": 4.8731971846309e-05, "epoch": 3.832783278327833, "percentage": 19.16, "elapsed_time": "1:21:50", "remaining_time": "5:45:11", "throughput": 1497.24, "total_tokens": 7351776} {"current_steps": 34845, "total_steps": 181800, "loss": 0.0344, "lr": 4.873121707069515e-05, "epoch": 3.8333333333333335, "percentage": 19.17, "elapsed_time": "1:21:50", "remaining_time": "5:45:11", "throughput": 1497.25, "total_tokens": 7352864} {"current_steps": 34850, "total_steps": 181800, "loss": 0.1152, "lr": 4.8730462076362066e-05, "epoch": 3.833883388338834, "percentage": 19.17, "elapsed_time": "1:21:51", "remaining_time": "5:45:10", "throughput": 1497.25, "total_tokens": 7353888} {"current_steps": 34855, "total_steps": 181800, "loss": 0.0664, "lr": 4.872970686331669e-05, "epoch": 3.8344334433443343, "percentage": 19.17, "elapsed_time": "1:21:52", "remaining_time": "5:45:09", "throughput": 1497.25, "total_tokens": 7354912} {"current_steps": 34860, "total_steps": 181800, "loss": 0.1039, "lr": 4.8728951431566004e-05, "epoch": 3.834983498349835, "percentage": 19.17, "elapsed_time": "1:21:52", "remaining_time": "5:45:08", "throughput": 1497.25, "total_tokens": 7355936} {"current_steps": 34865, "total_steps": 181800, "loss": 0.0756, "lr": 4.872819578111696e-05, "epoch": 3.8355335533553356, "percentage": 19.18, "elapsed_time": "1:21:53", "remaining_time": "5:45:08", "throughput": 1497.26, "total_tokens": 7357024} {"current_steps": 34870, "total_steps": 181800, "loss": 0.0299, "lr": 4.872743991197651e-05, "epoch": 3.836083608360836, "percentage": 19.18, "elapsed_time": "1:21:54", "remaining_time": "5:45:07", "throughput": 1497.27, "total_tokens": 7358112} {"current_steps": 34875, "total_steps": 181800, "loss": 0.0709, "lr": 4.872668382415164e-05, "epoch": 3.8366336633663365, "percentage": 19.18, "elapsed_time": "1:21:55", "remaining_time": "5:45:06", "throughput": 1497.3, "total_tokens": 7359264} {"current_steps": 34880, "total_steps": 181800, "loss": 0.0105, "lr": 4.872592751764931e-05, "epoch": 3.837183718371837, "percentage": 19.19, "elapsed_time": "1:21:55", "remaining_time": "5:45:05", "throughput": 1497.29, "total_tokens": 7360288} {"current_steps": 34885, "total_steps": 181800, "loss": 0.0214, "lr": 4.872517099247649e-05, "epoch": 3.837733773377338, "percentage": 19.19, "elapsed_time": "1:21:56", "remaining_time": "5:45:05", "throughput": 1497.29, "total_tokens": 7361312} {"current_steps": 34890, "total_steps": 181800, "loss": 0.1288, "lr": 4.8724414248640154e-05, "epoch": 3.8382838283828384, "percentage": 19.19, "elapsed_time": "1:21:57", "remaining_time": "5:45:04", "throughput": 1497.3, "total_tokens": 7362400} {"current_steps": 34895, "total_steps": 181800, "loss": 0.047, "lr": 4.872365728614727e-05, "epoch": 3.8388338833883386, "percentage": 19.19, "elapsed_time": "1:21:57", "remaining_time": "5:45:03", "throughput": 1497.3, "total_tokens": 7363456} {"current_steps": 34900, "total_steps": 181800, "loss": 0.0676, "lr": 4.872290010500483e-05, "epoch": 3.8393839383938393, "percentage": 19.2, "elapsed_time": "1:21:58", "remaining_time": "5:45:02", "throughput": 1497.3, "total_tokens": 7364480} {"current_steps": 34905, "total_steps": 181800, "loss": 0.1001, "lr": 4.87221427052198e-05, "epoch": 3.83993399339934, "percentage": 19.2, "elapsed_time": "1:21:59", "remaining_time": "5:45:02", "throughput": 1497.31, "total_tokens": 7365536} {"current_steps": 34910, "total_steps": 181800, "loss": 0.0522, "lr": 4.872138508679916e-05, "epoch": 3.8404840484048406, "percentage": 19.2, "elapsed_time": "1:21:59", "remaining_time": "5:45:01", "throughput": 1497.3, "total_tokens": 7366528} {"current_steps": 34915, "total_steps": 181800, "loss": 0.0302, "lr": 4.8720627249749904e-05, "epoch": 3.8410341034103412, "percentage": 19.21, "elapsed_time": "1:22:00", "remaining_time": "5:45:00", "throughput": 1497.3, "total_tokens": 7367584} {"current_steps": 34920, "total_steps": 181800, "loss": 0.1113, "lr": 4.8719869194079e-05, "epoch": 3.8415841584158414, "percentage": 19.21, "elapsed_time": "1:22:01", "remaining_time": "5:44:59", "throughput": 1497.31, "total_tokens": 7368672} {"current_steps": 34925, "total_steps": 181800, "loss": 0.1189, "lr": 4.871911091979345e-05, "epoch": 3.842134213421342, "percentage": 19.21, "elapsed_time": "1:22:01", "remaining_time": "5:44:59", "throughput": 1497.32, "total_tokens": 7369760} {"current_steps": 34930, "total_steps": 181800, "loss": 0.0603, "lr": 4.8718352426900234e-05, "epoch": 3.8426842684268427, "percentage": 19.21, "elapsed_time": "1:22:02", "remaining_time": "5:44:58", "throughput": 1497.33, "total_tokens": 7370816} {"current_steps": 34935, "total_steps": 181800, "loss": 0.0649, "lr": 4.871759371540634e-05, "epoch": 3.8432343234323434, "percentage": 19.22, "elapsed_time": "1:22:03", "remaining_time": "5:44:57", "throughput": 1497.34, "total_tokens": 7371936} {"current_steps": 34940, "total_steps": 181800, "loss": 0.068, "lr": 4.871683478531877e-05, "epoch": 3.843784378437844, "percentage": 19.22, "elapsed_time": "1:22:04", "remaining_time": "5:44:56", "throughput": 1497.36, "total_tokens": 7373056} {"current_steps": 34945, "total_steps": 181800, "loss": 0.0375, "lr": 4.8716075636644516e-05, "epoch": 3.8443344334433442, "percentage": 19.22, "elapsed_time": "1:22:04", "remaining_time": "5:44:55", "throughput": 1497.37, "total_tokens": 7374112} {"current_steps": 34950, "total_steps": 181800, "loss": 0.1578, "lr": 4.871531626939057e-05, "epoch": 3.844884488448845, "percentage": 19.22, "elapsed_time": "1:22:05", "remaining_time": "5:44:55", "throughput": 1497.36, "total_tokens": 7375104} {"current_steps": 34955, "total_steps": 181800, "loss": 0.0906, "lr": 4.871455668356393e-05, "epoch": 3.8454345434543455, "percentage": 19.23, "elapsed_time": "1:22:06", "remaining_time": "5:44:54", "throughput": 1497.37, "total_tokens": 7376192} {"current_steps": 34960, "total_steps": 181800, "loss": 0.0816, "lr": 4.871379687917161e-05, "epoch": 3.8459845984598457, "percentage": 19.23, "elapsed_time": "1:22:06", "remaining_time": "5:44:53", "throughput": 1497.37, "total_tokens": 7377216} {"current_steps": 34965, "total_steps": 181800, "loss": 0.0425, "lr": 4.8713036856220596e-05, "epoch": 3.8465346534653464, "percentage": 19.23, "elapsed_time": "1:22:07", "remaining_time": "5:44:52", "throughput": 1497.37, "total_tokens": 7378272} {"current_steps": 34970, "total_steps": 181800, "loss": 0.0614, "lr": 4.87122766147179e-05, "epoch": 3.847084708470847, "percentage": 19.24, "elapsed_time": "1:22:08", "remaining_time": "5:44:52", "throughput": 1497.36, "total_tokens": 7379232} {"current_steps": 34975, "total_steps": 181800, "loss": 0.0446, "lr": 4.8711516154670533e-05, "epoch": 3.8476347634763477, "percentage": 19.24, "elapsed_time": "1:22:08", "remaining_time": "5:44:51", "throughput": 1497.37, "total_tokens": 7380288} {"current_steps": 34980, "total_steps": 181800, "loss": 0.0845, "lr": 4.87107554760855e-05, "epoch": 3.8481848184818483, "percentage": 19.24, "elapsed_time": "1:22:09", "remaining_time": "5:44:50", "throughput": 1497.36, "total_tokens": 7381280} {"current_steps": 34985, "total_steps": 181800, "loss": 0.0409, "lr": 4.870999457896981e-05, "epoch": 3.8487348734873486, "percentage": 19.24, "elapsed_time": "1:22:10", "remaining_time": "5:44:49", "throughput": 1497.36, "total_tokens": 7382304} {"current_steps": 34990, "total_steps": 181800, "loss": 0.0246, "lr": 4.870923346333047e-05, "epoch": 3.849284928492849, "percentage": 19.25, "elapsed_time": "1:22:10", "remaining_time": "5:44:48", "throughput": 1497.35, "total_tokens": 7383296} {"current_steps": 34995, "total_steps": 181800, "loss": 0.0777, "lr": 4.870847212917451e-05, "epoch": 3.84983498349835, "percentage": 19.25, "elapsed_time": "1:22:11", "remaining_time": "5:44:48", "throughput": 1497.35, "total_tokens": 7384320} {"current_steps": 35000, "total_steps": 181800, "loss": 0.0525, "lr": 4.8707710576508935e-05, "epoch": 3.8503850385038505, "percentage": 19.25, "elapsed_time": "1:22:12", "remaining_time": "5:44:47", "throughput": 1497.35, "total_tokens": 7385376} {"current_steps": 35005, "total_steps": 181800, "loss": 0.0652, "lr": 4.870694880534077e-05, "epoch": 3.850935093509351, "percentage": 19.25, "elapsed_time": "1:22:12", "remaining_time": "5:44:46", "throughput": 1497.37, "total_tokens": 7386464} {"current_steps": 35010, "total_steps": 181800, "loss": 0.1057, "lr": 4.8706186815677034e-05, "epoch": 3.8514851485148514, "percentage": 19.26, "elapsed_time": "1:22:13", "remaining_time": "5:44:45", "throughput": 1497.36, "total_tokens": 7387456} {"current_steps": 35015, "total_steps": 181800, "loss": 0.0617, "lr": 4.870542460752475e-05, "epoch": 3.852035203520352, "percentage": 19.26, "elapsed_time": "1:22:14", "remaining_time": "5:44:45", "throughput": 1497.35, "total_tokens": 7388480} {"current_steps": 35020, "total_steps": 181800, "loss": 0.072, "lr": 4.870466218089094e-05, "epoch": 3.8525852585258527, "percentage": 19.26, "elapsed_time": "1:22:15", "remaining_time": "5:44:44", "throughput": 1497.36, "total_tokens": 7389536} {"current_steps": 35025, "total_steps": 181800, "loss": 0.032, "lr": 4.8703899535782624e-05, "epoch": 3.8531353135313533, "percentage": 19.27, "elapsed_time": "1:22:15", "remaining_time": "5:44:43", "throughput": 1497.38, "total_tokens": 7390656} {"current_steps": 35030, "total_steps": 181800, "loss": 0.0598, "lr": 4.8703136672206854e-05, "epoch": 3.853685368536854, "percentage": 19.27, "elapsed_time": "1:22:16", "remaining_time": "5:44:42", "throughput": 1497.38, "total_tokens": 7391680} {"current_steps": 35035, "total_steps": 181800, "loss": 0.0523, "lr": 4.870237359017065e-05, "epoch": 3.854235423542354, "percentage": 19.27, "elapsed_time": "1:22:17", "remaining_time": "5:44:42", "throughput": 1497.37, "total_tokens": 7392704} {"current_steps": 35040, "total_steps": 181800, "loss": 0.0981, "lr": 4.8701610289681035e-05, "epoch": 3.854785478547855, "percentage": 19.27, "elapsed_time": "1:22:17", "remaining_time": "5:44:41", "throughput": 1497.37, "total_tokens": 7393728} {"current_steps": 35045, "total_steps": 181800, "loss": 0.1298, "lr": 4.8700846770745046e-05, "epoch": 3.8553355335533555, "percentage": 19.28, "elapsed_time": "1:22:18", "remaining_time": "5:44:40", "throughput": 1497.38, "total_tokens": 7394784} {"current_steps": 35050, "total_steps": 181800, "loss": 0.028, "lr": 4.870008303336973e-05, "epoch": 3.8558855885588557, "percentage": 19.28, "elapsed_time": "1:22:19", "remaining_time": "5:44:39", "throughput": 1497.38, "total_tokens": 7395840} {"current_steps": 35055, "total_steps": 181800, "loss": 0.087, "lr": 4.8699319077562124e-05, "epoch": 3.8564356435643563, "percentage": 19.28, "elapsed_time": "1:22:19", "remaining_time": "5:44:38", "throughput": 1497.39, "total_tokens": 7396896} {"current_steps": 35060, "total_steps": 181800, "loss": 0.0125, "lr": 4.869855490332926e-05, "epoch": 3.856985698569857, "percentage": 19.28, "elapsed_time": "1:22:20", "remaining_time": "5:44:38", "throughput": 1497.39, "total_tokens": 7397920} {"current_steps": 35065, "total_steps": 181800, "loss": 0.129, "lr": 4.8697790510678196e-05, "epoch": 3.8575357535753576, "percentage": 19.29, "elapsed_time": "1:22:21", "remaining_time": "5:44:37", "throughput": 1497.38, "total_tokens": 7398912} {"current_steps": 35070, "total_steps": 181800, "loss": 0.0882, "lr": 4.869702589961596e-05, "epoch": 3.8580858085808583, "percentage": 19.29, "elapsed_time": "1:22:21", "remaining_time": "5:44:36", "throughput": 1497.4, "total_tokens": 7400064} {"current_steps": 35075, "total_steps": 181800, "loss": 0.0563, "lr": 4.8696261070149605e-05, "epoch": 3.8586358635863585, "percentage": 19.29, "elapsed_time": "1:22:22", "remaining_time": "5:44:35", "throughput": 1497.4, "total_tokens": 7401088} {"current_steps": 35080, "total_steps": 181800, "loss": 0.0581, "lr": 4.869549602228619e-05, "epoch": 3.859185918591859, "percentage": 19.3, "elapsed_time": "1:22:23", "remaining_time": "5:44:35", "throughput": 1497.41, "total_tokens": 7402144} {"current_steps": 35085, "total_steps": 181800, "loss": 0.0606, "lr": 4.869473075603276e-05, "epoch": 3.8597359735973598, "percentage": 19.3, "elapsed_time": "1:22:24", "remaining_time": "5:44:34", "throughput": 1497.42, "total_tokens": 7403232} {"current_steps": 35090, "total_steps": 181800, "loss": 0.0295, "lr": 4.869396527139636e-05, "epoch": 3.8602860286028604, "percentage": 19.3, "elapsed_time": "1:22:24", "remaining_time": "5:44:33", "throughput": 1497.4, "total_tokens": 7404192} {"current_steps": 35095, "total_steps": 181800, "loss": 0.0626, "lr": 4.869319956838405e-05, "epoch": 3.860836083608361, "percentage": 19.3, "elapsed_time": "1:22:25", "remaining_time": "5:44:32", "throughput": 1497.41, "total_tokens": 7405248} {"current_steps": 35100, "total_steps": 181800, "loss": 0.0574, "lr": 4.8692433647002896e-05, "epoch": 3.8613861386138613, "percentage": 19.31, "elapsed_time": "1:22:26", "remaining_time": "5:44:32", "throughput": 1497.4, "total_tokens": 7406240} {"current_steps": 35105, "total_steps": 181800, "loss": 0.0587, "lr": 4.869166750725995e-05, "epoch": 3.861936193619362, "percentage": 19.31, "elapsed_time": "1:22:26", "remaining_time": "5:44:31", "throughput": 1497.39, "total_tokens": 7407232} {"current_steps": 35110, "total_steps": 181800, "loss": 0.0865, "lr": 4.8690901149162266e-05, "epoch": 3.8624862486248626, "percentage": 19.31, "elapsed_time": "1:22:27", "remaining_time": "5:44:30", "throughput": 1497.4, "total_tokens": 7408320} {"current_steps": 35115, "total_steps": 181800, "loss": 0.0952, "lr": 4.869013457271692e-05, "epoch": 3.8630363036303628, "percentage": 19.32, "elapsed_time": "1:22:28", "remaining_time": "5:44:29", "throughput": 1497.4, "total_tokens": 7409344} {"current_steps": 35120, "total_steps": 181800, "loss": 0.018, "lr": 4.868936777793097e-05, "epoch": 3.863586358635864, "percentage": 19.32, "elapsed_time": "1:22:28", "remaining_time": "5:44:28", "throughput": 1497.41, "total_tokens": 7410400} {"current_steps": 35125, "total_steps": 181800, "loss": 0.1414, "lr": 4.868860076481148e-05, "epoch": 3.864136413641364, "percentage": 19.32, "elapsed_time": "1:22:29", "remaining_time": "5:44:28", "throughput": 1497.41, "total_tokens": 7411456} {"current_steps": 35130, "total_steps": 181800, "loss": 0.0311, "lr": 4.868783353336552e-05, "epoch": 3.8646864686468647, "percentage": 19.32, "elapsed_time": "1:22:30", "remaining_time": "5:44:27", "throughput": 1497.41, "total_tokens": 7412480} {"current_steps": 35135, "total_steps": 181800, "loss": 0.024, "lr": 4.868706608360018e-05, "epoch": 3.8652365236523654, "percentage": 19.33, "elapsed_time": "1:22:30", "remaining_time": "5:44:26", "throughput": 1497.42, "total_tokens": 7413568} {"current_steps": 35140, "total_steps": 181800, "loss": 0.0142, "lr": 4.8686298415522505e-05, "epoch": 3.8657865786578656, "percentage": 19.33, "elapsed_time": "1:22:31", "remaining_time": "5:44:25", "throughput": 1497.42, "total_tokens": 7414560} {"current_steps": 35145, "total_steps": 181800, "loss": 0.0232, "lr": 4.868553052913959e-05, "epoch": 3.866336633663366, "percentage": 19.33, "elapsed_time": "1:22:32", "remaining_time": "5:44:25", "throughput": 1497.41, "total_tokens": 7415584} {"current_steps": 35150, "total_steps": 181800, "loss": 0.054, "lr": 4.868476242445851e-05, "epoch": 3.866886688668867, "percentage": 19.33, "elapsed_time": "1:22:32", "remaining_time": "5:44:24", "throughput": 1497.42, "total_tokens": 7416640} {"current_steps": 35155, "total_steps": 181800, "loss": 0.0521, "lr": 4.868399410148633e-05, "epoch": 3.8674367436743675, "percentage": 19.34, "elapsed_time": "1:22:33", "remaining_time": "5:44:23", "throughput": 1497.43, "total_tokens": 7417728} {"current_steps": 35160, "total_steps": 181800, "loss": 0.0317, "lr": 4.8683225560230136e-05, "epoch": 3.867986798679868, "percentage": 19.34, "elapsed_time": "1:22:34", "remaining_time": "5:44:22", "throughput": 1497.44, "total_tokens": 7418816} {"current_steps": 35165, "total_steps": 181800, "loss": 0.0989, "lr": 4.8682456800697026e-05, "epoch": 3.8685368536853684, "percentage": 19.34, "elapsed_time": "1:22:35", "remaining_time": "5:44:21", "throughput": 1497.45, "total_tokens": 7419872} {"current_steps": 35170, "total_steps": 181800, "loss": 0.0396, "lr": 4.8681687822894077e-05, "epoch": 3.869086908690869, "percentage": 19.35, "elapsed_time": "1:22:35", "remaining_time": "5:44:21", "throughput": 1497.45, "total_tokens": 7420928} {"current_steps": 35175, "total_steps": 181800, "loss": 0.0366, "lr": 4.8680918626828375e-05, "epoch": 3.8696369636963697, "percentage": 19.35, "elapsed_time": "1:22:36", "remaining_time": "5:44:20", "throughput": 1497.47, "total_tokens": 7422016} {"current_steps": 35180, "total_steps": 181800, "loss": 0.0923, "lr": 4.8680149212507e-05, "epoch": 3.8701870187018703, "percentage": 19.35, "elapsed_time": "1:22:37", "remaining_time": "5:44:19", "throughput": 1497.46, "total_tokens": 7423008} {"current_steps": 35185, "total_steps": 181800, "loss": 0.0139, "lr": 4.867937957993707e-05, "epoch": 3.870737073707371, "percentage": 19.35, "elapsed_time": "1:22:37", "remaining_time": "5:44:18", "throughput": 1497.46, "total_tokens": 7424064} {"current_steps": 35190, "total_steps": 181800, "loss": 0.1055, "lr": 4.8678609729125646e-05, "epoch": 3.871287128712871, "percentage": 19.36, "elapsed_time": "1:22:38", "remaining_time": "5:44:18", "throughput": 1497.47, "total_tokens": 7425152} {"current_steps": 35195, "total_steps": 181800, "loss": 0.0913, "lr": 4.8677839660079837e-05, "epoch": 3.871837183718372, "percentage": 19.36, "elapsed_time": "1:22:39", "remaining_time": "5:44:17", "throughput": 1497.48, "total_tokens": 7426208} {"current_steps": 35200, "total_steps": 181800, "loss": 0.1295, "lr": 4.867706937280675e-05, "epoch": 3.8723872387238725, "percentage": 19.36, "elapsed_time": "1:22:39", "remaining_time": "5:44:16", "throughput": 1497.5, "total_tokens": 7427328} {"current_steps": 35205, "total_steps": 181800, "loss": 0.058, "lr": 4.867629886731347e-05, "epoch": 3.8729372937293727, "percentage": 19.36, "elapsed_time": "1:22:40", "remaining_time": "5:44:15", "throughput": 1497.5, "total_tokens": 7428352} {"current_steps": 35210, "total_steps": 181800, "loss": 0.0843, "lr": 4.8675528143607106e-05, "epoch": 3.8734873487348733, "percentage": 19.37, "elapsed_time": "1:22:41", "remaining_time": "5:44:14", "throughput": 1497.51, "total_tokens": 7429440} {"current_steps": 35215, "total_steps": 181800, "loss": 0.0465, "lr": 4.8674757201694766e-05, "epoch": 3.874037403740374, "percentage": 19.37, "elapsed_time": "1:22:41", "remaining_time": "5:44:14", "throughput": 1497.52, "total_tokens": 7430496} {"current_steps": 35220, "total_steps": 181800, "loss": 0.0989, "lr": 4.867398604158354e-05, "epoch": 3.8745874587458746, "percentage": 19.37, "elapsed_time": "1:22:42", "remaining_time": "5:44:13", "throughput": 1497.52, "total_tokens": 7431552} {"current_steps": 35225, "total_steps": 181800, "loss": 0.0864, "lr": 4.867321466328055e-05, "epoch": 3.8751375137513753, "percentage": 19.38, "elapsed_time": "1:22:43", "remaining_time": "5:44:12", "throughput": 1497.51, "total_tokens": 7432544} {"current_steps": 35230, "total_steps": 181800, "loss": 0.0564, "lr": 4.8672443066792894e-05, "epoch": 3.8756875687568755, "percentage": 19.38, "elapsed_time": "1:22:43", "remaining_time": "5:44:11", "throughput": 1497.51, "total_tokens": 7433536} {"current_steps": 35235, "total_steps": 181800, "loss": 0.023, "lr": 4.8671671252127696e-05, "epoch": 3.876237623762376, "percentage": 19.38, "elapsed_time": "1:22:44", "remaining_time": "5:44:11", "throughput": 1497.52, "total_tokens": 7434624} {"current_steps": 35240, "total_steps": 181800, "loss": 0.0167, "lr": 4.8670899219292065e-05, "epoch": 3.8767876787678768, "percentage": 19.38, "elapsed_time": "1:22:45", "remaining_time": "5:44:10", "throughput": 1497.53, "total_tokens": 7435744} {"current_steps": 35245, "total_steps": 181800, "loss": 0.111, "lr": 4.8670126968293104e-05, "epoch": 3.8773377337733774, "percentage": 19.39, "elapsed_time": "1:22:46", "remaining_time": "5:44:09", "throughput": 1497.53, "total_tokens": 7436768} {"current_steps": 35250, "total_steps": 181800, "loss": 0.0875, "lr": 4.8669354499137955e-05, "epoch": 3.877887788778878, "percentage": 19.39, "elapsed_time": "1:22:46", "remaining_time": "5:44:08", "throughput": 1497.54, "total_tokens": 7437824} {"current_steps": 35255, "total_steps": 181800, "loss": 0.0916, "lr": 4.866858181183371e-05, "epoch": 3.8784378437843783, "percentage": 19.39, "elapsed_time": "1:22:47", "remaining_time": "5:44:08", "throughput": 1497.54, "total_tokens": 7438880} {"current_steps": 35260, "total_steps": 181800, "loss": 0.1656, "lr": 4.866780890638751e-05, "epoch": 3.878987898789879, "percentage": 19.39, "elapsed_time": "1:22:48", "remaining_time": "5:44:07", "throughput": 1497.56, "total_tokens": 7440000} {"current_steps": 35265, "total_steps": 181800, "loss": 0.063, "lr": 4.8667035782806466e-05, "epoch": 3.8795379537953796, "percentage": 19.4, "elapsed_time": "1:22:48", "remaining_time": "5:44:06", "throughput": 1497.55, "total_tokens": 7441024} {"current_steps": 35270, "total_steps": 181800, "loss": 0.0398, "lr": 4.866626244109772e-05, "epoch": 3.8800880088008802, "percentage": 19.4, "elapsed_time": "1:22:49", "remaining_time": "5:44:05", "throughput": 1497.57, "total_tokens": 7442144} {"current_steps": 35275, "total_steps": 181800, "loss": 0.0685, "lr": 4.866548888126838e-05, "epoch": 3.880638063806381, "percentage": 19.4, "elapsed_time": "1:22:50", "remaining_time": "5:44:05", "throughput": 1497.56, "total_tokens": 7443104} {"current_steps": 35280, "total_steps": 181800, "loss": 0.1108, "lr": 4.866471510332559e-05, "epoch": 3.881188118811881, "percentage": 19.41, "elapsed_time": "1:22:50", "remaining_time": "5:44:04", "throughput": 1497.56, "total_tokens": 7444128} {"current_steps": 35285, "total_steps": 181800, "loss": 0.0448, "lr": 4.866394110727647e-05, "epoch": 3.8817381738173817, "percentage": 19.41, "elapsed_time": "1:22:51", "remaining_time": "5:44:03", "throughput": 1497.56, "total_tokens": 7445184} {"current_steps": 35290, "total_steps": 181800, "loss": 0.0799, "lr": 4.866316689312817e-05, "epoch": 3.8822882288228824, "percentage": 19.41, "elapsed_time": "1:22:52", "remaining_time": "5:44:02", "throughput": 1497.56, "total_tokens": 7446208} {"current_steps": 35295, "total_steps": 181800, "loss": 0.0663, "lr": 4.8662392460887806e-05, "epoch": 3.8828382838283826, "percentage": 19.41, "elapsed_time": "1:22:52", "remaining_time": "5:44:01", "throughput": 1497.56, "total_tokens": 7447232} {"current_steps": 35300, "total_steps": 181800, "loss": 0.0664, "lr": 4.866161781056253e-05, "epoch": 3.8833883388338832, "percentage": 19.42, "elapsed_time": "1:22:53", "remaining_time": "5:44:01", "throughput": 1497.56, "total_tokens": 7448288} {"current_steps": 35305, "total_steps": 181800, "loss": 0.0443, "lr": 4.866084294215948e-05, "epoch": 3.883938393839384, "percentage": 19.42, "elapsed_time": "1:22:54", "remaining_time": "5:44:00", "throughput": 1497.58, "total_tokens": 7449408} {"current_steps": 35310, "total_steps": 181800, "loss": 0.0645, "lr": 4.866006785568579e-05, "epoch": 3.8844884488448845, "percentage": 19.42, "elapsed_time": "1:22:54", "remaining_time": "5:43:59", "throughput": 1497.59, "total_tokens": 7450464} {"current_steps": 35315, "total_steps": 181800, "loss": 0.0342, "lr": 4.8659292551148606e-05, "epoch": 3.885038503850385, "percentage": 19.43, "elapsed_time": "1:22:55", "remaining_time": "5:43:58", "throughput": 1497.59, "total_tokens": 7451488} {"current_steps": 35320, "total_steps": 181800, "loss": 0.0492, "lr": 4.865851702855508e-05, "epoch": 3.8855885588558854, "percentage": 19.43, "elapsed_time": "1:22:56", "remaining_time": "5:43:58", "throughput": 1497.59, "total_tokens": 7452544} {"current_steps": 35325, "total_steps": 181800, "loss": 0.0869, "lr": 4.865774128791235e-05, "epoch": 3.886138613861386, "percentage": 19.43, "elapsed_time": "1:22:57", "remaining_time": "5:43:57", "throughput": 1497.6, "total_tokens": 7453632} {"current_steps": 35330, "total_steps": 181800, "loss": 0.0104, "lr": 4.8656965329227574e-05, "epoch": 3.8866886688668867, "percentage": 19.43, "elapsed_time": "1:22:57", "remaining_time": "5:43:56", "throughput": 1497.61, "total_tokens": 7454688} {"current_steps": 35335, "total_steps": 181800, "loss": 0.0536, "lr": 4.8656189152507896e-05, "epoch": 3.8872387238723873, "percentage": 19.44, "elapsed_time": "1:22:58", "remaining_time": "5:43:55", "throughput": 1497.62, "total_tokens": 7455808} {"current_steps": 35340, "total_steps": 181800, "loss": 0.1194, "lr": 4.8655412757760473e-05, "epoch": 3.887788778877888, "percentage": 19.44, "elapsed_time": "1:22:59", "remaining_time": "5:43:55", "throughput": 1497.64, "total_tokens": 7456928} {"current_steps": 35345, "total_steps": 181800, "loss": 0.0523, "lr": 4.865463614499247e-05, "epoch": 3.888338833883388, "percentage": 19.44, "elapsed_time": "1:22:59", "remaining_time": "5:43:54", "throughput": 1497.64, "total_tokens": 7457952} {"current_steps": 35350, "total_steps": 181800, "loss": 0.0501, "lr": 4.865385931421104e-05, "epoch": 3.888888888888889, "percentage": 19.44, "elapsed_time": "1:23:00", "remaining_time": "5:43:53", "throughput": 1497.65, "total_tokens": 7459072} {"current_steps": 35355, "total_steps": 181800, "loss": 0.0348, "lr": 4.8653082265423325e-05, "epoch": 3.8894389438943895, "percentage": 19.45, "elapsed_time": "1:23:01", "remaining_time": "5:43:52", "throughput": 1497.65, "total_tokens": 7460064} {"current_steps": 35360, "total_steps": 181800, "loss": 0.1074, "lr": 4.86523049986365e-05, "epoch": 3.88998899889989, "percentage": 19.45, "elapsed_time": "1:23:01", "remaining_time": "5:43:51", "throughput": 1497.64, "total_tokens": 7461088} {"current_steps": 35365, "total_steps": 181800, "loss": 0.0891, "lr": 4.865152751385774e-05, "epoch": 3.890539053905391, "percentage": 19.45, "elapsed_time": "1:23:02", "remaining_time": "5:43:51", "throughput": 1497.65, "total_tokens": 7462176} {"current_steps": 35370, "total_steps": 181800, "loss": 0.0666, "lr": 4.86507498110942e-05, "epoch": 3.891089108910891, "percentage": 19.46, "elapsed_time": "1:23:03", "remaining_time": "5:43:50", "throughput": 1497.66, "total_tokens": 7463232} {"current_steps": 35375, "total_steps": 181800, "loss": 0.01, "lr": 4.864997189035304e-05, "epoch": 3.8916391639163916, "percentage": 19.46, "elapsed_time": "1:23:03", "remaining_time": "5:43:49", "throughput": 1497.66, "total_tokens": 7464256} {"current_steps": 35380, "total_steps": 181800, "loss": 0.1015, "lr": 4.864919375164144e-05, "epoch": 3.8921892189218923, "percentage": 19.46, "elapsed_time": "1:23:04", "remaining_time": "5:43:48", "throughput": 1497.67, "total_tokens": 7465344} {"current_steps": 35385, "total_steps": 181800, "loss": 0.0171, "lr": 4.864841539496657e-05, "epoch": 3.8927392739273925, "percentage": 19.46, "elapsed_time": "1:23:05", "remaining_time": "5:43:48", "throughput": 1497.68, "total_tokens": 7466432} {"current_steps": 35390, "total_steps": 181800, "loss": 0.0659, "lr": 4.8647636820335604e-05, "epoch": 3.893289328932893, "percentage": 19.47, "elapsed_time": "1:23:06", "remaining_time": "5:43:47", "throughput": 1497.69, "total_tokens": 7467488} {"current_steps": 35395, "total_steps": 181800, "loss": 0.0206, "lr": 4.864685802775571e-05, "epoch": 3.893839383938394, "percentage": 19.47, "elapsed_time": "1:23:06", "remaining_time": "5:43:46", "throughput": 1497.69, "total_tokens": 7468544} {"current_steps": 35400, "total_steps": 181800, "loss": 0.0154, "lr": 4.864607901723408e-05, "epoch": 3.8943894389438944, "percentage": 19.47, "elapsed_time": "1:23:07", "remaining_time": "5:43:45", "throughput": 1497.7, "total_tokens": 7469632} {"current_steps": 35405, "total_steps": 181800, "loss": 0.131, "lr": 4.864529978877789e-05, "epoch": 3.894939493949395, "percentage": 19.47, "elapsed_time": "1:23:08", "remaining_time": "5:43:45", "throughput": 1497.71, "total_tokens": 7470720} {"current_steps": 35410, "total_steps": 181800, "loss": 0.0551, "lr": 4.8644520342394305e-05, "epoch": 3.8954895489548953, "percentage": 19.48, "elapsed_time": "1:23:08", "remaining_time": "5:43:44", "throughput": 1497.7, "total_tokens": 7471712} {"current_steps": 35415, "total_steps": 181800, "loss": 0.1458, "lr": 4.864374067809053e-05, "epoch": 3.896039603960396, "percentage": 19.48, "elapsed_time": "1:23:09", "remaining_time": "5:43:43", "throughput": 1497.71, "total_tokens": 7472768} {"current_steps": 35420, "total_steps": 181800, "loss": 0.1204, "lr": 4.864296079587374e-05, "epoch": 3.8965896589658966, "percentage": 19.48, "elapsed_time": "1:23:10", "remaining_time": "5:43:42", "throughput": 1497.73, "total_tokens": 7473888} {"current_steps": 35425, "total_steps": 181800, "loss": 0.1044, "lr": 4.8642180695751133e-05, "epoch": 3.8971397139713972, "percentage": 19.49, "elapsed_time": "1:23:10", "remaining_time": "5:43:42", "throughput": 1497.72, "total_tokens": 7474880} {"current_steps": 35430, "total_steps": 181800, "loss": 0.0462, "lr": 4.864140037772988e-05, "epoch": 3.897689768976898, "percentage": 19.49, "elapsed_time": "1:23:11", "remaining_time": "5:43:41", "throughput": 1497.72, "total_tokens": 7475936} {"current_steps": 35435, "total_steps": 181800, "loss": 0.0664, "lr": 4.864061984181719e-05, "epoch": 3.898239823982398, "percentage": 19.49, "elapsed_time": "1:23:12", "remaining_time": "5:43:40", "throughput": 1497.73, "total_tokens": 7477024} {"current_steps": 35440, "total_steps": 181800, "loss": 0.0166, "lr": 4.863983908802026e-05, "epoch": 3.8987898789878987, "percentage": 19.49, "elapsed_time": "1:23:12", "remaining_time": "5:43:39", "throughput": 1497.73, "total_tokens": 7478048} {"current_steps": 35445, "total_steps": 181800, "loss": 0.0272, "lr": 4.863905811634626e-05, "epoch": 3.8993399339933994, "percentage": 19.5, "elapsed_time": "1:23:13", "remaining_time": "5:43:38", "throughput": 1497.72, "total_tokens": 7479008} {"current_steps": 35450, "total_steps": 181800, "loss": 0.0333, "lr": 4.86382769268024e-05, "epoch": 3.8998899889989, "percentage": 19.5, "elapsed_time": "1:23:14", "remaining_time": "5:43:38", "throughput": 1497.72, "total_tokens": 7480064} {"current_steps": 35455, "total_steps": 181800, "loss": 0.0492, "lr": 4.86374955193959e-05, "epoch": 3.9004400440044007, "percentage": 19.5, "elapsed_time": "1:23:14", "remaining_time": "5:43:37", "throughput": 1497.73, "total_tokens": 7481120} {"current_steps": 35460, "total_steps": 181800, "loss": 0.0322, "lr": 4.8636713894133946e-05, "epoch": 3.900990099009901, "percentage": 19.5, "elapsed_time": "1:23:15", "remaining_time": "5:43:36", "throughput": 1497.73, "total_tokens": 7482176} {"current_steps": 35465, "total_steps": 181800, "loss": 0.0806, "lr": 4.8635932051023734e-05, "epoch": 3.9015401540154016, "percentage": 19.51, "elapsed_time": "1:23:16", "remaining_time": "5:43:35", "throughput": 1497.73, "total_tokens": 7483200} {"current_steps": 35470, "total_steps": 181800, "loss": 0.0799, "lr": 4.8635149990072484e-05, "epoch": 3.902090209020902, "percentage": 19.51, "elapsed_time": "1:23:17", "remaining_time": "5:43:35", "throughput": 1497.74, "total_tokens": 7484256} {"current_steps": 35475, "total_steps": 181800, "loss": 0.0625, "lr": 4.86343677112874e-05, "epoch": 3.9026402640264024, "percentage": 19.51, "elapsed_time": "1:23:17", "remaining_time": "5:43:34", "throughput": 1497.76, "total_tokens": 7485408} {"current_steps": 35480, "total_steps": 181800, "loss": 0.1066, "lr": 4.863358521467568e-05, "epoch": 3.903190319031903, "percentage": 19.52, "elapsed_time": "1:23:18", "remaining_time": "5:43:33", "throughput": 1497.76, "total_tokens": 7486464} {"current_steps": 35485, "total_steps": 181800, "loss": 0.0277, "lr": 4.863280250024455e-05, "epoch": 3.9037403740374037, "percentage": 19.52, "elapsed_time": "1:23:19", "remaining_time": "5:43:32", "throughput": 1497.77, "total_tokens": 7487520} {"current_steps": 35490, "total_steps": 181800, "loss": 0.0895, "lr": 4.863201956800122e-05, "epoch": 3.9042904290429044, "percentage": 19.52, "elapsed_time": "1:23:19", "remaining_time": "5:43:32", "throughput": 1497.77, "total_tokens": 7488544} {"current_steps": 35495, "total_steps": 181800, "loss": 0.1767, "lr": 4.8631236417952905e-05, "epoch": 3.904840484048405, "percentage": 19.52, "elapsed_time": "1:23:20", "remaining_time": "5:43:31", "throughput": 1497.77, "total_tokens": 7489568} {"current_steps": 35500, "total_steps": 181800, "loss": 0.0885, "lr": 4.863045305010682e-05, "epoch": 3.905390539053905, "percentage": 19.53, "elapsed_time": "1:23:21", "remaining_time": "5:43:30", "throughput": 1497.77, "total_tokens": 7490592} {"current_steps": 35505, "total_steps": 181800, "loss": 0.1074, "lr": 4.862966946447019e-05, "epoch": 3.905940594059406, "percentage": 19.53, "elapsed_time": "1:23:21", "remaining_time": "5:43:29", "throughput": 1497.77, "total_tokens": 7491648} {"current_steps": 35510, "total_steps": 181800, "loss": 0.0894, "lr": 4.862888566105024e-05, "epoch": 3.9064906490649065, "percentage": 19.53, "elapsed_time": "1:23:22", "remaining_time": "5:43:28", "throughput": 1497.77, "total_tokens": 7492672} {"current_steps": 35515, "total_steps": 181800, "loss": 0.1276, "lr": 4.862810163985418e-05, "epoch": 3.907040704070407, "percentage": 19.54, "elapsed_time": "1:23:23", "remaining_time": "5:43:28", "throughput": 1497.77, "total_tokens": 7493728} {"current_steps": 35520, "total_steps": 181800, "loss": 0.0378, "lr": 4.862731740088926e-05, "epoch": 3.907590759075908, "percentage": 19.54, "elapsed_time": "1:23:23", "remaining_time": "5:43:27", "throughput": 1497.77, "total_tokens": 7494752} {"current_steps": 35525, "total_steps": 181800, "loss": 0.0445, "lr": 4.862653294416268e-05, "epoch": 3.908140814081408, "percentage": 19.54, "elapsed_time": "1:23:24", "remaining_time": "5:43:26", "throughput": 1497.77, "total_tokens": 7495776} {"current_steps": 35530, "total_steps": 181800, "loss": 0.0579, "lr": 4.862574826968169e-05, "epoch": 3.9086908690869087, "percentage": 19.54, "elapsed_time": "1:23:25", "remaining_time": "5:43:25", "throughput": 1497.78, "total_tokens": 7496832} {"current_steps": 35535, "total_steps": 181800, "loss": 0.0824, "lr": 4.8624963377453516e-05, "epoch": 3.9092409240924093, "percentage": 19.55, "elapsed_time": "1:23:25", "remaining_time": "5:43:25", "throughput": 1497.78, "total_tokens": 7497856} {"current_steps": 35540, "total_steps": 181800, "loss": 0.0398, "lr": 4.862417826748538e-05, "epoch": 3.9097909790979095, "percentage": 19.55, "elapsed_time": "1:23:26", "remaining_time": "5:43:24", "throughput": 1497.79, "total_tokens": 7498944} {"current_steps": 35545, "total_steps": 181800, "loss": 0.0581, "lr": 4.862339293978454e-05, "epoch": 3.9103410341034106, "percentage": 19.55, "elapsed_time": "1:23:27", "remaining_time": "5:43:23", "throughput": 1497.79, "total_tokens": 7500000} {"current_steps": 35550, "total_steps": 181800, "loss": 0.0245, "lr": 4.8622607394358215e-05, "epoch": 3.910891089108911, "percentage": 19.55, "elapsed_time": "1:23:28", "remaining_time": "5:43:22", "throughput": 1497.81, "total_tokens": 7501088} {"current_steps": 35555, "total_steps": 181800, "loss": 0.0412, "lr": 4.862182163121366e-05, "epoch": 3.9114411441144115, "percentage": 19.56, "elapsed_time": "1:23:28", "remaining_time": "5:43:21", "throughput": 1497.82, "total_tokens": 7502176} {"current_steps": 35560, "total_steps": 181800, "loss": 0.0185, "lr": 4.862103565035811e-05, "epoch": 3.911991199119912, "percentage": 19.56, "elapsed_time": "1:23:29", "remaining_time": "5:43:21", "throughput": 1497.83, "total_tokens": 7503264} {"current_steps": 35565, "total_steps": 181800, "loss": 0.026, "lr": 4.86202494517988e-05, "epoch": 3.9125412541254123, "percentage": 19.56, "elapsed_time": "1:23:30", "remaining_time": "5:43:20", "throughput": 1497.83, "total_tokens": 7504320} {"current_steps": 35570, "total_steps": 181800, "loss": 0.0208, "lr": 4.861946303554299e-05, "epoch": 3.913091309130913, "percentage": 19.57, "elapsed_time": "1:23:30", "remaining_time": "5:43:19", "throughput": 1497.83, "total_tokens": 7505344} {"current_steps": 35575, "total_steps": 181800, "loss": 0.1064, "lr": 4.861867640159792e-05, "epoch": 3.9136413641364136, "percentage": 19.57, "elapsed_time": "1:23:31", "remaining_time": "5:43:18", "throughput": 1497.84, "total_tokens": 7506432} {"current_steps": 35580, "total_steps": 181800, "loss": 0.1211, "lr": 4.861788954997085e-05, "epoch": 3.9141914191419143, "percentage": 19.57, "elapsed_time": "1:23:32", "remaining_time": "5:43:18", "throughput": 1497.85, "total_tokens": 7507488} {"current_steps": 35585, "total_steps": 181800, "loss": 0.1182, "lr": 4.861710248066902e-05, "epoch": 3.914741474147415, "percentage": 19.57, "elapsed_time": "1:23:32", "remaining_time": "5:43:17", "throughput": 1497.85, "total_tokens": 7508544} {"current_steps": 35590, "total_steps": 181800, "loss": 0.0753, "lr": 4.861631519369969e-05, "epoch": 3.915291529152915, "percentage": 19.58, "elapsed_time": "1:23:33", "remaining_time": "5:43:16", "throughput": 1497.84, "total_tokens": 7509536} {"current_steps": 35595, "total_steps": 181800, "loss": 0.0283, "lr": 4.8615527689070115e-05, "epoch": 3.9158415841584158, "percentage": 19.58, "elapsed_time": "1:23:34", "remaining_time": "5:43:15", "throughput": 1497.86, "total_tokens": 7510656} {"current_steps": 35600, "total_steps": 181800, "loss": 0.0186, "lr": 4.861473996678756e-05, "epoch": 3.9163916391639164, "percentage": 19.58, "elapsed_time": "1:23:34", "remaining_time": "5:43:15", "throughput": 1497.86, "total_tokens": 7511680} {"current_steps": 35605, "total_steps": 181800, "loss": 0.0591, "lr": 4.861395202685927e-05, "epoch": 3.916941694169417, "percentage": 19.58, "elapsed_time": "1:23:35", "remaining_time": "5:43:14", "throughput": 1497.86, "total_tokens": 7512704} {"current_steps": 35610, "total_steps": 181800, "loss": 0.0306, "lr": 4.861316386929251e-05, "epoch": 3.9174917491749177, "percentage": 19.59, "elapsed_time": "1:23:36", "remaining_time": "5:43:13", "throughput": 1497.87, "total_tokens": 7513792} {"current_steps": 35615, "total_steps": 181800, "loss": 0.0427, "lr": 4.861237549409456e-05, "epoch": 3.918041804180418, "percentage": 19.59, "elapsed_time": "1:23:37", "remaining_time": "5:43:12", "throughput": 1497.87, "total_tokens": 7514816} {"current_steps": 35620, "total_steps": 181800, "loss": 0.0966, "lr": 4.8611586901272664e-05, "epoch": 3.9185918591859186, "percentage": 19.59, "elapsed_time": "1:23:37", "remaining_time": "5:43:11", "throughput": 1497.87, "total_tokens": 7515872} {"current_steps": 35625, "total_steps": 181800, "loss": 0.0168, "lr": 4.861079809083411e-05, "epoch": 3.919141914191419, "percentage": 19.6, "elapsed_time": "1:23:38", "remaining_time": "5:43:11", "throughput": 1497.88, "total_tokens": 7516928} {"current_steps": 35630, "total_steps": 181800, "loss": 0.0348, "lr": 4.861000906278616e-05, "epoch": 3.9196919691969194, "percentage": 19.6, "elapsed_time": "1:23:39", "remaining_time": "5:43:10", "throughput": 1497.88, "total_tokens": 7517952} {"current_steps": 35635, "total_steps": 181800, "loss": 0.0663, "lr": 4.8609219817136087e-05, "epoch": 3.9202420242024205, "percentage": 19.6, "elapsed_time": "1:23:39", "remaining_time": "5:43:09", "throughput": 1497.87, "total_tokens": 7518944} {"current_steps": 35640, "total_steps": 181800, "loss": 0.0302, "lr": 4.860843035389116e-05, "epoch": 3.9207920792079207, "percentage": 19.6, "elapsed_time": "1:23:40", "remaining_time": "5:43:08", "throughput": 1497.88, "total_tokens": 7520032} {"current_steps": 35645, "total_steps": 181800, "loss": 0.0254, "lr": 4.860764067305866e-05, "epoch": 3.9213421342134214, "percentage": 19.61, "elapsed_time": "1:23:41", "remaining_time": "5:43:08", "throughput": 1497.89, "total_tokens": 7521088} {"current_steps": 35650, "total_steps": 181800, "loss": 0.0719, "lr": 4.8606850774645864e-05, "epoch": 3.921892189218922, "percentage": 19.61, "elapsed_time": "1:23:41", "remaining_time": "5:43:07", "throughput": 1497.89, "total_tokens": 7522112} {"current_steps": 35655, "total_steps": 181800, "loss": 0.0225, "lr": 4.860606065866005e-05, "epoch": 3.9224422442244222, "percentage": 19.61, "elapsed_time": "1:23:42", "remaining_time": "5:43:06", "throughput": 1497.89, "total_tokens": 7523168} {"current_steps": 35660, "total_steps": 181800, "loss": 0.0331, "lr": 4.86052703251085e-05, "epoch": 3.922992299229923, "percentage": 19.61, "elapsed_time": "1:23:43", "remaining_time": "5:43:05", "throughput": 1497.9, "total_tokens": 7524224} {"current_steps": 35665, "total_steps": 181800, "loss": 0.0504, "lr": 4.8604479773998515e-05, "epoch": 3.9235423542354235, "percentage": 19.62, "elapsed_time": "1:23:43", "remaining_time": "5:43:04", "throughput": 1497.91, "total_tokens": 7525312} {"current_steps": 35670, "total_steps": 181800, "loss": 0.0368, "lr": 4.860368900533735e-05, "epoch": 3.924092409240924, "percentage": 19.62, "elapsed_time": "1:23:44", "remaining_time": "5:43:04", "throughput": 1497.92, "total_tokens": 7526400} {"current_steps": 35675, "total_steps": 181800, "loss": 0.0372, "lr": 4.8602898019132316e-05, "epoch": 3.924642464246425, "percentage": 19.62, "elapsed_time": "1:23:45", "remaining_time": "5:43:03", "throughput": 1497.92, "total_tokens": 7527424} {"current_steps": 35680, "total_steps": 181800, "loss": 0.0287, "lr": 4.860210681539069e-05, "epoch": 3.925192519251925, "percentage": 19.63, "elapsed_time": "1:23:45", "remaining_time": "5:43:02", "throughput": 1497.93, "total_tokens": 7528512} {"current_steps": 35685, "total_steps": 181800, "loss": 0.0233, "lr": 4.860131539411978e-05, "epoch": 3.9257425742574257, "percentage": 19.63, "elapsed_time": "1:23:46", "remaining_time": "5:43:01", "throughput": 1497.93, "total_tokens": 7529536} {"current_steps": 35690, "total_steps": 181800, "loss": 0.1307, "lr": 4.8600523755326865e-05, "epoch": 3.9262926292629263, "percentage": 19.63, "elapsed_time": "1:23:47", "remaining_time": "5:43:01", "throughput": 1497.94, "total_tokens": 7530592} {"current_steps": 35695, "total_steps": 181800, "loss": 0.0185, "lr": 4.859973189901925e-05, "epoch": 3.926842684268427, "percentage": 19.63, "elapsed_time": "1:23:47", "remaining_time": "5:43:00", "throughput": 1497.93, "total_tokens": 7531584} {"current_steps": 35700, "total_steps": 181800, "loss": 0.0267, "lr": 4.859893982520424e-05, "epoch": 3.9273927392739276, "percentage": 19.64, "elapsed_time": "1:23:48", "remaining_time": "5:42:59", "throughput": 1497.92, "total_tokens": 7532576} {"current_steps": 35705, "total_steps": 181800, "loss": 0.0428, "lr": 4.859814753388911e-05, "epoch": 3.927942794279428, "percentage": 19.64, "elapsed_time": "1:23:49", "remaining_time": "5:42:58", "throughput": 1497.94, "total_tokens": 7533664} {"current_steps": 35710, "total_steps": 181800, "loss": 0.1296, "lr": 4.859735502508118e-05, "epoch": 3.9284928492849285, "percentage": 19.64, "elapsed_time": "1:23:50", "remaining_time": "5:42:57", "throughput": 1497.95, "total_tokens": 7534752} {"current_steps": 35715, "total_steps": 181800, "loss": 0.0574, "lr": 4.859656229878776e-05, "epoch": 3.929042904290429, "percentage": 19.65, "elapsed_time": "1:23:50", "remaining_time": "5:42:57", "throughput": 1497.95, "total_tokens": 7535776} {"current_steps": 35720, "total_steps": 181800, "loss": 0.0117, "lr": 4.859576935501614e-05, "epoch": 3.9295929592959293, "percentage": 19.65, "elapsed_time": "1:23:51", "remaining_time": "5:42:56", "throughput": 1497.95, "total_tokens": 7536832} {"current_steps": 35725, "total_steps": 181800, "loss": 0.0116, "lr": 4.8594976193773646e-05, "epoch": 3.93014301430143, "percentage": 19.65, "elapsed_time": "1:23:52", "remaining_time": "5:42:55", "throughput": 1497.95, "total_tokens": 7537856} {"current_steps": 35730, "total_steps": 181800, "loss": 0.1272, "lr": 4.859418281506757e-05, "epoch": 3.9306930693069306, "percentage": 19.65, "elapsed_time": "1:23:52", "remaining_time": "5:42:54", "throughput": 1497.97, "total_tokens": 7538976} {"current_steps": 35735, "total_steps": 181800, "loss": 0.0404, "lr": 4.8593389218905234e-05, "epoch": 3.9312431243124313, "percentage": 19.66, "elapsed_time": "1:23:53", "remaining_time": "5:42:54", "throughput": 1497.99, "total_tokens": 7540096} {"current_steps": 35740, "total_steps": 181800, "loss": 0.0388, "lr": 4.859259540529395e-05, "epoch": 3.931793179317932, "percentage": 19.66, "elapsed_time": "1:23:54", "remaining_time": "5:42:53", "throughput": 1497.99, "total_tokens": 7541120} {"current_steps": 35745, "total_steps": 181800, "loss": 0.1331, "lr": 4.859180137424104e-05, "epoch": 3.932343234323432, "percentage": 19.66, "elapsed_time": "1:23:54", "remaining_time": "5:42:52", "throughput": 1498.0, "total_tokens": 7542208} {"current_steps": 35750, "total_steps": 181800, "loss": 0.0183, "lr": 4.8591007125753807e-05, "epoch": 3.932893289328933, "percentage": 19.66, "elapsed_time": "1:23:55", "remaining_time": "5:42:51", "throughput": 1498.0, "total_tokens": 7543232} {"current_steps": 35755, "total_steps": 181800, "loss": 0.0618, "lr": 4.859021265983959e-05, "epoch": 3.9334433443344334, "percentage": 19.67, "elapsed_time": "1:23:56", "remaining_time": "5:42:51", "throughput": 1498.0, "total_tokens": 7544256} {"current_steps": 35760, "total_steps": 181800, "loss": 0.0792, "lr": 4.85894179765057e-05, "epoch": 3.933993399339934, "percentage": 19.67, "elapsed_time": "1:23:56", "remaining_time": "5:42:50", "throughput": 1498.01, "total_tokens": 7545376} {"current_steps": 35765, "total_steps": 181800, "loss": 0.0017, "lr": 4.858862307575947e-05, "epoch": 3.9345434543454347, "percentage": 19.67, "elapsed_time": "1:23:57", "remaining_time": "5:42:49", "throughput": 1498.03, "total_tokens": 7546464} {"current_steps": 35770, "total_steps": 181800, "loss": 0.0312, "lr": 4.858782795760821e-05, "epoch": 3.935093509350935, "percentage": 19.68, "elapsed_time": "1:23:58", "remaining_time": "5:42:48", "throughput": 1498.03, "total_tokens": 7547520} {"current_steps": 35775, "total_steps": 181800, "loss": 0.0609, "lr": 4.8587032622059263e-05, "epoch": 3.9356435643564356, "percentage": 19.68, "elapsed_time": "1:23:58", "remaining_time": "5:42:47", "throughput": 1498.03, "total_tokens": 7548544} {"current_steps": 35780, "total_steps": 181800, "loss": 0.0524, "lr": 4.8586237069119956e-05, "epoch": 3.9361936193619362, "percentage": 19.68, "elapsed_time": "1:23:59", "remaining_time": "5:42:47", "throughput": 1498.04, "total_tokens": 7549632} {"current_steps": 35785, "total_steps": 181800, "loss": 0.1745, "lr": 4.858544129879762e-05, "epoch": 3.936743674367437, "percentage": 19.68, "elapsed_time": "1:24:00", "remaining_time": "5:42:46", "throughput": 1498.04, "total_tokens": 7550656} {"current_steps": 35790, "total_steps": 181800, "loss": 0.0492, "lr": 4.858464531109959e-05, "epoch": 3.9372937293729375, "percentage": 19.69, "elapsed_time": "1:24:01", "remaining_time": "5:42:45", "throughput": 1498.04, "total_tokens": 7551712} {"current_steps": 35795, "total_steps": 181800, "loss": 0.0948, "lr": 4.858384910603319e-05, "epoch": 3.9378437843784377, "percentage": 19.69, "elapsed_time": "1:24:01", "remaining_time": "5:42:44", "throughput": 1498.05, "total_tokens": 7552768} {"current_steps": 35800, "total_steps": 181800, "loss": 0.0416, "lr": 4.858305268360578e-05, "epoch": 3.9383938393839384, "percentage": 19.69, "elapsed_time": "1:24:02", "remaining_time": "5:42:44", "throughput": 1498.04, "total_tokens": 7553792} {"current_steps": 35805, "total_steps": 181800, "loss": 0.0854, "lr": 4.858225604382469e-05, "epoch": 3.938943894389439, "percentage": 19.69, "elapsed_time": "1:24:03", "remaining_time": "5:42:43", "throughput": 1498.05, "total_tokens": 7554880} {"current_steps": 35810, "total_steps": 181800, "loss": 0.0634, "lr": 4.858145918669725e-05, "epoch": 3.9394939493949392, "percentage": 19.7, "elapsed_time": "1:24:03", "remaining_time": "5:42:42", "throughput": 1498.06, "total_tokens": 7555936} {"current_steps": 35815, "total_steps": 181800, "loss": 0.094, "lr": 4.858066211223083e-05, "epoch": 3.94004400440044, "percentage": 19.7, "elapsed_time": "1:24:04", "remaining_time": "5:42:41", "throughput": 1498.05, "total_tokens": 7556928} {"current_steps": 35820, "total_steps": 181800, "loss": 0.1515, "lr": 4.857986482043276e-05, "epoch": 3.9405940594059405, "percentage": 19.7, "elapsed_time": "1:24:05", "remaining_time": "5:42:41", "throughput": 1498.05, "total_tokens": 7557984} {"current_steps": 35825, "total_steps": 181800, "loss": 0.0665, "lr": 4.857906731131039e-05, "epoch": 3.941144114411441, "percentage": 19.71, "elapsed_time": "1:24:05", "remaining_time": "5:42:40", "throughput": 1498.06, "total_tokens": 7559072} {"current_steps": 35830, "total_steps": 181800, "loss": 0.1232, "lr": 4.8578269584871063e-05, "epoch": 3.941694169416942, "percentage": 19.71, "elapsed_time": "1:24:06", "remaining_time": "5:42:39", "throughput": 1498.08, "total_tokens": 7560160} {"current_steps": 35835, "total_steps": 181800, "loss": 0.0312, "lr": 4.8577471641122146e-05, "epoch": 3.942244224422442, "percentage": 19.71, "elapsed_time": "1:24:07", "remaining_time": "5:42:38", "throughput": 1498.08, "total_tokens": 7561184} {"current_steps": 35840, "total_steps": 181800, "loss": 0.0454, "lr": 4.857667348007099e-05, "epoch": 3.9427942794279427, "percentage": 19.71, "elapsed_time": "1:24:07", "remaining_time": "5:42:38", "throughput": 1498.07, "total_tokens": 7562208} {"current_steps": 35845, "total_steps": 181800, "loss": 0.0402, "lr": 4.857587510172494e-05, "epoch": 3.9433443344334433, "percentage": 19.72, "elapsed_time": "1:24:08", "remaining_time": "5:42:37", "throughput": 1498.07, "total_tokens": 7563200} {"current_steps": 35850, "total_steps": 181800, "loss": 0.0263, "lr": 4.857507650609137e-05, "epoch": 3.943894389438944, "percentage": 19.72, "elapsed_time": "1:24:09", "remaining_time": "5:42:36", "throughput": 1498.07, "total_tokens": 7564256} {"current_steps": 35855, "total_steps": 181800, "loss": 0.0231, "lr": 4.857427769317762e-05, "epoch": 3.9444444444444446, "percentage": 19.72, "elapsed_time": "1:24:10", "remaining_time": "5:42:35", "throughput": 1498.08, "total_tokens": 7565312} {"current_steps": 35860, "total_steps": 181800, "loss": 0.0654, "lr": 4.857347866299108e-05, "epoch": 3.944994499449945, "percentage": 19.72, "elapsed_time": "1:24:10", "remaining_time": "5:42:34", "throughput": 1498.07, "total_tokens": 7566336} {"current_steps": 35865, "total_steps": 181800, "loss": 0.0612, "lr": 4.857267941553908e-05, "epoch": 3.9455445544554455, "percentage": 19.73, "elapsed_time": "1:24:11", "remaining_time": "5:42:34", "throughput": 1498.07, "total_tokens": 7567360} {"current_steps": 35870, "total_steps": 181800, "loss": 0.0434, "lr": 4.8571879950829026e-05, "epoch": 3.946094609460946, "percentage": 19.73, "elapsed_time": "1:24:12", "remaining_time": "5:42:33", "throughput": 1498.09, "total_tokens": 7568480} {"current_steps": 35875, "total_steps": 181800, "loss": 0.082, "lr": 4.857108026886825e-05, "epoch": 3.946644664466447, "percentage": 19.73, "elapsed_time": "1:24:12", "remaining_time": "5:42:32", "throughput": 1498.09, "total_tokens": 7569536} {"current_steps": 35880, "total_steps": 181800, "loss": 0.0989, "lr": 4.857028036966415e-05, "epoch": 3.9471947194719474, "percentage": 19.74, "elapsed_time": "1:24:13", "remaining_time": "5:42:31", "throughput": 1498.09, "total_tokens": 7570560} {"current_steps": 35885, "total_steps": 181800, "loss": 0.0848, "lr": 4.856948025322407e-05, "epoch": 3.9477447744774476, "percentage": 19.74, "elapsed_time": "1:24:14", "remaining_time": "5:42:31", "throughput": 1498.09, "total_tokens": 7571584} {"current_steps": 35890, "total_steps": 181800, "loss": 0.026, "lr": 4.856867991955542e-05, "epoch": 3.9482948294829483, "percentage": 19.74, "elapsed_time": "1:24:14", "remaining_time": "5:42:30", "throughput": 1498.1, "total_tokens": 7572672} {"current_steps": 35895, "total_steps": 181800, "loss": 0.1273, "lr": 4.8567879368665536e-05, "epoch": 3.948844884488449, "percentage": 19.74, "elapsed_time": "1:24:15", "remaining_time": "5:42:29", "throughput": 1498.1, "total_tokens": 7573728} {"current_steps": 35900, "total_steps": 181800, "loss": 0.1662, "lr": 4.8567078600561834e-05, "epoch": 3.949394939493949, "percentage": 19.75, "elapsed_time": "1:24:16", "remaining_time": "5:42:28", "throughput": 1498.1, "total_tokens": 7574752} {"current_steps": 35905, "total_steps": 181800, "loss": 0.1173, "lr": 4.8566277615251665e-05, "epoch": 3.94994499449945, "percentage": 19.75, "elapsed_time": "1:24:16", "remaining_time": "5:42:28", "throughput": 1498.11, "total_tokens": 7575840} {"current_steps": 35910, "total_steps": 181800, "loss": 0.073, "lr": 4.856547641274243e-05, "epoch": 3.9504950495049505, "percentage": 19.75, "elapsed_time": "1:24:17", "remaining_time": "5:42:27", "throughput": 1498.12, "total_tokens": 7576896} {"current_steps": 35915, "total_steps": 181800, "loss": 0.0338, "lr": 4.856467499304151e-05, "epoch": 3.951045104510451, "percentage": 19.76, "elapsed_time": "1:24:18", "remaining_time": "5:42:26", "throughput": 1498.12, "total_tokens": 7577952} {"current_steps": 35920, "total_steps": 181800, "loss": 0.0123, "lr": 4.856387335615628e-05, "epoch": 3.9515951595159517, "percentage": 19.76, "elapsed_time": "1:24:18", "remaining_time": "5:42:25", "throughput": 1498.13, "total_tokens": 7579008} {"current_steps": 35925, "total_steps": 181800, "loss": 0.0393, "lr": 4.856307150209414e-05, "epoch": 3.952145214521452, "percentage": 19.76, "elapsed_time": "1:24:19", "remaining_time": "5:42:24", "throughput": 1498.14, "total_tokens": 7580096} {"current_steps": 35930, "total_steps": 181800, "loss": 0.1098, "lr": 4.8562269430862475e-05, "epoch": 3.9526952695269526, "percentage": 19.76, "elapsed_time": "1:24:20", "remaining_time": "5:42:24", "throughput": 1498.14, "total_tokens": 7581120} {"current_steps": 35935, "total_steps": 181800, "loss": 0.0377, "lr": 4.8561467142468674e-05, "epoch": 3.9532453245324533, "percentage": 19.77, "elapsed_time": "1:24:21", "remaining_time": "5:42:23", "throughput": 1498.14, "total_tokens": 7582144} {"current_steps": 35940, "total_steps": 181800, "loss": 0.0382, "lr": 4.856066463692015e-05, "epoch": 3.953795379537954, "percentage": 19.77, "elapsed_time": "1:24:21", "remaining_time": "5:42:22", "throughput": 1498.13, "total_tokens": 7583168} {"current_steps": 35945, "total_steps": 181800, "loss": 0.0384, "lr": 4.855986191422427e-05, "epoch": 3.9543454345434546, "percentage": 19.77, "elapsed_time": "1:24:22", "remaining_time": "5:42:21", "throughput": 1498.13, "total_tokens": 7584192} {"current_steps": 35950, "total_steps": 181800, "loss": 0.0193, "lr": 4.855905897438846e-05, "epoch": 3.9548954895489548, "percentage": 19.77, "elapsed_time": "1:24:23", "remaining_time": "5:42:21", "throughput": 1498.14, "total_tokens": 7585248} {"current_steps": 35955, "total_steps": 181800, "loss": 0.0699, "lr": 4.855825581742011e-05, "epoch": 3.9554455445544554, "percentage": 19.78, "elapsed_time": "1:24:23", "remaining_time": "5:42:20", "throughput": 1498.14, "total_tokens": 7586272} {"current_steps": 35960, "total_steps": 181800, "loss": 0.0858, "lr": 4.8557452443326615e-05, "epoch": 3.955995599559956, "percentage": 19.78, "elapsed_time": "1:24:24", "remaining_time": "5:42:19", "throughput": 1498.14, "total_tokens": 7587328} {"current_steps": 35965, "total_steps": 181800, "loss": 0.1078, "lr": 4.8556648852115375e-05, "epoch": 3.9565456545654567, "percentage": 19.78, "elapsed_time": "1:24:25", "remaining_time": "5:42:18", "throughput": 1498.15, "total_tokens": 7588384} {"current_steps": 35970, "total_steps": 181800, "loss": 0.088, "lr": 4.8555845043793816e-05, "epoch": 3.9570957095709574, "percentage": 19.79, "elapsed_time": "1:24:25", "remaining_time": "5:42:18", "throughput": 1498.15, "total_tokens": 7589440} {"current_steps": 35975, "total_steps": 181800, "loss": 0.0165, "lr": 4.855504101836934e-05, "epoch": 3.9576457645764576, "percentage": 19.79, "elapsed_time": "1:24:26", "remaining_time": "5:42:17", "throughput": 1498.16, "total_tokens": 7590496} {"current_steps": 35980, "total_steps": 181800, "loss": 0.1204, "lr": 4.855423677584935e-05, "epoch": 3.958195819581958, "percentage": 19.79, "elapsed_time": "1:24:27", "remaining_time": "5:42:16", "throughput": 1498.17, "total_tokens": 7591584} {"current_steps": 35985, "total_steps": 181800, "loss": 0.0085, "lr": 4.855343231624125e-05, "epoch": 3.958745874587459, "percentage": 19.79, "elapsed_time": "1:24:27", "remaining_time": "5:42:15", "throughput": 1498.17, "total_tokens": 7592608} {"current_steps": 35990, "total_steps": 181800, "loss": 0.0651, "lr": 4.8552627639552485e-05, "epoch": 3.959295929592959, "percentage": 19.8, "elapsed_time": "1:24:28", "remaining_time": "5:42:14", "throughput": 1498.18, "total_tokens": 7593696} {"current_steps": 35995, "total_steps": 181800, "loss": 0.0342, "lr": 4.8551822745790445e-05, "epoch": 3.9598459845984597, "percentage": 19.8, "elapsed_time": "1:24:29", "remaining_time": "5:42:14", "throughput": 1498.2, "total_tokens": 7594816} {"current_steps": 36000, "total_steps": 181800, "loss": 0.0368, "lr": 4.855101763496256e-05, "epoch": 3.9603960396039604, "percentage": 19.8, "elapsed_time": "1:24:29", "remaining_time": "5:42:13", "throughput": 1498.19, "total_tokens": 7595808} {"current_steps": 36005, "total_steps": 181800, "loss": 0.0789, "lr": 4.855021230707624e-05, "epoch": 3.960946094609461, "percentage": 19.8, "elapsed_time": "1:24:30", "remaining_time": "5:42:12", "throughput": 1498.2, "total_tokens": 7596864} {"current_steps": 36010, "total_steps": 181800, "loss": 0.0486, "lr": 4.854940676213892e-05, "epoch": 3.9614961496149617, "percentage": 19.81, "elapsed_time": "1:24:31", "remaining_time": "5:42:11", "throughput": 1498.2, "total_tokens": 7597920} {"current_steps": 36015, "total_steps": 181800, "loss": 0.0205, "lr": 4.854860100015801e-05, "epoch": 3.962046204620462, "percentage": 19.81, "elapsed_time": "1:24:32", "remaining_time": "5:42:11", "throughput": 1498.2, "total_tokens": 7598912} {"current_steps": 36020, "total_steps": 181800, "loss": 0.0605, "lr": 4.854779502114095e-05, "epoch": 3.9625962596259625, "percentage": 19.81, "elapsed_time": "1:24:32", "remaining_time": "5:42:10", "throughput": 1498.2, "total_tokens": 7599936} {"current_steps": 36025, "total_steps": 181800, "loss": 0.0729, "lr": 4.854698882509516e-05, "epoch": 3.963146314631463, "percentage": 19.82, "elapsed_time": "1:24:33", "remaining_time": "5:42:09", "throughput": 1498.2, "total_tokens": 7600992} {"current_steps": 36030, "total_steps": 181800, "loss": 0.0709, "lr": 4.8546182412028075e-05, "epoch": 3.963696369636964, "percentage": 19.82, "elapsed_time": "1:24:34", "remaining_time": "5:42:08", "throughput": 1498.2, "total_tokens": 7602016} {"current_steps": 36035, "total_steps": 181800, "loss": 0.0913, "lr": 4.854537578194712e-05, "epoch": 3.9642464246424645, "percentage": 19.82, "elapsed_time": "1:24:34", "remaining_time": "5:42:07", "throughput": 1498.21, "total_tokens": 7603072} {"current_steps": 36040, "total_steps": 181800, "loss": 0.125, "lr": 4.854456893485975e-05, "epoch": 3.9647964796479647, "percentage": 19.82, "elapsed_time": "1:24:35", "remaining_time": "5:42:07", "throughput": 1498.19, "total_tokens": 7604032} {"current_steps": 36045, "total_steps": 181800, "loss": 0.0109, "lr": 4.854376187077337e-05, "epoch": 3.9653465346534653, "percentage": 19.83, "elapsed_time": "1:24:36", "remaining_time": "5:42:06", "throughput": 1498.2, "total_tokens": 7605120} {"current_steps": 36050, "total_steps": 181800, "loss": 0.027, "lr": 4.854295458969544e-05, "epoch": 3.965896589658966, "percentage": 19.83, "elapsed_time": "1:24:36", "remaining_time": "5:42:05", "throughput": 1498.19, "total_tokens": 7606112} {"current_steps": 36055, "total_steps": 181800, "loss": 0.0316, "lr": 4.854214709163339e-05, "epoch": 3.966446644664466, "percentage": 19.83, "elapsed_time": "1:24:37", "remaining_time": "5:42:04", "throughput": 1498.2, "total_tokens": 7607168} {"current_steps": 36060, "total_steps": 181800, "loss": 0.011, "lr": 4.854133937659467e-05, "epoch": 3.9669966996699673, "percentage": 19.83, "elapsed_time": "1:24:38", "remaining_time": "5:42:04", "throughput": 1498.21, "total_tokens": 7608256} {"current_steps": 36065, "total_steps": 181800, "loss": 0.0994, "lr": 4.854053144458672e-05, "epoch": 3.9675467546754675, "percentage": 19.84, "elapsed_time": "1:24:38", "remaining_time": "5:42:03", "throughput": 1498.21, "total_tokens": 7609280} {"current_steps": 36070, "total_steps": 181800, "loss": 0.1534, "lr": 4.8539723295616994e-05, "epoch": 3.968096809680968, "percentage": 19.84, "elapsed_time": "1:24:39", "remaining_time": "5:42:02", "throughput": 1498.21, "total_tokens": 7610336} {"current_steps": 36075, "total_steps": 181800, "loss": 0.1159, "lr": 4.853891492969293e-05, "epoch": 3.9686468646864688, "percentage": 19.84, "elapsed_time": "1:24:40", "remaining_time": "5:42:01", "throughput": 1498.23, "total_tokens": 7611456} {"current_steps": 36080, "total_steps": 181800, "loss": 0.1144, "lr": 4.853810634682198e-05, "epoch": 3.969196919691969, "percentage": 19.85, "elapsed_time": "1:24:40", "remaining_time": "5:42:01", "throughput": 1498.25, "total_tokens": 7612576} {"current_steps": 36085, "total_steps": 181800, "loss": 0.23, "lr": 4.85372975470116e-05, "epoch": 3.9697469746974696, "percentage": 19.85, "elapsed_time": "1:24:41", "remaining_time": "5:42:00", "throughput": 1498.26, "total_tokens": 7613696} {"current_steps": 36090, "total_steps": 181800, "loss": 0.1003, "lr": 4.853648853026924e-05, "epoch": 3.9702970297029703, "percentage": 19.85, "elapsed_time": "1:24:42", "remaining_time": "5:41:59", "throughput": 1498.26, "total_tokens": 7614720} {"current_steps": 36095, "total_steps": 181800, "loss": 0.0574, "lr": 4.853567929660237e-05, "epoch": 3.970847084708471, "percentage": 19.85, "elapsed_time": "1:24:43", "remaining_time": "5:41:58", "throughput": 1498.27, "total_tokens": 7615776} {"current_steps": 36100, "total_steps": 181800, "loss": 0.0101, "lr": 4.853486984601843e-05, "epoch": 3.9713971397139716, "percentage": 19.86, "elapsed_time": "1:24:43", "remaining_time": "5:41:58", "throughput": 1498.27, "total_tokens": 7616800} {"current_steps": 36105, "total_steps": 181800, "loss": 0.1147, "lr": 4.853406017852488e-05, "epoch": 3.9719471947194718, "percentage": 19.86, "elapsed_time": "1:24:44", "remaining_time": "5:41:57", "throughput": 1498.28, "total_tokens": 7617920} {"current_steps": 36110, "total_steps": 181800, "loss": 0.0293, "lr": 4.85332502941292e-05, "epoch": 3.9724972497249724, "percentage": 19.86, "elapsed_time": "1:24:45", "remaining_time": "5:41:56", "throughput": 1498.29, "total_tokens": 7619008} {"current_steps": 36115, "total_steps": 181800, "loss": 0.0482, "lr": 4.853244019283884e-05, "epoch": 3.973047304730473, "percentage": 19.87, "elapsed_time": "1:24:45", "remaining_time": "5:41:55", "throughput": 1498.3, "total_tokens": 7620064} {"current_steps": 36120, "total_steps": 181800, "loss": 0.0622, "lr": 4.853162987466128e-05, "epoch": 3.9735973597359737, "percentage": 19.87, "elapsed_time": "1:24:46", "remaining_time": "5:41:55", "throughput": 1498.31, "total_tokens": 7621184} {"current_steps": 36125, "total_steps": 181800, "loss": 0.0397, "lr": 4.853081933960396e-05, "epoch": 3.9741474147414744, "percentage": 19.87, "elapsed_time": "1:24:47", "remaining_time": "5:41:54", "throughput": 1498.34, "total_tokens": 7622336} {"current_steps": 36130, "total_steps": 181800, "loss": 0.1568, "lr": 4.8530008587674386e-05, "epoch": 3.9746974697469746, "percentage": 19.87, "elapsed_time": "1:24:47", "remaining_time": "5:41:53", "throughput": 1498.35, "total_tokens": 7623456} {"current_steps": 36135, "total_steps": 181800, "loss": 0.064, "lr": 4.852919761888001e-05, "epoch": 3.9752475247524752, "percentage": 19.88, "elapsed_time": "1:24:48", "remaining_time": "5:41:52", "throughput": 1498.36, "total_tokens": 7624512} {"current_steps": 36140, "total_steps": 181800, "loss": 0.0137, "lr": 4.8528386433228306e-05, "epoch": 3.975797579757976, "percentage": 19.88, "elapsed_time": "1:24:49", "remaining_time": "5:41:51", "throughput": 1498.36, "total_tokens": 7625536} {"current_steps": 36145, "total_steps": 181800, "loss": 0.0928, "lr": 4.8527575030726755e-05, "epoch": 3.976347634763476, "percentage": 19.88, "elapsed_time": "1:24:49", "remaining_time": "5:41:51", "throughput": 1498.36, "total_tokens": 7626592} {"current_steps": 36150, "total_steps": 181800, "loss": 0.0768, "lr": 4.852676341138284e-05, "epoch": 3.976897689768977, "percentage": 19.88, "elapsed_time": "1:24:50", "remaining_time": "5:41:50", "throughput": 1498.37, "total_tokens": 7627680} {"current_steps": 36155, "total_steps": 181800, "loss": 0.01, "lr": 4.852595157520403e-05, "epoch": 3.9774477447744774, "percentage": 19.89, "elapsed_time": "1:24:51", "remaining_time": "5:41:49", "throughput": 1498.38, "total_tokens": 7628736} {"current_steps": 36160, "total_steps": 181800, "loss": 0.1131, "lr": 4.852513952219782e-05, "epoch": 3.977997799779978, "percentage": 19.89, "elapsed_time": "1:24:52", "remaining_time": "5:41:48", "throughput": 1498.37, "total_tokens": 7629728} {"current_steps": 36165, "total_steps": 181800, "loss": 0.0452, "lr": 4.852432725237168e-05, "epoch": 3.9785478547854787, "percentage": 19.89, "elapsed_time": "1:24:52", "remaining_time": "5:41:48", "throughput": 1498.38, "total_tokens": 7630816} {"current_steps": 36170, "total_steps": 181800, "loss": 0.045, "lr": 4.85235147657331e-05, "epoch": 3.979097909790979, "percentage": 19.9, "elapsed_time": "1:24:53", "remaining_time": "5:41:47", "throughput": 1498.39, "total_tokens": 7631872} {"current_steps": 36175, "total_steps": 181800, "loss": 0.0978, "lr": 4.8522702062289584e-05, "epoch": 3.9796479647964795, "percentage": 19.9, "elapsed_time": "1:24:54", "remaining_time": "5:41:46", "throughput": 1498.4, "total_tokens": 7632992} {"current_steps": 36180, "total_steps": 181800, "loss": 0.0324, "lr": 4.85218891420486e-05, "epoch": 3.98019801980198, "percentage": 19.9, "elapsed_time": "1:24:54", "remaining_time": "5:41:45", "throughput": 1498.41, "total_tokens": 7634048} {"current_steps": 36185, "total_steps": 181800, "loss": 0.0338, "lr": 4.852107600501766e-05, "epoch": 3.980748074807481, "percentage": 19.9, "elapsed_time": "1:24:55", "remaining_time": "5:41:45", "throughput": 1498.42, "total_tokens": 7635168} {"current_steps": 36190, "total_steps": 181800, "loss": 0.0596, "lr": 4.852026265120424e-05, "epoch": 3.9812981298129815, "percentage": 19.91, "elapsed_time": "1:24:56", "remaining_time": "5:41:44", "throughput": 1498.44, "total_tokens": 7636288} {"current_steps": 36195, "total_steps": 181800, "loss": 0.043, "lr": 4.8519449080615855e-05, "epoch": 3.9818481848184817, "percentage": 19.91, "elapsed_time": "1:24:56", "remaining_time": "5:41:43", "throughput": 1498.44, "total_tokens": 7637312} {"current_steps": 36200, "total_steps": 181800, "loss": 0.149, "lr": 4.8518635293259987e-05, "epoch": 3.9823982398239823, "percentage": 19.91, "elapsed_time": "1:24:57", "remaining_time": "5:41:42", "throughput": 1498.45, "total_tokens": 7638400} {"current_steps": 36205, "total_steps": 181800, "loss": 0.019, "lr": 4.851782128914414e-05, "epoch": 3.982948294829483, "percentage": 19.91, "elapsed_time": "1:24:58", "remaining_time": "5:41:42", "throughput": 1498.46, "total_tokens": 7639488} {"current_steps": 36210, "total_steps": 181800, "loss": 0.0165, "lr": 4.8517007068275825e-05, "epoch": 3.9834983498349836, "percentage": 19.92, "elapsed_time": "1:24:58", "remaining_time": "5:41:41", "throughput": 1498.46, "total_tokens": 7640512} {"current_steps": 36215, "total_steps": 181800, "loss": 0.0049, "lr": 4.851619263066254e-05, "epoch": 3.9840484048404843, "percentage": 19.92, "elapsed_time": "1:24:59", "remaining_time": "5:41:40", "throughput": 1498.46, "total_tokens": 7641568} {"current_steps": 36220, "total_steps": 181800, "loss": 0.0231, "lr": 4.8515377976311795e-05, "epoch": 3.9845984598459845, "percentage": 19.92, "elapsed_time": "1:25:00", "remaining_time": "5:41:39", "throughput": 1498.46, "total_tokens": 7642592} {"current_steps": 36225, "total_steps": 181800, "loss": 0.078, "lr": 4.851456310523108e-05, "epoch": 3.985148514851485, "percentage": 19.93, "elapsed_time": "1:25:00", "remaining_time": "5:41:38", "throughput": 1498.47, "total_tokens": 7643648} {"current_steps": 36230, "total_steps": 181800, "loss": 0.1433, "lr": 4.8513748017427934e-05, "epoch": 3.985698569856986, "percentage": 19.93, "elapsed_time": "1:25:01", "remaining_time": "5:41:38", "throughput": 1498.48, "total_tokens": 7644768} {"current_steps": 36235, "total_steps": 181800, "loss": 0.0775, "lr": 4.8512932712909856e-05, "epoch": 3.986248624862486, "percentage": 19.93, "elapsed_time": "1:25:02", "remaining_time": "5:41:37", "throughput": 1498.49, "total_tokens": 7645856} {"current_steps": 36240, "total_steps": 181800, "loss": 0.0605, "lr": 4.8512117191684355e-05, "epoch": 3.9867986798679866, "percentage": 19.93, "elapsed_time": "1:25:03", "remaining_time": "5:41:36", "throughput": 1498.5, "total_tokens": 7646912} {"current_steps": 36245, "total_steps": 181800, "loss": 0.1035, "lr": 4.851130145375895e-05, "epoch": 3.9873487348734873, "percentage": 19.94, "elapsed_time": "1:25:03", "remaining_time": "5:41:35", "throughput": 1498.5, "total_tokens": 7647936} {"current_steps": 36250, "total_steps": 181800, "loss": 0.1561, "lr": 4.851048549914117e-05, "epoch": 3.987898789878988, "percentage": 19.94, "elapsed_time": "1:25:04", "remaining_time": "5:41:35", "throughput": 1498.49, "total_tokens": 7648960} {"current_steps": 36255, "total_steps": 181800, "loss": 0.1416, "lr": 4.8509669327838514e-05, "epoch": 3.9884488448844886, "percentage": 19.94, "elapsed_time": "1:25:05", "remaining_time": "5:41:34", "throughput": 1498.49, "total_tokens": 7649984} {"current_steps": 36260, "total_steps": 181800, "loss": 0.0277, "lr": 4.850885293985853e-05, "epoch": 3.988998899889989, "percentage": 19.94, "elapsed_time": "1:25:05", "remaining_time": "5:41:33", "throughput": 1498.5, "total_tokens": 7651040} {"current_steps": 36265, "total_steps": 181800, "loss": 0.0276, "lr": 4.850803633520872e-05, "epoch": 3.9895489548954894, "percentage": 19.95, "elapsed_time": "1:25:06", "remaining_time": "5:41:32", "throughput": 1498.51, "total_tokens": 7652128} {"current_steps": 36270, "total_steps": 181800, "loss": 0.0147, "lr": 4.850721951389662e-05, "epoch": 3.99009900990099, "percentage": 19.95, "elapsed_time": "1:25:07", "remaining_time": "5:41:32", "throughput": 1498.52, "total_tokens": 7653216} {"current_steps": 36275, "total_steps": 181800, "loss": 0.1222, "lr": 4.850640247592976e-05, "epoch": 3.9906490649064907, "percentage": 19.95, "elapsed_time": "1:25:07", "remaining_time": "5:41:31", "throughput": 1498.53, "total_tokens": 7654272} {"current_steps": 36280, "total_steps": 181800, "loss": 0.1314, "lr": 4.8505585221315666e-05, "epoch": 3.9911991199119914, "percentage": 19.96, "elapsed_time": "1:25:08", "remaining_time": "5:41:30", "throughput": 1498.53, "total_tokens": 7655328} {"current_steps": 36285, "total_steps": 181800, "loss": 0.0473, "lr": 4.850476775006188e-05, "epoch": 3.9917491749174916, "percentage": 19.96, "elapsed_time": "1:25:09", "remaining_time": "5:41:29", "throughput": 1498.54, "total_tokens": 7656416} {"current_steps": 36290, "total_steps": 181800, "loss": 0.0425, "lr": 4.8503950062175916e-05, "epoch": 3.9922992299229922, "percentage": 19.96, "elapsed_time": "1:25:09", "remaining_time": "5:41:29", "throughput": 1498.55, "total_tokens": 7657472} {"current_steps": 36295, "total_steps": 181800, "loss": 0.0794, "lr": 4.850313215766533e-05, "epoch": 3.992849284928493, "percentage": 19.96, "elapsed_time": "1:25:10", "remaining_time": "5:41:28", "throughput": 1498.54, "total_tokens": 7658464} {"current_steps": 36300, "total_steps": 181800, "loss": 0.0972, "lr": 4.850231403653766e-05, "epoch": 3.9933993399339935, "percentage": 19.97, "elapsed_time": "1:25:11", "remaining_time": "5:41:27", "throughput": 1498.54, "total_tokens": 7659488} {"current_steps": 36305, "total_steps": 181800, "loss": 0.0582, "lr": 4.850149569880042e-05, "epoch": 3.993949394939494, "percentage": 19.97, "elapsed_time": "1:25:12", "remaining_time": "5:41:26", "throughput": 1498.55, "total_tokens": 7660608} {"current_steps": 36310, "total_steps": 181800, "loss": 0.0627, "lr": 4.850067714446118e-05, "epoch": 3.9944994499449944, "percentage": 19.97, "elapsed_time": "1:25:12", "remaining_time": "5:41:25", "throughput": 1498.56, "total_tokens": 7661664} {"current_steps": 36315, "total_steps": 181800, "loss": 0.0409, "lr": 4.849985837352749e-05, "epoch": 3.995049504950495, "percentage": 19.98, "elapsed_time": "1:25:13", "remaining_time": "5:41:25", "throughput": 1498.55, "total_tokens": 7662688} {"current_steps": 36320, "total_steps": 181800, "loss": 0.0473, "lr": 4.8499039386006864e-05, "epoch": 3.9955995599559957, "percentage": 19.98, "elapsed_time": "1:25:14", "remaining_time": "5:41:24", "throughput": 1498.56, "total_tokens": 7663744} {"current_steps": 36325, "total_steps": 181800, "loss": 0.0296, "lr": 4.849822018190687e-05, "epoch": 3.996149614961496, "percentage": 19.98, "elapsed_time": "1:25:14", "remaining_time": "5:41:23", "throughput": 1498.57, "total_tokens": 7664832} {"current_steps": 36330, "total_steps": 181800, "loss": 0.1328, "lr": 4.8497400761235056e-05, "epoch": 3.9966996699669965, "percentage": 19.98, "elapsed_time": "1:25:15", "remaining_time": "5:41:22", "throughput": 1498.56, "total_tokens": 7665856} {"current_steps": 36335, "total_steps": 181800, "loss": 0.0137, "lr": 4.8496581123998976e-05, "epoch": 3.997249724972497, "percentage": 19.99, "elapsed_time": "1:25:16", "remaining_time": "5:41:22", "throughput": 1498.57, "total_tokens": 7666912} {"current_steps": 36340, "total_steps": 181800, "loss": 0.0184, "lr": 4.8495761270206184e-05, "epoch": 3.997799779977998, "percentage": 19.99, "elapsed_time": "1:25:16", "remaining_time": "5:41:21", "throughput": 1498.56, "total_tokens": 7667904} {"current_steps": 36345, "total_steps": 181800, "loss": 0.015, "lr": 4.8494941199864235e-05, "epoch": 3.9983498349834985, "percentage": 19.99, "elapsed_time": "1:25:17", "remaining_time": "5:41:20", "throughput": 1498.58, "total_tokens": 7669024} {"current_steps": 36350, "total_steps": 181800, "loss": 0.0423, "lr": 4.849412091298069e-05, "epoch": 3.9988998899889987, "percentage": 19.99, "elapsed_time": "1:25:18", "remaining_time": "5:41:19", "throughput": 1498.57, "total_tokens": 7670016} {"current_steps": 36355, "total_steps": 181800, "loss": 0.1273, "lr": 4.84933004095631e-05, "epoch": 3.9994499449944994, "percentage": 20.0, "elapsed_time": "1:25:18", "remaining_time": "5:41:19", "throughput": 1498.57, "total_tokens": 7671072} {"current_steps": 36360, "total_steps": 181800, "loss": 0.2799, "lr": 4.8492479689619036e-05, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "1:25:19", "remaining_time": "5:41:18", "throughput": 1498.54, "total_tokens": 7672000} {"current_steps": 36360, "total_steps": 181800, "eval_loss": 0.06972524523735046, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "1:25:56", "remaining_time": "5:43:46", "throughput": 1487.79, "total_tokens": 7672000} {"current_steps": 36365, "total_steps": 181800, "loss": 0.0687, "lr": 4.849165875315606e-05, "epoch": 4.0005500550055, "percentage": 20.0, "elapsed_time": "1:25:58", "remaining_time": "5:43:50", "throughput": 1487.46, "total_tokens": 7673024} {"current_steps": 36370, "total_steps": 181800, "loss": 0.0794, "lr": 4.849083760018174e-05, "epoch": 4.001100110011001, "percentage": 20.01, "elapsed_time": "1:25:59", "remaining_time": "5:43:49", "throughput": 1487.47, "total_tokens": 7674144} {"current_steps": 36375, "total_steps": 181800, "loss": 0.1, "lr": 4.849001623070364e-05, "epoch": 4.0016501650165015, "percentage": 20.01, "elapsed_time": "1:25:59", "remaining_time": "5:43:48", "throughput": 1487.47, "total_tokens": 7675168} {"current_steps": 36380, "total_steps": 181800, "loss": 0.1086, "lr": 4.848919464472933e-05, "epoch": 4.002200220022003, "percentage": 20.01, "elapsed_time": "1:26:00", "remaining_time": "5:43:48", "throughput": 1487.46, "total_tokens": 7676192} {"current_steps": 36385, "total_steps": 181800, "loss": 0.0462, "lr": 4.8488372842266386e-05, "epoch": 4.002750275027503, "percentage": 20.01, "elapsed_time": "1:26:01", "remaining_time": "5:43:47", "throughput": 1487.48, "total_tokens": 7677312} {"current_steps": 36390, "total_steps": 181800, "loss": 0.0844, "lr": 4.848755082332238e-05, "epoch": 4.003300330033003, "percentage": 20.02, "elapsed_time": "1:26:01", "remaining_time": "5:43:46", "throughput": 1487.48, "total_tokens": 7678368} {"current_steps": 36395, "total_steps": 181800, "loss": 0.0649, "lr": 4.848672858790488e-05, "epoch": 4.003850385038504, "percentage": 20.02, "elapsed_time": "1:26:02", "remaining_time": "5:43:45", "throughput": 1487.5, "total_tokens": 7679488} {"current_steps": 36400, "total_steps": 181800, "loss": 0.0681, "lr": 4.848590613602148e-05, "epoch": 4.004400440044004, "percentage": 20.02, "elapsed_time": "1:26:03", "remaining_time": "5:43:45", "throughput": 1487.48, "total_tokens": 7680448} {"current_steps": 36405, "total_steps": 181800, "loss": 0.0152, "lr": 4.8485083467679756e-05, "epoch": 4.0049504950495045, "percentage": 20.02, "elapsed_time": "1:26:04", "remaining_time": "5:43:45", "throughput": 1487.44, "total_tokens": 7681472} {"current_steps": 36410, "total_steps": 181800, "loss": 0.0267, "lr": 4.8484260582887284e-05, "epoch": 4.005500550055006, "percentage": 20.03, "elapsed_time": "1:26:04", "remaining_time": "5:43:44", "throughput": 1487.45, "total_tokens": 7682592} {"current_steps": 36415, "total_steps": 181800, "loss": 0.008, "lr": 4.848343748165165e-05, "epoch": 4.006050605060506, "percentage": 20.03, "elapsed_time": "1:26:05", "remaining_time": "5:43:43", "throughput": 1487.45, "total_tokens": 7683616} {"current_steps": 36420, "total_steps": 181800, "loss": 0.0388, "lr": 4.848261416398044e-05, "epoch": 4.006600660066007, "percentage": 20.03, "elapsed_time": "1:26:06", "remaining_time": "5:43:42", "throughput": 1487.46, "total_tokens": 7684704} {"current_steps": 36425, "total_steps": 181800, "loss": 0.0133, "lr": 4.848179062988125e-05, "epoch": 4.007150715071507, "percentage": 20.04, "elapsed_time": "1:26:07", "remaining_time": "5:43:42", "throughput": 1487.46, "total_tokens": 7685760} {"current_steps": 36430, "total_steps": 181800, "loss": 0.067, "lr": 4.848096687936165e-05, "epoch": 4.007700770077007, "percentage": 20.04, "elapsed_time": "1:26:07", "remaining_time": "5:43:41", "throughput": 1487.48, "total_tokens": 7686912} {"current_steps": 36435, "total_steps": 181800, "loss": 0.0493, "lr": 4.848014291242926e-05, "epoch": 4.008250825082508, "percentage": 20.04, "elapsed_time": "1:26:08", "remaining_time": "5:43:40", "throughput": 1487.51, "total_tokens": 7688096} {"current_steps": 36440, "total_steps": 181800, "loss": 0.0666, "lr": 4.847931872909166e-05, "epoch": 4.008800880088009, "percentage": 20.04, "elapsed_time": "1:26:09", "remaining_time": "5:43:39", "throughput": 1487.52, "total_tokens": 7689152} {"current_steps": 36445, "total_steps": 181800, "loss": 0.0324, "lr": 4.847849432935644e-05, "epoch": 4.00935093509351, "percentage": 20.05, "elapsed_time": "1:26:09", "remaining_time": "5:43:38", "throughput": 1487.51, "total_tokens": 7690112} {"current_steps": 36450, "total_steps": 181800, "loss": 0.0838, "lr": 4.84776697132312e-05, "epoch": 4.00990099009901, "percentage": 20.05, "elapsed_time": "1:26:10", "remaining_time": "5:43:38", "throughput": 1487.52, "total_tokens": 7691200} {"current_steps": 36455, "total_steps": 181800, "loss": 0.1302, "lr": 4.847684488072355e-05, "epoch": 4.01045104510451, "percentage": 20.05, "elapsed_time": "1:26:11", "remaining_time": "5:43:37", "throughput": 1487.5, "total_tokens": 7692160} {"current_steps": 36460, "total_steps": 181800, "loss": 0.0304, "lr": 4.847601983184108e-05, "epoch": 4.011001100110011, "percentage": 20.06, "elapsed_time": "1:26:11", "remaining_time": "5:43:36", "throughput": 1487.51, "total_tokens": 7693248} {"current_steps": 36465, "total_steps": 181800, "loss": 0.037, "lr": 4.847519456659141e-05, "epoch": 4.011551155115511, "percentage": 20.06, "elapsed_time": "1:26:12", "remaining_time": "5:43:35", "throughput": 1487.51, "total_tokens": 7694240} {"current_steps": 36470, "total_steps": 181800, "loss": 0.0219, "lr": 4.847436908498213e-05, "epoch": 4.0121012101210125, "percentage": 20.06, "elapsed_time": "1:26:13", "remaining_time": "5:43:35", "throughput": 1487.53, "total_tokens": 7695392} {"current_steps": 36475, "total_steps": 181800, "loss": 0.0887, "lr": 4.8473543387020846e-05, "epoch": 4.012651265126513, "percentage": 20.06, "elapsed_time": "1:26:13", "remaining_time": "5:43:34", "throughput": 1487.55, "total_tokens": 7696512} {"current_steps": 36480, "total_steps": 181800, "loss": 0.087, "lr": 4.847271747271519e-05, "epoch": 4.013201320132013, "percentage": 20.07, "elapsed_time": "1:26:14", "remaining_time": "5:43:33", "throughput": 1487.55, "total_tokens": 7697536} {"current_steps": 36485, "total_steps": 181800, "loss": 0.0566, "lr": 4.847189134207275e-05, "epoch": 4.013751375137514, "percentage": 20.07, "elapsed_time": "1:26:15", "remaining_time": "5:43:32", "throughput": 1487.56, "total_tokens": 7698624} {"current_steps": 36490, "total_steps": 181800, "loss": 0.13, "lr": 4.847106499510116e-05, "epoch": 4.014301430143014, "percentage": 20.07, "elapsed_time": "1:26:16", "remaining_time": "5:43:31", "throughput": 1487.58, "total_tokens": 7699776} {"current_steps": 36495, "total_steps": 181800, "loss": 0.0334, "lr": 4.8470238431808024e-05, "epoch": 4.014851485148514, "percentage": 20.07, "elapsed_time": "1:26:16", "remaining_time": "5:43:31", "throughput": 1487.58, "total_tokens": 7700800} {"current_steps": 36500, "total_steps": 181800, "loss": 0.0688, "lr": 4.846941165220096e-05, "epoch": 4.0154015401540155, "percentage": 20.08, "elapsed_time": "1:26:17", "remaining_time": "5:43:30", "throughput": 1487.59, "total_tokens": 7701888} {"current_steps": 36505, "total_steps": 181800, "loss": 0.0508, "lr": 4.8468584656287594e-05, "epoch": 4.015951595159516, "percentage": 20.08, "elapsed_time": "1:26:18", "remaining_time": "5:43:29", "throughput": 1487.61, "total_tokens": 7703008} {"current_steps": 36510, "total_steps": 181800, "loss": 0.0308, "lr": 4.8467757444075535e-05, "epoch": 4.016501650165017, "percentage": 20.08, "elapsed_time": "1:26:18", "remaining_time": "5:43:28", "throughput": 1487.6, "total_tokens": 7704000} {"current_steps": 36515, "total_steps": 181800, "loss": 0.0324, "lr": 4.846693001557243e-05, "epoch": 4.017051705170517, "percentage": 20.09, "elapsed_time": "1:26:19", "remaining_time": "5:43:28", "throughput": 1487.6, "total_tokens": 7705056} {"current_steps": 36520, "total_steps": 181800, "loss": 0.0356, "lr": 4.846610237078588e-05, "epoch": 4.017601760176017, "percentage": 20.09, "elapsed_time": "1:26:20", "remaining_time": "5:43:27", "throughput": 1487.62, "total_tokens": 7706176} {"current_steps": 36525, "total_steps": 181800, "loss": 0.0265, "lr": 4.846527450972353e-05, "epoch": 4.018151815181518, "percentage": 20.09, "elapsed_time": "1:26:20", "remaining_time": "5:43:26", "throughput": 1487.63, "total_tokens": 7707264} {"current_steps": 36530, "total_steps": 181800, "loss": 0.0682, "lr": 4.846444643239301e-05, "epoch": 4.0187018701870185, "percentage": 20.09, "elapsed_time": "1:26:21", "remaining_time": "5:43:25", "throughput": 1487.65, "total_tokens": 7708384} {"current_steps": 36535, "total_steps": 181800, "loss": 0.0586, "lr": 4.846361813880194e-05, "epoch": 4.01925192519252, "percentage": 20.1, "elapsed_time": "1:26:22", "remaining_time": "5:43:25", "throughput": 1487.65, "total_tokens": 7709408} {"current_steps": 36540, "total_steps": 181800, "loss": 0.0641, "lr": 4.846278962895795e-05, "epoch": 4.01980198019802, "percentage": 20.1, "elapsed_time": "1:26:22", "remaining_time": "5:43:24", "throughput": 1487.65, "total_tokens": 7710464} {"current_steps": 36545, "total_steps": 181800, "loss": 0.0606, "lr": 4.84619609028687e-05, "epoch": 4.02035203520352, "percentage": 20.1, "elapsed_time": "1:26:23", "remaining_time": "5:43:23", "throughput": 1487.66, "total_tokens": 7711520} {"current_steps": 36550, "total_steps": 181800, "loss": 0.0358, "lr": 4.8461131960541814e-05, "epoch": 4.020902090209021, "percentage": 20.1, "elapsed_time": "1:26:24", "remaining_time": "5:43:22", "throughput": 1487.67, "total_tokens": 7712608} {"current_steps": 36555, "total_steps": 181800, "loss": 0.0322, "lr": 4.846030280198493e-05, "epoch": 4.021452145214521, "percentage": 20.11, "elapsed_time": "1:26:25", "remaining_time": "5:43:21", "throughput": 1487.67, "total_tokens": 7713664} {"current_steps": 36560, "total_steps": 181800, "loss": 0.0648, "lr": 4.8459473427205694e-05, "epoch": 4.022002200220022, "percentage": 20.11, "elapsed_time": "1:26:25", "remaining_time": "5:43:21", "throughput": 1487.68, "total_tokens": 7714720} {"current_steps": 36565, "total_steps": 181800, "loss": 0.1092, "lr": 4.845864383621175e-05, "epoch": 4.022552255225523, "percentage": 20.11, "elapsed_time": "1:26:26", "remaining_time": "5:43:20", "throughput": 1487.69, "total_tokens": 7715776} {"current_steps": 36570, "total_steps": 181800, "loss": 0.0273, "lr": 4.8457814029010737e-05, "epoch": 4.023102310231023, "percentage": 20.12, "elapsed_time": "1:26:27", "remaining_time": "5:43:19", "throughput": 1487.69, "total_tokens": 7716832} {"current_steps": 36575, "total_steps": 181800, "loss": 0.0749, "lr": 4.845698400561031e-05, "epoch": 4.023652365236524, "percentage": 20.12, "elapsed_time": "1:26:27", "remaining_time": "5:43:18", "throughput": 1487.69, "total_tokens": 7717824} {"current_steps": 36580, "total_steps": 181800, "loss": 0.0289, "lr": 4.845615376601812e-05, "epoch": 4.024202420242024, "percentage": 20.12, "elapsed_time": "1:26:28", "remaining_time": "5:43:17", "throughput": 1487.69, "total_tokens": 7718848} {"current_steps": 36585, "total_steps": 181800, "loss": 0.0491, "lr": 4.845532331024181e-05, "epoch": 4.024752475247524, "percentage": 20.12, "elapsed_time": "1:26:29", "remaining_time": "5:43:17", "throughput": 1487.7, "total_tokens": 7719936} {"current_steps": 36590, "total_steps": 181800, "loss": 0.0534, "lr": 4.845449263828904e-05, "epoch": 4.025302530253025, "percentage": 20.13, "elapsed_time": "1:26:29", "remaining_time": "5:43:16", "throughput": 1487.71, "total_tokens": 7721024} {"current_steps": 36595, "total_steps": 181800, "loss": 0.1104, "lr": 4.845366175016748e-05, "epoch": 4.025852585258526, "percentage": 20.13, "elapsed_time": "1:26:30", "remaining_time": "5:43:15", "throughput": 1487.71, "total_tokens": 7722080} {"current_steps": 36600, "total_steps": 181800, "loss": 0.0449, "lr": 4.845283064588476e-05, "epoch": 4.026402640264027, "percentage": 20.13, "elapsed_time": "1:26:31", "remaining_time": "5:43:14", "throughput": 1487.73, "total_tokens": 7723168} {"current_steps": 36605, "total_steps": 181800, "loss": 0.068, "lr": 4.845199932544856e-05, "epoch": 4.026952695269527, "percentage": 20.13, "elapsed_time": "1:26:31", "remaining_time": "5:43:14", "throughput": 1487.72, "total_tokens": 7724160} {"current_steps": 36610, "total_steps": 181800, "loss": 0.0543, "lr": 4.845116778886653e-05, "epoch": 4.027502750275027, "percentage": 20.14, "elapsed_time": "1:26:32", "remaining_time": "5:43:13", "throughput": 1487.72, "total_tokens": 7725184} {"current_steps": 36615, "total_steps": 181800, "loss": 0.0681, "lr": 4.8450336036146336e-05, "epoch": 4.028052805280528, "percentage": 20.14, "elapsed_time": "1:26:33", "remaining_time": "5:43:12", "throughput": 1487.72, "total_tokens": 7726240} {"current_steps": 36620, "total_steps": 181800, "loss": 0.1198, "lr": 4.844950406729566e-05, "epoch": 4.028602860286028, "percentage": 20.14, "elapsed_time": "1:26:34", "remaining_time": "5:43:11", "throughput": 1487.74, "total_tokens": 7727360} {"current_steps": 36625, "total_steps": 181800, "loss": 0.0594, "lr": 4.844867188232215e-05, "epoch": 4.0291529152915295, "percentage": 20.15, "elapsed_time": "1:26:34", "remaining_time": "5:43:10", "throughput": 1487.75, "total_tokens": 7728416} {"current_steps": 36630, "total_steps": 181800, "loss": 0.0991, "lr": 4.844783948123348e-05, "epoch": 4.02970297029703, "percentage": 20.15, "elapsed_time": "1:26:35", "remaining_time": "5:43:10", "throughput": 1487.74, "total_tokens": 7729408} {"current_steps": 36635, "total_steps": 181800, "loss": 0.0058, "lr": 4.844700686403733e-05, "epoch": 4.03025302530253, "percentage": 20.15, "elapsed_time": "1:26:36", "remaining_time": "5:43:09", "throughput": 1487.74, "total_tokens": 7730432} {"current_steps": 36640, "total_steps": 181800, "loss": 0.05, "lr": 4.844617403074137e-05, "epoch": 4.030803080308031, "percentage": 20.15, "elapsed_time": "1:26:36", "remaining_time": "5:43:08", "throughput": 1487.74, "total_tokens": 7731456} {"current_steps": 36645, "total_steps": 181800, "loss": 0.0666, "lr": 4.844534098135327e-05, "epoch": 4.031353135313531, "percentage": 20.16, "elapsed_time": "1:26:37", "remaining_time": "5:43:07", "throughput": 1487.74, "total_tokens": 7732512} {"current_steps": 36650, "total_steps": 181800, "loss": 0.0594, "lr": 4.8444507715880716e-05, "epoch": 4.031903190319032, "percentage": 20.16, "elapsed_time": "1:26:38", "remaining_time": "5:43:07", "throughput": 1487.74, "total_tokens": 7733536} {"current_steps": 36655, "total_steps": 181800, "loss": 0.024, "lr": 4.844367423433138e-05, "epoch": 4.0324532453245325, "percentage": 20.16, "elapsed_time": "1:26:38", "remaining_time": "5:43:06", "throughput": 1487.76, "total_tokens": 7734624} {"current_steps": 36660, "total_steps": 181800, "loss": 0.0404, "lr": 4.844284053671295e-05, "epoch": 4.033003300330033, "percentage": 20.17, "elapsed_time": "1:26:39", "remaining_time": "5:43:05", "throughput": 1487.77, "total_tokens": 7735712} {"current_steps": 36665, "total_steps": 181800, "loss": 0.0301, "lr": 4.844200662303311e-05, "epoch": 4.033553355335534, "percentage": 20.17, "elapsed_time": "1:26:40", "remaining_time": "5:43:04", "throughput": 1487.79, "total_tokens": 7736832} {"current_steps": 36670, "total_steps": 181800, "loss": 0.0884, "lr": 4.844117249329955e-05, "epoch": 4.034103410341034, "percentage": 20.17, "elapsed_time": "1:26:40", "remaining_time": "5:43:03", "throughput": 1487.8, "total_tokens": 7737920} {"current_steps": 36675, "total_steps": 181800, "loss": 0.0131, "lr": 4.844033814751994e-05, "epoch": 4.034653465346534, "percentage": 20.17, "elapsed_time": "1:26:41", "remaining_time": "5:43:03", "throughput": 1487.8, "total_tokens": 7738976} {"current_steps": 36680, "total_steps": 181800, "loss": 0.1108, "lr": 4.843950358570198e-05, "epoch": 4.035203520352035, "percentage": 20.18, "elapsed_time": "1:26:42", "remaining_time": "5:43:02", "throughput": 1487.81, "total_tokens": 7740032} {"current_steps": 36685, "total_steps": 181800, "loss": 0.0619, "lr": 4.843866880785337e-05, "epoch": 4.0357535753575355, "percentage": 20.18, "elapsed_time": "1:26:42", "remaining_time": "5:43:01", "throughput": 1487.81, "total_tokens": 7741056} {"current_steps": 36690, "total_steps": 181800, "loss": 0.0071, "lr": 4.843783381398179e-05, "epoch": 4.036303630363037, "percentage": 20.18, "elapsed_time": "1:26:43", "remaining_time": "5:43:00", "throughput": 1487.81, "total_tokens": 7742080} {"current_steps": 36695, "total_steps": 181800, "loss": 0.0466, "lr": 4.8436998604094945e-05, "epoch": 4.036853685368537, "percentage": 20.18, "elapsed_time": "1:26:44", "remaining_time": "5:42:59", "throughput": 1487.81, "total_tokens": 7743136} {"current_steps": 36700, "total_steps": 181800, "loss": 0.0511, "lr": 4.8436163178200534e-05, "epoch": 4.037403740374037, "percentage": 20.19, "elapsed_time": "1:26:45", "remaining_time": "5:42:59", "throughput": 1487.83, "total_tokens": 7744256} {"current_steps": 36705, "total_steps": 181800, "loss": 0.003, "lr": 4.843532753630625e-05, "epoch": 4.037953795379538, "percentage": 20.19, "elapsed_time": "1:26:45", "remaining_time": "5:42:58", "throughput": 1487.84, "total_tokens": 7745344} {"current_steps": 36710, "total_steps": 181800, "loss": 0.033, "lr": 4.843449167841979e-05, "epoch": 4.038503850385038, "percentage": 20.19, "elapsed_time": "1:26:46", "remaining_time": "5:42:57", "throughput": 1487.84, "total_tokens": 7746336} {"current_steps": 36715, "total_steps": 181800, "loss": 0.0204, "lr": 4.8433655604548875e-05, "epoch": 4.039053905390539, "percentage": 20.2, "elapsed_time": "1:26:47", "remaining_time": "5:42:56", "throughput": 1487.84, "total_tokens": 7747360} {"current_steps": 36720, "total_steps": 181800, "loss": 0.0416, "lr": 4.84328193147012e-05, "epoch": 4.03960396039604, "percentage": 20.2, "elapsed_time": "1:26:47", "remaining_time": "5:42:56", "throughput": 1487.83, "total_tokens": 7748384} {"current_steps": 36725, "total_steps": 181800, "loss": 0.0482, "lr": 4.843198280888447e-05, "epoch": 4.04015401540154, "percentage": 20.2, "elapsed_time": "1:26:48", "remaining_time": "5:42:55", "throughput": 1487.83, "total_tokens": 7749408} {"current_steps": 36730, "total_steps": 181800, "loss": 0.0699, "lr": 4.8431146087106405e-05, "epoch": 4.040704070407041, "percentage": 20.2, "elapsed_time": "1:26:49", "remaining_time": "5:42:54", "throughput": 1487.84, "total_tokens": 7750432} {"current_steps": 36735, "total_steps": 181800, "loss": 0.0363, "lr": 4.8430309149374695e-05, "epoch": 4.041254125412541, "percentage": 20.21, "elapsed_time": "1:26:49", "remaining_time": "5:42:53", "throughput": 1487.83, "total_tokens": 7751424} {"current_steps": 36740, "total_steps": 181800, "loss": 0.0321, "lr": 4.8429471995697084e-05, "epoch": 4.041804180418042, "percentage": 20.21, "elapsed_time": "1:26:50", "remaining_time": "5:42:52", "throughput": 1487.83, "total_tokens": 7752480} {"current_steps": 36745, "total_steps": 181800, "loss": 0.0735, "lr": 4.842863462608127e-05, "epoch": 4.042354235423542, "percentage": 20.21, "elapsed_time": "1:26:51", "remaining_time": "5:42:52", "throughput": 1487.83, "total_tokens": 7753504} {"current_steps": 36750, "total_steps": 181800, "loss": 0.0552, "lr": 4.842779704053497e-05, "epoch": 4.042904290429043, "percentage": 20.21, "elapsed_time": "1:26:51", "remaining_time": "5:42:51", "throughput": 1487.85, "total_tokens": 7754624} {"current_steps": 36755, "total_steps": 181800, "loss": 0.0075, "lr": 4.8426959239065905e-05, "epoch": 4.043454345434544, "percentage": 20.22, "elapsed_time": "1:26:52", "remaining_time": "5:42:50", "throughput": 1487.86, "total_tokens": 7755680} {"current_steps": 36760, "total_steps": 181800, "loss": 0.1002, "lr": 4.8426121221681795e-05, "epoch": 4.044004400440044, "percentage": 20.22, "elapsed_time": "1:26:53", "remaining_time": "5:42:49", "throughput": 1487.86, "total_tokens": 7756736} {"current_steps": 36765, "total_steps": 181800, "loss": 0.0753, "lr": 4.8425282988390376e-05, "epoch": 4.044554455445544, "percentage": 20.22, "elapsed_time": "1:26:54", "remaining_time": "5:42:48", "throughput": 1487.86, "total_tokens": 7757760} {"current_steps": 36770, "total_steps": 181800, "loss": 0.0155, "lr": 4.842444453919935e-05, "epoch": 4.045104510451045, "percentage": 20.23, "elapsed_time": "1:26:54", "remaining_time": "5:42:48", "throughput": 1487.87, "total_tokens": 7758816} {"current_steps": 36775, "total_steps": 181800, "loss": 0.0239, "lr": 4.8423605874116475e-05, "epoch": 4.0456545654565454, "percentage": 20.23, "elapsed_time": "1:26:55", "remaining_time": "5:42:47", "throughput": 1487.88, "total_tokens": 7759904} {"current_steps": 36780, "total_steps": 181800, "loss": 0.0555, "lr": 4.842276699314945e-05, "epoch": 4.0462046204620465, "percentage": 20.23, "elapsed_time": "1:26:56", "remaining_time": "5:42:46", "throughput": 1487.89, "total_tokens": 7760960} {"current_steps": 36785, "total_steps": 181800, "loss": 0.0551, "lr": 4.842192789630603e-05, "epoch": 4.046754675467547, "percentage": 20.23, "elapsed_time": "1:26:56", "remaining_time": "5:42:45", "throughput": 1487.89, "total_tokens": 7761984} {"current_steps": 36790, "total_steps": 181800, "loss": 0.0718, "lr": 4.842108858359394e-05, "epoch": 4.047304730473047, "percentage": 20.24, "elapsed_time": "1:26:57", "remaining_time": "5:42:44", "throughput": 1487.9, "total_tokens": 7763072} {"current_steps": 36795, "total_steps": 181800, "loss": 0.0212, "lr": 4.842024905502091e-05, "epoch": 4.047854785478548, "percentage": 20.24, "elapsed_time": "1:26:58", "remaining_time": "5:42:44", "throughput": 1487.91, "total_tokens": 7764160} {"current_steps": 36800, "total_steps": 181800, "loss": 0.0781, "lr": 4.841940931059469e-05, "epoch": 4.048404840484048, "percentage": 20.24, "elapsed_time": "1:26:58", "remaining_time": "5:42:43", "throughput": 1487.92, "total_tokens": 7765248} {"current_steps": 36805, "total_steps": 181800, "loss": 0.0193, "lr": 4.8418569350323e-05, "epoch": 4.048954895489549, "percentage": 20.24, "elapsed_time": "1:26:59", "remaining_time": "5:42:42", "throughput": 1487.93, "total_tokens": 7766304} {"current_steps": 36810, "total_steps": 181800, "loss": 0.11, "lr": 4.84177291742136e-05, "epoch": 4.0495049504950495, "percentage": 20.25, "elapsed_time": "1:27:00", "remaining_time": "5:42:41", "throughput": 1487.93, "total_tokens": 7767360} {"current_steps": 36815, "total_steps": 181800, "loss": 0.0377, "lr": 4.841688878227423e-05, "epoch": 4.05005500550055, "percentage": 20.25, "elapsed_time": "1:27:00", "remaining_time": "5:42:41", "throughput": 1487.94, "total_tokens": 7768416} {"current_steps": 36820, "total_steps": 181800, "loss": 0.0387, "lr": 4.841604817451263e-05, "epoch": 4.050605060506051, "percentage": 20.25, "elapsed_time": "1:27:01", "remaining_time": "5:42:40", "throughput": 1487.94, "total_tokens": 7769440} {"current_steps": 36825, "total_steps": 181800, "loss": 0.0336, "lr": 4.8415207350936554e-05, "epoch": 4.051155115511551, "percentage": 20.26, "elapsed_time": "1:27:02", "remaining_time": "5:42:39", "throughput": 1487.95, "total_tokens": 7770528} {"current_steps": 36830, "total_steps": 181800, "loss": 0.0188, "lr": 4.8414366311553736e-05, "epoch": 4.051705170517051, "percentage": 20.26, "elapsed_time": "1:27:02", "remaining_time": "5:42:38", "throughput": 1487.95, "total_tokens": 7771552} {"current_steps": 36835, "total_steps": 181800, "loss": 0.0225, "lr": 4.8413525056371955e-05, "epoch": 4.052255225522552, "percentage": 20.26, "elapsed_time": "1:27:03", "remaining_time": "5:42:37", "throughput": 1487.95, "total_tokens": 7772608} {"current_steps": 36840, "total_steps": 181800, "loss": 0.0873, "lr": 4.8412683585398935e-05, "epoch": 4.052805280528053, "percentage": 20.26, "elapsed_time": "1:27:04", "remaining_time": "5:42:37", "throughput": 1487.96, "total_tokens": 7773664} {"current_steps": 36845, "total_steps": 181800, "loss": 0.0939, "lr": 4.841184189864245e-05, "epoch": 4.053355335533554, "percentage": 20.27, "elapsed_time": "1:27:05", "remaining_time": "5:42:36", "throughput": 1487.96, "total_tokens": 7774720} {"current_steps": 36850, "total_steps": 181800, "loss": 0.0701, "lr": 4.8410999996110256e-05, "epoch": 4.053905390539054, "percentage": 20.27, "elapsed_time": "1:27:05", "remaining_time": "5:42:35", "throughput": 1487.95, "total_tokens": 7775680} {"current_steps": 36855, "total_steps": 181800, "loss": 0.0218, "lr": 4.84101578778101e-05, "epoch": 4.054455445544554, "percentage": 20.27, "elapsed_time": "1:27:06", "remaining_time": "5:42:34", "throughput": 1487.96, "total_tokens": 7776768} {"current_steps": 36860, "total_steps": 181800, "loss": 0.0814, "lr": 4.840931554374976e-05, "epoch": 4.055005500550055, "percentage": 20.28, "elapsed_time": "1:27:07", "remaining_time": "5:42:34", "throughput": 1487.97, "total_tokens": 7777824} {"current_steps": 36865, "total_steps": 181800, "loss": 0.1534, "lr": 4.8408472993936994e-05, "epoch": 4.055555555555555, "percentage": 20.28, "elapsed_time": "1:27:07", "remaining_time": "5:42:33", "throughput": 1487.97, "total_tokens": 7778880} {"current_steps": 36870, "total_steps": 181800, "loss": 0.0948, "lr": 4.840763022837956e-05, "epoch": 4.0561056105610565, "percentage": 20.28, "elapsed_time": "1:27:08", "remaining_time": "5:42:32", "throughput": 1487.98, "total_tokens": 7779936} {"current_steps": 36875, "total_steps": 181800, "loss": 0.0457, "lr": 4.8406787247085226e-05, "epoch": 4.056655665566557, "percentage": 20.28, "elapsed_time": "1:27:09", "remaining_time": "5:42:31", "throughput": 1487.99, "total_tokens": 7781024} {"current_steps": 36880, "total_steps": 181800, "loss": 0.0648, "lr": 4.840594405006177e-05, "epoch": 4.057205720572057, "percentage": 20.29, "elapsed_time": "1:27:09", "remaining_time": "5:42:30", "throughput": 1488.0, "total_tokens": 7782080} {"current_steps": 36885, "total_steps": 181800, "loss": 0.0747, "lr": 4.8405100637316956e-05, "epoch": 4.057755775577558, "percentage": 20.29, "elapsed_time": "1:27:10", "remaining_time": "5:42:30", "throughput": 1488.02, "total_tokens": 7783232} {"current_steps": 36890, "total_steps": 181800, "loss": 0.1225, "lr": 4.8404257008858564e-05, "epoch": 4.058305830583058, "percentage": 20.29, "elapsed_time": "1:27:11", "remaining_time": "5:42:29", "throughput": 1488.02, "total_tokens": 7784256} {"current_steps": 36895, "total_steps": 181800, "loss": 0.2069, "lr": 4.840341316469437e-05, "epoch": 4.058855885588559, "percentage": 20.29, "elapsed_time": "1:27:11", "remaining_time": "5:42:28", "throughput": 1488.04, "total_tokens": 7785376} {"current_steps": 36900, "total_steps": 181800, "loss": 0.06, "lr": 4.840256910483214e-05, "epoch": 4.0594059405940595, "percentage": 20.3, "elapsed_time": "1:27:12", "remaining_time": "5:42:27", "throughput": 1488.04, "total_tokens": 7786432} {"current_steps": 36905, "total_steps": 181800, "loss": 0.1058, "lr": 4.840172482927966e-05, "epoch": 4.05995599559956, "percentage": 20.3, "elapsed_time": "1:27:13", "remaining_time": "5:42:27", "throughput": 1488.04, "total_tokens": 7787424} {"current_steps": 36910, "total_steps": 181800, "loss": 0.0248, "lr": 4.840088033804472e-05, "epoch": 4.060506050605061, "percentage": 20.3, "elapsed_time": "1:27:14", "remaining_time": "5:42:26", "throughput": 1488.03, "total_tokens": 7788448} {"current_steps": 36915, "total_steps": 181800, "loss": 0.0432, "lr": 4.8400035631135084e-05, "epoch": 4.061056105610561, "percentage": 20.31, "elapsed_time": "1:27:14", "remaining_time": "5:42:25", "throughput": 1488.03, "total_tokens": 7789472} {"current_steps": 36920, "total_steps": 181800, "loss": 0.0439, "lr": 4.839919070855855e-05, "epoch": 4.061606160616061, "percentage": 20.31, "elapsed_time": "1:27:15", "remaining_time": "5:42:24", "throughput": 1488.05, "total_tokens": 7790560} {"current_steps": 36925, "total_steps": 181800, "loss": 0.031, "lr": 4.8398345570322906e-05, "epoch": 4.062156215621562, "percentage": 20.31, "elapsed_time": "1:27:16", "remaining_time": "5:42:23", "throughput": 1488.05, "total_tokens": 7791616} {"current_steps": 36930, "total_steps": 181800, "loss": 0.0223, "lr": 4.839750021643594e-05, "epoch": 4.0627062706270625, "percentage": 20.31, "elapsed_time": "1:27:16", "remaining_time": "5:42:23", "throughput": 1488.05, "total_tokens": 7792608} {"current_steps": 36935, "total_steps": 181800, "loss": 0.0416, "lr": 4.839665464690544e-05, "epoch": 4.063256325632564, "percentage": 20.32, "elapsed_time": "1:27:17", "remaining_time": "5:42:22", "throughput": 1488.05, "total_tokens": 7793664} {"current_steps": 36940, "total_steps": 181800, "loss": 0.0246, "lr": 4.83958088617392e-05, "epoch": 4.063806380638064, "percentage": 20.32, "elapsed_time": "1:27:18", "remaining_time": "5:42:21", "throughput": 1488.05, "total_tokens": 7794656} {"current_steps": 36945, "total_steps": 181800, "loss": 0.1206, "lr": 4.839496286094501e-05, "epoch": 4.064356435643564, "percentage": 20.32, "elapsed_time": "1:27:18", "remaining_time": "5:42:20", "throughput": 1488.05, "total_tokens": 7795680} {"current_steps": 36950, "total_steps": 181800, "loss": 0.0142, "lr": 4.839411664453068e-05, "epoch": 4.064906490649065, "percentage": 20.32, "elapsed_time": "1:27:19", "remaining_time": "5:42:19", "throughput": 1488.05, "total_tokens": 7796736} {"current_steps": 36955, "total_steps": 181800, "loss": 0.0952, "lr": 4.8393270212504006e-05, "epoch": 4.065456545654565, "percentage": 20.33, "elapsed_time": "1:27:20", "remaining_time": "5:42:19", "throughput": 1488.05, "total_tokens": 7797728} {"current_steps": 36960, "total_steps": 181800, "loss": 0.0217, "lr": 4.839242356487278e-05, "epoch": 4.066006600660066, "percentage": 20.33, "elapsed_time": "1:27:20", "remaining_time": "5:42:18", "throughput": 1488.04, "total_tokens": 7798720} {"current_steps": 36965, "total_steps": 181800, "loss": 0.0682, "lr": 4.839157670164481e-05, "epoch": 4.066556655665567, "percentage": 20.33, "elapsed_time": "1:27:21", "remaining_time": "5:42:17", "throughput": 1488.04, "total_tokens": 7799744} {"current_steps": 36970, "total_steps": 181800, "loss": 0.0618, "lr": 4.839072962282791e-05, "epoch": 4.067106710671067, "percentage": 20.34, "elapsed_time": "1:27:22", "remaining_time": "5:42:16", "throughput": 1488.05, "total_tokens": 7800832} {"current_steps": 36975, "total_steps": 181800, "loss": 0.0496, "lr": 4.838988232842987e-05, "epoch": 4.067656765676568, "percentage": 20.34, "elapsed_time": "1:27:22", "remaining_time": "5:42:15", "throughput": 1488.05, "total_tokens": 7801856} {"current_steps": 36980, "total_steps": 181800, "loss": 0.0345, "lr": 4.8389034818458514e-05, "epoch": 4.068206820682068, "percentage": 20.34, "elapsed_time": "1:27:23", "remaining_time": "5:42:15", "throughput": 1488.06, "total_tokens": 7802912} {"current_steps": 36985, "total_steps": 181800, "loss": 0.1839, "lr": 4.8388187092921645e-05, "epoch": 4.068756875687569, "percentage": 20.34, "elapsed_time": "1:27:24", "remaining_time": "5:42:14", "throughput": 1488.05, "total_tokens": 7803872} {"current_steps": 36990, "total_steps": 181800, "loss": 0.0407, "lr": 4.838733915182708e-05, "epoch": 4.069306930693069, "percentage": 20.35, "elapsed_time": "1:27:25", "remaining_time": "5:42:13", "throughput": 1488.04, "total_tokens": 7804864} {"current_steps": 36995, "total_steps": 181800, "loss": 0.0363, "lr": 4.838649099518263e-05, "epoch": 4.06985698569857, "percentage": 20.35, "elapsed_time": "1:27:25", "remaining_time": "5:42:12", "throughput": 1488.05, "total_tokens": 7805920} {"current_steps": 37000, "total_steps": 181800, "loss": 0.0786, "lr": 4.838564262299612e-05, "epoch": 4.070407040704071, "percentage": 20.35, "elapsed_time": "1:27:26", "remaining_time": "5:42:11", "throughput": 1488.05, "total_tokens": 7806944} {"current_steps": 37005, "total_steps": 181800, "loss": 0.0077, "lr": 4.838479403527535e-05, "epoch": 4.070957095709571, "percentage": 20.35, "elapsed_time": "1:27:27", "remaining_time": "5:42:11", "throughput": 1488.05, "total_tokens": 7808000} {"current_steps": 37010, "total_steps": 181800, "loss": 0.0952, "lr": 4.838394523202817e-05, "epoch": 4.071507150715071, "percentage": 20.36, "elapsed_time": "1:27:27", "remaining_time": "5:42:10", "throughput": 1488.06, "total_tokens": 7809056} {"current_steps": 37015, "total_steps": 181800, "loss": 0.0092, "lr": 4.838309621326238e-05, "epoch": 4.072057205720572, "percentage": 20.36, "elapsed_time": "1:27:28", "remaining_time": "5:42:09", "throughput": 1488.08, "total_tokens": 7810176} {"current_steps": 37020, "total_steps": 181800, "loss": 0.0388, "lr": 4.838224697898581e-05, "epoch": 4.072607260726072, "percentage": 20.36, "elapsed_time": "1:27:29", "remaining_time": "5:42:08", "throughput": 1488.08, "total_tokens": 7811200} {"current_steps": 37025, "total_steps": 181800, "loss": 0.0605, "lr": 4.838139752920629e-05, "epoch": 4.0731573157315735, "percentage": 20.37, "elapsed_time": "1:27:29", "remaining_time": "5:42:08", "throughput": 1488.08, "total_tokens": 7812224} {"current_steps": 37030, "total_steps": 181800, "loss": 0.0357, "lr": 4.838054786393166e-05, "epoch": 4.073707370737074, "percentage": 20.37, "elapsed_time": "1:27:30", "remaining_time": "5:42:07", "throughput": 1488.09, "total_tokens": 7813312} {"current_steps": 37035, "total_steps": 181800, "loss": 0.0173, "lr": 4.837969798316973e-05, "epoch": 4.074257425742574, "percentage": 20.37, "elapsed_time": "1:27:31", "remaining_time": "5:42:06", "throughput": 1488.09, "total_tokens": 7814368} {"current_steps": 37040, "total_steps": 181800, "loss": 0.0674, "lr": 4.8378847886928335e-05, "epoch": 4.074807480748075, "percentage": 20.37, "elapsed_time": "1:27:31", "remaining_time": "5:42:05", "throughput": 1488.1, "total_tokens": 7815424} {"current_steps": 37045, "total_steps": 181800, "loss": 0.0614, "lr": 4.8377997575215326e-05, "epoch": 4.075357535753575, "percentage": 20.38, "elapsed_time": "1:27:32", "remaining_time": "5:42:04", "throughput": 1488.12, "total_tokens": 7816544} {"current_steps": 37050, "total_steps": 181800, "loss": 0.015, "lr": 4.837714704803853e-05, "epoch": 4.075907590759076, "percentage": 20.38, "elapsed_time": "1:27:33", "remaining_time": "5:42:04", "throughput": 1488.11, "total_tokens": 7817536} {"current_steps": 37055, "total_steps": 181800, "loss": 0.1291, "lr": 4.837629630540579e-05, "epoch": 4.0764576457645765, "percentage": 20.38, "elapsed_time": "1:27:34", "remaining_time": "5:42:03", "throughput": 1488.11, "total_tokens": 7818560} {"current_steps": 37060, "total_steps": 181800, "loss": 0.0279, "lr": 4.8375445347324946e-05, "epoch": 4.077007700770077, "percentage": 20.39, "elapsed_time": "1:27:34", "remaining_time": "5:42:02", "throughput": 1488.13, "total_tokens": 7819712} {"current_steps": 37065, "total_steps": 181800, "loss": 0.0267, "lr": 4.8374594173803835e-05, "epoch": 4.077557755775578, "percentage": 20.39, "elapsed_time": "1:27:35", "remaining_time": "5:42:01", "throughput": 1488.14, "total_tokens": 7820800} {"current_steps": 37070, "total_steps": 181800, "loss": 0.0389, "lr": 4.8373742784850296e-05, "epoch": 4.078107810781078, "percentage": 20.39, "elapsed_time": "1:27:36", "remaining_time": "5:42:01", "throughput": 1488.15, "total_tokens": 7821856} {"current_steps": 37075, "total_steps": 181800, "loss": 0.0413, "lr": 4.83728911804722e-05, "epoch": 4.078657865786579, "percentage": 20.39, "elapsed_time": "1:27:36", "remaining_time": "5:42:00", "throughput": 1488.16, "total_tokens": 7822944} {"current_steps": 37080, "total_steps": 181800, "loss": 0.081, "lr": 4.837203936067737e-05, "epoch": 4.079207920792079, "percentage": 20.4, "elapsed_time": "1:27:37", "remaining_time": "5:41:59", "throughput": 1488.16, "total_tokens": 7824000} {"current_steps": 37085, "total_steps": 181800, "loss": 0.0248, "lr": 4.837118732547368e-05, "epoch": 4.0797579757975795, "percentage": 20.4, "elapsed_time": "1:27:38", "remaining_time": "5:41:58", "throughput": 1488.16, "total_tokens": 7825024} {"current_steps": 37090, "total_steps": 181800, "loss": 0.0816, "lr": 4.837033507486897e-05, "epoch": 4.080308030803081, "percentage": 20.4, "elapsed_time": "1:27:38", "remaining_time": "5:41:57", "throughput": 1488.16, "total_tokens": 7826048} {"current_steps": 37095, "total_steps": 181800, "loss": 0.0435, "lr": 4.836948260887108e-05, "epoch": 4.080858085808581, "percentage": 20.4, "elapsed_time": "1:27:39", "remaining_time": "5:41:57", "throughput": 1488.18, "total_tokens": 7827168} {"current_steps": 37100, "total_steps": 181800, "loss": 0.067, "lr": 4.836862992748789e-05, "epoch": 4.081408140814081, "percentage": 20.41, "elapsed_time": "1:27:40", "remaining_time": "5:41:56", "throughput": 1488.17, "total_tokens": 7828160} {"current_steps": 37105, "total_steps": 181800, "loss": 0.2055, "lr": 4.8367777030727264e-05, "epoch": 4.081958195819582, "percentage": 20.41, "elapsed_time": "1:27:40", "remaining_time": "5:41:55", "throughput": 1488.18, "total_tokens": 7829216} {"current_steps": 37110, "total_steps": 181800, "loss": 0.0878, "lr": 4.836692391859704e-05, "epoch": 4.082508250825082, "percentage": 20.41, "elapsed_time": "1:27:41", "remaining_time": "5:41:54", "throughput": 1488.18, "total_tokens": 7830272} {"current_steps": 37115, "total_steps": 181800, "loss": 0.0766, "lr": 4.8366070591105095e-05, "epoch": 4.083058305830583, "percentage": 20.42, "elapsed_time": "1:27:42", "remaining_time": "5:41:54", "throughput": 1488.19, "total_tokens": 7831328} {"current_steps": 37120, "total_steps": 181800, "loss": 0.0759, "lr": 4.8365217048259284e-05, "epoch": 4.083608360836084, "percentage": 20.42, "elapsed_time": "1:27:43", "remaining_time": "5:41:53", "throughput": 1488.21, "total_tokens": 7832448} {"current_steps": 37125, "total_steps": 181800, "loss": 0.0682, "lr": 4.836436329006748e-05, "epoch": 4.084158415841584, "percentage": 20.42, "elapsed_time": "1:27:43", "remaining_time": "5:41:52", "throughput": 1488.22, "total_tokens": 7833536} {"current_steps": 37130, "total_steps": 181800, "loss": 0.0466, "lr": 4.836350931653755e-05, "epoch": 4.084708470847085, "percentage": 20.42, "elapsed_time": "1:27:44", "remaining_time": "5:41:51", "throughput": 1488.22, "total_tokens": 7834560} {"current_steps": 37135, "total_steps": 181800, "loss": 0.099, "lr": 4.836265512767737e-05, "epoch": 4.085258525852585, "percentage": 20.43, "elapsed_time": "1:27:45", "remaining_time": "5:41:50", "throughput": 1488.22, "total_tokens": 7835584} {"current_steps": 37140, "total_steps": 181800, "loss": 0.0113, "lr": 4.836180072349481e-05, "epoch": 4.085808580858086, "percentage": 20.43, "elapsed_time": "1:27:45", "remaining_time": "5:41:50", "throughput": 1488.22, "total_tokens": 7836640} {"current_steps": 37145, "total_steps": 181800, "loss": 0.0994, "lr": 4.8360946103997735e-05, "epoch": 4.086358635863586, "percentage": 20.43, "elapsed_time": "1:27:46", "remaining_time": "5:41:49", "throughput": 1488.22, "total_tokens": 7837664} {"current_steps": 37150, "total_steps": 181800, "loss": 0.0305, "lr": 4.836009126919403e-05, "epoch": 4.086908690869087, "percentage": 20.43, "elapsed_time": "1:27:47", "remaining_time": "5:41:48", "throughput": 1488.23, "total_tokens": 7838720} {"current_steps": 37155, "total_steps": 181800, "loss": 0.0857, "lr": 4.835923621909158e-05, "epoch": 4.087458745874588, "percentage": 20.44, "elapsed_time": "1:27:47", "remaining_time": "5:41:47", "throughput": 1488.23, "total_tokens": 7839776} {"current_steps": 37160, "total_steps": 181800, "loss": 0.0532, "lr": 4.8358380953698254e-05, "epoch": 4.088008800880088, "percentage": 20.44, "elapsed_time": "1:27:48", "remaining_time": "5:41:47", "throughput": 1488.24, "total_tokens": 7840832} {"current_steps": 37165, "total_steps": 181800, "loss": 0.0811, "lr": 4.835752547302194e-05, "epoch": 4.088558855885589, "percentage": 20.44, "elapsed_time": "1:27:49", "remaining_time": "5:41:46", "throughput": 1488.26, "total_tokens": 7841952} {"current_steps": 37170, "total_steps": 181800, "loss": 0.0157, "lr": 4.8356669777070525e-05, "epoch": 4.089108910891089, "percentage": 20.45, "elapsed_time": "1:27:49", "remaining_time": "5:41:45", "throughput": 1488.25, "total_tokens": 7842944} {"current_steps": 37175, "total_steps": 181800, "loss": 0.0341, "lr": 4.835581386585188e-05, "epoch": 4.089658965896589, "percentage": 20.45, "elapsed_time": "1:27:50", "remaining_time": "5:41:44", "throughput": 1488.26, "total_tokens": 7844000} {"current_steps": 37180, "total_steps": 181800, "loss": 0.0559, "lr": 4.835495773937392e-05, "epoch": 4.0902090209020905, "percentage": 20.45, "elapsed_time": "1:27:51", "remaining_time": "5:41:43", "throughput": 1488.27, "total_tokens": 7845120} {"current_steps": 37185, "total_steps": 181800, "loss": 0.0754, "lr": 4.835410139764452e-05, "epoch": 4.090759075907591, "percentage": 20.45, "elapsed_time": "1:27:51", "remaining_time": "5:41:43", "throughput": 1488.29, "total_tokens": 7846208} {"current_steps": 37190, "total_steps": 181800, "loss": 0.0814, "lr": 4.835324484067157e-05, "epoch": 4.091309130913091, "percentage": 20.46, "elapsed_time": "1:27:52", "remaining_time": "5:41:42", "throughput": 1488.29, "total_tokens": 7847264} {"current_steps": 37195, "total_steps": 181800, "loss": 0.0126, "lr": 4.8352388068462965e-05, "epoch": 4.091859185918592, "percentage": 20.46, "elapsed_time": "1:27:53", "remaining_time": "5:41:41", "throughput": 1488.3, "total_tokens": 7848320} {"current_steps": 37200, "total_steps": 181800, "loss": 0.0913, "lr": 4.8351531081026614e-05, "epoch": 4.092409240924092, "percentage": 20.46, "elapsed_time": "1:27:54", "remaining_time": "5:41:40", "throughput": 1488.3, "total_tokens": 7849376} {"current_steps": 37205, "total_steps": 181800, "loss": 0.0624, "lr": 4.835067387837039e-05, "epoch": 4.092959295929593, "percentage": 20.46, "elapsed_time": "1:27:54", "remaining_time": "5:41:39", "throughput": 1488.32, "total_tokens": 7850464} {"current_steps": 37210, "total_steps": 181800, "loss": 0.0487, "lr": 4.834981646050223e-05, "epoch": 4.0935093509350935, "percentage": 20.47, "elapsed_time": "1:27:55", "remaining_time": "5:41:39", "throughput": 1488.31, "total_tokens": 7851456} {"current_steps": 37215, "total_steps": 181800, "loss": 0.0731, "lr": 4.834895882743e-05, "epoch": 4.094059405940594, "percentage": 20.47, "elapsed_time": "1:27:56", "remaining_time": "5:41:38", "throughput": 1488.32, "total_tokens": 7852544} {"current_steps": 37220, "total_steps": 181800, "loss": 0.017, "lr": 4.834810097916163e-05, "epoch": 4.094609460946095, "percentage": 20.47, "elapsed_time": "1:27:56", "remaining_time": "5:41:37", "throughput": 1488.33, "total_tokens": 7853600} {"current_steps": 37225, "total_steps": 181800, "loss": 0.0495, "lr": 4.834724291570501e-05, "epoch": 4.095159515951595, "percentage": 20.48, "elapsed_time": "1:27:57", "remaining_time": "5:41:36", "throughput": 1488.34, "total_tokens": 7854656} {"current_steps": 37230, "total_steps": 181800, "loss": 0.065, "lr": 4.834638463706805e-05, "epoch": 4.095709570957096, "percentage": 20.48, "elapsed_time": "1:27:58", "remaining_time": "5:41:35", "throughput": 1488.35, "total_tokens": 7855744} {"current_steps": 37235, "total_steps": 181800, "loss": 0.028, "lr": 4.834552614325868e-05, "epoch": 4.096259625962596, "percentage": 20.48, "elapsed_time": "1:27:58", "remaining_time": "5:41:35", "throughput": 1488.35, "total_tokens": 7856768} {"current_steps": 37240, "total_steps": 181800, "loss": 0.0305, "lr": 4.83446674342848e-05, "epoch": 4.0968096809680965, "percentage": 20.48, "elapsed_time": "1:27:59", "remaining_time": "5:41:34", "throughput": 1488.35, "total_tokens": 7857824} {"current_steps": 37245, "total_steps": 181800, "loss": 0.0104, "lr": 4.834380851015431e-05, "epoch": 4.097359735973598, "percentage": 20.49, "elapsed_time": "1:28:00", "remaining_time": "5:41:33", "throughput": 1488.35, "total_tokens": 7858848} {"current_steps": 37250, "total_steps": 181800, "loss": 0.0374, "lr": 4.834294937087514e-05, "epoch": 4.097909790979098, "percentage": 20.49, "elapsed_time": "1:28:00", "remaining_time": "5:41:32", "throughput": 1488.37, "total_tokens": 7859968} {"current_steps": 37255, "total_steps": 181800, "loss": 0.0498, "lr": 4.834209001645521e-05, "epoch": 4.098459845984599, "percentage": 20.49, "elapsed_time": "1:28:01", "remaining_time": "5:41:32", "throughput": 1488.37, "total_tokens": 7861024} {"current_steps": 37260, "total_steps": 181800, "loss": 0.029, "lr": 4.834123044690243e-05, "epoch": 4.099009900990099, "percentage": 20.5, "elapsed_time": "1:28:02", "remaining_time": "5:41:31", "throughput": 1488.38, "total_tokens": 7862080} {"current_steps": 37265, "total_steps": 181800, "loss": 0.0455, "lr": 4.834037066222474e-05, "epoch": 4.099559955995599, "percentage": 20.5, "elapsed_time": "1:28:02", "remaining_time": "5:41:30", "throughput": 1488.39, "total_tokens": 7863168} {"current_steps": 37270, "total_steps": 181800, "loss": 0.1879, "lr": 4.8339510662430046e-05, "epoch": 4.1001100110011, "percentage": 20.5, "elapsed_time": "1:28:03", "remaining_time": "5:41:29", "throughput": 1488.39, "total_tokens": 7864192} {"current_steps": 37275, "total_steps": 181800, "loss": 0.0206, "lr": 4.833865044752628e-05, "epoch": 4.100660066006601, "percentage": 20.5, "elapsed_time": "1:28:04", "remaining_time": "5:41:29", "throughput": 1488.34, "total_tokens": 7865280} {"current_steps": 37280, "total_steps": 181800, "loss": 0.1647, "lr": 4.833779001752138e-05, "epoch": 4.101210121012101, "percentage": 20.51, "elapsed_time": "1:28:05", "remaining_time": "5:41:29", "throughput": 1488.34, "total_tokens": 7866304} {"current_steps": 37285, "total_steps": 181800, "loss": 0.0526, "lr": 4.833692937242327e-05, "epoch": 4.101760176017602, "percentage": 20.51, "elapsed_time": "1:28:05", "remaining_time": "5:41:28", "throughput": 1488.34, "total_tokens": 7867360} {"current_steps": 37290, "total_steps": 181800, "loss": 0.0059, "lr": 4.833606851223986e-05, "epoch": 4.102310231023102, "percentage": 20.51, "elapsed_time": "1:28:06", "remaining_time": "5:41:27", "throughput": 1488.34, "total_tokens": 7868384} {"current_steps": 37295, "total_steps": 181800, "loss": 0.0994, "lr": 4.8335207436979124e-05, "epoch": 4.102860286028603, "percentage": 20.51, "elapsed_time": "1:28:07", "remaining_time": "5:41:26", "throughput": 1488.34, "total_tokens": 7869440} {"current_steps": 37300, "total_steps": 181800, "loss": 0.043, "lr": 4.833434614664897e-05, "epoch": 4.103410341034103, "percentage": 20.52, "elapsed_time": "1:28:08", "remaining_time": "5:41:25", "throughput": 1488.34, "total_tokens": 7870432} {"current_steps": 37305, "total_steps": 181800, "loss": 0.0682, "lr": 4.8333484641257355e-05, "epoch": 4.103960396039604, "percentage": 20.52, "elapsed_time": "1:28:08", "remaining_time": "5:41:25", "throughput": 1488.34, "total_tokens": 7871488} {"current_steps": 37310, "total_steps": 181800, "loss": 0.0464, "lr": 4.83326229208122e-05, "epoch": 4.104510451045105, "percentage": 20.52, "elapsed_time": "1:28:09", "remaining_time": "5:41:24", "throughput": 1488.33, "total_tokens": 7872448} {"current_steps": 37315, "total_steps": 181800, "loss": 0.0097, "lr": 4.833176098532145e-05, "epoch": 4.105060506050605, "percentage": 20.53, "elapsed_time": "1:28:10", "remaining_time": "5:41:23", "throughput": 1488.33, "total_tokens": 7873472} {"current_steps": 37320, "total_steps": 181800, "loss": 0.2284, "lr": 4.833089883479306e-05, "epoch": 4.105610561056106, "percentage": 20.53, "elapsed_time": "1:28:10", "remaining_time": "5:41:22", "throughput": 1488.33, "total_tokens": 7874528} {"current_steps": 37325, "total_steps": 181800, "loss": 0.0221, "lr": 4.8330036469234974e-05, "epoch": 4.106160616061606, "percentage": 20.53, "elapsed_time": "1:28:11", "remaining_time": "5:41:22", "throughput": 1488.33, "total_tokens": 7875552} {"current_steps": 37330, "total_steps": 181800, "loss": 0.0629, "lr": 4.8329173888655134e-05, "epoch": 4.106710671067106, "percentage": 20.53, "elapsed_time": "1:28:12", "remaining_time": "5:41:21", "throughput": 1488.34, "total_tokens": 7876608} {"current_steps": 37335, "total_steps": 181800, "loss": 0.1031, "lr": 4.83283110930615e-05, "epoch": 4.1072607260726075, "percentage": 20.54, "elapsed_time": "1:28:12", "remaining_time": "5:41:20", "throughput": 1488.33, "total_tokens": 7877600} {"current_steps": 37340, "total_steps": 181800, "loss": 0.0263, "lr": 4.8327448082462004e-05, "epoch": 4.107810781078108, "percentage": 20.54, "elapsed_time": "1:28:13", "remaining_time": "5:41:19", "throughput": 1488.34, "total_tokens": 7878688} {"current_steps": 37345, "total_steps": 181800, "loss": 0.0361, "lr": 4.8326584856864617e-05, "epoch": 4.108360836083609, "percentage": 20.54, "elapsed_time": "1:28:14", "remaining_time": "5:41:18", "throughput": 1488.35, "total_tokens": 7879744} {"current_steps": 37350, "total_steps": 181800, "loss": 0.0391, "lr": 4.832572141627729e-05, "epoch": 4.108910891089109, "percentage": 20.54, "elapsed_time": "1:28:14", "remaining_time": "5:41:18", "throughput": 1488.34, "total_tokens": 7880736} {"current_steps": 37355, "total_steps": 181800, "loss": 0.062, "lr": 4.832485776070799e-05, "epoch": 4.109460946094609, "percentage": 20.55, "elapsed_time": "1:28:15", "remaining_time": "5:41:17", "throughput": 1488.34, "total_tokens": 7881760} {"current_steps": 37360, "total_steps": 181800, "loss": 0.1196, "lr": 4.832399389016465e-05, "epoch": 4.11001100110011, "percentage": 20.55, "elapsed_time": "1:28:16", "remaining_time": "5:41:16", "throughput": 1488.35, "total_tokens": 7882816} {"current_steps": 37365, "total_steps": 181800, "loss": 0.0355, "lr": 4.832312980465526e-05, "epoch": 4.1105610561056105, "percentage": 20.55, "elapsed_time": "1:28:17", "remaining_time": "5:41:15", "throughput": 1488.35, "total_tokens": 7883872} {"current_steps": 37370, "total_steps": 181800, "loss": 0.0816, "lr": 4.832226550418778e-05, "epoch": 4.111111111111111, "percentage": 20.56, "elapsed_time": "1:28:17", "remaining_time": "5:41:15", "throughput": 1488.35, "total_tokens": 7884896} {"current_steps": 37375, "total_steps": 181800, "loss": 0.1345, "lr": 4.832140098877017e-05, "epoch": 4.111661166116612, "percentage": 20.56, "elapsed_time": "1:28:18", "remaining_time": "5:41:14", "throughput": 1488.36, "total_tokens": 7885984} {"current_steps": 37380, "total_steps": 181800, "loss": 0.1007, "lr": 4.832053625841039e-05, "epoch": 4.112211221122112, "percentage": 20.56, "elapsed_time": "1:28:19", "remaining_time": "5:41:13", "throughput": 1488.37, "total_tokens": 7887040} {"current_steps": 37385, "total_steps": 181800, "loss": 0.1133, "lr": 4.831967131311642e-05, "epoch": 4.112761276127613, "percentage": 20.56, "elapsed_time": "1:28:19", "remaining_time": "5:41:12", "throughput": 1488.38, "total_tokens": 7888096} {"current_steps": 37390, "total_steps": 181800, "loss": 0.0527, "lr": 4.8318806152896235e-05, "epoch": 4.113311331133113, "percentage": 20.57, "elapsed_time": "1:28:20", "remaining_time": "5:41:11", "throughput": 1488.38, "total_tokens": 7889152} {"current_steps": 37395, "total_steps": 181800, "loss": 0.0913, "lr": 4.83179407777578e-05, "epoch": 4.1138613861386135, "percentage": 20.57, "elapsed_time": "1:28:21", "remaining_time": "5:41:11", "throughput": 1488.39, "total_tokens": 7890208} {"current_steps": 37400, "total_steps": 181800, "loss": 0.0936, "lr": 4.831707518770909e-05, "epoch": 4.114411441144115, "percentage": 20.57, "elapsed_time": "1:28:21", "remaining_time": "5:41:10", "throughput": 1488.39, "total_tokens": 7891232} {"current_steps": 37405, "total_steps": 181800, "loss": 0.0823, "lr": 4.831620938275809e-05, "epoch": 4.114961496149615, "percentage": 20.57, "elapsed_time": "1:28:22", "remaining_time": "5:41:09", "throughput": 1488.41, "total_tokens": 7892352} {"current_steps": 37410, "total_steps": 181800, "loss": 0.2123, "lr": 4.8315343362912776e-05, "epoch": 4.115511551155116, "percentage": 20.58, "elapsed_time": "1:28:23", "remaining_time": "5:41:08", "throughput": 1488.42, "total_tokens": 7893440} {"current_steps": 37415, "total_steps": 181800, "loss": 0.0418, "lr": 4.831447712818113e-05, "epoch": 4.116061606160616, "percentage": 20.58, "elapsed_time": "1:28:23", "remaining_time": "5:41:07", "throughput": 1488.43, "total_tokens": 7894528} {"current_steps": 37420, "total_steps": 181800, "loss": 0.0797, "lr": 4.831361067857113e-05, "epoch": 4.116611661166116, "percentage": 20.58, "elapsed_time": "1:28:24", "remaining_time": "5:41:07", "throughput": 1488.43, "total_tokens": 7895552} {"current_steps": 37425, "total_steps": 181800, "loss": 0.0205, "lr": 4.831274401409077e-05, "epoch": 4.117161716171617, "percentage": 20.59, "elapsed_time": "1:28:25", "remaining_time": "5:41:06", "throughput": 1488.42, "total_tokens": 7896512} {"current_steps": 37430, "total_steps": 181800, "loss": 0.0389, "lr": 4.831187713474804e-05, "epoch": 4.117711771177118, "percentage": 20.59, "elapsed_time": "1:28:26", "remaining_time": "5:41:05", "throughput": 1488.41, "total_tokens": 7897504} {"current_steps": 37435, "total_steps": 181800, "loss": 0.0523, "lr": 4.831101004055092e-05, "epoch": 4.118261826182618, "percentage": 20.59, "elapsed_time": "1:28:26", "remaining_time": "5:41:04", "throughput": 1488.42, "total_tokens": 7898592} {"current_steps": 37440, "total_steps": 181800, "loss": 0.051, "lr": 4.8310142731507416e-05, "epoch": 4.118811881188119, "percentage": 20.59, "elapsed_time": "1:28:27", "remaining_time": "5:41:04", "throughput": 1488.43, "total_tokens": 7899680} {"current_steps": 37445, "total_steps": 181800, "loss": 0.0406, "lr": 4.83092752076255e-05, "epoch": 4.119361936193619, "percentage": 20.6, "elapsed_time": "1:28:28", "remaining_time": "5:41:03", "throughput": 1488.45, "total_tokens": 7900768} {"current_steps": 37450, "total_steps": 181800, "loss": 0.0408, "lr": 4.830840746891318e-05, "epoch": 4.11991199119912, "percentage": 20.6, "elapsed_time": "1:28:28", "remaining_time": "5:41:02", "throughput": 1488.46, "total_tokens": 7901856} {"current_steps": 37455, "total_steps": 181800, "loss": 0.0336, "lr": 4.830753951537846e-05, "epoch": 4.12046204620462, "percentage": 20.6, "elapsed_time": "1:28:29", "remaining_time": "5:41:01", "throughput": 1488.48, "total_tokens": 7903008} {"current_steps": 37460, "total_steps": 181800, "loss": 0.0793, "lr": 4.830667134702933e-05, "epoch": 4.121012101210121, "percentage": 20.61, "elapsed_time": "1:28:30", "remaining_time": "5:41:00", "throughput": 1488.49, "total_tokens": 7904096} {"current_steps": 37465, "total_steps": 181800, "loss": 0.1165, "lr": 4.830580296387379e-05, "epoch": 4.121562156215622, "percentage": 20.61, "elapsed_time": "1:28:30", "remaining_time": "5:41:00", "throughput": 1488.48, "total_tokens": 7905088} {"current_steps": 37470, "total_steps": 181800, "loss": 0.0793, "lr": 4.830493436591985e-05, "epoch": 4.122112211221122, "percentage": 20.61, "elapsed_time": "1:28:31", "remaining_time": "5:40:59", "throughput": 1488.47, "total_tokens": 7906048} {"current_steps": 37475, "total_steps": 181800, "loss": 0.0489, "lr": 4.8304065553175515e-05, "epoch": 4.122662266226623, "percentage": 20.61, "elapsed_time": "1:28:32", "remaining_time": "5:40:58", "throughput": 1488.47, "total_tokens": 7907072} {"current_steps": 37480, "total_steps": 181800, "loss": 0.0231, "lr": 4.8303196525648783e-05, "epoch": 4.123212321232123, "percentage": 20.62, "elapsed_time": "1:28:32", "remaining_time": "5:40:57", "throughput": 1488.48, "total_tokens": 7908160} {"current_steps": 37485, "total_steps": 181800, "loss": 0.059, "lr": 4.830232728334767e-05, "epoch": 4.123762376237623, "percentage": 20.62, "elapsed_time": "1:28:33", "remaining_time": "5:40:56", "throughput": 1488.48, "total_tokens": 7909152} {"current_steps": 37490, "total_steps": 181800, "loss": 0.011, "lr": 4.83014578262802e-05, "epoch": 4.1243124312431245, "percentage": 20.62, "elapsed_time": "1:28:34", "remaining_time": "5:40:56", "throughput": 1488.47, "total_tokens": 7910144} {"current_steps": 37495, "total_steps": 181800, "loss": 0.0275, "lr": 4.830058815445437e-05, "epoch": 4.124862486248625, "percentage": 20.62, "elapsed_time": "1:28:34", "remaining_time": "5:40:55", "throughput": 1488.48, "total_tokens": 7911200} {"current_steps": 37500, "total_steps": 181800, "loss": 0.1185, "lr": 4.829971826787819e-05, "epoch": 4.125412541254126, "percentage": 20.63, "elapsed_time": "1:28:35", "remaining_time": "5:40:54", "throughput": 1488.48, "total_tokens": 7912224} {"current_steps": 37505, "total_steps": 181800, "loss": 0.0334, "lr": 4.8298848166559695e-05, "epoch": 4.125962596259626, "percentage": 20.63, "elapsed_time": "1:28:36", "remaining_time": "5:40:53", "throughput": 1488.48, "total_tokens": 7913280} {"current_steps": 37510, "total_steps": 181800, "loss": 0.02, "lr": 4.8297977850506895e-05, "epoch": 4.126512651265126, "percentage": 20.63, "elapsed_time": "1:28:37", "remaining_time": "5:40:53", "throughput": 1488.49, "total_tokens": 7914368} {"current_steps": 37515, "total_steps": 181800, "loss": 0.0526, "lr": 4.829710731972782e-05, "epoch": 4.127062706270627, "percentage": 20.64, "elapsed_time": "1:28:37", "remaining_time": "5:40:52", "throughput": 1488.5, "total_tokens": 7915424} {"current_steps": 37520, "total_steps": 181800, "loss": 0.0529, "lr": 4.8296236574230474e-05, "epoch": 4.1276127612761275, "percentage": 20.64, "elapsed_time": "1:28:38", "remaining_time": "5:40:51", "throughput": 1488.51, "total_tokens": 7916512} {"current_steps": 37525, "total_steps": 181800, "loss": 0.1229, "lr": 4.82953656140229e-05, "epoch": 4.128162816281628, "percentage": 20.64, "elapsed_time": "1:28:39", "remaining_time": "5:40:50", "throughput": 1488.52, "total_tokens": 7917568} {"current_steps": 37530, "total_steps": 181800, "loss": 0.0279, "lr": 4.829449443911312e-05, "epoch": 4.128712871287129, "percentage": 20.64, "elapsed_time": "1:28:39", "remaining_time": "5:40:49", "throughput": 1488.53, "total_tokens": 7918656} {"current_steps": 37535, "total_steps": 181800, "loss": 0.0084, "lr": 4.829362304950916e-05, "epoch": 4.129262926292629, "percentage": 20.65, "elapsed_time": "1:28:40", "remaining_time": "5:40:49", "throughput": 1488.53, "total_tokens": 7919680} {"current_steps": 37540, "total_steps": 181800, "loss": 0.0179, "lr": 4.8292751445219056e-05, "epoch": 4.12981298129813, "percentage": 20.65, "elapsed_time": "1:28:41", "remaining_time": "5:40:48", "throughput": 1488.54, "total_tokens": 7920768} {"current_steps": 37545, "total_steps": 181800, "loss": 0.0157, "lr": 4.8291879626250835e-05, "epoch": 4.13036303630363, "percentage": 20.65, "elapsed_time": "1:28:41", "remaining_time": "5:40:47", "throughput": 1488.56, "total_tokens": 7921888} {"current_steps": 37550, "total_steps": 181800, "loss": 0.0594, "lr": 4.8291007592612535e-05, "epoch": 4.1309130913091305, "percentage": 20.65, "elapsed_time": "1:28:42", "remaining_time": "5:40:46", "throughput": 1488.57, "total_tokens": 7923008} {"current_steps": 37555, "total_steps": 181800, "loss": 0.0431, "lr": 4.82901353443122e-05, "epoch": 4.131463146314632, "percentage": 20.66, "elapsed_time": "1:28:43", "remaining_time": "5:40:46", "throughput": 1488.58, "total_tokens": 7924064} {"current_steps": 37560, "total_steps": 181800, "loss": 0.0623, "lr": 4.828926288135787e-05, "epoch": 4.132013201320132, "percentage": 20.66, "elapsed_time": "1:28:43", "remaining_time": "5:40:45", "throughput": 1488.6, "total_tokens": 7925184} {"current_steps": 37565, "total_steps": 181800, "loss": 0.0379, "lr": 4.828839020375756e-05, "epoch": 4.132563256325633, "percentage": 20.66, "elapsed_time": "1:28:44", "remaining_time": "5:40:44", "throughput": 1488.6, "total_tokens": 7926240} {"current_steps": 37570, "total_steps": 181800, "loss": 0.0278, "lr": 4.8287517311519346e-05, "epoch": 4.133113311331133, "percentage": 20.67, "elapsed_time": "1:28:45", "remaining_time": "5:40:43", "throughput": 1488.61, "total_tokens": 7927296} {"current_steps": 37575, "total_steps": 181800, "loss": 0.0813, "lr": 4.828664420465126e-05, "epoch": 4.133663366336633, "percentage": 20.67, "elapsed_time": "1:28:46", "remaining_time": "5:40:42", "throughput": 1488.61, "total_tokens": 7928320} {"current_steps": 37580, "total_steps": 181800, "loss": 0.081, "lr": 4.828577088316134e-05, "epoch": 4.134213421342134, "percentage": 20.67, "elapsed_time": "1:28:46", "remaining_time": "5:40:42", "throughput": 1488.61, "total_tokens": 7929344} {"current_steps": 37585, "total_steps": 181800, "loss": 0.0587, "lr": 4.828489734705764e-05, "epoch": 4.134763476347635, "percentage": 20.67, "elapsed_time": "1:28:47", "remaining_time": "5:40:41", "throughput": 1488.6, "total_tokens": 7930336} {"current_steps": 37590, "total_steps": 181800, "loss": 0.0494, "lr": 4.8284023596348224e-05, "epoch": 4.135313531353136, "percentage": 20.68, "elapsed_time": "1:28:48", "remaining_time": "5:40:40", "throughput": 1488.61, "total_tokens": 7931424} {"current_steps": 37595, "total_steps": 181800, "loss": 0.02, "lr": 4.828314963104114e-05, "epoch": 4.135863586358636, "percentage": 20.68, "elapsed_time": "1:28:48", "remaining_time": "5:40:39", "throughput": 1488.61, "total_tokens": 7932448} {"current_steps": 37600, "total_steps": 181800, "loss": 0.0116, "lr": 4.8282275451144434e-05, "epoch": 4.136413641364136, "percentage": 20.68, "elapsed_time": "1:28:49", "remaining_time": "5:40:39", "throughput": 1488.6, "total_tokens": 7933440} {"current_steps": 37605, "total_steps": 181800, "loss": 0.0435, "lr": 4.828140105666616e-05, "epoch": 4.136963696369637, "percentage": 20.68, "elapsed_time": "1:28:50", "remaining_time": "5:40:38", "throughput": 1488.6, "total_tokens": 7934432} {"current_steps": 37610, "total_steps": 181800, "loss": 0.0342, "lr": 4.828052644761439e-05, "epoch": 4.137513751375137, "percentage": 20.69, "elapsed_time": "1:28:50", "remaining_time": "5:40:37", "throughput": 1488.6, "total_tokens": 7935456} {"current_steps": 37615, "total_steps": 181800, "loss": 0.0232, "lr": 4.827965162399718e-05, "epoch": 4.138063806380638, "percentage": 20.69, "elapsed_time": "1:28:51", "remaining_time": "5:40:36", "throughput": 1488.61, "total_tokens": 7936544} {"current_steps": 37620, "total_steps": 181800, "loss": 0.01, "lr": 4.827877658582258e-05, "epoch": 4.138613861386139, "percentage": 20.69, "elapsed_time": "1:28:52", "remaining_time": "5:40:35", "throughput": 1488.61, "total_tokens": 7937568} {"current_steps": 37625, "total_steps": 181800, "loss": 0.0221, "lr": 4.827790133309868e-05, "epoch": 4.139163916391639, "percentage": 20.7, "elapsed_time": "1:28:52", "remaining_time": "5:40:35", "throughput": 1488.62, "total_tokens": 7938624} {"current_steps": 37630, "total_steps": 181800, "loss": 0.0353, "lr": 4.827702586583353e-05, "epoch": 4.13971397139714, "percentage": 20.7, "elapsed_time": "1:28:53", "remaining_time": "5:40:34", "throughput": 1488.61, "total_tokens": 7939648} {"current_steps": 37635, "total_steps": 181800, "loss": 0.0227, "lr": 4.8276150184035194e-05, "epoch": 4.14026402640264, "percentage": 20.7, "elapsed_time": "1:28:54", "remaining_time": "5:40:33", "throughput": 1488.61, "total_tokens": 7940640} {"current_steps": 37640, "total_steps": 181800, "loss": 0.0456, "lr": 4.8275274287711767e-05, "epoch": 4.1408140814081404, "percentage": 20.7, "elapsed_time": "1:28:54", "remaining_time": "5:40:32", "throughput": 1488.61, "total_tokens": 7941696} {"current_steps": 37645, "total_steps": 181800, "loss": 0.0192, "lr": 4.8274398176871295e-05, "epoch": 4.1413641364136415, "percentage": 20.71, "elapsed_time": "1:28:55", "remaining_time": "5:40:31", "throughput": 1488.62, "total_tokens": 7942720} {"current_steps": 37650, "total_steps": 181800, "loss": 0.1587, "lr": 4.8273521851521865e-05, "epoch": 4.141914191419142, "percentage": 20.71, "elapsed_time": "1:28:56", "remaining_time": "5:40:31", "throughput": 1488.62, "total_tokens": 7943744} {"current_steps": 37655, "total_steps": 181800, "loss": 0.024, "lr": 4.827264531167155e-05, "epoch": 4.142464246424643, "percentage": 20.71, "elapsed_time": "1:28:57", "remaining_time": "5:40:30", "throughput": 1488.62, "total_tokens": 7944800} {"current_steps": 37660, "total_steps": 181800, "loss": 0.0964, "lr": 4.827176855732843e-05, "epoch": 4.143014301430143, "percentage": 20.72, "elapsed_time": "1:28:57", "remaining_time": "5:40:29", "throughput": 1488.62, "total_tokens": 7945856} {"current_steps": 37665, "total_steps": 181800, "loss": 0.0822, "lr": 4.827089158850059e-05, "epoch": 4.143564356435643, "percentage": 20.72, "elapsed_time": "1:28:58", "remaining_time": "5:40:28", "throughput": 1488.64, "total_tokens": 7946944} {"current_steps": 37670, "total_steps": 181800, "loss": 0.3062, "lr": 4.82700144051961e-05, "epoch": 4.144114411441144, "percentage": 20.72, "elapsed_time": "1:28:59", "remaining_time": "5:40:28", "throughput": 1488.64, "total_tokens": 7948000} {"current_steps": 37675, "total_steps": 181800, "loss": 0.0761, "lr": 4.826913700742306e-05, "epoch": 4.1446644664466445, "percentage": 20.72, "elapsed_time": "1:28:59", "remaining_time": "5:40:27", "throughput": 1488.65, "total_tokens": 7949056} {"current_steps": 37680, "total_steps": 181800, "loss": 0.0374, "lr": 4.826825939518955e-05, "epoch": 4.145214521452146, "percentage": 20.73, "elapsed_time": "1:29:00", "remaining_time": "5:40:26", "throughput": 1488.65, "total_tokens": 7950080} {"current_steps": 37685, "total_steps": 181800, "loss": 0.1279, "lr": 4.826738156850366e-05, "epoch": 4.145764576457646, "percentage": 20.73, "elapsed_time": "1:29:01", "remaining_time": "5:40:25", "throughput": 1488.65, "total_tokens": 7951136} {"current_steps": 37690, "total_steps": 181800, "loss": 0.0176, "lr": 4.826650352737347e-05, "epoch": 4.146314631463146, "percentage": 20.73, "elapsed_time": "1:29:01", "remaining_time": "5:40:24", "throughput": 1488.66, "total_tokens": 7952192} {"current_steps": 37695, "total_steps": 181800, "loss": 0.1109, "lr": 4.826562527180709e-05, "epoch": 4.146864686468647, "percentage": 20.73, "elapsed_time": "1:29:02", "remaining_time": "5:40:24", "throughput": 1488.66, "total_tokens": 7953216} {"current_steps": 37700, "total_steps": 181800, "loss": 0.1081, "lr": 4.826474680181261e-05, "epoch": 4.147414741474147, "percentage": 20.74, "elapsed_time": "1:29:03", "remaining_time": "5:40:23", "throughput": 1488.66, "total_tokens": 7954272} {"current_steps": 37705, "total_steps": 181800, "loss": 0.0415, "lr": 4.826386811739811e-05, "epoch": 4.1479647964796476, "percentage": 20.74, "elapsed_time": "1:29:03", "remaining_time": "5:40:22", "throughput": 1488.67, "total_tokens": 7955328} {"current_steps": 37710, "total_steps": 181800, "loss": 0.0372, "lr": 4.826298921857171e-05, "epoch": 4.148514851485149, "percentage": 20.74, "elapsed_time": "1:29:04", "remaining_time": "5:40:21", "throughput": 1488.67, "total_tokens": 7956352} {"current_steps": 37715, "total_steps": 181800, "loss": 0.0189, "lr": 4.82621101053415e-05, "epoch": 4.149064906490649, "percentage": 20.75, "elapsed_time": "1:29:05", "remaining_time": "5:40:20", "throughput": 1488.67, "total_tokens": 7957408} {"current_steps": 37720, "total_steps": 181800, "loss": 0.029, "lr": 4.826123077771557e-05, "epoch": 4.14961496149615, "percentage": 20.75, "elapsed_time": "1:29:05", "remaining_time": "5:40:20", "throughput": 1488.68, "total_tokens": 7958432} {"current_steps": 37725, "total_steps": 181800, "loss": 0.051, "lr": 4.826035123570205e-05, "epoch": 4.15016501650165, "percentage": 20.75, "elapsed_time": "1:29:06", "remaining_time": "5:40:19", "throughput": 1488.68, "total_tokens": 7959488} {"current_steps": 37730, "total_steps": 181800, "loss": 0.0857, "lr": 4.825947147930904e-05, "epoch": 4.15071507150715, "percentage": 20.75, "elapsed_time": "1:29:07", "remaining_time": "5:40:18", "throughput": 1488.69, "total_tokens": 7960544} {"current_steps": 37735, "total_steps": 181800, "loss": 0.0611, "lr": 4.8258591508544624e-05, "epoch": 4.1512651265126514, "percentage": 20.76, "elapsed_time": "1:29:08", "remaining_time": "5:40:17", "throughput": 1488.69, "total_tokens": 7961600} {"current_steps": 37740, "total_steps": 181800, "loss": 0.1069, "lr": 4.8257711323416946e-05, "epoch": 4.151815181518152, "percentage": 20.76, "elapsed_time": "1:29:08", "remaining_time": "5:40:17", "throughput": 1488.7, "total_tokens": 7962656} {"current_steps": 37745, "total_steps": 181800, "loss": 0.0161, "lr": 4.8256830923934104e-05, "epoch": 4.152365236523653, "percentage": 20.76, "elapsed_time": "1:29:09", "remaining_time": "5:40:16", "throughput": 1488.7, "total_tokens": 7963712} {"current_steps": 37750, "total_steps": 181800, "loss": 0.0279, "lr": 4.82559503101042e-05, "epoch": 4.152915291529153, "percentage": 20.76, "elapsed_time": "1:29:10", "remaining_time": "5:40:15", "throughput": 1488.72, "total_tokens": 7964864} {"current_steps": 37755, "total_steps": 181800, "loss": 0.0271, "lr": 4.825506948193537e-05, "epoch": 4.153465346534653, "percentage": 20.77, "elapsed_time": "1:29:10", "remaining_time": "5:40:14", "throughput": 1488.73, "total_tokens": 7965952} {"current_steps": 37760, "total_steps": 181800, "loss": 0.0601, "lr": 4.825418843943572e-05, "epoch": 4.154015401540154, "percentage": 20.77, "elapsed_time": "1:29:11", "remaining_time": "5:40:13", "throughput": 1488.73, "total_tokens": 7966976} {"current_steps": 37765, "total_steps": 181800, "loss": 0.0275, "lr": 4.825330718261337e-05, "epoch": 4.1545654565456545, "percentage": 20.77, "elapsed_time": "1:29:12", "remaining_time": "5:40:13", "throughput": 1488.74, "total_tokens": 7968032} {"current_steps": 37770, "total_steps": 181800, "loss": 0.0761, "lr": 4.825242571147645e-05, "epoch": 4.1551155115511555, "percentage": 20.78, "elapsed_time": "1:29:12", "remaining_time": "5:40:12", "throughput": 1488.74, "total_tokens": 7969088} {"current_steps": 37775, "total_steps": 181800, "loss": 0.1157, "lr": 4.825154402603308e-05, "epoch": 4.155665566556656, "percentage": 20.78, "elapsed_time": "1:29:13", "remaining_time": "5:40:11", "throughput": 1488.73, "total_tokens": 7970048} {"current_steps": 37780, "total_steps": 181800, "loss": 0.0118, "lr": 4.825066212629139e-05, "epoch": 4.156215621562156, "percentage": 20.78, "elapsed_time": "1:29:14", "remaining_time": "5:40:10", "throughput": 1488.75, "total_tokens": 7971168} {"current_steps": 37785, "total_steps": 181800, "loss": 0.0255, "lr": 4.824978001225949e-05, "epoch": 4.156765676567657, "percentage": 20.78, "elapsed_time": "1:29:14", "remaining_time": "5:40:10", "throughput": 1488.75, "total_tokens": 7972224} {"current_steps": 37790, "total_steps": 181800, "loss": 0.0698, "lr": 4.824889768394554e-05, "epoch": 4.157315731573157, "percentage": 20.79, "elapsed_time": "1:29:15", "remaining_time": "5:40:09", "throughput": 1488.77, "total_tokens": 7973312} {"current_steps": 37795, "total_steps": 181800, "loss": 0.1034, "lr": 4.824801514135765e-05, "epoch": 4.1578657865786575, "percentage": 20.79, "elapsed_time": "1:29:16", "remaining_time": "5:40:08", "throughput": 1488.77, "total_tokens": 7974368} {"current_steps": 37800, "total_steps": 181800, "loss": 0.0148, "lr": 4.8247132384503954e-05, "epoch": 4.158415841584159, "percentage": 20.79, "elapsed_time": "1:29:17", "remaining_time": "5:40:07", "throughput": 1488.78, "total_tokens": 7975424} {"current_steps": 37805, "total_steps": 181800, "loss": 0.007, "lr": 4.82462494133926e-05, "epoch": 4.158965896589659, "percentage": 20.79, "elapsed_time": "1:29:17", "remaining_time": "5:40:06", "throughput": 1488.78, "total_tokens": 7976448} {"current_steps": 37810, "total_steps": 181800, "loss": 0.1717, "lr": 4.8245366228031716e-05, "epoch": 4.15951595159516, "percentage": 20.8, "elapsed_time": "1:29:18", "remaining_time": "5:40:06", "throughput": 1488.77, "total_tokens": 7977440} {"current_steps": 37815, "total_steps": 181800, "loss": 0.1174, "lr": 4.824448282842945e-05, "epoch": 4.16006600660066, "percentage": 20.8, "elapsed_time": "1:29:19", "remaining_time": "5:40:05", "throughput": 1488.77, "total_tokens": 7978464} {"current_steps": 37820, "total_steps": 181800, "loss": 0.1021, "lr": 4.824359921459394e-05, "epoch": 4.16061606160616, "percentage": 20.8, "elapsed_time": "1:29:19", "remaining_time": "5:40:04", "throughput": 1488.77, "total_tokens": 7979488} {"current_steps": 37825, "total_steps": 181800, "loss": 0.0089, "lr": 4.824271538653333e-05, "epoch": 4.161166116611661, "percentage": 20.81, "elapsed_time": "1:29:20", "remaining_time": "5:40:03", "throughput": 1488.78, "total_tokens": 7980544} {"current_steps": 37830, "total_steps": 181800, "loss": 0.0153, "lr": 4.824183134425576e-05, "epoch": 4.161716171617162, "percentage": 20.81, "elapsed_time": "1:29:21", "remaining_time": "5:40:03", "throughput": 1488.78, "total_tokens": 7981600} {"current_steps": 37835, "total_steps": 181800, "loss": 0.1074, "lr": 4.824094708776938e-05, "epoch": 4.162266226622663, "percentage": 20.81, "elapsed_time": "1:29:21", "remaining_time": "5:40:02", "throughput": 1488.79, "total_tokens": 7982656} {"current_steps": 37840, "total_steps": 181800, "loss": 0.0834, "lr": 4.8240062617082356e-05, "epoch": 4.162816281628163, "percentage": 20.81, "elapsed_time": "1:29:22", "remaining_time": "5:40:01", "throughput": 1488.8, "total_tokens": 7983744} {"current_steps": 37845, "total_steps": 181800, "loss": 0.0266, "lr": 4.8239177932202816e-05, "epoch": 4.163366336633663, "percentage": 20.82, "elapsed_time": "1:29:23", "remaining_time": "5:40:00", "throughput": 1488.82, "total_tokens": 7984864} {"current_steps": 37850, "total_steps": 181800, "loss": 0.1044, "lr": 4.823829303313893e-05, "epoch": 4.163916391639164, "percentage": 20.82, "elapsed_time": "1:29:23", "remaining_time": "5:39:59", "throughput": 1488.83, "total_tokens": 7985952} {"current_steps": 37855, "total_steps": 181800, "loss": 0.0576, "lr": 4.823740791989885e-05, "epoch": 4.164466446644664, "percentage": 20.82, "elapsed_time": "1:29:24", "remaining_time": "5:39:59", "throughput": 1488.84, "total_tokens": 7987040} {"current_steps": 37860, "total_steps": 181800, "loss": 0.0218, "lr": 4.8236522592490715e-05, "epoch": 4.165016501650165, "percentage": 20.83, "elapsed_time": "1:29:25", "remaining_time": "5:39:58", "throughput": 1488.83, "total_tokens": 7988032} {"current_steps": 37865, "total_steps": 181800, "loss": 0.0702, "lr": 4.8235637050922724e-05, "epoch": 4.165566556655666, "percentage": 20.83, "elapsed_time": "1:29:25", "remaining_time": "5:39:57", "throughput": 1488.84, "total_tokens": 7989120} {"current_steps": 37870, "total_steps": 181800, "loss": 0.043, "lr": 4.8234751295203e-05, "epoch": 4.166116611661166, "percentage": 20.83, "elapsed_time": "1:29:26", "remaining_time": "5:39:56", "throughput": 1488.85, "total_tokens": 7990176} {"current_steps": 37875, "total_steps": 181800, "loss": 0.031, "lr": 4.823386532533973e-05, "epoch": 4.166666666666667, "percentage": 20.83, "elapsed_time": "1:29:27", "remaining_time": "5:39:56", "throughput": 1488.85, "total_tokens": 7991200} {"current_steps": 37880, "total_steps": 181800, "loss": 0.0679, "lr": 4.823297914134106e-05, "epoch": 4.167216721672167, "percentage": 20.84, "elapsed_time": "1:29:28", "remaining_time": "5:39:55", "throughput": 1488.86, "total_tokens": 7992288} {"current_steps": 37885, "total_steps": 181800, "loss": 0.0249, "lr": 4.823209274321518e-05, "epoch": 4.167766776677667, "percentage": 20.84, "elapsed_time": "1:29:28", "remaining_time": "5:39:54", "throughput": 1488.86, "total_tokens": 7993312} {"current_steps": 37890, "total_steps": 181800, "loss": 0.0191, "lr": 4.823120613097025e-05, "epoch": 4.1683168316831685, "percentage": 20.84, "elapsed_time": "1:29:29", "remaining_time": "5:39:53", "throughput": 1488.86, "total_tokens": 7994368} {"current_steps": 37895, "total_steps": 181800, "loss": 0.0363, "lr": 4.8230319304614444e-05, "epoch": 4.168866886688669, "percentage": 20.84, "elapsed_time": "1:29:30", "remaining_time": "5:39:52", "throughput": 1488.87, "total_tokens": 7995424} {"current_steps": 37900, "total_steps": 181800, "loss": 0.0664, "lr": 4.822943226415592e-05, "epoch": 4.16941694169417, "percentage": 20.85, "elapsed_time": "1:29:30", "remaining_time": "5:39:52", "throughput": 1488.87, "total_tokens": 7996480} {"current_steps": 37905, "total_steps": 181800, "loss": 0.0179, "lr": 4.822854500960288e-05, "epoch": 4.16996699669967, "percentage": 20.85, "elapsed_time": "1:29:31", "remaining_time": "5:39:51", "throughput": 1488.89, "total_tokens": 7997568} {"current_steps": 37910, "total_steps": 181800, "loss": 0.1062, "lr": 4.8227657540963475e-05, "epoch": 4.17051705170517, "percentage": 20.85, "elapsed_time": "1:29:32", "remaining_time": "5:39:50", "throughput": 1488.9, "total_tokens": 7998656} {"current_steps": 37915, "total_steps": 181800, "loss": 0.0332, "lr": 4.8226769858245894e-05, "epoch": 4.171067106710671, "percentage": 20.86, "elapsed_time": "1:29:32", "remaining_time": "5:39:49", "throughput": 1488.91, "total_tokens": 7999776} {"current_steps": 37920, "total_steps": 181800, "loss": 0.1712, "lr": 4.822588196145833e-05, "epoch": 4.1716171617161715, "percentage": 20.86, "elapsed_time": "1:29:33", "remaining_time": "5:39:49", "throughput": 1488.92, "total_tokens": 8000832} {"current_steps": 37925, "total_steps": 181800, "loss": 0.0063, "lr": 4.822499385060895e-05, "epoch": 4.172167216721673, "percentage": 20.86, "elapsed_time": "1:29:34", "remaining_time": "5:39:48", "throughput": 1488.91, "total_tokens": 8001824} {"current_steps": 37930, "total_steps": 181800, "loss": 0.0252, "lr": 4.8224105525705955e-05, "epoch": 4.172717271727173, "percentage": 20.86, "elapsed_time": "1:29:34", "remaining_time": "5:39:47", "throughput": 1488.91, "total_tokens": 8002848} {"current_steps": 37935, "total_steps": 181800, "loss": 0.0778, "lr": 4.8223216986757517e-05, "epoch": 4.173267326732673, "percentage": 20.87, "elapsed_time": "1:29:35", "remaining_time": "5:39:46", "throughput": 1488.92, "total_tokens": 8003936} {"current_steps": 37940, "total_steps": 181800, "loss": 0.0056, "lr": 4.822232823377183e-05, "epoch": 4.173817381738174, "percentage": 20.87, "elapsed_time": "1:29:36", "remaining_time": "5:39:45", "throughput": 1488.92, "total_tokens": 8004960} {"current_steps": 37945, "total_steps": 181800, "loss": 0.035, "lr": 4.822143926675709e-05, "epoch": 4.174367436743674, "percentage": 20.87, "elapsed_time": "1:29:37", "remaining_time": "5:39:45", "throughput": 1488.92, "total_tokens": 8005952} {"current_steps": 37950, "total_steps": 181800, "loss": 0.1785, "lr": 4.822055008572148e-05, "epoch": 4.174917491749175, "percentage": 20.87, "elapsed_time": "1:29:37", "remaining_time": "5:39:44", "throughput": 1488.94, "total_tokens": 8007072} {"current_steps": 37955, "total_steps": 181800, "loss": 0.0241, "lr": 4.8219660690673205e-05, "epoch": 4.175467546754676, "percentage": 20.88, "elapsed_time": "1:29:38", "remaining_time": "5:39:43", "throughput": 1488.94, "total_tokens": 8008096} {"current_steps": 37960, "total_steps": 181800, "loss": 0.0886, "lr": 4.821877108162047e-05, "epoch": 4.176017601760176, "percentage": 20.88, "elapsed_time": "1:29:39", "remaining_time": "5:39:42", "throughput": 1488.95, "total_tokens": 8009216} {"current_steps": 37965, "total_steps": 181800, "loss": 0.0516, "lr": 4.821788125857145e-05, "epoch": 4.176567656765677, "percentage": 20.88, "elapsed_time": "1:29:39", "remaining_time": "5:39:41", "throughput": 1488.95, "total_tokens": 8010208} {"current_steps": 37970, "total_steps": 181800, "loss": 0.0201, "lr": 4.821699122153437e-05, "epoch": 4.177117711771177, "percentage": 20.89, "elapsed_time": "1:29:40", "remaining_time": "5:39:41", "throughput": 1488.95, "total_tokens": 8011264} {"current_steps": 37975, "total_steps": 181800, "loss": 0.0282, "lr": 4.821610097051742e-05, "epoch": 4.177667766776677, "percentage": 20.89, "elapsed_time": "1:29:41", "remaining_time": "5:39:40", "throughput": 1488.97, "total_tokens": 8012384} {"current_steps": 37980, "total_steps": 181800, "loss": 0.1215, "lr": 4.82152105055288e-05, "epoch": 4.178217821782178, "percentage": 20.89, "elapsed_time": "1:29:41", "remaining_time": "5:39:39", "throughput": 1488.98, "total_tokens": 8013472} {"current_steps": 37985, "total_steps": 181800, "loss": 0.1032, "lr": 4.821431982657673e-05, "epoch": 4.178767876787679, "percentage": 20.89, "elapsed_time": "1:29:42", "remaining_time": "5:39:38", "throughput": 1488.98, "total_tokens": 8014496} {"current_steps": 37990, "total_steps": 181800, "loss": 0.0265, "lr": 4.821342893366941e-05, "epoch": 4.17931793179318, "percentage": 20.9, "elapsed_time": "1:29:43", "remaining_time": "5:39:38", "throughput": 1489.0, "total_tokens": 8015616} {"current_steps": 37995, "total_steps": 181800, "loss": 0.0339, "lr": 4.8212537826815064e-05, "epoch": 4.17986798679868, "percentage": 20.9, "elapsed_time": "1:29:43", "remaining_time": "5:39:37", "throughput": 1489.02, "total_tokens": 8016736} {"current_steps": 38000, "total_steps": 181800, "loss": 0.0128, "lr": 4.8211646506021884e-05, "epoch": 4.18041804180418, "percentage": 20.9, "elapsed_time": "1:29:44", "remaining_time": "5:39:36", "throughput": 1489.01, "total_tokens": 8017728} {"current_steps": 38005, "total_steps": 181800, "loss": 0.0361, "lr": 4.82107549712981e-05, "epoch": 4.180968096809681, "percentage": 20.9, "elapsed_time": "1:29:45", "remaining_time": "5:39:35", "throughput": 1489.01, "total_tokens": 8018784} {"current_steps": 38010, "total_steps": 181800, "loss": 0.0555, "lr": 4.820986322265193e-05, "epoch": 4.181518151815181, "percentage": 20.91, "elapsed_time": "1:29:45", "remaining_time": "5:39:34", "throughput": 1489.02, "total_tokens": 8019840} {"current_steps": 38015, "total_steps": 181800, "loss": 0.0178, "lr": 4.820897126009158e-05, "epoch": 4.1820682068206825, "percentage": 20.91, "elapsed_time": "1:29:46", "remaining_time": "5:39:34", "throughput": 1489.03, "total_tokens": 8020896} {"current_steps": 38020, "total_steps": 181800, "loss": 0.1161, "lr": 4.8208079083625285e-05, "epoch": 4.182618261826183, "percentage": 20.91, "elapsed_time": "1:29:47", "remaining_time": "5:39:33", "throughput": 1489.03, "total_tokens": 8021952} {"current_steps": 38025, "total_steps": 181800, "loss": 0.0378, "lr": 4.820718669326126e-05, "epoch": 4.183168316831683, "percentage": 20.92, "elapsed_time": "1:29:48", "remaining_time": "5:39:32", "throughput": 1489.04, "total_tokens": 8023008} {"current_steps": 38030, "total_steps": 181800, "loss": 0.0711, "lr": 4.820629408900773e-05, "epoch": 4.183718371837184, "percentage": 20.92, "elapsed_time": "1:29:48", "remaining_time": "5:39:31", "throughput": 1489.04, "total_tokens": 8024032} {"current_steps": 38035, "total_steps": 181800, "loss": 0.1315, "lr": 4.820540127087292e-05, "epoch": 4.184268426842684, "percentage": 20.92, "elapsed_time": "1:29:49", "remaining_time": "5:39:31", "throughput": 1489.03, "total_tokens": 8025056} {"current_steps": 38040, "total_steps": 181800, "loss": 0.0116, "lr": 4.8204508238865064e-05, "epoch": 4.184818481848184, "percentage": 20.92, "elapsed_time": "1:29:50", "remaining_time": "5:39:30", "throughput": 1489.03, "total_tokens": 8026080} {"current_steps": 38045, "total_steps": 181800, "loss": 0.0397, "lr": 4.8203614992992396e-05, "epoch": 4.1853685368536855, "percentage": 20.93, "elapsed_time": "1:29:50", "remaining_time": "5:39:29", "throughput": 1489.04, "total_tokens": 8027136} {"current_steps": 38050, "total_steps": 181800, "loss": 0.2281, "lr": 4.8202721533263134e-05, "epoch": 4.185918591859186, "percentage": 20.93, "elapsed_time": "1:29:51", "remaining_time": "5:39:28", "throughput": 1489.04, "total_tokens": 8028160} {"current_steps": 38055, "total_steps": 181800, "loss": 0.0252, "lr": 4.820182785968552e-05, "epoch": 4.186468646864687, "percentage": 20.93, "elapsed_time": "1:29:52", "remaining_time": "5:39:27", "throughput": 1489.04, "total_tokens": 8029216} {"current_steps": 38060, "total_steps": 181800, "loss": 0.0463, "lr": 4.8200933972267803e-05, "epoch": 4.187018701870187, "percentage": 20.94, "elapsed_time": "1:29:52", "remaining_time": "5:39:27", "throughput": 1489.04, "total_tokens": 8030208} {"current_steps": 38065, "total_steps": 181800, "loss": 0.0826, "lr": 4.8200039871018196e-05, "epoch": 4.187568756875687, "percentage": 20.94, "elapsed_time": "1:29:53", "remaining_time": "5:39:26", "throughput": 1489.04, "total_tokens": 8031232} {"current_steps": 38070, "total_steps": 181800, "loss": 0.0292, "lr": 4.8199145555944966e-05, "epoch": 4.188118811881188, "percentage": 20.94, "elapsed_time": "1:29:54", "remaining_time": "5:39:25", "throughput": 1489.04, "total_tokens": 8032256} {"current_steps": 38075, "total_steps": 181800, "loss": 0.01, "lr": 4.819825102705634e-05, "epoch": 4.1886688668866885, "percentage": 20.94, "elapsed_time": "1:29:54", "remaining_time": "5:39:24", "throughput": 1489.05, "total_tokens": 8033344} {"current_steps": 38080, "total_steps": 181800, "loss": 0.0294, "lr": 4.819735628436057e-05, "epoch": 4.18921892189219, "percentage": 20.95, "elapsed_time": "1:29:55", "remaining_time": "5:39:24", "throughput": 1489.05, "total_tokens": 8034400} {"current_steps": 38085, "total_steps": 181800, "loss": 0.0548, "lr": 4.819646132786589e-05, "epoch": 4.18976897689769, "percentage": 20.95, "elapsed_time": "1:29:56", "remaining_time": "5:39:23", "throughput": 1489.06, "total_tokens": 8035456} {"current_steps": 38090, "total_steps": 181800, "loss": 0.0456, "lr": 4.819556615758056e-05, "epoch": 4.19031903190319, "percentage": 20.95, "elapsed_time": "1:29:57", "remaining_time": "5:39:22", "throughput": 1489.06, "total_tokens": 8036480} {"current_steps": 38095, "total_steps": 181800, "loss": 0.0489, "lr": 4.819467077351283e-05, "epoch": 4.190869086908691, "percentage": 20.95, "elapsed_time": "1:29:57", "remaining_time": "5:39:21", "throughput": 1489.08, "total_tokens": 8037600} {"current_steps": 38100, "total_steps": 181800, "loss": 0.1198, "lr": 4.8193775175670944e-05, "epoch": 4.191419141914191, "percentage": 20.96, "elapsed_time": "1:29:58", "remaining_time": "5:39:20", "throughput": 1489.08, "total_tokens": 8038624} {"current_steps": 38105, "total_steps": 181800, "loss": 0.0479, "lr": 4.819287936406317e-05, "epoch": 4.191969196919692, "percentage": 20.96, "elapsed_time": "1:29:59", "remaining_time": "5:39:20", "throughput": 1489.09, "total_tokens": 8039712} {"current_steps": 38110, "total_steps": 181800, "loss": 0.0475, "lr": 4.819198333869774e-05, "epoch": 4.192519251925193, "percentage": 20.96, "elapsed_time": "1:29:59", "remaining_time": "5:39:19", "throughput": 1489.09, "total_tokens": 8040768} {"current_steps": 38115, "total_steps": 181800, "loss": 0.0368, "lr": 4.8191087099582944e-05, "epoch": 4.193069306930693, "percentage": 20.97, "elapsed_time": "1:30:00", "remaining_time": "5:39:18", "throughput": 1489.09, "total_tokens": 8041792} {"current_steps": 38120, "total_steps": 181800, "loss": 0.01, "lr": 4.819019064672703e-05, "epoch": 4.193619361936194, "percentage": 20.97, "elapsed_time": "1:30:01", "remaining_time": "5:39:17", "throughput": 1489.11, "total_tokens": 8042944} {"current_steps": 38125, "total_steps": 181800, "loss": 0.0148, "lr": 4.8189293980138236e-05, "epoch": 4.194169416941694, "percentage": 20.97, "elapsed_time": "1:30:01", "remaining_time": "5:39:17", "throughput": 1489.12, "total_tokens": 8044000} {"current_steps": 38130, "total_steps": 181800, "loss": 0.0431, "lr": 4.8188397099824865e-05, "epoch": 4.194719471947194, "percentage": 20.97, "elapsed_time": "1:30:02", "remaining_time": "5:39:16", "throughput": 1489.13, "total_tokens": 8045088} {"current_steps": 38135, "total_steps": 181800, "loss": 0.0184, "lr": 4.8187500005795154e-05, "epoch": 4.195269526952695, "percentage": 20.98, "elapsed_time": "1:30:03", "remaining_time": "5:39:15", "throughput": 1489.13, "total_tokens": 8046144} {"current_steps": 38140, "total_steps": 181800, "loss": 0.0833, "lr": 4.8186602698057385e-05, "epoch": 4.195819581958196, "percentage": 20.98, "elapsed_time": "1:30:03", "remaining_time": "5:39:14", "throughput": 1489.13, "total_tokens": 8047168} {"current_steps": 38145, "total_steps": 181800, "loss": 0.1183, "lr": 4.8185705176619836e-05, "epoch": 4.196369636963697, "percentage": 20.98, "elapsed_time": "1:30:04", "remaining_time": "5:39:13", "throughput": 1489.15, "total_tokens": 8048288} {"current_steps": 38150, "total_steps": 181800, "loss": 0.064, "lr": 4.8184807441490756e-05, "epoch": 4.196919691969197, "percentage": 20.98, "elapsed_time": "1:30:05", "remaining_time": "5:39:13", "throughput": 1489.15, "total_tokens": 8049344} {"current_steps": 38155, "total_steps": 181800, "loss": 0.0819, "lr": 4.8183909492678424e-05, "epoch": 4.197469746974697, "percentage": 20.99, "elapsed_time": "1:30:05", "remaining_time": "5:39:12", "throughput": 1489.15, "total_tokens": 8050336} {"current_steps": 38160, "total_steps": 181800, "loss": 0.0967, "lr": 4.8183011330191135e-05, "epoch": 4.198019801980198, "percentage": 20.99, "elapsed_time": "1:30:06", "remaining_time": "5:39:11", "throughput": 1489.15, "total_tokens": 8051392} {"current_steps": 38165, "total_steps": 181800, "loss": 0.0694, "lr": 4.818211295403715e-05, "epoch": 4.198569856985698, "percentage": 20.99, "elapsed_time": "1:30:07", "remaining_time": "5:39:10", "throughput": 1489.16, "total_tokens": 8052480} {"current_steps": 38170, "total_steps": 181800, "loss": 0.0567, "lr": 4.818121436422476e-05, "epoch": 4.1991199119911995, "percentage": 21.0, "elapsed_time": "1:30:08", "remaining_time": "5:39:10", "throughput": 1489.17, "total_tokens": 8053536} {"current_steps": 38175, "total_steps": 181800, "loss": 0.0396, "lr": 4.8180315560762236e-05, "epoch": 4.1996699669967, "percentage": 21.0, "elapsed_time": "1:30:08", "remaining_time": "5:39:09", "throughput": 1489.18, "total_tokens": 8054624} {"current_steps": 38180, "total_steps": 181800, "loss": 0.0965, "lr": 4.8179416543657864e-05, "epoch": 4.2002200220022, "percentage": 21.0, "elapsed_time": "1:30:09", "remaining_time": "5:39:08", "throughput": 1489.19, "total_tokens": 8055680} {"current_steps": 38185, "total_steps": 181800, "loss": 0.0266, "lr": 4.817851731291994e-05, "epoch": 4.200770077007701, "percentage": 21.0, "elapsed_time": "1:30:10", "remaining_time": "5:39:07", "throughput": 1489.19, "total_tokens": 8056736} {"current_steps": 38190, "total_steps": 181800, "loss": 0.0716, "lr": 4.8177617868556736e-05, "epoch": 4.201320132013201, "percentage": 21.01, "elapsed_time": "1:30:10", "remaining_time": "5:39:06", "throughput": 1489.2, "total_tokens": 8057792} {"current_steps": 38195, "total_steps": 181800, "loss": 0.0812, "lr": 4.817671821057655e-05, "epoch": 4.201870187018702, "percentage": 21.01, "elapsed_time": "1:30:11", "remaining_time": "5:39:06", "throughput": 1489.2, "total_tokens": 8058848} {"current_steps": 38200, "total_steps": 181800, "loss": 0.052, "lr": 4.817581833898768e-05, "epoch": 4.2024202420242025, "percentage": 21.01, "elapsed_time": "1:30:12", "remaining_time": "5:39:05", "throughput": 1489.2, "total_tokens": 8059840} {"current_steps": 38205, "total_steps": 181800, "loss": 0.0256, "lr": 4.817491825379841e-05, "epoch": 4.202970297029703, "percentage": 21.01, "elapsed_time": "1:30:12", "remaining_time": "5:39:04", "throughput": 1489.2, "total_tokens": 8060896} {"current_steps": 38210, "total_steps": 181800, "loss": 0.0129, "lr": 4.8174017955017034e-05, "epoch": 4.203520352035204, "percentage": 21.02, "elapsed_time": "1:30:13", "remaining_time": "5:39:03", "throughput": 1489.2, "total_tokens": 8061920} {"current_steps": 38215, "total_steps": 181800, "loss": 0.0751, "lr": 4.8173117442651864e-05, "epoch": 4.204070407040704, "percentage": 21.02, "elapsed_time": "1:30:14", "remaining_time": "5:39:03", "throughput": 1489.2, "total_tokens": 8062944} {"current_steps": 38220, "total_steps": 181800, "loss": 0.1302, "lr": 4.8172216716711185e-05, "epoch": 4.204620462046204, "percentage": 21.02, "elapsed_time": "1:30:14", "remaining_time": "5:39:02", "throughput": 1489.21, "total_tokens": 8064000} {"current_steps": 38225, "total_steps": 181800, "loss": 0.1105, "lr": 4.81713157772033e-05, "epoch": 4.205170517051705, "percentage": 21.03, "elapsed_time": "1:30:15", "remaining_time": "5:39:01", "throughput": 1489.21, "total_tokens": 8065088} {"current_steps": 38230, "total_steps": 181800, "loss": 0.0593, "lr": 4.817041462413652e-05, "epoch": 4.2057205720572055, "percentage": 21.03, "elapsed_time": "1:30:16", "remaining_time": "5:39:00", "throughput": 1489.21, "total_tokens": 8066112} {"current_steps": 38235, "total_steps": 181800, "loss": 0.0447, "lr": 4.816951325751915e-05, "epoch": 4.206270627062707, "percentage": 21.03, "elapsed_time": "1:30:17", "remaining_time": "5:38:59", "throughput": 1489.22, "total_tokens": 8067168} {"current_steps": 38240, "total_steps": 181800, "loss": 0.0294, "lr": 4.816861167735948e-05, "epoch": 4.206820682068207, "percentage": 21.03, "elapsed_time": "1:30:17", "remaining_time": "5:38:59", "throughput": 1489.23, "total_tokens": 8068256} {"current_steps": 38245, "total_steps": 181800, "loss": 0.1964, "lr": 4.816770988366584e-05, "epoch": 4.207370737073707, "percentage": 21.04, "elapsed_time": "1:30:18", "remaining_time": "5:38:58", "throughput": 1489.23, "total_tokens": 8069312} {"current_steps": 38250, "total_steps": 181800, "loss": 0.0142, "lr": 4.8166807876446546e-05, "epoch": 4.207920792079208, "percentage": 21.04, "elapsed_time": "1:30:19", "remaining_time": "5:38:57", "throughput": 1489.24, "total_tokens": 8070368} {"current_steps": 38255, "total_steps": 181800, "loss": 0.0211, "lr": 4.8165905655709895e-05, "epoch": 4.208470847084708, "percentage": 21.04, "elapsed_time": "1:30:19", "remaining_time": "5:38:56", "throughput": 1489.24, "total_tokens": 8071424} {"current_steps": 38260, "total_steps": 181800, "loss": 0.029, "lr": 4.81650032214642e-05, "epoch": 4.209020902090209, "percentage": 21.05, "elapsed_time": "1:30:20", "remaining_time": "5:38:56", "throughput": 1489.25, "total_tokens": 8072480} {"current_steps": 38265, "total_steps": 181800, "loss": 0.1123, "lr": 4.81641005737178e-05, "epoch": 4.20957095709571, "percentage": 21.05, "elapsed_time": "1:30:21", "remaining_time": "5:38:55", "throughput": 1489.26, "total_tokens": 8073536} {"current_steps": 38270, "total_steps": 181800, "loss": 0.0668, "lr": 4.816319771247899e-05, "epoch": 4.21012101210121, "percentage": 21.05, "elapsed_time": "1:30:21", "remaining_time": "5:38:54", "throughput": 1489.26, "total_tokens": 8074560} {"current_steps": 38275, "total_steps": 181800, "loss": 0.0232, "lr": 4.81622946377561e-05, "epoch": 4.210671067106711, "percentage": 21.05, "elapsed_time": "1:30:22", "remaining_time": "5:38:53", "throughput": 1489.26, "total_tokens": 8075616} {"current_steps": 38280, "total_steps": 181800, "loss": 0.0367, "lr": 4.816139134955746e-05, "epoch": 4.211221122112211, "percentage": 21.06, "elapsed_time": "1:30:23", "remaining_time": "5:38:52", "throughput": 1489.27, "total_tokens": 8076704} {"current_steps": 38285, "total_steps": 181800, "loss": 0.032, "lr": 4.816048784789139e-05, "epoch": 4.211771177117711, "percentage": 21.06, "elapsed_time": "1:30:23", "remaining_time": "5:38:52", "throughput": 1489.28, "total_tokens": 8077792} {"current_steps": 38290, "total_steps": 181800, "loss": 0.0273, "lr": 4.815958413276621e-05, "epoch": 4.212321232123212, "percentage": 21.06, "elapsed_time": "1:30:24", "remaining_time": "5:38:51", "throughput": 1489.29, "total_tokens": 8078848} {"current_steps": 38295, "total_steps": 181800, "loss": 0.0968, "lr": 4.8158680204190264e-05, "epoch": 4.212871287128713, "percentage": 21.06, "elapsed_time": "1:30:25", "remaining_time": "5:38:50", "throughput": 1489.3, "total_tokens": 8079904} {"current_steps": 38300, "total_steps": 181800, "loss": 0.0264, "lr": 4.8157776062171875e-05, "epoch": 4.213421342134214, "percentage": 21.07, "elapsed_time": "1:30:26", "remaining_time": "5:38:49", "throughput": 1489.3, "total_tokens": 8080960} {"current_steps": 38305, "total_steps": 181800, "loss": 0.0379, "lr": 4.815687170671937e-05, "epoch": 4.213971397139714, "percentage": 21.07, "elapsed_time": "1:30:26", "remaining_time": "5:38:49", "throughput": 1489.3, "total_tokens": 8081984} {"current_steps": 38310, "total_steps": 181800, "loss": 0.0645, "lr": 4.8155967137841094e-05, "epoch": 4.214521452145214, "percentage": 21.07, "elapsed_time": "1:30:27", "remaining_time": "5:38:48", "throughput": 1489.31, "total_tokens": 8083072} {"current_steps": 38315, "total_steps": 181800, "loss": 0.1061, "lr": 4.815506235554538e-05, "epoch": 4.215071507150715, "percentage": 21.08, "elapsed_time": "1:30:28", "remaining_time": "5:38:47", "throughput": 1489.32, "total_tokens": 8084160} {"current_steps": 38320, "total_steps": 181800, "loss": 0.1685, "lr": 4.815415735984057e-05, "epoch": 4.215621562156215, "percentage": 21.08, "elapsed_time": "1:30:28", "remaining_time": "5:38:46", "throughput": 1489.32, "total_tokens": 8085152} {"current_steps": 38325, "total_steps": 181800, "loss": 0.0714, "lr": 4.8153252150734996e-05, "epoch": 4.2161716171617165, "percentage": 21.08, "elapsed_time": "1:30:29", "remaining_time": "5:38:45", "throughput": 1489.32, "total_tokens": 8086176} {"current_steps": 38330, "total_steps": 181800, "loss": 0.0244, "lr": 4.8152346728237006e-05, "epoch": 4.216721672167217, "percentage": 21.08, "elapsed_time": "1:30:30", "remaining_time": "5:38:45", "throughput": 1489.33, "total_tokens": 8087264} {"current_steps": 38335, "total_steps": 181800, "loss": 0.0228, "lr": 4.815144109235496e-05, "epoch": 4.217271727172717, "percentage": 21.09, "elapsed_time": "1:30:30", "remaining_time": "5:38:44", "throughput": 1489.34, "total_tokens": 8088352} {"current_steps": 38340, "total_steps": 181800, "loss": 0.0342, "lr": 4.815053524309717e-05, "epoch": 4.217821782178218, "percentage": 21.09, "elapsed_time": "1:30:31", "remaining_time": "5:38:43", "throughput": 1489.34, "total_tokens": 8089408} {"current_steps": 38345, "total_steps": 181800, "loss": 0.0225, "lr": 4.814962918047202e-05, "epoch": 4.218371837183718, "percentage": 21.09, "elapsed_time": "1:30:32", "remaining_time": "5:38:42", "throughput": 1489.35, "total_tokens": 8090496} {"current_steps": 38350, "total_steps": 181800, "loss": 0.0311, "lr": 4.8148722904487845e-05, "epoch": 4.218921892189219, "percentage": 21.09, "elapsed_time": "1:30:32", "remaining_time": "5:38:42", "throughput": 1489.36, "total_tokens": 8091552} {"current_steps": 38355, "total_steps": 181800, "loss": 0.0163, "lr": 4.814781641515299e-05, "epoch": 4.2194719471947195, "percentage": 21.1, "elapsed_time": "1:30:33", "remaining_time": "5:38:41", "throughput": 1489.36, "total_tokens": 8092576} {"current_steps": 38360, "total_steps": 181800, "loss": 0.0411, "lr": 4.814690971247583e-05, "epoch": 4.22002200220022, "percentage": 21.1, "elapsed_time": "1:30:34", "remaining_time": "5:38:40", "throughput": 1489.35, "total_tokens": 8093600} {"current_steps": 38365, "total_steps": 181800, "loss": 0.019, "lr": 4.81460027964647e-05, "epoch": 4.220572057205721, "percentage": 21.1, "elapsed_time": "1:30:34", "remaining_time": "5:38:39", "throughput": 1489.36, "total_tokens": 8094656} {"current_steps": 38370, "total_steps": 181800, "loss": 0.0142, "lr": 4.814509566712797e-05, "epoch": 4.221122112211221, "percentage": 21.11, "elapsed_time": "1:30:35", "remaining_time": "5:38:38", "throughput": 1489.37, "total_tokens": 8095712} {"current_steps": 38375, "total_steps": 181800, "loss": 0.0186, "lr": 4.8144188324474e-05, "epoch": 4.221672167216722, "percentage": 21.11, "elapsed_time": "1:30:36", "remaining_time": "5:38:38", "throughput": 1489.37, "total_tokens": 8096768} {"current_steps": 38380, "total_steps": 181800, "loss": 0.0305, "lr": 4.814328076851116e-05, "epoch": 4.222222222222222, "percentage": 21.11, "elapsed_time": "1:30:37", "remaining_time": "5:38:37", "throughput": 1489.38, "total_tokens": 8097856} {"current_steps": 38385, "total_steps": 181800, "loss": 0.163, "lr": 4.8142372999247795e-05, "epoch": 4.2227722772277225, "percentage": 21.11, "elapsed_time": "1:30:37", "remaining_time": "5:38:36", "throughput": 1489.39, "total_tokens": 8098912} {"current_steps": 38390, "total_steps": 181800, "loss": 0.1097, "lr": 4.814146501669229e-05, "epoch": 4.223322332233224, "percentage": 21.12, "elapsed_time": "1:30:38", "remaining_time": "5:38:35", "throughput": 1489.4, "total_tokens": 8100000} {"current_steps": 38395, "total_steps": 181800, "loss": 0.1376, "lr": 4.814055682085301e-05, "epoch": 4.223872387238724, "percentage": 21.12, "elapsed_time": "1:30:39", "remaining_time": "5:38:35", "throughput": 1489.41, "total_tokens": 8101088} {"current_steps": 38400, "total_steps": 181800, "loss": 0.0992, "lr": 4.813964841173831e-05, "epoch": 4.224422442244224, "percentage": 21.12, "elapsed_time": "1:30:39", "remaining_time": "5:38:34", "throughput": 1489.41, "total_tokens": 8102112} {"current_steps": 38405, "total_steps": 181800, "loss": 0.0381, "lr": 4.813873978935659e-05, "epoch": 4.224972497249725, "percentage": 21.12, "elapsed_time": "1:30:40", "remaining_time": "5:38:33", "throughput": 1489.43, "total_tokens": 8103232} {"current_steps": 38410, "total_steps": 181800, "loss": 0.0304, "lr": 4.81378309537162e-05, "epoch": 4.225522552255225, "percentage": 21.13, "elapsed_time": "1:30:41", "remaining_time": "5:38:32", "throughput": 1489.43, "total_tokens": 8104288} {"current_steps": 38415, "total_steps": 181800, "loss": 0.0628, "lr": 4.813692190482552e-05, "epoch": 4.226072607260726, "percentage": 21.13, "elapsed_time": "1:30:41", "remaining_time": "5:38:31", "throughput": 1489.45, "total_tokens": 8105376} {"current_steps": 38420, "total_steps": 181800, "loss": 0.0686, "lr": 4.813601264269294e-05, "epoch": 4.226622662266227, "percentage": 21.13, "elapsed_time": "1:30:42", "remaining_time": "5:38:31", "throughput": 1489.45, "total_tokens": 8106432} {"current_steps": 38425, "total_steps": 181800, "loss": 0.0383, "lr": 4.813510316732682e-05, "epoch": 4.227172717271727, "percentage": 21.14, "elapsed_time": "1:30:43", "remaining_time": "5:38:30", "throughput": 1489.44, "total_tokens": 8107424} {"current_steps": 38430, "total_steps": 181800, "loss": 0.0641, "lr": 4.813419347873557e-05, "epoch": 4.227722772277228, "percentage": 21.14, "elapsed_time": "1:30:43", "remaining_time": "5:38:29", "throughput": 1489.45, "total_tokens": 8108480} {"current_steps": 38435, "total_steps": 181800, "loss": 0.0465, "lr": 4.813328357692756e-05, "epoch": 4.228272827282728, "percentage": 21.14, "elapsed_time": "1:30:44", "remaining_time": "5:38:28", "throughput": 1489.46, "total_tokens": 8109536} {"current_steps": 38440, "total_steps": 181800, "loss": 0.0114, "lr": 4.813237346191117e-05, "epoch": 4.228822882288229, "percentage": 21.14, "elapsed_time": "1:30:45", "remaining_time": "5:38:28", "throughput": 1489.45, "total_tokens": 8110560} {"current_steps": 38445, "total_steps": 181800, "loss": 0.0903, "lr": 4.813146313369479e-05, "epoch": 4.229372937293729, "percentage": 21.15, "elapsed_time": "1:30:46", "remaining_time": "5:38:27", "throughput": 1489.45, "total_tokens": 8111584} {"current_steps": 38450, "total_steps": 181800, "loss": 0.1077, "lr": 4.813055259228682e-05, "epoch": 4.22992299229923, "percentage": 21.15, "elapsed_time": "1:30:46", "remaining_time": "5:38:26", "throughput": 1489.46, "total_tokens": 8112640} {"current_steps": 38455, "total_steps": 181800, "loss": 0.1089, "lr": 4.812964183769564e-05, "epoch": 4.230473047304731, "percentage": 21.15, "elapsed_time": "1:30:47", "remaining_time": "5:38:25", "throughput": 1489.47, "total_tokens": 8113696} {"current_steps": 38460, "total_steps": 181800, "loss": 0.0182, "lr": 4.812873086992966e-05, "epoch": 4.231023102310231, "percentage": 21.16, "elapsed_time": "1:30:48", "remaining_time": "5:38:24", "throughput": 1489.48, "total_tokens": 8114784} {"current_steps": 38465, "total_steps": 181800, "loss": 0.1222, "lr": 4.8127819688997256e-05, "epoch": 4.231573157315731, "percentage": 21.16, "elapsed_time": "1:30:48", "remaining_time": "5:38:24", "throughput": 1489.48, "total_tokens": 8115840} {"current_steps": 38470, "total_steps": 181800, "loss": 0.1046, "lr": 4.8126908294906843e-05, "epoch": 4.232123212321232, "percentage": 21.16, "elapsed_time": "1:30:49", "remaining_time": "5:38:23", "throughput": 1489.48, "total_tokens": 8116864} {"current_steps": 38475, "total_steps": 181800, "loss": 0.109, "lr": 4.812599668766681e-05, "epoch": 4.232673267326732, "percentage": 21.16, "elapsed_time": "1:30:50", "remaining_time": "5:38:22", "throughput": 1489.48, "total_tokens": 8117856} {"current_steps": 38480, "total_steps": 181800, "loss": 0.0368, "lr": 4.812508486728557e-05, "epoch": 4.2332233223322335, "percentage": 21.17, "elapsed_time": "1:30:50", "remaining_time": "5:38:21", "throughput": 1489.48, "total_tokens": 8118880} {"current_steps": 38485, "total_steps": 181800, "loss": 0.0534, "lr": 4.81241728337715e-05, "epoch": 4.233773377337734, "percentage": 21.17, "elapsed_time": "1:30:51", "remaining_time": "5:38:20", "throughput": 1489.48, "total_tokens": 8119904} {"current_steps": 38490, "total_steps": 181800, "loss": 0.0154, "lr": 4.812326058713304e-05, "epoch": 4.234323432343234, "percentage": 21.17, "elapsed_time": "1:30:52", "remaining_time": "5:38:20", "throughput": 1489.5, "total_tokens": 8121024} {"current_steps": 38495, "total_steps": 181800, "loss": 0.0391, "lr": 4.812234812737858e-05, "epoch": 4.234873487348735, "percentage": 21.17, "elapsed_time": "1:30:52", "remaining_time": "5:38:19", "throughput": 1489.5, "total_tokens": 8122048} {"current_steps": 38500, "total_steps": 181800, "loss": 0.0757, "lr": 4.8121435454516537e-05, "epoch": 4.235423542354235, "percentage": 21.18, "elapsed_time": "1:30:53", "remaining_time": "5:38:18", "throughput": 1489.49, "total_tokens": 8123040} {"current_steps": 38505, "total_steps": 181800, "loss": 0.0774, "lr": 4.812052256855531e-05, "epoch": 4.235973597359736, "percentage": 21.18, "elapsed_time": "1:30:54", "remaining_time": "5:38:17", "throughput": 1489.5, "total_tokens": 8124096} {"current_steps": 38510, "total_steps": 181800, "loss": 0.0762, "lr": 4.8119609469503326e-05, "epoch": 4.2365236523652365, "percentage": 21.18, "elapsed_time": "1:30:54", "remaining_time": "5:38:17", "throughput": 1489.49, "total_tokens": 8125120} {"current_steps": 38515, "total_steps": 181800, "loss": 0.0333, "lr": 4.811869615736899e-05, "epoch": 4.237073707370737, "percentage": 21.19, "elapsed_time": "1:30:55", "remaining_time": "5:38:16", "throughput": 1489.51, "total_tokens": 8126240} {"current_steps": 38520, "total_steps": 181800, "loss": 0.033, "lr": 4.811778263216073e-05, "epoch": 4.237623762376238, "percentage": 21.19, "elapsed_time": "1:30:56", "remaining_time": "5:38:15", "throughput": 1489.52, "total_tokens": 8127328} {"current_steps": 38525, "total_steps": 181800, "loss": 0.0462, "lr": 4.811686889388696e-05, "epoch": 4.238173817381738, "percentage": 21.19, "elapsed_time": "1:30:57", "remaining_time": "5:38:14", "throughput": 1489.53, "total_tokens": 8128416} {"current_steps": 38530, "total_steps": 181800, "loss": 0.0239, "lr": 4.81159549425561e-05, "epoch": 4.238723872387239, "percentage": 21.19, "elapsed_time": "1:30:57", "remaining_time": "5:38:13", "throughput": 1489.53, "total_tokens": 8129408} {"current_steps": 38535, "total_steps": 181800, "loss": 0.078, "lr": 4.811504077817658e-05, "epoch": 4.239273927392739, "percentage": 21.2, "elapsed_time": "1:30:58", "remaining_time": "5:38:13", "throughput": 1489.53, "total_tokens": 8130432} {"current_steps": 38540, "total_steps": 181800, "loss": 0.0711, "lr": 4.811412640075681e-05, "epoch": 4.2398239823982395, "percentage": 21.2, "elapsed_time": "1:30:59", "remaining_time": "5:38:12", "throughput": 1489.53, "total_tokens": 8131456} {"current_steps": 38545, "total_steps": 181800, "loss": 0.1011, "lr": 4.8113211810305235e-05, "epoch": 4.240374037403741, "percentage": 21.2, "elapsed_time": "1:30:59", "remaining_time": "5:38:11", "throughput": 1489.54, "total_tokens": 8132544} {"current_steps": 38550, "total_steps": 181800, "loss": 0.1399, "lr": 4.811229700683028e-05, "epoch": 4.240924092409241, "percentage": 21.2, "elapsed_time": "1:31:00", "remaining_time": "5:38:10", "throughput": 1489.54, "total_tokens": 8133568} {"current_steps": 38555, "total_steps": 181800, "loss": 0.0563, "lr": 4.8111381990340374e-05, "epoch": 4.241474147414741, "percentage": 21.21, "elapsed_time": "1:31:01", "remaining_time": "5:38:10", "throughput": 1489.55, "total_tokens": 8134656} {"current_steps": 38560, "total_steps": 181800, "loss": 0.0827, "lr": 4.811046676084395e-05, "epoch": 4.242024202420242, "percentage": 21.21, "elapsed_time": "1:31:01", "remaining_time": "5:38:09", "throughput": 1489.57, "total_tokens": 8135776} {"current_steps": 38565, "total_steps": 181800, "loss": 0.0476, "lr": 4.8109551318349436e-05, "epoch": 4.242574257425742, "percentage": 21.21, "elapsed_time": "1:31:02", "remaining_time": "5:38:08", "throughput": 1489.56, "total_tokens": 8136800} {"current_steps": 38570, "total_steps": 181800, "loss": 0.0559, "lr": 4.810863566286529e-05, "epoch": 4.243124312431243, "percentage": 21.22, "elapsed_time": "1:31:03", "remaining_time": "5:38:07", "throughput": 1489.58, "total_tokens": 8137888} {"current_steps": 38575, "total_steps": 181800, "loss": 0.0723, "lr": 4.810771979439992e-05, "epoch": 4.243674367436744, "percentage": 21.22, "elapsed_time": "1:31:03", "remaining_time": "5:38:06", "throughput": 1489.59, "total_tokens": 8138976} {"current_steps": 38580, "total_steps": 181800, "loss": 0.0571, "lr": 4.81068037129618e-05, "epoch": 4.244224422442244, "percentage": 21.22, "elapsed_time": "1:31:04", "remaining_time": "5:38:06", "throughput": 1489.59, "total_tokens": 8140032} {"current_steps": 38585, "total_steps": 181800, "loss": 0.0107, "lr": 4.8105887418559346e-05, "epoch": 4.244774477447745, "percentage": 21.22, "elapsed_time": "1:31:05", "remaining_time": "5:38:05", "throughput": 1489.59, "total_tokens": 8141056} {"current_steps": 38590, "total_steps": 181800, "loss": 0.1833, "lr": 4.8104970911201025e-05, "epoch": 4.245324532453245, "percentage": 21.23, "elapsed_time": "1:31:05", "remaining_time": "5:38:04", "throughput": 1489.6, "total_tokens": 8142112} {"current_steps": 38595, "total_steps": 181800, "loss": 0.0223, "lr": 4.810405419089527e-05, "epoch": 4.245874587458746, "percentage": 21.23, "elapsed_time": "1:31:06", "remaining_time": "5:38:03", "throughput": 1489.6, "total_tokens": 8143136} {"current_steps": 38600, "total_steps": 181800, "loss": 0.0792, "lr": 4.8103137257650534e-05, "epoch": 4.2464246424642464, "percentage": 21.23, "elapsed_time": "1:31:07", "remaining_time": "5:38:03", "throughput": 1489.6, "total_tokens": 8144160} {"current_steps": 38605, "total_steps": 181800, "loss": 0.0252, "lr": 4.810222011147527e-05, "epoch": 4.246974697469747, "percentage": 21.23, "elapsed_time": "1:31:08", "remaining_time": "5:38:02", "throughput": 1489.61, "total_tokens": 8145248} {"current_steps": 38610, "total_steps": 181800, "loss": 0.0115, "lr": 4.810130275237792e-05, "epoch": 4.247524752475248, "percentage": 21.24, "elapsed_time": "1:31:08", "remaining_time": "5:38:01", "throughput": 1489.61, "total_tokens": 8146304} {"current_steps": 38615, "total_steps": 181800, "loss": 0.0223, "lr": 4.8100385180366955e-05, "epoch": 4.248074807480748, "percentage": 21.24, "elapsed_time": "1:31:09", "remaining_time": "5:38:00", "throughput": 1489.63, "total_tokens": 8147392} {"current_steps": 38620, "total_steps": 181800, "loss": 0.085, "lr": 4.809946739545083e-05, "epoch": 4.248624862486249, "percentage": 21.24, "elapsed_time": "1:31:10", "remaining_time": "5:37:59", "throughput": 1489.63, "total_tokens": 8148448} {"current_steps": 38625, "total_steps": 181800, "loss": 0.1156, "lr": 4.8098549397637985e-05, "epoch": 4.249174917491749, "percentage": 21.25, "elapsed_time": "1:31:10", "remaining_time": "5:37:59", "throughput": 1489.65, "total_tokens": 8149568} {"current_steps": 38630, "total_steps": 181800, "loss": 0.0361, "lr": 4.809763118693691e-05, "epoch": 4.2497249724972495, "percentage": 21.25, "elapsed_time": "1:31:11", "remaining_time": "5:37:58", "throughput": 1489.66, "total_tokens": 8150624} {"current_steps": 38635, "total_steps": 181800, "loss": 0.1174, "lr": 4.8096712763356036e-05, "epoch": 4.2502750275027505, "percentage": 21.25, "elapsed_time": "1:31:12", "remaining_time": "5:37:57", "throughput": 1489.67, "total_tokens": 8151712} {"current_steps": 38640, "total_steps": 181800, "loss": 0.0151, "lr": 4.809579412690385e-05, "epoch": 4.250825082508251, "percentage": 21.25, "elapsed_time": "1:31:12", "remaining_time": "5:37:56", "throughput": 1489.68, "total_tokens": 8152832} {"current_steps": 38645, "total_steps": 181800, "loss": 0.0377, "lr": 4.8094875277588815e-05, "epoch": 4.251375137513751, "percentage": 21.26, "elapsed_time": "1:31:13", "remaining_time": "5:37:55", "throughput": 1489.69, "total_tokens": 8153888} {"current_steps": 38650, "total_steps": 181800, "loss": 0.0529, "lr": 4.809395621541939e-05, "epoch": 4.251925192519252, "percentage": 21.26, "elapsed_time": "1:31:14", "remaining_time": "5:37:55", "throughput": 1489.69, "total_tokens": 8154912} {"current_steps": 38655, "total_steps": 181800, "loss": 0.046, "lr": 4.809303694040406e-05, "epoch": 4.252475247524752, "percentage": 21.26, "elapsed_time": "1:31:14", "remaining_time": "5:37:54", "throughput": 1489.71, "total_tokens": 8156032} {"current_steps": 38660, "total_steps": 181800, "loss": 0.108, "lr": 4.8092117452551286e-05, "epoch": 4.253025302530253, "percentage": 21.27, "elapsed_time": "1:31:15", "remaining_time": "5:37:53", "throughput": 1489.72, "total_tokens": 8157120} {"current_steps": 38665, "total_steps": 181800, "loss": 0.0692, "lr": 4.8091197751869544e-05, "epoch": 4.2535753575357536, "percentage": 21.27, "elapsed_time": "1:31:16", "remaining_time": "5:37:52", "throughput": 1489.73, "total_tokens": 8158208} {"current_steps": 38670, "total_steps": 181800, "loss": 0.0413, "lr": 4.809027783836731e-05, "epoch": 4.254125412541254, "percentage": 21.27, "elapsed_time": "1:31:16", "remaining_time": "5:37:52", "throughput": 1489.75, "total_tokens": 8159328} {"current_steps": 38675, "total_steps": 181800, "loss": 0.0287, "lr": 4.808935771205307e-05, "epoch": 4.254675467546755, "percentage": 21.27, "elapsed_time": "1:31:17", "remaining_time": "5:37:51", "throughput": 1489.75, "total_tokens": 8160352} {"current_steps": 38680, "total_steps": 181800, "loss": 0.013, "lr": 4.8088437372935305e-05, "epoch": 4.255225522552255, "percentage": 21.28, "elapsed_time": "1:31:18", "remaining_time": "5:37:50", "throughput": 1489.76, "total_tokens": 8161440} {"current_steps": 38685, "total_steps": 181800, "loss": 0.096, "lr": 4.808751682102248e-05, "epoch": 4.255775577557756, "percentage": 21.28, "elapsed_time": "1:31:19", "remaining_time": "5:37:49", "throughput": 1489.77, "total_tokens": 8162496} {"current_steps": 38690, "total_steps": 181800, "loss": 0.0102, "lr": 4.8086596056323094e-05, "epoch": 4.256325632563256, "percentage": 21.28, "elapsed_time": "1:31:19", "remaining_time": "5:37:48", "throughput": 1489.77, "total_tokens": 8163552} {"current_steps": 38695, "total_steps": 181800, "loss": 0.0795, "lr": 4.808567507884563e-05, "epoch": 4.256875687568757, "percentage": 21.28, "elapsed_time": "1:31:20", "remaining_time": "5:37:48", "throughput": 1489.78, "total_tokens": 8164608} {"current_steps": 38700, "total_steps": 181800, "loss": 0.0543, "lr": 4.808475388859858e-05, "epoch": 4.257425742574258, "percentage": 21.29, "elapsed_time": "1:31:21", "remaining_time": "5:37:47", "throughput": 1489.78, "total_tokens": 8165664} {"current_steps": 38705, "total_steps": 181800, "loss": 0.0307, "lr": 4.808383248559043e-05, "epoch": 4.257975797579758, "percentage": 21.29, "elapsed_time": "1:31:21", "remaining_time": "5:37:46", "throughput": 1489.79, "total_tokens": 8166720} {"current_steps": 38710, "total_steps": 181800, "loss": 0.0712, "lr": 4.808291086982967e-05, "epoch": 4.258525852585258, "percentage": 21.29, "elapsed_time": "1:31:22", "remaining_time": "5:37:45", "throughput": 1489.78, "total_tokens": 8167712} {"current_steps": 38715, "total_steps": 181800, "loss": 0.0245, "lr": 4.80819890413248e-05, "epoch": 4.259075907590759, "percentage": 21.3, "elapsed_time": "1:31:23", "remaining_time": "5:37:44", "throughput": 1489.79, "total_tokens": 8168768} {"current_steps": 38720, "total_steps": 181800, "loss": 0.1098, "lr": 4.808106700008431e-05, "epoch": 4.259625962596259, "percentage": 21.3, "elapsed_time": "1:31:23", "remaining_time": "5:37:44", "throughput": 1489.79, "total_tokens": 8169824} {"current_steps": 38725, "total_steps": 181800, "loss": 0.1146, "lr": 4.80801447461167e-05, "epoch": 4.2601760176017605, "percentage": 21.3, "elapsed_time": "1:31:24", "remaining_time": "5:37:43", "throughput": 1489.79, "total_tokens": 8170848} {"current_steps": 38730, "total_steps": 181800, "loss": 0.0128, "lr": 4.8079222279430476e-05, "epoch": 4.260726072607261, "percentage": 21.3, "elapsed_time": "1:31:25", "remaining_time": "5:37:42", "throughput": 1489.81, "total_tokens": 8171968} {"current_steps": 38735, "total_steps": 181800, "loss": 0.0635, "lr": 4.807829960003413e-05, "epoch": 4.261276127612761, "percentage": 21.31, "elapsed_time": "1:31:25", "remaining_time": "5:37:41", "throughput": 1489.81, "total_tokens": 8173024} {"current_steps": 38740, "total_steps": 181800, "loss": 0.0335, "lr": 4.8077376707936174e-05, "epoch": 4.261826182618262, "percentage": 21.31, "elapsed_time": "1:31:26", "remaining_time": "5:37:41", "throughput": 1489.81, "total_tokens": 8174048} {"current_steps": 38745, "total_steps": 181800, "loss": 0.0348, "lr": 4.807645360314511e-05, "epoch": 4.262376237623762, "percentage": 21.31, "elapsed_time": "1:31:27", "remaining_time": "5:37:40", "throughput": 1489.81, "total_tokens": 8175072} {"current_steps": 38750, "total_steps": 181800, "loss": 0.1074, "lr": 4.8075530285669444e-05, "epoch": 4.262926292629263, "percentage": 21.31, "elapsed_time": "1:31:28", "remaining_time": "5:37:39", "throughput": 1489.81, "total_tokens": 8176096} {"current_steps": 38755, "total_steps": 181800, "loss": 0.0338, "lr": 4.807460675551769e-05, "epoch": 4.2634763476347635, "percentage": 21.32, "elapsed_time": "1:31:28", "remaining_time": "5:37:38", "throughput": 1489.8, "total_tokens": 8177056} {"current_steps": 38760, "total_steps": 181800, "loss": 0.0262, "lr": 4.807368301269836e-05, "epoch": 4.264026402640264, "percentage": 21.32, "elapsed_time": "1:31:29", "remaining_time": "5:37:38", "throughput": 1489.8, "total_tokens": 8178112} {"current_steps": 38765, "total_steps": 181800, "loss": 0.0395, "lr": 4.8072759057219955e-05, "epoch": 4.264576457645765, "percentage": 21.32, "elapsed_time": "1:31:30", "remaining_time": "5:37:37", "throughput": 1489.81, "total_tokens": 8179168} {"current_steps": 38770, "total_steps": 181800, "loss": 0.0444, "lr": 4.8071834889091e-05, "epoch": 4.265126512651265, "percentage": 21.33, "elapsed_time": "1:31:30", "remaining_time": "5:37:36", "throughput": 1489.81, "total_tokens": 8180192} {"current_steps": 38775, "total_steps": 181800, "loss": 0.0189, "lr": 4.807091050832003e-05, "epoch": 4.265676567656766, "percentage": 21.33, "elapsed_time": "1:31:31", "remaining_time": "5:37:35", "throughput": 1489.82, "total_tokens": 8181280} {"current_steps": 38780, "total_steps": 181800, "loss": 0.0324, "lr": 4.806998591491554e-05, "epoch": 4.266226622662266, "percentage": 21.33, "elapsed_time": "1:31:32", "remaining_time": "5:37:34", "throughput": 1489.82, "total_tokens": 8182336} {"current_steps": 38785, "total_steps": 181800, "loss": 0.1236, "lr": 4.806906110888606e-05, "epoch": 4.2667766776677665, "percentage": 21.33, "elapsed_time": "1:31:32", "remaining_time": "5:37:34", "throughput": 1489.82, "total_tokens": 8183360} {"current_steps": 38790, "total_steps": 181800, "loss": 0.2037, "lr": 4.806813609024011e-05, "epoch": 4.267326732673268, "percentage": 21.34, "elapsed_time": "1:31:33", "remaining_time": "5:37:33", "throughput": 1489.82, "total_tokens": 8184384} {"current_steps": 38795, "total_steps": 181800, "loss": 0.0151, "lr": 4.806721085898623e-05, "epoch": 4.267876787678768, "percentage": 21.34, "elapsed_time": "1:31:34", "remaining_time": "5:37:32", "throughput": 1489.83, "total_tokens": 8185472} {"current_steps": 38800, "total_steps": 181800, "loss": 0.1175, "lr": 4.806628541513293e-05, "epoch": 4.268426842684269, "percentage": 21.34, "elapsed_time": "1:31:34", "remaining_time": "5:37:31", "throughput": 1489.83, "total_tokens": 8186528} {"current_steps": 38805, "total_steps": 181800, "loss": 0.0264, "lr": 4.806535975868874e-05, "epoch": 4.268976897689769, "percentage": 21.34, "elapsed_time": "1:31:35", "remaining_time": "5:37:31", "throughput": 1489.84, "total_tokens": 8187616} {"current_steps": 38810, "total_steps": 181800, "loss": 0.0126, "lr": 4.80644338896622e-05, "epoch": 4.269526952695269, "percentage": 21.35, "elapsed_time": "1:31:36", "remaining_time": "5:37:30", "throughput": 1489.86, "total_tokens": 8188736} {"current_steps": 38815, "total_steps": 181800, "loss": 0.0315, "lr": 4.8063507808061846e-05, "epoch": 4.27007700770077, "percentage": 21.35, "elapsed_time": "1:31:36", "remaining_time": "5:37:29", "throughput": 1489.87, "total_tokens": 8189792} {"current_steps": 38820, "total_steps": 181800, "loss": 0.0774, "lr": 4.80625815138962e-05, "epoch": 4.270627062706271, "percentage": 21.35, "elapsed_time": "1:31:37", "remaining_time": "5:37:28", "throughput": 1489.87, "total_tokens": 8190848} {"current_steps": 38825, "total_steps": 181800, "loss": 0.1529, "lr": 4.806165500717381e-05, "epoch": 4.271177117711771, "percentage": 21.36, "elapsed_time": "1:31:38", "remaining_time": "5:37:28", "throughput": 1489.87, "total_tokens": 8191840} {"current_steps": 38830, "total_steps": 181800, "loss": 0.0789, "lr": 4.8060728287903214e-05, "epoch": 4.271727172717272, "percentage": 21.36, "elapsed_time": "1:31:39", "remaining_time": "5:37:27", "throughput": 1489.86, "total_tokens": 8192864} {"current_steps": 38835, "total_steps": 181800, "loss": 0.0521, "lr": 4.805980135609295e-05, "epoch": 4.272277227722772, "percentage": 21.36, "elapsed_time": "1:31:39", "remaining_time": "5:37:26", "throughput": 1489.87, "total_tokens": 8193920} {"current_steps": 38840, "total_steps": 181800, "loss": 0.1166, "lr": 4.805887421175156e-05, "epoch": 4.272827282728273, "percentage": 21.36, "elapsed_time": "1:31:40", "remaining_time": "5:37:25", "throughput": 1489.87, "total_tokens": 8194944} {"current_steps": 38845, "total_steps": 181800, "loss": 0.0134, "lr": 4.805794685488759e-05, "epoch": 4.273377337733773, "percentage": 21.37, "elapsed_time": "1:31:41", "remaining_time": "5:37:24", "throughput": 1489.88, "total_tokens": 8196000} {"current_steps": 38850, "total_steps": 181800, "loss": 0.0519, "lr": 4.805701928550959e-05, "epoch": 4.273927392739274, "percentage": 21.37, "elapsed_time": "1:31:41", "remaining_time": "5:37:24", "throughput": 1489.89, "total_tokens": 8197120} {"current_steps": 38855, "total_steps": 181800, "loss": 0.0637, "lr": 4.80560915036261e-05, "epoch": 4.274477447744775, "percentage": 21.37, "elapsed_time": "1:31:42", "remaining_time": "5:37:23", "throughput": 1489.89, "total_tokens": 8198144} {"current_steps": 38860, "total_steps": 181800, "loss": 0.085, "lr": 4.8055163509245694e-05, "epoch": 4.275027502750275, "percentage": 21.38, "elapsed_time": "1:31:43", "remaining_time": "5:37:22", "throughput": 1489.9, "total_tokens": 8199232} {"current_steps": 38865, "total_steps": 181800, "loss": 0.0315, "lr": 4.805423530237689e-05, "epoch": 4.275577557755776, "percentage": 21.38, "elapsed_time": "1:31:43", "remaining_time": "5:37:21", "throughput": 1489.92, "total_tokens": 8200352} {"current_steps": 38870, "total_steps": 181800, "loss": 0.0567, "lr": 4.805330688302828e-05, "epoch": 4.276127612761276, "percentage": 21.38, "elapsed_time": "1:31:44", "remaining_time": "5:37:21", "throughput": 1489.92, "total_tokens": 8201376} {"current_steps": 38875, "total_steps": 181800, "loss": 0.0514, "lr": 4.80523782512084e-05, "epoch": 4.276677667766776, "percentage": 21.38, "elapsed_time": "1:31:45", "remaining_time": "5:37:20", "throughput": 1489.91, "total_tokens": 8202368} {"current_steps": 38880, "total_steps": 181800, "loss": 0.0661, "lr": 4.8051449406925795e-05, "epoch": 4.2772277227722775, "percentage": 21.39, "elapsed_time": "1:31:45", "remaining_time": "5:37:19", "throughput": 1489.92, "total_tokens": 8203424} {"current_steps": 38885, "total_steps": 181800, "loss": 0.0116, "lr": 4.805052035018905e-05, "epoch": 4.277777777777778, "percentage": 21.39, "elapsed_time": "1:31:46", "remaining_time": "5:37:18", "throughput": 1489.92, "total_tokens": 8204480} {"current_steps": 38890, "total_steps": 181800, "loss": 0.0394, "lr": 4.804959108100673e-05, "epoch": 4.278327832783278, "percentage": 21.39, "elapsed_time": "1:31:47", "remaining_time": "5:37:17", "throughput": 1489.92, "total_tokens": 8205472} {"current_steps": 38895, "total_steps": 181800, "loss": 0.02, "lr": 4.804866159938738e-05, "epoch": 4.278877887788779, "percentage": 21.39, "elapsed_time": "1:31:48", "remaining_time": "5:37:17", "throughput": 1489.92, "total_tokens": 8206496} {"current_steps": 38900, "total_steps": 181800, "loss": 0.0967, "lr": 4.8047731905339574e-05, "epoch": 4.279427942794279, "percentage": 21.4, "elapsed_time": "1:31:48", "remaining_time": "5:37:16", "throughput": 1489.93, "total_tokens": 8207616} {"current_steps": 38905, "total_steps": 181800, "loss": 0.085, "lr": 4.804680199887189e-05, "epoch": 4.27997799779978, "percentage": 21.4, "elapsed_time": "1:31:49", "remaining_time": "5:37:15", "throughput": 1489.93, "total_tokens": 8208640} {"current_steps": 38910, "total_steps": 181800, "loss": 0.0252, "lr": 4.804587187999289e-05, "epoch": 4.2805280528052805, "percentage": 21.4, "elapsed_time": "1:31:50", "remaining_time": "5:37:14", "throughput": 1489.93, "total_tokens": 8209664} {"current_steps": 38915, "total_steps": 181800, "loss": 0.1085, "lr": 4.804494154871114e-05, "epoch": 4.281078107810781, "percentage": 21.41, "elapsed_time": "1:31:50", "remaining_time": "5:37:14", "throughput": 1489.93, "total_tokens": 8210688} {"current_steps": 38920, "total_steps": 181800, "loss": 0.1568, "lr": 4.804401100503523e-05, "epoch": 4.281628162816282, "percentage": 21.41, "elapsed_time": "1:31:51", "remaining_time": "5:37:13", "throughput": 1489.94, "total_tokens": 8211744} {"current_steps": 38925, "total_steps": 181800, "loss": 0.0926, "lr": 4.804308024897371e-05, "epoch": 4.282178217821782, "percentage": 21.41, "elapsed_time": "1:31:52", "remaining_time": "5:37:12", "throughput": 1489.94, "total_tokens": 8212800} {"current_steps": 38930, "total_steps": 181800, "loss": 0.0556, "lr": 4.80421492805352e-05, "epoch": 4.282728272827283, "percentage": 21.41, "elapsed_time": "1:31:52", "remaining_time": "5:37:11", "throughput": 1489.95, "total_tokens": 8213888} {"current_steps": 38935, "total_steps": 181800, "loss": 0.0569, "lr": 4.804121809972825e-05, "epoch": 4.283278327832783, "percentage": 21.42, "elapsed_time": "1:31:53", "remaining_time": "5:37:10", "throughput": 1489.95, "total_tokens": 8214912} {"current_steps": 38940, "total_steps": 181800, "loss": 0.013, "lr": 4.804028670656145e-05, "epoch": 4.2838283828382835, "percentage": 21.42, "elapsed_time": "1:31:54", "remaining_time": "5:37:10", "throughput": 1489.95, "total_tokens": 8215936} {"current_steps": 38945, "total_steps": 181800, "loss": 0.0541, "lr": 4.803935510104337e-05, "epoch": 4.284378437843785, "percentage": 21.42, "elapsed_time": "1:31:54", "remaining_time": "5:37:09", "throughput": 1489.97, "total_tokens": 8217024} {"current_steps": 38950, "total_steps": 181800, "loss": 0.1482, "lr": 4.8038423283182623e-05, "epoch": 4.284928492849285, "percentage": 21.42, "elapsed_time": "1:31:55", "remaining_time": "5:37:08", "throughput": 1489.98, "total_tokens": 8218144} {"current_steps": 38955, "total_steps": 181800, "loss": 0.1072, "lr": 4.803749125298777e-05, "epoch": 4.285478547854786, "percentage": 21.43, "elapsed_time": "1:31:56", "remaining_time": "5:37:07", "throughput": 1489.98, "total_tokens": 8219168} {"current_steps": 38960, "total_steps": 181800, "loss": 0.0106, "lr": 4.803655901046743e-05, "epoch": 4.286028602860286, "percentage": 21.43, "elapsed_time": "1:31:56", "remaining_time": "5:37:07", "throughput": 1489.98, "total_tokens": 8220192} {"current_steps": 38965, "total_steps": 181800, "loss": 0.0352, "lr": 4.803562655563018e-05, "epoch": 4.286578657865786, "percentage": 21.43, "elapsed_time": "1:31:57", "remaining_time": "5:37:06", "throughput": 1490.0, "total_tokens": 8221312} {"current_steps": 38970, "total_steps": 181800, "loss": 0.1245, "lr": 4.80346938884846e-05, "epoch": 4.287128712871287, "percentage": 21.44, "elapsed_time": "1:31:58", "remaining_time": "5:37:05", "throughput": 1490.01, "total_tokens": 8222400} {"current_steps": 38975, "total_steps": 181800, "loss": 0.0751, "lr": 4.80337610090393e-05, "epoch": 4.287678767876788, "percentage": 21.44, "elapsed_time": "1:31:59", "remaining_time": "5:37:04", "throughput": 1490.04, "total_tokens": 8223552} {"current_steps": 38980, "total_steps": 181800, "loss": 0.0503, "lr": 4.8032827917302895e-05, "epoch": 4.288228822882289, "percentage": 21.44, "elapsed_time": "1:31:59", "remaining_time": "5:37:03", "throughput": 1490.05, "total_tokens": 8224640} {"current_steps": 38985, "total_steps": 181800, "loss": 0.0562, "lr": 4.803189461328395e-05, "epoch": 4.288778877887789, "percentage": 21.44, "elapsed_time": "1:32:00", "remaining_time": "5:37:03", "throughput": 1490.06, "total_tokens": 8225728} {"current_steps": 38990, "total_steps": 181800, "loss": 0.0264, "lr": 4.803096109699109e-05, "epoch": 4.289328932893289, "percentage": 21.45, "elapsed_time": "1:32:01", "remaining_time": "5:37:02", "throughput": 1490.06, "total_tokens": 8226752} {"current_steps": 38995, "total_steps": 181800, "loss": 0.0154, "lr": 4.803002736843292e-05, "epoch": 4.28987898789879, "percentage": 21.45, "elapsed_time": "1:32:01", "remaining_time": "5:37:01", "throughput": 1490.07, "total_tokens": 8227840} {"current_steps": 39000, "total_steps": 181800, "loss": 0.0419, "lr": 4.802909342761803e-05, "epoch": 4.29042904290429, "percentage": 21.45, "elapsed_time": "1:32:02", "remaining_time": "5:37:00", "throughput": 1490.08, "total_tokens": 8228928} {"current_steps": 39005, "total_steps": 181800, "loss": 0.0153, "lr": 4.8028159274555033e-05, "epoch": 4.290979097909791, "percentage": 21.45, "elapsed_time": "1:32:03", "remaining_time": "5:36:59", "throughput": 1490.09, "total_tokens": 8229984} {"current_steps": 39010, "total_steps": 181800, "loss": 0.0223, "lr": 4.802722490925255e-05, "epoch": 4.291529152915292, "percentage": 21.46, "elapsed_time": "1:32:03", "remaining_time": "5:36:59", "throughput": 1490.1, "total_tokens": 8231072} {"current_steps": 39015, "total_steps": 181800, "loss": 0.077, "lr": 4.802629033171918e-05, "epoch": 4.292079207920792, "percentage": 21.46, "elapsed_time": "1:32:04", "remaining_time": "5:36:58", "throughput": 1490.1, "total_tokens": 8232096} {"current_steps": 39020, "total_steps": 181800, "loss": 0.0813, "lr": 4.802535554196355e-05, "epoch": 4.292629262926293, "percentage": 21.46, "elapsed_time": "1:32:05", "remaining_time": "5:36:57", "throughput": 1490.09, "total_tokens": 8233088} {"current_steps": 39025, "total_steps": 181800, "loss": 0.0346, "lr": 4.802442053999425e-05, "epoch": 4.293179317931793, "percentage": 21.47, "elapsed_time": "1:32:05", "remaining_time": "5:36:56", "throughput": 1490.11, "total_tokens": 8234208} {"current_steps": 39030, "total_steps": 181800, "loss": 0.0568, "lr": 4.802348532581993e-05, "epoch": 4.293729372937293, "percentage": 21.47, "elapsed_time": "1:32:06", "remaining_time": "5:36:56", "throughput": 1490.12, "total_tokens": 8235264} {"current_steps": 39035, "total_steps": 181800, "loss": 0.0543, "lr": 4.8022549899449186e-05, "epoch": 4.2942794279427945, "percentage": 21.47, "elapsed_time": "1:32:07", "remaining_time": "5:36:55", "throughput": 1490.13, "total_tokens": 8236352} {"current_steps": 39040, "total_steps": 181800, "loss": 0.0496, "lr": 4.8021614260890647e-05, "epoch": 4.294829482948295, "percentage": 21.47, "elapsed_time": "1:32:07", "remaining_time": "5:36:54", "throughput": 1490.13, "total_tokens": 8237408} {"current_steps": 39045, "total_steps": 181800, "loss": 0.1333, "lr": 4.8020678410152935e-05, "epoch": 4.295379537953796, "percentage": 21.48, "elapsed_time": "1:32:08", "remaining_time": "5:36:53", "throughput": 1490.14, "total_tokens": 8238496} {"current_steps": 39050, "total_steps": 181800, "loss": 0.0172, "lr": 4.801974234724468e-05, "epoch": 4.295929592959296, "percentage": 21.48, "elapsed_time": "1:32:09", "remaining_time": "5:36:52", "throughput": 1490.16, "total_tokens": 8239616} {"current_steps": 39055, "total_steps": 181800, "loss": 0.0235, "lr": 4.80188060721745e-05, "epoch": 4.296479647964796, "percentage": 21.48, "elapsed_time": "1:32:10", "remaining_time": "5:36:52", "throughput": 1490.18, "total_tokens": 8240736} {"current_steps": 39060, "total_steps": 181800, "loss": 0.053, "lr": 4.8017869584951035e-05, "epoch": 4.297029702970297, "percentage": 21.49, "elapsed_time": "1:32:10", "remaining_time": "5:36:51", "throughput": 1490.19, "total_tokens": 8241824} {"current_steps": 39065, "total_steps": 181800, "loss": 0.04, "lr": 4.801693288558291e-05, "epoch": 4.2975797579757975, "percentage": 21.49, "elapsed_time": "1:32:11", "remaining_time": "5:36:50", "throughput": 1490.19, "total_tokens": 8242848} {"current_steps": 39070, "total_steps": 181800, "loss": 0.0626, "lr": 4.8015995974078764e-05, "epoch": 4.298129812981298, "percentage": 21.49, "elapsed_time": "1:32:12", "remaining_time": "5:36:49", "throughput": 1490.19, "total_tokens": 8243872} {"current_steps": 39075, "total_steps": 181800, "loss": 0.0862, "lr": 4.801505885044723e-05, "epoch": 4.298679867986799, "percentage": 21.49, "elapsed_time": "1:32:12", "remaining_time": "5:36:49", "throughput": 1490.19, "total_tokens": 8244896} {"current_steps": 39080, "total_steps": 181800, "loss": 0.1842, "lr": 4.801412151469693e-05, "epoch": 4.299229922992299, "percentage": 21.5, "elapsed_time": "1:32:13", "remaining_time": "5:36:48", "throughput": 1490.19, "total_tokens": 8245952} {"current_steps": 39085, "total_steps": 181800, "loss": 0.1169, "lr": 4.801318396683652e-05, "epoch": 4.2997799779978, "percentage": 21.5, "elapsed_time": "1:32:14", "remaining_time": "5:36:47", "throughput": 1490.19, "total_tokens": 8246976} {"current_steps": 39090, "total_steps": 181800, "loss": 0.0438, "lr": 4.801224620687463e-05, "epoch": 4.3003300330033, "percentage": 21.5, "elapsed_time": "1:32:14", "remaining_time": "5:36:46", "throughput": 1490.18, "total_tokens": 8247936} {"current_steps": 39095, "total_steps": 181800, "loss": 0.073, "lr": 4.8011308234819916e-05, "epoch": 4.3008800880088005, "percentage": 21.5, "elapsed_time": "1:32:15", "remaining_time": "5:36:45", "throughput": 1490.18, "total_tokens": 8248992} {"current_steps": 39100, "total_steps": 181800, "loss": 0.0279, "lr": 4.801037005068102e-05, "epoch": 4.301430143014302, "percentage": 21.51, "elapsed_time": "1:32:16", "remaining_time": "5:36:45", "throughput": 1490.19, "total_tokens": 8250016} {"current_steps": 39105, "total_steps": 181800, "loss": 0.0788, "lr": 4.800943165446657e-05, "epoch": 4.301980198019802, "percentage": 21.51, "elapsed_time": "1:32:16", "remaining_time": "5:36:44", "throughput": 1490.2, "total_tokens": 8251136} {"current_steps": 39110, "total_steps": 181800, "loss": 0.0405, "lr": 4.800849304618525e-05, "epoch": 4.302530253025303, "percentage": 21.51, "elapsed_time": "1:32:17", "remaining_time": "5:36:43", "throughput": 1490.21, "total_tokens": 8252192} {"current_steps": 39115, "total_steps": 181800, "loss": 0.0797, "lr": 4.8007554225845674e-05, "epoch": 4.303080308030803, "percentage": 21.52, "elapsed_time": "1:32:18", "remaining_time": "5:36:42", "throughput": 1490.21, "total_tokens": 8253216} {"current_steps": 39120, "total_steps": 181800, "loss": 0.0369, "lr": 4.8006615193456514e-05, "epoch": 4.303630363036303, "percentage": 21.52, "elapsed_time": "1:32:18", "remaining_time": "5:36:42", "throughput": 1490.21, "total_tokens": 8254240} {"current_steps": 39125, "total_steps": 181800, "loss": 0.0562, "lr": 4.800567594902643e-05, "epoch": 4.304180418041804, "percentage": 21.52, "elapsed_time": "1:32:19", "remaining_time": "5:36:41", "throughput": 1490.22, "total_tokens": 8255328} {"current_steps": 39130, "total_steps": 181800, "loss": 0.1004, "lr": 4.800473649256406e-05, "epoch": 4.304730473047305, "percentage": 21.52, "elapsed_time": "1:32:20", "remaining_time": "5:36:40", "throughput": 1490.22, "total_tokens": 8256352} {"current_steps": 39135, "total_steps": 181800, "loss": 0.0557, "lr": 4.800379682407808e-05, "epoch": 4.305280528052805, "percentage": 21.53, "elapsed_time": "1:32:21", "remaining_time": "5:36:39", "throughput": 1490.24, "total_tokens": 8257472} {"current_steps": 39140, "total_steps": 181800, "loss": 0.0304, "lr": 4.800285694357714e-05, "epoch": 4.305830583058306, "percentage": 21.53, "elapsed_time": "1:32:21", "remaining_time": "5:36:38", "throughput": 1490.24, "total_tokens": 8258496} {"current_steps": 39145, "total_steps": 181800, "loss": 0.0619, "lr": 4.800191685106991e-05, "epoch": 4.306380638063806, "percentage": 21.53, "elapsed_time": "1:32:22", "remaining_time": "5:36:38", "throughput": 1490.24, "total_tokens": 8259520} {"current_steps": 39150, "total_steps": 181800, "loss": 0.0745, "lr": 4.8000976546565036e-05, "epoch": 4.306930693069307, "percentage": 21.53, "elapsed_time": "1:32:23", "remaining_time": "5:36:37", "throughput": 1490.24, "total_tokens": 8260576} {"current_steps": 39155, "total_steps": 181800, "loss": 0.1612, "lr": 4.800003603007121e-05, "epoch": 4.307480748074807, "percentage": 21.54, "elapsed_time": "1:32:23", "remaining_time": "5:36:36", "throughput": 1490.24, "total_tokens": 8261600} {"current_steps": 39160, "total_steps": 181800, "loss": 0.1338, "lr": 4.7999095301597084e-05, "epoch": 4.3080308030803085, "percentage": 21.54, "elapsed_time": "1:32:24", "remaining_time": "5:36:35", "throughput": 1490.24, "total_tokens": 8262624} {"current_steps": 39165, "total_steps": 181800, "loss": 0.0771, "lr": 4.799815436115134e-05, "epoch": 4.308580858085809, "percentage": 21.54, "elapsed_time": "1:32:25", "remaining_time": "5:36:34", "throughput": 1490.24, "total_tokens": 8263648} {"current_steps": 39170, "total_steps": 181800, "loss": 0.0324, "lr": 4.799721320874263e-05, "epoch": 4.309130913091309, "percentage": 21.55, "elapsed_time": "1:32:25", "remaining_time": "5:36:34", "throughput": 1490.26, "total_tokens": 8264768} {"current_steps": 39175, "total_steps": 181800, "loss": 0.0333, "lr": 4.799627184437965e-05, "epoch": 4.30968096809681, "percentage": 21.55, "elapsed_time": "1:32:26", "remaining_time": "5:36:33", "throughput": 1490.27, "total_tokens": 8265888} {"current_steps": 39180, "total_steps": 181800, "loss": 0.1214, "lr": 4.799533026807107e-05, "epoch": 4.31023102310231, "percentage": 21.55, "elapsed_time": "1:32:27", "remaining_time": "5:36:32", "throughput": 1490.29, "total_tokens": 8266976} {"current_steps": 39185, "total_steps": 181800, "loss": 0.0265, "lr": 4.799438847982555e-05, "epoch": 4.31078107810781, "percentage": 21.55, "elapsed_time": "1:32:27", "remaining_time": "5:36:31", "throughput": 1490.3, "total_tokens": 8268064} {"current_steps": 39190, "total_steps": 181800, "loss": 0.0251, "lr": 4.79934464796518e-05, "epoch": 4.3113311331133115, "percentage": 21.56, "elapsed_time": "1:32:28", "remaining_time": "5:36:31", "throughput": 1490.31, "total_tokens": 8269152} {"current_steps": 39195, "total_steps": 181800, "loss": 0.0466, "lr": 4.799250426755848e-05, "epoch": 4.311881188118812, "percentage": 21.56, "elapsed_time": "1:32:29", "remaining_time": "5:36:30", "throughput": 1490.32, "total_tokens": 8270240} {"current_steps": 39200, "total_steps": 181800, "loss": 0.0776, "lr": 4.799156184355428e-05, "epoch": 4.312431243124313, "percentage": 21.56, "elapsed_time": "1:32:30", "remaining_time": "5:36:29", "throughput": 1490.33, "total_tokens": 8271360} {"current_steps": 39205, "total_steps": 181800, "loss": 0.0351, "lr": 4.799061920764789e-05, "epoch": 4.312981298129813, "percentage": 21.56, "elapsed_time": "1:32:30", "remaining_time": "5:36:28", "throughput": 1490.35, "total_tokens": 8272480} {"current_steps": 39210, "total_steps": 181800, "loss": 0.0738, "lr": 4.7989676359848e-05, "epoch": 4.313531353135313, "percentage": 21.57, "elapsed_time": "1:32:31", "remaining_time": "5:36:28", "throughput": 1490.35, "total_tokens": 8273536} {"current_steps": 39215, "total_steps": 181800, "loss": 0.0076, "lr": 4.798873330016329e-05, "epoch": 4.314081408140814, "percentage": 21.57, "elapsed_time": "1:32:32", "remaining_time": "5:36:27", "throughput": 1490.36, "total_tokens": 8274592} {"current_steps": 39220, "total_steps": 181800, "loss": 0.0374, "lr": 4.7987790028602454e-05, "epoch": 4.3146314631463145, "percentage": 21.57, "elapsed_time": "1:32:32", "remaining_time": "5:36:26", "throughput": 1490.37, "total_tokens": 8275680} {"current_steps": 39225, "total_steps": 181800, "loss": 0.0443, "lr": 4.798684654517419e-05, "epoch": 4.315181518151816, "percentage": 21.58, "elapsed_time": "1:32:33", "remaining_time": "5:36:25", "throughput": 1490.37, "total_tokens": 8276736} {"current_steps": 39230, "total_steps": 181800, "loss": 0.0741, "lr": 4.798590284988719e-05, "epoch": 4.315731573157316, "percentage": 21.58, "elapsed_time": "1:32:34", "remaining_time": "5:36:24", "throughput": 1490.37, "total_tokens": 8277760} {"current_steps": 39235, "total_steps": 181800, "loss": 0.0826, "lr": 4.798495894275015e-05, "epoch": 4.316281628162816, "percentage": 21.58, "elapsed_time": "1:32:34", "remaining_time": "5:36:24", "throughput": 1490.38, "total_tokens": 8278848} {"current_steps": 39240, "total_steps": 181800, "loss": 0.0304, "lr": 4.798401482377178e-05, "epoch": 4.316831683168317, "percentage": 21.58, "elapsed_time": "1:32:35", "remaining_time": "5:36:23", "throughput": 1490.39, "total_tokens": 8279904} {"current_steps": 39245, "total_steps": 181800, "loss": 0.0078, "lr": 4.798307049296077e-05, "epoch": 4.317381738173817, "percentage": 21.59, "elapsed_time": "1:32:36", "remaining_time": "5:36:22", "throughput": 1490.39, "total_tokens": 8280928} {"current_steps": 39250, "total_steps": 181800, "loss": 0.0261, "lr": 4.798212595032583e-05, "epoch": 4.3179317931793175, "percentage": 21.59, "elapsed_time": "1:32:36", "remaining_time": "5:36:21", "throughput": 1490.4, "total_tokens": 8282016} {"current_steps": 39255, "total_steps": 181800, "loss": 0.0127, "lr": 4.798118119587566e-05, "epoch": 4.318481848184819, "percentage": 21.59, "elapsed_time": "1:32:37", "remaining_time": "5:36:21", "throughput": 1490.41, "total_tokens": 8283104} {"current_steps": 39260, "total_steps": 181800, "loss": 0.0681, "lr": 4.7980236229618974e-05, "epoch": 4.319031903190319, "percentage": 21.6, "elapsed_time": "1:32:38", "remaining_time": "5:36:20", "throughput": 1490.41, "total_tokens": 8284128} {"current_steps": 39265, "total_steps": 181800, "loss": 0.1041, "lr": 4.797929105156448e-05, "epoch": 4.31958195819582, "percentage": 21.6, "elapsed_time": "1:32:38", "remaining_time": "5:36:19", "throughput": 1490.41, "total_tokens": 8285184} {"current_steps": 39270, "total_steps": 181800, "loss": 0.0912, "lr": 4.797834566172088e-05, "epoch": 4.32013201320132, "percentage": 21.6, "elapsed_time": "1:32:39", "remaining_time": "5:36:18", "throughput": 1490.42, "total_tokens": 8286272} {"current_steps": 39275, "total_steps": 181800, "loss": 0.0265, "lr": 4.797740006009689e-05, "epoch": 4.32068206820682, "percentage": 21.6, "elapsed_time": "1:32:40", "remaining_time": "5:36:18", "throughput": 1490.43, "total_tokens": 8287360} {"current_steps": 39280, "total_steps": 181800, "loss": 0.0591, "lr": 4.7976454246701244e-05, "epoch": 4.321232123212321, "percentage": 21.61, "elapsed_time": "1:32:41", "remaining_time": "5:36:17", "throughput": 1490.43, "total_tokens": 8288416} {"current_steps": 39285, "total_steps": 181800, "loss": 0.1039, "lr": 4.797550822154263e-05, "epoch": 4.321782178217822, "percentage": 21.61, "elapsed_time": "1:32:41", "remaining_time": "5:36:16", "throughput": 1490.44, "total_tokens": 8289472} {"current_steps": 39290, "total_steps": 181800, "loss": 0.0081, "lr": 4.797456198462979e-05, "epoch": 4.322332233223323, "percentage": 21.61, "elapsed_time": "1:32:42", "remaining_time": "5:36:15", "throughput": 1490.44, "total_tokens": 8290528} {"current_steps": 39295, "total_steps": 181800, "loss": 0.0862, "lr": 4.797361553597143e-05, "epoch": 4.322882288228823, "percentage": 21.61, "elapsed_time": "1:32:43", "remaining_time": "5:36:14", "throughput": 1490.45, "total_tokens": 8291584} {"current_steps": 39300, "total_steps": 181800, "loss": 0.0089, "lr": 4.7972668875576285e-05, "epoch": 4.323432343234323, "percentage": 21.62, "elapsed_time": "1:32:43", "remaining_time": "5:36:14", "throughput": 1490.46, "total_tokens": 8292672} {"current_steps": 39305, "total_steps": 181800, "loss": 0.0117, "lr": 4.7971722003453076e-05, "epoch": 4.323982398239824, "percentage": 21.62, "elapsed_time": "1:32:44", "remaining_time": "5:36:13", "throughput": 1490.46, "total_tokens": 8293728} {"current_steps": 39310, "total_steps": 181800, "loss": 0.0491, "lr": 4.7970774919610525e-05, "epoch": 4.324532453245324, "percentage": 21.62, "elapsed_time": "1:32:45", "remaining_time": "5:36:12", "throughput": 1490.47, "total_tokens": 8294784} {"current_steps": 39315, "total_steps": 181800, "loss": 0.0157, "lr": 4.796982762405736e-05, "epoch": 4.325082508250825, "percentage": 21.63, "elapsed_time": "1:32:45", "remaining_time": "5:36:11", "throughput": 1490.47, "total_tokens": 8295840} {"current_steps": 39320, "total_steps": 181800, "loss": 0.1354, "lr": 4.7968880116802326e-05, "epoch": 4.325632563256326, "percentage": 21.63, "elapsed_time": "1:32:46", "remaining_time": "5:36:11", "throughput": 1490.49, "total_tokens": 8296960} {"current_steps": 39325, "total_steps": 181800, "loss": 0.0471, "lr": 4.796793239785414e-05, "epoch": 4.326182618261826, "percentage": 21.63, "elapsed_time": "1:32:47", "remaining_time": "5:36:10", "throughput": 1490.49, "total_tokens": 8298016} {"current_steps": 39330, "total_steps": 181800, "loss": 0.1379, "lr": 4.7966984467221544e-05, "epoch": 4.326732673267327, "percentage": 21.63, "elapsed_time": "1:32:47", "remaining_time": "5:36:09", "throughput": 1490.49, "total_tokens": 8299040} {"current_steps": 39335, "total_steps": 181800, "loss": 0.0353, "lr": 4.7966036324913266e-05, "epoch": 4.327282728272827, "percentage": 21.64, "elapsed_time": "1:32:48", "remaining_time": "5:36:08", "throughput": 1490.5, "total_tokens": 8300128} {"current_steps": 39340, "total_steps": 181800, "loss": 0.0451, "lr": 4.7965087970938055e-05, "epoch": 4.327832783278327, "percentage": 21.64, "elapsed_time": "1:32:49", "remaining_time": "5:36:08", "throughput": 1490.51, "total_tokens": 8301184} {"current_steps": 39345, "total_steps": 181800, "loss": 0.0746, "lr": 4.796413940530465e-05, "epoch": 4.3283828382838285, "percentage": 21.64, "elapsed_time": "1:32:50", "remaining_time": "5:36:07", "throughput": 1490.52, "total_tokens": 8302272} {"current_steps": 39350, "total_steps": 181800, "loss": 0.0575, "lr": 4.796319062802179e-05, "epoch": 4.328932893289329, "percentage": 21.64, "elapsed_time": "1:32:50", "remaining_time": "5:36:06", "throughput": 1490.53, "total_tokens": 8303360} {"current_steps": 39355, "total_steps": 181800, "loss": 0.0133, "lr": 4.796224163909822e-05, "epoch": 4.32948294829483, "percentage": 21.65, "elapsed_time": "1:32:51", "remaining_time": "5:36:05", "throughput": 1490.54, "total_tokens": 8304416} {"current_steps": 39360, "total_steps": 181800, "loss": 0.0437, "lr": 4.7961292438542685e-05, "epoch": 4.33003300330033, "percentage": 21.65, "elapsed_time": "1:32:52", "remaining_time": "5:36:04", "throughput": 1490.53, "total_tokens": 8305408} {"current_steps": 39365, "total_steps": 181800, "loss": 0.0162, "lr": 4.796034302636394e-05, "epoch": 4.33058305830583, "percentage": 21.65, "elapsed_time": "1:32:52", "remaining_time": "5:36:04", "throughput": 1490.53, "total_tokens": 8306464} {"current_steps": 39370, "total_steps": 181800, "loss": 0.0404, "lr": 4.795939340257073e-05, "epoch": 4.331133113311331, "percentage": 21.66, "elapsed_time": "1:32:53", "remaining_time": "5:36:03", "throughput": 1490.55, "total_tokens": 8307552} {"current_steps": 39375, "total_steps": 181800, "loss": 0.0596, "lr": 4.795844356717181e-05, "epoch": 4.3316831683168315, "percentage": 21.66, "elapsed_time": "1:32:54", "remaining_time": "5:36:02", "throughput": 1490.56, "total_tokens": 8308640} {"current_steps": 39380, "total_steps": 181800, "loss": 0.0586, "lr": 4.795749352017593e-05, "epoch": 4.332233223322333, "percentage": 21.66, "elapsed_time": "1:32:54", "remaining_time": "5:36:01", "throughput": 1490.57, "total_tokens": 8309728} {"current_steps": 39385, "total_steps": 181800, "loss": 0.0797, "lr": 4.7956543261591846e-05, "epoch": 4.332783278327833, "percentage": 21.66, "elapsed_time": "1:32:55", "remaining_time": "5:36:01", "throughput": 1490.57, "total_tokens": 8310784} {"current_steps": 39390, "total_steps": 181800, "loss": 0.0973, "lr": 4.7955592791428314e-05, "epoch": 4.333333333333333, "percentage": 21.67, "elapsed_time": "1:32:56", "remaining_time": "5:36:00", "throughput": 1490.58, "total_tokens": 8311872} {"current_steps": 39395, "total_steps": 181800, "loss": 0.0674, "lr": 4.795464210969411e-05, "epoch": 4.333883388338834, "percentage": 21.67, "elapsed_time": "1:32:56", "remaining_time": "5:35:59", "throughput": 1490.58, "total_tokens": 8312896} {"current_steps": 39400, "total_steps": 181800, "loss": 0.0987, "lr": 4.7953691216397975e-05, "epoch": 4.334433443344334, "percentage": 21.67, "elapsed_time": "1:32:57", "remaining_time": "5:35:58", "throughput": 1490.58, "total_tokens": 8313920} {"current_steps": 39405, "total_steps": 181800, "loss": 0.0156, "lr": 4.795274011154869e-05, "epoch": 4.334983498349835, "percentage": 21.67, "elapsed_time": "1:32:58", "remaining_time": "5:35:58", "throughput": 1490.58, "total_tokens": 8314976} {"current_steps": 39410, "total_steps": 181800, "loss": 0.033, "lr": 4.795178879515501e-05, "epoch": 4.335533553355336, "percentage": 21.68, "elapsed_time": "1:32:59", "remaining_time": "5:35:57", "throughput": 1490.59, "total_tokens": 8316032} {"current_steps": 39415, "total_steps": 181800, "loss": 0.0372, "lr": 4.7950837267225704e-05, "epoch": 4.336083608360836, "percentage": 21.68, "elapsed_time": "1:32:59", "remaining_time": "5:35:56", "throughput": 1490.59, "total_tokens": 8317056} {"current_steps": 39420, "total_steps": 181800, "loss": 0.0121, "lr": 4.7949885527769545e-05, "epoch": 4.336633663366337, "percentage": 21.68, "elapsed_time": "1:33:00", "remaining_time": "5:35:55", "throughput": 1490.59, "total_tokens": 8318112} {"current_steps": 39425, "total_steps": 181800, "loss": 0.0466, "lr": 4.7948933576795306e-05, "epoch": 4.337183718371837, "percentage": 21.69, "elapsed_time": "1:33:01", "remaining_time": "5:35:54", "throughput": 1490.59, "total_tokens": 8319168} {"current_steps": 39430, "total_steps": 181800, "loss": 0.0508, "lr": 4.794798141431176e-05, "epoch": 4.337733773377337, "percentage": 21.69, "elapsed_time": "1:33:01", "remaining_time": "5:35:54", "throughput": 1490.6, "total_tokens": 8320256} {"current_steps": 39435, "total_steps": 181800, "loss": 0.1816, "lr": 4.794702904032767e-05, "epoch": 4.338283828382838, "percentage": 21.69, "elapsed_time": "1:33:02", "remaining_time": "5:35:53", "throughput": 1490.6, "total_tokens": 8321248} {"current_steps": 39440, "total_steps": 181800, "loss": 0.0247, "lr": 4.794607645485183e-05, "epoch": 4.338833883388339, "percentage": 21.69, "elapsed_time": "1:33:03", "remaining_time": "5:35:52", "throughput": 1490.6, "total_tokens": 8322272} {"current_steps": 39445, "total_steps": 181800, "loss": 0.0933, "lr": 4.7945123657893023e-05, "epoch": 4.33938393839384, "percentage": 21.7, "elapsed_time": "1:33:03", "remaining_time": "5:35:51", "throughput": 1490.6, "total_tokens": 8323328} {"current_steps": 39450, "total_steps": 181800, "loss": 0.0958, "lr": 4.794417064946001e-05, "epoch": 4.33993399339934, "percentage": 21.7, "elapsed_time": "1:33:04", "remaining_time": "5:35:51", "throughput": 1490.61, "total_tokens": 8324416} {"current_steps": 39455, "total_steps": 181800, "loss": 0.0234, "lr": 4.794321742956159e-05, "epoch": 4.34048404840484, "percentage": 21.7, "elapsed_time": "1:33:05", "remaining_time": "5:35:50", "throughput": 1490.62, "total_tokens": 8325472} {"current_steps": 39460, "total_steps": 181800, "loss": 0.0511, "lr": 4.794226399820654e-05, "epoch": 4.341034103410341, "percentage": 21.71, "elapsed_time": "1:33:05", "remaining_time": "5:35:49", "throughput": 1490.63, "total_tokens": 8326592} {"current_steps": 39465, "total_steps": 181800, "loss": 0.0343, "lr": 4.7941310355403656e-05, "epoch": 4.341584158415841, "percentage": 21.71, "elapsed_time": "1:33:06", "remaining_time": "5:35:48", "throughput": 1490.63, "total_tokens": 8327584} {"current_steps": 39470, "total_steps": 181800, "loss": 0.0687, "lr": 4.794035650116172e-05, "epoch": 4.3421342134213425, "percentage": 21.71, "elapsed_time": "1:33:07", "remaining_time": "5:35:48", "throughput": 1490.62, "total_tokens": 8328576} {"current_steps": 39475, "total_steps": 181800, "loss": 0.0798, "lr": 4.793940243548953e-05, "epoch": 4.342684268426843, "percentage": 21.71, "elapsed_time": "1:33:08", "remaining_time": "5:35:47", "throughput": 1490.61, "total_tokens": 8329568} {"current_steps": 39480, "total_steps": 181800, "loss": 0.0479, "lr": 4.793844815839588e-05, "epoch": 4.343234323432343, "percentage": 21.72, "elapsed_time": "1:33:08", "remaining_time": "5:35:46", "throughput": 1490.62, "total_tokens": 8330624} {"current_steps": 39485, "total_steps": 181800, "loss": 0.0876, "lr": 4.7937493669889546e-05, "epoch": 4.343784378437844, "percentage": 21.72, "elapsed_time": "1:33:09", "remaining_time": "5:35:45", "throughput": 1490.63, "total_tokens": 8331680} {"current_steps": 39490, "total_steps": 181800, "loss": 0.0228, "lr": 4.793653896997935e-05, "epoch": 4.344334433443344, "percentage": 21.72, "elapsed_time": "1:33:10", "remaining_time": "5:35:44", "throughput": 1490.64, "total_tokens": 8332768} {"current_steps": 39495, "total_steps": 181800, "loss": 0.05, "lr": 4.793558405867408e-05, "epoch": 4.3448844884488445, "percentage": 21.72, "elapsed_time": "1:33:10", "remaining_time": "5:35:44", "throughput": 1490.65, "total_tokens": 8333856} {"current_steps": 39500, "total_steps": 181800, "loss": 0.0599, "lr": 4.793462893598253e-05, "epoch": 4.3454345434543455, "percentage": 21.73, "elapsed_time": "1:33:11", "remaining_time": "5:35:43", "throughput": 1490.67, "total_tokens": 8335008} {"current_steps": 39505, "total_steps": 181800, "loss": 0.0807, "lr": 4.793367360191351e-05, "epoch": 4.345984598459846, "percentage": 21.73, "elapsed_time": "1:33:12", "remaining_time": "5:35:42", "throughput": 1490.68, "total_tokens": 8336096} {"current_steps": 39510, "total_steps": 181800, "loss": 0.1011, "lr": 4.793271805647583e-05, "epoch": 4.346534653465347, "percentage": 21.73, "elapsed_time": "1:33:12", "remaining_time": "5:35:41", "throughput": 1490.67, "total_tokens": 8337088} {"current_steps": 39515, "total_steps": 181800, "loss": 0.1204, "lr": 4.7931762299678295e-05, "epoch": 4.347084708470847, "percentage": 21.74, "elapsed_time": "1:33:13", "remaining_time": "5:35:41", "throughput": 1490.68, "total_tokens": 8338176} {"current_steps": 39520, "total_steps": 181800, "loss": 0.0426, "lr": 4.793080633152971e-05, "epoch": 4.347634763476347, "percentage": 21.74, "elapsed_time": "1:33:14", "remaining_time": "5:35:40", "throughput": 1490.7, "total_tokens": 8339264} {"current_steps": 39525, "total_steps": 181800, "loss": 0.041, "lr": 4.792985015203888e-05, "epoch": 4.348184818481848, "percentage": 21.74, "elapsed_time": "1:33:14", "remaining_time": "5:35:39", "throughput": 1490.71, "total_tokens": 8340352} {"current_steps": 39530, "total_steps": 181800, "loss": 0.0598, "lr": 4.792889376121462e-05, "epoch": 4.3487348734873486, "percentage": 21.74, "elapsed_time": "1:33:15", "remaining_time": "5:35:38", "throughput": 1490.71, "total_tokens": 8341376} {"current_steps": 39535, "total_steps": 181800, "loss": 0.0123, "lr": 4.792793715906576e-05, "epoch": 4.34928492849285, "percentage": 21.75, "elapsed_time": "1:33:16", "remaining_time": "5:35:37", "throughput": 1490.71, "total_tokens": 8342432} {"current_steps": 39540, "total_steps": 181800, "loss": 0.0462, "lr": 4.79269803456011e-05, "epoch": 4.34983498349835, "percentage": 21.75, "elapsed_time": "1:33:16", "remaining_time": "5:35:37", "throughput": 1490.71, "total_tokens": 8343488} {"current_steps": 39545, "total_steps": 181800, "loss": 0.0589, "lr": 4.792602332082946e-05, "epoch": 4.35038503850385, "percentage": 21.75, "elapsed_time": "1:33:17", "remaining_time": "5:35:36", "throughput": 1490.72, "total_tokens": 8344576} {"current_steps": 39550, "total_steps": 181800, "loss": 0.0222, "lr": 4.792506608475967e-05, "epoch": 4.350935093509351, "percentage": 21.75, "elapsed_time": "1:33:18", "remaining_time": "5:35:35", "throughput": 1490.73, "total_tokens": 8345632} {"current_steps": 39555, "total_steps": 181800, "loss": 0.0601, "lr": 4.7924108637400546e-05, "epoch": 4.351485148514851, "percentage": 21.76, "elapsed_time": "1:33:19", "remaining_time": "5:35:34", "throughput": 1490.75, "total_tokens": 8346784} {"current_steps": 39560, "total_steps": 181800, "loss": 0.0449, "lr": 4.792315097876091e-05, "epoch": 4.3520352035203524, "percentage": 21.76, "elapsed_time": "1:33:19", "remaining_time": "5:35:34", "throughput": 1490.75, "total_tokens": 8347808} {"current_steps": 39565, "total_steps": 181800, "loss": 0.0579, "lr": 4.79221931088496e-05, "epoch": 4.352585258525853, "percentage": 21.76, "elapsed_time": "1:33:20", "remaining_time": "5:35:33", "throughput": 1490.75, "total_tokens": 8348832} {"current_steps": 39570, "total_steps": 181800, "loss": 0.1124, "lr": 4.7921235027675426e-05, "epoch": 4.353135313531353, "percentage": 21.77, "elapsed_time": "1:33:21", "remaining_time": "5:35:32", "throughput": 1490.75, "total_tokens": 8349856} {"current_steps": 39575, "total_steps": 181800, "loss": 0.0321, "lr": 4.792027673524723e-05, "epoch": 4.353685368536854, "percentage": 21.77, "elapsed_time": "1:33:21", "remaining_time": "5:35:31", "throughput": 1490.74, "total_tokens": 8350816} {"current_steps": 39580, "total_steps": 181800, "loss": 0.0418, "lr": 4.791931823157384e-05, "epoch": 4.354235423542354, "percentage": 21.77, "elapsed_time": "1:33:22", "remaining_time": "5:35:31", "throughput": 1490.74, "total_tokens": 8351840} {"current_steps": 39585, "total_steps": 181800, "loss": 0.0786, "lr": 4.791835951666409e-05, "epoch": 4.354785478547855, "percentage": 21.77, "elapsed_time": "1:33:23", "remaining_time": "5:35:30", "throughput": 1490.74, "total_tokens": 8352864} {"current_steps": 39590, "total_steps": 181800, "loss": 0.1301, "lr": 4.791740059052682e-05, "epoch": 4.3553355335533555, "percentage": 21.78, "elapsed_time": "1:33:23", "remaining_time": "5:35:29", "throughput": 1490.74, "total_tokens": 8353888} {"current_steps": 39595, "total_steps": 181800, "loss": 0.0817, "lr": 4.7916441453170866e-05, "epoch": 4.355885588558856, "percentage": 21.78, "elapsed_time": "1:33:24", "remaining_time": "5:35:28", "throughput": 1490.74, "total_tokens": 8354944} {"current_steps": 39600, "total_steps": 181800, "loss": 0.0959, "lr": 4.791548210460507e-05, "epoch": 4.356435643564357, "percentage": 21.78, "elapsed_time": "1:33:25", "remaining_time": "5:35:27", "throughput": 1490.75, "total_tokens": 8356032} {"current_steps": 39605, "total_steps": 181800, "loss": 0.0735, "lr": 4.791452254483827e-05, "epoch": 4.356985698569857, "percentage": 21.78, "elapsed_time": "1:33:25", "remaining_time": "5:35:27", "throughput": 1490.76, "total_tokens": 8357088} {"current_steps": 39610, "total_steps": 181800, "loss": 0.1228, "lr": 4.7913562773879303e-05, "epoch": 4.357535753575357, "percentage": 21.79, "elapsed_time": "1:33:26", "remaining_time": "5:35:26", "throughput": 1490.77, "total_tokens": 8358176} {"current_steps": 39615, "total_steps": 181800, "loss": 0.0376, "lr": 4.7912602791737035e-05, "epoch": 4.358085808580858, "percentage": 21.79, "elapsed_time": "1:33:27", "remaining_time": "5:35:25", "throughput": 1490.78, "total_tokens": 8359264} {"current_steps": 39620, "total_steps": 181800, "loss": 0.0741, "lr": 4.791164259842029e-05, "epoch": 4.3586358635863585, "percentage": 21.79, "elapsed_time": "1:33:28", "remaining_time": "5:35:24", "throughput": 1490.78, "total_tokens": 8360288} {"current_steps": 39625, "total_steps": 181800, "loss": 0.0455, "lr": 4.791068219393794e-05, "epoch": 4.3591859185918596, "percentage": 21.8, "elapsed_time": "1:33:28", "remaining_time": "5:35:24", "throughput": 1490.78, "total_tokens": 8361344} {"current_steps": 39630, "total_steps": 181800, "loss": 0.1071, "lr": 4.790972157829882e-05, "epoch": 4.35973597359736, "percentage": 21.8, "elapsed_time": "1:33:29", "remaining_time": "5:35:23", "throughput": 1490.79, "total_tokens": 8362432} {"current_steps": 39635, "total_steps": 181800, "loss": 0.013, "lr": 4.790876075151179e-05, "epoch": 4.36028602860286, "percentage": 21.8, "elapsed_time": "1:33:30", "remaining_time": "5:35:22", "throughput": 1490.8, "total_tokens": 8363488} {"current_steps": 39640, "total_steps": 181800, "loss": 0.0267, "lr": 4.7907799713585705e-05, "epoch": 4.360836083608361, "percentage": 21.8, "elapsed_time": "1:33:30", "remaining_time": "5:35:21", "throughput": 1490.81, "total_tokens": 8364576} {"current_steps": 39645, "total_steps": 181800, "loss": 0.027, "lr": 4.790683846452943e-05, "epoch": 4.361386138613861, "percentage": 21.81, "elapsed_time": "1:33:31", "remaining_time": "5:35:21", "throughput": 1490.81, "total_tokens": 8365632} {"current_steps": 39650, "total_steps": 181800, "loss": 0.1117, "lr": 4.79058770043518e-05, "epoch": 4.361936193619362, "percentage": 21.81, "elapsed_time": "1:33:32", "remaining_time": "5:35:20", "throughput": 1490.81, "total_tokens": 8366688} {"current_steps": 39655, "total_steps": 181800, "loss": 0.0193, "lr": 4.790491533306171e-05, "epoch": 4.362486248624863, "percentage": 21.81, "elapsed_time": "1:33:32", "remaining_time": "5:35:19", "throughput": 1490.81, "total_tokens": 8367712} {"current_steps": 39660, "total_steps": 181800, "loss": 0.1611, "lr": 4.790395345066799e-05, "epoch": 4.363036303630363, "percentage": 21.82, "elapsed_time": "1:33:33", "remaining_time": "5:35:18", "throughput": 1490.82, "total_tokens": 8368800} {"current_steps": 39665, "total_steps": 181800, "loss": 0.0439, "lr": 4.790299135717953e-05, "epoch": 4.363586358635864, "percentage": 21.82, "elapsed_time": "1:33:34", "remaining_time": "5:35:17", "throughput": 1490.83, "total_tokens": 8369856} {"current_steps": 39670, "total_steps": 181800, "loss": 0.0438, "lr": 4.7902029052605194e-05, "epoch": 4.364136413641364, "percentage": 21.82, "elapsed_time": "1:33:34", "remaining_time": "5:35:17", "throughput": 1490.83, "total_tokens": 8370880} {"current_steps": 39675, "total_steps": 181800, "loss": 0.1084, "lr": 4.790106653695384e-05, "epoch": 4.364686468646864, "percentage": 21.82, "elapsed_time": "1:33:35", "remaining_time": "5:35:16", "throughput": 1490.84, "total_tokens": 8372000} {"current_steps": 39680, "total_steps": 181800, "loss": 0.0277, "lr": 4.790010381023434e-05, "epoch": 4.365236523652365, "percentage": 21.83, "elapsed_time": "1:33:36", "remaining_time": "5:35:15", "throughput": 1490.85, "total_tokens": 8373056} {"current_steps": 39685, "total_steps": 181800, "loss": 0.0908, "lr": 4.7899140872455584e-05, "epoch": 4.365786578657866, "percentage": 21.83, "elapsed_time": "1:33:36", "remaining_time": "5:35:14", "throughput": 1490.86, "total_tokens": 8374144} {"current_steps": 39690, "total_steps": 181800, "loss": 0.2098, "lr": 4.7898177723626425e-05, "epoch": 4.366336633663367, "percentage": 21.83, "elapsed_time": "1:33:37", "remaining_time": "5:35:14", "throughput": 1490.87, "total_tokens": 8375264} {"current_steps": 39695, "total_steps": 181800, "loss": 0.0446, "lr": 4.789721436375575e-05, "epoch": 4.366886688668867, "percentage": 21.83, "elapsed_time": "1:33:38", "remaining_time": "5:35:13", "throughput": 1490.87, "total_tokens": 8376256} {"current_steps": 39700, "total_steps": 181800, "loss": 0.0155, "lr": 4.789625079285244e-05, "epoch": 4.367436743674367, "percentage": 21.84, "elapsed_time": "1:33:39", "remaining_time": "5:35:12", "throughput": 1490.88, "total_tokens": 8377376} {"current_steps": 39705, "total_steps": 181800, "loss": 0.0184, "lr": 4.789528701092537e-05, "epoch": 4.367986798679868, "percentage": 21.84, "elapsed_time": "1:33:39", "remaining_time": "5:35:11", "throughput": 1490.89, "total_tokens": 8378432} {"current_steps": 39710, "total_steps": 181800, "loss": 0.0386, "lr": 4.789432301798343e-05, "epoch": 4.368536853685368, "percentage": 21.84, "elapsed_time": "1:33:40", "remaining_time": "5:35:11", "throughput": 1490.9, "total_tokens": 8379520} {"current_steps": 39715, "total_steps": 181800, "loss": 0.0167, "lr": 4.78933588140355e-05, "epoch": 4.3690869086908695, "percentage": 21.85, "elapsed_time": "1:33:41", "remaining_time": "5:35:10", "throughput": 1490.89, "total_tokens": 8380512} {"current_steps": 39720, "total_steps": 181800, "loss": 0.0684, "lr": 4.789239439909047e-05, "epoch": 4.36963696369637, "percentage": 21.85, "elapsed_time": "1:33:41", "remaining_time": "5:35:09", "throughput": 1490.9, "total_tokens": 8381568} {"current_steps": 39725, "total_steps": 181800, "loss": 0.0562, "lr": 4.789142977315721e-05, "epoch": 4.37018701870187, "percentage": 21.85, "elapsed_time": "1:33:42", "remaining_time": "5:35:08", "throughput": 1490.9, "total_tokens": 8382592} {"current_steps": 39730, "total_steps": 181800, "loss": 0.0623, "lr": 4.789046493624464e-05, "epoch": 4.370737073707371, "percentage": 21.85, "elapsed_time": "1:33:43", "remaining_time": "5:35:07", "throughput": 1490.89, "total_tokens": 8383584} {"current_steps": 39735, "total_steps": 181800, "loss": 0.0755, "lr": 4.7889499888361636e-05, "epoch": 4.371287128712871, "percentage": 21.86, "elapsed_time": "1:33:43", "remaining_time": "5:35:07", "throughput": 1490.88, "total_tokens": 8384576} {"current_steps": 39740, "total_steps": 181800, "loss": 0.073, "lr": 4.78885346295171e-05, "epoch": 4.371837183718371, "percentage": 21.86, "elapsed_time": "1:33:44", "remaining_time": "5:35:06", "throughput": 1490.89, "total_tokens": 8385632} {"current_steps": 39745, "total_steps": 181800, "loss": 0.1005, "lr": 4.7887569159719914e-05, "epoch": 4.3723872387238725, "percentage": 21.86, "elapsed_time": "1:33:45", "remaining_time": "5:35:05", "throughput": 1490.9, "total_tokens": 8386720} {"current_steps": 39750, "total_steps": 181800, "loss": 0.1355, "lr": 4.7886603478978996e-05, "epoch": 4.372937293729373, "percentage": 21.86, "elapsed_time": "1:33:45", "remaining_time": "5:35:04", "throughput": 1490.91, "total_tokens": 8387808} {"current_steps": 39755, "total_steps": 181800, "loss": 0.0563, "lr": 4.7885637587303225e-05, "epoch": 4.373487348734874, "percentage": 21.87, "elapsed_time": "1:33:46", "remaining_time": "5:35:04", "throughput": 1490.91, "total_tokens": 8388832} {"current_steps": 39760, "total_steps": 181800, "loss": 0.0308, "lr": 4.788467148470152e-05, "epoch": 4.374037403740374, "percentage": 21.87, "elapsed_time": "1:33:47", "remaining_time": "5:35:03", "throughput": 1490.9, "total_tokens": 8389824} {"current_steps": 39765, "total_steps": 181800, "loss": 0.0595, "lr": 4.788370517118278e-05, "epoch": 4.374587458745874, "percentage": 21.87, "elapsed_time": "1:33:48", "remaining_time": "5:35:02", "throughput": 1490.9, "total_tokens": 8390848} {"current_steps": 39770, "total_steps": 181800, "loss": 0.0601, "lr": 4.788273864675591e-05, "epoch": 4.375137513751375, "percentage": 21.88, "elapsed_time": "1:33:48", "remaining_time": "5:35:02", "throughput": 1490.85, "total_tokens": 8391872} {"current_steps": 39775, "total_steps": 181800, "loss": 0.0202, "lr": 4.788177191142981e-05, "epoch": 4.3756875687568755, "percentage": 21.88, "elapsed_time": "1:33:49", "remaining_time": "5:35:01", "throughput": 1490.84, "total_tokens": 8392864} {"current_steps": 39780, "total_steps": 181800, "loss": 0.0209, "lr": 4.788080496521341e-05, "epoch": 4.376237623762377, "percentage": 21.88, "elapsed_time": "1:33:50", "remaining_time": "5:35:00", "throughput": 1490.85, "total_tokens": 8393952} {"current_steps": 39785, "total_steps": 181800, "loss": 0.0304, "lr": 4.78798378081156e-05, "epoch": 4.376787678767877, "percentage": 21.88, "elapsed_time": "1:33:50", "remaining_time": "5:35:00", "throughput": 1490.87, "total_tokens": 8395104} {"current_steps": 39790, "total_steps": 181800, "loss": 0.0628, "lr": 4.787887044014531e-05, "epoch": 4.377337733773377, "percentage": 21.89, "elapsed_time": "1:33:51", "remaining_time": "5:34:59", "throughput": 1490.88, "total_tokens": 8396192} {"current_steps": 39795, "total_steps": 181800, "loss": 0.0494, "lr": 4.7877902861311446e-05, "epoch": 4.377887788778878, "percentage": 21.89, "elapsed_time": "1:33:52", "remaining_time": "5:34:58", "throughput": 1490.89, "total_tokens": 8397280} {"current_steps": 39800, "total_steps": 181800, "loss": 0.0269, "lr": 4.787693507162293e-05, "epoch": 4.378437843784378, "percentage": 21.89, "elapsed_time": "1:33:53", "remaining_time": "5:34:57", "throughput": 1490.91, "total_tokens": 8398368} {"current_steps": 39805, "total_steps": 181800, "loss": 0.0105, "lr": 4.787596707108868e-05, "epoch": 4.378987898789879, "percentage": 21.89, "elapsed_time": "1:33:53", "remaining_time": "5:34:57", "throughput": 1490.9, "total_tokens": 8399392} {"current_steps": 39810, "total_steps": 181800, "loss": 0.14, "lr": 4.7874998859717624e-05, "epoch": 4.37953795379538, "percentage": 21.9, "elapsed_time": "1:33:54", "remaining_time": "5:34:56", "throughput": 1490.92, "total_tokens": 8400512} {"current_steps": 39815, "total_steps": 181800, "loss": 0.0685, "lr": 4.787403043751867e-05, "epoch": 4.38008800880088, "percentage": 21.9, "elapsed_time": "1:33:55", "remaining_time": "5:34:55", "throughput": 1490.93, "total_tokens": 8401600} {"current_steps": 39820, "total_steps": 181800, "loss": 0.0998, "lr": 4.787306180450076e-05, "epoch": 4.380638063806381, "percentage": 21.9, "elapsed_time": "1:33:55", "remaining_time": "5:34:54", "throughput": 1490.94, "total_tokens": 8402656} {"current_steps": 39825, "total_steps": 181800, "loss": 0.0062, "lr": 4.787209296067282e-05, "epoch": 4.381188118811881, "percentage": 21.91, "elapsed_time": "1:33:56", "remaining_time": "5:34:54", "throughput": 1490.94, "total_tokens": 8403712} {"current_steps": 39830, "total_steps": 181800, "loss": 0.0377, "lr": 4.787112390604377e-05, "epoch": 4.381738173817382, "percentage": 21.91, "elapsed_time": "1:33:57", "remaining_time": "5:34:53", "throughput": 1490.94, "total_tokens": 8404736} {"current_steps": 39835, "total_steps": 181800, "loss": 0.1168, "lr": 4.787015464062254e-05, "epoch": 4.382288228822882, "percentage": 21.91, "elapsed_time": "1:33:57", "remaining_time": "5:34:52", "throughput": 1490.96, "total_tokens": 8405888} {"current_steps": 39840, "total_steps": 181800, "loss": 0.1071, "lr": 4.786918516441807e-05, "epoch": 4.382838283828383, "percentage": 21.91, "elapsed_time": "1:33:58", "remaining_time": "5:34:51", "throughput": 1490.97, "total_tokens": 8406976} {"current_steps": 39845, "total_steps": 181800, "loss": 0.0191, "lr": 4.786821547743931e-05, "epoch": 4.383388338833884, "percentage": 21.92, "elapsed_time": "1:33:59", "remaining_time": "5:34:50", "throughput": 1490.98, "total_tokens": 8408032} {"current_steps": 39850, "total_steps": 181800, "loss": 0.0664, "lr": 4.786724557969516e-05, "epoch": 4.383938393839384, "percentage": 21.92, "elapsed_time": "1:33:59", "remaining_time": "5:34:50", "throughput": 1490.98, "total_tokens": 8409056} {"current_steps": 39855, "total_steps": 181800, "loss": 0.1042, "lr": 4.786627547119459e-05, "epoch": 4.384488448844884, "percentage": 21.92, "elapsed_time": "1:34:00", "remaining_time": "5:34:49", "throughput": 1490.99, "total_tokens": 8410176} {"current_steps": 39860, "total_steps": 181800, "loss": 0.0265, "lr": 4.786530515194653e-05, "epoch": 4.385038503850385, "percentage": 21.93, "elapsed_time": "1:34:01", "remaining_time": "5:34:48", "throughput": 1491.0, "total_tokens": 8411232} {"current_steps": 39865, "total_steps": 181800, "loss": 0.019, "lr": 4.7864334621959916e-05, "epoch": 4.385588558855885, "percentage": 21.93, "elapsed_time": "1:34:02", "remaining_time": "5:34:47", "throughput": 1491.0, "total_tokens": 8412256} {"current_steps": 39870, "total_steps": 181800, "loss": 0.0495, "lr": 4.786336388124372e-05, "epoch": 4.3861386138613865, "percentage": 21.93, "elapsed_time": "1:34:02", "remaining_time": "5:34:47", "throughput": 1491.01, "total_tokens": 8413376} {"current_steps": 39875, "total_steps": 181800, "loss": 0.0401, "lr": 4.786239292980685e-05, "epoch": 4.386688668866887, "percentage": 21.93, "elapsed_time": "1:34:03", "remaining_time": "5:34:46", "throughput": 1491.02, "total_tokens": 8414432} {"current_steps": 39880, "total_steps": 181800, "loss": 0.0364, "lr": 4.786142176765829e-05, "epoch": 4.387238723872387, "percentage": 21.94, "elapsed_time": "1:34:04", "remaining_time": "5:34:45", "throughput": 1491.02, "total_tokens": 8415456} {"current_steps": 39885, "total_steps": 181800, "loss": 0.0171, "lr": 4.7860450394806966e-05, "epoch": 4.387788778877888, "percentage": 21.94, "elapsed_time": "1:34:04", "remaining_time": "5:34:44", "throughput": 1491.02, "total_tokens": 8416512} {"current_steps": 39890, "total_steps": 181800, "loss": 0.0682, "lr": 4.785947881126184e-05, "epoch": 4.388338833883388, "percentage": 21.94, "elapsed_time": "1:34:05", "remaining_time": "5:34:44", "throughput": 1491.04, "total_tokens": 8417664} {"current_steps": 39895, "total_steps": 181800, "loss": 0.0589, "lr": 4.7858507017031876e-05, "epoch": 4.388888888888889, "percentage": 21.94, "elapsed_time": "1:34:06", "remaining_time": "5:34:43", "throughput": 1491.05, "total_tokens": 8418720} {"current_steps": 39900, "total_steps": 181800, "loss": 0.0311, "lr": 4.785753501212601e-05, "epoch": 4.3894389438943895, "percentage": 21.95, "elapsed_time": "1:34:06", "remaining_time": "5:34:42", "throughput": 1491.05, "total_tokens": 8419744} {"current_steps": 39905, "total_steps": 181800, "loss": 0.0074, "lr": 4.785656279655322e-05, "epoch": 4.38998899889989, "percentage": 21.95, "elapsed_time": "1:34:07", "remaining_time": "5:34:41", "throughput": 1491.06, "total_tokens": 8420832} {"current_steps": 39910, "total_steps": 181800, "loss": 0.0534, "lr": 4.7855590370322455e-05, "epoch": 4.390539053905391, "percentage": 21.95, "elapsed_time": "1:34:08", "remaining_time": "5:34:40", "throughput": 1491.06, "total_tokens": 8421888} {"current_steps": 39915, "total_steps": 181800, "loss": 0.054, "lr": 4.7854617733442686e-05, "epoch": 4.391089108910891, "percentage": 21.96, "elapsed_time": "1:34:08", "remaining_time": "5:34:40", "throughput": 1491.07, "total_tokens": 8422976} {"current_steps": 39920, "total_steps": 181800, "loss": 0.0291, "lr": 4.7853644885922865e-05, "epoch": 4.391639163916391, "percentage": 21.96, "elapsed_time": "1:34:09", "remaining_time": "5:34:39", "throughput": 1491.08, "total_tokens": 8424032} {"current_steps": 39925, "total_steps": 181800, "loss": 0.0499, "lr": 4.7852671827771964e-05, "epoch": 4.392189218921892, "percentage": 21.96, "elapsed_time": "1:34:10", "remaining_time": "5:34:38", "throughput": 1491.08, "total_tokens": 8425056} {"current_steps": 39930, "total_steps": 181800, "loss": 0.0103, "lr": 4.785169855899896e-05, "epoch": 4.3927392739273925, "percentage": 21.96, "elapsed_time": "1:34:11", "remaining_time": "5:34:37", "throughput": 1491.09, "total_tokens": 8426176} {"current_steps": 39935, "total_steps": 181800, "loss": 0.0815, "lr": 4.785072507961281e-05, "epoch": 4.393289328932894, "percentage": 21.97, "elapsed_time": "1:34:11", "remaining_time": "5:34:37", "throughput": 1491.11, "total_tokens": 8427296} {"current_steps": 39940, "total_steps": 181800, "loss": 0.0405, "lr": 4.78497513896225e-05, "epoch": 4.393839383938394, "percentage": 21.97, "elapsed_time": "1:34:12", "remaining_time": "5:34:36", "throughput": 1491.11, "total_tokens": 8428352} {"current_steps": 39945, "total_steps": 181800, "loss": 0.0324, "lr": 4.784877748903699e-05, "epoch": 4.394389438943894, "percentage": 21.97, "elapsed_time": "1:34:13", "remaining_time": "5:34:35", "throughput": 1491.12, "total_tokens": 8429440} {"current_steps": 39950, "total_steps": 181800, "loss": 0.0935, "lr": 4.784780337786526e-05, "epoch": 4.394939493949395, "percentage": 21.97, "elapsed_time": "1:34:13", "remaining_time": "5:34:34", "throughput": 1491.13, "total_tokens": 8430496} {"current_steps": 39955, "total_steps": 181800, "loss": 0.0411, "lr": 4.7846829056116295e-05, "epoch": 4.395489548954895, "percentage": 21.98, "elapsed_time": "1:34:14", "remaining_time": "5:34:34", "throughput": 1491.13, "total_tokens": 8431520} {"current_steps": 39960, "total_steps": 181800, "loss": 0.1238, "lr": 4.7845854523799065e-05, "epoch": 4.396039603960396, "percentage": 21.98, "elapsed_time": "1:34:15", "remaining_time": "5:34:33", "throughput": 1491.14, "total_tokens": 8432608} {"current_steps": 39965, "total_steps": 181800, "loss": 0.0655, "lr": 4.784487978092256e-05, "epoch": 4.396589658965897, "percentage": 21.98, "elapsed_time": "1:34:15", "remaining_time": "5:34:32", "throughput": 1491.15, "total_tokens": 8433696} {"current_steps": 39970, "total_steps": 181800, "loss": 0.1367, "lr": 4.7843904827495755e-05, "epoch": 4.397139713971397, "percentage": 21.99, "elapsed_time": "1:34:16", "remaining_time": "5:34:31", "throughput": 1491.15, "total_tokens": 8434752} {"current_steps": 39975, "total_steps": 181800, "loss": 0.038, "lr": 4.7842929663527645e-05, "epoch": 4.397689768976898, "percentage": 21.99, "elapsed_time": "1:34:17", "remaining_time": "5:34:30", "throughput": 1491.17, "total_tokens": 8435872} {"current_steps": 39980, "total_steps": 181800, "loss": 0.1114, "lr": 4.784195428902721e-05, "epoch": 4.398239823982398, "percentage": 21.99, "elapsed_time": "1:34:17", "remaining_time": "5:34:30", "throughput": 1491.17, "total_tokens": 8436928} {"current_steps": 39985, "total_steps": 181800, "loss": 0.0239, "lr": 4.784097870400345e-05, "epoch": 4.398789878987899, "percentage": 21.99, "elapsed_time": "1:34:18", "remaining_time": "5:34:29", "throughput": 1491.19, "total_tokens": 8438048} {"current_steps": 39990, "total_steps": 181800, "loss": 0.0649, "lr": 4.784000290846534e-05, "epoch": 4.399339933993399, "percentage": 22.0, "elapsed_time": "1:34:19", "remaining_time": "5:34:28", "throughput": 1491.19, "total_tokens": 8439104} {"current_steps": 39995, "total_steps": 181800, "loss": 0.0419, "lr": 4.7839026902421894e-05, "epoch": 4.3998899889989, "percentage": 22.0, "elapsed_time": "1:34:20", "remaining_time": "5:34:27", "throughput": 1491.2, "total_tokens": 8440192} {"current_steps": 40000, "total_steps": 181800, "loss": 0.0556, "lr": 4.7838050685882085e-05, "epoch": 4.400440044004401, "percentage": 22.0, "elapsed_time": "1:34:20", "remaining_time": "5:34:27", "throughput": 1491.21, "total_tokens": 8441280} {"current_steps": 40005, "total_steps": 181800, "loss": 0.1145, "lr": 4.783707425885493e-05, "epoch": 4.400990099009901, "percentage": 22.0, "elapsed_time": "1:34:21", "remaining_time": "5:34:26", "throughput": 1491.21, "total_tokens": 8442304} {"current_steps": 40010, "total_steps": 181800, "loss": 0.0399, "lr": 4.783609762134941e-05, "epoch": 4.401540154015402, "percentage": 22.01, "elapsed_time": "1:34:22", "remaining_time": "5:34:25", "throughput": 1491.21, "total_tokens": 8443328} {"current_steps": 40015, "total_steps": 181800, "loss": 0.034, "lr": 4.783512077337454e-05, "epoch": 4.402090209020902, "percentage": 22.01, "elapsed_time": "1:34:22", "remaining_time": "5:34:24", "throughput": 1491.2, "total_tokens": 8444320} {"current_steps": 40020, "total_steps": 181800, "loss": 0.0896, "lr": 4.7834143714939326e-05, "epoch": 4.402640264026402, "percentage": 22.01, "elapsed_time": "1:34:23", "remaining_time": "5:34:24", "throughput": 1491.2, "total_tokens": 8445344} {"current_steps": 40025, "total_steps": 181800, "loss": 0.0281, "lr": 4.7833166446052756e-05, "epoch": 4.4031903190319035, "percentage": 22.02, "elapsed_time": "1:34:24", "remaining_time": "5:34:23", "throughput": 1491.2, "total_tokens": 8446368} {"current_steps": 40030, "total_steps": 181800, "loss": 0.1027, "lr": 4.783218896672386e-05, "epoch": 4.403740374037404, "percentage": 22.02, "elapsed_time": "1:34:24", "remaining_time": "5:34:22", "throughput": 1491.21, "total_tokens": 8447456} {"current_steps": 40035, "total_steps": 181800, "loss": 0.0596, "lr": 4.783121127696162e-05, "epoch": 4.404290429042904, "percentage": 22.02, "elapsed_time": "1:34:25", "remaining_time": "5:34:21", "throughput": 1491.21, "total_tokens": 8448480} {"current_steps": 40040, "total_steps": 181800, "loss": 0.0135, "lr": 4.7830233376775066e-05, "epoch": 4.404840484048405, "percentage": 22.02, "elapsed_time": "1:34:26", "remaining_time": "5:34:20", "throughput": 1491.22, "total_tokens": 8449568} {"current_steps": 40045, "total_steps": 181800, "loss": 0.0515, "lr": 4.782925526617321e-05, "epoch": 4.405390539053905, "percentage": 22.03, "elapsed_time": "1:34:26", "remaining_time": "5:34:20", "throughput": 1491.21, "total_tokens": 8450528} {"current_steps": 40050, "total_steps": 181800, "loss": 0.0579, "lr": 4.782827694516506e-05, "epoch": 4.405940594059406, "percentage": 22.03, "elapsed_time": "1:34:27", "remaining_time": "5:34:19", "throughput": 1491.21, "total_tokens": 8451552} {"current_steps": 40055, "total_steps": 181800, "loss": 0.0382, "lr": 4.782729841375963e-05, "epoch": 4.4064906490649065, "percentage": 22.03, "elapsed_time": "1:34:28", "remaining_time": "5:34:18", "throughput": 1491.21, "total_tokens": 8452608} {"current_steps": 40060, "total_steps": 181800, "loss": 0.0993, "lr": 4.782631967196596e-05, "epoch": 4.407040704070407, "percentage": 22.04, "elapsed_time": "1:34:28", "remaining_time": "5:34:17", "throughput": 1491.21, "total_tokens": 8453632} {"current_steps": 40065, "total_steps": 181800, "loss": 0.0546, "lr": 4.782534071979304e-05, "epoch": 4.407590759075908, "percentage": 22.04, "elapsed_time": "1:34:29", "remaining_time": "5:34:17", "throughput": 1491.22, "total_tokens": 8454688} {"current_steps": 40070, "total_steps": 181800, "loss": 0.0995, "lr": 4.782436155724992e-05, "epoch": 4.408140814081408, "percentage": 22.04, "elapsed_time": "1:34:30", "remaining_time": "5:34:16", "throughput": 1491.2, "total_tokens": 8455648} {"current_steps": 40075, "total_steps": 181800, "loss": 0.0742, "lr": 4.78233821843456e-05, "epoch": 4.408690869086909, "percentage": 22.04, "elapsed_time": "1:34:31", "remaining_time": "5:34:15", "throughput": 1491.2, "total_tokens": 8456672} {"current_steps": 40080, "total_steps": 181800, "loss": 0.1552, "lr": 4.782240260108912e-05, "epoch": 4.409240924092409, "percentage": 22.05, "elapsed_time": "1:34:31", "remaining_time": "5:34:14", "throughput": 1491.21, "total_tokens": 8457728} {"current_steps": 40085, "total_steps": 181800, "loss": 0.0203, "lr": 4.7821422807489515e-05, "epoch": 4.4097909790979095, "percentage": 22.05, "elapsed_time": "1:34:32", "remaining_time": "5:34:14", "throughput": 1491.21, "total_tokens": 8458784} {"current_steps": 40090, "total_steps": 181800, "loss": 0.0977, "lr": 4.78204428035558e-05, "epoch": 4.410341034103411, "percentage": 22.05, "elapsed_time": "1:34:33", "remaining_time": "5:34:13", "throughput": 1491.22, "total_tokens": 8459840} {"current_steps": 40095, "total_steps": 181800, "loss": 0.0424, "lr": 4.781946258929702e-05, "epoch": 4.410891089108911, "percentage": 22.05, "elapsed_time": "1:34:33", "remaining_time": "5:34:12", "throughput": 1491.22, "total_tokens": 8460896} {"current_steps": 40100, "total_steps": 181800, "loss": 0.0752, "lr": 4.7818482164722186e-05, "epoch": 4.411441144114411, "percentage": 22.06, "elapsed_time": "1:34:34", "remaining_time": "5:34:11", "throughput": 1491.22, "total_tokens": 8461888} {"current_steps": 40105, "total_steps": 181800, "loss": 0.0597, "lr": 4.781750152984037e-05, "epoch": 4.411991199119912, "percentage": 22.06, "elapsed_time": "1:34:35", "remaining_time": "5:34:10", "throughput": 1491.22, "total_tokens": 8462944} {"current_steps": 40110, "total_steps": 181800, "loss": 0.1008, "lr": 4.781652068466058e-05, "epoch": 4.412541254125412, "percentage": 22.06, "elapsed_time": "1:34:35", "remaining_time": "5:34:10", "throughput": 1491.23, "total_tokens": 8464032} {"current_steps": 40115, "total_steps": 181800, "loss": 0.0993, "lr": 4.781553962919187e-05, "epoch": 4.413091309130913, "percentage": 22.07, "elapsed_time": "1:34:36", "remaining_time": "5:34:09", "throughput": 1491.24, "total_tokens": 8465088} {"current_steps": 40120, "total_steps": 181800, "loss": 0.0755, "lr": 4.7814558363443284e-05, "epoch": 4.413641364136414, "percentage": 22.07, "elapsed_time": "1:34:37", "remaining_time": "5:34:08", "throughput": 1491.24, "total_tokens": 8466144} {"current_steps": 40125, "total_steps": 181800, "loss": 0.0572, "lr": 4.781357688742386e-05, "epoch": 4.414191419141914, "percentage": 22.07, "elapsed_time": "1:34:37", "remaining_time": "5:34:07", "throughput": 1491.25, "total_tokens": 8467200} {"current_steps": 40130, "total_steps": 181800, "loss": 0.0269, "lr": 4.781259520114264e-05, "epoch": 4.414741474147415, "percentage": 22.07, "elapsed_time": "1:34:38", "remaining_time": "5:34:07", "throughput": 1491.25, "total_tokens": 8468256} {"current_steps": 40135, "total_steps": 181800, "loss": 0.0357, "lr": 4.7811613304608684e-05, "epoch": 4.415291529152915, "percentage": 22.08, "elapsed_time": "1:34:39", "remaining_time": "5:34:06", "throughput": 1491.25, "total_tokens": 8469248} {"current_steps": 40140, "total_steps": 181800, "loss": 0.047, "lr": 4.781063119783103e-05, "epoch": 4.415841584158416, "percentage": 22.08, "elapsed_time": "1:34:39", "remaining_time": "5:34:05", "throughput": 1491.25, "total_tokens": 8470304} {"current_steps": 40145, "total_steps": 181800, "loss": 0.0356, "lr": 4.780964888081872e-05, "epoch": 4.416391639163916, "percentage": 22.08, "elapsed_time": "1:34:40", "remaining_time": "5:34:04", "throughput": 1491.27, "total_tokens": 8471424} {"current_steps": 40150, "total_steps": 181800, "loss": 0.0179, "lr": 4.780866635358084e-05, "epoch": 4.416941694169417, "percentage": 22.08, "elapsed_time": "1:34:41", "remaining_time": "5:34:04", "throughput": 1491.28, "total_tokens": 8472512} {"current_steps": 40155, "total_steps": 181800, "loss": 0.0248, "lr": 4.7807683616126426e-05, "epoch": 4.417491749174918, "percentage": 22.09, "elapsed_time": "1:34:42", "remaining_time": "5:34:03", "throughput": 1491.29, "total_tokens": 8473600} {"current_steps": 40160, "total_steps": 181800, "loss": 0.0187, "lr": 4.7806700668464535e-05, "epoch": 4.418041804180418, "percentage": 22.09, "elapsed_time": "1:34:42", "remaining_time": "5:34:02", "throughput": 1491.29, "total_tokens": 8474656} {"current_steps": 40165, "total_steps": 181800, "loss": 0.0533, "lr": 4.780571751060422e-05, "epoch": 4.418591859185918, "percentage": 22.09, "elapsed_time": "1:34:43", "remaining_time": "5:34:01", "throughput": 1491.31, "total_tokens": 8475776} {"current_steps": 40170, "total_steps": 181800, "loss": 0.0289, "lr": 4.7804734142554554e-05, "epoch": 4.419141914191419, "percentage": 22.1, "elapsed_time": "1:34:44", "remaining_time": "5:34:00", "throughput": 1491.32, "total_tokens": 8476832} {"current_steps": 40175, "total_steps": 181800, "loss": 0.0673, "lr": 4.78037505643246e-05, "epoch": 4.419691969196919, "percentage": 22.1, "elapsed_time": "1:34:44", "remaining_time": "5:34:00", "throughput": 1491.33, "total_tokens": 8477920} {"current_steps": 40180, "total_steps": 181800, "loss": 0.0196, "lr": 4.7802766775923416e-05, "epoch": 4.4202420242024205, "percentage": 22.1, "elapsed_time": "1:34:45", "remaining_time": "5:33:59", "throughput": 1491.35, "total_tokens": 8479072} {"current_steps": 40185, "total_steps": 181800, "loss": 0.0762, "lr": 4.7801782777360074e-05, "epoch": 4.420792079207921, "percentage": 22.1, "elapsed_time": "1:34:46", "remaining_time": "5:33:58", "throughput": 1491.36, "total_tokens": 8480160} {"current_steps": 40190, "total_steps": 181800, "loss": 0.0358, "lr": 4.7800798568643635e-05, "epoch": 4.421342134213421, "percentage": 22.11, "elapsed_time": "1:34:46", "remaining_time": "5:33:57", "throughput": 1491.35, "total_tokens": 8481152} {"current_steps": 40195, "total_steps": 181800, "loss": 0.0274, "lr": 4.779981414978318e-05, "epoch": 4.421892189218922, "percentage": 22.11, "elapsed_time": "1:34:47", "remaining_time": "5:33:57", "throughput": 1491.34, "total_tokens": 8482112} {"current_steps": 40200, "total_steps": 181800, "loss": 0.0281, "lr": 4.779882952078778e-05, "epoch": 4.422442244224422, "percentage": 22.11, "elapsed_time": "1:34:48", "remaining_time": "5:33:56", "throughput": 1491.35, "total_tokens": 8483200} {"current_steps": 40205, "total_steps": 181800, "loss": 0.104, "lr": 4.779784468166651e-05, "epoch": 4.422992299229923, "percentage": 22.11, "elapsed_time": "1:34:48", "remaining_time": "5:33:55", "throughput": 1491.36, "total_tokens": 8484288} {"current_steps": 40210, "total_steps": 181800, "loss": 0.1158, "lr": 4.779685963242844e-05, "epoch": 4.4235423542354235, "percentage": 22.12, "elapsed_time": "1:34:49", "remaining_time": "5:33:54", "throughput": 1491.36, "total_tokens": 8485344} {"current_steps": 40215, "total_steps": 181800, "loss": 0.0392, "lr": 4.779587437308266e-05, "epoch": 4.424092409240924, "percentage": 22.12, "elapsed_time": "1:34:50", "remaining_time": "5:33:54", "throughput": 1491.36, "total_tokens": 8486368} {"current_steps": 40220, "total_steps": 181800, "loss": 0.1385, "lr": 4.779488890363824e-05, "epoch": 4.424642464246425, "percentage": 22.12, "elapsed_time": "1:34:51", "remaining_time": "5:33:53", "throughput": 1491.37, "total_tokens": 8487424} {"current_steps": 40225, "total_steps": 181800, "loss": 0.0164, "lr": 4.779390322410427e-05, "epoch": 4.425192519251925, "percentage": 22.13, "elapsed_time": "1:34:51", "remaining_time": "5:33:52", "throughput": 1491.37, "total_tokens": 8488448} {"current_steps": 40230, "total_steps": 181800, "loss": 0.1146, "lr": 4.779291733448983e-05, "epoch": 4.425742574257426, "percentage": 22.13, "elapsed_time": "1:34:52", "remaining_time": "5:33:51", "throughput": 1491.36, "total_tokens": 8489440} {"current_steps": 40235, "total_steps": 181800, "loss": 0.0649, "lr": 4.779193123480401e-05, "epoch": 4.426292629262926, "percentage": 22.13, "elapsed_time": "1:34:53", "remaining_time": "5:33:50", "throughput": 1491.36, "total_tokens": 8490496} {"current_steps": 40240, "total_steps": 181800, "loss": 0.0363, "lr": 4.7790944925055894e-05, "epoch": 4.4268426842684265, "percentage": 22.13, "elapsed_time": "1:34:53", "remaining_time": "5:33:50", "throughput": 1491.37, "total_tokens": 8491552} {"current_steps": 40245, "total_steps": 181800, "loss": 0.0618, "lr": 4.778995840525458e-05, "epoch": 4.427392739273928, "percentage": 22.14, "elapsed_time": "1:34:54", "remaining_time": "5:33:49", "throughput": 1491.38, "total_tokens": 8492640} {"current_steps": 40250, "total_steps": 181800, "loss": 0.0211, "lr": 4.7788971675409144e-05, "epoch": 4.427942794279428, "percentage": 22.14, "elapsed_time": "1:34:55", "remaining_time": "5:33:48", "throughput": 1491.38, "total_tokens": 8493664} {"current_steps": 40255, "total_steps": 181800, "loss": 0.1119, "lr": 4.77879847355287e-05, "epoch": 4.428492849284929, "percentage": 22.14, "elapsed_time": "1:34:55", "remaining_time": "5:33:47", "throughput": 1491.38, "total_tokens": 8494688} {"current_steps": 40260, "total_steps": 181800, "loss": 0.1371, "lr": 4.778699758562233e-05, "epoch": 4.429042904290429, "percentage": 22.15, "elapsed_time": "1:34:56", "remaining_time": "5:33:47", "throughput": 1491.37, "total_tokens": 8495680} {"current_steps": 40265, "total_steps": 181800, "loss": 0.0471, "lr": 4.778601022569914e-05, "epoch": 4.429592959295929, "percentage": 22.15, "elapsed_time": "1:34:57", "remaining_time": "5:33:46", "throughput": 1491.38, "total_tokens": 8496736} {"current_steps": 40270, "total_steps": 181800, "loss": 0.1001, "lr": 4.778502265576823e-05, "epoch": 4.43014301430143, "percentage": 22.15, "elapsed_time": "1:34:57", "remaining_time": "5:33:45", "throughput": 1491.39, "total_tokens": 8497824} {"current_steps": 40275, "total_steps": 181800, "loss": 0.0146, "lr": 4.7784034875838696e-05, "epoch": 4.430693069306931, "percentage": 22.15, "elapsed_time": "1:34:58", "remaining_time": "5:33:44", "throughput": 1491.39, "total_tokens": 8498880} {"current_steps": 40280, "total_steps": 181800, "loss": 0.0654, "lr": 4.7783046885919646e-05, "epoch": 4.431243124312431, "percentage": 22.16, "elapsed_time": "1:34:59", "remaining_time": "5:33:43", "throughput": 1491.4, "total_tokens": 8499936} {"current_steps": 40285, "total_steps": 181800, "loss": 0.0531, "lr": 4.7782058686020186e-05, "epoch": 4.431793179317932, "percentage": 22.16, "elapsed_time": "1:35:00", "remaining_time": "5:33:43", "throughput": 1491.41, "total_tokens": 8501024} {"current_steps": 40290, "total_steps": 181800, "loss": 0.0153, "lr": 4.778107027614942e-05, "epoch": 4.432343234323432, "percentage": 22.16, "elapsed_time": "1:35:00", "remaining_time": "5:33:42", "throughput": 1491.41, "total_tokens": 8502080} {"current_steps": 40295, "total_steps": 181800, "loss": 0.0705, "lr": 4.778008165631647e-05, "epoch": 4.432893289328933, "percentage": 22.16, "elapsed_time": "1:35:01", "remaining_time": "5:33:41", "throughput": 1491.42, "total_tokens": 8503168} {"current_steps": 40300, "total_steps": 181800, "loss": 0.0152, "lr": 4.777909282653042e-05, "epoch": 4.433443344334433, "percentage": 22.17, "elapsed_time": "1:35:02", "remaining_time": "5:33:40", "throughput": 1491.42, "total_tokens": 8504192} {"current_steps": 40305, "total_steps": 181800, "loss": 0.0888, "lr": 4.777810378680042e-05, "epoch": 4.433993399339934, "percentage": 22.17, "elapsed_time": "1:35:02", "remaining_time": "5:33:40", "throughput": 1491.44, "total_tokens": 8505312} {"current_steps": 40310, "total_steps": 181800, "loss": 0.0551, "lr": 4.777711453713557e-05, "epoch": 4.434543454345435, "percentage": 22.17, "elapsed_time": "1:35:03", "remaining_time": "5:33:39", "throughput": 1491.43, "total_tokens": 8506304} {"current_steps": 40315, "total_steps": 181800, "loss": 0.0094, "lr": 4.777612507754497e-05, "epoch": 4.435093509350935, "percentage": 22.18, "elapsed_time": "1:35:04", "remaining_time": "5:33:38", "throughput": 1491.43, "total_tokens": 8507360} {"current_steps": 40320, "total_steps": 181800, "loss": 0.0349, "lr": 4.7775135408037765e-05, "epoch": 4.435643564356436, "percentage": 22.18, "elapsed_time": "1:35:04", "remaining_time": "5:33:37", "throughput": 1491.44, "total_tokens": 8508448} {"current_steps": 40325, "total_steps": 181800, "loss": 0.0763, "lr": 4.777414552862306e-05, "epoch": 4.436193619361936, "percentage": 22.18, "elapsed_time": "1:35:05", "remaining_time": "5:33:37", "throughput": 1491.45, "total_tokens": 8509504} {"current_steps": 40330, "total_steps": 181800, "loss": 0.1333, "lr": 4.777315543930998e-05, "epoch": 4.436743674367436, "percentage": 22.18, "elapsed_time": "1:35:06", "remaining_time": "5:33:36", "throughput": 1491.45, "total_tokens": 8510528} {"current_steps": 40335, "total_steps": 181800, "loss": 0.0213, "lr": 4.777216514010766e-05, "epoch": 4.4372937293729375, "percentage": 22.19, "elapsed_time": "1:35:06", "remaining_time": "5:33:35", "throughput": 1491.45, "total_tokens": 8511552} {"current_steps": 40340, "total_steps": 181800, "loss": 0.016, "lr": 4.777117463102522e-05, "epoch": 4.437843784378438, "percentage": 22.19, "elapsed_time": "1:35:07", "remaining_time": "5:33:34", "throughput": 1491.46, "total_tokens": 8512640} {"current_steps": 40345, "total_steps": 181800, "loss": 0.0124, "lr": 4.777018391207179e-05, "epoch": 4.438393839383938, "percentage": 22.19, "elapsed_time": "1:35:08", "remaining_time": "5:33:33", "throughput": 1491.46, "total_tokens": 8513696} {"current_steps": 40350, "total_steps": 181800, "loss": 0.0349, "lr": 4.77691929832565e-05, "epoch": 4.438943894389439, "percentage": 22.19, "elapsed_time": "1:35:08", "remaining_time": "5:33:33", "throughput": 1491.48, "total_tokens": 8514816} {"current_steps": 40355, "total_steps": 181800, "loss": 0.0295, "lr": 4.776820184458848e-05, "epoch": 4.439493949394939, "percentage": 22.2, "elapsed_time": "1:35:09", "remaining_time": "5:33:32", "throughput": 1491.48, "total_tokens": 8515840} {"current_steps": 40360, "total_steps": 181800, "loss": 0.0359, "lr": 4.776721049607687e-05, "epoch": 4.44004400440044, "percentage": 22.2, "elapsed_time": "1:35:10", "remaining_time": "5:33:31", "throughput": 1491.48, "total_tokens": 8516864} {"current_steps": 40365, "total_steps": 181800, "loss": 0.1688, "lr": 4.7766218937730816e-05, "epoch": 4.4405940594059405, "percentage": 22.2, "elapsed_time": "1:35:11", "remaining_time": "5:33:30", "throughput": 1491.48, "total_tokens": 8517920} {"current_steps": 40370, "total_steps": 181800, "loss": 0.0556, "lr": 4.7765227169559444e-05, "epoch": 4.441144114411441, "percentage": 22.21, "elapsed_time": "1:35:11", "remaining_time": "5:33:30", "throughput": 1491.49, "total_tokens": 8519008} {"current_steps": 40375, "total_steps": 181800, "loss": 0.0241, "lr": 4.776423519157189e-05, "epoch": 4.441694169416942, "percentage": 22.21, "elapsed_time": "1:35:12", "remaining_time": "5:33:29", "throughput": 1491.49, "total_tokens": 8520032} {"current_steps": 40380, "total_steps": 181800, "loss": 0.0279, "lr": 4.77632430037773e-05, "epoch": 4.442244224422442, "percentage": 22.21, "elapsed_time": "1:35:13", "remaining_time": "5:33:28", "throughput": 1491.49, "total_tokens": 8521056} {"current_steps": 40385, "total_steps": 181800, "loss": 0.0411, "lr": 4.776225060618483e-05, "epoch": 4.442794279427943, "percentage": 22.21, "elapsed_time": "1:35:13", "remaining_time": "5:33:27", "throughput": 1491.49, "total_tokens": 8522080} {"current_steps": 40390, "total_steps": 181800, "loss": 0.0114, "lr": 4.776125799880362e-05, "epoch": 4.443344334433443, "percentage": 22.22, "elapsed_time": "1:35:14", "remaining_time": "5:33:27", "throughput": 1491.51, "total_tokens": 8523200} {"current_steps": 40395, "total_steps": 181800, "loss": 0.0759, "lr": 4.7760265181642816e-05, "epoch": 4.4438943894389435, "percentage": 22.22, "elapsed_time": "1:35:15", "remaining_time": "5:33:26", "throughput": 1491.51, "total_tokens": 8524224} {"current_steps": 40400, "total_steps": 181800, "loss": 0.015, "lr": 4.775927215471156e-05, "epoch": 4.444444444444445, "percentage": 22.22, "elapsed_time": "1:35:15", "remaining_time": "5:33:25", "throughput": 1491.52, "total_tokens": 8525312} {"current_steps": 40405, "total_steps": 181800, "loss": 0.0761, "lr": 4.775827891801903e-05, "epoch": 4.444994499449945, "percentage": 22.22, "elapsed_time": "1:35:16", "remaining_time": "5:33:24", "throughput": 1491.52, "total_tokens": 8526368} {"current_steps": 40410, "total_steps": 181800, "loss": 0.0314, "lr": 4.7757285471574355e-05, "epoch": 4.445544554455446, "percentage": 22.23, "elapsed_time": "1:35:17", "remaining_time": "5:33:24", "throughput": 1491.54, "total_tokens": 8527488} {"current_steps": 40415, "total_steps": 181800, "loss": 0.0766, "lr": 4.77562918153867e-05, "epoch": 4.446094609460946, "percentage": 22.23, "elapsed_time": "1:35:17", "remaining_time": "5:33:23", "throughput": 1491.54, "total_tokens": 8528512} {"current_steps": 40420, "total_steps": 181800, "loss": 0.0374, "lr": 4.7755297949465216e-05, "epoch": 4.446644664466446, "percentage": 22.23, "elapsed_time": "1:35:18", "remaining_time": "5:33:22", "throughput": 1491.54, "total_tokens": 8529536} {"current_steps": 40425, "total_steps": 181800, "loss": 0.0512, "lr": 4.7754303873819076e-05, "epoch": 4.447194719471947, "percentage": 22.24, "elapsed_time": "1:35:19", "remaining_time": "5:33:21", "throughput": 1491.54, "total_tokens": 8530592} {"current_steps": 40430, "total_steps": 181800, "loss": 0.0327, "lr": 4.775330958845744e-05, "epoch": 4.447744774477448, "percentage": 22.24, "elapsed_time": "1:35:19", "remaining_time": "5:33:20", "throughput": 1491.55, "total_tokens": 8531648} {"current_steps": 40435, "total_steps": 181800, "loss": 0.1297, "lr": 4.775231509338946e-05, "epoch": 4.448294829482949, "percentage": 22.24, "elapsed_time": "1:35:20", "remaining_time": "5:33:20", "throughput": 1491.55, "total_tokens": 8532672} {"current_steps": 40440, "total_steps": 181800, "loss": 0.0753, "lr": 4.775132038862431e-05, "epoch": 4.448844884488449, "percentage": 22.24, "elapsed_time": "1:35:21", "remaining_time": "5:33:19", "throughput": 1491.55, "total_tokens": 8533728} {"current_steps": 40445, "total_steps": 181800, "loss": 0.062, "lr": 4.775032547417116e-05, "epoch": 4.449394939493949, "percentage": 22.25, "elapsed_time": "1:35:22", "remaining_time": "5:33:18", "throughput": 1491.55, "total_tokens": 8534752} {"current_steps": 40450, "total_steps": 181800, "loss": 0.076, "lr": 4.774933035003918e-05, "epoch": 4.44994499449945, "percentage": 22.25, "elapsed_time": "1:35:22", "remaining_time": "5:33:17", "throughput": 1491.55, "total_tokens": 8535776} {"current_steps": 40455, "total_steps": 181800, "loss": 0.0258, "lr": 4.7748335016237534e-05, "epoch": 4.4504950495049505, "percentage": 22.25, "elapsed_time": "1:35:23", "remaining_time": "5:33:17", "throughput": 1491.56, "total_tokens": 8536832} {"current_steps": 40460, "total_steps": 181800, "loss": 0.1189, "lr": 4.77473394727754e-05, "epoch": 4.451045104510451, "percentage": 22.26, "elapsed_time": "1:35:24", "remaining_time": "5:33:16", "throughput": 1491.56, "total_tokens": 8537888} {"current_steps": 40465, "total_steps": 181800, "loss": 0.0179, "lr": 4.774634371966196e-05, "epoch": 4.451595159515952, "percentage": 22.26, "elapsed_time": "1:35:24", "remaining_time": "5:33:15", "throughput": 1491.57, "total_tokens": 8538976} {"current_steps": 40470, "total_steps": 181800, "loss": 0.0494, "lr": 4.774534775690637e-05, "epoch": 4.452145214521452, "percentage": 22.26, "elapsed_time": "1:35:25", "remaining_time": "5:33:14", "throughput": 1491.59, "total_tokens": 8540128} {"current_steps": 40475, "total_steps": 181800, "loss": 0.0596, "lr": 4.7744351584517836e-05, "epoch": 4.452695269526953, "percentage": 22.26, "elapsed_time": "1:35:26", "remaining_time": "5:33:13", "throughput": 1491.6, "total_tokens": 8541216} {"current_steps": 40480, "total_steps": 181800, "loss": 0.1079, "lr": 4.7743355202505525e-05, "epoch": 4.453245324532453, "percentage": 22.27, "elapsed_time": "1:35:26", "remaining_time": "5:33:13", "throughput": 1491.61, "total_tokens": 8542304} {"current_steps": 40485, "total_steps": 181800, "loss": 0.0743, "lr": 4.774235861087862e-05, "epoch": 4.4537953795379535, "percentage": 22.27, "elapsed_time": "1:35:27", "remaining_time": "5:33:12", "throughput": 1491.62, "total_tokens": 8543360} {"current_steps": 40490, "total_steps": 181800, "loss": 0.1276, "lr": 4.774136180964631e-05, "epoch": 4.4543454345434546, "percentage": 22.27, "elapsed_time": "1:35:28", "remaining_time": "5:33:11", "throughput": 1491.63, "total_tokens": 8544480} {"current_steps": 40495, "total_steps": 181800, "loss": 0.0117, "lr": 4.774036479881778e-05, "epoch": 4.454895489548955, "percentage": 22.27, "elapsed_time": "1:35:28", "remaining_time": "5:33:10", "throughput": 1491.64, "total_tokens": 8545536} {"current_steps": 40500, "total_steps": 181800, "loss": 0.042, "lr": 4.7739367578402224e-05, "epoch": 4.455445544554456, "percentage": 22.28, "elapsed_time": "1:35:29", "remaining_time": "5:33:10", "throughput": 1491.66, "total_tokens": 8546688} {"current_steps": 40505, "total_steps": 181800, "loss": 0.046, "lr": 4.773837014840882e-05, "epoch": 4.455995599559956, "percentage": 22.28, "elapsed_time": "1:35:30", "remaining_time": "5:33:09", "throughput": 1491.66, "total_tokens": 8547744} {"current_steps": 40510, "total_steps": 181800, "loss": 0.0683, "lr": 4.773737250884678e-05, "epoch": 4.456545654565456, "percentage": 22.28, "elapsed_time": "1:35:31", "remaining_time": "5:33:08", "throughput": 1491.65, "total_tokens": 8548736} {"current_steps": 40515, "total_steps": 181800, "loss": 0.0127, "lr": 4.773637465972528e-05, "epoch": 4.457095709570957, "percentage": 22.29, "elapsed_time": "1:35:31", "remaining_time": "5:33:07", "throughput": 1491.66, "total_tokens": 8549792} {"current_steps": 40520, "total_steps": 181800, "loss": 0.0265, "lr": 4.773537660105353e-05, "epoch": 4.457645764576458, "percentage": 22.29, "elapsed_time": "1:35:32", "remaining_time": "5:33:07", "throughput": 1491.65, "total_tokens": 8550784} {"current_steps": 40525, "total_steps": 181800, "loss": 0.0686, "lr": 4.773437833284071e-05, "epoch": 4.458195819581958, "percentage": 22.29, "elapsed_time": "1:35:33", "remaining_time": "5:33:06", "throughput": 1491.66, "total_tokens": 8551872} {"current_steps": 40530, "total_steps": 181800, "loss": 0.0701, "lr": 4.773337985509605e-05, "epoch": 4.458745874587459, "percentage": 22.29, "elapsed_time": "1:35:33", "remaining_time": "5:33:05", "throughput": 1491.65, "total_tokens": 8552864} {"current_steps": 40535, "total_steps": 181800, "loss": 0.0334, "lr": 4.7732381167828735e-05, "epoch": 4.459295929592959, "percentage": 22.3, "elapsed_time": "1:35:34", "remaining_time": "5:33:04", "throughput": 1491.67, "total_tokens": 8553984} {"current_steps": 40540, "total_steps": 181800, "loss": 0.0277, "lr": 4.773138227104796e-05, "epoch": 4.45984598459846, "percentage": 22.3, "elapsed_time": "1:35:35", "remaining_time": "5:33:04", "throughput": 1491.67, "total_tokens": 8555040} {"current_steps": 40545, "total_steps": 181800, "loss": 0.0335, "lr": 4.773038316476295e-05, "epoch": 4.46039603960396, "percentage": 22.3, "elapsed_time": "1:35:35", "remaining_time": "5:33:03", "throughput": 1491.68, "total_tokens": 8556096} {"current_steps": 40550, "total_steps": 181800, "loss": 0.1117, "lr": 4.77293838489829e-05, "epoch": 4.460946094609461, "percentage": 22.3, "elapsed_time": "1:35:36", "remaining_time": "5:33:02", "throughput": 1491.69, "total_tokens": 8557152} {"current_steps": 40555, "total_steps": 181800, "loss": 0.024, "lr": 4.772838432371703e-05, "epoch": 4.461496149614962, "percentage": 22.31, "elapsed_time": "1:35:37", "remaining_time": "5:33:01", "throughput": 1491.7, "total_tokens": 8558240} {"current_steps": 40560, "total_steps": 181800, "loss": 0.0673, "lr": 4.7727384588974544e-05, "epoch": 4.462046204620462, "percentage": 22.31, "elapsed_time": "1:35:37", "remaining_time": "5:33:00", "throughput": 1491.7, "total_tokens": 8559296} {"current_steps": 40565, "total_steps": 181800, "loss": 0.0217, "lr": 4.7726384644764665e-05, "epoch": 4.462596259625963, "percentage": 22.31, "elapsed_time": "1:35:38", "remaining_time": "5:33:00", "throughput": 1491.71, "total_tokens": 8560384} {"current_steps": 40570, "total_steps": 181800, "loss": 0.1419, "lr": 4.77253844910966e-05, "epoch": 4.463146314631463, "percentage": 22.32, "elapsed_time": "1:35:39", "remaining_time": "5:32:59", "throughput": 1491.72, "total_tokens": 8561472} {"current_steps": 40575, "total_steps": 181800, "loss": 0.0439, "lr": 4.772438412797958e-05, "epoch": 4.463696369636963, "percentage": 22.32, "elapsed_time": "1:35:40", "remaining_time": "5:32:58", "throughput": 1491.72, "total_tokens": 8562528} {"current_steps": 40580, "total_steps": 181800, "loss": 0.035, "lr": 4.7723383555422805e-05, "epoch": 4.4642464246424645, "percentage": 22.32, "elapsed_time": "1:35:40", "remaining_time": "5:32:57", "throughput": 1491.72, "total_tokens": 8563552} {"current_steps": 40585, "total_steps": 181800, "loss": 0.0589, "lr": 4.7722382773435515e-05, "epoch": 4.464796479647965, "percentage": 22.32, "elapsed_time": "1:35:41", "remaining_time": "5:32:57", "throughput": 1491.73, "total_tokens": 8564608} {"current_steps": 40590, "total_steps": 181800, "loss": 0.0575, "lr": 4.772138178202692e-05, "epoch": 4.465346534653466, "percentage": 22.33, "elapsed_time": "1:35:42", "remaining_time": "5:32:56", "throughput": 1491.73, "total_tokens": 8565664} {"current_steps": 40595, "total_steps": 181800, "loss": 0.0406, "lr": 4.7720380581206256e-05, "epoch": 4.465896589658966, "percentage": 22.33, "elapsed_time": "1:35:42", "remaining_time": "5:32:55", "throughput": 1491.73, "total_tokens": 8566688} {"current_steps": 40600, "total_steps": 181800, "loss": 0.0436, "lr": 4.771937917098274e-05, "epoch": 4.466446644664466, "percentage": 22.33, "elapsed_time": "1:35:43", "remaining_time": "5:32:54", "throughput": 1491.73, "total_tokens": 8567744} {"current_steps": 40605, "total_steps": 181800, "loss": 0.055, "lr": 4.771837755136561e-05, "epoch": 4.466996699669967, "percentage": 22.33, "elapsed_time": "1:35:44", "remaining_time": "5:32:54", "throughput": 1491.72, "total_tokens": 8568704} {"current_steps": 40610, "total_steps": 181800, "loss": 0.0461, "lr": 4.77173757223641e-05, "epoch": 4.4675467546754675, "percentage": 22.34, "elapsed_time": "1:35:44", "remaining_time": "5:32:53", "throughput": 1491.72, "total_tokens": 8569696} {"current_steps": 40615, "total_steps": 181800, "loss": 0.159, "lr": 4.7716373683987435e-05, "epoch": 4.468096809680969, "percentage": 22.34, "elapsed_time": "1:35:45", "remaining_time": "5:32:52", "throughput": 1491.73, "total_tokens": 8570784} {"current_steps": 40620, "total_steps": 181800, "loss": 0.0337, "lr": 4.771537143624486e-05, "epoch": 4.468646864686469, "percentage": 22.34, "elapsed_time": "1:35:46", "remaining_time": "5:32:51", "throughput": 1491.73, "total_tokens": 8571808} {"current_steps": 40625, "total_steps": 181800, "loss": 0.0856, "lr": 4.771436897914561e-05, "epoch": 4.469196919691969, "percentage": 22.35, "elapsed_time": "1:35:46", "remaining_time": "5:32:50", "throughput": 1491.73, "total_tokens": 8572864} {"current_steps": 40630, "total_steps": 181800, "loss": 0.0765, "lr": 4.7713366312698906e-05, "epoch": 4.46974697469747, "percentage": 22.35, "elapsed_time": "1:35:47", "remaining_time": "5:32:50", "throughput": 1491.74, "total_tokens": 8573952} {"current_steps": 40635, "total_steps": 181800, "loss": 0.0267, "lr": 4.771236343691401e-05, "epoch": 4.47029702970297, "percentage": 22.35, "elapsed_time": "1:35:48", "remaining_time": "5:32:49", "throughput": 1491.74, "total_tokens": 8574976} {"current_steps": 40640, "total_steps": 181800, "loss": 0.0083, "lr": 4.771136035180016e-05, "epoch": 4.4708470847084705, "percentage": 22.35, "elapsed_time": "1:35:48", "remaining_time": "5:32:48", "throughput": 1491.74, "total_tokens": 8576000} {"current_steps": 40645, "total_steps": 181800, "loss": 0.1466, "lr": 4.77103570573666e-05, "epoch": 4.471397139713972, "percentage": 22.36, "elapsed_time": "1:35:49", "remaining_time": "5:32:47", "throughput": 1491.74, "total_tokens": 8577056} {"current_steps": 40650, "total_steps": 181800, "loss": 0.0152, "lr": 4.770935355362257e-05, "epoch": 4.471947194719472, "percentage": 22.36, "elapsed_time": "1:35:50", "remaining_time": "5:32:47", "throughput": 1491.75, "total_tokens": 8578112} {"current_steps": 40655, "total_steps": 181800, "loss": 0.1367, "lr": 4.7708349840577336e-05, "epoch": 4.472497249724973, "percentage": 22.36, "elapsed_time": "1:35:51", "remaining_time": "5:32:46", "throughput": 1491.75, "total_tokens": 8579136} {"current_steps": 40660, "total_steps": 181800, "loss": 0.1309, "lr": 4.7707345918240134e-05, "epoch": 4.473047304730473, "percentage": 22.37, "elapsed_time": "1:35:51", "remaining_time": "5:32:45", "throughput": 1491.76, "total_tokens": 8580224} {"current_steps": 40665, "total_steps": 181800, "loss": 0.1418, "lr": 4.770634178662022e-05, "epoch": 4.473597359735973, "percentage": 22.37, "elapsed_time": "1:35:52", "remaining_time": "5:32:44", "throughput": 1491.76, "total_tokens": 8581280} {"current_steps": 40670, "total_steps": 181800, "loss": 0.0668, "lr": 4.770533744572685e-05, "epoch": 4.474147414741474, "percentage": 22.37, "elapsed_time": "1:35:53", "remaining_time": "5:32:44", "throughput": 1491.78, "total_tokens": 8582432} {"current_steps": 40675, "total_steps": 181800, "loss": 0.1523, "lr": 4.7704332895569274e-05, "epoch": 4.474697469746975, "percentage": 22.37, "elapsed_time": "1:35:53", "remaining_time": "5:32:43", "throughput": 1491.79, "total_tokens": 8583488} {"current_steps": 40680, "total_steps": 181800, "loss": 0.0849, "lr": 4.770332813615677e-05, "epoch": 4.475247524752476, "percentage": 22.38, "elapsed_time": "1:35:54", "remaining_time": "5:32:42", "throughput": 1491.8, "total_tokens": 8584608} {"current_steps": 40685, "total_steps": 181800, "loss": 0.0587, "lr": 4.7702323167498565e-05, "epoch": 4.475797579757976, "percentage": 22.38, "elapsed_time": "1:35:55", "remaining_time": "5:32:41", "throughput": 1491.82, "total_tokens": 8585728} {"current_steps": 40690, "total_steps": 181800, "loss": 0.0055, "lr": 4.770131798960396e-05, "epoch": 4.476347634763476, "percentage": 22.38, "elapsed_time": "1:35:55", "remaining_time": "5:32:41", "throughput": 1491.81, "total_tokens": 8586720} {"current_steps": 40695, "total_steps": 181800, "loss": 0.1386, "lr": 4.770031260248219e-05, "epoch": 4.476897689768977, "percentage": 22.38, "elapsed_time": "1:35:56", "remaining_time": "5:32:40", "throughput": 1491.82, "total_tokens": 8587808} {"current_steps": 40700, "total_steps": 181800, "loss": 0.0851, "lr": 4.769930700614253e-05, "epoch": 4.477447744774477, "percentage": 22.39, "elapsed_time": "1:35:57", "remaining_time": "5:32:39", "throughput": 1491.82, "total_tokens": 8588832} {"current_steps": 40705, "total_steps": 181800, "loss": 0.0266, "lr": 4.7698301200594254e-05, "epoch": 4.477997799779978, "percentage": 22.39, "elapsed_time": "1:35:57", "remaining_time": "5:32:38", "throughput": 1491.82, "total_tokens": 8589856} {"current_steps": 40710, "total_steps": 181800, "loss": 0.0153, "lr": 4.7697295185846626e-05, "epoch": 4.478547854785479, "percentage": 22.39, "elapsed_time": "1:35:58", "remaining_time": "5:32:37", "throughput": 1491.84, "total_tokens": 8591008} {"current_steps": 40715, "total_steps": 181800, "loss": 0.0535, "lr": 4.769628896190892e-05, "epoch": 4.479097909790979, "percentage": 22.4, "elapsed_time": "1:35:59", "remaining_time": "5:32:37", "throughput": 1491.84, "total_tokens": 8592032} {"current_steps": 40720, "total_steps": 181800, "loss": 0.0558, "lr": 4.7695282528790405e-05, "epoch": 4.47964796479648, "percentage": 22.4, "elapsed_time": "1:36:00", "remaining_time": "5:32:36", "throughput": 1491.84, "total_tokens": 8593056} {"current_steps": 40725, "total_steps": 181800, "loss": 0.1263, "lr": 4.7694275886500366e-05, "epoch": 4.48019801980198, "percentage": 22.4, "elapsed_time": "1:36:00", "remaining_time": "5:32:35", "throughput": 1491.85, "total_tokens": 8594176} {"current_steps": 40730, "total_steps": 181800, "loss": 0.0903, "lr": 4.769326903504808e-05, "epoch": 4.48074807480748, "percentage": 22.4, "elapsed_time": "1:36:01", "remaining_time": "5:32:34", "throughput": 1491.85, "total_tokens": 8595168} {"current_steps": 40735, "total_steps": 181800, "loss": 0.0198, "lr": 4.769226197444282e-05, "epoch": 4.4812981298129815, "percentage": 22.41, "elapsed_time": "1:36:02", "remaining_time": "5:32:34", "throughput": 1491.86, "total_tokens": 8596256} {"current_steps": 40740, "total_steps": 181800, "loss": 0.0195, "lr": 4.769125470469387e-05, "epoch": 4.481848184818482, "percentage": 22.41, "elapsed_time": "1:36:02", "remaining_time": "5:32:33", "throughput": 1491.86, "total_tokens": 8597280} {"current_steps": 40745, "total_steps": 181800, "loss": 0.1071, "lr": 4.76902472258105e-05, "epoch": 4.482398239823983, "percentage": 22.41, "elapsed_time": "1:36:03", "remaining_time": "5:32:32", "throughput": 1491.86, "total_tokens": 8598336} {"current_steps": 40750, "total_steps": 181800, "loss": 0.0488, "lr": 4.7689239537802025e-05, "epoch": 4.482948294829483, "percentage": 22.41, "elapsed_time": "1:36:04", "remaining_time": "5:32:31", "throughput": 1491.86, "total_tokens": 8599392} {"current_steps": 40755, "total_steps": 181800, "loss": 0.037, "lr": 4.768823164067772e-05, "epoch": 4.483498349834983, "percentage": 22.42, "elapsed_time": "1:36:04", "remaining_time": "5:32:31", "throughput": 1491.86, "total_tokens": 8600416} {"current_steps": 40760, "total_steps": 181800, "loss": 0.0234, "lr": 4.768722353444686e-05, "epoch": 4.484048404840484, "percentage": 22.42, "elapsed_time": "1:36:05", "remaining_time": "5:32:30", "throughput": 1491.87, "total_tokens": 8601504} {"current_steps": 40765, "total_steps": 181800, "loss": 0.0056, "lr": 4.768621521911875e-05, "epoch": 4.4845984598459845, "percentage": 22.42, "elapsed_time": "1:36:06", "remaining_time": "5:32:29", "throughput": 1491.88, "total_tokens": 8602592} {"current_steps": 40770, "total_steps": 181800, "loss": 0.0192, "lr": 4.7685206694702676e-05, "epoch": 4.485148514851485, "percentage": 22.43, "elapsed_time": "1:36:06", "remaining_time": "5:32:28", "throughput": 1491.88, "total_tokens": 8603616} {"current_steps": 40775, "total_steps": 181800, "loss": 0.1024, "lr": 4.7684197961207945e-05, "epoch": 4.485698569856986, "percentage": 22.43, "elapsed_time": "1:36:07", "remaining_time": "5:32:28", "throughput": 1491.9, "total_tokens": 8604736} {"current_steps": 40780, "total_steps": 181800, "loss": 0.0281, "lr": 4.768318901864384e-05, "epoch": 4.486248624862486, "percentage": 22.43, "elapsed_time": "1:36:08", "remaining_time": "5:32:27", "throughput": 1491.91, "total_tokens": 8605824} {"current_steps": 40785, "total_steps": 181800, "loss": 0.0591, "lr": 4.768217986701967e-05, "epoch": 4.486798679867987, "percentage": 22.43, "elapsed_time": "1:36:09", "remaining_time": "5:32:26", "throughput": 1491.93, "total_tokens": 8606976} {"current_steps": 40790, "total_steps": 181800, "loss": 0.0513, "lr": 4.768117050634473e-05, "epoch": 4.487348734873487, "percentage": 22.44, "elapsed_time": "1:36:09", "remaining_time": "5:32:25", "throughput": 1491.93, "total_tokens": 8608000} {"current_steps": 40795, "total_steps": 181800, "loss": 0.0754, "lr": 4.7680160936628334e-05, "epoch": 4.4878987898789875, "percentage": 22.44, "elapsed_time": "1:36:10", "remaining_time": "5:32:24", "throughput": 1491.93, "total_tokens": 8609024} {"current_steps": 40800, "total_steps": 181800, "loss": 0.0226, "lr": 4.767915115787977e-05, "epoch": 4.488448844884489, "percentage": 22.44, "elapsed_time": "1:36:11", "remaining_time": "5:32:24", "throughput": 1491.93, "total_tokens": 8610080} {"current_steps": 40805, "total_steps": 181800, "loss": 0.0105, "lr": 4.7678141170108345e-05, "epoch": 4.488998899889989, "percentage": 22.44, "elapsed_time": "1:36:11", "remaining_time": "5:32:23", "throughput": 1491.93, "total_tokens": 8611072} {"current_steps": 40810, "total_steps": 181800, "loss": 0.0078, "lr": 4.7677130973323385e-05, "epoch": 4.48954895489549, "percentage": 22.45, "elapsed_time": "1:36:12", "remaining_time": "5:32:22", "throughput": 1491.93, "total_tokens": 8612128} {"current_steps": 40815, "total_steps": 181800, "loss": 0.0925, "lr": 4.767612056753419e-05, "epoch": 4.49009900990099, "percentage": 22.45, "elapsed_time": "1:36:13", "remaining_time": "5:32:21", "throughput": 1491.93, "total_tokens": 8613184} {"current_steps": 40820, "total_steps": 181800, "loss": 0.0394, "lr": 4.767510995275007e-05, "epoch": 4.49064906490649, "percentage": 22.45, "elapsed_time": "1:36:13", "remaining_time": "5:32:21", "throughput": 1491.93, "total_tokens": 8614208} {"current_steps": 40825, "total_steps": 181800, "loss": 0.046, "lr": 4.7674099128980345e-05, "epoch": 4.491199119911991, "percentage": 22.46, "elapsed_time": "1:36:14", "remaining_time": "5:32:20", "throughput": 1491.93, "total_tokens": 8615232} {"current_steps": 40830, "total_steps": 181800, "loss": 0.1449, "lr": 4.767308809623432e-05, "epoch": 4.491749174917492, "percentage": 22.46, "elapsed_time": "1:36:15", "remaining_time": "5:32:19", "throughput": 1491.93, "total_tokens": 8616288} {"current_steps": 40835, "total_steps": 181800, "loss": 0.031, "lr": 4.767207685452133e-05, "epoch": 4.492299229922993, "percentage": 22.46, "elapsed_time": "1:36:15", "remaining_time": "5:32:18", "throughput": 1491.93, "total_tokens": 8617312} {"current_steps": 40840, "total_steps": 181800, "loss": 0.0092, "lr": 4.767106540385068e-05, "epoch": 4.492849284928493, "percentage": 22.46, "elapsed_time": "1:36:16", "remaining_time": "5:32:18", "throughput": 1491.94, "total_tokens": 8618400} {"current_steps": 40845, "total_steps": 181800, "loss": 0.051, "lr": 4.767005374423171e-05, "epoch": 4.493399339933993, "percentage": 22.47, "elapsed_time": "1:36:17", "remaining_time": "5:32:17", "throughput": 1491.95, "total_tokens": 8619456} {"current_steps": 40850, "total_steps": 181800, "loss": 0.229, "lr": 4.7669041875673726e-05, "epoch": 4.493949394939494, "percentage": 22.47, "elapsed_time": "1:36:18", "remaining_time": "5:32:16", "throughput": 1491.96, "total_tokens": 8620544} {"current_steps": 40855, "total_steps": 181800, "loss": 0.0327, "lr": 4.7668029798186066e-05, "epoch": 4.494499449944994, "percentage": 22.47, "elapsed_time": "1:36:18", "remaining_time": "5:32:15", "throughput": 1491.97, "total_tokens": 8621632} {"current_steps": 40860, "total_steps": 181800, "loss": 0.0812, "lr": 4.766701751177805e-05, "epoch": 4.4950495049504955, "percentage": 22.48, "elapsed_time": "1:36:19", "remaining_time": "5:32:15", "throughput": 1491.99, "total_tokens": 8622784} {"current_steps": 40865, "total_steps": 181800, "loss": 0.0219, "lr": 4.7666005016459e-05, "epoch": 4.495599559955996, "percentage": 22.48, "elapsed_time": "1:36:20", "remaining_time": "5:32:14", "throughput": 1491.99, "total_tokens": 8623808} {"current_steps": 40870, "total_steps": 181800, "loss": 0.0696, "lr": 4.766499231223827e-05, "epoch": 4.496149614961496, "percentage": 22.48, "elapsed_time": "1:36:20", "remaining_time": "5:32:13", "throughput": 1491.98, "total_tokens": 8624800} {"current_steps": 40875, "total_steps": 181800, "loss": 0.0381, "lr": 4.766397939912517e-05, "epoch": 4.496699669966997, "percentage": 22.48, "elapsed_time": "1:36:21", "remaining_time": "5:32:12", "throughput": 1492.0, "total_tokens": 8625920} {"current_steps": 40880, "total_steps": 181800, "loss": 0.0592, "lr": 4.7662966277129056e-05, "epoch": 4.497249724972497, "percentage": 22.49, "elapsed_time": "1:36:22", "remaining_time": "5:32:12", "throughput": 1492.0, "total_tokens": 8626976} {"current_steps": 40885, "total_steps": 181800, "loss": 0.0625, "lr": 4.766195294625926e-05, "epoch": 4.497799779977997, "percentage": 22.49, "elapsed_time": "1:36:22", "remaining_time": "5:32:11", "throughput": 1492.0, "total_tokens": 8628000} {"current_steps": 40890, "total_steps": 181800, "loss": 0.0843, "lr": 4.7660939406525104e-05, "epoch": 4.4983498349834985, "percentage": 22.49, "elapsed_time": "1:36:23", "remaining_time": "5:32:10", "throughput": 1492.01, "total_tokens": 8629088} {"current_steps": 40895, "total_steps": 181800, "loss": 0.0192, "lr": 4.7659925657935955e-05, "epoch": 4.498899889988999, "percentage": 22.49, "elapsed_time": "1:36:24", "remaining_time": "5:32:09", "throughput": 1492.01, "total_tokens": 8630080} {"current_steps": 40900, "total_steps": 181800, "loss": 0.1363, "lr": 4.765891170050114e-05, "epoch": 4.4994499449945, "percentage": 22.5, "elapsed_time": "1:36:24", "remaining_time": "5:32:08", "throughput": 1492.01, "total_tokens": 8631136} {"current_steps": 40905, "total_steps": 181800, "loss": 0.0443, "lr": 4.765789753423001e-05, "epoch": 4.5, "percentage": 22.5, "elapsed_time": "1:36:25", "remaining_time": "5:32:08", "throughput": 1492.02, "total_tokens": 8632224} {"current_steps": 40910, "total_steps": 181800, "loss": 0.0437, "lr": 4.765688315913192e-05, "epoch": 4.5005500550055, "percentage": 22.5, "elapsed_time": "1:36:26", "remaining_time": "5:32:07", "throughput": 1492.04, "total_tokens": 8633344} {"current_steps": 40915, "total_steps": 181800, "loss": 0.0753, "lr": 4.7655868575216196e-05, "epoch": 4.501100110011001, "percentage": 22.51, "elapsed_time": "1:36:26", "remaining_time": "5:32:06", "throughput": 1492.03, "total_tokens": 8634368} {"current_steps": 40920, "total_steps": 181800, "loss": 0.0457, "lr": 4.76548537824922e-05, "epoch": 4.5016501650165015, "percentage": 22.51, "elapsed_time": "1:36:27", "remaining_time": "5:32:05", "throughput": 1492.03, "total_tokens": 8635392} {"current_steps": 40925, "total_steps": 181800, "loss": 0.1559, "lr": 4.76538387809693e-05, "epoch": 4.502200220022003, "percentage": 22.51, "elapsed_time": "1:36:28", "remaining_time": "5:32:05", "throughput": 1492.04, "total_tokens": 8636448} {"current_steps": 40930, "total_steps": 181800, "loss": 0.1078, "lr": 4.765282357065683e-05, "epoch": 4.502750275027503, "percentage": 22.51, "elapsed_time": "1:36:29", "remaining_time": "5:32:04", "throughput": 1492.05, "total_tokens": 8637536} {"current_steps": 40935, "total_steps": 181800, "loss": 0.0095, "lr": 4.765180815156416e-05, "epoch": 4.503300330033003, "percentage": 22.52, "elapsed_time": "1:36:29", "remaining_time": "5:32:03", "throughput": 1492.06, "total_tokens": 8638624} {"current_steps": 40940, "total_steps": 181800, "loss": 0.0204, "lr": 4.765079252370064e-05, "epoch": 4.503850385038504, "percentage": 22.52, "elapsed_time": "1:36:30", "remaining_time": "5:32:02", "throughput": 1492.05, "total_tokens": 8639648} {"current_steps": 40945, "total_steps": 181800, "loss": 0.061, "lr": 4.764977668707564e-05, "epoch": 4.504400440044004, "percentage": 22.52, "elapsed_time": "1:36:31", "remaining_time": "5:32:02", "throughput": 1492.05, "total_tokens": 8640672} {"current_steps": 40950, "total_steps": 181800, "loss": 0.074, "lr": 4.7648760641698514e-05, "epoch": 4.5049504950495045, "percentage": 22.52, "elapsed_time": "1:36:31", "remaining_time": "5:32:01", "throughput": 1492.07, "total_tokens": 8641792} {"current_steps": 40955, "total_steps": 181800, "loss": 0.0469, "lr": 4.764774438757863e-05, "epoch": 4.505500550055006, "percentage": 22.53, "elapsed_time": "1:36:32", "remaining_time": "5:32:00", "throughput": 1492.08, "total_tokens": 8642880} {"current_steps": 40960, "total_steps": 181800, "loss": 0.0544, "lr": 4.764672792472535e-05, "epoch": 4.506050605060506, "percentage": 22.53, "elapsed_time": "1:36:33", "remaining_time": "5:31:59", "throughput": 1492.09, "total_tokens": 8644000} {"current_steps": 40965, "total_steps": 181800, "loss": 0.0432, "lr": 4.764571125314805e-05, "epoch": 4.506600660066007, "percentage": 22.53, "elapsed_time": "1:36:33", "remaining_time": "5:31:59", "throughput": 1492.09, "total_tokens": 8645024} {"current_steps": 40970, "total_steps": 181800, "loss": 0.0584, "lr": 4.764469437285609e-05, "epoch": 4.507150715071507, "percentage": 22.54, "elapsed_time": "1:36:34", "remaining_time": "5:31:58", "throughput": 1492.1, "total_tokens": 8646112} {"current_steps": 40975, "total_steps": 181800, "loss": 0.0151, "lr": 4.764367728385885e-05, "epoch": 4.507700770077007, "percentage": 22.54, "elapsed_time": "1:36:35", "remaining_time": "5:31:57", "throughput": 1492.11, "total_tokens": 8647200} {"current_steps": 40980, "total_steps": 181800, "loss": 0.0963, "lr": 4.76426599861657e-05, "epoch": 4.508250825082508, "percentage": 22.54, "elapsed_time": "1:36:35", "remaining_time": "5:31:56", "throughput": 1492.12, "total_tokens": 8648256} {"current_steps": 40985, "total_steps": 181800, "loss": 0.0198, "lr": 4.764164247978603e-05, "epoch": 4.508800880088009, "percentage": 22.54, "elapsed_time": "1:36:36", "remaining_time": "5:31:55", "throughput": 1492.12, "total_tokens": 8649280} {"current_steps": 40990, "total_steps": 181800, "loss": 0.0282, "lr": 4.7640624764729193e-05, "epoch": 4.50935093509351, "percentage": 22.55, "elapsed_time": "1:36:37", "remaining_time": "5:31:55", "throughput": 1492.12, "total_tokens": 8650304} {"current_steps": 40995, "total_steps": 181800, "loss": 0.0267, "lr": 4.763960684100458e-05, "epoch": 4.50990099009901, "percentage": 22.55, "elapsed_time": "1:36:38", "remaining_time": "5:31:54", "throughput": 1492.12, "total_tokens": 8651360} {"current_steps": 41000, "total_steps": 181800, "loss": 0.182, "lr": 4.763858870862158e-05, "epoch": 4.51045104510451, "percentage": 22.55, "elapsed_time": "1:36:38", "remaining_time": "5:31:53", "throughput": 1492.12, "total_tokens": 8652416} {"current_steps": 41005, "total_steps": 181800, "loss": 0.062, "lr": 4.763757036758957e-05, "epoch": 4.511001100110011, "percentage": 22.56, "elapsed_time": "1:36:39", "remaining_time": "5:31:52", "throughput": 1492.12, "total_tokens": 8653440} {"current_steps": 41010, "total_steps": 181800, "loss": 0.0269, "lr": 4.763655181791794e-05, "epoch": 4.511551155115511, "percentage": 22.56, "elapsed_time": "1:36:40", "remaining_time": "5:31:52", "throughput": 1492.12, "total_tokens": 8654464} {"current_steps": 41015, "total_steps": 181800, "loss": 0.0166, "lr": 4.763553305961607e-05, "epoch": 4.512101210121012, "percentage": 22.56, "elapsed_time": "1:36:40", "remaining_time": "5:31:51", "throughput": 1492.13, "total_tokens": 8655552} {"current_steps": 41020, "total_steps": 181800, "loss": 0.0619, "lr": 4.7634514092693354e-05, "epoch": 4.512651265126513, "percentage": 22.56, "elapsed_time": "1:36:41", "remaining_time": "5:31:50", "throughput": 1492.14, "total_tokens": 8656608} {"current_steps": 41025, "total_steps": 181800, "loss": 0.0558, "lr": 4.7633494917159185e-05, "epoch": 4.513201320132013, "percentage": 22.57, "elapsed_time": "1:36:42", "remaining_time": "5:31:49", "throughput": 1492.13, "total_tokens": 8657600} {"current_steps": 41030, "total_steps": 181800, "loss": 0.0407, "lr": 4.7632475533022946e-05, "epoch": 4.513751375137514, "percentage": 22.57, "elapsed_time": "1:36:42", "remaining_time": "5:31:49", "throughput": 1492.13, "total_tokens": 8658624} {"current_steps": 41035, "total_steps": 181800, "loss": 0.1044, "lr": 4.763145594029405e-05, "epoch": 4.514301430143014, "percentage": 22.57, "elapsed_time": "1:36:43", "remaining_time": "5:31:48", "throughput": 1492.13, "total_tokens": 8659648} {"current_steps": 41040, "total_steps": 181800, "loss": 0.0653, "lr": 4.763043613898188e-05, "epoch": 4.514851485148515, "percentage": 22.57, "elapsed_time": "1:36:44", "remaining_time": "5:31:47", "throughput": 1492.12, "total_tokens": 8660608} {"current_steps": 41045, "total_steps": 181800, "loss": 0.0119, "lr": 4.7629416129095836e-05, "epoch": 4.5154015401540155, "percentage": 22.58, "elapsed_time": "1:36:44", "remaining_time": "5:31:46", "throughput": 1492.11, "total_tokens": 8661632} {"current_steps": 41050, "total_steps": 181800, "loss": 0.0633, "lr": 4.762839591064533e-05, "epoch": 4.515951595159516, "percentage": 22.58, "elapsed_time": "1:36:45", "remaining_time": "5:31:46", "throughput": 1492.12, "total_tokens": 8662720} {"current_steps": 41055, "total_steps": 181800, "loss": 0.0678, "lr": 4.7627375483639756e-05, "epoch": 4.516501650165017, "percentage": 22.58, "elapsed_time": "1:36:46", "remaining_time": "5:31:45", "throughput": 1492.12, "total_tokens": 8663712} {"current_steps": 41060, "total_steps": 181800, "loss": 0.0645, "lr": 4.762635484808851e-05, "epoch": 4.517051705170517, "percentage": 22.59, "elapsed_time": "1:36:47", "remaining_time": "5:31:44", "throughput": 1492.12, "total_tokens": 8664768} {"current_steps": 41065, "total_steps": 181800, "loss": 0.0585, "lr": 4.762533400400102e-05, "epoch": 4.517601760176017, "percentage": 22.59, "elapsed_time": "1:36:47", "remaining_time": "5:31:43", "throughput": 1492.12, "total_tokens": 8665760} {"current_steps": 41070, "total_steps": 181800, "loss": 0.0647, "lr": 4.762431295138667e-05, "epoch": 4.518151815181518, "percentage": 22.59, "elapsed_time": "1:36:48", "remaining_time": "5:31:42", "throughput": 1492.12, "total_tokens": 8666816} {"current_steps": 41075, "total_steps": 181800, "loss": 0.1003, "lr": 4.76232916902549e-05, "epoch": 4.5187018701870185, "percentage": 22.59, "elapsed_time": "1:36:49", "remaining_time": "5:31:42", "throughput": 1492.13, "total_tokens": 8667904} {"current_steps": 41080, "total_steps": 181800, "loss": 0.1051, "lr": 4.7622270220615096e-05, "epoch": 4.51925192519252, "percentage": 22.6, "elapsed_time": "1:36:49", "remaining_time": "5:31:41", "throughput": 1492.14, "total_tokens": 8668960} {"current_steps": 41085, "total_steps": 181800, "loss": 0.031, "lr": 4.762124854247668e-05, "epoch": 4.51980198019802, "percentage": 22.6, "elapsed_time": "1:36:50", "remaining_time": "5:31:40", "throughput": 1492.14, "total_tokens": 8670016} {"current_steps": 41090, "total_steps": 181800, "loss": 0.0161, "lr": 4.762022665584908e-05, "epoch": 4.52035203520352, "percentage": 22.6, "elapsed_time": "1:36:51", "remaining_time": "5:31:39", "throughput": 1492.14, "total_tokens": 8671072} {"current_steps": 41095, "total_steps": 181800, "loss": 0.004, "lr": 4.7619204560741704e-05, "epoch": 4.520902090209021, "percentage": 22.6, "elapsed_time": "1:36:51", "remaining_time": "5:31:39", "throughput": 1492.14, "total_tokens": 8672096} {"current_steps": 41100, "total_steps": 181800, "loss": 0.0479, "lr": 4.761818225716397e-05, "epoch": 4.521452145214521, "percentage": 22.61, "elapsed_time": "1:36:52", "remaining_time": "5:31:38", "throughput": 1492.15, "total_tokens": 8673152} {"current_steps": 41105, "total_steps": 181800, "loss": 0.0329, "lr": 4.76171597451253e-05, "epoch": 4.522002200220022, "percentage": 22.61, "elapsed_time": "1:36:53", "remaining_time": "5:31:37", "throughput": 1492.16, "total_tokens": 8674240} {"current_steps": 41110, "total_steps": 181800, "loss": 0.0226, "lr": 4.761613702463512e-05, "epoch": 4.522552255225523, "percentage": 22.61, "elapsed_time": "1:36:53", "remaining_time": "5:31:36", "throughput": 1492.16, "total_tokens": 8675264} {"current_steps": 41115, "total_steps": 181800, "loss": 0.0466, "lr": 4.761511409570287e-05, "epoch": 4.523102310231023, "percentage": 22.62, "elapsed_time": "1:36:54", "remaining_time": "5:31:36", "throughput": 1492.15, "total_tokens": 8676288} {"current_steps": 41120, "total_steps": 181800, "loss": 0.0146, "lr": 4.761409095833796e-05, "epoch": 4.523652365236524, "percentage": 22.62, "elapsed_time": "1:36:55", "remaining_time": "5:31:35", "throughput": 1492.17, "total_tokens": 8677408} {"current_steps": 41125, "total_steps": 181800, "loss": 0.0683, "lr": 4.7613067612549816e-05, "epoch": 4.524202420242024, "percentage": 22.62, "elapsed_time": "1:36:55", "remaining_time": "5:31:34", "throughput": 1492.18, "total_tokens": 8678496} {"current_steps": 41130, "total_steps": 181800, "loss": 0.1559, "lr": 4.761204405834788e-05, "epoch": 4.524752475247524, "percentage": 22.62, "elapsed_time": "1:36:56", "remaining_time": "5:31:33", "throughput": 1492.19, "total_tokens": 8679552} {"current_steps": 41135, "total_steps": 181800, "loss": 0.0069, "lr": 4.761102029574159e-05, "epoch": 4.525302530253025, "percentage": 22.63, "elapsed_time": "1:36:57", "remaining_time": "5:31:33", "throughput": 1492.19, "total_tokens": 8680608} {"current_steps": 41140, "total_steps": 181800, "loss": 0.0689, "lr": 4.760999632474038e-05, "epoch": 4.525852585258526, "percentage": 22.63, "elapsed_time": "1:36:58", "remaining_time": "5:31:32", "throughput": 1492.2, "total_tokens": 8681696} {"current_steps": 41145, "total_steps": 181800, "loss": 0.0775, "lr": 4.760897214535368e-05, "epoch": 4.526402640264027, "percentage": 22.63, "elapsed_time": "1:36:58", "remaining_time": "5:31:31", "throughput": 1492.2, "total_tokens": 8682720} {"current_steps": 41150, "total_steps": 181800, "loss": 0.0686, "lr": 4.7607947757590934e-05, "epoch": 4.526952695269527, "percentage": 22.63, "elapsed_time": "1:36:59", "remaining_time": "5:31:30", "throughput": 1492.21, "total_tokens": 8683808} {"current_steps": 41155, "total_steps": 181800, "loss": 0.0578, "lr": 4.760692316146157e-05, "epoch": 4.527502750275027, "percentage": 22.64, "elapsed_time": "1:37:00", "remaining_time": "5:31:29", "throughput": 1492.21, "total_tokens": 8684864} {"current_steps": 41160, "total_steps": 181800, "loss": 0.1052, "lr": 4.7605898356975055e-05, "epoch": 4.528052805280528, "percentage": 22.64, "elapsed_time": "1:37:00", "remaining_time": "5:31:29", "throughput": 1492.21, "total_tokens": 8685888} {"current_steps": 41165, "total_steps": 181800, "loss": 0.0215, "lr": 4.760487334414082e-05, "epoch": 4.528602860286028, "percentage": 22.64, "elapsed_time": "1:37:01", "remaining_time": "5:31:28", "throughput": 1492.22, "total_tokens": 8686944} {"current_steps": 41170, "total_steps": 181800, "loss": 0.0647, "lr": 4.760384812296831e-05, "epoch": 4.5291529152915295, "percentage": 22.65, "elapsed_time": "1:37:02", "remaining_time": "5:31:27", "throughput": 1492.21, "total_tokens": 8687936} {"current_steps": 41175, "total_steps": 181800, "loss": 0.0328, "lr": 4.760282269346698e-05, "epoch": 4.52970297029703, "percentage": 22.65, "elapsed_time": "1:37:02", "remaining_time": "5:31:26", "throughput": 1492.22, "total_tokens": 8689024} {"current_steps": 41180, "total_steps": 181800, "loss": 0.0753, "lr": 4.760179705564628e-05, "epoch": 4.53025302530253, "percentage": 22.65, "elapsed_time": "1:37:03", "remaining_time": "5:31:26", "throughput": 1492.22, "total_tokens": 8690048} {"current_steps": 41185, "total_steps": 181800, "loss": 0.0484, "lr": 4.760077120951567e-05, "epoch": 4.530803080308031, "percentage": 22.65, "elapsed_time": "1:37:04", "remaining_time": "5:31:25", "throughput": 1492.23, "total_tokens": 8691104} {"current_steps": 41190, "total_steps": 181800, "loss": 0.1192, "lr": 4.7599745155084584e-05, "epoch": 4.531353135313531, "percentage": 22.66, "elapsed_time": "1:37:04", "remaining_time": "5:31:24", "throughput": 1492.24, "total_tokens": 8692224} {"current_steps": 41195, "total_steps": 181800, "loss": 0.0676, "lr": 4.7598718892362496e-05, "epoch": 4.531903190319031, "percentage": 22.66, "elapsed_time": "1:37:05", "remaining_time": "5:31:23", "throughput": 1492.23, "total_tokens": 8693184} {"current_steps": 41200, "total_steps": 181800, "loss": 0.0261, "lr": 4.759769242135886e-05, "epoch": 4.5324532453245325, "percentage": 22.66, "elapsed_time": "1:37:06", "remaining_time": "5:31:23", "throughput": 1492.23, "total_tokens": 8694240} {"current_steps": 41205, "total_steps": 181800, "loss": 0.0249, "lr": 4.7596665742083135e-05, "epoch": 4.533003300330033, "percentage": 22.67, "elapsed_time": "1:37:07", "remaining_time": "5:31:22", "throughput": 1492.25, "total_tokens": 8695360} {"current_steps": 41210, "total_steps": 181800, "loss": 0.0179, "lr": 4.759563885454479e-05, "epoch": 4.533553355335534, "percentage": 22.67, "elapsed_time": "1:37:07", "remaining_time": "5:31:21", "throughput": 1492.24, "total_tokens": 8696352} {"current_steps": 41215, "total_steps": 181800, "loss": 0.0577, "lr": 4.759461175875328e-05, "epoch": 4.534103410341034, "percentage": 22.67, "elapsed_time": "1:37:08", "remaining_time": "5:31:20", "throughput": 1492.24, "total_tokens": 8697376} {"current_steps": 41220, "total_steps": 181800, "loss": 0.1191, "lr": 4.759358445471808e-05, "epoch": 4.534653465346535, "percentage": 22.67, "elapsed_time": "1:37:09", "remaining_time": "5:31:19", "throughput": 1492.25, "total_tokens": 8698464} {"current_steps": 41225, "total_steps": 181800, "loss": 0.0367, "lr": 4.759255694244865e-05, "epoch": 4.535203520352035, "percentage": 22.68, "elapsed_time": "1:37:09", "remaining_time": "5:31:19", "throughput": 1492.26, "total_tokens": 8699520} {"current_steps": 41230, "total_steps": 181800, "loss": 0.0102, "lr": 4.759152922195445e-05, "epoch": 4.5357535753575355, "percentage": 22.68, "elapsed_time": "1:37:10", "remaining_time": "5:31:18", "throughput": 1492.25, "total_tokens": 8700512} {"current_steps": 41235, "total_steps": 181800, "loss": 0.044, "lr": 4.759050129324499e-05, "epoch": 4.536303630363037, "percentage": 22.68, "elapsed_time": "1:37:11", "remaining_time": "5:31:17", "throughput": 1492.25, "total_tokens": 8701536} {"current_steps": 41240, "total_steps": 181800, "loss": 0.017, "lr": 4.7589473156329704e-05, "epoch": 4.536853685368537, "percentage": 22.68, "elapsed_time": "1:37:11", "remaining_time": "5:31:16", "throughput": 1492.27, "total_tokens": 8702688} {"current_steps": 41245, "total_steps": 181800, "loss": 0.0421, "lr": 4.758844481121809e-05, "epoch": 4.537403740374037, "percentage": 22.69, "elapsed_time": "1:37:12", "remaining_time": "5:31:16", "throughput": 1492.27, "total_tokens": 8703712} {"current_steps": 41250, "total_steps": 181800, "loss": 0.0175, "lr": 4.7587416257919616e-05, "epoch": 4.537953795379538, "percentage": 22.69, "elapsed_time": "1:37:13", "remaining_time": "5:31:15", "throughput": 1492.26, "total_tokens": 8704704} {"current_steps": 41255, "total_steps": 181800, "loss": 0.0096, "lr": 4.758638749644376e-05, "epoch": 4.538503850385038, "percentage": 22.69, "elapsed_time": "1:37:13", "remaining_time": "5:31:14", "throughput": 1492.27, "total_tokens": 8705760} {"current_steps": 41260, "total_steps": 181800, "loss": 0.0776, "lr": 4.7585358526800024e-05, "epoch": 4.539053905390539, "percentage": 22.7, "elapsed_time": "1:37:14", "remaining_time": "5:31:13", "throughput": 1492.26, "total_tokens": 8706784} {"current_steps": 41265, "total_steps": 181800, "loss": 0.0815, "lr": 4.7584329348997866e-05, "epoch": 4.53960396039604, "percentage": 22.7, "elapsed_time": "1:37:15", "remaining_time": "5:31:13", "throughput": 1492.27, "total_tokens": 8707840} {"current_steps": 41270, "total_steps": 181800, "loss": 0.0189, "lr": 4.758329996304678e-05, "epoch": 4.54015401540154, "percentage": 22.7, "elapsed_time": "1:37:15", "remaining_time": "5:31:12", "throughput": 1492.28, "total_tokens": 8708928} {"current_steps": 41275, "total_steps": 181800, "loss": 0.0269, "lr": 4.7582270368956254e-05, "epoch": 4.540704070407041, "percentage": 22.7, "elapsed_time": "1:37:16", "remaining_time": "5:31:11", "throughput": 1492.28, "total_tokens": 8709952} {"current_steps": 41280, "total_steps": 181800, "loss": 0.0383, "lr": 4.758124056673578e-05, "epoch": 4.541254125412541, "percentage": 22.71, "elapsed_time": "1:37:17", "remaining_time": "5:31:10", "throughput": 1492.28, "total_tokens": 8711008} {"current_steps": 41285, "total_steps": 181800, "loss": 0.0623, "lr": 4.758021055639485e-05, "epoch": 4.541804180418042, "percentage": 22.71, "elapsed_time": "1:37:18", "remaining_time": "5:31:10", "throughput": 1492.29, "total_tokens": 8712064} {"current_steps": 41290, "total_steps": 181800, "loss": 0.0545, "lr": 4.757918033794295e-05, "epoch": 4.542354235423542, "percentage": 22.71, "elapsed_time": "1:37:18", "remaining_time": "5:31:09", "throughput": 1492.3, "total_tokens": 8713152} {"current_steps": 41295, "total_steps": 181800, "loss": 0.0223, "lr": 4.757814991138958e-05, "epoch": 4.542904290429043, "percentage": 22.71, "elapsed_time": "1:37:19", "remaining_time": "5:31:08", "throughput": 1492.32, "total_tokens": 8714272} {"current_steps": 41300, "total_steps": 181800, "loss": 0.0439, "lr": 4.7577119276744245e-05, "epoch": 4.543454345434544, "percentage": 22.72, "elapsed_time": "1:37:20", "remaining_time": "5:31:07", "throughput": 1492.31, "total_tokens": 8715296} {"current_steps": 41305, "total_steps": 181800, "loss": 0.0186, "lr": 4.7576088434016417e-05, "epoch": 4.544004400440044, "percentage": 22.72, "elapsed_time": "1:37:20", "remaining_time": "5:31:06", "throughput": 1492.31, "total_tokens": 8716320} {"current_steps": 41310, "total_steps": 181800, "loss": 0.0749, "lr": 4.757505738321563e-05, "epoch": 4.544554455445544, "percentage": 22.72, "elapsed_time": "1:37:21", "remaining_time": "5:31:06", "throughput": 1492.31, "total_tokens": 8717344} {"current_steps": 41315, "total_steps": 181800, "loss": 0.1121, "lr": 4.757402612435137e-05, "epoch": 4.545104510451045, "percentage": 22.73, "elapsed_time": "1:37:22", "remaining_time": "5:31:05", "throughput": 1492.31, "total_tokens": 8718368} {"current_steps": 41320, "total_steps": 181800, "loss": 0.132, "lr": 4.757299465743314e-05, "epoch": 4.5456545654565454, "percentage": 22.73, "elapsed_time": "1:37:22", "remaining_time": "5:31:04", "throughput": 1492.32, "total_tokens": 8719456} {"current_steps": 41325, "total_steps": 181800, "loss": 0.0717, "lr": 4.757196298247045e-05, "epoch": 4.5462046204620465, "percentage": 22.73, "elapsed_time": "1:37:23", "remaining_time": "5:31:03", "throughput": 1492.32, "total_tokens": 8720480} {"current_steps": 41330, "total_steps": 181800, "loss": 0.0084, "lr": 4.757093109947281e-05, "epoch": 4.546754675467547, "percentage": 22.73, "elapsed_time": "1:37:24", "remaining_time": "5:31:03", "throughput": 1492.34, "total_tokens": 8721600} {"current_steps": 41335, "total_steps": 181800, "loss": 0.1359, "lr": 4.756989900844973e-05, "epoch": 4.547304730473047, "percentage": 22.74, "elapsed_time": "1:37:24", "remaining_time": "5:31:02", "throughput": 1492.34, "total_tokens": 8722656} {"current_steps": 41340, "total_steps": 181800, "loss": 0.0416, "lr": 4.756886670941071e-05, "epoch": 4.547854785478548, "percentage": 22.74, "elapsed_time": "1:37:25", "remaining_time": "5:31:01", "throughput": 1492.35, "total_tokens": 8723744} {"current_steps": 41345, "total_steps": 181800, "loss": 0.0886, "lr": 4.7567834202365294e-05, "epoch": 4.548404840484048, "percentage": 22.74, "elapsed_time": "1:37:26", "remaining_time": "5:31:00", "throughput": 1492.36, "total_tokens": 8724800} {"current_steps": 41350, "total_steps": 181800, "loss": 0.0801, "lr": 4.756680148732297e-05, "epoch": 4.548954895489549, "percentage": 22.74, "elapsed_time": "1:37:27", "remaining_time": "5:31:00", "throughput": 1492.36, "total_tokens": 8725856} {"current_steps": 41355, "total_steps": 181800, "loss": 0.0327, "lr": 4.756576856429326e-05, "epoch": 4.5495049504950495, "percentage": 22.75, "elapsed_time": "1:37:27", "remaining_time": "5:30:59", "throughput": 1492.35, "total_tokens": 8726848} {"current_steps": 41360, "total_steps": 181800, "loss": 0.0801, "lr": 4.756473543328569e-05, "epoch": 4.55005500550055, "percentage": 22.75, "elapsed_time": "1:37:28", "remaining_time": "5:30:58", "throughput": 1492.35, "total_tokens": 8727872} {"current_steps": 41365, "total_steps": 181800, "loss": 0.0565, "lr": 4.756370209430978e-05, "epoch": 4.550605060506051, "percentage": 22.75, "elapsed_time": "1:37:29", "remaining_time": "5:30:57", "throughput": 1492.37, "total_tokens": 8728992} {"current_steps": 41370, "total_steps": 181800, "loss": 0.0496, "lr": 4.756266854737507e-05, "epoch": 4.551155115511551, "percentage": 22.76, "elapsed_time": "1:37:29", "remaining_time": "5:30:57", "throughput": 1492.37, "total_tokens": 8730016} {"current_steps": 41375, "total_steps": 181800, "loss": 0.0169, "lr": 4.756163479249105e-05, "epoch": 4.551705170517051, "percentage": 22.76, "elapsed_time": "1:37:30", "remaining_time": "5:30:56", "throughput": 1492.37, "total_tokens": 8731072} {"current_steps": 41380, "total_steps": 181800, "loss": 0.0511, "lr": 4.756060082966728e-05, "epoch": 4.552255225522552, "percentage": 22.76, "elapsed_time": "1:37:31", "remaining_time": "5:30:55", "throughput": 1492.37, "total_tokens": 8732128} {"current_steps": 41385, "total_steps": 181800, "loss": 0.0711, "lr": 4.755956665891328e-05, "epoch": 4.552805280528053, "percentage": 22.76, "elapsed_time": "1:37:31", "remaining_time": "5:30:54", "throughput": 1492.38, "total_tokens": 8733216} {"current_steps": 41390, "total_steps": 181800, "loss": 0.0439, "lr": 4.755853228023858e-05, "epoch": 4.553355335533554, "percentage": 22.77, "elapsed_time": "1:37:32", "remaining_time": "5:30:53", "throughput": 1492.39, "total_tokens": 8734272} {"current_steps": 41395, "total_steps": 181800, "loss": 0.0318, "lr": 4.7557497693652694e-05, "epoch": 4.553905390539054, "percentage": 22.77, "elapsed_time": "1:37:33", "remaining_time": "5:30:53", "throughput": 1492.4, "total_tokens": 8735360} {"current_steps": 41400, "total_steps": 181800, "loss": 0.0176, "lr": 4.7556462899165196e-05, "epoch": 4.554455445544555, "percentage": 22.77, "elapsed_time": "1:37:33", "remaining_time": "5:30:52", "throughput": 1492.42, "total_tokens": 8736480} {"current_steps": 41405, "total_steps": 181800, "loss": 0.0107, "lr": 4.75554278967856e-05, "epoch": 4.555005500550055, "percentage": 22.78, "elapsed_time": "1:37:34", "remaining_time": "5:30:51", "throughput": 1492.42, "total_tokens": 8737536} {"current_steps": 41410, "total_steps": 181800, "loss": 0.2192, "lr": 4.755439268652344e-05, "epoch": 4.555555555555555, "percentage": 22.78, "elapsed_time": "1:37:35", "remaining_time": "5:30:50", "throughput": 1492.42, "total_tokens": 8738560} {"current_steps": 41415, "total_steps": 181800, "loss": 0.0379, "lr": 4.755335726838828e-05, "epoch": 4.5561056105610565, "percentage": 22.78, "elapsed_time": "1:37:35", "remaining_time": "5:30:50", "throughput": 1492.42, "total_tokens": 8739584} {"current_steps": 41420, "total_steps": 181800, "loss": 0.0324, "lr": 4.755232164238963e-05, "epoch": 4.556655665566557, "percentage": 22.78, "elapsed_time": "1:37:36", "remaining_time": "5:30:49", "throughput": 1492.43, "total_tokens": 8740672} {"current_steps": 41425, "total_steps": 181800, "loss": 0.077, "lr": 4.755128580853706e-05, "epoch": 4.557205720572057, "percentage": 22.79, "elapsed_time": "1:37:37", "remaining_time": "5:30:48", "throughput": 1492.43, "total_tokens": 8741696} {"current_steps": 41430, "total_steps": 181800, "loss": 0.0217, "lr": 4.7550249766840115e-05, "epoch": 4.557755775577558, "percentage": 22.79, "elapsed_time": "1:37:38", "remaining_time": "5:30:47", "throughput": 1492.43, "total_tokens": 8742752} {"current_steps": 41435, "total_steps": 181800, "loss": 0.0697, "lr": 4.7549213517308335e-05, "epoch": 4.558305830583058, "percentage": 22.79, "elapsed_time": "1:37:38", "remaining_time": "5:30:47", "throughput": 1492.45, "total_tokens": 8743872} {"current_steps": 41440, "total_steps": 181800, "loss": 0.037, "lr": 4.754817705995127e-05, "epoch": 4.558855885588558, "percentage": 22.79, "elapsed_time": "1:37:39", "remaining_time": "5:30:46", "throughput": 1492.46, "total_tokens": 8744960} {"current_steps": 41445, "total_steps": 181800, "loss": 0.0579, "lr": 4.754714039477848e-05, "epoch": 4.5594059405940595, "percentage": 22.8, "elapsed_time": "1:37:40", "remaining_time": "5:30:45", "throughput": 1492.47, "total_tokens": 8746048} {"current_steps": 41450, "total_steps": 181800, "loss": 0.0255, "lr": 4.7546103521799526e-05, "epoch": 4.55995599559956, "percentage": 22.8, "elapsed_time": "1:37:40", "remaining_time": "5:30:44", "throughput": 1492.48, "total_tokens": 8747136} {"current_steps": 41455, "total_steps": 181800, "loss": 0.0223, "lr": 4.754506644102395e-05, "epoch": 4.560506050605061, "percentage": 22.8, "elapsed_time": "1:37:41", "remaining_time": "5:30:43", "throughput": 1492.5, "total_tokens": 8748256} {"current_steps": 41460, "total_steps": 181800, "loss": 0.0756, "lr": 4.75440291524613e-05, "epoch": 4.561056105610561, "percentage": 22.81, "elapsed_time": "1:37:42", "remaining_time": "5:30:43", "throughput": 1492.5, "total_tokens": 8749312} {"current_steps": 41465, "total_steps": 181800, "loss": 0.04, "lr": 4.754299165612116e-05, "epoch": 4.561606160616062, "percentage": 22.81, "elapsed_time": "1:37:42", "remaining_time": "5:30:42", "throughput": 1492.51, "total_tokens": 8750400} {"current_steps": 41470, "total_steps": 181800, "loss": 0.0621, "lr": 4.7541953952013084e-05, "epoch": 4.562156215621562, "percentage": 22.81, "elapsed_time": "1:37:43", "remaining_time": "5:30:41", "throughput": 1492.5, "total_tokens": 8751392} {"current_steps": 41475, "total_steps": 181800, "loss": 0.0544, "lr": 4.754091604014664e-05, "epoch": 4.5627062706270625, "percentage": 22.81, "elapsed_time": "1:37:44", "remaining_time": "5:30:40", "throughput": 1492.51, "total_tokens": 8752480} {"current_steps": 41480, "total_steps": 181800, "loss": 0.0264, "lr": 4.7539877920531384e-05, "epoch": 4.563256325632564, "percentage": 22.82, "elapsed_time": "1:37:44", "remaining_time": "5:30:40", "throughput": 1492.51, "total_tokens": 8753504} {"current_steps": 41485, "total_steps": 181800, "loss": 0.054, "lr": 4.753883959317689e-05, "epoch": 4.563806380638064, "percentage": 22.82, "elapsed_time": "1:37:45", "remaining_time": "5:30:39", "throughput": 1492.51, "total_tokens": 8754528} {"current_steps": 41490, "total_steps": 181800, "loss": 0.0167, "lr": 4.7537801058092725e-05, "epoch": 4.564356435643564, "percentage": 22.82, "elapsed_time": "1:37:46", "remaining_time": "5:30:38", "throughput": 1492.51, "total_tokens": 8755552} {"current_steps": 41495, "total_steps": 181800, "loss": 0.0809, "lr": 4.753676231528846e-05, "epoch": 4.564906490649065, "percentage": 22.82, "elapsed_time": "1:37:47", "remaining_time": "5:30:37", "throughput": 1492.52, "total_tokens": 8756608} {"current_steps": 41500, "total_steps": 181800, "loss": 0.0271, "lr": 4.753572336477368e-05, "epoch": 4.565456545654565, "percentage": 22.83, "elapsed_time": "1:37:47", "remaining_time": "5:30:37", "throughput": 1492.52, "total_tokens": 8757664} {"current_steps": 41505, "total_steps": 181800, "loss": 0.0241, "lr": 4.753468420655794e-05, "epoch": 4.566006600660066, "percentage": 22.83, "elapsed_time": "1:37:48", "remaining_time": "5:30:36", "throughput": 1492.52, "total_tokens": 8758688} {"current_steps": 41510, "total_steps": 181800, "loss": 0.0598, "lr": 4.7533644840650834e-05, "epoch": 4.566556655665567, "percentage": 22.83, "elapsed_time": "1:37:49", "remaining_time": "5:30:35", "throughput": 1492.52, "total_tokens": 8759712} {"current_steps": 41515, "total_steps": 181800, "loss": 0.0759, "lr": 4.753260526706194e-05, "epoch": 4.567106710671067, "percentage": 22.84, "elapsed_time": "1:37:49", "remaining_time": "5:30:34", "throughput": 1492.52, "total_tokens": 8760768} {"current_steps": 41520, "total_steps": 181800, "loss": 0.0679, "lr": 4.7531565485800834e-05, "epoch": 4.567656765676568, "percentage": 22.84, "elapsed_time": "1:37:50", "remaining_time": "5:30:34", "throughput": 1492.52, "total_tokens": 8761792} {"current_steps": 41525, "total_steps": 181800, "loss": 0.0352, "lr": 4.75305254968771e-05, "epoch": 4.568206820682068, "percentage": 22.84, "elapsed_time": "1:37:51", "remaining_time": "5:30:33", "throughput": 1492.53, "total_tokens": 8762848} {"current_steps": 41530, "total_steps": 181800, "loss": 0.1349, "lr": 4.7529485300300324e-05, "epoch": 4.568756875687569, "percentage": 22.84, "elapsed_time": "1:37:51", "remaining_time": "5:30:32", "throughput": 1492.53, "total_tokens": 8763872} {"current_steps": 41535, "total_steps": 181800, "loss": 0.0985, "lr": 4.752844489608009e-05, "epoch": 4.569306930693069, "percentage": 22.85, "elapsed_time": "1:37:52", "remaining_time": "5:30:31", "throughput": 1492.53, "total_tokens": 8764928} {"current_steps": 41540, "total_steps": 181800, "loss": 0.0168, "lr": 4.7527404284225984e-05, "epoch": 4.56985698569857, "percentage": 22.85, "elapsed_time": "1:37:53", "remaining_time": "5:30:30", "throughput": 1492.54, "total_tokens": 8766016} {"current_steps": 41545, "total_steps": 181800, "loss": 0.0813, "lr": 4.752636346474762e-05, "epoch": 4.570407040704071, "percentage": 22.85, "elapsed_time": "1:37:53", "remaining_time": "5:30:30", "throughput": 1492.55, "total_tokens": 8767104} {"current_steps": 41550, "total_steps": 181800, "loss": 0.1093, "lr": 4.7525322437654555e-05, "epoch": 4.570957095709571, "percentage": 22.85, "elapsed_time": "1:37:54", "remaining_time": "5:30:29", "throughput": 1492.56, "total_tokens": 8768192} {"current_steps": 41555, "total_steps": 181800, "loss": 0.0072, "lr": 4.752428120295641e-05, "epoch": 4.571507150715071, "percentage": 22.86, "elapsed_time": "1:37:55", "remaining_time": "5:30:28", "throughput": 1492.56, "total_tokens": 8769184} {"current_steps": 41560, "total_steps": 181800, "loss": 0.1079, "lr": 4.752323976066277e-05, "epoch": 4.572057205720572, "percentage": 22.86, "elapsed_time": "1:37:55", "remaining_time": "5:30:27", "throughput": 1492.55, "total_tokens": 8770176} {"current_steps": 41565, "total_steps": 181800, "loss": 0.1065, "lr": 4.752219811078325e-05, "epoch": 4.572607260726072, "percentage": 22.86, "elapsed_time": "1:37:56", "remaining_time": "5:30:27", "throughput": 1492.56, "total_tokens": 8771232} {"current_steps": 41570, "total_steps": 181800, "loss": 0.0227, "lr": 4.7521156253327424e-05, "epoch": 4.5731573157315735, "percentage": 22.87, "elapsed_time": "1:37:57", "remaining_time": "5:30:26", "throughput": 1492.56, "total_tokens": 8772256} {"current_steps": 41575, "total_steps": 181800, "loss": 0.0822, "lr": 4.752011418830491e-05, "epoch": 4.573707370737074, "percentage": 22.87, "elapsed_time": "1:37:58", "remaining_time": "5:30:25", "throughput": 1492.57, "total_tokens": 8773344} {"current_steps": 41580, "total_steps": 181800, "loss": 0.1688, "lr": 4.7519071915725304e-05, "epoch": 4.574257425742574, "percentage": 22.87, "elapsed_time": "1:37:58", "remaining_time": "5:30:24", "throughput": 1492.58, "total_tokens": 8774432} {"current_steps": 41585, "total_steps": 181800, "loss": 0.1213, "lr": 4.751802943559823e-05, "epoch": 4.574807480748075, "percentage": 22.87, "elapsed_time": "1:37:59", "remaining_time": "5:30:23", "throughput": 1492.58, "total_tokens": 8775456} {"current_steps": 41590, "total_steps": 181800, "loss": 0.0429, "lr": 4.751698674793327e-05, "epoch": 4.575357535753575, "percentage": 22.88, "elapsed_time": "1:38:00", "remaining_time": "5:30:23", "throughput": 1492.58, "total_tokens": 8776480} {"current_steps": 41595, "total_steps": 181800, "loss": 0.0662, "lr": 4.751594385274006e-05, "epoch": 4.575907590759076, "percentage": 22.88, "elapsed_time": "1:38:00", "remaining_time": "5:30:22", "throughput": 1492.58, "total_tokens": 8777536} {"current_steps": 41600, "total_steps": 181800, "loss": 0.0329, "lr": 4.751490075002819e-05, "epoch": 4.5764576457645765, "percentage": 22.88, "elapsed_time": "1:38:01", "remaining_time": "5:30:21", "throughput": 1492.58, "total_tokens": 8778560} {"current_steps": 41605, "total_steps": 181800, "loss": 0.0078, "lr": 4.75138574398073e-05, "epoch": 4.577007700770077, "percentage": 22.89, "elapsed_time": "1:38:02", "remaining_time": "5:30:20", "throughput": 1492.57, "total_tokens": 8779552} {"current_steps": 41610, "total_steps": 181800, "loss": 0.0388, "lr": 4.751281392208698e-05, "epoch": 4.577557755775578, "percentage": 22.89, "elapsed_time": "1:38:02", "remaining_time": "5:30:20", "throughput": 1492.59, "total_tokens": 8780672} {"current_steps": 41615, "total_steps": 181800, "loss": 0.0697, "lr": 4.751177019687685e-05, "epoch": 4.578107810781078, "percentage": 22.89, "elapsed_time": "1:38:03", "remaining_time": "5:30:19", "throughput": 1492.59, "total_tokens": 8781696} {"current_steps": 41620, "total_steps": 181800, "loss": 0.0704, "lr": 4.751072626418653e-05, "epoch": 4.578657865786578, "percentage": 22.89, "elapsed_time": "1:38:04", "remaining_time": "5:30:18", "throughput": 1492.58, "total_tokens": 8782688} {"current_steps": 41625, "total_steps": 181800, "loss": 0.0198, "lr": 4.750968212402567e-05, "epoch": 4.579207920792079, "percentage": 22.9, "elapsed_time": "1:38:04", "remaining_time": "5:30:17", "throughput": 1492.59, "total_tokens": 8783744} {"current_steps": 41630, "total_steps": 181800, "loss": 0.079, "lr": 4.750863777640385e-05, "epoch": 4.5797579757975795, "percentage": 22.9, "elapsed_time": "1:38:05", "remaining_time": "5:30:17", "throughput": 1492.6, "total_tokens": 8784832} {"current_steps": 41635, "total_steps": 181800, "loss": 0.037, "lr": 4.7507593221330725e-05, "epoch": 4.580308030803081, "percentage": 22.9, "elapsed_time": "1:38:06", "remaining_time": "5:30:16", "throughput": 1492.6, "total_tokens": 8785856} {"current_steps": 41640, "total_steps": 181800, "loss": 0.0604, "lr": 4.750654845881592e-05, "epoch": 4.580858085808581, "percentage": 22.9, "elapsed_time": "1:38:06", "remaining_time": "5:30:15", "throughput": 1492.61, "total_tokens": 8786944} {"current_steps": 41645, "total_steps": 181800, "loss": 0.0239, "lr": 4.750550348886905e-05, "epoch": 4.581408140814082, "percentage": 22.91, "elapsed_time": "1:38:07", "remaining_time": "5:30:14", "throughput": 1492.61, "total_tokens": 8788000} {"current_steps": 41650, "total_steps": 181800, "loss": 0.015, "lr": 4.750445831149976e-05, "epoch": 4.581958195819582, "percentage": 22.91, "elapsed_time": "1:38:08", "remaining_time": "5:30:13", "throughput": 1492.62, "total_tokens": 8789088} {"current_steps": 41655, "total_steps": 181800, "loss": 0.062, "lr": 4.750341292671767e-05, "epoch": 4.582508250825082, "percentage": 22.91, "elapsed_time": "1:38:09", "remaining_time": "5:30:13", "throughput": 1492.63, "total_tokens": 8790144} {"current_steps": 41660, "total_steps": 181800, "loss": 0.0427, "lr": 4.750236733453242e-05, "epoch": 4.583058305830583, "percentage": 22.92, "elapsed_time": "1:38:09", "remaining_time": "5:30:12", "throughput": 1492.64, "total_tokens": 8791232} {"current_steps": 41665, "total_steps": 181800, "loss": 0.037, "lr": 4.7501321534953656e-05, "epoch": 4.583608360836084, "percentage": 22.92, "elapsed_time": "1:38:10", "remaining_time": "5:30:11", "throughput": 1492.65, "total_tokens": 8792288} {"current_steps": 41670, "total_steps": 181800, "loss": 0.0664, "lr": 4.7500275527991e-05, "epoch": 4.584158415841584, "percentage": 22.92, "elapsed_time": "1:38:11", "remaining_time": "5:30:10", "throughput": 1492.64, "total_tokens": 8793280} {"current_steps": 41675, "total_steps": 181800, "loss": 0.0496, "lr": 4.7499229313654105e-05, "epoch": 4.584708470847085, "percentage": 22.92, "elapsed_time": "1:38:11", "remaining_time": "5:30:10", "throughput": 1492.64, "total_tokens": 8794304} {"current_steps": 41680, "total_steps": 181800, "loss": 0.0205, "lr": 4.749818289195261e-05, "epoch": 4.585258525852585, "percentage": 22.93, "elapsed_time": "1:38:12", "remaining_time": "5:30:09", "throughput": 1492.63, "total_tokens": 8795296} {"current_steps": 41685, "total_steps": 181800, "loss": 0.0111, "lr": 4.749713626289616e-05, "epoch": 4.585808580858086, "percentage": 22.93, "elapsed_time": "1:38:13", "remaining_time": "5:30:08", "throughput": 1492.63, "total_tokens": 8796320} {"current_steps": 41690, "total_steps": 181800, "loss": 0.0232, "lr": 4.74960894264944e-05, "epoch": 4.586358635863586, "percentage": 22.93, "elapsed_time": "1:38:13", "remaining_time": "5:30:07", "throughput": 1492.63, "total_tokens": 8797344} {"current_steps": 41695, "total_steps": 181800, "loss": 0.0258, "lr": 4.749504238275698e-05, "epoch": 4.586908690869087, "percentage": 22.93, "elapsed_time": "1:38:14", "remaining_time": "5:30:07", "throughput": 1492.64, "total_tokens": 8798400} {"current_steps": 41700, "total_steps": 181800, "loss": 0.0377, "lr": 4.749399513169354e-05, "epoch": 4.587458745874588, "percentage": 22.94, "elapsed_time": "1:38:15", "remaining_time": "5:30:06", "throughput": 1492.63, "total_tokens": 8799424} {"current_steps": 41705, "total_steps": 181800, "loss": 0.0716, "lr": 4.749294767331375e-05, "epoch": 4.588008800880088, "percentage": 22.94, "elapsed_time": "1:38:15", "remaining_time": "5:30:05", "throughput": 1492.64, "total_tokens": 8800480} {"current_steps": 41710, "total_steps": 181800, "loss": 0.0203, "lr": 4.749190000762725e-05, "epoch": 4.588558855885589, "percentage": 22.94, "elapsed_time": "1:38:16", "remaining_time": "5:30:04", "throughput": 1492.64, "total_tokens": 8801504} {"current_steps": 41715, "total_steps": 181800, "loss": 0.0414, "lr": 4.74908521346437e-05, "epoch": 4.589108910891089, "percentage": 22.95, "elapsed_time": "1:38:17", "remaining_time": "5:30:03", "throughput": 1492.63, "total_tokens": 8802496} {"current_steps": 41720, "total_steps": 181800, "loss": 0.0729, "lr": 4.748980405437276e-05, "epoch": 4.589658965896589, "percentage": 22.95, "elapsed_time": "1:38:17", "remaining_time": "5:30:03", "throughput": 1492.63, "total_tokens": 8803488} {"current_steps": 41725, "total_steps": 181800, "loss": 0.0528, "lr": 4.7488755766824086e-05, "epoch": 4.5902090209020905, "percentage": 22.95, "elapsed_time": "1:38:18", "remaining_time": "5:30:02", "throughput": 1492.64, "total_tokens": 8804576} {"current_steps": 41730, "total_steps": 181800, "loss": 0.0722, "lr": 4.748770727200734e-05, "epoch": 4.590759075907591, "percentage": 22.95, "elapsed_time": "1:38:19", "remaining_time": "5:30:01", "throughput": 1492.63, "total_tokens": 8805568} {"current_steps": 41735, "total_steps": 181800, "loss": 0.1381, "lr": 4.748665856993219e-05, "epoch": 4.591309130913091, "percentage": 22.96, "elapsed_time": "1:38:20", "remaining_time": "5:30:00", "throughput": 1492.65, "total_tokens": 8806688} {"current_steps": 41740, "total_steps": 181800, "loss": 0.0255, "lr": 4.7485609660608296e-05, "epoch": 4.591859185918592, "percentage": 22.96, "elapsed_time": "1:38:20", "remaining_time": "5:30:00", "throughput": 1492.66, "total_tokens": 8807776} {"current_steps": 41745, "total_steps": 181800, "loss": 0.0125, "lr": 4.748456054404533e-05, "epoch": 4.592409240924092, "percentage": 22.96, "elapsed_time": "1:38:21", "remaining_time": "5:29:59", "throughput": 1492.67, "total_tokens": 8808864} {"current_steps": 41750, "total_steps": 181800, "loss": 0.0278, "lr": 4.748351122025295e-05, "epoch": 4.592959295929593, "percentage": 22.96, "elapsed_time": "1:38:22", "remaining_time": "5:29:58", "throughput": 1492.67, "total_tokens": 8809920} {"current_steps": 41755, "total_steps": 181800, "loss": 0.099, "lr": 4.748246168924085e-05, "epoch": 4.5935093509350935, "percentage": 22.97, "elapsed_time": "1:38:22", "remaining_time": "5:29:57", "throughput": 1492.67, "total_tokens": 8810944} {"current_steps": 41760, "total_steps": 181800, "loss": 0.0248, "lr": 4.748141195101868e-05, "epoch": 4.594059405940594, "percentage": 22.97, "elapsed_time": "1:38:23", "remaining_time": "5:29:57", "throughput": 1492.68, "total_tokens": 8812032} {"current_steps": 41765, "total_steps": 181800, "loss": 0.0637, "lr": 4.7480362005596126e-05, "epoch": 4.594609460946095, "percentage": 22.97, "elapsed_time": "1:38:24", "remaining_time": "5:29:56", "throughput": 1492.69, "total_tokens": 8813088} {"current_steps": 41770, "total_steps": 181800, "loss": 0.0361, "lr": 4.747931185298286e-05, "epoch": 4.595159515951595, "percentage": 22.98, "elapsed_time": "1:38:24", "remaining_time": "5:29:55", "throughput": 1492.69, "total_tokens": 8814144} {"current_steps": 41775, "total_steps": 181800, "loss": 0.0934, "lr": 4.747826149318856e-05, "epoch": 4.595709570957096, "percentage": 22.98, "elapsed_time": "1:38:25", "remaining_time": "5:29:54", "throughput": 1492.69, "total_tokens": 8815168} {"current_steps": 41780, "total_steps": 181800, "loss": 0.0062, "lr": 4.747721092622292e-05, "epoch": 4.596259625962596, "percentage": 22.98, "elapsed_time": "1:38:26", "remaining_time": "5:29:53", "throughput": 1492.7, "total_tokens": 8816224} {"current_steps": 41785, "total_steps": 181800, "loss": 0.072, "lr": 4.74761601520956e-05, "epoch": 4.5968096809680965, "percentage": 22.98, "elapsed_time": "1:38:26", "remaining_time": "5:29:53", "throughput": 1492.7, "total_tokens": 8817280} {"current_steps": 41790, "total_steps": 181800, "loss": 0.0146, "lr": 4.747510917081631e-05, "epoch": 4.597359735973598, "percentage": 22.99, "elapsed_time": "1:38:27", "remaining_time": "5:29:52", "throughput": 1492.7, "total_tokens": 8818336} {"current_steps": 41795, "total_steps": 181800, "loss": 0.0131, "lr": 4.747405798239472e-05, "epoch": 4.597909790979098, "percentage": 22.99, "elapsed_time": "1:38:28", "remaining_time": "5:29:51", "throughput": 1492.7, "total_tokens": 8819360} {"current_steps": 41800, "total_steps": 181800, "loss": 0.0613, "lr": 4.747300658684052e-05, "epoch": 4.598459845984598, "percentage": 22.99, "elapsed_time": "1:38:29", "remaining_time": "5:29:50", "throughput": 1492.7, "total_tokens": 8820384} {"current_steps": 41805, "total_steps": 181800, "loss": 0.0423, "lr": 4.7471954984163404e-05, "epoch": 4.599009900990099, "percentage": 23.0, "elapsed_time": "1:38:29", "remaining_time": "5:29:50", "throughput": 1492.7, "total_tokens": 8821440} {"current_steps": 41810, "total_steps": 181800, "loss": 0.0775, "lr": 4.747090317437306e-05, "epoch": 4.599559955995599, "percentage": 23.0, "elapsed_time": "1:38:30", "remaining_time": "5:29:49", "throughput": 1492.71, "total_tokens": 8822528} {"current_steps": 41815, "total_steps": 181800, "loss": 0.0251, "lr": 4.7469851157479177e-05, "epoch": 4.6001100110011, "percentage": 23.0, "elapsed_time": "1:38:31", "remaining_time": "5:29:48", "throughput": 1492.72, "total_tokens": 8823584} {"current_steps": 41820, "total_steps": 181800, "loss": 0.0832, "lr": 4.746879893349147e-05, "epoch": 4.600660066006601, "percentage": 23.0, "elapsed_time": "1:38:31", "remaining_time": "5:29:47", "throughput": 1492.72, "total_tokens": 8824640} {"current_steps": 41825, "total_steps": 181800, "loss": 0.0589, "lr": 4.746774650241961e-05, "epoch": 4.601210121012102, "percentage": 23.01, "elapsed_time": "1:38:32", "remaining_time": "5:29:47", "throughput": 1492.73, "total_tokens": 8825696} {"current_steps": 41830, "total_steps": 181800, "loss": 0.0528, "lr": 4.7466693864273325e-05, "epoch": 4.601760176017602, "percentage": 23.01, "elapsed_time": "1:38:33", "remaining_time": "5:29:46", "throughput": 1492.73, "total_tokens": 8826784} {"current_steps": 41835, "total_steps": 181800, "loss": 0.0208, "lr": 4.74656410190623e-05, "epoch": 4.602310231023102, "percentage": 23.01, "elapsed_time": "1:38:33", "remaining_time": "5:29:45", "throughput": 1492.74, "total_tokens": 8827872} {"current_steps": 41840, "total_steps": 181800, "loss": 0.0845, "lr": 4.7464587966796234e-05, "epoch": 4.602860286028603, "percentage": 23.01, "elapsed_time": "1:38:34", "remaining_time": "5:29:44", "throughput": 1492.75, "total_tokens": 8828960} {"current_steps": 41845, "total_steps": 181800, "loss": 0.0675, "lr": 4.746353470748485e-05, "epoch": 4.603410341034103, "percentage": 23.02, "elapsed_time": "1:38:35", "remaining_time": "5:29:44", "throughput": 1492.75, "total_tokens": 8829952} {"current_steps": 41850, "total_steps": 181800, "loss": 0.0042, "lr": 4.746248124113785e-05, "epoch": 4.603960396039604, "percentage": 23.02, "elapsed_time": "1:38:35", "remaining_time": "5:29:43", "throughput": 1492.75, "total_tokens": 8831008} {"current_steps": 41855, "total_steps": 181800, "loss": 0.0823, "lr": 4.7461427567764924e-05, "epoch": 4.604510451045105, "percentage": 23.02, "elapsed_time": "1:38:36", "remaining_time": "5:29:42", "throughput": 1492.77, "total_tokens": 8832128} {"current_steps": 41860, "total_steps": 181800, "loss": 0.0506, "lr": 4.7460373687375805e-05, "epoch": 4.605060506050605, "percentage": 23.03, "elapsed_time": "1:38:37", "remaining_time": "5:29:41", "throughput": 1492.77, "total_tokens": 8833184} {"current_steps": 41865, "total_steps": 181800, "loss": 0.0466, "lr": 4.74593195999802e-05, "epoch": 4.605610561056105, "percentage": 23.03, "elapsed_time": "1:38:38", "remaining_time": "5:29:41", "throughput": 1492.78, "total_tokens": 8834272} {"current_steps": 41870, "total_steps": 181800, "loss": 0.0167, "lr": 4.745826530558782e-05, "epoch": 4.606160616061606, "percentage": 23.03, "elapsed_time": "1:38:38", "remaining_time": "5:29:40", "throughput": 1492.77, "total_tokens": 8835264} {"current_steps": 41875, "total_steps": 181800, "loss": 0.116, "lr": 4.7457210804208396e-05, "epoch": 4.606710671067106, "percentage": 23.03, "elapsed_time": "1:38:39", "remaining_time": "5:29:39", "throughput": 1492.77, "total_tokens": 8836288} {"current_steps": 41880, "total_steps": 181800, "loss": 0.0684, "lr": 4.7456156095851625e-05, "epoch": 4.6072607260726075, "percentage": 23.04, "elapsed_time": "1:38:40", "remaining_time": "5:29:38", "throughput": 1492.77, "total_tokens": 8837312} {"current_steps": 41885, "total_steps": 181800, "loss": 0.1047, "lr": 4.745510118052724e-05, "epoch": 4.607810781078108, "percentage": 23.04, "elapsed_time": "1:38:40", "remaining_time": "5:29:38", "throughput": 1492.78, "total_tokens": 8838400} {"current_steps": 41890, "total_steps": 181800, "loss": 0.2514, "lr": 4.745404605824497e-05, "epoch": 4.608360836083609, "percentage": 23.04, "elapsed_time": "1:38:41", "remaining_time": "5:29:37", "throughput": 1492.78, "total_tokens": 8839456} {"current_steps": 41895, "total_steps": 181800, "loss": 0.0758, "lr": 4.7452990729014526e-05, "epoch": 4.608910891089109, "percentage": 23.04, "elapsed_time": "1:38:42", "remaining_time": "5:29:36", "throughput": 1492.79, "total_tokens": 8840512} {"current_steps": 41900, "total_steps": 181800, "loss": 0.0331, "lr": 4.745193519284564e-05, "epoch": 4.609460946094609, "percentage": 23.05, "elapsed_time": "1:38:42", "remaining_time": "5:29:35", "throughput": 1492.78, "total_tokens": 8841504} {"current_steps": 41905, "total_steps": 181800, "loss": 0.037, "lr": 4.745087944974804e-05, "epoch": 4.61001100110011, "percentage": 23.05, "elapsed_time": "1:38:43", "remaining_time": "5:29:35", "throughput": 1492.78, "total_tokens": 8842528} {"current_steps": 41910, "total_steps": 181800, "loss": 0.1503, "lr": 4.744982349973146e-05, "epoch": 4.6105610561056105, "percentage": 23.05, "elapsed_time": "1:38:44", "remaining_time": "5:29:34", "throughput": 1492.78, "total_tokens": 8843552} {"current_steps": 41915, "total_steps": 181800, "loss": 0.0489, "lr": 4.744876734280562e-05, "epoch": 4.611111111111111, "percentage": 23.06, "elapsed_time": "1:38:44", "remaining_time": "5:29:33", "throughput": 1492.79, "total_tokens": 8844640} {"current_steps": 41920, "total_steps": 181800, "loss": 0.028, "lr": 4.7447710978980274e-05, "epoch": 4.611661166116612, "percentage": 23.06, "elapsed_time": "1:38:45", "remaining_time": "5:29:32", "throughput": 1492.8, "total_tokens": 8845728} {"current_steps": 41925, "total_steps": 181800, "loss": 0.055, "lr": 4.7446654408265146e-05, "epoch": 4.612211221122112, "percentage": 23.06, "elapsed_time": "1:38:46", "remaining_time": "5:29:31", "throughput": 1492.8, "total_tokens": 8846752} {"current_steps": 41930, "total_steps": 181800, "loss": 0.0298, "lr": 4.744559763066998e-05, "epoch": 4.612761276127613, "percentage": 23.06, "elapsed_time": "1:38:46", "remaining_time": "5:29:31", "throughput": 1492.8, "total_tokens": 8847808} {"current_steps": 41935, "total_steps": 181800, "loss": 0.0316, "lr": 4.7444540646204504e-05, "epoch": 4.613311331133113, "percentage": 23.07, "elapsed_time": "1:38:47", "remaining_time": "5:29:30", "throughput": 1492.81, "total_tokens": 8848896} {"current_steps": 41940, "total_steps": 181800, "loss": 0.021, "lr": 4.7443483454878466e-05, "epoch": 4.6138613861386135, "percentage": 23.07, "elapsed_time": "1:38:48", "remaining_time": "5:29:29", "throughput": 1492.82, "total_tokens": 8849952} {"current_steps": 41945, "total_steps": 181800, "loss": 0.0548, "lr": 4.744242605670161e-05, "epoch": 4.614411441144115, "percentage": 23.07, "elapsed_time": "1:38:49", "remaining_time": "5:29:28", "throughput": 1492.84, "total_tokens": 8851072} {"current_steps": 41950, "total_steps": 181800, "loss": 0.0622, "lr": 4.744136845168369e-05, "epoch": 4.614961496149615, "percentage": 23.07, "elapsed_time": "1:38:49", "remaining_time": "5:29:28", "throughput": 1492.85, "total_tokens": 8852160} {"current_steps": 41955, "total_steps": 181800, "loss": 0.0841, "lr": 4.744031063983444e-05, "epoch": 4.615511551155116, "percentage": 23.08, "elapsed_time": "1:38:50", "remaining_time": "5:29:27", "throughput": 1492.84, "total_tokens": 8853152} {"current_steps": 41960, "total_steps": 181800, "loss": 0.0431, "lr": 4.743925262116361e-05, "epoch": 4.616061606160616, "percentage": 23.08, "elapsed_time": "1:38:51", "remaining_time": "5:29:26", "throughput": 1492.84, "total_tokens": 8854208} {"current_steps": 41965, "total_steps": 181800, "loss": 0.0268, "lr": 4.743819439568096e-05, "epoch": 4.616611661166116, "percentage": 23.08, "elapsed_time": "1:38:51", "remaining_time": "5:29:25", "throughput": 1492.85, "total_tokens": 8855264} {"current_steps": 41970, "total_steps": 181800, "loss": 0.01, "lr": 4.743713596339624e-05, "epoch": 4.617161716171617, "percentage": 23.09, "elapsed_time": "1:38:52", "remaining_time": "5:29:25", "throughput": 1492.85, "total_tokens": 8856320} {"current_steps": 41975, "total_steps": 181800, "loss": 0.1279, "lr": 4.743607732431921e-05, "epoch": 4.617711771177118, "percentage": 23.09, "elapsed_time": "1:38:53", "remaining_time": "5:29:24", "throughput": 1492.86, "total_tokens": 8857408} {"current_steps": 41980, "total_steps": 181800, "loss": 0.1116, "lr": 4.743501847845961e-05, "epoch": 4.618261826182618, "percentage": 23.09, "elapsed_time": "1:38:53", "remaining_time": "5:29:23", "throughput": 1492.85, "total_tokens": 8858368} {"current_steps": 41985, "total_steps": 181800, "loss": 0.1152, "lr": 4.7433959425827215e-05, "epoch": 4.618811881188119, "percentage": 23.09, "elapsed_time": "1:38:54", "remaining_time": "5:29:22", "throughput": 1492.86, "total_tokens": 8859456} {"current_steps": 41990, "total_steps": 181800, "loss": 0.0461, "lr": 4.743290016643178e-05, "epoch": 4.619361936193619, "percentage": 23.1, "elapsed_time": "1:38:55", "remaining_time": "5:29:22", "throughput": 1492.87, "total_tokens": 8860576} {"current_steps": 41995, "total_steps": 181800, "loss": 0.1175, "lr": 4.743184070028307e-05, "epoch": 4.61991199119912, "percentage": 23.1, "elapsed_time": "1:38:55", "remaining_time": "5:29:21", "throughput": 1492.87, "total_tokens": 8861600} {"current_steps": 42000, "total_steps": 181800, "loss": 0.1205, "lr": 4.7430781027390845e-05, "epoch": 4.62046204620462, "percentage": 23.1, "elapsed_time": "1:38:56", "remaining_time": "5:29:20", "throughput": 1492.87, "total_tokens": 8862624} {"current_steps": 42005, "total_steps": 181800, "loss": 0.1072, "lr": 4.7429721147764886e-05, "epoch": 4.621012101210121, "percentage": 23.11, "elapsed_time": "1:38:57", "remaining_time": "5:29:19", "throughput": 1492.89, "total_tokens": 8863744} {"current_steps": 42010, "total_steps": 181800, "loss": 0.0091, "lr": 4.742866106141494e-05, "epoch": 4.621562156215622, "percentage": 23.11, "elapsed_time": "1:38:58", "remaining_time": "5:29:18", "throughput": 1492.89, "total_tokens": 8864800} {"current_steps": 42015, "total_steps": 181800, "loss": 0.0179, "lr": 4.742760076835078e-05, "epoch": 4.622112211221122, "percentage": 23.11, "elapsed_time": "1:38:58", "remaining_time": "5:29:18", "throughput": 1492.9, "total_tokens": 8865888} {"current_steps": 42020, "total_steps": 181800, "loss": 0.1471, "lr": 4.74265402685822e-05, "epoch": 4.622662266226623, "percentage": 23.11, "elapsed_time": "1:38:59", "remaining_time": "5:29:17", "throughput": 1492.89, "total_tokens": 8866880} {"current_steps": 42025, "total_steps": 181800, "loss": 0.0619, "lr": 4.742547956211895e-05, "epoch": 4.623212321232123, "percentage": 23.12, "elapsed_time": "1:39:00", "remaining_time": "5:29:16", "throughput": 1492.89, "total_tokens": 8867872} {"current_steps": 42030, "total_steps": 181800, "loss": 0.0998, "lr": 4.742441864897082e-05, "epoch": 4.623762376237623, "percentage": 23.12, "elapsed_time": "1:39:00", "remaining_time": "5:29:15", "throughput": 1492.89, "total_tokens": 8868928} {"current_steps": 42035, "total_steps": 181800, "loss": 0.0462, "lr": 4.742335752914758e-05, "epoch": 4.6243124312431245, "percentage": 23.12, "elapsed_time": "1:39:01", "remaining_time": "5:29:15", "throughput": 1492.88, "total_tokens": 8869920} {"current_steps": 42040, "total_steps": 181800, "loss": 0.0319, "lr": 4.742229620265902e-05, "epoch": 4.624862486248625, "percentage": 23.12, "elapsed_time": "1:39:02", "remaining_time": "5:29:14", "throughput": 1492.89, "total_tokens": 8870976} {"current_steps": 42045, "total_steps": 181800, "loss": 0.0603, "lr": 4.742123466951491e-05, "epoch": 4.625412541254125, "percentage": 23.13, "elapsed_time": "1:39:02", "remaining_time": "5:29:13", "throughput": 1492.89, "total_tokens": 8872000} {"current_steps": 42050, "total_steps": 181800, "loss": 0.0208, "lr": 4.742017292972504e-05, "epoch": 4.625962596259626, "percentage": 23.13, "elapsed_time": "1:39:03", "remaining_time": "5:29:12", "throughput": 1492.89, "total_tokens": 8873056} {"current_steps": 42055, "total_steps": 181800, "loss": 0.0193, "lr": 4.74191109832992e-05, "epoch": 4.626512651265126, "percentage": 23.13, "elapsed_time": "1:39:04", "remaining_time": "5:29:12", "throughput": 1492.89, "total_tokens": 8874112} {"current_steps": 42060, "total_steps": 181800, "loss": 0.0356, "lr": 4.7418048830247164e-05, "epoch": 4.627062706270627, "percentage": 23.14, "elapsed_time": "1:39:04", "remaining_time": "5:29:11", "throughput": 1492.89, "total_tokens": 8875136} {"current_steps": 42065, "total_steps": 181800, "loss": 0.0719, "lr": 4.741698647057873e-05, "epoch": 4.6276127612761275, "percentage": 23.14, "elapsed_time": "1:39:05", "remaining_time": "5:29:10", "throughput": 1492.9, "total_tokens": 8876224} {"current_steps": 42070, "total_steps": 181800, "loss": 0.0103, "lr": 4.7415923904303695e-05, "epoch": 4.628162816281629, "percentage": 23.14, "elapsed_time": "1:39:06", "remaining_time": "5:29:09", "throughput": 1492.91, "total_tokens": 8877312} {"current_steps": 42075, "total_steps": 181800, "loss": 0.0976, "lr": 4.741486113143184e-05, "epoch": 4.628712871287129, "percentage": 23.14, "elapsed_time": "1:39:07", "remaining_time": "5:29:09", "throughput": 1492.91, "total_tokens": 8878336} {"current_steps": 42080, "total_steps": 181800, "loss": 0.0152, "lr": 4.741379815197297e-05, "epoch": 4.629262926292629, "percentage": 23.15, "elapsed_time": "1:39:07", "remaining_time": "5:29:08", "throughput": 1492.9, "total_tokens": 8879360} {"current_steps": 42085, "total_steps": 181800, "loss": 0.0705, "lr": 4.7412734965936865e-05, "epoch": 4.62981298129813, "percentage": 23.15, "elapsed_time": "1:39:08", "remaining_time": "5:29:07", "throughput": 1492.9, "total_tokens": 8880384} {"current_steps": 42090, "total_steps": 181800, "loss": 0.0294, "lr": 4.741167157333335e-05, "epoch": 4.63036303630363, "percentage": 23.15, "elapsed_time": "1:39:09", "remaining_time": "5:29:06", "throughput": 1492.9, "total_tokens": 8881408} {"current_steps": 42095, "total_steps": 181800, "loss": 0.0981, "lr": 4.741060797417221e-05, "epoch": 4.6309130913091305, "percentage": 23.15, "elapsed_time": "1:39:09", "remaining_time": "5:29:06", "throughput": 1492.91, "total_tokens": 8882464} {"current_steps": 42100, "total_steps": 181800, "loss": 0.1245, "lr": 4.740954416846324e-05, "epoch": 4.631463146314632, "percentage": 23.16, "elapsed_time": "1:39:10", "remaining_time": "5:29:05", "throughput": 1492.91, "total_tokens": 8883488} {"current_steps": 42105, "total_steps": 181800, "loss": 0.0769, "lr": 4.7408480156216264e-05, "epoch": 4.632013201320132, "percentage": 23.16, "elapsed_time": "1:39:11", "remaining_time": "5:29:04", "throughput": 1492.92, "total_tokens": 8884576} {"current_steps": 42110, "total_steps": 181800, "loss": 0.0556, "lr": 4.740741593744108e-05, "epoch": 4.632563256325633, "percentage": 23.16, "elapsed_time": "1:39:11", "remaining_time": "5:29:03", "throughput": 1492.91, "total_tokens": 8885600} {"current_steps": 42115, "total_steps": 181800, "loss": 0.0754, "lr": 4.740635151214749e-05, "epoch": 4.633113311331133, "percentage": 23.17, "elapsed_time": "1:39:12", "remaining_time": "5:29:03", "throughput": 1492.92, "total_tokens": 8886688} {"current_steps": 42120, "total_steps": 181800, "loss": 0.0107, "lr": 4.740528688034531e-05, "epoch": 4.633663366336633, "percentage": 23.17, "elapsed_time": "1:39:13", "remaining_time": "5:29:02", "throughput": 1492.92, "total_tokens": 8887712} {"current_steps": 42125, "total_steps": 181800, "loss": 0.0512, "lr": 4.740422204204435e-05, "epoch": 4.634213421342134, "percentage": 23.17, "elapsed_time": "1:39:13", "remaining_time": "5:29:01", "throughput": 1492.92, "total_tokens": 8888736} {"current_steps": 42130, "total_steps": 181800, "loss": 0.1244, "lr": 4.740315699725444e-05, "epoch": 4.634763476347635, "percentage": 23.17, "elapsed_time": "1:39:14", "remaining_time": "5:29:00", "throughput": 1492.92, "total_tokens": 8889760} {"current_steps": 42135, "total_steps": 181800, "loss": 0.1313, "lr": 4.7402091745985366e-05, "epoch": 4.635313531353136, "percentage": 23.18, "elapsed_time": "1:39:15", "remaining_time": "5:29:00", "throughput": 1492.91, "total_tokens": 8890752} {"current_steps": 42140, "total_steps": 181800, "loss": 0.0918, "lr": 4.740102628824697e-05, "epoch": 4.635863586358636, "percentage": 23.18, "elapsed_time": "1:39:15", "remaining_time": "5:28:59", "throughput": 1492.92, "total_tokens": 8891840} {"current_steps": 42145, "total_steps": 181800, "loss": 0.0054, "lr": 4.739996062404907e-05, "epoch": 4.636413641364136, "percentage": 23.18, "elapsed_time": "1:39:16", "remaining_time": "5:28:58", "throughput": 1492.93, "total_tokens": 8892896} {"current_steps": 42150, "total_steps": 181800, "loss": 0.1602, "lr": 4.7398894753401466e-05, "epoch": 4.636963696369637, "percentage": 23.18, "elapsed_time": "1:39:17", "remaining_time": "5:28:57", "throughput": 1492.92, "total_tokens": 8893888} {"current_steps": 42155, "total_steps": 181800, "loss": 0.0553, "lr": 4.7397828676314004e-05, "epoch": 4.637513751375137, "percentage": 23.19, "elapsed_time": "1:39:18", "remaining_time": "5:28:56", "throughput": 1492.93, "total_tokens": 8894944} {"current_steps": 42160, "total_steps": 181800, "loss": 0.0168, "lr": 4.739676239279651e-05, "epoch": 4.638063806380638, "percentage": 23.19, "elapsed_time": "1:39:18", "remaining_time": "5:28:56", "throughput": 1492.94, "total_tokens": 8896064} {"current_steps": 42165, "total_steps": 181800, "loss": 0.0471, "lr": 4.739569590285879e-05, "epoch": 4.638613861386139, "percentage": 23.19, "elapsed_time": "1:39:19", "remaining_time": "5:28:55", "throughput": 1492.95, "total_tokens": 8897152} {"current_steps": 42170, "total_steps": 181800, "loss": 0.0194, "lr": 4.73946292065107e-05, "epoch": 4.639163916391639, "percentage": 23.2, "elapsed_time": "1:39:20", "remaining_time": "5:28:54", "throughput": 1492.96, "total_tokens": 8898240} {"current_steps": 42175, "total_steps": 181800, "loss": 0.0769, "lr": 4.739356230376205e-05, "epoch": 4.63971397139714, "percentage": 23.2, "elapsed_time": "1:39:20", "remaining_time": "5:28:53", "throughput": 1492.98, "total_tokens": 8899360} {"current_steps": 42180, "total_steps": 181800, "loss": 0.0058, "lr": 4.739249519462269e-05, "epoch": 4.64026402640264, "percentage": 23.2, "elapsed_time": "1:39:21", "remaining_time": "5:28:53", "throughput": 1492.97, "total_tokens": 8900352} {"current_steps": 42185, "total_steps": 181800, "loss": 0.0354, "lr": 4.739142787910244e-05, "epoch": 4.6408140814081404, "percentage": 23.2, "elapsed_time": "1:39:22", "remaining_time": "5:28:52", "throughput": 1492.98, "total_tokens": 8901440} {"current_steps": 42190, "total_steps": 181800, "loss": 0.0576, "lr": 4.739036035721114e-05, "epoch": 4.6413641364136415, "percentage": 23.21, "elapsed_time": "1:39:22", "remaining_time": "5:28:51", "throughput": 1492.99, "total_tokens": 8902528} {"current_steps": 42195, "total_steps": 181800, "loss": 0.042, "lr": 4.738929262895864e-05, "epoch": 4.641914191419142, "percentage": 23.21, "elapsed_time": "1:39:23", "remaining_time": "5:28:50", "throughput": 1493.0, "total_tokens": 8903616} {"current_steps": 42200, "total_steps": 181800, "loss": 0.071, "lr": 4.738822469435477e-05, "epoch": 4.642464246424643, "percentage": 23.21, "elapsed_time": "1:39:24", "remaining_time": "5:28:50", "throughput": 1493.0, "total_tokens": 8904640} {"current_steps": 42205, "total_steps": 181800, "loss": 0.0647, "lr": 4.738715655340938e-05, "epoch": 4.643014301430143, "percentage": 23.22, "elapsed_time": "1:39:24", "remaining_time": "5:28:49", "throughput": 1493.01, "total_tokens": 8905760} {"current_steps": 42210, "total_steps": 181800, "loss": 0.0282, "lr": 4.738608820613231e-05, "epoch": 4.643564356435643, "percentage": 23.22, "elapsed_time": "1:39:25", "remaining_time": "5:28:48", "throughput": 1493.02, "total_tokens": 8906816} {"current_steps": 42215, "total_steps": 181800, "loss": 0.048, "lr": 4.73850196525334e-05, "epoch": 4.644114411441144, "percentage": 23.22, "elapsed_time": "1:39:26", "remaining_time": "5:28:47", "throughput": 1493.01, "total_tokens": 8907776} {"current_steps": 42220, "total_steps": 181800, "loss": 0.0465, "lr": 4.7383950892622506e-05, "epoch": 4.6446644664466445, "percentage": 23.22, "elapsed_time": "1:39:27", "remaining_time": "5:28:47", "throughput": 1493.02, "total_tokens": 8908864} {"current_steps": 42225, "total_steps": 181800, "loss": 0.1327, "lr": 4.738288192640949e-05, "epoch": 4.645214521452145, "percentage": 23.23, "elapsed_time": "1:39:27", "remaining_time": "5:28:46", "throughput": 1493.01, "total_tokens": 8909888} {"current_steps": 42230, "total_steps": 181800, "loss": 0.0732, "lr": 4.7381812753904176e-05, "epoch": 4.645764576457646, "percentage": 23.23, "elapsed_time": "1:39:28", "remaining_time": "5:28:45", "throughput": 1493.01, "total_tokens": 8910880} {"current_steps": 42235, "total_steps": 181800, "loss": 0.0094, "lr": 4.7380743375116445e-05, "epoch": 4.646314631463146, "percentage": 23.23, "elapsed_time": "1:39:29", "remaining_time": "5:28:44", "throughput": 1493.02, "total_tokens": 8911968} {"current_steps": 42240, "total_steps": 181800, "loss": 0.0268, "lr": 4.7379673790056133e-05, "epoch": 4.646864686468647, "percentage": 23.23, "elapsed_time": "1:39:29", "remaining_time": "5:28:44", "throughput": 1493.03, "total_tokens": 8913056} {"current_steps": 42245, "total_steps": 181800, "loss": 0.0298, "lr": 4.7378603998733115e-05, "epoch": 4.647414741474147, "percentage": 23.24, "elapsed_time": "1:39:30", "remaining_time": "5:28:43", "throughput": 1492.98, "total_tokens": 8914080} {"current_steps": 42250, "total_steps": 181800, "loss": 0.0592, "lr": 4.7377534001157235e-05, "epoch": 4.647964796479648, "percentage": 23.24, "elapsed_time": "1:39:31", "remaining_time": "5:28:43", "throughput": 1492.98, "total_tokens": 8915136} {"current_steps": 42255, "total_steps": 181800, "loss": 0.0557, "lr": 4.7376463797338366e-05, "epoch": 4.648514851485149, "percentage": 23.24, "elapsed_time": "1:39:32", "remaining_time": "5:28:42", "throughput": 1492.99, "total_tokens": 8916224} {"current_steps": 42260, "total_steps": 181800, "loss": 0.0588, "lr": 4.737539338728637e-05, "epoch": 4.649064906490649, "percentage": 23.25, "elapsed_time": "1:39:32", "remaining_time": "5:28:41", "throughput": 1493.0, "total_tokens": 8917280} {"current_steps": 42265, "total_steps": 181800, "loss": 0.0263, "lr": 4.73743227710111e-05, "epoch": 4.64961496149615, "percentage": 23.25, "elapsed_time": "1:39:33", "remaining_time": "5:28:40", "throughput": 1493.0, "total_tokens": 8918336} {"current_steps": 42270, "total_steps": 181800, "loss": 0.0917, "lr": 4.737325194852244e-05, "epoch": 4.65016501650165, "percentage": 23.25, "elapsed_time": "1:39:34", "remaining_time": "5:28:40", "throughput": 1493.01, "total_tokens": 8919392} {"current_steps": 42275, "total_steps": 181800, "loss": 0.0292, "lr": 4.737218091983026e-05, "epoch": 4.65071507150715, "percentage": 23.25, "elapsed_time": "1:39:34", "remaining_time": "5:28:39", "throughput": 1493.01, "total_tokens": 8920416} {"current_steps": 42280, "total_steps": 181800, "loss": 0.103, "lr": 4.7371109684944406e-05, "epoch": 4.6512651265126514, "percentage": 23.26, "elapsed_time": "1:39:35", "remaining_time": "5:28:38", "throughput": 1493.02, "total_tokens": 8921504} {"current_steps": 42285, "total_steps": 181800, "loss": 0.0213, "lr": 4.7370038243874785e-05, "epoch": 4.651815181518152, "percentage": 23.26, "elapsed_time": "1:39:36", "remaining_time": "5:28:37", "throughput": 1493.02, "total_tokens": 8922592} {"current_steps": 42290, "total_steps": 181800, "loss": 0.0272, "lr": 4.7368966596631245e-05, "epoch": 4.652365236523653, "percentage": 23.26, "elapsed_time": "1:39:36", "remaining_time": "5:28:37", "throughput": 1493.02, "total_tokens": 8923584} {"current_steps": 42295, "total_steps": 181800, "loss": 0.07, "lr": 4.736789474322368e-05, "epoch": 4.652915291529153, "percentage": 23.26, "elapsed_time": "1:39:37", "remaining_time": "5:28:36", "throughput": 1493.04, "total_tokens": 8924736} {"current_steps": 42300, "total_steps": 181800, "loss": 0.199, "lr": 4.736682268366196e-05, "epoch": 4.653465346534653, "percentage": 23.27, "elapsed_time": "1:39:38", "remaining_time": "5:28:35", "throughput": 1493.04, "total_tokens": 8925760} {"current_steps": 42305, "total_steps": 181800, "loss": 0.0094, "lr": 4.736575041795597e-05, "epoch": 4.654015401540154, "percentage": 23.27, "elapsed_time": "1:39:38", "remaining_time": "5:28:34", "throughput": 1493.03, "total_tokens": 8926720} {"current_steps": 42310, "total_steps": 181800, "loss": 0.0571, "lr": 4.736467794611558e-05, "epoch": 4.6545654565456545, "percentage": 23.27, "elapsed_time": "1:39:39", "remaining_time": "5:28:33", "throughput": 1493.03, "total_tokens": 8927776} {"current_steps": 42315, "total_steps": 181800, "loss": 0.095, "lr": 4.7363605268150704e-05, "epoch": 4.6551155115511555, "percentage": 23.28, "elapsed_time": "1:39:40", "remaining_time": "5:28:33", "throughput": 1493.04, "total_tokens": 8928864} {"current_steps": 42320, "total_steps": 181800, "loss": 0.0442, "lr": 4.736253238407119e-05, "epoch": 4.655665566556656, "percentage": 23.28, "elapsed_time": "1:39:41", "remaining_time": "5:28:32", "throughput": 1493.06, "total_tokens": 8929984} {"current_steps": 42325, "total_steps": 181800, "loss": 0.0094, "lr": 4.7361459293886956e-05, "epoch": 4.656215621562156, "percentage": 23.28, "elapsed_time": "1:39:41", "remaining_time": "5:28:31", "throughput": 1493.06, "total_tokens": 8931008} {"current_steps": 42330, "total_steps": 181800, "loss": 0.0409, "lr": 4.736038599760788e-05, "epoch": 4.656765676567657, "percentage": 23.28, "elapsed_time": "1:39:42", "remaining_time": "5:28:30", "throughput": 1493.06, "total_tokens": 8932064} {"current_steps": 42335, "total_steps": 181800, "loss": 0.0177, "lr": 4.735931249524386e-05, "epoch": 4.657315731573157, "percentage": 23.29, "elapsed_time": "1:39:43", "remaining_time": "5:28:30", "throughput": 1493.06, "total_tokens": 8933056} {"current_steps": 42340, "total_steps": 181800, "loss": 0.1042, "lr": 4.735823878680478e-05, "epoch": 4.6578657865786575, "percentage": 23.29, "elapsed_time": "1:39:43", "remaining_time": "5:28:29", "throughput": 1493.06, "total_tokens": 8934112} {"current_steps": 42345, "total_steps": 181800, "loss": 0.0127, "lr": 4.735716487230054e-05, "epoch": 4.658415841584159, "percentage": 23.29, "elapsed_time": "1:39:44", "remaining_time": "5:28:28", "throughput": 1493.07, "total_tokens": 8935168} {"current_steps": 42350, "total_steps": 181800, "loss": 0.0493, "lr": 4.735609075174105e-05, "epoch": 4.658965896589659, "percentage": 23.29, "elapsed_time": "1:39:45", "remaining_time": "5:28:27", "throughput": 1493.06, "total_tokens": 8936192} {"current_steps": 42355, "total_steps": 181800, "loss": 0.0934, "lr": 4.735501642513619e-05, "epoch": 4.65951595159516, "percentage": 23.3, "elapsed_time": "1:39:45", "remaining_time": "5:28:27", "throughput": 1493.07, "total_tokens": 8937248} {"current_steps": 42360, "total_steps": 181800, "loss": 0.0889, "lr": 4.735394189249587e-05, "epoch": 4.66006600660066, "percentage": 23.3, "elapsed_time": "1:39:46", "remaining_time": "5:28:26", "throughput": 1493.08, "total_tokens": 8938368} {"current_steps": 42365, "total_steps": 181800, "loss": 0.0784, "lr": 4.7352867153829994e-05, "epoch": 4.66061606160616, "percentage": 23.3, "elapsed_time": "1:39:47", "remaining_time": "5:28:25", "throughput": 1493.08, "total_tokens": 8939392} {"current_steps": 42370, "total_steps": 181800, "loss": 0.0232, "lr": 4.735179220914847e-05, "epoch": 4.661166116611661, "percentage": 23.31, "elapsed_time": "1:39:47", "remaining_time": "5:28:24", "throughput": 1493.09, "total_tokens": 8940480} {"current_steps": 42375, "total_steps": 181800, "loss": 0.0933, "lr": 4.7350717058461205e-05, "epoch": 4.661716171617162, "percentage": 23.31, "elapsed_time": "1:39:48", "remaining_time": "5:28:24", "throughput": 1493.09, "total_tokens": 8941504} {"current_steps": 42380, "total_steps": 181800, "loss": 0.0921, "lr": 4.73496417017781e-05, "epoch": 4.662266226622663, "percentage": 23.31, "elapsed_time": "1:39:49", "remaining_time": "5:28:23", "throughput": 1493.09, "total_tokens": 8942528} {"current_steps": 42385, "total_steps": 181800, "loss": 0.0414, "lr": 4.734856613910907e-05, "epoch": 4.662816281628163, "percentage": 23.31, "elapsed_time": "1:39:49", "remaining_time": "5:28:22", "throughput": 1493.1, "total_tokens": 8943616} {"current_steps": 42390, "total_steps": 181800, "loss": 0.024, "lr": 4.734749037046404e-05, "epoch": 4.663366336633663, "percentage": 23.32, "elapsed_time": "1:39:50", "remaining_time": "5:28:21", "throughput": 1493.1, "total_tokens": 8944672} {"current_steps": 42395, "total_steps": 181800, "loss": 0.0573, "lr": 4.734641439585291e-05, "epoch": 4.663916391639164, "percentage": 23.32, "elapsed_time": "1:39:51", "remaining_time": "5:28:21", "throughput": 1493.1, "total_tokens": 8945664} {"current_steps": 42400, "total_steps": 181800, "loss": 0.1449, "lr": 4.73453382152856e-05, "epoch": 4.664466446644664, "percentage": 23.32, "elapsed_time": "1:39:52", "remaining_time": "5:28:20", "throughput": 1493.11, "total_tokens": 8946752} {"current_steps": 42405, "total_steps": 181800, "loss": 0.0831, "lr": 4.734426182877203e-05, "epoch": 4.665016501650165, "percentage": 23.33, "elapsed_time": "1:39:52", "remaining_time": "5:28:19", "throughput": 1493.12, "total_tokens": 8947872} {"current_steps": 42410, "total_steps": 181800, "loss": 0.0371, "lr": 4.734318523632212e-05, "epoch": 4.665566556655666, "percentage": 23.33, "elapsed_time": "1:39:53", "remaining_time": "5:28:18", "throughput": 1493.12, "total_tokens": 8948896} {"current_steps": 42415, "total_steps": 181800, "loss": 0.0914, "lr": 4.73421084379458e-05, "epoch": 4.666116611661166, "percentage": 23.33, "elapsed_time": "1:39:54", "remaining_time": "5:28:17", "throughput": 1493.11, "total_tokens": 8949888} {"current_steps": 42420, "total_steps": 181800, "loss": 0.0404, "lr": 4.7341031433652976e-05, "epoch": 4.666666666666667, "percentage": 23.33, "elapsed_time": "1:39:54", "remaining_time": "5:28:17", "throughput": 1493.12, "total_tokens": 8950944} {"current_steps": 42425, "total_steps": 181800, "loss": 0.0272, "lr": 4.73399542234536e-05, "epoch": 4.667216721672167, "percentage": 23.34, "elapsed_time": "1:39:55", "remaining_time": "5:28:16", "throughput": 1493.12, "total_tokens": 8952032} {"current_steps": 42430, "total_steps": 181800, "loss": 0.0815, "lr": 4.733887680735757e-05, "epoch": 4.667766776677668, "percentage": 23.34, "elapsed_time": "1:39:56", "remaining_time": "5:28:15", "throughput": 1493.12, "total_tokens": 8953056} {"current_steps": 42435, "total_steps": 181800, "loss": 0.0488, "lr": 4.7337799185374844e-05, "epoch": 4.6683168316831685, "percentage": 23.34, "elapsed_time": "1:39:56", "remaining_time": "5:28:14", "throughput": 1493.13, "total_tokens": 8954144} {"current_steps": 42440, "total_steps": 181800, "loss": 0.0642, "lr": 4.7336721357515335e-05, "epoch": 4.668866886688669, "percentage": 23.34, "elapsed_time": "1:39:57", "remaining_time": "5:28:14", "throughput": 1493.13, "total_tokens": 8955168} {"current_steps": 42445, "total_steps": 181800, "loss": 0.0739, "lr": 4.733564332378898e-05, "epoch": 4.66941694169417, "percentage": 23.35, "elapsed_time": "1:39:58", "remaining_time": "5:28:13", "throughput": 1493.13, "total_tokens": 8956192} {"current_steps": 42450, "total_steps": 181800, "loss": 0.054, "lr": 4.7334565084205724e-05, "epoch": 4.66996699669967, "percentage": 23.35, "elapsed_time": "1:39:58", "remaining_time": "5:28:12", "throughput": 1493.13, "total_tokens": 8957216} {"current_steps": 42455, "total_steps": 181800, "loss": 0.0354, "lr": 4.7333486638775496e-05, "epoch": 4.67051705170517, "percentage": 23.35, "elapsed_time": "1:39:59", "remaining_time": "5:28:11", "throughput": 1493.14, "total_tokens": 8958304} {"current_steps": 42460, "total_steps": 181800, "loss": 0.0431, "lr": 4.7332407987508246e-05, "epoch": 4.671067106710671, "percentage": 23.36, "elapsed_time": "1:40:00", "remaining_time": "5:28:11", "throughput": 1493.14, "total_tokens": 8959328} {"current_steps": 42465, "total_steps": 181800, "loss": 0.0127, "lr": 4.733132913041389e-05, "epoch": 4.6716171617161715, "percentage": 23.36, "elapsed_time": "1:40:01", "remaining_time": "5:28:10", "throughput": 1493.14, "total_tokens": 8960384} {"current_steps": 42470, "total_steps": 181800, "loss": 0.0113, "lr": 4.733025006750241e-05, "epoch": 4.672167216721672, "percentage": 23.36, "elapsed_time": "1:40:01", "remaining_time": "5:28:09", "throughput": 1493.15, "total_tokens": 8961472} {"current_steps": 42475, "total_steps": 181800, "loss": 0.0377, "lr": 4.732917079878372e-05, "epoch": 4.672717271727173, "percentage": 23.36, "elapsed_time": "1:40:02", "remaining_time": "5:28:08", "throughput": 1493.15, "total_tokens": 8962528} {"current_steps": 42480, "total_steps": 181800, "loss": 0.2108, "lr": 4.7328091324267774e-05, "epoch": 4.673267326732673, "percentage": 23.37, "elapsed_time": "1:40:03", "remaining_time": "5:28:08", "throughput": 1493.16, "total_tokens": 8963616} {"current_steps": 42485, "total_steps": 181800, "loss": 0.0245, "lr": 4.732701164396453e-05, "epoch": 4.673817381738174, "percentage": 23.37, "elapsed_time": "1:40:03", "remaining_time": "5:28:07", "throughput": 1493.16, "total_tokens": 8964640} {"current_steps": 42490, "total_steps": 181800, "loss": 0.0359, "lr": 4.7325931757883934e-05, "epoch": 4.674367436743674, "percentage": 23.37, "elapsed_time": "1:40:04", "remaining_time": "5:28:06", "throughput": 1493.18, "total_tokens": 8965760} {"current_steps": 42495, "total_steps": 181800, "loss": 0.1318, "lr": 4.732485166603593e-05, "epoch": 4.674917491749175, "percentage": 23.37, "elapsed_time": "1:40:05", "remaining_time": "5:28:05", "throughput": 1493.17, "total_tokens": 8966784} {"current_steps": 42500, "total_steps": 181800, "loss": 0.1104, "lr": 4.732377136843049e-05, "epoch": 4.675467546754676, "percentage": 23.38, "elapsed_time": "1:40:05", "remaining_time": "5:28:05", "throughput": 1493.18, "total_tokens": 8967872} {"current_steps": 42505, "total_steps": 181800, "loss": 0.0134, "lr": 4.7322690865077554e-05, "epoch": 4.676017601760176, "percentage": 23.38, "elapsed_time": "1:40:06", "remaining_time": "5:28:04", "throughput": 1493.19, "total_tokens": 8968960} {"current_steps": 42510, "total_steps": 181800, "loss": 0.0359, "lr": 4.732161015598709e-05, "epoch": 4.676567656765677, "percentage": 23.38, "elapsed_time": "1:40:07", "remaining_time": "5:28:03", "throughput": 1493.18, "total_tokens": 8969952} {"current_steps": 42515, "total_steps": 181800, "loss": 0.0118, "lr": 4.7320529241169065e-05, "epoch": 4.677117711771177, "percentage": 23.39, "elapsed_time": "1:40:07", "remaining_time": "5:28:02", "throughput": 1493.19, "total_tokens": 8971008} {"current_steps": 42520, "total_steps": 181800, "loss": 0.1233, "lr": 4.731944812063343e-05, "epoch": 4.677667766776677, "percentage": 23.39, "elapsed_time": "1:40:08", "remaining_time": "5:28:02", "throughput": 1493.2, "total_tokens": 8972096} {"current_steps": 42525, "total_steps": 181800, "loss": 0.0639, "lr": 4.731836679439014e-05, "epoch": 4.678217821782178, "percentage": 23.39, "elapsed_time": "1:40:09", "remaining_time": "5:28:01", "throughput": 1493.2, "total_tokens": 8973120} {"current_steps": 42530, "total_steps": 181800, "loss": 0.0991, "lr": 4.731728526244918e-05, "epoch": 4.678767876787679, "percentage": 23.39, "elapsed_time": "1:40:10", "remaining_time": "5:28:00", "throughput": 1493.21, "total_tokens": 8974240} {"current_steps": 42535, "total_steps": 181800, "loss": 0.0312, "lr": 4.7316203524820504e-05, "epoch": 4.67931793179318, "percentage": 23.4, "elapsed_time": "1:40:10", "remaining_time": "5:27:59", "throughput": 1493.21, "total_tokens": 8975296} {"current_steps": 42540, "total_steps": 181800, "loss": 0.0481, "lr": 4.73151215815141e-05, "epoch": 4.67986798679868, "percentage": 23.4, "elapsed_time": "1:40:11", "remaining_time": "5:27:59", "throughput": 1493.2, "total_tokens": 8976256} {"current_steps": 42545, "total_steps": 181800, "loss": 0.037, "lr": 4.7314039432539924e-05, "epoch": 4.68041804180418, "percentage": 23.4, "elapsed_time": "1:40:12", "remaining_time": "5:27:58", "throughput": 1493.21, "total_tokens": 8977312} {"current_steps": 42550, "total_steps": 181800, "loss": 0.015, "lr": 4.731295707790795e-05, "epoch": 4.680968096809681, "percentage": 23.4, "elapsed_time": "1:40:12", "remaining_time": "5:27:57", "throughput": 1493.21, "total_tokens": 8978336} {"current_steps": 42555, "total_steps": 181800, "loss": 0.0418, "lr": 4.731187451762816e-05, "epoch": 4.681518151815181, "percentage": 23.41, "elapsed_time": "1:40:13", "remaining_time": "5:27:56", "throughput": 1493.21, "total_tokens": 8979360} {"current_steps": 42560, "total_steps": 181800, "loss": 0.0344, "lr": 4.7310791751710526e-05, "epoch": 4.6820682068206825, "percentage": 23.41, "elapsed_time": "1:40:14", "remaining_time": "5:27:56", "throughput": 1493.21, "total_tokens": 8980416} {"current_steps": 42565, "total_steps": 181800, "loss": 0.0413, "lr": 4.7309708780165036e-05, "epoch": 4.682618261826183, "percentage": 23.41, "elapsed_time": "1:40:14", "remaining_time": "5:27:55", "throughput": 1493.21, "total_tokens": 8981440} {"current_steps": 42570, "total_steps": 181800, "loss": 0.0492, "lr": 4.730862560300166e-05, "epoch": 4.683168316831683, "percentage": 23.42, "elapsed_time": "1:40:15", "remaining_time": "5:27:54", "throughput": 1493.22, "total_tokens": 8982528} {"current_steps": 42575, "total_steps": 181800, "loss": 0.0234, "lr": 4.730754222023039e-05, "epoch": 4.683718371837184, "percentage": 23.42, "elapsed_time": "1:40:16", "remaining_time": "5:27:53", "throughput": 1493.22, "total_tokens": 8983584} {"current_steps": 42580, "total_steps": 181800, "loss": 0.0986, "lr": 4.7306458631861205e-05, "epoch": 4.684268426842684, "percentage": 23.42, "elapsed_time": "1:40:16", "remaining_time": "5:27:53", "throughput": 1493.24, "total_tokens": 8984704} {"current_steps": 42585, "total_steps": 181800, "loss": 0.0525, "lr": 4.730537483790409e-05, "epoch": 4.684818481848184, "percentage": 23.42, "elapsed_time": "1:40:17", "remaining_time": "5:27:52", "throughput": 1493.23, "total_tokens": 8985728} {"current_steps": 42590, "total_steps": 181800, "loss": 0.017, "lr": 4.730429083836905e-05, "epoch": 4.6853685368536855, "percentage": 23.43, "elapsed_time": "1:40:18", "remaining_time": "5:27:51", "throughput": 1493.24, "total_tokens": 8986784} {"current_steps": 42595, "total_steps": 181800, "loss": 0.0033, "lr": 4.7303206633266064e-05, "epoch": 4.685918591859186, "percentage": 23.43, "elapsed_time": "1:40:19", "remaining_time": "5:27:50", "throughput": 1493.24, "total_tokens": 8987840} {"current_steps": 42600, "total_steps": 181800, "loss": 0.0344, "lr": 4.730212222260512e-05, "epoch": 4.686468646864687, "percentage": 23.43, "elapsed_time": "1:40:19", "remaining_time": "5:27:50", "throughput": 1493.25, "total_tokens": 8988896} {"current_steps": 42605, "total_steps": 181800, "loss": 0.0742, "lr": 4.730103760639621e-05, "epoch": 4.687018701870187, "percentage": 23.44, "elapsed_time": "1:40:20", "remaining_time": "5:27:49", "throughput": 1493.25, "total_tokens": 8989984} {"current_steps": 42610, "total_steps": 181800, "loss": 0.0807, "lr": 4.729995278464934e-05, "epoch": 4.687568756875687, "percentage": 23.44, "elapsed_time": "1:40:21", "remaining_time": "5:27:48", "throughput": 1493.25, "total_tokens": 8991008} {"current_steps": 42615, "total_steps": 181800, "loss": 0.029, "lr": 4.729886775737451e-05, "epoch": 4.688118811881188, "percentage": 23.44, "elapsed_time": "1:40:21", "remaining_time": "5:27:47", "throughput": 1493.25, "total_tokens": 8992000} {"current_steps": 42620, "total_steps": 181800, "loss": 0.1147, "lr": 4.729778252458171e-05, "epoch": 4.6886688668866885, "percentage": 23.44, "elapsed_time": "1:40:22", "remaining_time": "5:27:46", "throughput": 1493.25, "total_tokens": 8993056} {"current_steps": 42625, "total_steps": 181800, "loss": 0.0811, "lr": 4.729669708628096e-05, "epoch": 4.68921892189219, "percentage": 23.45, "elapsed_time": "1:40:23", "remaining_time": "5:27:46", "throughput": 1493.26, "total_tokens": 8994112} {"current_steps": 42630, "total_steps": 181800, "loss": 0.044, "lr": 4.7295611442482244e-05, "epoch": 4.68976897689769, "percentage": 23.45, "elapsed_time": "1:40:23", "remaining_time": "5:27:45", "throughput": 1493.26, "total_tokens": 8995168} {"current_steps": 42635, "total_steps": 181800, "loss": 0.0259, "lr": 4.729452559319558e-05, "epoch": 4.69031903190319, "percentage": 23.45, "elapsed_time": "1:40:24", "remaining_time": "5:27:44", "throughput": 1493.26, "total_tokens": 8996192} {"current_steps": 42640, "total_steps": 181800, "loss": 0.0099, "lr": 4.7293439538430964e-05, "epoch": 4.690869086908691, "percentage": 23.45, "elapsed_time": "1:40:25", "remaining_time": "5:27:43", "throughput": 1493.26, "total_tokens": 8997248} {"current_steps": 42645, "total_steps": 181800, "loss": 0.0552, "lr": 4.729235327819842e-05, "epoch": 4.691419141914191, "percentage": 23.46, "elapsed_time": "1:40:25", "remaining_time": "5:27:43", "throughput": 1493.27, "total_tokens": 8998304} {"current_steps": 42650, "total_steps": 181800, "loss": 0.0906, "lr": 4.729126681250795e-05, "epoch": 4.6919691969196915, "percentage": 23.46, "elapsed_time": "1:40:26", "remaining_time": "5:27:42", "throughput": 1493.27, "total_tokens": 8999328} {"current_steps": 42655, "total_steps": 181800, "loss": 0.077, "lr": 4.7290180141369564e-05, "epoch": 4.692519251925193, "percentage": 23.46, "elapsed_time": "1:40:27", "remaining_time": "5:27:41", "throughput": 1493.27, "total_tokens": 9000352} {"current_steps": 42660, "total_steps": 181800, "loss": 0.0094, "lr": 4.7289093264793296e-05, "epoch": 4.693069306930693, "percentage": 23.47, "elapsed_time": "1:40:27", "remaining_time": "5:27:40", "throughput": 1493.28, "total_tokens": 9001440} {"current_steps": 42665, "total_steps": 181800, "loss": 0.0254, "lr": 4.728800618278915e-05, "epoch": 4.693619361936194, "percentage": 23.47, "elapsed_time": "1:40:28", "remaining_time": "5:27:40", "throughput": 1493.28, "total_tokens": 9002464} {"current_steps": 42670, "total_steps": 181800, "loss": 0.0151, "lr": 4.728691889536713e-05, "epoch": 4.694169416941694, "percentage": 23.47, "elapsed_time": "1:40:29", "remaining_time": "5:27:39", "throughput": 1493.29, "total_tokens": 9003552} {"current_steps": 42675, "total_steps": 181800, "loss": 0.0381, "lr": 4.728583140253728e-05, "epoch": 4.694719471947195, "percentage": 23.47, "elapsed_time": "1:40:30", "remaining_time": "5:27:38", "throughput": 1493.29, "total_tokens": 9004608} {"current_steps": 42680, "total_steps": 181800, "loss": 0.0987, "lr": 4.7284743704309626e-05, "epoch": 4.695269526952695, "percentage": 23.48, "elapsed_time": "1:40:30", "remaining_time": "5:27:37", "throughput": 1493.3, "total_tokens": 9005728} {"current_steps": 42685, "total_steps": 181800, "loss": 0.0828, "lr": 4.728365580069417e-05, "epoch": 4.695819581958196, "percentage": 23.48, "elapsed_time": "1:40:31", "remaining_time": "5:27:37", "throughput": 1493.32, "total_tokens": 9006848} {"current_steps": 42690, "total_steps": 181800, "loss": 0.0113, "lr": 4.7282567691700966e-05, "epoch": 4.696369636963697, "percentage": 23.48, "elapsed_time": "1:40:32", "remaining_time": "5:27:36", "throughput": 1493.32, "total_tokens": 9007872} {"current_steps": 42695, "total_steps": 181800, "loss": 0.059, "lr": 4.728147937734001e-05, "epoch": 4.696919691969197, "percentage": 23.48, "elapsed_time": "1:40:32", "remaining_time": "5:27:35", "throughput": 1493.31, "total_tokens": 9008864} {"current_steps": 42700, "total_steps": 181800, "loss": 0.0608, "lr": 4.728039085762136e-05, "epoch": 4.697469746974697, "percentage": 23.49, "elapsed_time": "1:40:33", "remaining_time": "5:27:34", "throughput": 1493.31, "total_tokens": 9009920} {"current_steps": 42705, "total_steps": 181800, "loss": 0.0305, "lr": 4.727930213255504e-05, "epoch": 4.698019801980198, "percentage": 23.49, "elapsed_time": "1:40:34", "remaining_time": "5:27:34", "throughput": 1493.31, "total_tokens": 9010944} {"current_steps": 42710, "total_steps": 181800, "loss": 0.072, "lr": 4.727821320215108e-05, "epoch": 4.698569856985698, "percentage": 23.49, "elapsed_time": "1:40:34", "remaining_time": "5:27:33", "throughput": 1493.32, "total_tokens": 9012032} {"current_steps": 42715, "total_steps": 181800, "loss": 0.0291, "lr": 4.727712406641952e-05, "epoch": 4.6991199119911995, "percentage": 23.5, "elapsed_time": "1:40:35", "remaining_time": "5:27:32", "throughput": 1493.34, "total_tokens": 9013184} {"current_steps": 42720, "total_steps": 181800, "loss": 0.0659, "lr": 4.72760347253704e-05, "epoch": 4.6996699669967, "percentage": 23.5, "elapsed_time": "1:40:36", "remaining_time": "5:27:31", "throughput": 1493.35, "total_tokens": 9014240} {"current_steps": 42725, "total_steps": 181800, "loss": 0.0251, "lr": 4.727494517901375e-05, "epoch": 4.7002200220022, "percentage": 23.5, "elapsed_time": "1:40:36", "remaining_time": "5:27:30", "throughput": 1493.36, "total_tokens": 9015328} {"current_steps": 42730, "total_steps": 181800, "loss": 0.0586, "lr": 4.727385542735962e-05, "epoch": 4.700770077007701, "percentage": 23.5, "elapsed_time": "1:40:37", "remaining_time": "5:27:30", "throughput": 1493.36, "total_tokens": 9016352} {"current_steps": 42735, "total_steps": 181800, "loss": 0.0488, "lr": 4.727276547041805e-05, "epoch": 4.701320132013201, "percentage": 23.51, "elapsed_time": "1:40:38", "remaining_time": "5:27:29", "throughput": 1493.36, "total_tokens": 9017408} {"current_steps": 42740, "total_steps": 181800, "loss": 0.0725, "lr": 4.7271675308199106e-05, "epoch": 4.701870187018702, "percentage": 23.51, "elapsed_time": "1:40:39", "remaining_time": "5:27:28", "throughput": 1493.36, "total_tokens": 9018432} {"current_steps": 42745, "total_steps": 181800, "loss": 0.0378, "lr": 4.72705849407128e-05, "epoch": 4.7024202420242025, "percentage": 23.51, "elapsed_time": "1:40:39", "remaining_time": "5:27:27", "throughput": 1493.36, "total_tokens": 9019456} {"current_steps": 42750, "total_steps": 181800, "loss": 0.059, "lr": 4.72694943679692e-05, "epoch": 4.702970297029703, "percentage": 23.51, "elapsed_time": "1:40:40", "remaining_time": "5:27:27", "throughput": 1493.36, "total_tokens": 9020480} {"current_steps": 42755, "total_steps": 181800, "loss": 0.0539, "lr": 4.726840358997836e-05, "epoch": 4.703520352035204, "percentage": 23.52, "elapsed_time": "1:40:41", "remaining_time": "5:27:26", "throughput": 1493.36, "total_tokens": 9021504} {"current_steps": 42760, "total_steps": 181800, "loss": 0.0485, "lr": 4.7267312606750334e-05, "epoch": 4.704070407040704, "percentage": 23.52, "elapsed_time": "1:40:41", "remaining_time": "5:27:25", "throughput": 1493.35, "total_tokens": 9022496} {"current_steps": 42765, "total_steps": 181800, "loss": 0.1899, "lr": 4.726622141829516e-05, "epoch": 4.704620462046204, "percentage": 23.52, "elapsed_time": "1:40:42", "remaining_time": "5:27:24", "throughput": 1493.35, "total_tokens": 9023520} {"current_steps": 42770, "total_steps": 181800, "loss": 0.0487, "lr": 4.726513002462292e-05, "epoch": 4.705170517051705, "percentage": 23.53, "elapsed_time": "1:40:43", "remaining_time": "5:27:24", "throughput": 1493.34, "total_tokens": 9024512} {"current_steps": 42775, "total_steps": 181800, "loss": 0.065, "lr": 4.726403842574366e-05, "epoch": 4.7057205720572055, "percentage": 23.53, "elapsed_time": "1:40:43", "remaining_time": "5:27:23", "throughput": 1493.35, "total_tokens": 9025568} {"current_steps": 42780, "total_steps": 181800, "loss": 0.0091, "lr": 4.7262946621667435e-05, "epoch": 4.706270627062707, "percentage": 23.53, "elapsed_time": "1:40:44", "remaining_time": "5:27:22", "throughput": 1493.36, "total_tokens": 9026656} {"current_steps": 42785, "total_steps": 181800, "loss": 0.149, "lr": 4.7261854612404316e-05, "epoch": 4.706820682068207, "percentage": 23.53, "elapsed_time": "1:40:45", "remaining_time": "5:27:21", "throughput": 1493.37, "total_tokens": 9027744} {"current_steps": 42790, "total_steps": 181800, "loss": 0.0159, "lr": 4.7260762397964365e-05, "epoch": 4.707370737073707, "percentage": 23.54, "elapsed_time": "1:40:45", "remaining_time": "5:27:21", "throughput": 1493.36, "total_tokens": 9028768} {"current_steps": 42795, "total_steps": 181800, "loss": 0.0556, "lr": 4.725966997835765e-05, "epoch": 4.707920792079208, "percentage": 23.54, "elapsed_time": "1:40:46", "remaining_time": "5:27:20", "throughput": 1493.36, "total_tokens": 9029792} {"current_steps": 42800, "total_steps": 181800, "loss": 0.0449, "lr": 4.7258577353594235e-05, "epoch": 4.708470847084708, "percentage": 23.54, "elapsed_time": "1:40:47", "remaining_time": "5:27:19", "throughput": 1493.37, "total_tokens": 9030848} {"current_steps": 42805, "total_steps": 181800, "loss": 0.0291, "lr": 4.72574845236842e-05, "epoch": 4.709020902090209, "percentage": 23.55, "elapsed_time": "1:40:47", "remaining_time": "5:27:18", "throughput": 1493.37, "total_tokens": 9031904} {"current_steps": 42810, "total_steps": 181800, "loss": 0.0883, "lr": 4.7256391488637606e-05, "epoch": 4.70957095709571, "percentage": 23.55, "elapsed_time": "1:40:48", "remaining_time": "5:27:18", "throughput": 1493.38, "total_tokens": 9032992} {"current_steps": 42815, "total_steps": 181800, "loss": 0.078, "lr": 4.725529824846453e-05, "epoch": 4.71012101210121, "percentage": 23.55, "elapsed_time": "1:40:49", "remaining_time": "5:27:17", "throughput": 1493.39, "total_tokens": 9034048} {"current_steps": 42820, "total_steps": 181800, "loss": 0.0124, "lr": 4.725420480317505e-05, "epoch": 4.710671067106711, "percentage": 23.55, "elapsed_time": "1:40:50", "remaining_time": "5:27:16", "throughput": 1493.39, "total_tokens": 9035072} {"current_steps": 42825, "total_steps": 181800, "loss": 0.0678, "lr": 4.725311115277924e-05, "epoch": 4.711221122112211, "percentage": 23.56, "elapsed_time": "1:40:50", "remaining_time": "5:27:15", "throughput": 1493.39, "total_tokens": 9036128} {"current_steps": 42830, "total_steps": 181800, "loss": 0.0205, "lr": 4.7252017297287186e-05, "epoch": 4.711771177117711, "percentage": 23.56, "elapsed_time": "1:40:51", "remaining_time": "5:27:15", "throughput": 1493.39, "total_tokens": 9037152} {"current_steps": 42835, "total_steps": 181800, "loss": 0.0198, "lr": 4.725092323670897e-05, "epoch": 4.712321232123212, "percentage": 23.56, "elapsed_time": "1:40:52", "remaining_time": "5:27:14", "throughput": 1493.39, "total_tokens": 9038208} {"current_steps": 42840, "total_steps": 181800, "loss": 0.0375, "lr": 4.7249828971054664e-05, "epoch": 4.712871287128713, "percentage": 23.56, "elapsed_time": "1:40:52", "remaining_time": "5:27:13", "throughput": 1493.4, "total_tokens": 9039264} {"current_steps": 42845, "total_steps": 181800, "loss": 0.0106, "lr": 4.7248734500334366e-05, "epoch": 4.713421342134214, "percentage": 23.57, "elapsed_time": "1:40:53", "remaining_time": "5:27:12", "throughput": 1493.4, "total_tokens": 9040288} {"current_steps": 42850, "total_steps": 181800, "loss": 0.0342, "lr": 4.724763982455815e-05, "epoch": 4.713971397139714, "percentage": 23.57, "elapsed_time": "1:40:54", "remaining_time": "5:27:11", "throughput": 1493.4, "total_tokens": 9041344} {"current_steps": 42855, "total_steps": 181800, "loss": 0.0279, "lr": 4.724654494373613e-05, "epoch": 4.714521452145215, "percentage": 23.57, "elapsed_time": "1:40:54", "remaining_time": "5:27:11", "throughput": 1493.4, "total_tokens": 9042368} {"current_steps": 42860, "total_steps": 181800, "loss": 0.0093, "lr": 4.7245449857878365e-05, "epoch": 4.715071507150715, "percentage": 23.58, "elapsed_time": "1:40:55", "remaining_time": "5:27:10", "throughput": 1493.4, "total_tokens": 9043424} {"current_steps": 42865, "total_steps": 181800, "loss": 0.0715, "lr": 4.724435456699497e-05, "epoch": 4.715621562156215, "percentage": 23.58, "elapsed_time": "1:40:56", "remaining_time": "5:27:09", "throughput": 1493.4, "total_tokens": 9044448} {"current_steps": 42870, "total_steps": 181800, "loss": 0.0639, "lr": 4.724325907109603e-05, "epoch": 4.7161716171617165, "percentage": 23.58, "elapsed_time": "1:40:56", "remaining_time": "5:27:08", "throughput": 1493.41, "total_tokens": 9045504} {"current_steps": 42875, "total_steps": 181800, "loss": 0.0336, "lr": 4.724216337019165e-05, "epoch": 4.716721672167217, "percentage": 23.58, "elapsed_time": "1:40:57", "remaining_time": "5:27:08", "throughput": 1493.41, "total_tokens": 9046560} {"current_steps": 42880, "total_steps": 181800, "loss": 0.0177, "lr": 4.724106746429191e-05, "epoch": 4.717271727172717, "percentage": 23.59, "elapsed_time": "1:40:58", "remaining_time": "5:27:07", "throughput": 1493.42, "total_tokens": 9047648} {"current_steps": 42885, "total_steps": 181800, "loss": 0.0136, "lr": 4.7239971353406936e-05, "epoch": 4.717821782178218, "percentage": 23.59, "elapsed_time": "1:40:59", "remaining_time": "5:27:06", "throughput": 1493.42, "total_tokens": 9048672} {"current_steps": 42890, "total_steps": 181800, "loss": 0.1322, "lr": 4.723887503754681e-05, "epoch": 4.718371837183718, "percentage": 23.59, "elapsed_time": "1:40:59", "remaining_time": "5:27:05", "throughput": 1493.43, "total_tokens": 9049728} {"current_steps": 42895, "total_steps": 181800, "loss": 0.0538, "lr": 4.723777851672165e-05, "epoch": 4.718921892189218, "percentage": 23.59, "elapsed_time": "1:41:00", "remaining_time": "5:27:05", "throughput": 1493.43, "total_tokens": 9050784} {"current_steps": 42900, "total_steps": 181800, "loss": 0.1245, "lr": 4.7236681790941554e-05, "epoch": 4.7194719471947195, "percentage": 23.6, "elapsed_time": "1:41:01", "remaining_time": "5:27:04", "throughput": 1493.44, "total_tokens": 9051872} {"current_steps": 42905, "total_steps": 181800, "loss": 0.0325, "lr": 4.723558486021663e-05, "epoch": 4.72002200220022, "percentage": 23.6, "elapsed_time": "1:41:01", "remaining_time": "5:27:03", "throughput": 1493.44, "total_tokens": 9052864} {"current_steps": 42910, "total_steps": 181800, "loss": 0.0948, "lr": 4.7234487724557e-05, "epoch": 4.720572057205721, "percentage": 23.6, "elapsed_time": "1:41:02", "remaining_time": "5:27:02", "throughput": 1493.43, "total_tokens": 9053856} {"current_steps": 42915, "total_steps": 181800, "loss": 0.1433, "lr": 4.7233390383972754e-05, "epoch": 4.721122112211221, "percentage": 23.61, "elapsed_time": "1:41:03", "remaining_time": "5:27:02", "throughput": 1493.44, "total_tokens": 9054912} {"current_steps": 42920, "total_steps": 181800, "loss": 0.0263, "lr": 4.723229283847402e-05, "epoch": 4.721672167216722, "percentage": 23.61, "elapsed_time": "1:41:03", "remaining_time": "5:27:01", "throughput": 1493.45, "total_tokens": 9056000} {"current_steps": 42925, "total_steps": 181800, "loss": 0.0343, "lr": 4.723119508807091e-05, "epoch": 4.722222222222222, "percentage": 23.61, "elapsed_time": "1:41:04", "remaining_time": "5:27:00", "throughput": 1493.46, "total_tokens": 9057088} {"current_steps": 42930, "total_steps": 181800, "loss": 0.0657, "lr": 4.7230097132773545e-05, "epoch": 4.7227722772277225, "percentage": 23.61, "elapsed_time": "1:41:05", "remaining_time": "5:26:59", "throughput": 1493.46, "total_tokens": 9058144} {"current_steps": 42935, "total_steps": 181800, "loss": 0.0465, "lr": 4.722899897259204e-05, "epoch": 4.723322332233224, "percentage": 23.62, "elapsed_time": "1:41:05", "remaining_time": "5:26:58", "throughput": 1493.48, "total_tokens": 9059264} {"current_steps": 42940, "total_steps": 181800, "loss": 0.0727, "lr": 4.7227900607536525e-05, "epoch": 4.723872387238724, "percentage": 23.62, "elapsed_time": "1:41:06", "remaining_time": "5:26:58", "throughput": 1493.47, "total_tokens": 9060256} {"current_steps": 42945, "total_steps": 181800, "loss": 0.1143, "lr": 4.7226802037617105e-05, "epoch": 4.724422442244224, "percentage": 23.62, "elapsed_time": "1:41:07", "remaining_time": "5:26:57", "throughput": 1493.48, "total_tokens": 9061344} {"current_steps": 42950, "total_steps": 181800, "loss": 0.0326, "lr": 4.7225703262843925e-05, "epoch": 4.724972497249725, "percentage": 23.62, "elapsed_time": "1:41:07", "remaining_time": "5:26:56", "throughput": 1493.47, "total_tokens": 9062336} {"current_steps": 42955, "total_steps": 181800, "loss": 0.016, "lr": 4.7224604283227095e-05, "epoch": 4.725522552255225, "percentage": 23.63, "elapsed_time": "1:41:08", "remaining_time": "5:26:55", "throughput": 1493.47, "total_tokens": 9063328} {"current_steps": 42960, "total_steps": 181800, "loss": 0.163, "lr": 4.722350509877676e-05, "epoch": 4.726072607260726, "percentage": 23.63, "elapsed_time": "1:41:09", "remaining_time": "5:26:55", "throughput": 1493.47, "total_tokens": 9064384} {"current_steps": 42965, "total_steps": 181800, "loss": 0.1064, "lr": 4.722240570950304e-05, "epoch": 4.726622662266227, "percentage": 23.63, "elapsed_time": "1:41:10", "remaining_time": "5:26:54", "throughput": 1493.47, "total_tokens": 9065408} {"current_steps": 42970, "total_steps": 181800, "loss": 0.0722, "lr": 4.722130611541606e-05, "epoch": 4.727172717271727, "percentage": 23.64, "elapsed_time": "1:41:10", "remaining_time": "5:26:53", "throughput": 1493.47, "total_tokens": 9066432} {"current_steps": 42975, "total_steps": 181800, "loss": 0.0081, "lr": 4.7220206316525976e-05, "epoch": 4.727722772277228, "percentage": 23.64, "elapsed_time": "1:41:11", "remaining_time": "5:26:52", "throughput": 1493.48, "total_tokens": 9067520} {"current_steps": 42980, "total_steps": 181800, "loss": 0.032, "lr": 4.721910631284291e-05, "epoch": 4.728272827282728, "percentage": 23.64, "elapsed_time": "1:41:12", "remaining_time": "5:26:52", "throughput": 1493.49, "total_tokens": 9068608} {"current_steps": 42985, "total_steps": 181800, "loss": 0.0226, "lr": 4.721800610437701e-05, "epoch": 4.728822882288229, "percentage": 23.64, "elapsed_time": "1:41:12", "remaining_time": "5:26:51", "throughput": 1493.51, "total_tokens": 9069760} {"current_steps": 42990, "total_steps": 181800, "loss": 0.0059, "lr": 4.7216905691138396e-05, "epoch": 4.729372937293729, "percentage": 23.65, "elapsed_time": "1:41:13", "remaining_time": "5:26:50", "throughput": 1493.52, "total_tokens": 9070880} {"current_steps": 42995, "total_steps": 181800, "loss": 0.0679, "lr": 4.721580507313723e-05, "epoch": 4.72992299229923, "percentage": 23.65, "elapsed_time": "1:41:14", "remaining_time": "5:26:49", "throughput": 1493.53, "total_tokens": 9071968} {"current_steps": 43000, "total_steps": 181800, "loss": 0.04, "lr": 4.721470425038365e-05, "epoch": 4.730473047304731, "percentage": 23.65, "elapsed_time": "1:41:14", "remaining_time": "5:26:49", "throughput": 1493.52, "total_tokens": 9072960} {"current_steps": 43005, "total_steps": 181800, "loss": 0.1045, "lr": 4.7213603222887795e-05, "epoch": 4.731023102310231, "percentage": 23.66, "elapsed_time": "1:41:15", "remaining_time": "5:26:48", "throughput": 1493.53, "total_tokens": 9074048} {"current_steps": 43010, "total_steps": 181800, "loss": 0.0271, "lr": 4.7212501990659816e-05, "epoch": 4.731573157315731, "percentage": 23.66, "elapsed_time": "1:41:16", "remaining_time": "5:26:47", "throughput": 1493.53, "total_tokens": 9075072} {"current_steps": 43015, "total_steps": 181800, "loss": 0.0237, "lr": 4.721140055370987e-05, "epoch": 4.732123212321232, "percentage": 23.66, "elapsed_time": "1:41:16", "remaining_time": "5:26:46", "throughput": 1493.53, "total_tokens": 9076096} {"current_steps": 43020, "total_steps": 181800, "loss": 0.0641, "lr": 4.7210298912048105e-05, "epoch": 4.732673267326732, "percentage": 23.66, "elapsed_time": "1:41:17", "remaining_time": "5:26:46", "throughput": 1493.54, "total_tokens": 9077184} {"current_steps": 43025, "total_steps": 181800, "loss": 0.0624, "lr": 4.7209197065684675e-05, "epoch": 4.7332233223322335, "percentage": 23.67, "elapsed_time": "1:41:18", "remaining_time": "5:26:45", "throughput": 1493.54, "total_tokens": 9078240} {"current_steps": 43030, "total_steps": 181800, "loss": 0.017, "lr": 4.720809501462973e-05, "epoch": 4.733773377337734, "percentage": 23.67, "elapsed_time": "1:41:19", "remaining_time": "5:26:44", "throughput": 1493.53, "total_tokens": 9079200} {"current_steps": 43035, "total_steps": 181800, "loss": 0.0486, "lr": 4.720699275889342e-05, "epoch": 4.734323432343234, "percentage": 23.67, "elapsed_time": "1:41:19", "remaining_time": "5:26:43", "throughput": 1493.54, "total_tokens": 9080288} {"current_steps": 43040, "total_steps": 181800, "loss": 0.0948, "lr": 4.720589029848592e-05, "epoch": 4.734873487348735, "percentage": 23.67, "elapsed_time": "1:41:20", "remaining_time": "5:26:43", "throughput": 1493.55, "total_tokens": 9081408} {"current_steps": 43045, "total_steps": 181800, "loss": 0.0236, "lr": 4.7204787633417394e-05, "epoch": 4.735423542354235, "percentage": 23.68, "elapsed_time": "1:41:21", "remaining_time": "5:26:42", "throughput": 1493.56, "total_tokens": 9082496} {"current_steps": 43050, "total_steps": 181800, "loss": 0.1834, "lr": 4.720368476369798e-05, "epoch": 4.735973597359736, "percentage": 23.68, "elapsed_time": "1:41:21", "remaining_time": "5:26:41", "throughput": 1493.57, "total_tokens": 9083584} {"current_steps": 43055, "total_steps": 181800, "loss": 0.0066, "lr": 4.7202581689337865e-05, "epoch": 4.7365236523652365, "percentage": 23.68, "elapsed_time": "1:41:22", "remaining_time": "5:26:40", "throughput": 1493.57, "total_tokens": 9084576} {"current_steps": 43060, "total_steps": 181800, "loss": 0.056, "lr": 4.720147841034721e-05, "epoch": 4.737073707370737, "percentage": 23.69, "elapsed_time": "1:41:23", "remaining_time": "5:26:40", "throughput": 1493.57, "total_tokens": 9085632} {"current_steps": 43065, "total_steps": 181800, "loss": 0.1396, "lr": 4.720037492673618e-05, "epoch": 4.737623762376238, "percentage": 23.69, "elapsed_time": "1:41:23", "remaining_time": "5:26:39", "throughput": 1493.57, "total_tokens": 9086656} {"current_steps": 43070, "total_steps": 181800, "loss": 0.0333, "lr": 4.7199271238514945e-05, "epoch": 4.738173817381738, "percentage": 23.69, "elapsed_time": "1:41:24", "remaining_time": "5:26:38", "throughput": 1493.58, "total_tokens": 9087776} {"current_steps": 43075, "total_steps": 181800, "loss": 0.0427, "lr": 4.719816734569369e-05, "epoch": 4.738723872387238, "percentage": 23.69, "elapsed_time": "1:41:25", "remaining_time": "5:26:37", "throughput": 1493.59, "total_tokens": 9088832} {"current_steps": 43080, "total_steps": 181800, "loss": 0.017, "lr": 4.719706324828256e-05, "epoch": 4.739273927392739, "percentage": 23.7, "elapsed_time": "1:41:25", "remaining_time": "5:26:37", "throughput": 1493.6, "total_tokens": 9089952} {"current_steps": 43085, "total_steps": 181800, "loss": 0.0495, "lr": 4.719595894629176e-05, "epoch": 4.7398239823982395, "percentage": 23.7, "elapsed_time": "1:41:26", "remaining_time": "5:26:36", "throughput": 1493.6, "total_tokens": 9090976} {"current_steps": 43090, "total_steps": 181800, "loss": 0.0353, "lr": 4.719485443973146e-05, "epoch": 4.740374037403741, "percentage": 23.7, "elapsed_time": "1:41:27", "remaining_time": "5:26:35", "throughput": 1493.61, "total_tokens": 9092032} {"current_steps": 43095, "total_steps": 181800, "loss": 0.1079, "lr": 4.7193749728611835e-05, "epoch": 4.740924092409241, "percentage": 23.7, "elapsed_time": "1:41:27", "remaining_time": "5:26:34", "throughput": 1493.6, "total_tokens": 9093024} {"current_steps": 43100, "total_steps": 181800, "loss": 0.0815, "lr": 4.719264481294306e-05, "epoch": 4.741474147414742, "percentage": 23.71, "elapsed_time": "1:41:28", "remaining_time": "5:26:33", "throughput": 1493.61, "total_tokens": 9094144} {"current_steps": 43105, "total_steps": 181800, "loss": 0.0584, "lr": 4.7191539692735336e-05, "epoch": 4.742024202420242, "percentage": 23.71, "elapsed_time": "1:41:29", "remaining_time": "5:26:33", "throughput": 1493.62, "total_tokens": 9095200} {"current_steps": 43110, "total_steps": 181800, "loss": 0.133, "lr": 4.719043436799884e-05, "epoch": 4.742574257425742, "percentage": 23.71, "elapsed_time": "1:41:30", "remaining_time": "5:26:32", "throughput": 1493.63, "total_tokens": 9096288} {"current_steps": 43115, "total_steps": 181800, "loss": 0.0352, "lr": 4.718932883874375e-05, "epoch": 4.743124312431243, "percentage": 23.72, "elapsed_time": "1:41:30", "remaining_time": "5:26:31", "throughput": 1493.63, "total_tokens": 9097312} {"current_steps": 43120, "total_steps": 181800, "loss": 0.0293, "lr": 4.718822310498027e-05, "epoch": 4.743674367436744, "percentage": 23.72, "elapsed_time": "1:41:31", "remaining_time": "5:26:30", "throughput": 1493.63, "total_tokens": 9098368} {"current_steps": 43125, "total_steps": 181800, "loss": 0.0411, "lr": 4.718711716671859e-05, "epoch": 4.744224422442244, "percentage": 23.72, "elapsed_time": "1:41:32", "remaining_time": "5:26:30", "throughput": 1493.62, "total_tokens": 9099328} {"current_steps": 43130, "total_steps": 181800, "loss": 0.0698, "lr": 4.7186011023968886e-05, "epoch": 4.744774477447745, "percentage": 23.72, "elapsed_time": "1:41:32", "remaining_time": "5:26:29", "throughput": 1493.61, "total_tokens": 9100320} {"current_steps": 43135, "total_steps": 181800, "loss": 0.0276, "lr": 4.7184904676741365e-05, "epoch": 4.745324532453245, "percentage": 23.73, "elapsed_time": "1:41:33", "remaining_time": "5:26:28", "throughput": 1493.61, "total_tokens": 9101312} {"current_steps": 43140, "total_steps": 181800, "loss": 0.0779, "lr": 4.718379812504623e-05, "epoch": 4.745874587458746, "percentage": 23.73, "elapsed_time": "1:41:34", "remaining_time": "5:26:27", "throughput": 1493.61, "total_tokens": 9102368} {"current_steps": 43145, "total_steps": 181800, "loss": 0.0489, "lr": 4.7182691368893664e-05, "epoch": 4.7464246424642464, "percentage": 23.73, "elapsed_time": "1:41:34", "remaining_time": "5:26:27", "throughput": 1493.62, "total_tokens": 9103424} {"current_steps": 43150, "total_steps": 181800, "loss": 0.1286, "lr": 4.718158440829388e-05, "epoch": 4.746974697469747, "percentage": 23.73, "elapsed_time": "1:41:35", "remaining_time": "5:26:26", "throughput": 1493.63, "total_tokens": 9104512} {"current_steps": 43155, "total_steps": 181800, "loss": 0.2594, "lr": 4.7180477243257085e-05, "epoch": 4.747524752475248, "percentage": 23.74, "elapsed_time": "1:41:36", "remaining_time": "5:26:25", "throughput": 1493.64, "total_tokens": 9105600} {"current_steps": 43160, "total_steps": 181800, "loss": 0.108, "lr": 4.717936987379347e-05, "epoch": 4.748074807480748, "percentage": 23.74, "elapsed_time": "1:41:36", "remaining_time": "5:26:24", "throughput": 1493.65, "total_tokens": 9106688} {"current_steps": 43165, "total_steps": 181800, "loss": 0.0657, "lr": 4.7178262299913236e-05, "epoch": 4.748624862486249, "percentage": 23.74, "elapsed_time": "1:41:37", "remaining_time": "5:26:24", "throughput": 1493.66, "total_tokens": 9107808} {"current_steps": 43170, "total_steps": 181800, "loss": 0.0662, "lr": 4.717715452162661e-05, "epoch": 4.749174917491749, "percentage": 23.75, "elapsed_time": "1:41:38", "remaining_time": "5:26:23", "throughput": 1493.67, "total_tokens": 9108864} {"current_steps": 43175, "total_steps": 181800, "loss": 0.1061, "lr": 4.7176046538943784e-05, "epoch": 4.7497249724972495, "percentage": 23.75, "elapsed_time": "1:41:39", "remaining_time": "5:26:22", "throughput": 1493.67, "total_tokens": 9109920} {"current_steps": 43180, "total_steps": 181800, "loss": 0.1083, "lr": 4.717493835187499e-05, "epoch": 4.7502750275027505, "percentage": 23.75, "elapsed_time": "1:41:39", "remaining_time": "5:26:21", "throughput": 1493.67, "total_tokens": 9110944} {"current_steps": 43185, "total_steps": 181800, "loss": 0.0168, "lr": 4.7173829960430416e-05, "epoch": 4.750825082508251, "percentage": 23.75, "elapsed_time": "1:41:40", "remaining_time": "5:26:21", "throughput": 1493.67, "total_tokens": 9112000} {"current_steps": 43190, "total_steps": 181800, "loss": 0.0419, "lr": 4.7172721364620295e-05, "epoch": 4.751375137513751, "percentage": 23.76, "elapsed_time": "1:41:41", "remaining_time": "5:26:20", "throughput": 1493.67, "total_tokens": 9112992} {"current_steps": 43195, "total_steps": 181800, "loss": 0.1357, "lr": 4.717161256445485e-05, "epoch": 4.751925192519252, "percentage": 23.76, "elapsed_time": "1:41:41", "remaining_time": "5:26:19", "throughput": 1493.67, "total_tokens": 9114048} {"current_steps": 43200, "total_steps": 181800, "loss": 0.0463, "lr": 4.717050355994428e-05, "epoch": 4.752475247524752, "percentage": 23.76, "elapsed_time": "1:41:42", "remaining_time": "5:26:18", "throughput": 1493.7, "total_tokens": 9115232} {"current_steps": 43205, "total_steps": 181800, "loss": 0.0445, "lr": 4.716939435109883e-05, "epoch": 4.753025302530253, "percentage": 23.77, "elapsed_time": "1:41:43", "remaining_time": "5:26:17", "throughput": 1493.71, "total_tokens": 9116288} {"current_steps": 43210, "total_steps": 181800, "loss": 0.0214, "lr": 4.71682849379287e-05, "epoch": 4.7535753575357536, "percentage": 23.77, "elapsed_time": "1:41:43", "remaining_time": "5:26:17", "throughput": 1493.71, "total_tokens": 9117344} {"current_steps": 43215, "total_steps": 181800, "loss": 0.0642, "lr": 4.716717532044412e-05, "epoch": 4.754125412541254, "percentage": 23.77, "elapsed_time": "1:41:44", "remaining_time": "5:26:16", "throughput": 1493.72, "total_tokens": 9118432} {"current_steps": 43220, "total_steps": 181800, "loss": 0.0755, "lr": 4.7166065498655336e-05, "epoch": 4.754675467546755, "percentage": 23.77, "elapsed_time": "1:41:45", "remaining_time": "5:26:15", "throughput": 1493.74, "total_tokens": 9119552} {"current_steps": 43225, "total_steps": 181800, "loss": 0.0418, "lr": 4.716495547257256e-05, "epoch": 4.755225522552255, "percentage": 23.78, "elapsed_time": "1:41:45", "remaining_time": "5:26:14", "throughput": 1493.73, "total_tokens": 9120576} {"current_steps": 43230, "total_steps": 181800, "loss": 0.1039, "lr": 4.7163845242206016e-05, "epoch": 4.755775577557756, "percentage": 23.78, "elapsed_time": "1:41:46", "remaining_time": "5:26:14", "throughput": 1493.74, "total_tokens": 9121664} {"current_steps": 43235, "total_steps": 181800, "loss": 0.0246, "lr": 4.7162734807565957e-05, "epoch": 4.756325632563256, "percentage": 23.78, "elapsed_time": "1:41:47", "remaining_time": "5:26:13", "throughput": 1493.74, "total_tokens": 9122688} {"current_steps": 43240, "total_steps": 181800, "loss": 0.0958, "lr": 4.71616241686626e-05, "epoch": 4.756875687568757, "percentage": 23.78, "elapsed_time": "1:41:47", "remaining_time": "5:26:12", "throughput": 1493.75, "total_tokens": 9123744} {"current_steps": 43245, "total_steps": 181800, "loss": 0.0772, "lr": 4.716051332550618e-05, "epoch": 4.757425742574258, "percentage": 23.79, "elapsed_time": "1:41:48", "remaining_time": "5:26:11", "throughput": 1493.75, "total_tokens": 9124768} {"current_steps": 43250, "total_steps": 181800, "loss": 0.0926, "lr": 4.715940227810695e-05, "epoch": 4.757975797579758, "percentage": 23.79, "elapsed_time": "1:41:49", "remaining_time": "5:26:11", "throughput": 1493.76, "total_tokens": 9125888} {"current_steps": 43255, "total_steps": 181800, "loss": 0.0165, "lr": 4.715829102647514e-05, "epoch": 4.758525852585258, "percentage": 23.79, "elapsed_time": "1:41:50", "remaining_time": "5:26:10", "throughput": 1493.76, "total_tokens": 9126880} {"current_steps": 43260, "total_steps": 181800, "loss": 0.0215, "lr": 4.7157179570621e-05, "epoch": 4.759075907590759, "percentage": 23.8, "elapsed_time": "1:41:50", "remaining_time": "5:26:09", "throughput": 1493.76, "total_tokens": 9127904} {"current_steps": 43265, "total_steps": 181800, "loss": 0.0199, "lr": 4.715606791055477e-05, "epoch": 4.759625962596259, "percentage": 23.8, "elapsed_time": "1:41:51", "remaining_time": "5:26:08", "throughput": 1493.77, "total_tokens": 9129024} {"current_steps": 43270, "total_steps": 181800, "loss": 0.0116, "lr": 4.715495604628668e-05, "epoch": 4.7601760176017605, "percentage": 23.8, "elapsed_time": "1:41:52", "remaining_time": "5:26:07", "throughput": 1493.78, "total_tokens": 9130080} {"current_steps": 43275, "total_steps": 181800, "loss": 0.0434, "lr": 4.7153843977827e-05, "epoch": 4.760726072607261, "percentage": 23.8, "elapsed_time": "1:41:52", "remaining_time": "5:26:07", "throughput": 1493.78, "total_tokens": 9131104} {"current_steps": 43280, "total_steps": 181800, "loss": 0.0064, "lr": 4.715273170518597e-05, "epoch": 4.761276127612762, "percentage": 23.81, "elapsed_time": "1:41:53", "remaining_time": "5:26:06", "throughput": 1493.78, "total_tokens": 9132160} {"current_steps": 43285, "total_steps": 181800, "loss": 0.0719, "lr": 4.715161922837384e-05, "epoch": 4.761826182618262, "percentage": 23.81, "elapsed_time": "1:41:54", "remaining_time": "5:26:05", "throughput": 1493.78, "total_tokens": 9133216} {"current_steps": 43290, "total_steps": 181800, "loss": 0.1009, "lr": 4.715050654740086e-05, "epoch": 4.762376237623762, "percentage": 23.81, "elapsed_time": "1:41:54", "remaining_time": "5:26:04", "throughput": 1493.79, "total_tokens": 9134272} {"current_steps": 43295, "total_steps": 181800, "loss": 0.0991, "lr": 4.71493936622773e-05, "epoch": 4.762926292629263, "percentage": 23.81, "elapsed_time": "1:41:55", "remaining_time": "5:26:04", "throughput": 1493.79, "total_tokens": 9135296} {"current_steps": 43300, "total_steps": 181800, "loss": 0.0134, "lr": 4.71482805730134e-05, "epoch": 4.7634763476347635, "percentage": 23.82, "elapsed_time": "1:41:56", "remaining_time": "5:26:03", "throughput": 1493.79, "total_tokens": 9136320} {"current_steps": 43305, "total_steps": 181800, "loss": 0.0179, "lr": 4.714716727961943e-05, "epoch": 4.764026402640264, "percentage": 23.82, "elapsed_time": "1:41:56", "remaining_time": "5:26:02", "throughput": 1493.8, "total_tokens": 9137408} {"current_steps": 43310, "total_steps": 181800, "loss": 0.1576, "lr": 4.7146053782105646e-05, "epoch": 4.764576457645765, "percentage": 23.82, "elapsed_time": "1:41:57", "remaining_time": "5:26:01", "throughput": 1493.79, "total_tokens": 9138432} {"current_steps": 43315, "total_steps": 181800, "loss": 0.0396, "lr": 4.714494008048231e-05, "epoch": 4.765126512651265, "percentage": 23.83, "elapsed_time": "1:41:58", "remaining_time": "5:26:01", "throughput": 1493.81, "total_tokens": 9139552} {"current_steps": 43320, "total_steps": 181800, "loss": 0.044, "lr": 4.714382617475969e-05, "epoch": 4.765676567656766, "percentage": 23.83, "elapsed_time": "1:41:58", "remaining_time": "5:26:00", "throughput": 1493.81, "total_tokens": 9140576} {"current_steps": 43325, "total_steps": 181800, "loss": 0.0961, "lr": 4.7142712064948045e-05, "epoch": 4.766226622662266, "percentage": 23.83, "elapsed_time": "1:41:59", "remaining_time": "5:25:59", "throughput": 1493.81, "total_tokens": 9141632} {"current_steps": 43330, "total_steps": 181800, "loss": 0.0683, "lr": 4.714159775105765e-05, "epoch": 4.7667766776677665, "percentage": 23.83, "elapsed_time": "1:42:00", "remaining_time": "5:25:58", "throughput": 1493.82, "total_tokens": 9142688} {"current_steps": 43335, "total_steps": 181800, "loss": 0.0346, "lr": 4.714048323309878e-05, "epoch": 4.767326732673268, "percentage": 23.84, "elapsed_time": "1:42:01", "remaining_time": "5:25:58", "throughput": 1493.82, "total_tokens": 9143776} {"current_steps": 43340, "total_steps": 181800, "loss": 0.0334, "lr": 4.7139368511081686e-05, "epoch": 4.767876787678768, "percentage": 23.84, "elapsed_time": "1:42:01", "remaining_time": "5:25:57", "throughput": 1493.83, "total_tokens": 9144864} {"current_steps": 43345, "total_steps": 181800, "loss": 0.0778, "lr": 4.713825358501667e-05, "epoch": 4.768426842684269, "percentage": 23.84, "elapsed_time": "1:42:02", "remaining_time": "5:25:56", "throughput": 1493.84, "total_tokens": 9145920} {"current_steps": 43350, "total_steps": 181800, "loss": 0.0969, "lr": 4.713713845491399e-05, "epoch": 4.768976897689769, "percentage": 23.84, "elapsed_time": "1:42:03", "remaining_time": "5:25:55", "throughput": 1493.83, "total_tokens": 9146912} {"current_steps": 43355, "total_steps": 181800, "loss": 0.0314, "lr": 4.713602312078392e-05, "epoch": 4.769526952695269, "percentage": 23.85, "elapsed_time": "1:42:03", "remaining_time": "5:25:55", "throughput": 1493.84, "total_tokens": 9147968} {"current_steps": 43360, "total_steps": 181800, "loss": 0.0406, "lr": 4.713490758263675e-05, "epoch": 4.77007700770077, "percentage": 23.85, "elapsed_time": "1:42:04", "remaining_time": "5:25:54", "throughput": 1493.84, "total_tokens": 9149024} {"current_steps": 43365, "total_steps": 181800, "loss": 0.0329, "lr": 4.7133791840482755e-05, "epoch": 4.770627062706271, "percentage": 23.85, "elapsed_time": "1:42:05", "remaining_time": "5:25:53", "throughput": 1493.84, "total_tokens": 9150048} {"current_steps": 43370, "total_steps": 181800, "loss": 0.0556, "lr": 4.713267589433223e-05, "epoch": 4.771177117711771, "percentage": 23.86, "elapsed_time": "1:42:05", "remaining_time": "5:25:52", "throughput": 1493.85, "total_tokens": 9151104} {"current_steps": 43375, "total_steps": 181800, "loss": 0.1376, "lr": 4.7131559744195445e-05, "epoch": 4.771727172717272, "percentage": 23.86, "elapsed_time": "1:42:06", "remaining_time": "5:25:52", "throughput": 1493.85, "total_tokens": 9152160} {"current_steps": 43380, "total_steps": 181800, "loss": 0.1875, "lr": 4.71304433900827e-05, "epoch": 4.772277227722772, "percentage": 23.86, "elapsed_time": "1:42:07", "remaining_time": "5:25:51", "throughput": 1493.84, "total_tokens": 9153152} {"current_steps": 43385, "total_steps": 181800, "loss": 0.1542, "lr": 4.712932683200427e-05, "epoch": 4.772827282728273, "percentage": 23.86, "elapsed_time": "1:42:07", "remaining_time": "5:25:50", "throughput": 1493.85, "total_tokens": 9154240} {"current_steps": 43390, "total_steps": 181800, "loss": 0.0174, "lr": 4.712821006997046e-05, "epoch": 4.773377337733773, "percentage": 23.87, "elapsed_time": "1:42:08", "remaining_time": "5:25:49", "throughput": 1493.86, "total_tokens": 9155296} {"current_steps": 43395, "total_steps": 181800, "loss": 0.0789, "lr": 4.712709310399155e-05, "epoch": 4.773927392739274, "percentage": 23.87, "elapsed_time": "1:42:09", "remaining_time": "5:25:48", "throughput": 1493.87, "total_tokens": 9156384} {"current_steps": 43400, "total_steps": 181800, "loss": 0.0232, "lr": 4.712597593407784e-05, "epoch": 4.774477447744775, "percentage": 23.87, "elapsed_time": "1:42:10", "remaining_time": "5:25:48", "throughput": 1493.88, "total_tokens": 9157472} {"current_steps": 43405, "total_steps": 181800, "loss": 0.0501, "lr": 4.712485856023963e-05, "epoch": 4.775027502750275, "percentage": 23.88, "elapsed_time": "1:42:10", "remaining_time": "5:25:47", "throughput": 1493.89, "total_tokens": 9158560} {"current_steps": 43410, "total_steps": 181800, "loss": 0.0495, "lr": 4.712374098248722e-05, "epoch": 4.775577557755776, "percentage": 23.88, "elapsed_time": "1:42:11", "remaining_time": "5:25:46", "throughput": 1493.9, "total_tokens": 9159680} {"current_steps": 43415, "total_steps": 181800, "loss": 0.0729, "lr": 4.712262320083089e-05, "epoch": 4.776127612761276, "percentage": 23.88, "elapsed_time": "1:42:12", "remaining_time": "5:25:45", "throughput": 1493.9, "total_tokens": 9160736} {"current_steps": 43420, "total_steps": 181800, "loss": 0.0185, "lr": 4.712150521528098e-05, "epoch": 4.776677667766776, "percentage": 23.88, "elapsed_time": "1:42:12", "remaining_time": "5:25:45", "throughput": 1493.91, "total_tokens": 9161792} {"current_steps": 43425, "total_steps": 181800, "loss": 0.0392, "lr": 4.7120387025847754e-05, "epoch": 4.7772277227722775, "percentage": 23.89, "elapsed_time": "1:42:13", "remaining_time": "5:25:44", "throughput": 1493.91, "total_tokens": 9162816} {"current_steps": 43430, "total_steps": 181800, "loss": 0.016, "lr": 4.711926863254154e-05, "epoch": 4.777777777777778, "percentage": 23.89, "elapsed_time": "1:42:14", "remaining_time": "5:25:43", "throughput": 1493.92, "total_tokens": 9163936} {"current_steps": 43435, "total_steps": 181800, "loss": 0.0421, "lr": 4.711815003537264e-05, "epoch": 4.778327832783278, "percentage": 23.89, "elapsed_time": "1:42:14", "remaining_time": "5:25:42", "throughput": 1493.94, "total_tokens": 9165056} {"current_steps": 43440, "total_steps": 181800, "loss": 0.1035, "lr": 4.711703123435137e-05, "epoch": 4.778877887788779, "percentage": 23.89, "elapsed_time": "1:42:15", "remaining_time": "5:25:42", "throughput": 1493.94, "total_tokens": 9166144} {"current_steps": 43445, "total_steps": 181800, "loss": 0.0178, "lr": 4.711591222948803e-05, "epoch": 4.779427942794279, "percentage": 23.9, "elapsed_time": "1:42:16", "remaining_time": "5:25:41", "throughput": 1493.95, "total_tokens": 9167200} {"current_steps": 43450, "total_steps": 181800, "loss": 0.0222, "lr": 4.7114793020792944e-05, "epoch": 4.77997799779978, "percentage": 23.9, "elapsed_time": "1:42:16", "remaining_time": "5:25:40", "throughput": 1493.95, "total_tokens": 9168256} {"current_steps": 43455, "total_steps": 181800, "loss": 0.1033, "lr": 4.711367360827642e-05, "epoch": 4.7805280528052805, "percentage": 23.9, "elapsed_time": "1:42:17", "remaining_time": "5:25:39", "throughput": 1493.96, "total_tokens": 9169312} {"current_steps": 43460, "total_steps": 181800, "loss": 0.1235, "lr": 4.711255399194877e-05, "epoch": 4.781078107810782, "percentage": 23.91, "elapsed_time": "1:42:18", "remaining_time": "5:25:39", "throughput": 1493.97, "total_tokens": 9170464} {"current_steps": 43465, "total_steps": 181800, "loss": 0.0338, "lr": 4.711143417182033e-05, "epoch": 4.781628162816282, "percentage": 23.91, "elapsed_time": "1:42:18", "remaining_time": "5:25:38", "throughput": 1493.97, "total_tokens": 9171488} {"current_steps": 43470, "total_steps": 181800, "loss": 0.1197, "lr": 4.711031414790141e-05, "epoch": 4.782178217821782, "percentage": 23.91, "elapsed_time": "1:42:19", "remaining_time": "5:25:37", "throughput": 1493.97, "total_tokens": 9172512} {"current_steps": 43475, "total_steps": 181800, "loss": 0.0736, "lr": 4.710919392020233e-05, "epoch": 4.782728272827283, "percentage": 23.91, "elapsed_time": "1:42:20", "remaining_time": "5:25:36", "throughput": 1493.97, "total_tokens": 9173504} {"current_steps": 43480, "total_steps": 181800, "loss": 0.0749, "lr": 4.710807348873342e-05, "epoch": 4.783278327832783, "percentage": 23.92, "elapsed_time": "1:42:21", "remaining_time": "5:25:36", "throughput": 1493.98, "total_tokens": 9174624} {"current_steps": 43485, "total_steps": 181800, "loss": 0.0551, "lr": 4.710695285350501e-05, "epoch": 4.7838283828382835, "percentage": 23.92, "elapsed_time": "1:42:21", "remaining_time": "5:25:35", "throughput": 1493.96, "total_tokens": 9175584} {"current_steps": 43490, "total_steps": 181800, "loss": 0.0809, "lr": 4.710583201452742e-05, "epoch": 4.784378437843785, "percentage": 23.92, "elapsed_time": "1:42:22", "remaining_time": "5:25:34", "throughput": 1493.97, "total_tokens": 9176672} {"current_steps": 43495, "total_steps": 181800, "loss": 0.0249, "lr": 4.710471097181098e-05, "epoch": 4.784928492849285, "percentage": 23.92, "elapsed_time": "1:42:23", "remaining_time": "5:25:33", "throughput": 1493.98, "total_tokens": 9177760} {"current_steps": 43500, "total_steps": 181800, "loss": 0.0847, "lr": 4.710358972536603e-05, "epoch": 4.785478547854785, "percentage": 23.93, "elapsed_time": "1:42:23", "remaining_time": "5:25:33", "throughput": 1493.99, "total_tokens": 9178816} {"current_steps": 43505, "total_steps": 181800, "loss": 0.0642, "lr": 4.7102468275202906e-05, "epoch": 4.786028602860286, "percentage": 23.93, "elapsed_time": "1:42:24", "remaining_time": "5:25:32", "throughput": 1493.99, "total_tokens": 9179840} {"current_steps": 43510, "total_steps": 181800, "loss": 0.0174, "lr": 4.7101346621331926e-05, "epoch": 4.786578657865786, "percentage": 23.93, "elapsed_time": "1:42:25", "remaining_time": "5:25:31", "throughput": 1493.99, "total_tokens": 9180896} {"current_steps": 43515, "total_steps": 181800, "loss": 0.0596, "lr": 4.710022476376345e-05, "epoch": 4.787128712871287, "percentage": 23.94, "elapsed_time": "1:42:25", "remaining_time": "5:25:30", "throughput": 1494.0, "total_tokens": 9181984} {"current_steps": 43520, "total_steps": 181800, "loss": 0.0537, "lr": 4.70991027025078e-05, "epoch": 4.787678767876788, "percentage": 23.94, "elapsed_time": "1:42:26", "remaining_time": "5:25:30", "throughput": 1494.0, "total_tokens": 9183008} {"current_steps": 43525, "total_steps": 181800, "loss": 0.0964, "lr": 4.7097980437575324e-05, "epoch": 4.788228822882289, "percentage": 23.94, "elapsed_time": "1:42:27", "remaining_time": "5:25:29", "throughput": 1493.99, "total_tokens": 9184000} {"current_steps": 43530, "total_steps": 181800, "loss": 0.0096, "lr": 4.709685796897637e-05, "epoch": 4.788778877887789, "percentage": 23.94, "elapsed_time": "1:42:27", "remaining_time": "5:25:28", "throughput": 1493.99, "total_tokens": 9185024} {"current_steps": 43535, "total_steps": 181800, "loss": 0.0382, "lr": 4.709573529672128e-05, "epoch": 4.789328932893289, "percentage": 23.95, "elapsed_time": "1:42:28", "remaining_time": "5:25:27", "throughput": 1494.0, "total_tokens": 9186112} {"current_steps": 43540, "total_steps": 181800, "loss": 0.0322, "lr": 4.7094612420820396e-05, "epoch": 4.78987898789879, "percentage": 23.95, "elapsed_time": "1:42:29", "remaining_time": "5:25:27", "throughput": 1494.0, "total_tokens": 9187136} {"current_steps": 43545, "total_steps": 181800, "loss": 0.0335, "lr": 4.709348934128407e-05, "epoch": 4.79042904290429, "percentage": 23.95, "elapsed_time": "1:42:30", "remaining_time": "5:25:26", "throughput": 1493.99, "total_tokens": 9188128} {"current_steps": 43550, "total_steps": 181800, "loss": 0.019, "lr": 4.709236605812266e-05, "epoch": 4.790979097909791, "percentage": 23.95, "elapsed_time": "1:42:30", "remaining_time": "5:25:25", "throughput": 1494.0, "total_tokens": 9189216} {"current_steps": 43555, "total_steps": 181800, "loss": 0.0322, "lr": 4.709124257134651e-05, "epoch": 4.791529152915292, "percentage": 23.96, "elapsed_time": "1:42:31", "remaining_time": "5:25:24", "throughput": 1493.99, "total_tokens": 9190176} {"current_steps": 43560, "total_steps": 181800, "loss": 0.1131, "lr": 4.709011888096597e-05, "epoch": 4.792079207920792, "percentage": 23.96, "elapsed_time": "1:42:32", "remaining_time": "5:25:24", "throughput": 1493.99, "total_tokens": 9191232} {"current_steps": 43565, "total_steps": 181800, "loss": 0.1252, "lr": 4.708899498699142e-05, "epoch": 4.792629262926293, "percentage": 23.96, "elapsed_time": "1:42:32", "remaining_time": "5:25:23", "throughput": 1494.0, "total_tokens": 9192288} {"current_steps": 43570, "total_steps": 181800, "loss": 0.0959, "lr": 4.708787088943319e-05, "epoch": 4.793179317931793, "percentage": 23.97, "elapsed_time": "1:42:33", "remaining_time": "5:25:22", "throughput": 1494.0, "total_tokens": 9193344} {"current_steps": 43575, "total_steps": 181800, "loss": 0.012, "lr": 4.708674658830166e-05, "epoch": 4.793729372937293, "percentage": 23.97, "elapsed_time": "1:42:34", "remaining_time": "5:25:21", "throughput": 1494.0, "total_tokens": 9194400} {"current_steps": 43580, "total_steps": 181800, "loss": 0.0459, "lr": 4.708562208360718e-05, "epoch": 4.7942794279427945, "percentage": 23.97, "elapsed_time": "1:42:34", "remaining_time": "5:25:21", "throughput": 1494.01, "total_tokens": 9195456} {"current_steps": 43585, "total_steps": 181800, "loss": 0.0822, "lr": 4.708449737536013e-05, "epoch": 4.794829482948295, "percentage": 23.97, "elapsed_time": "1:42:35", "remaining_time": "5:25:20", "throughput": 1494.01, "total_tokens": 9196480} {"current_steps": 43590, "total_steps": 181800, "loss": 0.0275, "lr": 4.708337246357085e-05, "epoch": 4.795379537953796, "percentage": 23.98, "elapsed_time": "1:42:36", "remaining_time": "5:25:19", "throughput": 1494.01, "total_tokens": 9197536} {"current_steps": 43595, "total_steps": 181800, "loss": 0.0047, "lr": 4.708224734824973e-05, "epoch": 4.795929592959296, "percentage": 23.98, "elapsed_time": "1:42:36", "remaining_time": "5:25:18", "throughput": 1494.02, "total_tokens": 9198624} {"current_steps": 43600, "total_steps": 181800, "loss": 0.0992, "lr": 4.708112202940713e-05, "epoch": 4.796479647964796, "percentage": 23.98, "elapsed_time": "1:42:37", "remaining_time": "5:25:18", "throughput": 1494.02, "total_tokens": 9199648} {"current_steps": 43605, "total_steps": 181800, "loss": 0.0188, "lr": 4.707999650705342e-05, "epoch": 4.797029702970297, "percentage": 23.99, "elapsed_time": "1:42:38", "remaining_time": "5:25:17", "throughput": 1494.04, "total_tokens": 9200768} {"current_steps": 43610, "total_steps": 181800, "loss": 0.0172, "lr": 4.7078870781198984e-05, "epoch": 4.7975797579757975, "percentage": 23.99, "elapsed_time": "1:42:39", "remaining_time": "5:25:16", "throughput": 1494.04, "total_tokens": 9201824} {"current_steps": 43615, "total_steps": 181800, "loss": 0.0664, "lr": 4.707774485185419e-05, "epoch": 4.798129812981298, "percentage": 23.99, "elapsed_time": "1:42:39", "remaining_time": "5:25:15", "throughput": 1494.05, "total_tokens": 9202880} {"current_steps": 43620, "total_steps": 181800, "loss": 0.0373, "lr": 4.707661871902942e-05, "epoch": 4.798679867986799, "percentage": 23.99, "elapsed_time": "1:42:40", "remaining_time": "5:25:14", "throughput": 1494.05, "total_tokens": 9203936} {"current_steps": 43625, "total_steps": 181800, "loss": 0.0254, "lr": 4.707549238273504e-05, "epoch": 4.799229922992299, "percentage": 24.0, "elapsed_time": "1:42:41", "remaining_time": "5:25:14", "throughput": 1494.07, "total_tokens": 9205088} {"current_steps": 43630, "total_steps": 181800, "loss": 0.1468, "lr": 4.7074365842981435e-05, "epoch": 4.7997799779978, "percentage": 24.0, "elapsed_time": "1:42:41", "remaining_time": "5:25:13", "throughput": 1494.07, "total_tokens": 9206144} {"current_steps": 43635, "total_steps": 181800, "loss": 0.0096, "lr": 4.707323909977901e-05, "epoch": 4.8003300330033, "percentage": 24.0, "elapsed_time": "1:42:42", "remaining_time": "5:25:12", "throughput": 1494.08, "total_tokens": 9207232} {"current_steps": 43640, "total_steps": 181800, "loss": 0.0988, "lr": 4.7072112153138114e-05, "epoch": 4.8008800880088005, "percentage": 24.0, "elapsed_time": "1:42:43", "remaining_time": "5:25:11", "throughput": 1494.09, "total_tokens": 9208320} {"current_steps": 43645, "total_steps": 181800, "loss": 0.0419, "lr": 4.707098500306916e-05, "epoch": 4.801430143014302, "percentage": 24.01, "elapsed_time": "1:42:43", "remaining_time": "5:25:11", "throughput": 1494.1, "total_tokens": 9209440} {"current_steps": 43650, "total_steps": 181800, "loss": 0.0114, "lr": 4.706985764958253e-05, "epoch": 4.801980198019802, "percentage": 24.01, "elapsed_time": "1:42:44", "remaining_time": "5:25:10", "throughput": 1494.1, "total_tokens": 9210464} {"current_steps": 43655, "total_steps": 181800, "loss": 0.0587, "lr": 4.706873009268861e-05, "epoch": 4.802530253025303, "percentage": 24.01, "elapsed_time": "1:42:45", "remaining_time": "5:25:09", "throughput": 1494.12, "total_tokens": 9211584} {"current_steps": 43660, "total_steps": 181800, "loss": 0.081, "lr": 4.70676023323978e-05, "epoch": 4.803080308030803, "percentage": 24.02, "elapsed_time": "1:42:45", "remaining_time": "5:25:08", "throughput": 1494.13, "total_tokens": 9212704} {"current_steps": 43665, "total_steps": 181800, "loss": 0.0606, "lr": 4.706647436872048e-05, "epoch": 4.803630363036303, "percentage": 24.02, "elapsed_time": "1:42:46", "remaining_time": "5:25:08", "throughput": 1494.13, "total_tokens": 9213760} {"current_steps": 43670, "total_steps": 181800, "loss": 0.0439, "lr": 4.706534620166705e-05, "epoch": 4.804180418041804, "percentage": 24.02, "elapsed_time": "1:42:47", "remaining_time": "5:25:07", "throughput": 1494.15, "total_tokens": 9214880} {"current_steps": 43675, "total_steps": 181800, "loss": 0.0171, "lr": 4.706421783124792e-05, "epoch": 4.804730473047305, "percentage": 24.02, "elapsed_time": "1:42:48", "remaining_time": "5:25:06", "throughput": 1494.14, "total_tokens": 9215872} {"current_steps": 43680, "total_steps": 181800, "loss": 0.0145, "lr": 4.706308925747348e-05, "epoch": 4.805280528052805, "percentage": 24.03, "elapsed_time": "1:42:48", "remaining_time": "5:25:05", "throughput": 1494.15, "total_tokens": 9216928} {"current_steps": 43685, "total_steps": 181800, "loss": 0.1115, "lr": 4.7061960480354134e-05, "epoch": 4.805830583058306, "percentage": 24.03, "elapsed_time": "1:42:49", "remaining_time": "5:25:05", "throughput": 1494.15, "total_tokens": 9218016} {"current_steps": 43690, "total_steps": 181800, "loss": 0.0836, "lr": 4.7060831499900285e-05, "epoch": 4.806380638063806, "percentage": 24.03, "elapsed_time": "1:42:50", "remaining_time": "5:25:04", "throughput": 1494.15, "total_tokens": 9219040} {"current_steps": 43695, "total_steps": 181800, "loss": 0.0745, "lr": 4.705970231612234e-05, "epoch": 4.806930693069307, "percentage": 24.03, "elapsed_time": "1:42:50", "remaining_time": "5:25:03", "throughput": 1494.16, "total_tokens": 9220128} {"current_steps": 43700, "total_steps": 181800, "loss": 0.0807, "lr": 4.70585729290307e-05, "epoch": 4.807480748074807, "percentage": 24.04, "elapsed_time": "1:42:51", "remaining_time": "5:25:02", "throughput": 1494.16, "total_tokens": 9221120} {"current_steps": 43705, "total_steps": 181800, "loss": 0.0597, "lr": 4.7057443338635775e-05, "epoch": 4.8080308030803085, "percentage": 24.04, "elapsed_time": "1:42:52", "remaining_time": "5:25:02", "throughput": 1494.15, "total_tokens": 9222112} {"current_steps": 43710, "total_steps": 181800, "loss": 0.0671, "lr": 4.7056313544947985e-05, "epoch": 4.808580858085809, "percentage": 24.04, "elapsed_time": "1:42:52", "remaining_time": "5:25:01", "throughput": 1494.16, "total_tokens": 9223168} {"current_steps": 43715, "total_steps": 181800, "loss": 0.0122, "lr": 4.705518354797773e-05, "epoch": 4.809130913091309, "percentage": 24.05, "elapsed_time": "1:42:53", "remaining_time": "5:25:00", "throughput": 1494.17, "total_tokens": 9224256} {"current_steps": 43720, "total_steps": 181800, "loss": 0.0851, "lr": 4.7054053347735436e-05, "epoch": 4.80968096809681, "percentage": 24.05, "elapsed_time": "1:42:54", "remaining_time": "5:24:59", "throughput": 1494.17, "total_tokens": 9225312} {"current_steps": 43725, "total_steps": 181800, "loss": 0.068, "lr": 4.7052922944231514e-05, "epoch": 4.81023102310231, "percentage": 24.05, "elapsed_time": "1:42:54", "remaining_time": "5:24:59", "throughput": 1494.17, "total_tokens": 9226368} {"current_steps": 43730, "total_steps": 181800, "loss": 0.0419, "lr": 4.7051792337476385e-05, "epoch": 4.81078107810781, "percentage": 24.05, "elapsed_time": "1:42:55", "remaining_time": "5:24:58", "throughput": 1494.18, "total_tokens": 9227424} {"current_steps": 43735, "total_steps": 181800, "loss": 0.193, "lr": 4.7050661527480464e-05, "epoch": 4.8113311331133115, "percentage": 24.06, "elapsed_time": "1:42:56", "remaining_time": "5:24:57", "throughput": 1494.17, "total_tokens": 9228416} {"current_steps": 43740, "total_steps": 181800, "loss": 0.0915, "lr": 4.704953051425418e-05, "epoch": 4.811881188118812, "percentage": 24.06, "elapsed_time": "1:42:56", "remaining_time": "5:24:56", "throughput": 1494.17, "total_tokens": 9229472} {"current_steps": 43745, "total_steps": 181800, "loss": 0.0272, "lr": 4.7048399297807954e-05, "epoch": 4.812431243124313, "percentage": 24.06, "elapsed_time": "1:42:57", "remaining_time": "5:24:56", "throughput": 1494.17, "total_tokens": 9230496} {"current_steps": 43750, "total_steps": 181800, "loss": 0.0857, "lr": 4.7047267878152215e-05, "epoch": 4.812981298129813, "percentage": 24.06, "elapsed_time": "1:42:58", "remaining_time": "5:24:55", "throughput": 1494.17, "total_tokens": 9231520} {"current_steps": 43755, "total_steps": 181800, "loss": 0.0371, "lr": 4.704613625529738e-05, "epoch": 4.813531353135313, "percentage": 24.07, "elapsed_time": "1:42:59", "remaining_time": "5:24:54", "throughput": 1494.18, "total_tokens": 9232576} {"current_steps": 43760, "total_steps": 181800, "loss": 0.0174, "lr": 4.7045004429253894e-05, "epoch": 4.814081408140814, "percentage": 24.07, "elapsed_time": "1:42:59", "remaining_time": "5:24:53", "throughput": 1494.18, "total_tokens": 9233632} {"current_steps": 43765, "total_steps": 181800, "loss": 0.016, "lr": 4.7043872400032176e-05, "epoch": 4.8146314631463145, "percentage": 24.07, "elapsed_time": "1:43:00", "remaining_time": "5:24:53", "throughput": 1494.19, "total_tokens": 9234688} {"current_steps": 43770, "total_steps": 181800, "loss": 0.0161, "lr": 4.704274016764266e-05, "epoch": 4.815181518151816, "percentage": 24.08, "elapsed_time": "1:43:01", "remaining_time": "5:24:52", "throughput": 1494.18, "total_tokens": 9235712} {"current_steps": 43775, "total_steps": 181800, "loss": 0.1107, "lr": 4.704160773209578e-05, "epoch": 4.815731573157316, "percentage": 24.08, "elapsed_time": "1:43:01", "remaining_time": "5:24:51", "throughput": 1494.2, "total_tokens": 9236832} {"current_steps": 43780, "total_steps": 181800, "loss": 0.0411, "lr": 4.7040475093401994e-05, "epoch": 4.816281628162816, "percentage": 24.08, "elapsed_time": "1:43:02", "remaining_time": "5:24:50", "throughput": 1494.21, "total_tokens": 9237920} {"current_steps": 43785, "total_steps": 181800, "loss": 0.0244, "lr": 4.703934225157171e-05, "epoch": 4.816831683168317, "percentage": 24.08, "elapsed_time": "1:43:03", "remaining_time": "5:24:50", "throughput": 1494.22, "total_tokens": 9239008} {"current_steps": 43790, "total_steps": 181800, "loss": 0.0951, "lr": 4.703820920661539e-05, "epoch": 4.817381738173817, "percentage": 24.09, "elapsed_time": "1:43:03", "remaining_time": "5:24:49", "throughput": 1494.22, "total_tokens": 9240032} {"current_steps": 43795, "total_steps": 181800, "loss": 0.0256, "lr": 4.7037075958543475e-05, "epoch": 4.8179317931793175, "percentage": 24.09, "elapsed_time": "1:43:04", "remaining_time": "5:24:48", "throughput": 1494.23, "total_tokens": 9241120} {"current_steps": 43800, "total_steps": 181800, "loss": 0.1106, "lr": 4.70359425073664e-05, "epoch": 4.818481848184819, "percentage": 24.09, "elapsed_time": "1:43:05", "remaining_time": "5:24:47", "throughput": 1494.23, "total_tokens": 9242176} {"current_steps": 43805, "total_steps": 181800, "loss": 0.0321, "lr": 4.703480885309462e-05, "epoch": 4.819031903190319, "percentage": 24.1, "elapsed_time": "1:43:05", "remaining_time": "5:24:46", "throughput": 1494.24, "total_tokens": 9243264} {"current_steps": 43810, "total_steps": 181800, "loss": 0.0066, "lr": 4.703367499573857e-05, "epoch": 4.81958195819582, "percentage": 24.1, "elapsed_time": "1:43:06", "remaining_time": "5:24:46", "throughput": 1494.25, "total_tokens": 9244352} {"current_steps": 43815, "total_steps": 181800, "loss": 0.1029, "lr": 4.7032540935308726e-05, "epoch": 4.82013201320132, "percentage": 24.1, "elapsed_time": "1:43:07", "remaining_time": "5:24:45", "throughput": 1494.26, "total_tokens": 9245408} {"current_steps": 43820, "total_steps": 181800, "loss": 0.0083, "lr": 4.703140667181552e-05, "epoch": 4.82068206820682, "percentage": 24.1, "elapsed_time": "1:43:07", "remaining_time": "5:24:44", "throughput": 1494.25, "total_tokens": 9246400} {"current_steps": 43825, "total_steps": 181800, "loss": 0.0852, "lr": 4.703027220526941e-05, "epoch": 4.821232123212321, "percentage": 24.11, "elapsed_time": "1:43:08", "remaining_time": "5:24:43", "throughput": 1494.25, "total_tokens": 9247424} {"current_steps": 43830, "total_steps": 181800, "loss": 0.0477, "lr": 4.702913753568084e-05, "epoch": 4.821782178217822, "percentage": 24.11, "elapsed_time": "1:43:09", "remaining_time": "5:24:43", "throughput": 1494.25, "total_tokens": 9248448} {"current_steps": 43835, "total_steps": 181800, "loss": 0.0077, "lr": 4.70280026630603e-05, "epoch": 4.822332233223323, "percentage": 24.11, "elapsed_time": "1:43:10", "remaining_time": "5:24:42", "throughput": 1494.25, "total_tokens": 9249504} {"current_steps": 43840, "total_steps": 181800, "loss": 0.0543, "lr": 4.7026867587418215e-05, "epoch": 4.822882288228823, "percentage": 24.11, "elapsed_time": "1:43:10", "remaining_time": "5:24:41", "throughput": 1494.26, "total_tokens": 9250560} {"current_steps": 43845, "total_steps": 181800, "loss": 0.1181, "lr": 4.702573230876507e-05, "epoch": 4.823432343234323, "percentage": 24.12, "elapsed_time": "1:43:11", "remaining_time": "5:24:40", "throughput": 1494.27, "total_tokens": 9251648} {"current_steps": 43850, "total_steps": 181800, "loss": 0.1124, "lr": 4.7024596827111314e-05, "epoch": 4.823982398239824, "percentage": 24.12, "elapsed_time": "1:43:12", "remaining_time": "5:24:40", "throughput": 1494.27, "total_tokens": 9252704} {"current_steps": 43855, "total_steps": 181800, "loss": 0.0263, "lr": 4.702346114246742e-05, "epoch": 4.824532453245324, "percentage": 24.12, "elapsed_time": "1:43:12", "remaining_time": "5:24:39", "throughput": 1494.27, "total_tokens": 9253728} {"current_steps": 43860, "total_steps": 181800, "loss": 0.0195, "lr": 4.702232525484385e-05, "epoch": 4.825082508250825, "percentage": 24.13, "elapsed_time": "1:43:13", "remaining_time": "5:24:38", "throughput": 1494.27, "total_tokens": 9254752} {"current_steps": 43865, "total_steps": 181800, "loss": 0.0909, "lr": 4.702118916425108e-05, "epoch": 4.825632563256326, "percentage": 24.13, "elapsed_time": "1:43:14", "remaining_time": "5:24:37", "throughput": 1494.28, "total_tokens": 9255840} {"current_steps": 43870, "total_steps": 181800, "loss": 0.0644, "lr": 4.7020052870699566e-05, "epoch": 4.826182618261826, "percentage": 24.13, "elapsed_time": "1:43:14", "remaining_time": "5:24:37", "throughput": 1494.29, "total_tokens": 9256960} {"current_steps": 43875, "total_steps": 181800, "loss": 0.1315, "lr": 4.70189163741998e-05, "epoch": 4.826732673267327, "percentage": 24.13, "elapsed_time": "1:43:15", "remaining_time": "5:24:36", "throughput": 1494.28, "total_tokens": 9257920} {"current_steps": 43880, "total_steps": 181800, "loss": 0.0139, "lr": 4.701777967476224e-05, "epoch": 4.827282728272827, "percentage": 24.14, "elapsed_time": "1:43:16", "remaining_time": "5:24:35", "throughput": 1494.29, "total_tokens": 9259040} {"current_steps": 43885, "total_steps": 181800, "loss": 0.023, "lr": 4.701664277239738e-05, "epoch": 4.827832783278328, "percentage": 24.14, "elapsed_time": "1:43:16", "remaining_time": "5:24:34", "throughput": 1494.3, "total_tokens": 9260096} {"current_steps": 43890, "total_steps": 181800, "loss": 0.0216, "lr": 4.701550566711568e-05, "epoch": 4.8283828382838285, "percentage": 24.14, "elapsed_time": "1:43:17", "remaining_time": "5:24:34", "throughput": 1494.3, "total_tokens": 9261152} {"current_steps": 43895, "total_steps": 181800, "loss": 0.0792, "lr": 4.701436835892764e-05, "epoch": 4.828932893289329, "percentage": 24.14, "elapsed_time": "1:43:18", "remaining_time": "5:24:33", "throughput": 1494.3, "total_tokens": 9262176} {"current_steps": 43900, "total_steps": 181800, "loss": 0.0471, "lr": 4.7013230847843715e-05, "epoch": 4.82948294829483, "percentage": 24.15, "elapsed_time": "1:43:19", "remaining_time": "5:24:32", "throughput": 1494.31, "total_tokens": 9263296} {"current_steps": 43905, "total_steps": 181800, "loss": 0.1433, "lr": 4.7012093133874415e-05, "epoch": 4.83003300330033, "percentage": 24.15, "elapsed_time": "1:43:19", "remaining_time": "5:24:31", "throughput": 1494.31, "total_tokens": 9264320} {"current_steps": 43910, "total_steps": 181800, "loss": 0.0264, "lr": 4.701095521703021e-05, "epoch": 4.83058305830583, "percentage": 24.15, "elapsed_time": "1:43:20", "remaining_time": "5:24:31", "throughput": 1494.31, "total_tokens": 9265344} {"current_steps": 43915, "total_steps": 181800, "loss": 0.1093, "lr": 4.700981709732159e-05, "epoch": 4.831133113311331, "percentage": 24.16, "elapsed_time": "1:43:21", "remaining_time": "5:24:30", "throughput": 1494.31, "total_tokens": 9266400} {"current_steps": 43920, "total_steps": 181800, "loss": 0.0219, "lr": 4.700867877475905e-05, "epoch": 4.8316831683168315, "percentage": 24.16, "elapsed_time": "1:43:21", "remaining_time": "5:24:29", "throughput": 1494.33, "total_tokens": 9267520} {"current_steps": 43925, "total_steps": 181800, "loss": 0.0733, "lr": 4.7007540249353086e-05, "epoch": 4.832233223322332, "percentage": 24.16, "elapsed_time": "1:43:22", "remaining_time": "5:24:28", "throughput": 1494.33, "total_tokens": 9268544} {"current_steps": 43930, "total_steps": 181800, "loss": 0.0422, "lr": 4.700640152111417e-05, "epoch": 4.832783278327833, "percentage": 24.16, "elapsed_time": "1:43:23", "remaining_time": "5:24:28", "throughput": 1494.33, "total_tokens": 9269568} {"current_steps": 43935, "total_steps": 181800, "loss": 0.0217, "lr": 4.7005262590052826e-05, "epoch": 4.833333333333333, "percentage": 24.17, "elapsed_time": "1:43:23", "remaining_time": "5:24:27", "throughput": 1494.32, "total_tokens": 9270560} {"current_steps": 43940, "total_steps": 181800, "loss": 0.0659, "lr": 4.700412345617952e-05, "epoch": 4.833883388338834, "percentage": 24.17, "elapsed_time": "1:43:24", "remaining_time": "5:24:26", "throughput": 1494.32, "total_tokens": 9271616} {"current_steps": 43945, "total_steps": 181800, "loss": 0.027, "lr": 4.7002984119504775e-05, "epoch": 4.834433443344334, "percentage": 24.17, "elapsed_time": "1:43:25", "remaining_time": "5:24:25", "throughput": 1494.32, "total_tokens": 9272640} {"current_steps": 43950, "total_steps": 181800, "loss": 0.0451, "lr": 4.7001844580039084e-05, "epoch": 4.834983498349835, "percentage": 24.17, "elapsed_time": "1:43:25", "remaining_time": "5:24:25", "throughput": 1494.33, "total_tokens": 9273728} {"current_steps": 43955, "total_steps": 181800, "loss": 0.0952, "lr": 4.700070483779295e-05, "epoch": 4.835533553355336, "percentage": 24.18, "elapsed_time": "1:43:26", "remaining_time": "5:24:24", "throughput": 1494.34, "total_tokens": 9274848} {"current_steps": 43960, "total_steps": 181800, "loss": 0.0149, "lr": 4.699956489277687e-05, "epoch": 4.836083608360836, "percentage": 24.18, "elapsed_time": "1:43:27", "remaining_time": "5:24:23", "throughput": 1494.35, "total_tokens": 9275904} {"current_steps": 43965, "total_steps": 181800, "loss": 0.0259, "lr": 4.699842474500137e-05, "epoch": 4.836633663366337, "percentage": 24.18, "elapsed_time": "1:43:28", "remaining_time": "5:24:22", "throughput": 1494.35, "total_tokens": 9276960} {"current_steps": 43970, "total_steps": 181800, "loss": 0.0432, "lr": 4.699728439447693e-05, "epoch": 4.837183718371837, "percentage": 24.19, "elapsed_time": "1:43:28", "remaining_time": "5:24:22", "throughput": 1494.35, "total_tokens": 9278016} {"current_steps": 43975, "total_steps": 181800, "loss": 0.1086, "lr": 4.699614384121408e-05, "epoch": 4.837733773377337, "percentage": 24.19, "elapsed_time": "1:43:29", "remaining_time": "5:24:21", "throughput": 1494.37, "total_tokens": 9279136} {"current_steps": 43980, "total_steps": 181800, "loss": 0.038, "lr": 4.6995003085223334e-05, "epoch": 4.838283828382838, "percentage": 24.19, "elapsed_time": "1:43:30", "remaining_time": "5:24:20", "throughput": 1494.38, "total_tokens": 9280224} {"current_steps": 43985, "total_steps": 181800, "loss": 0.0686, "lr": 4.6993862126515186e-05, "epoch": 4.838833883388339, "percentage": 24.19, "elapsed_time": "1:43:30", "remaining_time": "5:24:19", "throughput": 1494.37, "total_tokens": 9281216} {"current_steps": 43990, "total_steps": 181800, "loss": 0.0049, "lr": 4.699272096510018e-05, "epoch": 4.83938393839384, "percentage": 24.2, "elapsed_time": "1:43:31", "remaining_time": "5:24:19", "throughput": 1494.37, "total_tokens": 9282240} {"current_steps": 43995, "total_steps": 181800, "loss": 0.0436, "lr": 4.6991579600988804e-05, "epoch": 4.83993399339934, "percentage": 24.2, "elapsed_time": "1:43:32", "remaining_time": "5:24:18", "throughput": 1494.37, "total_tokens": 9283232} {"current_steps": 44000, "total_steps": 181800, "loss": 0.0263, "lr": 4.69904380341916e-05, "epoch": 4.84048404840484, "percentage": 24.2, "elapsed_time": "1:43:32", "remaining_time": "5:24:17", "throughput": 1494.37, "total_tokens": 9284288} {"current_steps": 44005, "total_steps": 181800, "loss": 0.0327, "lr": 4.698929626471908e-05, "epoch": 4.841034103410341, "percentage": 24.21, "elapsed_time": "1:43:33", "remaining_time": "5:24:16", "throughput": 1494.37, "total_tokens": 9285312} {"current_steps": 44010, "total_steps": 181800, "loss": 0.042, "lr": 4.698815429258177e-05, "epoch": 4.841584158415841, "percentage": 24.21, "elapsed_time": "1:43:34", "remaining_time": "5:24:16", "throughput": 1494.35, "total_tokens": 9286272} {"current_steps": 44015, "total_steps": 181800, "loss": 0.0225, "lr": 4.698701211779018e-05, "epoch": 4.8421342134213425, "percentage": 24.21, "elapsed_time": "1:43:34", "remaining_time": "5:24:15", "throughput": 1494.36, "total_tokens": 9287360} {"current_steps": 44020, "total_steps": 181800, "loss": 0.0311, "lr": 4.698586974035486e-05, "epoch": 4.842684268426843, "percentage": 24.21, "elapsed_time": "1:43:35", "remaining_time": "5:24:14", "throughput": 1494.36, "total_tokens": 9288352} {"current_steps": 44025, "total_steps": 181800, "loss": 0.0224, "lr": 4.6984727160286326e-05, "epoch": 4.843234323432343, "percentage": 24.22, "elapsed_time": "1:43:36", "remaining_time": "5:24:13", "throughput": 1494.36, "total_tokens": 9289408} {"current_steps": 44030, "total_steps": 181800, "loss": 0.0393, "lr": 4.6983584377595116e-05, "epoch": 4.843784378437844, "percentage": 24.22, "elapsed_time": "1:43:36", "remaining_time": "5:24:12", "throughput": 1494.37, "total_tokens": 9290464} {"current_steps": 44035, "total_steps": 181800, "loss": 0.0091, "lr": 4.698244139229175e-05, "epoch": 4.844334433443344, "percentage": 24.22, "elapsed_time": "1:43:37", "remaining_time": "5:24:12", "throughput": 1494.37, "total_tokens": 9291520} {"current_steps": 44040, "total_steps": 181800, "loss": 0.0236, "lr": 4.698129820438677e-05, "epoch": 4.8448844884488445, "percentage": 24.22, "elapsed_time": "1:43:38", "remaining_time": "5:24:11", "throughput": 1494.37, "total_tokens": 9292576} {"current_steps": 44045, "total_steps": 181800, "loss": 0.0894, "lr": 4.698015481389072e-05, "epoch": 4.8454345434543455, "percentage": 24.23, "elapsed_time": "1:43:39", "remaining_time": "5:24:10", "throughput": 1494.38, "total_tokens": 9293632} {"current_steps": 44050, "total_steps": 181800, "loss": 0.0433, "lr": 4.697901122081412e-05, "epoch": 4.845984598459846, "percentage": 24.23, "elapsed_time": "1:43:39", "remaining_time": "5:24:09", "throughput": 1494.38, "total_tokens": 9294656} {"current_steps": 44055, "total_steps": 181800, "loss": 0.0273, "lr": 4.697786742516753e-05, "epoch": 4.846534653465347, "percentage": 24.23, "elapsed_time": "1:43:40", "remaining_time": "5:24:09", "throughput": 1494.37, "total_tokens": 9295680} {"current_steps": 44060, "total_steps": 181800, "loss": 0.083, "lr": 4.6976723426961475e-05, "epoch": 4.847084708470847, "percentage": 24.24, "elapsed_time": "1:43:41", "remaining_time": "5:24:08", "throughput": 1494.37, "total_tokens": 9296672} {"current_steps": 44065, "total_steps": 181800, "loss": 0.0559, "lr": 4.6975579226206505e-05, "epoch": 4.847634763476347, "percentage": 24.24, "elapsed_time": "1:43:41", "remaining_time": "5:24:07", "throughput": 1494.37, "total_tokens": 9297728} {"current_steps": 44070, "total_steps": 181800, "loss": 0.0109, "lr": 4.697443482291317e-05, "epoch": 4.848184818481848, "percentage": 24.24, "elapsed_time": "1:43:42", "remaining_time": "5:24:06", "throughput": 1494.38, "total_tokens": 9298784} {"current_steps": 44075, "total_steps": 181800, "loss": 0.0884, "lr": 4.6973290217092016e-05, "epoch": 4.8487348734873486, "percentage": 24.24, "elapsed_time": "1:43:43", "remaining_time": "5:24:06", "throughput": 1494.39, "total_tokens": 9299872} {"current_steps": 44080, "total_steps": 181800, "loss": 0.0508, "lr": 4.6972145408753584e-05, "epoch": 4.84928492849285, "percentage": 24.25, "elapsed_time": "1:43:43", "remaining_time": "5:24:05", "throughput": 1494.39, "total_tokens": 9300960} {"current_steps": 44085, "total_steps": 181800, "loss": 0.0237, "lr": 4.697100039790844e-05, "epoch": 4.84983498349835, "percentage": 24.25, "elapsed_time": "1:43:44", "remaining_time": "5:24:04", "throughput": 1494.4, "total_tokens": 9302048} {"current_steps": 44090, "total_steps": 181800, "loss": 0.0734, "lr": 4.696985518456711e-05, "epoch": 4.85038503850385, "percentage": 24.25, "elapsed_time": "1:43:45", "remaining_time": "5:24:03", "throughput": 1494.4, "total_tokens": 9303072} {"current_steps": 44095, "total_steps": 181800, "loss": 0.0163, "lr": 4.696870976874018e-05, "epoch": 4.850935093509351, "percentage": 24.25, "elapsed_time": "1:43:45", "remaining_time": "5:24:03", "throughput": 1494.4, "total_tokens": 9304096} {"current_steps": 44100, "total_steps": 181800, "loss": 0.029, "lr": 4.69675641504382e-05, "epoch": 4.851485148514851, "percentage": 24.26, "elapsed_time": "1:43:46", "remaining_time": "5:24:02", "throughput": 1494.39, "total_tokens": 9305088} {"current_steps": 44105, "total_steps": 181800, "loss": 0.0328, "lr": 4.6966418329671715e-05, "epoch": 4.852035203520352, "percentage": 24.26, "elapsed_time": "1:43:47", "remaining_time": "5:24:01", "throughput": 1494.4, "total_tokens": 9306176} {"current_steps": 44110, "total_steps": 181800, "loss": 0.0674, "lr": 4.696527230645129e-05, "epoch": 4.852585258525853, "percentage": 24.26, "elapsed_time": "1:43:48", "remaining_time": "5:24:00", "throughput": 1494.4, "total_tokens": 9307200} {"current_steps": 44115, "total_steps": 181800, "loss": 0.0057, "lr": 4.696412608078749e-05, "epoch": 4.853135313531353, "percentage": 24.27, "elapsed_time": "1:43:48", "remaining_time": "5:24:00", "throughput": 1494.4, "total_tokens": 9308256} {"current_steps": 44120, "total_steps": 181800, "loss": 0.1185, "lr": 4.696297965269089e-05, "epoch": 4.853685368536854, "percentage": 24.27, "elapsed_time": "1:43:49", "remaining_time": "5:23:59", "throughput": 1494.41, "total_tokens": 9309344} {"current_steps": 44125, "total_steps": 181800, "loss": 0.0094, "lr": 4.696183302217203e-05, "epoch": 4.854235423542354, "percentage": 24.27, "elapsed_time": "1:43:50", "remaining_time": "5:23:58", "throughput": 1494.42, "total_tokens": 9310400} {"current_steps": 44130, "total_steps": 181800, "loss": 0.0386, "lr": 4.69606861892415e-05, "epoch": 4.854785478547855, "percentage": 24.27, "elapsed_time": "1:43:50", "remaining_time": "5:23:57", "throughput": 1494.42, "total_tokens": 9311456} {"current_steps": 44135, "total_steps": 181800, "loss": 0.0257, "lr": 4.695953915390987e-05, "epoch": 4.8553355335533555, "percentage": 24.28, "elapsed_time": "1:43:51", "remaining_time": "5:23:57", "throughput": 1494.43, "total_tokens": 9312512} {"current_steps": 44140, "total_steps": 181800, "loss": 0.0147, "lr": 4.6958391916187695e-05, "epoch": 4.855885588558856, "percentage": 24.28, "elapsed_time": "1:43:52", "remaining_time": "5:23:56", "throughput": 1494.43, "total_tokens": 9313568} {"current_steps": 44145, "total_steps": 181800, "loss": 0.0175, "lr": 4.695724447608556e-05, "epoch": 4.856435643564357, "percentage": 24.28, "elapsed_time": "1:43:52", "remaining_time": "5:23:55", "throughput": 1494.44, "total_tokens": 9314624} {"current_steps": 44150, "total_steps": 181800, "loss": 0.1386, "lr": 4.695609683361404e-05, "epoch": 4.856985698569857, "percentage": 24.28, "elapsed_time": "1:43:53", "remaining_time": "5:23:54", "throughput": 1494.44, "total_tokens": 9315680} {"current_steps": 44155, "total_steps": 181800, "loss": 0.1238, "lr": 4.695494898878371e-05, "epoch": 4.857535753575357, "percentage": 24.29, "elapsed_time": "1:43:54", "remaining_time": "5:23:54", "throughput": 1494.44, "total_tokens": 9316736} {"current_steps": 44160, "total_steps": 181800, "loss": 0.036, "lr": 4.6953800941605156e-05, "epoch": 4.858085808580858, "percentage": 24.29, "elapsed_time": "1:43:54", "remaining_time": "5:23:53", "throughput": 1494.44, "total_tokens": 9317760} {"current_steps": 44165, "total_steps": 181800, "loss": 0.0398, "lr": 4.695265269208895e-05, "epoch": 4.8586358635863585, "percentage": 24.29, "elapsed_time": "1:43:55", "remaining_time": "5:23:52", "throughput": 1494.44, "total_tokens": 9318816} {"current_steps": 44170, "total_steps": 181800, "loss": 0.0476, "lr": 4.695150424024567e-05, "epoch": 4.8591859185918596, "percentage": 24.3, "elapsed_time": "1:43:56", "remaining_time": "5:23:51", "throughput": 1494.44, "total_tokens": 9319840} {"current_steps": 44175, "total_steps": 181800, "loss": 0.0774, "lr": 4.695035558608592e-05, "epoch": 4.85973597359736, "percentage": 24.3, "elapsed_time": "1:43:57", "remaining_time": "5:23:51", "throughput": 1494.43, "total_tokens": 9320800} {"current_steps": 44180, "total_steps": 181800, "loss": 0.1008, "lr": 4.694920672962027e-05, "epoch": 4.86028602860286, "percentage": 24.3, "elapsed_time": "1:43:57", "remaining_time": "5:23:50", "throughput": 1494.44, "total_tokens": 9321888} {"current_steps": 44185, "total_steps": 181800, "loss": 0.0587, "lr": 4.694805767085932e-05, "epoch": 4.860836083608361, "percentage": 24.3, "elapsed_time": "1:43:58", "remaining_time": "5:23:49", "throughput": 1494.44, "total_tokens": 9322912} {"current_steps": 44190, "total_steps": 181800, "loss": 0.0275, "lr": 4.694690840981365e-05, "epoch": 4.861386138613861, "percentage": 24.31, "elapsed_time": "1:43:59", "remaining_time": "5:23:48", "throughput": 1494.44, "total_tokens": 9323968} {"current_steps": 44195, "total_steps": 181800, "loss": 0.0172, "lr": 4.694575894649386e-05, "epoch": 4.861936193619362, "percentage": 24.31, "elapsed_time": "1:43:59", "remaining_time": "5:23:48", "throughput": 1494.45, "total_tokens": 9325024} {"current_steps": 44200, "total_steps": 181800, "loss": 0.0147, "lr": 4.694460928091053e-05, "epoch": 4.862486248624863, "percentage": 24.31, "elapsed_time": "1:44:00", "remaining_time": "5:23:47", "throughput": 1494.45, "total_tokens": 9326080} {"current_steps": 44205, "total_steps": 181800, "loss": 0.0932, "lr": 4.6943459413074275e-05, "epoch": 4.863036303630363, "percentage": 24.32, "elapsed_time": "1:44:01", "remaining_time": "5:23:46", "throughput": 1494.45, "total_tokens": 9327104} {"current_steps": 44210, "total_steps": 181800, "loss": 0.0112, "lr": 4.6942309342995676e-05, "epoch": 4.863586358635864, "percentage": 24.32, "elapsed_time": "1:44:01", "remaining_time": "5:23:45", "throughput": 1494.47, "total_tokens": 9328224} {"current_steps": 44215, "total_steps": 181800, "loss": 0.0432, "lr": 4.6941159070685345e-05, "epoch": 4.864136413641364, "percentage": 24.32, "elapsed_time": "1:44:02", "remaining_time": "5:23:45", "throughput": 1494.47, "total_tokens": 9329280} {"current_steps": 44220, "total_steps": 181800, "loss": 0.0835, "lr": 4.694000859615389e-05, "epoch": 4.864686468646864, "percentage": 24.32, "elapsed_time": "1:44:03", "remaining_time": "5:23:44", "throughput": 1494.48, "total_tokens": 9330368} {"current_steps": 44225, "total_steps": 181800, "loss": 0.044, "lr": 4.693885791941189e-05, "epoch": 4.865236523652365, "percentage": 24.33, "elapsed_time": "1:44:03", "remaining_time": "5:23:43", "throughput": 1494.49, "total_tokens": 9331456} {"current_steps": 44230, "total_steps": 181800, "loss": 0.0151, "lr": 4.693770704046997e-05, "epoch": 4.865786578657866, "percentage": 24.33, "elapsed_time": "1:44:04", "remaining_time": "5:23:42", "throughput": 1494.49, "total_tokens": 9332512} {"current_steps": 44235, "total_steps": 181800, "loss": 0.0548, "lr": 4.6936555959338726e-05, "epoch": 4.866336633663367, "percentage": 24.33, "elapsed_time": "1:44:05", "remaining_time": "5:23:42", "throughput": 1494.49, "total_tokens": 9333536} {"current_steps": 44240, "total_steps": 181800, "loss": 0.1062, "lr": 4.6935404676028775e-05, "epoch": 4.866886688668867, "percentage": 24.33, "elapsed_time": "1:44:05", "remaining_time": "5:23:41", "throughput": 1494.49, "total_tokens": 9334560} {"current_steps": 44245, "total_steps": 181800, "loss": 0.064, "lr": 4.693425319055073e-05, "epoch": 4.867436743674367, "percentage": 24.34, "elapsed_time": "1:44:06", "remaining_time": "5:23:40", "throughput": 1494.5, "total_tokens": 9335648} {"current_steps": 44250, "total_steps": 181800, "loss": 0.0046, "lr": 4.693310150291518e-05, "epoch": 4.867986798679868, "percentage": 24.34, "elapsed_time": "1:44:07", "remaining_time": "5:23:39", "throughput": 1494.5, "total_tokens": 9336672} {"current_steps": 44255, "total_steps": 181800, "loss": 0.2001, "lr": 4.693194961313277e-05, "epoch": 4.868536853685368, "percentage": 24.34, "elapsed_time": "1:44:08", "remaining_time": "5:23:39", "throughput": 1494.5, "total_tokens": 9337696} {"current_steps": 44260, "total_steps": 181800, "loss": 0.1478, "lr": 4.693079752121411e-05, "epoch": 4.8690869086908695, "percentage": 24.35, "elapsed_time": "1:44:08", "remaining_time": "5:23:38", "throughput": 1494.5, "total_tokens": 9338752} {"current_steps": 44265, "total_steps": 181800, "loss": 0.0266, "lr": 4.692964522716981e-05, "epoch": 4.86963696369637, "percentage": 24.35, "elapsed_time": "1:44:09", "remaining_time": "5:23:37", "throughput": 1494.5, "total_tokens": 9339808} {"current_steps": 44270, "total_steps": 181800, "loss": 0.2132, "lr": 4.692849273101049e-05, "epoch": 4.87018701870187, "percentage": 24.35, "elapsed_time": "1:44:10", "remaining_time": "5:23:36", "throughput": 1494.5, "total_tokens": 9340832} {"current_steps": 44275, "total_steps": 181800, "loss": 0.0605, "lr": 4.692734003274678e-05, "epoch": 4.870737073707371, "percentage": 24.35, "elapsed_time": "1:44:10", "remaining_time": "5:23:35", "throughput": 1494.51, "total_tokens": 9341888} {"current_steps": 44280, "total_steps": 181800, "loss": 0.0074, "lr": 4.692618713238929e-05, "epoch": 4.871287128712871, "percentage": 24.36, "elapsed_time": "1:44:11", "remaining_time": "5:23:35", "throughput": 1494.51, "total_tokens": 9342944} {"current_steps": 44285, "total_steps": 181800, "loss": 0.0707, "lr": 4.6925034029948654e-05, "epoch": 4.871837183718371, "percentage": 24.36, "elapsed_time": "1:44:12", "remaining_time": "5:23:34", "throughput": 1494.52, "total_tokens": 9344032} {"current_steps": 44290, "total_steps": 181800, "loss": 0.0346, "lr": 4.692388072543551e-05, "epoch": 4.8723872387238725, "percentage": 24.36, "elapsed_time": "1:44:12", "remaining_time": "5:23:33", "throughput": 1494.52, "total_tokens": 9345088} {"current_steps": 44295, "total_steps": 181800, "loss": 0.0149, "lr": 4.692272721886048e-05, "epoch": 4.872937293729373, "percentage": 24.36, "elapsed_time": "1:44:13", "remaining_time": "5:23:32", "throughput": 1494.52, "total_tokens": 9346080} {"current_steps": 44300, "total_steps": 181800, "loss": 0.0496, "lr": 4.6921573510234176e-05, "epoch": 4.873487348734874, "percentage": 24.37, "elapsed_time": "1:44:14", "remaining_time": "5:23:32", "throughput": 1494.53, "total_tokens": 9347200} {"current_steps": 44305, "total_steps": 181800, "loss": 0.0203, "lr": 4.6920419599567255e-05, "epoch": 4.874037403740374, "percentage": 24.37, "elapsed_time": "1:44:14", "remaining_time": "5:23:31", "throughput": 1494.55, "total_tokens": 9348320} {"current_steps": 44310, "total_steps": 181800, "loss": 0.1098, "lr": 4.6919265486870344e-05, "epoch": 4.874587458745875, "percentage": 24.37, "elapsed_time": "1:44:15", "remaining_time": "5:23:30", "throughput": 1494.54, "total_tokens": 9349280} {"current_steps": 44315, "total_steps": 181800, "loss": 0.0195, "lr": 4.691811117215409e-05, "epoch": 4.875137513751375, "percentage": 24.38, "elapsed_time": "1:44:16", "remaining_time": "5:23:29", "throughput": 1494.55, "total_tokens": 9350368} {"current_steps": 44320, "total_steps": 181800, "loss": 0.0606, "lr": 4.691695665542911e-05, "epoch": 4.8756875687568755, "percentage": 24.38, "elapsed_time": "1:44:17", "remaining_time": "5:23:29", "throughput": 1494.55, "total_tokens": 9351424} {"current_steps": 44325, "total_steps": 181800, "loss": 0.062, "lr": 4.691580193670607e-05, "epoch": 4.876237623762377, "percentage": 24.38, "elapsed_time": "1:44:17", "remaining_time": "5:23:28", "throughput": 1494.56, "total_tokens": 9352512} {"current_steps": 44330, "total_steps": 181800, "loss": 0.0693, "lr": 4.691464701599559e-05, "epoch": 4.876787678767877, "percentage": 24.38, "elapsed_time": "1:44:18", "remaining_time": "5:23:27", "throughput": 1494.56, "total_tokens": 9353536} {"current_steps": 44335, "total_steps": 181800, "loss": 0.0471, "lr": 4.691349189330833e-05, "epoch": 4.877337733773377, "percentage": 24.39, "elapsed_time": "1:44:19", "remaining_time": "5:23:26", "throughput": 1494.57, "total_tokens": 9354624} {"current_steps": 44340, "total_steps": 181800, "loss": 0.1223, "lr": 4.6912336568654925e-05, "epoch": 4.877887788778878, "percentage": 24.39, "elapsed_time": "1:44:19", "remaining_time": "5:23:26", "throughput": 1494.59, "total_tokens": 9355776} {"current_steps": 44345, "total_steps": 181800, "loss": 0.0255, "lr": 4.691118104204603e-05, "epoch": 4.878437843784378, "percentage": 24.39, "elapsed_time": "1:44:20", "remaining_time": "5:23:25", "throughput": 1494.59, "total_tokens": 9356832} {"current_steps": 44350, "total_steps": 181800, "loss": 0.1039, "lr": 4.691002531349229e-05, "epoch": 4.878987898789879, "percentage": 24.39, "elapsed_time": "1:44:21", "remaining_time": "5:23:24", "throughput": 1494.6, "total_tokens": 9357920} {"current_steps": 44355, "total_steps": 181800, "loss": 0.1848, "lr": 4.6908869383004374e-05, "epoch": 4.87953795379538, "percentage": 24.4, "elapsed_time": "1:44:21", "remaining_time": "5:23:23", "throughput": 1494.6, "total_tokens": 9358912} {"current_steps": 44360, "total_steps": 181800, "loss": 0.1037, "lr": 4.690771325059291e-05, "epoch": 4.88008800880088, "percentage": 24.4, "elapsed_time": "1:44:22", "remaining_time": "5:23:23", "throughput": 1494.6, "total_tokens": 9360000} {"current_steps": 44365, "total_steps": 181800, "loss": 0.0382, "lr": 4.690655691626856e-05, "epoch": 4.880638063806381, "percentage": 24.4, "elapsed_time": "1:44:23", "remaining_time": "5:23:22", "throughput": 1494.61, "total_tokens": 9361056} {"current_steps": 44370, "total_steps": 181800, "loss": 0.0145, "lr": 4.6905400380042006e-05, "epoch": 4.881188118811881, "percentage": 24.41, "elapsed_time": "1:44:23", "remaining_time": "5:23:21", "throughput": 1494.61, "total_tokens": 9362112} {"current_steps": 44375, "total_steps": 181800, "loss": 0.0197, "lr": 4.690424364192387e-05, "epoch": 4.881738173817382, "percentage": 24.41, "elapsed_time": "1:44:24", "remaining_time": "5:23:20", "throughput": 1494.63, "total_tokens": 9363232} {"current_steps": 44380, "total_steps": 181800, "loss": 0.0897, "lr": 4.6903086701924836e-05, "epoch": 4.882288228822882, "percentage": 24.41, "elapsed_time": "1:44:25", "remaining_time": "5:23:20", "throughput": 1494.62, "total_tokens": 9364224} {"current_steps": 44385, "total_steps": 181800, "loss": 0.0145, "lr": 4.690192956005557e-05, "epoch": 4.882838283828383, "percentage": 24.41, "elapsed_time": "1:44:25", "remaining_time": "5:23:19", "throughput": 1494.63, "total_tokens": 9365312} {"current_steps": 44390, "total_steps": 181800, "loss": 0.1399, "lr": 4.690077221632672e-05, "epoch": 4.883388338833884, "percentage": 24.42, "elapsed_time": "1:44:26", "remaining_time": "5:23:18", "throughput": 1494.64, "total_tokens": 9366400} {"current_steps": 44395, "total_steps": 181800, "loss": 0.0331, "lr": 4.689961467074896e-05, "epoch": 4.883938393839384, "percentage": 24.42, "elapsed_time": "1:44:27", "remaining_time": "5:23:17", "throughput": 1494.64, "total_tokens": 9367456} {"current_steps": 44400, "total_steps": 181800, "loss": 0.1037, "lr": 4.689845692333297e-05, "epoch": 4.884488448844884, "percentage": 24.42, "elapsed_time": "1:44:28", "remaining_time": "5:23:17", "throughput": 1494.65, "total_tokens": 9368512} {"current_steps": 44405, "total_steps": 181800, "loss": 0.0714, "lr": 4.68972989740894e-05, "epoch": 4.885038503850385, "percentage": 24.43, "elapsed_time": "1:44:28", "remaining_time": "5:23:16", "throughput": 1494.66, "total_tokens": 9369600} {"current_steps": 44410, "total_steps": 181800, "loss": 0.0128, "lr": 4.689614082302894e-05, "epoch": 4.885588558855885, "percentage": 24.43, "elapsed_time": "1:44:29", "remaining_time": "5:23:15", "throughput": 1494.67, "total_tokens": 9370720} {"current_steps": 44415, "total_steps": 181800, "loss": 0.0199, "lr": 4.6894982470162254e-05, "epoch": 4.8861386138613865, "percentage": 24.43, "elapsed_time": "1:44:30", "remaining_time": "5:23:14", "throughput": 1494.67, "total_tokens": 9371776} {"current_steps": 44420, "total_steps": 181800, "loss": 0.0347, "lr": 4.689382391550002e-05, "epoch": 4.886688668866887, "percentage": 24.43, "elapsed_time": "1:44:30", "remaining_time": "5:23:14", "throughput": 1494.67, "total_tokens": 9372800} {"current_steps": 44425, "total_steps": 181800, "loss": 0.094, "lr": 4.6892665159052916e-05, "epoch": 4.887238723872387, "percentage": 24.44, "elapsed_time": "1:44:31", "remaining_time": "5:23:13", "throughput": 1494.68, "total_tokens": 9373856} {"current_steps": 44430, "total_steps": 181800, "loss": 0.0158, "lr": 4.689150620083163e-05, "epoch": 4.887788778877888, "percentage": 24.44, "elapsed_time": "1:44:32", "remaining_time": "5:23:12", "throughput": 1494.67, "total_tokens": 9374848} {"current_steps": 44435, "total_steps": 181800, "loss": 0.0372, "lr": 4.6890347040846825e-05, "epoch": 4.888338833883388, "percentage": 24.44, "elapsed_time": "1:44:32", "remaining_time": "5:23:11", "throughput": 1494.67, "total_tokens": 9375904} {"current_steps": 44440, "total_steps": 181800, "loss": 0.077, "lr": 4.68891876791092e-05, "epoch": 4.888888888888889, "percentage": 24.44, "elapsed_time": "1:44:33", "remaining_time": "5:23:11", "throughput": 1494.68, "total_tokens": 9376992} {"current_steps": 44445, "total_steps": 181800, "loss": 0.1261, "lr": 4.6888028115629436e-05, "epoch": 4.8894389438943895, "percentage": 24.45, "elapsed_time": "1:44:34", "remaining_time": "5:23:10", "throughput": 1494.68, "total_tokens": 9378016} {"current_steps": 44450, "total_steps": 181800, "loss": 0.0202, "lr": 4.6886868350418214e-05, "epoch": 4.88998899889989, "percentage": 24.45, "elapsed_time": "1:44:34", "remaining_time": "5:23:09", "throughput": 1494.69, "total_tokens": 9379072} {"current_steps": 44455, "total_steps": 181800, "loss": 0.08, "lr": 4.688570838348624e-05, "epoch": 4.890539053905391, "percentage": 24.45, "elapsed_time": "1:44:35", "remaining_time": "5:23:08", "throughput": 1494.69, "total_tokens": 9380128} {"current_steps": 44460, "total_steps": 181800, "loss": 0.0164, "lr": 4.688454821484418e-05, "epoch": 4.891089108910891, "percentage": 24.46, "elapsed_time": "1:44:36", "remaining_time": "5:23:08", "throughput": 1494.68, "total_tokens": 9381088} {"current_steps": 44465, "total_steps": 181800, "loss": 0.0505, "lr": 4.6883387844502755e-05, "epoch": 4.891639163916391, "percentage": 24.46, "elapsed_time": "1:44:37", "remaining_time": "5:23:07", "throughput": 1494.68, "total_tokens": 9382144} {"current_steps": 44470, "total_steps": 181800, "loss": 0.0071, "lr": 4.6882227272472634e-05, "epoch": 4.892189218921892, "percentage": 24.46, "elapsed_time": "1:44:37", "remaining_time": "5:23:06", "throughput": 1494.69, "total_tokens": 9383200} {"current_steps": 44475, "total_steps": 181800, "loss": 0.0299, "lr": 4.6881066498764524e-05, "epoch": 4.8927392739273925, "percentage": 24.46, "elapsed_time": "1:44:38", "remaining_time": "5:23:05", "throughput": 1494.7, "total_tokens": 9384320} {"current_steps": 44480, "total_steps": 181800, "loss": 0.0488, "lr": 4.687990552338913e-05, "epoch": 4.893289328932894, "percentage": 24.47, "elapsed_time": "1:44:39", "remaining_time": "5:23:04", "throughput": 1494.7, "total_tokens": 9385344} {"current_steps": 44485, "total_steps": 181800, "loss": 0.035, "lr": 4.687874434635715e-05, "epoch": 4.893839383938394, "percentage": 24.47, "elapsed_time": "1:44:39", "remaining_time": "5:23:04", "throughput": 1494.7, "total_tokens": 9386400} {"current_steps": 44490, "total_steps": 181800, "loss": 0.0465, "lr": 4.687758296767927e-05, "epoch": 4.894389438943895, "percentage": 24.47, "elapsed_time": "1:44:40", "remaining_time": "5:23:03", "throughput": 1494.7, "total_tokens": 9387424} {"current_steps": 44495, "total_steps": 181800, "loss": 0.1937, "lr": 4.687642138736621e-05, "epoch": 4.894939493949395, "percentage": 24.47, "elapsed_time": "1:44:41", "remaining_time": "5:23:02", "throughput": 1494.71, "total_tokens": 9388480} {"current_steps": 44500, "total_steps": 181800, "loss": 0.0429, "lr": 4.6875259605428674e-05, "epoch": 4.895489548954895, "percentage": 24.48, "elapsed_time": "1:44:41", "remaining_time": "5:23:01", "throughput": 1494.71, "total_tokens": 9389504} {"current_steps": 44505, "total_steps": 181800, "loss": 0.0442, "lr": 4.6874097621877364e-05, "epoch": 4.896039603960396, "percentage": 24.48, "elapsed_time": "1:44:42", "remaining_time": "5:23:01", "throughput": 1494.71, "total_tokens": 9390560} {"current_steps": 44510, "total_steps": 181800, "loss": 0.0493, "lr": 4.6872935436723e-05, "epoch": 4.896589658965897, "percentage": 24.48, "elapsed_time": "1:44:43", "remaining_time": "5:23:00", "throughput": 1494.72, "total_tokens": 9391680} {"current_steps": 44515, "total_steps": 181800, "loss": 0.2077, "lr": 4.687177304997627e-05, "epoch": 4.897139713971397, "percentage": 24.49, "elapsed_time": "1:44:43", "remaining_time": "5:22:59", "throughput": 1494.73, "total_tokens": 9392768} {"current_steps": 44520, "total_steps": 181800, "loss": 0.0439, "lr": 4.687061046164792e-05, "epoch": 4.897689768976898, "percentage": 24.49, "elapsed_time": "1:44:44", "remaining_time": "5:22:58", "throughput": 1494.75, "total_tokens": 9393888} {"current_steps": 44525, "total_steps": 181800, "loss": 0.0054, "lr": 4.686944767174864e-05, "epoch": 4.898239823982398, "percentage": 24.49, "elapsed_time": "1:44:45", "remaining_time": "5:22:58", "throughput": 1494.76, "total_tokens": 9395040} {"current_steps": 44530, "total_steps": 181800, "loss": 0.0094, "lr": 4.6868284680289154e-05, "epoch": 4.898789878987898, "percentage": 24.49, "elapsed_time": "1:44:45", "remaining_time": "5:22:57", "throughput": 1494.76, "total_tokens": 9396064} {"current_steps": 44535, "total_steps": 181800, "loss": 0.0455, "lr": 4.686712148728019e-05, "epoch": 4.899339933993399, "percentage": 24.5, "elapsed_time": "1:44:46", "remaining_time": "5:22:56", "throughput": 1494.77, "total_tokens": 9397120} {"current_steps": 44540, "total_steps": 181800, "loss": 0.0667, "lr": 4.686595809273244e-05, "epoch": 4.8998899889989, "percentage": 24.5, "elapsed_time": "1:44:47", "remaining_time": "5:22:55", "throughput": 1494.76, "total_tokens": 9398144} {"current_steps": 44545, "total_steps": 181800, "loss": 0.0312, "lr": 4.686479449665666e-05, "epoch": 4.900440044004401, "percentage": 24.5, "elapsed_time": "1:44:48", "remaining_time": "5:22:55", "throughput": 1494.77, "total_tokens": 9399200} {"current_steps": 44550, "total_steps": 181800, "loss": 0.0156, "lr": 4.686363069906357e-05, "epoch": 4.900990099009901, "percentage": 24.5, "elapsed_time": "1:44:48", "remaining_time": "5:22:54", "throughput": 1494.77, "total_tokens": 9400256} {"current_steps": 44555, "total_steps": 181800, "loss": 0.0237, "lr": 4.686246669996387e-05, "epoch": 4.901540154015402, "percentage": 24.51, "elapsed_time": "1:44:49", "remaining_time": "5:22:53", "throughput": 1494.78, "total_tokens": 9401312} {"current_steps": 44560, "total_steps": 181800, "loss": 0.0411, "lr": 4.686130249936831e-05, "epoch": 4.902090209020902, "percentage": 24.51, "elapsed_time": "1:44:50", "remaining_time": "5:22:52", "throughput": 1494.78, "total_tokens": 9402368} {"current_steps": 44565, "total_steps": 181800, "loss": 0.1011, "lr": 4.686013809728762e-05, "epoch": 4.902640264026402, "percentage": 24.51, "elapsed_time": "1:44:50", "remaining_time": "5:22:52", "throughput": 1494.77, "total_tokens": 9403360} {"current_steps": 44570, "total_steps": 181800, "loss": 0.0823, "lr": 4.685897349373253e-05, "epoch": 4.9031903190319035, "percentage": 24.52, "elapsed_time": "1:44:51", "remaining_time": "5:22:51", "throughput": 1494.78, "total_tokens": 9404448} {"current_steps": 44575, "total_steps": 181800, "loss": 0.1207, "lr": 4.6857808688713754e-05, "epoch": 4.903740374037404, "percentage": 24.52, "elapsed_time": "1:44:52", "remaining_time": "5:22:50", "throughput": 1494.79, "total_tokens": 9405536} {"current_steps": 44580, "total_steps": 181800, "loss": 0.0191, "lr": 4.685664368224206e-05, "epoch": 4.904290429042904, "percentage": 24.52, "elapsed_time": "1:44:52", "remaining_time": "5:22:49", "throughput": 1494.81, "total_tokens": 9406656} {"current_steps": 44585, "total_steps": 181800, "loss": 0.0328, "lr": 4.685547847432816e-05, "epoch": 4.904840484048405, "percentage": 24.52, "elapsed_time": "1:44:53", "remaining_time": "5:22:49", "throughput": 1494.8, "total_tokens": 9407680} {"current_steps": 44590, "total_steps": 181800, "loss": 0.0479, "lr": 4.685431306498281e-05, "epoch": 4.905390539053905, "percentage": 24.53, "elapsed_time": "1:44:54", "remaining_time": "5:22:48", "throughput": 1494.81, "total_tokens": 9408736} {"current_steps": 44595, "total_steps": 181800, "loss": 0.0096, "lr": 4.685314745421674e-05, "epoch": 4.905940594059406, "percentage": 24.53, "elapsed_time": "1:44:54", "remaining_time": "5:22:47", "throughput": 1494.81, "total_tokens": 9409792} {"current_steps": 44600, "total_steps": 181800, "loss": 0.0069, "lr": 4.685198164204069e-05, "epoch": 4.9064906490649065, "percentage": 24.53, "elapsed_time": "1:44:55", "remaining_time": "5:22:46", "throughput": 1494.82, "total_tokens": 9410848} {"current_steps": 44605, "total_steps": 181800, "loss": 0.0083, "lr": 4.6850815628465416e-05, "epoch": 4.907040704070407, "percentage": 24.54, "elapsed_time": "1:44:56", "remaining_time": "5:22:46", "throughput": 1494.82, "total_tokens": 9411936} {"current_steps": 44610, "total_steps": 181800, "loss": 0.0913, "lr": 4.6849649413501664e-05, "epoch": 4.907590759075908, "percentage": 24.54, "elapsed_time": "1:44:57", "remaining_time": "5:22:45", "throughput": 1494.83, "total_tokens": 9412992} {"current_steps": 44615, "total_steps": 181800, "loss": 0.1388, "lr": 4.684848299716017e-05, "epoch": 4.908140814081408, "percentage": 24.54, "elapsed_time": "1:44:57", "remaining_time": "5:22:44", "throughput": 1494.84, "total_tokens": 9414112} {"current_steps": 44620, "total_steps": 181800, "loss": 0.0174, "lr": 4.684731637945169e-05, "epoch": 4.908690869086909, "percentage": 24.54, "elapsed_time": "1:44:58", "remaining_time": "5:22:43", "throughput": 1494.85, "total_tokens": 9415168} {"current_steps": 44625, "total_steps": 181800, "loss": 0.0229, "lr": 4.684614956038699e-05, "epoch": 4.909240924092409, "percentage": 24.55, "elapsed_time": "1:44:59", "remaining_time": "5:22:43", "throughput": 1494.86, "total_tokens": 9416256} {"current_steps": 44630, "total_steps": 181800, "loss": 0.0721, "lr": 4.68449825399768e-05, "epoch": 4.9097909790979095, "percentage": 24.55, "elapsed_time": "1:44:59", "remaining_time": "5:22:42", "throughput": 1494.86, "total_tokens": 9417280} {"current_steps": 44635, "total_steps": 181800, "loss": 0.0754, "lr": 4.684381531823189e-05, "epoch": 4.910341034103411, "percentage": 24.55, "elapsed_time": "1:45:00", "remaining_time": "5:22:41", "throughput": 1494.86, "total_tokens": 9418336} {"current_steps": 44640, "total_steps": 181800, "loss": 0.0634, "lr": 4.684264789516302e-05, "epoch": 4.910891089108911, "percentage": 24.55, "elapsed_time": "1:45:01", "remaining_time": "5:22:40", "throughput": 1494.87, "total_tokens": 9419392} {"current_steps": 44645, "total_steps": 181800, "loss": 0.0353, "lr": 4.684148027078094e-05, "epoch": 4.911441144114411, "percentage": 24.56, "elapsed_time": "1:45:01", "remaining_time": "5:22:40", "throughput": 1494.86, "total_tokens": 9420384} {"current_steps": 44650, "total_steps": 181800, "loss": 0.1438, "lr": 4.684031244509643e-05, "epoch": 4.911991199119912, "percentage": 24.56, "elapsed_time": "1:45:02", "remaining_time": "5:22:39", "throughput": 1494.86, "total_tokens": 9421440} {"current_steps": 44655, "total_steps": 181800, "loss": 0.0402, "lr": 4.683914441812023e-05, "epoch": 4.912541254125412, "percentage": 24.56, "elapsed_time": "1:45:03", "remaining_time": "5:22:38", "throughput": 1494.86, "total_tokens": 9422464} {"current_steps": 44660, "total_steps": 181800, "loss": 0.0177, "lr": 4.683797618986312e-05, "epoch": 4.913091309130913, "percentage": 24.57, "elapsed_time": "1:45:03", "remaining_time": "5:22:37", "throughput": 1494.86, "total_tokens": 9423488} {"current_steps": 44665, "total_steps": 181800, "loss": 0.0197, "lr": 4.6836807760335857e-05, "epoch": 4.913641364136414, "percentage": 24.57, "elapsed_time": "1:45:04", "remaining_time": "5:22:37", "throughput": 1494.87, "total_tokens": 9424576} {"current_steps": 44670, "total_steps": 181800, "loss": 0.011, "lr": 4.683563912954921e-05, "epoch": 4.914191419141914, "percentage": 24.57, "elapsed_time": "1:45:05", "remaining_time": "5:22:36", "throughput": 1494.88, "total_tokens": 9425664} {"current_steps": 44675, "total_steps": 181800, "loss": 0.1025, "lr": 4.683447029751397e-05, "epoch": 4.914741474147415, "percentage": 24.57, "elapsed_time": "1:45:05", "remaining_time": "5:22:35", "throughput": 1494.88, "total_tokens": 9426688} {"current_steps": 44680, "total_steps": 181800, "loss": 0.072, "lr": 4.683330126424089e-05, "epoch": 4.915291529152915, "percentage": 24.58, "elapsed_time": "1:45:06", "remaining_time": "5:22:34", "throughput": 1494.88, "total_tokens": 9427712} {"current_steps": 44685, "total_steps": 181800, "loss": 0.034, "lr": 4.6832132029740746e-05, "epoch": 4.915841584158416, "percentage": 24.58, "elapsed_time": "1:45:07", "remaining_time": "5:22:34", "throughput": 1494.88, "total_tokens": 9428768} {"current_steps": 44690, "total_steps": 181800, "loss": 0.0628, "lr": 4.6830962594024316e-05, "epoch": 4.916391639163916, "percentage": 24.58, "elapsed_time": "1:45:08", "remaining_time": "5:22:33", "throughput": 1494.89, "total_tokens": 9429824} {"current_steps": 44695, "total_steps": 181800, "loss": 0.0502, "lr": 4.682979295710238e-05, "epoch": 4.916941694169417, "percentage": 24.58, "elapsed_time": "1:45:08", "remaining_time": "5:22:32", "throughput": 1494.89, "total_tokens": 9430880} {"current_steps": 44700, "total_steps": 181800, "loss": 0.0205, "lr": 4.682862311898572e-05, "epoch": 4.917491749174918, "percentage": 24.59, "elapsed_time": "1:45:09", "remaining_time": "5:22:31", "throughput": 1494.9, "total_tokens": 9432000} {"current_steps": 44705, "total_steps": 181800, "loss": 0.05, "lr": 4.6827453079685116e-05, "epoch": 4.918041804180418, "percentage": 24.59, "elapsed_time": "1:45:10", "remaining_time": "5:22:31", "throughput": 1494.9, "total_tokens": 9432992} {"current_steps": 44710, "total_steps": 181800, "loss": 0.0127, "lr": 4.682628283921134e-05, "epoch": 4.918591859185918, "percentage": 24.59, "elapsed_time": "1:45:10", "remaining_time": "5:22:30", "throughput": 1494.9, "total_tokens": 9434016} {"current_steps": 44715, "total_steps": 181800, "loss": 0.0923, "lr": 4.68251123975752e-05, "epoch": 4.919141914191419, "percentage": 24.6, "elapsed_time": "1:45:11", "remaining_time": "5:22:29", "throughput": 1494.9, "total_tokens": 9435040} {"current_steps": 44720, "total_steps": 181800, "loss": 0.031, "lr": 4.6823941754787464e-05, "epoch": 4.919691969196919, "percentage": 24.6, "elapsed_time": "1:45:12", "remaining_time": "5:22:28", "throughput": 1494.89, "total_tokens": 9436064} {"current_steps": 44725, "total_steps": 181800, "loss": 0.0847, "lr": 4.682277091085893e-05, "epoch": 4.9202420242024205, "percentage": 24.6, "elapsed_time": "1:45:12", "remaining_time": "5:22:27", "throughput": 1494.89, "total_tokens": 9437088} {"current_steps": 44730, "total_steps": 181800, "loss": 0.0277, "lr": 4.6821599865800395e-05, "epoch": 4.920792079207921, "percentage": 24.6, "elapsed_time": "1:45:13", "remaining_time": "5:22:27", "throughput": 1494.9, "total_tokens": 9438144} {"current_steps": 44735, "total_steps": 181800, "loss": 0.043, "lr": 4.682042861962264e-05, "epoch": 4.921342134213422, "percentage": 24.61, "elapsed_time": "1:45:14", "remaining_time": "5:22:26", "throughput": 1494.9, "total_tokens": 9439200} {"current_steps": 44740, "total_steps": 181800, "loss": 0.0508, "lr": 4.6819257172336466e-05, "epoch": 4.921892189218922, "percentage": 24.61, "elapsed_time": "1:45:14", "remaining_time": "5:22:25", "throughput": 1494.9, "total_tokens": 9440192} {"current_steps": 44745, "total_steps": 181800, "loss": 0.0999, "lr": 4.681808552395267e-05, "epoch": 4.922442244224422, "percentage": 24.61, "elapsed_time": "1:45:15", "remaining_time": "5:22:24", "throughput": 1494.91, "total_tokens": 9441280} {"current_steps": 44750, "total_steps": 181800, "loss": 0.0106, "lr": 4.681691367448204e-05, "epoch": 4.922992299229923, "percentage": 24.61, "elapsed_time": "1:45:16", "remaining_time": "5:22:24", "throughput": 1494.92, "total_tokens": 9442368} {"current_steps": 44755, "total_steps": 181800, "loss": 0.0169, "lr": 4.681574162393539e-05, "epoch": 4.9235423542354235, "percentage": 24.62, "elapsed_time": "1:45:17", "remaining_time": "5:22:23", "throughput": 1494.93, "total_tokens": 9443456} {"current_steps": 44760, "total_steps": 181800, "loss": 0.0229, "lr": 4.681456937232352e-05, "epoch": 4.924092409240924, "percentage": 24.62, "elapsed_time": "1:45:17", "remaining_time": "5:22:22", "throughput": 1494.93, "total_tokens": 9444480} {"current_steps": 44765, "total_steps": 181800, "loss": 0.0214, "lr": 4.681339691965724e-05, "epoch": 4.924642464246425, "percentage": 24.62, "elapsed_time": "1:45:18", "remaining_time": "5:22:21", "throughput": 1494.93, "total_tokens": 9445568} {"current_steps": 44770, "total_steps": 181800, "loss": 0.1002, "lr": 4.6812224265947344e-05, "epoch": 4.925192519251925, "percentage": 24.63, "elapsed_time": "1:45:19", "remaining_time": "5:22:21", "throughput": 1494.95, "total_tokens": 9446688} {"current_steps": 44775, "total_steps": 181800, "loss": 0.0296, "lr": 4.681105141120463e-05, "epoch": 4.925742574257426, "percentage": 24.63, "elapsed_time": "1:45:19", "remaining_time": "5:22:20", "throughput": 1494.93, "total_tokens": 9447840} {"current_steps": 44780, "total_steps": 181800, "loss": 0.0365, "lr": 4.6809878355439935e-05, "epoch": 4.926292629262926, "percentage": 24.63, "elapsed_time": "1:45:20", "remaining_time": "5:22:20", "throughput": 1494.94, "total_tokens": 9448928} {"current_steps": 44785, "total_steps": 181800, "loss": 0.0154, "lr": 4.680870509866405e-05, "epoch": 4.9268426842684265, "percentage": 24.63, "elapsed_time": "1:45:21", "remaining_time": "5:22:19", "throughput": 1494.94, "total_tokens": 9450016} {"current_steps": 44790, "total_steps": 181800, "loss": 0.0622, "lr": 4.68075316408878e-05, "epoch": 4.927392739273928, "percentage": 24.64, "elapsed_time": "1:45:22", "remaining_time": "5:22:18", "throughput": 1494.94, "total_tokens": 9451040} {"current_steps": 44795, "total_steps": 181800, "loss": 0.0424, "lr": 4.680635798212199e-05, "epoch": 4.927942794279428, "percentage": 24.64, "elapsed_time": "1:45:22", "remaining_time": "5:22:17", "throughput": 1494.95, "total_tokens": 9452128} {"current_steps": 44800, "total_steps": 181800, "loss": 0.0399, "lr": 4.680518412237744e-05, "epoch": 4.928492849284929, "percentage": 24.64, "elapsed_time": "1:45:23", "remaining_time": "5:22:17", "throughput": 1494.96, "total_tokens": 9453216} {"current_steps": 44805, "total_steps": 181800, "loss": 0.0286, "lr": 4.680401006166498e-05, "epoch": 4.929042904290429, "percentage": 24.65, "elapsed_time": "1:45:24", "remaining_time": "5:22:16", "throughput": 1494.96, "total_tokens": 9454272} {"current_steps": 44810, "total_steps": 181800, "loss": 0.0229, "lr": 4.680283579999541e-05, "epoch": 4.929592959295929, "percentage": 24.65, "elapsed_time": "1:45:24", "remaining_time": "5:22:15", "throughput": 1494.96, "total_tokens": 9455296} {"current_steps": 44815, "total_steps": 181800, "loss": 0.1071, "lr": 4.6801661337379575e-05, "epoch": 4.93014301430143, "percentage": 24.65, "elapsed_time": "1:45:25", "remaining_time": "5:22:14", "throughput": 1494.96, "total_tokens": 9456288} {"current_steps": 44820, "total_steps": 181800, "loss": 0.0408, "lr": 4.680048667382829e-05, "epoch": 4.930693069306931, "percentage": 24.65, "elapsed_time": "1:45:26", "remaining_time": "5:22:14", "throughput": 1494.97, "total_tokens": 9457408} {"current_steps": 44825, "total_steps": 181800, "loss": 0.0894, "lr": 4.6799311809352376e-05, "epoch": 4.931243124312431, "percentage": 24.66, "elapsed_time": "1:45:26", "remaining_time": "5:22:13", "throughput": 1494.97, "total_tokens": 9458432} {"current_steps": 44830, "total_steps": 181800, "loss": 0.0091, "lr": 4.6798136743962665e-05, "epoch": 4.931793179317932, "percentage": 24.66, "elapsed_time": "1:45:27", "remaining_time": "5:22:12", "throughput": 1494.98, "total_tokens": 9459488} {"current_steps": 44835, "total_steps": 181800, "loss": 0.1337, "lr": 4.6796961477669986e-05, "epoch": 4.932343234323432, "percentage": 24.66, "elapsed_time": "1:45:28", "remaining_time": "5:22:11", "throughput": 1494.97, "total_tokens": 9460480} {"current_steps": 44840, "total_steps": 181800, "loss": 0.0277, "lr": 4.6795786010485175e-05, "epoch": 4.932893289328933, "percentage": 24.66, "elapsed_time": "1:45:28", "remaining_time": "5:22:11", "throughput": 1494.97, "total_tokens": 9461504} {"current_steps": 44845, "total_steps": 181800, "loss": 0.0449, "lr": 4.679461034241906e-05, "epoch": 4.933443344334433, "percentage": 24.67, "elapsed_time": "1:45:29", "remaining_time": "5:22:10", "throughput": 1494.97, "total_tokens": 9462560} {"current_steps": 44850, "total_steps": 181800, "loss": 0.0143, "lr": 4.6793434473482484e-05, "epoch": 4.933993399339934, "percentage": 24.67, "elapsed_time": "1:45:30", "remaining_time": "5:22:09", "throughput": 1494.97, "total_tokens": 9463584} {"current_steps": 44855, "total_steps": 181800, "loss": 0.0197, "lr": 4.6792258403686275e-05, "epoch": 4.934543454345435, "percentage": 24.67, "elapsed_time": "1:45:30", "remaining_time": "5:22:08", "throughput": 1494.97, "total_tokens": 9464608} {"current_steps": 44860, "total_steps": 181800, "loss": 0.0276, "lr": 4.679108213304128e-05, "epoch": 4.935093509350935, "percentage": 24.68, "elapsed_time": "1:45:31", "remaining_time": "5:22:08", "throughput": 1494.97, "total_tokens": 9465664} {"current_steps": 44865, "total_steps": 181800, "loss": 0.0437, "lr": 4.6789905661558344e-05, "epoch": 4.935643564356436, "percentage": 24.68, "elapsed_time": "1:45:32", "remaining_time": "5:22:07", "throughput": 1494.98, "total_tokens": 9466720} {"current_steps": 44870, "total_steps": 181800, "loss": 0.0177, "lr": 4.6788728989248286e-05, "epoch": 4.936193619361936, "percentage": 24.68, "elapsed_time": "1:45:33", "remaining_time": "5:22:06", "throughput": 1494.98, "total_tokens": 9467776} {"current_steps": 44875, "total_steps": 181800, "loss": 0.0335, "lr": 4.678755211612198e-05, "epoch": 4.936743674367436, "percentage": 24.68, "elapsed_time": "1:45:33", "remaining_time": "5:22:05", "throughput": 1494.99, "total_tokens": 9468864} {"current_steps": 44880, "total_steps": 181800, "loss": 0.0633, "lr": 4.678637504219026e-05, "epoch": 4.9372937293729375, "percentage": 24.69, "elapsed_time": "1:45:34", "remaining_time": "5:22:05", "throughput": 1495.01, "total_tokens": 9469984} {"current_steps": 44885, "total_steps": 181800, "loss": 0.0612, "lr": 4.678519776746397e-05, "epoch": 4.937843784378438, "percentage": 24.69, "elapsed_time": "1:45:35", "remaining_time": "5:22:04", "throughput": 1495.01, "total_tokens": 9471072} {"current_steps": 44890, "total_steps": 181800, "loss": 0.0266, "lr": 4.678402029195398e-05, "epoch": 4.938393839383938, "percentage": 24.69, "elapsed_time": "1:45:35", "remaining_time": "5:22:03", "throughput": 1495.02, "total_tokens": 9472128} {"current_steps": 44895, "total_steps": 181800, "loss": 0.0941, "lr": 4.678284261567111e-05, "epoch": 4.938943894389439, "percentage": 24.69, "elapsed_time": "1:45:36", "remaining_time": "5:22:02", "throughput": 1495.03, "total_tokens": 9473216} {"current_steps": 44900, "total_steps": 181800, "loss": 0.1373, "lr": 4.678166473862624e-05, "epoch": 4.939493949394939, "percentage": 24.7, "elapsed_time": "1:45:37", "remaining_time": "5:22:02", "throughput": 1495.03, "total_tokens": 9474240} {"current_steps": 44905, "total_steps": 181800, "loss": 0.0068, "lr": 4.678048666083022e-05, "epoch": 4.94004400440044, "percentage": 24.7, "elapsed_time": "1:45:37", "remaining_time": "5:22:01", "throughput": 1495.04, "total_tokens": 9475360} {"current_steps": 44910, "total_steps": 181800, "loss": 0.1315, "lr": 4.6779308382293904e-05, "epoch": 4.9405940594059405, "percentage": 24.7, "elapsed_time": "1:45:38", "remaining_time": "5:22:00", "throughput": 1495.05, "total_tokens": 9476416} {"current_steps": 44915, "total_steps": 181800, "loss": 0.0303, "lr": 4.677812990302816e-05, "epoch": 4.941144114411442, "percentage": 24.71, "elapsed_time": "1:45:39", "remaining_time": "5:21:59", "throughput": 1495.05, "total_tokens": 9477504} {"current_steps": 44920, "total_steps": 181800, "loss": 0.0486, "lr": 4.677695122304383e-05, "epoch": 4.941694169416942, "percentage": 24.71, "elapsed_time": "1:45:39", "remaining_time": "5:21:58", "throughput": 1495.06, "total_tokens": 9478592} {"current_steps": 44925, "total_steps": 181800, "loss": 0.0041, "lr": 4.6775772342351795e-05, "epoch": 4.942244224422442, "percentage": 24.71, "elapsed_time": "1:45:40", "remaining_time": "5:21:58", "throughput": 1495.07, "total_tokens": 9479680} {"current_steps": 44930, "total_steps": 181800, "loss": 0.0247, "lr": 4.6774593260962915e-05, "epoch": 4.942794279427943, "percentage": 24.71, "elapsed_time": "1:45:41", "remaining_time": "5:21:57", "throughput": 1495.07, "total_tokens": 9480704} {"current_steps": 44935, "total_steps": 181800, "loss": 0.0204, "lr": 4.677341397888806e-05, "epoch": 4.943344334433443, "percentage": 24.72, "elapsed_time": "1:45:41", "remaining_time": "5:21:56", "throughput": 1495.08, "total_tokens": 9481760} {"current_steps": 44940, "total_steps": 181800, "loss": 0.0987, "lr": 4.67722344961381e-05, "epoch": 4.9438943894389435, "percentage": 24.72, "elapsed_time": "1:45:42", "remaining_time": "5:21:55", "throughput": 1495.07, "total_tokens": 9482720} {"current_steps": 44945, "total_steps": 181800, "loss": 0.0951, "lr": 4.6771054812723896e-05, "epoch": 4.944444444444445, "percentage": 24.72, "elapsed_time": "1:45:43", "remaining_time": "5:21:55", "throughput": 1495.07, "total_tokens": 9483776} {"current_steps": 44950, "total_steps": 181800, "loss": 0.1456, "lr": 4.676987492865633e-05, "epoch": 4.944994499449945, "percentage": 24.72, "elapsed_time": "1:45:44", "remaining_time": "5:21:54", "throughput": 1495.08, "total_tokens": 9484832} {"current_steps": 44955, "total_steps": 181800, "loss": 0.0246, "lr": 4.676869484394627e-05, "epoch": 4.945544554455445, "percentage": 24.73, "elapsed_time": "1:45:44", "remaining_time": "5:21:53", "throughput": 1495.08, "total_tokens": 9485856} {"current_steps": 44960, "total_steps": 181800, "loss": 0.0203, "lr": 4.6767514558604596e-05, "epoch": 4.946094609460946, "percentage": 24.73, "elapsed_time": "1:45:45", "remaining_time": "5:21:52", "throughput": 1495.08, "total_tokens": 9486912} {"current_steps": 44965, "total_steps": 181800, "loss": 0.0885, "lr": 4.676633407264218e-05, "epoch": 4.946644664466446, "percentage": 24.73, "elapsed_time": "1:45:46", "remaining_time": "5:21:52", "throughput": 1495.08, "total_tokens": 9487968} {"current_steps": 44970, "total_steps": 181800, "loss": 0.0208, "lr": 4.6765153386069915e-05, "epoch": 4.947194719471947, "percentage": 24.74, "elapsed_time": "1:45:46", "remaining_time": "5:21:51", "throughput": 1495.1, "total_tokens": 9489088} {"current_steps": 44975, "total_steps": 181800, "loss": 0.0273, "lr": 4.676397249889868e-05, "epoch": 4.947744774477448, "percentage": 24.74, "elapsed_time": "1:45:47", "remaining_time": "5:21:50", "throughput": 1495.1, "total_tokens": 9490144} {"current_steps": 44980, "total_steps": 181800, "loss": 0.0573, "lr": 4.676279141113934e-05, "epoch": 4.948294829482949, "percentage": 24.74, "elapsed_time": "1:45:48", "remaining_time": "5:21:49", "throughput": 1495.11, "total_tokens": 9491200} {"current_steps": 44985, "total_steps": 181800, "loss": 0.0116, "lr": 4.67616101228028e-05, "epoch": 4.948844884488449, "percentage": 24.74, "elapsed_time": "1:45:48", "remaining_time": "5:21:49", "throughput": 1495.1, "total_tokens": 9492224} {"current_steps": 44990, "total_steps": 181800, "loss": 0.0815, "lr": 4.6760428633899946e-05, "epoch": 4.949394939493949, "percentage": 24.75, "elapsed_time": "1:45:49", "remaining_time": "5:21:48", "throughput": 1495.1, "total_tokens": 9493248} {"current_steps": 44995, "total_steps": 181800, "loss": 0.0617, "lr": 4.675924694444166e-05, "epoch": 4.94994499449945, "percentage": 24.75, "elapsed_time": "1:45:50", "remaining_time": "5:21:47", "throughput": 1495.11, "total_tokens": 9494304} {"current_steps": 45000, "total_steps": 181800, "loss": 0.0262, "lr": 4.6758065054438834e-05, "epoch": 4.9504950495049505, "percentage": 24.75, "elapsed_time": "1:45:50", "remaining_time": "5:21:46", "throughput": 1495.11, "total_tokens": 9495328} {"current_steps": 45005, "total_steps": 181800, "loss": 0.0096, "lr": 4.675688296390237e-05, "epoch": 4.951045104510451, "percentage": 24.76, "elapsed_time": "1:45:51", "remaining_time": "5:21:46", "throughput": 1495.1, "total_tokens": 9496320} {"current_steps": 45010, "total_steps": 181800, "loss": 0.06, "lr": 4.675570067284315e-05, "epoch": 4.951595159515952, "percentage": 24.76, "elapsed_time": "1:45:52", "remaining_time": "5:21:45", "throughput": 1495.11, "total_tokens": 9497408} {"current_steps": 45015, "total_steps": 181800, "loss": 0.153, "lr": 4.6754518181272075e-05, "epoch": 4.952145214521452, "percentage": 24.76, "elapsed_time": "1:45:52", "remaining_time": "5:21:44", "throughput": 1495.12, "total_tokens": 9498496} {"current_steps": 45020, "total_steps": 181800, "loss": 0.0091, "lr": 4.6753335489200044e-05, "epoch": 4.952695269526953, "percentage": 24.76, "elapsed_time": "1:45:53", "remaining_time": "5:21:43", "throughput": 1495.12, "total_tokens": 9499520} {"current_steps": 45025, "total_steps": 181800, "loss": 0.0531, "lr": 4.6752152596637965e-05, "epoch": 4.953245324532453, "percentage": 24.77, "elapsed_time": "1:45:54", "remaining_time": "5:21:43", "throughput": 1495.13, "total_tokens": 9500608} {"current_steps": 45030, "total_steps": 181800, "loss": 0.0054, "lr": 4.675096950359673e-05, "epoch": 4.9537953795379535, "percentage": 24.77, "elapsed_time": "1:45:55", "remaining_time": "5:21:42", "throughput": 1495.14, "total_tokens": 9501664} {"current_steps": 45035, "total_steps": 181800, "loss": 0.0841, "lr": 4.674978621008724e-05, "epoch": 4.9543454345434546, "percentage": 24.77, "elapsed_time": "1:45:55", "remaining_time": "5:21:41", "throughput": 1495.15, "total_tokens": 9502752} {"current_steps": 45040, "total_steps": 181800, "loss": 0.0781, "lr": 4.6748602716120414e-05, "epoch": 4.954895489548955, "percentage": 24.77, "elapsed_time": "1:45:56", "remaining_time": "5:21:40", "throughput": 1495.15, "total_tokens": 9503776} {"current_steps": 45045, "total_steps": 181800, "loss": 0.0256, "lr": 4.674741902170715e-05, "epoch": 4.955445544554456, "percentage": 24.78, "elapsed_time": "1:45:57", "remaining_time": "5:21:39", "throughput": 1495.15, "total_tokens": 9504832} {"current_steps": 45050, "total_steps": 181800, "loss": 0.0208, "lr": 4.674623512685836e-05, "epoch": 4.955995599559956, "percentage": 24.78, "elapsed_time": "1:45:57", "remaining_time": "5:21:39", "throughput": 1495.15, "total_tokens": 9505856} {"current_steps": 45055, "total_steps": 181800, "loss": 0.0139, "lr": 4.6745051031584964e-05, "epoch": 4.956545654565456, "percentage": 24.78, "elapsed_time": "1:45:58", "remaining_time": "5:21:38", "throughput": 1495.16, "total_tokens": 9506976} {"current_steps": 45060, "total_steps": 181800, "loss": 0.0445, "lr": 4.674386673589786e-05, "epoch": 4.957095709570957, "percentage": 24.79, "elapsed_time": "1:45:59", "remaining_time": "5:21:37", "throughput": 1495.16, "total_tokens": 9507968} {"current_steps": 45065, "total_steps": 181800, "loss": 0.0265, "lr": 4.674268223980797e-05, "epoch": 4.957645764576458, "percentage": 24.79, "elapsed_time": "1:45:59", "remaining_time": "5:21:36", "throughput": 1495.18, "total_tokens": 9509120} {"current_steps": 45070, "total_steps": 181800, "loss": 0.1053, "lr": 4.6741497543326206e-05, "epoch": 4.958195819581958, "percentage": 24.79, "elapsed_time": "1:46:00", "remaining_time": "5:21:36", "throughput": 1495.18, "total_tokens": 9510208} {"current_steps": 45075, "total_steps": 181800, "loss": 0.0325, "lr": 4.67403126464635e-05, "epoch": 4.958745874587459, "percentage": 24.79, "elapsed_time": "1:46:01", "remaining_time": "5:21:35", "throughput": 1495.19, "total_tokens": 9511296} {"current_steps": 45080, "total_steps": 181800, "loss": 0.0193, "lr": 4.6739127549230754e-05, "epoch": 4.959295929592959, "percentage": 24.8, "elapsed_time": "1:46:01", "remaining_time": "5:21:34", "throughput": 1495.21, "total_tokens": 9512448} {"current_steps": 45085, "total_steps": 181800, "loss": 0.0598, "lr": 4.673794225163891e-05, "epoch": 4.95984598459846, "percentage": 24.8, "elapsed_time": "1:46:02", "remaining_time": "5:21:33", "throughput": 1495.21, "total_tokens": 9513472} {"current_steps": 45090, "total_steps": 181800, "loss": 0.0231, "lr": 4.6736756753698884e-05, "epoch": 4.96039603960396, "percentage": 24.8, "elapsed_time": "1:46:03", "remaining_time": "5:21:33", "throughput": 1495.21, "total_tokens": 9514464} {"current_steps": 45095, "total_steps": 181800, "loss": 0.0052, "lr": 4.6735571055421604e-05, "epoch": 4.960946094609461, "percentage": 24.8, "elapsed_time": "1:46:03", "remaining_time": "5:21:32", "throughput": 1495.23, "total_tokens": 9515616} {"current_steps": 45100, "total_steps": 181800, "loss": 0.0179, "lr": 4.673438515681798e-05, "epoch": 4.961496149614962, "percentage": 24.81, "elapsed_time": "1:46:04", "remaining_time": "5:21:31", "throughput": 1495.22, "total_tokens": 9516608} {"current_steps": 45105, "total_steps": 181800, "loss": 0.0977, "lr": 4.673319905789897e-05, "epoch": 4.962046204620462, "percentage": 24.81, "elapsed_time": "1:46:05", "remaining_time": "5:21:30", "throughput": 1495.22, "total_tokens": 9517632} {"current_steps": 45110, "total_steps": 181800, "loss": 0.0621, "lr": 4.673201275867549e-05, "epoch": 4.962596259625963, "percentage": 24.81, "elapsed_time": "1:46:06", "remaining_time": "5:21:30", "throughput": 1495.22, "total_tokens": 9518656} {"current_steps": 45115, "total_steps": 181800, "loss": 0.1297, "lr": 4.673082625915847e-05, "epoch": 4.963146314631463, "percentage": 24.82, "elapsed_time": "1:46:06", "remaining_time": "5:21:29", "throughput": 1495.21, "total_tokens": 9519648} {"current_steps": 45120, "total_steps": 181800, "loss": 0.0234, "lr": 4.672963955935886e-05, "epoch": 4.963696369636963, "percentage": 24.82, "elapsed_time": "1:46:07", "remaining_time": "5:21:28", "throughput": 1495.21, "total_tokens": 9520672} {"current_steps": 45125, "total_steps": 181800, "loss": 0.0319, "lr": 4.672845265928759e-05, "epoch": 4.9642464246424645, "percentage": 24.82, "elapsed_time": "1:46:08", "remaining_time": "5:21:27", "throughput": 1495.22, "total_tokens": 9521760} {"current_steps": 45130, "total_steps": 181800, "loss": 0.0292, "lr": 4.672726555895559e-05, "epoch": 4.964796479647965, "percentage": 24.82, "elapsed_time": "1:46:08", "remaining_time": "5:21:27", "throughput": 1495.23, "total_tokens": 9522816} {"current_steps": 45135, "total_steps": 181800, "loss": 0.1076, "lr": 4.672607825837382e-05, "epoch": 4.965346534653465, "percentage": 24.83, "elapsed_time": "1:46:09", "remaining_time": "5:21:26", "throughput": 1495.24, "total_tokens": 9523936} {"current_steps": 45140, "total_steps": 181800, "loss": 0.0699, "lr": 4.67248907575532e-05, "epoch": 4.965896589658966, "percentage": 24.83, "elapsed_time": "1:46:10", "remaining_time": "5:21:25", "throughput": 1495.24, "total_tokens": 9524928} {"current_steps": 45145, "total_steps": 181800, "loss": 0.0799, "lr": 4.6723703056504697e-05, "epoch": 4.966446644664466, "percentage": 24.83, "elapsed_time": "1:46:10", "remaining_time": "5:21:24", "throughput": 1495.23, "total_tokens": 9525888} {"current_steps": 45150, "total_steps": 181800, "loss": 0.0427, "lr": 4.6722515155239245e-05, "epoch": 4.966996699669967, "percentage": 24.83, "elapsed_time": "1:46:11", "remaining_time": "5:21:24", "throughput": 1495.23, "total_tokens": 9526944} {"current_steps": 45155, "total_steps": 181800, "loss": 0.0249, "lr": 4.672132705376779e-05, "epoch": 4.9675467546754675, "percentage": 24.84, "elapsed_time": "1:46:12", "remaining_time": "5:21:23", "throughput": 1495.24, "total_tokens": 9528032} {"current_steps": 45160, "total_steps": 181800, "loss": 0.0228, "lr": 4.6720138752101287e-05, "epoch": 4.968096809680969, "percentage": 24.84, "elapsed_time": "1:46:12", "remaining_time": "5:21:22", "throughput": 1495.24, "total_tokens": 9529056} {"current_steps": 45165, "total_steps": 181800, "loss": 0.0408, "lr": 4.671895025025069e-05, "epoch": 4.968646864686469, "percentage": 24.84, "elapsed_time": "1:46:13", "remaining_time": "5:21:21", "throughput": 1495.24, "total_tokens": 9530080} {"current_steps": 45170, "total_steps": 181800, "loss": 0.0689, "lr": 4.6717761548226946e-05, "epoch": 4.969196919691969, "percentage": 24.85, "elapsed_time": "1:46:14", "remaining_time": "5:21:20", "throughput": 1495.23, "total_tokens": 9531072} {"current_steps": 45175, "total_steps": 181800, "loss": 0.0392, "lr": 4.6716572646041024e-05, "epoch": 4.96974697469747, "percentage": 24.85, "elapsed_time": "1:46:14", "remaining_time": "5:21:20", "throughput": 1495.23, "total_tokens": 9532096} {"current_steps": 45180, "total_steps": 181800, "loss": 0.0458, "lr": 4.671538354370386e-05, "epoch": 4.97029702970297, "percentage": 24.85, "elapsed_time": "1:46:15", "remaining_time": "5:21:19", "throughput": 1495.23, "total_tokens": 9533120} {"current_steps": 45185, "total_steps": 181800, "loss": 0.0609, "lr": 4.6714194241226436e-05, "epoch": 4.9708470847084705, "percentage": 24.85, "elapsed_time": "1:46:16", "remaining_time": "5:21:18", "throughput": 1495.23, "total_tokens": 9534144} {"current_steps": 45190, "total_steps": 181800, "loss": 0.0377, "lr": 4.6713004738619705e-05, "epoch": 4.971397139713972, "percentage": 24.86, "elapsed_time": "1:46:17", "remaining_time": "5:21:17", "throughput": 1495.25, "total_tokens": 9535264} {"current_steps": 45195, "total_steps": 181800, "loss": 0.0217, "lr": 4.671181503589461e-05, "epoch": 4.971947194719472, "percentage": 24.86, "elapsed_time": "1:46:17", "remaining_time": "5:21:17", "throughput": 1495.25, "total_tokens": 9536288} {"current_steps": 45200, "total_steps": 181800, "loss": 0.0798, "lr": 4.6710625133062155e-05, "epoch": 4.972497249724973, "percentage": 24.86, "elapsed_time": "1:46:18", "remaining_time": "5:21:16", "throughput": 1495.26, "total_tokens": 9537376} {"current_steps": 45205, "total_steps": 181800, "loss": 0.0098, "lr": 4.670943503013328e-05, "epoch": 4.973047304730473, "percentage": 24.87, "elapsed_time": "1:46:19", "remaining_time": "5:21:15", "throughput": 1495.26, "total_tokens": 9538432} {"current_steps": 45210, "total_steps": 181800, "loss": 0.0232, "lr": 4.6708244727118955e-05, "epoch": 4.973597359735973, "percentage": 24.87, "elapsed_time": "1:46:19", "remaining_time": "5:21:14", "throughput": 1495.26, "total_tokens": 9539488} {"current_steps": 45215, "total_steps": 181800, "loss": 0.061, "lr": 4.670705422403016e-05, "epoch": 4.974147414741474, "percentage": 24.87, "elapsed_time": "1:46:20", "remaining_time": "5:21:14", "throughput": 1495.26, "total_tokens": 9540512} {"current_steps": 45220, "total_steps": 181800, "loss": 0.1276, "lr": 4.670586352087786e-05, "epoch": 4.974697469746975, "percentage": 24.87, "elapsed_time": "1:46:21", "remaining_time": "5:21:13", "throughput": 1495.27, "total_tokens": 9541600} {"current_steps": 45225, "total_steps": 181800, "loss": 0.0235, "lr": 4.670467261767303e-05, "epoch": 4.975247524752476, "percentage": 24.88, "elapsed_time": "1:46:21", "remaining_time": "5:21:12", "throughput": 1495.27, "total_tokens": 9542624} {"current_steps": 45230, "total_steps": 181800, "loss": 0.0905, "lr": 4.670348151442665e-05, "epoch": 4.975797579757976, "percentage": 24.88, "elapsed_time": "1:46:22", "remaining_time": "5:21:11", "throughput": 1495.26, "total_tokens": 9543584} {"current_steps": 45235, "total_steps": 181800, "loss": 0.0425, "lr": 4.670229021114969e-05, "epoch": 4.976347634763476, "percentage": 24.88, "elapsed_time": "1:46:23", "remaining_time": "5:21:11", "throughput": 1495.26, "total_tokens": 9544608} {"current_steps": 45240, "total_steps": 181800, "loss": 0.0168, "lr": 4.670109870785314e-05, "epoch": 4.976897689768977, "percentage": 24.88, "elapsed_time": "1:46:23", "remaining_time": "5:21:10", "throughput": 1495.28, "total_tokens": 9545728} {"current_steps": 45245, "total_steps": 181800, "loss": 0.0776, "lr": 4.669990700454797e-05, "epoch": 4.977447744774477, "percentage": 24.89, "elapsed_time": "1:46:24", "remaining_time": "5:21:09", "throughput": 1495.29, "total_tokens": 9546816} {"current_steps": 45250, "total_steps": 181800, "loss": 0.0208, "lr": 4.6698715101245186e-05, "epoch": 4.977997799779978, "percentage": 24.89, "elapsed_time": "1:46:25", "remaining_time": "5:21:08", "throughput": 1495.29, "total_tokens": 9547872} {"current_steps": 45255, "total_steps": 181800, "loss": 0.0885, "lr": 4.669752299795574e-05, "epoch": 4.978547854785479, "percentage": 24.89, "elapsed_time": "1:46:25", "remaining_time": "5:21:08", "throughput": 1495.29, "total_tokens": 9548864} {"current_steps": 45260, "total_steps": 181800, "loss": 0.0701, "lr": 4.669633069469064e-05, "epoch": 4.979097909790979, "percentage": 24.9, "elapsed_time": "1:46:26", "remaining_time": "5:21:07", "throughput": 1495.29, "total_tokens": 9549952} {"current_steps": 45265, "total_steps": 181800, "loss": 0.114, "lr": 4.669513819146087e-05, "epoch": 4.97964796479648, "percentage": 24.9, "elapsed_time": "1:46:27", "remaining_time": "5:21:06", "throughput": 1495.3, "total_tokens": 9551040} {"current_steps": 45270, "total_steps": 181800, "loss": 0.004, "lr": 4.669394548827742e-05, "epoch": 4.98019801980198, "percentage": 24.9, "elapsed_time": "1:46:28", "remaining_time": "5:21:05", "throughput": 1495.3, "total_tokens": 9552064} {"current_steps": 45275, "total_steps": 181800, "loss": 0.1026, "lr": 4.66927525851513e-05, "epoch": 4.98074807480748, "percentage": 24.9, "elapsed_time": "1:46:28", "remaining_time": "5:21:04", "throughput": 1495.31, "total_tokens": 9553120} {"current_steps": 45280, "total_steps": 181800, "loss": 0.0704, "lr": 4.669155948209347e-05, "epoch": 4.9812981298129815, "percentage": 24.91, "elapsed_time": "1:46:29", "remaining_time": "5:21:04", "throughput": 1495.32, "total_tokens": 9554240} {"current_steps": 45285, "total_steps": 181800, "loss": 0.0993, "lr": 4.669036617911495e-05, "epoch": 4.981848184818482, "percentage": 24.91, "elapsed_time": "1:46:30", "remaining_time": "5:21:03", "throughput": 1495.33, "total_tokens": 9555360} {"current_steps": 45290, "total_steps": 181800, "loss": 0.0349, "lr": 4.6689172676226744e-05, "epoch": 4.982398239823983, "percentage": 24.91, "elapsed_time": "1:46:30", "remaining_time": "5:21:02", "throughput": 1495.33, "total_tokens": 9556384} {"current_steps": 45295, "total_steps": 181800, "loss": 0.0846, "lr": 4.6687978973439825e-05, "epoch": 4.982948294829483, "percentage": 24.91, "elapsed_time": "1:46:31", "remaining_time": "5:21:01", "throughput": 1495.34, "total_tokens": 9557472} {"current_steps": 45300, "total_steps": 181800, "loss": 0.088, "lr": 4.668678507076522e-05, "epoch": 4.983498349834983, "percentage": 24.92, "elapsed_time": "1:46:32", "remaining_time": "5:21:01", "throughput": 1495.34, "total_tokens": 9558528} {"current_steps": 45305, "total_steps": 181800, "loss": 0.1247, "lr": 4.6685590968213924e-05, "epoch": 4.984048404840484, "percentage": 24.92, "elapsed_time": "1:46:32", "remaining_time": "5:21:00", "throughput": 1495.35, "total_tokens": 9559616} {"current_steps": 45310, "total_steps": 181800, "loss": 0.0496, "lr": 4.668439666579694e-05, "epoch": 4.9845984598459845, "percentage": 24.92, "elapsed_time": "1:46:33", "remaining_time": "5:20:59", "throughput": 1495.36, "total_tokens": 9560672} {"current_steps": 45315, "total_steps": 181800, "loss": 0.0179, "lr": 4.668320216352527e-05, "epoch": 4.985148514851485, "percentage": 24.93, "elapsed_time": "1:46:34", "remaining_time": "5:20:58", "throughput": 1495.37, "total_tokens": 9561760} {"current_steps": 45320, "total_steps": 181800, "loss": 0.0608, "lr": 4.668200746140994e-05, "epoch": 4.985698569856986, "percentage": 24.93, "elapsed_time": "1:46:34", "remaining_time": "5:20:58", "throughput": 1495.37, "total_tokens": 9562784} {"current_steps": 45325, "total_steps": 181800, "loss": 0.0492, "lr": 4.668081255946195e-05, "epoch": 4.986248624862486, "percentage": 24.93, "elapsed_time": "1:46:35", "remaining_time": "5:20:57", "throughput": 1495.37, "total_tokens": 9563808} {"current_steps": 45330, "total_steps": 181800, "loss": 0.0146, "lr": 4.667961745769231e-05, "epoch": 4.986798679867987, "percentage": 24.93, "elapsed_time": "1:46:36", "remaining_time": "5:20:56", "throughput": 1495.36, "total_tokens": 9564832} {"current_steps": 45335, "total_steps": 181800, "loss": 0.0242, "lr": 4.667842215611204e-05, "epoch": 4.987348734873487, "percentage": 24.94, "elapsed_time": "1:46:37", "remaining_time": "5:20:55", "throughput": 1495.37, "total_tokens": 9565888} {"current_steps": 45340, "total_steps": 181800, "loss": 0.0709, "lr": 4.6677226654732154e-05, "epoch": 4.987898789878988, "percentage": 24.94, "elapsed_time": "1:46:37", "remaining_time": "5:20:55", "throughput": 1495.36, "total_tokens": 9566880} {"current_steps": 45345, "total_steps": 181800, "loss": 0.056, "lr": 4.667603095356368e-05, "epoch": 4.988448844884489, "percentage": 24.94, "elapsed_time": "1:46:38", "remaining_time": "5:20:54", "throughput": 1495.37, "total_tokens": 9567936} {"current_steps": 45350, "total_steps": 181800, "loss": 0.0221, "lr": 4.667483505261762e-05, "epoch": 4.988998899889989, "percentage": 24.94, "elapsed_time": "1:46:39", "remaining_time": "5:20:53", "throughput": 1495.38, "total_tokens": 9569024} {"current_steps": 45355, "total_steps": 181800, "loss": 0.024, "lr": 4.667363895190501e-05, "epoch": 4.98954895489549, "percentage": 24.95, "elapsed_time": "1:46:39", "remaining_time": "5:20:52", "throughput": 1495.39, "total_tokens": 9570112} {"current_steps": 45360, "total_steps": 181800, "loss": 0.0353, "lr": 4.6672442651436864e-05, "epoch": 4.99009900990099, "percentage": 24.95, "elapsed_time": "1:46:40", "remaining_time": "5:20:52", "throughput": 1495.38, "total_tokens": 9571136} {"current_steps": 45365, "total_steps": 181800, "loss": 0.0891, "lr": 4.667124615122422e-05, "epoch": 4.99064906490649, "percentage": 24.95, "elapsed_time": "1:46:41", "remaining_time": "5:20:51", "throughput": 1495.39, "total_tokens": 9572224} {"current_steps": 45370, "total_steps": 181800, "loss": 0.0344, "lr": 4.66700494512781e-05, "epoch": 4.991199119911991, "percentage": 24.96, "elapsed_time": "1:46:41", "remaining_time": "5:20:50", "throughput": 1495.4, "total_tokens": 9573312} {"current_steps": 45375, "total_steps": 181800, "loss": 0.084, "lr": 4.6668852551609524e-05, "epoch": 4.991749174917492, "percentage": 24.96, "elapsed_time": "1:46:42", "remaining_time": "5:20:49", "throughput": 1495.4, "total_tokens": 9574336} {"current_steps": 45380, "total_steps": 181800, "loss": 0.0111, "lr": 4.666765545222954e-05, "epoch": 4.992299229922993, "percentage": 24.96, "elapsed_time": "1:46:43", "remaining_time": "5:20:49", "throughput": 1495.4, "total_tokens": 9575360} {"current_steps": 45385, "total_steps": 181800, "loss": 0.0068, "lr": 4.666645815314917e-05, "epoch": 4.992849284928493, "percentage": 24.96, "elapsed_time": "1:46:43", "remaining_time": "5:20:48", "throughput": 1495.4, "total_tokens": 9576416} {"current_steps": 45390, "total_steps": 181800, "loss": 0.0456, "lr": 4.666526065437945e-05, "epoch": 4.993399339933993, "percentage": 24.97, "elapsed_time": "1:46:44", "remaining_time": "5:20:47", "throughput": 1495.4, "total_tokens": 9577408} {"current_steps": 45395, "total_steps": 181800, "loss": 0.0704, "lr": 4.666406295593143e-05, "epoch": 4.993949394939494, "percentage": 24.97, "elapsed_time": "1:46:45", "remaining_time": "5:20:46", "throughput": 1495.39, "total_tokens": 9578432} {"current_steps": 45400, "total_steps": 181800, "loss": 0.0246, "lr": 4.6662865057816125e-05, "epoch": 4.994499449944994, "percentage": 24.97, "elapsed_time": "1:46:45", "remaining_time": "5:20:46", "throughput": 1495.4, "total_tokens": 9579520} {"current_steps": 45405, "total_steps": 181800, "loss": 0.1024, "lr": 4.666166696004459e-05, "epoch": 4.9950495049504955, "percentage": 24.98, "elapsed_time": "1:46:46", "remaining_time": "5:20:45", "throughput": 1495.4, "total_tokens": 9580576} {"current_steps": 45410, "total_steps": 181800, "loss": 0.0076, "lr": 4.666046866262787e-05, "epoch": 4.995599559955996, "percentage": 24.98, "elapsed_time": "1:46:47", "remaining_time": "5:20:44", "throughput": 1495.41, "total_tokens": 9581632} {"current_steps": 45415, "total_steps": 181800, "loss": 0.1061, "lr": 4.6659270165577e-05, "epoch": 4.996149614961496, "percentage": 24.98, "elapsed_time": "1:46:48", "remaining_time": "5:20:43", "throughput": 1495.41, "total_tokens": 9582688} {"current_steps": 45420, "total_steps": 181800, "loss": 0.0237, "lr": 4.665807146890303e-05, "epoch": 4.996699669966997, "percentage": 24.98, "elapsed_time": "1:46:48", "remaining_time": "5:20:43", "throughput": 1495.42, "total_tokens": 9583744} {"current_steps": 45425, "total_steps": 181800, "loss": 0.0986, "lr": 4.665687257261701e-05, "epoch": 4.997249724972497, "percentage": 24.99, "elapsed_time": "1:46:49", "remaining_time": "5:20:42", "throughput": 1495.42, "total_tokens": 9584800} {"current_steps": 45430, "total_steps": 181800, "loss": 0.0991, "lr": 4.665567347672998e-05, "epoch": 4.997799779977997, "percentage": 24.99, "elapsed_time": "1:46:50", "remaining_time": "5:20:41", "throughput": 1495.44, "total_tokens": 9585920} {"current_steps": 45435, "total_steps": 181800, "loss": 0.0536, "lr": 4.6654474181253e-05, "epoch": 4.9983498349834985, "percentage": 24.99, "elapsed_time": "1:46:50", "remaining_time": "5:20:40", "throughput": 1495.45, "total_tokens": 9587008} {"current_steps": 45440, "total_steps": 181800, "loss": 0.1271, "lr": 4.665327468619713e-05, "epoch": 4.998899889988999, "percentage": 24.99, "elapsed_time": "1:46:51", "remaining_time": "5:20:40", "throughput": 1495.43, "total_tokens": 9587968} {"current_steps": 45445, "total_steps": 181800, "loss": 0.0884, "lr": 4.6652074991573416e-05, "epoch": 4.9994499449945, "percentage": 25.0, "elapsed_time": "1:46:52", "remaining_time": "5:20:39", "throughput": 1495.44, "total_tokens": 9589056} {"current_steps": 45450, "total_steps": 181800, "loss": 0.0141, "lr": 4.665087509739291e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "1:46:52", "remaining_time": "5:20:38", "throughput": 1495.43, "total_tokens": 9590080} {"current_steps": 45450, "total_steps": 181800, "eval_loss": 0.0657351166009903, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "1:47:29", "remaining_time": "5:22:29", "throughput": 1486.85, "total_tokens": 9590080} {"current_steps": 45455, "total_steps": 181800, "loss": 0.0572, "lr": 4.6649675003666684e-05, "epoch": 5.0005500550055, "percentage": 25.0, "elapsed_time": "1:47:31", "remaining_time": "5:22:32", "throughput": 1486.59, "total_tokens": 9591168} {"current_steps": 45460, "total_steps": 181800, "loss": 0.0582, "lr": 4.664847471040579e-05, "epoch": 5.001100110011001, "percentage": 25.01, "elapsed_time": "1:47:32", "remaining_time": "5:22:31", "throughput": 1486.58, "total_tokens": 9592192} {"current_steps": 45465, "total_steps": 181800, "loss": 0.091, "lr": 4.664727421762129e-05, "epoch": 5.0016501650165015, "percentage": 25.01, "elapsed_time": "1:47:33", "remaining_time": "5:22:31", "throughput": 1486.59, "total_tokens": 9593248} {"current_steps": 45470, "total_steps": 181800, "loss": 0.0206, "lr": 4.664607352532425e-05, "epoch": 5.002200220022003, "percentage": 25.01, "elapsed_time": "1:47:33", "remaining_time": "5:22:30", "throughput": 1486.59, "total_tokens": 9594304} {"current_steps": 45475, "total_steps": 181800, "loss": 0.0122, "lr": 4.6644872633525745e-05, "epoch": 5.002750275027503, "percentage": 25.01, "elapsed_time": "1:47:34", "remaining_time": "5:22:29", "throughput": 1486.59, "total_tokens": 9595328} {"current_steps": 45480, "total_steps": 181800, "loss": 0.0649, "lr": 4.6643671542236824e-05, "epoch": 5.003300330033003, "percentage": 25.02, "elapsed_time": "1:47:35", "remaining_time": "5:22:28", "throughput": 1486.58, "total_tokens": 9596320} {"current_steps": 45485, "total_steps": 181800, "loss": 0.0424, "lr": 4.6642470251468575e-05, "epoch": 5.003850385038504, "percentage": 25.02, "elapsed_time": "1:47:35", "remaining_time": "5:22:28", "throughput": 1486.59, "total_tokens": 9597408} {"current_steps": 45490, "total_steps": 181800, "loss": 0.0779, "lr": 4.664126876123206e-05, "epoch": 5.004400440044004, "percentage": 25.02, "elapsed_time": "1:47:36", "remaining_time": "5:22:27", "throughput": 1486.58, "total_tokens": 9598464} {"current_steps": 45495, "total_steps": 181800, "loss": 0.0628, "lr": 4.664006707153836e-05, "epoch": 5.0049504950495045, "percentage": 25.02, "elapsed_time": "1:47:37", "remaining_time": "5:22:27", "throughput": 1486.56, "total_tokens": 9599520} {"current_steps": 45500, "total_steps": 181800, "loss": 0.0742, "lr": 4.663886518239855e-05, "epoch": 5.005500550055006, "percentage": 25.03, "elapsed_time": "1:47:38", "remaining_time": "5:22:26", "throughput": 1486.56, "total_tokens": 9600576} {"current_steps": 45505, "total_steps": 181800, "loss": 0.09, "lr": 4.663766309382369e-05, "epoch": 5.006050605060506, "percentage": 25.03, "elapsed_time": "1:47:38", "remaining_time": "5:22:25", "throughput": 1486.57, "total_tokens": 9601664} {"current_steps": 45510, "total_steps": 181800, "loss": 0.0149, "lr": 4.663646080582488e-05, "epoch": 5.006600660066007, "percentage": 25.03, "elapsed_time": "1:47:39", "remaining_time": "5:22:24", "throughput": 1486.58, "total_tokens": 9602784} {"current_steps": 45515, "total_steps": 181800, "loss": 0.0523, "lr": 4.6635258318413186e-05, "epoch": 5.007150715071507, "percentage": 25.04, "elapsed_time": "1:47:40", "remaining_time": "5:22:24", "throughput": 1486.58, "total_tokens": 9603808} {"current_steps": 45520, "total_steps": 181800, "loss": 0.0427, "lr": 4.663405563159971e-05, "epoch": 5.007700770077007, "percentage": 25.04, "elapsed_time": "1:47:41", "remaining_time": "5:22:23", "throughput": 1486.58, "total_tokens": 9604864} {"current_steps": 45525, "total_steps": 181800, "loss": 0.125, "lr": 4.663285274539552e-05, "epoch": 5.008250825082508, "percentage": 25.04, "elapsed_time": "1:47:41", "remaining_time": "5:22:22", "throughput": 1486.59, "total_tokens": 9605984} {"current_steps": 45530, "total_steps": 181800, "loss": 0.0395, "lr": 4.66316496598117e-05, "epoch": 5.008800880088009, "percentage": 25.04, "elapsed_time": "1:47:42", "remaining_time": "5:22:21", "throughput": 1486.6, "total_tokens": 9607072} {"current_steps": 45535, "total_steps": 181800, "loss": 0.0713, "lr": 4.663044637485935e-05, "epoch": 5.00935093509351, "percentage": 25.05, "elapsed_time": "1:47:43", "remaining_time": "5:22:21", "throughput": 1486.6, "total_tokens": 9608096} {"current_steps": 45540, "total_steps": 181800, "loss": 0.1859, "lr": 4.662924289054955e-05, "epoch": 5.00990099009901, "percentage": 25.05, "elapsed_time": "1:47:43", "remaining_time": "5:22:20", "throughput": 1486.62, "total_tokens": 9609216} {"current_steps": 45545, "total_steps": 181800, "loss": 0.0389, "lr": 4.66280392068934e-05, "epoch": 5.01045104510451, "percentage": 25.05, "elapsed_time": "1:47:44", "remaining_time": "5:22:19", "throughput": 1486.62, "total_tokens": 9610272} {"current_steps": 45550, "total_steps": 181800, "loss": 0.0492, "lr": 4.6626835323902e-05, "epoch": 5.011001100110011, "percentage": 25.06, "elapsed_time": "1:47:45", "remaining_time": "5:22:18", "throughput": 1486.62, "total_tokens": 9611328} {"current_steps": 45555, "total_steps": 181800, "loss": 0.0394, "lr": 4.662563124158642e-05, "epoch": 5.011551155115511, "percentage": 25.06, "elapsed_time": "1:47:45", "remaining_time": "5:22:18", "throughput": 1486.63, "total_tokens": 9612384} {"current_steps": 45560, "total_steps": 181800, "loss": 0.0283, "lr": 4.6624426959957785e-05, "epoch": 5.0121012101210125, "percentage": 25.06, "elapsed_time": "1:47:46", "remaining_time": "5:22:17", "throughput": 1486.64, "total_tokens": 9613504} {"current_steps": 45565, "total_steps": 181800, "loss": 0.0949, "lr": 4.6623222479027176e-05, "epoch": 5.012651265126513, "percentage": 25.06, "elapsed_time": "1:47:47", "remaining_time": "5:22:16", "throughput": 1486.64, "total_tokens": 9614560} {"current_steps": 45570, "total_steps": 181800, "loss": 0.0472, "lr": 4.6622017798805705e-05, "epoch": 5.013201320132013, "percentage": 25.07, "elapsed_time": "1:47:47", "remaining_time": "5:22:15", "throughput": 1486.66, "total_tokens": 9615680} {"current_steps": 45575, "total_steps": 181800, "loss": 0.0262, "lr": 4.6620812919304474e-05, "epoch": 5.013751375137514, "percentage": 25.07, "elapsed_time": "1:47:48", "remaining_time": "5:22:15", "throughput": 1486.66, "total_tokens": 9616704} {"current_steps": 45580, "total_steps": 181800, "loss": 0.0297, "lr": 4.661960784053459e-05, "epoch": 5.014301430143014, "percentage": 25.07, "elapsed_time": "1:47:49", "remaining_time": "5:22:14", "throughput": 1486.66, "total_tokens": 9617760} {"current_steps": 45585, "total_steps": 181800, "loss": 0.0449, "lr": 4.661840256250714e-05, "epoch": 5.014851485148514, "percentage": 25.07, "elapsed_time": "1:47:50", "remaining_time": "5:22:13", "throughput": 1486.66, "total_tokens": 9618784} {"current_steps": 45590, "total_steps": 181800, "loss": 0.0943, "lr": 4.6617197085233256e-05, "epoch": 5.0154015401540155, "percentage": 25.08, "elapsed_time": "1:47:50", "remaining_time": "5:22:12", "throughput": 1486.67, "total_tokens": 9619872} {"current_steps": 45595, "total_steps": 181800, "loss": 0.0847, "lr": 4.661599140872404e-05, "epoch": 5.015951595159516, "percentage": 25.08, "elapsed_time": "1:47:51", "remaining_time": "5:22:12", "throughput": 1486.67, "total_tokens": 9620896} {"current_steps": 45600, "total_steps": 181800, "loss": 0.0109, "lr": 4.6614785532990595e-05, "epoch": 5.016501650165017, "percentage": 25.08, "elapsed_time": "1:47:52", "remaining_time": "5:22:11", "throughput": 1486.67, "total_tokens": 9621920} {"current_steps": 45605, "total_steps": 181800, "loss": 0.0164, "lr": 4.661357945804405e-05, "epoch": 5.017051705170517, "percentage": 25.09, "elapsed_time": "1:47:52", "remaining_time": "5:22:10", "throughput": 1486.67, "total_tokens": 9622976} {"current_steps": 45610, "total_steps": 181800, "loss": 0.0166, "lr": 4.6612373183895516e-05, "epoch": 5.017601760176017, "percentage": 25.09, "elapsed_time": "1:47:53", "remaining_time": "5:22:09", "throughput": 1486.67, "total_tokens": 9623968} {"current_steps": 45615, "total_steps": 181800, "loss": 0.0292, "lr": 4.6611166710556104e-05, "epoch": 5.018151815181518, "percentage": 25.09, "elapsed_time": "1:47:54", "remaining_time": "5:22:08", "throughput": 1486.68, "total_tokens": 9625056} {"current_steps": 45620, "total_steps": 181800, "loss": 0.0693, "lr": 4.660996003803694e-05, "epoch": 5.0187018701870185, "percentage": 25.09, "elapsed_time": "1:47:54", "remaining_time": "5:22:08", "throughput": 1486.68, "total_tokens": 9626112} {"current_steps": 45625, "total_steps": 181800, "loss": 0.0494, "lr": 4.660875316634915e-05, "epoch": 5.01925192519252, "percentage": 25.1, "elapsed_time": "1:47:55", "remaining_time": "5:22:07", "throughput": 1486.69, "total_tokens": 9627168} {"current_steps": 45630, "total_steps": 181800, "loss": 0.0168, "lr": 4.660754609550384e-05, "epoch": 5.01980198019802, "percentage": 25.1, "elapsed_time": "1:47:56", "remaining_time": "5:22:06", "throughput": 1486.7, "total_tokens": 9628256} {"current_steps": 45635, "total_steps": 181800, "loss": 0.0399, "lr": 4.660633882551215e-05, "epoch": 5.02035203520352, "percentage": 25.1, "elapsed_time": "1:47:56", "remaining_time": "5:22:05", "throughput": 1486.7, "total_tokens": 9629280} {"current_steps": 45640, "total_steps": 181800, "loss": 0.0427, "lr": 4.660513135638521e-05, "epoch": 5.020902090209021, "percentage": 25.1, "elapsed_time": "1:47:57", "remaining_time": "5:22:05", "throughput": 1486.7, "total_tokens": 9630304} {"current_steps": 45645, "total_steps": 181800, "loss": 0.0276, "lr": 4.660392368813414e-05, "epoch": 5.021452145214521, "percentage": 25.11, "elapsed_time": "1:47:58", "remaining_time": "5:22:04", "throughput": 1486.7, "total_tokens": 9631328} {"current_steps": 45650, "total_steps": 181800, "loss": 0.0914, "lr": 4.660271582077007e-05, "epoch": 5.022002200220022, "percentage": 25.11, "elapsed_time": "1:47:59", "remaining_time": "5:22:03", "throughput": 1486.7, "total_tokens": 9632352} {"current_steps": 45655, "total_steps": 181800, "loss": 0.0221, "lr": 4.660150775430413e-05, "epoch": 5.022552255225523, "percentage": 25.11, "elapsed_time": "1:47:59", "remaining_time": "5:22:02", "throughput": 1486.7, "total_tokens": 9633408} {"current_steps": 45660, "total_steps": 181800, "loss": 0.0266, "lr": 4.6600299488747456e-05, "epoch": 5.023102310231023, "percentage": 25.12, "elapsed_time": "1:48:00", "remaining_time": "5:22:01", "throughput": 1486.72, "total_tokens": 9634528} {"current_steps": 45665, "total_steps": 181800, "loss": 0.0549, "lr": 4.6599091024111194e-05, "epoch": 5.023652365236524, "percentage": 25.12, "elapsed_time": "1:48:01", "remaining_time": "5:22:01", "throughput": 1486.73, "total_tokens": 9635616} {"current_steps": 45670, "total_steps": 181800, "loss": 0.0138, "lr": 4.6597882360406475e-05, "epoch": 5.024202420242024, "percentage": 25.12, "elapsed_time": "1:48:01", "remaining_time": "5:22:00", "throughput": 1486.73, "total_tokens": 9636672} {"current_steps": 45675, "total_steps": 181800, "loss": 0.0067, "lr": 4.6596673497644427e-05, "epoch": 5.024752475247524, "percentage": 25.12, "elapsed_time": "1:48:02", "remaining_time": "5:21:59", "throughput": 1486.73, "total_tokens": 9637664} {"current_steps": 45680, "total_steps": 181800, "loss": 0.0539, "lr": 4.659546443583621e-05, "epoch": 5.025302530253025, "percentage": 25.13, "elapsed_time": "1:48:03", "remaining_time": "5:21:58", "throughput": 1486.74, "total_tokens": 9638752} {"current_steps": 45685, "total_steps": 181800, "loss": 0.0348, "lr": 4.659425517499296e-05, "epoch": 5.025852585258526, "percentage": 25.13, "elapsed_time": "1:48:03", "remaining_time": "5:21:58", "throughput": 1486.75, "total_tokens": 9639872} {"current_steps": 45690, "total_steps": 181800, "loss": 0.1143, "lr": 4.659304571512583e-05, "epoch": 5.026402640264027, "percentage": 25.13, "elapsed_time": "1:48:04", "remaining_time": "5:21:57", "throughput": 1486.76, "total_tokens": 9640960} {"current_steps": 45695, "total_steps": 181800, "loss": 0.0976, "lr": 4.6591836056245944e-05, "epoch": 5.026952695269527, "percentage": 25.13, "elapsed_time": "1:48:05", "remaining_time": "5:21:56", "throughput": 1486.77, "total_tokens": 9642016} {"current_steps": 45700, "total_steps": 181800, "loss": 0.0197, "lr": 4.6590626198364476e-05, "epoch": 5.027502750275027, "percentage": 25.14, "elapsed_time": "1:48:05", "remaining_time": "5:21:55", "throughput": 1486.77, "total_tokens": 9643072} {"current_steps": 45705, "total_steps": 181800, "loss": 0.0635, "lr": 4.658941614149256e-05, "epoch": 5.028052805280528, "percentage": 25.14, "elapsed_time": "1:48:06", "remaining_time": "5:21:55", "throughput": 1486.77, "total_tokens": 9644096} {"current_steps": 45710, "total_steps": 181800, "loss": 0.0551, "lr": 4.6588205885641355e-05, "epoch": 5.028602860286028, "percentage": 25.14, "elapsed_time": "1:48:07", "remaining_time": "5:21:54", "throughput": 1486.78, "total_tokens": 9645184} {"current_steps": 45715, "total_steps": 181800, "loss": 0.0558, "lr": 4.6586995430822024e-05, "epoch": 5.0291529152915295, "percentage": 25.15, "elapsed_time": "1:48:07", "remaining_time": "5:21:53", "throughput": 1486.78, "total_tokens": 9646208} {"current_steps": 45720, "total_steps": 181800, "loss": 0.0079, "lr": 4.658578477704571e-05, "epoch": 5.02970297029703, "percentage": 25.15, "elapsed_time": "1:48:08", "remaining_time": "5:21:52", "throughput": 1486.79, "total_tokens": 9647296} {"current_steps": 45725, "total_steps": 181800, "loss": 0.1027, "lr": 4.658457392432357e-05, "epoch": 5.03025302530253, "percentage": 25.15, "elapsed_time": "1:48:09", "remaining_time": "5:21:51", "throughput": 1486.81, "total_tokens": 9648480} {"current_steps": 45730, "total_steps": 181800, "loss": 0.063, "lr": 4.658336287266678e-05, "epoch": 5.030803080308031, "percentage": 25.15, "elapsed_time": "1:48:10", "remaining_time": "5:21:51", "throughput": 1486.82, "total_tokens": 9649568} {"current_steps": 45735, "total_steps": 181800, "loss": 0.0781, "lr": 4.6582151622086484e-05, "epoch": 5.031353135313531, "percentage": 25.16, "elapsed_time": "1:48:10", "remaining_time": "5:21:50", "throughput": 1486.83, "total_tokens": 9650656} {"current_steps": 45740, "total_steps": 181800, "loss": 0.1097, "lr": 4.6580940172593855e-05, "epoch": 5.031903190319032, "percentage": 25.16, "elapsed_time": "1:48:11", "remaining_time": "5:21:49", "throughput": 1486.84, "total_tokens": 9651712} {"current_steps": 45745, "total_steps": 181800, "loss": 0.0628, "lr": 4.657972852420005e-05, "epoch": 5.0324532453245325, "percentage": 25.16, "elapsed_time": "1:48:12", "remaining_time": "5:21:48", "throughput": 1486.84, "total_tokens": 9652768} {"current_steps": 45750, "total_steps": 181800, "loss": 0.0571, "lr": 4.657851667691625e-05, "epoch": 5.033003300330033, "percentage": 25.17, "elapsed_time": "1:48:12", "remaining_time": "5:21:48", "throughput": 1486.85, "total_tokens": 9653824} {"current_steps": 45755, "total_steps": 181800, "loss": 0.0544, "lr": 4.657730463075362e-05, "epoch": 5.033553355335534, "percentage": 25.17, "elapsed_time": "1:48:13", "remaining_time": "5:21:47", "throughput": 1486.85, "total_tokens": 9654880} {"current_steps": 45760, "total_steps": 181800, "loss": 0.0215, "lr": 4.6576092385723315e-05, "epoch": 5.034103410341034, "percentage": 25.17, "elapsed_time": "1:48:14", "remaining_time": "5:21:46", "throughput": 1486.86, "total_tokens": 9656000} {"current_steps": 45765, "total_steps": 181800, "loss": 0.0742, "lr": 4.657487994183652e-05, "epoch": 5.034653465346534, "percentage": 25.17, "elapsed_time": "1:48:14", "remaining_time": "5:21:45", "throughput": 1486.86, "total_tokens": 9657024} {"current_steps": 45770, "total_steps": 181800, "loss": 0.0467, "lr": 4.657366729910442e-05, "epoch": 5.035203520352035, "percentage": 25.18, "elapsed_time": "1:48:15", "remaining_time": "5:21:45", "throughput": 1486.88, "total_tokens": 9658176} {"current_steps": 45775, "total_steps": 181800, "loss": 0.0258, "lr": 4.657245445753817e-05, "epoch": 5.0357535753575355, "percentage": 25.18, "elapsed_time": "1:48:16", "remaining_time": "5:21:44", "throughput": 1486.88, "total_tokens": 9659168} {"current_steps": 45780, "total_steps": 181800, "loss": 0.135, "lr": 4.6571241417148966e-05, "epoch": 5.036303630363037, "percentage": 25.18, "elapsed_time": "1:48:16", "remaining_time": "5:21:43", "throughput": 1486.89, "total_tokens": 9660288} {"current_steps": 45785, "total_steps": 181800, "loss": 0.0187, "lr": 4.6570028177947974e-05, "epoch": 5.036853685368537, "percentage": 25.18, "elapsed_time": "1:48:17", "remaining_time": "5:21:42", "throughput": 1486.9, "total_tokens": 9661344} {"current_steps": 45790, "total_steps": 181800, "loss": 0.0062, "lr": 4.6568814739946385e-05, "epoch": 5.037403740374037, "percentage": 25.19, "elapsed_time": "1:48:18", "remaining_time": "5:21:42", "throughput": 1486.9, "total_tokens": 9662400} {"current_steps": 45795, "total_steps": 181800, "loss": 0.0245, "lr": 4.6567601103155386e-05, "epoch": 5.037953795379538, "percentage": 25.19, "elapsed_time": "1:48:19", "remaining_time": "5:21:41", "throughput": 1486.91, "total_tokens": 9663488} {"current_steps": 45800, "total_steps": 181800, "loss": 0.0492, "lr": 4.656638726758615e-05, "epoch": 5.038503850385038, "percentage": 25.19, "elapsed_time": "1:48:19", "remaining_time": "5:21:40", "throughput": 1486.92, "total_tokens": 9664576} {"current_steps": 45805, "total_steps": 181800, "loss": 0.0612, "lr": 4.6565173233249874e-05, "epoch": 5.039053905390539, "percentage": 25.2, "elapsed_time": "1:48:20", "remaining_time": "5:21:39", "throughput": 1486.93, "total_tokens": 9665632} {"current_steps": 45810, "total_steps": 181800, "loss": 0.0291, "lr": 4.6563959000157756e-05, "epoch": 5.03960396039604, "percentage": 25.2, "elapsed_time": "1:48:21", "remaining_time": "5:21:38", "throughput": 1486.93, "total_tokens": 9666656} {"current_steps": 45815, "total_steps": 181800, "loss": 0.0582, "lr": 4.656274456832096e-05, "epoch": 5.04015401540154, "percentage": 25.2, "elapsed_time": "1:48:21", "remaining_time": "5:21:38", "throughput": 1486.93, "total_tokens": 9667680} {"current_steps": 45820, "total_steps": 181800, "loss": 0.012, "lr": 4.6561529937750695e-05, "epoch": 5.040704070407041, "percentage": 25.2, "elapsed_time": "1:48:22", "remaining_time": "5:21:37", "throughput": 1486.92, "total_tokens": 9668672} {"current_steps": 45825, "total_steps": 181800, "loss": 0.0718, "lr": 4.6560315108458154e-05, "epoch": 5.041254125412541, "percentage": 25.21, "elapsed_time": "1:48:23", "remaining_time": "5:21:36", "throughput": 1486.92, "total_tokens": 9669728} {"current_steps": 45830, "total_steps": 181800, "loss": 0.1537, "lr": 4.6559100080454536e-05, "epoch": 5.041804180418042, "percentage": 25.21, "elapsed_time": "1:48:23", "remaining_time": "5:21:35", "throughput": 1486.93, "total_tokens": 9670816} {"current_steps": 45835, "total_steps": 181800, "loss": 0.0125, "lr": 4.655788485375104e-05, "epoch": 5.042354235423542, "percentage": 25.21, "elapsed_time": "1:48:24", "remaining_time": "5:21:35", "throughput": 1486.95, "total_tokens": 9671936} {"current_steps": 45840, "total_steps": 181800, "loss": 0.0456, "lr": 4.655666942835887e-05, "epoch": 5.042904290429043, "percentage": 25.21, "elapsed_time": "1:48:25", "remaining_time": "5:21:34", "throughput": 1486.95, "total_tokens": 9672960} {"current_steps": 45845, "total_steps": 181800, "loss": 0.0144, "lr": 4.6555453804289215e-05, "epoch": 5.043454345434544, "percentage": 25.22, "elapsed_time": "1:48:25", "remaining_time": "5:21:33", "throughput": 1486.95, "total_tokens": 9674016} {"current_steps": 45850, "total_steps": 181800, "loss": 0.0285, "lr": 4.655423798155328e-05, "epoch": 5.044004400440044, "percentage": 25.22, "elapsed_time": "1:48:26", "remaining_time": "5:21:32", "throughput": 1486.95, "total_tokens": 9675008} {"current_steps": 45855, "total_steps": 181800, "loss": 0.0281, "lr": 4.655302196016228e-05, "epoch": 5.044554455445544, "percentage": 25.22, "elapsed_time": "1:48:27", "remaining_time": "5:21:32", "throughput": 1486.95, "total_tokens": 9676032} {"current_steps": 45860, "total_steps": 181800, "loss": 0.0118, "lr": 4.6551805740127426e-05, "epoch": 5.045104510451045, "percentage": 25.23, "elapsed_time": "1:48:28", "remaining_time": "5:21:31", "throughput": 1486.96, "total_tokens": 9677120} {"current_steps": 45865, "total_steps": 181800, "loss": 0.01, "lr": 4.655058932145991e-05, "epoch": 5.0456545654565454, "percentage": 25.23, "elapsed_time": "1:48:28", "remaining_time": "5:21:30", "throughput": 1486.95, "total_tokens": 9678144} {"current_steps": 45870, "total_steps": 181800, "loss": 0.0801, "lr": 4.6549372704170956e-05, "epoch": 5.0462046204620465, "percentage": 25.23, "elapsed_time": "1:48:29", "remaining_time": "5:21:29", "throughput": 1486.96, "total_tokens": 9679232} {"current_steps": 45875, "total_steps": 181800, "loss": 0.0244, "lr": 4.654815588827178e-05, "epoch": 5.046754675467547, "percentage": 25.23, "elapsed_time": "1:48:30", "remaining_time": "5:21:29", "throughput": 1486.97, "total_tokens": 9680288} {"current_steps": 45880, "total_steps": 181800, "loss": 0.0195, "lr": 4.6546938873773585e-05, "epoch": 5.047304730473047, "percentage": 25.24, "elapsed_time": "1:48:30", "remaining_time": "5:21:28", "throughput": 1486.98, "total_tokens": 9681408} {"current_steps": 45885, "total_steps": 181800, "loss": 0.0426, "lr": 4.65457216606876e-05, "epoch": 5.047854785478548, "percentage": 25.24, "elapsed_time": "1:48:31", "remaining_time": "5:21:27", "throughput": 1487.0, "total_tokens": 9682528} {"current_steps": 45890, "total_steps": 181800, "loss": 0.0108, "lr": 4.654450424902503e-05, "epoch": 5.048404840484048, "percentage": 25.24, "elapsed_time": "1:48:32", "remaining_time": "5:21:26", "throughput": 1487.0, "total_tokens": 9683584} {"current_steps": 45895, "total_steps": 181800, "loss": 0.1378, "lr": 4.65432866387971e-05, "epoch": 5.048954895489549, "percentage": 25.24, "elapsed_time": "1:48:32", "remaining_time": "5:21:25", "throughput": 1487.0, "total_tokens": 9684608} {"current_steps": 45900, "total_steps": 181800, "loss": 0.0299, "lr": 4.654206883001504e-05, "epoch": 5.0495049504950495, "percentage": 25.25, "elapsed_time": "1:48:33", "remaining_time": "5:21:25", "throughput": 1487.01, "total_tokens": 9685696} {"current_steps": 45905, "total_steps": 181800, "loss": 0.0347, "lr": 4.654085082269007e-05, "epoch": 5.05005500550055, "percentage": 25.25, "elapsed_time": "1:48:34", "remaining_time": "5:21:24", "throughput": 1487.02, "total_tokens": 9686784} {"current_steps": 45910, "total_steps": 181800, "loss": 0.0295, "lr": 4.653963261683342e-05, "epoch": 5.050605060506051, "percentage": 25.25, "elapsed_time": "1:48:34", "remaining_time": "5:21:23", "throughput": 1487.02, "total_tokens": 9687840} {"current_steps": 45915, "total_steps": 181800, "loss": 0.0299, "lr": 4.65384142124563e-05, "epoch": 5.051155115511551, "percentage": 25.26, "elapsed_time": "1:48:35", "remaining_time": "5:21:22", "throughput": 1487.02, "total_tokens": 9688864} {"current_steps": 45920, "total_steps": 181800, "loss": 0.0423, "lr": 4.653719560956995e-05, "epoch": 5.051705170517051, "percentage": 25.26, "elapsed_time": "1:48:36", "remaining_time": "5:21:22", "throughput": 1487.03, "total_tokens": 9689920} {"current_steps": 45925, "total_steps": 181800, "loss": 0.1419, "lr": 4.653597680818561e-05, "epoch": 5.052255225522552, "percentage": 25.26, "elapsed_time": "1:48:36", "remaining_time": "5:21:21", "throughput": 1487.03, "total_tokens": 9690976} {"current_steps": 45930, "total_steps": 181800, "loss": 0.0453, "lr": 4.6534757808314505e-05, "epoch": 5.052805280528053, "percentage": 25.26, "elapsed_time": "1:48:37", "remaining_time": "5:21:20", "throughput": 1487.03, "total_tokens": 9691968} {"current_steps": 45935, "total_steps": 181800, "loss": 0.0139, "lr": 4.653353860996787e-05, "epoch": 5.053355335533554, "percentage": 25.27, "elapsed_time": "1:48:38", "remaining_time": "5:21:19", "throughput": 1487.03, "total_tokens": 9693024} {"current_steps": 45940, "total_steps": 181800, "loss": 0.0081, "lr": 4.653231921315694e-05, "epoch": 5.053905390539054, "percentage": 25.27, "elapsed_time": "1:48:39", "remaining_time": "5:21:19", "throughput": 1487.04, "total_tokens": 9694144} {"current_steps": 45945, "total_steps": 181800, "loss": 0.0394, "lr": 4.653109961789296e-05, "epoch": 5.054455445544554, "percentage": 25.27, "elapsed_time": "1:48:39", "remaining_time": "5:21:18", "throughput": 1487.05, "total_tokens": 9695232} {"current_steps": 45950, "total_steps": 181800, "loss": 0.1441, "lr": 4.652987982418716e-05, "epoch": 5.055005500550055, "percentage": 25.28, "elapsed_time": "1:48:40", "remaining_time": "5:21:17", "throughput": 1487.06, "total_tokens": 9696288} {"current_steps": 45955, "total_steps": 181800, "loss": 0.017, "lr": 4.65286598320508e-05, "epoch": 5.055555555555555, "percentage": 25.28, "elapsed_time": "1:48:41", "remaining_time": "5:21:16", "throughput": 1487.06, "total_tokens": 9697344} {"current_steps": 45960, "total_steps": 181800, "loss": 0.0328, "lr": 4.65274396414951e-05, "epoch": 5.0561056105610565, "percentage": 25.28, "elapsed_time": "1:48:41", "remaining_time": "5:21:16", "throughput": 1487.07, "total_tokens": 9698432} {"current_steps": 45965, "total_steps": 181800, "loss": 0.1218, "lr": 4.652621925253133e-05, "epoch": 5.056655665566557, "percentage": 25.28, "elapsed_time": "1:48:42", "remaining_time": "5:21:15", "throughput": 1487.08, "total_tokens": 9699488} {"current_steps": 45970, "total_steps": 181800, "loss": 0.0177, "lr": 4.652499866517072e-05, "epoch": 5.057205720572057, "percentage": 25.29, "elapsed_time": "1:48:43", "remaining_time": "5:21:14", "throughput": 1487.08, "total_tokens": 9700544} {"current_steps": 45975, "total_steps": 181800, "loss": 0.1368, "lr": 4.6523777879424524e-05, "epoch": 5.057755775577558, "percentage": 25.29, "elapsed_time": "1:48:43", "remaining_time": "5:21:13", "throughput": 1487.1, "total_tokens": 9701696} {"current_steps": 45980, "total_steps": 181800, "loss": 0.0348, "lr": 4.652255689530401e-05, "epoch": 5.058305830583058, "percentage": 25.29, "elapsed_time": "1:48:44", "remaining_time": "5:21:12", "throughput": 1487.1, "total_tokens": 9702720} {"current_steps": 45985, "total_steps": 181800, "loss": 0.0228, "lr": 4.6521335712820394e-05, "epoch": 5.058855885588559, "percentage": 25.29, "elapsed_time": "1:48:45", "remaining_time": "5:21:12", "throughput": 1487.09, "total_tokens": 9703680} {"current_steps": 45990, "total_steps": 181800, "loss": 0.0679, "lr": 4.652011433198496e-05, "epoch": 5.0594059405940595, "percentage": 25.3, "elapsed_time": "1:48:45", "remaining_time": "5:21:11", "throughput": 1487.1, "total_tokens": 9704768} {"current_steps": 45995, "total_steps": 181800, "loss": 0.1323, "lr": 4.6518892752808966e-05, "epoch": 5.05995599559956, "percentage": 25.3, "elapsed_time": "1:48:46", "remaining_time": "5:21:10", "throughput": 1487.1, "total_tokens": 9705792} {"current_steps": 46000, "total_steps": 181800, "loss": 0.0468, "lr": 4.651767097530366e-05, "epoch": 5.060506050605061, "percentage": 25.3, "elapsed_time": "1:48:47", "remaining_time": "5:21:09", "throughput": 1487.11, "total_tokens": 9706880} {"current_steps": 46005, "total_steps": 181800, "loss": 0.0518, "lr": 4.651644899948031e-05, "epoch": 5.061056105610561, "percentage": 25.31, "elapsed_time": "1:48:48", "remaining_time": "5:21:09", "throughput": 1487.13, "total_tokens": 9708000} {"current_steps": 46010, "total_steps": 181800, "loss": 0.0074, "lr": 4.6515226825350174e-05, "epoch": 5.061606160616061, "percentage": 25.31, "elapsed_time": "1:48:48", "remaining_time": "5:21:08", "throughput": 1487.13, "total_tokens": 9709024} {"current_steps": 46015, "total_steps": 181800, "loss": 0.036, "lr": 4.651400445292451e-05, "epoch": 5.062156215621562, "percentage": 25.31, "elapsed_time": "1:48:49", "remaining_time": "5:21:07", "throughput": 1487.12, "total_tokens": 9709984} {"current_steps": 46020, "total_steps": 181800, "loss": 0.062, "lr": 4.65127818822146e-05, "epoch": 5.0627062706270625, "percentage": 25.31, "elapsed_time": "1:48:50", "remaining_time": "5:21:06", "throughput": 1487.11, "total_tokens": 9710944} {"current_steps": 46025, "total_steps": 181800, "loss": 0.2284, "lr": 4.651155911323168e-05, "epoch": 5.063256325632564, "percentage": 25.32, "elapsed_time": "1:48:50", "remaining_time": "5:21:05", "throughput": 1487.11, "total_tokens": 9712000} {"current_steps": 46030, "total_steps": 181800, "loss": 0.038, "lr": 4.651033614598706e-05, "epoch": 5.063806380638064, "percentage": 25.32, "elapsed_time": "1:48:51", "remaining_time": "5:21:05", "throughput": 1487.11, "total_tokens": 9713024} {"current_steps": 46035, "total_steps": 181800, "loss": 0.0305, "lr": 4.6509112980492e-05, "epoch": 5.064356435643564, "percentage": 25.32, "elapsed_time": "1:48:52", "remaining_time": "5:21:04", "throughput": 1487.11, "total_tokens": 9714048} {"current_steps": 46040, "total_steps": 181800, "loss": 0.0435, "lr": 4.6507889616757756e-05, "epoch": 5.064906490649065, "percentage": 25.32, "elapsed_time": "1:48:52", "remaining_time": "5:21:03", "throughput": 1487.13, "total_tokens": 9715168} {"current_steps": 46045, "total_steps": 181800, "loss": 0.0903, "lr": 4.650666605479561e-05, "epoch": 5.065456545654565, "percentage": 25.33, "elapsed_time": "1:48:53", "remaining_time": "5:21:02", "throughput": 1487.14, "total_tokens": 9716256} {"current_steps": 46050, "total_steps": 181800, "loss": 0.087, "lr": 4.6505442294616855e-05, "epoch": 5.066006600660066, "percentage": 25.33, "elapsed_time": "1:48:54", "remaining_time": "5:21:02", "throughput": 1487.14, "total_tokens": 9717344} {"current_steps": 46055, "total_steps": 181800, "loss": 0.0105, "lr": 4.650421833623275e-05, "epoch": 5.066556655665567, "percentage": 25.33, "elapsed_time": "1:48:54", "remaining_time": "5:21:01", "throughput": 1487.15, "total_tokens": 9718432} {"current_steps": 46060, "total_steps": 181800, "loss": 0.0279, "lr": 4.650299417965458e-05, "epoch": 5.067106710671067, "percentage": 25.34, "elapsed_time": "1:48:55", "remaining_time": "5:21:00", "throughput": 1487.16, "total_tokens": 9719488} {"current_steps": 46065, "total_steps": 181800, "loss": 0.0786, "lr": 4.650176982489364e-05, "epoch": 5.067656765676568, "percentage": 25.34, "elapsed_time": "1:48:56", "remaining_time": "5:20:59", "throughput": 1487.16, "total_tokens": 9720512} {"current_steps": 46070, "total_steps": 181800, "loss": 0.0617, "lr": 4.65005452719612e-05, "epoch": 5.068206820682068, "percentage": 25.34, "elapsed_time": "1:48:56", "remaining_time": "5:20:59", "throughput": 1487.17, "total_tokens": 9721632} {"current_steps": 46075, "total_steps": 181800, "loss": 0.054, "lr": 4.649932052086855e-05, "epoch": 5.068756875687569, "percentage": 25.34, "elapsed_time": "1:48:57", "remaining_time": "5:20:58", "throughput": 1487.17, "total_tokens": 9722656} {"current_steps": 46080, "total_steps": 181800, "loss": 0.1035, "lr": 4.6498095571626975e-05, "epoch": 5.069306930693069, "percentage": 25.35, "elapsed_time": "1:48:58", "remaining_time": "5:20:57", "throughput": 1487.18, "total_tokens": 9723744} {"current_steps": 46085, "total_steps": 181800, "loss": 0.0267, "lr": 4.649687042424778e-05, "epoch": 5.06985698569857, "percentage": 25.35, "elapsed_time": "1:48:59", "remaining_time": "5:20:56", "throughput": 1487.19, "total_tokens": 9724832} {"current_steps": 46090, "total_steps": 181800, "loss": 0.0615, "lr": 4.6495645078742235e-05, "epoch": 5.070407040704071, "percentage": 25.35, "elapsed_time": "1:48:59", "remaining_time": "5:20:56", "throughput": 1487.21, "total_tokens": 9725984} {"current_steps": 46095, "total_steps": 181800, "loss": 0.0822, "lr": 4.6494419535121655e-05, "epoch": 5.070957095709571, "percentage": 25.35, "elapsed_time": "1:49:00", "remaining_time": "5:20:55", "throughput": 1487.22, "total_tokens": 9727104} {"current_steps": 46100, "total_steps": 181800, "loss": 0.0287, "lr": 4.6493193793397315e-05, "epoch": 5.071507150715071, "percentage": 25.36, "elapsed_time": "1:49:01", "remaining_time": "5:20:54", "throughput": 1487.22, "total_tokens": 9728096} {"current_steps": 46105, "total_steps": 181800, "loss": 0.059, "lr": 4.649196785358052e-05, "epoch": 5.072057205720572, "percentage": 25.36, "elapsed_time": "1:49:01", "remaining_time": "5:20:53", "throughput": 1487.23, "total_tokens": 9729216} {"current_steps": 46110, "total_steps": 181800, "loss": 0.0785, "lr": 4.6490741715682576e-05, "epoch": 5.072607260726072, "percentage": 25.36, "elapsed_time": "1:49:02", "remaining_time": "5:20:52", "throughput": 1487.24, "total_tokens": 9730304} {"current_steps": 46115, "total_steps": 181800, "loss": 0.0836, "lr": 4.648951537971478e-05, "epoch": 5.0731573157315735, "percentage": 25.37, "elapsed_time": "1:49:03", "remaining_time": "5:20:52", "throughput": 1487.24, "total_tokens": 9731328} {"current_steps": 46120, "total_steps": 181800, "loss": 0.1005, "lr": 4.648828884568843e-05, "epoch": 5.073707370737074, "percentage": 25.37, "elapsed_time": "1:49:03", "remaining_time": "5:20:51", "throughput": 1487.24, "total_tokens": 9732320} {"current_steps": 46125, "total_steps": 181800, "loss": 0.0636, "lr": 4.6487062113614827e-05, "epoch": 5.074257425742574, "percentage": 25.37, "elapsed_time": "1:49:04", "remaining_time": "5:20:50", "throughput": 1487.24, "total_tokens": 9733312} {"current_steps": 46130, "total_steps": 181800, "loss": 0.0076, "lr": 4.648583518350529e-05, "epoch": 5.074807480748075, "percentage": 25.37, "elapsed_time": "1:49:05", "remaining_time": "5:20:49", "throughput": 1487.24, "total_tokens": 9734368} {"current_steps": 46135, "total_steps": 181800, "loss": 0.0182, "lr": 4.6484608055371114e-05, "epoch": 5.075357535753575, "percentage": 25.38, "elapsed_time": "1:49:05", "remaining_time": "5:20:49", "throughput": 1487.25, "total_tokens": 9735456} {"current_steps": 46140, "total_steps": 181800, "loss": 0.0508, "lr": 4.648338072922362e-05, "epoch": 5.075907590759076, "percentage": 25.38, "elapsed_time": "1:49:06", "remaining_time": "5:20:48", "throughput": 1487.27, "total_tokens": 9736576} {"current_steps": 46145, "total_steps": 181800, "loss": 0.0249, "lr": 4.6482153205074115e-05, "epoch": 5.0764576457645765, "percentage": 25.38, "elapsed_time": "1:49:07", "remaining_time": "5:20:47", "throughput": 1487.27, "total_tokens": 9737632} {"current_steps": 46150, "total_steps": 181800, "loss": 0.1353, "lr": 4.648092548293391e-05, "epoch": 5.077007700770077, "percentage": 25.39, "elapsed_time": "1:49:08", "remaining_time": "5:20:46", "throughput": 1487.28, "total_tokens": 9738720} {"current_steps": 46155, "total_steps": 181800, "loss": 0.0139, "lr": 4.6479697562814315e-05, "epoch": 5.077557755775578, "percentage": 25.39, "elapsed_time": "1:49:08", "remaining_time": "5:20:45", "throughput": 1487.28, "total_tokens": 9739744} {"current_steps": 46160, "total_steps": 181800, "loss": 0.0235, "lr": 4.647846944472667e-05, "epoch": 5.078107810781078, "percentage": 25.39, "elapsed_time": "1:49:09", "remaining_time": "5:20:45", "throughput": 1487.29, "total_tokens": 9740832} {"current_steps": 46165, "total_steps": 181800, "loss": 0.0071, "lr": 4.647724112868227e-05, "epoch": 5.078657865786579, "percentage": 25.39, "elapsed_time": "1:49:10", "remaining_time": "5:20:44", "throughput": 1487.3, "total_tokens": 9741888} {"current_steps": 46170, "total_steps": 181800, "loss": 0.0217, "lr": 4.6476012614692446e-05, "epoch": 5.079207920792079, "percentage": 25.4, "elapsed_time": "1:49:10", "remaining_time": "5:20:43", "throughput": 1487.3, "total_tokens": 9742976} {"current_steps": 46175, "total_steps": 181800, "loss": 0.0209, "lr": 4.647478390276851e-05, "epoch": 5.0797579757975795, "percentage": 25.4, "elapsed_time": "1:49:11", "remaining_time": "5:20:42", "throughput": 1487.31, "total_tokens": 9744032} {"current_steps": 46180, "total_steps": 181800, "loss": 0.0753, "lr": 4.6473554992921805e-05, "epoch": 5.080308030803081, "percentage": 25.4, "elapsed_time": "1:49:12", "remaining_time": "5:20:42", "throughput": 1487.31, "total_tokens": 9745056} {"current_steps": 46185, "total_steps": 181800, "loss": 0.1226, "lr": 4.647232588516365e-05, "epoch": 5.080858085808581, "percentage": 25.4, "elapsed_time": "1:49:12", "remaining_time": "5:20:41", "throughput": 1487.33, "total_tokens": 9746208} {"current_steps": 46190, "total_steps": 181800, "loss": 0.074, "lr": 4.647109657950536e-05, "epoch": 5.081408140814081, "percentage": 25.41, "elapsed_time": "1:49:13", "remaining_time": "5:20:40", "throughput": 1487.32, "total_tokens": 9747200} {"current_steps": 46195, "total_steps": 181800, "loss": 0.0238, "lr": 4.6469867075958286e-05, "epoch": 5.081958195819582, "percentage": 25.41, "elapsed_time": "1:49:14", "remaining_time": "5:20:39", "throughput": 1487.32, "total_tokens": 9748192} {"current_steps": 46200, "total_steps": 181800, "loss": 0.036, "lr": 4.646863737453374e-05, "epoch": 5.082508250825082, "percentage": 25.41, "elapsed_time": "1:49:14", "remaining_time": "5:20:39", "throughput": 1487.32, "total_tokens": 9749248} {"current_steps": 46205, "total_steps": 181800, "loss": 0.0139, "lr": 4.6467407475243076e-05, "epoch": 5.083058305830583, "percentage": 25.42, "elapsed_time": "1:49:15", "remaining_time": "5:20:38", "throughput": 1487.33, "total_tokens": 9750304} {"current_steps": 46210, "total_steps": 181800, "loss": 0.0218, "lr": 4.646617737809761e-05, "epoch": 5.083608360836084, "percentage": 25.42, "elapsed_time": "1:49:16", "remaining_time": "5:20:37", "throughput": 1487.33, "total_tokens": 9751360} {"current_steps": 46215, "total_steps": 181800, "loss": 0.0469, "lr": 4.646494708310869e-05, "epoch": 5.084158415841584, "percentage": 25.42, "elapsed_time": "1:49:16", "remaining_time": "5:20:36", "throughput": 1487.33, "total_tokens": 9752384} {"current_steps": 46220, "total_steps": 181800, "loss": 0.0922, "lr": 4.6463716590287656e-05, "epoch": 5.084708470847085, "percentage": 25.42, "elapsed_time": "1:49:17", "remaining_time": "5:20:35", "throughput": 1487.34, "total_tokens": 9753472} {"current_steps": 46225, "total_steps": 181800, "loss": 0.0394, "lr": 4.646248589964584e-05, "epoch": 5.085258525852585, "percentage": 25.43, "elapsed_time": "1:49:18", "remaining_time": "5:20:35", "throughput": 1487.34, "total_tokens": 9754464} {"current_steps": 46230, "total_steps": 181800, "loss": 0.0413, "lr": 4.6461255011194596e-05, "epoch": 5.085808580858086, "percentage": 25.43, "elapsed_time": "1:49:19", "remaining_time": "5:20:34", "throughput": 1487.35, "total_tokens": 9755520} {"current_steps": 46235, "total_steps": 181800, "loss": 0.0294, "lr": 4.6460023924945256e-05, "epoch": 5.086358635863586, "percentage": 25.43, "elapsed_time": "1:49:19", "remaining_time": "5:20:33", "throughput": 1487.36, "total_tokens": 9756640} {"current_steps": 46240, "total_steps": 181800, "loss": 0.0526, "lr": 4.6458792640909175e-05, "epoch": 5.086908690869087, "percentage": 25.43, "elapsed_time": "1:49:20", "remaining_time": "5:20:32", "throughput": 1487.36, "total_tokens": 9757664} {"current_steps": 46245, "total_steps": 181800, "loss": 0.1255, "lr": 4.6457561159097704e-05, "epoch": 5.087458745874588, "percentage": 25.44, "elapsed_time": "1:49:21", "remaining_time": "5:20:32", "throughput": 1487.36, "total_tokens": 9758656} {"current_steps": 46250, "total_steps": 181800, "loss": 0.0876, "lr": 4.645632947952219e-05, "epoch": 5.088008800880088, "percentage": 25.44, "elapsed_time": "1:49:21", "remaining_time": "5:20:31", "throughput": 1487.36, "total_tokens": 9759680} {"current_steps": 46255, "total_steps": 181800, "loss": 0.0348, "lr": 4.645509760219397e-05, "epoch": 5.088558855885589, "percentage": 25.44, "elapsed_time": "1:49:22", "remaining_time": "5:20:30", "throughput": 1487.36, "total_tokens": 9760736} {"current_steps": 46260, "total_steps": 181800, "loss": 0.0962, "lr": 4.6453865527124416e-05, "epoch": 5.089108910891089, "percentage": 25.45, "elapsed_time": "1:49:23", "remaining_time": "5:20:29", "throughput": 1487.37, "total_tokens": 9761792} {"current_steps": 46265, "total_steps": 181800, "loss": 0.0471, "lr": 4.645263325432488e-05, "epoch": 5.089658965896589, "percentage": 25.45, "elapsed_time": "1:49:23", "remaining_time": "5:20:28", "throughput": 1487.37, "total_tokens": 9762848} {"current_steps": 46270, "total_steps": 181800, "loss": 0.0286, "lr": 4.645140078380672e-05, "epoch": 5.0902090209020905, "percentage": 25.45, "elapsed_time": "1:49:24", "remaining_time": "5:20:28", "throughput": 1487.38, "total_tokens": 9763904} {"current_steps": 46275, "total_steps": 181800, "loss": 0.0191, "lr": 4.6450168115581295e-05, "epoch": 5.090759075907591, "percentage": 25.45, "elapsed_time": "1:49:25", "remaining_time": "5:20:27", "throughput": 1487.37, "total_tokens": 9764896} {"current_steps": 46280, "total_steps": 181800, "loss": 0.0244, "lr": 4.644893524965995e-05, "epoch": 5.091309130913091, "percentage": 25.46, "elapsed_time": "1:49:25", "remaining_time": "5:20:26", "throughput": 1487.38, "total_tokens": 9765952} {"current_steps": 46285, "total_steps": 181800, "loss": 0.0115, "lr": 4.644770218605408e-05, "epoch": 5.091859185918592, "percentage": 25.46, "elapsed_time": "1:49:26", "remaining_time": "5:20:25", "throughput": 1487.38, "total_tokens": 9766976} {"current_steps": 46290, "total_steps": 181800, "loss": 0.0084, "lr": 4.644646892477501e-05, "epoch": 5.092409240924092, "percentage": 25.46, "elapsed_time": "1:49:27", "remaining_time": "5:20:25", "throughput": 1487.4, "total_tokens": 9768128} {"current_steps": 46295, "total_steps": 181800, "loss": 0.0482, "lr": 4.6445235465834134e-05, "epoch": 5.092959295929593, "percentage": 25.46, "elapsed_time": "1:49:27", "remaining_time": "5:20:24", "throughput": 1487.4, "total_tokens": 9769184} {"current_steps": 46300, "total_steps": 181800, "loss": 0.0467, "lr": 4.6444001809242824e-05, "epoch": 5.0935093509350935, "percentage": 25.47, "elapsed_time": "1:49:28", "remaining_time": "5:20:23", "throughput": 1487.41, "total_tokens": 9770240} {"current_steps": 46305, "total_steps": 181800, "loss": 0.0442, "lr": 4.644276795501242e-05, "epoch": 5.094059405940594, "percentage": 25.47, "elapsed_time": "1:49:29", "remaining_time": "5:20:22", "throughput": 1487.4, "total_tokens": 9771232} {"current_steps": 46310, "total_steps": 181800, "loss": 0.0059, "lr": 4.644153390315433e-05, "epoch": 5.094609460946095, "percentage": 25.47, "elapsed_time": "1:49:30", "remaining_time": "5:20:21", "throughput": 1487.41, "total_tokens": 9772288} {"current_steps": 46315, "total_steps": 181800, "loss": 0.1428, "lr": 4.64402996536799e-05, "epoch": 5.095159515951595, "percentage": 25.48, "elapsed_time": "1:49:30", "remaining_time": "5:20:21", "throughput": 1487.41, "total_tokens": 9773312} {"current_steps": 46320, "total_steps": 181800, "loss": 0.1068, "lr": 4.643906520660052e-05, "epoch": 5.095709570957096, "percentage": 25.48, "elapsed_time": "1:49:31", "remaining_time": "5:20:20", "throughput": 1487.41, "total_tokens": 9774368} {"current_steps": 46325, "total_steps": 181800, "loss": 0.169, "lr": 4.643783056192757e-05, "epoch": 5.096259625962596, "percentage": 25.48, "elapsed_time": "1:49:32", "remaining_time": "5:20:19", "throughput": 1487.42, "total_tokens": 9775424} {"current_steps": 46330, "total_steps": 181800, "loss": 0.0156, "lr": 4.643659571967242e-05, "epoch": 5.0968096809680965, "percentage": 25.48, "elapsed_time": "1:49:32", "remaining_time": "5:20:18", "throughput": 1487.41, "total_tokens": 9776416} {"current_steps": 46335, "total_steps": 181800, "loss": 0.0366, "lr": 4.643536067984645e-05, "epoch": 5.097359735973598, "percentage": 25.49, "elapsed_time": "1:49:33", "remaining_time": "5:20:18", "throughput": 1487.41, "total_tokens": 9777440} {"current_steps": 46340, "total_steps": 181800, "loss": 0.0441, "lr": 4.643412544246104e-05, "epoch": 5.097909790979098, "percentage": 25.49, "elapsed_time": "1:49:34", "remaining_time": "5:20:17", "throughput": 1487.41, "total_tokens": 9778432} {"current_steps": 46345, "total_steps": 181800, "loss": 0.0105, "lr": 4.643289000752759e-05, "epoch": 5.098459845984599, "percentage": 25.49, "elapsed_time": "1:49:34", "remaining_time": "5:20:16", "throughput": 1487.41, "total_tokens": 9779488} {"current_steps": 46350, "total_steps": 181800, "loss": 0.0454, "lr": 4.6431654375057474e-05, "epoch": 5.099009900990099, "percentage": 25.5, "elapsed_time": "1:49:35", "remaining_time": "5:20:15", "throughput": 1487.41, "total_tokens": 9780512} {"current_steps": 46355, "total_steps": 181800, "loss": 0.0059, "lr": 4.643041854506208e-05, "epoch": 5.099559955995599, "percentage": 25.5, "elapsed_time": "1:49:36", "remaining_time": "5:20:15", "throughput": 1487.41, "total_tokens": 9781568} {"current_steps": 46360, "total_steps": 181800, "loss": 0.0964, "lr": 4.642918251755281e-05, "epoch": 5.1001100110011, "percentage": 25.5, "elapsed_time": "1:49:36", "remaining_time": "5:20:14", "throughput": 1487.41, "total_tokens": 9782592} {"current_steps": 46365, "total_steps": 181800, "loss": 0.092, "lr": 4.642794629254104e-05, "epoch": 5.100660066006601, "percentage": 25.5, "elapsed_time": "1:49:37", "remaining_time": "5:20:13", "throughput": 1487.42, "total_tokens": 9783680} {"current_steps": 46370, "total_steps": 181800, "loss": 0.0308, "lr": 4.642670987003818e-05, "epoch": 5.101210121012101, "percentage": 25.51, "elapsed_time": "1:49:38", "remaining_time": "5:20:12", "throughput": 1487.43, "total_tokens": 9784768} {"current_steps": 46375, "total_steps": 181800, "loss": 0.004, "lr": 4.642547325005561e-05, "epoch": 5.101760176017602, "percentage": 25.51, "elapsed_time": "1:49:38", "remaining_time": "5:20:12", "throughput": 1487.44, "total_tokens": 9785824} {"current_steps": 46380, "total_steps": 181800, "loss": 0.0165, "lr": 4.642423643260473e-05, "epoch": 5.102310231023102, "percentage": 25.51, "elapsed_time": "1:49:39", "remaining_time": "5:20:11", "throughput": 1487.45, "total_tokens": 9786880} {"current_steps": 46385, "total_steps": 181800, "loss": 0.1676, "lr": 4.6422999417696954e-05, "epoch": 5.102860286028603, "percentage": 25.51, "elapsed_time": "1:49:40", "remaining_time": "5:20:10", "throughput": 1487.46, "total_tokens": 9787968} {"current_steps": 46390, "total_steps": 181800, "loss": 0.0298, "lr": 4.642176220534367e-05, "epoch": 5.103410341034103, "percentage": 25.52, "elapsed_time": "1:49:41", "remaining_time": "5:20:09", "throughput": 1487.46, "total_tokens": 9789024} {"current_steps": 46395, "total_steps": 181800, "loss": 0.0196, "lr": 4.6420524795556274e-05, "epoch": 5.103960396039604, "percentage": 25.52, "elapsed_time": "1:49:41", "remaining_time": "5:20:08", "throughput": 1487.47, "total_tokens": 9790080} {"current_steps": 46400, "total_steps": 181800, "loss": 0.0274, "lr": 4.641928718834618e-05, "epoch": 5.104510451045105, "percentage": 25.52, "elapsed_time": "1:49:42", "remaining_time": "5:20:08", "throughput": 1487.48, "total_tokens": 9791168} {"current_steps": 46405, "total_steps": 181800, "loss": 0.0191, "lr": 4.6418049383724806e-05, "epoch": 5.105060506050605, "percentage": 25.53, "elapsed_time": "1:49:43", "remaining_time": "5:20:07", "throughput": 1487.48, "total_tokens": 9792192} {"current_steps": 46410, "total_steps": 181800, "loss": 0.0605, "lr": 4.641681138170354e-05, "epoch": 5.105610561056106, "percentage": 25.53, "elapsed_time": "1:49:43", "remaining_time": "5:20:06", "throughput": 1487.49, "total_tokens": 9793312} {"current_steps": 46415, "total_steps": 181800, "loss": 0.0509, "lr": 4.64155731822938e-05, "epoch": 5.106160616061606, "percentage": 25.53, "elapsed_time": "1:49:44", "remaining_time": "5:20:05", "throughput": 1487.49, "total_tokens": 9794368} {"current_steps": 46420, "total_steps": 181800, "loss": 0.037, "lr": 4.6414334785506995e-05, "epoch": 5.106710671067106, "percentage": 25.53, "elapsed_time": "1:49:45", "remaining_time": "5:20:05", "throughput": 1487.5, "total_tokens": 9795456} {"current_steps": 46425, "total_steps": 181800, "loss": 0.0121, "lr": 4.641309619135454e-05, "epoch": 5.1072607260726075, "percentage": 25.54, "elapsed_time": "1:49:45", "remaining_time": "5:20:04", "throughput": 1487.52, "total_tokens": 9796576} {"current_steps": 46430, "total_steps": 181800, "loss": 0.0745, "lr": 4.641185739984787e-05, "epoch": 5.107810781078108, "percentage": 25.54, "elapsed_time": "1:49:46", "remaining_time": "5:20:03", "throughput": 1487.52, "total_tokens": 9797632} {"current_steps": 46435, "total_steps": 181800, "loss": 0.0129, "lr": 4.641061841099837e-05, "epoch": 5.108360836083609, "percentage": 25.54, "elapsed_time": "1:49:47", "remaining_time": "5:20:02", "throughput": 1487.53, "total_tokens": 9798688} {"current_steps": 46440, "total_steps": 181800, "loss": 0.037, "lr": 4.640937922481748e-05, "epoch": 5.108910891089109, "percentage": 25.54, "elapsed_time": "1:49:47", "remaining_time": "5:20:02", "throughput": 1487.52, "total_tokens": 9799680} {"current_steps": 46445, "total_steps": 181800, "loss": 0.0088, "lr": 4.6408139841316614e-05, "epoch": 5.109460946094609, "percentage": 25.55, "elapsed_time": "1:49:48", "remaining_time": "5:20:01", "throughput": 1487.54, "total_tokens": 9800800} {"current_steps": 46450, "total_steps": 181800, "loss": 0.0431, "lr": 4.640690026050719e-05, "epoch": 5.11001100110011, "percentage": 25.55, "elapsed_time": "1:49:49", "remaining_time": "5:20:00", "throughput": 1487.54, "total_tokens": 9801856} {"current_steps": 46455, "total_steps": 181800, "loss": 0.0111, "lr": 4.6405660482400645e-05, "epoch": 5.1105610561056105, "percentage": 25.55, "elapsed_time": "1:49:49", "remaining_time": "5:19:59", "throughput": 1487.54, "total_tokens": 9802912} {"current_steps": 46460, "total_steps": 181800, "loss": 0.0083, "lr": 4.6404420507008397e-05, "epoch": 5.111111111111111, "percentage": 25.56, "elapsed_time": "1:49:50", "remaining_time": "5:19:58", "throughput": 1487.55, "total_tokens": 9804000} {"current_steps": 46465, "total_steps": 181800, "loss": 0.0148, "lr": 4.640318033434187e-05, "epoch": 5.111661166116612, "percentage": 25.56, "elapsed_time": "1:49:51", "remaining_time": "5:19:58", "throughput": 1487.55, "total_tokens": 9805024} {"current_steps": 46470, "total_steps": 181800, "loss": 0.0136, "lr": 4.6401939964412503e-05, "epoch": 5.112211221122112, "percentage": 25.56, "elapsed_time": "1:49:52", "remaining_time": "5:19:57", "throughput": 1487.56, "total_tokens": 9806080} {"current_steps": 46475, "total_steps": 181800, "loss": 0.1335, "lr": 4.640069939723173e-05, "epoch": 5.112761276127613, "percentage": 25.56, "elapsed_time": "1:49:52", "remaining_time": "5:19:56", "throughput": 1487.56, "total_tokens": 9807136} {"current_steps": 46480, "total_steps": 181800, "loss": 0.0282, "lr": 4.6399458632810977e-05, "epoch": 5.113311331133113, "percentage": 25.57, "elapsed_time": "1:49:53", "remaining_time": "5:19:55", "throughput": 1487.56, "total_tokens": 9808160} {"current_steps": 46485, "total_steps": 181800, "loss": 0.1289, "lr": 4.639821767116168e-05, "epoch": 5.1138613861386135, "percentage": 25.57, "elapsed_time": "1:49:54", "remaining_time": "5:19:55", "throughput": 1487.57, "total_tokens": 9809248} {"current_steps": 46490, "total_steps": 181800, "loss": 0.0917, "lr": 4.639697651229528e-05, "epoch": 5.114411441144115, "percentage": 25.57, "elapsed_time": "1:49:54", "remaining_time": "5:19:54", "throughput": 1487.57, "total_tokens": 9810240} {"current_steps": 46495, "total_steps": 181800, "loss": 0.0246, "lr": 4.639573515622322e-05, "epoch": 5.114961496149615, "percentage": 25.57, "elapsed_time": "1:49:55", "remaining_time": "5:19:53", "throughput": 1487.57, "total_tokens": 9811296} {"current_steps": 46500, "total_steps": 181800, "loss": 0.0202, "lr": 4.6394493602956926e-05, "epoch": 5.115511551155116, "percentage": 25.58, "elapsed_time": "1:49:56", "remaining_time": "5:19:52", "throughput": 1487.57, "total_tokens": 9812320} {"current_steps": 46505, "total_steps": 181800, "loss": 0.0131, "lr": 4.639325185250786e-05, "epoch": 5.116061606160616, "percentage": 25.58, "elapsed_time": "1:49:56", "remaining_time": "5:19:52", "throughput": 1487.57, "total_tokens": 9813376} {"current_steps": 46510, "total_steps": 181800, "loss": 0.0292, "lr": 4.639200990488745e-05, "epoch": 5.116611661166116, "percentage": 25.58, "elapsed_time": "1:49:57", "remaining_time": "5:19:51", "throughput": 1487.57, "total_tokens": 9814400} {"current_steps": 46515, "total_steps": 181800, "loss": 0.0104, "lr": 4.639076776010716e-05, "epoch": 5.117161716171617, "percentage": 25.59, "elapsed_time": "1:49:58", "remaining_time": "5:19:50", "throughput": 1487.58, "total_tokens": 9815488} {"current_steps": 46520, "total_steps": 181800, "loss": 0.0683, "lr": 4.638952541817841e-05, "epoch": 5.117711771177118, "percentage": 25.59, "elapsed_time": "1:49:58", "remaining_time": "5:19:49", "throughput": 1487.58, "total_tokens": 9816480} {"current_steps": 46525, "total_steps": 181800, "loss": 0.0374, "lr": 4.638828287911268e-05, "epoch": 5.118261826182618, "percentage": 25.59, "elapsed_time": "1:49:59", "remaining_time": "5:19:49", "throughput": 1487.59, "total_tokens": 9817568} {"current_steps": 46530, "total_steps": 181800, "loss": 0.0402, "lr": 4.638704014292141e-05, "epoch": 5.118811881188119, "percentage": 25.59, "elapsed_time": "1:50:00", "remaining_time": "5:19:48", "throughput": 1487.6, "total_tokens": 9818656} {"current_steps": 46535, "total_steps": 181800, "loss": 0.0483, "lr": 4.6385797209616054e-05, "epoch": 5.119361936193619, "percentage": 25.6, "elapsed_time": "1:50:01", "remaining_time": "5:19:47", "throughput": 1487.6, "total_tokens": 9819744} {"current_steps": 46540, "total_steps": 181800, "loss": 0.0085, "lr": 4.638455407920807e-05, "epoch": 5.11991199119912, "percentage": 25.6, "elapsed_time": "1:50:01", "remaining_time": "5:19:46", "throughput": 1487.61, "total_tokens": 9820800} {"current_steps": 46545, "total_steps": 181800, "loss": 0.0036, "lr": 4.63833107517089e-05, "epoch": 5.12046204620462, "percentage": 25.6, "elapsed_time": "1:50:02", "remaining_time": "5:19:45", "throughput": 1487.61, "total_tokens": 9821856} {"current_steps": 46550, "total_steps": 181800, "loss": 0.0381, "lr": 4.638206722713002e-05, "epoch": 5.121012101210121, "percentage": 25.61, "elapsed_time": "1:50:03", "remaining_time": "5:19:45", "throughput": 1487.61, "total_tokens": 9822880} {"current_steps": 46555, "total_steps": 181800, "loss": 0.0636, "lr": 4.638082350548289e-05, "epoch": 5.121562156215622, "percentage": 25.61, "elapsed_time": "1:50:03", "remaining_time": "5:19:44", "throughput": 1487.62, "total_tokens": 9823968} {"current_steps": 46560, "total_steps": 181800, "loss": 0.0607, "lr": 4.6379579586778965e-05, "epoch": 5.122112211221122, "percentage": 25.61, "elapsed_time": "1:50:04", "remaining_time": "5:19:43", "throughput": 1487.63, "total_tokens": 9825056} {"current_steps": 46565, "total_steps": 181800, "loss": 0.0777, "lr": 4.637833547102972e-05, "epoch": 5.122662266226623, "percentage": 25.61, "elapsed_time": "1:50:05", "remaining_time": "5:19:42", "throughput": 1487.64, "total_tokens": 9826144} {"current_steps": 46570, "total_steps": 181800, "loss": 0.0065, "lr": 4.637709115824661e-05, "epoch": 5.123212321232123, "percentage": 25.62, "elapsed_time": "1:50:05", "remaining_time": "5:19:42", "throughput": 1487.65, "total_tokens": 9827200} {"current_steps": 46575, "total_steps": 181800, "loss": 0.0102, "lr": 4.6375846648441116e-05, "epoch": 5.123762376237623, "percentage": 25.62, "elapsed_time": "1:50:06", "remaining_time": "5:19:41", "throughput": 1487.64, "total_tokens": 9828224} {"current_steps": 46580, "total_steps": 181800, "loss": 0.0761, "lr": 4.63746019416247e-05, "epoch": 5.1243124312431245, "percentage": 25.62, "elapsed_time": "1:50:07", "remaining_time": "5:19:40", "throughput": 1487.64, "total_tokens": 9829248} {"current_steps": 46585, "total_steps": 181800, "loss": 0.0379, "lr": 4.637335703780882e-05, "epoch": 5.124862486248625, "percentage": 25.62, "elapsed_time": "1:50:07", "remaining_time": "5:19:39", "throughput": 1487.65, "total_tokens": 9830304} {"current_steps": 46590, "total_steps": 181800, "loss": 0.0673, "lr": 4.6372111937004976e-05, "epoch": 5.125412541254126, "percentage": 25.63, "elapsed_time": "1:50:08", "remaining_time": "5:19:39", "throughput": 1487.66, "total_tokens": 9831392} {"current_steps": 46595, "total_steps": 181800, "loss": 0.0701, "lr": 4.637086663922463e-05, "epoch": 5.125962596259626, "percentage": 25.63, "elapsed_time": "1:50:09", "remaining_time": "5:19:38", "throughput": 1487.66, "total_tokens": 9832384} {"current_steps": 46600, "total_steps": 181800, "loss": 0.0655, "lr": 4.636962114447926e-05, "epoch": 5.126512651265126, "percentage": 25.63, "elapsed_time": "1:50:10", "remaining_time": "5:19:37", "throughput": 1487.66, "total_tokens": 9833440} {"current_steps": 46605, "total_steps": 181800, "loss": 0.0392, "lr": 4.6368375452780344e-05, "epoch": 5.127062706270627, "percentage": 25.64, "elapsed_time": "1:50:10", "remaining_time": "5:19:36", "throughput": 1487.67, "total_tokens": 9834528} {"current_steps": 46610, "total_steps": 181800, "loss": 0.0934, "lr": 4.636712956413937e-05, "epoch": 5.1276127612761275, "percentage": 25.64, "elapsed_time": "1:50:11", "remaining_time": "5:19:35", "throughput": 1487.68, "total_tokens": 9835616} {"current_steps": 46615, "total_steps": 181800, "loss": 0.0803, "lr": 4.636588347856781e-05, "epoch": 5.128162816281628, "percentage": 25.64, "elapsed_time": "1:50:12", "remaining_time": "5:19:35", "throughput": 1487.68, "total_tokens": 9836672} {"current_steps": 46620, "total_steps": 181800, "loss": 0.0231, "lr": 4.6364637196077164e-05, "epoch": 5.128712871287129, "percentage": 25.64, "elapsed_time": "1:50:12", "remaining_time": "5:19:34", "throughput": 1487.69, "total_tokens": 9837728} {"current_steps": 46625, "total_steps": 181800, "loss": 0.0418, "lr": 4.63633907166789e-05, "epoch": 5.129262926292629, "percentage": 25.65, "elapsed_time": "1:50:13", "remaining_time": "5:19:33", "throughput": 1487.68, "total_tokens": 9838688} {"current_steps": 46630, "total_steps": 181800, "loss": 0.0133, "lr": 4.636214404038451e-05, "epoch": 5.12981298129813, "percentage": 25.65, "elapsed_time": "1:50:14", "remaining_time": "5:19:32", "throughput": 1487.68, "total_tokens": 9839712} {"current_steps": 46635, "total_steps": 181800, "loss": 0.0106, "lr": 4.63608971672055e-05, "epoch": 5.13036303630363, "percentage": 25.65, "elapsed_time": "1:50:14", "remaining_time": "5:19:32", "throughput": 1487.68, "total_tokens": 9840768} {"current_steps": 46640, "total_steps": 181800, "loss": 0.054, "lr": 4.635965009715335e-05, "epoch": 5.1309130913091305, "percentage": 25.65, "elapsed_time": "1:50:15", "remaining_time": "5:19:31", "throughput": 1487.68, "total_tokens": 9841824} {"current_steps": 46645, "total_steps": 181800, "loss": 0.0128, "lr": 4.635840283023955e-05, "epoch": 5.131463146314632, "percentage": 25.66, "elapsed_time": "1:50:16", "remaining_time": "5:19:30", "throughput": 1487.7, "total_tokens": 9842944} {"current_steps": 46650, "total_steps": 181800, "loss": 0.0376, "lr": 4.63571553664756e-05, "epoch": 5.132013201320132, "percentage": 25.66, "elapsed_time": "1:50:16", "remaining_time": "5:19:29", "throughput": 1487.7, "total_tokens": 9844000} {"current_steps": 46655, "total_steps": 181800, "loss": 0.1091, "lr": 4.6355907705873e-05, "epoch": 5.132563256325633, "percentage": 25.66, "elapsed_time": "1:50:17", "remaining_time": "5:19:29", "throughput": 1487.7, "total_tokens": 9845024} {"current_steps": 46660, "total_steps": 181800, "loss": 0.0072, "lr": 4.635465984844325e-05, "epoch": 5.133113311331133, "percentage": 25.67, "elapsed_time": "1:50:18", "remaining_time": "5:19:28", "throughput": 1487.71, "total_tokens": 9846080} {"current_steps": 46665, "total_steps": 181800, "loss": 0.0384, "lr": 4.6353411794197837e-05, "epoch": 5.133663366336633, "percentage": 25.67, "elapsed_time": "1:50:18", "remaining_time": "5:19:27", "throughput": 1487.71, "total_tokens": 9847136} {"current_steps": 46670, "total_steps": 181800, "loss": 0.0301, "lr": 4.6352163543148275e-05, "epoch": 5.134213421342134, "percentage": 25.67, "elapsed_time": "1:50:19", "remaining_time": "5:19:26", "throughput": 1487.73, "total_tokens": 9848256} {"current_steps": 46675, "total_steps": 181800, "loss": 0.0649, "lr": 4.635091509530607e-05, "epoch": 5.134763476347635, "percentage": 25.67, "elapsed_time": "1:50:20", "remaining_time": "5:19:26", "throughput": 1487.73, "total_tokens": 9849344} {"current_steps": 46680, "total_steps": 181800, "loss": 0.0234, "lr": 4.6349666450682726e-05, "epoch": 5.135313531353136, "percentage": 25.68, "elapsed_time": "1:50:21", "remaining_time": "5:19:25", "throughput": 1487.75, "total_tokens": 9850464} {"current_steps": 46685, "total_steps": 181800, "loss": 0.013, "lr": 4.634841760928976e-05, "epoch": 5.135863586358636, "percentage": 25.68, "elapsed_time": "1:50:21", "remaining_time": "5:19:24", "throughput": 1487.75, "total_tokens": 9851520} {"current_steps": 46690, "total_steps": 181800, "loss": 0.0622, "lr": 4.634716857113866e-05, "epoch": 5.136413641364136, "percentage": 25.68, "elapsed_time": "1:50:22", "remaining_time": "5:19:23", "throughput": 1487.75, "total_tokens": 9852512} {"current_steps": 46695, "total_steps": 181800, "loss": 0.036, "lr": 4.6345919336240955e-05, "epoch": 5.136963696369637, "percentage": 25.68, "elapsed_time": "1:50:23", "remaining_time": "5:19:23", "throughput": 1487.74, "total_tokens": 9853504} {"current_steps": 46700, "total_steps": 181800, "loss": 0.1013, "lr": 4.6344669904608154e-05, "epoch": 5.137513751375137, "percentage": 25.69, "elapsed_time": "1:50:23", "remaining_time": "5:19:22", "throughput": 1487.75, "total_tokens": 9854592} {"current_steps": 46705, "total_steps": 181800, "loss": 0.0037, "lr": 4.634342027625177e-05, "epoch": 5.138063806380638, "percentage": 25.69, "elapsed_time": "1:50:24", "remaining_time": "5:19:21", "throughput": 1487.76, "total_tokens": 9855648} {"current_steps": 46710, "total_steps": 181800, "loss": 0.2269, "lr": 4.634217045118333e-05, "epoch": 5.138613861386139, "percentage": 25.69, "elapsed_time": "1:50:25", "remaining_time": "5:19:20", "throughput": 1487.76, "total_tokens": 9856704} {"current_steps": 46715, "total_steps": 181800, "loss": 0.1386, "lr": 4.634092042941434e-05, "epoch": 5.139163916391639, "percentage": 25.7, "elapsed_time": "1:50:25", "remaining_time": "5:19:19", "throughput": 1487.76, "total_tokens": 9857728} {"current_steps": 46720, "total_steps": 181800, "loss": 0.1089, "lr": 4.633967021095633e-05, "epoch": 5.13971397139714, "percentage": 25.7, "elapsed_time": "1:50:26", "remaining_time": "5:19:19", "throughput": 1487.76, "total_tokens": 9858752} {"current_steps": 46725, "total_steps": 181800, "loss": 0.0344, "lr": 4.633841979582082e-05, "epoch": 5.14026402640264, "percentage": 25.7, "elapsed_time": "1:50:27", "remaining_time": "5:19:18", "throughput": 1487.76, "total_tokens": 9859776} {"current_steps": 46730, "total_steps": 181800, "loss": 0.0481, "lr": 4.633716918401933e-05, "epoch": 5.1408140814081404, "percentage": 25.7, "elapsed_time": "1:50:27", "remaining_time": "5:19:17", "throughput": 1487.76, "total_tokens": 9860768} {"current_steps": 46735, "total_steps": 181800, "loss": 0.0105, "lr": 4.633591837556339e-05, "epoch": 5.1413641364136415, "percentage": 25.71, "elapsed_time": "1:50:28", "remaining_time": "5:19:16", "throughput": 1487.76, "total_tokens": 9861824} {"current_steps": 46740, "total_steps": 181800, "loss": 0.0586, "lr": 4.6334667370464535e-05, "epoch": 5.141914191419142, "percentage": 25.71, "elapsed_time": "1:50:29", "remaining_time": "5:19:16", "throughput": 1487.77, "total_tokens": 9862912} {"current_steps": 46745, "total_steps": 181800, "loss": 0.0782, "lr": 4.633341616873428e-05, "epoch": 5.142464246424643, "percentage": 25.71, "elapsed_time": "1:50:30", "remaining_time": "5:19:15", "throughput": 1487.78, "total_tokens": 9864000} {"current_steps": 46750, "total_steps": 181800, "loss": 0.1618, "lr": 4.633216477038417e-05, "epoch": 5.143014301430143, "percentage": 25.72, "elapsed_time": "1:50:30", "remaining_time": "5:19:14", "throughput": 1487.77, "total_tokens": 9864992} {"current_steps": 46755, "total_steps": 181800, "loss": 0.0792, "lr": 4.633091317542573e-05, "epoch": 5.143564356435643, "percentage": 25.72, "elapsed_time": "1:50:31", "remaining_time": "5:19:13", "throughput": 1487.77, "total_tokens": 9866016} {"current_steps": 46760, "total_steps": 181800, "loss": 0.1814, "lr": 4.6329661383870505e-05, "epoch": 5.144114411441144, "percentage": 25.72, "elapsed_time": "1:50:32", "remaining_time": "5:19:13", "throughput": 1487.78, "total_tokens": 9867104} {"current_steps": 46765, "total_steps": 181800, "loss": 0.0586, "lr": 4.632840939573002e-05, "epoch": 5.1446644664466445, "percentage": 25.72, "elapsed_time": "1:50:32", "remaining_time": "5:19:12", "throughput": 1487.79, "total_tokens": 9868160} {"current_steps": 46770, "total_steps": 181800, "loss": 0.0246, "lr": 4.6327157211015824e-05, "epoch": 5.145214521452146, "percentage": 25.73, "elapsed_time": "1:50:33", "remaining_time": "5:19:11", "throughput": 1487.79, "total_tokens": 9869184} {"current_steps": 46775, "total_steps": 181800, "loss": 0.1479, "lr": 4.6325904829739456e-05, "epoch": 5.145764576457646, "percentage": 25.73, "elapsed_time": "1:50:34", "remaining_time": "5:19:10", "throughput": 1487.79, "total_tokens": 9870240} {"current_steps": 46780, "total_steps": 181800, "loss": 0.0968, "lr": 4.6324652251912446e-05, "epoch": 5.146314631463146, "percentage": 25.73, "elapsed_time": "1:50:34", "remaining_time": "5:19:10", "throughput": 1487.8, "total_tokens": 9871328} {"current_steps": 46785, "total_steps": 181800, "loss": 0.0099, "lr": 4.6323399477546356e-05, "epoch": 5.146864686468647, "percentage": 25.73, "elapsed_time": "1:50:35", "remaining_time": "5:19:09", "throughput": 1487.8, "total_tokens": 9872384} {"current_steps": 46790, "total_steps": 181800, "loss": 0.0785, "lr": 4.632214650665272e-05, "epoch": 5.147414741474147, "percentage": 25.74, "elapsed_time": "1:50:36", "remaining_time": "5:19:08", "throughput": 1487.8, "total_tokens": 9873376} {"current_steps": 46795, "total_steps": 181800, "loss": 0.0655, "lr": 4.63208933392431e-05, "epoch": 5.1479647964796476, "percentage": 25.74, "elapsed_time": "1:50:36", "remaining_time": "5:19:07", "throughput": 1487.8, "total_tokens": 9874400} {"current_steps": 46800, "total_steps": 181800, "loss": 0.0388, "lr": 4.6319639975329026e-05, "epoch": 5.148514851485149, "percentage": 25.74, "elapsed_time": "1:50:37", "remaining_time": "5:19:06", "throughput": 1487.79, "total_tokens": 9875360} {"current_steps": 46805, "total_steps": 181800, "loss": 0.0839, "lr": 4.6318386414922066e-05, "epoch": 5.149064906490649, "percentage": 25.75, "elapsed_time": "1:50:38", "remaining_time": "5:19:06", "throughput": 1487.8, "total_tokens": 9876480} {"current_steps": 46810, "total_steps": 181800, "loss": 0.0994, "lr": 4.6317132658033766e-05, "epoch": 5.14961496149615, "percentage": 25.75, "elapsed_time": "1:50:38", "remaining_time": "5:19:05", "throughput": 1487.8, "total_tokens": 9877504} {"current_steps": 46815, "total_steps": 181800, "loss": 0.0328, "lr": 4.6315878704675685e-05, "epoch": 5.15016501650165, "percentage": 25.75, "elapsed_time": "1:50:39", "remaining_time": "5:19:04", "throughput": 1487.8, "total_tokens": 9878528} {"current_steps": 46820, "total_steps": 181800, "loss": 0.0035, "lr": 4.6314624554859386e-05, "epoch": 5.15071507150715, "percentage": 25.75, "elapsed_time": "1:50:40", "remaining_time": "5:19:03", "throughput": 1487.8, "total_tokens": 9879552} {"current_steps": 46825, "total_steps": 181800, "loss": 0.0497, "lr": 4.6313370208596406e-05, "epoch": 5.1512651265126514, "percentage": 25.76, "elapsed_time": "1:50:41", "remaining_time": "5:19:03", "throughput": 1487.81, "total_tokens": 9880640} {"current_steps": 46830, "total_steps": 181800, "loss": 0.0066, "lr": 4.6312115665898334e-05, "epoch": 5.151815181518152, "percentage": 25.76, "elapsed_time": "1:50:41", "remaining_time": "5:19:02", "throughput": 1487.81, "total_tokens": 9881664} {"current_steps": 46835, "total_steps": 181800, "loss": 0.1123, "lr": 4.631086092677671e-05, "epoch": 5.152365236523653, "percentage": 25.76, "elapsed_time": "1:50:42", "remaining_time": "5:19:01", "throughput": 1487.81, "total_tokens": 9882688} {"current_steps": 46840, "total_steps": 181800, "loss": 0.0545, "lr": 4.630960599124311e-05, "epoch": 5.152915291529153, "percentage": 25.76, "elapsed_time": "1:50:43", "remaining_time": "5:19:00", "throughput": 1487.82, "total_tokens": 9883744} {"current_steps": 46845, "total_steps": 181800, "loss": 0.0732, "lr": 4.630835085930909e-05, "epoch": 5.153465346534653, "percentage": 25.77, "elapsed_time": "1:50:43", "remaining_time": "5:19:00", "throughput": 1487.83, "total_tokens": 9884864} {"current_steps": 46850, "total_steps": 181800, "loss": 0.0383, "lr": 4.6307095530986234e-05, "epoch": 5.154015401540154, "percentage": 25.77, "elapsed_time": "1:50:44", "remaining_time": "5:18:59", "throughput": 1487.83, "total_tokens": 9885856} {"current_steps": 46855, "total_steps": 181800, "loss": 0.058, "lr": 4.630584000628609e-05, "epoch": 5.1545654565456545, "percentage": 25.77, "elapsed_time": "1:50:45", "remaining_time": "5:18:58", "throughput": 1487.84, "total_tokens": 9886944} {"current_steps": 46860, "total_steps": 181800, "loss": 0.1093, "lr": 4.630458428522025e-05, "epoch": 5.1551155115511555, "percentage": 25.78, "elapsed_time": "1:50:45", "remaining_time": "5:18:57", "throughput": 1487.84, "total_tokens": 9888000} {"current_steps": 46865, "total_steps": 181800, "loss": 0.0094, "lr": 4.6303328367800284e-05, "epoch": 5.155665566556656, "percentage": 25.78, "elapsed_time": "1:50:46", "remaining_time": "5:18:56", "throughput": 1487.85, "total_tokens": 9889120} {"current_steps": 46870, "total_steps": 181800, "loss": 0.0376, "lr": 4.6302072254037766e-05, "epoch": 5.156215621562156, "percentage": 25.78, "elapsed_time": "1:50:47", "remaining_time": "5:18:56", "throughput": 1487.86, "total_tokens": 9890208} {"current_steps": 46875, "total_steps": 181800, "loss": 0.143, "lr": 4.630081594394425e-05, "epoch": 5.156765676567657, "percentage": 25.78, "elapsed_time": "1:50:47", "remaining_time": "5:18:55", "throughput": 1487.87, "total_tokens": 9891264} {"current_steps": 46880, "total_steps": 181800, "loss": 0.1292, "lr": 4.629955943753135e-05, "epoch": 5.157315731573157, "percentage": 25.79, "elapsed_time": "1:50:48", "remaining_time": "5:18:54", "throughput": 1487.86, "total_tokens": 9892256} {"current_steps": 46885, "total_steps": 181800, "loss": 0.018, "lr": 4.629830273481063e-05, "epoch": 5.1578657865786575, "percentage": 25.79, "elapsed_time": "1:50:49", "remaining_time": "5:18:53", "throughput": 1487.87, "total_tokens": 9893312} {"current_steps": 46890, "total_steps": 181800, "loss": 0.1219, "lr": 4.629704583579367e-05, "epoch": 5.158415841584159, "percentage": 25.79, "elapsed_time": "1:50:50", "remaining_time": "5:18:53", "throughput": 1487.87, "total_tokens": 9894368} {"current_steps": 46895, "total_steps": 181800, "loss": 0.0736, "lr": 4.6295788740492064e-05, "epoch": 5.158965896589659, "percentage": 25.79, "elapsed_time": "1:50:50", "remaining_time": "5:18:52", "throughput": 1487.86, "total_tokens": 9895328} {"current_steps": 46900, "total_steps": 181800, "loss": 0.0441, "lr": 4.6294531448917386e-05, "epoch": 5.15951595159516, "percentage": 25.8, "elapsed_time": "1:50:51", "remaining_time": "5:18:51", "throughput": 1487.86, "total_tokens": 9896352} {"current_steps": 46905, "total_steps": 181800, "loss": 0.0189, "lr": 4.6293273961081237e-05, "epoch": 5.16006600660066, "percentage": 25.8, "elapsed_time": "1:50:52", "remaining_time": "5:18:50", "throughput": 1487.86, "total_tokens": 9897408} {"current_steps": 46910, "total_steps": 181800, "loss": 0.0422, "lr": 4.629201627699519e-05, "epoch": 5.16061606160616, "percentage": 25.8, "elapsed_time": "1:50:52", "remaining_time": "5:18:50", "throughput": 1487.87, "total_tokens": 9898464} {"current_steps": 46915, "total_steps": 181800, "loss": 0.0863, "lr": 4.6290758396670854e-05, "epoch": 5.161166116611661, "percentage": 25.81, "elapsed_time": "1:50:53", "remaining_time": "5:18:49", "throughput": 1487.87, "total_tokens": 9899488} {"current_steps": 46920, "total_steps": 181800, "loss": 0.122, "lr": 4.62895003201198e-05, "epoch": 5.161716171617162, "percentage": 25.81, "elapsed_time": "1:50:54", "remaining_time": "5:18:48", "throughput": 1487.88, "total_tokens": 9900576} {"current_steps": 46925, "total_steps": 181800, "loss": 0.0984, "lr": 4.628824204735365e-05, "epoch": 5.162266226622663, "percentage": 25.81, "elapsed_time": "1:50:54", "remaining_time": "5:18:47", "throughput": 1487.88, "total_tokens": 9901600} {"current_steps": 46930, "total_steps": 181800, "loss": 0.0497, "lr": 4.628698357838399e-05, "epoch": 5.162816281628163, "percentage": 25.81, "elapsed_time": "1:50:55", "remaining_time": "5:18:47", "throughput": 1487.89, "total_tokens": 9902688} {"current_steps": 46935, "total_steps": 181800, "loss": 0.0805, "lr": 4.6285724913222415e-05, "epoch": 5.163366336633663, "percentage": 25.82, "elapsed_time": "1:50:56", "remaining_time": "5:18:46", "throughput": 1487.9, "total_tokens": 9903808} {"current_steps": 46940, "total_steps": 181800, "loss": 0.055, "lr": 4.628446605188052e-05, "epoch": 5.163916391639164, "percentage": 25.82, "elapsed_time": "1:50:56", "remaining_time": "5:18:45", "throughput": 1487.91, "total_tokens": 9904864} {"current_steps": 46945, "total_steps": 181800, "loss": 0.0369, "lr": 4.628320699436992e-05, "epoch": 5.164466446644664, "percentage": 25.82, "elapsed_time": "1:50:57", "remaining_time": "5:18:44", "throughput": 1487.91, "total_tokens": 9905888} {"current_steps": 46950, "total_steps": 181800, "loss": 0.083, "lr": 4.6281947740702215e-05, "epoch": 5.165016501650165, "percentage": 25.83, "elapsed_time": "1:50:58", "remaining_time": "5:18:43", "throughput": 1487.91, "total_tokens": 9906912} {"current_steps": 46955, "total_steps": 181800, "loss": 0.0398, "lr": 4.628068829088901e-05, "epoch": 5.165566556655666, "percentage": 25.83, "elapsed_time": "1:50:58", "remaining_time": "5:18:43", "throughput": 1487.92, "total_tokens": 9908000} {"current_steps": 46960, "total_steps": 181800, "loss": 0.0169, "lr": 4.6279428644941904e-05, "epoch": 5.166116611661166, "percentage": 25.83, "elapsed_time": "1:50:59", "remaining_time": "5:18:42", "throughput": 1487.92, "total_tokens": 9909088} {"current_steps": 46965, "total_steps": 181800, "loss": 0.0327, "lr": 4.6278168802872525e-05, "epoch": 5.166666666666667, "percentage": 25.83, "elapsed_time": "1:51:00", "remaining_time": "5:18:41", "throughput": 1487.93, "total_tokens": 9910144} {"current_steps": 46970, "total_steps": 181800, "loss": 0.0785, "lr": 4.6276908764692474e-05, "epoch": 5.167216721672167, "percentage": 25.84, "elapsed_time": "1:51:01", "remaining_time": "5:18:40", "throughput": 1487.94, "total_tokens": 9911264} {"current_steps": 46975, "total_steps": 181800, "loss": 0.0217, "lr": 4.627564853041336e-05, "epoch": 5.167766776677667, "percentage": 25.84, "elapsed_time": "1:51:01", "remaining_time": "5:18:40", "throughput": 1487.96, "total_tokens": 9912416} {"current_steps": 46980, "total_steps": 181800, "loss": 0.1461, "lr": 4.62743881000468e-05, "epoch": 5.1683168316831685, "percentage": 25.84, "elapsed_time": "1:51:02", "remaining_time": "5:18:39", "throughput": 1487.97, "total_tokens": 9913472} {"current_steps": 46985, "total_steps": 181800, "loss": 0.0272, "lr": 4.6273127473604415e-05, "epoch": 5.168866886688669, "percentage": 25.84, "elapsed_time": "1:51:03", "remaining_time": "5:18:38", "throughput": 1487.97, "total_tokens": 9914496} {"current_steps": 46990, "total_steps": 181800, "loss": 0.0186, "lr": 4.627186665109783e-05, "epoch": 5.16941694169417, "percentage": 25.85, "elapsed_time": "1:51:03", "remaining_time": "5:18:37", "throughput": 1487.98, "total_tokens": 9915584} {"current_steps": 46995, "total_steps": 181800, "loss": 0.0854, "lr": 4.627060563253865e-05, "epoch": 5.16996699669967, "percentage": 25.85, "elapsed_time": "1:51:04", "remaining_time": "5:18:37", "throughput": 1487.98, "total_tokens": 9916608} {"current_steps": 47000, "total_steps": 181800, "loss": 0.0089, "lr": 4.626934441793851e-05, "epoch": 5.17051705170517, "percentage": 25.85, "elapsed_time": "1:51:05", "remaining_time": "5:18:36", "throughput": 1487.98, "total_tokens": 9917632} {"current_steps": 47005, "total_steps": 181800, "loss": 0.0671, "lr": 4.626808300730902e-05, "epoch": 5.171067106710671, "percentage": 25.86, "elapsed_time": "1:51:05", "remaining_time": "5:18:35", "throughput": 1487.98, "total_tokens": 9918688} {"current_steps": 47010, "total_steps": 181800, "loss": 0.0609, "lr": 4.626682140066182e-05, "epoch": 5.1716171617161715, "percentage": 25.86, "elapsed_time": "1:51:06", "remaining_time": "5:18:34", "throughput": 1487.99, "total_tokens": 9919776} {"current_steps": 47015, "total_steps": 181800, "loss": 0.1121, "lr": 4.626555959800853e-05, "epoch": 5.172167216721673, "percentage": 25.86, "elapsed_time": "1:51:07", "remaining_time": "5:18:34", "throughput": 1488.0, "total_tokens": 9920864} {"current_steps": 47020, "total_steps": 181800, "loss": 0.0353, "lr": 4.6264297599360787e-05, "epoch": 5.172717271727173, "percentage": 25.86, "elapsed_time": "1:51:07", "remaining_time": "5:18:33", "throughput": 1488.0, "total_tokens": 9921888} {"current_steps": 47025, "total_steps": 181800, "loss": 0.0132, "lr": 4.62630354047302e-05, "epoch": 5.173267326732673, "percentage": 25.87, "elapsed_time": "1:51:08", "remaining_time": "5:18:32", "throughput": 1488.01, "total_tokens": 9922944} {"current_steps": 47030, "total_steps": 181800, "loss": 0.0532, "lr": 4.626177301412844e-05, "epoch": 5.173817381738174, "percentage": 25.87, "elapsed_time": "1:51:09", "remaining_time": "5:18:31", "throughput": 1488.01, "total_tokens": 9924000} {"current_steps": 47035, "total_steps": 181800, "loss": 0.0513, "lr": 4.62605104275671e-05, "epoch": 5.174367436743674, "percentage": 25.87, "elapsed_time": "1:51:09", "remaining_time": "5:18:30", "throughput": 1488.02, "total_tokens": 9925120} {"current_steps": 47040, "total_steps": 181800, "loss": 0.0966, "lr": 4.6259247645057854e-05, "epoch": 5.174917491749175, "percentage": 25.87, "elapsed_time": "1:51:10", "remaining_time": "5:18:30", "throughput": 1488.03, "total_tokens": 9926176} {"current_steps": 47045, "total_steps": 181800, "loss": 0.0981, "lr": 4.625798466661232e-05, "epoch": 5.175467546754676, "percentage": 25.88, "elapsed_time": "1:51:11", "remaining_time": "5:18:29", "throughput": 1488.02, "total_tokens": 9927136} {"current_steps": 47050, "total_steps": 181800, "loss": 0.1303, "lr": 4.6256721492242136e-05, "epoch": 5.176017601760176, "percentage": 25.88, "elapsed_time": "1:51:12", "remaining_time": "5:18:28", "throughput": 1488.03, "total_tokens": 9928224} {"current_steps": 47055, "total_steps": 181800, "loss": 0.0102, "lr": 4.625545812195896e-05, "epoch": 5.176567656765677, "percentage": 25.88, "elapsed_time": "1:51:12", "remaining_time": "5:18:27", "throughput": 1488.04, "total_tokens": 9929312} {"current_steps": 47060, "total_steps": 181800, "loss": 0.0717, "lr": 4.625419455577442e-05, "epoch": 5.177117711771177, "percentage": 25.89, "elapsed_time": "1:51:13", "remaining_time": "5:18:27", "throughput": 1488.03, "total_tokens": 9930304} {"current_steps": 47065, "total_steps": 181800, "loss": 0.0357, "lr": 4.625293079370017e-05, "epoch": 5.177667766776677, "percentage": 25.89, "elapsed_time": "1:51:14", "remaining_time": "5:18:26", "throughput": 1488.04, "total_tokens": 9931392} {"current_steps": 47070, "total_steps": 181800, "loss": 0.1749, "lr": 4.625166683574784e-05, "epoch": 5.178217821782178, "percentage": 25.89, "elapsed_time": "1:51:14", "remaining_time": "5:18:25", "throughput": 1488.04, "total_tokens": 9932448} {"current_steps": 47075, "total_steps": 181800, "loss": 0.0596, "lr": 4.6250402681929115e-05, "epoch": 5.178767876787679, "percentage": 25.89, "elapsed_time": "1:51:15", "remaining_time": "5:18:24", "throughput": 1488.05, "total_tokens": 9933536} {"current_steps": 47080, "total_steps": 181800, "loss": 0.0537, "lr": 4.6249138332255614e-05, "epoch": 5.17931793179318, "percentage": 25.9, "elapsed_time": "1:51:16", "remaining_time": "5:18:24", "throughput": 1488.05, "total_tokens": 9934528} {"current_steps": 47085, "total_steps": 181800, "loss": 0.0112, "lr": 4.6247873786739e-05, "epoch": 5.17986798679868, "percentage": 25.9, "elapsed_time": "1:51:16", "remaining_time": "5:18:23", "throughput": 1488.06, "total_tokens": 9935616} {"current_steps": 47090, "total_steps": 181800, "loss": 0.0857, "lr": 4.624660904539094e-05, "epoch": 5.18041804180418, "percentage": 25.9, "elapsed_time": "1:51:17", "remaining_time": "5:18:22", "throughput": 1488.07, "total_tokens": 9936704} {"current_steps": 47095, "total_steps": 181800, "loss": 0.009, "lr": 4.624534410822307e-05, "epoch": 5.180968096809681, "percentage": 25.9, "elapsed_time": "1:51:18", "remaining_time": "5:18:21", "throughput": 1488.07, "total_tokens": 9937728} {"current_steps": 47100, "total_steps": 181800, "loss": 0.0381, "lr": 4.6244078975247064e-05, "epoch": 5.181518151815181, "percentage": 25.91, "elapsed_time": "1:51:18", "remaining_time": "5:18:20", "throughput": 1488.08, "total_tokens": 9938848} {"current_steps": 47105, "total_steps": 181800, "loss": 0.0392, "lr": 4.624281364647457e-05, "epoch": 5.1820682068206825, "percentage": 25.91, "elapsed_time": "1:51:19", "remaining_time": "5:18:20", "throughput": 1488.08, "total_tokens": 9939872} {"current_steps": 47110, "total_steps": 181800, "loss": 0.0303, "lr": 4.624154812191725e-05, "epoch": 5.182618261826183, "percentage": 25.91, "elapsed_time": "1:51:20", "remaining_time": "5:18:19", "throughput": 1488.09, "total_tokens": 9940960} {"current_steps": 47115, "total_steps": 181800, "loss": 0.0094, "lr": 4.6240282401586786e-05, "epoch": 5.183168316831683, "percentage": 25.92, "elapsed_time": "1:51:21", "remaining_time": "5:18:18", "throughput": 1488.09, "total_tokens": 9941984} {"current_steps": 47120, "total_steps": 181800, "loss": 0.0358, "lr": 4.623901648549483e-05, "epoch": 5.183718371837184, "percentage": 25.92, "elapsed_time": "1:51:21", "remaining_time": "5:18:17", "throughput": 1488.09, "total_tokens": 9943008} {"current_steps": 47125, "total_steps": 181800, "loss": 0.0062, "lr": 4.623775037365305e-05, "epoch": 5.184268426842684, "percentage": 25.92, "elapsed_time": "1:51:22", "remaining_time": "5:18:17", "throughput": 1488.1, "total_tokens": 9944064} {"current_steps": 47130, "total_steps": 181800, "loss": 0.0809, "lr": 4.6236484066073117e-05, "epoch": 5.184818481848184, "percentage": 25.92, "elapsed_time": "1:51:23", "remaining_time": "5:18:16", "throughput": 1488.1, "total_tokens": 9945120} {"current_steps": 47135, "total_steps": 181800, "loss": 0.0075, "lr": 4.623521756276669e-05, "epoch": 5.1853685368536855, "percentage": 25.93, "elapsed_time": "1:51:23", "remaining_time": "5:18:15", "throughput": 1488.11, "total_tokens": 9946176} {"current_steps": 47140, "total_steps": 181800, "loss": 0.0402, "lr": 4.6233950863745464e-05, "epoch": 5.185918591859186, "percentage": 25.93, "elapsed_time": "1:51:24", "remaining_time": "5:18:14", "throughput": 1488.1, "total_tokens": 9947168} {"current_steps": 47145, "total_steps": 181800, "loss": 0.0391, "lr": 4.6232683969021096e-05, "epoch": 5.186468646864687, "percentage": 25.93, "elapsed_time": "1:51:25", "remaining_time": "5:18:14", "throughput": 1488.1, "total_tokens": 9948192} {"current_steps": 47150, "total_steps": 181800, "loss": 0.0077, "lr": 4.623141687860527e-05, "epoch": 5.187018701870187, "percentage": 25.94, "elapsed_time": "1:51:25", "remaining_time": "5:18:13", "throughput": 1488.11, "total_tokens": 9949280} {"current_steps": 47155, "total_steps": 181800, "loss": 0.1433, "lr": 4.623014959250966e-05, "epoch": 5.187568756875687, "percentage": 25.94, "elapsed_time": "1:51:26", "remaining_time": "5:18:12", "throughput": 1488.12, "total_tokens": 9950336} {"current_steps": 47160, "total_steps": 181800, "loss": 0.0403, "lr": 4.622888211074595e-05, "epoch": 5.188118811881188, "percentage": 25.94, "elapsed_time": "1:51:27", "remaining_time": "5:18:11", "throughput": 1488.12, "total_tokens": 9951360} {"current_steps": 47165, "total_steps": 181800, "loss": 0.1107, "lr": 4.622761443332582e-05, "epoch": 5.1886688668866885, "percentage": 25.94, "elapsed_time": "1:51:27", "remaining_time": "5:18:10", "throughput": 1488.12, "total_tokens": 9952416} {"current_steps": 47170, "total_steps": 181800, "loss": 0.0481, "lr": 4.622634656026096e-05, "epoch": 5.18921892189219, "percentage": 25.95, "elapsed_time": "1:51:28", "remaining_time": "5:18:10", "throughput": 1488.13, "total_tokens": 9953472} {"current_steps": 47175, "total_steps": 181800, "loss": 0.0638, "lr": 4.622507849156305e-05, "epoch": 5.18976897689769, "percentage": 25.95, "elapsed_time": "1:51:29", "remaining_time": "5:18:09", "throughput": 1488.13, "total_tokens": 9954528} {"current_steps": 47180, "total_steps": 181800, "loss": 0.1676, "lr": 4.622381022724376e-05, "epoch": 5.19031903190319, "percentage": 25.95, "elapsed_time": "1:51:29", "remaining_time": "5:18:08", "throughput": 1488.13, "total_tokens": 9955584} {"current_steps": 47185, "total_steps": 181800, "loss": 0.019, "lr": 4.6222541767314806e-05, "epoch": 5.190869086908691, "percentage": 25.95, "elapsed_time": "1:51:30", "remaining_time": "5:18:07", "throughput": 1488.14, "total_tokens": 9956640} {"current_steps": 47190, "total_steps": 181800, "loss": 0.0211, "lr": 4.622127311178787e-05, "epoch": 5.191419141914191, "percentage": 25.96, "elapsed_time": "1:51:31", "remaining_time": "5:18:07", "throughput": 1488.14, "total_tokens": 9957664} {"current_steps": 47195, "total_steps": 181800, "loss": 0.1468, "lr": 4.622000426067464e-05, "epoch": 5.191969196919692, "percentage": 25.96, "elapsed_time": "1:51:32", "remaining_time": "5:18:06", "throughput": 1488.15, "total_tokens": 9958784} {"current_steps": 47200, "total_steps": 181800, "loss": 0.0434, "lr": 4.621873521398681e-05, "epoch": 5.192519251925193, "percentage": 25.96, "elapsed_time": "1:51:32", "remaining_time": "5:18:05", "throughput": 1488.16, "total_tokens": 9959840} {"current_steps": 47205, "total_steps": 181800, "loss": 0.0407, "lr": 4.6217465971736086e-05, "epoch": 5.193069306930693, "percentage": 25.97, "elapsed_time": "1:51:33", "remaining_time": "5:18:04", "throughput": 1488.15, "total_tokens": 9960800} {"current_steps": 47210, "total_steps": 181800, "loss": 0.0398, "lr": 4.621619653393415e-05, "epoch": 5.193619361936194, "percentage": 25.97, "elapsed_time": "1:51:34", "remaining_time": "5:18:04", "throughput": 1488.16, "total_tokens": 9961888} {"current_steps": 47215, "total_steps": 181800, "loss": 0.0103, "lr": 4.621492690059272e-05, "epoch": 5.194169416941694, "percentage": 25.97, "elapsed_time": "1:51:34", "remaining_time": "5:18:03", "throughput": 1488.16, "total_tokens": 9962944} {"current_steps": 47220, "total_steps": 181800, "loss": 0.0049, "lr": 4.621365707172348e-05, "epoch": 5.194719471947194, "percentage": 25.97, "elapsed_time": "1:51:35", "remaining_time": "5:18:02", "throughput": 1488.17, "total_tokens": 9964000} {"current_steps": 47225, "total_steps": 181800, "loss": 0.1483, "lr": 4.621238704733815e-05, "epoch": 5.195269526952695, "percentage": 25.98, "elapsed_time": "1:51:36", "remaining_time": "5:18:01", "throughput": 1488.18, "total_tokens": 9965120} {"current_steps": 47230, "total_steps": 181800, "loss": 0.014, "lr": 4.621111682744843e-05, "epoch": 5.195819581958196, "percentage": 25.98, "elapsed_time": "1:51:36", "remaining_time": "5:18:01", "throughput": 1488.18, "total_tokens": 9966176} {"current_steps": 47235, "total_steps": 181800, "loss": 0.0537, "lr": 4.6209846412066016e-05, "epoch": 5.196369636963697, "percentage": 25.98, "elapsed_time": "1:51:37", "remaining_time": "5:18:00", "throughput": 1488.19, "total_tokens": 9967264} {"current_steps": 47240, "total_steps": 181800, "loss": 0.0346, "lr": 4.6208575801202625e-05, "epoch": 5.196919691969197, "percentage": 25.98, "elapsed_time": "1:51:38", "remaining_time": "5:17:59", "throughput": 1488.21, "total_tokens": 9968384} {"current_steps": 47245, "total_steps": 181800, "loss": 0.0419, "lr": 4.620730499486997e-05, "epoch": 5.197469746974697, "percentage": 25.99, "elapsed_time": "1:51:39", "remaining_time": "5:17:59", "throughput": 1488.15, "total_tokens": 9969408} {"current_steps": 47250, "total_steps": 181800, "loss": 0.0203, "lr": 4.6206033993079765e-05, "epoch": 5.198019801980198, "percentage": 25.99, "elapsed_time": "1:51:39", "remaining_time": "5:17:58", "throughput": 1488.15, "total_tokens": 9970432} {"current_steps": 47255, "total_steps": 181800, "loss": 0.0258, "lr": 4.6204762795843715e-05, "epoch": 5.198569856985698, "percentage": 25.99, "elapsed_time": "1:51:40", "remaining_time": "5:17:57", "throughput": 1488.16, "total_tokens": 9971488} {"current_steps": 47260, "total_steps": 181800, "loss": 0.0399, "lr": 4.620349140317355e-05, "epoch": 5.1991199119911995, "percentage": 26.0, "elapsed_time": "1:51:41", "remaining_time": "5:17:57", "throughput": 1488.17, "total_tokens": 9972576} {"current_steps": 47265, "total_steps": 181800, "loss": 0.011, "lr": 4.620221981508097e-05, "epoch": 5.1996699669967, "percentage": 26.0, "elapsed_time": "1:51:41", "remaining_time": "5:17:56", "throughput": 1488.17, "total_tokens": 9973632} {"current_steps": 47270, "total_steps": 181800, "loss": 0.0734, "lr": 4.6200948031577705e-05, "epoch": 5.2002200220022, "percentage": 26.0, "elapsed_time": "1:51:42", "remaining_time": "5:17:55", "throughput": 1488.18, "total_tokens": 9974752} {"current_steps": 47275, "total_steps": 181800, "loss": 0.0181, "lr": 4.619967605267548e-05, "epoch": 5.200770077007701, "percentage": 26.0, "elapsed_time": "1:51:43", "remaining_time": "5:17:54", "throughput": 1488.19, "total_tokens": 9975840} {"current_steps": 47280, "total_steps": 181800, "loss": 0.0512, "lr": 4.619840387838601e-05, "epoch": 5.201320132013201, "percentage": 26.01, "elapsed_time": "1:51:44", "remaining_time": "5:17:54", "throughput": 1488.2, "total_tokens": 9976896} {"current_steps": 47285, "total_steps": 181800, "loss": 0.0577, "lr": 4.6197131508721026e-05, "epoch": 5.201870187018702, "percentage": 26.01, "elapsed_time": "1:51:44", "remaining_time": "5:17:53", "throughput": 1488.2, "total_tokens": 9977952} {"current_steps": 47290, "total_steps": 181800, "loss": 0.0148, "lr": 4.619585894369225e-05, "epoch": 5.2024202420242025, "percentage": 26.01, "elapsed_time": "1:51:45", "remaining_time": "5:17:52", "throughput": 1488.2, "total_tokens": 9978944} {"current_steps": 47295, "total_steps": 181800, "loss": 0.0818, "lr": 4.61945861833114e-05, "epoch": 5.202970297029703, "percentage": 26.01, "elapsed_time": "1:51:46", "remaining_time": "5:17:51", "throughput": 1488.2, "total_tokens": 9980000} {"current_steps": 47300, "total_steps": 181800, "loss": 0.019, "lr": 4.619331322759024e-05, "epoch": 5.203520352035204, "percentage": 26.02, "elapsed_time": "1:51:46", "remaining_time": "5:17:51", "throughput": 1488.21, "total_tokens": 9981056} {"current_steps": 47305, "total_steps": 181800, "loss": 0.0078, "lr": 4.6192040076540476e-05, "epoch": 5.204070407040704, "percentage": 26.02, "elapsed_time": "1:51:47", "remaining_time": "5:17:50", "throughput": 1488.21, "total_tokens": 9982080} {"current_steps": 47310, "total_steps": 181800, "loss": 0.0233, "lr": 4.619076673017384e-05, "epoch": 5.204620462046204, "percentage": 26.02, "elapsed_time": "1:51:48", "remaining_time": "5:17:49", "throughput": 1488.21, "total_tokens": 9983104} {"current_steps": 47315, "total_steps": 181800, "loss": 0.0445, "lr": 4.618949318850209e-05, "epoch": 5.205170517051705, "percentage": 26.03, "elapsed_time": "1:51:48", "remaining_time": "5:17:48", "throughput": 1488.21, "total_tokens": 9984128} {"current_steps": 47320, "total_steps": 181800, "loss": 0.0105, "lr": 4.618821945153694e-05, "epoch": 5.2057205720572055, "percentage": 26.03, "elapsed_time": "1:51:49", "remaining_time": "5:17:47", "throughput": 1488.21, "total_tokens": 9985152} {"current_steps": 47325, "total_steps": 181800, "loss": 0.008, "lr": 4.618694551929013e-05, "epoch": 5.206270627062707, "percentage": 26.03, "elapsed_time": "1:51:50", "remaining_time": "5:17:47", "throughput": 1488.2, "total_tokens": 9986144} {"current_steps": 47330, "total_steps": 181800, "loss": 0.058, "lr": 4.618567139177342e-05, "epoch": 5.206820682068207, "percentage": 26.03, "elapsed_time": "1:51:50", "remaining_time": "5:17:46", "throughput": 1488.2, "total_tokens": 9987200} {"current_steps": 47335, "total_steps": 181800, "loss": 0.0801, "lr": 4.618439706899854e-05, "epoch": 5.207370737073707, "percentage": 26.04, "elapsed_time": "1:51:51", "remaining_time": "5:17:45", "throughput": 1488.2, "total_tokens": 9988224} {"current_steps": 47340, "total_steps": 181800, "loss": 0.0093, "lr": 4.6183122550977234e-05, "epoch": 5.207920792079208, "percentage": 26.04, "elapsed_time": "1:51:52", "remaining_time": "5:17:44", "throughput": 1488.22, "total_tokens": 9989344} {"current_steps": 47345, "total_steps": 181800, "loss": 0.0205, "lr": 4.618184783772126e-05, "epoch": 5.208470847084708, "percentage": 26.04, "elapsed_time": "1:51:52", "remaining_time": "5:17:44", "throughput": 1488.22, "total_tokens": 9990368} {"current_steps": 47350, "total_steps": 181800, "loss": 0.0335, "lr": 4.618057292924235e-05, "epoch": 5.209020902090209, "percentage": 26.05, "elapsed_time": "1:51:53", "remaining_time": "5:17:43", "throughput": 1488.22, "total_tokens": 9991392} {"current_steps": 47355, "total_steps": 181800, "loss": 0.0903, "lr": 4.617929782555227e-05, "epoch": 5.20957095709571, "percentage": 26.05, "elapsed_time": "1:51:54", "remaining_time": "5:17:42", "throughput": 1488.22, "total_tokens": 9992416} {"current_steps": 47360, "total_steps": 181800, "loss": 0.0907, "lr": 4.617802252666276e-05, "epoch": 5.21012101210121, "percentage": 26.05, "elapsed_time": "1:51:55", "remaining_time": "5:17:41", "throughput": 1488.23, "total_tokens": 9993504} {"current_steps": 47365, "total_steps": 181800, "loss": 0.0613, "lr": 4.617674703258559e-05, "epoch": 5.210671067106711, "percentage": 26.05, "elapsed_time": "1:51:55", "remaining_time": "5:17:41", "throughput": 1488.24, "total_tokens": 9994624} {"current_steps": 47370, "total_steps": 181800, "loss": 0.0969, "lr": 4.6175471343332485e-05, "epoch": 5.211221122112211, "percentage": 26.06, "elapsed_time": "1:51:56", "remaining_time": "5:17:40", "throughput": 1488.24, "total_tokens": 9995648} {"current_steps": 47375, "total_steps": 181800, "loss": 0.0719, "lr": 4.6174195458915236e-05, "epoch": 5.211771177117711, "percentage": 26.06, "elapsed_time": "1:51:57", "remaining_time": "5:17:39", "throughput": 1488.25, "total_tokens": 9996736} {"current_steps": 47380, "total_steps": 181800, "loss": 0.0373, "lr": 4.617291937934558e-05, "epoch": 5.212321232123212, "percentage": 26.06, "elapsed_time": "1:51:57", "remaining_time": "5:17:38", "throughput": 1488.26, "total_tokens": 9997824} {"current_steps": 47385, "total_steps": 181800, "loss": 0.0602, "lr": 4.617164310463529e-05, "epoch": 5.212871287128713, "percentage": 26.06, "elapsed_time": "1:51:58", "remaining_time": "5:17:37", "throughput": 1488.27, "total_tokens": 9998880} {"current_steps": 47390, "total_steps": 181800, "loss": 0.021, "lr": 4.6170366634796125e-05, "epoch": 5.213421342134214, "percentage": 26.07, "elapsed_time": "1:51:59", "remaining_time": "5:17:37", "throughput": 1488.27, "total_tokens": 9999936} {"current_steps": 47395, "total_steps": 181800, "loss": 0.0204, "lr": 4.6169089969839844e-05, "epoch": 5.213971397139714, "percentage": 26.07, "elapsed_time": "1:51:59", "remaining_time": "5:17:36", "throughput": 1488.27, "total_tokens": 10000960} {"current_steps": 47400, "total_steps": 181800, "loss": 0.0049, "lr": 4.6167813109778225e-05, "epoch": 5.214521452145214, "percentage": 26.07, "elapsed_time": "1:52:00", "remaining_time": "5:17:35", "throughput": 1488.28, "total_tokens": 10002016} {"current_steps": 47405, "total_steps": 181800, "loss": 0.1109, "lr": 4.6166536054623025e-05, "epoch": 5.215071507150715, "percentage": 26.08, "elapsed_time": "1:52:01", "remaining_time": "5:17:34", "throughput": 1488.28, "total_tokens": 10003040} {"current_steps": 47410, "total_steps": 181800, "loss": 0.125, "lr": 4.6165258804386026e-05, "epoch": 5.215621562156215, "percentage": 26.08, "elapsed_time": "1:52:01", "remaining_time": "5:17:34", "throughput": 1488.28, "total_tokens": 10004096} {"current_steps": 47415, "total_steps": 181800, "loss": 0.0099, "lr": 4.6163981359078986e-05, "epoch": 5.2161716171617165, "percentage": 26.08, "elapsed_time": "1:52:02", "remaining_time": "5:17:33", "throughput": 1488.3, "total_tokens": 10005216} {"current_steps": 47420, "total_steps": 181800, "loss": 0.0469, "lr": 4.616270371871368e-05, "epoch": 5.216721672167217, "percentage": 26.08, "elapsed_time": "1:52:03", "remaining_time": "5:17:32", "throughput": 1488.3, "total_tokens": 10006272} {"current_steps": 47425, "total_steps": 181800, "loss": 0.1479, "lr": 4.61614258833019e-05, "epoch": 5.217271727172717, "percentage": 26.09, "elapsed_time": "1:52:03", "remaining_time": "5:17:31", "throughput": 1488.31, "total_tokens": 10007328} {"current_steps": 47430, "total_steps": 181800, "loss": 0.1485, "lr": 4.6160147852855405e-05, "epoch": 5.217821782178218, "percentage": 26.09, "elapsed_time": "1:52:04", "remaining_time": "5:17:31", "throughput": 1488.31, "total_tokens": 10008384} {"current_steps": 47435, "total_steps": 181800, "loss": 0.0192, "lr": 4.6158869627385986e-05, "epoch": 5.218371837183718, "percentage": 26.09, "elapsed_time": "1:52:05", "remaining_time": "5:17:30", "throughput": 1488.32, "total_tokens": 10009472} {"current_steps": 47440, "total_steps": 181800, "loss": 0.072, "lr": 4.615759120690542e-05, "epoch": 5.218921892189219, "percentage": 26.09, "elapsed_time": "1:52:06", "remaining_time": "5:17:29", "throughput": 1488.33, "total_tokens": 10010528} {"current_steps": 47445, "total_steps": 181800, "loss": 0.0253, "lr": 4.6156312591425485e-05, "epoch": 5.2194719471947195, "percentage": 26.1, "elapsed_time": "1:52:06", "remaining_time": "5:17:28", "throughput": 1488.33, "total_tokens": 10011616} {"current_steps": 47450, "total_steps": 181800, "loss": 0.0371, "lr": 4.6155033780957965e-05, "epoch": 5.22002200220022, "percentage": 26.1, "elapsed_time": "1:52:07", "remaining_time": "5:17:28", "throughput": 1488.33, "total_tokens": 10012640} {"current_steps": 47455, "total_steps": 181800, "loss": 0.011, "lr": 4.6153754775514655e-05, "epoch": 5.220572057205721, "percentage": 26.1, "elapsed_time": "1:52:08", "remaining_time": "5:17:27", "throughput": 1488.34, "total_tokens": 10013728} {"current_steps": 47460, "total_steps": 181800, "loss": 0.0342, "lr": 4.615247557510733e-05, "epoch": 5.221122112211221, "percentage": 26.11, "elapsed_time": "1:52:08", "remaining_time": "5:17:26", "throughput": 1488.35, "total_tokens": 10014784} {"current_steps": 47465, "total_steps": 181800, "loss": 0.0135, "lr": 4.61511961797478e-05, "epoch": 5.221672167216722, "percentage": 26.11, "elapsed_time": "1:52:09", "remaining_time": "5:17:25", "throughput": 1488.36, "total_tokens": 10015904} {"current_steps": 47470, "total_steps": 181800, "loss": 0.0276, "lr": 4.6149916589447836e-05, "epoch": 5.222222222222222, "percentage": 26.11, "elapsed_time": "1:52:10", "remaining_time": "5:17:24", "throughput": 1488.37, "total_tokens": 10016992} {"current_steps": 47475, "total_steps": 181800, "loss": 0.101, "lr": 4.614863680421924e-05, "epoch": 5.2227722772277225, "percentage": 26.11, "elapsed_time": "1:52:10", "remaining_time": "5:17:24", "throughput": 1488.4, "total_tokens": 10018176} {"current_steps": 47480, "total_steps": 181800, "loss": 0.0213, "lr": 4.6147356824073805e-05, "epoch": 5.223322332233224, "percentage": 26.12, "elapsed_time": "1:52:11", "remaining_time": "5:17:23", "throughput": 1488.41, "total_tokens": 10019296} {"current_steps": 47485, "total_steps": 181800, "loss": 0.0154, "lr": 4.614607664902333e-05, "epoch": 5.223872387238724, "percentage": 26.12, "elapsed_time": "1:52:12", "remaining_time": "5:17:22", "throughput": 1488.41, "total_tokens": 10020352} {"current_steps": 47490, "total_steps": 181800, "loss": 0.0297, "lr": 4.614479627907962e-05, "epoch": 5.224422442244224, "percentage": 26.12, "elapsed_time": "1:52:12", "remaining_time": "5:17:21", "throughput": 1488.41, "total_tokens": 10021376} {"current_steps": 47495, "total_steps": 181800, "loss": 0.1359, "lr": 4.6143515714254465e-05, "epoch": 5.224972497249725, "percentage": 26.12, "elapsed_time": "1:52:13", "remaining_time": "5:17:21", "throughput": 1488.42, "total_tokens": 10022464} {"current_steps": 47500, "total_steps": 181800, "loss": 0.0328, "lr": 4.614223495455967e-05, "epoch": 5.225522552255225, "percentage": 26.13, "elapsed_time": "1:52:14", "remaining_time": "5:17:20", "throughput": 1488.42, "total_tokens": 10023488} {"current_steps": 47505, "total_steps": 181800, "loss": 0.0153, "lr": 4.614095400000704e-05, "epoch": 5.226072607260726, "percentage": 26.13, "elapsed_time": "1:52:14", "remaining_time": "5:17:19", "throughput": 1488.43, "total_tokens": 10024544} {"current_steps": 47510, "total_steps": 181800, "loss": 0.0873, "lr": 4.613967285060839e-05, "epoch": 5.226622662266227, "percentage": 26.13, "elapsed_time": "1:52:15", "remaining_time": "5:17:18", "throughput": 1488.43, "total_tokens": 10025568} {"current_steps": 47515, "total_steps": 181800, "loss": 0.0081, "lr": 4.613839150637551e-05, "epoch": 5.227172717271727, "percentage": 26.14, "elapsed_time": "1:52:16", "remaining_time": "5:17:18", "throughput": 1488.43, "total_tokens": 10026592} {"current_steps": 47520, "total_steps": 181800, "loss": 0.0102, "lr": 4.613710996732021e-05, "epoch": 5.227722772277228, "percentage": 26.14, "elapsed_time": "1:52:17", "remaining_time": "5:17:17", "throughput": 1488.43, "total_tokens": 10027648} {"current_steps": 47525, "total_steps": 181800, "loss": 0.1098, "lr": 4.6135828233454325e-05, "epoch": 5.228272827282728, "percentage": 26.14, "elapsed_time": "1:52:17", "remaining_time": "5:17:16", "throughput": 1488.44, "total_tokens": 10028704} {"current_steps": 47530, "total_steps": 181800, "loss": 0.0236, "lr": 4.613454630478965e-05, "epoch": 5.228822882288229, "percentage": 26.14, "elapsed_time": "1:52:18", "remaining_time": "5:17:15", "throughput": 1488.44, "total_tokens": 10029792} {"current_steps": 47535, "total_steps": 181800, "loss": 0.015, "lr": 4.6133264181338006e-05, "epoch": 5.229372937293729, "percentage": 26.15, "elapsed_time": "1:52:19", "remaining_time": "5:17:15", "throughput": 1488.45, "total_tokens": 10030880} {"current_steps": 47540, "total_steps": 181800, "loss": 0.0591, "lr": 4.6131981863111204e-05, "epoch": 5.22992299229923, "percentage": 26.15, "elapsed_time": "1:52:19", "remaining_time": "5:17:14", "throughput": 1488.46, "total_tokens": 10031968} {"current_steps": 47545, "total_steps": 181800, "loss": 0.0683, "lr": 4.613069935012106e-05, "epoch": 5.230473047304731, "percentage": 26.15, "elapsed_time": "1:52:20", "remaining_time": "5:17:13", "throughput": 1488.47, "total_tokens": 10033024} {"current_steps": 47550, "total_steps": 181800, "loss": 0.0304, "lr": 4.61294166423794e-05, "epoch": 5.231023102310231, "percentage": 26.16, "elapsed_time": "1:52:21", "remaining_time": "5:17:12", "throughput": 1488.47, "total_tokens": 10034080} {"current_steps": 47555, "total_steps": 181800, "loss": 0.0182, "lr": 4.612813373989805e-05, "epoch": 5.231573157315731, "percentage": 26.16, "elapsed_time": "1:52:21", "remaining_time": "5:17:11", "throughput": 1488.48, "total_tokens": 10035168} {"current_steps": 47560, "total_steps": 181800, "loss": 0.0059, "lr": 4.6126850642688834e-05, "epoch": 5.232123212321232, "percentage": 26.16, "elapsed_time": "1:52:22", "remaining_time": "5:17:11", "throughput": 1488.49, "total_tokens": 10036288} {"current_steps": 47565, "total_steps": 181800, "loss": 0.1173, "lr": 4.612556735076357e-05, "epoch": 5.232673267326732, "percentage": 26.16, "elapsed_time": "1:52:23", "remaining_time": "5:17:10", "throughput": 1488.51, "total_tokens": 10037408} {"current_steps": 47570, "total_steps": 181800, "loss": 0.0426, "lr": 4.6124283864134077e-05, "epoch": 5.2332233223322335, "percentage": 26.17, "elapsed_time": "1:52:23", "remaining_time": "5:17:09", "throughput": 1488.52, "total_tokens": 10038528} {"current_steps": 47575, "total_steps": 181800, "loss": 0.0406, "lr": 4.612300018281221e-05, "epoch": 5.233773377337734, "percentage": 26.17, "elapsed_time": "1:52:24", "remaining_time": "5:17:08", "throughput": 1488.52, "total_tokens": 10039584} {"current_steps": 47580, "total_steps": 181800, "loss": 0.0114, "lr": 4.612171630680978e-05, "epoch": 5.234323432343234, "percentage": 26.17, "elapsed_time": "1:52:25", "remaining_time": "5:17:08", "throughput": 1488.53, "total_tokens": 10040640} {"current_steps": 47585, "total_steps": 181800, "loss": 0.1001, "lr": 4.612043223613863e-05, "epoch": 5.234873487348735, "percentage": 26.17, "elapsed_time": "1:52:26", "remaining_time": "5:17:07", "throughput": 1488.53, "total_tokens": 10041696} {"current_steps": 47590, "total_steps": 181800, "loss": 0.0157, "lr": 4.611914797081059e-05, "epoch": 5.235423542354235, "percentage": 26.18, "elapsed_time": "1:52:26", "remaining_time": "5:17:06", "throughput": 1488.53, "total_tokens": 10042720} {"current_steps": 47595, "total_steps": 181800, "loss": 0.0131, "lr": 4.611786351083749e-05, "epoch": 5.235973597359736, "percentage": 26.18, "elapsed_time": "1:52:27", "remaining_time": "5:17:05", "throughput": 1488.54, "total_tokens": 10043808} {"current_steps": 47600, "total_steps": 181800, "loss": 0.0451, "lr": 4.611657885623119e-05, "epoch": 5.2365236523652365, "percentage": 26.18, "elapsed_time": "1:52:28", "remaining_time": "5:17:05", "throughput": 1488.55, "total_tokens": 10044896} {"current_steps": 47605, "total_steps": 181800, "loss": 0.0684, "lr": 4.61152940070035e-05, "epoch": 5.237073707370737, "percentage": 26.19, "elapsed_time": "1:52:28", "remaining_time": "5:17:04", "throughput": 1488.55, "total_tokens": 10045920} {"current_steps": 47610, "total_steps": 181800, "loss": 0.0485, "lr": 4.611400896316628e-05, "epoch": 5.237623762376238, "percentage": 26.19, "elapsed_time": "1:52:29", "remaining_time": "5:17:03", "throughput": 1488.54, "total_tokens": 10046880} {"current_steps": 47615, "total_steps": 181800, "loss": 0.0768, "lr": 4.611272372473138e-05, "epoch": 5.238173817381738, "percentage": 26.19, "elapsed_time": "1:52:30", "remaining_time": "5:17:02", "throughput": 1488.55, "total_tokens": 10048000} {"current_steps": 47620, "total_steps": 181800, "loss": 0.0351, "lr": 4.611143829171063e-05, "epoch": 5.238723872387239, "percentage": 26.19, "elapsed_time": "1:52:30", "remaining_time": "5:17:02", "throughput": 1488.55, "total_tokens": 10049056} {"current_steps": 47625, "total_steps": 181800, "loss": 0.0794, "lr": 4.611015266411588e-05, "epoch": 5.239273927392739, "percentage": 26.2, "elapsed_time": "1:52:31", "remaining_time": "5:17:01", "throughput": 1488.57, "total_tokens": 10050176} {"current_steps": 47630, "total_steps": 181800, "loss": 0.0165, "lr": 4.6108866841958985e-05, "epoch": 5.2398239823982395, "percentage": 26.2, "elapsed_time": "1:52:32", "remaining_time": "5:17:00", "throughput": 1488.57, "total_tokens": 10051232} {"current_steps": 47635, "total_steps": 181800, "loss": 0.06, "lr": 4.61075808252518e-05, "epoch": 5.240374037403741, "percentage": 26.2, "elapsed_time": "1:52:32", "remaining_time": "5:16:59", "throughput": 1488.57, "total_tokens": 10052288} {"current_steps": 47640, "total_steps": 181800, "loss": 0.0059, "lr": 4.610629461400617e-05, "epoch": 5.240924092409241, "percentage": 26.2, "elapsed_time": "1:52:33", "remaining_time": "5:16:59", "throughput": 1488.57, "total_tokens": 10053312} {"current_steps": 47645, "total_steps": 181800, "loss": 0.0353, "lr": 4.6105008208233945e-05, "epoch": 5.241474147414741, "percentage": 26.21, "elapsed_time": "1:52:34", "remaining_time": "5:16:58", "throughput": 1488.58, "total_tokens": 10054368} {"current_steps": 47650, "total_steps": 181800, "loss": 0.0316, "lr": 4.610372160794699e-05, "epoch": 5.242024202420242, "percentage": 26.21, "elapsed_time": "1:52:35", "remaining_time": "5:16:57", "throughput": 1488.58, "total_tokens": 10055424} {"current_steps": 47655, "total_steps": 181800, "loss": 0.0186, "lr": 4.610243481315715e-05, "epoch": 5.242574257425742, "percentage": 26.21, "elapsed_time": "1:52:35", "remaining_time": "5:16:56", "throughput": 1488.59, "total_tokens": 10056512} {"current_steps": 47660, "total_steps": 181800, "loss": 0.2065, "lr": 4.61011478238763e-05, "epoch": 5.243124312431243, "percentage": 26.22, "elapsed_time": "1:52:36", "remaining_time": "5:16:56", "throughput": 1488.6, "total_tokens": 10057568} {"current_steps": 47665, "total_steps": 181800, "loss": 0.0643, "lr": 4.6099860640116296e-05, "epoch": 5.243674367436744, "percentage": 26.22, "elapsed_time": "1:52:37", "remaining_time": "5:16:55", "throughput": 1488.6, "total_tokens": 10058592} {"current_steps": 47670, "total_steps": 181800, "loss": 0.0497, "lr": 4.609857326188901e-05, "epoch": 5.244224422442244, "percentage": 26.22, "elapsed_time": "1:52:37", "remaining_time": "5:16:54", "throughput": 1488.6, "total_tokens": 10059648} {"current_steps": 47675, "total_steps": 181800, "loss": 0.0382, "lr": 4.6097285689206297e-05, "epoch": 5.244774477447745, "percentage": 26.22, "elapsed_time": "1:52:38", "remaining_time": "5:16:53", "throughput": 1488.61, "total_tokens": 10060736} {"current_steps": 47680, "total_steps": 181800, "loss": 0.0387, "lr": 4.609599792208001e-05, "epoch": 5.245324532453245, "percentage": 26.23, "elapsed_time": "1:52:39", "remaining_time": "5:16:52", "throughput": 1488.61, "total_tokens": 10061728} {"current_steps": 47685, "total_steps": 181800, "loss": 0.0608, "lr": 4.609470996052204e-05, "epoch": 5.245874587458746, "percentage": 26.23, "elapsed_time": "1:52:39", "remaining_time": "5:16:52", "throughput": 1488.61, "total_tokens": 10062816} {"current_steps": 47690, "total_steps": 181800, "loss": 0.1528, "lr": 4.6093421804544256e-05, "epoch": 5.2464246424642464, "percentage": 26.23, "elapsed_time": "1:52:40", "remaining_time": "5:16:51", "throughput": 1488.61, "total_tokens": 10063840} {"current_steps": 47695, "total_steps": 181800, "loss": 0.0421, "lr": 4.609213345415852e-05, "epoch": 5.246974697469747, "percentage": 26.23, "elapsed_time": "1:52:41", "remaining_time": "5:16:50", "throughput": 1488.61, "total_tokens": 10064864} {"current_steps": 47700, "total_steps": 181800, "loss": 0.1518, "lr": 4.6090844909376716e-05, "epoch": 5.247524752475248, "percentage": 26.24, "elapsed_time": "1:52:41", "remaining_time": "5:16:49", "throughput": 1488.62, "total_tokens": 10065952} {"current_steps": 47705, "total_steps": 181800, "loss": 0.0183, "lr": 4.6089556170210715e-05, "epoch": 5.248074807480748, "percentage": 26.24, "elapsed_time": "1:52:42", "remaining_time": "5:16:49", "throughput": 1488.64, "total_tokens": 10067072} {"current_steps": 47710, "total_steps": 181800, "loss": 0.0407, "lr": 4.608826723667239e-05, "epoch": 5.248624862486249, "percentage": 26.24, "elapsed_time": "1:52:43", "remaining_time": "5:16:48", "throughput": 1488.64, "total_tokens": 10068128} {"current_steps": 47715, "total_steps": 181800, "loss": 0.0903, "lr": 4.608697810877363e-05, "epoch": 5.249174917491749, "percentage": 26.25, "elapsed_time": "1:52:43", "remaining_time": "5:16:47", "throughput": 1488.65, "total_tokens": 10069184} {"current_steps": 47720, "total_steps": 181800, "loss": 0.0735, "lr": 4.60856887865263e-05, "epoch": 5.2497249724972495, "percentage": 26.25, "elapsed_time": "1:52:44", "remaining_time": "5:16:46", "throughput": 1488.65, "total_tokens": 10070240} {"current_steps": 47725, "total_steps": 181800, "loss": 0.0617, "lr": 4.6084399269942305e-05, "epoch": 5.2502750275027505, "percentage": 26.25, "elapsed_time": "1:52:45", "remaining_time": "5:16:46", "throughput": 1488.65, "total_tokens": 10071264} {"current_steps": 47730, "total_steps": 181800, "loss": 0.0429, "lr": 4.608310955903351e-05, "epoch": 5.250825082508251, "percentage": 26.25, "elapsed_time": "1:52:46", "remaining_time": "5:16:45", "throughput": 1488.65, "total_tokens": 10072288} {"current_steps": 47735, "total_steps": 181800, "loss": 0.033, "lr": 4.608181965381182e-05, "epoch": 5.251375137513751, "percentage": 26.26, "elapsed_time": "1:52:46", "remaining_time": "5:16:44", "throughput": 1488.65, "total_tokens": 10073312} {"current_steps": 47740, "total_steps": 181800, "loss": 0.0434, "lr": 4.608052955428911e-05, "epoch": 5.251925192519252, "percentage": 26.26, "elapsed_time": "1:52:47", "remaining_time": "5:16:43", "throughput": 1488.67, "total_tokens": 10074432} {"current_steps": 47745, "total_steps": 181800, "loss": 0.0454, "lr": 4.607923926047727e-05, "epoch": 5.252475247524752, "percentage": 26.26, "elapsed_time": "1:52:48", "remaining_time": "5:16:43", "throughput": 1488.67, "total_tokens": 10075488} {"current_steps": 47750, "total_steps": 181800, "loss": 0.0112, "lr": 4.607794877238821e-05, "epoch": 5.253025302530253, "percentage": 26.27, "elapsed_time": "1:52:48", "remaining_time": "5:16:42", "throughput": 1488.68, "total_tokens": 10076608} {"current_steps": 47755, "total_steps": 181800, "loss": 0.0497, "lr": 4.60766580900338e-05, "epoch": 5.2535753575357536, "percentage": 26.27, "elapsed_time": "1:52:49", "remaining_time": "5:16:41", "throughput": 1488.69, "total_tokens": 10077696} {"current_steps": 47760, "total_steps": 181800, "loss": 0.0054, "lr": 4.607536721342595e-05, "epoch": 5.254125412541254, "percentage": 26.27, "elapsed_time": "1:52:50", "remaining_time": "5:16:40", "throughput": 1488.69, "total_tokens": 10078720} {"current_steps": 47765, "total_steps": 181800, "loss": 0.0867, "lr": 4.607407614257655e-05, "epoch": 5.254675467546755, "percentage": 26.27, "elapsed_time": "1:52:50", "remaining_time": "5:16:39", "throughput": 1488.69, "total_tokens": 10079744} {"current_steps": 47770, "total_steps": 181800, "loss": 0.1097, "lr": 4.6072784877497504e-05, "epoch": 5.255225522552255, "percentage": 26.28, "elapsed_time": "1:52:51", "remaining_time": "5:16:39", "throughput": 1488.69, "total_tokens": 10080768} {"current_steps": 47775, "total_steps": 181800, "loss": 0.0571, "lr": 4.6071493418200714e-05, "epoch": 5.255775577557756, "percentage": 26.28, "elapsed_time": "1:52:52", "remaining_time": "5:16:38", "throughput": 1488.7, "total_tokens": 10081856} {"current_steps": 47780, "total_steps": 181800, "loss": 0.0375, "lr": 4.607020176469807e-05, "epoch": 5.256325632563256, "percentage": 26.28, "elapsed_time": "1:52:52", "remaining_time": "5:16:37", "throughput": 1488.71, "total_tokens": 10082912} {"current_steps": 47785, "total_steps": 181800, "loss": 0.047, "lr": 4.60689099170015e-05, "epoch": 5.256875687568757, "percentage": 26.28, "elapsed_time": "1:52:53", "remaining_time": "5:16:36", "throughput": 1488.72, "total_tokens": 10084000} {"current_steps": 47790, "total_steps": 181800, "loss": 0.0125, "lr": 4.606761787512289e-05, "epoch": 5.257425742574258, "percentage": 26.29, "elapsed_time": "1:52:54", "remaining_time": "5:16:36", "throughput": 1488.72, "total_tokens": 10085056} {"current_steps": 47795, "total_steps": 181800, "loss": 0.1356, "lr": 4.606632563907416e-05, "epoch": 5.257975797579758, "percentage": 26.29, "elapsed_time": "1:52:55", "remaining_time": "5:16:35", "throughput": 1488.72, "total_tokens": 10086080} {"current_steps": 47800, "total_steps": 181800, "loss": 0.0348, "lr": 4.6065033208867216e-05, "epoch": 5.258525852585258, "percentage": 26.29, "elapsed_time": "1:52:55", "remaining_time": "5:16:34", "throughput": 1488.72, "total_tokens": 10087136} {"current_steps": 47805, "total_steps": 181800, "loss": 0.0245, "lr": 4.606374058451396e-05, "epoch": 5.259075907590759, "percentage": 26.3, "elapsed_time": "1:52:56", "remaining_time": "5:16:33", "throughput": 1488.72, "total_tokens": 10088128} {"current_steps": 47810, "total_steps": 181800, "loss": 0.0535, "lr": 4.606244776602632e-05, "epoch": 5.259625962596259, "percentage": 26.3, "elapsed_time": "1:52:57", "remaining_time": "5:16:33", "throughput": 1488.72, "total_tokens": 10089184} {"current_steps": 47815, "total_steps": 181800, "loss": 0.196, "lr": 4.60611547534162e-05, "epoch": 5.2601760176017605, "percentage": 26.3, "elapsed_time": "1:52:57", "remaining_time": "5:16:32", "throughput": 1488.73, "total_tokens": 10090272} {"current_steps": 47820, "total_steps": 181800, "loss": 0.0756, "lr": 4.605986154669554e-05, "epoch": 5.260726072607261, "percentage": 26.3, "elapsed_time": "1:52:58", "remaining_time": "5:16:31", "throughput": 1488.73, "total_tokens": 10091264} {"current_steps": 47825, "total_steps": 181800, "loss": 0.139, "lr": 4.605856814587622e-05, "epoch": 5.261276127612761, "percentage": 26.31, "elapsed_time": "1:52:59", "remaining_time": "5:16:30", "throughput": 1488.73, "total_tokens": 10092288} {"current_steps": 47830, "total_steps": 181800, "loss": 0.017, "lr": 4.60572745509702e-05, "epoch": 5.261826182618262, "percentage": 26.31, "elapsed_time": "1:52:59", "remaining_time": "5:16:30", "throughput": 1488.73, "total_tokens": 10093312} {"current_steps": 47835, "total_steps": 181800, "loss": 0.0402, "lr": 4.605598076198937e-05, "epoch": 5.262376237623762, "percentage": 26.31, "elapsed_time": "1:53:00", "remaining_time": "5:16:29", "throughput": 1488.72, "total_tokens": 10094336} {"current_steps": 47840, "total_steps": 181800, "loss": 0.0342, "lr": 4.6054686778945674e-05, "epoch": 5.262926292629263, "percentage": 26.31, "elapsed_time": "1:53:01", "remaining_time": "5:16:28", "throughput": 1488.73, "total_tokens": 10095392} {"current_steps": 47845, "total_steps": 181800, "loss": 0.0523, "lr": 4.605339260185104e-05, "epoch": 5.2634763476347635, "percentage": 26.32, "elapsed_time": "1:53:01", "remaining_time": "5:16:27", "throughput": 1488.73, "total_tokens": 10096416} {"current_steps": 47850, "total_steps": 181800, "loss": 0.0587, "lr": 4.6052098230717376e-05, "epoch": 5.264026402640264, "percentage": 26.32, "elapsed_time": "1:53:02", "remaining_time": "5:16:27", "throughput": 1488.73, "total_tokens": 10097440} {"current_steps": 47855, "total_steps": 181800, "loss": 0.009, "lr": 4.605080366555664e-05, "epoch": 5.264576457645765, "percentage": 26.32, "elapsed_time": "1:53:03", "remaining_time": "5:16:26", "throughput": 1488.74, "total_tokens": 10098560} {"current_steps": 47860, "total_steps": 181800, "loss": 0.0737, "lr": 4.604950890638073e-05, "epoch": 5.265126512651265, "percentage": 26.33, "elapsed_time": "1:53:03", "remaining_time": "5:16:25", "throughput": 1488.74, "total_tokens": 10099584} {"current_steps": 47865, "total_steps": 181800, "loss": 0.0038, "lr": 4.6048213953201615e-05, "epoch": 5.265676567656766, "percentage": 26.33, "elapsed_time": "1:53:04", "remaining_time": "5:16:24", "throughput": 1488.74, "total_tokens": 10100640} {"current_steps": 47870, "total_steps": 181800, "loss": 0.0239, "lr": 4.60469188060312e-05, "epoch": 5.266226622662266, "percentage": 26.33, "elapsed_time": "1:53:05", "remaining_time": "5:16:23", "throughput": 1488.74, "total_tokens": 10101664} {"current_steps": 47875, "total_steps": 181800, "loss": 0.022, "lr": 4.604562346488144e-05, "epoch": 5.2667766776677665, "percentage": 26.33, "elapsed_time": "1:53:06", "remaining_time": "5:16:23", "throughput": 1488.74, "total_tokens": 10102688} {"current_steps": 47880, "total_steps": 181800, "loss": 0.0277, "lr": 4.6044327929764264e-05, "epoch": 5.267326732673268, "percentage": 26.34, "elapsed_time": "1:53:06", "remaining_time": "5:16:22", "throughput": 1488.74, "total_tokens": 10103680} {"current_steps": 47885, "total_steps": 181800, "loss": 0.0239, "lr": 4.6043032200691616e-05, "epoch": 5.267876787678768, "percentage": 26.34, "elapsed_time": "1:53:07", "remaining_time": "5:16:21", "throughput": 1488.75, "total_tokens": 10104768} {"current_steps": 47890, "total_steps": 181800, "loss": 0.0237, "lr": 4.6041736277675434e-05, "epoch": 5.268426842684269, "percentage": 26.34, "elapsed_time": "1:53:08", "remaining_time": "5:16:20", "throughput": 1488.74, "total_tokens": 10105760} {"current_steps": 47895, "total_steps": 181800, "loss": 0.0246, "lr": 4.604044016072767e-05, "epoch": 5.268976897689769, "percentage": 26.34, "elapsed_time": "1:53:08", "remaining_time": "5:16:20", "throughput": 1488.75, "total_tokens": 10106816} {"current_steps": 47900, "total_steps": 181800, "loss": 0.0364, "lr": 4.6039143849860264e-05, "epoch": 5.269526952695269, "percentage": 26.35, "elapsed_time": "1:53:09", "remaining_time": "5:16:19", "throughput": 1488.74, "total_tokens": 10107808} {"current_steps": 47905, "total_steps": 181800, "loss": 0.1539, "lr": 4.603784734508516e-05, "epoch": 5.27007700770077, "percentage": 26.35, "elapsed_time": "1:53:10", "remaining_time": "5:16:18", "throughput": 1488.74, "total_tokens": 10108832} {"current_steps": 47910, "total_steps": 181800, "loss": 0.0658, "lr": 4.603655064641432e-05, "epoch": 5.270627062706271, "percentage": 26.35, "elapsed_time": "1:53:10", "remaining_time": "5:16:17", "throughput": 1488.75, "total_tokens": 10109920} {"current_steps": 47915, "total_steps": 181800, "loss": 0.0477, "lr": 4.603525375385968e-05, "epoch": 5.271177117711771, "percentage": 26.36, "elapsed_time": "1:53:11", "remaining_time": "5:16:17", "throughput": 1488.76, "total_tokens": 10110976} {"current_steps": 47920, "total_steps": 181800, "loss": 0.0251, "lr": 4.603395666743321e-05, "epoch": 5.271727172717272, "percentage": 26.36, "elapsed_time": "1:53:12", "remaining_time": "5:16:16", "throughput": 1488.76, "total_tokens": 10112032} {"current_steps": 47925, "total_steps": 181800, "loss": 0.0036, "lr": 4.603265938714685e-05, "epoch": 5.272277227722772, "percentage": 26.36, "elapsed_time": "1:53:12", "remaining_time": "5:16:15", "throughput": 1488.76, "total_tokens": 10113024} {"current_steps": 47930, "total_steps": 181800, "loss": 0.0568, "lr": 4.603136191301256e-05, "epoch": 5.272827282728273, "percentage": 26.36, "elapsed_time": "1:53:13", "remaining_time": "5:16:14", "throughput": 1488.76, "total_tokens": 10114080} {"current_steps": 47935, "total_steps": 181800, "loss": 0.0645, "lr": 4.6030064245042295e-05, "epoch": 5.273377337733773, "percentage": 26.37, "elapsed_time": "1:53:14", "remaining_time": "5:16:14", "throughput": 1488.77, "total_tokens": 10115136} {"current_steps": 47940, "total_steps": 181800, "loss": 0.0232, "lr": 4.602876638324802e-05, "epoch": 5.273927392739274, "percentage": 26.37, "elapsed_time": "1:53:15", "remaining_time": "5:16:13", "throughput": 1488.76, "total_tokens": 10116160} {"current_steps": 47945, "total_steps": 181800, "loss": 0.0125, "lr": 4.60274683276417e-05, "epoch": 5.274477447744775, "percentage": 26.37, "elapsed_time": "1:53:15", "remaining_time": "5:16:12", "throughput": 1488.77, "total_tokens": 10117248} {"current_steps": 47950, "total_steps": 181800, "loss": 0.0637, "lr": 4.602617007823529e-05, "epoch": 5.275027502750275, "percentage": 26.38, "elapsed_time": "1:53:16", "remaining_time": "5:16:11", "throughput": 1488.78, "total_tokens": 10118304} {"current_steps": 47955, "total_steps": 181800, "loss": 0.0713, "lr": 4.602487163504077e-05, "epoch": 5.275577557755776, "percentage": 26.38, "elapsed_time": "1:53:17", "remaining_time": "5:16:10", "throughput": 1488.79, "total_tokens": 10119424} {"current_steps": 47960, "total_steps": 181800, "loss": 0.0431, "lr": 4.602357299807008e-05, "epoch": 5.276127612761276, "percentage": 26.38, "elapsed_time": "1:53:17", "remaining_time": "5:16:10", "throughput": 1488.8, "total_tokens": 10120512} {"current_steps": 47965, "total_steps": 181800, "loss": 0.0892, "lr": 4.6022274167335225e-05, "epoch": 5.276677667766776, "percentage": 26.38, "elapsed_time": "1:53:18", "remaining_time": "5:16:09", "throughput": 1488.8, "total_tokens": 10121536} {"current_steps": 47970, "total_steps": 181800, "loss": 0.034, "lr": 4.6020975142848146e-05, "epoch": 5.2772277227722775, "percentage": 26.39, "elapsed_time": "1:53:19", "remaining_time": "5:16:08", "throughput": 1488.82, "total_tokens": 10122656} {"current_steps": 47975, "total_steps": 181800, "loss": 0.0127, "lr": 4.601967592462082e-05, "epoch": 5.277777777777778, "percentage": 26.39, "elapsed_time": "1:53:19", "remaining_time": "5:16:07", "throughput": 1488.82, "total_tokens": 10123680} {"current_steps": 47980, "total_steps": 181800, "loss": 0.0037, "lr": 4.6018376512665235e-05, "epoch": 5.278327832783278, "percentage": 26.39, "elapsed_time": "1:53:20", "remaining_time": "5:16:07", "throughput": 1488.82, "total_tokens": 10124736} {"current_steps": 47985, "total_steps": 181800, "loss": 0.0495, "lr": 4.601707690699336e-05, "epoch": 5.278877887788779, "percentage": 26.39, "elapsed_time": "1:53:21", "remaining_time": "5:16:06", "throughput": 1488.83, "total_tokens": 10125824} {"current_steps": 47990, "total_steps": 181800, "loss": 0.0321, "lr": 4.601577710761717e-05, "epoch": 5.279427942794279, "percentage": 26.4, "elapsed_time": "1:53:21", "remaining_time": "5:16:05", "throughput": 1488.84, "total_tokens": 10126880} {"current_steps": 47995, "total_steps": 181800, "loss": 0.0406, "lr": 4.6014477114548645e-05, "epoch": 5.27997799779978, "percentage": 26.4, "elapsed_time": "1:53:22", "remaining_time": "5:16:04", "throughput": 1488.83, "total_tokens": 10127904} {"current_steps": 48000, "total_steps": 181800, "loss": 0.0064, "lr": 4.6013176927799764e-05, "epoch": 5.2805280528052805, "percentage": 26.4, "elapsed_time": "1:53:23", "remaining_time": "5:16:04", "throughput": 1488.85, "total_tokens": 10129024} {"current_steps": 48005, "total_steps": 181800, "loss": 0.0549, "lr": 4.6011876547382526e-05, "epoch": 5.281078107810781, "percentage": 26.41, "elapsed_time": "1:53:23", "remaining_time": "5:16:03", "throughput": 1488.86, "total_tokens": 10130112} {"current_steps": 48010, "total_steps": 181800, "loss": 0.0116, "lr": 4.60105759733089e-05, "epoch": 5.281628162816282, "percentage": 26.41, "elapsed_time": "1:53:24", "remaining_time": "5:16:02", "throughput": 1488.87, "total_tokens": 10131200} {"current_steps": 48015, "total_steps": 181800, "loss": 0.0833, "lr": 4.600927520559087e-05, "epoch": 5.282178217821782, "percentage": 26.41, "elapsed_time": "1:53:25", "remaining_time": "5:16:01", "throughput": 1488.87, "total_tokens": 10132288} {"current_steps": 48020, "total_steps": 181800, "loss": 0.0062, "lr": 4.600797424424044e-05, "epoch": 5.282728272827283, "percentage": 26.41, "elapsed_time": "1:53:26", "remaining_time": "5:16:01", "throughput": 1488.87, "total_tokens": 10133280} {"current_steps": 48025, "total_steps": 181800, "loss": 0.1359, "lr": 4.600667308926959e-05, "epoch": 5.283278327832783, "percentage": 26.42, "elapsed_time": "1:53:26", "remaining_time": "5:16:00", "throughput": 1488.87, "total_tokens": 10134336} {"current_steps": 48030, "total_steps": 181800, "loss": 0.005, "lr": 4.6005371740690304e-05, "epoch": 5.2838283828382835, "percentage": 26.42, "elapsed_time": "1:53:27", "remaining_time": "5:15:59", "throughput": 1488.87, "total_tokens": 10135360} {"current_steps": 48035, "total_steps": 181800, "loss": 0.0748, "lr": 4.6004070198514606e-05, "epoch": 5.284378437843785, "percentage": 26.42, "elapsed_time": "1:53:28", "remaining_time": "5:15:58", "throughput": 1488.89, "total_tokens": 10136480} {"current_steps": 48040, "total_steps": 181800, "loss": 0.0143, "lr": 4.600276846275446e-05, "epoch": 5.284928492849285, "percentage": 26.42, "elapsed_time": "1:53:28", "remaining_time": "5:15:58", "throughput": 1488.9, "total_tokens": 10137568} {"current_steps": 48045, "total_steps": 181800, "loss": 0.0449, "lr": 4.6001466533421875e-05, "epoch": 5.285478547854786, "percentage": 26.43, "elapsed_time": "1:53:29", "remaining_time": "5:15:57", "throughput": 1488.9, "total_tokens": 10138592} {"current_steps": 48050, "total_steps": 181800, "loss": 0.0778, "lr": 4.6000164410528845e-05, "epoch": 5.286028602860286, "percentage": 26.43, "elapsed_time": "1:53:30", "remaining_time": "5:15:56", "throughput": 1488.91, "total_tokens": 10139680} {"current_steps": 48055, "total_steps": 181800, "loss": 0.0263, "lr": 4.599886209408739e-05, "epoch": 5.286578657865786, "percentage": 26.43, "elapsed_time": "1:53:30", "remaining_time": "5:15:55", "throughput": 1488.91, "total_tokens": 10140736} {"current_steps": 48060, "total_steps": 181800, "loss": 0.0206, "lr": 4.599755958410949e-05, "epoch": 5.287128712871287, "percentage": 26.44, "elapsed_time": "1:53:31", "remaining_time": "5:15:54", "throughput": 1488.91, "total_tokens": 10141760} {"current_steps": 48065, "total_steps": 181800, "loss": 0.0657, "lr": 4.5996256880607156e-05, "epoch": 5.287678767876788, "percentage": 26.44, "elapsed_time": "1:53:32", "remaining_time": "5:15:54", "throughput": 1488.93, "total_tokens": 10142912} {"current_steps": 48070, "total_steps": 181800, "loss": 0.0315, "lr": 4.5994953983592406e-05, "epoch": 5.288228822882289, "percentage": 26.44, "elapsed_time": "1:53:32", "remaining_time": "5:15:53", "throughput": 1488.94, "total_tokens": 10144000} {"current_steps": 48075, "total_steps": 181800, "loss": 0.1362, "lr": 4.599365089307724e-05, "epoch": 5.288778877887789, "percentage": 26.44, "elapsed_time": "1:53:33", "remaining_time": "5:15:52", "throughput": 1488.95, "total_tokens": 10145088} {"current_steps": 48080, "total_steps": 181800, "loss": 0.0301, "lr": 4.599234760907366e-05, "epoch": 5.289328932893289, "percentage": 26.45, "elapsed_time": "1:53:34", "remaining_time": "5:15:51", "throughput": 1488.96, "total_tokens": 10146176} {"current_steps": 48085, "total_steps": 181800, "loss": 0.0406, "lr": 4.599104413159369e-05, "epoch": 5.28987898789879, "percentage": 26.45, "elapsed_time": "1:53:34", "remaining_time": "5:15:51", "throughput": 1488.96, "total_tokens": 10147264} {"current_steps": 48090, "total_steps": 181800, "loss": 0.0205, "lr": 4.598974046064934e-05, "epoch": 5.29042904290429, "percentage": 26.45, "elapsed_time": "1:53:35", "remaining_time": "5:15:50", "throughput": 1488.96, "total_tokens": 10148288} {"current_steps": 48095, "total_steps": 181800, "loss": 0.0287, "lr": 4.598843659625262e-05, "epoch": 5.290979097909791, "percentage": 26.45, "elapsed_time": "1:53:36", "remaining_time": "5:15:49", "throughput": 1488.97, "total_tokens": 10149376} {"current_steps": 48100, "total_steps": 181800, "loss": 0.0956, "lr": 4.598713253841556e-05, "epoch": 5.291529152915292, "percentage": 26.46, "elapsed_time": "1:53:37", "remaining_time": "5:15:48", "throughput": 1488.97, "total_tokens": 10150368} {"current_steps": 48105, "total_steps": 181800, "loss": 0.0172, "lr": 4.598582828715016e-05, "epoch": 5.292079207920792, "percentage": 26.46, "elapsed_time": "1:53:37", "remaining_time": "5:15:48", "throughput": 1488.98, "total_tokens": 10151424} {"current_steps": 48110, "total_steps": 181800, "loss": 0.0465, "lr": 4.598452384246845e-05, "epoch": 5.292629262926293, "percentage": 26.46, "elapsed_time": "1:53:38", "remaining_time": "5:15:47", "throughput": 1488.97, "total_tokens": 10152384} {"current_steps": 48115, "total_steps": 181800, "loss": 0.0492, "lr": 4.598321920438245e-05, "epoch": 5.293179317931793, "percentage": 26.47, "elapsed_time": "1:53:39", "remaining_time": "5:15:46", "throughput": 1488.97, "total_tokens": 10153408} {"current_steps": 48120, "total_steps": 181800, "loss": 0.0069, "lr": 4.59819143729042e-05, "epoch": 5.293729372937293, "percentage": 26.47, "elapsed_time": "1:53:39", "remaining_time": "5:15:45", "throughput": 1488.97, "total_tokens": 10154432} {"current_steps": 48125, "total_steps": 181800, "loss": 0.0146, "lr": 4.5980609348045705e-05, "epoch": 5.2942794279427945, "percentage": 26.47, "elapsed_time": "1:53:40", "remaining_time": "5:15:44", "throughput": 1488.97, "total_tokens": 10155456} {"current_steps": 48130, "total_steps": 181800, "loss": 0.052, "lr": 4.5979304129819e-05, "epoch": 5.294829482948295, "percentage": 26.47, "elapsed_time": "1:53:41", "remaining_time": "5:15:44", "throughput": 1488.97, "total_tokens": 10156512} {"current_steps": 48135, "total_steps": 181800, "loss": 0.0794, "lr": 4.5977998718236126e-05, "epoch": 5.295379537953796, "percentage": 26.48, "elapsed_time": "1:53:41", "remaining_time": "5:15:43", "throughput": 1488.99, "total_tokens": 10157664} {"current_steps": 48140, "total_steps": 181800, "loss": 0.0146, "lr": 4.59766931133091e-05, "epoch": 5.295929592959296, "percentage": 26.48, "elapsed_time": "1:53:42", "remaining_time": "5:15:42", "throughput": 1488.99, "total_tokens": 10158688} {"current_steps": 48145, "total_steps": 181800, "loss": 0.0105, "lr": 4.597538731504995e-05, "epoch": 5.296479647964796, "percentage": 26.48, "elapsed_time": "1:53:43", "remaining_time": "5:15:41", "throughput": 1488.99, "total_tokens": 10159712} {"current_steps": 48150, "total_steps": 181800, "loss": 0.1638, "lr": 4.597408132347073e-05, "epoch": 5.297029702970297, "percentage": 26.49, "elapsed_time": "1:53:43", "remaining_time": "5:15:41", "throughput": 1488.99, "total_tokens": 10160736} {"current_steps": 48155, "total_steps": 181800, "loss": 0.1015, "lr": 4.597277513858346e-05, "epoch": 5.2975797579757975, "percentage": 26.49, "elapsed_time": "1:53:44", "remaining_time": "5:15:40", "throughput": 1489.01, "total_tokens": 10161888} {"current_steps": 48160, "total_steps": 181800, "loss": 0.0204, "lr": 4.597146876040019e-05, "epoch": 5.298129812981298, "percentage": 26.49, "elapsed_time": "1:53:45", "remaining_time": "5:15:39", "throughput": 1489.02, "total_tokens": 10162976} {"current_steps": 48165, "total_steps": 181800, "loss": 0.1741, "lr": 4.5970162188932954e-05, "epoch": 5.298679867986799, "percentage": 26.49, "elapsed_time": "1:53:45", "remaining_time": "5:15:38", "throughput": 1489.02, "total_tokens": 10164032} {"current_steps": 48170, "total_steps": 181800, "loss": 0.0042, "lr": 4.596885542419379e-05, "epoch": 5.299229922992299, "percentage": 26.5, "elapsed_time": "1:53:46", "remaining_time": "5:15:38", "throughput": 1489.02, "total_tokens": 10165056} {"current_steps": 48175, "total_steps": 181800, "loss": 0.0598, "lr": 4.596754846619475e-05, "epoch": 5.2997799779978, "percentage": 26.5, "elapsed_time": "1:53:47", "remaining_time": "5:15:37", "throughput": 1489.03, "total_tokens": 10166144} {"current_steps": 48180, "total_steps": 181800, "loss": 0.0081, "lr": 4.596624131494789e-05, "epoch": 5.3003300330033, "percentage": 26.5, "elapsed_time": "1:53:48", "remaining_time": "5:15:36", "throughput": 1489.04, "total_tokens": 10167232} {"current_steps": 48185, "total_steps": 181800, "loss": 0.0588, "lr": 4.596493397046523e-05, "epoch": 5.3008800880088005, "percentage": 26.5, "elapsed_time": "1:53:48", "remaining_time": "5:15:35", "throughput": 1489.05, "total_tokens": 10168288} {"current_steps": 48190, "total_steps": 181800, "loss": 0.0753, "lr": 4.5963626432758836e-05, "epoch": 5.301430143014302, "percentage": 26.51, "elapsed_time": "1:53:49", "remaining_time": "5:15:35", "throughput": 1489.05, "total_tokens": 10169344} {"current_steps": 48195, "total_steps": 181800, "loss": 0.0058, "lr": 4.5962318701840754e-05, "epoch": 5.301980198019802, "percentage": 26.51, "elapsed_time": "1:53:50", "remaining_time": "5:15:34", "throughput": 1489.06, "total_tokens": 10170400} {"current_steps": 48200, "total_steps": 181800, "loss": 0.0402, "lr": 4.596101077772305e-05, "epoch": 5.302530253025303, "percentage": 26.51, "elapsed_time": "1:53:50", "remaining_time": "5:15:33", "throughput": 1489.06, "total_tokens": 10171424} {"current_steps": 48205, "total_steps": 181800, "loss": 0.0392, "lr": 4.595970266041776e-05, "epoch": 5.303080308030803, "percentage": 26.52, "elapsed_time": "1:53:51", "remaining_time": "5:15:32", "throughput": 1489.06, "total_tokens": 10172448} {"current_steps": 48210, "total_steps": 181800, "loss": 0.0169, "lr": 4.595839434993695e-05, "epoch": 5.303630363036303, "percentage": 26.52, "elapsed_time": "1:53:52", "remaining_time": "5:15:31", "throughput": 1489.06, "total_tokens": 10173504} {"current_steps": 48215, "total_steps": 181800, "loss": 0.0124, "lr": 4.5957085846292674e-05, "epoch": 5.304180418041804, "percentage": 26.52, "elapsed_time": "1:53:52", "remaining_time": "5:15:31", "throughput": 1489.07, "total_tokens": 10174592} {"current_steps": 48220, "total_steps": 181800, "loss": 0.0663, "lr": 4.5955777149496994e-05, "epoch": 5.304730473047305, "percentage": 26.52, "elapsed_time": "1:53:53", "remaining_time": "5:15:30", "throughput": 1489.07, "total_tokens": 10175648} {"current_steps": 48225, "total_steps": 181800, "loss": 0.051, "lr": 4.595446825956198e-05, "epoch": 5.305280528052805, "percentage": 26.53, "elapsed_time": "1:53:54", "remaining_time": "5:15:29", "throughput": 1489.08, "total_tokens": 10176736} {"current_steps": 48230, "total_steps": 181800, "loss": 0.0199, "lr": 4.595315917649967e-05, "epoch": 5.305830583058306, "percentage": 26.53, "elapsed_time": "1:53:54", "remaining_time": "5:15:28", "throughput": 1489.08, "total_tokens": 10177728} {"current_steps": 48235, "total_steps": 181800, "loss": 0.0597, "lr": 4.5951849900322165e-05, "epoch": 5.306380638063806, "percentage": 26.53, "elapsed_time": "1:53:55", "remaining_time": "5:15:28", "throughput": 1489.08, "total_tokens": 10178784} {"current_steps": 48240, "total_steps": 181800, "loss": 0.048, "lr": 4.59505404310415e-05, "epoch": 5.306930693069307, "percentage": 26.53, "elapsed_time": "1:53:56", "remaining_time": "5:15:27", "throughput": 1489.08, "total_tokens": 10179840} {"current_steps": 48245, "total_steps": 181800, "loss": 0.0039, "lr": 4.594923076866976e-05, "epoch": 5.307480748074807, "percentage": 26.54, "elapsed_time": "1:53:57", "remaining_time": "5:15:26", "throughput": 1489.09, "total_tokens": 10180928} {"current_steps": 48250, "total_steps": 181800, "loss": 0.0156, "lr": 4.594792091321901e-05, "epoch": 5.3080308030803085, "percentage": 26.54, "elapsed_time": "1:53:57", "remaining_time": "5:15:25", "throughput": 1489.1, "total_tokens": 10182016} {"current_steps": 48255, "total_steps": 181800, "loss": 0.0393, "lr": 4.5946610864701335e-05, "epoch": 5.308580858085809, "percentage": 26.54, "elapsed_time": "1:53:58", "remaining_time": "5:15:25", "throughput": 1489.1, "total_tokens": 10183072} {"current_steps": 48260, "total_steps": 181800, "loss": 0.0559, "lr": 4.594530062312879e-05, "epoch": 5.309130913091309, "percentage": 26.55, "elapsed_time": "1:53:59", "remaining_time": "5:15:24", "throughput": 1489.1, "total_tokens": 10184096} {"current_steps": 48265, "total_steps": 181800, "loss": 0.1302, "lr": 4.594399018851346e-05, "epoch": 5.30968096809681, "percentage": 26.55, "elapsed_time": "1:53:59", "remaining_time": "5:15:23", "throughput": 1489.11, "total_tokens": 10185152} {"current_steps": 48270, "total_steps": 181800, "loss": 0.1223, "lr": 4.5942679560867425e-05, "epoch": 5.31023102310231, "percentage": 26.55, "elapsed_time": "1:54:00", "remaining_time": "5:15:22", "throughput": 1489.11, "total_tokens": 10186208} {"current_steps": 48275, "total_steps": 181800, "loss": 0.0222, "lr": 4.594136874020276e-05, "epoch": 5.31078107810781, "percentage": 26.55, "elapsed_time": "1:54:01", "remaining_time": "5:15:22", "throughput": 1489.11, "total_tokens": 10187200} {"current_steps": 48280, "total_steps": 181800, "loss": 0.0955, "lr": 4.5940057726531546e-05, "epoch": 5.3113311331133115, "percentage": 26.56, "elapsed_time": "1:54:01", "remaining_time": "5:15:21", "throughput": 1489.11, "total_tokens": 10188256} {"current_steps": 48285, "total_steps": 181800, "loss": 0.007, "lr": 4.593874651986587e-05, "epoch": 5.311881188118812, "percentage": 26.56, "elapsed_time": "1:54:02", "remaining_time": "5:15:20", "throughput": 1489.12, "total_tokens": 10189312} {"current_steps": 48290, "total_steps": 181800, "loss": 0.1214, "lr": 4.593743512021782e-05, "epoch": 5.312431243124313, "percentage": 26.56, "elapsed_time": "1:54:03", "remaining_time": "5:15:19", "throughput": 1489.13, "total_tokens": 10190400} {"current_steps": 48295, "total_steps": 181800, "loss": 0.0168, "lr": 4.5936123527599474e-05, "epoch": 5.312981298129813, "percentage": 26.56, "elapsed_time": "1:54:03", "remaining_time": "5:15:19", "throughput": 1489.13, "total_tokens": 10191424} {"current_steps": 48300, "total_steps": 181800, "loss": 0.0265, "lr": 4.593481174202292e-05, "epoch": 5.313531353135313, "percentage": 26.57, "elapsed_time": "1:54:04", "remaining_time": "5:15:18", "throughput": 1489.13, "total_tokens": 10192512} {"current_steps": 48305, "total_steps": 181800, "loss": 0.0512, "lr": 4.593349976350025e-05, "epoch": 5.314081408140814, "percentage": 26.57, "elapsed_time": "1:54:05", "remaining_time": "5:15:17", "throughput": 1489.14, "total_tokens": 10193600} {"current_steps": 48310, "total_steps": 181800, "loss": 0.0328, "lr": 4.593218759204356e-05, "epoch": 5.3146314631463145, "percentage": 26.57, "elapsed_time": "1:54:05", "remaining_time": "5:15:16", "throughput": 1489.14, "total_tokens": 10194624} {"current_steps": 48315, "total_steps": 181800, "loss": 0.0902, "lr": 4.593087522766495e-05, "epoch": 5.315181518151816, "percentage": 26.58, "elapsed_time": "1:54:06", "remaining_time": "5:15:16", "throughput": 1489.14, "total_tokens": 10195616} {"current_steps": 48320, "total_steps": 181800, "loss": 0.0136, "lr": 4.59295626703765e-05, "epoch": 5.315731573157316, "percentage": 26.58, "elapsed_time": "1:54:07", "remaining_time": "5:15:15", "throughput": 1489.14, "total_tokens": 10196672} {"current_steps": 48325, "total_steps": 181800, "loss": 0.0417, "lr": 4.5928249920190315e-05, "epoch": 5.316281628162816, "percentage": 26.58, "elapsed_time": "1:54:08", "remaining_time": "5:15:14", "throughput": 1489.15, "total_tokens": 10197792} {"current_steps": 48330, "total_steps": 181800, "loss": 0.1, "lr": 4.5926936977118486e-05, "epoch": 5.316831683168317, "percentage": 26.58, "elapsed_time": "1:54:08", "remaining_time": "5:15:13", "throughput": 1489.15, "total_tokens": 10198784} {"current_steps": 48335, "total_steps": 181800, "loss": 0.1138, "lr": 4.592562384117313e-05, "epoch": 5.317381738173817, "percentage": 26.59, "elapsed_time": "1:54:09", "remaining_time": "5:15:12", "throughput": 1489.14, "total_tokens": 10199776} {"current_steps": 48340, "total_steps": 181800, "loss": 0.0516, "lr": 4.592431051236633e-05, "epoch": 5.3179317931793175, "percentage": 26.59, "elapsed_time": "1:54:10", "remaining_time": "5:15:12", "throughput": 1489.15, "total_tokens": 10200864} {"current_steps": 48345, "total_steps": 181800, "loss": 0.1036, "lr": 4.592299699071021e-05, "epoch": 5.318481848184819, "percentage": 26.59, "elapsed_time": "1:54:10", "remaining_time": "5:15:11", "throughput": 1489.14, "total_tokens": 10201824} {"current_steps": 48350, "total_steps": 181800, "loss": 0.1375, "lr": 4.592168327621686e-05, "epoch": 5.319031903190319, "percentage": 26.6, "elapsed_time": "1:54:11", "remaining_time": "5:15:10", "throughput": 1489.15, "total_tokens": 10202912} {"current_steps": 48355, "total_steps": 181800, "loss": 0.0097, "lr": 4.59203693688984e-05, "epoch": 5.31958195819582, "percentage": 26.6, "elapsed_time": "1:54:12", "remaining_time": "5:15:09", "throughput": 1489.16, "total_tokens": 10203968} {"current_steps": 48360, "total_steps": 181800, "loss": 0.026, "lr": 4.591905526876693e-05, "epoch": 5.32013201320132, "percentage": 26.6, "elapsed_time": "1:54:12", "remaining_time": "5:15:09", "throughput": 1489.16, "total_tokens": 10204992} {"current_steps": 48365, "total_steps": 181800, "loss": 0.0055, "lr": 4.5917740975834565e-05, "epoch": 5.32068206820682, "percentage": 26.6, "elapsed_time": "1:54:13", "remaining_time": "5:15:08", "throughput": 1489.16, "total_tokens": 10206016} {"current_steps": 48370, "total_steps": 181800, "loss": 0.068, "lr": 4.591642649011342e-05, "epoch": 5.321232123212321, "percentage": 26.61, "elapsed_time": "1:54:14", "remaining_time": "5:15:07", "throughput": 1489.17, "total_tokens": 10207104} {"current_steps": 48375, "total_steps": 181800, "loss": 0.044, "lr": 4.5915111811615607e-05, "epoch": 5.321782178217822, "percentage": 26.61, "elapsed_time": "1:54:14", "remaining_time": "5:15:06", "throughput": 1489.17, "total_tokens": 10208192} {"current_steps": 48380, "total_steps": 181800, "loss": 0.0356, "lr": 4.591379694035325e-05, "epoch": 5.322332233223323, "percentage": 26.61, "elapsed_time": "1:54:15", "remaining_time": "5:15:06", "throughput": 1489.17, "total_tokens": 10209216} {"current_steps": 48385, "total_steps": 181800, "loss": 0.0491, "lr": 4.591248187633845e-05, "epoch": 5.322882288228823, "percentage": 26.61, "elapsed_time": "1:54:16", "remaining_time": "5:15:05", "throughput": 1489.17, "total_tokens": 10210240} {"current_steps": 48390, "total_steps": 181800, "loss": 0.0697, "lr": 4.591116661958336e-05, "epoch": 5.323432343234323, "percentage": 26.62, "elapsed_time": "1:54:17", "remaining_time": "5:15:04", "throughput": 1489.17, "total_tokens": 10211232} {"current_steps": 48395, "total_steps": 181800, "loss": 0.0787, "lr": 4.5909851170100064e-05, "epoch": 5.323982398239824, "percentage": 26.62, "elapsed_time": "1:54:17", "remaining_time": "5:15:03", "throughput": 1489.17, "total_tokens": 10212288} {"current_steps": 48400, "total_steps": 181800, "loss": 0.0128, "lr": 4.5908535527900706e-05, "epoch": 5.324532453245324, "percentage": 26.62, "elapsed_time": "1:54:18", "remaining_time": "5:15:03", "throughput": 1489.19, "total_tokens": 10213408} {"current_steps": 48405, "total_steps": 181800, "loss": 0.0381, "lr": 4.5907219692997416e-05, "epoch": 5.325082508250825, "percentage": 26.63, "elapsed_time": "1:54:19", "remaining_time": "5:15:02", "throughput": 1489.19, "total_tokens": 10214464} {"current_steps": 48410, "total_steps": 181800, "loss": 0.0118, "lr": 4.590590366540231e-05, "epoch": 5.325632563256326, "percentage": 26.63, "elapsed_time": "1:54:19", "remaining_time": "5:15:01", "throughput": 1489.19, "total_tokens": 10215488} {"current_steps": 48415, "total_steps": 181800, "loss": 0.0166, "lr": 4.590458744512752e-05, "epoch": 5.326182618261826, "percentage": 26.63, "elapsed_time": "1:54:20", "remaining_time": "5:15:00", "throughput": 1489.19, "total_tokens": 10216544} {"current_steps": 48420, "total_steps": 181800, "loss": 0.0588, "lr": 4.590327103218518e-05, "epoch": 5.326732673267327, "percentage": 26.63, "elapsed_time": "1:54:21", "remaining_time": "5:15:00", "throughput": 1489.2, "total_tokens": 10217632} {"current_steps": 48425, "total_steps": 181800, "loss": 0.0195, "lr": 4.5901954426587425e-05, "epoch": 5.327282728272827, "percentage": 26.64, "elapsed_time": "1:54:21", "remaining_time": "5:14:59", "throughput": 1489.21, "total_tokens": 10218688} {"current_steps": 48430, "total_steps": 181800, "loss": 0.0677, "lr": 4.5900637628346374e-05, "epoch": 5.327832783278327, "percentage": 26.64, "elapsed_time": "1:54:22", "remaining_time": "5:14:58", "throughput": 1489.21, "total_tokens": 10219712} {"current_steps": 48435, "total_steps": 181800, "loss": 0.0548, "lr": 4.589932063747419e-05, "epoch": 5.3283828382838285, "percentage": 26.64, "elapsed_time": "1:54:23", "remaining_time": "5:14:57", "throughput": 1489.21, "total_tokens": 10220736} {"current_steps": 48440, "total_steps": 181800, "loss": 0.0159, "lr": 4.589800345398298e-05, "epoch": 5.328932893289329, "percentage": 26.64, "elapsed_time": "1:54:23", "remaining_time": "5:14:57", "throughput": 1489.21, "total_tokens": 10221792} {"current_steps": 48445, "total_steps": 181800, "loss": 0.0241, "lr": 4.589668607788492e-05, "epoch": 5.32948294829483, "percentage": 26.65, "elapsed_time": "1:54:24", "remaining_time": "5:14:56", "throughput": 1489.21, "total_tokens": 10222816} {"current_steps": 48450, "total_steps": 181800, "loss": 0.0142, "lr": 4.5895368509192115e-05, "epoch": 5.33003300330033, "percentage": 26.65, "elapsed_time": "1:54:25", "remaining_time": "5:14:55", "throughput": 1489.22, "total_tokens": 10223904} {"current_steps": 48455, "total_steps": 181800, "loss": 0.0492, "lr": 4.589405074791674e-05, "epoch": 5.33058305830583, "percentage": 26.65, "elapsed_time": "1:54:25", "remaining_time": "5:14:54", "throughput": 1489.22, "total_tokens": 10224992} {"current_steps": 48460, "total_steps": 181800, "loss": 0.0978, "lr": 4.5892732794070914e-05, "epoch": 5.331133113311331, "percentage": 26.66, "elapsed_time": "1:54:26", "remaining_time": "5:14:53", "throughput": 1489.23, "total_tokens": 10226080} {"current_steps": 48465, "total_steps": 181800, "loss": 0.007, "lr": 4.58914146476668e-05, "epoch": 5.3316831683168315, "percentage": 26.66, "elapsed_time": "1:54:27", "remaining_time": "5:14:53", "throughput": 1489.23, "total_tokens": 10227072} {"current_steps": 48470, "total_steps": 181800, "loss": 0.0104, "lr": 4.589009630871653e-05, "epoch": 5.332233223322333, "percentage": 26.66, "elapsed_time": "1:54:28", "remaining_time": "5:14:52", "throughput": 1489.23, "total_tokens": 10228128} {"current_steps": 48475, "total_steps": 181800, "loss": 0.0348, "lr": 4.5888777777232286e-05, "epoch": 5.332783278327833, "percentage": 26.66, "elapsed_time": "1:54:28", "remaining_time": "5:14:51", "throughput": 1489.25, "total_tokens": 10229248} {"current_steps": 48480, "total_steps": 181800, "loss": 0.1137, "lr": 4.588745905322619e-05, "epoch": 5.333333333333333, "percentage": 26.67, "elapsed_time": "1:54:29", "remaining_time": "5:14:50", "throughput": 1489.24, "total_tokens": 10230240} {"current_steps": 48485, "total_steps": 181800, "loss": 0.0158, "lr": 4.5886140136710396e-05, "epoch": 5.333883388338834, "percentage": 26.67, "elapsed_time": "1:54:30", "remaining_time": "5:14:50", "throughput": 1489.25, "total_tokens": 10231328} {"current_steps": 48490, "total_steps": 181800, "loss": 0.0128, "lr": 4.588482102769709e-05, "epoch": 5.334433443344334, "percentage": 26.67, "elapsed_time": "1:54:30", "remaining_time": "5:14:49", "throughput": 1489.25, "total_tokens": 10232384} {"current_steps": 48495, "total_steps": 181800, "loss": 0.0207, "lr": 4.5883501726198396e-05, "epoch": 5.334983498349835, "percentage": 26.67, "elapsed_time": "1:54:31", "remaining_time": "5:14:48", "throughput": 1489.25, "total_tokens": 10233376} {"current_steps": 48500, "total_steps": 181800, "loss": 0.1173, "lr": 4.588218223222649e-05, "epoch": 5.335533553355336, "percentage": 26.68, "elapsed_time": "1:54:32", "remaining_time": "5:14:47", "throughput": 1489.25, "total_tokens": 10234400} {"current_steps": 48505, "total_steps": 181800, "loss": 0.0106, "lr": 4.588086254579353e-05, "epoch": 5.336083608360836, "percentage": 26.68, "elapsed_time": "1:54:32", "remaining_time": "5:14:47", "throughput": 1489.25, "total_tokens": 10235424} {"current_steps": 48510, "total_steps": 181800, "loss": 0.1011, "lr": 4.587954266691169e-05, "epoch": 5.336633663366337, "percentage": 26.68, "elapsed_time": "1:54:33", "remaining_time": "5:14:46", "throughput": 1489.25, "total_tokens": 10236448} {"current_steps": 48515, "total_steps": 181800, "loss": 0.0119, "lr": 4.587822259559312e-05, "epoch": 5.337183718371837, "percentage": 26.69, "elapsed_time": "1:54:34", "remaining_time": "5:14:45", "throughput": 1489.25, "total_tokens": 10237472} {"current_steps": 48520, "total_steps": 181800, "loss": 0.11, "lr": 4.587690233184999e-05, "epoch": 5.337733773377337, "percentage": 26.69, "elapsed_time": "1:54:34", "remaining_time": "5:14:44", "throughput": 1489.25, "total_tokens": 10238496} {"current_steps": 48525, "total_steps": 181800, "loss": 0.209, "lr": 4.587558187569446e-05, "epoch": 5.338283828382838, "percentage": 26.69, "elapsed_time": "1:54:35", "remaining_time": "5:14:44", "throughput": 1489.25, "total_tokens": 10239552} {"current_steps": 48530, "total_steps": 181800, "loss": 0.0053, "lr": 4.587426122713872e-05, "epoch": 5.338833883388339, "percentage": 26.69, "elapsed_time": "1:54:36", "remaining_time": "5:14:43", "throughput": 1489.25, "total_tokens": 10240576} {"current_steps": 48535, "total_steps": 181800, "loss": 0.0204, "lr": 4.587294038619493e-05, "epoch": 5.33938393839384, "percentage": 26.7, "elapsed_time": "1:54:37", "remaining_time": "5:14:42", "throughput": 1489.26, "total_tokens": 10241632} {"current_steps": 48540, "total_steps": 181800, "loss": 0.0417, "lr": 4.5871619352875256e-05, "epoch": 5.33993399339934, "percentage": 26.7, "elapsed_time": "1:54:37", "remaining_time": "5:14:41", "throughput": 1489.25, "total_tokens": 10242592} {"current_steps": 48545, "total_steps": 181800, "loss": 0.0584, "lr": 4.587029812719189e-05, "epoch": 5.34048404840484, "percentage": 26.7, "elapsed_time": "1:54:38", "remaining_time": "5:14:41", "throughput": 1489.24, "total_tokens": 10243584} {"current_steps": 48550, "total_steps": 181800, "loss": 0.0684, "lr": 4.5868976709156995e-05, "epoch": 5.341034103410341, "percentage": 26.71, "elapsed_time": "1:54:39", "remaining_time": "5:14:40", "throughput": 1489.24, "total_tokens": 10244608} {"current_steps": 48555, "total_steps": 181800, "loss": 0.0276, "lr": 4.5867655098782756e-05, "epoch": 5.341584158415841, "percentage": 26.71, "elapsed_time": "1:54:39", "remaining_time": "5:14:39", "throughput": 1489.25, "total_tokens": 10245696} {"current_steps": 48560, "total_steps": 181800, "loss": 0.0603, "lr": 4.586633329608135e-05, "epoch": 5.3421342134213425, "percentage": 26.71, "elapsed_time": "1:54:40", "remaining_time": "5:14:38", "throughput": 1489.25, "total_tokens": 10246688} {"current_steps": 48565, "total_steps": 181800, "loss": 0.0677, "lr": 4.586501130106498e-05, "epoch": 5.342684268426843, "percentage": 26.71, "elapsed_time": "1:54:41", "remaining_time": "5:14:37", "throughput": 1489.25, "total_tokens": 10247744} {"current_steps": 48570, "total_steps": 181800, "loss": 0.0506, "lr": 4.5863689113745794e-05, "epoch": 5.343234323432343, "percentage": 26.72, "elapsed_time": "1:54:41", "remaining_time": "5:14:37", "throughput": 1489.26, "total_tokens": 10248800} {"current_steps": 48575, "total_steps": 181800, "loss": 0.0794, "lr": 4.5862366734136e-05, "epoch": 5.343784378437844, "percentage": 26.72, "elapsed_time": "1:54:42", "remaining_time": "5:14:36", "throughput": 1489.27, "total_tokens": 10249952} {"current_steps": 48580, "total_steps": 181800, "loss": 0.0869, "lr": 4.586104416224779e-05, "epoch": 5.344334433443344, "percentage": 26.72, "elapsed_time": "1:54:43", "remaining_time": "5:14:35", "throughput": 1489.28, "total_tokens": 10251040} {"current_steps": 48585, "total_steps": 181800, "loss": 0.0592, "lr": 4.5859721398093344e-05, "epoch": 5.3448844884488445, "percentage": 26.72, "elapsed_time": "1:54:43", "remaining_time": "5:14:34", "throughput": 1489.29, "total_tokens": 10252128} {"current_steps": 48590, "total_steps": 181800, "loss": 0.0371, "lr": 4.585839844168485e-05, "epoch": 5.3454345434543455, "percentage": 26.73, "elapsed_time": "1:54:44", "remaining_time": "5:14:34", "throughput": 1489.3, "total_tokens": 10253184} {"current_steps": 48595, "total_steps": 181800, "loss": 0.011, "lr": 4.5857075293034514e-05, "epoch": 5.345984598459846, "percentage": 26.73, "elapsed_time": "1:54:45", "remaining_time": "5:14:33", "throughput": 1489.3, "total_tokens": 10254240} {"current_steps": 48600, "total_steps": 181800, "loss": 0.0173, "lr": 4.5855751952154515e-05, "epoch": 5.346534653465347, "percentage": 26.73, "elapsed_time": "1:54:45", "remaining_time": "5:14:32", "throughput": 1489.31, "total_tokens": 10255360} {"current_steps": 48605, "total_steps": 181800, "loss": 0.0295, "lr": 4.585442841905706e-05, "epoch": 5.347084708470847, "percentage": 26.74, "elapsed_time": "1:54:46", "remaining_time": "5:14:31", "throughput": 1489.32, "total_tokens": 10256448} {"current_steps": 48610, "total_steps": 181800, "loss": 0.0236, "lr": 4.585310469375435e-05, "epoch": 5.347634763476347, "percentage": 26.74, "elapsed_time": "1:54:47", "remaining_time": "5:14:31", "throughput": 1489.33, "total_tokens": 10257504} {"current_steps": 48615, "total_steps": 181800, "loss": 0.0769, "lr": 4.585178077625858e-05, "epoch": 5.348184818481848, "percentage": 26.74, "elapsed_time": "1:54:48", "remaining_time": "5:14:30", "throughput": 1489.32, "total_tokens": 10258528} {"current_steps": 48620, "total_steps": 181800, "loss": 0.0946, "lr": 4.585045666658194e-05, "epoch": 5.3487348734873486, "percentage": 26.74, "elapsed_time": "1:54:48", "remaining_time": "5:14:29", "throughput": 1489.32, "total_tokens": 10259552} {"current_steps": 48625, "total_steps": 181800, "loss": 0.0948, "lr": 4.584913236473666e-05, "epoch": 5.34928492849285, "percentage": 26.75, "elapsed_time": "1:54:49", "remaining_time": "5:14:28", "throughput": 1489.32, "total_tokens": 10260544} {"current_steps": 48630, "total_steps": 181800, "loss": 0.0556, "lr": 4.5847807870734926e-05, "epoch": 5.34983498349835, "percentage": 26.75, "elapsed_time": "1:54:50", "remaining_time": "5:14:28", "throughput": 1489.32, "total_tokens": 10261568} {"current_steps": 48635, "total_steps": 181800, "loss": 0.0148, "lr": 4.584648318458895e-05, "epoch": 5.35038503850385, "percentage": 26.75, "elapsed_time": "1:54:50", "remaining_time": "5:14:27", "throughput": 1489.31, "total_tokens": 10262560} {"current_steps": 48640, "total_steps": 181800, "loss": 0.0791, "lr": 4.5845158306310944e-05, "epoch": 5.350935093509351, "percentage": 26.75, "elapsed_time": "1:54:51", "remaining_time": "5:14:26", "throughput": 1489.31, "total_tokens": 10263584} {"current_steps": 48645, "total_steps": 181800, "loss": 0.1058, "lr": 4.5843833235913116e-05, "epoch": 5.351485148514851, "percentage": 26.76, "elapsed_time": "1:54:52", "remaining_time": "5:14:25", "throughput": 1489.33, "total_tokens": 10264704} {"current_steps": 48650, "total_steps": 181800, "loss": 0.0105, "lr": 4.584250797340768e-05, "epoch": 5.3520352035203524, "percentage": 26.76, "elapsed_time": "1:54:52", "remaining_time": "5:14:25", "throughput": 1489.33, "total_tokens": 10265728} {"current_steps": 48655, "total_steps": 181800, "loss": 0.0147, "lr": 4.584118251880685e-05, "epoch": 5.352585258525853, "percentage": 26.76, "elapsed_time": "1:54:53", "remaining_time": "5:14:24", "throughput": 1489.34, "total_tokens": 10266816} {"current_steps": 48660, "total_steps": 181800, "loss": 0.0269, "lr": 4.583985687212283e-05, "epoch": 5.353135313531353, "percentage": 26.77, "elapsed_time": "1:54:54", "remaining_time": "5:14:23", "throughput": 1489.33, "total_tokens": 10267808} {"current_steps": 48665, "total_steps": 181800, "loss": 0.0094, "lr": 4.5838531033367856e-05, "epoch": 5.353685368536854, "percentage": 26.77, "elapsed_time": "1:54:54", "remaining_time": "5:14:22", "throughput": 1489.33, "total_tokens": 10268832} {"current_steps": 48670, "total_steps": 181800, "loss": 0.0434, "lr": 4.583720500255415e-05, "epoch": 5.354235423542354, "percentage": 26.77, "elapsed_time": "1:54:55", "remaining_time": "5:14:22", "throughput": 1489.33, "total_tokens": 10269856} {"current_steps": 48675, "total_steps": 181800, "loss": 0.0152, "lr": 4.583587877969392e-05, "epoch": 5.354785478547855, "percentage": 26.77, "elapsed_time": "1:54:56", "remaining_time": "5:14:21", "throughput": 1489.34, "total_tokens": 10270976} {"current_steps": 48680, "total_steps": 181800, "loss": 0.1027, "lr": 4.583455236479939e-05, "epoch": 5.3553355335533555, "percentage": 26.78, "elapsed_time": "1:54:56", "remaining_time": "5:14:20", "throughput": 1489.34, "total_tokens": 10272000} {"current_steps": 48685, "total_steps": 181800, "loss": 0.0821, "lr": 4.5833225757882786e-05, "epoch": 5.355885588558856, "percentage": 26.78, "elapsed_time": "1:54:57", "remaining_time": "5:14:19", "throughput": 1489.34, "total_tokens": 10272992} {"current_steps": 48690, "total_steps": 181800, "loss": 0.164, "lr": 4.5831898958956335e-05, "epoch": 5.356435643564357, "percentage": 26.78, "elapsed_time": "1:54:58", "remaining_time": "5:14:18", "throughput": 1489.34, "total_tokens": 10273984} {"current_steps": 48695, "total_steps": 181800, "loss": 0.0429, "lr": 4.5830571968032277e-05, "epoch": 5.356985698569857, "percentage": 26.78, "elapsed_time": "1:54:59", "remaining_time": "5:14:18", "throughput": 1489.34, "total_tokens": 10275040} {"current_steps": 48700, "total_steps": 181800, "loss": 0.0252, "lr": 4.5829244785122827e-05, "epoch": 5.357535753575357, "percentage": 26.79, "elapsed_time": "1:54:59", "remaining_time": "5:14:17", "throughput": 1489.35, "total_tokens": 10276096} {"current_steps": 48705, "total_steps": 181800, "loss": 0.1976, "lr": 4.582791741024022e-05, "epoch": 5.358085808580858, "percentage": 26.79, "elapsed_time": "1:55:00", "remaining_time": "5:14:16", "throughput": 1489.36, "total_tokens": 10277216} {"current_steps": 48710, "total_steps": 181800, "loss": 0.0509, "lr": 4.582658984339669e-05, "epoch": 5.3586358635863585, "percentage": 26.79, "elapsed_time": "1:55:01", "remaining_time": "5:14:15", "throughput": 1489.37, "total_tokens": 10278304} {"current_steps": 48715, "total_steps": 181800, "loss": 0.0432, "lr": 4.582526208460449e-05, "epoch": 5.3591859185918596, "percentage": 26.8, "elapsed_time": "1:55:01", "remaining_time": "5:14:15", "throughput": 1489.38, "total_tokens": 10279392} {"current_steps": 48720, "total_steps": 181800, "loss": 0.0435, "lr": 4.5823934133875834e-05, "epoch": 5.35973597359736, "percentage": 26.8, "elapsed_time": "1:55:02", "remaining_time": "5:14:14", "throughput": 1489.39, "total_tokens": 10280512} {"current_steps": 48725, "total_steps": 181800, "loss": 0.0187, "lr": 4.5822605991222964e-05, "epoch": 5.36028602860286, "percentage": 26.8, "elapsed_time": "1:55:03", "remaining_time": "5:14:13", "throughput": 1489.39, "total_tokens": 10281536} {"current_steps": 48730, "total_steps": 181800, "loss": 0.116, "lr": 4.582127765665813e-05, "epoch": 5.360836083608361, "percentage": 26.8, "elapsed_time": "1:55:03", "remaining_time": "5:14:12", "throughput": 1489.4, "total_tokens": 10282656} {"current_steps": 48735, "total_steps": 181800, "loss": 0.0601, "lr": 4.581994913019357e-05, "epoch": 5.361386138613861, "percentage": 26.81, "elapsed_time": "1:55:04", "remaining_time": "5:14:12", "throughput": 1489.41, "total_tokens": 10283744} {"current_steps": 48740, "total_steps": 181800, "loss": 0.0122, "lr": 4.581862041184154e-05, "epoch": 5.361936193619362, "percentage": 26.81, "elapsed_time": "1:55:05", "remaining_time": "5:14:11", "throughput": 1489.42, "total_tokens": 10284832} {"current_steps": 48745, "total_steps": 181800, "loss": 0.008, "lr": 4.5817291501614254e-05, "epoch": 5.362486248624863, "percentage": 26.81, "elapsed_time": "1:55:05", "remaining_time": "5:14:10", "throughput": 1489.43, "total_tokens": 10285920} {"current_steps": 48750, "total_steps": 181800, "loss": 0.0386, "lr": 4.5815962399524e-05, "epoch": 5.363036303630363, "percentage": 26.82, "elapsed_time": "1:55:06", "remaining_time": "5:14:09", "throughput": 1489.43, "total_tokens": 10286944} {"current_steps": 48755, "total_steps": 181800, "loss": 0.0101, "lr": 4.5814633105583e-05, "epoch": 5.363586358635864, "percentage": 26.82, "elapsed_time": "1:55:07", "remaining_time": "5:14:08", "throughput": 1489.43, "total_tokens": 10287968} {"current_steps": 48760, "total_steps": 181800, "loss": 0.2083, "lr": 4.581330361980352e-05, "epoch": 5.364136413641364, "percentage": 26.82, "elapsed_time": "1:55:07", "remaining_time": "5:14:08", "throughput": 1489.43, "total_tokens": 10288992} {"current_steps": 48765, "total_steps": 181800, "loss": 0.077, "lr": 4.58119739421978e-05, "epoch": 5.364686468646864, "percentage": 26.82, "elapsed_time": "1:55:08", "remaining_time": "5:14:07", "throughput": 1489.44, "total_tokens": 10290048} {"current_steps": 48770, "total_steps": 181800, "loss": 0.0295, "lr": 4.5810644072778106e-05, "epoch": 5.365236523652365, "percentage": 26.83, "elapsed_time": "1:55:09", "remaining_time": "5:14:06", "throughput": 1489.45, "total_tokens": 10291136} {"current_steps": 48775, "total_steps": 181800, "loss": 0.0255, "lr": 4.5809314011556694e-05, "epoch": 5.365786578657866, "percentage": 26.83, "elapsed_time": "1:55:10", "remaining_time": "5:14:05", "throughput": 1489.45, "total_tokens": 10292192} {"current_steps": 48780, "total_steps": 181800, "loss": 0.0432, "lr": 4.580798375854582e-05, "epoch": 5.366336633663367, "percentage": 26.83, "elapsed_time": "1:55:10", "remaining_time": "5:14:05", "throughput": 1489.45, "total_tokens": 10293248} {"current_steps": 48785, "total_steps": 181800, "loss": 0.09, "lr": 4.580665331375774e-05, "epoch": 5.366886688668867, "percentage": 26.83, "elapsed_time": "1:55:11", "remaining_time": "5:14:04", "throughput": 1489.45, "total_tokens": 10294272} {"current_steps": 48790, "total_steps": 181800, "loss": 0.0322, "lr": 4.5805322677204725e-05, "epoch": 5.367436743674367, "percentage": 26.84, "elapsed_time": "1:55:12", "remaining_time": "5:14:03", "throughput": 1489.45, "total_tokens": 10295296} {"current_steps": 48795, "total_steps": 181800, "loss": 0.0996, "lr": 4.580399184889903e-05, "epoch": 5.367986798679868, "percentage": 26.84, "elapsed_time": "1:55:12", "remaining_time": "5:14:02", "throughput": 1489.47, "total_tokens": 10296416} {"current_steps": 48800, "total_steps": 181800, "loss": 0.1257, "lr": 4.580266082885293e-05, "epoch": 5.368536853685368, "percentage": 26.84, "elapsed_time": "1:55:13", "remaining_time": "5:14:02", "throughput": 1489.48, "total_tokens": 10297504} {"current_steps": 48805, "total_steps": 181800, "loss": 0.0226, "lr": 4.5801329617078685e-05, "epoch": 5.3690869086908695, "percentage": 26.85, "elapsed_time": "1:55:14", "remaining_time": "5:14:01", "throughput": 1489.48, "total_tokens": 10298560} {"current_steps": 48810, "total_steps": 181800, "loss": 0.0282, "lr": 4.579999821358857e-05, "epoch": 5.36963696369637, "percentage": 26.85, "elapsed_time": "1:55:14", "remaining_time": "5:14:00", "throughput": 1489.49, "total_tokens": 10299616} {"current_steps": 48815, "total_steps": 181800, "loss": 0.0543, "lr": 4.579866661839485e-05, "epoch": 5.37018701870187, "percentage": 26.85, "elapsed_time": "1:55:15", "remaining_time": "5:13:59", "throughput": 1489.49, "total_tokens": 10300672} {"current_steps": 48820, "total_steps": 181800, "loss": 0.0755, "lr": 4.57973348315098e-05, "epoch": 5.370737073707371, "percentage": 26.85, "elapsed_time": "1:55:16", "remaining_time": "5:13:59", "throughput": 1489.51, "total_tokens": 10301824} {"current_steps": 48825, "total_steps": 181800, "loss": 0.0204, "lr": 4.579600285294568e-05, "epoch": 5.371287128712871, "percentage": 26.86, "elapsed_time": "1:55:16", "remaining_time": "5:13:58", "throughput": 1489.51, "total_tokens": 10302848} {"current_steps": 48830, "total_steps": 181800, "loss": 0.0588, "lr": 4.5794670682714805e-05, "epoch": 5.371837183718371, "percentage": 26.86, "elapsed_time": "1:55:17", "remaining_time": "5:13:57", "throughput": 1489.5, "total_tokens": 10303840} {"current_steps": 48835, "total_steps": 181800, "loss": 0.0072, "lr": 4.5793338320829414e-05, "epoch": 5.3723872387238725, "percentage": 26.86, "elapsed_time": "1:55:18", "remaining_time": "5:13:56", "throughput": 1489.5, "total_tokens": 10304832} {"current_steps": 48840, "total_steps": 181800, "loss": 0.0364, "lr": 4.57920057673018e-05, "epoch": 5.372937293729373, "percentage": 26.86, "elapsed_time": "1:55:19", "remaining_time": "5:13:56", "throughput": 1489.49, "total_tokens": 10305824} {"current_steps": 48845, "total_steps": 181800, "loss": 0.0418, "lr": 4.5790673022144255e-05, "epoch": 5.373487348734874, "percentage": 26.87, "elapsed_time": "1:55:19", "remaining_time": "5:13:55", "throughput": 1489.49, "total_tokens": 10306816} {"current_steps": 48850, "total_steps": 181800, "loss": 0.0629, "lr": 4.578934008536905e-05, "epoch": 5.374037403740374, "percentage": 26.87, "elapsed_time": "1:55:20", "remaining_time": "5:13:54", "throughput": 1489.49, "total_tokens": 10307872} {"current_steps": 48855, "total_steps": 181800, "loss": 0.1346, "lr": 4.578800695698847e-05, "epoch": 5.374587458745874, "percentage": 26.87, "elapsed_time": "1:55:21", "remaining_time": "5:13:53", "throughput": 1489.48, "total_tokens": 10308832} {"current_steps": 48860, "total_steps": 181800, "loss": 0.0569, "lr": 4.578667363701481e-05, "epoch": 5.375137513751375, "percentage": 26.88, "elapsed_time": "1:55:21", "remaining_time": "5:13:53", "throughput": 1489.49, "total_tokens": 10309888} {"current_steps": 48865, "total_steps": 181800, "loss": 0.0209, "lr": 4.578534012546034e-05, "epoch": 5.3756875687568755, "percentage": 26.88, "elapsed_time": "1:55:22", "remaining_time": "5:13:52", "throughput": 1489.5, "total_tokens": 10311008} {"current_steps": 48870, "total_steps": 181800, "loss": 0.0073, "lr": 4.578400642233738e-05, "epoch": 5.376237623762377, "percentage": 26.88, "elapsed_time": "1:55:23", "remaining_time": "5:13:51", "throughput": 1489.51, "total_tokens": 10312096} {"current_steps": 48875, "total_steps": 181800, "loss": 0.0209, "lr": 4.57826725276582e-05, "epoch": 5.376787678767877, "percentage": 26.88, "elapsed_time": "1:55:23", "remaining_time": "5:13:50", "throughput": 1489.51, "total_tokens": 10313120} {"current_steps": 48880, "total_steps": 181800, "loss": 0.0794, "lr": 4.5781338441435095e-05, "epoch": 5.377337733773377, "percentage": 26.89, "elapsed_time": "1:55:24", "remaining_time": "5:13:49", "throughput": 1489.51, "total_tokens": 10314144} {"current_steps": 48885, "total_steps": 181800, "loss": 0.0026, "lr": 4.5780004163680365e-05, "epoch": 5.377887788778878, "percentage": 26.89, "elapsed_time": "1:55:25", "remaining_time": "5:13:49", "throughput": 1489.51, "total_tokens": 10315200} {"current_steps": 48890, "total_steps": 181800, "loss": 0.1138, "lr": 4.5778669694406315e-05, "epoch": 5.378437843784378, "percentage": 26.89, "elapsed_time": "1:55:25", "remaining_time": "5:13:48", "throughput": 1489.51, "total_tokens": 10316192} {"current_steps": 48895, "total_steps": 181800, "loss": 0.1083, "lr": 4.577733503362524e-05, "epoch": 5.378987898789879, "percentage": 26.89, "elapsed_time": "1:55:26", "remaining_time": "5:13:47", "throughput": 1489.51, "total_tokens": 10317216} {"current_steps": 48900, "total_steps": 181800, "loss": 0.0496, "lr": 4.577600018134943e-05, "epoch": 5.37953795379538, "percentage": 26.9, "elapsed_time": "1:55:27", "remaining_time": "5:13:46", "throughput": 1489.51, "total_tokens": 10318272} {"current_steps": 48905, "total_steps": 181800, "loss": 0.0752, "lr": 4.57746651375912e-05, "epoch": 5.38008800880088, "percentage": 26.9, "elapsed_time": "1:55:27", "remaining_time": "5:13:46", "throughput": 1489.52, "total_tokens": 10319328} {"current_steps": 48910, "total_steps": 181800, "loss": 0.0332, "lr": 4.577332990236285e-05, "epoch": 5.380638063806381, "percentage": 26.9, "elapsed_time": "1:55:28", "remaining_time": "5:13:45", "throughput": 1489.52, "total_tokens": 10320384} {"current_steps": 48915, "total_steps": 181800, "loss": 0.0279, "lr": 4.577199447567668e-05, "epoch": 5.381188118811881, "percentage": 26.91, "elapsed_time": "1:55:29", "remaining_time": "5:13:44", "throughput": 1489.53, "total_tokens": 10321472} {"current_steps": 48920, "total_steps": 181800, "loss": 0.0046, "lr": 4.577065885754501e-05, "epoch": 5.381738173817382, "percentage": 26.91, "elapsed_time": "1:55:30", "remaining_time": "5:13:43", "throughput": 1489.53, "total_tokens": 10322528} {"current_steps": 48925, "total_steps": 181800, "loss": 0.015, "lr": 4.5769323047980146e-05, "epoch": 5.382288228822882, "percentage": 26.91, "elapsed_time": "1:55:30", "remaining_time": "5:13:43", "throughput": 1489.54, "total_tokens": 10323584} {"current_steps": 48930, "total_steps": 181800, "loss": 0.0531, "lr": 4.5767987046994395e-05, "epoch": 5.382838283828383, "percentage": 26.91, "elapsed_time": "1:55:31", "remaining_time": "5:13:42", "throughput": 1489.54, "total_tokens": 10324640} {"current_steps": 48935, "total_steps": 181800, "loss": 0.0537, "lr": 4.576665085460007e-05, "epoch": 5.383388338833884, "percentage": 26.92, "elapsed_time": "1:55:32", "remaining_time": "5:13:41", "throughput": 1489.55, "total_tokens": 10325728} {"current_steps": 48940, "total_steps": 181800, "loss": 0.0738, "lr": 4.576531447080949e-05, "epoch": 5.383938393839384, "percentage": 26.92, "elapsed_time": "1:55:32", "remaining_time": "5:13:40", "throughput": 1489.56, "total_tokens": 10326816} {"current_steps": 48945, "total_steps": 181800, "loss": 0.0187, "lr": 4.576397789563497e-05, "epoch": 5.384488448844884, "percentage": 26.92, "elapsed_time": "1:55:33", "remaining_time": "5:13:40", "throughput": 1489.56, "total_tokens": 10327840} {"current_steps": 48950, "total_steps": 181800, "loss": 0.0645, "lr": 4.576264112908884e-05, "epoch": 5.385038503850385, "percentage": 26.93, "elapsed_time": "1:55:34", "remaining_time": "5:13:39", "throughput": 1489.57, "total_tokens": 10328960} {"current_steps": 48955, "total_steps": 181800, "loss": 0.0158, "lr": 4.5761304171183396e-05, "epoch": 5.385588558855885, "percentage": 26.93, "elapsed_time": "1:55:34", "remaining_time": "5:13:38", "throughput": 1489.57, "total_tokens": 10330016} {"current_steps": 48960, "total_steps": 181800, "loss": 0.0271, "lr": 4.5759967021930976e-05, "epoch": 5.3861386138613865, "percentage": 26.93, "elapsed_time": "1:55:35", "remaining_time": "5:13:37", "throughput": 1489.57, "total_tokens": 10331040} {"current_steps": 48965, "total_steps": 181800, "loss": 0.0278, "lr": 4.575862968134391e-05, "epoch": 5.386688668866887, "percentage": 26.93, "elapsed_time": "1:55:36", "remaining_time": "5:13:37", "throughput": 1489.57, "total_tokens": 10332032} {"current_steps": 48970, "total_steps": 181800, "loss": 0.0489, "lr": 4.57572921494345e-05, "epoch": 5.387238723872387, "percentage": 26.94, "elapsed_time": "1:55:36", "remaining_time": "5:13:36", "throughput": 1489.58, "total_tokens": 10333120} {"current_steps": 48975, "total_steps": 181800, "loss": 0.0809, "lr": 4.57559544262151e-05, "epoch": 5.387788778877888, "percentage": 26.94, "elapsed_time": "1:55:37", "remaining_time": "5:13:35", "throughput": 1489.58, "total_tokens": 10334144} {"current_steps": 48980, "total_steps": 181800, "loss": 0.0229, "lr": 4.5754616511698026e-05, "epoch": 5.388338833883388, "percentage": 26.94, "elapsed_time": "1:55:38", "remaining_time": "5:13:34", "throughput": 1489.58, "total_tokens": 10335168} {"current_steps": 48985, "total_steps": 181800, "loss": 0.084, "lr": 4.5753278405895614e-05, "epoch": 5.388888888888889, "percentage": 26.94, "elapsed_time": "1:55:39", "remaining_time": "5:13:34", "throughput": 1489.59, "total_tokens": 10336256} {"current_steps": 48990, "total_steps": 181800, "loss": 0.0058, "lr": 4.575194010882019e-05, "epoch": 5.3894389438943895, "percentage": 26.95, "elapsed_time": "1:55:39", "remaining_time": "5:13:33", "throughput": 1489.6, "total_tokens": 10337376} {"current_steps": 48995, "total_steps": 181800, "loss": 0.0544, "lr": 4.575060162048409e-05, "epoch": 5.38998899889989, "percentage": 26.95, "elapsed_time": "1:55:40", "remaining_time": "5:13:32", "throughput": 1489.61, "total_tokens": 10338464} {"current_steps": 49000, "total_steps": 181800, "loss": 0.1435, "lr": 4.574926294089965e-05, "epoch": 5.390539053905391, "percentage": 26.95, "elapsed_time": "1:55:41", "remaining_time": "5:13:31", "throughput": 1489.62, "total_tokens": 10339552} {"current_steps": 49005, "total_steps": 181800, "loss": 0.0354, "lr": 4.574792407007922e-05, "epoch": 5.391089108910891, "percentage": 26.96, "elapsed_time": "1:55:41", "remaining_time": "5:13:30", "throughput": 1489.62, "total_tokens": 10340608} {"current_steps": 49010, "total_steps": 181800, "loss": 0.0615, "lr": 4.5746585008035116e-05, "epoch": 5.391639163916391, "percentage": 26.96, "elapsed_time": "1:55:42", "remaining_time": "5:13:30", "throughput": 1489.63, "total_tokens": 10341664} {"current_steps": 49015, "total_steps": 181800, "loss": 0.0622, "lr": 4.5745245754779696e-05, "epoch": 5.392189218921892, "percentage": 26.96, "elapsed_time": "1:55:43", "remaining_time": "5:13:29", "throughput": 1489.64, "total_tokens": 10342752} {"current_steps": 49020, "total_steps": 181800, "loss": 0.0117, "lr": 4.574390631032531e-05, "epoch": 5.3927392739273925, "percentage": 26.96, "elapsed_time": "1:55:43", "remaining_time": "5:13:28", "throughput": 1489.64, "total_tokens": 10343776} {"current_steps": 49025, "total_steps": 181800, "loss": 0.0744, "lr": 4.5742566674684286e-05, "epoch": 5.393289328932894, "percentage": 26.97, "elapsed_time": "1:55:44", "remaining_time": "5:13:27", "throughput": 1489.65, "total_tokens": 10344896} {"current_steps": 49030, "total_steps": 181800, "loss": 0.0861, "lr": 4.574122684786898e-05, "epoch": 5.393839383938394, "percentage": 26.97, "elapsed_time": "1:55:45", "remaining_time": "5:13:27", "throughput": 1489.65, "total_tokens": 10345920} {"current_steps": 49035, "total_steps": 181800, "loss": 0.0377, "lr": 4.5739886829891745e-05, "epoch": 5.394389438943894, "percentage": 26.97, "elapsed_time": "1:55:45", "remaining_time": "5:13:26", "throughput": 1489.64, "total_tokens": 10346912} {"current_steps": 49040, "total_steps": 181800, "loss": 0.0099, "lr": 4.573854662076491e-05, "epoch": 5.394939493949395, "percentage": 26.97, "elapsed_time": "1:55:46", "remaining_time": "5:13:25", "throughput": 1489.64, "total_tokens": 10347904} {"current_steps": 49045, "total_steps": 181800, "loss": 0.059, "lr": 4.573720622050085e-05, "epoch": 5.395489548954895, "percentage": 26.98, "elapsed_time": "1:55:47", "remaining_time": "5:13:24", "throughput": 1489.65, "total_tokens": 10348992} {"current_steps": 49050, "total_steps": 181800, "loss": 0.0497, "lr": 4.573586562911192e-05, "epoch": 5.396039603960396, "percentage": 26.98, "elapsed_time": "1:55:47", "remaining_time": "5:13:24", "throughput": 1489.65, "total_tokens": 10350016} {"current_steps": 49055, "total_steps": 181800, "loss": 0.0204, "lr": 4.5734524846610454e-05, "epoch": 5.396589658965897, "percentage": 26.98, "elapsed_time": "1:55:48", "remaining_time": "5:13:23", "throughput": 1489.65, "total_tokens": 10351072} {"current_steps": 49060, "total_steps": 181800, "loss": 0.0241, "lr": 4.573318387300883e-05, "epoch": 5.397139713971397, "percentage": 26.99, "elapsed_time": "1:55:49", "remaining_time": "5:13:22", "throughput": 1489.65, "total_tokens": 10352096} {"current_steps": 49065, "total_steps": 181800, "loss": 0.0182, "lr": 4.573184270831939e-05, "epoch": 5.397689768976898, "percentage": 26.99, "elapsed_time": "1:55:50", "remaining_time": "5:13:21", "throughput": 1489.65, "total_tokens": 10353152} {"current_steps": 49070, "total_steps": 181800, "loss": 0.0182, "lr": 4.5730501352554515e-05, "epoch": 5.398239823982398, "percentage": 26.99, "elapsed_time": "1:55:50", "remaining_time": "5:13:21", "throughput": 1489.67, "total_tokens": 10354272} {"current_steps": 49075, "total_steps": 181800, "loss": 0.028, "lr": 4.572915980572655e-05, "epoch": 5.398789878987899, "percentage": 26.99, "elapsed_time": "1:55:51", "remaining_time": "5:13:20", "throughput": 1489.67, "total_tokens": 10355296} {"current_steps": 49080, "total_steps": 181800, "loss": 0.0582, "lr": 4.572781806784786e-05, "epoch": 5.399339933993399, "percentage": 27.0, "elapsed_time": "1:55:52", "remaining_time": "5:13:19", "throughput": 1489.66, "total_tokens": 10356288} {"current_steps": 49085, "total_steps": 181800, "loss": 0.022, "lr": 4.572647613893083e-05, "epoch": 5.3998899889989, "percentage": 27.0, "elapsed_time": "1:55:52", "remaining_time": "5:13:18", "throughput": 1489.67, "total_tokens": 10357344} {"current_steps": 49090, "total_steps": 181800, "loss": 0.013, "lr": 4.57251340189878e-05, "epoch": 5.400440044004401, "percentage": 27.0, "elapsed_time": "1:55:53", "remaining_time": "5:13:18", "throughput": 1489.66, "total_tokens": 10358336} {"current_steps": 49095, "total_steps": 181800, "loss": 0.0176, "lr": 4.5723791708031174e-05, "epoch": 5.400990099009901, "percentage": 27.0, "elapsed_time": "1:55:54", "remaining_time": "5:13:17", "throughput": 1489.66, "total_tokens": 10359328} {"current_steps": 49100, "total_steps": 181800, "loss": 0.0486, "lr": 4.572244920607329e-05, "epoch": 5.401540154015402, "percentage": 27.01, "elapsed_time": "1:55:54", "remaining_time": "5:13:16", "throughput": 1489.66, "total_tokens": 10360352} {"current_steps": 49105, "total_steps": 181800, "loss": 0.0335, "lr": 4.572110651312654e-05, "epoch": 5.402090209020902, "percentage": 27.01, "elapsed_time": "1:55:55", "remaining_time": "5:13:15", "throughput": 1489.65, "total_tokens": 10361344} {"current_steps": 49110, "total_steps": 181800, "loss": 0.0223, "lr": 4.5719763629203295e-05, "epoch": 5.402640264026402, "percentage": 27.01, "elapsed_time": "1:55:56", "remaining_time": "5:13:14", "throughput": 1489.65, "total_tokens": 10362368} {"current_steps": 49115, "total_steps": 181800, "loss": 0.1142, "lr": 4.571842055431592e-05, "epoch": 5.4031903190319035, "percentage": 27.02, "elapsed_time": "1:55:56", "remaining_time": "5:13:14", "throughput": 1489.66, "total_tokens": 10363424} {"current_steps": 49120, "total_steps": 181800, "loss": 0.1286, "lr": 4.5717077288476816e-05, "epoch": 5.403740374037404, "percentage": 27.02, "elapsed_time": "1:55:57", "remaining_time": "5:13:13", "throughput": 1489.66, "total_tokens": 10364480} {"current_steps": 49125, "total_steps": 181800, "loss": 0.0432, "lr": 4.571573383169835e-05, "epoch": 5.404290429042904, "percentage": 27.02, "elapsed_time": "1:55:58", "remaining_time": "5:13:12", "throughput": 1489.66, "total_tokens": 10365472} {"current_steps": 49130, "total_steps": 181800, "loss": 0.0171, "lr": 4.571439018399291e-05, "epoch": 5.404840484048405, "percentage": 27.02, "elapsed_time": "1:55:58", "remaining_time": "5:13:11", "throughput": 1489.66, "total_tokens": 10366528} {"current_steps": 49135, "total_steps": 181800, "loss": 0.0802, "lr": 4.571304634537286e-05, "epoch": 5.405390539053905, "percentage": 27.03, "elapsed_time": "1:55:59", "remaining_time": "5:13:11", "throughput": 1489.66, "total_tokens": 10367552} {"current_steps": 49140, "total_steps": 181800, "loss": 0.0546, "lr": 4.5711702315850614e-05, "epoch": 5.405940594059406, "percentage": 27.03, "elapsed_time": "1:56:00", "remaining_time": "5:13:10", "throughput": 1489.66, "total_tokens": 10368608} {"current_steps": 49145, "total_steps": 181800, "loss": 0.0373, "lr": 4.571035809543854e-05, "epoch": 5.4064906490649065, "percentage": 27.03, "elapsed_time": "1:56:01", "remaining_time": "5:13:09", "throughput": 1489.67, "total_tokens": 10369664} {"current_steps": 49150, "total_steps": 181800, "loss": 0.0154, "lr": 4.570901368414904e-05, "epoch": 5.407040704070407, "percentage": 27.04, "elapsed_time": "1:56:01", "remaining_time": "5:13:08", "throughput": 1489.67, "total_tokens": 10370720} {"current_steps": 49155, "total_steps": 181800, "loss": 0.0149, "lr": 4.5707669081994495e-05, "epoch": 5.407590759075908, "percentage": 27.04, "elapsed_time": "1:56:02", "remaining_time": "5:13:08", "throughput": 1489.66, "total_tokens": 10371680} {"current_steps": 49160, "total_steps": 181800, "loss": 0.0058, "lr": 4.57063242889873e-05, "epoch": 5.408140814081408, "percentage": 27.04, "elapsed_time": "1:56:03", "remaining_time": "5:13:07", "throughput": 1489.66, "total_tokens": 10372704} {"current_steps": 49165, "total_steps": 181800, "loss": 0.0075, "lr": 4.570497930513985e-05, "epoch": 5.408690869086909, "percentage": 27.04, "elapsed_time": "1:56:03", "remaining_time": "5:13:06", "throughput": 1489.67, "total_tokens": 10373760} {"current_steps": 49170, "total_steps": 181800, "loss": 0.0141, "lr": 4.5703634130464535e-05, "epoch": 5.409240924092409, "percentage": 27.05, "elapsed_time": "1:56:04", "remaining_time": "5:13:05", "throughput": 1489.66, "total_tokens": 10374752} {"current_steps": 49175, "total_steps": 181800, "loss": 0.0879, "lr": 4.570228876497377e-05, "epoch": 5.4097909790979095, "percentage": 27.05, "elapsed_time": "1:56:05", "remaining_time": "5:13:05", "throughput": 1489.67, "total_tokens": 10375808} {"current_steps": 49180, "total_steps": 181800, "loss": 0.0557, "lr": 4.5700943208679935e-05, "epoch": 5.410341034103411, "percentage": 27.05, "elapsed_time": "1:56:05", "remaining_time": "5:13:04", "throughput": 1489.66, "total_tokens": 10376800} {"current_steps": 49185, "total_steps": 181800, "loss": 0.0654, "lr": 4.569959746159545e-05, "epoch": 5.410891089108911, "percentage": 27.05, "elapsed_time": "1:56:06", "remaining_time": "5:13:03", "throughput": 1489.66, "total_tokens": 10377824} {"current_steps": 49190, "total_steps": 181800, "loss": 0.0141, "lr": 4.569825152373269e-05, "epoch": 5.411441144114411, "percentage": 27.06, "elapsed_time": "1:56:07", "remaining_time": "5:13:02", "throughput": 1489.68, "total_tokens": 10379008} {"current_steps": 49195, "total_steps": 181800, "loss": 0.1224, "lr": 4.5696905395104095e-05, "epoch": 5.411991199119912, "percentage": 27.06, "elapsed_time": "1:56:07", "remaining_time": "5:13:02", "throughput": 1489.68, "total_tokens": 10380032} {"current_steps": 49200, "total_steps": 181800, "loss": 0.0541, "lr": 4.5695559075722046e-05, "epoch": 5.412541254125412, "percentage": 27.06, "elapsed_time": "1:56:08", "remaining_time": "5:13:01", "throughput": 1489.68, "total_tokens": 10381056} {"current_steps": 49205, "total_steps": 181800, "loss": 0.0095, "lr": 4.569421256559896e-05, "epoch": 5.413091309130913, "percentage": 27.07, "elapsed_time": "1:56:09", "remaining_time": "5:13:00", "throughput": 1489.69, "total_tokens": 10382176} {"current_steps": 49210, "total_steps": 181800, "loss": 0.0625, "lr": 4.569286586474725e-05, "epoch": 5.413641364136414, "percentage": 27.07, "elapsed_time": "1:56:10", "remaining_time": "5:12:59", "throughput": 1489.7, "total_tokens": 10383232} {"current_steps": 49215, "total_steps": 181800, "loss": 0.0467, "lr": 4.569151897317931e-05, "epoch": 5.414191419141914, "percentage": 27.07, "elapsed_time": "1:56:10", "remaining_time": "5:12:59", "throughput": 1489.7, "total_tokens": 10384288} {"current_steps": 49220, "total_steps": 181800, "loss": 0.0611, "lr": 4.569017189090759e-05, "epoch": 5.414741474147415, "percentage": 27.07, "elapsed_time": "1:56:11", "remaining_time": "5:12:58", "throughput": 1489.71, "total_tokens": 10385376} {"current_steps": 49225, "total_steps": 181800, "loss": 0.182, "lr": 4.568882461794448e-05, "epoch": 5.415291529152915, "percentage": 27.08, "elapsed_time": "1:56:12", "remaining_time": "5:12:57", "throughput": 1489.72, "total_tokens": 10386464} {"current_steps": 49230, "total_steps": 181800, "loss": 0.0249, "lr": 4.5687477154302396e-05, "epoch": 5.415841584158416, "percentage": 27.08, "elapsed_time": "1:56:12", "remaining_time": "5:12:56", "throughput": 1489.73, "total_tokens": 10387584} {"current_steps": 49235, "total_steps": 181800, "loss": 0.0953, "lr": 4.568612949999376e-05, "epoch": 5.416391639163916, "percentage": 27.08, "elapsed_time": "1:56:13", "remaining_time": "5:12:56", "throughput": 1489.73, "total_tokens": 10388608} {"current_steps": 49240, "total_steps": 181800, "loss": 0.0238, "lr": 4.5684781655030996e-05, "epoch": 5.416941694169417, "percentage": 27.08, "elapsed_time": "1:56:14", "remaining_time": "5:12:55", "throughput": 1489.72, "total_tokens": 10389568} {"current_steps": 49245, "total_steps": 181800, "loss": 0.009, "lr": 4.568343361942652e-05, "epoch": 5.417491749174918, "percentage": 27.09, "elapsed_time": "1:56:14", "remaining_time": "5:12:54", "throughput": 1489.72, "total_tokens": 10390592} {"current_steps": 49250, "total_steps": 181800, "loss": 0.0195, "lr": 4.568208539319276e-05, "epoch": 5.418041804180418, "percentage": 27.09, "elapsed_time": "1:56:15", "remaining_time": "5:12:53", "throughput": 1489.73, "total_tokens": 10391648} {"current_steps": 49255, "total_steps": 181800, "loss": 0.0785, "lr": 4.568073697634216e-05, "epoch": 5.418591859185918, "percentage": 27.09, "elapsed_time": "1:56:16", "remaining_time": "5:12:53", "throughput": 1489.74, "total_tokens": 10392768} {"current_steps": 49260, "total_steps": 181800, "loss": 0.0848, "lr": 4.567938836888712e-05, "epoch": 5.419141914191419, "percentage": 27.1, "elapsed_time": "1:56:16", "remaining_time": "5:12:52", "throughput": 1489.74, "total_tokens": 10393824} {"current_steps": 49265, "total_steps": 181800, "loss": 0.0351, "lr": 4.567803957084008e-05, "epoch": 5.419691969196919, "percentage": 27.1, "elapsed_time": "1:56:17", "remaining_time": "5:12:51", "throughput": 1489.75, "total_tokens": 10394880} {"current_steps": 49270, "total_steps": 181800, "loss": 0.0537, "lr": 4.567669058221347e-05, "epoch": 5.4202420242024205, "percentage": 27.1, "elapsed_time": "1:56:18", "remaining_time": "5:12:50", "throughput": 1489.76, "total_tokens": 10396000} {"current_steps": 49275, "total_steps": 181800, "loss": 0.0245, "lr": 4.5675341403019725e-05, "epoch": 5.420792079207921, "percentage": 27.1, "elapsed_time": "1:56:18", "remaining_time": "5:12:49", "throughput": 1489.77, "total_tokens": 10397088} {"current_steps": 49280, "total_steps": 181800, "loss": 0.0161, "lr": 4.5673992033271286e-05, "epoch": 5.421342134213421, "percentage": 27.11, "elapsed_time": "1:56:19", "remaining_time": "5:12:49", "throughput": 1489.77, "total_tokens": 10398144} {"current_steps": 49285, "total_steps": 181800, "loss": 0.0316, "lr": 4.567264247298058e-05, "epoch": 5.421892189218922, "percentage": 27.11, "elapsed_time": "1:56:20", "remaining_time": "5:12:48", "throughput": 1489.77, "total_tokens": 10399136} {"current_steps": 49290, "total_steps": 181800, "loss": 0.1031, "lr": 4.567129272216004e-05, "epoch": 5.422442244224422, "percentage": 27.11, "elapsed_time": "1:56:21", "remaining_time": "5:12:47", "throughput": 1489.76, "total_tokens": 10400128} {"current_steps": 49295, "total_steps": 181800, "loss": 0.0247, "lr": 4.566994278082212e-05, "epoch": 5.422992299229923, "percentage": 27.11, "elapsed_time": "1:56:21", "remaining_time": "5:12:46", "throughput": 1489.77, "total_tokens": 10401184} {"current_steps": 49300, "total_steps": 181800, "loss": 0.0067, "lr": 4.566859264897926e-05, "epoch": 5.4235423542354235, "percentage": 27.12, "elapsed_time": "1:56:22", "remaining_time": "5:12:46", "throughput": 1489.78, "total_tokens": 10402272} {"current_steps": 49305, "total_steps": 181800, "loss": 0.0992, "lr": 4.5667242326643894e-05, "epoch": 5.424092409240924, "percentage": 27.12, "elapsed_time": "1:56:23", "remaining_time": "5:12:45", "throughput": 1489.78, "total_tokens": 10403360} {"current_steps": 49310, "total_steps": 181800, "loss": 0.0911, "lr": 4.566589181382847e-05, "epoch": 5.424642464246425, "percentage": 27.12, "elapsed_time": "1:56:23", "remaining_time": "5:12:44", "throughput": 1489.78, "total_tokens": 10404352} {"current_steps": 49315, "total_steps": 181800, "loss": 0.0051, "lr": 4.5664541110545445e-05, "epoch": 5.425192519251925, "percentage": 27.13, "elapsed_time": "1:56:24", "remaining_time": "5:12:43", "throughput": 1489.78, "total_tokens": 10405376} {"current_steps": 49320, "total_steps": 181800, "loss": 0.1593, "lr": 4.566319021680726e-05, "epoch": 5.425742574257426, "percentage": 27.13, "elapsed_time": "1:56:25", "remaining_time": "5:12:43", "throughput": 1489.78, "total_tokens": 10406432} {"current_steps": 49325, "total_steps": 181800, "loss": 0.0091, "lr": 4.566183913262636e-05, "epoch": 5.426292629262926, "percentage": 27.13, "elapsed_time": "1:56:25", "remaining_time": "5:12:42", "throughput": 1489.79, "total_tokens": 10407520} {"current_steps": 49330, "total_steps": 181800, "loss": 0.0602, "lr": 4.56604878580152e-05, "epoch": 5.4268426842684265, "percentage": 27.13, "elapsed_time": "1:56:26", "remaining_time": "5:12:41", "throughput": 1489.79, "total_tokens": 10408512} {"current_steps": 49335, "total_steps": 181800, "loss": 0.0706, "lr": 4.5659136392986245e-05, "epoch": 5.427392739273928, "percentage": 27.14, "elapsed_time": "1:56:27", "remaining_time": "5:12:40", "throughput": 1489.79, "total_tokens": 10409536} {"current_steps": 49340, "total_steps": 181800, "loss": 0.0139, "lr": 4.5657784737551945e-05, "epoch": 5.427942794279428, "percentage": 27.14, "elapsed_time": "1:56:27", "remaining_time": "5:12:40", "throughput": 1489.78, "total_tokens": 10410528} {"current_steps": 49345, "total_steps": 181800, "loss": 0.0195, "lr": 4.565643289172475e-05, "epoch": 5.428492849284929, "percentage": 27.14, "elapsed_time": "1:56:28", "remaining_time": "5:12:39", "throughput": 1489.78, "total_tokens": 10411552} {"current_steps": 49350, "total_steps": 181800, "loss": 0.0355, "lr": 4.565508085551713e-05, "epoch": 5.429042904290429, "percentage": 27.15, "elapsed_time": "1:56:29", "remaining_time": "5:12:38", "throughput": 1489.79, "total_tokens": 10412640} {"current_steps": 49355, "total_steps": 181800, "loss": 0.1632, "lr": 4.5653728628941536e-05, "epoch": 5.429592959295929, "percentage": 27.15, "elapsed_time": "1:56:30", "remaining_time": "5:12:37", "throughput": 1489.8, "total_tokens": 10413760} {"current_steps": 49360, "total_steps": 181800, "loss": 0.0333, "lr": 4.5652376212010434e-05, "epoch": 5.43014301430143, "percentage": 27.15, "elapsed_time": "1:56:30", "remaining_time": "5:12:37", "throughput": 1489.81, "total_tokens": 10414816} {"current_steps": 49365, "total_steps": 181800, "loss": 0.0512, "lr": 4.5651023604736296e-05, "epoch": 5.430693069306931, "percentage": 27.15, "elapsed_time": "1:56:31", "remaining_time": "5:12:36", "throughput": 1489.81, "total_tokens": 10415840} {"current_steps": 49370, "total_steps": 181800, "loss": 0.0361, "lr": 4.5649670807131586e-05, "epoch": 5.431243124312431, "percentage": 27.16, "elapsed_time": "1:56:32", "remaining_time": "5:12:35", "throughput": 1489.81, "total_tokens": 10416896} {"current_steps": 49375, "total_steps": 181800, "loss": 0.0285, "lr": 4.5648317819208756e-05, "epoch": 5.431793179317932, "percentage": 27.16, "elapsed_time": "1:56:32", "remaining_time": "5:12:34", "throughput": 1489.82, "total_tokens": 10417984} {"current_steps": 49380, "total_steps": 181800, "loss": 0.0338, "lr": 4.56469646409803e-05, "epoch": 5.432343234323432, "percentage": 27.16, "elapsed_time": "1:56:33", "remaining_time": "5:12:34", "throughput": 1489.82, "total_tokens": 10419008} {"current_steps": 49385, "total_steps": 181800, "loss": 0.0375, "lr": 4.564561127245868e-05, "epoch": 5.432893289328933, "percentage": 27.16, "elapsed_time": "1:56:34", "remaining_time": "5:12:33", "throughput": 1489.82, "total_tokens": 10420032} {"current_steps": 49390, "total_steps": 181800, "loss": 0.0054, "lr": 4.5644257713656356e-05, "epoch": 5.433443344334433, "percentage": 27.17, "elapsed_time": "1:56:34", "remaining_time": "5:12:32", "throughput": 1489.82, "total_tokens": 10421056} {"current_steps": 49395, "total_steps": 181800, "loss": 0.0201, "lr": 4.564290396458582e-05, "epoch": 5.433993399339934, "percentage": 27.17, "elapsed_time": "1:56:35", "remaining_time": "5:12:31", "throughput": 1489.82, "total_tokens": 10422112} {"current_steps": 49400, "total_steps": 181800, "loss": 0.1285, "lr": 4.564155002525955e-05, "epoch": 5.434543454345435, "percentage": 27.17, "elapsed_time": "1:56:36", "remaining_time": "5:12:30", "throughput": 1489.82, "total_tokens": 10423136} {"current_steps": 49405, "total_steps": 181800, "loss": 0.0213, "lr": 4.5640195895690006e-05, "epoch": 5.435093509350935, "percentage": 27.18, "elapsed_time": "1:56:36", "remaining_time": "5:12:30", "throughput": 1489.82, "total_tokens": 10424128} {"current_steps": 49410, "total_steps": 181800, "loss": 0.0426, "lr": 4.563884157588969e-05, "epoch": 5.435643564356436, "percentage": 27.18, "elapsed_time": "1:56:37", "remaining_time": "5:12:29", "throughput": 1489.83, "total_tokens": 10425248} {"current_steps": 49415, "total_steps": 181800, "loss": 0.067, "lr": 4.563748706587107e-05, "epoch": 5.436193619361936, "percentage": 27.18, "elapsed_time": "1:56:38", "remaining_time": "5:12:28", "throughput": 1489.83, "total_tokens": 10426240} {"current_steps": 49420, "total_steps": 181800, "loss": 0.2398, "lr": 4.5636132365646636e-05, "epoch": 5.436743674367436, "percentage": 27.18, "elapsed_time": "1:56:38", "remaining_time": "5:12:27", "throughput": 1489.83, "total_tokens": 10427296} {"current_steps": 49425, "total_steps": 181800, "loss": 0.0612, "lr": 4.5634777475228874e-05, "epoch": 5.4372937293729375, "percentage": 27.19, "elapsed_time": "1:56:39", "remaining_time": "5:12:27", "throughput": 1489.84, "total_tokens": 10428352} {"current_steps": 49430, "total_steps": 181800, "loss": 0.0223, "lr": 4.563342239463027e-05, "epoch": 5.437843784378438, "percentage": 27.19, "elapsed_time": "1:56:40", "remaining_time": "5:12:26", "throughput": 1489.83, "total_tokens": 10429376} {"current_steps": 49435, "total_steps": 181800, "loss": 0.0437, "lr": 4.563206712386331e-05, "epoch": 5.438393839383938, "percentage": 27.19, "elapsed_time": "1:56:41", "remaining_time": "5:12:25", "throughput": 1489.83, "total_tokens": 10430400} {"current_steps": 49440, "total_steps": 181800, "loss": 0.0353, "lr": 4.563071166294049e-05, "epoch": 5.438943894389439, "percentage": 27.19, "elapsed_time": "1:56:41", "remaining_time": "5:12:24", "throughput": 1489.84, "total_tokens": 10431456} {"current_steps": 49445, "total_steps": 181800, "loss": 0.093, "lr": 4.56293560118743e-05, "epoch": 5.439493949394939, "percentage": 27.2, "elapsed_time": "1:56:42", "remaining_time": "5:12:24", "throughput": 1489.84, "total_tokens": 10432512} {"current_steps": 49450, "total_steps": 181800, "loss": 0.261, "lr": 4.562800017067723e-05, "epoch": 5.44004400440044, "percentage": 27.2, "elapsed_time": "1:56:43", "remaining_time": "5:12:23", "throughput": 1489.85, "total_tokens": 10433568} {"current_steps": 49455, "total_steps": 181800, "loss": 0.1417, "lr": 4.5626644139361784e-05, "epoch": 5.4405940594059405, "percentage": 27.2, "elapsed_time": "1:56:43", "remaining_time": "5:12:22", "throughput": 1489.86, "total_tokens": 10434688} {"current_steps": 49460, "total_steps": 181800, "loss": 0.0108, "lr": 4.5625287917940457e-05, "epoch": 5.441144114411441, "percentage": 27.21, "elapsed_time": "1:56:44", "remaining_time": "5:12:21", "throughput": 1489.87, "total_tokens": 10435776} {"current_steps": 49465, "total_steps": 181800, "loss": 0.0083, "lr": 4.5623931506425746e-05, "epoch": 5.441694169416942, "percentage": 27.21, "elapsed_time": "1:56:45", "remaining_time": "5:12:21", "throughput": 1489.87, "total_tokens": 10436832} {"current_steps": 49470, "total_steps": 181800, "loss": 0.0166, "lr": 4.562257490483016e-05, "epoch": 5.442244224422442, "percentage": 27.21, "elapsed_time": "1:56:45", "remaining_time": "5:12:20", "throughput": 1489.88, "total_tokens": 10437952} {"current_steps": 49475, "total_steps": 181800, "loss": 0.018, "lr": 4.562121811316619e-05, "epoch": 5.442794279427943, "percentage": 27.21, "elapsed_time": "1:56:46", "remaining_time": "5:12:19", "throughput": 1489.89, "total_tokens": 10439040} {"current_steps": 49480, "total_steps": 181800, "loss": 0.0193, "lr": 4.5619861131446354e-05, "epoch": 5.443344334433443, "percentage": 27.22, "elapsed_time": "1:56:47", "remaining_time": "5:12:18", "throughput": 1489.89, "total_tokens": 10440064} {"current_steps": 49485, "total_steps": 181800, "loss": 0.0768, "lr": 4.5618503959683144e-05, "epoch": 5.4438943894389435, "percentage": 27.22, "elapsed_time": "1:56:47", "remaining_time": "5:12:18", "throughput": 1489.9, "total_tokens": 10441152} {"current_steps": 49490, "total_steps": 181800, "loss": 0.0239, "lr": 4.561714659788908e-05, "epoch": 5.444444444444445, "percentage": 27.22, "elapsed_time": "1:56:48", "remaining_time": "5:12:17", "throughput": 1489.91, "total_tokens": 10442208} {"current_steps": 49495, "total_steps": 181800, "loss": 0.0649, "lr": 4.5615789046076676e-05, "epoch": 5.444994499449945, "percentage": 27.22, "elapsed_time": "1:56:49", "remaining_time": "5:12:16", "throughput": 1489.91, "total_tokens": 10443232} {"current_steps": 49500, "total_steps": 181800, "loss": 0.0936, "lr": 4.561443130425843e-05, "epoch": 5.445544554455446, "percentage": 27.23, "elapsed_time": "1:56:50", "remaining_time": "5:12:15", "throughput": 1489.92, "total_tokens": 10444320} {"current_steps": 49505, "total_steps": 181800, "loss": 0.016, "lr": 4.561307337244687e-05, "epoch": 5.446094609460946, "percentage": 27.23, "elapsed_time": "1:56:50", "remaining_time": "5:12:15", "throughput": 1489.92, "total_tokens": 10445376} {"current_steps": 49510, "total_steps": 181800, "loss": 0.069, "lr": 4.5611715250654495e-05, "epoch": 5.446644664466446, "percentage": 27.23, "elapsed_time": "1:56:51", "remaining_time": "5:12:14", "throughput": 1489.92, "total_tokens": 10446400} {"current_steps": 49515, "total_steps": 181800, "loss": 0.0437, "lr": 4.5610356938893825e-05, "epoch": 5.447194719471947, "percentage": 27.24, "elapsed_time": "1:56:52", "remaining_time": "5:12:13", "throughput": 1489.92, "total_tokens": 10447456} {"current_steps": 49520, "total_steps": 181800, "loss": 0.0153, "lr": 4.56089984371774e-05, "epoch": 5.447744774477448, "percentage": 27.24, "elapsed_time": "1:56:52", "remaining_time": "5:12:12", "throughput": 1489.92, "total_tokens": 10448480} {"current_steps": 49525, "total_steps": 181800, "loss": 0.0178, "lr": 4.560763974551772e-05, "epoch": 5.448294829482949, "percentage": 27.24, "elapsed_time": "1:56:53", "remaining_time": "5:12:12", "throughput": 1489.93, "total_tokens": 10449536} {"current_steps": 49530, "total_steps": 181800, "loss": 0.1408, "lr": 4.5606280863927313e-05, "epoch": 5.448844884488449, "percentage": 27.24, "elapsed_time": "1:56:54", "remaining_time": "5:12:11", "throughput": 1489.93, "total_tokens": 10450592} {"current_steps": 49535, "total_steps": 181800, "loss": 0.0808, "lr": 4.56049217924187e-05, "epoch": 5.449394939493949, "percentage": 27.25, "elapsed_time": "1:56:54", "remaining_time": "5:12:10", "throughput": 1489.94, "total_tokens": 10451680} {"current_steps": 49540, "total_steps": 181800, "loss": 0.088, "lr": 4.560356253100442e-05, "epoch": 5.44994499449945, "percentage": 27.25, "elapsed_time": "1:56:55", "remaining_time": "5:12:09", "throughput": 1489.94, "total_tokens": 10452704} {"current_steps": 49545, "total_steps": 181800, "loss": 0.0841, "lr": 4.560220307969698e-05, "epoch": 5.4504950495049505, "percentage": 27.25, "elapsed_time": "1:56:56", "remaining_time": "5:12:09", "throughput": 1489.93, "total_tokens": 10453696} {"current_steps": 49550, "total_steps": 181800, "loss": 0.0221, "lr": 4.560084343850892e-05, "epoch": 5.451045104510451, "percentage": 27.26, "elapsed_time": "1:56:56", "remaining_time": "5:12:08", "throughput": 1489.94, "total_tokens": 10454752} {"current_steps": 49555, "total_steps": 181800, "loss": 0.111, "lr": 4.559948360745278e-05, "epoch": 5.451595159515952, "percentage": 27.26, "elapsed_time": "1:56:57", "remaining_time": "5:12:07", "throughput": 1489.95, "total_tokens": 10455840} {"current_steps": 49560, "total_steps": 181800, "loss": 0.0133, "lr": 4.559812358654107e-05, "epoch": 5.452145214521452, "percentage": 27.26, "elapsed_time": "1:56:58", "remaining_time": "5:12:06", "throughput": 1489.95, "total_tokens": 10456928} {"current_steps": 49565, "total_steps": 181800, "loss": 0.0541, "lr": 4.559676337578635e-05, "epoch": 5.452695269526953, "percentage": 27.26, "elapsed_time": "1:56:58", "remaining_time": "5:12:06", "throughput": 1489.95, "total_tokens": 10457920} {"current_steps": 49570, "total_steps": 181800, "loss": 0.0307, "lr": 4.559540297520114e-05, "epoch": 5.453245324532453, "percentage": 27.27, "elapsed_time": "1:56:59", "remaining_time": "5:12:05", "throughput": 1489.95, "total_tokens": 10458944} {"current_steps": 49575, "total_steps": 181800, "loss": 0.0888, "lr": 4.5594042384797994e-05, "epoch": 5.4537953795379535, "percentage": 27.27, "elapsed_time": "1:57:00", "remaining_time": "5:12:04", "throughput": 1489.95, "total_tokens": 10460000} {"current_steps": 49580, "total_steps": 181800, "loss": 0.013, "lr": 4.559268160458943e-05, "epoch": 5.4543454345434546, "percentage": 27.27, "elapsed_time": "1:57:01", "remaining_time": "5:12:03", "throughput": 1489.96, "total_tokens": 10461088} {"current_steps": 49585, "total_steps": 181800, "loss": 0.1252, "lr": 4.5591320634588004e-05, "epoch": 5.454895489548955, "percentage": 27.27, "elapsed_time": "1:57:01", "remaining_time": "5:12:02", "throughput": 1489.97, "total_tokens": 10462176} {"current_steps": 49590, "total_steps": 181800, "loss": 0.0394, "lr": 4.558995947480625e-05, "epoch": 5.455445544554456, "percentage": 27.28, "elapsed_time": "1:57:02", "remaining_time": "5:12:02", "throughput": 1489.97, "total_tokens": 10463232} {"current_steps": 49595, "total_steps": 181800, "loss": 0.011, "lr": 4.558859812525673e-05, "epoch": 5.455995599559956, "percentage": 27.28, "elapsed_time": "1:57:03", "remaining_time": "5:12:01", "throughput": 1489.97, "total_tokens": 10464256} {"current_steps": 49600, "total_steps": 181800, "loss": 0.0199, "lr": 4.558723658595198e-05, "epoch": 5.456545654565456, "percentage": 27.28, "elapsed_time": "1:57:03", "remaining_time": "5:12:00", "throughput": 1489.98, "total_tokens": 10465312} {"current_steps": 49605, "total_steps": 181800, "loss": 0.0337, "lr": 4.558587485690454e-05, "epoch": 5.457095709570957, "percentage": 27.29, "elapsed_time": "1:57:04", "remaining_time": "5:11:59", "throughput": 1489.97, "total_tokens": 10466304} {"current_steps": 49610, "total_steps": 181800, "loss": 0.0067, "lr": 4.558451293812698e-05, "epoch": 5.457645764576458, "percentage": 27.29, "elapsed_time": "1:57:05", "remaining_time": "5:11:59", "throughput": 1489.98, "total_tokens": 10467360} {"current_steps": 49615, "total_steps": 181800, "loss": 0.0219, "lr": 4.558315082963184e-05, "epoch": 5.458195819581958, "percentage": 27.29, "elapsed_time": "1:57:05", "remaining_time": "5:11:58", "throughput": 1489.97, "total_tokens": 10468352} {"current_steps": 49620, "total_steps": 181800, "loss": 0.0119, "lr": 4.558178853143167e-05, "epoch": 5.458745874587459, "percentage": 27.29, "elapsed_time": "1:57:06", "remaining_time": "5:11:57", "throughput": 1489.99, "total_tokens": 10469472} {"current_steps": 49625, "total_steps": 181800, "loss": 0.1246, "lr": 4.558042604353904e-05, "epoch": 5.459295929592959, "percentage": 27.3, "elapsed_time": "1:57:07", "remaining_time": "5:11:56", "throughput": 1490.0, "total_tokens": 10470624} {"current_steps": 49630, "total_steps": 181800, "loss": 0.0801, "lr": 4.557906336596649e-05, "epoch": 5.45984598459846, "percentage": 27.3, "elapsed_time": "1:57:07", "remaining_time": "5:11:56", "throughput": 1490.0, "total_tokens": 10471648} {"current_steps": 49635, "total_steps": 181800, "loss": 0.0089, "lr": 4.557770049872659e-05, "epoch": 5.46039603960396, "percentage": 27.3, "elapsed_time": "1:57:08", "remaining_time": "5:11:55", "throughput": 1490.01, "total_tokens": 10472704} {"current_steps": 49640, "total_steps": 181800, "loss": 0.1011, "lr": 4.5576337441831895e-05, "epoch": 5.460946094609461, "percentage": 27.3, "elapsed_time": "1:57:09", "remaining_time": "5:11:54", "throughput": 1490.02, "total_tokens": 10473792} {"current_steps": 49645, "total_steps": 181800, "loss": 0.0183, "lr": 4.557497419529498e-05, "epoch": 5.461496149614962, "percentage": 27.31, "elapsed_time": "1:57:10", "remaining_time": "5:11:53", "throughput": 1490.02, "total_tokens": 10474848} {"current_steps": 49650, "total_steps": 181800, "loss": 0.0382, "lr": 4.557361075912839e-05, "epoch": 5.462046204620462, "percentage": 27.31, "elapsed_time": "1:57:10", "remaining_time": "5:11:53", "throughput": 1490.03, "total_tokens": 10475936} {"current_steps": 49655, "total_steps": 181800, "loss": 0.0167, "lr": 4.5572247133344716e-05, "epoch": 5.462596259625963, "percentage": 27.31, "elapsed_time": "1:57:11", "remaining_time": "5:11:52", "throughput": 1490.03, "total_tokens": 10476960} {"current_steps": 49660, "total_steps": 181800, "loss": 0.0395, "lr": 4.5570883317956505e-05, "epoch": 5.463146314631463, "percentage": 27.32, "elapsed_time": "1:57:12", "remaining_time": "5:11:51", "throughput": 1490.03, "total_tokens": 10477984} {"current_steps": 49665, "total_steps": 181800, "loss": 0.087, "lr": 4.5569519312976326e-05, "epoch": 5.463696369636963, "percentage": 27.32, "elapsed_time": "1:57:12", "remaining_time": "5:11:50", "throughput": 1490.03, "total_tokens": 10479040} {"current_steps": 49670, "total_steps": 181800, "loss": 0.0226, "lr": 4.556815511841676e-05, "epoch": 5.4642464246424645, "percentage": 27.32, "elapsed_time": "1:57:13", "remaining_time": "5:11:50", "throughput": 1490.03, "total_tokens": 10480064} {"current_steps": 49675, "total_steps": 181800, "loss": 0.0336, "lr": 4.556679073429039e-05, "epoch": 5.464796479647965, "percentage": 27.32, "elapsed_time": "1:57:14", "remaining_time": "5:11:49", "throughput": 1490.03, "total_tokens": 10481088} {"current_steps": 49680, "total_steps": 181800, "loss": 0.005, "lr": 4.5565426160609766e-05, "epoch": 5.465346534653466, "percentage": 27.33, "elapsed_time": "1:57:14", "remaining_time": "5:11:48", "throughput": 1490.04, "total_tokens": 10482208} {"current_steps": 49685, "total_steps": 181800, "loss": 0.0257, "lr": 4.556406139738748e-05, "epoch": 5.465896589658966, "percentage": 27.33, "elapsed_time": "1:57:15", "remaining_time": "5:11:47", "throughput": 1490.04, "total_tokens": 10483232} {"current_steps": 49690, "total_steps": 181800, "loss": 0.0299, "lr": 4.556269644463611e-05, "epoch": 5.466446644664466, "percentage": 27.33, "elapsed_time": "1:57:16", "remaining_time": "5:11:47", "throughput": 1490.04, "total_tokens": 10484256} {"current_steps": 49695, "total_steps": 181800, "loss": 0.028, "lr": 4.556133130236823e-05, "epoch": 5.466996699669967, "percentage": 27.33, "elapsed_time": "1:57:16", "remaining_time": "5:11:46", "throughput": 1490.04, "total_tokens": 10485312} {"current_steps": 49700, "total_steps": 181800, "loss": 0.0291, "lr": 4.555996597059643e-05, "epoch": 5.4675467546754675, "percentage": 27.34, "elapsed_time": "1:57:17", "remaining_time": "5:11:45", "throughput": 1490.05, "total_tokens": 10486400} {"current_steps": 49705, "total_steps": 181800, "loss": 0.0715, "lr": 4.555860044933329e-05, "epoch": 5.468096809680969, "percentage": 27.34, "elapsed_time": "1:57:18", "remaining_time": "5:11:44", "throughput": 1490.05, "total_tokens": 10487424} {"current_steps": 49710, "total_steps": 181800, "loss": 0.0288, "lr": 4.555723473859139e-05, "epoch": 5.468646864686469, "percentage": 27.34, "elapsed_time": "1:57:18", "remaining_time": "5:11:44", "throughput": 1490.05, "total_tokens": 10488480} {"current_steps": 49715, "total_steps": 181800, "loss": 0.1465, "lr": 4.5555868838383326e-05, "epoch": 5.469196919691969, "percentage": 27.35, "elapsed_time": "1:57:19", "remaining_time": "5:11:43", "throughput": 1490.02, "total_tokens": 10489536} {"current_steps": 49720, "total_steps": 181800, "loss": 0.0316, "lr": 4.5554502748721687e-05, "epoch": 5.46974697469747, "percentage": 27.35, "elapsed_time": "1:57:20", "remaining_time": "5:11:43", "throughput": 1490.03, "total_tokens": 10490688} {"current_steps": 49725, "total_steps": 181800, "loss": 0.0095, "lr": 4.555313646961905e-05, "epoch": 5.47029702970297, "percentage": 27.35, "elapsed_time": "1:57:21", "remaining_time": "5:11:42", "throughput": 1490.03, "total_tokens": 10491712} {"current_steps": 49730, "total_steps": 181800, "loss": 0.1198, "lr": 4.5551770001088015e-05, "epoch": 5.4708470847084705, "percentage": 27.35, "elapsed_time": "1:57:21", "remaining_time": "5:11:41", "throughput": 1490.04, "total_tokens": 10492832} {"current_steps": 49735, "total_steps": 181800, "loss": 0.0277, "lr": 4.555040334314118e-05, "epoch": 5.471397139713972, "percentage": 27.36, "elapsed_time": "1:57:22", "remaining_time": "5:11:40", "throughput": 1490.05, "total_tokens": 10493888} {"current_steps": 49740, "total_steps": 181800, "loss": 0.0271, "lr": 4.5549036495791144e-05, "epoch": 5.471947194719472, "percentage": 27.36, "elapsed_time": "1:57:23", "remaining_time": "5:11:40", "throughput": 1490.05, "total_tokens": 10494912} {"current_steps": 49745, "total_steps": 181800, "loss": 0.0238, "lr": 4.554766945905049e-05, "epoch": 5.472497249724973, "percentage": 27.36, "elapsed_time": "1:57:24", "remaining_time": "5:11:39", "throughput": 1490.05, "total_tokens": 10495968} {"current_steps": 49750, "total_steps": 181800, "loss": 0.054, "lr": 4.554630223293184e-05, "epoch": 5.473047304730473, "percentage": 27.37, "elapsed_time": "1:57:24", "remaining_time": "5:11:38", "throughput": 1490.06, "total_tokens": 10497056} {"current_steps": 49755, "total_steps": 181800, "loss": 0.0062, "lr": 4.554493481744777e-05, "epoch": 5.473597359735973, "percentage": 27.37, "elapsed_time": "1:57:25", "remaining_time": "5:11:37", "throughput": 1490.06, "total_tokens": 10498112} {"current_steps": 49760, "total_steps": 181800, "loss": 0.0346, "lr": 4.554356721261089e-05, "epoch": 5.474147414741474, "percentage": 27.37, "elapsed_time": "1:57:26", "remaining_time": "5:11:37", "throughput": 1490.06, "total_tokens": 10499136} {"current_steps": 49765, "total_steps": 181800, "loss": 0.0365, "lr": 4.5542199418433825e-05, "epoch": 5.474697469746975, "percentage": 27.37, "elapsed_time": "1:57:26", "remaining_time": "5:11:36", "throughput": 1490.06, "total_tokens": 10500128} {"current_steps": 49770, "total_steps": 181800, "loss": 0.057, "lr": 4.554083143492915e-05, "epoch": 5.475247524752476, "percentage": 27.38, "elapsed_time": "1:57:27", "remaining_time": "5:11:35", "throughput": 1490.06, "total_tokens": 10501152} {"current_steps": 49775, "total_steps": 181800, "loss": 0.0514, "lr": 4.553946326210949e-05, "epoch": 5.475797579757976, "percentage": 27.38, "elapsed_time": "1:57:28", "remaining_time": "5:11:34", "throughput": 1490.07, "total_tokens": 10502240} {"current_steps": 49780, "total_steps": 181800, "loss": 0.0747, "lr": 4.553809489998747e-05, "epoch": 5.476347634763476, "percentage": 27.38, "elapsed_time": "1:57:28", "remaining_time": "5:11:34", "throughput": 1490.07, "total_tokens": 10503264} {"current_steps": 49785, "total_steps": 181800, "loss": 0.0178, "lr": 4.5536726348575666e-05, "epoch": 5.476897689768977, "percentage": 27.38, "elapsed_time": "1:57:29", "remaining_time": "5:11:33", "throughput": 1490.08, "total_tokens": 10504384} {"current_steps": 49790, "total_steps": 181800, "loss": 0.0415, "lr": 4.553535760788672e-05, "epoch": 5.477447744774477, "percentage": 27.39, "elapsed_time": "1:57:30", "remaining_time": "5:11:32", "throughput": 1490.08, "total_tokens": 10505440} {"current_steps": 49795, "total_steps": 181800, "loss": 0.0763, "lr": 4.553398867793322e-05, "epoch": 5.477997799779978, "percentage": 27.39, "elapsed_time": "1:57:30", "remaining_time": "5:11:31", "throughput": 1490.09, "total_tokens": 10506496} {"current_steps": 49800, "total_steps": 181800, "loss": 0.0573, "lr": 4.553261955872782e-05, "epoch": 5.478547854785479, "percentage": 27.39, "elapsed_time": "1:57:31", "remaining_time": "5:11:31", "throughput": 1490.1, "total_tokens": 10507616} {"current_steps": 49805, "total_steps": 181800, "loss": 0.0527, "lr": 4.553125025028311e-05, "epoch": 5.479097909790979, "percentage": 27.4, "elapsed_time": "1:57:32", "remaining_time": "5:11:30", "throughput": 1490.11, "total_tokens": 10508704} {"current_steps": 49810, "total_steps": 181800, "loss": 0.0137, "lr": 4.552988075261172e-05, "epoch": 5.47964796479648, "percentage": 27.4, "elapsed_time": "1:57:33", "remaining_time": "5:11:29", "throughput": 1490.11, "total_tokens": 10509728} {"current_steps": 49815, "total_steps": 181800, "loss": 0.0316, "lr": 4.5528511065726267e-05, "epoch": 5.48019801980198, "percentage": 27.4, "elapsed_time": "1:57:33", "remaining_time": "5:11:28", "throughput": 1490.11, "total_tokens": 10510784} {"current_steps": 49820, "total_steps": 181800, "loss": 0.0388, "lr": 4.552714118963938e-05, "epoch": 5.48074807480748, "percentage": 27.4, "elapsed_time": "1:57:34", "remaining_time": "5:11:28", "throughput": 1490.11, "total_tokens": 10511808} {"current_steps": 49825, "total_steps": 181800, "loss": 0.0328, "lr": 4.552577112436368e-05, "epoch": 5.4812981298129815, "percentage": 27.41, "elapsed_time": "1:57:35", "remaining_time": "5:11:27", "throughput": 1490.12, "total_tokens": 10512864} {"current_steps": 49830, "total_steps": 181800, "loss": 0.0158, "lr": 4.5524400869911796e-05, "epoch": 5.481848184818482, "percentage": 27.41, "elapsed_time": "1:57:35", "remaining_time": "5:11:26", "throughput": 1490.12, "total_tokens": 10513920} {"current_steps": 49835, "total_steps": 181800, "loss": 0.0464, "lr": 4.552303042629637e-05, "epoch": 5.482398239823983, "percentage": 27.41, "elapsed_time": "1:57:36", "remaining_time": "5:11:25", "throughput": 1490.13, "total_tokens": 10515040} {"current_steps": 49840, "total_steps": 181800, "loss": 0.0465, "lr": 4.5521659793530006e-05, "epoch": 5.482948294829483, "percentage": 27.41, "elapsed_time": "1:57:37", "remaining_time": "5:11:24", "throughput": 1490.14, "total_tokens": 10516128} {"current_steps": 49845, "total_steps": 181800, "loss": 0.1383, "lr": 4.5520288971625354e-05, "epoch": 5.483498349834983, "percentage": 27.42, "elapsed_time": "1:57:37", "remaining_time": "5:11:24", "throughput": 1490.14, "total_tokens": 10517152} {"current_steps": 49850, "total_steps": 181800, "loss": 0.0937, "lr": 4.551891796059505e-05, "epoch": 5.484048404840484, "percentage": 27.42, "elapsed_time": "1:57:38", "remaining_time": "5:11:23", "throughput": 1490.14, "total_tokens": 10518144} {"current_steps": 49855, "total_steps": 181800, "loss": 0.0082, "lr": 4.551754676045172e-05, "epoch": 5.4845984598459845, "percentage": 27.42, "elapsed_time": "1:57:39", "remaining_time": "5:11:22", "throughput": 1490.14, "total_tokens": 10519168} {"current_steps": 49860, "total_steps": 181800, "loss": 0.0505, "lr": 4.5516175371208e-05, "epoch": 5.485148514851485, "percentage": 27.43, "elapsed_time": "1:57:39", "remaining_time": "5:11:21", "throughput": 1490.15, "total_tokens": 10520256} {"current_steps": 49865, "total_steps": 181800, "loss": 0.0115, "lr": 4.5514803792876556e-05, "epoch": 5.485698569856986, "percentage": 27.43, "elapsed_time": "1:57:40", "remaining_time": "5:11:21", "throughput": 1490.15, "total_tokens": 10521344} {"current_steps": 49870, "total_steps": 181800, "loss": 0.0067, "lr": 4.5513432025469994e-05, "epoch": 5.486248624862486, "percentage": 27.43, "elapsed_time": "1:57:41", "remaining_time": "5:11:20", "throughput": 1490.15, "total_tokens": 10522368} {"current_steps": 49875, "total_steps": 181800, "loss": 0.132, "lr": 4.5512060069000976e-05, "epoch": 5.486798679867987, "percentage": 27.43, "elapsed_time": "1:57:41", "remaining_time": "5:11:19", "throughput": 1490.15, "total_tokens": 10523392} {"current_steps": 49880, "total_steps": 181800, "loss": 0.1468, "lr": 4.5510687923482145e-05, "epoch": 5.487348734873487, "percentage": 27.44, "elapsed_time": "1:57:42", "remaining_time": "5:11:18", "throughput": 1490.17, "total_tokens": 10524512} {"current_steps": 49885, "total_steps": 181800, "loss": 0.0251, "lr": 4.550931558892615e-05, "epoch": 5.4878987898789875, "percentage": 27.44, "elapsed_time": "1:57:43", "remaining_time": "5:11:18", "throughput": 1490.17, "total_tokens": 10525568} {"current_steps": 49890, "total_steps": 181800, "loss": 0.0254, "lr": 4.550794306534563e-05, "epoch": 5.488448844884489, "percentage": 27.44, "elapsed_time": "1:57:44", "remaining_time": "5:11:17", "throughput": 1490.18, "total_tokens": 10526656} {"current_steps": 49895, "total_steps": 181800, "loss": 0.0498, "lr": 4.550657035275323e-05, "epoch": 5.488998899889989, "percentage": 27.44, "elapsed_time": "1:57:44", "remaining_time": "5:11:16", "throughput": 1490.18, "total_tokens": 10527680} {"current_steps": 49900, "total_steps": 181800, "loss": 0.0575, "lr": 4.550519745116162e-05, "epoch": 5.48954895489549, "percentage": 27.45, "elapsed_time": "1:57:45", "remaining_time": "5:11:15", "throughput": 1490.19, "total_tokens": 10528768} {"current_steps": 49905, "total_steps": 181800, "loss": 0.1838, "lr": 4.5503824360583445e-05, "epoch": 5.49009900990099, "percentage": 27.45, "elapsed_time": "1:57:46", "remaining_time": "5:11:15", "throughput": 1490.19, "total_tokens": 10529824} {"current_steps": 49910, "total_steps": 181800, "loss": 0.0201, "lr": 4.550245108103136e-05, "epoch": 5.49064906490649, "percentage": 27.45, "elapsed_time": "1:57:46", "remaining_time": "5:11:14", "throughput": 1490.19, "total_tokens": 10530880} {"current_steps": 49915, "total_steps": 181800, "loss": 0.0368, "lr": 4.550107761251802e-05, "epoch": 5.491199119911991, "percentage": 27.46, "elapsed_time": "1:57:47", "remaining_time": "5:11:13", "throughput": 1490.19, "total_tokens": 10531904} {"current_steps": 49920, "total_steps": 181800, "loss": 0.0411, "lr": 4.5499703955056085e-05, "epoch": 5.491749174917492, "percentage": 27.46, "elapsed_time": "1:57:48", "remaining_time": "5:11:12", "throughput": 1490.2, "total_tokens": 10532960} {"current_steps": 49925, "total_steps": 181800, "loss": 0.0235, "lr": 4.549833010865821e-05, "epoch": 5.492299229922993, "percentage": 27.46, "elapsed_time": "1:57:48", "remaining_time": "5:11:12", "throughput": 1490.2, "total_tokens": 10534016} {"current_steps": 49930, "total_steps": 181800, "loss": 0.0567, "lr": 4.549695607333707e-05, "epoch": 5.492849284928493, "percentage": 27.46, "elapsed_time": "1:57:49", "remaining_time": "5:11:11", "throughput": 1490.21, "total_tokens": 10535104} {"current_steps": 49935, "total_steps": 181800, "loss": 0.0488, "lr": 4.549558184910532e-05, "epoch": 5.493399339933993, "percentage": 27.47, "elapsed_time": "1:57:50", "remaining_time": "5:11:10", "throughput": 1490.21, "total_tokens": 10536096} {"current_steps": 49940, "total_steps": 181800, "loss": 0.0141, "lr": 4.5494207435975625e-05, "epoch": 5.493949394939494, "percentage": 27.47, "elapsed_time": "1:57:50", "remaining_time": "5:11:09", "throughput": 1490.21, "total_tokens": 10537120} {"current_steps": 49945, "total_steps": 181800, "loss": 0.0639, "lr": 4.5492832833960654e-05, "epoch": 5.494499449944994, "percentage": 27.47, "elapsed_time": "1:57:51", "remaining_time": "5:11:09", "throughput": 1490.21, "total_tokens": 10538176} {"current_steps": 49950, "total_steps": 181800, "loss": 0.0145, "lr": 4.549145804307308e-05, "epoch": 5.4950495049504955, "percentage": 27.48, "elapsed_time": "1:57:52", "remaining_time": "5:11:08", "throughput": 1490.22, "total_tokens": 10539296} {"current_steps": 49955, "total_steps": 181800, "loss": 0.0526, "lr": 4.549008306332556e-05, "epoch": 5.495599559955996, "percentage": 27.48, "elapsed_time": "1:57:52", "remaining_time": "5:11:07", "throughput": 1490.23, "total_tokens": 10540352} {"current_steps": 49960, "total_steps": 181800, "loss": 0.0708, "lr": 4.5488707894730785e-05, "epoch": 5.496149614961496, "percentage": 27.48, "elapsed_time": "1:57:53", "remaining_time": "5:11:06", "throughput": 1490.23, "total_tokens": 10541440} {"current_steps": 49965, "total_steps": 181800, "loss": 0.0779, "lr": 4.548733253730142e-05, "epoch": 5.496699669966997, "percentage": 27.48, "elapsed_time": "1:57:54", "remaining_time": "5:11:06", "throughput": 1490.24, "total_tokens": 10542496} {"current_steps": 49970, "total_steps": 181800, "loss": 0.0979, "lr": 4.5485956991050135e-05, "epoch": 5.497249724972497, "percentage": 27.49, "elapsed_time": "1:57:55", "remaining_time": "5:11:05", "throughput": 1490.24, "total_tokens": 10543552} {"current_steps": 49975, "total_steps": 181800, "loss": 0.0161, "lr": 4.548458125598963e-05, "epoch": 5.497799779977997, "percentage": 27.49, "elapsed_time": "1:57:55", "remaining_time": "5:11:04", "throughput": 1490.25, "total_tokens": 10544640} {"current_steps": 49980, "total_steps": 181800, "loss": 0.1062, "lr": 4.548320533213256e-05, "epoch": 5.4983498349834985, "percentage": 27.49, "elapsed_time": "1:57:56", "remaining_time": "5:11:03", "throughput": 1490.25, "total_tokens": 10545632} {"current_steps": 49985, "total_steps": 181800, "loss": 0.0835, "lr": 4.548182921949161e-05, "epoch": 5.498899889988999, "percentage": 27.49, "elapsed_time": "1:57:57", "remaining_time": "5:11:03", "throughput": 1490.26, "total_tokens": 10546752} {"current_steps": 49990, "total_steps": 181800, "loss": 0.021, "lr": 4.548045291807948e-05, "epoch": 5.4994499449945, "percentage": 27.5, "elapsed_time": "1:57:57", "remaining_time": "5:11:02", "throughput": 1490.26, "total_tokens": 10547744} {"current_steps": 49995, "total_steps": 181800, "loss": 0.0369, "lr": 4.547907642790883e-05, "epoch": 5.5, "percentage": 27.5, "elapsed_time": "1:57:58", "remaining_time": "5:11:01", "throughput": 1490.26, "total_tokens": 10548768} {"current_steps": 50000, "total_steps": 181800, "loss": 0.0305, "lr": 4.5477699748992364e-05, "epoch": 5.5005500550055, "percentage": 27.5, "elapsed_time": "1:57:59", "remaining_time": "5:11:00", "throughput": 1490.26, "total_tokens": 10549856} {"current_steps": 50005, "total_steps": 181800, "loss": 0.0984, "lr": 4.547632288134277e-05, "epoch": 5.501100110011001, "percentage": 27.51, "elapsed_time": "1:57:59", "remaining_time": "5:10:59", "throughput": 1490.29, "total_tokens": 10551040} {"current_steps": 50010, "total_steps": 181800, "loss": 0.1045, "lr": 4.547494582497272e-05, "epoch": 5.5016501650165015, "percentage": 27.51, "elapsed_time": "1:58:00", "remaining_time": "5:10:59", "throughput": 1490.3, "total_tokens": 10552160} {"current_steps": 50015, "total_steps": 181800, "loss": 0.0317, "lr": 4.547356857989494e-05, "epoch": 5.502200220022003, "percentage": 27.51, "elapsed_time": "1:58:01", "remaining_time": "5:10:58", "throughput": 1490.3, "total_tokens": 10553216} {"current_steps": 50020, "total_steps": 181800, "loss": 0.011, "lr": 4.547219114612209e-05, "epoch": 5.502750275027503, "percentage": 27.51, "elapsed_time": "1:58:01", "remaining_time": "5:10:57", "throughput": 1490.3, "total_tokens": 10554240} {"current_steps": 50025, "total_steps": 181800, "loss": 0.0053, "lr": 4.547081352366688e-05, "epoch": 5.503300330033003, "percentage": 27.52, "elapsed_time": "1:58:02", "remaining_time": "5:10:56", "throughput": 1490.32, "total_tokens": 10555360} {"current_steps": 50030, "total_steps": 181800, "loss": 0.1303, "lr": 4.546943571254201e-05, "epoch": 5.503850385038504, "percentage": 27.52, "elapsed_time": "1:58:03", "remaining_time": "5:10:56", "throughput": 1490.32, "total_tokens": 10556448} {"current_steps": 50035, "total_steps": 181800, "loss": 0.0215, "lr": 4.546805771276016e-05, "epoch": 5.504400440044004, "percentage": 27.52, "elapsed_time": "1:58:04", "remaining_time": "5:10:55", "throughput": 1490.32, "total_tokens": 10557472} {"current_steps": 50040, "total_steps": 181800, "loss": 0.0078, "lr": 4.5466679524334054e-05, "epoch": 5.5049504950495045, "percentage": 27.52, "elapsed_time": "1:58:04", "remaining_time": "5:10:54", "throughput": 1490.33, "total_tokens": 10558560} {"current_steps": 50045, "total_steps": 181800, "loss": 0.0461, "lr": 4.546530114727638e-05, "epoch": 5.505500550055006, "percentage": 27.53, "elapsed_time": "1:58:05", "remaining_time": "5:10:53", "throughput": 1490.33, "total_tokens": 10559584} {"current_steps": 50050, "total_steps": 181800, "loss": 0.0753, "lr": 4.546392258159985e-05, "epoch": 5.506050605060506, "percentage": 27.53, "elapsed_time": "1:58:06", "remaining_time": "5:10:53", "throughput": 1490.33, "total_tokens": 10560608} {"current_steps": 50055, "total_steps": 181800, "loss": 0.0391, "lr": 4.546254382731716e-05, "epoch": 5.506600660066007, "percentage": 27.53, "elapsed_time": "1:58:06", "remaining_time": "5:10:52", "throughput": 1490.33, "total_tokens": 10561664} {"current_steps": 50060, "total_steps": 181800, "loss": 0.0073, "lr": 4.546116488444102e-05, "epoch": 5.507150715071507, "percentage": 27.54, "elapsed_time": "1:58:07", "remaining_time": "5:10:51", "throughput": 1490.33, "total_tokens": 10562688} {"current_steps": 50065, "total_steps": 181800, "loss": 0.0399, "lr": 4.545978575298415e-05, "epoch": 5.507700770077007, "percentage": 27.54, "elapsed_time": "1:58:08", "remaining_time": "5:10:50", "throughput": 1490.34, "total_tokens": 10563776} {"current_steps": 50070, "total_steps": 181800, "loss": 0.1349, "lr": 4.5458406432959246e-05, "epoch": 5.508250825082508, "percentage": 27.54, "elapsed_time": "1:58:08", "remaining_time": "5:10:50", "throughput": 1490.35, "total_tokens": 10564864} {"current_steps": 50075, "total_steps": 181800, "loss": 0.0303, "lr": 4.545702692437903e-05, "epoch": 5.508800880088009, "percentage": 27.54, "elapsed_time": "1:58:09", "remaining_time": "5:10:49", "throughput": 1490.35, "total_tokens": 10565920} {"current_steps": 50080, "total_steps": 181800, "loss": 0.0201, "lr": 4.545564722725621e-05, "epoch": 5.50935093509351, "percentage": 27.55, "elapsed_time": "1:58:10", "remaining_time": "5:10:48", "throughput": 1490.36, "total_tokens": 10567008} {"current_steps": 50085, "total_steps": 181800, "loss": 0.0383, "lr": 4.545426734160351e-05, "epoch": 5.50990099009901, "percentage": 27.55, "elapsed_time": "1:58:10", "remaining_time": "5:10:47", "throughput": 1490.36, "total_tokens": 10568064} {"current_steps": 50090, "total_steps": 181800, "loss": 0.0248, "lr": 4.5452887267433635e-05, "epoch": 5.51045104510451, "percentage": 27.55, "elapsed_time": "1:58:11", "remaining_time": "5:10:47", "throughput": 1490.37, "total_tokens": 10569152} {"current_steps": 50095, "total_steps": 181800, "loss": 0.0265, "lr": 4.545150700475932e-05, "epoch": 5.511001100110011, "percentage": 27.56, "elapsed_time": "1:58:12", "remaining_time": "5:10:46", "throughput": 1490.38, "total_tokens": 10570208} {"current_steps": 50100, "total_steps": 181800, "loss": 0.1296, "lr": 4.5450126553593275e-05, "epoch": 5.511551155115511, "percentage": 27.56, "elapsed_time": "1:58:13", "remaining_time": "5:10:45", "throughput": 1490.38, "total_tokens": 10571296} {"current_steps": 50105, "total_steps": 181800, "loss": 0.0262, "lr": 4.544874591394822e-05, "epoch": 5.512101210121012, "percentage": 27.56, "elapsed_time": "1:58:13", "remaining_time": "5:10:44", "throughput": 1490.38, "total_tokens": 10572320} {"current_steps": 50110, "total_steps": 181800, "loss": 0.057, "lr": 4.54473650858369e-05, "epoch": 5.512651265126513, "percentage": 27.56, "elapsed_time": "1:58:14", "remaining_time": "5:10:44", "throughput": 1490.38, "total_tokens": 10573376} {"current_steps": 50115, "total_steps": 181800, "loss": 0.0477, "lr": 4.5445984069272016e-05, "epoch": 5.513201320132013, "percentage": 27.57, "elapsed_time": "1:58:15", "remaining_time": "5:10:43", "throughput": 1490.39, "total_tokens": 10574432} {"current_steps": 50120, "total_steps": 181800, "loss": 0.0588, "lr": 4.5444602864266314e-05, "epoch": 5.513751375137514, "percentage": 27.57, "elapsed_time": "1:58:15", "remaining_time": "5:10:42", "throughput": 1490.4, "total_tokens": 10575520} {"current_steps": 50125, "total_steps": 181800, "loss": 0.0427, "lr": 4.544322147083252e-05, "epoch": 5.514301430143014, "percentage": 27.57, "elapsed_time": "1:58:16", "remaining_time": "5:10:41", "throughput": 1490.39, "total_tokens": 10576544} {"current_steps": 50130, "total_steps": 181800, "loss": 0.1083, "lr": 4.5441839888983354e-05, "epoch": 5.514851485148515, "percentage": 27.57, "elapsed_time": "1:58:17", "remaining_time": "5:10:41", "throughput": 1490.39, "total_tokens": 10577536} {"current_steps": 50135, "total_steps": 181800, "loss": 0.0151, "lr": 4.544045811873157e-05, "epoch": 5.5154015401540155, "percentage": 27.58, "elapsed_time": "1:58:17", "remaining_time": "5:10:40", "throughput": 1490.39, "total_tokens": 10578560} {"current_steps": 50140, "total_steps": 181800, "loss": 0.0342, "lr": 4.543907616008988e-05, "epoch": 5.515951595159516, "percentage": 27.58, "elapsed_time": "1:58:18", "remaining_time": "5:10:39", "throughput": 1490.39, "total_tokens": 10579584} {"current_steps": 50145, "total_steps": 181800, "loss": 0.0204, "lr": 4.5437694013071044e-05, "epoch": 5.516501650165017, "percentage": 27.58, "elapsed_time": "1:58:19", "remaining_time": "5:10:38", "throughput": 1490.39, "total_tokens": 10580608} {"current_steps": 50150, "total_steps": 181800, "loss": 0.025, "lr": 4.543631167768778e-05, "epoch": 5.517051705170517, "percentage": 27.59, "elapsed_time": "1:58:19", "remaining_time": "5:10:38", "throughput": 1490.39, "total_tokens": 10581632} {"current_steps": 50155, "total_steps": 181800, "loss": 0.0416, "lr": 4.5434929153952846e-05, "epoch": 5.517601760176017, "percentage": 27.59, "elapsed_time": "1:58:20", "remaining_time": "5:10:37", "throughput": 1490.39, "total_tokens": 10582688} {"current_steps": 50160, "total_steps": 181800, "loss": 0.0217, "lr": 4.5433546441878966e-05, "epoch": 5.518151815181518, "percentage": 27.59, "elapsed_time": "1:58:21", "remaining_time": "5:10:36", "throughput": 1490.4, "total_tokens": 10583744} {"current_steps": 50165, "total_steps": 181800, "loss": 0.0431, "lr": 4.54321635414789e-05, "epoch": 5.5187018701870185, "percentage": 27.59, "elapsed_time": "1:58:21", "remaining_time": "5:10:35", "throughput": 1490.4, "total_tokens": 10584800} {"current_steps": 50170, "total_steps": 181800, "loss": 0.095, "lr": 4.5430780452765386e-05, "epoch": 5.51925192519252, "percentage": 27.6, "elapsed_time": "1:58:22", "remaining_time": "5:10:35", "throughput": 1490.41, "total_tokens": 10585888} {"current_steps": 50175, "total_steps": 181800, "loss": 0.0274, "lr": 4.5429397175751165e-05, "epoch": 5.51980198019802, "percentage": 27.6, "elapsed_time": "1:58:23", "remaining_time": "5:10:34", "throughput": 1490.42, "total_tokens": 10587008} {"current_steps": 50180, "total_steps": 181800, "loss": 0.0114, "lr": 4.5428013710449e-05, "epoch": 5.52035203520352, "percentage": 27.6, "elapsed_time": "1:58:24", "remaining_time": "5:10:33", "throughput": 1490.43, "total_tokens": 10588064} {"current_steps": 50185, "total_steps": 181800, "loss": 0.1525, "lr": 4.542663005687164e-05, "epoch": 5.520902090209021, "percentage": 27.6, "elapsed_time": "1:58:24", "remaining_time": "5:10:32", "throughput": 1490.44, "total_tokens": 10589184} {"current_steps": 50190, "total_steps": 181800, "loss": 0.0161, "lr": 4.542524621503182e-05, "epoch": 5.521452145214521, "percentage": 27.61, "elapsed_time": "1:58:25", "remaining_time": "5:10:32", "throughput": 1490.44, "total_tokens": 10590240} {"current_steps": 50195, "total_steps": 181800, "loss": 0.0446, "lr": 4.5423862184942326e-05, "epoch": 5.522002200220022, "percentage": 27.61, "elapsed_time": "1:58:26", "remaining_time": "5:10:31", "throughput": 1490.45, "total_tokens": 10591296} {"current_steps": 50200, "total_steps": 181800, "loss": 0.0926, "lr": 4.542247796661587e-05, "epoch": 5.522552255225523, "percentage": 27.61, "elapsed_time": "1:58:26", "remaining_time": "5:10:30", "throughput": 1490.46, "total_tokens": 10592416} {"current_steps": 50205, "total_steps": 181800, "loss": 0.0763, "lr": 4.542109356006525e-05, "epoch": 5.523102310231023, "percentage": 27.62, "elapsed_time": "1:58:27", "remaining_time": "5:10:29", "throughput": 1490.46, "total_tokens": 10593440} {"current_steps": 50210, "total_steps": 181800, "loss": 0.0563, "lr": 4.541970896530321e-05, "epoch": 5.523652365236524, "percentage": 27.62, "elapsed_time": "1:58:28", "remaining_time": "5:10:29", "throughput": 1490.47, "total_tokens": 10594528} {"current_steps": 50215, "total_steps": 181800, "loss": 0.0723, "lr": 4.541832418234251e-05, "epoch": 5.524202420242024, "percentage": 27.62, "elapsed_time": "1:58:28", "remaining_time": "5:10:28", "throughput": 1490.47, "total_tokens": 10595584} {"current_steps": 50220, "total_steps": 181800, "loss": 0.0214, "lr": 4.541693921119591e-05, "epoch": 5.524752475247524, "percentage": 27.62, "elapsed_time": "1:58:29", "remaining_time": "5:10:27", "throughput": 1490.47, "total_tokens": 10596608} {"current_steps": 50225, "total_steps": 181800, "loss": 0.0605, "lr": 4.5415554051876174e-05, "epoch": 5.525302530253025, "percentage": 27.63, "elapsed_time": "1:58:30", "remaining_time": "5:10:26", "throughput": 1490.47, "total_tokens": 10597632} {"current_steps": 50230, "total_steps": 181800, "loss": 0.0058, "lr": 4.541416870439608e-05, "epoch": 5.525852585258526, "percentage": 27.63, "elapsed_time": "1:58:30", "remaining_time": "5:10:26", "throughput": 1490.47, "total_tokens": 10598656} {"current_steps": 50235, "total_steps": 181800, "loss": 0.0301, "lr": 4.541278316876839e-05, "epoch": 5.526402640264027, "percentage": 27.63, "elapsed_time": "1:58:31", "remaining_time": "5:10:25", "throughput": 1490.47, "total_tokens": 10599712} {"current_steps": 50240, "total_steps": 181800, "loss": 0.0091, "lr": 4.5411397445005864e-05, "epoch": 5.526952695269527, "percentage": 27.63, "elapsed_time": "1:58:32", "remaining_time": "5:10:24", "throughput": 1490.47, "total_tokens": 10600736} {"current_steps": 50245, "total_steps": 181800, "loss": 0.0664, "lr": 4.541001153312129e-05, "epoch": 5.527502750275027, "percentage": 27.64, "elapsed_time": "1:58:33", "remaining_time": "5:10:23", "throughput": 1490.48, "total_tokens": 10601824} {"current_steps": 50250, "total_steps": 181800, "loss": 0.0339, "lr": 4.540862543312743e-05, "epoch": 5.528052805280528, "percentage": 27.64, "elapsed_time": "1:58:33", "remaining_time": "5:10:23", "throughput": 1490.49, "total_tokens": 10602880} {"current_steps": 50255, "total_steps": 181800, "loss": 0.0688, "lr": 4.540723914503706e-05, "epoch": 5.528602860286028, "percentage": 27.64, "elapsed_time": "1:58:34", "remaining_time": "5:10:22", "throughput": 1490.48, "total_tokens": 10603872} {"current_steps": 50260, "total_steps": 181800, "loss": 0.1069, "lr": 4.5405852668862955e-05, "epoch": 5.5291529152915295, "percentage": 27.65, "elapsed_time": "1:58:35", "remaining_time": "5:10:21", "throughput": 1490.48, "total_tokens": 10604896} {"current_steps": 50265, "total_steps": 181800, "loss": 0.0285, "lr": 4.540446600461791e-05, "epoch": 5.52970297029703, "percentage": 27.65, "elapsed_time": "1:58:35", "remaining_time": "5:10:20", "throughput": 1490.48, "total_tokens": 10605952} {"current_steps": 50270, "total_steps": 181800, "loss": 0.0258, "lr": 4.5403079152314686e-05, "epoch": 5.53025302530253, "percentage": 27.65, "elapsed_time": "1:58:36", "remaining_time": "5:10:20", "throughput": 1490.48, "total_tokens": 10606976} {"current_steps": 50275, "total_steps": 181800, "loss": 0.0678, "lr": 4.5401692111966074e-05, "epoch": 5.530803080308031, "percentage": 27.65, "elapsed_time": "1:58:37", "remaining_time": "5:10:19", "throughput": 1490.49, "total_tokens": 10608064} {"current_steps": 50280, "total_steps": 181800, "loss": 0.048, "lr": 4.5400304883584856e-05, "epoch": 5.531353135313531, "percentage": 27.66, "elapsed_time": "1:58:37", "remaining_time": "5:10:18", "throughput": 1490.5, "total_tokens": 10609152} {"current_steps": 50285, "total_steps": 181800, "loss": 0.0163, "lr": 4.539891746718381e-05, "epoch": 5.531903190319031, "percentage": 27.66, "elapsed_time": "1:58:38", "remaining_time": "5:10:17", "throughput": 1490.51, "total_tokens": 10610240} {"current_steps": 50290, "total_steps": 181800, "loss": 0.0145, "lr": 4.539752986277574e-05, "epoch": 5.5324532453245325, "percentage": 27.66, "elapsed_time": "1:58:39", "remaining_time": "5:10:16", "throughput": 1490.52, "total_tokens": 10611360} {"current_steps": 50295, "total_steps": 181800, "loss": 0.0405, "lr": 4.539614207037342e-05, "epoch": 5.533003300330033, "percentage": 27.67, "elapsed_time": "1:58:39", "remaining_time": "5:10:16", "throughput": 1490.52, "total_tokens": 10612384} {"current_steps": 50300, "total_steps": 181800, "loss": 0.1041, "lr": 4.539475408998964e-05, "epoch": 5.533553355335534, "percentage": 27.67, "elapsed_time": "1:58:40", "remaining_time": "5:10:15", "throughput": 1490.53, "total_tokens": 10613440} {"current_steps": 50305, "total_steps": 181800, "loss": 0.0277, "lr": 4.539336592163721e-05, "epoch": 5.534103410341034, "percentage": 27.67, "elapsed_time": "1:58:41", "remaining_time": "5:10:14", "throughput": 1490.54, "total_tokens": 10614528} {"current_steps": 50310, "total_steps": 181800, "loss": 0.036, "lr": 4.5391977565328904e-05, "epoch": 5.534653465346535, "percentage": 27.67, "elapsed_time": "1:58:41", "remaining_time": "5:10:13", "throughput": 1490.54, "total_tokens": 10615616} {"current_steps": 50315, "total_steps": 181800, "loss": 0.0098, "lr": 4.5390589021077536e-05, "epoch": 5.535203520352035, "percentage": 27.68, "elapsed_time": "1:58:42", "remaining_time": "5:10:13", "throughput": 1490.55, "total_tokens": 10616704} {"current_steps": 50320, "total_steps": 181800, "loss": 0.1342, "lr": 4.5389200288895876e-05, "epoch": 5.5357535753575355, "percentage": 27.68, "elapsed_time": "1:58:43", "remaining_time": "5:10:12", "throughput": 1490.57, "total_tokens": 10617856} {"current_steps": 50325, "total_steps": 181800, "loss": 0.0071, "lr": 4.538781136879675e-05, "epoch": 5.536303630363037, "percentage": 27.68, "elapsed_time": "1:58:44", "remaining_time": "5:10:11", "throughput": 1490.58, "total_tokens": 10618912} {"current_steps": 50330, "total_steps": 181800, "loss": 0.0125, "lr": 4.538642226079295e-05, "epoch": 5.536853685368537, "percentage": 27.68, "elapsed_time": "1:58:44", "remaining_time": "5:10:10", "throughput": 1490.58, "total_tokens": 10619936} {"current_steps": 50335, "total_steps": 181800, "loss": 0.008, "lr": 4.538503296489728e-05, "epoch": 5.537403740374037, "percentage": 27.69, "elapsed_time": "1:58:45", "remaining_time": "5:10:10", "throughput": 1490.57, "total_tokens": 10620960} {"current_steps": 50340, "total_steps": 181800, "loss": 0.0463, "lr": 4.538364348112254e-05, "epoch": 5.537953795379538, "percentage": 27.69, "elapsed_time": "1:58:46", "remaining_time": "5:10:09", "throughput": 1490.58, "total_tokens": 10622048} {"current_steps": 50345, "total_steps": 181800, "loss": 0.0115, "lr": 4.538225380948154e-05, "epoch": 5.538503850385038, "percentage": 27.69, "elapsed_time": "1:58:46", "remaining_time": "5:10:08", "throughput": 1490.58, "total_tokens": 10623072} {"current_steps": 50350, "total_steps": 181800, "loss": 0.1325, "lr": 4.538086394998709e-05, "epoch": 5.539053905390539, "percentage": 27.7, "elapsed_time": "1:58:47", "remaining_time": "5:10:07", "throughput": 1490.58, "total_tokens": 10624064} {"current_steps": 50355, "total_steps": 181800, "loss": 0.1247, "lr": 4.537947390265199e-05, "epoch": 5.53960396039604, "percentage": 27.7, "elapsed_time": "1:58:48", "remaining_time": "5:10:07", "throughput": 1490.58, "total_tokens": 10625120} {"current_steps": 50360, "total_steps": 181800, "loss": 0.0423, "lr": 4.537808366748906e-05, "epoch": 5.54015401540154, "percentage": 27.7, "elapsed_time": "1:58:48", "remaining_time": "5:10:06", "throughput": 1490.58, "total_tokens": 10626144} {"current_steps": 50365, "total_steps": 181800, "loss": 0.1178, "lr": 4.537669324451111e-05, "epoch": 5.540704070407041, "percentage": 27.7, "elapsed_time": "1:58:49", "remaining_time": "5:10:05", "throughput": 1490.58, "total_tokens": 10627168} {"current_steps": 50370, "total_steps": 181800, "loss": 0.0399, "lr": 4.537530263373097e-05, "epoch": 5.541254125412541, "percentage": 27.71, "elapsed_time": "1:58:50", "remaining_time": "5:10:04", "throughput": 1490.58, "total_tokens": 10628192} {"current_steps": 50375, "total_steps": 181800, "loss": 0.0516, "lr": 4.537391183516142e-05, "epoch": 5.541804180418042, "percentage": 27.71, "elapsed_time": "1:58:50", "remaining_time": "5:10:04", "throughput": 1490.57, "total_tokens": 10629152} {"current_steps": 50380, "total_steps": 181800, "loss": 0.038, "lr": 4.5372520848815316e-05, "epoch": 5.542354235423542, "percentage": 27.71, "elapsed_time": "1:58:51", "remaining_time": "5:10:03", "throughput": 1490.59, "total_tokens": 10630304} {"current_steps": 50385, "total_steps": 181800, "loss": 0.1454, "lr": 4.537112967470546e-05, "epoch": 5.542904290429043, "percentage": 27.71, "elapsed_time": "1:58:52", "remaining_time": "5:10:02", "throughput": 1490.59, "total_tokens": 10631360} {"current_steps": 50390, "total_steps": 181800, "loss": 0.0048, "lr": 4.536973831284468e-05, "epoch": 5.543454345434544, "percentage": 27.72, "elapsed_time": "1:58:52", "remaining_time": "5:10:01", "throughput": 1490.59, "total_tokens": 10632352} {"current_steps": 50395, "total_steps": 181800, "loss": 0.0241, "lr": 4.5368346763245786e-05, "epoch": 5.544004400440044, "percentage": 27.72, "elapsed_time": "1:58:53", "remaining_time": "5:10:01", "throughput": 1490.59, "total_tokens": 10633440} {"current_steps": 50400, "total_steps": 181800, "loss": 0.2434, "lr": 4.536695502592162e-05, "epoch": 5.544554455445544, "percentage": 27.72, "elapsed_time": "1:58:54", "remaining_time": "5:10:00", "throughput": 1490.61, "total_tokens": 10634560} {"current_steps": 50405, "total_steps": 181800, "loss": 0.0306, "lr": 4.5365563100885e-05, "epoch": 5.545104510451045, "percentage": 27.73, "elapsed_time": "1:58:55", "remaining_time": "5:09:59", "throughput": 1490.61, "total_tokens": 10635616} {"current_steps": 50410, "total_steps": 181800, "loss": 0.015, "lr": 4.536417098814877e-05, "epoch": 5.5456545654565454, "percentage": 27.73, "elapsed_time": "1:58:55", "remaining_time": "5:09:58", "throughput": 1490.61, "total_tokens": 10636672} {"current_steps": 50415, "total_steps": 181800, "loss": 0.0178, "lr": 4.5362778687725733e-05, "epoch": 5.5462046204620465, "percentage": 27.73, "elapsed_time": "1:58:56", "remaining_time": "5:09:58", "throughput": 1490.63, "total_tokens": 10637792} {"current_steps": 50420, "total_steps": 181800, "loss": 0.0192, "lr": 4.536138619962874e-05, "epoch": 5.546754675467547, "percentage": 27.73, "elapsed_time": "1:58:57", "remaining_time": "5:09:57", "throughput": 1490.63, "total_tokens": 10638816} {"current_steps": 50425, "total_steps": 181800, "loss": 0.069, "lr": 4.535999352387062e-05, "epoch": 5.547304730473047, "percentage": 27.74, "elapsed_time": "1:58:57", "remaining_time": "5:09:56", "throughput": 1490.63, "total_tokens": 10639904} {"current_steps": 50430, "total_steps": 181800, "loss": 0.097, "lr": 4.535860066046421e-05, "epoch": 5.547854785478548, "percentage": 27.74, "elapsed_time": "1:58:58", "remaining_time": "5:09:55", "throughput": 1490.64, "total_tokens": 10640992} {"current_steps": 50435, "total_steps": 181800, "loss": 0.0454, "lr": 4.535720760942235e-05, "epoch": 5.548404840484048, "percentage": 27.74, "elapsed_time": "1:58:59", "remaining_time": "5:09:55", "throughput": 1490.64, "total_tokens": 10642016} {"current_steps": 50440, "total_steps": 181800, "loss": 0.0587, "lr": 4.535581437075787e-05, "epoch": 5.548954895489549, "percentage": 27.74, "elapsed_time": "1:58:59", "remaining_time": "5:09:54", "throughput": 1490.65, "total_tokens": 10643072} {"current_steps": 50445, "total_steps": 181800, "loss": 0.0511, "lr": 4.535442094448362e-05, "epoch": 5.5495049504950495, "percentage": 27.75, "elapsed_time": "1:59:00", "remaining_time": "5:09:53", "throughput": 1490.65, "total_tokens": 10644096} {"current_steps": 50450, "total_steps": 181800, "loss": 0.0428, "lr": 4.535302733061244e-05, "epoch": 5.55005500550055, "percentage": 27.75, "elapsed_time": "1:59:01", "remaining_time": "5:09:52", "throughput": 1490.65, "total_tokens": 10645152} {"current_steps": 50455, "total_steps": 181800, "loss": 0.0431, "lr": 4.535163352915717e-05, "epoch": 5.550605060506051, "percentage": 27.75, "elapsed_time": "1:59:01", "remaining_time": "5:09:52", "throughput": 1490.66, "total_tokens": 10646240} {"current_steps": 50460, "total_steps": 181800, "loss": 0.0703, "lr": 4.535023954013066e-05, "epoch": 5.551155115511551, "percentage": 27.76, "elapsed_time": "1:59:02", "remaining_time": "5:09:51", "throughput": 1490.66, "total_tokens": 10647264} {"current_steps": 50465, "total_steps": 181800, "loss": 0.042, "lr": 4.534884536354575e-05, "epoch": 5.551705170517051, "percentage": 27.76, "elapsed_time": "1:59:03", "remaining_time": "5:09:50", "throughput": 1490.68, "total_tokens": 10648384} {"current_steps": 50470, "total_steps": 181800, "loss": 0.0542, "lr": 4.5347450999415315e-05, "epoch": 5.552255225522552, "percentage": 27.76, "elapsed_time": "1:59:04", "remaining_time": "5:09:49", "throughput": 1490.68, "total_tokens": 10649408} {"current_steps": 50475, "total_steps": 181800, "loss": 0.0154, "lr": 4.5346056447752176e-05, "epoch": 5.552805280528053, "percentage": 27.76, "elapsed_time": "1:59:04", "remaining_time": "5:09:48", "throughput": 1490.69, "total_tokens": 10650496} {"current_steps": 50480, "total_steps": 181800, "loss": 0.0307, "lr": 4.53446617085692e-05, "epoch": 5.553355335533554, "percentage": 27.77, "elapsed_time": "1:59:05", "remaining_time": "5:09:48", "throughput": 1490.69, "total_tokens": 10651552} {"current_steps": 50485, "total_steps": 181800, "loss": 0.0596, "lr": 4.534326678187924e-05, "epoch": 5.553905390539054, "percentage": 27.77, "elapsed_time": "1:59:06", "remaining_time": "5:09:47", "throughput": 1490.68, "total_tokens": 10652512} {"current_steps": 50490, "total_steps": 181800, "loss": 0.0357, "lr": 4.534187166769515e-05, "epoch": 5.554455445544555, "percentage": 27.77, "elapsed_time": "1:59:06", "remaining_time": "5:09:46", "throughput": 1490.69, "total_tokens": 10653600} {"current_steps": 50495, "total_steps": 181800, "loss": 0.0634, "lr": 4.5340476366029796e-05, "epoch": 5.555005500550055, "percentage": 27.78, "elapsed_time": "1:59:07", "remaining_time": "5:09:45", "throughput": 1490.68, "total_tokens": 10654592} {"current_steps": 50500, "total_steps": 181800, "loss": 0.0243, "lr": 4.533908087689602e-05, "epoch": 5.555555555555555, "percentage": 27.78, "elapsed_time": "1:59:08", "remaining_time": "5:09:45", "throughput": 1490.69, "total_tokens": 10655648} {"current_steps": 50505, "total_steps": 181800, "loss": 0.0341, "lr": 4.533768520030671e-05, "epoch": 5.5561056105610565, "percentage": 27.78, "elapsed_time": "1:59:08", "remaining_time": "5:09:44", "throughput": 1490.71, "total_tokens": 10656832} {"current_steps": 50510, "total_steps": 181800, "loss": 0.0469, "lr": 4.53362893362747e-05, "epoch": 5.556655665566557, "percentage": 27.78, "elapsed_time": "1:59:09", "remaining_time": "5:09:43", "throughput": 1490.71, "total_tokens": 10657856} {"current_steps": 50515, "total_steps": 181800, "loss": 0.0329, "lr": 4.5334893284812876e-05, "epoch": 5.557205720572057, "percentage": 27.79, "elapsed_time": "1:59:10", "remaining_time": "5:09:42", "throughput": 1490.71, "total_tokens": 10658880} {"current_steps": 50520, "total_steps": 181800, "loss": 0.0225, "lr": 4.5333497045934096e-05, "epoch": 5.557755775577558, "percentage": 27.79, "elapsed_time": "1:59:10", "remaining_time": "5:09:42", "throughput": 1490.72, "total_tokens": 10659936} {"current_steps": 50525, "total_steps": 181800, "loss": 0.0868, "lr": 4.533210061965123e-05, "epoch": 5.558305830583058, "percentage": 27.79, "elapsed_time": "1:59:11", "remaining_time": "5:09:41", "throughput": 1490.71, "total_tokens": 10660960} {"current_steps": 50530, "total_steps": 181800, "loss": 0.0372, "lr": 4.533070400597715e-05, "epoch": 5.558855885588558, "percentage": 27.79, "elapsed_time": "1:59:12", "remaining_time": "5:09:40", "throughput": 1490.72, "total_tokens": 10662016} {"current_steps": 50535, "total_steps": 181800, "loss": 0.0894, "lr": 4.532930720492473e-05, "epoch": 5.5594059405940595, "percentage": 27.8, "elapsed_time": "1:59:12", "remaining_time": "5:09:39", "throughput": 1490.73, "total_tokens": 10663136} {"current_steps": 50540, "total_steps": 181800, "loss": 0.0109, "lr": 4.532791021650684e-05, "epoch": 5.55995599559956, "percentage": 27.8, "elapsed_time": "1:59:13", "remaining_time": "5:09:39", "throughput": 1490.74, "total_tokens": 10664224} {"current_steps": 50545, "total_steps": 181800, "loss": 0.0234, "lr": 4.532651304073636e-05, "epoch": 5.560506050605061, "percentage": 27.8, "elapsed_time": "1:59:14", "remaining_time": "5:09:38", "throughput": 1490.75, "total_tokens": 10665312} {"current_steps": 50550, "total_steps": 181800, "loss": 0.0239, "lr": 4.532511567762615e-05, "epoch": 5.561056105610561, "percentage": 27.81, "elapsed_time": "1:59:15", "remaining_time": "5:09:37", "throughput": 1490.75, "total_tokens": 10666368} {"current_steps": 50555, "total_steps": 181800, "loss": 0.1118, "lr": 4.5323718127189116e-05, "epoch": 5.561606160616062, "percentage": 27.81, "elapsed_time": "1:59:15", "remaining_time": "5:09:36", "throughput": 1490.76, "total_tokens": 10667456} {"current_steps": 50560, "total_steps": 181800, "loss": 0.0494, "lr": 4.532232038943811e-05, "epoch": 5.562156215621562, "percentage": 27.81, "elapsed_time": "1:59:16", "remaining_time": "5:09:36", "throughput": 1490.77, "total_tokens": 10668544} {"current_steps": 50565, "total_steps": 181800, "loss": 0.0192, "lr": 4.532092246438604e-05, "epoch": 5.5627062706270625, "percentage": 27.81, "elapsed_time": "1:59:17", "remaining_time": "5:09:35", "throughput": 1490.77, "total_tokens": 10669568} {"current_steps": 50570, "total_steps": 181800, "loss": 0.0359, "lr": 4.531952435204577e-05, "epoch": 5.563256325632564, "percentage": 27.82, "elapsed_time": "1:59:17", "remaining_time": "5:09:34", "throughput": 1490.77, "total_tokens": 10670592} {"current_steps": 50575, "total_steps": 181800, "loss": 0.0396, "lr": 4.53181260524302e-05, "epoch": 5.563806380638064, "percentage": 27.82, "elapsed_time": "1:59:18", "remaining_time": "5:09:33", "throughput": 1490.77, "total_tokens": 10671648} {"current_steps": 50580, "total_steps": 181800, "loss": 0.1386, "lr": 4.531672756555221e-05, "epoch": 5.564356435643564, "percentage": 27.82, "elapsed_time": "1:59:19", "remaining_time": "5:09:33", "throughput": 1490.77, "total_tokens": 10672672} {"current_steps": 50585, "total_steps": 181800, "loss": 0.2194, "lr": 4.531532889142469e-05, "epoch": 5.564906490649065, "percentage": 27.82, "elapsed_time": "1:59:19", "remaining_time": "5:09:32", "throughput": 1490.77, "total_tokens": 10673728} {"current_steps": 50590, "total_steps": 181800, "loss": 0.0364, "lr": 4.531393003006054e-05, "epoch": 5.565456545654565, "percentage": 27.83, "elapsed_time": "1:59:20", "remaining_time": "5:09:31", "throughput": 1490.78, "total_tokens": 10674784} {"current_steps": 50595, "total_steps": 181800, "loss": 0.1383, "lr": 4.531253098147263e-05, "epoch": 5.566006600660066, "percentage": 27.83, "elapsed_time": "1:59:21", "remaining_time": "5:09:30", "throughput": 1490.77, "total_tokens": 10675776} {"current_steps": 50600, "total_steps": 181800, "loss": 0.0101, "lr": 4.531113174567389e-05, "epoch": 5.566556655665567, "percentage": 27.83, "elapsed_time": "1:59:21", "remaining_time": "5:09:30", "throughput": 1490.78, "total_tokens": 10676896} {"current_steps": 50605, "total_steps": 181800, "loss": 0.0302, "lr": 4.530973232267717e-05, "epoch": 5.567106710671067, "percentage": 27.84, "elapsed_time": "1:59:22", "remaining_time": "5:09:29", "throughput": 1490.79, "total_tokens": 10677952} {"current_steps": 50610, "total_steps": 181800, "loss": 0.0266, "lr": 4.5308332712495406e-05, "epoch": 5.567656765676568, "percentage": 27.84, "elapsed_time": "1:59:23", "remaining_time": "5:09:28", "throughput": 1490.79, "total_tokens": 10678976} {"current_steps": 50615, "total_steps": 181800, "loss": 0.1105, "lr": 4.530693291514149e-05, "epoch": 5.568206820682068, "percentage": 27.84, "elapsed_time": "1:59:23", "remaining_time": "5:09:27", "throughput": 1490.81, "total_tokens": 10680128} {"current_steps": 50620, "total_steps": 181800, "loss": 0.0135, "lr": 4.5305532930628305e-05, "epoch": 5.568756875687569, "percentage": 27.84, "elapsed_time": "1:59:24", "remaining_time": "5:09:27", "throughput": 1490.8, "total_tokens": 10681088} {"current_steps": 50625, "total_steps": 181800, "loss": 0.1014, "lr": 4.530413275896877e-05, "epoch": 5.569306930693069, "percentage": 27.85, "elapsed_time": "1:59:25", "remaining_time": "5:09:26", "throughput": 1490.8, "total_tokens": 10682144} {"current_steps": 50630, "total_steps": 181800, "loss": 0.0074, "lr": 4.5302732400175786e-05, "epoch": 5.56985698569857, "percentage": 27.85, "elapsed_time": "1:59:26", "remaining_time": "5:09:25", "throughput": 1490.8, "total_tokens": 10683136} {"current_steps": 50635, "total_steps": 181800, "loss": 0.103, "lr": 4.530133185426226e-05, "epoch": 5.570407040704071, "percentage": 27.85, "elapsed_time": "1:59:26", "remaining_time": "5:09:24", "throughput": 1490.8, "total_tokens": 10684192} {"current_steps": 50640, "total_steps": 181800, "loss": 0.0245, "lr": 4.52999311212411e-05, "epoch": 5.570957095709571, "percentage": 27.85, "elapsed_time": "1:59:27", "remaining_time": "5:09:24", "throughput": 1490.81, "total_tokens": 10685280} {"current_steps": 50645, "total_steps": 181800, "loss": 0.0617, "lr": 4.5298530201125224e-05, "epoch": 5.571507150715071, "percentage": 27.86, "elapsed_time": "1:59:28", "remaining_time": "5:09:23", "throughput": 1490.82, "total_tokens": 10686368} {"current_steps": 50650, "total_steps": 181800, "loss": 0.0177, "lr": 4.529712909392753e-05, "epoch": 5.572057205720572, "percentage": 27.86, "elapsed_time": "1:59:28", "remaining_time": "5:09:22", "throughput": 1490.81, "total_tokens": 10687360} {"current_steps": 50655, "total_steps": 181800, "loss": 0.0414, "lr": 4.529572779966093e-05, "epoch": 5.572607260726072, "percentage": 27.86, "elapsed_time": "1:59:29", "remaining_time": "5:09:21", "throughput": 1490.81, "total_tokens": 10688384} {"current_steps": 50660, "total_steps": 181800, "loss": 0.0214, "lr": 4.5294326318338355e-05, "epoch": 5.5731573157315735, "percentage": 27.87, "elapsed_time": "1:59:30", "remaining_time": "5:09:21", "throughput": 1490.81, "total_tokens": 10689408} {"current_steps": 50665, "total_steps": 181800, "loss": 0.0204, "lr": 4.5292924649972704e-05, "epoch": 5.573707370737074, "percentage": 27.87, "elapsed_time": "1:59:30", "remaining_time": "5:09:20", "throughput": 1490.8, "total_tokens": 10690400} {"current_steps": 50670, "total_steps": 181800, "loss": 0.048, "lr": 4.5291522794576914e-05, "epoch": 5.574257425742574, "percentage": 27.87, "elapsed_time": "1:59:31", "remaining_time": "5:09:19", "throughput": 1490.81, "total_tokens": 10691456} {"current_steps": 50675, "total_steps": 181800, "loss": 0.0867, "lr": 4.5290120752163885e-05, "epoch": 5.574807480748075, "percentage": 27.87, "elapsed_time": "1:59:32", "remaining_time": "5:09:18", "throughput": 1490.81, "total_tokens": 10692480} {"current_steps": 50680, "total_steps": 181800, "loss": 0.0211, "lr": 4.5288718522746554e-05, "epoch": 5.575357535753575, "percentage": 27.88, "elapsed_time": "1:59:32", "remaining_time": "5:09:17", "throughput": 1490.82, "total_tokens": 10693568} {"current_steps": 50685, "total_steps": 181800, "loss": 0.0371, "lr": 4.528731610633784e-05, "epoch": 5.575907590759076, "percentage": 27.88, "elapsed_time": "1:59:33", "remaining_time": "5:09:17", "throughput": 1490.81, "total_tokens": 10694560} {"current_steps": 50690, "total_steps": 181800, "loss": 0.0041, "lr": 4.528591350295067e-05, "epoch": 5.5764576457645765, "percentage": 27.88, "elapsed_time": "1:59:34", "remaining_time": "5:09:16", "throughput": 1490.82, "total_tokens": 10695616} {"current_steps": 50695, "total_steps": 181800, "loss": 0.0333, "lr": 4.528451071259796e-05, "epoch": 5.577007700770077, "percentage": 27.89, "elapsed_time": "1:59:35", "remaining_time": "5:09:15", "throughput": 1490.82, "total_tokens": 10696672} {"current_steps": 50700, "total_steps": 181800, "loss": 0.1267, "lr": 4.5283107735292665e-05, "epoch": 5.577557755775578, "percentage": 27.89, "elapsed_time": "1:59:35", "remaining_time": "5:09:14", "throughput": 1490.82, "total_tokens": 10697728} {"current_steps": 50705, "total_steps": 181800, "loss": 0.0725, "lr": 4.5281704571047687e-05, "epoch": 5.578107810781078, "percentage": 27.89, "elapsed_time": "1:59:36", "remaining_time": "5:09:14", "throughput": 1490.83, "total_tokens": 10698816} {"current_steps": 50710, "total_steps": 181800, "loss": 0.0328, "lr": 4.528030121987597e-05, "epoch": 5.578657865786578, "percentage": 27.89, "elapsed_time": "1:59:37", "remaining_time": "5:09:13", "throughput": 1490.84, "total_tokens": 10699904} {"current_steps": 50715, "total_steps": 181800, "loss": 0.0695, "lr": 4.527889768179044e-05, "epoch": 5.579207920792079, "percentage": 27.9, "elapsed_time": "1:59:37", "remaining_time": "5:09:12", "throughput": 1490.84, "total_tokens": 10700960} {"current_steps": 50720, "total_steps": 181800, "loss": 0.1819, "lr": 4.527749395680406e-05, "epoch": 5.5797579757975795, "percentage": 27.9, "elapsed_time": "1:59:38", "remaining_time": "5:09:11", "throughput": 1490.85, "total_tokens": 10702016} {"current_steps": 50725, "total_steps": 181800, "loss": 0.1464, "lr": 4.5276090044929736e-05, "epoch": 5.580308030803081, "percentage": 27.9, "elapsed_time": "1:59:39", "remaining_time": "5:09:11", "throughput": 1490.85, "total_tokens": 10703040} {"current_steps": 50730, "total_steps": 181800, "loss": 0.0562, "lr": 4.527468594618043e-05, "epoch": 5.580858085808581, "percentage": 27.9, "elapsed_time": "1:59:39", "remaining_time": "5:09:10", "throughput": 1490.85, "total_tokens": 10704128} {"current_steps": 50735, "total_steps": 181800, "loss": 0.037, "lr": 4.527328166056906e-05, "epoch": 5.581408140814082, "percentage": 27.91, "elapsed_time": "1:59:40", "remaining_time": "5:09:09", "throughput": 1490.87, "total_tokens": 10705248} {"current_steps": 50740, "total_steps": 181800, "loss": 0.1228, "lr": 4.527187718810859e-05, "epoch": 5.581958195819582, "percentage": 27.91, "elapsed_time": "1:59:41", "remaining_time": "5:09:08", "throughput": 1490.87, "total_tokens": 10706304} {"current_steps": 50745, "total_steps": 181800, "loss": 0.0084, "lr": 4.527047252881195e-05, "epoch": 5.582508250825082, "percentage": 27.91, "elapsed_time": "1:59:41", "remaining_time": "5:09:08", "throughput": 1490.87, "total_tokens": 10707328} {"current_steps": 50750, "total_steps": 181800, "loss": 0.0743, "lr": 4.526906768269209e-05, "epoch": 5.583058305830583, "percentage": 27.92, "elapsed_time": "1:59:42", "remaining_time": "5:09:07", "throughput": 1490.87, "total_tokens": 10708384} {"current_steps": 50755, "total_steps": 181800, "loss": 0.1324, "lr": 4.5267662649761965e-05, "epoch": 5.583608360836084, "percentage": 27.92, "elapsed_time": "1:59:43", "remaining_time": "5:09:06", "throughput": 1490.89, "total_tokens": 10709536} {"current_steps": 50760, "total_steps": 181800, "loss": 0.0113, "lr": 4.5266257430034514e-05, "epoch": 5.584158415841584, "percentage": 27.92, "elapsed_time": "1:59:43", "remaining_time": "5:09:05", "throughput": 1490.9, "total_tokens": 10710592} {"current_steps": 50765, "total_steps": 181800, "loss": 0.0118, "lr": 4.52648520235227e-05, "epoch": 5.584708470847085, "percentage": 27.92, "elapsed_time": "1:59:44", "remaining_time": "5:09:05", "throughput": 1490.89, "total_tokens": 10711616} {"current_steps": 50770, "total_steps": 181800, "loss": 0.0165, "lr": 4.526344643023946e-05, "epoch": 5.585258525852585, "percentage": 27.93, "elapsed_time": "1:59:45", "remaining_time": "5:09:04", "throughput": 1490.89, "total_tokens": 10712640} {"current_steps": 50775, "total_steps": 181800, "loss": 0.1295, "lr": 4.5262040650197755e-05, "epoch": 5.585808580858086, "percentage": 27.93, "elapsed_time": "1:59:46", "remaining_time": "5:09:03", "throughput": 1490.9, "total_tokens": 10713696} {"current_steps": 50780, "total_steps": 181800, "loss": 0.0244, "lr": 4.5260634683410554e-05, "epoch": 5.586358635863586, "percentage": 27.93, "elapsed_time": "1:59:46", "remaining_time": "5:09:02", "throughput": 1490.91, "total_tokens": 10714816} {"current_steps": 50785, "total_steps": 181800, "loss": 0.0201, "lr": 4.52592285298908e-05, "epoch": 5.586908690869087, "percentage": 27.93, "elapsed_time": "1:59:47", "remaining_time": "5:09:02", "throughput": 1490.91, "total_tokens": 10715840} {"current_steps": 50790, "total_steps": 181800, "loss": 0.0197, "lr": 4.525782218965146e-05, "epoch": 5.587458745874588, "percentage": 27.94, "elapsed_time": "1:59:48", "remaining_time": "5:09:01", "throughput": 1490.93, "total_tokens": 10716992} {"current_steps": 50795, "total_steps": 181800, "loss": 0.0161, "lr": 4.52564156627055e-05, "epoch": 5.588008800880088, "percentage": 27.94, "elapsed_time": "1:59:48", "remaining_time": "5:09:00", "throughput": 1490.93, "total_tokens": 10718048} {"current_steps": 50800, "total_steps": 181800, "loss": 0.0296, "lr": 4.525500894906587e-05, "epoch": 5.588558855885589, "percentage": 27.94, "elapsed_time": "1:59:49", "remaining_time": "5:08:59", "throughput": 1490.93, "total_tokens": 10719104} {"current_steps": 50805, "total_steps": 181800, "loss": 0.0512, "lr": 4.5253602048745535e-05, "epoch": 5.589108910891089, "percentage": 27.95, "elapsed_time": "1:59:50", "remaining_time": "5:08:59", "throughput": 1490.94, "total_tokens": 10720192} {"current_steps": 50810, "total_steps": 181800, "loss": 0.0131, "lr": 4.525219496175748e-05, "epoch": 5.589658965896589, "percentage": 27.95, "elapsed_time": "1:59:50", "remaining_time": "5:08:58", "throughput": 1490.96, "total_tokens": 10721312} {"current_steps": 50815, "total_steps": 181800, "loss": 0.0787, "lr": 4.5250787688114653e-05, "epoch": 5.5902090209020905, "percentage": 27.95, "elapsed_time": "1:59:51", "remaining_time": "5:08:57", "throughput": 1490.96, "total_tokens": 10722400} {"current_steps": 50820, "total_steps": 181800, "loss": 0.0507, "lr": 4.524938022783004e-05, "epoch": 5.590759075907591, "percentage": 27.95, "elapsed_time": "1:59:52", "remaining_time": "5:08:56", "throughput": 1490.97, "total_tokens": 10723488} {"current_steps": 50825, "total_steps": 181800, "loss": 0.0436, "lr": 4.52479725809166e-05, "epoch": 5.591309130913091, "percentage": 27.96, "elapsed_time": "1:59:52", "remaining_time": "5:08:56", "throughput": 1490.97, "total_tokens": 10724480} {"current_steps": 50830, "total_steps": 181800, "loss": 0.0426, "lr": 4.5246564747387323e-05, "epoch": 5.591859185918592, "percentage": 27.96, "elapsed_time": "1:59:53", "remaining_time": "5:08:55", "throughput": 1490.97, "total_tokens": 10725504} {"current_steps": 50835, "total_steps": 181800, "loss": 0.0197, "lr": 4.524515672725516e-05, "epoch": 5.592409240924092, "percentage": 27.96, "elapsed_time": "1:59:54", "remaining_time": "5:08:54", "throughput": 1490.97, "total_tokens": 10726560} {"current_steps": 50840, "total_steps": 181800, "loss": 0.0732, "lr": 4.524374852053311e-05, "epoch": 5.592959295929593, "percentage": 27.96, "elapsed_time": "1:59:55", "remaining_time": "5:08:53", "throughput": 1490.97, "total_tokens": 10727552} {"current_steps": 50845, "total_steps": 181800, "loss": 0.0904, "lr": 4.524234012723414e-05, "epoch": 5.5935093509350935, "percentage": 27.97, "elapsed_time": "1:59:55", "remaining_time": "5:08:53", "throughput": 1490.97, "total_tokens": 10728576} {"current_steps": 50850, "total_steps": 181800, "loss": 0.0952, "lr": 4.524093154737124e-05, "epoch": 5.594059405940594, "percentage": 27.97, "elapsed_time": "1:59:56", "remaining_time": "5:08:52", "throughput": 1490.97, "total_tokens": 10729632} {"current_steps": 50855, "total_steps": 181800, "loss": 0.0576, "lr": 4.5239522780957384e-05, "epoch": 5.594609460946095, "percentage": 27.97, "elapsed_time": "1:59:57", "remaining_time": "5:08:51", "throughput": 1490.98, "total_tokens": 10730720} {"current_steps": 50860, "total_steps": 181800, "loss": 0.0124, "lr": 4.523811382800556e-05, "epoch": 5.595159515951595, "percentage": 27.98, "elapsed_time": "1:59:57", "remaining_time": "5:08:50", "throughput": 1490.98, "total_tokens": 10731776} {"current_steps": 50865, "total_steps": 181800, "loss": 0.0389, "lr": 4.523670468852875e-05, "epoch": 5.595709570957096, "percentage": 27.98, "elapsed_time": "1:59:58", "remaining_time": "5:08:50", "throughput": 1490.99, "total_tokens": 10732832} {"current_steps": 50870, "total_steps": 181800, "loss": 0.0716, "lr": 4.5235295362539944e-05, "epoch": 5.596259625962596, "percentage": 27.98, "elapsed_time": "1:59:59", "remaining_time": "5:08:49", "throughput": 1490.99, "total_tokens": 10733888} {"current_steps": 50875, "total_steps": 181800, "loss": 0.0288, "lr": 4.5233885850052125e-05, "epoch": 5.5968096809680965, "percentage": 27.98, "elapsed_time": "1:59:59", "remaining_time": "5:08:48", "throughput": 1491.0, "total_tokens": 10734976} {"current_steps": 50880, "total_steps": 181800, "loss": 0.0091, "lr": 4.523247615107829e-05, "epoch": 5.597359735973598, "percentage": 27.99, "elapsed_time": "2:00:00", "remaining_time": "5:08:47", "throughput": 1490.99, "total_tokens": 10735968} {"current_steps": 50885, "total_steps": 181800, "loss": 0.0592, "lr": 4.523106626563144e-05, "epoch": 5.597909790979098, "percentage": 27.99, "elapsed_time": "2:00:01", "remaining_time": "5:08:47", "throughput": 1491.0, "total_tokens": 10737056} {"current_steps": 50890, "total_steps": 181800, "loss": 0.0942, "lr": 4.522965619372456e-05, "epoch": 5.598459845984598, "percentage": 27.99, "elapsed_time": "2:00:01", "remaining_time": "5:08:46", "throughput": 1491.0, "total_tokens": 10738080} {"current_steps": 50895, "total_steps": 181800, "loss": 0.0154, "lr": 4.522824593537064e-05, "epoch": 5.599009900990099, "percentage": 28.0, "elapsed_time": "2:00:02", "remaining_time": "5:08:45", "throughput": 1491.01, "total_tokens": 10739168} {"current_steps": 50900, "total_steps": 181800, "loss": 0.0182, "lr": 4.522683549058268e-05, "epoch": 5.599559955995599, "percentage": 28.0, "elapsed_time": "2:00:03", "remaining_time": "5:08:44", "throughput": 1491.02, "total_tokens": 10740288} {"current_steps": 50905, "total_steps": 181800, "loss": 0.0479, "lr": 4.522542485937369e-05, "epoch": 5.6001100110011, "percentage": 28.0, "elapsed_time": "2:00:04", "remaining_time": "5:08:44", "throughput": 1491.04, "total_tokens": 10741440} {"current_steps": 50910, "total_steps": 181800, "loss": 0.1187, "lr": 4.5224014041756655e-05, "epoch": 5.600660066006601, "percentage": 28.0, "elapsed_time": "2:00:04", "remaining_time": "5:08:43", "throughput": 1491.03, "total_tokens": 10742464} {"current_steps": 50915, "total_steps": 181800, "loss": 0.0137, "lr": 4.52226030377446e-05, "epoch": 5.601210121012102, "percentage": 28.01, "elapsed_time": "2:00:05", "remaining_time": "5:08:42", "throughput": 1491.03, "total_tokens": 10743488} {"current_steps": 50920, "total_steps": 181800, "loss": 0.0731, "lr": 4.5221191847350505e-05, "epoch": 5.601760176017602, "percentage": 28.01, "elapsed_time": "2:00:06", "remaining_time": "5:08:41", "throughput": 1491.03, "total_tokens": 10744512} {"current_steps": 50925, "total_steps": 181800, "loss": 0.0227, "lr": 4.52197804705874e-05, "epoch": 5.602310231023102, "percentage": 28.01, "elapsed_time": "2:00:06", "remaining_time": "5:08:41", "throughput": 1491.03, "total_tokens": 10745536} {"current_steps": 50930, "total_steps": 181800, "loss": 0.0163, "lr": 4.5218368907468273e-05, "epoch": 5.602860286028603, "percentage": 28.01, "elapsed_time": "2:00:07", "remaining_time": "5:08:40", "throughput": 1491.04, "total_tokens": 10746592} {"current_steps": 50935, "total_steps": 181800, "loss": 0.0642, "lr": 4.521695715800614e-05, "epoch": 5.603410341034103, "percentage": 28.02, "elapsed_time": "2:00:08", "remaining_time": "5:08:39", "throughput": 1491.05, "total_tokens": 10747712} {"current_steps": 50940, "total_steps": 181800, "loss": 0.0558, "lr": 4.5215545222214016e-05, "epoch": 5.603960396039604, "percentage": 28.02, "elapsed_time": "2:00:08", "remaining_time": "5:08:38", "throughput": 1491.05, "total_tokens": 10748736} {"current_steps": 50945, "total_steps": 181800, "loss": 0.0821, "lr": 4.521413310010492e-05, "epoch": 5.604510451045105, "percentage": 28.02, "elapsed_time": "2:00:09", "remaining_time": "5:08:38", "throughput": 1491.06, "total_tokens": 10749824} {"current_steps": 50950, "total_steps": 181800, "loss": 0.0323, "lr": 4.521272079169184e-05, "epoch": 5.605060506050605, "percentage": 28.03, "elapsed_time": "2:00:10", "remaining_time": "5:08:37", "throughput": 1491.07, "total_tokens": 10750944} {"current_steps": 50955, "total_steps": 181800, "loss": 0.0455, "lr": 4.521130829698783e-05, "epoch": 5.605610561056105, "percentage": 28.03, "elapsed_time": "2:00:10", "remaining_time": "5:08:36", "throughput": 1491.08, "total_tokens": 10752032} {"current_steps": 50960, "total_steps": 181800, "loss": 0.0869, "lr": 4.5209895616005885e-05, "epoch": 5.606160616061606, "percentage": 28.03, "elapsed_time": "2:00:11", "remaining_time": "5:08:35", "throughput": 1491.09, "total_tokens": 10753120} {"current_steps": 50965, "total_steps": 181800, "loss": 0.1085, "lr": 4.5208482748759016e-05, "epoch": 5.606710671067106, "percentage": 28.03, "elapsed_time": "2:00:12", "remaining_time": "5:08:35", "throughput": 1491.1, "total_tokens": 10754208} {"current_steps": 50970, "total_steps": 181800, "loss": 0.0677, "lr": 4.5207069695260274e-05, "epoch": 5.6072607260726075, "percentage": 28.04, "elapsed_time": "2:00:12", "remaining_time": "5:08:34", "throughput": 1491.11, "total_tokens": 10755296} {"current_steps": 50975, "total_steps": 181800, "loss": 0.0446, "lr": 4.520565645552266e-05, "epoch": 5.607810781078108, "percentage": 28.04, "elapsed_time": "2:00:13", "remaining_time": "5:08:33", "throughput": 1491.12, "total_tokens": 10756384} {"current_steps": 50980, "total_steps": 181800, "loss": 0.0351, "lr": 4.5204243029559215e-05, "epoch": 5.608360836083609, "percentage": 28.04, "elapsed_time": "2:00:14", "remaining_time": "5:08:32", "throughput": 1491.12, "total_tokens": 10757408} {"current_steps": 50985, "total_steps": 181800, "loss": 0.085, "lr": 4.520282941738295e-05, "epoch": 5.608910891089109, "percentage": 28.04, "elapsed_time": "2:00:15", "remaining_time": "5:08:31", "throughput": 1491.12, "total_tokens": 10758464} {"current_steps": 50990, "total_steps": 181800, "loss": 0.028, "lr": 4.5201415619006906e-05, "epoch": 5.609460946094609, "percentage": 28.05, "elapsed_time": "2:00:15", "remaining_time": "5:08:31", "throughput": 1491.13, "total_tokens": 10759584} {"current_steps": 50995, "total_steps": 181800, "loss": 0.0226, "lr": 4.52000016344441e-05, "epoch": 5.61001100110011, "percentage": 28.05, "elapsed_time": "2:00:16", "remaining_time": "5:08:30", "throughput": 1491.14, "total_tokens": 10760704} {"current_steps": 51000, "total_steps": 181800, "loss": 0.1102, "lr": 4.519858746370757e-05, "epoch": 5.6105610561056105, "percentage": 28.05, "elapsed_time": "2:00:17", "remaining_time": "5:08:29", "throughput": 1491.15, "total_tokens": 10761760} {"current_steps": 51005, "total_steps": 181800, "loss": 0.0042, "lr": 4.519717310681036e-05, "epoch": 5.611111111111111, "percentage": 28.06, "elapsed_time": "2:00:17", "remaining_time": "5:08:28", "throughput": 1491.15, "total_tokens": 10762816} {"current_steps": 51010, "total_steps": 181800, "loss": 0.0168, "lr": 4.519575856376549e-05, "epoch": 5.611661166116612, "percentage": 28.06, "elapsed_time": "2:00:18", "remaining_time": "5:08:28", "throughput": 1491.15, "total_tokens": 10763840} {"current_steps": 51015, "total_steps": 181800, "loss": 0.0102, "lr": 4.519434383458601e-05, "epoch": 5.612211221122112, "percentage": 28.06, "elapsed_time": "2:00:19", "remaining_time": "5:08:27", "throughput": 1491.16, "total_tokens": 10764896} {"current_steps": 51020, "total_steps": 181800, "loss": 0.0119, "lr": 4.519292891928495e-05, "epoch": 5.612761276127613, "percentage": 28.06, "elapsed_time": "2:00:19", "remaining_time": "5:08:26", "throughput": 1491.15, "total_tokens": 10765888} {"current_steps": 51025, "total_steps": 181800, "loss": 0.0162, "lr": 4.5191513817875354e-05, "epoch": 5.613311331133113, "percentage": 28.07, "elapsed_time": "2:00:20", "remaining_time": "5:08:25", "throughput": 1491.16, "total_tokens": 10766976} {"current_steps": 51030, "total_steps": 181800, "loss": 0.1357, "lr": 4.5190098530370263e-05, "epoch": 5.6138613861386135, "percentage": 28.07, "elapsed_time": "2:00:21", "remaining_time": "5:08:25", "throughput": 1491.16, "total_tokens": 10768000} {"current_steps": 51035, "total_steps": 181800, "loss": 0.1441, "lr": 4.518868305678273e-05, "epoch": 5.614411441144115, "percentage": 28.07, "elapsed_time": "2:00:21", "remaining_time": "5:08:24", "throughput": 1491.16, "total_tokens": 10769024} {"current_steps": 51040, "total_steps": 181800, "loss": 0.0441, "lr": 4.518726739712578e-05, "epoch": 5.614961496149615, "percentage": 28.07, "elapsed_time": "2:00:22", "remaining_time": "5:08:23", "throughput": 1491.17, "total_tokens": 10770112} {"current_steps": 51045, "total_steps": 181800, "loss": 0.0141, "lr": 4.518585155141248e-05, "epoch": 5.615511551155116, "percentage": 28.08, "elapsed_time": "2:00:23", "remaining_time": "5:08:22", "throughput": 1491.17, "total_tokens": 10771136} {"current_steps": 51050, "total_steps": 181800, "loss": 0.0559, "lr": 4.5184435519655875e-05, "epoch": 5.616061606160616, "percentage": 28.08, "elapsed_time": "2:00:23", "remaining_time": "5:08:22", "throughput": 1491.18, "total_tokens": 10772192} {"current_steps": 51055, "total_steps": 181800, "loss": 0.0585, "lr": 4.518301930186901e-05, "epoch": 5.616611661166116, "percentage": 28.08, "elapsed_time": "2:00:24", "remaining_time": "5:08:21", "throughput": 1491.17, "total_tokens": 10773216} {"current_steps": 51060, "total_steps": 181800, "loss": 0.0849, "lr": 4.5181602898064934e-05, "epoch": 5.617161716171617, "percentage": 28.09, "elapsed_time": "2:00:25", "remaining_time": "5:08:20", "throughput": 1491.19, "total_tokens": 10774336} {"current_steps": 51065, "total_steps": 181800, "loss": 0.0644, "lr": 4.518018630825672e-05, "epoch": 5.617711771177118, "percentage": 28.09, "elapsed_time": "2:00:26", "remaining_time": "5:08:19", "throughput": 1491.2, "total_tokens": 10775424} {"current_steps": 51070, "total_steps": 181800, "loss": 0.0262, "lr": 4.517876953245741e-05, "epoch": 5.618261826182618, "percentage": 28.09, "elapsed_time": "2:00:26", "remaining_time": "5:08:19", "throughput": 1491.2, "total_tokens": 10776448} {"current_steps": 51075, "total_steps": 181800, "loss": 0.0764, "lr": 4.517735257068005e-05, "epoch": 5.618811881188119, "percentage": 28.09, "elapsed_time": "2:00:27", "remaining_time": "5:08:18", "throughput": 1491.2, "total_tokens": 10777504} {"current_steps": 51080, "total_steps": 181800, "loss": 0.0871, "lr": 4.517593542293773e-05, "epoch": 5.619361936193619, "percentage": 28.1, "elapsed_time": "2:00:28", "remaining_time": "5:08:17", "throughput": 1491.2, "total_tokens": 10778560} {"current_steps": 51085, "total_steps": 181800, "loss": 0.1258, "lr": 4.517451808924349e-05, "epoch": 5.61991199119912, "percentage": 28.1, "elapsed_time": "2:00:28", "remaining_time": "5:08:16", "throughput": 1491.21, "total_tokens": 10779616} {"current_steps": 51090, "total_steps": 181800, "loss": 0.0136, "lr": 4.5173100569610395e-05, "epoch": 5.62046204620462, "percentage": 28.1, "elapsed_time": "2:00:29", "remaining_time": "5:08:16", "throughput": 1491.21, "total_tokens": 10780672} {"current_steps": 51095, "total_steps": 181800, "loss": 0.0472, "lr": 4.517168286405151e-05, "epoch": 5.621012101210121, "percentage": 28.11, "elapsed_time": "2:00:30", "remaining_time": "5:08:15", "throughput": 1491.21, "total_tokens": 10781728} {"current_steps": 51100, "total_steps": 181800, "loss": 0.0169, "lr": 4.517026497257991e-05, "epoch": 5.621562156215622, "percentage": 28.11, "elapsed_time": "2:00:30", "remaining_time": "5:08:14", "throughput": 1491.22, "total_tokens": 10782784} {"current_steps": 51105, "total_steps": 181800, "loss": 0.0343, "lr": 4.516884689520866e-05, "epoch": 5.622112211221122, "percentage": 28.11, "elapsed_time": "2:00:31", "remaining_time": "5:08:13", "throughput": 1491.23, "total_tokens": 10783872} {"current_steps": 51110, "total_steps": 181800, "loss": 0.0736, "lr": 4.516742863195081e-05, "epoch": 5.622662266226623, "percentage": 28.11, "elapsed_time": "2:00:32", "remaining_time": "5:08:13", "throughput": 1491.23, "total_tokens": 10784960} {"current_steps": 51115, "total_steps": 181800, "loss": 0.0099, "lr": 4.516601018281946e-05, "epoch": 5.623212321232123, "percentage": 28.12, "elapsed_time": "2:00:32", "remaining_time": "5:08:12", "throughput": 1491.24, "total_tokens": 10786016} {"current_steps": 51120, "total_steps": 181800, "loss": 0.0835, "lr": 4.516459154782767e-05, "epoch": 5.623762376237623, "percentage": 28.12, "elapsed_time": "2:00:33", "remaining_time": "5:08:11", "throughput": 1491.25, "total_tokens": 10787136} {"current_steps": 51125, "total_steps": 181800, "loss": 0.0534, "lr": 4.516317272698851e-05, "epoch": 5.6243124312431245, "percentage": 28.12, "elapsed_time": "2:00:34", "remaining_time": "5:08:10", "throughput": 1491.25, "total_tokens": 10788192} {"current_steps": 51130, "total_steps": 181800, "loss": 0.1459, "lr": 4.5161753720315067e-05, "epoch": 5.624862486248625, "percentage": 28.12, "elapsed_time": "2:00:34", "remaining_time": "5:08:10", "throughput": 1491.26, "total_tokens": 10789280} {"current_steps": 51135, "total_steps": 181800, "loss": 0.0712, "lr": 4.516033452782041e-05, "epoch": 5.625412541254125, "percentage": 28.13, "elapsed_time": "2:00:35", "remaining_time": "5:08:09", "throughput": 1491.26, "total_tokens": 10790304} {"current_steps": 51140, "total_steps": 181800, "loss": 0.0735, "lr": 4.515891514951763e-05, "epoch": 5.625962596259626, "percentage": 28.13, "elapsed_time": "2:00:36", "remaining_time": "5:08:08", "throughput": 1491.26, "total_tokens": 10791360} {"current_steps": 51145, "total_steps": 181800, "loss": 0.0902, "lr": 4.51574955854198e-05, "epoch": 5.626512651265126, "percentage": 28.13, "elapsed_time": "2:00:37", "remaining_time": "5:08:07", "throughput": 1491.28, "total_tokens": 10792480} {"current_steps": 51150, "total_steps": 181800, "loss": 0.0329, "lr": 4.515607583554e-05, "epoch": 5.627062706270627, "percentage": 28.14, "elapsed_time": "2:00:37", "remaining_time": "5:08:07", "throughput": 1491.29, "total_tokens": 10793568} {"current_steps": 51155, "total_steps": 181800, "loss": 0.0489, "lr": 4.515465589989133e-05, "epoch": 5.6276127612761275, "percentage": 28.14, "elapsed_time": "2:00:38", "remaining_time": "5:08:06", "throughput": 1491.29, "total_tokens": 10794656} {"current_steps": 51160, "total_steps": 181800, "loss": 0.1717, "lr": 4.515323577848686e-05, "epoch": 5.628162816281629, "percentage": 28.14, "elapsed_time": "2:00:39", "remaining_time": "5:08:05", "throughput": 1491.3, "total_tokens": 10795744} {"current_steps": 51165, "total_steps": 181800, "loss": 0.0691, "lr": 4.5151815471339694e-05, "epoch": 5.628712871287129, "percentage": 28.14, "elapsed_time": "2:00:39", "remaining_time": "5:08:04", "throughput": 1491.3, "total_tokens": 10796800} {"current_steps": 51170, "total_steps": 181800, "loss": 0.0156, "lr": 4.515039497846291e-05, "epoch": 5.629262926292629, "percentage": 28.15, "elapsed_time": "2:00:40", "remaining_time": "5:08:04", "throughput": 1491.3, "total_tokens": 10797824} {"current_steps": 51175, "total_steps": 181800, "loss": 0.0286, "lr": 4.51489742998696e-05, "epoch": 5.62981298129813, "percentage": 28.15, "elapsed_time": "2:00:41", "remaining_time": "5:08:03", "throughput": 1491.32, "total_tokens": 10798944} {"current_steps": 51180, "total_steps": 181800, "loss": 0.0239, "lr": 4.514755343557287e-05, "epoch": 5.63036303630363, "percentage": 28.15, "elapsed_time": "2:00:41", "remaining_time": "5:08:02", "throughput": 1491.31, "total_tokens": 10799968} {"current_steps": 51185, "total_steps": 181800, "loss": 0.0196, "lr": 4.51461323855858e-05, "epoch": 5.6309130913091305, "percentage": 28.15, "elapsed_time": "2:00:42", "remaining_time": "5:08:01", "throughput": 1491.33, "total_tokens": 10801088} {"current_steps": 51190, "total_steps": 181800, "loss": 0.0352, "lr": 4.51447111499215e-05, "epoch": 5.631463146314632, "percentage": 28.16, "elapsed_time": "2:00:43", "remaining_time": "5:08:01", "throughput": 1491.34, "total_tokens": 10802208} {"current_steps": 51195, "total_steps": 181800, "loss": 0.0168, "lr": 4.5143289728593064e-05, "epoch": 5.632013201320132, "percentage": 28.16, "elapsed_time": "2:00:43", "remaining_time": "5:08:00", "throughput": 1491.34, "total_tokens": 10803232} {"current_steps": 51200, "total_steps": 181800, "loss": 0.0752, "lr": 4.51418681216136e-05, "epoch": 5.632563256325633, "percentage": 28.16, "elapsed_time": "2:00:44", "remaining_time": "5:07:59", "throughput": 1491.34, "total_tokens": 10804288} {"current_steps": 51205, "total_steps": 181800, "loss": 0.0873, "lr": 4.514044632899619e-05, "epoch": 5.633113311331133, "percentage": 28.17, "elapsed_time": "2:00:45", "remaining_time": "5:07:58", "throughput": 1491.35, "total_tokens": 10805344} {"current_steps": 51210, "total_steps": 181800, "loss": 0.1013, "lr": 4.513902435075395e-05, "epoch": 5.633663366336633, "percentage": 28.17, "elapsed_time": "2:00:46", "remaining_time": "5:07:58", "throughput": 1491.35, "total_tokens": 10806400} {"current_steps": 51215, "total_steps": 181800, "loss": 0.0321, "lr": 4.5137602186899993e-05, "epoch": 5.634213421342134, "percentage": 28.17, "elapsed_time": "2:00:46", "remaining_time": "5:07:57", "throughput": 1491.36, "total_tokens": 10807520} {"current_steps": 51220, "total_steps": 181800, "loss": 0.0391, "lr": 4.513617983744741e-05, "epoch": 5.634763476347635, "percentage": 28.17, "elapsed_time": "2:00:47", "remaining_time": "5:07:56", "throughput": 1491.37, "total_tokens": 10808608} {"current_steps": 51225, "total_steps": 181800, "loss": 0.0114, "lr": 4.513475730240934e-05, "epoch": 5.635313531353136, "percentage": 28.18, "elapsed_time": "2:00:48", "remaining_time": "5:07:55", "throughput": 1491.37, "total_tokens": 10809664} {"current_steps": 51230, "total_steps": 181800, "loss": 0.0077, "lr": 4.513333458179886e-05, "epoch": 5.635863586358636, "percentage": 28.18, "elapsed_time": "2:00:48", "remaining_time": "5:07:55", "throughput": 1491.37, "total_tokens": 10810688} {"current_steps": 51235, "total_steps": 181800, "loss": 0.026, "lr": 4.513191167562909e-05, "epoch": 5.636413641364136, "percentage": 28.18, "elapsed_time": "2:00:49", "remaining_time": "5:07:54", "throughput": 1491.39, "total_tokens": 10811840} {"current_steps": 51240, "total_steps": 181800, "loss": 0.14, "lr": 4.513048858391316e-05, "epoch": 5.636963696369637, "percentage": 28.18, "elapsed_time": "2:00:50", "remaining_time": "5:07:53", "throughput": 1491.39, "total_tokens": 10812896} {"current_steps": 51245, "total_steps": 181800, "loss": 0.1401, "lr": 4.512906530666417e-05, "epoch": 5.637513751375137, "percentage": 28.19, "elapsed_time": "2:00:50", "remaining_time": "5:07:52", "throughput": 1491.4, "total_tokens": 10814016} {"current_steps": 51250, "total_steps": 181800, "loss": 0.0157, "lr": 4.512764184389525e-05, "epoch": 5.638063806380638, "percentage": 28.19, "elapsed_time": "2:00:51", "remaining_time": "5:07:52", "throughput": 1491.41, "total_tokens": 10815072} {"current_steps": 51255, "total_steps": 181800, "loss": 0.078, "lr": 4.5126218195619506e-05, "epoch": 5.638613861386139, "percentage": 28.19, "elapsed_time": "2:00:52", "remaining_time": "5:07:51", "throughput": 1491.41, "total_tokens": 10816128} {"current_steps": 51260, "total_steps": 181800, "loss": 0.0552, "lr": 4.512479436185008e-05, "epoch": 5.639163916391639, "percentage": 28.2, "elapsed_time": "2:00:52", "remaining_time": "5:07:50", "throughput": 1491.43, "total_tokens": 10817280} {"current_steps": 51265, "total_steps": 181800, "loss": 0.0683, "lr": 4.512337034260006e-05, "epoch": 5.63971397139714, "percentage": 28.2, "elapsed_time": "2:00:53", "remaining_time": "5:07:49", "throughput": 1491.43, "total_tokens": 10818304} {"current_steps": 51270, "total_steps": 181800, "loss": 0.0582, "lr": 4.512194613788261e-05, "epoch": 5.64026402640264, "percentage": 28.2, "elapsed_time": "2:00:54", "remaining_time": "5:07:49", "throughput": 1491.42, "total_tokens": 10819328} {"current_steps": 51275, "total_steps": 181800, "loss": 0.0136, "lr": 4.512052174771083e-05, "epoch": 5.6408140814081404, "percentage": 28.2, "elapsed_time": "2:00:55", "remaining_time": "5:07:48", "throughput": 1491.43, "total_tokens": 10820384} {"current_steps": 51280, "total_steps": 181800, "loss": 0.0623, "lr": 4.5119097172097855e-05, "epoch": 5.6413641364136415, "percentage": 28.21, "elapsed_time": "2:00:55", "remaining_time": "5:07:47", "throughput": 1491.43, "total_tokens": 10821440} {"current_steps": 51285, "total_steps": 181800, "loss": 0.0202, "lr": 4.511767241105682e-05, "epoch": 5.641914191419142, "percentage": 28.21, "elapsed_time": "2:00:56", "remaining_time": "5:07:46", "throughput": 1491.43, "total_tokens": 10822464} {"current_steps": 51290, "total_steps": 181800, "loss": 0.0334, "lr": 4.5116247464600847e-05, "epoch": 5.642464246424643, "percentage": 28.21, "elapsed_time": "2:00:57", "remaining_time": "5:07:46", "throughput": 1491.43, "total_tokens": 10823520} {"current_steps": 51295, "total_steps": 181800, "loss": 0.0422, "lr": 4.511482233274308e-05, "epoch": 5.643014301430143, "percentage": 28.22, "elapsed_time": "2:00:57", "remaining_time": "5:07:45", "throughput": 1491.44, "total_tokens": 10824576} {"current_steps": 51300, "total_steps": 181800, "loss": 0.0068, "lr": 4.5113397015496636e-05, "epoch": 5.643564356435643, "percentage": 28.22, "elapsed_time": "2:00:58", "remaining_time": "5:07:44", "throughput": 1491.45, "total_tokens": 10825664} {"current_steps": 51305, "total_steps": 181800, "loss": 0.0606, "lr": 4.511197151287468e-05, "epoch": 5.644114411441144, "percentage": 28.22, "elapsed_time": "2:00:59", "remaining_time": "5:07:43", "throughput": 1491.46, "total_tokens": 10826816} {"current_steps": 51310, "total_steps": 181800, "loss": 0.014, "lr": 4.5110545824890324e-05, "epoch": 5.6446644664466445, "percentage": 28.22, "elapsed_time": "2:00:59", "remaining_time": "5:07:43", "throughput": 1491.46, "total_tokens": 10827808} {"current_steps": 51315, "total_steps": 181800, "loss": 0.0553, "lr": 4.510911995155671e-05, "epoch": 5.645214521452145, "percentage": 28.23, "elapsed_time": "2:01:00", "remaining_time": "5:07:42", "throughput": 1491.45, "total_tokens": 10828800} {"current_steps": 51320, "total_steps": 181800, "loss": 0.0065, "lr": 4.5107693892887e-05, "epoch": 5.645764576457646, "percentage": 28.23, "elapsed_time": "2:01:01", "remaining_time": "5:07:41", "throughput": 1491.46, "total_tokens": 10829920} {"current_steps": 51325, "total_steps": 181800, "loss": 0.0345, "lr": 4.510626764889432e-05, "epoch": 5.646314631463146, "percentage": 28.23, "elapsed_time": "2:01:01", "remaining_time": "5:07:40", "throughput": 1491.47, "total_tokens": 10830976} {"current_steps": 51330, "total_steps": 181800, "loss": 0.0055, "lr": 4.510484121959181e-05, "epoch": 5.646864686468647, "percentage": 28.23, "elapsed_time": "2:01:02", "remaining_time": "5:07:40", "throughput": 1491.47, "total_tokens": 10832000} {"current_steps": 51335, "total_steps": 181800, "loss": 0.0919, "lr": 4.5103414604992636e-05, "epoch": 5.647414741474147, "percentage": 28.24, "elapsed_time": "2:01:03", "remaining_time": "5:07:39", "throughput": 1491.47, "total_tokens": 10833056} {"current_steps": 51340, "total_steps": 181800, "loss": 0.0047, "lr": 4.510198780510993e-05, "epoch": 5.647964796479648, "percentage": 28.24, "elapsed_time": "2:01:04", "remaining_time": "5:07:38", "throughput": 1491.47, "total_tokens": 10834112} {"current_steps": 51345, "total_steps": 181800, "loss": 0.0876, "lr": 4.510056081995685e-05, "epoch": 5.648514851485149, "percentage": 28.24, "elapsed_time": "2:01:04", "remaining_time": "5:07:37", "throughput": 1491.47, "total_tokens": 10835136} {"current_steps": 51350, "total_steps": 181800, "loss": 0.0703, "lr": 4.509913364954655e-05, "epoch": 5.649064906490649, "percentage": 28.25, "elapsed_time": "2:01:05", "remaining_time": "5:07:37", "throughput": 1491.48, "total_tokens": 10836224} {"current_steps": 51355, "total_steps": 181800, "loss": 0.048, "lr": 4.509770629389218e-05, "epoch": 5.64961496149615, "percentage": 28.25, "elapsed_time": "2:01:06", "remaining_time": "5:07:36", "throughput": 1491.49, "total_tokens": 10837344} {"current_steps": 51360, "total_steps": 181800, "loss": 0.1268, "lr": 4.509627875300689e-05, "epoch": 5.65016501650165, "percentage": 28.25, "elapsed_time": "2:01:06", "remaining_time": "5:07:35", "throughput": 1491.49, "total_tokens": 10838368} {"current_steps": 51365, "total_steps": 181800, "loss": 0.0505, "lr": 4.509485102690385e-05, "epoch": 5.65071507150715, "percentage": 28.25, "elapsed_time": "2:01:07", "remaining_time": "5:07:34", "throughput": 1491.5, "total_tokens": 10839456} {"current_steps": 51370, "total_steps": 181800, "loss": 0.0625, "lr": 4.50934231155962e-05, "epoch": 5.6512651265126514, "percentage": 28.26, "elapsed_time": "2:01:08", "remaining_time": "5:07:34", "throughput": 1491.5, "total_tokens": 10840512} {"current_steps": 51375, "total_steps": 181800, "loss": 0.0104, "lr": 4.509199501909711e-05, "epoch": 5.651815181518152, "percentage": 28.26, "elapsed_time": "2:01:08", "remaining_time": "5:07:33", "throughput": 1491.51, "total_tokens": 10841568} {"current_steps": 51380, "total_steps": 181800, "loss": 0.0364, "lr": 4.509056673741975e-05, "epoch": 5.652365236523653, "percentage": 28.26, "elapsed_time": "2:01:09", "remaining_time": "5:07:32", "throughput": 1491.51, "total_tokens": 10842592} {"current_steps": 51385, "total_steps": 181800, "loss": 0.1274, "lr": 4.508913827057728e-05, "epoch": 5.652915291529153, "percentage": 28.26, "elapsed_time": "2:01:10", "remaining_time": "5:07:31", "throughput": 1491.51, "total_tokens": 10843680} {"current_steps": 51390, "total_steps": 181800, "loss": 0.0914, "lr": 4.508770961858285e-05, "epoch": 5.653465346534653, "percentage": 28.27, "elapsed_time": "2:01:10", "remaining_time": "5:07:31", "throughput": 1491.52, "total_tokens": 10844768} {"current_steps": 51395, "total_steps": 181800, "loss": 0.0732, "lr": 4.5086280781449654e-05, "epoch": 5.654015401540154, "percentage": 28.27, "elapsed_time": "2:01:11", "remaining_time": "5:07:30", "throughput": 1491.53, "total_tokens": 10845856} {"current_steps": 51400, "total_steps": 181800, "loss": 0.0799, "lr": 4.508485175919084e-05, "epoch": 5.6545654565456545, "percentage": 28.27, "elapsed_time": "2:01:12", "remaining_time": "5:07:29", "throughput": 1491.53, "total_tokens": 10846912} {"current_steps": 51405, "total_steps": 181800, "loss": 0.1264, "lr": 4.508342255181958e-05, "epoch": 5.6551155115511555, "percentage": 28.28, "elapsed_time": "2:01:13", "remaining_time": "5:07:28", "throughput": 1491.53, "total_tokens": 10847936} {"current_steps": 51410, "total_steps": 181800, "loss": 0.0967, "lr": 4.5081993159349056e-05, "epoch": 5.655665566556656, "percentage": 28.28, "elapsed_time": "2:01:13", "remaining_time": "5:07:28", "throughput": 1491.54, "total_tokens": 10849024} {"current_steps": 51415, "total_steps": 181800, "loss": 0.0195, "lr": 4.5080563581792436e-05, "epoch": 5.656215621562156, "percentage": 28.28, "elapsed_time": "2:01:14", "remaining_time": "5:07:27", "throughput": 1491.55, "total_tokens": 10850112} {"current_steps": 51420, "total_steps": 181800, "loss": 0.0071, "lr": 4.50791338191629e-05, "epoch": 5.656765676567657, "percentage": 28.28, "elapsed_time": "2:01:15", "remaining_time": "5:07:26", "throughput": 1491.55, "total_tokens": 10851168} {"current_steps": 51425, "total_steps": 181800, "loss": 0.0071, "lr": 4.507770387147362e-05, "epoch": 5.657315731573157, "percentage": 28.29, "elapsed_time": "2:01:15", "remaining_time": "5:07:25", "throughput": 1491.55, "total_tokens": 10852192} {"current_steps": 51430, "total_steps": 181800, "loss": 0.0167, "lr": 4.507627373873777e-05, "epoch": 5.6578657865786575, "percentage": 28.29, "elapsed_time": "2:01:16", "remaining_time": "5:07:25", "throughput": 1491.56, "total_tokens": 10853280} {"current_steps": 51435, "total_steps": 181800, "loss": 0.0138, "lr": 4.5074843420968546e-05, "epoch": 5.658415841584159, "percentage": 28.29, "elapsed_time": "2:01:17", "remaining_time": "5:07:24", "throughput": 1491.56, "total_tokens": 10854336} {"current_steps": 51440, "total_steps": 181800, "loss": 0.0483, "lr": 4.507341291817913e-05, "epoch": 5.658965896589659, "percentage": 28.29, "elapsed_time": "2:01:17", "remaining_time": "5:07:23", "throughput": 1491.56, "total_tokens": 10855328} {"current_steps": 51445, "total_steps": 181800, "loss": 0.0351, "lr": 4.507198223038269e-05, "epoch": 5.65951595159516, "percentage": 28.3, "elapsed_time": "2:01:18", "remaining_time": "5:07:22", "throughput": 1491.56, "total_tokens": 10856352} {"current_steps": 51450, "total_steps": 181800, "loss": 0.0081, "lr": 4.507055135759243e-05, "epoch": 5.66006600660066, "percentage": 28.3, "elapsed_time": "2:01:19", "remaining_time": "5:07:22", "throughput": 1491.56, "total_tokens": 10857408} {"current_steps": 51455, "total_steps": 181800, "loss": 0.0579, "lr": 4.506912029982152e-05, "epoch": 5.66061606160616, "percentage": 28.3, "elapsed_time": "2:01:19", "remaining_time": "5:07:21", "throughput": 1491.57, "total_tokens": 10858528} {"current_steps": 51460, "total_steps": 181800, "loss": 0.1358, "lr": 4.506768905708316e-05, "epoch": 5.661166116611661, "percentage": 28.31, "elapsed_time": "2:01:20", "remaining_time": "5:07:20", "throughput": 1491.59, "total_tokens": 10859680} {"current_steps": 51465, "total_steps": 181800, "loss": 0.057, "lr": 4.5066257629390544e-05, "epoch": 5.661716171617162, "percentage": 28.31, "elapsed_time": "2:01:21", "remaining_time": "5:07:19", "throughput": 1491.59, "total_tokens": 10860704} {"current_steps": 51470, "total_steps": 181800, "loss": 0.0524, "lr": 4.506482601675685e-05, "epoch": 5.662266226622663, "percentage": 28.31, "elapsed_time": "2:01:21", "remaining_time": "5:07:19", "throughput": 1491.6, "total_tokens": 10861792} {"current_steps": 51475, "total_steps": 181800, "loss": 0.1238, "lr": 4.5063394219195284e-05, "epoch": 5.662816281628163, "percentage": 28.31, "elapsed_time": "2:01:22", "remaining_time": "5:07:18", "throughput": 1491.59, "total_tokens": 10862784} {"current_steps": 51480, "total_steps": 181800, "loss": 0.0179, "lr": 4.506196223671906e-05, "epoch": 5.663366336633663, "percentage": 28.32, "elapsed_time": "2:01:23", "remaining_time": "5:07:17", "throughput": 1491.6, "total_tokens": 10863872} {"current_steps": 51485, "total_steps": 181800, "loss": 0.0424, "lr": 4.506053006934133e-05, "epoch": 5.663916391639164, "percentage": 28.32, "elapsed_time": "2:01:24", "remaining_time": "5:07:16", "throughput": 1491.61, "total_tokens": 10864960} {"current_steps": 51490, "total_steps": 181800, "loss": 0.0901, "lr": 4.505909771707534e-05, "epoch": 5.664466446644664, "percentage": 28.32, "elapsed_time": "2:01:24", "remaining_time": "5:07:16", "throughput": 1491.61, "total_tokens": 10866016} {"current_steps": 51495, "total_steps": 181800, "loss": 0.0367, "lr": 4.505766517993426e-05, "epoch": 5.665016501650165, "percentage": 28.33, "elapsed_time": "2:01:25", "remaining_time": "5:07:15", "throughput": 1491.61, "total_tokens": 10867040} {"current_steps": 51500, "total_steps": 181800, "loss": 0.036, "lr": 4.505623245793131e-05, "epoch": 5.665566556655666, "percentage": 28.33, "elapsed_time": "2:01:26", "remaining_time": "5:07:14", "throughput": 1491.62, "total_tokens": 10868128} {"current_steps": 51505, "total_steps": 181800, "loss": 0.0436, "lr": 4.5054799551079695e-05, "epoch": 5.666116611661166, "percentage": 28.33, "elapsed_time": "2:01:26", "remaining_time": "5:07:13", "throughput": 1491.62, "total_tokens": 10869152} {"current_steps": 51510, "total_steps": 181800, "loss": 0.0163, "lr": 4.5053366459392607e-05, "epoch": 5.666666666666667, "percentage": 28.33, "elapsed_time": "2:01:27", "remaining_time": "5:07:13", "throughput": 1491.63, "total_tokens": 10870240} {"current_steps": 51515, "total_steps": 181800, "loss": 0.0635, "lr": 4.505193318288327e-05, "epoch": 5.667216721672167, "percentage": 28.34, "elapsed_time": "2:01:28", "remaining_time": "5:07:12", "throughput": 1491.63, "total_tokens": 10871296} {"current_steps": 51520, "total_steps": 181800, "loss": 0.1289, "lr": 4.505049972156487e-05, "epoch": 5.667766776677668, "percentage": 28.34, "elapsed_time": "2:01:28", "remaining_time": "5:07:11", "throughput": 1491.63, "total_tokens": 10872320} {"current_steps": 51525, "total_steps": 181800, "loss": 0.0797, "lr": 4.5049066075450655e-05, "epoch": 5.6683168316831685, "percentage": 28.34, "elapsed_time": "2:01:29", "remaining_time": "5:07:10", "throughput": 1491.64, "total_tokens": 10873408} {"current_steps": 51530, "total_steps": 181800, "loss": 0.0722, "lr": 4.5047632244553814e-05, "epoch": 5.668866886688669, "percentage": 28.34, "elapsed_time": "2:01:30", "remaining_time": "5:07:10", "throughput": 1491.64, "total_tokens": 10874432} {"current_steps": 51535, "total_steps": 181800, "loss": 0.2496, "lr": 4.504619822888756e-05, "epoch": 5.66941694169417, "percentage": 28.35, "elapsed_time": "2:01:30", "remaining_time": "5:07:09", "throughput": 1491.64, "total_tokens": 10875488} {"current_steps": 51540, "total_steps": 181800, "loss": 0.0219, "lr": 4.504476402846512e-05, "epoch": 5.66996699669967, "percentage": 28.35, "elapsed_time": "2:01:31", "remaining_time": "5:07:08", "throughput": 1491.64, "total_tokens": 10876512} {"current_steps": 51545, "total_steps": 181800, "loss": 0.0748, "lr": 4.5043329643299706e-05, "epoch": 5.67051705170517, "percentage": 28.35, "elapsed_time": "2:01:32", "remaining_time": "5:07:07", "throughput": 1491.64, "total_tokens": 10877536} {"current_steps": 51550, "total_steps": 181800, "loss": 0.1403, "lr": 4.5041895073404546e-05, "epoch": 5.671067106710671, "percentage": 28.36, "elapsed_time": "2:01:33", "remaining_time": "5:07:07", "throughput": 1491.64, "total_tokens": 10878528} {"current_steps": 51555, "total_steps": 181800, "loss": 0.1082, "lr": 4.504046031879285e-05, "epoch": 5.6716171617161715, "percentage": 28.36, "elapsed_time": "2:01:33", "remaining_time": "5:07:06", "throughput": 1491.64, "total_tokens": 10879584} {"current_steps": 51560, "total_steps": 181800, "loss": 0.0389, "lr": 4.503902537947785e-05, "epoch": 5.672167216721672, "percentage": 28.36, "elapsed_time": "2:01:34", "remaining_time": "5:07:05", "throughput": 1491.63, "total_tokens": 10880576} {"current_steps": 51565, "total_steps": 181800, "loss": 0.0374, "lr": 4.503759025547277e-05, "epoch": 5.672717271727173, "percentage": 28.36, "elapsed_time": "2:01:35", "remaining_time": "5:07:04", "throughput": 1491.63, "total_tokens": 10881600} {"current_steps": 51570, "total_steps": 181800, "loss": 0.0274, "lr": 4.503615494679083e-05, "epoch": 5.673267326732673, "percentage": 28.37, "elapsed_time": "2:01:35", "remaining_time": "5:07:04", "throughput": 1491.64, "total_tokens": 10882688} {"current_steps": 51575, "total_steps": 181800, "loss": 0.0726, "lr": 4.5034719453445275e-05, "epoch": 5.673817381738174, "percentage": 28.37, "elapsed_time": "2:01:36", "remaining_time": "5:07:03", "throughput": 1491.64, "total_tokens": 10883712} {"current_steps": 51580, "total_steps": 181800, "loss": 0.089, "lr": 4.5033283775449313e-05, "epoch": 5.674367436743674, "percentage": 28.37, "elapsed_time": "2:01:37", "remaining_time": "5:07:02", "throughput": 1491.64, "total_tokens": 10884736} {"current_steps": 51585, "total_steps": 181800, "loss": 0.0466, "lr": 4.5031847912816196e-05, "epoch": 5.674917491749175, "percentage": 28.37, "elapsed_time": "2:01:37", "remaining_time": "5:07:01", "throughput": 1491.64, "total_tokens": 10885760} {"current_steps": 51590, "total_steps": 181800, "loss": 0.1005, "lr": 4.503041186555914e-05, "epoch": 5.675467546754676, "percentage": 28.38, "elapsed_time": "2:01:38", "remaining_time": "5:07:01", "throughput": 1491.64, "total_tokens": 10886816} {"current_steps": 51595, "total_steps": 181800, "loss": 0.0098, "lr": 4.502897563369139e-05, "epoch": 5.676017601760176, "percentage": 28.38, "elapsed_time": "2:01:39", "remaining_time": "5:07:00", "throughput": 1491.64, "total_tokens": 10887840} {"current_steps": 51600, "total_steps": 181800, "loss": 0.0344, "lr": 4.502753921722619e-05, "epoch": 5.676567656765677, "percentage": 28.38, "elapsed_time": "2:01:39", "remaining_time": "5:06:59", "throughput": 1491.64, "total_tokens": 10888864} {"current_steps": 51605, "total_steps": 181800, "loss": 0.0791, "lr": 4.502610261617677e-05, "epoch": 5.677117711771177, "percentage": 28.39, "elapsed_time": "2:01:40", "remaining_time": "5:06:58", "throughput": 1491.64, "total_tokens": 10889888} {"current_steps": 51610, "total_steps": 181800, "loss": 0.0273, "lr": 4.502466583055637e-05, "epoch": 5.677667766776677, "percentage": 28.39, "elapsed_time": "2:01:41", "remaining_time": "5:06:58", "throughput": 1491.65, "total_tokens": 10890944} {"current_steps": 51615, "total_steps": 181800, "loss": 0.0336, "lr": 4.502322886037823e-05, "epoch": 5.678217821782178, "percentage": 28.39, "elapsed_time": "2:01:41", "remaining_time": "5:06:57", "throughput": 1491.66, "total_tokens": 10892032} {"current_steps": 51620, "total_steps": 181800, "loss": 0.0269, "lr": 4.5021791705655605e-05, "epoch": 5.678767876787679, "percentage": 28.39, "elapsed_time": "2:01:42", "remaining_time": "5:06:56", "throughput": 1491.66, "total_tokens": 10893056} {"current_steps": 51625, "total_steps": 181800, "loss": 0.0211, "lr": 4.502035436640173e-05, "epoch": 5.67931793179318, "percentage": 28.4, "elapsed_time": "2:01:43", "remaining_time": "5:06:55", "throughput": 1491.67, "total_tokens": 10894176} {"current_steps": 51630, "total_steps": 181800, "loss": 0.0169, "lr": 4.5018916842629854e-05, "epoch": 5.67986798679868, "percentage": 28.4, "elapsed_time": "2:01:44", "remaining_time": "5:06:55", "throughput": 1491.67, "total_tokens": 10895232} {"current_steps": 51635, "total_steps": 181800, "loss": 0.0163, "lr": 4.5017479134353225e-05, "epoch": 5.68041804180418, "percentage": 28.4, "elapsed_time": "2:01:44", "remaining_time": "5:06:54", "throughput": 1491.68, "total_tokens": 10896320} {"current_steps": 51640, "total_steps": 181800, "loss": 0.0097, "lr": 4.50160412415851e-05, "epoch": 5.680968096809681, "percentage": 28.4, "elapsed_time": "2:01:45", "remaining_time": "5:06:53", "throughput": 1491.67, "total_tokens": 10897312} {"current_steps": 51645, "total_steps": 181800, "loss": 0.0642, "lr": 4.501460316433873e-05, "epoch": 5.681518151815181, "percentage": 28.41, "elapsed_time": "2:01:46", "remaining_time": "5:06:52", "throughput": 1491.67, "total_tokens": 10898336} {"current_steps": 51650, "total_steps": 181800, "loss": 0.0913, "lr": 4.501316490262736e-05, "epoch": 5.6820682068206825, "percentage": 28.41, "elapsed_time": "2:01:46", "remaining_time": "5:06:52", "throughput": 1491.67, "total_tokens": 10899360} {"current_steps": 51655, "total_steps": 181800, "loss": 0.0239, "lr": 4.501172645646426e-05, "epoch": 5.682618261826183, "percentage": 28.41, "elapsed_time": "2:01:47", "remaining_time": "5:06:51", "throughput": 1491.69, "total_tokens": 10900480} {"current_steps": 51660, "total_steps": 181800, "loss": 0.0998, "lr": 4.5010287825862676e-05, "epoch": 5.683168316831683, "percentage": 28.42, "elapsed_time": "2:01:48", "remaining_time": "5:06:50", "throughput": 1491.69, "total_tokens": 10901536} {"current_steps": 51665, "total_steps": 181800, "loss": 0.0169, "lr": 4.500884901083587e-05, "epoch": 5.683718371837184, "percentage": 28.42, "elapsed_time": "2:01:48", "remaining_time": "5:06:49", "throughput": 1491.7, "total_tokens": 10902624} {"current_steps": 51670, "total_steps": 181800, "loss": 0.0113, "lr": 4.50074100113971e-05, "epoch": 5.684268426842684, "percentage": 28.42, "elapsed_time": "2:01:49", "remaining_time": "5:06:48", "throughput": 1491.7, "total_tokens": 10903648} {"current_steps": 51675, "total_steps": 181800, "loss": 0.0513, "lr": 4.500597082755964e-05, "epoch": 5.684818481848184, "percentage": 28.42, "elapsed_time": "2:01:50", "remaining_time": "5:06:48", "throughput": 1491.7, "total_tokens": 10904672} {"current_steps": 51680, "total_steps": 181800, "loss": 0.0175, "lr": 4.500453145933674e-05, "epoch": 5.6853685368536855, "percentage": 28.43, "elapsed_time": "2:01:50", "remaining_time": "5:06:47", "throughput": 1491.71, "total_tokens": 10905792} {"current_steps": 51685, "total_steps": 181800, "loss": 0.0459, "lr": 4.500309190674168e-05, "epoch": 5.685918591859186, "percentage": 28.43, "elapsed_time": "2:01:51", "remaining_time": "5:06:46", "throughput": 1491.71, "total_tokens": 10906816} {"current_steps": 51690, "total_steps": 181800, "loss": 0.0331, "lr": 4.5001652169787715e-05, "epoch": 5.686468646864687, "percentage": 28.43, "elapsed_time": "2:01:52", "remaining_time": "5:06:45", "throughput": 1491.7, "total_tokens": 10907776} {"current_steps": 51695, "total_steps": 181800, "loss": 0.1041, "lr": 4.500021224848812e-05, "epoch": 5.687018701870187, "percentage": 28.44, "elapsed_time": "2:01:52", "remaining_time": "5:06:45", "throughput": 1491.7, "total_tokens": 10908768} {"current_steps": 51700, "total_steps": 181800, "loss": 0.0733, "lr": 4.499877214285617e-05, "epoch": 5.687568756875687, "percentage": 28.44, "elapsed_time": "2:01:53", "remaining_time": "5:06:44", "throughput": 1491.69, "total_tokens": 10909760} {"current_steps": 51705, "total_steps": 181800, "loss": 0.0427, "lr": 4.499733185290513e-05, "epoch": 5.688118811881188, "percentage": 28.44, "elapsed_time": "2:01:54", "remaining_time": "5:06:43", "throughput": 1491.69, "total_tokens": 10910752} {"current_steps": 51710, "total_steps": 181800, "loss": 0.0182, "lr": 4.499589137864828e-05, "epoch": 5.6886688668866885, "percentage": 28.44, "elapsed_time": "2:01:55", "remaining_time": "5:06:42", "throughput": 1491.69, "total_tokens": 10911776} {"current_steps": 51715, "total_steps": 181800, "loss": 0.0175, "lr": 4.499445072009889e-05, "epoch": 5.68921892189219, "percentage": 28.45, "elapsed_time": "2:01:55", "remaining_time": "5:06:42", "throughput": 1491.68, "total_tokens": 10912768} {"current_steps": 51720, "total_steps": 181800, "loss": 0.0306, "lr": 4.499300987727024e-05, "epoch": 5.68976897689769, "percentage": 28.45, "elapsed_time": "2:01:56", "remaining_time": "5:06:41", "throughput": 1491.69, "total_tokens": 10913824} {"current_steps": 51725, "total_steps": 181800, "loss": 0.0389, "lr": 4.4991568850175626e-05, "epoch": 5.69031903190319, "percentage": 28.45, "elapsed_time": "2:01:57", "remaining_time": "5:06:40", "throughput": 1491.69, "total_tokens": 10914880} {"current_steps": 51730, "total_steps": 181800, "loss": 0.0235, "lr": 4.49901276388283e-05, "epoch": 5.690869086908691, "percentage": 28.45, "elapsed_time": "2:01:57", "remaining_time": "5:06:39", "throughput": 1491.7, "total_tokens": 10916000} {"current_steps": 51735, "total_steps": 181800, "loss": 0.0271, "lr": 4.4988686243241564e-05, "epoch": 5.691419141914191, "percentage": 28.46, "elapsed_time": "2:01:58", "remaining_time": "5:06:39", "throughput": 1491.7, "total_tokens": 10917056} {"current_steps": 51740, "total_steps": 181800, "loss": 0.008, "lr": 4.49872446634287e-05, "epoch": 5.6919691969196915, "percentage": 28.46, "elapsed_time": "2:01:59", "remaining_time": "5:06:38", "throughput": 1491.71, "total_tokens": 10918112} {"current_steps": 51745, "total_steps": 181800, "loss": 0.0452, "lr": 4.498580289940299e-05, "epoch": 5.692519251925193, "percentage": 28.46, "elapsed_time": "2:01:59", "remaining_time": "5:06:37", "throughput": 1491.71, "total_tokens": 10919136} {"current_steps": 51750, "total_steps": 181800, "loss": 0.0083, "lr": 4.498436095117773e-05, "epoch": 5.693069306930693, "percentage": 28.47, "elapsed_time": "2:02:00", "remaining_time": "5:06:36", "throughput": 1491.71, "total_tokens": 10920192} {"current_steps": 51755, "total_steps": 181800, "loss": 0.0316, "lr": 4.49829188187662e-05, "epoch": 5.693619361936194, "percentage": 28.47, "elapsed_time": "2:02:01", "remaining_time": "5:06:36", "throughput": 1491.72, "total_tokens": 10921312} {"current_steps": 51760, "total_steps": 181800, "loss": 0.0983, "lr": 4.4981476502181695e-05, "epoch": 5.694169416941694, "percentage": 28.47, "elapsed_time": "2:02:01", "remaining_time": "5:06:35", "throughput": 1491.73, "total_tokens": 10922400} {"current_steps": 51765, "total_steps": 181800, "loss": 0.0602, "lr": 4.498003400143751e-05, "epoch": 5.694719471947195, "percentage": 28.47, "elapsed_time": "2:02:02", "remaining_time": "5:06:34", "throughput": 1491.74, "total_tokens": 10923520} {"current_steps": 51770, "total_steps": 181800, "loss": 0.0183, "lr": 4.4978591316546945e-05, "epoch": 5.695269526952695, "percentage": 28.48, "elapsed_time": "2:02:03", "remaining_time": "5:06:33", "throughput": 1491.75, "total_tokens": 10924608} {"current_steps": 51775, "total_steps": 181800, "loss": 0.0341, "lr": 4.497714844752329e-05, "epoch": 5.695819581958196, "percentage": 28.48, "elapsed_time": "2:02:04", "remaining_time": "5:06:33", "throughput": 1491.75, "total_tokens": 10925664} {"current_steps": 51780, "total_steps": 181800, "loss": 0.0245, "lr": 4.497570539437983e-05, "epoch": 5.696369636963697, "percentage": 28.48, "elapsed_time": "2:02:04", "remaining_time": "5:06:32", "throughput": 1491.76, "total_tokens": 10926720} {"current_steps": 51785, "total_steps": 181800, "loss": 0.1512, "lr": 4.497426215712989e-05, "epoch": 5.696919691969197, "percentage": 28.48, "elapsed_time": "2:02:05", "remaining_time": "5:06:31", "throughput": 1491.76, "total_tokens": 10927808} {"current_steps": 51790, "total_steps": 181800, "loss": 0.1003, "lr": 4.497281873578676e-05, "epoch": 5.697469746974697, "percentage": 28.49, "elapsed_time": "2:02:06", "remaining_time": "5:06:30", "throughput": 1491.76, "total_tokens": 10928800} {"current_steps": 51795, "total_steps": 181800, "loss": 0.0365, "lr": 4.4971375130363744e-05, "epoch": 5.698019801980198, "percentage": 28.49, "elapsed_time": "2:02:06", "remaining_time": "5:06:30", "throughput": 1491.76, "total_tokens": 10929856} {"current_steps": 51800, "total_steps": 181800, "loss": 0.0376, "lr": 4.496993134087414e-05, "epoch": 5.698569856985698, "percentage": 28.49, "elapsed_time": "2:02:07", "remaining_time": "5:06:29", "throughput": 1491.77, "total_tokens": 10930912} {"current_steps": 51805, "total_steps": 181800, "loss": 0.0226, "lr": 4.4968487367331266e-05, "epoch": 5.6991199119911995, "percentage": 28.5, "elapsed_time": "2:02:08", "remaining_time": "5:06:28", "throughput": 1491.77, "total_tokens": 10931936} {"current_steps": 51810, "total_steps": 181800, "loss": 0.1438, "lr": 4.496704320974843e-05, "epoch": 5.6996699669967, "percentage": 28.5, "elapsed_time": "2:02:08", "remaining_time": "5:06:27", "throughput": 1491.77, "total_tokens": 10932992} {"current_steps": 51815, "total_steps": 181800, "loss": 0.0465, "lr": 4.496559886813893e-05, "epoch": 5.7002200220022, "percentage": 28.5, "elapsed_time": "2:02:09", "remaining_time": "5:06:27", "throughput": 1491.78, "total_tokens": 10934048} {"current_steps": 51820, "total_steps": 181800, "loss": 0.0139, "lr": 4.496415434251609e-05, "epoch": 5.700770077007701, "percentage": 28.5, "elapsed_time": "2:02:10", "remaining_time": "5:06:26", "throughput": 1491.78, "total_tokens": 10935072} {"current_steps": 51825, "total_steps": 181800, "loss": 0.088, "lr": 4.496270963289322e-05, "epoch": 5.701320132013201, "percentage": 28.51, "elapsed_time": "2:02:10", "remaining_time": "5:06:25", "throughput": 1491.78, "total_tokens": 10936160} {"current_steps": 51830, "total_steps": 181800, "loss": 0.0325, "lr": 4.496126473928363e-05, "epoch": 5.701870187018702, "percentage": 28.51, "elapsed_time": "2:02:11", "remaining_time": "5:06:24", "throughput": 1491.79, "total_tokens": 10937216} {"current_steps": 51835, "total_steps": 181800, "loss": 0.0069, "lr": 4.495981966170065e-05, "epoch": 5.7024202420242025, "percentage": 28.51, "elapsed_time": "2:02:12", "remaining_time": "5:06:24", "throughput": 1491.8, "total_tokens": 10938304} {"current_steps": 51840, "total_steps": 181800, "loss": 0.0037, "lr": 4.495837440015758e-05, "epoch": 5.702970297029703, "percentage": 28.51, "elapsed_time": "2:02:12", "remaining_time": "5:06:23", "throughput": 1491.79, "total_tokens": 10939296} {"current_steps": 51845, "total_steps": 181800, "loss": 0.1326, "lr": 4.4956928954667755e-05, "epoch": 5.703520352035204, "percentage": 28.52, "elapsed_time": "2:02:13", "remaining_time": "5:06:22", "throughput": 1491.8, "total_tokens": 10940384} {"current_steps": 51850, "total_steps": 181800, "loss": 0.0199, "lr": 4.4955483325244484e-05, "epoch": 5.704070407040704, "percentage": 28.52, "elapsed_time": "2:02:14", "remaining_time": "5:06:21", "throughput": 1491.81, "total_tokens": 10941472} {"current_steps": 51855, "total_steps": 181800, "loss": 0.1066, "lr": 4.495403751190111e-05, "epoch": 5.704620462046204, "percentage": 28.52, "elapsed_time": "2:02:15", "remaining_time": "5:06:21", "throughput": 1491.81, "total_tokens": 10942528} {"current_steps": 51860, "total_steps": 181800, "loss": 0.0088, "lr": 4.4952591514650947e-05, "epoch": 5.705170517051705, "percentage": 28.53, "elapsed_time": "2:02:15", "remaining_time": "5:06:20", "throughput": 1491.8, "total_tokens": 10943520} {"current_steps": 51865, "total_steps": 181800, "loss": 0.0239, "lr": 4.495114533350732e-05, "epoch": 5.7057205720572055, "percentage": 28.53, "elapsed_time": "2:02:16", "remaining_time": "5:06:19", "throughput": 1491.81, "total_tokens": 10944608} {"current_steps": 51870, "total_steps": 181800, "loss": 0.0347, "lr": 4.4949698968483556e-05, "epoch": 5.706270627062707, "percentage": 28.53, "elapsed_time": "2:02:17", "remaining_time": "5:06:18", "throughput": 1491.82, "total_tokens": 10945696} {"current_steps": 51875, "total_steps": 181800, "loss": 0.0948, "lr": 4.494825241959298e-05, "epoch": 5.706820682068207, "percentage": 28.53, "elapsed_time": "2:02:17", "remaining_time": "5:06:18", "throughput": 1491.83, "total_tokens": 10946816} {"current_steps": 51880, "total_steps": 181800, "loss": 0.0249, "lr": 4.4946805686848956e-05, "epoch": 5.707370737073707, "percentage": 28.54, "elapsed_time": "2:02:18", "remaining_time": "5:06:17", "throughput": 1491.83, "total_tokens": 10947872} {"current_steps": 51885, "total_steps": 181800, "loss": 0.0266, "lr": 4.4945358770264776e-05, "epoch": 5.707920792079208, "percentage": 28.54, "elapsed_time": "2:02:19", "remaining_time": "5:06:16", "throughput": 1491.84, "total_tokens": 10948992} {"current_steps": 51890, "total_steps": 181800, "loss": 0.022, "lr": 4.494391166985381e-05, "epoch": 5.708470847084708, "percentage": 28.54, "elapsed_time": "2:02:19", "remaining_time": "5:06:15", "throughput": 1491.85, "total_tokens": 10950048} {"current_steps": 51895, "total_steps": 181800, "loss": 0.0291, "lr": 4.494246438562937e-05, "epoch": 5.709020902090209, "percentage": 28.55, "elapsed_time": "2:02:20", "remaining_time": "5:06:15", "throughput": 1491.86, "total_tokens": 10951168} {"current_steps": 51900, "total_steps": 181800, "loss": 0.0317, "lr": 4.494101691760481e-05, "epoch": 5.70957095709571, "percentage": 28.55, "elapsed_time": "2:02:21", "remaining_time": "5:06:14", "throughput": 1491.86, "total_tokens": 10952224} {"current_steps": 51905, "total_steps": 181800, "loss": 0.0211, "lr": 4.493956926579347e-05, "epoch": 5.71012101210121, "percentage": 28.55, "elapsed_time": "2:02:21", "remaining_time": "5:06:13", "throughput": 1491.87, "total_tokens": 10953312} {"current_steps": 51910, "total_steps": 181800, "loss": 0.0212, "lr": 4.493812143020868e-05, "epoch": 5.710671067106711, "percentage": 28.55, "elapsed_time": "2:02:22", "remaining_time": "5:06:12", "throughput": 1491.88, "total_tokens": 10954368} {"current_steps": 51915, "total_steps": 181800, "loss": 0.007, "lr": 4.493667341086379e-05, "epoch": 5.711221122112211, "percentage": 28.56, "elapsed_time": "2:02:23", "remaining_time": "5:06:12", "throughput": 1491.88, "total_tokens": 10955424} {"current_steps": 51920, "total_steps": 181800, "loss": 0.0441, "lr": 4.493522520777215e-05, "epoch": 5.711771177117711, "percentage": 28.56, "elapsed_time": "2:02:24", "remaining_time": "5:06:11", "throughput": 1491.88, "total_tokens": 10956480} {"current_steps": 51925, "total_steps": 181800, "loss": 0.0418, "lr": 4.493377682094711e-05, "epoch": 5.712321232123212, "percentage": 28.56, "elapsed_time": "2:02:24", "remaining_time": "5:06:10", "throughput": 1491.89, "total_tokens": 10957536} {"current_steps": 51930, "total_steps": 181800, "loss": 0.0217, "lr": 4.4932328250402014e-05, "epoch": 5.712871287128713, "percentage": 28.56, "elapsed_time": "2:02:25", "remaining_time": "5:06:09", "throughput": 1491.89, "total_tokens": 10958592} {"current_steps": 51935, "total_steps": 181800, "loss": 0.0431, "lr": 4.493087949615021e-05, "epoch": 5.713421342134214, "percentage": 28.57, "elapsed_time": "2:02:26", "remaining_time": "5:06:09", "throughput": 1491.89, "total_tokens": 10959616} {"current_steps": 51940, "total_steps": 181800, "loss": 0.0027, "lr": 4.492943055820505e-05, "epoch": 5.713971397139714, "percentage": 28.57, "elapsed_time": "2:02:26", "remaining_time": "5:06:08", "throughput": 1491.89, "total_tokens": 10960672} {"current_steps": 51945, "total_steps": 181800, "loss": 0.0106, "lr": 4.492798143657989e-05, "epoch": 5.714521452145215, "percentage": 28.57, "elapsed_time": "2:02:27", "remaining_time": "5:06:07", "throughput": 1491.89, "total_tokens": 10961696} {"current_steps": 51950, "total_steps": 181800, "loss": 0.0571, "lr": 4.49265321312881e-05, "epoch": 5.715071507150715, "percentage": 28.58, "elapsed_time": "2:02:28", "remaining_time": "5:06:06", "throughput": 1491.9, "total_tokens": 10962784} {"current_steps": 51955, "total_steps": 181800, "loss": 0.0898, "lr": 4.4925082642343016e-05, "epoch": 5.715621562156215, "percentage": 28.58, "elapsed_time": "2:02:28", "remaining_time": "5:06:06", "throughput": 1491.91, "total_tokens": 10963872} {"current_steps": 51960, "total_steps": 181800, "loss": 0.0354, "lr": 4.492363296975801e-05, "epoch": 5.7161716171617165, "percentage": 28.58, "elapsed_time": "2:02:29", "remaining_time": "5:06:05", "throughput": 1491.91, "total_tokens": 10964928} {"current_steps": 51965, "total_steps": 181800, "loss": 0.0136, "lr": 4.4922183113546435e-05, "epoch": 5.716721672167217, "percentage": 28.58, "elapsed_time": "2:02:30", "remaining_time": "5:06:04", "throughput": 1491.91, "total_tokens": 10965952} {"current_steps": 51970, "total_steps": 181800, "loss": 0.0567, "lr": 4.4920733073721664e-05, "epoch": 5.717271727172717, "percentage": 28.59, "elapsed_time": "2:02:30", "remaining_time": "5:06:03", "throughput": 1491.91, "total_tokens": 10966976} {"current_steps": 51975, "total_steps": 181800, "loss": 0.0066, "lr": 4.491928285029705e-05, "epoch": 5.717821782178218, "percentage": 28.59, "elapsed_time": "2:02:31", "remaining_time": "5:06:03", "throughput": 1491.91, "total_tokens": 10968032} {"current_steps": 51980, "total_steps": 181800, "loss": 0.0545, "lr": 4.4917832443285965e-05, "epoch": 5.718371837183718, "percentage": 28.59, "elapsed_time": "2:02:32", "remaining_time": "5:06:02", "throughput": 1491.92, "total_tokens": 10969088} {"current_steps": 51985, "total_steps": 181800, "loss": 0.1169, "lr": 4.491638185270177e-05, "epoch": 5.718921892189218, "percentage": 28.59, "elapsed_time": "2:02:33", "remaining_time": "5:06:01", "throughput": 1491.92, "total_tokens": 10970144} {"current_steps": 51990, "total_steps": 181800, "loss": 0.0721, "lr": 4.491493107855785e-05, "epoch": 5.7194719471947195, "percentage": 28.6, "elapsed_time": "2:02:33", "remaining_time": "5:06:00", "throughput": 1491.94, "total_tokens": 10971296} {"current_steps": 51995, "total_steps": 181800, "loss": 0.0413, "lr": 4.491348012086757e-05, "epoch": 5.72002200220022, "percentage": 28.6, "elapsed_time": "2:02:34", "remaining_time": "5:06:00", "throughput": 1491.95, "total_tokens": 10972416} {"current_steps": 52000, "total_steps": 181800, "loss": 0.0046, "lr": 4.4912028979644286e-05, "epoch": 5.720572057205721, "percentage": 28.6, "elapsed_time": "2:02:35", "remaining_time": "5:05:59", "throughput": 1491.95, "total_tokens": 10973472} {"current_steps": 52005, "total_steps": 181800, "loss": 0.0126, "lr": 4.491057765490139e-05, "epoch": 5.721122112211221, "percentage": 28.61, "elapsed_time": "2:02:35", "remaining_time": "5:05:58", "throughput": 1491.95, "total_tokens": 10974496} {"current_steps": 52010, "total_steps": 181800, "loss": 0.0135, "lr": 4.490912614665226e-05, "epoch": 5.721672167216722, "percentage": 28.61, "elapsed_time": "2:02:36", "remaining_time": "5:05:57", "throughput": 1491.96, "total_tokens": 10975616} {"current_steps": 52015, "total_steps": 181800, "loss": 0.0626, "lr": 4.4907674454910265e-05, "epoch": 5.722222222222222, "percentage": 28.61, "elapsed_time": "2:02:37", "remaining_time": "5:05:57", "throughput": 1491.97, "total_tokens": 10976672} {"current_steps": 52020, "total_steps": 181800, "loss": 0.1634, "lr": 4.4906222579688784e-05, "epoch": 5.7227722772277225, "percentage": 28.61, "elapsed_time": "2:02:37", "remaining_time": "5:05:56", "throughput": 1491.97, "total_tokens": 10977696} {"current_steps": 52025, "total_steps": 181800, "loss": 0.1024, "lr": 4.49047705210012e-05, "epoch": 5.723322332233224, "percentage": 28.62, "elapsed_time": "2:02:38", "remaining_time": "5:05:55", "throughput": 1491.97, "total_tokens": 10978752} {"current_steps": 52030, "total_steps": 181800, "loss": 0.1566, "lr": 4.49033182788609e-05, "epoch": 5.723872387238724, "percentage": 28.62, "elapsed_time": "2:02:39", "remaining_time": "5:05:54", "throughput": 1491.98, "total_tokens": 10979808} {"current_steps": 52035, "total_steps": 181800, "loss": 0.0484, "lr": 4.490186585328127e-05, "epoch": 5.724422442244224, "percentage": 28.62, "elapsed_time": "2:02:39", "remaining_time": "5:05:54", "throughput": 1491.97, "total_tokens": 10980800} {"current_steps": 52040, "total_steps": 181800, "loss": 0.0225, "lr": 4.4900413244275686e-05, "epoch": 5.724972497249725, "percentage": 28.62, "elapsed_time": "2:02:40", "remaining_time": "5:05:53", "throughput": 1491.97, "total_tokens": 10981824} {"current_steps": 52045, "total_steps": 181800, "loss": 0.0587, "lr": 4.489896045185754e-05, "epoch": 5.725522552255225, "percentage": 28.63, "elapsed_time": "2:02:41", "remaining_time": "5:05:52", "throughput": 1491.97, "total_tokens": 10982880} {"current_steps": 52050, "total_steps": 181800, "loss": 0.086, "lr": 4.4897507476040235e-05, "epoch": 5.726072607260726, "percentage": 28.63, "elapsed_time": "2:02:42", "remaining_time": "5:05:51", "throughput": 1491.96, "total_tokens": 10983840} {"current_steps": 52055, "total_steps": 181800, "loss": 0.0043, "lr": 4.4896054316837146e-05, "epoch": 5.726622662266227, "percentage": 28.63, "elapsed_time": "2:02:42", "remaining_time": "5:05:51", "throughput": 1491.96, "total_tokens": 10984864} {"current_steps": 52060, "total_steps": 181800, "loss": 0.0581, "lr": 4.489460097426167e-05, "epoch": 5.727172717271727, "percentage": 28.64, "elapsed_time": "2:02:43", "remaining_time": "5:05:50", "throughput": 1491.97, "total_tokens": 10985920} {"current_steps": 52065, "total_steps": 181800, "loss": 0.0175, "lr": 4.48931474483272e-05, "epoch": 5.727722772277228, "percentage": 28.64, "elapsed_time": "2:02:44", "remaining_time": "5:05:49", "throughput": 1491.98, "total_tokens": 10987008} {"current_steps": 52070, "total_steps": 181800, "loss": 0.0255, "lr": 4.489169373904713e-05, "epoch": 5.728272827282728, "percentage": 28.64, "elapsed_time": "2:02:44", "remaining_time": "5:05:48", "throughput": 1491.98, "total_tokens": 10988064} {"current_steps": 52075, "total_steps": 181800, "loss": 0.035, "lr": 4.489023984643488e-05, "epoch": 5.728822882288229, "percentage": 28.64, "elapsed_time": "2:02:45", "remaining_time": "5:05:48", "throughput": 1491.97, "total_tokens": 10989056} {"current_steps": 52080, "total_steps": 181800, "loss": 0.0296, "lr": 4.488878577050383e-05, "epoch": 5.729372937293729, "percentage": 28.65, "elapsed_time": "2:02:46", "remaining_time": "5:05:47", "throughput": 1491.98, "total_tokens": 10990144} {"current_steps": 52085, "total_steps": 181800, "loss": 0.111, "lr": 4.4887331511267384e-05, "epoch": 5.72992299229923, "percentage": 28.65, "elapsed_time": "2:02:46", "remaining_time": "5:05:46", "throughput": 1492.0, "total_tokens": 10991296} {"current_steps": 52090, "total_steps": 181800, "loss": 0.0505, "lr": 4.488587706873894e-05, "epoch": 5.730473047304731, "percentage": 28.65, "elapsed_time": "2:02:47", "remaining_time": "5:05:45", "throughput": 1492.0, "total_tokens": 10992320} {"current_steps": 52095, "total_steps": 181800, "loss": 0.0125, "lr": 4.488442244293192e-05, "epoch": 5.731023102310231, "percentage": 28.66, "elapsed_time": "2:02:48", "remaining_time": "5:05:45", "throughput": 1492.01, "total_tokens": 10993440} {"current_steps": 52100, "total_steps": 181800, "loss": 0.0988, "lr": 4.4882967633859705e-05, "epoch": 5.731573157315731, "percentage": 28.66, "elapsed_time": "2:02:48", "remaining_time": "5:05:44", "throughput": 1492.01, "total_tokens": 10994464} {"current_steps": 52105, "total_steps": 181800, "loss": 0.0042, "lr": 4.488151264153573e-05, "epoch": 5.732123212321232, "percentage": 28.66, "elapsed_time": "2:02:49", "remaining_time": "5:05:43", "throughput": 1492.01, "total_tokens": 10995488} {"current_steps": 52110, "total_steps": 181800, "loss": 0.0114, "lr": 4.488005746597338e-05, "epoch": 5.732673267326732, "percentage": 28.66, "elapsed_time": "2:02:50", "remaining_time": "5:05:42", "throughput": 1492.01, "total_tokens": 10996544} {"current_steps": 52115, "total_steps": 181800, "loss": 0.0409, "lr": 4.48786021071861e-05, "epoch": 5.7332233223322335, "percentage": 28.67, "elapsed_time": "2:02:50", "remaining_time": "5:05:42", "throughput": 1492.01, "total_tokens": 10997600} {"current_steps": 52120, "total_steps": 181800, "loss": 0.0722, "lr": 4.4877146565187264e-05, "epoch": 5.733773377337734, "percentage": 28.67, "elapsed_time": "2:02:51", "remaining_time": "5:05:41", "throughput": 1492.02, "total_tokens": 10998688} {"current_steps": 52125, "total_steps": 181800, "loss": 0.0384, "lr": 4.4875690839990316e-05, "epoch": 5.734323432343234, "percentage": 28.67, "elapsed_time": "2:02:52", "remaining_time": "5:05:40", "throughput": 1492.02, "total_tokens": 10999712} {"current_steps": 52130, "total_steps": 181800, "loss": 0.0563, "lr": 4.487423493160866e-05, "epoch": 5.734873487348735, "percentage": 28.67, "elapsed_time": "2:02:53", "remaining_time": "5:05:39", "throughput": 1492.02, "total_tokens": 11000704} {"current_steps": 52135, "total_steps": 181800, "loss": 0.0538, "lr": 4.4872778840055715e-05, "epoch": 5.735423542354235, "percentage": 28.68, "elapsed_time": "2:02:53", "remaining_time": "5:05:39", "throughput": 1492.02, "total_tokens": 11001792} {"current_steps": 52140, "total_steps": 181800, "loss": 0.0725, "lr": 4.487132256534491e-05, "epoch": 5.735973597359736, "percentage": 28.68, "elapsed_time": "2:02:54", "remaining_time": "5:05:38", "throughput": 1492.02, "total_tokens": 11002816} {"current_steps": 52145, "total_steps": 181800, "loss": 0.0956, "lr": 4.4869866107489656e-05, "epoch": 5.7365236523652365, "percentage": 28.68, "elapsed_time": "2:02:55", "remaining_time": "5:05:37", "throughput": 1492.04, "total_tokens": 11003936} {"current_steps": 52150, "total_steps": 181800, "loss": 0.0074, "lr": 4.486840946650338e-05, "epoch": 5.737073707370737, "percentage": 28.69, "elapsed_time": "2:02:55", "remaining_time": "5:05:36", "throughput": 1492.04, "total_tokens": 11004992} {"current_steps": 52155, "total_steps": 181800, "loss": 0.0366, "lr": 4.486695264239951e-05, "epoch": 5.737623762376238, "percentage": 28.69, "elapsed_time": "2:02:56", "remaining_time": "5:05:36", "throughput": 1492.04, "total_tokens": 11006048} {"current_steps": 52160, "total_steps": 181800, "loss": 0.0714, "lr": 4.486549563519147e-05, "epoch": 5.738173817381738, "percentage": 28.69, "elapsed_time": "2:02:57", "remaining_time": "5:05:35", "throughput": 1492.04, "total_tokens": 11007072} {"current_steps": 52165, "total_steps": 181800, "loss": 0.019, "lr": 4.4864038444892685e-05, "epoch": 5.738723872387238, "percentage": 28.69, "elapsed_time": "2:02:57", "remaining_time": "5:05:34", "throughput": 1492.04, "total_tokens": 11008096} {"current_steps": 52170, "total_steps": 181800, "loss": 0.0274, "lr": 4.48625810715166e-05, "epoch": 5.739273927392739, "percentage": 28.7, "elapsed_time": "2:02:58", "remaining_time": "5:05:33", "throughput": 1492.04, "total_tokens": 11009120} {"current_steps": 52175, "total_steps": 181800, "loss": 0.0134, "lr": 4.486112351507663e-05, "epoch": 5.7398239823982395, "percentage": 28.7, "elapsed_time": "2:02:59", "remaining_time": "5:05:33", "throughput": 1492.04, "total_tokens": 11010144} {"current_steps": 52180, "total_steps": 181800, "loss": 0.0239, "lr": 4.485966577558621e-05, "epoch": 5.740374037403741, "percentage": 28.7, "elapsed_time": "2:02:59", "remaining_time": "5:05:32", "throughput": 1492.05, "total_tokens": 11011232} {"current_steps": 52185, "total_steps": 181800, "loss": 0.1724, "lr": 4.485820785305879e-05, "epoch": 5.740924092409241, "percentage": 28.7, "elapsed_time": "2:03:00", "remaining_time": "5:05:31", "throughput": 1492.06, "total_tokens": 11012352} {"current_steps": 52190, "total_steps": 181800, "loss": 0.0985, "lr": 4.485674974750779e-05, "epoch": 5.741474147414742, "percentage": 28.71, "elapsed_time": "2:03:01", "remaining_time": "5:05:30", "throughput": 1492.06, "total_tokens": 11013408} {"current_steps": 52195, "total_steps": 181800, "loss": 0.108, "lr": 4.4855291458946655e-05, "epoch": 5.742024202420242, "percentage": 28.71, "elapsed_time": "2:03:02", "remaining_time": "5:05:30", "throughput": 1492.07, "total_tokens": 11014528} {"current_steps": 52200, "total_steps": 181800, "loss": 0.048, "lr": 4.485383298738882e-05, "epoch": 5.742574257425742, "percentage": 28.71, "elapsed_time": "2:03:02", "remaining_time": "5:05:29", "throughput": 1492.09, "total_tokens": 11015648} {"current_steps": 52205, "total_steps": 181800, "loss": 0.0325, "lr": 4.485237433284775e-05, "epoch": 5.743124312431243, "percentage": 28.72, "elapsed_time": "2:03:03", "remaining_time": "5:05:28", "throughput": 1492.08, "total_tokens": 11016640} {"current_steps": 52210, "total_steps": 181800, "loss": 0.0949, "lr": 4.485091549533686e-05, "epoch": 5.743674367436744, "percentage": 28.72, "elapsed_time": "2:03:04", "remaining_time": "5:05:27", "throughput": 1492.09, "total_tokens": 11017696} {"current_steps": 52215, "total_steps": 181800, "loss": 0.0124, "lr": 4.484945647486961e-05, "epoch": 5.744224422442244, "percentage": 28.72, "elapsed_time": "2:03:04", "remaining_time": "5:05:27", "throughput": 1492.09, "total_tokens": 11018720} {"current_steps": 52220, "total_steps": 181800, "loss": 0.0229, "lr": 4.484799727145944e-05, "epoch": 5.744774477447745, "percentage": 28.72, "elapsed_time": "2:03:05", "remaining_time": "5:05:26", "throughput": 1492.08, "total_tokens": 11019712} {"current_steps": 52225, "total_steps": 181800, "loss": 0.0075, "lr": 4.484653788511981e-05, "epoch": 5.745324532453245, "percentage": 28.73, "elapsed_time": "2:03:06", "remaining_time": "5:05:25", "throughput": 1492.08, "total_tokens": 11020768} {"current_steps": 52230, "total_steps": 181800, "loss": 0.0195, "lr": 4.4845078315864165e-05, "epoch": 5.745874587458746, "percentage": 28.73, "elapsed_time": "2:03:06", "remaining_time": "5:05:24", "throughput": 1492.08, "total_tokens": 11021792} {"current_steps": 52235, "total_steps": 181800, "loss": 0.0828, "lr": 4.484361856370595e-05, "epoch": 5.7464246424642464, "percentage": 28.73, "elapsed_time": "2:03:07", "remaining_time": "5:05:24", "throughput": 1492.09, "total_tokens": 11022880} {"current_steps": 52240, "total_steps": 181800, "loss": 0.0922, "lr": 4.4842158628658625e-05, "epoch": 5.746974697469747, "percentage": 28.73, "elapsed_time": "2:03:08", "remaining_time": "5:05:23", "throughput": 1492.1, "total_tokens": 11023968} {"current_steps": 52245, "total_steps": 181800, "loss": 0.1193, "lr": 4.4840698510735646e-05, "epoch": 5.747524752475248, "percentage": 28.74, "elapsed_time": "2:03:08", "remaining_time": "5:05:22", "throughput": 1492.1, "total_tokens": 11025024} {"current_steps": 52250, "total_steps": 181800, "loss": 0.0073, "lr": 4.483923820995047e-05, "epoch": 5.748074807480748, "percentage": 28.74, "elapsed_time": "2:03:09", "remaining_time": "5:05:22", "throughput": 1492.07, "total_tokens": 11026112} {"current_steps": 52255, "total_steps": 181800, "loss": 0.0093, "lr": 4.483777772631656e-05, "epoch": 5.748624862486249, "percentage": 28.74, "elapsed_time": "2:03:10", "remaining_time": "5:05:21", "throughput": 1492.08, "total_tokens": 11027168} {"current_steps": 52260, "total_steps": 181800, "loss": 0.0806, "lr": 4.4836317059847366e-05, "epoch": 5.749174917491749, "percentage": 28.75, "elapsed_time": "2:03:11", "remaining_time": "5:05:20", "throughput": 1492.08, "total_tokens": 11028224} {"current_steps": 52265, "total_steps": 181800, "loss": 0.0113, "lr": 4.483485621055636e-05, "epoch": 5.7497249724972495, "percentage": 28.75, "elapsed_time": "2:03:11", "remaining_time": "5:05:20", "throughput": 1492.08, "total_tokens": 11029248} {"current_steps": 52270, "total_steps": 181800, "loss": 0.0248, "lr": 4.483339517845699e-05, "epoch": 5.7502750275027505, "percentage": 28.75, "elapsed_time": "2:03:12", "remaining_time": "5:05:19", "throughput": 1492.08, "total_tokens": 11030272} {"current_steps": 52275, "total_steps": 181800, "loss": 0.1043, "lr": 4.483193396356275e-05, "epoch": 5.750825082508251, "percentage": 28.75, "elapsed_time": "2:03:13", "remaining_time": "5:05:18", "throughput": 1492.09, "total_tokens": 11031360} {"current_steps": 52280, "total_steps": 181800, "loss": 0.1034, "lr": 4.483047256588708e-05, "epoch": 5.751375137513751, "percentage": 28.76, "elapsed_time": "2:03:13", "remaining_time": "5:05:17", "throughput": 1492.09, "total_tokens": 11032352} {"current_steps": 52285, "total_steps": 181800, "loss": 0.1161, "lr": 4.482901098544347e-05, "epoch": 5.751925192519252, "percentage": 28.76, "elapsed_time": "2:03:14", "remaining_time": "5:05:17", "throughput": 1492.1, "total_tokens": 11033440} {"current_steps": 52290, "total_steps": 181800, "loss": 0.011, "lr": 4.482754922224538e-05, "epoch": 5.752475247524752, "percentage": 28.76, "elapsed_time": "2:03:15", "remaining_time": "5:05:16", "throughput": 1492.1, "total_tokens": 11034496} {"current_steps": 52295, "total_steps": 181800, "loss": 0.0573, "lr": 4.482608727630627e-05, "epoch": 5.753025302530253, "percentage": 28.77, "elapsed_time": "2:03:15", "remaining_time": "5:05:15", "throughput": 1492.09, "total_tokens": 11035488} {"current_steps": 52300, "total_steps": 181800, "loss": 0.0434, "lr": 4.482462514763963e-05, "epoch": 5.7535753575357536, "percentage": 28.77, "elapsed_time": "2:03:16", "remaining_time": "5:05:14", "throughput": 1492.11, "total_tokens": 11036608} {"current_steps": 52305, "total_steps": 181800, "loss": 0.0295, "lr": 4.482316283625894e-05, "epoch": 5.754125412541254, "percentage": 28.77, "elapsed_time": "2:03:17", "remaining_time": "5:05:14", "throughput": 1492.11, "total_tokens": 11037664} {"current_steps": 52310, "total_steps": 181800, "loss": 0.0722, "lr": 4.4821700342177666e-05, "epoch": 5.754675467546755, "percentage": 28.77, "elapsed_time": "2:03:18", "remaining_time": "5:05:13", "throughput": 1492.11, "total_tokens": 11038688} {"current_steps": 52315, "total_steps": 181800, "loss": 0.0057, "lr": 4.48202376654093e-05, "epoch": 5.755225522552255, "percentage": 28.78, "elapsed_time": "2:03:18", "remaining_time": "5:05:12", "throughput": 1492.11, "total_tokens": 11039712} {"current_steps": 52320, "total_steps": 181800, "loss": 0.0667, "lr": 4.48187748059673e-05, "epoch": 5.755775577557756, "percentage": 28.78, "elapsed_time": "2:03:19", "remaining_time": "5:05:11", "throughput": 1492.12, "total_tokens": 11040800} {"current_steps": 52325, "total_steps": 181800, "loss": 0.0318, "lr": 4.481731176386517e-05, "epoch": 5.756325632563256, "percentage": 28.78, "elapsed_time": "2:03:20", "remaining_time": "5:05:11", "throughput": 1492.12, "total_tokens": 11041824} {"current_steps": 52330, "total_steps": 181800, "loss": 0.0624, "lr": 4.481584853911639e-05, "epoch": 5.756875687568757, "percentage": 28.78, "elapsed_time": "2:03:20", "remaining_time": "5:05:10", "throughput": 1492.13, "total_tokens": 11042912} {"current_steps": 52335, "total_steps": 181800, "loss": 0.0626, "lr": 4.4814385131734435e-05, "epoch": 5.757425742574258, "percentage": 28.79, "elapsed_time": "2:03:21", "remaining_time": "5:05:09", "throughput": 1492.13, "total_tokens": 11043968} {"current_steps": 52340, "total_steps": 181800, "loss": 0.1203, "lr": 4.481292154173281e-05, "epoch": 5.757975797579758, "percentage": 28.79, "elapsed_time": "2:03:22", "remaining_time": "5:05:08", "throughput": 1492.14, "total_tokens": 11045056} {"current_steps": 52345, "total_steps": 181800, "loss": 0.0316, "lr": 4.481145776912499e-05, "epoch": 5.758525852585258, "percentage": 28.79, "elapsed_time": "2:03:22", "remaining_time": "5:05:08", "throughput": 1492.14, "total_tokens": 11046048} {"current_steps": 52350, "total_steps": 181800, "loss": 0.1223, "lr": 4.480999381392447e-05, "epoch": 5.759075907590759, "percentage": 28.8, "elapsed_time": "2:03:23", "remaining_time": "5:05:07", "throughput": 1492.14, "total_tokens": 11047072} {"current_steps": 52355, "total_steps": 181800, "loss": 0.0814, "lr": 4.480852967614474e-05, "epoch": 5.759625962596259, "percentage": 28.8, "elapsed_time": "2:03:24", "remaining_time": "5:05:06", "throughput": 1492.14, "total_tokens": 11048128} {"current_steps": 52360, "total_steps": 181800, "loss": 0.1304, "lr": 4.480706535579929e-05, "epoch": 5.7601760176017605, "percentage": 28.8, "elapsed_time": "2:03:24", "remaining_time": "5:05:05", "throughput": 1492.15, "total_tokens": 11049184} {"current_steps": 52365, "total_steps": 181800, "loss": 0.0489, "lr": 4.4805600852901635e-05, "epoch": 5.760726072607261, "percentage": 28.8, "elapsed_time": "2:03:25", "remaining_time": "5:05:05", "throughput": 1492.16, "total_tokens": 11050304} {"current_steps": 52370, "total_steps": 181800, "loss": 0.0209, "lr": 4.480413616746526e-05, "epoch": 5.761276127612762, "percentage": 28.81, "elapsed_time": "2:03:26", "remaining_time": "5:05:04", "throughput": 1492.17, "total_tokens": 11051392} {"current_steps": 52375, "total_steps": 181800, "loss": 0.1715, "lr": 4.480267129950366e-05, "epoch": 5.761826182618262, "percentage": 28.81, "elapsed_time": "2:03:26", "remaining_time": "5:05:03", "throughput": 1492.16, "total_tokens": 11052384} {"current_steps": 52380, "total_steps": 181800, "loss": 0.0504, "lr": 4.480120624903034e-05, "epoch": 5.762376237623762, "percentage": 28.81, "elapsed_time": "2:03:27", "remaining_time": "5:05:02", "throughput": 1492.16, "total_tokens": 11053440} {"current_steps": 52385, "total_steps": 181800, "loss": 0.0324, "lr": 4.4799741016058806e-05, "epoch": 5.762926292629263, "percentage": 28.81, "elapsed_time": "2:03:28", "remaining_time": "5:05:02", "throughput": 1492.17, "total_tokens": 11054528} {"current_steps": 52390, "total_steps": 181800, "loss": 0.0188, "lr": 4.4798275600602554e-05, "epoch": 5.7634763476347635, "percentage": 28.82, "elapsed_time": "2:03:29", "remaining_time": "5:05:01", "throughput": 1492.17, "total_tokens": 11055520} {"current_steps": 52395, "total_steps": 181800, "loss": 0.071, "lr": 4.479681000267511e-05, "epoch": 5.764026402640264, "percentage": 28.82, "elapsed_time": "2:03:29", "remaining_time": "5:05:00", "throughput": 1492.17, "total_tokens": 11056576} {"current_steps": 52400, "total_steps": 181800, "loss": 0.004, "lr": 4.479534422228996e-05, "epoch": 5.764576457645765, "percentage": 28.82, "elapsed_time": "2:03:30", "remaining_time": "5:04:59", "throughput": 1492.19, "total_tokens": 11057728} {"current_steps": 52405, "total_steps": 181800, "loss": 0.0443, "lr": 4.479387825946062e-05, "epoch": 5.765126512651265, "percentage": 28.83, "elapsed_time": "2:03:31", "remaining_time": "5:04:58", "throughput": 1492.2, "total_tokens": 11058848} {"current_steps": 52410, "total_steps": 181800, "loss": 0.0213, "lr": 4.47924121142006e-05, "epoch": 5.765676567656766, "percentage": 28.83, "elapsed_time": "2:03:31", "remaining_time": "5:04:58", "throughput": 1492.21, "total_tokens": 11059936} {"current_steps": 52415, "total_steps": 181800, "loss": 0.0836, "lr": 4.479094578652342e-05, "epoch": 5.766226622662266, "percentage": 28.83, "elapsed_time": "2:03:32", "remaining_time": "5:04:57", "throughput": 1492.2, "total_tokens": 11060928} {"current_steps": 52420, "total_steps": 181800, "loss": 0.1148, "lr": 4.478947927644258e-05, "epoch": 5.7667766776677665, "percentage": 28.83, "elapsed_time": "2:03:33", "remaining_time": "5:04:56", "throughput": 1492.21, "total_tokens": 11062016} {"current_steps": 52425, "total_steps": 181800, "loss": 0.0649, "lr": 4.478801258397162e-05, "epoch": 5.767326732673268, "percentage": 28.84, "elapsed_time": "2:03:33", "remaining_time": "5:04:55", "throughput": 1492.22, "total_tokens": 11063072} {"current_steps": 52430, "total_steps": 181800, "loss": 0.0588, "lr": 4.478654570912404e-05, "epoch": 5.767876787678768, "percentage": 28.84, "elapsed_time": "2:03:34", "remaining_time": "5:04:55", "throughput": 1492.22, "total_tokens": 11064096} {"current_steps": 52435, "total_steps": 181800, "loss": 0.0404, "lr": 4.478507865191335e-05, "epoch": 5.768426842684269, "percentage": 28.84, "elapsed_time": "2:03:35", "remaining_time": "5:04:54", "throughput": 1492.23, "total_tokens": 11065216} {"current_steps": 52440, "total_steps": 181800, "loss": 0.1032, "lr": 4.47836114123531e-05, "epoch": 5.768976897689769, "percentage": 28.84, "elapsed_time": "2:03:35", "remaining_time": "5:04:53", "throughput": 1492.23, "total_tokens": 11066240} {"current_steps": 52445, "total_steps": 181800, "loss": 0.0975, "lr": 4.4782143990456784e-05, "epoch": 5.769526952695269, "percentage": 28.85, "elapsed_time": "2:03:36", "remaining_time": "5:04:52", "throughput": 1492.22, "total_tokens": 11067232} {"current_steps": 52450, "total_steps": 181800, "loss": 0.0256, "lr": 4.478067638623794e-05, "epoch": 5.77007700770077, "percentage": 28.85, "elapsed_time": "2:03:37", "remaining_time": "5:04:52", "throughput": 1492.22, "total_tokens": 11068256} {"current_steps": 52455, "total_steps": 181800, "loss": 0.0255, "lr": 4.4779208599710096e-05, "epoch": 5.770627062706271, "percentage": 28.85, "elapsed_time": "2:03:37", "remaining_time": "5:04:51", "throughput": 1492.23, "total_tokens": 11069344} {"current_steps": 52460, "total_steps": 181800, "loss": 0.0077, "lr": 4.477774063088679e-05, "epoch": 5.771177117711771, "percentage": 28.86, "elapsed_time": "2:03:38", "remaining_time": "5:04:50", "throughput": 1492.23, "total_tokens": 11070400} {"current_steps": 52465, "total_steps": 181800, "loss": 0.0376, "lr": 4.477627247978152e-05, "epoch": 5.771727172717272, "percentage": 28.86, "elapsed_time": "2:03:39", "remaining_time": "5:04:50", "throughput": 1492.24, "total_tokens": 11071456} {"current_steps": 52470, "total_steps": 181800, "loss": 0.061, "lr": 4.4774804146407844e-05, "epoch": 5.772277227722772, "percentage": 28.86, "elapsed_time": "2:03:40", "remaining_time": "5:04:49", "throughput": 1492.23, "total_tokens": 11072480} {"current_steps": 52475, "total_steps": 181800, "loss": 0.0575, "lr": 4.477333563077929e-05, "epoch": 5.772827282728273, "percentage": 28.86, "elapsed_time": "2:03:40", "remaining_time": "5:04:48", "throughput": 1492.23, "total_tokens": 11073472} {"current_steps": 52480, "total_steps": 181800, "loss": 0.0186, "lr": 4.477186693290939e-05, "epoch": 5.773377337733773, "percentage": 28.87, "elapsed_time": "2:03:41", "remaining_time": "5:04:47", "throughput": 1492.23, "total_tokens": 11074496} {"current_steps": 52485, "total_steps": 181800, "loss": 0.0271, "lr": 4.477039805281167e-05, "epoch": 5.773927392739274, "percentage": 28.87, "elapsed_time": "2:03:42", "remaining_time": "5:04:47", "throughput": 1492.24, "total_tokens": 11075616} {"current_steps": 52490, "total_steps": 181800, "loss": 0.0194, "lr": 4.476892899049969e-05, "epoch": 5.774477447744775, "percentage": 28.87, "elapsed_time": "2:03:42", "remaining_time": "5:04:46", "throughput": 1492.26, "total_tokens": 11076768} {"current_steps": 52495, "total_steps": 181800, "loss": 0.0181, "lr": 4.4767459745986974e-05, "epoch": 5.775027502750275, "percentage": 28.88, "elapsed_time": "2:03:43", "remaining_time": "5:04:45", "throughput": 1492.27, "total_tokens": 11077888} {"current_steps": 52500, "total_steps": 181800, "loss": 0.1411, "lr": 4.476599031928707e-05, "epoch": 5.775577557755776, "percentage": 28.88, "elapsed_time": "2:03:44", "remaining_time": "5:04:44", "throughput": 1492.27, "total_tokens": 11078912} {"current_steps": 52505, "total_steps": 181800, "loss": 0.028, "lr": 4.47645207104135e-05, "epoch": 5.776127612761276, "percentage": 28.88, "elapsed_time": "2:03:44", "remaining_time": "5:04:44", "throughput": 1492.27, "total_tokens": 11079968} {"current_steps": 52510, "total_steps": 181800, "loss": 0.0261, "lr": 4.476305091937984e-05, "epoch": 5.776677667766776, "percentage": 28.88, "elapsed_time": "2:03:45", "remaining_time": "5:04:43", "throughput": 1492.27, "total_tokens": 11080992} {"current_steps": 52515, "total_steps": 181800, "loss": 0.0276, "lr": 4.476158094619963e-05, "epoch": 5.7772277227722775, "percentage": 28.89, "elapsed_time": "2:03:46", "remaining_time": "5:04:42", "throughput": 1492.27, "total_tokens": 11081984} {"current_steps": 52520, "total_steps": 181800, "loss": 0.0061, "lr": 4.47601107908864e-05, "epoch": 5.777777777777778, "percentage": 28.89, "elapsed_time": "2:03:46", "remaining_time": "5:04:41", "throughput": 1492.27, "total_tokens": 11083040} {"current_steps": 52525, "total_steps": 181800, "loss": 0.0058, "lr": 4.475864045345371e-05, "epoch": 5.778327832783278, "percentage": 28.89, "elapsed_time": "2:03:47", "remaining_time": "5:04:41", "throughput": 1492.28, "total_tokens": 11084128} {"current_steps": 52530, "total_steps": 181800, "loss": 0.0353, "lr": 4.475716993391512e-05, "epoch": 5.778877887788779, "percentage": 28.89, "elapsed_time": "2:03:48", "remaining_time": "5:04:40", "throughput": 1492.28, "total_tokens": 11085184} {"current_steps": 52535, "total_steps": 181800, "loss": 0.0838, "lr": 4.475569923228417e-05, "epoch": 5.779427942794279, "percentage": 28.9, "elapsed_time": "2:03:49", "remaining_time": "5:04:39", "throughput": 1492.28, "total_tokens": 11086208} {"current_steps": 52540, "total_steps": 181800, "loss": 0.0692, "lr": 4.475422834857442e-05, "epoch": 5.77997799779978, "percentage": 28.9, "elapsed_time": "2:03:49", "remaining_time": "5:04:38", "throughput": 1492.28, "total_tokens": 11087264} {"current_steps": 52545, "total_steps": 181800, "loss": 0.033, "lr": 4.475275728279943e-05, "epoch": 5.7805280528052805, "percentage": 28.9, "elapsed_time": "2:03:50", "remaining_time": "5:04:38", "throughput": 1492.28, "total_tokens": 11088320} {"current_steps": 52550, "total_steps": 181800, "loss": 0.081, "lr": 4.475128603497275e-05, "epoch": 5.781078107810782, "percentage": 28.91, "elapsed_time": "2:03:51", "remaining_time": "5:04:37", "throughput": 1492.28, "total_tokens": 11089312} {"current_steps": 52555, "total_steps": 181800, "loss": 0.0416, "lr": 4.4749814605107945e-05, "epoch": 5.781628162816282, "percentage": 28.91, "elapsed_time": "2:03:51", "remaining_time": "5:04:36", "throughput": 1492.29, "total_tokens": 11090432} {"current_steps": 52560, "total_steps": 181800, "loss": 0.0256, "lr": 4.474834299321858e-05, "epoch": 5.782178217821782, "percentage": 28.91, "elapsed_time": "2:03:52", "remaining_time": "5:04:35", "throughput": 1492.29, "total_tokens": 11091456} {"current_steps": 52565, "total_steps": 181800, "loss": 0.03, "lr": 4.474687119931821e-05, "epoch": 5.782728272827283, "percentage": 28.91, "elapsed_time": "2:03:53", "remaining_time": "5:04:35", "throughput": 1492.29, "total_tokens": 11092480} {"current_steps": 52570, "total_steps": 181800, "loss": 0.0653, "lr": 4.47453992234204e-05, "epoch": 5.783278327832783, "percentage": 28.92, "elapsed_time": "2:03:53", "remaining_time": "5:04:34", "throughput": 1492.3, "total_tokens": 11093568} {"current_steps": 52575, "total_steps": 181800, "loss": 0.0762, "lr": 4.4743927065538725e-05, "epoch": 5.7838283828382835, "percentage": 28.92, "elapsed_time": "2:03:54", "remaining_time": "5:04:33", "throughput": 1492.3, "total_tokens": 11094624} {"current_steps": 52580, "total_steps": 181800, "loss": 0.1306, "lr": 4.4742454725686744e-05, "epoch": 5.784378437843785, "percentage": 28.92, "elapsed_time": "2:03:55", "remaining_time": "5:04:32", "throughput": 1492.31, "total_tokens": 11095680} {"current_steps": 52585, "total_steps": 181800, "loss": 0.0607, "lr": 4.474098220387803e-05, "epoch": 5.784928492849285, "percentage": 28.92, "elapsed_time": "2:03:55", "remaining_time": "5:04:32", "throughput": 1492.32, "total_tokens": 11096800} {"current_steps": 52590, "total_steps": 181800, "loss": 0.0072, "lr": 4.473950950012617e-05, "epoch": 5.785478547854785, "percentage": 28.93, "elapsed_time": "2:03:56", "remaining_time": "5:04:31", "throughput": 1492.32, "total_tokens": 11097824} {"current_steps": 52595, "total_steps": 181800, "loss": 0.0162, "lr": 4.473803661444471e-05, "epoch": 5.786028602860286, "percentage": 28.93, "elapsed_time": "2:03:57", "remaining_time": "5:04:30", "throughput": 1492.32, "total_tokens": 11098880} {"current_steps": 52600, "total_steps": 181800, "loss": 0.1134, "lr": 4.473656354684724e-05, "epoch": 5.786578657865786, "percentage": 28.93, "elapsed_time": "2:03:58", "remaining_time": "5:04:29", "throughput": 1492.32, "total_tokens": 11099936} {"current_steps": 52605, "total_steps": 181800, "loss": 0.1674, "lr": 4.4735090297347336e-05, "epoch": 5.787128712871287, "percentage": 28.94, "elapsed_time": "2:03:58", "remaining_time": "5:04:29", "throughput": 1492.33, "total_tokens": 11100992} {"current_steps": 52610, "total_steps": 181800, "loss": 0.0303, "lr": 4.473361686595857e-05, "epoch": 5.787678767876788, "percentage": 28.94, "elapsed_time": "2:03:59", "remaining_time": "5:04:28", "throughput": 1492.34, "total_tokens": 11102112} {"current_steps": 52615, "total_steps": 181800, "loss": 0.0296, "lr": 4.4732143252694535e-05, "epoch": 5.788228822882289, "percentage": 28.94, "elapsed_time": "2:04:00", "remaining_time": "5:04:27", "throughput": 1492.33, "total_tokens": 11103104} {"current_steps": 52620, "total_steps": 181800, "loss": 0.0696, "lr": 4.4730669457568794e-05, "epoch": 5.788778877887789, "percentage": 28.94, "elapsed_time": "2:04:00", "remaining_time": "5:04:26", "throughput": 1492.33, "total_tokens": 11104128} {"current_steps": 52625, "total_steps": 181800, "loss": 0.1065, "lr": 4.472919548059495e-05, "epoch": 5.789328932893289, "percentage": 28.95, "elapsed_time": "2:04:01", "remaining_time": "5:04:26", "throughput": 1492.33, "total_tokens": 11105152} {"current_steps": 52630, "total_steps": 181800, "loss": 0.0623, "lr": 4.4727721321786576e-05, "epoch": 5.78987898789879, "percentage": 28.95, "elapsed_time": "2:04:02", "remaining_time": "5:04:25", "throughput": 1492.33, "total_tokens": 11106144} {"current_steps": 52635, "total_steps": 181800, "loss": 0.016, "lr": 4.472624698115726e-05, "epoch": 5.79042904290429, "percentage": 28.95, "elapsed_time": "2:04:02", "remaining_time": "5:04:24", "throughput": 1492.34, "total_tokens": 11107264} {"current_steps": 52640, "total_steps": 181800, "loss": 0.039, "lr": 4.4724772458720585e-05, "epoch": 5.790979097909791, "percentage": 28.95, "elapsed_time": "2:04:03", "remaining_time": "5:04:23", "throughput": 1492.34, "total_tokens": 11108288} {"current_steps": 52645, "total_steps": 181800, "loss": 0.0884, "lr": 4.472329775449016e-05, "epoch": 5.791529152915292, "percentage": 28.96, "elapsed_time": "2:04:04", "remaining_time": "5:04:23", "throughput": 1492.33, "total_tokens": 11109280} {"current_steps": 52650, "total_steps": 181800, "loss": 0.0205, "lr": 4.472182286847955e-05, "epoch": 5.792079207920792, "percentage": 28.96, "elapsed_time": "2:04:04", "remaining_time": "5:04:22", "throughput": 1492.33, "total_tokens": 11110304} {"current_steps": 52655, "total_steps": 181800, "loss": 0.0673, "lr": 4.472034780070237e-05, "epoch": 5.792629262926293, "percentage": 28.96, "elapsed_time": "2:04:05", "remaining_time": "5:04:21", "throughput": 1492.34, "total_tokens": 11111392} {"current_steps": 52660, "total_steps": 181800, "loss": 0.0323, "lr": 4.4718872551172206e-05, "epoch": 5.793179317931793, "percentage": 28.97, "elapsed_time": "2:04:06", "remaining_time": "5:04:20", "throughput": 1492.34, "total_tokens": 11112448} {"current_steps": 52665, "total_steps": 181800, "loss": 0.0163, "lr": 4.471739711990265e-05, "epoch": 5.793729372937293, "percentage": 28.97, "elapsed_time": "2:04:07", "remaining_time": "5:04:20", "throughput": 1492.35, "total_tokens": 11113504} {"current_steps": 52670, "total_steps": 181800, "loss": 0.061, "lr": 4.471592150690731e-05, "epoch": 5.7942794279427945, "percentage": 28.97, "elapsed_time": "2:04:07", "remaining_time": "5:04:19", "throughput": 1492.35, "total_tokens": 11114560} {"current_steps": 52675, "total_steps": 181800, "loss": 0.0103, "lr": 4.471444571219978e-05, "epoch": 5.794829482948295, "percentage": 28.97, "elapsed_time": "2:04:08", "remaining_time": "5:04:18", "throughput": 1492.35, "total_tokens": 11115584} {"current_steps": 52680, "total_steps": 181800, "loss": 0.0894, "lr": 4.471296973579367e-05, "epoch": 5.795379537953796, "percentage": 28.98, "elapsed_time": "2:04:09", "remaining_time": "5:04:17", "throughput": 1492.34, "total_tokens": 11116544} {"current_steps": 52685, "total_steps": 181800, "loss": 0.0475, "lr": 4.4711493577702573e-05, "epoch": 5.795929592959296, "percentage": 28.98, "elapsed_time": "2:04:09", "remaining_time": "5:04:17", "throughput": 1492.34, "total_tokens": 11117568} {"current_steps": 52690, "total_steps": 181800, "loss": 0.0255, "lr": 4.47100172379401e-05, "epoch": 5.796479647964796, "percentage": 28.98, "elapsed_time": "2:04:10", "remaining_time": "5:04:16", "throughput": 1492.34, "total_tokens": 11118592} {"current_steps": 52695, "total_steps": 181800, "loss": 0.0091, "lr": 4.470854071651985e-05, "epoch": 5.797029702970297, "percentage": 28.99, "elapsed_time": "2:04:11", "remaining_time": "5:04:15", "throughput": 1492.34, "total_tokens": 11119584} {"current_steps": 52700, "total_steps": 181800, "loss": 0.0832, "lr": 4.470706401345545e-05, "epoch": 5.7975797579757975, "percentage": 28.99, "elapsed_time": "2:04:11", "remaining_time": "5:04:14", "throughput": 1492.35, "total_tokens": 11120704} {"current_steps": 52705, "total_steps": 181800, "loss": 0.0493, "lr": 4.4705587128760486e-05, "epoch": 5.798129812981298, "percentage": 28.99, "elapsed_time": "2:04:12", "remaining_time": "5:04:14", "throughput": 1492.35, "total_tokens": 11121728} {"current_steps": 52710, "total_steps": 181800, "loss": 0.0898, "lr": 4.470411006244859e-05, "epoch": 5.798679867986799, "percentage": 28.99, "elapsed_time": "2:04:13", "remaining_time": "5:04:13", "throughput": 1492.35, "total_tokens": 11122784} {"current_steps": 52715, "total_steps": 181800, "loss": 0.0228, "lr": 4.470263281453336e-05, "epoch": 5.799229922992299, "percentage": 29.0, "elapsed_time": "2:04:13", "remaining_time": "5:04:12", "throughput": 1492.36, "total_tokens": 11123872} {"current_steps": 52720, "total_steps": 181800, "loss": 0.1064, "lr": 4.4701155385028416e-05, "epoch": 5.7997799779978, "percentage": 29.0, "elapsed_time": "2:04:14", "remaining_time": "5:04:11", "throughput": 1492.37, "total_tokens": 11124960} {"current_steps": 52725, "total_steps": 181800, "loss": 0.0067, "lr": 4.469967777394738e-05, "epoch": 5.8003300330033, "percentage": 29.0, "elapsed_time": "2:04:15", "remaining_time": "5:04:11", "throughput": 1492.37, "total_tokens": 11126048} {"current_steps": 52730, "total_steps": 181800, "loss": 0.0506, "lr": 4.469819998130386e-05, "epoch": 5.8008800880088005, "percentage": 29.0, "elapsed_time": "2:04:15", "remaining_time": "5:04:10", "throughput": 1492.38, "total_tokens": 11127104} {"current_steps": 52735, "total_steps": 181800, "loss": 0.0916, "lr": 4.4696722007111494e-05, "epoch": 5.801430143014302, "percentage": 29.01, "elapsed_time": "2:04:16", "remaining_time": "5:04:09", "throughput": 1492.38, "total_tokens": 11128160} {"current_steps": 52740, "total_steps": 181800, "loss": 0.0174, "lr": 4.469524385138388e-05, "epoch": 5.801980198019802, "percentage": 29.01, "elapsed_time": "2:04:17", "remaining_time": "5:04:08", "throughput": 1492.39, "total_tokens": 11129216} {"current_steps": 52745, "total_steps": 181800, "loss": 0.0234, "lr": 4.469376551413467e-05, "epoch": 5.802530253025303, "percentage": 29.01, "elapsed_time": "2:04:18", "remaining_time": "5:04:08", "throughput": 1492.4, "total_tokens": 11130336} {"current_steps": 52750, "total_steps": 181800, "loss": 0.0287, "lr": 4.469228699537747e-05, "epoch": 5.803080308030803, "percentage": 29.02, "elapsed_time": "2:04:18", "remaining_time": "5:04:07", "throughput": 1492.41, "total_tokens": 11131424} {"current_steps": 52755, "total_steps": 181800, "loss": 0.0574, "lr": 4.4690808295125894e-05, "epoch": 5.803630363036303, "percentage": 29.02, "elapsed_time": "2:04:19", "remaining_time": "5:04:06", "throughput": 1492.4, "total_tokens": 11132448} {"current_steps": 52760, "total_steps": 181800, "loss": 0.0064, "lr": 4.46893294133936e-05, "epoch": 5.804180418041804, "percentage": 29.02, "elapsed_time": "2:04:20", "remaining_time": "5:04:05", "throughput": 1492.41, "total_tokens": 11133504} {"current_steps": 52765, "total_steps": 181800, "loss": 0.0381, "lr": 4.46878503501942e-05, "epoch": 5.804730473047305, "percentage": 29.02, "elapsed_time": "2:04:20", "remaining_time": "5:04:05", "throughput": 1492.42, "total_tokens": 11134592} {"current_steps": 52770, "total_steps": 181800, "loss": 0.1372, "lr": 4.468637110554133e-05, "epoch": 5.805280528052805, "percentage": 29.03, "elapsed_time": "2:04:21", "remaining_time": "5:04:04", "throughput": 1492.42, "total_tokens": 11135648} {"current_steps": 52775, "total_steps": 181800, "loss": 0.0491, "lr": 4.468489167944863e-05, "epoch": 5.805830583058306, "percentage": 29.03, "elapsed_time": "2:04:22", "remaining_time": "5:04:03", "throughput": 1492.43, "total_tokens": 11136736} {"current_steps": 52780, "total_steps": 181800, "loss": 0.0143, "lr": 4.468341207192972e-05, "epoch": 5.806380638063806, "percentage": 29.03, "elapsed_time": "2:04:22", "remaining_time": "5:04:02", "throughput": 1492.43, "total_tokens": 11137792} {"current_steps": 52785, "total_steps": 181800, "loss": 0.0639, "lr": 4.468193228299826e-05, "epoch": 5.806930693069307, "percentage": 29.03, "elapsed_time": "2:04:23", "remaining_time": "5:04:02", "throughput": 1492.43, "total_tokens": 11138784} {"current_steps": 52790, "total_steps": 181800, "loss": 0.0512, "lr": 4.4680452312667856e-05, "epoch": 5.807480748074807, "percentage": 29.04, "elapsed_time": "2:04:24", "remaining_time": "5:04:01", "throughput": 1492.43, "total_tokens": 11139808} {"current_steps": 52795, "total_steps": 181800, "loss": 0.0084, "lr": 4.4678972160952185e-05, "epoch": 5.8080308030803085, "percentage": 29.04, "elapsed_time": "2:04:24", "remaining_time": "5:04:00", "throughput": 1492.43, "total_tokens": 11140864} {"current_steps": 52800, "total_steps": 181800, "loss": 0.1061, "lr": 4.467749182786486e-05, "epoch": 5.808580858085809, "percentage": 29.04, "elapsed_time": "2:04:25", "remaining_time": "5:03:59", "throughput": 1492.44, "total_tokens": 11141952} {"current_steps": 52805, "total_steps": 181800, "loss": 0.0103, "lr": 4.467601131341953e-05, "epoch": 5.809130913091309, "percentage": 29.05, "elapsed_time": "2:04:26", "remaining_time": "5:03:59", "throughput": 1492.45, "total_tokens": 11143072} {"current_steps": 52810, "total_steps": 181800, "loss": 0.0655, "lr": 4.467453061762986e-05, "epoch": 5.80968096809681, "percentage": 29.05, "elapsed_time": "2:04:26", "remaining_time": "5:03:58", "throughput": 1492.46, "total_tokens": 11144128} {"current_steps": 52815, "total_steps": 181800, "loss": 0.0121, "lr": 4.467304974050947e-05, "epoch": 5.81023102310231, "percentage": 29.05, "elapsed_time": "2:04:27", "remaining_time": "5:03:57", "throughput": 1492.46, "total_tokens": 11145184} {"current_steps": 52820, "total_steps": 181800, "loss": 0.1158, "lr": 4.467156868207203e-05, "epoch": 5.81078107810781, "percentage": 29.05, "elapsed_time": "2:04:28", "remaining_time": "5:03:56", "throughput": 1492.47, "total_tokens": 11146272} {"current_steps": 52825, "total_steps": 181800, "loss": 0.0055, "lr": 4.467008744233117e-05, "epoch": 5.8113311331133115, "percentage": 29.06, "elapsed_time": "2:04:29", "remaining_time": "5:03:56", "throughput": 1492.48, "total_tokens": 11147360} {"current_steps": 52830, "total_steps": 181800, "loss": 0.1263, "lr": 4.466860602130056e-05, "epoch": 5.811881188118812, "percentage": 29.06, "elapsed_time": "2:04:29", "remaining_time": "5:03:55", "throughput": 1492.48, "total_tokens": 11148416} {"current_steps": 52835, "total_steps": 181800, "loss": 0.0854, "lr": 4.466712441899384e-05, "epoch": 5.812431243124313, "percentage": 29.06, "elapsed_time": "2:04:30", "remaining_time": "5:03:54", "throughput": 1492.49, "total_tokens": 11149536} {"current_steps": 52840, "total_steps": 181800, "loss": 0.064, "lr": 4.466564263542468e-05, "epoch": 5.812981298129813, "percentage": 29.06, "elapsed_time": "2:04:31", "remaining_time": "5:03:53", "throughput": 1492.49, "total_tokens": 11150592} {"current_steps": 52845, "total_steps": 181800, "loss": 0.0583, "lr": 4.466416067060673e-05, "epoch": 5.813531353135313, "percentage": 29.07, "elapsed_time": "2:04:31", "remaining_time": "5:03:53", "throughput": 1492.49, "total_tokens": 11151584} {"current_steps": 52850, "total_steps": 181800, "loss": 0.0432, "lr": 4.4662678524553635e-05, "epoch": 5.814081408140814, "percentage": 29.07, "elapsed_time": "2:04:32", "remaining_time": "5:03:52", "throughput": 1492.49, "total_tokens": 11152576} {"current_steps": 52855, "total_steps": 181800, "loss": 0.0545, "lr": 4.466119619727907e-05, "epoch": 5.8146314631463145, "percentage": 29.07, "elapsed_time": "2:04:33", "remaining_time": "5:03:51", "throughput": 1492.49, "total_tokens": 11153664} {"current_steps": 52860, "total_steps": 181800, "loss": 0.1174, "lr": 4.46597136887967e-05, "epoch": 5.815181518151816, "percentage": 29.08, "elapsed_time": "2:04:33", "remaining_time": "5:03:50", "throughput": 1492.49, "total_tokens": 11154688} {"current_steps": 52865, "total_steps": 181800, "loss": 0.1267, "lr": 4.4658230999120174e-05, "epoch": 5.815731573157316, "percentage": 29.08, "elapsed_time": "2:04:34", "remaining_time": "5:03:50", "throughput": 1492.5, "total_tokens": 11155744} {"current_steps": 52870, "total_steps": 181800, "loss": 0.0624, "lr": 4.465674812826318e-05, "epoch": 5.816281628162816, "percentage": 29.08, "elapsed_time": "2:04:35", "remaining_time": "5:03:49", "throughput": 1492.5, "total_tokens": 11156800} {"current_steps": 52875, "total_steps": 181800, "loss": 0.0923, "lr": 4.465526507623936e-05, "epoch": 5.816831683168317, "percentage": 29.08, "elapsed_time": "2:04:35", "remaining_time": "5:03:48", "throughput": 1492.5, "total_tokens": 11157792} {"current_steps": 52880, "total_steps": 181800, "loss": 0.0195, "lr": 4.465378184306239e-05, "epoch": 5.817381738173817, "percentage": 29.09, "elapsed_time": "2:04:36", "remaining_time": "5:03:47", "throughput": 1492.5, "total_tokens": 11158848} {"current_steps": 52885, "total_steps": 181800, "loss": 0.0579, "lr": 4.4652298428745954e-05, "epoch": 5.8179317931793175, "percentage": 29.09, "elapsed_time": "2:04:37", "remaining_time": "5:03:47", "throughput": 1492.5, "total_tokens": 11159872} {"current_steps": 52890, "total_steps": 181800, "loss": 0.0975, "lr": 4.465081483330371e-05, "epoch": 5.818481848184819, "percentage": 29.09, "elapsed_time": "2:04:37", "remaining_time": "5:03:46", "throughput": 1492.5, "total_tokens": 11160928} {"current_steps": 52895, "total_steps": 181800, "loss": 0.092, "lr": 4.4649331056749335e-05, "epoch": 5.819031903190319, "percentage": 29.1, "elapsed_time": "2:04:38", "remaining_time": "5:03:45", "throughput": 1492.51, "total_tokens": 11161984} {"current_steps": 52900, "total_steps": 181800, "loss": 0.071, "lr": 4.46478470990965e-05, "epoch": 5.81958195819582, "percentage": 29.1, "elapsed_time": "2:04:39", "remaining_time": "5:03:44", "throughput": 1492.52, "total_tokens": 11163104} {"current_steps": 52905, "total_steps": 181800, "loss": 0.0401, "lr": 4.464636296035889e-05, "epoch": 5.82013201320132, "percentage": 29.1, "elapsed_time": "2:04:40", "remaining_time": "5:03:44", "throughput": 1492.53, "total_tokens": 11164224} {"current_steps": 52910, "total_steps": 181800, "loss": 0.0497, "lr": 4.4644878640550184e-05, "epoch": 5.82068206820682, "percentage": 29.1, "elapsed_time": "2:04:40", "remaining_time": "5:03:43", "throughput": 1492.54, "total_tokens": 11165280} {"current_steps": 52915, "total_steps": 181800, "loss": 0.0174, "lr": 4.4643394139684045e-05, "epoch": 5.821232123212321, "percentage": 29.11, "elapsed_time": "2:04:41", "remaining_time": "5:03:42", "throughput": 1492.53, "total_tokens": 11166272} {"current_steps": 52920, "total_steps": 181800, "loss": 0.0288, "lr": 4.464190945777418e-05, "epoch": 5.821782178217822, "percentage": 29.11, "elapsed_time": "2:04:42", "remaining_time": "5:03:41", "throughput": 1492.53, "total_tokens": 11167296} {"current_steps": 52925, "total_steps": 181800, "loss": 0.0344, "lr": 4.464042459483425e-05, "epoch": 5.822332233223323, "percentage": 29.11, "elapsed_time": "2:04:42", "remaining_time": "5:03:40", "throughput": 1492.54, "total_tokens": 11168384} {"current_steps": 52930, "total_steps": 181800, "loss": 0.0106, "lr": 4.4638939550877964e-05, "epoch": 5.822882288228823, "percentage": 29.11, "elapsed_time": "2:04:43", "remaining_time": "5:03:40", "throughput": 1492.55, "total_tokens": 11169440} {"current_steps": 52935, "total_steps": 181800, "loss": 0.0131, "lr": 4.463745432591899e-05, "epoch": 5.823432343234323, "percentage": 29.12, "elapsed_time": "2:04:44", "remaining_time": "5:03:39", "throughput": 1492.55, "total_tokens": 11170464} {"current_steps": 52940, "total_steps": 181800, "loss": 0.0696, "lr": 4.463596891997102e-05, "epoch": 5.823982398239824, "percentage": 29.12, "elapsed_time": "2:04:44", "remaining_time": "5:03:38", "throughput": 1492.54, "total_tokens": 11171456} {"current_steps": 52945, "total_steps": 181800, "loss": 0.0076, "lr": 4.463448333304775e-05, "epoch": 5.824532453245324, "percentage": 29.12, "elapsed_time": "2:04:45", "remaining_time": "5:03:37", "throughput": 1492.56, "total_tokens": 11172608} {"current_steps": 52950, "total_steps": 181800, "loss": 0.1348, "lr": 4.463299756516286e-05, "epoch": 5.825082508250825, "percentage": 29.13, "elapsed_time": "2:04:46", "remaining_time": "5:03:37", "throughput": 1492.56, "total_tokens": 11173696} {"current_steps": 52955, "total_steps": 181800, "loss": 0.0117, "lr": 4.463151161633007e-05, "epoch": 5.825632563256326, "percentage": 29.13, "elapsed_time": "2:04:46", "remaining_time": "5:03:36", "throughput": 1492.58, "total_tokens": 11174816} {"current_steps": 52960, "total_steps": 181800, "loss": 0.0283, "lr": 4.463002548656304e-05, "epoch": 5.826182618261826, "percentage": 29.13, "elapsed_time": "2:04:47", "remaining_time": "5:03:35", "throughput": 1492.58, "total_tokens": 11175904} {"current_steps": 52965, "total_steps": 181800, "loss": 0.009, "lr": 4.46285391758755e-05, "epoch": 5.826732673267327, "percentage": 29.13, "elapsed_time": "2:04:48", "remaining_time": "5:03:34", "throughput": 1492.58, "total_tokens": 11176864} {"current_steps": 52970, "total_steps": 181800, "loss": 0.0051, "lr": 4.462705268428112e-05, "epoch": 5.827282728272827, "percentage": 29.14, "elapsed_time": "2:04:48", "remaining_time": "5:03:34", "throughput": 1492.58, "total_tokens": 11177952} {"current_steps": 52975, "total_steps": 181800, "loss": 0.0553, "lr": 4.462556601179362e-05, "epoch": 5.827832783278328, "percentage": 29.14, "elapsed_time": "2:04:49", "remaining_time": "5:03:33", "throughput": 1492.58, "total_tokens": 11178976} {"current_steps": 52980, "total_steps": 181800, "loss": 0.0726, "lr": 4.462407915842669e-05, "epoch": 5.8283828382838285, "percentage": 29.14, "elapsed_time": "2:04:50", "remaining_time": "5:03:32", "throughput": 1492.59, "total_tokens": 11180032} {"current_steps": 52985, "total_steps": 181800, "loss": 0.029, "lr": 4.462259212419404e-05, "epoch": 5.828932893289329, "percentage": 29.14, "elapsed_time": "2:04:51", "remaining_time": "5:03:31", "throughput": 1492.59, "total_tokens": 11181088} {"current_steps": 52990, "total_steps": 181800, "loss": 0.0842, "lr": 4.462110490910938e-05, "epoch": 5.82948294829483, "percentage": 29.15, "elapsed_time": "2:04:51", "remaining_time": "5:03:31", "throughput": 1492.59, "total_tokens": 11182112} {"current_steps": 52995, "total_steps": 181800, "loss": 0.0541, "lr": 4.4619617513186406e-05, "epoch": 5.83003300330033, "percentage": 29.15, "elapsed_time": "2:04:52", "remaining_time": "5:03:30", "throughput": 1492.59, "total_tokens": 11183168} {"current_steps": 53000, "total_steps": 181800, "loss": 0.1264, "lr": 4.461812993643883e-05, "epoch": 5.83058305830583, "percentage": 29.15, "elapsed_time": "2:04:53", "remaining_time": "5:03:29", "throughput": 1492.59, "total_tokens": 11184192} {"current_steps": 53005, "total_steps": 181800, "loss": 0.0279, "lr": 4.461664217888037e-05, "epoch": 5.831133113311331, "percentage": 29.16, "elapsed_time": "2:04:53", "remaining_time": "5:03:28", "throughput": 1492.59, "total_tokens": 11185216} {"current_steps": 53010, "total_steps": 181800, "loss": 0.0115, "lr": 4.4615154240524736e-05, "epoch": 5.8316831683168315, "percentage": 29.16, "elapsed_time": "2:04:54", "remaining_time": "5:03:28", "throughput": 1492.6, "total_tokens": 11186272} {"current_steps": 53015, "total_steps": 181800, "loss": 0.0972, "lr": 4.4613666121385625e-05, "epoch": 5.832233223322332, "percentage": 29.16, "elapsed_time": "2:04:55", "remaining_time": "5:03:27", "throughput": 1492.61, "total_tokens": 11187392} {"current_steps": 53020, "total_steps": 181800, "loss": 0.0242, "lr": 4.4612177821476774e-05, "epoch": 5.832783278327833, "percentage": 29.16, "elapsed_time": "2:04:55", "remaining_time": "5:03:26", "throughput": 1492.61, "total_tokens": 11188448} {"current_steps": 53025, "total_steps": 181800, "loss": 0.0791, "lr": 4.461068934081189e-05, "epoch": 5.833333333333333, "percentage": 29.17, "elapsed_time": "2:04:56", "remaining_time": "5:03:25", "throughput": 1492.61, "total_tokens": 11189472} {"current_steps": 53030, "total_steps": 181800, "loss": 0.0748, "lr": 4.4609200679404686e-05, "epoch": 5.833883388338834, "percentage": 29.17, "elapsed_time": "2:04:57", "remaining_time": "5:03:25", "throughput": 1492.62, "total_tokens": 11190560} {"current_steps": 53035, "total_steps": 181800, "loss": 0.0465, "lr": 4.4607711837268893e-05, "epoch": 5.834433443344334, "percentage": 29.17, "elapsed_time": "2:04:57", "remaining_time": "5:03:24", "throughput": 1492.62, "total_tokens": 11191616} {"current_steps": 53040, "total_steps": 181800, "loss": 0.0562, "lr": 4.460622281441823e-05, "epoch": 5.834983498349835, "percentage": 29.17, "elapsed_time": "2:04:58", "remaining_time": "5:03:23", "throughput": 1492.62, "total_tokens": 11192640} {"current_steps": 53045, "total_steps": 181800, "loss": 0.0628, "lr": 4.460473361086642e-05, "epoch": 5.835533553355336, "percentage": 29.18, "elapsed_time": "2:04:59", "remaining_time": "5:03:22", "throughput": 1492.63, "total_tokens": 11193696} {"current_steps": 53050, "total_steps": 181800, "loss": 0.0282, "lr": 4.460324422662718e-05, "epoch": 5.836083608360836, "percentage": 29.18, "elapsed_time": "2:05:00", "remaining_time": "5:03:22", "throughput": 1492.63, "total_tokens": 11194720} {"current_steps": 53055, "total_steps": 181800, "loss": 0.0082, "lr": 4.460175466171426e-05, "epoch": 5.836633663366337, "percentage": 29.18, "elapsed_time": "2:05:00", "remaining_time": "5:03:21", "throughput": 1492.63, "total_tokens": 11195808} {"current_steps": 53060, "total_steps": 181800, "loss": 0.172, "lr": 4.4600264916141365e-05, "epoch": 5.837183718371837, "percentage": 29.19, "elapsed_time": "2:05:01", "remaining_time": "5:03:20", "throughput": 1492.64, "total_tokens": 11196896} {"current_steps": 53065, "total_steps": 181800, "loss": 0.0137, "lr": 4.459877498992223e-05, "epoch": 5.837733773377337, "percentage": 29.19, "elapsed_time": "2:05:02", "remaining_time": "5:03:19", "throughput": 1492.64, "total_tokens": 11197920} {"current_steps": 53070, "total_steps": 181800, "loss": 0.0716, "lr": 4.459728488307059e-05, "epoch": 5.838283828382838, "percentage": 29.19, "elapsed_time": "2:05:02", "remaining_time": "5:03:19", "throughput": 1492.64, "total_tokens": 11198976} {"current_steps": 53075, "total_steps": 181800, "loss": 0.0977, "lr": 4.459579459560018e-05, "epoch": 5.838833883388339, "percentage": 29.19, "elapsed_time": "2:05:03", "remaining_time": "5:03:18", "throughput": 1492.64, "total_tokens": 11199968} {"current_steps": 53080, "total_steps": 181800, "loss": 0.0265, "lr": 4.459430412752473e-05, "epoch": 5.83938393839384, "percentage": 29.2, "elapsed_time": "2:05:04", "remaining_time": "5:03:17", "throughput": 1492.64, "total_tokens": 11201056} {"current_steps": 53085, "total_steps": 181800, "loss": 0.0857, "lr": 4.4592813478857995e-05, "epoch": 5.83993399339934, "percentage": 29.2, "elapsed_time": "2:05:04", "remaining_time": "5:03:16", "throughput": 1492.65, "total_tokens": 11202112} {"current_steps": 53090, "total_steps": 181800, "loss": 0.0838, "lr": 4.4591322649613685e-05, "epoch": 5.84048404840484, "percentage": 29.2, "elapsed_time": "2:05:05", "remaining_time": "5:03:16", "throughput": 1492.65, "total_tokens": 11203168} {"current_steps": 53095, "total_steps": 181800, "loss": 0.0568, "lr": 4.458983163980557e-05, "epoch": 5.841034103410341, "percentage": 29.21, "elapsed_time": "2:05:06", "remaining_time": "5:03:15", "throughput": 1492.66, "total_tokens": 11204224} {"current_steps": 53100, "total_steps": 181800, "loss": 0.0567, "lr": 4.458834044944736e-05, "epoch": 5.841584158415841, "percentage": 29.21, "elapsed_time": "2:05:06", "remaining_time": "5:03:14", "throughput": 1492.67, "total_tokens": 11205344} {"current_steps": 53105, "total_steps": 181800, "loss": 0.0365, "lr": 4.458684907855283e-05, "epoch": 5.8421342134213425, "percentage": 29.21, "elapsed_time": "2:05:07", "remaining_time": "5:03:13", "throughput": 1492.66, "total_tokens": 11206336} {"current_steps": 53110, "total_steps": 181800, "loss": 0.0481, "lr": 4.45853575271357e-05, "epoch": 5.842684268426843, "percentage": 29.21, "elapsed_time": "2:05:08", "remaining_time": "5:03:13", "throughput": 1492.67, "total_tokens": 11207392} {"current_steps": 53115, "total_steps": 181800, "loss": 0.0358, "lr": 4.458386579520973e-05, "epoch": 5.843234323432343, "percentage": 29.22, "elapsed_time": "2:05:08", "remaining_time": "5:03:12", "throughput": 1492.67, "total_tokens": 11208416} {"current_steps": 53120, "total_steps": 181800, "loss": 0.0411, "lr": 4.4582373882788676e-05, "epoch": 5.843784378437844, "percentage": 29.22, "elapsed_time": "2:05:09", "remaining_time": "5:03:11", "throughput": 1492.67, "total_tokens": 11209472} {"current_steps": 53125, "total_steps": 181800, "loss": 0.1087, "lr": 4.4580881789886264e-05, "epoch": 5.844334433443344, "percentage": 29.22, "elapsed_time": "2:05:10", "remaining_time": "5:03:11", "throughput": 1492.67, "total_tokens": 11210496} {"current_steps": 53130, "total_steps": 181800, "loss": 0.007, "lr": 4.4579389516516265e-05, "epoch": 5.8448844884488445, "percentage": 29.22, "elapsed_time": "2:05:11", "remaining_time": "5:03:10", "throughput": 1492.67, "total_tokens": 11211552} {"current_steps": 53135, "total_steps": 181800, "loss": 0.0493, "lr": 4.457789706269243e-05, "epoch": 5.8454345434543455, "percentage": 29.23, "elapsed_time": "2:05:11", "remaining_time": "5:03:09", "throughput": 1492.68, "total_tokens": 11212608} {"current_steps": 53140, "total_steps": 181800, "loss": 0.0732, "lr": 4.457640442842851e-05, "epoch": 5.845984598459846, "percentage": 29.23, "elapsed_time": "2:05:12", "remaining_time": "5:03:08", "throughput": 1492.68, "total_tokens": 11213696} {"current_steps": 53145, "total_steps": 181800, "loss": 0.0401, "lr": 4.457491161373827e-05, "epoch": 5.846534653465347, "percentage": 29.23, "elapsed_time": "2:05:13", "remaining_time": "5:03:08", "throughput": 1492.68, "total_tokens": 11214688} {"current_steps": 53150, "total_steps": 181800, "loss": 0.0307, "lr": 4.4573418618635465e-05, "epoch": 5.847084708470847, "percentage": 29.24, "elapsed_time": "2:05:13", "remaining_time": "5:03:07", "throughput": 1492.69, "total_tokens": 11215776} {"current_steps": 53155, "total_steps": 181800, "loss": 0.0422, "lr": 4.4571925443133846e-05, "epoch": 5.847634763476347, "percentage": 29.24, "elapsed_time": "2:05:14", "remaining_time": "5:03:06", "throughput": 1492.69, "total_tokens": 11216832} {"current_steps": 53160, "total_steps": 181800, "loss": 0.0089, "lr": 4.4570432087247175e-05, "epoch": 5.848184818481848, "percentage": 29.24, "elapsed_time": "2:05:15", "remaining_time": "5:03:05", "throughput": 1492.7, "total_tokens": 11217920} {"current_steps": 53165, "total_steps": 181800, "loss": 0.0207, "lr": 4.456893855098924e-05, "epoch": 5.8487348734873486, "percentage": 29.24, "elapsed_time": "2:05:15", "remaining_time": "5:03:05", "throughput": 1492.69, "total_tokens": 11218912} {"current_steps": 53170, "total_steps": 181800, "loss": 0.0135, "lr": 4.456744483437377e-05, "epoch": 5.84928492849285, "percentage": 29.25, "elapsed_time": "2:05:16", "remaining_time": "5:03:04", "throughput": 1492.69, "total_tokens": 11219936} {"current_steps": 53175, "total_steps": 181800, "loss": 0.0254, "lr": 4.456595093741456e-05, "epoch": 5.84983498349835, "percentage": 29.25, "elapsed_time": "2:05:17", "remaining_time": "5:03:03", "throughput": 1492.69, "total_tokens": 11220960} {"current_steps": 53180, "total_steps": 181800, "loss": 0.0174, "lr": 4.456445686012537e-05, "epoch": 5.85038503850385, "percentage": 29.25, "elapsed_time": "2:05:17", "remaining_time": "5:03:02", "throughput": 1492.69, "total_tokens": 11221984} {"current_steps": 53185, "total_steps": 181800, "loss": 0.0163, "lr": 4.456296260251996e-05, "epoch": 5.850935093509351, "percentage": 29.25, "elapsed_time": "2:05:18", "remaining_time": "5:03:01", "throughput": 1492.7, "total_tokens": 11223072} {"current_steps": 53190, "total_steps": 181800, "loss": 0.013, "lr": 4.456146816461212e-05, "epoch": 5.851485148514851, "percentage": 29.26, "elapsed_time": "2:05:19", "remaining_time": "5:03:01", "throughput": 1492.7, "total_tokens": 11224096} {"current_steps": 53195, "total_steps": 181800, "loss": 0.0301, "lr": 4.4559973546415614e-05, "epoch": 5.852035203520352, "percentage": 29.26, "elapsed_time": "2:05:20", "remaining_time": "5:03:00", "throughput": 1492.71, "total_tokens": 11225152} {"current_steps": 53200, "total_steps": 181800, "loss": 0.0463, "lr": 4.455847874794421e-05, "epoch": 5.852585258525853, "percentage": 29.26, "elapsed_time": "2:05:20", "remaining_time": "5:02:59", "throughput": 1492.72, "total_tokens": 11226304} {"current_steps": 53205, "total_steps": 181800, "loss": 0.0776, "lr": 4.45569837692117e-05, "epoch": 5.853135313531353, "percentage": 29.27, "elapsed_time": "2:05:21", "remaining_time": "5:02:58", "throughput": 1492.73, "total_tokens": 11227392} {"current_steps": 53210, "total_steps": 181800, "loss": 0.0787, "lr": 4.4555488610231854e-05, "epoch": 5.853685368536854, "percentage": 29.27, "elapsed_time": "2:05:22", "remaining_time": "5:02:58", "throughput": 1492.73, "total_tokens": 11228448} {"current_steps": 53215, "total_steps": 181800, "loss": 0.0727, "lr": 4.455399327101845e-05, "epoch": 5.854235423542354, "percentage": 29.27, "elapsed_time": "2:05:22", "remaining_time": "5:02:57", "throughput": 1492.74, "total_tokens": 11229536} {"current_steps": 53220, "total_steps": 181800, "loss": 0.0401, "lr": 4.455249775158527e-05, "epoch": 5.854785478547855, "percentage": 29.27, "elapsed_time": "2:05:23", "remaining_time": "5:02:56", "throughput": 1492.75, "total_tokens": 11230592} {"current_steps": 53225, "total_steps": 181800, "loss": 0.0355, "lr": 4.455100205194611e-05, "epoch": 5.8553355335533555, "percentage": 29.28, "elapsed_time": "2:05:24", "remaining_time": "5:02:55", "throughput": 1492.75, "total_tokens": 11231680} {"current_steps": 53230, "total_steps": 181800, "loss": 0.0453, "lr": 4.4549506172114744e-05, "epoch": 5.855885588558856, "percentage": 29.28, "elapsed_time": "2:05:24", "remaining_time": "5:02:55", "throughput": 1492.76, "total_tokens": 11232736} {"current_steps": 53235, "total_steps": 181800, "loss": 0.0945, "lr": 4.4548010112104955e-05, "epoch": 5.856435643564357, "percentage": 29.28, "elapsed_time": "2:05:25", "remaining_time": "5:02:54", "throughput": 1492.77, "total_tokens": 11233824} {"current_steps": 53240, "total_steps": 181800, "loss": 0.0696, "lr": 4.454651387193054e-05, "epoch": 5.856985698569857, "percentage": 29.28, "elapsed_time": "2:05:26", "remaining_time": "5:02:53", "throughput": 1492.77, "total_tokens": 11234912} {"current_steps": 53245, "total_steps": 181800, "loss": 0.0334, "lr": 4.454501745160529e-05, "epoch": 5.857535753575357, "percentage": 29.29, "elapsed_time": "2:05:26", "remaining_time": "5:02:52", "throughput": 1492.77, "total_tokens": 11235936} {"current_steps": 53250, "total_steps": 181800, "loss": 0.0849, "lr": 4.454352085114298e-05, "epoch": 5.858085808580858, "percentage": 29.29, "elapsed_time": "2:05:27", "remaining_time": "5:02:52", "throughput": 1492.78, "total_tokens": 11236992} {"current_steps": 53255, "total_steps": 181800, "loss": 0.0126, "lr": 4.454202407055742e-05, "epoch": 5.8586358635863585, "percentage": 29.29, "elapsed_time": "2:05:28", "remaining_time": "5:02:51", "throughput": 1492.78, "total_tokens": 11238048} {"current_steps": 53260, "total_steps": 181800, "loss": 0.0112, "lr": 4.454052710986241e-05, "epoch": 5.8591859185918596, "percentage": 29.3, "elapsed_time": "2:05:28", "remaining_time": "5:02:50", "throughput": 1492.78, "total_tokens": 11239040} {"current_steps": 53265, "total_steps": 181800, "loss": 0.0103, "lr": 4.4539029969071734e-05, "epoch": 5.85973597359736, "percentage": 29.3, "elapsed_time": "2:05:29", "remaining_time": "5:02:49", "throughput": 1492.77, "total_tokens": 11240032} {"current_steps": 53270, "total_steps": 181800, "loss": 0.0373, "lr": 4.453753264819919e-05, "epoch": 5.86028602860286, "percentage": 29.3, "elapsed_time": "2:05:30", "remaining_time": "5:02:49", "throughput": 1492.78, "total_tokens": 11241088} {"current_steps": 53275, "total_steps": 181800, "loss": 0.0879, "lr": 4.453603514725859e-05, "epoch": 5.860836083608361, "percentage": 29.3, "elapsed_time": "2:05:31", "remaining_time": "5:02:48", "throughput": 1492.78, "total_tokens": 11242144} {"current_steps": 53280, "total_steps": 181800, "loss": 0.1222, "lr": 4.4534537466263726e-05, "epoch": 5.861386138613861, "percentage": 29.31, "elapsed_time": "2:05:31", "remaining_time": "5:02:47", "throughput": 1492.78, "total_tokens": 11243200} {"current_steps": 53285, "total_steps": 181800, "loss": 0.1126, "lr": 4.45330396052284e-05, "epoch": 5.861936193619362, "percentage": 29.31, "elapsed_time": "2:05:32", "remaining_time": "5:02:46", "throughput": 1492.8, "total_tokens": 11244320} {"current_steps": 53290, "total_steps": 181800, "loss": 0.0381, "lr": 4.453154156416642e-05, "epoch": 5.862486248624863, "percentage": 29.31, "elapsed_time": "2:05:33", "remaining_time": "5:02:46", "throughput": 1492.8, "total_tokens": 11245376} {"current_steps": 53295, "total_steps": 181800, "loss": 0.0333, "lr": 4.4530043343091596e-05, "epoch": 5.863036303630363, "percentage": 29.32, "elapsed_time": "2:05:33", "remaining_time": "5:02:45", "throughput": 1492.8, "total_tokens": 11246400} {"current_steps": 53300, "total_steps": 181800, "loss": 0.1207, "lr": 4.452854494201774e-05, "epoch": 5.863586358635864, "percentage": 29.32, "elapsed_time": "2:05:34", "remaining_time": "5:02:44", "throughput": 1492.81, "total_tokens": 11247488} {"current_steps": 53305, "total_steps": 181800, "loss": 0.1344, "lr": 4.452704636095865e-05, "epoch": 5.864136413641364, "percentage": 29.32, "elapsed_time": "2:05:35", "remaining_time": "5:02:43", "throughput": 1492.82, "total_tokens": 11248576} {"current_steps": 53310, "total_steps": 181800, "loss": 0.011, "lr": 4.452554759992814e-05, "epoch": 5.864686468646864, "percentage": 29.32, "elapsed_time": "2:05:35", "remaining_time": "5:02:43", "throughput": 1492.82, "total_tokens": 11249632} {"current_steps": 53315, "total_steps": 181800, "loss": 0.0725, "lr": 4.452404865894003e-05, "epoch": 5.865236523652365, "percentage": 29.33, "elapsed_time": "2:05:36", "remaining_time": "5:02:42", "throughput": 1492.82, "total_tokens": 11250656} {"current_steps": 53320, "total_steps": 181800, "loss": 0.1043, "lr": 4.452254953800814e-05, "epoch": 5.865786578657866, "percentage": 29.33, "elapsed_time": "2:05:37", "remaining_time": "5:02:41", "throughput": 1492.82, "total_tokens": 11251680} {"current_steps": 53325, "total_steps": 181800, "loss": 0.0815, "lr": 4.4521050237146274e-05, "epoch": 5.866336633663367, "percentage": 29.33, "elapsed_time": "2:05:37", "remaining_time": "5:02:40", "throughput": 1492.82, "total_tokens": 11252704} {"current_steps": 53330, "total_steps": 181800, "loss": 0.0415, "lr": 4.451955075636825e-05, "epoch": 5.866886688668867, "percentage": 29.33, "elapsed_time": "2:05:38", "remaining_time": "5:02:40", "throughput": 1492.83, "total_tokens": 11253792} {"current_steps": 53335, "total_steps": 181800, "loss": 0.1996, "lr": 4.45180510956879e-05, "epoch": 5.867436743674367, "percentage": 29.34, "elapsed_time": "2:05:39", "remaining_time": "5:02:39", "throughput": 1492.83, "total_tokens": 11254880} {"current_steps": 53340, "total_steps": 181800, "loss": 0.0324, "lr": 4.451655125511903e-05, "epoch": 5.867986798679868, "percentage": 29.34, "elapsed_time": "2:05:39", "remaining_time": "5:02:38", "throughput": 1492.84, "total_tokens": 11255968} {"current_steps": 53345, "total_steps": 181800, "loss": 0.0148, "lr": 4.4515051234675475e-05, "epoch": 5.868536853685368, "percentage": 29.34, "elapsed_time": "2:05:40", "remaining_time": "5:02:37", "throughput": 1492.84, "total_tokens": 11256992} {"current_steps": 53350, "total_steps": 181800, "loss": 0.0296, "lr": 4.451355103437106e-05, "epoch": 5.8690869086908695, "percentage": 29.35, "elapsed_time": "2:05:41", "remaining_time": "5:02:37", "throughput": 1492.84, "total_tokens": 11258016} {"current_steps": 53355, "total_steps": 181800, "loss": 0.041, "lr": 4.451205065421961e-05, "epoch": 5.86963696369637, "percentage": 29.35, "elapsed_time": "2:05:42", "remaining_time": "5:02:36", "throughput": 1492.85, "total_tokens": 11259072} {"current_steps": 53360, "total_steps": 181800, "loss": 0.0494, "lr": 4.4510550094234947e-05, "epoch": 5.87018701870187, "percentage": 29.35, "elapsed_time": "2:05:42", "remaining_time": "5:02:35", "throughput": 1492.84, "total_tokens": 11260096} {"current_steps": 53365, "total_steps": 181800, "loss": 0.0631, "lr": 4.450904935443091e-05, "epoch": 5.870737073707371, "percentage": 29.35, "elapsed_time": "2:05:43", "remaining_time": "5:02:34", "throughput": 1492.84, "total_tokens": 11261056} {"current_steps": 53370, "total_steps": 181800, "loss": 0.058, "lr": 4.4507548434821326e-05, "epoch": 5.871287128712871, "percentage": 29.36, "elapsed_time": "2:05:44", "remaining_time": "5:02:34", "throughput": 1492.84, "total_tokens": 11262144} {"current_steps": 53375, "total_steps": 181800, "loss": 0.0245, "lr": 4.450604733542003e-05, "epoch": 5.871837183718371, "percentage": 29.36, "elapsed_time": "2:05:44", "remaining_time": "5:02:33", "throughput": 1492.85, "total_tokens": 11263232} {"current_steps": 53380, "total_steps": 181800, "loss": 0.079, "lr": 4.450454605624085e-05, "epoch": 5.8723872387238725, "percentage": 29.36, "elapsed_time": "2:05:45", "remaining_time": "5:02:32", "throughput": 1492.85, "total_tokens": 11264256} {"current_steps": 53385, "total_steps": 181800, "loss": 0.016, "lr": 4.4503044597297634e-05, "epoch": 5.872937293729373, "percentage": 29.36, "elapsed_time": "2:05:46", "remaining_time": "5:02:31", "throughput": 1492.86, "total_tokens": 11265344} {"current_steps": 53390, "total_steps": 181800, "loss": 0.0131, "lr": 4.450154295860422e-05, "epoch": 5.873487348734874, "percentage": 29.37, "elapsed_time": "2:05:46", "remaining_time": "5:02:31", "throughput": 1492.85, "total_tokens": 11266336} {"current_steps": 53395, "total_steps": 181800, "loss": 0.0302, "lr": 4.450004114017443e-05, "epoch": 5.874037403740374, "percentage": 29.37, "elapsed_time": "2:05:47", "remaining_time": "5:02:30", "throughput": 1492.86, "total_tokens": 11267392} {"current_steps": 53400, "total_steps": 181800, "loss": 0.0218, "lr": 4.449853914202212e-05, "epoch": 5.874587458745875, "percentage": 29.37, "elapsed_time": "2:05:48", "remaining_time": "5:02:29", "throughput": 1492.86, "total_tokens": 11268448} {"current_steps": 53405, "total_steps": 181800, "loss": 0.0223, "lr": 4.4497036964161134e-05, "epoch": 5.875137513751375, "percentage": 29.38, "elapsed_time": "2:05:48", "remaining_time": "5:02:28", "throughput": 1492.87, "total_tokens": 11269536} {"current_steps": 53410, "total_steps": 181800, "loss": 0.0092, "lr": 4.449553460660531e-05, "epoch": 5.8756875687568755, "percentage": 29.38, "elapsed_time": "2:05:49", "remaining_time": "5:02:28", "throughput": 1492.88, "total_tokens": 11270656} {"current_steps": 53415, "total_steps": 181800, "loss": 0.0445, "lr": 4.44940320693685e-05, "epoch": 5.876237623762377, "percentage": 29.38, "elapsed_time": "2:05:50", "remaining_time": "5:02:27", "throughput": 1492.88, "total_tokens": 11271680} {"current_steps": 53420, "total_steps": 181800, "loss": 0.0648, "lr": 4.449252935246455e-05, "epoch": 5.876787678767877, "percentage": 29.38, "elapsed_time": "2:05:50", "remaining_time": "5:02:26", "throughput": 1492.89, "total_tokens": 11272800} {"current_steps": 53425, "total_steps": 181800, "loss": 0.055, "lr": 4.4491026455907314e-05, "epoch": 5.877337733773377, "percentage": 29.39, "elapsed_time": "2:05:51", "remaining_time": "5:02:25", "throughput": 1492.89, "total_tokens": 11273856} {"current_steps": 53430, "total_steps": 181800, "loss": 0.0904, "lr": 4.448952337971064e-05, "epoch": 5.877887788778878, "percentage": 29.39, "elapsed_time": "2:05:52", "remaining_time": "5:02:25", "throughput": 1492.9, "total_tokens": 11274912} {"current_steps": 53435, "total_steps": 181800, "loss": 0.0329, "lr": 4.448802012388838e-05, "epoch": 5.878437843784378, "percentage": 29.39, "elapsed_time": "2:05:53", "remaining_time": "5:02:24", "throughput": 1492.9, "total_tokens": 11275968} {"current_steps": 53440, "total_steps": 181800, "loss": 0.0351, "lr": 4.4486516688454385e-05, "epoch": 5.878987898789879, "percentage": 29.39, "elapsed_time": "2:05:53", "remaining_time": "5:02:23", "throughput": 1492.91, "total_tokens": 11277024} {"current_steps": 53445, "total_steps": 181800, "loss": 0.0048, "lr": 4.4485013073422524e-05, "epoch": 5.87953795379538, "percentage": 29.4, "elapsed_time": "2:05:54", "remaining_time": "5:02:22", "throughput": 1492.91, "total_tokens": 11278080} {"current_steps": 53450, "total_steps": 181800, "loss": 0.0169, "lr": 4.448350927880665e-05, "epoch": 5.88008800880088, "percentage": 29.4, "elapsed_time": "2:05:55", "remaining_time": "5:02:22", "throughput": 1492.91, "total_tokens": 11279072} {"current_steps": 53455, "total_steps": 181800, "loss": 0.0116, "lr": 4.4482005304620606e-05, "epoch": 5.880638063806381, "percentage": 29.4, "elapsed_time": "2:05:55", "remaining_time": "5:02:21", "throughput": 1492.92, "total_tokens": 11280192} {"current_steps": 53460, "total_steps": 181800, "loss": 0.0872, "lr": 4.448050115087827e-05, "epoch": 5.881188118811881, "percentage": 29.41, "elapsed_time": "2:05:56", "remaining_time": "5:02:20", "throughput": 1492.92, "total_tokens": 11281248} {"current_steps": 53465, "total_steps": 181800, "loss": 0.0568, "lr": 4.447899681759351e-05, "epoch": 5.881738173817382, "percentage": 29.41, "elapsed_time": "2:05:57", "remaining_time": "5:02:19", "throughput": 1492.93, "total_tokens": 11282336} {"current_steps": 53470, "total_steps": 181800, "loss": 0.0172, "lr": 4.447749230478018e-05, "epoch": 5.882288228822882, "percentage": 29.41, "elapsed_time": "2:05:57", "remaining_time": "5:02:19", "throughput": 1492.93, "total_tokens": 11283392} {"current_steps": 53475, "total_steps": 181800, "loss": 0.0194, "lr": 4.447598761245215e-05, "epoch": 5.882838283828383, "percentage": 29.41, "elapsed_time": "2:05:58", "remaining_time": "5:02:18", "throughput": 1492.93, "total_tokens": 11284416} {"current_steps": 53480, "total_steps": 181800, "loss": 0.0154, "lr": 4.447448274062329e-05, "epoch": 5.883388338833884, "percentage": 29.42, "elapsed_time": "2:05:59", "remaining_time": "5:02:17", "throughput": 1492.95, "total_tokens": 11285536} {"current_steps": 53485, "total_steps": 181800, "loss": 0.0701, "lr": 4.4472977689307474e-05, "epoch": 5.883938393839384, "percentage": 29.42, "elapsed_time": "2:05:59", "remaining_time": "5:02:16", "throughput": 1492.95, "total_tokens": 11286592} {"current_steps": 53490, "total_steps": 181800, "loss": 0.1863, "lr": 4.447147245851855e-05, "epoch": 5.884488448844884, "percentage": 29.42, "elapsed_time": "2:06:00", "remaining_time": "5:02:16", "throughput": 1492.96, "total_tokens": 11287680} {"current_steps": 53495, "total_steps": 181800, "loss": 0.037, "lr": 4.446996704827042e-05, "epoch": 5.885038503850385, "percentage": 29.43, "elapsed_time": "2:06:01", "remaining_time": "5:02:15", "throughput": 1492.96, "total_tokens": 11288736} {"current_steps": 53500, "total_steps": 181800, "loss": 0.0148, "lr": 4.446846145857694e-05, "epoch": 5.885588558855885, "percentage": 29.43, "elapsed_time": "2:06:02", "remaining_time": "5:02:14", "throughput": 1492.96, "total_tokens": 11289792} {"current_steps": 53505, "total_steps": 181800, "loss": 0.0203, "lr": 4.446695568945199e-05, "epoch": 5.8861386138613865, "percentage": 29.43, "elapsed_time": "2:06:02", "remaining_time": "5:02:13", "throughput": 1492.97, "total_tokens": 11290848} {"current_steps": 53510, "total_steps": 181800, "loss": 0.0094, "lr": 4.446544974090946e-05, "epoch": 5.886688668866887, "percentage": 29.43, "elapsed_time": "2:06:03", "remaining_time": "5:02:13", "throughput": 1492.97, "total_tokens": 11291872} {"current_steps": 53515, "total_steps": 181800, "loss": 0.016, "lr": 4.4463943612963216e-05, "epoch": 5.887238723872387, "percentage": 29.44, "elapsed_time": "2:06:04", "remaining_time": "5:02:12", "throughput": 1492.96, "total_tokens": 11292864} {"current_steps": 53520, "total_steps": 181800, "loss": 0.067, "lr": 4.4462437305627144e-05, "epoch": 5.887788778877888, "percentage": 29.44, "elapsed_time": "2:06:04", "remaining_time": "5:02:11", "throughput": 1492.96, "total_tokens": 11293888} {"current_steps": 53525, "total_steps": 181800, "loss": 0.0483, "lr": 4.446093081891513e-05, "epoch": 5.888338833883388, "percentage": 29.44, "elapsed_time": "2:06:05", "remaining_time": "5:02:10", "throughput": 1492.97, "total_tokens": 11294944} {"current_steps": 53530, "total_steps": 181800, "loss": 0.0414, "lr": 4.4459424152841046e-05, "epoch": 5.888888888888889, "percentage": 29.44, "elapsed_time": "2:06:06", "remaining_time": "5:02:10", "throughput": 1492.97, "total_tokens": 11296000} {"current_steps": 53535, "total_steps": 181800, "loss": 0.0187, "lr": 4.445791730741879e-05, "epoch": 5.8894389438943895, "percentage": 29.45, "elapsed_time": "2:06:06", "remaining_time": "5:02:09", "throughput": 1492.98, "total_tokens": 11297088} {"current_steps": 53540, "total_steps": 181800, "loss": 0.0108, "lr": 4.4456410282662244e-05, "epoch": 5.88998899889989, "percentage": 29.45, "elapsed_time": "2:06:07", "remaining_time": "5:02:08", "throughput": 1492.98, "total_tokens": 11298176} {"current_steps": 53545, "total_steps": 181800, "loss": 0.0511, "lr": 4.4454903078585306e-05, "epoch": 5.890539053905391, "percentage": 29.45, "elapsed_time": "2:06:08", "remaining_time": "5:02:07", "throughput": 1492.99, "total_tokens": 11299232} {"current_steps": 53550, "total_steps": 181800, "loss": 0.0551, "lr": 4.445339569520186e-05, "epoch": 5.891089108910891, "percentage": 29.46, "elapsed_time": "2:06:08", "remaining_time": "5:02:07", "throughput": 1493.0, "total_tokens": 11300352} {"current_steps": 53555, "total_steps": 181800, "loss": 0.0143, "lr": 4.445188813252581e-05, "epoch": 5.891639163916391, "percentage": 29.46, "elapsed_time": "2:06:09", "remaining_time": "5:02:06", "throughput": 1492.99, "total_tokens": 11301344} {"current_steps": 53560, "total_steps": 181800, "loss": 0.0642, "lr": 4.445038039057102e-05, "epoch": 5.892189218921892, "percentage": 29.46, "elapsed_time": "2:06:10", "remaining_time": "5:02:05", "throughput": 1493.0, "total_tokens": 11302400} {"current_steps": 53565, "total_steps": 181800, "loss": 0.0102, "lr": 4.444887246935143e-05, "epoch": 5.8927392739273925, "percentage": 29.46, "elapsed_time": "2:06:10", "remaining_time": "5:02:04", "throughput": 1492.99, "total_tokens": 11303392} {"current_steps": 53570, "total_steps": 181800, "loss": 0.1245, "lr": 4.44473643688809e-05, "epoch": 5.893289328932894, "percentage": 29.47, "elapsed_time": "2:06:11", "remaining_time": "5:02:04", "throughput": 1492.99, "total_tokens": 11304416} {"current_steps": 53575, "total_steps": 181800, "loss": 0.0065, "lr": 4.4445856089173346e-05, "epoch": 5.893839383938394, "percentage": 29.47, "elapsed_time": "2:06:12", "remaining_time": "5:02:03", "throughput": 1493.0, "total_tokens": 11305472} {"current_steps": 53580, "total_steps": 181800, "loss": 0.0349, "lr": 4.444434763024267e-05, "epoch": 5.894389438943895, "percentage": 29.47, "elapsed_time": "2:06:13", "remaining_time": "5:02:02", "throughput": 1492.99, "total_tokens": 11306496} {"current_steps": 53585, "total_steps": 181800, "loss": 0.0075, "lr": 4.4442838992102774e-05, "epoch": 5.894939493949395, "percentage": 29.47, "elapsed_time": "2:06:13", "remaining_time": "5:02:01", "throughput": 1493.0, "total_tokens": 11307552} {"current_steps": 53590, "total_steps": 181800, "loss": 0.0486, "lr": 4.444133017476756e-05, "epoch": 5.895489548954895, "percentage": 29.48, "elapsed_time": "2:06:14", "remaining_time": "5:02:01", "throughput": 1493.01, "total_tokens": 11308640} {"current_steps": 53595, "total_steps": 181800, "loss": 0.0139, "lr": 4.4439821178250926e-05, "epoch": 5.896039603960396, "percentage": 29.48, "elapsed_time": "2:06:15", "remaining_time": "5:02:00", "throughput": 1493.0, "total_tokens": 11309664} {"current_steps": 53600, "total_steps": 181800, "loss": 0.0448, "lr": 4.44383120025668e-05, "epoch": 5.896589658965897, "percentage": 29.48, "elapsed_time": "2:06:15", "remaining_time": "5:01:59", "throughput": 1493.0, "total_tokens": 11310688} {"current_steps": 53605, "total_steps": 181800, "loss": 0.0164, "lr": 4.443680264772908e-05, "epoch": 5.897139713971397, "percentage": 29.49, "elapsed_time": "2:06:16", "remaining_time": "5:01:58", "throughput": 1493.01, "total_tokens": 11311744} {"current_steps": 53610, "total_steps": 181800, "loss": 0.0151, "lr": 4.443529311375167e-05, "epoch": 5.897689768976898, "percentage": 29.49, "elapsed_time": "2:06:17", "remaining_time": "5:01:58", "throughput": 1493.01, "total_tokens": 11312768} {"current_steps": 53615, "total_steps": 181800, "loss": 0.1017, "lr": 4.443378340064849e-05, "epoch": 5.898239823982398, "percentage": 29.49, "elapsed_time": "2:06:17", "remaining_time": "5:01:57", "throughput": 1493.02, "total_tokens": 11313920} {"current_steps": 53620, "total_steps": 181800, "loss": 0.0454, "lr": 4.4432273508433455e-05, "epoch": 5.898789878987898, "percentage": 29.49, "elapsed_time": "2:06:18", "remaining_time": "5:01:56", "throughput": 1493.02, "total_tokens": 11314944} {"current_steps": 53625, "total_steps": 181800, "loss": 0.0439, "lr": 4.443076343712048e-05, "epoch": 5.899339933993399, "percentage": 29.5, "elapsed_time": "2:06:19", "remaining_time": "5:01:55", "throughput": 1493.03, "total_tokens": 11316064} {"current_steps": 53630, "total_steps": 181800, "loss": 0.0463, "lr": 4.442925318672348e-05, "epoch": 5.8998899889989, "percentage": 29.5, "elapsed_time": "2:06:19", "remaining_time": "5:01:55", "throughput": 1493.04, "total_tokens": 11317120} {"current_steps": 53635, "total_steps": 181800, "loss": 0.0411, "lr": 4.442774275725638e-05, "epoch": 5.900440044004401, "percentage": 29.5, "elapsed_time": "2:06:20", "remaining_time": "5:01:54", "throughput": 1493.05, "total_tokens": 11318208} {"current_steps": 53640, "total_steps": 181800, "loss": 0.015, "lr": 4.4426232148733096e-05, "epoch": 5.900990099009901, "percentage": 29.5, "elapsed_time": "2:06:21", "remaining_time": "5:01:53", "throughput": 1493.06, "total_tokens": 11319328} {"current_steps": 53645, "total_steps": 181800, "loss": 0.0383, "lr": 4.4424721361167557e-05, "epoch": 5.901540154015402, "percentage": 29.51, "elapsed_time": "2:06:21", "remaining_time": "5:01:52", "throughput": 1493.06, "total_tokens": 11320384} {"current_steps": 53650, "total_steps": 181800, "loss": 0.0247, "lr": 4.442321039457367e-05, "epoch": 5.902090209020902, "percentage": 29.51, "elapsed_time": "2:06:22", "remaining_time": "5:01:52", "throughput": 1493.06, "total_tokens": 11321440} {"current_steps": 53655, "total_steps": 181800, "loss": 0.0126, "lr": 4.4421699248965385e-05, "epoch": 5.902640264026402, "percentage": 29.51, "elapsed_time": "2:06:23", "remaining_time": "5:01:51", "throughput": 1493.06, "total_tokens": 11322464} {"current_steps": 53660, "total_steps": 181800, "loss": 0.0227, "lr": 4.44201879243566e-05, "epoch": 5.9031903190319035, "percentage": 29.52, "elapsed_time": "2:06:24", "remaining_time": "5:01:50", "throughput": 1493.06, "total_tokens": 11323488} {"current_steps": 53665, "total_steps": 181800, "loss": 0.0446, "lr": 4.441867642076128e-05, "epoch": 5.903740374037404, "percentage": 29.52, "elapsed_time": "2:06:24", "remaining_time": "5:01:49", "throughput": 1493.06, "total_tokens": 11324512} {"current_steps": 53670, "total_steps": 181800, "loss": 0.0504, "lr": 4.441716473819333e-05, "epoch": 5.904290429042904, "percentage": 29.52, "elapsed_time": "2:06:25", "remaining_time": "5:01:49", "throughput": 1493.06, "total_tokens": 11325536} {"current_steps": 53675, "total_steps": 181800, "loss": 0.0569, "lr": 4.441565287666669e-05, "epoch": 5.904840484048405, "percentage": 29.52, "elapsed_time": "2:06:26", "remaining_time": "5:01:48", "throughput": 1493.06, "total_tokens": 11326592} {"current_steps": 53680, "total_steps": 181800, "loss": 0.0065, "lr": 4.44141408361953e-05, "epoch": 5.905390539053905, "percentage": 29.53, "elapsed_time": "2:06:26", "remaining_time": "5:01:47", "throughput": 1493.07, "total_tokens": 11327648} {"current_steps": 53685, "total_steps": 181800, "loss": 0.0909, "lr": 4.441262861679308e-05, "epoch": 5.905940594059406, "percentage": 29.53, "elapsed_time": "2:06:27", "remaining_time": "5:01:47", "throughput": 1493.07, "total_tokens": 11328672} {"current_steps": 53690, "total_steps": 181800, "loss": 0.0083, "lr": 4.441111621847398e-05, "epoch": 5.9064906490649065, "percentage": 29.53, "elapsed_time": "2:06:28", "remaining_time": "5:01:46", "throughput": 1493.06, "total_tokens": 11329664} {"current_steps": 53695, "total_steps": 181800, "loss": 0.0395, "lr": 4.440960364125194e-05, "epoch": 5.907040704070407, "percentage": 29.54, "elapsed_time": "2:06:28", "remaining_time": "5:01:45", "throughput": 1493.06, "total_tokens": 11330688} {"current_steps": 53700, "total_steps": 181800, "loss": 0.0699, "lr": 4.44080908851409e-05, "epoch": 5.907590759075908, "percentage": 29.54, "elapsed_time": "2:06:29", "remaining_time": "5:01:44", "throughput": 1493.07, "total_tokens": 11331808} {"current_steps": 53705, "total_steps": 181800, "loss": 0.2498, "lr": 4.440657795015479e-05, "epoch": 5.908140814081408, "percentage": 29.54, "elapsed_time": "2:06:30", "remaining_time": "5:01:44", "throughput": 1493.07, "total_tokens": 11332832} {"current_steps": 53710, "total_steps": 181800, "loss": 0.0488, "lr": 4.4405064836307566e-05, "epoch": 5.908690869086909, "percentage": 29.54, "elapsed_time": "2:06:30", "remaining_time": "5:01:43", "throughput": 1493.07, "total_tokens": 11333856} {"current_steps": 53715, "total_steps": 181800, "loss": 0.06, "lr": 4.440355154361318e-05, "epoch": 5.909240924092409, "percentage": 29.55, "elapsed_time": "2:06:31", "remaining_time": "5:01:42", "throughput": 1493.07, "total_tokens": 11334912} {"current_steps": 53720, "total_steps": 181800, "loss": 0.0601, "lr": 4.4402038072085557e-05, "epoch": 5.9097909790979095, "percentage": 29.55, "elapsed_time": "2:06:32", "remaining_time": "5:01:41", "throughput": 1493.08, "total_tokens": 11336032} {"current_steps": 53725, "total_steps": 181800, "loss": 0.0163, "lr": 4.440052442173866e-05, "epoch": 5.910341034103411, "percentage": 29.55, "elapsed_time": "2:06:33", "remaining_time": "5:01:41", "throughput": 1493.09, "total_tokens": 11337120} {"current_steps": 53730, "total_steps": 181800, "loss": 0.118, "lr": 4.4399010592586446e-05, "epoch": 5.910891089108911, "percentage": 29.55, "elapsed_time": "2:06:33", "remaining_time": "5:01:40", "throughput": 1493.09, "total_tokens": 11338176} {"current_steps": 53735, "total_steps": 181800, "loss": 0.0621, "lr": 4.439749658464286e-05, "epoch": 5.911441144114411, "percentage": 29.56, "elapsed_time": "2:06:34", "remaining_time": "5:01:39", "throughput": 1493.1, "total_tokens": 11339232} {"current_steps": 53740, "total_steps": 181800, "loss": 0.0496, "lr": 4.439598239792185e-05, "epoch": 5.911991199119912, "percentage": 29.56, "elapsed_time": "2:06:35", "remaining_time": "5:01:38", "throughput": 1493.1, "total_tokens": 11340256} {"current_steps": 53745, "total_steps": 181800, "loss": 0.0529, "lr": 4.439446803243738e-05, "epoch": 5.912541254125412, "percentage": 29.56, "elapsed_time": "2:06:35", "remaining_time": "5:01:38", "throughput": 1493.1, "total_tokens": 11341312} {"current_steps": 53750, "total_steps": 181800, "loss": 0.0397, "lr": 4.43929534882034e-05, "epoch": 5.913091309130913, "percentage": 29.57, "elapsed_time": "2:06:36", "remaining_time": "5:01:37", "throughput": 1493.1, "total_tokens": 11342368} {"current_steps": 53755, "total_steps": 181800, "loss": 0.0161, "lr": 4.4391438765233885e-05, "epoch": 5.913641364136414, "percentage": 29.57, "elapsed_time": "2:06:37", "remaining_time": "5:01:36", "throughput": 1493.12, "total_tokens": 11343488} {"current_steps": 53760, "total_steps": 181800, "loss": 0.0654, "lr": 4.4389923863542774e-05, "epoch": 5.914191419141914, "percentage": 29.57, "elapsed_time": "2:06:37", "remaining_time": "5:01:35", "throughput": 1493.12, "total_tokens": 11344544} {"current_steps": 53765, "total_steps": 181800, "loss": 0.0661, "lr": 4.438840878314404e-05, "epoch": 5.914741474147415, "percentage": 29.57, "elapsed_time": "2:06:38", "remaining_time": "5:01:35", "throughput": 1493.12, "total_tokens": 11345568} {"current_steps": 53770, "total_steps": 181800, "loss": 0.0131, "lr": 4.4386893524051655e-05, "epoch": 5.915291529152915, "percentage": 29.58, "elapsed_time": "2:06:39", "remaining_time": "5:01:34", "throughput": 1493.12, "total_tokens": 11346592} {"current_steps": 53775, "total_steps": 181800, "loss": 0.027, "lr": 4.438537808627956e-05, "epoch": 5.915841584158416, "percentage": 29.58, "elapsed_time": "2:06:39", "remaining_time": "5:01:33", "throughput": 1493.12, "total_tokens": 11347648} {"current_steps": 53780, "total_steps": 181800, "loss": 0.0942, "lr": 4.4383862469841745e-05, "epoch": 5.916391639163916, "percentage": 29.58, "elapsed_time": "2:06:40", "remaining_time": "5:01:32", "throughput": 1493.13, "total_tokens": 11348736} {"current_steps": 53785, "total_steps": 181800, "loss": 0.0341, "lr": 4.4382346674752175e-05, "epoch": 5.916941694169417, "percentage": 29.58, "elapsed_time": "2:06:41", "remaining_time": "5:01:32", "throughput": 1493.14, "total_tokens": 11349856} {"current_steps": 53790, "total_steps": 181800, "loss": 0.0317, "lr": 4.438083070102481e-05, "epoch": 5.917491749174918, "percentage": 29.59, "elapsed_time": "2:06:42", "remaining_time": "5:01:31", "throughput": 1493.14, "total_tokens": 11350880} {"current_steps": 53795, "total_steps": 181800, "loss": 0.0106, "lr": 4.437931454867364e-05, "epoch": 5.918041804180418, "percentage": 29.59, "elapsed_time": "2:06:42", "remaining_time": "5:01:30", "throughput": 1493.15, "total_tokens": 11352032} {"current_steps": 53800, "total_steps": 181800, "loss": 0.0323, "lr": 4.437779821771261e-05, "epoch": 5.918591859185918, "percentage": 29.59, "elapsed_time": "2:06:43", "remaining_time": "5:01:29", "throughput": 1493.16, "total_tokens": 11353088} {"current_steps": 53805, "total_steps": 181800, "loss": 0.011, "lr": 4.4376281708155714e-05, "epoch": 5.919141914191419, "percentage": 29.6, "elapsed_time": "2:06:44", "remaining_time": "5:01:29", "throughput": 1493.17, "total_tokens": 11354176} {"current_steps": 53810, "total_steps": 181800, "loss": 0.1136, "lr": 4.437476502001693e-05, "epoch": 5.919691969196919, "percentage": 29.6, "elapsed_time": "2:06:44", "remaining_time": "5:01:28", "throughput": 1493.18, "total_tokens": 11355328} {"current_steps": 53815, "total_steps": 181800, "loss": 0.1548, "lr": 4.437324815331024e-05, "epoch": 5.9202420242024205, "percentage": 29.6, "elapsed_time": "2:06:45", "remaining_time": "5:01:27", "throughput": 1493.18, "total_tokens": 11356352} {"current_steps": 53820, "total_steps": 181800, "loss": 0.0817, "lr": 4.4371731108049615e-05, "epoch": 5.920792079207921, "percentage": 29.6, "elapsed_time": "2:06:46", "remaining_time": "5:01:26", "throughput": 1493.19, "total_tokens": 11357440} {"current_steps": 53825, "total_steps": 181800, "loss": 0.033, "lr": 4.4370213884249034e-05, "epoch": 5.921342134213422, "percentage": 29.61, "elapsed_time": "2:06:46", "remaining_time": "5:01:26", "throughput": 1493.18, "total_tokens": 11358432} {"current_steps": 53830, "total_steps": 181800, "loss": 0.0873, "lr": 4.4368696481922495e-05, "epoch": 5.921892189218922, "percentage": 29.61, "elapsed_time": "2:06:47", "remaining_time": "5:01:25", "throughput": 1493.18, "total_tokens": 11359424} {"current_steps": 53835, "total_steps": 181800, "loss": 0.1713, "lr": 4.4367178901083974e-05, "epoch": 5.922442244224422, "percentage": 29.61, "elapsed_time": "2:06:48", "remaining_time": "5:01:24", "throughput": 1493.18, "total_tokens": 11360480} {"current_steps": 53840, "total_steps": 181800, "loss": 0.0149, "lr": 4.436566114174745e-05, "epoch": 5.922992299229923, "percentage": 29.61, "elapsed_time": "2:06:48", "remaining_time": "5:01:23", "throughput": 1493.18, "total_tokens": 11361536} {"current_steps": 53845, "total_steps": 181800, "loss": 0.076, "lr": 4.4364143203926925e-05, "epoch": 5.9235423542354235, "percentage": 29.62, "elapsed_time": "2:06:49", "remaining_time": "5:01:23", "throughput": 1493.18, "total_tokens": 11362560} {"current_steps": 53850, "total_steps": 181800, "loss": 0.0216, "lr": 4.436262508763638e-05, "epoch": 5.924092409240924, "percentage": 29.62, "elapsed_time": "2:06:50", "remaining_time": "5:01:22", "throughput": 1493.19, "total_tokens": 11363616} {"current_steps": 53855, "total_steps": 181800, "loss": 0.0152, "lr": 4.436110679288982e-05, "epoch": 5.924642464246425, "percentage": 29.62, "elapsed_time": "2:06:50", "remaining_time": "5:01:21", "throughput": 1493.19, "total_tokens": 11364672} {"current_steps": 53860, "total_steps": 181800, "loss": 0.0113, "lr": 4.4359588319701224e-05, "epoch": 5.925192519251925, "percentage": 29.63, "elapsed_time": "2:06:51", "remaining_time": "5:01:20", "throughput": 1493.19, "total_tokens": 11365728} {"current_steps": 53865, "total_steps": 181800, "loss": 0.0107, "lr": 4.435806966808459e-05, "epoch": 5.925742574257426, "percentage": 29.63, "elapsed_time": "2:06:52", "remaining_time": "5:01:20", "throughput": 1493.2, "total_tokens": 11366784} {"current_steps": 53870, "total_steps": 181800, "loss": 0.0313, "lr": 4.435655083805392e-05, "epoch": 5.926292629262926, "percentage": 29.63, "elapsed_time": "2:06:53", "remaining_time": "5:01:19", "throughput": 1493.2, "total_tokens": 11367840} {"current_steps": 53875, "total_steps": 181800, "loss": 0.0131, "lr": 4.4355031829623204e-05, "epoch": 5.9268426842684265, "percentage": 29.63, "elapsed_time": "2:06:53", "remaining_time": "5:01:18", "throughput": 1493.2, "total_tokens": 11368896} {"current_steps": 53880, "total_steps": 181800, "loss": 0.0115, "lr": 4.4353512642806454e-05, "epoch": 5.927392739273928, "percentage": 29.64, "elapsed_time": "2:06:54", "remaining_time": "5:01:17", "throughput": 1493.21, "total_tokens": 11369952} {"current_steps": 53885, "total_steps": 181800, "loss": 0.0163, "lr": 4.435199327761766e-05, "epoch": 5.927942794279428, "percentage": 29.64, "elapsed_time": "2:06:55", "remaining_time": "5:01:17", "throughput": 1493.21, "total_tokens": 11371008} {"current_steps": 53890, "total_steps": 181800, "loss": 0.093, "lr": 4.435047373407083e-05, "epoch": 5.928492849284929, "percentage": 29.64, "elapsed_time": "2:06:55", "remaining_time": "5:01:16", "throughput": 1493.22, "total_tokens": 11372096} {"current_steps": 53895, "total_steps": 181800, "loss": 0.0164, "lr": 4.4348954012179974e-05, "epoch": 5.929042904290429, "percentage": 29.65, "elapsed_time": "2:06:56", "remaining_time": "5:01:15", "throughput": 1493.22, "total_tokens": 11373120} {"current_steps": 53900, "total_steps": 181800, "loss": 0.0636, "lr": 4.434743411195909e-05, "epoch": 5.929592959295929, "percentage": 29.65, "elapsed_time": "2:06:57", "remaining_time": "5:01:14", "throughput": 1493.22, "total_tokens": 11374208} {"current_steps": 53905, "total_steps": 181800, "loss": 0.1266, "lr": 4.434591403342219e-05, "epoch": 5.93014301430143, "percentage": 29.65, "elapsed_time": "2:06:57", "remaining_time": "5:01:14", "throughput": 1493.22, "total_tokens": 11375200} {"current_steps": 53910, "total_steps": 181800, "loss": 0.0139, "lr": 4.434439377658328e-05, "epoch": 5.930693069306931, "percentage": 29.65, "elapsed_time": "2:06:58", "remaining_time": "5:01:13", "throughput": 1493.22, "total_tokens": 11376224} {"current_steps": 53915, "total_steps": 181800, "loss": 0.0141, "lr": 4.4342873341456374e-05, "epoch": 5.931243124312431, "percentage": 29.66, "elapsed_time": "2:06:59", "remaining_time": "5:01:12", "throughput": 1493.22, "total_tokens": 11377248} {"current_steps": 53920, "total_steps": 181800, "loss": 0.1045, "lr": 4.43413527280555e-05, "epoch": 5.931793179317932, "percentage": 29.66, "elapsed_time": "2:06:59", "remaining_time": "5:01:11", "throughput": 1493.22, "total_tokens": 11378272} {"current_steps": 53925, "total_steps": 181800, "loss": 0.0067, "lr": 4.4339831936394635e-05, "epoch": 5.932343234323432, "percentage": 29.66, "elapsed_time": "2:07:00", "remaining_time": "5:01:11", "throughput": 1493.22, "total_tokens": 11379296} {"current_steps": 53930, "total_steps": 181800, "loss": 0.0233, "lr": 4.433831096648784e-05, "epoch": 5.932893289328933, "percentage": 29.66, "elapsed_time": "2:07:01", "remaining_time": "5:01:10", "throughput": 1493.22, "total_tokens": 11380352} {"current_steps": 53935, "total_steps": 181800, "loss": 0.0439, "lr": 4.43367898183491e-05, "epoch": 5.933443344334433, "percentage": 29.67, "elapsed_time": "2:07:02", "remaining_time": "5:01:09", "throughput": 1493.22, "total_tokens": 11381376} {"current_steps": 53940, "total_steps": 181800, "loss": 0.0188, "lr": 4.4335268491992455e-05, "epoch": 5.933993399339934, "percentage": 29.67, "elapsed_time": "2:07:02", "remaining_time": "5:01:09", "throughput": 1493.23, "total_tokens": 11382496} {"current_steps": 53945, "total_steps": 181800, "loss": 0.0682, "lr": 4.4333746987431916e-05, "epoch": 5.934543454345435, "percentage": 29.67, "elapsed_time": "2:07:03", "remaining_time": "5:01:08", "throughput": 1493.24, "total_tokens": 11383616} {"current_steps": 53950, "total_steps": 181800, "loss": 0.0197, "lr": 4.433222530468151e-05, "epoch": 5.935093509350935, "percentage": 29.68, "elapsed_time": "2:07:04", "remaining_time": "5:01:07", "throughput": 1493.24, "total_tokens": 11384608} {"current_steps": 53955, "total_steps": 181800, "loss": 0.0126, "lr": 4.433070344375525e-05, "epoch": 5.935643564356436, "percentage": 29.68, "elapsed_time": "2:07:04", "remaining_time": "5:01:06", "throughput": 1493.24, "total_tokens": 11385632} {"current_steps": 53960, "total_steps": 181800, "loss": 0.0359, "lr": 4.432918140466718e-05, "epoch": 5.936193619361936, "percentage": 29.68, "elapsed_time": "2:07:05", "remaining_time": "5:01:06", "throughput": 1493.24, "total_tokens": 11386720} {"current_steps": 53965, "total_steps": 181800, "loss": 0.0122, "lr": 4.432765918743132e-05, "epoch": 5.936743674367436, "percentage": 29.68, "elapsed_time": "2:07:06", "remaining_time": "5:01:05", "throughput": 1493.25, "total_tokens": 11387840} {"current_steps": 53970, "total_steps": 181800, "loss": 0.1203, "lr": 4.43261367920617e-05, "epoch": 5.9372937293729375, "percentage": 29.69, "elapsed_time": "2:07:06", "remaining_time": "5:01:04", "throughput": 1493.25, "total_tokens": 11388864} {"current_steps": 53975, "total_steps": 181800, "loss": 0.0554, "lr": 4.432461421857235e-05, "epoch": 5.937843784378438, "percentage": 29.69, "elapsed_time": "2:07:07", "remaining_time": "5:01:03", "throughput": 1493.25, "total_tokens": 11389856} {"current_steps": 53980, "total_steps": 181800, "loss": 0.0666, "lr": 4.43230914669773e-05, "epoch": 5.938393839383938, "percentage": 29.69, "elapsed_time": "2:07:08", "remaining_time": "5:01:03", "throughput": 1493.26, "total_tokens": 11390976} {"current_steps": 53985, "total_steps": 181800, "loss": 0.0184, "lr": 4.4321568537290595e-05, "epoch": 5.938943894389439, "percentage": 29.69, "elapsed_time": "2:07:08", "remaining_time": "5:01:02", "throughput": 1493.26, "total_tokens": 11392032} {"current_steps": 53990, "total_steps": 181800, "loss": 0.0163, "lr": 4.432004542952626e-05, "epoch": 5.939493949394939, "percentage": 29.7, "elapsed_time": "2:07:09", "remaining_time": "5:01:01", "throughput": 1493.27, "total_tokens": 11393088} {"current_steps": 53995, "total_steps": 181800, "loss": 0.1146, "lr": 4.431852214369834e-05, "epoch": 5.94004400440044, "percentage": 29.7, "elapsed_time": "2:07:10", "remaining_time": "5:01:00", "throughput": 1493.26, "total_tokens": 11394080} {"current_steps": 54000, "total_steps": 181800, "loss": 0.018, "lr": 4.431699867982086e-05, "epoch": 5.9405940594059405, "percentage": 29.7, "elapsed_time": "2:07:11", "remaining_time": "5:01:00", "throughput": 1493.27, "total_tokens": 11395168} {"current_steps": 54005, "total_steps": 181800, "loss": 0.0344, "lr": 4.431547503790788e-05, "epoch": 5.941144114411442, "percentage": 29.71, "elapsed_time": "2:07:11", "remaining_time": "5:00:59", "throughput": 1493.27, "total_tokens": 11396192} {"current_steps": 54010, "total_steps": 181800, "loss": 0.0756, "lr": 4.4313951217973435e-05, "epoch": 5.941694169416942, "percentage": 29.71, "elapsed_time": "2:07:12", "remaining_time": "5:00:58", "throughput": 1493.27, "total_tokens": 11397216} {"current_steps": 54015, "total_steps": 181800, "loss": 0.0073, "lr": 4.431242722003158e-05, "epoch": 5.942244224422442, "percentage": 29.71, "elapsed_time": "2:07:13", "remaining_time": "5:00:57", "throughput": 1493.27, "total_tokens": 11398240} {"current_steps": 54020, "total_steps": 181800, "loss": 0.0501, "lr": 4.431090304409634e-05, "epoch": 5.942794279427943, "percentage": 29.71, "elapsed_time": "2:07:13", "remaining_time": "5:00:57", "throughput": 1493.27, "total_tokens": 11399296} {"current_steps": 54025, "total_steps": 181800, "loss": 0.0096, "lr": 4.430937869018177e-05, "epoch": 5.943344334433443, "percentage": 29.72, "elapsed_time": "2:07:14", "remaining_time": "5:00:56", "throughput": 1493.27, "total_tokens": 11400352} {"current_steps": 54030, "total_steps": 181800, "loss": 0.0323, "lr": 4.4307854158301924e-05, "epoch": 5.9438943894389435, "percentage": 29.72, "elapsed_time": "2:07:15", "remaining_time": "5:00:55", "throughput": 1493.27, "total_tokens": 11401376} {"current_steps": 54035, "total_steps": 181800, "loss": 0.0497, "lr": 4.430632944847085e-05, "epoch": 5.944444444444445, "percentage": 29.72, "elapsed_time": "2:07:15", "remaining_time": "5:00:54", "throughput": 1493.27, "total_tokens": 11402400} {"current_steps": 54040, "total_steps": 181800, "loss": 0.0686, "lr": 4.430480456070261e-05, "epoch": 5.944994499449945, "percentage": 29.72, "elapsed_time": "2:07:16", "remaining_time": "5:00:54", "throughput": 1493.27, "total_tokens": 11403424} {"current_steps": 54045, "total_steps": 181800, "loss": 0.0158, "lr": 4.430327949501124e-05, "epoch": 5.945544554455445, "percentage": 29.73, "elapsed_time": "2:07:17", "remaining_time": "5:00:53", "throughput": 1493.28, "total_tokens": 11404512} {"current_steps": 54050, "total_steps": 181800, "loss": 0.0463, "lr": 4.430175425141081e-05, "epoch": 5.946094609460946, "percentage": 29.73, "elapsed_time": "2:07:17", "remaining_time": "5:00:52", "throughput": 1493.28, "total_tokens": 11405568} {"current_steps": 54055, "total_steps": 181800, "loss": 0.0299, "lr": 4.430022882991538e-05, "epoch": 5.946644664466446, "percentage": 29.73, "elapsed_time": "2:07:18", "remaining_time": "5:00:51", "throughput": 1493.29, "total_tokens": 11406656} {"current_steps": 54060, "total_steps": 181800, "loss": 0.0428, "lr": 4.429870323053899e-05, "epoch": 5.947194719471947, "percentage": 29.74, "elapsed_time": "2:07:19", "remaining_time": "5:00:51", "throughput": 1493.29, "total_tokens": 11407712} {"current_steps": 54065, "total_steps": 181800, "loss": 0.0628, "lr": 4.429717745329571e-05, "epoch": 5.947744774477448, "percentage": 29.74, "elapsed_time": "2:07:19", "remaining_time": "5:00:50", "throughput": 1493.29, "total_tokens": 11408704} {"current_steps": 54070, "total_steps": 181800, "loss": 0.0161, "lr": 4.429565149819962e-05, "epoch": 5.948294829482949, "percentage": 29.74, "elapsed_time": "2:07:20", "remaining_time": "5:00:49", "throughput": 1493.29, "total_tokens": 11409792} {"current_steps": 54075, "total_steps": 181800, "loss": 0.0194, "lr": 4.429412536526476e-05, "epoch": 5.948844884488449, "percentage": 29.74, "elapsed_time": "2:07:21", "remaining_time": "5:00:48", "throughput": 1493.3, "total_tokens": 11410880} {"current_steps": 54080, "total_steps": 181800, "loss": 0.0763, "lr": 4.429259905450521e-05, "epoch": 5.949394939493949, "percentage": 29.75, "elapsed_time": "2:07:22", "remaining_time": "5:00:48", "throughput": 1493.3, "total_tokens": 11411904} {"current_steps": 54085, "total_steps": 181800, "loss": 0.0246, "lr": 4.4291072565935025e-05, "epoch": 5.94994499449945, "percentage": 29.75, "elapsed_time": "2:07:22", "remaining_time": "5:00:47", "throughput": 1493.3, "total_tokens": 11412960} {"current_steps": 54090, "total_steps": 181800, "loss": 0.0643, "lr": 4.428954589956829e-05, "epoch": 5.9504950495049505, "percentage": 29.75, "elapsed_time": "2:07:23", "remaining_time": "5:00:46", "throughput": 1493.3, "total_tokens": 11413984} {"current_steps": 54095, "total_steps": 181800, "loss": 0.0233, "lr": 4.4288019055419054e-05, "epoch": 5.951045104510451, "percentage": 29.76, "elapsed_time": "2:07:24", "remaining_time": "5:00:45", "throughput": 1493.31, "total_tokens": 11415072} {"current_steps": 54100, "total_steps": 181800, "loss": 0.0235, "lr": 4.428649203350141e-05, "epoch": 5.951595159515952, "percentage": 29.76, "elapsed_time": "2:07:24", "remaining_time": "5:00:45", "throughput": 1493.31, "total_tokens": 11416096} {"current_steps": 54105, "total_steps": 181800, "loss": 0.0703, "lr": 4.428496483382942e-05, "epoch": 5.952145214521452, "percentage": 29.76, "elapsed_time": "2:07:25", "remaining_time": "5:00:44", "throughput": 1493.31, "total_tokens": 11417184} {"current_steps": 54110, "total_steps": 181800, "loss": 0.0193, "lr": 4.428343745641716e-05, "epoch": 5.952695269526953, "percentage": 29.76, "elapsed_time": "2:07:26", "remaining_time": "5:00:43", "throughput": 1493.32, "total_tokens": 11418272} {"current_steps": 54115, "total_steps": 181800, "loss": 0.0811, "lr": 4.428190990127872e-05, "epoch": 5.953245324532453, "percentage": 29.77, "elapsed_time": "2:07:26", "remaining_time": "5:00:42", "throughput": 1493.32, "total_tokens": 11419264} {"current_steps": 54120, "total_steps": 181800, "loss": 0.0703, "lr": 4.4280382168428166e-05, "epoch": 5.9537953795379535, "percentage": 29.77, "elapsed_time": "2:07:27", "remaining_time": "5:00:42", "throughput": 1493.32, "total_tokens": 11420288} {"current_steps": 54125, "total_steps": 181800, "loss": 0.1222, "lr": 4.4278854257879575e-05, "epoch": 5.9543454345434546, "percentage": 29.77, "elapsed_time": "2:07:28", "remaining_time": "5:00:41", "throughput": 1493.32, "total_tokens": 11421344} {"current_steps": 54130, "total_steps": 181800, "loss": 0.018, "lr": 4.427732616964704e-05, "epoch": 5.954895489548955, "percentage": 29.77, "elapsed_time": "2:07:28", "remaining_time": "5:00:40", "throughput": 1493.31, "total_tokens": 11422336} {"current_steps": 54135, "total_steps": 181800, "loss": 0.0378, "lr": 4.427579790374464e-05, "epoch": 5.955445544554456, "percentage": 29.78, "elapsed_time": "2:07:29", "remaining_time": "5:00:40", "throughput": 1493.33, "total_tokens": 11423456} {"current_steps": 54140, "total_steps": 181800, "loss": 0.1558, "lr": 4.427426946018646e-05, "epoch": 5.955995599559956, "percentage": 29.78, "elapsed_time": "2:07:30", "remaining_time": "5:00:39", "throughput": 1493.33, "total_tokens": 11424512} {"current_steps": 54145, "total_steps": 181800, "loss": 0.1543, "lr": 4.4272740838986585e-05, "epoch": 5.956545654565456, "percentage": 29.78, "elapsed_time": "2:07:31", "remaining_time": "5:00:38", "throughput": 1493.34, "total_tokens": 11425632} {"current_steps": 54150, "total_steps": 181800, "loss": 0.0118, "lr": 4.42712120401591e-05, "epoch": 5.957095709570957, "percentage": 29.79, "elapsed_time": "2:07:31", "remaining_time": "5:00:37", "throughput": 1493.35, "total_tokens": 11426752} {"current_steps": 54155, "total_steps": 181800, "loss": 0.0317, "lr": 4.4269683063718115e-05, "epoch": 5.957645764576458, "percentage": 29.79, "elapsed_time": "2:07:32", "remaining_time": "5:00:37", "throughput": 1493.35, "total_tokens": 11427808} {"current_steps": 54160, "total_steps": 181800, "loss": 0.0191, "lr": 4.4268153909677704e-05, "epoch": 5.958195819581958, "percentage": 29.79, "elapsed_time": "2:07:33", "remaining_time": "5:00:36", "throughput": 1493.35, "total_tokens": 11428832} {"current_steps": 54165, "total_steps": 181800, "loss": 0.1083, "lr": 4.426662457805195e-05, "epoch": 5.958745874587459, "percentage": 29.79, "elapsed_time": "2:07:33", "remaining_time": "5:00:35", "throughput": 1493.36, "total_tokens": 11429888} {"current_steps": 54170, "total_steps": 181800, "loss": 0.1463, "lr": 4.426509506885498e-05, "epoch": 5.959295929592959, "percentage": 29.8, "elapsed_time": "2:07:34", "remaining_time": "5:00:34", "throughput": 1493.36, "total_tokens": 11430912} {"current_steps": 54175, "total_steps": 181800, "loss": 0.0413, "lr": 4.426356538210087e-05, "epoch": 5.95984598459846, "percentage": 29.8, "elapsed_time": "2:07:35", "remaining_time": "5:00:34", "throughput": 1493.37, "total_tokens": 11432032} {"current_steps": 54180, "total_steps": 181800, "loss": 0.1475, "lr": 4.4262035517803716e-05, "epoch": 5.96039603960396, "percentage": 29.8, "elapsed_time": "2:07:35", "remaining_time": "5:00:33", "throughput": 1493.37, "total_tokens": 11433088} {"current_steps": 54185, "total_steps": 181800, "loss": 0.035, "lr": 4.426050547597762e-05, "epoch": 5.960946094609461, "percentage": 29.8, "elapsed_time": "2:07:36", "remaining_time": "5:00:32", "throughput": 1493.39, "total_tokens": 11434240} {"current_steps": 54190, "total_steps": 181800, "loss": 0.0821, "lr": 4.4258975256636694e-05, "epoch": 5.961496149614962, "percentage": 29.81, "elapsed_time": "2:07:37", "remaining_time": "5:00:31", "throughput": 1493.39, "total_tokens": 11435296} {"current_steps": 54195, "total_steps": 181800, "loss": 0.0126, "lr": 4.4257444859795024e-05, "epoch": 5.962046204620462, "percentage": 29.81, "elapsed_time": "2:07:37", "remaining_time": "5:00:31", "throughput": 1493.39, "total_tokens": 11436320} {"current_steps": 54200, "total_steps": 181800, "loss": 0.0251, "lr": 4.4255914285466735e-05, "epoch": 5.962596259625963, "percentage": 29.81, "elapsed_time": "2:07:38", "remaining_time": "5:00:30", "throughput": 1493.4, "total_tokens": 11437408} {"current_steps": 54205, "total_steps": 181800, "loss": 0.0336, "lr": 4.425438353366593e-05, "epoch": 5.963146314631463, "percentage": 29.82, "elapsed_time": "2:07:39", "remaining_time": "5:00:29", "throughput": 1493.4, "total_tokens": 11438432} {"current_steps": 54210, "total_steps": 181800, "loss": 0.0114, "lr": 4.42528526044067e-05, "epoch": 5.963696369636963, "percentage": 29.82, "elapsed_time": "2:07:40", "remaining_time": "5:00:28", "throughput": 1493.39, "total_tokens": 11439456} {"current_steps": 54215, "total_steps": 181800, "loss": 0.0463, "lr": 4.425132149770317e-05, "epoch": 5.9642464246424645, "percentage": 29.82, "elapsed_time": "2:07:40", "remaining_time": "5:00:28", "throughput": 1493.4, "total_tokens": 11440544} {"current_steps": 54220, "total_steps": 181800, "loss": 0.1784, "lr": 4.424979021356944e-05, "epoch": 5.964796479647965, "percentage": 29.82, "elapsed_time": "2:07:41", "remaining_time": "5:00:27", "throughput": 1493.4, "total_tokens": 11441568} {"current_steps": 54225, "total_steps": 181800, "loss": 0.0056, "lr": 4.424825875201964e-05, "epoch": 5.965346534653465, "percentage": 29.83, "elapsed_time": "2:07:42", "remaining_time": "5:00:26", "throughput": 1493.41, "total_tokens": 11442688} {"current_steps": 54230, "total_steps": 181800, "loss": 0.0106, "lr": 4.424672711306788e-05, "epoch": 5.965896589658966, "percentage": 29.83, "elapsed_time": "2:07:42", "remaining_time": "5:00:25", "throughput": 1493.44, "total_tokens": 11443904} {"current_steps": 54235, "total_steps": 181800, "loss": 0.0383, "lr": 4.424519529672826e-05, "epoch": 5.966446644664466, "percentage": 29.83, "elapsed_time": "2:07:43", "remaining_time": "5:00:25", "throughput": 1493.44, "total_tokens": 11444992} {"current_steps": 54240, "total_steps": 181800, "loss": 0.0689, "lr": 4.4243663303014914e-05, "epoch": 5.966996699669967, "percentage": 29.83, "elapsed_time": "2:07:44", "remaining_time": "5:00:24", "throughput": 1493.46, "total_tokens": 11446176} {"current_steps": 54245, "total_steps": 181800, "loss": 0.0296, "lr": 4.4242131131941956e-05, "epoch": 5.9675467546754675, "percentage": 29.84, "elapsed_time": "2:07:44", "remaining_time": "5:00:23", "throughput": 1493.46, "total_tokens": 11447200} {"current_steps": 54250, "total_steps": 181800, "loss": 0.1082, "lr": 4.4240598783523514e-05, "epoch": 5.968096809680969, "percentage": 29.84, "elapsed_time": "2:07:45", "remaining_time": "5:00:22", "throughput": 1493.46, "total_tokens": 11448256} {"current_steps": 54255, "total_steps": 181800, "loss": 0.0051, "lr": 4.4239066257773696e-05, "epoch": 5.968646864686469, "percentage": 29.84, "elapsed_time": "2:07:46", "remaining_time": "5:00:22", "throughput": 1493.47, "total_tokens": 11449312} {"current_steps": 54260, "total_steps": 181800, "loss": 0.0349, "lr": 4.4237533554706646e-05, "epoch": 5.969196919691969, "percentage": 29.85, "elapsed_time": "2:07:46", "remaining_time": "5:00:21", "throughput": 1493.48, "total_tokens": 11450432} {"current_steps": 54265, "total_steps": 181800, "loss": 0.0142, "lr": 4.4236000674336476e-05, "epoch": 5.96974697469747, "percentage": 29.85, "elapsed_time": "2:07:47", "remaining_time": "5:00:20", "throughput": 1493.48, "total_tokens": 11451488} {"current_steps": 54270, "total_steps": 181800, "loss": 0.0403, "lr": 4.4234467616677324e-05, "epoch": 5.97029702970297, "percentage": 29.85, "elapsed_time": "2:07:48", "remaining_time": "5:00:19", "throughput": 1493.48, "total_tokens": 11452544} {"current_steps": 54275, "total_steps": 181800, "loss": 0.0785, "lr": 4.42329343817433e-05, "epoch": 5.9708470847084705, "percentage": 29.85, "elapsed_time": "2:07:49", "remaining_time": "5:00:19", "throughput": 1493.48, "total_tokens": 11453536} {"current_steps": 54280, "total_steps": 181800, "loss": 0.0152, "lr": 4.4231400969548556e-05, "epoch": 5.971397139713972, "percentage": 29.86, "elapsed_time": "2:07:49", "remaining_time": "5:00:18", "throughput": 1493.48, "total_tokens": 11454560} {"current_steps": 54285, "total_steps": 181800, "loss": 0.0663, "lr": 4.422986738010722e-05, "epoch": 5.971947194719472, "percentage": 29.86, "elapsed_time": "2:07:50", "remaining_time": "5:00:17", "throughput": 1493.49, "total_tokens": 11455648} {"current_steps": 54290, "total_steps": 181800, "loss": 0.1369, "lr": 4.422833361343342e-05, "epoch": 5.972497249724973, "percentage": 29.86, "elapsed_time": "2:07:51", "remaining_time": "5:00:16", "throughput": 1493.48, "total_tokens": 11456608} {"current_steps": 54295, "total_steps": 181800, "loss": 0.0382, "lr": 4.42267996695413e-05, "epoch": 5.973047304730473, "percentage": 29.87, "elapsed_time": "2:07:51", "remaining_time": "5:00:16", "throughput": 1493.48, "total_tokens": 11457664} {"current_steps": 54300, "total_steps": 181800, "loss": 0.0686, "lr": 4.4225265548444986e-05, "epoch": 5.973597359735973, "percentage": 29.87, "elapsed_time": "2:07:52", "remaining_time": "5:00:15", "throughput": 1493.5, "total_tokens": 11458784} {"current_steps": 54305, "total_steps": 181800, "loss": 0.0452, "lr": 4.422373125015863e-05, "epoch": 5.974147414741474, "percentage": 29.87, "elapsed_time": "2:07:53", "remaining_time": "5:00:14", "throughput": 1493.49, "total_tokens": 11459776} {"current_steps": 54310, "total_steps": 181800, "loss": 0.0528, "lr": 4.422219677469637e-05, "epoch": 5.974697469746975, "percentage": 29.87, "elapsed_time": "2:07:53", "remaining_time": "5:00:13", "throughput": 1493.49, "total_tokens": 11460768} {"current_steps": 54315, "total_steps": 181800, "loss": 0.0508, "lr": 4.422066212207234e-05, "epoch": 5.975247524752476, "percentage": 29.88, "elapsed_time": "2:07:54", "remaining_time": "5:00:13", "throughput": 1493.49, "total_tokens": 11461792} {"current_steps": 54320, "total_steps": 181800, "loss": 0.1759, "lr": 4.42191272923007e-05, "epoch": 5.975797579757976, "percentage": 29.88, "elapsed_time": "2:07:55", "remaining_time": "5:00:12", "throughput": 1493.48, "total_tokens": 11462784} {"current_steps": 54325, "total_steps": 181800, "loss": 0.0922, "lr": 4.421759228539557e-05, "epoch": 5.976347634763476, "percentage": 29.88, "elapsed_time": "2:07:55", "remaining_time": "5:00:11", "throughput": 1493.49, "total_tokens": 11463840} {"current_steps": 54330, "total_steps": 181800, "loss": 0.0425, "lr": 4.421605710137112e-05, "epoch": 5.976897689768977, "percentage": 29.88, "elapsed_time": "2:07:56", "remaining_time": "5:00:10", "throughput": 1493.48, "total_tokens": 11464864} {"current_steps": 54335, "total_steps": 181800, "loss": 0.0758, "lr": 4.42145217402415e-05, "epoch": 5.977447744774477, "percentage": 29.89, "elapsed_time": "2:07:57", "remaining_time": "5:00:10", "throughput": 1493.48, "total_tokens": 11465888} {"current_steps": 54340, "total_steps": 181800, "loss": 0.0921, "lr": 4.421298620202085e-05, "epoch": 5.977997799779978, "percentage": 29.89, "elapsed_time": "2:07:57", "remaining_time": "5:00:09", "throughput": 1493.48, "total_tokens": 11466912} {"current_steps": 54345, "total_steps": 181800, "loss": 0.0314, "lr": 4.4211450486723324e-05, "epoch": 5.978547854785479, "percentage": 29.89, "elapsed_time": "2:07:58", "remaining_time": "5:00:08", "throughput": 1493.49, "total_tokens": 11468000} {"current_steps": 54350, "total_steps": 181800, "loss": 0.0869, "lr": 4.420991459436308e-05, "epoch": 5.979097909790979, "percentage": 29.9, "elapsed_time": "2:07:59", "remaining_time": "5:00:07", "throughput": 1493.5, "total_tokens": 11469088} {"current_steps": 54355, "total_steps": 181800, "loss": 0.0742, "lr": 4.420837852495426e-05, "epoch": 5.97964796479648, "percentage": 29.9, "elapsed_time": "2:08:00", "remaining_time": "5:00:07", "throughput": 1493.5, "total_tokens": 11470144} {"current_steps": 54360, "total_steps": 181800, "loss": 0.0315, "lr": 4.420684227851104e-05, "epoch": 5.98019801980198, "percentage": 29.9, "elapsed_time": "2:08:00", "remaining_time": "5:00:06", "throughput": 1493.51, "total_tokens": 11471232} {"current_steps": 54365, "total_steps": 181800, "loss": 0.1457, "lr": 4.4205305855047575e-05, "epoch": 5.98074807480748, "percentage": 29.9, "elapsed_time": "2:08:01", "remaining_time": "5:00:05", "throughput": 1493.51, "total_tokens": 11472288} {"current_steps": 54370, "total_steps": 181800, "loss": 0.0073, "lr": 4.420376925457802e-05, "epoch": 5.9812981298129815, "percentage": 29.91, "elapsed_time": "2:08:02", "remaining_time": "5:00:04", "throughput": 1493.52, "total_tokens": 11473344} {"current_steps": 54375, "total_steps": 181800, "loss": 0.0083, "lr": 4.420223247711653e-05, "epoch": 5.981848184818482, "percentage": 29.91, "elapsed_time": "2:08:02", "remaining_time": "5:00:04", "throughput": 1493.52, "total_tokens": 11474400} {"current_steps": 54380, "total_steps": 181800, "loss": 0.0494, "lr": 4.4200695522677284e-05, "epoch": 5.982398239823983, "percentage": 29.91, "elapsed_time": "2:08:03", "remaining_time": "5:00:03", "throughput": 1493.52, "total_tokens": 11475456} {"current_steps": 54385, "total_steps": 181800, "loss": 0.0628, "lr": 4.419915839127444e-05, "epoch": 5.982948294829483, "percentage": 29.91, "elapsed_time": "2:08:04", "remaining_time": "5:00:02", "throughput": 1493.53, "total_tokens": 11476512} {"current_steps": 54390, "total_steps": 181800, "loss": 0.0111, "lr": 4.419762108292217e-05, "epoch": 5.983498349834983, "percentage": 29.92, "elapsed_time": "2:08:04", "remaining_time": "5:00:01", "throughput": 1493.53, "total_tokens": 11477600} {"current_steps": 54395, "total_steps": 181800, "loss": 0.0563, "lr": 4.419608359763463e-05, "epoch": 5.984048404840484, "percentage": 29.92, "elapsed_time": "2:08:05", "remaining_time": "5:00:01", "throughput": 1493.54, "total_tokens": 11478656} {"current_steps": 54400, "total_steps": 181800, "loss": 0.0875, "lr": 4.419454593542601e-05, "epoch": 5.9845984598459845, "percentage": 29.92, "elapsed_time": "2:08:06", "remaining_time": "5:00:00", "throughput": 1493.54, "total_tokens": 11479680} {"current_steps": 54405, "total_steps": 181800, "loss": 0.1491, "lr": 4.419300809631046e-05, "epoch": 5.985148514851485, "percentage": 29.93, "elapsed_time": "2:08:06", "remaining_time": "4:59:59", "throughput": 1493.54, "total_tokens": 11480704} {"current_steps": 54410, "total_steps": 181800, "loss": 0.0146, "lr": 4.419147008030217e-05, "epoch": 5.985698569856986, "percentage": 29.93, "elapsed_time": "2:08:07", "remaining_time": "4:59:58", "throughput": 1493.54, "total_tokens": 11481760} {"current_steps": 54415, "total_steps": 181800, "loss": 0.011, "lr": 4.4189931887415304e-05, "epoch": 5.986248624862486, "percentage": 29.93, "elapsed_time": "2:08:08", "remaining_time": "4:59:58", "throughput": 1493.55, "total_tokens": 11482848} {"current_steps": 54420, "total_steps": 181800, "loss": 0.0269, "lr": 4.418839351766405e-05, "epoch": 5.986798679867987, "percentage": 29.93, "elapsed_time": "2:08:08", "remaining_time": "4:59:57", "throughput": 1493.55, "total_tokens": 11483904} {"current_steps": 54425, "total_steps": 181800, "loss": 0.0375, "lr": 4.4186854971062575e-05, "epoch": 5.987348734873487, "percentage": 29.94, "elapsed_time": "2:08:09", "remaining_time": "4:59:56", "throughput": 1493.55, "total_tokens": 11484960} {"current_steps": 54430, "total_steps": 181800, "loss": 0.0685, "lr": 4.418531624762507e-05, "epoch": 5.987898789878988, "percentage": 29.94, "elapsed_time": "2:08:10", "remaining_time": "4:59:56", "throughput": 1493.55, "total_tokens": 11485984} {"current_steps": 54435, "total_steps": 181800, "loss": 0.0981, "lr": 4.4183777347365704e-05, "epoch": 5.988448844884489, "percentage": 29.94, "elapsed_time": "2:08:11", "remaining_time": "4:59:55", "throughput": 1493.56, "total_tokens": 11487072} {"current_steps": 54440, "total_steps": 181800, "loss": 0.0373, "lr": 4.418223827029867e-05, "epoch": 5.988998899889989, "percentage": 29.94, "elapsed_time": "2:08:11", "remaining_time": "4:59:54", "throughput": 1493.55, "total_tokens": 11488064} {"current_steps": 54445, "total_steps": 181800, "loss": 0.0236, "lr": 4.418069901643815e-05, "epoch": 5.98954895489549, "percentage": 29.95, "elapsed_time": "2:08:12", "remaining_time": "4:59:53", "throughput": 1493.57, "total_tokens": 11489184} {"current_steps": 54450, "total_steps": 181800, "loss": 0.0061, "lr": 4.4179159585798344e-05, "epoch": 5.99009900990099, "percentage": 29.95, "elapsed_time": "2:08:13", "remaining_time": "4:59:53", "throughput": 1493.57, "total_tokens": 11490208} {"current_steps": 54455, "total_steps": 181800, "loss": 0.0568, "lr": 4.417761997839341e-05, "epoch": 5.99064906490649, "percentage": 29.95, "elapsed_time": "2:08:13", "remaining_time": "4:59:52", "throughput": 1493.57, "total_tokens": 11491232} {"current_steps": 54460, "total_steps": 181800, "loss": 0.0074, "lr": 4.417608019423756e-05, "epoch": 5.991199119911991, "percentage": 29.96, "elapsed_time": "2:08:14", "remaining_time": "4:59:51", "throughput": 1493.57, "total_tokens": 11492320} {"current_steps": 54465, "total_steps": 181800, "loss": 0.0235, "lr": 4.4174540233344985e-05, "epoch": 5.991749174917492, "percentage": 29.96, "elapsed_time": "2:08:15", "remaining_time": "4:59:50", "throughput": 1493.58, "total_tokens": 11493376} {"current_steps": 54470, "total_steps": 181800, "loss": 0.0283, "lr": 4.417300009572987e-05, "epoch": 5.992299229922993, "percentage": 29.96, "elapsed_time": "2:08:15", "remaining_time": "4:59:50", "throughput": 1493.58, "total_tokens": 11494432} {"current_steps": 54475, "total_steps": 181800, "loss": 0.0875, "lr": 4.417145978140641e-05, "epoch": 5.992849284928493, "percentage": 29.96, "elapsed_time": "2:08:16", "remaining_time": "4:59:49", "throughput": 1493.58, "total_tokens": 11495456} {"current_steps": 54480, "total_steps": 181800, "loss": 0.0099, "lr": 4.416991929038881e-05, "epoch": 5.993399339933993, "percentage": 29.97, "elapsed_time": "2:08:17", "remaining_time": "4:59:48", "throughput": 1493.59, "total_tokens": 11496576} {"current_steps": 54485, "total_steps": 181800, "loss": 0.0328, "lr": 4.4168378622691266e-05, "epoch": 5.993949394939494, "percentage": 29.97, "elapsed_time": "2:08:17", "remaining_time": "4:59:47", "throughput": 1493.6, "total_tokens": 11497664} {"current_steps": 54490, "total_steps": 181800, "loss": 0.0227, "lr": 4.4166837778327964e-05, "epoch": 5.994499449944994, "percentage": 29.97, "elapsed_time": "2:08:18", "remaining_time": "4:59:47", "throughput": 1493.61, "total_tokens": 11498752} {"current_steps": 54495, "total_steps": 181800, "loss": 0.1561, "lr": 4.416529675731312e-05, "epoch": 5.9950495049504955, "percentage": 29.98, "elapsed_time": "2:08:19", "remaining_time": "4:59:46", "throughput": 1493.6, "total_tokens": 11499776} {"current_steps": 54500, "total_steps": 181800, "loss": 0.0682, "lr": 4.4163755559660936e-05, "epoch": 5.995599559955996, "percentage": 29.98, "elapsed_time": "2:08:20", "remaining_time": "4:59:45", "throughput": 1493.6, "total_tokens": 11500800} {"current_steps": 54505, "total_steps": 181800, "loss": 0.1347, "lr": 4.41622141853856e-05, "epoch": 5.996149614961496, "percentage": 29.98, "elapsed_time": "2:08:20", "remaining_time": "4:59:44", "throughput": 1493.61, "total_tokens": 11501856} {"current_steps": 54510, "total_steps": 181800, "loss": 0.0344, "lr": 4.4160672634501345e-05, "epoch": 5.996699669966997, "percentage": 29.98, "elapsed_time": "2:08:21", "remaining_time": "4:59:44", "throughput": 1493.61, "total_tokens": 11502880} {"current_steps": 54515, "total_steps": 181800, "loss": 0.0734, "lr": 4.415913090702236e-05, "epoch": 5.997249724972497, "percentage": 29.99, "elapsed_time": "2:08:22", "remaining_time": "4:59:43", "throughput": 1493.61, "total_tokens": 11503904} {"current_steps": 54520, "total_steps": 181800, "loss": 0.1083, "lr": 4.4157589002962856e-05, "epoch": 5.997799779977997, "percentage": 29.99, "elapsed_time": "2:08:22", "remaining_time": "4:59:42", "throughput": 1493.61, "total_tokens": 11504992} {"current_steps": 54525, "total_steps": 181800, "loss": 0.1102, "lr": 4.4156046922337044e-05, "epoch": 5.9983498349834985, "percentage": 29.99, "elapsed_time": "2:08:23", "remaining_time": "4:59:41", "throughput": 1493.61, "total_tokens": 11505984} {"current_steps": 54530, "total_steps": 181800, "loss": 0.0331, "lr": 4.415450466515915e-05, "epoch": 5.998899889988999, "percentage": 29.99, "elapsed_time": "2:08:24", "remaining_time": "4:59:41", "throughput": 1493.62, "total_tokens": 11507072} {"current_steps": 54535, "total_steps": 181800, "loss": 0.0765, "lr": 4.4152962231443376e-05, "epoch": 5.9994499449945, "percentage": 30.0, "elapsed_time": "2:08:24", "remaining_time": "4:59:40", "throughput": 1493.62, "total_tokens": 11508096} {"current_steps": 54540, "total_steps": 181800, "loss": 0.1489, "lr": 4.4151419621203925e-05, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "2:08:25", "remaining_time": "4:59:39", "throughput": 1493.6, "total_tokens": 11509088} {"current_steps": 54540, "total_steps": 181800, "eval_loss": 0.062062107026576996, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "2:09:02", "remaining_time": "5:01:06", "throughput": 1486.44, "total_tokens": 11509088} {"current_steps": 54545, "total_steps": 181800, "loss": 0.0484, "lr": 4.414987683445505e-05, "epoch": 6.0005500550055, "percentage": 30.0, "elapsed_time": "2:09:04", "remaining_time": "5:01:08", "throughput": 1486.21, "total_tokens": 11510144} {"current_steps": 54550, "total_steps": 181800, "loss": 0.0181, "lr": 4.4148333871210936e-05, "epoch": 6.001100110011001, "percentage": 30.01, "elapsed_time": "2:09:05", "remaining_time": "5:01:07", "throughput": 1486.21, "total_tokens": 11511168} {"current_steps": 54555, "total_steps": 181800, "loss": 0.0418, "lr": 4.4146790731485823e-05, "epoch": 6.0016501650165015, "percentage": 30.01, "elapsed_time": "2:09:06", "remaining_time": "5:01:06", "throughput": 1486.21, "total_tokens": 11512224} {"current_steps": 54560, "total_steps": 181800, "loss": 0.0564, "lr": 4.414524741529392e-05, "epoch": 6.002200220022003, "percentage": 30.01, "elapsed_time": "2:09:06", "remaining_time": "5:01:06", "throughput": 1486.21, "total_tokens": 11513280} {"current_steps": 54565, "total_steps": 181800, "loss": 0.0293, "lr": 4.414370392264946e-05, "epoch": 6.002750275027503, "percentage": 30.01, "elapsed_time": "2:09:07", "remaining_time": "5:01:05", "throughput": 1486.2, "total_tokens": 11514240} {"current_steps": 54570, "total_steps": 181800, "loss": 0.0059, "lr": 4.414216025356667e-05, "epoch": 6.003300330033003, "percentage": 30.02, "elapsed_time": "2:09:08", "remaining_time": "5:01:04", "throughput": 1486.21, "total_tokens": 11515296} {"current_steps": 54575, "total_steps": 181800, "loss": 0.0216, "lr": 4.4140616408059775e-05, "epoch": 6.003850385038504, "percentage": 30.02, "elapsed_time": "2:09:08", "remaining_time": "5:01:04", "throughput": 1486.21, "total_tokens": 11516384} {"current_steps": 54580, "total_steps": 181800, "loss": 0.0347, "lr": 4.4139072386143e-05, "epoch": 6.004400440044004, "percentage": 30.02, "elapsed_time": "2:09:09", "remaining_time": "5:01:03", "throughput": 1486.22, "total_tokens": 11517504} {"current_steps": 54585, "total_steps": 181800, "loss": 0.0537, "lr": 4.413752818783058e-05, "epoch": 6.0049504950495045, "percentage": 30.02, "elapsed_time": "2:09:10", "remaining_time": "5:01:02", "throughput": 1486.18, "total_tokens": 11518464} {"current_steps": 54590, "total_steps": 181800, "loss": 0.0496, "lr": 4.413598381313675e-05, "epoch": 6.005500550055006, "percentage": 30.03, "elapsed_time": "2:09:11", "remaining_time": "5:01:02", "throughput": 1486.19, "total_tokens": 11519552} {"current_steps": 54595, "total_steps": 181800, "loss": 0.0564, "lr": 4.413443926207573e-05, "epoch": 6.006050605060506, "percentage": 30.03, "elapsed_time": "2:09:11", "remaining_time": "5:01:01", "throughput": 1486.18, "total_tokens": 11520544} {"current_steps": 54600, "total_steps": 181800, "loss": 0.0813, "lr": 4.4132894534661775e-05, "epoch": 6.006600660066007, "percentage": 30.03, "elapsed_time": "2:09:12", "remaining_time": "5:01:00", "throughput": 1486.19, "total_tokens": 11521664} {"current_steps": 54605, "total_steps": 181800, "loss": 0.022, "lr": 4.4131349630909106e-05, "epoch": 6.007150715071507, "percentage": 30.04, "elapsed_time": "2:09:13", "remaining_time": "5:00:59", "throughput": 1486.2, "total_tokens": 11522752} {"current_steps": 54610, "total_steps": 181800, "loss": 0.0221, "lr": 4.412980455083197e-05, "epoch": 6.007700770077007, "percentage": 30.04, "elapsed_time": "2:09:13", "remaining_time": "5:00:59", "throughput": 1486.2, "total_tokens": 11523776} {"current_steps": 54615, "total_steps": 181800, "loss": 0.0551, "lr": 4.412825929444461e-05, "epoch": 6.008250825082508, "percentage": 30.04, "elapsed_time": "2:09:14", "remaining_time": "5:00:58", "throughput": 1486.19, "total_tokens": 11524768} {"current_steps": 54620, "total_steps": 181800, "loss": 0.0259, "lr": 4.4126713861761245e-05, "epoch": 6.008800880088009, "percentage": 30.04, "elapsed_time": "2:09:15", "remaining_time": "5:00:57", "throughput": 1486.19, "total_tokens": 11525792} {"current_steps": 54625, "total_steps": 181800, "loss": 0.0163, "lr": 4.412516825279616e-05, "epoch": 6.00935093509351, "percentage": 30.05, "elapsed_time": "2:09:15", "remaining_time": "5:00:56", "throughput": 1486.19, "total_tokens": 11526848} {"current_steps": 54630, "total_steps": 181800, "loss": 0.0132, "lr": 4.4123622467563555e-05, "epoch": 6.00990099009901, "percentage": 30.05, "elapsed_time": "2:09:16", "remaining_time": "5:00:56", "throughput": 1486.19, "total_tokens": 11527840} {"current_steps": 54635, "total_steps": 181800, "loss": 0.0962, "lr": 4.412207650607771e-05, "epoch": 6.01045104510451, "percentage": 30.05, "elapsed_time": "2:09:17", "remaining_time": "5:00:55", "throughput": 1486.2, "total_tokens": 11528928} {"current_steps": 54640, "total_steps": 181800, "loss": 0.0275, "lr": 4.4120530368352864e-05, "epoch": 6.011001100110011, "percentage": 30.06, "elapsed_time": "2:09:18", "remaining_time": "5:00:54", "throughput": 1486.2, "total_tokens": 11529952} {"current_steps": 54645, "total_steps": 181800, "loss": 0.0325, "lr": 4.411898405440326e-05, "epoch": 6.011551155115511, "percentage": 30.06, "elapsed_time": "2:09:18", "remaining_time": "5:00:53", "throughput": 1486.19, "total_tokens": 11530912} {"current_steps": 54650, "total_steps": 181800, "loss": 0.1133, "lr": 4.4117437564243144e-05, "epoch": 6.0121012101210125, "percentage": 30.06, "elapsed_time": "2:09:19", "remaining_time": "5:00:53", "throughput": 1486.19, "total_tokens": 11531936} {"current_steps": 54655, "total_steps": 181800, "loss": 0.0737, "lr": 4.4115890897886794e-05, "epoch": 6.012651265126513, "percentage": 30.06, "elapsed_time": "2:09:20", "remaining_time": "5:00:52", "throughput": 1486.19, "total_tokens": 11532992} {"current_steps": 54660, "total_steps": 181800, "loss": 0.0406, "lr": 4.4114344055348445e-05, "epoch": 6.013201320132013, "percentage": 30.07, "elapsed_time": "2:09:20", "remaining_time": "5:00:51", "throughput": 1486.2, "total_tokens": 11534080} {"current_steps": 54665, "total_steps": 181800, "loss": 0.0306, "lr": 4.411279703664236e-05, "epoch": 6.013751375137514, "percentage": 30.07, "elapsed_time": "2:09:21", "remaining_time": "5:00:51", "throughput": 1486.2, "total_tokens": 11535136} {"current_steps": 54670, "total_steps": 181800, "loss": 0.0173, "lr": 4.41112498417828e-05, "epoch": 6.014301430143014, "percentage": 30.07, "elapsed_time": "2:09:22", "remaining_time": "5:00:50", "throughput": 1486.2, "total_tokens": 11536192} {"current_steps": 54675, "total_steps": 181800, "loss": 0.1279, "lr": 4.410970247078401e-05, "epoch": 6.014851485148514, "percentage": 30.07, "elapsed_time": "2:09:22", "remaining_time": "5:00:49", "throughput": 1486.2, "total_tokens": 11537184} {"current_steps": 54680, "total_steps": 181800, "loss": 0.0481, "lr": 4.410815492366027e-05, "epoch": 6.0154015401540155, "percentage": 30.08, "elapsed_time": "2:09:23", "remaining_time": "5:00:48", "throughput": 1486.2, "total_tokens": 11538240} {"current_steps": 54685, "total_steps": 181800, "loss": 0.0328, "lr": 4.410660720042583e-05, "epoch": 6.015951595159516, "percentage": 30.08, "elapsed_time": "2:09:24", "remaining_time": "5:00:48", "throughput": 1486.2, "total_tokens": 11539296} {"current_steps": 54690, "total_steps": 181800, "loss": 0.0258, "lr": 4.4105059301094965e-05, "epoch": 6.016501650165017, "percentage": 30.08, "elapsed_time": "2:09:24", "remaining_time": "5:00:47", "throughput": 1486.22, "total_tokens": 11540480} {"current_steps": 54695, "total_steps": 181800, "loss": 0.0131, "lr": 4.410351122568193e-05, "epoch": 6.017051705170517, "percentage": 30.09, "elapsed_time": "2:09:25", "remaining_time": "5:00:46", "throughput": 1486.23, "total_tokens": 11541536} {"current_steps": 54700, "total_steps": 181800, "loss": 0.0292, "lr": 4.410196297420101e-05, "epoch": 6.017601760176017, "percentage": 30.09, "elapsed_time": "2:09:26", "remaining_time": "5:00:45", "throughput": 1486.22, "total_tokens": 11542528} {"current_steps": 54705, "total_steps": 181800, "loss": 0.0356, "lr": 4.4100414546666445e-05, "epoch": 6.018151815181518, "percentage": 30.09, "elapsed_time": "2:09:27", "remaining_time": "5:00:45", "throughput": 1486.23, "total_tokens": 11543584} {"current_steps": 54710, "total_steps": 181800, "loss": 0.023, "lr": 4.409886594309254e-05, "epoch": 6.0187018701870185, "percentage": 30.09, "elapsed_time": "2:09:27", "remaining_time": "5:00:44", "throughput": 1486.23, "total_tokens": 11544640} {"current_steps": 54715, "total_steps": 181800, "loss": 0.0104, "lr": 4.409731716349354e-05, "epoch": 6.01925192519252, "percentage": 30.1, "elapsed_time": "2:09:28", "remaining_time": "5:00:43", "throughput": 1486.23, "total_tokens": 11545696} {"current_steps": 54720, "total_steps": 181800, "loss": 0.1033, "lr": 4.409576820788375e-05, "epoch": 6.01980198019802, "percentage": 30.1, "elapsed_time": "2:09:29", "remaining_time": "5:00:43", "throughput": 1486.19, "total_tokens": 11546720} {"current_steps": 54725, "total_steps": 181800, "loss": 0.0388, "lr": 4.409421907627741e-05, "epoch": 6.02035203520352, "percentage": 30.1, "elapsed_time": "2:09:30", "remaining_time": "5:00:42", "throughput": 1486.19, "total_tokens": 11547776} {"current_steps": 54730, "total_steps": 181800, "loss": 0.0258, "lr": 4.4092669768688824e-05, "epoch": 6.020902090209021, "percentage": 30.1, "elapsed_time": "2:09:30", "remaining_time": "5:00:41", "throughput": 1486.2, "total_tokens": 11548832} {"current_steps": 54735, "total_steps": 181800, "loss": 0.0189, "lr": 4.409112028513226e-05, "epoch": 6.021452145214521, "percentage": 30.11, "elapsed_time": "2:09:31", "remaining_time": "5:00:41", "throughput": 1486.19, "total_tokens": 11549856} {"current_steps": 54740, "total_steps": 181800, "loss": 0.0499, "lr": 4.4089570625622e-05, "epoch": 6.022002200220022, "percentage": 30.11, "elapsed_time": "2:09:32", "remaining_time": "5:00:40", "throughput": 1486.2, "total_tokens": 11550912} {"current_steps": 54745, "total_steps": 181800, "loss": 0.078, "lr": 4.408802079017233e-05, "epoch": 6.022552255225523, "percentage": 30.11, "elapsed_time": "2:09:32", "remaining_time": "5:00:39", "throughput": 1486.19, "total_tokens": 11551904} {"current_steps": 54750, "total_steps": 181800, "loss": 0.0854, "lr": 4.408647077879753e-05, "epoch": 6.023102310231023, "percentage": 30.12, "elapsed_time": "2:09:33", "remaining_time": "5:00:38", "throughput": 1486.19, "total_tokens": 11552896} {"current_steps": 54755, "total_steps": 181800, "loss": 0.0354, "lr": 4.408492059151188e-05, "epoch": 6.023652365236524, "percentage": 30.12, "elapsed_time": "2:09:34", "remaining_time": "5:00:38", "throughput": 1486.19, "total_tokens": 11553952} {"current_steps": 54760, "total_steps": 181800, "loss": 0.0132, "lr": 4.408337022832969e-05, "epoch": 6.024202420242024, "percentage": 30.12, "elapsed_time": "2:09:34", "remaining_time": "5:00:37", "throughput": 1486.2, "total_tokens": 11555008} {"current_steps": 54765, "total_steps": 181800, "loss": 0.0475, "lr": 4.408181968926522e-05, "epoch": 6.024752475247524, "percentage": 30.12, "elapsed_time": "2:09:35", "remaining_time": "5:00:36", "throughput": 1486.19, "total_tokens": 11556000} {"current_steps": 54770, "total_steps": 181800, "loss": 0.0733, "lr": 4.408026897433278e-05, "epoch": 6.025302530253025, "percentage": 30.13, "elapsed_time": "2:09:36", "remaining_time": "5:00:35", "throughput": 1486.2, "total_tokens": 11557088} {"current_steps": 54775, "total_steps": 181800, "loss": 0.0091, "lr": 4.407871808354665e-05, "epoch": 6.025852585258526, "percentage": 30.13, "elapsed_time": "2:09:36", "remaining_time": "5:00:35", "throughput": 1486.21, "total_tokens": 11558176} {"current_steps": 54780, "total_steps": 181800, "loss": 0.0143, "lr": 4.4077167016921145e-05, "epoch": 6.026402640264027, "percentage": 30.13, "elapsed_time": "2:09:37", "remaining_time": "5:00:34", "throughput": 1486.22, "total_tokens": 11559264} {"current_steps": 54785, "total_steps": 181800, "loss": 0.1361, "lr": 4.407561577447054e-05, "epoch": 6.026952695269527, "percentage": 30.13, "elapsed_time": "2:09:38", "remaining_time": "5:00:33", "throughput": 1486.22, "total_tokens": 11560320} {"current_steps": 54790, "total_steps": 181800, "loss": 0.0528, "lr": 4.4074064356209135e-05, "epoch": 6.027502750275027, "percentage": 30.14, "elapsed_time": "2:09:39", "remaining_time": "5:00:32", "throughput": 1486.23, "total_tokens": 11561376} {"current_steps": 54795, "total_steps": 181800, "loss": 0.1489, "lr": 4.407251276215123e-05, "epoch": 6.028052805280528, "percentage": 30.14, "elapsed_time": "2:09:39", "remaining_time": "5:00:31", "throughput": 1486.23, "total_tokens": 11562464} {"current_steps": 54800, "total_steps": 181800, "loss": 0.0847, "lr": 4.407096099231113e-05, "epoch": 6.028602860286028, "percentage": 30.14, "elapsed_time": "2:09:40", "remaining_time": "5:00:31", "throughput": 1486.24, "total_tokens": 11563520} {"current_steps": 54805, "total_steps": 181800, "loss": 0.0675, "lr": 4.406940904670313e-05, "epoch": 6.0291529152915295, "percentage": 30.15, "elapsed_time": "2:09:41", "remaining_time": "5:00:30", "throughput": 1486.24, "total_tokens": 11564544} {"current_steps": 54810, "total_steps": 181800, "loss": 0.0234, "lr": 4.406785692534154e-05, "epoch": 6.02970297029703, "percentage": 30.15, "elapsed_time": "2:09:41", "remaining_time": "5:00:29", "throughput": 1486.25, "total_tokens": 11565632} {"current_steps": 54815, "total_steps": 181800, "loss": 0.031, "lr": 4.4066304628240664e-05, "epoch": 6.03025302530253, "percentage": 30.15, "elapsed_time": "2:09:42", "remaining_time": "5:00:28", "throughput": 1486.25, "total_tokens": 11566688} {"current_steps": 54820, "total_steps": 181800, "loss": 0.0689, "lr": 4.40647521554148e-05, "epoch": 6.030803080308031, "percentage": 30.15, "elapsed_time": "2:09:43", "remaining_time": "5:00:28", "throughput": 1486.27, "total_tokens": 11567840} {"current_steps": 54825, "total_steps": 181800, "loss": 0.0618, "lr": 4.406319950687827e-05, "epoch": 6.031353135313531, "percentage": 30.16, "elapsed_time": "2:09:43", "remaining_time": "5:00:27", "throughput": 1486.26, "total_tokens": 11568832} {"current_steps": 54830, "total_steps": 181800, "loss": 0.0188, "lr": 4.406164668264537e-05, "epoch": 6.031903190319032, "percentage": 30.16, "elapsed_time": "2:09:44", "remaining_time": "5:00:26", "throughput": 1486.28, "total_tokens": 11569952} {"current_steps": 54835, "total_steps": 181800, "loss": 0.0168, "lr": 4.406009368273043e-05, "epoch": 6.0324532453245325, "percentage": 30.16, "elapsed_time": "2:09:45", "remaining_time": "5:00:25", "throughput": 1486.28, "total_tokens": 11571008} {"current_steps": 54840, "total_steps": 181800, "loss": 0.0793, "lr": 4.405854050714775e-05, "epoch": 6.033003300330033, "percentage": 30.17, "elapsed_time": "2:09:45", "remaining_time": "5:00:25", "throughput": 1486.29, "total_tokens": 11572096} {"current_steps": 54845, "total_steps": 181800, "loss": 0.1175, "lr": 4.4056987155911647e-05, "epoch": 6.033553355335534, "percentage": 30.17, "elapsed_time": "2:09:46", "remaining_time": "5:00:24", "throughput": 1486.29, "total_tokens": 11573120} {"current_steps": 54850, "total_steps": 181800, "loss": 0.0562, "lr": 4.405543362903644e-05, "epoch": 6.034103410341034, "percentage": 30.17, "elapsed_time": "2:09:47", "remaining_time": "5:00:23", "throughput": 1486.3, "total_tokens": 11574208} {"current_steps": 54855, "total_steps": 181800, "loss": 0.0075, "lr": 4.405387992653643e-05, "epoch": 6.034653465346534, "percentage": 30.17, "elapsed_time": "2:09:47", "remaining_time": "5:00:22", "throughput": 1486.3, "total_tokens": 11575232} {"current_steps": 54860, "total_steps": 181800, "loss": 0.0289, "lr": 4.405232604842596e-05, "epoch": 6.035203520352035, "percentage": 30.18, "elapsed_time": "2:09:48", "remaining_time": "5:00:22", "throughput": 1486.3, "total_tokens": 11576288} {"current_steps": 54865, "total_steps": 181800, "loss": 0.0625, "lr": 4.405077199471935e-05, "epoch": 6.0357535753575355, "percentage": 30.18, "elapsed_time": "2:09:49", "remaining_time": "5:00:21", "throughput": 1486.3, "total_tokens": 11577344} {"current_steps": 54870, "total_steps": 181800, "loss": 0.0352, "lr": 4.404921776543091e-05, "epoch": 6.036303630363037, "percentage": 30.18, "elapsed_time": "2:09:50", "remaining_time": "5:00:20", "throughput": 1486.3, "total_tokens": 11578368} {"current_steps": 54875, "total_steps": 181800, "loss": 0.03, "lr": 4.4047663360574974e-05, "epoch": 6.036853685368537, "percentage": 30.18, "elapsed_time": "2:09:50", "remaining_time": "5:00:19", "throughput": 1486.31, "total_tokens": 11579424} {"current_steps": 54880, "total_steps": 181800, "loss": 0.0889, "lr": 4.404610878016586e-05, "epoch": 6.037403740374037, "percentage": 30.19, "elapsed_time": "2:09:51", "remaining_time": "5:00:19", "throughput": 1486.31, "total_tokens": 11580480} {"current_steps": 54885, "total_steps": 181800, "loss": 0.0525, "lr": 4.40445540242179e-05, "epoch": 6.037953795379538, "percentage": 30.19, "elapsed_time": "2:09:52", "remaining_time": "5:00:18", "throughput": 1486.32, "total_tokens": 11581600} {"current_steps": 54890, "total_steps": 181800, "loss": 0.0254, "lr": 4.404299909274543e-05, "epoch": 6.038503850385038, "percentage": 30.19, "elapsed_time": "2:09:52", "remaining_time": "5:00:17", "throughput": 1486.32, "total_tokens": 11582624} {"current_steps": 54895, "total_steps": 181800, "loss": 0.0062, "lr": 4.4041443985762774e-05, "epoch": 6.039053905390539, "percentage": 30.2, "elapsed_time": "2:09:53", "remaining_time": "5:00:16", "throughput": 1486.32, "total_tokens": 11583648} {"current_steps": 54900, "total_steps": 181800, "loss": 0.0261, "lr": 4.4039888703284265e-05, "epoch": 6.03960396039604, "percentage": 30.2, "elapsed_time": "2:09:54", "remaining_time": "5:00:16", "throughput": 1486.32, "total_tokens": 11584672} {"current_steps": 54905, "total_steps": 181800, "loss": 0.0135, "lr": 4.403833324532424e-05, "epoch": 6.04015401540154, "percentage": 30.2, "elapsed_time": "2:09:54", "remaining_time": "5:00:15", "throughput": 1486.32, "total_tokens": 11585696} {"current_steps": 54910, "total_steps": 181800, "loss": 0.0325, "lr": 4.403677761189703e-05, "epoch": 6.040704070407041, "percentage": 30.2, "elapsed_time": "2:09:55", "remaining_time": "5:00:14", "throughput": 1486.32, "total_tokens": 11586720} {"current_steps": 54915, "total_steps": 181800, "loss": 0.006, "lr": 4.4035221803016974e-05, "epoch": 6.041254125412541, "percentage": 30.21, "elapsed_time": "2:09:56", "remaining_time": "5:00:13", "throughput": 1486.34, "total_tokens": 11587872} {"current_steps": 54920, "total_steps": 181800, "loss": 0.0252, "lr": 4.403366581869841e-05, "epoch": 6.041804180418042, "percentage": 30.21, "elapsed_time": "2:09:56", "remaining_time": "5:00:13", "throughput": 1486.35, "total_tokens": 11588960} {"current_steps": 54925, "total_steps": 181800, "loss": 0.0958, "lr": 4.403210965895569e-05, "epoch": 6.042354235423542, "percentage": 30.21, "elapsed_time": "2:09:57", "remaining_time": "5:00:12", "throughput": 1486.35, "total_tokens": 11589984} {"current_steps": 54930, "total_steps": 181800, "loss": 0.0094, "lr": 4.403055332380314e-05, "epoch": 6.042904290429043, "percentage": 30.21, "elapsed_time": "2:09:58", "remaining_time": "5:00:11", "throughput": 1486.34, "total_tokens": 11590976} {"current_steps": 54935, "total_steps": 181800, "loss": 0.0099, "lr": 4.402899681325512e-05, "epoch": 6.043454345434544, "percentage": 30.22, "elapsed_time": "2:09:59", "remaining_time": "5:00:10", "throughput": 1486.35, "total_tokens": 11592064} {"current_steps": 54940, "total_steps": 181800, "loss": 0.0154, "lr": 4.402744012732596e-05, "epoch": 6.044004400440044, "percentage": 30.22, "elapsed_time": "2:09:59", "remaining_time": "5:00:09", "throughput": 1486.36, "total_tokens": 11593120} {"current_steps": 54945, "total_steps": 181800, "loss": 0.0058, "lr": 4.402588326603002e-05, "epoch": 6.044554455445544, "percentage": 30.22, "elapsed_time": "2:10:00", "remaining_time": "5:00:09", "throughput": 1486.36, "total_tokens": 11594176} {"current_steps": 54950, "total_steps": 181800, "loss": 0.1089, "lr": 4.402432622938164e-05, "epoch": 6.045104510451045, "percentage": 30.23, "elapsed_time": "2:10:01", "remaining_time": "5:00:08", "throughput": 1486.36, "total_tokens": 11595200} {"current_steps": 54955, "total_steps": 181800, "loss": 0.0509, "lr": 4.402276901739517e-05, "epoch": 6.0456545654565454, "percentage": 30.23, "elapsed_time": "2:10:01", "remaining_time": "5:00:07", "throughput": 1486.37, "total_tokens": 11596288} {"current_steps": 54960, "total_steps": 181800, "loss": 0.1367, "lr": 4.402121163008497e-05, "epoch": 6.0462046204620465, "percentage": 30.23, "elapsed_time": "2:10:02", "remaining_time": "5:00:06", "throughput": 1486.38, "total_tokens": 11597376} {"current_steps": 54965, "total_steps": 181800, "loss": 0.1054, "lr": 4.401965406746539e-05, "epoch": 6.046754675467547, "percentage": 30.23, "elapsed_time": "2:10:03", "remaining_time": "5:00:06", "throughput": 1486.38, "total_tokens": 11598432} {"current_steps": 54970, "total_steps": 181800, "loss": 0.0394, "lr": 4.4018096329550786e-05, "epoch": 6.047304730473047, "percentage": 30.24, "elapsed_time": "2:10:03", "remaining_time": "5:00:05", "throughput": 1486.39, "total_tokens": 11599520} {"current_steps": 54975, "total_steps": 181800, "loss": 0.0368, "lr": 4.401653841635551e-05, "epoch": 6.047854785478548, "percentage": 30.24, "elapsed_time": "2:10:04", "remaining_time": "5:00:04", "throughput": 1486.38, "total_tokens": 11600480} {"current_steps": 54980, "total_steps": 181800, "loss": 0.0834, "lr": 4.401498032789393e-05, "epoch": 6.048404840484048, "percentage": 30.24, "elapsed_time": "2:10:05", "remaining_time": "5:00:03", "throughput": 1486.38, "total_tokens": 11601472} {"current_steps": 54985, "total_steps": 181800, "loss": 0.065, "lr": 4.40134220641804e-05, "epoch": 6.048954895489549, "percentage": 30.24, "elapsed_time": "2:10:05", "remaining_time": "5:00:03", "throughput": 1486.38, "total_tokens": 11602528} {"current_steps": 54990, "total_steps": 181800, "loss": 0.0996, "lr": 4.4011863625229276e-05, "epoch": 6.0495049504950495, "percentage": 30.25, "elapsed_time": "2:10:06", "remaining_time": "5:00:02", "throughput": 1486.39, "total_tokens": 11603648} {"current_steps": 54995, "total_steps": 181800, "loss": 0.0615, "lr": 4.4010305011054933e-05, "epoch": 6.05005500550055, "percentage": 30.25, "elapsed_time": "2:10:07", "remaining_time": "5:00:01", "throughput": 1486.4, "total_tokens": 11604704} {"current_steps": 55000, "total_steps": 181800, "loss": 0.0136, "lr": 4.400874622167173e-05, "epoch": 6.050605060506051, "percentage": 30.25, "elapsed_time": "2:10:07", "remaining_time": "5:00:00", "throughput": 1486.41, "total_tokens": 11605792} {"current_steps": 55005, "total_steps": 181800, "loss": 0.0248, "lr": 4.4007187257094034e-05, "epoch": 6.051155115511551, "percentage": 30.26, "elapsed_time": "2:10:08", "remaining_time": "5:00:00", "throughput": 1486.41, "total_tokens": 11606816} {"current_steps": 55010, "total_steps": 181800, "loss": 0.0269, "lr": 4.4005628117336216e-05, "epoch": 6.051705170517051, "percentage": 30.26, "elapsed_time": "2:10:09", "remaining_time": "4:59:59", "throughput": 1486.41, "total_tokens": 11607872} {"current_steps": 55015, "total_steps": 181800, "loss": 0.0806, "lr": 4.400406880241264e-05, "epoch": 6.052255225522552, "percentage": 30.26, "elapsed_time": "2:10:10", "remaining_time": "4:59:58", "throughput": 1486.41, "total_tokens": 11608896} {"current_steps": 55020, "total_steps": 181800, "loss": 0.0513, "lr": 4.400250931233768e-05, "epoch": 6.052805280528053, "percentage": 30.26, "elapsed_time": "2:10:10", "remaining_time": "4:59:57", "throughput": 1486.41, "total_tokens": 11609920} {"current_steps": 55025, "total_steps": 181800, "loss": 0.0125, "lr": 4.400094964712571e-05, "epoch": 6.053355335533554, "percentage": 30.27, "elapsed_time": "2:10:11", "remaining_time": "4:59:57", "throughput": 1486.41, "total_tokens": 11610912} {"current_steps": 55030, "total_steps": 181800, "loss": 0.1066, "lr": 4.399938980679111e-05, "epoch": 6.053905390539054, "percentage": 30.27, "elapsed_time": "2:10:12", "remaining_time": "4:59:56", "throughput": 1486.41, "total_tokens": 11611936} {"current_steps": 55035, "total_steps": 181800, "loss": 0.0176, "lr": 4.399782979134825e-05, "epoch": 6.054455445544554, "percentage": 30.27, "elapsed_time": "2:10:12", "remaining_time": "4:59:55", "throughput": 1486.41, "total_tokens": 11612960} {"current_steps": 55040, "total_steps": 181800, "loss": 0.0161, "lr": 4.39962696008115e-05, "epoch": 6.055005500550055, "percentage": 30.28, "elapsed_time": "2:10:13", "remaining_time": "4:59:54", "throughput": 1486.41, "total_tokens": 11613984} {"current_steps": 55045, "total_steps": 181800, "loss": 0.0613, "lr": 4.3994709235195264e-05, "epoch": 6.055555555555555, "percentage": 30.28, "elapsed_time": "2:10:14", "remaining_time": "4:59:54", "throughput": 1486.41, "total_tokens": 11615040} {"current_steps": 55050, "total_steps": 181800, "loss": 0.0115, "lr": 4.39931486945139e-05, "epoch": 6.0561056105610565, "percentage": 30.28, "elapsed_time": "2:10:14", "remaining_time": "4:59:53", "throughput": 1486.41, "total_tokens": 11616064} {"current_steps": 55055, "total_steps": 181800, "loss": 0.0647, "lr": 4.399158797878179e-05, "epoch": 6.056655665566557, "percentage": 30.28, "elapsed_time": "2:10:15", "remaining_time": "4:59:52", "throughput": 1486.41, "total_tokens": 11617120} {"current_steps": 55060, "total_steps": 181800, "loss": 0.0178, "lr": 4.3990027088013335e-05, "epoch": 6.057205720572057, "percentage": 30.29, "elapsed_time": "2:10:16", "remaining_time": "4:59:51", "throughput": 1486.41, "total_tokens": 11618144} {"current_steps": 55065, "total_steps": 181800, "loss": 0.0199, "lr": 4.3988466022222907e-05, "epoch": 6.057755775577558, "percentage": 30.29, "elapsed_time": "2:10:16", "remaining_time": "4:59:51", "throughput": 1486.42, "total_tokens": 11619232} {"current_steps": 55070, "total_steps": 181800, "loss": 0.0485, "lr": 4.398690478142491e-05, "epoch": 6.058305830583058, "percentage": 30.29, "elapsed_time": "2:10:17", "remaining_time": "4:59:50", "throughput": 1486.43, "total_tokens": 11620288} {"current_steps": 55075, "total_steps": 181800, "loss": 0.015, "lr": 4.3985343365633716e-05, "epoch": 6.058855885588559, "percentage": 30.29, "elapsed_time": "2:10:18", "remaining_time": "4:59:49", "throughput": 1486.42, "total_tokens": 11621280} {"current_steps": 55080, "total_steps": 181800, "loss": 0.0161, "lr": 4.398378177486372e-05, "epoch": 6.0594059405940595, "percentage": 30.3, "elapsed_time": "2:10:18", "remaining_time": "4:59:48", "throughput": 1486.42, "total_tokens": 11622304} {"current_steps": 55085, "total_steps": 181800, "loss": 0.0201, "lr": 4.3982220009129316e-05, "epoch": 6.05995599559956, "percentage": 30.3, "elapsed_time": "2:10:19", "remaining_time": "4:59:48", "throughput": 1486.44, "total_tokens": 11623456} {"current_steps": 55090, "total_steps": 181800, "loss": 0.0038, "lr": 4.39806580684449e-05, "epoch": 6.060506050605061, "percentage": 30.3, "elapsed_time": "2:10:20", "remaining_time": "4:59:47", "throughput": 1486.45, "total_tokens": 11624544} {"current_steps": 55095, "total_steps": 181800, "loss": 0.0035, "lr": 4.397909595282487e-05, "epoch": 6.061056105610561, "percentage": 30.31, "elapsed_time": "2:10:21", "remaining_time": "4:59:46", "throughput": 1486.46, "total_tokens": 11625664} {"current_steps": 55100, "total_steps": 181800, "loss": 0.0573, "lr": 4.3977533662283624e-05, "epoch": 6.061606160616061, "percentage": 30.31, "elapsed_time": "2:10:21", "remaining_time": "4:59:45", "throughput": 1486.46, "total_tokens": 11626688} {"current_steps": 55105, "total_steps": 181800, "loss": 0.1276, "lr": 4.3975971196835544e-05, "epoch": 6.062156215621562, "percentage": 30.31, "elapsed_time": "2:10:22", "remaining_time": "4:59:44", "throughput": 1486.46, "total_tokens": 11627744} {"current_steps": 55110, "total_steps": 181800, "loss": 0.0232, "lr": 4.397440855649505e-05, "epoch": 6.0627062706270625, "percentage": 30.31, "elapsed_time": "2:10:23", "remaining_time": "4:59:44", "throughput": 1486.47, "total_tokens": 11628832} {"current_steps": 55115, "total_steps": 181800, "loss": 0.0438, "lr": 4.397284574127654e-05, "epoch": 6.063256325632564, "percentage": 30.32, "elapsed_time": "2:10:23", "remaining_time": "4:59:43", "throughput": 1486.48, "total_tokens": 11629952} {"current_steps": 55120, "total_steps": 181800, "loss": 0.0722, "lr": 4.397128275119441e-05, "epoch": 6.063806380638064, "percentage": 30.32, "elapsed_time": "2:10:24", "remaining_time": "4:59:42", "throughput": 1486.49, "total_tokens": 11631040} {"current_steps": 55125, "total_steps": 181800, "loss": 0.0177, "lr": 4.3969719586263065e-05, "epoch": 6.064356435643564, "percentage": 30.32, "elapsed_time": "2:10:25", "remaining_time": "4:59:41", "throughput": 1486.5, "total_tokens": 11632160} {"current_steps": 55130, "total_steps": 181800, "loss": 0.0477, "lr": 4.3968156246496925e-05, "epoch": 6.064906490649065, "percentage": 30.32, "elapsed_time": "2:10:25", "remaining_time": "4:59:41", "throughput": 1486.51, "total_tokens": 11633216} {"current_steps": 55135, "total_steps": 181800, "loss": 0.1024, "lr": 4.396659273191039e-05, "epoch": 6.065456545654565, "percentage": 30.33, "elapsed_time": "2:10:26", "remaining_time": "4:59:40", "throughput": 1486.51, "total_tokens": 11634272} {"current_steps": 55140, "total_steps": 181800, "loss": 0.0276, "lr": 4.396502904251787e-05, "epoch": 6.066006600660066, "percentage": 30.33, "elapsed_time": "2:10:27", "remaining_time": "4:59:39", "throughput": 1486.52, "total_tokens": 11635360} {"current_steps": 55145, "total_steps": 181800, "loss": 0.0154, "lr": 4.396346517833377e-05, "epoch": 6.066556655665567, "percentage": 30.33, "elapsed_time": "2:10:27", "remaining_time": "4:59:38", "throughput": 1486.52, "total_tokens": 11636384} {"current_steps": 55150, "total_steps": 181800, "loss": 0.033, "lr": 4.396190113937252e-05, "epoch": 6.067106710671067, "percentage": 30.34, "elapsed_time": "2:10:28", "remaining_time": "4:59:38", "throughput": 1486.53, "total_tokens": 11637472} {"current_steps": 55155, "total_steps": 181800, "loss": 0.0512, "lr": 4.3960336925648526e-05, "epoch": 6.067656765676568, "percentage": 30.34, "elapsed_time": "2:10:29", "remaining_time": "4:59:37", "throughput": 1486.52, "total_tokens": 11638496} {"current_steps": 55160, "total_steps": 181800, "loss": 0.0196, "lr": 4.3958772537176206e-05, "epoch": 6.068206820682068, "percentage": 30.34, "elapsed_time": "2:10:30", "remaining_time": "4:59:36", "throughput": 1486.54, "total_tokens": 11639616} {"current_steps": 55165, "total_steps": 181800, "loss": 0.0119, "lr": 4.3957207973969975e-05, "epoch": 6.068756875687569, "percentage": 30.34, "elapsed_time": "2:10:30", "remaining_time": "4:59:35", "throughput": 1486.54, "total_tokens": 11640672} {"current_steps": 55170, "total_steps": 181800, "loss": 0.0358, "lr": 4.395564323604425e-05, "epoch": 6.069306930693069, "percentage": 30.35, "elapsed_time": "2:10:31", "remaining_time": "4:59:35", "throughput": 1486.54, "total_tokens": 11641696} {"current_steps": 55175, "total_steps": 181800, "loss": 0.0227, "lr": 4.395407832341346e-05, "epoch": 6.06985698569857, "percentage": 30.35, "elapsed_time": "2:10:32", "remaining_time": "4:59:34", "throughput": 1486.54, "total_tokens": 11642720} {"current_steps": 55180, "total_steps": 181800, "loss": 0.0076, "lr": 4.395251323609203e-05, "epoch": 6.070407040704071, "percentage": 30.35, "elapsed_time": "2:10:32", "remaining_time": "4:59:33", "throughput": 1486.54, "total_tokens": 11643744} {"current_steps": 55185, "total_steps": 181800, "loss": 0.0326, "lr": 4.3950947974094376e-05, "epoch": 6.070957095709571, "percentage": 30.35, "elapsed_time": "2:10:33", "remaining_time": "4:59:32", "throughput": 1486.54, "total_tokens": 11644768} {"current_steps": 55190, "total_steps": 181800, "loss": 0.1469, "lr": 4.3949382537434925e-05, "epoch": 6.071507150715071, "percentage": 30.36, "elapsed_time": "2:10:34", "remaining_time": "4:59:32", "throughput": 1486.55, "total_tokens": 11645856} {"current_steps": 55195, "total_steps": 181800, "loss": 0.0635, "lr": 4.394781692612811e-05, "epoch": 6.072057205720572, "percentage": 30.36, "elapsed_time": "2:10:34", "remaining_time": "4:59:31", "throughput": 1486.55, "total_tokens": 11646912} {"current_steps": 55200, "total_steps": 181800, "loss": 0.0211, "lr": 4.394625114018836e-05, "epoch": 6.072607260726072, "percentage": 30.36, "elapsed_time": "2:10:35", "remaining_time": "4:59:30", "throughput": 1486.55, "total_tokens": 11647968} {"current_steps": 55205, "total_steps": 181800, "loss": 0.0715, "lr": 4.39446851796301e-05, "epoch": 6.0731573157315735, "percentage": 30.37, "elapsed_time": "2:10:36", "remaining_time": "4:59:29", "throughput": 1486.56, "total_tokens": 11649056} {"current_steps": 55210, "total_steps": 181800, "loss": 0.0087, "lr": 4.3943119044467774e-05, "epoch": 6.073707370737074, "percentage": 30.37, "elapsed_time": "2:10:36", "remaining_time": "4:59:29", "throughput": 1486.56, "total_tokens": 11650080} {"current_steps": 55215, "total_steps": 181800, "loss": 0.0499, "lr": 4.3941552734715804e-05, "epoch": 6.074257425742574, "percentage": 30.37, "elapsed_time": "2:10:37", "remaining_time": "4:59:28", "throughput": 1486.57, "total_tokens": 11651200} {"current_steps": 55220, "total_steps": 181800, "loss": 0.0165, "lr": 4.393998625038863e-05, "epoch": 6.074807480748075, "percentage": 30.37, "elapsed_time": "2:10:38", "remaining_time": "4:59:27", "throughput": 1486.57, "total_tokens": 11652192} {"current_steps": 55225, "total_steps": 181800, "loss": 0.0443, "lr": 4.39384195915007e-05, "epoch": 6.075357535753575, "percentage": 30.38, "elapsed_time": "2:10:39", "remaining_time": "4:59:26", "throughput": 1486.57, "total_tokens": 11653216} {"current_steps": 55230, "total_steps": 181800, "loss": 0.0097, "lr": 4.393685275806644e-05, "epoch": 6.075907590759076, "percentage": 30.38, "elapsed_time": "2:10:39", "remaining_time": "4:59:26", "throughput": 1486.57, "total_tokens": 11654272} {"current_steps": 55235, "total_steps": 181800, "loss": 0.0928, "lr": 4.39352857501003e-05, "epoch": 6.0764576457645765, "percentage": 30.38, "elapsed_time": "2:10:40", "remaining_time": "4:59:25", "throughput": 1486.58, "total_tokens": 11655360} {"current_steps": 55240, "total_steps": 181800, "loss": 0.0689, "lr": 4.39337185676167e-05, "epoch": 6.077007700770077, "percentage": 30.39, "elapsed_time": "2:10:41", "remaining_time": "4:59:24", "throughput": 1486.57, "total_tokens": 11656320} {"current_steps": 55245, "total_steps": 181800, "loss": 0.0233, "lr": 4.393215121063011e-05, "epoch": 6.077557755775578, "percentage": 30.39, "elapsed_time": "2:10:41", "remaining_time": "4:59:23", "throughput": 1486.57, "total_tokens": 11657344} {"current_steps": 55250, "total_steps": 181800, "loss": 0.0804, "lr": 4.393058367915498e-05, "epoch": 6.078107810781078, "percentage": 30.39, "elapsed_time": "2:10:42", "remaining_time": "4:59:23", "throughput": 1486.58, "total_tokens": 11658400} {"current_steps": 55255, "total_steps": 181800, "loss": 0.1253, "lr": 4.392901597320573e-05, "epoch": 6.078657865786579, "percentage": 30.39, "elapsed_time": "2:10:43", "remaining_time": "4:59:22", "throughput": 1486.57, "total_tokens": 11659392} {"current_steps": 55260, "total_steps": 181800, "loss": 0.0071, "lr": 4.3927448092796824e-05, "epoch": 6.079207920792079, "percentage": 30.4, "elapsed_time": "2:10:43", "remaining_time": "4:59:21", "throughput": 1486.58, "total_tokens": 11660512} {"current_steps": 55265, "total_steps": 181800, "loss": 0.0165, "lr": 4.392588003794271e-05, "epoch": 6.0797579757975795, "percentage": 30.4, "elapsed_time": "2:10:44", "remaining_time": "4:59:20", "throughput": 1486.59, "total_tokens": 11661568} {"current_steps": 55270, "total_steps": 181800, "loss": 0.0519, "lr": 4.392431180865785e-05, "epoch": 6.080308030803081, "percentage": 30.4, "elapsed_time": "2:10:45", "remaining_time": "4:59:20", "throughput": 1486.6, "total_tokens": 11662688} {"current_steps": 55275, "total_steps": 181800, "loss": 0.0037, "lr": 4.392274340495668e-05, "epoch": 6.080858085808581, "percentage": 30.4, "elapsed_time": "2:10:45", "remaining_time": "4:59:19", "throughput": 1486.6, "total_tokens": 11663712} {"current_steps": 55280, "total_steps": 181800, "loss": 0.0278, "lr": 4.392117482685367e-05, "epoch": 6.081408140814081, "percentage": 30.41, "elapsed_time": "2:10:46", "remaining_time": "4:59:18", "throughput": 1486.6, "total_tokens": 11664768} {"current_steps": 55285, "total_steps": 181800, "loss": 0.0776, "lr": 4.391960607436327e-05, "epoch": 6.081958195819582, "percentage": 30.41, "elapsed_time": "2:10:47", "remaining_time": "4:59:17", "throughput": 1486.61, "total_tokens": 11665856} {"current_steps": 55290, "total_steps": 181800, "loss": 0.0027, "lr": 4.3918037147499935e-05, "epoch": 6.082508250825082, "percentage": 30.41, "elapsed_time": "2:10:47", "remaining_time": "4:59:17", "throughput": 1486.61, "total_tokens": 11666880} {"current_steps": 55295, "total_steps": 181800, "loss": 0.0064, "lr": 4.391646804627814e-05, "epoch": 6.083058305830583, "percentage": 30.42, "elapsed_time": "2:10:48", "remaining_time": "4:59:16", "throughput": 1486.61, "total_tokens": 11667872} {"current_steps": 55300, "total_steps": 181800, "loss": 0.096, "lr": 4.391489877071232e-05, "epoch": 6.083608360836084, "percentage": 30.42, "elapsed_time": "2:10:49", "remaining_time": "4:59:15", "throughput": 1486.61, "total_tokens": 11668928} {"current_steps": 55305, "total_steps": 181800, "loss": 0.0977, "lr": 4.3913329320816966e-05, "epoch": 6.084158415841584, "percentage": 30.42, "elapsed_time": "2:10:50", "remaining_time": "4:59:14", "throughput": 1486.62, "total_tokens": 11670016} {"current_steps": 55310, "total_steps": 181800, "loss": 0.0311, "lr": 4.3911759696606526e-05, "epoch": 6.084708470847085, "percentage": 30.42, "elapsed_time": "2:10:50", "remaining_time": "4:59:14", "throughput": 1486.62, "total_tokens": 11671040} {"current_steps": 55315, "total_steps": 181800, "loss": 0.0017, "lr": 4.391018989809546e-05, "epoch": 6.085258525852585, "percentage": 30.43, "elapsed_time": "2:10:51", "remaining_time": "4:59:13", "throughput": 1486.63, "total_tokens": 11672128} {"current_steps": 55320, "total_steps": 181800, "loss": 0.0447, "lr": 4.390861992529827e-05, "epoch": 6.085808580858086, "percentage": 30.43, "elapsed_time": "2:10:52", "remaining_time": "4:59:12", "throughput": 1486.63, "total_tokens": 11673152} {"current_steps": 55325, "total_steps": 181800, "loss": 0.099, "lr": 4.3907049778229395e-05, "epoch": 6.086358635863586, "percentage": 30.43, "elapsed_time": "2:10:52", "remaining_time": "4:59:11", "throughput": 1486.63, "total_tokens": 11674176} {"current_steps": 55330, "total_steps": 181800, "loss": 0.044, "lr": 4.390547945690331e-05, "epoch": 6.086908690869087, "percentage": 30.43, "elapsed_time": "2:10:53", "remaining_time": "4:59:11", "throughput": 1486.63, "total_tokens": 11675264} {"current_steps": 55335, "total_steps": 181800, "loss": 0.092, "lr": 4.39039089613345e-05, "epoch": 6.087458745874588, "percentage": 30.44, "elapsed_time": "2:10:54", "remaining_time": "4:59:10", "throughput": 1486.64, "total_tokens": 11676320} {"current_steps": 55340, "total_steps": 181800, "loss": 0.0214, "lr": 4.390233829153742e-05, "epoch": 6.088008800880088, "percentage": 30.44, "elapsed_time": "2:10:54", "remaining_time": "4:59:09", "throughput": 1486.63, "total_tokens": 11677312} {"current_steps": 55345, "total_steps": 181800, "loss": 0.04, "lr": 4.390076744752657e-05, "epoch": 6.088558855885589, "percentage": 30.44, "elapsed_time": "2:10:55", "remaining_time": "4:59:08", "throughput": 1486.64, "total_tokens": 11678368} {"current_steps": 55350, "total_steps": 181800, "loss": 0.0605, "lr": 4.389919642931642e-05, "epoch": 6.089108910891089, "percentage": 30.45, "elapsed_time": "2:10:56", "remaining_time": "4:59:07", "throughput": 1486.64, "total_tokens": 11679392} {"current_steps": 55355, "total_steps": 181800, "loss": 0.0753, "lr": 4.389762523692144e-05, "epoch": 6.089658965896589, "percentage": 30.45, "elapsed_time": "2:10:56", "remaining_time": "4:59:07", "throughput": 1486.64, "total_tokens": 11680448} {"current_steps": 55360, "total_steps": 181800, "loss": 0.0236, "lr": 4.3896053870356114e-05, "epoch": 6.0902090209020905, "percentage": 30.45, "elapsed_time": "2:10:57", "remaining_time": "4:59:06", "throughput": 1486.64, "total_tokens": 11681472} {"current_steps": 55365, "total_steps": 181800, "loss": 0.0351, "lr": 4.389448232963492e-05, "epoch": 6.090759075907591, "percentage": 30.45, "elapsed_time": "2:10:58", "remaining_time": "4:59:05", "throughput": 1486.64, "total_tokens": 11682528} {"current_steps": 55370, "total_steps": 181800, "loss": 0.0058, "lr": 4.3892910614772354e-05, "epoch": 6.091309130913091, "percentage": 30.46, "elapsed_time": "2:10:59", "remaining_time": "4:59:04", "throughput": 1486.65, "total_tokens": 11683584} {"current_steps": 55375, "total_steps": 181800, "loss": 0.0435, "lr": 4.3891338725782907e-05, "epoch": 6.091859185918592, "percentage": 30.46, "elapsed_time": "2:10:59", "remaining_time": "4:59:04", "throughput": 1486.64, "total_tokens": 11684576} {"current_steps": 55380, "total_steps": 181800, "loss": 0.0287, "lr": 4.388976666268104e-05, "epoch": 6.092409240924092, "percentage": 30.46, "elapsed_time": "2:11:00", "remaining_time": "4:59:03", "throughput": 1486.65, "total_tokens": 11685632} {"current_steps": 55385, "total_steps": 181800, "loss": 0.0266, "lr": 4.3888194425481266e-05, "epoch": 6.092959295929593, "percentage": 30.46, "elapsed_time": "2:11:01", "remaining_time": "4:59:02", "throughput": 1486.65, "total_tokens": 11686720} {"current_steps": 55390, "total_steps": 181800, "loss": 0.1545, "lr": 4.388662201419806e-05, "epoch": 6.0935093509350935, "percentage": 30.47, "elapsed_time": "2:11:01", "remaining_time": "4:59:02", "throughput": 1486.66, "total_tokens": 11687808} {"current_steps": 55395, "total_steps": 181800, "loss": 0.0115, "lr": 4.3885049428845935e-05, "epoch": 6.094059405940594, "percentage": 30.47, "elapsed_time": "2:11:02", "remaining_time": "4:59:01", "throughput": 1486.66, "total_tokens": 11688832} {"current_steps": 55400, "total_steps": 181800, "loss": 0.0148, "lr": 4.388347666943936e-05, "epoch": 6.094609460946095, "percentage": 30.47, "elapsed_time": "2:11:03", "remaining_time": "4:59:00", "throughput": 1486.66, "total_tokens": 11689888} {"current_steps": 55405, "total_steps": 181800, "loss": 0.0501, "lr": 4.388190373599285e-05, "epoch": 6.095159515951595, "percentage": 30.48, "elapsed_time": "2:11:03", "remaining_time": "4:58:59", "throughput": 1486.67, "total_tokens": 11690976} {"current_steps": 55410, "total_steps": 181800, "loss": 0.061, "lr": 4.3880330628520886e-05, "epoch": 6.095709570957096, "percentage": 30.48, "elapsed_time": "2:11:04", "remaining_time": "4:58:59", "throughput": 1486.67, "total_tokens": 11691968} {"current_steps": 55415, "total_steps": 181800, "loss": 0.0627, "lr": 4.387875734703798e-05, "epoch": 6.096259625962596, "percentage": 30.48, "elapsed_time": "2:11:05", "remaining_time": "4:58:58", "throughput": 1486.67, "total_tokens": 11693024} {"current_steps": 55420, "total_steps": 181800, "loss": 0.0914, "lr": 4.3877183891558624e-05, "epoch": 6.0968096809680965, "percentage": 30.48, "elapsed_time": "2:11:05", "remaining_time": "4:58:57", "throughput": 1486.68, "total_tokens": 11694144} {"current_steps": 55425, "total_steps": 181800, "loss": 0.042, "lr": 4.387561026209732e-05, "epoch": 6.097359735973598, "percentage": 30.49, "elapsed_time": "2:11:06", "remaining_time": "4:58:56", "throughput": 1486.69, "total_tokens": 11695232} {"current_steps": 55430, "total_steps": 181800, "loss": 0.0714, "lr": 4.387403645866858e-05, "epoch": 6.097909790979098, "percentage": 30.49, "elapsed_time": "2:11:07", "remaining_time": "4:58:55", "throughput": 1486.7, "total_tokens": 11696320} {"current_steps": 55435, "total_steps": 181800, "loss": 0.101, "lr": 4.38724624812869e-05, "epoch": 6.098459845984599, "percentage": 30.49, "elapsed_time": "2:11:08", "remaining_time": "4:58:55", "throughput": 1486.7, "total_tokens": 11697376} {"current_steps": 55440, "total_steps": 181800, "loss": 0.0295, "lr": 4.387088832996679e-05, "epoch": 6.099009900990099, "percentage": 30.5, "elapsed_time": "2:11:08", "remaining_time": "4:58:54", "throughput": 1486.71, "total_tokens": 11698432} {"current_steps": 55445, "total_steps": 181800, "loss": 0.0718, "lr": 4.386931400472275e-05, "epoch": 6.099559955995599, "percentage": 30.5, "elapsed_time": "2:11:09", "remaining_time": "4:58:53", "throughput": 1486.71, "total_tokens": 11699520} {"current_steps": 55450, "total_steps": 181800, "loss": 0.1517, "lr": 4.386773950556931e-05, "epoch": 6.1001100110011, "percentage": 30.5, "elapsed_time": "2:11:10", "remaining_time": "4:58:52", "throughput": 1486.71, "total_tokens": 11700544} {"current_steps": 55455, "total_steps": 181800, "loss": 0.0157, "lr": 4.3866164832520954e-05, "epoch": 6.100660066006601, "percentage": 30.5, "elapsed_time": "2:11:10", "remaining_time": "4:58:52", "throughput": 1486.72, "total_tokens": 11701600} {"current_steps": 55460, "total_steps": 181800, "loss": 0.0414, "lr": 4.386458998559222e-05, "epoch": 6.101210121012101, "percentage": 30.51, "elapsed_time": "2:11:11", "remaining_time": "4:58:51", "throughput": 1486.73, "total_tokens": 11702688} {"current_steps": 55465, "total_steps": 181800, "loss": 0.0383, "lr": 4.3863014964797607e-05, "epoch": 6.101760176017602, "percentage": 30.51, "elapsed_time": "2:11:12", "remaining_time": "4:58:50", "throughput": 1486.72, "total_tokens": 11703680} {"current_steps": 55470, "total_steps": 181800, "loss": 0.0034, "lr": 4.3861439770151636e-05, "epoch": 6.102310231023102, "percentage": 30.51, "elapsed_time": "2:11:12", "remaining_time": "4:58:49", "throughput": 1486.72, "total_tokens": 11704640} {"current_steps": 55475, "total_steps": 181800, "loss": 0.0351, "lr": 4.385986440166883e-05, "epoch": 6.102860286028603, "percentage": 30.51, "elapsed_time": "2:11:13", "remaining_time": "4:58:49", "throughput": 1486.72, "total_tokens": 11705696} {"current_steps": 55480, "total_steps": 181800, "loss": 0.0404, "lr": 4.3858288859363694e-05, "epoch": 6.103410341034103, "percentage": 30.52, "elapsed_time": "2:11:14", "remaining_time": "4:58:48", "throughput": 1486.73, "total_tokens": 11706784} {"current_steps": 55485, "total_steps": 181800, "loss": 0.0599, "lr": 4.385671314325077e-05, "epoch": 6.103960396039604, "percentage": 30.52, "elapsed_time": "2:11:14", "remaining_time": "4:58:47", "throughput": 1486.73, "total_tokens": 11707808} {"current_steps": 55490, "total_steps": 181800, "loss": 0.0126, "lr": 4.385513725334457e-05, "epoch": 6.104510451045105, "percentage": 30.52, "elapsed_time": "2:11:15", "remaining_time": "4:58:46", "throughput": 1486.73, "total_tokens": 11708864} {"current_steps": 55495, "total_steps": 181800, "loss": 0.0468, "lr": 4.385356118965961e-05, "epoch": 6.105060506050605, "percentage": 30.53, "elapsed_time": "2:11:16", "remaining_time": "4:58:46", "throughput": 1486.74, "total_tokens": 11709952} {"current_steps": 55500, "total_steps": 181800, "loss": 0.0284, "lr": 4.385198495221042e-05, "epoch": 6.105610561056106, "percentage": 30.53, "elapsed_time": "2:11:16", "remaining_time": "4:58:45", "throughput": 1486.74, "total_tokens": 11710976} {"current_steps": 55505, "total_steps": 181800, "loss": 0.1103, "lr": 4.385040854101154e-05, "epoch": 6.106160616061606, "percentage": 30.53, "elapsed_time": "2:11:17", "remaining_time": "4:58:44", "throughput": 1486.74, "total_tokens": 11712000} {"current_steps": 55510, "total_steps": 181800, "loss": 0.0089, "lr": 4.3848831956077486e-05, "epoch": 6.106710671067106, "percentage": 30.53, "elapsed_time": "2:11:18", "remaining_time": "4:58:43", "throughput": 1486.75, "total_tokens": 11713088} {"current_steps": 55515, "total_steps": 181800, "loss": 0.0304, "lr": 4.3847255197422793e-05, "epoch": 6.1072607260726075, "percentage": 30.54, "elapsed_time": "2:11:19", "remaining_time": "4:58:43", "throughput": 1486.75, "total_tokens": 11714144} {"current_steps": 55520, "total_steps": 181800, "loss": 0.0893, "lr": 4.3845678265062e-05, "epoch": 6.107810781078108, "percentage": 30.54, "elapsed_time": "2:11:19", "remaining_time": "4:58:42", "throughput": 1486.76, "total_tokens": 11715232} {"current_steps": 55525, "total_steps": 181800, "loss": 0.0286, "lr": 4.384410115900962e-05, "epoch": 6.108360836083609, "percentage": 30.54, "elapsed_time": "2:11:20", "remaining_time": "4:58:41", "throughput": 1486.76, "total_tokens": 11716288} {"current_steps": 55530, "total_steps": 181800, "loss": 0.0559, "lr": 4.3842523879280205e-05, "epoch": 6.108910891089109, "percentage": 30.54, "elapsed_time": "2:11:21", "remaining_time": "4:58:40", "throughput": 1486.78, "total_tokens": 11717408} {"current_steps": 55535, "total_steps": 181800, "loss": 0.0739, "lr": 4.3840946425888296e-05, "epoch": 6.109460946094609, "percentage": 30.55, "elapsed_time": "2:11:21", "remaining_time": "4:58:40", "throughput": 1486.77, "total_tokens": 11718400} {"current_steps": 55540, "total_steps": 181800, "loss": 0.0132, "lr": 4.383936879884842e-05, "epoch": 6.11001100110011, "percentage": 30.55, "elapsed_time": "2:11:22", "remaining_time": "4:58:39", "throughput": 1486.77, "total_tokens": 11719392} {"current_steps": 55545, "total_steps": 181800, "loss": 0.0207, "lr": 4.383779099817512e-05, "epoch": 6.1105610561056105, "percentage": 30.55, "elapsed_time": "2:11:23", "remaining_time": "4:58:38", "throughput": 1486.77, "total_tokens": 11720448} {"current_steps": 55550, "total_steps": 181800, "loss": 0.0328, "lr": 4.383621302388294e-05, "epoch": 6.111111111111111, "percentage": 30.56, "elapsed_time": "2:11:23", "remaining_time": "4:58:37", "throughput": 1486.77, "total_tokens": 11721504} {"current_steps": 55555, "total_steps": 181800, "loss": 0.0053, "lr": 4.3834634875986426e-05, "epoch": 6.111661166116612, "percentage": 30.56, "elapsed_time": "2:11:24", "remaining_time": "4:58:37", "throughput": 1486.78, "total_tokens": 11722592} {"current_steps": 55560, "total_steps": 181800, "loss": 0.1782, "lr": 4.3833056554500116e-05, "epoch": 6.112211221122112, "percentage": 30.56, "elapsed_time": "2:11:25", "remaining_time": "4:58:36", "throughput": 1486.78, "total_tokens": 11723616} {"current_steps": 55565, "total_steps": 181800, "loss": 0.0483, "lr": 4.383147805943857e-05, "epoch": 6.112761276127613, "percentage": 30.56, "elapsed_time": "2:11:25", "remaining_time": "4:58:35", "throughput": 1486.8, "total_tokens": 11724768} {"current_steps": 55570, "total_steps": 181800, "loss": 0.0681, "lr": 4.382989939081632e-05, "epoch": 6.113311331133113, "percentage": 30.57, "elapsed_time": "2:11:26", "remaining_time": "4:58:34", "throughput": 1486.81, "total_tokens": 11725888} {"current_steps": 55575, "total_steps": 181800, "loss": 0.0236, "lr": 4.382832054864792e-05, "epoch": 6.1138613861386135, "percentage": 30.57, "elapsed_time": "2:11:27", "remaining_time": "4:58:34", "throughput": 1486.82, "total_tokens": 11726976} {"current_steps": 55580, "total_steps": 181800, "loss": 0.1202, "lr": 4.382674153294793e-05, "epoch": 6.114411441144115, "percentage": 30.57, "elapsed_time": "2:11:27", "remaining_time": "4:58:33", "throughput": 1486.82, "total_tokens": 11728032} {"current_steps": 55585, "total_steps": 181800, "loss": 0.0791, "lr": 4.3825162343730894e-05, "epoch": 6.114961496149615, "percentage": 30.57, "elapsed_time": "2:11:28", "remaining_time": "4:58:32", "throughput": 1486.84, "total_tokens": 11729152} {"current_steps": 55590, "total_steps": 181800, "loss": 0.0515, "lr": 4.382358298101137e-05, "epoch": 6.115511551155116, "percentage": 30.58, "elapsed_time": "2:11:29", "remaining_time": "4:58:31", "throughput": 1486.84, "total_tokens": 11730240} {"current_steps": 55595, "total_steps": 181800, "loss": 0.0463, "lr": 4.382200344480392e-05, "epoch": 6.116061606160616, "percentage": 30.58, "elapsed_time": "2:11:30", "remaining_time": "4:58:31", "throughput": 1486.84, "total_tokens": 11731232} {"current_steps": 55600, "total_steps": 181800, "loss": 0.1218, "lr": 4.3820423735123084e-05, "epoch": 6.116611661166116, "percentage": 30.58, "elapsed_time": "2:11:30", "remaining_time": "4:58:30", "throughput": 1486.84, "total_tokens": 11732256} {"current_steps": 55605, "total_steps": 181800, "loss": 0.0576, "lr": 4.381884385198344e-05, "epoch": 6.117161716171617, "percentage": 30.59, "elapsed_time": "2:11:31", "remaining_time": "4:58:29", "throughput": 1486.85, "total_tokens": 11733376} {"current_steps": 55610, "total_steps": 181800, "loss": 0.0141, "lr": 4.3817263795399544e-05, "epoch": 6.117711771177118, "percentage": 30.59, "elapsed_time": "2:11:32", "remaining_time": "4:58:28", "throughput": 1486.85, "total_tokens": 11734400} {"current_steps": 55615, "total_steps": 181800, "loss": 0.1207, "lr": 4.3815683565385956e-05, "epoch": 6.118261826182618, "percentage": 30.59, "elapsed_time": "2:11:32", "remaining_time": "4:58:27", "throughput": 1486.86, "total_tokens": 11735456} {"current_steps": 55620, "total_steps": 181800, "loss": 0.0164, "lr": 4.3814103161957246e-05, "epoch": 6.118811881188119, "percentage": 30.59, "elapsed_time": "2:11:33", "remaining_time": "4:58:27", "throughput": 1486.86, "total_tokens": 11736512} {"current_steps": 55625, "total_steps": 181800, "loss": 0.0135, "lr": 4.381252258512797e-05, "epoch": 6.119361936193619, "percentage": 30.6, "elapsed_time": "2:11:34", "remaining_time": "4:58:26", "throughput": 1486.86, "total_tokens": 11737568} {"current_steps": 55630, "total_steps": 181800, "loss": 0.0237, "lr": 4.3810941834912695e-05, "epoch": 6.11991199119912, "percentage": 30.6, "elapsed_time": "2:11:34", "remaining_time": "4:58:25", "throughput": 1486.87, "total_tokens": 11738656} {"current_steps": 55635, "total_steps": 181800, "loss": 0.1347, "lr": 4.3809360911326006e-05, "epoch": 6.12046204620462, "percentage": 30.6, "elapsed_time": "2:11:35", "remaining_time": "4:58:24", "throughput": 1486.87, "total_tokens": 11739648} {"current_steps": 55640, "total_steps": 181800, "loss": 0.0625, "lr": 4.3807779814382456e-05, "epoch": 6.121012101210121, "percentage": 30.61, "elapsed_time": "2:11:36", "remaining_time": "4:58:24", "throughput": 1486.87, "total_tokens": 11740704} {"current_steps": 55645, "total_steps": 181800, "loss": 0.0201, "lr": 4.380619854409662e-05, "epoch": 6.121562156215622, "percentage": 30.61, "elapsed_time": "2:11:36", "remaining_time": "4:58:23", "throughput": 1486.87, "total_tokens": 11741728} {"current_steps": 55650, "total_steps": 181800, "loss": 0.0269, "lr": 4.380461710048309e-05, "epoch": 6.122112211221122, "percentage": 30.61, "elapsed_time": "2:11:37", "remaining_time": "4:58:22", "throughput": 1486.88, "total_tokens": 11742784} {"current_steps": 55655, "total_steps": 181800, "loss": 0.0723, "lr": 4.3803035483556415e-05, "epoch": 6.122662266226623, "percentage": 30.61, "elapsed_time": "2:11:38", "remaining_time": "4:58:21", "throughput": 1486.88, "total_tokens": 11743840} {"current_steps": 55660, "total_steps": 181800, "loss": 0.0446, "lr": 4.3801453693331184e-05, "epoch": 6.123212321232123, "percentage": 30.62, "elapsed_time": "2:11:38", "remaining_time": "4:58:21", "throughput": 1486.88, "total_tokens": 11744896} {"current_steps": 55665, "total_steps": 181800, "loss": 0.0139, "lr": 4.3799871729821986e-05, "epoch": 6.123762376237623, "percentage": 30.62, "elapsed_time": "2:11:39", "remaining_time": "4:58:20", "throughput": 1486.89, "total_tokens": 11745984} {"current_steps": 55670, "total_steps": 181800, "loss": 0.1025, "lr": 4.379828959304338e-05, "epoch": 6.1243124312431245, "percentage": 30.62, "elapsed_time": "2:11:40", "remaining_time": "4:58:19", "throughput": 1486.9, "total_tokens": 11747072} {"current_steps": 55675, "total_steps": 181800, "loss": 0.019, "lr": 4.379670728300998e-05, "epoch": 6.124862486248625, "percentage": 30.62, "elapsed_time": "2:11:41", "remaining_time": "4:58:18", "throughput": 1486.9, "total_tokens": 11748096} {"current_steps": 55680, "total_steps": 181800, "loss": 0.0081, "lr": 4.3795124799736324e-05, "epoch": 6.125412541254126, "percentage": 30.63, "elapsed_time": "2:11:41", "remaining_time": "4:58:18", "throughput": 1486.91, "total_tokens": 11749184} {"current_steps": 55685, "total_steps": 181800, "loss": 0.0548, "lr": 4.3793542143237034e-05, "epoch": 6.125962596259626, "percentage": 30.63, "elapsed_time": "2:11:42", "remaining_time": "4:58:17", "throughput": 1486.92, "total_tokens": 11750272} {"current_steps": 55690, "total_steps": 181800, "loss": 0.0217, "lr": 4.379195931352668e-05, "epoch": 6.126512651265126, "percentage": 30.63, "elapsed_time": "2:11:43", "remaining_time": "4:58:16", "throughput": 1486.92, "total_tokens": 11751296} {"current_steps": 55695, "total_steps": 181800, "loss": 0.0563, "lr": 4.379037631061986e-05, "epoch": 6.127062706270627, "percentage": 30.64, "elapsed_time": "2:11:43", "remaining_time": "4:58:15", "throughput": 1486.92, "total_tokens": 11752384} {"current_steps": 55700, "total_steps": 181800, "loss": 0.0767, "lr": 4.378879313453115e-05, "epoch": 6.1276127612761275, "percentage": 30.64, "elapsed_time": "2:11:44", "remaining_time": "4:58:15", "throughput": 1486.92, "total_tokens": 11753376} {"current_steps": 55705, "total_steps": 181800, "loss": 0.066, "lr": 4.378720978527515e-05, "epoch": 6.128162816281628, "percentage": 30.64, "elapsed_time": "2:11:45", "remaining_time": "4:58:14", "throughput": 1486.92, "total_tokens": 11754400} {"current_steps": 55710, "total_steps": 181800, "loss": 0.0381, "lr": 4.3785626262866464e-05, "epoch": 6.128712871287129, "percentage": 30.64, "elapsed_time": "2:11:45", "remaining_time": "4:58:13", "throughput": 1486.93, "total_tokens": 11755488} {"current_steps": 55715, "total_steps": 181800, "loss": 0.0414, "lr": 4.3784042567319664e-05, "epoch": 6.129262926292629, "percentage": 30.65, "elapsed_time": "2:11:46", "remaining_time": "4:58:12", "throughput": 1486.93, "total_tokens": 11756544} {"current_steps": 55720, "total_steps": 181800, "loss": 0.098, "lr": 4.3782458698649365e-05, "epoch": 6.12981298129813, "percentage": 30.65, "elapsed_time": "2:11:47", "remaining_time": "4:58:12", "throughput": 1486.94, "total_tokens": 11757632} {"current_steps": 55725, "total_steps": 181800, "loss": 0.1344, "lr": 4.378087465687015e-05, "epoch": 6.13036303630363, "percentage": 30.65, "elapsed_time": "2:11:47", "remaining_time": "4:58:11", "throughput": 1486.94, "total_tokens": 11758624} {"current_steps": 55730, "total_steps": 181800, "loss": 0.0112, "lr": 4.377929044199662e-05, "epoch": 6.1309130913091305, "percentage": 30.65, "elapsed_time": "2:11:48", "remaining_time": "4:58:10", "throughput": 1486.94, "total_tokens": 11759680} {"current_steps": 55735, "total_steps": 181800, "loss": 0.0227, "lr": 4.3777706054043395e-05, "epoch": 6.131463146314632, "percentage": 30.66, "elapsed_time": "2:11:49", "remaining_time": "4:58:09", "throughput": 1486.94, "total_tokens": 11760704} {"current_steps": 55740, "total_steps": 181800, "loss": 0.0419, "lr": 4.3776121493025054e-05, "epoch": 6.132013201320132, "percentage": 30.66, "elapsed_time": "2:11:50", "remaining_time": "4:58:09", "throughput": 1486.94, "total_tokens": 11761760} {"current_steps": 55745, "total_steps": 181800, "loss": 0.0152, "lr": 4.377453675895622e-05, "epoch": 6.132563256325633, "percentage": 30.66, "elapsed_time": "2:11:50", "remaining_time": "4:58:08", "throughput": 1486.95, "total_tokens": 11762880} {"current_steps": 55750, "total_steps": 181800, "loss": 0.0175, "lr": 4.3772951851851476e-05, "epoch": 6.133113311331133, "percentage": 30.67, "elapsed_time": "2:11:51", "remaining_time": "4:58:07", "throughput": 1486.96, "total_tokens": 11763968} {"current_steps": 55755, "total_steps": 181800, "loss": 0.1111, "lr": 4.377136677172545e-05, "epoch": 6.133663366336633, "percentage": 30.67, "elapsed_time": "2:11:52", "remaining_time": "4:58:06", "throughput": 1486.97, "total_tokens": 11765056} {"current_steps": 55760, "total_steps": 181800, "loss": 0.0175, "lr": 4.376978151859275e-05, "epoch": 6.134213421342134, "percentage": 30.67, "elapsed_time": "2:11:52", "remaining_time": "4:58:06", "throughput": 1486.98, "total_tokens": 11766144} {"current_steps": 55765, "total_steps": 181800, "loss": 0.0721, "lr": 4.376819609246797e-05, "epoch": 6.134763476347635, "percentage": 30.67, "elapsed_time": "2:11:53", "remaining_time": "4:58:05", "throughput": 1486.98, "total_tokens": 11767168} {"current_steps": 55770, "total_steps": 181800, "loss": 0.0885, "lr": 4.3766610493365734e-05, "epoch": 6.135313531353136, "percentage": 30.68, "elapsed_time": "2:11:54", "remaining_time": "4:58:04", "throughput": 1486.98, "total_tokens": 11768224} {"current_steps": 55775, "total_steps": 181800, "loss": 0.0182, "lr": 4.376502472130066e-05, "epoch": 6.135863586358636, "percentage": 30.68, "elapsed_time": "2:11:54", "remaining_time": "4:58:03", "throughput": 1486.98, "total_tokens": 11769216} {"current_steps": 55780, "total_steps": 181800, "loss": 0.0424, "lr": 4.376343877628736e-05, "epoch": 6.136413641364136, "percentage": 30.68, "elapsed_time": "2:11:55", "remaining_time": "4:58:03", "throughput": 1486.98, "total_tokens": 11770272} {"current_steps": 55785, "total_steps": 181800, "loss": 0.0289, "lr": 4.376185265834044e-05, "epoch": 6.136963696369637, "percentage": 30.68, "elapsed_time": "2:11:56", "remaining_time": "4:58:02", "throughput": 1486.98, "total_tokens": 11771264} {"current_steps": 55790, "total_steps": 181800, "loss": 0.1132, "lr": 4.3760266367474526e-05, "epoch": 6.137513751375137, "percentage": 30.69, "elapsed_time": "2:11:56", "remaining_time": "4:58:01", "throughput": 1486.98, "total_tokens": 11772320} {"current_steps": 55795, "total_steps": 181800, "loss": 0.0785, "lr": 4.375867990370425e-05, "epoch": 6.138063806380638, "percentage": 30.69, "elapsed_time": "2:11:57", "remaining_time": "4:58:00", "throughput": 1486.99, "total_tokens": 11773440} {"current_steps": 55800, "total_steps": 181800, "loss": 0.0369, "lr": 4.3757093267044215e-05, "epoch": 6.138613861386139, "percentage": 30.69, "elapsed_time": "2:11:58", "remaining_time": "4:58:00", "throughput": 1487.0, "total_tokens": 11774528} {"current_steps": 55805, "total_steps": 181800, "loss": 0.1824, "lr": 4.375550645750905e-05, "epoch": 6.139163916391639, "percentage": 30.7, "elapsed_time": "2:11:59", "remaining_time": "4:57:59", "throughput": 1487.01, "total_tokens": 11775616} {"current_steps": 55810, "total_steps": 181800, "loss": 0.0914, "lr": 4.3753919475113384e-05, "epoch": 6.13971397139714, "percentage": 30.7, "elapsed_time": "2:11:59", "remaining_time": "4:57:58", "throughput": 1487.0, "total_tokens": 11776608} {"current_steps": 55815, "total_steps": 181800, "loss": 0.0073, "lr": 4.375233231987184e-05, "epoch": 6.14026402640264, "percentage": 30.7, "elapsed_time": "2:12:00", "remaining_time": "4:57:57", "throughput": 1487.01, "total_tokens": 11777664} {"current_steps": 55820, "total_steps": 181800, "loss": 0.0924, "lr": 4.3750744991799045e-05, "epoch": 6.1408140814081404, "percentage": 30.7, "elapsed_time": "2:12:01", "remaining_time": "4:57:57", "throughput": 1487.02, "total_tokens": 11778784} {"current_steps": 55825, "total_steps": 181800, "loss": 0.0202, "lr": 4.3749157490909634e-05, "epoch": 6.1413641364136415, "percentage": 30.71, "elapsed_time": "2:12:01", "remaining_time": "4:57:56", "throughput": 1487.01, "total_tokens": 11779776} {"current_steps": 55830, "total_steps": 181800, "loss": 0.0133, "lr": 4.374756981721824e-05, "epoch": 6.141914191419142, "percentage": 30.71, "elapsed_time": "2:12:02", "remaining_time": "4:57:55", "throughput": 1487.01, "total_tokens": 11780800} {"current_steps": 55835, "total_steps": 181800, "loss": 0.0431, "lr": 4.3745981970739486e-05, "epoch": 6.142464246424643, "percentage": 30.71, "elapsed_time": "2:12:03", "remaining_time": "4:57:54", "throughput": 1487.01, "total_tokens": 11781824} {"current_steps": 55840, "total_steps": 181800, "loss": 0.0769, "lr": 4.3744393951488015e-05, "epoch": 6.143014301430143, "percentage": 30.72, "elapsed_time": "2:12:03", "remaining_time": "4:57:54", "throughput": 1487.02, "total_tokens": 11782880} {"current_steps": 55845, "total_steps": 181800, "loss": 0.0314, "lr": 4.3742805759478456e-05, "epoch": 6.143564356435643, "percentage": 30.72, "elapsed_time": "2:12:04", "remaining_time": "4:57:53", "throughput": 1487.03, "total_tokens": 11784000} {"current_steps": 55850, "total_steps": 181800, "loss": 0.0131, "lr": 4.3741217394725445e-05, "epoch": 6.144114411441144, "percentage": 30.72, "elapsed_time": "2:12:05", "remaining_time": "4:57:52", "throughput": 1487.03, "total_tokens": 11785056} {"current_steps": 55855, "total_steps": 181800, "loss": 0.0407, "lr": 4.373962885724364e-05, "epoch": 6.1446644664466445, "percentage": 30.72, "elapsed_time": "2:12:05", "remaining_time": "4:57:51", "throughput": 1487.03, "total_tokens": 11786080} {"current_steps": 55860, "total_steps": 181800, "loss": 0.1464, "lr": 4.3738040147047654e-05, "epoch": 6.145214521452146, "percentage": 30.73, "elapsed_time": "2:12:06", "remaining_time": "4:57:51", "throughput": 1487.03, "total_tokens": 11787104} {"current_steps": 55865, "total_steps": 181800, "loss": 0.0165, "lr": 4.373645126415215e-05, "epoch": 6.145764576457646, "percentage": 30.73, "elapsed_time": "2:12:07", "remaining_time": "4:57:50", "throughput": 1487.02, "total_tokens": 11788096} {"current_steps": 55870, "total_steps": 181800, "loss": 0.0537, "lr": 4.373486220857176e-05, "epoch": 6.146314631463146, "percentage": 30.73, "elapsed_time": "2:12:07", "remaining_time": "4:57:49", "throughput": 1487.02, "total_tokens": 11789120} {"current_steps": 55875, "total_steps": 181800, "loss": 0.0526, "lr": 4.3733272980321144e-05, "epoch": 6.146864686468647, "percentage": 30.73, "elapsed_time": "2:12:08", "remaining_time": "4:57:48", "throughput": 1487.03, "total_tokens": 11790240} {"current_steps": 55880, "total_steps": 181800, "loss": 0.0353, "lr": 4.3731683579414934e-05, "epoch": 6.147414741474147, "percentage": 30.74, "elapsed_time": "2:12:09", "remaining_time": "4:57:48", "throughput": 1487.04, "total_tokens": 11791328} {"current_steps": 55885, "total_steps": 181800, "loss": 0.051, "lr": 4.3730094005867784e-05, "epoch": 6.1479647964796476, "percentage": 30.74, "elapsed_time": "2:12:10", "remaining_time": "4:57:47", "throughput": 1487.04, "total_tokens": 11792320} {"current_steps": 55890, "total_steps": 181800, "loss": 0.0336, "lr": 4.372850425969435e-05, "epoch": 6.148514851485149, "percentage": 30.74, "elapsed_time": "2:12:10", "remaining_time": "4:57:46", "throughput": 1487.04, "total_tokens": 11793376} {"current_steps": 55895, "total_steps": 181800, "loss": 0.1868, "lr": 4.3726914340909275e-05, "epoch": 6.149064906490649, "percentage": 30.75, "elapsed_time": "2:12:11", "remaining_time": "4:57:45", "throughput": 1487.04, "total_tokens": 11794400} {"current_steps": 55900, "total_steps": 181800, "loss": 0.0703, "lr": 4.372532424952722e-05, "epoch": 6.14961496149615, "percentage": 30.75, "elapsed_time": "2:12:12", "remaining_time": "4:57:45", "throughput": 1487.05, "total_tokens": 11795488} {"current_steps": 55905, "total_steps": 181800, "loss": 0.1169, "lr": 4.3723733985562834e-05, "epoch": 6.15016501650165, "percentage": 30.75, "elapsed_time": "2:12:12", "remaining_time": "4:57:44", "throughput": 1487.06, "total_tokens": 11796576} {"current_steps": 55910, "total_steps": 181800, "loss": 0.0995, "lr": 4.3722143549030775e-05, "epoch": 6.15071507150715, "percentage": 30.75, "elapsed_time": "2:12:13", "remaining_time": "4:57:43", "throughput": 1487.06, "total_tokens": 11797632} {"current_steps": 55915, "total_steps": 181800, "loss": 0.0268, "lr": 4.3720552939945704e-05, "epoch": 6.1512651265126514, "percentage": 30.76, "elapsed_time": "2:12:14", "remaining_time": "4:57:42", "throughput": 1487.06, "total_tokens": 11798688} {"current_steps": 55920, "total_steps": 181800, "loss": 0.0228, "lr": 4.371896215832228e-05, "epoch": 6.151815181518152, "percentage": 30.76, "elapsed_time": "2:12:14", "remaining_time": "4:57:42", "throughput": 1487.08, "total_tokens": 11799808} {"current_steps": 55925, "total_steps": 181800, "loss": 0.1788, "lr": 4.371737120417516e-05, "epoch": 6.152365236523653, "percentage": 30.76, "elapsed_time": "2:12:15", "remaining_time": "4:57:41", "throughput": 1487.08, "total_tokens": 11800896} {"current_steps": 55930, "total_steps": 181800, "loss": 0.0246, "lr": 4.3715780077519016e-05, "epoch": 6.152915291529153, "percentage": 30.76, "elapsed_time": "2:12:16", "remaining_time": "4:57:40", "throughput": 1487.08, "total_tokens": 11801920} {"current_steps": 55935, "total_steps": 181800, "loss": 0.0351, "lr": 4.37141887783685e-05, "epoch": 6.153465346534653, "percentage": 30.77, "elapsed_time": "2:12:16", "remaining_time": "4:57:39", "throughput": 1487.08, "total_tokens": 11802944} {"current_steps": 55940, "total_steps": 181800, "loss": 0.0206, "lr": 4.37125973067383e-05, "epoch": 6.154015401540154, "percentage": 30.77, "elapsed_time": "2:12:17", "remaining_time": "4:57:39", "throughput": 1487.09, "total_tokens": 11804032} {"current_steps": 55945, "total_steps": 181800, "loss": 0.0518, "lr": 4.371100566264306e-05, "epoch": 6.1545654565456545, "percentage": 30.77, "elapsed_time": "2:12:18", "remaining_time": "4:57:38", "throughput": 1487.09, "total_tokens": 11805056} {"current_steps": 55950, "total_steps": 181800, "loss": 0.1262, "lr": 4.3709413846097465e-05, "epoch": 6.1551155115511555, "percentage": 30.78, "elapsed_time": "2:12:19", "remaining_time": "4:57:37", "throughput": 1487.1, "total_tokens": 11806176} {"current_steps": 55955, "total_steps": 181800, "loss": 0.0295, "lr": 4.3707821857116176e-05, "epoch": 6.155665566556656, "percentage": 30.78, "elapsed_time": "2:12:19", "remaining_time": "4:57:36", "throughput": 1487.11, "total_tokens": 11807232} {"current_steps": 55960, "total_steps": 181800, "loss": 0.0459, "lr": 4.370622969571388e-05, "epoch": 6.156215621562156, "percentage": 30.78, "elapsed_time": "2:12:20", "remaining_time": "4:57:36", "throughput": 1487.11, "total_tokens": 11808288} {"current_steps": 55965, "total_steps": 181800, "loss": 0.0166, "lr": 4.370463736190522e-05, "epoch": 6.156765676567657, "percentage": 30.78, "elapsed_time": "2:12:21", "remaining_time": "4:57:35", "throughput": 1487.11, "total_tokens": 11809312} {"current_steps": 55970, "total_steps": 181800, "loss": 0.0526, "lr": 4.370304485570491e-05, "epoch": 6.157315731573157, "percentage": 30.79, "elapsed_time": "2:12:21", "remaining_time": "4:57:34", "throughput": 1487.12, "total_tokens": 11810400} {"current_steps": 55975, "total_steps": 181800, "loss": 0.0079, "lr": 4.37014521771276e-05, "epoch": 6.1578657865786575, "percentage": 30.79, "elapsed_time": "2:12:22", "remaining_time": "4:57:33", "throughput": 1487.13, "total_tokens": 11811488} {"current_steps": 55980, "total_steps": 181800, "loss": 0.037, "lr": 4.369985932618799e-05, "epoch": 6.158415841584159, "percentage": 30.79, "elapsed_time": "2:12:23", "remaining_time": "4:57:32", "throughput": 1487.12, "total_tokens": 11812480} {"current_steps": 55985, "total_steps": 181800, "loss": 0.0231, "lr": 4.369826630290074e-05, "epoch": 6.158965896589659, "percentage": 30.79, "elapsed_time": "2:12:23", "remaining_time": "4:57:32", "throughput": 1487.13, "total_tokens": 11813536} {"current_steps": 55990, "total_steps": 181800, "loss": 0.0099, "lr": 4.369667310728054e-05, "epoch": 6.15951595159516, "percentage": 30.8, "elapsed_time": "2:12:24", "remaining_time": "4:57:31", "throughput": 1487.13, "total_tokens": 11814624} {"current_steps": 55995, "total_steps": 181800, "loss": 0.0091, "lr": 4.369507973934208e-05, "epoch": 6.16006600660066, "percentage": 30.8, "elapsed_time": "2:12:25", "remaining_time": "4:57:30", "throughput": 1487.14, "total_tokens": 11815680} {"current_steps": 56000, "total_steps": 181800, "loss": 0.0282, "lr": 4.369348619910005e-05, "epoch": 6.16061606160616, "percentage": 30.8, "elapsed_time": "2:12:25", "remaining_time": "4:57:29", "throughput": 1487.15, "total_tokens": 11816800} {"current_steps": 56005, "total_steps": 181800, "loss": 0.0973, "lr": 4.369189248656912e-05, "epoch": 6.161166116611661, "percentage": 30.81, "elapsed_time": "2:12:26", "remaining_time": "4:57:29", "throughput": 1487.15, "total_tokens": 11817856} {"current_steps": 56010, "total_steps": 181800, "loss": 0.1168, "lr": 4.369029860176398e-05, "epoch": 6.161716171617162, "percentage": 30.81, "elapsed_time": "2:12:27", "remaining_time": "4:57:28", "throughput": 1487.17, "total_tokens": 11818976} {"current_steps": 56015, "total_steps": 181800, "loss": 0.0482, "lr": 4.3688704544699334e-05, "epoch": 6.162266226622663, "percentage": 30.81, "elapsed_time": "2:12:28", "remaining_time": "4:57:27", "throughput": 1487.17, "total_tokens": 11820064} {"current_steps": 56020, "total_steps": 181800, "loss": 0.0128, "lr": 4.368711031538987e-05, "epoch": 6.162816281628163, "percentage": 30.81, "elapsed_time": "2:12:28", "remaining_time": "4:57:26", "throughput": 1487.18, "total_tokens": 11821152} {"current_steps": 56025, "total_steps": 181800, "loss": 0.0583, "lr": 4.368551591385026e-05, "epoch": 6.163366336633663, "percentage": 30.82, "elapsed_time": "2:12:29", "remaining_time": "4:57:26", "throughput": 1487.18, "total_tokens": 11822176} {"current_steps": 56030, "total_steps": 181800, "loss": 0.045, "lr": 4.368392134009523e-05, "epoch": 6.163916391639164, "percentage": 30.82, "elapsed_time": "2:12:30", "remaining_time": "4:57:25", "throughput": 1487.18, "total_tokens": 11823232} {"current_steps": 56035, "total_steps": 181800, "loss": 0.0343, "lr": 4.368232659413946e-05, "epoch": 6.164466446644664, "percentage": 30.82, "elapsed_time": "2:12:30", "remaining_time": "4:57:24", "throughput": 1487.19, "total_tokens": 11824288} {"current_steps": 56040, "total_steps": 181800, "loss": 0.0249, "lr": 4.368073167599765e-05, "epoch": 6.165016501650165, "percentage": 30.83, "elapsed_time": "2:12:31", "remaining_time": "4:57:23", "throughput": 1487.19, "total_tokens": 11825344} {"current_steps": 56045, "total_steps": 181800, "loss": 0.0716, "lr": 4.36791365856845e-05, "epoch": 6.165566556655666, "percentage": 30.83, "elapsed_time": "2:12:32", "remaining_time": "4:57:23", "throughput": 1487.2, "total_tokens": 11826432} {"current_steps": 56050, "total_steps": 181800, "loss": 0.0171, "lr": 4.367754132321471e-05, "epoch": 6.166116611661166, "percentage": 30.83, "elapsed_time": "2:12:32", "remaining_time": "4:57:22", "throughput": 1487.21, "total_tokens": 11827520} {"current_steps": 56055, "total_steps": 181800, "loss": 0.0077, "lr": 4.367594588860299e-05, "epoch": 6.166666666666667, "percentage": 30.83, "elapsed_time": "2:12:33", "remaining_time": "4:57:21", "throughput": 1487.22, "total_tokens": 11828640} {"current_steps": 56060, "total_steps": 181800, "loss": 0.0663, "lr": 4.367435028186403e-05, "epoch": 6.167216721672167, "percentage": 30.84, "elapsed_time": "2:12:34", "remaining_time": "4:57:20", "throughput": 1487.23, "total_tokens": 11829728} {"current_steps": 56065, "total_steps": 181800, "loss": 0.0336, "lr": 4.367275450301255e-05, "epoch": 6.167766776677667, "percentage": 30.84, "elapsed_time": "2:12:34", "remaining_time": "4:57:20", "throughput": 1487.24, "total_tokens": 11830848} {"current_steps": 56070, "total_steps": 181800, "loss": 0.0085, "lr": 4.3671158552063245e-05, "epoch": 6.1683168316831685, "percentage": 30.84, "elapsed_time": "2:12:35", "remaining_time": "4:57:19", "throughput": 1487.24, "total_tokens": 11831904} {"current_steps": 56075, "total_steps": 181800, "loss": 0.0211, "lr": 4.366956242903083e-05, "epoch": 6.168866886688669, "percentage": 30.84, "elapsed_time": "2:12:36", "remaining_time": "4:57:18", "throughput": 1487.24, "total_tokens": 11832928} {"current_steps": 56080, "total_steps": 181800, "loss": 0.0062, "lr": 4.366796613393003e-05, "epoch": 6.16941694169417, "percentage": 30.85, "elapsed_time": "2:12:36", "remaining_time": "4:57:17", "throughput": 1487.24, "total_tokens": 11833952} {"current_steps": 56085, "total_steps": 181800, "loss": 0.0371, "lr": 4.366636966677553e-05, "epoch": 6.16996699669967, "percentage": 30.85, "elapsed_time": "2:12:37", "remaining_time": "4:57:17", "throughput": 1487.24, "total_tokens": 11834976} {"current_steps": 56090, "total_steps": 181800, "loss": 0.0262, "lr": 4.3664773027582065e-05, "epoch": 6.17051705170517, "percentage": 30.85, "elapsed_time": "2:12:38", "remaining_time": "4:57:16", "throughput": 1487.25, "total_tokens": 11836032} {"current_steps": 56095, "total_steps": 181800, "loss": 0.0271, "lr": 4.366317621636434e-05, "epoch": 6.171067106710671, "percentage": 30.86, "elapsed_time": "2:12:39", "remaining_time": "4:57:15", "throughput": 1487.24, "total_tokens": 11837024} {"current_steps": 56100, "total_steps": 181800, "loss": 0.094, "lr": 4.366157923313708e-05, "epoch": 6.1716171617161715, "percentage": 30.86, "elapsed_time": "2:12:39", "remaining_time": "4:57:14", "throughput": 1487.25, "total_tokens": 11838080} {"current_steps": 56105, "total_steps": 181800, "loss": 0.0248, "lr": 4.365998207791499e-05, "epoch": 6.172167216721673, "percentage": 30.86, "elapsed_time": "2:12:40", "remaining_time": "4:57:14", "throughput": 1487.24, "total_tokens": 11839072} {"current_steps": 56110, "total_steps": 181800, "loss": 0.042, "lr": 4.365838475071281e-05, "epoch": 6.172717271727173, "percentage": 30.86, "elapsed_time": "2:12:41", "remaining_time": "4:57:13", "throughput": 1487.25, "total_tokens": 11840128} {"current_steps": 56115, "total_steps": 181800, "loss": 0.0273, "lr": 4.365678725154525e-05, "epoch": 6.173267326732673, "percentage": 30.87, "elapsed_time": "2:12:41", "remaining_time": "4:57:12", "throughput": 1487.26, "total_tokens": 11841216} {"current_steps": 56120, "total_steps": 181800, "loss": 0.0246, "lr": 4.365518958042703e-05, "epoch": 6.173817381738174, "percentage": 30.87, "elapsed_time": "2:12:42", "remaining_time": "4:57:11", "throughput": 1487.26, "total_tokens": 11842240} {"current_steps": 56125, "total_steps": 181800, "loss": 0.0175, "lr": 4.365359173737288e-05, "epoch": 6.174367436743674, "percentage": 30.87, "elapsed_time": "2:12:43", "remaining_time": "4:57:11", "throughput": 1487.26, "total_tokens": 11843296} {"current_steps": 56130, "total_steps": 181800, "loss": 0.0477, "lr": 4.365199372239752e-05, "epoch": 6.174917491749175, "percentage": 30.87, "elapsed_time": "2:12:43", "remaining_time": "4:57:10", "throughput": 1487.26, "total_tokens": 11844352} {"current_steps": 56135, "total_steps": 181800, "loss": 0.0193, "lr": 4.3650395535515694e-05, "epoch": 6.175467546754676, "percentage": 30.88, "elapsed_time": "2:12:44", "remaining_time": "4:57:09", "throughput": 1487.27, "total_tokens": 11845472} {"current_steps": 56140, "total_steps": 181800, "loss": 0.0126, "lr": 4.364879717674212e-05, "epoch": 6.176017601760176, "percentage": 30.88, "elapsed_time": "2:12:45", "remaining_time": "4:57:08", "throughput": 1487.28, "total_tokens": 11846560} {"current_steps": 56145, "total_steps": 181800, "loss": 0.0043, "lr": 4.3647198646091523e-05, "epoch": 6.176567656765677, "percentage": 30.88, "elapsed_time": "2:12:45", "remaining_time": "4:57:08", "throughput": 1487.28, "total_tokens": 11847552} {"current_steps": 56150, "total_steps": 181800, "loss": 0.0041, "lr": 4.3645599943578655e-05, "epoch": 6.177117711771177, "percentage": 30.89, "elapsed_time": "2:12:46", "remaining_time": "4:57:07", "throughput": 1487.28, "total_tokens": 11848608} {"current_steps": 56155, "total_steps": 181800, "loss": 0.0902, "lr": 4.3644001069218225e-05, "epoch": 6.177667766776677, "percentage": 30.89, "elapsed_time": "2:12:47", "remaining_time": "4:57:06", "throughput": 1487.28, "total_tokens": 11849664} {"current_steps": 56160, "total_steps": 181800, "loss": 0.0485, "lr": 4.3642402023025e-05, "epoch": 6.178217821782178, "percentage": 30.89, "elapsed_time": "2:12:48", "remaining_time": "4:57:05", "throughput": 1487.28, "total_tokens": 11850624} {"current_steps": 56165, "total_steps": 181800, "loss": 0.055, "lr": 4.3640802805013685e-05, "epoch": 6.178767876787679, "percentage": 30.89, "elapsed_time": "2:12:48", "remaining_time": "4:57:05", "throughput": 1487.28, "total_tokens": 11851648} {"current_steps": 56170, "total_steps": 181800, "loss": 0.0781, "lr": 4.3639203415199046e-05, "epoch": 6.17931793179318, "percentage": 30.9, "elapsed_time": "2:12:49", "remaining_time": "4:57:04", "throughput": 1487.28, "total_tokens": 11852704} {"current_steps": 56175, "total_steps": 181800, "loss": 0.0149, "lr": 4.363760385359581e-05, "epoch": 6.17986798679868, "percentage": 30.9, "elapsed_time": "2:12:50", "remaining_time": "4:57:03", "throughput": 1487.28, "total_tokens": 11853728} {"current_steps": 56180, "total_steps": 181800, "loss": 0.0091, "lr": 4.363600412021872e-05, "epoch": 6.18041804180418, "percentage": 30.9, "elapsed_time": "2:12:50", "remaining_time": "4:57:02", "throughput": 1487.29, "total_tokens": 11854816} {"current_steps": 56185, "total_steps": 181800, "loss": 0.0709, "lr": 4.3634404215082524e-05, "epoch": 6.180968096809681, "percentage": 30.9, "elapsed_time": "2:12:51", "remaining_time": "4:57:02", "throughput": 1487.29, "total_tokens": 11855872} {"current_steps": 56190, "total_steps": 181800, "loss": 0.0309, "lr": 4.363280413820197e-05, "epoch": 6.181518151815181, "percentage": 30.91, "elapsed_time": "2:12:52", "remaining_time": "4:57:01", "throughput": 1487.29, "total_tokens": 11856896} {"current_steps": 56195, "total_steps": 181800, "loss": 0.038, "lr": 4.36312038895918e-05, "epoch": 6.1820682068206825, "percentage": 30.91, "elapsed_time": "2:12:52", "remaining_time": "4:57:00", "throughput": 1487.3, "total_tokens": 11857984} {"current_steps": 56200, "total_steps": 181800, "loss": 0.1014, "lr": 4.362960346926676e-05, "epoch": 6.182618261826183, "percentage": 30.91, "elapsed_time": "2:12:53", "remaining_time": "4:56:59", "throughput": 1487.3, "total_tokens": 11859008} {"current_steps": 56205, "total_steps": 181800, "loss": 0.1293, "lr": 4.36280028772416e-05, "epoch": 6.183168316831683, "percentage": 30.92, "elapsed_time": "2:12:54", "remaining_time": "4:56:59", "throughput": 1487.3, "total_tokens": 11860064} {"current_steps": 56210, "total_steps": 181800, "loss": 0.0867, "lr": 4.362640211353109e-05, "epoch": 6.183718371837184, "percentage": 30.92, "elapsed_time": "2:12:54", "remaining_time": "4:56:58", "throughput": 1487.32, "total_tokens": 11861184} {"current_steps": 56215, "total_steps": 181800, "loss": 0.0242, "lr": 4.362480117814996e-05, "epoch": 6.184268426842684, "percentage": 30.92, "elapsed_time": "2:12:55", "remaining_time": "4:56:57", "throughput": 1487.32, "total_tokens": 11862240} {"current_steps": 56220, "total_steps": 181800, "loss": 0.0084, "lr": 4.362320007111298e-05, "epoch": 6.184818481848184, "percentage": 30.92, "elapsed_time": "2:12:56", "remaining_time": "4:56:56", "throughput": 1487.33, "total_tokens": 11863328} {"current_steps": 56225, "total_steps": 181800, "loss": 0.1728, "lr": 4.3621598792434895e-05, "epoch": 6.1853685368536855, "percentage": 30.93, "elapsed_time": "2:12:56", "remaining_time": "4:56:56", "throughput": 1487.32, "total_tokens": 11864320} {"current_steps": 56230, "total_steps": 181800, "loss": 0.0577, "lr": 4.361999734213047e-05, "epoch": 6.185918591859186, "percentage": 30.93, "elapsed_time": "2:12:57", "remaining_time": "4:56:55", "throughput": 1487.32, "total_tokens": 11865344} {"current_steps": 56235, "total_steps": 181800, "loss": 0.0048, "lr": 4.3618395720214465e-05, "epoch": 6.186468646864687, "percentage": 30.93, "elapsed_time": "2:12:58", "remaining_time": "4:56:54", "throughput": 1487.33, "total_tokens": 11866464} {"current_steps": 56240, "total_steps": 181800, "loss": 0.0104, "lr": 4.361679392670164e-05, "epoch": 6.187018701870187, "percentage": 30.94, "elapsed_time": "2:12:59", "remaining_time": "4:56:53", "throughput": 1487.34, "total_tokens": 11867520} {"current_steps": 56245, "total_steps": 181800, "loss": 0.0126, "lr": 4.361519196160677e-05, "epoch": 6.187568756875687, "percentage": 30.94, "elapsed_time": "2:12:59", "remaining_time": "4:56:53", "throughput": 1487.34, "total_tokens": 11868576} {"current_steps": 56250, "total_steps": 181800, "loss": 0.0565, "lr": 4.3613589824944586e-05, "epoch": 6.188118811881188, "percentage": 30.94, "elapsed_time": "2:13:00", "remaining_time": "4:56:52", "throughput": 1487.35, "total_tokens": 11869696} {"current_steps": 56255, "total_steps": 181800, "loss": 0.0558, "lr": 4.3611987516729894e-05, "epoch": 6.1886688668866885, "percentage": 30.94, "elapsed_time": "2:13:01", "remaining_time": "4:56:51", "throughput": 1487.35, "total_tokens": 11870720} {"current_steps": 56260, "total_steps": 181800, "loss": 0.0088, "lr": 4.3610385036977444e-05, "epoch": 6.18921892189219, "percentage": 30.95, "elapsed_time": "2:13:01", "remaining_time": "4:56:50", "throughput": 1487.35, "total_tokens": 11871744} {"current_steps": 56265, "total_steps": 181800, "loss": 0.0484, "lr": 4.3608782385701995e-05, "epoch": 6.18976897689769, "percentage": 30.95, "elapsed_time": "2:13:02", "remaining_time": "4:56:50", "throughput": 1487.36, "total_tokens": 11872800} {"current_steps": 56270, "total_steps": 181800, "loss": 0.0349, "lr": 4.360717956291833e-05, "epoch": 6.19031903190319, "percentage": 30.95, "elapsed_time": "2:13:03", "remaining_time": "4:56:49", "throughput": 1487.36, "total_tokens": 11873888} {"current_steps": 56275, "total_steps": 181800, "loss": 0.0435, "lr": 4.3605576568641226e-05, "epoch": 6.190869086908691, "percentage": 30.95, "elapsed_time": "2:13:03", "remaining_time": "4:56:48", "throughput": 1487.36, "total_tokens": 11874912} {"current_steps": 56280, "total_steps": 181800, "loss": 0.1169, "lr": 4.3603973402885445e-05, "epoch": 6.191419141914191, "percentage": 30.96, "elapsed_time": "2:13:04", "remaining_time": "4:56:47", "throughput": 1487.36, "total_tokens": 11875936} {"current_steps": 56285, "total_steps": 181800, "loss": 0.0756, "lr": 4.3602370065665774e-05, "epoch": 6.191969196919692, "percentage": 30.96, "elapsed_time": "2:13:05", "remaining_time": "4:56:47", "throughput": 1487.37, "total_tokens": 11876992} {"current_steps": 56290, "total_steps": 181800, "loss": 0.0089, "lr": 4.3600766556996985e-05, "epoch": 6.192519251925193, "percentage": 30.96, "elapsed_time": "2:13:05", "remaining_time": "4:56:46", "throughput": 1487.37, "total_tokens": 11878016} {"current_steps": 56295, "total_steps": 181800, "loss": 0.0215, "lr": 4.359916287689385e-05, "epoch": 6.193069306930693, "percentage": 30.97, "elapsed_time": "2:13:06", "remaining_time": "4:56:45", "throughput": 1487.36, "total_tokens": 11879008} {"current_steps": 56300, "total_steps": 181800, "loss": 0.0082, "lr": 4.3597559025371156e-05, "epoch": 6.193619361936194, "percentage": 30.97, "elapsed_time": "2:13:07", "remaining_time": "4:56:44", "throughput": 1487.37, "total_tokens": 11880064} {"current_steps": 56305, "total_steps": 181800, "loss": 0.0133, "lr": 4.359595500244369e-05, "epoch": 6.194169416941694, "percentage": 30.97, "elapsed_time": "2:13:08", "remaining_time": "4:56:44", "throughput": 1487.37, "total_tokens": 11881152} {"current_steps": 56310, "total_steps": 181800, "loss": 0.0347, "lr": 4.3594350808126224e-05, "epoch": 6.194719471947194, "percentage": 30.97, "elapsed_time": "2:13:08", "remaining_time": "4:56:43", "throughput": 1487.38, "total_tokens": 11882208} {"current_steps": 56315, "total_steps": 181800, "loss": 0.0695, "lr": 4.359274644243355e-05, "epoch": 6.195269526952695, "percentage": 30.98, "elapsed_time": "2:13:09", "remaining_time": "4:56:42", "throughput": 1487.38, "total_tokens": 11883264} {"current_steps": 56320, "total_steps": 181800, "loss": 0.052, "lr": 4.359114190538045e-05, "epoch": 6.195819581958196, "percentage": 30.98, "elapsed_time": "2:13:10", "remaining_time": "4:56:41", "throughput": 1487.39, "total_tokens": 11884320} {"current_steps": 56325, "total_steps": 181800, "loss": 0.0162, "lr": 4.358953719698172e-05, "epoch": 6.196369636963697, "percentage": 30.98, "elapsed_time": "2:13:10", "remaining_time": "4:56:40", "throughput": 1487.39, "total_tokens": 11885376} {"current_steps": 56330, "total_steps": 181800, "loss": 0.0877, "lr": 4.358793231725215e-05, "epoch": 6.196919691969197, "percentage": 30.98, "elapsed_time": "2:13:11", "remaining_time": "4:56:40", "throughput": 1487.4, "total_tokens": 11886464} {"current_steps": 56335, "total_steps": 181800, "loss": 0.0254, "lr": 4.358632726620653e-05, "epoch": 6.197469746974697, "percentage": 30.99, "elapsed_time": "2:13:12", "remaining_time": "4:56:39", "throughput": 1487.4, "total_tokens": 11887520} {"current_steps": 56340, "total_steps": 181800, "loss": 0.1423, "lr": 4.358472204385964e-05, "epoch": 6.198019801980198, "percentage": 30.99, "elapsed_time": "2:13:12", "remaining_time": "4:56:38", "throughput": 1487.41, "total_tokens": 11888608} {"current_steps": 56345, "total_steps": 181800, "loss": 0.0756, "lr": 4.358311665022629e-05, "epoch": 6.198569856985698, "percentage": 30.99, "elapsed_time": "2:13:13", "remaining_time": "4:56:37", "throughput": 1487.42, "total_tokens": 11889728} {"current_steps": 56350, "total_steps": 181800, "loss": 0.0094, "lr": 4.358151108532127e-05, "epoch": 6.1991199119911995, "percentage": 31.0, "elapsed_time": "2:13:14", "remaining_time": "4:56:37", "throughput": 1487.41, "total_tokens": 11890688} {"current_steps": 56355, "total_steps": 181800, "loss": 0.0419, "lr": 4.357990534915938e-05, "epoch": 6.1996699669967, "percentage": 31.0, "elapsed_time": "2:13:14", "remaining_time": "4:56:36", "throughput": 1487.41, "total_tokens": 11891712} {"current_steps": 56360, "total_steps": 181800, "loss": 0.1897, "lr": 4.357829944175541e-05, "epoch": 6.2002200220022, "percentage": 31.0, "elapsed_time": "2:13:15", "remaining_time": "4:56:35", "throughput": 1487.41, "total_tokens": 11892704} {"current_steps": 56365, "total_steps": 181800, "loss": 0.0403, "lr": 4.3576693363124176e-05, "epoch": 6.200770077007701, "percentage": 31.0, "elapsed_time": "2:13:16", "remaining_time": "4:56:34", "throughput": 1487.41, "total_tokens": 11893728} {"current_steps": 56370, "total_steps": 181800, "loss": 0.0375, "lr": 4.357508711328047e-05, "epoch": 6.201320132013201, "percentage": 31.01, "elapsed_time": "2:13:16", "remaining_time": "4:56:34", "throughput": 1487.41, "total_tokens": 11894752} {"current_steps": 56375, "total_steps": 181800, "loss": 0.0088, "lr": 4.3573480692239097e-05, "epoch": 6.201870187018702, "percentage": 31.01, "elapsed_time": "2:13:17", "remaining_time": "4:56:33", "throughput": 1487.41, "total_tokens": 11895808} {"current_steps": 56380, "total_steps": 181800, "loss": 0.0395, "lr": 4.3571874100014876e-05, "epoch": 6.2024202420242025, "percentage": 31.01, "elapsed_time": "2:13:18", "remaining_time": "4:56:32", "throughput": 1487.41, "total_tokens": 11896864} {"current_steps": 56385, "total_steps": 181800, "loss": 0.0725, "lr": 4.35702673366226e-05, "epoch": 6.202970297029703, "percentage": 31.01, "elapsed_time": "2:13:19", "remaining_time": "4:56:31", "throughput": 1487.42, "total_tokens": 11897920} {"current_steps": 56390, "total_steps": 181800, "loss": 0.0406, "lr": 4.356866040207707e-05, "epoch": 6.203520352035204, "percentage": 31.02, "elapsed_time": "2:13:19", "remaining_time": "4:56:31", "throughput": 1487.43, "total_tokens": 11899008} {"current_steps": 56395, "total_steps": 181800, "loss": 0.0226, "lr": 4.3567053296393115e-05, "epoch": 6.204070407040704, "percentage": 31.02, "elapsed_time": "2:13:20", "remaining_time": "4:56:30", "throughput": 1487.43, "total_tokens": 11900096} {"current_steps": 56400, "total_steps": 181800, "loss": 0.0354, "lr": 4.3565446019585544e-05, "epoch": 6.204620462046204, "percentage": 31.02, "elapsed_time": "2:13:21", "remaining_time": "4:56:29", "throughput": 1487.44, "total_tokens": 11901152} {"current_steps": 56405, "total_steps": 181800, "loss": 0.0714, "lr": 4.356383857166916e-05, "epoch": 6.205170517051705, "percentage": 31.03, "elapsed_time": "2:13:21", "remaining_time": "4:56:28", "throughput": 1487.45, "total_tokens": 11902240} {"current_steps": 56410, "total_steps": 181800, "loss": 0.0678, "lr": 4.356223095265878e-05, "epoch": 6.2057205720572055, "percentage": 31.03, "elapsed_time": "2:13:22", "remaining_time": "4:56:28", "throughput": 1487.46, "total_tokens": 11903360} {"current_steps": 56415, "total_steps": 181800, "loss": 0.0078, "lr": 4.3560623162569225e-05, "epoch": 6.206270627062707, "percentage": 31.03, "elapsed_time": "2:13:23", "remaining_time": "4:56:27", "throughput": 1487.46, "total_tokens": 11904384} {"current_steps": 56420, "total_steps": 181800, "loss": 0.0515, "lr": 4.3559015201415316e-05, "epoch": 6.206820682068207, "percentage": 31.03, "elapsed_time": "2:13:23", "remaining_time": "4:56:26", "throughput": 1487.46, "total_tokens": 11905440} {"current_steps": 56425, "total_steps": 181800, "loss": 0.0302, "lr": 4.355740706921187e-05, "epoch": 6.207370737073707, "percentage": 31.04, "elapsed_time": "2:13:24", "remaining_time": "4:56:25", "throughput": 1487.48, "total_tokens": 11906592} {"current_steps": 56430, "total_steps": 181800, "loss": 0.0091, "lr": 4.3555798765973705e-05, "epoch": 6.207920792079208, "percentage": 31.04, "elapsed_time": "2:13:25", "remaining_time": "4:56:25", "throughput": 1487.49, "total_tokens": 11907712} {"current_steps": 56435, "total_steps": 181800, "loss": 0.0469, "lr": 4.355419029171565e-05, "epoch": 6.208470847084708, "percentage": 31.04, "elapsed_time": "2:13:25", "remaining_time": "4:56:24", "throughput": 1487.5, "total_tokens": 11908800} {"current_steps": 56440, "total_steps": 181800, "loss": 0.0745, "lr": 4.3552581646452525e-05, "epoch": 6.209020902090209, "percentage": 31.05, "elapsed_time": "2:13:26", "remaining_time": "4:56:23", "throughput": 1487.5, "total_tokens": 11909856} {"current_steps": 56445, "total_steps": 181800, "loss": 0.0283, "lr": 4.355097283019916e-05, "epoch": 6.20957095709571, "percentage": 31.05, "elapsed_time": "2:13:27", "remaining_time": "4:56:22", "throughput": 1487.51, "total_tokens": 11910976} {"current_steps": 56450, "total_steps": 181800, "loss": 0.087, "lr": 4.354936384297037e-05, "epoch": 6.21012101210121, "percentage": 31.05, "elapsed_time": "2:13:28", "remaining_time": "4:56:22", "throughput": 1487.52, "total_tokens": 11912096} {"current_steps": 56455, "total_steps": 181800, "loss": 0.062, "lr": 4.3547754684781005e-05, "epoch": 6.210671067106711, "percentage": 31.05, "elapsed_time": "2:13:28", "remaining_time": "4:56:21", "throughput": 1487.53, "total_tokens": 11913152} {"current_steps": 56460, "total_steps": 181800, "loss": 0.0871, "lr": 4.354614535564588e-05, "epoch": 6.211221122112211, "percentage": 31.06, "elapsed_time": "2:13:29", "remaining_time": "4:56:20", "throughput": 1487.53, "total_tokens": 11914176} {"current_steps": 56465, "total_steps": 181800, "loss": 0.0274, "lr": 4.354453585557984e-05, "epoch": 6.211771177117711, "percentage": 31.06, "elapsed_time": "2:13:30", "remaining_time": "4:56:19", "throughput": 1487.53, "total_tokens": 11915232} {"current_steps": 56470, "total_steps": 181800, "loss": 0.0171, "lr": 4.3542926184597696e-05, "epoch": 6.212321232123212, "percentage": 31.06, "elapsed_time": "2:13:30", "remaining_time": "4:56:19", "throughput": 1487.53, "total_tokens": 11916256} {"current_steps": 56475, "total_steps": 181800, "loss": 0.0684, "lr": 4.3541316342714314e-05, "epoch": 6.212871287128713, "percentage": 31.06, "elapsed_time": "2:13:31", "remaining_time": "4:56:18", "throughput": 1487.53, "total_tokens": 11917280} {"current_steps": 56480, "total_steps": 181800, "loss": 0.0464, "lr": 4.353970632994451e-05, "epoch": 6.213421342134214, "percentage": 31.07, "elapsed_time": "2:13:32", "remaining_time": "4:56:17", "throughput": 1487.53, "total_tokens": 11918304} {"current_steps": 56485, "total_steps": 181800, "loss": 0.1896, "lr": 4.3538096146303134e-05, "epoch": 6.213971397139714, "percentage": 31.07, "elapsed_time": "2:13:32", "remaining_time": "4:56:16", "throughput": 1487.53, "total_tokens": 11919328} {"current_steps": 56490, "total_steps": 181800, "loss": 0.0845, "lr": 4.3536485791805015e-05, "epoch": 6.214521452145214, "percentage": 31.07, "elapsed_time": "2:13:33", "remaining_time": "4:56:16", "throughput": 1487.54, "total_tokens": 11920416} {"current_steps": 56495, "total_steps": 181800, "loss": 0.0685, "lr": 4.3534875266465005e-05, "epoch": 6.215071507150715, "percentage": 31.08, "elapsed_time": "2:13:34", "remaining_time": "4:56:15", "throughput": 1487.55, "total_tokens": 11921504} {"current_steps": 56500, "total_steps": 181800, "loss": 0.1318, "lr": 4.353326457029794e-05, "epoch": 6.215621562156215, "percentage": 31.08, "elapsed_time": "2:13:34", "remaining_time": "4:56:14", "throughput": 1487.55, "total_tokens": 11922592} {"current_steps": 56505, "total_steps": 181800, "loss": 0.0163, "lr": 4.353165370331867e-05, "epoch": 6.2161716171617165, "percentage": 31.08, "elapsed_time": "2:13:35", "remaining_time": "4:56:13", "throughput": 1487.57, "total_tokens": 11923744} {"current_steps": 56510, "total_steps": 181800, "loss": 0.0167, "lr": 4.353004266554204e-05, "epoch": 6.216721672167217, "percentage": 31.08, "elapsed_time": "2:13:36", "remaining_time": "4:56:13", "throughput": 1487.56, "total_tokens": 11924704} {"current_steps": 56515, "total_steps": 181800, "loss": 0.0366, "lr": 4.35284314569829e-05, "epoch": 6.217271727172717, "percentage": 31.09, "elapsed_time": "2:13:36", "remaining_time": "4:56:12", "throughput": 1487.56, "total_tokens": 11925696} {"current_steps": 56520, "total_steps": 181800, "loss": 0.0158, "lr": 4.3526820077656095e-05, "epoch": 6.217821782178218, "percentage": 31.09, "elapsed_time": "2:13:37", "remaining_time": "4:56:11", "throughput": 1487.56, "total_tokens": 11926720} {"current_steps": 56525, "total_steps": 181800, "loss": 0.0418, "lr": 4.352520852757648e-05, "epoch": 6.218371837183718, "percentage": 31.09, "elapsed_time": "2:13:38", "remaining_time": "4:56:10", "throughput": 1487.56, "total_tokens": 11927744} {"current_steps": 56530, "total_steps": 181800, "loss": 0.1518, "lr": 4.3523596806758916e-05, "epoch": 6.218921892189219, "percentage": 31.09, "elapsed_time": "2:13:39", "remaining_time": "4:56:10", "throughput": 1487.56, "total_tokens": 11928800} {"current_steps": 56535, "total_steps": 181800, "loss": 0.135, "lr": 4.3521984915218236e-05, "epoch": 6.2194719471947195, "percentage": 31.1, "elapsed_time": "2:13:39", "remaining_time": "4:56:09", "throughput": 1487.57, "total_tokens": 11929888} {"current_steps": 56540, "total_steps": 181800, "loss": 0.0531, "lr": 4.3520372852969314e-05, "epoch": 6.22002200220022, "percentage": 31.1, "elapsed_time": "2:13:40", "remaining_time": "4:56:08", "throughput": 1487.57, "total_tokens": 11930912} {"current_steps": 56545, "total_steps": 181800, "loss": 0.0225, "lr": 4.3518760620027e-05, "epoch": 6.220572057205721, "percentage": 31.1, "elapsed_time": "2:13:41", "remaining_time": "4:56:07", "throughput": 1487.58, "total_tokens": 11932032} {"current_steps": 56550, "total_steps": 181800, "loss": 0.0784, "lr": 4.351714821640616e-05, "epoch": 6.221122112211221, "percentage": 31.11, "elapsed_time": "2:13:41", "remaining_time": "4:56:07", "throughput": 1487.59, "total_tokens": 11933184} {"current_steps": 56555, "total_steps": 181800, "loss": 0.1301, "lr": 4.351553564212165e-05, "epoch": 6.221672167216722, "percentage": 31.11, "elapsed_time": "2:13:42", "remaining_time": "4:56:06", "throughput": 1487.59, "total_tokens": 11934208} {"current_steps": 56560, "total_steps": 181800, "loss": 0.015, "lr": 4.351392289718833e-05, "epoch": 6.222222222222222, "percentage": 31.11, "elapsed_time": "2:13:43", "remaining_time": "4:56:05", "throughput": 1487.6, "total_tokens": 11935264} {"current_steps": 56565, "total_steps": 181800, "loss": 0.0047, "lr": 4.3512309981621066e-05, "epoch": 6.2227722772277225, "percentage": 31.11, "elapsed_time": "2:13:43", "remaining_time": "4:56:04", "throughput": 1487.6, "total_tokens": 11936320} {"current_steps": 56570, "total_steps": 181800, "loss": 0.0177, "lr": 4.3510696895434726e-05, "epoch": 6.223322332233224, "percentage": 31.12, "elapsed_time": "2:13:44", "remaining_time": "4:56:04", "throughput": 1487.6, "total_tokens": 11937312} {"current_steps": 56575, "total_steps": 181800, "loss": 0.132, "lr": 4.3509083638644174e-05, "epoch": 6.223872387238724, "percentage": 31.12, "elapsed_time": "2:13:45", "remaining_time": "4:56:03", "throughput": 1487.6, "total_tokens": 11938368} {"current_steps": 56580, "total_steps": 181800, "loss": 0.0887, "lr": 4.3507470211264275e-05, "epoch": 6.224422442244224, "percentage": 31.12, "elapsed_time": "2:13:45", "remaining_time": "4:56:02", "throughput": 1487.6, "total_tokens": 11939424} {"current_steps": 56585, "total_steps": 181800, "loss": 0.0298, "lr": 4.350585661330991e-05, "epoch": 6.224972497249725, "percentage": 31.12, "elapsed_time": "2:13:46", "remaining_time": "4:56:01", "throughput": 1487.62, "total_tokens": 11940544} {"current_steps": 56590, "total_steps": 181800, "loss": 0.0212, "lr": 4.350424284479595e-05, "epoch": 6.225522552255225, "percentage": 31.13, "elapsed_time": "2:13:47", "remaining_time": "4:56:01", "throughput": 1487.61, "total_tokens": 11941536} {"current_steps": 56595, "total_steps": 181800, "loss": 0.0341, "lr": 4.350262890573725e-05, "epoch": 6.226072607260726, "percentage": 31.13, "elapsed_time": "2:13:48", "remaining_time": "4:56:00", "throughput": 1487.62, "total_tokens": 11942656} {"current_steps": 56600, "total_steps": 181800, "loss": 0.0383, "lr": 4.350101479614871e-05, "epoch": 6.226622662266227, "percentage": 31.13, "elapsed_time": "2:13:48", "remaining_time": "4:55:59", "throughput": 1487.63, "total_tokens": 11943712} {"current_steps": 56605, "total_steps": 181800, "loss": 0.0292, "lr": 4.3499400516045186e-05, "epoch": 6.227172717271727, "percentage": 31.14, "elapsed_time": "2:13:49", "remaining_time": "4:55:58", "throughput": 1487.62, "total_tokens": 11944704} {"current_steps": 56610, "total_steps": 181800, "loss": 0.1124, "lr": 4.349778606544157e-05, "epoch": 6.227722772277228, "percentage": 31.14, "elapsed_time": "2:13:50", "remaining_time": "4:55:58", "throughput": 1487.64, "total_tokens": 11945824} {"current_steps": 56615, "total_steps": 181800, "loss": 0.0144, "lr": 4.349617144435273e-05, "epoch": 6.228272827282728, "percentage": 31.14, "elapsed_time": "2:13:50", "remaining_time": "4:55:57", "throughput": 1487.64, "total_tokens": 11946880} {"current_steps": 56620, "total_steps": 181800, "loss": 0.0273, "lr": 4.3494556652793556e-05, "epoch": 6.228822882288229, "percentage": 31.14, "elapsed_time": "2:13:51", "remaining_time": "4:55:56", "throughput": 1487.64, "total_tokens": 11947936} {"current_steps": 56625, "total_steps": 181800, "loss": 0.0566, "lr": 4.349294169077893e-05, "epoch": 6.229372937293729, "percentage": 31.15, "elapsed_time": "2:13:52", "remaining_time": "4:55:55", "throughput": 1487.65, "total_tokens": 11948992} {"current_steps": 56630, "total_steps": 181800, "loss": 0.0042, "lr": 4.349132655832373e-05, "epoch": 6.22992299229923, "percentage": 31.15, "elapsed_time": "2:13:52", "remaining_time": "4:55:55", "throughput": 1487.65, "total_tokens": 11950048} {"current_steps": 56635, "total_steps": 181800, "loss": 0.0542, "lr": 4.3489711255442844e-05, "epoch": 6.230473047304731, "percentage": 31.15, "elapsed_time": "2:13:53", "remaining_time": "4:55:54", "throughput": 1487.65, "total_tokens": 11951072} {"current_steps": 56640, "total_steps": 181800, "loss": 0.1025, "lr": 4.348809578215117e-05, "epoch": 6.231023102310231, "percentage": 31.16, "elapsed_time": "2:13:54", "remaining_time": "4:55:53", "throughput": 1487.66, "total_tokens": 11952128} {"current_steps": 56645, "total_steps": 181800, "loss": 0.1255, "lr": 4.348648013846358e-05, "epoch": 6.231573157315731, "percentage": 31.16, "elapsed_time": "2:13:54", "remaining_time": "4:55:52", "throughput": 1487.66, "total_tokens": 11953216} {"current_steps": 56650, "total_steps": 181800, "loss": 0.0364, "lr": 4.348486432439498e-05, "epoch": 6.232123212321232, "percentage": 31.16, "elapsed_time": "2:13:55", "remaining_time": "4:55:52", "throughput": 1487.66, "total_tokens": 11954240} {"current_steps": 56655, "total_steps": 181800, "loss": 0.0647, "lr": 4.348324833996025e-05, "epoch": 6.232673267326732, "percentage": 31.16, "elapsed_time": "2:13:56", "remaining_time": "4:55:51", "throughput": 1487.67, "total_tokens": 11955296} {"current_steps": 56660, "total_steps": 181800, "loss": 0.0413, "lr": 4.348163218517429e-05, "epoch": 6.2332233223322335, "percentage": 31.17, "elapsed_time": "2:13:56", "remaining_time": "4:55:50", "throughput": 1487.67, "total_tokens": 11956320} {"current_steps": 56665, "total_steps": 181800, "loss": 0.07, "lr": 4.3480015860052004e-05, "epoch": 6.233773377337734, "percentage": 31.17, "elapsed_time": "2:13:57", "remaining_time": "4:55:49", "throughput": 1487.66, "total_tokens": 11957312} {"current_steps": 56670, "total_steps": 181800, "loss": 0.0909, "lr": 4.347839936460827e-05, "epoch": 6.234323432343234, "percentage": 31.17, "elapsed_time": "2:13:58", "remaining_time": "4:55:48", "throughput": 1487.67, "total_tokens": 11958368} {"current_steps": 56675, "total_steps": 181800, "loss": 0.2219, "lr": 4.3476782698858e-05, "epoch": 6.234873487348735, "percentage": 31.17, "elapsed_time": "2:13:59", "remaining_time": "4:55:48", "throughput": 1487.67, "total_tokens": 11959424} {"current_steps": 56680, "total_steps": 181800, "loss": 0.0984, "lr": 4.347516586281608e-05, "epoch": 6.235423542354235, "percentage": 31.18, "elapsed_time": "2:13:59", "remaining_time": "4:55:47", "throughput": 1487.68, "total_tokens": 11960512} {"current_steps": 56685, "total_steps": 181800, "loss": 0.036, "lr": 4.347354885649744e-05, "epoch": 6.235973597359736, "percentage": 31.18, "elapsed_time": "2:14:00", "remaining_time": "4:55:46", "throughput": 1487.69, "total_tokens": 11961600} {"current_steps": 56690, "total_steps": 181800, "loss": 0.0196, "lr": 4.347193167991694e-05, "epoch": 6.2365236523652365, "percentage": 31.18, "elapsed_time": "2:14:01", "remaining_time": "4:55:45", "throughput": 1487.69, "total_tokens": 11962624} {"current_steps": 56695, "total_steps": 181800, "loss": 0.0624, "lr": 4.3470314333089534e-05, "epoch": 6.237073707370737, "percentage": 31.19, "elapsed_time": "2:14:01", "remaining_time": "4:55:45", "throughput": 1487.68, "total_tokens": 11963616} {"current_steps": 56700, "total_steps": 181800, "loss": 0.0116, "lr": 4.3468696816030086e-05, "epoch": 6.237623762376238, "percentage": 31.19, "elapsed_time": "2:14:02", "remaining_time": "4:55:44", "throughput": 1487.69, "total_tokens": 11964672} {"current_steps": 56705, "total_steps": 181800, "loss": 0.019, "lr": 4.3467079128753526e-05, "epoch": 6.238173817381738, "percentage": 31.19, "elapsed_time": "2:14:03", "remaining_time": "4:55:43", "throughput": 1487.69, "total_tokens": 11965728} {"current_steps": 56710, "total_steps": 181800, "loss": 0.0231, "lr": 4.346546127127477e-05, "epoch": 6.238723872387239, "percentage": 31.19, "elapsed_time": "2:14:03", "remaining_time": "4:55:42", "throughput": 1487.7, "total_tokens": 11966816} {"current_steps": 56715, "total_steps": 181800, "loss": 0.0194, "lr": 4.34638432436087e-05, "epoch": 6.239273927392739, "percentage": 31.2, "elapsed_time": "2:14:04", "remaining_time": "4:55:42", "throughput": 1487.7, "total_tokens": 11967872} {"current_steps": 56720, "total_steps": 181800, "loss": 0.01, "lr": 4.3462225045770266e-05, "epoch": 6.2398239823982395, "percentage": 31.2, "elapsed_time": "2:14:05", "remaining_time": "4:55:41", "throughput": 1487.7, "total_tokens": 11968896} {"current_steps": 56725, "total_steps": 181800, "loss": 0.0366, "lr": 4.346060667777435e-05, "epoch": 6.240374037403741, "percentage": 31.2, "elapsed_time": "2:14:05", "remaining_time": "4:55:40", "throughput": 1487.71, "total_tokens": 11969984} {"current_steps": 56730, "total_steps": 181800, "loss": 0.0495, "lr": 4.345898813963588e-05, "epoch": 6.240924092409241, "percentage": 31.2, "elapsed_time": "2:14:06", "remaining_time": "4:55:39", "throughput": 1487.72, "total_tokens": 11971040} {"current_steps": 56735, "total_steps": 181800, "loss": 0.0525, "lr": 4.3457369431369774e-05, "epoch": 6.241474147414741, "percentage": 31.21, "elapsed_time": "2:14:07", "remaining_time": "4:55:39", "throughput": 1487.73, "total_tokens": 11972192} {"current_steps": 56740, "total_steps": 181800, "loss": 0.0272, "lr": 4.345575055299096e-05, "epoch": 6.242024202420242, "percentage": 31.21, "elapsed_time": "2:14:07", "remaining_time": "4:55:38", "throughput": 1487.73, "total_tokens": 11973216} {"current_steps": 56745, "total_steps": 181800, "loss": 0.0144, "lr": 4.3454131504514344e-05, "epoch": 6.242574257425742, "percentage": 31.21, "elapsed_time": "2:14:08", "remaining_time": "4:55:37", "throughput": 1487.74, "total_tokens": 11974304} {"current_steps": 56750, "total_steps": 181800, "loss": 0.0226, "lr": 4.345251228595485e-05, "epoch": 6.243124312431243, "percentage": 31.22, "elapsed_time": "2:14:09", "remaining_time": "4:55:36", "throughput": 1487.74, "total_tokens": 11975296} {"current_steps": 56755, "total_steps": 181800, "loss": 0.0304, "lr": 4.345089289732741e-05, "epoch": 6.243674367436744, "percentage": 31.22, "elapsed_time": "2:14:10", "remaining_time": "4:55:36", "throughput": 1487.74, "total_tokens": 11976352} {"current_steps": 56760, "total_steps": 181800, "loss": 0.0413, "lr": 4.344927333864694e-05, "epoch": 6.244224422442244, "percentage": 31.22, "elapsed_time": "2:14:10", "remaining_time": "4:55:35", "throughput": 1487.74, "total_tokens": 11977408} {"current_steps": 56765, "total_steps": 181800, "loss": 0.0124, "lr": 4.3447653609928366e-05, "epoch": 6.244774477447745, "percentage": 31.22, "elapsed_time": "2:14:11", "remaining_time": "4:55:34", "throughput": 1487.75, "total_tokens": 11978496} {"current_steps": 56770, "total_steps": 181800, "loss": 0.0536, "lr": 4.344603371118663e-05, "epoch": 6.245324532453245, "percentage": 31.23, "elapsed_time": "2:14:12", "remaining_time": "4:55:33", "throughput": 1487.75, "total_tokens": 11979552} {"current_steps": 56775, "total_steps": 181800, "loss": 0.0334, "lr": 4.344441364243665e-05, "epoch": 6.245874587458746, "percentage": 31.23, "elapsed_time": "2:14:12", "remaining_time": "4:55:33", "throughput": 1487.76, "total_tokens": 11980640} {"current_steps": 56780, "total_steps": 181800, "loss": 0.0572, "lr": 4.344279340369336e-05, "epoch": 6.2464246424642464, "percentage": 31.23, "elapsed_time": "2:14:13", "remaining_time": "4:55:32", "throughput": 1487.77, "total_tokens": 11981760} {"current_steps": 56785, "total_steps": 181800, "loss": 0.0876, "lr": 4.3441172994971693e-05, "epoch": 6.246974697469747, "percentage": 31.23, "elapsed_time": "2:14:14", "remaining_time": "4:55:31", "throughput": 1487.77, "total_tokens": 11982784} {"current_steps": 56790, "total_steps": 181800, "loss": 0.194, "lr": 4.343955241628658e-05, "epoch": 6.247524752475248, "percentage": 31.24, "elapsed_time": "2:14:14", "remaining_time": "4:55:30", "throughput": 1487.77, "total_tokens": 11983808} {"current_steps": 56795, "total_steps": 181800, "loss": 0.0795, "lr": 4.3437931667652956e-05, "epoch": 6.248074807480748, "percentage": 31.24, "elapsed_time": "2:14:15", "remaining_time": "4:55:30", "throughput": 1487.78, "total_tokens": 11984864} {"current_steps": 56800, "total_steps": 181800, "loss": 0.0986, "lr": 4.3436310749085774e-05, "epoch": 6.248624862486249, "percentage": 31.24, "elapsed_time": "2:14:16", "remaining_time": "4:55:29", "throughput": 1487.78, "total_tokens": 11985920} {"current_steps": 56805, "total_steps": 181800, "loss": 0.0829, "lr": 4.343468966059996e-05, "epoch": 6.249174917491749, "percentage": 31.25, "elapsed_time": "2:14:16", "remaining_time": "4:55:28", "throughput": 1487.78, "total_tokens": 11986976} {"current_steps": 56810, "total_steps": 181800, "loss": 0.0618, "lr": 4.343306840221045e-05, "epoch": 6.2497249724972495, "percentage": 31.25, "elapsed_time": "2:14:17", "remaining_time": "4:55:27", "throughput": 1487.78, "total_tokens": 11988000} {"current_steps": 56815, "total_steps": 181800, "loss": 0.0276, "lr": 4.34314469739322e-05, "epoch": 6.2502750275027505, "percentage": 31.25, "elapsed_time": "2:14:18", "remaining_time": "4:55:27", "throughput": 1487.79, "total_tokens": 11989088} {"current_steps": 56820, "total_steps": 181800, "loss": 0.034, "lr": 4.342982537578014e-05, "epoch": 6.250825082508251, "percentage": 31.25, "elapsed_time": "2:14:19", "remaining_time": "4:55:26", "throughput": 1487.79, "total_tokens": 11990144} {"current_steps": 56825, "total_steps": 181800, "loss": 0.0275, "lr": 4.3428203607769233e-05, "epoch": 6.251375137513751, "percentage": 31.26, "elapsed_time": "2:14:19", "remaining_time": "4:55:25", "throughput": 1487.8, "total_tokens": 11991200} {"current_steps": 56830, "total_steps": 181800, "loss": 0.035, "lr": 4.342658166991441e-05, "epoch": 6.251925192519252, "percentage": 31.26, "elapsed_time": "2:14:20", "remaining_time": "4:55:24", "throughput": 1487.8, "total_tokens": 11992288} {"current_steps": 56835, "total_steps": 181800, "loss": 0.0095, "lr": 4.342495956223063e-05, "epoch": 6.252475247524752, "percentage": 31.26, "elapsed_time": "2:14:21", "remaining_time": "4:55:24", "throughput": 1487.8, "total_tokens": 11993312} {"current_steps": 56840, "total_steps": 181800, "loss": 0.0098, "lr": 4.342333728473283e-05, "epoch": 6.253025302530253, "percentage": 31.27, "elapsed_time": "2:14:21", "remaining_time": "4:55:23", "throughput": 1487.81, "total_tokens": 11994400} {"current_steps": 56845, "total_steps": 181800, "loss": 0.0089, "lr": 4.3421714837435986e-05, "epoch": 6.2535753575357536, "percentage": 31.27, "elapsed_time": "2:14:22", "remaining_time": "4:55:22", "throughput": 1487.81, "total_tokens": 11995456} {"current_steps": 56850, "total_steps": 181800, "loss": 0.0092, "lr": 4.3420092220355024e-05, "epoch": 6.254125412541254, "percentage": 31.27, "elapsed_time": "2:14:23", "remaining_time": "4:55:21", "throughput": 1487.82, "total_tokens": 11996544} {"current_steps": 56855, "total_steps": 181800, "loss": 0.022, "lr": 4.3418469433504916e-05, "epoch": 6.254675467546755, "percentage": 31.27, "elapsed_time": "2:14:23", "remaining_time": "4:55:21", "throughput": 1487.83, "total_tokens": 11997632} {"current_steps": 56860, "total_steps": 181800, "loss": 0.0364, "lr": 4.341684647690061e-05, "epoch": 6.255225522552255, "percentage": 31.28, "elapsed_time": "2:14:24", "remaining_time": "4:55:20", "throughput": 1487.83, "total_tokens": 11998688} {"current_steps": 56865, "total_steps": 181800, "loss": 0.0322, "lr": 4.3415223350557074e-05, "epoch": 6.255775577557756, "percentage": 31.28, "elapsed_time": "2:14:25", "remaining_time": "4:55:19", "throughput": 1487.84, "total_tokens": 11999776} {"current_steps": 56870, "total_steps": 181800, "loss": 0.0165, "lr": 4.341360005448925e-05, "epoch": 6.256325632563256, "percentage": 31.28, "elapsed_time": "2:14:25", "remaining_time": "4:55:18", "throughput": 1487.84, "total_tokens": 12000800} {"current_steps": 56875, "total_steps": 181800, "loss": 0.003, "lr": 4.3411976588712115e-05, "epoch": 6.256875687568757, "percentage": 31.28, "elapsed_time": "2:14:26", "remaining_time": "4:55:18", "throughput": 1487.85, "total_tokens": 12001920} {"current_steps": 56880, "total_steps": 181800, "loss": 0.0417, "lr": 4.341035295324063e-05, "epoch": 6.257425742574258, "percentage": 31.29, "elapsed_time": "2:14:27", "remaining_time": "4:55:17", "throughput": 1487.86, "total_tokens": 12003008} {"current_steps": 56885, "total_steps": 181800, "loss": 0.0581, "lr": 4.3408729148089754e-05, "epoch": 6.257975797579758, "percentage": 31.29, "elapsed_time": "2:14:27", "remaining_time": "4:55:16", "throughput": 1487.86, "total_tokens": 12004064} {"current_steps": 56890, "total_steps": 181800, "loss": 0.0185, "lr": 4.3407105173274454e-05, "epoch": 6.258525852585258, "percentage": 31.29, "elapsed_time": "2:14:28", "remaining_time": "4:55:15", "throughput": 1487.87, "total_tokens": 12005152} {"current_steps": 56895, "total_steps": 181800, "loss": 0.0562, "lr": 4.3405481028809696e-05, "epoch": 6.259075907590759, "percentage": 31.3, "elapsed_time": "2:14:29", "remaining_time": "4:55:15", "throughput": 1487.87, "total_tokens": 12006176} {"current_steps": 56900, "total_steps": 181800, "loss": 0.0216, "lr": 4.3403856714710456e-05, "epoch": 6.259625962596259, "percentage": 31.3, "elapsed_time": "2:14:30", "remaining_time": "4:55:14", "throughput": 1487.88, "total_tokens": 12007328} {"current_steps": 56905, "total_steps": 181800, "loss": 0.038, "lr": 4.340223223099169e-05, "epoch": 6.2601760176017605, "percentage": 31.3, "elapsed_time": "2:14:30", "remaining_time": "4:55:13", "throughput": 1487.89, "total_tokens": 12008448} {"current_steps": 56910, "total_steps": 181800, "loss": 0.1171, "lr": 4.34006075776684e-05, "epoch": 6.260726072607261, "percentage": 31.3, "elapsed_time": "2:14:31", "remaining_time": "4:55:12", "throughput": 1487.91, "total_tokens": 12009568} {"current_steps": 56915, "total_steps": 181800, "loss": 0.1003, "lr": 4.339898275475552e-05, "epoch": 6.261276127612761, "percentage": 31.31, "elapsed_time": "2:14:32", "remaining_time": "4:55:12", "throughput": 1487.91, "total_tokens": 12010624} {"current_steps": 56920, "total_steps": 181800, "loss": 0.0199, "lr": 4.339735776226805e-05, "epoch": 6.261826182618262, "percentage": 31.31, "elapsed_time": "2:14:32", "remaining_time": "4:55:11", "throughput": 1487.91, "total_tokens": 12011680} {"current_steps": 56925, "total_steps": 181800, "loss": 0.0174, "lr": 4.339573260022096e-05, "epoch": 6.262376237623762, "percentage": 31.31, "elapsed_time": "2:14:33", "remaining_time": "4:55:10", "throughput": 1487.93, "total_tokens": 12012800} {"current_steps": 56930, "total_steps": 181800, "loss": 0.0039, "lr": 4.339410726862924e-05, "epoch": 6.262926292629263, "percentage": 31.31, "elapsed_time": "2:14:34", "remaining_time": "4:55:09", "throughput": 1487.93, "total_tokens": 12013856} {"current_steps": 56935, "total_steps": 181800, "loss": 0.0535, "lr": 4.339248176750784e-05, "epoch": 6.2634763476347635, "percentage": 31.32, "elapsed_time": "2:14:34", "remaining_time": "4:55:09", "throughput": 1487.93, "total_tokens": 12014880} {"current_steps": 56940, "total_steps": 181800, "loss": 0.0172, "lr": 4.339085609687178e-05, "epoch": 6.264026402640264, "percentage": 31.32, "elapsed_time": "2:14:35", "remaining_time": "4:55:08", "throughput": 1487.93, "total_tokens": 12015936} {"current_steps": 56945, "total_steps": 181800, "loss": 0.0214, "lr": 4.3389230256736015e-05, "epoch": 6.264576457645765, "percentage": 31.32, "elapsed_time": "2:14:36", "remaining_time": "4:55:07", "throughput": 1487.93, "total_tokens": 12016928} {"current_steps": 56950, "total_steps": 181800, "loss": 0.0234, "lr": 4.338760424711554e-05, "epoch": 6.265126512651265, "percentage": 31.33, "elapsed_time": "2:14:36", "remaining_time": "4:55:06", "throughput": 1487.93, "total_tokens": 12017952} {"current_steps": 56955, "total_steps": 181800, "loss": 0.1169, "lr": 4.338597806802534e-05, "epoch": 6.265676567656766, "percentage": 31.33, "elapsed_time": "2:14:37", "remaining_time": "4:55:06", "throughput": 1487.93, "total_tokens": 12018976} {"current_steps": 56960, "total_steps": 181800, "loss": 0.0088, "lr": 4.33843517194804e-05, "epoch": 6.266226622662266, "percentage": 31.33, "elapsed_time": "2:14:38", "remaining_time": "4:55:05", "throughput": 1487.93, "total_tokens": 12020000} {"current_steps": 56965, "total_steps": 181800, "loss": 0.0027, "lr": 4.3382725201495723e-05, "epoch": 6.2667766776677665, "percentage": 31.33, "elapsed_time": "2:14:39", "remaining_time": "4:55:04", "throughput": 1487.93, "total_tokens": 12021056} {"current_steps": 56970, "total_steps": 181800, "loss": 0.0418, "lr": 4.3381098514086276e-05, "epoch": 6.267326732673268, "percentage": 31.34, "elapsed_time": "2:14:39", "remaining_time": "4:55:03", "throughput": 1487.93, "total_tokens": 12022112} {"current_steps": 56975, "total_steps": 181800, "loss": 0.1237, "lr": 4.337947165726707e-05, "epoch": 6.267876787678768, "percentage": 31.34, "elapsed_time": "2:14:40", "remaining_time": "4:55:03", "throughput": 1487.94, "total_tokens": 12023200} {"current_steps": 56980, "total_steps": 181800, "loss": 0.0764, "lr": 4.337784463105309e-05, "epoch": 6.268426842684269, "percentage": 31.34, "elapsed_time": "2:14:41", "remaining_time": "4:55:02", "throughput": 1487.95, "total_tokens": 12024288} {"current_steps": 56985, "total_steps": 181800, "loss": 0.0106, "lr": 4.337621743545934e-05, "epoch": 6.268976897689769, "percentage": 31.34, "elapsed_time": "2:14:41", "remaining_time": "4:55:01", "throughput": 1487.95, "total_tokens": 12025312} {"current_steps": 56990, "total_steps": 181800, "loss": 0.0672, "lr": 4.3374590070500804e-05, "epoch": 6.269526952695269, "percentage": 31.35, "elapsed_time": "2:14:42", "remaining_time": "4:55:00", "throughput": 1487.95, "total_tokens": 12026336} {"current_steps": 56995, "total_steps": 181800, "loss": 0.1712, "lr": 4.33729625361925e-05, "epoch": 6.27007700770077, "percentage": 31.35, "elapsed_time": "2:14:43", "remaining_time": "4:55:00", "throughput": 1487.95, "total_tokens": 12027392} {"current_steps": 57000, "total_steps": 181800, "loss": 0.0231, "lr": 4.3371334832549404e-05, "epoch": 6.270627062706271, "percentage": 31.35, "elapsed_time": "2:14:43", "remaining_time": "4:54:59", "throughput": 1487.95, "total_tokens": 12028416} {"current_steps": 57005, "total_steps": 181800, "loss": 0.0552, "lr": 4.336970695958653e-05, "epoch": 6.271177117711771, "percentage": 31.36, "elapsed_time": "2:14:44", "remaining_time": "4:54:58", "throughput": 1487.95, "total_tokens": 12029408} {"current_steps": 57010, "total_steps": 181800, "loss": 0.0208, "lr": 4.336807891731889e-05, "epoch": 6.271727172717272, "percentage": 31.36, "elapsed_time": "2:14:45", "remaining_time": "4:54:57", "throughput": 1487.95, "total_tokens": 12030464} {"current_steps": 57015, "total_steps": 181800, "loss": 0.0483, "lr": 4.336645070576148e-05, "epoch": 6.272277227722772, "percentage": 31.36, "elapsed_time": "2:14:45", "remaining_time": "4:54:57", "throughput": 1487.96, "total_tokens": 12031552} {"current_steps": 57020, "total_steps": 181800, "loss": 0.0083, "lr": 4.33648223249293e-05, "epoch": 6.272827282728273, "percentage": 31.36, "elapsed_time": "2:14:46", "remaining_time": "4:54:56", "throughput": 1487.96, "total_tokens": 12032576} {"current_steps": 57025, "total_steps": 181800, "loss": 0.0258, "lr": 4.3363193774837374e-05, "epoch": 6.273377337733773, "percentage": 31.37, "elapsed_time": "2:14:47", "remaining_time": "4:54:55", "throughput": 1487.95, "total_tokens": 12033536} {"current_steps": 57030, "total_steps": 181800, "loss": 0.0292, "lr": 4.3361565055500695e-05, "epoch": 6.273927392739274, "percentage": 31.37, "elapsed_time": "2:14:48", "remaining_time": "4:54:54", "throughput": 1487.94, "total_tokens": 12034528} {"current_steps": 57035, "total_steps": 181800, "loss": 0.0044, "lr": 4.3359936166934286e-05, "epoch": 6.274477447744775, "percentage": 31.37, "elapsed_time": "2:14:48", "remaining_time": "4:54:54", "throughput": 1487.95, "total_tokens": 12035584} {"current_steps": 57040, "total_steps": 181800, "loss": 0.0187, "lr": 4.335830710915315e-05, "epoch": 6.275027502750275, "percentage": 31.38, "elapsed_time": "2:14:49", "remaining_time": "4:54:53", "throughput": 1487.95, "total_tokens": 12036640} {"current_steps": 57045, "total_steps": 181800, "loss": 0.015, "lr": 4.3356677882172314e-05, "epoch": 6.275577557755776, "percentage": 31.38, "elapsed_time": "2:14:50", "remaining_time": "4:54:52", "throughput": 1487.95, "total_tokens": 12037664} {"current_steps": 57050, "total_steps": 181800, "loss": 0.0215, "lr": 4.3355048486006775e-05, "epoch": 6.276127612761276, "percentage": 31.38, "elapsed_time": "2:14:50", "remaining_time": "4:54:51", "throughput": 1487.96, "total_tokens": 12038752} {"current_steps": 57055, "total_steps": 181800, "loss": 0.0099, "lr": 4.335341892067157e-05, "epoch": 6.276677667766776, "percentage": 31.38, "elapsed_time": "2:14:51", "remaining_time": "4:54:51", "throughput": 1487.96, "total_tokens": 12039808} {"current_steps": 57060, "total_steps": 181800, "loss": 0.137, "lr": 4.3351789186181715e-05, "epoch": 6.2772277227722775, "percentage": 31.39, "elapsed_time": "2:14:52", "remaining_time": "4:54:50", "throughput": 1487.96, "total_tokens": 12040800} {"current_steps": 57065, "total_steps": 181800, "loss": 0.1252, "lr": 4.335015928255222e-05, "epoch": 6.277777777777778, "percentage": 31.39, "elapsed_time": "2:14:52", "remaining_time": "4:54:49", "throughput": 1487.98, "total_tokens": 12041952} {"current_steps": 57070, "total_steps": 181800, "loss": 0.0222, "lr": 4.334852920979811e-05, "epoch": 6.278327832783278, "percentage": 31.39, "elapsed_time": "2:14:53", "remaining_time": "4:54:48", "throughput": 1487.98, "total_tokens": 12043040} {"current_steps": 57075, "total_steps": 181800, "loss": 0.0079, "lr": 4.334689896793441e-05, "epoch": 6.278877887788779, "percentage": 31.39, "elapsed_time": "2:14:54", "remaining_time": "4:54:48", "throughput": 1487.98, "total_tokens": 12044064} {"current_steps": 57080, "total_steps": 181800, "loss": 0.0092, "lr": 4.334526855697615e-05, "epoch": 6.279427942794279, "percentage": 31.4, "elapsed_time": "2:14:54", "remaining_time": "4:54:47", "throughput": 1487.98, "total_tokens": 12045088} {"current_steps": 57085, "total_steps": 181800, "loss": 0.0616, "lr": 4.334363797693834e-05, "epoch": 6.27997799779978, "percentage": 31.4, "elapsed_time": "2:14:55", "remaining_time": "4:54:46", "throughput": 1487.99, "total_tokens": 12046176} {"current_steps": 57090, "total_steps": 181800, "loss": 0.0371, "lr": 4.3342007227836046e-05, "epoch": 6.2805280528052805, "percentage": 31.4, "elapsed_time": "2:14:56", "remaining_time": "4:54:45", "throughput": 1488.0, "total_tokens": 12047232} {"current_steps": 57095, "total_steps": 181800, "loss": 0.0642, "lr": 4.334037630968425e-05, "epoch": 6.281078107810781, "percentage": 31.41, "elapsed_time": "2:14:56", "remaining_time": "4:54:45", "throughput": 1488.0, "total_tokens": 12048320} {"current_steps": 57100, "total_steps": 181800, "loss": 0.0406, "lr": 4.333874522249802e-05, "epoch": 6.281628162816282, "percentage": 31.41, "elapsed_time": "2:14:57", "remaining_time": "4:54:44", "throughput": 1488.01, "total_tokens": 12049408} {"current_steps": 57105, "total_steps": 181800, "loss": 0.0217, "lr": 4.3337113966292365e-05, "epoch": 6.282178217821782, "percentage": 31.41, "elapsed_time": "2:14:58", "remaining_time": "4:54:43", "throughput": 1488.01, "total_tokens": 12050464} {"current_steps": 57110, "total_steps": 181800, "loss": 0.0406, "lr": 4.333548254108234e-05, "epoch": 6.282728272827283, "percentage": 31.41, "elapsed_time": "2:14:59", "remaining_time": "4:54:42", "throughput": 1488.02, "total_tokens": 12051520} {"current_steps": 57115, "total_steps": 181800, "loss": 0.0725, "lr": 4.333385094688296e-05, "epoch": 6.283278327832783, "percentage": 31.42, "elapsed_time": "2:14:59", "remaining_time": "4:54:42", "throughput": 1488.02, "total_tokens": 12052576} {"current_steps": 57120, "total_steps": 181800, "loss": 0.0114, "lr": 4.333221918370928e-05, "epoch": 6.2838283828382835, "percentage": 31.42, "elapsed_time": "2:15:00", "remaining_time": "4:54:41", "throughput": 1488.02, "total_tokens": 12053600} {"current_steps": 57125, "total_steps": 181800, "loss": 0.0529, "lr": 4.3330587251576327e-05, "epoch": 6.284378437843785, "percentage": 31.42, "elapsed_time": "2:15:01", "remaining_time": "4:54:40", "throughput": 1488.03, "total_tokens": 12054656} {"current_steps": 57130, "total_steps": 181800, "loss": 0.0521, "lr": 4.332895515049915e-05, "epoch": 6.284928492849285, "percentage": 31.42, "elapsed_time": "2:15:01", "remaining_time": "4:54:39", "throughput": 1488.03, "total_tokens": 12055712} {"current_steps": 57135, "total_steps": 181800, "loss": 0.0504, "lr": 4.332732288049279e-05, "epoch": 6.285478547854786, "percentage": 31.43, "elapsed_time": "2:15:02", "remaining_time": "4:54:39", "throughput": 1488.03, "total_tokens": 12056768} {"current_steps": 57140, "total_steps": 181800, "loss": 0.0361, "lr": 4.3325690441572286e-05, "epoch": 6.286028602860286, "percentage": 31.43, "elapsed_time": "2:15:03", "remaining_time": "4:54:38", "throughput": 1488.04, "total_tokens": 12057856} {"current_steps": 57145, "total_steps": 181800, "loss": 0.0769, "lr": 4.3324057833752694e-05, "epoch": 6.286578657865786, "percentage": 31.43, "elapsed_time": "2:15:03", "remaining_time": "4:54:37", "throughput": 1488.05, "total_tokens": 12058944} {"current_steps": 57150, "total_steps": 181800, "loss": 0.0234, "lr": 4.3322425057049043e-05, "epoch": 6.287128712871287, "percentage": 31.44, "elapsed_time": "2:15:04", "remaining_time": "4:54:36", "throughput": 1488.05, "total_tokens": 12059936} {"current_steps": 57155, "total_steps": 181800, "loss": 0.0428, "lr": 4.33207921114764e-05, "epoch": 6.287678767876788, "percentage": 31.44, "elapsed_time": "2:15:05", "remaining_time": "4:54:36", "throughput": 1488.05, "total_tokens": 12060992} {"current_steps": 57160, "total_steps": 181800, "loss": 0.0807, "lr": 4.33191589970498e-05, "epoch": 6.288228822882289, "percentage": 31.44, "elapsed_time": "2:15:05", "remaining_time": "4:54:35", "throughput": 1488.05, "total_tokens": 12062048} {"current_steps": 57165, "total_steps": 181800, "loss": 0.0871, "lr": 4.331752571378431e-05, "epoch": 6.288778877887789, "percentage": 31.44, "elapsed_time": "2:15:06", "remaining_time": "4:54:34", "throughput": 1488.06, "total_tokens": 12063136} {"current_steps": 57170, "total_steps": 181800, "loss": 0.0054, "lr": 4.331589226169497e-05, "epoch": 6.289328932893289, "percentage": 31.45, "elapsed_time": "2:15:07", "remaining_time": "4:54:33", "throughput": 1488.07, "total_tokens": 12064224} {"current_steps": 57175, "total_steps": 181800, "loss": 0.0258, "lr": 4.331425864079685e-05, "epoch": 6.28987898789879, "percentage": 31.45, "elapsed_time": "2:15:07", "remaining_time": "4:54:33", "throughput": 1488.08, "total_tokens": 12065312} {"current_steps": 57180, "total_steps": 181800, "loss": 0.011, "lr": 4.331262485110498e-05, "epoch": 6.29042904290429, "percentage": 31.45, "elapsed_time": "2:15:08", "remaining_time": "4:54:32", "throughput": 1488.08, "total_tokens": 12066400} {"current_steps": 57185, "total_steps": 181800, "loss": 0.0342, "lr": 4.331099089263445e-05, "epoch": 6.290979097909791, "percentage": 31.45, "elapsed_time": "2:15:09", "remaining_time": "4:54:31", "throughput": 1488.09, "total_tokens": 12067456} {"current_steps": 57190, "total_steps": 181800, "loss": 0.0711, "lr": 4.330935676540029e-05, "epoch": 6.291529152915292, "percentage": 31.46, "elapsed_time": "2:15:10", "remaining_time": "4:54:30", "throughput": 1488.09, "total_tokens": 12068544} {"current_steps": 57195, "total_steps": 181800, "loss": 0.036, "lr": 4.330772246941758e-05, "epoch": 6.292079207920792, "percentage": 31.46, "elapsed_time": "2:15:10", "remaining_time": "4:54:30", "throughput": 1488.09, "total_tokens": 12069568} {"current_steps": 57200, "total_steps": 181800, "loss": 0.068, "lr": 4.330608800470138e-05, "epoch": 6.292629262926293, "percentage": 31.46, "elapsed_time": "2:15:11", "remaining_time": "4:54:29", "throughput": 1488.1, "total_tokens": 12070656} {"current_steps": 57205, "total_steps": 181800, "loss": 0.0381, "lr": 4.330445337126675e-05, "epoch": 6.293179317931793, "percentage": 31.47, "elapsed_time": "2:15:12", "remaining_time": "4:54:28", "throughput": 1488.1, "total_tokens": 12071680} {"current_steps": 57210, "total_steps": 181800, "loss": 0.0137, "lr": 4.3302818569128746e-05, "epoch": 6.293729372937293, "percentage": 31.47, "elapsed_time": "2:15:12", "remaining_time": "4:54:27", "throughput": 1488.11, "total_tokens": 12072768} {"current_steps": 57215, "total_steps": 181800, "loss": 0.0191, "lr": 4.330118359830246e-05, "epoch": 6.2942794279427945, "percentage": 31.47, "elapsed_time": "2:15:13", "remaining_time": "4:54:27", "throughput": 1488.11, "total_tokens": 12073792} {"current_steps": 57220, "total_steps": 181800, "loss": 0.0058, "lr": 4.3299548458802944e-05, "epoch": 6.294829482948295, "percentage": 31.47, "elapsed_time": "2:15:14", "remaining_time": "4:54:26", "throughput": 1488.11, "total_tokens": 12074848} {"current_steps": 57225, "total_steps": 181800, "loss": 0.1052, "lr": 4.3297913150645264e-05, "epoch": 6.295379537953796, "percentage": 31.48, "elapsed_time": "2:15:14", "remaining_time": "4:54:25", "throughput": 1488.11, "total_tokens": 12075872} {"current_steps": 57230, "total_steps": 181800, "loss": 0.1087, "lr": 4.3296277673844496e-05, "epoch": 6.295929592959296, "percentage": 31.48, "elapsed_time": "2:15:15", "remaining_time": "4:54:24", "throughput": 1488.11, "total_tokens": 12076928} {"current_steps": 57235, "total_steps": 181800, "loss": 0.0246, "lr": 4.3294642028415725e-05, "epoch": 6.296479647964796, "percentage": 31.48, "elapsed_time": "2:15:16", "remaining_time": "4:54:24", "throughput": 1488.11, "total_tokens": 12077920} {"current_steps": 57240, "total_steps": 181800, "loss": 0.0549, "lr": 4.329300621437401e-05, "epoch": 6.297029702970297, "percentage": 31.49, "elapsed_time": "2:15:17", "remaining_time": "4:54:23", "throughput": 1488.08, "total_tokens": 12079008} {"current_steps": 57245, "total_steps": 181800, "loss": 0.0251, "lr": 4.329137023173444e-05, "epoch": 6.2975797579757975, "percentage": 31.49, "elapsed_time": "2:15:17", "remaining_time": "4:54:22", "throughput": 1488.09, "total_tokens": 12080096} {"current_steps": 57250, "total_steps": 181800, "loss": 0.0108, "lr": 4.328973408051209e-05, "epoch": 6.298129812981298, "percentage": 31.49, "elapsed_time": "2:15:18", "remaining_time": "4:54:22", "throughput": 1488.1, "total_tokens": 12081152} {"current_steps": 57255, "total_steps": 181800, "loss": 0.0325, "lr": 4.328809776072203e-05, "epoch": 6.298679867986799, "percentage": 31.49, "elapsed_time": "2:15:19", "remaining_time": "4:54:21", "throughput": 1488.1, "total_tokens": 12082176} {"current_steps": 57260, "total_steps": 181800, "loss": 0.0415, "lr": 4.3286461272379355e-05, "epoch": 6.299229922992299, "percentage": 31.5, "elapsed_time": "2:15:19", "remaining_time": "4:54:20", "throughput": 1488.09, "total_tokens": 12083168} {"current_steps": 57265, "total_steps": 181800, "loss": 0.0493, "lr": 4.328482461549914e-05, "epoch": 6.2997799779978, "percentage": 31.5, "elapsed_time": "2:15:20", "remaining_time": "4:54:19", "throughput": 1488.09, "total_tokens": 12084160} {"current_steps": 57270, "total_steps": 181800, "loss": 0.0821, "lr": 4.328318779009647e-05, "epoch": 6.3003300330033, "percentage": 31.5, "elapsed_time": "2:15:21", "remaining_time": "4:54:19", "throughput": 1488.1, "total_tokens": 12085248} {"current_steps": 57275, "total_steps": 181800, "loss": 0.0395, "lr": 4.3281550796186426e-05, "epoch": 6.3008800880088005, "percentage": 31.5, "elapsed_time": "2:15:21", "remaining_time": "4:54:18", "throughput": 1488.1, "total_tokens": 12086304} {"current_steps": 57280, "total_steps": 181800, "loss": 0.0052, "lr": 4.327991363378411e-05, "epoch": 6.301430143014302, "percentage": 31.51, "elapsed_time": "2:15:22", "remaining_time": "4:54:17", "throughput": 1488.1, "total_tokens": 12087360} {"current_steps": 57285, "total_steps": 181800, "loss": 0.1377, "lr": 4.327827630290459e-05, "epoch": 6.301980198019802, "percentage": 31.51, "elapsed_time": "2:15:23", "remaining_time": "4:54:16", "throughput": 1488.1, "total_tokens": 12088384} {"current_steps": 57290, "total_steps": 181800, "loss": 0.018, "lr": 4.3276638803562975e-05, "epoch": 6.302530253025303, "percentage": 31.51, "elapsed_time": "2:15:24", "remaining_time": "4:54:16", "throughput": 1488.11, "total_tokens": 12089504} {"current_steps": 57295, "total_steps": 181800, "loss": 0.0573, "lr": 4.327500113577435e-05, "epoch": 6.303080308030803, "percentage": 31.52, "elapsed_time": "2:15:24", "remaining_time": "4:54:15", "throughput": 1488.11, "total_tokens": 12090528} {"current_steps": 57300, "total_steps": 181800, "loss": 0.0097, "lr": 4.327336329955381e-05, "epoch": 6.303630363036303, "percentage": 31.52, "elapsed_time": "2:15:25", "remaining_time": "4:54:14", "throughput": 1488.11, "total_tokens": 12091552} {"current_steps": 57305, "total_steps": 181800, "loss": 0.0306, "lr": 4.3271725294916445e-05, "epoch": 6.304180418041804, "percentage": 31.52, "elapsed_time": "2:15:26", "remaining_time": "4:54:13", "throughput": 1488.12, "total_tokens": 12092608} {"current_steps": 57310, "total_steps": 181800, "loss": 0.0318, "lr": 4.327008712187736e-05, "epoch": 6.304730473047305, "percentage": 31.52, "elapsed_time": "2:15:26", "remaining_time": "4:54:13", "throughput": 1488.12, "total_tokens": 12093664} {"current_steps": 57315, "total_steps": 181800, "loss": 0.0041, "lr": 4.326844878045164e-05, "epoch": 6.305280528052805, "percentage": 31.53, "elapsed_time": "2:15:27", "remaining_time": "4:54:12", "throughput": 1488.13, "total_tokens": 12094784} {"current_steps": 57320, "total_steps": 181800, "loss": 0.0185, "lr": 4.32668102706544e-05, "epoch": 6.305830583058306, "percentage": 31.53, "elapsed_time": "2:15:28", "remaining_time": "4:54:11", "throughput": 1488.13, "total_tokens": 12095776} {"current_steps": 57325, "total_steps": 181800, "loss": 0.0145, "lr": 4.326517159250074e-05, "epoch": 6.306380638063806, "percentage": 31.53, "elapsed_time": "2:15:28", "remaining_time": "4:54:10", "throughput": 1488.12, "total_tokens": 12096768} {"current_steps": 57330, "total_steps": 181800, "loss": 0.0383, "lr": 4.326353274600575e-05, "epoch": 6.306930693069307, "percentage": 31.53, "elapsed_time": "2:15:29", "remaining_time": "4:54:10", "throughput": 1488.12, "total_tokens": 12097792} {"current_steps": 57335, "total_steps": 181800, "loss": 0.0117, "lr": 4.326189373118454e-05, "epoch": 6.307480748074807, "percentage": 31.54, "elapsed_time": "2:15:30", "remaining_time": "4:54:09", "throughput": 1488.13, "total_tokens": 12098880} {"current_steps": 57340, "total_steps": 181800, "loss": 0.0205, "lr": 4.326025454805223e-05, "epoch": 6.3080308030803085, "percentage": 31.54, "elapsed_time": "2:15:30", "remaining_time": "4:54:08", "throughput": 1488.13, "total_tokens": 12099936} {"current_steps": 57345, "total_steps": 181800, "loss": 0.0595, "lr": 4.325861519662391e-05, "epoch": 6.308580858085809, "percentage": 31.54, "elapsed_time": "2:15:31", "remaining_time": "4:54:08", "throughput": 1488.14, "total_tokens": 12101056} {"current_steps": 57350, "total_steps": 181800, "loss": 0.0191, "lr": 4.3256975676914695e-05, "epoch": 6.309130913091309, "percentage": 31.55, "elapsed_time": "2:15:32", "remaining_time": "4:54:07", "throughput": 1488.15, "total_tokens": 12102112} {"current_steps": 57355, "total_steps": 181800, "loss": 0.0248, "lr": 4.325533598893969e-05, "epoch": 6.30968096809681, "percentage": 31.55, "elapsed_time": "2:15:33", "remaining_time": "4:54:06", "throughput": 1488.15, "total_tokens": 12103168} {"current_steps": 57360, "total_steps": 181800, "loss": 0.1197, "lr": 4.325369613271403e-05, "epoch": 6.31023102310231, "percentage": 31.55, "elapsed_time": "2:15:33", "remaining_time": "4:54:05", "throughput": 1488.14, "total_tokens": 12104160} {"current_steps": 57365, "total_steps": 181800, "loss": 0.1016, "lr": 4.3252056108252795e-05, "epoch": 6.31078107810781, "percentage": 31.55, "elapsed_time": "2:15:34", "remaining_time": "4:54:05", "throughput": 1488.14, "total_tokens": 12105184} {"current_steps": 57370, "total_steps": 181800, "loss": 0.0305, "lr": 4.3250415915571116e-05, "epoch": 6.3113311331133115, "percentage": 31.56, "elapsed_time": "2:15:35", "remaining_time": "4:54:04", "throughput": 1488.14, "total_tokens": 12106144} {"current_steps": 57375, "total_steps": 181800, "loss": 0.0171, "lr": 4.324877555468412e-05, "epoch": 6.311881188118812, "percentage": 31.56, "elapsed_time": "2:15:35", "remaining_time": "4:54:03", "throughput": 1488.14, "total_tokens": 12107200} {"current_steps": 57380, "total_steps": 181800, "loss": 0.0304, "lr": 4.3247135025606914e-05, "epoch": 6.312431243124313, "percentage": 31.56, "elapsed_time": "2:15:36", "remaining_time": "4:54:02", "throughput": 1488.14, "total_tokens": 12108224} {"current_steps": 57385, "total_steps": 181800, "loss": 0.0568, "lr": 4.324549432835463e-05, "epoch": 6.312981298129813, "percentage": 31.56, "elapsed_time": "2:15:37", "remaining_time": "4:54:02", "throughput": 1488.14, "total_tokens": 12109248} {"current_steps": 57390, "total_steps": 181800, "loss": 0.0051, "lr": 4.324385346294236e-05, "epoch": 6.313531353135313, "percentage": 31.57, "elapsed_time": "2:15:37", "remaining_time": "4:54:01", "throughput": 1488.14, "total_tokens": 12110240} {"current_steps": 57395, "total_steps": 181800, "loss": 0.0305, "lr": 4.324221242938526e-05, "epoch": 6.314081408140814, "percentage": 31.57, "elapsed_time": "2:15:38", "remaining_time": "4:54:00", "throughput": 1488.13, "total_tokens": 12111200} {"current_steps": 57400, "total_steps": 181800, "loss": 0.1356, "lr": 4.3240571227698436e-05, "epoch": 6.3146314631463145, "percentage": 31.57, "elapsed_time": "2:15:39", "remaining_time": "4:53:59", "throughput": 1488.13, "total_tokens": 12112256} {"current_steps": 57405, "total_steps": 181800, "loss": 0.0846, "lr": 4.323892985789702e-05, "epoch": 6.315181518151816, "percentage": 31.58, "elapsed_time": "2:15:39", "remaining_time": "4:53:59", "throughput": 1488.13, "total_tokens": 12113312} {"current_steps": 57410, "total_steps": 181800, "loss": 0.083, "lr": 4.3237288319996146e-05, "epoch": 6.315731573157316, "percentage": 31.58, "elapsed_time": "2:15:40", "remaining_time": "4:53:58", "throughput": 1488.13, "total_tokens": 12114304} {"current_steps": 57415, "total_steps": 181800, "loss": 0.0273, "lr": 4.3235646614010926e-05, "epoch": 6.316281628162816, "percentage": 31.58, "elapsed_time": "2:15:41", "remaining_time": "4:53:57", "throughput": 1488.14, "total_tokens": 12115424} {"current_steps": 57420, "total_steps": 181800, "loss": 0.1645, "lr": 4.3234004739956515e-05, "epoch": 6.316831683168317, "percentage": 31.58, "elapsed_time": "2:15:42", "remaining_time": "4:53:56", "throughput": 1488.14, "total_tokens": 12116416} {"current_steps": 57425, "total_steps": 181800, "loss": 0.1094, "lr": 4.3232362697848015e-05, "epoch": 6.317381738173817, "percentage": 31.59, "elapsed_time": "2:15:42", "remaining_time": "4:53:56", "throughput": 1488.14, "total_tokens": 12117472} {"current_steps": 57430, "total_steps": 181800, "loss": 0.0584, "lr": 4.323072048770059e-05, "epoch": 6.3179317931793175, "percentage": 31.59, "elapsed_time": "2:15:43", "remaining_time": "4:53:55", "throughput": 1488.15, "total_tokens": 12118592} {"current_steps": 57435, "total_steps": 181800, "loss": 0.0215, "lr": 4.322907810952936e-05, "epoch": 6.318481848184819, "percentage": 31.59, "elapsed_time": "2:15:44", "remaining_time": "4:53:54", "throughput": 1488.15, "total_tokens": 12119648} {"current_steps": 57440, "total_steps": 181800, "loss": 0.06, "lr": 4.322743556334946e-05, "epoch": 6.319031903190319, "percentage": 31.6, "elapsed_time": "2:15:44", "remaining_time": "4:53:53", "throughput": 1488.15, "total_tokens": 12120672} {"current_steps": 57445, "total_steps": 181800, "loss": 0.0076, "lr": 4.3225792849176036e-05, "epoch": 6.31958195819582, "percentage": 31.6, "elapsed_time": "2:15:45", "remaining_time": "4:53:53", "throughput": 1488.15, "total_tokens": 12121664} {"current_steps": 57450, "total_steps": 181800, "loss": 0.1102, "lr": 4.3224149967024216e-05, "epoch": 6.32013201320132, "percentage": 31.6, "elapsed_time": "2:15:46", "remaining_time": "4:53:52", "throughput": 1488.15, "total_tokens": 12122720} {"current_steps": 57455, "total_steps": 181800, "loss": 0.0355, "lr": 4.3222506916909165e-05, "epoch": 6.32068206820682, "percentage": 31.6, "elapsed_time": "2:15:46", "remaining_time": "4:53:51", "throughput": 1488.15, "total_tokens": 12123712} {"current_steps": 57460, "total_steps": 181800, "loss": 0.0913, "lr": 4.3220863698846e-05, "epoch": 6.321232123212321, "percentage": 31.61, "elapsed_time": "2:15:47", "remaining_time": "4:53:50", "throughput": 1488.15, "total_tokens": 12124768} {"current_steps": 57465, "total_steps": 181800, "loss": 0.0501, "lr": 4.321922031284989e-05, "epoch": 6.321782178217822, "percentage": 31.61, "elapsed_time": "2:15:48", "remaining_time": "4:53:50", "throughput": 1488.16, "total_tokens": 12125824} {"current_steps": 57470, "total_steps": 181800, "loss": 0.049, "lr": 4.321757675893596e-05, "epoch": 6.322332233223323, "percentage": 31.61, "elapsed_time": "2:15:48", "remaining_time": "4:53:49", "throughput": 1488.17, "total_tokens": 12126944} {"current_steps": 57475, "total_steps": 181800, "loss": 0.0578, "lr": 4.321593303711937e-05, "epoch": 6.322882288228823, "percentage": 31.61, "elapsed_time": "2:15:49", "remaining_time": "4:53:48", "throughput": 1488.17, "total_tokens": 12128000} {"current_steps": 57480, "total_steps": 181800, "loss": 0.0309, "lr": 4.321428914741526e-05, "epoch": 6.323432343234323, "percentage": 31.62, "elapsed_time": "2:15:50", "remaining_time": "4:53:47", "throughput": 1488.18, "total_tokens": 12129088} {"current_steps": 57485, "total_steps": 181800, "loss": 0.0181, "lr": 4.321264508983879e-05, "epoch": 6.323982398239824, "percentage": 31.62, "elapsed_time": "2:15:50", "remaining_time": "4:53:47", "throughput": 1488.18, "total_tokens": 12130144} {"current_steps": 57490, "total_steps": 181800, "loss": 0.0205, "lr": 4.3211000864405115e-05, "epoch": 6.324532453245324, "percentage": 31.62, "elapsed_time": "2:15:51", "remaining_time": "4:53:46", "throughput": 1488.19, "total_tokens": 12131232} {"current_steps": 57495, "total_steps": 181800, "loss": 0.0368, "lr": 4.320935647112938e-05, "epoch": 6.325082508250825, "percentage": 31.63, "elapsed_time": "2:15:52", "remaining_time": "4:53:45", "throughput": 1488.19, "total_tokens": 12132256} {"current_steps": 57500, "total_steps": 181800, "loss": 0.0572, "lr": 4.320771191002674e-05, "epoch": 6.325632563256326, "percentage": 31.63, "elapsed_time": "2:15:53", "remaining_time": "4:53:44", "throughput": 1488.2, "total_tokens": 12133344} {"current_steps": 57505, "total_steps": 181800, "loss": 0.0102, "lr": 4.3206067181112364e-05, "epoch": 6.326182618261826, "percentage": 31.63, "elapsed_time": "2:15:53", "remaining_time": "4:53:44", "throughput": 1488.2, "total_tokens": 12134432} {"current_steps": 57510, "total_steps": 181800, "loss": 0.0191, "lr": 4.320442228440139e-05, "epoch": 6.326732673267327, "percentage": 31.63, "elapsed_time": "2:15:54", "remaining_time": "4:53:43", "throughput": 1488.2, "total_tokens": 12135456} {"current_steps": 57515, "total_steps": 181800, "loss": 0.1633, "lr": 4.320277721990901e-05, "epoch": 6.327282728272827, "percentage": 31.64, "elapsed_time": "2:15:55", "remaining_time": "4:53:42", "throughput": 1488.22, "total_tokens": 12136608} {"current_steps": 57520, "total_steps": 181800, "loss": 0.0112, "lr": 4.320113198765035e-05, "epoch": 6.327832783278327, "percentage": 31.64, "elapsed_time": "2:15:55", "remaining_time": "4:53:41", "throughput": 1488.22, "total_tokens": 12137664} {"current_steps": 57525, "total_steps": 181800, "loss": 0.0382, "lr": 4.31994865876406e-05, "epoch": 6.3283828382838285, "percentage": 31.64, "elapsed_time": "2:15:56", "remaining_time": "4:53:41", "throughput": 1488.22, "total_tokens": 12138688} {"current_steps": 57530, "total_steps": 181800, "loss": 0.0173, "lr": 4.3197841019894914e-05, "epoch": 6.328932893289329, "percentage": 31.64, "elapsed_time": "2:15:57", "remaining_time": "4:53:40", "throughput": 1488.22, "total_tokens": 12139712} {"current_steps": 57535, "total_steps": 181800, "loss": 0.0631, "lr": 4.319619528442845e-05, "epoch": 6.32948294829483, "percentage": 31.65, "elapsed_time": "2:15:57", "remaining_time": "4:53:39", "throughput": 1488.23, "total_tokens": 12140800} {"current_steps": 57540, "total_steps": 181800, "loss": 0.048, "lr": 4.31945493812564e-05, "epoch": 6.33003300330033, "percentage": 31.65, "elapsed_time": "2:15:58", "remaining_time": "4:53:38", "throughput": 1488.23, "total_tokens": 12141856} {"current_steps": 57545, "total_steps": 181800, "loss": 0.0414, "lr": 4.319290331039391e-05, "epoch": 6.33058305830583, "percentage": 31.65, "elapsed_time": "2:15:59", "remaining_time": "4:53:38", "throughput": 1488.24, "total_tokens": 12142944} {"current_steps": 57550, "total_steps": 181800, "loss": 0.0951, "lr": 4.319125707185616e-05, "epoch": 6.331133113311331, "percentage": 31.66, "elapsed_time": "2:15:59", "remaining_time": "4:53:37", "throughput": 1488.25, "total_tokens": 12144032} {"current_steps": 57555, "total_steps": 181800, "loss": 0.0793, "lr": 4.318961066565832e-05, "epoch": 6.3316831683168315, "percentage": 31.66, "elapsed_time": "2:16:00", "remaining_time": "4:53:36", "throughput": 1488.25, "total_tokens": 12145088} {"current_steps": 57560, "total_steps": 181800, "loss": 0.0052, "lr": 4.3187964091815575e-05, "epoch": 6.332233223322333, "percentage": 31.66, "elapsed_time": "2:16:01", "remaining_time": "4:53:35", "throughput": 1488.25, "total_tokens": 12146112} {"current_steps": 57565, "total_steps": 181800, "loss": 0.0129, "lr": 4.318631735034308e-05, "epoch": 6.332783278327833, "percentage": 31.66, "elapsed_time": "2:16:02", "remaining_time": "4:53:35", "throughput": 1488.25, "total_tokens": 12147168} {"current_steps": 57570, "total_steps": 181800, "loss": 0.1708, "lr": 4.3184670441256045e-05, "epoch": 6.333333333333333, "percentage": 31.67, "elapsed_time": "2:16:02", "remaining_time": "4:53:34", "throughput": 1488.25, "total_tokens": 12148160} {"current_steps": 57575, "total_steps": 181800, "loss": 0.0205, "lr": 4.3183023364569614e-05, "epoch": 6.333883388338834, "percentage": 31.67, "elapsed_time": "2:16:03", "remaining_time": "4:53:33", "throughput": 1488.25, "total_tokens": 12149184} {"current_steps": 57580, "total_steps": 181800, "loss": 0.0132, "lr": 4.318137612029898e-05, "epoch": 6.334433443344334, "percentage": 31.67, "elapsed_time": "2:16:04", "remaining_time": "4:53:32", "throughput": 1488.25, "total_tokens": 12150240} {"current_steps": 57585, "total_steps": 181800, "loss": 0.0071, "lr": 4.317972870845933e-05, "epoch": 6.334983498349835, "percentage": 31.67, "elapsed_time": "2:16:04", "remaining_time": "4:53:32", "throughput": 1488.26, "total_tokens": 12151328} {"current_steps": 57590, "total_steps": 181800, "loss": 0.141, "lr": 4.317808112906585e-05, "epoch": 6.335533553355336, "percentage": 31.68, "elapsed_time": "2:16:05", "remaining_time": "4:53:31", "throughput": 1488.27, "total_tokens": 12152416} {"current_steps": 57595, "total_steps": 181800, "loss": 0.0954, "lr": 4.317643338213371e-05, "epoch": 6.336083608360836, "percentage": 31.68, "elapsed_time": "2:16:06", "remaining_time": "4:53:30", "throughput": 1488.27, "total_tokens": 12153472} {"current_steps": 57600, "total_steps": 181800, "loss": 0.042, "lr": 4.317478546767811e-05, "epoch": 6.336633663366337, "percentage": 31.68, "elapsed_time": "2:16:06", "remaining_time": "4:53:29", "throughput": 1488.28, "total_tokens": 12154560} {"current_steps": 57605, "total_steps": 181800, "loss": 0.0126, "lr": 4.3173137385714236e-05, "epoch": 6.337183718371837, "percentage": 31.69, "elapsed_time": "2:16:07", "remaining_time": "4:53:29", "throughput": 1488.28, "total_tokens": 12155584} {"current_steps": 57610, "total_steps": 181800, "loss": 0.0102, "lr": 4.317148913625727e-05, "epoch": 6.337733773377337, "percentage": 31.69, "elapsed_time": "2:16:08", "remaining_time": "4:53:28", "throughput": 1488.29, "total_tokens": 12156672} {"current_steps": 57615, "total_steps": 181800, "loss": 0.0158, "lr": 4.3169840719322406e-05, "epoch": 6.338283828382838, "percentage": 31.69, "elapsed_time": "2:16:08", "remaining_time": "4:53:27", "throughput": 1488.29, "total_tokens": 12157728} {"current_steps": 57620, "total_steps": 181800, "loss": 0.0095, "lr": 4.316819213492484e-05, "epoch": 6.338833883388339, "percentage": 31.69, "elapsed_time": "2:16:09", "remaining_time": "4:53:26", "throughput": 1488.29, "total_tokens": 12158752} {"current_steps": 57625, "total_steps": 181800, "loss": 0.0037, "lr": 4.316654338307977e-05, "epoch": 6.33938393839384, "percentage": 31.7, "elapsed_time": "2:16:10", "remaining_time": "4:53:25", "throughput": 1488.3, "total_tokens": 12159808} {"current_steps": 57630, "total_steps": 181800, "loss": 0.0253, "lr": 4.3164894463802385e-05, "epoch": 6.33993399339934, "percentage": 31.7, "elapsed_time": "2:16:10", "remaining_time": "4:53:25", "throughput": 1488.3, "total_tokens": 12160864} {"current_steps": 57635, "total_steps": 181800, "loss": 0.0249, "lr": 4.316324537710789e-05, "epoch": 6.34048404840484, "percentage": 31.7, "elapsed_time": "2:16:11", "remaining_time": "4:53:24", "throughput": 1488.3, "total_tokens": 12161920} {"current_steps": 57640, "total_steps": 181800, "loss": 0.0728, "lr": 4.3161596123011464e-05, "epoch": 6.341034103410341, "percentage": 31.71, "elapsed_time": "2:16:12", "remaining_time": "4:53:23", "throughput": 1488.3, "total_tokens": 12162944} {"current_steps": 57645, "total_steps": 181800, "loss": 0.0483, "lr": 4.315994670152833e-05, "epoch": 6.341584158415841, "percentage": 31.71, "elapsed_time": "2:16:13", "remaining_time": "4:53:22", "throughput": 1488.3, "total_tokens": 12163968} {"current_steps": 57650, "total_steps": 181800, "loss": 0.0732, "lr": 4.3158297112673686e-05, "epoch": 6.3421342134213425, "percentage": 31.71, "elapsed_time": "2:16:13", "remaining_time": "4:53:22", "throughput": 1488.31, "total_tokens": 12165024} {"current_steps": 57655, "total_steps": 181800, "loss": 0.0101, "lr": 4.315664735646272e-05, "epoch": 6.342684268426843, "percentage": 31.71, "elapsed_time": "2:16:14", "remaining_time": "4:53:21", "throughput": 1488.31, "total_tokens": 12166080} {"current_steps": 57660, "total_steps": 181800, "loss": 0.0119, "lr": 4.3154997432910646e-05, "epoch": 6.343234323432343, "percentage": 31.72, "elapsed_time": "2:16:15", "remaining_time": "4:53:20", "throughput": 1488.32, "total_tokens": 12167168} {"current_steps": 57665, "total_steps": 181800, "loss": 0.1044, "lr": 4.3153347342032684e-05, "epoch": 6.343784378437844, "percentage": 31.72, "elapsed_time": "2:16:15", "remaining_time": "4:53:19", "throughput": 1488.33, "total_tokens": 12168256} {"current_steps": 57670, "total_steps": 181800, "loss": 0.0137, "lr": 4.3151697083844025e-05, "epoch": 6.344334433443344, "percentage": 31.72, "elapsed_time": "2:16:16", "remaining_time": "4:53:19", "throughput": 1488.32, "total_tokens": 12169248} {"current_steps": 57675, "total_steps": 181800, "loss": 0.0885, "lr": 4.315004665835988e-05, "epoch": 6.3448844884488445, "percentage": 31.72, "elapsed_time": "2:16:17", "remaining_time": "4:53:18", "throughput": 1488.32, "total_tokens": 12170272} {"current_steps": 57680, "total_steps": 181800, "loss": 0.0873, "lr": 4.3148396065595476e-05, "epoch": 6.3454345434543455, "percentage": 31.73, "elapsed_time": "2:16:17", "remaining_time": "4:53:17", "throughput": 1488.32, "total_tokens": 12171296} {"current_steps": 57685, "total_steps": 181800, "loss": 0.0412, "lr": 4.3146745305566005e-05, "epoch": 6.345984598459846, "percentage": 31.73, "elapsed_time": "2:16:18", "remaining_time": "4:53:16", "throughput": 1488.32, "total_tokens": 12172352} {"current_steps": 57690, "total_steps": 181800, "loss": 0.0039, "lr": 4.314509437828669e-05, "epoch": 6.346534653465347, "percentage": 31.73, "elapsed_time": "2:16:19", "remaining_time": "4:53:16", "throughput": 1488.32, "total_tokens": 12173376} {"current_steps": 57695, "total_steps": 181800, "loss": 0.0257, "lr": 4.314344328377274e-05, "epoch": 6.347084708470847, "percentage": 31.74, "elapsed_time": "2:16:19", "remaining_time": "4:53:15", "throughput": 1488.32, "total_tokens": 12174400} {"current_steps": 57700, "total_steps": 181800, "loss": 0.018, "lr": 4.3141792022039396e-05, "epoch": 6.347634763476347, "percentage": 31.74, "elapsed_time": "2:16:20", "remaining_time": "4:53:14", "throughput": 1488.34, "total_tokens": 12175584} {"current_steps": 57705, "total_steps": 181800, "loss": 0.015, "lr": 4.3140140593101855e-05, "epoch": 6.348184818481848, "percentage": 31.74, "elapsed_time": "2:16:21", "remaining_time": "4:53:13", "throughput": 1488.34, "total_tokens": 12176608} {"current_steps": 57710, "total_steps": 181800, "loss": 0.0625, "lr": 4.313848899697534e-05, "epoch": 6.3487348734873486, "percentage": 31.74, "elapsed_time": "2:16:21", "remaining_time": "4:53:13", "throughput": 1488.35, "total_tokens": 12177664} {"current_steps": 57715, "total_steps": 181800, "loss": 0.224, "lr": 4.313683723367507e-05, "epoch": 6.34928492849285, "percentage": 31.75, "elapsed_time": "2:16:22", "remaining_time": "4:53:12", "throughput": 1488.36, "total_tokens": 12178752} {"current_steps": 57720, "total_steps": 181800, "loss": 0.0175, "lr": 4.313518530321628e-05, "epoch": 6.34983498349835, "percentage": 31.75, "elapsed_time": "2:16:23", "remaining_time": "4:53:11", "throughput": 1488.36, "total_tokens": 12179776} {"current_steps": 57725, "total_steps": 181800, "loss": 0.0285, "lr": 4.3133533205614185e-05, "epoch": 6.35038503850385, "percentage": 31.75, "elapsed_time": "2:16:24", "remaining_time": "4:53:10", "throughput": 1488.36, "total_tokens": 12180800} {"current_steps": 57730, "total_steps": 181800, "loss": 0.0111, "lr": 4.313188094088402e-05, "epoch": 6.350935093509351, "percentage": 31.75, "elapsed_time": "2:16:24", "remaining_time": "4:53:10", "throughput": 1488.36, "total_tokens": 12181856} {"current_steps": 57735, "total_steps": 181800, "loss": 0.0649, "lr": 4.313022850904101e-05, "epoch": 6.351485148514851, "percentage": 31.76, "elapsed_time": "2:16:25", "remaining_time": "4:53:09", "throughput": 1488.37, "total_tokens": 12182944} {"current_steps": 57740, "total_steps": 181800, "loss": 0.0439, "lr": 4.3128575910100375e-05, "epoch": 6.3520352035203524, "percentage": 31.76, "elapsed_time": "2:16:26", "remaining_time": "4:53:08", "throughput": 1488.37, "total_tokens": 12184000} {"current_steps": 57745, "total_steps": 181800, "loss": 0.0505, "lr": 4.312692314407737e-05, "epoch": 6.352585258525853, "percentage": 31.76, "elapsed_time": "2:16:26", "remaining_time": "4:53:07", "throughput": 1488.38, "total_tokens": 12185088} {"current_steps": 57750, "total_steps": 181800, "loss": 0.0181, "lr": 4.31252702109872e-05, "epoch": 6.353135313531353, "percentage": 31.77, "elapsed_time": "2:16:27", "remaining_time": "4:53:07", "throughput": 1488.38, "total_tokens": 12186144} {"current_steps": 57755, "total_steps": 181800, "loss": 0.0378, "lr": 4.312361711084512e-05, "epoch": 6.353685368536854, "percentage": 31.77, "elapsed_time": "2:16:28", "remaining_time": "4:53:06", "throughput": 1488.4, "total_tokens": 12187264} {"current_steps": 57760, "total_steps": 181800, "loss": 0.0875, "lr": 4.312196384366635e-05, "epoch": 6.354235423542354, "percentage": 31.77, "elapsed_time": "2:16:28", "remaining_time": "4:53:05", "throughput": 1488.4, "total_tokens": 12188320} {"current_steps": 57765, "total_steps": 181800, "loss": 0.0038, "lr": 4.312031040946614e-05, "epoch": 6.354785478547855, "percentage": 31.77, "elapsed_time": "2:16:29", "remaining_time": "4:53:04", "throughput": 1488.4, "total_tokens": 12189344} {"current_steps": 57770, "total_steps": 181800, "loss": 0.0373, "lr": 4.311865680825971e-05, "epoch": 6.3553355335533555, "percentage": 31.78, "elapsed_time": "2:16:30", "remaining_time": "4:53:04", "throughput": 1488.4, "total_tokens": 12190400} {"current_steps": 57775, "total_steps": 181800, "loss": 0.1152, "lr": 4.311700304006233e-05, "epoch": 6.355885588558856, "percentage": 31.78, "elapsed_time": "2:16:30", "remaining_time": "4:53:03", "throughput": 1488.41, "total_tokens": 12191488} {"current_steps": 57780, "total_steps": 181800, "loss": 0.0054, "lr": 4.311534910488923e-05, "epoch": 6.356435643564357, "percentage": 31.78, "elapsed_time": "2:16:31", "remaining_time": "4:53:02", "throughput": 1488.41, "total_tokens": 12192544} {"current_steps": 57785, "total_steps": 181800, "loss": 0.0162, "lr": 4.3113695002755635e-05, "epoch": 6.356985698569857, "percentage": 31.78, "elapsed_time": "2:16:32", "remaining_time": "4:53:01", "throughput": 1488.41, "total_tokens": 12193568} {"current_steps": 57790, "total_steps": 181800, "loss": 0.0418, "lr": 4.311204073367682e-05, "epoch": 6.357535753575357, "percentage": 31.79, "elapsed_time": "2:16:33", "remaining_time": "4:53:01", "throughput": 1488.41, "total_tokens": 12194592} {"current_steps": 57795, "total_steps": 181800, "loss": 0.047, "lr": 4.311038629766801e-05, "epoch": 6.358085808580858, "percentage": 31.79, "elapsed_time": "2:16:33", "remaining_time": "4:53:00", "throughput": 1488.42, "total_tokens": 12195648} {"current_steps": 57800, "total_steps": 181800, "loss": 0.1455, "lr": 4.310873169474446e-05, "epoch": 6.3586358635863585, "percentage": 31.79, "elapsed_time": "2:16:34", "remaining_time": "4:52:59", "throughput": 1488.42, "total_tokens": 12196704} {"current_steps": 57805, "total_steps": 181800, "loss": 0.0999, "lr": 4.310707692492142e-05, "epoch": 6.3591859185918596, "percentage": 31.8, "elapsed_time": "2:16:35", "remaining_time": "4:52:58", "throughput": 1488.43, "total_tokens": 12197856} {"current_steps": 57810, "total_steps": 181800, "loss": 0.0415, "lr": 4.3105421988214135e-05, "epoch": 6.35973597359736, "percentage": 31.8, "elapsed_time": "2:16:35", "remaining_time": "4:52:58", "throughput": 1488.44, "total_tokens": 12198912} {"current_steps": 57815, "total_steps": 181800, "loss": 0.0685, "lr": 4.310376688463787e-05, "epoch": 6.36028602860286, "percentage": 31.8, "elapsed_time": "2:16:36", "remaining_time": "4:52:57", "throughput": 1488.44, "total_tokens": 12199936} {"current_steps": 57820, "total_steps": 181800, "loss": 0.0174, "lr": 4.310211161420787e-05, "epoch": 6.360836083608361, "percentage": 31.8, "elapsed_time": "2:16:37", "remaining_time": "4:52:56", "throughput": 1488.44, "total_tokens": 12200960} {"current_steps": 57825, "total_steps": 181800, "loss": 0.0412, "lr": 4.3100456176939394e-05, "epoch": 6.361386138613861, "percentage": 31.81, "elapsed_time": "2:16:37", "remaining_time": "4:52:55", "throughput": 1488.44, "total_tokens": 12201984} {"current_steps": 57830, "total_steps": 181800, "loss": 0.0673, "lr": 4.30988005728477e-05, "epoch": 6.361936193619362, "percentage": 31.81, "elapsed_time": "2:16:38", "remaining_time": "4:52:55", "throughput": 1488.44, "total_tokens": 12203040} {"current_steps": 57835, "total_steps": 181800, "loss": 0.0056, "lr": 4.3097144801948045e-05, "epoch": 6.362486248624863, "percentage": 31.81, "elapsed_time": "2:16:39", "remaining_time": "4:52:54", "throughput": 1488.44, "total_tokens": 12204096} {"current_steps": 57840, "total_steps": 181800, "loss": 0.0882, "lr": 4.309548886425568e-05, "epoch": 6.363036303630363, "percentage": 31.82, "elapsed_time": "2:16:39", "remaining_time": "4:52:53", "throughput": 1488.46, "total_tokens": 12205216} {"current_steps": 57845, "total_steps": 181800, "loss": 0.1251, "lr": 4.309383275978589e-05, "epoch": 6.363586358635864, "percentage": 31.82, "elapsed_time": "2:16:40", "remaining_time": "4:52:52", "throughput": 1488.46, "total_tokens": 12206240} {"current_steps": 57850, "total_steps": 181800, "loss": 0.0394, "lr": 4.309217648855393e-05, "epoch": 6.364136413641364, "percentage": 31.82, "elapsed_time": "2:16:41", "remaining_time": "4:52:52", "throughput": 1488.46, "total_tokens": 12207296} {"current_steps": 57855, "total_steps": 181800, "loss": 0.0692, "lr": 4.309052005057505e-05, "epoch": 6.364686468646864, "percentage": 31.82, "elapsed_time": "2:16:41", "remaining_time": "4:52:51", "throughput": 1488.46, "total_tokens": 12208352} {"current_steps": 57860, "total_steps": 181800, "loss": 0.04, "lr": 4.308886344586452e-05, "epoch": 6.365236523652365, "percentage": 31.83, "elapsed_time": "2:16:42", "remaining_time": "4:52:50", "throughput": 1488.48, "total_tokens": 12209504} {"current_steps": 57865, "total_steps": 181800, "loss": 0.1148, "lr": 4.308720667443763e-05, "epoch": 6.365786578657866, "percentage": 31.83, "elapsed_time": "2:16:43", "remaining_time": "4:52:49", "throughput": 1488.49, "total_tokens": 12210592} {"current_steps": 57870, "total_steps": 181800, "loss": 0.0988, "lr": 4.3085549736309634e-05, "epoch": 6.366336633663367, "percentage": 31.83, "elapsed_time": "2:16:44", "remaining_time": "4:52:49", "throughput": 1488.49, "total_tokens": 12211648} {"current_steps": 57875, "total_steps": 181800, "loss": 0.0207, "lr": 4.3083892631495806e-05, "epoch": 6.366886688668867, "percentage": 31.83, "elapsed_time": "2:16:44", "remaining_time": "4:52:48", "throughput": 1488.5, "total_tokens": 12212736} {"current_steps": 57880, "total_steps": 181800, "loss": 0.0253, "lr": 4.3082235360011406e-05, "epoch": 6.367436743674367, "percentage": 31.84, "elapsed_time": "2:16:45", "remaining_time": "4:52:47", "throughput": 1488.5, "total_tokens": 12213792} {"current_steps": 57885, "total_steps": 181800, "loss": 0.0132, "lr": 4.308057792187173e-05, "epoch": 6.367986798679868, "percentage": 31.84, "elapsed_time": "2:16:46", "remaining_time": "4:52:46", "throughput": 1488.51, "total_tokens": 12214880} {"current_steps": 57890, "total_steps": 181800, "loss": 0.0784, "lr": 4.307892031709204e-05, "epoch": 6.368536853685368, "percentage": 31.84, "elapsed_time": "2:16:46", "remaining_time": "4:52:46", "throughput": 1488.5, "total_tokens": 12215872} {"current_steps": 57895, "total_steps": 181800, "loss": 0.0272, "lr": 4.307726254568761e-05, "epoch": 6.3690869086908695, "percentage": 31.85, "elapsed_time": "2:16:47", "remaining_time": "4:52:45", "throughput": 1488.5, "total_tokens": 12216896} {"current_steps": 57900, "total_steps": 181800, "loss": 0.0967, "lr": 4.307560460767374e-05, "epoch": 6.36963696369637, "percentage": 31.85, "elapsed_time": "2:16:48", "remaining_time": "4:52:44", "throughput": 1488.51, "total_tokens": 12217984} {"current_steps": 57905, "total_steps": 181800, "loss": 0.0217, "lr": 4.307394650306568e-05, "epoch": 6.37018701870187, "percentage": 31.85, "elapsed_time": "2:16:48", "remaining_time": "4:52:43", "throughput": 1488.52, "total_tokens": 12219040} {"current_steps": 57910, "total_steps": 181800, "loss": 0.0368, "lr": 4.307228823187874e-05, "epoch": 6.370737073707371, "percentage": 31.85, "elapsed_time": "2:16:49", "remaining_time": "4:52:43", "throughput": 1488.52, "total_tokens": 12220096} {"current_steps": 57915, "total_steps": 181800, "loss": 0.0633, "lr": 4.3070629794128184e-05, "epoch": 6.371287128712871, "percentage": 31.86, "elapsed_time": "2:16:50", "remaining_time": "4:52:42", "throughput": 1488.52, "total_tokens": 12221120} {"current_steps": 57920, "total_steps": 181800, "loss": 0.0152, "lr": 4.3068971189829304e-05, "epoch": 6.371837183718371, "percentage": 31.86, "elapsed_time": "2:16:50", "remaining_time": "4:52:41", "throughput": 1488.52, "total_tokens": 12222176} {"current_steps": 57925, "total_steps": 181800, "loss": 0.0143, "lr": 4.306731241899739e-05, "epoch": 6.3723872387238725, "percentage": 31.86, "elapsed_time": "2:16:51", "remaining_time": "4:52:40", "throughput": 1488.52, "total_tokens": 12223200} {"current_steps": 57930, "total_steps": 181800, "loss": 0.0313, "lr": 4.306565348164773e-05, "epoch": 6.372937293729373, "percentage": 31.86, "elapsed_time": "2:16:52", "remaining_time": "4:52:40", "throughput": 1488.52, "total_tokens": 12224224} {"current_steps": 57935, "total_steps": 181800, "loss": 0.1084, "lr": 4.3063994377795604e-05, "epoch": 6.373487348734874, "percentage": 31.87, "elapsed_time": "2:16:53", "remaining_time": "4:52:39", "throughput": 1488.53, "total_tokens": 12225312} {"current_steps": 57940, "total_steps": 181800, "loss": 0.0178, "lr": 4.3062335107456306e-05, "epoch": 6.374037403740374, "percentage": 31.87, "elapsed_time": "2:16:53", "remaining_time": "4:52:38", "throughput": 1488.53, "total_tokens": 12226336} {"current_steps": 57945, "total_steps": 181800, "loss": 0.2292, "lr": 4.3060675670645144e-05, "epoch": 6.374587458745874, "percentage": 31.87, "elapsed_time": "2:16:54", "remaining_time": "4:52:37", "throughput": 1488.54, "total_tokens": 12227424} {"current_steps": 57950, "total_steps": 181800, "loss": 0.0157, "lr": 4.30590160673774e-05, "epoch": 6.375137513751375, "percentage": 31.88, "elapsed_time": "2:16:55", "remaining_time": "4:52:37", "throughput": 1488.54, "total_tokens": 12228448} {"current_steps": 57955, "total_steps": 181800, "loss": 0.0429, "lr": 4.305735629766836e-05, "epoch": 6.3756875687568755, "percentage": 31.88, "elapsed_time": "2:16:55", "remaining_time": "4:52:36", "throughput": 1488.53, "total_tokens": 12229472} {"current_steps": 57960, "total_steps": 181800, "loss": 0.0418, "lr": 4.305569636153334e-05, "epoch": 6.376237623762377, "percentage": 31.88, "elapsed_time": "2:16:56", "remaining_time": "4:52:35", "throughput": 1488.54, "total_tokens": 12230528} {"current_steps": 57965, "total_steps": 181800, "loss": 0.0471, "lr": 4.305403625898763e-05, "epoch": 6.376787678767877, "percentage": 31.88, "elapsed_time": "2:16:57", "remaining_time": "4:52:34", "throughput": 1488.53, "total_tokens": 12231520} {"current_steps": 57970, "total_steps": 181800, "loss": 0.0073, "lr": 4.305237599004653e-05, "epoch": 6.377337733773377, "percentage": 31.89, "elapsed_time": "2:16:57", "remaining_time": "4:52:34", "throughput": 1488.54, "total_tokens": 12232576} {"current_steps": 57975, "total_steps": 181800, "loss": 0.0089, "lr": 4.305071555472534e-05, "epoch": 6.377887788778878, "percentage": 31.89, "elapsed_time": "2:16:58", "remaining_time": "4:52:33", "throughput": 1488.53, "total_tokens": 12233568} {"current_steps": 57980, "total_steps": 181800, "loss": 0.076, "lr": 4.3049054953039366e-05, "epoch": 6.378437843784378, "percentage": 31.89, "elapsed_time": "2:16:59", "remaining_time": "4:52:32", "throughput": 1488.54, "total_tokens": 12234656} {"current_steps": 57985, "total_steps": 181800, "loss": 0.0703, "lr": 4.304739418500392e-05, "epoch": 6.378987898789879, "percentage": 31.89, "elapsed_time": "2:16:59", "remaining_time": "4:52:31", "throughput": 1488.55, "total_tokens": 12235712} {"current_steps": 57990, "total_steps": 181800, "loss": 0.013, "lr": 4.30457332506343e-05, "epoch": 6.37953795379538, "percentage": 31.9, "elapsed_time": "2:17:00", "remaining_time": "4:52:31", "throughput": 1488.55, "total_tokens": 12236800} {"current_steps": 57995, "total_steps": 181800, "loss": 0.1148, "lr": 4.304407214994581e-05, "epoch": 6.38008800880088, "percentage": 31.9, "elapsed_time": "2:17:01", "remaining_time": "4:52:30", "throughput": 1488.56, "total_tokens": 12237920} {"current_steps": 58000, "total_steps": 181800, "loss": 0.0184, "lr": 4.304241088295377e-05, "epoch": 6.380638063806381, "percentage": 31.9, "elapsed_time": "2:17:01", "remaining_time": "4:52:29", "throughput": 1488.57, "total_tokens": 12239008} {"current_steps": 58005, "total_steps": 181800, "loss": 0.0783, "lr": 4.304074944967349e-05, "epoch": 6.381188118811881, "percentage": 31.91, "elapsed_time": "2:17:02", "remaining_time": "4:52:28", "throughput": 1488.58, "total_tokens": 12240064} {"current_steps": 58010, "total_steps": 181800, "loss": 0.084, "lr": 4.303908785012027e-05, "epoch": 6.381738173817382, "percentage": 31.91, "elapsed_time": "2:17:03", "remaining_time": "4:52:28", "throughput": 1488.57, "total_tokens": 12241056} {"current_steps": 58015, "total_steps": 181800, "loss": 0.0182, "lr": 4.303742608430944e-05, "epoch": 6.382288228822882, "percentage": 31.91, "elapsed_time": "2:17:04", "remaining_time": "4:52:27", "throughput": 1488.58, "total_tokens": 12242112} {"current_steps": 58020, "total_steps": 181800, "loss": 0.0473, "lr": 4.303576415225631e-05, "epoch": 6.382838283828383, "percentage": 31.91, "elapsed_time": "2:17:04", "remaining_time": "4:52:26", "throughput": 1488.58, "total_tokens": 12243168} {"current_steps": 58025, "total_steps": 181800, "loss": 0.0595, "lr": 4.3034102053976186e-05, "epoch": 6.383388338833884, "percentage": 31.92, "elapsed_time": "2:17:05", "remaining_time": "4:52:25", "throughput": 1488.6, "total_tokens": 12244320} {"current_steps": 58030, "total_steps": 181800, "loss": 0.0416, "lr": 4.303243978948441e-05, "epoch": 6.383938393839384, "percentage": 31.92, "elapsed_time": "2:17:06", "remaining_time": "4:52:25", "throughput": 1488.59, "total_tokens": 12245344} {"current_steps": 58035, "total_steps": 181800, "loss": 0.0434, "lr": 4.3030777358796284e-05, "epoch": 6.384488448844884, "percentage": 31.92, "elapsed_time": "2:17:06", "remaining_time": "4:52:24", "throughput": 1488.6, "total_tokens": 12246432} {"current_steps": 58040, "total_steps": 181800, "loss": 0.0462, "lr": 4.302911476192714e-05, "epoch": 6.385038503850385, "percentage": 31.93, "elapsed_time": "2:17:07", "remaining_time": "4:52:23", "throughput": 1488.6, "total_tokens": 12247456} {"current_steps": 58045, "total_steps": 181800, "loss": 0.0207, "lr": 4.302745199889228e-05, "epoch": 6.385588558855885, "percentage": 31.93, "elapsed_time": "2:17:08", "remaining_time": "4:52:22", "throughput": 1488.6, "total_tokens": 12248512} {"current_steps": 58050, "total_steps": 181800, "loss": 0.105, "lr": 4.302578906970706e-05, "epoch": 6.3861386138613865, "percentage": 31.93, "elapsed_time": "2:17:08", "remaining_time": "4:52:22", "throughput": 1488.6, "total_tokens": 12249536} {"current_steps": 58055, "total_steps": 181800, "loss": 0.0206, "lr": 4.3024125974386786e-05, "epoch": 6.386688668866887, "percentage": 31.93, "elapsed_time": "2:17:09", "remaining_time": "4:52:21", "throughput": 1488.6, "total_tokens": 12250560} {"current_steps": 58060, "total_steps": 181800, "loss": 0.0207, "lr": 4.302246271294679e-05, "epoch": 6.387238723872387, "percentage": 31.94, "elapsed_time": "2:17:10", "remaining_time": "4:52:20", "throughput": 1488.61, "total_tokens": 12251616} {"current_steps": 58065, "total_steps": 181800, "loss": 0.0308, "lr": 4.3020799285402416e-05, "epoch": 6.387788778877888, "percentage": 31.94, "elapsed_time": "2:17:10", "remaining_time": "4:52:19", "throughput": 1488.61, "total_tokens": 12252640} {"current_steps": 58070, "total_steps": 181800, "loss": 0.1072, "lr": 4.301913569176897e-05, "epoch": 6.388338833883388, "percentage": 31.94, "elapsed_time": "2:17:11", "remaining_time": "4:52:19", "throughput": 1488.61, "total_tokens": 12253696} {"current_steps": 58075, "total_steps": 181800, "loss": 0.0359, "lr": 4.30174719320618e-05, "epoch": 6.388888888888889, "percentage": 31.94, "elapsed_time": "2:17:12", "remaining_time": "4:52:18", "throughput": 1488.62, "total_tokens": 12254784} {"current_steps": 58080, "total_steps": 181800, "loss": 0.2017, "lr": 4.301580800629623e-05, "epoch": 6.3894389438943895, "percentage": 31.95, "elapsed_time": "2:17:13", "remaining_time": "4:52:17", "throughput": 1488.61, "total_tokens": 12255776} {"current_steps": 58085, "total_steps": 181800, "loss": 0.0307, "lr": 4.301414391448761e-05, "epoch": 6.38998899889989, "percentage": 31.95, "elapsed_time": "2:17:13", "remaining_time": "4:52:16", "throughput": 1488.62, "total_tokens": 12256832} {"current_steps": 58090, "total_steps": 181800, "loss": 0.045, "lr": 4.301247965665127e-05, "epoch": 6.390539053905391, "percentage": 31.95, "elapsed_time": "2:17:14", "remaining_time": "4:52:16", "throughput": 1488.63, "total_tokens": 12257920} {"current_steps": 58095, "total_steps": 181800, "loss": 0.0085, "lr": 4.3010815232802546e-05, "epoch": 6.391089108910891, "percentage": 31.96, "elapsed_time": "2:17:15", "remaining_time": "4:52:15", "throughput": 1488.62, "total_tokens": 12258944} {"current_steps": 58100, "total_steps": 181800, "loss": 0.0119, "lr": 4.300915064295679e-05, "epoch": 6.391639163916391, "percentage": 31.96, "elapsed_time": "2:17:15", "remaining_time": "4:52:14", "throughput": 1488.63, "total_tokens": 12260000} {"current_steps": 58105, "total_steps": 181800, "loss": 0.0143, "lr": 4.3007485887129315e-05, "epoch": 6.392189218921892, "percentage": 31.96, "elapsed_time": "2:17:16", "remaining_time": "4:52:13", "throughput": 1488.64, "total_tokens": 12261088} {"current_steps": 58110, "total_steps": 181800, "loss": 0.0805, "lr": 4.30058209653355e-05, "epoch": 6.3927392739273925, "percentage": 31.96, "elapsed_time": "2:17:17", "remaining_time": "4:52:13", "throughput": 1488.63, "total_tokens": 12262080} {"current_steps": 58115, "total_steps": 181800, "loss": 0.0393, "lr": 4.300415587759067e-05, "epoch": 6.393289328932894, "percentage": 31.97, "elapsed_time": "2:17:17", "remaining_time": "4:52:12", "throughput": 1488.64, "total_tokens": 12263168} {"current_steps": 58120, "total_steps": 181800, "loss": 0.1168, "lr": 4.300249062391017e-05, "epoch": 6.393839383938394, "percentage": 31.97, "elapsed_time": "2:17:18", "remaining_time": "4:52:11", "throughput": 1488.64, "total_tokens": 12264192} {"current_steps": 58125, "total_steps": 181800, "loss": 0.0375, "lr": 4.300082520430935e-05, "epoch": 6.394389438943894, "percentage": 31.97, "elapsed_time": "2:17:19", "remaining_time": "4:52:10", "throughput": 1488.65, "total_tokens": 12265280} {"current_steps": 58130, "total_steps": 181800, "loss": 0.0609, "lr": 4.2999159618803566e-05, "epoch": 6.394939493949395, "percentage": 31.97, "elapsed_time": "2:17:19", "remaining_time": "4:52:10", "throughput": 1488.65, "total_tokens": 12266368} {"current_steps": 58135, "total_steps": 181800, "loss": 0.1104, "lr": 4.2997493867408166e-05, "epoch": 6.395489548954895, "percentage": 31.98, "elapsed_time": "2:17:20", "remaining_time": "4:52:09", "throughput": 1488.66, "total_tokens": 12267424} {"current_steps": 58140, "total_steps": 181800, "loss": 0.0341, "lr": 4.29958279501385e-05, "epoch": 6.396039603960396, "percentage": 31.98, "elapsed_time": "2:17:21", "remaining_time": "4:52:08", "throughput": 1488.65, "total_tokens": 12268416} {"current_steps": 58145, "total_steps": 181800, "loss": 0.0278, "lr": 4.299416186700992e-05, "epoch": 6.396589658965897, "percentage": 31.98, "elapsed_time": "2:17:21", "remaining_time": "4:52:07", "throughput": 1488.66, "total_tokens": 12269472} {"current_steps": 58150, "total_steps": 181800, "loss": 0.0218, "lr": 4.2992495618037785e-05, "epoch": 6.397139713971397, "percentage": 31.99, "elapsed_time": "2:17:22", "remaining_time": "4:52:07", "throughput": 1488.66, "total_tokens": 12270528} {"current_steps": 58155, "total_steps": 181800, "loss": 0.0093, "lr": 4.299082920323746e-05, "epoch": 6.397689768976898, "percentage": 31.99, "elapsed_time": "2:17:23", "remaining_time": "4:52:06", "throughput": 1488.65, "total_tokens": 12271488} {"current_steps": 58160, "total_steps": 181800, "loss": 0.086, "lr": 4.298916262262429e-05, "epoch": 6.398239823982398, "percentage": 31.99, "elapsed_time": "2:17:24", "remaining_time": "4:52:05", "throughput": 1488.67, "total_tokens": 12272608} {"current_steps": 58165, "total_steps": 181800, "loss": 0.0205, "lr": 4.298749587621363e-05, "epoch": 6.398789878987899, "percentage": 31.99, "elapsed_time": "2:17:24", "remaining_time": "4:52:04", "throughput": 1488.67, "total_tokens": 12273664} {"current_steps": 58170, "total_steps": 181800, "loss": 0.0591, "lr": 4.298582896402087e-05, "epoch": 6.399339933993399, "percentage": 32.0, "elapsed_time": "2:17:25", "remaining_time": "4:52:04", "throughput": 1488.67, "total_tokens": 12274720} {"current_steps": 58175, "total_steps": 181800, "loss": 0.1045, "lr": 4.298416188606133e-05, "epoch": 6.3998899889989, "percentage": 32.0, "elapsed_time": "2:17:26", "remaining_time": "4:52:03", "throughput": 1488.68, "total_tokens": 12275776} {"current_steps": 58180, "total_steps": 181800, "loss": 0.0781, "lr": 4.2982494642350425e-05, "epoch": 6.400440044004401, "percentage": 32.0, "elapsed_time": "2:17:26", "remaining_time": "4:52:02", "throughput": 1488.68, "total_tokens": 12276800} {"current_steps": 58185, "total_steps": 181800, "loss": 0.0265, "lr": 4.298082723290349e-05, "epoch": 6.400990099009901, "percentage": 32.0, "elapsed_time": "2:17:27", "remaining_time": "4:52:01", "throughput": 1488.68, "total_tokens": 12277856} {"current_steps": 58190, "total_steps": 181800, "loss": 0.0472, "lr": 4.297915965773589e-05, "epoch": 6.401540154015402, "percentage": 32.01, "elapsed_time": "2:17:28", "remaining_time": "4:52:01", "throughput": 1488.68, "total_tokens": 12278880} {"current_steps": 58195, "total_steps": 181800, "loss": 0.0254, "lr": 4.297749191686301e-05, "epoch": 6.402090209020902, "percentage": 32.01, "elapsed_time": "2:17:28", "remaining_time": "4:52:00", "throughput": 1488.68, "total_tokens": 12279936} {"current_steps": 58200, "total_steps": 181800, "loss": 0.0603, "lr": 4.29758240103002e-05, "epoch": 6.402640264026402, "percentage": 32.01, "elapsed_time": "2:17:29", "remaining_time": "4:51:59", "throughput": 1488.68, "total_tokens": 12280960} {"current_steps": 58205, "total_steps": 181800, "loss": 0.0047, "lr": 4.297415593806286e-05, "epoch": 6.4031903190319035, "percentage": 32.02, "elapsed_time": "2:17:30", "remaining_time": "4:51:58", "throughput": 1488.68, "total_tokens": 12282016} {"current_steps": 58210, "total_steps": 181800, "loss": 0.0132, "lr": 4.297248770016635e-05, "epoch": 6.403740374037404, "percentage": 32.02, "elapsed_time": "2:17:30", "remaining_time": "4:51:58", "throughput": 1488.69, "total_tokens": 12283104} {"current_steps": 58215, "total_steps": 181800, "loss": 0.1623, "lr": 4.297081929662604e-05, "epoch": 6.404290429042904, "percentage": 32.02, "elapsed_time": "2:17:31", "remaining_time": "4:51:57", "throughput": 1488.69, "total_tokens": 12284160} {"current_steps": 58220, "total_steps": 181800, "loss": 0.0201, "lr": 4.296915072745731e-05, "epoch": 6.404840484048405, "percentage": 32.02, "elapsed_time": "2:17:32", "remaining_time": "4:51:56", "throughput": 1488.71, "total_tokens": 12285312} {"current_steps": 58225, "total_steps": 181800, "loss": 0.0409, "lr": 4.296748199267554e-05, "epoch": 6.405390539053905, "percentage": 32.03, "elapsed_time": "2:17:33", "remaining_time": "4:51:55", "throughput": 1488.71, "total_tokens": 12286336} {"current_steps": 58230, "total_steps": 181800, "loss": 0.0137, "lr": 4.2965813092296115e-05, "epoch": 6.405940594059406, "percentage": 32.03, "elapsed_time": "2:17:33", "remaining_time": "4:51:55", "throughput": 1488.7, "total_tokens": 12287328} {"current_steps": 58235, "total_steps": 181800, "loss": 0.0305, "lr": 4.296414402633441e-05, "epoch": 6.4064906490649065, "percentage": 32.03, "elapsed_time": "2:17:34", "remaining_time": "4:51:54", "throughput": 1488.7, "total_tokens": 12288352} {"current_steps": 58240, "total_steps": 181800, "loss": 0.0169, "lr": 4.296247479480581e-05, "epoch": 6.407040704070407, "percentage": 32.04, "elapsed_time": "2:17:35", "remaining_time": "4:51:53", "throughput": 1488.71, "total_tokens": 12289408} {"current_steps": 58245, "total_steps": 181800, "loss": 0.0254, "lr": 4.296080539772569e-05, "epoch": 6.407590759075908, "percentage": 32.04, "elapsed_time": "2:17:35", "remaining_time": "4:51:52", "throughput": 1488.71, "total_tokens": 12290464} {"current_steps": 58250, "total_steps": 181800, "loss": 0.0157, "lr": 4.295913583510946e-05, "epoch": 6.408140814081408, "percentage": 32.04, "elapsed_time": "2:17:36", "remaining_time": "4:51:52", "throughput": 1488.71, "total_tokens": 12291520} {"current_steps": 58255, "total_steps": 181800, "loss": 0.0711, "lr": 4.2957466106972486e-05, "epoch": 6.408690869086909, "percentage": 32.04, "elapsed_time": "2:17:37", "remaining_time": "4:51:51", "throughput": 1488.71, "total_tokens": 12292544} {"current_steps": 58260, "total_steps": 181800, "loss": 0.0829, "lr": 4.2955796213330156e-05, "epoch": 6.409240924092409, "percentage": 32.05, "elapsed_time": "2:17:37", "remaining_time": "4:51:50", "throughput": 1488.72, "total_tokens": 12293600} {"current_steps": 58265, "total_steps": 181800, "loss": 0.097, "lr": 4.295412615419788e-05, "epoch": 6.4097909790979095, "percentage": 32.05, "elapsed_time": "2:17:38", "remaining_time": "4:51:49", "throughput": 1488.72, "total_tokens": 12294656} {"current_steps": 58270, "total_steps": 181800, "loss": 0.0945, "lr": 4.295245592959103e-05, "epoch": 6.410341034103411, "percentage": 32.05, "elapsed_time": "2:17:39", "remaining_time": "4:51:49", "throughput": 1488.72, "total_tokens": 12295680} {"current_steps": 58275, "total_steps": 181800, "loss": 0.1495, "lr": 4.2950785539525016e-05, "epoch": 6.410891089108911, "percentage": 32.05, "elapsed_time": "2:17:39", "remaining_time": "4:51:48", "throughput": 1488.72, "total_tokens": 12296704} {"current_steps": 58280, "total_steps": 181800, "loss": 0.1735, "lr": 4.294911498401522e-05, "epoch": 6.411441144114411, "percentage": 32.06, "elapsed_time": "2:17:40", "remaining_time": "4:51:47", "throughput": 1488.73, "total_tokens": 12297792} {"current_steps": 58285, "total_steps": 181800, "loss": 0.0221, "lr": 4.2947444263077044e-05, "epoch": 6.411991199119912, "percentage": 32.06, "elapsed_time": "2:17:41", "remaining_time": "4:51:46", "throughput": 1488.73, "total_tokens": 12298848} {"current_steps": 58290, "total_steps": 181800, "loss": 0.0278, "lr": 4.294577337672589e-05, "epoch": 6.412541254125412, "percentage": 32.06, "elapsed_time": "2:17:41", "remaining_time": "4:51:46", "throughput": 1488.74, "total_tokens": 12299968} {"current_steps": 58295, "total_steps": 181800, "loss": 0.0149, "lr": 4.294410232497715e-05, "epoch": 6.413091309130913, "percentage": 32.07, "elapsed_time": "2:17:42", "remaining_time": "4:51:45", "throughput": 1488.74, "total_tokens": 12300992} {"current_steps": 58300, "total_steps": 181800, "loss": 0.0699, "lr": 4.294243110784623e-05, "epoch": 6.413641364136414, "percentage": 32.07, "elapsed_time": "2:17:43", "remaining_time": "4:51:44", "throughput": 1488.74, "total_tokens": 12302016} {"current_steps": 58305, "total_steps": 181800, "loss": 0.0093, "lr": 4.2940759725348535e-05, "epoch": 6.414191419141914, "percentage": 32.07, "elapsed_time": "2:17:44", "remaining_time": "4:51:43", "throughput": 1488.75, "total_tokens": 12303104} {"current_steps": 58310, "total_steps": 181800, "loss": 0.0654, "lr": 4.2939088177499465e-05, "epoch": 6.414741474147415, "percentage": 32.07, "elapsed_time": "2:17:44", "remaining_time": "4:51:43", "throughput": 1488.76, "total_tokens": 12304224} {"current_steps": 58315, "total_steps": 181800, "loss": 0.027, "lr": 4.293741646431443e-05, "epoch": 6.415291529152915, "percentage": 32.08, "elapsed_time": "2:17:45", "remaining_time": "4:51:42", "throughput": 1488.77, "total_tokens": 12305312} {"current_steps": 58320, "total_steps": 181800, "loss": 0.0595, "lr": 4.293574458580882e-05, "epoch": 6.415841584158416, "percentage": 32.08, "elapsed_time": "2:17:46", "remaining_time": "4:51:41", "throughput": 1488.77, "total_tokens": 12306368} {"current_steps": 58325, "total_steps": 181800, "loss": 0.0067, "lr": 4.2934072541998076e-05, "epoch": 6.416391639163916, "percentage": 32.08, "elapsed_time": "2:17:46", "remaining_time": "4:51:41", "throughput": 1488.78, "total_tokens": 12307456} {"current_steps": 58330, "total_steps": 181800, "loss": 0.0061, "lr": 4.2932400332897585e-05, "epoch": 6.416941694169417, "percentage": 32.08, "elapsed_time": "2:17:47", "remaining_time": "4:51:40", "throughput": 1488.77, "total_tokens": 12308448} {"current_steps": 58335, "total_steps": 181800, "loss": 0.0155, "lr": 4.2930727958522764e-05, "epoch": 6.417491749174918, "percentage": 32.09, "elapsed_time": "2:17:48", "remaining_time": "4:51:39", "throughput": 1488.78, "total_tokens": 12309504} {"current_steps": 58340, "total_steps": 181800, "loss": 0.0391, "lr": 4.292905541888903e-05, "epoch": 6.418041804180418, "percentage": 32.09, "elapsed_time": "2:17:48", "remaining_time": "4:51:38", "throughput": 1488.78, "total_tokens": 12310560} {"current_steps": 58345, "total_steps": 181800, "loss": 0.0419, "lr": 4.2927382714011785e-05, "epoch": 6.418591859185918, "percentage": 32.09, "elapsed_time": "2:17:49", "remaining_time": "4:51:38", "throughput": 1488.78, "total_tokens": 12311616} {"current_steps": 58350, "total_steps": 181800, "loss": 0.1164, "lr": 4.292570984390647e-05, "epoch": 6.419141914191419, "percentage": 32.1, "elapsed_time": "2:17:50", "remaining_time": "4:51:37", "throughput": 1488.79, "total_tokens": 12312704} {"current_steps": 58355, "total_steps": 181800, "loss": 0.0179, "lr": 4.292403680858848e-05, "epoch": 6.419691969196919, "percentage": 32.1, "elapsed_time": "2:17:50", "remaining_time": "4:51:36", "throughput": 1488.79, "total_tokens": 12313760} {"current_steps": 58360, "total_steps": 181800, "loss": 0.0666, "lr": 4.292236360807325e-05, "epoch": 6.4202420242024205, "percentage": 32.1, "elapsed_time": "2:17:51", "remaining_time": "4:51:35", "throughput": 1488.8, "total_tokens": 12314848} {"current_steps": 58365, "total_steps": 181800, "loss": 0.0536, "lr": 4.292069024237619e-05, "epoch": 6.420792079207921, "percentage": 32.1, "elapsed_time": "2:17:52", "remaining_time": "4:51:35", "throughput": 1488.81, "total_tokens": 12315968} {"current_steps": 58370, "total_steps": 181800, "loss": 0.0141, "lr": 4.2919016711512735e-05, "epoch": 6.421342134213421, "percentage": 32.11, "elapsed_time": "2:17:53", "remaining_time": "4:51:34", "throughput": 1488.81, "total_tokens": 12317024} {"current_steps": 58375, "total_steps": 181800, "loss": 0.02, "lr": 4.291734301549829e-05, "epoch": 6.421892189218922, "percentage": 32.11, "elapsed_time": "2:17:53", "remaining_time": "4:51:33", "throughput": 1488.82, "total_tokens": 12318080} {"current_steps": 58380, "total_steps": 181800, "loss": 0.1381, "lr": 4.29156691543483e-05, "epoch": 6.422442244224422, "percentage": 32.11, "elapsed_time": "2:17:54", "remaining_time": "4:51:32", "throughput": 1488.81, "total_tokens": 12319072} {"current_steps": 58385, "total_steps": 181800, "loss": 0.0648, "lr": 4.2913995128078174e-05, "epoch": 6.422992299229923, "percentage": 32.11, "elapsed_time": "2:17:55", "remaining_time": "4:51:32", "throughput": 1488.82, "total_tokens": 12320192} {"current_steps": 58390, "total_steps": 181800, "loss": 0.044, "lr": 4.2912320936703366e-05, "epoch": 6.4235423542354235, "percentage": 32.12, "elapsed_time": "2:17:55", "remaining_time": "4:51:31", "throughput": 1488.83, "total_tokens": 12321248} {"current_steps": 58395, "total_steps": 181800, "loss": 0.0507, "lr": 4.291064658023928e-05, "epoch": 6.424092409240924, "percentage": 32.12, "elapsed_time": "2:17:56", "remaining_time": "4:51:30", "throughput": 1488.84, "total_tokens": 12322336} {"current_steps": 58400, "total_steps": 181800, "loss": 0.1092, "lr": 4.2908972058701364e-05, "epoch": 6.424642464246425, "percentage": 32.12, "elapsed_time": "2:17:57", "remaining_time": "4:51:29", "throughput": 1488.84, "total_tokens": 12323392} {"current_steps": 58405, "total_steps": 181800, "loss": 0.0756, "lr": 4.290729737210504e-05, "epoch": 6.425192519251925, "percentage": 32.13, "elapsed_time": "2:17:57", "remaining_time": "4:51:29", "throughput": 1488.85, "total_tokens": 12324512} {"current_steps": 58410, "total_steps": 181800, "loss": 0.0035, "lr": 4.290562252046576e-05, "epoch": 6.425742574257426, "percentage": 32.13, "elapsed_time": "2:17:58", "remaining_time": "4:51:28", "throughput": 1488.85, "total_tokens": 12325536} {"current_steps": 58415, "total_steps": 181800, "loss": 0.0052, "lr": 4.290394750379894e-05, "epoch": 6.426292629262926, "percentage": 32.13, "elapsed_time": "2:17:59", "remaining_time": "4:51:27", "throughput": 1488.85, "total_tokens": 12326592} {"current_steps": 58420, "total_steps": 181800, "loss": 0.0331, "lr": 4.290227232212003e-05, "epoch": 6.4268426842684265, "percentage": 32.13, "elapsed_time": "2:17:59", "remaining_time": "4:51:26", "throughput": 1488.85, "total_tokens": 12327648} {"current_steps": 58425, "total_steps": 181800, "loss": 0.0445, "lr": 4.290059697544446e-05, "epoch": 6.427392739273928, "percentage": 32.14, "elapsed_time": "2:18:00", "remaining_time": "4:51:26", "throughput": 1488.86, "total_tokens": 12328704} {"current_steps": 58430, "total_steps": 181800, "loss": 0.0092, "lr": 4.289892146378769e-05, "epoch": 6.427942794279428, "percentage": 32.14, "elapsed_time": "2:18:01", "remaining_time": "4:51:25", "throughput": 1488.86, "total_tokens": 12329728} {"current_steps": 58435, "total_steps": 181800, "loss": 0.0763, "lr": 4.289724578716514e-05, "epoch": 6.428492849284929, "percentage": 32.14, "elapsed_time": "2:18:02", "remaining_time": "4:51:24", "throughput": 1488.86, "total_tokens": 12330784} {"current_steps": 58440, "total_steps": 181800, "loss": 0.006, "lr": 4.289556994559226e-05, "epoch": 6.429042904290429, "percentage": 32.15, "elapsed_time": "2:18:02", "remaining_time": "4:51:23", "throughput": 1488.86, "total_tokens": 12331808} {"current_steps": 58445, "total_steps": 181800, "loss": 0.0202, "lr": 4.289389393908451e-05, "epoch": 6.429592959295929, "percentage": 32.15, "elapsed_time": "2:18:03", "remaining_time": "4:51:23", "throughput": 1488.86, "total_tokens": 12332832} {"current_steps": 58450, "total_steps": 181800, "loss": 0.0286, "lr": 4.289221776765732e-05, "epoch": 6.43014301430143, "percentage": 32.15, "elapsed_time": "2:18:04", "remaining_time": "4:51:22", "throughput": 1488.86, "total_tokens": 12333856} {"current_steps": 58455, "total_steps": 181800, "loss": 0.0175, "lr": 4.289054143132615e-05, "epoch": 6.430693069306931, "percentage": 32.15, "elapsed_time": "2:18:04", "remaining_time": "4:51:21", "throughput": 1488.87, "total_tokens": 12334944} {"current_steps": 58460, "total_steps": 181800, "loss": 0.1417, "lr": 4.288886493010643e-05, "epoch": 6.431243124312431, "percentage": 32.16, "elapsed_time": "2:18:05", "remaining_time": "4:51:20", "throughput": 1488.86, "total_tokens": 12335936} {"current_steps": 58465, "total_steps": 181800, "loss": 0.0083, "lr": 4.288718826401364e-05, "epoch": 6.431793179317932, "percentage": 32.16, "elapsed_time": "2:18:06", "remaining_time": "4:51:20", "throughput": 1488.87, "total_tokens": 12337056} {"current_steps": 58470, "total_steps": 181800, "loss": 0.051, "lr": 4.288551143306322e-05, "epoch": 6.432343234323432, "percentage": 32.16, "elapsed_time": "2:18:06", "remaining_time": "4:51:19", "throughput": 1488.88, "total_tokens": 12338112} {"current_steps": 58475, "total_steps": 181800, "loss": 0.026, "lr": 4.288383443727061e-05, "epoch": 6.432893289328933, "percentage": 32.16, "elapsed_time": "2:18:07", "remaining_time": "4:51:18", "throughput": 1488.88, "total_tokens": 12339168} {"current_steps": 58480, "total_steps": 181800, "loss": 0.0539, "lr": 4.288215727665129e-05, "epoch": 6.433443344334433, "percentage": 32.17, "elapsed_time": "2:18:08", "remaining_time": "4:51:17", "throughput": 1488.88, "total_tokens": 12340224} {"current_steps": 58485, "total_steps": 181800, "loss": 0.0274, "lr": 4.28804799512207e-05, "epoch": 6.433993399339934, "percentage": 32.17, "elapsed_time": "2:18:08", "remaining_time": "4:51:17", "throughput": 1488.88, "total_tokens": 12341216} {"current_steps": 58490, "total_steps": 181800, "loss": 0.0169, "lr": 4.287880246099432e-05, "epoch": 6.434543454345435, "percentage": 32.17, "elapsed_time": "2:18:09", "remaining_time": "4:51:16", "throughput": 1488.88, "total_tokens": 12342272} {"current_steps": 58495, "total_steps": 181800, "loss": 0.0441, "lr": 4.2877124805987576e-05, "epoch": 6.435093509350935, "percentage": 32.18, "elapsed_time": "2:18:10", "remaining_time": "4:51:15", "throughput": 1488.88, "total_tokens": 12343296} {"current_steps": 58500, "total_steps": 181800, "loss": 0.0028, "lr": 4.287544698621597e-05, "epoch": 6.435643564356436, "percentage": 32.18, "elapsed_time": "2:18:11", "remaining_time": "4:51:14", "throughput": 1488.88, "total_tokens": 12344352} {"current_steps": 58505, "total_steps": 181800, "loss": 0.044, "lr": 4.287376900169494e-05, "epoch": 6.436193619361936, "percentage": 32.18, "elapsed_time": "2:18:11", "remaining_time": "4:51:14", "throughput": 1488.88, "total_tokens": 12345344} {"current_steps": 58510, "total_steps": 181800, "loss": 0.0223, "lr": 4.287209085243995e-05, "epoch": 6.436743674367436, "percentage": 32.18, "elapsed_time": "2:18:12", "remaining_time": "4:51:13", "throughput": 1488.89, "total_tokens": 12346432} {"current_steps": 58515, "total_steps": 181800, "loss": 0.0128, "lr": 4.287041253846649e-05, "epoch": 6.4372937293729375, "percentage": 32.19, "elapsed_time": "2:18:13", "remaining_time": "4:51:12", "throughput": 1488.9, "total_tokens": 12347520} {"current_steps": 58520, "total_steps": 181800, "loss": 0.0169, "lr": 4.2868734059789994e-05, "epoch": 6.437843784378438, "percentage": 32.19, "elapsed_time": "2:18:13", "remaining_time": "4:51:11", "throughput": 1488.9, "total_tokens": 12348544} {"current_steps": 58525, "total_steps": 181800, "loss": 0.0791, "lr": 4.286705541642596e-05, "epoch": 6.438393839383938, "percentage": 32.19, "elapsed_time": "2:18:14", "remaining_time": "4:51:11", "throughput": 1488.9, "total_tokens": 12349632} {"current_steps": 58530, "total_steps": 181800, "loss": 0.009, "lr": 4.286537660838985e-05, "epoch": 6.438943894389439, "percentage": 32.19, "elapsed_time": "2:18:15", "remaining_time": "4:51:10", "throughput": 1488.91, "total_tokens": 12350720} {"current_steps": 58535, "total_steps": 181800, "loss": 0.0063, "lr": 4.286369763569714e-05, "epoch": 6.439493949394939, "percentage": 32.2, "elapsed_time": "2:18:15", "remaining_time": "4:51:09", "throughput": 1488.92, "total_tokens": 12351808} {"current_steps": 58540, "total_steps": 181800, "loss": 0.0156, "lr": 4.28620184983633e-05, "epoch": 6.44004400440044, "percentage": 32.2, "elapsed_time": "2:18:16", "remaining_time": "4:51:08", "throughput": 1488.92, "total_tokens": 12352832} {"current_steps": 58545, "total_steps": 181800, "loss": 0.0404, "lr": 4.28603391964038e-05, "epoch": 6.4405940594059405, "percentage": 32.2, "elapsed_time": "2:18:17", "remaining_time": "4:51:08", "throughput": 1488.91, "total_tokens": 12353856} {"current_steps": 58550, "total_steps": 181800, "loss": 0.036, "lr": 4.2858659729834126e-05, "epoch": 6.441144114411441, "percentage": 32.21, "elapsed_time": "2:18:17", "remaining_time": "4:51:07", "throughput": 1488.92, "total_tokens": 12354976} {"current_steps": 58555, "total_steps": 181800, "loss": 0.1489, "lr": 4.2856980098669755e-05, "epoch": 6.441694169416942, "percentage": 32.21, "elapsed_time": "2:18:18", "remaining_time": "4:51:06", "throughput": 1488.92, "total_tokens": 12356000} {"current_steps": 58560, "total_steps": 181800, "loss": 0.0175, "lr": 4.285530030292617e-05, "epoch": 6.442244224422442, "percentage": 32.21, "elapsed_time": "2:18:19", "remaining_time": "4:51:05", "throughput": 1488.93, "total_tokens": 12357088} {"current_steps": 58565, "total_steps": 181800, "loss": 0.0457, "lr": 4.285362034261885e-05, "epoch": 6.442794279427943, "percentage": 32.21, "elapsed_time": "2:18:19", "remaining_time": "4:51:05", "throughput": 1488.94, "total_tokens": 12358144} {"current_steps": 58570, "total_steps": 181800, "loss": 0.0114, "lr": 4.285194021776328e-05, "epoch": 6.443344334433443, "percentage": 32.22, "elapsed_time": "2:18:20", "remaining_time": "4:51:04", "throughput": 1488.95, "total_tokens": 12359264} {"current_steps": 58575, "total_steps": 181800, "loss": 0.0859, "lr": 4.285025992837494e-05, "epoch": 6.4438943894389435, "percentage": 32.22, "elapsed_time": "2:18:21", "remaining_time": "4:51:03", "throughput": 1488.95, "total_tokens": 12360352} {"current_steps": 58580, "total_steps": 181800, "loss": 0.0205, "lr": 4.284857947446931e-05, "epoch": 6.444444444444445, "percentage": 32.22, "elapsed_time": "2:18:22", "remaining_time": "4:51:02", "throughput": 1488.95, "total_tokens": 12361376} {"current_steps": 58585, "total_steps": 181800, "loss": 0.0192, "lr": 4.2846898856061904e-05, "epoch": 6.444994499449945, "percentage": 32.22, "elapsed_time": "2:18:22", "remaining_time": "4:51:02", "throughput": 1488.95, "total_tokens": 12362400} {"current_steps": 58590, "total_steps": 181800, "loss": 0.0065, "lr": 4.284521807316818e-05, "epoch": 6.445544554455446, "percentage": 32.23, "elapsed_time": "2:18:23", "remaining_time": "4:51:01", "throughput": 1488.96, "total_tokens": 12363488} {"current_steps": 58595, "total_steps": 181800, "loss": 0.0271, "lr": 4.2843537125803656e-05, "epoch": 6.446094609460946, "percentage": 32.23, "elapsed_time": "2:18:24", "remaining_time": "4:51:00", "throughput": 1488.97, "total_tokens": 12364608} {"current_steps": 58600, "total_steps": 181800, "loss": 0.0551, "lr": 4.28418560139838e-05, "epoch": 6.446644664466446, "percentage": 32.23, "elapsed_time": "2:18:24", "remaining_time": "4:50:59", "throughput": 1488.98, "total_tokens": 12365696} {"current_steps": 58605, "total_steps": 181800, "loss": 0.0887, "lr": 4.284017473772414e-05, "epoch": 6.447194719471947, "percentage": 32.24, "elapsed_time": "2:18:25", "remaining_time": "4:50:59", "throughput": 1488.98, "total_tokens": 12366720} {"current_steps": 58610, "total_steps": 181800, "loss": 0.0437, "lr": 4.283849329704013e-05, "epoch": 6.447744774477448, "percentage": 32.24, "elapsed_time": "2:18:26", "remaining_time": "4:50:58", "throughput": 1488.99, "total_tokens": 12367808} {"current_steps": 58615, "total_steps": 181800, "loss": 0.0564, "lr": 4.28368116919473e-05, "epoch": 6.448294829482949, "percentage": 32.24, "elapsed_time": "2:18:26", "remaining_time": "4:50:57", "throughput": 1488.98, "total_tokens": 12368800} {"current_steps": 58620, "total_steps": 181800, "loss": 0.1306, "lr": 4.283512992246113e-05, "epoch": 6.448844884488449, "percentage": 32.24, "elapsed_time": "2:18:27", "remaining_time": "4:50:56", "throughput": 1488.98, "total_tokens": 12369792} {"current_steps": 58625, "total_steps": 181800, "loss": 0.0085, "lr": 4.283344798859712e-05, "epoch": 6.449394939493949, "percentage": 32.25, "elapsed_time": "2:18:28", "remaining_time": "4:50:56", "throughput": 1488.99, "total_tokens": 12370880} {"current_steps": 58630, "total_steps": 181800, "loss": 0.0237, "lr": 4.283176589037078e-05, "epoch": 6.44994499449945, "percentage": 32.25, "elapsed_time": "2:18:28", "remaining_time": "4:50:55", "throughput": 1488.99, "total_tokens": 12371936} {"current_steps": 58635, "total_steps": 181800, "loss": 0.0228, "lr": 4.2830083627797614e-05, "epoch": 6.4504950495049505, "percentage": 32.25, "elapsed_time": "2:18:29", "remaining_time": "4:50:54", "throughput": 1488.99, "total_tokens": 12372960} {"current_steps": 58640, "total_steps": 181800, "loss": 0.0473, "lr": 4.282840120089312e-05, "epoch": 6.451045104510451, "percentage": 32.26, "elapsed_time": "2:18:30", "remaining_time": "4:50:53", "throughput": 1488.99, "total_tokens": 12373984} {"current_steps": 58645, "total_steps": 181800, "loss": 0.016, "lr": 4.282671860967281e-05, "epoch": 6.451595159515952, "percentage": 32.26, "elapsed_time": "2:18:31", "remaining_time": "4:50:53", "throughput": 1488.99, "total_tokens": 12375040} {"current_steps": 58650, "total_steps": 181800, "loss": 0.1076, "lr": 4.2825035854152184e-05, "epoch": 6.452145214521452, "percentage": 32.26, "elapsed_time": "2:18:31", "remaining_time": "4:50:52", "throughput": 1489.0, "total_tokens": 12376128} {"current_steps": 58655, "total_steps": 181800, "loss": 0.0563, "lr": 4.282335293434676e-05, "epoch": 6.452695269526953, "percentage": 32.26, "elapsed_time": "2:18:32", "remaining_time": "4:50:51", "throughput": 1489.01, "total_tokens": 12377216} {"current_steps": 58660, "total_steps": 181800, "loss": 0.0227, "lr": 4.282166985027205e-05, "epoch": 6.453245324532453, "percentage": 32.27, "elapsed_time": "2:18:33", "remaining_time": "4:50:50", "throughput": 1489.02, "total_tokens": 12378336} {"current_steps": 58665, "total_steps": 181800, "loss": 0.0047, "lr": 4.2819986601943546e-05, "epoch": 6.4537953795379535, "percentage": 32.27, "elapsed_time": "2:18:33", "remaining_time": "4:50:50", "throughput": 1489.02, "total_tokens": 12379424} {"current_steps": 58670, "total_steps": 181800, "loss": 0.0221, "lr": 4.2818303189376785e-05, "epoch": 6.4543454345434546, "percentage": 32.27, "elapsed_time": "2:18:34", "remaining_time": "4:50:49", "throughput": 1489.03, "total_tokens": 12380512} {"current_steps": 58675, "total_steps": 181800, "loss": 0.0363, "lr": 4.281661961258727e-05, "epoch": 6.454895489548955, "percentage": 32.27, "elapsed_time": "2:18:35", "remaining_time": "4:50:48", "throughput": 1489.04, "total_tokens": 12381600} {"current_steps": 58680, "total_steps": 181800, "loss": 0.0207, "lr": 4.281493587159053e-05, "epoch": 6.455445544554456, "percentage": 32.28, "elapsed_time": "2:18:35", "remaining_time": "4:50:48", "throughput": 1489.03, "total_tokens": 12382592} {"current_steps": 58685, "total_steps": 181800, "loss": 0.0083, "lr": 4.2813251966402066e-05, "epoch": 6.455995599559956, "percentage": 32.28, "elapsed_time": "2:18:36", "remaining_time": "4:50:47", "throughput": 1489.04, "total_tokens": 12383648} {"current_steps": 58690, "total_steps": 181800, "loss": 0.0107, "lr": 4.281156789703741e-05, "epoch": 6.456545654565456, "percentage": 32.28, "elapsed_time": "2:18:37", "remaining_time": "4:50:46", "throughput": 1489.05, "total_tokens": 12384768} {"current_steps": 58695, "total_steps": 181800, "loss": 0.0395, "lr": 4.280988366351208e-05, "epoch": 6.457095709570957, "percentage": 32.29, "elapsed_time": "2:18:37", "remaining_time": "4:50:45", "throughput": 1489.04, "total_tokens": 12385760} {"current_steps": 58700, "total_steps": 181800, "loss": 0.085, "lr": 4.2808199265841594e-05, "epoch": 6.457645764576458, "percentage": 32.29, "elapsed_time": "2:18:38", "remaining_time": "4:50:45", "throughput": 1489.04, "total_tokens": 12386784} {"current_steps": 58705, "total_steps": 181800, "loss": 0.0084, "lr": 4.280651470404148e-05, "epoch": 6.458195819581958, "percentage": 32.29, "elapsed_time": "2:18:39", "remaining_time": "4:50:44", "throughput": 1489.05, "total_tokens": 12387872} {"current_steps": 58710, "total_steps": 181800, "loss": 0.0571, "lr": 4.280482997812727e-05, "epoch": 6.458745874587459, "percentage": 32.29, "elapsed_time": "2:18:40", "remaining_time": "4:50:43", "throughput": 1489.05, "total_tokens": 12388896} {"current_steps": 58715, "total_steps": 181800, "loss": 0.0935, "lr": 4.280314508811448e-05, "epoch": 6.459295929592959, "percentage": 32.3, "elapsed_time": "2:18:40", "remaining_time": "4:50:42", "throughput": 1489.07, "total_tokens": 12390080} {"current_steps": 58720, "total_steps": 181800, "loss": 0.0055, "lr": 4.280146003401865e-05, "epoch": 6.45984598459846, "percentage": 32.3, "elapsed_time": "2:18:41", "remaining_time": "4:50:42", "throughput": 1489.07, "total_tokens": 12391136} {"current_steps": 58725, "total_steps": 181800, "loss": 0.0739, "lr": 4.27997748158553e-05, "epoch": 6.46039603960396, "percentage": 32.3, "elapsed_time": "2:18:42", "remaining_time": "4:50:41", "throughput": 1489.07, "total_tokens": 12392160} {"current_steps": 58730, "total_steps": 181800, "loss": 0.0716, "lr": 4.279808943363998e-05, "epoch": 6.460946094609461, "percentage": 32.3, "elapsed_time": "2:18:42", "remaining_time": "4:50:40", "throughput": 1489.08, "total_tokens": 12393248} {"current_steps": 58735, "total_steps": 181800, "loss": 0.0309, "lr": 4.279640388738819e-05, "epoch": 6.461496149614962, "percentage": 32.31, "elapsed_time": "2:18:43", "remaining_time": "4:50:39", "throughput": 1489.09, "total_tokens": 12394368} {"current_steps": 58740, "total_steps": 181800, "loss": 0.078, "lr": 4.27947181771155e-05, "epoch": 6.462046204620462, "percentage": 32.31, "elapsed_time": "2:18:44", "remaining_time": "4:50:39", "throughput": 1489.08, "total_tokens": 12395328} {"current_steps": 58745, "total_steps": 181800, "loss": 0.0694, "lr": 4.279303230283742e-05, "epoch": 6.462596259625963, "percentage": 32.31, "elapsed_time": "2:18:44", "remaining_time": "4:50:38", "throughput": 1489.08, "total_tokens": 12396352} {"current_steps": 58750, "total_steps": 181800, "loss": 0.0925, "lr": 4.279134626456951e-05, "epoch": 6.463146314631463, "percentage": 32.32, "elapsed_time": "2:18:45", "remaining_time": "4:50:37", "throughput": 1489.08, "total_tokens": 12397344} {"current_steps": 58755, "total_steps": 181800, "loss": 0.0578, "lr": 4.278966006232729e-05, "epoch": 6.463696369636963, "percentage": 32.32, "elapsed_time": "2:18:46", "remaining_time": "4:50:36", "throughput": 1489.09, "total_tokens": 12398432} {"current_steps": 58760, "total_steps": 181800, "loss": 0.1167, "lr": 4.278797369612631e-05, "epoch": 6.4642464246424645, "percentage": 32.32, "elapsed_time": "2:18:46", "remaining_time": "4:50:36", "throughput": 1489.09, "total_tokens": 12399456} {"current_steps": 58765, "total_steps": 181800, "loss": 0.1294, "lr": 4.278628716598212e-05, "epoch": 6.464796479647965, "percentage": 32.32, "elapsed_time": "2:18:47", "remaining_time": "4:50:35", "throughput": 1489.09, "total_tokens": 12400480} {"current_steps": 58770, "total_steps": 181800, "loss": 0.0611, "lr": 4.2784600471910255e-05, "epoch": 6.465346534653466, "percentage": 32.33, "elapsed_time": "2:18:48", "remaining_time": "4:50:34", "throughput": 1489.09, "total_tokens": 12401536} {"current_steps": 58775, "total_steps": 181800, "loss": 0.0262, "lr": 4.278291361392625e-05, "epoch": 6.465896589658966, "percentage": 32.33, "elapsed_time": "2:18:48", "remaining_time": "4:50:33", "throughput": 1489.1, "total_tokens": 12402656} {"current_steps": 58780, "total_steps": 181800, "loss": 0.1053, "lr": 4.278122659204567e-05, "epoch": 6.466446644664466, "percentage": 32.33, "elapsed_time": "2:18:49", "remaining_time": "4:50:33", "throughput": 1489.11, "total_tokens": 12403712} {"current_steps": 58785, "total_steps": 181800, "loss": 0.0437, "lr": 4.2779539406284055e-05, "epoch": 6.466996699669967, "percentage": 32.33, "elapsed_time": "2:18:50", "remaining_time": "4:50:32", "throughput": 1489.12, "total_tokens": 12404832} {"current_steps": 58790, "total_steps": 181800, "loss": 0.0564, "lr": 4.277785205665696e-05, "epoch": 6.4675467546754675, "percentage": 32.34, "elapsed_time": "2:18:51", "remaining_time": "4:50:31", "throughput": 1489.13, "total_tokens": 12405984} {"current_steps": 58795, "total_steps": 181800, "loss": 0.0366, "lr": 4.277616454317993e-05, "epoch": 6.468096809680969, "percentage": 32.34, "elapsed_time": "2:18:51", "remaining_time": "4:50:30", "throughput": 1489.13, "total_tokens": 12406976} {"current_steps": 58800, "total_steps": 181800, "loss": 0.0958, "lr": 4.277447686586853e-05, "epoch": 6.468646864686469, "percentage": 32.34, "elapsed_time": "2:18:52", "remaining_time": "4:50:30", "throughput": 1489.13, "total_tokens": 12408032} {"current_steps": 58805, "total_steps": 181800, "loss": 0.0279, "lr": 4.27727890247383e-05, "epoch": 6.469196919691969, "percentage": 32.35, "elapsed_time": "2:18:53", "remaining_time": "4:50:29", "throughput": 1489.14, "total_tokens": 12409088} {"current_steps": 58810, "total_steps": 181800, "loss": 0.0302, "lr": 4.27711010198048e-05, "epoch": 6.46974697469747, "percentage": 32.35, "elapsed_time": "2:18:53", "remaining_time": "4:50:28", "throughput": 1489.15, "total_tokens": 12410208} {"current_steps": 58815, "total_steps": 181800, "loss": 0.0585, "lr": 4.276941285108359e-05, "epoch": 6.47029702970297, "percentage": 32.35, "elapsed_time": "2:18:54", "remaining_time": "4:50:27", "throughput": 1489.15, "total_tokens": 12411264} {"current_steps": 58820, "total_steps": 181800, "loss": 0.0458, "lr": 4.276772451859022e-05, "epoch": 6.4708470847084705, "percentage": 32.35, "elapsed_time": "2:18:55", "remaining_time": "4:50:27", "throughput": 1489.16, "total_tokens": 12412352} {"current_steps": 58825, "total_steps": 181800, "loss": 0.0309, "lr": 4.276603602234027e-05, "epoch": 6.471397139713972, "percentage": 32.36, "elapsed_time": "2:18:55", "remaining_time": "4:50:26", "throughput": 1489.16, "total_tokens": 12413440} {"current_steps": 58830, "total_steps": 181800, "loss": 0.0073, "lr": 4.2764347362349285e-05, "epoch": 6.471947194719472, "percentage": 32.36, "elapsed_time": "2:18:56", "remaining_time": "4:50:25", "throughput": 1489.16, "total_tokens": 12414464} {"current_steps": 58835, "total_steps": 181800, "loss": 0.0303, "lr": 4.276265853863285e-05, "epoch": 6.472497249724973, "percentage": 32.36, "elapsed_time": "2:18:57", "remaining_time": "4:50:24", "throughput": 1489.18, "total_tokens": 12415616} {"current_steps": 58840, "total_steps": 181800, "loss": 0.0277, "lr": 4.2760969551206495e-05, "epoch": 6.473047304730473, "percentage": 32.37, "elapsed_time": "2:18:57", "remaining_time": "4:50:24", "throughput": 1489.17, "total_tokens": 12416608} {"current_steps": 58845, "total_steps": 181800, "loss": 0.0032, "lr": 4.2759280400085815e-05, "epoch": 6.473597359735973, "percentage": 32.37, "elapsed_time": "2:18:58", "remaining_time": "4:50:23", "throughput": 1489.18, "total_tokens": 12417664} {"current_steps": 58850, "total_steps": 181800, "loss": 0.018, "lr": 4.2757591085286366e-05, "epoch": 6.474147414741474, "percentage": 32.37, "elapsed_time": "2:18:59", "remaining_time": "4:50:22", "throughput": 1489.19, "total_tokens": 12418784} {"current_steps": 58855, "total_steps": 181800, "loss": 0.0084, "lr": 4.2755901606823725e-05, "epoch": 6.474697469746975, "percentage": 32.37, "elapsed_time": "2:18:59", "remaining_time": "4:50:21", "throughput": 1489.19, "total_tokens": 12419840} {"current_steps": 58860, "total_steps": 181800, "loss": 0.0643, "lr": 4.275421196471346e-05, "epoch": 6.475247524752476, "percentage": 32.38, "elapsed_time": "2:19:00", "remaining_time": "4:50:21", "throughput": 1489.2, "total_tokens": 12420896} {"current_steps": 58865, "total_steps": 181800, "loss": 0.0656, "lr": 4.275252215897114e-05, "epoch": 6.475797579757976, "percentage": 32.38, "elapsed_time": "2:19:01", "remaining_time": "4:50:20", "throughput": 1489.19, "total_tokens": 12421888} {"current_steps": 58870, "total_steps": 181800, "loss": 0.0412, "lr": 4.275083218961234e-05, "epoch": 6.476347634763476, "percentage": 32.38, "elapsed_time": "2:19:02", "remaining_time": "4:50:19", "throughput": 1489.2, "total_tokens": 12422976} {"current_steps": 58875, "total_steps": 181800, "loss": 0.0153, "lr": 4.2749142056652635e-05, "epoch": 6.476897689768977, "percentage": 32.38, "elapsed_time": "2:19:02", "remaining_time": "4:50:18", "throughput": 1489.2, "total_tokens": 12424064} {"current_steps": 58880, "total_steps": 181800, "loss": 0.06, "lr": 4.2747451760107603e-05, "epoch": 6.477447744774477, "percentage": 32.39, "elapsed_time": "2:19:03", "remaining_time": "4:50:18", "throughput": 1489.2, "total_tokens": 12425088} {"current_steps": 58885, "total_steps": 181800, "loss": 0.0306, "lr": 4.274576129999284e-05, "epoch": 6.477997799779978, "percentage": 32.39, "elapsed_time": "2:19:04", "remaining_time": "4:50:17", "throughput": 1489.22, "total_tokens": 12426208} {"current_steps": 58890, "total_steps": 181800, "loss": 0.0101, "lr": 4.274407067632389e-05, "epoch": 6.478547854785479, "percentage": 32.39, "elapsed_time": "2:19:04", "remaining_time": "4:50:16", "throughput": 1489.22, "total_tokens": 12427264} {"current_steps": 58895, "total_steps": 181800, "loss": 0.0952, "lr": 4.274237988911637e-05, "epoch": 6.479097909790979, "percentage": 32.4, "elapsed_time": "2:19:05", "remaining_time": "4:50:15", "throughput": 1489.22, "total_tokens": 12428320} {"current_steps": 58900, "total_steps": 181800, "loss": 0.0233, "lr": 4.274068893838584e-05, "epoch": 6.47964796479648, "percentage": 32.4, "elapsed_time": "2:19:06", "remaining_time": "4:50:15", "throughput": 1489.23, "total_tokens": 12429408} {"current_steps": 58905, "total_steps": 181800, "loss": 0.1448, "lr": 4.2738997824147896e-05, "epoch": 6.48019801980198, "percentage": 32.4, "elapsed_time": "2:19:06", "remaining_time": "4:50:14", "throughput": 1489.23, "total_tokens": 12430432} {"current_steps": 58910, "total_steps": 181800, "loss": 0.0205, "lr": 4.273730654641812e-05, "epoch": 6.48074807480748, "percentage": 32.4, "elapsed_time": "2:19:07", "remaining_time": "4:50:13", "throughput": 1489.23, "total_tokens": 12431488} {"current_steps": 58915, "total_steps": 181800, "loss": 0.1426, "lr": 4.27356151052121e-05, "epoch": 6.4812981298129815, "percentage": 32.41, "elapsed_time": "2:19:08", "remaining_time": "4:50:12", "throughput": 1489.24, "total_tokens": 12432608} {"current_steps": 58920, "total_steps": 181800, "loss": 0.0468, "lr": 4.273392350054544e-05, "epoch": 6.481848184818482, "percentage": 32.41, "elapsed_time": "2:19:08", "remaining_time": "4:50:12", "throughput": 1489.25, "total_tokens": 12433664} {"current_steps": 58925, "total_steps": 181800, "loss": 0.0028, "lr": 4.2732231732433695e-05, "epoch": 6.482398239823983, "percentage": 32.41, "elapsed_time": "2:19:09", "remaining_time": "4:50:11", "throughput": 1489.25, "total_tokens": 12434752} {"current_steps": 58930, "total_steps": 181800, "loss": 0.0171, "lr": 4.273053980089249e-05, "epoch": 6.482948294829483, "percentage": 32.41, "elapsed_time": "2:19:10", "remaining_time": "4:50:10", "throughput": 1489.26, "total_tokens": 12435808} {"current_steps": 58935, "total_steps": 181800, "loss": 0.107, "lr": 4.27288477059374e-05, "epoch": 6.483498349834983, "percentage": 32.42, "elapsed_time": "2:19:11", "remaining_time": "4:50:09", "throughput": 1489.26, "total_tokens": 12436864} {"current_steps": 58940, "total_steps": 181800, "loss": 0.0224, "lr": 4.272715544758404e-05, "epoch": 6.484048404840484, "percentage": 32.42, "elapsed_time": "2:19:11", "remaining_time": "4:50:09", "throughput": 1489.26, "total_tokens": 12437920} {"current_steps": 58945, "total_steps": 181800, "loss": 0.034, "lr": 4.2725463025847984e-05, "epoch": 6.4845984598459845, "percentage": 32.42, "elapsed_time": "2:19:12", "remaining_time": "4:50:08", "throughput": 1489.27, "total_tokens": 12439008} {"current_steps": 58950, "total_steps": 181800, "loss": 0.0197, "lr": 4.272377044074485e-05, "epoch": 6.485148514851485, "percentage": 32.43, "elapsed_time": "2:19:13", "remaining_time": "4:50:07", "throughput": 1489.27, "total_tokens": 12440032} {"current_steps": 58955, "total_steps": 181800, "loss": 0.0963, "lr": 4.272207769229022e-05, "epoch": 6.485698569856986, "percentage": 32.43, "elapsed_time": "2:19:13", "remaining_time": "4:50:06", "throughput": 1489.28, "total_tokens": 12441088} {"current_steps": 58960, "total_steps": 181800, "loss": 0.0969, "lr": 4.27203847804997e-05, "epoch": 6.486248624862486, "percentage": 32.43, "elapsed_time": "2:19:14", "remaining_time": "4:50:06", "throughput": 1489.28, "total_tokens": 12442112} {"current_steps": 58965, "total_steps": 181800, "loss": 0.0176, "lr": 4.2718691705388917e-05, "epoch": 6.486798679867987, "percentage": 32.43, "elapsed_time": "2:19:15", "remaining_time": "4:50:05", "throughput": 1489.28, "total_tokens": 12443168} {"current_steps": 58970, "total_steps": 181800, "loss": 0.0527, "lr": 4.271699846697344e-05, "epoch": 6.487348734873487, "percentage": 32.44, "elapsed_time": "2:19:15", "remaining_time": "4:50:04", "throughput": 1489.29, "total_tokens": 12444288} {"current_steps": 58975, "total_steps": 181800, "loss": 0.0532, "lr": 4.2715305065268884e-05, "epoch": 6.4878987898789875, "percentage": 32.44, "elapsed_time": "2:19:16", "remaining_time": "4:50:03", "throughput": 1489.29, "total_tokens": 12445344} {"current_steps": 58980, "total_steps": 181800, "loss": 0.0703, "lr": 4.2713611500290876e-05, "epoch": 6.488448844884489, "percentage": 32.44, "elapsed_time": "2:19:17", "remaining_time": "4:50:03", "throughput": 1489.29, "total_tokens": 12446368} {"current_steps": 58985, "total_steps": 181800, "loss": 0.0083, "lr": 4.2711917772055e-05, "epoch": 6.488998899889989, "percentage": 32.44, "elapsed_time": "2:19:17", "remaining_time": "4:50:02", "throughput": 1489.29, "total_tokens": 12447424} {"current_steps": 58990, "total_steps": 181800, "loss": 0.0114, "lr": 4.2710223880576874e-05, "epoch": 6.48954895489549, "percentage": 32.45, "elapsed_time": "2:19:18", "remaining_time": "4:50:01", "throughput": 1489.29, "total_tokens": 12448416} {"current_steps": 58995, "total_steps": 181800, "loss": 0.0631, "lr": 4.2708529825872125e-05, "epoch": 6.49009900990099, "percentage": 32.45, "elapsed_time": "2:19:19", "remaining_time": "4:50:00", "throughput": 1489.3, "total_tokens": 12449504} {"current_steps": 59000, "total_steps": 181800, "loss": 0.0081, "lr": 4.2706835607956344e-05, "epoch": 6.49064906490649, "percentage": 32.45, "elapsed_time": "2:19:20", "remaining_time": "4:50:00", "throughput": 1489.3, "total_tokens": 12450560} {"current_steps": 59005, "total_steps": 181800, "loss": 0.027, "lr": 4.270514122684516e-05, "epoch": 6.491199119911991, "percentage": 32.46, "elapsed_time": "2:19:20", "remaining_time": "4:49:59", "throughput": 1489.3, "total_tokens": 12451616} {"current_steps": 59010, "total_steps": 181800, "loss": 0.0595, "lr": 4.2703446682554186e-05, "epoch": 6.491749174917492, "percentage": 32.46, "elapsed_time": "2:19:21", "remaining_time": "4:49:58", "throughput": 1489.31, "total_tokens": 12452672} {"current_steps": 59015, "total_steps": 181800, "loss": 0.059, "lr": 4.2701751975099034e-05, "epoch": 6.492299229922993, "percentage": 32.46, "elapsed_time": "2:19:22", "remaining_time": "4:49:57", "throughput": 1489.31, "total_tokens": 12453696} {"current_steps": 59020, "total_steps": 181800, "loss": 0.0742, "lr": 4.270005710449534e-05, "epoch": 6.492849284928493, "percentage": 32.46, "elapsed_time": "2:19:22", "remaining_time": "4:49:57", "throughput": 1489.3, "total_tokens": 12454688} {"current_steps": 59025, "total_steps": 181800, "loss": 0.005, "lr": 4.26983620707587e-05, "epoch": 6.493399339933993, "percentage": 32.47, "elapsed_time": "2:19:23", "remaining_time": "4:49:56", "throughput": 1489.31, "total_tokens": 12455776} {"current_steps": 59030, "total_steps": 181800, "loss": 0.1207, "lr": 4.269666687390476e-05, "epoch": 6.493949394939494, "percentage": 32.47, "elapsed_time": "2:19:24", "remaining_time": "4:49:55", "throughput": 1489.32, "total_tokens": 12456864} {"current_steps": 59035, "total_steps": 181800, "loss": 0.0069, "lr": 4.2694971513949124e-05, "epoch": 6.494499449944994, "percentage": 32.47, "elapsed_time": "2:19:24", "remaining_time": "4:49:54", "throughput": 1489.32, "total_tokens": 12457920} {"current_steps": 59040, "total_steps": 181800, "loss": 0.1585, "lr": 4.269327599090743e-05, "epoch": 6.4950495049504955, "percentage": 32.48, "elapsed_time": "2:19:25", "remaining_time": "4:49:54", "throughput": 1489.33, "total_tokens": 12459040} {"current_steps": 59045, "total_steps": 181800, "loss": 0.1111, "lr": 4.26915803047953e-05, "epoch": 6.495599559955996, "percentage": 32.48, "elapsed_time": "2:19:26", "remaining_time": "4:49:53", "throughput": 1489.34, "total_tokens": 12460128} {"current_steps": 59050, "total_steps": 181800, "loss": 0.1132, "lr": 4.268988445562836e-05, "epoch": 6.496149614961496, "percentage": 32.48, "elapsed_time": "2:19:26", "remaining_time": "4:49:52", "throughput": 1489.35, "total_tokens": 12461216} {"current_steps": 59055, "total_steps": 181800, "loss": 0.0179, "lr": 4.268818844342225e-05, "epoch": 6.496699669966997, "percentage": 32.48, "elapsed_time": "2:19:27", "remaining_time": "4:49:51", "throughput": 1489.36, "total_tokens": 12462336} {"current_steps": 59060, "total_steps": 181800, "loss": 0.0688, "lr": 4.268649226819259e-05, "epoch": 6.497249724972497, "percentage": 32.49, "elapsed_time": "2:19:28", "remaining_time": "4:49:51", "throughput": 1489.36, "total_tokens": 12463392} {"current_steps": 59065, "total_steps": 181800, "loss": 0.0041, "lr": 4.268479592995502e-05, "epoch": 6.497799779977997, "percentage": 32.49, "elapsed_time": "2:19:28", "remaining_time": "4:49:50", "throughput": 1489.35, "total_tokens": 12464384} {"current_steps": 59070, "total_steps": 181800, "loss": 0.0248, "lr": 4.268309942872518e-05, "epoch": 6.4983498349834985, "percentage": 32.49, "elapsed_time": "2:19:29", "remaining_time": "4:49:49", "throughput": 1489.36, "total_tokens": 12465472} {"current_steps": 59075, "total_steps": 181800, "loss": 0.0888, "lr": 4.2681402764518684e-05, "epoch": 6.498899889988999, "percentage": 32.49, "elapsed_time": "2:19:30", "remaining_time": "4:49:48", "throughput": 1489.37, "total_tokens": 12466528} {"current_steps": 59080, "total_steps": 181800, "loss": 0.0153, "lr": 4.267970593735119e-05, "epoch": 6.4994499449945, "percentage": 32.5, "elapsed_time": "2:19:31", "remaining_time": "4:49:48", "throughput": 1489.36, "total_tokens": 12467552} {"current_steps": 59085, "total_steps": 181800, "loss": 0.1014, "lr": 4.2678008947238336e-05, "epoch": 6.5, "percentage": 32.5, "elapsed_time": "2:19:31", "remaining_time": "4:49:47", "throughput": 1489.37, "total_tokens": 12468640} {"current_steps": 59090, "total_steps": 181800, "loss": 0.0111, "lr": 4.2676311794195744e-05, "epoch": 6.5005500550055, "percentage": 32.5, "elapsed_time": "2:19:32", "remaining_time": "4:49:46", "throughput": 1489.37, "total_tokens": 12469664} {"current_steps": 59095, "total_steps": 181800, "loss": 0.1235, "lr": 4.267461447823907e-05, "epoch": 6.501100110011001, "percentage": 32.51, "elapsed_time": "2:19:33", "remaining_time": "4:49:45", "throughput": 1489.37, "total_tokens": 12470720} {"current_steps": 59100, "total_steps": 181800, "loss": 0.025, "lr": 4.267291699938396e-05, "epoch": 6.5016501650165015, "percentage": 32.51, "elapsed_time": "2:19:33", "remaining_time": "4:49:45", "throughput": 1489.38, "total_tokens": 12471808} {"current_steps": 59105, "total_steps": 181800, "loss": 0.0201, "lr": 4.267121935764605e-05, "epoch": 6.502200220022003, "percentage": 32.51, "elapsed_time": "2:19:34", "remaining_time": "4:49:44", "throughput": 1489.38, "total_tokens": 12472832} {"current_steps": 59110, "total_steps": 181800, "loss": 0.0148, "lr": 4.2669521553041e-05, "epoch": 6.502750275027503, "percentage": 32.51, "elapsed_time": "2:19:35", "remaining_time": "4:49:43", "throughput": 1489.39, "total_tokens": 12473920} {"current_steps": 59115, "total_steps": 181800, "loss": 0.02, "lr": 4.2667823585584445e-05, "epoch": 6.503300330033003, "percentage": 32.52, "elapsed_time": "2:19:35", "remaining_time": "4:49:43", "throughput": 1489.39, "total_tokens": 12475008} {"current_steps": 59120, "total_steps": 181800, "loss": 0.0346, "lr": 4.266612545529203e-05, "epoch": 6.503850385038504, "percentage": 32.52, "elapsed_time": "2:19:36", "remaining_time": "4:49:42", "throughput": 1489.4, "total_tokens": 12476064} {"current_steps": 59125, "total_steps": 181800, "loss": 0.0115, "lr": 4.266442716217942e-05, "epoch": 6.504400440044004, "percentage": 32.52, "elapsed_time": "2:19:37", "remaining_time": "4:49:41", "throughput": 1489.41, "total_tokens": 12477152} {"current_steps": 59130, "total_steps": 181800, "loss": 0.0214, "lr": 4.2662728706262255e-05, "epoch": 6.5049504950495045, "percentage": 32.52, "elapsed_time": "2:19:37", "remaining_time": "4:49:40", "throughput": 1489.41, "total_tokens": 12478240} {"current_steps": 59135, "total_steps": 181800, "loss": 0.0213, "lr": 4.2661030087556196e-05, "epoch": 6.505500550055006, "percentage": 32.53, "elapsed_time": "2:19:38", "remaining_time": "4:49:40", "throughput": 1489.42, "total_tokens": 12479296} {"current_steps": 59140, "total_steps": 181800, "loss": 0.0679, "lr": 4.265933130607691e-05, "epoch": 6.506050605060506, "percentage": 32.53, "elapsed_time": "2:19:39", "remaining_time": "4:49:39", "throughput": 1489.43, "total_tokens": 12480416} {"current_steps": 59145, "total_steps": 181800, "loss": 0.0461, "lr": 4.2657632361840024e-05, "epoch": 6.506600660066007, "percentage": 32.53, "elapsed_time": "2:19:40", "remaining_time": "4:49:38", "throughput": 1489.43, "total_tokens": 12481472} {"current_steps": 59150, "total_steps": 181800, "loss": 0.0159, "lr": 4.2655933254861226e-05, "epoch": 6.507150715071507, "percentage": 32.54, "elapsed_time": "2:19:40", "remaining_time": "4:49:37", "throughput": 1489.43, "total_tokens": 12482496} {"current_steps": 59155, "total_steps": 181800, "loss": 0.0519, "lr": 4.265423398515616e-05, "epoch": 6.507700770077007, "percentage": 32.54, "elapsed_time": "2:19:41", "remaining_time": "4:49:37", "throughput": 1489.43, "total_tokens": 12483552} {"current_steps": 59160, "total_steps": 181800, "loss": 0.0111, "lr": 4.2652534552740496e-05, "epoch": 6.508250825082508, "percentage": 32.54, "elapsed_time": "2:19:42", "remaining_time": "4:49:36", "throughput": 1489.45, "total_tokens": 12484704} {"current_steps": 59165, "total_steps": 181800, "loss": 0.0046, "lr": 4.2650834957629885e-05, "epoch": 6.508800880088009, "percentage": 32.54, "elapsed_time": "2:19:42", "remaining_time": "4:49:35", "throughput": 1489.45, "total_tokens": 12485728} {"current_steps": 59170, "total_steps": 181800, "loss": 0.0294, "lr": 4.2649135199839996e-05, "epoch": 6.50935093509351, "percentage": 32.55, "elapsed_time": "2:19:43", "remaining_time": "4:49:34", "throughput": 1489.44, "total_tokens": 12486720} {"current_steps": 59175, "total_steps": 181800, "loss": 0.0168, "lr": 4.2647435279386496e-05, "epoch": 6.50990099009901, "percentage": 32.55, "elapsed_time": "2:19:44", "remaining_time": "4:49:34", "throughput": 1489.45, "total_tokens": 12487808} {"current_steps": 59180, "total_steps": 181800, "loss": 0.022, "lr": 4.264573519628505e-05, "epoch": 6.51045104510451, "percentage": 32.55, "elapsed_time": "2:19:44", "remaining_time": "4:49:33", "throughput": 1489.45, "total_tokens": 12488800} {"current_steps": 59185, "total_steps": 181800, "loss": 0.0099, "lr": 4.2644034950551344e-05, "epoch": 6.511001100110011, "percentage": 32.56, "elapsed_time": "2:19:45", "remaining_time": "4:49:32", "throughput": 1489.45, "total_tokens": 12489856} {"current_steps": 59190, "total_steps": 181800, "loss": 0.011, "lr": 4.2642334542201026e-05, "epoch": 6.511551155115511, "percentage": 32.56, "elapsed_time": "2:19:46", "remaining_time": "4:49:31", "throughput": 1489.44, "total_tokens": 12490848} {"current_steps": 59195, "total_steps": 181800, "loss": 0.0017, "lr": 4.264063397124978e-05, "epoch": 6.512101210121012, "percentage": 32.56, "elapsed_time": "2:19:46", "remaining_time": "4:49:31", "throughput": 1489.44, "total_tokens": 12491872} {"current_steps": 59200, "total_steps": 181800, "loss": 0.108, "lr": 4.2638933237713264e-05, "epoch": 6.512651265126513, "percentage": 32.56, "elapsed_time": "2:19:47", "remaining_time": "4:49:30", "throughput": 1489.45, "total_tokens": 12492960} {"current_steps": 59205, "total_steps": 181800, "loss": 0.0026, "lr": 4.263723234160717e-05, "epoch": 6.513201320132013, "percentage": 32.57, "elapsed_time": "2:19:48", "remaining_time": "4:49:29", "throughput": 1489.46, "total_tokens": 12494048} {"current_steps": 59210, "total_steps": 181800, "loss": 0.0229, "lr": 4.2635531282947175e-05, "epoch": 6.513751375137514, "percentage": 32.57, "elapsed_time": "2:19:49", "remaining_time": "4:49:28", "throughput": 1489.47, "total_tokens": 12495136} {"current_steps": 59215, "total_steps": 181800, "loss": 0.1393, "lr": 4.2633830061748946e-05, "epoch": 6.514301430143014, "percentage": 32.57, "elapsed_time": "2:19:49", "remaining_time": "4:49:28", "throughput": 1489.47, "total_tokens": 12496224} {"current_steps": 59220, "total_steps": 181800, "loss": 0.0758, "lr": 4.2632128678028175e-05, "epoch": 6.514851485148515, "percentage": 32.57, "elapsed_time": "2:19:50", "remaining_time": "4:49:27", "throughput": 1489.47, "total_tokens": 12497248} {"current_steps": 59225, "total_steps": 181800, "loss": 0.1531, "lr": 4.263042713180052e-05, "epoch": 6.5154015401540155, "percentage": 32.58, "elapsed_time": "2:19:51", "remaining_time": "4:49:26", "throughput": 1489.48, "total_tokens": 12498336} {"current_steps": 59230, "total_steps": 181800, "loss": 0.0099, "lr": 4.2628725423081684e-05, "epoch": 6.515951595159516, "percentage": 32.58, "elapsed_time": "2:19:51", "remaining_time": "4:49:25", "throughput": 1489.48, "total_tokens": 12499328} {"current_steps": 59235, "total_steps": 181800, "loss": 0.1243, "lr": 4.2627023551887346e-05, "epoch": 6.516501650165017, "percentage": 32.58, "elapsed_time": "2:19:52", "remaining_time": "4:49:25", "throughput": 1489.48, "total_tokens": 12500352} {"current_steps": 59240, "total_steps": 181800, "loss": 0.0105, "lr": 4.262532151823319e-05, "epoch": 6.517051705170517, "percentage": 32.59, "elapsed_time": "2:19:53", "remaining_time": "4:49:24", "throughput": 1489.48, "total_tokens": 12501376} {"current_steps": 59245, "total_steps": 181800, "loss": 0.0121, "lr": 4.26236193221349e-05, "epoch": 6.517601760176017, "percentage": 32.59, "elapsed_time": "2:19:53", "remaining_time": "4:49:23", "throughput": 1489.48, "total_tokens": 12502432} {"current_steps": 59250, "total_steps": 181800, "loss": 0.0182, "lr": 4.262191696360817e-05, "epoch": 6.518151815181518, "percentage": 32.59, "elapsed_time": "2:19:54", "remaining_time": "4:49:22", "throughput": 1489.49, "total_tokens": 12503520} {"current_steps": 59255, "total_steps": 181800, "loss": 0.0912, "lr": 4.2620214442668696e-05, "epoch": 6.5187018701870185, "percentage": 32.59, "elapsed_time": "2:19:55", "remaining_time": "4:49:22", "throughput": 1489.5, "total_tokens": 12504640} {"current_steps": 59260, "total_steps": 181800, "loss": 0.106, "lr": 4.261851175933215e-05, "epoch": 6.51925192519252, "percentage": 32.6, "elapsed_time": "2:19:55", "remaining_time": "4:49:21", "throughput": 1489.5, "total_tokens": 12505664} {"current_steps": 59265, "total_steps": 181800, "loss": 0.019, "lr": 4.261680891361423e-05, "epoch": 6.51980198019802, "percentage": 32.6, "elapsed_time": "2:19:56", "remaining_time": "4:49:20", "throughput": 1489.51, "total_tokens": 12506816} {"current_steps": 59270, "total_steps": 181800, "loss": 0.0528, "lr": 4.261510590553065e-05, "epoch": 6.52035203520352, "percentage": 32.6, "elapsed_time": "2:19:57", "remaining_time": "4:49:19", "throughput": 1489.52, "total_tokens": 12507904} {"current_steps": 59275, "total_steps": 181800, "loss": 0.0219, "lr": 4.2613402735097075e-05, "epoch": 6.520902090209021, "percentage": 32.6, "elapsed_time": "2:19:57", "remaining_time": "4:49:19", "throughput": 1489.52, "total_tokens": 12508928} {"current_steps": 59280, "total_steps": 181800, "loss": 0.0031, "lr": 4.261169940232923e-05, "epoch": 6.521452145214521, "percentage": 32.61, "elapsed_time": "2:19:58", "remaining_time": "4:49:18", "throughput": 1489.52, "total_tokens": 12509952} {"current_steps": 59285, "total_steps": 181800, "loss": 0.0373, "lr": 4.260999590724281e-05, "epoch": 6.522002200220022, "percentage": 32.61, "elapsed_time": "2:19:59", "remaining_time": "4:49:17", "throughput": 1489.53, "total_tokens": 12511040} {"current_steps": 59290, "total_steps": 181800, "loss": 0.0247, "lr": 4.260829224985349e-05, "epoch": 6.522552255225523, "percentage": 32.61, "elapsed_time": "2:20:00", "remaining_time": "4:49:16", "throughput": 1489.53, "total_tokens": 12512096} {"current_steps": 59295, "total_steps": 181800, "loss": 0.055, "lr": 4.2606588430177e-05, "epoch": 6.523102310231023, "percentage": 32.62, "elapsed_time": "2:20:00", "remaining_time": "4:49:16", "throughput": 1489.53, "total_tokens": 12513152} {"current_steps": 59300, "total_steps": 181800, "loss": 0.057, "lr": 4.260488444822903e-05, "epoch": 6.523652365236524, "percentage": 32.62, "elapsed_time": "2:20:01", "remaining_time": "4:49:15", "throughput": 1489.53, "total_tokens": 12514144} {"current_steps": 59305, "total_steps": 181800, "loss": 0.0064, "lr": 4.260318030402529e-05, "epoch": 6.524202420242024, "percentage": 32.62, "elapsed_time": "2:20:02", "remaining_time": "4:49:14", "throughput": 1489.53, "total_tokens": 12515200} {"current_steps": 59310, "total_steps": 181800, "loss": 0.105, "lr": 4.260147599758148e-05, "epoch": 6.524752475247524, "percentage": 32.62, "elapsed_time": "2:20:02", "remaining_time": "4:49:13", "throughput": 1489.54, "total_tokens": 12516256} {"current_steps": 59315, "total_steps": 181800, "loss": 0.0043, "lr": 4.259977152891331e-05, "epoch": 6.525302530253025, "percentage": 32.63, "elapsed_time": "2:20:03", "remaining_time": "4:49:13", "throughput": 1489.54, "total_tokens": 12517312} {"current_steps": 59320, "total_steps": 181800, "loss": 0.0469, "lr": 4.25980668980365e-05, "epoch": 6.525852585258526, "percentage": 32.63, "elapsed_time": "2:20:04", "remaining_time": "4:49:12", "throughput": 1489.54, "total_tokens": 12518368} {"current_steps": 59325, "total_steps": 181800, "loss": 0.0373, "lr": 4.259636210496675e-05, "epoch": 6.526402640264027, "percentage": 32.63, "elapsed_time": "2:20:04", "remaining_time": "4:49:11", "throughput": 1489.55, "total_tokens": 12519424} {"current_steps": 59330, "total_steps": 181800, "loss": 0.0954, "lr": 4.259465714971977e-05, "epoch": 6.526952695269527, "percentage": 32.63, "elapsed_time": "2:20:05", "remaining_time": "4:49:10", "throughput": 1489.56, "total_tokens": 12520576} {"current_steps": 59335, "total_steps": 181800, "loss": 0.0076, "lr": 4.259295203231128e-05, "epoch": 6.527502750275027, "percentage": 32.64, "elapsed_time": "2:20:06", "remaining_time": "4:49:10", "throughput": 1489.57, "total_tokens": 12521664} {"current_steps": 59340, "total_steps": 181800, "loss": 0.0931, "lr": 4.2591246752756986e-05, "epoch": 6.528052805280528, "percentage": 32.64, "elapsed_time": "2:20:06", "remaining_time": "4:49:09", "throughput": 1489.57, "total_tokens": 12522688} {"current_steps": 59345, "total_steps": 181800, "loss": 0.0557, "lr": 4.258954131107262e-05, "epoch": 6.528602860286028, "percentage": 32.64, "elapsed_time": "2:20:07", "remaining_time": "4:49:08", "throughput": 1489.57, "total_tokens": 12523744} {"current_steps": 59350, "total_steps": 181800, "loss": 0.0742, "lr": 4.2587835707273895e-05, "epoch": 6.5291529152915295, "percentage": 32.65, "elapsed_time": "2:20:08", "remaining_time": "4:49:07", "throughput": 1489.58, "total_tokens": 12524832} {"current_steps": 59355, "total_steps": 181800, "loss": 0.0263, "lr": 4.2586129941376515e-05, "epoch": 6.52970297029703, "percentage": 32.65, "elapsed_time": "2:20:08", "remaining_time": "4:49:07", "throughput": 1489.58, "total_tokens": 12525888} {"current_steps": 59360, "total_steps": 181800, "loss": 0.018, "lr": 4.258442401339622e-05, "epoch": 6.53025302530253, "percentage": 32.65, "elapsed_time": "2:20:09", "remaining_time": "4:49:06", "throughput": 1489.59, "total_tokens": 12527008} {"current_steps": 59365, "total_steps": 181800, "loss": 0.0095, "lr": 4.258271792334873e-05, "epoch": 6.530803080308031, "percentage": 32.65, "elapsed_time": "2:20:10", "remaining_time": "4:49:05", "throughput": 1489.6, "total_tokens": 12528064} {"current_steps": 59370, "total_steps": 181800, "loss": 0.1624, "lr": 4.2581011671249766e-05, "epoch": 6.531353135313531, "percentage": 32.66, "elapsed_time": "2:20:11", "remaining_time": "4:49:04", "throughput": 1489.6, "total_tokens": 12529120} {"current_steps": 59375, "total_steps": 181800, "loss": 0.0049, "lr": 4.2579305257115057e-05, "epoch": 6.531903190319031, "percentage": 32.66, "elapsed_time": "2:20:11", "remaining_time": "4:49:04", "throughput": 1489.6, "total_tokens": 12530176} {"current_steps": 59380, "total_steps": 181800, "loss": 0.027, "lr": 4.257759868096032e-05, "epoch": 6.5324532453245325, "percentage": 32.66, "elapsed_time": "2:20:12", "remaining_time": "4:49:03", "throughput": 1489.61, "total_tokens": 12531264} {"current_steps": 59385, "total_steps": 181800, "loss": 0.0635, "lr": 4.2575891942801286e-05, "epoch": 6.533003300330033, "percentage": 32.67, "elapsed_time": "2:20:13", "remaining_time": "4:49:02", "throughput": 1489.62, "total_tokens": 12532320} {"current_steps": 59390, "total_steps": 181800, "loss": 0.1089, "lr": 4.2574185042653695e-05, "epoch": 6.533553355335534, "percentage": 32.67, "elapsed_time": "2:20:13", "remaining_time": "4:49:01", "throughput": 1489.62, "total_tokens": 12533344} {"current_steps": 59395, "total_steps": 181800, "loss": 0.0077, "lr": 4.257247798053328e-05, "epoch": 6.534103410341034, "percentage": 32.67, "elapsed_time": "2:20:14", "remaining_time": "4:49:01", "throughput": 1489.62, "total_tokens": 12534400} {"current_steps": 59400, "total_steps": 181800, "loss": 0.0137, "lr": 4.257077075645576e-05, "epoch": 6.534653465346535, "percentage": 32.67, "elapsed_time": "2:20:15", "remaining_time": "4:49:00", "throughput": 1489.61, "total_tokens": 12535392} {"current_steps": 59405, "total_steps": 181800, "loss": 0.0267, "lr": 4.256906337043688e-05, "epoch": 6.535203520352035, "percentage": 32.68, "elapsed_time": "2:20:15", "remaining_time": "4:48:59", "throughput": 1489.62, "total_tokens": 12536512} {"current_steps": 59410, "total_steps": 181800, "loss": 0.0541, "lr": 4.256735582249237e-05, "epoch": 6.5357535753575355, "percentage": 32.68, "elapsed_time": "2:20:16", "remaining_time": "4:48:58", "throughput": 1489.62, "total_tokens": 12537504} {"current_steps": 59415, "total_steps": 181800, "loss": 0.0156, "lr": 4.256564811263797e-05, "epoch": 6.536303630363037, "percentage": 32.68, "elapsed_time": "2:20:17", "remaining_time": "4:48:58", "throughput": 1489.62, "total_tokens": 12538528} {"current_steps": 59420, "total_steps": 181800, "loss": 0.0434, "lr": 4.2563940240889425e-05, "epoch": 6.536853685368537, "percentage": 32.68, "elapsed_time": "2:20:17", "remaining_time": "4:48:57", "throughput": 1489.62, "total_tokens": 12539584} {"current_steps": 59425, "total_steps": 181800, "loss": 0.0945, "lr": 4.256223220726247e-05, "epoch": 6.537403740374037, "percentage": 32.69, "elapsed_time": "2:20:18", "remaining_time": "4:48:56", "throughput": 1489.63, "total_tokens": 12540640} {"current_steps": 59430, "total_steps": 181800, "loss": 0.0598, "lr": 4.256052401177285e-05, "epoch": 6.537953795379538, "percentage": 32.69, "elapsed_time": "2:20:19", "remaining_time": "4:48:55", "throughput": 1489.64, "total_tokens": 12541728} {"current_steps": 59435, "total_steps": 181800, "loss": 0.0209, "lr": 4.25588156544363e-05, "epoch": 6.538503850385038, "percentage": 32.69, "elapsed_time": "2:20:20", "remaining_time": "4:48:55", "throughput": 1489.64, "total_tokens": 12542752} {"current_steps": 59440, "total_steps": 181800, "loss": 0.066, "lr": 4.255710713526857e-05, "epoch": 6.539053905390539, "percentage": 32.7, "elapsed_time": "2:20:20", "remaining_time": "4:48:54", "throughput": 1489.64, "total_tokens": 12543776} {"current_steps": 59445, "total_steps": 181800, "loss": 0.0186, "lr": 4.2555398454285424e-05, "epoch": 6.53960396039604, "percentage": 32.7, "elapsed_time": "2:20:21", "remaining_time": "4:48:53", "throughput": 1489.64, "total_tokens": 12544800} {"current_steps": 59450, "total_steps": 181800, "loss": 0.0647, "lr": 4.255368961150258e-05, "epoch": 6.54015401540154, "percentage": 32.7, "elapsed_time": "2:20:22", "remaining_time": "4:48:52", "throughput": 1489.64, "total_tokens": 12545856} {"current_steps": 59455, "total_steps": 181800, "loss": 0.0661, "lr": 4.25519806069358e-05, "epoch": 6.540704070407041, "percentage": 32.7, "elapsed_time": "2:20:22", "remaining_time": "4:48:52", "throughput": 1489.65, "total_tokens": 12546944} {"current_steps": 59460, "total_steps": 181800, "loss": 0.0703, "lr": 4.255027144060085e-05, "epoch": 6.541254125412541, "percentage": 32.71, "elapsed_time": "2:20:23", "remaining_time": "4:48:51", "throughput": 1489.65, "total_tokens": 12548032} {"current_steps": 59465, "total_steps": 181800, "loss": 0.0595, "lr": 4.254856211251346e-05, "epoch": 6.541804180418042, "percentage": 32.71, "elapsed_time": "2:20:24", "remaining_time": "4:48:50", "throughput": 1489.66, "total_tokens": 12549120} {"current_steps": 59470, "total_steps": 181800, "loss": 0.1438, "lr": 4.254685262268939e-05, "epoch": 6.542354235423542, "percentage": 32.71, "elapsed_time": "2:20:24", "remaining_time": "4:48:49", "throughput": 1489.67, "total_tokens": 12550240} {"current_steps": 59475, "total_steps": 181800, "loss": 0.0929, "lr": 4.254514297114441e-05, "epoch": 6.542904290429043, "percentage": 32.71, "elapsed_time": "2:20:25", "remaining_time": "4:48:49", "throughput": 1489.67, "total_tokens": 12551296} {"current_steps": 59480, "total_steps": 181800, "loss": 0.01, "lr": 4.254343315789427e-05, "epoch": 6.543454345434544, "percentage": 32.72, "elapsed_time": "2:20:26", "remaining_time": "4:48:48", "throughput": 1489.67, "total_tokens": 12552288} {"current_steps": 59485, "total_steps": 181800, "loss": 0.0404, "lr": 4.254172318295471e-05, "epoch": 6.544004400440044, "percentage": 32.72, "elapsed_time": "2:20:26", "remaining_time": "4:48:47", "throughput": 1489.67, "total_tokens": 12553312} {"current_steps": 59490, "total_steps": 181800, "loss": 0.0201, "lr": 4.254001304634151e-05, "epoch": 6.544554455445544, "percentage": 32.72, "elapsed_time": "2:20:27", "remaining_time": "4:48:46", "throughput": 1489.67, "total_tokens": 12554400} {"current_steps": 59495, "total_steps": 181800, "loss": 0.0941, "lr": 4.2538302748070427e-05, "epoch": 6.545104510451045, "percentage": 32.73, "elapsed_time": "2:20:28", "remaining_time": "4:48:46", "throughput": 1489.67, "total_tokens": 12555424} {"current_steps": 59500, "total_steps": 181800, "loss": 0.0965, "lr": 4.253659228815722e-05, "epoch": 6.5456545654565454, "percentage": 32.73, "elapsed_time": "2:20:28", "remaining_time": "4:48:45", "throughput": 1489.67, "total_tokens": 12556448} {"current_steps": 59505, "total_steps": 181800, "loss": 0.01, "lr": 4.253488166661767e-05, "epoch": 6.5462046204620465, "percentage": 32.73, "elapsed_time": "2:20:29", "remaining_time": "4:48:44", "throughput": 1489.68, "total_tokens": 12557568} {"current_steps": 59510, "total_steps": 181800, "loss": 0.0487, "lr": 4.253317088346751e-05, "epoch": 6.546754675467547, "percentage": 32.73, "elapsed_time": "2:20:30", "remaining_time": "4:48:43", "throughput": 1489.68, "total_tokens": 12558528} {"current_steps": 59515, "total_steps": 181800, "loss": 0.0644, "lr": 4.253145993872254e-05, "epoch": 6.547304730473047, "percentage": 32.74, "elapsed_time": "2:20:31", "remaining_time": "4:48:43", "throughput": 1489.69, "total_tokens": 12559648} {"current_steps": 59520, "total_steps": 181800, "loss": 0.0043, "lr": 4.2529748832398513e-05, "epoch": 6.547854785478548, "percentage": 32.74, "elapsed_time": "2:20:31", "remaining_time": "4:48:42", "throughput": 1489.69, "total_tokens": 12560672} {"current_steps": 59525, "total_steps": 181800, "loss": 0.0306, "lr": 4.2528037564511204e-05, "epoch": 6.548404840484048, "percentage": 32.74, "elapsed_time": "2:20:32", "remaining_time": "4:48:41", "throughput": 1489.69, "total_tokens": 12561696} {"current_steps": 59530, "total_steps": 181800, "loss": 0.0539, "lr": 4.2526326135076375e-05, "epoch": 6.548954895489549, "percentage": 32.74, "elapsed_time": "2:20:33", "remaining_time": "4:48:41", "throughput": 1489.7, "total_tokens": 12562816} {"current_steps": 59535, "total_steps": 181800, "loss": 0.0361, "lr": 4.252461454410982e-05, "epoch": 6.5495049504950495, "percentage": 32.75, "elapsed_time": "2:20:33", "remaining_time": "4:48:40", "throughput": 1489.7, "total_tokens": 12563840} {"current_steps": 59540, "total_steps": 181800, "loss": 0.0041, "lr": 4.2522902791627294e-05, "epoch": 6.55005500550055, "percentage": 32.75, "elapsed_time": "2:20:34", "remaining_time": "4:48:39", "throughput": 1489.71, "total_tokens": 12564960} {"current_steps": 59545, "total_steps": 181800, "loss": 0.0592, "lr": 4.252119087764459e-05, "epoch": 6.550605060506051, "percentage": 32.75, "elapsed_time": "2:20:35", "remaining_time": "4:48:38", "throughput": 1489.71, "total_tokens": 12565984} {"current_steps": 59550, "total_steps": 181800, "loss": 0.0276, "lr": 4.251947880217747e-05, "epoch": 6.551155115511551, "percentage": 32.76, "elapsed_time": "2:20:35", "remaining_time": "4:48:38", "throughput": 1489.71, "total_tokens": 12567072} {"current_steps": 59555, "total_steps": 181800, "loss": 0.0323, "lr": 4.251776656524172e-05, "epoch": 6.551705170517051, "percentage": 32.76, "elapsed_time": "2:20:36", "remaining_time": "4:48:37", "throughput": 1489.72, "total_tokens": 12568128} {"current_steps": 59560, "total_steps": 181800, "loss": 0.0497, "lr": 4.251605416685312e-05, "epoch": 6.552255225522552, "percentage": 32.76, "elapsed_time": "2:20:37", "remaining_time": "4:48:36", "throughput": 1489.73, "total_tokens": 12569280} {"current_steps": 59565, "total_steps": 181800, "loss": 0.0184, "lr": 4.251434160702746e-05, "epoch": 6.552805280528053, "percentage": 32.76, "elapsed_time": "2:20:37", "remaining_time": "4:48:35", "throughput": 1489.73, "total_tokens": 12570336} {"current_steps": 59570, "total_steps": 181800, "loss": 0.0503, "lr": 4.251262888578052e-05, "epoch": 6.553355335533554, "percentage": 32.77, "elapsed_time": "2:20:38", "remaining_time": "4:48:35", "throughput": 1489.73, "total_tokens": 12571360} {"current_steps": 59575, "total_steps": 181800, "loss": 0.0125, "lr": 4.2510916003128076e-05, "epoch": 6.553905390539054, "percentage": 32.77, "elapsed_time": "2:20:39", "remaining_time": "4:48:34", "throughput": 1489.74, "total_tokens": 12572416} {"current_steps": 59580, "total_steps": 181800, "loss": 0.0396, "lr": 4.250920295908593e-05, "epoch": 6.554455445544555, "percentage": 32.77, "elapsed_time": "2:20:40", "remaining_time": "4:48:33", "throughput": 1489.74, "total_tokens": 12573440} {"current_steps": 59585, "total_steps": 181800, "loss": 0.1402, "lr": 4.250748975366985e-05, "epoch": 6.555005500550055, "percentage": 32.78, "elapsed_time": "2:20:40", "remaining_time": "4:48:32", "throughput": 1489.74, "total_tokens": 12574528} {"current_steps": 59590, "total_steps": 181800, "loss": 0.0561, "lr": 4.2505776386895644e-05, "epoch": 6.555555555555555, "percentage": 32.78, "elapsed_time": "2:20:41", "remaining_time": "4:48:32", "throughput": 1489.75, "total_tokens": 12575584} {"current_steps": 59595, "total_steps": 181800, "loss": 0.0219, "lr": 4.250406285877909e-05, "epoch": 6.5561056105610565, "percentage": 32.78, "elapsed_time": "2:20:42", "remaining_time": "4:48:31", "throughput": 1489.75, "total_tokens": 12576608} {"current_steps": 59600, "total_steps": 181800, "loss": 0.0305, "lr": 4.2502349169335996e-05, "epoch": 6.556655665566557, "percentage": 32.78, "elapsed_time": "2:20:42", "remaining_time": "4:48:30", "throughput": 1489.74, "total_tokens": 12577600} {"current_steps": 59605, "total_steps": 181800, "loss": 0.0172, "lr": 4.250063531858215e-05, "epoch": 6.557205720572057, "percentage": 32.79, "elapsed_time": "2:20:43", "remaining_time": "4:48:29", "throughput": 1489.74, "total_tokens": 12578592} {"current_steps": 59610, "total_steps": 181800, "loss": 0.0126, "lr": 4.249892130653335e-05, "epoch": 6.557755775577558, "percentage": 32.79, "elapsed_time": "2:20:44", "remaining_time": "4:48:29", "throughput": 1489.74, "total_tokens": 12579648} {"current_steps": 59615, "total_steps": 181800, "loss": 0.0742, "lr": 4.249720713320537e-05, "epoch": 6.558305830583058, "percentage": 32.79, "elapsed_time": "2:20:44", "remaining_time": "4:48:28", "throughput": 1489.74, "total_tokens": 12580704} {"current_steps": 59620, "total_steps": 181800, "loss": 0.0072, "lr": 4.249549279861404e-05, "epoch": 6.558855885588558, "percentage": 32.79, "elapsed_time": "2:20:45", "remaining_time": "4:48:27", "throughput": 1489.73, "total_tokens": 12581664} {"current_steps": 59625, "total_steps": 181800, "loss": 0.0197, "lr": 4.2493778302775155e-05, "epoch": 6.5594059405940595, "percentage": 32.8, "elapsed_time": "2:20:46", "remaining_time": "4:48:26", "throughput": 1489.74, "total_tokens": 12582720} {"current_steps": 59630, "total_steps": 181800, "loss": 0.011, "lr": 4.2492063645704496e-05, "epoch": 6.55995599559956, "percentage": 32.8, "elapsed_time": "2:20:46", "remaining_time": "4:48:26", "throughput": 1489.74, "total_tokens": 12583776} {"current_steps": 59635, "total_steps": 181800, "loss": 0.0107, "lr": 4.2490348827417894e-05, "epoch": 6.560506050605061, "percentage": 32.8, "elapsed_time": "2:20:47", "remaining_time": "4:48:25", "throughput": 1489.74, "total_tokens": 12584768} {"current_steps": 59640, "total_steps": 181800, "loss": 0.0098, "lr": 4.248863384793113e-05, "epoch": 6.561056105610561, "percentage": 32.81, "elapsed_time": "2:20:48", "remaining_time": "4:48:24", "throughput": 1489.74, "total_tokens": 12585824} {"current_steps": 59645, "total_steps": 181800, "loss": 0.0123, "lr": 4.248691870726002e-05, "epoch": 6.561606160616062, "percentage": 32.81, "elapsed_time": "2:20:49", "remaining_time": "4:48:23", "throughput": 1489.75, "total_tokens": 12586912} {"current_steps": 59650, "total_steps": 181800, "loss": 0.0037, "lr": 4.248520340542037e-05, "epoch": 6.562156215621562, "percentage": 32.81, "elapsed_time": "2:20:49", "remaining_time": "4:48:23", "throughput": 1489.75, "total_tokens": 12587968} {"current_steps": 59655, "total_steps": 181800, "loss": 0.1172, "lr": 4.248348794242799e-05, "epoch": 6.5627062706270625, "percentage": 32.81, "elapsed_time": "2:20:50", "remaining_time": "4:48:22", "throughput": 1489.75, "total_tokens": 12589024} {"current_steps": 59660, "total_steps": 181800, "loss": 0.0978, "lr": 4.24817723182987e-05, "epoch": 6.563256325632564, "percentage": 32.82, "elapsed_time": "2:20:51", "remaining_time": "4:48:21", "throughput": 1489.75, "total_tokens": 12590048} {"current_steps": 59665, "total_steps": 181800, "loss": 0.0118, "lr": 4.2480056533048296e-05, "epoch": 6.563806380638064, "percentage": 32.82, "elapsed_time": "2:20:51", "remaining_time": "4:48:20", "throughput": 1489.75, "total_tokens": 12591072} {"current_steps": 59670, "total_steps": 181800, "loss": 0.0047, "lr": 4.24783405866926e-05, "epoch": 6.564356435643564, "percentage": 32.82, "elapsed_time": "2:20:52", "remaining_time": "4:48:20", "throughput": 1489.75, "total_tokens": 12592096} {"current_steps": 59675, "total_steps": 181800, "loss": 0.0663, "lr": 4.247662447924743e-05, "epoch": 6.564906490649065, "percentage": 32.82, "elapsed_time": "2:20:53", "remaining_time": "4:48:19", "throughput": 1489.75, "total_tokens": 12593120} {"current_steps": 59680, "total_steps": 181800, "loss": 0.0667, "lr": 4.2474908210728594e-05, "epoch": 6.565456545654565, "percentage": 32.83, "elapsed_time": "2:20:53", "remaining_time": "4:48:18", "throughput": 1489.75, "total_tokens": 12594112} {"current_steps": 59685, "total_steps": 181800, "loss": 0.0437, "lr": 4.247319178115191e-05, "epoch": 6.566006600660066, "percentage": 32.83, "elapsed_time": "2:20:54", "remaining_time": "4:48:17", "throughput": 1489.75, "total_tokens": 12595136} {"current_steps": 59690, "total_steps": 181800, "loss": 0.0818, "lr": 4.2471475190533204e-05, "epoch": 6.566556655665567, "percentage": 32.83, "elapsed_time": "2:20:55", "remaining_time": "4:48:17", "throughput": 1489.77, "total_tokens": 12596320} {"current_steps": 59695, "total_steps": 181800, "loss": 0.0487, "lr": 4.2469758438888295e-05, "epoch": 6.567106710671067, "percentage": 32.84, "elapsed_time": "2:20:55", "remaining_time": "4:48:16", "throughput": 1489.77, "total_tokens": 12597376} {"current_steps": 59700, "total_steps": 181800, "loss": 0.0615, "lr": 4.2468041526233014e-05, "epoch": 6.567656765676568, "percentage": 32.84, "elapsed_time": "2:20:56", "remaining_time": "4:48:15", "throughput": 1489.77, "total_tokens": 12598432} {"current_steps": 59705, "total_steps": 181800, "loss": 0.0982, "lr": 4.2466324452583164e-05, "epoch": 6.568206820682068, "percentage": 32.84, "elapsed_time": "2:20:57", "remaining_time": "4:48:14", "throughput": 1489.77, "total_tokens": 12599456} {"current_steps": 59710, "total_steps": 181800, "loss": 0.0892, "lr": 4.2464607217954594e-05, "epoch": 6.568756875687569, "percentage": 32.84, "elapsed_time": "2:20:57", "remaining_time": "4:48:14", "throughput": 1489.78, "total_tokens": 12600512} {"current_steps": 59715, "total_steps": 181800, "loss": 0.0165, "lr": 4.246288982236311e-05, "epoch": 6.569306930693069, "percentage": 32.85, "elapsed_time": "2:20:58", "remaining_time": "4:48:13", "throughput": 1489.78, "total_tokens": 12601600} {"current_steps": 59720, "total_steps": 181800, "loss": 0.0168, "lr": 4.2461172265824556e-05, "epoch": 6.56985698569857, "percentage": 32.85, "elapsed_time": "2:20:59", "remaining_time": "4:48:12", "throughput": 1489.78, "total_tokens": 12602592} {"current_steps": 59725, "total_steps": 181800, "loss": 0.0282, "lr": 4.245945454835475e-05, "epoch": 6.570407040704071, "percentage": 32.85, "elapsed_time": "2:21:00", "remaining_time": "4:48:11", "throughput": 1489.78, "total_tokens": 12603616} {"current_steps": 59730, "total_steps": 181800, "loss": 0.0146, "lr": 4.2457736669969536e-05, "epoch": 6.570957095709571, "percentage": 32.85, "elapsed_time": "2:21:00", "remaining_time": "4:48:11", "throughput": 1489.78, "total_tokens": 12604672} {"current_steps": 59735, "total_steps": 181800, "loss": 0.0398, "lr": 4.245601863068474e-05, "epoch": 6.571507150715071, "percentage": 32.86, "elapsed_time": "2:21:01", "remaining_time": "4:48:10", "throughput": 1489.78, "total_tokens": 12605696} {"current_steps": 59740, "total_steps": 181800, "loss": 0.0111, "lr": 4.245430043051619e-05, "epoch": 6.572057205720572, "percentage": 32.86, "elapsed_time": "2:21:02", "remaining_time": "4:48:09", "throughput": 1489.79, "total_tokens": 12606752} {"current_steps": 59745, "total_steps": 181800, "loss": 0.1071, "lr": 4.245258206947973e-05, "epoch": 6.572607260726072, "percentage": 32.86, "elapsed_time": "2:21:02", "remaining_time": "4:48:08", "throughput": 1489.79, "total_tokens": 12607808} {"current_steps": 59750, "total_steps": 181800, "loss": 0.0116, "lr": 4.2450863547591204e-05, "epoch": 6.5731573157315735, "percentage": 32.87, "elapsed_time": "2:21:03", "remaining_time": "4:48:08", "throughput": 1489.77, "total_tokens": 12608928} {"current_steps": 59755, "total_steps": 181800, "loss": 0.0437, "lr": 4.244914486486643e-05, "epoch": 6.573707370737074, "percentage": 32.87, "elapsed_time": "2:21:04", "remaining_time": "4:48:07", "throughput": 1489.78, "total_tokens": 12610016} {"current_steps": 59760, "total_steps": 181800, "loss": 0.0359, "lr": 4.244742602132127e-05, "epoch": 6.574257425742574, "percentage": 32.87, "elapsed_time": "2:21:05", "remaining_time": "4:48:07", "throughput": 1489.79, "total_tokens": 12611168} {"current_steps": 59765, "total_steps": 181800, "loss": 0.0195, "lr": 4.244570701697155e-05, "epoch": 6.574807480748075, "percentage": 32.87, "elapsed_time": "2:21:05", "remaining_time": "4:48:06", "throughput": 1489.79, "total_tokens": 12612160} {"current_steps": 59770, "total_steps": 181800, "loss": 0.0228, "lr": 4.2443987851833124e-05, "epoch": 6.575357535753575, "percentage": 32.88, "elapsed_time": "2:21:06", "remaining_time": "4:48:05", "throughput": 1489.79, "total_tokens": 12613216} {"current_steps": 59775, "total_steps": 181800, "loss": 0.0921, "lr": 4.244226852592183e-05, "epoch": 6.575907590759076, "percentage": 32.88, "elapsed_time": "2:21:07", "remaining_time": "4:48:04", "throughput": 1489.79, "total_tokens": 12614272} {"current_steps": 59780, "total_steps": 181800, "loss": 0.0055, "lr": 4.244054903925352e-05, "epoch": 6.5764576457645765, "percentage": 32.88, "elapsed_time": "2:21:07", "remaining_time": "4:48:04", "throughput": 1489.79, "total_tokens": 12615296} {"current_steps": 59785, "total_steps": 181800, "loss": 0.0291, "lr": 4.243882939184404e-05, "epoch": 6.577007700770077, "percentage": 32.89, "elapsed_time": "2:21:08", "remaining_time": "4:48:03", "throughput": 1489.79, "total_tokens": 12616288} {"current_steps": 59790, "total_steps": 181800, "loss": 0.056, "lr": 4.243710958370923e-05, "epoch": 6.577557755775578, "percentage": 32.89, "elapsed_time": "2:21:09", "remaining_time": "4:48:02", "throughput": 1489.79, "total_tokens": 12617344} {"current_steps": 59795, "total_steps": 181800, "loss": 0.0312, "lr": 4.243538961486495e-05, "epoch": 6.578107810781078, "percentage": 32.89, "elapsed_time": "2:21:09", "remaining_time": "4:48:01", "throughput": 1489.79, "total_tokens": 12618304} {"current_steps": 59800, "total_steps": 181800, "loss": 0.1134, "lr": 4.243366948532705e-05, "epoch": 6.578657865786578, "percentage": 32.89, "elapsed_time": "2:21:10", "remaining_time": "4:48:01", "throughput": 1489.79, "total_tokens": 12619360} {"current_steps": 59805, "total_steps": 181800, "loss": 0.0091, "lr": 4.243194919511139e-05, "epoch": 6.579207920792079, "percentage": 32.9, "elapsed_time": "2:21:11", "remaining_time": "4:48:00", "throughput": 1489.79, "total_tokens": 12620416} {"current_steps": 59810, "total_steps": 181800, "loss": 0.0591, "lr": 4.243022874423381e-05, "epoch": 6.5797579757975795, "percentage": 32.9, "elapsed_time": "2:21:11", "remaining_time": "4:47:59", "throughput": 1489.8, "total_tokens": 12621536} {"current_steps": 59815, "total_steps": 181800, "loss": 0.0353, "lr": 4.242850813271018e-05, "epoch": 6.580308030803081, "percentage": 32.9, "elapsed_time": "2:21:12", "remaining_time": "4:47:58", "throughput": 1489.8, "total_tokens": 12622560} {"current_steps": 59820, "total_steps": 181800, "loss": 0.0226, "lr": 4.2426787360556355e-05, "epoch": 6.580858085808581, "percentage": 32.9, "elapsed_time": "2:21:13", "remaining_time": "4:47:58", "throughput": 1489.81, "total_tokens": 12623648} {"current_steps": 59825, "total_steps": 181800, "loss": 0.0358, "lr": 4.24250664277882e-05, "epoch": 6.581408140814082, "percentage": 32.91, "elapsed_time": "2:21:14", "remaining_time": "4:47:57", "throughput": 1489.81, "total_tokens": 12624704} {"current_steps": 59830, "total_steps": 181800, "loss": 0.1307, "lr": 4.242334533442156e-05, "epoch": 6.581958195819582, "percentage": 32.91, "elapsed_time": "2:21:14", "remaining_time": "4:47:56", "throughput": 1489.82, "total_tokens": 12625760} {"current_steps": 59835, "total_steps": 181800, "loss": 0.0824, "lr": 4.24216240804723e-05, "epoch": 6.582508250825082, "percentage": 32.91, "elapsed_time": "2:21:15", "remaining_time": "4:47:55", "throughput": 1489.82, "total_tokens": 12626816} {"current_steps": 59840, "total_steps": 181800, "loss": 0.0178, "lr": 4.24199026659563e-05, "epoch": 6.583058305830583, "percentage": 32.92, "elapsed_time": "2:21:16", "remaining_time": "4:47:55", "throughput": 1489.83, "total_tokens": 12627904} {"current_steps": 59845, "total_steps": 181800, "loss": 0.0114, "lr": 4.2418181090889415e-05, "epoch": 6.583608360836084, "percentage": 32.92, "elapsed_time": "2:21:16", "remaining_time": "4:47:54", "throughput": 1489.84, "total_tokens": 12629024} {"current_steps": 59850, "total_steps": 181800, "loss": 0.0697, "lr": 4.241645935528751e-05, "epoch": 6.584158415841584, "percentage": 32.92, "elapsed_time": "2:21:17", "remaining_time": "4:47:53", "throughput": 1489.83, "total_tokens": 12630016} {"current_steps": 59855, "total_steps": 181800, "loss": 0.0294, "lr": 4.241473745916646e-05, "epoch": 6.584708470847085, "percentage": 32.92, "elapsed_time": "2:21:18", "remaining_time": "4:47:52", "throughput": 1489.84, "total_tokens": 12631104} {"current_steps": 59860, "total_steps": 181800, "loss": 0.0417, "lr": 4.2413015402542125e-05, "epoch": 6.585258525852585, "percentage": 32.93, "elapsed_time": "2:21:18", "remaining_time": "4:47:52", "throughput": 1489.85, "total_tokens": 12632224} {"current_steps": 59865, "total_steps": 181800, "loss": 0.0365, "lr": 4.241129318543039e-05, "epoch": 6.585808580858086, "percentage": 32.93, "elapsed_time": "2:21:19", "remaining_time": "4:47:51", "throughput": 1489.86, "total_tokens": 12633280} {"current_steps": 59870, "total_steps": 181800, "loss": 0.0654, "lr": 4.2409570807847115e-05, "epoch": 6.586358635863586, "percentage": 32.93, "elapsed_time": "2:21:20", "remaining_time": "4:47:50", "throughput": 1489.86, "total_tokens": 12634336} {"current_steps": 59875, "total_steps": 181800, "loss": 0.1339, "lr": 4.2407848269808185e-05, "epoch": 6.586908690869087, "percentage": 32.93, "elapsed_time": "2:21:20", "remaining_time": "4:47:49", "throughput": 1489.87, "total_tokens": 12635456} {"current_steps": 59880, "total_steps": 181800, "loss": 0.06, "lr": 4.240612557132947e-05, "epoch": 6.587458745874588, "percentage": 32.94, "elapsed_time": "2:21:21", "remaining_time": "4:47:49", "throughput": 1489.88, "total_tokens": 12636544} {"current_steps": 59885, "total_steps": 181800, "loss": 0.0697, "lr": 4.2404402712426844e-05, "epoch": 6.588008800880088, "percentage": 32.94, "elapsed_time": "2:21:22", "remaining_time": "4:47:48", "throughput": 1489.88, "total_tokens": 12637568} {"current_steps": 59890, "total_steps": 181800, "loss": 0.0049, "lr": 4.240267969311619e-05, "epoch": 6.588558855885589, "percentage": 32.94, "elapsed_time": "2:21:22", "remaining_time": "4:47:47", "throughput": 1489.89, "total_tokens": 12638688} {"current_steps": 59895, "total_steps": 181800, "loss": 0.0028, "lr": 4.240095651341339e-05, "epoch": 6.589108910891089, "percentage": 32.95, "elapsed_time": "2:21:23", "remaining_time": "4:47:46", "throughput": 1489.89, "total_tokens": 12639712} {"current_steps": 59900, "total_steps": 181800, "loss": 0.0253, "lr": 4.239923317333433e-05, "epoch": 6.589658965896589, "percentage": 32.95, "elapsed_time": "2:21:24", "remaining_time": "4:47:46", "throughput": 1489.89, "total_tokens": 12640736} {"current_steps": 59905, "total_steps": 181800, "loss": 0.038, "lr": 4.239750967289487e-05, "epoch": 6.5902090209020905, "percentage": 32.95, "elapsed_time": "2:21:25", "remaining_time": "4:47:45", "throughput": 1489.89, "total_tokens": 12641760} {"current_steps": 59910, "total_steps": 181800, "loss": 0.0144, "lr": 4.2395786012110924e-05, "epoch": 6.590759075907591, "percentage": 32.95, "elapsed_time": "2:21:25", "remaining_time": "4:47:44", "throughput": 1489.89, "total_tokens": 12642784} {"current_steps": 59915, "total_steps": 181800, "loss": 0.0345, "lr": 4.2394062190998365e-05, "epoch": 6.591309130913091, "percentage": 32.96, "elapsed_time": "2:21:26", "remaining_time": "4:47:43", "throughput": 1489.9, "total_tokens": 12643872} {"current_steps": 59920, "total_steps": 181800, "loss": 0.0147, "lr": 4.2392338209573076e-05, "epoch": 6.591859185918592, "percentage": 32.96, "elapsed_time": "2:21:27", "remaining_time": "4:47:43", "throughput": 1489.9, "total_tokens": 12644960} {"current_steps": 59925, "total_steps": 181800, "loss": 0.0289, "lr": 4.2390614067850956e-05, "epoch": 6.592409240924092, "percentage": 32.96, "elapsed_time": "2:21:27", "remaining_time": "4:47:42", "throughput": 1489.91, "total_tokens": 12646016} {"current_steps": 59930, "total_steps": 181800, "loss": 0.0046, "lr": 4.2388889765847895e-05, "epoch": 6.592959295929593, "percentage": 32.96, "elapsed_time": "2:21:28", "remaining_time": "4:47:41", "throughput": 1489.91, "total_tokens": 12647040} {"current_steps": 59935, "total_steps": 181800, "loss": 0.057, "lr": 4.238716530357977e-05, "epoch": 6.5935093509350935, "percentage": 32.97, "elapsed_time": "2:21:29", "remaining_time": "4:47:40", "throughput": 1489.91, "total_tokens": 12648096} {"current_steps": 59940, "total_steps": 181800, "loss": 0.029, "lr": 4.238544068106249e-05, "epoch": 6.594059405940594, "percentage": 32.97, "elapsed_time": "2:21:29", "remaining_time": "4:47:40", "throughput": 1489.91, "total_tokens": 12649152} {"current_steps": 59945, "total_steps": 181800, "loss": 0.0818, "lr": 4.238371589831195e-05, "epoch": 6.594609460946095, "percentage": 32.97, "elapsed_time": "2:21:30", "remaining_time": "4:47:39", "throughput": 1489.91, "total_tokens": 12650176} {"current_steps": 59950, "total_steps": 181800, "loss": 0.0396, "lr": 4.238199095534404e-05, "epoch": 6.595159515951595, "percentage": 32.98, "elapsed_time": "2:21:31", "remaining_time": "4:47:38", "throughput": 1489.92, "total_tokens": 12651264} {"current_steps": 59955, "total_steps": 181800, "loss": 0.0463, "lr": 4.238026585217466e-05, "epoch": 6.595709570957096, "percentage": 32.98, "elapsed_time": "2:21:31", "remaining_time": "4:47:37", "throughput": 1489.92, "total_tokens": 12652320} {"current_steps": 59960, "total_steps": 181800, "loss": 0.0142, "lr": 4.237854058881971e-05, "epoch": 6.596259625962596, "percentage": 32.98, "elapsed_time": "2:21:32", "remaining_time": "4:47:37", "throughput": 1489.93, "total_tokens": 12653376} {"current_steps": 59965, "total_steps": 181800, "loss": 0.0143, "lr": 4.237681516529508e-05, "epoch": 6.5968096809680965, "percentage": 32.98, "elapsed_time": "2:21:33", "remaining_time": "4:47:36", "throughput": 1489.93, "total_tokens": 12654432} {"current_steps": 59970, "total_steps": 181800, "loss": 0.011, "lr": 4.23750895816167e-05, "epoch": 6.597359735973598, "percentage": 32.99, "elapsed_time": "2:21:33", "remaining_time": "4:47:35", "throughput": 1489.94, "total_tokens": 12655520} {"current_steps": 59975, "total_steps": 181800, "loss": 0.0059, "lr": 4.237336383780045e-05, "epoch": 6.597909790979098, "percentage": 32.99, "elapsed_time": "2:21:34", "remaining_time": "4:47:34", "throughput": 1489.94, "total_tokens": 12656608} {"current_steps": 59980, "total_steps": 181800, "loss": 0.0789, "lr": 4.2371637933862234e-05, "epoch": 6.598459845984598, "percentage": 32.99, "elapsed_time": "2:21:35", "remaining_time": "4:47:34", "throughput": 1489.94, "total_tokens": 12657600} {"current_steps": 59985, "total_steps": 181800, "loss": 0.0839, "lr": 4.236991186981798e-05, "epoch": 6.599009900990099, "percentage": 33.0, "elapsed_time": "2:21:36", "remaining_time": "4:47:33", "throughput": 1489.95, "total_tokens": 12658720} {"current_steps": 59990, "total_steps": 181800, "loss": 0.0543, "lr": 4.2368185645683564e-05, "epoch": 6.599559955995599, "percentage": 33.0, "elapsed_time": "2:21:36", "remaining_time": "4:47:32", "throughput": 1489.95, "total_tokens": 12659776} {"current_steps": 59995, "total_steps": 181800, "loss": 0.0134, "lr": 4.2366459261474933e-05, "epoch": 6.6001100110011, "percentage": 33.0, "elapsed_time": "2:21:37", "remaining_time": "4:47:31", "throughput": 1489.95, "total_tokens": 12660800} {"current_steps": 60000, "total_steps": 181800, "loss": 0.0431, "lr": 4.2364732717207976e-05, "epoch": 6.600660066006601, "percentage": 33.0, "elapsed_time": "2:21:38", "remaining_time": "4:47:31", "throughput": 1489.95, "total_tokens": 12661824} {"current_steps": 60005, "total_steps": 181800, "loss": 0.0979, "lr": 4.236300601289861e-05, "epoch": 6.601210121012102, "percentage": 33.01, "elapsed_time": "2:21:38", "remaining_time": "4:47:30", "throughput": 1489.96, "total_tokens": 12662880} {"current_steps": 60010, "total_steps": 181800, "loss": 0.0145, "lr": 4.236127914856275e-05, "epoch": 6.601760176017602, "percentage": 33.01, "elapsed_time": "2:21:39", "remaining_time": "4:47:29", "throughput": 1489.97, "total_tokens": 12664000} {"current_steps": 60015, "total_steps": 181800, "loss": 0.0771, "lr": 4.2359552124216306e-05, "epoch": 6.602310231023102, "percentage": 33.01, "elapsed_time": "2:21:40", "remaining_time": "4:47:28", "throughput": 1489.97, "total_tokens": 12665056} {"current_steps": 60020, "total_steps": 181800, "loss": 0.0171, "lr": 4.23578249398752e-05, "epoch": 6.602860286028603, "percentage": 33.01, "elapsed_time": "2:21:40", "remaining_time": "4:47:28", "throughput": 1489.98, "total_tokens": 12666112} {"current_steps": 60025, "total_steps": 181800, "loss": 0.0371, "lr": 4.2356097595555355e-05, "epoch": 6.603410341034103, "percentage": 33.02, "elapsed_time": "2:21:41", "remaining_time": "4:47:27", "throughput": 1489.98, "total_tokens": 12667136} {"current_steps": 60030, "total_steps": 181800, "loss": 0.0627, "lr": 4.2354370091272686e-05, "epoch": 6.603960396039604, "percentage": 33.02, "elapsed_time": "2:21:42", "remaining_time": "4:47:26", "throughput": 1489.98, "total_tokens": 12668224} {"current_steps": 60035, "total_steps": 181800, "loss": 0.0079, "lr": 4.235264242704311e-05, "epoch": 6.604510451045105, "percentage": 33.02, "elapsed_time": "2:21:42", "remaining_time": "4:47:25", "throughput": 1489.99, "total_tokens": 12669312} {"current_steps": 60040, "total_steps": 181800, "loss": 0.0182, "lr": 4.2350914602882564e-05, "epoch": 6.605060506050605, "percentage": 33.03, "elapsed_time": "2:21:43", "remaining_time": "4:47:25", "throughput": 1489.99, "total_tokens": 12670336} {"current_steps": 60045, "total_steps": 181800, "loss": 0.11, "lr": 4.234918661880696e-05, "epoch": 6.605610561056105, "percentage": 33.03, "elapsed_time": "2:21:44", "remaining_time": "4:47:24", "throughput": 1489.99, "total_tokens": 12671328} {"current_steps": 60050, "total_steps": 181800, "loss": 0.038, "lr": 4.234745847483222e-05, "epoch": 6.606160616061606, "percentage": 33.03, "elapsed_time": "2:21:45", "remaining_time": "4:47:23", "throughput": 1489.99, "total_tokens": 12672384} {"current_steps": 60055, "total_steps": 181800, "loss": 0.1194, "lr": 4.23457301709743e-05, "epoch": 6.606710671067106, "percentage": 33.03, "elapsed_time": "2:21:45", "remaining_time": "4:47:22", "throughput": 1490.0, "total_tokens": 12673472} {"current_steps": 60060, "total_steps": 181800, "loss": 0.007, "lr": 4.234400170724909e-05, "epoch": 6.6072607260726075, "percentage": 33.04, "elapsed_time": "2:21:46", "remaining_time": "4:47:22", "throughput": 1489.99, "total_tokens": 12674464} {"current_steps": 60065, "total_steps": 181800, "loss": 0.0117, "lr": 4.2342273083672546e-05, "epoch": 6.607810781078108, "percentage": 33.04, "elapsed_time": "2:21:47", "remaining_time": "4:47:21", "throughput": 1489.99, "total_tokens": 12675488} {"current_steps": 60070, "total_steps": 181800, "loss": 0.006, "lr": 4.234054430026059e-05, "epoch": 6.608360836083609, "percentage": 33.04, "elapsed_time": "2:21:47", "remaining_time": "4:47:20", "throughput": 1490.01, "total_tokens": 12676640} {"current_steps": 60075, "total_steps": 181800, "loss": 0.2213, "lr": 4.2338815357029154e-05, "epoch": 6.608910891089109, "percentage": 33.04, "elapsed_time": "2:21:48", "remaining_time": "4:47:20", "throughput": 1490.01, "total_tokens": 12677696} {"current_steps": 60080, "total_steps": 181800, "loss": 0.054, "lr": 4.2337086253994186e-05, "epoch": 6.609460946094609, "percentage": 33.05, "elapsed_time": "2:21:49", "remaining_time": "4:47:19", "throughput": 1490.01, "total_tokens": 12678720} {"current_steps": 60085, "total_steps": 181800, "loss": 0.1365, "lr": 4.23353569911716e-05, "epoch": 6.61001100110011, "percentage": 33.05, "elapsed_time": "2:21:49", "remaining_time": "4:47:18", "throughput": 1490.01, "total_tokens": 12679744} {"current_steps": 60090, "total_steps": 181800, "loss": 0.0592, "lr": 4.233362756857736e-05, "epoch": 6.6105610561056105, "percentage": 33.05, "elapsed_time": "2:21:50", "remaining_time": "4:47:17", "throughput": 1490.01, "total_tokens": 12680800} {"current_steps": 60095, "total_steps": 181800, "loss": 0.013, "lr": 4.233189798622739e-05, "epoch": 6.611111111111111, "percentage": 33.06, "elapsed_time": "2:21:51", "remaining_time": "4:47:17", "throughput": 1490.02, "total_tokens": 12681920} {"current_steps": 60100, "total_steps": 181800, "loss": 0.1064, "lr": 4.2330168244137626e-05, "epoch": 6.611661166116612, "percentage": 33.06, "elapsed_time": "2:21:51", "remaining_time": "4:47:16", "throughput": 1490.03, "total_tokens": 12683040} {"current_steps": 60105, "total_steps": 181800, "loss": 0.0356, "lr": 4.2328438342324026e-05, "epoch": 6.612211221122112, "percentage": 33.06, "elapsed_time": "2:21:52", "remaining_time": "4:47:15", "throughput": 1490.04, "total_tokens": 12684128} {"current_steps": 60110, "total_steps": 181800, "loss": 0.1106, "lr": 4.232670828080252e-05, "epoch": 6.612761276127613, "percentage": 33.06, "elapsed_time": "2:21:53", "remaining_time": "4:47:14", "throughput": 1490.04, "total_tokens": 12685184} {"current_steps": 60115, "total_steps": 181800, "loss": 0.0678, "lr": 4.232497805958906e-05, "epoch": 6.613311331133113, "percentage": 33.07, "elapsed_time": "2:21:53", "remaining_time": "4:47:14", "throughput": 1490.05, "total_tokens": 12686272} {"current_steps": 60120, "total_steps": 181800, "loss": 0.0575, "lr": 4.2323247678699586e-05, "epoch": 6.6138613861386135, "percentage": 33.07, "elapsed_time": "2:21:54", "remaining_time": "4:47:13", "throughput": 1490.06, "total_tokens": 12687360} {"current_steps": 60125, "total_steps": 181800, "loss": 0.1072, "lr": 4.2321517138150055e-05, "epoch": 6.614411441144115, "percentage": 33.07, "elapsed_time": "2:21:55", "remaining_time": "4:47:12", "throughput": 1490.06, "total_tokens": 12688384} {"current_steps": 60130, "total_steps": 181800, "loss": 0.0155, "lr": 4.231978643795641e-05, "epoch": 6.614961496149615, "percentage": 33.07, "elapsed_time": "2:21:56", "remaining_time": "4:47:11", "throughput": 1490.06, "total_tokens": 12689376} {"current_steps": 60135, "total_steps": 181800, "loss": 0.0092, "lr": 4.23180555781346e-05, "epoch": 6.615511551155116, "percentage": 33.08, "elapsed_time": "2:21:56", "remaining_time": "4:47:11", "throughput": 1490.05, "total_tokens": 12690336} {"current_steps": 60140, "total_steps": 181800, "loss": 0.0223, "lr": 4.231632455870059e-05, "epoch": 6.616061606160616, "percentage": 33.08, "elapsed_time": "2:21:57", "remaining_time": "4:47:10", "throughput": 1490.06, "total_tokens": 12691456} {"current_steps": 60145, "total_steps": 181800, "loss": 0.0153, "lr": 4.231459337967032e-05, "epoch": 6.616611661166116, "percentage": 33.08, "elapsed_time": "2:21:58", "remaining_time": "4:47:09", "throughput": 1490.06, "total_tokens": 12692544} {"current_steps": 60150, "total_steps": 181800, "loss": 0.0372, "lr": 4.2312862041059755e-05, "epoch": 6.617161716171617, "percentage": 33.09, "elapsed_time": "2:21:58", "remaining_time": "4:47:08", "throughput": 1490.07, "total_tokens": 12693664} {"current_steps": 60155, "total_steps": 181800, "loss": 0.0128, "lr": 4.231113054288485e-05, "epoch": 6.617711771177118, "percentage": 33.09, "elapsed_time": "2:21:59", "remaining_time": "4:47:08", "throughput": 1490.09, "total_tokens": 12694784} {"current_steps": 60160, "total_steps": 181800, "loss": 0.008, "lr": 4.230939888516155e-05, "epoch": 6.618261826182618, "percentage": 33.09, "elapsed_time": "2:22:00", "remaining_time": "4:47:07", "throughput": 1490.08, "total_tokens": 12695808} {"current_steps": 60165, "total_steps": 181800, "loss": 0.0269, "lr": 4.230766706790584e-05, "epoch": 6.618811881188119, "percentage": 33.09, "elapsed_time": "2:22:00", "remaining_time": "4:47:06", "throughput": 1490.08, "total_tokens": 12696800} {"current_steps": 60170, "total_steps": 181800, "loss": 0.0838, "lr": 4.2305935091133664e-05, "epoch": 6.619361936193619, "percentage": 33.1, "elapsed_time": "2:22:01", "remaining_time": "4:47:05", "throughput": 1490.07, "total_tokens": 12697792} {"current_steps": 60175, "total_steps": 181800, "loss": 0.0679, "lr": 4.2304202954860986e-05, "epoch": 6.61991199119912, "percentage": 33.1, "elapsed_time": "2:22:02", "remaining_time": "4:47:05", "throughput": 1490.07, "total_tokens": 12698816} {"current_steps": 60180, "total_steps": 181800, "loss": 0.0145, "lr": 4.230247065910377e-05, "epoch": 6.62046204620462, "percentage": 33.1, "elapsed_time": "2:22:02", "remaining_time": "4:47:04", "throughput": 1490.08, "total_tokens": 12699872} {"current_steps": 60185, "total_steps": 181800, "loss": 0.061, "lr": 4.230073820387799e-05, "epoch": 6.621012101210121, "percentage": 33.11, "elapsed_time": "2:22:03", "remaining_time": "4:47:03", "throughput": 1490.08, "total_tokens": 12700928} {"current_steps": 60190, "total_steps": 181800, "loss": 0.0252, "lr": 4.2299005589199604e-05, "epoch": 6.621562156215622, "percentage": 33.11, "elapsed_time": "2:22:04", "remaining_time": "4:47:02", "throughput": 1490.09, "total_tokens": 12701984} {"current_steps": 60195, "total_steps": 181800, "loss": 0.0115, "lr": 4.229727281508459e-05, "epoch": 6.622112211221122, "percentage": 33.11, "elapsed_time": "2:22:05", "remaining_time": "4:47:02", "throughput": 1490.09, "total_tokens": 12703072} {"current_steps": 60200, "total_steps": 181800, "loss": 0.0551, "lr": 4.2295539881548905e-05, "epoch": 6.622662266226623, "percentage": 33.11, "elapsed_time": "2:22:05", "remaining_time": "4:47:01", "throughput": 1490.1, "total_tokens": 12704160} {"current_steps": 60205, "total_steps": 181800, "loss": 0.0063, "lr": 4.229380678860853e-05, "epoch": 6.623212321232123, "percentage": 33.12, "elapsed_time": "2:22:06", "remaining_time": "4:47:00", "throughput": 1490.11, "total_tokens": 12705248} {"current_steps": 60210, "total_steps": 181800, "loss": 0.0227, "lr": 4.229207353627944e-05, "epoch": 6.623762376237623, "percentage": 33.12, "elapsed_time": "2:22:07", "remaining_time": "4:46:59", "throughput": 1490.12, "total_tokens": 12706368} {"current_steps": 60215, "total_steps": 181800, "loss": 0.0476, "lr": 4.22903401245776e-05, "epoch": 6.6243124312431245, "percentage": 33.12, "elapsed_time": "2:22:07", "remaining_time": "4:46:59", "throughput": 1490.12, "total_tokens": 12707424} {"current_steps": 60220, "total_steps": 181800, "loss": 0.0867, "lr": 4.228860655351899e-05, "epoch": 6.624862486248625, "percentage": 33.12, "elapsed_time": "2:22:08", "remaining_time": "4:46:58", "throughput": 1490.13, "total_tokens": 12708480} {"current_steps": 60225, "total_steps": 181800, "loss": 0.0225, "lr": 4.22868728231196e-05, "epoch": 6.625412541254125, "percentage": 33.13, "elapsed_time": "2:22:09", "remaining_time": "4:46:57", "throughput": 1490.12, "total_tokens": 12709472} {"current_steps": 60230, "total_steps": 181800, "loss": 0.004, "lr": 4.228513893339539e-05, "epoch": 6.625962596259626, "percentage": 33.13, "elapsed_time": "2:22:09", "remaining_time": "4:46:56", "throughput": 1490.13, "total_tokens": 12710528} {"current_steps": 60235, "total_steps": 181800, "loss": 0.0552, "lr": 4.228340488436235e-05, "epoch": 6.626512651265126, "percentage": 33.13, "elapsed_time": "2:22:10", "remaining_time": "4:46:56", "throughput": 1490.13, "total_tokens": 12711584} {"current_steps": 60240, "total_steps": 181800, "loss": 0.014, "lr": 4.228167067603647e-05, "epoch": 6.627062706270627, "percentage": 33.14, "elapsed_time": "2:22:11", "remaining_time": "4:46:55", "throughput": 1490.13, "total_tokens": 12712608} {"current_steps": 60245, "total_steps": 181800, "loss": 0.0242, "lr": 4.227993630843371e-05, "epoch": 6.6276127612761275, "percentage": 33.14, "elapsed_time": "2:22:11", "remaining_time": "4:46:54", "throughput": 1490.14, "total_tokens": 12713696} {"current_steps": 60250, "total_steps": 181800, "loss": 0.0845, "lr": 4.227820178157008e-05, "epoch": 6.628162816281629, "percentage": 33.14, "elapsed_time": "2:22:12", "remaining_time": "4:46:53", "throughput": 1490.14, "total_tokens": 12714752} {"current_steps": 60255, "total_steps": 181800, "loss": 0.0102, "lr": 4.2276467095461545e-05, "epoch": 6.628712871287129, "percentage": 33.14, "elapsed_time": "2:22:13", "remaining_time": "4:46:53", "throughput": 1490.15, "total_tokens": 12715840} {"current_steps": 60260, "total_steps": 181800, "loss": 0.0043, "lr": 4.227473225012411e-05, "epoch": 6.629262926292629, "percentage": 33.15, "elapsed_time": "2:22:13", "remaining_time": "4:46:52", "throughput": 1490.15, "total_tokens": 12716864} {"current_steps": 60265, "total_steps": 181800, "loss": 0.125, "lr": 4.2272997245573756e-05, "epoch": 6.62981298129813, "percentage": 33.15, "elapsed_time": "2:22:14", "remaining_time": "4:46:51", "throughput": 1490.15, "total_tokens": 12717920} {"current_steps": 60270, "total_steps": 181800, "loss": 0.0034, "lr": 4.2271262081826465e-05, "epoch": 6.63036303630363, "percentage": 33.15, "elapsed_time": "2:22:15", "remaining_time": "4:46:50", "throughput": 1490.15, "total_tokens": 12718912} {"current_steps": 60275, "total_steps": 181800, "loss": 0.0045, "lr": 4.226952675889825e-05, "epoch": 6.6309130913091305, "percentage": 33.15, "elapsed_time": "2:22:16", "remaining_time": "4:46:50", "throughput": 1490.15, "total_tokens": 12719936} {"current_steps": 60280, "total_steps": 181800, "loss": 0.111, "lr": 4.22677912768051e-05, "epoch": 6.631463146314632, "percentage": 33.16, "elapsed_time": "2:22:16", "remaining_time": "4:46:49", "throughput": 1490.16, "total_tokens": 12721024} {"current_steps": 60285, "total_steps": 181800, "loss": 0.0717, "lr": 4.2266055635562995e-05, "epoch": 6.632013201320132, "percentage": 33.16, "elapsed_time": "2:22:17", "remaining_time": "4:46:48", "throughput": 1490.16, "total_tokens": 12722112} {"current_steps": 60290, "total_steps": 181800, "loss": 0.0266, "lr": 4.226431983518794e-05, "epoch": 6.632563256325633, "percentage": 33.16, "elapsed_time": "2:22:18", "remaining_time": "4:46:47", "throughput": 1490.16, "total_tokens": 12723104} {"current_steps": 60295, "total_steps": 181800, "loss": 0.0259, "lr": 4.226258387569593e-05, "epoch": 6.633113311331133, "percentage": 33.17, "elapsed_time": "2:22:18", "remaining_time": "4:46:47", "throughput": 1490.16, "total_tokens": 12724128} {"current_steps": 60300, "total_steps": 181800, "loss": 0.0782, "lr": 4.226084775710297e-05, "epoch": 6.633663366336633, "percentage": 33.17, "elapsed_time": "2:22:19", "remaining_time": "4:46:46", "throughput": 1490.17, "total_tokens": 12725216} {"current_steps": 60305, "total_steps": 181800, "loss": 0.0101, "lr": 4.225911147942506e-05, "epoch": 6.634213421342134, "percentage": 33.17, "elapsed_time": "2:22:20", "remaining_time": "4:46:45", "throughput": 1490.17, "total_tokens": 12726240} {"current_steps": 60310, "total_steps": 181800, "loss": 0.0945, "lr": 4.225737504267821e-05, "epoch": 6.634763476347635, "percentage": 33.17, "elapsed_time": "2:22:20", "remaining_time": "4:46:44", "throughput": 1490.17, "total_tokens": 12727296} {"current_steps": 60315, "total_steps": 181800, "loss": 0.0726, "lr": 4.22556384468784e-05, "epoch": 6.635313531353136, "percentage": 33.18, "elapsed_time": "2:22:21", "remaining_time": "4:46:44", "throughput": 1490.17, "total_tokens": 12728320} {"current_steps": 60320, "total_steps": 181800, "loss": 0.0739, "lr": 4.2253901692041654e-05, "epoch": 6.635863586358636, "percentage": 33.18, "elapsed_time": "2:22:22", "remaining_time": "4:46:43", "throughput": 1490.17, "total_tokens": 12729312} {"current_steps": 60325, "total_steps": 181800, "loss": 0.073, "lr": 4.225216477818398e-05, "epoch": 6.636413641364136, "percentage": 33.18, "elapsed_time": "2:22:22", "remaining_time": "4:46:42", "throughput": 1490.18, "total_tokens": 12730432} {"current_steps": 60330, "total_steps": 181800, "loss": 0.023, "lr": 4.225042770532138e-05, "epoch": 6.636963696369637, "percentage": 33.18, "elapsed_time": "2:22:23", "remaining_time": "4:46:41", "throughput": 1490.18, "total_tokens": 12731456} {"current_steps": 60335, "total_steps": 181800, "loss": 0.1255, "lr": 4.224869047346986e-05, "epoch": 6.637513751375137, "percentage": 33.19, "elapsed_time": "2:22:24", "remaining_time": "4:46:41", "throughput": 1490.19, "total_tokens": 12732544} {"current_steps": 60340, "total_steps": 181800, "loss": 0.031, "lr": 4.224695308264545e-05, "epoch": 6.638063806380638, "percentage": 33.19, "elapsed_time": "2:22:24", "remaining_time": "4:46:40", "throughput": 1490.2, "total_tokens": 12733664} {"current_steps": 60345, "total_steps": 181800, "loss": 0.0451, "lr": 4.224521553286413e-05, "epoch": 6.638613861386139, "percentage": 33.19, "elapsed_time": "2:22:25", "remaining_time": "4:46:39", "throughput": 1490.21, "total_tokens": 12734784} {"current_steps": 60350, "total_steps": 181800, "loss": 0.1255, "lr": 4.224347782414195e-05, "epoch": 6.639163916391639, "percentage": 33.2, "elapsed_time": "2:22:26", "remaining_time": "4:46:38", "throughput": 1490.21, "total_tokens": 12735808} {"current_steps": 60355, "total_steps": 181800, "loss": 0.0122, "lr": 4.2241739956494906e-05, "epoch": 6.63971397139714, "percentage": 33.2, "elapsed_time": "2:22:27", "remaining_time": "4:46:38", "throughput": 1490.22, "total_tokens": 12736896} {"current_steps": 60360, "total_steps": 181800, "loss": 0.047, "lr": 4.224000192993901e-05, "epoch": 6.64026402640264, "percentage": 33.2, "elapsed_time": "2:22:27", "remaining_time": "4:46:37", "throughput": 1490.21, "total_tokens": 12737888} {"current_steps": 60365, "total_steps": 181800, "loss": 0.0749, "lr": 4.223826374449029e-05, "epoch": 6.6408140814081404, "percentage": 33.2, "elapsed_time": "2:22:28", "remaining_time": "4:46:36", "throughput": 1490.21, "total_tokens": 12738944} {"current_steps": 60370, "total_steps": 181800, "loss": 0.0111, "lr": 4.2236525400164774e-05, "epoch": 6.6413641364136415, "percentage": 33.21, "elapsed_time": "2:22:29", "remaining_time": "4:46:35", "throughput": 1490.22, "total_tokens": 12740000} {"current_steps": 60375, "total_steps": 181800, "loss": 0.0146, "lr": 4.2234786896978475e-05, "epoch": 6.641914191419142, "percentage": 33.21, "elapsed_time": "2:22:29", "remaining_time": "4:46:35", "throughput": 1490.23, "total_tokens": 12741120} {"current_steps": 60380, "total_steps": 181800, "loss": 0.0095, "lr": 4.22330482349474e-05, "epoch": 6.642464246424643, "percentage": 33.21, "elapsed_time": "2:22:30", "remaining_time": "4:46:34", "throughput": 1490.23, "total_tokens": 12742176} {"current_steps": 60385, "total_steps": 181800, "loss": 0.0464, "lr": 4.22313094140876e-05, "epoch": 6.643014301430143, "percentage": 33.22, "elapsed_time": "2:22:31", "remaining_time": "4:46:33", "throughput": 1490.23, "total_tokens": 12743200} {"current_steps": 60390, "total_steps": 181800, "loss": 0.0493, "lr": 4.222957043441509e-05, "epoch": 6.643564356435643, "percentage": 33.22, "elapsed_time": "2:22:31", "remaining_time": "4:46:32", "throughput": 1490.25, "total_tokens": 12744352} {"current_steps": 60395, "total_steps": 181800, "loss": 0.018, "lr": 4.22278312959459e-05, "epoch": 6.644114411441144, "percentage": 33.22, "elapsed_time": "2:22:32", "remaining_time": "4:46:32", "throughput": 1490.25, "total_tokens": 12745408} {"current_steps": 60400, "total_steps": 181800, "loss": 0.0232, "lr": 4.222609199869605e-05, "epoch": 6.6446644664466445, "percentage": 33.22, "elapsed_time": "2:22:33", "remaining_time": "4:46:31", "throughput": 1490.25, "total_tokens": 12746400} {"current_steps": 60405, "total_steps": 181800, "loss": 0.0281, "lr": 4.222435254268158e-05, "epoch": 6.645214521452145, "percentage": 33.23, "elapsed_time": "2:22:33", "remaining_time": "4:46:30", "throughput": 1490.24, "total_tokens": 12747392} {"current_steps": 60410, "total_steps": 181800, "loss": 0.129, "lr": 4.2222612927918506e-05, "epoch": 6.645764576457646, "percentage": 33.23, "elapsed_time": "2:22:34", "remaining_time": "4:46:29", "throughput": 1490.25, "total_tokens": 12748448} {"current_steps": 60415, "total_steps": 181800, "loss": 0.0637, "lr": 4.222087315442288e-05, "epoch": 6.646314631463146, "percentage": 33.23, "elapsed_time": "2:22:35", "remaining_time": "4:46:29", "throughput": 1490.25, "total_tokens": 12749536} {"current_steps": 60420, "total_steps": 181800, "loss": 0.0691, "lr": 4.221913322221074e-05, "epoch": 6.646864686468647, "percentage": 33.23, "elapsed_time": "2:22:35", "remaining_time": "4:46:28", "throughput": 1490.26, "total_tokens": 12750592} {"current_steps": 60425, "total_steps": 181800, "loss": 0.0865, "lr": 4.22173931312981e-05, "epoch": 6.647414741474147, "percentage": 33.24, "elapsed_time": "2:22:36", "remaining_time": "4:46:27", "throughput": 1490.26, "total_tokens": 12751648} {"current_steps": 60430, "total_steps": 181800, "loss": 0.0603, "lr": 4.221565288170101e-05, "epoch": 6.647964796479648, "percentage": 33.24, "elapsed_time": "2:22:37", "remaining_time": "4:46:26", "throughput": 1490.27, "total_tokens": 12752736} {"current_steps": 60435, "total_steps": 181800, "loss": 0.0473, "lr": 4.2213912473435505e-05, "epoch": 6.648514851485149, "percentage": 33.24, "elapsed_time": "2:22:38", "remaining_time": "4:46:26", "throughput": 1490.27, "total_tokens": 12753760} {"current_steps": 60440, "total_steps": 181800, "loss": 0.0397, "lr": 4.2212171906517635e-05, "epoch": 6.649064906490649, "percentage": 33.25, "elapsed_time": "2:22:38", "remaining_time": "4:46:25", "throughput": 1490.27, "total_tokens": 12754848} {"current_steps": 60445, "total_steps": 181800, "loss": 0.1157, "lr": 4.221043118096344e-05, "epoch": 6.64961496149615, "percentage": 33.25, "elapsed_time": "2:22:39", "remaining_time": "4:46:24", "throughput": 1490.28, "total_tokens": 12755904} {"current_steps": 60450, "total_steps": 181800, "loss": 0.0151, "lr": 4.220869029678894e-05, "epoch": 6.65016501650165, "percentage": 33.25, "elapsed_time": "2:22:40", "remaining_time": "4:46:23", "throughput": 1490.28, "total_tokens": 12756928} {"current_steps": 60455, "total_steps": 181800, "loss": 0.0269, "lr": 4.220694925401022e-05, "epoch": 6.65071507150715, "percentage": 33.25, "elapsed_time": "2:22:40", "remaining_time": "4:46:23", "throughput": 1490.28, "total_tokens": 12757984} {"current_steps": 60460, "total_steps": 181800, "loss": 0.0308, "lr": 4.2205208052643296e-05, "epoch": 6.6512651265126514, "percentage": 33.26, "elapsed_time": "2:22:41", "remaining_time": "4:46:22", "throughput": 1490.28, "total_tokens": 12759040} {"current_steps": 60465, "total_steps": 181800, "loss": 0.0243, "lr": 4.220346669270423e-05, "epoch": 6.651815181518152, "percentage": 33.26, "elapsed_time": "2:22:42", "remaining_time": "4:46:21", "throughput": 1490.29, "total_tokens": 12760160} {"current_steps": 60470, "total_steps": 181800, "loss": 0.0388, "lr": 4.2201725174209064e-05, "epoch": 6.652365236523653, "percentage": 33.26, "elapsed_time": "2:22:42", "remaining_time": "4:46:20", "throughput": 1490.3, "total_tokens": 12761248} {"current_steps": 60475, "total_steps": 181800, "loss": 0.0521, "lr": 4.219998349717385e-05, "epoch": 6.652915291529153, "percentage": 33.26, "elapsed_time": "2:22:43", "remaining_time": "4:46:20", "throughput": 1490.32, "total_tokens": 12762400} {"current_steps": 60480, "total_steps": 181800, "loss": 0.0104, "lr": 4.219824166161464e-05, "epoch": 6.653465346534653, "percentage": 33.27, "elapsed_time": "2:22:44", "remaining_time": "4:46:19", "throughput": 1490.32, "total_tokens": 12763456} {"current_steps": 60485, "total_steps": 181800, "loss": 0.0564, "lr": 4.21964996675475e-05, "epoch": 6.654015401540154, "percentage": 33.27, "elapsed_time": "2:22:44", "remaining_time": "4:46:18", "throughput": 1490.32, "total_tokens": 12764512} {"current_steps": 60490, "total_steps": 181800, "loss": 0.018, "lr": 4.2194757514988456e-05, "epoch": 6.6545654565456545, "percentage": 33.27, "elapsed_time": "2:22:45", "remaining_time": "4:46:17", "throughput": 1490.33, "total_tokens": 12765600} {"current_steps": 60495, "total_steps": 181800, "loss": 0.0534, "lr": 4.2193015203953596e-05, "epoch": 6.6551155115511555, "percentage": 33.28, "elapsed_time": "2:22:46", "remaining_time": "4:46:17", "throughput": 1490.34, "total_tokens": 12766688} {"current_steps": 60500, "total_steps": 181800, "loss": 0.0233, "lr": 4.2191272734458955e-05, "epoch": 6.655665566556656, "percentage": 33.28, "elapsed_time": "2:22:46", "remaining_time": "4:46:16", "throughput": 1490.34, "total_tokens": 12767744} {"current_steps": 60505, "total_steps": 181800, "loss": 0.0082, "lr": 4.2189530106520616e-05, "epoch": 6.656215621562156, "percentage": 33.28, "elapsed_time": "2:22:47", "remaining_time": "4:46:15", "throughput": 1490.35, "total_tokens": 12768832} {"current_steps": 60510, "total_steps": 181800, "loss": 0.0669, "lr": 4.2187787320154616e-05, "epoch": 6.656765676567657, "percentage": 33.28, "elapsed_time": "2:22:48", "remaining_time": "4:46:14", "throughput": 1490.35, "total_tokens": 12769888} {"current_steps": 60515, "total_steps": 181800, "loss": 0.011, "lr": 4.218604437537703e-05, "epoch": 6.657315731573157, "percentage": 33.29, "elapsed_time": "2:22:49", "remaining_time": "4:46:14", "throughput": 1490.35, "total_tokens": 12770912} {"current_steps": 60520, "total_steps": 181800, "loss": 0.0708, "lr": 4.218430127220392e-05, "epoch": 6.6578657865786575, "percentage": 33.29, "elapsed_time": "2:22:49", "remaining_time": "4:46:13", "throughput": 1490.36, "total_tokens": 12772032} {"current_steps": 60525, "total_steps": 181800, "loss": 0.033, "lr": 4.2182558010651355e-05, "epoch": 6.658415841584159, "percentage": 33.29, "elapsed_time": "2:22:50", "remaining_time": "4:46:12", "throughput": 1490.37, "total_tokens": 12773088} {"current_steps": 60530, "total_steps": 181800, "loss": 0.0749, "lr": 4.218081459073539e-05, "epoch": 6.658965896589659, "percentage": 33.29, "elapsed_time": "2:22:51", "remaining_time": "4:46:11", "throughput": 1490.37, "total_tokens": 12774112} {"current_steps": 60535, "total_steps": 181800, "loss": 0.0225, "lr": 4.2179071012472104e-05, "epoch": 6.65951595159516, "percentage": 33.3, "elapsed_time": "2:22:51", "remaining_time": "4:46:11", "throughput": 1490.37, "total_tokens": 12775200} {"current_steps": 60540, "total_steps": 181800, "loss": 0.0776, "lr": 4.217732727587757e-05, "epoch": 6.66006600660066, "percentage": 33.3, "elapsed_time": "2:22:52", "remaining_time": "4:46:10", "throughput": 1490.37, "total_tokens": 12776192} {"current_steps": 60545, "total_steps": 181800, "loss": 0.0068, "lr": 4.217558338096785e-05, "epoch": 6.66061606160616, "percentage": 33.3, "elapsed_time": "2:22:53", "remaining_time": "4:46:09", "throughput": 1490.37, "total_tokens": 12777184} {"current_steps": 60550, "total_steps": 181800, "loss": 0.0487, "lr": 4.217383932775901e-05, "epoch": 6.661166116611661, "percentage": 33.31, "elapsed_time": "2:22:53", "remaining_time": "4:46:08", "throughput": 1490.37, "total_tokens": 12778272} {"current_steps": 60555, "total_steps": 181800, "loss": 0.0152, "lr": 4.2172095116267146e-05, "epoch": 6.661716171617162, "percentage": 33.31, "elapsed_time": "2:22:54", "remaining_time": "4:46:08", "throughput": 1490.38, "total_tokens": 12779360} {"current_steps": 60560, "total_steps": 181800, "loss": 0.0119, "lr": 4.217035074650831e-05, "epoch": 6.662266226622663, "percentage": 33.31, "elapsed_time": "2:22:55", "remaining_time": "4:46:07", "throughput": 1490.38, "total_tokens": 12780416} {"current_steps": 60565, "total_steps": 181800, "loss": 0.0159, "lr": 4.2168606218498604e-05, "epoch": 6.662816281628163, "percentage": 33.31, "elapsed_time": "2:22:55", "remaining_time": "4:46:06", "throughput": 1490.39, "total_tokens": 12781504} {"current_steps": 60570, "total_steps": 181800, "loss": 0.0169, "lr": 4.216686153225409e-05, "epoch": 6.663366336633663, "percentage": 33.32, "elapsed_time": "2:22:56", "remaining_time": "4:46:05", "throughput": 1490.39, "total_tokens": 12782528} {"current_steps": 60575, "total_steps": 181800, "loss": 0.0228, "lr": 4.216511668779084e-05, "epoch": 6.663916391639164, "percentage": 33.32, "elapsed_time": "2:22:57", "remaining_time": "4:46:05", "throughput": 1490.4, "total_tokens": 12783584} {"current_steps": 60580, "total_steps": 181800, "loss": 0.0541, "lr": 4.2163371685124955e-05, "epoch": 6.664466446644664, "percentage": 33.32, "elapsed_time": "2:22:58", "remaining_time": "4:46:04", "throughput": 1490.41, "total_tokens": 12784704} {"current_steps": 60585, "total_steps": 181800, "loss": 0.0272, "lr": 4.216162652427251e-05, "epoch": 6.665016501650165, "percentage": 33.33, "elapsed_time": "2:22:58", "remaining_time": "4:46:03", "throughput": 1490.4, "total_tokens": 12785696} {"current_steps": 60590, "total_steps": 181800, "loss": 0.0109, "lr": 4.2159881205249586e-05, "epoch": 6.665566556655666, "percentage": 33.33, "elapsed_time": "2:22:59", "remaining_time": "4:46:03", "throughput": 1490.4, "total_tokens": 12786720} {"current_steps": 60595, "total_steps": 181800, "loss": 0.0458, "lr": 4.215813572807227e-05, "epoch": 6.666116611661166, "percentage": 33.33, "elapsed_time": "2:23:00", "remaining_time": "4:46:02", "throughput": 1490.41, "total_tokens": 12787840} {"current_steps": 60600, "total_steps": 181800, "loss": 0.0478, "lr": 4.215639009275665e-05, "epoch": 6.666666666666667, "percentage": 33.33, "elapsed_time": "2:23:00", "remaining_time": "4:46:01", "throughput": 1490.41, "total_tokens": 12788864} {"current_steps": 60605, "total_steps": 181800, "loss": 0.0084, "lr": 4.2154644299318816e-05, "epoch": 6.667216721672167, "percentage": 33.34, "elapsed_time": "2:23:01", "remaining_time": "4:46:00", "throughput": 1490.42, "total_tokens": 12789984} {"current_steps": 60610, "total_steps": 181800, "loss": 0.0058, "lr": 4.215289834777485e-05, "epoch": 6.667766776677668, "percentage": 33.34, "elapsed_time": "2:23:02", "remaining_time": "4:46:00", "throughput": 1490.42, "total_tokens": 12791008} {"current_steps": 60615, "total_steps": 181800, "loss": 0.0724, "lr": 4.215115223814086e-05, "epoch": 6.6683168316831685, "percentage": 33.34, "elapsed_time": "2:23:02", "remaining_time": "4:45:59", "throughput": 1490.42, "total_tokens": 12792064} {"current_steps": 60620, "total_steps": 181800, "loss": 0.1367, "lr": 4.214940597043293e-05, "epoch": 6.668866886688669, "percentage": 33.34, "elapsed_time": "2:23:03", "remaining_time": "4:45:58", "throughput": 1490.43, "total_tokens": 12793120} {"current_steps": 60625, "total_steps": 181800, "loss": 0.0508, "lr": 4.2147659544667146e-05, "epoch": 6.66941694169417, "percentage": 33.35, "elapsed_time": "2:23:04", "remaining_time": "4:45:57", "throughput": 1490.44, "total_tokens": 12794240} {"current_steps": 60630, "total_steps": 181800, "loss": 0.0971, "lr": 4.214591296085962e-05, "epoch": 6.66996699669967, "percentage": 33.35, "elapsed_time": "2:23:04", "remaining_time": "4:45:57", "throughput": 1490.44, "total_tokens": 12795264} {"current_steps": 60635, "total_steps": 181800, "loss": 0.0041, "lr": 4.214416621902644e-05, "epoch": 6.67051705170517, "percentage": 33.35, "elapsed_time": "2:23:05", "remaining_time": "4:45:56", "throughput": 1490.45, "total_tokens": 12796384} {"current_steps": 60640, "total_steps": 181800, "loss": 0.0053, "lr": 4.21424193191837e-05, "epoch": 6.671067106710671, "percentage": 33.36, "elapsed_time": "2:23:06", "remaining_time": "4:45:55", "throughput": 1490.44, "total_tokens": 12797344} {"current_steps": 60645, "total_steps": 181800, "loss": 0.0684, "lr": 4.2140672261347514e-05, "epoch": 6.6716171617161715, "percentage": 33.36, "elapsed_time": "2:23:06", "remaining_time": "4:45:54", "throughput": 1490.44, "total_tokens": 12798368} {"current_steps": 60650, "total_steps": 181800, "loss": 0.0536, "lr": 4.213892504553397e-05, "epoch": 6.672167216721672, "percentage": 33.36, "elapsed_time": "2:23:07", "remaining_time": "4:45:54", "throughput": 1490.44, "total_tokens": 12799392} {"current_steps": 60655, "total_steps": 181800, "loss": 0.1115, "lr": 4.213717767175919e-05, "epoch": 6.672717271727173, "percentage": 33.36, "elapsed_time": "2:23:08", "remaining_time": "4:45:53", "throughput": 1490.44, "total_tokens": 12800448} {"current_steps": 60660, "total_steps": 181800, "loss": 0.0365, "lr": 4.213543014003926e-05, "epoch": 6.673267326732673, "percentage": 33.37, "elapsed_time": "2:23:09", "remaining_time": "4:45:52", "throughput": 1490.44, "total_tokens": 12801472} {"current_steps": 60665, "total_steps": 181800, "loss": 0.0142, "lr": 4.213368245039029e-05, "epoch": 6.673817381738174, "percentage": 33.37, "elapsed_time": "2:23:09", "remaining_time": "4:45:51", "throughput": 1490.45, "total_tokens": 12802528} {"current_steps": 60670, "total_steps": 181800, "loss": 0.0267, "lr": 4.213193460282839e-05, "epoch": 6.674367436743674, "percentage": 33.37, "elapsed_time": "2:23:10", "remaining_time": "4:45:51", "throughput": 1490.45, "total_tokens": 12803584} {"current_steps": 60675, "total_steps": 181800, "loss": 0.0136, "lr": 4.213018659736967e-05, "epoch": 6.674917491749175, "percentage": 33.37, "elapsed_time": "2:23:11", "remaining_time": "4:45:50", "throughput": 1490.46, "total_tokens": 12804672} {"current_steps": 60680, "total_steps": 181800, "loss": 0.0176, "lr": 4.212843843403025e-05, "epoch": 6.675467546754676, "percentage": 33.38, "elapsed_time": "2:23:11", "remaining_time": "4:45:49", "throughput": 1490.45, "total_tokens": 12805632} {"current_steps": 60685, "total_steps": 181800, "loss": 0.0213, "lr": 4.212669011282622e-05, "epoch": 6.676017601760176, "percentage": 33.38, "elapsed_time": "2:23:12", "remaining_time": "4:45:48", "throughput": 1490.45, "total_tokens": 12806656} {"current_steps": 60690, "total_steps": 181800, "loss": 0.0378, "lr": 4.2124941633773706e-05, "epoch": 6.676567656765677, "percentage": 33.38, "elapsed_time": "2:23:13", "remaining_time": "4:45:48", "throughput": 1490.45, "total_tokens": 12807712} {"current_steps": 60695, "total_steps": 181800, "loss": 0.0076, "lr": 4.2123192996888825e-05, "epoch": 6.677117711771177, "percentage": 33.39, "elapsed_time": "2:23:13", "remaining_time": "4:45:47", "throughput": 1490.45, "total_tokens": 12808736} {"current_steps": 60700, "total_steps": 181800, "loss": 0.0318, "lr": 4.21214442021877e-05, "epoch": 6.677667766776677, "percentage": 33.39, "elapsed_time": "2:23:14", "remaining_time": "4:45:46", "throughput": 1490.45, "total_tokens": 12809760} {"current_steps": 60705, "total_steps": 181800, "loss": 0.0378, "lr": 4.211969524968643e-05, "epoch": 6.678217821782178, "percentage": 33.39, "elapsed_time": "2:23:15", "remaining_time": "4:45:45", "throughput": 1490.46, "total_tokens": 12810816} {"current_steps": 60710, "total_steps": 181800, "loss": 0.0186, "lr": 4.211794613940114e-05, "epoch": 6.678767876787679, "percentage": 33.39, "elapsed_time": "2:23:15", "remaining_time": "4:45:45", "throughput": 1490.46, "total_tokens": 12811904} {"current_steps": 60715, "total_steps": 181800, "loss": 0.0405, "lr": 4.211619687134796e-05, "epoch": 6.67931793179318, "percentage": 33.4, "elapsed_time": "2:23:16", "remaining_time": "4:45:44", "throughput": 1490.46, "total_tokens": 12812864} {"current_steps": 60720, "total_steps": 181800, "loss": 0.0285, "lr": 4.2114447445543e-05, "epoch": 6.67986798679868, "percentage": 33.4, "elapsed_time": "2:23:17", "remaining_time": "4:45:43", "throughput": 1490.45, "total_tokens": 12813856} {"current_steps": 60725, "total_steps": 181800, "loss": 0.0348, "lr": 4.2112697862002404e-05, "epoch": 6.68041804180418, "percentage": 33.4, "elapsed_time": "2:23:17", "remaining_time": "4:45:42", "throughput": 1490.45, "total_tokens": 12814880} {"current_steps": 60730, "total_steps": 181800, "loss": 0.0131, "lr": 4.211094812074228e-05, "epoch": 6.680968096809681, "percentage": 33.4, "elapsed_time": "2:23:18", "remaining_time": "4:45:42", "throughput": 1490.45, "total_tokens": 12815872} {"current_steps": 60735, "total_steps": 181800, "loss": 0.0022, "lr": 4.2109198221778746e-05, "epoch": 6.681518151815181, "percentage": 33.41, "elapsed_time": "2:23:19", "remaining_time": "4:45:41", "throughput": 1490.45, "total_tokens": 12816928} {"current_steps": 60740, "total_steps": 181800, "loss": 0.0212, "lr": 4.210744816512795e-05, "epoch": 6.6820682068206825, "percentage": 33.41, "elapsed_time": "2:23:20", "remaining_time": "4:45:40", "throughput": 1490.45, "total_tokens": 12817952} {"current_steps": 60745, "total_steps": 181800, "loss": 0.0186, "lr": 4.2105697950806014e-05, "epoch": 6.682618261826183, "percentage": 33.41, "elapsed_time": "2:23:20", "remaining_time": "4:45:39", "throughput": 1490.46, "total_tokens": 12819040} {"current_steps": 60750, "total_steps": 181800, "loss": 0.1233, "lr": 4.210394757882906e-05, "epoch": 6.683168316831683, "percentage": 33.42, "elapsed_time": "2:23:21", "remaining_time": "4:45:39", "throughput": 1490.45, "total_tokens": 12820000} {"current_steps": 60755, "total_steps": 181800, "loss": 0.0597, "lr": 4.210219704921324e-05, "epoch": 6.683718371837184, "percentage": 33.42, "elapsed_time": "2:23:22", "remaining_time": "4:45:38", "throughput": 1490.46, "total_tokens": 12821056} {"current_steps": 60760, "total_steps": 181800, "loss": 0.1451, "lr": 4.2100446361974665e-05, "epoch": 6.684268426842684, "percentage": 33.42, "elapsed_time": "2:23:22", "remaining_time": "4:45:37", "throughput": 1490.46, "total_tokens": 12822144} {"current_steps": 60765, "total_steps": 181800, "loss": 0.0686, "lr": 4.2098695517129495e-05, "epoch": 6.684818481848184, "percentage": 33.42, "elapsed_time": "2:23:23", "remaining_time": "4:45:36", "throughput": 1490.47, "total_tokens": 12823200} {"current_steps": 60770, "total_steps": 181800, "loss": 0.0372, "lr": 4.209694451469384e-05, "epoch": 6.6853685368536855, "percentage": 33.43, "elapsed_time": "2:23:24", "remaining_time": "4:45:36", "throughput": 1490.48, "total_tokens": 12824288} {"current_steps": 60775, "total_steps": 181800, "loss": 0.0118, "lr": 4.2095193354683856e-05, "epoch": 6.685918591859186, "percentage": 33.43, "elapsed_time": "2:23:24", "remaining_time": "4:45:35", "throughput": 1490.48, "total_tokens": 12825344} {"current_steps": 60780, "total_steps": 181800, "loss": 0.0369, "lr": 4.2093442037115683e-05, "epoch": 6.686468646864687, "percentage": 33.43, "elapsed_time": "2:23:25", "remaining_time": "4:45:34", "throughput": 1490.48, "total_tokens": 12826368} {"current_steps": 60785, "total_steps": 181800, "loss": 0.0214, "lr": 4.209169056200545e-05, "epoch": 6.687018701870187, "percentage": 33.44, "elapsed_time": "2:23:26", "remaining_time": "4:45:33", "throughput": 1490.49, "total_tokens": 12827456} {"current_steps": 60790, "total_steps": 181800, "loss": 0.0134, "lr": 4.208993892936931e-05, "epoch": 6.687568756875687, "percentage": 33.44, "elapsed_time": "2:23:26", "remaining_time": "4:45:33", "throughput": 1490.49, "total_tokens": 12828544} {"current_steps": 60795, "total_steps": 181800, "loss": 0.0238, "lr": 4.20881871392234e-05, "epoch": 6.688118811881188, "percentage": 33.44, "elapsed_time": "2:23:27", "remaining_time": "4:45:32", "throughput": 1490.49, "total_tokens": 12829536} {"current_steps": 60800, "total_steps": 181800, "loss": 0.036, "lr": 4.208643519158387e-05, "epoch": 6.6886688668866885, "percentage": 33.44, "elapsed_time": "2:23:28", "remaining_time": "4:45:31", "throughput": 1490.5, "total_tokens": 12830688} {"current_steps": 60805, "total_steps": 181800, "loss": 0.0302, "lr": 4.208468308646687e-05, "epoch": 6.68921892189219, "percentage": 33.45, "elapsed_time": "2:23:28", "remaining_time": "4:45:30", "throughput": 1490.5, "total_tokens": 12831712} {"current_steps": 60810, "total_steps": 181800, "loss": 0.0852, "lr": 4.208293082388854e-05, "epoch": 6.68976897689769, "percentage": 33.45, "elapsed_time": "2:23:29", "remaining_time": "4:45:30", "throughput": 1490.51, "total_tokens": 12832768} {"current_steps": 60815, "total_steps": 181800, "loss": 0.0046, "lr": 4.208117840386504e-05, "epoch": 6.69031903190319, "percentage": 33.45, "elapsed_time": "2:23:30", "remaining_time": "4:45:29", "throughput": 1490.52, "total_tokens": 12833888} {"current_steps": 60820, "total_steps": 181800, "loss": 0.0217, "lr": 4.2079425826412503e-05, "epoch": 6.690869086908691, "percentage": 33.45, "elapsed_time": "2:23:31", "remaining_time": "4:45:28", "throughput": 1490.53, "total_tokens": 12835008} {"current_steps": 60825, "total_steps": 181800, "loss": 0.0335, "lr": 4.20776730915471e-05, "epoch": 6.691419141914191, "percentage": 33.46, "elapsed_time": "2:23:31", "remaining_time": "4:45:27", "throughput": 1490.53, "total_tokens": 12836064} {"current_steps": 60830, "total_steps": 181800, "loss": 0.0232, "lr": 4.207592019928498e-05, "epoch": 6.6919691969196915, "percentage": 33.46, "elapsed_time": "2:23:32", "remaining_time": "4:45:27", "throughput": 1490.53, "total_tokens": 12837088} {"current_steps": 60835, "total_steps": 181800, "loss": 0.0303, "lr": 4.2074167149642296e-05, "epoch": 6.692519251925193, "percentage": 33.46, "elapsed_time": "2:23:33", "remaining_time": "4:45:26", "throughput": 1490.54, "total_tokens": 12838144} {"current_steps": 60840, "total_steps": 181800, "loss": 0.0458, "lr": 4.207241394263521e-05, "epoch": 6.693069306930693, "percentage": 33.47, "elapsed_time": "2:23:33", "remaining_time": "4:45:25", "throughput": 1490.54, "total_tokens": 12839200} {"current_steps": 60845, "total_steps": 181800, "loss": 0.0099, "lr": 4.207066057827988e-05, "epoch": 6.693619361936194, "percentage": 33.47, "elapsed_time": "2:23:34", "remaining_time": "4:45:24", "throughput": 1490.55, "total_tokens": 12840320} {"current_steps": 60850, "total_steps": 181800, "loss": 0.0168, "lr": 4.206890705659245e-05, "epoch": 6.694169416941694, "percentage": 33.47, "elapsed_time": "2:23:35", "remaining_time": "4:45:24", "throughput": 1490.56, "total_tokens": 12841408} {"current_steps": 60855, "total_steps": 181800, "loss": 0.1378, "lr": 4.20671533775891e-05, "epoch": 6.694719471947195, "percentage": 33.47, "elapsed_time": "2:23:35", "remaining_time": "4:45:23", "throughput": 1490.56, "total_tokens": 12842496} {"current_steps": 60860, "total_steps": 181800, "loss": 0.0421, "lr": 4.2065399541285986e-05, "epoch": 6.695269526952695, "percentage": 33.48, "elapsed_time": "2:23:36", "remaining_time": "4:45:22", "throughput": 1490.58, "total_tokens": 12843648} {"current_steps": 60865, "total_steps": 181800, "loss": 0.0258, "lr": 4.2063645547699274e-05, "epoch": 6.695819581958196, "percentage": 33.48, "elapsed_time": "2:23:37", "remaining_time": "4:45:21", "throughput": 1490.58, "total_tokens": 12844704} {"current_steps": 60870, "total_steps": 181800, "loss": 0.0716, "lr": 4.2061891396845134e-05, "epoch": 6.696369636963697, "percentage": 33.48, "elapsed_time": "2:23:37", "remaining_time": "4:45:21", "throughput": 1490.59, "total_tokens": 12845792} {"current_steps": 60875, "total_steps": 181800, "loss": 0.0425, "lr": 4.206013708873973e-05, "epoch": 6.696919691969197, "percentage": 33.48, "elapsed_time": "2:23:38", "remaining_time": "4:45:20", "throughput": 1490.6, "total_tokens": 12846880} {"current_steps": 60880, "total_steps": 181800, "loss": 0.0249, "lr": 4.2058382623399215e-05, "epoch": 6.697469746974697, "percentage": 33.49, "elapsed_time": "2:23:39", "remaining_time": "4:45:19", "throughput": 1490.6, "total_tokens": 12847904} {"current_steps": 60885, "total_steps": 181800, "loss": 0.022, "lr": 4.205662800083978e-05, "epoch": 6.698019801980198, "percentage": 33.49, "elapsed_time": "2:23:39", "remaining_time": "4:45:18", "throughput": 1490.6, "total_tokens": 12848960} {"current_steps": 60890, "total_steps": 181800, "loss": 0.0769, "lr": 4.205487322107759e-05, "epoch": 6.698569856985698, "percentage": 33.49, "elapsed_time": "2:23:40", "remaining_time": "4:45:18", "throughput": 1490.6, "total_tokens": 12849984} {"current_steps": 60895, "total_steps": 181800, "loss": 0.0506, "lr": 4.2053118284128815e-05, "epoch": 6.6991199119911995, "percentage": 33.5, "elapsed_time": "2:23:41", "remaining_time": "4:45:17", "throughput": 1490.6, "total_tokens": 12850976} {"current_steps": 60900, "total_steps": 181800, "loss": 0.0477, "lr": 4.205136319000964e-05, "epoch": 6.6996699669967, "percentage": 33.5, "elapsed_time": "2:23:42", "remaining_time": "4:45:16", "throughput": 1490.6, "total_tokens": 12852032} {"current_steps": 60905, "total_steps": 181800, "loss": 0.0373, "lr": 4.204960793873622e-05, "epoch": 6.7002200220022, "percentage": 33.5, "elapsed_time": "2:23:42", "remaining_time": "4:45:15", "throughput": 1490.6, "total_tokens": 12853056} {"current_steps": 60910, "total_steps": 181800, "loss": 0.0139, "lr": 4.204785253032475e-05, "epoch": 6.700770077007701, "percentage": 33.5, "elapsed_time": "2:23:43", "remaining_time": "4:45:15", "throughput": 1490.61, "total_tokens": 12854144} {"current_steps": 60915, "total_steps": 181800, "loss": 0.0236, "lr": 4.2046096964791404e-05, "epoch": 6.701320132013201, "percentage": 33.51, "elapsed_time": "2:23:44", "remaining_time": "4:45:14", "throughput": 1490.6, "total_tokens": 12855136} {"current_steps": 60920, "total_steps": 181800, "loss": 0.0509, "lr": 4.2044341242152366e-05, "epoch": 6.701870187018702, "percentage": 33.51, "elapsed_time": "2:23:44", "remaining_time": "4:45:13", "throughput": 1490.6, "total_tokens": 12856160} {"current_steps": 60925, "total_steps": 181800, "loss": 0.1633, "lr": 4.204258536242381e-05, "epoch": 6.7024202420242025, "percentage": 33.51, "elapsed_time": "2:23:45", "remaining_time": "4:45:12", "throughput": 1490.61, "total_tokens": 12857248} {"current_steps": 60930, "total_steps": 181800, "loss": 0.0764, "lr": 4.204082932562192e-05, "epoch": 6.702970297029703, "percentage": 33.51, "elapsed_time": "2:23:46", "remaining_time": "4:45:12", "throughput": 1490.61, "total_tokens": 12858272} {"current_steps": 60935, "total_steps": 181800, "loss": 0.0495, "lr": 4.203907313176289e-05, "epoch": 6.703520352035204, "percentage": 33.52, "elapsed_time": "2:23:46", "remaining_time": "4:45:11", "throughput": 1490.62, "total_tokens": 12859392} {"current_steps": 60940, "total_steps": 181800, "loss": 0.0832, "lr": 4.203731678086289e-05, "epoch": 6.704070407040704, "percentage": 33.52, "elapsed_time": "2:23:47", "remaining_time": "4:45:10", "throughput": 1490.62, "total_tokens": 12860448} {"current_steps": 60945, "total_steps": 181800, "loss": 0.069, "lr": 4.2035560272938124e-05, "epoch": 6.704620462046204, "percentage": 33.52, "elapsed_time": "2:23:48", "remaining_time": "4:45:09", "throughput": 1490.63, "total_tokens": 12861568} {"current_steps": 60950, "total_steps": 181800, "loss": 0.0423, "lr": 4.203380360800476e-05, "epoch": 6.705170517051705, "percentage": 33.53, "elapsed_time": "2:23:48", "remaining_time": "4:45:09", "throughput": 1490.63, "total_tokens": 12862560} {"current_steps": 60955, "total_steps": 181800, "loss": 0.0089, "lr": 4.203204678607902e-05, "epoch": 6.7057205720572055, "percentage": 33.53, "elapsed_time": "2:23:49", "remaining_time": "4:45:08", "throughput": 1490.64, "total_tokens": 12863712} {"current_steps": 60960, "total_steps": 181800, "loss": 0.0789, "lr": 4.203028980717707e-05, "epoch": 6.706270627062707, "percentage": 33.53, "elapsed_time": "2:23:50", "remaining_time": "4:45:07", "throughput": 1490.65, "total_tokens": 12864768} {"current_steps": 60965, "total_steps": 181800, "loss": 0.0434, "lr": 4.202853267131511e-05, "epoch": 6.706820682068207, "percentage": 33.53, "elapsed_time": "2:23:51", "remaining_time": "4:45:07", "throughput": 1490.65, "total_tokens": 12865792} {"current_steps": 60970, "total_steps": 181800, "loss": 0.0224, "lr": 4.202677537850934e-05, "epoch": 6.707370737073707, "percentage": 33.54, "elapsed_time": "2:23:51", "remaining_time": "4:45:06", "throughput": 1490.64, "total_tokens": 12866784} {"current_steps": 60975, "total_steps": 181800, "loss": 0.2365, "lr": 4.202501792877595e-05, "epoch": 6.707920792079208, "percentage": 33.54, "elapsed_time": "2:23:52", "remaining_time": "4:45:05", "throughput": 1490.65, "total_tokens": 12867840} {"current_steps": 60980, "total_steps": 181800, "loss": 0.016, "lr": 4.202326032213113e-05, "epoch": 6.708470847084708, "percentage": 33.54, "elapsed_time": "2:23:53", "remaining_time": "4:45:04", "throughput": 1490.65, "total_tokens": 12868864} {"current_steps": 60985, "total_steps": 181800, "loss": 0.0103, "lr": 4.202150255859109e-05, "epoch": 6.709020902090209, "percentage": 33.55, "elapsed_time": "2:23:53", "remaining_time": "4:45:04", "throughput": 1490.65, "total_tokens": 12869888} {"current_steps": 60990, "total_steps": 181800, "loss": 0.0402, "lr": 4.201974463817204e-05, "epoch": 6.70957095709571, "percentage": 33.55, "elapsed_time": "2:23:54", "remaining_time": "4:45:03", "throughput": 1490.65, "total_tokens": 12870976} {"current_steps": 60995, "total_steps": 181800, "loss": 0.0446, "lr": 4.201798656089016e-05, "epoch": 6.71012101210121, "percentage": 33.55, "elapsed_time": "2:23:55", "remaining_time": "4:45:02", "throughput": 1490.66, "total_tokens": 12872032} {"current_steps": 61000, "total_steps": 181800, "loss": 0.0133, "lr": 4.201622832676167e-05, "epoch": 6.710671067106711, "percentage": 33.55, "elapsed_time": "2:23:55", "remaining_time": "4:45:01", "throughput": 1490.66, "total_tokens": 12873088} {"current_steps": 61005, "total_steps": 181800, "loss": 0.0142, "lr": 4.201446993580276e-05, "epoch": 6.711221122112211, "percentage": 33.56, "elapsed_time": "2:23:56", "remaining_time": "4:45:01", "throughput": 1490.66, "total_tokens": 12874144} {"current_steps": 61010, "total_steps": 181800, "loss": 0.0184, "lr": 4.201271138802965e-05, "epoch": 6.711771177117711, "percentage": 33.56, "elapsed_time": "2:23:57", "remaining_time": "4:45:00", "throughput": 1490.66, "total_tokens": 12875200} {"current_steps": 61015, "total_steps": 181800, "loss": 0.1046, "lr": 4.201095268345855e-05, "epoch": 6.712321232123212, "percentage": 33.56, "elapsed_time": "2:23:57", "remaining_time": "4:44:59", "throughput": 1490.66, "total_tokens": 12876192} {"current_steps": 61020, "total_steps": 181800, "loss": 0.0214, "lr": 4.2009193822105654e-05, "epoch": 6.712871287128713, "percentage": 33.56, "elapsed_time": "2:23:58", "remaining_time": "4:44:58", "throughput": 1490.66, "total_tokens": 12877216} {"current_steps": 61025, "total_steps": 181800, "loss": 0.0044, "lr": 4.200743480398718e-05, "epoch": 6.713421342134214, "percentage": 33.57, "elapsed_time": "2:23:59", "remaining_time": "4:44:58", "throughput": 1490.66, "total_tokens": 12878272} {"current_steps": 61030, "total_steps": 181800, "loss": 0.1053, "lr": 4.2005675629119344e-05, "epoch": 6.713971397139714, "percentage": 33.57, "elapsed_time": "2:23:59", "remaining_time": "4:44:57", "throughput": 1490.67, "total_tokens": 12879328} {"current_steps": 61035, "total_steps": 181800, "loss": 0.0793, "lr": 4.2003916297518354e-05, "epoch": 6.714521452145215, "percentage": 33.57, "elapsed_time": "2:24:00", "remaining_time": "4:44:56", "throughput": 1490.67, "total_tokens": 12880416} {"current_steps": 61040, "total_steps": 181800, "loss": 0.0719, "lr": 4.200215680920043e-05, "epoch": 6.715071507150715, "percentage": 33.58, "elapsed_time": "2:24:01", "remaining_time": "4:44:55", "throughput": 1490.68, "total_tokens": 12881504} {"current_steps": 61045, "total_steps": 181800, "loss": 0.0067, "lr": 4.200039716418178e-05, "epoch": 6.715621562156215, "percentage": 33.58, "elapsed_time": "2:24:02", "remaining_time": "4:44:55", "throughput": 1490.68, "total_tokens": 12882560} {"current_steps": 61050, "total_steps": 181800, "loss": 0.0975, "lr": 4.199863736247863e-05, "epoch": 6.7161716171617165, "percentage": 33.58, "elapsed_time": "2:24:02", "remaining_time": "4:44:54", "throughput": 1490.69, "total_tokens": 12883648} {"current_steps": 61055, "total_steps": 181800, "loss": 0.1071, "lr": 4.1996877404107196e-05, "epoch": 6.716721672167217, "percentage": 33.58, "elapsed_time": "2:24:03", "remaining_time": "4:44:53", "throughput": 1490.7, "total_tokens": 12884736} {"current_steps": 61060, "total_steps": 181800, "loss": 0.0179, "lr": 4.19951172890837e-05, "epoch": 6.717271727172717, "percentage": 33.59, "elapsed_time": "2:24:04", "remaining_time": "4:44:52", "throughput": 1490.7, "total_tokens": 12885824} {"current_steps": 61065, "total_steps": 181800, "loss": 0.1302, "lr": 4.199335701742436e-05, "epoch": 6.717821782178218, "percentage": 33.59, "elapsed_time": "2:24:04", "remaining_time": "4:44:52", "throughput": 1490.71, "total_tokens": 12886944} {"current_steps": 61070, "total_steps": 181800, "loss": 0.0693, "lr": 4.1991596589145407e-05, "epoch": 6.718371837183718, "percentage": 33.59, "elapsed_time": "2:24:05", "remaining_time": "4:44:51", "throughput": 1490.72, "total_tokens": 12888000} {"current_steps": 61075, "total_steps": 181800, "loss": 0.0111, "lr": 4.198983600426305e-05, "epoch": 6.718921892189218, "percentage": 33.59, "elapsed_time": "2:24:06", "remaining_time": "4:44:50", "throughput": 1490.72, "total_tokens": 12889088} {"current_steps": 61080, "total_steps": 181800, "loss": 0.0726, "lr": 4.1988075262793534e-05, "epoch": 6.7194719471947195, "percentage": 33.6, "elapsed_time": "2:24:06", "remaining_time": "4:44:49", "throughput": 1490.73, "total_tokens": 12890144} {"current_steps": 61085, "total_steps": 181800, "loss": 0.0092, "lr": 4.198631436475309e-05, "epoch": 6.72002200220022, "percentage": 33.6, "elapsed_time": "2:24:07", "remaining_time": "4:44:49", "throughput": 1490.74, "total_tokens": 12891264} {"current_steps": 61090, "total_steps": 181800, "loss": 0.0415, "lr": 4.198455331015793e-05, "epoch": 6.720572057205721, "percentage": 33.6, "elapsed_time": "2:24:08", "remaining_time": "4:44:48", "throughput": 1490.74, "total_tokens": 12892320} {"current_steps": 61095, "total_steps": 181800, "loss": 0.0091, "lr": 4.198279209902429e-05, "epoch": 6.721122112211221, "percentage": 33.61, "elapsed_time": "2:24:08", "remaining_time": "4:44:47", "throughput": 1490.75, "total_tokens": 12893440} {"current_steps": 61100, "total_steps": 181800, "loss": 0.0182, "lr": 4.1981030731368395e-05, "epoch": 6.721672167216722, "percentage": 33.61, "elapsed_time": "2:24:09", "remaining_time": "4:44:46", "throughput": 1490.76, "total_tokens": 12894560} {"current_steps": 61105, "total_steps": 181800, "loss": 0.033, "lr": 4.197926920720651e-05, "epoch": 6.722222222222222, "percentage": 33.61, "elapsed_time": "2:24:10", "remaining_time": "4:44:46", "throughput": 1490.76, "total_tokens": 12895616} {"current_steps": 61110, "total_steps": 181800, "loss": 0.1126, "lr": 4.1977507526554835e-05, "epoch": 6.7227722772277225, "percentage": 33.61, "elapsed_time": "2:24:11", "remaining_time": "4:44:45", "throughput": 1490.77, "total_tokens": 12896736} {"current_steps": 61115, "total_steps": 181800, "loss": 0.0281, "lr": 4.197574568942962e-05, "epoch": 6.723322332233224, "percentage": 33.62, "elapsed_time": "2:24:11", "remaining_time": "4:44:44", "throughput": 1490.77, "total_tokens": 12897728} {"current_steps": 61120, "total_steps": 181800, "loss": 0.0644, "lr": 4.19739836958471e-05, "epoch": 6.723872387238724, "percentage": 33.62, "elapsed_time": "2:24:12", "remaining_time": "4:44:43", "throughput": 1490.78, "total_tokens": 12898816} {"current_steps": 61125, "total_steps": 181800, "loss": 0.0365, "lr": 4.197222154582352e-05, "epoch": 6.724422442244224, "percentage": 33.62, "elapsed_time": "2:24:13", "remaining_time": "4:44:43", "throughput": 1490.78, "total_tokens": 12899904} {"current_steps": 61130, "total_steps": 181800, "loss": 0.0889, "lr": 4.197045923937512e-05, "epoch": 6.724972497249725, "percentage": 33.62, "elapsed_time": "2:24:13", "remaining_time": "4:44:42", "throughput": 1490.79, "total_tokens": 12900960} {"current_steps": 61135, "total_steps": 181800, "loss": 0.0079, "lr": 4.1968696776518145e-05, "epoch": 6.725522552255225, "percentage": 33.63, "elapsed_time": "2:24:14", "remaining_time": "4:44:41", "throughput": 1490.79, "total_tokens": 12902016} {"current_steps": 61140, "total_steps": 181800, "loss": 0.0329, "lr": 4.1966934157268823e-05, "epoch": 6.726072607260726, "percentage": 33.63, "elapsed_time": "2:24:15", "remaining_time": "4:44:41", "throughput": 1490.8, "total_tokens": 12903104} {"current_steps": 61145, "total_steps": 181800, "loss": 0.0162, "lr": 4.196517138164342e-05, "epoch": 6.726622662266227, "percentage": 33.63, "elapsed_time": "2:24:15", "remaining_time": "4:44:40", "throughput": 1490.8, "total_tokens": 12904192} {"current_steps": 61150, "total_steps": 181800, "loss": 0.0111, "lr": 4.196340844965817e-05, "epoch": 6.727172717271727, "percentage": 33.64, "elapsed_time": "2:24:16", "remaining_time": "4:44:39", "throughput": 1490.8, "total_tokens": 12905216} {"current_steps": 61155, "total_steps": 181800, "loss": 0.0051, "lr": 4.196164536132932e-05, "epoch": 6.727722772277228, "percentage": 33.64, "elapsed_time": "2:24:17", "remaining_time": "4:44:38", "throughput": 1490.81, "total_tokens": 12906336} {"current_steps": 61160, "total_steps": 181800, "loss": 0.0234, "lr": 4.1959882116673126e-05, "epoch": 6.728272827282728, "percentage": 33.64, "elapsed_time": "2:24:17", "remaining_time": "4:44:38", "throughput": 1490.82, "total_tokens": 12907392} {"current_steps": 61165, "total_steps": 181800, "loss": 0.0147, "lr": 4.195811871570584e-05, "epoch": 6.728822882288229, "percentage": 33.64, "elapsed_time": "2:24:18", "remaining_time": "4:44:37", "throughput": 1490.83, "total_tokens": 12908544} {"current_steps": 61170, "total_steps": 181800, "loss": 0.018, "lr": 4.195635515844371e-05, "epoch": 6.729372937293729, "percentage": 33.65, "elapsed_time": "2:24:19", "remaining_time": "4:44:36", "throughput": 1490.83, "total_tokens": 12909600} {"current_steps": 61175, "total_steps": 181800, "loss": 0.0429, "lr": 4.1954591444902994e-05, "epoch": 6.72992299229923, "percentage": 33.65, "elapsed_time": "2:24:20", "remaining_time": "4:44:35", "throughput": 1490.84, "total_tokens": 12910688} {"current_steps": 61180, "total_steps": 181800, "loss": 0.0994, "lr": 4.1952827575099934e-05, "epoch": 6.730473047304731, "percentage": 33.65, "elapsed_time": "2:24:20", "remaining_time": "4:44:35", "throughput": 1490.84, "total_tokens": 12911680} {"current_steps": 61185, "total_steps": 181800, "loss": 0.1149, "lr": 4.1951063549050806e-05, "epoch": 6.731023102310231, "percentage": 33.66, "elapsed_time": "2:24:21", "remaining_time": "4:44:34", "throughput": 1490.84, "total_tokens": 12912704} {"current_steps": 61190, "total_steps": 181800, "loss": 0.117, "lr": 4.194929936677185e-05, "epoch": 6.731573157315731, "percentage": 33.66, "elapsed_time": "2:24:22", "remaining_time": "4:44:33", "throughput": 1490.84, "total_tokens": 12913792} {"current_steps": 61195, "total_steps": 181800, "loss": 0.0183, "lr": 4.194753502827935e-05, "epoch": 6.732123212321232, "percentage": 33.66, "elapsed_time": "2:24:22", "remaining_time": "4:44:32", "throughput": 1490.85, "total_tokens": 12914848} {"current_steps": 61200, "total_steps": 181800, "loss": 0.1613, "lr": 4.1945770533589535e-05, "epoch": 6.732673267326732, "percentage": 33.66, "elapsed_time": "2:24:23", "remaining_time": "4:44:32", "throughput": 1490.85, "total_tokens": 12915936} {"current_steps": 61205, "total_steps": 181800, "loss": 0.0616, "lr": 4.194400588271869e-05, "epoch": 6.7332233223322335, "percentage": 33.67, "elapsed_time": "2:24:24", "remaining_time": "4:44:31", "throughput": 1490.85, "total_tokens": 12916928} {"current_steps": 61210, "total_steps": 181800, "loss": 0.0107, "lr": 4.1942241075683084e-05, "epoch": 6.733773377337734, "percentage": 33.67, "elapsed_time": "2:24:24", "remaining_time": "4:44:30", "throughput": 1490.84, "total_tokens": 12917920} {"current_steps": 61215, "total_steps": 181800, "loss": 0.0847, "lr": 4.194047611249896e-05, "epoch": 6.734323432343234, "percentage": 33.67, "elapsed_time": "2:24:25", "remaining_time": "4:44:29", "throughput": 1490.84, "total_tokens": 12918944} {"current_steps": 61220, "total_steps": 181800, "loss": 0.0691, "lr": 4.193871099318259e-05, "epoch": 6.734873487348735, "percentage": 33.67, "elapsed_time": "2:24:26", "remaining_time": "4:44:29", "throughput": 1490.85, "total_tokens": 12920000} {"current_steps": 61225, "total_steps": 181800, "loss": 0.0652, "lr": 4.1936945717750266e-05, "epoch": 6.735423542354235, "percentage": 33.68, "elapsed_time": "2:24:26", "remaining_time": "4:44:28", "throughput": 1490.85, "total_tokens": 12921088} {"current_steps": 61230, "total_steps": 181800, "loss": 0.0316, "lr": 4.193518028621824e-05, "epoch": 6.735973597359736, "percentage": 33.68, "elapsed_time": "2:24:27", "remaining_time": "4:44:27", "throughput": 1490.86, "total_tokens": 12922144} {"current_steps": 61235, "total_steps": 181800, "loss": 0.0562, "lr": 4.193341469860277e-05, "epoch": 6.7365236523652365, "percentage": 33.68, "elapsed_time": "2:24:28", "remaining_time": "4:44:26", "throughput": 1490.86, "total_tokens": 12923232} {"current_steps": 61240, "total_steps": 181800, "loss": 0.033, "lr": 4.193164895492015e-05, "epoch": 6.737073707370737, "percentage": 33.69, "elapsed_time": "2:24:28", "remaining_time": "4:44:26", "throughput": 1490.87, "total_tokens": 12924320} {"current_steps": 61245, "total_steps": 181800, "loss": 0.0066, "lr": 4.192988305518664e-05, "epoch": 6.737623762376238, "percentage": 33.69, "elapsed_time": "2:24:29", "remaining_time": "4:44:25", "throughput": 1490.87, "total_tokens": 12925344} {"current_steps": 61250, "total_steps": 181800, "loss": 0.021, "lr": 4.1928116999418525e-05, "epoch": 6.738173817381738, "percentage": 33.69, "elapsed_time": "2:24:30", "remaining_time": "4:44:24", "throughput": 1490.87, "total_tokens": 12926368} {"current_steps": 61255, "total_steps": 181800, "loss": 0.0285, "lr": 4.192635078763209e-05, "epoch": 6.738723872387238, "percentage": 33.69, "elapsed_time": "2:24:31", "remaining_time": "4:44:23", "throughput": 1490.88, "total_tokens": 12927488} {"current_steps": 61260, "total_steps": 181800, "loss": 0.0462, "lr": 4.192458441984359e-05, "epoch": 6.739273927392739, "percentage": 33.7, "elapsed_time": "2:24:31", "remaining_time": "4:44:23", "throughput": 1490.88, "total_tokens": 12928544} {"current_steps": 61265, "total_steps": 181800, "loss": 0.0301, "lr": 4.192281789606931e-05, "epoch": 6.7398239823982395, "percentage": 33.7, "elapsed_time": "2:24:32", "remaining_time": "4:44:22", "throughput": 1490.89, "total_tokens": 12929664} {"current_steps": 61270, "total_steps": 181800, "loss": 0.026, "lr": 4.1921051216325554e-05, "epoch": 6.740374037403741, "percentage": 33.7, "elapsed_time": "2:24:33", "remaining_time": "4:44:21", "throughput": 1490.89, "total_tokens": 12930720} {"current_steps": 61275, "total_steps": 181800, "loss": 0.0121, "lr": 4.191928438062857e-05, "epoch": 6.740924092409241, "percentage": 33.7, "elapsed_time": "2:24:33", "remaining_time": "4:44:21", "throughput": 1490.89, "total_tokens": 12931744} {"current_steps": 61280, "total_steps": 181800, "loss": 0.0189, "lr": 4.191751738899468e-05, "epoch": 6.741474147414742, "percentage": 33.71, "elapsed_time": "2:24:34", "remaining_time": "4:44:20", "throughput": 1490.89, "total_tokens": 12932800} {"current_steps": 61285, "total_steps": 181800, "loss": 0.0055, "lr": 4.191575024144014e-05, "epoch": 6.742024202420242, "percentage": 33.71, "elapsed_time": "2:24:35", "remaining_time": "4:44:19", "throughput": 1490.9, "total_tokens": 12933856} {"current_steps": 61290, "total_steps": 181800, "loss": 0.02, "lr": 4.191398293798125e-05, "epoch": 6.742574257425742, "percentage": 33.71, "elapsed_time": "2:24:35", "remaining_time": "4:44:18", "throughput": 1490.9, "total_tokens": 12934912} {"current_steps": 61295, "total_steps": 181800, "loss": 0.0096, "lr": 4.1912215478634286e-05, "epoch": 6.743124312431243, "percentage": 33.72, "elapsed_time": "2:24:36", "remaining_time": "4:44:18", "throughput": 1490.91, "total_tokens": 12936000} {"current_steps": 61300, "total_steps": 181800, "loss": 0.034, "lr": 4.191044786341556e-05, "epoch": 6.743674367436744, "percentage": 33.72, "elapsed_time": "2:24:37", "remaining_time": "4:44:17", "throughput": 1490.92, "total_tokens": 12937120} {"current_steps": 61305, "total_steps": 181800, "loss": 0.0159, "lr": 4.190868009234134e-05, "epoch": 6.744224422442244, "percentage": 33.72, "elapsed_time": "2:24:37", "remaining_time": "4:44:16", "throughput": 1490.92, "total_tokens": 12938208} {"current_steps": 61310, "total_steps": 181800, "loss": 0.0125, "lr": 4.190691216542794e-05, "epoch": 6.744774477447745, "percentage": 33.72, "elapsed_time": "2:24:38", "remaining_time": "4:44:15", "throughput": 1490.93, "total_tokens": 12939296} {"current_steps": 61315, "total_steps": 181800, "loss": 0.0495, "lr": 4.190514408269164e-05, "epoch": 6.745324532453245, "percentage": 33.73, "elapsed_time": "2:24:39", "remaining_time": "4:44:15", "throughput": 1490.93, "total_tokens": 12940352} {"current_steps": 61320, "total_steps": 181800, "loss": 0.084, "lr": 4.190337584414873e-05, "epoch": 6.745874587458746, "percentage": 33.73, "elapsed_time": "2:24:40", "remaining_time": "4:44:14", "throughput": 1490.93, "total_tokens": 12941344} {"current_steps": 61325, "total_steps": 181800, "loss": 0.0028, "lr": 4.190160744981553e-05, "epoch": 6.7464246424642464, "percentage": 33.73, "elapsed_time": "2:24:40", "remaining_time": "4:44:13", "throughput": 1490.93, "total_tokens": 12942368} {"current_steps": 61330, "total_steps": 181800, "loss": 0.0864, "lr": 4.189983889970832e-05, "epoch": 6.746974697469747, "percentage": 33.73, "elapsed_time": "2:24:41", "remaining_time": "4:44:12", "throughput": 1490.94, "total_tokens": 12943456} {"current_steps": 61335, "total_steps": 181800, "loss": 0.0144, "lr": 4.18980701938434e-05, "epoch": 6.747524752475248, "percentage": 33.74, "elapsed_time": "2:24:42", "remaining_time": "4:44:12", "throughput": 1490.94, "total_tokens": 12944512} {"current_steps": 61340, "total_steps": 181800, "loss": 0.0166, "lr": 4.189630133223707e-05, "epoch": 6.748074807480748, "percentage": 33.74, "elapsed_time": "2:24:42", "remaining_time": "4:44:11", "throughput": 1490.94, "total_tokens": 12945568} {"current_steps": 61345, "total_steps": 181800, "loss": 0.1143, "lr": 4.1894532314905644e-05, "epoch": 6.748624862486249, "percentage": 33.74, "elapsed_time": "2:24:43", "remaining_time": "4:44:10", "throughput": 1490.94, "total_tokens": 12946592} {"current_steps": 61350, "total_steps": 181800, "loss": 0.0507, "lr": 4.189276314186542e-05, "epoch": 6.749174917491749, "percentage": 33.75, "elapsed_time": "2:24:44", "remaining_time": "4:44:09", "throughput": 1490.95, "total_tokens": 12947712} {"current_steps": 61355, "total_steps": 181800, "loss": 0.0346, "lr": 4.189099381313271e-05, "epoch": 6.7497249724972495, "percentage": 33.75, "elapsed_time": "2:24:44", "remaining_time": "4:44:09", "throughput": 1490.95, "total_tokens": 12948736} {"current_steps": 61360, "total_steps": 181800, "loss": 0.0761, "lr": 4.188922432872381e-05, "epoch": 6.7502750275027505, "percentage": 33.75, "elapsed_time": "2:24:45", "remaining_time": "4:44:08", "throughput": 1490.95, "total_tokens": 12949760} {"current_steps": 61365, "total_steps": 181800, "loss": 0.0422, "lr": 4.1887454688655034e-05, "epoch": 6.750825082508251, "percentage": 33.75, "elapsed_time": "2:24:46", "remaining_time": "4:44:07", "throughput": 1490.96, "total_tokens": 12950880} {"current_steps": 61370, "total_steps": 181800, "loss": 0.0285, "lr": 4.188568489294269e-05, "epoch": 6.751375137513751, "percentage": 33.76, "elapsed_time": "2:24:46", "remaining_time": "4:44:06", "throughput": 1490.96, "total_tokens": 12951904} {"current_steps": 61375, "total_steps": 181800, "loss": 0.0551, "lr": 4.18839149416031e-05, "epoch": 6.751925192519252, "percentage": 33.76, "elapsed_time": "2:24:47", "remaining_time": "4:44:06", "throughput": 1490.97, "total_tokens": 12952992} {"current_steps": 61380, "total_steps": 181800, "loss": 0.0286, "lr": 4.1882144834652555e-05, "epoch": 6.752475247524752, "percentage": 33.76, "elapsed_time": "2:24:48", "remaining_time": "4:44:05", "throughput": 1490.97, "total_tokens": 12954016} {"current_steps": 61385, "total_steps": 181800, "loss": 0.0615, "lr": 4.1880374572107386e-05, "epoch": 6.753025302530253, "percentage": 33.77, "elapsed_time": "2:24:49", "remaining_time": "4:44:04", "throughput": 1490.98, "total_tokens": 12955136} {"current_steps": 61390, "total_steps": 181800, "loss": 0.0168, "lr": 4.18786041539839e-05, "epoch": 6.7535753575357536, "percentage": 33.77, "elapsed_time": "2:24:49", "remaining_time": "4:44:03", "throughput": 1490.97, "total_tokens": 12956128} {"current_steps": 61395, "total_steps": 181800, "loss": 0.0031, "lr": 4.187683358029843e-05, "epoch": 6.754125412541254, "percentage": 33.77, "elapsed_time": "2:24:50", "remaining_time": "4:44:03", "throughput": 1490.98, "total_tokens": 12957184} {"current_steps": 61400, "total_steps": 181800, "loss": 0.0223, "lr": 4.187506285106728e-05, "epoch": 6.754675467546755, "percentage": 33.77, "elapsed_time": "2:24:51", "remaining_time": "4:44:02", "throughput": 1490.98, "total_tokens": 12958240} {"current_steps": 61405, "total_steps": 181800, "loss": 0.0296, "lr": 4.1873291966306773e-05, "epoch": 6.755225522552255, "percentage": 33.78, "elapsed_time": "2:24:51", "remaining_time": "4:44:01", "throughput": 1490.99, "total_tokens": 12959328} {"current_steps": 61410, "total_steps": 181800, "loss": 0.0729, "lr": 4.187152092603322e-05, "epoch": 6.755775577557756, "percentage": 33.78, "elapsed_time": "2:24:52", "remaining_time": "4:44:00", "throughput": 1490.99, "total_tokens": 12960352} {"current_steps": 61415, "total_steps": 181800, "loss": 0.0149, "lr": 4.186974973026296e-05, "epoch": 6.756325632563256, "percentage": 33.78, "elapsed_time": "2:24:53", "remaining_time": "4:44:00", "throughput": 1490.99, "total_tokens": 12961376} {"current_steps": 61420, "total_steps": 181800, "loss": 0.1836, "lr": 4.186797837901232e-05, "epoch": 6.756875687568757, "percentage": 33.78, "elapsed_time": "2:24:53", "remaining_time": "4:43:59", "throughput": 1490.99, "total_tokens": 12962400} {"current_steps": 61425, "total_steps": 181800, "loss": 0.0478, "lr": 4.186620687229761e-05, "epoch": 6.757425742574258, "percentage": 33.79, "elapsed_time": "2:24:54", "remaining_time": "4:43:58", "throughput": 1491.0, "total_tokens": 12963520} {"current_steps": 61430, "total_steps": 181800, "loss": 0.0559, "lr": 4.186443521013517e-05, "epoch": 6.757975797579758, "percentage": 33.79, "elapsed_time": "2:24:55", "remaining_time": "4:43:57", "throughput": 1491.0, "total_tokens": 12964576} {"current_steps": 61435, "total_steps": 181800, "loss": 0.0245, "lr": 4.186266339254131e-05, "epoch": 6.758525852585258, "percentage": 33.79, "elapsed_time": "2:24:55", "remaining_time": "4:43:57", "throughput": 1490.99, "total_tokens": 12965536} {"current_steps": 61440, "total_steps": 181800, "loss": 0.0522, "lr": 4.186089141953238e-05, "epoch": 6.759075907590759, "percentage": 33.8, "elapsed_time": "2:24:56", "remaining_time": "4:43:56", "throughput": 1491.0, "total_tokens": 12966624} {"current_steps": 61445, "total_steps": 181800, "loss": 0.0292, "lr": 4.1859119291124715e-05, "epoch": 6.759625962596259, "percentage": 33.8, "elapsed_time": "2:24:57", "remaining_time": "4:43:55", "throughput": 1491.0, "total_tokens": 12967680} {"current_steps": 61450, "total_steps": 181800, "loss": 0.0554, "lr": 4.1857347007334626e-05, "epoch": 6.7601760176017605, "percentage": 33.8, "elapsed_time": "2:24:57", "remaining_time": "4:43:55", "throughput": 1491.01, "total_tokens": 12968736} {"current_steps": 61455, "total_steps": 181800, "loss": 0.0296, "lr": 4.1855574568178454e-05, "epoch": 6.760726072607261, "percentage": 33.8, "elapsed_time": "2:24:58", "remaining_time": "4:43:54", "throughput": 1491.01, "total_tokens": 12969760} {"current_steps": 61460, "total_steps": 181800, "loss": 0.0177, "lr": 4.185380197367255e-05, "epoch": 6.761276127612762, "percentage": 33.81, "elapsed_time": "2:24:59", "remaining_time": "4:43:53", "throughput": 1491.01, "total_tokens": 12970784} {"current_steps": 61465, "total_steps": 181800, "loss": 0.0081, "lr": 4.185202922383324e-05, "epoch": 6.761826182618262, "percentage": 33.81, "elapsed_time": "2:25:00", "remaining_time": "4:43:52", "throughput": 1491.01, "total_tokens": 12971808} {"current_steps": 61470, "total_steps": 181800, "loss": 0.0107, "lr": 4.185025631867686e-05, "epoch": 6.762376237623762, "percentage": 33.81, "elapsed_time": "2:25:00", "remaining_time": "4:43:52", "throughput": 1491.0, "total_tokens": 12972832} {"current_steps": 61475, "total_steps": 181800, "loss": 0.0597, "lr": 4.1848483258219753e-05, "epoch": 6.762926292629263, "percentage": 33.81, "elapsed_time": "2:25:01", "remaining_time": "4:43:51", "throughput": 1491.01, "total_tokens": 12973952} {"current_steps": 61480, "total_steps": 181800, "loss": 0.0294, "lr": 4.184671004247826e-05, "epoch": 6.7634763476347635, "percentage": 33.82, "elapsed_time": "2:25:02", "remaining_time": "4:43:50", "throughput": 1491.02, "total_tokens": 12975008} {"current_steps": 61485, "total_steps": 181800, "loss": 0.0458, "lr": 4.184493667146873e-05, "epoch": 6.764026402640264, "percentage": 33.82, "elapsed_time": "2:25:02", "remaining_time": "4:43:49", "throughput": 1491.02, "total_tokens": 12976032} {"current_steps": 61490, "total_steps": 181800, "loss": 0.0228, "lr": 4.184316314520749e-05, "epoch": 6.764576457645765, "percentage": 33.82, "elapsed_time": "2:25:03", "remaining_time": "4:43:49", "throughput": 1491.02, "total_tokens": 12977088} {"current_steps": 61495, "total_steps": 181800, "loss": 0.0198, "lr": 4.18413894637109e-05, "epoch": 6.765126512651265, "percentage": 33.83, "elapsed_time": "2:25:04", "remaining_time": "4:43:48", "throughput": 1491.03, "total_tokens": 12978176} {"current_steps": 61500, "total_steps": 181800, "loss": 0.0169, "lr": 4.1839615626995315e-05, "epoch": 6.765676567656766, "percentage": 33.83, "elapsed_time": "2:25:04", "remaining_time": "4:43:47", "throughput": 1491.03, "total_tokens": 12979264} {"current_steps": 61505, "total_steps": 181800, "loss": 0.0433, "lr": 4.183784163507707e-05, "epoch": 6.766226622662266, "percentage": 33.83, "elapsed_time": "2:25:05", "remaining_time": "4:43:46", "throughput": 1491.05, "total_tokens": 12980384} {"current_steps": 61510, "total_steps": 181800, "loss": 0.0118, "lr": 4.183606748797251e-05, "epoch": 6.7667766776677665, "percentage": 33.83, "elapsed_time": "2:25:06", "remaining_time": "4:43:46", "throughput": 1491.04, "total_tokens": 12981376} {"current_steps": 61515, "total_steps": 181800, "loss": 0.0691, "lr": 4.1834293185698e-05, "epoch": 6.767326732673268, "percentage": 33.84, "elapsed_time": "2:25:06", "remaining_time": "4:43:45", "throughput": 1491.05, "total_tokens": 12982464} {"current_steps": 61520, "total_steps": 181800, "loss": 0.0074, "lr": 4.183251872826989e-05, "epoch": 6.767876787678768, "percentage": 33.84, "elapsed_time": "2:25:07", "remaining_time": "4:43:44", "throughput": 1491.05, "total_tokens": 12983520} {"current_steps": 61525, "total_steps": 181800, "loss": 0.0754, "lr": 4.1830744115704524e-05, "epoch": 6.768426842684269, "percentage": 33.84, "elapsed_time": "2:25:08", "remaining_time": "4:43:43", "throughput": 1491.05, "total_tokens": 12984544} {"current_steps": 61530, "total_steps": 181800, "loss": 0.0896, "lr": 4.1828969348018276e-05, "epoch": 6.768976897689769, "percentage": 33.84, "elapsed_time": "2:25:09", "remaining_time": "4:43:43", "throughput": 1491.05, "total_tokens": 12985600} {"current_steps": 61535, "total_steps": 181800, "loss": 0.0076, "lr": 4.182719442522748e-05, "epoch": 6.769526952695269, "percentage": 33.85, "elapsed_time": "2:25:09", "remaining_time": "4:43:42", "throughput": 1491.06, "total_tokens": 12986656} {"current_steps": 61540, "total_steps": 181800, "loss": 0.0369, "lr": 4.182541934734852e-05, "epoch": 6.77007700770077, "percentage": 33.85, "elapsed_time": "2:25:10", "remaining_time": "4:43:41", "throughput": 1491.06, "total_tokens": 12987680} {"current_steps": 61545, "total_steps": 181800, "loss": 0.0081, "lr": 4.182364411439774e-05, "epoch": 6.770627062706271, "percentage": 33.85, "elapsed_time": "2:25:11", "remaining_time": "4:43:40", "throughput": 1491.06, "total_tokens": 12988768} {"current_steps": 61550, "total_steps": 181800, "loss": 0.1122, "lr": 4.18218687263915e-05, "epoch": 6.771177117711771, "percentage": 33.86, "elapsed_time": "2:25:11", "remaining_time": "4:43:40", "throughput": 1491.07, "total_tokens": 12989824} {"current_steps": 61555, "total_steps": 181800, "loss": 0.0062, "lr": 4.1820093183346174e-05, "epoch": 6.771727172717272, "percentage": 33.86, "elapsed_time": "2:25:12", "remaining_time": "4:43:39", "throughput": 1491.07, "total_tokens": 12990912} {"current_steps": 61560, "total_steps": 181800, "loss": 0.0401, "lr": 4.181831748527811e-05, "epoch": 6.772277227722772, "percentage": 33.86, "elapsed_time": "2:25:13", "remaining_time": "4:43:38", "throughput": 1491.08, "total_tokens": 12991968} {"current_steps": 61565, "total_steps": 181800, "loss": 0.0549, "lr": 4.18165416322037e-05, "epoch": 6.772827282728273, "percentage": 33.86, "elapsed_time": "2:25:13", "remaining_time": "4:43:37", "throughput": 1491.08, "total_tokens": 12992992} {"current_steps": 61570, "total_steps": 181800, "loss": 0.0582, "lr": 4.1814765624139286e-05, "epoch": 6.773377337733773, "percentage": 33.87, "elapsed_time": "2:25:14", "remaining_time": "4:43:37", "throughput": 1491.08, "total_tokens": 12994048} {"current_steps": 61575, "total_steps": 181800, "loss": 0.017, "lr": 4.181298946110125e-05, "epoch": 6.773927392739274, "percentage": 33.87, "elapsed_time": "2:25:15", "remaining_time": "4:43:36", "throughput": 1491.09, "total_tokens": 12995168} {"current_steps": 61580, "total_steps": 181800, "loss": 0.0868, "lr": 4.181121314310595e-05, "epoch": 6.774477447744775, "percentage": 33.87, "elapsed_time": "2:25:15", "remaining_time": "4:43:35", "throughput": 1491.08, "total_tokens": 12996128} {"current_steps": 61585, "total_steps": 181800, "loss": 0.0711, "lr": 4.180943667016977e-05, "epoch": 6.775027502750275, "percentage": 33.88, "elapsed_time": "2:25:16", "remaining_time": "4:43:34", "throughput": 1491.08, "total_tokens": 12997152} {"current_steps": 61590, "total_steps": 181800, "loss": 0.0151, "lr": 4.180766004230908e-05, "epoch": 6.775577557755776, "percentage": 33.88, "elapsed_time": "2:25:17", "remaining_time": "4:43:34", "throughput": 1491.08, "total_tokens": 12998208} {"current_steps": 61595, "total_steps": 181800, "loss": 0.102, "lr": 4.1805883259540245e-05, "epoch": 6.776127612761276, "percentage": 33.88, "elapsed_time": "2:25:17", "remaining_time": "4:43:33", "throughput": 1491.08, "total_tokens": 12999232} {"current_steps": 61600, "total_steps": 181800, "loss": 0.0529, "lr": 4.1804106321879654e-05, "epoch": 6.776677667766776, "percentage": 33.88, "elapsed_time": "2:25:18", "remaining_time": "4:43:32", "throughput": 1491.09, "total_tokens": 13000352} {"current_steps": 61605, "total_steps": 181800, "loss": 0.0188, "lr": 4.180232922934368e-05, "epoch": 6.7772277227722775, "percentage": 33.89, "elapsed_time": "2:25:19", "remaining_time": "4:43:31", "throughput": 1491.09, "total_tokens": 13001376} {"current_steps": 61610, "total_steps": 181800, "loss": 0.0573, "lr": 4.18005519819487e-05, "epoch": 6.777777777777778, "percentage": 33.89, "elapsed_time": "2:25:20", "remaining_time": "4:43:31", "throughput": 1491.09, "total_tokens": 13002368} {"current_steps": 61615, "total_steps": 181800, "loss": 0.0598, "lr": 4.179877457971109e-05, "epoch": 6.778327832783278, "percentage": 33.89, "elapsed_time": "2:25:20", "remaining_time": "4:43:30", "throughput": 1491.09, "total_tokens": 13003392} {"current_steps": 61620, "total_steps": 181800, "loss": 0.0396, "lr": 4.179699702264724e-05, "epoch": 6.778877887788779, "percentage": 33.89, "elapsed_time": "2:25:21", "remaining_time": "4:43:29", "throughput": 1491.1, "total_tokens": 13004480} {"current_steps": 61625, "total_steps": 181800, "loss": 0.0357, "lr": 4.179521931077352e-05, "epoch": 6.779427942794279, "percentage": 33.9, "elapsed_time": "2:25:22", "remaining_time": "4:43:29", "throughput": 1491.1, "total_tokens": 13005504} {"current_steps": 61630, "total_steps": 181800, "loss": 0.0889, "lr": 4.179344144410633e-05, "epoch": 6.77997799779978, "percentage": 33.9, "elapsed_time": "2:25:22", "remaining_time": "4:43:28", "throughput": 1491.11, "total_tokens": 13006624} {"current_steps": 61635, "total_steps": 181800, "loss": 0.105, "lr": 4.1791663422662055e-05, "epoch": 6.7805280528052805, "percentage": 33.9, "elapsed_time": "2:25:23", "remaining_time": "4:43:27", "throughput": 1491.1, "total_tokens": 13007616} {"current_steps": 61640, "total_steps": 181800, "loss": 0.0483, "lr": 4.178988524645706e-05, "epoch": 6.781078107810782, "percentage": 33.91, "elapsed_time": "2:25:24", "remaining_time": "4:43:26", "throughput": 1491.1, "total_tokens": 13008672} {"current_steps": 61645, "total_steps": 181800, "loss": 0.1251, "lr": 4.1788106915507765e-05, "epoch": 6.781628162816282, "percentage": 33.91, "elapsed_time": "2:25:24", "remaining_time": "4:43:26", "throughput": 1491.11, "total_tokens": 13009728} {"current_steps": 61650, "total_steps": 181800, "loss": 0.0067, "lr": 4.178632842983053e-05, "epoch": 6.782178217821782, "percentage": 33.91, "elapsed_time": "2:25:25", "remaining_time": "4:43:25", "throughput": 1491.11, "total_tokens": 13010816} {"current_steps": 61655, "total_steps": 181800, "loss": 0.0521, "lr": 4.178454978944177e-05, "epoch": 6.782728272827283, "percentage": 33.91, "elapsed_time": "2:25:26", "remaining_time": "4:43:24", "throughput": 1491.12, "total_tokens": 13011872} {"current_steps": 61660, "total_steps": 181800, "loss": 0.1282, "lr": 4.178277099435787e-05, "epoch": 6.783278327832783, "percentage": 33.92, "elapsed_time": "2:25:26", "remaining_time": "4:43:23", "throughput": 1491.13, "total_tokens": 13012992} {"current_steps": 61665, "total_steps": 181800, "loss": 0.0287, "lr": 4.178099204459521e-05, "epoch": 6.7838283828382835, "percentage": 33.92, "elapsed_time": "2:25:27", "remaining_time": "4:43:23", "throughput": 1491.12, "total_tokens": 13014016} {"current_steps": 61670, "total_steps": 181800, "loss": 0.0735, "lr": 4.177921294017021e-05, "epoch": 6.784378437843785, "percentage": 33.92, "elapsed_time": "2:25:28", "remaining_time": "4:43:22", "throughput": 1491.12, "total_tokens": 13015040} {"current_steps": 61675, "total_steps": 181800, "loss": 0.0044, "lr": 4.1777433681099255e-05, "epoch": 6.784928492849285, "percentage": 33.92, "elapsed_time": "2:25:29", "remaining_time": "4:43:21", "throughput": 1491.13, "total_tokens": 13016128} {"current_steps": 61680, "total_steps": 181800, "loss": 0.006, "lr": 4.177565426739875e-05, "epoch": 6.785478547854785, "percentage": 33.93, "elapsed_time": "2:25:29", "remaining_time": "4:43:20", "throughput": 1491.13, "total_tokens": 13017120} {"current_steps": 61685, "total_steps": 181800, "loss": 0.122, "lr": 4.177387469908507e-05, "epoch": 6.786028602860286, "percentage": 33.93, "elapsed_time": "2:25:30", "remaining_time": "4:43:20", "throughput": 1491.13, "total_tokens": 13018208} {"current_steps": 61690, "total_steps": 181800, "loss": 0.0155, "lr": 4.177209497617465e-05, "epoch": 6.786578657865786, "percentage": 33.93, "elapsed_time": "2:25:31", "remaining_time": "4:43:19", "throughput": 1491.14, "total_tokens": 13019264} {"current_steps": 61695, "total_steps": 181800, "loss": 0.0769, "lr": 4.1770315098683875e-05, "epoch": 6.787128712871287, "percentage": 33.94, "elapsed_time": "2:25:31", "remaining_time": "4:43:18", "throughput": 1491.14, "total_tokens": 13020320} {"current_steps": 61700, "total_steps": 181800, "loss": 0.0266, "lr": 4.176853506662916e-05, "epoch": 6.787678767876788, "percentage": 33.94, "elapsed_time": "2:25:32", "remaining_time": "4:43:17", "throughput": 1491.15, "total_tokens": 13021440} {"current_steps": 61705, "total_steps": 181800, "loss": 0.037, "lr": 4.1766754880026895e-05, "epoch": 6.788228822882289, "percentage": 33.94, "elapsed_time": "2:25:33", "remaining_time": "4:43:17", "throughput": 1491.15, "total_tokens": 13022496} {"current_steps": 61710, "total_steps": 181800, "loss": 0.0395, "lr": 4.17649745388935e-05, "epoch": 6.788778877887789, "percentage": 33.94, "elapsed_time": "2:25:33", "remaining_time": "4:43:16", "throughput": 1491.16, "total_tokens": 13023552} {"current_steps": 61715, "total_steps": 181800, "loss": 0.0153, "lr": 4.1763194043245366e-05, "epoch": 6.789328932893289, "percentage": 33.95, "elapsed_time": "2:25:34", "remaining_time": "4:43:15", "throughput": 1491.15, "total_tokens": 13024576} {"current_steps": 61720, "total_steps": 181800, "loss": 0.0199, "lr": 4.1761413393098936e-05, "epoch": 6.78987898789879, "percentage": 33.95, "elapsed_time": "2:25:35", "remaining_time": "4:43:14", "throughput": 1491.15, "total_tokens": 13025568} {"current_steps": 61725, "total_steps": 181800, "loss": 0.0133, "lr": 4.175963258847059e-05, "epoch": 6.79042904290429, "percentage": 33.95, "elapsed_time": "2:25:35", "remaining_time": "4:43:14", "throughput": 1491.16, "total_tokens": 13026656} {"current_steps": 61730, "total_steps": 181800, "loss": 0.1185, "lr": 4.175785162937676e-05, "epoch": 6.790979097909791, "percentage": 33.95, "elapsed_time": "2:25:36", "remaining_time": "4:43:13", "throughput": 1491.16, "total_tokens": 13027712} {"current_steps": 61735, "total_steps": 181800, "loss": 0.0974, "lr": 4.1756070515833845e-05, "epoch": 6.791529152915292, "percentage": 33.96, "elapsed_time": "2:25:37", "remaining_time": "4:43:12", "throughput": 1491.16, "total_tokens": 13028704} {"current_steps": 61740, "total_steps": 181800, "loss": 0.1084, "lr": 4.175428924785828e-05, "epoch": 6.792079207920792, "percentage": 33.96, "elapsed_time": "2:25:38", "remaining_time": "4:43:11", "throughput": 1491.15, "total_tokens": 13029696} {"current_steps": 61745, "total_steps": 181800, "loss": 0.1072, "lr": 4.175250782546646e-05, "epoch": 6.792629262926293, "percentage": 33.96, "elapsed_time": "2:25:38", "remaining_time": "4:43:11", "throughput": 1491.16, "total_tokens": 13030752} {"current_steps": 61750, "total_steps": 181800, "loss": 0.0112, "lr": 4.175072624867481e-05, "epoch": 6.793179317931793, "percentage": 33.97, "elapsed_time": "2:25:39", "remaining_time": "4:43:10", "throughput": 1491.15, "total_tokens": 13031712} {"current_steps": 61755, "total_steps": 181800, "loss": 0.019, "lr": 4.174894451749977e-05, "epoch": 6.793729372937293, "percentage": 33.97, "elapsed_time": "2:25:40", "remaining_time": "4:43:09", "throughput": 1491.15, "total_tokens": 13032800} {"current_steps": 61760, "total_steps": 181800, "loss": 0.0954, "lr": 4.174716263195773e-05, "epoch": 6.7942794279427945, "percentage": 33.97, "elapsed_time": "2:25:40", "remaining_time": "4:43:09", "throughput": 1491.15, "total_tokens": 13033792} {"current_steps": 61765, "total_steps": 181800, "loss": 0.0921, "lr": 4.174538059206513e-05, "epoch": 6.794829482948295, "percentage": 33.97, "elapsed_time": "2:25:41", "remaining_time": "4:43:08", "throughput": 1491.15, "total_tokens": 13034816} {"current_steps": 61770, "total_steps": 181800, "loss": 0.0107, "lr": 4.1743598397838405e-05, "epoch": 6.795379537953796, "percentage": 33.98, "elapsed_time": "2:25:42", "remaining_time": "4:43:07", "throughput": 1491.15, "total_tokens": 13035840} {"current_steps": 61775, "total_steps": 181800, "loss": 0.0336, "lr": 4.174181604929396e-05, "epoch": 6.795929592959296, "percentage": 33.98, "elapsed_time": "2:25:42", "remaining_time": "4:43:06", "throughput": 1491.15, "total_tokens": 13036864} {"current_steps": 61780, "total_steps": 181800, "loss": 0.0208, "lr": 4.174003354644823e-05, "epoch": 6.796479647964796, "percentage": 33.98, "elapsed_time": "2:25:43", "remaining_time": "4:43:06", "throughput": 1491.15, "total_tokens": 13037920} {"current_steps": 61785, "total_steps": 181800, "loss": 0.004, "lr": 4.1738250889317635e-05, "epoch": 6.797029702970297, "percentage": 33.99, "elapsed_time": "2:25:44", "remaining_time": "4:43:05", "throughput": 1491.15, "total_tokens": 13038912} {"current_steps": 61790, "total_steps": 181800, "loss": 0.0426, "lr": 4.1736468077918624e-05, "epoch": 6.7975797579757975, "percentage": 33.99, "elapsed_time": "2:25:44", "remaining_time": "4:43:04", "throughput": 1491.16, "total_tokens": 13040000} {"current_steps": 61795, "total_steps": 181800, "loss": 0.0493, "lr": 4.1734685112267615e-05, "epoch": 6.798129812981298, "percentage": 33.99, "elapsed_time": "2:25:45", "remaining_time": "4:43:03", "throughput": 1491.17, "total_tokens": 13041120} {"current_steps": 61800, "total_steps": 181800, "loss": 0.0385, "lr": 4.173290199238105e-05, "epoch": 6.798679867986799, "percentage": 33.99, "elapsed_time": "2:25:46", "remaining_time": "4:43:03", "throughput": 1491.16, "total_tokens": 13042112} {"current_steps": 61805, "total_steps": 181800, "loss": 0.0233, "lr": 4.173111871827534e-05, "epoch": 6.799229922992299, "percentage": 34.0, "elapsed_time": "2:25:46", "remaining_time": "4:43:02", "throughput": 1491.17, "total_tokens": 13043168} {"current_steps": 61810, "total_steps": 181800, "loss": 0.0101, "lr": 4.1729335289966947e-05, "epoch": 6.7997799779978, "percentage": 34.0, "elapsed_time": "2:25:47", "remaining_time": "4:43:01", "throughput": 1491.16, "total_tokens": 13044192} {"current_steps": 61815, "total_steps": 181800, "loss": 0.0758, "lr": 4.17275517074723e-05, "epoch": 6.8003300330033, "percentage": 34.0, "elapsed_time": "2:25:48", "remaining_time": "4:43:00", "throughput": 1491.16, "total_tokens": 13045184} {"current_steps": 61820, "total_steps": 181800, "loss": 0.0228, "lr": 4.1725767970807835e-05, "epoch": 6.8008800880088005, "percentage": 34.0, "elapsed_time": "2:25:49", "remaining_time": "4:43:00", "throughput": 1491.16, "total_tokens": 13046208} {"current_steps": 61825, "total_steps": 181800, "loss": 0.0659, "lr": 4.172398407998999e-05, "epoch": 6.801430143014302, "percentage": 34.01, "elapsed_time": "2:25:49", "remaining_time": "4:42:59", "throughput": 1491.16, "total_tokens": 13047264} {"current_steps": 61830, "total_steps": 181800, "loss": 0.0993, "lr": 4.1722200035035206e-05, "epoch": 6.801980198019802, "percentage": 34.01, "elapsed_time": "2:25:50", "remaining_time": "4:42:58", "throughput": 1491.17, "total_tokens": 13048320} {"current_steps": 61835, "total_steps": 181800, "loss": 0.0115, "lr": 4.172041583595994e-05, "epoch": 6.802530253025303, "percentage": 34.01, "elapsed_time": "2:25:51", "remaining_time": "4:42:57", "throughput": 1491.17, "total_tokens": 13049376} {"current_steps": 61840, "total_steps": 181800, "loss": 0.0112, "lr": 4.171863148278061e-05, "epoch": 6.803080308030803, "percentage": 34.02, "elapsed_time": "2:25:51", "remaining_time": "4:42:57", "throughput": 1491.17, "total_tokens": 13050432} {"current_steps": 61845, "total_steps": 181800, "loss": 0.0394, "lr": 4.171684697551368e-05, "epoch": 6.803630363036303, "percentage": 34.02, "elapsed_time": "2:25:52", "remaining_time": "4:42:56", "throughput": 1491.18, "total_tokens": 13051520} {"current_steps": 61850, "total_steps": 181800, "loss": 0.0325, "lr": 4.17150623141756e-05, "epoch": 6.804180418041804, "percentage": 34.02, "elapsed_time": "2:25:53", "remaining_time": "4:42:55", "throughput": 1491.19, "total_tokens": 13052608} {"current_steps": 61855, "total_steps": 181800, "loss": 0.013, "lr": 4.171327749878281e-05, "epoch": 6.804730473047305, "percentage": 34.02, "elapsed_time": "2:25:53", "remaining_time": "4:42:54", "throughput": 1491.19, "total_tokens": 13053696} {"current_steps": 61860, "total_steps": 181800, "loss": 0.0909, "lr": 4.1711492529351757e-05, "epoch": 6.805280528052805, "percentage": 34.03, "elapsed_time": "2:25:54", "remaining_time": "4:42:54", "throughput": 1491.2, "total_tokens": 13054784} {"current_steps": 61865, "total_steps": 181800, "loss": 0.0326, "lr": 4.170970740589889e-05, "epoch": 6.805830583058306, "percentage": 34.03, "elapsed_time": "2:25:55", "remaining_time": "4:42:53", "throughput": 1491.19, "total_tokens": 13055776} {"current_steps": 61870, "total_steps": 181800, "loss": 0.0447, "lr": 4.170792212844068e-05, "epoch": 6.806380638063806, "percentage": 34.03, "elapsed_time": "2:25:55", "remaining_time": "4:42:52", "throughput": 1491.2, "total_tokens": 13056896} {"current_steps": 61875, "total_steps": 181800, "loss": 0.0531, "lr": 4.1706136696993565e-05, "epoch": 6.806930693069307, "percentage": 34.03, "elapsed_time": "2:25:56", "remaining_time": "4:42:51", "throughput": 1491.2, "total_tokens": 13057856} {"current_steps": 61880, "total_steps": 181800, "loss": 0.0215, "lr": 4.1704351111574005e-05, "epoch": 6.807480748074807, "percentage": 34.04, "elapsed_time": "2:25:57", "remaining_time": "4:42:51", "throughput": 1491.19, "total_tokens": 13058848} {"current_steps": 61885, "total_steps": 181800, "loss": 0.0102, "lr": 4.1702565372198454e-05, "epoch": 6.8080308030803085, "percentage": 34.04, "elapsed_time": "2:25:58", "remaining_time": "4:42:50", "throughput": 1491.19, "total_tokens": 13059872} {"current_steps": 61890, "total_steps": 181800, "loss": 0.0153, "lr": 4.1700779478883366e-05, "epoch": 6.808580858085809, "percentage": 34.04, "elapsed_time": "2:25:58", "remaining_time": "4:42:49", "throughput": 1491.2, "total_tokens": 13060928} {"current_steps": 61895, "total_steps": 181800, "loss": 0.0232, "lr": 4.169899343164522e-05, "epoch": 6.809130913091309, "percentage": 34.05, "elapsed_time": "2:25:59", "remaining_time": "4:42:48", "throughput": 1491.2, "total_tokens": 13061952} {"current_steps": 61900, "total_steps": 181800, "loss": 0.2393, "lr": 4.169720723050046e-05, "epoch": 6.80968096809681, "percentage": 34.05, "elapsed_time": "2:26:00", "remaining_time": "4:42:48", "throughput": 1491.2, "total_tokens": 13063040} {"current_steps": 61905, "total_steps": 181800, "loss": 0.0556, "lr": 4.1695420875465555e-05, "epoch": 6.81023102310231, "percentage": 34.05, "elapsed_time": "2:26:00", "remaining_time": "4:42:47", "throughput": 1491.21, "total_tokens": 13064128} {"current_steps": 61910, "total_steps": 181800, "loss": 0.0826, "lr": 4.169363436655696e-05, "epoch": 6.81078107810781, "percentage": 34.05, "elapsed_time": "2:26:01", "remaining_time": "4:42:46", "throughput": 1491.21, "total_tokens": 13065152} {"current_steps": 61915, "total_steps": 181800, "loss": 0.0384, "lr": 4.169184770379115e-05, "epoch": 6.8113311331133115, "percentage": 34.06, "elapsed_time": "2:26:02", "remaining_time": "4:42:46", "throughput": 1491.21, "total_tokens": 13066176} {"current_steps": 61920, "total_steps": 181800, "loss": 0.2032, "lr": 4.169006088718459e-05, "epoch": 6.811881188118812, "percentage": 34.06, "elapsed_time": "2:26:02", "remaining_time": "4:42:45", "throughput": 1491.21, "total_tokens": 13067264} {"current_steps": 61925, "total_steps": 181800, "loss": 0.0238, "lr": 4.168827391675375e-05, "epoch": 6.812431243124313, "percentage": 34.06, "elapsed_time": "2:26:03", "remaining_time": "4:42:44", "throughput": 1491.21, "total_tokens": 13068256} {"current_steps": 61930, "total_steps": 181800, "loss": 0.0404, "lr": 4.16864867925151e-05, "epoch": 6.812981298129813, "percentage": 34.06, "elapsed_time": "2:26:04", "remaining_time": "4:42:43", "throughput": 1491.22, "total_tokens": 13069344} {"current_steps": 61935, "total_steps": 181800, "loss": 0.043, "lr": 4.16846995144851e-05, "epoch": 6.813531353135313, "percentage": 34.07, "elapsed_time": "2:26:04", "remaining_time": "4:42:43", "throughput": 1491.22, "total_tokens": 13070400} {"current_steps": 61940, "total_steps": 181800, "loss": 0.0694, "lr": 4.1682912082680234e-05, "epoch": 6.814081408140814, "percentage": 34.07, "elapsed_time": "2:26:05", "remaining_time": "4:42:42", "throughput": 1491.22, "total_tokens": 13071456} {"current_steps": 61945, "total_steps": 181800, "loss": 0.0257, "lr": 4.168112449711698e-05, "epoch": 6.8146314631463145, "percentage": 34.07, "elapsed_time": "2:26:06", "remaining_time": "4:42:41", "throughput": 1491.22, "total_tokens": 13072512} {"current_steps": 61950, "total_steps": 181800, "loss": 0.0642, "lr": 4.167933675781179e-05, "epoch": 6.815181518151816, "percentage": 34.08, "elapsed_time": "2:26:06", "remaining_time": "4:42:40", "throughput": 1491.22, "total_tokens": 13073536} {"current_steps": 61955, "total_steps": 181800, "loss": 0.0186, "lr": 4.167754886478117e-05, "epoch": 6.815731573157316, "percentage": 34.08, "elapsed_time": "2:26:07", "remaining_time": "4:42:40", "throughput": 1491.23, "total_tokens": 13074624} {"current_steps": 61960, "total_steps": 181800, "loss": 0.0224, "lr": 4.167576081804158e-05, "epoch": 6.816281628162816, "percentage": 34.08, "elapsed_time": "2:26:08", "remaining_time": "4:42:39", "throughput": 1491.23, "total_tokens": 13075680} {"current_steps": 61965, "total_steps": 181800, "loss": 0.0191, "lr": 4.167397261760951e-05, "epoch": 6.816831683168317, "percentage": 34.08, "elapsed_time": "2:26:09", "remaining_time": "4:42:38", "throughput": 1491.23, "total_tokens": 13076704} {"current_steps": 61970, "total_steps": 181800, "loss": 0.0357, "lr": 4.1672184263501426e-05, "epoch": 6.817381738173817, "percentage": 34.09, "elapsed_time": "2:26:09", "remaining_time": "4:42:37", "throughput": 1491.24, "total_tokens": 13077760} {"current_steps": 61975, "total_steps": 181800, "loss": 0.0056, "lr": 4.167039575573383e-05, "epoch": 6.8179317931793175, "percentage": 34.09, "elapsed_time": "2:26:10", "remaining_time": "4:42:37", "throughput": 1491.24, "total_tokens": 13078848} {"current_steps": 61980, "total_steps": 181800, "loss": 0.0144, "lr": 4.1668607094323185e-05, "epoch": 6.818481848184819, "percentage": 34.09, "elapsed_time": "2:26:11", "remaining_time": "4:42:36", "throughput": 1491.25, "total_tokens": 13079968} {"current_steps": 61985, "total_steps": 181800, "loss": 0.086, "lr": 4.166681827928599e-05, "epoch": 6.819031903190319, "percentage": 34.1, "elapsed_time": "2:26:11", "remaining_time": "4:42:35", "throughput": 1491.25, "total_tokens": 13080960} {"current_steps": 61990, "total_steps": 181800, "loss": 0.0099, "lr": 4.166502931063873e-05, "epoch": 6.81958195819582, "percentage": 34.1, "elapsed_time": "2:26:12", "remaining_time": "4:42:34", "throughput": 1491.25, "total_tokens": 13082016} {"current_steps": 61995, "total_steps": 181800, "loss": 0.1253, "lr": 4.166324018839789e-05, "epoch": 6.82013201320132, "percentage": 34.1, "elapsed_time": "2:26:13", "remaining_time": "4:42:34", "throughput": 1491.26, "total_tokens": 13083136} {"current_steps": 62000, "total_steps": 181800, "loss": 0.0147, "lr": 4.1661450912579966e-05, "epoch": 6.82068206820682, "percentage": 34.1, "elapsed_time": "2:26:13", "remaining_time": "4:42:33", "throughput": 1491.27, "total_tokens": 13084224} {"current_steps": 62005, "total_steps": 181800, "loss": 0.0736, "lr": 4.165966148320144e-05, "epoch": 6.821232123212321, "percentage": 34.11, "elapsed_time": "2:26:14", "remaining_time": "4:42:32", "throughput": 1491.27, "total_tokens": 13085280} {"current_steps": 62010, "total_steps": 181800, "loss": 0.0341, "lr": 4.165787190027881e-05, "epoch": 6.821782178217822, "percentage": 34.11, "elapsed_time": "2:26:15", "remaining_time": "4:42:31", "throughput": 1491.28, "total_tokens": 13086336} {"current_steps": 62015, "total_steps": 181800, "loss": 0.0255, "lr": 4.1656082163828566e-05, "epoch": 6.822332233223323, "percentage": 34.11, "elapsed_time": "2:26:15", "remaining_time": "4:42:31", "throughput": 1491.28, "total_tokens": 13087360} {"current_steps": 62020, "total_steps": 181800, "loss": 0.0263, "lr": 4.16542922738672e-05, "epoch": 6.822882288228823, "percentage": 34.11, "elapsed_time": "2:26:16", "remaining_time": "4:42:30", "throughput": 1491.28, "total_tokens": 13088448} {"current_steps": 62025, "total_steps": 181800, "loss": 0.032, "lr": 4.165250223041122e-05, "epoch": 6.823432343234323, "percentage": 34.12, "elapsed_time": "2:26:17", "remaining_time": "4:42:29", "throughput": 1491.28, "total_tokens": 13089440} {"current_steps": 62030, "total_steps": 181800, "loss": 0.0167, "lr": 4.165071203347711e-05, "epoch": 6.823982398239824, "percentage": 34.12, "elapsed_time": "2:26:18", "remaining_time": "4:42:28", "throughput": 1491.28, "total_tokens": 13090464} {"current_steps": 62035, "total_steps": 181800, "loss": 0.0117, "lr": 4.164892168308139e-05, "epoch": 6.824532453245324, "percentage": 34.12, "elapsed_time": "2:26:18", "remaining_time": "4:42:28", "throughput": 1491.28, "total_tokens": 13091552} {"current_steps": 62040, "total_steps": 181800, "loss": 0.0075, "lr": 4.164713117924054e-05, "epoch": 6.825082508250825, "percentage": 34.13, "elapsed_time": "2:26:19", "remaining_time": "4:42:27", "throughput": 1491.29, "total_tokens": 13092608} {"current_steps": 62045, "total_steps": 181800, "loss": 0.0134, "lr": 4.164534052197108e-05, "epoch": 6.825632563256326, "percentage": 34.13, "elapsed_time": "2:26:20", "remaining_time": "4:42:26", "throughput": 1491.29, "total_tokens": 13093696} {"current_steps": 62050, "total_steps": 181800, "loss": 0.0321, "lr": 4.164354971128949e-05, "epoch": 6.826182618261826, "percentage": 34.13, "elapsed_time": "2:26:20", "remaining_time": "4:42:25", "throughput": 1491.29, "total_tokens": 13094720} {"current_steps": 62055, "total_steps": 181800, "loss": 0.142, "lr": 4.1641758747212286e-05, "epoch": 6.826732673267327, "percentage": 34.13, "elapsed_time": "2:26:21", "remaining_time": "4:42:25", "throughput": 1491.3, "total_tokens": 13095776} {"current_steps": 62060, "total_steps": 181800, "loss": 0.0136, "lr": 4.1639967629756e-05, "epoch": 6.827282728272827, "percentage": 34.14, "elapsed_time": "2:26:22", "remaining_time": "4:42:24", "throughput": 1491.31, "total_tokens": 13096896} {"current_steps": 62065, "total_steps": 181800, "loss": 0.042, "lr": 4.1638176358937094e-05, "epoch": 6.827832783278328, "percentage": 34.14, "elapsed_time": "2:26:22", "remaining_time": "4:42:23", "throughput": 1491.32, "total_tokens": 13098048} {"current_steps": 62070, "total_steps": 181800, "loss": 0.0517, "lr": 4.1636384934772106e-05, "epoch": 6.8283828382838285, "percentage": 34.14, "elapsed_time": "2:26:23", "remaining_time": "4:42:23", "throughput": 1491.32, "total_tokens": 13099072} {"current_steps": 62075, "total_steps": 181800, "loss": 0.0124, "lr": 4.163459335727754e-05, "epoch": 6.828932893289329, "percentage": 34.14, "elapsed_time": "2:26:24", "remaining_time": "4:42:22", "throughput": 1491.32, "total_tokens": 13100128} {"current_steps": 62080, "total_steps": 181800, "loss": 0.1179, "lr": 4.1632801626469906e-05, "epoch": 6.82948294829483, "percentage": 34.15, "elapsed_time": "2:26:24", "remaining_time": "4:42:21", "throughput": 1491.33, "total_tokens": 13101216} {"current_steps": 62085, "total_steps": 181800, "loss": 0.0093, "lr": 4.1631009742365736e-05, "epoch": 6.83003300330033, "percentage": 34.15, "elapsed_time": "2:26:25", "remaining_time": "4:42:20", "throughput": 1491.34, "total_tokens": 13102336} {"current_steps": 62090, "total_steps": 181800, "loss": 0.1197, "lr": 4.1629217704981515e-05, "epoch": 6.83058305830583, "percentage": 34.15, "elapsed_time": "2:26:26", "remaining_time": "4:42:20", "throughput": 1491.34, "total_tokens": 13103360} {"current_steps": 62095, "total_steps": 181800, "loss": 0.0655, "lr": 4.162742551433378e-05, "epoch": 6.831133113311331, "percentage": 34.16, "elapsed_time": "2:26:26", "remaining_time": "4:42:19", "throughput": 1491.34, "total_tokens": 13104384} {"current_steps": 62100, "total_steps": 181800, "loss": 0.0892, "lr": 4.1625633170439035e-05, "epoch": 6.8316831683168315, "percentage": 34.16, "elapsed_time": "2:26:27", "remaining_time": "4:42:18", "throughput": 1491.34, "total_tokens": 13105440} {"current_steps": 62105, "total_steps": 181800, "loss": 0.0034, "lr": 4.162384067331382e-05, "epoch": 6.832233223322332, "percentage": 34.16, "elapsed_time": "2:26:28", "remaining_time": "4:42:17", "throughput": 1491.34, "total_tokens": 13106464} {"current_steps": 62110, "total_steps": 181800, "loss": 0.0366, "lr": 4.162204802297464e-05, "epoch": 6.832783278327833, "percentage": 34.16, "elapsed_time": "2:26:29", "remaining_time": "4:42:17", "throughput": 1491.35, "total_tokens": 13107584} {"current_steps": 62115, "total_steps": 181800, "loss": 0.0872, "lr": 4.162025521943801e-05, "epoch": 6.833333333333333, "percentage": 34.17, "elapsed_time": "2:26:29", "remaining_time": "4:42:16", "throughput": 1491.36, "total_tokens": 13108672} {"current_steps": 62120, "total_steps": 181800, "loss": 0.0416, "lr": 4.161846226272047e-05, "epoch": 6.833883388338834, "percentage": 34.17, "elapsed_time": "2:26:30", "remaining_time": "4:42:15", "throughput": 1491.36, "total_tokens": 13109728} {"current_steps": 62125, "total_steps": 181800, "loss": 0.0629, "lr": 4.1616669152838536e-05, "epoch": 6.834433443344334, "percentage": 34.17, "elapsed_time": "2:26:31", "remaining_time": "4:42:14", "throughput": 1491.36, "total_tokens": 13110784} {"current_steps": 62130, "total_steps": 181800, "loss": 0.0308, "lr": 4.161487588980873e-05, "epoch": 6.834983498349835, "percentage": 34.17, "elapsed_time": "2:26:31", "remaining_time": "4:42:14", "throughput": 1491.37, "total_tokens": 13111840} {"current_steps": 62135, "total_steps": 181800, "loss": 0.1412, "lr": 4.16130824736476e-05, "epoch": 6.835533553355336, "percentage": 34.18, "elapsed_time": "2:26:32", "remaining_time": "4:42:13", "throughput": 1491.36, "total_tokens": 13112832} {"current_steps": 62140, "total_steps": 181800, "loss": 0.0897, "lr": 4.161128890437165e-05, "epoch": 6.836083608360836, "percentage": 34.18, "elapsed_time": "2:26:33", "remaining_time": "4:42:12", "throughput": 1491.36, "total_tokens": 13113888} {"current_steps": 62145, "total_steps": 181800, "loss": 0.0648, "lr": 4.1609495181997424e-05, "epoch": 6.836633663366337, "percentage": 34.18, "elapsed_time": "2:26:33", "remaining_time": "4:42:11", "throughput": 1491.37, "total_tokens": 13114976} {"current_steps": 62150, "total_steps": 181800, "loss": 0.0294, "lr": 4.160770130654145e-05, "epoch": 6.837183718371837, "percentage": 34.19, "elapsed_time": "2:26:34", "remaining_time": "4:42:11", "throughput": 1491.37, "total_tokens": 13116000} {"current_steps": 62155, "total_steps": 181800, "loss": 0.0072, "lr": 4.160590727802026e-05, "epoch": 6.837733773377337, "percentage": 34.19, "elapsed_time": "2:26:35", "remaining_time": "4:42:10", "throughput": 1491.38, "total_tokens": 13117120} {"current_steps": 62160, "total_steps": 181800, "loss": 0.0365, "lr": 4.1604113096450394e-05, "epoch": 6.838283828382838, "percentage": 34.19, "elapsed_time": "2:26:35", "remaining_time": "4:42:09", "throughput": 1491.39, "total_tokens": 13118208} {"current_steps": 62165, "total_steps": 181800, "loss": 0.0452, "lr": 4.160231876184838e-05, "epoch": 6.838833883388339, "percentage": 34.19, "elapsed_time": "2:26:36", "remaining_time": "4:42:08", "throughput": 1491.39, "total_tokens": 13119264} {"current_steps": 62170, "total_steps": 181800, "loss": 0.0493, "lr": 4.160052427423077e-05, "epoch": 6.83938393839384, "percentage": 34.2, "elapsed_time": "2:26:37", "remaining_time": "4:42:08", "throughput": 1491.39, "total_tokens": 13120288} {"current_steps": 62175, "total_steps": 181800, "loss": 0.0526, "lr": 4.159872963361408e-05, "epoch": 6.83993399339934, "percentage": 34.2, "elapsed_time": "2:26:38", "remaining_time": "4:42:07", "throughput": 1491.39, "total_tokens": 13121344} {"current_steps": 62180, "total_steps": 181800, "loss": 0.1416, "lr": 4.159693484001488e-05, "epoch": 6.84048404840484, "percentage": 34.2, "elapsed_time": "2:26:38", "remaining_time": "4:42:06", "throughput": 1491.39, "total_tokens": 13122336} {"current_steps": 62185, "total_steps": 181800, "loss": 0.0888, "lr": 4.1595139893449686e-05, "epoch": 6.841034103410341, "percentage": 34.21, "elapsed_time": "2:26:39", "remaining_time": "4:42:06", "throughput": 1491.4, "total_tokens": 13123424} {"current_steps": 62190, "total_steps": 181800, "loss": 0.0191, "lr": 4.159334479393505e-05, "epoch": 6.841584158415841, "percentage": 34.21, "elapsed_time": "2:26:40", "remaining_time": "4:42:05", "throughput": 1491.39, "total_tokens": 13124448} {"current_steps": 62195, "total_steps": 181800, "loss": 0.0117, "lr": 4.159154954148752e-05, "epoch": 6.8421342134213425, "percentage": 34.21, "elapsed_time": "2:26:40", "remaining_time": "4:42:04", "throughput": 1491.4, "total_tokens": 13125536} {"current_steps": 62200, "total_steps": 181800, "loss": 0.1073, "lr": 4.158975413612363e-05, "epoch": 6.842684268426843, "percentage": 34.21, "elapsed_time": "2:26:41", "remaining_time": "4:42:03", "throughput": 1491.41, "total_tokens": 13126624} {"current_steps": 62205, "total_steps": 181800, "loss": 0.0448, "lr": 4.158795857785995e-05, "epoch": 6.843234323432343, "percentage": 34.22, "elapsed_time": "2:26:42", "remaining_time": "4:42:03", "throughput": 1491.41, "total_tokens": 13127648} {"current_steps": 62210, "total_steps": 181800, "loss": 0.0485, "lr": 4.158616286671301e-05, "epoch": 6.843784378437844, "percentage": 34.22, "elapsed_time": "2:26:42", "remaining_time": "4:42:02", "throughput": 1491.41, "total_tokens": 13128736} {"current_steps": 62215, "total_steps": 181800, "loss": 0.0296, "lr": 4.158436700269936e-05, "epoch": 6.844334433443344, "percentage": 34.22, "elapsed_time": "2:26:43", "remaining_time": "4:42:01", "throughput": 1491.41, "total_tokens": 13129696} {"current_steps": 62220, "total_steps": 181800, "loss": 0.0409, "lr": 4.158257098583557e-05, "epoch": 6.8448844884488445, "percentage": 34.22, "elapsed_time": "2:26:44", "remaining_time": "4:42:00", "throughput": 1491.41, "total_tokens": 13130720} {"current_steps": 62225, "total_steps": 181800, "loss": 0.1551, "lr": 4.158077481613817e-05, "epoch": 6.8454345434543455, "percentage": 34.23, "elapsed_time": "2:26:44", "remaining_time": "4:42:00", "throughput": 1491.41, "total_tokens": 13131776} {"current_steps": 62230, "total_steps": 181800, "loss": 0.0768, "lr": 4.157897849362373e-05, "epoch": 6.845984598459846, "percentage": 34.23, "elapsed_time": "2:26:45", "remaining_time": "4:41:59", "throughput": 1491.42, "total_tokens": 13132896} {"current_steps": 62235, "total_steps": 181800, "loss": 0.0146, "lr": 4.15771820183088e-05, "epoch": 6.846534653465347, "percentage": 34.23, "elapsed_time": "2:26:46", "remaining_time": "4:41:58", "throughput": 1491.43, "total_tokens": 13134048} {"current_steps": 62240, "total_steps": 181800, "loss": 0.122, "lr": 4.157538539020994e-05, "epoch": 6.847084708470847, "percentage": 34.24, "elapsed_time": "2:26:47", "remaining_time": "4:41:57", "throughput": 1491.44, "total_tokens": 13135104} {"current_steps": 62245, "total_steps": 181800, "loss": 0.0103, "lr": 4.15735886093437e-05, "epoch": 6.847634763476347, "percentage": 34.24, "elapsed_time": "2:26:47", "remaining_time": "4:41:57", "throughput": 1491.44, "total_tokens": 13136128} {"current_steps": 62250, "total_steps": 181800, "loss": 0.0445, "lr": 4.157179167572665e-05, "epoch": 6.848184818481848, "percentage": 34.24, "elapsed_time": "2:26:48", "remaining_time": "4:41:56", "throughput": 1491.44, "total_tokens": 13137184} {"current_steps": 62255, "total_steps": 181800, "loss": 0.1447, "lr": 4.156999458937535e-05, "epoch": 6.8487348734873486, "percentage": 34.24, "elapsed_time": "2:26:49", "remaining_time": "4:41:55", "throughput": 1491.44, "total_tokens": 13138240} {"current_steps": 62260, "total_steps": 181800, "loss": 0.13, "lr": 4.156819735030636e-05, "epoch": 6.84928492849285, "percentage": 34.25, "elapsed_time": "2:26:49", "remaining_time": "4:41:55", "throughput": 1491.42, "total_tokens": 13139328} {"current_steps": 62265, "total_steps": 181800, "loss": 0.0306, "lr": 4.156639995853624e-05, "epoch": 6.84983498349835, "percentage": 34.25, "elapsed_time": "2:26:50", "remaining_time": "4:41:54", "throughput": 1491.41, "total_tokens": 13140320} {"current_steps": 62270, "total_steps": 181800, "loss": 0.0244, "lr": 4.156460241408157e-05, "epoch": 6.85038503850385, "percentage": 34.25, "elapsed_time": "2:26:51", "remaining_time": "4:41:53", "throughput": 1491.41, "total_tokens": 13141344} {"current_steps": 62275, "total_steps": 181800, "loss": 0.0815, "lr": 4.15628047169589e-05, "epoch": 6.850935093509351, "percentage": 34.25, "elapsed_time": "2:26:52", "remaining_time": "4:41:53", "throughput": 1491.42, "total_tokens": 13142432} {"current_steps": 62280, "total_steps": 181800, "loss": 0.0471, "lr": 4.156100686718481e-05, "epoch": 6.851485148514851, "percentage": 34.26, "elapsed_time": "2:26:52", "remaining_time": "4:41:52", "throughput": 1491.42, "total_tokens": 13143488} {"current_steps": 62285, "total_steps": 181800, "loss": 0.0057, "lr": 4.155920886477587e-05, "epoch": 6.852035203520352, "percentage": 34.26, "elapsed_time": "2:26:53", "remaining_time": "4:41:51", "throughput": 1491.42, "total_tokens": 13144512} {"current_steps": 62290, "total_steps": 181800, "loss": 0.016, "lr": 4.155741070974864e-05, "epoch": 6.852585258525853, "percentage": 34.26, "elapsed_time": "2:26:54", "remaining_time": "4:41:50", "throughput": 1491.42, "total_tokens": 13145568} {"current_steps": 62295, "total_steps": 181800, "loss": 0.0093, "lr": 4.15556124021197e-05, "epoch": 6.853135313531353, "percentage": 34.27, "elapsed_time": "2:26:54", "remaining_time": "4:41:50", "throughput": 1491.42, "total_tokens": 13146560} {"current_steps": 62300, "total_steps": 181800, "loss": 0.0107, "lr": 4.155381394190564e-05, "epoch": 6.853685368536854, "percentage": 34.27, "elapsed_time": "2:26:55", "remaining_time": "4:41:49", "throughput": 1491.43, "total_tokens": 13147648} {"current_steps": 62305, "total_steps": 181800, "loss": 0.0222, "lr": 4.1552015329123006e-05, "epoch": 6.854235423542354, "percentage": 34.27, "elapsed_time": "2:26:56", "remaining_time": "4:41:48", "throughput": 1491.43, "total_tokens": 13148672} {"current_steps": 62310, "total_steps": 181800, "loss": 0.0788, "lr": 4.1550216563788394e-05, "epoch": 6.854785478547855, "percentage": 34.27, "elapsed_time": "2:26:56", "remaining_time": "4:41:47", "throughput": 1491.42, "total_tokens": 13149664} {"current_steps": 62315, "total_steps": 181800, "loss": 0.1086, "lr": 4.154841764591837e-05, "epoch": 6.8553355335533555, "percentage": 34.28, "elapsed_time": "2:26:57", "remaining_time": "4:41:47", "throughput": 1491.43, "total_tokens": 13150752} {"current_steps": 62320, "total_steps": 181800, "loss": 0.028, "lr": 4.154661857552953e-05, "epoch": 6.855885588558856, "percentage": 34.28, "elapsed_time": "2:26:58", "remaining_time": "4:41:46", "throughput": 1491.43, "total_tokens": 13151808} {"current_steps": 62325, "total_steps": 181800, "loss": 0.0146, "lr": 4.1544819352638445e-05, "epoch": 6.856435643564357, "percentage": 34.28, "elapsed_time": "2:26:58", "remaining_time": "4:41:45", "throughput": 1491.44, "total_tokens": 13152864} {"current_steps": 62330, "total_steps": 181800, "loss": 0.1659, "lr": 4.15430199772617e-05, "epoch": 6.856985698569857, "percentage": 34.28, "elapsed_time": "2:26:59", "remaining_time": "4:41:44", "throughput": 1491.44, "total_tokens": 13153920} {"current_steps": 62335, "total_steps": 181800, "loss": 0.0446, "lr": 4.154122044941587e-05, "epoch": 6.857535753575357, "percentage": 34.29, "elapsed_time": "2:27:00", "remaining_time": "4:41:44", "throughput": 1491.44, "total_tokens": 13154976} {"current_steps": 62340, "total_steps": 181800, "loss": 0.0584, "lr": 4.1539420769117557e-05, "epoch": 6.858085808580858, "percentage": 34.29, "elapsed_time": "2:27:00", "remaining_time": "4:41:43", "throughput": 1491.45, "total_tokens": 13156064} {"current_steps": 62345, "total_steps": 181800, "loss": 0.0805, "lr": 4.153762093638334e-05, "epoch": 6.8586358635863585, "percentage": 34.29, "elapsed_time": "2:27:01", "remaining_time": "4:41:42", "throughput": 1491.45, "total_tokens": 13157088} {"current_steps": 62350, "total_steps": 181800, "loss": 0.0464, "lr": 4.1535820951229795e-05, "epoch": 6.8591859185918596, "percentage": 34.3, "elapsed_time": "2:27:02", "remaining_time": "4:41:41", "throughput": 1491.45, "total_tokens": 13158112} {"current_steps": 62355, "total_steps": 181800, "loss": 0.0753, "lr": 4.153402081367353e-05, "epoch": 6.85973597359736, "percentage": 34.3, "elapsed_time": "2:27:03", "remaining_time": "4:41:41", "throughput": 1491.45, "total_tokens": 13159168} {"current_steps": 62360, "total_steps": 181800, "loss": 0.0191, "lr": 4.153222052373113e-05, "epoch": 6.86028602860286, "percentage": 34.3, "elapsed_time": "2:27:03", "remaining_time": "4:41:40", "throughput": 1491.46, "total_tokens": 13160256} {"current_steps": 62365, "total_steps": 181800, "loss": 0.0472, "lr": 4.1530420081419185e-05, "epoch": 6.860836083608361, "percentage": 34.3, "elapsed_time": "2:27:04", "remaining_time": "4:41:39", "throughput": 1491.47, "total_tokens": 13161344} {"current_steps": 62370, "total_steps": 181800, "loss": 0.0529, "lr": 4.152861948675429e-05, "epoch": 6.861386138613861, "percentage": 34.31, "elapsed_time": "2:27:05", "remaining_time": "4:41:38", "throughput": 1491.48, "total_tokens": 13162464} {"current_steps": 62375, "total_steps": 181800, "loss": 0.0408, "lr": 4.1526818739753046e-05, "epoch": 6.861936193619362, "percentage": 34.31, "elapsed_time": "2:27:05", "remaining_time": "4:41:38", "throughput": 1491.49, "total_tokens": 13163584} {"current_steps": 62380, "total_steps": 181800, "loss": 0.0192, "lr": 4.152501784043203e-05, "epoch": 6.862486248624863, "percentage": 34.31, "elapsed_time": "2:27:06", "remaining_time": "4:41:37", "throughput": 1491.49, "total_tokens": 13164608} {"current_steps": 62385, "total_steps": 181800, "loss": 0.0385, "lr": 4.1523216788807875e-05, "epoch": 6.863036303630363, "percentage": 34.32, "elapsed_time": "2:27:07", "remaining_time": "4:41:36", "throughput": 1491.48, "total_tokens": 13165600} {"current_steps": 62390, "total_steps": 181800, "loss": 0.0197, "lr": 4.152141558489714e-05, "epoch": 6.863586358635864, "percentage": 34.32, "elapsed_time": "2:27:07", "remaining_time": "4:41:35", "throughput": 1491.48, "total_tokens": 13166624} {"current_steps": 62395, "total_steps": 181800, "loss": 0.0333, "lr": 4.151961422871646e-05, "epoch": 6.864136413641364, "percentage": 34.32, "elapsed_time": "2:27:08", "remaining_time": "4:41:35", "throughput": 1491.48, "total_tokens": 13167648} {"current_steps": 62400, "total_steps": 181800, "loss": 0.0169, "lr": 4.151781272028241e-05, "epoch": 6.864686468646864, "percentage": 34.32, "elapsed_time": "2:27:09", "remaining_time": "4:41:34", "throughput": 1491.48, "total_tokens": 13168704} {"current_steps": 62405, "total_steps": 181800, "loss": 0.0698, "lr": 4.1516011059611614e-05, "epoch": 6.865236523652365, "percentage": 34.33, "elapsed_time": "2:27:09", "remaining_time": "4:41:33", "throughput": 1491.48, "total_tokens": 13169696} {"current_steps": 62410, "total_steps": 181800, "loss": 0.073, "lr": 4.151420924672067e-05, "epoch": 6.865786578657866, "percentage": 34.33, "elapsed_time": "2:27:10", "remaining_time": "4:41:32", "throughput": 1491.48, "total_tokens": 13170752} {"current_steps": 62415, "total_steps": 181800, "loss": 0.0362, "lr": 4.1512407281626175e-05, "epoch": 6.866336633663367, "percentage": 34.33, "elapsed_time": "2:27:11", "remaining_time": "4:41:32", "throughput": 1491.5, "total_tokens": 13171904} {"current_steps": 62420, "total_steps": 181800, "loss": 0.0981, "lr": 4.151060516434475e-05, "epoch": 6.866886688668867, "percentage": 34.33, "elapsed_time": "2:27:12", "remaining_time": "4:41:31", "throughput": 1491.51, "total_tokens": 13173024} {"current_steps": 62425, "total_steps": 181800, "loss": 0.0361, "lr": 4.150880289489301e-05, "epoch": 6.867436743674367, "percentage": 34.34, "elapsed_time": "2:27:12", "remaining_time": "4:41:30", "throughput": 1491.51, "total_tokens": 13174048} {"current_steps": 62430, "total_steps": 181800, "loss": 0.0027, "lr": 4.150700047328754e-05, "epoch": 6.867986798679868, "percentage": 34.34, "elapsed_time": "2:27:13", "remaining_time": "4:41:29", "throughput": 1491.51, "total_tokens": 13175104} {"current_steps": 62435, "total_steps": 181800, "loss": 0.0588, "lr": 4.1505197899544974e-05, "epoch": 6.868536853685368, "percentage": 34.34, "elapsed_time": "2:27:14", "remaining_time": "4:41:29", "throughput": 1491.53, "total_tokens": 13176256} {"current_steps": 62440, "total_steps": 181800, "loss": 0.069, "lr": 4.1503395173681917e-05, "epoch": 6.8690869086908695, "percentage": 34.35, "elapsed_time": "2:27:14", "remaining_time": "4:41:28", "throughput": 1491.53, "total_tokens": 13177312} {"current_steps": 62445, "total_steps": 181800, "loss": 0.0376, "lr": 4.150159229571499e-05, "epoch": 6.86963696369637, "percentage": 34.35, "elapsed_time": "2:27:15", "remaining_time": "4:41:27", "throughput": 1491.53, "total_tokens": 13178368} {"current_steps": 62450, "total_steps": 181800, "loss": 0.0612, "lr": 4.149978926566081e-05, "epoch": 6.87018701870187, "percentage": 34.35, "elapsed_time": "2:27:16", "remaining_time": "4:41:27", "throughput": 1491.54, "total_tokens": 13179424} {"current_steps": 62455, "total_steps": 181800, "loss": 0.0242, "lr": 4.149798608353598e-05, "epoch": 6.870737073707371, "percentage": 34.35, "elapsed_time": "2:27:16", "remaining_time": "4:41:26", "throughput": 1491.54, "total_tokens": 13180448} {"current_steps": 62460, "total_steps": 181800, "loss": 0.061, "lr": 4.149618274935713e-05, "epoch": 6.871287128712871, "percentage": 34.36, "elapsed_time": "2:27:17", "remaining_time": "4:41:25", "throughput": 1491.54, "total_tokens": 13181536} {"current_steps": 62465, "total_steps": 181800, "loss": 0.0585, "lr": 4.149437926314088e-05, "epoch": 6.871837183718371, "percentage": 34.36, "elapsed_time": "2:27:18", "remaining_time": "4:41:24", "throughput": 1491.55, "total_tokens": 13182592} {"current_steps": 62470, "total_steps": 181800, "loss": 0.0078, "lr": 4.149257562490385e-05, "epoch": 6.8723872387238725, "percentage": 34.36, "elapsed_time": "2:27:18", "remaining_time": "4:41:24", "throughput": 1491.55, "total_tokens": 13183616} {"current_steps": 62475, "total_steps": 181800, "loss": 0.0255, "lr": 4.149077183466267e-05, "epoch": 6.872937293729373, "percentage": 34.36, "elapsed_time": "2:27:19", "remaining_time": "4:41:23", "throughput": 1491.55, "total_tokens": 13184672} {"current_steps": 62480, "total_steps": 181800, "loss": 0.0025, "lr": 4.148896789243395e-05, "epoch": 6.873487348734874, "percentage": 34.37, "elapsed_time": "2:27:20", "remaining_time": "4:41:22", "throughput": 1491.55, "total_tokens": 13185728} {"current_steps": 62485, "total_steps": 181800, "loss": 0.0359, "lr": 4.148716379823433e-05, "epoch": 6.874037403740374, "percentage": 34.37, "elapsed_time": "2:27:20", "remaining_time": "4:41:21", "throughput": 1491.55, "total_tokens": 13186784} {"current_steps": 62490, "total_steps": 181800, "loss": 0.044, "lr": 4.1485359552080424e-05, "epoch": 6.874587458745875, "percentage": 34.37, "elapsed_time": "2:27:21", "remaining_time": "4:41:21", "throughput": 1491.55, "total_tokens": 13187808} {"current_steps": 62495, "total_steps": 181800, "loss": 0.0232, "lr": 4.148355515398888e-05, "epoch": 6.875137513751375, "percentage": 34.38, "elapsed_time": "2:27:22", "remaining_time": "4:41:20", "throughput": 1491.56, "total_tokens": 13188864} {"current_steps": 62500, "total_steps": 181800, "loss": 0.0118, "lr": 4.1481750603976324e-05, "epoch": 6.8756875687568755, "percentage": 34.38, "elapsed_time": "2:27:23", "remaining_time": "4:41:19", "throughput": 1491.56, "total_tokens": 13189920} {"current_steps": 62505, "total_steps": 181800, "loss": 0.0242, "lr": 4.147994590205937e-05, "epoch": 6.876237623762377, "percentage": 34.38, "elapsed_time": "2:27:23", "remaining_time": "4:41:18", "throughput": 1491.56, "total_tokens": 13190912} {"current_steps": 62510, "total_steps": 181800, "loss": 0.0233, "lr": 4.147814104825466e-05, "epoch": 6.876787678767877, "percentage": 34.38, "elapsed_time": "2:27:24", "remaining_time": "4:41:18", "throughput": 1491.56, "total_tokens": 13191936} {"current_steps": 62515, "total_steps": 181800, "loss": 0.0159, "lr": 4.147633604257884e-05, "epoch": 6.877337733773377, "percentage": 34.39, "elapsed_time": "2:27:25", "remaining_time": "4:41:17", "throughput": 1491.56, "total_tokens": 13193024} {"current_steps": 62520, "total_steps": 181800, "loss": 0.0238, "lr": 4.147453088504854e-05, "epoch": 6.877887788778878, "percentage": 34.39, "elapsed_time": "2:27:25", "remaining_time": "4:41:16", "throughput": 1491.56, "total_tokens": 13194016} {"current_steps": 62525, "total_steps": 181800, "loss": 0.0217, "lr": 4.147272557568038e-05, "epoch": 6.878437843784378, "percentage": 34.39, "elapsed_time": "2:27:26", "remaining_time": "4:41:15", "throughput": 1491.56, "total_tokens": 13195072} {"current_steps": 62530, "total_steps": 181800, "loss": 0.1093, "lr": 4.147092011449102e-05, "epoch": 6.878987898789879, "percentage": 34.39, "elapsed_time": "2:27:27", "remaining_time": "4:41:15", "throughput": 1491.56, "total_tokens": 13196096} {"current_steps": 62535, "total_steps": 181800, "loss": 0.0499, "lr": 4.1469114501497096e-05, "epoch": 6.87953795379538, "percentage": 34.4, "elapsed_time": "2:27:27", "remaining_time": "4:41:14", "throughput": 1491.56, "total_tokens": 13197120} {"current_steps": 62540, "total_steps": 181800, "loss": 0.0118, "lr": 4.1467308736715245e-05, "epoch": 6.88008800880088, "percentage": 34.4, "elapsed_time": "2:27:28", "remaining_time": "4:41:13", "throughput": 1491.56, "total_tokens": 13198176} {"current_steps": 62545, "total_steps": 181800, "loss": 0.0238, "lr": 4.1465502820162104e-05, "epoch": 6.880638063806381, "percentage": 34.4, "elapsed_time": "2:27:29", "remaining_time": "4:41:12", "throughput": 1491.57, "total_tokens": 13199232} {"current_steps": 62550, "total_steps": 181800, "loss": 0.0727, "lr": 4.146369675185433e-05, "epoch": 6.881188118811881, "percentage": 34.41, "elapsed_time": "2:27:29", "remaining_time": "4:41:12", "throughput": 1491.57, "total_tokens": 13200320} {"current_steps": 62555, "total_steps": 181800, "loss": 0.0678, "lr": 4.146189053180857e-05, "epoch": 6.881738173817382, "percentage": 34.41, "elapsed_time": "2:27:30", "remaining_time": "4:41:11", "throughput": 1491.58, "total_tokens": 13201408} {"current_steps": 62560, "total_steps": 181800, "loss": 0.0845, "lr": 4.146008416004146e-05, "epoch": 6.882288228822882, "percentage": 34.41, "elapsed_time": "2:27:31", "remaining_time": "4:41:10", "throughput": 1491.58, "total_tokens": 13202432} {"current_steps": 62565, "total_steps": 181800, "loss": 0.013, "lr": 4.145827763656964e-05, "epoch": 6.882838283828383, "percentage": 34.41, "elapsed_time": "2:27:32", "remaining_time": "4:41:09", "throughput": 1491.59, "total_tokens": 13203584} {"current_steps": 62570, "total_steps": 181800, "loss": 0.1234, "lr": 4.145647096140979e-05, "epoch": 6.883388338833884, "percentage": 34.42, "elapsed_time": "2:27:32", "remaining_time": "4:41:09", "throughput": 1491.58, "total_tokens": 13204544} {"current_steps": 62575, "total_steps": 181800, "loss": 0.0179, "lr": 4.145466413457853e-05, "epoch": 6.883938393839384, "percentage": 34.42, "elapsed_time": "2:27:33", "remaining_time": "4:41:08", "throughput": 1491.59, "total_tokens": 13205600} {"current_steps": 62580, "total_steps": 181800, "loss": 0.0803, "lr": 4.1452857156092526e-05, "epoch": 6.884488448844884, "percentage": 34.42, "elapsed_time": "2:27:34", "remaining_time": "4:41:07", "throughput": 1491.59, "total_tokens": 13206624} {"current_steps": 62585, "total_steps": 181800, "loss": 0.0188, "lr": 4.145105002596845e-05, "epoch": 6.885038503850385, "percentage": 34.43, "elapsed_time": "2:27:34", "remaining_time": "4:41:07", "throughput": 1491.59, "total_tokens": 13207680} {"current_steps": 62590, "total_steps": 181800, "loss": 0.0861, "lr": 4.1449242744222925e-05, "epoch": 6.885588558855885, "percentage": 34.43, "elapsed_time": "2:27:35", "remaining_time": "4:41:06", "throughput": 1491.6, "total_tokens": 13208768} {"current_steps": 62595, "total_steps": 181800, "loss": 0.0126, "lr": 4.1447435310872626e-05, "epoch": 6.8861386138613865, "percentage": 34.43, "elapsed_time": "2:27:36", "remaining_time": "4:41:05", "throughput": 1491.6, "total_tokens": 13209824} {"current_steps": 62600, "total_steps": 181800, "loss": 0.0046, "lr": 4.144562772593421e-05, "epoch": 6.886688668866887, "percentage": 34.43, "elapsed_time": "2:27:36", "remaining_time": "4:41:04", "throughput": 1491.61, "total_tokens": 13210944} {"current_steps": 62605, "total_steps": 181800, "loss": 0.0583, "lr": 4.1443819989424325e-05, "epoch": 6.887238723872387, "percentage": 34.44, "elapsed_time": "2:27:37", "remaining_time": "4:41:04", "throughput": 1491.61, "total_tokens": 13212000} {"current_steps": 62610, "total_steps": 181800, "loss": 0.016, "lr": 4.1442012101359656e-05, "epoch": 6.887788778877888, "percentage": 34.44, "elapsed_time": "2:27:38", "remaining_time": "4:41:03", "throughput": 1491.62, "total_tokens": 13213088} {"current_steps": 62615, "total_steps": 181800, "loss": 0.0177, "lr": 4.144020406175684e-05, "epoch": 6.888338833883388, "percentage": 34.44, "elapsed_time": "2:27:38", "remaining_time": "4:41:02", "throughput": 1491.62, "total_tokens": 13214144} {"current_steps": 62620, "total_steps": 181800, "loss": 0.0338, "lr": 4.1438395870632565e-05, "epoch": 6.888888888888889, "percentage": 34.44, "elapsed_time": "2:27:39", "remaining_time": "4:41:01", "throughput": 1491.62, "total_tokens": 13215136} {"current_steps": 62625, "total_steps": 181800, "loss": 0.0389, "lr": 4.143658752800347e-05, "epoch": 6.8894389438943895, "percentage": 34.45, "elapsed_time": "2:27:40", "remaining_time": "4:41:01", "throughput": 1491.62, "total_tokens": 13216192} {"current_steps": 62630, "total_steps": 181800, "loss": 0.0594, "lr": 4.143477903388624e-05, "epoch": 6.88998899889989, "percentage": 34.45, "elapsed_time": "2:27:40", "remaining_time": "4:41:00", "throughput": 1491.64, "total_tokens": 13217344} {"current_steps": 62635, "total_steps": 181800, "loss": 0.0533, "lr": 4.143297038829754e-05, "epoch": 6.890539053905391, "percentage": 34.45, "elapsed_time": "2:27:41", "remaining_time": "4:40:59", "throughput": 1491.63, "total_tokens": 13218336} {"current_steps": 62640, "total_steps": 181800, "loss": 0.0251, "lr": 4.143116159125403e-05, "epoch": 6.891089108910891, "percentage": 34.46, "elapsed_time": "2:27:42", "remaining_time": "4:40:58", "throughput": 1491.64, "total_tokens": 13219424} {"current_steps": 62645, "total_steps": 181800, "loss": 0.0238, "lr": 4.142935264277239e-05, "epoch": 6.891639163916391, "percentage": 34.46, "elapsed_time": "2:27:43", "remaining_time": "4:40:58", "throughput": 1491.64, "total_tokens": 13220448} {"current_steps": 62650, "total_steps": 181800, "loss": 0.076, "lr": 4.14275435428693e-05, "epoch": 6.892189218921892, "percentage": 34.46, "elapsed_time": "2:27:43", "remaining_time": "4:40:57", "throughput": 1491.64, "total_tokens": 13221472} {"current_steps": 62655, "total_steps": 181800, "loss": 0.168, "lr": 4.142573429156141e-05, "epoch": 6.8927392739273925, "percentage": 34.46, "elapsed_time": "2:27:44", "remaining_time": "4:40:56", "throughput": 1491.63, "total_tokens": 13222464} {"current_steps": 62660, "total_steps": 181800, "loss": 0.1182, "lr": 4.142392488886542e-05, "epoch": 6.893289328932894, "percentage": 34.47, "elapsed_time": "2:27:45", "remaining_time": "4:40:55", "throughput": 1491.64, "total_tokens": 13223520} {"current_steps": 62665, "total_steps": 181800, "loss": 0.0832, "lr": 4.1422115334798e-05, "epoch": 6.893839383938394, "percentage": 34.47, "elapsed_time": "2:27:45", "remaining_time": "4:40:55", "throughput": 1491.64, "total_tokens": 13224608} {"current_steps": 62670, "total_steps": 181800, "loss": 0.0326, "lr": 4.1420305629375804e-05, "epoch": 6.894389438943895, "percentage": 34.47, "elapsed_time": "2:27:46", "remaining_time": "4:40:54", "throughput": 1491.65, "total_tokens": 13225728} {"current_steps": 62675, "total_steps": 181800, "loss": 0.0713, "lr": 4.141849577261554e-05, "epoch": 6.894939493949395, "percentage": 34.47, "elapsed_time": "2:27:47", "remaining_time": "4:40:53", "throughput": 1491.66, "total_tokens": 13226816} {"current_steps": 62680, "total_steps": 181800, "loss": 0.0402, "lr": 4.141668576453388e-05, "epoch": 6.895489548954895, "percentage": 34.48, "elapsed_time": "2:27:47", "remaining_time": "4:40:52", "throughput": 1491.66, "total_tokens": 13227840} {"current_steps": 62685, "total_steps": 181800, "loss": 0.0239, "lr": 4.1414875605147504e-05, "epoch": 6.896039603960396, "percentage": 34.48, "elapsed_time": "2:27:48", "remaining_time": "4:40:52", "throughput": 1491.66, "total_tokens": 13228864} {"current_steps": 62690, "total_steps": 181800, "loss": 0.0374, "lr": 4.1413065294473094e-05, "epoch": 6.896589658965897, "percentage": 34.48, "elapsed_time": "2:27:49", "remaining_time": "4:40:51", "throughput": 1491.66, "total_tokens": 13229888} {"current_steps": 62695, "total_steps": 181800, "loss": 0.0282, "lr": 4.141125483252735e-05, "epoch": 6.897139713971397, "percentage": 34.49, "elapsed_time": "2:27:49", "remaining_time": "4:40:50", "throughput": 1491.66, "total_tokens": 13230912} {"current_steps": 62700, "total_steps": 181800, "loss": 0.066, "lr": 4.140944421932693e-05, "epoch": 6.897689768976898, "percentage": 34.49, "elapsed_time": "2:27:50", "remaining_time": "4:40:49", "throughput": 1491.66, "total_tokens": 13231936} {"current_steps": 62705, "total_steps": 181800, "loss": 0.015, "lr": 4.140763345488854e-05, "epoch": 6.898239823982398, "percentage": 34.49, "elapsed_time": "2:27:51", "remaining_time": "4:40:49", "throughput": 1491.66, "total_tokens": 13232992} {"current_steps": 62710, "total_steps": 181800, "loss": 0.0795, "lr": 4.140582253922887e-05, "epoch": 6.898789878987898, "percentage": 34.49, "elapsed_time": "2:27:52", "remaining_time": "4:40:48", "throughput": 1491.66, "total_tokens": 13234016} {"current_steps": 62715, "total_steps": 181800, "loss": 0.0149, "lr": 4.1404011472364595e-05, "epoch": 6.899339933993399, "percentage": 34.5, "elapsed_time": "2:27:52", "remaining_time": "4:40:47", "throughput": 1491.66, "total_tokens": 13235104} {"current_steps": 62720, "total_steps": 181800, "loss": 0.0332, "lr": 4.140220025431243e-05, "epoch": 6.8998899889989, "percentage": 34.5, "elapsed_time": "2:27:53", "remaining_time": "4:40:47", "throughput": 1491.67, "total_tokens": 13236160} {"current_steps": 62725, "total_steps": 181800, "loss": 0.0578, "lr": 4.1400388885089045e-05, "epoch": 6.900440044004401, "percentage": 34.5, "elapsed_time": "2:27:54", "remaining_time": "4:40:46", "throughput": 1491.67, "total_tokens": 13237184} {"current_steps": 62730, "total_steps": 181800, "loss": 0.0825, "lr": 4.1398577364711154e-05, "epoch": 6.900990099009901, "percentage": 34.5, "elapsed_time": "2:27:54", "remaining_time": "4:40:45", "throughput": 1491.67, "total_tokens": 13238208} {"current_steps": 62735, "total_steps": 181800, "loss": 0.0585, "lr": 4.139676569319544e-05, "epoch": 6.901540154015402, "percentage": 34.51, "elapsed_time": "2:27:55", "remaining_time": "4:40:44", "throughput": 1491.66, "total_tokens": 13239200} {"current_steps": 62740, "total_steps": 181800, "loss": 0.0227, "lr": 4.139495387055861e-05, "epoch": 6.902090209020902, "percentage": 34.51, "elapsed_time": "2:27:56", "remaining_time": "4:40:44", "throughput": 1491.66, "total_tokens": 13240256} {"current_steps": 62745, "total_steps": 181800, "loss": 0.0336, "lr": 4.139314189681735e-05, "epoch": 6.902640264026402, "percentage": 34.51, "elapsed_time": "2:27:56", "remaining_time": "4:40:43", "throughput": 1491.67, "total_tokens": 13241312} {"current_steps": 62750, "total_steps": 181800, "loss": 0.0108, "lr": 4.139132977198837e-05, "epoch": 6.9031903190319035, "percentage": 34.52, "elapsed_time": "2:27:57", "remaining_time": "4:40:42", "throughput": 1491.66, "total_tokens": 13242304} {"current_steps": 62755, "total_steps": 181800, "loss": 0.0212, "lr": 4.138951749608837e-05, "epoch": 6.903740374037404, "percentage": 34.52, "elapsed_time": "2:27:58", "remaining_time": "4:40:41", "throughput": 1491.67, "total_tokens": 13243392} {"current_steps": 62760, "total_steps": 181800, "loss": 0.1138, "lr": 4.1387705069134054e-05, "epoch": 6.904290429042904, "percentage": 34.52, "elapsed_time": "2:27:58", "remaining_time": "4:40:41", "throughput": 1491.67, "total_tokens": 13244384} {"current_steps": 62765, "total_steps": 181800, "loss": 0.098, "lr": 4.138589249114212e-05, "epoch": 6.904840484048405, "percentage": 34.52, "elapsed_time": "2:27:59", "remaining_time": "4:40:40", "throughput": 1491.67, "total_tokens": 13245472} {"current_steps": 62770, "total_steps": 181800, "loss": 0.0253, "lr": 4.138407976212928e-05, "epoch": 6.905390539053905, "percentage": 34.53, "elapsed_time": "2:28:00", "remaining_time": "4:40:39", "throughput": 1491.67, "total_tokens": 13246496} {"current_steps": 62775, "total_steps": 181800, "loss": 0.0392, "lr": 4.138226688211223e-05, "epoch": 6.905940594059406, "percentage": 34.53, "elapsed_time": "2:28:00", "remaining_time": "4:40:38", "throughput": 1491.67, "total_tokens": 13247552} {"current_steps": 62780, "total_steps": 181800, "loss": 0.0094, "lr": 4.13804538511077e-05, "epoch": 6.9064906490649065, "percentage": 34.53, "elapsed_time": "2:28:01", "remaining_time": "4:40:38", "throughput": 1491.68, "total_tokens": 13248608} {"current_steps": 62785, "total_steps": 181800, "loss": 0.0622, "lr": 4.137864066913238e-05, "epoch": 6.907040704070407, "percentage": 34.54, "elapsed_time": "2:28:02", "remaining_time": "4:40:37", "throughput": 1491.68, "total_tokens": 13249696} {"current_steps": 62790, "total_steps": 181800, "loss": 0.0046, "lr": 4.137682733620298e-05, "epoch": 6.907590759075908, "percentage": 34.54, "elapsed_time": "2:28:03", "remaining_time": "4:40:36", "throughput": 1491.68, "total_tokens": 13250720} {"current_steps": 62795, "total_steps": 181800, "loss": 0.0682, "lr": 4.137501385233624e-05, "epoch": 6.908140814081408, "percentage": 34.54, "elapsed_time": "2:28:03", "remaining_time": "4:40:35", "throughput": 1491.69, "total_tokens": 13251776} {"current_steps": 62800, "total_steps": 181800, "loss": 0.0206, "lr": 4.1373200217548844e-05, "epoch": 6.908690869086909, "percentage": 34.54, "elapsed_time": "2:28:04", "remaining_time": "4:40:35", "throughput": 1491.69, "total_tokens": 13252864} {"current_steps": 62805, "total_steps": 181800, "loss": 0.0243, "lr": 4.1371386431857515e-05, "epoch": 6.909240924092409, "percentage": 34.55, "elapsed_time": "2:28:05", "remaining_time": "4:40:34", "throughput": 1491.7, "total_tokens": 13253920} {"current_steps": 62810, "total_steps": 181800, "loss": 0.1846, "lr": 4.136957249527898e-05, "epoch": 6.9097909790979095, "percentage": 34.55, "elapsed_time": "2:28:05", "remaining_time": "4:40:33", "throughput": 1491.69, "total_tokens": 13254880} {"current_steps": 62815, "total_steps": 181800, "loss": 0.0047, "lr": 4.136775840782995e-05, "epoch": 6.910341034103411, "percentage": 34.55, "elapsed_time": "2:28:06", "remaining_time": "4:40:32", "throughput": 1491.69, "total_tokens": 13255936} {"current_steps": 62820, "total_steps": 181800, "loss": 0.0126, "lr": 4.136594416952714e-05, "epoch": 6.910891089108911, "percentage": 34.55, "elapsed_time": "2:28:07", "remaining_time": "4:40:32", "throughput": 1491.7, "total_tokens": 13256992} {"current_steps": 62825, "total_steps": 181800, "loss": 0.0798, "lr": 4.1364129780387275e-05, "epoch": 6.911441144114411, "percentage": 34.56, "elapsed_time": "2:28:07", "remaining_time": "4:40:31", "throughput": 1491.7, "total_tokens": 13258048} {"current_steps": 62830, "total_steps": 181800, "loss": 0.1433, "lr": 4.1362315240427086e-05, "epoch": 6.911991199119912, "percentage": 34.56, "elapsed_time": "2:28:08", "remaining_time": "4:40:30", "throughput": 1491.7, "total_tokens": 13259072} {"current_steps": 62835, "total_steps": 181800, "loss": 0.0325, "lr": 4.1360500549663286e-05, "epoch": 6.912541254125412, "percentage": 34.56, "elapsed_time": "2:28:09", "remaining_time": "4:40:29", "throughput": 1491.7, "total_tokens": 13260128} {"current_steps": 62840, "total_steps": 181800, "loss": 0.0067, "lr": 4.13586857081126e-05, "epoch": 6.913091309130913, "percentage": 34.57, "elapsed_time": "2:28:09", "remaining_time": "4:40:29", "throughput": 1491.71, "total_tokens": 13261216} {"current_steps": 62845, "total_steps": 181800, "loss": 0.0203, "lr": 4.135687071579176e-05, "epoch": 6.913641364136414, "percentage": 34.57, "elapsed_time": "2:28:10", "remaining_time": "4:40:28", "throughput": 1491.72, "total_tokens": 13262336} {"current_steps": 62850, "total_steps": 181800, "loss": 0.0176, "lr": 4.135505557271749e-05, "epoch": 6.914191419141914, "percentage": 34.57, "elapsed_time": "2:28:11", "remaining_time": "4:40:27", "throughput": 1491.72, "total_tokens": 13263360} {"current_steps": 62855, "total_steps": 181800, "loss": 0.0296, "lr": 4.1353240278906515e-05, "epoch": 6.914741474147415, "percentage": 34.57, "elapsed_time": "2:28:12", "remaining_time": "4:40:26", "throughput": 1491.72, "total_tokens": 13264352} {"current_steps": 62860, "total_steps": 181800, "loss": 0.0902, "lr": 4.135142483437558e-05, "epoch": 6.915291529152915, "percentage": 34.58, "elapsed_time": "2:28:12", "remaining_time": "4:40:26", "throughput": 1491.72, "total_tokens": 13265376} {"current_steps": 62865, "total_steps": 181800, "loss": 0.0273, "lr": 4.13496092391414e-05, "epoch": 6.915841584158416, "percentage": 34.58, "elapsed_time": "2:28:13", "remaining_time": "4:40:25", "throughput": 1491.72, "total_tokens": 13266400} {"current_steps": 62870, "total_steps": 181800, "loss": 0.0178, "lr": 4.1347793493220724e-05, "epoch": 6.916391639163916, "percentage": 34.58, "elapsed_time": "2:28:14", "remaining_time": "4:40:24", "throughput": 1491.73, "total_tokens": 13267520} {"current_steps": 62875, "total_steps": 181800, "loss": 0.0734, "lr": 4.134597759663028e-05, "epoch": 6.916941694169417, "percentage": 34.58, "elapsed_time": "2:28:14", "remaining_time": "4:40:23", "throughput": 1491.73, "total_tokens": 13268608} {"current_steps": 62880, "total_steps": 181800, "loss": 0.0928, "lr": 4.1344161549386806e-05, "epoch": 6.917491749174918, "percentage": 34.59, "elapsed_time": "2:28:15", "remaining_time": "4:40:23", "throughput": 1491.74, "total_tokens": 13269696} {"current_steps": 62885, "total_steps": 181800, "loss": 0.0314, "lr": 4.134234535150703e-05, "epoch": 6.918041804180418, "percentage": 34.59, "elapsed_time": "2:28:16", "remaining_time": "4:40:22", "throughput": 1491.74, "total_tokens": 13270720} {"current_steps": 62890, "total_steps": 181800, "loss": 0.0358, "lr": 4.13405290030077e-05, "epoch": 6.918591859185918, "percentage": 34.59, "elapsed_time": "2:28:16", "remaining_time": "4:40:21", "throughput": 1491.74, "total_tokens": 13271776} {"current_steps": 62895, "total_steps": 181800, "loss": 0.0567, "lr": 4.133871250390556e-05, "epoch": 6.919141914191419, "percentage": 34.6, "elapsed_time": "2:28:17", "remaining_time": "4:40:21", "throughput": 1491.74, "total_tokens": 13272768} {"current_steps": 62900, "total_steps": 181800, "loss": 0.0292, "lr": 4.1336895854217345e-05, "epoch": 6.919691969196919, "percentage": 34.6, "elapsed_time": "2:28:18", "remaining_time": "4:40:20", "throughput": 1491.75, "total_tokens": 13273888} {"current_steps": 62905, "total_steps": 181800, "loss": 0.0294, "lr": 4.13350790539598e-05, "epoch": 6.9202420242024205, "percentage": 34.6, "elapsed_time": "2:28:18", "remaining_time": "4:40:19", "throughput": 1491.76, "total_tokens": 13274976} {"current_steps": 62910, "total_steps": 181800, "loss": 0.1591, "lr": 4.1333262103149676e-05, "epoch": 6.920792079207921, "percentage": 34.6, "elapsed_time": "2:28:19", "remaining_time": "4:40:18", "throughput": 1491.76, "total_tokens": 13276064} {"current_steps": 62915, "total_steps": 181800, "loss": 0.0066, "lr": 4.13314450018037e-05, "epoch": 6.921342134213422, "percentage": 34.61, "elapsed_time": "2:28:20", "remaining_time": "4:40:18", "throughput": 1491.77, "total_tokens": 13277152} {"current_steps": 62920, "total_steps": 181800, "loss": 0.0017, "lr": 4.1329627749938637e-05, "epoch": 6.921892189218922, "percentage": 34.61, "elapsed_time": "2:28:20", "remaining_time": "4:40:17", "throughput": 1491.78, "total_tokens": 13278240} {"current_steps": 62925, "total_steps": 181800, "loss": 0.0577, "lr": 4.132781034757123e-05, "epoch": 6.922442244224422, "percentage": 34.61, "elapsed_time": "2:28:21", "remaining_time": "4:40:16", "throughput": 1491.78, "total_tokens": 13279264} {"current_steps": 62930, "total_steps": 181800, "loss": 0.0634, "lr": 4.1325992794718236e-05, "epoch": 6.922992299229923, "percentage": 34.61, "elapsed_time": "2:28:22", "remaining_time": "4:40:15", "throughput": 1491.78, "total_tokens": 13280288} {"current_steps": 62935, "total_steps": 181800, "loss": 0.1017, "lr": 4.132417509139639e-05, "epoch": 6.9235423542354235, "percentage": 34.62, "elapsed_time": "2:28:23", "remaining_time": "4:40:15", "throughput": 1491.78, "total_tokens": 13281312} {"current_steps": 62940, "total_steps": 181800, "loss": 0.0983, "lr": 4.132235723762247e-05, "epoch": 6.924092409240924, "percentage": 34.62, "elapsed_time": "2:28:23", "remaining_time": "4:40:14", "throughput": 1491.78, "total_tokens": 13282368} {"current_steps": 62945, "total_steps": 181800, "loss": 0.0114, "lr": 4.13205392334132e-05, "epoch": 6.924642464246425, "percentage": 34.62, "elapsed_time": "2:28:24", "remaining_time": "4:40:13", "throughput": 1491.78, "total_tokens": 13283424} {"current_steps": 62950, "total_steps": 181800, "loss": 0.13, "lr": 4.131872107878536e-05, "epoch": 6.925192519251925, "percentage": 34.63, "elapsed_time": "2:28:25", "remaining_time": "4:40:12", "throughput": 1491.78, "total_tokens": 13284448} {"current_steps": 62955, "total_steps": 181800, "loss": 0.0614, "lr": 4.1316902773755696e-05, "epoch": 6.925742574257426, "percentage": 34.63, "elapsed_time": "2:28:25", "remaining_time": "4:40:12", "throughput": 1491.79, "total_tokens": 13285536} {"current_steps": 62960, "total_steps": 181800, "loss": 0.0916, "lr": 4.131508431834097e-05, "epoch": 6.926292629262926, "percentage": 34.63, "elapsed_time": "2:28:26", "remaining_time": "4:40:11", "throughput": 1491.8, "total_tokens": 13286656} {"current_steps": 62965, "total_steps": 181800, "loss": 0.0228, "lr": 4.131326571255794e-05, "epoch": 6.9268426842684265, "percentage": 34.63, "elapsed_time": "2:28:27", "remaining_time": "4:40:10", "throughput": 1491.8, "total_tokens": 13287648} {"current_steps": 62970, "total_steps": 181800, "loss": 0.0079, "lr": 4.1311446956423374e-05, "epoch": 6.927392739273928, "percentage": 34.64, "elapsed_time": "2:28:27", "remaining_time": "4:40:09", "throughput": 1491.8, "total_tokens": 13288672} {"current_steps": 62975, "total_steps": 181800, "loss": 0.0184, "lr": 4.130962804995402e-05, "epoch": 6.927942794279428, "percentage": 34.64, "elapsed_time": "2:28:28", "remaining_time": "4:40:09", "throughput": 1491.8, "total_tokens": 13289728} {"current_steps": 62980, "total_steps": 181800, "loss": 0.0167, "lr": 4.1307808993166656e-05, "epoch": 6.928492849284929, "percentage": 34.64, "elapsed_time": "2:28:29", "remaining_time": "4:40:08", "throughput": 1491.8, "total_tokens": 13290752} {"current_steps": 62985, "total_steps": 181800, "loss": 0.0749, "lr": 4.130598978607803e-05, "epoch": 6.929042904290429, "percentage": 34.65, "elapsed_time": "2:28:29", "remaining_time": "4:40:07", "throughput": 1491.8, "total_tokens": 13291776} {"current_steps": 62990, "total_steps": 181800, "loss": 0.0275, "lr": 4.130417042870494e-05, "epoch": 6.929592959295929, "percentage": 34.65, "elapsed_time": "2:28:30", "remaining_time": "4:40:06", "throughput": 1491.81, "total_tokens": 13292864} {"current_steps": 62995, "total_steps": 181800, "loss": 0.0214, "lr": 4.130235092106412e-05, "epoch": 6.93014301430143, "percentage": 34.65, "elapsed_time": "2:28:31", "remaining_time": "4:40:06", "throughput": 1491.81, "total_tokens": 13293888} {"current_steps": 63000, "total_steps": 181800, "loss": 0.0608, "lr": 4.130053126317235e-05, "epoch": 6.930693069306931, "percentage": 34.65, "elapsed_time": "2:28:31", "remaining_time": "4:40:05", "throughput": 1491.81, "total_tokens": 13294976} {"current_steps": 63005, "total_steps": 181800, "loss": 0.0147, "lr": 4.129871145504641e-05, "epoch": 6.931243124312431, "percentage": 34.66, "elapsed_time": "2:28:32", "remaining_time": "4:40:04", "throughput": 1491.81, "total_tokens": 13296000} {"current_steps": 63010, "total_steps": 181800, "loss": 0.0506, "lr": 4.129689149670307e-05, "epoch": 6.931793179317932, "percentage": 34.66, "elapsed_time": "2:28:33", "remaining_time": "4:40:03", "throughput": 1491.81, "total_tokens": 13297056} {"current_steps": 63015, "total_steps": 181800, "loss": 0.0638, "lr": 4.129507138815911e-05, "epoch": 6.932343234323432, "percentage": 34.66, "elapsed_time": "2:28:34", "remaining_time": "4:40:03", "throughput": 1491.83, "total_tokens": 13298176} {"current_steps": 63020, "total_steps": 181800, "loss": 0.0793, "lr": 4.129325112943129e-05, "epoch": 6.932893289328933, "percentage": 34.66, "elapsed_time": "2:28:34", "remaining_time": "4:40:02", "throughput": 1491.84, "total_tokens": 13299328} {"current_steps": 63025, "total_steps": 181800, "loss": 0.0426, "lr": 4.129143072053638e-05, "epoch": 6.933443344334433, "percentage": 34.67, "elapsed_time": "2:28:35", "remaining_time": "4:40:01", "throughput": 1491.85, "total_tokens": 13300416} {"current_steps": 63030, "total_steps": 181800, "loss": 0.0406, "lr": 4.128961016149118e-05, "epoch": 6.933993399339934, "percentage": 34.67, "elapsed_time": "2:28:36", "remaining_time": "4:40:00", "throughput": 1491.85, "total_tokens": 13301440} {"current_steps": 63035, "total_steps": 181800, "loss": 0.0127, "lr": 4.128778945231246e-05, "epoch": 6.934543454345435, "percentage": 34.67, "elapsed_time": "2:28:36", "remaining_time": "4:40:00", "throughput": 1491.85, "total_tokens": 13302528} {"current_steps": 63040, "total_steps": 181800, "loss": 0.0085, "lr": 4.1285968593017006e-05, "epoch": 6.935093509350935, "percentage": 34.68, "elapsed_time": "2:28:37", "remaining_time": "4:39:59", "throughput": 1491.85, "total_tokens": 13303520} {"current_steps": 63045, "total_steps": 181800, "loss": 0.0105, "lr": 4.1284147583621586e-05, "epoch": 6.935643564356436, "percentage": 34.68, "elapsed_time": "2:28:38", "remaining_time": "4:39:58", "throughput": 1491.85, "total_tokens": 13304544} {"current_steps": 63050, "total_steps": 181800, "loss": 0.0189, "lr": 4.1282326424142994e-05, "epoch": 6.936193619361936, "percentage": 34.68, "elapsed_time": "2:28:38", "remaining_time": "4:39:57", "throughput": 1491.85, "total_tokens": 13305600} {"current_steps": 63055, "total_steps": 181800, "loss": 0.0633, "lr": 4.1280505114598014e-05, "epoch": 6.936743674367436, "percentage": 34.68, "elapsed_time": "2:28:39", "remaining_time": "4:39:57", "throughput": 1491.86, "total_tokens": 13306688} {"current_steps": 63060, "total_steps": 181800, "loss": 0.0799, "lr": 4.1278683655003424e-05, "epoch": 6.9372937293729375, "percentage": 34.69, "elapsed_time": "2:28:40", "remaining_time": "4:39:56", "throughput": 1491.86, "total_tokens": 13307680} {"current_steps": 63065, "total_steps": 181800, "loss": 0.0083, "lr": 4.127686204537603e-05, "epoch": 6.937843784378438, "percentage": 34.69, "elapsed_time": "2:28:40", "remaining_time": "4:39:55", "throughput": 1491.86, "total_tokens": 13308736} {"current_steps": 63070, "total_steps": 181800, "loss": 0.0275, "lr": 4.12750402857326e-05, "epoch": 6.938393839383938, "percentage": 34.69, "elapsed_time": "2:28:41", "remaining_time": "4:39:55", "throughput": 1491.86, "total_tokens": 13309760} {"current_steps": 63075, "total_steps": 181800, "loss": 0.0246, "lr": 4.127321837608993e-05, "epoch": 6.938943894389439, "percentage": 34.69, "elapsed_time": "2:28:42", "remaining_time": "4:39:54", "throughput": 1491.86, "total_tokens": 13310816} {"current_steps": 63080, "total_steps": 181800, "loss": 0.0041, "lr": 4.127139631646482e-05, "epoch": 6.939493949394939, "percentage": 34.7, "elapsed_time": "2:28:42", "remaining_time": "4:39:53", "throughput": 1491.87, "total_tokens": 13311904} {"current_steps": 63085, "total_steps": 181800, "loss": 0.0618, "lr": 4.126957410687407e-05, "epoch": 6.94004400440044, "percentage": 34.7, "elapsed_time": "2:28:43", "remaining_time": "4:39:52", "throughput": 1491.87, "total_tokens": 13312928} {"current_steps": 63090, "total_steps": 181800, "loss": 0.0175, "lr": 4.126775174733444e-05, "epoch": 6.9405940594059405, "percentage": 34.7, "elapsed_time": "2:28:44", "remaining_time": "4:39:52", "throughput": 1491.87, "total_tokens": 13313984} {"current_steps": 63095, "total_steps": 181800, "loss": 0.0533, "lr": 4.126592923786276e-05, "epoch": 6.941144114411442, "percentage": 34.71, "elapsed_time": "2:28:45", "remaining_time": "4:39:51", "throughput": 1491.88, "total_tokens": 13315104} {"current_steps": 63100, "total_steps": 181800, "loss": 0.0908, "lr": 4.126410657847581e-05, "epoch": 6.941694169416942, "percentage": 34.71, "elapsed_time": "2:28:45", "remaining_time": "4:39:50", "throughput": 1491.89, "total_tokens": 13316192} {"current_steps": 63105, "total_steps": 181800, "loss": 0.0229, "lr": 4.12622837691904e-05, "epoch": 6.942244224422442, "percentage": 34.71, "elapsed_time": "2:28:46", "remaining_time": "4:39:49", "throughput": 1491.89, "total_tokens": 13317216} {"current_steps": 63110, "total_steps": 181800, "loss": 0.0217, "lr": 4.1260460810023326e-05, "epoch": 6.942794279427943, "percentage": 34.71, "elapsed_time": "2:28:47", "remaining_time": "4:39:49", "throughput": 1491.89, "total_tokens": 13318304} {"current_steps": 63115, "total_steps": 181800, "loss": 0.0114, "lr": 4.125863770099138e-05, "epoch": 6.943344334433443, "percentage": 34.72, "elapsed_time": "2:28:47", "remaining_time": "4:39:48", "throughput": 1491.9, "total_tokens": 13319360} {"current_steps": 63120, "total_steps": 181800, "loss": 0.0271, "lr": 4.1256814442111374e-05, "epoch": 6.9438943894389435, "percentage": 34.72, "elapsed_time": "2:28:48", "remaining_time": "4:39:47", "throughput": 1491.9, "total_tokens": 13320416} {"current_steps": 63125, "total_steps": 181800, "loss": 0.0603, "lr": 4.1254991033400114e-05, "epoch": 6.944444444444445, "percentage": 34.72, "elapsed_time": "2:28:49", "remaining_time": "4:39:46", "throughput": 1491.91, "total_tokens": 13321504} {"current_steps": 63130, "total_steps": 181800, "loss": 0.0356, "lr": 4.12531674748744e-05, "epoch": 6.944994499449945, "percentage": 34.72, "elapsed_time": "2:28:49", "remaining_time": "4:39:46", "throughput": 1491.91, "total_tokens": 13322528} {"current_steps": 63135, "total_steps": 181800, "loss": 0.0671, "lr": 4.1251343766551035e-05, "epoch": 6.945544554455445, "percentage": 34.73, "elapsed_time": "2:28:50", "remaining_time": "4:39:45", "throughput": 1491.91, "total_tokens": 13323584} {"current_steps": 63140, "total_steps": 181800, "loss": 0.0818, "lr": 4.124951990844684e-05, "epoch": 6.946094609460946, "percentage": 34.73, "elapsed_time": "2:28:51", "remaining_time": "4:39:44", "throughput": 1491.92, "total_tokens": 13324672} {"current_steps": 63145, "total_steps": 181800, "loss": 0.0193, "lr": 4.124769590057861e-05, "epoch": 6.946644664466446, "percentage": 34.73, "elapsed_time": "2:28:51", "remaining_time": "4:39:43", "throughput": 1491.91, "total_tokens": 13325664} {"current_steps": 63150, "total_steps": 181800, "loss": 0.0617, "lr": 4.124587174296317e-05, "epoch": 6.947194719471947, "percentage": 34.74, "elapsed_time": "2:28:52", "remaining_time": "4:39:43", "throughput": 1491.92, "total_tokens": 13326752} {"current_steps": 63155, "total_steps": 181800, "loss": 0.0553, "lr": 4.1244047435617324e-05, "epoch": 6.947744774477448, "percentage": 34.74, "elapsed_time": "2:28:53", "remaining_time": "4:39:42", "throughput": 1491.92, "total_tokens": 13327808} {"current_steps": 63160, "total_steps": 181800, "loss": 0.043, "lr": 4.124222297855789e-05, "epoch": 6.948294829482949, "percentage": 34.74, "elapsed_time": "2:28:54", "remaining_time": "4:39:41", "throughput": 1491.92, "total_tokens": 13328864} {"current_steps": 63165, "total_steps": 181800, "loss": 0.0525, "lr": 4.124039837180167e-05, "epoch": 6.948844884488449, "percentage": 34.74, "elapsed_time": "2:28:54", "remaining_time": "4:39:40", "throughput": 1491.93, "total_tokens": 13329920} {"current_steps": 63170, "total_steps": 181800, "loss": 0.0387, "lr": 4.1238573615365494e-05, "epoch": 6.949394939493949, "percentage": 34.75, "elapsed_time": "2:28:55", "remaining_time": "4:39:40", "throughput": 1491.93, "total_tokens": 13331008} {"current_steps": 63175, "total_steps": 181800, "loss": 0.1007, "lr": 4.1236748709266185e-05, "epoch": 6.94994499449945, "percentage": 34.75, "elapsed_time": "2:28:56", "remaining_time": "4:39:39", "throughput": 1491.94, "total_tokens": 13332064} {"current_steps": 63180, "total_steps": 181800, "loss": 0.016, "lr": 4.123492365352055e-05, "epoch": 6.9504950495049505, "percentage": 34.75, "elapsed_time": "2:28:56", "remaining_time": "4:39:38", "throughput": 1491.94, "total_tokens": 13333152} {"current_steps": 63185, "total_steps": 181800, "loss": 0.1226, "lr": 4.123309844814541e-05, "epoch": 6.951045104510451, "percentage": 34.76, "elapsed_time": "2:28:57", "remaining_time": "4:39:37", "throughput": 1491.94, "total_tokens": 13334208} {"current_steps": 63190, "total_steps": 181800, "loss": 0.0036, "lr": 4.12312730931576e-05, "epoch": 6.951595159515952, "percentage": 34.76, "elapsed_time": "2:28:58", "remaining_time": "4:39:37", "throughput": 1491.94, "total_tokens": 13335200} {"current_steps": 63195, "total_steps": 181800, "loss": 0.0221, "lr": 4.122944758857393e-05, "epoch": 6.952145214521452, "percentage": 34.76, "elapsed_time": "2:28:58", "remaining_time": "4:39:36", "throughput": 1491.94, "total_tokens": 13336224} {"current_steps": 63200, "total_steps": 181800, "loss": 0.0945, "lr": 4.122762193441123e-05, "epoch": 6.952695269526953, "percentage": 34.76, "elapsed_time": "2:28:59", "remaining_time": "4:39:35", "throughput": 1491.94, "total_tokens": 13337248} {"current_steps": 63205, "total_steps": 181800, "loss": 0.0328, "lr": 4.1225796130686325e-05, "epoch": 6.953245324532453, "percentage": 34.77, "elapsed_time": "2:29:00", "remaining_time": "4:39:35", "throughput": 1491.94, "total_tokens": 13338272} {"current_steps": 63210, "total_steps": 181800, "loss": 0.0422, "lr": 4.122397017741604e-05, "epoch": 6.9537953795379535, "percentage": 34.77, "elapsed_time": "2:29:00", "remaining_time": "4:39:34", "throughput": 1491.94, "total_tokens": 13339360} {"current_steps": 63215, "total_steps": 181800, "loss": 0.0331, "lr": 4.1222144074617206e-05, "epoch": 6.9543454345434546, "percentage": 34.77, "elapsed_time": "2:29:01", "remaining_time": "4:39:33", "throughput": 1491.94, "total_tokens": 13340352} {"current_steps": 63220, "total_steps": 181800, "loss": 0.1347, "lr": 4.122031782230666e-05, "epoch": 6.954895489548955, "percentage": 34.77, "elapsed_time": "2:29:02", "remaining_time": "4:39:32", "throughput": 1491.94, "total_tokens": 13341408} {"current_steps": 63225, "total_steps": 181800, "loss": 0.0231, "lr": 4.121849142050123e-05, "epoch": 6.955445544554456, "percentage": 34.78, "elapsed_time": "2:29:02", "remaining_time": "4:39:32", "throughput": 1491.95, "total_tokens": 13342464} {"current_steps": 63230, "total_steps": 181800, "loss": 0.0963, "lr": 4.121666486921774e-05, "epoch": 6.955995599559956, "percentage": 34.78, "elapsed_time": "2:29:03", "remaining_time": "4:39:31", "throughput": 1491.95, "total_tokens": 13343520} {"current_steps": 63235, "total_steps": 181800, "loss": 0.0277, "lr": 4.121483816847304e-05, "epoch": 6.956545654565456, "percentage": 34.78, "elapsed_time": "2:29:04", "remaining_time": "4:39:30", "throughput": 1491.95, "total_tokens": 13344576} {"current_steps": 63240, "total_steps": 181800, "loss": 0.0055, "lr": 4.121301131828394e-05, "epoch": 6.957095709570957, "percentage": 34.79, "elapsed_time": "2:29:05", "remaining_time": "4:39:29", "throughput": 1491.95, "total_tokens": 13345600} {"current_steps": 63245, "total_steps": 181800, "loss": 0.0563, "lr": 4.1211184318667306e-05, "epoch": 6.957645764576458, "percentage": 34.79, "elapsed_time": "2:29:05", "remaining_time": "4:39:29", "throughput": 1491.95, "total_tokens": 13346624} {"current_steps": 63250, "total_steps": 181800, "loss": 0.1038, "lr": 4.1209357169639965e-05, "epoch": 6.958195819581958, "percentage": 34.79, "elapsed_time": "2:29:06", "remaining_time": "4:39:28", "throughput": 1491.95, "total_tokens": 13347616} {"current_steps": 63255, "total_steps": 181800, "loss": 0.0539, "lr": 4.120752987121876e-05, "epoch": 6.958745874587459, "percentage": 34.79, "elapsed_time": "2:29:07", "remaining_time": "4:39:27", "throughput": 1491.95, "total_tokens": 13348672} {"current_steps": 63260, "total_steps": 181800, "loss": 0.1157, "lr": 4.1205702423420525e-05, "epoch": 6.959295929592959, "percentage": 34.8, "elapsed_time": "2:29:07", "remaining_time": "4:39:26", "throughput": 1491.95, "total_tokens": 13349728} {"current_steps": 63265, "total_steps": 181800, "loss": 0.114, "lr": 4.120387482626211e-05, "epoch": 6.95984598459846, "percentage": 34.8, "elapsed_time": "2:29:08", "remaining_time": "4:39:26", "throughput": 1491.95, "total_tokens": 13350752} {"current_steps": 63270, "total_steps": 181800, "loss": 0.0263, "lr": 4.1202047079760354e-05, "epoch": 6.96039603960396, "percentage": 34.8, "elapsed_time": "2:29:09", "remaining_time": "4:39:25", "throughput": 1491.96, "total_tokens": 13351872} {"current_steps": 63275, "total_steps": 181800, "loss": 0.0882, "lr": 4.12002191839321e-05, "epoch": 6.960946094609461, "percentage": 34.8, "elapsed_time": "2:29:09", "remaining_time": "4:39:24", "throughput": 1491.97, "total_tokens": 13352928} {"current_steps": 63280, "total_steps": 181800, "loss": 0.0307, "lr": 4.11983911387942e-05, "epoch": 6.961496149614962, "percentage": 34.81, "elapsed_time": "2:29:10", "remaining_time": "4:39:23", "throughput": 1491.98, "total_tokens": 13354048} {"current_steps": 63285, "total_steps": 181800, "loss": 0.0395, "lr": 4.119656294436351e-05, "epoch": 6.962046204620462, "percentage": 34.81, "elapsed_time": "2:29:11", "remaining_time": "4:39:23", "throughput": 1491.98, "total_tokens": 13355136} {"current_steps": 63290, "total_steps": 181800, "loss": 0.0305, "lr": 4.119473460065687e-05, "epoch": 6.962596259625963, "percentage": 34.81, "elapsed_time": "2:29:11", "remaining_time": "4:39:22", "throughput": 1491.99, "total_tokens": 13356256} {"current_steps": 63295, "total_steps": 181800, "loss": 0.0574, "lr": 4.119290610769112e-05, "epoch": 6.963146314631463, "percentage": 34.82, "elapsed_time": "2:29:12", "remaining_time": "4:39:21", "throughput": 1492.0, "total_tokens": 13357312} {"current_steps": 63300, "total_steps": 181800, "loss": 0.061, "lr": 4.1191077465483144e-05, "epoch": 6.963696369636963, "percentage": 34.82, "elapsed_time": "2:29:13", "remaining_time": "4:39:20", "throughput": 1492.0, "total_tokens": 13358368} {"current_steps": 63305, "total_steps": 181800, "loss": 0.0306, "lr": 4.118924867404976e-05, "epoch": 6.9642464246424645, "percentage": 34.82, "elapsed_time": "2:29:14", "remaining_time": "4:39:20", "throughput": 1492.01, "total_tokens": 13359488} {"current_steps": 63310, "total_steps": 181800, "loss": 0.1848, "lr": 4.1187419733407845e-05, "epoch": 6.964796479647965, "percentage": 34.82, "elapsed_time": "2:29:14", "remaining_time": "4:39:19", "throughput": 1492.02, "total_tokens": 13360608} {"current_steps": 63315, "total_steps": 181800, "loss": 0.0322, "lr": 4.1185590643574244e-05, "epoch": 6.965346534653465, "percentage": 34.83, "elapsed_time": "2:29:15", "remaining_time": "4:39:18", "throughput": 1492.03, "total_tokens": 13361728} {"current_steps": 63320, "total_steps": 181800, "loss": 0.0233, "lr": 4.1183761404565836e-05, "epoch": 6.965896589658966, "percentage": 34.83, "elapsed_time": "2:29:16", "remaining_time": "4:39:18", "throughput": 1492.02, "total_tokens": 13362720} {"current_steps": 63325, "total_steps": 181800, "loss": 0.056, "lr": 4.1181932016399446e-05, "epoch": 6.966446644664466, "percentage": 34.83, "elapsed_time": "2:29:16", "remaining_time": "4:39:17", "throughput": 1492.03, "total_tokens": 13363808} {"current_steps": 63330, "total_steps": 181800, "loss": 0.0357, "lr": 4.118010247909197e-05, "epoch": 6.966996699669967, "percentage": 34.83, "elapsed_time": "2:29:17", "remaining_time": "4:39:16", "throughput": 1492.04, "total_tokens": 13364896} {"current_steps": 63335, "total_steps": 181800, "loss": 0.0068, "lr": 4.1178272792660244e-05, "epoch": 6.9675467546754675, "percentage": 34.84, "elapsed_time": "2:29:18", "remaining_time": "4:39:15", "throughput": 1492.03, "total_tokens": 13365888} {"current_steps": 63340, "total_steps": 181800, "loss": 0.0102, "lr": 4.1176442957121144e-05, "epoch": 6.968096809680969, "percentage": 34.84, "elapsed_time": "2:29:18", "remaining_time": "4:39:15", "throughput": 1492.03, "total_tokens": 13366880} {"current_steps": 63345, "total_steps": 181800, "loss": 0.0184, "lr": 4.117461297249153e-05, "epoch": 6.968646864686469, "percentage": 34.84, "elapsed_time": "2:29:19", "remaining_time": "4:39:14", "throughput": 1492.04, "total_tokens": 13368000} {"current_steps": 63350, "total_steps": 181800, "loss": 0.1172, "lr": 4.1172782838788265e-05, "epoch": 6.969196919691969, "percentage": 34.85, "elapsed_time": "2:29:20", "remaining_time": "4:39:13", "throughput": 1492.04, "total_tokens": 13369056} {"current_steps": 63355, "total_steps": 181800, "loss": 0.1589, "lr": 4.117095255602823e-05, "epoch": 6.96974697469747, "percentage": 34.85, "elapsed_time": "2:29:20", "remaining_time": "4:39:12", "throughput": 1492.05, "total_tokens": 13370112} {"current_steps": 63360, "total_steps": 181800, "loss": 0.0118, "lr": 4.116912212422828e-05, "epoch": 6.97029702970297, "percentage": 34.85, "elapsed_time": "2:29:21", "remaining_time": "4:39:12", "throughput": 1492.05, "total_tokens": 13371168} {"current_steps": 63365, "total_steps": 181800, "loss": 0.0318, "lr": 4.116729154340528e-05, "epoch": 6.9708470847084705, "percentage": 34.85, "elapsed_time": "2:29:22", "remaining_time": "4:39:11", "throughput": 1492.06, "total_tokens": 13372256} {"current_steps": 63370, "total_steps": 181800, "loss": 0.0977, "lr": 4.116546081357613e-05, "epoch": 6.971397139713972, "percentage": 34.86, "elapsed_time": "2:29:22", "remaining_time": "4:39:10", "throughput": 1492.06, "total_tokens": 13373280} {"current_steps": 63375, "total_steps": 181800, "loss": 0.1044, "lr": 4.1163629934757676e-05, "epoch": 6.971947194719472, "percentage": 34.86, "elapsed_time": "2:29:23", "remaining_time": "4:39:09", "throughput": 1492.07, "total_tokens": 13374400} {"current_steps": 63380, "total_steps": 181800, "loss": 0.0588, "lr": 4.11617989069668e-05, "epoch": 6.972497249724973, "percentage": 34.86, "elapsed_time": "2:29:24", "remaining_time": "4:39:09", "throughput": 1492.07, "total_tokens": 13375488} {"current_steps": 63385, "total_steps": 181800, "loss": 0.0489, "lr": 4.1159967730220384e-05, "epoch": 6.973047304730473, "percentage": 34.87, "elapsed_time": "2:29:25", "remaining_time": "4:39:08", "throughput": 1492.08, "total_tokens": 13376544} {"current_steps": 63390, "total_steps": 181800, "loss": 0.1017, "lr": 4.11581364045353e-05, "epoch": 6.973597359735973, "percentage": 34.87, "elapsed_time": "2:29:25", "remaining_time": "4:39:07", "throughput": 1492.08, "total_tokens": 13377632} {"current_steps": 63395, "total_steps": 181800, "loss": 0.1172, "lr": 4.1156304929928425e-05, "epoch": 6.974147414741474, "percentage": 34.87, "elapsed_time": "2:29:26", "remaining_time": "4:39:06", "throughput": 1492.08, "total_tokens": 13378688} {"current_steps": 63400, "total_steps": 181800, "loss": 0.0423, "lr": 4.115447330641663e-05, "epoch": 6.974697469746975, "percentage": 34.87, "elapsed_time": "2:29:27", "remaining_time": "4:39:06", "throughput": 1492.09, "total_tokens": 13379744} {"current_steps": 63405, "total_steps": 181800, "loss": 0.115, "lr": 4.1152641534016816e-05, "epoch": 6.975247524752476, "percentage": 34.88, "elapsed_time": "2:29:27", "remaining_time": "4:39:05", "throughput": 1492.08, "total_tokens": 13380736} {"current_steps": 63410, "total_steps": 181800, "loss": 0.0511, "lr": 4.1150809612745854e-05, "epoch": 6.975797579757976, "percentage": 34.88, "elapsed_time": "2:29:28", "remaining_time": "4:39:04", "throughput": 1492.08, "total_tokens": 13381760} {"current_steps": 63415, "total_steps": 181800, "loss": 0.0357, "lr": 4.114897754262063e-05, "epoch": 6.976347634763476, "percentage": 34.88, "elapsed_time": "2:29:29", "remaining_time": "4:39:03", "throughput": 1492.08, "total_tokens": 13382784} {"current_steps": 63420, "total_steps": 181800, "loss": 0.0659, "lr": 4.114714532365803e-05, "epoch": 6.976897689768977, "percentage": 34.88, "elapsed_time": "2:29:29", "remaining_time": "4:39:03", "throughput": 1492.08, "total_tokens": 13383776} {"current_steps": 63425, "total_steps": 181800, "loss": 0.0872, "lr": 4.114531295587494e-05, "epoch": 6.977447744774477, "percentage": 34.89, "elapsed_time": "2:29:30", "remaining_time": "4:39:02", "throughput": 1492.08, "total_tokens": 13384832} {"current_steps": 63430, "total_steps": 181800, "loss": 0.0511, "lr": 4.114348043928824e-05, "epoch": 6.977997799779978, "percentage": 34.89, "elapsed_time": "2:29:31", "remaining_time": "4:39:01", "throughput": 1492.09, "total_tokens": 13385920} {"current_steps": 63435, "total_steps": 181800, "loss": 0.0245, "lr": 4.1141647773914835e-05, "epoch": 6.978547854785479, "percentage": 34.89, "elapsed_time": "2:29:31", "remaining_time": "4:39:01", "throughput": 1492.09, "total_tokens": 13386944} {"current_steps": 63440, "total_steps": 181800, "loss": 0.0821, "lr": 4.11398149597716e-05, "epoch": 6.979097909790979, "percentage": 34.9, "elapsed_time": "2:29:32", "remaining_time": "4:39:00", "throughput": 1492.09, "total_tokens": 13388032} {"current_steps": 63445, "total_steps": 181800, "loss": 0.0495, "lr": 4.113798199687545e-05, "epoch": 6.97964796479648, "percentage": 34.9, "elapsed_time": "2:29:33", "remaining_time": "4:38:59", "throughput": 1492.1, "total_tokens": 13389088} {"current_steps": 63450, "total_steps": 181800, "loss": 0.0462, "lr": 4.113614888524325e-05, "epoch": 6.98019801980198, "percentage": 34.9, "elapsed_time": "2:29:34", "remaining_time": "4:38:58", "throughput": 1492.09, "total_tokens": 13390080} {"current_steps": 63455, "total_steps": 181800, "loss": 0.0356, "lr": 4.1134315624891914e-05, "epoch": 6.98074807480748, "percentage": 34.9, "elapsed_time": "2:29:34", "remaining_time": "4:38:58", "throughput": 1492.09, "total_tokens": 13391104} {"current_steps": 63460, "total_steps": 181800, "loss": 0.0374, "lr": 4.113248221583833e-05, "epoch": 6.9812981298129815, "percentage": 34.91, "elapsed_time": "2:29:35", "remaining_time": "4:38:57", "throughput": 1492.09, "total_tokens": 13392128} {"current_steps": 63465, "total_steps": 181800, "loss": 0.0614, "lr": 4.11306486580994e-05, "epoch": 6.981848184818482, "percentage": 34.91, "elapsed_time": "2:29:36", "remaining_time": "4:38:56", "throughput": 1492.09, "total_tokens": 13393152} {"current_steps": 63470, "total_steps": 181800, "loss": 0.0031, "lr": 4.112881495169203e-05, "epoch": 6.982398239823983, "percentage": 34.91, "elapsed_time": "2:29:36", "remaining_time": "4:38:55", "throughput": 1492.09, "total_tokens": 13394144} {"current_steps": 63475, "total_steps": 181800, "loss": 0.0156, "lr": 4.11269810966331e-05, "epoch": 6.982948294829483, "percentage": 34.91, "elapsed_time": "2:29:37", "remaining_time": "4:38:55", "throughput": 1492.1, "total_tokens": 13395264} {"current_steps": 63480, "total_steps": 181800, "loss": 0.0198, "lr": 4.1125147092939524e-05, "epoch": 6.983498349834983, "percentage": 34.92, "elapsed_time": "2:29:38", "remaining_time": "4:38:54", "throughput": 1492.1, "total_tokens": 13396320} {"current_steps": 63485, "total_steps": 181800, "loss": 0.0539, "lr": 4.112331294062821e-05, "epoch": 6.984048404840484, "percentage": 34.92, "elapsed_time": "2:29:38", "remaining_time": "4:38:53", "throughput": 1492.1, "total_tokens": 13397376} {"current_steps": 63490, "total_steps": 181800, "loss": 0.0273, "lr": 4.112147863971606e-05, "epoch": 6.9845984598459845, "percentage": 34.92, "elapsed_time": "2:29:39", "remaining_time": "4:38:52", "throughput": 1492.11, "total_tokens": 13398464} {"current_steps": 63495, "total_steps": 181800, "loss": 0.0517, "lr": 4.111964419021998e-05, "epoch": 6.985148514851485, "percentage": 34.93, "elapsed_time": "2:29:40", "remaining_time": "4:38:52", "throughput": 1492.11, "total_tokens": 13399456} {"current_steps": 63500, "total_steps": 181800, "loss": 0.0554, "lr": 4.1117809592156857e-05, "epoch": 6.985698569856986, "percentage": 34.93, "elapsed_time": "2:29:40", "remaining_time": "4:38:51", "throughput": 1492.12, "total_tokens": 13400576} {"current_steps": 63505, "total_steps": 181800, "loss": 0.0317, "lr": 4.1115974845543626e-05, "epoch": 6.986248624862486, "percentage": 34.93, "elapsed_time": "2:29:41", "remaining_time": "4:38:50", "throughput": 1492.12, "total_tokens": 13401632} {"current_steps": 63510, "total_steps": 181800, "loss": 0.0443, "lr": 4.11141399503972e-05, "epoch": 6.986798679867987, "percentage": 34.93, "elapsed_time": "2:29:42", "remaining_time": "4:38:49", "throughput": 1492.12, "total_tokens": 13402656} {"current_steps": 63515, "total_steps": 181800, "loss": 0.0398, "lr": 4.1112304906734466e-05, "epoch": 6.987348734873487, "percentage": 34.94, "elapsed_time": "2:29:42", "remaining_time": "4:38:49", "throughput": 1492.12, "total_tokens": 13403680} {"current_steps": 63520, "total_steps": 181800, "loss": 0.0157, "lr": 4.111046971457235e-05, "epoch": 6.987898789878988, "percentage": 34.94, "elapsed_time": "2:29:43", "remaining_time": "4:38:48", "throughput": 1492.12, "total_tokens": 13404704} {"current_steps": 63525, "total_steps": 181800, "loss": 0.0151, "lr": 4.1108634373927764e-05, "epoch": 6.988448844884489, "percentage": 34.94, "elapsed_time": "2:29:44", "remaining_time": "4:38:47", "throughput": 1492.12, "total_tokens": 13405728} {"current_steps": 63530, "total_steps": 181800, "loss": 0.1173, "lr": 4.110679888481763e-05, "epoch": 6.988998899889989, "percentage": 34.94, "elapsed_time": "2:29:45", "remaining_time": "4:38:46", "throughput": 1492.12, "total_tokens": 13406816} {"current_steps": 63535, "total_steps": 181800, "loss": 0.088, "lr": 4.110496324725886e-05, "epoch": 6.98954895489549, "percentage": 34.95, "elapsed_time": "2:29:45", "remaining_time": "4:38:46", "throughput": 1492.12, "total_tokens": 13407808} {"current_steps": 63540, "total_steps": 181800, "loss": 0.0256, "lr": 4.110312746126836e-05, "epoch": 6.99009900990099, "percentage": 34.95, "elapsed_time": "2:29:46", "remaining_time": "4:38:45", "throughput": 1492.12, "total_tokens": 13408864} {"current_steps": 63545, "total_steps": 181800, "loss": 0.0316, "lr": 4.110129152686307e-05, "epoch": 6.99064906490649, "percentage": 34.95, "elapsed_time": "2:29:47", "remaining_time": "4:38:44", "throughput": 1492.12, "total_tokens": 13409888} {"current_steps": 63550, "total_steps": 181800, "loss": 0.0397, "lr": 4.10994554440599e-05, "epoch": 6.991199119911991, "percentage": 34.96, "elapsed_time": "2:29:47", "remaining_time": "4:38:43", "throughput": 1492.13, "total_tokens": 13410944} {"current_steps": 63555, "total_steps": 181800, "loss": 0.023, "lr": 4.109761921287578e-05, "epoch": 6.991749174917492, "percentage": 34.96, "elapsed_time": "2:29:48", "remaining_time": "4:38:43", "throughput": 1492.13, "total_tokens": 13411968} {"current_steps": 63560, "total_steps": 181800, "loss": 0.0295, "lr": 4.109578283332762e-05, "epoch": 6.992299229922993, "percentage": 34.96, "elapsed_time": "2:29:49", "remaining_time": "4:38:42", "throughput": 1492.12, "total_tokens": 13412960} {"current_steps": 63565, "total_steps": 181800, "loss": 0.0389, "lr": 4.1093946305432365e-05, "epoch": 6.992849284928493, "percentage": 34.96, "elapsed_time": "2:29:49", "remaining_time": "4:38:41", "throughput": 1492.13, "total_tokens": 13414080} {"current_steps": 63570, "total_steps": 181800, "loss": 0.0148, "lr": 4.109210962920692e-05, "epoch": 6.993399339933993, "percentage": 34.97, "elapsed_time": "2:29:50", "remaining_time": "4:38:41", "throughput": 1492.13, "total_tokens": 13415136} {"current_steps": 63575, "total_steps": 181800, "loss": 0.0641, "lr": 4.109027280466822e-05, "epoch": 6.993949394939494, "percentage": 34.97, "elapsed_time": "2:29:51", "remaining_time": "4:38:40", "throughput": 1492.14, "total_tokens": 13416192} {"current_steps": 63580, "total_steps": 181800, "loss": 0.0657, "lr": 4.1088435831833206e-05, "epoch": 6.994499449944994, "percentage": 34.97, "elapsed_time": "2:29:51", "remaining_time": "4:38:39", "throughput": 1492.15, "total_tokens": 13417344} {"current_steps": 63585, "total_steps": 181800, "loss": 0.0486, "lr": 4.108659871071879e-05, "epoch": 6.9950495049504955, "percentage": 34.98, "elapsed_time": "2:29:52", "remaining_time": "4:38:38", "throughput": 1492.15, "total_tokens": 13418400} {"current_steps": 63590, "total_steps": 181800, "loss": 0.0655, "lr": 4.108476144134192e-05, "epoch": 6.995599559955996, "percentage": 34.98, "elapsed_time": "2:29:53", "remaining_time": "4:38:38", "throughput": 1492.15, "total_tokens": 13419424} {"current_steps": 63595, "total_steps": 181800, "loss": 0.0091, "lr": 4.1082924023719516e-05, "epoch": 6.996149614961496, "percentage": 34.98, "elapsed_time": "2:29:54", "remaining_time": "4:38:37", "throughput": 1492.16, "total_tokens": 13420512} {"current_steps": 63600, "total_steps": 181800, "loss": 0.0184, "lr": 4.108108645786852e-05, "epoch": 6.996699669966997, "percentage": 34.98, "elapsed_time": "2:29:54", "remaining_time": "4:38:36", "throughput": 1492.16, "total_tokens": 13421504} {"current_steps": 63605, "total_steps": 181800, "loss": 0.0171, "lr": 4.107924874380587e-05, "epoch": 6.997249724972497, "percentage": 34.99, "elapsed_time": "2:29:55", "remaining_time": "4:38:35", "throughput": 1492.16, "total_tokens": 13422560} {"current_steps": 63610, "total_steps": 181800, "loss": 0.0112, "lr": 4.10774108815485e-05, "epoch": 6.997799779977997, "percentage": 34.99, "elapsed_time": "2:29:56", "remaining_time": "4:38:35", "throughput": 1492.16, "total_tokens": 13423584} {"current_steps": 63615, "total_steps": 181800, "loss": 0.0121, "lr": 4.107557287111334e-05, "epoch": 6.9983498349834985, "percentage": 34.99, "elapsed_time": "2:29:56", "remaining_time": "4:38:34", "throughput": 1492.16, "total_tokens": 13424608} {"current_steps": 63620, "total_steps": 181800, "loss": 0.2137, "lr": 4.1073734712517345e-05, "epoch": 6.998899889988999, "percentage": 34.99, "elapsed_time": "2:29:57", "remaining_time": "4:38:33", "throughput": 1492.17, "total_tokens": 13425696} {"current_steps": 63625, "total_steps": 181800, "loss": 0.0364, "lr": 4.1071896405777454e-05, "epoch": 6.9994499449945, "percentage": 35.0, "elapsed_time": "2:29:58", "remaining_time": "4:38:32", "throughput": 1492.16, "total_tokens": 13426720} {"current_steps": 63630, "total_steps": 181800, "loss": 0.0257, "lr": 4.10700579509106e-05, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "2:29:58", "remaining_time": "4:38:32", "throughput": 1492.15, "total_tokens": 13427712} {"current_steps": 63630, "total_steps": 181800, "eval_loss": 0.06129888445138931, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "2:30:35", "remaining_time": "4:39:40", "throughput": 1486.05, "total_tokens": 13427712} {"current_steps": 63635, "total_steps": 181800, "loss": 0.0174, "lr": 4.106821934793373e-05, "epoch": 7.0005500550055, "percentage": 35.0, "elapsed_time": "2:30:37", "remaining_time": "4:39:42", "throughput": 1485.85, "total_tokens": 13428736} {"current_steps": 63640, "total_steps": 181800, "loss": 0.0092, "lr": 4.10663805968638e-05, "epoch": 7.001100110011001, "percentage": 35.01, "elapsed_time": "2:30:38", "remaining_time": "4:39:41", "throughput": 1485.84, "total_tokens": 13429728} {"current_steps": 63645, "total_steps": 181800, "loss": 0.0046, "lr": 4.1064541697717754e-05, "epoch": 7.0016501650165015, "percentage": 35.01, "elapsed_time": "2:30:39", "remaining_time": "4:39:40", "throughput": 1485.85, "total_tokens": 13430816} {"current_steps": 63650, "total_steps": 181800, "loss": 0.0364, "lr": 4.1062702650512516e-05, "epoch": 7.002200220022003, "percentage": 35.01, "elapsed_time": "2:30:39", "remaining_time": "4:39:40", "throughput": 1485.85, "total_tokens": 13431904} {"current_steps": 63655, "total_steps": 181800, "loss": 0.2089, "lr": 4.1060863455265075e-05, "epoch": 7.002750275027503, "percentage": 35.01, "elapsed_time": "2:30:40", "remaining_time": "4:39:39", "throughput": 1485.86, "total_tokens": 13433024} {"current_steps": 63660, "total_steps": 181800, "loss": 0.0493, "lr": 4.105902411199236e-05, "epoch": 7.003300330033003, "percentage": 35.02, "elapsed_time": "2:30:41", "remaining_time": "4:39:38", "throughput": 1485.86, "total_tokens": 13434080} {"current_steps": 63665, "total_steps": 181800, "loss": 0.054, "lr": 4.1057184620711314e-05, "epoch": 7.003850385038504, "percentage": 35.02, "elapsed_time": "2:30:41", "remaining_time": "4:39:38", "throughput": 1485.86, "total_tokens": 13435104} {"current_steps": 63670, "total_steps": 181800, "loss": 0.0426, "lr": 4.105534498143891e-05, "epoch": 7.004400440044004, "percentage": 35.02, "elapsed_time": "2:30:42", "remaining_time": "4:39:37", "throughput": 1485.85, "total_tokens": 13436128} {"current_steps": 63675, "total_steps": 181800, "loss": 0.0373, "lr": 4.105350519419209e-05, "epoch": 7.0049504950495045, "percentage": 35.02, "elapsed_time": "2:30:43", "remaining_time": "4:39:36", "throughput": 1485.84, "total_tokens": 13437184} {"current_steps": 63680, "total_steps": 181800, "loss": 0.044, "lr": 4.105166525898783e-05, "epoch": 7.005500550055006, "percentage": 35.03, "elapsed_time": "2:30:44", "remaining_time": "4:39:36", "throughput": 1485.84, "total_tokens": 13438208} {"current_steps": 63685, "total_steps": 181800, "loss": 0.0265, "lr": 4.104982517584306e-05, "epoch": 7.006050605060506, "percentage": 35.03, "elapsed_time": "2:30:44", "remaining_time": "4:39:35", "throughput": 1485.85, "total_tokens": 13439328} {"current_steps": 63690, "total_steps": 181800, "loss": 0.0281, "lr": 4.1047984944774756e-05, "epoch": 7.006600660066007, "percentage": 35.03, "elapsed_time": "2:30:45", "remaining_time": "4:39:34", "throughput": 1485.84, "total_tokens": 13440352} {"current_steps": 63695, "total_steps": 181800, "loss": 0.0597, "lr": 4.104614456579987e-05, "epoch": 7.007150715071507, "percentage": 35.04, "elapsed_time": "2:30:46", "remaining_time": "4:39:33", "throughput": 1485.84, "total_tokens": 13441344} {"current_steps": 63700, "total_steps": 181800, "loss": 0.0646, "lr": 4.104430403893538e-05, "epoch": 7.007700770077007, "percentage": 35.04, "elapsed_time": "2:30:47", "remaining_time": "4:39:33", "throughput": 1485.84, "total_tokens": 13442400} {"current_steps": 63705, "total_steps": 181800, "loss": 0.0246, "lr": 4.104246336419824e-05, "epoch": 7.008250825082508, "percentage": 35.04, "elapsed_time": "2:30:47", "remaining_time": "4:39:32", "throughput": 1485.84, "total_tokens": 13443456} {"current_steps": 63710, "total_steps": 181800, "loss": 0.0055, "lr": 4.10406225416054e-05, "epoch": 7.008800880088009, "percentage": 35.04, "elapsed_time": "2:30:48", "remaining_time": "4:39:31", "throughput": 1485.84, "total_tokens": 13444448} {"current_steps": 63715, "total_steps": 181800, "loss": 0.0756, "lr": 4.1038781571173844e-05, "epoch": 7.00935093509351, "percentage": 35.05, "elapsed_time": "2:30:49", "remaining_time": "4:39:30", "throughput": 1485.83, "total_tokens": 13445440} {"current_steps": 63720, "total_steps": 181800, "loss": 0.0701, "lr": 4.1036940452920534e-05, "epoch": 7.00990099009901, "percentage": 35.05, "elapsed_time": "2:30:49", "remaining_time": "4:39:30", "throughput": 1485.83, "total_tokens": 13446432} {"current_steps": 63725, "total_steps": 181800, "loss": 0.067, "lr": 4.103509918686245e-05, "epoch": 7.01045104510451, "percentage": 35.05, "elapsed_time": "2:30:50", "remaining_time": "4:39:29", "throughput": 1485.83, "total_tokens": 13447456} {"current_steps": 63730, "total_steps": 181800, "loss": 0.0149, "lr": 4.103325777301654e-05, "epoch": 7.011001100110011, "percentage": 35.06, "elapsed_time": "2:30:51", "remaining_time": "4:39:28", "throughput": 1485.84, "total_tokens": 13448544} {"current_steps": 63735, "total_steps": 181800, "loss": 0.0125, "lr": 4.1031416211399785e-05, "epoch": 7.011551155115511, "percentage": 35.06, "elapsed_time": "2:30:51", "remaining_time": "4:39:27", "throughput": 1485.84, "total_tokens": 13449632} {"current_steps": 63740, "total_steps": 181800, "loss": 0.0453, "lr": 4.1029574502029164e-05, "epoch": 7.0121012101210125, "percentage": 35.06, "elapsed_time": "2:30:52", "remaining_time": "4:39:27", "throughput": 1485.85, "total_tokens": 13450688} {"current_steps": 63745, "total_steps": 181800, "loss": 0.3208, "lr": 4.1027732644921644e-05, "epoch": 7.012651265126513, "percentage": 35.06, "elapsed_time": "2:30:53", "remaining_time": "4:39:26", "throughput": 1485.85, "total_tokens": 13451744} {"current_steps": 63750, "total_steps": 181800, "loss": 0.0241, "lr": 4.102589064009421e-05, "epoch": 7.013201320132013, "percentage": 35.07, "elapsed_time": "2:30:53", "remaining_time": "4:39:25", "throughput": 1485.85, "total_tokens": 13452736} {"current_steps": 63755, "total_steps": 181800, "loss": 0.0441, "lr": 4.102404848756382e-05, "epoch": 7.013751375137514, "percentage": 35.07, "elapsed_time": "2:30:54", "remaining_time": "4:39:24", "throughput": 1485.85, "total_tokens": 13453792} {"current_steps": 63760, "total_steps": 181800, "loss": 0.0529, "lr": 4.102220618734748e-05, "epoch": 7.014301430143014, "percentage": 35.07, "elapsed_time": "2:30:55", "remaining_time": "4:39:24", "throughput": 1485.85, "total_tokens": 13454848} {"current_steps": 63765, "total_steps": 181800, "loss": 0.0104, "lr": 4.1020363739462145e-05, "epoch": 7.014851485148514, "percentage": 35.07, "elapsed_time": "2:30:55", "remaining_time": "4:39:23", "throughput": 1485.85, "total_tokens": 13455872} {"current_steps": 63770, "total_steps": 181800, "loss": 0.0523, "lr": 4.101852114392481e-05, "epoch": 7.0154015401540155, "percentage": 35.08, "elapsed_time": "2:30:56", "remaining_time": "4:39:22", "throughput": 1485.86, "total_tokens": 13456960} {"current_steps": 63775, "total_steps": 181800, "loss": 0.1455, "lr": 4.101667840075244e-05, "epoch": 7.015951595159516, "percentage": 35.08, "elapsed_time": "2:30:57", "remaining_time": "4:39:22", "throughput": 1485.86, "total_tokens": 13457952} {"current_steps": 63780, "total_steps": 181800, "loss": 0.0532, "lr": 4.101483550996204e-05, "epoch": 7.016501650165017, "percentage": 35.08, "elapsed_time": "2:30:58", "remaining_time": "4:39:21", "throughput": 1485.85, "total_tokens": 13458944} {"current_steps": 63785, "total_steps": 181800, "loss": 0.0116, "lr": 4.1012992471570584e-05, "epoch": 7.017051705170517, "percentage": 35.09, "elapsed_time": "2:30:58", "remaining_time": "4:39:20", "throughput": 1485.85, "total_tokens": 13460000} {"current_steps": 63790, "total_steps": 181800, "loss": 0.0039, "lr": 4.101114928559506e-05, "epoch": 7.017601760176017, "percentage": 35.09, "elapsed_time": "2:30:59", "remaining_time": "4:39:19", "throughput": 1485.86, "total_tokens": 13461056} {"current_steps": 63795, "total_steps": 181800, "loss": 0.092, "lr": 4.100930595205246e-05, "epoch": 7.018151815181518, "percentage": 35.09, "elapsed_time": "2:31:00", "remaining_time": "4:39:19", "throughput": 1485.85, "total_tokens": 13462048} {"current_steps": 63800, "total_steps": 181800, "loss": 0.0533, "lr": 4.100746247095976e-05, "epoch": 7.0187018701870185, "percentage": 35.09, "elapsed_time": "2:31:00", "remaining_time": "4:39:18", "throughput": 1485.85, "total_tokens": 13463040} {"current_steps": 63805, "total_steps": 181800, "loss": 0.0532, "lr": 4.100561884233396e-05, "epoch": 7.01925192519252, "percentage": 35.1, "elapsed_time": "2:31:01", "remaining_time": "4:39:17", "throughput": 1485.85, "total_tokens": 13464096} {"current_steps": 63810, "total_steps": 181800, "loss": 0.0583, "lr": 4.1003775066192054e-05, "epoch": 7.01980198019802, "percentage": 35.1, "elapsed_time": "2:31:02", "remaining_time": "4:39:16", "throughput": 1485.86, "total_tokens": 13465184} {"current_steps": 63815, "total_steps": 181800, "loss": 0.0101, "lr": 4.100193114255104e-05, "epoch": 7.02035203520352, "percentage": 35.1, "elapsed_time": "2:31:02", "remaining_time": "4:39:16", "throughput": 1485.86, "total_tokens": 13466208} {"current_steps": 63820, "total_steps": 181800, "loss": 0.0463, "lr": 4.1000087071427895e-05, "epoch": 7.020902090209021, "percentage": 35.1, "elapsed_time": "2:31:03", "remaining_time": "4:39:15", "throughput": 1485.86, "total_tokens": 13467232} {"current_steps": 63825, "total_steps": 181800, "loss": 0.0309, "lr": 4.099824285283963e-05, "epoch": 7.021452145214521, "percentage": 35.11, "elapsed_time": "2:31:04", "remaining_time": "4:39:14", "throughput": 1485.87, "total_tokens": 13468320} {"current_steps": 63830, "total_steps": 181800, "loss": 0.055, "lr": 4.099639848680324e-05, "epoch": 7.022002200220022, "percentage": 35.11, "elapsed_time": "2:31:04", "remaining_time": "4:39:13", "throughput": 1485.87, "total_tokens": 13469312} {"current_steps": 63835, "total_steps": 181800, "loss": 0.0232, "lr": 4.099455397333572e-05, "epoch": 7.022552255225523, "percentage": 35.11, "elapsed_time": "2:31:05", "remaining_time": "4:39:13", "throughput": 1485.87, "total_tokens": 13470400} {"current_steps": 63840, "total_steps": 181800, "loss": 0.0346, "lr": 4.0992709312454065e-05, "epoch": 7.023102310231023, "percentage": 35.12, "elapsed_time": "2:31:06", "remaining_time": "4:39:12", "throughput": 1485.87, "total_tokens": 13471392} {"current_steps": 63845, "total_steps": 181800, "loss": 0.0251, "lr": 4.099086450417528e-05, "epoch": 7.023652365236524, "percentage": 35.12, "elapsed_time": "2:31:07", "remaining_time": "4:39:11", "throughput": 1485.87, "total_tokens": 13472416} {"current_steps": 63850, "total_steps": 181800, "loss": 0.047, "lr": 4.098901954851638e-05, "epoch": 7.024202420242024, "percentage": 35.12, "elapsed_time": "2:31:07", "remaining_time": "4:39:10", "throughput": 1485.88, "total_tokens": 13473504} {"current_steps": 63855, "total_steps": 181800, "loss": 0.0424, "lr": 4.098717444549436e-05, "epoch": 7.024752475247524, "percentage": 35.12, "elapsed_time": "2:31:08", "remaining_time": "4:39:10", "throughput": 1485.88, "total_tokens": 13474592} {"current_steps": 63860, "total_steps": 181800, "loss": 0.0151, "lr": 4.098532919512622e-05, "epoch": 7.025302530253025, "percentage": 35.13, "elapsed_time": "2:31:09", "remaining_time": "4:39:09", "throughput": 1485.88, "total_tokens": 13475616} {"current_steps": 63865, "total_steps": 181800, "loss": 0.0341, "lr": 4.098348379742897e-05, "epoch": 7.025852585258526, "percentage": 35.13, "elapsed_time": "2:31:09", "remaining_time": "4:39:08", "throughput": 1485.89, "total_tokens": 13476672} {"current_steps": 63870, "total_steps": 181800, "loss": 0.0149, "lr": 4.098163825241962e-05, "epoch": 7.026402640264027, "percentage": 35.13, "elapsed_time": "2:31:10", "remaining_time": "4:39:07", "throughput": 1485.89, "total_tokens": 13477728} {"current_steps": 63875, "total_steps": 181800, "loss": 0.0346, "lr": 4.0979792560115175e-05, "epoch": 7.026952695269527, "percentage": 35.13, "elapsed_time": "2:31:11", "remaining_time": "4:39:07", "throughput": 1485.9, "total_tokens": 13478784} {"current_steps": 63880, "total_steps": 181800, "loss": 0.135, "lr": 4.0977946720532654e-05, "epoch": 7.027502750275027, "percentage": 35.14, "elapsed_time": "2:31:11", "remaining_time": "4:39:06", "throughput": 1485.89, "total_tokens": 13479744} {"current_steps": 63885, "total_steps": 181800, "loss": 0.1318, "lr": 4.0976100733689065e-05, "epoch": 7.028052805280528, "percentage": 35.14, "elapsed_time": "2:31:12", "remaining_time": "4:39:05", "throughput": 1485.89, "total_tokens": 13480800} {"current_steps": 63890, "total_steps": 181800, "loss": 0.0065, "lr": 4.097425459960142e-05, "epoch": 7.028602860286028, "percentage": 35.14, "elapsed_time": "2:31:13", "remaining_time": "4:39:04", "throughput": 1485.9, "total_tokens": 13481888} {"current_steps": 63895, "total_steps": 181800, "loss": 0.0632, "lr": 4.0972408318286734e-05, "epoch": 7.0291529152915295, "percentage": 35.15, "elapsed_time": "2:31:13", "remaining_time": "4:39:04", "throughput": 1485.91, "total_tokens": 13482976} {"current_steps": 63900, "total_steps": 181800, "loss": 0.0493, "lr": 4.0970561889762036e-05, "epoch": 7.02970297029703, "percentage": 35.15, "elapsed_time": "2:31:14", "remaining_time": "4:39:03", "throughput": 1485.91, "total_tokens": 13484064} {"current_steps": 63905, "total_steps": 181800, "loss": 0.0236, "lr": 4.0968715314044323e-05, "epoch": 7.03025302530253, "percentage": 35.15, "elapsed_time": "2:31:15", "remaining_time": "4:39:02", "throughput": 1485.92, "total_tokens": 13485184} {"current_steps": 63910, "total_steps": 181800, "loss": 0.0205, "lr": 4.096686859115062e-05, "epoch": 7.030803080308031, "percentage": 35.15, "elapsed_time": "2:31:15", "remaining_time": "4:39:01", "throughput": 1485.92, "total_tokens": 13486144} {"current_steps": 63915, "total_steps": 181800, "loss": 0.0981, "lr": 4.096502172109796e-05, "epoch": 7.031353135313531, "percentage": 35.16, "elapsed_time": "2:31:16", "remaining_time": "4:39:01", "throughput": 1485.92, "total_tokens": 13487168} {"current_steps": 63920, "total_steps": 181800, "loss": 0.0221, "lr": 4.096317470390335e-05, "epoch": 7.031903190319032, "percentage": 35.16, "elapsed_time": "2:31:17", "remaining_time": "4:39:00", "throughput": 1485.92, "total_tokens": 13488192} {"current_steps": 63925, "total_steps": 181800, "loss": 0.0032, "lr": 4.0961327539583824e-05, "epoch": 7.0324532453245325, "percentage": 35.16, "elapsed_time": "2:31:18", "remaining_time": "4:38:59", "throughput": 1485.91, "total_tokens": 13489184} {"current_steps": 63930, "total_steps": 181800, "loss": 0.0435, "lr": 4.09594802281564e-05, "epoch": 7.033003300330033, "percentage": 35.17, "elapsed_time": "2:31:18", "remaining_time": "4:38:58", "throughput": 1485.91, "total_tokens": 13490208} {"current_steps": 63935, "total_steps": 181800, "loss": 0.0024, "lr": 4.09576327696381e-05, "epoch": 7.033553355335534, "percentage": 35.17, "elapsed_time": "2:31:19", "remaining_time": "4:38:58", "throughput": 1485.92, "total_tokens": 13491264} {"current_steps": 63940, "total_steps": 181800, "loss": 0.0405, "lr": 4.095578516404596e-05, "epoch": 7.034103410341034, "percentage": 35.17, "elapsed_time": "2:31:20", "remaining_time": "4:38:57", "throughput": 1485.92, "total_tokens": 13492320} {"current_steps": 63945, "total_steps": 181800, "loss": 0.0461, "lr": 4.0953937411397e-05, "epoch": 7.034653465346534, "percentage": 35.17, "elapsed_time": "2:31:20", "remaining_time": "4:38:56", "throughput": 1485.94, "total_tokens": 13493472} {"current_steps": 63950, "total_steps": 181800, "loss": 0.0155, "lr": 4.095208951170826e-05, "epoch": 7.035203520352035, "percentage": 35.18, "elapsed_time": "2:31:21", "remaining_time": "4:38:55", "throughput": 1485.94, "total_tokens": 13494528} {"current_steps": 63955, "total_steps": 181800, "loss": 0.0334, "lr": 4.095024146499675e-05, "epoch": 7.0357535753575355, "percentage": 35.18, "elapsed_time": "2:31:22", "remaining_time": "4:38:55", "throughput": 1485.95, "total_tokens": 13495616} {"current_steps": 63960, "total_steps": 181800, "loss": 0.0741, "lr": 4.094839327127954e-05, "epoch": 7.036303630363037, "percentage": 35.18, "elapsed_time": "2:31:22", "remaining_time": "4:38:54", "throughput": 1485.95, "total_tokens": 13496704} {"current_steps": 63965, "total_steps": 181800, "loss": 0.0038, "lr": 4.094654493057363e-05, "epoch": 7.036853685368537, "percentage": 35.18, "elapsed_time": "2:31:23", "remaining_time": "4:38:53", "throughput": 1485.95, "total_tokens": 13497728} {"current_steps": 63970, "total_steps": 181800, "loss": 0.0959, "lr": 4.094469644289607e-05, "epoch": 7.037403740374037, "percentage": 35.19, "elapsed_time": "2:31:24", "remaining_time": "4:38:52", "throughput": 1485.96, "total_tokens": 13498816} {"current_steps": 63975, "total_steps": 181800, "loss": 0.0284, "lr": 4.094284780826389e-05, "epoch": 7.037953795379538, "percentage": 35.19, "elapsed_time": "2:31:24", "remaining_time": "4:38:52", "throughput": 1485.96, "total_tokens": 13499840} {"current_steps": 63980, "total_steps": 181800, "loss": 0.0073, "lr": 4.094099902669414e-05, "epoch": 7.038503850385038, "percentage": 35.19, "elapsed_time": "2:31:25", "remaining_time": "4:38:51", "throughput": 1485.97, "total_tokens": 13500928} {"current_steps": 63985, "total_steps": 181800, "loss": 0.003, "lr": 4.093915009820385e-05, "epoch": 7.039053905390539, "percentage": 35.2, "elapsed_time": "2:31:26", "remaining_time": "4:38:50", "throughput": 1485.98, "total_tokens": 13502048} {"current_steps": 63990, "total_steps": 181800, "loss": 0.0052, "lr": 4.0937301022810056e-05, "epoch": 7.03960396039604, "percentage": 35.2, "elapsed_time": "2:31:27", "remaining_time": "4:38:49", "throughput": 1485.97, "total_tokens": 13503040} {"current_steps": 63995, "total_steps": 181800, "loss": 0.0049, "lr": 4.093545180052981e-05, "epoch": 7.04015401540154, "percentage": 35.2, "elapsed_time": "2:31:27", "remaining_time": "4:38:49", "throughput": 1485.98, "total_tokens": 13504128} {"current_steps": 64000, "total_steps": 181800, "loss": 0.0236, "lr": 4.093360243138015e-05, "epoch": 7.040704070407041, "percentage": 35.2, "elapsed_time": "2:31:28", "remaining_time": "4:38:48", "throughput": 1485.98, "total_tokens": 13505184} {"current_steps": 64005, "total_steps": 181800, "loss": 0.0686, "lr": 4.093175291537812e-05, "epoch": 7.041254125412541, "percentage": 35.21, "elapsed_time": "2:31:29", "remaining_time": "4:38:47", "throughput": 1485.99, "total_tokens": 13506272} {"current_steps": 64010, "total_steps": 181800, "loss": 0.0834, "lr": 4.092990325254077e-05, "epoch": 7.041804180418042, "percentage": 35.21, "elapsed_time": "2:31:29", "remaining_time": "4:38:46", "throughput": 1485.99, "total_tokens": 13507328} {"current_steps": 64015, "total_steps": 181800, "loss": 0.0315, "lr": 4.0928053442885146e-05, "epoch": 7.042354235423542, "percentage": 35.21, "elapsed_time": "2:31:30", "remaining_time": "4:38:46", "throughput": 1485.99, "total_tokens": 13508384} {"current_steps": 64020, "total_steps": 181800, "loss": 0.1215, "lr": 4.09262034864283e-05, "epoch": 7.042904290429043, "percentage": 35.21, "elapsed_time": "2:31:31", "remaining_time": "4:38:45", "throughput": 1486.0, "total_tokens": 13509440} {"current_steps": 64025, "total_steps": 181800, "loss": 0.0649, "lr": 4.0924353383187265e-05, "epoch": 7.043454345434544, "percentage": 35.22, "elapsed_time": "2:31:31", "remaining_time": "4:38:44", "throughput": 1486.01, "total_tokens": 13510528} {"current_steps": 64030, "total_steps": 181800, "loss": 0.0281, "lr": 4.0922503133179114e-05, "epoch": 7.044004400440044, "percentage": 35.22, "elapsed_time": "2:31:32", "remaining_time": "4:38:43", "throughput": 1486.01, "total_tokens": 13511584} {"current_steps": 64035, "total_steps": 181800, "loss": 0.0129, "lr": 4.09206527364209e-05, "epoch": 7.044554455445544, "percentage": 35.22, "elapsed_time": "2:31:33", "remaining_time": "4:38:43", "throughput": 1486.01, "total_tokens": 13512640} {"current_steps": 64040, "total_steps": 181800, "loss": 0.0187, "lr": 4.091880219292966e-05, "epoch": 7.045104510451045, "percentage": 35.23, "elapsed_time": "2:31:33", "remaining_time": "4:38:42", "throughput": 1486.01, "total_tokens": 13513632} {"current_steps": 64045, "total_steps": 181800, "loss": 0.0105, "lr": 4.0916951502722464e-05, "epoch": 7.0456545654565454, "percentage": 35.23, "elapsed_time": "2:31:34", "remaining_time": "4:38:41", "throughput": 1486.01, "total_tokens": 13514656} {"current_steps": 64050, "total_steps": 181800, "loss": 0.0228, "lr": 4.091510066581636e-05, "epoch": 7.0462046204620465, "percentage": 35.23, "elapsed_time": "2:31:35", "remaining_time": "4:38:40", "throughput": 1486.01, "total_tokens": 13515680} {"current_steps": 64055, "total_steps": 181800, "loss": 0.0149, "lr": 4.091324968222841e-05, "epoch": 7.046754675467547, "percentage": 35.23, "elapsed_time": "2:31:35", "remaining_time": "4:38:40", "throughput": 1486.01, "total_tokens": 13516736} {"current_steps": 64060, "total_steps": 181800, "loss": 0.0095, "lr": 4.091139855197568e-05, "epoch": 7.047304730473047, "percentage": 35.24, "elapsed_time": "2:31:36", "remaining_time": "4:38:39", "throughput": 1486.02, "total_tokens": 13517824} {"current_steps": 64065, "total_steps": 181800, "loss": 0.0819, "lr": 4.090954727507522e-05, "epoch": 7.047854785478548, "percentage": 35.24, "elapsed_time": "2:31:37", "remaining_time": "4:38:38", "throughput": 1486.02, "total_tokens": 13518848} {"current_steps": 64070, "total_steps": 181800, "loss": 0.0144, "lr": 4.090769585154409e-05, "epoch": 7.048404840484048, "percentage": 35.24, "elapsed_time": "2:31:38", "remaining_time": "4:38:37", "throughput": 1486.02, "total_tokens": 13519904} {"current_steps": 64075, "total_steps": 181800, "loss": 0.0249, "lr": 4.090584428139937e-05, "epoch": 7.048954895489549, "percentage": 35.24, "elapsed_time": "2:31:38", "remaining_time": "4:38:37", "throughput": 1486.03, "total_tokens": 13520960} {"current_steps": 64080, "total_steps": 181800, "loss": 0.0275, "lr": 4.0903992564658114e-05, "epoch": 7.0495049504950495, "percentage": 35.25, "elapsed_time": "2:31:39", "remaining_time": "4:38:36", "throughput": 1486.03, "total_tokens": 13522016} {"current_steps": 64085, "total_steps": 181800, "loss": 0.0092, "lr": 4.090214070133739e-05, "epoch": 7.05005500550055, "percentage": 35.25, "elapsed_time": "2:31:40", "remaining_time": "4:38:35", "throughput": 1486.03, "total_tokens": 13523040} {"current_steps": 64090, "total_steps": 181800, "loss": 0.0116, "lr": 4.090028869145426e-05, "epoch": 7.050605060506051, "percentage": 35.25, "elapsed_time": "2:31:40", "remaining_time": "4:38:34", "throughput": 1486.03, "total_tokens": 13524064} {"current_steps": 64095, "total_steps": 181800, "loss": 0.0527, "lr": 4.0898436535025806e-05, "epoch": 7.051155115511551, "percentage": 35.26, "elapsed_time": "2:31:41", "remaining_time": "4:38:34", "throughput": 1486.04, "total_tokens": 13525184} {"current_steps": 64100, "total_steps": 181800, "loss": 0.022, "lr": 4.0896584232069084e-05, "epoch": 7.051705170517051, "percentage": 35.26, "elapsed_time": "2:31:42", "remaining_time": "4:38:33", "throughput": 1486.04, "total_tokens": 13526208} {"current_steps": 64105, "total_steps": 181800, "loss": 0.1603, "lr": 4.089473178260118e-05, "epoch": 7.052255225522552, "percentage": 35.26, "elapsed_time": "2:31:42", "remaining_time": "4:38:32", "throughput": 1486.05, "total_tokens": 13527264} {"current_steps": 64110, "total_steps": 181800, "loss": 0.0319, "lr": 4.089287918663916e-05, "epoch": 7.052805280528053, "percentage": 35.26, "elapsed_time": "2:31:43", "remaining_time": "4:38:31", "throughput": 1486.04, "total_tokens": 13528256} {"current_steps": 64115, "total_steps": 181800, "loss": 0.0113, "lr": 4.08910264442001e-05, "epoch": 7.053355335533554, "percentage": 35.27, "elapsed_time": "2:31:44", "remaining_time": "4:38:31", "throughput": 1486.05, "total_tokens": 13529312} {"current_steps": 64120, "total_steps": 181800, "loss": 0.0077, "lr": 4.0889173555301066e-05, "epoch": 7.053905390539054, "percentage": 35.27, "elapsed_time": "2:31:44", "remaining_time": "4:38:30", "throughput": 1486.06, "total_tokens": 13530464} {"current_steps": 64125, "total_steps": 181800, "loss": 0.1716, "lr": 4.088732051995915e-05, "epoch": 7.054455445544554, "percentage": 35.27, "elapsed_time": "2:31:45", "remaining_time": "4:38:29", "throughput": 1486.07, "total_tokens": 13531552} {"current_steps": 64130, "total_steps": 181800, "loss": 0.0277, "lr": 4.0885467338191426e-05, "epoch": 7.055005500550055, "percentage": 35.28, "elapsed_time": "2:31:46", "remaining_time": "4:38:28", "throughput": 1486.07, "total_tokens": 13532640} {"current_steps": 64135, "total_steps": 181800, "loss": 0.0585, "lr": 4.0883614010014966e-05, "epoch": 7.055555555555555, "percentage": 35.28, "elapsed_time": "2:31:46", "remaining_time": "4:38:28", "throughput": 1486.07, "total_tokens": 13533664} {"current_steps": 64140, "total_steps": 181800, "loss": 0.0185, "lr": 4.088176053544686e-05, "epoch": 7.0561056105610565, "percentage": 35.28, "elapsed_time": "2:31:47", "remaining_time": "4:38:27", "throughput": 1486.08, "total_tokens": 13534752} {"current_steps": 64145, "total_steps": 181800, "loss": 0.0624, "lr": 4.087990691450419e-05, "epoch": 7.056655665566557, "percentage": 35.28, "elapsed_time": "2:31:48", "remaining_time": "4:38:26", "throughput": 1486.08, "total_tokens": 13535776} {"current_steps": 64150, "total_steps": 181800, "loss": 0.0444, "lr": 4.087805314720403e-05, "epoch": 7.057205720572057, "percentage": 35.29, "elapsed_time": "2:31:49", "remaining_time": "4:38:25", "throughput": 1486.08, "total_tokens": 13536800} {"current_steps": 64155, "total_steps": 181800, "loss": 0.0249, "lr": 4.0876199233563485e-05, "epoch": 7.057755775577558, "percentage": 35.29, "elapsed_time": "2:31:49", "remaining_time": "4:38:25", "throughput": 1486.08, "total_tokens": 13537888} {"current_steps": 64160, "total_steps": 181800, "loss": 0.0423, "lr": 4.0874345173599625e-05, "epoch": 7.058305830583058, "percentage": 35.29, "elapsed_time": "2:31:50", "remaining_time": "4:38:24", "throughput": 1486.09, "total_tokens": 13538944} {"current_steps": 64165, "total_steps": 181800, "loss": 0.0092, "lr": 4.087249096732954e-05, "epoch": 7.058855885588559, "percentage": 35.29, "elapsed_time": "2:31:51", "remaining_time": "4:38:23", "throughput": 1486.08, "total_tokens": 13539936} {"current_steps": 64170, "total_steps": 181800, "loss": 0.0913, "lr": 4.0870636614770326e-05, "epoch": 7.0594059405940595, "percentage": 35.3, "elapsed_time": "2:31:51", "remaining_time": "4:38:22", "throughput": 1486.09, "total_tokens": 13541024} {"current_steps": 64175, "total_steps": 181800, "loss": 0.0179, "lr": 4.0868782115939066e-05, "epoch": 7.05995599559956, "percentage": 35.3, "elapsed_time": "2:31:52", "remaining_time": "4:38:22", "throughput": 1486.09, "total_tokens": 13542016} {"current_steps": 64180, "total_steps": 181800, "loss": 0.0074, "lr": 4.0866927470852856e-05, "epoch": 7.060506050605061, "percentage": 35.3, "elapsed_time": "2:31:53", "remaining_time": "4:38:21", "throughput": 1486.09, "total_tokens": 13543072} {"current_steps": 64185, "total_steps": 181800, "loss": 0.0036, "lr": 4.086507267952879e-05, "epoch": 7.061056105610561, "percentage": 35.31, "elapsed_time": "2:31:53", "remaining_time": "4:38:20", "throughput": 1486.1, "total_tokens": 13544160} {"current_steps": 64190, "total_steps": 181800, "loss": 0.0668, "lr": 4.086321774198397e-05, "epoch": 7.061606160616061, "percentage": 35.31, "elapsed_time": "2:31:54", "remaining_time": "4:38:19", "throughput": 1486.1, "total_tokens": 13545216} {"current_steps": 64195, "total_steps": 181800, "loss": 0.0068, "lr": 4.086136265823547e-05, "epoch": 7.062156215621562, "percentage": 35.31, "elapsed_time": "2:31:55", "remaining_time": "4:38:19", "throughput": 1486.1, "total_tokens": 13546208} {"current_steps": 64200, "total_steps": 181800, "loss": 0.0674, "lr": 4.085950742830042e-05, "epoch": 7.0627062706270625, "percentage": 35.31, "elapsed_time": "2:31:55", "remaining_time": "4:38:18", "throughput": 1486.1, "total_tokens": 13547264} {"current_steps": 64205, "total_steps": 181800, "loss": 0.0246, "lr": 4.085765205219588e-05, "epoch": 7.063256325632564, "percentage": 35.32, "elapsed_time": "2:31:56", "remaining_time": "4:38:17", "throughput": 1486.11, "total_tokens": 13548352} {"current_steps": 64210, "total_steps": 181800, "loss": 0.0159, "lr": 4.0855796529938986e-05, "epoch": 7.063806380638064, "percentage": 35.32, "elapsed_time": "2:31:57", "remaining_time": "4:38:16", "throughput": 1486.11, "total_tokens": 13549344} {"current_steps": 64215, "total_steps": 181800, "loss": 0.0468, "lr": 4.085394086154681e-05, "epoch": 7.064356435643564, "percentage": 35.32, "elapsed_time": "2:31:58", "remaining_time": "4:38:16", "throughput": 1486.11, "total_tokens": 13550400} {"current_steps": 64220, "total_steps": 181800, "loss": 0.1071, "lr": 4.085208504703647e-05, "epoch": 7.064906490649065, "percentage": 35.32, "elapsed_time": "2:31:58", "remaining_time": "4:38:15", "throughput": 1486.12, "total_tokens": 13551520} {"current_steps": 64225, "total_steps": 181800, "loss": 0.151, "lr": 4.085022908642508e-05, "epoch": 7.065456545654565, "percentage": 35.33, "elapsed_time": "2:31:59", "remaining_time": "4:38:14", "throughput": 1486.12, "total_tokens": 13552544} {"current_steps": 64230, "total_steps": 181800, "loss": 0.0463, "lr": 4.084837297972973e-05, "epoch": 7.066006600660066, "percentage": 35.33, "elapsed_time": "2:32:00", "remaining_time": "4:38:13", "throughput": 1486.11, "total_tokens": 13553536} {"current_steps": 64235, "total_steps": 181800, "loss": 0.0251, "lr": 4.0846516726967524e-05, "epoch": 7.066556655665567, "percentage": 35.33, "elapsed_time": "2:32:00", "remaining_time": "4:38:13", "throughput": 1486.12, "total_tokens": 13554592} {"current_steps": 64240, "total_steps": 181800, "loss": 0.0202, "lr": 4.084466032815558e-05, "epoch": 7.067106710671067, "percentage": 35.34, "elapsed_time": "2:32:01", "remaining_time": "4:38:12", "throughput": 1486.13, "total_tokens": 13555712} {"current_steps": 64245, "total_steps": 181800, "loss": 0.0145, "lr": 4.0842803783311014e-05, "epoch": 7.067656765676568, "percentage": 35.34, "elapsed_time": "2:32:02", "remaining_time": "4:38:11", "throughput": 1486.13, "total_tokens": 13556768} {"current_steps": 64250, "total_steps": 181800, "loss": 0.0107, "lr": 4.084094709245092e-05, "epoch": 7.068206820682068, "percentage": 35.34, "elapsed_time": "2:32:02", "remaining_time": "4:38:10", "throughput": 1486.14, "total_tokens": 13557856} {"current_steps": 64255, "total_steps": 181800, "loss": 0.0179, "lr": 4.0839090255592415e-05, "epoch": 7.068756875687569, "percentage": 35.34, "elapsed_time": "2:32:03", "remaining_time": "4:38:10", "throughput": 1486.14, "total_tokens": 13558880} {"current_steps": 64260, "total_steps": 181800, "loss": 0.0499, "lr": 4.083723327275262e-05, "epoch": 7.069306930693069, "percentage": 35.35, "elapsed_time": "2:32:04", "remaining_time": "4:38:09", "throughput": 1486.15, "total_tokens": 13560000} {"current_steps": 64265, "total_steps": 181800, "loss": 0.0722, "lr": 4.083537614394865e-05, "epoch": 7.06985698569857, "percentage": 35.35, "elapsed_time": "2:32:04", "remaining_time": "4:38:08", "throughput": 1486.16, "total_tokens": 13561120} {"current_steps": 64270, "total_steps": 181800, "loss": 0.0134, "lr": 4.083351886919761e-05, "epoch": 7.070407040704071, "percentage": 35.35, "elapsed_time": "2:32:05", "remaining_time": "4:38:07", "throughput": 1486.17, "total_tokens": 13562208} {"current_steps": 64275, "total_steps": 181800, "loss": 0.0116, "lr": 4.083166144851662e-05, "epoch": 7.070957095709571, "percentage": 35.35, "elapsed_time": "2:32:06", "remaining_time": "4:38:07", "throughput": 1486.18, "total_tokens": 13563328} {"current_steps": 64280, "total_steps": 181800, "loss": 0.1586, "lr": 4.0829803881922805e-05, "epoch": 7.071507150715071, "percentage": 35.36, "elapsed_time": "2:32:06", "remaining_time": "4:38:06", "throughput": 1486.18, "total_tokens": 13564352} {"current_steps": 64285, "total_steps": 181800, "loss": 0.0078, "lr": 4.082794616943329e-05, "epoch": 7.072057205720572, "percentage": 35.36, "elapsed_time": "2:32:07", "remaining_time": "4:38:05", "throughput": 1486.18, "total_tokens": 13565376} {"current_steps": 64290, "total_steps": 181800, "loss": 0.0856, "lr": 4.0826088311065185e-05, "epoch": 7.072607260726072, "percentage": 35.36, "elapsed_time": "2:32:08", "remaining_time": "4:38:04", "throughput": 1486.18, "total_tokens": 13566432} {"current_steps": 64295, "total_steps": 181800, "loss": 0.0184, "lr": 4.082423030683562e-05, "epoch": 7.0731573157315735, "percentage": 35.37, "elapsed_time": "2:32:09", "remaining_time": "4:38:04", "throughput": 1486.19, "total_tokens": 13567488} {"current_steps": 64300, "total_steps": 181800, "loss": 0.007, "lr": 4.082237215676172e-05, "epoch": 7.073707370737074, "percentage": 35.37, "elapsed_time": "2:32:09", "remaining_time": "4:38:03", "throughput": 1486.19, "total_tokens": 13568512} {"current_steps": 64305, "total_steps": 181800, "loss": 0.1028, "lr": 4.0820513860860606e-05, "epoch": 7.074257425742574, "percentage": 35.37, "elapsed_time": "2:32:10", "remaining_time": "4:38:02", "throughput": 1486.19, "total_tokens": 13569536} {"current_steps": 64310, "total_steps": 181800, "loss": 0.0307, "lr": 4.08186554191494e-05, "epoch": 7.074807480748075, "percentage": 35.37, "elapsed_time": "2:32:11", "remaining_time": "4:38:01", "throughput": 1486.19, "total_tokens": 13570560} {"current_steps": 64315, "total_steps": 181800, "loss": 0.1082, "lr": 4.081679683164525e-05, "epoch": 7.075357535753575, "percentage": 35.38, "elapsed_time": "2:32:11", "remaining_time": "4:38:01", "throughput": 1486.18, "total_tokens": 13571520} {"current_steps": 64320, "total_steps": 181800, "loss": 0.0253, "lr": 4.081493809836528e-05, "epoch": 7.075907590759076, "percentage": 35.38, "elapsed_time": "2:32:12", "remaining_time": "4:38:00", "throughput": 1486.19, "total_tokens": 13572576} {"current_steps": 64325, "total_steps": 181800, "loss": 0.0236, "lr": 4.081307921932659e-05, "epoch": 7.0764576457645765, "percentage": 35.38, "elapsed_time": "2:32:13", "remaining_time": "4:37:59", "throughput": 1486.19, "total_tokens": 13573600} {"current_steps": 64330, "total_steps": 181800, "loss": 0.0698, "lr": 4.081122019454635e-05, "epoch": 7.077007700770077, "percentage": 35.39, "elapsed_time": "2:32:13", "remaining_time": "4:37:58", "throughput": 1486.19, "total_tokens": 13574656} {"current_steps": 64335, "total_steps": 181800, "loss": 0.0871, "lr": 4.0809361024041684e-05, "epoch": 7.077557755775578, "percentage": 35.39, "elapsed_time": "2:32:14", "remaining_time": "4:37:58", "throughput": 1486.19, "total_tokens": 13575648} {"current_steps": 64340, "total_steps": 181800, "loss": 0.1174, "lr": 4.080750170782971e-05, "epoch": 7.078107810781078, "percentage": 35.39, "elapsed_time": "2:32:15", "remaining_time": "4:37:57", "throughput": 1486.2, "total_tokens": 13576800} {"current_steps": 64345, "total_steps": 181800, "loss": 0.1083, "lr": 4.080564224592759e-05, "epoch": 7.078657865786579, "percentage": 35.39, "elapsed_time": "2:32:15", "remaining_time": "4:37:56", "throughput": 1486.2, "total_tokens": 13577856} {"current_steps": 64350, "total_steps": 181800, "loss": 0.0446, "lr": 4.080378263835245e-05, "epoch": 7.079207920792079, "percentage": 35.4, "elapsed_time": "2:32:16", "remaining_time": "4:37:55", "throughput": 1486.21, "total_tokens": 13578880} {"current_steps": 64355, "total_steps": 181800, "loss": 0.0157, "lr": 4.0801922885121424e-05, "epoch": 7.0797579757975795, "percentage": 35.4, "elapsed_time": "2:32:17", "remaining_time": "4:37:55", "throughput": 1486.21, "total_tokens": 13579904} {"current_steps": 64360, "total_steps": 181800, "loss": 0.0026, "lr": 4.0800062986251654e-05, "epoch": 7.080308030803081, "percentage": 35.4, "elapsed_time": "2:32:17", "remaining_time": "4:37:54", "throughput": 1486.22, "total_tokens": 13581024} {"current_steps": 64365, "total_steps": 181800, "loss": 0.2415, "lr": 4.079820294176029e-05, "epoch": 7.080858085808581, "percentage": 35.4, "elapsed_time": "2:32:18", "remaining_time": "4:37:53", "throughput": 1486.22, "total_tokens": 13582112} {"current_steps": 64370, "total_steps": 181800, "loss": 0.0095, "lr": 4.0796342751664474e-05, "epoch": 7.081408140814081, "percentage": 35.41, "elapsed_time": "2:32:19", "remaining_time": "4:37:52", "throughput": 1486.23, "total_tokens": 13583232} {"current_steps": 64375, "total_steps": 181800, "loss": 0.0035, "lr": 4.079448241598134e-05, "epoch": 7.081958195819582, "percentage": 35.41, "elapsed_time": "2:32:20", "remaining_time": "4:37:52", "throughput": 1486.23, "total_tokens": 13584224} {"current_steps": 64380, "total_steps": 181800, "loss": 0.0596, "lr": 4.079262193472804e-05, "epoch": 7.082508250825082, "percentage": 35.41, "elapsed_time": "2:32:20", "remaining_time": "4:37:51", "throughput": 1486.24, "total_tokens": 13585312} {"current_steps": 64385, "total_steps": 181800, "loss": 0.0241, "lr": 4.079076130792172e-05, "epoch": 7.083058305830583, "percentage": 35.42, "elapsed_time": "2:32:21", "remaining_time": "4:37:50", "throughput": 1486.24, "total_tokens": 13586368} {"current_steps": 64390, "total_steps": 181800, "loss": 0.018, "lr": 4.078890053557954e-05, "epoch": 7.083608360836084, "percentage": 35.42, "elapsed_time": "2:32:22", "remaining_time": "4:37:49", "throughput": 1486.25, "total_tokens": 13587456} {"current_steps": 64395, "total_steps": 181800, "loss": 0.0161, "lr": 4.078703961771864e-05, "epoch": 7.084158415841584, "percentage": 35.42, "elapsed_time": "2:32:22", "remaining_time": "4:37:49", "throughput": 1486.25, "total_tokens": 13588512} {"current_steps": 64400, "total_steps": 181800, "loss": 0.0043, "lr": 4.0785178554356166e-05, "epoch": 7.084708470847085, "percentage": 35.42, "elapsed_time": "2:32:23", "remaining_time": "4:37:48", "throughput": 1486.25, "total_tokens": 13589536} {"current_steps": 64405, "total_steps": 181800, "loss": 0.0354, "lr": 4.078331734550927e-05, "epoch": 7.085258525852585, "percentage": 35.43, "elapsed_time": "2:32:24", "remaining_time": "4:37:47", "throughput": 1486.26, "total_tokens": 13590624} {"current_steps": 64410, "total_steps": 181800, "loss": 0.0726, "lr": 4.0781455991195115e-05, "epoch": 7.085808580858086, "percentage": 35.43, "elapsed_time": "2:32:24", "remaining_time": "4:37:46", "throughput": 1486.27, "total_tokens": 13591744} {"current_steps": 64415, "total_steps": 181800, "loss": 0.0522, "lr": 4.077959449143086e-05, "epoch": 7.086358635863586, "percentage": 35.43, "elapsed_time": "2:32:25", "remaining_time": "4:37:46", "throughput": 1486.27, "total_tokens": 13592768} {"current_steps": 64420, "total_steps": 181800, "loss": 0.0632, "lr": 4.077773284623365e-05, "epoch": 7.086908690869087, "percentage": 35.43, "elapsed_time": "2:32:26", "remaining_time": "4:37:45", "throughput": 1486.27, "total_tokens": 13593824} {"current_steps": 64425, "total_steps": 181800, "loss": 0.0331, "lr": 4.077587105562064e-05, "epoch": 7.087458745874588, "percentage": 35.44, "elapsed_time": "2:32:26", "remaining_time": "4:37:44", "throughput": 1486.27, "total_tokens": 13594880} {"current_steps": 64430, "total_steps": 181800, "loss": 0.0428, "lr": 4.0774009119609005e-05, "epoch": 7.088008800880088, "percentage": 35.44, "elapsed_time": "2:32:27", "remaining_time": "4:37:43", "throughput": 1486.28, "total_tokens": 13595968} {"current_steps": 64435, "total_steps": 181800, "loss": 0.0138, "lr": 4.077214703821589e-05, "epoch": 7.088558855885589, "percentage": 35.44, "elapsed_time": "2:32:28", "remaining_time": "4:37:43", "throughput": 1486.28, "total_tokens": 13597024} {"current_steps": 64440, "total_steps": 181800, "loss": 0.0177, "lr": 4.077028481145847e-05, "epoch": 7.089108910891089, "percentage": 35.45, "elapsed_time": "2:32:29", "remaining_time": "4:37:42", "throughput": 1486.28, "total_tokens": 13598048} {"current_steps": 64445, "total_steps": 181800, "loss": 0.004, "lr": 4.076842243935391e-05, "epoch": 7.089658965896589, "percentage": 35.45, "elapsed_time": "2:32:29", "remaining_time": "4:37:41", "throughput": 1486.29, "total_tokens": 13599168} {"current_steps": 64450, "total_steps": 181800, "loss": 0.0243, "lr": 4.076655992191936e-05, "epoch": 7.0902090209020905, "percentage": 35.45, "elapsed_time": "2:32:30", "remaining_time": "4:37:40", "throughput": 1486.29, "total_tokens": 13600192} {"current_steps": 64455, "total_steps": 181800, "loss": 0.0441, "lr": 4.076469725917198e-05, "epoch": 7.090759075907591, "percentage": 35.45, "elapsed_time": "2:32:31", "remaining_time": "4:37:40", "throughput": 1486.29, "total_tokens": 13601216} {"current_steps": 64460, "total_steps": 181800, "loss": 0.0098, "lr": 4.076283445112897e-05, "epoch": 7.091309130913091, "percentage": 35.46, "elapsed_time": "2:32:31", "remaining_time": "4:37:39", "throughput": 1486.29, "total_tokens": 13602208} {"current_steps": 64465, "total_steps": 181800, "loss": 0.0042, "lr": 4.076097149780746e-05, "epoch": 7.091859185918592, "percentage": 35.46, "elapsed_time": "2:32:32", "remaining_time": "4:37:38", "throughput": 1486.29, "total_tokens": 13603264} {"current_steps": 64470, "total_steps": 181800, "loss": 0.0089, "lr": 4.0759108399224656e-05, "epoch": 7.092409240924092, "percentage": 35.46, "elapsed_time": "2:32:33", "remaining_time": "4:37:38", "throughput": 1486.3, "total_tokens": 13604384} {"current_steps": 64475, "total_steps": 181800, "loss": 0.0133, "lr": 4.075724515539771e-05, "epoch": 7.092959295929593, "percentage": 35.46, "elapsed_time": "2:32:33", "remaining_time": "4:37:37", "throughput": 1486.3, "total_tokens": 13605376} {"current_steps": 64480, "total_steps": 181800, "loss": 0.0515, "lr": 4.075538176634378e-05, "epoch": 7.0935093509350935, "percentage": 35.47, "elapsed_time": "2:32:34", "remaining_time": "4:37:36", "throughput": 1486.31, "total_tokens": 13606464} {"current_steps": 64485, "total_steps": 181800, "loss": 0.0027, "lr": 4.0753518232080066e-05, "epoch": 7.094059405940594, "percentage": 35.47, "elapsed_time": "2:32:35", "remaining_time": "4:37:35", "throughput": 1486.31, "total_tokens": 13607488} {"current_steps": 64490, "total_steps": 181800, "loss": 0.0043, "lr": 4.0751654552623735e-05, "epoch": 7.094609460946095, "percentage": 35.47, "elapsed_time": "2:32:35", "remaining_time": "4:37:35", "throughput": 1486.31, "total_tokens": 13608512} {"current_steps": 64495, "total_steps": 181800, "loss": 0.0816, "lr": 4.074979072799197e-05, "epoch": 7.095159515951595, "percentage": 35.48, "elapsed_time": "2:32:36", "remaining_time": "4:37:34", "throughput": 1486.31, "total_tokens": 13609568} {"current_steps": 64500, "total_steps": 181800, "loss": 0.066, "lr": 4.0747926758201927e-05, "epoch": 7.095709570957096, "percentage": 35.48, "elapsed_time": "2:32:37", "remaining_time": "4:37:33", "throughput": 1486.31, "total_tokens": 13610560} {"current_steps": 64505, "total_steps": 181800, "loss": 0.108, "lr": 4.0746062643270805e-05, "epoch": 7.096259625962596, "percentage": 35.48, "elapsed_time": "2:32:37", "remaining_time": "4:37:32", "throughput": 1486.31, "total_tokens": 13611648} {"current_steps": 64510, "total_steps": 181800, "loss": 0.1209, "lr": 4.074419838321578e-05, "epoch": 7.0968096809680965, "percentage": 35.48, "elapsed_time": "2:32:38", "remaining_time": "4:37:32", "throughput": 1486.32, "total_tokens": 13612704} {"current_steps": 64515, "total_steps": 181800, "loss": 0.0709, "lr": 4.074233397805404e-05, "epoch": 7.097359735973598, "percentage": 35.49, "elapsed_time": "2:32:39", "remaining_time": "4:37:31", "throughput": 1486.32, "total_tokens": 13613760} {"current_steps": 64520, "total_steps": 181800, "loss": 0.042, "lr": 4.0740469427802754e-05, "epoch": 7.097909790979098, "percentage": 35.49, "elapsed_time": "2:32:40", "remaining_time": "4:37:30", "throughput": 1486.32, "total_tokens": 13614816} {"current_steps": 64525, "total_steps": 181800, "loss": 0.034, "lr": 4.0738604732479115e-05, "epoch": 7.098459845984599, "percentage": 35.49, "elapsed_time": "2:32:40", "remaining_time": "4:37:29", "throughput": 1486.32, "total_tokens": 13615808} {"current_steps": 64530, "total_steps": 181800, "loss": 0.0324, "lr": 4.07367398921003e-05, "epoch": 7.099009900990099, "percentage": 35.5, "elapsed_time": "2:32:41", "remaining_time": "4:37:29", "throughput": 1486.33, "total_tokens": 13616896} {"current_steps": 64535, "total_steps": 181800, "loss": 0.0848, "lr": 4.073487490668352e-05, "epoch": 7.099559955995599, "percentage": 35.5, "elapsed_time": "2:32:42", "remaining_time": "4:37:28", "throughput": 1486.33, "total_tokens": 13617920} {"current_steps": 64540, "total_steps": 181800, "loss": 0.0268, "lr": 4.073300977624594e-05, "epoch": 7.1001100110011, "percentage": 35.5, "elapsed_time": "2:32:42", "remaining_time": "4:37:27", "throughput": 1486.33, "total_tokens": 13618944} {"current_steps": 64545, "total_steps": 181800, "loss": 0.022, "lr": 4.0731144500804755e-05, "epoch": 7.100660066006601, "percentage": 35.5, "elapsed_time": "2:32:43", "remaining_time": "4:37:26", "throughput": 1486.33, "total_tokens": 13619968} {"current_steps": 64550, "total_steps": 181800, "loss": 0.0599, "lr": 4.072927908037717e-05, "epoch": 7.101210121012101, "percentage": 35.51, "elapsed_time": "2:32:44", "remaining_time": "4:37:26", "throughput": 1486.33, "total_tokens": 13620960} {"current_steps": 64555, "total_steps": 181800, "loss": 0.0202, "lr": 4.072741351498036e-05, "epoch": 7.101760176017602, "percentage": 35.51, "elapsed_time": "2:32:44", "remaining_time": "4:37:25", "throughput": 1486.33, "total_tokens": 13622048} {"current_steps": 64560, "total_steps": 181800, "loss": 0.1009, "lr": 4.072554780463153e-05, "epoch": 7.102310231023102, "percentage": 35.51, "elapsed_time": "2:32:45", "remaining_time": "4:37:24", "throughput": 1486.33, "total_tokens": 13623040} {"current_steps": 64565, "total_steps": 181800, "loss": 0.1071, "lr": 4.072368194934787e-05, "epoch": 7.102860286028603, "percentage": 35.51, "elapsed_time": "2:32:46", "remaining_time": "4:37:23", "throughput": 1486.33, "total_tokens": 13624064} {"current_steps": 64570, "total_steps": 181800, "loss": 0.0264, "lr": 4.072181594914658e-05, "epoch": 7.103410341034103, "percentage": 35.52, "elapsed_time": "2:32:46", "remaining_time": "4:37:23", "throughput": 1486.34, "total_tokens": 13625152} {"current_steps": 64575, "total_steps": 181800, "loss": 0.0163, "lr": 4.0719949804044857e-05, "epoch": 7.103960396039604, "percentage": 35.52, "elapsed_time": "2:32:47", "remaining_time": "4:37:22", "throughput": 1486.34, "total_tokens": 13626240} {"current_steps": 64580, "total_steps": 181800, "loss": 0.0554, "lr": 4.07180835140599e-05, "epoch": 7.104510451045105, "percentage": 35.52, "elapsed_time": "2:32:48", "remaining_time": "4:37:21", "throughput": 1486.34, "total_tokens": 13627264} {"current_steps": 64585, "total_steps": 181800, "loss": 0.0245, "lr": 4.07162170792089e-05, "epoch": 7.105060506050605, "percentage": 35.53, "elapsed_time": "2:32:49", "remaining_time": "4:37:20", "throughput": 1486.34, "total_tokens": 13628288} {"current_steps": 64590, "total_steps": 181800, "loss": 0.0271, "lr": 4.071435049950908e-05, "epoch": 7.105610561056106, "percentage": 35.53, "elapsed_time": "2:32:49", "remaining_time": "4:37:20", "throughput": 1486.34, "total_tokens": 13629280} {"current_steps": 64595, "total_steps": 181800, "loss": 0.1145, "lr": 4.0712483774977623e-05, "epoch": 7.106160616061606, "percentage": 35.53, "elapsed_time": "2:32:50", "remaining_time": "4:37:19", "throughput": 1486.34, "total_tokens": 13630368} {"current_steps": 64600, "total_steps": 181800, "loss": 0.1081, "lr": 4.071061690563175e-05, "epoch": 7.106710671067106, "percentage": 35.53, "elapsed_time": "2:32:51", "remaining_time": "4:37:18", "throughput": 1486.35, "total_tokens": 13631424} {"current_steps": 64605, "total_steps": 181800, "loss": 0.023, "lr": 4.070874989148866e-05, "epoch": 7.1072607260726075, "percentage": 35.54, "elapsed_time": "2:32:51", "remaining_time": "4:37:17", "throughput": 1486.35, "total_tokens": 13632480} {"current_steps": 64610, "total_steps": 181800, "loss": 0.0723, "lr": 4.070688273256556e-05, "epoch": 7.107810781078108, "percentage": 35.54, "elapsed_time": "2:32:52", "remaining_time": "4:37:17", "throughput": 1486.35, "total_tokens": 13633536} {"current_steps": 64615, "total_steps": 181800, "loss": 0.0397, "lr": 4.070501542887965e-05, "epoch": 7.108360836083609, "percentage": 35.54, "elapsed_time": "2:32:53", "remaining_time": "4:37:16", "throughput": 1486.34, "total_tokens": 13634496} {"current_steps": 64620, "total_steps": 181800, "loss": 0.0998, "lr": 4.070314798044815e-05, "epoch": 7.108910891089109, "percentage": 35.54, "elapsed_time": "2:32:53", "remaining_time": "4:37:15", "throughput": 1486.35, "total_tokens": 13635584} {"current_steps": 64625, "total_steps": 181800, "loss": 0.0117, "lr": 4.070128038728828e-05, "epoch": 7.109460946094609, "percentage": 35.55, "elapsed_time": "2:32:54", "remaining_time": "4:37:14", "throughput": 1486.34, "total_tokens": 13636544} {"current_steps": 64630, "total_steps": 181800, "loss": 0.0766, "lr": 4.069941264941723e-05, "epoch": 7.11001100110011, "percentage": 35.55, "elapsed_time": "2:32:55", "remaining_time": "4:37:14", "throughput": 1486.35, "total_tokens": 13637600} {"current_steps": 64635, "total_steps": 181800, "loss": 0.0532, "lr": 4.0697544766852234e-05, "epoch": 7.1105610561056105, "percentage": 35.55, "elapsed_time": "2:32:55", "remaining_time": "4:37:13", "throughput": 1486.35, "total_tokens": 13638656} {"current_steps": 64640, "total_steps": 181800, "loss": 0.0096, "lr": 4.0695676739610506e-05, "epoch": 7.111111111111111, "percentage": 35.56, "elapsed_time": "2:32:56", "remaining_time": "4:37:12", "throughput": 1486.35, "total_tokens": 13639680} {"current_steps": 64645, "total_steps": 181800, "loss": 0.0273, "lr": 4.069380856770925e-05, "epoch": 7.111661166116612, "percentage": 35.56, "elapsed_time": "2:32:57", "remaining_time": "4:37:11", "throughput": 1486.35, "total_tokens": 13640736} {"current_steps": 64650, "total_steps": 181800, "loss": 0.0332, "lr": 4.069194025116569e-05, "epoch": 7.112211221122112, "percentage": 35.56, "elapsed_time": "2:32:58", "remaining_time": "4:37:11", "throughput": 1486.36, "total_tokens": 13641824} {"current_steps": 64655, "total_steps": 181800, "loss": 0.0098, "lr": 4.0690071789997055e-05, "epoch": 7.112761276127613, "percentage": 35.56, "elapsed_time": "2:32:58", "remaining_time": "4:37:10", "throughput": 1486.36, "total_tokens": 13642880} {"current_steps": 64660, "total_steps": 181800, "loss": 0.0139, "lr": 4.0688203184220555e-05, "epoch": 7.113311331133113, "percentage": 35.57, "elapsed_time": "2:32:59", "remaining_time": "4:37:09", "throughput": 1486.36, "total_tokens": 13643904} {"current_steps": 64665, "total_steps": 181800, "loss": 0.0251, "lr": 4.068633443385341e-05, "epoch": 7.1138613861386135, "percentage": 35.57, "elapsed_time": "2:33:00", "remaining_time": "4:37:08", "throughput": 1486.36, "total_tokens": 13644896} {"current_steps": 64670, "total_steps": 181800, "loss": 0.005, "lr": 4.0684465538912845e-05, "epoch": 7.114411441144115, "percentage": 35.57, "elapsed_time": "2:33:00", "remaining_time": "4:37:08", "throughput": 1486.36, "total_tokens": 13645888} {"current_steps": 64675, "total_steps": 181800, "loss": 0.117, "lr": 4.068259649941609e-05, "epoch": 7.114961496149615, "percentage": 35.57, "elapsed_time": "2:33:01", "remaining_time": "4:37:07", "throughput": 1486.36, "total_tokens": 13646976} {"current_steps": 64680, "total_steps": 181800, "loss": 0.0083, "lr": 4.068072731538037e-05, "epoch": 7.115511551155116, "percentage": 35.58, "elapsed_time": "2:33:02", "remaining_time": "4:37:06", "throughput": 1486.37, "total_tokens": 13648064} {"current_steps": 64685, "total_steps": 181800, "loss": 0.0064, "lr": 4.067885798682291e-05, "epoch": 7.116061606160616, "percentage": 35.58, "elapsed_time": "2:33:02", "remaining_time": "4:37:05", "throughput": 1486.38, "total_tokens": 13649152} {"current_steps": 64690, "total_steps": 181800, "loss": 0.0416, "lr": 4.067698851376094e-05, "epoch": 7.116611661166116, "percentage": 35.58, "elapsed_time": "2:33:03", "remaining_time": "4:37:05", "throughput": 1486.38, "total_tokens": 13650208} {"current_steps": 64695, "total_steps": 181800, "loss": 0.0296, "lr": 4.067511889621168e-05, "epoch": 7.117161716171617, "percentage": 35.59, "elapsed_time": "2:33:04", "remaining_time": "4:37:04", "throughput": 1486.38, "total_tokens": 13651264} {"current_steps": 64700, "total_steps": 181800, "loss": 0.0421, "lr": 4.067324913419239e-05, "epoch": 7.117711771177118, "percentage": 35.59, "elapsed_time": "2:33:04", "remaining_time": "4:37:03", "throughput": 1486.39, "total_tokens": 13652320} {"current_steps": 64705, "total_steps": 181800, "loss": 0.0539, "lr": 4.067137922772027e-05, "epoch": 7.118261826182618, "percentage": 35.59, "elapsed_time": "2:33:05", "remaining_time": "4:37:02", "throughput": 1486.39, "total_tokens": 13653376} {"current_steps": 64710, "total_steps": 181800, "loss": 0.0274, "lr": 4.066950917681257e-05, "epoch": 7.118811881188119, "percentage": 35.59, "elapsed_time": "2:33:06", "remaining_time": "4:37:02", "throughput": 1486.39, "total_tokens": 13654432} {"current_steps": 64715, "total_steps": 181800, "loss": 0.0358, "lr": 4.066763898148652e-05, "epoch": 7.119361936193619, "percentage": 35.6, "elapsed_time": "2:33:06", "remaining_time": "4:37:01", "throughput": 1486.4, "total_tokens": 13655488} {"current_steps": 64720, "total_steps": 181800, "loss": 0.0178, "lr": 4.066576864175936e-05, "epoch": 7.11991199119912, "percentage": 35.6, "elapsed_time": "2:33:07", "remaining_time": "4:37:00", "throughput": 1486.4, "total_tokens": 13656576} {"current_steps": 64725, "total_steps": 181800, "loss": 0.0265, "lr": 4.066389815764834e-05, "epoch": 7.12046204620462, "percentage": 35.6, "elapsed_time": "2:33:08", "remaining_time": "4:36:59", "throughput": 1486.42, "total_tokens": 13657728} {"current_steps": 64730, "total_steps": 181800, "loss": 0.0506, "lr": 4.066202752917067e-05, "epoch": 7.121012101210121, "percentage": 35.61, "elapsed_time": "2:33:09", "remaining_time": "4:36:59", "throughput": 1486.42, "total_tokens": 13658752} {"current_steps": 64735, "total_steps": 181800, "loss": 0.0914, "lr": 4.066015675634362e-05, "epoch": 7.121562156215622, "percentage": 35.61, "elapsed_time": "2:33:09", "remaining_time": "4:36:58", "throughput": 1486.43, "total_tokens": 13659872} {"current_steps": 64740, "total_steps": 181800, "loss": 0.0953, "lr": 4.065828583918441e-05, "epoch": 7.122112211221122, "percentage": 35.61, "elapsed_time": "2:33:10", "remaining_time": "4:36:58", "throughput": 1486.4, "total_tokens": 13660960} {"current_steps": 64745, "total_steps": 181800, "loss": 0.0834, "lr": 4.065641477771029e-05, "epoch": 7.122662266226623, "percentage": 35.61, "elapsed_time": "2:33:11", "remaining_time": "4:36:57", "throughput": 1486.4, "total_tokens": 13662048} {"current_steps": 64750, "total_steps": 181800, "loss": 0.1165, "lr": 4.0654543571938526e-05, "epoch": 7.123212321232123, "percentage": 35.62, "elapsed_time": "2:33:12", "remaining_time": "4:36:56", "throughput": 1486.41, "total_tokens": 13663136} {"current_steps": 64755, "total_steps": 181800, "loss": 0.0141, "lr": 4.065267222188633e-05, "epoch": 7.123762376237623, "percentage": 35.62, "elapsed_time": "2:33:12", "remaining_time": "4:36:55", "throughput": 1486.41, "total_tokens": 13664128} {"current_steps": 64760, "total_steps": 181800, "loss": 0.0075, "lr": 4.065080072757097e-05, "epoch": 7.1243124312431245, "percentage": 35.62, "elapsed_time": "2:33:13", "remaining_time": "4:36:55", "throughput": 1486.41, "total_tokens": 13665152} {"current_steps": 64765, "total_steps": 181800, "loss": 0.0842, "lr": 4.0648929089009694e-05, "epoch": 7.124862486248625, "percentage": 35.62, "elapsed_time": "2:33:14", "remaining_time": "4:36:54", "throughput": 1486.41, "total_tokens": 13666176} {"current_steps": 64770, "total_steps": 181800, "loss": 0.0491, "lr": 4.0647057306219746e-05, "epoch": 7.125412541254126, "percentage": 35.63, "elapsed_time": "2:33:14", "remaining_time": "4:36:53", "throughput": 1486.41, "total_tokens": 13667200} {"current_steps": 64775, "total_steps": 181800, "loss": 0.0323, "lr": 4.064518537921837e-05, "epoch": 7.125962596259626, "percentage": 35.63, "elapsed_time": "2:33:15", "remaining_time": "4:36:52", "throughput": 1486.41, "total_tokens": 13668256} {"current_steps": 64780, "total_steps": 181800, "loss": 0.0397, "lr": 4.064331330802283e-05, "epoch": 7.126512651265126, "percentage": 35.63, "elapsed_time": "2:33:16", "remaining_time": "4:36:52", "throughput": 1486.41, "total_tokens": 13669280} {"current_steps": 64785, "total_steps": 181800, "loss": 0.0829, "lr": 4.064144109265039e-05, "epoch": 7.127062706270627, "percentage": 35.64, "elapsed_time": "2:33:16", "remaining_time": "4:36:51", "throughput": 1486.41, "total_tokens": 13670304} {"current_steps": 64790, "total_steps": 181800, "loss": 0.0189, "lr": 4.063956873311828e-05, "epoch": 7.1276127612761275, "percentage": 35.64, "elapsed_time": "2:33:17", "remaining_time": "4:36:50", "throughput": 1486.41, "total_tokens": 13671296} {"current_steps": 64795, "total_steps": 181800, "loss": 0.0428, "lr": 4.063769622944378e-05, "epoch": 7.128162816281628, "percentage": 35.64, "elapsed_time": "2:33:18", "remaining_time": "4:36:49", "throughput": 1486.41, "total_tokens": 13672352} {"current_steps": 64800, "total_steps": 181800, "loss": 0.0324, "lr": 4.0635823581644126e-05, "epoch": 7.128712871287129, "percentage": 35.64, "elapsed_time": "2:33:18", "remaining_time": "4:36:49", "throughput": 1486.41, "total_tokens": 13673376} {"current_steps": 64805, "total_steps": 181800, "loss": 0.056, "lr": 4.06339507897366e-05, "epoch": 7.129262926292629, "percentage": 35.65, "elapsed_time": "2:33:19", "remaining_time": "4:36:48", "throughput": 1486.41, "total_tokens": 13674400} {"current_steps": 64810, "total_steps": 181800, "loss": 0.0127, "lr": 4.063207785373844e-05, "epoch": 7.12981298129813, "percentage": 35.65, "elapsed_time": "2:33:20", "remaining_time": "4:36:47", "throughput": 1486.42, "total_tokens": 13675488} {"current_steps": 64815, "total_steps": 181800, "loss": 0.092, "lr": 4.0630204773666925e-05, "epoch": 7.13036303630363, "percentage": 35.65, "elapsed_time": "2:33:20", "remaining_time": "4:36:46", "throughput": 1486.42, "total_tokens": 13676512} {"current_steps": 64820, "total_steps": 181800, "loss": 0.0213, "lr": 4.062833154953931e-05, "epoch": 7.1309130913091305, "percentage": 35.65, "elapsed_time": "2:33:21", "remaining_time": "4:36:46", "throughput": 1486.42, "total_tokens": 13677536} {"current_steps": 64825, "total_steps": 181800, "loss": 0.0171, "lr": 4.062645818137287e-05, "epoch": 7.131463146314632, "percentage": 35.66, "elapsed_time": "2:33:22", "remaining_time": "4:36:45", "throughput": 1486.42, "total_tokens": 13678592} {"current_steps": 64830, "total_steps": 181800, "loss": 0.0098, "lr": 4.0624584669184855e-05, "epoch": 7.132013201320132, "percentage": 35.66, "elapsed_time": "2:33:23", "remaining_time": "4:36:44", "throughput": 1486.42, "total_tokens": 13679584} {"current_steps": 64835, "total_steps": 181800, "loss": 0.0369, "lr": 4.062271101299254e-05, "epoch": 7.132563256325633, "percentage": 35.66, "elapsed_time": "2:33:23", "remaining_time": "4:36:43", "throughput": 1486.42, "total_tokens": 13680672} {"current_steps": 64840, "total_steps": 181800, "loss": 0.1128, "lr": 4.06208372128132e-05, "epoch": 7.133113311331133, "percentage": 35.67, "elapsed_time": "2:33:24", "remaining_time": "4:36:43", "throughput": 1486.43, "total_tokens": 13681792} {"current_steps": 64845, "total_steps": 181800, "loss": 0.053, "lr": 4.06189632686641e-05, "epoch": 7.133663366336633, "percentage": 35.67, "elapsed_time": "2:33:25", "remaining_time": "4:36:42", "throughput": 1486.44, "total_tokens": 13682880} {"current_steps": 64850, "total_steps": 181800, "loss": 0.0056, "lr": 4.0617089180562506e-05, "epoch": 7.134213421342134, "percentage": 35.67, "elapsed_time": "2:33:25", "remaining_time": "4:36:41", "throughput": 1486.44, "total_tokens": 13683904} {"current_steps": 64855, "total_steps": 181800, "loss": 0.0161, "lr": 4.061521494852569e-05, "epoch": 7.134763476347635, "percentage": 35.67, "elapsed_time": "2:33:26", "remaining_time": "4:36:40", "throughput": 1486.45, "total_tokens": 13684992} {"current_steps": 64860, "total_steps": 181800, "loss": 0.0921, "lr": 4.0613340572570944e-05, "epoch": 7.135313531353136, "percentage": 35.68, "elapsed_time": "2:33:27", "remaining_time": "4:36:40", "throughput": 1486.45, "total_tokens": 13686016} {"current_steps": 64865, "total_steps": 181800, "loss": 0.0155, "lr": 4.0611466052715525e-05, "epoch": 7.135863586358636, "percentage": 35.68, "elapsed_time": "2:33:27", "remaining_time": "4:36:39", "throughput": 1486.45, "total_tokens": 13687104} {"current_steps": 64870, "total_steps": 181800, "loss": 0.0217, "lr": 4.0609591388976707e-05, "epoch": 7.136413641364136, "percentage": 35.68, "elapsed_time": "2:33:28", "remaining_time": "4:36:38", "throughput": 1486.47, "total_tokens": 13688256} {"current_steps": 64875, "total_steps": 181800, "loss": 0.1088, "lr": 4.060771658137178e-05, "epoch": 7.136963696369637, "percentage": 35.68, "elapsed_time": "2:33:29", "remaining_time": "4:36:37", "throughput": 1486.47, "total_tokens": 13689312} {"current_steps": 64880, "total_steps": 181800, "loss": 0.0163, "lr": 4.060584162991802e-05, "epoch": 7.137513751375137, "percentage": 35.69, "elapsed_time": "2:33:29", "remaining_time": "4:36:37", "throughput": 1486.47, "total_tokens": 13690304} {"current_steps": 64885, "total_steps": 181800, "loss": 0.0176, "lr": 4.060396653463271e-05, "epoch": 7.138063806380638, "percentage": 35.69, "elapsed_time": "2:33:30", "remaining_time": "4:36:36", "throughput": 1486.47, "total_tokens": 13691360} {"current_steps": 64890, "total_steps": 181800, "loss": 0.0106, "lr": 4.060209129553313e-05, "epoch": 7.138613861386139, "percentage": 35.69, "elapsed_time": "2:33:31", "remaining_time": "4:36:35", "throughput": 1486.48, "total_tokens": 13692416} {"current_steps": 64895, "total_steps": 181800, "loss": 0.0075, "lr": 4.060021591263655e-05, "epoch": 7.139163916391639, "percentage": 35.7, "elapsed_time": "2:33:32", "remaining_time": "4:36:34", "throughput": 1486.48, "total_tokens": 13693504} {"current_steps": 64900, "total_steps": 181800, "loss": 0.0104, "lr": 4.059834038596026e-05, "epoch": 7.13971397139714, "percentage": 35.7, "elapsed_time": "2:33:32", "remaining_time": "4:36:34", "throughput": 1486.49, "total_tokens": 13694592} {"current_steps": 64905, "total_steps": 181800, "loss": 0.2444, "lr": 4.0596464715521566e-05, "epoch": 7.14026402640264, "percentage": 35.7, "elapsed_time": "2:33:33", "remaining_time": "4:36:33", "throughput": 1486.5, "total_tokens": 13695680} {"current_steps": 64910, "total_steps": 181800, "loss": 0.0078, "lr": 4.059458890133774e-05, "epoch": 7.1408140814081404, "percentage": 35.7, "elapsed_time": "2:33:34", "remaining_time": "4:36:32", "throughput": 1486.51, "total_tokens": 13696800} {"current_steps": 64915, "total_steps": 181800, "loss": 0.0753, "lr": 4.059271294342607e-05, "epoch": 7.1413641364136415, "percentage": 35.71, "elapsed_time": "2:33:34", "remaining_time": "4:36:31", "throughput": 1486.51, "total_tokens": 13697824} {"current_steps": 64920, "total_steps": 181800, "loss": 0.0288, "lr": 4.059083684180384e-05, "epoch": 7.141914191419142, "percentage": 35.71, "elapsed_time": "2:33:35", "remaining_time": "4:36:31", "throughput": 1486.52, "total_tokens": 13698944} {"current_steps": 64925, "total_steps": 181800, "loss": 0.0091, "lr": 4.058896059648836e-05, "epoch": 7.142464246424643, "percentage": 35.71, "elapsed_time": "2:33:36", "remaining_time": "4:36:30", "throughput": 1486.52, "total_tokens": 13700000} {"current_steps": 64930, "total_steps": 181800, "loss": 0.0456, "lr": 4.0587084207496895e-05, "epoch": 7.143014301430143, "percentage": 35.72, "elapsed_time": "2:33:36", "remaining_time": "4:36:29", "throughput": 1486.53, "total_tokens": 13701120} {"current_steps": 64935, "total_steps": 181800, "loss": 0.0284, "lr": 4.058520767484676e-05, "epoch": 7.143564356435643, "percentage": 35.72, "elapsed_time": "2:33:37", "remaining_time": "4:36:29", "throughput": 1486.53, "total_tokens": 13702144} {"current_steps": 64940, "total_steps": 181800, "loss": 0.0085, "lr": 4.0583330998555246e-05, "epoch": 7.144114411441144, "percentage": 35.72, "elapsed_time": "2:33:38", "remaining_time": "4:36:28", "throughput": 1486.53, "total_tokens": 13703200} {"current_steps": 64945, "total_steps": 181800, "loss": 0.0052, "lr": 4.0581454178639654e-05, "epoch": 7.1446644664466445, "percentage": 35.72, "elapsed_time": "2:33:38", "remaining_time": "4:36:27", "throughput": 1486.54, "total_tokens": 13704320} {"current_steps": 64950, "total_steps": 181800, "loss": 0.0437, "lr": 4.057957721511727e-05, "epoch": 7.145214521452146, "percentage": 35.73, "elapsed_time": "2:33:39", "remaining_time": "4:36:26", "throughput": 1486.55, "total_tokens": 13705408} {"current_steps": 64955, "total_steps": 181800, "loss": 0.0743, "lr": 4.05777001080054e-05, "epoch": 7.145764576457646, "percentage": 35.73, "elapsed_time": "2:33:40", "remaining_time": "4:36:26", "throughput": 1486.56, "total_tokens": 13706496} {"current_steps": 64960, "total_steps": 181800, "loss": 0.0182, "lr": 4.057582285732135e-05, "epoch": 7.146314631463146, "percentage": 35.73, "elapsed_time": "2:33:40", "remaining_time": "4:36:25", "throughput": 1486.56, "total_tokens": 13707584} {"current_steps": 64965, "total_steps": 181800, "loss": 0.0439, "lr": 4.05739454630824e-05, "epoch": 7.146864686468647, "percentage": 35.73, "elapsed_time": "2:33:41", "remaining_time": "4:36:24", "throughput": 1486.57, "total_tokens": 13708672} {"current_steps": 64970, "total_steps": 181800, "loss": 0.1109, "lr": 4.0572067925305866e-05, "epoch": 7.147414741474147, "percentage": 35.74, "elapsed_time": "2:33:42", "remaining_time": "4:36:23", "throughput": 1486.58, "total_tokens": 13709760} {"current_steps": 64975, "total_steps": 181800, "loss": 0.0823, "lr": 4.057019024400906e-05, "epoch": 7.1479647964796476, "percentage": 35.74, "elapsed_time": "2:33:43", "remaining_time": "4:36:23", "throughput": 1486.58, "total_tokens": 13710816} {"current_steps": 64980, "total_steps": 181800, "loss": 0.027, "lr": 4.0568312419209286e-05, "epoch": 7.148514851485149, "percentage": 35.74, "elapsed_time": "2:33:43", "remaining_time": "4:36:22", "throughput": 1486.59, "total_tokens": 13711904} {"current_steps": 64985, "total_steps": 181800, "loss": 0.0119, "lr": 4.056643445092385e-05, "epoch": 7.149064906490649, "percentage": 35.75, "elapsed_time": "2:33:44", "remaining_time": "4:36:21", "throughput": 1486.59, "total_tokens": 13712960} {"current_steps": 64990, "total_steps": 181800, "loss": 0.0035, "lr": 4.056455633917005e-05, "epoch": 7.14961496149615, "percentage": 35.75, "elapsed_time": "2:33:45", "remaining_time": "4:36:20", "throughput": 1486.59, "total_tokens": 13713984} {"current_steps": 64995, "total_steps": 181800, "loss": 0.0062, "lr": 4.05626780839652e-05, "epoch": 7.15016501650165, "percentage": 35.75, "elapsed_time": "2:33:45", "remaining_time": "4:36:20", "throughput": 1486.6, "total_tokens": 13715104} {"current_steps": 65000, "total_steps": 181800, "loss": 0.053, "lr": 4.056079968532662e-05, "epoch": 7.15071507150715, "percentage": 35.75, "elapsed_time": "2:33:46", "remaining_time": "4:36:19", "throughput": 1486.6, "total_tokens": 13716096} {"current_steps": 65005, "total_steps": 181800, "loss": 0.1243, "lr": 4.055892114327162e-05, "epoch": 7.1512651265126514, "percentage": 35.76, "elapsed_time": "2:33:47", "remaining_time": "4:36:18", "throughput": 1486.6, "total_tokens": 13717088} {"current_steps": 65010, "total_steps": 181800, "loss": 0.0385, "lr": 4.05570424578175e-05, "epoch": 7.151815181518152, "percentage": 35.76, "elapsed_time": "2:33:47", "remaining_time": "4:36:17", "throughput": 1486.6, "total_tokens": 13718144} {"current_steps": 65015, "total_steps": 181800, "loss": 0.0247, "lr": 4.055516362898159e-05, "epoch": 7.152365236523653, "percentage": 35.76, "elapsed_time": "2:33:48", "remaining_time": "4:36:17", "throughput": 1486.61, "total_tokens": 13719232} {"current_steps": 65020, "total_steps": 181800, "loss": 0.0728, "lr": 4.05532846567812e-05, "epoch": 7.152915291529153, "percentage": 35.76, "elapsed_time": "2:33:49", "remaining_time": "4:36:16", "throughput": 1486.61, "total_tokens": 13720288} {"current_steps": 65025, "total_steps": 181800, "loss": 0.0673, "lr": 4.055140554123364e-05, "epoch": 7.153465346534653, "percentage": 35.77, "elapsed_time": "2:33:49", "remaining_time": "4:36:15", "throughput": 1486.61, "total_tokens": 13721344} {"current_steps": 65030, "total_steps": 181800, "loss": 0.1211, "lr": 4.054952628235625e-05, "epoch": 7.154015401540154, "percentage": 35.77, "elapsed_time": "2:33:50", "remaining_time": "4:36:14", "throughput": 1486.62, "total_tokens": 13722400} {"current_steps": 65035, "total_steps": 181800, "loss": 0.037, "lr": 4.054764688016633e-05, "epoch": 7.1545654565456545, "percentage": 35.77, "elapsed_time": "2:33:51", "remaining_time": "4:36:14", "throughput": 1486.62, "total_tokens": 13723456} {"current_steps": 65040, "total_steps": 181800, "loss": 0.0487, "lr": 4.054576733468122e-05, "epoch": 7.1551155115511555, "percentage": 35.78, "elapsed_time": "2:33:52", "remaining_time": "4:36:13", "throughput": 1486.63, "total_tokens": 13724544} {"current_steps": 65045, "total_steps": 181800, "loss": 0.0541, "lr": 4.054388764591822e-05, "epoch": 7.155665566556656, "percentage": 35.78, "elapsed_time": "2:33:52", "remaining_time": "4:36:12", "throughput": 1486.63, "total_tokens": 13725600} {"current_steps": 65050, "total_steps": 181800, "loss": 0.0263, "lr": 4.054200781389468e-05, "epoch": 7.156215621562156, "percentage": 35.78, "elapsed_time": "2:33:53", "remaining_time": "4:36:11", "throughput": 1486.63, "total_tokens": 13726624} {"current_steps": 65055, "total_steps": 181800, "loss": 0.0216, "lr": 4.05401278386279e-05, "epoch": 7.156765676567657, "percentage": 35.78, "elapsed_time": "2:33:54", "remaining_time": "4:36:11", "throughput": 1486.63, "total_tokens": 13727680} {"current_steps": 65060, "total_steps": 181800, "loss": 0.0223, "lr": 4.053824772013522e-05, "epoch": 7.157315731573157, "percentage": 35.79, "elapsed_time": "2:33:54", "remaining_time": "4:36:10", "throughput": 1486.63, "total_tokens": 13728672} {"current_steps": 65065, "total_steps": 181800, "loss": 0.0156, "lr": 4.053636745843397e-05, "epoch": 7.1578657865786575, "percentage": 35.79, "elapsed_time": "2:33:55", "remaining_time": "4:36:09", "throughput": 1486.63, "total_tokens": 13729696} {"current_steps": 65070, "total_steps": 181800, "loss": 0.0088, "lr": 4.053448705354147e-05, "epoch": 7.158415841584159, "percentage": 35.79, "elapsed_time": "2:33:56", "remaining_time": "4:36:08", "throughput": 1486.63, "total_tokens": 13730720} {"current_steps": 65075, "total_steps": 181800, "loss": 0.0251, "lr": 4.0532606505475065e-05, "epoch": 7.158965896589659, "percentage": 35.79, "elapsed_time": "2:33:56", "remaining_time": "4:36:08", "throughput": 1486.64, "total_tokens": 13731840} {"current_steps": 65080, "total_steps": 181800, "loss": 0.0071, "lr": 4.053072581425208e-05, "epoch": 7.15951595159516, "percentage": 35.8, "elapsed_time": "2:33:57", "remaining_time": "4:36:07", "throughput": 1486.65, "total_tokens": 13732992} {"current_steps": 65085, "total_steps": 181800, "loss": 0.0082, "lr": 4.052884497988983e-05, "epoch": 7.16006600660066, "percentage": 35.8, "elapsed_time": "2:33:58", "remaining_time": "4:36:06", "throughput": 1486.66, "total_tokens": 13734048} {"current_steps": 65090, "total_steps": 181800, "loss": 0.0265, "lr": 4.052696400240569e-05, "epoch": 7.16061606160616, "percentage": 35.8, "elapsed_time": "2:33:58", "remaining_time": "4:36:05", "throughput": 1486.67, "total_tokens": 13735168} {"current_steps": 65095, "total_steps": 181800, "loss": 0.0681, "lr": 4.052508288181696e-05, "epoch": 7.161166116611661, "percentage": 35.81, "elapsed_time": "2:33:59", "remaining_time": "4:36:05", "throughput": 1486.67, "total_tokens": 13736224} {"current_steps": 65100, "total_steps": 181800, "loss": 0.083, "lr": 4.052320161814099e-05, "epoch": 7.161716171617162, "percentage": 35.81, "elapsed_time": "2:34:00", "remaining_time": "4:36:04", "throughput": 1486.67, "total_tokens": 13737248} {"current_steps": 65105, "total_steps": 181800, "loss": 0.0061, "lr": 4.052132021139513e-05, "epoch": 7.162266226622663, "percentage": 35.81, "elapsed_time": "2:34:00", "remaining_time": "4:36:03", "throughput": 1486.67, "total_tokens": 13738272} {"current_steps": 65110, "total_steps": 181800, "loss": 0.0824, "lr": 4.05194386615967e-05, "epoch": 7.162816281628163, "percentage": 35.81, "elapsed_time": "2:34:01", "remaining_time": "4:36:02", "throughput": 1486.67, "total_tokens": 13739296} {"current_steps": 65115, "total_steps": 181800, "loss": 0.0909, "lr": 4.051755696876306e-05, "epoch": 7.163366336633663, "percentage": 35.82, "elapsed_time": "2:34:02", "remaining_time": "4:36:02", "throughput": 1486.67, "total_tokens": 13740352} {"current_steps": 65120, "total_steps": 181800, "loss": 0.0315, "lr": 4.051567513291153e-05, "epoch": 7.163916391639164, "percentage": 35.82, "elapsed_time": "2:34:03", "remaining_time": "4:36:01", "throughput": 1486.68, "total_tokens": 13741408} {"current_steps": 65125, "total_steps": 181800, "loss": 0.0238, "lr": 4.0513793154059476e-05, "epoch": 7.164466446644664, "percentage": 35.82, "elapsed_time": "2:34:03", "remaining_time": "4:36:00", "throughput": 1486.68, "total_tokens": 13742464} {"current_steps": 65130, "total_steps": 181800, "loss": 0.1014, "lr": 4.0511911032224234e-05, "epoch": 7.165016501650165, "percentage": 35.83, "elapsed_time": "2:34:04", "remaining_time": "4:35:59", "throughput": 1486.68, "total_tokens": 13743520} {"current_steps": 65135, "total_steps": 181800, "loss": 0.0612, "lr": 4.051002876742316e-05, "epoch": 7.165566556655666, "percentage": 35.83, "elapsed_time": "2:34:05", "remaining_time": "4:35:59", "throughput": 1486.68, "total_tokens": 13744512} {"current_steps": 65140, "total_steps": 181800, "loss": 0.038, "lr": 4.050814635967358e-05, "epoch": 7.166116611661166, "percentage": 35.83, "elapsed_time": "2:34:05", "remaining_time": "4:35:58", "throughput": 1486.68, "total_tokens": 13745568} {"current_steps": 65145, "total_steps": 181800, "loss": 0.0653, "lr": 4.0506263808992854e-05, "epoch": 7.166666666666667, "percentage": 35.83, "elapsed_time": "2:34:06", "remaining_time": "4:35:57", "throughput": 1486.68, "total_tokens": 13746592} {"current_steps": 65150, "total_steps": 181800, "loss": 0.0945, "lr": 4.050438111539835e-05, "epoch": 7.167216721672167, "percentage": 35.84, "elapsed_time": "2:34:07", "remaining_time": "4:35:56", "throughput": 1486.68, "total_tokens": 13747616} {"current_steps": 65155, "total_steps": 181800, "loss": 0.0662, "lr": 4.05024982789074e-05, "epoch": 7.167766776677667, "percentage": 35.84, "elapsed_time": "2:34:07", "remaining_time": "4:35:56", "throughput": 1486.69, "total_tokens": 13748704} {"current_steps": 65160, "total_steps": 181800, "loss": 0.0284, "lr": 4.0500615299537356e-05, "epoch": 7.1683168316831685, "percentage": 35.84, "elapsed_time": "2:34:08", "remaining_time": "4:35:55", "throughput": 1486.69, "total_tokens": 13749760} {"current_steps": 65165, "total_steps": 181800, "loss": 0.0053, "lr": 4.049873217730558e-05, "epoch": 7.168866886688669, "percentage": 35.84, "elapsed_time": "2:34:09", "remaining_time": "4:35:54", "throughput": 1486.7, "total_tokens": 13750880} {"current_steps": 65170, "total_steps": 181800, "loss": 0.0584, "lr": 4.0496848912229425e-05, "epoch": 7.16941694169417, "percentage": 35.85, "elapsed_time": "2:34:09", "remaining_time": "4:35:53", "throughput": 1486.7, "total_tokens": 13751936} {"current_steps": 65175, "total_steps": 181800, "loss": 0.0405, "lr": 4.049496550432625e-05, "epoch": 7.16996699669967, "percentage": 35.85, "elapsed_time": "2:34:10", "remaining_time": "4:35:53", "throughput": 1486.71, "total_tokens": 13753056} {"current_steps": 65180, "total_steps": 181800, "loss": 0.0092, "lr": 4.0493081953613424e-05, "epoch": 7.17051705170517, "percentage": 35.85, "elapsed_time": "2:34:11", "remaining_time": "4:35:52", "throughput": 1486.72, "total_tokens": 13754112} {"current_steps": 65185, "total_steps": 181800, "loss": 0.0375, "lr": 4.0491198260108284e-05, "epoch": 7.171067106710671, "percentage": 35.86, "elapsed_time": "2:34:12", "remaining_time": "4:35:51", "throughput": 1486.72, "total_tokens": 13755168} {"current_steps": 65190, "total_steps": 181800, "loss": 0.0458, "lr": 4.0489314423828206e-05, "epoch": 7.1716171617161715, "percentage": 35.86, "elapsed_time": "2:34:12", "remaining_time": "4:35:50", "throughput": 1486.72, "total_tokens": 13756192} {"current_steps": 65195, "total_steps": 181800, "loss": 0.009, "lr": 4.048743044479055e-05, "epoch": 7.172167216721673, "percentage": 35.86, "elapsed_time": "2:34:13", "remaining_time": "4:35:50", "throughput": 1486.72, "total_tokens": 13757216} {"current_steps": 65200, "total_steps": 181800, "loss": 0.0347, "lr": 4.0485546323012684e-05, "epoch": 7.172717271727173, "percentage": 35.86, "elapsed_time": "2:34:14", "remaining_time": "4:35:49", "throughput": 1486.72, "total_tokens": 13758272} {"current_steps": 65205, "total_steps": 181800, "loss": 0.0972, "lr": 4.048366205851196e-05, "epoch": 7.173267326732673, "percentage": 35.87, "elapsed_time": "2:34:14", "remaining_time": "4:35:48", "throughput": 1486.72, "total_tokens": 13759328} {"current_steps": 65210, "total_steps": 181800, "loss": 0.0847, "lr": 4.048177765130576e-05, "epoch": 7.173817381738174, "percentage": 35.87, "elapsed_time": "2:34:15", "remaining_time": "4:35:48", "throughput": 1486.73, "total_tokens": 13760448} {"current_steps": 65215, "total_steps": 181800, "loss": 0.1131, "lr": 4.047989310141144e-05, "epoch": 7.174367436743674, "percentage": 35.87, "elapsed_time": "2:34:16", "remaining_time": "4:35:47", "throughput": 1486.74, "total_tokens": 13761504} {"current_steps": 65220, "total_steps": 181800, "loss": 0.0837, "lr": 4.047800840884637e-05, "epoch": 7.174917491749175, "percentage": 35.87, "elapsed_time": "2:34:16", "remaining_time": "4:35:46", "throughput": 1486.74, "total_tokens": 13762560} {"current_steps": 65225, "total_steps": 181800, "loss": 0.0499, "lr": 4.047612357362793e-05, "epoch": 7.175467546754676, "percentage": 35.88, "elapsed_time": "2:34:17", "remaining_time": "4:35:45", "throughput": 1486.75, "total_tokens": 13763648} {"current_steps": 65230, "total_steps": 181800, "loss": 0.015, "lr": 4.047423859577348e-05, "epoch": 7.176017601760176, "percentage": 35.88, "elapsed_time": "2:34:18", "remaining_time": "4:35:45", "throughput": 1486.75, "total_tokens": 13764736} {"current_steps": 65235, "total_steps": 181800, "loss": 0.0298, "lr": 4.047235347530041e-05, "epoch": 7.176567656765677, "percentage": 35.88, "elapsed_time": "2:34:18", "remaining_time": "4:35:44", "throughput": 1486.76, "total_tokens": 13765792} {"current_steps": 65240, "total_steps": 181800, "loss": 0.0233, "lr": 4.047046821222607e-05, "epoch": 7.177117711771177, "percentage": 35.89, "elapsed_time": "2:34:19", "remaining_time": "4:35:43", "throughput": 1486.75, "total_tokens": 13766784} {"current_steps": 65245, "total_steps": 181800, "loss": 0.0087, "lr": 4.046858280656785e-05, "epoch": 7.177667766776677, "percentage": 35.89, "elapsed_time": "2:34:20", "remaining_time": "4:35:42", "throughput": 1486.75, "total_tokens": 13767776} {"current_steps": 65250, "total_steps": 181800, "loss": 0.0143, "lr": 4.0466697258343126e-05, "epoch": 7.178217821782178, "percentage": 35.89, "elapsed_time": "2:34:21", "remaining_time": "4:35:42", "throughput": 1486.74, "total_tokens": 13768736} {"current_steps": 65255, "total_steps": 181800, "loss": 0.0128, "lr": 4.0464811567569276e-05, "epoch": 7.178767876787679, "percentage": 35.89, "elapsed_time": "2:34:21", "remaining_time": "4:35:41", "throughput": 1486.75, "total_tokens": 13769792} {"current_steps": 65260, "total_steps": 181800, "loss": 0.0234, "lr": 4.046292573426368e-05, "epoch": 7.17931793179318, "percentage": 35.9, "elapsed_time": "2:34:22", "remaining_time": "4:35:40", "throughput": 1486.75, "total_tokens": 13770880} {"current_steps": 65265, "total_steps": 181800, "loss": 0.0305, "lr": 4.046103975844371e-05, "epoch": 7.17986798679868, "percentage": 35.9, "elapsed_time": "2:34:23", "remaining_time": "4:35:39", "throughput": 1486.76, "total_tokens": 13772000} {"current_steps": 65270, "total_steps": 181800, "loss": 0.007, "lr": 4.045915364012677e-05, "epoch": 7.18041804180418, "percentage": 35.9, "elapsed_time": "2:34:23", "remaining_time": "4:35:39", "throughput": 1486.76, "total_tokens": 13773024} {"current_steps": 65275, "total_steps": 181800, "loss": 0.1247, "lr": 4.045726737933021e-05, "epoch": 7.180968096809681, "percentage": 35.9, "elapsed_time": "2:34:24", "remaining_time": "4:35:38", "throughput": 1486.77, "total_tokens": 13774112} {"current_steps": 65280, "total_steps": 181800, "loss": 0.0539, "lr": 4.045538097607144e-05, "epoch": 7.181518151815181, "percentage": 35.91, "elapsed_time": "2:34:25", "remaining_time": "4:35:37", "throughput": 1486.77, "total_tokens": 13775168} {"current_steps": 65285, "total_steps": 181800, "loss": 0.0108, "lr": 4.0453494430367844e-05, "epoch": 7.1820682068206825, "percentage": 35.91, "elapsed_time": "2:34:25", "remaining_time": "4:35:36", "throughput": 1486.78, "total_tokens": 13776224} {"current_steps": 65290, "total_steps": 181800, "loss": 0.04, "lr": 4.045160774223681e-05, "epoch": 7.182618261826183, "percentage": 35.91, "elapsed_time": "2:34:26", "remaining_time": "4:35:36", "throughput": 1486.78, "total_tokens": 13777312} {"current_steps": 65295, "total_steps": 181800, "loss": 0.1552, "lr": 4.044972091169572e-05, "epoch": 7.183168316831683, "percentage": 35.92, "elapsed_time": "2:34:27", "remaining_time": "4:35:35", "throughput": 1486.79, "total_tokens": 13778368} {"current_steps": 65300, "total_steps": 181800, "loss": 0.0396, "lr": 4.044783393876196e-05, "epoch": 7.183718371837184, "percentage": 35.92, "elapsed_time": "2:34:27", "remaining_time": "4:35:34", "throughput": 1486.79, "total_tokens": 13779424} {"current_steps": 65305, "total_steps": 181800, "loss": 0.009, "lr": 4.044594682345292e-05, "epoch": 7.184268426842684, "percentage": 35.92, "elapsed_time": "2:34:28", "remaining_time": "4:35:33", "throughput": 1486.8, "total_tokens": 13780512} {"current_steps": 65310, "total_steps": 181800, "loss": 0.0757, "lr": 4.0444059565786014e-05, "epoch": 7.184818481848184, "percentage": 35.92, "elapsed_time": "2:34:29", "remaining_time": "4:35:33", "throughput": 1486.8, "total_tokens": 13781600} {"current_steps": 65315, "total_steps": 181800, "loss": 0.0286, "lr": 4.044217216577861e-05, "epoch": 7.1853685368536855, "percentage": 35.93, "elapsed_time": "2:34:29", "remaining_time": "4:35:32", "throughput": 1486.8, "total_tokens": 13782656} {"current_steps": 65320, "total_steps": 181800, "loss": 0.0253, "lr": 4.0440284623448134e-05, "epoch": 7.185918591859186, "percentage": 35.93, "elapsed_time": "2:34:30", "remaining_time": "4:35:31", "throughput": 1486.81, "total_tokens": 13783744} {"current_steps": 65325, "total_steps": 181800, "loss": 0.023, "lr": 4.0438396938811953e-05, "epoch": 7.186468646864687, "percentage": 35.93, "elapsed_time": "2:34:31", "remaining_time": "4:35:30", "throughput": 1486.81, "total_tokens": 13784800} {"current_steps": 65330, "total_steps": 181800, "loss": 0.0682, "lr": 4.0436509111887465e-05, "epoch": 7.187018701870187, "percentage": 35.94, "elapsed_time": "2:34:32", "remaining_time": "4:35:30", "throughput": 1486.81, "total_tokens": 13785824} {"current_steps": 65335, "total_steps": 181800, "loss": 0.0178, "lr": 4.043462114269208e-05, "epoch": 7.187568756875687, "percentage": 35.94, "elapsed_time": "2:34:32", "remaining_time": "4:35:29", "throughput": 1486.82, "total_tokens": 13786912} {"current_steps": 65340, "total_steps": 181800, "loss": 0.0118, "lr": 4.043273303124322e-05, "epoch": 7.188118811881188, "percentage": 35.94, "elapsed_time": "2:34:33", "remaining_time": "4:35:28", "throughput": 1486.82, "total_tokens": 13787904} {"current_steps": 65345, "total_steps": 181800, "loss": 0.0668, "lr": 4.0430844777558254e-05, "epoch": 7.1886688668866885, "percentage": 35.94, "elapsed_time": "2:34:34", "remaining_time": "4:35:27", "throughput": 1486.82, "total_tokens": 13788928} {"current_steps": 65350, "total_steps": 181800, "loss": 0.0552, "lr": 4.042895638165459e-05, "epoch": 7.18921892189219, "percentage": 35.95, "elapsed_time": "2:34:34", "remaining_time": "4:35:27", "throughput": 1486.82, "total_tokens": 13789952} {"current_steps": 65355, "total_steps": 181800, "loss": 0.0206, "lr": 4.042706784354964e-05, "epoch": 7.18976897689769, "percentage": 35.95, "elapsed_time": "2:34:35", "remaining_time": "4:35:26", "throughput": 1486.82, "total_tokens": 13791040} {"current_steps": 65360, "total_steps": 181800, "loss": 0.0215, "lr": 4.0425179163260806e-05, "epoch": 7.19031903190319, "percentage": 35.95, "elapsed_time": "2:34:36", "remaining_time": "4:35:25", "throughput": 1486.82, "total_tokens": 13792064} {"current_steps": 65365, "total_steps": 181800, "loss": 0.0373, "lr": 4.042329034080551e-05, "epoch": 7.190869086908691, "percentage": 35.95, "elapsed_time": "2:34:36", "remaining_time": "4:35:24", "throughput": 1486.81, "total_tokens": 13793024} {"current_steps": 65370, "total_steps": 181800, "loss": 0.167, "lr": 4.0421401376201134e-05, "epoch": 7.191419141914191, "percentage": 35.96, "elapsed_time": "2:34:37", "remaining_time": "4:35:24", "throughput": 1486.81, "total_tokens": 13794048} {"current_steps": 65375, "total_steps": 181800, "loss": 0.0186, "lr": 4.041951226946511e-05, "epoch": 7.191969196919692, "percentage": 35.96, "elapsed_time": "2:34:38", "remaining_time": "4:35:23", "throughput": 1486.81, "total_tokens": 13795072} {"current_steps": 65380, "total_steps": 181800, "loss": 0.014, "lr": 4.041762302061484e-05, "epoch": 7.192519251925193, "percentage": 35.96, "elapsed_time": "2:34:38", "remaining_time": "4:35:22", "throughput": 1486.82, "total_tokens": 13796128} {"current_steps": 65385, "total_steps": 181800, "loss": 0.0644, "lr": 4.041573362966773e-05, "epoch": 7.193069306930693, "percentage": 35.97, "elapsed_time": "2:34:39", "remaining_time": "4:35:22", "throughput": 1486.82, "total_tokens": 13797216} {"current_steps": 65390, "total_steps": 181800, "loss": 0.008, "lr": 4.0413844096641204e-05, "epoch": 7.193619361936194, "percentage": 35.97, "elapsed_time": "2:34:40", "remaining_time": "4:35:21", "throughput": 1486.82, "total_tokens": 13798208} {"current_steps": 65395, "total_steps": 181800, "loss": 0.1184, "lr": 4.041195442155268e-05, "epoch": 7.194169416941694, "percentage": 35.97, "elapsed_time": "2:34:41", "remaining_time": "4:35:20", "throughput": 1486.82, "total_tokens": 13799200} {"current_steps": 65400, "total_steps": 181800, "loss": 0.0132, "lr": 4.041006460441955e-05, "epoch": 7.194719471947194, "percentage": 35.97, "elapsed_time": "2:34:41", "remaining_time": "4:35:19", "throughput": 1486.82, "total_tokens": 13800256} {"current_steps": 65405, "total_steps": 181800, "loss": 0.0275, "lr": 4.040817464525927e-05, "epoch": 7.195269526952695, "percentage": 35.98, "elapsed_time": "2:34:42", "remaining_time": "4:35:19", "throughput": 1486.82, "total_tokens": 13801312} {"current_steps": 65410, "total_steps": 181800, "loss": 0.0121, "lr": 4.0406284544089224e-05, "epoch": 7.195819581958196, "percentage": 35.98, "elapsed_time": "2:34:43", "remaining_time": "4:35:18", "throughput": 1486.83, "total_tokens": 13802368} {"current_steps": 65415, "total_steps": 181800, "loss": 0.0323, "lr": 4.040439430092685e-05, "epoch": 7.196369636963697, "percentage": 35.98, "elapsed_time": "2:34:43", "remaining_time": "4:35:17", "throughput": 1486.83, "total_tokens": 13803392} {"current_steps": 65420, "total_steps": 181800, "loss": 0.133, "lr": 4.0402503915789566e-05, "epoch": 7.196919691969197, "percentage": 35.98, "elapsed_time": "2:34:44", "remaining_time": "4:35:16", "throughput": 1486.83, "total_tokens": 13804448} {"current_steps": 65425, "total_steps": 181800, "loss": 0.0139, "lr": 4.040061338869479e-05, "epoch": 7.197469746974697, "percentage": 35.99, "elapsed_time": "2:34:45", "remaining_time": "4:35:16", "throughput": 1486.83, "total_tokens": 13805440} {"current_steps": 65430, "total_steps": 181800, "loss": 0.0252, "lr": 4.039872271965995e-05, "epoch": 7.198019801980198, "percentage": 35.99, "elapsed_time": "2:34:45", "remaining_time": "4:35:15", "throughput": 1486.84, "total_tokens": 13806560} {"current_steps": 65435, "total_steps": 181800, "loss": 0.0395, "lr": 4.039683190870248e-05, "epoch": 7.198569856985698, "percentage": 35.99, "elapsed_time": "2:34:46", "remaining_time": "4:35:14", "throughput": 1486.84, "total_tokens": 13807648} {"current_steps": 65440, "total_steps": 181800, "loss": 0.0272, "lr": 4.03949409558398e-05, "epoch": 7.1991199119911995, "percentage": 36.0, "elapsed_time": "2:34:47", "remaining_time": "4:35:13", "throughput": 1486.84, "total_tokens": 13808704} {"current_steps": 65445, "total_steps": 181800, "loss": 0.066, "lr": 4.039304986108933e-05, "epoch": 7.1996699669967, "percentage": 36.0, "elapsed_time": "2:34:47", "remaining_time": "4:35:13", "throughput": 1486.85, "total_tokens": 13809824} {"current_steps": 65450, "total_steps": 181800, "loss": 0.1218, "lr": 4.03911586244685e-05, "epoch": 7.2002200220022, "percentage": 36.0, "elapsed_time": "2:34:48", "remaining_time": "4:35:12", "throughput": 1486.86, "total_tokens": 13810880} {"current_steps": 65455, "total_steps": 181800, "loss": 0.194, "lr": 4.038926724599475e-05, "epoch": 7.200770077007701, "percentage": 36.0, "elapsed_time": "2:34:49", "remaining_time": "4:35:11", "throughput": 1486.86, "total_tokens": 13811936} {"current_steps": 65460, "total_steps": 181800, "loss": 0.0648, "lr": 4.0387375725685514e-05, "epoch": 7.201320132013201, "percentage": 36.01, "elapsed_time": "2:34:50", "remaining_time": "4:35:10", "throughput": 1486.87, "total_tokens": 13813024} {"current_steps": 65465, "total_steps": 181800, "loss": 0.0429, "lr": 4.038548406355822e-05, "epoch": 7.201870187018702, "percentage": 36.01, "elapsed_time": "2:34:50", "remaining_time": "4:35:10", "throughput": 1486.87, "total_tokens": 13814080} {"current_steps": 65470, "total_steps": 181800, "loss": 0.0395, "lr": 4.03835922596303e-05, "epoch": 7.2024202420242025, "percentage": 36.01, "elapsed_time": "2:34:51", "remaining_time": "4:35:09", "throughput": 1486.87, "total_tokens": 13815136} {"current_steps": 65475, "total_steps": 181800, "loss": 0.096, "lr": 4.038170031391919e-05, "epoch": 7.202970297029703, "percentage": 36.01, "elapsed_time": "2:34:52", "remaining_time": "4:35:08", "throughput": 1486.88, "total_tokens": 13816224} {"current_steps": 65480, "total_steps": 181800, "loss": 0.0189, "lr": 4.037980822644233e-05, "epoch": 7.203520352035204, "percentage": 36.02, "elapsed_time": "2:34:52", "remaining_time": "4:35:07", "throughput": 1486.87, "total_tokens": 13817184} {"current_steps": 65485, "total_steps": 181800, "loss": 0.0044, "lr": 4.0377915997217153e-05, "epoch": 7.204070407040704, "percentage": 36.02, "elapsed_time": "2:34:53", "remaining_time": "4:35:07", "throughput": 1486.88, "total_tokens": 13818240} {"current_steps": 65490, "total_steps": 181800, "loss": 0.043, "lr": 4.037602362626111e-05, "epoch": 7.204620462046204, "percentage": 36.02, "elapsed_time": "2:34:54", "remaining_time": "4:35:06", "throughput": 1486.88, "total_tokens": 13819264} {"current_steps": 65495, "total_steps": 181800, "loss": 0.044, "lr": 4.0374131113591626e-05, "epoch": 7.205170517051705, "percentage": 36.03, "elapsed_time": "2:34:54", "remaining_time": "4:35:05", "throughput": 1486.88, "total_tokens": 13820320} {"current_steps": 65500, "total_steps": 181800, "loss": 0.0268, "lr": 4.0372238459226166e-05, "epoch": 7.2057205720572055, "percentage": 36.03, "elapsed_time": "2:34:55", "remaining_time": "4:35:04", "throughput": 1486.89, "total_tokens": 13821408} {"current_steps": 65505, "total_steps": 181800, "loss": 0.0167, "lr": 4.0370345663182154e-05, "epoch": 7.206270627062707, "percentage": 36.03, "elapsed_time": "2:34:56", "remaining_time": "4:35:04", "throughput": 1486.89, "total_tokens": 13822496} {"current_steps": 65510, "total_steps": 181800, "loss": 0.0527, "lr": 4.0368452725477045e-05, "epoch": 7.206820682068207, "percentage": 36.03, "elapsed_time": "2:34:56", "remaining_time": "4:35:03", "throughput": 1486.9, "total_tokens": 13823584} {"current_steps": 65515, "total_steps": 181800, "loss": 0.0169, "lr": 4.0366559646128274e-05, "epoch": 7.207370737073707, "percentage": 36.04, "elapsed_time": "2:34:57", "remaining_time": "4:35:02", "throughput": 1486.9, "total_tokens": 13824640} {"current_steps": 65520, "total_steps": 181800, "loss": 0.0721, "lr": 4.03646664251533e-05, "epoch": 7.207920792079208, "percentage": 36.04, "elapsed_time": "2:34:58", "remaining_time": "4:35:01", "throughput": 1486.91, "total_tokens": 13825728} {"current_steps": 65525, "total_steps": 181800, "loss": 0.0343, "lr": 4.036277306256957e-05, "epoch": 7.208470847084708, "percentage": 36.04, "elapsed_time": "2:34:58", "remaining_time": "4:35:01", "throughput": 1486.91, "total_tokens": 13826784} {"current_steps": 65530, "total_steps": 181800, "loss": 0.0066, "lr": 4.0360879558394535e-05, "epoch": 7.209020902090209, "percentage": 36.05, "elapsed_time": "2:34:59", "remaining_time": "4:35:00", "throughput": 1486.91, "total_tokens": 13827840} {"current_steps": 65535, "total_steps": 181800, "loss": 0.1298, "lr": 4.0358985912645634e-05, "epoch": 7.20957095709571, "percentage": 36.05, "elapsed_time": "2:35:00", "remaining_time": "4:34:59", "throughput": 1486.92, "total_tokens": 13828896} {"current_steps": 65540, "total_steps": 181800, "loss": 0.0111, "lr": 4.0357092125340336e-05, "epoch": 7.21012101210121, "percentage": 36.05, "elapsed_time": "2:35:01", "remaining_time": "4:34:58", "throughput": 1486.92, "total_tokens": 13829952} {"current_steps": 65545, "total_steps": 181800, "loss": 0.023, "lr": 4.035519819649609e-05, "epoch": 7.210671067106711, "percentage": 36.05, "elapsed_time": "2:35:01", "remaining_time": "4:34:58", "throughput": 1486.93, "total_tokens": 13831072} {"current_steps": 65550, "total_steps": 181800, "loss": 0.0095, "lr": 4.035330412613035e-05, "epoch": 7.211221122112211, "percentage": 36.06, "elapsed_time": "2:35:02", "remaining_time": "4:34:57", "throughput": 1486.94, "total_tokens": 13832160} {"current_steps": 65555, "total_steps": 181800, "loss": 0.0432, "lr": 4.0351409914260576e-05, "epoch": 7.211771177117711, "percentage": 36.06, "elapsed_time": "2:35:03", "remaining_time": "4:34:56", "throughput": 1486.94, "total_tokens": 13833248} {"current_steps": 65560, "total_steps": 181800, "loss": 0.0656, "lr": 4.034951556090422e-05, "epoch": 7.212321232123212, "percentage": 36.06, "elapsed_time": "2:35:03", "remaining_time": "4:34:55", "throughput": 1486.95, "total_tokens": 13834304} {"current_steps": 65565, "total_steps": 181800, "loss": 0.0207, "lr": 4.034762106607874e-05, "epoch": 7.212871287128713, "percentage": 36.06, "elapsed_time": "2:35:04", "remaining_time": "4:34:55", "throughput": 1486.96, "total_tokens": 13835392} {"current_steps": 65570, "total_steps": 181800, "loss": 0.0234, "lr": 4.03457264298016e-05, "epoch": 7.213421342134214, "percentage": 36.07, "elapsed_time": "2:35:05", "remaining_time": "4:34:54", "throughput": 1486.96, "total_tokens": 13836480} {"current_steps": 65575, "total_steps": 181800, "loss": 0.037, "lr": 4.034383165209027e-05, "epoch": 7.213971397139714, "percentage": 36.07, "elapsed_time": "2:35:05", "remaining_time": "4:34:53", "throughput": 1486.96, "total_tokens": 13837504} {"current_steps": 65580, "total_steps": 181800, "loss": 0.026, "lr": 4.0341936732962206e-05, "epoch": 7.214521452145214, "percentage": 36.07, "elapsed_time": "2:35:06", "remaining_time": "4:34:52", "throughput": 1486.97, "total_tokens": 13838560} {"current_steps": 65585, "total_steps": 181800, "loss": 0.0351, "lr": 4.034004167243487e-05, "epoch": 7.215071507150715, "percentage": 36.08, "elapsed_time": "2:35:07", "remaining_time": "4:34:52", "throughput": 1486.97, "total_tokens": 13839616} {"current_steps": 65590, "total_steps": 181800, "loss": 0.0045, "lr": 4.033814647052574e-05, "epoch": 7.215621562156215, "percentage": 36.08, "elapsed_time": "2:35:07", "remaining_time": "4:34:51", "throughput": 1486.97, "total_tokens": 13840640} {"current_steps": 65595, "total_steps": 181800, "loss": 0.0051, "lr": 4.033625112725226e-05, "epoch": 7.2161716171617165, "percentage": 36.08, "elapsed_time": "2:35:08", "remaining_time": "4:34:50", "throughput": 1486.97, "total_tokens": 13841696} {"current_steps": 65600, "total_steps": 181800, "loss": 0.0424, "lr": 4.033435564263192e-05, "epoch": 7.216721672167217, "percentage": 36.08, "elapsed_time": "2:35:09", "remaining_time": "4:34:50", "throughput": 1486.97, "total_tokens": 13842720} {"current_steps": 65605, "total_steps": 181800, "loss": 0.1002, "lr": 4.033246001668218e-05, "epoch": 7.217271727172717, "percentage": 36.09, "elapsed_time": "2:35:10", "remaining_time": "4:34:49", "throughput": 1486.98, "total_tokens": 13843808} {"current_steps": 65610, "total_steps": 181800, "loss": 0.0165, "lr": 4.033056424942051e-05, "epoch": 7.217821782178218, "percentage": 36.09, "elapsed_time": "2:35:10", "remaining_time": "4:34:48", "throughput": 1486.98, "total_tokens": 13844864} {"current_steps": 65615, "total_steps": 181800, "loss": 0.095, "lr": 4.032866834086439e-05, "epoch": 7.218371837183718, "percentage": 36.09, "elapsed_time": "2:35:11", "remaining_time": "4:34:47", "throughput": 1486.99, "total_tokens": 13845952} {"current_steps": 65620, "total_steps": 181800, "loss": 0.0228, "lr": 4.032677229103129e-05, "epoch": 7.218921892189219, "percentage": 36.09, "elapsed_time": "2:35:12", "remaining_time": "4:34:47", "throughput": 1486.99, "total_tokens": 13847008} {"current_steps": 65625, "total_steps": 181800, "loss": 0.0789, "lr": 4.032487609993869e-05, "epoch": 7.2194719471947195, "percentage": 36.1, "elapsed_time": "2:35:12", "remaining_time": "4:34:46", "throughput": 1486.99, "total_tokens": 13848064} {"current_steps": 65630, "total_steps": 181800, "loss": 0.1536, "lr": 4.0322979767604055e-05, "epoch": 7.22002200220022, "percentage": 36.1, "elapsed_time": "2:35:13", "remaining_time": "4:34:45", "throughput": 1486.99, "total_tokens": 13849056} {"current_steps": 65635, "total_steps": 181800, "loss": 0.0627, "lr": 4.032108329404486e-05, "epoch": 7.220572057205721, "percentage": 36.1, "elapsed_time": "2:35:14", "remaining_time": "4:34:44", "throughput": 1486.99, "total_tokens": 13850112} {"current_steps": 65640, "total_steps": 181800, "loss": 0.0308, "lr": 4.03191866792786e-05, "epoch": 7.221122112211221, "percentage": 36.11, "elapsed_time": "2:35:14", "remaining_time": "4:34:44", "throughput": 1487.0, "total_tokens": 13851168} {"current_steps": 65645, "total_steps": 181800, "loss": 0.0062, "lr": 4.031728992332274e-05, "epoch": 7.221672167216722, "percentage": 36.11, "elapsed_time": "2:35:15", "remaining_time": "4:34:43", "throughput": 1486.99, "total_tokens": 13852160} {"current_steps": 65650, "total_steps": 181800, "loss": 0.1484, "lr": 4.031539302619478e-05, "epoch": 7.222222222222222, "percentage": 36.11, "elapsed_time": "2:35:16", "remaining_time": "4:34:42", "throughput": 1486.99, "total_tokens": 13853184} {"current_steps": 65655, "total_steps": 181800, "loss": 0.0743, "lr": 4.0313495987912184e-05, "epoch": 7.2227722772277225, "percentage": 36.11, "elapsed_time": "2:35:16", "remaining_time": "4:34:41", "throughput": 1487.0, "total_tokens": 13854304} {"current_steps": 65660, "total_steps": 181800, "loss": 0.0686, "lr": 4.031159880849244e-05, "epoch": 7.223322332233224, "percentage": 36.12, "elapsed_time": "2:35:17", "remaining_time": "4:34:41", "throughput": 1486.99, "total_tokens": 13855264} {"current_steps": 65665, "total_steps": 181800, "loss": 0.0761, "lr": 4.0309701487953056e-05, "epoch": 7.223872387238724, "percentage": 36.12, "elapsed_time": "2:35:18", "remaining_time": "4:34:40", "throughput": 1486.99, "total_tokens": 13856256} {"current_steps": 65670, "total_steps": 181800, "loss": 0.0293, "lr": 4.030780402631148e-05, "epoch": 7.224422442244224, "percentage": 36.12, "elapsed_time": "2:35:19", "remaining_time": "4:34:39", "throughput": 1486.99, "total_tokens": 13857280} {"current_steps": 65675, "total_steps": 181800, "loss": 0.0098, "lr": 4.030590642358523e-05, "epoch": 7.224972497249725, "percentage": 36.12, "elapsed_time": "2:35:19", "remaining_time": "4:34:38", "throughput": 1486.99, "total_tokens": 13858336} {"current_steps": 65680, "total_steps": 181800, "loss": 0.0177, "lr": 4.030400867979178e-05, "epoch": 7.225522552255225, "percentage": 36.13, "elapsed_time": "2:35:20", "remaining_time": "4:34:38", "throughput": 1487.0, "total_tokens": 13859424} {"current_steps": 65685, "total_steps": 181800, "loss": 0.038, "lr": 4.030211079494863e-05, "epoch": 7.226072607260726, "percentage": 36.13, "elapsed_time": "2:35:21", "remaining_time": "4:34:37", "throughput": 1487.0, "total_tokens": 13860512} {"current_steps": 65690, "total_steps": 181800, "loss": 0.0288, "lr": 4.0300212769073265e-05, "epoch": 7.226622662266227, "percentage": 36.13, "elapsed_time": "2:35:21", "remaining_time": "4:34:36", "throughput": 1487.0, "total_tokens": 13861536} {"current_steps": 65695, "total_steps": 181800, "loss": 0.072, "lr": 4.029831460218317e-05, "epoch": 7.227172717271727, "percentage": 36.14, "elapsed_time": "2:35:22", "remaining_time": "4:34:35", "throughput": 1487.01, "total_tokens": 13862592} {"current_steps": 65700, "total_steps": 181800, "loss": 0.0059, "lr": 4.029641629429587e-05, "epoch": 7.227722772277228, "percentage": 36.14, "elapsed_time": "2:35:23", "remaining_time": "4:34:35", "throughput": 1487.01, "total_tokens": 13863616} {"current_steps": 65705, "total_steps": 181800, "loss": 0.0317, "lr": 4.029451784542883e-05, "epoch": 7.228272827282728, "percentage": 36.14, "elapsed_time": "2:35:23", "remaining_time": "4:34:34", "throughput": 1487.01, "total_tokens": 13864736} {"current_steps": 65710, "total_steps": 181800, "loss": 0.0253, "lr": 4.0292619255599564e-05, "epoch": 7.228822882288229, "percentage": 36.14, "elapsed_time": "2:35:24", "remaining_time": "4:34:33", "throughput": 1487.02, "total_tokens": 13865792} {"current_steps": 65715, "total_steps": 181800, "loss": 0.0062, "lr": 4.0290720524825556e-05, "epoch": 7.229372937293729, "percentage": 36.15, "elapsed_time": "2:35:25", "remaining_time": "4:34:32", "throughput": 1487.02, "total_tokens": 13866848} {"current_steps": 65720, "total_steps": 181800, "loss": 0.0171, "lr": 4.028882165312432e-05, "epoch": 7.22992299229923, "percentage": 36.15, "elapsed_time": "2:35:25", "remaining_time": "4:34:32", "throughput": 1487.02, "total_tokens": 13867872} {"current_steps": 65725, "total_steps": 181800, "loss": 0.0593, "lr": 4.028692264051335e-05, "epoch": 7.230473047304731, "percentage": 36.15, "elapsed_time": "2:35:26", "remaining_time": "4:34:31", "throughput": 1487.03, "total_tokens": 13868992} {"current_steps": 65730, "total_steps": 181800, "loss": 0.0205, "lr": 4.0285023487010146e-05, "epoch": 7.231023102310231, "percentage": 36.16, "elapsed_time": "2:35:27", "remaining_time": "4:34:30", "throughput": 1487.04, "total_tokens": 13870080} {"current_steps": 65735, "total_steps": 181800, "loss": 0.0079, "lr": 4.028312419263222e-05, "epoch": 7.231573157315731, "percentage": 36.16, "elapsed_time": "2:35:28", "remaining_time": "4:34:30", "throughput": 1487.05, "total_tokens": 13871200} {"current_steps": 65740, "total_steps": 181800, "loss": 0.0956, "lr": 4.028122475739706e-05, "epoch": 7.232123212321232, "percentage": 36.16, "elapsed_time": "2:35:28", "remaining_time": "4:34:29", "throughput": 1487.05, "total_tokens": 13872288} {"current_steps": 65745, "total_steps": 181800, "loss": 0.1421, "lr": 4.02793251813222e-05, "epoch": 7.232673267326732, "percentage": 36.16, "elapsed_time": "2:35:29", "remaining_time": "4:34:28", "throughput": 1487.05, "total_tokens": 13873344} {"current_steps": 65750, "total_steps": 181800, "loss": 0.0016, "lr": 4.0277425464425126e-05, "epoch": 7.2332233223322335, "percentage": 36.17, "elapsed_time": "2:35:30", "remaining_time": "4:34:27", "throughput": 1487.06, "total_tokens": 13874400} {"current_steps": 65755, "total_steps": 181800, "loss": 0.0194, "lr": 4.027552560672335e-05, "epoch": 7.233773377337734, "percentage": 36.17, "elapsed_time": "2:35:30", "remaining_time": "4:34:27", "throughput": 1487.06, "total_tokens": 13875488} {"current_steps": 65760, "total_steps": 181800, "loss": 0.111, "lr": 4.0273625608234385e-05, "epoch": 7.234323432343234, "percentage": 36.17, "elapsed_time": "2:35:31", "remaining_time": "4:34:26", "throughput": 1487.07, "total_tokens": 13876544} {"current_steps": 65765, "total_steps": 181800, "loss": 0.064, "lr": 4.027172546897574e-05, "epoch": 7.234873487348735, "percentage": 36.17, "elapsed_time": "2:35:32", "remaining_time": "4:34:25", "throughput": 1487.06, "total_tokens": 13877568} {"current_steps": 65770, "total_steps": 181800, "loss": 0.006, "lr": 4.026982518896494e-05, "epoch": 7.235423542354235, "percentage": 36.18, "elapsed_time": "2:35:32", "remaining_time": "4:34:24", "throughput": 1487.07, "total_tokens": 13878656} {"current_steps": 65775, "total_steps": 181800, "loss": 0.0856, "lr": 4.026792476821948e-05, "epoch": 7.235973597359736, "percentage": 36.18, "elapsed_time": "2:35:33", "remaining_time": "4:34:24", "throughput": 1487.08, "total_tokens": 13879776} {"current_steps": 65780, "total_steps": 181800, "loss": 0.0097, "lr": 4.026602420675688e-05, "epoch": 7.2365236523652365, "percentage": 36.18, "elapsed_time": "2:35:34", "remaining_time": "4:34:23", "throughput": 1487.08, "total_tokens": 13880832} {"current_steps": 65785, "total_steps": 181800, "loss": 0.0879, "lr": 4.026412350459466e-05, "epoch": 7.237073707370737, "percentage": 36.19, "elapsed_time": "2:35:34", "remaining_time": "4:34:22", "throughput": 1487.09, "total_tokens": 13881952} {"current_steps": 65790, "total_steps": 181800, "loss": 0.0087, "lr": 4.026222266175034e-05, "epoch": 7.237623762376238, "percentage": 36.19, "elapsed_time": "2:35:35", "remaining_time": "4:34:21", "throughput": 1487.1, "total_tokens": 13883040} {"current_steps": 65795, "total_steps": 181800, "loss": 0.087, "lr": 4.026032167824144e-05, "epoch": 7.238173817381738, "percentage": 36.19, "elapsed_time": "2:35:36", "remaining_time": "4:34:21", "throughput": 1487.1, "total_tokens": 13884032} {"current_steps": 65800, "total_steps": 181800, "loss": 0.0393, "lr": 4.025842055408548e-05, "epoch": 7.238723872387239, "percentage": 36.19, "elapsed_time": "2:35:37", "remaining_time": "4:34:20", "throughput": 1487.1, "total_tokens": 13885056} {"current_steps": 65805, "total_steps": 181800, "loss": 0.0249, "lr": 4.025651928929998e-05, "epoch": 7.239273927392739, "percentage": 36.2, "elapsed_time": "2:35:37", "remaining_time": "4:34:19", "throughput": 1487.11, "total_tokens": 13886208} {"current_steps": 65810, "total_steps": 181800, "loss": 0.0272, "lr": 4.0254617883902454e-05, "epoch": 7.2398239823982395, "percentage": 36.2, "elapsed_time": "2:35:38", "remaining_time": "4:34:18", "throughput": 1487.11, "total_tokens": 13887200} {"current_steps": 65815, "total_steps": 181800, "loss": 0.052, "lr": 4.0252716337910444e-05, "epoch": 7.240374037403741, "percentage": 36.2, "elapsed_time": "2:35:39", "remaining_time": "4:34:18", "throughput": 1487.11, "total_tokens": 13888224} {"current_steps": 65820, "total_steps": 181800, "loss": 0.0272, "lr": 4.0250814651341464e-05, "epoch": 7.240924092409241, "percentage": 36.2, "elapsed_time": "2:35:39", "remaining_time": "4:34:17", "throughput": 1487.11, "total_tokens": 13889312} {"current_steps": 65825, "total_steps": 181800, "loss": 0.0305, "lr": 4.024891282421304e-05, "epoch": 7.241474147414741, "percentage": 36.21, "elapsed_time": "2:35:40", "remaining_time": "4:34:16", "throughput": 1487.11, "total_tokens": 13890272} {"current_steps": 65830, "total_steps": 181800, "loss": 0.0239, "lr": 4.02470108565427e-05, "epoch": 7.242024202420242, "percentage": 36.21, "elapsed_time": "2:35:41", "remaining_time": "4:34:15", "throughput": 1487.12, "total_tokens": 13891424} {"current_steps": 65835, "total_steps": 181800, "loss": 0.0623, "lr": 4.0245108748347985e-05, "epoch": 7.242574257425742, "percentage": 36.21, "elapsed_time": "2:35:41", "remaining_time": "4:34:15", "throughput": 1487.13, "total_tokens": 13892512} {"current_steps": 65840, "total_steps": 181800, "loss": 0.0019, "lr": 4.024320649964642e-05, "epoch": 7.243124312431243, "percentage": 36.22, "elapsed_time": "2:35:42", "remaining_time": "4:34:14", "throughput": 1487.14, "total_tokens": 13893600} {"current_steps": 65845, "total_steps": 181800, "loss": 0.0166, "lr": 4.0241304110455524e-05, "epoch": 7.243674367436744, "percentage": 36.22, "elapsed_time": "2:35:43", "remaining_time": "4:34:13", "throughput": 1487.15, "total_tokens": 13894720} {"current_steps": 65850, "total_steps": 181800, "loss": 0.0457, "lr": 4.023940158079285e-05, "epoch": 7.244224422442244, "percentage": 36.22, "elapsed_time": "2:35:43", "remaining_time": "4:34:12", "throughput": 1487.16, "total_tokens": 13895840} {"current_steps": 65855, "total_steps": 181800, "loss": 0.0299, "lr": 4.023749891067592e-05, "epoch": 7.244774477447745, "percentage": 36.22, "elapsed_time": "2:35:44", "remaining_time": "4:34:12", "throughput": 1487.16, "total_tokens": 13896896} {"current_steps": 65860, "total_steps": 181800, "loss": 0.0795, "lr": 4.023559610012228e-05, "epoch": 7.245324532453245, "percentage": 36.23, "elapsed_time": "2:35:45", "remaining_time": "4:34:11", "throughput": 1487.16, "total_tokens": 13897952} {"current_steps": 65865, "total_steps": 181800, "loss": 0.0111, "lr": 4.023369314914946e-05, "epoch": 7.245874587458746, "percentage": 36.23, "elapsed_time": "2:35:45", "remaining_time": "4:34:10", "throughput": 1487.17, "total_tokens": 13899008} {"current_steps": 65870, "total_steps": 181800, "loss": 0.0134, "lr": 4.0231790057774995e-05, "epoch": 7.2464246424642464, "percentage": 36.23, "elapsed_time": "2:35:46", "remaining_time": "4:34:09", "throughput": 1487.16, "total_tokens": 13900032} {"current_steps": 65875, "total_steps": 181800, "loss": 0.2226, "lr": 4.022988682601644e-05, "epoch": 7.246974697469747, "percentage": 36.23, "elapsed_time": "2:35:47", "remaining_time": "4:34:09", "throughput": 1487.17, "total_tokens": 13901088} {"current_steps": 65880, "total_steps": 181800, "loss": 0.0488, "lr": 4.0227983453891314e-05, "epoch": 7.247524752475248, "percentage": 36.24, "elapsed_time": "2:35:48", "remaining_time": "4:34:08", "throughput": 1487.17, "total_tokens": 13902176} {"current_steps": 65885, "total_steps": 181800, "loss": 0.067, "lr": 4.022607994141718e-05, "epoch": 7.248074807480748, "percentage": 36.24, "elapsed_time": "2:35:48", "remaining_time": "4:34:07", "throughput": 1487.18, "total_tokens": 13903232} {"current_steps": 65890, "total_steps": 181800, "loss": 0.0295, "lr": 4.022417628861157e-05, "epoch": 7.248624862486249, "percentage": 36.24, "elapsed_time": "2:35:49", "remaining_time": "4:34:06", "throughput": 1487.18, "total_tokens": 13904256} {"current_steps": 65895, "total_steps": 181800, "loss": 0.0518, "lr": 4.022227249549203e-05, "epoch": 7.249174917491749, "percentage": 36.25, "elapsed_time": "2:35:50", "remaining_time": "4:34:06", "throughput": 1487.18, "total_tokens": 13905312} {"current_steps": 65900, "total_steps": 181800, "loss": 0.0281, "lr": 4.022036856207611e-05, "epoch": 7.2497249724972495, "percentage": 36.25, "elapsed_time": "2:35:50", "remaining_time": "4:34:05", "throughput": 1487.19, "total_tokens": 13906400} {"current_steps": 65905, "total_steps": 181800, "loss": 0.0653, "lr": 4.021846448838136e-05, "epoch": 7.2502750275027505, "percentage": 36.25, "elapsed_time": "2:35:51", "remaining_time": "4:34:04", "throughput": 1487.18, "total_tokens": 13907392} {"current_steps": 65910, "total_steps": 181800, "loss": 0.0643, "lr": 4.021656027442533e-05, "epoch": 7.250825082508251, "percentage": 36.25, "elapsed_time": "2:35:52", "remaining_time": "4:34:04", "throughput": 1487.18, "total_tokens": 13908416} {"current_steps": 65915, "total_steps": 181800, "loss": 0.0313, "lr": 4.0214655920225555e-05, "epoch": 7.251375137513751, "percentage": 36.26, "elapsed_time": "2:35:52", "remaining_time": "4:34:03", "throughput": 1487.19, "total_tokens": 13909536} {"current_steps": 65920, "total_steps": 181800, "loss": 0.0427, "lr": 4.02127514257996e-05, "epoch": 7.251925192519252, "percentage": 36.26, "elapsed_time": "2:35:53", "remaining_time": "4:34:02", "throughput": 1487.19, "total_tokens": 13910560} {"current_steps": 65925, "total_steps": 181800, "loss": 0.0673, "lr": 4.0210846791165016e-05, "epoch": 7.252475247524752, "percentage": 36.26, "elapsed_time": "2:35:54", "remaining_time": "4:34:01", "throughput": 1487.2, "total_tokens": 13911616} {"current_steps": 65930, "total_steps": 181800, "loss": 0.0384, "lr": 4.020894201633935e-05, "epoch": 7.253025302530253, "percentage": 36.27, "elapsed_time": "2:35:54", "remaining_time": "4:34:01", "throughput": 1487.2, "total_tokens": 13912672} {"current_steps": 65935, "total_steps": 181800, "loss": 0.0391, "lr": 4.020703710134017e-05, "epoch": 7.2535753575357536, "percentage": 36.27, "elapsed_time": "2:35:55", "remaining_time": "4:34:00", "throughput": 1487.2, "total_tokens": 13913728} {"current_steps": 65940, "total_steps": 181800, "loss": 0.0264, "lr": 4.020513204618503e-05, "epoch": 7.254125412541254, "percentage": 36.27, "elapsed_time": "2:35:56", "remaining_time": "4:33:59", "throughput": 1487.2, "total_tokens": 13914752} {"current_steps": 65945, "total_steps": 181800, "loss": 0.0265, "lr": 4.020322685089147e-05, "epoch": 7.254675467546755, "percentage": 36.27, "elapsed_time": "2:35:57", "remaining_time": "4:33:58", "throughput": 1487.21, "total_tokens": 13915808} {"current_steps": 65950, "total_steps": 181800, "loss": 0.0167, "lr": 4.0201321515477074e-05, "epoch": 7.255225522552255, "percentage": 36.28, "elapsed_time": "2:35:57", "remaining_time": "4:33:58", "throughput": 1487.21, "total_tokens": 13916832} {"current_steps": 65955, "total_steps": 181800, "loss": 0.0668, "lr": 4.019941603995939e-05, "epoch": 7.255775577557756, "percentage": 36.28, "elapsed_time": "2:35:58", "remaining_time": "4:33:57", "throughput": 1487.22, "total_tokens": 13917952} {"current_steps": 65960, "total_steps": 181800, "loss": 0.0347, "lr": 4.019751042435599e-05, "epoch": 7.256325632563256, "percentage": 36.28, "elapsed_time": "2:35:59", "remaining_time": "4:33:56", "throughput": 1487.22, "total_tokens": 13919008} {"current_steps": 65965, "total_steps": 181800, "loss": 0.008, "lr": 4.019560466868442e-05, "epoch": 7.256875687568757, "percentage": 36.28, "elapsed_time": "2:35:59", "remaining_time": "4:33:55", "throughput": 1487.22, "total_tokens": 13920064} {"current_steps": 65970, "total_steps": 181800, "loss": 0.0612, "lr": 4.019369877296225e-05, "epoch": 7.257425742574258, "percentage": 36.29, "elapsed_time": "2:36:00", "remaining_time": "4:33:55", "throughput": 1487.23, "total_tokens": 13921152} {"current_steps": 65975, "total_steps": 181800, "loss": 0.0126, "lr": 4.019179273720706e-05, "epoch": 7.257975797579758, "percentage": 36.29, "elapsed_time": "2:36:01", "remaining_time": "4:33:54", "throughput": 1487.23, "total_tokens": 13922176} {"current_steps": 65980, "total_steps": 181800, "loss": 0.278, "lr": 4.01898865614364e-05, "epoch": 7.258525852585258, "percentage": 36.29, "elapsed_time": "2:36:01", "remaining_time": "4:33:53", "throughput": 1487.22, "total_tokens": 13923168} {"current_steps": 65985, "total_steps": 181800, "loss": 0.05, "lr": 4.0187980245667846e-05, "epoch": 7.259075907590759, "percentage": 36.3, "elapsed_time": "2:36:02", "remaining_time": "4:33:52", "throughput": 1487.22, "total_tokens": 13924128} {"current_steps": 65990, "total_steps": 181800, "loss": 0.0349, "lr": 4.018607378991896e-05, "epoch": 7.259625962596259, "percentage": 36.3, "elapsed_time": "2:36:03", "remaining_time": "4:33:52", "throughput": 1487.22, "total_tokens": 13925216} {"current_steps": 65995, "total_steps": 181800, "loss": 0.0185, "lr": 4.0184167194207325e-05, "epoch": 7.2601760176017605, "percentage": 36.3, "elapsed_time": "2:36:03", "remaining_time": "4:33:51", "throughput": 1487.22, "total_tokens": 13926208} {"current_steps": 66000, "total_steps": 181800, "loss": 0.024, "lr": 4.01822604585505e-05, "epoch": 7.260726072607261, "percentage": 36.3, "elapsed_time": "2:36:04", "remaining_time": "4:33:50", "throughput": 1487.22, "total_tokens": 13927232} {"current_steps": 66005, "total_steps": 181800, "loss": 0.0082, "lr": 4.018035358296607e-05, "epoch": 7.261276127612761, "percentage": 36.31, "elapsed_time": "2:36:05", "remaining_time": "4:33:49", "throughput": 1487.23, "total_tokens": 13928320} {"current_steps": 66010, "total_steps": 181800, "loss": 0.0176, "lr": 4.017844656747161e-05, "epoch": 7.261826182618262, "percentage": 36.31, "elapsed_time": "2:36:05", "remaining_time": "4:33:49", "throughput": 1487.23, "total_tokens": 13929376} {"current_steps": 66015, "total_steps": 181800, "loss": 0.0641, "lr": 4.0176539412084684e-05, "epoch": 7.262376237623762, "percentage": 36.31, "elapsed_time": "2:36:06", "remaining_time": "4:33:48", "throughput": 1487.23, "total_tokens": 13930368} {"current_steps": 66020, "total_steps": 181800, "loss": 0.0197, "lr": 4.017463211682288e-05, "epoch": 7.262926292629263, "percentage": 36.31, "elapsed_time": "2:36:07", "remaining_time": "4:33:47", "throughput": 1487.23, "total_tokens": 13931392} {"current_steps": 66025, "total_steps": 181800, "loss": 0.0091, "lr": 4.017272468170377e-05, "epoch": 7.2634763476347635, "percentage": 36.32, "elapsed_time": "2:36:08", "remaining_time": "4:33:46", "throughput": 1487.23, "total_tokens": 13932448} {"current_steps": 66030, "total_steps": 181800, "loss": 0.0045, "lr": 4.017081710674494e-05, "epoch": 7.264026402640264, "percentage": 36.32, "elapsed_time": "2:36:08", "remaining_time": "4:33:46", "throughput": 1487.23, "total_tokens": 13933536} {"current_steps": 66035, "total_steps": 181800, "loss": 0.0133, "lr": 4.0168909391963973e-05, "epoch": 7.264576457645765, "percentage": 36.32, "elapsed_time": "2:36:09", "remaining_time": "4:33:45", "throughput": 1487.24, "total_tokens": 13934592} {"current_steps": 66040, "total_steps": 181800, "loss": 0.026, "lr": 4.0167001537378443e-05, "epoch": 7.265126512651265, "percentage": 36.33, "elapsed_time": "2:36:10", "remaining_time": "4:33:44", "throughput": 1487.24, "total_tokens": 13935680} {"current_steps": 66045, "total_steps": 181800, "loss": 0.2335, "lr": 4.016509354300594e-05, "epoch": 7.265676567656766, "percentage": 36.33, "elapsed_time": "2:36:10", "remaining_time": "4:33:43", "throughput": 1487.25, "total_tokens": 13936768} {"current_steps": 66050, "total_steps": 181800, "loss": 0.0032, "lr": 4.016318540886404e-05, "epoch": 7.266226622662266, "percentage": 36.33, "elapsed_time": "2:36:11", "remaining_time": "4:33:43", "throughput": 1487.25, "total_tokens": 13937824} {"current_steps": 66055, "total_steps": 181800, "loss": 0.0551, "lr": 4.0161277134970345e-05, "epoch": 7.2667766776677665, "percentage": 36.33, "elapsed_time": "2:36:12", "remaining_time": "4:33:42", "throughput": 1487.25, "total_tokens": 13938848} {"current_steps": 66060, "total_steps": 181800, "loss": 0.0028, "lr": 4.015936872134242e-05, "epoch": 7.267326732673268, "percentage": 36.34, "elapsed_time": "2:36:12", "remaining_time": "4:33:41", "throughput": 1487.26, "total_tokens": 13939936} {"current_steps": 66065, "total_steps": 181800, "loss": 0.0573, "lr": 4.015746016799788e-05, "epoch": 7.267876787678768, "percentage": 36.34, "elapsed_time": "2:36:13", "remaining_time": "4:33:40", "throughput": 1487.26, "total_tokens": 13940992} {"current_steps": 66070, "total_steps": 181800, "loss": 0.1309, "lr": 4.0155551474954296e-05, "epoch": 7.268426842684269, "percentage": 36.34, "elapsed_time": "2:36:14", "remaining_time": "4:33:40", "throughput": 1487.26, "total_tokens": 13941984} {"current_steps": 66075, "total_steps": 181800, "loss": 0.0443, "lr": 4.0153642642229274e-05, "epoch": 7.268976897689769, "percentage": 36.34, "elapsed_time": "2:36:14", "remaining_time": "4:33:39", "throughput": 1487.27, "total_tokens": 13943072} {"current_steps": 66080, "total_steps": 181800, "loss": 0.0291, "lr": 4.01517336698404e-05, "epoch": 7.269526952695269, "percentage": 36.35, "elapsed_time": "2:36:15", "remaining_time": "4:33:38", "throughput": 1487.27, "total_tokens": 13944160} {"current_steps": 66085, "total_steps": 181800, "loss": 0.0987, "lr": 4.014982455780525e-05, "epoch": 7.27007700770077, "percentage": 36.35, "elapsed_time": "2:36:16", "remaining_time": "4:33:38", "throughput": 1487.28, "total_tokens": 13945216} {"current_steps": 66090, "total_steps": 181800, "loss": 0.0438, "lr": 4.014791530614145e-05, "epoch": 7.270627062706271, "percentage": 36.35, "elapsed_time": "2:36:17", "remaining_time": "4:33:37", "throughput": 1487.28, "total_tokens": 13946272} {"current_steps": 66095, "total_steps": 181800, "loss": 0.0124, "lr": 4.014600591486658e-05, "epoch": 7.271177117711771, "percentage": 36.36, "elapsed_time": "2:36:17", "remaining_time": "4:33:36", "throughput": 1487.28, "total_tokens": 13947296} {"current_steps": 66100, "total_steps": 181800, "loss": 0.0689, "lr": 4.0144096383998256e-05, "epoch": 7.271727172717272, "percentage": 36.36, "elapsed_time": "2:36:18", "remaining_time": "4:33:35", "throughput": 1487.28, "total_tokens": 13948352} {"current_steps": 66105, "total_steps": 181800, "loss": 0.0098, "lr": 4.0142186713554045e-05, "epoch": 7.272277227722772, "percentage": 36.36, "elapsed_time": "2:36:19", "remaining_time": "4:33:35", "throughput": 1487.29, "total_tokens": 13949440} {"current_steps": 66110, "total_steps": 181800, "loss": 0.0724, "lr": 4.0140276903551566e-05, "epoch": 7.272827282728273, "percentage": 36.36, "elapsed_time": "2:36:19", "remaining_time": "4:33:34", "throughput": 1487.3, "total_tokens": 13950528} {"current_steps": 66115, "total_steps": 181800, "loss": 0.0688, "lr": 4.013836695400842e-05, "epoch": 7.273377337733773, "percentage": 36.37, "elapsed_time": "2:36:20", "remaining_time": "4:33:33", "throughput": 1487.29, "total_tokens": 13951520} {"current_steps": 66120, "total_steps": 181800, "loss": 0.0392, "lr": 4.0136456864942216e-05, "epoch": 7.273927392739274, "percentage": 36.37, "elapsed_time": "2:36:21", "remaining_time": "4:33:32", "throughput": 1487.3, "total_tokens": 13952608} {"current_steps": 66125, "total_steps": 181800, "loss": 0.0209, "lr": 4.0134546636370553e-05, "epoch": 7.274477447744775, "percentage": 36.37, "elapsed_time": "2:36:21", "remaining_time": "4:33:32", "throughput": 1487.31, "total_tokens": 13953696} {"current_steps": 66130, "total_steps": 181800, "loss": 0.0234, "lr": 4.013263626831103e-05, "epoch": 7.275027502750275, "percentage": 36.38, "elapsed_time": "2:36:22", "remaining_time": "4:33:31", "throughput": 1487.3, "total_tokens": 13954688} {"current_steps": 66135, "total_steps": 181800, "loss": 0.0369, "lr": 4.013072576078126e-05, "epoch": 7.275577557755776, "percentage": 36.38, "elapsed_time": "2:36:23", "remaining_time": "4:33:30", "throughput": 1487.31, "total_tokens": 13955776} {"current_steps": 66140, "total_steps": 181800, "loss": 0.0527, "lr": 4.012881511379886e-05, "epoch": 7.276127612761276, "percentage": 36.38, "elapsed_time": "2:36:23", "remaining_time": "4:33:29", "throughput": 1487.31, "total_tokens": 13956832} {"current_steps": 66145, "total_steps": 181800, "loss": 0.0426, "lr": 4.012690432738142e-05, "epoch": 7.276677667766776, "percentage": 36.38, "elapsed_time": "2:36:24", "remaining_time": "4:33:29", "throughput": 1487.32, "total_tokens": 13957888} {"current_steps": 66150, "total_steps": 181800, "loss": 0.0989, "lr": 4.012499340154656e-05, "epoch": 7.2772277227722775, "percentage": 36.39, "elapsed_time": "2:36:25", "remaining_time": "4:33:28", "throughput": 1487.32, "total_tokens": 13958912} {"current_steps": 66155, "total_steps": 181800, "loss": 0.0127, "lr": 4.0123082336311904e-05, "epoch": 7.277777777777778, "percentage": 36.39, "elapsed_time": "2:36:25", "remaining_time": "4:33:27", "throughput": 1487.32, "total_tokens": 13959936} {"current_steps": 66160, "total_steps": 181800, "loss": 0.0252, "lr": 4.012117113169505e-05, "epoch": 7.278327832783278, "percentage": 36.39, "elapsed_time": "2:36:26", "remaining_time": "4:33:26", "throughput": 1487.32, "total_tokens": 13960960} {"current_steps": 66165, "total_steps": 181800, "loss": 0.0399, "lr": 4.011925978771361e-05, "epoch": 7.278877887788779, "percentage": 36.39, "elapsed_time": "2:36:27", "remaining_time": "4:33:26", "throughput": 1487.33, "total_tokens": 13962080} {"current_steps": 66170, "total_steps": 181800, "loss": 0.0188, "lr": 4.011734830438522e-05, "epoch": 7.279427942794279, "percentage": 36.4, "elapsed_time": "2:36:28", "remaining_time": "4:33:25", "throughput": 1487.33, "total_tokens": 13963136} {"current_steps": 66175, "total_steps": 181800, "loss": 0.0331, "lr": 4.011543668172748e-05, "epoch": 7.27997799779978, "percentage": 36.4, "elapsed_time": "2:36:28", "remaining_time": "4:33:24", "throughput": 1487.33, "total_tokens": 13964192} {"current_steps": 66180, "total_steps": 181800, "loss": 0.1425, "lr": 4.011352491975802e-05, "epoch": 7.2805280528052805, "percentage": 36.4, "elapsed_time": "2:36:29", "remaining_time": "4:33:23", "throughput": 1487.33, "total_tokens": 13965248} {"current_steps": 66185, "total_steps": 181800, "loss": 0.0159, "lr": 4.0111613018494435e-05, "epoch": 7.281078107810781, "percentage": 36.41, "elapsed_time": "2:36:30", "remaining_time": "4:33:23", "throughput": 1487.34, "total_tokens": 13966368} {"current_steps": 66190, "total_steps": 181800, "loss": 0.0163, "lr": 4.010970097795438e-05, "epoch": 7.281628162816282, "percentage": 36.41, "elapsed_time": "2:36:30", "remaining_time": "4:33:22", "throughput": 1487.35, "total_tokens": 13967424} {"current_steps": 66195, "total_steps": 181800, "loss": 0.0864, "lr": 4.0107788798155456e-05, "epoch": 7.282178217821782, "percentage": 36.41, "elapsed_time": "2:36:31", "remaining_time": "4:33:21", "throughput": 1487.35, "total_tokens": 13968512} {"current_steps": 66200, "total_steps": 181800, "loss": 0.013, "lr": 4.010587647911529e-05, "epoch": 7.282728272827283, "percentage": 36.41, "elapsed_time": "2:36:32", "remaining_time": "4:33:20", "throughput": 1487.36, "total_tokens": 13969600} {"current_steps": 66205, "total_steps": 181800, "loss": 0.0145, "lr": 4.0103964020851514e-05, "epoch": 7.283278327832783, "percentage": 36.42, "elapsed_time": "2:36:32", "remaining_time": "4:33:20", "throughput": 1487.37, "total_tokens": 13970720} {"current_steps": 66210, "total_steps": 181800, "loss": 0.0417, "lr": 4.010205142338175e-05, "epoch": 7.2838283828382835, "percentage": 36.42, "elapsed_time": "2:36:33", "remaining_time": "4:33:19", "throughput": 1487.37, "total_tokens": 13971712} {"current_steps": 66215, "total_steps": 181800, "loss": 0.0227, "lr": 4.010013868672362e-05, "epoch": 7.284378437843785, "percentage": 36.42, "elapsed_time": "2:36:34", "remaining_time": "4:33:18", "throughput": 1487.37, "total_tokens": 13972768} {"current_steps": 66220, "total_steps": 181800, "loss": 0.0735, "lr": 4.009822581089475e-05, "epoch": 7.284928492849285, "percentage": 36.42, "elapsed_time": "2:36:34", "remaining_time": "4:33:17", "throughput": 1487.37, "total_tokens": 13973792} {"current_steps": 66225, "total_steps": 181800, "loss": 0.0707, "lr": 4.009631279591279e-05, "epoch": 7.285478547854786, "percentage": 36.43, "elapsed_time": "2:36:35", "remaining_time": "4:33:17", "throughput": 1487.38, "total_tokens": 13974912} {"current_steps": 66230, "total_steps": 181800, "loss": 0.059, "lr": 4.009439964179536e-05, "epoch": 7.286028602860286, "percentage": 36.43, "elapsed_time": "2:36:36", "remaining_time": "4:33:16", "throughput": 1487.39, "total_tokens": 13976032} {"current_steps": 66235, "total_steps": 181800, "loss": 0.0226, "lr": 4.009248634856008e-05, "epoch": 7.286578657865786, "percentage": 36.43, "elapsed_time": "2:36:37", "remaining_time": "4:33:15", "throughput": 1487.39, "total_tokens": 13977024} {"current_steps": 66240, "total_steps": 181800, "loss": 0.0536, "lr": 4.00905729162246e-05, "epoch": 7.287128712871287, "percentage": 36.44, "elapsed_time": "2:36:37", "remaining_time": "4:33:14", "throughput": 1487.39, "total_tokens": 13978112} {"current_steps": 66245, "total_steps": 181800, "loss": 0.0061, "lr": 4.0088659344806556e-05, "epoch": 7.287678767876788, "percentage": 36.44, "elapsed_time": "2:36:38", "remaining_time": "4:33:14", "throughput": 1487.4, "total_tokens": 13979168} {"current_steps": 66250, "total_steps": 181800, "loss": 0.0117, "lr": 4.0086745634323574e-05, "epoch": 7.288228822882289, "percentage": 36.44, "elapsed_time": "2:36:39", "remaining_time": "4:33:13", "throughput": 1487.4, "total_tokens": 13980192} {"current_steps": 66255, "total_steps": 181800, "loss": 0.0407, "lr": 4.00848317847933e-05, "epoch": 7.288778877887789, "percentage": 36.44, "elapsed_time": "2:36:39", "remaining_time": "4:33:12", "throughput": 1487.4, "total_tokens": 13981280} {"current_steps": 66260, "total_steps": 181800, "loss": 0.0052, "lr": 4.008291779623337e-05, "epoch": 7.289328932893289, "percentage": 36.45, "elapsed_time": "2:36:40", "remaining_time": "4:33:11", "throughput": 1487.41, "total_tokens": 13982336} {"current_steps": 66265, "total_steps": 181800, "loss": 0.0808, "lr": 4.008100366866142e-05, "epoch": 7.28987898789879, "percentage": 36.45, "elapsed_time": "2:36:41", "remaining_time": "4:33:11", "throughput": 1487.41, "total_tokens": 13983392} {"current_steps": 66270, "total_steps": 181800, "loss": 0.0378, "lr": 4.00790894020951e-05, "epoch": 7.29042904290429, "percentage": 36.45, "elapsed_time": "2:36:41", "remaining_time": "4:33:10", "throughput": 1487.42, "total_tokens": 13984480} {"current_steps": 66275, "total_steps": 181800, "loss": 0.0369, "lr": 4.007717499655205e-05, "epoch": 7.290979097909791, "percentage": 36.45, "elapsed_time": "2:36:42", "remaining_time": "4:33:09", "throughput": 1487.42, "total_tokens": 13985568} {"current_steps": 66280, "total_steps": 181800, "loss": 0.0208, "lr": 4.0075260452049906e-05, "epoch": 7.291529152915292, "percentage": 36.46, "elapsed_time": "2:36:43", "remaining_time": "4:33:08", "throughput": 1487.44, "total_tokens": 13986720} {"current_steps": 66285, "total_steps": 181800, "loss": 0.0177, "lr": 4.007334576860633e-05, "epoch": 7.292079207920792, "percentage": 36.46, "elapsed_time": "2:36:43", "remaining_time": "4:33:08", "throughput": 1487.45, "total_tokens": 13987872} {"current_steps": 66290, "total_steps": 181800, "loss": 0.0254, "lr": 4.007143094623894e-05, "epoch": 7.292629262926293, "percentage": 36.46, "elapsed_time": "2:36:44", "remaining_time": "4:33:07", "throughput": 1487.45, "total_tokens": 13988928} {"current_steps": 66295, "total_steps": 181800, "loss": 0.0326, "lr": 4.006951598496542e-05, "epoch": 7.293179317931793, "percentage": 36.47, "elapsed_time": "2:36:45", "remaining_time": "4:33:06", "throughput": 1487.45, "total_tokens": 13989984} {"current_steps": 66300, "total_steps": 181800, "loss": 0.0585, "lr": 4.00676008848034e-05, "epoch": 7.293729372937293, "percentage": 36.47, "elapsed_time": "2:36:46", "remaining_time": "4:33:06", "throughput": 1487.46, "total_tokens": 13991104} {"current_steps": 66305, "total_steps": 181800, "loss": 0.1065, "lr": 4.006568564577054e-05, "epoch": 7.2942794279427945, "percentage": 36.47, "elapsed_time": "2:36:46", "remaining_time": "4:33:05", "throughput": 1487.47, "total_tokens": 13992160} {"current_steps": 66310, "total_steps": 181800, "loss": 0.0242, "lr": 4.006377026788447e-05, "epoch": 7.294829482948295, "percentage": 36.47, "elapsed_time": "2:36:47", "remaining_time": "4:33:04", "throughput": 1487.47, "total_tokens": 13993248} {"current_steps": 66315, "total_steps": 181800, "loss": 0.0187, "lr": 4.006185475116286e-05, "epoch": 7.295379537953796, "percentage": 36.48, "elapsed_time": "2:36:48", "remaining_time": "4:33:03", "throughput": 1487.48, "total_tokens": 13994304} {"current_steps": 66320, "total_steps": 181800, "loss": 0.0182, "lr": 4.0059939095623365e-05, "epoch": 7.295929592959296, "percentage": 36.48, "elapsed_time": "2:36:48", "remaining_time": "4:33:03", "throughput": 1487.48, "total_tokens": 13995360} {"current_steps": 66325, "total_steps": 181800, "loss": 0.027, "lr": 4.0058023301283634e-05, "epoch": 7.296479647964796, "percentage": 36.48, "elapsed_time": "2:36:49", "remaining_time": "4:33:02", "throughput": 1487.48, "total_tokens": 13996416} {"current_steps": 66330, "total_steps": 181800, "loss": 0.013, "lr": 4.0056107368161336e-05, "epoch": 7.297029702970297, "percentage": 36.49, "elapsed_time": "2:36:50", "remaining_time": "4:33:01", "throughput": 1487.49, "total_tokens": 13997472} {"current_steps": 66335, "total_steps": 181800, "loss": 0.0468, "lr": 4.0054191296274116e-05, "epoch": 7.2975797579757975, "percentage": 36.49, "elapsed_time": "2:36:50", "remaining_time": "4:33:00", "throughput": 1487.49, "total_tokens": 13998560} {"current_steps": 66340, "total_steps": 181800, "loss": 0.0032, "lr": 4.005227508563964e-05, "epoch": 7.298129812981298, "percentage": 36.49, "elapsed_time": "2:36:51", "remaining_time": "4:33:00", "throughput": 1487.5, "total_tokens": 13999648} {"current_steps": 66345, "total_steps": 181800, "loss": 0.0064, "lr": 4.0050358736275567e-05, "epoch": 7.298679867986799, "percentage": 36.49, "elapsed_time": "2:36:52", "remaining_time": "4:32:59", "throughput": 1487.49, "total_tokens": 14000608} {"current_steps": 66350, "total_steps": 181800, "loss": 0.0153, "lr": 4.0048442248199555e-05, "epoch": 7.299229922992299, "percentage": 36.5, "elapsed_time": "2:36:52", "remaining_time": "4:32:58", "throughput": 1487.5, "total_tokens": 14001696} {"current_steps": 66355, "total_steps": 181800, "loss": 0.0619, "lr": 4.004652562142928e-05, "epoch": 7.2997799779978, "percentage": 36.5, "elapsed_time": "2:36:53", "remaining_time": "4:32:57", "throughput": 1487.51, "total_tokens": 14002816} {"current_steps": 66360, "total_steps": 181800, "loss": 0.1149, "lr": 4.0044608855982394e-05, "epoch": 7.3003300330033, "percentage": 36.5, "elapsed_time": "2:36:54", "remaining_time": "4:32:57", "throughput": 1487.51, "total_tokens": 14003872} {"current_steps": 66365, "total_steps": 181800, "loss": 0.1518, "lr": 4.004269195187657e-05, "epoch": 7.3008800880088005, "percentage": 36.5, "elapsed_time": "2:36:54", "remaining_time": "4:32:56", "throughput": 1487.51, "total_tokens": 14004896} {"current_steps": 66370, "total_steps": 181800, "loss": 0.0515, "lr": 4.004077490912946e-05, "epoch": 7.301430143014302, "percentage": 36.51, "elapsed_time": "2:36:55", "remaining_time": "4:32:55", "throughput": 1487.52, "total_tokens": 14005984} {"current_steps": 66375, "total_steps": 181800, "loss": 0.0364, "lr": 4.003885772775876e-05, "epoch": 7.301980198019802, "percentage": 36.51, "elapsed_time": "2:36:56", "remaining_time": "4:32:54", "throughput": 1487.51, "total_tokens": 14006976} {"current_steps": 66380, "total_steps": 181800, "loss": 0.2154, "lr": 4.003694040778212e-05, "epoch": 7.302530253025303, "percentage": 36.51, "elapsed_time": "2:36:57", "remaining_time": "4:32:54", "throughput": 1487.52, "total_tokens": 14008032} {"current_steps": 66385, "total_steps": 181800, "loss": 0.0835, "lr": 4.003502294921722e-05, "epoch": 7.303080308030803, "percentage": 36.52, "elapsed_time": "2:36:57", "remaining_time": "4:32:53", "throughput": 1487.52, "total_tokens": 14009120} {"current_steps": 66390, "total_steps": 181800, "loss": 0.0391, "lr": 4.003310535208172e-05, "epoch": 7.303630363036303, "percentage": 36.52, "elapsed_time": "2:36:58", "remaining_time": "4:32:52", "throughput": 1487.53, "total_tokens": 14010240} {"current_steps": 66395, "total_steps": 181800, "loss": 0.0107, "lr": 4.0031187616393304e-05, "epoch": 7.304180418041804, "percentage": 36.52, "elapsed_time": "2:36:59", "remaining_time": "4:32:51", "throughput": 1487.52, "total_tokens": 14011200} {"current_steps": 66400, "total_steps": 181800, "loss": 0.0264, "lr": 4.002926974216965e-05, "epoch": 7.304730473047305, "percentage": 36.52, "elapsed_time": "2:36:59", "remaining_time": "4:32:51", "throughput": 1487.53, "total_tokens": 14012256} {"current_steps": 66405, "total_steps": 181800, "loss": 0.0799, "lr": 4.002735172942842e-05, "epoch": 7.305280528052805, "percentage": 36.53, "elapsed_time": "2:37:00", "remaining_time": "4:32:50", "throughput": 1487.53, "total_tokens": 14013344} {"current_steps": 66410, "total_steps": 181800, "loss": 0.0086, "lr": 4.002543357818731e-05, "epoch": 7.305830583058306, "percentage": 36.53, "elapsed_time": "2:37:01", "remaining_time": "4:32:49", "throughput": 1487.54, "total_tokens": 14014400} {"current_steps": 66415, "total_steps": 181800, "loss": 0.0229, "lr": 4.002351528846398e-05, "epoch": 7.306380638063806, "percentage": 36.53, "elapsed_time": "2:37:01", "remaining_time": "4:32:49", "throughput": 1487.54, "total_tokens": 14015456} {"current_steps": 66420, "total_steps": 181800, "loss": 0.0376, "lr": 4.002159686027611e-05, "epoch": 7.306930693069307, "percentage": 36.53, "elapsed_time": "2:37:02", "remaining_time": "4:32:48", "throughput": 1487.54, "total_tokens": 14016512} {"current_steps": 66425, "total_steps": 181800, "loss": 0.0743, "lr": 4.0019678293641405e-05, "epoch": 7.307480748074807, "percentage": 36.54, "elapsed_time": "2:37:03", "remaining_time": "4:32:47", "throughput": 1487.54, "total_tokens": 14017536} {"current_steps": 66430, "total_steps": 181800, "loss": 0.0261, "lr": 4.001775958857753e-05, "epoch": 7.3080308030803085, "percentage": 36.54, "elapsed_time": "2:37:03", "remaining_time": "4:32:46", "throughput": 1487.55, "total_tokens": 14018624} {"current_steps": 66435, "total_steps": 181800, "loss": 0.1543, "lr": 4.0015840745102175e-05, "epoch": 7.308580858085809, "percentage": 36.54, "elapsed_time": "2:37:04", "remaining_time": "4:32:46", "throughput": 1487.55, "total_tokens": 14019648} {"current_steps": 66440, "total_steps": 181800, "loss": 0.1207, "lr": 4.001392176323301e-05, "epoch": 7.309130913091309, "percentage": 36.55, "elapsed_time": "2:37:05", "remaining_time": "4:32:45", "throughput": 1487.55, "total_tokens": 14020672} {"current_steps": 66445, "total_steps": 181800, "loss": 0.0093, "lr": 4.001200264298773e-05, "epoch": 7.30968096809681, "percentage": 36.55, "elapsed_time": "2:37:06", "remaining_time": "4:32:44", "throughput": 1487.55, "total_tokens": 14021696} {"current_steps": 66450, "total_steps": 181800, "loss": 0.0344, "lr": 4.001008338438403e-05, "epoch": 7.31023102310231, "percentage": 36.55, "elapsed_time": "2:37:06", "remaining_time": "4:32:43", "throughput": 1487.55, "total_tokens": 14022784} {"current_steps": 66455, "total_steps": 181800, "loss": 0.0352, "lr": 4.000816398743961e-05, "epoch": 7.31078107810781, "percentage": 36.55, "elapsed_time": "2:37:07", "remaining_time": "4:32:43", "throughput": 1487.56, "total_tokens": 14023840} {"current_steps": 66460, "total_steps": 181800, "loss": 0.0315, "lr": 4.0006244452172124e-05, "epoch": 7.3113311331133115, "percentage": 36.56, "elapsed_time": "2:37:08", "remaining_time": "4:32:42", "throughput": 1487.57, "total_tokens": 14024992} {"current_steps": 66465, "total_steps": 181800, "loss": 0.0069, "lr": 4.000432477859929e-05, "epoch": 7.311881188118812, "percentage": 36.56, "elapsed_time": "2:37:08", "remaining_time": "4:32:41", "throughput": 1487.57, "total_tokens": 14026048} {"current_steps": 66470, "total_steps": 181800, "loss": 0.0798, "lr": 4.0002404966738794e-05, "epoch": 7.312431243124313, "percentage": 36.56, "elapsed_time": "2:37:09", "remaining_time": "4:32:40", "throughput": 1487.57, "total_tokens": 14027040} {"current_steps": 66475, "total_steps": 181800, "loss": 0.1126, "lr": 4.0000485016608334e-05, "epoch": 7.312981298129813, "percentage": 36.56, "elapsed_time": "2:37:10", "remaining_time": "4:32:40", "throughput": 1487.58, "total_tokens": 14028160} {"current_steps": 66480, "total_steps": 181800, "loss": 0.0041, "lr": 3.99985649282256e-05, "epoch": 7.313531353135313, "percentage": 36.57, "elapsed_time": "2:37:10", "remaining_time": "4:32:39", "throughput": 1487.58, "total_tokens": 14029184} {"current_steps": 66485, "total_steps": 181800, "loss": 0.0343, "lr": 3.999664470160829e-05, "epoch": 7.314081408140814, "percentage": 36.57, "elapsed_time": "2:37:11", "remaining_time": "4:32:38", "throughput": 1487.59, "total_tokens": 14030304} {"current_steps": 66490, "total_steps": 181800, "loss": 0.0195, "lr": 3.99947243367741e-05, "epoch": 7.3146314631463145, "percentage": 36.57, "elapsed_time": "2:37:12", "remaining_time": "4:32:37", "throughput": 1487.6, "total_tokens": 14031392} {"current_steps": 66495, "total_steps": 181800, "loss": 0.0479, "lr": 3.999280383374073e-05, "epoch": 7.315181518151816, "percentage": 36.58, "elapsed_time": "2:37:12", "remaining_time": "4:32:37", "throughput": 1487.6, "total_tokens": 14032480} {"current_steps": 66500, "total_steps": 181800, "loss": 0.0185, "lr": 3.9990883192525876e-05, "epoch": 7.315731573157316, "percentage": 36.58, "elapsed_time": "2:37:13", "remaining_time": "4:32:36", "throughput": 1487.6, "total_tokens": 14033504} {"current_steps": 66505, "total_steps": 181800, "loss": 0.0985, "lr": 3.9988962413147254e-05, "epoch": 7.316281628162816, "percentage": 36.58, "elapsed_time": "2:37:14", "remaining_time": "4:32:35", "throughput": 1487.6, "total_tokens": 14034528} {"current_steps": 66510, "total_steps": 181800, "loss": 0.0474, "lr": 3.998704149562256e-05, "epoch": 7.316831683168317, "percentage": 36.58, "elapsed_time": "2:37:15", "remaining_time": "4:32:34", "throughput": 1487.61, "total_tokens": 14035584} {"current_steps": 66515, "total_steps": 181800, "loss": 0.0291, "lr": 3.998512043996949e-05, "epoch": 7.317381738173817, "percentage": 36.59, "elapsed_time": "2:37:15", "remaining_time": "4:32:34", "throughput": 1487.61, "total_tokens": 14036640} {"current_steps": 66520, "total_steps": 181800, "loss": 0.0045, "lr": 3.998319924620576e-05, "epoch": 7.3179317931793175, "percentage": 36.59, "elapsed_time": "2:37:16", "remaining_time": "4:32:33", "throughput": 1487.61, "total_tokens": 14037664} {"current_steps": 66525, "total_steps": 181800, "loss": 0.0806, "lr": 3.998127791434907e-05, "epoch": 7.318481848184819, "percentage": 36.59, "elapsed_time": "2:37:17", "remaining_time": "4:32:32", "throughput": 1487.61, "total_tokens": 14038688} {"current_steps": 66530, "total_steps": 181800, "loss": 0.0518, "lr": 3.9979356444417125e-05, "epoch": 7.319031903190319, "percentage": 36.6, "elapsed_time": "2:37:17", "remaining_time": "4:32:31", "throughput": 1487.62, "total_tokens": 14039776} {"current_steps": 66535, "total_steps": 181800, "loss": 0.0567, "lr": 3.997743483642765e-05, "epoch": 7.31958195819582, "percentage": 36.6, "elapsed_time": "2:37:18", "remaining_time": "4:32:31", "throughput": 1487.62, "total_tokens": 14040864} {"current_steps": 66540, "total_steps": 181800, "loss": 0.0294, "lr": 3.997551309039833e-05, "epoch": 7.32013201320132, "percentage": 36.6, "elapsed_time": "2:37:19", "remaining_time": "4:32:30", "throughput": 1487.63, "total_tokens": 14041952} {"current_steps": 66545, "total_steps": 181800, "loss": 0.071, "lr": 3.9973591206346904e-05, "epoch": 7.32068206820682, "percentage": 36.6, "elapsed_time": "2:37:19", "remaining_time": "4:32:29", "throughput": 1487.63, "total_tokens": 14043008} {"current_steps": 66550, "total_steps": 181800, "loss": 0.0229, "lr": 3.997166918429107e-05, "epoch": 7.321232123212321, "percentage": 36.61, "elapsed_time": "2:37:20", "remaining_time": "4:32:28", "throughput": 1487.63, "total_tokens": 14044032} {"current_steps": 66555, "total_steps": 181800, "loss": 0.0209, "lr": 3.996974702424855e-05, "epoch": 7.321782178217822, "percentage": 36.61, "elapsed_time": "2:37:21", "remaining_time": "4:32:28", "throughput": 1487.63, "total_tokens": 14045056} {"current_steps": 66560, "total_steps": 181800, "loss": 0.0327, "lr": 3.996782472623705e-05, "epoch": 7.322332233223323, "percentage": 36.61, "elapsed_time": "2:37:21", "remaining_time": "4:32:27", "throughput": 1487.64, "total_tokens": 14046208} {"current_steps": 66565, "total_steps": 181800, "loss": 0.0387, "lr": 3.996590229027428e-05, "epoch": 7.322882288228823, "percentage": 36.61, "elapsed_time": "2:37:22", "remaining_time": "4:32:26", "throughput": 1487.65, "total_tokens": 14047296} {"current_steps": 66570, "total_steps": 181800, "loss": 0.077, "lr": 3.996397971637799e-05, "epoch": 7.323432343234323, "percentage": 36.62, "elapsed_time": "2:37:23", "remaining_time": "4:32:25", "throughput": 1487.65, "total_tokens": 14048320} {"current_steps": 66575, "total_steps": 181800, "loss": 0.0447, "lr": 3.9962057004565864e-05, "epoch": 7.323982398239824, "percentage": 36.62, "elapsed_time": "2:37:23", "remaining_time": "4:32:25", "throughput": 1487.66, "total_tokens": 14049408} {"current_steps": 66580, "total_steps": 181800, "loss": 0.0362, "lr": 3.996013415485565e-05, "epoch": 7.324532453245324, "percentage": 36.62, "elapsed_time": "2:37:24", "remaining_time": "4:32:24", "throughput": 1487.66, "total_tokens": 14050528} {"current_steps": 66585, "total_steps": 181800, "loss": 0.087, "lr": 3.995821116726505e-05, "epoch": 7.325082508250825, "percentage": 36.63, "elapsed_time": "2:37:25", "remaining_time": "4:32:23", "throughput": 1487.66, "total_tokens": 14051552} {"current_steps": 66590, "total_steps": 181800, "loss": 0.0192, "lr": 3.99562880418118e-05, "epoch": 7.325632563256326, "percentage": 36.63, "elapsed_time": "2:37:26", "remaining_time": "4:32:23", "throughput": 1487.67, "total_tokens": 14052608} {"current_steps": 66595, "total_steps": 181800, "loss": 0.0441, "lr": 3.995436477851361e-05, "epoch": 7.326182618261826, "percentage": 36.63, "elapsed_time": "2:37:26", "remaining_time": "4:32:22", "throughput": 1487.66, "total_tokens": 14053600} {"current_steps": 66600, "total_steps": 181800, "loss": 0.0194, "lr": 3.995244137738823e-05, "epoch": 7.326732673267327, "percentage": 36.63, "elapsed_time": "2:37:27", "remaining_time": "4:32:21", "throughput": 1487.67, "total_tokens": 14054656} {"current_steps": 66605, "total_steps": 181800, "loss": 0.021, "lr": 3.995051783845337e-05, "epoch": 7.327282728272827, "percentage": 36.64, "elapsed_time": "2:37:28", "remaining_time": "4:32:20", "throughput": 1487.67, "total_tokens": 14055712} {"current_steps": 66610, "total_steps": 181800, "loss": 0.0142, "lr": 3.9948594161726754e-05, "epoch": 7.327832783278327, "percentage": 36.64, "elapsed_time": "2:37:28", "remaining_time": "4:32:20", "throughput": 1487.68, "total_tokens": 14056800} {"current_steps": 66615, "total_steps": 181800, "loss": 0.0461, "lr": 3.994667034722612e-05, "epoch": 7.3283828382838285, "percentage": 36.64, "elapsed_time": "2:37:29", "remaining_time": "4:32:19", "throughput": 1487.69, "total_tokens": 14057888} {"current_steps": 66620, "total_steps": 181800, "loss": 0.0299, "lr": 3.99447463949692e-05, "epoch": 7.328932893289329, "percentage": 36.64, "elapsed_time": "2:37:30", "remaining_time": "4:32:18", "throughput": 1487.69, "total_tokens": 14058944} {"current_steps": 66625, "total_steps": 181800, "loss": 0.0207, "lr": 3.9942822304973725e-05, "epoch": 7.32948294829483, "percentage": 36.65, "elapsed_time": "2:37:30", "remaining_time": "4:32:17", "throughput": 1487.69, "total_tokens": 14060032} {"current_steps": 66630, "total_steps": 181800, "loss": 0.0441, "lr": 3.9940898077257425e-05, "epoch": 7.33003300330033, "percentage": 36.65, "elapsed_time": "2:37:31", "remaining_time": "4:32:17", "throughput": 1487.69, "total_tokens": 14061056} {"current_steps": 66635, "total_steps": 181800, "loss": 0.002, "lr": 3.9938973711838037e-05, "epoch": 7.33058305830583, "percentage": 36.65, "elapsed_time": "2:37:32", "remaining_time": "4:32:16", "throughput": 1487.7, "total_tokens": 14062112} {"current_steps": 66640, "total_steps": 181800, "loss": 0.0604, "lr": 3.9937049208733294e-05, "epoch": 7.331133113311331, "percentage": 36.66, "elapsed_time": "2:37:32", "remaining_time": "4:32:15", "throughput": 1487.69, "total_tokens": 14063072} {"current_steps": 66645, "total_steps": 181800, "loss": 0.1468, "lr": 3.9935124567960937e-05, "epoch": 7.3316831683168315, "percentage": 36.66, "elapsed_time": "2:37:33", "remaining_time": "4:32:14", "throughput": 1487.69, "total_tokens": 14064064} {"current_steps": 66650, "total_steps": 181800, "loss": 0.0399, "lr": 3.993319978953871e-05, "epoch": 7.332233223322333, "percentage": 36.66, "elapsed_time": "2:37:34", "remaining_time": "4:32:14", "throughput": 1487.69, "total_tokens": 14065120} {"current_steps": 66655, "total_steps": 181800, "loss": 0.0076, "lr": 3.993127487348434e-05, "epoch": 7.332783278327833, "percentage": 36.66, "elapsed_time": "2:37:35", "remaining_time": "4:32:13", "throughput": 1487.7, "total_tokens": 14066208} {"current_steps": 66660, "total_steps": 181800, "loss": 0.0906, "lr": 3.9929349819815574e-05, "epoch": 7.333333333333333, "percentage": 36.67, "elapsed_time": "2:37:35", "remaining_time": "4:32:12", "throughput": 1487.71, "total_tokens": 14067296} {"current_steps": 66665, "total_steps": 181800, "loss": 0.0322, "lr": 3.9927424628550155e-05, "epoch": 7.333883388338834, "percentage": 36.67, "elapsed_time": "2:37:36", "remaining_time": "4:32:11", "throughput": 1487.71, "total_tokens": 14068384} {"current_steps": 66670, "total_steps": 181800, "loss": 0.0175, "lr": 3.992549929970582e-05, "epoch": 7.334433443344334, "percentage": 36.67, "elapsed_time": "2:37:37", "remaining_time": "4:32:11", "throughput": 1487.72, "total_tokens": 14069472} {"current_steps": 66675, "total_steps": 181800, "loss": 0.0155, "lr": 3.992357383330034e-05, "epoch": 7.334983498349835, "percentage": 36.67, "elapsed_time": "2:37:37", "remaining_time": "4:32:10", "throughput": 1487.72, "total_tokens": 14070528} {"current_steps": 66680, "total_steps": 181800, "loss": 0.0234, "lr": 3.992164822935143e-05, "epoch": 7.335533553355336, "percentage": 36.68, "elapsed_time": "2:37:38", "remaining_time": "4:32:09", "throughput": 1487.72, "total_tokens": 14071520} {"current_steps": 66685, "total_steps": 181800, "loss": 0.018, "lr": 3.9919722487876846e-05, "epoch": 7.336083608360836, "percentage": 36.68, "elapsed_time": "2:37:39", "remaining_time": "4:32:08", "throughput": 1487.72, "total_tokens": 14072544} {"current_steps": 66690, "total_steps": 181800, "loss": 0.0233, "lr": 3.991779660889433e-05, "epoch": 7.336633663366337, "percentage": 36.68, "elapsed_time": "2:37:39", "remaining_time": "4:32:08", "throughput": 1487.72, "total_tokens": 14073568} {"current_steps": 66695, "total_steps": 181800, "loss": 0.0633, "lr": 3.991587059242165e-05, "epoch": 7.337183718371837, "percentage": 36.69, "elapsed_time": "2:37:40", "remaining_time": "4:32:07", "throughput": 1487.72, "total_tokens": 14074560} {"current_steps": 66700, "total_steps": 181800, "loss": 0.1696, "lr": 3.991394443847655e-05, "epoch": 7.337733773377337, "percentage": 36.69, "elapsed_time": "2:37:41", "remaining_time": "4:32:06", "throughput": 1487.72, "total_tokens": 14075584} {"current_steps": 66705, "total_steps": 181800, "loss": 0.0436, "lr": 3.991201814707678e-05, "epoch": 7.338283828382838, "percentage": 36.69, "elapsed_time": "2:37:41", "remaining_time": "4:32:05", "throughput": 1487.72, "total_tokens": 14076672} {"current_steps": 66710, "total_steps": 181800, "loss": 0.0142, "lr": 3.9910091718240095e-05, "epoch": 7.338833883388339, "percentage": 36.69, "elapsed_time": "2:37:42", "remaining_time": "4:32:05", "throughput": 1487.72, "total_tokens": 14077696} {"current_steps": 66715, "total_steps": 181800, "loss": 0.006, "lr": 3.990816515198424e-05, "epoch": 7.33938393839384, "percentage": 36.7, "elapsed_time": "2:37:43", "remaining_time": "4:32:04", "throughput": 1487.72, "total_tokens": 14078720} {"current_steps": 66720, "total_steps": 181800, "loss": 0.0167, "lr": 3.9906238448326995e-05, "epoch": 7.33993399339934, "percentage": 36.7, "elapsed_time": "2:37:43", "remaining_time": "4:32:03", "throughput": 1487.72, "total_tokens": 14079744} {"current_steps": 66725, "total_steps": 181800, "loss": 0.0033, "lr": 3.990431160728609e-05, "epoch": 7.34048404840484, "percentage": 36.7, "elapsed_time": "2:37:44", "remaining_time": "4:32:02", "throughput": 1487.74, "total_tokens": 14080896} {"current_steps": 66730, "total_steps": 181800, "loss": 0.0362, "lr": 3.990238462887931e-05, "epoch": 7.341034103410341, "percentage": 36.71, "elapsed_time": "2:37:45", "remaining_time": "4:32:02", "throughput": 1487.74, "total_tokens": 14081920} {"current_steps": 66735, "total_steps": 181800, "loss": 0.0129, "lr": 3.990045751312439e-05, "epoch": 7.341584158415841, "percentage": 36.71, "elapsed_time": "2:37:46", "remaining_time": "4:32:01", "throughput": 1487.75, "total_tokens": 14083072} {"current_steps": 66740, "total_steps": 181800, "loss": 0.0351, "lr": 3.989853026003911e-05, "epoch": 7.3421342134213425, "percentage": 36.71, "elapsed_time": "2:37:46", "remaining_time": "4:32:00", "throughput": 1487.75, "total_tokens": 14084128} {"current_steps": 66745, "total_steps": 181800, "loss": 0.0172, "lr": 3.989660286964122e-05, "epoch": 7.342684268426843, "percentage": 36.71, "elapsed_time": "2:37:47", "remaining_time": "4:31:59", "throughput": 1487.76, "total_tokens": 14085184} {"current_steps": 66750, "total_steps": 181800, "loss": 0.0072, "lr": 3.9894675341948496e-05, "epoch": 7.343234323432343, "percentage": 36.72, "elapsed_time": "2:37:48", "remaining_time": "4:31:59", "throughput": 1487.76, "total_tokens": 14086208} {"current_steps": 66755, "total_steps": 181800, "loss": 0.0296, "lr": 3.989274767697869e-05, "epoch": 7.343784378437844, "percentage": 36.72, "elapsed_time": "2:37:48", "remaining_time": "4:31:58", "throughput": 1487.77, "total_tokens": 14087360} {"current_steps": 66760, "total_steps": 181800, "loss": 0.0355, "lr": 3.989081987474957e-05, "epoch": 7.344334433443344, "percentage": 36.72, "elapsed_time": "2:37:49", "remaining_time": "4:31:57", "throughput": 1487.77, "total_tokens": 14088416} {"current_steps": 66765, "total_steps": 181800, "loss": 0.0899, "lr": 3.9888891935278926e-05, "epoch": 7.3448844884488445, "percentage": 36.72, "elapsed_time": "2:37:50", "remaining_time": "4:31:56", "throughput": 1487.78, "total_tokens": 14089504} {"current_steps": 66770, "total_steps": 181800, "loss": 0.0241, "lr": 3.98869638585845e-05, "epoch": 7.3454345434543455, "percentage": 36.73, "elapsed_time": "2:37:50", "remaining_time": "4:31:56", "throughput": 1487.79, "total_tokens": 14090592} {"current_steps": 66775, "total_steps": 181800, "loss": 0.0067, "lr": 3.9885035644684065e-05, "epoch": 7.345984598459846, "percentage": 36.73, "elapsed_time": "2:37:51", "remaining_time": "4:31:55", "throughput": 1487.8, "total_tokens": 14091712} {"current_steps": 66780, "total_steps": 181800, "loss": 0.0186, "lr": 3.9883107293595406e-05, "epoch": 7.346534653465347, "percentage": 36.73, "elapsed_time": "2:37:52", "remaining_time": "4:31:54", "throughput": 1487.8, "total_tokens": 14092768} {"current_steps": 66785, "total_steps": 181800, "loss": 0.0673, "lr": 3.988117880533629e-05, "epoch": 7.347084708470847, "percentage": 36.74, "elapsed_time": "2:37:52", "remaining_time": "4:31:53", "throughput": 1487.8, "total_tokens": 14093792} {"current_steps": 66790, "total_steps": 181800, "loss": 0.0529, "lr": 3.987925017992449e-05, "epoch": 7.347634763476347, "percentage": 36.74, "elapsed_time": "2:37:53", "remaining_time": "4:31:53", "throughput": 1487.8, "total_tokens": 14094848} {"current_steps": 66795, "total_steps": 181800, "loss": 0.0476, "lr": 3.987732141737778e-05, "epoch": 7.348184818481848, "percentage": 36.74, "elapsed_time": "2:37:54", "remaining_time": "4:31:52", "throughput": 1487.8, "total_tokens": 14095872} {"current_steps": 66800, "total_steps": 181800, "loss": 0.0071, "lr": 3.9875392517713936e-05, "epoch": 7.3487348734873486, "percentage": 36.74, "elapsed_time": "2:37:54", "remaining_time": "4:31:51", "throughput": 1487.8, "total_tokens": 14096864} {"current_steps": 66805, "total_steps": 181800, "loss": 0.0044, "lr": 3.987346348095074e-05, "epoch": 7.34928492849285, "percentage": 36.75, "elapsed_time": "2:37:55", "remaining_time": "4:31:50", "throughput": 1487.81, "total_tokens": 14097952} {"current_steps": 66810, "total_steps": 181800, "loss": 0.0656, "lr": 3.987153430710595e-05, "epoch": 7.34983498349835, "percentage": 36.75, "elapsed_time": "2:37:56", "remaining_time": "4:31:50", "throughput": 1487.81, "total_tokens": 14098976} {"current_steps": 66815, "total_steps": 181800, "loss": 0.0652, "lr": 3.986960499619739e-05, "epoch": 7.35038503850385, "percentage": 36.75, "elapsed_time": "2:37:57", "remaining_time": "4:31:49", "throughput": 1487.82, "total_tokens": 14100096} {"current_steps": 66820, "total_steps": 181800, "loss": 0.063, "lr": 3.98676755482428e-05, "epoch": 7.350935093509351, "percentage": 36.75, "elapsed_time": "2:37:57", "remaining_time": "4:31:48", "throughput": 1487.82, "total_tokens": 14101152} {"current_steps": 66825, "total_steps": 181800, "loss": 0.0637, "lr": 3.986574596325998e-05, "epoch": 7.351485148514851, "percentage": 36.76, "elapsed_time": "2:37:58", "remaining_time": "4:31:47", "throughput": 1487.82, "total_tokens": 14102176} {"current_steps": 66830, "total_steps": 181800, "loss": 0.0398, "lr": 3.986381624126672e-05, "epoch": 7.3520352035203524, "percentage": 36.76, "elapsed_time": "2:37:59", "remaining_time": "4:31:47", "throughput": 1487.82, "total_tokens": 14103200} {"current_steps": 66835, "total_steps": 181800, "loss": 0.0053, "lr": 3.9861886382280796e-05, "epoch": 7.352585258525853, "percentage": 36.76, "elapsed_time": "2:37:59", "remaining_time": "4:31:46", "throughput": 1487.83, "total_tokens": 14104320} {"current_steps": 66840, "total_steps": 181800, "loss": 0.1392, "lr": 3.985995638632e-05, "epoch": 7.353135313531353, "percentage": 36.77, "elapsed_time": "2:38:00", "remaining_time": "4:31:45", "throughput": 1487.83, "total_tokens": 14105344} {"current_steps": 66845, "total_steps": 181800, "loss": 0.0049, "lr": 3.9858026253402105e-05, "epoch": 7.353685368536854, "percentage": 36.77, "elapsed_time": "2:38:01", "remaining_time": "4:31:45", "throughput": 1487.83, "total_tokens": 14106368} {"current_steps": 66850, "total_steps": 181800, "loss": 0.0365, "lr": 3.9856095983544916e-05, "epoch": 7.354235423542354, "percentage": 36.77, "elapsed_time": "2:38:01", "remaining_time": "4:31:44", "throughput": 1487.83, "total_tokens": 14107392} {"current_steps": 66855, "total_steps": 181800, "loss": 0.0771, "lr": 3.985416557676622e-05, "epoch": 7.354785478547855, "percentage": 36.77, "elapsed_time": "2:38:02", "remaining_time": "4:31:43", "throughput": 1487.83, "total_tokens": 14108448} {"current_steps": 66860, "total_steps": 181800, "loss": 0.1292, "lr": 3.985223503308381e-05, "epoch": 7.3553355335533555, "percentage": 36.78, "elapsed_time": "2:38:03", "remaining_time": "4:31:42", "throughput": 1487.83, "total_tokens": 14109472} {"current_steps": 66865, "total_steps": 181800, "loss": 0.0272, "lr": 3.985030435251548e-05, "epoch": 7.355885588558856, "percentage": 36.78, "elapsed_time": "2:38:03", "remaining_time": "4:31:42", "throughput": 1487.83, "total_tokens": 14110496} {"current_steps": 66870, "total_steps": 181800, "loss": 0.0222, "lr": 3.9848373535079016e-05, "epoch": 7.356435643564357, "percentage": 36.78, "elapsed_time": "2:38:04", "remaining_time": "4:31:41", "throughput": 1487.82, "total_tokens": 14111488} {"current_steps": 66875, "total_steps": 181800, "loss": 0.0082, "lr": 3.9846442580792216e-05, "epoch": 7.356985698569857, "percentage": 36.78, "elapsed_time": "2:38:05", "remaining_time": "4:31:40", "throughput": 1487.83, "total_tokens": 14112576} {"current_steps": 66880, "total_steps": 181800, "loss": 0.1253, "lr": 3.984451148967288e-05, "epoch": 7.357535753575357, "percentage": 36.79, "elapsed_time": "2:38:06", "remaining_time": "4:31:39", "throughput": 1487.83, "total_tokens": 14113632} {"current_steps": 66885, "total_steps": 181800, "loss": 0.0377, "lr": 3.984258026173881e-05, "epoch": 7.358085808580858, "percentage": 36.79, "elapsed_time": "2:38:06", "remaining_time": "4:31:39", "throughput": 1487.85, "total_tokens": 14114816} {"current_steps": 66890, "total_steps": 181800, "loss": 0.0039, "lr": 3.9840648897007794e-05, "epoch": 7.3586358635863585, "percentage": 36.79, "elapsed_time": "2:38:07", "remaining_time": "4:31:38", "throughput": 1487.85, "total_tokens": 14115808} {"current_steps": 66895, "total_steps": 181800, "loss": 0.0867, "lr": 3.9838717395497635e-05, "epoch": 7.3591859185918596, "percentage": 36.8, "elapsed_time": "2:38:08", "remaining_time": "4:31:37", "throughput": 1487.85, "total_tokens": 14116896} {"current_steps": 66900, "total_steps": 181800, "loss": 0.0635, "lr": 3.983678575722615e-05, "epoch": 7.35973597359736, "percentage": 36.8, "elapsed_time": "2:38:08", "remaining_time": "4:31:36", "throughput": 1487.86, "total_tokens": 14117952} {"current_steps": 66905, "total_steps": 181800, "loss": 0.0195, "lr": 3.983485398221112e-05, "epoch": 7.36028602860286, "percentage": 36.8, "elapsed_time": "2:38:09", "remaining_time": "4:31:36", "throughput": 1487.86, "total_tokens": 14118976} {"current_steps": 66910, "total_steps": 181800, "loss": 0.0208, "lr": 3.983292207047036e-05, "epoch": 7.360836083608361, "percentage": 36.8, "elapsed_time": "2:38:10", "remaining_time": "4:31:35", "throughput": 1487.86, "total_tokens": 14120064} {"current_steps": 66915, "total_steps": 181800, "loss": 0.0023, "lr": 3.9830990022021675e-05, "epoch": 7.361386138613861, "percentage": 36.81, "elapsed_time": "2:38:10", "remaining_time": "4:31:34", "throughput": 1487.86, "total_tokens": 14121088} {"current_steps": 66920, "total_steps": 181800, "loss": 0.0231, "lr": 3.9829057836882874e-05, "epoch": 7.361936193619362, "percentage": 36.81, "elapsed_time": "2:38:11", "remaining_time": "4:31:33", "throughput": 1487.88, "total_tokens": 14122240} {"current_steps": 66925, "total_steps": 181800, "loss": 0.0383, "lr": 3.982712551507176e-05, "epoch": 7.362486248624863, "percentage": 36.81, "elapsed_time": "2:38:12", "remaining_time": "4:31:33", "throughput": 1487.88, "total_tokens": 14123264} {"current_steps": 66930, "total_steps": 181800, "loss": 0.0298, "lr": 3.982519305660615e-05, "epoch": 7.363036303630363, "percentage": 36.82, "elapsed_time": "2:38:12", "remaining_time": "4:31:32", "throughput": 1487.88, "total_tokens": 14124288} {"current_steps": 66935, "total_steps": 181800, "loss": 0.0675, "lr": 3.982326046150385e-05, "epoch": 7.363586358635864, "percentage": 36.82, "elapsed_time": "2:38:13", "remaining_time": "4:31:31", "throughput": 1487.88, "total_tokens": 14125376} {"current_steps": 66940, "total_steps": 181800, "loss": 0.1007, "lr": 3.982132772978267e-05, "epoch": 7.364136413641364, "percentage": 36.82, "elapsed_time": "2:38:14", "remaining_time": "4:31:30", "throughput": 1487.89, "total_tokens": 14126464} {"current_steps": 66945, "total_steps": 181800, "loss": 0.0379, "lr": 3.9819394861460416e-05, "epoch": 7.364686468646864, "percentage": 36.82, "elapsed_time": "2:38:14", "remaining_time": "4:31:30", "throughput": 1487.88, "total_tokens": 14127456} {"current_steps": 66950, "total_steps": 181800, "loss": 0.0118, "lr": 3.9817461856554915e-05, "epoch": 7.365236523652365, "percentage": 36.83, "elapsed_time": "2:38:15", "remaining_time": "4:31:29", "throughput": 1487.88, "total_tokens": 14128480} {"current_steps": 66955, "total_steps": 181800, "loss": 0.0547, "lr": 3.9815528715083986e-05, "epoch": 7.365786578657866, "percentage": 36.83, "elapsed_time": "2:38:16", "remaining_time": "4:31:28", "throughput": 1487.89, "total_tokens": 14129536} {"current_steps": 66960, "total_steps": 181800, "loss": 0.0378, "lr": 3.981359543706543e-05, "epoch": 7.366336633663367, "percentage": 36.83, "elapsed_time": "2:38:17", "remaining_time": "4:31:27", "throughput": 1487.89, "total_tokens": 14130592} {"current_steps": 66965, "total_steps": 181800, "loss": 0.0184, "lr": 3.981166202251707e-05, "epoch": 7.366886688668867, "percentage": 36.83, "elapsed_time": "2:38:17", "remaining_time": "4:31:27", "throughput": 1487.88, "total_tokens": 14131552} {"current_steps": 66970, "total_steps": 181800, "loss": 0.0126, "lr": 3.980972847145673e-05, "epoch": 7.367436743674367, "percentage": 36.84, "elapsed_time": "2:38:18", "remaining_time": "4:31:26", "throughput": 1487.89, "total_tokens": 14132640} {"current_steps": 66975, "total_steps": 181800, "loss": 0.13, "lr": 3.980779478390224e-05, "epoch": 7.367986798679868, "percentage": 36.84, "elapsed_time": "2:38:19", "remaining_time": "4:31:25", "throughput": 1487.9, "total_tokens": 14133760} {"current_steps": 66980, "total_steps": 181800, "loss": 0.0018, "lr": 3.98058609598714e-05, "epoch": 7.368536853685368, "percentage": 36.84, "elapsed_time": "2:38:19", "remaining_time": "4:31:25", "throughput": 1487.91, "total_tokens": 14134848} {"current_steps": 66985, "total_steps": 181800, "loss": 0.0122, "lr": 3.9803926999382046e-05, "epoch": 7.3690869086908695, "percentage": 36.85, "elapsed_time": "2:38:20", "remaining_time": "4:31:24", "throughput": 1487.91, "total_tokens": 14135904} {"current_steps": 66990, "total_steps": 181800, "loss": 0.0198, "lr": 3.9801992902452e-05, "epoch": 7.36963696369637, "percentage": 36.85, "elapsed_time": "2:38:21", "remaining_time": "4:31:23", "throughput": 1487.91, "total_tokens": 14136960} {"current_steps": 66995, "total_steps": 181800, "loss": 0.0473, "lr": 3.980005866909909e-05, "epoch": 7.37018701870187, "percentage": 36.85, "elapsed_time": "2:38:21", "remaining_time": "4:31:22", "throughput": 1487.92, "total_tokens": 14138048} {"current_steps": 67000, "total_steps": 181800, "loss": 0.0092, "lr": 3.9798124299341145e-05, "epoch": 7.370737073707371, "percentage": 36.85, "elapsed_time": "2:38:22", "remaining_time": "4:31:22", "throughput": 1487.92, "total_tokens": 14139104} {"current_steps": 67005, "total_steps": 181800, "loss": 0.0113, "lr": 3.979618979319598e-05, "epoch": 7.371287128712871, "percentage": 36.86, "elapsed_time": "2:38:23", "remaining_time": "4:31:21", "throughput": 1487.92, "total_tokens": 14140160} {"current_steps": 67010, "total_steps": 181800, "loss": 0.0264, "lr": 3.9794255150681445e-05, "epoch": 7.371837183718371, "percentage": 36.86, "elapsed_time": "2:38:23", "remaining_time": "4:31:20", "throughput": 1487.92, "total_tokens": 14141184} {"current_steps": 67015, "total_steps": 181800, "loss": 0.143, "lr": 3.979232037181535e-05, "epoch": 7.3723872387238725, "percentage": 36.86, "elapsed_time": "2:38:24", "remaining_time": "4:31:19", "throughput": 1487.92, "total_tokens": 14142208} {"current_steps": 67020, "total_steps": 181800, "loss": 0.0472, "lr": 3.9790385456615536e-05, "epoch": 7.372937293729373, "percentage": 36.86, "elapsed_time": "2:38:25", "remaining_time": "4:31:19", "throughput": 1487.93, "total_tokens": 14143328} {"current_steps": 67025, "total_steps": 181800, "loss": 0.0318, "lr": 3.978845040509984e-05, "epoch": 7.373487348734874, "percentage": 36.87, "elapsed_time": "2:38:26", "remaining_time": "4:31:18", "throughput": 1487.94, "total_tokens": 14144384} {"current_steps": 67030, "total_steps": 181800, "loss": 0.1109, "lr": 3.97865152172861e-05, "epoch": 7.374037403740374, "percentage": 36.87, "elapsed_time": "2:38:26", "remaining_time": "4:31:17", "throughput": 1487.93, "total_tokens": 14145376} {"current_steps": 67035, "total_steps": 181800, "loss": 0.0197, "lr": 3.978457989319213e-05, "epoch": 7.374587458745874, "percentage": 36.87, "elapsed_time": "2:38:27", "remaining_time": "4:31:16", "throughput": 1487.94, "total_tokens": 14146496} {"current_steps": 67040, "total_steps": 181800, "loss": 0.07, "lr": 3.978264443283579e-05, "epoch": 7.375137513751375, "percentage": 36.88, "elapsed_time": "2:38:28", "remaining_time": "4:31:16", "throughput": 1487.94, "total_tokens": 14147552} {"current_steps": 67045, "total_steps": 181800, "loss": 0.031, "lr": 3.97807088362349e-05, "epoch": 7.3756875687568755, "percentage": 36.88, "elapsed_time": "2:38:28", "remaining_time": "4:31:15", "throughput": 1487.94, "total_tokens": 14148576} {"current_steps": 67050, "total_steps": 181800, "loss": 0.0047, "lr": 3.977877310340732e-05, "epoch": 7.376237623762377, "percentage": 36.88, "elapsed_time": "2:38:29", "remaining_time": "4:31:14", "throughput": 1487.95, "total_tokens": 14149632} {"current_steps": 67055, "total_steps": 181800, "loss": 0.0055, "lr": 3.9776837234370875e-05, "epoch": 7.376787678767877, "percentage": 36.88, "elapsed_time": "2:38:30", "remaining_time": "4:31:13", "throughput": 1487.95, "total_tokens": 14150656} {"current_steps": 67060, "total_steps": 181800, "loss": 0.0312, "lr": 3.977490122914342e-05, "epoch": 7.377337733773377, "percentage": 36.89, "elapsed_time": "2:38:30", "remaining_time": "4:31:13", "throughput": 1487.94, "total_tokens": 14151680} {"current_steps": 67065, "total_steps": 181800, "loss": 0.1946, "lr": 3.977296508774278e-05, "epoch": 7.377887788778878, "percentage": 36.89, "elapsed_time": "2:38:31", "remaining_time": "4:31:12", "throughput": 1487.95, "total_tokens": 14152768} {"current_steps": 67070, "total_steps": 181800, "loss": 0.0746, "lr": 3.977102881018682e-05, "epoch": 7.378437843784378, "percentage": 36.89, "elapsed_time": "2:38:32", "remaining_time": "4:31:11", "throughput": 1487.95, "total_tokens": 14153824} {"current_steps": 67075, "total_steps": 181800, "loss": 0.0513, "lr": 3.976909239649337e-05, "epoch": 7.378987898789879, "percentage": 36.89, "elapsed_time": "2:38:32", "remaining_time": "4:31:10", "throughput": 1487.96, "total_tokens": 14154912} {"current_steps": 67080, "total_steps": 181800, "loss": 0.1241, "lr": 3.9767155846680274e-05, "epoch": 7.37953795379538, "percentage": 36.9, "elapsed_time": "2:38:33", "remaining_time": "4:31:10", "throughput": 1487.97, "total_tokens": 14156064} {"current_steps": 67085, "total_steps": 181800, "loss": 0.0154, "lr": 3.97652191607654e-05, "epoch": 7.38008800880088, "percentage": 36.9, "elapsed_time": "2:38:34", "remaining_time": "4:31:09", "throughput": 1487.98, "total_tokens": 14157120} {"current_steps": 67090, "total_steps": 181800, "loss": 0.0438, "lr": 3.9763282338766575e-05, "epoch": 7.380638063806381, "percentage": 36.9, "elapsed_time": "2:38:35", "remaining_time": "4:31:08", "throughput": 1487.99, "total_tokens": 14158272} {"current_steps": 67095, "total_steps": 181800, "loss": 0.049, "lr": 3.976134538070167e-05, "epoch": 7.381188118811881, "percentage": 36.91, "elapsed_time": "2:38:35", "remaining_time": "4:31:08", "throughput": 1487.99, "total_tokens": 14159360} {"current_steps": 67100, "total_steps": 181800, "loss": 0.0493, "lr": 3.975940828658853e-05, "epoch": 7.381738173817382, "percentage": 36.91, "elapsed_time": "2:38:36", "remaining_time": "4:31:07", "throughput": 1487.99, "total_tokens": 14160384} {"current_steps": 67105, "total_steps": 181800, "loss": 0.1262, "lr": 3.9757471056444996e-05, "epoch": 7.382288228822882, "percentage": 36.91, "elapsed_time": "2:38:37", "remaining_time": "4:31:06", "throughput": 1488.0, "total_tokens": 14161440} {"current_steps": 67110, "total_steps": 181800, "loss": 0.0494, "lr": 3.975553369028894e-05, "epoch": 7.382838283828383, "percentage": 36.91, "elapsed_time": "2:38:37", "remaining_time": "4:31:05", "throughput": 1488.01, "total_tokens": 14162592} {"current_steps": 67115, "total_steps": 181800, "loss": 0.0834, "lr": 3.97535961881382e-05, "epoch": 7.383388338833884, "percentage": 36.92, "elapsed_time": "2:38:38", "remaining_time": "4:31:05", "throughput": 1488.01, "total_tokens": 14163616} {"current_steps": 67120, "total_steps": 181800, "loss": 0.0309, "lr": 3.975165855001066e-05, "epoch": 7.383938393839384, "percentage": 36.92, "elapsed_time": "2:38:39", "remaining_time": "4:31:04", "throughput": 1488.02, "total_tokens": 14164704} {"current_steps": 67125, "total_steps": 181800, "loss": 0.0821, "lr": 3.974972077592415e-05, "epoch": 7.384488448844884, "percentage": 36.92, "elapsed_time": "2:38:39", "remaining_time": "4:31:03", "throughput": 1488.02, "total_tokens": 14165728} {"current_steps": 67130, "total_steps": 181800, "loss": 0.0478, "lr": 3.9747782865896544e-05, "epoch": 7.385038503850385, "percentage": 36.93, "elapsed_time": "2:38:40", "remaining_time": "4:31:02", "throughput": 1488.02, "total_tokens": 14166752} {"current_steps": 67135, "total_steps": 181800, "loss": 0.0177, "lr": 3.9745844819945696e-05, "epoch": 7.385588558855885, "percentage": 36.93, "elapsed_time": "2:38:41", "remaining_time": "4:31:02", "throughput": 1488.02, "total_tokens": 14167840} {"current_steps": 67140, "total_steps": 181800, "loss": 0.0695, "lr": 3.9743906638089476e-05, "epoch": 7.3861386138613865, "percentage": 36.93, "elapsed_time": "2:38:41", "remaining_time": "4:31:01", "throughput": 1488.03, "total_tokens": 14168928} {"current_steps": 67145, "total_steps": 181800, "loss": 0.0139, "lr": 3.9741968320345746e-05, "epoch": 7.386688668866887, "percentage": 36.93, "elapsed_time": "2:38:42", "remaining_time": "4:31:00", "throughput": 1488.03, "total_tokens": 14169984} {"current_steps": 67150, "total_steps": 181800, "loss": 0.0186, "lr": 3.974002986673237e-05, "epoch": 7.387238723872387, "percentage": 36.94, "elapsed_time": "2:38:43", "remaining_time": "4:30:59", "throughput": 1488.03, "total_tokens": 14171008} {"current_steps": 67155, "total_steps": 181800, "loss": 0.0376, "lr": 3.973809127726721e-05, "epoch": 7.387788778877888, "percentage": 36.94, "elapsed_time": "2:38:44", "remaining_time": "4:30:59", "throughput": 1488.04, "total_tokens": 14172096} {"current_steps": 67160, "total_steps": 181800, "loss": 0.0901, "lr": 3.973615255196813e-05, "epoch": 7.388338833883388, "percentage": 36.94, "elapsed_time": "2:38:44", "remaining_time": "4:30:58", "throughput": 1488.04, "total_tokens": 14173152} {"current_steps": 67165, "total_steps": 181800, "loss": 0.0838, "lr": 3.9734213690853006e-05, "epoch": 7.388888888888889, "percentage": 36.94, "elapsed_time": "2:38:45", "remaining_time": "4:30:57", "throughput": 1488.05, "total_tokens": 14174304} {"current_steps": 67170, "total_steps": 181800, "loss": 0.1616, "lr": 3.9732274693939705e-05, "epoch": 7.3894389438943895, "percentage": 36.95, "elapsed_time": "2:38:46", "remaining_time": "4:30:56", "throughput": 1488.05, "total_tokens": 14175328} {"current_steps": 67175, "total_steps": 181800, "loss": 0.0183, "lr": 3.973033556124609e-05, "epoch": 7.38998899889989, "percentage": 36.95, "elapsed_time": "2:38:46", "remaining_time": "4:30:56", "throughput": 1488.06, "total_tokens": 14176416} {"current_steps": 67180, "total_steps": 181800, "loss": 0.0275, "lr": 3.972839629279005e-05, "epoch": 7.390539053905391, "percentage": 36.95, "elapsed_time": "2:38:47", "remaining_time": "4:30:55", "throughput": 1488.06, "total_tokens": 14177440} {"current_steps": 67185, "total_steps": 181800, "loss": 0.0067, "lr": 3.972645688858944e-05, "epoch": 7.391089108910891, "percentage": 36.96, "elapsed_time": "2:38:48", "remaining_time": "4:30:54", "throughput": 1488.06, "total_tokens": 14178496} {"current_steps": 67190, "total_steps": 181800, "loss": 0.0243, "lr": 3.972451734866215e-05, "epoch": 7.391639163916391, "percentage": 36.96, "elapsed_time": "2:38:48", "remaining_time": "4:30:53", "throughput": 1488.07, "total_tokens": 14179552} {"current_steps": 67195, "total_steps": 181800, "loss": 0.0225, "lr": 3.972257767302605e-05, "epoch": 7.392189218921892, "percentage": 36.96, "elapsed_time": "2:38:49", "remaining_time": "4:30:53", "throughput": 1488.07, "total_tokens": 14180576} {"current_steps": 67200, "total_steps": 181800, "loss": 0.037, "lr": 3.972063786169902e-05, "epoch": 7.3927392739273925, "percentage": 36.96, "elapsed_time": "2:38:50", "remaining_time": "4:30:52", "throughput": 1488.07, "total_tokens": 14181632} {"current_steps": 67205, "total_steps": 181800, "loss": 0.0257, "lr": 3.971869791469892e-05, "epoch": 7.393289328932894, "percentage": 36.97, "elapsed_time": "2:38:50", "remaining_time": "4:30:51", "throughput": 1488.08, "total_tokens": 14182720} {"current_steps": 67210, "total_steps": 181800, "loss": 0.0555, "lr": 3.971675783204365e-05, "epoch": 7.393839383938394, "percentage": 36.97, "elapsed_time": "2:38:51", "remaining_time": "4:30:50", "throughput": 1488.08, "total_tokens": 14183808} {"current_steps": 67215, "total_steps": 181800, "loss": 0.0278, "lr": 3.971481761375109e-05, "epoch": 7.394389438943894, "percentage": 36.97, "elapsed_time": "2:38:52", "remaining_time": "4:30:50", "throughput": 1488.08, "total_tokens": 14184832} {"current_steps": 67220, "total_steps": 181800, "loss": 0.035, "lr": 3.9712877259839114e-05, "epoch": 7.394939493949395, "percentage": 36.97, "elapsed_time": "2:38:52", "remaining_time": "4:30:49", "throughput": 1488.09, "total_tokens": 14185920} {"current_steps": 67225, "total_steps": 181800, "loss": 0.0061, "lr": 3.971093677032561e-05, "epoch": 7.395489548954895, "percentage": 36.98, "elapsed_time": "2:38:53", "remaining_time": "4:30:48", "throughput": 1488.09, "total_tokens": 14186976} {"current_steps": 67230, "total_steps": 181800, "loss": 0.0016, "lr": 3.970899614522846e-05, "epoch": 7.396039603960396, "percentage": 36.98, "elapsed_time": "2:38:54", "remaining_time": "4:30:47", "throughput": 1488.1, "total_tokens": 14188064} {"current_steps": 67235, "total_steps": 181800, "loss": 0.0177, "lr": 3.970705538456554e-05, "epoch": 7.396589658965897, "percentage": 36.98, "elapsed_time": "2:38:55", "remaining_time": "4:30:47", "throughput": 1488.1, "total_tokens": 14189152} {"current_steps": 67240, "total_steps": 181800, "loss": 0.0056, "lr": 3.9705114488354764e-05, "epoch": 7.397139713971397, "percentage": 36.99, "elapsed_time": "2:38:55", "remaining_time": "4:30:46", "throughput": 1488.1, "total_tokens": 14190176} {"current_steps": 67245, "total_steps": 181800, "loss": 0.0814, "lr": 3.9703173456614e-05, "epoch": 7.397689768976898, "percentage": 36.99, "elapsed_time": "2:38:56", "remaining_time": "4:30:45", "throughput": 1488.11, "total_tokens": 14191264} {"current_steps": 67250, "total_steps": 181800, "loss": 0.0904, "lr": 3.970123228936113e-05, "epoch": 7.398239823982398, "percentage": 36.99, "elapsed_time": "2:38:57", "remaining_time": "4:30:45", "throughput": 1488.11, "total_tokens": 14192320} {"current_steps": 67255, "total_steps": 181800, "loss": 0.0464, "lr": 3.969929098661407e-05, "epoch": 7.398789878987899, "percentage": 36.99, "elapsed_time": "2:38:57", "remaining_time": "4:30:44", "throughput": 1488.11, "total_tokens": 14193344} {"current_steps": 67260, "total_steps": 181800, "loss": 0.0128, "lr": 3.9697349548390696e-05, "epoch": 7.399339933993399, "percentage": 37.0, "elapsed_time": "2:38:58", "remaining_time": "4:30:43", "throughput": 1488.09, "total_tokens": 14194400} {"current_steps": 67265, "total_steps": 181800, "loss": 0.0282, "lr": 3.96954079747089e-05, "epoch": 7.3998899889989, "percentage": 37.0, "elapsed_time": "2:38:59", "remaining_time": "4:30:43", "throughput": 1488.09, "total_tokens": 14195456} {"current_steps": 67270, "total_steps": 181800, "loss": 0.0737, "lr": 3.969346626558657e-05, "epoch": 7.400440044004401, "percentage": 37.0, "elapsed_time": "2:39:00", "remaining_time": "4:30:42", "throughput": 1488.1, "total_tokens": 14196608} {"current_steps": 67275, "total_steps": 181800, "loss": 0.0032, "lr": 3.969152442104163e-05, "epoch": 7.400990099009901, "percentage": 37.0, "elapsed_time": "2:39:00", "remaining_time": "4:30:41", "throughput": 1488.11, "total_tokens": 14197696} {"current_steps": 67280, "total_steps": 181800, "loss": 0.0495, "lr": 3.968958244109196e-05, "epoch": 7.401540154015402, "percentage": 37.01, "elapsed_time": "2:39:01", "remaining_time": "4:30:40", "throughput": 1488.11, "total_tokens": 14198752} {"current_steps": 67285, "total_steps": 181800, "loss": 0.0142, "lr": 3.968764032575544e-05, "epoch": 7.402090209020902, "percentage": 37.01, "elapsed_time": "2:39:02", "remaining_time": "4:30:40", "throughput": 1488.11, "total_tokens": 14199776} {"current_steps": 67290, "total_steps": 181800, "loss": 0.0643, "lr": 3.9685698075050006e-05, "epoch": 7.402640264026402, "percentage": 37.01, "elapsed_time": "2:39:02", "remaining_time": "4:30:39", "throughput": 1488.11, "total_tokens": 14200800} {"current_steps": 67295, "total_steps": 181800, "loss": 0.0115, "lr": 3.968375568899353e-05, "epoch": 7.4031903190319035, "percentage": 37.02, "elapsed_time": "2:39:03", "remaining_time": "4:30:38", "throughput": 1488.12, "total_tokens": 14201888} {"current_steps": 67300, "total_steps": 181800, "loss": 0.0519, "lr": 3.968181316760392e-05, "epoch": 7.403740374037404, "percentage": 37.02, "elapsed_time": "2:39:04", "remaining_time": "4:30:37", "throughput": 1488.12, "total_tokens": 14202976} {"current_steps": 67305, "total_steps": 181800, "loss": 0.0158, "lr": 3.967987051089909e-05, "epoch": 7.404290429042904, "percentage": 37.02, "elapsed_time": "2:39:04", "remaining_time": "4:30:37", "throughput": 1488.12, "total_tokens": 14204000} {"current_steps": 67310, "total_steps": 181800, "loss": 0.0549, "lr": 3.9677927718896936e-05, "epoch": 7.404840484048405, "percentage": 37.02, "elapsed_time": "2:39:05", "remaining_time": "4:30:36", "throughput": 1488.13, "total_tokens": 14205056} {"current_steps": 67315, "total_steps": 181800, "loss": 0.0424, "lr": 3.967598479161536e-05, "epoch": 7.405390539053905, "percentage": 37.03, "elapsed_time": "2:39:06", "remaining_time": "4:30:35", "throughput": 1488.13, "total_tokens": 14206112} {"current_steps": 67320, "total_steps": 181800, "loss": 0.0373, "lr": 3.967404172907228e-05, "epoch": 7.405940594059406, "percentage": 37.03, "elapsed_time": "2:39:06", "remaining_time": "4:30:34", "throughput": 1488.13, "total_tokens": 14207168} {"current_steps": 67325, "total_steps": 181800, "loss": 0.0125, "lr": 3.96720985312856e-05, "epoch": 7.4064906490649065, "percentage": 37.03, "elapsed_time": "2:39:07", "remaining_time": "4:30:34", "throughput": 1488.13, "total_tokens": 14208192} {"current_steps": 67330, "total_steps": 181800, "loss": 0.0018, "lr": 3.967015519827322e-05, "epoch": 7.407040704070407, "percentage": 37.04, "elapsed_time": "2:39:08", "remaining_time": "4:30:33", "throughput": 1488.13, "total_tokens": 14209248} {"current_steps": 67335, "total_steps": 181800, "loss": 0.0073, "lr": 3.966821173005306e-05, "epoch": 7.407590759075908, "percentage": 37.04, "elapsed_time": "2:39:09", "remaining_time": "4:30:32", "throughput": 1488.14, "total_tokens": 14210368} {"current_steps": 67340, "total_steps": 181800, "loss": 0.0091, "lr": 3.966626812664304e-05, "epoch": 7.408140814081408, "percentage": 37.04, "elapsed_time": "2:39:09", "remaining_time": "4:30:32", "throughput": 1488.14, "total_tokens": 14211360} {"current_steps": 67345, "total_steps": 181800, "loss": 0.0427, "lr": 3.966432438806106e-05, "epoch": 7.408690869086909, "percentage": 37.04, "elapsed_time": "2:39:10", "remaining_time": "4:30:31", "throughput": 1488.14, "total_tokens": 14212416} {"current_steps": 67350, "total_steps": 181800, "loss": 0.0284, "lr": 3.966238051432504e-05, "epoch": 7.409240924092409, "percentage": 37.05, "elapsed_time": "2:39:11", "remaining_time": "4:30:30", "throughput": 1488.14, "total_tokens": 14213440} {"current_steps": 67355, "total_steps": 181800, "loss": 0.0031, "lr": 3.9660436505452894e-05, "epoch": 7.4097909790979095, "percentage": 37.05, "elapsed_time": "2:39:11", "remaining_time": "4:30:29", "throughput": 1488.15, "total_tokens": 14214528} {"current_steps": 67360, "total_steps": 181800, "loss": 0.0321, "lr": 3.965849236146254e-05, "epoch": 7.410341034103411, "percentage": 37.05, "elapsed_time": "2:39:12", "remaining_time": "4:30:29", "throughput": 1488.15, "total_tokens": 14215552} {"current_steps": 67365, "total_steps": 181800, "loss": 0.0894, "lr": 3.9656548082371894e-05, "epoch": 7.410891089108911, "percentage": 37.05, "elapsed_time": "2:39:13", "remaining_time": "4:30:28", "throughput": 1488.16, "total_tokens": 14216704} {"current_steps": 67370, "total_steps": 181800, "loss": 0.0268, "lr": 3.9654603668198874e-05, "epoch": 7.411441144114411, "percentage": 37.06, "elapsed_time": "2:39:13", "remaining_time": "4:30:27", "throughput": 1488.17, "total_tokens": 14217760} {"current_steps": 67375, "total_steps": 181800, "loss": 0.1153, "lr": 3.965265911896141e-05, "epoch": 7.411991199119912, "percentage": 37.06, "elapsed_time": "2:39:14", "remaining_time": "4:30:26", "throughput": 1488.17, "total_tokens": 14218816} {"current_steps": 67380, "total_steps": 181800, "loss": 0.0296, "lr": 3.965071443467741e-05, "epoch": 7.412541254125412, "percentage": 37.06, "elapsed_time": "2:39:15", "remaining_time": "4:30:26", "throughput": 1488.18, "total_tokens": 14219904} {"current_steps": 67385, "total_steps": 181800, "loss": 0.0249, "lr": 3.964876961536481e-05, "epoch": 7.413091309130913, "percentage": 37.07, "elapsed_time": "2:39:15", "remaining_time": "4:30:25", "throughput": 1488.18, "total_tokens": 14220992} {"current_steps": 67390, "total_steps": 181800, "loss": 0.0059, "lr": 3.9646824661041534e-05, "epoch": 7.413641364136414, "percentage": 37.07, "elapsed_time": "2:39:16", "remaining_time": "4:30:24", "throughput": 1488.18, "total_tokens": 14221984} {"current_steps": 67395, "total_steps": 181800, "loss": 0.0041, "lr": 3.96448795717255e-05, "epoch": 7.414191419141914, "percentage": 37.07, "elapsed_time": "2:39:17", "remaining_time": "4:30:23", "throughput": 1488.18, "total_tokens": 14223008} {"current_steps": 67400, "total_steps": 181800, "loss": 0.0067, "lr": 3.964293434743463e-05, "epoch": 7.414741474147415, "percentage": 37.07, "elapsed_time": "2:39:18", "remaining_time": "4:30:23", "throughput": 1488.18, "total_tokens": 14224064} {"current_steps": 67405, "total_steps": 181800, "loss": 0.0057, "lr": 3.964098898818688e-05, "epoch": 7.415291529152915, "percentage": 37.08, "elapsed_time": "2:39:18", "remaining_time": "4:30:22", "throughput": 1488.18, "total_tokens": 14225088} {"current_steps": 67410, "total_steps": 181800, "loss": 0.0134, "lr": 3.963904349400015e-05, "epoch": 7.415841584158416, "percentage": 37.08, "elapsed_time": "2:39:19", "remaining_time": "4:30:21", "throughput": 1488.18, "total_tokens": 14226112} {"current_steps": 67415, "total_steps": 181800, "loss": 0.0442, "lr": 3.963709786489237e-05, "epoch": 7.416391639163916, "percentage": 37.08, "elapsed_time": "2:39:20", "remaining_time": "4:30:20", "throughput": 1488.18, "total_tokens": 14227136} {"current_steps": 67420, "total_steps": 181800, "loss": 0.0443, "lr": 3.963515210088149e-05, "epoch": 7.416941694169417, "percentage": 37.08, "elapsed_time": "2:39:20", "remaining_time": "4:30:20", "throughput": 1488.18, "total_tokens": 14228160} {"current_steps": 67425, "total_steps": 181800, "loss": 0.0633, "lr": 3.963320620198544e-05, "epoch": 7.417491749174918, "percentage": 37.09, "elapsed_time": "2:39:21", "remaining_time": "4:30:19", "throughput": 1488.18, "total_tokens": 14229152} {"current_steps": 67430, "total_steps": 181800, "loss": 0.0327, "lr": 3.9631260168222144e-05, "epoch": 7.418041804180418, "percentage": 37.09, "elapsed_time": "2:39:22", "remaining_time": "4:30:18", "throughput": 1488.18, "total_tokens": 14230240} {"current_steps": 67435, "total_steps": 181800, "loss": 0.0625, "lr": 3.9629313999609554e-05, "epoch": 7.418591859185918, "percentage": 37.09, "elapsed_time": "2:39:22", "remaining_time": "4:30:17", "throughput": 1488.19, "total_tokens": 14231296} {"current_steps": 67440, "total_steps": 181800, "loss": 0.0078, "lr": 3.962736769616559e-05, "epoch": 7.419141914191419, "percentage": 37.1, "elapsed_time": "2:39:23", "remaining_time": "4:30:17", "throughput": 1488.19, "total_tokens": 14232384} {"current_steps": 67445, "total_steps": 181800, "loss": 0.0289, "lr": 3.962542125790819e-05, "epoch": 7.419691969196919, "percentage": 37.1, "elapsed_time": "2:39:24", "remaining_time": "4:30:16", "throughput": 1488.2, "total_tokens": 14233472} {"current_steps": 67450, "total_steps": 181800, "loss": 0.0397, "lr": 3.96234746848553e-05, "epoch": 7.4202420242024205, "percentage": 37.1, "elapsed_time": "2:39:24", "remaining_time": "4:30:15", "throughput": 1488.2, "total_tokens": 14234496} {"current_steps": 67455, "total_steps": 181800, "loss": 0.0938, "lr": 3.962152797702487e-05, "epoch": 7.420792079207921, "percentage": 37.1, "elapsed_time": "2:39:25", "remaining_time": "4:30:14", "throughput": 1488.21, "total_tokens": 14235680} {"current_steps": 67460, "total_steps": 181800, "loss": 0.0121, "lr": 3.961958113443483e-05, "epoch": 7.421342134213421, "percentage": 37.11, "elapsed_time": "2:39:26", "remaining_time": "4:30:14", "throughput": 1488.21, "total_tokens": 14236672} {"current_steps": 67465, "total_steps": 181800, "loss": 0.0059, "lr": 3.9617634157103136e-05, "epoch": 7.421892189218922, "percentage": 37.11, "elapsed_time": "2:39:26", "remaining_time": "4:30:13", "throughput": 1488.21, "total_tokens": 14237664} {"current_steps": 67470, "total_steps": 181800, "loss": 0.0161, "lr": 3.961568704504771e-05, "epoch": 7.422442244224422, "percentage": 37.11, "elapsed_time": "2:39:27", "remaining_time": "4:30:12", "throughput": 1488.2, "total_tokens": 14238656} {"current_steps": 67475, "total_steps": 181800, "loss": 0.0629, "lr": 3.961373979828651e-05, "epoch": 7.422992299229923, "percentage": 37.11, "elapsed_time": "2:39:28", "remaining_time": "4:30:11", "throughput": 1488.21, "total_tokens": 14239712} {"current_steps": 67480, "total_steps": 181800, "loss": 0.0056, "lr": 3.961179241683749e-05, "epoch": 7.4235423542354235, "percentage": 37.12, "elapsed_time": "2:39:29", "remaining_time": "4:30:11", "throughput": 1488.22, "total_tokens": 14240832} {"current_steps": 67485, "total_steps": 181800, "loss": 0.0138, "lr": 3.960984490071858e-05, "epoch": 7.424092409240924, "percentage": 37.12, "elapsed_time": "2:39:29", "remaining_time": "4:30:10", "throughput": 1488.23, "total_tokens": 14241952} {"current_steps": 67490, "total_steps": 181800, "loss": 0.0511, "lr": 3.960789724994774e-05, "epoch": 7.424642464246425, "percentage": 37.12, "elapsed_time": "2:39:30", "remaining_time": "4:30:09", "throughput": 1488.23, "total_tokens": 14243072} {"current_steps": 67495, "total_steps": 181800, "loss": 0.0978, "lr": 3.960594946454293e-05, "epoch": 7.425192519251925, "percentage": 37.13, "elapsed_time": "2:39:31", "remaining_time": "4:30:09", "throughput": 1488.24, "total_tokens": 14244192} {"current_steps": 67500, "total_steps": 181800, "loss": 0.0134, "lr": 3.960400154452209e-05, "epoch": 7.425742574257426, "percentage": 37.13, "elapsed_time": "2:39:31", "remaining_time": "4:30:08", "throughput": 1488.24, "total_tokens": 14245216} {"current_steps": 67505, "total_steps": 181800, "loss": 0.0073, "lr": 3.960205348990317e-05, "epoch": 7.426292629262926, "percentage": 37.13, "elapsed_time": "2:39:32", "remaining_time": "4:30:07", "throughput": 1488.25, "total_tokens": 14246272} {"current_steps": 67510, "total_steps": 181800, "loss": 0.0354, "lr": 3.960010530070414e-05, "epoch": 7.4268426842684265, "percentage": 37.13, "elapsed_time": "2:39:33", "remaining_time": "4:30:06", "throughput": 1488.25, "total_tokens": 14247360} {"current_steps": 67515, "total_steps": 181800, "loss": 0.0055, "lr": 3.9598156976942935e-05, "epoch": 7.427392739273928, "percentage": 37.14, "elapsed_time": "2:39:33", "remaining_time": "4:30:06", "throughput": 1488.25, "total_tokens": 14248384} {"current_steps": 67520, "total_steps": 181800, "loss": 0.0409, "lr": 3.959620851863752e-05, "epoch": 7.427942794279428, "percentage": 37.14, "elapsed_time": "2:39:34", "remaining_time": "4:30:05", "throughput": 1488.26, "total_tokens": 14249440} {"current_steps": 67525, "total_steps": 181800, "loss": 0.0492, "lr": 3.959425992580587e-05, "epoch": 7.428492849284929, "percentage": 37.14, "elapsed_time": "2:39:35", "remaining_time": "4:30:04", "throughput": 1488.26, "total_tokens": 14250528} {"current_steps": 67530, "total_steps": 181800, "loss": 0.1167, "lr": 3.959231119846591e-05, "epoch": 7.429042904290429, "percentage": 37.15, "elapsed_time": "2:39:35", "remaining_time": "4:30:03", "throughput": 1488.27, "total_tokens": 14251584} {"current_steps": 67535, "total_steps": 181800, "loss": 0.0478, "lr": 3.9590362336635636e-05, "epoch": 7.429592959295929, "percentage": 37.15, "elapsed_time": "2:39:36", "remaining_time": "4:30:03", "throughput": 1488.27, "total_tokens": 14252640} {"current_steps": 67540, "total_steps": 181800, "loss": 0.0609, "lr": 3.9588413340332984e-05, "epoch": 7.43014301430143, "percentage": 37.15, "elapsed_time": "2:39:37", "remaining_time": "4:30:02", "throughput": 1488.27, "total_tokens": 14253696} {"current_steps": 67545, "total_steps": 181800, "loss": 0.0953, "lr": 3.9586464209575934e-05, "epoch": 7.430693069306931, "percentage": 37.15, "elapsed_time": "2:39:38", "remaining_time": "4:30:01", "throughput": 1488.28, "total_tokens": 14254784} {"current_steps": 67550, "total_steps": 181800, "loss": 0.1862, "lr": 3.958451494438244e-05, "epoch": 7.431243124312431, "percentage": 37.16, "elapsed_time": "2:39:38", "remaining_time": "4:30:00", "throughput": 1488.28, "total_tokens": 14255840} {"current_steps": 67555, "total_steps": 181800, "loss": 0.0756, "lr": 3.958256554477047e-05, "epoch": 7.431793179317932, "percentage": 37.16, "elapsed_time": "2:39:39", "remaining_time": "4:30:00", "throughput": 1488.29, "total_tokens": 14256896} {"current_steps": 67560, "total_steps": 181800, "loss": 0.0298, "lr": 3.9580616010757985e-05, "epoch": 7.432343234323432, "percentage": 37.16, "elapsed_time": "2:39:40", "remaining_time": "4:29:59", "throughput": 1488.3, "total_tokens": 14258016} {"current_steps": 67565, "total_steps": 181800, "loss": 0.0837, "lr": 3.957866634236297e-05, "epoch": 7.432893289328933, "percentage": 37.16, "elapsed_time": "2:39:40", "remaining_time": "4:29:58", "throughput": 1488.3, "total_tokens": 14259072} {"current_steps": 67570, "total_steps": 181800, "loss": 0.0212, "lr": 3.957671653960337e-05, "epoch": 7.433443344334433, "percentage": 37.17, "elapsed_time": "2:39:41", "remaining_time": "4:29:57", "throughput": 1488.3, "total_tokens": 14260096} {"current_steps": 67575, "total_steps": 181800, "loss": 0.0112, "lr": 3.957476660249718e-05, "epoch": 7.433993399339934, "percentage": 37.17, "elapsed_time": "2:39:42", "remaining_time": "4:29:57", "throughput": 1488.31, "total_tokens": 14261216} {"current_steps": 67580, "total_steps": 181800, "loss": 0.0061, "lr": 3.957281653106235e-05, "epoch": 7.434543454345435, "percentage": 37.17, "elapsed_time": "2:39:42", "remaining_time": "4:29:56", "throughput": 1488.31, "total_tokens": 14262272} {"current_steps": 67585, "total_steps": 181800, "loss": 0.0501, "lr": 3.9570866325316865e-05, "epoch": 7.435093509350935, "percentage": 37.18, "elapsed_time": "2:39:43", "remaining_time": "4:29:55", "throughput": 1488.32, "total_tokens": 14263328} {"current_steps": 67590, "total_steps": 181800, "loss": 0.0376, "lr": 3.95689159852787e-05, "epoch": 7.435643564356436, "percentage": 37.18, "elapsed_time": "2:39:44", "remaining_time": "4:29:54", "throughput": 1488.32, "total_tokens": 14264352} {"current_steps": 67595, "total_steps": 181800, "loss": 0.0286, "lr": 3.956696551096582e-05, "epoch": 7.436193619361936, "percentage": 37.18, "elapsed_time": "2:39:44", "remaining_time": "4:29:54", "throughput": 1488.32, "total_tokens": 14265440} {"current_steps": 67600, "total_steps": 181800, "loss": 0.109, "lr": 3.9565014902396216e-05, "epoch": 7.436743674367436, "percentage": 37.18, "elapsed_time": "2:39:45", "remaining_time": "4:29:53", "throughput": 1488.32, "total_tokens": 14266464} {"current_steps": 67605, "total_steps": 181800, "loss": 0.0092, "lr": 3.956306415958786e-05, "epoch": 7.4372937293729375, "percentage": 37.19, "elapsed_time": "2:39:46", "remaining_time": "4:29:52", "throughput": 1488.32, "total_tokens": 14267520} {"current_steps": 67610, "total_steps": 181800, "loss": 0.0138, "lr": 3.9561113282558724e-05, "epoch": 7.437843784378438, "percentage": 37.19, "elapsed_time": "2:39:46", "remaining_time": "4:29:51", "throughput": 1488.33, "total_tokens": 14268608} {"current_steps": 67615, "total_steps": 181800, "loss": 0.0057, "lr": 3.95591622713268e-05, "epoch": 7.438393839383938, "percentage": 37.19, "elapsed_time": "2:39:47", "remaining_time": "4:29:51", "throughput": 1488.33, "total_tokens": 14269632} {"current_steps": 67620, "total_steps": 181800, "loss": 0.0327, "lr": 3.9557211125910057e-05, "epoch": 7.438943894389439, "percentage": 37.19, "elapsed_time": "2:39:48", "remaining_time": "4:29:50", "throughput": 1488.33, "total_tokens": 14270656} {"current_steps": 67625, "total_steps": 181800, "loss": 0.0072, "lr": 3.955525984632649e-05, "epoch": 7.439493949394939, "percentage": 37.2, "elapsed_time": "2:39:49", "remaining_time": "4:29:49", "throughput": 1488.34, "total_tokens": 14271776} {"current_steps": 67630, "total_steps": 181800, "loss": 0.0193, "lr": 3.955330843259407e-05, "epoch": 7.44004400440044, "percentage": 37.2, "elapsed_time": "2:39:49", "remaining_time": "4:29:48", "throughput": 1488.35, "total_tokens": 14272864} {"current_steps": 67635, "total_steps": 181800, "loss": 0.007, "lr": 3.95513568847308e-05, "epoch": 7.4405940594059405, "percentage": 37.2, "elapsed_time": "2:39:50", "remaining_time": "4:29:48", "throughput": 1488.35, "total_tokens": 14273952} {"current_steps": 67640, "total_steps": 181800, "loss": 0.0534, "lr": 3.9549405202754654e-05, "epoch": 7.441144114411441, "percentage": 37.21, "elapsed_time": "2:39:51", "remaining_time": "4:29:47", "throughput": 1488.36, "total_tokens": 14275040} {"current_steps": 67645, "total_steps": 181800, "loss": 0.0945, "lr": 3.954745338668362e-05, "epoch": 7.441694169416942, "percentage": 37.21, "elapsed_time": "2:39:51", "remaining_time": "4:29:46", "throughput": 1488.36, "total_tokens": 14276096} {"current_steps": 67650, "total_steps": 181800, "loss": 0.0221, "lr": 3.954550143653568e-05, "epoch": 7.442244224422442, "percentage": 37.21, "elapsed_time": "2:39:52", "remaining_time": "4:29:45", "throughput": 1488.38, "total_tokens": 14277280} {"current_steps": 67655, "total_steps": 181800, "loss": 0.0743, "lr": 3.954354935232885e-05, "epoch": 7.442794279427943, "percentage": 37.21, "elapsed_time": "2:39:53", "remaining_time": "4:29:45", "throughput": 1488.38, "total_tokens": 14278336} {"current_steps": 67660, "total_steps": 181800, "loss": 0.0747, "lr": 3.954159713408109e-05, "epoch": 7.443344334433443, "percentage": 37.22, "elapsed_time": "2:39:53", "remaining_time": "4:29:44", "throughput": 1488.39, "total_tokens": 14279456} {"current_steps": 67665, "total_steps": 181800, "loss": 0.0605, "lr": 3.9539644781810404e-05, "epoch": 7.4438943894389435, "percentage": 37.22, "elapsed_time": "2:39:54", "remaining_time": "4:29:43", "throughput": 1488.4, "total_tokens": 14280512} {"current_steps": 67670, "total_steps": 181800, "loss": 0.0142, "lr": 3.95376922955348e-05, "epoch": 7.444444444444445, "percentage": 37.22, "elapsed_time": "2:39:55", "remaining_time": "4:29:43", "throughput": 1488.4, "total_tokens": 14281568} {"current_steps": 67675, "total_steps": 181800, "loss": 0.0082, "lr": 3.953573967527225e-05, "epoch": 7.444994499449945, "percentage": 37.22, "elapsed_time": "2:39:55", "remaining_time": "4:29:42", "throughput": 1488.41, "total_tokens": 14282688} {"current_steps": 67680, "total_steps": 181800, "loss": 0.0172, "lr": 3.9533786921040776e-05, "epoch": 7.445544554455446, "percentage": 37.23, "elapsed_time": "2:39:56", "remaining_time": "4:29:41", "throughput": 1488.41, "total_tokens": 14283680} {"current_steps": 67685, "total_steps": 181800, "loss": 0.1551, "lr": 3.953183403285836e-05, "epoch": 7.446094609460946, "percentage": 37.23, "elapsed_time": "2:39:57", "remaining_time": "4:29:40", "throughput": 1488.41, "total_tokens": 14284704} {"current_steps": 67690, "total_steps": 181800, "loss": 0.177, "lr": 3.9529881010743e-05, "epoch": 7.446644664466446, "percentage": 37.23, "elapsed_time": "2:39:58", "remaining_time": "4:29:40", "throughput": 1488.41, "total_tokens": 14285728} {"current_steps": 67695, "total_steps": 181800, "loss": 0.1113, "lr": 3.9527927854712695e-05, "epoch": 7.447194719471947, "percentage": 37.24, "elapsed_time": "2:39:58", "remaining_time": "4:29:39", "throughput": 1488.4, "total_tokens": 14286720} {"current_steps": 67700, "total_steps": 181800, "loss": 0.0182, "lr": 3.952597456478545e-05, "epoch": 7.447744774477448, "percentage": 37.24, "elapsed_time": "2:39:59", "remaining_time": "4:29:38", "throughput": 1488.4, "total_tokens": 14287712} {"current_steps": 67705, "total_steps": 181800, "loss": 0.0478, "lr": 3.952402114097927e-05, "epoch": 7.448294829482949, "percentage": 37.24, "elapsed_time": "2:40:00", "remaining_time": "4:29:37", "throughput": 1488.41, "total_tokens": 14288832} {"current_steps": 67710, "total_steps": 181800, "loss": 0.0987, "lr": 3.952206758331216e-05, "epoch": 7.448844884488449, "percentage": 37.24, "elapsed_time": "2:40:00", "remaining_time": "4:29:37", "throughput": 1488.41, "total_tokens": 14289856} {"current_steps": 67715, "total_steps": 181800, "loss": 0.0045, "lr": 3.952011389180211e-05, "epoch": 7.449394939493949, "percentage": 37.25, "elapsed_time": "2:40:01", "remaining_time": "4:29:36", "throughput": 1488.41, "total_tokens": 14290912} {"current_steps": 67720, "total_steps": 181800, "loss": 0.0072, "lr": 3.951816006646716e-05, "epoch": 7.44994499449945, "percentage": 37.25, "elapsed_time": "2:40:02", "remaining_time": "4:29:35", "throughput": 1488.41, "total_tokens": 14291968} {"current_steps": 67725, "total_steps": 181800, "loss": 0.0072, "lr": 3.951620610732527e-05, "epoch": 7.4504950495049505, "percentage": 37.25, "elapsed_time": "2:40:02", "remaining_time": "4:29:34", "throughput": 1488.42, "total_tokens": 14293056} {"current_steps": 67730, "total_steps": 181800, "loss": 0.0154, "lr": 3.9514252014394496e-05, "epoch": 7.451045104510451, "percentage": 37.26, "elapsed_time": "2:40:03", "remaining_time": "4:29:34", "throughput": 1488.42, "total_tokens": 14294080} {"current_steps": 67735, "total_steps": 181800, "loss": 0.119, "lr": 3.951229778769281e-05, "epoch": 7.451595159515952, "percentage": 37.26, "elapsed_time": "2:40:04", "remaining_time": "4:29:33", "throughput": 1488.42, "total_tokens": 14295168} {"current_steps": 67740, "total_steps": 181800, "loss": 0.0443, "lr": 3.9510343427238246e-05, "epoch": 7.452145214521452, "percentage": 37.26, "elapsed_time": "2:40:04", "remaining_time": "4:29:32", "throughput": 1488.43, "total_tokens": 14296224} {"current_steps": 67745, "total_steps": 181800, "loss": 0.0269, "lr": 3.950838893304881e-05, "epoch": 7.452695269526953, "percentage": 37.26, "elapsed_time": "2:40:05", "remaining_time": "4:29:31", "throughput": 1488.43, "total_tokens": 14297248} {"current_steps": 67750, "total_steps": 181800, "loss": 0.0644, "lr": 3.9506434305142506e-05, "epoch": 7.453245324532453, "percentage": 37.27, "elapsed_time": "2:40:06", "remaining_time": "4:29:31", "throughput": 1488.44, "total_tokens": 14298368} {"current_steps": 67755, "total_steps": 181800, "loss": 0.0338, "lr": 3.9504479543537366e-05, "epoch": 7.4537953795379535, "percentage": 37.27, "elapsed_time": "2:40:06", "remaining_time": "4:29:30", "throughput": 1488.44, "total_tokens": 14299424} {"current_steps": 67760, "total_steps": 181800, "loss": 0.0632, "lr": 3.950252464825139e-05, "epoch": 7.4543454345434546, "percentage": 37.27, "elapsed_time": "2:40:07", "remaining_time": "4:29:29", "throughput": 1488.44, "total_tokens": 14300480} {"current_steps": 67765, "total_steps": 181800, "loss": 0.058, "lr": 3.950056961930262e-05, "epoch": 7.454895489548955, "percentage": 37.27, "elapsed_time": "2:40:08", "remaining_time": "4:29:28", "throughput": 1488.44, "total_tokens": 14301472} {"current_steps": 67770, "total_steps": 181800, "loss": 0.0242, "lr": 3.9498614456709045e-05, "epoch": 7.455445544554456, "percentage": 37.28, "elapsed_time": "2:40:09", "remaining_time": "4:29:28", "throughput": 1488.44, "total_tokens": 14302496} {"current_steps": 67775, "total_steps": 181800, "loss": 0.0175, "lr": 3.949665916048869e-05, "epoch": 7.455995599559956, "percentage": 37.28, "elapsed_time": "2:40:09", "remaining_time": "4:29:27", "throughput": 1488.44, "total_tokens": 14303520} {"current_steps": 67780, "total_steps": 181800, "loss": 0.0118, "lr": 3.94947037306596e-05, "epoch": 7.456545654565456, "percentage": 37.28, "elapsed_time": "2:40:10", "remaining_time": "4:29:26", "throughput": 1488.45, "total_tokens": 14304608} {"current_steps": 67785, "total_steps": 181800, "loss": 0.0495, "lr": 3.949274816723977e-05, "epoch": 7.457095709570957, "percentage": 37.29, "elapsed_time": "2:40:11", "remaining_time": "4:29:25", "throughput": 1488.45, "total_tokens": 14305664} {"current_steps": 67790, "total_steps": 181800, "loss": 0.0998, "lr": 3.9490792470247244e-05, "epoch": 7.457645764576458, "percentage": 37.29, "elapsed_time": "2:40:11", "remaining_time": "4:29:25", "throughput": 1488.45, "total_tokens": 14306720} {"current_steps": 67795, "total_steps": 181800, "loss": 0.054, "lr": 3.9488836639700036e-05, "epoch": 7.458195819581958, "percentage": 37.29, "elapsed_time": "2:40:12", "remaining_time": "4:29:24", "throughput": 1488.45, "total_tokens": 14307712} {"current_steps": 67800, "total_steps": 181800, "loss": 0.0172, "lr": 3.948688067561617e-05, "epoch": 7.458745874587459, "percentage": 37.29, "elapsed_time": "2:40:13", "remaining_time": "4:29:23", "throughput": 1488.45, "total_tokens": 14308768} {"current_steps": 67805, "total_steps": 181800, "loss": 0.0063, "lr": 3.948492457801367e-05, "epoch": 7.459295929592959, "percentage": 37.3, "elapsed_time": "2:40:13", "remaining_time": "4:29:23", "throughput": 1488.45, "total_tokens": 14309760} {"current_steps": 67810, "total_steps": 181800, "loss": 0.063, "lr": 3.948296834691058e-05, "epoch": 7.45984598459846, "percentage": 37.3, "elapsed_time": "2:40:14", "remaining_time": "4:29:22", "throughput": 1488.44, "total_tokens": 14310752} {"current_steps": 67815, "total_steps": 181800, "loss": 0.053, "lr": 3.948101198232491e-05, "epoch": 7.46039603960396, "percentage": 37.3, "elapsed_time": "2:40:15", "remaining_time": "4:29:21", "throughput": 1488.45, "total_tokens": 14311872} {"current_steps": 67820, "total_steps": 181800, "loss": 0.0174, "lr": 3.947905548427471e-05, "epoch": 7.460946094609461, "percentage": 37.3, "elapsed_time": "2:40:15", "remaining_time": "4:29:20", "throughput": 1488.46, "total_tokens": 14312928} {"current_steps": 67825, "total_steps": 181800, "loss": 0.04, "lr": 3.9477098852778e-05, "epoch": 7.461496149614962, "percentage": 37.31, "elapsed_time": "2:40:16", "remaining_time": "4:29:20", "throughput": 1488.47, "total_tokens": 14314048} {"current_steps": 67830, "total_steps": 181800, "loss": 0.0126, "lr": 3.9475142087852827e-05, "epoch": 7.462046204620462, "percentage": 37.31, "elapsed_time": "2:40:17", "remaining_time": "4:29:19", "throughput": 1488.47, "total_tokens": 14315136} {"current_steps": 67835, "total_steps": 181800, "loss": 0.0393, "lr": 3.94731851895172e-05, "epoch": 7.462596259625963, "percentage": 37.31, "elapsed_time": "2:40:18", "remaining_time": "4:29:18", "throughput": 1488.47, "total_tokens": 14316128} {"current_steps": 67840, "total_steps": 181800, "loss": 0.0278, "lr": 3.947122815778917e-05, "epoch": 7.463146314631463, "percentage": 37.32, "elapsed_time": "2:40:18", "remaining_time": "4:29:17", "throughput": 1488.47, "total_tokens": 14317184} {"current_steps": 67845, "total_steps": 181800, "loss": 0.085, "lr": 3.946927099268679e-05, "epoch": 7.463696369636963, "percentage": 37.32, "elapsed_time": "2:40:19", "remaining_time": "4:29:17", "throughput": 1488.47, "total_tokens": 14318208} {"current_steps": 67850, "total_steps": 181800, "loss": 0.0225, "lr": 3.946731369422807e-05, "epoch": 7.4642464246424645, "percentage": 37.32, "elapsed_time": "2:40:20", "remaining_time": "4:29:16", "throughput": 1488.48, "total_tokens": 14319296} {"current_steps": 67855, "total_steps": 181800, "loss": 0.0031, "lr": 3.9465356262431064e-05, "epoch": 7.464796479647965, "percentage": 37.32, "elapsed_time": "2:40:20", "remaining_time": "4:29:15", "throughput": 1488.48, "total_tokens": 14320352} {"current_steps": 67860, "total_steps": 181800, "loss": 0.0142, "lr": 3.9463398697313816e-05, "epoch": 7.465346534653466, "percentage": 37.33, "elapsed_time": "2:40:21", "remaining_time": "4:29:14", "throughput": 1488.49, "total_tokens": 14321440} {"current_steps": 67865, "total_steps": 181800, "loss": 0.0102, "lr": 3.946144099889435e-05, "epoch": 7.465896589658966, "percentage": 37.33, "elapsed_time": "2:40:22", "remaining_time": "4:29:14", "throughput": 1488.49, "total_tokens": 14322464} {"current_steps": 67870, "total_steps": 181800, "loss": 0.0188, "lr": 3.945948316719073e-05, "epoch": 7.466446644664466, "percentage": 37.33, "elapsed_time": "2:40:22", "remaining_time": "4:29:13", "throughput": 1488.49, "total_tokens": 14323520} {"current_steps": 67875, "total_steps": 181800, "loss": 0.0144, "lr": 3.945752520222099e-05, "epoch": 7.466996699669967, "percentage": 37.33, "elapsed_time": "2:40:23", "remaining_time": "4:29:12", "throughput": 1488.49, "total_tokens": 14324544} {"current_steps": 67880, "total_steps": 181800, "loss": 0.0809, "lr": 3.9455567104003176e-05, "epoch": 7.4675467546754675, "percentage": 37.34, "elapsed_time": "2:40:24", "remaining_time": "4:29:11", "throughput": 1488.5, "total_tokens": 14325600} {"current_steps": 67885, "total_steps": 181800, "loss": 0.0188, "lr": 3.9453608872555344e-05, "epoch": 7.468096809680969, "percentage": 37.34, "elapsed_time": "2:40:24", "remaining_time": "4:29:11", "throughput": 1488.51, "total_tokens": 14326720} {"current_steps": 67890, "total_steps": 181800, "loss": 0.0098, "lr": 3.9451650507895535e-05, "epoch": 7.468646864686469, "percentage": 37.34, "elapsed_time": "2:40:25", "remaining_time": "4:29:10", "throughput": 1488.51, "total_tokens": 14327808} {"current_steps": 67895, "total_steps": 181800, "loss": 0.011, "lr": 3.9449692010041787e-05, "epoch": 7.469196919691969, "percentage": 37.35, "elapsed_time": "2:40:26", "remaining_time": "4:29:09", "throughput": 1488.51, "total_tokens": 14328832} {"current_steps": 67900, "total_steps": 181800, "loss": 0.1805, "lr": 3.9447733379012165e-05, "epoch": 7.46974697469747, "percentage": 37.35, "elapsed_time": "2:40:26", "remaining_time": "4:29:08", "throughput": 1488.52, "total_tokens": 14329952} {"current_steps": 67905, "total_steps": 181800, "loss": 0.0041, "lr": 3.9445774614824716e-05, "epoch": 7.47029702970297, "percentage": 37.35, "elapsed_time": "2:40:27", "remaining_time": "4:29:08", "throughput": 1488.53, "total_tokens": 14331040} {"current_steps": 67910, "total_steps": 181800, "loss": 0.0838, "lr": 3.9443815717497504e-05, "epoch": 7.4708470847084705, "percentage": 37.35, "elapsed_time": "2:40:28", "remaining_time": "4:29:07", "throughput": 1488.53, "total_tokens": 14332064} {"current_steps": 67915, "total_steps": 181800, "loss": 0.1052, "lr": 3.944185668704856e-05, "epoch": 7.471397139713972, "percentage": 37.36, "elapsed_time": "2:40:29", "remaining_time": "4:29:06", "throughput": 1488.53, "total_tokens": 14333120} {"current_steps": 67920, "total_steps": 181800, "loss": 0.0092, "lr": 3.943989752349596e-05, "epoch": 7.471947194719472, "percentage": 37.36, "elapsed_time": "2:40:29", "remaining_time": "4:29:05", "throughput": 1488.53, "total_tokens": 14334144} {"current_steps": 67925, "total_steps": 181800, "loss": 0.1073, "lr": 3.943793822685775e-05, "epoch": 7.472497249724973, "percentage": 37.36, "elapsed_time": "2:40:30", "remaining_time": "4:29:05", "throughput": 1488.54, "total_tokens": 14335232} {"current_steps": 67930, "total_steps": 181800, "loss": 0.018, "lr": 3.9435978797151997e-05, "epoch": 7.473047304730473, "percentage": 37.37, "elapsed_time": "2:40:31", "remaining_time": "4:29:04", "throughput": 1488.54, "total_tokens": 14336288} {"current_steps": 67935, "total_steps": 181800, "loss": 0.067, "lr": 3.9434019234396745e-05, "epoch": 7.473597359735973, "percentage": 37.37, "elapsed_time": "2:40:31", "remaining_time": "4:29:03", "throughput": 1488.54, "total_tokens": 14337344} {"current_steps": 67940, "total_steps": 181800, "loss": 0.0914, "lr": 3.9432059538610077e-05, "epoch": 7.474147414741474, "percentage": 37.37, "elapsed_time": "2:40:32", "remaining_time": "4:29:02", "throughput": 1488.54, "total_tokens": 14338336} {"current_steps": 67945, "total_steps": 181800, "loss": 0.0153, "lr": 3.943009970981003e-05, "epoch": 7.474697469746975, "percentage": 37.37, "elapsed_time": "2:40:33", "remaining_time": "4:29:02", "throughput": 1488.54, "total_tokens": 14339360} {"current_steps": 67950, "total_steps": 181800, "loss": 0.0377, "lr": 3.9428139748014683e-05, "epoch": 7.475247524752476, "percentage": 37.38, "elapsed_time": "2:40:33", "remaining_time": "4:29:01", "throughput": 1488.54, "total_tokens": 14340384} {"current_steps": 67955, "total_steps": 181800, "loss": 0.0909, "lr": 3.94261796532421e-05, "epoch": 7.475797579757976, "percentage": 37.38, "elapsed_time": "2:40:34", "remaining_time": "4:29:00", "throughput": 1488.54, "total_tokens": 14341408} {"current_steps": 67960, "total_steps": 181800, "loss": 0.0177, "lr": 3.9424219425510335e-05, "epoch": 7.476347634763476, "percentage": 37.38, "elapsed_time": "2:40:35", "remaining_time": "4:29:00", "throughput": 1488.54, "total_tokens": 14342464} {"current_steps": 67965, "total_steps": 181800, "loss": 0.0594, "lr": 3.942225906483746e-05, "epoch": 7.476897689768977, "percentage": 37.38, "elapsed_time": "2:40:35", "remaining_time": "4:28:59", "throughput": 1488.55, "total_tokens": 14343520} {"current_steps": 67970, "total_steps": 181800, "loss": 0.018, "lr": 3.942029857124154e-05, "epoch": 7.477447744774477, "percentage": 37.39, "elapsed_time": "2:40:36", "remaining_time": "4:28:58", "throughput": 1488.55, "total_tokens": 14344640} {"current_steps": 67975, "total_steps": 181800, "loss": 0.0069, "lr": 3.941833794474066e-05, "epoch": 7.477997799779978, "percentage": 37.39, "elapsed_time": "2:40:37", "remaining_time": "4:28:57", "throughput": 1488.55, "total_tokens": 14345664} {"current_steps": 67980, "total_steps": 181800, "loss": 0.1178, "lr": 3.9416377185352874e-05, "epoch": 7.478547854785479, "percentage": 37.39, "elapsed_time": "2:40:38", "remaining_time": "4:28:57", "throughput": 1488.56, "total_tokens": 14346720} {"current_steps": 67985, "total_steps": 181800, "loss": 0.0103, "lr": 3.941441629309626e-05, "epoch": 7.479097909790979, "percentage": 37.4, "elapsed_time": "2:40:38", "remaining_time": "4:28:56", "throughput": 1488.56, "total_tokens": 14347808} {"current_steps": 67990, "total_steps": 181800, "loss": 0.0319, "lr": 3.941245526798887e-05, "epoch": 7.47964796479648, "percentage": 37.4, "elapsed_time": "2:40:39", "remaining_time": "4:28:55", "throughput": 1488.57, "total_tokens": 14348896} {"current_steps": 67995, "total_steps": 181800, "loss": 0.0161, "lr": 3.941049411004881e-05, "epoch": 7.48019801980198, "percentage": 37.4, "elapsed_time": "2:40:40", "remaining_time": "4:28:54", "throughput": 1488.58, "total_tokens": 14350016} {"current_steps": 68000, "total_steps": 181800, "loss": 0.0099, "lr": 3.9408532819294144e-05, "epoch": 7.48074807480748, "percentage": 37.4, "elapsed_time": "2:40:40", "remaining_time": "4:28:54", "throughput": 1488.58, "total_tokens": 14351008} {"current_steps": 68005, "total_steps": 181800, "loss": 0.087, "lr": 3.9406571395742945e-05, "epoch": 7.4812981298129815, "percentage": 37.41, "elapsed_time": "2:40:41", "remaining_time": "4:28:53", "throughput": 1488.58, "total_tokens": 14352096} {"current_steps": 68010, "total_steps": 181800, "loss": 0.0392, "lr": 3.940460983941327e-05, "epoch": 7.481848184818482, "percentage": 37.41, "elapsed_time": "2:40:42", "remaining_time": "4:28:52", "throughput": 1488.58, "total_tokens": 14353152} {"current_steps": 68015, "total_steps": 181800, "loss": 0.0039, "lr": 3.940264815032324e-05, "epoch": 7.482398239823983, "percentage": 37.41, "elapsed_time": "2:40:42", "remaining_time": "4:28:51", "throughput": 1488.59, "total_tokens": 14354240} {"current_steps": 68020, "total_steps": 181800, "loss": 0.0198, "lr": 3.94006863284909e-05, "epoch": 7.482948294829483, "percentage": 37.41, "elapsed_time": "2:40:43", "remaining_time": "4:28:51", "throughput": 1488.6, "total_tokens": 14355328} {"current_steps": 68025, "total_steps": 181800, "loss": 0.0899, "lr": 3.9398724373934355e-05, "epoch": 7.483498349834983, "percentage": 37.42, "elapsed_time": "2:40:44", "remaining_time": "4:28:50", "throughput": 1488.6, "total_tokens": 14356416} {"current_steps": 68030, "total_steps": 181800, "loss": 0.0205, "lr": 3.939676228667167e-05, "epoch": 7.484048404840484, "percentage": 37.42, "elapsed_time": "2:40:44", "remaining_time": "4:28:49", "throughput": 1488.61, "total_tokens": 14357472} {"current_steps": 68035, "total_steps": 181800, "loss": 0.0823, "lr": 3.939480006672094e-05, "epoch": 7.4845984598459845, "percentage": 37.42, "elapsed_time": "2:40:45", "remaining_time": "4:28:48", "throughput": 1488.61, "total_tokens": 14358528} {"current_steps": 68040, "total_steps": 181800, "loss": 0.008, "lr": 3.939283771410024e-05, "epoch": 7.485148514851485, "percentage": 37.43, "elapsed_time": "2:40:46", "remaining_time": "4:28:48", "throughput": 1488.61, "total_tokens": 14359552} {"current_steps": 68045, "total_steps": 181800, "loss": 0.0046, "lr": 3.939087522882766e-05, "epoch": 7.485698569856986, "percentage": 37.43, "elapsed_time": "2:40:46", "remaining_time": "4:28:47", "throughput": 1488.62, "total_tokens": 14360672} {"current_steps": 68050, "total_steps": 181800, "loss": 0.0152, "lr": 3.93889126109213e-05, "epoch": 7.486248624862486, "percentage": 37.43, "elapsed_time": "2:40:47", "remaining_time": "4:28:46", "throughput": 1488.62, "total_tokens": 14361696} {"current_steps": 68055, "total_steps": 181800, "loss": 0.0958, "lr": 3.938694986039922e-05, "epoch": 7.486798679867987, "percentage": 37.43, "elapsed_time": "2:40:48", "remaining_time": "4:28:45", "throughput": 1488.62, "total_tokens": 14362752} {"current_steps": 68060, "total_steps": 181800, "loss": 0.0136, "lr": 3.9384986977279535e-05, "epoch": 7.487348734873487, "percentage": 37.44, "elapsed_time": "2:40:49", "remaining_time": "4:28:45", "throughput": 1488.63, "total_tokens": 14363840} {"current_steps": 68065, "total_steps": 181800, "loss": 0.0073, "lr": 3.938302396158033e-05, "epoch": 7.4878987898789875, "percentage": 37.44, "elapsed_time": "2:40:49", "remaining_time": "4:28:44", "throughput": 1488.63, "total_tokens": 14364864} {"current_steps": 68070, "total_steps": 181800, "loss": 0.0124, "lr": 3.938106081331969e-05, "epoch": 7.488448844884489, "percentage": 37.44, "elapsed_time": "2:40:50", "remaining_time": "4:28:43", "throughput": 1488.63, "total_tokens": 14365920} {"current_steps": 68075, "total_steps": 181800, "loss": 0.0655, "lr": 3.9379097532515725e-05, "epoch": 7.488998899889989, "percentage": 37.44, "elapsed_time": "2:40:51", "remaining_time": "4:28:43", "throughput": 1488.63, "total_tokens": 14366944} {"current_steps": 68080, "total_steps": 181800, "loss": 0.0187, "lr": 3.9377134119186507e-05, "epoch": 7.48954895489549, "percentage": 37.45, "elapsed_time": "2:40:51", "remaining_time": "4:28:42", "throughput": 1488.63, "total_tokens": 14367968} {"current_steps": 68085, "total_steps": 181800, "loss": 0.0091, "lr": 3.937517057335014e-05, "epoch": 7.49009900990099, "percentage": 37.45, "elapsed_time": "2:40:52", "remaining_time": "4:28:41", "throughput": 1488.63, "total_tokens": 14369056} {"current_steps": 68090, "total_steps": 181800, "loss": 0.0436, "lr": 3.937320689502473e-05, "epoch": 7.49064906490649, "percentage": 37.45, "elapsed_time": "2:40:53", "remaining_time": "4:28:40", "throughput": 1488.63, "total_tokens": 14370080} {"current_steps": 68095, "total_steps": 181800, "loss": 0.0022, "lr": 3.937124308422837e-05, "epoch": 7.491199119911991, "percentage": 37.46, "elapsed_time": "2:40:53", "remaining_time": "4:28:40", "throughput": 1488.64, "total_tokens": 14371136} {"current_steps": 68100, "total_steps": 181800, "loss": 0.0052, "lr": 3.936927914097915e-05, "epoch": 7.491749174917492, "percentage": 37.46, "elapsed_time": "2:40:54", "remaining_time": "4:28:39", "throughput": 1488.64, "total_tokens": 14372224} {"current_steps": 68105, "total_steps": 181800, "loss": 0.0639, "lr": 3.936731506529519e-05, "epoch": 7.492299229922993, "percentage": 37.46, "elapsed_time": "2:40:55", "remaining_time": "4:28:38", "throughput": 1488.65, "total_tokens": 14373312} {"current_steps": 68110, "total_steps": 181800, "loss": 0.0335, "lr": 3.936535085719457e-05, "epoch": 7.492849284928493, "percentage": 37.46, "elapsed_time": "2:40:55", "remaining_time": "4:28:37", "throughput": 1488.65, "total_tokens": 14374368} {"current_steps": 68115, "total_steps": 181800, "loss": 0.0187, "lr": 3.936338651669541e-05, "epoch": 7.493399339933993, "percentage": 37.47, "elapsed_time": "2:40:56", "remaining_time": "4:28:37", "throughput": 1488.65, "total_tokens": 14375360} {"current_steps": 68120, "total_steps": 181800, "loss": 0.0342, "lr": 3.936142204381581e-05, "epoch": 7.493949394939494, "percentage": 37.47, "elapsed_time": "2:40:57", "remaining_time": "4:28:36", "throughput": 1488.65, "total_tokens": 14376448} {"current_steps": 68125, "total_steps": 181800, "loss": 0.0362, "lr": 3.935945743857388e-05, "epoch": 7.494499449944994, "percentage": 37.47, "elapsed_time": "2:40:58", "remaining_time": "4:28:35", "throughput": 1488.65, "total_tokens": 14377440} {"current_steps": 68130, "total_steps": 181800, "loss": 0.0315, "lr": 3.935749270098771e-05, "epoch": 7.4950495049504955, "percentage": 37.48, "elapsed_time": "2:40:58", "remaining_time": "4:28:34", "throughput": 1488.65, "total_tokens": 14378464} {"current_steps": 68135, "total_steps": 181800, "loss": 0.0952, "lr": 3.935552783107542e-05, "epoch": 7.495599559955996, "percentage": 37.48, "elapsed_time": "2:40:59", "remaining_time": "4:28:34", "throughput": 1488.65, "total_tokens": 14379488} {"current_steps": 68140, "total_steps": 181800, "loss": 0.0781, "lr": 3.9353562828855124e-05, "epoch": 7.496149614961496, "percentage": 37.48, "elapsed_time": "2:41:00", "remaining_time": "4:28:33", "throughput": 1488.65, "total_tokens": 14380576} {"current_steps": 68145, "total_steps": 181800, "loss": 0.1264, "lr": 3.935159769434493e-05, "epoch": 7.496699669966997, "percentage": 37.48, "elapsed_time": "2:41:00", "remaining_time": "4:28:32", "throughput": 1488.66, "total_tokens": 14381696} {"current_steps": 68150, "total_steps": 181800, "loss": 0.0858, "lr": 3.934963242756294e-05, "epoch": 7.497249724972497, "percentage": 37.49, "elapsed_time": "2:41:01", "remaining_time": "4:28:31", "throughput": 1488.67, "total_tokens": 14382784} {"current_steps": 68155, "total_steps": 181800, "loss": 0.0608, "lr": 3.9347667028527276e-05, "epoch": 7.497799779977997, "percentage": 37.49, "elapsed_time": "2:41:02", "remaining_time": "4:28:31", "throughput": 1488.67, "total_tokens": 14383840} {"current_steps": 68160, "total_steps": 181800, "loss": 0.028, "lr": 3.9345701497256046e-05, "epoch": 7.4983498349834985, "percentage": 37.49, "elapsed_time": "2:41:02", "remaining_time": "4:28:30", "throughput": 1488.67, "total_tokens": 14384864} {"current_steps": 68165, "total_steps": 181800, "loss": 0.0714, "lr": 3.934373583376737e-05, "epoch": 7.498899889988999, "percentage": 37.49, "elapsed_time": "2:41:03", "remaining_time": "4:28:29", "throughput": 1488.68, "total_tokens": 14385984} {"current_steps": 68170, "total_steps": 181800, "loss": 0.0048, "lr": 3.934177003807937e-05, "epoch": 7.4994499449945, "percentage": 37.5, "elapsed_time": "2:41:04", "remaining_time": "4:28:28", "throughput": 1488.69, "total_tokens": 14387104} {"current_steps": 68175, "total_steps": 181800, "loss": 0.0138, "lr": 3.933980411021015e-05, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "2:41:04", "remaining_time": "4:28:28", "throughput": 1488.7, "total_tokens": 14388192} {"current_steps": 68180, "total_steps": 181800, "loss": 0.0435, "lr": 3.933783805017784e-05, "epoch": 7.5005500550055, "percentage": 37.5, "elapsed_time": "2:41:05", "remaining_time": "4:28:27", "throughput": 1488.71, "total_tokens": 14389280} {"current_steps": 68185, "total_steps": 181800, "loss": 0.0464, "lr": 3.933587185800055e-05, "epoch": 7.501100110011001, "percentage": 37.51, "elapsed_time": "2:41:06", "remaining_time": "4:28:26", "throughput": 1488.71, "total_tokens": 14390368} {"current_steps": 68190, "total_steps": 181800, "loss": 0.0382, "lr": 3.933390553369642e-05, "epoch": 7.5016501650165015, "percentage": 37.51, "elapsed_time": "2:41:06", "remaining_time": "4:28:25", "throughput": 1488.71, "total_tokens": 14391392} {"current_steps": 68195, "total_steps": 181800, "loss": 0.038, "lr": 3.933193907728355e-05, "epoch": 7.502200220022003, "percentage": 37.51, "elapsed_time": "2:41:07", "remaining_time": "4:28:25", "throughput": 1488.72, "total_tokens": 14392480} {"current_steps": 68200, "total_steps": 181800, "loss": 0.0719, "lr": 3.9329972488780086e-05, "epoch": 7.502750275027503, "percentage": 37.51, "elapsed_time": "2:41:08", "remaining_time": "4:28:24", "throughput": 1488.73, "total_tokens": 14393568} {"current_steps": 68205, "total_steps": 181800, "loss": 0.006, "lr": 3.932800576820413e-05, "epoch": 7.503300330033003, "percentage": 37.52, "elapsed_time": "2:41:09", "remaining_time": "4:28:23", "throughput": 1488.72, "total_tokens": 14394560} {"current_steps": 68210, "total_steps": 181800, "loss": 0.0625, "lr": 3.932603891557382e-05, "epoch": 7.503850385038504, "percentage": 37.52, "elapsed_time": "2:41:09", "remaining_time": "4:28:23", "throughput": 1488.72, "total_tokens": 14395552} {"current_steps": 68215, "total_steps": 181800, "loss": 0.0286, "lr": 3.9324071930907294e-05, "epoch": 7.504400440044004, "percentage": 37.52, "elapsed_time": "2:41:10", "remaining_time": "4:28:22", "throughput": 1488.72, "total_tokens": 14396640} {"current_steps": 68220, "total_steps": 181800, "loss": 0.0277, "lr": 3.932210481422267e-05, "epoch": 7.5049504950495045, "percentage": 37.52, "elapsed_time": "2:41:11", "remaining_time": "4:28:21", "throughput": 1488.73, "total_tokens": 14397696} {"current_steps": 68225, "total_steps": 181800, "loss": 0.1133, "lr": 3.932013756553807e-05, "epoch": 7.505500550055006, "percentage": 37.53, "elapsed_time": "2:41:11", "remaining_time": "4:28:20", "throughput": 1488.73, "total_tokens": 14398752} {"current_steps": 68230, "total_steps": 181800, "loss": 0.0784, "lr": 3.931817018487164e-05, "epoch": 7.506050605060506, "percentage": 37.53, "elapsed_time": "2:41:12", "remaining_time": "4:28:20", "throughput": 1488.74, "total_tokens": 14399840} {"current_steps": 68235, "total_steps": 181800, "loss": 0.0171, "lr": 3.93162026722415e-05, "epoch": 7.506600660066007, "percentage": 37.53, "elapsed_time": "2:41:13", "remaining_time": "4:28:19", "throughput": 1488.74, "total_tokens": 14400864} {"current_steps": 68240, "total_steps": 181800, "loss": 0.0864, "lr": 3.931423502766579e-05, "epoch": 7.507150715071507, "percentage": 37.54, "elapsed_time": "2:41:13", "remaining_time": "4:28:18", "throughput": 1488.73, "total_tokens": 14401856} {"current_steps": 68245, "total_steps": 181800, "loss": 0.0866, "lr": 3.9312267251162646e-05, "epoch": 7.507700770077007, "percentage": 37.54, "elapsed_time": "2:41:14", "remaining_time": "4:28:17", "throughput": 1488.73, "total_tokens": 14402848} {"current_steps": 68250, "total_steps": 181800, "loss": 0.0245, "lr": 3.931029934275021e-05, "epoch": 7.508250825082508, "percentage": 37.54, "elapsed_time": "2:41:15", "remaining_time": "4:28:17", "throughput": 1488.73, "total_tokens": 14403936} {"current_steps": 68255, "total_steps": 181800, "loss": 0.0297, "lr": 3.93083313024466e-05, "epoch": 7.508800880088009, "percentage": 37.54, "elapsed_time": "2:41:15", "remaining_time": "4:28:16", "throughput": 1488.73, "total_tokens": 14404928} {"current_steps": 68260, "total_steps": 181800, "loss": 0.0513, "lr": 3.930636313026997e-05, "epoch": 7.50935093509351, "percentage": 37.55, "elapsed_time": "2:41:16", "remaining_time": "4:28:15", "throughput": 1488.73, "total_tokens": 14405984} {"current_steps": 68265, "total_steps": 181800, "loss": 0.0149, "lr": 3.9304394826238464e-05, "epoch": 7.50990099009901, "percentage": 37.55, "elapsed_time": "2:41:17", "remaining_time": "4:28:14", "throughput": 1488.74, "total_tokens": 14407072} {"current_steps": 68270, "total_steps": 181800, "loss": 0.0193, "lr": 3.930242639037021e-05, "epoch": 7.51045104510451, "percentage": 37.55, "elapsed_time": "2:41:18", "remaining_time": "4:28:14", "throughput": 1488.74, "total_tokens": 14408128} {"current_steps": 68275, "total_steps": 181800, "loss": 0.0274, "lr": 3.930045782268335e-05, "epoch": 7.511001100110011, "percentage": 37.56, "elapsed_time": "2:41:18", "remaining_time": "4:28:13", "throughput": 1488.75, "total_tokens": 14409216} {"current_steps": 68280, "total_steps": 181800, "loss": 0.0756, "lr": 3.929848912319603e-05, "epoch": 7.511551155115511, "percentage": 37.56, "elapsed_time": "2:41:19", "remaining_time": "4:28:12", "throughput": 1488.75, "total_tokens": 14410240} {"current_steps": 68285, "total_steps": 181800, "loss": 0.0251, "lr": 3.92965202919264e-05, "epoch": 7.512101210121012, "percentage": 37.56, "elapsed_time": "2:41:20", "remaining_time": "4:28:11", "throughput": 1488.75, "total_tokens": 14411264} {"current_steps": 68290, "total_steps": 181800, "loss": 0.027, "lr": 3.929455132889261e-05, "epoch": 7.512651265126513, "percentage": 37.56, "elapsed_time": "2:41:20", "remaining_time": "4:28:11", "throughput": 1488.75, "total_tokens": 14412352} {"current_steps": 68295, "total_steps": 181800, "loss": 0.0174, "lr": 3.929258223411279e-05, "epoch": 7.513201320132013, "percentage": 37.57, "elapsed_time": "2:41:21", "remaining_time": "4:28:10", "throughput": 1488.75, "total_tokens": 14413376} {"current_steps": 68300, "total_steps": 181800, "loss": 0.0412, "lr": 3.9290613007605104e-05, "epoch": 7.513751375137514, "percentage": 37.57, "elapsed_time": "2:41:22", "remaining_time": "4:28:09", "throughput": 1488.76, "total_tokens": 14414432} {"current_steps": 68305, "total_steps": 181800, "loss": 0.1087, "lr": 3.928864364938769e-05, "epoch": 7.514301430143014, "percentage": 37.57, "elapsed_time": "2:41:22", "remaining_time": "4:28:08", "throughput": 1488.76, "total_tokens": 14415488} {"current_steps": 68310, "total_steps": 181800, "loss": 0.0091, "lr": 3.9286674159478706e-05, "epoch": 7.514851485148515, "percentage": 37.57, "elapsed_time": "2:41:23", "remaining_time": "4:28:08", "throughput": 1488.76, "total_tokens": 14416544} {"current_steps": 68315, "total_steps": 181800, "loss": 0.005, "lr": 3.928470453789631e-05, "epoch": 7.5154015401540155, "percentage": 37.58, "elapsed_time": "2:41:24", "remaining_time": "4:28:07", "throughput": 1488.77, "total_tokens": 14417600} {"current_steps": 68320, "total_steps": 181800, "loss": 0.0166, "lr": 3.9282734784658636e-05, "epoch": 7.515951595159516, "percentage": 37.58, "elapsed_time": "2:41:24", "remaining_time": "4:28:06", "throughput": 1488.77, "total_tokens": 14418688} {"current_steps": 68325, "total_steps": 181800, "loss": 0.024, "lr": 3.928076489978385e-05, "epoch": 7.516501650165017, "percentage": 37.58, "elapsed_time": "2:41:25", "remaining_time": "4:28:06", "throughput": 1488.77, "total_tokens": 14419712} {"current_steps": 68330, "total_steps": 181800, "loss": 0.0533, "lr": 3.9278794883290116e-05, "epoch": 7.517051705170517, "percentage": 37.59, "elapsed_time": "2:41:26", "remaining_time": "4:28:05", "throughput": 1488.77, "total_tokens": 14420736} {"current_steps": 68335, "total_steps": 181800, "loss": 0.0258, "lr": 3.927682473519557e-05, "epoch": 7.517601760176017, "percentage": 37.59, "elapsed_time": "2:41:27", "remaining_time": "4:28:04", "throughput": 1488.77, "total_tokens": 14421760} {"current_steps": 68340, "total_steps": 181800, "loss": 0.0023, "lr": 3.927485445551839e-05, "epoch": 7.518151815181518, "percentage": 37.59, "elapsed_time": "2:41:27", "remaining_time": "4:28:03", "throughput": 1488.77, "total_tokens": 14422816} {"current_steps": 68345, "total_steps": 181800, "loss": 0.0107, "lr": 3.9272884044276714e-05, "epoch": 7.5187018701870185, "percentage": 37.59, "elapsed_time": "2:41:28", "remaining_time": "4:28:03", "throughput": 1488.77, "total_tokens": 14423840} {"current_steps": 68350, "total_steps": 181800, "loss": 0.0709, "lr": 3.927091350148873e-05, "epoch": 7.51925192519252, "percentage": 37.6, "elapsed_time": "2:41:29", "remaining_time": "4:28:02", "throughput": 1488.77, "total_tokens": 14424864} {"current_steps": 68355, "total_steps": 181800, "loss": 0.0433, "lr": 3.9268942827172573e-05, "epoch": 7.51980198019802, "percentage": 37.6, "elapsed_time": "2:41:29", "remaining_time": "4:28:01", "throughput": 1488.77, "total_tokens": 14425888} {"current_steps": 68360, "total_steps": 181800, "loss": 0.0215, "lr": 3.926697202134642e-05, "epoch": 7.52035203520352, "percentage": 37.6, "elapsed_time": "2:41:30", "remaining_time": "4:28:00", "throughput": 1488.77, "total_tokens": 14426880} {"current_steps": 68365, "total_steps": 181800, "loss": 0.0188, "lr": 3.926500108402843e-05, "epoch": 7.520902090209021, "percentage": 37.6, "elapsed_time": "2:41:31", "remaining_time": "4:28:00", "throughput": 1488.77, "total_tokens": 14427872} {"current_steps": 68370, "total_steps": 181800, "loss": 0.0245, "lr": 3.9263030015236776e-05, "epoch": 7.521452145214521, "percentage": 37.61, "elapsed_time": "2:41:31", "remaining_time": "4:27:59", "throughput": 1488.77, "total_tokens": 14428896} {"current_steps": 68375, "total_steps": 181800, "loss": 0.0247, "lr": 3.926105881498961e-05, "epoch": 7.522002200220022, "percentage": 37.61, "elapsed_time": "2:41:32", "remaining_time": "4:27:58", "throughput": 1488.77, "total_tokens": 14429952} {"current_steps": 68380, "total_steps": 181800, "loss": 0.0258, "lr": 3.925908748330511e-05, "epoch": 7.522552255225523, "percentage": 37.61, "elapsed_time": "2:41:33", "remaining_time": "4:27:57", "throughput": 1488.77, "total_tokens": 14431008} {"current_steps": 68385, "total_steps": 181800, "loss": 0.0454, "lr": 3.925711602020144e-05, "epoch": 7.523102310231023, "percentage": 37.62, "elapsed_time": "2:41:33", "remaining_time": "4:27:57", "throughput": 1488.78, "total_tokens": 14432096} {"current_steps": 68390, "total_steps": 181800, "loss": 0.2015, "lr": 3.925514442569679e-05, "epoch": 7.523652365236524, "percentage": 37.62, "elapsed_time": "2:41:34", "remaining_time": "4:27:56", "throughput": 1488.78, "total_tokens": 14433152} {"current_steps": 68395, "total_steps": 181800, "loss": 0.0358, "lr": 3.92531726998093e-05, "epoch": 7.524202420242024, "percentage": 37.62, "elapsed_time": "2:41:35", "remaining_time": "4:27:55", "throughput": 1488.79, "total_tokens": 14434240} {"current_steps": 68400, "total_steps": 181800, "loss": 0.0232, "lr": 3.925120084255716e-05, "epoch": 7.524752475247524, "percentage": 37.62, "elapsed_time": "2:41:35", "remaining_time": "4:27:54", "throughput": 1488.78, "total_tokens": 14435232} {"current_steps": 68405, "total_steps": 181800, "loss": 0.0118, "lr": 3.924922885395854e-05, "epoch": 7.525302530253025, "percentage": 37.63, "elapsed_time": "2:41:36", "remaining_time": "4:27:54", "throughput": 1488.78, "total_tokens": 14436256} {"current_steps": 68410, "total_steps": 181800, "loss": 0.0175, "lr": 3.924725673403161e-05, "epoch": 7.525852585258526, "percentage": 37.63, "elapsed_time": "2:41:37", "remaining_time": "4:27:53", "throughput": 1488.78, "total_tokens": 14437280} {"current_steps": 68415, "total_steps": 181800, "loss": 0.1558, "lr": 3.9245284482794555e-05, "epoch": 7.526402640264027, "percentage": 37.63, "elapsed_time": "2:41:38", "remaining_time": "4:27:52", "throughput": 1488.78, "total_tokens": 14438304} {"current_steps": 68420, "total_steps": 181800, "loss": 0.0277, "lr": 3.924331210026555e-05, "epoch": 7.526952695269527, "percentage": 37.63, "elapsed_time": "2:41:38", "remaining_time": "4:27:51", "throughput": 1488.79, "total_tokens": 14439392} {"current_steps": 68425, "total_steps": 181800, "loss": 0.0575, "lr": 3.924133958646277e-05, "epoch": 7.527502750275027, "percentage": 37.64, "elapsed_time": "2:41:39", "remaining_time": "4:27:51", "throughput": 1488.79, "total_tokens": 14440448} {"current_steps": 68430, "total_steps": 181800, "loss": 0.0146, "lr": 3.92393669414044e-05, "epoch": 7.528052805280528, "percentage": 37.64, "elapsed_time": "2:41:40", "remaining_time": "4:27:50", "throughput": 1488.79, "total_tokens": 14441472} {"current_steps": 68435, "total_steps": 181800, "loss": 0.0027, "lr": 3.923739416510862e-05, "epoch": 7.528602860286028, "percentage": 37.64, "elapsed_time": "2:41:40", "remaining_time": "4:27:49", "throughput": 1488.79, "total_tokens": 14442464} {"current_steps": 68440, "total_steps": 181800, "loss": 0.0159, "lr": 3.92354212575936e-05, "epoch": 7.5291529152915295, "percentage": 37.65, "elapsed_time": "2:41:41", "remaining_time": "4:27:49", "throughput": 1488.79, "total_tokens": 14443488} {"current_steps": 68445, "total_steps": 181800, "loss": 0.0018, "lr": 3.9233448218877536e-05, "epoch": 7.52970297029703, "percentage": 37.65, "elapsed_time": "2:41:42", "remaining_time": "4:27:48", "throughput": 1488.8, "total_tokens": 14444576} {"current_steps": 68450, "total_steps": 181800, "loss": 0.0046, "lr": 3.923147504897861e-05, "epoch": 7.53025302530253, "percentage": 37.65, "elapsed_time": "2:41:42", "remaining_time": "4:27:47", "throughput": 1488.79, "total_tokens": 14445568} {"current_steps": 68455, "total_steps": 181800, "loss": 0.0897, "lr": 3.922950174791501e-05, "epoch": 7.530803080308031, "percentage": 37.65, "elapsed_time": "2:41:43", "remaining_time": "4:27:46", "throughput": 1488.8, "total_tokens": 14446656} {"current_steps": 68460, "total_steps": 181800, "loss": 0.148, "lr": 3.922752831570492e-05, "epoch": 7.531353135313531, "percentage": 37.66, "elapsed_time": "2:41:44", "remaining_time": "4:27:46", "throughput": 1488.8, "total_tokens": 14447712} {"current_steps": 68465, "total_steps": 181800, "loss": 0.0413, "lr": 3.9225554752366526e-05, "epoch": 7.531903190319031, "percentage": 37.66, "elapsed_time": "2:41:44", "remaining_time": "4:27:45", "throughput": 1488.8, "total_tokens": 14448768} {"current_steps": 68470, "total_steps": 181800, "loss": 0.0319, "lr": 3.922358105791802e-05, "epoch": 7.5324532453245325, "percentage": 37.66, "elapsed_time": "2:41:45", "remaining_time": "4:27:44", "throughput": 1488.8, "total_tokens": 14449792} {"current_steps": 68475, "total_steps": 181800, "loss": 0.0032, "lr": 3.92216072323776e-05, "epoch": 7.533003300330033, "percentage": 37.67, "elapsed_time": "2:41:46", "remaining_time": "4:27:43", "throughput": 1488.81, "total_tokens": 14450880} {"current_steps": 68480, "total_steps": 181800, "loss": 0.0214, "lr": 3.9219633275763445e-05, "epoch": 7.533553355335534, "percentage": 37.67, "elapsed_time": "2:41:47", "remaining_time": "4:27:43", "throughput": 1488.82, "total_tokens": 14452000} {"current_steps": 68485, "total_steps": 181800, "loss": 0.0185, "lr": 3.9217659188093746e-05, "epoch": 7.534103410341034, "percentage": 37.67, "elapsed_time": "2:41:47", "remaining_time": "4:27:42", "throughput": 1488.82, "total_tokens": 14453056} {"current_steps": 68490, "total_steps": 181800, "loss": 0.033, "lr": 3.9215684969386715e-05, "epoch": 7.534653465346535, "percentage": 37.67, "elapsed_time": "2:41:48", "remaining_time": "4:27:41", "throughput": 1488.82, "total_tokens": 14454080} {"current_steps": 68495, "total_steps": 181800, "loss": 0.0798, "lr": 3.921371061966053e-05, "epoch": 7.535203520352035, "percentage": 37.68, "elapsed_time": "2:41:49", "remaining_time": "4:27:40", "throughput": 1488.82, "total_tokens": 14455072} {"current_steps": 68500, "total_steps": 181800, "loss": 0.0352, "lr": 3.9211736138933394e-05, "epoch": 7.5357535753575355, "percentage": 37.68, "elapsed_time": "2:41:49", "remaining_time": "4:27:40", "throughput": 1488.81, "total_tokens": 14456064} {"current_steps": 68505, "total_steps": 181800, "loss": 0.0996, "lr": 3.920976152722352e-05, "epoch": 7.536303630363037, "percentage": 37.68, "elapsed_time": "2:41:50", "remaining_time": "4:27:39", "throughput": 1488.82, "total_tokens": 14457120} {"current_steps": 68510, "total_steps": 181800, "loss": 0.0081, "lr": 3.920778678454908e-05, "epoch": 7.536853685368537, "percentage": 37.68, "elapsed_time": "2:41:51", "remaining_time": "4:27:38", "throughput": 1488.82, "total_tokens": 14458208} {"current_steps": 68515, "total_steps": 181800, "loss": 0.0177, "lr": 3.920581191092829e-05, "epoch": 7.537403740374037, "percentage": 37.69, "elapsed_time": "2:41:51", "remaining_time": "4:27:37", "throughput": 1488.83, "total_tokens": 14459296} {"current_steps": 68520, "total_steps": 181800, "loss": 0.0651, "lr": 3.9203836906379346e-05, "epoch": 7.537953795379538, "percentage": 37.69, "elapsed_time": "2:41:52", "remaining_time": "4:27:37", "throughput": 1488.84, "total_tokens": 14460384} {"current_steps": 68525, "total_steps": 181800, "loss": 0.0045, "lr": 3.920186177092046e-05, "epoch": 7.538503850385038, "percentage": 37.69, "elapsed_time": "2:41:53", "remaining_time": "4:27:36", "throughput": 1488.84, "total_tokens": 14461440} {"current_steps": 68530, "total_steps": 181800, "loss": 0.0233, "lr": 3.9199886504569814e-05, "epoch": 7.539053905390539, "percentage": 37.7, "elapsed_time": "2:41:53", "remaining_time": "4:27:35", "throughput": 1488.85, "total_tokens": 14462560} {"current_steps": 68535, "total_steps": 181800, "loss": 0.0288, "lr": 3.919791110734564e-05, "epoch": 7.53960396039604, "percentage": 37.7, "elapsed_time": "2:41:54", "remaining_time": "4:27:34", "throughput": 1488.85, "total_tokens": 14463616} {"current_steps": 68540, "total_steps": 181800, "loss": 0.0768, "lr": 3.9195935579266125e-05, "epoch": 7.54015401540154, "percentage": 37.7, "elapsed_time": "2:41:55", "remaining_time": "4:27:34", "throughput": 1488.85, "total_tokens": 14464640} {"current_steps": 68545, "total_steps": 181800, "loss": 0.068, "lr": 3.919395992034949e-05, "epoch": 7.540704070407041, "percentage": 37.7, "elapsed_time": "2:41:56", "remaining_time": "4:27:33", "throughput": 1488.86, "total_tokens": 14465728} {"current_steps": 68550, "total_steps": 181800, "loss": 0.0126, "lr": 3.9191984130613934e-05, "epoch": 7.541254125412541, "percentage": 37.71, "elapsed_time": "2:41:56", "remaining_time": "4:27:32", "throughput": 1488.86, "total_tokens": 14466784} {"current_steps": 68555, "total_steps": 181800, "loss": 0.0794, "lr": 3.919000821007767e-05, "epoch": 7.541804180418042, "percentage": 37.71, "elapsed_time": "2:41:57", "remaining_time": "4:27:32", "throughput": 1488.86, "total_tokens": 14467840} {"current_steps": 68560, "total_steps": 181800, "loss": 0.0672, "lr": 3.918803215875892e-05, "epoch": 7.542354235423542, "percentage": 37.71, "elapsed_time": "2:41:58", "remaining_time": "4:27:31", "throughput": 1488.87, "total_tokens": 14468992} {"current_steps": 68565, "total_steps": 181800, "loss": 0.0807, "lr": 3.9186055976675864e-05, "epoch": 7.542904290429043, "percentage": 37.71, "elapsed_time": "2:41:58", "remaining_time": "4:27:30", "throughput": 1488.87, "total_tokens": 14469984} {"current_steps": 68570, "total_steps": 181800, "loss": 0.1542, "lr": 3.918407966384675e-05, "epoch": 7.543454345434544, "percentage": 37.72, "elapsed_time": "2:41:59", "remaining_time": "4:27:29", "throughput": 1488.88, "total_tokens": 14471072} {"current_steps": 68575, "total_steps": 181800, "loss": 0.0097, "lr": 3.918210322028978e-05, "epoch": 7.544004400440044, "percentage": 37.72, "elapsed_time": "2:42:00", "remaining_time": "4:27:29", "throughput": 1488.87, "total_tokens": 14472032} {"current_steps": 68580, "total_steps": 181800, "loss": 0.0189, "lr": 3.918012664602317e-05, "epoch": 7.544554455445544, "percentage": 37.72, "elapsed_time": "2:42:00", "remaining_time": "4:27:28", "throughput": 1488.87, "total_tokens": 14473056} {"current_steps": 68585, "total_steps": 181800, "loss": 0.0456, "lr": 3.9178149941065135e-05, "epoch": 7.545104510451045, "percentage": 37.73, "elapsed_time": "2:42:01", "remaining_time": "4:27:27", "throughput": 1488.87, "total_tokens": 14474144} {"current_steps": 68590, "total_steps": 181800, "loss": 0.0538, "lr": 3.9176173105433896e-05, "epoch": 7.5456545654565454, "percentage": 37.73, "elapsed_time": "2:42:02", "remaining_time": "4:27:26", "throughput": 1488.88, "total_tokens": 14475200} {"current_steps": 68595, "total_steps": 181800, "loss": 0.0584, "lr": 3.917419613914767e-05, "epoch": 7.5462046204620465, "percentage": 37.73, "elapsed_time": "2:42:02", "remaining_time": "4:27:26", "throughput": 1488.88, "total_tokens": 14476224} {"current_steps": 68600, "total_steps": 181800, "loss": 0.1496, "lr": 3.917221904222469e-05, "epoch": 7.546754675467547, "percentage": 37.73, "elapsed_time": "2:42:03", "remaining_time": "4:27:25", "throughput": 1488.89, "total_tokens": 14477344} {"current_steps": 68605, "total_steps": 181800, "loss": 0.0105, "lr": 3.917024181468315e-05, "epoch": 7.547304730473047, "percentage": 37.74, "elapsed_time": "2:42:04", "remaining_time": "4:27:24", "throughput": 1488.89, "total_tokens": 14478400} {"current_steps": 68610, "total_steps": 181800, "loss": 0.0499, "lr": 3.91682644565413e-05, "epoch": 7.547854785478548, "percentage": 37.74, "elapsed_time": "2:42:04", "remaining_time": "4:27:23", "throughput": 1488.89, "total_tokens": 14479456} {"current_steps": 68615, "total_steps": 181800, "loss": 0.0098, "lr": 3.916628696781736e-05, "epoch": 7.548404840484048, "percentage": 37.74, "elapsed_time": "2:42:05", "remaining_time": "4:27:23", "throughput": 1488.89, "total_tokens": 14480448} {"current_steps": 68620, "total_steps": 181800, "loss": 0.0392, "lr": 3.9164309348529546e-05, "epoch": 7.548954895489549, "percentage": 37.74, "elapsed_time": "2:42:06", "remaining_time": "4:27:22", "throughput": 1488.89, "total_tokens": 14481472} {"current_steps": 68625, "total_steps": 181800, "loss": 0.0251, "lr": 3.916233159869609e-05, "epoch": 7.5495049504950495, "percentage": 37.75, "elapsed_time": "2:42:07", "remaining_time": "4:27:21", "throughput": 1488.89, "total_tokens": 14482496} {"current_steps": 68630, "total_steps": 181800, "loss": 0.0621, "lr": 3.916035371833522e-05, "epoch": 7.55005500550055, "percentage": 37.75, "elapsed_time": "2:42:07", "remaining_time": "4:27:20", "throughput": 1488.9, "total_tokens": 14483648} {"current_steps": 68635, "total_steps": 181800, "loss": 0.0289, "lr": 3.915837570746515e-05, "epoch": 7.550605060506051, "percentage": 37.75, "elapsed_time": "2:42:08", "remaining_time": "4:27:20", "throughput": 1488.91, "total_tokens": 14484736} {"current_steps": 68640, "total_steps": 181800, "loss": 0.04, "lr": 3.9156397566104145e-05, "epoch": 7.551155115511551, "percentage": 37.76, "elapsed_time": "2:42:09", "remaining_time": "4:27:19", "throughput": 1488.91, "total_tokens": 14485792} {"current_steps": 68645, "total_steps": 181800, "loss": 0.0917, "lr": 3.915441929427042e-05, "epoch": 7.551705170517051, "percentage": 37.76, "elapsed_time": "2:42:09", "remaining_time": "4:27:18", "throughput": 1488.92, "total_tokens": 14486880} {"current_steps": 68650, "total_steps": 181800, "loss": 0.0062, "lr": 3.915244089198219e-05, "epoch": 7.552255225522552, "percentage": 37.76, "elapsed_time": "2:42:10", "remaining_time": "4:27:17", "throughput": 1488.92, "total_tokens": 14487936} {"current_steps": 68655, "total_steps": 181800, "loss": 0.0332, "lr": 3.91504623592577e-05, "epoch": 7.552805280528053, "percentage": 37.76, "elapsed_time": "2:42:11", "remaining_time": "4:27:17", "throughput": 1488.92, "total_tokens": 14489024} {"current_steps": 68660, "total_steps": 181800, "loss": 0.0107, "lr": 3.91484836961152e-05, "epoch": 7.553355335533554, "percentage": 37.77, "elapsed_time": "2:42:11", "remaining_time": "4:27:16", "throughput": 1488.92, "total_tokens": 14490016} {"current_steps": 68665, "total_steps": 181800, "loss": 0.0744, "lr": 3.914650490257291e-05, "epoch": 7.553905390539054, "percentage": 37.77, "elapsed_time": "2:42:12", "remaining_time": "4:27:15", "throughput": 1488.93, "total_tokens": 14491104} {"current_steps": 68670, "total_steps": 181800, "loss": 0.0105, "lr": 3.914452597864907e-05, "epoch": 7.554455445544555, "percentage": 37.77, "elapsed_time": "2:42:13", "remaining_time": "4:27:15", "throughput": 1488.94, "total_tokens": 14492224} {"current_steps": 68675, "total_steps": 181800, "loss": 0.0185, "lr": 3.914254692436193e-05, "epoch": 7.555005500550055, "percentage": 37.78, "elapsed_time": "2:42:13", "remaining_time": "4:27:14", "throughput": 1488.94, "total_tokens": 14493248} {"current_steps": 68680, "total_steps": 181800, "loss": 0.0287, "lr": 3.9140567739729715e-05, "epoch": 7.555555555555555, "percentage": 37.78, "elapsed_time": "2:42:14", "remaining_time": "4:27:13", "throughput": 1488.94, "total_tokens": 14494336} {"current_steps": 68685, "total_steps": 181800, "loss": 0.0073, "lr": 3.913858842477067e-05, "epoch": 7.5561056105610565, "percentage": 37.78, "elapsed_time": "2:42:15", "remaining_time": "4:27:12", "throughput": 1488.94, "total_tokens": 14495360} {"current_steps": 68690, "total_steps": 181800, "loss": 0.0036, "lr": 3.913660897950304e-05, "epoch": 7.556655665566557, "percentage": 37.78, "elapsed_time": "2:42:16", "remaining_time": "4:27:12", "throughput": 1488.94, "total_tokens": 14496384} {"current_steps": 68695, "total_steps": 181800, "loss": 0.0793, "lr": 3.9134629403945075e-05, "epoch": 7.557205720572057, "percentage": 37.79, "elapsed_time": "2:42:16", "remaining_time": "4:27:11", "throughput": 1488.95, "total_tokens": 14497472} {"current_steps": 68700, "total_steps": 181800, "loss": 0.1276, "lr": 3.913264969811501e-05, "epoch": 7.557755775577558, "percentage": 37.79, "elapsed_time": "2:42:17", "remaining_time": "4:27:10", "throughput": 1488.95, "total_tokens": 14498528} {"current_steps": 68705, "total_steps": 181800, "loss": 0.0021, "lr": 3.913066986203109e-05, "epoch": 7.558305830583058, "percentage": 37.79, "elapsed_time": "2:42:18", "remaining_time": "4:27:09", "throughput": 1488.95, "total_tokens": 14499552} {"current_steps": 68710, "total_steps": 181800, "loss": 0.0282, "lr": 3.912868989571157e-05, "epoch": 7.558855885588558, "percentage": 37.79, "elapsed_time": "2:42:18", "remaining_time": "4:27:09", "throughput": 1488.95, "total_tokens": 14500576} {"current_steps": 68715, "total_steps": 181800, "loss": 0.061, "lr": 3.91267097991747e-05, "epoch": 7.5594059405940595, "percentage": 37.8, "elapsed_time": "2:42:19", "remaining_time": "4:27:08", "throughput": 1488.95, "total_tokens": 14501600} {"current_steps": 68720, "total_steps": 181800, "loss": 0.0191, "lr": 3.9124729572438724e-05, "epoch": 7.55995599559956, "percentage": 37.8, "elapsed_time": "2:42:20", "remaining_time": "4:27:07", "throughput": 1488.95, "total_tokens": 14502688} {"current_steps": 68725, "total_steps": 181800, "loss": 0.0083, "lr": 3.912274921552189e-05, "epoch": 7.560506050605061, "percentage": 37.8, "elapsed_time": "2:42:20", "remaining_time": "4:27:06", "throughput": 1488.95, "total_tokens": 14503712} {"current_steps": 68730, "total_steps": 181800, "loss": 0.0151, "lr": 3.9120768728442445e-05, "epoch": 7.561056105610561, "percentage": 37.81, "elapsed_time": "2:42:21", "remaining_time": "4:27:06", "throughput": 1488.95, "total_tokens": 14504704} {"current_steps": 68735, "total_steps": 181800, "loss": 0.0539, "lr": 3.911878811121866e-05, "epoch": 7.561606160616062, "percentage": 37.81, "elapsed_time": "2:42:22", "remaining_time": "4:27:05", "throughput": 1488.95, "total_tokens": 14505728} {"current_steps": 68740, "total_steps": 181800, "loss": 0.0096, "lr": 3.9116807363868776e-05, "epoch": 7.562156215621562, "percentage": 37.81, "elapsed_time": "2:42:22", "remaining_time": "4:27:04", "throughput": 1488.96, "total_tokens": 14506848} {"current_steps": 68745, "total_steps": 181800, "loss": 0.0021, "lr": 3.911482648641105e-05, "epoch": 7.5627062706270625, "percentage": 37.81, "elapsed_time": "2:42:23", "remaining_time": "4:27:03", "throughput": 1488.96, "total_tokens": 14507872} {"current_steps": 68750, "total_steps": 181800, "loss": 0.0892, "lr": 3.911284547886375e-05, "epoch": 7.563256325632564, "percentage": 37.82, "elapsed_time": "2:42:24", "remaining_time": "4:27:03", "throughput": 1488.95, "total_tokens": 14508864} {"current_steps": 68755, "total_steps": 181800, "loss": 0.0206, "lr": 3.911086434124512e-05, "epoch": 7.563806380638064, "percentage": 37.82, "elapsed_time": "2:42:25", "remaining_time": "4:27:02", "throughput": 1488.96, "total_tokens": 14509920} {"current_steps": 68760, "total_steps": 181800, "loss": 0.0197, "lr": 3.910888307357342e-05, "epoch": 7.564356435643564, "percentage": 37.82, "elapsed_time": "2:42:25", "remaining_time": "4:27:01", "throughput": 1488.95, "total_tokens": 14510880} {"current_steps": 68765, "total_steps": 181800, "loss": 0.005, "lr": 3.910690167586693e-05, "epoch": 7.564906490649065, "percentage": 37.82, "elapsed_time": "2:42:26", "remaining_time": "4:27:01", "throughput": 1488.95, "total_tokens": 14511904} {"current_steps": 68770, "total_steps": 181800, "loss": 0.1338, "lr": 3.910492014814388e-05, "epoch": 7.565456545654565, "percentage": 37.83, "elapsed_time": "2:42:27", "remaining_time": "4:27:00", "throughput": 1488.96, "total_tokens": 14512992} {"current_steps": 68775, "total_steps": 181800, "loss": 0.0683, "lr": 3.910293849042256e-05, "epoch": 7.566006600660066, "percentage": 37.83, "elapsed_time": "2:42:27", "remaining_time": "4:26:59", "throughput": 1488.97, "total_tokens": 14514112} {"current_steps": 68780, "total_steps": 181800, "loss": 0.0813, "lr": 3.910095670272122e-05, "epoch": 7.566556655665567, "percentage": 37.83, "elapsed_time": "2:42:28", "remaining_time": "4:26:58", "throughput": 1488.96, "total_tokens": 14515136} {"current_steps": 68785, "total_steps": 181800, "loss": 0.0632, "lr": 3.9098974785058116e-05, "epoch": 7.567106710671067, "percentage": 37.84, "elapsed_time": "2:42:29", "remaining_time": "4:26:58", "throughput": 1488.97, "total_tokens": 14516256} {"current_steps": 68790, "total_steps": 181800, "loss": 0.0648, "lr": 3.909699273745154e-05, "epoch": 7.567656765676568, "percentage": 37.84, "elapsed_time": "2:42:29", "remaining_time": "4:26:57", "throughput": 1488.97, "total_tokens": 14517280} {"current_steps": 68795, "total_steps": 181800, "loss": 0.1067, "lr": 3.9095010559919744e-05, "epoch": 7.568206820682068, "percentage": 37.84, "elapsed_time": "2:42:30", "remaining_time": "4:26:56", "throughput": 1488.97, "total_tokens": 14518272} {"current_steps": 68800, "total_steps": 181800, "loss": 0.1239, "lr": 3.9093028252481e-05, "epoch": 7.568756875687569, "percentage": 37.84, "elapsed_time": "2:42:31", "remaining_time": "4:26:55", "throughput": 1488.97, "total_tokens": 14519328} {"current_steps": 68805, "total_steps": 181800, "loss": 0.0074, "lr": 3.9091045815153573e-05, "epoch": 7.569306930693069, "percentage": 37.85, "elapsed_time": "2:42:31", "remaining_time": "4:26:55", "throughput": 1488.97, "total_tokens": 14520352} {"current_steps": 68810, "total_steps": 181800, "loss": 0.027, "lr": 3.9089063247955746e-05, "epoch": 7.56985698569857, "percentage": 37.85, "elapsed_time": "2:42:32", "remaining_time": "4:26:54", "throughput": 1488.97, "total_tokens": 14521408} {"current_steps": 68815, "total_steps": 181800, "loss": 0.0501, "lr": 3.9087080550905776e-05, "epoch": 7.570407040704071, "percentage": 37.85, "elapsed_time": "2:42:33", "remaining_time": "4:26:53", "throughput": 1488.98, "total_tokens": 14522496} {"current_steps": 68820, "total_steps": 181800, "loss": 0.0465, "lr": 3.9085097724021945e-05, "epoch": 7.570957095709571, "percentage": 37.85, "elapsed_time": "2:42:34", "remaining_time": "4:26:52", "throughput": 1488.98, "total_tokens": 14523520} {"current_steps": 68825, "total_steps": 181800, "loss": 0.095, "lr": 3.908311476732253e-05, "epoch": 7.571507150715071, "percentage": 37.86, "elapsed_time": "2:42:34", "remaining_time": "4:26:52", "throughput": 1488.98, "total_tokens": 14524576} {"current_steps": 68830, "total_steps": 181800, "loss": 0.0164, "lr": 3.90811316808258e-05, "epoch": 7.572057205720572, "percentage": 37.86, "elapsed_time": "2:42:35", "remaining_time": "4:26:51", "throughput": 1488.98, "total_tokens": 14525568} {"current_steps": 68835, "total_steps": 181800, "loss": 0.1267, "lr": 3.9079148464550044e-05, "epoch": 7.572607260726072, "percentage": 37.86, "elapsed_time": "2:42:36", "remaining_time": "4:26:50", "throughput": 1488.98, "total_tokens": 14526560} {"current_steps": 68840, "total_steps": 181800, "loss": 0.0633, "lr": 3.9077165118513526e-05, "epoch": 7.5731573157315735, "percentage": 37.87, "elapsed_time": "2:42:36", "remaining_time": "4:26:49", "throughput": 1488.98, "total_tokens": 14527648} {"current_steps": 68845, "total_steps": 181800, "loss": 0.1028, "lr": 3.907518164273453e-05, "epoch": 7.573707370737074, "percentage": 37.87, "elapsed_time": "2:42:37", "remaining_time": "4:26:49", "throughput": 1488.98, "total_tokens": 14528704} {"current_steps": 68850, "total_steps": 181800, "loss": 0.0919, "lr": 3.9073198037231345e-05, "epoch": 7.574257425742574, "percentage": 37.87, "elapsed_time": "2:42:38", "remaining_time": "4:26:48", "throughput": 1488.99, "total_tokens": 14529792} {"current_steps": 68855, "total_steps": 181800, "loss": 0.0721, "lr": 3.907121430202224e-05, "epoch": 7.574807480748075, "percentage": 37.87, "elapsed_time": "2:42:38", "remaining_time": "4:26:47", "throughput": 1488.99, "total_tokens": 14530784} {"current_steps": 68860, "total_steps": 181800, "loss": 0.0063, "lr": 3.906923043712551e-05, "epoch": 7.575357535753575, "percentage": 37.88, "elapsed_time": "2:42:39", "remaining_time": "4:26:46", "throughput": 1488.99, "total_tokens": 14531808} {"current_steps": 68865, "total_steps": 181800, "loss": 0.0211, "lr": 3.906724644255944e-05, "epoch": 7.575907590759076, "percentage": 37.88, "elapsed_time": "2:42:40", "remaining_time": "4:26:46", "throughput": 1488.99, "total_tokens": 14532864} {"current_steps": 68870, "total_steps": 181800, "loss": 0.027, "lr": 3.90652623183423e-05, "epoch": 7.5764576457645765, "percentage": 37.88, "elapsed_time": "2:42:40", "remaining_time": "4:26:45", "throughput": 1489.0, "total_tokens": 14534016} {"current_steps": 68875, "total_steps": 181800, "loss": 0.0758, "lr": 3.906327806449238e-05, "epoch": 7.577007700770077, "percentage": 37.89, "elapsed_time": "2:42:41", "remaining_time": "4:26:44", "throughput": 1489.0, "total_tokens": 14534976} {"current_steps": 68880, "total_steps": 181800, "loss": 0.01, "lr": 3.906129368102799e-05, "epoch": 7.577557755775578, "percentage": 37.89, "elapsed_time": "2:42:42", "remaining_time": "4:26:44", "throughput": 1489.0, "total_tokens": 14536032} {"current_steps": 68885, "total_steps": 181800, "loss": 0.0493, "lr": 3.90593091679674e-05, "epoch": 7.578107810781078, "percentage": 37.89, "elapsed_time": "2:42:42", "remaining_time": "4:26:43", "throughput": 1489.01, "total_tokens": 14537120} {"current_steps": 68890, "total_steps": 181800, "loss": 0.0049, "lr": 3.90573245253289e-05, "epoch": 7.578657865786578, "percentage": 37.89, "elapsed_time": "2:42:43", "remaining_time": "4:26:42", "throughput": 1489.01, "total_tokens": 14538176} {"current_steps": 68895, "total_steps": 181800, "loss": 0.0116, "lr": 3.9055339753130785e-05, "epoch": 7.579207920792079, "percentage": 37.9, "elapsed_time": "2:42:44", "remaining_time": "4:26:41", "throughput": 1489.01, "total_tokens": 14539232} {"current_steps": 68900, "total_steps": 181800, "loss": 0.0675, "lr": 3.905335485139135e-05, "epoch": 7.5797579757975795, "percentage": 37.9, "elapsed_time": "2:42:45", "remaining_time": "4:26:41", "throughput": 1489.01, "total_tokens": 14540288} {"current_steps": 68905, "total_steps": 181800, "loss": 0.0723, "lr": 3.905136982012888e-05, "epoch": 7.580308030803081, "percentage": 37.9, "elapsed_time": "2:42:45", "remaining_time": "4:26:40", "throughput": 1489.02, "total_tokens": 14541408} {"current_steps": 68910, "total_steps": 181800, "loss": 0.0255, "lr": 3.904938465936168e-05, "epoch": 7.580858085808581, "percentage": 37.9, "elapsed_time": "2:42:46", "remaining_time": "4:26:39", "throughput": 1489.03, "total_tokens": 14542464} {"current_steps": 68915, "total_steps": 181800, "loss": 0.0181, "lr": 3.904739936910805e-05, "epoch": 7.581408140814082, "percentage": 37.91, "elapsed_time": "2:42:47", "remaining_time": "4:26:38", "throughput": 1489.03, "total_tokens": 14543552} {"current_steps": 68920, "total_steps": 181800, "loss": 0.0453, "lr": 3.9045413949386274e-05, "epoch": 7.581958195819582, "percentage": 37.91, "elapsed_time": "2:42:47", "remaining_time": "4:26:38", "throughput": 1489.03, "total_tokens": 14544544} {"current_steps": 68925, "total_steps": 181800, "loss": 0.052, "lr": 3.9043428400214654e-05, "epoch": 7.582508250825082, "percentage": 37.91, "elapsed_time": "2:42:48", "remaining_time": "4:26:37", "throughput": 1489.03, "total_tokens": 14545600} {"current_steps": 68930, "total_steps": 181800, "loss": 0.0099, "lr": 3.90414427216115e-05, "epoch": 7.583058305830583, "percentage": 37.92, "elapsed_time": "2:42:49", "remaining_time": "4:26:36", "throughput": 1489.03, "total_tokens": 14546592} {"current_steps": 68935, "total_steps": 181800, "loss": 0.0662, "lr": 3.9039456913595104e-05, "epoch": 7.583608360836084, "percentage": 37.92, "elapsed_time": "2:42:49", "remaining_time": "4:26:35", "throughput": 1489.04, "total_tokens": 14547712} {"current_steps": 68940, "total_steps": 181800, "loss": 0.0567, "lr": 3.903747097618377e-05, "epoch": 7.584158415841584, "percentage": 37.92, "elapsed_time": "2:42:50", "remaining_time": "4:26:35", "throughput": 1489.04, "total_tokens": 14548768} {"current_steps": 68945, "total_steps": 181800, "loss": 0.0605, "lr": 3.90354849093958e-05, "epoch": 7.584708470847085, "percentage": 37.92, "elapsed_time": "2:42:51", "remaining_time": "4:26:34", "throughput": 1489.05, "total_tokens": 14549856} {"current_steps": 68950, "total_steps": 181800, "loss": 0.0659, "lr": 3.903349871324951e-05, "epoch": 7.585258525852585, "percentage": 37.93, "elapsed_time": "2:42:51", "remaining_time": "4:26:33", "throughput": 1489.06, "total_tokens": 14550976} {"current_steps": 68955, "total_steps": 181800, "loss": 0.0089, "lr": 3.903151238776319e-05, "epoch": 7.585808580858086, "percentage": 37.93, "elapsed_time": "2:42:52", "remaining_time": "4:26:32", "throughput": 1489.07, "total_tokens": 14552096} {"current_steps": 68960, "total_steps": 181800, "loss": 0.0133, "lr": 3.902952593295515e-05, "epoch": 7.586358635863586, "percentage": 37.93, "elapsed_time": "2:42:53", "remaining_time": "4:26:32", "throughput": 1489.07, "total_tokens": 14553152} {"current_steps": 68965, "total_steps": 181800, "loss": 0.0311, "lr": 3.90275393488437e-05, "epoch": 7.586908690869087, "percentage": 37.93, "elapsed_time": "2:42:54", "remaining_time": "4:26:31", "throughput": 1489.07, "total_tokens": 14554208} {"current_steps": 68970, "total_steps": 181800, "loss": 0.0449, "lr": 3.902555263544716e-05, "epoch": 7.587458745874588, "percentage": 37.94, "elapsed_time": "2:42:54", "remaining_time": "4:26:30", "throughput": 1489.07, "total_tokens": 14555264} {"current_steps": 68975, "total_steps": 181800, "loss": 0.0043, "lr": 3.902356579278382e-05, "epoch": 7.588008800880088, "percentage": 37.94, "elapsed_time": "2:42:55", "remaining_time": "4:26:30", "throughput": 1489.08, "total_tokens": 14556320} {"current_steps": 68980, "total_steps": 181800, "loss": 0.0252, "lr": 3.9021578820872015e-05, "epoch": 7.588558855885589, "percentage": 37.94, "elapsed_time": "2:42:56", "remaining_time": "4:26:29", "throughput": 1489.08, "total_tokens": 14557344} {"current_steps": 68985, "total_steps": 181800, "loss": 0.07, "lr": 3.9019591719730045e-05, "epoch": 7.589108910891089, "percentage": 37.95, "elapsed_time": "2:42:56", "remaining_time": "4:26:28", "throughput": 1489.08, "total_tokens": 14558400} {"current_steps": 68990, "total_steps": 181800, "loss": 0.009, "lr": 3.9017604489376214e-05, "epoch": 7.589658965896589, "percentage": 37.95, "elapsed_time": "2:42:57", "remaining_time": "4:26:27", "throughput": 1489.08, "total_tokens": 14559488} {"current_steps": 68995, "total_steps": 181800, "loss": 0.1238, "lr": 3.901561712982886e-05, "epoch": 7.5902090209020905, "percentage": 37.95, "elapsed_time": "2:42:58", "remaining_time": "4:26:27", "throughput": 1489.08, "total_tokens": 14560512} {"current_steps": 69000, "total_steps": 181800, "loss": 0.0787, "lr": 3.901362964110628e-05, "epoch": 7.590759075907591, "percentage": 37.95, "elapsed_time": "2:42:58", "remaining_time": "4:26:26", "throughput": 1489.09, "total_tokens": 14561632} {"current_steps": 69005, "total_steps": 181800, "loss": 0.058, "lr": 3.901164202322681e-05, "epoch": 7.591309130913091, "percentage": 37.96, "elapsed_time": "2:42:59", "remaining_time": "4:26:25", "throughput": 1489.09, "total_tokens": 14562592} {"current_steps": 69010, "total_steps": 181800, "loss": 0.0214, "lr": 3.900965427620875e-05, "epoch": 7.591859185918592, "percentage": 37.96, "elapsed_time": "2:43:00", "remaining_time": "4:26:24", "throughput": 1489.09, "total_tokens": 14563616} {"current_steps": 69015, "total_steps": 181800, "loss": 0.0326, "lr": 3.900766640007043e-05, "epoch": 7.592409240924092, "percentage": 37.96, "elapsed_time": "2:43:00", "remaining_time": "4:26:24", "throughput": 1489.09, "total_tokens": 14564704} {"current_steps": 69020, "total_steps": 181800, "loss": 0.0316, "lr": 3.900567839483017e-05, "epoch": 7.592959295929593, "percentage": 37.96, "elapsed_time": "2:43:01", "remaining_time": "4:26:23", "throughput": 1489.1, "total_tokens": 14565792} {"current_steps": 69025, "total_steps": 181800, "loss": 0.05, "lr": 3.90036902605063e-05, "epoch": 7.5935093509350935, "percentage": 37.97, "elapsed_time": "2:43:02", "remaining_time": "4:26:22", "throughput": 1489.1, "total_tokens": 14566816} {"current_steps": 69030, "total_steps": 181800, "loss": 0.0095, "lr": 3.9001701997117135e-05, "epoch": 7.594059405940594, "percentage": 37.97, "elapsed_time": "2:43:02", "remaining_time": "4:26:21", "throughput": 1489.11, "total_tokens": 14567904} {"current_steps": 69035, "total_steps": 181800, "loss": 0.0039, "lr": 3.8999713604681e-05, "epoch": 7.594609460946095, "percentage": 37.97, "elapsed_time": "2:43:03", "remaining_time": "4:26:21", "throughput": 1489.11, "total_tokens": 14568960} {"current_steps": 69040, "total_steps": 181800, "loss": 0.0154, "lr": 3.899772508321622e-05, "epoch": 7.595159515951595, "percentage": 37.98, "elapsed_time": "2:43:04", "remaining_time": "4:26:20", "throughput": 1489.12, "total_tokens": 14570080} {"current_steps": 69045, "total_steps": 181800, "loss": 0.0197, "lr": 3.899573643274112e-05, "epoch": 7.595709570957096, "percentage": 37.98, "elapsed_time": "2:43:05", "remaining_time": "4:26:19", "throughput": 1489.12, "total_tokens": 14571136} {"current_steps": 69050, "total_steps": 181800, "loss": 0.0079, "lr": 3.899374765327404e-05, "epoch": 7.596259625962596, "percentage": 37.98, "elapsed_time": "2:43:05", "remaining_time": "4:26:18", "throughput": 1489.12, "total_tokens": 14572160} {"current_steps": 69055, "total_steps": 181800, "loss": 0.0195, "lr": 3.89917587448333e-05, "epoch": 7.5968096809680965, "percentage": 37.98, "elapsed_time": "2:43:06", "remaining_time": "4:26:18", "throughput": 1489.12, "total_tokens": 14573216} {"current_steps": 69060, "total_steps": 181800, "loss": 0.1369, "lr": 3.8989769707437234e-05, "epoch": 7.597359735973598, "percentage": 37.99, "elapsed_time": "2:43:07", "remaining_time": "4:26:17", "throughput": 1489.13, "total_tokens": 14574272} {"current_steps": 69065, "total_steps": 181800, "loss": 0.011, "lr": 3.8987780541104174e-05, "epoch": 7.597909790979098, "percentage": 37.99, "elapsed_time": "2:43:07", "remaining_time": "4:26:16", "throughput": 1489.12, "total_tokens": 14575296} {"current_steps": 69070, "total_steps": 181800, "loss": 0.0238, "lr": 3.8985791245852455e-05, "epoch": 7.598459845984598, "percentage": 37.99, "elapsed_time": "2:43:08", "remaining_time": "4:26:15", "throughput": 1489.12, "total_tokens": 14576288} {"current_steps": 69075, "total_steps": 181800, "loss": 0.0127, "lr": 3.898380182170041e-05, "epoch": 7.599009900990099, "percentage": 38.0, "elapsed_time": "2:43:09", "remaining_time": "4:26:15", "throughput": 1489.12, "total_tokens": 14577344} {"current_steps": 69080, "total_steps": 181800, "loss": 0.0663, "lr": 3.898181226866637e-05, "epoch": 7.599559955995599, "percentage": 38.0, "elapsed_time": "2:43:09", "remaining_time": "4:26:14", "throughput": 1489.12, "total_tokens": 14578368} {"current_steps": 69085, "total_steps": 181800, "loss": 0.0126, "lr": 3.897982258676867e-05, "epoch": 7.6001100110011, "percentage": 38.0, "elapsed_time": "2:43:10", "remaining_time": "4:26:13", "throughput": 1489.12, "total_tokens": 14579392} {"current_steps": 69090, "total_steps": 181800, "loss": 0.0128, "lr": 3.8977832776025666e-05, "epoch": 7.600660066006601, "percentage": 38.0, "elapsed_time": "2:43:11", "remaining_time": "4:26:13", "throughput": 1489.13, "total_tokens": 14580480} {"current_steps": 69095, "total_steps": 181800, "loss": 0.0347, "lr": 3.8975842836455676e-05, "epoch": 7.601210121012102, "percentage": 38.01, "elapsed_time": "2:43:11", "remaining_time": "4:26:12", "throughput": 1489.13, "total_tokens": 14581568} {"current_steps": 69100, "total_steps": 181800, "loss": 0.0066, "lr": 3.8973852768077054e-05, "epoch": 7.601760176017602, "percentage": 38.01, "elapsed_time": "2:43:12", "remaining_time": "4:26:11", "throughput": 1489.13, "total_tokens": 14582560} {"current_steps": 69105, "total_steps": 181800, "loss": 0.048, "lr": 3.897186257090813e-05, "epoch": 7.602310231023102, "percentage": 38.01, "elapsed_time": "2:43:13", "remaining_time": "4:26:10", "throughput": 1489.13, "total_tokens": 14583616} {"current_steps": 69110, "total_steps": 181800, "loss": 0.0331, "lr": 3.896987224496725e-05, "epoch": 7.602860286028603, "percentage": 38.01, "elapsed_time": "2:43:14", "remaining_time": "4:26:10", "throughput": 1489.14, "total_tokens": 14584672} {"current_steps": 69115, "total_steps": 181800, "loss": 0.009, "lr": 3.896788179027277e-05, "epoch": 7.603410341034103, "percentage": 38.02, "elapsed_time": "2:43:14", "remaining_time": "4:26:09", "throughput": 1489.13, "total_tokens": 14585664} {"current_steps": 69120, "total_steps": 181800, "loss": 0.0335, "lr": 3.896589120684303e-05, "epoch": 7.603960396039604, "percentage": 38.02, "elapsed_time": "2:43:15", "remaining_time": "4:26:08", "throughput": 1489.14, "total_tokens": 14586784} {"current_steps": 69125, "total_steps": 181800, "loss": 0.106, "lr": 3.896390049469636e-05, "epoch": 7.604510451045105, "percentage": 38.02, "elapsed_time": "2:43:16", "remaining_time": "4:26:07", "throughput": 1489.14, "total_tokens": 14587808} {"current_steps": 69130, "total_steps": 181800, "loss": 0.0108, "lr": 3.896190965385113e-05, "epoch": 7.605060506050605, "percentage": 38.03, "elapsed_time": "2:43:16", "remaining_time": "4:26:07", "throughput": 1489.14, "total_tokens": 14588864} {"current_steps": 69135, "total_steps": 181800, "loss": 0.0225, "lr": 3.895991868432567e-05, "epoch": 7.605610561056105, "percentage": 38.03, "elapsed_time": "2:43:17", "remaining_time": "4:26:06", "throughput": 1489.15, "total_tokens": 14589984} {"current_steps": 69140, "total_steps": 181800, "loss": 0.0849, "lr": 3.8957927586138345e-05, "epoch": 7.606160616061606, "percentage": 38.03, "elapsed_time": "2:43:18", "remaining_time": "4:26:05", "throughput": 1489.15, "total_tokens": 14590976} {"current_steps": 69145, "total_steps": 181800, "loss": 0.0056, "lr": 3.8955936359307496e-05, "epoch": 7.606710671067106, "percentage": 38.03, "elapsed_time": "2:43:18", "remaining_time": "4:26:04", "throughput": 1489.15, "total_tokens": 14592032} {"current_steps": 69150, "total_steps": 181800, "loss": 0.0809, "lr": 3.8953945003851475e-05, "epoch": 7.6072607260726075, "percentage": 38.04, "elapsed_time": "2:43:19", "remaining_time": "4:26:04", "throughput": 1489.15, "total_tokens": 14593088} {"current_steps": 69155, "total_steps": 181800, "loss": 0.0146, "lr": 3.895195351978864e-05, "epoch": 7.607810781078108, "percentage": 38.04, "elapsed_time": "2:43:20", "remaining_time": "4:26:03", "throughput": 1489.16, "total_tokens": 14594144} {"current_steps": 69160, "total_steps": 181800, "loss": 0.0066, "lr": 3.8949961907137346e-05, "epoch": 7.608360836083609, "percentage": 38.04, "elapsed_time": "2:43:20", "remaining_time": "4:26:02", "throughput": 1489.16, "total_tokens": 14595232} {"current_steps": 69165, "total_steps": 181800, "loss": 0.0172, "lr": 3.8947970165915945e-05, "epoch": 7.608910891089109, "percentage": 38.04, "elapsed_time": "2:43:21", "remaining_time": "4:26:01", "throughput": 1489.16, "total_tokens": 14596256} {"current_steps": 69170, "total_steps": 181800, "loss": 0.1164, "lr": 3.89459782961428e-05, "epoch": 7.609460946094609, "percentage": 38.05, "elapsed_time": "2:43:22", "remaining_time": "4:26:01", "throughput": 1489.16, "total_tokens": 14597280} {"current_steps": 69175, "total_steps": 181800, "loss": 0.0265, "lr": 3.8943986297836266e-05, "epoch": 7.61001100110011, "percentage": 38.05, "elapsed_time": "2:43:23", "remaining_time": "4:26:00", "throughput": 1489.16, "total_tokens": 14598304} {"current_steps": 69180, "total_steps": 181800, "loss": 0.0288, "lr": 3.8941994171014696e-05, "epoch": 7.6105610561056105, "percentage": 38.05, "elapsed_time": "2:43:23", "remaining_time": "4:25:59", "throughput": 1489.17, "total_tokens": 14599424} {"current_steps": 69185, "total_steps": 181800, "loss": 0.0437, "lr": 3.894000191569645e-05, "epoch": 7.611111111111111, "percentage": 38.06, "elapsed_time": "2:43:24", "remaining_time": "4:25:59", "throughput": 1489.17, "total_tokens": 14600448} {"current_steps": 69190, "total_steps": 181800, "loss": 0.0081, "lr": 3.893800953189991e-05, "epoch": 7.611661166116612, "percentage": 38.06, "elapsed_time": "2:43:25", "remaining_time": "4:25:58", "throughput": 1489.17, "total_tokens": 14601536} {"current_steps": 69195, "total_steps": 181800, "loss": 0.012, "lr": 3.893601701964342e-05, "epoch": 7.612211221122112, "percentage": 38.06, "elapsed_time": "2:43:25", "remaining_time": "4:25:57", "throughput": 1489.18, "total_tokens": 14602656} {"current_steps": 69200, "total_steps": 181800, "loss": 0.0152, "lr": 3.8934024378945345e-05, "epoch": 7.612761276127613, "percentage": 38.06, "elapsed_time": "2:43:26", "remaining_time": "4:25:56", "throughput": 1489.18, "total_tokens": 14603648} {"current_steps": 69205, "total_steps": 181800, "loss": 0.0478, "lr": 3.893203160982405e-05, "epoch": 7.613311331133113, "percentage": 38.07, "elapsed_time": "2:43:27", "remaining_time": "4:25:56", "throughput": 1489.19, "total_tokens": 14604736} {"current_steps": 69210, "total_steps": 181800, "loss": 0.0801, "lr": 3.893003871229791e-05, "epoch": 7.6138613861386135, "percentage": 38.07, "elapsed_time": "2:43:27", "remaining_time": "4:25:55", "throughput": 1489.2, "total_tokens": 14605856} {"current_steps": 69215, "total_steps": 181800, "loss": 0.0347, "lr": 3.892804568638528e-05, "epoch": 7.614411441144115, "percentage": 38.07, "elapsed_time": "2:43:28", "remaining_time": "4:25:54", "throughput": 1489.2, "total_tokens": 14606880} {"current_steps": 69220, "total_steps": 181800, "loss": 0.0973, "lr": 3.8926052532104554e-05, "epoch": 7.614961496149615, "percentage": 38.07, "elapsed_time": "2:43:29", "remaining_time": "4:25:53", "throughput": 1489.2, "total_tokens": 14607936} {"current_steps": 69225, "total_steps": 181800, "loss": 0.0239, "lr": 3.892405924947406e-05, "epoch": 7.615511551155116, "percentage": 38.08, "elapsed_time": "2:43:29", "remaining_time": "4:25:53", "throughput": 1489.2, "total_tokens": 14608960} {"current_steps": 69230, "total_steps": 181800, "loss": 0.0402, "lr": 3.892206583851221e-05, "epoch": 7.616061606160616, "percentage": 38.08, "elapsed_time": "2:43:30", "remaining_time": "4:25:52", "throughput": 1489.19, "total_tokens": 14609952} {"current_steps": 69235, "total_steps": 181800, "loss": 0.0141, "lr": 3.892007229923736e-05, "epoch": 7.616611661166116, "percentage": 38.08, "elapsed_time": "2:43:31", "remaining_time": "4:25:51", "throughput": 1489.2, "total_tokens": 14611008} {"current_steps": 69240, "total_steps": 181800, "loss": 0.0367, "lr": 3.891807863166788e-05, "epoch": 7.617161716171617, "percentage": 38.09, "elapsed_time": "2:43:32", "remaining_time": "4:25:50", "throughput": 1489.2, "total_tokens": 14612032} {"current_steps": 69245, "total_steps": 181800, "loss": 0.0351, "lr": 3.891608483582214e-05, "epoch": 7.617711771177118, "percentage": 38.09, "elapsed_time": "2:43:32", "remaining_time": "4:25:50", "throughput": 1489.2, "total_tokens": 14613056} {"current_steps": 69250, "total_steps": 181800, "loss": 0.0082, "lr": 3.8914090911718536e-05, "epoch": 7.618261826182618, "percentage": 38.09, "elapsed_time": "2:43:33", "remaining_time": "4:25:49", "throughput": 1489.2, "total_tokens": 14614144} {"current_steps": 69255, "total_steps": 181800, "loss": 0.1115, "lr": 3.891209685937542e-05, "epoch": 7.618811881188119, "percentage": 38.09, "elapsed_time": "2:43:34", "remaining_time": "4:25:48", "throughput": 1489.2, "total_tokens": 14615136} {"current_steps": 69260, "total_steps": 181800, "loss": 0.0048, "lr": 3.891010267881119e-05, "epoch": 7.619361936193619, "percentage": 38.1, "elapsed_time": "2:43:34", "remaining_time": "4:25:47", "throughput": 1489.19, "total_tokens": 14616128} {"current_steps": 69265, "total_steps": 181800, "loss": 0.0263, "lr": 3.890810837004423e-05, "epoch": 7.61991199119912, "percentage": 38.1, "elapsed_time": "2:43:35", "remaining_time": "4:25:47", "throughput": 1489.19, "total_tokens": 14617120} {"current_steps": 69270, "total_steps": 181800, "loss": 0.0108, "lr": 3.890611393309289e-05, "epoch": 7.62046204620462, "percentage": 38.1, "elapsed_time": "2:43:36", "remaining_time": "4:25:46", "throughput": 1489.2, "total_tokens": 14618208} {"current_steps": 69275, "total_steps": 181800, "loss": 0.1826, "lr": 3.890411936797558e-05, "epoch": 7.621012101210121, "percentage": 38.11, "elapsed_time": "2:43:36", "remaining_time": "4:25:45", "throughput": 1489.19, "total_tokens": 14619168} {"current_steps": 69280, "total_steps": 181800, "loss": 0.0107, "lr": 3.8902124674710674e-05, "epoch": 7.621562156215622, "percentage": 38.11, "elapsed_time": "2:43:37", "remaining_time": "4:25:45", "throughput": 1489.2, "total_tokens": 14620256} {"current_steps": 69285, "total_steps": 181800, "loss": 0.0063, "lr": 3.890012985331655e-05, "epoch": 7.622112211221122, "percentage": 38.11, "elapsed_time": "2:43:38", "remaining_time": "4:25:44", "throughput": 1489.2, "total_tokens": 14621312} {"current_steps": 69290, "total_steps": 181800, "loss": 0.0053, "lr": 3.88981349038116e-05, "epoch": 7.622662266226623, "percentage": 38.11, "elapsed_time": "2:43:38", "remaining_time": "4:25:43", "throughput": 1489.2, "total_tokens": 14622368} {"current_steps": 69295, "total_steps": 181800, "loss": 0.0504, "lr": 3.8896139826214214e-05, "epoch": 7.623212321232123, "percentage": 38.12, "elapsed_time": "2:43:39", "remaining_time": "4:25:42", "throughput": 1489.21, "total_tokens": 14623424} {"current_steps": 69300, "total_steps": 181800, "loss": 0.0058, "lr": 3.889414462054277e-05, "epoch": 7.623762376237623, "percentage": 38.12, "elapsed_time": "2:43:40", "remaining_time": "4:25:42", "throughput": 1489.2, "total_tokens": 14624416} {"current_steps": 69305, "total_steps": 181800, "loss": 0.026, "lr": 3.889214928681566e-05, "epoch": 7.6243124312431245, "percentage": 38.12, "elapsed_time": "2:43:40", "remaining_time": "4:25:41", "throughput": 1489.21, "total_tokens": 14625504} {"current_steps": 69310, "total_steps": 181800, "loss": 0.0504, "lr": 3.889015382505129e-05, "epoch": 7.624862486248625, "percentage": 38.12, "elapsed_time": "2:43:41", "remaining_time": "4:25:40", "throughput": 1489.22, "total_tokens": 14626624} {"current_steps": 69315, "total_steps": 181800, "loss": 0.0033, "lr": 3.888815823526803e-05, "epoch": 7.625412541254125, "percentage": 38.13, "elapsed_time": "2:43:42", "remaining_time": "4:25:39", "throughput": 1489.22, "total_tokens": 14627680} {"current_steps": 69320, "total_steps": 181800, "loss": 0.0351, "lr": 3.888616251748428e-05, "epoch": 7.625962596259626, "percentage": 38.13, "elapsed_time": "2:43:43", "remaining_time": "4:25:39", "throughput": 1489.22, "total_tokens": 14628672} {"current_steps": 69325, "total_steps": 181800, "loss": 0.0337, "lr": 3.888416667171843e-05, "epoch": 7.626512651265126, "percentage": 38.13, "elapsed_time": "2:43:43", "remaining_time": "4:25:38", "throughput": 1489.22, "total_tokens": 14629696} {"current_steps": 69330, "total_steps": 181800, "loss": 0.0189, "lr": 3.888217069798887e-05, "epoch": 7.627062706270627, "percentage": 38.14, "elapsed_time": "2:43:44", "remaining_time": "4:25:37", "throughput": 1489.21, "total_tokens": 14630688} {"current_steps": 69335, "total_steps": 181800, "loss": 0.062, "lr": 3.8880174596314024e-05, "epoch": 7.6276127612761275, "percentage": 38.14, "elapsed_time": "2:43:45", "remaining_time": "4:25:36", "throughput": 1489.21, "total_tokens": 14631680} {"current_steps": 69340, "total_steps": 181800, "loss": 0.2388, "lr": 3.887817836671226e-05, "epoch": 7.628162816281629, "percentage": 38.14, "elapsed_time": "2:43:45", "remaining_time": "4:25:36", "throughput": 1489.21, "total_tokens": 14632768} {"current_steps": 69345, "total_steps": 181800, "loss": 0.1484, "lr": 3.887618200920198e-05, "epoch": 7.628712871287129, "percentage": 38.14, "elapsed_time": "2:43:46", "remaining_time": "4:25:35", "throughput": 1489.22, "total_tokens": 14633856} {"current_steps": 69350, "total_steps": 181800, "loss": 0.0337, "lr": 3.887418552380159e-05, "epoch": 7.629262926292629, "percentage": 38.15, "elapsed_time": "2:43:47", "remaining_time": "4:25:34", "throughput": 1489.22, "total_tokens": 14634880} {"current_steps": 69355, "total_steps": 181800, "loss": 0.0666, "lr": 3.8872188910529496e-05, "epoch": 7.62981298129813, "percentage": 38.15, "elapsed_time": "2:43:47", "remaining_time": "4:25:33", "throughput": 1489.23, "total_tokens": 14635968} {"current_steps": 69360, "total_steps": 181800, "loss": 0.0149, "lr": 3.887019216940409e-05, "epoch": 7.63036303630363, "percentage": 38.15, "elapsed_time": "2:43:48", "remaining_time": "4:25:33", "throughput": 1489.23, "total_tokens": 14636992} {"current_steps": 69365, "total_steps": 181800, "loss": 0.0111, "lr": 3.886819530044378e-05, "epoch": 7.6309130913091305, "percentage": 38.15, "elapsed_time": "2:43:49", "remaining_time": "4:25:32", "throughput": 1489.23, "total_tokens": 14638080} {"current_steps": 69370, "total_steps": 181800, "loss": 0.0314, "lr": 3.886619830366697e-05, "epoch": 7.631463146314632, "percentage": 38.16, "elapsed_time": "2:43:49", "remaining_time": "4:25:31", "throughput": 1489.23, "total_tokens": 14639104} {"current_steps": 69375, "total_steps": 181800, "loss": 0.0135, "lr": 3.8864201179092055e-05, "epoch": 7.632013201320132, "percentage": 38.16, "elapsed_time": "2:43:50", "remaining_time": "4:25:30", "throughput": 1489.23, "total_tokens": 14640128} {"current_steps": 69380, "total_steps": 181800, "loss": 0.0471, "lr": 3.8862203926737464e-05, "epoch": 7.632563256325633, "percentage": 38.16, "elapsed_time": "2:43:51", "remaining_time": "4:25:30", "throughput": 1489.23, "total_tokens": 14641152} {"current_steps": 69385, "total_steps": 181800, "loss": 0.0307, "lr": 3.886020654662158e-05, "epoch": 7.633113311331133, "percentage": 38.17, "elapsed_time": "2:43:52", "remaining_time": "4:25:29", "throughput": 1489.24, "total_tokens": 14642240} {"current_steps": 69390, "total_steps": 181800, "loss": 0.0063, "lr": 3.885820903876282e-05, "epoch": 7.633663366336633, "percentage": 38.17, "elapsed_time": "2:43:52", "remaining_time": "4:25:28", "throughput": 1489.24, "total_tokens": 14643264} {"current_steps": 69395, "total_steps": 181800, "loss": 0.0403, "lr": 3.885621140317961e-05, "epoch": 7.634213421342134, "percentage": 38.17, "elapsed_time": "2:43:53", "remaining_time": "4:25:28", "throughput": 1489.24, "total_tokens": 14644288} {"current_steps": 69400, "total_steps": 181800, "loss": 0.0243, "lr": 3.8854213639890336e-05, "epoch": 7.634763476347635, "percentage": 38.17, "elapsed_time": "2:43:54", "remaining_time": "4:25:27", "throughput": 1489.24, "total_tokens": 14645344} {"current_steps": 69405, "total_steps": 181800, "loss": 0.0082, "lr": 3.885221574891343e-05, "epoch": 7.635313531353136, "percentage": 38.18, "elapsed_time": "2:43:54", "remaining_time": "4:25:26", "throughput": 1489.25, "total_tokens": 14646432} {"current_steps": 69410, "total_steps": 181800, "loss": 0.0028, "lr": 3.8850217730267297e-05, "epoch": 7.635863586358636, "percentage": 38.18, "elapsed_time": "2:43:55", "remaining_time": "4:25:25", "throughput": 1489.25, "total_tokens": 14647520} {"current_steps": 69415, "total_steps": 181800, "loss": 0.0915, "lr": 3.8848219583970356e-05, "epoch": 7.636413641364136, "percentage": 38.18, "elapsed_time": "2:43:56", "remaining_time": "4:25:25", "throughput": 1489.25, "total_tokens": 14648512} {"current_steps": 69420, "total_steps": 181800, "loss": 0.0189, "lr": 3.8846221310041006e-05, "epoch": 7.636963696369637, "percentage": 38.18, "elapsed_time": "2:43:56", "remaining_time": "4:25:24", "throughput": 1489.25, "total_tokens": 14649536} {"current_steps": 69425, "total_steps": 181800, "loss": 0.0049, "lr": 3.884422290849769e-05, "epoch": 7.637513751375137, "percentage": 38.19, "elapsed_time": "2:43:57", "remaining_time": "4:25:23", "throughput": 1489.25, "total_tokens": 14650592} {"current_steps": 69430, "total_steps": 181800, "loss": 0.0854, "lr": 3.884222437935883e-05, "epoch": 7.638063806380638, "percentage": 38.19, "elapsed_time": "2:43:58", "remaining_time": "4:25:22", "throughput": 1489.26, "total_tokens": 14651680} {"current_steps": 69435, "total_steps": 181800, "loss": 0.0092, "lr": 3.884022572264281e-05, "epoch": 7.638613861386139, "percentage": 38.19, "elapsed_time": "2:43:58", "remaining_time": "4:25:22", "throughput": 1489.26, "total_tokens": 14652768} {"current_steps": 69440, "total_steps": 181800, "loss": 0.0255, "lr": 3.883822693836807e-05, "epoch": 7.639163916391639, "percentage": 38.2, "elapsed_time": "2:43:59", "remaining_time": "4:25:21", "throughput": 1489.26, "total_tokens": 14653760} {"current_steps": 69445, "total_steps": 181800, "loss": 0.054, "lr": 3.8836228026553035e-05, "epoch": 7.63971397139714, "percentage": 38.2, "elapsed_time": "2:44:00", "remaining_time": "4:25:20", "throughput": 1489.26, "total_tokens": 14654848} {"current_steps": 69450, "total_steps": 181800, "loss": 0.0267, "lr": 3.8834228987216126e-05, "epoch": 7.64026402640264, "percentage": 38.2, "elapsed_time": "2:44:01", "remaining_time": "4:25:19", "throughput": 1489.27, "total_tokens": 14655904} {"current_steps": 69455, "total_steps": 181800, "loss": 0.0155, "lr": 3.8832229820375773e-05, "epoch": 7.6408140814081404, "percentage": 38.2, "elapsed_time": "2:44:01", "remaining_time": "4:25:19", "throughput": 1489.27, "total_tokens": 14656928} {"current_steps": 69460, "total_steps": 181800, "loss": 0.1128, "lr": 3.883023052605039e-05, "epoch": 7.6413641364136415, "percentage": 38.21, "elapsed_time": "2:44:02", "remaining_time": "4:25:18", "throughput": 1489.27, "total_tokens": 14657952} {"current_steps": 69465, "total_steps": 181800, "loss": 0.1362, "lr": 3.8828231104258406e-05, "epoch": 7.641914191419142, "percentage": 38.21, "elapsed_time": "2:44:03", "remaining_time": "4:25:17", "throughput": 1489.28, "total_tokens": 14659072} {"current_steps": 69470, "total_steps": 181800, "loss": 0.1024, "lr": 3.882623155501825e-05, "epoch": 7.642464246424643, "percentage": 38.21, "elapsed_time": "2:44:03", "remaining_time": "4:25:16", "throughput": 1489.28, "total_tokens": 14660160} {"current_steps": 69475, "total_steps": 181800, "loss": 0.0149, "lr": 3.882423187834836e-05, "epoch": 7.643014301430143, "percentage": 38.22, "elapsed_time": "2:44:04", "remaining_time": "4:25:16", "throughput": 1489.28, "total_tokens": 14661184} {"current_steps": 69480, "total_steps": 181800, "loss": 0.0168, "lr": 3.882223207426716e-05, "epoch": 7.643564356435643, "percentage": 38.22, "elapsed_time": "2:44:05", "remaining_time": "4:25:15", "throughput": 1489.28, "total_tokens": 14662208} {"current_steps": 69485, "total_steps": 181800, "loss": 0.0149, "lr": 3.882023214279308e-05, "epoch": 7.644114411441144, "percentage": 38.22, "elapsed_time": "2:44:05", "remaining_time": "4:25:14", "throughput": 1489.28, "total_tokens": 14663264} {"current_steps": 69490, "total_steps": 181800, "loss": 0.0442, "lr": 3.881823208394454e-05, "epoch": 7.6446644664466445, "percentage": 38.22, "elapsed_time": "2:44:06", "remaining_time": "4:25:13", "throughput": 1489.29, "total_tokens": 14664384} {"current_steps": 69495, "total_steps": 181800, "loss": 0.0139, "lr": 3.881623189774e-05, "epoch": 7.645214521452145, "percentage": 38.23, "elapsed_time": "2:44:07", "remaining_time": "4:25:13", "throughput": 1489.31, "total_tokens": 14665536} {"current_steps": 69500, "total_steps": 181800, "loss": 0.0165, "lr": 3.881423158419787e-05, "epoch": 7.645764576457646, "percentage": 38.23, "elapsed_time": "2:44:07", "remaining_time": "4:25:12", "throughput": 1489.31, "total_tokens": 14666560} {"current_steps": 69505, "total_steps": 181800, "loss": 0.0514, "lr": 3.8812231143336595e-05, "epoch": 7.646314631463146, "percentage": 38.23, "elapsed_time": "2:44:08", "remaining_time": "4:25:11", "throughput": 1489.32, "total_tokens": 14667680} {"current_steps": 69510, "total_steps": 181800, "loss": 0.0618, "lr": 3.881023057517462e-05, "epoch": 7.646864686468647, "percentage": 38.23, "elapsed_time": "2:44:09", "remaining_time": "4:25:11", "throughput": 1489.32, "total_tokens": 14668704} {"current_steps": 69515, "total_steps": 181800, "loss": 0.1277, "lr": 3.880822987973037e-05, "epoch": 7.647414741474147, "percentage": 38.24, "elapsed_time": "2:44:09", "remaining_time": "4:25:10", "throughput": 1489.32, "total_tokens": 14669728} {"current_steps": 69520, "total_steps": 181800, "loss": 0.0228, "lr": 3.880622905702229e-05, "epoch": 7.647964796479648, "percentage": 38.24, "elapsed_time": "2:44:10", "remaining_time": "4:25:09", "throughput": 1489.32, "total_tokens": 14670784} {"current_steps": 69525, "total_steps": 181800, "loss": 0.0052, "lr": 3.880422810706883e-05, "epoch": 7.648514851485149, "percentage": 38.24, "elapsed_time": "2:44:11", "remaining_time": "4:25:08", "throughput": 1489.32, "total_tokens": 14671840} {"current_steps": 69530, "total_steps": 181800, "loss": 0.0081, "lr": 3.8802227029888425e-05, "epoch": 7.649064906490649, "percentage": 38.25, "elapsed_time": "2:44:12", "remaining_time": "4:25:08", "throughput": 1489.32, "total_tokens": 14672864} {"current_steps": 69535, "total_steps": 181800, "loss": 0.0996, "lr": 3.88002258254995e-05, "epoch": 7.64961496149615, "percentage": 38.25, "elapsed_time": "2:44:12", "remaining_time": "4:25:07", "throughput": 1489.33, "total_tokens": 14673952} {"current_steps": 69540, "total_steps": 181800, "loss": 0.02, "lr": 3.8798224493920534e-05, "epoch": 7.65016501650165, "percentage": 38.25, "elapsed_time": "2:44:13", "remaining_time": "4:25:06", "throughput": 1489.33, "total_tokens": 14675008} {"current_steps": 69545, "total_steps": 181800, "loss": 0.0041, "lr": 3.879622303516994e-05, "epoch": 7.65071507150715, "percentage": 38.25, "elapsed_time": "2:44:14", "remaining_time": "4:25:05", "throughput": 1489.34, "total_tokens": 14676160} {"current_steps": 69550, "total_steps": 181800, "loss": 0.0593, "lr": 3.8794221449266187e-05, "epoch": 7.6512651265126514, "percentage": 38.26, "elapsed_time": "2:44:14", "remaining_time": "4:25:05", "throughput": 1489.35, "total_tokens": 14677248} {"current_steps": 69555, "total_steps": 181800, "loss": 0.0142, "lr": 3.879221973622772e-05, "epoch": 7.651815181518152, "percentage": 38.26, "elapsed_time": "2:44:15", "remaining_time": "4:25:04", "throughput": 1489.35, "total_tokens": 14678336} {"current_steps": 69560, "total_steps": 181800, "loss": 0.0217, "lr": 3.879021789607297e-05, "epoch": 7.652365236523653, "percentage": 38.26, "elapsed_time": "2:44:16", "remaining_time": "4:25:03", "throughput": 1489.36, "total_tokens": 14679456} {"current_steps": 69565, "total_steps": 181800, "loss": 0.008, "lr": 3.87882159288204e-05, "epoch": 7.652915291529153, "percentage": 38.26, "elapsed_time": "2:44:16", "remaining_time": "4:25:02", "throughput": 1489.36, "total_tokens": 14680512} {"current_steps": 69570, "total_steps": 181800, "loss": 0.0093, "lr": 3.878621383448846e-05, "epoch": 7.653465346534653, "percentage": 38.27, "elapsed_time": "2:44:17", "remaining_time": "4:25:02", "throughput": 1489.36, "total_tokens": 14681472} {"current_steps": 69575, "total_steps": 181800, "loss": 0.0532, "lr": 3.878421161309561e-05, "epoch": 7.654015401540154, "percentage": 38.27, "elapsed_time": "2:44:18", "remaining_time": "4:25:01", "throughput": 1489.36, "total_tokens": 14682528} {"current_steps": 69580, "total_steps": 181800, "loss": 0.0176, "lr": 3.878220926466028e-05, "epoch": 7.6545654565456545, "percentage": 38.27, "elapsed_time": "2:44:18", "remaining_time": "4:25:00", "throughput": 1489.36, "total_tokens": 14683584} {"current_steps": 69585, "total_steps": 181800, "loss": 0.0214, "lr": 3.8780206789200954e-05, "epoch": 7.6551155115511555, "percentage": 38.28, "elapsed_time": "2:44:19", "remaining_time": "4:25:00", "throughput": 1489.36, "total_tokens": 14684640} {"current_steps": 69590, "total_steps": 181800, "loss": 0.0043, "lr": 3.8778204186736076e-05, "epoch": 7.655665566556656, "percentage": 38.28, "elapsed_time": "2:44:20", "remaining_time": "4:24:59", "throughput": 1489.36, "total_tokens": 14685664} {"current_steps": 69595, "total_steps": 181800, "loss": 0.0331, "lr": 3.87762014572841e-05, "epoch": 7.656215621562156, "percentage": 38.28, "elapsed_time": "2:44:21", "remaining_time": "4:24:58", "throughput": 1489.36, "total_tokens": 14686688} {"current_steps": 69600, "total_steps": 181800, "loss": 0.0391, "lr": 3.877419860086348e-05, "epoch": 7.656765676567657, "percentage": 38.28, "elapsed_time": "2:44:21", "remaining_time": "4:24:57", "throughput": 1489.37, "total_tokens": 14687776} {"current_steps": 69605, "total_steps": 181800, "loss": 0.0578, "lr": 3.877219561749269e-05, "epoch": 7.657315731573157, "percentage": 38.29, "elapsed_time": "2:44:22", "remaining_time": "4:24:57", "throughput": 1489.38, "total_tokens": 14688864} {"current_steps": 69610, "total_steps": 181800, "loss": 0.0556, "lr": 3.877019250719017e-05, "epoch": 7.6578657865786575, "percentage": 38.29, "elapsed_time": "2:44:23", "remaining_time": "4:24:56", "throughput": 1489.38, "total_tokens": 14689920} {"current_steps": 69615, "total_steps": 181800, "loss": 0.0455, "lr": 3.87681892699744e-05, "epoch": 7.658415841584159, "percentage": 38.29, "elapsed_time": "2:44:23", "remaining_time": "4:24:55", "throughput": 1489.39, "total_tokens": 14691040} {"current_steps": 69620, "total_steps": 181800, "loss": 0.0399, "lr": 3.876618590586383e-05, "epoch": 7.658965896589659, "percentage": 38.29, "elapsed_time": "2:44:24", "remaining_time": "4:24:54", "throughput": 1489.4, "total_tokens": 14692192} {"current_steps": 69625, "total_steps": 181800, "loss": 0.1289, "lr": 3.8764182414876935e-05, "epoch": 7.65951595159516, "percentage": 38.3, "elapsed_time": "2:44:25", "remaining_time": "4:24:54", "throughput": 1489.4, "total_tokens": 14693216} {"current_steps": 69630, "total_steps": 181800, "loss": 0.0662, "lr": 3.876217879703218e-05, "epoch": 7.66006600660066, "percentage": 38.3, "elapsed_time": "2:44:25", "remaining_time": "4:24:53", "throughput": 1489.41, "total_tokens": 14694336} {"current_steps": 69635, "total_steps": 181800, "loss": 0.0754, "lr": 3.8760175052348026e-05, "epoch": 7.66061606160616, "percentage": 38.3, "elapsed_time": "2:44:26", "remaining_time": "4:24:52", "throughput": 1489.41, "total_tokens": 14695328} {"current_steps": 69640, "total_steps": 181800, "loss": 0.0114, "lr": 3.875817118084293e-05, "epoch": 7.661166116611661, "percentage": 38.31, "elapsed_time": "2:44:27", "remaining_time": "4:24:51", "throughput": 1489.41, "total_tokens": 14696352} {"current_steps": 69645, "total_steps": 181800, "loss": 0.0174, "lr": 3.8756167182535386e-05, "epoch": 7.661716171617162, "percentage": 38.31, "elapsed_time": "2:44:27", "remaining_time": "4:24:51", "throughput": 1489.41, "total_tokens": 14697408} {"current_steps": 69650, "total_steps": 181800, "loss": 0.0644, "lr": 3.875416305744384e-05, "epoch": 7.662266226622663, "percentage": 38.31, "elapsed_time": "2:44:28", "remaining_time": "4:24:50", "throughput": 1489.41, "total_tokens": 14698400} {"current_steps": 69655, "total_steps": 181800, "loss": 0.014, "lr": 3.8752158805586775e-05, "epoch": 7.662816281628163, "percentage": 38.31, "elapsed_time": "2:44:29", "remaining_time": "4:24:49", "throughput": 1489.41, "total_tokens": 14699424} {"current_steps": 69660, "total_steps": 181800, "loss": 0.0591, "lr": 3.875015442698266e-05, "epoch": 7.663366336633663, "percentage": 38.32, "elapsed_time": "2:44:30", "remaining_time": "4:24:48", "throughput": 1489.41, "total_tokens": 14700448} {"current_steps": 69665, "total_steps": 181800, "loss": 0.0237, "lr": 3.8748149921649973e-05, "epoch": 7.663916391639164, "percentage": 38.32, "elapsed_time": "2:44:30", "remaining_time": "4:24:48", "throughput": 1489.42, "total_tokens": 14701568} {"current_steps": 69670, "total_steps": 181800, "loss": 0.005, "lr": 3.8746145289607186e-05, "epoch": 7.664466446644664, "percentage": 38.32, "elapsed_time": "2:44:31", "remaining_time": "4:24:47", "throughput": 1489.41, "total_tokens": 14702560} {"current_steps": 69675, "total_steps": 181800, "loss": 0.0046, "lr": 3.8744140530872773e-05, "epoch": 7.665016501650165, "percentage": 38.33, "elapsed_time": "2:44:32", "remaining_time": "4:24:46", "throughput": 1489.42, "total_tokens": 14703616} {"current_steps": 69680, "total_steps": 181800, "loss": 0.0176, "lr": 3.874213564546521e-05, "epoch": 7.665566556655666, "percentage": 38.33, "elapsed_time": "2:44:32", "remaining_time": "4:24:45", "throughput": 1489.41, "total_tokens": 14704608} {"current_steps": 69685, "total_steps": 181800, "loss": 0.0161, "lr": 3.874013063340298e-05, "epoch": 7.666116611661166, "percentage": 38.33, "elapsed_time": "2:44:33", "remaining_time": "4:24:45", "throughput": 1489.42, "total_tokens": 14705728} {"current_steps": 69690, "total_steps": 181800, "loss": 0.0098, "lr": 3.873812549470456e-05, "epoch": 7.666666666666667, "percentage": 38.33, "elapsed_time": "2:44:34", "remaining_time": "4:24:44", "throughput": 1489.42, "total_tokens": 14706720} {"current_steps": 69695, "total_steps": 181800, "loss": 0.044, "lr": 3.8736120229388426e-05, "epoch": 7.667216721672167, "percentage": 38.34, "elapsed_time": "2:44:34", "remaining_time": "4:24:43", "throughput": 1489.42, "total_tokens": 14707744} {"current_steps": 69700, "total_steps": 181800, "loss": 0.0047, "lr": 3.873411483747306e-05, "epoch": 7.667766776677668, "percentage": 38.34, "elapsed_time": "2:44:35", "remaining_time": "4:24:43", "throughput": 1489.43, "total_tokens": 14708864} {"current_steps": 69705, "total_steps": 181800, "loss": 0.0715, "lr": 3.873210931897695e-05, "epoch": 7.6683168316831685, "percentage": 38.34, "elapsed_time": "2:44:36", "remaining_time": "4:24:42", "throughput": 1489.43, "total_tokens": 14709920} {"current_steps": 69710, "total_steps": 181800, "loss": 0.0838, "lr": 3.8730103673918575e-05, "epoch": 7.668866886688669, "percentage": 38.34, "elapsed_time": "2:44:36", "remaining_time": "4:24:41", "throughput": 1489.43, "total_tokens": 14710944} {"current_steps": 69715, "total_steps": 181800, "loss": 0.0022, "lr": 3.872809790231643e-05, "epoch": 7.66941694169417, "percentage": 38.35, "elapsed_time": "2:44:37", "remaining_time": "4:24:40", "throughput": 1489.44, "total_tokens": 14712096} {"current_steps": 69720, "total_steps": 181800, "loss": 0.0253, "lr": 3.8726092004189e-05, "epoch": 7.66996699669967, "percentage": 38.35, "elapsed_time": "2:44:38", "remaining_time": "4:24:40", "throughput": 1489.44, "total_tokens": 14713120} {"current_steps": 69725, "total_steps": 181800, "loss": 0.059, "lr": 3.8724085979554745e-05, "epoch": 7.67051705170517, "percentage": 38.35, "elapsed_time": "2:44:38", "remaining_time": "4:24:39", "throughput": 1489.44, "total_tokens": 14714144} {"current_steps": 69730, "total_steps": 181800, "loss": 0.0414, "lr": 3.872207982843219e-05, "epoch": 7.671067106710671, "percentage": 38.36, "elapsed_time": "2:44:39", "remaining_time": "4:24:38", "throughput": 1489.44, "total_tokens": 14715200} {"current_steps": 69735, "total_steps": 181800, "loss": 0.0168, "lr": 3.872007355083981e-05, "epoch": 7.6716171617161715, "percentage": 38.36, "elapsed_time": "2:44:40", "remaining_time": "4:24:37", "throughput": 1489.44, "total_tokens": 14716224} {"current_steps": 69740, "total_steps": 181800, "loss": 0.1419, "lr": 3.871806714679609e-05, "epoch": 7.672167216721672, "percentage": 38.36, "elapsed_time": "2:44:41", "remaining_time": "4:24:37", "throughput": 1489.44, "total_tokens": 14717248} {"current_steps": 69745, "total_steps": 181800, "loss": 0.1012, "lr": 3.871606061631953e-05, "epoch": 7.672717271727173, "percentage": 38.36, "elapsed_time": "2:44:41", "remaining_time": "4:24:36", "throughput": 1489.45, "total_tokens": 14718336} {"current_steps": 69750, "total_steps": 181800, "loss": 0.0554, "lr": 3.871405395942862e-05, "epoch": 7.673267326732673, "percentage": 38.37, "elapsed_time": "2:44:42", "remaining_time": "4:24:35", "throughput": 1489.46, "total_tokens": 14719456} {"current_steps": 69755, "total_steps": 181800, "loss": 0.003, "lr": 3.8712047176141857e-05, "epoch": 7.673817381738174, "percentage": 38.37, "elapsed_time": "2:44:43", "remaining_time": "4:24:34", "throughput": 1489.46, "total_tokens": 14720544} {"current_steps": 69760, "total_steps": 181800, "loss": 0.1276, "lr": 3.8710040266477734e-05, "epoch": 7.674367436743674, "percentage": 38.37, "elapsed_time": "2:44:43", "remaining_time": "4:24:34", "throughput": 1489.47, "total_tokens": 14721600} {"current_steps": 69765, "total_steps": 181800, "loss": 0.0362, "lr": 3.8708033230454754e-05, "epoch": 7.674917491749175, "percentage": 38.37, "elapsed_time": "2:44:44", "remaining_time": "4:24:33", "throughput": 1489.46, "total_tokens": 14722560} {"current_steps": 69770, "total_steps": 181800, "loss": 0.0458, "lr": 3.87060260680914e-05, "epoch": 7.675467546754676, "percentage": 38.38, "elapsed_time": "2:44:45", "remaining_time": "4:24:33", "throughput": 1489.43, "total_tokens": 14723584} {"current_steps": 69775, "total_steps": 181800, "loss": 0.0113, "lr": 3.870401877940618e-05, "epoch": 7.676017601760176, "percentage": 38.38, "elapsed_time": "2:44:46", "remaining_time": "4:24:32", "throughput": 1489.43, "total_tokens": 14724640} {"current_steps": 69780, "total_steps": 181800, "loss": 0.1013, "lr": 3.870201136441761e-05, "epoch": 7.676567656765677, "percentage": 38.38, "elapsed_time": "2:44:46", "remaining_time": "4:24:31", "throughput": 1489.43, "total_tokens": 14725664} {"current_steps": 69785, "total_steps": 181800, "loss": 0.0363, "lr": 3.870000382314416e-05, "epoch": 7.677117711771177, "percentage": 38.39, "elapsed_time": "2:44:47", "remaining_time": "4:24:30", "throughput": 1489.43, "total_tokens": 14726720} {"current_steps": 69790, "total_steps": 181800, "loss": 0.0076, "lr": 3.8697996155604354e-05, "epoch": 7.677667766776677, "percentage": 38.39, "elapsed_time": "2:44:48", "remaining_time": "4:24:30", "throughput": 1489.43, "total_tokens": 14727712} {"current_steps": 69795, "total_steps": 181800, "loss": 0.0347, "lr": 3.8695988361816694e-05, "epoch": 7.678217821782178, "percentage": 38.39, "elapsed_time": "2:44:48", "remaining_time": "4:24:29", "throughput": 1489.43, "total_tokens": 14728736} {"current_steps": 69800, "total_steps": 181800, "loss": 0.0645, "lr": 3.869398044179968e-05, "epoch": 7.678767876787679, "percentage": 38.39, "elapsed_time": "2:44:49", "remaining_time": "4:24:28", "throughput": 1489.43, "total_tokens": 14729760} {"current_steps": 69805, "total_steps": 181800, "loss": 0.0031, "lr": 3.869197239557181e-05, "epoch": 7.67931793179318, "percentage": 38.4, "elapsed_time": "2:44:50", "remaining_time": "4:24:27", "throughput": 1489.43, "total_tokens": 14730816} {"current_steps": 69810, "total_steps": 181800, "loss": 0.0083, "lr": 3.868996422315161e-05, "epoch": 7.67986798679868, "percentage": 38.4, "elapsed_time": "2:44:50", "remaining_time": "4:24:27", "throughput": 1489.43, "total_tokens": 14731808} {"current_steps": 69815, "total_steps": 181800, "loss": 0.0043, "lr": 3.868795592455759e-05, "epoch": 7.68041804180418, "percentage": 38.4, "elapsed_time": "2:44:51", "remaining_time": "4:24:26", "throughput": 1489.44, "total_tokens": 14732928} {"current_steps": 69820, "total_steps": 181800, "loss": 0.0672, "lr": 3.868594749980822e-05, "epoch": 7.680968096809681, "percentage": 38.4, "elapsed_time": "2:44:52", "remaining_time": "4:24:25", "throughput": 1489.45, "total_tokens": 14734048} {"current_steps": 69825, "total_steps": 181800, "loss": 0.0327, "lr": 3.868393894892206e-05, "epoch": 7.681518151815181, "percentage": 38.41, "elapsed_time": "2:44:52", "remaining_time": "4:24:24", "throughput": 1489.46, "total_tokens": 14735168} {"current_steps": 69830, "total_steps": 181800, "loss": 0.1042, "lr": 3.868193027191759e-05, "epoch": 7.6820682068206825, "percentage": 38.41, "elapsed_time": "2:44:53", "remaining_time": "4:24:24", "throughput": 1489.46, "total_tokens": 14736256} {"current_steps": 69835, "total_steps": 181800, "loss": 0.0168, "lr": 3.867992146881334e-05, "epoch": 7.682618261826183, "percentage": 38.41, "elapsed_time": "2:44:54", "remaining_time": "4:24:23", "throughput": 1489.46, "total_tokens": 14737248} {"current_steps": 69840, "total_steps": 181800, "loss": 0.053, "lr": 3.8677912539627815e-05, "epoch": 7.683168316831683, "percentage": 38.42, "elapsed_time": "2:44:55", "remaining_time": "4:24:22", "throughput": 1489.46, "total_tokens": 14738272} {"current_steps": 69845, "total_steps": 181800, "loss": 0.0114, "lr": 3.867590348437954e-05, "epoch": 7.683718371837184, "percentage": 38.42, "elapsed_time": "2:44:55", "remaining_time": "4:24:21", "throughput": 1489.46, "total_tokens": 14739328} {"current_steps": 69850, "total_steps": 181800, "loss": 0.0781, "lr": 3.867389430308702e-05, "epoch": 7.684268426842684, "percentage": 38.42, "elapsed_time": "2:44:56", "remaining_time": "4:24:21", "throughput": 1489.47, "total_tokens": 14740416} {"current_steps": 69855, "total_steps": 181800, "loss": 0.018, "lr": 3.8671884995768776e-05, "epoch": 7.684818481848184, "percentage": 38.42, "elapsed_time": "2:44:57", "remaining_time": "4:24:20", "throughput": 1489.46, "total_tokens": 14741408} {"current_steps": 69860, "total_steps": 181800, "loss": 0.0641, "lr": 3.8669875562443333e-05, "epoch": 7.6853685368536855, "percentage": 38.43, "elapsed_time": "2:44:57", "remaining_time": "4:24:19", "throughput": 1489.47, "total_tokens": 14742496} {"current_steps": 69865, "total_steps": 181800, "loss": 0.0559, "lr": 3.866786600312921e-05, "epoch": 7.685918591859186, "percentage": 38.43, "elapsed_time": "2:44:58", "remaining_time": "4:24:18", "throughput": 1489.47, "total_tokens": 14743552} {"current_steps": 69870, "total_steps": 181800, "loss": 0.0751, "lr": 3.8665856317844904e-05, "epoch": 7.686468646864687, "percentage": 38.43, "elapsed_time": "2:44:59", "remaining_time": "4:24:18", "throughput": 1489.47, "total_tokens": 14744576} {"current_steps": 69875, "total_steps": 181800, "loss": 0.057, "lr": 3.866384650660898e-05, "epoch": 7.687018701870187, "percentage": 38.44, "elapsed_time": "2:44:59", "remaining_time": "4:24:17", "throughput": 1489.48, "total_tokens": 14745664} {"current_steps": 69880, "total_steps": 181800, "loss": 0.0051, "lr": 3.866183656943994e-05, "epoch": 7.687568756875687, "percentage": 38.44, "elapsed_time": "2:45:00", "remaining_time": "4:24:16", "throughput": 1489.49, "total_tokens": 14746784} {"current_steps": 69885, "total_steps": 181800, "loss": 0.0177, "lr": 3.865982650635629e-05, "epoch": 7.688118811881188, "percentage": 38.44, "elapsed_time": "2:45:01", "remaining_time": "4:24:16", "throughput": 1489.49, "total_tokens": 14747840} {"current_steps": 69890, "total_steps": 181800, "loss": 0.0203, "lr": 3.865781631737658e-05, "epoch": 7.6886688668866885, "percentage": 38.44, "elapsed_time": "2:45:01", "remaining_time": "4:24:15", "throughput": 1489.5, "total_tokens": 14748928} {"current_steps": 69895, "total_steps": 181800, "loss": 0.013, "lr": 3.865580600251933e-05, "epoch": 7.68921892189219, "percentage": 38.45, "elapsed_time": "2:45:02", "remaining_time": "4:24:14", "throughput": 1489.5, "total_tokens": 14749984} {"current_steps": 69900, "total_steps": 181800, "loss": 0.0452, "lr": 3.865379556180307e-05, "epoch": 7.68976897689769, "percentage": 38.45, "elapsed_time": "2:45:03", "remaining_time": "4:24:13", "throughput": 1489.5, "total_tokens": 14751040} {"current_steps": 69905, "total_steps": 181800, "loss": 0.0658, "lr": 3.8651784995246336e-05, "epoch": 7.69031903190319, "percentage": 38.45, "elapsed_time": "2:45:04", "remaining_time": "4:24:13", "throughput": 1489.5, "total_tokens": 14752064} {"current_steps": 69910, "total_steps": 181800, "loss": 0.0075, "lr": 3.864977430286765e-05, "epoch": 7.690869086908691, "percentage": 38.45, "elapsed_time": "2:45:04", "remaining_time": "4:24:12", "throughput": 1489.51, "total_tokens": 14753152} {"current_steps": 69915, "total_steps": 181800, "loss": 0.0059, "lr": 3.864776348468553e-05, "epoch": 7.691419141914191, "percentage": 38.46, "elapsed_time": "2:45:05", "remaining_time": "4:24:11", "throughput": 1489.51, "total_tokens": 14754208} {"current_steps": 69920, "total_steps": 181800, "loss": 0.0721, "lr": 3.8645752540718536e-05, "epoch": 7.6919691969196915, "percentage": 38.46, "elapsed_time": "2:45:06", "remaining_time": "4:24:10", "throughput": 1489.51, "total_tokens": 14755264} {"current_steps": 69925, "total_steps": 181800, "loss": 0.0635, "lr": 3.8643741470985185e-05, "epoch": 7.692519251925193, "percentage": 38.46, "elapsed_time": "2:45:06", "remaining_time": "4:24:10", "throughput": 1489.52, "total_tokens": 14756384} {"current_steps": 69930, "total_steps": 181800, "loss": 0.1897, "lr": 3.864173027550402e-05, "epoch": 7.693069306930693, "percentage": 38.47, "elapsed_time": "2:45:07", "remaining_time": "4:24:09", "throughput": 1489.52, "total_tokens": 14757376} {"current_steps": 69935, "total_steps": 181800, "loss": 0.0193, "lr": 3.863971895429356e-05, "epoch": 7.693619361936194, "percentage": 38.47, "elapsed_time": "2:45:08", "remaining_time": "4:24:08", "throughput": 1489.52, "total_tokens": 14758368} {"current_steps": 69940, "total_steps": 181800, "loss": 0.0063, "lr": 3.8637707507372366e-05, "epoch": 7.694169416941694, "percentage": 38.47, "elapsed_time": "2:45:08", "remaining_time": "4:24:07", "throughput": 1489.53, "total_tokens": 14759520} {"current_steps": 69945, "total_steps": 181800, "loss": 0.0736, "lr": 3.8635695934758963e-05, "epoch": 7.694719471947195, "percentage": 38.47, "elapsed_time": "2:45:09", "remaining_time": "4:24:07", "throughput": 1489.54, "total_tokens": 14760640} {"current_steps": 69950, "total_steps": 181800, "loss": 0.0245, "lr": 3.863368423647189e-05, "epoch": 7.695269526952695, "percentage": 38.48, "elapsed_time": "2:45:10", "remaining_time": "4:24:06", "throughput": 1489.54, "total_tokens": 14761696} {"current_steps": 69955, "total_steps": 181800, "loss": 0.0998, "lr": 3.86316724125297e-05, "epoch": 7.695819581958196, "percentage": 38.48, "elapsed_time": "2:45:10", "remaining_time": "4:24:05", "throughput": 1489.54, "total_tokens": 14762752} {"current_steps": 69960, "total_steps": 181800, "loss": 0.0452, "lr": 3.8629660462950924e-05, "epoch": 7.696369636963697, "percentage": 38.48, "elapsed_time": "2:45:11", "remaining_time": "4:24:04", "throughput": 1489.54, "total_tokens": 14763744} {"current_steps": 69965, "total_steps": 181800, "loss": 0.0319, "lr": 3.86276483877541e-05, "epoch": 7.696919691969197, "percentage": 38.48, "elapsed_time": "2:45:12", "remaining_time": "4:24:04", "throughput": 1489.54, "total_tokens": 14764800} {"current_steps": 69970, "total_steps": 181800, "loss": 0.0396, "lr": 3.862563618695779e-05, "epoch": 7.697469746974697, "percentage": 38.49, "elapsed_time": "2:45:13", "remaining_time": "4:24:03", "throughput": 1489.55, "total_tokens": 14765952} {"current_steps": 69975, "total_steps": 181800, "loss": 0.0054, "lr": 3.8623623860580525e-05, "epoch": 7.698019801980198, "percentage": 38.49, "elapsed_time": "2:45:13", "remaining_time": "4:24:02", "throughput": 1489.56, "total_tokens": 14767008} {"current_steps": 69980, "total_steps": 181800, "loss": 0.0415, "lr": 3.8621611408640854e-05, "epoch": 7.698569856985698, "percentage": 38.49, "elapsed_time": "2:45:14", "remaining_time": "4:24:02", "throughput": 1489.56, "total_tokens": 14768064} {"current_steps": 69985, "total_steps": 181800, "loss": 0.0241, "lr": 3.8619598831157334e-05, "epoch": 7.6991199119911995, "percentage": 38.5, "elapsed_time": "2:45:15", "remaining_time": "4:24:01", "throughput": 1489.56, "total_tokens": 14769120} {"current_steps": 69990, "total_steps": 181800, "loss": 0.0893, "lr": 3.86175861281485e-05, "epoch": 7.6996699669967, "percentage": 38.5, "elapsed_time": "2:45:15", "remaining_time": "4:24:00", "throughput": 1489.57, "total_tokens": 14770208} {"current_steps": 69995, "total_steps": 181800, "loss": 0.0179, "lr": 3.8615573299632914e-05, "epoch": 7.7002200220022, "percentage": 38.5, "elapsed_time": "2:45:16", "remaining_time": "4:23:59", "throughput": 1489.57, "total_tokens": 14771296} {"current_steps": 70000, "total_steps": 181800, "loss": 0.05, "lr": 3.861356034562912e-05, "epoch": 7.700770077007701, "percentage": 38.5, "elapsed_time": "2:45:17", "remaining_time": "4:23:59", "throughput": 1489.58, "total_tokens": 14772384} {"current_steps": 70005, "total_steps": 181800, "loss": 0.014, "lr": 3.8611547266155665e-05, "epoch": 7.701320132013201, "percentage": 38.51, "elapsed_time": "2:45:17", "remaining_time": "4:23:58", "throughput": 1489.58, "total_tokens": 14773408} {"current_steps": 70010, "total_steps": 181800, "loss": 0.017, "lr": 3.860953406123112e-05, "epoch": 7.701870187018702, "percentage": 38.51, "elapsed_time": "2:45:18", "remaining_time": "4:23:57", "throughput": 1489.58, "total_tokens": 14774432} {"current_steps": 70015, "total_steps": 181800, "loss": 0.132, "lr": 3.860752073087403e-05, "epoch": 7.7024202420242025, "percentage": 38.51, "elapsed_time": "2:45:19", "remaining_time": "4:23:56", "throughput": 1489.58, "total_tokens": 14775488} {"current_steps": 70020, "total_steps": 181800, "loss": 0.0665, "lr": 3.8605507275102946e-05, "epoch": 7.702970297029703, "percentage": 38.51, "elapsed_time": "2:45:19", "remaining_time": "4:23:56", "throughput": 1489.58, "total_tokens": 14776544} {"current_steps": 70025, "total_steps": 181800, "loss": 0.0401, "lr": 3.860349369393643e-05, "epoch": 7.703520352035204, "percentage": 38.52, "elapsed_time": "2:45:20", "remaining_time": "4:23:55", "throughput": 1489.58, "total_tokens": 14777568} {"current_steps": 70030, "total_steps": 181800, "loss": 0.0582, "lr": 3.8601479987393044e-05, "epoch": 7.704070407040704, "percentage": 38.52, "elapsed_time": "2:45:21", "remaining_time": "4:23:54", "throughput": 1489.59, "total_tokens": 14778720} {"current_steps": 70035, "total_steps": 181800, "loss": 0.1643, "lr": 3.859946615549135e-05, "epoch": 7.704620462046204, "percentage": 38.52, "elapsed_time": "2:45:21", "remaining_time": "4:23:53", "throughput": 1489.59, "total_tokens": 14779744} {"current_steps": 70040, "total_steps": 181800, "loss": 0.0262, "lr": 3.859745219824989e-05, "epoch": 7.705170517051705, "percentage": 38.53, "elapsed_time": "2:45:22", "remaining_time": "4:23:53", "throughput": 1489.6, "total_tokens": 14780800} {"current_steps": 70045, "total_steps": 181800, "loss": 0.0433, "lr": 3.8595438115687235e-05, "epoch": 7.7057205720572055, "percentage": 38.53, "elapsed_time": "2:45:23", "remaining_time": "4:23:52", "throughput": 1489.6, "total_tokens": 14781888} {"current_steps": 70050, "total_steps": 181800, "loss": 0.035, "lr": 3.8593423907821966e-05, "epoch": 7.706270627062707, "percentage": 38.53, "elapsed_time": "2:45:24", "remaining_time": "4:23:51", "throughput": 1489.6, "total_tokens": 14782880} {"current_steps": 70055, "total_steps": 181800, "loss": 0.0336, "lr": 3.859140957467262e-05, "epoch": 7.706820682068207, "percentage": 38.53, "elapsed_time": "2:45:24", "remaining_time": "4:23:51", "throughput": 1489.6, "total_tokens": 14783936} {"current_steps": 70060, "total_steps": 181800, "loss": 0.0233, "lr": 3.858939511625778e-05, "epoch": 7.707370737073707, "percentage": 38.54, "elapsed_time": "2:45:25", "remaining_time": "4:23:50", "throughput": 1489.6, "total_tokens": 14784960} {"current_steps": 70065, "total_steps": 181800, "loss": 0.0356, "lr": 3.8587380532596e-05, "epoch": 7.707920792079208, "percentage": 38.54, "elapsed_time": "2:45:26", "remaining_time": "4:23:49", "throughput": 1489.6, "total_tokens": 14785984} {"current_steps": 70070, "total_steps": 181800, "loss": 0.0079, "lr": 3.858536582370586e-05, "epoch": 7.708470847084708, "percentage": 38.54, "elapsed_time": "2:45:26", "remaining_time": "4:23:48", "throughput": 1489.6, "total_tokens": 14787008} {"current_steps": 70075, "total_steps": 181800, "loss": 0.0076, "lr": 3.8583350989605916e-05, "epoch": 7.709020902090209, "percentage": 38.55, "elapsed_time": "2:45:27", "remaining_time": "4:23:48", "throughput": 1489.6, "total_tokens": 14788032} {"current_steps": 70080, "total_steps": 181800, "loss": 0.046, "lr": 3.858133603031475e-05, "epoch": 7.70957095709571, "percentage": 38.55, "elapsed_time": "2:45:28", "remaining_time": "4:23:47", "throughput": 1489.61, "total_tokens": 14789152} {"current_steps": 70085, "total_steps": 181800, "loss": 0.1085, "lr": 3.857932094585092e-05, "epoch": 7.71012101210121, "percentage": 38.55, "elapsed_time": "2:45:28", "remaining_time": "4:23:46", "throughput": 1489.61, "total_tokens": 14790208} {"current_steps": 70090, "total_steps": 181800, "loss": 0.0145, "lr": 3.8577305736233e-05, "epoch": 7.710671067106711, "percentage": 38.55, "elapsed_time": "2:45:29", "remaining_time": "4:23:45", "throughput": 1489.62, "total_tokens": 14791264} {"current_steps": 70095, "total_steps": 181800, "loss": 0.0735, "lr": 3.8575290401479586e-05, "epoch": 7.711221122112211, "percentage": 38.56, "elapsed_time": "2:45:30", "remaining_time": "4:23:45", "throughput": 1489.62, "total_tokens": 14792352} {"current_steps": 70100, "total_steps": 181800, "loss": 0.0108, "lr": 3.8573274941609225e-05, "epoch": 7.711771177117711, "percentage": 38.56, "elapsed_time": "2:45:30", "remaining_time": "4:23:44", "throughput": 1489.63, "total_tokens": 14793472} {"current_steps": 70105, "total_steps": 181800, "loss": 0.0126, "lr": 3.85712593566405e-05, "epoch": 7.712321232123212, "percentage": 38.56, "elapsed_time": "2:45:31", "remaining_time": "4:23:43", "throughput": 1489.63, "total_tokens": 14794496} {"current_steps": 70110, "total_steps": 181800, "loss": 0.0075, "lr": 3.856924364659199e-05, "epoch": 7.712871287128713, "percentage": 38.56, "elapsed_time": "2:45:32", "remaining_time": "4:23:42", "throughput": 1489.63, "total_tokens": 14795520} {"current_steps": 70115, "total_steps": 181800, "loss": 0.0223, "lr": 3.8567227811482276e-05, "epoch": 7.713421342134214, "percentage": 38.57, "elapsed_time": "2:45:33", "remaining_time": "4:23:42", "throughput": 1489.64, "total_tokens": 14796608} {"current_steps": 70120, "total_steps": 181800, "loss": 0.0311, "lr": 3.856521185132993e-05, "epoch": 7.713971397139714, "percentage": 38.57, "elapsed_time": "2:45:33", "remaining_time": "4:23:41", "throughput": 1489.63, "total_tokens": 14797600} {"current_steps": 70125, "total_steps": 181800, "loss": 0.0114, "lr": 3.8563195766153535e-05, "epoch": 7.714521452145215, "percentage": 38.57, "elapsed_time": "2:45:34", "remaining_time": "4:23:40", "throughput": 1489.63, "total_tokens": 14798592} {"current_steps": 70130, "total_steps": 181800, "loss": 0.0293, "lr": 3.856117955597168e-05, "epoch": 7.715071507150715, "percentage": 38.58, "elapsed_time": "2:45:35", "remaining_time": "4:23:39", "throughput": 1489.63, "total_tokens": 14799648} {"current_steps": 70135, "total_steps": 181800, "loss": 0.0417, "lr": 3.855916322080293e-05, "epoch": 7.715621562156215, "percentage": 38.58, "elapsed_time": "2:45:35", "remaining_time": "4:23:39", "throughput": 1489.64, "total_tokens": 14800736} {"current_steps": 70140, "total_steps": 181800, "loss": 0.0109, "lr": 3.8557146760665886e-05, "epoch": 7.7161716171617165, "percentage": 38.58, "elapsed_time": "2:45:36", "remaining_time": "4:23:38", "throughput": 1489.65, "total_tokens": 14801856} {"current_steps": 70145, "total_steps": 181800, "loss": 0.0284, "lr": 3.8555130175579123e-05, "epoch": 7.716721672167217, "percentage": 38.58, "elapsed_time": "2:45:37", "remaining_time": "4:23:37", "throughput": 1489.66, "total_tokens": 14802944} {"current_steps": 70150, "total_steps": 181800, "loss": 0.0033, "lr": 3.855311346556123e-05, "epoch": 7.717271727172717, "percentage": 38.59, "elapsed_time": "2:45:37", "remaining_time": "4:23:36", "throughput": 1489.66, "total_tokens": 14804032} {"current_steps": 70155, "total_steps": 181800, "loss": 0.0226, "lr": 3.855109663063079e-05, "epoch": 7.717821782178218, "percentage": 38.59, "elapsed_time": "2:45:38", "remaining_time": "4:23:36", "throughput": 1489.67, "total_tokens": 14805120} {"current_steps": 70160, "total_steps": 181800, "loss": 0.0084, "lr": 3.85490796708064e-05, "epoch": 7.718371837183718, "percentage": 38.59, "elapsed_time": "2:45:39", "remaining_time": "4:23:35", "throughput": 1489.67, "total_tokens": 14806208} {"current_steps": 70165, "total_steps": 181800, "loss": 0.0239, "lr": 3.854706258610664e-05, "epoch": 7.718921892189218, "percentage": 38.59, "elapsed_time": "2:45:39", "remaining_time": "4:23:34", "throughput": 1489.68, "total_tokens": 14807264} {"current_steps": 70170, "total_steps": 181800, "loss": 0.0054, "lr": 3.854504537655012e-05, "epoch": 7.7194719471947195, "percentage": 38.6, "elapsed_time": "2:45:40", "remaining_time": "4:23:34", "throughput": 1489.68, "total_tokens": 14808320} {"current_steps": 70175, "total_steps": 181800, "loss": 0.102, "lr": 3.85430280421554e-05, "epoch": 7.72002200220022, "percentage": 38.6, "elapsed_time": "2:45:41", "remaining_time": "4:23:33", "throughput": 1489.69, "total_tokens": 14809440} {"current_steps": 70180, "total_steps": 181800, "loss": 0.0731, "lr": 3.854101058294108e-05, "epoch": 7.720572057205721, "percentage": 38.6, "elapsed_time": "2:45:41", "remaining_time": "4:23:32", "throughput": 1489.69, "total_tokens": 14810496} {"current_steps": 70185, "total_steps": 181800, "loss": 0.0929, "lr": 3.8538992998925785e-05, "epoch": 7.721122112211221, "percentage": 38.61, "elapsed_time": "2:45:42", "remaining_time": "4:23:31", "throughput": 1489.7, "total_tokens": 14811584} {"current_steps": 70190, "total_steps": 181800, "loss": 0.0599, "lr": 3.853697529012808e-05, "epoch": 7.721672167216722, "percentage": 38.61, "elapsed_time": "2:45:43", "remaining_time": "4:23:31", "throughput": 1489.7, "total_tokens": 14812608} {"current_steps": 70195, "total_steps": 181800, "loss": 0.026, "lr": 3.8534957456566566e-05, "epoch": 7.722222222222222, "percentage": 38.61, "elapsed_time": "2:45:44", "remaining_time": "4:23:30", "throughput": 1489.7, "total_tokens": 14813664} {"current_steps": 70200, "total_steps": 181800, "loss": 0.0369, "lr": 3.8532939498259845e-05, "epoch": 7.7227722772277225, "percentage": 38.61, "elapsed_time": "2:45:44", "remaining_time": "4:23:29", "throughput": 1489.71, "total_tokens": 14814784} {"current_steps": 70205, "total_steps": 181800, "loss": 0.0266, "lr": 3.853092141522652e-05, "epoch": 7.723322332233224, "percentage": 38.62, "elapsed_time": "2:45:45", "remaining_time": "4:23:28", "throughput": 1489.72, "total_tokens": 14815904} {"current_steps": 70210, "total_steps": 181800, "loss": 0.0846, "lr": 3.852890320748518e-05, "epoch": 7.723872387238724, "percentage": 38.62, "elapsed_time": "2:45:46", "remaining_time": "4:23:28", "throughput": 1489.72, "total_tokens": 14816960} {"current_steps": 70215, "total_steps": 181800, "loss": 0.0356, "lr": 3.852688487505443e-05, "epoch": 7.724422442244224, "percentage": 38.62, "elapsed_time": "2:45:46", "remaining_time": "4:23:27", "throughput": 1489.73, "total_tokens": 14818048} {"current_steps": 70220, "total_steps": 181800, "loss": 0.0336, "lr": 3.852486641795288e-05, "epoch": 7.724972497249725, "percentage": 38.62, "elapsed_time": "2:45:47", "remaining_time": "4:23:26", "throughput": 1489.74, "total_tokens": 14819168} {"current_steps": 70225, "total_steps": 181800, "loss": 0.0158, "lr": 3.8522847836199116e-05, "epoch": 7.725522552255225, "percentage": 38.63, "elapsed_time": "2:45:48", "remaining_time": "4:23:25", "throughput": 1489.74, "total_tokens": 14820224} {"current_steps": 70230, "total_steps": 181800, "loss": 0.03, "lr": 3.8520829129811755e-05, "epoch": 7.726072607260726, "percentage": 38.63, "elapsed_time": "2:45:48", "remaining_time": "4:23:25", "throughput": 1489.75, "total_tokens": 14821344} {"current_steps": 70235, "total_steps": 181800, "loss": 0.0171, "lr": 3.85188102988094e-05, "epoch": 7.726622662266227, "percentage": 38.63, "elapsed_time": "2:45:49", "remaining_time": "4:23:24", "throughput": 1489.76, "total_tokens": 14822464} {"current_steps": 70240, "total_steps": 181800, "loss": 0.0165, "lr": 3.851679134321066e-05, "epoch": 7.727172717271727, "percentage": 38.64, "elapsed_time": "2:45:50", "remaining_time": "4:23:23", "throughput": 1489.77, "total_tokens": 14823616} {"current_steps": 70245, "total_steps": 181800, "loss": 0.0023, "lr": 3.851477226303414e-05, "epoch": 7.727722772277228, "percentage": 38.64, "elapsed_time": "2:45:50", "remaining_time": "4:23:22", "throughput": 1489.77, "total_tokens": 14824640} {"current_steps": 70250, "total_steps": 181800, "loss": 0.0737, "lr": 3.8512753058298445e-05, "epoch": 7.728272827282728, "percentage": 38.64, "elapsed_time": "2:45:51", "remaining_time": "4:23:22", "throughput": 1489.78, "total_tokens": 14825728} {"current_steps": 70255, "total_steps": 181800, "loss": 0.037, "lr": 3.85107337290222e-05, "epoch": 7.728822882288229, "percentage": 38.64, "elapsed_time": "2:45:52", "remaining_time": "4:23:21", "throughput": 1489.78, "total_tokens": 14826784} {"current_steps": 70260, "total_steps": 181800, "loss": 0.0302, "lr": 3.8508714275223994e-05, "epoch": 7.729372937293729, "percentage": 38.65, "elapsed_time": "2:45:53", "remaining_time": "4:23:20", "throughput": 1489.78, "total_tokens": 14827840} {"current_steps": 70265, "total_steps": 181800, "loss": 0.0044, "lr": 3.850669469692246e-05, "epoch": 7.72992299229923, "percentage": 38.65, "elapsed_time": "2:45:53", "remaining_time": "4:23:19", "throughput": 1489.79, "total_tokens": 14828896} {"current_steps": 70270, "total_steps": 181800, "loss": 0.0196, "lr": 3.850467499413619e-05, "epoch": 7.730473047304731, "percentage": 38.65, "elapsed_time": "2:45:54", "remaining_time": "4:23:19", "throughput": 1489.79, "total_tokens": 14829920} {"current_steps": 70275, "total_steps": 181800, "loss": 0.0076, "lr": 3.850265516688382e-05, "epoch": 7.731023102310231, "percentage": 38.66, "elapsed_time": "2:45:55", "remaining_time": "4:23:18", "throughput": 1489.79, "total_tokens": 14831008} {"current_steps": 70280, "total_steps": 181800, "loss": 0.0272, "lr": 3.8500635215183954e-05, "epoch": 7.731573157315731, "percentage": 38.66, "elapsed_time": "2:45:55", "remaining_time": "4:23:17", "throughput": 1489.79, "total_tokens": 14832064} {"current_steps": 70285, "total_steps": 181800, "loss": 0.121, "lr": 3.849861513905521e-05, "epoch": 7.732123212321232, "percentage": 38.66, "elapsed_time": "2:45:56", "remaining_time": "4:23:17", "throughput": 1489.8, "total_tokens": 14833120} {"current_steps": 70290, "total_steps": 181800, "loss": 0.132, "lr": 3.849659493851621e-05, "epoch": 7.732673267326732, "percentage": 38.66, "elapsed_time": "2:45:57", "remaining_time": "4:23:16", "throughput": 1489.79, "total_tokens": 14834080} {"current_steps": 70295, "total_steps": 181800, "loss": 0.0029, "lr": 3.849457461358556e-05, "epoch": 7.7332233223322335, "percentage": 38.67, "elapsed_time": "2:45:57", "remaining_time": "4:23:15", "throughput": 1489.79, "total_tokens": 14835072} {"current_steps": 70300, "total_steps": 181800, "loss": 0.087, "lr": 3.849255416428191e-05, "epoch": 7.733773377337734, "percentage": 38.67, "elapsed_time": "2:45:58", "remaining_time": "4:23:14", "throughput": 1489.79, "total_tokens": 14836160} {"current_steps": 70305, "total_steps": 181800, "loss": 0.0673, "lr": 3.8490533590623854e-05, "epoch": 7.734323432343234, "percentage": 38.67, "elapsed_time": "2:45:59", "remaining_time": "4:23:14", "throughput": 1489.79, "total_tokens": 14837216} {"current_steps": 70310, "total_steps": 181800, "loss": 0.183, "lr": 3.848851289263003e-05, "epoch": 7.734873487348735, "percentage": 38.67, "elapsed_time": "2:45:59", "remaining_time": "4:23:13", "throughput": 1489.8, "total_tokens": 14838272} {"current_steps": 70315, "total_steps": 181800, "loss": 0.0119, "lr": 3.848649207031904e-05, "epoch": 7.735423542354235, "percentage": 38.68, "elapsed_time": "2:46:00", "remaining_time": "4:23:12", "throughput": 1489.79, "total_tokens": 14839264} {"current_steps": 70320, "total_steps": 181800, "loss": 0.0614, "lr": 3.848447112370953e-05, "epoch": 7.735973597359736, "percentage": 38.68, "elapsed_time": "2:46:01", "remaining_time": "4:23:11", "throughput": 1489.8, "total_tokens": 14840352} {"current_steps": 70325, "total_steps": 181800, "loss": 0.0413, "lr": 3.848245005282013e-05, "epoch": 7.7365236523652365, "percentage": 38.68, "elapsed_time": "2:46:02", "remaining_time": "4:23:11", "throughput": 1489.8, "total_tokens": 14841408} {"current_steps": 70330, "total_steps": 181800, "loss": 0.069, "lr": 3.848042885766944e-05, "epoch": 7.737073707370737, "percentage": 38.69, "elapsed_time": "2:46:02", "remaining_time": "4:23:10", "throughput": 1489.81, "total_tokens": 14842496} {"current_steps": 70335, "total_steps": 181800, "loss": 0.0091, "lr": 3.8478407538276116e-05, "epoch": 7.737623762376238, "percentage": 38.69, "elapsed_time": "2:46:03", "remaining_time": "4:23:09", "throughput": 1489.81, "total_tokens": 14843520} {"current_steps": 70340, "total_steps": 181800, "loss": 0.1389, "lr": 3.8476386094658776e-05, "epoch": 7.738173817381738, "percentage": 38.69, "elapsed_time": "2:46:04", "remaining_time": "4:23:08", "throughput": 1489.81, "total_tokens": 14844544} {"current_steps": 70345, "total_steps": 181800, "loss": 0.0152, "lr": 3.847436452683605e-05, "epoch": 7.738723872387238, "percentage": 38.69, "elapsed_time": "2:46:04", "remaining_time": "4:23:08", "throughput": 1489.81, "total_tokens": 14845600} {"current_steps": 70350, "total_steps": 181800, "loss": 0.021, "lr": 3.847234283482658e-05, "epoch": 7.739273927392739, "percentage": 38.7, "elapsed_time": "2:46:05", "remaining_time": "4:23:07", "throughput": 1489.81, "total_tokens": 14846624} {"current_steps": 70355, "total_steps": 181800, "loss": 0.0204, "lr": 3.847032101864898e-05, "epoch": 7.7398239823982395, "percentage": 38.7, "elapsed_time": "2:46:06", "remaining_time": "4:23:06", "throughput": 1489.82, "total_tokens": 14847712} {"current_steps": 70360, "total_steps": 181800, "loss": 0.051, "lr": 3.84682990783219e-05, "epoch": 7.740374037403741, "percentage": 38.7, "elapsed_time": "2:46:06", "remaining_time": "4:23:06", "throughput": 1489.81, "total_tokens": 14848736} {"current_steps": 70365, "total_steps": 181800, "loss": 0.0125, "lr": 3.846627701386397e-05, "epoch": 7.740924092409241, "percentage": 38.7, "elapsed_time": "2:46:07", "remaining_time": "4:23:05", "throughput": 1489.82, "total_tokens": 14849792} {"current_steps": 70370, "total_steps": 181800, "loss": 0.0654, "lr": 3.846425482529383e-05, "epoch": 7.741474147414742, "percentage": 38.71, "elapsed_time": "2:46:08", "remaining_time": "4:23:04", "throughput": 1489.82, "total_tokens": 14850848} {"current_steps": 70375, "total_steps": 181800, "loss": 0.0078, "lr": 3.8462232512630106e-05, "epoch": 7.742024202420242, "percentage": 38.71, "elapsed_time": "2:46:08", "remaining_time": "4:23:03", "throughput": 1489.82, "total_tokens": 14851904} {"current_steps": 70380, "total_steps": 181800, "loss": 0.0609, "lr": 3.846021007589146e-05, "epoch": 7.742574257425742, "percentage": 38.71, "elapsed_time": "2:46:09", "remaining_time": "4:23:03", "throughput": 1489.82, "total_tokens": 14852928} {"current_steps": 70385, "total_steps": 181800, "loss": 0.0778, "lr": 3.84581875150965e-05, "epoch": 7.743124312431243, "percentage": 38.72, "elapsed_time": "2:46:10", "remaining_time": "4:23:02", "throughput": 1489.83, "total_tokens": 14853984} {"current_steps": 70390, "total_steps": 181800, "loss": 0.04, "lr": 3.8456164830263885e-05, "epoch": 7.743674367436744, "percentage": 38.72, "elapsed_time": "2:46:10", "remaining_time": "4:23:01", "throughput": 1489.82, "total_tokens": 14854944} {"current_steps": 70395, "total_steps": 181800, "loss": 0.094, "lr": 3.8454142021412264e-05, "epoch": 7.744224422442244, "percentage": 38.72, "elapsed_time": "2:46:11", "remaining_time": "4:23:00", "throughput": 1489.82, "total_tokens": 14856000} {"current_steps": 70400, "total_steps": 181800, "loss": 0.0096, "lr": 3.8452119088560265e-05, "epoch": 7.744774477447745, "percentage": 38.72, "elapsed_time": "2:46:12", "remaining_time": "4:23:00", "throughput": 1489.82, "total_tokens": 14857056} {"current_steps": 70405, "total_steps": 181800, "loss": 0.0371, "lr": 3.845009603172654e-05, "epoch": 7.745324532453245, "percentage": 38.73, "elapsed_time": "2:46:13", "remaining_time": "4:22:59", "throughput": 1489.83, "total_tokens": 14858176} {"current_steps": 70410, "total_steps": 181800, "loss": 0.0101, "lr": 3.844807285092974e-05, "epoch": 7.745874587458746, "percentage": 38.73, "elapsed_time": "2:46:13", "remaining_time": "4:22:58", "throughput": 1489.83, "total_tokens": 14859200} {"current_steps": 70415, "total_steps": 181800, "loss": 0.0208, "lr": 3.84460495461885e-05, "epoch": 7.7464246424642464, "percentage": 38.73, "elapsed_time": "2:46:14", "remaining_time": "4:22:57", "throughput": 1489.84, "total_tokens": 14860288} {"current_steps": 70420, "total_steps": 181800, "loss": 0.0125, "lr": 3.844402611752147e-05, "epoch": 7.746974697469747, "percentage": 38.73, "elapsed_time": "2:46:15", "remaining_time": "4:22:57", "throughput": 1489.84, "total_tokens": 14861344} {"current_steps": 70425, "total_steps": 181800, "loss": 0.0109, "lr": 3.844200256494731e-05, "epoch": 7.747524752475248, "percentage": 38.74, "elapsed_time": "2:46:15", "remaining_time": "4:22:56", "throughput": 1489.83, "total_tokens": 14862304} {"current_steps": 70430, "total_steps": 181800, "loss": 0.0042, "lr": 3.8439978888484664e-05, "epoch": 7.748074807480748, "percentage": 38.74, "elapsed_time": "2:46:16", "remaining_time": "4:22:55", "throughput": 1489.84, "total_tokens": 14863392} {"current_steps": 70435, "total_steps": 181800, "loss": 0.0653, "lr": 3.843795508815218e-05, "epoch": 7.748624862486249, "percentage": 38.74, "elapsed_time": "2:46:17", "remaining_time": "4:22:54", "throughput": 1489.84, "total_tokens": 14864384} {"current_steps": 70440, "total_steps": 181800, "loss": 0.0668, "lr": 3.843593116396851e-05, "epoch": 7.749174917491749, "percentage": 38.75, "elapsed_time": "2:46:17", "remaining_time": "4:22:54", "throughput": 1489.84, "total_tokens": 14865472} {"current_steps": 70445, "total_steps": 181800, "loss": 0.0736, "lr": 3.84339071159523e-05, "epoch": 7.7497249724972495, "percentage": 38.75, "elapsed_time": "2:46:18", "remaining_time": "4:22:53", "throughput": 1489.84, "total_tokens": 14866496} {"current_steps": 70450, "total_steps": 181800, "loss": 0.0077, "lr": 3.843188294412223e-05, "epoch": 7.7502750275027505, "percentage": 38.75, "elapsed_time": "2:46:19", "remaining_time": "4:22:52", "throughput": 1489.84, "total_tokens": 14867456} {"current_steps": 70455, "total_steps": 181800, "loss": 0.0028, "lr": 3.842985864849693e-05, "epoch": 7.750825082508251, "percentage": 38.75, "elapsed_time": "2:46:19", "remaining_time": "4:22:52", "throughput": 1489.84, "total_tokens": 14868480} {"current_steps": 70460, "total_steps": 181800, "loss": 0.1155, "lr": 3.8427834229095075e-05, "epoch": 7.751375137513751, "percentage": 38.76, "elapsed_time": "2:46:20", "remaining_time": "4:22:51", "throughput": 1489.84, "total_tokens": 14869536} {"current_steps": 70465, "total_steps": 181800, "loss": 0.0503, "lr": 3.842580968593531e-05, "epoch": 7.751925192519252, "percentage": 38.76, "elapsed_time": "2:46:21", "remaining_time": "4:22:50", "throughput": 1489.84, "total_tokens": 14870624} {"current_steps": 70470, "total_steps": 181800, "loss": 0.0129, "lr": 3.8423785019036295e-05, "epoch": 7.752475247524752, "percentage": 38.76, "elapsed_time": "2:46:22", "remaining_time": "4:22:49", "throughput": 1489.85, "total_tokens": 14871680} {"current_steps": 70475, "total_steps": 181800, "loss": 0.0472, "lr": 3.84217602284167e-05, "epoch": 7.753025302530253, "percentage": 38.77, "elapsed_time": "2:46:22", "remaining_time": "4:22:49", "throughput": 1489.84, "total_tokens": 14872672} {"current_steps": 70480, "total_steps": 181800, "loss": 0.0275, "lr": 3.841973531409518e-05, "epoch": 7.7535753575357536, "percentage": 38.77, "elapsed_time": "2:46:23", "remaining_time": "4:22:48", "throughput": 1489.85, "total_tokens": 14873728} {"current_steps": 70485, "total_steps": 181800, "loss": 0.0216, "lr": 3.8417710276090407e-05, "epoch": 7.754125412541254, "percentage": 38.77, "elapsed_time": "2:46:24", "remaining_time": "4:22:47", "throughput": 1489.85, "total_tokens": 14874816} {"current_steps": 70490, "total_steps": 181800, "loss": 0.0034, "lr": 3.841568511442103e-05, "epoch": 7.754675467546755, "percentage": 38.77, "elapsed_time": "2:46:24", "remaining_time": "4:22:46", "throughput": 1489.85, "total_tokens": 14875872} {"current_steps": 70495, "total_steps": 181800, "loss": 0.0187, "lr": 3.841365982910572e-05, "epoch": 7.755225522552255, "percentage": 38.78, "elapsed_time": "2:46:25", "remaining_time": "4:22:46", "throughput": 1489.85, "total_tokens": 14876896} {"current_steps": 70500, "total_steps": 181800, "loss": 0.0874, "lr": 3.841163442016315e-05, "epoch": 7.755775577557756, "percentage": 38.78, "elapsed_time": "2:46:26", "remaining_time": "4:22:45", "throughput": 1489.85, "total_tokens": 14877888} {"current_steps": 70505, "total_steps": 181800, "loss": 0.0782, "lr": 3.840960888761197e-05, "epoch": 7.756325632563256, "percentage": 38.78, "elapsed_time": "2:46:26", "remaining_time": "4:22:44", "throughput": 1489.85, "total_tokens": 14878912} {"current_steps": 70510, "total_steps": 181800, "loss": 0.0502, "lr": 3.840758323147087e-05, "epoch": 7.756875687568757, "percentage": 38.78, "elapsed_time": "2:46:27", "remaining_time": "4:22:43", "throughput": 1489.85, "total_tokens": 14879968} {"current_steps": 70515, "total_steps": 181800, "loss": 0.0081, "lr": 3.84055574517585e-05, "epoch": 7.757425742574258, "percentage": 38.79, "elapsed_time": "2:46:28", "remaining_time": "4:22:43", "throughput": 1489.85, "total_tokens": 14880960} {"current_steps": 70520, "total_steps": 181800, "loss": 0.0377, "lr": 3.8403531548493546e-05, "epoch": 7.757975797579758, "percentage": 38.79, "elapsed_time": "2:46:28", "remaining_time": "4:22:42", "throughput": 1489.85, "total_tokens": 14882048} {"current_steps": 70525, "total_steps": 181800, "loss": 0.0729, "lr": 3.8401505521694675e-05, "epoch": 7.758525852585258, "percentage": 38.79, "elapsed_time": "2:46:29", "remaining_time": "4:22:41", "throughput": 1489.86, "total_tokens": 14883104} {"current_steps": 70530, "total_steps": 181800, "loss": 0.004, "lr": 3.839947937138055e-05, "epoch": 7.759075907590759, "percentage": 38.8, "elapsed_time": "2:46:30", "remaining_time": "4:22:40", "throughput": 1489.86, "total_tokens": 14884128} {"current_steps": 70535, "total_steps": 181800, "loss": 0.0084, "lr": 3.839745309756986e-05, "epoch": 7.759625962596259, "percentage": 38.8, "elapsed_time": "2:46:30", "remaining_time": "4:22:40", "throughput": 1489.86, "total_tokens": 14885184} {"current_steps": 70540, "total_steps": 181800, "loss": 0.0708, "lr": 3.839542670028127e-05, "epoch": 7.7601760176017605, "percentage": 38.8, "elapsed_time": "2:46:31", "remaining_time": "4:22:39", "throughput": 1489.86, "total_tokens": 14886240} {"current_steps": 70545, "total_steps": 181800, "loss": 0.0442, "lr": 3.839340017953347e-05, "epoch": 7.760726072607261, "percentage": 38.8, "elapsed_time": "2:46:32", "remaining_time": "4:22:38", "throughput": 1489.87, "total_tokens": 14887296} {"current_steps": 70550, "total_steps": 181800, "loss": 0.1019, "lr": 3.839137353534511e-05, "epoch": 7.761276127612762, "percentage": 38.81, "elapsed_time": "2:46:33", "remaining_time": "4:22:38", "throughput": 1489.87, "total_tokens": 14888352} {"current_steps": 70555, "total_steps": 181800, "loss": 0.0044, "lr": 3.83893467677349e-05, "epoch": 7.761826182618262, "percentage": 38.81, "elapsed_time": "2:46:33", "remaining_time": "4:22:37", "throughput": 1489.87, "total_tokens": 14889376} {"current_steps": 70560, "total_steps": 181800, "loss": 0.144, "lr": 3.8387319876721496e-05, "epoch": 7.762376237623762, "percentage": 38.81, "elapsed_time": "2:46:34", "remaining_time": "4:22:36", "throughput": 1489.87, "total_tokens": 14890400} {"current_steps": 70565, "total_steps": 181800, "loss": 0.0412, "lr": 3.838529286232359e-05, "epoch": 7.762926292629263, "percentage": 38.81, "elapsed_time": "2:46:35", "remaining_time": "4:22:35", "throughput": 1489.87, "total_tokens": 14891456} {"current_steps": 70570, "total_steps": 181800, "loss": 0.0107, "lr": 3.838326572455987e-05, "epoch": 7.7634763476347635, "percentage": 38.82, "elapsed_time": "2:46:35", "remaining_time": "4:22:35", "throughput": 1489.87, "total_tokens": 14892512} {"current_steps": 70575, "total_steps": 181800, "loss": 0.0567, "lr": 3.838123846344901e-05, "epoch": 7.764026402640264, "percentage": 38.82, "elapsed_time": "2:46:36", "remaining_time": "4:22:34", "throughput": 1489.88, "total_tokens": 14893568} {"current_steps": 70580, "total_steps": 181800, "loss": 0.0305, "lr": 3.837921107900969e-05, "epoch": 7.764576457645765, "percentage": 38.82, "elapsed_time": "2:46:37", "remaining_time": "4:22:33", "throughput": 1489.88, "total_tokens": 14894624} {"current_steps": 70585, "total_steps": 181800, "loss": 0.0601, "lr": 3.8377183571260605e-05, "epoch": 7.765126512651265, "percentage": 38.83, "elapsed_time": "2:46:37", "remaining_time": "4:22:32", "throughput": 1489.88, "total_tokens": 14895648} {"current_steps": 70590, "total_steps": 181800, "loss": 0.0061, "lr": 3.8375155940220444e-05, "epoch": 7.765676567656766, "percentage": 38.83, "elapsed_time": "2:46:38", "remaining_time": "4:22:32", "throughput": 1489.88, "total_tokens": 14896736} {"current_steps": 70595, "total_steps": 181800, "loss": 0.0646, "lr": 3.837312818590788e-05, "epoch": 7.766226622662266, "percentage": 38.83, "elapsed_time": "2:46:39", "remaining_time": "4:22:31", "throughput": 1489.89, "total_tokens": 14897792} {"current_steps": 70600, "total_steps": 181800, "loss": 0.0389, "lr": 3.837110030834161e-05, "epoch": 7.7667766776677665, "percentage": 38.83, "elapsed_time": "2:46:39", "remaining_time": "4:22:30", "throughput": 1489.89, "total_tokens": 14898816} {"current_steps": 70605, "total_steps": 181800, "loss": 0.1157, "lr": 3.836907230754033e-05, "epoch": 7.767326732673268, "percentage": 38.84, "elapsed_time": "2:46:40", "remaining_time": "4:22:29", "throughput": 1489.89, "total_tokens": 14899872} {"current_steps": 70610, "total_steps": 181800, "loss": 0.0691, "lr": 3.836704418352271e-05, "epoch": 7.767876787678768, "percentage": 38.84, "elapsed_time": "2:46:41", "remaining_time": "4:22:29", "throughput": 1489.89, "total_tokens": 14900864} {"current_steps": 70615, "total_steps": 181800, "loss": 0.015, "lr": 3.836501593630748e-05, "epoch": 7.768426842684269, "percentage": 38.84, "elapsed_time": "2:46:42", "remaining_time": "4:22:28", "throughput": 1489.89, "total_tokens": 14901920} {"current_steps": 70620, "total_steps": 181800, "loss": 0.0372, "lr": 3.83629875659133e-05, "epoch": 7.768976897689769, "percentage": 38.84, "elapsed_time": "2:46:42", "remaining_time": "4:22:27", "throughput": 1489.89, "total_tokens": 14902944} {"current_steps": 70625, "total_steps": 181800, "loss": 0.0444, "lr": 3.836095907235888e-05, "epoch": 7.769526952695269, "percentage": 38.85, "elapsed_time": "2:46:43", "remaining_time": "4:22:26", "throughput": 1489.89, "total_tokens": 14904000} {"current_steps": 70630, "total_steps": 181800, "loss": 0.0036, "lr": 3.835893045566291e-05, "epoch": 7.77007700770077, "percentage": 38.85, "elapsed_time": "2:46:44", "remaining_time": "4:22:26", "throughput": 1489.9, "total_tokens": 14905088} {"current_steps": 70635, "total_steps": 181800, "loss": 0.0065, "lr": 3.835690171584409e-05, "epoch": 7.770627062706271, "percentage": 38.85, "elapsed_time": "2:46:44", "remaining_time": "4:22:25", "throughput": 1489.9, "total_tokens": 14906176} {"current_steps": 70640, "total_steps": 181800, "loss": 0.004, "lr": 3.835487285292112e-05, "epoch": 7.771177117711771, "percentage": 38.86, "elapsed_time": "2:46:45", "remaining_time": "4:22:24", "throughput": 1489.9, "total_tokens": 14907168} {"current_steps": 70645, "total_steps": 181800, "loss": 0.1176, "lr": 3.835284386691268e-05, "epoch": 7.771727172717272, "percentage": 38.86, "elapsed_time": "2:46:46", "remaining_time": "4:22:24", "throughput": 1489.91, "total_tokens": 14908288} {"current_steps": 70650, "total_steps": 181800, "loss": 0.042, "lr": 3.8350814757837495e-05, "epoch": 7.772277227722772, "percentage": 38.86, "elapsed_time": "2:46:46", "remaining_time": "4:22:23", "throughput": 1489.92, "total_tokens": 14909408} {"current_steps": 70655, "total_steps": 181800, "loss": 0.0225, "lr": 3.834878552571426e-05, "epoch": 7.772827282728273, "percentage": 38.86, "elapsed_time": "2:46:47", "remaining_time": "4:22:22", "throughput": 1489.91, "total_tokens": 14910400} {"current_steps": 70660, "total_steps": 181800, "loss": 0.0685, "lr": 3.834675617056167e-05, "epoch": 7.773377337733773, "percentage": 38.87, "elapsed_time": "2:46:48", "remaining_time": "4:22:21", "throughput": 1489.92, "total_tokens": 14911456} {"current_steps": 70665, "total_steps": 181800, "loss": 0.0102, "lr": 3.834472669239843e-05, "epoch": 7.773927392739274, "percentage": 38.87, "elapsed_time": "2:46:48", "remaining_time": "4:22:21", "throughput": 1489.92, "total_tokens": 14912480} {"current_steps": 70670, "total_steps": 181800, "loss": 0.0496, "lr": 3.834269709124325e-05, "epoch": 7.774477447744775, "percentage": 38.87, "elapsed_time": "2:46:49", "remaining_time": "4:22:20", "throughput": 1489.92, "total_tokens": 14913536} {"current_steps": 70675, "total_steps": 181800, "loss": 0.0735, "lr": 3.834066736711484e-05, "epoch": 7.775027502750275, "percentage": 38.88, "elapsed_time": "2:46:50", "remaining_time": "4:22:19", "throughput": 1489.92, "total_tokens": 14914592} {"current_steps": 70680, "total_steps": 181800, "loss": 0.0537, "lr": 3.833863752003189e-05, "epoch": 7.775577557755776, "percentage": 38.88, "elapsed_time": "2:46:50", "remaining_time": "4:22:18", "throughput": 1489.92, "total_tokens": 14915616} {"current_steps": 70685, "total_steps": 181800, "loss": 0.0381, "lr": 3.833660755001313e-05, "epoch": 7.776127612761276, "percentage": 38.88, "elapsed_time": "2:46:51", "remaining_time": "4:22:18", "throughput": 1489.92, "total_tokens": 14916640} {"current_steps": 70690, "total_steps": 181800, "loss": 0.0064, "lr": 3.833457745707725e-05, "epoch": 7.776677667766776, "percentage": 38.88, "elapsed_time": "2:46:52", "remaining_time": "4:22:17", "throughput": 1489.92, "total_tokens": 14917664} {"current_steps": 70695, "total_steps": 181800, "loss": 0.0065, "lr": 3.833254724124297e-05, "epoch": 7.7772277227722775, "percentage": 38.89, "elapsed_time": "2:46:53", "remaining_time": "4:22:16", "throughput": 1489.93, "total_tokens": 14918752} {"current_steps": 70700, "total_steps": 181800, "loss": 0.0425, "lr": 3.833051690252899e-05, "epoch": 7.777777777777778, "percentage": 38.89, "elapsed_time": "2:46:53", "remaining_time": "4:22:15", "throughput": 1489.92, "total_tokens": 14919744} {"current_steps": 70705, "total_steps": 181800, "loss": 0.0871, "lr": 3.832848644095405e-05, "epoch": 7.778327832783278, "percentage": 38.89, "elapsed_time": "2:46:54", "remaining_time": "4:22:15", "throughput": 1489.93, "total_tokens": 14920800} {"current_steps": 70710, "total_steps": 181800, "loss": 0.0118, "lr": 3.832645585653682e-05, "epoch": 7.778877887788779, "percentage": 38.89, "elapsed_time": "2:46:55", "remaining_time": "4:22:14", "throughput": 1489.93, "total_tokens": 14921856} {"current_steps": 70715, "total_steps": 181800, "loss": 0.0299, "lr": 3.832442514929607e-05, "epoch": 7.779427942794279, "percentage": 38.9, "elapsed_time": "2:46:55", "remaining_time": "4:22:13", "throughput": 1489.93, "total_tokens": 14922880} {"current_steps": 70720, "total_steps": 181800, "loss": 0.0451, "lr": 3.832239431925047e-05, "epoch": 7.77997799779978, "percentage": 38.9, "elapsed_time": "2:46:56", "remaining_time": "4:22:12", "throughput": 1489.92, "total_tokens": 14923840} {"current_steps": 70725, "total_steps": 181800, "loss": 0.0069, "lr": 3.832036336641877e-05, "epoch": 7.7805280528052805, "percentage": 38.9, "elapsed_time": "2:46:57", "remaining_time": "4:22:12", "throughput": 1489.93, "total_tokens": 14924896} {"current_steps": 70730, "total_steps": 181800, "loss": 0.0221, "lr": 3.831833229081966e-05, "epoch": 7.781078107810782, "percentage": 38.91, "elapsed_time": "2:46:57", "remaining_time": "4:22:11", "throughput": 1489.93, "total_tokens": 14925984} {"current_steps": 70735, "total_steps": 181800, "loss": 0.0091, "lr": 3.8316301092471875e-05, "epoch": 7.781628162816282, "percentage": 38.91, "elapsed_time": "2:46:58", "remaining_time": "4:22:10", "throughput": 1489.93, "total_tokens": 14927040} {"current_steps": 70740, "total_steps": 181800, "loss": 0.0203, "lr": 3.831426977139413e-05, "epoch": 7.782178217821782, "percentage": 38.91, "elapsed_time": "2:46:59", "remaining_time": "4:22:10", "throughput": 1489.93, "total_tokens": 14928064} {"current_steps": 70745, "total_steps": 181800, "loss": 0.0857, "lr": 3.831223832760515e-05, "epoch": 7.782728272827283, "percentage": 38.91, "elapsed_time": "2:46:59", "remaining_time": "4:22:09", "throughput": 1489.94, "total_tokens": 14929120} {"current_steps": 70750, "total_steps": 181800, "loss": 0.0366, "lr": 3.8310206761123655e-05, "epoch": 7.783278327832783, "percentage": 38.92, "elapsed_time": "2:47:00", "remaining_time": "4:22:08", "throughput": 1489.94, "total_tokens": 14930176} {"current_steps": 70755, "total_steps": 181800, "loss": 0.0111, "lr": 3.830817507196837e-05, "epoch": 7.7838283828382835, "percentage": 38.92, "elapsed_time": "2:47:01", "remaining_time": "4:22:07", "throughput": 1489.94, "total_tokens": 14931232} {"current_steps": 70760, "total_steps": 181800, "loss": 0.0778, "lr": 3.830614326015803e-05, "epoch": 7.784378437843785, "percentage": 38.92, "elapsed_time": "2:47:02", "remaining_time": "4:22:07", "throughput": 1489.94, "total_tokens": 14932256} {"current_steps": 70765, "total_steps": 181800, "loss": 0.0064, "lr": 3.830411132571135e-05, "epoch": 7.784928492849285, "percentage": 38.92, "elapsed_time": "2:47:02", "remaining_time": "4:22:06", "throughput": 1489.94, "total_tokens": 14933280} {"current_steps": 70770, "total_steps": 181800, "loss": 0.0113, "lr": 3.830207926864705e-05, "epoch": 7.785478547854785, "percentage": 38.93, "elapsed_time": "2:47:03", "remaining_time": "4:22:05", "throughput": 1489.95, "total_tokens": 14934368} {"current_steps": 70775, "total_steps": 181800, "loss": 0.01, "lr": 3.830004708898388e-05, "epoch": 7.786028602860286, "percentage": 38.93, "elapsed_time": "2:47:04", "remaining_time": "4:22:04", "throughput": 1489.96, "total_tokens": 14935488} {"current_steps": 70780, "total_steps": 181800, "loss": 0.0073, "lr": 3.8298014786740556e-05, "epoch": 7.786578657865786, "percentage": 38.93, "elapsed_time": "2:47:04", "remaining_time": "4:22:04", "throughput": 1489.96, "total_tokens": 14936512} {"current_steps": 70785, "total_steps": 181800, "loss": 0.0056, "lr": 3.8295982361935814e-05, "epoch": 7.787128712871287, "percentage": 38.94, "elapsed_time": "2:47:05", "remaining_time": "4:22:03", "throughput": 1489.95, "total_tokens": 14937504} {"current_steps": 70790, "total_steps": 181800, "loss": 0.0227, "lr": 3.829394981458837e-05, "epoch": 7.787678767876788, "percentage": 38.94, "elapsed_time": "2:47:06", "remaining_time": "4:22:02", "throughput": 1489.96, "total_tokens": 14938624} {"current_steps": 70795, "total_steps": 181800, "loss": 0.0096, "lr": 3.829191714471698e-05, "epoch": 7.788228822882289, "percentage": 38.94, "elapsed_time": "2:47:06", "remaining_time": "4:22:01", "throughput": 1489.97, "total_tokens": 14939712} {"current_steps": 70800, "total_steps": 181800, "loss": 0.0132, "lr": 3.828988435234036e-05, "epoch": 7.788778877887789, "percentage": 38.94, "elapsed_time": "2:47:07", "remaining_time": "4:22:01", "throughput": 1489.98, "total_tokens": 14940800} {"current_steps": 70805, "total_steps": 181800, "loss": 0.01, "lr": 3.828785143747726e-05, "epoch": 7.789328932893289, "percentage": 38.95, "elapsed_time": "2:47:08", "remaining_time": "4:22:00", "throughput": 1489.98, "total_tokens": 14941888} {"current_steps": 70810, "total_steps": 181800, "loss": 0.0271, "lr": 3.828581840014641e-05, "epoch": 7.78987898789879, "percentage": 38.95, "elapsed_time": "2:47:08", "remaining_time": "4:21:59", "throughput": 1489.98, "total_tokens": 14942912} {"current_steps": 70815, "total_steps": 181800, "loss": 0.008, "lr": 3.8283785240366544e-05, "epoch": 7.79042904290429, "percentage": 38.95, "elapsed_time": "2:47:09", "remaining_time": "4:21:58", "throughput": 1489.98, "total_tokens": 14943936} {"current_steps": 70820, "total_steps": 181800, "loss": 0.1141, "lr": 3.82817519581564e-05, "epoch": 7.790979097909791, "percentage": 38.95, "elapsed_time": "2:47:10", "remaining_time": "4:21:58", "throughput": 1489.99, "total_tokens": 14944992} {"current_steps": 70825, "total_steps": 181800, "loss": 0.0488, "lr": 3.8279718553534725e-05, "epoch": 7.791529152915292, "percentage": 38.96, "elapsed_time": "2:47:10", "remaining_time": "4:21:57", "throughput": 1489.99, "total_tokens": 14946080} {"current_steps": 70830, "total_steps": 181800, "loss": 0.1162, "lr": 3.827768502652026e-05, "epoch": 7.792079207920792, "percentage": 38.96, "elapsed_time": "2:47:11", "remaining_time": "4:21:56", "throughput": 1490.0, "total_tokens": 14947168} {"current_steps": 70835, "total_steps": 181800, "loss": 0.0386, "lr": 3.827565137713174e-05, "epoch": 7.792629262926293, "percentage": 38.96, "elapsed_time": "2:47:12", "remaining_time": "4:21:55", "throughput": 1490.0, "total_tokens": 14948224} {"current_steps": 70840, "total_steps": 181800, "loss": 0.0719, "lr": 3.827361760538791e-05, "epoch": 7.793179317931793, "percentage": 38.97, "elapsed_time": "2:47:13", "remaining_time": "4:21:55", "throughput": 1490.0, "total_tokens": 14949248} {"current_steps": 70845, "total_steps": 181800, "loss": 0.0427, "lr": 3.827158371130752e-05, "epoch": 7.793729372937293, "percentage": 38.97, "elapsed_time": "2:47:13", "remaining_time": "4:21:54", "throughput": 1490.01, "total_tokens": 14950336} {"current_steps": 70850, "total_steps": 181800, "loss": 0.0073, "lr": 3.8269549694909304e-05, "epoch": 7.7942794279427945, "percentage": 38.97, "elapsed_time": "2:47:14", "remaining_time": "4:21:53", "throughput": 1490.01, "total_tokens": 14951360} {"current_steps": 70855, "total_steps": 181800, "loss": 0.0303, "lr": 3.826751555621202e-05, "epoch": 7.794829482948295, "percentage": 38.97, "elapsed_time": "2:47:15", "remaining_time": "4:21:53", "throughput": 1490.01, "total_tokens": 14952384} {"current_steps": 70860, "total_steps": 181800, "loss": 0.019, "lr": 3.826548129523442e-05, "epoch": 7.795379537953796, "percentage": 38.98, "elapsed_time": "2:47:15", "remaining_time": "4:21:52", "throughput": 1490.01, "total_tokens": 14953440} {"current_steps": 70865, "total_steps": 181800, "loss": 0.1221, "lr": 3.8263446911995234e-05, "epoch": 7.795929592959296, "percentage": 38.98, "elapsed_time": "2:47:16", "remaining_time": "4:21:51", "throughput": 1490.01, "total_tokens": 14954528} {"current_steps": 70870, "total_steps": 181800, "loss": 0.0145, "lr": 3.826141240651322e-05, "epoch": 7.796479647964796, "percentage": 38.98, "elapsed_time": "2:47:17", "remaining_time": "4:21:50", "throughput": 1490.02, "total_tokens": 14955584} {"current_steps": 70875, "total_steps": 181800, "loss": 0.0302, "lr": 3.825937777880714e-05, "epoch": 7.797029702970297, "percentage": 38.99, "elapsed_time": "2:47:17", "remaining_time": "4:21:50", "throughput": 1490.03, "total_tokens": 14956736} {"current_steps": 70880, "total_steps": 181800, "loss": 0.0492, "lr": 3.825734302889573e-05, "epoch": 7.7975797579757975, "percentage": 38.99, "elapsed_time": "2:47:18", "remaining_time": "4:21:49", "throughput": 1490.03, "total_tokens": 14957760} {"current_steps": 70885, "total_steps": 181800, "loss": 0.0228, "lr": 3.825530815679775e-05, "epoch": 7.798129812981298, "percentage": 38.99, "elapsed_time": "2:47:19", "remaining_time": "4:21:48", "throughput": 1490.04, "total_tokens": 14958848} {"current_steps": 70890, "total_steps": 181800, "loss": 0.0098, "lr": 3.825327316253196e-05, "epoch": 7.798679867986799, "percentage": 38.99, "elapsed_time": "2:47:19", "remaining_time": "4:21:47", "throughput": 1490.03, "total_tokens": 14959840} {"current_steps": 70895, "total_steps": 181800, "loss": 0.0899, "lr": 3.825123804611711e-05, "epoch": 7.799229922992299, "percentage": 39.0, "elapsed_time": "2:47:20", "remaining_time": "4:21:47", "throughput": 1490.04, "total_tokens": 14960928} {"current_steps": 70900, "total_steps": 181800, "loss": 0.0089, "lr": 3.824920280757196e-05, "epoch": 7.7997799779978, "percentage": 39.0, "elapsed_time": "2:47:21", "remaining_time": "4:21:46", "throughput": 1490.04, "total_tokens": 14961952} {"current_steps": 70905, "total_steps": 181800, "loss": 0.071, "lr": 3.824716744691527e-05, "epoch": 7.8003300330033, "percentage": 39.0, "elapsed_time": "2:47:22", "remaining_time": "4:21:45", "throughput": 1490.05, "total_tokens": 14963104} {"current_steps": 70910, "total_steps": 181800, "loss": 0.1976, "lr": 3.824513196416578e-05, "epoch": 7.8008800880088005, "percentage": 39.0, "elapsed_time": "2:47:22", "remaining_time": "4:21:44", "throughput": 1490.05, "total_tokens": 14964096} {"current_steps": 70915, "total_steps": 181800, "loss": 0.0595, "lr": 3.8243096359342265e-05, "epoch": 7.801430143014302, "percentage": 39.01, "elapsed_time": "2:47:23", "remaining_time": "4:21:44", "throughput": 1490.05, "total_tokens": 14965152} {"current_steps": 70920, "total_steps": 181800, "loss": 0.0889, "lr": 3.82410606324635e-05, "epoch": 7.801980198019802, "percentage": 39.01, "elapsed_time": "2:47:24", "remaining_time": "4:21:43", "throughput": 1490.05, "total_tokens": 14966176} {"current_steps": 70925, "total_steps": 181800, "loss": 0.0481, "lr": 3.8239024783548224e-05, "epoch": 7.802530253025303, "percentage": 39.01, "elapsed_time": "2:47:24", "remaining_time": "4:21:42", "throughput": 1490.06, "total_tokens": 14967264} {"current_steps": 70930, "total_steps": 181800, "loss": 0.0218, "lr": 3.823698881261521e-05, "epoch": 7.803080308030803, "percentage": 39.02, "elapsed_time": "2:47:25", "remaining_time": "4:21:41", "throughput": 1490.06, "total_tokens": 14968352} {"current_steps": 70935, "total_steps": 181800, "loss": 0.0617, "lr": 3.823495271968322e-05, "epoch": 7.803630363036303, "percentage": 39.02, "elapsed_time": "2:47:26", "remaining_time": "4:21:41", "throughput": 1490.07, "total_tokens": 14969408} {"current_steps": 70940, "total_steps": 181800, "loss": 0.025, "lr": 3.8232916504771024e-05, "epoch": 7.804180418041804, "percentage": 39.02, "elapsed_time": "2:47:26", "remaining_time": "4:21:40", "throughput": 1490.07, "total_tokens": 14970432} {"current_steps": 70945, "total_steps": 181800, "loss": 0.0485, "lr": 3.823088016789738e-05, "epoch": 7.804730473047305, "percentage": 39.02, "elapsed_time": "2:47:27", "remaining_time": "4:21:39", "throughput": 1490.07, "total_tokens": 14971520} {"current_steps": 70950, "total_steps": 181800, "loss": 0.0489, "lr": 3.8228843709081075e-05, "epoch": 7.805280528052805, "percentage": 39.03, "elapsed_time": "2:47:28", "remaining_time": "4:21:38", "throughput": 1490.08, "total_tokens": 14972576} {"current_steps": 70955, "total_steps": 181800, "loss": 0.0921, "lr": 3.822680712834086e-05, "epoch": 7.805830583058306, "percentage": 39.03, "elapsed_time": "2:47:28", "remaining_time": "4:21:38", "throughput": 1490.07, "total_tokens": 14973568} {"current_steps": 70960, "total_steps": 181800, "loss": 0.0068, "lr": 3.822477042569551e-05, "epoch": 7.806380638063806, "percentage": 39.03, "elapsed_time": "2:47:29", "remaining_time": "4:21:37", "throughput": 1490.08, "total_tokens": 14974656} {"current_steps": 70965, "total_steps": 181800, "loss": 0.0669, "lr": 3.822273360116379e-05, "epoch": 7.806930693069307, "percentage": 39.03, "elapsed_time": "2:47:30", "remaining_time": "4:21:36", "throughput": 1490.08, "total_tokens": 14975680} {"current_steps": 70970, "total_steps": 181800, "loss": 0.0499, "lr": 3.8220696654764485e-05, "epoch": 7.807480748074807, "percentage": 39.04, "elapsed_time": "2:47:30", "remaining_time": "4:21:36", "throughput": 1490.08, "total_tokens": 14976768} {"current_steps": 70975, "total_steps": 181800, "loss": 0.0135, "lr": 3.8218659586516365e-05, "epoch": 7.8080308030803085, "percentage": 39.04, "elapsed_time": "2:47:31", "remaining_time": "4:21:35", "throughput": 1490.09, "total_tokens": 14977856} {"current_steps": 70980, "total_steps": 181800, "loss": 0.0216, "lr": 3.82166223964382e-05, "epoch": 7.808580858085809, "percentage": 39.04, "elapsed_time": "2:47:32", "remaining_time": "4:21:34", "throughput": 1490.09, "total_tokens": 14978944} {"current_steps": 70985, "total_steps": 181800, "loss": 0.0858, "lr": 3.8214585084548766e-05, "epoch": 7.809130913091309, "percentage": 39.05, "elapsed_time": "2:47:33", "remaining_time": "4:21:33", "throughput": 1490.09, "total_tokens": 14979936} {"current_steps": 70990, "total_steps": 181800, "loss": 0.0199, "lr": 3.821254765086685e-05, "epoch": 7.80968096809681, "percentage": 39.05, "elapsed_time": "2:47:33", "remaining_time": "4:21:33", "throughput": 1490.09, "total_tokens": 14980992} {"current_steps": 70995, "total_steps": 181800, "loss": 0.0538, "lr": 3.821051009541121e-05, "epoch": 7.81023102310231, "percentage": 39.05, "elapsed_time": "2:47:34", "remaining_time": "4:21:32", "throughput": 1490.1, "total_tokens": 14982080} {"current_steps": 71000, "total_steps": 181800, "loss": 0.0076, "lr": 3.8208472418200646e-05, "epoch": 7.81078107810781, "percentage": 39.05, "elapsed_time": "2:47:35", "remaining_time": "4:21:31", "throughput": 1490.11, "total_tokens": 14983168} {"current_steps": 71005, "total_steps": 181800, "loss": 0.0213, "lr": 3.820643461925393e-05, "epoch": 7.8113311331133115, "percentage": 39.06, "elapsed_time": "2:47:35", "remaining_time": "4:21:30", "throughput": 1490.11, "total_tokens": 14984256} {"current_steps": 71010, "total_steps": 181800, "loss": 0.1015, "lr": 3.820439669858984e-05, "epoch": 7.811881188118812, "percentage": 39.06, "elapsed_time": "2:47:36", "remaining_time": "4:21:30", "throughput": 1490.12, "total_tokens": 14985312} {"current_steps": 71015, "total_steps": 181800, "loss": 0.0459, "lr": 3.8202358656227165e-05, "epoch": 7.812431243124313, "percentage": 39.06, "elapsed_time": "2:47:37", "remaining_time": "4:21:29", "throughput": 1490.12, "total_tokens": 14986336} {"current_steps": 71020, "total_steps": 181800, "loss": 0.0778, "lr": 3.8200320492184685e-05, "epoch": 7.812981298129813, "percentage": 39.06, "elapsed_time": "2:47:37", "remaining_time": "4:21:28", "throughput": 1490.13, "total_tokens": 14987456} {"current_steps": 71025, "total_steps": 181800, "loss": 0.0047, "lr": 3.819828220648118e-05, "epoch": 7.813531353135313, "percentage": 39.07, "elapsed_time": "2:47:38", "remaining_time": "4:21:27", "throughput": 1490.14, "total_tokens": 14988608} {"current_steps": 71030, "total_steps": 181800, "loss": 0.015, "lr": 3.8196243799135446e-05, "epoch": 7.814081408140814, "percentage": 39.07, "elapsed_time": "2:47:39", "remaining_time": "4:21:27", "throughput": 1490.14, "total_tokens": 14989664} {"current_steps": 71035, "total_steps": 181800, "loss": 0.0037, "lr": 3.819420527016626e-05, "epoch": 7.8146314631463145, "percentage": 39.07, "elapsed_time": "2:47:39", "remaining_time": "4:21:26", "throughput": 1490.14, "total_tokens": 14990688} {"current_steps": 71040, "total_steps": 181800, "loss": 0.0305, "lr": 3.819216661959243e-05, "epoch": 7.815181518151816, "percentage": 39.08, "elapsed_time": "2:47:40", "remaining_time": "4:21:25", "throughput": 1490.14, "total_tokens": 14991712} {"current_steps": 71045, "total_steps": 181800, "loss": 0.1136, "lr": 3.819012784743272e-05, "epoch": 7.815731573157316, "percentage": 39.08, "elapsed_time": "2:47:41", "remaining_time": "4:21:24", "throughput": 1490.15, "total_tokens": 14992800} {"current_steps": 71050, "total_steps": 181800, "loss": 0.0167, "lr": 3.818808895370593e-05, "epoch": 7.816281628162816, "percentage": 39.08, "elapsed_time": "2:47:41", "remaining_time": "4:21:24", "throughput": 1490.15, "total_tokens": 14993824} {"current_steps": 71055, "total_steps": 181800, "loss": 0.0106, "lr": 3.818604993843085e-05, "epoch": 7.816831683168317, "percentage": 39.08, "elapsed_time": "2:47:42", "remaining_time": "4:21:23", "throughput": 1490.15, "total_tokens": 14994912} {"current_steps": 71060, "total_steps": 181800, "loss": 0.0775, "lr": 3.8184010801626275e-05, "epoch": 7.817381738173817, "percentage": 39.09, "elapsed_time": "2:47:43", "remaining_time": "4:21:22", "throughput": 1490.15, "total_tokens": 14995968} {"current_steps": 71065, "total_steps": 181800, "loss": 0.115, "lr": 3.8181971543311004e-05, "epoch": 7.8179317931793175, "percentage": 39.09, "elapsed_time": "2:47:44", "remaining_time": "4:21:22", "throughput": 1490.16, "total_tokens": 14997024} {"current_steps": 71070, "total_steps": 181800, "loss": 0.005, "lr": 3.8179932163503825e-05, "epoch": 7.818481848184819, "percentage": 39.09, "elapsed_time": "2:47:44", "remaining_time": "4:21:21", "throughput": 1490.16, "total_tokens": 14998048} {"current_steps": 71075, "total_steps": 181800, "loss": 0.1229, "lr": 3.8177892662223535e-05, "epoch": 7.819031903190319, "percentage": 39.1, "elapsed_time": "2:47:45", "remaining_time": "4:21:20", "throughput": 1490.16, "total_tokens": 14999136} {"current_steps": 71080, "total_steps": 181800, "loss": 0.1494, "lr": 3.8175853039488926e-05, "epoch": 7.81958195819582, "percentage": 39.1, "elapsed_time": "2:47:46", "remaining_time": "4:21:19", "throughput": 1490.16, "total_tokens": 15000160} {"current_steps": 71085, "total_steps": 181800, "loss": 0.002, "lr": 3.817381329531881e-05, "epoch": 7.82013201320132, "percentage": 39.1, "elapsed_time": "2:47:46", "remaining_time": "4:21:19", "throughput": 1490.16, "total_tokens": 15001216} {"current_steps": 71090, "total_steps": 181800, "loss": 0.0139, "lr": 3.817177342973197e-05, "epoch": 7.82068206820682, "percentage": 39.1, "elapsed_time": "2:47:47", "remaining_time": "4:21:18", "throughput": 1490.17, "total_tokens": 15002304} {"current_steps": 71095, "total_steps": 181800, "loss": 0.051, "lr": 3.816973344274723e-05, "epoch": 7.821232123212321, "percentage": 39.11, "elapsed_time": "2:47:48", "remaining_time": "4:21:17", "throughput": 1490.17, "total_tokens": 15003360} {"current_steps": 71100, "total_steps": 181800, "loss": 0.1163, "lr": 3.816769333438336e-05, "epoch": 7.821782178217822, "percentage": 39.11, "elapsed_time": "2:47:48", "remaining_time": "4:21:16", "throughput": 1490.18, "total_tokens": 15004416} {"current_steps": 71105, "total_steps": 181800, "loss": 0.0133, "lr": 3.8165653104659185e-05, "epoch": 7.822332233223323, "percentage": 39.11, "elapsed_time": "2:47:49", "remaining_time": "4:21:16", "throughput": 1490.18, "total_tokens": 15005472} {"current_steps": 71110, "total_steps": 181800, "loss": 0.0599, "lr": 3.816361275359351e-05, "epoch": 7.822882288228823, "percentage": 39.11, "elapsed_time": "2:47:50", "remaining_time": "4:21:15", "throughput": 1490.18, "total_tokens": 15006560} {"current_steps": 71115, "total_steps": 181800, "loss": 0.008, "lr": 3.816157228120513e-05, "epoch": 7.823432343234323, "percentage": 39.12, "elapsed_time": "2:47:50", "remaining_time": "4:21:14", "throughput": 1490.19, "total_tokens": 15007648} {"current_steps": 71120, "total_steps": 181800, "loss": 0.0552, "lr": 3.815953168751284e-05, "epoch": 7.823982398239824, "percentage": 39.12, "elapsed_time": "2:47:51", "remaining_time": "4:21:13", "throughput": 1490.19, "total_tokens": 15008672} {"current_steps": 71125, "total_steps": 181800, "loss": 0.1067, "lr": 3.815749097253548e-05, "epoch": 7.824532453245324, "percentage": 39.12, "elapsed_time": "2:47:52", "remaining_time": "4:21:13", "throughput": 1490.2, "total_tokens": 15009760} {"current_steps": 71130, "total_steps": 181800, "loss": 0.0067, "lr": 3.8155450136291824e-05, "epoch": 7.825082508250825, "percentage": 39.13, "elapsed_time": "2:47:53", "remaining_time": "4:21:12", "throughput": 1490.2, "total_tokens": 15010816} {"current_steps": 71135, "total_steps": 181800, "loss": 0.0231, "lr": 3.8153409178800704e-05, "epoch": 7.825632563256326, "percentage": 39.13, "elapsed_time": "2:47:53", "remaining_time": "4:21:11", "throughput": 1490.2, "total_tokens": 15011872} {"current_steps": 71140, "total_steps": 181800, "loss": 0.0112, "lr": 3.815136810008093e-05, "epoch": 7.826182618261826, "percentage": 39.13, "elapsed_time": "2:47:54", "remaining_time": "4:21:10", "throughput": 1490.2, "total_tokens": 15012928} {"current_steps": 71145, "total_steps": 181800, "loss": 0.0792, "lr": 3.814932690015129e-05, "epoch": 7.826732673267327, "percentage": 39.13, "elapsed_time": "2:47:55", "remaining_time": "4:21:10", "throughput": 1490.2, "total_tokens": 15013952} {"current_steps": 71150, "total_steps": 181800, "loss": 0.0227, "lr": 3.8147285579030624e-05, "epoch": 7.827282728272827, "percentage": 39.14, "elapsed_time": "2:47:55", "remaining_time": "4:21:09", "throughput": 1490.21, "total_tokens": 15015008} {"current_steps": 71155, "total_steps": 181800, "loss": 0.02, "lr": 3.814524413673774e-05, "epoch": 7.827832783278328, "percentage": 39.14, "elapsed_time": "2:47:56", "remaining_time": "4:21:08", "throughput": 1490.21, "total_tokens": 15016032} {"current_steps": 71160, "total_steps": 181800, "loss": 0.0184, "lr": 3.814320257329144e-05, "epoch": 7.8283828382838285, "percentage": 39.14, "elapsed_time": "2:47:57", "remaining_time": "4:21:08", "throughput": 1490.21, "total_tokens": 15017120} {"current_steps": 71165, "total_steps": 181800, "loss": 0.049, "lr": 3.814116088871055e-05, "epoch": 7.828932893289329, "percentage": 39.14, "elapsed_time": "2:47:57", "remaining_time": "4:21:07", "throughput": 1490.21, "total_tokens": 15018176} {"current_steps": 71170, "total_steps": 181800, "loss": 0.0338, "lr": 3.813911908301389e-05, "epoch": 7.82948294829483, "percentage": 39.15, "elapsed_time": "2:47:58", "remaining_time": "4:21:06", "throughput": 1490.22, "total_tokens": 15019232} {"current_steps": 71175, "total_steps": 181800, "loss": 0.08, "lr": 3.813707715622027e-05, "epoch": 7.83003300330033, "percentage": 39.15, "elapsed_time": "2:47:59", "remaining_time": "4:21:05", "throughput": 1490.22, "total_tokens": 15020288} {"current_steps": 71180, "total_steps": 181800, "loss": 0.0274, "lr": 3.813503510834851e-05, "epoch": 7.83058305830583, "percentage": 39.15, "elapsed_time": "2:47:59", "remaining_time": "4:21:05", "throughput": 1490.22, "total_tokens": 15021344} {"current_steps": 71185, "total_steps": 181800, "loss": 0.0218, "lr": 3.813299293941744e-05, "epoch": 7.831133113311331, "percentage": 39.16, "elapsed_time": "2:48:00", "remaining_time": "4:21:04", "throughput": 1490.22, "total_tokens": 15022368} {"current_steps": 71190, "total_steps": 181800, "loss": 0.0021, "lr": 3.813095064944588e-05, "epoch": 7.8316831683168315, "percentage": 39.16, "elapsed_time": "2:48:01", "remaining_time": "4:21:03", "throughput": 1490.23, "total_tokens": 15023456} {"current_steps": 71195, "total_steps": 181800, "loss": 0.0506, "lr": 3.8128908238452645e-05, "epoch": 7.832233223322332, "percentage": 39.16, "elapsed_time": "2:48:02", "remaining_time": "4:21:02", "throughput": 1490.23, "total_tokens": 15024512} {"current_steps": 71200, "total_steps": 181800, "loss": 0.0904, "lr": 3.812686570645656e-05, "epoch": 7.832783278327833, "percentage": 39.16, "elapsed_time": "2:48:02", "remaining_time": "4:21:02", "throughput": 1490.24, "total_tokens": 15025600} {"current_steps": 71205, "total_steps": 181800, "loss": 0.1071, "lr": 3.812482305347646e-05, "epoch": 7.833333333333333, "percentage": 39.17, "elapsed_time": "2:48:03", "remaining_time": "4:21:01", "throughput": 1490.24, "total_tokens": 15026688} {"current_steps": 71210, "total_steps": 181800, "loss": 0.0161, "lr": 3.812278027953115e-05, "epoch": 7.833883388338834, "percentage": 39.17, "elapsed_time": "2:48:04", "remaining_time": "4:21:00", "throughput": 1490.24, "total_tokens": 15027680} {"current_steps": 71215, "total_steps": 181800, "loss": 0.0042, "lr": 3.812073738463948e-05, "epoch": 7.834433443344334, "percentage": 39.17, "elapsed_time": "2:48:04", "remaining_time": "4:20:59", "throughput": 1490.25, "total_tokens": 15028832} {"current_steps": 71220, "total_steps": 181800, "loss": 0.0363, "lr": 3.8118694368820265e-05, "epoch": 7.834983498349835, "percentage": 39.17, "elapsed_time": "2:48:05", "remaining_time": "4:20:59", "throughput": 1490.25, "total_tokens": 15029856} {"current_steps": 71225, "total_steps": 181800, "loss": 0.0475, "lr": 3.811665123209235e-05, "epoch": 7.835533553355336, "percentage": 39.18, "elapsed_time": "2:48:06", "remaining_time": "4:20:58", "throughput": 1490.25, "total_tokens": 15030880} {"current_steps": 71230, "total_steps": 181800, "loss": 0.0526, "lr": 3.8114607974474545e-05, "epoch": 7.836083608360836, "percentage": 39.18, "elapsed_time": "2:48:06", "remaining_time": "4:20:57", "throughput": 1490.25, "total_tokens": 15031936} {"current_steps": 71235, "total_steps": 181800, "loss": 0.017, "lr": 3.81125645959857e-05, "epoch": 7.836633663366337, "percentage": 39.18, "elapsed_time": "2:48:07", "remaining_time": "4:20:57", "throughput": 1490.25, "total_tokens": 15032960} {"current_steps": 71240, "total_steps": 181800, "loss": 0.0523, "lr": 3.811052109664463e-05, "epoch": 7.837183718371837, "percentage": 39.19, "elapsed_time": "2:48:08", "remaining_time": "4:20:56", "throughput": 1490.26, "total_tokens": 15034016} {"current_steps": 71245, "total_steps": 181800, "loss": 0.0829, "lr": 3.8108477476470175e-05, "epoch": 7.837733773377337, "percentage": 39.19, "elapsed_time": "2:48:08", "remaining_time": "4:20:55", "throughput": 1490.26, "total_tokens": 15035072} {"current_steps": 71250, "total_steps": 181800, "loss": 0.0476, "lr": 3.8106433735481177e-05, "epoch": 7.838283828382838, "percentage": 39.19, "elapsed_time": "2:48:09", "remaining_time": "4:20:54", "throughput": 1490.26, "total_tokens": 15036160} {"current_steps": 71255, "total_steps": 181800, "loss": 0.0443, "lr": 3.810438987369647e-05, "epoch": 7.838833883388339, "percentage": 39.19, "elapsed_time": "2:48:10", "remaining_time": "4:20:54", "throughput": 1490.27, "total_tokens": 15037216} {"current_steps": 71260, "total_steps": 181800, "loss": 0.0421, "lr": 3.8102345891134896e-05, "epoch": 7.83938393839384, "percentage": 39.2, "elapsed_time": "2:48:10", "remaining_time": "4:20:53", "throughput": 1490.26, "total_tokens": 15038176} {"current_steps": 71265, "total_steps": 181800, "loss": 0.0386, "lr": 3.8100301787815276e-05, "epoch": 7.83993399339934, "percentage": 39.2, "elapsed_time": "2:48:11", "remaining_time": "4:20:52", "throughput": 1490.27, "total_tokens": 15039264} {"current_steps": 71270, "total_steps": 181800, "loss": 0.0619, "lr": 3.809825756375647e-05, "epoch": 7.84048404840484, "percentage": 39.2, "elapsed_time": "2:48:12", "remaining_time": "4:20:51", "throughput": 1490.27, "total_tokens": 15040320} {"current_steps": 71275, "total_steps": 181800, "loss": 0.0268, "lr": 3.809621321897731e-05, "epoch": 7.841034103410341, "percentage": 39.21, "elapsed_time": "2:48:13", "remaining_time": "4:20:51", "throughput": 1490.27, "total_tokens": 15041344} {"current_steps": 71280, "total_steps": 181800, "loss": 0.0501, "lr": 3.8094168753496614e-05, "epoch": 7.841584158415841, "percentage": 39.21, "elapsed_time": "2:48:13", "remaining_time": "4:20:50", "throughput": 1490.28, "total_tokens": 15042464} {"current_steps": 71285, "total_steps": 181800, "loss": 0.0403, "lr": 3.8092124167333276e-05, "epoch": 7.8421342134213425, "percentage": 39.21, "elapsed_time": "2:48:14", "remaining_time": "4:20:49", "throughput": 1490.28, "total_tokens": 15043552} {"current_steps": 71290, "total_steps": 181800, "loss": 0.0135, "lr": 3.80900794605061e-05, "epoch": 7.842684268426843, "percentage": 39.21, "elapsed_time": "2:48:15", "remaining_time": "4:20:48", "throughput": 1490.28, "total_tokens": 15044544} {"current_steps": 71295, "total_steps": 181800, "loss": 0.1218, "lr": 3.808803463303394e-05, "epoch": 7.843234323432343, "percentage": 39.22, "elapsed_time": "2:48:15", "remaining_time": "4:20:48", "throughput": 1490.29, "total_tokens": 15045664} {"current_steps": 71300, "total_steps": 181800, "loss": 0.0626, "lr": 3.808598968493565e-05, "epoch": 7.843784378437844, "percentage": 39.22, "elapsed_time": "2:48:16", "remaining_time": "4:20:47", "throughput": 1490.3, "total_tokens": 15046848} {"current_steps": 71305, "total_steps": 181800, "loss": 0.0086, "lr": 3.808394461623007e-05, "epoch": 7.844334433443344, "percentage": 39.22, "elapsed_time": "2:48:17", "remaining_time": "4:20:46", "throughput": 1490.31, "total_tokens": 15047968} {"current_steps": 71310, "total_steps": 181800, "loss": 0.0136, "lr": 3.808189942693606e-05, "epoch": 7.8448844884488445, "percentage": 39.22, "elapsed_time": "2:48:17", "remaining_time": "4:20:45", "throughput": 1490.31, "total_tokens": 15049024} {"current_steps": 71315, "total_steps": 181800, "loss": 0.0188, "lr": 3.807985411707245e-05, "epoch": 7.8454345434543455, "percentage": 39.23, "elapsed_time": "2:48:18", "remaining_time": "4:20:45", "throughput": 1490.32, "total_tokens": 15050080} {"current_steps": 71320, "total_steps": 181800, "loss": 0.0116, "lr": 3.80778086866581e-05, "epoch": 7.845984598459846, "percentage": 39.23, "elapsed_time": "2:48:19", "remaining_time": "4:20:44", "throughput": 1490.31, "total_tokens": 15051072} {"current_steps": 71325, "total_steps": 181800, "loss": 0.0261, "lr": 3.807576313571187e-05, "epoch": 7.846534653465347, "percentage": 39.23, "elapsed_time": "2:48:19", "remaining_time": "4:20:43", "throughput": 1490.31, "total_tokens": 15052064} {"current_steps": 71330, "total_steps": 181800, "loss": 0.0413, "lr": 3.80737174642526e-05, "epoch": 7.847084708470847, "percentage": 39.24, "elapsed_time": "2:48:20", "remaining_time": "4:20:43", "throughput": 1490.31, "total_tokens": 15053120} {"current_steps": 71335, "total_steps": 181800, "loss": 0.1791, "lr": 3.807167167229915e-05, "epoch": 7.847634763476347, "percentage": 39.24, "elapsed_time": "2:48:21", "remaining_time": "4:20:42", "throughput": 1490.32, "total_tokens": 15054208} {"current_steps": 71340, "total_steps": 181800, "loss": 0.0195, "lr": 3.806962575987038e-05, "epoch": 7.848184818481848, "percentage": 39.24, "elapsed_time": "2:48:22", "remaining_time": "4:20:41", "throughput": 1490.31, "total_tokens": 15055200} {"current_steps": 71345, "total_steps": 181800, "loss": 0.0079, "lr": 3.806757972698513e-05, "epoch": 7.8487348734873486, "percentage": 39.24, "elapsed_time": "2:48:22", "remaining_time": "4:20:40", "throughput": 1490.32, "total_tokens": 15056256} {"current_steps": 71350, "total_steps": 181800, "loss": 0.0341, "lr": 3.806553357366227e-05, "epoch": 7.84928492849285, "percentage": 39.25, "elapsed_time": "2:48:23", "remaining_time": "4:20:40", "throughput": 1490.32, "total_tokens": 15057280} {"current_steps": 71355, "total_steps": 181800, "loss": 0.0396, "lr": 3.806348729992067e-05, "epoch": 7.84983498349835, "percentage": 39.25, "elapsed_time": "2:48:24", "remaining_time": "4:20:39", "throughput": 1490.32, "total_tokens": 15058336} {"current_steps": 71360, "total_steps": 181800, "loss": 0.0497, "lr": 3.8061440905779165e-05, "epoch": 7.85038503850385, "percentage": 39.25, "elapsed_time": "2:48:24", "remaining_time": "4:20:38", "throughput": 1490.33, "total_tokens": 15059424} {"current_steps": 71365, "total_steps": 181800, "loss": 0.0149, "lr": 3.805939439125663e-05, "epoch": 7.850935093509351, "percentage": 39.25, "elapsed_time": "2:48:25", "remaining_time": "4:20:37", "throughput": 1490.33, "total_tokens": 15060512} {"current_steps": 71370, "total_steps": 181800, "loss": 0.09, "lr": 3.805734775637192e-05, "epoch": 7.851485148514851, "percentage": 39.26, "elapsed_time": "2:48:26", "remaining_time": "4:20:37", "throughput": 1490.34, "total_tokens": 15061632} {"current_steps": 71375, "total_steps": 181800, "loss": 0.0562, "lr": 3.8055301001143905e-05, "epoch": 7.852035203520352, "percentage": 39.26, "elapsed_time": "2:48:26", "remaining_time": "4:20:36", "throughput": 1490.35, "total_tokens": 15062720} {"current_steps": 71380, "total_steps": 181800, "loss": 0.0543, "lr": 3.805325412559144e-05, "epoch": 7.852585258525853, "percentage": 39.26, "elapsed_time": "2:48:27", "remaining_time": "4:20:35", "throughput": 1490.35, "total_tokens": 15063776} {"current_steps": 71385, "total_steps": 181800, "loss": 0.0288, "lr": 3.80512071297334e-05, "epoch": 7.853135313531353, "percentage": 39.27, "elapsed_time": "2:48:28", "remaining_time": "4:20:34", "throughput": 1490.36, "total_tokens": 15064864} {"current_steps": 71390, "total_steps": 181800, "loss": 0.0031, "lr": 3.804916001358865e-05, "epoch": 7.853685368536854, "percentage": 39.27, "elapsed_time": "2:48:28", "remaining_time": "4:20:34", "throughput": 1490.36, "total_tokens": 15065920} {"current_steps": 71395, "total_steps": 181800, "loss": 0.0184, "lr": 3.804711277717604e-05, "epoch": 7.854235423542354, "percentage": 39.27, "elapsed_time": "2:48:29", "remaining_time": "4:20:33", "throughput": 1490.37, "total_tokens": 15067008} {"current_steps": 71400, "total_steps": 181800, "loss": 0.0771, "lr": 3.8045065420514464e-05, "epoch": 7.854785478547855, "percentage": 39.27, "elapsed_time": "2:48:30", "remaining_time": "4:20:32", "throughput": 1490.36, "total_tokens": 15068032} {"current_steps": 71405, "total_steps": 181800, "loss": 0.0469, "lr": 3.804301794362278e-05, "epoch": 7.8553355335533555, "percentage": 39.28, "elapsed_time": "2:48:30", "remaining_time": "4:20:32", "throughput": 1490.37, "total_tokens": 15069120} {"current_steps": 71410, "total_steps": 181800, "loss": 0.021, "lr": 3.804097034651985e-05, "epoch": 7.855885588558856, "percentage": 39.28, "elapsed_time": "2:48:31", "remaining_time": "4:20:31", "throughput": 1490.37, "total_tokens": 15070176} {"current_steps": 71415, "total_steps": 181800, "loss": 0.0523, "lr": 3.8038922629224564e-05, "epoch": 7.856435643564357, "percentage": 39.28, "elapsed_time": "2:48:32", "remaining_time": "4:20:30", "throughput": 1490.37, "total_tokens": 15071200} {"current_steps": 71420, "total_steps": 181800, "loss": 0.026, "lr": 3.8036874791755784e-05, "epoch": 7.856985698569857, "percentage": 39.28, "elapsed_time": "2:48:33", "remaining_time": "4:20:29", "throughput": 1490.37, "total_tokens": 15072256} {"current_steps": 71425, "total_steps": 181800, "loss": 0.0235, "lr": 3.803482683413237e-05, "epoch": 7.857535753575357, "percentage": 39.29, "elapsed_time": "2:48:33", "remaining_time": "4:20:29", "throughput": 1490.37, "total_tokens": 15073280} {"current_steps": 71430, "total_steps": 181800, "loss": 0.0361, "lr": 3.8032778756373235e-05, "epoch": 7.858085808580858, "percentage": 39.29, "elapsed_time": "2:48:34", "remaining_time": "4:20:28", "throughput": 1490.38, "total_tokens": 15074368} {"current_steps": 71435, "total_steps": 181800, "loss": 0.0596, "lr": 3.803073055849721e-05, "epoch": 7.8586358635863585, "percentage": 39.29, "elapsed_time": "2:48:35", "remaining_time": "4:20:27", "throughput": 1490.38, "total_tokens": 15075424} {"current_steps": 71440, "total_steps": 181800, "loss": 0.0424, "lr": 3.8028682240523206e-05, "epoch": 7.8591859185918596, "percentage": 39.3, "elapsed_time": "2:48:35", "remaining_time": "4:20:26", "throughput": 1490.39, "total_tokens": 15076480} {"current_steps": 71445, "total_steps": 181800, "loss": 0.0096, "lr": 3.802663380247009e-05, "epoch": 7.85973597359736, "percentage": 39.3, "elapsed_time": "2:48:36", "remaining_time": "4:20:26", "throughput": 1490.39, "total_tokens": 15077536} {"current_steps": 71450, "total_steps": 181800, "loss": 0.0179, "lr": 3.8024585244356734e-05, "epoch": 7.86028602860286, "percentage": 39.3, "elapsed_time": "2:48:37", "remaining_time": "4:20:25", "throughput": 1490.39, "total_tokens": 15078592} {"current_steps": 71455, "total_steps": 181800, "loss": 0.0037, "lr": 3.8022536566202036e-05, "epoch": 7.860836083608361, "percentage": 39.3, "elapsed_time": "2:48:37", "remaining_time": "4:20:24", "throughput": 1490.39, "total_tokens": 15079616} {"current_steps": 71460, "total_steps": 181800, "loss": 0.0046, "lr": 3.802048776802486e-05, "epoch": 7.861386138613861, "percentage": 39.31, "elapsed_time": "2:48:38", "remaining_time": "4:20:23", "throughput": 1490.39, "total_tokens": 15080672} {"current_steps": 71465, "total_steps": 181800, "loss": 0.0693, "lr": 3.801843884984409e-05, "epoch": 7.861936193619362, "percentage": 39.31, "elapsed_time": "2:48:39", "remaining_time": "4:20:23", "throughput": 1490.39, "total_tokens": 15081664} {"current_steps": 71470, "total_steps": 181800, "loss": 0.0091, "lr": 3.801638981167862e-05, "epoch": 7.862486248624863, "percentage": 39.31, "elapsed_time": "2:48:39", "remaining_time": "4:20:22", "throughput": 1490.39, "total_tokens": 15082720} {"current_steps": 71475, "total_steps": 181800, "loss": 0.0065, "lr": 3.801434065354734e-05, "epoch": 7.863036303630363, "percentage": 39.32, "elapsed_time": "2:48:40", "remaining_time": "4:20:21", "throughput": 1490.39, "total_tokens": 15083744} {"current_steps": 71480, "total_steps": 181800, "loss": 0.0575, "lr": 3.801229137546912e-05, "epoch": 7.863586358635864, "percentage": 39.32, "elapsed_time": "2:48:41", "remaining_time": "4:20:20", "throughput": 1490.39, "total_tokens": 15084768} {"current_steps": 71485, "total_steps": 181800, "loss": 0.0084, "lr": 3.801024197746286e-05, "epoch": 7.864136413641364, "percentage": 39.32, "elapsed_time": "2:48:42", "remaining_time": "4:20:20", "throughput": 1490.39, "total_tokens": 15085792} {"current_steps": 71490, "total_steps": 181800, "loss": 0.0527, "lr": 3.800819245954744e-05, "epoch": 7.864686468646864, "percentage": 39.32, "elapsed_time": "2:48:42", "remaining_time": "4:20:19", "throughput": 1490.4, "total_tokens": 15086848} {"current_steps": 71495, "total_steps": 181800, "loss": 0.01, "lr": 3.800614282174174e-05, "epoch": 7.865236523652365, "percentage": 39.33, "elapsed_time": "2:48:43", "remaining_time": "4:20:18", "throughput": 1490.4, "total_tokens": 15087936} {"current_steps": 71500, "total_steps": 181800, "loss": 0.1243, "lr": 3.8004093064064685e-05, "epoch": 7.865786578657866, "percentage": 39.33, "elapsed_time": "2:48:44", "remaining_time": "4:20:17", "throughput": 1490.41, "total_tokens": 15088992} {"current_steps": 71505, "total_steps": 181800, "loss": 0.0071, "lr": 3.800204318653513e-05, "epoch": 7.866336633663367, "percentage": 39.33, "elapsed_time": "2:48:44", "remaining_time": "4:20:17", "throughput": 1490.41, "total_tokens": 15090048} {"current_steps": 71510, "total_steps": 181800, "loss": 0.0173, "lr": 3.799999318917198e-05, "epoch": 7.866886688668867, "percentage": 39.33, "elapsed_time": "2:48:45", "remaining_time": "4:20:16", "throughput": 1490.41, "total_tokens": 15091104} {"current_steps": 71515, "total_steps": 181800, "loss": 0.0295, "lr": 3.7997943071994136e-05, "epoch": 7.867436743674367, "percentage": 39.34, "elapsed_time": "2:48:46", "remaining_time": "4:20:15", "throughput": 1490.43, "total_tokens": 15092288} {"current_steps": 71520, "total_steps": 181800, "loss": 0.0079, "lr": 3.7995892835020487e-05, "epoch": 7.867986798679868, "percentage": 39.34, "elapsed_time": "2:48:46", "remaining_time": "4:20:15", "throughput": 1490.43, "total_tokens": 15093312} {"current_steps": 71525, "total_steps": 181800, "loss": 0.0183, "lr": 3.799384247826993e-05, "epoch": 7.868536853685368, "percentage": 39.34, "elapsed_time": "2:48:47", "remaining_time": "4:20:14", "throughput": 1490.43, "total_tokens": 15094400} {"current_steps": 71530, "total_steps": 181800, "loss": 0.1029, "lr": 3.7991792001761363e-05, "epoch": 7.8690869086908695, "percentage": 39.35, "elapsed_time": "2:48:48", "remaining_time": "4:20:13", "throughput": 1490.43, "total_tokens": 15095456} {"current_steps": 71535, "total_steps": 181800, "loss": 0.0479, "lr": 3.798974140551368e-05, "epoch": 7.86963696369637, "percentage": 39.35, "elapsed_time": "2:48:48", "remaining_time": "4:20:12", "throughput": 1490.44, "total_tokens": 15096544} {"current_steps": 71540, "total_steps": 181800, "loss": 0.0918, "lr": 3.798769068954577e-05, "epoch": 7.87018701870187, "percentage": 39.35, "elapsed_time": "2:48:49", "remaining_time": "4:20:12", "throughput": 1490.44, "total_tokens": 15097536} {"current_steps": 71545, "total_steps": 181800, "loss": 0.0054, "lr": 3.798563985387658e-05, "epoch": 7.870737073707371, "percentage": 39.35, "elapsed_time": "2:48:50", "remaining_time": "4:20:11", "throughput": 1490.44, "total_tokens": 15098624} {"current_steps": 71550, "total_steps": 181800, "loss": 0.0963, "lr": 3.7983588898524955e-05, "epoch": 7.871287128712871, "percentage": 39.36, "elapsed_time": "2:48:50", "remaining_time": "4:20:10", "throughput": 1490.45, "total_tokens": 15099744} {"current_steps": 71555, "total_steps": 181800, "loss": 0.0797, "lr": 3.798153782350982e-05, "epoch": 7.871837183718371, "percentage": 39.36, "elapsed_time": "2:48:51", "remaining_time": "4:20:09", "throughput": 1490.45, "total_tokens": 15100768} {"current_steps": 71560, "total_steps": 181800, "loss": 0.0589, "lr": 3.7979486628850094e-05, "epoch": 7.8723872387238725, "percentage": 39.36, "elapsed_time": "2:48:52", "remaining_time": "4:20:09", "throughput": 1490.46, "total_tokens": 15101888} {"current_steps": 71565, "total_steps": 181800, "loss": 0.1165, "lr": 3.797743531456466e-05, "epoch": 7.872937293729373, "percentage": 39.36, "elapsed_time": "2:48:53", "remaining_time": "4:20:08", "throughput": 1490.46, "total_tokens": 15102912} {"current_steps": 71570, "total_steps": 181800, "loss": 0.0036, "lr": 3.797538388067243e-05, "epoch": 7.873487348734874, "percentage": 39.37, "elapsed_time": "2:48:53", "remaining_time": "4:20:07", "throughput": 1490.46, "total_tokens": 15103904} {"current_steps": 71575, "total_steps": 181800, "loss": 0.0722, "lr": 3.797333232719231e-05, "epoch": 7.874037403740374, "percentage": 39.37, "elapsed_time": "2:48:54", "remaining_time": "4:20:06", "throughput": 1490.46, "total_tokens": 15104928} {"current_steps": 71580, "total_steps": 181800, "loss": 0.0075, "lr": 3.797128065414323e-05, "epoch": 7.874587458745875, "percentage": 39.37, "elapsed_time": "2:48:55", "remaining_time": "4:20:06", "throughput": 1490.47, "total_tokens": 15106048} {"current_steps": 71585, "total_steps": 181800, "loss": 0.0041, "lr": 3.796922886154406e-05, "epoch": 7.875137513751375, "percentage": 39.38, "elapsed_time": "2:48:55", "remaining_time": "4:20:05", "throughput": 1490.47, "total_tokens": 15107072} {"current_steps": 71590, "total_steps": 181800, "loss": 0.037, "lr": 3.796717694941374e-05, "epoch": 7.8756875687568755, "percentage": 39.38, "elapsed_time": "2:48:56", "remaining_time": "4:20:04", "throughput": 1490.47, "total_tokens": 15108096} {"current_steps": 71595, "total_steps": 181800, "loss": 0.0104, "lr": 3.796512491777117e-05, "epoch": 7.876237623762377, "percentage": 39.38, "elapsed_time": "2:48:57", "remaining_time": "4:20:03", "throughput": 1490.47, "total_tokens": 15109152} {"current_steps": 71600, "total_steps": 181800, "loss": 0.0785, "lr": 3.796307276663526e-05, "epoch": 7.876787678767877, "percentage": 39.38, "elapsed_time": "2:48:57", "remaining_time": "4:20:03", "throughput": 1490.48, "total_tokens": 15110272} {"current_steps": 71605, "total_steps": 181800, "loss": 0.0533, "lr": 3.796102049602493e-05, "epoch": 7.877337733773377, "percentage": 39.39, "elapsed_time": "2:48:58", "remaining_time": "4:20:02", "throughput": 1490.48, "total_tokens": 15111264} {"current_steps": 71610, "total_steps": 181800, "loss": 0.0056, "lr": 3.79589681059591e-05, "epoch": 7.877887788778878, "percentage": 39.39, "elapsed_time": "2:48:59", "remaining_time": "4:20:01", "throughput": 1490.48, "total_tokens": 15112352} {"current_steps": 71615, "total_steps": 181800, "loss": 0.0232, "lr": 3.795691559645668e-05, "epoch": 7.878437843784378, "percentage": 39.39, "elapsed_time": "2:48:59", "remaining_time": "4:20:01", "throughput": 1490.48, "total_tokens": 15113408} {"current_steps": 71620, "total_steps": 181800, "loss": 0.0712, "lr": 3.7954862967536585e-05, "epoch": 7.878987898789879, "percentage": 39.39, "elapsed_time": "2:49:00", "remaining_time": "4:20:00", "throughput": 1490.48, "total_tokens": 15114400} {"current_steps": 71625, "total_steps": 181800, "loss": 0.0065, "lr": 3.7952810219217725e-05, "epoch": 7.87953795379538, "percentage": 39.4, "elapsed_time": "2:49:01", "remaining_time": "4:19:59", "throughput": 1490.49, "total_tokens": 15115488} {"current_steps": 71630, "total_steps": 181800, "loss": 0.105, "lr": 3.795075735151904e-05, "epoch": 7.88008800880088, "percentage": 39.4, "elapsed_time": "2:49:02", "remaining_time": "4:19:58", "throughput": 1490.49, "total_tokens": 15116544} {"current_steps": 71635, "total_steps": 181800, "loss": 0.1259, "lr": 3.794870436445943e-05, "epoch": 7.880638063806381, "percentage": 39.4, "elapsed_time": "2:49:02", "remaining_time": "4:19:58", "throughput": 1490.49, "total_tokens": 15117600} {"current_steps": 71640, "total_steps": 181800, "loss": 0.042, "lr": 3.794665125805783e-05, "epoch": 7.881188118811881, "percentage": 39.41, "elapsed_time": "2:49:03", "remaining_time": "4:19:57", "throughput": 1490.5, "total_tokens": 15118720} {"current_steps": 71645, "total_steps": 181800, "loss": 0.0598, "lr": 3.794459803233316e-05, "epoch": 7.881738173817382, "percentage": 39.41, "elapsed_time": "2:49:04", "remaining_time": "4:19:56", "throughput": 1490.51, "total_tokens": 15119808} {"current_steps": 71650, "total_steps": 181800, "loss": 0.1572, "lr": 3.794254468730434e-05, "epoch": 7.882288228822882, "percentage": 39.41, "elapsed_time": "2:49:04", "remaining_time": "4:19:55", "throughput": 1490.51, "total_tokens": 15120864} {"current_steps": 71655, "total_steps": 181800, "loss": 0.0136, "lr": 3.7940491222990296e-05, "epoch": 7.882838283828383, "percentage": 39.41, "elapsed_time": "2:49:05", "remaining_time": "4:19:55", "throughput": 1490.51, "total_tokens": 15121920} {"current_steps": 71660, "total_steps": 181800, "loss": 0.0614, "lr": 3.793843763940995e-05, "epoch": 7.883388338833884, "percentage": 39.42, "elapsed_time": "2:49:06", "remaining_time": "4:19:54", "throughput": 1490.51, "total_tokens": 15122944} {"current_steps": 71665, "total_steps": 181800, "loss": 0.1263, "lr": 3.7936383936582245e-05, "epoch": 7.883938393839384, "percentage": 39.42, "elapsed_time": "2:49:06", "remaining_time": "4:19:53", "throughput": 1490.52, "total_tokens": 15124032} {"current_steps": 71670, "total_steps": 181800, "loss": 0.0306, "lr": 3.7934330114526074e-05, "epoch": 7.884488448844884, "percentage": 39.42, "elapsed_time": "2:49:07", "remaining_time": "4:19:52", "throughput": 1490.51, "total_tokens": 15125056} {"current_steps": 71675, "total_steps": 181800, "loss": 0.1684, "lr": 3.79322761732604e-05, "epoch": 7.885038503850385, "percentage": 39.43, "elapsed_time": "2:49:08", "remaining_time": "4:19:52", "throughput": 1490.52, "total_tokens": 15126144} {"current_steps": 71680, "total_steps": 181800, "loss": 0.0087, "lr": 3.7930222112804146e-05, "epoch": 7.885588558855885, "percentage": 39.43, "elapsed_time": "2:49:08", "remaining_time": "4:19:51", "throughput": 1490.52, "total_tokens": 15127168} {"current_steps": 71685, "total_steps": 181800, "loss": 0.1751, "lr": 3.792816793317624e-05, "epoch": 7.8861386138613865, "percentage": 39.43, "elapsed_time": "2:49:09", "remaining_time": "4:19:50", "throughput": 1490.52, "total_tokens": 15128192} {"current_steps": 71690, "total_steps": 181800, "loss": 0.0873, "lr": 3.792611363439561e-05, "epoch": 7.886688668866887, "percentage": 39.43, "elapsed_time": "2:49:10", "remaining_time": "4:19:50", "throughput": 1490.53, "total_tokens": 15129280} {"current_steps": 71695, "total_steps": 181800, "loss": 0.0244, "lr": 3.79240592164812e-05, "epoch": 7.887238723872387, "percentage": 39.44, "elapsed_time": "2:49:10", "remaining_time": "4:19:49", "throughput": 1490.53, "total_tokens": 15130336} {"current_steps": 71700, "total_steps": 181800, "loss": 0.0432, "lr": 3.792200467945193e-05, "epoch": 7.887788778877888, "percentage": 39.44, "elapsed_time": "2:49:11", "remaining_time": "4:19:48", "throughput": 1490.53, "total_tokens": 15131360} {"current_steps": 71705, "total_steps": 181800, "loss": 0.0172, "lr": 3.7919950023326745e-05, "epoch": 7.888338833883388, "percentage": 39.44, "elapsed_time": "2:49:12", "remaining_time": "4:19:47", "throughput": 1490.53, "total_tokens": 15132416} {"current_steps": 71710, "total_steps": 181800, "loss": 0.0579, "lr": 3.791789524812458e-05, "epoch": 7.888888888888889, "percentage": 39.44, "elapsed_time": "2:49:13", "remaining_time": "4:19:47", "throughput": 1490.53, "total_tokens": 15133440} {"current_steps": 71715, "total_steps": 181800, "loss": 0.0225, "lr": 3.7915840353864375e-05, "epoch": 7.8894389438943895, "percentage": 39.45, "elapsed_time": "2:49:13", "remaining_time": "4:19:46", "throughput": 1490.53, "total_tokens": 15134496} {"current_steps": 71720, "total_steps": 181800, "loss": 0.1447, "lr": 3.791378534056507e-05, "epoch": 7.88998899889989, "percentage": 39.45, "elapsed_time": "2:49:14", "remaining_time": "4:19:45", "throughput": 1490.53, "total_tokens": 15135520} {"current_steps": 71725, "total_steps": 181800, "loss": 0.0294, "lr": 3.791173020824559e-05, "epoch": 7.890539053905391, "percentage": 39.45, "elapsed_time": "2:49:15", "remaining_time": "4:19:44", "throughput": 1490.54, "total_tokens": 15136576} {"current_steps": 71730, "total_steps": 181800, "loss": 0.0264, "lr": 3.79096749569249e-05, "epoch": 7.891089108910891, "percentage": 39.46, "elapsed_time": "2:49:15", "remaining_time": "4:19:44", "throughput": 1490.54, "total_tokens": 15137632} {"current_steps": 71735, "total_steps": 181800, "loss": 0.093, "lr": 3.7907619586621925e-05, "epoch": 7.891639163916391, "percentage": 39.46, "elapsed_time": "2:49:16", "remaining_time": "4:19:43", "throughput": 1490.54, "total_tokens": 15138688} {"current_steps": 71740, "total_steps": 181800, "loss": 0.0142, "lr": 3.7905564097355616e-05, "epoch": 7.892189218921892, "percentage": 39.46, "elapsed_time": "2:49:17", "remaining_time": "4:19:42", "throughput": 1490.55, "total_tokens": 15139776} {"current_steps": 71745, "total_steps": 181800, "loss": 0.0686, "lr": 3.7903508489144914e-05, "epoch": 7.8927392739273925, "percentage": 39.46, "elapsed_time": "2:49:17", "remaining_time": "4:19:41", "throughput": 1490.55, "total_tokens": 15140832} {"current_steps": 71750, "total_steps": 181800, "loss": 0.024, "lr": 3.7901452762008774e-05, "epoch": 7.893289328932894, "percentage": 39.47, "elapsed_time": "2:49:18", "remaining_time": "4:19:41", "throughput": 1490.55, "total_tokens": 15141920} {"current_steps": 71755, "total_steps": 181800, "loss": 0.1049, "lr": 3.789939691596612e-05, "epoch": 7.893839383938394, "percentage": 39.47, "elapsed_time": "2:49:19", "remaining_time": "4:19:40", "throughput": 1490.55, "total_tokens": 15142944} {"current_steps": 71760, "total_steps": 181800, "loss": 0.0068, "lr": 3.7897340951035925e-05, "epoch": 7.894389438943895, "percentage": 39.47, "elapsed_time": "2:49:19", "remaining_time": "4:19:39", "throughput": 1490.56, "total_tokens": 15144032} {"current_steps": 71765, "total_steps": 181800, "loss": 0.0262, "lr": 3.789528486723712e-05, "epoch": 7.894939493949395, "percentage": 39.47, "elapsed_time": "2:49:20", "remaining_time": "4:19:39", "throughput": 1490.57, "total_tokens": 15145184} {"current_steps": 71770, "total_steps": 181800, "loss": 0.0337, "lr": 3.7893228664588666e-05, "epoch": 7.895489548954895, "percentage": 39.48, "elapsed_time": "2:49:21", "remaining_time": "4:19:38", "throughput": 1490.57, "total_tokens": 15146240} {"current_steps": 71775, "total_steps": 181800, "loss": 0.0164, "lr": 3.789117234310952e-05, "epoch": 7.896039603960396, "percentage": 39.48, "elapsed_time": "2:49:22", "remaining_time": "4:19:37", "throughput": 1490.58, "total_tokens": 15147296} {"current_steps": 71780, "total_steps": 181800, "loss": 0.0151, "lr": 3.788911590281861e-05, "epoch": 7.896589658965897, "percentage": 39.48, "elapsed_time": "2:49:22", "remaining_time": "4:19:36", "throughput": 1490.58, "total_tokens": 15148352} {"current_steps": 71785, "total_steps": 181800, "loss": 0.0357, "lr": 3.788705934373491e-05, "epoch": 7.897139713971397, "percentage": 39.49, "elapsed_time": "2:49:23", "remaining_time": "4:19:36", "throughput": 1490.58, "total_tokens": 15149376} {"current_steps": 71790, "total_steps": 181800, "loss": 0.0305, "lr": 3.7885002665877367e-05, "epoch": 7.897689768976898, "percentage": 39.49, "elapsed_time": "2:49:24", "remaining_time": "4:19:35", "throughput": 1490.58, "total_tokens": 15150432} {"current_steps": 71795, "total_steps": 181800, "loss": 0.0124, "lr": 3.788294586926493e-05, "epoch": 7.898239823982398, "percentage": 39.49, "elapsed_time": "2:49:24", "remaining_time": "4:19:34", "throughput": 1490.58, "total_tokens": 15151456} {"current_steps": 71800, "total_steps": 181800, "loss": 0.0079, "lr": 3.788088895391657e-05, "epoch": 7.898789878987898, "percentage": 39.49, "elapsed_time": "2:49:25", "remaining_time": "4:19:33", "throughput": 1490.58, "total_tokens": 15152512} {"current_steps": 71805, "total_steps": 181800, "loss": 0.0075, "lr": 3.7878831919851244e-05, "epoch": 7.899339933993399, "percentage": 39.5, "elapsed_time": "2:49:26", "remaining_time": "4:19:33", "throughput": 1490.59, "total_tokens": 15153632} {"current_steps": 71810, "total_steps": 181800, "loss": 0.0184, "lr": 3.7876774767087896e-05, "epoch": 7.8998899889989, "percentage": 39.5, "elapsed_time": "2:49:26", "remaining_time": "4:19:32", "throughput": 1490.6, "total_tokens": 15154720} {"current_steps": 71815, "total_steps": 181800, "loss": 0.0081, "lr": 3.787471749564549e-05, "epoch": 7.900440044004401, "percentage": 39.5, "elapsed_time": "2:49:27", "remaining_time": "4:19:31", "throughput": 1490.6, "total_tokens": 15155776} {"current_steps": 71820, "total_steps": 181800, "loss": 0.0771, "lr": 3.7872660105543e-05, "epoch": 7.900990099009901, "percentage": 39.5, "elapsed_time": "2:49:28", "remaining_time": "4:19:30", "throughput": 1490.6, "total_tokens": 15156832} {"current_steps": 71825, "total_steps": 181800, "loss": 0.0594, "lr": 3.787060259679937e-05, "epoch": 7.901540154015402, "percentage": 39.51, "elapsed_time": "2:49:28", "remaining_time": "4:19:30", "throughput": 1490.61, "total_tokens": 15157888} {"current_steps": 71830, "total_steps": 181800, "loss": 0.0201, "lr": 3.786854496943358e-05, "epoch": 7.902090209020902, "percentage": 39.51, "elapsed_time": "2:49:29", "remaining_time": "4:19:29", "throughput": 1490.61, "total_tokens": 15159008} {"current_steps": 71835, "total_steps": 181800, "loss": 0.0176, "lr": 3.786648722346458e-05, "epoch": 7.902640264026402, "percentage": 39.51, "elapsed_time": "2:49:30", "remaining_time": "4:19:28", "throughput": 1490.61, "total_tokens": 15160000} {"current_steps": 71840, "total_steps": 181800, "loss": 0.0045, "lr": 3.786442935891135e-05, "epoch": 7.9031903190319035, "percentage": 39.52, "elapsed_time": "2:49:31", "remaining_time": "4:19:28", "throughput": 1490.61, "total_tokens": 15161088} {"current_steps": 71845, "total_steps": 181800, "loss": 0.0416, "lr": 3.7862371375792834e-05, "epoch": 7.903740374037404, "percentage": 39.52, "elapsed_time": "2:49:31", "remaining_time": "4:19:27", "throughput": 1490.62, "total_tokens": 15162176} {"current_steps": 71850, "total_steps": 181800, "loss": 0.0505, "lr": 3.786031327412802e-05, "epoch": 7.904290429042904, "percentage": 39.52, "elapsed_time": "2:49:32", "remaining_time": "4:19:26", "throughput": 1490.62, "total_tokens": 15163232} {"current_steps": 71855, "total_steps": 181800, "loss": 0.0599, "lr": 3.7858255053935866e-05, "epoch": 7.904840484048405, "percentage": 39.52, "elapsed_time": "2:49:33", "remaining_time": "4:19:25", "throughput": 1490.62, "total_tokens": 15164256} {"current_steps": 71860, "total_steps": 181800, "loss": 0.009, "lr": 3.785619671523535e-05, "epoch": 7.905390539053905, "percentage": 39.53, "elapsed_time": "2:49:33", "remaining_time": "4:19:25", "throughput": 1490.62, "total_tokens": 15165280} {"current_steps": 71865, "total_steps": 181800, "loss": 0.0412, "lr": 3.7854138258045434e-05, "epoch": 7.905940594059406, "percentage": 39.53, "elapsed_time": "2:49:34", "remaining_time": "4:19:24", "throughput": 1490.63, "total_tokens": 15166400} {"current_steps": 71870, "total_steps": 181800, "loss": 0.0487, "lr": 3.78520796823851e-05, "epoch": 7.9064906490649065, "percentage": 39.53, "elapsed_time": "2:49:35", "remaining_time": "4:19:23", "throughput": 1490.63, "total_tokens": 15167392} {"current_steps": 71875, "total_steps": 181800, "loss": 0.0561, "lr": 3.7850020988273306e-05, "epoch": 7.907040704070407, "percentage": 39.54, "elapsed_time": "2:49:35", "remaining_time": "4:19:22", "throughput": 1490.63, "total_tokens": 15168448} {"current_steps": 71880, "total_steps": 181800, "loss": 0.0233, "lr": 3.7847962175729043e-05, "epoch": 7.907590759075908, "percentage": 39.54, "elapsed_time": "2:49:36", "remaining_time": "4:19:22", "throughput": 1490.64, "total_tokens": 15169600} {"current_steps": 71885, "total_steps": 181800, "loss": 0.0858, "lr": 3.784590324477127e-05, "epoch": 7.908140814081408, "percentage": 39.54, "elapsed_time": "2:49:37", "remaining_time": "4:19:21", "throughput": 1490.65, "total_tokens": 15170656} {"current_steps": 71890, "total_steps": 181800, "loss": 0.0706, "lr": 3.784384419541898e-05, "epoch": 7.908690869086909, "percentage": 39.54, "elapsed_time": "2:49:37", "remaining_time": "4:19:20", "throughput": 1490.65, "total_tokens": 15171712} {"current_steps": 71895, "total_steps": 181800, "loss": 0.1637, "lr": 3.784178502769113e-05, "epoch": 7.909240924092409, "percentage": 39.55, "elapsed_time": "2:49:38", "remaining_time": "4:19:19", "throughput": 1490.65, "total_tokens": 15172736} {"current_steps": 71900, "total_steps": 181800, "loss": 0.0342, "lr": 3.783972574160672e-05, "epoch": 7.9097909790979095, "percentage": 39.55, "elapsed_time": "2:49:39", "remaining_time": "4:19:19", "throughput": 1490.66, "total_tokens": 15173824} {"current_steps": 71905, "total_steps": 181800, "loss": 0.0063, "lr": 3.783766633718471e-05, "epoch": 7.910341034103411, "percentage": 39.55, "elapsed_time": "2:49:39", "remaining_time": "4:19:18", "throughput": 1490.66, "total_tokens": 15174880} {"current_steps": 71910, "total_steps": 181800, "loss": 0.013, "lr": 3.78356068144441e-05, "epoch": 7.910891089108911, "percentage": 39.55, "elapsed_time": "2:49:40", "remaining_time": "4:19:17", "throughput": 1490.66, "total_tokens": 15175904} {"current_steps": 71915, "total_steps": 181800, "loss": 0.0687, "lr": 3.783354717340385e-05, "epoch": 7.911441144114411, "percentage": 39.56, "elapsed_time": "2:49:41", "remaining_time": "4:19:16", "throughput": 1490.66, "total_tokens": 15176960} {"current_steps": 71920, "total_steps": 181800, "loss": 0.0663, "lr": 3.7831487414082956e-05, "epoch": 7.911991199119912, "percentage": 39.56, "elapsed_time": "2:49:42", "remaining_time": "4:19:16", "throughput": 1490.67, "total_tokens": 15178080} {"current_steps": 71925, "total_steps": 181800, "loss": 0.0478, "lr": 3.7829427536500404e-05, "epoch": 7.912541254125412, "percentage": 39.56, "elapsed_time": "2:49:42", "remaining_time": "4:19:15", "throughput": 1490.68, "total_tokens": 15179200} {"current_steps": 71930, "total_steps": 181800, "loss": 0.0178, "lr": 3.782736754067518e-05, "epoch": 7.913091309130913, "percentage": 39.57, "elapsed_time": "2:49:43", "remaining_time": "4:19:14", "throughput": 1490.68, "total_tokens": 15180256} {"current_steps": 71935, "total_steps": 181800, "loss": 0.0373, "lr": 3.782530742662625e-05, "epoch": 7.913641364136414, "percentage": 39.57, "elapsed_time": "2:49:44", "remaining_time": "4:19:14", "throughput": 1490.68, "total_tokens": 15181280} {"current_steps": 71940, "total_steps": 181800, "loss": 0.0032, "lr": 3.7823247194372624e-05, "epoch": 7.914191419141914, "percentage": 39.57, "elapsed_time": "2:49:44", "remaining_time": "4:19:13", "throughput": 1490.69, "total_tokens": 15182368} {"current_steps": 71945, "total_steps": 181800, "loss": 0.0649, "lr": 3.782118684393328e-05, "epoch": 7.914741474147415, "percentage": 39.57, "elapsed_time": "2:49:45", "remaining_time": "4:19:12", "throughput": 1490.7, "total_tokens": 15183552} {"current_steps": 71950, "total_steps": 181800, "loss": 0.0968, "lr": 3.7819126375327214e-05, "epoch": 7.915291529152915, "percentage": 39.58, "elapsed_time": "2:49:46", "remaining_time": "4:19:11", "throughput": 1490.71, "total_tokens": 15184640} {"current_steps": 71955, "total_steps": 181800, "loss": 0.0693, "lr": 3.78170657885734e-05, "epoch": 7.915841584158416, "percentage": 39.58, "elapsed_time": "2:49:46", "remaining_time": "4:19:11", "throughput": 1490.71, "total_tokens": 15185664} {"current_steps": 71960, "total_steps": 181800, "loss": 0.0423, "lr": 3.781500508369085e-05, "epoch": 7.916391639163916, "percentage": 39.58, "elapsed_time": "2:49:47", "remaining_time": "4:19:10", "throughput": 1490.71, "total_tokens": 15186688} {"current_steps": 71965, "total_steps": 181800, "loss": 0.0234, "lr": 3.7812944260698546e-05, "epoch": 7.916941694169417, "percentage": 39.58, "elapsed_time": "2:49:48", "remaining_time": "4:19:09", "throughput": 1490.72, "total_tokens": 15187808} {"current_steps": 71970, "total_steps": 181800, "loss": 0.0821, "lr": 3.781088331961549e-05, "epoch": 7.917491749174918, "percentage": 39.59, "elapsed_time": "2:49:48", "remaining_time": "4:19:08", "throughput": 1490.72, "total_tokens": 15188864} {"current_steps": 71975, "total_steps": 181800, "loss": 0.0078, "lr": 3.780882226046065e-05, "epoch": 7.918041804180418, "percentage": 39.59, "elapsed_time": "2:49:49", "remaining_time": "4:19:08", "throughput": 1490.72, "total_tokens": 15189920} {"current_steps": 71980, "total_steps": 181800, "loss": 0.0657, "lr": 3.7806761083253064e-05, "epoch": 7.918591859185918, "percentage": 39.59, "elapsed_time": "2:49:50", "remaining_time": "4:19:07", "throughput": 1490.73, "total_tokens": 15191040} {"current_steps": 71985, "total_steps": 181800, "loss": 0.0301, "lr": 3.780469978801169e-05, "epoch": 7.919141914191419, "percentage": 39.6, "elapsed_time": "2:49:51", "remaining_time": "4:19:06", "throughput": 1490.73, "total_tokens": 15192064} {"current_steps": 71990, "total_steps": 181800, "loss": 0.201, "lr": 3.780263837475555e-05, "epoch": 7.919691969196919, "percentage": 39.6, "elapsed_time": "2:49:51", "remaining_time": "4:19:05", "throughput": 1490.73, "total_tokens": 15193120} {"current_steps": 71995, "total_steps": 181800, "loss": 0.0357, "lr": 3.780057684350363e-05, "epoch": 7.9202420242024205, "percentage": 39.6, "elapsed_time": "2:49:52", "remaining_time": "4:19:05", "throughput": 1490.73, "total_tokens": 15194176} {"current_steps": 72000, "total_steps": 181800, "loss": 0.0192, "lr": 3.779851519427494e-05, "epoch": 7.920792079207921, "percentage": 39.6, "elapsed_time": "2:49:53", "remaining_time": "4:19:04", "throughput": 1490.73, "total_tokens": 15195200} {"current_steps": 72005, "total_steps": 181800, "loss": 0.0264, "lr": 3.7796453427088474e-05, "epoch": 7.921342134213422, "percentage": 39.61, "elapsed_time": "2:49:53", "remaining_time": "4:19:03", "throughput": 1490.73, "total_tokens": 15196192} {"current_steps": 72010, "total_steps": 181800, "loss": 0.0286, "lr": 3.7794391541963244e-05, "epoch": 7.921892189218922, "percentage": 39.61, "elapsed_time": "2:49:54", "remaining_time": "4:19:03", "throughput": 1490.73, "total_tokens": 15197248} {"current_steps": 72015, "total_steps": 181800, "loss": 0.0816, "lr": 3.779232953891824e-05, "epoch": 7.922442244224422, "percentage": 39.61, "elapsed_time": "2:49:55", "remaining_time": "4:19:02", "throughput": 1490.73, "total_tokens": 15198304} {"current_steps": 72020, "total_steps": 181800, "loss": 0.024, "lr": 3.779026741797248e-05, "epoch": 7.922992299229923, "percentage": 39.61, "elapsed_time": "2:49:55", "remaining_time": "4:19:01", "throughput": 1490.73, "total_tokens": 15199328} {"current_steps": 72025, "total_steps": 181800, "loss": 0.0609, "lr": 3.778820517914495e-05, "epoch": 7.9235423542354235, "percentage": 39.62, "elapsed_time": "2:49:56", "remaining_time": "4:19:00", "throughput": 1490.74, "total_tokens": 15200416} {"current_steps": 72030, "total_steps": 181800, "loss": 0.1072, "lr": 3.778614282245468e-05, "epoch": 7.924092409240924, "percentage": 39.62, "elapsed_time": "2:49:57", "remaining_time": "4:19:00", "throughput": 1490.74, "total_tokens": 15201472} {"current_steps": 72035, "total_steps": 181800, "loss": 0.0392, "lr": 3.778408034792066e-05, "epoch": 7.924642464246425, "percentage": 39.62, "elapsed_time": "2:49:57", "remaining_time": "4:18:59", "throughput": 1490.74, "total_tokens": 15202496} {"current_steps": 72040, "total_steps": 181800, "loss": 0.0094, "lr": 3.778201775556191e-05, "epoch": 7.925192519251925, "percentage": 39.63, "elapsed_time": "2:49:58", "remaining_time": "4:18:58", "throughput": 1490.75, "total_tokens": 15203552} {"current_steps": 72045, "total_steps": 181800, "loss": 0.0107, "lr": 3.777995504539743e-05, "epoch": 7.925742574257426, "percentage": 39.63, "elapsed_time": "2:49:59", "remaining_time": "4:18:57", "throughput": 1490.75, "total_tokens": 15204576} {"current_steps": 72050, "total_steps": 181800, "loss": 0.0229, "lr": 3.7777892217446254e-05, "epoch": 7.926292629262926, "percentage": 39.63, "elapsed_time": "2:50:00", "remaining_time": "4:18:57", "throughput": 1490.76, "total_tokens": 15205728} {"current_steps": 72055, "total_steps": 181800, "loss": 0.0819, "lr": 3.777582927172736e-05, "epoch": 7.9268426842684265, "percentage": 39.63, "elapsed_time": "2:50:00", "remaining_time": "4:18:56", "throughput": 1490.76, "total_tokens": 15206752} {"current_steps": 72060, "total_steps": 181800, "loss": 0.0539, "lr": 3.777376620825979e-05, "epoch": 7.927392739273928, "percentage": 39.64, "elapsed_time": "2:50:01", "remaining_time": "4:18:55", "throughput": 1490.76, "total_tokens": 15207776} {"current_steps": 72065, "total_steps": 181800, "loss": 0.0091, "lr": 3.777170302706253e-05, "epoch": 7.927942794279428, "percentage": 39.64, "elapsed_time": "2:50:02", "remaining_time": "4:18:54", "throughput": 1490.75, "total_tokens": 15208768} {"current_steps": 72070, "total_steps": 181800, "loss": 0.0672, "lr": 3.776963972815463e-05, "epoch": 7.928492849284929, "percentage": 39.64, "elapsed_time": "2:50:02", "remaining_time": "4:18:54", "throughput": 1490.76, "total_tokens": 15209824} {"current_steps": 72075, "total_steps": 181800, "loss": 0.0138, "lr": 3.776757631155507e-05, "epoch": 7.929042904290429, "percentage": 39.65, "elapsed_time": "2:50:03", "remaining_time": "4:18:53", "throughput": 1490.76, "total_tokens": 15210880} {"current_steps": 72080, "total_steps": 181800, "loss": 0.0085, "lr": 3.77655127772829e-05, "epoch": 7.929592959295929, "percentage": 39.65, "elapsed_time": "2:50:04", "remaining_time": "4:18:52", "throughput": 1490.76, "total_tokens": 15211872} {"current_steps": 72085, "total_steps": 181800, "loss": 0.0316, "lr": 3.7763449125357114e-05, "epoch": 7.93014301430143, "percentage": 39.65, "elapsed_time": "2:50:04", "remaining_time": "4:18:51", "throughput": 1490.76, "total_tokens": 15212896} {"current_steps": 72090, "total_steps": 181800, "loss": 0.0191, "lr": 3.7761385355796745e-05, "epoch": 7.930693069306931, "percentage": 39.65, "elapsed_time": "2:50:05", "remaining_time": "4:18:51", "throughput": 1490.76, "total_tokens": 15213952} {"current_steps": 72095, "total_steps": 181800, "loss": 0.1901, "lr": 3.775932146862081e-05, "epoch": 7.931243124312431, "percentage": 39.66, "elapsed_time": "2:50:06", "remaining_time": "4:18:50", "throughput": 1490.77, "total_tokens": 15215072} {"current_steps": 72100, "total_steps": 181800, "loss": 0.059, "lr": 3.775725746384834e-05, "epoch": 7.931793179317932, "percentage": 39.66, "elapsed_time": "2:50:06", "remaining_time": "4:18:49", "throughput": 1490.77, "total_tokens": 15216096} {"current_steps": 72105, "total_steps": 181800, "loss": 0.007, "lr": 3.775519334149834e-05, "epoch": 7.932343234323432, "percentage": 39.66, "elapsed_time": "2:50:07", "remaining_time": "4:18:49", "throughput": 1490.77, "total_tokens": 15217120} {"current_steps": 72110, "total_steps": 181800, "loss": 0.0134, "lr": 3.775312910158985e-05, "epoch": 7.932893289328933, "percentage": 39.66, "elapsed_time": "2:50:08", "remaining_time": "4:18:48", "throughput": 1490.77, "total_tokens": 15218176} {"current_steps": 72115, "total_steps": 181800, "loss": 0.0871, "lr": 3.775106474414188e-05, "epoch": 7.933443344334433, "percentage": 39.67, "elapsed_time": "2:50:08", "remaining_time": "4:18:47", "throughput": 1490.77, "total_tokens": 15219168} {"current_steps": 72120, "total_steps": 181800, "loss": 0.0053, "lr": 3.774900026917347e-05, "epoch": 7.933993399339934, "percentage": 39.67, "elapsed_time": "2:50:09", "remaining_time": "4:18:46", "throughput": 1490.77, "total_tokens": 15220256} {"current_steps": 72125, "total_steps": 181800, "loss": 0.0997, "lr": 3.7746935676703646e-05, "epoch": 7.934543454345435, "percentage": 39.67, "elapsed_time": "2:50:10", "remaining_time": "4:18:46", "throughput": 1490.77, "total_tokens": 15221280} {"current_steps": 72130, "total_steps": 181800, "loss": 0.0477, "lr": 3.7744870966751435e-05, "epoch": 7.935093509350935, "percentage": 39.68, "elapsed_time": "2:50:11", "remaining_time": "4:18:45", "throughput": 1490.78, "total_tokens": 15222368} {"current_steps": 72135, "total_steps": 181800, "loss": 0.01, "lr": 3.774280613933585e-05, "epoch": 7.935643564356436, "percentage": 39.68, "elapsed_time": "2:50:11", "remaining_time": "4:18:44", "throughput": 1490.78, "total_tokens": 15223424} {"current_steps": 72140, "total_steps": 181800, "loss": 0.043, "lr": 3.774074119447595e-05, "epoch": 7.936193619361936, "percentage": 39.68, "elapsed_time": "2:50:12", "remaining_time": "4:18:43", "throughput": 1490.78, "total_tokens": 15224480} {"current_steps": 72145, "total_steps": 181800, "loss": 0.1263, "lr": 3.773867613219074e-05, "epoch": 7.936743674367436, "percentage": 39.68, "elapsed_time": "2:50:13", "remaining_time": "4:18:43", "throughput": 1490.78, "total_tokens": 15225504} {"current_steps": 72150, "total_steps": 181800, "loss": 0.0239, "lr": 3.773661095249927e-05, "epoch": 7.9372937293729375, "percentage": 39.69, "elapsed_time": "2:50:13", "remaining_time": "4:18:42", "throughput": 1490.78, "total_tokens": 15226496} {"current_steps": 72155, "total_steps": 181800, "loss": 0.0994, "lr": 3.773454565542057e-05, "epoch": 7.937843784378438, "percentage": 39.69, "elapsed_time": "2:50:14", "remaining_time": "4:18:41", "throughput": 1490.78, "total_tokens": 15227520} {"current_steps": 72160, "total_steps": 181800, "loss": 0.0366, "lr": 3.773248024097367e-05, "epoch": 7.938393839383938, "percentage": 39.69, "elapsed_time": "2:50:15", "remaining_time": "4:18:40", "throughput": 1490.78, "total_tokens": 15228608} {"current_steps": 72165, "total_steps": 181800, "loss": 0.014, "lr": 3.773041470917761e-05, "epoch": 7.938943894389439, "percentage": 39.69, "elapsed_time": "2:50:15", "remaining_time": "4:18:40", "throughput": 1490.79, "total_tokens": 15229728} {"current_steps": 72170, "total_steps": 181800, "loss": 0.0653, "lr": 3.772834906005143e-05, "epoch": 7.939493949394939, "percentage": 39.7, "elapsed_time": "2:50:16", "remaining_time": "4:18:39", "throughput": 1490.8, "total_tokens": 15230816} {"current_steps": 72175, "total_steps": 181800, "loss": 0.0744, "lr": 3.7726283293614164e-05, "epoch": 7.94004400440044, "percentage": 39.7, "elapsed_time": "2:50:17", "remaining_time": "4:18:38", "throughput": 1490.81, "total_tokens": 15231936} {"current_steps": 72180, "total_steps": 181800, "loss": 0.0067, "lr": 3.772421740988484e-05, "epoch": 7.9405940594059405, "percentage": 39.7, "elapsed_time": "2:50:17", "remaining_time": "4:18:37", "throughput": 1490.81, "total_tokens": 15232992} {"current_steps": 72185, "total_steps": 181800, "loss": 0.0093, "lr": 3.7722151408882525e-05, "epoch": 7.941144114411442, "percentage": 39.71, "elapsed_time": "2:50:18", "remaining_time": "4:18:37", "throughput": 1490.81, "total_tokens": 15234016} {"current_steps": 72190, "total_steps": 181800, "loss": 0.0193, "lr": 3.772008529062623e-05, "epoch": 7.941694169416942, "percentage": 39.71, "elapsed_time": "2:50:19", "remaining_time": "4:18:36", "throughput": 1490.82, "total_tokens": 15235104} {"current_steps": 72195, "total_steps": 181800, "loss": 0.0099, "lr": 3.771801905513502e-05, "epoch": 7.942244224422442, "percentage": 39.71, "elapsed_time": "2:50:19", "remaining_time": "4:18:35", "throughput": 1490.82, "total_tokens": 15236192} {"current_steps": 72200, "total_steps": 181800, "loss": 0.04, "lr": 3.7715952702427935e-05, "epoch": 7.942794279427943, "percentage": 39.71, "elapsed_time": "2:50:20", "remaining_time": "4:18:35", "throughput": 1490.82, "total_tokens": 15237248} {"current_steps": 72205, "total_steps": 181800, "loss": 0.0633, "lr": 3.771388623252402e-05, "epoch": 7.943344334433443, "percentage": 39.72, "elapsed_time": "2:50:21", "remaining_time": "4:18:34", "throughput": 1490.83, "total_tokens": 15238304} {"current_steps": 72210, "total_steps": 181800, "loss": 0.0396, "lr": 3.771181964544231e-05, "epoch": 7.9438943894389435, "percentage": 39.72, "elapsed_time": "2:50:22", "remaining_time": "4:18:33", "throughput": 1490.83, "total_tokens": 15239328} {"current_steps": 72215, "total_steps": 181800, "loss": 0.068, "lr": 3.770975294120186e-05, "epoch": 7.944444444444445, "percentage": 39.72, "elapsed_time": "2:50:22", "remaining_time": "4:18:32", "throughput": 1490.83, "total_tokens": 15240384} {"current_steps": 72220, "total_steps": 181800, "loss": 0.0265, "lr": 3.770768611982171e-05, "epoch": 7.944994499449945, "percentage": 39.72, "elapsed_time": "2:50:23", "remaining_time": "4:18:32", "throughput": 1490.83, "total_tokens": 15241440} {"current_steps": 72225, "total_steps": 181800, "loss": 0.0536, "lr": 3.770561918132092e-05, "epoch": 7.945544554455445, "percentage": 39.73, "elapsed_time": "2:50:24", "remaining_time": "4:18:31", "throughput": 1490.83, "total_tokens": 15242464} {"current_steps": 72230, "total_steps": 181800, "loss": 0.0383, "lr": 3.7703552125718525e-05, "epoch": 7.946094609460946, "percentage": 39.73, "elapsed_time": "2:50:24", "remaining_time": "4:18:30", "throughput": 1490.83, "total_tokens": 15243488} {"current_steps": 72235, "total_steps": 181800, "loss": 0.0093, "lr": 3.770148495303359e-05, "epoch": 7.946644664466446, "percentage": 39.73, "elapsed_time": "2:50:25", "remaining_time": "4:18:29", "throughput": 1490.83, "total_tokens": 15244512} {"current_steps": 72240, "total_steps": 181800, "loss": 0.085, "lr": 3.7699417663285175e-05, "epoch": 7.947194719471947, "percentage": 39.74, "elapsed_time": "2:50:26", "remaining_time": "4:18:29", "throughput": 1490.83, "total_tokens": 15245568} {"current_steps": 72245, "total_steps": 181800, "loss": 0.0834, "lr": 3.7697350256492316e-05, "epoch": 7.947744774477448, "percentage": 39.74, "elapsed_time": "2:50:26", "remaining_time": "4:18:28", "throughput": 1490.84, "total_tokens": 15246656} {"current_steps": 72250, "total_steps": 181800, "loss": 0.0842, "lr": 3.769528273267406e-05, "epoch": 7.948294829482949, "percentage": 39.74, "elapsed_time": "2:50:27", "remaining_time": "4:18:27", "throughput": 1490.84, "total_tokens": 15247744} {"current_steps": 72255, "total_steps": 181800, "loss": 0.0114, "lr": 3.769321509184949e-05, "epoch": 7.948844884488449, "percentage": 39.74, "elapsed_time": "2:50:28", "remaining_time": "4:18:26", "throughput": 1490.85, "total_tokens": 15248864} {"current_steps": 72260, "total_steps": 181800, "loss": 0.0386, "lr": 3.7691147334037645e-05, "epoch": 7.949394939493949, "percentage": 39.75, "elapsed_time": "2:50:28", "remaining_time": "4:18:26", "throughput": 1490.85, "total_tokens": 15249856} {"current_steps": 72265, "total_steps": 181800, "loss": 0.0528, "lr": 3.768907945925758e-05, "epoch": 7.94994499449945, "percentage": 39.75, "elapsed_time": "2:50:29", "remaining_time": "4:18:25", "throughput": 1490.82, "total_tokens": 15250880} {"current_steps": 72270, "total_steps": 181800, "loss": 0.0468, "lr": 3.768701146752836e-05, "epoch": 7.9504950495049505, "percentage": 39.75, "elapsed_time": "2:50:30", "remaining_time": "4:18:25", "throughput": 1490.82, "total_tokens": 15251904} {"current_steps": 72275, "total_steps": 181800, "loss": 0.0848, "lr": 3.768494335886904e-05, "epoch": 7.951045104510451, "percentage": 39.76, "elapsed_time": "2:50:31", "remaining_time": "4:18:24", "throughput": 1490.82, "total_tokens": 15252960} {"current_steps": 72280, "total_steps": 181800, "loss": 0.0562, "lr": 3.768287513329869e-05, "epoch": 7.951595159515952, "percentage": 39.76, "elapsed_time": "2:50:31", "remaining_time": "4:18:23", "throughput": 1490.83, "total_tokens": 15254048} {"current_steps": 72285, "total_steps": 181800, "loss": 0.0857, "lr": 3.768080679083637e-05, "epoch": 7.952145214521452, "percentage": 39.76, "elapsed_time": "2:50:32", "remaining_time": "4:18:22", "throughput": 1490.83, "total_tokens": 15255136} {"current_steps": 72290, "total_steps": 181800, "loss": 0.0607, "lr": 3.767873833150112e-05, "epoch": 7.952695269526953, "percentage": 39.76, "elapsed_time": "2:50:33", "remaining_time": "4:18:22", "throughput": 1490.84, "total_tokens": 15256256} {"current_steps": 72295, "total_steps": 181800, "loss": 0.0106, "lr": 3.767666975531203e-05, "epoch": 7.953245324532453, "percentage": 39.77, "elapsed_time": "2:50:34", "remaining_time": "4:18:21", "throughput": 1490.85, "total_tokens": 15257344} {"current_steps": 72300, "total_steps": 181800, "loss": 0.0511, "lr": 3.767460106228816e-05, "epoch": 7.9537953795379535, "percentage": 39.77, "elapsed_time": "2:50:34", "remaining_time": "4:18:20", "throughput": 1490.85, "total_tokens": 15258368} {"current_steps": 72305, "total_steps": 181800, "loss": 0.0502, "lr": 3.767253225244859e-05, "epoch": 7.9543454345434546, "percentage": 39.77, "elapsed_time": "2:50:35", "remaining_time": "4:18:19", "throughput": 1490.85, "total_tokens": 15259424} {"current_steps": 72310, "total_steps": 181800, "loss": 0.0708, "lr": 3.767046332581235e-05, "epoch": 7.954895489548955, "percentage": 39.77, "elapsed_time": "2:50:36", "remaining_time": "4:18:19", "throughput": 1490.86, "total_tokens": 15260544} {"current_steps": 72315, "total_steps": 181800, "loss": 0.1674, "lr": 3.766839428239853e-05, "epoch": 7.955445544554456, "percentage": 39.78, "elapsed_time": "2:50:36", "remaining_time": "4:18:18", "throughput": 1490.86, "total_tokens": 15261632} {"current_steps": 72320, "total_steps": 181800, "loss": 0.0052, "lr": 3.766632512222621e-05, "epoch": 7.955995599559956, "percentage": 39.78, "elapsed_time": "2:50:37", "remaining_time": "4:18:17", "throughput": 1490.86, "total_tokens": 15262656} {"current_steps": 72325, "total_steps": 181800, "loss": 0.0819, "lr": 3.766425584531445e-05, "epoch": 7.956545654565456, "percentage": 39.78, "elapsed_time": "2:50:38", "remaining_time": "4:18:17", "throughput": 1490.86, "total_tokens": 15263680} {"current_steps": 72330, "total_steps": 181800, "loss": 0.0369, "lr": 3.766218645168231e-05, "epoch": 7.957095709570957, "percentage": 39.79, "elapsed_time": "2:50:38", "remaining_time": "4:18:16", "throughput": 1490.87, "total_tokens": 15264736} {"current_steps": 72335, "total_steps": 181800, "loss": 0.0762, "lr": 3.766011694134888e-05, "epoch": 7.957645764576458, "percentage": 39.79, "elapsed_time": "2:50:39", "remaining_time": "4:18:15", "throughput": 1490.87, "total_tokens": 15265856} {"current_steps": 72340, "total_steps": 181800, "loss": 0.0467, "lr": 3.765804731433322e-05, "epoch": 7.958195819581958, "percentage": 39.79, "elapsed_time": "2:50:40", "remaining_time": "4:18:14", "throughput": 1490.88, "total_tokens": 15266912} {"current_steps": 72345, "total_steps": 181800, "loss": 0.0185, "lr": 3.765597757065442e-05, "epoch": 7.958745874587459, "percentage": 39.79, "elapsed_time": "2:50:40", "remaining_time": "4:18:14", "throughput": 1490.88, "total_tokens": 15267936} {"current_steps": 72350, "total_steps": 181800, "loss": 0.0191, "lr": 3.765390771033154e-05, "epoch": 7.959295929592959, "percentage": 39.8, "elapsed_time": "2:50:41", "remaining_time": "4:18:13", "throughput": 1490.87, "total_tokens": 15268896} {"current_steps": 72355, "total_steps": 181800, "loss": 0.0197, "lr": 3.7651837733383676e-05, "epoch": 7.95984598459846, "percentage": 39.8, "elapsed_time": "2:50:42", "remaining_time": "4:18:12", "throughput": 1490.87, "total_tokens": 15269984} {"current_steps": 72360, "total_steps": 181800, "loss": 0.0282, "lr": 3.764976763982989e-05, "epoch": 7.96039603960396, "percentage": 39.8, "elapsed_time": "2:50:42", "remaining_time": "4:18:11", "throughput": 1490.88, "total_tokens": 15271040} {"current_steps": 72365, "total_steps": 181800, "loss": 0.028, "lr": 3.764769742968926e-05, "epoch": 7.960946094609461, "percentage": 39.8, "elapsed_time": "2:50:43", "remaining_time": "4:18:11", "throughput": 1490.88, "total_tokens": 15272128} {"current_steps": 72370, "total_steps": 181800, "loss": 0.008, "lr": 3.7645627102980875e-05, "epoch": 7.961496149614962, "percentage": 39.81, "elapsed_time": "2:50:44", "remaining_time": "4:18:10", "throughput": 1490.89, "total_tokens": 15273184} {"current_steps": 72375, "total_steps": 181800, "loss": 0.0775, "lr": 3.764355665972381e-05, "epoch": 7.962046204620462, "percentage": 39.81, "elapsed_time": "2:50:45", "remaining_time": "4:18:09", "throughput": 1490.89, "total_tokens": 15274272} {"current_steps": 72380, "total_steps": 181800, "loss": 0.1149, "lr": 3.764148609993715e-05, "epoch": 7.962596259625963, "percentage": 39.81, "elapsed_time": "2:50:45", "remaining_time": "4:18:08", "throughput": 1490.9, "total_tokens": 15275360} {"current_steps": 72385, "total_steps": 181800, "loss": 0.02, "lr": 3.763941542363999e-05, "epoch": 7.963146314631463, "percentage": 39.82, "elapsed_time": "2:50:46", "remaining_time": "4:18:08", "throughput": 1490.9, "total_tokens": 15276384} {"current_steps": 72390, "total_steps": 181800, "loss": 0.0562, "lr": 3.763734463085139e-05, "epoch": 7.963696369636963, "percentage": 39.82, "elapsed_time": "2:50:47", "remaining_time": "4:18:07", "throughput": 1490.9, "total_tokens": 15277440} {"current_steps": 72395, "total_steps": 181800, "loss": 0.0292, "lr": 3.763527372159046e-05, "epoch": 7.9642464246424645, "percentage": 39.82, "elapsed_time": "2:50:47", "remaining_time": "4:18:06", "throughput": 1490.91, "total_tokens": 15278560} {"current_steps": 72400, "total_steps": 181800, "loss": 0.0095, "lr": 3.763320269587627e-05, "epoch": 7.964796479647965, "percentage": 39.82, "elapsed_time": "2:50:48", "remaining_time": "4:18:06", "throughput": 1490.9, "total_tokens": 15279552} {"current_steps": 72405, "total_steps": 181800, "loss": 0.0269, "lr": 3.7631131553727905e-05, "epoch": 7.965346534653465, "percentage": 39.83, "elapsed_time": "2:50:49", "remaining_time": "4:18:05", "throughput": 1490.91, "total_tokens": 15280608} {"current_steps": 72410, "total_steps": 181800, "loss": 0.0409, "lr": 3.7629060295164466e-05, "epoch": 7.965896589658966, "percentage": 39.83, "elapsed_time": "2:50:49", "remaining_time": "4:18:04", "throughput": 1490.9, "total_tokens": 15281600} {"current_steps": 72415, "total_steps": 181800, "loss": 0.1126, "lr": 3.7626988920205045e-05, "epoch": 7.966446644664466, "percentage": 39.83, "elapsed_time": "2:50:50", "remaining_time": "4:18:03", "throughput": 1490.91, "total_tokens": 15282688} {"current_steps": 72420, "total_steps": 181800, "loss": 0.1923, "lr": 3.762491742886872e-05, "epoch": 7.966996699669967, "percentage": 39.83, "elapsed_time": "2:50:51", "remaining_time": "4:18:03", "throughput": 1490.91, "total_tokens": 15283776} {"current_steps": 72425, "total_steps": 181800, "loss": 0.0911, "lr": 3.762284582117459e-05, "epoch": 7.9675467546754675, "percentage": 39.84, "elapsed_time": "2:50:51", "remaining_time": "4:18:02", "throughput": 1490.92, "total_tokens": 15284864} {"current_steps": 72430, "total_steps": 181800, "loss": 0.045, "lr": 3.762077409714174e-05, "epoch": 7.968096809680969, "percentage": 39.84, "elapsed_time": "2:50:52", "remaining_time": "4:18:01", "throughput": 1490.92, "total_tokens": 15285920} {"current_steps": 72435, "total_steps": 181800, "loss": 0.0353, "lr": 3.7618702256789285e-05, "epoch": 7.968646864686469, "percentage": 39.84, "elapsed_time": "2:50:53", "remaining_time": "4:18:00", "throughput": 1490.93, "total_tokens": 15287008} {"current_steps": 72440, "total_steps": 181800, "loss": 0.0233, "lr": 3.7616630300136296e-05, "epoch": 7.969196919691969, "percentage": 39.85, "elapsed_time": "2:50:54", "remaining_time": "4:18:00", "throughput": 1490.93, "total_tokens": 15288064} {"current_steps": 72445, "total_steps": 181800, "loss": 0.0267, "lr": 3.7614558227201886e-05, "epoch": 7.96974697469747, "percentage": 39.85, "elapsed_time": "2:50:54", "remaining_time": "4:17:59", "throughput": 1490.93, "total_tokens": 15289088} {"current_steps": 72450, "total_steps": 181800, "loss": 0.0281, "lr": 3.761248603800514e-05, "epoch": 7.97029702970297, "percentage": 39.85, "elapsed_time": "2:50:55", "remaining_time": "4:17:58", "throughput": 1490.94, "total_tokens": 15290176} {"current_steps": 72455, "total_steps": 181800, "loss": 0.0111, "lr": 3.761041373256517e-05, "epoch": 7.9708470847084705, "percentage": 39.85, "elapsed_time": "2:50:56", "remaining_time": "4:17:57", "throughput": 1490.94, "total_tokens": 15291200} {"current_steps": 72460, "total_steps": 181800, "loss": 0.1294, "lr": 3.760834131090106e-05, "epoch": 7.971397139713972, "percentage": 39.86, "elapsed_time": "2:50:56", "remaining_time": "4:17:57", "throughput": 1490.94, "total_tokens": 15292256} {"current_steps": 72465, "total_steps": 181800, "loss": 0.0725, "lr": 3.7606268773031926e-05, "epoch": 7.971947194719472, "percentage": 39.86, "elapsed_time": "2:50:57", "remaining_time": "4:17:56", "throughput": 1490.95, "total_tokens": 15293376} {"current_steps": 72470, "total_steps": 181800, "loss": 0.0238, "lr": 3.7604196118976854e-05, "epoch": 7.972497249724973, "percentage": 39.86, "elapsed_time": "2:50:58", "remaining_time": "4:17:55", "throughput": 1490.95, "total_tokens": 15294400} {"current_steps": 72475, "total_steps": 181800, "loss": 0.0155, "lr": 3.760212334875496e-05, "epoch": 7.973047304730473, "percentage": 39.87, "elapsed_time": "2:50:58", "remaining_time": "4:17:55", "throughput": 1490.94, "total_tokens": 15295392} {"current_steps": 72480, "total_steps": 181800, "loss": 0.0276, "lr": 3.760005046238534e-05, "epoch": 7.973597359735973, "percentage": 39.87, "elapsed_time": "2:50:59", "remaining_time": "4:17:54", "throughput": 1490.95, "total_tokens": 15296480} {"current_steps": 72485, "total_steps": 181800, "loss": 0.0304, "lr": 3.7597977459887105e-05, "epoch": 7.974147414741474, "percentage": 39.87, "elapsed_time": "2:51:00", "remaining_time": "4:17:53", "throughput": 1490.95, "total_tokens": 15297536} {"current_steps": 72490, "total_steps": 181800, "loss": 0.0393, "lr": 3.759590434127935e-05, "epoch": 7.974697469746975, "percentage": 39.87, "elapsed_time": "2:51:00", "remaining_time": "4:17:52", "throughput": 1490.95, "total_tokens": 15298592} {"current_steps": 72495, "total_steps": 181800, "loss": 0.0957, "lr": 3.759383110658119e-05, "epoch": 7.975247524752476, "percentage": 39.88, "elapsed_time": "2:51:01", "remaining_time": "4:17:52", "throughput": 1490.96, "total_tokens": 15299680} {"current_steps": 72500, "total_steps": 181800, "loss": 0.0081, "lr": 3.759175775581173e-05, "epoch": 7.975797579757976, "percentage": 39.88, "elapsed_time": "2:51:02", "remaining_time": "4:17:51", "throughput": 1490.96, "total_tokens": 15300672} {"current_steps": 72505, "total_steps": 181800, "loss": 0.0609, "lr": 3.758968428899009e-05, "epoch": 7.976347634763476, "percentage": 39.88, "elapsed_time": "2:51:03", "remaining_time": "4:17:50", "throughput": 1490.96, "total_tokens": 15301760} {"current_steps": 72510, "total_steps": 181800, "loss": 0.0182, "lr": 3.7587610706135366e-05, "epoch": 7.976897689768977, "percentage": 39.88, "elapsed_time": "2:51:03", "remaining_time": "4:17:49", "throughput": 1490.95, "total_tokens": 15302720} {"current_steps": 72515, "total_steps": 181800, "loss": 0.0081, "lr": 3.758553700726667e-05, "epoch": 7.977447744774477, "percentage": 39.89, "elapsed_time": "2:51:04", "remaining_time": "4:17:49", "throughput": 1490.96, "total_tokens": 15303808} {"current_steps": 72520, "total_steps": 181800, "loss": 0.0617, "lr": 3.758346319240312e-05, "epoch": 7.977997799779978, "percentage": 39.89, "elapsed_time": "2:51:05", "remaining_time": "4:17:48", "throughput": 1490.95, "total_tokens": 15304800} {"current_steps": 72525, "total_steps": 181800, "loss": 0.0301, "lr": 3.7581389261563824e-05, "epoch": 7.978547854785479, "percentage": 39.89, "elapsed_time": "2:51:05", "remaining_time": "4:17:47", "throughput": 1490.96, "total_tokens": 15305856} {"current_steps": 72530, "total_steps": 181800, "loss": 0.0072, "lr": 3.757931521476791e-05, "epoch": 7.979097909790979, "percentage": 39.9, "elapsed_time": "2:51:06", "remaining_time": "4:17:46", "throughput": 1490.96, "total_tokens": 15306880} {"current_steps": 72535, "total_steps": 181800, "loss": 0.0212, "lr": 3.757724105203448e-05, "epoch": 7.97964796479648, "percentage": 39.9, "elapsed_time": "2:51:07", "remaining_time": "4:17:46", "throughput": 1490.96, "total_tokens": 15307904} {"current_steps": 72540, "total_steps": 181800, "loss": 0.0091, "lr": 3.757516677338266e-05, "epoch": 7.98019801980198, "percentage": 39.9, "elapsed_time": "2:51:07", "remaining_time": "4:17:45", "throughput": 1490.96, "total_tokens": 15308960} {"current_steps": 72545, "total_steps": 181800, "loss": 0.0318, "lr": 3.7573092378831555e-05, "epoch": 7.98074807480748, "percentage": 39.9, "elapsed_time": "2:51:08", "remaining_time": "4:17:44", "throughput": 1490.96, "total_tokens": 15310016} {"current_steps": 72550, "total_steps": 181800, "loss": 0.0323, "lr": 3.757101786840029e-05, "epoch": 7.9812981298129815, "percentage": 39.91, "elapsed_time": "2:51:09", "remaining_time": "4:17:44", "throughput": 1490.96, "total_tokens": 15311040} {"current_steps": 72555, "total_steps": 181800, "loss": 0.0072, "lr": 3.756894324210799e-05, "epoch": 7.981848184818482, "percentage": 39.91, "elapsed_time": "2:51:09", "remaining_time": "4:17:43", "throughput": 1490.96, "total_tokens": 15312064} {"current_steps": 72560, "total_steps": 181800, "loss": 0.0825, "lr": 3.756686849997377e-05, "epoch": 7.982398239823983, "percentage": 39.91, "elapsed_time": "2:51:10", "remaining_time": "4:17:42", "throughput": 1490.97, "total_tokens": 15313152} {"current_steps": 72565, "total_steps": 181800, "loss": 0.0718, "lr": 3.756479364201675e-05, "epoch": 7.982948294829483, "percentage": 39.91, "elapsed_time": "2:51:11", "remaining_time": "4:17:41", "throughput": 1490.97, "total_tokens": 15314240} {"current_steps": 72570, "total_steps": 181800, "loss": 0.0318, "lr": 3.756271866825606e-05, "epoch": 7.983498349834983, "percentage": 39.92, "elapsed_time": "2:51:11", "remaining_time": "4:17:41", "throughput": 1490.98, "total_tokens": 15315296} {"current_steps": 72575, "total_steps": 181800, "loss": 0.0124, "lr": 3.756064357871082e-05, "epoch": 7.984048404840484, "percentage": 39.92, "elapsed_time": "2:51:12", "remaining_time": "4:17:40", "throughput": 1490.98, "total_tokens": 15316320} {"current_steps": 72580, "total_steps": 181800, "loss": 0.0108, "lr": 3.755856837340015e-05, "epoch": 7.9845984598459845, "percentage": 39.92, "elapsed_time": "2:51:13", "remaining_time": "4:17:39", "throughput": 1490.98, "total_tokens": 15317440} {"current_steps": 72585, "total_steps": 181800, "loss": 0.0137, "lr": 3.7556493052343187e-05, "epoch": 7.985148514851485, "percentage": 39.93, "elapsed_time": "2:51:14", "remaining_time": "4:17:38", "throughput": 1490.99, "total_tokens": 15318496} {"current_steps": 72590, "total_steps": 181800, "loss": 0.0131, "lr": 3.755441761555906e-05, "epoch": 7.985698569856986, "percentage": 39.93, "elapsed_time": "2:51:14", "remaining_time": "4:17:38", "throughput": 1490.98, "total_tokens": 15319456} {"current_steps": 72595, "total_steps": 181800, "loss": 0.0206, "lr": 3.755234206306687e-05, "epoch": 7.986248624862486, "percentage": 39.93, "elapsed_time": "2:51:15", "remaining_time": "4:17:37", "throughput": 1490.98, "total_tokens": 15320512} {"current_steps": 72600, "total_steps": 181800, "loss": 0.1867, "lr": 3.755026639488578e-05, "epoch": 7.986798679867987, "percentage": 39.93, "elapsed_time": "2:51:16", "remaining_time": "4:17:36", "throughput": 1490.98, "total_tokens": 15321536} {"current_steps": 72605, "total_steps": 181800, "loss": 0.0194, "lr": 3.7548190611034904e-05, "epoch": 7.987348734873487, "percentage": 39.94, "elapsed_time": "2:51:16", "remaining_time": "4:17:35", "throughput": 1490.98, "total_tokens": 15322560} {"current_steps": 72610, "total_steps": 181800, "loss": 0.0377, "lr": 3.754611471153337e-05, "epoch": 7.987898789878988, "percentage": 39.94, "elapsed_time": "2:51:17", "remaining_time": "4:17:35", "throughput": 1490.98, "total_tokens": 15323616} {"current_steps": 72615, "total_steps": 181800, "loss": 0.0583, "lr": 3.754403869640033e-05, "epoch": 7.988448844884489, "percentage": 39.94, "elapsed_time": "2:51:18", "remaining_time": "4:17:34", "throughput": 1490.98, "total_tokens": 15324640} {"current_steps": 72620, "total_steps": 181800, "loss": 0.0098, "lr": 3.75419625656549e-05, "epoch": 7.988998899889989, "percentage": 39.94, "elapsed_time": "2:51:18", "remaining_time": "4:17:33", "throughput": 1490.99, "total_tokens": 15325728} {"current_steps": 72625, "total_steps": 181800, "loss": 0.0099, "lr": 3.753988631931622e-05, "epoch": 7.98954895489549, "percentage": 39.95, "elapsed_time": "2:51:19", "remaining_time": "4:17:32", "throughput": 1490.99, "total_tokens": 15326784} {"current_steps": 72630, "total_steps": 181800, "loss": 0.0177, "lr": 3.753780995740342e-05, "epoch": 7.99009900990099, "percentage": 39.95, "elapsed_time": "2:51:20", "remaining_time": "4:17:32", "throughput": 1490.99, "total_tokens": 15327808} {"current_steps": 72635, "total_steps": 181800, "loss": 0.0086, "lr": 3.753573347993564e-05, "epoch": 7.99064906490649, "percentage": 39.95, "elapsed_time": "2:51:20", "remaining_time": "4:17:31", "throughput": 1491.0, "total_tokens": 15328928} {"current_steps": 72640, "total_steps": 181800, "loss": 0.0461, "lr": 3.753365688693202e-05, "epoch": 7.991199119911991, "percentage": 39.96, "elapsed_time": "2:51:21", "remaining_time": "4:17:30", "throughput": 1491.0, "total_tokens": 15329952} {"current_steps": 72645, "total_steps": 181800, "loss": 0.0099, "lr": 3.7531580178411705e-05, "epoch": 7.991749174917492, "percentage": 39.96, "elapsed_time": "2:51:22", "remaining_time": "4:17:30", "throughput": 1491.0, "total_tokens": 15331008} {"current_steps": 72650, "total_steps": 181800, "loss": 0.0418, "lr": 3.752950335439383e-05, "epoch": 7.992299229922993, "percentage": 39.96, "elapsed_time": "2:51:23", "remaining_time": "4:17:29", "throughput": 1491.0, "total_tokens": 15332000} {"current_steps": 72655, "total_steps": 181800, "loss": 0.0349, "lr": 3.7527426414897534e-05, "epoch": 7.992849284928493, "percentage": 39.96, "elapsed_time": "2:51:23", "remaining_time": "4:17:28", "throughput": 1491.0, "total_tokens": 15333024} {"current_steps": 72660, "total_steps": 181800, "loss": 0.0221, "lr": 3.7525349359941954e-05, "epoch": 7.993399339933993, "percentage": 39.97, "elapsed_time": "2:51:24", "remaining_time": "4:17:27", "throughput": 1490.99, "total_tokens": 15334016} {"current_steps": 72665, "total_steps": 181800, "loss": 0.0339, "lr": 3.7523272189546245e-05, "epoch": 7.993949394939494, "percentage": 39.97, "elapsed_time": "2:51:25", "remaining_time": "4:17:27", "throughput": 1491.0, "total_tokens": 15335072} {"current_steps": 72670, "total_steps": 181800, "loss": 0.0054, "lr": 3.752119490372954e-05, "epoch": 7.994499449944994, "percentage": 39.97, "elapsed_time": "2:51:25", "remaining_time": "4:17:26", "throughput": 1491.0, "total_tokens": 15336160} {"current_steps": 72675, "total_steps": 181800, "loss": 0.0034, "lr": 3.7519117502510994e-05, "epoch": 7.9950495049504955, "percentage": 39.98, "elapsed_time": "2:51:26", "remaining_time": "4:17:25", "throughput": 1491.0, "total_tokens": 15337184} {"current_steps": 72680, "total_steps": 181800, "loss": 0.0382, "lr": 3.7517039985909745e-05, "epoch": 7.995599559955996, "percentage": 39.98, "elapsed_time": "2:51:27", "remaining_time": "4:17:24", "throughput": 1491.01, "total_tokens": 15338272} {"current_steps": 72685, "total_steps": 181800, "loss": 0.018, "lr": 3.751496235394495e-05, "epoch": 7.996149614961496, "percentage": 39.98, "elapsed_time": "2:51:27", "remaining_time": "4:17:24", "throughput": 1491.01, "total_tokens": 15339360} {"current_steps": 72690, "total_steps": 181800, "loss": 0.0699, "lr": 3.751288460663575e-05, "epoch": 7.996699669966997, "percentage": 39.98, "elapsed_time": "2:51:28", "remaining_time": "4:17:23", "throughput": 1491.01, "total_tokens": 15340384} {"current_steps": 72695, "total_steps": 181800, "loss": 0.013, "lr": 3.75108067440013e-05, "epoch": 7.997249724972497, "percentage": 39.99, "elapsed_time": "2:51:29", "remaining_time": "4:17:22", "throughput": 1491.01, "total_tokens": 15341440} {"current_steps": 72700, "total_steps": 181800, "loss": 0.0869, "lr": 3.750872876606074e-05, "epoch": 7.997799779977997, "percentage": 39.99, "elapsed_time": "2:51:29", "remaining_time": "4:17:22", "throughput": 1491.02, "total_tokens": 15342496} {"current_steps": 72705, "total_steps": 181800, "loss": 0.0985, "lr": 3.750665067283323e-05, "epoch": 7.9983498349834985, "percentage": 39.99, "elapsed_time": "2:51:30", "remaining_time": "4:17:21", "throughput": 1491.02, "total_tokens": 15343552} {"current_steps": 72710, "total_steps": 181800, "loss": 0.0138, "lr": 3.7504572464337936e-05, "epoch": 7.998899889988999, "percentage": 39.99, "elapsed_time": "2:51:31", "remaining_time": "4:17:20", "throughput": 1491.02, "total_tokens": 15344608} {"current_steps": 72715, "total_steps": 181800, "loss": 0.0246, "lr": 3.750249414059398e-05, "epoch": 7.9994499449945, "percentage": 40.0, "elapsed_time": "2:51:32", "remaining_time": "4:17:19", "throughput": 1491.03, "total_tokens": 15345696} {"current_steps": 72720, "total_steps": 181800, "loss": 0.008, "lr": 3.7500415701620537e-05, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "2:51:32", "remaining_time": "4:17:19", "throughput": 1491.02, "total_tokens": 15346672} {"current_steps": 72720, "total_steps": 181800, "eval_loss": 0.06365779042243958, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "2:52:09", "remaining_time": "4:18:14", "throughput": 1485.68, "total_tokens": 15346672} {"current_steps": 72725, "total_steps": 181800, "loss": 0.0528, "lr": 3.749833714743677e-05, "epoch": 8.000550055005501, "percentage": 40.0, "elapsed_time": "2:52:11", "remaining_time": "4:18:15", "throughput": 1485.5, "total_tokens": 15347728} {"current_steps": 72730, "total_steps": 181800, "loss": 0.0957, "lr": 3.749625847806182e-05, "epoch": 8.001100110011, "percentage": 40.01, "elapsed_time": "2:52:12", "remaining_time": "4:18:15", "throughput": 1485.5, "total_tokens": 15348784} {"current_steps": 72735, "total_steps": 181800, "loss": 0.0028, "lr": 3.7494179693514866e-05, "epoch": 8.001650165016502, "percentage": 40.01, "elapsed_time": "2:52:13", "remaining_time": "4:18:14", "throughput": 1485.5, "total_tokens": 15349840} {"current_steps": 72740, "total_steps": 181800, "loss": 0.0306, "lr": 3.749210079381504e-05, "epoch": 8.002200220022003, "percentage": 40.01, "elapsed_time": "2:52:13", "remaining_time": "4:18:13", "throughput": 1485.51, "total_tokens": 15350928} {"current_steps": 72745, "total_steps": 181800, "loss": 0.0229, "lr": 3.749002177898151e-05, "epoch": 8.002750275027502, "percentage": 40.01, "elapsed_time": "2:52:14", "remaining_time": "4:18:12", "throughput": 1485.51, "total_tokens": 15352016} {"current_steps": 72750, "total_steps": 181800, "loss": 0.1151, "lr": 3.7487942649033445e-05, "epoch": 8.003300330033003, "percentage": 40.02, "elapsed_time": "2:52:15", "remaining_time": "4:18:12", "throughput": 1485.51, "total_tokens": 15353040} {"current_steps": 72755, "total_steps": 181800, "loss": 0.0486, "lr": 3.748586340399002e-05, "epoch": 8.003850385038504, "percentage": 40.02, "elapsed_time": "2:52:15", "remaining_time": "4:18:11", "throughput": 1485.51, "total_tokens": 15354032} {"current_steps": 72760, "total_steps": 181800, "loss": 0.0595, "lr": 3.748378404387037e-05, "epoch": 8.004400440044005, "percentage": 40.02, "elapsed_time": "2:52:16", "remaining_time": "4:18:10", "throughput": 1485.51, "total_tokens": 15355088} {"current_steps": 72765, "total_steps": 181800, "loss": 0.1207, "lr": 3.7481704568693674e-05, "epoch": 8.004950495049505, "percentage": 40.02, "elapsed_time": "2:52:17", "remaining_time": "4:18:10", "throughput": 1485.49, "total_tokens": 15356144} {"current_steps": 72770, "total_steps": 181800, "loss": 0.0567, "lr": 3.74796249784791e-05, "epoch": 8.005500550055006, "percentage": 40.03, "elapsed_time": "2:52:18", "remaining_time": "4:18:09", "throughput": 1485.49, "total_tokens": 15357168} {"current_steps": 72775, "total_steps": 181800, "loss": 0.0171, "lr": 3.7477545273245807e-05, "epoch": 8.006050605060507, "percentage": 40.03, "elapsed_time": "2:52:18", "remaining_time": "4:18:08", "throughput": 1485.49, "total_tokens": 15358192} {"current_steps": 72780, "total_steps": 181800, "loss": 0.0096, "lr": 3.747546545301297e-05, "epoch": 8.006600660066006, "percentage": 40.03, "elapsed_time": "2:52:19", "remaining_time": "4:18:08", "throughput": 1485.48, "total_tokens": 15359248} {"current_steps": 72785, "total_steps": 181800, "loss": 0.009, "lr": 3.747338551779975e-05, "epoch": 8.007150715071507, "percentage": 40.04, "elapsed_time": "2:52:20", "remaining_time": "4:18:07", "throughput": 1485.49, "total_tokens": 15360304} {"current_steps": 72790, "total_steps": 181800, "loss": 0.052, "lr": 3.747130546762532e-05, "epoch": 8.007700770077008, "percentage": 40.04, "elapsed_time": "2:52:20", "remaining_time": "4:18:06", "throughput": 1485.49, "total_tokens": 15361392} {"current_steps": 72795, "total_steps": 181800, "loss": 0.0773, "lr": 3.746922530250886e-05, "epoch": 8.008250825082508, "percentage": 40.04, "elapsed_time": "2:52:21", "remaining_time": "4:18:05", "throughput": 1485.49, "total_tokens": 15362448} {"current_steps": 72800, "total_steps": 181800, "loss": 0.0651, "lr": 3.746714502246953e-05, "epoch": 8.008800880088009, "percentage": 40.04, "elapsed_time": "2:52:22", "remaining_time": "4:18:05", "throughput": 1485.5, "total_tokens": 15363504} {"current_steps": 72805, "total_steps": 181800, "loss": 0.0331, "lr": 3.74650646275265e-05, "epoch": 8.00935093509351, "percentage": 40.05, "elapsed_time": "2:52:23", "remaining_time": "4:18:04", "throughput": 1485.5, "total_tokens": 15364528} {"current_steps": 72810, "total_steps": 181800, "loss": 0.0428, "lr": 3.746298411769896e-05, "epoch": 8.009900990099009, "percentage": 40.05, "elapsed_time": "2:52:23", "remaining_time": "4:18:03", "throughput": 1485.5, "total_tokens": 15365584} {"current_steps": 72815, "total_steps": 181800, "loss": 0.1353, "lr": 3.7460903493006075e-05, "epoch": 8.01045104510451, "percentage": 40.05, "elapsed_time": "2:52:24", "remaining_time": "4:18:02", "throughput": 1485.49, "total_tokens": 15366576} {"current_steps": 72820, "total_steps": 181800, "loss": 0.0478, "lr": 3.745882275346701e-05, "epoch": 8.011001100110011, "percentage": 40.06, "elapsed_time": "2:52:25", "remaining_time": "4:18:02", "throughput": 1485.49, "total_tokens": 15367536} {"current_steps": 72825, "total_steps": 181800, "loss": 0.0281, "lr": 3.7456741899100966e-05, "epoch": 8.011551155115512, "percentage": 40.06, "elapsed_time": "2:52:25", "remaining_time": "4:18:01", "throughput": 1485.49, "total_tokens": 15368624} {"current_steps": 72830, "total_steps": 181800, "loss": 0.0067, "lr": 3.745466092992711e-05, "epoch": 8.012101210121012, "percentage": 40.06, "elapsed_time": "2:52:26", "remaining_time": "4:18:00", "throughput": 1485.49, "total_tokens": 15369584} {"current_steps": 72835, "total_steps": 181800, "loss": 0.0057, "lr": 3.745257984596461e-05, "epoch": 8.012651265126513, "percentage": 40.06, "elapsed_time": "2:52:27", "remaining_time": "4:17:59", "throughput": 1485.49, "total_tokens": 15370672} {"current_steps": 72840, "total_steps": 181800, "loss": 0.0027, "lr": 3.7450498647232665e-05, "epoch": 8.013201320132014, "percentage": 40.07, "elapsed_time": "2:52:27", "remaining_time": "4:17:59", "throughput": 1485.5, "total_tokens": 15371728} {"current_steps": 72845, "total_steps": 181800, "loss": 0.0289, "lr": 3.7448417333750455e-05, "epoch": 8.013751375137513, "percentage": 40.07, "elapsed_time": "2:52:28", "remaining_time": "4:17:58", "throughput": 1485.5, "total_tokens": 15372752} {"current_steps": 72850, "total_steps": 181800, "loss": 0.052, "lr": 3.744633590553714e-05, "epoch": 8.014301430143014, "percentage": 40.07, "elapsed_time": "2:52:29", "remaining_time": "4:17:57", "throughput": 1485.5, "total_tokens": 15373776} {"current_steps": 72855, "total_steps": 181800, "loss": 0.0235, "lr": 3.744425436261193e-05, "epoch": 8.014851485148515, "percentage": 40.07, "elapsed_time": "2:52:29", "remaining_time": "4:17:56", "throughput": 1485.5, "total_tokens": 15374800} {"current_steps": 72860, "total_steps": 181800, "loss": 0.1141, "lr": 3.7442172704993995e-05, "epoch": 8.015401540154015, "percentage": 40.08, "elapsed_time": "2:52:30", "remaining_time": "4:17:56", "throughput": 1485.5, "total_tokens": 15375888} {"current_steps": 72865, "total_steps": 181800, "loss": 0.0687, "lr": 3.7440090932702524e-05, "epoch": 8.015951595159516, "percentage": 40.08, "elapsed_time": "2:52:31", "remaining_time": "4:17:55", "throughput": 1485.5, "total_tokens": 15376944} {"current_steps": 72870, "total_steps": 181800, "loss": 0.0753, "lr": 3.743800904575671e-05, "epoch": 8.016501650165017, "percentage": 40.08, "elapsed_time": "2:52:32", "remaining_time": "4:17:54", "throughput": 1485.5, "total_tokens": 15377936} {"current_steps": 72875, "total_steps": 181800, "loss": 0.0052, "lr": 3.743592704417573e-05, "epoch": 8.017051705170518, "percentage": 40.09, "elapsed_time": "2:52:32", "remaining_time": "4:17:54", "throughput": 1485.5, "total_tokens": 15378992} {"current_steps": 72880, "total_steps": 181800, "loss": 0.0731, "lr": 3.743384492797878e-05, "epoch": 8.017601760176017, "percentage": 40.09, "elapsed_time": "2:52:33", "remaining_time": "4:17:53", "throughput": 1485.51, "total_tokens": 15380048} {"current_steps": 72885, "total_steps": 181800, "loss": 0.0278, "lr": 3.743176269718504e-05, "epoch": 8.018151815181518, "percentage": 40.09, "elapsed_time": "2:52:34", "remaining_time": "4:17:52", "throughput": 1485.51, "total_tokens": 15381072} {"current_steps": 72890, "total_steps": 181800, "loss": 0.0116, "lr": 3.742968035181371e-05, "epoch": 8.01870187018702, "percentage": 40.09, "elapsed_time": "2:52:34", "remaining_time": "4:17:51", "throughput": 1485.51, "total_tokens": 15382160} {"current_steps": 72895, "total_steps": 181800, "loss": 0.0108, "lr": 3.7427597891883985e-05, "epoch": 8.019251925192519, "percentage": 40.1, "elapsed_time": "2:52:35", "remaining_time": "4:17:51", "throughput": 1485.51, "total_tokens": 15383184} {"current_steps": 72900, "total_steps": 181800, "loss": 0.0317, "lr": 3.7425515317415064e-05, "epoch": 8.01980198019802, "percentage": 40.1, "elapsed_time": "2:52:36", "remaining_time": "4:17:50", "throughput": 1485.52, "total_tokens": 15384272} {"current_steps": 72905, "total_steps": 181800, "loss": 0.0465, "lr": 3.7423432628426116e-05, "epoch": 8.020352035203521, "percentage": 40.1, "elapsed_time": "2:52:36", "remaining_time": "4:17:49", "throughput": 1485.52, "total_tokens": 15385328} {"current_steps": 72910, "total_steps": 181800, "loss": 0.0066, "lr": 3.742134982493635e-05, "epoch": 8.02090209020902, "percentage": 40.1, "elapsed_time": "2:52:37", "remaining_time": "4:17:48", "throughput": 1485.52, "total_tokens": 15386352} {"current_steps": 72915, "total_steps": 181800, "loss": 0.0071, "lr": 3.741926690696497e-05, "epoch": 8.021452145214521, "percentage": 40.11, "elapsed_time": "2:52:38", "remaining_time": "4:17:48", "throughput": 1485.53, "total_tokens": 15387440} {"current_steps": 72920, "total_steps": 181800, "loss": 0.0271, "lr": 3.7417183874531165e-05, "epoch": 8.022002200220022, "percentage": 40.11, "elapsed_time": "2:52:38", "remaining_time": "4:17:47", "throughput": 1485.53, "total_tokens": 15388496} {"current_steps": 72925, "total_steps": 181800, "loss": 0.0078, "lr": 3.7415100727654137e-05, "epoch": 8.022552255225522, "percentage": 40.11, "elapsed_time": "2:52:39", "remaining_time": "4:17:46", "throughput": 1485.54, "total_tokens": 15389584} {"current_steps": 72930, "total_steps": 181800, "loss": 0.0156, "lr": 3.741301746635308e-05, "epoch": 8.023102310231023, "percentage": 40.12, "elapsed_time": "2:52:40", "remaining_time": "4:17:45", "throughput": 1485.54, "total_tokens": 15390640} {"current_steps": 72935, "total_steps": 181800, "loss": 0.1108, "lr": 3.7410934090647193e-05, "epoch": 8.023652365236524, "percentage": 40.12, "elapsed_time": "2:52:40", "remaining_time": "4:17:45", "throughput": 1485.54, "total_tokens": 15391696} {"current_steps": 72940, "total_steps": 181800, "loss": 0.0199, "lr": 3.740885060055569e-05, "epoch": 8.024202420242025, "percentage": 40.12, "elapsed_time": "2:52:41", "remaining_time": "4:17:44", "throughput": 1485.55, "total_tokens": 15392816} {"current_steps": 72945, "total_steps": 181800, "loss": 0.0489, "lr": 3.740676699609776e-05, "epoch": 8.024752475247524, "percentage": 40.12, "elapsed_time": "2:52:42", "remaining_time": "4:17:43", "throughput": 1485.55, "total_tokens": 15393840} {"current_steps": 72950, "total_steps": 181800, "loss": 0.0047, "lr": 3.740468327729261e-05, "epoch": 8.025302530253025, "percentage": 40.13, "elapsed_time": "2:52:43", "remaining_time": "4:17:42", "throughput": 1485.56, "total_tokens": 15394928} {"current_steps": 72955, "total_steps": 181800, "loss": 0.0186, "lr": 3.740259944415945e-05, "epoch": 8.025852585258527, "percentage": 40.13, "elapsed_time": "2:52:43", "remaining_time": "4:17:42", "throughput": 1485.56, "total_tokens": 15396016} {"current_steps": 72960, "total_steps": 181800, "loss": 0.0036, "lr": 3.7400515496717484e-05, "epoch": 8.026402640264026, "percentage": 40.13, "elapsed_time": "2:52:44", "remaining_time": "4:17:41", "throughput": 1485.56, "total_tokens": 15397040} {"current_steps": 72965, "total_steps": 181800, "loss": 0.0565, "lr": 3.739843143498591e-05, "epoch": 8.026952695269527, "percentage": 40.13, "elapsed_time": "2:52:45", "remaining_time": "4:17:40", "throughput": 1485.57, "total_tokens": 15398096} {"current_steps": 72970, "total_steps": 181800, "loss": 0.1005, "lr": 3.739634725898396e-05, "epoch": 8.027502750275028, "percentage": 40.14, "elapsed_time": "2:52:45", "remaining_time": "4:17:39", "throughput": 1485.57, "total_tokens": 15399184} {"current_steps": 72975, "total_steps": 181800, "loss": 0.066, "lr": 3.7394262968730804e-05, "epoch": 8.028052805280527, "percentage": 40.14, "elapsed_time": "2:52:46", "remaining_time": "4:17:39", "throughput": 1485.58, "total_tokens": 15400272} {"current_steps": 72980, "total_steps": 181800, "loss": 0.0089, "lr": 3.739217856424568e-05, "epoch": 8.028602860286028, "percentage": 40.14, "elapsed_time": "2:52:47", "remaining_time": "4:17:38", "throughput": 1485.58, "total_tokens": 15401328} {"current_steps": 72985, "total_steps": 181800, "loss": 0.0103, "lr": 3.7390094045547804e-05, "epoch": 8.02915291529153, "percentage": 40.15, "elapsed_time": "2:52:47", "remaining_time": "4:17:37", "throughput": 1485.58, "total_tokens": 15402384} {"current_steps": 72990, "total_steps": 181800, "loss": 0.0283, "lr": 3.7388009412656366e-05, "epoch": 8.029702970297029, "percentage": 40.15, "elapsed_time": "2:52:48", "remaining_time": "4:17:36", "throughput": 1485.58, "total_tokens": 15403408} {"current_steps": 72995, "total_steps": 181800, "loss": 0.008, "lr": 3.738592466559059e-05, "epoch": 8.03025302530253, "percentage": 40.15, "elapsed_time": "2:52:49", "remaining_time": "4:17:36", "throughput": 1485.59, "total_tokens": 15404528} {"current_steps": 73000, "total_steps": 181800, "loss": 0.005, "lr": 3.738383980436969e-05, "epoch": 8.030803080308031, "percentage": 40.15, "elapsed_time": "2:52:49", "remaining_time": "4:17:35", "throughput": 1485.6, "total_tokens": 15405584} {"current_steps": 73005, "total_steps": 181800, "loss": 0.1234, "lr": 3.738175482901288e-05, "epoch": 8.031353135313532, "percentage": 40.16, "elapsed_time": "2:52:50", "remaining_time": "4:17:34", "throughput": 1485.6, "total_tokens": 15406672} {"current_steps": 73010, "total_steps": 181800, "loss": 0.0237, "lr": 3.737966973953938e-05, "epoch": 8.031903190319031, "percentage": 40.16, "elapsed_time": "2:52:51", "remaining_time": "4:17:34", "throughput": 1485.6, "total_tokens": 15407728} {"current_steps": 73015, "total_steps": 181800, "loss": 0.0196, "lr": 3.737758453596841e-05, "epoch": 8.032453245324533, "percentage": 40.16, "elapsed_time": "2:52:52", "remaining_time": "4:17:33", "throughput": 1485.61, "total_tokens": 15408784} {"current_steps": 73020, "total_steps": 181800, "loss": 0.0503, "lr": 3.7375499218319177e-05, "epoch": 8.033003300330034, "percentage": 40.17, "elapsed_time": "2:52:52", "remaining_time": "4:17:32", "throughput": 1485.61, "total_tokens": 15409840} {"current_steps": 73025, "total_steps": 181800, "loss": 0.1021, "lr": 3.73734137866109e-05, "epoch": 8.033553355335533, "percentage": 40.17, "elapsed_time": "2:52:53", "remaining_time": "4:17:31", "throughput": 1485.61, "total_tokens": 15410896} {"current_steps": 73030, "total_steps": 181800, "loss": 0.0256, "lr": 3.737132824086281e-05, "epoch": 8.034103410341034, "percentage": 40.17, "elapsed_time": "2:52:54", "remaining_time": "4:17:31", "throughput": 1485.61, "total_tokens": 15411920} {"current_steps": 73035, "total_steps": 181800, "loss": 0.0134, "lr": 3.736924258109412e-05, "epoch": 8.034653465346535, "percentage": 40.17, "elapsed_time": "2:52:54", "remaining_time": "4:17:30", "throughput": 1485.62, "total_tokens": 15413008} {"current_steps": 73040, "total_steps": 181800, "loss": 0.043, "lr": 3.7367156807324066e-05, "epoch": 8.035203520352034, "percentage": 40.18, "elapsed_time": "2:52:55", "remaining_time": "4:17:29", "throughput": 1485.62, "total_tokens": 15414032} {"current_steps": 73045, "total_steps": 181800, "loss": 0.0036, "lr": 3.736507091957186e-05, "epoch": 8.035753575357536, "percentage": 40.18, "elapsed_time": "2:52:56", "remaining_time": "4:17:28", "throughput": 1485.61, "total_tokens": 15415024} {"current_steps": 73050, "total_steps": 181800, "loss": 0.1193, "lr": 3.7362984917856724e-05, "epoch": 8.036303630363037, "percentage": 40.18, "elapsed_time": "2:52:56", "remaining_time": "4:17:28", "throughput": 1485.62, "total_tokens": 15416112} {"current_steps": 73055, "total_steps": 181800, "loss": 0.0766, "lr": 3.736089880219789e-05, "epoch": 8.036853685368538, "percentage": 40.18, "elapsed_time": "2:52:57", "remaining_time": "4:17:27", "throughput": 1485.62, "total_tokens": 15417168} {"current_steps": 73060, "total_steps": 181800, "loss": 0.0203, "lr": 3.7358812572614586e-05, "epoch": 8.037403740374037, "percentage": 40.19, "elapsed_time": "2:52:58", "remaining_time": "4:17:26", "throughput": 1485.63, "total_tokens": 15418288} {"current_steps": 73065, "total_steps": 181800, "loss": 0.0218, "lr": 3.7356726229126036e-05, "epoch": 8.037953795379538, "percentage": 40.19, "elapsed_time": "2:52:58", "remaining_time": "4:17:25", "throughput": 1485.63, "total_tokens": 15419280} {"current_steps": 73070, "total_steps": 181800, "loss": 0.0092, "lr": 3.735463977175147e-05, "epoch": 8.03850385038504, "percentage": 40.19, "elapsed_time": "2:52:59", "remaining_time": "4:17:25", "throughput": 1485.63, "total_tokens": 15420336} {"current_steps": 73075, "total_steps": 181800, "loss": 0.0257, "lr": 3.735255320051012e-05, "epoch": 8.039053905390539, "percentage": 40.2, "elapsed_time": "2:53:00", "remaining_time": "4:17:24", "throughput": 1485.64, "total_tokens": 15421424} {"current_steps": 73080, "total_steps": 181800, "loss": 0.0147, "lr": 3.73504665154212e-05, "epoch": 8.03960396039604, "percentage": 40.2, "elapsed_time": "2:53:01", "remaining_time": "4:17:23", "throughput": 1485.64, "total_tokens": 15422480} {"current_steps": 73085, "total_steps": 181800, "loss": 0.0716, "lr": 3.734837971650397e-05, "epoch": 8.04015401540154, "percentage": 40.2, "elapsed_time": "2:53:01", "remaining_time": "4:17:22", "throughput": 1485.64, "total_tokens": 15423536} {"current_steps": 73090, "total_steps": 181800, "loss": 0.081, "lr": 3.734629280377765e-05, "epoch": 8.04070407040704, "percentage": 40.2, "elapsed_time": "2:53:02", "remaining_time": "4:17:22", "throughput": 1485.65, "total_tokens": 15424624} {"current_steps": 73095, "total_steps": 181800, "loss": 0.0781, "lr": 3.734420577726146e-05, "epoch": 8.041254125412541, "percentage": 40.21, "elapsed_time": "2:53:03", "remaining_time": "4:17:21", "throughput": 1485.65, "total_tokens": 15425616} {"current_steps": 73100, "total_steps": 181800, "loss": 0.008, "lr": 3.7342118636974664e-05, "epoch": 8.041804180418042, "percentage": 40.21, "elapsed_time": "2:53:03", "remaining_time": "4:17:20", "throughput": 1485.65, "total_tokens": 15426704} {"current_steps": 73105, "total_steps": 181800, "loss": 0.0707, "lr": 3.734003138293648e-05, "epoch": 8.042354235423542, "percentage": 40.21, "elapsed_time": "2:53:04", "remaining_time": "4:17:19", "throughput": 1485.66, "total_tokens": 15427792} {"current_steps": 73110, "total_steps": 181800, "loss": 0.0502, "lr": 3.733794401516614e-05, "epoch": 8.042904290429043, "percentage": 40.21, "elapsed_time": "2:53:05", "remaining_time": "4:17:19", "throughput": 1485.67, "total_tokens": 15428880} {"current_steps": 73115, "total_steps": 181800, "loss": 0.0549, "lr": 3.73358565336829e-05, "epoch": 8.043454345434544, "percentage": 40.22, "elapsed_time": "2:53:05", "remaining_time": "4:17:18", "throughput": 1485.66, "total_tokens": 15429872} {"current_steps": 73120, "total_steps": 181800, "loss": 0.0333, "lr": 3.7333768938505984e-05, "epoch": 8.044004400440045, "percentage": 40.22, "elapsed_time": "2:53:06", "remaining_time": "4:17:17", "throughput": 1485.67, "total_tokens": 15430960} {"current_steps": 73125, "total_steps": 181800, "loss": 0.023, "lr": 3.7331681229654635e-05, "epoch": 8.044554455445544, "percentage": 40.22, "elapsed_time": "2:53:07", "remaining_time": "4:17:17", "throughput": 1485.67, "total_tokens": 15432016} {"current_steps": 73130, "total_steps": 181800, "loss": 0.0566, "lr": 3.73295934071481e-05, "epoch": 8.045104510451045, "percentage": 40.23, "elapsed_time": "2:53:07", "remaining_time": "4:17:16", "throughput": 1485.67, "total_tokens": 15433040} {"current_steps": 73135, "total_steps": 181800, "loss": 0.011, "lr": 3.7327505471005625e-05, "epoch": 8.045654565456546, "percentage": 40.23, "elapsed_time": "2:53:08", "remaining_time": "4:17:15", "throughput": 1485.67, "total_tokens": 15434096} {"current_steps": 73140, "total_steps": 181800, "loss": 0.0613, "lr": 3.7325417421246446e-05, "epoch": 8.046204620462046, "percentage": 40.23, "elapsed_time": "2:53:09", "remaining_time": "4:17:14", "throughput": 1485.67, "total_tokens": 15435088} {"current_steps": 73145, "total_steps": 181800, "loss": 0.0216, "lr": 3.732332925788981e-05, "epoch": 8.046754675467547, "percentage": 40.23, "elapsed_time": "2:53:09", "remaining_time": "4:17:14", "throughput": 1485.67, "total_tokens": 15436144} {"current_steps": 73150, "total_steps": 181800, "loss": 0.0657, "lr": 3.7321240980954955e-05, "epoch": 8.047304730473048, "percentage": 40.24, "elapsed_time": "2:53:10", "remaining_time": "4:17:13", "throughput": 1485.68, "total_tokens": 15437200} {"current_steps": 73155, "total_steps": 181800, "loss": 0.0161, "lr": 3.731915259046113e-05, "epoch": 8.047854785478547, "percentage": 40.24, "elapsed_time": "2:53:11", "remaining_time": "4:17:12", "throughput": 1485.67, "total_tokens": 15438192} {"current_steps": 73160, "total_steps": 181800, "loss": 0.001, "lr": 3.731706408642759e-05, "epoch": 8.048404840484048, "percentage": 40.24, "elapsed_time": "2:53:12", "remaining_time": "4:17:11", "throughput": 1485.67, "total_tokens": 15439216} {"current_steps": 73165, "total_steps": 181800, "loss": 0.0205, "lr": 3.7314975468873586e-05, "epoch": 8.04895489548955, "percentage": 40.24, "elapsed_time": "2:53:12", "remaining_time": "4:17:11", "throughput": 1485.67, "total_tokens": 15440208} {"current_steps": 73170, "total_steps": 181800, "loss": 0.0054, "lr": 3.7312886737818364e-05, "epoch": 8.049504950495049, "percentage": 40.25, "elapsed_time": "2:53:13", "remaining_time": "4:17:10", "throughput": 1485.68, "total_tokens": 15441296} {"current_steps": 73175, "total_steps": 181800, "loss": 0.0032, "lr": 3.731079789328117e-05, "epoch": 8.05005500550055, "percentage": 40.25, "elapsed_time": "2:53:14", "remaining_time": "4:17:09", "throughput": 1485.68, "total_tokens": 15442320} {"current_steps": 73180, "total_steps": 181800, "loss": 0.0177, "lr": 3.730870893528126e-05, "epoch": 8.05060506050605, "percentage": 40.25, "elapsed_time": "2:53:14", "remaining_time": "4:17:08", "throughput": 1485.68, "total_tokens": 15443344} {"current_steps": 73185, "total_steps": 181800, "loss": 0.0792, "lr": 3.730661986383788e-05, "epoch": 8.051155115511552, "percentage": 40.26, "elapsed_time": "2:53:15", "remaining_time": "4:17:08", "throughput": 1485.68, "total_tokens": 15444400} {"current_steps": 73190, "total_steps": 181800, "loss": 0.04, "lr": 3.73045306789703e-05, "epoch": 8.051705170517051, "percentage": 40.26, "elapsed_time": "2:53:16", "remaining_time": "4:17:07", "throughput": 1485.68, "total_tokens": 15445488} {"current_steps": 73195, "total_steps": 181800, "loss": 0.0822, "lr": 3.730244138069775e-05, "epoch": 8.052255225522552, "percentage": 40.26, "elapsed_time": "2:53:16", "remaining_time": "4:17:06", "throughput": 1485.69, "total_tokens": 15446576} {"current_steps": 73200, "total_steps": 181800, "loss": 0.0292, "lr": 3.730035196903952e-05, "epoch": 8.052805280528053, "percentage": 40.26, "elapsed_time": "2:53:17", "remaining_time": "4:17:05", "throughput": 1485.69, "total_tokens": 15447632} {"current_steps": 73205, "total_steps": 181800, "loss": 0.0712, "lr": 3.729826244401484e-05, "epoch": 8.053355335533553, "percentage": 40.27, "elapsed_time": "2:53:18", "remaining_time": "4:17:05", "throughput": 1485.7, "total_tokens": 15448688} {"current_steps": 73210, "total_steps": 181800, "loss": 0.0137, "lr": 3.729617280564297e-05, "epoch": 8.053905390539054, "percentage": 40.27, "elapsed_time": "2:53:18", "remaining_time": "4:17:04", "throughput": 1485.7, "total_tokens": 15449808} {"current_steps": 73215, "total_steps": 181800, "loss": 0.0607, "lr": 3.7294083053943184e-05, "epoch": 8.054455445544555, "percentage": 40.27, "elapsed_time": "2:53:19", "remaining_time": "4:17:03", "throughput": 1485.71, "total_tokens": 15450864} {"current_steps": 73220, "total_steps": 181800, "loss": 0.0294, "lr": 3.7291993188934726e-05, "epoch": 8.055005500550054, "percentage": 40.28, "elapsed_time": "2:53:20", "remaining_time": "4:17:02", "throughput": 1485.71, "total_tokens": 15451888} {"current_steps": 73225, "total_steps": 181800, "loss": 0.1446, "lr": 3.7289903210636865e-05, "epoch": 8.055555555555555, "percentage": 40.28, "elapsed_time": "2:53:21", "remaining_time": "4:17:02", "throughput": 1485.71, "total_tokens": 15452944} {"current_steps": 73230, "total_steps": 181800, "loss": 0.0154, "lr": 3.728781311906887e-05, "epoch": 8.056105610561056, "percentage": 40.28, "elapsed_time": "2:53:21", "remaining_time": "4:17:01", "throughput": 1485.71, "total_tokens": 15453968} {"current_steps": 73235, "total_steps": 181800, "loss": 0.0571, "lr": 3.728572291425001e-05, "epoch": 8.056655665566556, "percentage": 40.28, "elapsed_time": "2:53:22", "remaining_time": "4:17:00", "throughput": 1485.71, "total_tokens": 15455024} {"current_steps": 73240, "total_steps": 181800, "loss": 0.0804, "lr": 3.728363259619951e-05, "epoch": 8.057205720572057, "percentage": 40.29, "elapsed_time": "2:53:23", "remaining_time": "4:17:00", "throughput": 1485.72, "total_tokens": 15456112} {"current_steps": 73245, "total_steps": 181800, "loss": 0.0746, "lr": 3.7281542164936675e-05, "epoch": 8.057755775577558, "percentage": 40.29, "elapsed_time": "2:53:23", "remaining_time": "4:16:59", "throughput": 1485.72, "total_tokens": 15457168} {"current_steps": 73250, "total_steps": 181800, "loss": 0.0188, "lr": 3.7279451620480765e-05, "epoch": 8.058305830583059, "percentage": 40.29, "elapsed_time": "2:53:24", "remaining_time": "4:16:58", "throughput": 1485.72, "total_tokens": 15458224} {"current_steps": 73255, "total_steps": 181800, "loss": 0.0284, "lr": 3.7277360962851036e-05, "epoch": 8.058855885588558, "percentage": 40.29, "elapsed_time": "2:53:25", "remaining_time": "4:16:57", "throughput": 1485.72, "total_tokens": 15459280} {"current_steps": 73260, "total_steps": 181800, "loss": 0.0564, "lr": 3.7275270192066764e-05, "epoch": 8.05940594059406, "percentage": 40.3, "elapsed_time": "2:53:25", "remaining_time": "4:16:57", "throughput": 1485.74, "total_tokens": 15460432} {"current_steps": 73265, "total_steps": 181800, "loss": 0.0172, "lr": 3.7273179308147215e-05, "epoch": 8.05995599559956, "percentage": 40.3, "elapsed_time": "2:53:26", "remaining_time": "4:16:56", "throughput": 1485.74, "total_tokens": 15461456} {"current_steps": 73270, "total_steps": 181800, "loss": 0.039, "lr": 3.7271088311111654e-05, "epoch": 8.06050605060506, "percentage": 40.3, "elapsed_time": "2:53:27", "remaining_time": "4:16:55", "throughput": 1485.74, "total_tokens": 15462544} {"current_steps": 73275, "total_steps": 181800, "loss": 0.0175, "lr": 3.7268997200979373e-05, "epoch": 8.061056105610561, "percentage": 40.31, "elapsed_time": "2:53:27", "remaining_time": "4:16:54", "throughput": 1485.75, "total_tokens": 15463664} {"current_steps": 73280, "total_steps": 181800, "loss": 0.0152, "lr": 3.726690597776963e-05, "epoch": 8.061606160616062, "percentage": 40.31, "elapsed_time": "2:53:28", "remaining_time": "4:16:54", "throughput": 1485.75, "total_tokens": 15464656} {"current_steps": 73285, "total_steps": 181800, "loss": 0.058, "lr": 3.72648146415017e-05, "epoch": 8.062156215621561, "percentage": 40.31, "elapsed_time": "2:53:29", "remaining_time": "4:16:53", "throughput": 1485.75, "total_tokens": 15465712} {"current_steps": 73290, "total_steps": 181800, "loss": 0.005, "lr": 3.726272319219485e-05, "epoch": 8.062706270627062, "percentage": 40.31, "elapsed_time": "2:53:30", "remaining_time": "4:16:52", "throughput": 1485.75, "total_tokens": 15466704} {"current_steps": 73295, "total_steps": 181800, "loss": 0.0243, "lr": 3.726063162986838e-05, "epoch": 8.063256325632564, "percentage": 40.32, "elapsed_time": "2:53:30", "remaining_time": "4:16:51", "throughput": 1485.75, "total_tokens": 15467728} {"current_steps": 73300, "total_steps": 181800, "loss": 0.1082, "lr": 3.7258539954541536e-05, "epoch": 8.063806380638065, "percentage": 40.32, "elapsed_time": "2:53:31", "remaining_time": "4:16:51", "throughput": 1485.75, "total_tokens": 15468752} {"current_steps": 73305, "total_steps": 181800, "loss": 0.0049, "lr": 3.725644816623363e-05, "epoch": 8.064356435643564, "percentage": 40.32, "elapsed_time": "2:53:32", "remaining_time": "4:16:50", "throughput": 1485.75, "total_tokens": 15469808} {"current_steps": 73310, "total_steps": 181800, "loss": 0.0854, "lr": 3.72543562649639e-05, "epoch": 8.064906490649065, "percentage": 40.32, "elapsed_time": "2:53:32", "remaining_time": "4:16:49", "throughput": 1485.75, "total_tokens": 15470864} {"current_steps": 73315, "total_steps": 181800, "loss": 0.0086, "lr": 3.725226425075166e-05, "epoch": 8.065456545654566, "percentage": 40.33, "elapsed_time": "2:53:33", "remaining_time": "4:16:48", "throughput": 1485.76, "total_tokens": 15471952} {"current_steps": 73320, "total_steps": 181800, "loss": 0.0257, "lr": 3.725017212361618e-05, "epoch": 8.066006600660065, "percentage": 40.33, "elapsed_time": "2:53:34", "remaining_time": "4:16:48", "throughput": 1485.76, "total_tokens": 15473008} {"current_steps": 73325, "total_steps": 181800, "loss": 0.0293, "lr": 3.724807988357674e-05, "epoch": 8.066556655665567, "percentage": 40.33, "elapsed_time": "2:53:34", "remaining_time": "4:16:47", "throughput": 1485.76, "total_tokens": 15474000} {"current_steps": 73330, "total_steps": 181800, "loss": 0.0066, "lr": 3.724598753065263e-05, "epoch": 8.067106710671068, "percentage": 40.34, "elapsed_time": "2:53:35", "remaining_time": "4:16:46", "throughput": 1485.76, "total_tokens": 15475088} {"current_steps": 73335, "total_steps": 181800, "loss": 0.0172, "lr": 3.7243895064863124e-05, "epoch": 8.067656765676567, "percentage": 40.34, "elapsed_time": "2:53:36", "remaining_time": "4:16:46", "throughput": 1485.77, "total_tokens": 15476144} {"current_steps": 73340, "total_steps": 181800, "loss": 0.0524, "lr": 3.7241802486227505e-05, "epoch": 8.068206820682068, "percentage": 40.34, "elapsed_time": "2:53:36", "remaining_time": "4:16:45", "throughput": 1485.76, "total_tokens": 15477168} {"current_steps": 73345, "total_steps": 181800, "loss": 0.0123, "lr": 3.7239709794765085e-05, "epoch": 8.06875687568757, "percentage": 40.34, "elapsed_time": "2:53:37", "remaining_time": "4:16:44", "throughput": 1485.76, "total_tokens": 15478192} {"current_steps": 73350, "total_steps": 181800, "loss": 0.056, "lr": 3.723761699049512e-05, "epoch": 8.069306930693068, "percentage": 40.35, "elapsed_time": "2:53:38", "remaining_time": "4:16:43", "throughput": 1485.77, "total_tokens": 15479280} {"current_steps": 73355, "total_steps": 181800, "loss": 0.0083, "lr": 3.7235524073436915e-05, "epoch": 8.06985698569857, "percentage": 40.35, "elapsed_time": "2:53:39", "remaining_time": "4:16:43", "throughput": 1485.77, "total_tokens": 15480272} {"current_steps": 73360, "total_steps": 181800, "loss": 0.0447, "lr": 3.7233431043609755e-05, "epoch": 8.07040704070407, "percentage": 40.35, "elapsed_time": "2:53:39", "remaining_time": "4:16:42", "throughput": 1485.77, "total_tokens": 15481296} {"current_steps": 73365, "total_steps": 181800, "loss": 0.0071, "lr": 3.723133790103293e-05, "epoch": 8.070957095709572, "percentage": 40.35, "elapsed_time": "2:53:40", "remaining_time": "4:16:41", "throughput": 1485.77, "total_tokens": 15482320} {"current_steps": 73370, "total_steps": 181800, "loss": 0.0028, "lr": 3.722924464572573e-05, "epoch": 8.071507150715071, "percentage": 40.36, "elapsed_time": "2:53:41", "remaining_time": "4:16:40", "throughput": 1485.77, "total_tokens": 15483376} {"current_steps": 73375, "total_steps": 181800, "loss": 0.0374, "lr": 3.7227151277707464e-05, "epoch": 8.072057205720572, "percentage": 40.36, "elapsed_time": "2:53:41", "remaining_time": "4:16:40", "throughput": 1485.78, "total_tokens": 15484496} {"current_steps": 73380, "total_steps": 181800, "loss": 0.0106, "lr": 3.7225057796997396e-05, "epoch": 8.072607260726073, "percentage": 40.36, "elapsed_time": "2:53:42", "remaining_time": "4:16:39", "throughput": 1485.78, "total_tokens": 15485552} {"current_steps": 73385, "total_steps": 181800, "loss": 0.0899, "lr": 3.722296420361484e-05, "epoch": 8.073157315731573, "percentage": 40.37, "elapsed_time": "2:53:43", "remaining_time": "4:16:38", "throughput": 1485.78, "total_tokens": 15486608} {"current_steps": 73390, "total_steps": 181800, "loss": 0.0212, "lr": 3.7220870497579096e-05, "epoch": 8.073707370737074, "percentage": 40.37, "elapsed_time": "2:53:43", "remaining_time": "4:16:37", "throughput": 1485.79, "total_tokens": 15487696} {"current_steps": 73395, "total_steps": 181800, "loss": 0.0207, "lr": 3.721877667890945e-05, "epoch": 8.074257425742575, "percentage": 40.37, "elapsed_time": "2:53:44", "remaining_time": "4:16:37", "throughput": 1485.8, "total_tokens": 15488784} {"current_steps": 73400, "total_steps": 181800, "loss": 0.0088, "lr": 3.72166827476252e-05, "epoch": 8.074807480748074, "percentage": 40.37, "elapsed_time": "2:53:45", "remaining_time": "4:16:36", "throughput": 1485.8, "total_tokens": 15489840} {"current_steps": 73405, "total_steps": 181800, "loss": 0.0247, "lr": 3.7214588703745644e-05, "epoch": 8.075357535753575, "percentage": 40.38, "elapsed_time": "2:53:45", "remaining_time": "4:16:35", "throughput": 1485.8, "total_tokens": 15490928} {"current_steps": 73410, "total_steps": 181800, "loss": 0.003, "lr": 3.721249454729009e-05, "epoch": 8.075907590759076, "percentage": 40.38, "elapsed_time": "2:53:46", "remaining_time": "4:16:34", "throughput": 1485.81, "total_tokens": 15492016} {"current_steps": 73415, "total_steps": 181800, "loss": 0.0022, "lr": 3.721040027827783e-05, "epoch": 8.076457645764576, "percentage": 40.38, "elapsed_time": "2:53:47", "remaining_time": "4:16:34", "throughput": 1485.82, "total_tokens": 15493136} {"current_steps": 73420, "total_steps": 181800, "loss": 0.013, "lr": 3.720830589672817e-05, "epoch": 8.077007700770077, "percentage": 40.39, "elapsed_time": "2:53:48", "remaining_time": "4:16:33", "throughput": 1485.82, "total_tokens": 15494192} {"current_steps": 73425, "total_steps": 181800, "loss": 0.0175, "lr": 3.7206211402660415e-05, "epoch": 8.077557755775578, "percentage": 40.39, "elapsed_time": "2:53:48", "remaining_time": "4:16:32", "throughput": 1485.82, "total_tokens": 15495248} {"current_steps": 73430, "total_steps": 181800, "loss": 0.0111, "lr": 3.7204116796093865e-05, "epoch": 8.078107810781079, "percentage": 40.39, "elapsed_time": "2:53:49", "remaining_time": "4:16:32", "throughput": 1485.82, "total_tokens": 15496272} {"current_steps": 73435, "total_steps": 181800, "loss": 0.0634, "lr": 3.7202022077047825e-05, "epoch": 8.078657865786578, "percentage": 40.39, "elapsed_time": "2:53:50", "remaining_time": "4:16:31", "throughput": 1485.83, "total_tokens": 15497328} {"current_steps": 73440, "total_steps": 181800, "loss": 0.0467, "lr": 3.719992724554161e-05, "epoch": 8.07920792079208, "percentage": 40.4, "elapsed_time": "2:53:50", "remaining_time": "4:16:30", "throughput": 1485.83, "total_tokens": 15498416} {"current_steps": 73445, "total_steps": 181800, "loss": 0.0491, "lr": 3.7197832301594516e-05, "epoch": 8.07975797579758, "percentage": 40.4, "elapsed_time": "2:53:51", "remaining_time": "4:16:29", "throughput": 1485.84, "total_tokens": 15499536} {"current_steps": 73450, "total_steps": 181800, "loss": 0.029, "lr": 3.719573724522585e-05, "epoch": 8.08030803080308, "percentage": 40.4, "elapsed_time": "2:53:52", "remaining_time": "4:16:29", "throughput": 1485.84, "total_tokens": 15500592} {"current_steps": 73455, "total_steps": 181800, "loss": 0.1114, "lr": 3.719364207645493e-05, "epoch": 8.08085808580858, "percentage": 40.4, "elapsed_time": "2:53:52", "remaining_time": "4:16:28", "throughput": 1485.84, "total_tokens": 15501616} {"current_steps": 73460, "total_steps": 181800, "loss": 0.0636, "lr": 3.7191546795301064e-05, "epoch": 8.081408140814082, "percentage": 40.41, "elapsed_time": "2:53:53", "remaining_time": "4:16:27", "throughput": 1485.84, "total_tokens": 15502608} {"current_steps": 73465, "total_steps": 181800, "loss": 0.0285, "lr": 3.718945140178356e-05, "epoch": 8.081958195819581, "percentage": 40.41, "elapsed_time": "2:53:54", "remaining_time": "4:16:26", "throughput": 1485.85, "total_tokens": 15503728} {"current_steps": 73470, "total_steps": 181800, "loss": 0.0017, "lr": 3.718735589592173e-05, "epoch": 8.082508250825082, "percentage": 40.41, "elapsed_time": "2:53:54", "remaining_time": "4:16:26", "throughput": 1485.86, "total_tokens": 15504848} {"current_steps": 73475, "total_steps": 181800, "loss": 0.0385, "lr": 3.718526027773489e-05, "epoch": 8.083058305830583, "percentage": 40.42, "elapsed_time": "2:53:55", "remaining_time": "4:16:25", "throughput": 1485.86, "total_tokens": 15505872} {"current_steps": 73480, "total_steps": 181800, "loss": 0.0996, "lr": 3.7183164547242354e-05, "epoch": 8.083608360836084, "percentage": 40.42, "elapsed_time": "2:53:56", "remaining_time": "4:16:24", "throughput": 1485.86, "total_tokens": 15506928} {"current_steps": 73485, "total_steps": 181800, "loss": 0.0779, "lr": 3.7181068704463426e-05, "epoch": 8.084158415841584, "percentage": 40.42, "elapsed_time": "2:53:57", "remaining_time": "4:16:23", "throughput": 1485.86, "total_tokens": 15507920} {"current_steps": 73490, "total_steps": 181800, "loss": 0.0309, "lr": 3.717897274941744e-05, "epoch": 8.084708470847085, "percentage": 40.42, "elapsed_time": "2:53:57", "remaining_time": "4:16:23", "throughput": 1485.87, "total_tokens": 15509104} {"current_steps": 73495, "total_steps": 181800, "loss": 0.0384, "lr": 3.717687668212372e-05, "epoch": 8.085258525852586, "percentage": 40.43, "elapsed_time": "2:53:58", "remaining_time": "4:16:22", "throughput": 1485.87, "total_tokens": 15510096} {"current_steps": 73500, "total_steps": 181800, "loss": 0.0091, "lr": 3.7174780502601555e-05, "epoch": 8.085808580858085, "percentage": 40.43, "elapsed_time": "2:53:59", "remaining_time": "4:16:21", "throughput": 1485.87, "total_tokens": 15511152} {"current_steps": 73505, "total_steps": 181800, "loss": 0.0677, "lr": 3.7172684210870276e-05, "epoch": 8.086358635863586, "percentage": 40.43, "elapsed_time": "2:53:59", "remaining_time": "4:16:20", "throughput": 1485.87, "total_tokens": 15512144} {"current_steps": 73510, "total_steps": 181800, "loss": 0.0132, "lr": 3.717058780694922e-05, "epoch": 8.086908690869087, "percentage": 40.43, "elapsed_time": "2:54:00", "remaining_time": "4:16:20", "throughput": 1485.87, "total_tokens": 15513200} {"current_steps": 73515, "total_steps": 181800, "loss": 0.083, "lr": 3.716849129085769e-05, "epoch": 8.087458745874587, "percentage": 40.44, "elapsed_time": "2:54:01", "remaining_time": "4:16:19", "throughput": 1485.87, "total_tokens": 15514288} {"current_steps": 73520, "total_steps": 181800, "loss": 0.1209, "lr": 3.7166394662615024e-05, "epoch": 8.088008800880088, "percentage": 40.44, "elapsed_time": "2:54:01", "remaining_time": "4:16:18", "throughput": 1485.87, "total_tokens": 15515312} {"current_steps": 73525, "total_steps": 181800, "loss": 0.0912, "lr": 3.7164297922240526e-05, "epoch": 8.088558855885589, "percentage": 40.44, "elapsed_time": "2:54:02", "remaining_time": "4:16:18", "throughput": 1485.88, "total_tokens": 15516432} {"current_steps": 73530, "total_steps": 181800, "loss": 0.056, "lr": 3.7162201069753527e-05, "epoch": 8.089108910891088, "percentage": 40.45, "elapsed_time": "2:54:03", "remaining_time": "4:16:17", "throughput": 1485.88, "total_tokens": 15517488} {"current_steps": 73535, "total_steps": 181800, "loss": 0.0698, "lr": 3.7160104105173365e-05, "epoch": 8.08965896589659, "percentage": 40.45, "elapsed_time": "2:54:03", "remaining_time": "4:16:16", "throughput": 1485.89, "total_tokens": 15518544} {"current_steps": 73540, "total_steps": 181800, "loss": 0.0073, "lr": 3.715800702851937e-05, "epoch": 8.09020902090209, "percentage": 40.45, "elapsed_time": "2:54:04", "remaining_time": "4:16:15", "throughput": 1485.89, "total_tokens": 15519632} {"current_steps": 73545, "total_steps": 181800, "loss": 0.0807, "lr": 3.715590983981083e-05, "epoch": 8.090759075907592, "percentage": 40.45, "elapsed_time": "2:54:05", "remaining_time": "4:16:15", "throughput": 1485.89, "total_tokens": 15520624} {"current_steps": 73550, "total_steps": 181800, "loss": 0.0652, "lr": 3.7153812539067125e-05, "epoch": 8.091309130913091, "percentage": 40.46, "elapsed_time": "2:54:06", "remaining_time": "4:16:14", "throughput": 1485.89, "total_tokens": 15521680} {"current_steps": 73555, "total_steps": 181800, "loss": 0.0114, "lr": 3.7151715126307554e-05, "epoch": 8.091859185918592, "percentage": 40.46, "elapsed_time": "2:54:06", "remaining_time": "4:16:13", "throughput": 1485.89, "total_tokens": 15522704} {"current_steps": 73560, "total_steps": 181800, "loss": 0.036, "lr": 3.714961760155144e-05, "epoch": 8.092409240924093, "percentage": 40.46, "elapsed_time": "2:54:07", "remaining_time": "4:16:12", "throughput": 1485.89, "total_tokens": 15523760} {"current_steps": 73565, "total_steps": 181800, "loss": 0.0378, "lr": 3.714751996481816e-05, "epoch": 8.092959295929592, "percentage": 40.46, "elapsed_time": "2:54:08", "remaining_time": "4:16:12", "throughput": 1485.9, "total_tokens": 15524816} {"current_steps": 73570, "total_steps": 181800, "loss": 0.0288, "lr": 3.7145422216127e-05, "epoch": 8.093509350935093, "percentage": 40.47, "elapsed_time": "2:54:08", "remaining_time": "4:16:11", "throughput": 1485.89, "total_tokens": 15525776} {"current_steps": 73575, "total_steps": 181800, "loss": 0.0025, "lr": 3.714332435549731e-05, "epoch": 8.094059405940595, "percentage": 40.47, "elapsed_time": "2:54:09", "remaining_time": "4:16:10", "throughput": 1485.89, "total_tokens": 15526832} {"current_steps": 73580, "total_steps": 181800, "loss": 0.0045, "lr": 3.7141226382948434e-05, "epoch": 8.094609460946094, "percentage": 40.47, "elapsed_time": "2:54:10", "remaining_time": "4:16:09", "throughput": 1485.9, "total_tokens": 15527920} {"current_steps": 73585, "total_steps": 181800, "loss": 0.0161, "lr": 3.7139128298499704e-05, "epoch": 8.095159515951595, "percentage": 40.48, "elapsed_time": "2:54:10", "remaining_time": "4:16:09", "throughput": 1485.9, "total_tokens": 15528976} {"current_steps": 73590, "total_steps": 181800, "loss": 0.0023, "lr": 3.7137030102170445e-05, "epoch": 8.095709570957096, "percentage": 40.48, "elapsed_time": "2:54:11", "remaining_time": "4:16:08", "throughput": 1485.9, "total_tokens": 15529968} {"current_steps": 73595, "total_steps": 181800, "loss": 0.0215, "lr": 3.713493179398e-05, "epoch": 8.096259625962595, "percentage": 40.48, "elapsed_time": "2:54:12", "remaining_time": "4:16:07", "throughput": 1485.91, "total_tokens": 15531056} {"current_steps": 73600, "total_steps": 181800, "loss": 0.029, "lr": 3.713283337394772e-05, "epoch": 8.096809680968097, "percentage": 40.48, "elapsed_time": "2:54:12", "remaining_time": "4:16:06", "throughput": 1485.91, "total_tokens": 15532176} {"current_steps": 73605, "total_steps": 181800, "loss": 0.0076, "lr": 3.713073484209293e-05, "epoch": 8.097359735973598, "percentage": 40.49, "elapsed_time": "2:54:13", "remaining_time": "4:16:06", "throughput": 1485.91, "total_tokens": 15533200} {"current_steps": 73610, "total_steps": 181800, "loss": 0.019, "lr": 3.7128636198434985e-05, "epoch": 8.097909790979099, "percentage": 40.49, "elapsed_time": "2:54:14", "remaining_time": "4:16:05", "throughput": 1485.92, "total_tokens": 15534256} {"current_steps": 73615, "total_steps": 181800, "loss": 0.012, "lr": 3.7126537442993216e-05, "epoch": 8.098459845984598, "percentage": 40.49, "elapsed_time": "2:54:15", "remaining_time": "4:16:04", "throughput": 1485.92, "total_tokens": 15535344} {"current_steps": 73620, "total_steps": 181800, "loss": 0.0849, "lr": 3.712443857578697e-05, "epoch": 8.099009900990099, "percentage": 40.5, "elapsed_time": "2:54:15", "remaining_time": "4:16:04", "throughput": 1485.93, "total_tokens": 15536400} {"current_steps": 73625, "total_steps": 181800, "loss": 0.0079, "lr": 3.712233959683559e-05, "epoch": 8.0995599559956, "percentage": 40.5, "elapsed_time": "2:54:16", "remaining_time": "4:16:03", "throughput": 1485.93, "total_tokens": 15537488} {"current_steps": 73630, "total_steps": 181800, "loss": 0.0248, "lr": 3.712024050615843e-05, "epoch": 8.1001100110011, "percentage": 40.5, "elapsed_time": "2:54:17", "remaining_time": "4:16:02", "throughput": 1485.93, "total_tokens": 15538544} {"current_steps": 73635, "total_steps": 181800, "loss": 0.0161, "lr": 3.7118141303774826e-05, "epoch": 8.1006600660066, "percentage": 40.5, "elapsed_time": "2:54:17", "remaining_time": "4:16:01", "throughput": 1485.94, "total_tokens": 15539600} {"current_steps": 73640, "total_steps": 181800, "loss": 0.0072, "lr": 3.711604198970413e-05, "epoch": 8.101210121012102, "percentage": 40.51, "elapsed_time": "2:54:18", "remaining_time": "4:16:01", "throughput": 1485.93, "total_tokens": 15540592} {"current_steps": 73645, "total_steps": 181800, "loss": 0.0038, "lr": 3.7113942563965675e-05, "epoch": 8.101760176017601, "percentage": 40.51, "elapsed_time": "2:54:19", "remaining_time": "4:16:00", "throughput": 1485.94, "total_tokens": 15541712} {"current_steps": 73650, "total_steps": 181800, "loss": 0.05, "lr": 3.7111843026578834e-05, "epoch": 8.102310231023102, "percentage": 40.51, "elapsed_time": "2:54:19", "remaining_time": "4:15:59", "throughput": 1485.94, "total_tokens": 15542736} {"current_steps": 73655, "total_steps": 181800, "loss": 0.0215, "lr": 3.710974337756295e-05, "epoch": 8.102860286028603, "percentage": 40.51, "elapsed_time": "2:54:20", "remaining_time": "4:15:58", "throughput": 1485.95, "total_tokens": 15543824} {"current_steps": 73660, "total_steps": 181800, "loss": 0.0895, "lr": 3.710764361693737e-05, "epoch": 8.103410341034103, "percentage": 40.52, "elapsed_time": "2:54:21", "remaining_time": "4:15:58", "throughput": 1485.95, "total_tokens": 15544848} {"current_steps": 73665, "total_steps": 181800, "loss": 0.0332, "lr": 3.710554374472145e-05, "epoch": 8.103960396039604, "percentage": 40.52, "elapsed_time": "2:54:21", "remaining_time": "4:15:57", "throughput": 1485.95, "total_tokens": 15545904} {"current_steps": 73670, "total_steps": 181800, "loss": 0.0451, "lr": 3.710344376093454e-05, "epoch": 8.104510451045105, "percentage": 40.52, "elapsed_time": "2:54:22", "remaining_time": "4:15:56", "throughput": 1485.95, "total_tokens": 15546960} {"current_steps": 73675, "total_steps": 181800, "loss": 0.1335, "lr": 3.7101343665596e-05, "epoch": 8.105060506050606, "percentage": 40.53, "elapsed_time": "2:54:23", "remaining_time": "4:15:55", "throughput": 1485.96, "total_tokens": 15548016} {"current_steps": 73680, "total_steps": 181800, "loss": 0.0047, "lr": 3.7099243458725183e-05, "epoch": 8.105610561056105, "percentage": 40.53, "elapsed_time": "2:54:23", "remaining_time": "4:15:55", "throughput": 1485.96, "total_tokens": 15549104} {"current_steps": 73685, "total_steps": 181800, "loss": 0.0872, "lr": 3.7097143140341445e-05, "epoch": 8.106160616061606, "percentage": 40.53, "elapsed_time": "2:54:24", "remaining_time": "4:15:54", "throughput": 1485.97, "total_tokens": 15550192} {"current_steps": 73690, "total_steps": 181800, "loss": 0.0081, "lr": 3.7095042710464136e-05, "epoch": 8.106710671067107, "percentage": 40.53, "elapsed_time": "2:54:25", "remaining_time": "4:15:53", "throughput": 1485.97, "total_tokens": 15551248} {"current_steps": 73695, "total_steps": 181800, "loss": 0.0605, "lr": 3.709294216911263e-05, "epoch": 8.107260726072607, "percentage": 40.54, "elapsed_time": "2:54:26", "remaining_time": "4:15:52", "throughput": 1485.98, "total_tokens": 15552336} {"current_steps": 73700, "total_steps": 181800, "loss": 0.0187, "lr": 3.7090841516306276e-05, "epoch": 8.107810781078108, "percentage": 40.54, "elapsed_time": "2:54:26", "remaining_time": "4:15:52", "throughput": 1485.97, "total_tokens": 15553296} {"current_steps": 73705, "total_steps": 181800, "loss": 0.0606, "lr": 3.7088740752064425e-05, "epoch": 8.108360836083609, "percentage": 40.54, "elapsed_time": "2:54:27", "remaining_time": "4:15:51", "throughput": 1485.97, "total_tokens": 15554320} {"current_steps": 73710, "total_steps": 181800, "loss": 0.0203, "lr": 3.708663987640647e-05, "epoch": 8.108910891089108, "percentage": 40.54, "elapsed_time": "2:54:28", "remaining_time": "4:15:50", "throughput": 1485.97, "total_tokens": 15555376} {"current_steps": 73715, "total_steps": 181800, "loss": 0.0129, "lr": 3.708453888935175e-05, "epoch": 8.10946094609461, "percentage": 40.55, "elapsed_time": "2:54:28", "remaining_time": "4:15:49", "throughput": 1485.98, "total_tokens": 15556432} {"current_steps": 73720, "total_steps": 181800, "loss": 0.0103, "lr": 3.708243779091963e-05, "epoch": 8.11001100110011, "percentage": 40.55, "elapsed_time": "2:54:29", "remaining_time": "4:15:49", "throughput": 1485.98, "total_tokens": 15557456} {"current_steps": 73725, "total_steps": 181800, "loss": 0.0063, "lr": 3.7080336581129474e-05, "epoch": 8.110561056105611, "percentage": 40.55, "elapsed_time": "2:54:30", "remaining_time": "4:15:48", "throughput": 1485.99, "total_tokens": 15558608} {"current_steps": 73730, "total_steps": 181800, "loss": 0.0557, "lr": 3.707823526000066e-05, "epoch": 8.11111111111111, "percentage": 40.56, "elapsed_time": "2:54:30", "remaining_time": "4:15:47", "throughput": 1486.0, "total_tokens": 15559728} {"current_steps": 73735, "total_steps": 181800, "loss": 0.0078, "lr": 3.707613382755255e-05, "epoch": 8.111661166116612, "percentage": 40.56, "elapsed_time": "2:54:31", "remaining_time": "4:15:47", "throughput": 1486.0, "total_tokens": 15560848} {"current_steps": 73740, "total_steps": 181800, "loss": 0.0555, "lr": 3.7074032283804507e-05, "epoch": 8.112211221122113, "percentage": 40.56, "elapsed_time": "2:54:32", "remaining_time": "4:15:46", "throughput": 1486.01, "total_tokens": 15561904} {"current_steps": 73745, "total_steps": 181800, "loss": 0.0241, "lr": 3.7071930628775896e-05, "epoch": 8.112761276127612, "percentage": 40.56, "elapsed_time": "2:54:32", "remaining_time": "4:15:45", "throughput": 1486.01, "total_tokens": 15562928} {"current_steps": 73750, "total_steps": 181800, "loss": 0.0132, "lr": 3.706982886248609e-05, "epoch": 8.113311331133113, "percentage": 40.57, "elapsed_time": "2:54:33", "remaining_time": "4:15:44", "throughput": 1486.01, "total_tokens": 15564016} {"current_steps": 73755, "total_steps": 181800, "loss": 0.0118, "lr": 3.7067726984954484e-05, "epoch": 8.113861386138614, "percentage": 40.57, "elapsed_time": "2:54:34", "remaining_time": "4:15:44", "throughput": 1486.02, "total_tokens": 15565072} {"current_steps": 73760, "total_steps": 181800, "loss": 0.1196, "lr": 3.706562499620041e-05, "epoch": 8.114411441144114, "percentage": 40.57, "elapsed_time": "2:54:35", "remaining_time": "4:15:43", "throughput": 1486.02, "total_tokens": 15566128} {"current_steps": 73765, "total_steps": 181800, "loss": 0.1848, "lr": 3.7063522896243266e-05, "epoch": 8.114961496149615, "percentage": 40.57, "elapsed_time": "2:54:35", "remaining_time": "4:15:42", "throughput": 1486.02, "total_tokens": 15567184} {"current_steps": 73770, "total_steps": 181800, "loss": 0.0182, "lr": 3.706142068510242e-05, "epoch": 8.115511551155116, "percentage": 40.58, "elapsed_time": "2:54:36", "remaining_time": "4:15:41", "throughput": 1486.02, "total_tokens": 15568240} {"current_steps": 73775, "total_steps": 181800, "loss": 0.0062, "lr": 3.7059318362797244e-05, "epoch": 8.116061606160615, "percentage": 40.58, "elapsed_time": "2:54:37", "remaining_time": "4:15:41", "throughput": 1486.02, "total_tokens": 15569264} {"current_steps": 73780, "total_steps": 181800, "loss": 0.0154, "lr": 3.7057215929347124e-05, "epoch": 8.116611661166116, "percentage": 40.58, "elapsed_time": "2:54:37", "remaining_time": "4:15:40", "throughput": 1486.03, "total_tokens": 15570384} {"current_steps": 73785, "total_steps": 181800, "loss": 0.05, "lr": 3.705511338477143e-05, "epoch": 8.117161716171617, "percentage": 40.59, "elapsed_time": "2:54:38", "remaining_time": "4:15:39", "throughput": 1486.04, "total_tokens": 15571472} {"current_steps": 73790, "total_steps": 181800, "loss": 0.0165, "lr": 3.705301072908953e-05, "epoch": 8.117711771177119, "percentage": 40.59, "elapsed_time": "2:54:39", "remaining_time": "4:15:38", "throughput": 1486.04, "total_tokens": 15572528} {"current_steps": 73795, "total_steps": 181800, "loss": 0.0326, "lr": 3.705090796232083e-05, "epoch": 8.118261826182618, "percentage": 40.59, "elapsed_time": "2:54:39", "remaining_time": "4:15:38", "throughput": 1486.05, "total_tokens": 15573648} {"current_steps": 73800, "total_steps": 181800, "loss": 0.1962, "lr": 3.7048805084484676e-05, "epoch": 8.118811881188119, "percentage": 40.59, "elapsed_time": "2:54:40", "remaining_time": "4:15:37", "throughput": 1486.06, "total_tokens": 15574768} {"current_steps": 73805, "total_steps": 181800, "loss": 0.032, "lr": 3.704670209560048e-05, "epoch": 8.11936193619362, "percentage": 40.6, "elapsed_time": "2:54:41", "remaining_time": "4:15:36", "throughput": 1486.06, "total_tokens": 15575792} {"current_steps": 73810, "total_steps": 181800, "loss": 0.0112, "lr": 3.7044598995687604e-05, "epoch": 8.11991199119912, "percentage": 40.6, "elapsed_time": "2:54:41", "remaining_time": "4:15:35", "throughput": 1486.06, "total_tokens": 15576816} {"current_steps": 73815, "total_steps": 181800, "loss": 0.0364, "lr": 3.7042495784765444e-05, "epoch": 8.12046204620462, "percentage": 40.6, "elapsed_time": "2:54:42", "remaining_time": "4:15:35", "throughput": 1486.06, "total_tokens": 15577840} {"current_steps": 73820, "total_steps": 181800, "loss": 0.0211, "lr": 3.704039246285337e-05, "epoch": 8.121012101210122, "percentage": 40.61, "elapsed_time": "2:54:43", "remaining_time": "4:15:34", "throughput": 1486.06, "total_tokens": 15578832} {"current_steps": 73825, "total_steps": 181800, "loss": 0.0067, "lr": 3.703828902997079e-05, "epoch": 8.12156215621562, "percentage": 40.61, "elapsed_time": "2:54:44", "remaining_time": "4:15:33", "throughput": 1486.06, "total_tokens": 15579856} {"current_steps": 73830, "total_steps": 181800, "loss": 0.0221, "lr": 3.703618548613707e-05, "epoch": 8.122112211221122, "percentage": 40.61, "elapsed_time": "2:54:44", "remaining_time": "4:15:32", "throughput": 1486.07, "total_tokens": 15580976} {"current_steps": 73835, "total_steps": 181800, "loss": 0.0752, "lr": 3.70340818313716e-05, "epoch": 8.122662266226623, "percentage": 40.61, "elapsed_time": "2:54:45", "remaining_time": "4:15:32", "throughput": 1486.06, "total_tokens": 15582000} {"current_steps": 73840, "total_steps": 181800, "loss": 0.1273, "lr": 3.7031978065693775e-05, "epoch": 8.123212321232122, "percentage": 40.62, "elapsed_time": "2:54:46", "remaining_time": "4:15:31", "throughput": 1486.07, "total_tokens": 15583088} {"current_steps": 73845, "total_steps": 181800, "loss": 0.1109, "lr": 3.702987418912298e-05, "epoch": 8.123762376237623, "percentage": 40.62, "elapsed_time": "2:54:46", "remaining_time": "4:15:30", "throughput": 1486.07, "total_tokens": 15584144} {"current_steps": 73850, "total_steps": 181800, "loss": 0.0536, "lr": 3.7027770201678615e-05, "epoch": 8.124312431243125, "percentage": 40.62, "elapsed_time": "2:54:47", "remaining_time": "4:15:30", "throughput": 1486.08, "total_tokens": 15585200} {"current_steps": 73855, "total_steps": 181800, "loss": 0.0337, "lr": 3.702566610338006e-05, "epoch": 8.124862486248626, "percentage": 40.62, "elapsed_time": "2:54:48", "remaining_time": "4:15:29", "throughput": 1486.07, "total_tokens": 15586192} {"current_steps": 73860, "total_steps": 181800, "loss": 0.0683, "lr": 3.702356189424671e-05, "epoch": 8.125412541254125, "percentage": 40.63, "elapsed_time": "2:54:48", "remaining_time": "4:15:28", "throughput": 1486.08, "total_tokens": 15587280} {"current_steps": 73865, "total_steps": 181800, "loss": 0.0047, "lr": 3.7021457574297954e-05, "epoch": 8.125962596259626, "percentage": 40.63, "elapsed_time": "2:54:49", "remaining_time": "4:15:27", "throughput": 1486.09, "total_tokens": 15588368} {"current_steps": 73870, "total_steps": 181800, "loss": 0.0201, "lr": 3.701935314355319e-05, "epoch": 8.126512651265127, "percentage": 40.63, "elapsed_time": "2:54:50", "remaining_time": "4:15:27", "throughput": 1486.09, "total_tokens": 15589392} {"current_steps": 73875, "total_steps": 181800, "loss": 0.0085, "lr": 3.701724860203183e-05, "epoch": 8.127062706270626, "percentage": 40.64, "elapsed_time": "2:54:50", "remaining_time": "4:15:26", "throughput": 1486.08, "total_tokens": 15590384} {"current_steps": 73880, "total_steps": 181800, "loss": 0.0123, "lr": 3.7015143949753244e-05, "epoch": 8.127612761276128, "percentage": 40.64, "elapsed_time": "2:54:51", "remaining_time": "4:15:25", "throughput": 1486.08, "total_tokens": 15591408} {"current_steps": 73885, "total_steps": 181800, "loss": 0.0091, "lr": 3.701303918673685e-05, "epoch": 8.128162816281629, "percentage": 40.64, "elapsed_time": "2:54:52", "remaining_time": "4:15:24", "throughput": 1486.09, "total_tokens": 15592496} {"current_steps": 73890, "total_steps": 181800, "loss": 0.0951, "lr": 3.701093431300203e-05, "epoch": 8.128712871287128, "percentage": 40.64, "elapsed_time": "2:54:52", "remaining_time": "4:15:24", "throughput": 1486.1, "total_tokens": 15593648} {"current_steps": 73895, "total_steps": 181800, "loss": 0.0103, "lr": 3.7008829328568197e-05, "epoch": 8.129262926292629, "percentage": 40.65, "elapsed_time": "2:54:53", "remaining_time": "4:15:23", "throughput": 1486.1, "total_tokens": 15594704} {"current_steps": 73900, "total_steps": 181800, "loss": 0.028, "lr": 3.700672423345475e-05, "epoch": 8.12981298129813, "percentage": 40.65, "elapsed_time": "2:54:54", "remaining_time": "4:15:22", "throughput": 1486.1, "total_tokens": 15595696} {"current_steps": 73905, "total_steps": 181800, "loss": 0.124, "lr": 3.7004619027681084e-05, "epoch": 8.130363036303631, "percentage": 40.65, "elapsed_time": "2:54:55", "remaining_time": "4:15:21", "throughput": 1486.11, "total_tokens": 15596784} {"current_steps": 73910, "total_steps": 181800, "loss": 0.0177, "lr": 3.7002513711266596e-05, "epoch": 8.13091309130913, "percentage": 40.65, "elapsed_time": "2:54:55", "remaining_time": "4:15:21", "throughput": 1486.12, "total_tokens": 15597936} {"current_steps": 73915, "total_steps": 181800, "loss": 0.0073, "lr": 3.70004082842307e-05, "epoch": 8.131463146314632, "percentage": 40.66, "elapsed_time": "2:54:56", "remaining_time": "4:15:20", "throughput": 1486.12, "total_tokens": 15598992} {"current_steps": 73920, "total_steps": 181800, "loss": 0.0145, "lr": 3.699830274659281e-05, "epoch": 8.132013201320133, "percentage": 40.66, "elapsed_time": "2:54:57", "remaining_time": "4:15:19", "throughput": 1486.14, "total_tokens": 15600176} {"current_steps": 73925, "total_steps": 181800, "loss": 0.022, "lr": 3.6996197098372314e-05, "epoch": 8.132563256325632, "percentage": 40.66, "elapsed_time": "2:54:57", "remaining_time": "4:15:18", "throughput": 1486.14, "total_tokens": 15601232} {"current_steps": 73930, "total_steps": 181800, "loss": 0.0465, "lr": 3.6994091339588635e-05, "epoch": 8.133113311331133, "percentage": 40.67, "elapsed_time": "2:54:58", "remaining_time": "4:15:18", "throughput": 1486.15, "total_tokens": 15602320} {"current_steps": 73935, "total_steps": 181800, "loss": 0.0159, "lr": 3.699198547026116e-05, "epoch": 8.133663366336634, "percentage": 40.67, "elapsed_time": "2:54:59", "remaining_time": "4:15:17", "throughput": 1486.15, "total_tokens": 15603344} {"current_steps": 73940, "total_steps": 181800, "loss": 0.0515, "lr": 3.698987949040931e-05, "epoch": 8.134213421342134, "percentage": 40.67, "elapsed_time": "2:54:59", "remaining_time": "4:15:16", "throughput": 1486.15, "total_tokens": 15604368} {"current_steps": 73945, "total_steps": 181800, "loss": 0.093, "lr": 3.69877734000525e-05, "epoch": 8.134763476347635, "percentage": 40.67, "elapsed_time": "2:55:00", "remaining_time": "4:15:15", "throughput": 1486.15, "total_tokens": 15605392} {"current_steps": 73950, "total_steps": 181800, "loss": 0.015, "lr": 3.6985667199210125e-05, "epoch": 8.135313531353136, "percentage": 40.68, "elapsed_time": "2:55:01", "remaining_time": "4:15:15", "throughput": 1486.14, "total_tokens": 15606384} {"current_steps": 73955, "total_steps": 181800, "loss": 0.0063, "lr": 3.6983560887901616e-05, "epoch": 8.135863586358635, "percentage": 40.68, "elapsed_time": "2:55:01", "remaining_time": "4:15:14", "throughput": 1486.14, "total_tokens": 15607408} {"current_steps": 73960, "total_steps": 181800, "loss": 0.0494, "lr": 3.6981454466146374e-05, "epoch": 8.136413641364136, "percentage": 40.68, "elapsed_time": "2:55:02", "remaining_time": "4:15:13", "throughput": 1486.14, "total_tokens": 15608432} {"current_steps": 73965, "total_steps": 181800, "loss": 0.0114, "lr": 3.697934793396382e-05, "epoch": 8.136963696369637, "percentage": 40.68, "elapsed_time": "2:55:03", "remaining_time": "4:15:13", "throughput": 1486.15, "total_tokens": 15609520} {"current_steps": 73970, "total_steps": 181800, "loss": 0.0173, "lr": 3.697724129137336e-05, "epoch": 8.137513751375138, "percentage": 40.69, "elapsed_time": "2:55:04", "remaining_time": "4:15:12", "throughput": 1486.16, "total_tokens": 15610640} {"current_steps": 73975, "total_steps": 181800, "loss": 0.0492, "lr": 3.697513453839442e-05, "epoch": 8.138063806380638, "percentage": 40.69, "elapsed_time": "2:55:04", "remaining_time": "4:15:11", "throughput": 1486.16, "total_tokens": 15611664} {"current_steps": 73980, "total_steps": 181800, "loss": 0.0045, "lr": 3.69730276750464e-05, "epoch": 8.138613861386139, "percentage": 40.69, "elapsed_time": "2:55:05", "remaining_time": "4:15:10", "throughput": 1486.16, "total_tokens": 15612688} {"current_steps": 73985, "total_steps": 181800, "loss": 0.0031, "lr": 3.697092070134873e-05, "epoch": 8.13916391639164, "percentage": 40.7, "elapsed_time": "2:55:06", "remaining_time": "4:15:10", "throughput": 1486.15, "total_tokens": 15613680} {"current_steps": 73990, "total_steps": 181800, "loss": 0.0103, "lr": 3.696881361732084e-05, "epoch": 8.13971397139714, "percentage": 40.7, "elapsed_time": "2:55:06", "remaining_time": "4:15:09", "throughput": 1486.16, "total_tokens": 15614800} {"current_steps": 73995, "total_steps": 181800, "loss": 0.004, "lr": 3.696670642298213e-05, "epoch": 8.14026402640264, "percentage": 40.7, "elapsed_time": "2:55:07", "remaining_time": "4:15:08", "throughput": 1486.16, "total_tokens": 15615856} {"current_steps": 74000, "total_steps": 181800, "loss": 0.0842, "lr": 3.696459911835203e-05, "epoch": 8.140814081408141, "percentage": 40.7, "elapsed_time": "2:55:08", "remaining_time": "4:15:07", "throughput": 1486.17, "total_tokens": 15616912} {"current_steps": 74005, "total_steps": 181800, "loss": 0.0606, "lr": 3.696249170344996e-05, "epoch": 8.14136413641364, "percentage": 40.71, "elapsed_time": "2:55:08", "remaining_time": "4:15:07", "throughput": 1486.17, "total_tokens": 15617936} {"current_steps": 74010, "total_steps": 181800, "loss": 0.0568, "lr": 3.6960384178295335e-05, "epoch": 8.141914191419142, "percentage": 40.71, "elapsed_time": "2:55:09", "remaining_time": "4:15:06", "throughput": 1486.16, "total_tokens": 15618928} {"current_steps": 74015, "total_steps": 181800, "loss": 0.0509, "lr": 3.695827654290761e-05, "epoch": 8.142464246424643, "percentage": 40.71, "elapsed_time": "2:55:10", "remaining_time": "4:15:05", "throughput": 1486.16, "total_tokens": 15619920} {"current_steps": 74020, "total_steps": 181800, "loss": 0.0022, "lr": 3.695616879730617e-05, "epoch": 8.143014301430142, "percentage": 40.72, "elapsed_time": "2:55:10", "remaining_time": "4:15:04", "throughput": 1486.16, "total_tokens": 15620944} {"current_steps": 74025, "total_steps": 181800, "loss": 0.0189, "lr": 3.695406094151046e-05, "epoch": 8.143564356435643, "percentage": 40.72, "elapsed_time": "2:55:11", "remaining_time": "4:15:04", "throughput": 1486.16, "total_tokens": 15622032} {"current_steps": 74030, "total_steps": 181800, "loss": 0.0389, "lr": 3.695195297553992e-05, "epoch": 8.144114411441144, "percentage": 40.72, "elapsed_time": "2:55:12", "remaining_time": "4:15:03", "throughput": 1486.16, "total_tokens": 15623024} {"current_steps": 74035, "total_steps": 181800, "loss": 0.0089, "lr": 3.6949844899413956e-05, "epoch": 8.144664466446645, "percentage": 40.72, "elapsed_time": "2:55:13", "remaining_time": "4:15:02", "throughput": 1486.17, "total_tokens": 15624112} {"current_steps": 74040, "total_steps": 181800, "loss": 0.0933, "lr": 3.694773671315201e-05, "epoch": 8.145214521452145, "percentage": 40.73, "elapsed_time": "2:55:13", "remaining_time": "4:15:01", "throughput": 1486.17, "total_tokens": 15625168} {"current_steps": 74045, "total_steps": 181800, "loss": 0.075, "lr": 3.6945628416773506e-05, "epoch": 8.145764576457646, "percentage": 40.73, "elapsed_time": "2:55:14", "remaining_time": "4:15:01", "throughput": 1486.17, "total_tokens": 15626192} {"current_steps": 74050, "total_steps": 181800, "loss": 0.0673, "lr": 3.694352001029787e-05, "epoch": 8.146314631463147, "percentage": 40.73, "elapsed_time": "2:55:15", "remaining_time": "4:15:00", "throughput": 1486.18, "total_tokens": 15627312} {"current_steps": 74055, "total_steps": 181800, "loss": 0.0187, "lr": 3.6941411493744546e-05, "epoch": 8.146864686468646, "percentage": 40.73, "elapsed_time": "2:55:15", "remaining_time": "4:14:59", "throughput": 1486.18, "total_tokens": 15628368} {"current_steps": 74060, "total_steps": 181800, "loss": 0.0891, "lr": 3.6939302867132964e-05, "epoch": 8.147414741474147, "percentage": 40.74, "elapsed_time": "2:55:16", "remaining_time": "4:14:59", "throughput": 1486.18, "total_tokens": 15629392} {"current_steps": 74065, "total_steps": 181800, "loss": 0.0045, "lr": 3.693719413048255e-05, "epoch": 8.147964796479648, "percentage": 40.74, "elapsed_time": "2:55:17", "remaining_time": "4:14:58", "throughput": 1486.18, "total_tokens": 15630448} {"current_steps": 74070, "total_steps": 181800, "loss": 0.0592, "lr": 3.693508528381275e-05, "epoch": 8.148514851485148, "percentage": 40.74, "elapsed_time": "2:55:17", "remaining_time": "4:14:57", "throughput": 1486.18, "total_tokens": 15631472} {"current_steps": 74075, "total_steps": 181800, "loss": 0.0715, "lr": 3.6932976327143004e-05, "epoch": 8.149064906490649, "percentage": 40.75, "elapsed_time": "2:55:18", "remaining_time": "4:14:56", "throughput": 1486.19, "total_tokens": 15632560} {"current_steps": 74080, "total_steps": 181800, "loss": 0.009, "lr": 3.693086726049274e-05, "epoch": 8.14961496149615, "percentage": 40.75, "elapsed_time": "2:55:19", "remaining_time": "4:14:56", "throughput": 1486.19, "total_tokens": 15633648} {"current_steps": 74085, "total_steps": 181800, "loss": 0.0082, "lr": 3.6928758083881384e-05, "epoch": 8.150165016501651, "percentage": 40.75, "elapsed_time": "2:55:19", "remaining_time": "4:14:55", "throughput": 1486.19, "total_tokens": 15634640} {"current_steps": 74090, "total_steps": 181800, "loss": 0.078, "lr": 3.69266487973284e-05, "epoch": 8.15071507150715, "percentage": 40.75, "elapsed_time": "2:55:20", "remaining_time": "4:14:54", "throughput": 1486.19, "total_tokens": 15635664} {"current_steps": 74095, "total_steps": 181800, "loss": 0.0271, "lr": 3.692453940085321e-05, "epoch": 8.151265126512651, "percentage": 40.76, "elapsed_time": "2:55:21", "remaining_time": "4:14:53", "throughput": 1486.2, "total_tokens": 15636784} {"current_steps": 74100, "total_steps": 181800, "loss": 0.0348, "lr": 3.6922429894475266e-05, "epoch": 8.151815181518153, "percentage": 40.76, "elapsed_time": "2:55:22", "remaining_time": "4:14:53", "throughput": 1486.2, "total_tokens": 15637808} {"current_steps": 74105, "total_steps": 181800, "loss": 0.0406, "lr": 3.6920320278214e-05, "epoch": 8.152365236523652, "percentage": 40.76, "elapsed_time": "2:55:22", "remaining_time": "4:14:52", "throughput": 1486.2, "total_tokens": 15638896} {"current_steps": 74110, "total_steps": 181800, "loss": 0.0725, "lr": 3.6918210552088874e-05, "epoch": 8.152915291529153, "percentage": 40.76, "elapsed_time": "2:55:23", "remaining_time": "4:14:51", "throughput": 1486.2, "total_tokens": 15639920} {"current_steps": 74115, "total_steps": 181800, "loss": 0.1095, "lr": 3.691610071611931e-05, "epoch": 8.153465346534654, "percentage": 40.77, "elapsed_time": "2:55:24", "remaining_time": "4:14:50", "throughput": 1486.21, "total_tokens": 15641040} {"current_steps": 74120, "total_steps": 181800, "loss": 0.0386, "lr": 3.691399077032477e-05, "epoch": 8.154015401540153, "percentage": 40.77, "elapsed_time": "2:55:24", "remaining_time": "4:14:50", "throughput": 1486.22, "total_tokens": 15642096} {"current_steps": 74125, "total_steps": 181800, "loss": 0.0337, "lr": 3.6911880714724687e-05, "epoch": 8.154565456545654, "percentage": 40.77, "elapsed_time": "2:55:25", "remaining_time": "4:14:49", "throughput": 1486.22, "total_tokens": 15643152} {"current_steps": 74130, "total_steps": 181800, "loss": 0.0706, "lr": 3.6909770549338524e-05, "epoch": 8.155115511551156, "percentage": 40.78, "elapsed_time": "2:55:26", "remaining_time": "4:14:48", "throughput": 1486.22, "total_tokens": 15644208} {"current_steps": 74135, "total_steps": 181800, "loss": 0.009, "lr": 3.690766027418573e-05, "epoch": 8.155665566556655, "percentage": 40.78, "elapsed_time": "2:55:26", "remaining_time": "4:14:47", "throughput": 1486.22, "total_tokens": 15645232} {"current_steps": 74140, "total_steps": 181800, "loss": 0.0084, "lr": 3.690554988928572e-05, "epoch": 8.156215621562156, "percentage": 40.78, "elapsed_time": "2:55:27", "remaining_time": "4:14:47", "throughput": 1486.22, "total_tokens": 15646288} {"current_steps": 74145, "total_steps": 181800, "loss": 0.0118, "lr": 3.6903439394657976e-05, "epoch": 8.156765676567657, "percentage": 40.78, "elapsed_time": "2:55:28", "remaining_time": "4:14:46", "throughput": 1486.22, "total_tokens": 15647280} {"current_steps": 74150, "total_steps": 181800, "loss": 0.0294, "lr": 3.690132879032195e-05, "epoch": 8.157315731573158, "percentage": 40.79, "elapsed_time": "2:55:28", "remaining_time": "4:14:45", "throughput": 1486.22, "total_tokens": 15648336} {"current_steps": 74155, "total_steps": 181800, "loss": 0.0166, "lr": 3.6899218076297086e-05, "epoch": 8.157865786578657, "percentage": 40.79, "elapsed_time": "2:55:29", "remaining_time": "4:14:45", "throughput": 1486.23, "total_tokens": 15649392} {"current_steps": 74160, "total_steps": 181800, "loss": 0.0183, "lr": 3.6897107252602845e-05, "epoch": 8.158415841584159, "percentage": 40.79, "elapsed_time": "2:55:30", "remaining_time": "4:14:44", "throughput": 1486.23, "total_tokens": 15650416} {"current_steps": 74165, "total_steps": 181800, "loss": 0.0476, "lr": 3.6894996319258665e-05, "epoch": 8.15896589658966, "percentage": 40.79, "elapsed_time": "2:55:31", "remaining_time": "4:14:43", "throughput": 1486.22, "total_tokens": 15651408} {"current_steps": 74170, "total_steps": 181800, "loss": 0.0057, "lr": 3.689288527628402e-05, "epoch": 8.159515951595159, "percentage": 40.8, "elapsed_time": "2:55:31", "remaining_time": "4:14:42", "throughput": 1486.23, "total_tokens": 15652464} {"current_steps": 74175, "total_steps": 181800, "loss": 0.0606, "lr": 3.6890774123698345e-05, "epoch": 8.16006600660066, "percentage": 40.8, "elapsed_time": "2:55:32", "remaining_time": "4:14:42", "throughput": 1486.23, "total_tokens": 15653488} {"current_steps": 74180, "total_steps": 181800, "loss": 0.0207, "lr": 3.688866286152112e-05, "epoch": 8.160616061606161, "percentage": 40.8, "elapsed_time": "2:55:33", "remaining_time": "4:14:41", "throughput": 1486.23, "total_tokens": 15654608} {"current_steps": 74185, "total_steps": 181800, "loss": 0.0032, "lr": 3.68865514897718e-05, "epoch": 8.16116611661166, "percentage": 40.81, "elapsed_time": "2:55:33", "remaining_time": "4:14:40", "throughput": 1486.24, "total_tokens": 15655696} {"current_steps": 74190, "total_steps": 181800, "loss": 0.2349, "lr": 3.688444000846983e-05, "epoch": 8.161716171617162, "percentage": 40.81, "elapsed_time": "2:55:34", "remaining_time": "4:14:39", "throughput": 1486.25, "total_tokens": 15656784} {"current_steps": 74195, "total_steps": 181800, "loss": 0.0146, "lr": 3.6882328417634684e-05, "epoch": 8.162266226622663, "percentage": 40.81, "elapsed_time": "2:55:35", "remaining_time": "4:14:39", "throughput": 1486.24, "total_tokens": 15657776} {"current_steps": 74200, "total_steps": 181800, "loss": 0.0212, "lr": 3.6880216717285806e-05, "epoch": 8.162816281628162, "percentage": 40.81, "elapsed_time": "2:55:35", "remaining_time": "4:14:38", "throughput": 1486.25, "total_tokens": 15658832} {"current_steps": 74205, "total_steps": 181800, "loss": 0.0023, "lr": 3.687810490744269e-05, "epoch": 8.163366336633663, "percentage": 40.82, "elapsed_time": "2:55:36", "remaining_time": "4:14:37", "throughput": 1486.25, "total_tokens": 15659888} {"current_steps": 74210, "total_steps": 181800, "loss": 0.0442, "lr": 3.687599298812477e-05, "epoch": 8.163916391639164, "percentage": 40.82, "elapsed_time": "2:55:37", "remaining_time": "4:14:36", "throughput": 1486.26, "total_tokens": 15660976} {"current_steps": 74215, "total_steps": 181800, "loss": 0.0135, "lr": 3.687388095935152e-05, "epoch": 8.164466446644665, "percentage": 40.82, "elapsed_time": "2:55:37", "remaining_time": "4:14:36", "throughput": 1486.26, "total_tokens": 15662064} {"current_steps": 74220, "total_steps": 181800, "loss": 0.1277, "lr": 3.687176882114241e-05, "epoch": 8.165016501650165, "percentage": 40.83, "elapsed_time": "2:55:38", "remaining_time": "4:14:35", "throughput": 1486.27, "total_tokens": 15663152} {"current_steps": 74225, "total_steps": 181800, "loss": 0.0064, "lr": 3.686965657351691e-05, "epoch": 8.165566556655666, "percentage": 40.83, "elapsed_time": "2:55:39", "remaining_time": "4:14:34", "throughput": 1486.27, "total_tokens": 15664240} {"current_steps": 74230, "total_steps": 181800, "loss": 0.0106, "lr": 3.686754421649447e-05, "epoch": 8.166116611661167, "percentage": 40.83, "elapsed_time": "2:55:39", "remaining_time": "4:14:33", "throughput": 1486.27, "total_tokens": 15665264} {"current_steps": 74235, "total_steps": 181800, "loss": 0.0388, "lr": 3.686543175009457e-05, "epoch": 8.166666666666666, "percentage": 40.83, "elapsed_time": "2:55:40", "remaining_time": "4:14:33", "throughput": 1486.27, "total_tokens": 15666288} {"current_steps": 74240, "total_steps": 181800, "loss": 0.0656, "lr": 3.686331917433669e-05, "epoch": 8.167216721672167, "percentage": 40.84, "elapsed_time": "2:55:41", "remaining_time": "4:14:32", "throughput": 1486.28, "total_tokens": 15667376} {"current_steps": 74245, "total_steps": 181800, "loss": 0.0093, "lr": 3.686120648924028e-05, "epoch": 8.167766776677668, "percentage": 40.84, "elapsed_time": "2:55:42", "remaining_time": "4:14:31", "throughput": 1486.29, "total_tokens": 15668464} {"current_steps": 74250, "total_steps": 181800, "loss": 0.006, "lr": 3.685909369482482e-05, "epoch": 8.168316831683168, "percentage": 40.84, "elapsed_time": "2:55:42", "remaining_time": "4:14:30", "throughput": 1486.29, "total_tokens": 15669552} {"current_steps": 74255, "total_steps": 181800, "loss": 0.0051, "lr": 3.6856980791109794e-05, "epoch": 8.168866886688669, "percentage": 40.84, "elapsed_time": "2:55:43", "remaining_time": "4:14:30", "throughput": 1486.3, "total_tokens": 15670608} {"current_steps": 74260, "total_steps": 181800, "loss": 0.086, "lr": 3.6854867778114655e-05, "epoch": 8.16941694169417, "percentage": 40.85, "elapsed_time": "2:55:44", "remaining_time": "4:14:29", "throughput": 1486.3, "total_tokens": 15671696} {"current_steps": 74265, "total_steps": 181800, "loss": 0.0735, "lr": 3.685275465585889e-05, "epoch": 8.16996699669967, "percentage": 40.85, "elapsed_time": "2:55:44", "remaining_time": "4:14:28", "throughput": 1486.31, "total_tokens": 15672816} {"current_steps": 74270, "total_steps": 181800, "loss": 0.0129, "lr": 3.6850641424361977e-05, "epoch": 8.17051705170517, "percentage": 40.85, "elapsed_time": "2:55:45", "remaining_time": "4:14:28", "throughput": 1486.32, "total_tokens": 15673904} {"current_steps": 74275, "total_steps": 181800, "loss": 0.0252, "lr": 3.684852808364339e-05, "epoch": 8.171067106710671, "percentage": 40.86, "elapsed_time": "2:55:46", "remaining_time": "4:14:27", "throughput": 1486.32, "total_tokens": 15674992} {"current_steps": 74280, "total_steps": 181800, "loss": 0.0235, "lr": 3.6846414633722606e-05, "epoch": 8.171617161716172, "percentage": 40.86, "elapsed_time": "2:55:46", "remaining_time": "4:14:26", "throughput": 1486.32, "total_tokens": 15676048} {"current_steps": 74285, "total_steps": 181800, "loss": 0.1029, "lr": 3.6844301074619095e-05, "epoch": 8.172167216721672, "percentage": 40.86, "elapsed_time": "2:55:47", "remaining_time": "4:14:25", "throughput": 1486.32, "total_tokens": 15677072} {"current_steps": 74290, "total_steps": 181800, "loss": 0.0032, "lr": 3.684218740635235e-05, "epoch": 8.172717271727173, "percentage": 40.86, "elapsed_time": "2:55:48", "remaining_time": "4:14:25", "throughput": 1486.33, "total_tokens": 15678160} {"current_steps": 74295, "total_steps": 181800, "loss": 0.0452, "lr": 3.6840073628941844e-05, "epoch": 8.173267326732674, "percentage": 40.87, "elapsed_time": "2:55:48", "remaining_time": "4:14:24", "throughput": 1486.33, "total_tokens": 15679216} {"current_steps": 74300, "total_steps": 181800, "loss": 0.0166, "lr": 3.683795974240706e-05, "epoch": 8.173817381738173, "percentage": 40.87, "elapsed_time": "2:55:49", "remaining_time": "4:14:23", "throughput": 1486.33, "total_tokens": 15680240} {"current_steps": 74305, "total_steps": 181800, "loss": 0.1178, "lr": 3.683584574676748e-05, "epoch": 8.174367436743674, "percentage": 40.87, "elapsed_time": "2:55:50", "remaining_time": "4:14:22", "throughput": 1486.33, "total_tokens": 15681264} {"current_steps": 74310, "total_steps": 181800, "loss": 0.0519, "lr": 3.68337316420426e-05, "epoch": 8.174917491749175, "percentage": 40.87, "elapsed_time": "2:55:50", "remaining_time": "4:14:22", "throughput": 1486.34, "total_tokens": 15682320} {"current_steps": 74315, "total_steps": 181800, "loss": 0.0338, "lr": 3.683161742825188e-05, "epoch": 8.175467546754675, "percentage": 40.88, "elapsed_time": "2:55:51", "remaining_time": "4:14:21", "throughput": 1486.34, "total_tokens": 15683344} {"current_steps": 74320, "total_steps": 181800, "loss": 0.0565, "lr": 3.682950310541483e-05, "epoch": 8.176017601760176, "percentage": 40.88, "elapsed_time": "2:55:52", "remaining_time": "4:14:20", "throughput": 1486.33, "total_tokens": 15684336} {"current_steps": 74325, "total_steps": 181800, "loss": 0.002, "lr": 3.682738867355092e-05, "epoch": 8.176567656765677, "percentage": 40.88, "elapsed_time": "2:55:53", "remaining_time": "4:14:19", "throughput": 1486.33, "total_tokens": 15685360} {"current_steps": 74330, "total_steps": 181800, "loss": 0.0068, "lr": 3.6825274132679644e-05, "epoch": 8.177117711771178, "percentage": 40.89, "elapsed_time": "2:55:53", "remaining_time": "4:14:19", "throughput": 1486.34, "total_tokens": 15686416} {"current_steps": 74335, "total_steps": 181800, "loss": 0.0234, "lr": 3.6823159482820494e-05, "epoch": 8.177667766776677, "percentage": 40.89, "elapsed_time": "2:55:54", "remaining_time": "4:14:18", "throughput": 1486.34, "total_tokens": 15687440} {"current_steps": 74340, "total_steps": 181800, "loss": 0.0098, "lr": 3.6821044723992954e-05, "epoch": 8.178217821782178, "percentage": 40.89, "elapsed_time": "2:55:55", "remaining_time": "4:14:17", "throughput": 1486.34, "total_tokens": 15688464} {"current_steps": 74345, "total_steps": 181800, "loss": 0.005, "lr": 3.681892985621652e-05, "epoch": 8.17876787678768, "percentage": 40.89, "elapsed_time": "2:55:55", "remaining_time": "4:14:16", "throughput": 1486.34, "total_tokens": 15689488} {"current_steps": 74350, "total_steps": 181800, "loss": 0.0194, "lr": 3.681681487951068e-05, "epoch": 8.179317931793179, "percentage": 40.9, "elapsed_time": "2:55:56", "remaining_time": "4:14:16", "throughput": 1486.34, "total_tokens": 15690512} {"current_steps": 74355, "total_steps": 181800, "loss": 0.0967, "lr": 3.681469979389493e-05, "epoch": 8.17986798679868, "percentage": 40.9, "elapsed_time": "2:55:57", "remaining_time": "4:14:15", "throughput": 1486.34, "total_tokens": 15691536} {"current_steps": 74360, "total_steps": 181800, "loss": 0.0461, "lr": 3.681258459938875e-05, "epoch": 8.180418041804181, "percentage": 40.9, "elapsed_time": "2:55:57", "remaining_time": "4:14:14", "throughput": 1486.34, "total_tokens": 15692592} {"current_steps": 74365, "total_steps": 181800, "loss": 0.0191, "lr": 3.681046929601165e-05, "epoch": 8.18096809680968, "percentage": 40.9, "elapsed_time": "2:55:58", "remaining_time": "4:14:13", "throughput": 1486.34, "total_tokens": 15693616} {"current_steps": 74370, "total_steps": 181800, "loss": 0.0984, "lr": 3.680835388378313e-05, "epoch": 8.181518151815181, "percentage": 40.91, "elapsed_time": "2:55:59", "remaining_time": "4:14:13", "throughput": 1486.34, "total_tokens": 15694640} {"current_steps": 74375, "total_steps": 181800, "loss": 0.0695, "lr": 3.680623836272267e-05, "epoch": 8.182068206820682, "percentage": 40.91, "elapsed_time": "2:55:59", "remaining_time": "4:14:12", "throughput": 1486.34, "total_tokens": 15695632} {"current_steps": 74380, "total_steps": 181800, "loss": 0.0175, "lr": 3.6804122732849785e-05, "epoch": 8.182618261826182, "percentage": 40.91, "elapsed_time": "2:56:00", "remaining_time": "4:14:11", "throughput": 1486.34, "total_tokens": 15696688} {"current_steps": 74385, "total_steps": 181800, "loss": 0.0473, "lr": 3.680200699418396e-05, "epoch": 8.183168316831683, "percentage": 40.92, "elapsed_time": "2:56:01", "remaining_time": "4:14:11", "throughput": 1486.34, "total_tokens": 15697712} {"current_steps": 74390, "total_steps": 181800, "loss": 0.0371, "lr": 3.679989114674469e-05, "epoch": 8.183718371837184, "percentage": 40.92, "elapsed_time": "2:56:02", "remaining_time": "4:14:10", "throughput": 1486.35, "total_tokens": 15698832} {"current_steps": 74395, "total_steps": 181800, "loss": 0.0679, "lr": 3.67977751905515e-05, "epoch": 8.184268426842685, "percentage": 40.92, "elapsed_time": "2:56:02", "remaining_time": "4:14:09", "throughput": 1486.35, "total_tokens": 15699856} {"current_steps": 74400, "total_steps": 181800, "loss": 0.0298, "lr": 3.679565912562387e-05, "epoch": 8.184818481848184, "percentage": 40.92, "elapsed_time": "2:56:03", "remaining_time": "4:14:08", "throughput": 1486.35, "total_tokens": 15700912} {"current_steps": 74405, "total_steps": 181800, "loss": 0.0032, "lr": 3.6793542951981306e-05, "epoch": 8.185368536853685, "percentage": 40.93, "elapsed_time": "2:56:04", "remaining_time": "4:14:08", "throughput": 1486.35, "total_tokens": 15701936} {"current_steps": 74410, "total_steps": 181800, "loss": 0.0271, "lr": 3.679142666964332e-05, "epoch": 8.185918591859187, "percentage": 40.93, "elapsed_time": "2:56:04", "remaining_time": "4:14:07", "throughput": 1486.35, "total_tokens": 15702992} {"current_steps": 74415, "total_steps": 181800, "loss": 0.0041, "lr": 3.678931027862942e-05, "epoch": 8.186468646864686, "percentage": 40.93, "elapsed_time": "2:56:05", "remaining_time": "4:14:06", "throughput": 1486.35, "total_tokens": 15703984} {"current_steps": 74420, "total_steps": 181800, "loss": 0.0433, "lr": 3.67871937789591e-05, "epoch": 8.187018701870187, "percentage": 40.94, "elapsed_time": "2:56:06", "remaining_time": "4:14:05", "throughput": 1486.35, "total_tokens": 15705040} {"current_steps": 74425, "total_steps": 181800, "loss": 0.0199, "lr": 3.678507717065187e-05, "epoch": 8.187568756875688, "percentage": 40.94, "elapsed_time": "2:56:06", "remaining_time": "4:14:05", "throughput": 1486.36, "total_tokens": 15706160} {"current_steps": 74430, "total_steps": 181800, "loss": 0.1374, "lr": 3.678296045372723e-05, "epoch": 8.188118811881187, "percentage": 40.94, "elapsed_time": "2:56:07", "remaining_time": "4:14:04", "throughput": 1486.37, "total_tokens": 15707248} {"current_steps": 74435, "total_steps": 181800, "loss": 0.0852, "lr": 3.6780843628204706e-05, "epoch": 8.188668866886688, "percentage": 40.94, "elapsed_time": "2:56:08", "remaining_time": "4:14:03", "throughput": 1486.37, "total_tokens": 15708304} {"current_steps": 74440, "total_steps": 181800, "loss": 0.0322, "lr": 3.6778726694103803e-05, "epoch": 8.18921892189219, "percentage": 40.95, "elapsed_time": "2:56:08", "remaining_time": "4:14:02", "throughput": 1486.38, "total_tokens": 15709424} {"current_steps": 74445, "total_steps": 181800, "loss": 0.0124, "lr": 3.677660965144403e-05, "epoch": 8.189768976897689, "percentage": 40.95, "elapsed_time": "2:56:09", "remaining_time": "4:14:02", "throughput": 1486.38, "total_tokens": 15710448} {"current_steps": 74450, "total_steps": 181800, "loss": 0.1238, "lr": 3.677449250024488e-05, "epoch": 8.19031903190319, "percentage": 40.95, "elapsed_time": "2:56:10", "remaining_time": "4:14:01", "throughput": 1486.38, "total_tokens": 15711504} {"current_steps": 74455, "total_steps": 181800, "loss": 0.0069, "lr": 3.67723752405259e-05, "epoch": 8.190869086908691, "percentage": 40.95, "elapsed_time": "2:56:11", "remaining_time": "4:14:00", "throughput": 1486.38, "total_tokens": 15712528} {"current_steps": 74460, "total_steps": 181800, "loss": 0.0989, "lr": 3.677025787230657e-05, "epoch": 8.191419141914192, "percentage": 40.96, "elapsed_time": "2:56:11", "remaining_time": "4:13:59", "throughput": 1486.38, "total_tokens": 15713584} {"current_steps": 74465, "total_steps": 181800, "loss": 0.0049, "lr": 3.6768140395606434e-05, "epoch": 8.191969196919691, "percentage": 40.96, "elapsed_time": "2:56:12", "remaining_time": "4:13:59", "throughput": 1486.38, "total_tokens": 15714640} {"current_steps": 74470, "total_steps": 181800, "loss": 0.0179, "lr": 3.6766022810445e-05, "epoch": 8.192519251925193, "percentage": 40.96, "elapsed_time": "2:56:13", "remaining_time": "4:13:58", "throughput": 1486.39, "total_tokens": 15715696} {"current_steps": 74475, "total_steps": 181800, "loss": 0.0288, "lr": 3.676390511684177e-05, "epoch": 8.193069306930694, "percentage": 40.97, "elapsed_time": "2:56:13", "remaining_time": "4:13:57", "throughput": 1486.38, "total_tokens": 15716688} {"current_steps": 74480, "total_steps": 181800, "loss": 0.013, "lr": 3.676178731481626e-05, "epoch": 8.193619361936193, "percentage": 40.97, "elapsed_time": "2:56:14", "remaining_time": "4:13:56", "throughput": 1486.4, "total_tokens": 15717840} {"current_steps": 74485, "total_steps": 181800, "loss": 0.0572, "lr": 3.675966940438802e-05, "epoch": 8.194169416941694, "percentage": 40.97, "elapsed_time": "2:56:15", "remaining_time": "4:13:56", "throughput": 1486.4, "total_tokens": 15718928} {"current_steps": 74490, "total_steps": 181800, "loss": 0.0258, "lr": 3.675755138557654e-05, "epoch": 8.194719471947195, "percentage": 40.97, "elapsed_time": "2:56:15", "remaining_time": "4:13:55", "throughput": 1486.4, "total_tokens": 15719952} {"current_steps": 74495, "total_steps": 181800, "loss": 0.0263, "lr": 3.6755433258401354e-05, "epoch": 8.195269526952695, "percentage": 40.98, "elapsed_time": "2:56:16", "remaining_time": "4:13:54", "throughput": 1486.41, "total_tokens": 15721040} {"current_steps": 74500, "total_steps": 181800, "loss": 0.0392, "lr": 3.6753315022881986e-05, "epoch": 8.195819581958196, "percentage": 40.98, "elapsed_time": "2:56:17", "remaining_time": "4:13:54", "throughput": 1486.41, "total_tokens": 15722096} {"current_steps": 74505, "total_steps": 181800, "loss": 0.0558, "lr": 3.675119667903794e-05, "epoch": 8.196369636963697, "percentage": 40.98, "elapsed_time": "2:56:17", "remaining_time": "4:13:53", "throughput": 1486.41, "total_tokens": 15723088} {"current_steps": 74510, "total_steps": 181800, "loss": 0.0321, "lr": 3.674907822688876e-05, "epoch": 8.196919691969198, "percentage": 40.98, "elapsed_time": "2:56:18", "remaining_time": "4:13:52", "throughput": 1486.4, "total_tokens": 15724080} {"current_steps": 74515, "total_steps": 181800, "loss": 0.0359, "lr": 3.6746959666453966e-05, "epoch": 8.197469746974697, "percentage": 40.99, "elapsed_time": "2:56:19", "remaining_time": "4:13:51", "throughput": 1486.41, "total_tokens": 15725136} {"current_steps": 74520, "total_steps": 181800, "loss": 0.0655, "lr": 3.6744840997753086e-05, "epoch": 8.198019801980198, "percentage": 40.99, "elapsed_time": "2:56:19", "remaining_time": "4:13:51", "throughput": 1486.41, "total_tokens": 15726192} {"current_steps": 74525, "total_steps": 181800, "loss": 0.0423, "lr": 3.674272222080563e-05, "epoch": 8.1985698569857, "percentage": 40.99, "elapsed_time": "2:56:20", "remaining_time": "4:13:50", "throughput": 1486.42, "total_tokens": 15727280} {"current_steps": 74530, "total_steps": 181800, "loss": 0.0945, "lr": 3.674060333563114e-05, "epoch": 8.199119911991199, "percentage": 41.0, "elapsed_time": "2:56:21", "remaining_time": "4:13:49", "throughput": 1486.42, "total_tokens": 15728336} {"current_steps": 74535, "total_steps": 181800, "loss": 0.0457, "lr": 3.673848434224915e-05, "epoch": 8.1996699669967, "percentage": 41.0, "elapsed_time": "2:56:22", "remaining_time": "4:13:48", "throughput": 1486.42, "total_tokens": 15729392} {"current_steps": 74540, "total_steps": 181800, "loss": 0.0457, "lr": 3.673636524067918e-05, "epoch": 8.2002200220022, "percentage": 41.0, "elapsed_time": "2:56:22", "remaining_time": "4:13:48", "throughput": 1486.42, "total_tokens": 15730384} {"current_steps": 74545, "total_steps": 181800, "loss": 0.0498, "lr": 3.6734246030940756e-05, "epoch": 8.2007700770077, "percentage": 41.0, "elapsed_time": "2:56:23", "remaining_time": "4:13:47", "throughput": 1486.42, "total_tokens": 15731472} {"current_steps": 74550, "total_steps": 181800, "loss": 0.016, "lr": 3.673212671305343e-05, "epoch": 8.201320132013201, "percentage": 41.01, "elapsed_time": "2:56:24", "remaining_time": "4:13:46", "throughput": 1486.42, "total_tokens": 15732432} {"current_steps": 74555, "total_steps": 181800, "loss": 0.006, "lr": 3.673000728703671e-05, "epoch": 8.201870187018702, "percentage": 41.01, "elapsed_time": "2:56:24", "remaining_time": "4:13:45", "throughput": 1486.42, "total_tokens": 15733520} {"current_steps": 74560, "total_steps": 181800, "loss": 0.1229, "lr": 3.672788775291015e-05, "epoch": 8.202420242024202, "percentage": 41.01, "elapsed_time": "2:56:25", "remaining_time": "4:13:45", "throughput": 1486.43, "total_tokens": 15734608} {"current_steps": 74565, "total_steps": 181800, "loss": 0.0525, "lr": 3.672576811069327e-05, "epoch": 8.202970297029703, "percentage": 41.01, "elapsed_time": "2:56:26", "remaining_time": "4:13:44", "throughput": 1486.44, "total_tokens": 15735760} {"current_steps": 74570, "total_steps": 181800, "loss": 0.0032, "lr": 3.6723648360405614e-05, "epoch": 8.203520352035204, "percentage": 41.02, "elapsed_time": "2:56:26", "remaining_time": "4:13:43", "throughput": 1486.45, "total_tokens": 15736816} {"current_steps": 74575, "total_steps": 181800, "loss": 0.0922, "lr": 3.672152850206672e-05, "epoch": 8.204070407040705, "percentage": 41.02, "elapsed_time": "2:56:27", "remaining_time": "4:13:42", "throughput": 1486.44, "total_tokens": 15737840} {"current_steps": 74580, "total_steps": 181800, "loss": 0.0174, "lr": 3.671940853569611e-05, "epoch": 8.204620462046204, "percentage": 41.02, "elapsed_time": "2:56:28", "remaining_time": "4:13:42", "throughput": 1486.44, "total_tokens": 15738864} {"current_steps": 74585, "total_steps": 181800, "loss": 0.043, "lr": 3.671728846131335e-05, "epoch": 8.205170517051705, "percentage": 41.03, "elapsed_time": "2:56:28", "remaining_time": "4:13:41", "throughput": 1486.45, "total_tokens": 15739984} {"current_steps": 74590, "total_steps": 181800, "loss": 0.0719, "lr": 3.6715168278937954e-05, "epoch": 8.205720572057206, "percentage": 41.03, "elapsed_time": "2:56:29", "remaining_time": "4:13:40", "throughput": 1486.45, "total_tokens": 15741008} {"current_steps": 74595, "total_steps": 181800, "loss": 0.0187, "lr": 3.671304798858948e-05, "epoch": 8.206270627062706, "percentage": 41.03, "elapsed_time": "2:56:30", "remaining_time": "4:13:40", "throughput": 1486.46, "total_tokens": 15742064} {"current_steps": 74600, "total_steps": 181800, "loss": 0.0045, "lr": 3.6710927590287464e-05, "epoch": 8.206820682068207, "percentage": 41.03, "elapsed_time": "2:56:31", "remaining_time": "4:13:39", "throughput": 1486.46, "total_tokens": 15743120} {"current_steps": 74605, "total_steps": 181800, "loss": 0.0327, "lr": 3.670880708405144e-05, "epoch": 8.207370737073708, "percentage": 41.04, "elapsed_time": "2:56:31", "remaining_time": "4:13:38", "throughput": 1486.45, "total_tokens": 15744080} {"current_steps": 74610, "total_steps": 181800, "loss": 0.0181, "lr": 3.670668646990097e-05, "epoch": 8.207920792079207, "percentage": 41.04, "elapsed_time": "2:56:32", "remaining_time": "4:13:37", "throughput": 1486.45, "total_tokens": 15745104} {"current_steps": 74615, "total_steps": 181800, "loss": 0.0053, "lr": 3.6704565747855586e-05, "epoch": 8.208470847084708, "percentage": 41.04, "elapsed_time": "2:56:33", "remaining_time": "4:13:37", "throughput": 1486.45, "total_tokens": 15746128} {"current_steps": 74620, "total_steps": 181800, "loss": 0.01, "lr": 3.6702444917934826e-05, "epoch": 8.20902090209021, "percentage": 41.05, "elapsed_time": "2:56:33", "remaining_time": "4:13:36", "throughput": 1486.46, "total_tokens": 15747216} {"current_steps": 74625, "total_steps": 181800, "loss": 0.0171, "lr": 3.670032398015826e-05, "epoch": 8.209570957095709, "percentage": 41.05, "elapsed_time": "2:56:34", "remaining_time": "4:13:35", "throughput": 1486.45, "total_tokens": 15748208} {"current_steps": 74630, "total_steps": 181800, "loss": 0.0455, "lr": 3.669820293454541e-05, "epoch": 8.21012101210121, "percentage": 41.05, "elapsed_time": "2:56:35", "remaining_time": "4:13:34", "throughput": 1486.46, "total_tokens": 15749296} {"current_steps": 74635, "total_steps": 181800, "loss": 0.0071, "lr": 3.6696081781115844e-05, "epoch": 8.210671067106711, "percentage": 41.05, "elapsed_time": "2:56:35", "remaining_time": "4:13:34", "throughput": 1486.46, "total_tokens": 15750320} {"current_steps": 74640, "total_steps": 181800, "loss": 0.0239, "lr": 3.6693960519889106e-05, "epoch": 8.211221122112212, "percentage": 41.06, "elapsed_time": "2:56:36", "remaining_time": "4:13:33", "throughput": 1486.46, "total_tokens": 15751344} {"current_steps": 74645, "total_steps": 181800, "loss": 0.0146, "lr": 3.6691839150884744e-05, "epoch": 8.211771177117711, "percentage": 41.06, "elapsed_time": "2:56:37", "remaining_time": "4:13:32", "throughput": 1486.46, "total_tokens": 15752400} {"current_steps": 74650, "total_steps": 181800, "loss": 0.022, "lr": 3.6689717674122306e-05, "epoch": 8.212321232123212, "percentage": 41.06, "elapsed_time": "2:56:37", "remaining_time": "4:13:31", "throughput": 1486.47, "total_tokens": 15753520} {"current_steps": 74655, "total_steps": 181800, "loss": 0.0117, "lr": 3.668759608962135e-05, "epoch": 8.212871287128714, "percentage": 41.06, "elapsed_time": "2:56:38", "remaining_time": "4:13:31", "throughput": 1486.47, "total_tokens": 15754608} {"current_steps": 74660, "total_steps": 181800, "loss": 0.0422, "lr": 3.668547439740144e-05, "epoch": 8.213421342134213, "percentage": 41.07, "elapsed_time": "2:56:39", "remaining_time": "4:13:30", "throughput": 1486.48, "total_tokens": 15755696} {"current_steps": 74665, "total_steps": 181800, "loss": 0.0443, "lr": 3.66833525974821e-05, "epoch": 8.213971397139714, "percentage": 41.07, "elapsed_time": "2:56:40", "remaining_time": "4:13:29", "throughput": 1486.48, "total_tokens": 15756720} {"current_steps": 74670, "total_steps": 181800, "loss": 0.0199, "lr": 3.6681230689882924e-05, "epoch": 8.214521452145215, "percentage": 41.07, "elapsed_time": "2:56:40", "remaining_time": "4:13:28", "throughput": 1486.48, "total_tokens": 15757712} {"current_steps": 74675, "total_steps": 181800, "loss": 0.0255, "lr": 3.6679108674623444e-05, "epoch": 8.215071507150714, "percentage": 41.08, "elapsed_time": "2:56:41", "remaining_time": "4:13:28", "throughput": 1486.48, "total_tokens": 15758768} {"current_steps": 74680, "total_steps": 181800, "loss": 0.0232, "lr": 3.6676986551723214e-05, "epoch": 8.215621562156215, "percentage": 41.08, "elapsed_time": "2:56:42", "remaining_time": "4:13:27", "throughput": 1486.48, "total_tokens": 15759792} {"current_steps": 74685, "total_steps": 181800, "loss": 0.0228, "lr": 3.667486432120182e-05, "epoch": 8.216171617161717, "percentage": 41.08, "elapsed_time": "2:56:42", "remaining_time": "4:13:26", "throughput": 1486.48, "total_tokens": 15760816} {"current_steps": 74690, "total_steps": 181800, "loss": 0.0403, "lr": 3.667274198307879e-05, "epoch": 8.216721672167218, "percentage": 41.08, "elapsed_time": "2:56:43", "remaining_time": "4:13:26", "throughput": 1486.48, "total_tokens": 15761904} {"current_steps": 74695, "total_steps": 181800, "loss": 0.0821, "lr": 3.667061953737369e-05, "epoch": 8.217271727172717, "percentage": 41.09, "elapsed_time": "2:56:44", "remaining_time": "4:13:25", "throughput": 1486.48, "total_tokens": 15762864} {"current_steps": 74700, "total_steps": 181800, "loss": 0.0845, "lr": 3.666849698410611e-05, "epoch": 8.217821782178218, "percentage": 41.09, "elapsed_time": "2:56:44", "remaining_time": "4:13:24", "throughput": 1486.48, "total_tokens": 15763920} {"current_steps": 74705, "total_steps": 181800, "loss": 0.015, "lr": 3.666637432329559e-05, "epoch": 8.218371837183719, "percentage": 41.09, "elapsed_time": "2:56:45", "remaining_time": "4:13:23", "throughput": 1486.48, "total_tokens": 15764912} {"current_steps": 74710, "total_steps": 181800, "loss": 0.0443, "lr": 3.666425155496169e-05, "epoch": 8.218921892189218, "percentage": 41.09, "elapsed_time": "2:56:46", "remaining_time": "4:13:23", "throughput": 1486.48, "total_tokens": 15765968} {"current_steps": 74715, "total_steps": 181800, "loss": 0.0092, "lr": 3.666212867912398e-05, "epoch": 8.21947194719472, "percentage": 41.1, "elapsed_time": "2:56:46", "remaining_time": "4:13:22", "throughput": 1486.48, "total_tokens": 15767024} {"current_steps": 74720, "total_steps": 181800, "loss": 0.055, "lr": 3.666000569580202e-05, "epoch": 8.22002200220022, "percentage": 41.1, "elapsed_time": "2:56:47", "remaining_time": "4:13:21", "throughput": 1486.48, "total_tokens": 15768048} {"current_steps": 74725, "total_steps": 181800, "loss": 0.0132, "lr": 3.665788260501539e-05, "epoch": 8.22057205720572, "percentage": 41.1, "elapsed_time": "2:56:48", "remaining_time": "4:13:21", "throughput": 1486.45, "total_tokens": 15769072} {"current_steps": 74730, "total_steps": 181800, "loss": 0.0273, "lr": 3.665575940678366e-05, "epoch": 8.221122112211221, "percentage": 41.11, "elapsed_time": "2:56:49", "remaining_time": "4:13:20", "throughput": 1486.45, "total_tokens": 15770128} {"current_steps": 74735, "total_steps": 181800, "loss": 0.0281, "lr": 3.665363610112637e-05, "epoch": 8.221672167216722, "percentage": 41.11, "elapsed_time": "2:56:49", "remaining_time": "4:13:19", "throughput": 1486.46, "total_tokens": 15771184} {"current_steps": 74740, "total_steps": 181800, "loss": 0.0081, "lr": 3.665151268806312e-05, "epoch": 8.222222222222221, "percentage": 41.11, "elapsed_time": "2:56:50", "remaining_time": "4:13:18", "throughput": 1486.46, "total_tokens": 15772272} {"current_steps": 74745, "total_steps": 181800, "loss": 0.0198, "lr": 3.664938916761346e-05, "epoch": 8.222772277227723, "percentage": 41.11, "elapsed_time": "2:56:51", "remaining_time": "4:13:18", "throughput": 1486.47, "total_tokens": 15773392} {"current_steps": 74750, "total_steps": 181800, "loss": 0.047, "lr": 3.6647265539796975e-05, "epoch": 8.223322332233224, "percentage": 41.12, "elapsed_time": "2:56:51", "remaining_time": "4:13:17", "throughput": 1486.47, "total_tokens": 15774416} {"current_steps": 74755, "total_steps": 181800, "loss": 0.0742, "lr": 3.664514180463324e-05, "epoch": 8.223872387238725, "percentage": 41.12, "elapsed_time": "2:56:52", "remaining_time": "4:13:16", "throughput": 1486.47, "total_tokens": 15775440} {"current_steps": 74760, "total_steps": 181800, "loss": 0.0015, "lr": 3.664301796214181e-05, "epoch": 8.224422442244224, "percentage": 41.12, "elapsed_time": "2:56:53", "remaining_time": "4:13:16", "throughput": 1486.46, "total_tokens": 15776400} {"current_steps": 74765, "total_steps": 181800, "loss": 0.0165, "lr": 3.6640894012342267e-05, "epoch": 8.224972497249725, "percentage": 41.12, "elapsed_time": "2:56:54", "remaining_time": "4:13:15", "throughput": 1486.47, "total_tokens": 15777456} {"current_steps": 74770, "total_steps": 181800, "loss": 0.1036, "lr": 3.66387699552542e-05, "epoch": 8.225522552255226, "percentage": 41.13, "elapsed_time": "2:56:54", "remaining_time": "4:13:14", "throughput": 1486.47, "total_tokens": 15778544} {"current_steps": 74775, "total_steps": 181800, "loss": 0.0144, "lr": 3.6636645790897164e-05, "epoch": 8.226072607260726, "percentage": 41.13, "elapsed_time": "2:56:55", "remaining_time": "4:13:13", "throughput": 1486.47, "total_tokens": 15779536} {"current_steps": 74780, "total_steps": 181800, "loss": 0.0081, "lr": 3.663452151929076e-05, "epoch": 8.226622662266227, "percentage": 41.13, "elapsed_time": "2:56:56", "remaining_time": "4:13:13", "throughput": 1486.47, "total_tokens": 15780560} {"current_steps": 74785, "total_steps": 181800, "loss": 0.0083, "lr": 3.663239714045455e-05, "epoch": 8.227172717271728, "percentage": 41.14, "elapsed_time": "2:56:56", "remaining_time": "4:13:12", "throughput": 1486.47, "total_tokens": 15781584} {"current_steps": 74790, "total_steps": 181800, "loss": 0.027, "lr": 3.663027265440812e-05, "epoch": 8.227722772277227, "percentage": 41.14, "elapsed_time": "2:56:57", "remaining_time": "4:13:11", "throughput": 1486.47, "total_tokens": 15782672} {"current_steps": 74795, "total_steps": 181800, "loss": 0.0199, "lr": 3.662814806117103e-05, "epoch": 8.228272827282728, "percentage": 41.14, "elapsed_time": "2:56:58", "remaining_time": "4:13:10", "throughput": 1486.48, "total_tokens": 15783728} {"current_steps": 74800, "total_steps": 181800, "loss": 0.0727, "lr": 3.66260233607629e-05, "epoch": 8.22882288228823, "percentage": 41.14, "elapsed_time": "2:56:58", "remaining_time": "4:13:10", "throughput": 1486.47, "total_tokens": 15784720} {"current_steps": 74805, "total_steps": 181800, "loss": 0.0256, "lr": 3.662389855320329e-05, "epoch": 8.229372937293729, "percentage": 41.15, "elapsed_time": "2:56:59", "remaining_time": "4:13:09", "throughput": 1486.48, "total_tokens": 15785776} {"current_steps": 74810, "total_steps": 181800, "loss": 0.0739, "lr": 3.662177363851177e-05, "epoch": 8.22992299229923, "percentage": 41.15, "elapsed_time": "2:57:00", "remaining_time": "4:13:08", "throughput": 1486.48, "total_tokens": 15786864} {"current_steps": 74815, "total_steps": 181800, "loss": 0.1521, "lr": 3.6619648616707954e-05, "epoch": 8.23047304730473, "percentage": 41.15, "elapsed_time": "2:57:00", "remaining_time": "4:13:07", "throughput": 1486.49, "total_tokens": 15787920} {"current_steps": 74820, "total_steps": 181800, "loss": 0.0502, "lr": 3.66175234878114e-05, "epoch": 8.231023102310232, "percentage": 41.16, "elapsed_time": "2:57:01", "remaining_time": "4:13:07", "throughput": 1486.49, "total_tokens": 15788976} {"current_steps": 74825, "total_steps": 181800, "loss": 0.0207, "lr": 3.6615398251841716e-05, "epoch": 8.231573157315731, "percentage": 41.16, "elapsed_time": "2:57:02", "remaining_time": "4:13:06", "throughput": 1486.49, "total_tokens": 15790032} {"current_steps": 74830, "total_steps": 181800, "loss": 0.0187, "lr": 3.661327290881847e-05, "epoch": 8.232123212321232, "percentage": 41.16, "elapsed_time": "2:57:03", "remaining_time": "4:13:05", "throughput": 1486.49, "total_tokens": 15791088} {"current_steps": 74835, "total_steps": 181800, "loss": 0.1521, "lr": 3.661114745876127e-05, "epoch": 8.232673267326733, "percentage": 41.16, "elapsed_time": "2:57:03", "remaining_time": "4:13:04", "throughput": 1486.5, "total_tokens": 15792144} {"current_steps": 74840, "total_steps": 181800, "loss": 0.0077, "lr": 3.660902190168969e-05, "epoch": 8.233223322332233, "percentage": 41.17, "elapsed_time": "2:57:04", "remaining_time": "4:13:04", "throughput": 1486.51, "total_tokens": 15793296} {"current_steps": 74845, "total_steps": 181800, "loss": 0.0221, "lr": 3.6606896237623336e-05, "epoch": 8.233773377337734, "percentage": 41.17, "elapsed_time": "2:57:05", "remaining_time": "4:13:03", "throughput": 1486.52, "total_tokens": 15794416} {"current_steps": 74850, "total_steps": 181800, "loss": 0.0541, "lr": 3.660477046658178e-05, "epoch": 8.234323432343235, "percentage": 41.17, "elapsed_time": "2:57:05", "remaining_time": "4:13:02", "throughput": 1486.52, "total_tokens": 15795440} {"current_steps": 74855, "total_steps": 181800, "loss": 0.0145, "lr": 3.660264458858462e-05, "epoch": 8.234873487348734, "percentage": 41.17, "elapsed_time": "2:57:06", "remaining_time": "4:13:02", "throughput": 1486.52, "total_tokens": 15796496} {"current_steps": 74860, "total_steps": 181800, "loss": 0.0212, "lr": 3.660051860365146e-05, "epoch": 8.235423542354235, "percentage": 41.18, "elapsed_time": "2:57:07", "remaining_time": "4:13:01", "throughput": 1486.53, "total_tokens": 15797584} {"current_steps": 74865, "total_steps": 181800, "loss": 0.0369, "lr": 3.659839251180188e-05, "epoch": 8.235973597359736, "percentage": 41.18, "elapsed_time": "2:57:07", "remaining_time": "4:13:00", "throughput": 1486.53, "total_tokens": 15798608} {"current_steps": 74870, "total_steps": 181800, "loss": 0.0079, "lr": 3.6596266313055484e-05, "epoch": 8.236523652365236, "percentage": 41.18, "elapsed_time": "2:57:08", "remaining_time": "4:12:59", "throughput": 1486.53, "total_tokens": 15799728} {"current_steps": 74875, "total_steps": 181800, "loss": 0.075, "lr": 3.659414000743187e-05, "epoch": 8.237073707370737, "percentage": 41.19, "elapsed_time": "2:57:09", "remaining_time": "4:12:59", "throughput": 1486.53, "total_tokens": 15800720} {"current_steps": 74880, "total_steps": 181800, "loss": 0.0189, "lr": 3.659201359495062e-05, "epoch": 8.237623762376238, "percentage": 41.19, "elapsed_time": "2:57:09", "remaining_time": "4:12:58", "throughput": 1486.54, "total_tokens": 15801808} {"current_steps": 74885, "total_steps": 181800, "loss": 0.021, "lr": 3.658988707563135e-05, "epoch": 8.238173817381739, "percentage": 41.19, "elapsed_time": "2:57:10", "remaining_time": "4:12:57", "throughput": 1486.54, "total_tokens": 15802864} {"current_steps": 74890, "total_steps": 181800, "loss": 0.0105, "lr": 3.658776044949366e-05, "epoch": 8.238723872387238, "percentage": 41.19, "elapsed_time": "2:57:11", "remaining_time": "4:12:56", "throughput": 1486.54, "total_tokens": 15803920} {"current_steps": 74895, "total_steps": 181800, "loss": 0.0069, "lr": 3.658563371655713e-05, "epoch": 8.23927392739274, "percentage": 41.2, "elapsed_time": "2:57:12", "remaining_time": "4:12:56", "throughput": 1486.54, "total_tokens": 15804944} {"current_steps": 74900, "total_steps": 181800, "loss": 0.0267, "lr": 3.658350687684138e-05, "epoch": 8.23982398239824, "percentage": 41.2, "elapsed_time": "2:57:12", "remaining_time": "4:12:55", "throughput": 1486.54, "total_tokens": 15806000} {"current_steps": 74905, "total_steps": 181800, "loss": 0.012, "lr": 3.6581379930366005e-05, "epoch": 8.24037403740374, "percentage": 41.2, "elapsed_time": "2:57:13", "remaining_time": "4:12:54", "throughput": 1486.54, "total_tokens": 15806960} {"current_steps": 74910, "total_steps": 181800, "loss": 0.0029, "lr": 3.6579252877150606e-05, "epoch": 8.24092409240924, "percentage": 41.2, "elapsed_time": "2:57:14", "remaining_time": "4:12:53", "throughput": 1486.54, "total_tokens": 15808016} {"current_steps": 74915, "total_steps": 181800, "loss": 0.0027, "lr": 3.657712571721479e-05, "epoch": 8.241474147414742, "percentage": 41.21, "elapsed_time": "2:57:14", "remaining_time": "4:12:53", "throughput": 1486.55, "total_tokens": 15809104} {"current_steps": 74920, "total_steps": 181800, "loss": 0.0386, "lr": 3.657499845057817e-05, "epoch": 8.242024202420241, "percentage": 41.21, "elapsed_time": "2:57:15", "remaining_time": "4:12:52", "throughput": 1486.55, "total_tokens": 15810160} {"current_steps": 74925, "total_steps": 181800, "loss": 0.215, "lr": 3.6572871077260326e-05, "epoch": 8.242574257425742, "percentage": 41.21, "elapsed_time": "2:57:16", "remaining_time": "4:12:51", "throughput": 1486.55, "total_tokens": 15811184} {"current_steps": 74930, "total_steps": 181800, "loss": 0.0079, "lr": 3.6570743597280895e-05, "epoch": 8.243124312431243, "percentage": 41.22, "elapsed_time": "2:57:16", "remaining_time": "4:12:50", "throughput": 1486.55, "total_tokens": 15812208} {"current_steps": 74935, "total_steps": 181800, "loss": 0.0629, "lr": 3.656861601065947e-05, "epoch": 8.243674367436745, "percentage": 41.22, "elapsed_time": "2:57:17", "remaining_time": "4:12:50", "throughput": 1486.55, "total_tokens": 15813296} {"current_steps": 74940, "total_steps": 181800, "loss": 0.0104, "lr": 3.656648831741566e-05, "epoch": 8.244224422442244, "percentage": 41.22, "elapsed_time": "2:57:18", "remaining_time": "4:12:49", "throughput": 1486.56, "total_tokens": 15814384} {"current_steps": 74945, "total_steps": 181800, "loss": 0.0121, "lr": 3.6564360517569076e-05, "epoch": 8.244774477447745, "percentage": 41.22, "elapsed_time": "2:57:18", "remaining_time": "4:12:48", "throughput": 1486.56, "total_tokens": 15815440} {"current_steps": 74950, "total_steps": 181800, "loss": 0.1057, "lr": 3.656223261113934e-05, "epoch": 8.245324532453246, "percentage": 41.23, "elapsed_time": "2:57:19", "remaining_time": "4:12:48", "throughput": 1486.57, "total_tokens": 15816496} {"current_steps": 74955, "total_steps": 181800, "loss": 0.1502, "lr": 3.656010459814604e-05, "epoch": 8.245874587458745, "percentage": 41.23, "elapsed_time": "2:57:20", "remaining_time": "4:12:47", "throughput": 1486.57, "total_tokens": 15817552} {"current_steps": 74960, "total_steps": 181800, "loss": 0.0528, "lr": 3.655797647860881e-05, "epoch": 8.246424642464246, "percentage": 41.23, "elapsed_time": "2:57:20", "remaining_time": "4:12:46", "throughput": 1486.57, "total_tokens": 15818576} {"current_steps": 74965, "total_steps": 181800, "loss": 0.0693, "lr": 3.655584825254726e-05, "epoch": 8.246974697469748, "percentage": 41.23, "elapsed_time": "2:57:21", "remaining_time": "4:12:45", "throughput": 1486.57, "total_tokens": 15819632} {"current_steps": 74970, "total_steps": 181800, "loss": 0.0164, "lr": 3.6553719919981e-05, "epoch": 8.247524752475247, "percentage": 41.24, "elapsed_time": "2:57:22", "remaining_time": "4:12:45", "throughput": 1486.58, "total_tokens": 15820688} {"current_steps": 74975, "total_steps": 181800, "loss": 0.0489, "lr": 3.655159148092965e-05, "epoch": 8.248074807480748, "percentage": 41.24, "elapsed_time": "2:57:23", "remaining_time": "4:12:44", "throughput": 1486.57, "total_tokens": 15821712} {"current_steps": 74980, "total_steps": 181800, "loss": 0.0267, "lr": 3.654946293541282e-05, "epoch": 8.248624862486249, "percentage": 41.24, "elapsed_time": "2:57:23", "remaining_time": "4:12:43", "throughput": 1486.58, "total_tokens": 15822800} {"current_steps": 74985, "total_steps": 181800, "loss": 0.0596, "lr": 3.654733428345013e-05, "epoch": 8.249174917491748, "percentage": 41.25, "elapsed_time": "2:57:24", "remaining_time": "4:12:42", "throughput": 1486.58, "total_tokens": 15823824} {"current_steps": 74990, "total_steps": 181800, "loss": 0.0773, "lr": 3.654520552506121e-05, "epoch": 8.24972497249725, "percentage": 41.25, "elapsed_time": "2:57:25", "remaining_time": "4:12:42", "throughput": 1486.59, "total_tokens": 15824912} {"current_steps": 74995, "total_steps": 181800, "loss": 0.004, "lr": 3.6543076660265666e-05, "epoch": 8.25027502750275, "percentage": 41.25, "elapsed_time": "2:57:25", "remaining_time": "4:12:41", "throughput": 1486.58, "total_tokens": 15825936} {"current_steps": 75000, "total_steps": 181800, "loss": 0.0371, "lr": 3.654094768908312e-05, "epoch": 8.250825082508252, "percentage": 41.25, "elapsed_time": "2:57:26", "remaining_time": "4:12:40", "throughput": 1486.59, "total_tokens": 15827024} {"current_steps": 75005, "total_steps": 181800, "loss": 0.0069, "lr": 3.6538818611533196e-05, "epoch": 8.251375137513751, "percentage": 41.26, "elapsed_time": "2:57:27", "remaining_time": "4:12:39", "throughput": 1486.59, "total_tokens": 15828048} {"current_steps": 75010, "total_steps": 181800, "loss": 0.0924, "lr": 3.6536689427635516e-05, "epoch": 8.251925192519252, "percentage": 41.26, "elapsed_time": "2:57:27", "remaining_time": "4:12:39", "throughput": 1486.6, "total_tokens": 15829136} {"current_steps": 75015, "total_steps": 181800, "loss": 0.0982, "lr": 3.6534560137409715e-05, "epoch": 8.252475247524753, "percentage": 41.26, "elapsed_time": "2:57:28", "remaining_time": "4:12:38", "throughput": 1486.6, "total_tokens": 15830224} {"current_steps": 75020, "total_steps": 181800, "loss": 0.0854, "lr": 3.6532430740875404e-05, "epoch": 8.253025302530252, "percentage": 41.27, "elapsed_time": "2:57:29", "remaining_time": "4:12:37", "throughput": 1486.6, "total_tokens": 15831248} {"current_steps": 75025, "total_steps": 181800, "loss": 0.0659, "lr": 3.6530301238052214e-05, "epoch": 8.253575357535754, "percentage": 41.27, "elapsed_time": "2:57:29", "remaining_time": "4:12:36", "throughput": 1486.61, "total_tokens": 15832336} {"current_steps": 75030, "total_steps": 181800, "loss": 0.008, "lr": 3.652817162895976e-05, "epoch": 8.254125412541255, "percentage": 41.27, "elapsed_time": "2:57:30", "remaining_time": "4:12:36", "throughput": 1486.61, "total_tokens": 15833392} {"current_steps": 75035, "total_steps": 181800, "loss": 0.0929, "lr": 3.6526041913617687e-05, "epoch": 8.254675467546754, "percentage": 41.27, "elapsed_time": "2:57:31", "remaining_time": "4:12:35", "throughput": 1486.61, "total_tokens": 15834448} {"current_steps": 75040, "total_steps": 181800, "loss": 0.0134, "lr": 3.652391209204562e-05, "epoch": 8.255225522552255, "percentage": 41.28, "elapsed_time": "2:57:32", "remaining_time": "4:12:34", "throughput": 1486.62, "total_tokens": 15835536} {"current_steps": 75045, "total_steps": 181800, "loss": 0.0285, "lr": 3.6521782164263186e-05, "epoch": 8.255775577557756, "percentage": 41.28, "elapsed_time": "2:57:32", "remaining_time": "4:12:34", "throughput": 1486.63, "total_tokens": 15836656} {"current_steps": 75050, "total_steps": 181800, "loss": 0.0362, "lr": 3.651965213029e-05, "epoch": 8.256325632563255, "percentage": 41.28, "elapsed_time": "2:57:33", "remaining_time": "4:12:33", "throughput": 1486.63, "total_tokens": 15837712} {"current_steps": 75055, "total_steps": 181800, "loss": 0.0402, "lr": 3.651752199014572e-05, "epoch": 8.256875687568757, "percentage": 41.28, "elapsed_time": "2:57:34", "remaining_time": "4:12:32", "throughput": 1486.64, "total_tokens": 15838800} {"current_steps": 75060, "total_steps": 181800, "loss": 0.0196, "lr": 3.651539174384997e-05, "epoch": 8.257425742574258, "percentage": 41.29, "elapsed_time": "2:57:34", "remaining_time": "4:12:31", "throughput": 1486.64, "total_tokens": 15839856} {"current_steps": 75065, "total_steps": 181800, "loss": 0.0104, "lr": 3.6513261391422376e-05, "epoch": 8.257975797579759, "percentage": 41.29, "elapsed_time": "2:57:35", "remaining_time": "4:12:31", "throughput": 1486.65, "total_tokens": 15840976} {"current_steps": 75070, "total_steps": 181800, "loss": 0.1178, "lr": 3.6511130932882575e-05, "epoch": 8.258525852585258, "percentage": 41.29, "elapsed_time": "2:57:36", "remaining_time": "4:12:30", "throughput": 1486.65, "total_tokens": 15842032} {"current_steps": 75075, "total_steps": 181800, "loss": 0.055, "lr": 3.65090003682502e-05, "epoch": 8.25907590759076, "percentage": 41.3, "elapsed_time": "2:57:36", "remaining_time": "4:12:29", "throughput": 1486.66, "total_tokens": 15843120} {"current_steps": 75080, "total_steps": 181800, "loss": 0.0171, "lr": 3.6506869697544896e-05, "epoch": 8.25962596259626, "percentage": 41.3, "elapsed_time": "2:57:37", "remaining_time": "4:12:28", "throughput": 1486.65, "total_tokens": 15844112} {"current_steps": 75085, "total_steps": 181800, "loss": 0.0251, "lr": 3.6504738920786295e-05, "epoch": 8.26017601760176, "percentage": 41.3, "elapsed_time": "2:57:38", "remaining_time": "4:12:28", "throughput": 1486.66, "total_tokens": 15845200} {"current_steps": 75090, "total_steps": 181800, "loss": 0.0827, "lr": 3.650260803799404e-05, "epoch": 8.26072607260726, "percentage": 41.3, "elapsed_time": "2:57:38", "remaining_time": "4:12:27", "throughput": 1486.66, "total_tokens": 15846256} {"current_steps": 75095, "total_steps": 181800, "loss": 0.1675, "lr": 3.650047704918776e-05, "epoch": 8.261276127612762, "percentage": 41.31, "elapsed_time": "2:57:39", "remaining_time": "4:12:26", "throughput": 1486.67, "total_tokens": 15847344} {"current_steps": 75100, "total_steps": 181800, "loss": 0.0114, "lr": 3.64983459543871e-05, "epoch": 8.261826182618261, "percentage": 41.31, "elapsed_time": "2:57:40", "remaining_time": "4:12:25", "throughput": 1486.66, "total_tokens": 15848336} {"current_steps": 75105, "total_steps": 181800, "loss": 0.1125, "lr": 3.649621475361171e-05, "epoch": 8.262376237623762, "percentage": 41.31, "elapsed_time": "2:57:41", "remaining_time": "4:12:25", "throughput": 1486.66, "total_tokens": 15849360} {"current_steps": 75110, "total_steps": 181800, "loss": 0.0303, "lr": 3.649408344688122e-05, "epoch": 8.262926292629263, "percentage": 41.31, "elapsed_time": "2:57:41", "remaining_time": "4:12:24", "throughput": 1486.67, "total_tokens": 15850448} {"current_steps": 75115, "total_steps": 181800, "loss": 0.0079, "lr": 3.6491952034215284e-05, "epoch": 8.263476347634764, "percentage": 41.32, "elapsed_time": "2:57:42", "remaining_time": "4:12:23", "throughput": 1486.67, "total_tokens": 15851472} {"current_steps": 75120, "total_steps": 181800, "loss": 0.0482, "lr": 3.6489820515633535e-05, "epoch": 8.264026402640264, "percentage": 41.32, "elapsed_time": "2:57:43", "remaining_time": "4:12:22", "throughput": 1486.67, "total_tokens": 15852496} {"current_steps": 75125, "total_steps": 181800, "loss": 0.0443, "lr": 3.6487688891155625e-05, "epoch": 8.264576457645765, "percentage": 41.32, "elapsed_time": "2:57:43", "remaining_time": "4:12:22", "throughput": 1486.67, "total_tokens": 15853584} {"current_steps": 75130, "total_steps": 181800, "loss": 0.0166, "lr": 3.648555716080119e-05, "epoch": 8.265126512651266, "percentage": 41.33, "elapsed_time": "2:57:44", "remaining_time": "4:12:21", "throughput": 1486.68, "total_tokens": 15854672} {"current_steps": 75135, "total_steps": 181800, "loss": 0.0112, "lr": 3.64834253245899e-05, "epoch": 8.265676567656765, "percentage": 41.33, "elapsed_time": "2:57:45", "remaining_time": "4:12:20", "throughput": 1486.68, "total_tokens": 15855760} {"current_steps": 75140, "total_steps": 181800, "loss": 0.0171, "lr": 3.648129338254139e-05, "epoch": 8.266226622662266, "percentage": 41.33, "elapsed_time": "2:57:45", "remaining_time": "4:12:20", "throughput": 1486.68, "total_tokens": 15856752} {"current_steps": 75145, "total_steps": 181800, "loss": 0.0283, "lr": 3.6479161334675296e-05, "epoch": 8.266776677667767, "percentage": 41.33, "elapsed_time": "2:57:46", "remaining_time": "4:12:19", "throughput": 1486.69, "total_tokens": 15857840} {"current_steps": 75150, "total_steps": 181800, "loss": 0.0412, "lr": 3.647702918101128e-05, "epoch": 8.267326732673267, "percentage": 41.34, "elapsed_time": "2:57:47", "remaining_time": "4:12:18", "throughput": 1486.69, "total_tokens": 15858960} {"current_steps": 75155, "total_steps": 181800, "loss": 0.0204, "lr": 3.6474896921569e-05, "epoch": 8.267876787678768, "percentage": 41.34, "elapsed_time": "2:57:47", "remaining_time": "4:12:17", "throughput": 1486.7, "total_tokens": 15860048} {"current_steps": 75160, "total_steps": 181800, "loss": 0.0492, "lr": 3.6472764556368105e-05, "epoch": 8.268426842684269, "percentage": 41.34, "elapsed_time": "2:57:48", "remaining_time": "4:12:17", "throughput": 1486.7, "total_tokens": 15861104} {"current_steps": 75165, "total_steps": 181800, "loss": 0.1016, "lr": 3.647063208542824e-05, "epoch": 8.268976897689768, "percentage": 41.34, "elapsed_time": "2:57:49", "remaining_time": "4:12:16", "throughput": 1486.71, "total_tokens": 15862192} {"current_steps": 75170, "total_steps": 181800, "loss": 0.0614, "lr": 3.646849950876906e-05, "epoch": 8.26952695269527, "percentage": 41.35, "elapsed_time": "2:57:50", "remaining_time": "4:12:15", "throughput": 1486.71, "total_tokens": 15863216} {"current_steps": 75175, "total_steps": 181800, "loss": 0.0335, "lr": 3.646636682641022e-05, "epoch": 8.27007700770077, "percentage": 41.35, "elapsed_time": "2:57:50", "remaining_time": "4:12:14", "throughput": 1486.71, "total_tokens": 15864240} {"current_steps": 75180, "total_steps": 181800, "loss": 0.0143, "lr": 3.6464234038371394e-05, "epoch": 8.270627062706271, "percentage": 41.35, "elapsed_time": "2:57:51", "remaining_time": "4:12:14", "throughput": 1486.71, "total_tokens": 15865328} {"current_steps": 75185, "total_steps": 181800, "loss": 0.0246, "lr": 3.646210114467221e-05, "epoch": 8.27117711771177, "percentage": 41.36, "elapsed_time": "2:57:52", "remaining_time": "4:12:13", "throughput": 1486.72, "total_tokens": 15866416} {"current_steps": 75190, "total_steps": 181800, "loss": 0.0971, "lr": 3.645996814533235e-05, "epoch": 8.271727172717272, "percentage": 41.36, "elapsed_time": "2:57:52", "remaining_time": "4:12:12", "throughput": 1486.73, "total_tokens": 15867536} {"current_steps": 75195, "total_steps": 181800, "loss": 0.0088, "lr": 3.645783504037146e-05, "epoch": 8.272277227722773, "percentage": 41.36, "elapsed_time": "2:57:53", "remaining_time": "4:12:11", "throughput": 1486.73, "total_tokens": 15868592} {"current_steps": 75200, "total_steps": 181800, "loss": 0.0369, "lr": 3.6455701829809196e-05, "epoch": 8.272827282728272, "percentage": 41.36, "elapsed_time": "2:57:54", "remaining_time": "4:12:11", "throughput": 1486.74, "total_tokens": 15869712} {"current_steps": 75205, "total_steps": 181800, "loss": 0.0928, "lr": 3.6453568513665227e-05, "epoch": 8.273377337733773, "percentage": 41.37, "elapsed_time": "2:57:54", "remaining_time": "4:12:10", "throughput": 1486.74, "total_tokens": 15870768} {"current_steps": 75210, "total_steps": 181800, "loss": 0.0404, "lr": 3.645143509195922e-05, "epoch": 8.273927392739274, "percentage": 41.37, "elapsed_time": "2:57:55", "remaining_time": "4:12:09", "throughput": 1486.75, "total_tokens": 15871856} {"current_steps": 75215, "total_steps": 181800, "loss": 0.0037, "lr": 3.644930156471082e-05, "epoch": 8.274477447744774, "percentage": 41.37, "elapsed_time": "2:57:56", "remaining_time": "4:12:09", "throughput": 1486.75, "total_tokens": 15872976} {"current_steps": 75220, "total_steps": 181800, "loss": 0.0021, "lr": 3.644716793193971e-05, "epoch": 8.275027502750275, "percentage": 41.38, "elapsed_time": "2:57:56", "remaining_time": "4:12:08", "throughput": 1486.75, "total_tokens": 15874000} {"current_steps": 75225, "total_steps": 181800, "loss": 0.0572, "lr": 3.644503419366554e-05, "epoch": 8.275577557755776, "percentage": 41.38, "elapsed_time": "2:57:57", "remaining_time": "4:12:07", "throughput": 1486.75, "total_tokens": 15875024} {"current_steps": 75230, "total_steps": 181800, "loss": 0.0107, "lr": 3.6442900349907985e-05, "epoch": 8.276127612761275, "percentage": 41.38, "elapsed_time": "2:57:58", "remaining_time": "4:12:06", "throughput": 1486.76, "total_tokens": 15876144} {"current_steps": 75235, "total_steps": 181800, "loss": 0.0577, "lr": 3.644076640068671e-05, "epoch": 8.276677667766776, "percentage": 41.38, "elapsed_time": "2:57:59", "remaining_time": "4:12:06", "throughput": 1486.77, "total_tokens": 15877232} {"current_steps": 75240, "total_steps": 181800, "loss": 0.0567, "lr": 3.6438632346021376e-05, "epoch": 8.277227722772277, "percentage": 41.39, "elapsed_time": "2:57:59", "remaining_time": "4:12:05", "throughput": 1486.77, "total_tokens": 15878256} {"current_steps": 75245, "total_steps": 181800, "loss": 0.0567, "lr": 3.643649818593166e-05, "epoch": 8.277777777777779, "percentage": 41.39, "elapsed_time": "2:58:00", "remaining_time": "4:12:04", "throughput": 1486.77, "total_tokens": 15879344} {"current_steps": 75250, "total_steps": 181800, "loss": 0.0104, "lr": 3.6434363920437226e-05, "epoch": 8.278327832783278, "percentage": 41.39, "elapsed_time": "2:58:01", "remaining_time": "4:12:03", "throughput": 1486.77, "total_tokens": 15880368} {"current_steps": 75255, "total_steps": 181800, "loss": 0.0843, "lr": 3.6432229549557754e-05, "epoch": 8.278877887788779, "percentage": 41.39, "elapsed_time": "2:58:01", "remaining_time": "4:12:03", "throughput": 1486.78, "total_tokens": 15881456} {"current_steps": 75260, "total_steps": 181800, "loss": 0.0683, "lr": 3.64300950733129e-05, "epoch": 8.27942794279428, "percentage": 41.4, "elapsed_time": "2:58:02", "remaining_time": "4:12:02", "throughput": 1486.78, "total_tokens": 15882512} {"current_steps": 75265, "total_steps": 181800, "loss": 0.0344, "lr": 3.6427960491722346e-05, "epoch": 8.27997799779978, "percentage": 41.4, "elapsed_time": "2:58:03", "remaining_time": "4:12:01", "throughput": 1486.79, "total_tokens": 15883600} {"current_steps": 75270, "total_steps": 181800, "loss": 0.0291, "lr": 3.642582580480576e-05, "epoch": 8.28052805280528, "percentage": 41.4, "elapsed_time": "2:58:03", "remaining_time": "4:12:00", "throughput": 1486.8, "total_tokens": 15884688} {"current_steps": 75275, "total_steps": 181800, "loss": 0.0207, "lr": 3.642369101258283e-05, "epoch": 8.281078107810782, "percentage": 41.41, "elapsed_time": "2:58:04", "remaining_time": "4:12:00", "throughput": 1486.8, "total_tokens": 15885744} {"current_steps": 75280, "total_steps": 181800, "loss": 0.0235, "lr": 3.642155611507321e-05, "epoch": 8.281628162816281, "percentage": 41.41, "elapsed_time": "2:58:05", "remaining_time": "4:11:59", "throughput": 1486.8, "total_tokens": 15886832} {"current_steps": 75285, "total_steps": 181800, "loss": 0.0503, "lr": 3.6419421112296596e-05, "epoch": 8.282178217821782, "percentage": 41.41, "elapsed_time": "2:58:05", "remaining_time": "4:11:58", "throughput": 1486.81, "total_tokens": 15887888} {"current_steps": 75290, "total_steps": 181800, "loss": 0.0376, "lr": 3.6417286004272654e-05, "epoch": 8.282728272827283, "percentage": 41.41, "elapsed_time": "2:58:06", "remaining_time": "4:11:57", "throughput": 1486.81, "total_tokens": 15888944} {"current_steps": 75295, "total_steps": 181800, "loss": 0.0128, "lr": 3.641515079102107e-05, "epoch": 8.283278327832782, "percentage": 41.42, "elapsed_time": "2:58:07", "remaining_time": "4:11:57", "throughput": 1486.82, "total_tokens": 15890064} {"current_steps": 75300, "total_steps": 181800, "loss": 0.0168, "lr": 3.641301547256151e-05, "epoch": 8.283828382838283, "percentage": 41.42, "elapsed_time": "2:58:07", "remaining_time": "4:11:56", "throughput": 1486.82, "total_tokens": 15891120} {"current_steps": 75305, "total_steps": 181800, "loss": 0.0323, "lr": 3.641088004891367e-05, "epoch": 8.284378437843785, "percentage": 41.42, "elapsed_time": "2:58:08", "remaining_time": "4:11:55", "throughput": 1486.82, "total_tokens": 15892144} {"current_steps": 75310, "total_steps": 181800, "loss": 0.0968, "lr": 3.6408744520097226e-05, "epoch": 8.284928492849286, "percentage": 41.42, "elapsed_time": "2:58:09", "remaining_time": "4:11:54", "throughput": 1486.83, "total_tokens": 15893232} {"current_steps": 75315, "total_steps": 181800, "loss": 0.1052, "lr": 3.640660888613185e-05, "epoch": 8.285478547854785, "percentage": 41.43, "elapsed_time": "2:58:10", "remaining_time": "4:11:54", "throughput": 1486.83, "total_tokens": 15894288} {"current_steps": 75320, "total_steps": 181800, "loss": 0.1841, "lr": 3.6404473147037235e-05, "epoch": 8.286028602860286, "percentage": 41.43, "elapsed_time": "2:58:10", "remaining_time": "4:11:53", "throughput": 1486.83, "total_tokens": 15895312} {"current_steps": 75325, "total_steps": 181800, "loss": 0.0209, "lr": 3.640233730283307e-05, "epoch": 8.286578657865787, "percentage": 41.43, "elapsed_time": "2:58:11", "remaining_time": "4:11:52", "throughput": 1486.83, "total_tokens": 15896336} {"current_steps": 75330, "total_steps": 181800, "loss": 0.0152, "lr": 3.640020135353902e-05, "epoch": 8.287128712871286, "percentage": 41.44, "elapsed_time": "2:58:12", "remaining_time": "4:11:52", "throughput": 1486.84, "total_tokens": 15897424} {"current_steps": 75335, "total_steps": 181800, "loss": 0.1211, "lr": 3.63980652991748e-05, "epoch": 8.287678767876788, "percentage": 41.44, "elapsed_time": "2:58:12", "remaining_time": "4:11:51", "throughput": 1486.84, "total_tokens": 15898448} {"current_steps": 75340, "total_steps": 181800, "loss": 0.0473, "lr": 3.639592913976008e-05, "epoch": 8.288228822882289, "percentage": 41.44, "elapsed_time": "2:58:13", "remaining_time": "4:11:50", "throughput": 1486.84, "total_tokens": 15899536} {"current_steps": 75345, "total_steps": 181800, "loss": 0.0234, "lr": 3.639379287531454e-05, "epoch": 8.288778877887788, "percentage": 41.44, "elapsed_time": "2:58:14", "remaining_time": "4:11:49", "throughput": 1486.85, "total_tokens": 15900592} {"current_steps": 75350, "total_steps": 181800, "loss": 0.0115, "lr": 3.639165650585789e-05, "epoch": 8.289328932893289, "percentage": 41.45, "elapsed_time": "2:58:14", "remaining_time": "4:11:49", "throughput": 1486.85, "total_tokens": 15901680} {"current_steps": 75355, "total_steps": 181800, "loss": 0.03, "lr": 3.6389520031409794e-05, "epoch": 8.28987898789879, "percentage": 41.45, "elapsed_time": "2:58:15", "remaining_time": "4:11:48", "throughput": 1486.86, "total_tokens": 15902800} {"current_steps": 75360, "total_steps": 181800, "loss": 0.0058, "lr": 3.6387383451989964e-05, "epoch": 8.290429042904291, "percentage": 41.45, "elapsed_time": "2:58:16", "remaining_time": "4:11:47", "throughput": 1486.86, "total_tokens": 15903824} {"current_steps": 75365, "total_steps": 181800, "loss": 0.0076, "lr": 3.6385246767618083e-05, "epoch": 8.29097909790979, "percentage": 41.45, "elapsed_time": "2:58:16", "remaining_time": "4:11:46", "throughput": 1486.86, "total_tokens": 15904880} {"current_steps": 75370, "total_steps": 181800, "loss": 0.008, "lr": 3.638310997831386e-05, "epoch": 8.291529152915292, "percentage": 41.46, "elapsed_time": "2:58:17", "remaining_time": "4:11:46", "throughput": 1486.86, "total_tokens": 15905904} {"current_steps": 75375, "total_steps": 181800, "loss": 0.071, "lr": 3.638097308409696e-05, "epoch": 8.292079207920793, "percentage": 41.46, "elapsed_time": "2:58:18", "remaining_time": "4:11:45", "throughput": 1486.87, "total_tokens": 15906928} {"current_steps": 75380, "total_steps": 181800, "loss": 0.043, "lr": 3.637883608498709e-05, "epoch": 8.292629262926292, "percentage": 41.46, "elapsed_time": "2:58:18", "remaining_time": "4:11:44", "throughput": 1486.87, "total_tokens": 15907952} {"current_steps": 75385, "total_steps": 181800, "loss": 0.0034, "lr": 3.6376698981003955e-05, "epoch": 8.293179317931793, "percentage": 41.47, "elapsed_time": "2:58:19", "remaining_time": "4:11:43", "throughput": 1486.87, "total_tokens": 15909040} {"current_steps": 75390, "total_steps": 181800, "loss": 0.0202, "lr": 3.637456177216724e-05, "epoch": 8.293729372937294, "percentage": 41.47, "elapsed_time": "2:58:20", "remaining_time": "4:11:43", "throughput": 1486.87, "total_tokens": 15910064} {"current_steps": 75395, "total_steps": 181800, "loss": 0.0203, "lr": 3.6372424458496654e-05, "epoch": 8.294279427942794, "percentage": 41.47, "elapsed_time": "2:58:21", "remaining_time": "4:11:42", "throughput": 1486.88, "total_tokens": 15911152} {"current_steps": 75400, "total_steps": 181800, "loss": 0.0104, "lr": 3.637028704001188e-05, "epoch": 8.294829482948295, "percentage": 41.47, "elapsed_time": "2:58:21", "remaining_time": "4:11:41", "throughput": 1486.88, "total_tokens": 15912208} {"current_steps": 75405, "total_steps": 181800, "loss": 0.0013, "lr": 3.636814951673263e-05, "epoch": 8.295379537953796, "percentage": 41.48, "elapsed_time": "2:58:22", "remaining_time": "4:11:40", "throughput": 1486.88, "total_tokens": 15913264} {"current_steps": 75410, "total_steps": 181800, "loss": 0.0623, "lr": 3.63660118886786e-05, "epoch": 8.295929592959295, "percentage": 41.48, "elapsed_time": "2:58:23", "remaining_time": "4:11:40", "throughput": 1486.89, "total_tokens": 15914320} {"current_steps": 75415, "total_steps": 181800, "loss": 0.0212, "lr": 3.636387415586949e-05, "epoch": 8.296479647964796, "percentage": 41.48, "elapsed_time": "2:58:23", "remaining_time": "4:11:39", "throughput": 1486.88, "total_tokens": 15915312} {"current_steps": 75420, "total_steps": 181800, "loss": 0.012, "lr": 3.636173631832501e-05, "epoch": 8.297029702970297, "percentage": 41.49, "elapsed_time": "2:58:24", "remaining_time": "4:11:38", "throughput": 1486.89, "total_tokens": 15916400} {"current_steps": 75425, "total_steps": 181800, "loss": 0.0327, "lr": 3.6359598376064866e-05, "epoch": 8.297579757975798, "percentage": 41.49, "elapsed_time": "2:58:25", "remaining_time": "4:11:37", "throughput": 1486.89, "total_tokens": 15917456} {"current_steps": 75430, "total_steps": 181800, "loss": 0.061, "lr": 3.635746032910874e-05, "epoch": 8.298129812981298, "percentage": 41.49, "elapsed_time": "2:58:25", "remaining_time": "4:11:37", "throughput": 1486.9, "total_tokens": 15918544} {"current_steps": 75435, "total_steps": 181800, "loss": 0.0499, "lr": 3.635532217747636e-05, "epoch": 8.298679867986799, "percentage": 41.49, "elapsed_time": "2:58:26", "remaining_time": "4:11:36", "throughput": 1486.9, "total_tokens": 15919568} {"current_steps": 75440, "total_steps": 181800, "loss": 0.0266, "lr": 3.635318392118742e-05, "epoch": 8.2992299229923, "percentage": 41.5, "elapsed_time": "2:58:27", "remaining_time": "4:11:35", "throughput": 1486.89, "total_tokens": 15920560} {"current_steps": 75445, "total_steps": 181800, "loss": 0.0854, "lr": 3.6351045560261636e-05, "epoch": 8.2997799779978, "percentage": 41.5, "elapsed_time": "2:58:27", "remaining_time": "4:11:35", "throughput": 1486.9, "total_tokens": 15921616} {"current_steps": 75450, "total_steps": 181800, "loss": 0.0103, "lr": 3.6348907094718707e-05, "epoch": 8.3003300330033, "percentage": 41.5, "elapsed_time": "2:58:28", "remaining_time": "4:11:34", "throughput": 1486.9, "total_tokens": 15922736} {"current_steps": 75455, "total_steps": 181800, "loss": 0.013, "lr": 3.634676852457835e-05, "epoch": 8.300880088008801, "percentage": 41.5, "elapsed_time": "2:58:29", "remaining_time": "4:11:33", "throughput": 1486.91, "total_tokens": 15923792} {"current_steps": 75460, "total_steps": 181800, "loss": 0.1167, "lr": 3.6344629849860266e-05, "epoch": 8.3014301430143, "percentage": 41.51, "elapsed_time": "2:58:30", "remaining_time": "4:11:32", "throughput": 1486.91, "total_tokens": 15924848} {"current_steps": 75465, "total_steps": 181800, "loss": 0.0275, "lr": 3.6342491070584186e-05, "epoch": 8.301980198019802, "percentage": 41.51, "elapsed_time": "2:58:30", "remaining_time": "4:11:32", "throughput": 1486.91, "total_tokens": 15925904} {"current_steps": 75470, "total_steps": 181800, "loss": 0.0114, "lr": 3.63403521867698e-05, "epoch": 8.302530253025303, "percentage": 41.51, "elapsed_time": "2:58:31", "remaining_time": "4:11:31", "throughput": 1486.92, "total_tokens": 15926992} {"current_steps": 75475, "total_steps": 181800, "loss": 0.006, "lr": 3.633821319843683e-05, "epoch": 8.303080308030804, "percentage": 41.52, "elapsed_time": "2:58:32", "remaining_time": "4:11:30", "throughput": 1486.92, "total_tokens": 15928048} {"current_steps": 75480, "total_steps": 181800, "loss": 0.0063, "lr": 3.6336074105604986e-05, "epoch": 8.303630363036303, "percentage": 41.52, "elapsed_time": "2:58:32", "remaining_time": "4:11:29", "throughput": 1486.92, "total_tokens": 15929104} {"current_steps": 75485, "total_steps": 181800, "loss": 0.0197, "lr": 3.633393490829399e-05, "epoch": 8.304180418041804, "percentage": 41.52, "elapsed_time": "2:58:33", "remaining_time": "4:11:29", "throughput": 1486.93, "total_tokens": 15930160} {"current_steps": 75490, "total_steps": 181800, "loss": 0.0044, "lr": 3.6331795606523556e-05, "epoch": 8.304730473047305, "percentage": 41.52, "elapsed_time": "2:58:34", "remaining_time": "4:11:28", "throughput": 1486.92, "total_tokens": 15931184} {"current_steps": 75495, "total_steps": 181800, "loss": 0.0193, "lr": 3.63296562003134e-05, "epoch": 8.305280528052805, "percentage": 41.53, "elapsed_time": "2:58:34", "remaining_time": "4:11:27", "throughput": 1486.93, "total_tokens": 15932240} {"current_steps": 75500, "total_steps": 181800, "loss": 0.0197, "lr": 3.632751668968323e-05, "epoch": 8.305830583058306, "percentage": 41.53, "elapsed_time": "2:58:35", "remaining_time": "4:11:26", "throughput": 1486.93, "total_tokens": 15933328} {"current_steps": 75505, "total_steps": 181800, "loss": 0.0656, "lr": 3.632537707465278e-05, "epoch": 8.306380638063807, "percentage": 41.53, "elapsed_time": "2:58:36", "remaining_time": "4:11:26", "throughput": 1486.94, "total_tokens": 15934384} {"current_steps": 75510, "total_steps": 181800, "loss": 0.0133, "lr": 3.632323735524177e-05, "epoch": 8.306930693069306, "percentage": 41.53, "elapsed_time": "2:58:36", "remaining_time": "4:11:25", "throughput": 1486.94, "total_tokens": 15935504} {"current_steps": 75515, "total_steps": 181800, "loss": 0.0121, "lr": 3.6321097531469913e-05, "epoch": 8.307480748074807, "percentage": 41.54, "elapsed_time": "2:58:37", "remaining_time": "4:11:24", "throughput": 1486.94, "total_tokens": 15936528} {"current_steps": 75520, "total_steps": 181800, "loss": 0.1054, "lr": 3.631895760335692e-05, "epoch": 8.308030803080309, "percentage": 41.54, "elapsed_time": "2:58:38", "remaining_time": "4:11:24", "throughput": 1486.94, "total_tokens": 15937552} {"current_steps": 75525, "total_steps": 181800, "loss": 0.019, "lr": 3.631681757092254e-05, "epoch": 8.308580858085808, "percentage": 41.54, "elapsed_time": "2:58:39", "remaining_time": "4:11:23", "throughput": 1486.95, "total_tokens": 15938640} {"current_steps": 75530, "total_steps": 181800, "loss": 0.0015, "lr": 3.631467743418648e-05, "epoch": 8.309130913091309, "percentage": 41.55, "elapsed_time": "2:58:39", "remaining_time": "4:11:22", "throughput": 1486.94, "total_tokens": 15939600} {"current_steps": 75535, "total_steps": 181800, "loss": 0.0119, "lr": 3.631253719316847e-05, "epoch": 8.30968096809681, "percentage": 41.55, "elapsed_time": "2:58:40", "remaining_time": "4:11:21", "throughput": 1486.95, "total_tokens": 15940656} {"current_steps": 75540, "total_steps": 181800, "loss": 0.0852, "lr": 3.631039684788822e-05, "epoch": 8.310231023102311, "percentage": 41.55, "elapsed_time": "2:58:41", "remaining_time": "4:11:21", "throughput": 1486.95, "total_tokens": 15941744} {"current_steps": 75545, "total_steps": 181800, "loss": 0.026, "lr": 3.630825639836548e-05, "epoch": 8.31078107810781, "percentage": 41.55, "elapsed_time": "2:58:41", "remaining_time": "4:11:20", "throughput": 1486.96, "total_tokens": 15942864} {"current_steps": 75550, "total_steps": 181800, "loss": 0.0063, "lr": 3.630611584461996e-05, "epoch": 8.311331133113312, "percentage": 41.56, "elapsed_time": "2:58:42", "remaining_time": "4:11:19", "throughput": 1486.96, "total_tokens": 15943856} {"current_steps": 75555, "total_steps": 181800, "loss": 0.0512, "lr": 3.63039751866714e-05, "epoch": 8.311881188118813, "percentage": 41.56, "elapsed_time": "2:58:43", "remaining_time": "4:11:18", "throughput": 1486.96, "total_tokens": 15944912} {"current_steps": 75560, "total_steps": 181800, "loss": 0.0867, "lr": 3.630183442453954e-05, "epoch": 8.312431243124312, "percentage": 41.56, "elapsed_time": "2:58:43", "remaining_time": "4:11:18", "throughput": 1486.97, "total_tokens": 15946000} {"current_steps": 75565, "total_steps": 181800, "loss": 0.0022, "lr": 3.629969355824407e-05, "epoch": 8.312981298129813, "percentage": 41.56, "elapsed_time": "2:58:44", "remaining_time": "4:11:17", "throughput": 1486.97, "total_tokens": 15947056} {"current_steps": 75570, "total_steps": 181800, "loss": 0.0044, "lr": 3.629755258780476e-05, "epoch": 8.313531353135314, "percentage": 41.57, "elapsed_time": "2:58:45", "remaining_time": "4:11:16", "throughput": 1486.96, "total_tokens": 15948048} {"current_steps": 75575, "total_steps": 181800, "loss": 0.0121, "lr": 3.629541151324133e-05, "epoch": 8.314081408140813, "percentage": 41.57, "elapsed_time": "2:58:45", "remaining_time": "4:11:15", "throughput": 1486.97, "total_tokens": 15949104} {"current_steps": 75580, "total_steps": 181800, "loss": 0.0262, "lr": 3.6293270334573506e-05, "epoch": 8.314631463146315, "percentage": 41.57, "elapsed_time": "2:58:46", "remaining_time": "4:11:15", "throughput": 1486.97, "total_tokens": 15950160} {"current_steps": 75585, "total_steps": 181800, "loss": 0.0031, "lr": 3.629112905182103e-05, "epoch": 8.315181518151816, "percentage": 41.58, "elapsed_time": "2:58:47", "remaining_time": "4:11:14", "throughput": 1486.97, "total_tokens": 15951216} {"current_steps": 75590, "total_steps": 181800, "loss": 0.0181, "lr": 3.628898766500364e-05, "epoch": 8.315731573157315, "percentage": 41.58, "elapsed_time": "2:58:48", "remaining_time": "4:11:13", "throughput": 1486.98, "total_tokens": 15952336} {"current_steps": 75595, "total_steps": 181800, "loss": 0.0966, "lr": 3.628684617414106e-05, "epoch": 8.316281628162816, "percentage": 41.58, "elapsed_time": "2:58:48", "remaining_time": "4:11:12", "throughput": 1486.98, "total_tokens": 15953360} {"current_steps": 75600, "total_steps": 181800, "loss": 0.2327, "lr": 3.6284704579253035e-05, "epoch": 8.316831683168317, "percentage": 41.58, "elapsed_time": "2:58:49", "remaining_time": "4:11:12", "throughput": 1486.98, "total_tokens": 15954384} {"current_steps": 75605, "total_steps": 181800, "loss": 0.1677, "lr": 3.628256288035931e-05, "epoch": 8.317381738173818, "percentage": 41.59, "elapsed_time": "2:58:50", "remaining_time": "4:11:11", "throughput": 1486.98, "total_tokens": 15955408} {"current_steps": 75610, "total_steps": 181800, "loss": 0.0983, "lr": 3.628042107747962e-05, "epoch": 8.317931793179318, "percentage": 41.59, "elapsed_time": "2:58:50", "remaining_time": "4:11:10", "throughput": 1486.98, "total_tokens": 15956432} {"current_steps": 75615, "total_steps": 181800, "loss": 0.0863, "lr": 3.6278279170633687e-05, "epoch": 8.318481848184819, "percentage": 41.59, "elapsed_time": "2:58:51", "remaining_time": "4:11:10", "throughput": 1486.98, "total_tokens": 15957488} {"current_steps": 75620, "total_steps": 181800, "loss": 0.0063, "lr": 3.627613715984128e-05, "epoch": 8.31903190319032, "percentage": 41.6, "elapsed_time": "2:58:52", "remaining_time": "4:11:09", "throughput": 1486.98, "total_tokens": 15958544} {"current_steps": 75625, "total_steps": 181800, "loss": 0.0732, "lr": 3.6273995045122114e-05, "epoch": 8.319581958195819, "percentage": 41.6, "elapsed_time": "2:58:52", "remaining_time": "4:11:08", "throughput": 1486.99, "total_tokens": 15959632} {"current_steps": 75630, "total_steps": 181800, "loss": 0.1398, "lr": 3.627185282649596e-05, "epoch": 8.32013201320132, "percentage": 41.6, "elapsed_time": "2:58:53", "remaining_time": "4:11:07", "throughput": 1487.0, "total_tokens": 15960720} {"current_steps": 75635, "total_steps": 181800, "loss": 0.0485, "lr": 3.626971050398254e-05, "epoch": 8.320682068206821, "percentage": 41.6, "elapsed_time": "2:58:54", "remaining_time": "4:11:07", "throughput": 1487.0, "total_tokens": 15961744} {"current_steps": 75640, "total_steps": 181800, "loss": 0.0455, "lr": 3.6267568077601605e-05, "epoch": 8.32123212321232, "percentage": 41.61, "elapsed_time": "2:58:54", "remaining_time": "4:11:06", "throughput": 1487.0, "total_tokens": 15962832} {"current_steps": 75645, "total_steps": 181800, "loss": 0.1323, "lr": 3.6265425547372906e-05, "epoch": 8.321782178217822, "percentage": 41.61, "elapsed_time": "2:58:55", "remaining_time": "4:11:05", "throughput": 1487.0, "total_tokens": 15963888} {"current_steps": 75650, "total_steps": 181800, "loss": 0.0427, "lr": 3.626328291331618e-05, "epoch": 8.322332233223323, "percentage": 41.61, "elapsed_time": "2:58:56", "remaining_time": "4:11:04", "throughput": 1487.01, "total_tokens": 15964944} {"current_steps": 75655, "total_steps": 181800, "loss": 0.0171, "lr": 3.626114017545119e-05, "epoch": 8.322882288228822, "percentage": 41.61, "elapsed_time": "2:58:56", "remaining_time": "4:11:04", "throughput": 1487.01, "total_tokens": 15965968} {"current_steps": 75660, "total_steps": 181800, "loss": 0.0236, "lr": 3.6258997333797664e-05, "epoch": 8.323432343234323, "percentage": 41.62, "elapsed_time": "2:58:57", "remaining_time": "4:11:03", "throughput": 1487.02, "total_tokens": 15967120} {"current_steps": 75665, "total_steps": 181800, "loss": 0.0105, "lr": 3.625685438837537e-05, "epoch": 8.323982398239824, "percentage": 41.62, "elapsed_time": "2:58:58", "remaining_time": "4:11:02", "throughput": 1487.02, "total_tokens": 15968176} {"current_steps": 75670, "total_steps": 181800, "loss": 0.0422, "lr": 3.625471133920404e-05, "epoch": 8.324532453245325, "percentage": 41.62, "elapsed_time": "2:58:59", "remaining_time": "4:11:01", "throughput": 1487.02, "total_tokens": 15969232} {"current_steps": 75675, "total_steps": 181800, "loss": 0.0667, "lr": 3.625256818630345e-05, "epoch": 8.325082508250825, "percentage": 41.63, "elapsed_time": "2:58:59", "remaining_time": "4:11:01", "throughput": 1487.02, "total_tokens": 15970224} {"current_steps": 75680, "total_steps": 181800, "loss": 0.006, "lr": 3.625042492969333e-05, "epoch": 8.325632563256326, "percentage": 41.63, "elapsed_time": "2:59:00", "remaining_time": "4:11:00", "throughput": 1487.02, "total_tokens": 15971216} {"current_steps": 75685, "total_steps": 181800, "loss": 0.0179, "lr": 3.624828156939344e-05, "epoch": 8.326182618261827, "percentage": 41.63, "elapsed_time": "2:59:01", "remaining_time": "4:10:59", "throughput": 1487.02, "total_tokens": 15972240} {"current_steps": 75690, "total_steps": 181800, "loss": 0.0447, "lr": 3.6246138105423546e-05, "epoch": 8.326732673267326, "percentage": 41.63, "elapsed_time": "2:59:01", "remaining_time": "4:10:58", "throughput": 1487.02, "total_tokens": 15973296} {"current_steps": 75695, "total_steps": 181800, "loss": 0.0126, "lr": 3.624399453780338e-05, "epoch": 8.327282728272827, "percentage": 41.64, "elapsed_time": "2:59:02", "remaining_time": "4:10:58", "throughput": 1487.02, "total_tokens": 15974352} {"current_steps": 75700, "total_steps": 181800, "loss": 0.0184, "lr": 3.624185086655272e-05, "epoch": 8.327832783278328, "percentage": 41.64, "elapsed_time": "2:59:03", "remaining_time": "4:10:57", "throughput": 1487.02, "total_tokens": 15975376} {"current_steps": 75705, "total_steps": 181800, "loss": 0.0067, "lr": 3.623970709169132e-05, "epoch": 8.328382838283828, "percentage": 41.64, "elapsed_time": "2:59:03", "remaining_time": "4:10:56", "throughput": 1487.02, "total_tokens": 15976368} {"current_steps": 75710, "total_steps": 181800, "loss": 0.0046, "lr": 3.6237563213238924e-05, "epoch": 8.328932893289329, "percentage": 41.64, "elapsed_time": "2:59:04", "remaining_time": "4:10:56", "throughput": 1487.03, "total_tokens": 15977488} {"current_steps": 75715, "total_steps": 181800, "loss": 0.0297, "lr": 3.62354192312153e-05, "epoch": 8.32948294829483, "percentage": 41.65, "elapsed_time": "2:59:05", "remaining_time": "4:10:55", "throughput": 1487.03, "total_tokens": 15978544} {"current_steps": 75720, "total_steps": 181800, "loss": 0.0368, "lr": 3.623327514564021e-05, "epoch": 8.33003300330033, "percentage": 41.65, "elapsed_time": "2:59:05", "remaining_time": "4:10:54", "throughput": 1487.04, "total_tokens": 15979632} {"current_steps": 75725, "total_steps": 181800, "loss": 0.0533, "lr": 3.623113095653341e-05, "epoch": 8.33058305830583, "percentage": 41.65, "elapsed_time": "2:59:06", "remaining_time": "4:10:53", "throughput": 1487.04, "total_tokens": 15980624} {"current_steps": 75730, "total_steps": 181800, "loss": 0.0027, "lr": 3.622898666391468e-05, "epoch": 8.331133113311331, "percentage": 41.66, "elapsed_time": "2:59:07", "remaining_time": "4:10:53", "throughput": 1487.04, "total_tokens": 15981648} {"current_steps": 75735, "total_steps": 181800, "loss": 0.0061, "lr": 3.6226842267803756e-05, "epoch": 8.331683168316832, "percentage": 41.66, "elapsed_time": "2:59:07", "remaining_time": "4:10:52", "throughput": 1487.04, "total_tokens": 15982672} {"current_steps": 75740, "total_steps": 181800, "loss": 0.0132, "lr": 3.622469776822041e-05, "epoch": 8.332233223322332, "percentage": 41.66, "elapsed_time": "2:59:08", "remaining_time": "4:10:51", "throughput": 1487.04, "total_tokens": 15983728} {"current_steps": 75745, "total_steps": 181800, "loss": 0.1165, "lr": 3.622255316518442e-05, "epoch": 8.332783278327833, "percentage": 41.66, "elapsed_time": "2:59:09", "remaining_time": "4:10:50", "throughput": 1487.04, "total_tokens": 15984752} {"current_steps": 75750, "total_steps": 181800, "loss": 0.0251, "lr": 3.622040845871554e-05, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "2:59:10", "remaining_time": "4:10:50", "throughput": 1487.05, "total_tokens": 15985840} {"current_steps": 75755, "total_steps": 181800, "loss": 0.0342, "lr": 3.621826364883354e-05, "epoch": 8.333883388338833, "percentage": 41.67, "elapsed_time": "2:59:10", "remaining_time": "4:10:49", "throughput": 1487.05, "total_tokens": 15986928} {"current_steps": 75760, "total_steps": 181800, "loss": 0.006, "lr": 3.621611873555818e-05, "epoch": 8.334433443344334, "percentage": 41.67, "elapsed_time": "2:59:11", "remaining_time": "4:10:48", "throughput": 1487.05, "total_tokens": 15987984} {"current_steps": 75765, "total_steps": 181800, "loss": 0.0639, "lr": 3.621397371890924e-05, "epoch": 8.334983498349835, "percentage": 41.67, "elapsed_time": "2:59:12", "remaining_time": "4:10:47", "throughput": 1487.06, "total_tokens": 15989040} {"current_steps": 75770, "total_steps": 181800, "loss": 0.0975, "lr": 3.621182859890649e-05, "epoch": 8.335533553355335, "percentage": 41.68, "elapsed_time": "2:59:12", "remaining_time": "4:10:47", "throughput": 1487.07, "total_tokens": 15990160} {"current_steps": 75775, "total_steps": 181800, "loss": 0.0335, "lr": 3.62096833755697e-05, "epoch": 8.336083608360836, "percentage": 41.68, "elapsed_time": "2:59:13", "remaining_time": "4:10:46", "throughput": 1487.07, "total_tokens": 15991216} {"current_steps": 75780, "total_steps": 181800, "loss": 0.0157, "lr": 3.6207538048918625e-05, "epoch": 8.336633663366337, "percentage": 41.68, "elapsed_time": "2:59:14", "remaining_time": "4:10:45", "throughput": 1487.07, "total_tokens": 15992272} {"current_steps": 75785, "total_steps": 181800, "loss": 0.0033, "lr": 3.620539261897305e-05, "epoch": 8.337183718371838, "percentage": 41.69, "elapsed_time": "2:59:14", "remaining_time": "4:10:44", "throughput": 1487.08, "total_tokens": 15993360} {"current_steps": 75790, "total_steps": 181800, "loss": 0.0285, "lr": 3.6203247085752756e-05, "epoch": 8.337733773377337, "percentage": 41.69, "elapsed_time": "2:59:15", "remaining_time": "4:10:44", "throughput": 1487.07, "total_tokens": 15994352} {"current_steps": 75795, "total_steps": 181800, "loss": 0.0527, "lr": 3.62011014492775e-05, "epoch": 8.338283828382838, "percentage": 41.69, "elapsed_time": "2:59:16", "remaining_time": "4:10:43", "throughput": 1487.07, "total_tokens": 15995376} {"current_steps": 75800, "total_steps": 181800, "loss": 0.0223, "lr": 3.6198955709567076e-05, "epoch": 8.33883388338834, "percentage": 41.69, "elapsed_time": "2:59:16", "remaining_time": "4:10:42", "throughput": 1487.07, "total_tokens": 15996336} {"current_steps": 75805, "total_steps": 181800, "loss": 0.0142, "lr": 3.619680986664125e-05, "epoch": 8.339383938393839, "percentage": 41.7, "elapsed_time": "2:59:17", "remaining_time": "4:10:41", "throughput": 1487.08, "total_tokens": 15997456} {"current_steps": 75810, "total_steps": 181800, "loss": 0.1331, "lr": 3.61946639205198e-05, "epoch": 8.33993399339934, "percentage": 41.7, "elapsed_time": "2:59:18", "remaining_time": "4:10:41", "throughput": 1487.08, "total_tokens": 15998544} {"current_steps": 75815, "total_steps": 181800, "loss": 0.0142, "lr": 3.6192517871222497e-05, "epoch": 8.340484048404841, "percentage": 41.7, "elapsed_time": "2:59:19", "remaining_time": "4:10:40", "throughput": 1487.09, "total_tokens": 15999664} {"current_steps": 75820, "total_steps": 181800, "loss": 0.1305, "lr": 3.619037171876913e-05, "epoch": 8.34103410341034, "percentage": 41.71, "elapsed_time": "2:59:19", "remaining_time": "4:10:39", "throughput": 1487.09, "total_tokens": 16000688} {"current_steps": 75825, "total_steps": 181800, "loss": 0.166, "lr": 3.6188225463179485e-05, "epoch": 8.341584158415841, "percentage": 41.71, "elapsed_time": "2:59:20", "remaining_time": "4:10:39", "throughput": 1487.09, "total_tokens": 16001712} {"current_steps": 75830, "total_steps": 181800, "loss": 0.0283, "lr": 3.6186079104473327e-05, "epoch": 8.342134213421343, "percentage": 41.71, "elapsed_time": "2:59:21", "remaining_time": "4:10:38", "throughput": 1487.1, "total_tokens": 16002832} {"current_steps": 75835, "total_steps": 181800, "loss": 0.0103, "lr": 3.618393264267045e-05, "epoch": 8.342684268426842, "percentage": 41.71, "elapsed_time": "2:59:21", "remaining_time": "4:10:37", "throughput": 1487.1, "total_tokens": 16003920} {"current_steps": 75840, "total_steps": 181800, "loss": 0.0078, "lr": 3.618178607779062e-05, "epoch": 8.343234323432343, "percentage": 41.72, "elapsed_time": "2:59:22", "remaining_time": "4:10:36", "throughput": 1487.1, "total_tokens": 16004944} {"current_steps": 75845, "total_steps": 181800, "loss": 0.043, "lr": 3.617963940985365e-05, "epoch": 8.343784378437844, "percentage": 41.72, "elapsed_time": "2:59:23", "remaining_time": "4:10:36", "throughput": 1487.1, "total_tokens": 16005968} {"current_steps": 75850, "total_steps": 181800, "loss": 0.1195, "lr": 3.61774926388793e-05, "epoch": 8.344334433443345, "percentage": 41.72, "elapsed_time": "2:59:23", "remaining_time": "4:10:35", "throughput": 1487.11, "total_tokens": 16007088} {"current_steps": 75855, "total_steps": 181800, "loss": 0.0091, "lr": 3.6175345764887355e-05, "epoch": 8.344884488448844, "percentage": 41.72, "elapsed_time": "2:59:24", "remaining_time": "4:10:34", "throughput": 1487.12, "total_tokens": 16008176} {"current_steps": 75860, "total_steps": 181800, "loss": 0.0429, "lr": 3.617319878789763e-05, "epoch": 8.345434543454346, "percentage": 41.73, "elapsed_time": "2:59:25", "remaining_time": "4:10:33", "throughput": 1487.11, "total_tokens": 16009168} {"current_steps": 75865, "total_steps": 181800, "loss": 0.032, "lr": 3.617105170792988e-05, "epoch": 8.345984598459847, "percentage": 41.73, "elapsed_time": "2:59:25", "remaining_time": "4:10:33", "throughput": 1487.11, "total_tokens": 16010160} {"current_steps": 75870, "total_steps": 181800, "loss": 0.0116, "lr": 3.616890452500391e-05, "epoch": 8.346534653465346, "percentage": 41.73, "elapsed_time": "2:59:26", "remaining_time": "4:10:32", "throughput": 1487.11, "total_tokens": 16011216} {"current_steps": 75875, "total_steps": 181800, "loss": 0.1489, "lr": 3.616675723913951e-05, "epoch": 8.347084708470847, "percentage": 41.74, "elapsed_time": "2:59:27", "remaining_time": "4:10:31", "throughput": 1487.12, "total_tokens": 16012272} {"current_steps": 75880, "total_steps": 181800, "loss": 0.0379, "lr": 3.616460985035646e-05, "epoch": 8.347634763476348, "percentage": 41.74, "elapsed_time": "2:59:28", "remaining_time": "4:10:30", "throughput": 1487.12, "total_tokens": 16013360} {"current_steps": 75885, "total_steps": 181800, "loss": 0.0356, "lr": 3.616246235867456e-05, "epoch": 8.348184818481847, "percentage": 41.74, "elapsed_time": "2:59:28", "remaining_time": "4:10:30", "throughput": 1487.13, "total_tokens": 16014448} {"current_steps": 75890, "total_steps": 181800, "loss": 0.0113, "lr": 3.6160314764113604e-05, "epoch": 8.348734873487349, "percentage": 41.74, "elapsed_time": "2:59:29", "remaining_time": "4:10:29", "throughput": 1487.13, "total_tokens": 16015472} {"current_steps": 75895, "total_steps": 181800, "loss": 0.0301, "lr": 3.615816706669338e-05, "epoch": 8.34928492849285, "percentage": 41.75, "elapsed_time": "2:59:30", "remaining_time": "4:10:28", "throughput": 1487.13, "total_tokens": 16016528} {"current_steps": 75900, "total_steps": 181800, "loss": 0.067, "lr": 3.615601926643368e-05, "epoch": 8.34983498349835, "percentage": 41.75, "elapsed_time": "2:59:30", "remaining_time": "4:10:28", "throughput": 1487.13, "total_tokens": 16017520} {"current_steps": 75905, "total_steps": 181800, "loss": 0.1004, "lr": 3.615387136335431e-05, "epoch": 8.35038503850385, "percentage": 41.75, "elapsed_time": "2:59:31", "remaining_time": "4:10:27", "throughput": 1487.13, "total_tokens": 16018608} {"current_steps": 75910, "total_steps": 181800, "loss": 0.0167, "lr": 3.615172335747507e-05, "epoch": 8.350935093509351, "percentage": 41.75, "elapsed_time": "2:59:32", "remaining_time": "4:10:26", "throughput": 1487.13, "total_tokens": 16019632} {"current_steps": 75915, "total_steps": 181800, "loss": 0.0838, "lr": 3.614957524881573e-05, "epoch": 8.351485148514852, "percentage": 41.76, "elapsed_time": "2:59:32", "remaining_time": "4:10:25", "throughput": 1487.14, "total_tokens": 16020720} {"current_steps": 75920, "total_steps": 181800, "loss": 0.0033, "lr": 3.614742703739611e-05, "epoch": 8.352035203520352, "percentage": 41.76, "elapsed_time": "2:59:33", "remaining_time": "4:10:25", "throughput": 1487.14, "total_tokens": 16021808} {"current_steps": 75925, "total_steps": 181800, "loss": 0.1292, "lr": 3.6145278723236006e-05, "epoch": 8.352585258525853, "percentage": 41.76, "elapsed_time": "2:59:34", "remaining_time": "4:10:24", "throughput": 1487.15, "total_tokens": 16022864} {"current_steps": 75930, "total_steps": 181800, "loss": 0.0086, "lr": 3.6143130306355213e-05, "epoch": 8.353135313531354, "percentage": 41.77, "elapsed_time": "2:59:34", "remaining_time": "4:10:23", "throughput": 1487.16, "total_tokens": 16024048} {"current_steps": 75935, "total_steps": 181800, "loss": 0.0743, "lr": 3.614098178677353e-05, "epoch": 8.353685368536853, "percentage": 41.77, "elapsed_time": "2:59:35", "remaining_time": "4:10:22", "throughput": 1487.16, "total_tokens": 16025072} {"current_steps": 75940, "total_steps": 181800, "loss": 0.0587, "lr": 3.613883316451077e-05, "epoch": 8.354235423542354, "percentage": 41.77, "elapsed_time": "2:59:36", "remaining_time": "4:10:22", "throughput": 1487.16, "total_tokens": 16026128} {"current_steps": 75945, "total_steps": 181800, "loss": 0.0248, "lr": 3.6136684439586734e-05, "epoch": 8.354785478547855, "percentage": 41.77, "elapsed_time": "2:59:36", "remaining_time": "4:10:21", "throughput": 1487.17, "total_tokens": 16027216} {"current_steps": 75950, "total_steps": 181800, "loss": 0.0744, "lr": 3.613453561202122e-05, "epoch": 8.355335533553355, "percentage": 41.78, "elapsed_time": "2:59:37", "remaining_time": "4:10:20", "throughput": 1487.17, "total_tokens": 16028304} {"current_steps": 75955, "total_steps": 181800, "loss": 0.0194, "lr": 3.613238668183403e-05, "epoch": 8.355885588558856, "percentage": 41.78, "elapsed_time": "2:59:38", "remaining_time": "4:10:19", "throughput": 1487.18, "total_tokens": 16029328} {"current_steps": 75960, "total_steps": 181800, "loss": 0.0156, "lr": 3.613023764904497e-05, "epoch": 8.356435643564357, "percentage": 41.78, "elapsed_time": "2:59:39", "remaining_time": "4:10:19", "throughput": 1487.18, "total_tokens": 16030352} {"current_steps": 75965, "total_steps": 181800, "loss": 0.0646, "lr": 3.6128088513673865e-05, "epoch": 8.356985698569858, "percentage": 41.78, "elapsed_time": "2:59:39", "remaining_time": "4:10:18", "throughput": 1487.18, "total_tokens": 16031408} {"current_steps": 75970, "total_steps": 181800, "loss": 0.0405, "lr": 3.612593927574049e-05, "epoch": 8.357535753575357, "percentage": 41.79, "elapsed_time": "2:59:40", "remaining_time": "4:10:17", "throughput": 1487.18, "total_tokens": 16032432} {"current_steps": 75975, "total_steps": 181800, "loss": 0.0232, "lr": 3.612378993526468e-05, "epoch": 8.358085808580858, "percentage": 41.79, "elapsed_time": "2:59:41", "remaining_time": "4:10:16", "throughput": 1487.18, "total_tokens": 16033488} {"current_steps": 75980, "total_steps": 181800, "loss": 0.0059, "lr": 3.6121640492266234e-05, "epoch": 8.35863586358636, "percentage": 41.79, "elapsed_time": "2:59:41", "remaining_time": "4:10:16", "throughput": 1487.18, "total_tokens": 16034544} {"current_steps": 75985, "total_steps": 181800, "loss": 0.0259, "lr": 3.611949094676497e-05, "epoch": 8.359185918591859, "percentage": 41.8, "elapsed_time": "2:59:42", "remaining_time": "4:10:15", "throughput": 1487.18, "total_tokens": 16035504} {"current_steps": 75990, "total_steps": 181800, "loss": 0.0646, "lr": 3.611734129878069e-05, "epoch": 8.35973597359736, "percentage": 41.8, "elapsed_time": "2:59:43", "remaining_time": "4:10:14", "throughput": 1487.18, "total_tokens": 16036592} {"current_steps": 75995, "total_steps": 181800, "loss": 0.0874, "lr": 3.611519154833321e-05, "epoch": 8.36028602860286, "percentage": 41.8, "elapsed_time": "2:59:43", "remaining_time": "4:10:14", "throughput": 1487.18, "total_tokens": 16037584} {"current_steps": 76000, "total_steps": 181800, "loss": 0.0923, "lr": 3.611304169544234e-05, "epoch": 8.36083608360836, "percentage": 41.8, "elapsed_time": "2:59:44", "remaining_time": "4:10:13", "throughput": 1487.18, "total_tokens": 16038672} {"current_steps": 76005, "total_steps": 181800, "loss": 0.0339, "lr": 3.611089174012789e-05, "epoch": 8.361386138613861, "percentage": 41.81, "elapsed_time": "2:59:45", "remaining_time": "4:10:12", "throughput": 1487.18, "total_tokens": 16039696} {"current_steps": 76010, "total_steps": 181800, "loss": 0.023, "lr": 3.6108741682409696e-05, "epoch": 8.361936193619362, "percentage": 41.81, "elapsed_time": "2:59:45", "remaining_time": "4:10:11", "throughput": 1487.18, "total_tokens": 16040688} {"current_steps": 76015, "total_steps": 181800, "loss": 0.0846, "lr": 3.6106591522307566e-05, "epoch": 8.362486248624862, "percentage": 41.81, "elapsed_time": "2:59:46", "remaining_time": "4:10:11", "throughput": 1487.18, "total_tokens": 16041712} {"current_steps": 76020, "total_steps": 181800, "loss": 0.0314, "lr": 3.61044412598413e-05, "epoch": 8.363036303630363, "percentage": 41.82, "elapsed_time": "2:59:47", "remaining_time": "4:10:10", "throughput": 1487.18, "total_tokens": 16042704} {"current_steps": 76025, "total_steps": 181800, "loss": 0.0103, "lr": 3.610229089503073e-05, "epoch": 8.363586358635864, "percentage": 41.82, "elapsed_time": "2:59:48", "remaining_time": "4:10:09", "throughput": 1487.18, "total_tokens": 16043792} {"current_steps": 76030, "total_steps": 181800, "loss": 0.1051, "lr": 3.610014042789567e-05, "epoch": 8.364136413641365, "percentage": 41.82, "elapsed_time": "2:59:48", "remaining_time": "4:10:08", "throughput": 1487.19, "total_tokens": 16044848} {"current_steps": 76035, "total_steps": 181800, "loss": 0.0171, "lr": 3.609798985845594e-05, "epoch": 8.364686468646864, "percentage": 41.82, "elapsed_time": "2:59:49", "remaining_time": "4:10:08", "throughput": 1487.19, "total_tokens": 16045904} {"current_steps": 76040, "total_steps": 181800, "loss": 0.007, "lr": 3.6095839186731375e-05, "epoch": 8.365236523652365, "percentage": 41.83, "elapsed_time": "2:59:50", "remaining_time": "4:10:07", "throughput": 1487.2, "total_tokens": 16046992} {"current_steps": 76045, "total_steps": 181800, "loss": 0.022, "lr": 3.6093688412741764e-05, "epoch": 8.365786578657866, "percentage": 41.83, "elapsed_time": "2:59:50", "remaining_time": "4:10:06", "throughput": 1487.2, "total_tokens": 16048016} {"current_steps": 76050, "total_steps": 181800, "loss": 0.0104, "lr": 3.609153753650696e-05, "epoch": 8.366336633663366, "percentage": 41.83, "elapsed_time": "2:59:51", "remaining_time": "4:10:05", "throughput": 1487.2, "total_tokens": 16049104} {"current_steps": 76055, "total_steps": 181800, "loss": 0.0528, "lr": 3.608938655804678e-05, "epoch": 8.366886688668867, "percentage": 41.83, "elapsed_time": "2:59:52", "remaining_time": "4:10:05", "throughput": 1487.21, "total_tokens": 16050160} {"current_steps": 76060, "total_steps": 181800, "loss": 0.035, "lr": 3.6087235477381045e-05, "epoch": 8.367436743674368, "percentage": 41.84, "elapsed_time": "2:59:52", "remaining_time": "4:10:04", "throughput": 1487.2, "total_tokens": 16051152} {"current_steps": 76065, "total_steps": 181800, "loss": 0.0137, "lr": 3.6085084294529586e-05, "epoch": 8.367986798679867, "percentage": 41.84, "elapsed_time": "2:59:53", "remaining_time": "4:10:03", "throughput": 1487.21, "total_tokens": 16052272} {"current_steps": 76070, "total_steps": 181800, "loss": 0.0141, "lr": 3.6082933009512224e-05, "epoch": 8.368536853685368, "percentage": 41.84, "elapsed_time": "2:59:54", "remaining_time": "4:10:02", "throughput": 1487.21, "total_tokens": 16053264} {"current_steps": 76075, "total_steps": 181800, "loss": 0.0756, "lr": 3.608078162234877e-05, "epoch": 8.36908690869087, "percentage": 41.85, "elapsed_time": "2:59:54", "remaining_time": "4:10:02", "throughput": 1487.21, "total_tokens": 16054288} {"current_steps": 76080, "total_steps": 181800, "loss": 0.011, "lr": 3.6078630133059083e-05, "epoch": 8.369636963696369, "percentage": 41.85, "elapsed_time": "2:59:55", "remaining_time": "4:10:01", "throughput": 1487.22, "total_tokens": 16055408} {"current_steps": 76085, "total_steps": 181800, "loss": 0.0394, "lr": 3.607647854166297e-05, "epoch": 8.37018701870187, "percentage": 41.85, "elapsed_time": "2:59:56", "remaining_time": "4:10:00", "throughput": 1487.22, "total_tokens": 16056464} {"current_steps": 76090, "total_steps": 181800, "loss": 0.0097, "lr": 3.6074326848180276e-05, "epoch": 8.370737073707371, "percentage": 41.85, "elapsed_time": "2:59:56", "remaining_time": "4:09:59", "throughput": 1487.22, "total_tokens": 16057520} {"current_steps": 76095, "total_steps": 181800, "loss": 0.0273, "lr": 3.607217505263083e-05, "epoch": 8.371287128712872, "percentage": 41.86, "elapsed_time": "2:59:57", "remaining_time": "4:09:59", "throughput": 1487.22, "total_tokens": 16058544} {"current_steps": 76100, "total_steps": 181800, "loss": 0.0037, "lr": 3.607002315503445e-05, "epoch": 8.371837183718371, "percentage": 41.86, "elapsed_time": "2:59:58", "remaining_time": "4:09:58", "throughput": 1487.22, "total_tokens": 16059568} {"current_steps": 76105, "total_steps": 181800, "loss": 0.0607, "lr": 3.606787115541098e-05, "epoch": 8.372387238723872, "percentage": 41.86, "elapsed_time": "2:59:59", "remaining_time": "4:09:57", "throughput": 1487.22, "total_tokens": 16060560} {"current_steps": 76110, "total_steps": 181800, "loss": 0.0265, "lr": 3.606571905378026e-05, "epoch": 8.372937293729374, "percentage": 41.86, "elapsed_time": "2:59:59", "remaining_time": "4:09:57", "throughput": 1487.22, "total_tokens": 16061584} {"current_steps": 76115, "total_steps": 181800, "loss": 0.0024, "lr": 3.60635668501621e-05, "epoch": 8.373487348734873, "percentage": 41.87, "elapsed_time": "3:00:00", "remaining_time": "4:09:56", "throughput": 1487.23, "total_tokens": 16062672} {"current_steps": 76120, "total_steps": 181800, "loss": 0.0105, "lr": 3.6061414544576366e-05, "epoch": 8.374037403740374, "percentage": 41.87, "elapsed_time": "3:00:01", "remaining_time": "4:09:55", "throughput": 1487.23, "total_tokens": 16063696} {"current_steps": 76125, "total_steps": 181800, "loss": 0.0214, "lr": 3.605926213704288e-05, "epoch": 8.374587458745875, "percentage": 41.87, "elapsed_time": "3:00:01", "remaining_time": "4:09:54", "throughput": 1487.23, "total_tokens": 16064752} {"current_steps": 76130, "total_steps": 181800, "loss": 0.0018, "lr": 3.605710962758148e-05, "epoch": 8.375137513751374, "percentage": 41.88, "elapsed_time": "3:00:02", "remaining_time": "4:09:54", "throughput": 1487.24, "total_tokens": 16065872} {"current_steps": 76135, "total_steps": 181800, "loss": 0.1376, "lr": 3.605495701621201e-05, "epoch": 8.375687568756875, "percentage": 41.88, "elapsed_time": "3:00:03", "remaining_time": "4:09:53", "throughput": 1487.24, "total_tokens": 16066928} {"current_steps": 76140, "total_steps": 181800, "loss": 0.0723, "lr": 3.605280430295431e-05, "epoch": 8.376237623762377, "percentage": 41.88, "elapsed_time": "3:00:03", "remaining_time": "4:09:52", "throughput": 1487.24, "total_tokens": 16067952} {"current_steps": 76145, "total_steps": 181800, "loss": 0.0484, "lr": 3.6050651487828205e-05, "epoch": 8.376787678767876, "percentage": 41.88, "elapsed_time": "3:00:04", "remaining_time": "4:09:51", "throughput": 1487.24, "total_tokens": 16068976} {"current_steps": 76150, "total_steps": 181800, "loss": 0.0393, "lr": 3.604849857085355e-05, "epoch": 8.377337733773377, "percentage": 41.89, "elapsed_time": "3:00:05", "remaining_time": "4:09:51", "throughput": 1487.24, "total_tokens": 16070000} {"current_steps": 76155, "total_steps": 181800, "loss": 0.1241, "lr": 3.60463455520502e-05, "epoch": 8.377887788778878, "percentage": 41.89, "elapsed_time": "3:00:05", "remaining_time": "4:09:50", "throughput": 1487.24, "total_tokens": 16071056} {"current_steps": 76160, "total_steps": 181800, "loss": 0.1072, "lr": 3.604419243143796e-05, "epoch": 8.37843784378438, "percentage": 41.89, "elapsed_time": "3:00:06", "remaining_time": "4:09:49", "throughput": 1487.25, "total_tokens": 16072144} {"current_steps": 76165, "total_steps": 181800, "loss": 0.1001, "lr": 3.604203920903672e-05, "epoch": 8.378987898789878, "percentage": 41.89, "elapsed_time": "3:00:07", "remaining_time": "4:09:48", "throughput": 1487.26, "total_tokens": 16073264} {"current_steps": 76170, "total_steps": 181800, "loss": 0.0247, "lr": 3.603988588486629e-05, "epoch": 8.37953795379538, "percentage": 41.9, "elapsed_time": "3:00:08", "remaining_time": "4:09:48", "throughput": 1487.26, "total_tokens": 16074288} {"current_steps": 76175, "total_steps": 181800, "loss": 0.0259, "lr": 3.603773245894653e-05, "epoch": 8.38008800880088, "percentage": 41.9, "elapsed_time": "3:00:08", "remaining_time": "4:09:47", "throughput": 1487.25, "total_tokens": 16075280} {"current_steps": 76180, "total_steps": 181800, "loss": 0.0744, "lr": 3.603557893129729e-05, "epoch": 8.38063806380638, "percentage": 41.9, "elapsed_time": "3:00:09", "remaining_time": "4:09:46", "throughput": 1487.26, "total_tokens": 16076368} {"current_steps": 76185, "total_steps": 181800, "loss": 0.0128, "lr": 3.6033425301938414e-05, "epoch": 8.381188118811881, "percentage": 41.91, "elapsed_time": "3:00:10", "remaining_time": "4:09:45", "throughput": 1487.26, "total_tokens": 16077360} {"current_steps": 76190, "total_steps": 181800, "loss": 0.0131, "lr": 3.6031271570889746e-05, "epoch": 8.381738173817382, "percentage": 41.91, "elapsed_time": "3:00:10", "remaining_time": "4:09:45", "throughput": 1487.25, "total_tokens": 16078352} {"current_steps": 76195, "total_steps": 181800, "loss": 0.0032, "lr": 3.6029117738171145e-05, "epoch": 8.382288228822881, "percentage": 41.91, "elapsed_time": "3:00:11", "remaining_time": "4:09:44", "throughput": 1487.25, "total_tokens": 16079376} {"current_steps": 76200, "total_steps": 181800, "loss": 0.0849, "lr": 3.602696380380246e-05, "epoch": 8.382838283828383, "percentage": 41.91, "elapsed_time": "3:00:12", "remaining_time": "4:09:43", "throughput": 1487.25, "total_tokens": 16080400} {"current_steps": 76205, "total_steps": 181800, "loss": 0.0292, "lr": 3.602480976780354e-05, "epoch": 8.383388338833884, "percentage": 41.92, "elapsed_time": "3:00:12", "remaining_time": "4:09:43", "throughput": 1487.25, "total_tokens": 16081424} {"current_steps": 76210, "total_steps": 181800, "loss": 0.0236, "lr": 3.6022655630194234e-05, "epoch": 8.383938393839385, "percentage": 41.92, "elapsed_time": "3:00:13", "remaining_time": "4:09:42", "throughput": 1487.25, "total_tokens": 16082416} {"current_steps": 76215, "total_steps": 181800, "loss": 0.0671, "lr": 3.602050139099441e-05, "epoch": 8.384488448844884, "percentage": 41.92, "elapsed_time": "3:00:14", "remaining_time": "4:09:41", "throughput": 1487.25, "total_tokens": 16083408} {"current_steps": 76220, "total_steps": 181800, "loss": 0.0375, "lr": 3.60183470502239e-05, "epoch": 8.385038503850385, "percentage": 41.93, "elapsed_time": "3:00:14", "remaining_time": "4:09:40", "throughput": 1487.25, "total_tokens": 16084464} {"current_steps": 76225, "total_steps": 181800, "loss": 0.0465, "lr": 3.6016192607902584e-05, "epoch": 8.385588558855886, "percentage": 41.93, "elapsed_time": "3:00:15", "remaining_time": "4:09:40", "throughput": 1487.25, "total_tokens": 16085456} {"current_steps": 76230, "total_steps": 181800, "loss": 0.0928, "lr": 3.60140380640503e-05, "epoch": 8.386138613861386, "percentage": 41.93, "elapsed_time": "3:00:16", "remaining_time": "4:09:39", "throughput": 1487.26, "total_tokens": 16086576} {"current_steps": 76235, "total_steps": 181800, "loss": 0.0693, "lr": 3.6011883418686915e-05, "epoch": 8.386688668866887, "percentage": 41.93, "elapsed_time": "3:00:16", "remaining_time": "4:09:38", "throughput": 1487.26, "total_tokens": 16087664} {"current_steps": 76240, "total_steps": 181800, "loss": 0.1563, "lr": 3.6009728671832285e-05, "epoch": 8.387238723872388, "percentage": 41.94, "elapsed_time": "3:00:17", "remaining_time": "4:09:37", "throughput": 1487.26, "total_tokens": 16088656} {"current_steps": 76245, "total_steps": 181800, "loss": 0.0893, "lr": 3.600757382350627e-05, "epoch": 8.387788778877887, "percentage": 41.94, "elapsed_time": "3:00:18", "remaining_time": "4:09:37", "throughput": 1487.26, "total_tokens": 16089744} {"current_steps": 76250, "total_steps": 181800, "loss": 0.0052, "lr": 3.6005418873728724e-05, "epoch": 8.388338833883388, "percentage": 41.94, "elapsed_time": "3:00:19", "remaining_time": "4:09:36", "throughput": 1487.27, "total_tokens": 16090864} {"current_steps": 76255, "total_steps": 181800, "loss": 0.0196, "lr": 3.6003263822519516e-05, "epoch": 8.38888888888889, "percentage": 41.94, "elapsed_time": "3:00:19", "remaining_time": "4:09:35", "throughput": 1487.28, "total_tokens": 16091952} {"current_steps": 76260, "total_steps": 181800, "loss": 0.0708, "lr": 3.600110866989851e-05, "epoch": 8.389438943894389, "percentage": 41.95, "elapsed_time": "3:00:20", "remaining_time": "4:09:34", "throughput": 1487.28, "total_tokens": 16093008} {"current_steps": 76265, "total_steps": 181800, "loss": 0.0182, "lr": 3.599895341588556e-05, "epoch": 8.38998899889989, "percentage": 41.95, "elapsed_time": "3:00:21", "remaining_time": "4:09:34", "throughput": 1487.28, "total_tokens": 16094064} {"current_steps": 76270, "total_steps": 181800, "loss": 0.0151, "lr": 3.599679806050052e-05, "epoch": 8.39053905390539, "percentage": 41.95, "elapsed_time": "3:00:21", "remaining_time": "4:09:33", "throughput": 1487.29, "total_tokens": 16095120} {"current_steps": 76275, "total_steps": 181800, "loss": 0.04, "lr": 3.599464260376329e-05, "epoch": 8.391089108910892, "percentage": 41.96, "elapsed_time": "3:00:22", "remaining_time": "4:09:32", "throughput": 1487.29, "total_tokens": 16096176} {"current_steps": 76280, "total_steps": 181800, "loss": 0.0406, "lr": 3.599248704569371e-05, "epoch": 8.391639163916391, "percentage": 41.96, "elapsed_time": "3:00:23", "remaining_time": "4:09:31", "throughput": 1487.29, "total_tokens": 16097232} {"current_steps": 76285, "total_steps": 181800, "loss": 0.0593, "lr": 3.599033138631165e-05, "epoch": 8.392189218921892, "percentage": 41.96, "elapsed_time": "3:00:23", "remaining_time": "4:09:31", "throughput": 1487.29, "total_tokens": 16098288} {"current_steps": 76290, "total_steps": 181800, "loss": 0.0017, "lr": 3.598817562563698e-05, "epoch": 8.392739273927393, "percentage": 41.96, "elapsed_time": "3:00:24", "remaining_time": "4:09:30", "throughput": 1487.3, "total_tokens": 16099376} {"current_steps": 76295, "total_steps": 181800, "loss": 0.1735, "lr": 3.598601976368956e-05, "epoch": 8.393289328932893, "percentage": 41.97, "elapsed_time": "3:00:25", "remaining_time": "4:09:29", "throughput": 1487.3, "total_tokens": 16100432} {"current_steps": 76300, "total_steps": 181800, "loss": 0.0141, "lr": 3.5983863800489285e-05, "epoch": 8.393839383938394, "percentage": 41.97, "elapsed_time": "3:00:25", "remaining_time": "4:09:29", "throughput": 1487.31, "total_tokens": 16101584} {"current_steps": 76305, "total_steps": 181800, "loss": 0.0143, "lr": 3.5981707736055985e-05, "epoch": 8.394389438943895, "percentage": 41.97, "elapsed_time": "3:00:26", "remaining_time": "4:09:28", "throughput": 1487.31, "total_tokens": 16102608} {"current_steps": 76310, "total_steps": 181800, "loss": 0.0215, "lr": 3.597955157040957e-05, "epoch": 8.394939493949394, "percentage": 41.97, "elapsed_time": "3:00:27", "remaining_time": "4:09:27", "throughput": 1487.32, "total_tokens": 16103728} {"current_steps": 76315, "total_steps": 181800, "loss": 0.0132, "lr": 3.597739530356989e-05, "epoch": 8.395489548954895, "percentage": 41.98, "elapsed_time": "3:00:28", "remaining_time": "4:09:26", "throughput": 1487.32, "total_tokens": 16104752} {"current_steps": 76320, "total_steps": 181800, "loss": 0.0435, "lr": 3.597523893555683e-05, "epoch": 8.396039603960396, "percentage": 41.98, "elapsed_time": "3:00:28", "remaining_time": "4:09:26", "throughput": 1487.32, "total_tokens": 16105808} {"current_steps": 76325, "total_steps": 181800, "loss": 0.0633, "lr": 3.597308246639026e-05, "epoch": 8.396589658965897, "percentage": 41.98, "elapsed_time": "3:00:29", "remaining_time": "4:09:25", "throughput": 1487.33, "total_tokens": 16106896} {"current_steps": 76330, "total_steps": 181800, "loss": 0.043, "lr": 3.597092589609005e-05, "epoch": 8.397139713971397, "percentage": 41.99, "elapsed_time": "3:00:30", "remaining_time": "4:09:24", "throughput": 1487.33, "total_tokens": 16107984} {"current_steps": 76335, "total_steps": 181800, "loss": 0.0534, "lr": 3.596876922467608e-05, "epoch": 8.397689768976898, "percentage": 41.99, "elapsed_time": "3:00:30", "remaining_time": "4:09:23", "throughput": 1487.34, "total_tokens": 16109040} {"current_steps": 76340, "total_steps": 181800, "loss": 0.0337, "lr": 3.5966612452168225e-05, "epoch": 8.398239823982399, "percentage": 41.99, "elapsed_time": "3:00:31", "remaining_time": "4:09:23", "throughput": 1487.34, "total_tokens": 16110160} {"current_steps": 76345, "total_steps": 181800, "loss": 0.0224, "lr": 3.5964455578586374e-05, "epoch": 8.398789878987898, "percentage": 41.99, "elapsed_time": "3:00:32", "remaining_time": "4:09:22", "throughput": 1487.35, "total_tokens": 16111280} {"current_steps": 76350, "total_steps": 181800, "loss": 0.0131, "lr": 3.5962298603950396e-05, "epoch": 8.3993399339934, "percentage": 42.0, "elapsed_time": "3:00:32", "remaining_time": "4:09:21", "throughput": 1487.36, "total_tokens": 16112368} {"current_steps": 76355, "total_steps": 181800, "loss": 0.0098, "lr": 3.5960141528280165e-05, "epoch": 8.3998899889989, "percentage": 42.0, "elapsed_time": "3:00:33", "remaining_time": "4:09:20", "throughput": 1487.36, "total_tokens": 16113392} {"current_steps": 76360, "total_steps": 181800, "loss": 0.006, "lr": 3.595798435159558e-05, "epoch": 8.4004400440044, "percentage": 42.0, "elapsed_time": "3:00:34", "remaining_time": "4:09:20", "throughput": 1487.37, "total_tokens": 16114512} {"current_steps": 76365, "total_steps": 181800, "loss": 0.0878, "lr": 3.595582707391649e-05, "epoch": 8.400990099009901, "percentage": 42.0, "elapsed_time": "3:00:34", "remaining_time": "4:09:19", "throughput": 1487.37, "total_tokens": 16115600} {"current_steps": 76370, "total_steps": 181800, "loss": 0.0222, "lr": 3.595366969526282e-05, "epoch": 8.401540154015402, "percentage": 42.01, "elapsed_time": "3:00:35", "remaining_time": "4:09:18", "throughput": 1487.38, "total_tokens": 16116688} {"current_steps": 76375, "total_steps": 181800, "loss": 0.0361, "lr": 3.595151221565443e-05, "epoch": 8.402090209020901, "percentage": 42.01, "elapsed_time": "3:00:36", "remaining_time": "4:09:18", "throughput": 1487.37, "total_tokens": 16117680} {"current_steps": 76380, "total_steps": 181800, "loss": 0.0207, "lr": 3.594935463511119e-05, "epoch": 8.402640264026402, "percentage": 42.01, "elapsed_time": "3:00:37", "remaining_time": "4:09:17", "throughput": 1487.38, "total_tokens": 16118736} {"current_steps": 76385, "total_steps": 181800, "loss": 0.0194, "lr": 3.594719695365302e-05, "epoch": 8.403190319031903, "percentage": 42.02, "elapsed_time": "3:00:37", "remaining_time": "4:09:16", "throughput": 1487.38, "total_tokens": 16119792} {"current_steps": 76390, "total_steps": 181800, "loss": 0.0377, "lr": 3.5945039171299785e-05, "epoch": 8.403740374037405, "percentage": 42.02, "elapsed_time": "3:00:38", "remaining_time": "4:09:15", "throughput": 1487.38, "total_tokens": 16120848} {"current_steps": 76395, "total_steps": 181800, "loss": 0.0089, "lr": 3.594288128807137e-05, "epoch": 8.404290429042904, "percentage": 42.02, "elapsed_time": "3:00:39", "remaining_time": "4:09:15", "throughput": 1487.39, "total_tokens": 16121904} {"current_steps": 76400, "total_steps": 181800, "loss": 0.0288, "lr": 3.594072330398768e-05, "epoch": 8.404840484048405, "percentage": 42.02, "elapsed_time": "3:00:39", "remaining_time": "4:09:14", "throughput": 1487.38, "total_tokens": 16122864} {"current_steps": 76405, "total_steps": 181800, "loss": 0.0108, "lr": 3.5938565219068585e-05, "epoch": 8.405390539053906, "percentage": 42.03, "elapsed_time": "3:00:40", "remaining_time": "4:09:13", "throughput": 1487.38, "total_tokens": 16123920} {"current_steps": 76410, "total_steps": 181800, "loss": 0.0224, "lr": 3.5936407033333975e-05, "epoch": 8.405940594059405, "percentage": 42.03, "elapsed_time": "3:00:41", "remaining_time": "4:09:12", "throughput": 1487.39, "total_tokens": 16125008} {"current_steps": 76415, "total_steps": 181800, "loss": 0.0106, "lr": 3.593424874680376e-05, "epoch": 8.406490649064907, "percentage": 42.03, "elapsed_time": "3:00:41", "remaining_time": "4:09:12", "throughput": 1487.39, "total_tokens": 16126064} {"current_steps": 76420, "total_steps": 181800, "loss": 0.0032, "lr": 3.593209035949782e-05, "epoch": 8.407040704070408, "percentage": 42.04, "elapsed_time": "3:00:42", "remaining_time": "4:09:11", "throughput": 1487.39, "total_tokens": 16127088} {"current_steps": 76425, "total_steps": 181800, "loss": 0.0964, "lr": 3.592993187143605e-05, "epoch": 8.407590759075907, "percentage": 42.04, "elapsed_time": "3:00:43", "remaining_time": "4:09:10", "throughput": 1487.39, "total_tokens": 16128144} {"current_steps": 76430, "total_steps": 181800, "loss": 0.0012, "lr": 3.5927773282638345e-05, "epoch": 8.408140814081408, "percentage": 42.04, "elapsed_time": "3:00:43", "remaining_time": "4:09:09", "throughput": 1487.4, "total_tokens": 16129296} {"current_steps": 76435, "total_steps": 181800, "loss": 0.0123, "lr": 3.592561459312459e-05, "epoch": 8.408690869086909, "percentage": 42.04, "elapsed_time": "3:00:44", "remaining_time": "4:09:09", "throughput": 1487.41, "total_tokens": 16130384} {"current_steps": 76440, "total_steps": 181800, "loss": 0.0234, "lr": 3.5923455802914694e-05, "epoch": 8.409240924092408, "percentage": 42.05, "elapsed_time": "3:00:45", "remaining_time": "4:09:08", "throughput": 1487.41, "total_tokens": 16131440} {"current_steps": 76445, "total_steps": 181800, "loss": 0.0471, "lr": 3.5921296912028543e-05, "epoch": 8.40979097909791, "percentage": 42.05, "elapsed_time": "3:00:45", "remaining_time": "4:09:07", "throughput": 1487.42, "total_tokens": 16132528} {"current_steps": 76450, "total_steps": 181800, "loss": 0.0667, "lr": 3.591913792048604e-05, "epoch": 8.41034103410341, "percentage": 42.05, "elapsed_time": "3:00:46", "remaining_time": "4:09:07", "throughput": 1487.42, "total_tokens": 16133584} {"current_steps": 76455, "total_steps": 181800, "loss": 0.0292, "lr": 3.5916978828307077e-05, "epoch": 8.410891089108912, "percentage": 42.05, "elapsed_time": "3:00:47", "remaining_time": "4:09:06", "throughput": 1487.43, "total_tokens": 16134672} {"current_steps": 76460, "total_steps": 181800, "loss": 0.0488, "lr": 3.591481963551157e-05, "epoch": 8.411441144114411, "percentage": 42.06, "elapsed_time": "3:00:48", "remaining_time": "4:09:05", "throughput": 1487.43, "total_tokens": 16135728} {"current_steps": 76465, "total_steps": 181800, "loss": 0.0131, "lr": 3.59126603421194e-05, "epoch": 8.411991199119912, "percentage": 42.06, "elapsed_time": "3:00:48", "remaining_time": "4:09:04", "throughput": 1487.44, "total_tokens": 16136816} {"current_steps": 76470, "total_steps": 181800, "loss": 0.0098, "lr": 3.591050094815048e-05, "epoch": 8.412541254125413, "percentage": 42.06, "elapsed_time": "3:00:49", "remaining_time": "4:09:04", "throughput": 1487.43, "total_tokens": 16137808} {"current_steps": 76475, "total_steps": 181800, "loss": 0.0047, "lr": 3.590834145362471e-05, "epoch": 8.413091309130913, "percentage": 42.07, "elapsed_time": "3:00:50", "remaining_time": "4:09:03", "throughput": 1487.43, "total_tokens": 16138832} {"current_steps": 76480, "total_steps": 181800, "loss": 0.0136, "lr": 3.590618185856198e-05, "epoch": 8.413641364136414, "percentage": 42.07, "elapsed_time": "3:00:50", "remaining_time": "4:09:02", "throughput": 1487.43, "total_tokens": 16139856} {"current_steps": 76485, "total_steps": 181800, "loss": 0.0093, "lr": 3.590402216298222e-05, "epoch": 8.414191419141915, "percentage": 42.07, "elapsed_time": "3:00:51", "remaining_time": "4:09:01", "throughput": 1487.43, "total_tokens": 16140880} {"current_steps": 76490, "total_steps": 181800, "loss": 0.0023, "lr": 3.5901862366905317e-05, "epoch": 8.414741474147414, "percentage": 42.07, "elapsed_time": "3:00:52", "remaining_time": "4:09:01", "throughput": 1487.43, "total_tokens": 16141872} {"current_steps": 76495, "total_steps": 181800, "loss": 0.0755, "lr": 3.589970247035117e-05, "epoch": 8.415291529152915, "percentage": 42.08, "elapsed_time": "3:00:52", "remaining_time": "4:09:00", "throughput": 1487.43, "total_tokens": 16142896} {"current_steps": 76500, "total_steps": 181800, "loss": 0.0058, "lr": 3.58975424733397e-05, "epoch": 8.415841584158416, "percentage": 42.08, "elapsed_time": "3:00:53", "remaining_time": "4:08:59", "throughput": 1487.43, "total_tokens": 16143952} {"current_steps": 76505, "total_steps": 181800, "loss": 0.0034, "lr": 3.589538237589081e-05, "epoch": 8.416391639163916, "percentage": 42.08, "elapsed_time": "3:00:54", "remaining_time": "4:08:58", "throughput": 1487.43, "total_tokens": 16145008} {"current_steps": 76510, "total_steps": 181800, "loss": 0.1263, "lr": 3.589322217802441e-05, "epoch": 8.416941694169417, "percentage": 42.08, "elapsed_time": "3:00:54", "remaining_time": "4:08:58", "throughput": 1487.44, "total_tokens": 16146096} {"current_steps": 76515, "total_steps": 181800, "loss": 0.0062, "lr": 3.5891061879760416e-05, "epoch": 8.417491749174918, "percentage": 42.09, "elapsed_time": "3:00:55", "remaining_time": "4:08:57", "throughput": 1487.44, "total_tokens": 16147120} {"current_steps": 76520, "total_steps": 181800, "loss": 0.0074, "lr": 3.588890148111872e-05, "epoch": 8.418041804180419, "percentage": 42.09, "elapsed_time": "3:00:56", "remaining_time": "4:08:56", "throughput": 1487.44, "total_tokens": 16148176} {"current_steps": 76525, "total_steps": 181800, "loss": 0.0056, "lr": 3.5886740982119245e-05, "epoch": 8.418591859185918, "percentage": 42.09, "elapsed_time": "3:00:57", "remaining_time": "4:08:55", "throughput": 1487.44, "total_tokens": 16149168} {"current_steps": 76530, "total_steps": 181800, "loss": 0.0174, "lr": 3.5884580382781904e-05, "epoch": 8.41914191419142, "percentage": 42.1, "elapsed_time": "3:00:57", "remaining_time": "4:08:55", "throughput": 1487.44, "total_tokens": 16150256} {"current_steps": 76535, "total_steps": 181800, "loss": 0.0917, "lr": 3.588241968312661e-05, "epoch": 8.41969196919692, "percentage": 42.1, "elapsed_time": "3:00:58", "remaining_time": "4:08:54", "throughput": 1487.44, "total_tokens": 16151280} {"current_steps": 76540, "total_steps": 181800, "loss": 0.0062, "lr": 3.5880258883173276e-05, "epoch": 8.42024202420242, "percentage": 42.1, "elapsed_time": "3:00:59", "remaining_time": "4:08:53", "throughput": 1487.45, "total_tokens": 16152368} {"current_steps": 76545, "total_steps": 181800, "loss": 0.0283, "lr": 3.587809798294182e-05, "epoch": 8.42079207920792, "percentage": 42.1, "elapsed_time": "3:00:59", "remaining_time": "4:08:53", "throughput": 1487.45, "total_tokens": 16153424} {"current_steps": 76550, "total_steps": 181800, "loss": 0.0228, "lr": 3.587593698245215e-05, "epoch": 8.421342134213422, "percentage": 42.11, "elapsed_time": "3:01:00", "remaining_time": "4:08:52", "throughput": 1487.45, "total_tokens": 16154448} {"current_steps": 76555, "total_steps": 181800, "loss": 0.0038, "lr": 3.587377588172418e-05, "epoch": 8.421892189218921, "percentage": 42.11, "elapsed_time": "3:01:01", "remaining_time": "4:08:51", "throughput": 1487.45, "total_tokens": 16155472} {"current_steps": 76560, "total_steps": 181800, "loss": 0.0138, "lr": 3.587161468077785e-05, "epoch": 8.422442244224422, "percentage": 42.11, "elapsed_time": "3:01:01", "remaining_time": "4:08:50", "throughput": 1487.45, "total_tokens": 16156464} {"current_steps": 76565, "total_steps": 181800, "loss": 0.0115, "lr": 3.5869453379633056e-05, "epoch": 8.422992299229923, "percentage": 42.11, "elapsed_time": "3:01:02", "remaining_time": "4:08:50", "throughput": 1487.45, "total_tokens": 16157520} {"current_steps": 76570, "total_steps": 181800, "loss": 0.0992, "lr": 3.586729197830972e-05, "epoch": 8.423542354235423, "percentage": 42.12, "elapsed_time": "3:01:03", "remaining_time": "4:08:49", "throughput": 1487.45, "total_tokens": 16158544} {"current_steps": 76575, "total_steps": 181800, "loss": 0.0164, "lr": 3.586513047682778e-05, "epoch": 8.424092409240924, "percentage": 42.12, "elapsed_time": "3:01:03", "remaining_time": "4:08:48", "throughput": 1487.45, "total_tokens": 16159600} {"current_steps": 76580, "total_steps": 181800, "loss": 0.0452, "lr": 3.586296887520714e-05, "epoch": 8.424642464246425, "percentage": 42.12, "elapsed_time": "3:01:04", "remaining_time": "4:08:47", "throughput": 1487.46, "total_tokens": 16160656} {"current_steps": 76585, "total_steps": 181800, "loss": 0.0583, "lr": 3.586080717346773e-05, "epoch": 8.425192519251926, "percentage": 42.13, "elapsed_time": "3:01:05", "remaining_time": "4:08:47", "throughput": 1487.46, "total_tokens": 16161712} {"current_steps": 76590, "total_steps": 181800, "loss": 0.058, "lr": 3.585864537162947e-05, "epoch": 8.425742574257425, "percentage": 42.13, "elapsed_time": "3:01:05", "remaining_time": "4:08:46", "throughput": 1487.46, "total_tokens": 16162736} {"current_steps": 76595, "total_steps": 181800, "loss": 0.0094, "lr": 3.5856483469712293e-05, "epoch": 8.426292629262926, "percentage": 42.13, "elapsed_time": "3:01:06", "remaining_time": "4:08:45", "throughput": 1487.46, "total_tokens": 16163792} {"current_steps": 76600, "total_steps": 181800, "loss": 0.0013, "lr": 3.585432146773611e-05, "epoch": 8.426842684268427, "percentage": 42.13, "elapsed_time": "3:01:07", "remaining_time": "4:08:44", "throughput": 1487.46, "total_tokens": 16164784} {"current_steps": 76605, "total_steps": 181800, "loss": 0.004, "lr": 3.585215936572086e-05, "epoch": 8.427392739273927, "percentage": 42.14, "elapsed_time": "3:01:08", "remaining_time": "4:08:44", "throughput": 1487.47, "total_tokens": 16165872} {"current_steps": 76610, "total_steps": 181800, "loss": 0.0476, "lr": 3.5849997163686456e-05, "epoch": 8.427942794279428, "percentage": 42.14, "elapsed_time": "3:01:08", "remaining_time": "4:08:43", "throughput": 1487.46, "total_tokens": 16166832} {"current_steps": 76615, "total_steps": 181800, "loss": 0.0768, "lr": 3.584783486165284e-05, "epoch": 8.428492849284929, "percentage": 42.14, "elapsed_time": "3:01:09", "remaining_time": "4:08:42", "throughput": 1487.46, "total_tokens": 16167856} {"current_steps": 76620, "total_steps": 181800, "loss": 0.0516, "lr": 3.584567245963993e-05, "epoch": 8.429042904290428, "percentage": 42.15, "elapsed_time": "3:01:10", "remaining_time": "4:08:41", "throughput": 1487.46, "total_tokens": 16168848} {"current_steps": 76625, "total_steps": 181800, "loss": 0.1642, "lr": 3.584350995766767e-05, "epoch": 8.42959295929593, "percentage": 42.15, "elapsed_time": "3:01:10", "remaining_time": "4:08:41", "throughput": 1487.46, "total_tokens": 16169904} {"current_steps": 76630, "total_steps": 181800, "loss": 0.0695, "lr": 3.5841347355755986e-05, "epoch": 8.43014301430143, "percentage": 42.15, "elapsed_time": "3:01:11", "remaining_time": "4:08:40", "throughput": 1487.47, "total_tokens": 16170992} {"current_steps": 76635, "total_steps": 181800, "loss": 0.0434, "lr": 3.5839184653924794e-05, "epoch": 8.430693069306932, "percentage": 42.15, "elapsed_time": "3:01:12", "remaining_time": "4:08:39", "throughput": 1487.47, "total_tokens": 16172048} {"current_steps": 76640, "total_steps": 181800, "loss": 0.0533, "lr": 3.583702185219404e-05, "epoch": 8.43124312431243, "percentage": 42.16, "elapsed_time": "3:01:12", "remaining_time": "4:08:38", "throughput": 1487.47, "total_tokens": 16173072} {"current_steps": 76645, "total_steps": 181800, "loss": 0.0264, "lr": 3.583485895058366e-05, "epoch": 8.431793179317932, "percentage": 42.16, "elapsed_time": "3:01:13", "remaining_time": "4:08:38", "throughput": 1487.48, "total_tokens": 16174224} {"current_steps": 76650, "total_steps": 181800, "loss": 0.0306, "lr": 3.583269594911358e-05, "epoch": 8.432343234323433, "percentage": 42.16, "elapsed_time": "3:01:14", "remaining_time": "4:08:37", "throughput": 1487.48, "total_tokens": 16175280} {"current_steps": 76655, "total_steps": 181800, "loss": 0.0131, "lr": 3.583053284780374e-05, "epoch": 8.432893289328932, "percentage": 42.16, "elapsed_time": "3:01:14", "remaining_time": "4:08:36", "throughput": 1487.48, "total_tokens": 16176304} {"current_steps": 76660, "total_steps": 181800, "loss": 0.0023, "lr": 3.582836964667408e-05, "epoch": 8.433443344334433, "percentage": 42.17, "elapsed_time": "3:01:15", "remaining_time": "4:08:36", "throughput": 1487.49, "total_tokens": 16177360} {"current_steps": 76665, "total_steps": 181800, "loss": 0.1031, "lr": 3.5826206345744526e-05, "epoch": 8.433993399339935, "percentage": 42.17, "elapsed_time": "3:01:16", "remaining_time": "4:08:35", "throughput": 1487.5, "total_tokens": 16178480} {"current_steps": 76670, "total_steps": 181800, "loss": 0.0101, "lr": 3.582404294503502e-05, "epoch": 8.434543454345434, "percentage": 42.17, "elapsed_time": "3:01:17", "remaining_time": "4:08:34", "throughput": 1487.5, "total_tokens": 16179536} {"current_steps": 76675, "total_steps": 181800, "loss": 0.0857, "lr": 3.582187944456552e-05, "epoch": 8.435093509350935, "percentage": 42.18, "elapsed_time": "3:01:17", "remaining_time": "4:08:33", "throughput": 1487.51, "total_tokens": 16180656} {"current_steps": 76680, "total_steps": 181800, "loss": 0.0235, "lr": 3.581971584435594e-05, "epoch": 8.435643564356436, "percentage": 42.18, "elapsed_time": "3:01:18", "remaining_time": "4:08:33", "throughput": 1487.51, "total_tokens": 16181744} {"current_steps": 76685, "total_steps": 181800, "loss": 0.0075, "lr": 3.581755214442623e-05, "epoch": 8.436193619361935, "percentage": 42.18, "elapsed_time": "3:01:19", "remaining_time": "4:08:32", "throughput": 1487.52, "total_tokens": 16182832} {"current_steps": 76690, "total_steps": 181800, "loss": 0.029, "lr": 3.581538834479634e-05, "epoch": 8.436743674367436, "percentage": 42.18, "elapsed_time": "3:01:19", "remaining_time": "4:08:31", "throughput": 1487.52, "total_tokens": 16183920} {"current_steps": 76695, "total_steps": 181800, "loss": 0.1158, "lr": 3.58132244454862e-05, "epoch": 8.437293729372938, "percentage": 42.19, "elapsed_time": "3:01:20", "remaining_time": "4:08:30", "throughput": 1487.52, "total_tokens": 16184944} {"current_steps": 76700, "total_steps": 181800, "loss": 0.1126, "lr": 3.581106044651575e-05, "epoch": 8.437843784378439, "percentage": 42.19, "elapsed_time": "3:01:21", "remaining_time": "4:08:30", "throughput": 1487.53, "total_tokens": 16186064} {"current_steps": 76705, "total_steps": 181800, "loss": 0.0912, "lr": 3.5808896347904964e-05, "epoch": 8.438393839383938, "percentage": 42.19, "elapsed_time": "3:01:21", "remaining_time": "4:08:29", "throughput": 1487.54, "total_tokens": 16187184} {"current_steps": 76710, "total_steps": 181800, "loss": 0.021, "lr": 3.580673214967375e-05, "epoch": 8.438943894389439, "percentage": 42.19, "elapsed_time": "3:01:22", "remaining_time": "4:08:28", "throughput": 1487.54, "total_tokens": 16188240} {"current_steps": 76715, "total_steps": 181800, "loss": 0.0155, "lr": 3.580456785184208e-05, "epoch": 8.43949394939494, "percentage": 42.2, "elapsed_time": "3:01:23", "remaining_time": "4:08:27", "throughput": 1487.55, "total_tokens": 16189328} {"current_steps": 76720, "total_steps": 181800, "loss": 0.0105, "lr": 3.5802403454429886e-05, "epoch": 8.44004400440044, "percentage": 42.2, "elapsed_time": "3:01:23", "remaining_time": "4:08:27", "throughput": 1487.55, "total_tokens": 16190352} {"current_steps": 76725, "total_steps": 181800, "loss": 0.0509, "lr": 3.580023895745713e-05, "epoch": 8.44059405940594, "percentage": 42.2, "elapsed_time": "3:01:24", "remaining_time": "4:08:26", "throughput": 1487.56, "total_tokens": 16191440} {"current_steps": 76730, "total_steps": 181800, "loss": 0.0463, "lr": 3.5798074360943745e-05, "epoch": 8.441144114411442, "percentage": 42.21, "elapsed_time": "3:01:25", "remaining_time": "4:08:25", "throughput": 1487.56, "total_tokens": 16192496} {"current_steps": 76735, "total_steps": 181800, "loss": 0.1646, "lr": 3.57959096649097e-05, "epoch": 8.441694169416941, "percentage": 42.21, "elapsed_time": "3:01:25", "remaining_time": "4:08:24", "throughput": 1487.56, "total_tokens": 16193552} {"current_steps": 76740, "total_steps": 181800, "loss": 0.0666, "lr": 3.579374486937493e-05, "epoch": 8.442244224422442, "percentage": 42.21, "elapsed_time": "3:01:26", "remaining_time": "4:08:24", "throughput": 1487.57, "total_tokens": 16194704} {"current_steps": 76745, "total_steps": 181800, "loss": 0.0555, "lr": 3.579157997435939e-05, "epoch": 8.442794279427943, "percentage": 42.21, "elapsed_time": "3:01:27", "remaining_time": "4:08:23", "throughput": 1487.57, "total_tokens": 16195728} {"current_steps": 76750, "total_steps": 181800, "loss": 0.1294, "lr": 3.578941497988304e-05, "epoch": 8.443344334433444, "percentage": 42.22, "elapsed_time": "3:01:28", "remaining_time": "4:08:22", "throughput": 1487.58, "total_tokens": 16196784} {"current_steps": 76755, "total_steps": 181800, "loss": 0.0043, "lr": 3.578724988596583e-05, "epoch": 8.443894389438944, "percentage": 42.22, "elapsed_time": "3:01:28", "remaining_time": "4:08:22", "throughput": 1487.58, "total_tokens": 16197808} {"current_steps": 76760, "total_steps": 181800, "loss": 0.0779, "lr": 3.578508469262771e-05, "epoch": 8.444444444444445, "percentage": 42.22, "elapsed_time": "3:01:29", "remaining_time": "4:08:21", "throughput": 1487.57, "total_tokens": 16198800} {"current_steps": 76765, "total_steps": 181800, "loss": 0.013, "lr": 3.578291939988865e-05, "epoch": 8.444994499449946, "percentage": 42.22, "elapsed_time": "3:01:30", "remaining_time": "4:08:20", "throughput": 1487.57, "total_tokens": 16199792} {"current_steps": 76770, "total_steps": 181800, "loss": 0.0087, "lr": 3.578075400776859e-05, "epoch": 8.445544554455445, "percentage": 42.23, "elapsed_time": "3:01:30", "remaining_time": "4:08:19", "throughput": 1487.57, "total_tokens": 16200848} {"current_steps": 76775, "total_steps": 181800, "loss": 0.0105, "lr": 3.577858851628749e-05, "epoch": 8.446094609460946, "percentage": 42.23, "elapsed_time": "3:01:31", "remaining_time": "4:08:19", "throughput": 1487.58, "total_tokens": 16201904} {"current_steps": 76780, "total_steps": 181800, "loss": 0.0086, "lr": 3.577642292546532e-05, "epoch": 8.446644664466447, "percentage": 42.23, "elapsed_time": "3:01:32", "remaining_time": "4:08:18", "throughput": 1487.58, "total_tokens": 16202960} {"current_steps": 76785, "total_steps": 181800, "loss": 0.0134, "lr": 3.577425723532202e-05, "epoch": 8.447194719471947, "percentage": 42.24, "elapsed_time": "3:01:32", "remaining_time": "4:08:17", "throughput": 1487.58, "total_tokens": 16203984} {"current_steps": 76790, "total_steps": 181800, "loss": 0.0333, "lr": 3.5772091445877565e-05, "epoch": 8.447744774477448, "percentage": 42.24, "elapsed_time": "3:01:33", "remaining_time": "4:08:16", "throughput": 1487.58, "total_tokens": 16205008} {"current_steps": 76795, "total_steps": 181800, "loss": 0.1111, "lr": 3.576992555715191e-05, "epoch": 8.448294829482949, "percentage": 42.24, "elapsed_time": "3:01:34", "remaining_time": "4:08:16", "throughput": 1487.58, "total_tokens": 16206000} {"current_steps": 76800, "total_steps": 181800, "loss": 0.0064, "lr": 3.576775956916503e-05, "epoch": 8.448844884488448, "percentage": 42.24, "elapsed_time": "3:01:34", "remaining_time": "4:08:15", "throughput": 1487.57, "total_tokens": 16207024} {"current_steps": 76805, "total_steps": 181800, "loss": 0.0518, "lr": 3.576559348193687e-05, "epoch": 8.44939493949395, "percentage": 42.25, "elapsed_time": "3:01:35", "remaining_time": "4:08:14", "throughput": 1487.58, "total_tokens": 16208144} {"current_steps": 76810, "total_steps": 181800, "loss": 0.0749, "lr": 3.5763427295487394e-05, "epoch": 8.44994499449945, "percentage": 42.25, "elapsed_time": "3:01:36", "remaining_time": "4:08:13", "throughput": 1487.59, "total_tokens": 16209200} {"current_steps": 76815, "total_steps": 181800, "loss": 0.0844, "lr": 3.576126100983658e-05, "epoch": 8.450495049504951, "percentage": 42.25, "elapsed_time": "3:01:37", "remaining_time": "4:08:13", "throughput": 1487.58, "total_tokens": 16210192} {"current_steps": 76820, "total_steps": 181800, "loss": 0.0139, "lr": 3.575909462500439e-05, "epoch": 8.45104510451045, "percentage": 42.26, "elapsed_time": "3:01:37", "remaining_time": "4:08:12", "throughput": 1487.58, "total_tokens": 16211216} {"current_steps": 76825, "total_steps": 181800, "loss": 0.0109, "lr": 3.575692814101078e-05, "epoch": 8.451595159515952, "percentage": 42.26, "elapsed_time": "3:01:38", "remaining_time": "4:08:11", "throughput": 1487.58, "total_tokens": 16212272} {"current_steps": 76830, "total_steps": 181800, "loss": 0.0393, "lr": 3.5754761557875725e-05, "epoch": 8.452145214521453, "percentage": 42.26, "elapsed_time": "3:01:39", "remaining_time": "4:08:11", "throughput": 1487.58, "total_tokens": 16213264} {"current_steps": 76835, "total_steps": 181800, "loss": 0.2042, "lr": 3.57525948756192e-05, "epoch": 8.452695269526952, "percentage": 42.26, "elapsed_time": "3:01:39", "remaining_time": "4:08:10", "throughput": 1487.58, "total_tokens": 16214320} {"current_steps": 76840, "total_steps": 181800, "loss": 0.0261, "lr": 3.575042809426116e-05, "epoch": 8.453245324532453, "percentage": 42.27, "elapsed_time": "3:01:40", "remaining_time": "4:08:09", "throughput": 1487.59, "total_tokens": 16215376} {"current_steps": 76845, "total_steps": 181800, "loss": 0.0658, "lr": 3.574826121382159e-05, "epoch": 8.453795379537954, "percentage": 42.27, "elapsed_time": "3:01:41", "remaining_time": "4:08:08", "throughput": 1487.59, "total_tokens": 16216464} {"current_steps": 76850, "total_steps": 181800, "loss": 0.0167, "lr": 3.5746094234320454e-05, "epoch": 8.454345434543454, "percentage": 42.27, "elapsed_time": "3:01:41", "remaining_time": "4:08:08", "throughput": 1487.6, "total_tokens": 16217552} {"current_steps": 76855, "total_steps": 181800, "loss": 0.0602, "lr": 3.574392715577772e-05, "epoch": 8.454895489548955, "percentage": 42.27, "elapsed_time": "3:01:42", "remaining_time": "4:08:07", "throughput": 1487.6, "total_tokens": 16218608} {"current_steps": 76860, "total_steps": 181800, "loss": 0.0865, "lr": 3.5741759978213365e-05, "epoch": 8.455445544554456, "percentage": 42.28, "elapsed_time": "3:01:43", "remaining_time": "4:08:06", "throughput": 1487.61, "total_tokens": 16219664} {"current_steps": 76865, "total_steps": 181800, "loss": 0.0091, "lr": 3.573959270164736e-05, "epoch": 8.455995599559955, "percentage": 42.28, "elapsed_time": "3:01:43", "remaining_time": "4:08:05", "throughput": 1487.61, "total_tokens": 16220720} {"current_steps": 76870, "total_steps": 181800, "loss": 0.1228, "lr": 3.573742532609969e-05, "epoch": 8.456545654565456, "percentage": 42.28, "elapsed_time": "3:01:44", "remaining_time": "4:08:05", "throughput": 1487.61, "total_tokens": 16221808} {"current_steps": 76875, "total_steps": 181800, "loss": 0.0391, "lr": 3.573525785159032e-05, "epoch": 8.457095709570957, "percentage": 42.29, "elapsed_time": "3:01:45", "remaining_time": "4:08:04", "throughput": 1487.61, "total_tokens": 16222864} {"current_steps": 76880, "total_steps": 181800, "loss": 0.0755, "lr": 3.573309027813923e-05, "epoch": 8.457645764576458, "percentage": 42.29, "elapsed_time": "3:01:45", "remaining_time": "4:08:03", "throughput": 1487.61, "total_tokens": 16223856} {"current_steps": 76885, "total_steps": 181800, "loss": 0.0121, "lr": 3.57309226057664e-05, "epoch": 8.458195819581958, "percentage": 42.29, "elapsed_time": "3:01:46", "remaining_time": "4:08:02", "throughput": 1487.61, "total_tokens": 16224880} {"current_steps": 76890, "total_steps": 181800, "loss": 0.0049, "lr": 3.5728754834491794e-05, "epoch": 8.458745874587459, "percentage": 42.29, "elapsed_time": "3:01:47", "remaining_time": "4:08:02", "throughput": 1487.61, "total_tokens": 16225904} {"current_steps": 76895, "total_steps": 181800, "loss": 0.094, "lr": 3.5726586964335416e-05, "epoch": 8.45929592959296, "percentage": 42.3, "elapsed_time": "3:01:48", "remaining_time": "4:08:01", "throughput": 1487.61, "total_tokens": 16226896} {"current_steps": 76900, "total_steps": 181800, "loss": 0.0656, "lr": 3.572441899531722e-05, "epoch": 8.45984598459846, "percentage": 42.3, "elapsed_time": "3:01:48", "remaining_time": "4:08:00", "throughput": 1487.61, "total_tokens": 16227984} {"current_steps": 76905, "total_steps": 181800, "loss": 0.0365, "lr": 3.572225092745721e-05, "epoch": 8.46039603960396, "percentage": 42.3, "elapsed_time": "3:01:49", "remaining_time": "4:07:59", "throughput": 1487.62, "total_tokens": 16229072} {"current_steps": 76910, "total_steps": 181800, "loss": 0.1612, "lr": 3.572008276077536e-05, "epoch": 8.460946094609461, "percentage": 42.3, "elapsed_time": "3:01:50", "remaining_time": "4:07:59", "throughput": 1487.62, "total_tokens": 16230064} {"current_steps": 76915, "total_steps": 181800, "loss": 0.017, "lr": 3.571791449529165e-05, "epoch": 8.46149614961496, "percentage": 42.31, "elapsed_time": "3:01:50", "remaining_time": "4:07:58", "throughput": 1487.62, "total_tokens": 16231184} {"current_steps": 76920, "total_steps": 181800, "loss": 0.0197, "lr": 3.571574613102606e-05, "epoch": 8.462046204620462, "percentage": 42.31, "elapsed_time": "3:01:51", "remaining_time": "4:07:57", "throughput": 1487.62, "total_tokens": 16232208} {"current_steps": 76925, "total_steps": 181800, "loss": 0.068, "lr": 3.571357766799858e-05, "epoch": 8.462596259625963, "percentage": 42.31, "elapsed_time": "3:01:52", "remaining_time": "4:07:57", "throughput": 1487.63, "total_tokens": 16233264} {"current_steps": 76930, "total_steps": 181800, "loss": 0.0301, "lr": 3.57114091062292e-05, "epoch": 8.463146314631462, "percentage": 42.32, "elapsed_time": "3:01:52", "remaining_time": "4:07:56", "throughput": 1487.63, "total_tokens": 16234320} {"current_steps": 76935, "total_steps": 181800, "loss": 0.1205, "lr": 3.57092404457379e-05, "epoch": 8.463696369636963, "percentage": 42.32, "elapsed_time": "3:01:53", "remaining_time": "4:07:55", "throughput": 1487.64, "total_tokens": 16235408} {"current_steps": 76940, "total_steps": 181800, "loss": 0.0417, "lr": 3.5707071686544676e-05, "epoch": 8.464246424642464, "percentage": 42.32, "elapsed_time": "3:01:54", "remaining_time": "4:07:54", "throughput": 1487.64, "total_tokens": 16236528} {"current_steps": 76945, "total_steps": 181800, "loss": 0.039, "lr": 3.570490282866949e-05, "epoch": 8.464796479647966, "percentage": 42.32, "elapsed_time": "3:01:54", "remaining_time": "4:07:54", "throughput": 1487.65, "total_tokens": 16237584} {"current_steps": 76950, "total_steps": 181800, "loss": 0.0766, "lr": 3.570273387213237e-05, "epoch": 8.465346534653465, "percentage": 42.33, "elapsed_time": "3:01:55", "remaining_time": "4:07:53", "throughput": 1487.64, "total_tokens": 16238576} {"current_steps": 76955, "total_steps": 181800, "loss": 0.0146, "lr": 3.5700564816953286e-05, "epoch": 8.465896589658966, "percentage": 42.33, "elapsed_time": "3:01:56", "remaining_time": "4:07:52", "throughput": 1487.64, "total_tokens": 16239568} {"current_steps": 76960, "total_steps": 181800, "loss": 0.0211, "lr": 3.5698395663152215e-05, "epoch": 8.466446644664467, "percentage": 42.33, "elapsed_time": "3:01:57", "remaining_time": "4:07:51", "throughput": 1487.64, "total_tokens": 16240592} {"current_steps": 76965, "total_steps": 181800, "loss": 0.0167, "lr": 3.569622641074919e-05, "epoch": 8.466996699669966, "percentage": 42.33, "elapsed_time": "3:01:57", "remaining_time": "4:07:51", "throughput": 1487.64, "total_tokens": 16241648} {"current_steps": 76970, "total_steps": 181800, "loss": 0.0708, "lr": 3.569405705976416e-05, "epoch": 8.467546754675467, "percentage": 42.34, "elapsed_time": "3:01:58", "remaining_time": "4:07:50", "throughput": 1487.64, "total_tokens": 16242672} {"current_steps": 76975, "total_steps": 181800, "loss": 0.0894, "lr": 3.5691887610217146e-05, "epoch": 8.468096809680969, "percentage": 42.34, "elapsed_time": "3:01:59", "remaining_time": "4:07:49", "throughput": 1487.64, "total_tokens": 16243696} {"current_steps": 76980, "total_steps": 181800, "loss": 0.0717, "lr": 3.568971806212813e-05, "epoch": 8.468646864686468, "percentage": 42.34, "elapsed_time": "3:01:59", "remaining_time": "4:07:48", "throughput": 1487.64, "total_tokens": 16244720} {"current_steps": 76985, "total_steps": 181800, "loss": 0.0209, "lr": 3.568754841551711e-05, "epoch": 8.469196919691969, "percentage": 42.35, "elapsed_time": "3:02:00", "remaining_time": "4:07:48", "throughput": 1487.65, "total_tokens": 16245808} {"current_steps": 76990, "total_steps": 181800, "loss": 0.0079, "lr": 3.568537867040409e-05, "epoch": 8.46974697469747, "percentage": 42.35, "elapsed_time": "3:02:01", "remaining_time": "4:07:47", "throughput": 1487.64, "total_tokens": 16246832} {"current_steps": 76995, "total_steps": 181800, "loss": 0.0341, "lr": 3.568320882680906e-05, "epoch": 8.47029702970297, "percentage": 42.35, "elapsed_time": "3:02:01", "remaining_time": "4:07:46", "throughput": 1487.65, "total_tokens": 16247888} {"current_steps": 77000, "total_steps": 181800, "loss": 0.0213, "lr": 3.5681038884752026e-05, "epoch": 8.47084708470847, "percentage": 42.35, "elapsed_time": "3:02:02", "remaining_time": "4:07:46", "throughput": 1487.65, "total_tokens": 16248944} {"current_steps": 77005, "total_steps": 181800, "loss": 0.0066, "lr": 3.567886884425297e-05, "epoch": 8.471397139713972, "percentage": 42.36, "elapsed_time": "3:02:03", "remaining_time": "4:07:45", "throughput": 1487.65, "total_tokens": 16250000} {"current_steps": 77010, "total_steps": 181800, "loss": 0.0168, "lr": 3.5676698705331916e-05, "epoch": 8.471947194719473, "percentage": 42.36, "elapsed_time": "3:02:03", "remaining_time": "4:07:44", "throughput": 1487.66, "total_tokens": 16251088} {"current_steps": 77015, "total_steps": 181800, "loss": 0.0206, "lr": 3.567452846800885e-05, "epoch": 8.472497249724972, "percentage": 42.36, "elapsed_time": "3:02:04", "remaining_time": "4:07:43", "throughput": 1487.67, "total_tokens": 16252208} {"current_steps": 77020, "total_steps": 181800, "loss": 0.044, "lr": 3.5672358132303774e-05, "epoch": 8.473047304730473, "percentage": 42.37, "elapsed_time": "3:02:05", "remaining_time": "4:07:43", "throughput": 1487.67, "total_tokens": 16253264} {"current_steps": 77025, "total_steps": 181800, "loss": 0.0054, "lr": 3.567018769823669e-05, "epoch": 8.473597359735974, "percentage": 42.37, "elapsed_time": "3:02:06", "remaining_time": "4:07:42", "throughput": 1487.67, "total_tokens": 16254320} {"current_steps": 77030, "total_steps": 181800, "loss": 0.0733, "lr": 3.5668017165827616e-05, "epoch": 8.474147414741473, "percentage": 42.37, "elapsed_time": "3:02:06", "remaining_time": "4:07:41", "throughput": 1487.67, "total_tokens": 16255344} {"current_steps": 77035, "total_steps": 181800, "loss": 0.0108, "lr": 3.566584653509654e-05, "epoch": 8.474697469746975, "percentage": 42.37, "elapsed_time": "3:02:07", "remaining_time": "4:07:40", "throughput": 1487.67, "total_tokens": 16256400} {"current_steps": 77040, "total_steps": 181800, "loss": 0.0202, "lr": 3.566367580606348e-05, "epoch": 8.475247524752476, "percentage": 42.38, "elapsed_time": "3:02:08", "remaining_time": "4:07:40", "throughput": 1487.68, "total_tokens": 16257488} {"current_steps": 77045, "total_steps": 181800, "loss": 0.0071, "lr": 3.5661504978748436e-05, "epoch": 8.475797579757975, "percentage": 42.38, "elapsed_time": "3:02:08", "remaining_time": "4:07:39", "throughput": 1487.68, "total_tokens": 16258544} {"current_steps": 77050, "total_steps": 181800, "loss": 0.0115, "lr": 3.5659334053171415e-05, "epoch": 8.476347634763476, "percentage": 42.38, "elapsed_time": "3:02:09", "remaining_time": "4:07:38", "throughput": 1487.69, "total_tokens": 16259632} {"current_steps": 77055, "total_steps": 181800, "loss": 0.0145, "lr": 3.565716302935242e-05, "epoch": 8.476897689768977, "percentage": 42.38, "elapsed_time": "3:02:10", "remaining_time": "4:07:37", "throughput": 1487.7, "total_tokens": 16260752} {"current_steps": 77060, "total_steps": 181800, "loss": 0.0082, "lr": 3.5654991907311476e-05, "epoch": 8.477447744774478, "percentage": 42.39, "elapsed_time": "3:02:10", "remaining_time": "4:07:37", "throughput": 1487.7, "total_tokens": 16261808} {"current_steps": 77065, "total_steps": 181800, "loss": 0.0161, "lr": 3.565282068706858e-05, "epoch": 8.477997799779978, "percentage": 42.39, "elapsed_time": "3:02:11", "remaining_time": "4:07:36", "throughput": 1487.7, "total_tokens": 16262832} {"current_steps": 77070, "total_steps": 181800, "loss": 0.0105, "lr": 3.565064936864375e-05, "epoch": 8.478547854785479, "percentage": 42.39, "elapsed_time": "3:02:12", "remaining_time": "4:07:35", "throughput": 1487.71, "total_tokens": 16263952} {"current_steps": 77075, "total_steps": 181800, "loss": 0.0696, "lr": 3.5648477952056996e-05, "epoch": 8.47909790979098, "percentage": 42.4, "elapsed_time": "3:02:12", "remaining_time": "4:07:35", "throughput": 1487.71, "total_tokens": 16265008} {"current_steps": 77080, "total_steps": 181800, "loss": 0.0396, "lr": 3.564630643732832e-05, "epoch": 8.479647964796479, "percentage": 42.4, "elapsed_time": "3:02:13", "remaining_time": "4:07:34", "throughput": 1487.71, "total_tokens": 16266064} {"current_steps": 77085, "total_steps": 181800, "loss": 0.0431, "lr": 3.564413482447777e-05, "epoch": 8.48019801980198, "percentage": 42.4, "elapsed_time": "3:02:14", "remaining_time": "4:07:33", "throughput": 1487.71, "total_tokens": 16267120} {"current_steps": 77090, "total_steps": 181800, "loss": 0.0306, "lr": 3.564196311352531e-05, "epoch": 8.480748074807481, "percentage": 42.4, "elapsed_time": "3:02:14", "remaining_time": "4:07:32", "throughput": 1487.72, "total_tokens": 16268240} {"current_steps": 77095, "total_steps": 181800, "loss": 0.0552, "lr": 3.5639791304490997e-05, "epoch": 8.48129812981298, "percentage": 42.41, "elapsed_time": "3:02:15", "remaining_time": "4:07:32", "throughput": 1487.72, "total_tokens": 16269296} {"current_steps": 77100, "total_steps": 181800, "loss": 0.0777, "lr": 3.563761939739483e-05, "epoch": 8.481848184818482, "percentage": 42.41, "elapsed_time": "3:02:16", "remaining_time": "4:07:31", "throughput": 1487.73, "total_tokens": 16270352} {"current_steps": 77105, "total_steps": 181800, "loss": 0.03, "lr": 3.5635447392256834e-05, "epoch": 8.482398239823983, "percentage": 42.41, "elapsed_time": "3:02:17", "remaining_time": "4:07:30", "throughput": 1487.73, "total_tokens": 16271376} {"current_steps": 77110, "total_steps": 181800, "loss": 0.0252, "lr": 3.5633275289097015e-05, "epoch": 8.482948294829482, "percentage": 42.41, "elapsed_time": "3:02:17", "remaining_time": "4:07:29", "throughput": 1487.72, "total_tokens": 16272368} {"current_steps": 77115, "total_steps": 181800, "loss": 0.0888, "lr": 3.563110308793541e-05, "epoch": 8.483498349834983, "percentage": 42.42, "elapsed_time": "3:02:18", "remaining_time": "4:07:29", "throughput": 1487.73, "total_tokens": 16273424} {"current_steps": 77120, "total_steps": 181800, "loss": 0.075, "lr": 3.5628930788792015e-05, "epoch": 8.484048404840484, "percentage": 42.42, "elapsed_time": "3:02:19", "remaining_time": "4:07:28", "throughput": 1487.73, "total_tokens": 16274512} {"current_steps": 77125, "total_steps": 181800, "loss": 0.0105, "lr": 3.5626758391686874e-05, "epoch": 8.484598459845985, "percentage": 42.42, "elapsed_time": "3:02:19", "remaining_time": "4:07:27", "throughput": 1487.73, "total_tokens": 16275536} {"current_steps": 77130, "total_steps": 181800, "loss": 0.0469, "lr": 3.5624585896640004e-05, "epoch": 8.485148514851485, "percentage": 42.43, "elapsed_time": "3:02:20", "remaining_time": "4:07:26", "throughput": 1487.73, "total_tokens": 16276560} {"current_steps": 77135, "total_steps": 181800, "loss": 0.0454, "lr": 3.562241330367142e-05, "epoch": 8.485698569856986, "percentage": 42.43, "elapsed_time": "3:02:21", "remaining_time": "4:07:26", "throughput": 1487.73, "total_tokens": 16277584} {"current_steps": 77140, "total_steps": 181800, "loss": 0.0283, "lr": 3.562024061280115e-05, "epoch": 8.486248624862487, "percentage": 42.43, "elapsed_time": "3:02:21", "remaining_time": "4:07:25", "throughput": 1487.73, "total_tokens": 16278608} {"current_steps": 77145, "total_steps": 181800, "loss": 0.0062, "lr": 3.561806782404921e-05, "epoch": 8.486798679867986, "percentage": 42.43, "elapsed_time": "3:02:22", "remaining_time": "4:07:24", "throughput": 1487.72, "total_tokens": 16279568} {"current_steps": 77150, "total_steps": 181800, "loss": 0.0959, "lr": 3.561589493743564e-05, "epoch": 8.487348734873487, "percentage": 42.44, "elapsed_time": "3:02:23", "remaining_time": "4:07:24", "throughput": 1487.73, "total_tokens": 16280624} {"current_steps": 77155, "total_steps": 181800, "loss": 0.0744, "lr": 3.5613721952980464e-05, "epoch": 8.487898789878988, "percentage": 42.44, "elapsed_time": "3:02:23", "remaining_time": "4:07:23", "throughput": 1487.73, "total_tokens": 16281680} {"current_steps": 77160, "total_steps": 181800, "loss": 0.0029, "lr": 3.5611548870703704e-05, "epoch": 8.488448844884488, "percentage": 42.44, "elapsed_time": "3:02:24", "remaining_time": "4:07:22", "throughput": 1487.73, "total_tokens": 16282736} {"current_steps": 77165, "total_steps": 181800, "loss": 0.0844, "lr": 3.560937569062538e-05, "epoch": 8.488998899889989, "percentage": 42.44, "elapsed_time": "3:02:25", "remaining_time": "4:07:21", "throughput": 1487.74, "total_tokens": 16283824} {"current_steps": 77170, "total_steps": 181800, "loss": 0.0229, "lr": 3.560720241276555e-05, "epoch": 8.48954895489549, "percentage": 42.45, "elapsed_time": "3:02:26", "remaining_time": "4:07:21", "throughput": 1487.74, "total_tokens": 16284880} {"current_steps": 77175, "total_steps": 181800, "loss": 0.1445, "lr": 3.560502903714421e-05, "epoch": 8.490099009900991, "percentage": 42.45, "elapsed_time": "3:02:26", "remaining_time": "4:07:20", "throughput": 1487.74, "total_tokens": 16285936} {"current_steps": 77180, "total_steps": 181800, "loss": 0.0545, "lr": 3.560285556378142e-05, "epoch": 8.49064906490649, "percentage": 42.45, "elapsed_time": "3:02:27", "remaining_time": "4:07:19", "throughput": 1487.74, "total_tokens": 16286960} {"current_steps": 77185, "total_steps": 181800, "loss": 0.0245, "lr": 3.560068199269719e-05, "epoch": 8.491199119911991, "percentage": 42.46, "elapsed_time": "3:02:28", "remaining_time": "4:07:18", "throughput": 1487.75, "total_tokens": 16288048} {"current_steps": 77190, "total_steps": 181800, "loss": 0.0651, "lr": 3.5598508323911555e-05, "epoch": 8.491749174917492, "percentage": 42.46, "elapsed_time": "3:02:28", "remaining_time": "4:07:18", "throughput": 1487.75, "total_tokens": 16289104} {"current_steps": 77195, "total_steps": 181800, "loss": 0.083, "lr": 3.5596334557444556e-05, "epoch": 8.492299229922992, "percentage": 42.46, "elapsed_time": "3:02:29", "remaining_time": "4:07:17", "throughput": 1487.75, "total_tokens": 16290160} {"current_steps": 77200, "total_steps": 181800, "loss": 0.0797, "lr": 3.5594160693316236e-05, "epoch": 8.492849284928493, "percentage": 42.46, "elapsed_time": "3:02:30", "remaining_time": "4:07:16", "throughput": 1487.75, "total_tokens": 16291184} {"current_steps": 77205, "total_steps": 181800, "loss": 0.005, "lr": 3.5591986731546614e-05, "epoch": 8.493399339933994, "percentage": 42.47, "elapsed_time": "3:02:30", "remaining_time": "4:07:15", "throughput": 1487.76, "total_tokens": 16292272} {"current_steps": 77210, "total_steps": 181800, "loss": 0.038, "lr": 3.558981267215573e-05, "epoch": 8.493949394939493, "percentage": 42.47, "elapsed_time": "3:02:31", "remaining_time": "4:07:15", "throughput": 1487.76, "total_tokens": 16293328} {"current_steps": 77215, "total_steps": 181800, "loss": 0.0293, "lr": 3.558763851516363e-05, "epoch": 8.494499449944994, "percentage": 42.47, "elapsed_time": "3:02:32", "remaining_time": "4:07:14", "throughput": 1487.77, "total_tokens": 16294416} {"current_steps": 77220, "total_steps": 181800, "loss": 0.0534, "lr": 3.558546426059034e-05, "epoch": 8.495049504950495, "percentage": 42.48, "elapsed_time": "3:02:33", "remaining_time": "4:07:13", "throughput": 1487.74, "total_tokens": 16295440} {"current_steps": 77225, "total_steps": 181800, "loss": 0.0191, "lr": 3.558328990845591e-05, "epoch": 8.495599559955995, "percentage": 42.48, "elapsed_time": "3:02:33", "remaining_time": "4:07:13", "throughput": 1487.75, "total_tokens": 16296592} {"current_steps": 77230, "total_steps": 181800, "loss": 0.0273, "lr": 3.558111545878038e-05, "epoch": 8.496149614961496, "percentage": 42.48, "elapsed_time": "3:02:34", "remaining_time": "4:07:12", "throughput": 1487.76, "total_tokens": 16297648} {"current_steps": 77235, "total_steps": 181800, "loss": 0.0091, "lr": 3.557894091158377e-05, "epoch": 8.496699669966997, "percentage": 42.48, "elapsed_time": "3:02:35", "remaining_time": "4:07:11", "throughput": 1487.75, "total_tokens": 16298640} {"current_steps": 77240, "total_steps": 181800, "loss": 0.0195, "lr": 3.557676626688615e-05, "epoch": 8.497249724972498, "percentage": 42.49, "elapsed_time": "3:02:35", "remaining_time": "4:07:11", "throughput": 1487.75, "total_tokens": 16299632} {"current_steps": 77245, "total_steps": 181800, "loss": 0.0053, "lr": 3.557459152470755e-05, "epoch": 8.497799779977997, "percentage": 42.49, "elapsed_time": "3:02:36", "remaining_time": "4:07:10", "throughput": 1487.75, "total_tokens": 16300688} {"current_steps": 77250, "total_steps": 181800, "loss": 0.0297, "lr": 3.557241668506801e-05, "epoch": 8.498349834983498, "percentage": 42.49, "elapsed_time": "3:02:37", "remaining_time": "4:07:09", "throughput": 1487.76, "total_tokens": 16301744} {"current_steps": 77255, "total_steps": 181800, "loss": 0.0043, "lr": 3.557024174798759e-05, "epoch": 8.498899889989, "percentage": 42.49, "elapsed_time": "3:02:37", "remaining_time": "4:07:08", "throughput": 1487.76, "total_tokens": 16302768} {"current_steps": 77260, "total_steps": 181800, "loss": 0.0455, "lr": 3.5568066713486314e-05, "epoch": 8.499449944994499, "percentage": 42.5, "elapsed_time": "3:02:38", "remaining_time": "4:07:08", "throughput": 1487.75, "total_tokens": 16303760} {"current_steps": 77265, "total_steps": 181800, "loss": 0.0134, "lr": 3.556589158158423e-05, "epoch": 8.5, "percentage": 42.5, "elapsed_time": "3:02:39", "remaining_time": "4:07:07", "throughput": 1487.76, "total_tokens": 16304880} {"current_steps": 77270, "total_steps": 181800, "loss": 0.0387, "lr": 3.556371635230141e-05, "epoch": 8.500550055005501, "percentage": 42.5, "elapsed_time": "3:02:40", "remaining_time": "4:07:06", "throughput": 1487.77, "total_tokens": 16305936} {"current_steps": 77275, "total_steps": 181800, "loss": 0.0223, "lr": 3.556154102565788e-05, "epoch": 8.501100110011, "percentage": 42.51, "elapsed_time": "3:02:40", "remaining_time": "4:07:05", "throughput": 1487.77, "total_tokens": 16307024} {"current_steps": 77280, "total_steps": 181800, "loss": 0.0472, "lr": 3.555936560167369e-05, "epoch": 8.501650165016502, "percentage": 42.51, "elapsed_time": "3:02:41", "remaining_time": "4:07:05", "throughput": 1487.77, "total_tokens": 16308048} {"current_steps": 77285, "total_steps": 181800, "loss": 0.0415, "lr": 3.55571900803689e-05, "epoch": 8.502200220022003, "percentage": 42.51, "elapsed_time": "3:02:42", "remaining_time": "4:07:04", "throughput": 1487.77, "total_tokens": 16309104} {"current_steps": 77290, "total_steps": 181800, "loss": 0.004, "lr": 3.555501446176355e-05, "epoch": 8.502750275027502, "percentage": 42.51, "elapsed_time": "3:02:42", "remaining_time": "4:07:03", "throughput": 1487.78, "total_tokens": 16310160} {"current_steps": 77295, "total_steps": 181800, "loss": 0.0371, "lr": 3.555283874587769e-05, "epoch": 8.503300330033003, "percentage": 42.52, "elapsed_time": "3:02:43", "remaining_time": "4:07:02", "throughput": 1487.79, "total_tokens": 16311312} {"current_steps": 77300, "total_steps": 181800, "loss": 0.0375, "lr": 3.555066293273139e-05, "epoch": 8.503850385038504, "percentage": 42.52, "elapsed_time": "3:02:44", "remaining_time": "4:07:02", "throughput": 1487.79, "total_tokens": 16312336} {"current_steps": 77305, "total_steps": 181800, "loss": 0.0094, "lr": 3.5548487022344686e-05, "epoch": 8.504400440044005, "percentage": 42.52, "elapsed_time": "3:02:44", "remaining_time": "4:07:01", "throughput": 1487.79, "total_tokens": 16313360} {"current_steps": 77310, "total_steps": 181800, "loss": 0.0173, "lr": 3.554631101473764e-05, "epoch": 8.504950495049505, "percentage": 42.52, "elapsed_time": "3:02:45", "remaining_time": "4:07:00", "throughput": 1487.79, "total_tokens": 16314384} {"current_steps": 77315, "total_steps": 181800, "loss": 0.013, "lr": 3.554413490993031e-05, "epoch": 8.505500550055006, "percentage": 42.53, "elapsed_time": "3:02:46", "remaining_time": "4:06:59", "throughput": 1487.79, "total_tokens": 16315376} {"current_steps": 77320, "total_steps": 181800, "loss": 0.0042, "lr": 3.554195870794275e-05, "epoch": 8.506050605060507, "percentage": 42.53, "elapsed_time": "3:02:46", "remaining_time": "4:06:59", "throughput": 1487.79, "total_tokens": 16316464} {"current_steps": 77325, "total_steps": 181800, "loss": 0.0202, "lr": 3.5539782408795006e-05, "epoch": 8.506600660066006, "percentage": 42.53, "elapsed_time": "3:02:47", "remaining_time": "4:06:58", "throughput": 1487.79, "total_tokens": 16317488} {"current_steps": 77330, "total_steps": 181800, "loss": 0.025, "lr": 3.553760601250715e-05, "epoch": 8.507150715071507, "percentage": 42.54, "elapsed_time": "3:02:48", "remaining_time": "4:06:57", "throughput": 1487.79, "total_tokens": 16318544} {"current_steps": 77335, "total_steps": 181800, "loss": 0.0503, "lr": 3.553542951909924e-05, "epoch": 8.507700770077008, "percentage": 42.54, "elapsed_time": "3:02:48", "remaining_time": "4:06:57", "throughput": 1487.8, "total_tokens": 16319632} {"current_steps": 77340, "total_steps": 181800, "loss": 0.0384, "lr": 3.553325292859133e-05, "epoch": 8.508250825082508, "percentage": 42.54, "elapsed_time": "3:02:49", "remaining_time": "4:06:56", "throughput": 1487.8, "total_tokens": 16320656} {"current_steps": 77345, "total_steps": 181800, "loss": 0.1047, "lr": 3.553107624100348e-05, "epoch": 8.508800880088009, "percentage": 42.54, "elapsed_time": "3:02:50", "remaining_time": "4:06:55", "throughput": 1487.81, "total_tokens": 16321744} {"current_steps": 77350, "total_steps": 181800, "loss": 0.0252, "lr": 3.552889945635575e-05, "epoch": 8.50935093509351, "percentage": 42.55, "elapsed_time": "3:02:51", "remaining_time": "4:06:54", "throughput": 1487.81, "total_tokens": 16322832} {"current_steps": 77355, "total_steps": 181800, "loss": 0.0097, "lr": 3.552672257466821e-05, "epoch": 8.509900990099009, "percentage": 42.55, "elapsed_time": "3:02:51", "remaining_time": "4:06:54", "throughput": 1487.82, "total_tokens": 16323888} {"current_steps": 77360, "total_steps": 181800, "loss": 0.0539, "lr": 3.5524545595960914e-05, "epoch": 8.51045104510451, "percentage": 42.55, "elapsed_time": "3:02:52", "remaining_time": "4:06:53", "throughput": 1487.82, "total_tokens": 16324976} {"current_steps": 77365, "total_steps": 181800, "loss": 0.0144, "lr": 3.552236852025394e-05, "epoch": 8.511001100110011, "percentage": 42.56, "elapsed_time": "3:02:53", "remaining_time": "4:06:52", "throughput": 1487.82, "total_tokens": 16326032} {"current_steps": 77370, "total_steps": 181800, "loss": 0.0069, "lr": 3.552019134756734e-05, "epoch": 8.511551155115512, "percentage": 42.56, "elapsed_time": "3:02:53", "remaining_time": "4:06:51", "throughput": 1487.83, "total_tokens": 16327088} {"current_steps": 77375, "total_steps": 181800, "loss": 0.0069, "lr": 3.551801407792118e-05, "epoch": 8.512101210121012, "percentage": 42.56, "elapsed_time": "3:02:54", "remaining_time": "4:06:51", "throughput": 1487.83, "total_tokens": 16328176} {"current_steps": 77380, "total_steps": 181800, "loss": 0.004, "lr": 3.551583671133554e-05, "epoch": 8.512651265126513, "percentage": 42.56, "elapsed_time": "3:02:55", "remaining_time": "4:06:50", "throughput": 1487.84, "total_tokens": 16329232} {"current_steps": 77385, "total_steps": 181800, "loss": 0.0763, "lr": 3.551365924783047e-05, "epoch": 8.513201320132014, "percentage": 42.57, "elapsed_time": "3:02:55", "remaining_time": "4:06:49", "throughput": 1487.84, "total_tokens": 16330352} {"current_steps": 77390, "total_steps": 181800, "loss": 0.0536, "lr": 3.551148168742606e-05, "epoch": 8.513751375137513, "percentage": 42.57, "elapsed_time": "3:02:56", "remaining_time": "4:06:48", "throughput": 1487.84, "total_tokens": 16331376} {"current_steps": 77395, "total_steps": 181800, "loss": 0.0323, "lr": 3.550930403014235e-05, "epoch": 8.514301430143014, "percentage": 42.57, "elapsed_time": "3:02:57", "remaining_time": "4:06:48", "throughput": 1487.84, "total_tokens": 16332400} {"current_steps": 77400, "total_steps": 181800, "loss": 0.0039, "lr": 3.550712627599945e-05, "epoch": 8.514851485148515, "percentage": 42.57, "elapsed_time": "3:02:57", "remaining_time": "4:06:47", "throughput": 1487.84, "total_tokens": 16333424} {"current_steps": 77405, "total_steps": 181800, "loss": 0.0522, "lr": 3.550494842501739e-05, "epoch": 8.515401540154015, "percentage": 42.58, "elapsed_time": "3:02:58", "remaining_time": "4:06:46", "throughput": 1487.85, "total_tokens": 16334544} {"current_steps": 77410, "total_steps": 181800, "loss": 0.0033, "lr": 3.550277047721627e-05, "epoch": 8.515951595159516, "percentage": 42.58, "elapsed_time": "3:02:59", "remaining_time": "4:06:45", "throughput": 1487.85, "total_tokens": 16335536} {"current_steps": 77415, "total_steps": 181800, "loss": 0.0097, "lr": 3.550059243261615e-05, "epoch": 8.516501650165017, "percentage": 42.58, "elapsed_time": "3:02:59", "remaining_time": "4:06:45", "throughput": 1487.84, "total_tokens": 16336528} {"current_steps": 77420, "total_steps": 181800, "loss": 0.0202, "lr": 3.549841429123712e-05, "epoch": 8.517051705170516, "percentage": 42.59, "elapsed_time": "3:03:00", "remaining_time": "4:06:44", "throughput": 1487.84, "total_tokens": 16337520} {"current_steps": 77425, "total_steps": 181800, "loss": 0.0035, "lr": 3.549623605309922e-05, "epoch": 8.517601760176017, "percentage": 42.59, "elapsed_time": "3:03:01", "remaining_time": "4:06:43", "throughput": 1487.85, "total_tokens": 16338640} {"current_steps": 77430, "total_steps": 181800, "loss": 0.0169, "lr": 3.5494057718222565e-05, "epoch": 8.518151815181518, "percentage": 42.59, "elapsed_time": "3:03:02", "remaining_time": "4:06:43", "throughput": 1487.85, "total_tokens": 16339728} {"current_steps": 77435, "total_steps": 181800, "loss": 0.0115, "lr": 3.549187928662721e-05, "epoch": 8.51870187018702, "percentage": 42.59, "elapsed_time": "3:03:02", "remaining_time": "4:06:42", "throughput": 1487.86, "total_tokens": 16340784} {"current_steps": 77440, "total_steps": 181800, "loss": 0.0161, "lr": 3.548970075833324e-05, "epoch": 8.519251925192519, "percentage": 42.6, "elapsed_time": "3:03:03", "remaining_time": "4:06:41", "throughput": 1487.86, "total_tokens": 16341808} {"current_steps": 77445, "total_steps": 181800, "loss": 0.1405, "lr": 3.548752213336074e-05, "epoch": 8.51980198019802, "percentage": 42.6, "elapsed_time": "3:03:04", "remaining_time": "4:06:40", "throughput": 1487.86, "total_tokens": 16342896} {"current_steps": 77450, "total_steps": 181800, "loss": 0.0665, "lr": 3.5485343411729775e-05, "epoch": 8.520352035203521, "percentage": 42.6, "elapsed_time": "3:03:04", "remaining_time": "4:06:40", "throughput": 1487.86, "total_tokens": 16343952} {"current_steps": 77455, "total_steps": 181800, "loss": 0.0556, "lr": 3.548316459346042e-05, "epoch": 8.52090209020902, "percentage": 42.6, "elapsed_time": "3:03:05", "remaining_time": "4:06:39", "throughput": 1487.88, "total_tokens": 16345104} {"current_steps": 77460, "total_steps": 181800, "loss": 0.0177, "lr": 3.548098567857278e-05, "epoch": 8.521452145214521, "percentage": 42.61, "elapsed_time": "3:03:06", "remaining_time": "4:06:38", "throughput": 1487.87, "total_tokens": 16346096} {"current_steps": 77465, "total_steps": 181800, "loss": 0.0036, "lr": 3.547880666708692e-05, "epoch": 8.522002200220022, "percentage": 42.61, "elapsed_time": "3:03:06", "remaining_time": "4:06:37", "throughput": 1487.87, "total_tokens": 16347120} {"current_steps": 77470, "total_steps": 181800, "loss": 0.0092, "lr": 3.5476627559022926e-05, "epoch": 8.522552255225522, "percentage": 42.61, "elapsed_time": "3:03:07", "remaining_time": "4:06:37", "throughput": 1487.88, "total_tokens": 16348208} {"current_steps": 77475, "total_steps": 181800, "loss": 0.0704, "lr": 3.547444835440089e-05, "epoch": 8.523102310231023, "percentage": 42.62, "elapsed_time": "3:03:08", "remaining_time": "4:06:36", "throughput": 1487.88, "total_tokens": 16349264} {"current_steps": 77480, "total_steps": 181800, "loss": 0.0281, "lr": 3.5472269053240884e-05, "epoch": 8.523652365236524, "percentage": 42.62, "elapsed_time": "3:03:08", "remaining_time": "4:06:35", "throughput": 1487.88, "total_tokens": 16350288} {"current_steps": 77485, "total_steps": 181800, "loss": 0.043, "lr": 3.5470089655563e-05, "epoch": 8.524202420242025, "percentage": 42.62, "elapsed_time": "3:03:09", "remaining_time": "4:06:34", "throughput": 1487.88, "total_tokens": 16351312} {"current_steps": 77490, "total_steps": 181800, "loss": 0.0573, "lr": 3.546791016138732e-05, "epoch": 8.524752475247524, "percentage": 42.62, "elapsed_time": "3:03:10", "remaining_time": "4:06:34", "throughput": 1487.88, "total_tokens": 16352336} {"current_steps": 77495, "total_steps": 181800, "loss": 0.0074, "lr": 3.546573057073394e-05, "epoch": 8.525302530253025, "percentage": 42.63, "elapsed_time": "3:03:11", "remaining_time": "4:06:33", "throughput": 1487.88, "total_tokens": 16353360} {"current_steps": 77500, "total_steps": 181800, "loss": 0.0179, "lr": 3.546355088362294e-05, "epoch": 8.525852585258527, "percentage": 42.63, "elapsed_time": "3:03:11", "remaining_time": "4:06:32", "throughput": 1487.88, "total_tokens": 16354416} {"current_steps": 77505, "total_steps": 181800, "loss": 0.0197, "lr": 3.5461371100074415e-05, "epoch": 8.526402640264026, "percentage": 42.63, "elapsed_time": "3:03:12", "remaining_time": "4:06:32", "throughput": 1487.88, "total_tokens": 16355408} {"current_steps": 77510, "total_steps": 181800, "loss": 0.0548, "lr": 3.545919122010845e-05, "epoch": 8.526952695269527, "percentage": 42.63, "elapsed_time": "3:03:13", "remaining_time": "4:06:31", "throughput": 1487.88, "total_tokens": 16356432} {"current_steps": 77515, "total_steps": 181800, "loss": 0.0767, "lr": 3.545701124374514e-05, "epoch": 8.527502750275028, "percentage": 42.64, "elapsed_time": "3:03:13", "remaining_time": "4:06:30", "throughput": 1487.88, "total_tokens": 16357520} {"current_steps": 77520, "total_steps": 181800, "loss": 0.0318, "lr": 3.545483117100458e-05, "epoch": 8.528052805280527, "percentage": 42.64, "elapsed_time": "3:03:14", "remaining_time": "4:06:29", "throughput": 1487.89, "total_tokens": 16358576} {"current_steps": 77525, "total_steps": 181800, "loss": 0.0287, "lr": 3.5452651001906854e-05, "epoch": 8.528602860286028, "percentage": 42.64, "elapsed_time": "3:03:15", "remaining_time": "4:06:29", "throughput": 1487.89, "total_tokens": 16359664} {"current_steps": 77530, "total_steps": 181800, "loss": 0.0017, "lr": 3.5450470736472054e-05, "epoch": 8.52915291529153, "percentage": 42.65, "elapsed_time": "3:03:15", "remaining_time": "4:06:28", "throughput": 1487.89, "total_tokens": 16360720} {"current_steps": 77535, "total_steps": 181800, "loss": 0.0571, "lr": 3.5448290374720285e-05, "epoch": 8.52970297029703, "percentage": 42.65, "elapsed_time": "3:03:16", "remaining_time": "4:06:27", "throughput": 1487.9, "total_tokens": 16361776} {"current_steps": 77540, "total_steps": 181800, "loss": 0.0728, "lr": 3.544610991667163e-05, "epoch": 8.53025302530253, "percentage": 42.65, "elapsed_time": "3:03:17", "remaining_time": "4:06:26", "throughput": 1487.9, "total_tokens": 16362800} {"current_steps": 77545, "total_steps": 181800, "loss": 0.0295, "lr": 3.54439293623462e-05, "epoch": 8.530803080308031, "percentage": 42.65, "elapsed_time": "3:03:17", "remaining_time": "4:06:26", "throughput": 1487.9, "total_tokens": 16363824} {"current_steps": 77550, "total_steps": 181800, "loss": 0.0159, "lr": 3.544174871176409e-05, "epoch": 8.531353135313532, "percentage": 42.66, "elapsed_time": "3:03:18", "remaining_time": "4:06:25", "throughput": 1487.9, "total_tokens": 16364912} {"current_steps": 77555, "total_steps": 181800, "loss": 0.0445, "lr": 3.543956796494538e-05, "epoch": 8.531903190319031, "percentage": 42.66, "elapsed_time": "3:03:19", "remaining_time": "4:06:24", "throughput": 1487.9, "total_tokens": 16365904} {"current_steps": 77560, "total_steps": 181800, "loss": 0.0099, "lr": 3.543738712191019e-05, "epoch": 8.532453245324533, "percentage": 42.66, "elapsed_time": "3:03:20", "remaining_time": "4:06:23", "throughput": 1487.9, "total_tokens": 16366960} {"current_steps": 77565, "total_steps": 181800, "loss": 0.0098, "lr": 3.543520618267861e-05, "epoch": 8.533003300330034, "percentage": 42.67, "elapsed_time": "3:03:20", "remaining_time": "4:06:23", "throughput": 1487.9, "total_tokens": 16367952} {"current_steps": 77570, "total_steps": 181800, "loss": 0.056, "lr": 3.543302514727074e-05, "epoch": 8.533553355335533, "percentage": 42.67, "elapsed_time": "3:03:21", "remaining_time": "4:06:22", "throughput": 1487.89, "total_tokens": 16368944} {"current_steps": 77575, "total_steps": 181800, "loss": 0.012, "lr": 3.5430844015706674e-05, "epoch": 8.534103410341034, "percentage": 42.67, "elapsed_time": "3:03:22", "remaining_time": "4:06:21", "throughput": 1487.9, "total_tokens": 16370000} {"current_steps": 77580, "total_steps": 181800, "loss": 0.0035, "lr": 3.542866278800654e-05, "epoch": 8.534653465346535, "percentage": 42.67, "elapsed_time": "3:03:22", "remaining_time": "4:06:21", "throughput": 1487.9, "total_tokens": 16371024} {"current_steps": 77585, "total_steps": 181800, "loss": 0.0286, "lr": 3.542648146419042e-05, "epoch": 8.535203520352034, "percentage": 42.68, "elapsed_time": "3:03:23", "remaining_time": "4:06:20", "throughput": 1487.89, "total_tokens": 16372016} {"current_steps": 77590, "total_steps": 181800, "loss": 0.1209, "lr": 3.542430004427842e-05, "epoch": 8.535753575357536, "percentage": 42.68, "elapsed_time": "3:03:24", "remaining_time": "4:06:19", "throughput": 1487.89, "total_tokens": 16373008} {"current_steps": 77595, "total_steps": 181800, "loss": 0.0091, "lr": 3.542211852829065e-05, "epoch": 8.536303630363037, "percentage": 42.68, "elapsed_time": "3:03:24", "remaining_time": "4:06:18", "throughput": 1487.89, "total_tokens": 16374000} {"current_steps": 77600, "total_steps": 181800, "loss": 0.0027, "lr": 3.5419936916247216e-05, "epoch": 8.536853685368538, "percentage": 42.68, "elapsed_time": "3:03:25", "remaining_time": "4:06:18", "throughput": 1487.89, "total_tokens": 16375088} {"current_steps": 77605, "total_steps": 181800, "loss": 0.063, "lr": 3.541775520816823e-05, "epoch": 8.537403740374037, "percentage": 42.69, "elapsed_time": "3:03:26", "remaining_time": "4:06:17", "throughput": 1487.9, "total_tokens": 16376176} {"current_steps": 77610, "total_steps": 181800, "loss": 0.0428, "lr": 3.541557340407379e-05, "epoch": 8.537953795379538, "percentage": 42.69, "elapsed_time": "3:03:26", "remaining_time": "4:06:16", "throughput": 1487.91, "total_tokens": 16377296} {"current_steps": 77615, "total_steps": 181800, "loss": 0.0018, "lr": 3.5413391503984e-05, "epoch": 8.53850385038504, "percentage": 42.69, "elapsed_time": "3:03:27", "remaining_time": "4:06:15", "throughput": 1487.91, "total_tokens": 16378384} {"current_steps": 77620, "total_steps": 181800, "loss": 0.055, "lr": 3.541120950791897e-05, "epoch": 8.539053905390539, "percentage": 42.7, "elapsed_time": "3:03:28", "remaining_time": "4:06:15", "throughput": 1487.91, "total_tokens": 16379440} {"current_steps": 77625, "total_steps": 181800, "loss": 0.0065, "lr": 3.5409027415898835e-05, "epoch": 8.53960396039604, "percentage": 42.7, "elapsed_time": "3:03:29", "remaining_time": "4:06:14", "throughput": 1487.92, "total_tokens": 16380560} {"current_steps": 77630, "total_steps": 181800, "loss": 0.0019, "lr": 3.5406845227943686e-05, "epoch": 8.54015401540154, "percentage": 42.7, "elapsed_time": "3:03:29", "remaining_time": "4:06:13", "throughput": 1487.93, "total_tokens": 16381680} {"current_steps": 77635, "total_steps": 181800, "loss": 0.0241, "lr": 3.5404662944073635e-05, "epoch": 8.54070407040704, "percentage": 42.7, "elapsed_time": "3:03:30", "remaining_time": "4:06:12", "throughput": 1487.94, "total_tokens": 16382800} {"current_steps": 77640, "total_steps": 181800, "loss": 0.0284, "lr": 3.5402480564308797e-05, "epoch": 8.541254125412541, "percentage": 42.71, "elapsed_time": "3:03:31", "remaining_time": "4:06:12", "throughput": 1487.94, "total_tokens": 16383856} {"current_steps": 77645, "total_steps": 181800, "loss": 0.0278, "lr": 3.540029808866929e-05, "epoch": 8.541804180418042, "percentage": 42.71, "elapsed_time": "3:03:31", "remaining_time": "4:06:11", "throughput": 1487.94, "total_tokens": 16384944} {"current_steps": 77650, "total_steps": 181800, "loss": 0.0267, "lr": 3.539811551717522e-05, "epoch": 8.542354235423542, "percentage": 42.71, "elapsed_time": "3:03:32", "remaining_time": "4:06:10", "throughput": 1487.95, "total_tokens": 16386000} {"current_steps": 77655, "total_steps": 181800, "loss": 0.02, "lr": 3.539593284984672e-05, "epoch": 8.542904290429043, "percentage": 42.71, "elapsed_time": "3:03:33", "remaining_time": "4:06:10", "throughput": 1487.95, "total_tokens": 16387024} {"current_steps": 77660, "total_steps": 181800, "loss": 0.05, "lr": 3.539375008670389e-05, "epoch": 8.543454345434544, "percentage": 42.72, "elapsed_time": "3:03:33", "remaining_time": "4:06:09", "throughput": 1487.95, "total_tokens": 16388080} {"current_steps": 77665, "total_steps": 181800, "loss": 0.0092, "lr": 3.539156722776685e-05, "epoch": 8.544004400440045, "percentage": 42.72, "elapsed_time": "3:03:34", "remaining_time": "4:06:08", "throughput": 1487.95, "total_tokens": 16389104} {"current_steps": 77670, "total_steps": 181800, "loss": 0.096, "lr": 3.538938427305573e-05, "epoch": 8.544554455445544, "percentage": 42.72, "elapsed_time": "3:03:35", "remaining_time": "4:06:07", "throughput": 1487.96, "total_tokens": 16390192} {"current_steps": 77675, "total_steps": 181800, "loss": 0.0315, "lr": 3.5387201222590624e-05, "epoch": 8.545104510451045, "percentage": 42.73, "elapsed_time": "3:03:35", "remaining_time": "4:06:07", "throughput": 1487.96, "total_tokens": 16391280} {"current_steps": 77680, "total_steps": 181800, "loss": 0.1236, "lr": 3.538501807639168e-05, "epoch": 8.545654565456546, "percentage": 42.73, "elapsed_time": "3:03:36", "remaining_time": "4:06:06", "throughput": 1487.96, "total_tokens": 16392336} {"current_steps": 77685, "total_steps": 181800, "loss": 0.0861, "lr": 3.538283483447901e-05, "epoch": 8.546204620462046, "percentage": 42.73, "elapsed_time": "3:03:37", "remaining_time": "4:06:05", "throughput": 1487.97, "total_tokens": 16393456} {"current_steps": 77690, "total_steps": 181800, "loss": 0.0904, "lr": 3.538065149687272e-05, "epoch": 8.546754675467547, "percentage": 42.73, "elapsed_time": "3:03:37", "remaining_time": "4:06:04", "throughput": 1487.98, "total_tokens": 16394544} {"current_steps": 77695, "total_steps": 181800, "loss": 0.0181, "lr": 3.537846806359296e-05, "epoch": 8.547304730473048, "percentage": 42.74, "elapsed_time": "3:03:38", "remaining_time": "4:06:04", "throughput": 1487.98, "total_tokens": 16395568} {"current_steps": 77700, "total_steps": 181800, "loss": 0.0407, "lr": 3.537628453465984e-05, "epoch": 8.547854785478547, "percentage": 42.74, "elapsed_time": "3:03:39", "remaining_time": "4:06:03", "throughput": 1487.99, "total_tokens": 16396688} {"current_steps": 77705, "total_steps": 181800, "loss": 0.0111, "lr": 3.537410091009348e-05, "epoch": 8.548404840484048, "percentage": 42.74, "elapsed_time": "3:03:40", "remaining_time": "4:06:02", "throughput": 1488.0, "total_tokens": 16397808} {"current_steps": 77710, "total_steps": 181800, "loss": 0.1062, "lr": 3.537191718991401e-05, "epoch": 8.54895489548955, "percentage": 42.74, "elapsed_time": "3:03:40", "remaining_time": "4:06:01", "throughput": 1488.0, "total_tokens": 16398896} {"current_steps": 77715, "total_steps": 181800, "loss": 0.0075, "lr": 3.536973337414155e-05, "epoch": 8.549504950495049, "percentage": 42.75, "elapsed_time": "3:03:41", "remaining_time": "4:06:01", "throughput": 1488.0, "total_tokens": 16399952} {"current_steps": 77720, "total_steps": 181800, "loss": 0.0146, "lr": 3.536754946279624e-05, "epoch": 8.55005500550055, "percentage": 42.75, "elapsed_time": "3:03:42", "remaining_time": "4:06:00", "throughput": 1488.01, "total_tokens": 16401072} {"current_steps": 77725, "total_steps": 181800, "loss": 0.0968, "lr": 3.53653654558982e-05, "epoch": 8.55060506050605, "percentage": 42.75, "elapsed_time": "3:03:42", "remaining_time": "4:05:59", "throughput": 1488.01, "total_tokens": 16402096} {"current_steps": 77730, "total_steps": 181800, "loss": 0.029, "lr": 3.536318135346756e-05, "epoch": 8.551155115511552, "percentage": 42.76, "elapsed_time": "3:03:43", "remaining_time": "4:05:58", "throughput": 1488.02, "total_tokens": 16403184} {"current_steps": 77735, "total_steps": 181800, "loss": 0.0553, "lr": 3.536099715552446e-05, "epoch": 8.551705170517051, "percentage": 42.76, "elapsed_time": "3:03:44", "remaining_time": "4:05:58", "throughput": 1488.02, "total_tokens": 16404272} {"current_steps": 77740, "total_steps": 181800, "loss": 0.075, "lr": 3.535881286208901e-05, "epoch": 8.552255225522552, "percentage": 42.76, "elapsed_time": "3:03:44", "remaining_time": "4:05:57", "throughput": 1488.02, "total_tokens": 16405296} {"current_steps": 77745, "total_steps": 181800, "loss": 0.0067, "lr": 3.5356628473181345e-05, "epoch": 8.552805280528053, "percentage": 42.76, "elapsed_time": "3:03:45", "remaining_time": "4:05:56", "throughput": 1488.03, "total_tokens": 16406352} {"current_steps": 77750, "total_steps": 181800, "loss": 0.0033, "lr": 3.535444398882162e-05, "epoch": 8.553355335533553, "percentage": 42.77, "elapsed_time": "3:03:46", "remaining_time": "4:05:56", "throughput": 1488.03, "total_tokens": 16407408} {"current_steps": 77755, "total_steps": 181800, "loss": 0.029, "lr": 3.535225940902995e-05, "epoch": 8.553905390539054, "percentage": 42.77, "elapsed_time": "3:03:46", "remaining_time": "4:05:55", "throughput": 1488.03, "total_tokens": 16408400} {"current_steps": 77760, "total_steps": 181800, "loss": 0.0195, "lr": 3.5350074733826466e-05, "epoch": 8.554455445544555, "percentage": 42.77, "elapsed_time": "3:03:47", "remaining_time": "4:05:54", "throughput": 1488.03, "total_tokens": 16409456} {"current_steps": 77765, "total_steps": 181800, "loss": 0.0603, "lr": 3.5347889963231316e-05, "epoch": 8.555005500550054, "percentage": 42.78, "elapsed_time": "3:03:48", "remaining_time": "4:05:53", "throughput": 1488.04, "total_tokens": 16410576} {"current_steps": 77770, "total_steps": 181800, "loss": 0.1571, "lr": 3.5345705097264634e-05, "epoch": 8.555555555555555, "percentage": 42.78, "elapsed_time": "3:03:49", "remaining_time": "4:05:53", "throughput": 1488.03, "total_tokens": 16411568} {"current_steps": 77775, "total_steps": 181800, "loss": 0.1002, "lr": 3.5343520135946544e-05, "epoch": 8.556105610561056, "percentage": 42.78, "elapsed_time": "3:03:49", "remaining_time": "4:05:52", "throughput": 1488.03, "total_tokens": 16412592} {"current_steps": 77780, "total_steps": 181800, "loss": 0.027, "lr": 3.5341335079297194e-05, "epoch": 8.556655665566556, "percentage": 42.78, "elapsed_time": "3:03:50", "remaining_time": "4:05:51", "throughput": 1488.04, "total_tokens": 16413680} {"current_steps": 77785, "total_steps": 181800, "loss": 0.0325, "lr": 3.533914992733672e-05, "epoch": 8.557205720572057, "percentage": 42.79, "elapsed_time": "3:03:51", "remaining_time": "4:05:50", "throughput": 1488.05, "total_tokens": 16414768} {"current_steps": 77790, "total_steps": 181800, "loss": 0.0028, "lr": 3.533696468008526e-05, "epoch": 8.557755775577558, "percentage": 42.79, "elapsed_time": "3:03:51", "remaining_time": "4:05:50", "throughput": 1488.04, "total_tokens": 16415728} {"current_steps": 77795, "total_steps": 181800, "loss": 0.0724, "lr": 3.533477933756297e-05, "epoch": 8.558305830583059, "percentage": 42.79, "elapsed_time": "3:03:52", "remaining_time": "4:05:49", "throughput": 1488.05, "total_tokens": 16416880} {"current_steps": 77800, "total_steps": 181800, "loss": 0.0354, "lr": 3.533259389978997e-05, "epoch": 8.558855885588558, "percentage": 42.79, "elapsed_time": "3:03:53", "remaining_time": "4:05:48", "throughput": 1488.06, "total_tokens": 16417968} {"current_steps": 77805, "total_steps": 181800, "loss": 0.0131, "lr": 3.5330408366786406e-05, "epoch": 8.55940594059406, "percentage": 42.8, "elapsed_time": "3:03:53", "remaining_time": "4:05:47", "throughput": 1488.06, "total_tokens": 16419056} {"current_steps": 77810, "total_steps": 181800, "loss": 0.0499, "lr": 3.532822273857242e-05, "epoch": 8.55995599559956, "percentage": 42.8, "elapsed_time": "3:03:54", "remaining_time": "4:05:47", "throughput": 1488.07, "total_tokens": 16420112} {"current_steps": 77815, "total_steps": 181800, "loss": 0.0272, "lr": 3.532603701516817e-05, "epoch": 8.56050605060506, "percentage": 42.8, "elapsed_time": "3:03:55", "remaining_time": "4:05:46", "throughput": 1488.07, "total_tokens": 16421136} {"current_steps": 77820, "total_steps": 181800, "loss": 0.0028, "lr": 3.5323851196593794e-05, "epoch": 8.561056105610561, "percentage": 42.81, "elapsed_time": "3:03:55", "remaining_time": "4:05:45", "throughput": 1488.07, "total_tokens": 16422224} {"current_steps": 77825, "total_steps": 181800, "loss": 0.0085, "lr": 3.532166528286943e-05, "epoch": 8.561606160616062, "percentage": 42.81, "elapsed_time": "3:03:56", "remaining_time": "4:05:45", "throughput": 1488.08, "total_tokens": 16423344} {"current_steps": 77830, "total_steps": 181800, "loss": 0.0159, "lr": 3.5319479274015235e-05, "epoch": 8.562156215621561, "percentage": 42.81, "elapsed_time": "3:03:57", "remaining_time": "4:05:44", "throughput": 1488.08, "total_tokens": 16424336} {"current_steps": 77835, "total_steps": 181800, "loss": 0.0712, "lr": 3.531729317005134e-05, "epoch": 8.562706270627062, "percentage": 42.81, "elapsed_time": "3:03:57", "remaining_time": "4:05:43", "throughput": 1488.08, "total_tokens": 16425424} {"current_steps": 77840, "total_steps": 181800, "loss": 0.0228, "lr": 3.531510697099791e-05, "epoch": 8.563256325632564, "percentage": 42.82, "elapsed_time": "3:03:58", "remaining_time": "4:05:42", "throughput": 1488.08, "total_tokens": 16426480} {"current_steps": 77845, "total_steps": 181800, "loss": 0.1499, "lr": 3.53129206768751e-05, "epoch": 8.563806380638063, "percentage": 42.82, "elapsed_time": "3:03:59", "remaining_time": "4:05:42", "throughput": 1488.09, "total_tokens": 16427568} {"current_steps": 77850, "total_steps": 181800, "loss": 0.0045, "lr": 3.531073428770304e-05, "epoch": 8.564356435643564, "percentage": 42.82, "elapsed_time": "3:04:00", "remaining_time": "4:05:41", "throughput": 1488.09, "total_tokens": 16428592} {"current_steps": 77855, "total_steps": 181800, "loss": 0.0048, "lr": 3.530854780350189e-05, "epoch": 8.564906490649065, "percentage": 42.82, "elapsed_time": "3:04:00", "remaining_time": "4:05:40", "throughput": 1488.09, "total_tokens": 16429680} {"current_steps": 77860, "total_steps": 181800, "loss": 0.0763, "lr": 3.53063612242918e-05, "epoch": 8.565456545654566, "percentage": 42.83, "elapsed_time": "3:04:01", "remaining_time": "4:05:39", "throughput": 1488.09, "total_tokens": 16430704} {"current_steps": 77865, "total_steps": 181800, "loss": 0.0057, "lr": 3.5304174550092926e-05, "epoch": 8.566006600660065, "percentage": 42.83, "elapsed_time": "3:04:02", "remaining_time": "4:05:39", "throughput": 1488.1, "total_tokens": 16431792} {"current_steps": 77870, "total_steps": 181800, "loss": 0.0392, "lr": 3.5301987780925413e-05, "epoch": 8.566556655665567, "percentage": 42.83, "elapsed_time": "3:04:02", "remaining_time": "4:05:38", "throughput": 1488.1, "total_tokens": 16432848} {"current_steps": 77875, "total_steps": 181800, "loss": 0.0235, "lr": 3.5299800916809425e-05, "epoch": 8.567106710671068, "percentage": 42.84, "elapsed_time": "3:04:03", "remaining_time": "4:05:37", "throughput": 1488.11, "total_tokens": 16433936} {"current_steps": 77880, "total_steps": 181800, "loss": 0.1178, "lr": 3.529761395776512e-05, "epoch": 8.567656765676567, "percentage": 42.84, "elapsed_time": "3:04:04", "remaining_time": "4:05:36", "throughput": 1488.11, "total_tokens": 16435024} {"current_steps": 77885, "total_steps": 181800, "loss": 0.018, "lr": 3.529542690381265e-05, "epoch": 8.568206820682068, "percentage": 42.84, "elapsed_time": "3:04:04", "remaining_time": "4:05:36", "throughput": 1488.12, "total_tokens": 16436080} {"current_steps": 77890, "total_steps": 181800, "loss": 0.0136, "lr": 3.5293239754972165e-05, "epoch": 8.56875687568757, "percentage": 42.84, "elapsed_time": "3:04:05", "remaining_time": "4:05:35", "throughput": 1488.13, "total_tokens": 16437200} {"current_steps": 77895, "total_steps": 181800, "loss": 0.0359, "lr": 3.529105251126383e-05, "epoch": 8.569306930693068, "percentage": 42.85, "elapsed_time": "3:04:06", "remaining_time": "4:05:34", "throughput": 1488.12, "total_tokens": 16438192} {"current_steps": 77900, "total_steps": 181800, "loss": 0.113, "lr": 3.52888651727078e-05, "epoch": 8.56985698569857, "percentage": 42.85, "elapsed_time": "3:04:06", "remaining_time": "4:05:33", "throughput": 1488.12, "total_tokens": 16439152} {"current_steps": 77905, "total_steps": 181800, "loss": 0.0807, "lr": 3.528667773932424e-05, "epoch": 8.57040704070407, "percentage": 42.85, "elapsed_time": "3:04:07", "remaining_time": "4:05:33", "throughput": 1488.12, "total_tokens": 16440240} {"current_steps": 77910, "total_steps": 181800, "loss": 0.0129, "lr": 3.5284490211133306e-05, "epoch": 8.570957095709572, "percentage": 42.85, "elapsed_time": "3:04:08", "remaining_time": "4:05:32", "throughput": 1488.12, "total_tokens": 16441264} {"current_steps": 77915, "total_steps": 181800, "loss": 0.0286, "lr": 3.528230258815516e-05, "epoch": 8.571507150715071, "percentage": 42.86, "elapsed_time": "3:04:09", "remaining_time": "4:05:31", "throughput": 1488.12, "total_tokens": 16442320} {"current_steps": 77920, "total_steps": 181800, "loss": 0.0105, "lr": 3.5280114870409965e-05, "epoch": 8.572057205720572, "percentage": 42.86, "elapsed_time": "3:04:09", "remaining_time": "4:05:31", "throughput": 1488.13, "total_tokens": 16443408} {"current_steps": 77925, "total_steps": 181800, "loss": 0.0059, "lr": 3.527792705791788e-05, "epoch": 8.572607260726073, "percentage": 42.86, "elapsed_time": "3:04:10", "remaining_time": "4:05:30", "throughput": 1488.13, "total_tokens": 16444464} {"current_steps": 77930, "total_steps": 181800, "loss": 0.0074, "lr": 3.527573915069908e-05, "epoch": 8.573157315731573, "percentage": 42.87, "elapsed_time": "3:04:11", "remaining_time": "4:05:29", "throughput": 1488.13, "total_tokens": 16445520} {"current_steps": 77935, "total_steps": 181800, "loss": 0.0469, "lr": 3.5273551148773714e-05, "epoch": 8.573707370737074, "percentage": 42.87, "elapsed_time": "3:04:11", "remaining_time": "4:05:28", "throughput": 1488.14, "total_tokens": 16446576} {"current_steps": 77940, "total_steps": 181800, "loss": 0.1515, "lr": 3.527136305216197e-05, "epoch": 8.574257425742575, "percentage": 42.87, "elapsed_time": "3:04:12", "remaining_time": "4:05:28", "throughput": 1488.15, "total_tokens": 16447696} {"current_steps": 77945, "total_steps": 181800, "loss": 0.1674, "lr": 3.5269174860883996e-05, "epoch": 8.574807480748074, "percentage": 42.87, "elapsed_time": "3:04:13", "remaining_time": "4:05:27", "throughput": 1488.14, "total_tokens": 16448720} {"current_steps": 77950, "total_steps": 181800, "loss": 0.0453, "lr": 3.526698657495996e-05, "epoch": 8.575357535753575, "percentage": 42.88, "elapsed_time": "3:04:13", "remaining_time": "4:05:26", "throughput": 1488.15, "total_tokens": 16449808} {"current_steps": 77955, "total_steps": 181800, "loss": 0.0315, "lr": 3.5264798194410036e-05, "epoch": 8.575907590759076, "percentage": 42.88, "elapsed_time": "3:04:14", "remaining_time": "4:05:25", "throughput": 1488.15, "total_tokens": 16450864} {"current_steps": 77960, "total_steps": 181800, "loss": 0.0526, "lr": 3.5262609719254397e-05, "epoch": 8.576457645764577, "percentage": 42.88, "elapsed_time": "3:04:15", "remaining_time": "4:05:25", "throughput": 1488.16, "total_tokens": 16451952} {"current_steps": 77965, "total_steps": 181800, "loss": 0.0039, "lr": 3.5260421149513204e-05, "epoch": 8.577007700770077, "percentage": 42.89, "elapsed_time": "3:04:15", "remaining_time": "4:05:24", "throughput": 1488.16, "total_tokens": 16453040} {"current_steps": 77970, "total_steps": 181800, "loss": 0.0607, "lr": 3.5258232485206644e-05, "epoch": 8.577557755775578, "percentage": 42.89, "elapsed_time": "3:04:16", "remaining_time": "4:05:23", "throughput": 1488.16, "total_tokens": 16454000} {"current_steps": 77975, "total_steps": 181800, "loss": 0.0267, "lr": 3.525604372635486e-05, "epoch": 8.578107810781079, "percentage": 42.89, "elapsed_time": "3:04:17", "remaining_time": "4:05:22", "throughput": 1488.16, "total_tokens": 16455024} {"current_steps": 77980, "total_steps": 181800, "loss": 0.0052, "lr": 3.525385487297805e-05, "epoch": 8.578657865786578, "percentage": 42.89, "elapsed_time": "3:04:18", "remaining_time": "4:05:22", "throughput": 1488.16, "total_tokens": 16456112} {"current_steps": 77985, "total_steps": 181800, "loss": 0.0407, "lr": 3.525166592509639e-05, "epoch": 8.57920792079208, "percentage": 42.9, "elapsed_time": "3:04:18", "remaining_time": "4:05:21", "throughput": 1488.17, "total_tokens": 16457168} {"current_steps": 77990, "total_steps": 181800, "loss": 0.0639, "lr": 3.524947688273003e-05, "epoch": 8.57975797579758, "percentage": 42.9, "elapsed_time": "3:04:19", "remaining_time": "4:05:20", "throughput": 1488.17, "total_tokens": 16458224} {"current_steps": 77995, "total_steps": 181800, "loss": 0.0693, "lr": 3.524728774589917e-05, "epoch": 8.58030803080308, "percentage": 42.9, "elapsed_time": "3:04:20", "remaining_time": "4:05:20", "throughput": 1488.17, "total_tokens": 16459312} {"current_steps": 78000, "total_steps": 181800, "loss": 0.0161, "lr": 3.524509851462397e-05, "epoch": 8.58085808580858, "percentage": 42.9, "elapsed_time": "3:04:20", "remaining_time": "4:05:19", "throughput": 1488.18, "total_tokens": 16460368} {"current_steps": 78005, "total_steps": 181800, "loss": 0.0241, "lr": 3.524290918892462e-05, "epoch": 8.581408140814082, "percentage": 42.91, "elapsed_time": "3:04:21", "remaining_time": "4:05:18", "throughput": 1488.18, "total_tokens": 16461488} {"current_steps": 78010, "total_steps": 181800, "loss": 0.0062, "lr": 3.524071976882129e-05, "epoch": 8.581958195819581, "percentage": 42.91, "elapsed_time": "3:04:22", "remaining_time": "4:05:17", "throughput": 1488.18, "total_tokens": 16462512} {"current_steps": 78015, "total_steps": 181800, "loss": 0.0122, "lr": 3.523853025433415e-05, "epoch": 8.582508250825082, "percentage": 42.91, "elapsed_time": "3:04:22", "remaining_time": "4:05:17", "throughput": 1488.19, "total_tokens": 16463568} {"current_steps": 78020, "total_steps": 181800, "loss": 0.0107, "lr": 3.523634064548339e-05, "epoch": 8.583058305830583, "percentage": 42.92, "elapsed_time": "3:04:23", "remaining_time": "4:05:16", "throughput": 1488.19, "total_tokens": 16464656} {"current_steps": 78025, "total_steps": 181800, "loss": 0.0573, "lr": 3.5234150942289194e-05, "epoch": 8.583608360836084, "percentage": 42.92, "elapsed_time": "3:04:24", "remaining_time": "4:05:15", "throughput": 1488.2, "total_tokens": 16465776} {"current_steps": 78030, "total_steps": 181800, "loss": 0.0045, "lr": 3.523196114477174e-05, "epoch": 8.584158415841584, "percentage": 42.92, "elapsed_time": "3:04:24", "remaining_time": "4:05:14", "throughput": 1488.21, "total_tokens": 16466864} {"current_steps": 78035, "total_steps": 181800, "loss": 0.0023, "lr": 3.522977125295122e-05, "epoch": 8.584708470847085, "percentage": 42.92, "elapsed_time": "3:04:25", "remaining_time": "4:05:14", "throughput": 1488.2, "total_tokens": 16467888} {"current_steps": 78040, "total_steps": 181800, "loss": 0.0034, "lr": 3.522758126684779e-05, "epoch": 8.585258525852586, "percentage": 42.93, "elapsed_time": "3:04:26", "remaining_time": "4:05:13", "throughput": 1488.2, "total_tokens": 16468912} {"current_steps": 78045, "total_steps": 181800, "loss": 0.0301, "lr": 3.522539118648166e-05, "epoch": 8.585808580858085, "percentage": 42.93, "elapsed_time": "3:04:26", "remaining_time": "4:05:12", "throughput": 1488.21, "total_tokens": 16470032} {"current_steps": 78050, "total_steps": 181800, "loss": 0.0517, "lr": 3.5223201011873004e-05, "epoch": 8.586358635863586, "percentage": 42.93, "elapsed_time": "3:04:27", "remaining_time": "4:05:11", "throughput": 1488.22, "total_tokens": 16471088} {"current_steps": 78055, "total_steps": 181800, "loss": 0.0129, "lr": 3.522101074304201e-05, "epoch": 8.586908690869087, "percentage": 42.93, "elapsed_time": "3:04:28", "remaining_time": "4:05:11", "throughput": 1488.22, "total_tokens": 16472144} {"current_steps": 78060, "total_steps": 181800, "loss": 0.0066, "lr": 3.5218820380008874e-05, "epoch": 8.587458745874587, "percentage": 42.94, "elapsed_time": "3:04:29", "remaining_time": "4:05:10", "throughput": 1488.23, "total_tokens": 16473264} {"current_steps": 78065, "total_steps": 181800, "loss": 0.0239, "lr": 3.521662992279376e-05, "epoch": 8.588008800880088, "percentage": 42.94, "elapsed_time": "3:04:29", "remaining_time": "4:05:09", "throughput": 1488.23, "total_tokens": 16474288} {"current_steps": 78070, "total_steps": 181800, "loss": 0.0734, "lr": 3.521443937141687e-05, "epoch": 8.588558855885589, "percentage": 42.94, "elapsed_time": "3:04:30", "remaining_time": "4:05:09", "throughput": 1488.23, "total_tokens": 16475312} {"current_steps": 78075, "total_steps": 181800, "loss": 0.0059, "lr": 3.5212248725898406e-05, "epoch": 8.589108910891088, "percentage": 42.95, "elapsed_time": "3:04:31", "remaining_time": "4:05:08", "throughput": 1488.23, "total_tokens": 16476336} {"current_steps": 78080, "total_steps": 181800, "loss": 0.0043, "lr": 3.521005798625854e-05, "epoch": 8.58965896589659, "percentage": 42.95, "elapsed_time": "3:04:31", "remaining_time": "4:05:07", "throughput": 1488.23, "total_tokens": 16477392} {"current_steps": 78085, "total_steps": 181800, "loss": 0.0372, "lr": 3.520786715251747e-05, "epoch": 8.59020902090209, "percentage": 42.95, "elapsed_time": "3:04:32", "remaining_time": "4:05:06", "throughput": 1488.23, "total_tokens": 16478448} {"current_steps": 78090, "total_steps": 181800, "loss": 0.0541, "lr": 3.5205676224695386e-05, "epoch": 8.590759075907592, "percentage": 42.95, "elapsed_time": "3:04:33", "remaining_time": "4:05:06", "throughput": 1488.24, "total_tokens": 16479536} {"current_steps": 78095, "total_steps": 181800, "loss": 0.0239, "lr": 3.520348520281247e-05, "epoch": 8.591309130913091, "percentage": 42.96, "elapsed_time": "3:04:33", "remaining_time": "4:05:05", "throughput": 1488.24, "total_tokens": 16480592} {"current_steps": 78100, "total_steps": 181800, "loss": 0.0122, "lr": 3.520129408688894e-05, "epoch": 8.591859185918592, "percentage": 42.96, "elapsed_time": "3:04:34", "remaining_time": "4:05:04", "throughput": 1488.25, "total_tokens": 16481712} {"current_steps": 78105, "total_steps": 181800, "loss": 0.0094, "lr": 3.5199102876944986e-05, "epoch": 8.592409240924093, "percentage": 42.96, "elapsed_time": "3:04:35", "remaining_time": "4:05:03", "throughput": 1488.25, "total_tokens": 16482768} {"current_steps": 78110, "total_steps": 181800, "loss": 0.0174, "lr": 3.519691157300077e-05, "epoch": 8.592959295929592, "percentage": 42.96, "elapsed_time": "3:04:35", "remaining_time": "4:05:03", "throughput": 1488.26, "total_tokens": 16483920} {"current_steps": 78115, "total_steps": 181800, "loss": 0.0307, "lr": 3.519472017507653e-05, "epoch": 8.593509350935093, "percentage": 42.97, "elapsed_time": "3:04:36", "remaining_time": "4:05:02", "throughput": 1488.26, "total_tokens": 16485008} {"current_steps": 78120, "total_steps": 181800, "loss": 0.0969, "lr": 3.5192528683192444e-05, "epoch": 8.594059405940595, "percentage": 42.97, "elapsed_time": "3:04:37", "remaining_time": "4:05:01", "throughput": 1488.27, "total_tokens": 16486128} {"current_steps": 78125, "total_steps": 181800, "loss": 0.0109, "lr": 3.519033709736871e-05, "epoch": 8.594609460946094, "percentage": 42.97, "elapsed_time": "3:04:38", "remaining_time": "4:05:01", "throughput": 1488.27, "total_tokens": 16487152} {"current_steps": 78130, "total_steps": 181800, "loss": 0.0234, "lr": 3.5188145417625535e-05, "epoch": 8.595159515951595, "percentage": 42.98, "elapsed_time": "3:04:38", "remaining_time": "4:05:00", "throughput": 1488.27, "total_tokens": 16488176} {"current_steps": 78135, "total_steps": 181800, "loss": 0.0243, "lr": 3.518595364398311e-05, "epoch": 8.595709570957096, "percentage": 42.98, "elapsed_time": "3:04:39", "remaining_time": "4:04:59", "throughput": 1488.27, "total_tokens": 16489200} {"current_steps": 78140, "total_steps": 181800, "loss": 0.0526, "lr": 3.5183761776461625e-05, "epoch": 8.596259625962595, "percentage": 42.98, "elapsed_time": "3:04:40", "remaining_time": "4:04:58", "throughput": 1488.28, "total_tokens": 16490288} {"current_steps": 78145, "total_steps": 181800, "loss": 0.0215, "lr": 3.51815698150813e-05, "epoch": 8.596809680968097, "percentage": 42.98, "elapsed_time": "3:04:40", "remaining_time": "4:04:58", "throughput": 1488.28, "total_tokens": 16491344} {"current_steps": 78150, "total_steps": 181800, "loss": 0.0105, "lr": 3.517937775986234e-05, "epoch": 8.597359735973598, "percentage": 42.99, "elapsed_time": "3:04:41", "remaining_time": "4:04:57", "throughput": 1488.29, "total_tokens": 16492432} {"current_steps": 78155, "total_steps": 181800, "loss": 0.0495, "lr": 3.517718561082493e-05, "epoch": 8.597909790979099, "percentage": 42.99, "elapsed_time": "3:04:42", "remaining_time": "4:04:56", "throughput": 1488.29, "total_tokens": 16493552} {"current_steps": 78160, "total_steps": 181800, "loss": 0.0784, "lr": 3.517499336798929e-05, "epoch": 8.598459845984598, "percentage": 42.99, "elapsed_time": "3:04:42", "remaining_time": "4:04:55", "throughput": 1488.29, "total_tokens": 16494576} {"current_steps": 78165, "total_steps": 181800, "loss": 0.0629, "lr": 3.5172801031375624e-05, "epoch": 8.599009900990099, "percentage": 43.0, "elapsed_time": "3:04:43", "remaining_time": "4:04:55", "throughput": 1488.29, "total_tokens": 16495568} {"current_steps": 78170, "total_steps": 181800, "loss": 0.0452, "lr": 3.5170608601004124e-05, "epoch": 8.5995599559956, "percentage": 43.0, "elapsed_time": "3:04:44", "remaining_time": "4:04:54", "throughput": 1488.3, "total_tokens": 16496656} {"current_steps": 78175, "total_steps": 181800, "loss": 0.023, "lr": 3.516841607689501e-05, "epoch": 8.6001100110011, "percentage": 43.0, "elapsed_time": "3:04:44", "remaining_time": "4:04:53", "throughput": 1488.3, "total_tokens": 16497712} {"current_steps": 78180, "total_steps": 181800, "loss": 0.1023, "lr": 3.5166223459068484e-05, "epoch": 8.6006600660066, "percentage": 43.0, "elapsed_time": "3:04:45", "remaining_time": "4:04:52", "throughput": 1488.3, "total_tokens": 16498800} {"current_steps": 78185, "total_steps": 181800, "loss": 0.0604, "lr": 3.5164030747544746e-05, "epoch": 8.601210121012102, "percentage": 43.01, "elapsed_time": "3:04:46", "remaining_time": "4:04:52", "throughput": 1488.3, "total_tokens": 16499792} {"current_steps": 78190, "total_steps": 181800, "loss": 0.0086, "lr": 3.516183794234402e-05, "epoch": 8.601760176017601, "percentage": 43.01, "elapsed_time": "3:04:47", "remaining_time": "4:04:51", "throughput": 1488.3, "total_tokens": 16500848} {"current_steps": 78195, "total_steps": 181800, "loss": 0.0175, "lr": 3.515964504348651e-05, "epoch": 8.602310231023102, "percentage": 43.01, "elapsed_time": "3:04:47", "remaining_time": "4:04:50", "throughput": 1488.3, "total_tokens": 16501872} {"current_steps": 78200, "total_steps": 181800, "loss": 0.0096, "lr": 3.5157452050992426e-05, "epoch": 8.602860286028603, "percentage": 43.01, "elapsed_time": "3:04:48", "remaining_time": "4:04:50", "throughput": 1488.31, "total_tokens": 16502992} {"current_steps": 78205, "total_steps": 181800, "loss": 0.0635, "lr": 3.515525896488198e-05, "epoch": 8.603410341034103, "percentage": 43.02, "elapsed_time": "3:04:49", "remaining_time": "4:04:49", "throughput": 1488.31, "total_tokens": 16504048} {"current_steps": 78210, "total_steps": 181800, "loss": 0.0041, "lr": 3.515306578517538e-05, "epoch": 8.603960396039604, "percentage": 43.02, "elapsed_time": "3:04:49", "remaining_time": "4:04:48", "throughput": 1488.32, "total_tokens": 16505104} {"current_steps": 78215, "total_steps": 181800, "loss": 0.0177, "lr": 3.5150872511892855e-05, "epoch": 8.604510451045105, "percentage": 43.02, "elapsed_time": "3:04:50", "remaining_time": "4:04:47", "throughput": 1488.32, "total_tokens": 16506160} {"current_steps": 78220, "total_steps": 181800, "loss": 0.0054, "lr": 3.51486791450546e-05, "epoch": 8.605060506050606, "percentage": 43.03, "elapsed_time": "3:04:51", "remaining_time": "4:04:47", "throughput": 1488.32, "total_tokens": 16507248} {"current_steps": 78225, "total_steps": 181800, "loss": 0.0032, "lr": 3.514648568468085e-05, "epoch": 8.605610561056105, "percentage": 43.03, "elapsed_time": "3:04:51", "remaining_time": "4:04:46", "throughput": 1488.33, "total_tokens": 16508304} {"current_steps": 78230, "total_steps": 181800, "loss": 0.1725, "lr": 3.51442921307918e-05, "epoch": 8.606160616061606, "percentage": 43.03, "elapsed_time": "3:04:52", "remaining_time": "4:04:45", "throughput": 1488.33, "total_tokens": 16509328} {"current_steps": 78235, "total_steps": 181800, "loss": 0.0461, "lr": 3.5142098483407684e-05, "epoch": 8.606710671067107, "percentage": 43.03, "elapsed_time": "3:04:53", "remaining_time": "4:04:44", "throughput": 1488.33, "total_tokens": 16510416} {"current_steps": 78240, "total_steps": 181800, "loss": 0.0615, "lr": 3.51399047425487e-05, "epoch": 8.607260726072607, "percentage": 43.04, "elapsed_time": "3:04:53", "remaining_time": "4:04:44", "throughput": 1488.33, "total_tokens": 16511472} {"current_steps": 78245, "total_steps": 181800, "loss": 0.0433, "lr": 3.51377109082351e-05, "epoch": 8.607810781078108, "percentage": 43.04, "elapsed_time": "3:04:54", "remaining_time": "4:04:43", "throughput": 1488.34, "total_tokens": 16512528} {"current_steps": 78250, "total_steps": 181800, "loss": 0.0019, "lr": 3.5135516980487074e-05, "epoch": 8.608360836083609, "percentage": 43.04, "elapsed_time": "3:04:55", "remaining_time": "4:04:42", "throughput": 1488.33, "total_tokens": 16513520} {"current_steps": 78255, "total_steps": 181800, "loss": 0.0254, "lr": 3.513332295932484e-05, "epoch": 8.608910891089108, "percentage": 43.04, "elapsed_time": "3:04:56", "remaining_time": "4:04:41", "throughput": 1488.34, "total_tokens": 16514640} {"current_steps": 78260, "total_steps": 181800, "loss": 0.0049, "lr": 3.513112884476865e-05, "epoch": 8.60946094609461, "percentage": 43.05, "elapsed_time": "3:04:56", "remaining_time": "4:04:41", "throughput": 1488.34, "total_tokens": 16515664} {"current_steps": 78265, "total_steps": 181800, "loss": 0.0741, "lr": 3.512893463683869e-05, "epoch": 8.61001100110011, "percentage": 43.05, "elapsed_time": "3:04:57", "remaining_time": "4:04:40", "throughput": 1488.35, "total_tokens": 16516784} {"current_steps": 78270, "total_steps": 181800, "loss": 0.0139, "lr": 3.5126740335555205e-05, "epoch": 8.61056105610561, "percentage": 43.05, "elapsed_time": "3:04:58", "remaining_time": "4:04:39", "throughput": 1488.35, "total_tokens": 16517872} {"current_steps": 78275, "total_steps": 181800, "loss": 0.0161, "lr": 3.512454594093842e-05, "epoch": 8.61111111111111, "percentage": 43.06, "elapsed_time": "3:04:58", "remaining_time": "4:04:39", "throughput": 1488.35, "total_tokens": 16518896} {"current_steps": 78280, "total_steps": 181800, "loss": 0.0013, "lr": 3.512235145300855e-05, "epoch": 8.611661166116612, "percentage": 43.06, "elapsed_time": "3:04:59", "remaining_time": "4:04:38", "throughput": 1488.36, "total_tokens": 16519952} {"current_steps": 78285, "total_steps": 181800, "loss": 0.0675, "lr": 3.5120156871785814e-05, "epoch": 8.612211221122113, "percentage": 43.06, "elapsed_time": "3:05:00", "remaining_time": "4:04:37", "throughput": 1488.36, "total_tokens": 16521008} {"current_steps": 78290, "total_steps": 181800, "loss": 0.1006, "lr": 3.511796219729046e-05, "epoch": 8.612761276127612, "percentage": 43.06, "elapsed_time": "3:05:00", "remaining_time": "4:04:36", "throughput": 1488.36, "total_tokens": 16522064} {"current_steps": 78295, "total_steps": 181800, "loss": 0.0034, "lr": 3.51157674295427e-05, "epoch": 8.613311331133113, "percentage": 43.07, "elapsed_time": "3:05:01", "remaining_time": "4:04:36", "throughput": 1488.37, "total_tokens": 16523152} {"current_steps": 78300, "total_steps": 181800, "loss": 0.1032, "lr": 3.511357256856277e-05, "epoch": 8.613861386138614, "percentage": 43.07, "elapsed_time": "3:05:02", "remaining_time": "4:04:35", "throughput": 1488.37, "total_tokens": 16524240} {"current_steps": 78305, "total_steps": 181800, "loss": 0.0049, "lr": 3.511137761437089e-05, "epoch": 8.614411441144114, "percentage": 43.07, "elapsed_time": "3:05:02", "remaining_time": "4:04:34", "throughput": 1488.37, "total_tokens": 16525296} {"current_steps": 78310, "total_steps": 181800, "loss": 0.0224, "lr": 3.51091825669873e-05, "epoch": 8.614961496149615, "percentage": 43.07, "elapsed_time": "3:05:03", "remaining_time": "4:04:33", "throughput": 1488.37, "total_tokens": 16526320} {"current_steps": 78315, "total_steps": 181800, "loss": 0.0566, "lr": 3.510698742643221e-05, "epoch": 8.615511551155116, "percentage": 43.08, "elapsed_time": "3:05:04", "remaining_time": "4:04:33", "throughput": 1488.37, "total_tokens": 16527344} {"current_steps": 78320, "total_steps": 181800, "loss": 0.009, "lr": 3.510479219272588e-05, "epoch": 8.616061606160617, "percentage": 43.08, "elapsed_time": "3:05:04", "remaining_time": "4:04:32", "throughput": 1488.38, "total_tokens": 16528432} {"current_steps": 78325, "total_steps": 181800, "loss": 0.1462, "lr": 3.5102596865888525e-05, "epoch": 8.616611661166116, "percentage": 43.08, "elapsed_time": "3:05:05", "remaining_time": "4:04:31", "throughput": 1488.38, "total_tokens": 16529488} {"current_steps": 78330, "total_steps": 181800, "loss": 0.043, "lr": 3.5100401445940386e-05, "epoch": 8.617161716171617, "percentage": 43.09, "elapsed_time": "3:05:06", "remaining_time": "4:04:30", "throughput": 1488.39, "total_tokens": 16530544} {"current_steps": 78335, "total_steps": 181800, "loss": 0.0562, "lr": 3.509820593290169e-05, "epoch": 8.617711771177119, "percentage": 43.09, "elapsed_time": "3:05:07", "remaining_time": "4:04:30", "throughput": 1488.39, "total_tokens": 16531664} {"current_steps": 78340, "total_steps": 181800, "loss": 0.0206, "lr": 3.5096010326792675e-05, "epoch": 8.618261826182618, "percentage": 43.09, "elapsed_time": "3:05:07", "remaining_time": "4:04:29", "throughput": 1488.41, "total_tokens": 16532816} {"current_steps": 78345, "total_steps": 181800, "loss": 0.1009, "lr": 3.509381462763358e-05, "epoch": 8.618811881188119, "percentage": 43.09, "elapsed_time": "3:05:08", "remaining_time": "4:04:28", "throughput": 1488.4, "total_tokens": 16533936} {"current_steps": 78350, "total_steps": 181800, "loss": 0.0358, "lr": 3.509161883544464e-05, "epoch": 8.61936193619362, "percentage": 43.1, "elapsed_time": "3:05:09", "remaining_time": "4:04:28", "throughput": 1488.4, "total_tokens": 16534928} {"current_steps": 78355, "total_steps": 181800, "loss": 0.0109, "lr": 3.5089422950246084e-05, "epoch": 8.61991199119912, "percentage": 43.1, "elapsed_time": "3:05:09", "remaining_time": "4:04:27", "throughput": 1488.4, "total_tokens": 16535952} {"current_steps": 78360, "total_steps": 181800, "loss": 0.1181, "lr": 3.5087226972058164e-05, "epoch": 8.62046204620462, "percentage": 43.1, "elapsed_time": "3:05:10", "remaining_time": "4:04:26", "throughput": 1488.4, "total_tokens": 16536976} {"current_steps": 78365, "total_steps": 181800, "loss": 0.0079, "lr": 3.5085030900901115e-05, "epoch": 8.621012101210122, "percentage": 43.11, "elapsed_time": "3:05:11", "remaining_time": "4:04:25", "throughput": 1488.4, "total_tokens": 16538064} {"current_steps": 78370, "total_steps": 181800, "loss": 0.0949, "lr": 3.5082834736795175e-05, "epoch": 8.62156215621562, "percentage": 43.11, "elapsed_time": "3:05:11", "remaining_time": "4:04:25", "throughput": 1488.4, "total_tokens": 16539088} {"current_steps": 78375, "total_steps": 181800, "loss": 0.066, "lr": 3.508063847976058e-05, "epoch": 8.622112211221122, "percentage": 43.11, "elapsed_time": "3:05:12", "remaining_time": "4:04:24", "throughput": 1488.4, "total_tokens": 16540144} {"current_steps": 78380, "total_steps": 181800, "loss": 0.0271, "lr": 3.5078442129817585e-05, "epoch": 8.622662266226623, "percentage": 43.11, "elapsed_time": "3:05:13", "remaining_time": "4:04:23", "throughput": 1488.4, "total_tokens": 16541168} {"current_steps": 78385, "total_steps": 181800, "loss": 0.0602, "lr": 3.5076245686986415e-05, "epoch": 8.623212321232124, "percentage": 43.12, "elapsed_time": "3:05:14", "remaining_time": "4:04:22", "throughput": 1488.41, "total_tokens": 16542224} {"current_steps": 78390, "total_steps": 181800, "loss": 0.1037, "lr": 3.507404915128734e-05, "epoch": 8.623762376237623, "percentage": 43.12, "elapsed_time": "3:05:14", "remaining_time": "4:04:22", "throughput": 1488.41, "total_tokens": 16543312} {"current_steps": 78395, "total_steps": 181800, "loss": 0.0964, "lr": 3.507185252274057e-05, "epoch": 8.624312431243125, "percentage": 43.12, "elapsed_time": "3:05:15", "remaining_time": "4:04:21", "throughput": 1488.42, "total_tokens": 16544400} {"current_steps": 78400, "total_steps": 181800, "loss": 0.0069, "lr": 3.5069655801366376e-05, "epoch": 8.624862486248626, "percentage": 43.12, "elapsed_time": "3:05:16", "remaining_time": "4:04:20", "throughput": 1488.42, "total_tokens": 16545488} {"current_steps": 78405, "total_steps": 181800, "loss": 0.0478, "lr": 3.5067458987185e-05, "epoch": 8.625412541254125, "percentage": 43.13, "elapsed_time": "3:05:16", "remaining_time": "4:04:20", "throughput": 1488.43, "total_tokens": 16546576} {"current_steps": 78410, "total_steps": 181800, "loss": 0.021, "lr": 3.506526208021668e-05, "epoch": 8.625962596259626, "percentage": 43.13, "elapsed_time": "3:05:17", "remaining_time": "4:04:19", "throughput": 1488.42, "total_tokens": 16547568} {"current_steps": 78415, "total_steps": 181800, "loss": 0.0959, "lr": 3.506306508048167e-05, "epoch": 8.626512651265127, "percentage": 43.13, "elapsed_time": "3:05:18", "remaining_time": "4:04:18", "throughput": 1488.42, "total_tokens": 16548592} {"current_steps": 78420, "total_steps": 181800, "loss": 0.0585, "lr": 3.506086798800022e-05, "epoch": 8.627062706270626, "percentage": 43.14, "elapsed_time": "3:05:18", "remaining_time": "4:04:17", "throughput": 1488.43, "total_tokens": 16549680} {"current_steps": 78425, "total_steps": 181800, "loss": 0.0644, "lr": 3.5058670802792574e-05, "epoch": 8.627612761276128, "percentage": 43.14, "elapsed_time": "3:05:19", "remaining_time": "4:04:17", "throughput": 1488.43, "total_tokens": 16550736} {"current_steps": 78430, "total_steps": 181800, "loss": 0.0101, "lr": 3.505647352487899e-05, "epoch": 8.628162816281629, "percentage": 43.14, "elapsed_time": "3:05:20", "remaining_time": "4:04:16", "throughput": 1488.44, "total_tokens": 16551888} {"current_steps": 78435, "total_steps": 181800, "loss": 0.037, "lr": 3.505427615427971e-05, "epoch": 8.628712871287128, "percentage": 43.14, "elapsed_time": "3:05:20", "remaining_time": "4:04:15", "throughput": 1488.44, "total_tokens": 16552912} {"current_steps": 78440, "total_steps": 181800, "loss": 0.071, "lr": 3.5052078691015e-05, "epoch": 8.629262926292629, "percentage": 43.15, "elapsed_time": "3:05:21", "remaining_time": "4:04:14", "throughput": 1488.45, "total_tokens": 16553968} {"current_steps": 78445, "total_steps": 181800, "loss": 0.0465, "lr": 3.504988113510509e-05, "epoch": 8.62981298129813, "percentage": 43.15, "elapsed_time": "3:05:22", "remaining_time": "4:04:14", "throughput": 1488.45, "total_tokens": 16554992} {"current_steps": 78450, "total_steps": 181800, "loss": 0.0355, "lr": 3.504768348657026e-05, "epoch": 8.630363036303631, "percentage": 43.15, "elapsed_time": "3:05:23", "remaining_time": "4:04:13", "throughput": 1488.45, "total_tokens": 16556048} {"current_steps": 78455, "total_steps": 181800, "loss": 0.0124, "lr": 3.504548574543075e-05, "epoch": 8.63091309130913, "percentage": 43.15, "elapsed_time": "3:05:23", "remaining_time": "4:04:12", "throughput": 1488.46, "total_tokens": 16557168} {"current_steps": 78460, "total_steps": 181800, "loss": 0.1363, "lr": 3.5043287911706815e-05, "epoch": 8.631463146314632, "percentage": 43.16, "elapsed_time": "3:05:24", "remaining_time": "4:04:11", "throughput": 1488.46, "total_tokens": 16558192} {"current_steps": 78465, "total_steps": 181800, "loss": 0.088, "lr": 3.504108998541872e-05, "epoch": 8.632013201320133, "percentage": 43.16, "elapsed_time": "3:05:25", "remaining_time": "4:04:11", "throughput": 1488.46, "total_tokens": 16559280} {"current_steps": 78470, "total_steps": 181800, "loss": 0.0165, "lr": 3.5038891966586704e-05, "epoch": 8.632563256325632, "percentage": 43.16, "elapsed_time": "3:05:25", "remaining_time": "4:04:10", "throughput": 1488.46, "total_tokens": 16560272} {"current_steps": 78475, "total_steps": 181800, "loss": 0.0104, "lr": 3.503669385523105e-05, "epoch": 8.633113311331133, "percentage": 43.17, "elapsed_time": "3:05:26", "remaining_time": "4:04:09", "throughput": 1488.46, "total_tokens": 16561264} {"current_steps": 78480, "total_steps": 181800, "loss": 0.1514, "lr": 3.5034495651372e-05, "epoch": 8.633663366336634, "percentage": 43.17, "elapsed_time": "3:05:27", "remaining_time": "4:04:09", "throughput": 1488.46, "total_tokens": 16562288} {"current_steps": 78485, "total_steps": 181800, "loss": 0.0731, "lr": 3.5032297355029826e-05, "epoch": 8.634213421342134, "percentage": 43.17, "elapsed_time": "3:05:27", "remaining_time": "4:04:08", "throughput": 1488.46, "total_tokens": 16563376} {"current_steps": 78490, "total_steps": 181800, "loss": 0.0104, "lr": 3.503009896622478e-05, "epoch": 8.634763476347635, "percentage": 43.17, "elapsed_time": "3:05:28", "remaining_time": "4:04:07", "throughput": 1488.46, "total_tokens": 16564336} {"current_steps": 78495, "total_steps": 181800, "loss": 0.0114, "lr": 3.5027900484977114e-05, "epoch": 8.635313531353136, "percentage": 43.18, "elapsed_time": "3:05:29", "remaining_time": "4:04:06", "throughput": 1488.45, "total_tokens": 16565296} {"current_steps": 78500, "total_steps": 181800, "loss": 0.0863, "lr": 3.502570191130711e-05, "epoch": 8.635863586358635, "percentage": 43.18, "elapsed_time": "3:05:29", "remaining_time": "4:04:06", "throughput": 1488.45, "total_tokens": 16566320} {"current_steps": 78505, "total_steps": 181800, "loss": 0.0481, "lr": 3.5023503245235014e-05, "epoch": 8.636413641364136, "percentage": 43.18, "elapsed_time": "3:05:30", "remaining_time": "4:04:05", "throughput": 1488.45, "total_tokens": 16567376} {"current_steps": 78510, "total_steps": 181800, "loss": 0.0081, "lr": 3.5021304486781114e-05, "epoch": 8.636963696369637, "percentage": 43.18, "elapsed_time": "3:05:31", "remaining_time": "4:04:04", "throughput": 1488.45, "total_tokens": 16568400} {"current_steps": 78515, "total_steps": 181800, "loss": 0.0195, "lr": 3.5019105635965644e-05, "epoch": 8.637513751375138, "percentage": 43.19, "elapsed_time": "3:05:31", "remaining_time": "4:04:03", "throughput": 1488.46, "total_tokens": 16569488} {"current_steps": 78520, "total_steps": 181800, "loss": 0.0378, "lr": 3.501690669280889e-05, "epoch": 8.638063806380638, "percentage": 43.19, "elapsed_time": "3:05:32", "remaining_time": "4:04:03", "throughput": 1488.46, "total_tokens": 16570608} {"current_steps": 78525, "total_steps": 181800, "loss": 0.0252, "lr": 3.501470765733111e-05, "epoch": 8.638613861386139, "percentage": 43.19, "elapsed_time": "3:05:33", "remaining_time": "4:04:02", "throughput": 1488.47, "total_tokens": 16571664} {"current_steps": 78530, "total_steps": 181800, "loss": 0.0455, "lr": 3.501250852955258e-05, "epoch": 8.63916391639164, "percentage": 43.2, "elapsed_time": "3:05:34", "remaining_time": "4:04:01", "throughput": 1488.47, "total_tokens": 16572688} {"current_steps": 78535, "total_steps": 181800, "loss": 0.0162, "lr": 3.501030930949357e-05, "epoch": 8.63971397139714, "percentage": 43.2, "elapsed_time": "3:05:34", "remaining_time": "4:04:00", "throughput": 1488.47, "total_tokens": 16573776} {"current_steps": 78540, "total_steps": 181800, "loss": 0.0888, "lr": 3.5008109997174334e-05, "epoch": 8.64026402640264, "percentage": 43.2, "elapsed_time": "3:05:35", "remaining_time": "4:04:00", "throughput": 1488.48, "total_tokens": 16574896} {"current_steps": 78545, "total_steps": 181800, "loss": 0.0694, "lr": 3.500591059261515e-05, "epoch": 8.640814081408141, "percentage": 43.2, "elapsed_time": "3:05:36", "remaining_time": "4:03:59", "throughput": 1488.48, "total_tokens": 16575952} {"current_steps": 78550, "total_steps": 181800, "loss": 0.0078, "lr": 3.500371109583629e-05, "epoch": 8.64136413641364, "percentage": 43.21, "elapsed_time": "3:05:36", "remaining_time": "4:03:58", "throughput": 1488.49, "total_tokens": 16577008} {"current_steps": 78555, "total_steps": 181800, "loss": 0.0138, "lr": 3.5001511506858034e-05, "epoch": 8.641914191419142, "percentage": 43.21, "elapsed_time": "3:05:37", "remaining_time": "4:03:58", "throughput": 1488.49, "total_tokens": 16578032} {"current_steps": 78560, "total_steps": 181800, "loss": 0.0069, "lr": 3.499931182570063e-05, "epoch": 8.642464246424643, "percentage": 43.21, "elapsed_time": "3:05:38", "remaining_time": "4:03:57", "throughput": 1488.49, "total_tokens": 16579056} {"current_steps": 78565, "total_steps": 181800, "loss": 0.006, "lr": 3.499711205238437e-05, "epoch": 8.643014301430142, "percentage": 43.22, "elapsed_time": "3:05:38", "remaining_time": "4:03:56", "throughput": 1488.48, "total_tokens": 16580016} {"current_steps": 78570, "total_steps": 181800, "loss": 0.0587, "lr": 3.499491218692953e-05, "epoch": 8.643564356435643, "percentage": 43.22, "elapsed_time": "3:05:39", "remaining_time": "4:03:55", "throughput": 1488.48, "total_tokens": 16581104} {"current_steps": 78575, "total_steps": 181800, "loss": 0.0205, "lr": 3.4992712229356384e-05, "epoch": 8.644114411441144, "percentage": 43.22, "elapsed_time": "3:05:40", "remaining_time": "4:03:55", "throughput": 1488.49, "total_tokens": 16582192} {"current_steps": 78580, "total_steps": 181800, "loss": 0.0475, "lr": 3.49905121796852e-05, "epoch": 8.644664466446645, "percentage": 43.22, "elapsed_time": "3:05:40", "remaining_time": "4:03:54", "throughput": 1488.49, "total_tokens": 16583248} {"current_steps": 78585, "total_steps": 181800, "loss": 0.0038, "lr": 3.4988312037936266e-05, "epoch": 8.645214521452145, "percentage": 43.23, "elapsed_time": "3:05:41", "remaining_time": "4:03:53", "throughput": 1488.49, "total_tokens": 16584272} {"current_steps": 78590, "total_steps": 181800, "loss": 0.058, "lr": 3.498611180412984e-05, "epoch": 8.645764576457646, "percentage": 43.23, "elapsed_time": "3:05:42", "remaining_time": "4:03:52", "throughput": 1488.5, "total_tokens": 16585360} {"current_steps": 78595, "total_steps": 181800, "loss": 0.052, "lr": 3.4983911478286226e-05, "epoch": 8.646314631463147, "percentage": 43.23, "elapsed_time": "3:05:43", "remaining_time": "4:03:52", "throughput": 1488.5, "total_tokens": 16586416} {"current_steps": 78600, "total_steps": 181800, "loss": 0.0418, "lr": 3.4981711060425685e-05, "epoch": 8.646864686468646, "percentage": 43.23, "elapsed_time": "3:05:43", "remaining_time": "4:03:51", "throughput": 1488.5, "total_tokens": 16587472} {"current_steps": 78605, "total_steps": 181800, "loss": 0.0086, "lr": 3.49795105505685e-05, "epoch": 8.647414741474147, "percentage": 43.24, "elapsed_time": "3:05:44", "remaining_time": "4:03:50", "throughput": 1488.51, "total_tokens": 16588592} {"current_steps": 78610, "total_steps": 181800, "loss": 0.0867, "lr": 3.497730994873496e-05, "epoch": 8.647964796479648, "percentage": 43.24, "elapsed_time": "3:05:45", "remaining_time": "4:03:49", "throughput": 1488.52, "total_tokens": 16589680} {"current_steps": 78615, "total_steps": 181800, "loss": 0.0499, "lr": 3.497510925494534e-05, "epoch": 8.648514851485148, "percentage": 43.24, "elapsed_time": "3:05:45", "remaining_time": "4:03:49", "throughput": 1488.52, "total_tokens": 16590736} {"current_steps": 78620, "total_steps": 181800, "loss": 0.0255, "lr": 3.497290846921992e-05, "epoch": 8.649064906490649, "percentage": 43.25, "elapsed_time": "3:05:46", "remaining_time": "4:03:48", "throughput": 1488.52, "total_tokens": 16591792} {"current_steps": 78625, "total_steps": 181800, "loss": 0.0293, "lr": 3.497070759157899e-05, "epoch": 8.64961496149615, "percentage": 43.25, "elapsed_time": "3:05:47", "remaining_time": "4:03:47", "throughput": 1488.52, "total_tokens": 16592848} {"current_steps": 78630, "total_steps": 181800, "loss": 0.0086, "lr": 3.4968506622042835e-05, "epoch": 8.65016501650165, "percentage": 43.25, "elapsed_time": "3:05:47", "remaining_time": "4:03:47", "throughput": 1488.52, "total_tokens": 16593840} {"current_steps": 78635, "total_steps": 181800, "loss": 0.005, "lr": 3.496630556063174e-05, "epoch": 8.65071507150715, "percentage": 43.25, "elapsed_time": "3:05:48", "remaining_time": "4:03:46", "throughput": 1488.53, "total_tokens": 16594928} {"current_steps": 78640, "total_steps": 181800, "loss": 0.0032, "lr": 3.4964104407365985e-05, "epoch": 8.651265126512651, "percentage": 43.26, "elapsed_time": "3:05:49", "remaining_time": "4:03:45", "throughput": 1488.53, "total_tokens": 16595952} {"current_steps": 78645, "total_steps": 181800, "loss": 0.0836, "lr": 3.496190316226586e-05, "epoch": 8.651815181518153, "percentage": 43.26, "elapsed_time": "3:05:49", "remaining_time": "4:03:44", "throughput": 1488.53, "total_tokens": 16596976} {"current_steps": 78650, "total_steps": 181800, "loss": 0.0416, "lr": 3.495970182535166e-05, "epoch": 8.652365236523652, "percentage": 43.26, "elapsed_time": "3:05:50", "remaining_time": "4:03:44", "throughput": 1488.53, "total_tokens": 16598000} {"current_steps": 78655, "total_steps": 181800, "loss": 0.0222, "lr": 3.495750039664366e-05, "epoch": 8.652915291529153, "percentage": 43.26, "elapsed_time": "3:05:51", "remaining_time": "4:03:43", "throughput": 1488.53, "total_tokens": 16599056} {"current_steps": 78660, "total_steps": 181800, "loss": 0.1107, "lr": 3.4955298876162155e-05, "epoch": 8.653465346534654, "percentage": 43.27, "elapsed_time": "3:05:52", "remaining_time": "4:03:42", "throughput": 1488.54, "total_tokens": 16600208} {"current_steps": 78665, "total_steps": 181800, "loss": 0.1343, "lr": 3.495309726392745e-05, "epoch": 8.654015401540153, "percentage": 43.27, "elapsed_time": "3:05:52", "remaining_time": "4:03:41", "throughput": 1488.54, "total_tokens": 16601264} {"current_steps": 78670, "total_steps": 181800, "loss": 0.0327, "lr": 3.495089555995981e-05, "epoch": 8.654565456545654, "percentage": 43.27, "elapsed_time": "3:05:53", "remaining_time": "4:03:41", "throughput": 1488.55, "total_tokens": 16602352} {"current_steps": 78675, "total_steps": 181800, "loss": 0.0762, "lr": 3.494869376427955e-05, "epoch": 8.655115511551156, "percentage": 43.28, "elapsed_time": "3:05:54", "remaining_time": "4:03:40", "throughput": 1488.56, "total_tokens": 16603472} {"current_steps": 78680, "total_steps": 181800, "loss": 0.0622, "lr": 3.494649187690695e-05, "epoch": 8.655665566556655, "percentage": 43.28, "elapsed_time": "3:05:54", "remaining_time": "4:03:39", "throughput": 1488.56, "total_tokens": 16604560} {"current_steps": 78685, "total_steps": 181800, "loss": 0.0229, "lr": 3.494428989786231e-05, "epoch": 8.656215621562156, "percentage": 43.28, "elapsed_time": "3:05:55", "remaining_time": "4:03:38", "throughput": 1488.56, "total_tokens": 16605584} {"current_steps": 78690, "total_steps": 181800, "loss": 0.0051, "lr": 3.4942087827165915e-05, "epoch": 8.656765676567657, "percentage": 43.28, "elapsed_time": "3:05:56", "remaining_time": "4:03:38", "throughput": 1488.56, "total_tokens": 16606608} {"current_steps": 78695, "total_steps": 181800, "loss": 0.006, "lr": 3.493988566483807e-05, "epoch": 8.657315731573158, "percentage": 43.29, "elapsed_time": "3:05:56", "remaining_time": "4:03:37", "throughput": 1488.56, "total_tokens": 16607664} {"current_steps": 78700, "total_steps": 181800, "loss": 0.0794, "lr": 3.4937683410899074e-05, "epoch": 8.657865786578657, "percentage": 43.29, "elapsed_time": "3:05:57", "remaining_time": "4:03:36", "throughput": 1488.57, "total_tokens": 16608720} {"current_steps": 78705, "total_steps": 181800, "loss": 0.0715, "lr": 3.4935481065369204e-05, "epoch": 8.658415841584159, "percentage": 43.29, "elapsed_time": "3:05:58", "remaining_time": "4:03:36", "throughput": 1488.57, "total_tokens": 16609744} {"current_steps": 78710, "total_steps": 181800, "loss": 0.011, "lr": 3.493327862826879e-05, "epoch": 8.65896589658966, "percentage": 43.29, "elapsed_time": "3:05:58", "remaining_time": "4:03:35", "throughput": 1488.57, "total_tokens": 16610800} {"current_steps": 78715, "total_steps": 181800, "loss": 0.0298, "lr": 3.4931076099618104e-05, "epoch": 8.659515951595159, "percentage": 43.3, "elapsed_time": "3:05:59", "remaining_time": "4:03:34", "throughput": 1488.57, "total_tokens": 16611792} {"current_steps": 78720, "total_steps": 181800, "loss": 0.0724, "lr": 3.492887347943745e-05, "epoch": 8.66006600660066, "percentage": 43.3, "elapsed_time": "3:06:00", "remaining_time": "4:03:33", "throughput": 1488.56, "total_tokens": 16612784} {"current_steps": 78725, "total_steps": 181800, "loss": 0.0323, "lr": 3.492667076774715e-05, "epoch": 8.660616061606161, "percentage": 43.3, "elapsed_time": "3:06:00", "remaining_time": "4:03:33", "throughput": 1488.56, "total_tokens": 16613840} {"current_steps": 78730, "total_steps": 181800, "loss": 0.0109, "lr": 3.492446796456747e-05, "epoch": 8.66116611661166, "percentage": 43.31, "elapsed_time": "3:06:01", "remaining_time": "4:03:32", "throughput": 1488.56, "total_tokens": 16614864} {"current_steps": 78735, "total_steps": 181800, "loss": 0.0215, "lr": 3.492226506991874e-05, "epoch": 8.661716171617162, "percentage": 43.31, "elapsed_time": "3:06:02", "remaining_time": "4:03:31", "throughput": 1488.57, "total_tokens": 16615920} {"current_steps": 78740, "total_steps": 181800, "loss": 0.0475, "lr": 3.4920062083821256e-05, "epoch": 8.662266226622663, "percentage": 43.31, "elapsed_time": "3:06:03", "remaining_time": "4:03:30", "throughput": 1488.57, "total_tokens": 16616976} {"current_steps": 78745, "total_steps": 181800, "loss": 0.0063, "lr": 3.491785900629532e-05, "epoch": 8.662816281628164, "percentage": 43.31, "elapsed_time": "3:06:03", "remaining_time": "4:03:30", "throughput": 1488.57, "total_tokens": 16618000} {"current_steps": 78750, "total_steps": 181800, "loss": 0.007, "lr": 3.491565583736124e-05, "epoch": 8.663366336633663, "percentage": 43.32, "elapsed_time": "3:06:04", "remaining_time": "4:03:29", "throughput": 1488.57, "total_tokens": 16619024} {"current_steps": 78755, "total_steps": 181800, "loss": 0.0064, "lr": 3.491345257703931e-05, "epoch": 8.663916391639164, "percentage": 43.32, "elapsed_time": "3:06:05", "remaining_time": "4:03:28", "throughput": 1488.57, "total_tokens": 16620048} {"current_steps": 78760, "total_steps": 181800, "loss": 0.0255, "lr": 3.491124922534985e-05, "epoch": 8.664466446644665, "percentage": 43.32, "elapsed_time": "3:06:05", "remaining_time": "4:03:27", "throughput": 1488.57, "total_tokens": 16621136} {"current_steps": 78765, "total_steps": 181800, "loss": 0.0156, "lr": 3.4909045782313156e-05, "epoch": 8.665016501650165, "percentage": 43.33, "elapsed_time": "3:06:06", "remaining_time": "4:03:27", "throughput": 1488.58, "total_tokens": 16622192} {"current_steps": 78770, "total_steps": 181800, "loss": 0.0358, "lr": 3.4906842247949547e-05, "epoch": 8.665566556655666, "percentage": 43.33, "elapsed_time": "3:06:07", "remaining_time": "4:03:26", "throughput": 1488.57, "total_tokens": 16623152} {"current_steps": 78775, "total_steps": 181800, "loss": 0.0023, "lr": 3.4904638622279316e-05, "epoch": 8.666116611661167, "percentage": 43.33, "elapsed_time": "3:06:07", "remaining_time": "4:03:25", "throughput": 1488.58, "total_tokens": 16624240} {"current_steps": 78780, "total_steps": 181800, "loss": 0.0038, "lr": 3.490243490532279e-05, "epoch": 8.666666666666666, "percentage": 43.33, "elapsed_time": "3:06:08", "remaining_time": "4:03:25", "throughput": 1488.58, "total_tokens": 16625296} {"current_steps": 78785, "total_steps": 181800, "loss": 0.0234, "lr": 3.4900231097100286e-05, "epoch": 8.667216721672167, "percentage": 43.34, "elapsed_time": "3:06:09", "remaining_time": "4:03:24", "throughput": 1488.59, "total_tokens": 16626448} {"current_steps": 78790, "total_steps": 181800, "loss": 0.0245, "lr": 3.489802719763209e-05, "epoch": 8.667766776677668, "percentage": 43.34, "elapsed_time": "3:06:09", "remaining_time": "4:03:23", "throughput": 1488.58, "total_tokens": 16627408} {"current_steps": 78795, "total_steps": 181800, "loss": 0.0394, "lr": 3.4895823206938526e-05, "epoch": 8.668316831683168, "percentage": 43.34, "elapsed_time": "3:06:10", "remaining_time": "4:03:22", "throughput": 1488.59, "total_tokens": 16628496} {"current_steps": 78800, "total_steps": 181800, "loss": 0.1456, "lr": 3.489361912503991e-05, "epoch": 8.668866886688669, "percentage": 43.34, "elapsed_time": "3:06:11", "remaining_time": "4:03:22", "throughput": 1488.59, "total_tokens": 16629488} {"current_steps": 78805, "total_steps": 181800, "loss": 0.0051, "lr": 3.489141495195655e-05, "epoch": 8.66941694169417, "percentage": 43.35, "elapsed_time": "3:06:12", "remaining_time": "4:03:21", "throughput": 1488.59, "total_tokens": 16630576} {"current_steps": 78810, "total_steps": 181800, "loss": 0.0106, "lr": 3.488921068770877e-05, "epoch": 8.66996699669967, "percentage": 43.35, "elapsed_time": "3:06:12", "remaining_time": "4:03:20", "throughput": 1488.6, "total_tokens": 16631632} {"current_steps": 78815, "total_steps": 181800, "loss": 0.0135, "lr": 3.4887006332316886e-05, "epoch": 8.67051705170517, "percentage": 43.35, "elapsed_time": "3:06:13", "remaining_time": "4:03:19", "throughput": 1488.6, "total_tokens": 16632720} {"current_steps": 78820, "total_steps": 181800, "loss": 0.0739, "lr": 3.48848018858012e-05, "epoch": 8.671067106710671, "percentage": 43.36, "elapsed_time": "3:06:14", "remaining_time": "4:03:19", "throughput": 1488.61, "total_tokens": 16633808} {"current_steps": 78825, "total_steps": 181800, "loss": 0.0498, "lr": 3.488259734818204e-05, "epoch": 8.671617161716172, "percentage": 43.36, "elapsed_time": "3:06:14", "remaining_time": "4:03:18", "throughput": 1488.61, "total_tokens": 16634864} {"current_steps": 78830, "total_steps": 181800, "loss": 0.0464, "lr": 3.488039271947972e-05, "epoch": 8.672167216721672, "percentage": 43.36, "elapsed_time": "3:06:15", "remaining_time": "4:03:17", "throughput": 1488.61, "total_tokens": 16635920} {"current_steps": 78835, "total_steps": 181800, "loss": 0.0485, "lr": 3.4878187999714565e-05, "epoch": 8.672717271727173, "percentage": 43.36, "elapsed_time": "3:06:16", "remaining_time": "4:03:16", "throughput": 1488.62, "total_tokens": 16637008} {"current_steps": 78840, "total_steps": 181800, "loss": 0.0367, "lr": 3.48759831889069e-05, "epoch": 8.673267326732674, "percentage": 43.37, "elapsed_time": "3:06:16", "remaining_time": "4:03:16", "throughput": 1488.62, "total_tokens": 16638096} {"current_steps": 78845, "total_steps": 181800, "loss": 0.0754, "lr": 3.487377828707703e-05, "epoch": 8.673817381738173, "percentage": 43.37, "elapsed_time": "3:06:17", "remaining_time": "4:03:15", "throughput": 1488.63, "total_tokens": 16639152} {"current_steps": 78850, "total_steps": 181800, "loss": 0.0026, "lr": 3.487157329424527e-05, "epoch": 8.674367436743674, "percentage": 43.37, "elapsed_time": "3:06:18", "remaining_time": "4:03:14", "throughput": 1488.63, "total_tokens": 16640208} {"current_steps": 78855, "total_steps": 181800, "loss": 0.0696, "lr": 3.486936821043197e-05, "epoch": 8.674917491749175, "percentage": 43.37, "elapsed_time": "3:06:18", "remaining_time": "4:03:14", "throughput": 1488.63, "total_tokens": 16641232} {"current_steps": 78860, "total_steps": 181800, "loss": 0.1046, "lr": 3.4867163035657433e-05, "epoch": 8.675467546754675, "percentage": 43.38, "elapsed_time": "3:06:19", "remaining_time": "4:03:13", "throughput": 1488.64, "total_tokens": 16642352} {"current_steps": 78865, "total_steps": 181800, "loss": 0.0476, "lr": 3.4864957769942e-05, "epoch": 8.676017601760176, "percentage": 43.38, "elapsed_time": "3:06:20", "remaining_time": "4:03:12", "throughput": 1488.64, "total_tokens": 16643376} {"current_steps": 78870, "total_steps": 181800, "loss": 0.005, "lr": 3.4862752413305976e-05, "epoch": 8.676567656765677, "percentage": 43.38, "elapsed_time": "3:06:20", "remaining_time": "4:03:11", "throughput": 1488.64, "total_tokens": 16644400} {"current_steps": 78875, "total_steps": 181800, "loss": 0.0148, "lr": 3.4860546965769696e-05, "epoch": 8.677117711771178, "percentage": 43.39, "elapsed_time": "3:06:21", "remaining_time": "4:03:11", "throughput": 1488.64, "total_tokens": 16645456} {"current_steps": 78880, "total_steps": 181800, "loss": 0.0088, "lr": 3.485834142735348e-05, "epoch": 8.677667766776677, "percentage": 43.39, "elapsed_time": "3:06:22", "remaining_time": "4:03:10", "throughput": 1488.64, "total_tokens": 16646544} {"current_steps": 78885, "total_steps": 181800, "loss": 0.0605, "lr": 3.485613579807767e-05, "epoch": 8.678217821782178, "percentage": 43.39, "elapsed_time": "3:06:23", "remaining_time": "4:03:09", "throughput": 1488.65, "total_tokens": 16647600} {"current_steps": 78890, "total_steps": 181800, "loss": 0.1011, "lr": 3.485393007796259e-05, "epoch": 8.67876787678768, "percentage": 43.39, "elapsed_time": "3:06:23", "remaining_time": "4:03:08", "throughput": 1488.65, "total_tokens": 16648720} {"current_steps": 78895, "total_steps": 181800, "loss": 0.0634, "lr": 3.485172426702855e-05, "epoch": 8.679317931793179, "percentage": 43.4, "elapsed_time": "3:06:24", "remaining_time": "4:03:08", "throughput": 1488.65, "total_tokens": 16649744} {"current_steps": 78900, "total_steps": 181800, "loss": 0.0228, "lr": 3.484951836529591e-05, "epoch": 8.67986798679868, "percentage": 43.4, "elapsed_time": "3:06:25", "remaining_time": "4:03:07", "throughput": 1488.65, "total_tokens": 16650768} {"current_steps": 78905, "total_steps": 181800, "loss": 0.0091, "lr": 3.484731237278498e-05, "epoch": 8.680418041804181, "percentage": 43.4, "elapsed_time": "3:06:25", "remaining_time": "4:03:06", "throughput": 1488.66, "total_tokens": 16651888} {"current_steps": 78910, "total_steps": 181800, "loss": 0.0108, "lr": 3.484510628951609e-05, "epoch": 8.68096809680968, "percentage": 43.4, "elapsed_time": "3:06:26", "remaining_time": "4:03:05", "throughput": 1488.66, "total_tokens": 16652880} {"current_steps": 78915, "total_steps": 181800, "loss": 0.1955, "lr": 3.484290011550959e-05, "epoch": 8.681518151815181, "percentage": 43.41, "elapsed_time": "3:06:27", "remaining_time": "4:03:05", "throughput": 1488.66, "total_tokens": 16653968} {"current_steps": 78920, "total_steps": 181800, "loss": 0.0393, "lr": 3.48406938507858e-05, "epoch": 8.682068206820682, "percentage": 43.41, "elapsed_time": "3:06:27", "remaining_time": "4:03:04", "throughput": 1488.67, "total_tokens": 16655024} {"current_steps": 78925, "total_steps": 181800, "loss": 0.018, "lr": 3.4838487495365054e-05, "epoch": 8.682618261826182, "percentage": 43.41, "elapsed_time": "3:06:28", "remaining_time": "4:03:03", "throughput": 1488.67, "total_tokens": 16656080} {"current_steps": 78930, "total_steps": 181800, "loss": 0.004, "lr": 3.483628104926769e-05, "epoch": 8.683168316831683, "percentage": 43.42, "elapsed_time": "3:06:29", "remaining_time": "4:03:03", "throughput": 1488.67, "total_tokens": 16657136} {"current_steps": 78935, "total_steps": 181800, "loss": 0.0832, "lr": 3.4834074512514044e-05, "epoch": 8.683718371837184, "percentage": 43.42, "elapsed_time": "3:06:29", "remaining_time": "4:03:02", "throughput": 1488.68, "total_tokens": 16658256} {"current_steps": 78940, "total_steps": 181800, "loss": 0.0189, "lr": 3.483186788512445e-05, "epoch": 8.684268426842685, "percentage": 43.42, "elapsed_time": "3:06:30", "remaining_time": "4:03:01", "throughput": 1488.68, "total_tokens": 16659280} {"current_steps": 78945, "total_steps": 181800, "loss": 0.0132, "lr": 3.482966116711925e-05, "epoch": 8.684818481848184, "percentage": 43.42, "elapsed_time": "3:06:31", "remaining_time": "4:03:00", "throughput": 1488.69, "total_tokens": 16660400} {"current_steps": 78950, "total_steps": 181800, "loss": 0.072, "lr": 3.482745435851878e-05, "epoch": 8.685368536853685, "percentage": 43.43, "elapsed_time": "3:06:32", "remaining_time": "4:03:00", "throughput": 1488.69, "total_tokens": 16661456} {"current_steps": 78955, "total_steps": 181800, "loss": 0.0767, "lr": 3.482524745934338e-05, "epoch": 8.685918591859187, "percentage": 43.43, "elapsed_time": "3:06:32", "remaining_time": "4:02:59", "throughput": 1488.69, "total_tokens": 16662480} {"current_steps": 78960, "total_steps": 181800, "loss": 0.0051, "lr": 3.482304046961339e-05, "epoch": 8.686468646864686, "percentage": 43.43, "elapsed_time": "3:06:33", "remaining_time": "4:02:58", "throughput": 1488.7, "total_tokens": 16663568} {"current_steps": 78965, "total_steps": 181800, "loss": 0.013, "lr": 3.482083338934914e-05, "epoch": 8.687018701870187, "percentage": 43.44, "elapsed_time": "3:06:34", "remaining_time": "4:02:57", "throughput": 1488.71, "total_tokens": 16664688} {"current_steps": 78970, "total_steps": 181800, "loss": 0.0417, "lr": 3.4818626218570994e-05, "epoch": 8.687568756875688, "percentage": 43.44, "elapsed_time": "3:06:34", "remaining_time": "4:02:57", "throughput": 1488.71, "total_tokens": 16665808} {"current_steps": 78975, "total_steps": 181800, "loss": 0.02, "lr": 3.481641895729927e-05, "epoch": 8.688118811881187, "percentage": 43.44, "elapsed_time": "3:06:35", "remaining_time": "4:02:56", "throughput": 1488.72, "total_tokens": 16666896} {"current_steps": 78980, "total_steps": 181800, "loss": 0.0134, "lr": 3.481421160555433e-05, "epoch": 8.688668866886688, "percentage": 43.44, "elapsed_time": "3:06:36", "remaining_time": "4:02:55", "throughput": 1488.72, "total_tokens": 16667888} {"current_steps": 78985, "total_steps": 181800, "loss": 0.0116, "lr": 3.4812004163356507e-05, "epoch": 8.68921892189219, "percentage": 43.45, "elapsed_time": "3:06:36", "remaining_time": "4:02:54", "throughput": 1488.72, "total_tokens": 16668912} {"current_steps": 78990, "total_steps": 181800, "loss": 0.0906, "lr": 3.480979663072615e-05, "epoch": 8.689768976897689, "percentage": 43.45, "elapsed_time": "3:06:37", "remaining_time": "4:02:54", "throughput": 1488.72, "total_tokens": 16670000} {"current_steps": 78995, "total_steps": 181800, "loss": 0.0423, "lr": 3.480758900768361e-05, "epoch": 8.69031903190319, "percentage": 43.45, "elapsed_time": "3:06:38", "remaining_time": "4:02:53", "throughput": 1488.73, "total_tokens": 16671152} {"current_steps": 79000, "total_steps": 181800, "loss": 0.0291, "lr": 3.480538129424923e-05, "epoch": 8.690869086908691, "percentage": 43.45, "elapsed_time": "3:06:38", "remaining_time": "4:02:52", "throughput": 1488.74, "total_tokens": 16672272} {"current_steps": 79005, "total_steps": 181800, "loss": 0.2019, "lr": 3.4803173490443344e-05, "epoch": 8.691419141914192, "percentage": 43.46, "elapsed_time": "3:06:39", "remaining_time": "4:02:52", "throughput": 1488.75, "total_tokens": 16673328} {"current_steps": 79010, "total_steps": 181800, "loss": 0.082, "lr": 3.4800965596286325e-05, "epoch": 8.691969196919691, "percentage": 43.46, "elapsed_time": "3:06:40", "remaining_time": "4:02:51", "throughput": 1488.75, "total_tokens": 16674416} {"current_steps": 79015, "total_steps": 181800, "loss": 0.0345, "lr": 3.47987576117985e-05, "epoch": 8.692519251925193, "percentage": 43.46, "elapsed_time": "3:06:40", "remaining_time": "4:02:50", "throughput": 1488.76, "total_tokens": 16675504} {"current_steps": 79020, "total_steps": 181800, "loss": 0.0797, "lr": 3.479654953700023e-05, "epoch": 8.693069306930694, "percentage": 43.47, "elapsed_time": "3:06:41", "remaining_time": "4:02:49", "throughput": 1488.76, "total_tokens": 16676528} {"current_steps": 79025, "total_steps": 181800, "loss": 0.0301, "lr": 3.4794341371911864e-05, "epoch": 8.693619361936193, "percentage": 43.47, "elapsed_time": "3:06:42", "remaining_time": "4:02:49", "throughput": 1488.76, "total_tokens": 16677552} {"current_steps": 79030, "total_steps": 181800, "loss": 0.0028, "lr": 3.479213311655376e-05, "epoch": 8.694169416941694, "percentage": 43.47, "elapsed_time": "3:06:43", "remaining_time": "4:02:48", "throughput": 1488.76, "total_tokens": 16678608} {"current_steps": 79035, "total_steps": 181800, "loss": 0.0074, "lr": 3.478992477094626e-05, "epoch": 8.694719471947195, "percentage": 43.47, "elapsed_time": "3:06:43", "remaining_time": "4:02:47", "throughput": 1488.76, "total_tokens": 16679600} {"current_steps": 79040, "total_steps": 181800, "loss": 0.0317, "lr": 3.478771633510971e-05, "epoch": 8.695269526952695, "percentage": 43.48, "elapsed_time": "3:06:44", "remaining_time": "4:02:46", "throughput": 1488.76, "total_tokens": 16680720} {"current_steps": 79045, "total_steps": 181800, "loss": 0.0877, "lr": 3.4785507809064485e-05, "epoch": 8.695819581958196, "percentage": 43.48, "elapsed_time": "3:06:45", "remaining_time": "4:02:46", "throughput": 1488.77, "total_tokens": 16681840} {"current_steps": 79050, "total_steps": 181800, "loss": 0.0212, "lr": 3.478329919283093e-05, "epoch": 8.696369636963697, "percentage": 43.48, "elapsed_time": "3:06:45", "remaining_time": "4:02:45", "throughput": 1488.77, "total_tokens": 16682896} {"current_steps": 79055, "total_steps": 181800, "loss": 0.0877, "lr": 3.47810904864294e-05, "epoch": 8.696919691969196, "percentage": 43.48, "elapsed_time": "3:06:46", "remaining_time": "4:02:44", "throughput": 1488.78, "total_tokens": 16683984} {"current_steps": 79060, "total_steps": 181800, "loss": 0.0328, "lr": 3.477888168988025e-05, "epoch": 8.697469746974697, "percentage": 43.49, "elapsed_time": "3:06:47", "remaining_time": "4:02:43", "throughput": 1488.78, "total_tokens": 16685040} {"current_steps": 79065, "total_steps": 181800, "loss": 0.0917, "lr": 3.477667280320385e-05, "epoch": 8.698019801980198, "percentage": 43.49, "elapsed_time": "3:06:47", "remaining_time": "4:02:43", "throughput": 1488.79, "total_tokens": 16686096} {"current_steps": 79070, "total_steps": 181800, "loss": 0.0233, "lr": 3.477446382642053e-05, "epoch": 8.6985698569857, "percentage": 43.49, "elapsed_time": "3:06:48", "remaining_time": "4:02:42", "throughput": 1488.79, "total_tokens": 16687216} {"current_steps": 79075, "total_steps": 181800, "loss": 0.0791, "lr": 3.477225475955068e-05, "epoch": 8.699119911991199, "percentage": 43.5, "elapsed_time": "3:06:49", "remaining_time": "4:02:41", "throughput": 1488.8, "total_tokens": 16688272} {"current_steps": 79080, "total_steps": 181800, "loss": 0.1337, "lr": 3.477004560261464e-05, "epoch": 8.6996699669967, "percentage": 43.5, "elapsed_time": "3:06:49", "remaining_time": "4:02:40", "throughput": 1488.81, "total_tokens": 16689392} {"current_steps": 79085, "total_steps": 181800, "loss": 0.0446, "lr": 3.476783635563279e-05, "epoch": 8.7002200220022, "percentage": 43.5, "elapsed_time": "3:06:50", "remaining_time": "4:02:40", "throughput": 1488.81, "total_tokens": 16690480} {"current_steps": 79090, "total_steps": 181800, "loss": 0.057, "lr": 3.476562701862547e-05, "epoch": 8.7007700770077, "percentage": 43.5, "elapsed_time": "3:06:51", "remaining_time": "4:02:39", "throughput": 1488.81, "total_tokens": 16691472} {"current_steps": 79095, "total_steps": 181800, "loss": 0.1249, "lr": 3.476341759161305e-05, "epoch": 8.701320132013201, "percentage": 43.51, "elapsed_time": "3:06:52", "remaining_time": "4:02:38", "throughput": 1488.81, "total_tokens": 16692528} {"current_steps": 79100, "total_steps": 181800, "loss": 0.0108, "lr": 3.4761208074615895e-05, "epoch": 8.701870187018702, "percentage": 43.51, "elapsed_time": "3:06:52", "remaining_time": "4:02:38", "throughput": 1488.81, "total_tokens": 16693552} {"current_steps": 79105, "total_steps": 181800, "loss": 0.0582, "lr": 3.475899846765438e-05, "epoch": 8.702420242024202, "percentage": 43.51, "elapsed_time": "3:06:53", "remaining_time": "4:02:37", "throughput": 1488.81, "total_tokens": 16694608} {"current_steps": 79110, "total_steps": 181800, "loss": 0.0363, "lr": 3.475678877074885e-05, "epoch": 8.702970297029703, "percentage": 43.51, "elapsed_time": "3:06:54", "remaining_time": "4:02:36", "throughput": 1488.82, "total_tokens": 16695760} {"current_steps": 79115, "total_steps": 181800, "loss": 0.0446, "lr": 3.475457898391968e-05, "epoch": 8.703520352035204, "percentage": 43.52, "elapsed_time": "3:06:54", "remaining_time": "4:02:35", "throughput": 1488.84, "total_tokens": 16696944} {"current_steps": 79120, "total_steps": 181800, "loss": 0.0405, "lr": 3.4752369107187233e-05, "epoch": 8.704070407040705, "percentage": 43.52, "elapsed_time": "3:06:55", "remaining_time": "4:02:35", "throughput": 1488.84, "total_tokens": 16697968} {"current_steps": 79125, "total_steps": 181800, "loss": 0.1307, "lr": 3.4750159140571886e-05, "epoch": 8.704620462046204, "percentage": 43.52, "elapsed_time": "3:06:56", "remaining_time": "4:02:34", "throughput": 1488.85, "total_tokens": 16699120} {"current_steps": 79130, "total_steps": 181800, "loss": 0.0031, "lr": 3.4747949084094e-05, "epoch": 8.705170517051705, "percentage": 43.53, "elapsed_time": "3:06:56", "remaining_time": "4:02:33", "throughput": 1488.85, "total_tokens": 16700144} {"current_steps": 79135, "total_steps": 181800, "loss": 0.0252, "lr": 3.474573893777394e-05, "epoch": 8.705720572057206, "percentage": 43.53, "elapsed_time": "3:06:57", "remaining_time": "4:02:32", "throughput": 1488.85, "total_tokens": 16701200} {"current_steps": 79140, "total_steps": 181800, "loss": 0.0235, "lr": 3.4743528701632085e-05, "epoch": 8.706270627062706, "percentage": 43.53, "elapsed_time": "3:06:58", "remaining_time": "4:02:32", "throughput": 1488.85, "total_tokens": 16702288} {"current_steps": 79145, "total_steps": 181800, "loss": 0.0441, "lr": 3.47413183756888e-05, "epoch": 8.706820682068207, "percentage": 43.53, "elapsed_time": "3:06:58", "remaining_time": "4:02:31", "throughput": 1488.85, "total_tokens": 16703312} {"current_steps": 79150, "total_steps": 181800, "loss": 0.0233, "lr": 3.473910795996446e-05, "epoch": 8.707370737073708, "percentage": 43.54, "elapsed_time": "3:06:59", "remaining_time": "4:02:30", "throughput": 1488.86, "total_tokens": 16704400} {"current_steps": 79155, "total_steps": 181800, "loss": 0.0776, "lr": 3.473689745447943e-05, "epoch": 8.707920792079207, "percentage": 43.54, "elapsed_time": "3:07:00", "remaining_time": "4:02:30", "throughput": 1488.86, "total_tokens": 16705456} {"current_steps": 79160, "total_steps": 181800, "loss": 0.0847, "lr": 3.4734686859254094e-05, "epoch": 8.708470847084708, "percentage": 43.54, "elapsed_time": "3:07:00", "remaining_time": "4:02:29", "throughput": 1488.86, "total_tokens": 16706512} {"current_steps": 79165, "total_steps": 181800, "loss": 0.0232, "lr": 3.473247617430882e-05, "epoch": 8.70902090209021, "percentage": 43.55, "elapsed_time": "3:07:01", "remaining_time": "4:02:28", "throughput": 1488.87, "total_tokens": 16707568} {"current_steps": 79170, "total_steps": 181800, "loss": 0.0256, "lr": 3.473026539966398e-05, "epoch": 8.70957095709571, "percentage": 43.55, "elapsed_time": "3:07:02", "remaining_time": "4:02:27", "throughput": 1488.88, "total_tokens": 16708688} {"current_steps": 79175, "total_steps": 181800, "loss": 0.062, "lr": 3.472805453533995e-05, "epoch": 8.71012101210121, "percentage": 43.55, "elapsed_time": "3:07:03", "remaining_time": "4:02:27", "throughput": 1488.88, "total_tokens": 16709712} {"current_steps": 79180, "total_steps": 181800, "loss": 0.005, "lr": 3.472584358135712e-05, "epoch": 8.710671067106711, "percentage": 43.55, "elapsed_time": "3:07:03", "remaining_time": "4:02:26", "throughput": 1488.87, "total_tokens": 16710736} {"current_steps": 79185, "total_steps": 181800, "loss": 0.0422, "lr": 3.4723632537735846e-05, "epoch": 8.711221122112212, "percentage": 43.56, "elapsed_time": "3:07:04", "remaining_time": "4:02:25", "throughput": 1488.88, "total_tokens": 16711824} {"current_steps": 79190, "total_steps": 181800, "loss": 0.0102, "lr": 3.4721421404496525e-05, "epoch": 8.711771177117711, "percentage": 43.56, "elapsed_time": "3:07:05", "remaining_time": "4:02:24", "throughput": 1488.88, "total_tokens": 16712848} {"current_steps": 79195, "total_steps": 181800, "loss": 0.0321, "lr": 3.471921018165952e-05, "epoch": 8.712321232123212, "percentage": 43.56, "elapsed_time": "3:07:05", "remaining_time": "4:02:24", "throughput": 1488.88, "total_tokens": 16713936} {"current_steps": 79200, "total_steps": 181800, "loss": 0.0045, "lr": 3.471699886924522e-05, "epoch": 8.712871287128714, "percentage": 43.56, "elapsed_time": "3:07:06", "remaining_time": "4:02:23", "throughput": 1488.89, "total_tokens": 16714992} {"current_steps": 79205, "total_steps": 181800, "loss": 0.0856, "lr": 3.471478746727401e-05, "epoch": 8.713421342134213, "percentage": 43.57, "elapsed_time": "3:07:07", "remaining_time": "4:02:22", "throughput": 1488.88, "total_tokens": 16715984} {"current_steps": 79210, "total_steps": 181800, "loss": 0.0479, "lr": 3.471257597576626e-05, "epoch": 8.713971397139714, "percentage": 43.57, "elapsed_time": "3:07:07", "remaining_time": "4:02:21", "throughput": 1488.89, "total_tokens": 16717040} {"current_steps": 79215, "total_steps": 181800, "loss": 0.0083, "lr": 3.471036439474236e-05, "epoch": 8.714521452145215, "percentage": 43.57, "elapsed_time": "3:07:08", "remaining_time": "4:02:21", "throughput": 1488.89, "total_tokens": 16718096} {"current_steps": 79220, "total_steps": 181800, "loss": 0.0464, "lr": 3.470815272422269e-05, "epoch": 8.715071507150714, "percentage": 43.58, "elapsed_time": "3:07:09", "remaining_time": "4:02:20", "throughput": 1488.89, "total_tokens": 16719184} {"current_steps": 79225, "total_steps": 181800, "loss": 0.014, "lr": 3.470594096422764e-05, "epoch": 8.715621562156215, "percentage": 43.58, "elapsed_time": "3:07:09", "remaining_time": "4:02:19", "throughput": 1488.89, "total_tokens": 16720208} {"current_steps": 79230, "total_steps": 181800, "loss": 0.0064, "lr": 3.470372911477758e-05, "epoch": 8.716171617161717, "percentage": 43.58, "elapsed_time": "3:07:10", "remaining_time": "4:02:19", "throughput": 1488.89, "total_tokens": 16721200} {"current_steps": 79235, "total_steps": 181800, "loss": 0.0179, "lr": 3.470151717589291e-05, "epoch": 8.716721672167218, "percentage": 43.58, "elapsed_time": "3:07:11", "remaining_time": "4:02:18", "throughput": 1488.89, "total_tokens": 16722224} {"current_steps": 79240, "total_steps": 181800, "loss": 0.0129, "lr": 3.4699305147594016e-05, "epoch": 8.717271727172717, "percentage": 43.59, "elapsed_time": "3:07:12", "remaining_time": "4:02:17", "throughput": 1488.89, "total_tokens": 16723280} {"current_steps": 79245, "total_steps": 181800, "loss": 0.0941, "lr": 3.469709302990127e-05, "epoch": 8.717821782178218, "percentage": 43.59, "elapsed_time": "3:07:12", "remaining_time": "4:02:16", "throughput": 1488.9, "total_tokens": 16724400} {"current_steps": 79250, "total_steps": 181800, "loss": 0.0455, "lr": 3.469488082283508e-05, "epoch": 8.718371837183719, "percentage": 43.59, "elapsed_time": "3:07:13", "remaining_time": "4:02:16", "throughput": 1488.9, "total_tokens": 16725456} {"current_steps": 79255, "total_steps": 181800, "loss": 0.073, "lr": 3.469266852641582e-05, "epoch": 8.718921892189218, "percentage": 43.59, "elapsed_time": "3:07:14", "remaining_time": "4:02:15", "throughput": 1488.91, "total_tokens": 16726576} {"current_steps": 79260, "total_steps": 181800, "loss": 0.1117, "lr": 3.4690456140663884e-05, "epoch": 8.71947194719472, "percentage": 43.6, "elapsed_time": "3:07:14", "remaining_time": "4:02:14", "throughput": 1488.92, "total_tokens": 16727696} {"current_steps": 79265, "total_steps": 181800, "loss": 0.0052, "lr": 3.468824366559967e-05, "epoch": 8.72002200220022, "percentage": 43.6, "elapsed_time": "3:07:15", "remaining_time": "4:02:13", "throughput": 1488.92, "total_tokens": 16728720} {"current_steps": 79270, "total_steps": 181800, "loss": 0.0855, "lr": 3.468603110124356e-05, "epoch": 8.72057205720572, "percentage": 43.6, "elapsed_time": "3:07:16", "remaining_time": "4:02:13", "throughput": 1488.92, "total_tokens": 16729808} {"current_steps": 79275, "total_steps": 181800, "loss": 0.0135, "lr": 3.468381844761595e-05, "epoch": 8.721122112211221, "percentage": 43.61, "elapsed_time": "3:07:16", "remaining_time": "4:02:12", "throughput": 1488.92, "total_tokens": 16730800} {"current_steps": 79280, "total_steps": 181800, "loss": 0.0858, "lr": 3.468160570473723e-05, "epoch": 8.721672167216722, "percentage": 43.61, "elapsed_time": "3:07:17", "remaining_time": "4:02:11", "throughput": 1488.92, "total_tokens": 16731856} {"current_steps": 79285, "total_steps": 181800, "loss": 0.0493, "lr": 3.467939287262779e-05, "epoch": 8.722222222222221, "percentage": 43.61, "elapsed_time": "3:07:18", "remaining_time": "4:02:10", "throughput": 1488.92, "total_tokens": 16732880} {"current_steps": 79290, "total_steps": 181800, "loss": 0.0872, "lr": 3.467717995130804e-05, "epoch": 8.722772277227723, "percentage": 43.61, "elapsed_time": "3:07:18", "remaining_time": "4:02:10", "throughput": 1488.93, "total_tokens": 16733968} {"current_steps": 79295, "total_steps": 181800, "loss": 0.0949, "lr": 3.467496694079837e-05, "epoch": 8.723322332233224, "percentage": 43.62, "elapsed_time": "3:07:19", "remaining_time": "4:02:09", "throughput": 1488.93, "total_tokens": 16735024} {"current_steps": 79300, "total_steps": 181800, "loss": 0.045, "lr": 3.467275384111916e-05, "epoch": 8.723872387238725, "percentage": 43.62, "elapsed_time": "3:07:20", "remaining_time": "4:02:08", "throughput": 1488.92, "total_tokens": 16735984} {"current_steps": 79305, "total_steps": 181800, "loss": 0.0186, "lr": 3.4670540652290825e-05, "epoch": 8.724422442244224, "percentage": 43.62, "elapsed_time": "3:07:21", "remaining_time": "4:02:08", "throughput": 1488.92, "total_tokens": 16736976} {"current_steps": 79310, "total_steps": 181800, "loss": 0.0134, "lr": 3.466832737433376e-05, "epoch": 8.724972497249725, "percentage": 43.62, "elapsed_time": "3:07:21", "remaining_time": "4:02:07", "throughput": 1488.93, "total_tokens": 16738128} {"current_steps": 79315, "total_steps": 181800, "loss": 0.0375, "lr": 3.466611400726835e-05, "epoch": 8.725522552255226, "percentage": 43.63, "elapsed_time": "3:07:22", "remaining_time": "4:02:06", "throughput": 1488.94, "total_tokens": 16739280} {"current_steps": 79320, "total_steps": 181800, "loss": 0.0161, "lr": 3.4663900551115026e-05, "epoch": 8.726072607260726, "percentage": 43.63, "elapsed_time": "3:07:23", "remaining_time": "4:02:05", "throughput": 1488.94, "total_tokens": 16740304} {"current_steps": 79325, "total_steps": 181800, "loss": 0.0352, "lr": 3.466168700589415e-05, "epoch": 8.726622662266227, "percentage": 43.63, "elapsed_time": "3:07:23", "remaining_time": "4:02:05", "throughput": 1488.94, "total_tokens": 16741360} {"current_steps": 79330, "total_steps": 181800, "loss": 0.0151, "lr": 3.4659473371626146e-05, "epoch": 8.727172717271728, "percentage": 43.64, "elapsed_time": "3:07:24", "remaining_time": "4:02:04", "throughput": 1488.95, "total_tokens": 16742448} {"current_steps": 79335, "total_steps": 181800, "loss": 0.049, "lr": 3.465725964833141e-05, "epoch": 8.727722772277227, "percentage": 43.64, "elapsed_time": "3:07:25", "remaining_time": "4:02:03", "throughput": 1488.95, "total_tokens": 16743440} {"current_steps": 79340, "total_steps": 181800, "loss": 0.0075, "lr": 3.465504583603035e-05, "epoch": 8.728272827282728, "percentage": 43.64, "elapsed_time": "3:07:25", "remaining_time": "4:02:02", "throughput": 1488.95, "total_tokens": 16744464} {"current_steps": 79345, "total_steps": 181800, "loss": 0.055, "lr": 3.465283193474336e-05, "epoch": 8.72882288228823, "percentage": 43.64, "elapsed_time": "3:07:26", "remaining_time": "4:02:02", "throughput": 1488.95, "total_tokens": 16745552} {"current_steps": 79350, "total_steps": 181800, "loss": 0.0689, "lr": 3.4650617944490854e-05, "epoch": 8.729372937293729, "percentage": 43.65, "elapsed_time": "3:07:27", "remaining_time": "4:02:01", "throughput": 1488.95, "total_tokens": 16746576} {"current_steps": 79355, "total_steps": 181800, "loss": 0.0297, "lr": 3.4648403865293236e-05, "epoch": 8.72992299229923, "percentage": 43.65, "elapsed_time": "3:07:27", "remaining_time": "4:02:00", "throughput": 1488.95, "total_tokens": 16747600} {"current_steps": 79360, "total_steps": 181800, "loss": 0.0291, "lr": 3.4646189697170895e-05, "epoch": 8.73047304730473, "percentage": 43.65, "elapsed_time": "3:07:28", "remaining_time": "4:02:00", "throughput": 1488.95, "total_tokens": 16748656} {"current_steps": 79365, "total_steps": 181800, "loss": 0.0139, "lr": 3.464397544014427e-05, "epoch": 8.731023102310232, "percentage": 43.66, "elapsed_time": "3:07:29", "remaining_time": "4:01:59", "throughput": 1488.96, "total_tokens": 16749744} {"current_steps": 79370, "total_steps": 181800, "loss": 0.0348, "lr": 3.464176109423374e-05, "epoch": 8.731573157315731, "percentage": 43.66, "elapsed_time": "3:07:30", "remaining_time": "4:01:58", "throughput": 1488.96, "total_tokens": 16750800} {"current_steps": 79375, "total_steps": 181800, "loss": 0.0514, "lr": 3.463954665945973e-05, "epoch": 8.732123212321232, "percentage": 43.66, "elapsed_time": "3:07:30", "remaining_time": "4:01:57", "throughput": 1488.96, "total_tokens": 16751856} {"current_steps": 79380, "total_steps": 181800, "loss": 0.0387, "lr": 3.463733213584264e-05, "epoch": 8.732673267326733, "percentage": 43.66, "elapsed_time": "3:07:31", "remaining_time": "4:01:57", "throughput": 1488.97, "total_tokens": 16752944} {"current_steps": 79385, "total_steps": 181800, "loss": 0.0149, "lr": 3.463511752340289e-05, "epoch": 8.733223322332233, "percentage": 43.67, "elapsed_time": "3:07:32", "remaining_time": "4:01:56", "throughput": 1488.97, "total_tokens": 16754000} {"current_steps": 79390, "total_steps": 181800, "loss": 0.0818, "lr": 3.463290282216088e-05, "epoch": 8.733773377337734, "percentage": 43.67, "elapsed_time": "3:07:32", "remaining_time": "4:01:55", "throughput": 1488.96, "total_tokens": 16754960} {"current_steps": 79395, "total_steps": 181800, "loss": 0.0232, "lr": 3.463068803213703e-05, "epoch": 8.734323432343235, "percentage": 43.67, "elapsed_time": "3:07:33", "remaining_time": "4:01:54", "throughput": 1488.97, "total_tokens": 16756048} {"current_steps": 79400, "total_steps": 181800, "loss": 0.0458, "lr": 3.4628473153351746e-05, "epoch": 8.734873487348734, "percentage": 43.67, "elapsed_time": "3:07:34", "remaining_time": "4:01:54", "throughput": 1488.97, "total_tokens": 16757136} {"current_steps": 79405, "total_steps": 181800, "loss": 0.0923, "lr": 3.4626258185825445e-05, "epoch": 8.735423542354235, "percentage": 43.68, "elapsed_time": "3:07:34", "remaining_time": "4:01:53", "throughput": 1488.98, "total_tokens": 16758224} {"current_steps": 79410, "total_steps": 181800, "loss": 0.0185, "lr": 3.462404312957854e-05, "epoch": 8.735973597359736, "percentage": 43.68, "elapsed_time": "3:07:35", "remaining_time": "4:01:52", "throughput": 1488.98, "total_tokens": 16759312} {"current_steps": 79415, "total_steps": 181800, "loss": 0.0259, "lr": 3.462182798463145e-05, "epoch": 8.736523652365236, "percentage": 43.68, "elapsed_time": "3:07:36", "remaining_time": "4:01:51", "throughput": 1488.98, "total_tokens": 16760336} {"current_steps": 79420, "total_steps": 181800, "loss": 0.0313, "lr": 3.4619612751004594e-05, "epoch": 8.737073707370737, "percentage": 43.69, "elapsed_time": "3:07:36", "remaining_time": "4:01:51", "throughput": 1488.99, "total_tokens": 16761424} {"current_steps": 79425, "total_steps": 181800, "loss": 0.0064, "lr": 3.461739742871838e-05, "epoch": 8.737623762376238, "percentage": 43.69, "elapsed_time": "3:07:37", "remaining_time": "4:01:50", "throughput": 1488.99, "total_tokens": 16762480} {"current_steps": 79430, "total_steps": 181800, "loss": 0.0368, "lr": 3.4615182017793226e-05, "epoch": 8.738173817381739, "percentage": 43.69, "elapsed_time": "3:07:38", "remaining_time": "4:01:49", "throughput": 1489.0, "total_tokens": 16763568} {"current_steps": 79435, "total_steps": 181800, "loss": 0.0257, "lr": 3.4612966518249556e-05, "epoch": 8.738723872387238, "percentage": 43.69, "elapsed_time": "3:07:38", "remaining_time": "4:01:49", "throughput": 1489.0, "total_tokens": 16764624} {"current_steps": 79440, "total_steps": 181800, "loss": 0.0063, "lr": 3.4610750930107784e-05, "epoch": 8.73927392739274, "percentage": 43.7, "elapsed_time": "3:07:39", "remaining_time": "4:01:48", "throughput": 1489.0, "total_tokens": 16765712} {"current_steps": 79445, "total_steps": 181800, "loss": 0.0801, "lr": 3.460853525338833e-05, "epoch": 8.73982398239824, "percentage": 43.7, "elapsed_time": "3:07:40", "remaining_time": "4:01:47", "throughput": 1489.01, "total_tokens": 16766800} {"current_steps": 79450, "total_steps": 181800, "loss": 0.0156, "lr": 3.460631948811162e-05, "epoch": 8.74037403740374, "percentage": 43.7, "elapsed_time": "3:07:41", "remaining_time": "4:01:46", "throughput": 1489.01, "total_tokens": 16767824} {"current_steps": 79455, "total_steps": 181800, "loss": 0.0115, "lr": 3.460410363429807e-05, "epoch": 8.74092409240924, "percentage": 43.7, "elapsed_time": "3:07:41", "remaining_time": "4:01:46", "throughput": 1489.01, "total_tokens": 16768848} {"current_steps": 79460, "total_steps": 181800, "loss": 0.0043, "lr": 3.460188769196811e-05, "epoch": 8.741474147414742, "percentage": 43.71, "elapsed_time": "3:07:42", "remaining_time": "4:01:45", "throughput": 1489.01, "total_tokens": 16769840} {"current_steps": 79465, "total_steps": 181800, "loss": 0.0253, "lr": 3.459967166114216e-05, "epoch": 8.742024202420241, "percentage": 43.71, "elapsed_time": "3:07:43", "remaining_time": "4:01:44", "throughput": 1489.01, "total_tokens": 16770864} {"current_steps": 79470, "total_steps": 181800, "loss": 0.0201, "lr": 3.459745554184064e-05, "epoch": 8.742574257425742, "percentage": 43.71, "elapsed_time": "3:07:43", "remaining_time": "4:01:43", "throughput": 1489.01, "total_tokens": 16771952} {"current_steps": 79475, "total_steps": 181800, "loss": 0.0364, "lr": 3.4595239334083974e-05, "epoch": 8.743124312431243, "percentage": 43.72, "elapsed_time": "3:07:44", "remaining_time": "4:01:43", "throughput": 1489.02, "total_tokens": 16773040} {"current_steps": 79480, "total_steps": 181800, "loss": 0.0289, "lr": 3.45930230378926e-05, "epoch": 8.743674367436743, "percentage": 43.72, "elapsed_time": "3:07:45", "remaining_time": "4:01:42", "throughput": 1489.02, "total_tokens": 16774160} {"current_steps": 79485, "total_steps": 181800, "loss": 0.0088, "lr": 3.459080665328693e-05, "epoch": 8.744224422442244, "percentage": 43.72, "elapsed_time": "3:07:45", "remaining_time": "4:01:41", "throughput": 1489.02, "total_tokens": 16775184} {"current_steps": 79490, "total_steps": 181800, "loss": 0.0642, "lr": 3.4588590180287394e-05, "epoch": 8.744774477447745, "percentage": 43.72, "elapsed_time": "3:07:46", "remaining_time": "4:01:40", "throughput": 1489.02, "total_tokens": 16776208} {"current_steps": 79495, "total_steps": 181800, "loss": 0.0061, "lr": 3.458637361891442e-05, "epoch": 8.745324532453246, "percentage": 43.73, "elapsed_time": "3:07:47", "remaining_time": "4:01:40", "throughput": 1489.03, "total_tokens": 16777296} {"current_steps": 79500, "total_steps": 181800, "loss": 0.0714, "lr": 3.458415696918846e-05, "epoch": 8.745874587458745, "percentage": 43.73, "elapsed_time": "3:07:47", "remaining_time": "4:01:39", "throughput": 1489.03, "total_tokens": 16778384} {"current_steps": 79505, "total_steps": 181800, "loss": 0.0584, "lr": 3.4581940231129905e-05, "epoch": 8.746424642464246, "percentage": 43.73, "elapsed_time": "3:07:48", "remaining_time": "4:01:38", "throughput": 1489.04, "total_tokens": 16779472} {"current_steps": 79510, "total_steps": 181800, "loss": 0.0118, "lr": 3.4579723404759213e-05, "epoch": 8.746974697469748, "percentage": 43.73, "elapsed_time": "3:07:49", "remaining_time": "4:01:38", "throughput": 1489.04, "total_tokens": 16780560} {"current_steps": 79515, "total_steps": 181800, "loss": 0.0147, "lr": 3.457750649009681e-05, "epoch": 8.747524752475247, "percentage": 43.74, "elapsed_time": "3:07:50", "remaining_time": "4:01:37", "throughput": 1489.05, "total_tokens": 16781648} {"current_steps": 79520, "total_steps": 181800, "loss": 0.0038, "lr": 3.4575289487163116e-05, "epoch": 8.748074807480748, "percentage": 43.74, "elapsed_time": "3:07:50", "remaining_time": "4:01:36", "throughput": 1489.05, "total_tokens": 16782640} {"current_steps": 79525, "total_steps": 181800, "loss": 0.0258, "lr": 3.457307239597858e-05, "epoch": 8.748624862486249, "percentage": 43.74, "elapsed_time": "3:07:51", "remaining_time": "4:01:35", "throughput": 1489.05, "total_tokens": 16783664} {"current_steps": 79530, "total_steps": 181800, "loss": 0.0234, "lr": 3.4570855216563626e-05, "epoch": 8.749174917491748, "percentage": 43.75, "elapsed_time": "3:07:52", "remaining_time": "4:01:35", "throughput": 1489.05, "total_tokens": 16784688} {"current_steps": 79535, "total_steps": 181800, "loss": 0.033, "lr": 3.4568637948938696e-05, "epoch": 8.74972497249725, "percentage": 43.75, "elapsed_time": "3:07:52", "remaining_time": "4:01:34", "throughput": 1489.05, "total_tokens": 16785744} {"current_steps": 79540, "total_steps": 181800, "loss": 0.0019, "lr": 3.456642059312421e-05, "epoch": 8.75027502750275, "percentage": 43.75, "elapsed_time": "3:07:53", "remaining_time": "4:01:33", "throughput": 1489.05, "total_tokens": 16786768} {"current_steps": 79545, "total_steps": 181800, "loss": 0.0077, "lr": 3.456420314914063e-05, "epoch": 8.750825082508252, "percentage": 43.75, "elapsed_time": "3:07:54", "remaining_time": "4:01:32", "throughput": 1489.05, "total_tokens": 16787824} {"current_steps": 79550, "total_steps": 181800, "loss": 0.087, "lr": 3.4561985617008375e-05, "epoch": 8.751375137513751, "percentage": 43.76, "elapsed_time": "3:07:54", "remaining_time": "4:01:32", "throughput": 1489.06, "total_tokens": 16788880} {"current_steps": 79555, "total_steps": 181800, "loss": 0.082, "lr": 3.455976799674789e-05, "epoch": 8.751925192519252, "percentage": 43.76, "elapsed_time": "3:07:55", "remaining_time": "4:01:31", "throughput": 1489.06, "total_tokens": 16789936} {"current_steps": 79560, "total_steps": 181800, "loss": 0.0118, "lr": 3.45575502883796e-05, "epoch": 8.752475247524753, "percentage": 43.76, "elapsed_time": "3:07:56", "remaining_time": "4:01:30", "throughput": 1489.06, "total_tokens": 16790992} {"current_steps": 79565, "total_steps": 181800, "loss": 0.0304, "lr": 3.4555332491923964e-05, "epoch": 8.753025302530252, "percentage": 43.77, "elapsed_time": "3:07:56", "remaining_time": "4:01:29", "throughput": 1489.06, "total_tokens": 16792016} {"current_steps": 79570, "total_steps": 181800, "loss": 0.0134, "lr": 3.455311460740141e-05, "epoch": 8.753575357535754, "percentage": 43.77, "elapsed_time": "3:07:57", "remaining_time": "4:01:29", "throughput": 1489.07, "total_tokens": 16793104} {"current_steps": 79575, "total_steps": 181800, "loss": 0.0259, "lr": 3.455089663483239e-05, "epoch": 8.754125412541255, "percentage": 43.77, "elapsed_time": "3:07:58", "remaining_time": "4:01:28", "throughput": 1489.07, "total_tokens": 16794128} {"current_steps": 79580, "total_steps": 181800, "loss": 0.0427, "lr": 3.454867857423733e-05, "epoch": 8.754675467546754, "percentage": 43.77, "elapsed_time": "3:07:58", "remaining_time": "4:01:27", "throughput": 1489.07, "total_tokens": 16795216} {"current_steps": 79585, "total_steps": 181800, "loss": 0.007, "lr": 3.454646042563668e-05, "epoch": 8.755225522552255, "percentage": 43.78, "elapsed_time": "3:07:59", "remaining_time": "4:01:27", "throughput": 1489.08, "total_tokens": 16796272} {"current_steps": 79590, "total_steps": 181800, "loss": 0.026, "lr": 3.454424218905089e-05, "epoch": 8.755775577557756, "percentage": 43.78, "elapsed_time": "3:08:00", "remaining_time": "4:01:26", "throughput": 1489.09, "total_tokens": 16797456} {"current_steps": 79595, "total_steps": 181800, "loss": 0.0038, "lr": 3.454202386450039e-05, "epoch": 8.756325632563257, "percentage": 43.78, "elapsed_time": "3:08:01", "remaining_time": "4:01:25", "throughput": 1489.08, "total_tokens": 16798416} {"current_steps": 79600, "total_steps": 181800, "loss": 0.0284, "lr": 3.453980545200565e-05, "epoch": 8.756875687568757, "percentage": 43.78, "elapsed_time": "3:08:01", "remaining_time": "4:01:24", "throughput": 1489.09, "total_tokens": 16799472} {"current_steps": 79605, "total_steps": 181800, "loss": 0.0612, "lr": 3.45375869515871e-05, "epoch": 8.757425742574258, "percentage": 43.79, "elapsed_time": "3:08:02", "remaining_time": "4:01:24", "throughput": 1489.09, "total_tokens": 16800528} {"current_steps": 79610, "total_steps": 181800, "loss": 0.0077, "lr": 3.453536836326518e-05, "epoch": 8.757975797579759, "percentage": 43.79, "elapsed_time": "3:08:03", "remaining_time": "4:01:23", "throughput": 1489.09, "total_tokens": 16801552} {"current_steps": 79615, "total_steps": 181800, "loss": 0.0464, "lr": 3.4533149687060344e-05, "epoch": 8.758525852585258, "percentage": 43.79, "elapsed_time": "3:08:03", "remaining_time": "4:01:22", "throughput": 1489.1, "total_tokens": 16802672} {"current_steps": 79620, "total_steps": 181800, "loss": 0.0528, "lr": 3.4530930922993046e-05, "epoch": 8.75907590759076, "percentage": 43.8, "elapsed_time": "3:08:04", "remaining_time": "4:01:21", "throughput": 1489.1, "total_tokens": 16803760} {"current_steps": 79625, "total_steps": 181800, "loss": 0.001, "lr": 3.4528712071083737e-05, "epoch": 8.75962596259626, "percentage": 43.8, "elapsed_time": "3:08:05", "remaining_time": "4:01:21", "throughput": 1489.11, "total_tokens": 16804848} {"current_steps": 79630, "total_steps": 181800, "loss": 0.1651, "lr": 3.452649313135285e-05, "epoch": 8.76017601760176, "percentage": 43.8, "elapsed_time": "3:08:05", "remaining_time": "4:01:20", "throughput": 1489.11, "total_tokens": 16805872} {"current_steps": 79635, "total_steps": 181800, "loss": 0.1113, "lr": 3.452427410382085e-05, "epoch": 8.76072607260726, "percentage": 43.8, "elapsed_time": "3:08:06", "remaining_time": "4:01:19", "throughput": 1489.11, "total_tokens": 16806960} {"current_steps": 79640, "total_steps": 181800, "loss": 0.026, "lr": 3.4522054988508185e-05, "epoch": 8.761276127612762, "percentage": 43.81, "elapsed_time": "3:08:07", "remaining_time": "4:01:18", "throughput": 1489.11, "total_tokens": 16807984} {"current_steps": 79645, "total_steps": 181800, "loss": 0.0276, "lr": 3.451983578543531e-05, "epoch": 8.761826182618261, "percentage": 43.81, "elapsed_time": "3:08:07", "remaining_time": "4:01:18", "throughput": 1489.11, "total_tokens": 16809008} {"current_steps": 79650, "total_steps": 181800, "loss": 0.0504, "lr": 3.451761649462268e-05, "epoch": 8.762376237623762, "percentage": 43.81, "elapsed_time": "3:08:08", "remaining_time": "4:01:17", "throughput": 1489.11, "total_tokens": 16810064} {"current_steps": 79655, "total_steps": 181800, "loss": 0.0132, "lr": 3.451539711609074e-05, "epoch": 8.762926292629263, "percentage": 43.81, "elapsed_time": "3:08:09", "remaining_time": "4:01:16", "throughput": 1489.11, "total_tokens": 16811088} {"current_steps": 79660, "total_steps": 181800, "loss": 0.0322, "lr": 3.451317764985995e-05, "epoch": 8.763476347634764, "percentage": 43.82, "elapsed_time": "3:08:10", "remaining_time": "4:01:16", "throughput": 1489.12, "total_tokens": 16812208} {"current_steps": 79665, "total_steps": 181800, "loss": 0.0073, "lr": 3.451095809595077e-05, "epoch": 8.764026402640264, "percentage": 43.82, "elapsed_time": "3:08:10", "remaining_time": "4:01:15", "throughput": 1489.11, "total_tokens": 16813168} {"current_steps": 79670, "total_steps": 181800, "loss": 0.1182, "lr": 3.4508738454383656e-05, "epoch": 8.764576457645765, "percentage": 43.82, "elapsed_time": "3:08:11", "remaining_time": "4:01:14", "throughput": 1489.12, "total_tokens": 16814256} {"current_steps": 79675, "total_steps": 181800, "loss": 0.0111, "lr": 3.450651872517906e-05, "epoch": 8.765126512651266, "percentage": 43.83, "elapsed_time": "3:08:12", "remaining_time": "4:01:13", "throughput": 1489.12, "total_tokens": 16815280} {"current_steps": 79680, "total_steps": 181800, "loss": 0.0087, "lr": 3.4504298908357444e-05, "epoch": 8.765676567656765, "percentage": 43.83, "elapsed_time": "3:08:12", "remaining_time": "4:01:13", "throughput": 1489.12, "total_tokens": 16816336} {"current_steps": 79685, "total_steps": 181800, "loss": 0.0499, "lr": 3.450207900393926e-05, "epoch": 8.766226622662266, "percentage": 43.83, "elapsed_time": "3:08:13", "remaining_time": "4:01:12", "throughput": 1489.12, "total_tokens": 16817392} {"current_steps": 79690, "total_steps": 181800, "loss": 0.0063, "lr": 3.449985901194498e-05, "epoch": 8.766776677667767, "percentage": 43.83, "elapsed_time": "3:08:14", "remaining_time": "4:01:11", "throughput": 1489.13, "total_tokens": 16818480} {"current_steps": 79695, "total_steps": 181800, "loss": 0.0548, "lr": 3.449763893239505e-05, "epoch": 8.767326732673267, "percentage": 43.84, "elapsed_time": "3:08:14", "remaining_time": "4:01:10", "throughput": 1489.13, "total_tokens": 16819472} {"current_steps": 79700, "total_steps": 181800, "loss": 0.0033, "lr": 3.4495418765309946e-05, "epoch": 8.767876787678768, "percentage": 43.84, "elapsed_time": "3:08:15", "remaining_time": "4:01:10", "throughput": 1489.12, "total_tokens": 16820496} {"current_steps": 79705, "total_steps": 181800, "loss": 0.0121, "lr": 3.4493198510710125e-05, "epoch": 8.768426842684269, "percentage": 43.84, "elapsed_time": "3:08:16", "remaining_time": "4:01:09", "throughput": 1489.13, "total_tokens": 16821552} {"current_steps": 79710, "total_steps": 181800, "loss": 0.0216, "lr": 3.449097816861604e-05, "epoch": 8.768976897689768, "percentage": 43.84, "elapsed_time": "3:08:16", "remaining_time": "4:01:08", "throughput": 1489.13, "total_tokens": 16822640} {"current_steps": 79715, "total_steps": 181800, "loss": 0.0199, "lr": 3.448875773904817e-05, "epoch": 8.76952695269527, "percentage": 43.85, "elapsed_time": "3:08:17", "remaining_time": "4:01:08", "throughput": 1489.14, "total_tokens": 16823728} {"current_steps": 79720, "total_steps": 181800, "loss": 0.1181, "lr": 3.448653722202697e-05, "epoch": 8.77007700770077, "percentage": 43.85, "elapsed_time": "3:08:18", "remaining_time": "4:01:07", "throughput": 1489.13, "total_tokens": 16824720} {"current_steps": 79725, "total_steps": 181800, "loss": 0.0126, "lr": 3.448431661757291e-05, "epoch": 8.770627062706271, "percentage": 43.85, "elapsed_time": "3:08:19", "remaining_time": "4:01:06", "throughput": 1489.14, "total_tokens": 16825776} {"current_steps": 79730, "total_steps": 181800, "loss": 0.0164, "lr": 3.448209592570646e-05, "epoch": 8.77117711771177, "percentage": 43.86, "elapsed_time": "3:08:19", "remaining_time": "4:01:05", "throughput": 1489.14, "total_tokens": 16826832} {"current_steps": 79735, "total_steps": 181800, "loss": 0.0029, "lr": 3.447987514644807e-05, "epoch": 8.771727172717272, "percentage": 43.86, "elapsed_time": "3:08:20", "remaining_time": "4:01:05", "throughput": 1489.14, "total_tokens": 16827920} {"current_steps": 79740, "total_steps": 181800, "loss": 0.0484, "lr": 3.4477654279818226e-05, "epoch": 8.772277227722773, "percentage": 43.86, "elapsed_time": "3:08:21", "remaining_time": "4:01:04", "throughput": 1489.14, "total_tokens": 16828912} {"current_steps": 79745, "total_steps": 181800, "loss": 0.007, "lr": 3.4475433325837395e-05, "epoch": 8.772827282728272, "percentage": 43.86, "elapsed_time": "3:08:21", "remaining_time": "4:01:03", "throughput": 1489.12, "total_tokens": 16829936} {"current_steps": 79750, "total_steps": 181800, "loss": 0.0429, "lr": 3.447321228452604e-05, "epoch": 8.773377337733773, "percentage": 43.87, "elapsed_time": "3:08:22", "remaining_time": "4:01:03", "throughput": 1489.12, "total_tokens": 16830960} {"current_steps": 79755, "total_steps": 181800, "loss": 0.0243, "lr": 3.4470991155904625e-05, "epoch": 8.773927392739274, "percentage": 43.87, "elapsed_time": "3:08:23", "remaining_time": "4:01:02", "throughput": 1489.12, "total_tokens": 16832016} {"current_steps": 79760, "total_steps": 181800, "loss": 0.0611, "lr": 3.446876993999364e-05, "epoch": 8.774477447744774, "percentage": 43.87, "elapsed_time": "3:08:24", "remaining_time": "4:01:01", "throughput": 1489.12, "total_tokens": 16833072} {"current_steps": 79765, "total_steps": 181800, "loss": 0.0098, "lr": 3.4466548636813536e-05, "epoch": 8.775027502750275, "percentage": 43.88, "elapsed_time": "3:08:24", "remaining_time": "4:01:00", "throughput": 1489.13, "total_tokens": 16834160} {"current_steps": 79770, "total_steps": 181800, "loss": 0.0999, "lr": 3.44643272463848e-05, "epoch": 8.775577557755776, "percentage": 43.88, "elapsed_time": "3:08:25", "remaining_time": "4:01:00", "throughput": 1489.13, "total_tokens": 16835216} {"current_steps": 79775, "total_steps": 181800, "loss": 0.002, "lr": 3.4462105768727906e-05, "epoch": 8.776127612761275, "percentage": 43.88, "elapsed_time": "3:08:26", "remaining_time": "4:00:59", "throughput": 1489.14, "total_tokens": 16836336} {"current_steps": 79780, "total_steps": 181800, "loss": 0.0148, "lr": 3.4459884203863315e-05, "epoch": 8.776677667766776, "percentage": 43.88, "elapsed_time": "3:08:26", "remaining_time": "4:00:58", "throughput": 1489.14, "total_tokens": 16837456} {"current_steps": 79785, "total_steps": 181800, "loss": 0.0229, "lr": 3.4457662551811516e-05, "epoch": 8.777227722772277, "percentage": 43.89, "elapsed_time": "3:08:27", "remaining_time": "4:00:58", "throughput": 1489.15, "total_tokens": 16838512} {"current_steps": 79790, "total_steps": 181800, "loss": 0.0079, "lr": 3.445544081259298e-05, "epoch": 8.777777777777779, "percentage": 43.89, "elapsed_time": "3:08:28", "remaining_time": "4:00:57", "throughput": 1489.15, "total_tokens": 16839536} {"current_steps": 79795, "total_steps": 181800, "loss": 0.0696, "lr": 3.445321898622818e-05, "epoch": 8.778327832783278, "percentage": 43.89, "elapsed_time": "3:08:28", "remaining_time": "4:00:56", "throughput": 1489.15, "total_tokens": 16840624} {"current_steps": 79800, "total_steps": 181800, "loss": 0.115, "lr": 3.4450997072737604e-05, "epoch": 8.778877887788779, "percentage": 43.89, "elapsed_time": "3:08:29", "remaining_time": "4:00:55", "throughput": 1489.16, "total_tokens": 16841712} {"current_steps": 79805, "total_steps": 181800, "loss": 0.0473, "lr": 3.4448775072141714e-05, "epoch": 8.77942794279428, "percentage": 43.9, "elapsed_time": "3:08:30", "remaining_time": "4:00:55", "throughput": 1489.16, "total_tokens": 16842800} {"current_steps": 79810, "total_steps": 181800, "loss": 0.0165, "lr": 3.444655298446099e-05, "epoch": 8.77997799779978, "percentage": 43.9, "elapsed_time": "3:08:30", "remaining_time": "4:00:54", "throughput": 1489.16, "total_tokens": 16843824} {"current_steps": 79815, "total_steps": 181800, "loss": 0.0189, "lr": 3.444433080971594e-05, "epoch": 8.78052805280528, "percentage": 43.9, "elapsed_time": "3:08:31", "remaining_time": "4:00:53", "throughput": 1489.16, "total_tokens": 16844848} {"current_steps": 79820, "total_steps": 181800, "loss": 0.032, "lr": 3.444210854792702e-05, "epoch": 8.781078107810782, "percentage": 43.91, "elapsed_time": "3:08:32", "remaining_time": "4:00:52", "throughput": 1489.16, "total_tokens": 16845872} {"current_steps": 79825, "total_steps": 181800, "loss": 0.008, "lr": 3.443988619911471e-05, "epoch": 8.781628162816281, "percentage": 43.91, "elapsed_time": "3:08:33", "remaining_time": "4:00:52", "throughput": 1489.16, "total_tokens": 16846928} {"current_steps": 79830, "total_steps": 181800, "loss": 0.0518, "lr": 3.44376637632995e-05, "epoch": 8.782178217821782, "percentage": 43.91, "elapsed_time": "3:08:33", "remaining_time": "4:00:51", "throughput": 1489.17, "total_tokens": 16848048} {"current_steps": 79835, "total_steps": 181800, "loss": 0.0111, "lr": 3.443544124050187e-05, "epoch": 8.782728272827283, "percentage": 43.91, "elapsed_time": "3:08:34", "remaining_time": "4:00:50", "throughput": 1489.17, "total_tokens": 16849104} {"current_steps": 79840, "total_steps": 181800, "loss": 0.0809, "lr": 3.443321863074231e-05, "epoch": 8.783278327832782, "percentage": 43.92, "elapsed_time": "3:08:35", "remaining_time": "4:00:49", "throughput": 1489.17, "total_tokens": 16850160} {"current_steps": 79845, "total_steps": 181800, "loss": 0.0054, "lr": 3.44309959340413e-05, "epoch": 8.783828382838283, "percentage": 43.92, "elapsed_time": "3:08:35", "remaining_time": "4:00:49", "throughput": 1489.17, "total_tokens": 16851120} {"current_steps": 79850, "total_steps": 181800, "loss": 0.1109, "lr": 3.442877315041933e-05, "epoch": 8.784378437843785, "percentage": 43.92, "elapsed_time": "3:08:36", "remaining_time": "4:00:48", "throughput": 1489.17, "total_tokens": 16852144} {"current_steps": 79855, "total_steps": 181800, "loss": 0.0154, "lr": 3.442655027989687e-05, "epoch": 8.784928492849286, "percentage": 43.92, "elapsed_time": "3:08:37", "remaining_time": "4:00:47", "throughput": 1489.17, "total_tokens": 16853232} {"current_steps": 79860, "total_steps": 181800, "loss": 0.0446, "lr": 3.442432732249443e-05, "epoch": 8.785478547854785, "percentage": 43.93, "elapsed_time": "3:08:37", "remaining_time": "4:00:47", "throughput": 1489.18, "total_tokens": 16854320} {"current_steps": 79865, "total_steps": 181800, "loss": 0.0445, "lr": 3.442210427823248e-05, "epoch": 8.786028602860286, "percentage": 43.93, "elapsed_time": "3:08:38", "remaining_time": "4:00:46", "throughput": 1489.19, "total_tokens": 16855440} {"current_steps": 79870, "total_steps": 181800, "loss": 0.0692, "lr": 3.4419881147131514e-05, "epoch": 8.786578657865787, "percentage": 43.93, "elapsed_time": "3:08:39", "remaining_time": "4:00:45", "throughput": 1489.19, "total_tokens": 16856496} {"current_steps": 79875, "total_steps": 181800, "loss": 0.0114, "lr": 3.441765792921203e-05, "epoch": 8.787128712871286, "percentage": 43.94, "elapsed_time": "3:08:39", "remaining_time": "4:00:44", "throughput": 1489.19, "total_tokens": 16857584} {"current_steps": 79880, "total_steps": 181800, "loss": 0.0033, "lr": 3.441543462449451e-05, "epoch": 8.787678767876788, "percentage": 43.94, "elapsed_time": "3:08:40", "remaining_time": "4:00:44", "throughput": 1489.2, "total_tokens": 16858672} {"current_steps": 79885, "total_steps": 181800, "loss": 0.0351, "lr": 3.4413211232999446e-05, "epoch": 8.788228822882289, "percentage": 43.94, "elapsed_time": "3:08:41", "remaining_time": "4:00:43", "throughput": 1489.2, "total_tokens": 16859664} {"current_steps": 79890, "total_steps": 181800, "loss": 0.0265, "lr": 3.441098775474734e-05, "epoch": 8.788778877887788, "percentage": 43.94, "elapsed_time": "3:08:42", "remaining_time": "4:00:42", "throughput": 1489.19, "total_tokens": 16860688} {"current_steps": 79895, "total_steps": 181800, "loss": 0.1225, "lr": 3.440876418975867e-05, "epoch": 8.789328932893289, "percentage": 43.95, "elapsed_time": "3:08:42", "remaining_time": "4:00:41", "throughput": 1489.2, "total_tokens": 16861744} {"current_steps": 79900, "total_steps": 181800, "loss": 0.0318, "lr": 3.4406540538053935e-05, "epoch": 8.78987898789879, "percentage": 43.95, "elapsed_time": "3:08:43", "remaining_time": "4:00:41", "throughput": 1489.2, "total_tokens": 16862832} {"current_steps": 79905, "total_steps": 181800, "loss": 0.0592, "lr": 3.4404316799653626e-05, "epoch": 8.79042904290429, "percentage": 43.95, "elapsed_time": "3:08:44", "remaining_time": "4:00:40", "throughput": 1489.21, "total_tokens": 16863920} {"current_steps": 79910, "total_steps": 181800, "loss": 0.0809, "lr": 3.4402092974578245e-05, "epoch": 8.79097909790979, "percentage": 43.95, "elapsed_time": "3:08:44", "remaining_time": "4:00:39", "throughput": 1489.21, "total_tokens": 16864944} {"current_steps": 79915, "total_steps": 181800, "loss": 0.0039, "lr": 3.4399869062848284e-05, "epoch": 8.791529152915292, "percentage": 43.96, "elapsed_time": "3:08:45", "remaining_time": "4:00:39", "throughput": 1489.21, "total_tokens": 16866000} {"current_steps": 79920, "total_steps": 181800, "loss": 0.0542, "lr": 3.439764506448424e-05, "epoch": 8.792079207920793, "percentage": 43.96, "elapsed_time": "3:08:46", "remaining_time": "4:00:38", "throughput": 1489.21, "total_tokens": 16866992} {"current_steps": 79925, "total_steps": 181800, "loss": 0.0595, "lr": 3.439542097950661e-05, "epoch": 8.792629262926292, "percentage": 43.96, "elapsed_time": "3:08:46", "remaining_time": "4:00:37", "throughput": 1489.21, "total_tokens": 16868080} {"current_steps": 79930, "total_steps": 181800, "loss": 0.0037, "lr": 3.439319680793589e-05, "epoch": 8.793179317931793, "percentage": 43.97, "elapsed_time": "3:08:47", "remaining_time": "4:00:36", "throughput": 1489.21, "total_tokens": 16869104} {"current_steps": 79935, "total_steps": 181800, "loss": 0.0229, "lr": 3.439097254979259e-05, "epoch": 8.793729372937294, "percentage": 43.97, "elapsed_time": "3:08:48", "remaining_time": "4:00:36", "throughput": 1489.22, "total_tokens": 16870160} {"current_steps": 79940, "total_steps": 181800, "loss": 0.1138, "lr": 3.43887482050972e-05, "epoch": 8.794279427942794, "percentage": 43.97, "elapsed_time": "3:08:48", "remaining_time": "4:00:35", "throughput": 1489.22, "total_tokens": 16871248} {"current_steps": 79945, "total_steps": 181800, "loss": 0.0157, "lr": 3.438652377387022e-05, "epoch": 8.794829482948295, "percentage": 43.97, "elapsed_time": "3:08:49", "remaining_time": "4:00:34", "throughput": 1489.22, "total_tokens": 16872304} {"current_steps": 79950, "total_steps": 181800, "loss": 0.0116, "lr": 3.438429925613216e-05, "epoch": 8.795379537953796, "percentage": 43.98, "elapsed_time": "3:08:50", "remaining_time": "4:00:33", "throughput": 1489.23, "total_tokens": 16873360} {"current_steps": 79955, "total_steps": 181800, "loss": 0.0074, "lr": 3.4382074651903505e-05, "epoch": 8.795929592959295, "percentage": 43.98, "elapsed_time": "3:08:50", "remaining_time": "4:00:33", "throughput": 1489.23, "total_tokens": 16874384} {"current_steps": 79960, "total_steps": 181800, "loss": 0.006, "lr": 3.437984996120478e-05, "epoch": 8.796479647964796, "percentage": 43.98, "elapsed_time": "3:08:51", "remaining_time": "4:00:32", "throughput": 1489.23, "total_tokens": 16875408} {"current_steps": 79965, "total_steps": 181800, "loss": 0.1127, "lr": 3.437762518405648e-05, "epoch": 8.797029702970297, "percentage": 43.99, "elapsed_time": "3:08:52", "remaining_time": "4:00:31", "throughput": 1489.23, "total_tokens": 16876496} {"current_steps": 79970, "total_steps": 181800, "loss": 0.05, "lr": 3.43754003204791e-05, "epoch": 8.797579757975798, "percentage": 43.99, "elapsed_time": "3:08:53", "remaining_time": "4:00:30", "throughput": 1489.24, "total_tokens": 16877584} {"current_steps": 79975, "total_steps": 181800, "loss": 0.003, "lr": 3.437317537049316e-05, "epoch": 8.798129812981298, "percentage": 43.99, "elapsed_time": "3:08:53", "remaining_time": "4:00:30", "throughput": 1489.24, "total_tokens": 16878672} {"current_steps": 79980, "total_steps": 181800, "loss": 0.0051, "lr": 3.437095033411916e-05, "epoch": 8.798679867986799, "percentage": 43.99, "elapsed_time": "3:08:54", "remaining_time": "4:00:29", "throughput": 1489.24, "total_tokens": 16879664} {"current_steps": 79985, "total_steps": 181800, "loss": 0.0239, "lr": 3.436872521137761e-05, "epoch": 8.7992299229923, "percentage": 44.0, "elapsed_time": "3:08:55", "remaining_time": "4:00:28", "throughput": 1489.25, "total_tokens": 16880816} {"current_steps": 79990, "total_steps": 181800, "loss": 0.1092, "lr": 3.436650000228901e-05, "epoch": 8.7997799779978, "percentage": 44.0, "elapsed_time": "3:08:55", "remaining_time": "4:00:28", "throughput": 1489.25, "total_tokens": 16881808} {"current_steps": 79995, "total_steps": 181800, "loss": 0.0271, "lr": 3.436427470687388e-05, "epoch": 8.8003300330033, "percentage": 44.0, "elapsed_time": "3:08:56", "remaining_time": "4:00:27", "throughput": 1489.25, "total_tokens": 16882896} {"current_steps": 80000, "total_steps": 181800, "loss": 0.0666, "lr": 3.4362049325152714e-05, "epoch": 8.800880088008801, "percentage": 44.0, "elapsed_time": "3:08:57", "remaining_time": "4:00:26", "throughput": 1489.26, "total_tokens": 16884016} {"current_steps": 80005, "total_steps": 181800, "loss": 0.0292, "lr": 3.4359823857146045e-05, "epoch": 8.8014301430143, "percentage": 44.01, "elapsed_time": "3:08:57", "remaining_time": "4:00:25", "throughput": 1489.26, "total_tokens": 16885072} {"current_steps": 80010, "total_steps": 181800, "loss": 0.0588, "lr": 3.435759830287436e-05, "epoch": 8.801980198019802, "percentage": 44.01, "elapsed_time": "3:08:58", "remaining_time": "4:00:25", "throughput": 1489.26, "total_tokens": 16886064} {"current_steps": 80015, "total_steps": 181800, "loss": 0.0671, "lr": 3.435537266235818e-05, "epoch": 8.802530253025303, "percentage": 44.01, "elapsed_time": "3:08:59", "remaining_time": "4:00:24", "throughput": 1489.26, "total_tokens": 16887120} {"current_steps": 80020, "total_steps": 181800, "loss": 0.055, "lr": 3.435314693561803e-05, "epoch": 8.803080308030804, "percentage": 44.02, "elapsed_time": "3:08:59", "remaining_time": "4:00:23", "throughput": 1489.26, "total_tokens": 16888112} {"current_steps": 80025, "total_steps": 181800, "loss": 0.028, "lr": 3.435092112267441e-05, "epoch": 8.803630363036303, "percentage": 44.02, "elapsed_time": "3:09:00", "remaining_time": "4:00:22", "throughput": 1489.26, "total_tokens": 16889168} {"current_steps": 80030, "total_steps": 181800, "loss": 0.0286, "lr": 3.434869522354783e-05, "epoch": 8.804180418041804, "percentage": 44.02, "elapsed_time": "3:09:01", "remaining_time": "4:00:22", "throughput": 1489.26, "total_tokens": 16890224} {"current_steps": 80035, "total_steps": 181800, "loss": 0.1549, "lr": 3.434646923825882e-05, "epoch": 8.804730473047305, "percentage": 44.02, "elapsed_time": "3:09:02", "remaining_time": "4:00:21", "throughput": 1489.27, "total_tokens": 16891280} {"current_steps": 80040, "total_steps": 181800, "loss": 0.0074, "lr": 3.434424316682787e-05, "epoch": 8.805280528052805, "percentage": 44.03, "elapsed_time": "3:09:02", "remaining_time": "4:00:20", "throughput": 1489.27, "total_tokens": 16892304} {"current_steps": 80045, "total_steps": 181800, "loss": 0.0207, "lr": 3.434201700927554e-05, "epoch": 8.805830583058306, "percentage": 44.03, "elapsed_time": "3:09:03", "remaining_time": "4:00:19", "throughput": 1489.27, "total_tokens": 16893328} {"current_steps": 80050, "total_steps": 181800, "loss": 0.0158, "lr": 3.4339790765622305e-05, "epoch": 8.806380638063807, "percentage": 44.03, "elapsed_time": "3:09:04", "remaining_time": "4:00:19", "throughput": 1489.27, "total_tokens": 16894416} {"current_steps": 80055, "total_steps": 181800, "loss": 0.0887, "lr": 3.43375644358887e-05, "epoch": 8.806930693069306, "percentage": 44.03, "elapsed_time": "3:09:04", "remaining_time": "4:00:18", "throughput": 1489.28, "total_tokens": 16895504} {"current_steps": 80060, "total_steps": 181800, "loss": 0.0053, "lr": 3.4335338020095254e-05, "epoch": 8.807480748074807, "percentage": 44.04, "elapsed_time": "3:09:05", "remaining_time": "4:00:17", "throughput": 1489.27, "total_tokens": 16896496} {"current_steps": 80065, "total_steps": 181800, "loss": 0.0824, "lr": 3.433311151826247e-05, "epoch": 8.808030803080309, "percentage": 44.04, "elapsed_time": "3:09:06", "remaining_time": "4:00:17", "throughput": 1489.27, "total_tokens": 16897488} {"current_steps": 80070, "total_steps": 181800, "loss": 0.0074, "lr": 3.4330884930410876e-05, "epoch": 8.808580858085808, "percentage": 44.04, "elapsed_time": "3:09:06", "remaining_time": "4:00:16", "throughput": 1489.27, "total_tokens": 16898512} {"current_steps": 80075, "total_steps": 181800, "loss": 0.1722, "lr": 3.4328658256560995e-05, "epoch": 8.809130913091309, "percentage": 44.05, "elapsed_time": "3:09:07", "remaining_time": "4:00:15", "throughput": 1489.27, "total_tokens": 16899568} {"current_steps": 80080, "total_steps": 181800, "loss": 0.0973, "lr": 3.432643149673336e-05, "epoch": 8.80968096809681, "percentage": 44.05, "elapsed_time": "3:09:08", "remaining_time": "4:00:14", "throughput": 1489.27, "total_tokens": 16900624} {"current_steps": 80085, "total_steps": 181800, "loss": 0.0231, "lr": 3.432420465094846e-05, "epoch": 8.810231023102311, "percentage": 44.05, "elapsed_time": "3:09:08", "remaining_time": "4:00:14", "throughput": 1489.27, "total_tokens": 16901616} {"current_steps": 80090, "total_steps": 181800, "loss": 0.0417, "lr": 3.432197771922685e-05, "epoch": 8.81078107810781, "percentage": 44.05, "elapsed_time": "3:09:09", "remaining_time": "4:00:13", "throughput": 1489.27, "total_tokens": 16902672} {"current_steps": 80095, "total_steps": 181800, "loss": 0.0079, "lr": 3.431975070158904e-05, "epoch": 8.811331133113312, "percentage": 44.06, "elapsed_time": "3:09:10", "remaining_time": "4:00:12", "throughput": 1489.27, "total_tokens": 16903696} {"current_steps": 80100, "total_steps": 181800, "loss": 0.0376, "lr": 3.431752359805557e-05, "epoch": 8.811881188118813, "percentage": 44.06, "elapsed_time": "3:09:11", "remaining_time": "4:00:11", "throughput": 1489.27, "total_tokens": 16904688} {"current_steps": 80105, "total_steps": 181800, "loss": 0.1031, "lr": 3.431529640864695e-05, "epoch": 8.812431243124312, "percentage": 44.06, "elapsed_time": "3:09:11", "remaining_time": "4:00:11", "throughput": 1489.27, "total_tokens": 16905744} {"current_steps": 80110, "total_steps": 181800, "loss": 0.0122, "lr": 3.4313069133383705e-05, "epoch": 8.812981298129813, "percentage": 44.06, "elapsed_time": "3:09:12", "remaining_time": "4:00:10", "throughput": 1489.27, "total_tokens": 16906736} {"current_steps": 80115, "total_steps": 181800, "loss": 0.0947, "lr": 3.431084177228638e-05, "epoch": 8.813531353135314, "percentage": 44.07, "elapsed_time": "3:09:13", "remaining_time": "4:00:09", "throughput": 1489.27, "total_tokens": 16907792} {"current_steps": 80120, "total_steps": 181800, "loss": 0.0269, "lr": 3.4308614325375486e-05, "epoch": 8.814081408140813, "percentage": 44.07, "elapsed_time": "3:09:13", "remaining_time": "4:00:09", "throughput": 1489.27, "total_tokens": 16908848} {"current_steps": 80125, "total_steps": 181800, "loss": 0.0193, "lr": 3.4306386792671575e-05, "epoch": 8.814631463146315, "percentage": 44.07, "elapsed_time": "3:09:14", "remaining_time": "4:00:08", "throughput": 1489.27, "total_tokens": 16909872} {"current_steps": 80130, "total_steps": 181800, "loss": 0.045, "lr": 3.430415917419515e-05, "epoch": 8.815181518151816, "percentage": 44.08, "elapsed_time": "3:09:15", "remaining_time": "4:00:07", "throughput": 1489.28, "total_tokens": 16910928} {"current_steps": 80135, "total_steps": 181800, "loss": 0.0131, "lr": 3.430193146996676e-05, "epoch": 8.815731573157315, "percentage": 44.08, "elapsed_time": "3:09:15", "remaining_time": "4:00:06", "throughput": 1489.27, "total_tokens": 16911952} {"current_steps": 80140, "total_steps": 181800, "loss": 0.0297, "lr": 3.429970368000693e-05, "epoch": 8.816281628162816, "percentage": 44.08, "elapsed_time": "3:09:16", "remaining_time": "4:00:06", "throughput": 1489.28, "total_tokens": 16913040} {"current_steps": 80145, "total_steps": 181800, "loss": 0.0229, "lr": 3.4297475804336185e-05, "epoch": 8.816831683168317, "percentage": 44.08, "elapsed_time": "3:09:17", "remaining_time": "4:00:05", "throughput": 1489.28, "total_tokens": 16914096} {"current_steps": 80150, "total_steps": 181800, "loss": 0.0057, "lr": 3.429524784297508e-05, "epoch": 8.817381738173818, "percentage": 44.09, "elapsed_time": "3:09:17", "remaining_time": "4:00:04", "throughput": 1489.28, "total_tokens": 16915152} {"current_steps": 80155, "total_steps": 181800, "loss": 0.0226, "lr": 3.429301979594413e-05, "epoch": 8.817931793179318, "percentage": 44.09, "elapsed_time": "3:09:18", "remaining_time": "4:00:03", "throughput": 1489.29, "total_tokens": 16916208} {"current_steps": 80160, "total_steps": 181800, "loss": 0.0535, "lr": 3.429079166326388e-05, "epoch": 8.818481848184819, "percentage": 44.09, "elapsed_time": "3:09:19", "remaining_time": "4:00:03", "throughput": 1489.28, "total_tokens": 16917200} {"current_steps": 80165, "total_steps": 181800, "loss": 0.0196, "lr": 3.428856344495485e-05, "epoch": 8.81903190319032, "percentage": 44.1, "elapsed_time": "3:09:19", "remaining_time": "4:00:02", "throughput": 1489.28, "total_tokens": 16918192} {"current_steps": 80170, "total_steps": 181800, "loss": 0.0934, "lr": 3.428633514103759e-05, "epoch": 8.819581958195819, "percentage": 44.1, "elapsed_time": "3:09:20", "remaining_time": "4:00:01", "throughput": 1489.28, "total_tokens": 16919216} {"current_steps": 80175, "total_steps": 181800, "loss": 0.0627, "lr": 3.4284106751532655e-05, "epoch": 8.82013201320132, "percentage": 44.1, "elapsed_time": "3:09:21", "remaining_time": "4:00:00", "throughput": 1489.28, "total_tokens": 16920272} {"current_steps": 80180, "total_steps": 181800, "loss": 0.0211, "lr": 3.4281878276460544e-05, "epoch": 8.820682068206821, "percentage": 44.1, "elapsed_time": "3:09:22", "remaining_time": "4:00:00", "throughput": 1489.28, "total_tokens": 16921296} {"current_steps": 80185, "total_steps": 181800, "loss": 0.0106, "lr": 3.4279649715841825e-05, "epoch": 8.82123212321232, "percentage": 44.11, "elapsed_time": "3:09:22", "remaining_time": "3:59:59", "throughput": 1489.29, "total_tokens": 16922448} {"current_steps": 80190, "total_steps": 181800, "loss": 0.0347, "lr": 3.427742106969701e-05, "epoch": 8.821782178217822, "percentage": 44.11, "elapsed_time": "3:09:23", "remaining_time": "3:59:58", "throughput": 1489.3, "total_tokens": 16923504} {"current_steps": 80195, "total_steps": 181800, "loss": 0.0027, "lr": 3.427519233804667e-05, "epoch": 8.822332233223323, "percentage": 44.11, "elapsed_time": "3:09:24", "remaining_time": "3:59:58", "throughput": 1489.3, "total_tokens": 16924592} {"current_steps": 80200, "total_steps": 181800, "loss": 0.0129, "lr": 3.427296352091133e-05, "epoch": 8.822882288228822, "percentage": 44.11, "elapsed_time": "3:09:24", "remaining_time": "3:59:57", "throughput": 1489.3, "total_tokens": 16925648} {"current_steps": 80205, "total_steps": 181800, "loss": 0.0584, "lr": 3.427073461831154e-05, "epoch": 8.823432343234323, "percentage": 44.12, "elapsed_time": "3:09:25", "remaining_time": "3:59:56", "throughput": 1489.31, "total_tokens": 16926704} {"current_steps": 80210, "total_steps": 181800, "loss": 0.0187, "lr": 3.426850563026783e-05, "epoch": 8.823982398239824, "percentage": 44.12, "elapsed_time": "3:09:26", "remaining_time": "3:59:55", "throughput": 1489.31, "total_tokens": 16927728} {"current_steps": 80215, "total_steps": 181800, "loss": 0.0176, "lr": 3.4266276556800755e-05, "epoch": 8.824532453245325, "percentage": 44.12, "elapsed_time": "3:09:26", "remaining_time": "3:59:55", "throughput": 1489.31, "total_tokens": 16928816} {"current_steps": 80220, "total_steps": 181800, "loss": 0.0231, "lr": 3.426404739793086e-05, "epoch": 8.825082508250825, "percentage": 44.13, "elapsed_time": "3:09:27", "remaining_time": "3:59:54", "throughput": 1489.31, "total_tokens": 16929840} {"current_steps": 80225, "total_steps": 181800, "loss": 0.035, "lr": 3.426181815367868e-05, "epoch": 8.825632563256326, "percentage": 44.13, "elapsed_time": "3:09:28", "remaining_time": "3:59:53", "throughput": 1489.31, "total_tokens": 16930928} {"current_steps": 80230, "total_steps": 181800, "loss": 0.0083, "lr": 3.425958882406476e-05, "epoch": 8.826182618261827, "percentage": 44.13, "elapsed_time": "3:09:28", "remaining_time": "3:59:52", "throughput": 1489.31, "total_tokens": 16931952} {"current_steps": 80235, "total_steps": 181800, "loss": 0.0349, "lr": 3.4257359409109666e-05, "epoch": 8.826732673267326, "percentage": 44.13, "elapsed_time": "3:09:29", "remaining_time": "3:59:52", "throughput": 1489.31, "total_tokens": 16932976} {"current_steps": 80240, "total_steps": 181800, "loss": 0.0284, "lr": 3.4255129908833924e-05, "epoch": 8.827282728272827, "percentage": 44.14, "elapsed_time": "3:09:30", "remaining_time": "3:59:51", "throughput": 1489.31, "total_tokens": 16933968} {"current_steps": 80245, "total_steps": 181800, "loss": 0.0716, "lr": 3.4252900323258095e-05, "epoch": 8.827832783278328, "percentage": 44.14, "elapsed_time": "3:09:31", "remaining_time": "3:59:50", "throughput": 1489.32, "total_tokens": 16935152} {"current_steps": 80250, "total_steps": 181800, "loss": 0.0041, "lr": 3.4250670652402725e-05, "epoch": 8.828382838283828, "percentage": 44.14, "elapsed_time": "3:09:31", "remaining_time": "3:59:50", "throughput": 1489.33, "total_tokens": 16936208} {"current_steps": 80255, "total_steps": 181800, "loss": 0.0032, "lr": 3.424844089628836e-05, "epoch": 8.828932893289329, "percentage": 44.14, "elapsed_time": "3:09:32", "remaining_time": "3:59:49", "throughput": 1489.33, "total_tokens": 16937264} {"current_steps": 80260, "total_steps": 181800, "loss": 0.0104, "lr": 3.424621105493554e-05, "epoch": 8.82948294829483, "percentage": 44.15, "elapsed_time": "3:09:33", "remaining_time": "3:59:48", "throughput": 1489.33, "total_tokens": 16938288} {"current_steps": 80265, "total_steps": 181800, "loss": 0.0143, "lr": 3.424398112836485e-05, "epoch": 8.83003300330033, "percentage": 44.15, "elapsed_time": "3:09:33", "remaining_time": "3:59:47", "throughput": 1489.33, "total_tokens": 16939376} {"current_steps": 80270, "total_steps": 181800, "loss": 0.0026, "lr": 3.4241751116596823e-05, "epoch": 8.83058305830583, "percentage": 44.15, "elapsed_time": "3:09:34", "remaining_time": "3:59:47", "throughput": 1489.33, "total_tokens": 16940400} {"current_steps": 80275, "total_steps": 181800, "loss": 0.0123, "lr": 3.4239521019651985e-05, "epoch": 8.831133113311331, "percentage": 44.16, "elapsed_time": "3:09:35", "remaining_time": "3:59:46", "throughput": 1489.34, "total_tokens": 16941456} {"current_steps": 80280, "total_steps": 181800, "loss": 0.1961, "lr": 3.423729083755094e-05, "epoch": 8.831683168316832, "percentage": 44.16, "elapsed_time": "3:09:35", "remaining_time": "3:59:45", "throughput": 1489.34, "total_tokens": 16942512} {"current_steps": 80285, "total_steps": 181800, "loss": 0.015, "lr": 3.4235060570314206e-05, "epoch": 8.832233223322332, "percentage": 44.16, "elapsed_time": "3:09:36", "remaining_time": "3:59:44", "throughput": 1489.34, "total_tokens": 16943568} {"current_steps": 80290, "total_steps": 181800, "loss": 0.0671, "lr": 3.423283021796235e-05, "epoch": 8.832783278327833, "percentage": 44.16, "elapsed_time": "3:09:37", "remaining_time": "3:59:44", "throughput": 1489.35, "total_tokens": 16944656} {"current_steps": 80295, "total_steps": 181800, "loss": 0.0202, "lr": 3.423059978051594e-05, "epoch": 8.833333333333334, "percentage": 44.17, "elapsed_time": "3:09:37", "remaining_time": "3:59:43", "throughput": 1489.35, "total_tokens": 16945744} {"current_steps": 80300, "total_steps": 181800, "loss": 0.0844, "lr": 3.422836925799551e-05, "epoch": 8.833883388338833, "percentage": 44.17, "elapsed_time": "3:09:38", "remaining_time": "3:59:42", "throughput": 1489.35, "total_tokens": 16946800} {"current_steps": 80305, "total_steps": 181800, "loss": 0.0454, "lr": 3.422613865042163e-05, "epoch": 8.834433443344334, "percentage": 44.17, "elapsed_time": "3:09:39", "remaining_time": "3:59:41", "throughput": 1489.36, "total_tokens": 16947920} {"current_steps": 80310, "total_steps": 181800, "loss": 0.0095, "lr": 3.422390795781486e-05, "epoch": 8.834983498349835, "percentage": 44.17, "elapsed_time": "3:09:40", "remaining_time": "3:59:41", "throughput": 1489.37, "total_tokens": 16949040} {"current_steps": 80315, "total_steps": 181800, "loss": 0.1315, "lr": 3.422167718019576e-05, "epoch": 8.835533553355335, "percentage": 44.18, "elapsed_time": "3:09:40", "remaining_time": "3:59:40", "throughput": 1489.38, "total_tokens": 16950160} {"current_steps": 80320, "total_steps": 181800, "loss": 0.0252, "lr": 3.421944631758487e-05, "epoch": 8.836083608360836, "percentage": 44.18, "elapsed_time": "3:09:41", "remaining_time": "3:59:39", "throughput": 1489.38, "total_tokens": 16951248} {"current_steps": 80325, "total_steps": 181800, "loss": 0.0049, "lr": 3.4217215370002785e-05, "epoch": 8.836633663366337, "percentage": 44.18, "elapsed_time": "3:09:42", "remaining_time": "3:59:39", "throughput": 1489.38, "total_tokens": 16952208} {"current_steps": 80330, "total_steps": 181800, "loss": 0.0061, "lr": 3.421498433747004e-05, "epoch": 8.837183718371836, "percentage": 44.19, "elapsed_time": "3:09:42", "remaining_time": "3:59:38", "throughput": 1489.38, "total_tokens": 16953264} {"current_steps": 80335, "total_steps": 181800, "loss": 0.0115, "lr": 3.421275322000721e-05, "epoch": 8.837733773377337, "percentage": 44.19, "elapsed_time": "3:09:43", "remaining_time": "3:59:37", "throughput": 1489.38, "total_tokens": 16954352} {"current_steps": 80340, "total_steps": 181800, "loss": 0.0387, "lr": 3.4210522017634854e-05, "epoch": 8.838283828382838, "percentage": 44.19, "elapsed_time": "3:09:44", "remaining_time": "3:59:36", "throughput": 1489.38, "total_tokens": 16955376} {"current_steps": 80345, "total_steps": 181800, "loss": 0.0043, "lr": 3.4208290730373534e-05, "epoch": 8.83883388338834, "percentage": 44.19, "elapsed_time": "3:09:44", "remaining_time": "3:59:36", "throughput": 1489.39, "total_tokens": 16956496} {"current_steps": 80350, "total_steps": 181800, "loss": 0.065, "lr": 3.4206059358243815e-05, "epoch": 8.839383938393839, "percentage": 44.2, "elapsed_time": "3:09:45", "remaining_time": "3:59:35", "throughput": 1489.39, "total_tokens": 16957552} {"current_steps": 80355, "total_steps": 181800, "loss": 0.1826, "lr": 3.420382790126627e-05, "epoch": 8.83993399339934, "percentage": 44.2, "elapsed_time": "3:09:46", "remaining_time": "3:59:34", "throughput": 1489.4, "total_tokens": 16958672} {"current_steps": 80360, "total_steps": 181800, "loss": 0.0254, "lr": 3.420159635946146e-05, "epoch": 8.840484048404841, "percentage": 44.2, "elapsed_time": "3:09:46", "remaining_time": "3:59:33", "throughput": 1489.4, "total_tokens": 16959696} {"current_steps": 80365, "total_steps": 181800, "loss": 0.0122, "lr": 3.419936473284995e-05, "epoch": 8.84103410341034, "percentage": 44.21, "elapsed_time": "3:09:47", "remaining_time": "3:59:33", "throughput": 1489.4, "total_tokens": 16960752} {"current_steps": 80370, "total_steps": 181800, "loss": 0.1193, "lr": 3.4197133021452304e-05, "epoch": 8.841584158415841, "percentage": 44.21, "elapsed_time": "3:09:48", "remaining_time": "3:59:32", "throughput": 1489.41, "total_tokens": 16961872} {"current_steps": 80375, "total_steps": 181800, "loss": 0.1411, "lr": 3.41949012252891e-05, "epoch": 8.842134213421343, "percentage": 44.21, "elapsed_time": "3:09:48", "remaining_time": "3:59:31", "throughput": 1489.41, "total_tokens": 16962896} {"current_steps": 80380, "total_steps": 181800, "loss": 0.0322, "lr": 3.41926693443809e-05, "epoch": 8.842684268426842, "percentage": 44.21, "elapsed_time": "3:09:49", "remaining_time": "3:59:31", "throughput": 1489.42, "total_tokens": 16963984} {"current_steps": 80385, "total_steps": 181800, "loss": 0.0097, "lr": 3.4190437378748294e-05, "epoch": 8.843234323432343, "percentage": 44.22, "elapsed_time": "3:09:50", "remaining_time": "3:59:30", "throughput": 1489.42, "total_tokens": 16965008} {"current_steps": 80390, "total_steps": 181800, "loss": 0.0161, "lr": 3.418820532841182e-05, "epoch": 8.843784378437844, "percentage": 44.22, "elapsed_time": "3:09:51", "remaining_time": "3:59:29", "throughput": 1489.42, "total_tokens": 16966096} {"current_steps": 80395, "total_steps": 181800, "loss": 0.0149, "lr": 3.418597319339207e-05, "epoch": 8.844334433443345, "percentage": 44.22, "elapsed_time": "3:09:51", "remaining_time": "3:59:28", "throughput": 1489.43, "total_tokens": 16967152} {"current_steps": 80400, "total_steps": 181800, "loss": 0.1342, "lr": 3.418374097370961e-05, "epoch": 8.844884488448844, "percentage": 44.22, "elapsed_time": "3:09:52", "remaining_time": "3:59:28", "throughput": 1489.42, "total_tokens": 16968112} {"current_steps": 80405, "total_steps": 181800, "loss": 0.0351, "lr": 3.418150866938502e-05, "epoch": 8.845434543454346, "percentage": 44.23, "elapsed_time": "3:09:53", "remaining_time": "3:59:27", "throughput": 1489.42, "total_tokens": 16969200} {"current_steps": 80410, "total_steps": 181800, "loss": 0.0082, "lr": 3.4179276280438874e-05, "epoch": 8.845984598459847, "percentage": 44.23, "elapsed_time": "3:09:53", "remaining_time": "3:59:26", "throughput": 1489.43, "total_tokens": 16970288} {"current_steps": 80415, "total_steps": 181800, "loss": 0.0151, "lr": 3.4177043806891737e-05, "epoch": 8.846534653465346, "percentage": 44.23, "elapsed_time": "3:09:54", "remaining_time": "3:59:25", "throughput": 1489.42, "total_tokens": 16971248} {"current_steps": 80420, "total_steps": 181800, "loss": 0.0179, "lr": 3.417481124876419e-05, "epoch": 8.847084708470847, "percentage": 44.24, "elapsed_time": "3:09:55", "remaining_time": "3:59:25", "throughput": 1489.42, "total_tokens": 16972272} {"current_steps": 80425, "total_steps": 181800, "loss": 0.0771, "lr": 3.417257860607682e-05, "epoch": 8.847634763476348, "percentage": 44.24, "elapsed_time": "3:09:55", "remaining_time": "3:59:24", "throughput": 1489.42, "total_tokens": 16973296} {"current_steps": 80430, "total_steps": 181800, "loss": 0.0506, "lr": 3.4170345878850185e-05, "epoch": 8.848184818481847, "percentage": 44.24, "elapsed_time": "3:09:56", "remaining_time": "3:59:23", "throughput": 1489.42, "total_tokens": 16974320} {"current_steps": 80435, "total_steps": 181800, "loss": 0.0057, "lr": 3.4168113067104875e-05, "epoch": 8.848734873487349, "percentage": 44.24, "elapsed_time": "3:09:57", "remaining_time": "3:59:22", "throughput": 1489.42, "total_tokens": 16975312} {"current_steps": 80440, "total_steps": 181800, "loss": 0.0165, "lr": 3.416588017086146e-05, "epoch": 8.84928492849285, "percentage": 44.25, "elapsed_time": "3:09:57", "remaining_time": "3:59:22", "throughput": 1489.42, "total_tokens": 16976368} {"current_steps": 80445, "total_steps": 181800, "loss": 0.0706, "lr": 3.416364719014054e-05, "epoch": 8.84983498349835, "percentage": 44.25, "elapsed_time": "3:09:58", "remaining_time": "3:59:21", "throughput": 1489.42, "total_tokens": 16977392} {"current_steps": 80450, "total_steps": 181800, "loss": 0.1063, "lr": 3.416141412496266e-05, "epoch": 8.85038503850385, "percentage": 44.25, "elapsed_time": "3:09:59", "remaining_time": "3:59:20", "throughput": 1489.42, "total_tokens": 16978448} {"current_steps": 80455, "total_steps": 181800, "loss": 0.0433, "lr": 3.4159180975348446e-05, "epoch": 8.850935093509351, "percentage": 44.25, "elapsed_time": "3:10:00", "remaining_time": "3:59:20", "throughput": 1489.42, "total_tokens": 16979472} {"current_steps": 80460, "total_steps": 181800, "loss": 0.0285, "lr": 3.4156947741318445e-05, "epoch": 8.851485148514852, "percentage": 44.26, "elapsed_time": "3:10:00", "remaining_time": "3:59:19", "throughput": 1489.43, "total_tokens": 16980528} {"current_steps": 80465, "total_steps": 181800, "loss": 0.0072, "lr": 3.415471442289325e-05, "epoch": 8.852035203520352, "percentage": 44.26, "elapsed_time": "3:10:01", "remaining_time": "3:59:18", "throughput": 1489.43, "total_tokens": 16981616} {"current_steps": 80470, "total_steps": 181800, "loss": 0.0924, "lr": 3.415248102009345e-05, "epoch": 8.852585258525853, "percentage": 44.26, "elapsed_time": "3:10:02", "remaining_time": "3:59:17", "throughput": 1489.43, "total_tokens": 16982640} {"current_steps": 80475, "total_steps": 181800, "loss": 0.0676, "lr": 3.415024753293962e-05, "epoch": 8.853135313531354, "percentage": 44.27, "elapsed_time": "3:10:02", "remaining_time": "3:59:17", "throughput": 1489.43, "total_tokens": 16983664} {"current_steps": 80480, "total_steps": 181800, "loss": 0.0491, "lr": 3.414801396145235e-05, "epoch": 8.853685368536853, "percentage": 44.27, "elapsed_time": "3:10:03", "remaining_time": "3:59:16", "throughput": 1489.43, "total_tokens": 16984720} {"current_steps": 80485, "total_steps": 181800, "loss": 0.0657, "lr": 3.414578030565222e-05, "epoch": 8.854235423542354, "percentage": 44.27, "elapsed_time": "3:10:04", "remaining_time": "3:59:15", "throughput": 1489.44, "total_tokens": 16985776} {"current_steps": 80490, "total_steps": 181800, "loss": 0.0235, "lr": 3.414354656555983e-05, "epoch": 8.854785478547855, "percentage": 44.27, "elapsed_time": "3:10:04", "remaining_time": "3:59:14", "throughput": 1489.44, "total_tokens": 16986832} {"current_steps": 80495, "total_steps": 181800, "loss": 0.0039, "lr": 3.4141312741195744e-05, "epoch": 8.855335533553355, "percentage": 44.28, "elapsed_time": "3:10:05", "remaining_time": "3:59:14", "throughput": 1489.44, "total_tokens": 16987888} {"current_steps": 80500, "total_steps": 181800, "loss": 0.0116, "lr": 3.413907883258058e-05, "epoch": 8.855885588558856, "percentage": 44.28, "elapsed_time": "3:10:06", "remaining_time": "3:59:13", "throughput": 1489.44, "total_tokens": 16988912} {"current_steps": 80505, "total_steps": 181800, "loss": 0.0115, "lr": 3.4136844839734907e-05, "epoch": 8.856435643564357, "percentage": 44.28, "elapsed_time": "3:10:06", "remaining_time": "3:59:12", "throughput": 1489.44, "total_tokens": 16989968} {"current_steps": 80510, "total_steps": 181800, "loss": 0.0142, "lr": 3.413461076267932e-05, "epoch": 8.856985698569858, "percentage": 44.28, "elapsed_time": "3:10:07", "remaining_time": "3:59:11", "throughput": 1489.45, "total_tokens": 16991024} {"current_steps": 80515, "total_steps": 181800, "loss": 0.0395, "lr": 3.413237660143441e-05, "epoch": 8.857535753575357, "percentage": 44.29, "elapsed_time": "3:10:08", "remaining_time": "3:59:11", "throughput": 1489.45, "total_tokens": 16992080} {"current_steps": 80520, "total_steps": 181800, "loss": 0.0379, "lr": 3.4130142356020764e-05, "epoch": 8.858085808580858, "percentage": 44.29, "elapsed_time": "3:10:08", "remaining_time": "3:59:10", "throughput": 1489.46, "total_tokens": 16993200} {"current_steps": 80525, "total_steps": 181800, "loss": 0.0048, "lr": 3.4127908026458976e-05, "epoch": 8.85863586358636, "percentage": 44.29, "elapsed_time": "3:10:09", "remaining_time": "3:59:09", "throughput": 1489.46, "total_tokens": 16994288} {"current_steps": 80530, "total_steps": 181800, "loss": 0.0743, "lr": 3.412567361276965e-05, "epoch": 8.859185918591859, "percentage": 44.3, "elapsed_time": "3:10:10", "remaining_time": "3:59:09", "throughput": 1489.47, "total_tokens": 16995344} {"current_steps": 80535, "total_steps": 181800, "loss": 0.0044, "lr": 3.412343911497335e-05, "epoch": 8.85973597359736, "percentage": 44.3, "elapsed_time": "3:10:11", "remaining_time": "3:59:08", "throughput": 1489.47, "total_tokens": 16996368} {"current_steps": 80540, "total_steps": 181800, "loss": 0.0024, "lr": 3.412120453309071e-05, "epoch": 8.86028602860286, "percentage": 44.3, "elapsed_time": "3:10:11", "remaining_time": "3:59:07", "throughput": 1489.47, "total_tokens": 16997456} {"current_steps": 80545, "total_steps": 181800, "loss": 0.02, "lr": 3.4118969867142294e-05, "epoch": 8.86083608360836, "percentage": 44.3, "elapsed_time": "3:10:12", "remaining_time": "3:59:06", "throughput": 1489.47, "total_tokens": 16998448} {"current_steps": 80550, "total_steps": 181800, "loss": 0.0999, "lr": 3.411673511714871e-05, "epoch": 8.861386138613861, "percentage": 44.31, "elapsed_time": "3:10:13", "remaining_time": "3:59:06", "throughput": 1489.48, "total_tokens": 16999568} {"current_steps": 80555, "total_steps": 181800, "loss": 0.0068, "lr": 3.4114500283130554e-05, "epoch": 8.861936193619362, "percentage": 44.31, "elapsed_time": "3:10:13", "remaining_time": "3:59:05", "throughput": 1489.48, "total_tokens": 17000656} {"current_steps": 80560, "total_steps": 181800, "loss": 0.0596, "lr": 3.411226536510842e-05, "epoch": 8.862486248624862, "percentage": 44.31, "elapsed_time": "3:10:14", "remaining_time": "3:59:04", "throughput": 1489.49, "total_tokens": 17001744} {"current_steps": 80565, "total_steps": 181800, "loss": 0.0282, "lr": 3.4110030363102905e-05, "epoch": 8.863036303630363, "percentage": 44.32, "elapsed_time": "3:10:15", "remaining_time": "3:59:03", "throughput": 1489.49, "total_tokens": 17002800} {"current_steps": 80570, "total_steps": 181800, "loss": 0.0217, "lr": 3.410779527713461e-05, "epoch": 8.863586358635864, "percentage": 44.32, "elapsed_time": "3:10:15", "remaining_time": "3:59:03", "throughput": 1489.49, "total_tokens": 17003824} {"current_steps": 80575, "total_steps": 181800, "loss": 0.0083, "lr": 3.410556010722416e-05, "epoch": 8.864136413641365, "percentage": 44.32, "elapsed_time": "3:10:16", "remaining_time": "3:59:02", "throughput": 1489.49, "total_tokens": 17004880} {"current_steps": 80580, "total_steps": 181800, "loss": 0.0112, "lr": 3.4103324853392106e-05, "epoch": 8.864686468646864, "percentage": 44.32, "elapsed_time": "3:10:17", "remaining_time": "3:59:01", "throughput": 1489.49, "total_tokens": 17005904} {"current_steps": 80585, "total_steps": 181800, "loss": 0.0145, "lr": 3.4101089515659084e-05, "epoch": 8.865236523652365, "percentage": 44.33, "elapsed_time": "3:10:17", "remaining_time": "3:59:00", "throughput": 1489.49, "total_tokens": 17006928} {"current_steps": 80590, "total_steps": 181800, "loss": 0.0474, "lr": 3.409885409404568e-05, "epoch": 8.865786578657866, "percentage": 44.33, "elapsed_time": "3:10:18", "remaining_time": "3:59:00", "throughput": 1489.5, "total_tokens": 17008048} {"current_steps": 80595, "total_steps": 181800, "loss": 0.0232, "lr": 3.4096618588572516e-05, "epoch": 8.866336633663366, "percentage": 44.33, "elapsed_time": "3:10:19", "remaining_time": "3:58:59", "throughput": 1489.5, "total_tokens": 17009072} {"current_steps": 80600, "total_steps": 181800, "loss": 0.0061, "lr": 3.409438299926018e-05, "epoch": 8.866886688668867, "percentage": 44.33, "elapsed_time": "3:10:20", "remaining_time": "3:58:58", "throughput": 1489.49, "total_tokens": 17010064} {"current_steps": 80605, "total_steps": 181800, "loss": 0.014, "lr": 3.4092147326129274e-05, "epoch": 8.867436743674368, "percentage": 44.34, "elapsed_time": "3:10:20", "remaining_time": "3:58:58", "throughput": 1489.5, "total_tokens": 17011120} {"current_steps": 80610, "total_steps": 181800, "loss": 0.1321, "lr": 3.408991156920041e-05, "epoch": 8.867986798679867, "percentage": 44.34, "elapsed_time": "3:10:21", "remaining_time": "3:58:57", "throughput": 1489.49, "total_tokens": 17012112} {"current_steps": 80615, "total_steps": 181800, "loss": 0.0133, "lr": 3.4087675728494204e-05, "epoch": 8.868536853685368, "percentage": 44.34, "elapsed_time": "3:10:22", "remaining_time": "3:58:56", "throughput": 1489.5, "total_tokens": 17013168} {"current_steps": 80620, "total_steps": 181800, "loss": 0.0846, "lr": 3.408543980403124e-05, "epoch": 8.86908690869087, "percentage": 44.35, "elapsed_time": "3:10:22", "remaining_time": "3:58:55", "throughput": 1489.51, "total_tokens": 17014288} {"current_steps": 80625, "total_steps": 181800, "loss": 0.0294, "lr": 3.4083203795832144e-05, "epoch": 8.869636963696369, "percentage": 44.35, "elapsed_time": "3:10:23", "remaining_time": "3:58:55", "throughput": 1489.51, "total_tokens": 17015344} {"current_steps": 80630, "total_steps": 181800, "loss": 0.0125, "lr": 3.408096770391751e-05, "epoch": 8.87018701870187, "percentage": 44.35, "elapsed_time": "3:10:24", "remaining_time": "3:58:54", "throughput": 1489.51, "total_tokens": 17016400} {"current_steps": 80635, "total_steps": 181800, "loss": 0.0561, "lr": 3.4078731528307955e-05, "epoch": 8.870737073707371, "percentage": 44.35, "elapsed_time": "3:10:24", "remaining_time": "3:58:53", "throughput": 1489.51, "total_tokens": 17017424} {"current_steps": 80640, "total_steps": 181800, "loss": 0.0965, "lr": 3.407649526902409e-05, "epoch": 8.871287128712872, "percentage": 44.36, "elapsed_time": "3:10:25", "remaining_time": "3:58:52", "throughput": 1489.51, "total_tokens": 17018480} {"current_steps": 80645, "total_steps": 181800, "loss": 0.0334, "lr": 3.4074258926086524e-05, "epoch": 8.871837183718371, "percentage": 44.36, "elapsed_time": "3:10:26", "remaining_time": "3:58:52", "throughput": 1489.51, "total_tokens": 17019536} {"current_steps": 80650, "total_steps": 181800, "loss": 0.0182, "lr": 3.407202249951586e-05, "epoch": 8.872387238723872, "percentage": 44.36, "elapsed_time": "3:10:26", "remaining_time": "3:58:51", "throughput": 1489.53, "total_tokens": 17020688} {"current_steps": 80655, "total_steps": 181800, "loss": 0.0146, "lr": 3.406978598933273e-05, "epoch": 8.872937293729374, "percentage": 44.36, "elapsed_time": "3:10:27", "remaining_time": "3:58:50", "throughput": 1489.53, "total_tokens": 17021776} {"current_steps": 80660, "total_steps": 181800, "loss": 0.0127, "lr": 3.406754939555773e-05, "epoch": 8.873487348734873, "percentage": 44.37, "elapsed_time": "3:10:28", "remaining_time": "3:58:50", "throughput": 1489.53, "total_tokens": 17022768} {"current_steps": 80665, "total_steps": 181800, "loss": 0.0274, "lr": 3.406531271821148e-05, "epoch": 8.874037403740374, "percentage": 44.37, "elapsed_time": "3:10:28", "remaining_time": "3:58:49", "throughput": 1489.53, "total_tokens": 17023792} {"current_steps": 80670, "total_steps": 181800, "loss": 0.1053, "lr": 3.406307595731459e-05, "epoch": 8.874587458745875, "percentage": 44.37, "elapsed_time": "3:10:29", "remaining_time": "3:58:48", "throughput": 1489.53, "total_tokens": 17024816} {"current_steps": 80675, "total_steps": 181800, "loss": 0.0043, "lr": 3.4060839112887683e-05, "epoch": 8.875137513751374, "percentage": 44.38, "elapsed_time": "3:10:30", "remaining_time": "3:58:47", "throughput": 1489.53, "total_tokens": 17025872} {"current_steps": 80680, "total_steps": 181800, "loss": 0.0224, "lr": 3.4058602184951363e-05, "epoch": 8.875687568756875, "percentage": 44.38, "elapsed_time": "3:10:31", "remaining_time": "3:58:47", "throughput": 1489.53, "total_tokens": 17026960} {"current_steps": 80685, "total_steps": 181800, "loss": 0.0461, "lr": 3.405636517352625e-05, "epoch": 8.876237623762377, "percentage": 44.38, "elapsed_time": "3:10:31", "remaining_time": "3:58:46", "throughput": 1489.54, "total_tokens": 17028048} {"current_steps": 80690, "total_steps": 181800, "loss": 0.0465, "lr": 3.4054128078632975e-05, "epoch": 8.876787678767876, "percentage": 44.38, "elapsed_time": "3:10:32", "remaining_time": "3:58:45", "throughput": 1489.54, "total_tokens": 17029104} {"current_steps": 80695, "total_steps": 181800, "loss": 0.0074, "lr": 3.405189090029214e-05, "epoch": 8.877337733773377, "percentage": 44.39, "elapsed_time": "3:10:33", "remaining_time": "3:58:44", "throughput": 1489.55, "total_tokens": 17030192} {"current_steps": 80700, "total_steps": 181800, "loss": 0.0425, "lr": 3.404965363852437e-05, "epoch": 8.877887788778878, "percentage": 44.39, "elapsed_time": "3:10:33", "remaining_time": "3:58:44", "throughput": 1489.55, "total_tokens": 17031280} {"current_steps": 80705, "total_steps": 181800, "loss": 0.0239, "lr": 3.404741629335029e-05, "epoch": 8.87843784378438, "percentage": 44.39, "elapsed_time": "3:10:34", "remaining_time": "3:58:43", "throughput": 1489.55, "total_tokens": 17032272} {"current_steps": 80710, "total_steps": 181800, "loss": 0.0673, "lr": 3.404517886479051e-05, "epoch": 8.878987898789878, "percentage": 44.39, "elapsed_time": "3:10:35", "remaining_time": "3:58:42", "throughput": 1489.55, "total_tokens": 17033296} {"current_steps": 80715, "total_steps": 181800, "loss": 0.0082, "lr": 3.4042941352865657e-05, "epoch": 8.87953795379538, "percentage": 44.4, "elapsed_time": "3:10:35", "remaining_time": "3:58:41", "throughput": 1489.55, "total_tokens": 17034352} {"current_steps": 80720, "total_steps": 181800, "loss": 0.023, "lr": 3.404070375759636e-05, "epoch": 8.88008800880088, "percentage": 44.4, "elapsed_time": "3:10:36", "remaining_time": "3:58:41", "throughput": 1489.56, "total_tokens": 17035440} {"current_steps": 80725, "total_steps": 181800, "loss": 0.0072, "lr": 3.403846607900322e-05, "epoch": 8.88063806380638, "percentage": 44.4, "elapsed_time": "3:10:37", "remaining_time": "3:58:40", "throughput": 1489.57, "total_tokens": 17036560} {"current_steps": 80730, "total_steps": 181800, "loss": 0.0067, "lr": 3.403622831710689e-05, "epoch": 8.881188118811881, "percentage": 44.41, "elapsed_time": "3:10:37", "remaining_time": "3:58:39", "throughput": 1489.57, "total_tokens": 17037616} {"current_steps": 80735, "total_steps": 181800, "loss": 0.0036, "lr": 3.403399047192798e-05, "epoch": 8.881738173817382, "percentage": 44.41, "elapsed_time": "3:10:38", "remaining_time": "3:58:39", "throughput": 1489.56, "total_tokens": 17038576} {"current_steps": 80740, "total_steps": 181800, "loss": 0.1848, "lr": 3.4031752543487093e-05, "epoch": 8.882288228822881, "percentage": 44.41, "elapsed_time": "3:10:39", "remaining_time": "3:58:38", "throughput": 1489.57, "total_tokens": 17039632} {"current_steps": 80745, "total_steps": 181800, "loss": 0.0346, "lr": 3.40295145318049e-05, "epoch": 8.882838283828383, "percentage": 44.41, "elapsed_time": "3:10:40", "remaining_time": "3:58:37", "throughput": 1489.57, "total_tokens": 17040688} {"current_steps": 80750, "total_steps": 181800, "loss": 0.0362, "lr": 3.4027276436902e-05, "epoch": 8.883388338833884, "percentage": 44.42, "elapsed_time": "3:10:40", "remaining_time": "3:58:36", "throughput": 1489.57, "total_tokens": 17041744} {"current_steps": 80755, "total_steps": 181800, "loss": 0.0744, "lr": 3.4025038258799015e-05, "epoch": 8.883938393839383, "percentage": 44.42, "elapsed_time": "3:10:41", "remaining_time": "3:58:36", "throughput": 1489.58, "total_tokens": 17042896} {"current_steps": 80760, "total_steps": 181800, "loss": 0.1055, "lr": 3.402279999751659e-05, "epoch": 8.884488448844884, "percentage": 44.42, "elapsed_time": "3:10:42", "remaining_time": "3:58:35", "throughput": 1489.6, "total_tokens": 17044080} {"current_steps": 80765, "total_steps": 181800, "loss": 0.0128, "lr": 3.4020561653075356e-05, "epoch": 8.885038503850385, "percentage": 44.43, "elapsed_time": "3:10:42", "remaining_time": "3:58:34", "throughput": 1489.6, "total_tokens": 17045104} {"current_steps": 80770, "total_steps": 181800, "loss": 0.0087, "lr": 3.401832322549592e-05, "epoch": 8.885588558855886, "percentage": 44.43, "elapsed_time": "3:10:43", "remaining_time": "3:58:33", "throughput": 1489.6, "total_tokens": 17046224} {"current_steps": 80775, "total_steps": 181800, "loss": 0.01, "lr": 3.401608471479893e-05, "epoch": 8.886138613861386, "percentage": 44.43, "elapsed_time": "3:10:44", "remaining_time": "3:58:33", "throughput": 1489.61, "total_tokens": 17047280} {"current_steps": 80780, "total_steps": 181800, "loss": 0.0327, "lr": 3.401384612100501e-05, "epoch": 8.886688668866887, "percentage": 44.43, "elapsed_time": "3:10:44", "remaining_time": "3:58:32", "throughput": 1489.61, "total_tokens": 17048304} {"current_steps": 80785, "total_steps": 181800, "loss": 0.0206, "lr": 3.40116074441348e-05, "epoch": 8.887238723872388, "percentage": 44.44, "elapsed_time": "3:10:45", "remaining_time": "3:58:31", "throughput": 1489.61, "total_tokens": 17049360} {"current_steps": 80790, "total_steps": 181800, "loss": 0.1044, "lr": 3.400936868420893e-05, "epoch": 8.887788778877887, "percentage": 44.44, "elapsed_time": "3:10:46", "remaining_time": "3:58:30", "throughput": 1489.62, "total_tokens": 17050448} {"current_steps": 80795, "total_steps": 181800, "loss": 0.0967, "lr": 3.400712984124803e-05, "epoch": 8.888338833883388, "percentage": 44.44, "elapsed_time": "3:10:46", "remaining_time": "3:58:30", "throughput": 1489.62, "total_tokens": 17051472} {"current_steps": 80800, "total_steps": 181800, "loss": 0.0098, "lr": 3.400489091527274e-05, "epoch": 8.88888888888889, "percentage": 44.44, "elapsed_time": "3:10:47", "remaining_time": "3:58:29", "throughput": 1489.61, "total_tokens": 17052496} {"current_steps": 80805, "total_steps": 181800, "loss": 0.0094, "lr": 3.4002651906303676e-05, "epoch": 8.88943894389439, "percentage": 44.45, "elapsed_time": "3:10:48", "remaining_time": "3:58:28", "throughput": 1489.61, "total_tokens": 17053488} {"current_steps": 80810, "total_steps": 181800, "loss": 0.0301, "lr": 3.4000412814361504e-05, "epoch": 8.88998899889989, "percentage": 44.45, "elapsed_time": "3:10:48", "remaining_time": "3:58:28", "throughput": 1489.62, "total_tokens": 17054608} {"current_steps": 80815, "total_steps": 181800, "loss": 0.0323, "lr": 3.399817363946685e-05, "epoch": 8.89053905390539, "percentage": 44.45, "elapsed_time": "3:10:49", "remaining_time": "3:58:27", "throughput": 1489.62, "total_tokens": 17055600} {"current_steps": 80820, "total_steps": 181800, "loss": 0.0109, "lr": 3.3995934381640334e-05, "epoch": 8.891089108910892, "percentage": 44.46, "elapsed_time": "3:10:50", "remaining_time": "3:58:26", "throughput": 1489.62, "total_tokens": 17056688} {"current_steps": 80825, "total_steps": 181800, "loss": 0.011, "lr": 3.399369504090262e-05, "epoch": 8.891639163916391, "percentage": 44.46, "elapsed_time": "3:10:51", "remaining_time": "3:58:25", "throughput": 1489.62, "total_tokens": 17057712} {"current_steps": 80830, "total_steps": 181800, "loss": 0.1097, "lr": 3.3991455617274323e-05, "epoch": 8.892189218921892, "percentage": 44.46, "elapsed_time": "3:10:51", "remaining_time": "3:58:25", "throughput": 1489.62, "total_tokens": 17058736} {"current_steps": 80835, "total_steps": 181800, "loss": 0.0142, "lr": 3.3989216110776094e-05, "epoch": 8.892739273927393, "percentage": 44.46, "elapsed_time": "3:10:52", "remaining_time": "3:58:24", "throughput": 1489.62, "total_tokens": 17059728} {"current_steps": 80840, "total_steps": 181800, "loss": 0.0188, "lr": 3.398697652142858e-05, "epoch": 8.893289328932893, "percentage": 44.47, "elapsed_time": "3:10:53", "remaining_time": "3:58:23", "throughput": 1489.62, "total_tokens": 17060816} {"current_steps": 80845, "total_steps": 181800, "loss": 0.0058, "lr": 3.3984736849252416e-05, "epoch": 8.893839383938394, "percentage": 44.47, "elapsed_time": "3:10:53", "remaining_time": "3:58:22", "throughput": 1489.62, "total_tokens": 17061840} {"current_steps": 80850, "total_steps": 181800, "loss": 0.0201, "lr": 3.398249709426824e-05, "epoch": 8.894389438943895, "percentage": 44.47, "elapsed_time": "3:10:54", "remaining_time": "3:58:22", "throughput": 1489.63, "total_tokens": 17062992} {"current_steps": 80855, "total_steps": 181800, "loss": 0.1009, "lr": 3.3980257256496694e-05, "epoch": 8.894939493949394, "percentage": 44.47, "elapsed_time": "3:10:55", "remaining_time": "3:58:21", "throughput": 1489.64, "total_tokens": 17064048} {"current_steps": 80860, "total_steps": 181800, "loss": 0.0164, "lr": 3.397801733595843e-05, "epoch": 8.895489548954895, "percentage": 44.48, "elapsed_time": "3:10:55", "remaining_time": "3:58:20", "throughput": 1489.64, "total_tokens": 17065104} {"current_steps": 80865, "total_steps": 181800, "loss": 0.1844, "lr": 3.3975777332674106e-05, "epoch": 8.896039603960396, "percentage": 44.48, "elapsed_time": "3:10:56", "remaining_time": "3:58:19", "throughput": 1489.64, "total_tokens": 17066160} {"current_steps": 80870, "total_steps": 181800, "loss": 0.0311, "lr": 3.3973537246664326e-05, "epoch": 8.896589658965897, "percentage": 44.48, "elapsed_time": "3:10:57", "remaining_time": "3:58:19", "throughput": 1489.64, "total_tokens": 17067184} {"current_steps": 80875, "total_steps": 181800, "loss": 0.0571, "lr": 3.397129707794977e-05, "epoch": 8.897139713971397, "percentage": 44.49, "elapsed_time": "3:10:57", "remaining_time": "3:58:18", "throughput": 1489.65, "total_tokens": 17068272} {"current_steps": 80880, "total_steps": 181800, "loss": 0.0357, "lr": 3.396905682655107e-05, "epoch": 8.897689768976898, "percentage": 44.49, "elapsed_time": "3:10:58", "remaining_time": "3:58:17", "throughput": 1489.65, "total_tokens": 17069328} {"current_steps": 80885, "total_steps": 181800, "loss": 0.0487, "lr": 3.396681649248888e-05, "epoch": 8.898239823982399, "percentage": 44.49, "elapsed_time": "3:10:59", "remaining_time": "3:58:17", "throughput": 1489.65, "total_tokens": 17070384} {"current_steps": 80890, "total_steps": 181800, "loss": 0.1221, "lr": 3.3964576075783846e-05, "epoch": 8.898789878987898, "percentage": 44.49, "elapsed_time": "3:10:59", "remaining_time": "3:58:16", "throughput": 1489.66, "total_tokens": 17071440} {"current_steps": 80895, "total_steps": 181800, "loss": 0.0154, "lr": 3.396233557645661e-05, "epoch": 8.8993399339934, "percentage": 44.5, "elapsed_time": "3:11:00", "remaining_time": "3:58:15", "throughput": 1489.66, "total_tokens": 17072464} {"current_steps": 80900, "total_steps": 181800, "loss": 0.1136, "lr": 3.396009499452782e-05, "epoch": 8.8998899889989, "percentage": 44.5, "elapsed_time": "3:11:01", "remaining_time": "3:58:14", "throughput": 1489.65, "total_tokens": 17073488} {"current_steps": 80905, "total_steps": 181800, "loss": 0.0616, "lr": 3.3957854330018154e-05, "epoch": 8.9004400440044, "percentage": 44.5, "elapsed_time": "3:11:02", "remaining_time": "3:58:14", "throughput": 1489.65, "total_tokens": 17074512} {"current_steps": 80910, "total_steps": 181800, "loss": 0.0488, "lr": 3.395561358294824e-05, "epoch": 8.900990099009901, "percentage": 44.5, "elapsed_time": "3:11:02", "remaining_time": "3:58:13", "throughput": 1489.66, "total_tokens": 17075568} {"current_steps": 80915, "total_steps": 181800, "loss": 0.0075, "lr": 3.395337275333872e-05, "epoch": 8.901540154015402, "percentage": 44.51, "elapsed_time": "3:11:03", "remaining_time": "3:58:12", "throughput": 1489.66, "total_tokens": 17076624} {"current_steps": 80920, "total_steps": 181800, "loss": 0.003, "lr": 3.3951131841210266e-05, "epoch": 8.902090209020901, "percentage": 44.51, "elapsed_time": "3:11:04", "remaining_time": "3:58:11", "throughput": 1489.66, "total_tokens": 17077680} {"current_steps": 80925, "total_steps": 181800, "loss": 0.0442, "lr": 3.394889084658353e-05, "epoch": 8.902640264026402, "percentage": 44.51, "elapsed_time": "3:11:04", "remaining_time": "3:58:11", "throughput": 1489.66, "total_tokens": 17078640} {"current_steps": 80930, "total_steps": 181800, "loss": 0.0509, "lr": 3.3946649769479144e-05, "epoch": 8.903190319031903, "percentage": 44.52, "elapsed_time": "3:11:05", "remaining_time": "3:58:10", "throughput": 1489.66, "total_tokens": 17079664} {"current_steps": 80935, "total_steps": 181800, "loss": 0.0206, "lr": 3.39444086099178e-05, "epoch": 8.903740374037405, "percentage": 44.52, "elapsed_time": "3:11:06", "remaining_time": "3:58:09", "throughput": 1489.65, "total_tokens": 17080656} {"current_steps": 80940, "total_steps": 181800, "loss": 0.0233, "lr": 3.394216736792012e-05, "epoch": 8.904290429042904, "percentage": 44.52, "elapsed_time": "3:11:06", "remaining_time": "3:58:08", "throughput": 1489.65, "total_tokens": 17081712} {"current_steps": 80945, "total_steps": 181800, "loss": 0.1366, "lr": 3.393992604350678e-05, "epoch": 8.904840484048405, "percentage": 44.52, "elapsed_time": "3:11:07", "remaining_time": "3:58:08", "throughput": 1489.66, "total_tokens": 17082800} {"current_steps": 80950, "total_steps": 181800, "loss": 0.0401, "lr": 3.393768463669844e-05, "epoch": 8.905390539053906, "percentage": 44.53, "elapsed_time": "3:11:08", "remaining_time": "3:58:07", "throughput": 1489.66, "total_tokens": 17083856} {"current_steps": 80955, "total_steps": 181800, "loss": 0.0519, "lr": 3.393544314751573e-05, "epoch": 8.905940594059405, "percentage": 44.53, "elapsed_time": "3:11:08", "remaining_time": "3:58:06", "throughput": 1489.67, "total_tokens": 17084912} {"current_steps": 80960, "total_steps": 181800, "loss": 0.166, "lr": 3.3933201575979346e-05, "epoch": 8.906490649064907, "percentage": 44.53, "elapsed_time": "3:11:09", "remaining_time": "3:58:06", "throughput": 1489.67, "total_tokens": 17085936} {"current_steps": 80965, "total_steps": 181800, "loss": 0.0122, "lr": 3.393095992210992e-05, "epoch": 8.907040704070408, "percentage": 44.54, "elapsed_time": "3:11:10", "remaining_time": "3:58:05", "throughput": 1489.67, "total_tokens": 17087024} {"current_steps": 80970, "total_steps": 181800, "loss": 0.0681, "lr": 3.3928718185928125e-05, "epoch": 8.907590759075907, "percentage": 44.54, "elapsed_time": "3:11:11", "remaining_time": "3:58:04", "throughput": 1489.68, "total_tokens": 17088112} {"current_steps": 80975, "total_steps": 181800, "loss": 0.0179, "lr": 3.392647636745462e-05, "epoch": 8.908140814081408, "percentage": 44.54, "elapsed_time": "3:11:11", "remaining_time": "3:58:03", "throughput": 1489.68, "total_tokens": 17089168} {"current_steps": 80980, "total_steps": 181800, "loss": 0.0207, "lr": 3.392423446671007e-05, "epoch": 8.908690869086909, "percentage": 44.54, "elapsed_time": "3:11:12", "remaining_time": "3:58:03", "throughput": 1489.68, "total_tokens": 17090192} {"current_steps": 80985, "total_steps": 181800, "loss": 0.0337, "lr": 3.392199248371512e-05, "epoch": 8.909240924092408, "percentage": 44.55, "elapsed_time": "3:11:13", "remaining_time": "3:58:02", "throughput": 1489.68, "total_tokens": 17091280} {"current_steps": 80990, "total_steps": 181800, "loss": 0.0032, "lr": 3.3919750418490455e-05, "epoch": 8.90979097909791, "percentage": 44.55, "elapsed_time": "3:11:13", "remaining_time": "3:58:01", "throughput": 1489.68, "total_tokens": 17092304} {"current_steps": 80995, "total_steps": 181800, "loss": 0.005, "lr": 3.3917508271056734e-05, "epoch": 8.91034103410341, "percentage": 44.55, "elapsed_time": "3:11:14", "remaining_time": "3:58:00", "throughput": 1489.68, "total_tokens": 17093360} {"current_steps": 81000, "total_steps": 181800, "loss": 0.0092, "lr": 3.391526604143461e-05, "epoch": 8.910891089108912, "percentage": 44.55, "elapsed_time": "3:11:15", "remaining_time": "3:58:00", "throughput": 1489.69, "total_tokens": 17094416} {"current_steps": 81005, "total_steps": 181800, "loss": 0.0043, "lr": 3.391302372964476e-05, "epoch": 8.911441144114411, "percentage": 44.56, "elapsed_time": "3:11:15", "remaining_time": "3:57:59", "throughput": 1489.68, "total_tokens": 17095376} {"current_steps": 81010, "total_steps": 181800, "loss": 0.033, "lr": 3.391078133570785e-05, "epoch": 8.911991199119912, "percentage": 44.56, "elapsed_time": "3:11:16", "remaining_time": "3:57:58", "throughput": 1489.68, "total_tokens": 17096400} {"current_steps": 81015, "total_steps": 181800, "loss": 0.0327, "lr": 3.390853885964454e-05, "epoch": 8.912541254125413, "percentage": 44.56, "elapsed_time": "3:11:17", "remaining_time": "3:57:58", "throughput": 1489.69, "total_tokens": 17097488} {"current_steps": 81020, "total_steps": 181800, "loss": 0.0553, "lr": 3.3906296301475506e-05, "epoch": 8.913091309130913, "percentage": 44.57, "elapsed_time": "3:11:17", "remaining_time": "3:57:57", "throughput": 1489.69, "total_tokens": 17098576} {"current_steps": 81025, "total_steps": 181800, "loss": 0.0364, "lr": 3.390405366122141e-05, "epoch": 8.913641364136414, "percentage": 44.57, "elapsed_time": "3:11:18", "remaining_time": "3:57:56", "throughput": 1489.7, "total_tokens": 17099664} {"current_steps": 81030, "total_steps": 181800, "loss": 0.0023, "lr": 3.390181093890292e-05, "epoch": 8.914191419141915, "percentage": 44.57, "elapsed_time": "3:11:19", "remaining_time": "3:57:55", "throughput": 1489.7, "total_tokens": 17100752} {"current_steps": 81035, "total_steps": 181800, "loss": 0.0584, "lr": 3.389956813454072e-05, "epoch": 8.914741474147414, "percentage": 44.57, "elapsed_time": "3:11:20", "remaining_time": "3:57:55", "throughput": 1489.7, "total_tokens": 17101808} {"current_steps": 81040, "total_steps": 181800, "loss": 0.0948, "lr": 3.3897325248155466e-05, "epoch": 8.915291529152915, "percentage": 44.58, "elapsed_time": "3:11:20", "remaining_time": "3:57:54", "throughput": 1489.71, "total_tokens": 17102864} {"current_steps": 81045, "total_steps": 181800, "loss": 0.025, "lr": 3.389508227976783e-05, "epoch": 8.915841584158416, "percentage": 44.58, "elapsed_time": "3:11:21", "remaining_time": "3:57:53", "throughput": 1489.71, "total_tokens": 17103952} {"current_steps": 81050, "total_steps": 181800, "loss": 0.0096, "lr": 3.389283922939849e-05, "epoch": 8.916391639163916, "percentage": 44.58, "elapsed_time": "3:11:22", "remaining_time": "3:57:52", "throughput": 1489.72, "total_tokens": 17105040} {"current_steps": 81055, "total_steps": 181800, "loss": 0.0319, "lr": 3.3890596097068125e-05, "epoch": 8.916941694169417, "percentage": 44.58, "elapsed_time": "3:11:22", "remaining_time": "3:57:52", "throughput": 1489.72, "total_tokens": 17106128} {"current_steps": 81060, "total_steps": 181800, "loss": 0.0061, "lr": 3.3888352882797397e-05, "epoch": 8.917491749174918, "percentage": 44.59, "elapsed_time": "3:11:23", "remaining_time": "3:57:51", "throughput": 1489.72, "total_tokens": 17107152} {"current_steps": 81065, "total_steps": 181800, "loss": 0.0235, "lr": 3.388610958660699e-05, "epoch": 8.918041804180419, "percentage": 44.59, "elapsed_time": "3:11:24", "remaining_time": "3:57:50", "throughput": 1489.72, "total_tokens": 17108144} {"current_steps": 81070, "total_steps": 181800, "loss": 0.0443, "lr": 3.3883866208517566e-05, "epoch": 8.918591859185918, "percentage": 44.59, "elapsed_time": "3:11:24", "remaining_time": "3:57:49", "throughput": 1489.72, "total_tokens": 17109200} {"current_steps": 81075, "total_steps": 181800, "loss": 0.0287, "lr": 3.388162274854983e-05, "epoch": 8.91914191419142, "percentage": 44.6, "elapsed_time": "3:11:25", "remaining_time": "3:57:49", "throughput": 1489.72, "total_tokens": 17110224} {"current_steps": 81080, "total_steps": 181800, "loss": 0.0232, "lr": 3.387937920672442e-05, "epoch": 8.91969196919692, "percentage": 44.6, "elapsed_time": "3:11:26", "remaining_time": "3:57:48", "throughput": 1489.72, "total_tokens": 17111248} {"current_steps": 81085, "total_steps": 181800, "loss": 0.0792, "lr": 3.387713558306204e-05, "epoch": 8.92024202420242, "percentage": 44.6, "elapsed_time": "3:11:26", "remaining_time": "3:57:47", "throughput": 1489.72, "total_tokens": 17112272} {"current_steps": 81090, "total_steps": 181800, "loss": 0.0752, "lr": 3.387489187758335e-05, "epoch": 8.92079207920792, "percentage": 44.6, "elapsed_time": "3:11:27", "remaining_time": "3:57:47", "throughput": 1489.72, "total_tokens": 17113328} {"current_steps": 81095, "total_steps": 181800, "loss": 0.1223, "lr": 3.387264809030904e-05, "epoch": 8.921342134213422, "percentage": 44.61, "elapsed_time": "3:11:28", "remaining_time": "3:57:46", "throughput": 1489.73, "total_tokens": 17114448} {"current_steps": 81100, "total_steps": 181800, "loss": 0.0052, "lr": 3.38704042212598e-05, "epoch": 8.921892189218921, "percentage": 44.61, "elapsed_time": "3:11:28", "remaining_time": "3:57:45", "throughput": 1489.73, "total_tokens": 17115472} {"current_steps": 81105, "total_steps": 181800, "loss": 0.0166, "lr": 3.3868160270456305e-05, "epoch": 8.922442244224422, "percentage": 44.61, "elapsed_time": "3:11:29", "remaining_time": "3:57:44", "throughput": 1489.72, "total_tokens": 17116464} {"current_steps": 81110, "total_steps": 181800, "loss": 0.0014, "lr": 3.386591623791922e-05, "epoch": 8.922992299229923, "percentage": 44.61, "elapsed_time": "3:11:30", "remaining_time": "3:57:44", "throughput": 1489.73, "total_tokens": 17117520} {"current_steps": 81115, "total_steps": 181800, "loss": 0.0207, "lr": 3.386367212366925e-05, "epoch": 8.923542354235423, "percentage": 44.62, "elapsed_time": "3:11:31", "remaining_time": "3:57:43", "throughput": 1489.73, "total_tokens": 17118608} {"current_steps": 81120, "total_steps": 181800, "loss": 0.0168, "lr": 3.386142792772706e-05, "epoch": 8.924092409240924, "percentage": 44.62, "elapsed_time": "3:11:31", "remaining_time": "3:57:42", "throughput": 1489.74, "total_tokens": 17119728} {"current_steps": 81125, "total_steps": 181800, "loss": 0.0257, "lr": 3.3859183650113355e-05, "epoch": 8.924642464246425, "percentage": 44.62, "elapsed_time": "3:11:32", "remaining_time": "3:57:41", "throughput": 1489.75, "total_tokens": 17120816} {"current_steps": 81130, "total_steps": 181800, "loss": 0.0612, "lr": 3.3856939290848784e-05, "epoch": 8.925192519251926, "percentage": 44.63, "elapsed_time": "3:11:33", "remaining_time": "3:57:41", "throughput": 1489.75, "total_tokens": 17121904} {"current_steps": 81135, "total_steps": 181800, "loss": 0.042, "lr": 3.385469484995407e-05, "epoch": 8.925742574257425, "percentage": 44.63, "elapsed_time": "3:11:33", "remaining_time": "3:57:40", "throughput": 1489.75, "total_tokens": 17122960} {"current_steps": 81140, "total_steps": 181800, "loss": 0.0256, "lr": 3.385245032744987e-05, "epoch": 8.926292629262926, "percentage": 44.63, "elapsed_time": "3:11:34", "remaining_time": "3:57:39", "throughput": 1489.76, "total_tokens": 17124016} {"current_steps": 81145, "total_steps": 181800, "loss": 0.0067, "lr": 3.385020572335689e-05, "epoch": 8.926842684268427, "percentage": 44.63, "elapsed_time": "3:11:35", "remaining_time": "3:57:39", "throughput": 1489.76, "total_tokens": 17125136} {"current_steps": 81150, "total_steps": 181800, "loss": 0.0656, "lr": 3.384796103769581e-05, "epoch": 8.927392739273927, "percentage": 44.64, "elapsed_time": "3:11:35", "remaining_time": "3:57:38", "throughput": 1489.77, "total_tokens": 17126192} {"current_steps": 81155, "total_steps": 181800, "loss": 0.0159, "lr": 3.384571627048732e-05, "epoch": 8.927942794279428, "percentage": 44.64, "elapsed_time": "3:11:36", "remaining_time": "3:57:37", "throughput": 1489.77, "total_tokens": 17127248} {"current_steps": 81160, "total_steps": 181800, "loss": 0.0586, "lr": 3.384347142175211e-05, "epoch": 8.928492849284929, "percentage": 44.64, "elapsed_time": "3:11:37", "remaining_time": "3:57:36", "throughput": 1489.76, "total_tokens": 17128208} {"current_steps": 81165, "total_steps": 181800, "loss": 0.0153, "lr": 3.384122649151086e-05, "epoch": 8.929042904290428, "percentage": 44.65, "elapsed_time": "3:11:37", "remaining_time": "3:57:36", "throughput": 1489.76, "total_tokens": 17129232} {"current_steps": 81170, "total_steps": 181800, "loss": 0.0025, "lr": 3.383898147978427e-05, "epoch": 8.92959295929593, "percentage": 44.65, "elapsed_time": "3:11:38", "remaining_time": "3:57:35", "throughput": 1489.76, "total_tokens": 17130256} {"current_steps": 81175, "total_steps": 181800, "loss": 0.0363, "lr": 3.3836736386593026e-05, "epoch": 8.93014301430143, "percentage": 44.65, "elapsed_time": "3:11:39", "remaining_time": "3:57:34", "throughput": 1489.77, "total_tokens": 17131312} {"current_steps": 81180, "total_steps": 181800, "loss": 0.0224, "lr": 3.383449121195783e-05, "epoch": 8.930693069306932, "percentage": 44.65, "elapsed_time": "3:11:40", "remaining_time": "3:57:33", "throughput": 1489.78, "total_tokens": 17132464} {"current_steps": 81185, "total_steps": 181800, "loss": 0.0194, "lr": 3.383224595589937e-05, "epoch": 8.93124312431243, "percentage": 44.66, "elapsed_time": "3:11:40", "remaining_time": "3:57:33", "throughput": 1489.78, "total_tokens": 17133520} {"current_steps": 81190, "total_steps": 181800, "loss": 0.0264, "lr": 3.383000061843833e-05, "epoch": 8.931793179317932, "percentage": 44.66, "elapsed_time": "3:11:41", "remaining_time": "3:57:32", "throughput": 1489.78, "total_tokens": 17134544} {"current_steps": 81195, "total_steps": 181800, "loss": 0.0419, "lr": 3.382775519959541e-05, "epoch": 8.932343234323433, "percentage": 44.66, "elapsed_time": "3:11:42", "remaining_time": "3:57:31", "throughput": 1489.77, "total_tokens": 17135536} {"current_steps": 81200, "total_steps": 181800, "loss": 0.1334, "lr": 3.382550969939132e-05, "epoch": 8.932893289328932, "percentage": 44.66, "elapsed_time": "3:11:42", "remaining_time": "3:57:30", "throughput": 1489.78, "total_tokens": 17136624} {"current_steps": 81205, "total_steps": 181800, "loss": 0.0979, "lr": 3.382326411784672e-05, "epoch": 8.933443344334433, "percentage": 44.67, "elapsed_time": "3:11:43", "remaining_time": "3:57:30", "throughput": 1489.78, "total_tokens": 17137616} {"current_steps": 81210, "total_steps": 181800, "loss": 0.026, "lr": 3.382101845498235e-05, "epoch": 8.933993399339935, "percentage": 44.67, "elapsed_time": "3:11:44", "remaining_time": "3:57:29", "throughput": 1489.78, "total_tokens": 17138672} {"current_steps": 81215, "total_steps": 181800, "loss": 0.0711, "lr": 3.381877271081887e-05, "epoch": 8.934543454345434, "percentage": 44.67, "elapsed_time": "3:11:44", "remaining_time": "3:57:28", "throughput": 1489.78, "total_tokens": 17139728} {"current_steps": 81220, "total_steps": 181800, "loss": 0.0555, "lr": 3.3816526885377006e-05, "epoch": 8.935093509350935, "percentage": 44.68, "elapsed_time": "3:11:45", "remaining_time": "3:57:28", "throughput": 1489.79, "total_tokens": 17140848} {"current_steps": 81225, "total_steps": 181800, "loss": 0.0235, "lr": 3.381428097867744e-05, "epoch": 8.935643564356436, "percentage": 44.68, "elapsed_time": "3:11:46", "remaining_time": "3:57:27", "throughput": 1489.79, "total_tokens": 17141936} {"current_steps": 81230, "total_steps": 181800, "loss": 0.0737, "lr": 3.381203499074087e-05, "epoch": 8.936193619361937, "percentage": 44.68, "elapsed_time": "3:11:46", "remaining_time": "3:57:26", "throughput": 1489.8, "total_tokens": 17142992} {"current_steps": 81235, "total_steps": 181800, "loss": 0.0269, "lr": 3.3809788921588e-05, "epoch": 8.936743674367436, "percentage": 44.68, "elapsed_time": "3:11:47", "remaining_time": "3:57:25", "throughput": 1489.8, "total_tokens": 17144048} {"current_steps": 81240, "total_steps": 181800, "loss": 0.01, "lr": 3.3807542771239544e-05, "epoch": 8.937293729372938, "percentage": 44.69, "elapsed_time": "3:11:48", "remaining_time": "3:57:25", "throughput": 1489.8, "total_tokens": 17145072} {"current_steps": 81245, "total_steps": 181800, "loss": 0.0134, "lr": 3.380529653971619e-05, "epoch": 8.937843784378439, "percentage": 44.69, "elapsed_time": "3:11:48", "remaining_time": "3:57:24", "throughput": 1489.8, "total_tokens": 17146128} {"current_steps": 81250, "total_steps": 181800, "loss": 0.0532, "lr": 3.3803050227038635e-05, "epoch": 8.938393839383938, "percentage": 44.69, "elapsed_time": "3:11:49", "remaining_time": "3:57:23", "throughput": 1489.81, "total_tokens": 17147216} {"current_steps": 81255, "total_steps": 181800, "loss": 0.0679, "lr": 3.3800803833227596e-05, "epoch": 8.938943894389439, "percentage": 44.69, "elapsed_time": "3:11:50", "remaining_time": "3:57:22", "throughput": 1489.81, "total_tokens": 17148304} {"current_steps": 81260, "total_steps": 181800, "loss": 0.0837, "lr": 3.379855735830377e-05, "epoch": 8.93949394939494, "percentage": 44.7, "elapsed_time": "3:11:51", "remaining_time": "3:57:22", "throughput": 1489.81, "total_tokens": 17149360} {"current_steps": 81265, "total_steps": 181800, "loss": 0.0358, "lr": 3.3796310802287864e-05, "epoch": 8.94004400440044, "percentage": 44.7, "elapsed_time": "3:11:51", "remaining_time": "3:57:21", "throughput": 1489.82, "total_tokens": 17150448} {"current_steps": 81270, "total_steps": 181800, "loss": 0.014, "lr": 3.379406416520058e-05, "epoch": 8.94059405940594, "percentage": 44.7, "elapsed_time": "3:11:52", "remaining_time": "3:57:20", "throughput": 1489.82, "total_tokens": 17151440} {"current_steps": 81275, "total_steps": 181800, "loss": 0.0433, "lr": 3.379181744706263e-05, "epoch": 8.941144114411442, "percentage": 44.71, "elapsed_time": "3:11:53", "remaining_time": "3:57:20", "throughput": 1489.82, "total_tokens": 17152496} {"current_steps": 81280, "total_steps": 181800, "loss": 0.0171, "lr": 3.3789570647894706e-05, "epoch": 8.941694169416941, "percentage": 44.71, "elapsed_time": "3:11:53", "remaining_time": "3:57:19", "throughput": 1489.82, "total_tokens": 17153520} {"current_steps": 81285, "total_steps": 181800, "loss": 0.0366, "lr": 3.378732376771754e-05, "epoch": 8.942244224422442, "percentage": 44.71, "elapsed_time": "3:11:54", "remaining_time": "3:57:18", "throughput": 1489.82, "total_tokens": 17154608} {"current_steps": 81290, "total_steps": 181800, "loss": 0.02, "lr": 3.3785076806551824e-05, "epoch": 8.942794279427943, "percentage": 44.71, "elapsed_time": "3:11:55", "remaining_time": "3:57:17", "throughput": 1489.82, "total_tokens": 17155632} {"current_steps": 81295, "total_steps": 181800, "loss": 0.0924, "lr": 3.378282976441827e-05, "epoch": 8.943344334433444, "percentage": 44.72, "elapsed_time": "3:11:55", "remaining_time": "3:57:17", "throughput": 1489.82, "total_tokens": 17156656} {"current_steps": 81300, "total_steps": 181800, "loss": 0.0683, "lr": 3.3780582641337586e-05, "epoch": 8.943894389438944, "percentage": 44.72, "elapsed_time": "3:11:56", "remaining_time": "3:57:16", "throughput": 1489.83, "total_tokens": 17157744} {"current_steps": 81305, "total_steps": 181800, "loss": 0.0114, "lr": 3.3778335437330494e-05, "epoch": 8.944444444444445, "percentage": 44.72, "elapsed_time": "3:11:57", "remaining_time": "3:57:15", "throughput": 1489.83, "total_tokens": 17158832} {"current_steps": 81310, "total_steps": 181800, "loss": 0.0378, "lr": 3.377608815241769e-05, "epoch": 8.944994499449946, "percentage": 44.72, "elapsed_time": "3:11:57", "remaining_time": "3:57:14", "throughput": 1489.83, "total_tokens": 17159888} {"current_steps": 81315, "total_steps": 181800, "loss": 0.0308, "lr": 3.3773840786619896e-05, "epoch": 8.945544554455445, "percentage": 44.73, "elapsed_time": "3:11:58", "remaining_time": "3:57:14", "throughput": 1489.84, "total_tokens": 17160976} {"current_steps": 81320, "total_steps": 181800, "loss": 0.0307, "lr": 3.3771593339957806e-05, "epoch": 8.946094609460946, "percentage": 44.73, "elapsed_time": "3:11:59", "remaining_time": "3:57:13", "throughput": 1489.84, "total_tokens": 17162032} {"current_steps": 81325, "total_steps": 181800, "loss": 0.0332, "lr": 3.376934581245217e-05, "epoch": 8.946644664466447, "percentage": 44.73, "elapsed_time": "3:12:00", "remaining_time": "3:57:12", "throughput": 1489.85, "total_tokens": 17163120} {"current_steps": 81330, "total_steps": 181800, "loss": 0.0456, "lr": 3.376709820412367e-05, "epoch": 8.947194719471947, "percentage": 44.74, "elapsed_time": "3:12:00", "remaining_time": "3:57:12", "throughput": 1489.85, "total_tokens": 17164176} {"current_steps": 81335, "total_steps": 181800, "loss": 0.0634, "lr": 3.376485051499303e-05, "epoch": 8.947744774477448, "percentage": 44.74, "elapsed_time": "3:12:01", "remaining_time": "3:57:11", "throughput": 1489.85, "total_tokens": 17165232} {"current_steps": 81340, "total_steps": 181800, "loss": 0.1507, "lr": 3.3762602745080985e-05, "epoch": 8.948294829482949, "percentage": 44.74, "elapsed_time": "3:12:02", "remaining_time": "3:57:10", "throughput": 1489.85, "total_tokens": 17166192} {"current_steps": 81345, "total_steps": 181800, "loss": 0.0065, "lr": 3.376035489440822e-05, "epoch": 8.948844884488448, "percentage": 44.74, "elapsed_time": "3:12:02", "remaining_time": "3:57:09", "throughput": 1489.85, "total_tokens": 17167248} {"current_steps": 81350, "total_steps": 181800, "loss": 0.0058, "lr": 3.3758106962995465e-05, "epoch": 8.94939493949395, "percentage": 44.75, "elapsed_time": "3:12:03", "remaining_time": "3:57:09", "throughput": 1489.85, "total_tokens": 17168336} {"current_steps": 81355, "total_steps": 181800, "loss": 0.0037, "lr": 3.375585895086345e-05, "epoch": 8.94994499449945, "percentage": 44.75, "elapsed_time": "3:12:04", "remaining_time": "3:57:08", "throughput": 1489.86, "total_tokens": 17169424} {"current_steps": 81360, "total_steps": 181800, "loss": 0.0093, "lr": 3.375361085803289e-05, "epoch": 8.950495049504951, "percentage": 44.75, "elapsed_time": "3:12:04", "remaining_time": "3:57:07", "throughput": 1489.86, "total_tokens": 17170480} {"current_steps": 81365, "total_steps": 181800, "loss": 0.0115, "lr": 3.375136268452449e-05, "epoch": 8.95104510451045, "percentage": 44.76, "elapsed_time": "3:12:05", "remaining_time": "3:57:06", "throughput": 1489.86, "total_tokens": 17171536} {"current_steps": 81370, "total_steps": 181800, "loss": 0.0083, "lr": 3.374911443035898e-05, "epoch": 8.951595159515952, "percentage": 44.76, "elapsed_time": "3:12:06", "remaining_time": "3:57:06", "throughput": 1489.87, "total_tokens": 17172624} {"current_steps": 81375, "total_steps": 181800, "loss": 0.0846, "lr": 3.374686609555708e-05, "epoch": 8.952145214521453, "percentage": 44.76, "elapsed_time": "3:12:06", "remaining_time": "3:57:05", "throughput": 1489.87, "total_tokens": 17173680} {"current_steps": 81380, "total_steps": 181800, "loss": 0.0051, "lr": 3.374461768013951e-05, "epoch": 8.952695269526952, "percentage": 44.76, "elapsed_time": "3:12:07", "remaining_time": "3:57:04", "throughput": 1489.87, "total_tokens": 17174704} {"current_steps": 81385, "total_steps": 181800, "loss": 0.1189, "lr": 3.3742369184127005e-05, "epoch": 8.953245324532453, "percentage": 44.77, "elapsed_time": "3:12:08", "remaining_time": "3:57:03", "throughput": 1489.88, "total_tokens": 17175792} {"current_steps": 81390, "total_steps": 181800, "loss": 0.0183, "lr": 3.374012060754027e-05, "epoch": 8.953795379537954, "percentage": 44.77, "elapsed_time": "3:12:09", "remaining_time": "3:57:03", "throughput": 1489.88, "total_tokens": 17176880} {"current_steps": 81395, "total_steps": 181800, "loss": 0.1919, "lr": 3.373787195040003e-05, "epoch": 8.954345434543454, "percentage": 44.77, "elapsed_time": "3:12:09", "remaining_time": "3:57:02", "throughput": 1489.89, "total_tokens": 17177968} {"current_steps": 81400, "total_steps": 181800, "loss": 0.0128, "lr": 3.373562321272704e-05, "epoch": 8.954895489548955, "percentage": 44.77, "elapsed_time": "3:12:10", "remaining_time": "3:57:01", "throughput": 1489.89, "total_tokens": 17179056} {"current_steps": 81405, "total_steps": 181800, "loss": 0.0078, "lr": 3.3733374394541984e-05, "epoch": 8.955445544554456, "percentage": 44.78, "elapsed_time": "3:12:11", "remaining_time": "3:57:01", "throughput": 1489.9, "total_tokens": 17180144} {"current_steps": 81410, "total_steps": 181800, "loss": 0.0441, "lr": 3.373112549586561e-05, "epoch": 8.955995599559955, "percentage": 44.78, "elapsed_time": "3:12:11", "remaining_time": "3:57:00", "throughput": 1489.9, "total_tokens": 17181168} {"current_steps": 81415, "total_steps": 181800, "loss": 0.0848, "lr": 3.372887651671864e-05, "epoch": 8.956545654565456, "percentage": 44.78, "elapsed_time": "3:12:12", "remaining_time": "3:56:59", "throughput": 1489.9, "total_tokens": 17182288} {"current_steps": 81420, "total_steps": 181800, "loss": 0.0105, "lr": 3.372662745712182e-05, "epoch": 8.957095709570957, "percentage": 44.79, "elapsed_time": "3:12:13", "remaining_time": "3:56:58", "throughput": 1489.91, "total_tokens": 17183344} {"current_steps": 81425, "total_steps": 181800, "loss": 0.0786, "lr": 3.372437831709584e-05, "epoch": 8.957645764576458, "percentage": 44.79, "elapsed_time": "3:12:13", "remaining_time": "3:56:58", "throughput": 1489.91, "total_tokens": 17184400} {"current_steps": 81430, "total_steps": 181800, "loss": 0.0338, "lr": 3.372212909666146e-05, "epoch": 8.958195819581958, "percentage": 44.79, "elapsed_time": "3:12:14", "remaining_time": "3:56:57", "throughput": 1489.91, "total_tokens": 17185424} {"current_steps": 81435, "total_steps": 181800, "loss": 0.0431, "lr": 3.3719879795839406e-05, "epoch": 8.958745874587459, "percentage": 44.79, "elapsed_time": "3:12:15", "remaining_time": "3:56:56", "throughput": 1489.91, "total_tokens": 17186448} {"current_steps": 81440, "total_steps": 181800, "loss": 0.0209, "lr": 3.37176304146504e-05, "epoch": 8.95929592959296, "percentage": 44.8, "elapsed_time": "3:12:15", "remaining_time": "3:56:55", "throughput": 1489.91, "total_tokens": 17187440} {"current_steps": 81445, "total_steps": 181800, "loss": 0.0073, "lr": 3.3715380953115175e-05, "epoch": 8.95984598459846, "percentage": 44.8, "elapsed_time": "3:12:16", "remaining_time": "3:56:55", "throughput": 1489.92, "total_tokens": 17188624} {"current_steps": 81450, "total_steps": 181800, "loss": 0.0247, "lr": 3.371313141125447e-05, "epoch": 8.96039603960396, "percentage": 44.8, "elapsed_time": "3:12:17", "remaining_time": "3:56:54", "throughput": 1489.93, "total_tokens": 17189744} {"current_steps": 81455, "total_steps": 181800, "loss": 0.1495, "lr": 3.371088178908901e-05, "epoch": 8.960946094609461, "percentage": 44.8, "elapsed_time": "3:12:17", "remaining_time": "3:56:53", "throughput": 1489.93, "total_tokens": 17190800} {"current_steps": 81460, "total_steps": 181800, "loss": 0.0209, "lr": 3.370863208663954e-05, "epoch": 8.96149614961496, "percentage": 44.81, "elapsed_time": "3:12:18", "remaining_time": "3:56:53", "throughput": 1489.93, "total_tokens": 17191824} {"current_steps": 81465, "total_steps": 181800, "loss": 0.0063, "lr": 3.370638230392678e-05, "epoch": 8.962046204620462, "percentage": 44.81, "elapsed_time": "3:12:19", "remaining_time": "3:56:52", "throughput": 1489.93, "total_tokens": 17192880} {"current_steps": 81470, "total_steps": 181800, "loss": 0.0412, "lr": 3.3704132440971474e-05, "epoch": 8.962596259625963, "percentage": 44.81, "elapsed_time": "3:12:20", "remaining_time": "3:56:51", "throughput": 1489.93, "total_tokens": 17193936} {"current_steps": 81475, "total_steps": 181800, "loss": 0.0345, "lr": 3.370188249779436e-05, "epoch": 8.963146314631462, "percentage": 44.82, "elapsed_time": "3:12:20", "remaining_time": "3:56:50", "throughput": 1489.93, "total_tokens": 17194960} {"current_steps": 81480, "total_steps": 181800, "loss": 0.0065, "lr": 3.369963247441617e-05, "epoch": 8.963696369636963, "percentage": 44.82, "elapsed_time": "3:12:21", "remaining_time": "3:56:50", "throughput": 1489.93, "total_tokens": 17195984} {"current_steps": 81485, "total_steps": 181800, "loss": 0.0541, "lr": 3.369738237085763e-05, "epoch": 8.964246424642464, "percentage": 44.82, "elapsed_time": "3:12:22", "remaining_time": "3:56:49", "throughput": 1489.94, "total_tokens": 17197040} {"current_steps": 81490, "total_steps": 181800, "loss": 0.08, "lr": 3.36951321871395e-05, "epoch": 8.964796479647966, "percentage": 44.82, "elapsed_time": "3:12:22", "remaining_time": "3:56:48", "throughput": 1489.94, "total_tokens": 17198096} {"current_steps": 81495, "total_steps": 181800, "loss": 0.0091, "lr": 3.3692881923282506e-05, "epoch": 8.965346534653465, "percentage": 44.83, "elapsed_time": "3:12:23", "remaining_time": "3:56:47", "throughput": 1489.94, "total_tokens": 17199120} {"current_steps": 81500, "total_steps": 181800, "loss": 0.027, "lr": 3.369063157930739e-05, "epoch": 8.965896589658966, "percentage": 44.83, "elapsed_time": "3:12:24", "remaining_time": "3:56:47", "throughput": 1489.94, "total_tokens": 17200112} {"current_steps": 81505, "total_steps": 181800, "loss": 0.1687, "lr": 3.3688381155234904e-05, "epoch": 8.966446644664467, "percentage": 44.83, "elapsed_time": "3:12:24", "remaining_time": "3:56:46", "throughput": 1489.94, "total_tokens": 17201200} {"current_steps": 81510, "total_steps": 181800, "loss": 0.0713, "lr": 3.3686130651085764e-05, "epoch": 8.966996699669966, "percentage": 44.83, "elapsed_time": "3:12:25", "remaining_time": "3:56:45", "throughput": 1489.94, "total_tokens": 17202224} {"current_steps": 81515, "total_steps": 181800, "loss": 0.0249, "lr": 3.368388006688073e-05, "epoch": 8.967546754675467, "percentage": 44.84, "elapsed_time": "3:12:26", "remaining_time": "3:56:44", "throughput": 1489.95, "total_tokens": 17203312} {"current_steps": 81520, "total_steps": 181800, "loss": 0.0682, "lr": 3.368162940264054e-05, "epoch": 8.968096809680969, "percentage": 44.84, "elapsed_time": "3:12:26", "remaining_time": "3:56:44", "throughput": 1489.95, "total_tokens": 17204368} {"current_steps": 81525, "total_steps": 181800, "loss": 0.0372, "lr": 3.367937865838594e-05, "epoch": 8.968646864686468, "percentage": 44.84, "elapsed_time": "3:12:27", "remaining_time": "3:56:43", "throughput": 1489.95, "total_tokens": 17205392} {"current_steps": 81530, "total_steps": 181800, "loss": 0.0459, "lr": 3.3677127834137674e-05, "epoch": 8.969196919691969, "percentage": 44.85, "elapsed_time": "3:12:28", "remaining_time": "3:56:42", "throughput": 1489.95, "total_tokens": 17206416} {"current_steps": 81535, "total_steps": 181800, "loss": 0.0038, "lr": 3.3674876929916476e-05, "epoch": 8.96974697469747, "percentage": 44.85, "elapsed_time": "3:12:29", "remaining_time": "3:56:42", "throughput": 1489.95, "total_tokens": 17207440} {"current_steps": 81540, "total_steps": 181800, "loss": 0.0228, "lr": 3.3672625945743106e-05, "epoch": 8.97029702970297, "percentage": 44.85, "elapsed_time": "3:12:29", "remaining_time": "3:56:41", "throughput": 1489.94, "total_tokens": 17208432} {"current_steps": 81545, "total_steps": 181800, "loss": 0.0207, "lr": 3.36703748816383e-05, "epoch": 8.97084708470847, "percentage": 44.85, "elapsed_time": "3:12:30", "remaining_time": "3:56:40", "throughput": 1489.95, "total_tokens": 17209520} {"current_steps": 81550, "total_steps": 181800, "loss": 0.012, "lr": 3.366812373762282e-05, "epoch": 8.971397139713972, "percentage": 44.86, "elapsed_time": "3:12:31", "remaining_time": "3:56:39", "throughput": 1489.95, "total_tokens": 17210544} {"current_steps": 81555, "total_steps": 181800, "loss": 0.0934, "lr": 3.366587251371739e-05, "epoch": 8.971947194719473, "percentage": 44.86, "elapsed_time": "3:12:31", "remaining_time": "3:56:39", "throughput": 1489.95, "total_tokens": 17211632} {"current_steps": 81560, "total_steps": 181800, "loss": 0.0462, "lr": 3.366362120994277e-05, "epoch": 8.972497249724972, "percentage": 44.86, "elapsed_time": "3:12:32", "remaining_time": "3:56:38", "throughput": 1489.96, "total_tokens": 17212688} {"current_steps": 81565, "total_steps": 181800, "loss": 0.0342, "lr": 3.366136982631973e-05, "epoch": 8.973047304730473, "percentage": 44.87, "elapsed_time": "3:12:33", "remaining_time": "3:56:37", "throughput": 1489.96, "total_tokens": 17213744} {"current_steps": 81570, "total_steps": 181800, "loss": 0.0825, "lr": 3.365911836286898e-05, "epoch": 8.973597359735974, "percentage": 44.87, "elapsed_time": "3:12:33", "remaining_time": "3:56:36", "throughput": 1489.96, "total_tokens": 17214736} {"current_steps": 81575, "total_steps": 181800, "loss": 0.0163, "lr": 3.3656866819611306e-05, "epoch": 8.974147414741473, "percentage": 44.87, "elapsed_time": "3:12:34", "remaining_time": "3:56:36", "throughput": 1489.96, "total_tokens": 17215824} {"current_steps": 81580, "total_steps": 181800, "loss": 0.0069, "lr": 3.3654615196567435e-05, "epoch": 8.974697469746975, "percentage": 44.87, "elapsed_time": "3:12:35", "remaining_time": "3:56:35", "throughput": 1489.97, "total_tokens": 17216912} {"current_steps": 81585, "total_steps": 181800, "loss": 0.0072, "lr": 3.3652363493758126e-05, "epoch": 8.975247524752476, "percentage": 44.88, "elapsed_time": "3:12:35", "remaining_time": "3:56:34", "throughput": 1489.96, "total_tokens": 17217904} {"current_steps": 81590, "total_steps": 181800, "loss": 0.1511, "lr": 3.365011171120414e-05, "epoch": 8.975797579757975, "percentage": 44.88, "elapsed_time": "3:12:36", "remaining_time": "3:56:33", "throughput": 1489.96, "total_tokens": 17218928} {"current_steps": 81595, "total_steps": 181800, "loss": 0.1391, "lr": 3.364785984892622e-05, "epoch": 8.976347634763476, "percentage": 44.88, "elapsed_time": "3:12:37", "remaining_time": "3:56:33", "throughput": 1489.97, "total_tokens": 17220016} {"current_steps": 81600, "total_steps": 181800, "loss": 0.0072, "lr": 3.3645607906945134e-05, "epoch": 8.976897689768977, "percentage": 44.88, "elapsed_time": "3:12:37", "remaining_time": "3:56:32", "throughput": 1489.97, "total_tokens": 17221008} {"current_steps": 81605, "total_steps": 181800, "loss": 0.018, "lr": 3.364335588528162e-05, "epoch": 8.977447744774478, "percentage": 44.89, "elapsed_time": "3:12:38", "remaining_time": "3:56:31", "throughput": 1489.97, "total_tokens": 17222032} {"current_steps": 81610, "total_steps": 181800, "loss": 0.0891, "lr": 3.364110378395645e-05, "epoch": 8.977997799779978, "percentage": 44.89, "elapsed_time": "3:12:39", "remaining_time": "3:56:31", "throughput": 1489.97, "total_tokens": 17223056} {"current_steps": 81615, "total_steps": 181800, "loss": 0.0985, "lr": 3.363885160299037e-05, "epoch": 8.978547854785479, "percentage": 44.89, "elapsed_time": "3:12:40", "remaining_time": "3:56:30", "throughput": 1489.97, "total_tokens": 17224176} {"current_steps": 81620, "total_steps": 181800, "loss": 0.0648, "lr": 3.363659934240414e-05, "epoch": 8.97909790979098, "percentage": 44.9, "elapsed_time": "3:12:40", "remaining_time": "3:56:29", "throughput": 1489.98, "total_tokens": 17225232} {"current_steps": 81625, "total_steps": 181800, "loss": 0.0542, "lr": 3.3634347002218514e-05, "epoch": 8.979647964796479, "percentage": 44.9, "elapsed_time": "3:12:41", "remaining_time": "3:56:28", "throughput": 1489.98, "total_tokens": 17226256} {"current_steps": 81630, "total_steps": 181800, "loss": 0.1231, "lr": 3.363209458245426e-05, "epoch": 8.98019801980198, "percentage": 44.9, "elapsed_time": "3:12:42", "remaining_time": "3:56:28", "throughput": 1489.97, "total_tokens": 17227280} {"current_steps": 81635, "total_steps": 181800, "loss": 0.0441, "lr": 3.3629842083132126e-05, "epoch": 8.980748074807481, "percentage": 44.9, "elapsed_time": "3:12:42", "remaining_time": "3:56:27", "throughput": 1489.98, "total_tokens": 17228368} {"current_steps": 81640, "total_steps": 181800, "loss": 0.0387, "lr": 3.3627589504272886e-05, "epoch": 8.98129812981298, "percentage": 44.91, "elapsed_time": "3:12:43", "remaining_time": "3:56:26", "throughput": 1489.98, "total_tokens": 17229424} {"current_steps": 81645, "total_steps": 181800, "loss": 0.0385, "lr": 3.3625336845897296e-05, "epoch": 8.981848184818482, "percentage": 44.91, "elapsed_time": "3:12:44", "remaining_time": "3:56:25", "throughput": 1489.99, "total_tokens": 17230544} {"current_steps": 81650, "total_steps": 181800, "loss": 0.0102, "lr": 3.362308410802611e-05, "epoch": 8.982398239823983, "percentage": 44.91, "elapsed_time": "3:12:44", "remaining_time": "3:56:25", "throughput": 1490.0, "total_tokens": 17231664} {"current_steps": 81655, "total_steps": 181800, "loss": 0.0141, "lr": 3.362083129068009e-05, "epoch": 8.982948294829484, "percentage": 44.91, "elapsed_time": "3:12:45", "remaining_time": "3:56:24", "throughput": 1490.0, "total_tokens": 17232720} {"current_steps": 81660, "total_steps": 181800, "loss": 0.0673, "lr": 3.361857839388001e-05, "epoch": 8.983498349834983, "percentage": 44.92, "elapsed_time": "3:12:46", "remaining_time": "3:56:23", "throughput": 1490.0, "total_tokens": 17233712} {"current_steps": 81665, "total_steps": 181800, "loss": 0.0267, "lr": 3.3616325417646624e-05, "epoch": 8.984048404840484, "percentage": 44.92, "elapsed_time": "3:12:46", "remaining_time": "3:56:23", "throughput": 1490.0, "total_tokens": 17234768} {"current_steps": 81670, "total_steps": 181800, "loss": 0.0076, "lr": 3.361407236200071e-05, "epoch": 8.984598459845985, "percentage": 44.92, "elapsed_time": "3:12:47", "remaining_time": "3:56:22", "throughput": 1490.0, "total_tokens": 17235824} {"current_steps": 81675, "total_steps": 181800, "loss": 0.0199, "lr": 3.361181922696302e-05, "epoch": 8.985148514851485, "percentage": 44.93, "elapsed_time": "3:12:48", "remaining_time": "3:56:21", "throughput": 1490.01, "total_tokens": 17236880} {"current_steps": 81680, "total_steps": 181800, "loss": 0.1151, "lr": 3.360956601255433e-05, "epoch": 8.985698569856986, "percentage": 44.93, "elapsed_time": "3:12:49", "remaining_time": "3:56:20", "throughput": 1490.01, "total_tokens": 17237936} {"current_steps": 81685, "total_steps": 181800, "loss": 0.0814, "lr": 3.360731271879538e-05, "epoch": 8.986248624862487, "percentage": 44.93, "elapsed_time": "3:12:49", "remaining_time": "3:56:20", "throughput": 1490.01, "total_tokens": 17238992} {"current_steps": 81690, "total_steps": 181800, "loss": 0.0538, "lr": 3.360505934570698e-05, "epoch": 8.986798679867986, "percentage": 44.93, "elapsed_time": "3:12:50", "remaining_time": "3:56:19", "throughput": 1490.01, "total_tokens": 17239984} {"current_steps": 81695, "total_steps": 181800, "loss": 0.0246, "lr": 3.360280589330988e-05, "epoch": 8.987348734873487, "percentage": 44.94, "elapsed_time": "3:12:51", "remaining_time": "3:56:18", "throughput": 1490.02, "total_tokens": 17241104} {"current_steps": 81700, "total_steps": 181800, "loss": 0.0442, "lr": 3.3600552361624833e-05, "epoch": 8.987898789878988, "percentage": 44.94, "elapsed_time": "3:12:51", "remaining_time": "3:56:17", "throughput": 1490.01, "total_tokens": 17242128} {"current_steps": 81705, "total_steps": 181800, "loss": 0.0067, "lr": 3.359829875067263e-05, "epoch": 8.988448844884488, "percentage": 44.94, "elapsed_time": "3:12:52", "remaining_time": "3:56:17", "throughput": 1490.02, "total_tokens": 17243216} {"current_steps": 81710, "total_steps": 181800, "loss": 0.0048, "lr": 3.359604506047403e-05, "epoch": 8.988998899889989, "percentage": 44.94, "elapsed_time": "3:12:53", "remaining_time": "3:56:16", "throughput": 1490.03, "total_tokens": 17244368} {"current_steps": 81715, "total_steps": 181800, "loss": 0.0357, "lr": 3.35937912910498e-05, "epoch": 8.98954895489549, "percentage": 44.95, "elapsed_time": "3:12:53", "remaining_time": "3:56:15", "throughput": 1490.04, "total_tokens": 17245456} {"current_steps": 81720, "total_steps": 181800, "loss": 0.0074, "lr": 3.359153744242073e-05, "epoch": 8.990099009900991, "percentage": 44.95, "elapsed_time": "3:12:54", "remaining_time": "3:56:14", "throughput": 1490.03, "total_tokens": 17246480} {"current_steps": 81725, "total_steps": 181800, "loss": 0.0074, "lr": 3.358928351460758e-05, "epoch": 8.99064906490649, "percentage": 44.95, "elapsed_time": "3:12:55", "remaining_time": "3:56:14", "throughput": 1490.03, "total_tokens": 17247504} {"current_steps": 81730, "total_steps": 181800, "loss": 0.0128, "lr": 3.358702950763112e-05, "epoch": 8.991199119911991, "percentage": 44.96, "elapsed_time": "3:12:55", "remaining_time": "3:56:13", "throughput": 1490.04, "total_tokens": 17248560} {"current_steps": 81735, "total_steps": 181800, "loss": 0.0027, "lr": 3.358477542151214e-05, "epoch": 8.991749174917492, "percentage": 44.96, "elapsed_time": "3:12:56", "remaining_time": "3:56:12", "throughput": 1490.04, "total_tokens": 17249616} {"current_steps": 81740, "total_steps": 181800, "loss": 0.0993, "lr": 3.35825212562714e-05, "epoch": 8.992299229922992, "percentage": 44.96, "elapsed_time": "3:12:57", "remaining_time": "3:56:12", "throughput": 1490.04, "total_tokens": 17250704} {"current_steps": 81745, "total_steps": 181800, "loss": 0.0343, "lr": 3.358026701192968e-05, "epoch": 8.992849284928493, "percentage": 44.96, "elapsed_time": "3:12:57", "remaining_time": "3:56:11", "throughput": 1490.06, "total_tokens": 17251856} {"current_steps": 81750, "total_steps": 181800, "loss": 0.0476, "lr": 3.357801268850775e-05, "epoch": 8.993399339933994, "percentage": 44.97, "elapsed_time": "3:12:58", "remaining_time": "3:56:10", "throughput": 1490.06, "total_tokens": 17252912} {"current_steps": 81755, "total_steps": 181800, "loss": 0.0442, "lr": 3.35757582860264e-05, "epoch": 8.993949394939493, "percentage": 44.97, "elapsed_time": "3:12:59", "remaining_time": "3:56:09", "throughput": 1490.07, "total_tokens": 17254064} {"current_steps": 81760, "total_steps": 181800, "loss": 0.1434, "lr": 3.357350380450639e-05, "epoch": 8.994499449944994, "percentage": 44.97, "elapsed_time": "3:13:00", "remaining_time": "3:56:09", "throughput": 1490.07, "total_tokens": 17255088} {"current_steps": 81765, "total_steps": 181800, "loss": 0.0342, "lr": 3.357124924396853e-05, "epoch": 8.995049504950495, "percentage": 44.98, "elapsed_time": "3:13:00", "remaining_time": "3:56:08", "throughput": 1490.07, "total_tokens": 17256112} {"current_steps": 81770, "total_steps": 181800, "loss": 0.0219, "lr": 3.356899460443356e-05, "epoch": 8.995599559955995, "percentage": 44.98, "elapsed_time": "3:13:01", "remaining_time": "3:56:07", "throughput": 1490.06, "total_tokens": 17257104} {"current_steps": 81775, "total_steps": 181800, "loss": 0.0555, "lr": 3.356673988592228e-05, "epoch": 8.996149614961496, "percentage": 44.98, "elapsed_time": "3:13:02", "remaining_time": "3:56:06", "throughput": 1490.06, "total_tokens": 17258096} {"current_steps": 81780, "total_steps": 181800, "loss": 0.0292, "lr": 3.356448508845548e-05, "epoch": 8.996699669966997, "percentage": 44.98, "elapsed_time": "3:13:02", "remaining_time": "3:56:06", "throughput": 1490.07, "total_tokens": 17259216} {"current_steps": 81785, "total_steps": 181800, "loss": 0.0559, "lr": 3.356223021205392e-05, "epoch": 8.997249724972498, "percentage": 44.99, "elapsed_time": "3:13:03", "remaining_time": "3:56:05", "throughput": 1490.08, "total_tokens": 17260336} {"current_steps": 81790, "total_steps": 181800, "loss": 0.0066, "lr": 3.35599752567384e-05, "epoch": 8.997799779977997, "percentage": 44.99, "elapsed_time": "3:13:04", "remaining_time": "3:56:04", "throughput": 1490.07, "total_tokens": 17261328} {"current_steps": 81795, "total_steps": 181800, "loss": 0.044, "lr": 3.355772022252969e-05, "epoch": 8.998349834983498, "percentage": 44.99, "elapsed_time": "3:13:04", "remaining_time": "3:56:04", "throughput": 1490.07, "total_tokens": 17262320} {"current_steps": 81800, "total_steps": 181800, "loss": 0.0481, "lr": 3.355546510944858e-05, "epoch": 8.998899889989, "percentage": 44.99, "elapsed_time": "3:13:05", "remaining_time": "3:56:03", "throughput": 1490.07, "total_tokens": 17263376} {"current_steps": 81805, "total_steps": 181800, "loss": 0.0064, "lr": 3.355320991751586e-05, "epoch": 8.999449944994499, "percentage": 45.0, "elapsed_time": "3:13:06", "remaining_time": "3:56:02", "throughput": 1490.08, "total_tokens": 17264432} {"current_steps": 81810, "total_steps": 181800, "loss": 0.0722, "lr": 3.3550954646752304e-05, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "3:13:07", "remaining_time": "3:56:01", "throughput": 1490.06, "total_tokens": 17265344} {"current_steps": 81810, "total_steps": 181800, "eval_loss": 0.06155921891331673, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "3:13:44", "remaining_time": "3:56:47", "throughput": 1485.31, "total_tokens": 17265344} {"current_steps": 81815, "total_steps": 181800, "loss": 0.0094, "lr": 3.35486992971787e-05, "epoch": 9.000550055005501, "percentage": 45.0, "elapsed_time": "3:13:46", "remaining_time": "3:56:48", "throughput": 1485.14, "total_tokens": 17266336} {"current_steps": 81820, "total_steps": 181800, "loss": 0.0073, "lr": 3.354644386881584e-05, "epoch": 9.001100110011, "percentage": 45.01, "elapsed_time": "3:13:46", "remaining_time": "3:56:47", "throughput": 1485.14, "total_tokens": 17267392} {"current_steps": 81825, "total_steps": 181800, "loss": 0.0073, "lr": 3.354418836168451e-05, "epoch": 9.001650165016502, "percentage": 45.01, "elapsed_time": "3:13:47", "remaining_time": "3:56:46", "throughput": 1485.14, "total_tokens": 17268416} {"current_steps": 81830, "total_steps": 181800, "loss": 0.0555, "lr": 3.3541932775805485e-05, "epoch": 9.002200220022003, "percentage": 45.01, "elapsed_time": "3:13:48", "remaining_time": "3:56:45", "throughput": 1485.14, "total_tokens": 17269376} {"current_steps": 81835, "total_steps": 181800, "loss": 0.0081, "lr": 3.3539677111199573e-05, "epoch": 9.002750275027502, "percentage": 45.01, "elapsed_time": "3:13:48", "remaining_time": "3:56:45", "throughput": 1485.13, "total_tokens": 17270368} {"current_steps": 81840, "total_steps": 181800, "loss": 0.0409, "lr": 3.353742136788756e-05, "epoch": 9.003300330033003, "percentage": 45.02, "elapsed_time": "3:13:49", "remaining_time": "3:56:44", "throughput": 1485.13, "total_tokens": 17271392} {"current_steps": 81845, "total_steps": 181800, "loss": 0.0991, "lr": 3.353516554589022e-05, "epoch": 9.003850385038504, "percentage": 45.02, "elapsed_time": "3:13:50", "remaining_time": "3:56:43", "throughput": 1485.13, "total_tokens": 17272480} {"current_steps": 81850, "total_steps": 181800, "loss": 0.0031, "lr": 3.3532909645228354e-05, "epoch": 9.004400440044005, "percentage": 45.02, "elapsed_time": "3:13:50", "remaining_time": "3:56:42", "throughput": 1485.14, "total_tokens": 17273600} {"current_steps": 81855, "total_steps": 181800, "loss": 0.0127, "lr": 3.353065366592276e-05, "epoch": 9.004950495049505, "percentage": 45.02, "elapsed_time": "3:13:51", "remaining_time": "3:56:42", "throughput": 1485.13, "total_tokens": 17274720} {"current_steps": 81860, "total_steps": 181800, "loss": 0.0371, "lr": 3.3528397607994226e-05, "epoch": 9.005500550055006, "percentage": 45.03, "elapsed_time": "3:13:52", "remaining_time": "3:56:41", "throughput": 1485.13, "total_tokens": 17275776} {"current_steps": 81865, "total_steps": 181800, "loss": 0.0879, "lr": 3.352614147146355e-05, "epoch": 9.006050605060507, "percentage": 45.03, "elapsed_time": "3:13:53", "remaining_time": "3:56:40", "throughput": 1485.13, "total_tokens": 17276832} {"current_steps": 81870, "total_steps": 181800, "loss": 0.0281, "lr": 3.3523885256351504e-05, "epoch": 9.006600660066006, "percentage": 45.03, "elapsed_time": "3:13:53", "remaining_time": "3:56:40", "throughput": 1485.13, "total_tokens": 17277888} {"current_steps": 81875, "total_steps": 181800, "loss": 0.0295, "lr": 3.35216289626789e-05, "epoch": 9.007150715071507, "percentage": 45.04, "elapsed_time": "3:13:54", "remaining_time": "3:56:39", "throughput": 1485.14, "total_tokens": 17279040} {"current_steps": 81880, "total_steps": 181800, "loss": 0.0573, "lr": 3.351937259046654e-05, "epoch": 9.007700770077008, "percentage": 45.04, "elapsed_time": "3:13:55", "remaining_time": "3:56:38", "throughput": 1485.14, "total_tokens": 17280096} {"current_steps": 81885, "total_steps": 181800, "loss": 0.0061, "lr": 3.35171161397352e-05, "epoch": 9.008250825082508, "percentage": 45.04, "elapsed_time": "3:13:56", "remaining_time": "3:56:38", "throughput": 1485.15, "total_tokens": 17281184} {"current_steps": 81890, "total_steps": 181800, "loss": 0.0497, "lr": 3.35148596105057e-05, "epoch": 9.008800880088009, "percentage": 45.04, "elapsed_time": "3:13:56", "remaining_time": "3:56:37", "throughput": 1485.14, "total_tokens": 17282176} {"current_steps": 81895, "total_steps": 181800, "loss": 0.0111, "lr": 3.351260300279882e-05, "epoch": 9.00935093509351, "percentage": 45.05, "elapsed_time": "3:13:57", "remaining_time": "3:56:36", "throughput": 1485.15, "total_tokens": 17283232} {"current_steps": 81900, "total_steps": 181800, "loss": 0.0202, "lr": 3.351034631663536e-05, "epoch": 9.009900990099009, "percentage": 45.05, "elapsed_time": "3:13:58", "remaining_time": "3:56:35", "throughput": 1485.15, "total_tokens": 17284288} {"current_steps": 81905, "total_steps": 181800, "loss": 0.0109, "lr": 3.3508089552036114e-05, "epoch": 9.01045104510451, "percentage": 45.05, "elapsed_time": "3:13:58", "remaining_time": "3:56:35", "throughput": 1485.15, "total_tokens": 17285344} {"current_steps": 81910, "total_steps": 181800, "loss": 0.0663, "lr": 3.3505832709021906e-05, "epoch": 9.011001100110011, "percentage": 45.06, "elapsed_time": "3:13:59", "remaining_time": "3:56:34", "throughput": 1485.15, "total_tokens": 17286400} {"current_steps": 81915, "total_steps": 181800, "loss": 0.0523, "lr": 3.3503575787613505e-05, "epoch": 9.011551155115512, "percentage": 45.06, "elapsed_time": "3:14:00", "remaining_time": "3:56:33", "throughput": 1485.15, "total_tokens": 17287424} {"current_steps": 81920, "total_steps": 181800, "loss": 0.0604, "lr": 3.3501318787831734e-05, "epoch": 9.012101210121012, "percentage": 45.06, "elapsed_time": "3:14:00", "remaining_time": "3:56:33", "throughput": 1485.15, "total_tokens": 17288480} {"current_steps": 81925, "total_steps": 181800, "loss": 0.1174, "lr": 3.349906170969739e-05, "epoch": 9.012651265126513, "percentage": 45.06, "elapsed_time": "3:14:01", "remaining_time": "3:56:32", "throughput": 1485.15, "total_tokens": 17289536} {"current_steps": 81930, "total_steps": 181800, "loss": 0.0039, "lr": 3.349680455323127e-05, "epoch": 9.013201320132014, "percentage": 45.07, "elapsed_time": "3:14:02", "remaining_time": "3:56:31", "throughput": 1485.16, "total_tokens": 17290592} {"current_steps": 81935, "total_steps": 181800, "loss": 0.0718, "lr": 3.349454731845418e-05, "epoch": 9.013751375137513, "percentage": 45.07, "elapsed_time": "3:14:02", "remaining_time": "3:56:30", "throughput": 1485.16, "total_tokens": 17291680} {"current_steps": 81940, "total_steps": 181800, "loss": 0.0118, "lr": 3.3492290005386917e-05, "epoch": 9.014301430143014, "percentage": 45.07, "elapsed_time": "3:14:03", "remaining_time": "3:56:30", "throughput": 1485.16, "total_tokens": 17292704} {"current_steps": 81945, "total_steps": 181800, "loss": 0.0047, "lr": 3.3490032614050295e-05, "epoch": 9.014851485148515, "percentage": 45.07, "elapsed_time": "3:14:04", "remaining_time": "3:56:29", "throughput": 1485.16, "total_tokens": 17293760} {"current_steps": 81950, "total_steps": 181800, "loss": 0.1509, "lr": 3.3487775144465115e-05, "epoch": 9.015401540154015, "percentage": 45.08, "elapsed_time": "3:14:05", "remaining_time": "3:56:28", "throughput": 1485.16, "total_tokens": 17294752} {"current_steps": 81955, "total_steps": 181800, "loss": 0.0733, "lr": 3.348551759665219e-05, "epoch": 9.015951595159516, "percentage": 45.08, "elapsed_time": "3:14:05", "remaining_time": "3:56:27", "throughput": 1485.16, "total_tokens": 17295776} {"current_steps": 81960, "total_steps": 181800, "loss": 0.0528, "lr": 3.348325997063232e-05, "epoch": 9.016501650165017, "percentage": 45.08, "elapsed_time": "3:14:06", "remaining_time": "3:56:27", "throughput": 1485.16, "total_tokens": 17296832} {"current_steps": 81965, "total_steps": 181800, "loss": 0.0569, "lr": 3.348100226642631e-05, "epoch": 9.017051705170518, "percentage": 45.09, "elapsed_time": "3:14:07", "remaining_time": "3:56:26", "throughput": 1485.17, "total_tokens": 17297952} {"current_steps": 81970, "total_steps": 181800, "loss": 0.0063, "lr": 3.347874448405498e-05, "epoch": 9.017601760176017, "percentage": 45.09, "elapsed_time": "3:14:07", "remaining_time": "3:56:25", "throughput": 1485.18, "total_tokens": 17299040} {"current_steps": 81975, "total_steps": 181800, "loss": 0.0095, "lr": 3.3476486623539115e-05, "epoch": 9.018151815181518, "percentage": 45.09, "elapsed_time": "3:14:08", "remaining_time": "3:56:24", "throughput": 1485.18, "total_tokens": 17300160} {"current_steps": 81980, "total_steps": 181800, "loss": 0.0226, "lr": 3.3474228684899554e-05, "epoch": 9.01870187018702, "percentage": 45.09, "elapsed_time": "3:14:09", "remaining_time": "3:56:24", "throughput": 1485.19, "total_tokens": 17301216} {"current_steps": 81985, "total_steps": 181800, "loss": 0.0419, "lr": 3.347197066815709e-05, "epoch": 9.019251925192519, "percentage": 45.1, "elapsed_time": "3:14:09", "remaining_time": "3:56:23", "throughput": 1485.19, "total_tokens": 17302272} {"current_steps": 81990, "total_steps": 181800, "loss": 0.0726, "lr": 3.3469712573332535e-05, "epoch": 9.01980198019802, "percentage": 45.1, "elapsed_time": "3:14:10", "remaining_time": "3:56:22", "throughput": 1485.19, "total_tokens": 17303328} {"current_steps": 81995, "total_steps": 181800, "loss": 0.0191, "lr": 3.346745440044671e-05, "epoch": 9.020352035203521, "percentage": 45.1, "elapsed_time": "3:14:11", "remaining_time": "3:56:22", "throughput": 1485.19, "total_tokens": 17304416} {"current_steps": 82000, "total_steps": 181800, "loss": 0.005, "lr": 3.346519614952041e-05, "epoch": 9.02090209020902, "percentage": 45.1, "elapsed_time": "3:14:11", "remaining_time": "3:56:21", "throughput": 1485.19, "total_tokens": 17305440} {"current_steps": 82005, "total_steps": 181800, "loss": 0.0463, "lr": 3.3462937820574466e-05, "epoch": 9.021452145214521, "percentage": 45.11, "elapsed_time": "3:14:12", "remaining_time": "3:56:20", "throughput": 1485.2, "total_tokens": 17306528} {"current_steps": 82010, "total_steps": 181800, "loss": 0.0047, "lr": 3.346067941362969e-05, "epoch": 9.022002200220022, "percentage": 45.11, "elapsed_time": "3:14:13", "remaining_time": "3:56:19", "throughput": 1485.2, "total_tokens": 17307616} {"current_steps": 82015, "total_steps": 181800, "loss": 0.0191, "lr": 3.345842092870688e-05, "epoch": 9.022552255225522, "percentage": 45.11, "elapsed_time": "3:14:14", "remaining_time": "3:56:19", "throughput": 1485.2, "total_tokens": 17308640} {"current_steps": 82020, "total_steps": 181800, "loss": 0.007, "lr": 3.3456162365826865e-05, "epoch": 9.023102310231023, "percentage": 45.12, "elapsed_time": "3:14:14", "remaining_time": "3:56:18", "throughput": 1485.21, "total_tokens": 17309728} {"current_steps": 82025, "total_steps": 181800, "loss": 0.0949, "lr": 3.345390372501047e-05, "epoch": 9.023652365236524, "percentage": 45.12, "elapsed_time": "3:14:15", "remaining_time": "3:56:17", "throughput": 1485.21, "total_tokens": 17310752} {"current_steps": 82030, "total_steps": 181800, "loss": 0.0858, "lr": 3.345164500627849e-05, "epoch": 9.024202420242025, "percentage": 45.12, "elapsed_time": "3:14:16", "remaining_time": "3:56:16", "throughput": 1485.21, "total_tokens": 17311840} {"current_steps": 82035, "total_steps": 181800, "loss": 0.0098, "lr": 3.3449386209651754e-05, "epoch": 9.024752475247524, "percentage": 45.12, "elapsed_time": "3:14:16", "remaining_time": "3:56:16", "throughput": 1485.21, "total_tokens": 17312896} {"current_steps": 82040, "total_steps": 181800, "loss": 0.0064, "lr": 3.3447127335151084e-05, "epoch": 9.025302530253025, "percentage": 45.13, "elapsed_time": "3:14:17", "remaining_time": "3:56:15", "throughput": 1485.21, "total_tokens": 17313920} {"current_steps": 82045, "total_steps": 181800, "loss": 0.0462, "lr": 3.34448683827973e-05, "epoch": 9.025852585258527, "percentage": 45.13, "elapsed_time": "3:14:18", "remaining_time": "3:56:14", "throughput": 1485.22, "total_tokens": 17314976} {"current_steps": 82050, "total_steps": 181800, "loss": 0.0289, "lr": 3.3442609352611205e-05, "epoch": 9.026402640264026, "percentage": 45.13, "elapsed_time": "3:14:18", "remaining_time": "3:56:14", "throughput": 1485.22, "total_tokens": 17316064} {"current_steps": 82055, "total_steps": 181800, "loss": 0.0182, "lr": 3.344035024461364e-05, "epoch": 9.026952695269527, "percentage": 45.13, "elapsed_time": "3:14:19", "remaining_time": "3:56:13", "throughput": 1485.23, "total_tokens": 17317152} {"current_steps": 82060, "total_steps": 181800, "loss": 0.0103, "lr": 3.343809105882541e-05, "epoch": 9.027502750275028, "percentage": 45.14, "elapsed_time": "3:14:20", "remaining_time": "3:56:12", "throughput": 1485.23, "total_tokens": 17318208} {"current_steps": 82065, "total_steps": 181800, "loss": 0.0046, "lr": 3.343583179526734e-05, "epoch": 9.028052805280527, "percentage": 45.14, "elapsed_time": "3:14:20", "remaining_time": "3:56:11", "throughput": 1485.23, "total_tokens": 17319296} {"current_steps": 82070, "total_steps": 181800, "loss": 0.0524, "lr": 3.343357245396026e-05, "epoch": 9.028602860286028, "percentage": 45.14, "elapsed_time": "3:14:21", "remaining_time": "3:56:11", "throughput": 1485.23, "total_tokens": 17320320} {"current_steps": 82075, "total_steps": 181800, "loss": 0.0025, "lr": 3.343131303492499e-05, "epoch": 9.02915291529153, "percentage": 45.15, "elapsed_time": "3:14:22", "remaining_time": "3:56:10", "throughput": 1485.24, "total_tokens": 17321408} {"current_steps": 82080, "total_steps": 181800, "loss": 0.004, "lr": 3.3429053538182366e-05, "epoch": 9.029702970297029, "percentage": 45.15, "elapsed_time": "3:14:23", "remaining_time": "3:56:09", "throughput": 1485.24, "total_tokens": 17322432} {"current_steps": 82085, "total_steps": 181800, "loss": 0.0027, "lr": 3.342679396375319e-05, "epoch": 9.03025302530253, "percentage": 45.15, "elapsed_time": "3:14:23", "remaining_time": "3:56:08", "throughput": 1485.23, "total_tokens": 17323424} {"current_steps": 82090, "total_steps": 181800, "loss": 0.0052, "lr": 3.3424534311658297e-05, "epoch": 9.030803080308031, "percentage": 45.15, "elapsed_time": "3:14:24", "remaining_time": "3:56:08", "throughput": 1485.24, "total_tokens": 17324512} {"current_steps": 82095, "total_steps": 181800, "loss": 0.0801, "lr": 3.342227458191851e-05, "epoch": 9.031353135313532, "percentage": 45.16, "elapsed_time": "3:14:25", "remaining_time": "3:56:07", "throughput": 1485.25, "total_tokens": 17325600} {"current_steps": 82100, "total_steps": 181800, "loss": 0.0343, "lr": 3.342001477455466e-05, "epoch": 9.031903190319031, "percentage": 45.16, "elapsed_time": "3:14:25", "remaining_time": "3:56:06", "throughput": 1485.25, "total_tokens": 17326656} {"current_steps": 82105, "total_steps": 181800, "loss": 0.1319, "lr": 3.3417754889587576e-05, "epoch": 9.032453245324533, "percentage": 45.16, "elapsed_time": "3:14:26", "remaining_time": "3:56:05", "throughput": 1485.26, "total_tokens": 17327776} {"current_steps": 82110, "total_steps": 181800, "loss": 0.0037, "lr": 3.3415494927038085e-05, "epoch": 9.033003300330034, "percentage": 45.17, "elapsed_time": "3:14:27", "remaining_time": "3:56:05", "throughput": 1485.26, "total_tokens": 17328864} {"current_steps": 82115, "total_steps": 181800, "loss": 0.0488, "lr": 3.341323488692702e-05, "epoch": 9.033553355335533, "percentage": 45.17, "elapsed_time": "3:14:27", "remaining_time": "3:56:04", "throughput": 1485.26, "total_tokens": 17329920} {"current_steps": 82120, "total_steps": 181800, "loss": 0.0411, "lr": 3.3410974769275205e-05, "epoch": 9.034103410341034, "percentage": 45.17, "elapsed_time": "3:14:28", "remaining_time": "3:56:03", "throughput": 1485.26, "total_tokens": 17330912} {"current_steps": 82125, "total_steps": 181800, "loss": 0.0405, "lr": 3.340871457410347e-05, "epoch": 9.034653465346535, "percentage": 45.17, "elapsed_time": "3:14:29", "remaining_time": "3:56:03", "throughput": 1485.26, "total_tokens": 17331968} {"current_steps": 82130, "total_steps": 181800, "loss": 0.0682, "lr": 3.3406454301432646e-05, "epoch": 9.035203520352034, "percentage": 45.18, "elapsed_time": "3:14:29", "remaining_time": "3:56:02", "throughput": 1485.26, "total_tokens": 17332960} {"current_steps": 82135, "total_steps": 181800, "loss": 0.0186, "lr": 3.340419395128356e-05, "epoch": 9.035753575357536, "percentage": 45.18, "elapsed_time": "3:14:30", "remaining_time": "3:56:01", "throughput": 1485.26, "total_tokens": 17333984} {"current_steps": 82140, "total_steps": 181800, "loss": 0.0876, "lr": 3.340193352367706e-05, "epoch": 9.036303630363037, "percentage": 45.18, "elapsed_time": "3:14:31", "remaining_time": "3:56:00", "throughput": 1485.27, "total_tokens": 17335104} {"current_steps": 82145, "total_steps": 181800, "loss": 0.011, "lr": 3.339967301863398e-05, "epoch": 9.036853685368538, "percentage": 45.18, "elapsed_time": "3:14:32", "remaining_time": "3:56:00", "throughput": 1485.26, "total_tokens": 17336096} {"current_steps": 82150, "total_steps": 181800, "loss": 0.0597, "lr": 3.339741243617512e-05, "epoch": 9.037403740374037, "percentage": 45.19, "elapsed_time": "3:14:32", "remaining_time": "3:55:59", "throughput": 1485.27, "total_tokens": 17337152} {"current_steps": 82155, "total_steps": 181800, "loss": 0.0275, "lr": 3.339515177632136e-05, "epoch": 9.037953795379538, "percentage": 45.19, "elapsed_time": "3:14:33", "remaining_time": "3:55:58", "throughput": 1485.27, "total_tokens": 17338240} {"current_steps": 82160, "total_steps": 181800, "loss": 0.0079, "lr": 3.3392891039093503e-05, "epoch": 9.03850385038504, "percentage": 45.19, "elapsed_time": "3:14:34", "remaining_time": "3:55:57", "throughput": 1485.27, "total_tokens": 17339264} {"current_steps": 82165, "total_steps": 181800, "loss": 0.0146, "lr": 3.33906302245124e-05, "epoch": 9.039053905390539, "percentage": 45.2, "elapsed_time": "3:14:34", "remaining_time": "3:55:57", "throughput": 1485.28, "total_tokens": 17340320} {"current_steps": 82170, "total_steps": 181800, "loss": 0.0181, "lr": 3.338836933259889e-05, "epoch": 9.03960396039604, "percentage": 45.2, "elapsed_time": "3:14:35", "remaining_time": "3:55:56", "throughput": 1485.28, "total_tokens": 17341376} {"current_steps": 82175, "total_steps": 181800, "loss": 0.0609, "lr": 3.33861083633738e-05, "epoch": 9.04015401540154, "percentage": 45.2, "elapsed_time": "3:14:36", "remaining_time": "3:55:55", "throughput": 1485.29, "total_tokens": 17342496} {"current_steps": 82180, "total_steps": 181800, "loss": 0.0061, "lr": 3.338384731685796e-05, "epoch": 9.04070407040704, "percentage": 45.2, "elapsed_time": "3:14:36", "remaining_time": "3:55:54", "throughput": 1485.29, "total_tokens": 17343584} {"current_steps": 82185, "total_steps": 181800, "loss": 0.0111, "lr": 3.3381586193072244e-05, "epoch": 9.041254125412541, "percentage": 45.21, "elapsed_time": "3:14:37", "remaining_time": "3:55:54", "throughput": 1485.3, "total_tokens": 17344672} {"current_steps": 82190, "total_steps": 181800, "loss": 0.0027, "lr": 3.337932499203746e-05, "epoch": 9.041804180418042, "percentage": 45.21, "elapsed_time": "3:14:38", "remaining_time": "3:55:53", "throughput": 1485.31, "total_tokens": 17345792} {"current_steps": 82195, "total_steps": 181800, "loss": 0.0083, "lr": 3.337706371377446e-05, "epoch": 9.042354235423542, "percentage": 45.21, "elapsed_time": "3:14:38", "remaining_time": "3:55:52", "throughput": 1485.3, "total_tokens": 17346784} {"current_steps": 82200, "total_steps": 181800, "loss": 0.0125, "lr": 3.337480235830408e-05, "epoch": 9.042904290429043, "percentage": 45.21, "elapsed_time": "3:14:39", "remaining_time": "3:55:51", "throughput": 1485.3, "total_tokens": 17347808} {"current_steps": 82205, "total_steps": 181800, "loss": 0.0332, "lr": 3.3372540925647175e-05, "epoch": 9.043454345434544, "percentage": 45.22, "elapsed_time": "3:14:40", "remaining_time": "3:55:51", "throughput": 1485.31, "total_tokens": 17348896} {"current_steps": 82210, "total_steps": 181800, "loss": 0.0715, "lr": 3.3370279415824565e-05, "epoch": 9.044004400440045, "percentage": 45.22, "elapsed_time": "3:14:41", "remaining_time": "3:55:50", "throughput": 1485.31, "total_tokens": 17349952} {"current_steps": 82215, "total_steps": 181800, "loss": 0.0018, "lr": 3.336801782885712e-05, "epoch": 9.044554455445544, "percentage": 45.22, "elapsed_time": "3:14:41", "remaining_time": "3:55:49", "throughput": 1485.31, "total_tokens": 17351008} {"current_steps": 82220, "total_steps": 181800, "loss": 0.0459, "lr": 3.336575616476565e-05, "epoch": 9.045104510451045, "percentage": 45.23, "elapsed_time": "3:14:42", "remaining_time": "3:55:49", "throughput": 1485.31, "total_tokens": 17352032} {"current_steps": 82225, "total_steps": 181800, "loss": 0.0437, "lr": 3.336349442357103e-05, "epoch": 9.045654565456546, "percentage": 45.23, "elapsed_time": "3:14:43", "remaining_time": "3:55:48", "throughput": 1485.32, "total_tokens": 17353088} {"current_steps": 82230, "total_steps": 181800, "loss": 0.0197, "lr": 3.3361232605294104e-05, "epoch": 9.046204620462046, "percentage": 45.23, "elapsed_time": "3:14:44", "remaining_time": "3:55:47", "throughput": 1485.29, "total_tokens": 17354112} {"current_steps": 82235, "total_steps": 181800, "loss": 0.0554, "lr": 3.33589707099557e-05, "epoch": 9.046754675467547, "percentage": 45.23, "elapsed_time": "3:14:44", "remaining_time": "3:55:47", "throughput": 1485.29, "total_tokens": 17355232} {"current_steps": 82240, "total_steps": 181800, "loss": 0.032, "lr": 3.335670873757668e-05, "epoch": 9.047304730473048, "percentage": 45.24, "elapsed_time": "3:14:45", "remaining_time": "3:55:46", "throughput": 1485.3, "total_tokens": 17356320} {"current_steps": 82245, "total_steps": 181800, "loss": 0.0227, "lr": 3.335444668817788e-05, "epoch": 9.047854785478547, "percentage": 45.24, "elapsed_time": "3:14:46", "remaining_time": "3:55:45", "throughput": 1485.3, "total_tokens": 17357344} {"current_steps": 82250, "total_steps": 181800, "loss": 0.0797, "lr": 3.3352184561780154e-05, "epoch": 9.048404840484048, "percentage": 45.24, "elapsed_time": "3:14:46", "remaining_time": "3:55:44", "throughput": 1485.3, "total_tokens": 17358400} {"current_steps": 82255, "total_steps": 181800, "loss": 0.0836, "lr": 3.334992235840435e-05, "epoch": 9.04895489548955, "percentage": 45.24, "elapsed_time": "3:14:47", "remaining_time": "3:55:44", "throughput": 1485.3, "total_tokens": 17359456} {"current_steps": 82260, "total_steps": 181800, "loss": 0.0474, "lr": 3.334766007807132e-05, "epoch": 9.049504950495049, "percentage": 45.25, "elapsed_time": "3:14:48", "remaining_time": "3:55:43", "throughput": 1485.31, "total_tokens": 17360576} {"current_steps": 82265, "total_steps": 181800, "loss": 0.0099, "lr": 3.334539772080191e-05, "epoch": 9.05005500550055, "percentage": 45.25, "elapsed_time": "3:14:48", "remaining_time": "3:55:42", "throughput": 1485.31, "total_tokens": 17361632} {"current_steps": 82270, "total_steps": 181800, "loss": 0.0122, "lr": 3.334313528661698e-05, "epoch": 9.05060506050605, "percentage": 45.25, "elapsed_time": "3:14:49", "remaining_time": "3:55:41", "throughput": 1485.32, "total_tokens": 17362720} {"current_steps": 82275, "total_steps": 181800, "loss": 0.0304, "lr": 3.334087277553737e-05, "epoch": 9.051155115511552, "percentage": 45.26, "elapsed_time": "3:14:50", "remaining_time": "3:55:41", "throughput": 1485.32, "total_tokens": 17363744} {"current_steps": 82280, "total_steps": 181800, "loss": 0.1302, "lr": 3.3338610187583944e-05, "epoch": 9.051705170517051, "percentage": 45.26, "elapsed_time": "3:14:50", "remaining_time": "3:55:40", "throughput": 1485.32, "total_tokens": 17364800} {"current_steps": 82285, "total_steps": 181800, "loss": 0.0137, "lr": 3.3336347522777544e-05, "epoch": 9.052255225522552, "percentage": 45.26, "elapsed_time": "3:14:51", "remaining_time": "3:55:39", "throughput": 1485.32, "total_tokens": 17365856} {"current_steps": 82290, "total_steps": 181800, "loss": 0.0129, "lr": 3.3334084781139035e-05, "epoch": 9.052805280528053, "percentage": 45.26, "elapsed_time": "3:14:52", "remaining_time": "3:55:39", "throughput": 1485.32, "total_tokens": 17366848} {"current_steps": 82295, "total_steps": 181800, "loss": 0.0057, "lr": 3.333182196268926e-05, "epoch": 9.053355335533553, "percentage": 45.27, "elapsed_time": "3:14:53", "remaining_time": "3:55:38", "throughput": 1485.32, "total_tokens": 17367904} {"current_steps": 82300, "total_steps": 181800, "loss": 0.0285, "lr": 3.332955906744908e-05, "epoch": 9.053905390539054, "percentage": 45.27, "elapsed_time": "3:14:53", "remaining_time": "3:55:37", "throughput": 1485.33, "total_tokens": 17368992} {"current_steps": 82305, "total_steps": 181800, "loss": 0.0034, "lr": 3.332729609543935e-05, "epoch": 9.054455445544555, "percentage": 45.27, "elapsed_time": "3:14:54", "remaining_time": "3:55:36", "throughput": 1485.33, "total_tokens": 17370080} {"current_steps": 82310, "total_steps": 181800, "loss": 0.0747, "lr": 3.332503304668093e-05, "epoch": 9.055005500550054, "percentage": 45.28, "elapsed_time": "3:14:55", "remaining_time": "3:55:36", "throughput": 1485.33, "total_tokens": 17371104} {"current_steps": 82315, "total_steps": 181800, "loss": 0.0056, "lr": 3.3322769921194674e-05, "epoch": 9.055555555555555, "percentage": 45.28, "elapsed_time": "3:14:55", "remaining_time": "3:55:35", "throughput": 1485.34, "total_tokens": 17372192} {"current_steps": 82320, "total_steps": 181800, "loss": 0.0063, "lr": 3.332050671900144e-05, "epoch": 9.056105610561056, "percentage": 45.28, "elapsed_time": "3:14:56", "remaining_time": "3:55:34", "throughput": 1485.34, "total_tokens": 17373248} {"current_steps": 82325, "total_steps": 181800, "loss": 0.0103, "lr": 3.331824344012209e-05, "epoch": 9.056655665566556, "percentage": 45.28, "elapsed_time": "3:14:57", "remaining_time": "3:55:33", "throughput": 1485.35, "total_tokens": 17374336} {"current_steps": 82330, "total_steps": 181800, "loss": 0.0681, "lr": 3.331598008457748e-05, "epoch": 9.057205720572057, "percentage": 45.29, "elapsed_time": "3:14:57", "remaining_time": "3:55:33", "throughput": 1485.35, "total_tokens": 17375360} {"current_steps": 82335, "total_steps": 181800, "loss": 0.0329, "lr": 3.3313716652388486e-05, "epoch": 9.057755775577558, "percentage": 45.29, "elapsed_time": "3:14:58", "remaining_time": "3:55:32", "throughput": 1485.35, "total_tokens": 17376416} {"current_steps": 82340, "total_steps": 181800, "loss": 0.0138, "lr": 3.331145314357593e-05, "epoch": 9.058305830583059, "percentage": 45.29, "elapsed_time": "3:14:59", "remaining_time": "3:55:31", "throughput": 1485.35, "total_tokens": 17377440} {"current_steps": 82345, "total_steps": 181800, "loss": 0.0157, "lr": 3.3309189558160715e-05, "epoch": 9.058855885588558, "percentage": 45.29, "elapsed_time": "3:14:59", "remaining_time": "3:55:30", "throughput": 1485.35, "total_tokens": 17378432} {"current_steps": 82350, "total_steps": 181800, "loss": 0.0533, "lr": 3.3306925896163683e-05, "epoch": 9.05940594059406, "percentage": 45.3, "elapsed_time": "3:15:00", "remaining_time": "3:55:30", "throughput": 1485.35, "total_tokens": 17379488} {"current_steps": 82355, "total_steps": 181800, "loss": 0.0071, "lr": 3.3304662157605695e-05, "epoch": 9.05995599559956, "percentage": 45.3, "elapsed_time": "3:15:01", "remaining_time": "3:55:29", "throughput": 1485.35, "total_tokens": 17380576} {"current_steps": 82360, "total_steps": 181800, "loss": 0.0666, "lr": 3.3302398342507634e-05, "epoch": 9.06050605060506, "percentage": 45.3, "elapsed_time": "3:15:01", "remaining_time": "3:55:28", "throughput": 1485.36, "total_tokens": 17381664} {"current_steps": 82365, "total_steps": 181800, "loss": 0.0872, "lr": 3.3300134450890345e-05, "epoch": 9.061056105610561, "percentage": 45.31, "elapsed_time": "3:15:02", "remaining_time": "3:55:28", "throughput": 1485.37, "total_tokens": 17382784} {"current_steps": 82370, "total_steps": 181800, "loss": 0.0041, "lr": 3.32978704827747e-05, "epoch": 9.061606160616062, "percentage": 45.31, "elapsed_time": "3:15:03", "remaining_time": "3:55:27", "throughput": 1485.36, "total_tokens": 17383776} {"current_steps": 82375, "total_steps": 181800, "loss": 0.0339, "lr": 3.329560643818156e-05, "epoch": 9.062156215621561, "percentage": 45.31, "elapsed_time": "3:15:04", "remaining_time": "3:55:26", "throughput": 1485.37, "total_tokens": 17384832} {"current_steps": 82380, "total_steps": 181800, "loss": 0.0232, "lr": 3.32933423171318e-05, "epoch": 9.062706270627062, "percentage": 45.31, "elapsed_time": "3:15:04", "remaining_time": "3:55:25", "throughput": 1485.37, "total_tokens": 17385920} {"current_steps": 82385, "total_steps": 181800, "loss": 0.015, "lr": 3.329107811964629e-05, "epoch": 9.063256325632564, "percentage": 45.32, "elapsed_time": "3:15:05", "remaining_time": "3:55:25", "throughput": 1485.37, "total_tokens": 17386976} {"current_steps": 82390, "total_steps": 181800, "loss": 0.0131, "lr": 3.328881384574588e-05, "epoch": 9.063806380638065, "percentage": 45.32, "elapsed_time": "3:15:06", "remaining_time": "3:55:24", "throughput": 1485.38, "total_tokens": 17388064} {"current_steps": 82395, "total_steps": 181800, "loss": 0.0397, "lr": 3.328654949545146e-05, "epoch": 9.064356435643564, "percentage": 45.32, "elapsed_time": "3:15:06", "remaining_time": "3:55:23", "throughput": 1485.38, "total_tokens": 17389056} {"current_steps": 82400, "total_steps": 181800, "loss": 0.0082, "lr": 3.3284285068783874e-05, "epoch": 9.064906490649065, "percentage": 45.32, "elapsed_time": "3:15:07", "remaining_time": "3:55:22", "throughput": 1485.38, "total_tokens": 17390112} {"current_steps": 82405, "total_steps": 181800, "loss": 0.0498, "lr": 3.328202056576403e-05, "epoch": 9.065456545654566, "percentage": 45.33, "elapsed_time": "3:15:08", "remaining_time": "3:55:22", "throughput": 1485.38, "total_tokens": 17391168} {"current_steps": 82410, "total_steps": 181800, "loss": 0.0016, "lr": 3.327975598641275e-05, "epoch": 9.066006600660065, "percentage": 45.33, "elapsed_time": "3:15:08", "remaining_time": "3:55:21", "throughput": 1485.38, "total_tokens": 17392256} {"current_steps": 82415, "total_steps": 181800, "loss": 0.0635, "lr": 3.327749133075095e-05, "epoch": 9.066556655665567, "percentage": 45.33, "elapsed_time": "3:15:09", "remaining_time": "3:55:20", "throughput": 1485.38, "total_tokens": 17393312} {"current_steps": 82420, "total_steps": 181800, "loss": 0.0021, "lr": 3.327522659879948e-05, "epoch": 9.067106710671068, "percentage": 45.34, "elapsed_time": "3:15:10", "remaining_time": "3:55:20", "throughput": 1485.39, "total_tokens": 17394400} {"current_steps": 82425, "total_steps": 181800, "loss": 0.056, "lr": 3.327296179057922e-05, "epoch": 9.067656765676567, "percentage": 45.34, "elapsed_time": "3:15:11", "remaining_time": "3:55:19", "throughput": 1485.39, "total_tokens": 17395488} {"current_steps": 82430, "total_steps": 181800, "loss": 0.0094, "lr": 3.3270696906111045e-05, "epoch": 9.068206820682068, "percentage": 45.34, "elapsed_time": "3:15:11", "remaining_time": "3:55:18", "throughput": 1485.4, "total_tokens": 17396544} {"current_steps": 82435, "total_steps": 181800, "loss": 0.0715, "lr": 3.326843194541582e-05, "epoch": 9.06875687568757, "percentage": 45.34, "elapsed_time": "3:15:12", "remaining_time": "3:55:17", "throughput": 1485.4, "total_tokens": 17397664} {"current_steps": 82440, "total_steps": 181800, "loss": 0.01, "lr": 3.326616690851442e-05, "epoch": 9.069306930693068, "percentage": 45.35, "elapsed_time": "3:15:13", "remaining_time": "3:55:17", "throughput": 1485.41, "total_tokens": 17398752} {"current_steps": 82445, "total_steps": 181800, "loss": 0.0917, "lr": 3.3263901795427724e-05, "epoch": 9.06985698569857, "percentage": 45.35, "elapsed_time": "3:15:13", "remaining_time": "3:55:16", "throughput": 1485.41, "total_tokens": 17399808} {"current_steps": 82450, "total_steps": 181800, "loss": 0.0822, "lr": 3.326163660617662e-05, "epoch": 9.07040704070407, "percentage": 45.35, "elapsed_time": "3:15:14", "remaining_time": "3:55:15", "throughput": 1485.41, "total_tokens": 17400832} {"current_steps": 82455, "total_steps": 181800, "loss": 0.0074, "lr": 3.325937134078198e-05, "epoch": 9.070957095709572, "percentage": 45.35, "elapsed_time": "3:15:15", "remaining_time": "3:55:14", "throughput": 1485.41, "total_tokens": 17401888} {"current_steps": 82460, "total_steps": 181800, "loss": 0.0577, "lr": 3.325710599926467e-05, "epoch": 9.071507150715071, "percentage": 45.36, "elapsed_time": "3:15:15", "remaining_time": "3:55:14", "throughput": 1485.41, "total_tokens": 17402944} {"current_steps": 82465, "total_steps": 181800, "loss": 0.0239, "lr": 3.325484058164557e-05, "epoch": 9.072057205720572, "percentage": 45.36, "elapsed_time": "3:15:16", "remaining_time": "3:55:13", "throughput": 1485.42, "total_tokens": 17404032} {"current_steps": 82470, "total_steps": 181800, "loss": 0.0237, "lr": 3.325257508794557e-05, "epoch": 9.072607260726073, "percentage": 45.36, "elapsed_time": "3:15:17", "remaining_time": "3:55:12", "throughput": 1485.42, "total_tokens": 17405088} {"current_steps": 82475, "total_steps": 181800, "loss": 0.0077, "lr": 3.325030951818555e-05, "epoch": 9.073157315731573, "percentage": 45.37, "elapsed_time": "3:15:17", "remaining_time": "3:55:12", "throughput": 1485.42, "total_tokens": 17406080} {"current_steps": 82480, "total_steps": 181800, "loss": 0.0025, "lr": 3.3248043872386393e-05, "epoch": 9.073707370737074, "percentage": 45.37, "elapsed_time": "3:15:18", "remaining_time": "3:55:11", "throughput": 1485.42, "total_tokens": 17407168} {"current_steps": 82485, "total_steps": 181800, "loss": 0.0051, "lr": 3.3245778150568955e-05, "epoch": 9.074257425742575, "percentage": 45.37, "elapsed_time": "3:15:19", "remaining_time": "3:55:10", "throughput": 1485.42, "total_tokens": 17408256} {"current_steps": 82490, "total_steps": 181800, "loss": 0.0039, "lr": 3.324351235275415e-05, "epoch": 9.074807480748074, "percentage": 45.37, "elapsed_time": "3:15:20", "remaining_time": "3:55:09", "throughput": 1485.43, "total_tokens": 17409376} {"current_steps": 82495, "total_steps": 181800, "loss": 0.0857, "lr": 3.324124647896284e-05, "epoch": 9.075357535753575, "percentage": 45.38, "elapsed_time": "3:15:20", "remaining_time": "3:55:09", "throughput": 1485.43, "total_tokens": 17410432} {"current_steps": 82500, "total_steps": 181800, "loss": 0.0624, "lr": 3.3238980529215916e-05, "epoch": 9.075907590759076, "percentage": 45.38, "elapsed_time": "3:15:21", "remaining_time": "3:55:08", "throughput": 1485.44, "total_tokens": 17411520} {"current_steps": 82505, "total_steps": 181800, "loss": 0.0071, "lr": 3.323671450353427e-05, "epoch": 9.076457645764576, "percentage": 45.38, "elapsed_time": "3:15:22", "remaining_time": "3:55:07", "throughput": 1485.44, "total_tokens": 17412544} {"current_steps": 82510, "total_steps": 181800, "loss": 0.2027, "lr": 3.323444840193877e-05, "epoch": 9.077007700770077, "percentage": 45.39, "elapsed_time": "3:15:22", "remaining_time": "3:55:06", "throughput": 1485.44, "total_tokens": 17413600} {"current_steps": 82515, "total_steps": 181800, "loss": 0.0219, "lr": 3.3232182224450315e-05, "epoch": 9.077557755775578, "percentage": 45.39, "elapsed_time": "3:15:23", "remaining_time": "3:55:06", "throughput": 1485.44, "total_tokens": 17414656} {"current_steps": 82520, "total_steps": 181800, "loss": 0.1287, "lr": 3.322991597108978e-05, "epoch": 9.078107810781079, "percentage": 45.39, "elapsed_time": "3:15:24", "remaining_time": "3:55:05", "throughput": 1485.44, "total_tokens": 17415648} {"current_steps": 82525, "total_steps": 181800, "loss": 0.0513, "lr": 3.3227649641878065e-05, "epoch": 9.078657865786578, "percentage": 45.39, "elapsed_time": "3:15:24", "remaining_time": "3:55:04", "throughput": 1485.44, "total_tokens": 17416736} {"current_steps": 82530, "total_steps": 181800, "loss": 0.0404, "lr": 3.322538323683605e-05, "epoch": 9.07920792079208, "percentage": 45.4, "elapsed_time": "3:15:25", "remaining_time": "3:55:04", "throughput": 1485.44, "total_tokens": 17417760} {"current_steps": 82535, "total_steps": 181800, "loss": 0.1705, "lr": 3.322311675598463e-05, "epoch": 9.07975797579758, "percentage": 45.4, "elapsed_time": "3:15:26", "remaining_time": "3:55:03", "throughput": 1485.44, "total_tokens": 17418848} {"current_steps": 82540, "total_steps": 181800, "loss": 0.003, "lr": 3.322085019934468e-05, "epoch": 9.08030803080308, "percentage": 45.4, "elapsed_time": "3:15:27", "remaining_time": "3:55:02", "throughput": 1485.44, "total_tokens": 17419936} {"current_steps": 82545, "total_steps": 181800, "loss": 0.0421, "lr": 3.32185835669371e-05, "epoch": 9.08085808580858, "percentage": 45.4, "elapsed_time": "3:15:27", "remaining_time": "3:55:01", "throughput": 1485.44, "total_tokens": 17420992} {"current_steps": 82550, "total_steps": 181800, "loss": 0.0074, "lr": 3.3216316858782785e-05, "epoch": 9.081408140814082, "percentage": 45.41, "elapsed_time": "3:15:28", "remaining_time": "3:55:01", "throughput": 1485.44, "total_tokens": 17422048} {"current_steps": 82555, "total_steps": 181800, "loss": 0.0202, "lr": 3.3214050074902616e-05, "epoch": 9.081958195819581, "percentage": 45.41, "elapsed_time": "3:15:29", "remaining_time": "3:55:00", "throughput": 1485.45, "total_tokens": 17423136} {"current_steps": 82560, "total_steps": 181800, "loss": 0.1641, "lr": 3.321178321531749e-05, "epoch": 9.082508250825082, "percentage": 45.41, "elapsed_time": "3:15:29", "remaining_time": "3:54:59", "throughput": 1485.45, "total_tokens": 17424192} {"current_steps": 82565, "total_steps": 181800, "loss": 0.0369, "lr": 3.3209516280048294e-05, "epoch": 9.083058305830583, "percentage": 45.42, "elapsed_time": "3:15:30", "remaining_time": "3:54:59", "throughput": 1485.44, "total_tokens": 17425184} {"current_steps": 82570, "total_steps": 181800, "loss": 0.002, "lr": 3.320724926911593e-05, "epoch": 9.083608360836084, "percentage": 45.42, "elapsed_time": "3:15:31", "remaining_time": "3:54:58", "throughput": 1485.45, "total_tokens": 17426272} {"current_steps": 82575, "total_steps": 181800, "loss": 0.063, "lr": 3.320498218254129e-05, "epoch": 9.084158415841584, "percentage": 45.42, "elapsed_time": "3:15:32", "remaining_time": "3:54:57", "throughput": 1485.45, "total_tokens": 17427360} {"current_steps": 82580, "total_steps": 181800, "loss": 0.0308, "lr": 3.320271502034526e-05, "epoch": 9.084708470847085, "percentage": 45.42, "elapsed_time": "3:15:32", "remaining_time": "3:54:56", "throughput": 1485.45, "total_tokens": 17428384} {"current_steps": 82585, "total_steps": 181800, "loss": 0.0093, "lr": 3.320044778254874e-05, "epoch": 9.085258525852586, "percentage": 45.43, "elapsed_time": "3:15:33", "remaining_time": "3:54:56", "throughput": 1485.45, "total_tokens": 17429472} {"current_steps": 82590, "total_steps": 181800, "loss": 0.0607, "lr": 3.3198180469172636e-05, "epoch": 9.085808580858085, "percentage": 45.43, "elapsed_time": "3:15:34", "remaining_time": "3:54:55", "throughput": 1485.46, "total_tokens": 17430560} {"current_steps": 82595, "total_steps": 181800, "loss": 0.0108, "lr": 3.319591308023783e-05, "epoch": 9.086358635863586, "percentage": 45.43, "elapsed_time": "3:15:34", "remaining_time": "3:54:54", "throughput": 1485.46, "total_tokens": 17431648} {"current_steps": 82600, "total_steps": 181800, "loss": 0.0782, "lr": 3.3193645615765234e-05, "epoch": 9.086908690869087, "percentage": 45.43, "elapsed_time": "3:15:35", "remaining_time": "3:54:54", "throughput": 1485.47, "total_tokens": 17432736} {"current_steps": 82605, "total_steps": 181800, "loss": 0.0121, "lr": 3.319137807577573e-05, "epoch": 9.087458745874587, "percentage": 45.44, "elapsed_time": "3:15:36", "remaining_time": "3:54:53", "throughput": 1485.46, "total_tokens": 17433760} {"current_steps": 82610, "total_steps": 181800, "loss": 0.0105, "lr": 3.318911046029023e-05, "epoch": 9.088008800880088, "percentage": 45.44, "elapsed_time": "3:15:36", "remaining_time": "3:54:52", "throughput": 1485.46, "total_tokens": 17434752} {"current_steps": 82615, "total_steps": 181800, "loss": 0.0035, "lr": 3.318684276932962e-05, "epoch": 9.088558855885589, "percentage": 45.44, "elapsed_time": "3:15:37", "remaining_time": "3:54:51", "throughput": 1485.46, "total_tokens": 17435776} {"current_steps": 82620, "total_steps": 181800, "loss": 0.0282, "lr": 3.318457500291482e-05, "epoch": 9.089108910891088, "percentage": 45.45, "elapsed_time": "3:15:38", "remaining_time": "3:54:51", "throughput": 1485.46, "total_tokens": 17436864} {"current_steps": 82625, "total_steps": 181800, "loss": 0.0052, "lr": 3.318230716106672e-05, "epoch": 9.08965896589659, "percentage": 45.45, "elapsed_time": "3:15:39", "remaining_time": "3:54:50", "throughput": 1485.47, "total_tokens": 17438016} {"current_steps": 82630, "total_steps": 181800, "loss": 0.1, "lr": 3.318003924380621e-05, "epoch": 9.09020902090209, "percentage": 45.45, "elapsed_time": "3:15:39", "remaining_time": "3:54:49", "throughput": 1485.46, "total_tokens": 17438976} {"current_steps": 82635, "total_steps": 181800, "loss": 0.0179, "lr": 3.3177771251154214e-05, "epoch": 9.090759075907592, "percentage": 45.45, "elapsed_time": "3:15:40", "remaining_time": "3:54:48", "throughput": 1485.46, "total_tokens": 17439968} {"current_steps": 82640, "total_steps": 181800, "loss": 0.1411, "lr": 3.3175503183131616e-05, "epoch": 9.091309130913091, "percentage": 45.46, "elapsed_time": "3:15:41", "remaining_time": "3:54:48", "throughput": 1485.45, "total_tokens": 17440960} {"current_steps": 82645, "total_steps": 181800, "loss": 0.054, "lr": 3.317323503975933e-05, "epoch": 9.091859185918592, "percentage": 45.46, "elapsed_time": "3:15:41", "remaining_time": "3:54:47", "throughput": 1485.46, "total_tokens": 17442080} {"current_steps": 82650, "total_steps": 181800, "loss": 0.0072, "lr": 3.317096682105827e-05, "epoch": 9.092409240924093, "percentage": 45.46, "elapsed_time": "3:15:42", "remaining_time": "3:54:46", "throughput": 1485.46, "total_tokens": 17443136} {"current_steps": 82655, "total_steps": 181800, "loss": 0.076, "lr": 3.316869852704931e-05, "epoch": 9.092959295929592, "percentage": 45.46, "elapsed_time": "3:15:43", "remaining_time": "3:54:46", "throughput": 1485.46, "total_tokens": 17444128} {"current_steps": 82660, "total_steps": 181800, "loss": 0.0044, "lr": 3.316643015775338e-05, "epoch": 9.093509350935093, "percentage": 45.47, "elapsed_time": "3:15:43", "remaining_time": "3:54:45", "throughput": 1485.46, "total_tokens": 17445184} {"current_steps": 82665, "total_steps": 181800, "loss": 0.0963, "lr": 3.316416171319139e-05, "epoch": 9.094059405940595, "percentage": 45.47, "elapsed_time": "3:15:44", "remaining_time": "3:54:44", "throughput": 1485.47, "total_tokens": 17446304} {"current_steps": 82670, "total_steps": 181800, "loss": 0.0156, "lr": 3.316189319338424e-05, "epoch": 9.094609460946094, "percentage": 45.47, "elapsed_time": "3:15:45", "remaining_time": "3:54:43", "throughput": 1485.47, "total_tokens": 17447296} {"current_steps": 82675, "total_steps": 181800, "loss": 0.0221, "lr": 3.3159624598352835e-05, "epoch": 9.095159515951595, "percentage": 45.48, "elapsed_time": "3:15:46", "remaining_time": "3:54:43", "throughput": 1485.47, "total_tokens": 17448352} {"current_steps": 82680, "total_steps": 181800, "loss": 0.0057, "lr": 3.315735592811808e-05, "epoch": 9.095709570957096, "percentage": 45.48, "elapsed_time": "3:15:46", "remaining_time": "3:54:42", "throughput": 1485.47, "total_tokens": 17449408} {"current_steps": 82685, "total_steps": 181800, "loss": 0.0093, "lr": 3.3155087182700895e-05, "epoch": 9.096259625962595, "percentage": 45.48, "elapsed_time": "3:15:47", "remaining_time": "3:54:41", "throughput": 1485.47, "total_tokens": 17450496} {"current_steps": 82690, "total_steps": 181800, "loss": 0.0558, "lr": 3.315281836212218e-05, "epoch": 9.096809680968097, "percentage": 45.48, "elapsed_time": "3:15:48", "remaining_time": "3:54:40", "throughput": 1485.47, "total_tokens": 17451488} {"current_steps": 82695, "total_steps": 181800, "loss": 0.0062, "lr": 3.315054946640286e-05, "epoch": 9.097359735973598, "percentage": 45.49, "elapsed_time": "3:15:48", "remaining_time": "3:54:40", "throughput": 1485.47, "total_tokens": 17452448} {"current_steps": 82700, "total_steps": 181800, "loss": 0.0231, "lr": 3.314828049556382e-05, "epoch": 9.097909790979099, "percentage": 45.49, "elapsed_time": "3:15:49", "remaining_time": "3:54:39", "throughput": 1485.47, "total_tokens": 17453472} {"current_steps": 82705, "total_steps": 181800, "loss": 0.0267, "lr": 3.3146011449626e-05, "epoch": 9.098459845984598, "percentage": 45.49, "elapsed_time": "3:15:50", "remaining_time": "3:54:38", "throughput": 1485.46, "total_tokens": 17454464} {"current_steps": 82710, "total_steps": 181800, "loss": 0.015, "lr": 3.31437423286103e-05, "epoch": 9.099009900990099, "percentage": 45.5, "elapsed_time": "3:15:50", "remaining_time": "3:54:38", "throughput": 1485.47, "total_tokens": 17455552} {"current_steps": 82715, "total_steps": 181800, "loss": 0.0085, "lr": 3.314147313253764e-05, "epoch": 9.0995599559956, "percentage": 45.5, "elapsed_time": "3:15:51", "remaining_time": "3:54:37", "throughput": 1485.47, "total_tokens": 17456576} {"current_steps": 82720, "total_steps": 181800, "loss": 0.0831, "lr": 3.313920386142892e-05, "epoch": 9.1001100110011, "percentage": 45.5, "elapsed_time": "3:15:52", "remaining_time": "3:54:36", "throughput": 1485.47, "total_tokens": 17457632} {"current_steps": 82725, "total_steps": 181800, "loss": 0.0476, "lr": 3.313693451530507e-05, "epoch": 9.1006600660066, "percentage": 45.5, "elapsed_time": "3:15:52", "remaining_time": "3:54:35", "throughput": 1485.47, "total_tokens": 17458624} {"current_steps": 82730, "total_steps": 181800, "loss": 0.0689, "lr": 3.313466509418699e-05, "epoch": 9.101210121012102, "percentage": 45.51, "elapsed_time": "3:15:53", "remaining_time": "3:54:35", "throughput": 1485.47, "total_tokens": 17459712} {"current_steps": 82735, "total_steps": 181800, "loss": 0.0121, "lr": 3.313239559809561e-05, "epoch": 9.101760176017601, "percentage": 45.51, "elapsed_time": "3:15:54", "remaining_time": "3:54:34", "throughput": 1485.48, "total_tokens": 17460768} {"current_steps": 82740, "total_steps": 181800, "loss": 0.0085, "lr": 3.313012602705185e-05, "epoch": 9.102310231023102, "percentage": 45.51, "elapsed_time": "3:15:55", "remaining_time": "3:54:33", "throughput": 1485.48, "total_tokens": 17461792} {"current_steps": 82745, "total_steps": 181800, "loss": 0.0318, "lr": 3.3127856381076604e-05, "epoch": 9.102860286028603, "percentage": 45.51, "elapsed_time": "3:15:55", "remaining_time": "3:54:32", "throughput": 1485.48, "total_tokens": 17462848} {"current_steps": 82750, "total_steps": 181800, "loss": 0.0175, "lr": 3.312558666019082e-05, "epoch": 9.103410341034103, "percentage": 45.52, "elapsed_time": "3:15:56", "remaining_time": "3:54:32", "throughput": 1485.48, "total_tokens": 17463872} {"current_steps": 82755, "total_steps": 181800, "loss": 0.0232, "lr": 3.31233168644154e-05, "epoch": 9.103960396039604, "percentage": 45.52, "elapsed_time": "3:15:57", "remaining_time": "3:54:31", "throughput": 1485.49, "total_tokens": 17464992} {"current_steps": 82760, "total_steps": 181800, "loss": 0.0108, "lr": 3.312104699377126e-05, "epoch": 9.104510451045105, "percentage": 45.52, "elapsed_time": "3:15:57", "remaining_time": "3:54:30", "throughput": 1485.49, "total_tokens": 17466016} {"current_steps": 82765, "total_steps": 181800, "loss": 0.1262, "lr": 3.311877704827933e-05, "epoch": 9.105060506050606, "percentage": 45.53, "elapsed_time": "3:15:58", "remaining_time": "3:54:29", "throughput": 1485.49, "total_tokens": 17467104} {"current_steps": 82770, "total_steps": 181800, "loss": 0.0043, "lr": 3.311650702796053e-05, "epoch": 9.105610561056105, "percentage": 45.53, "elapsed_time": "3:15:59", "remaining_time": "3:54:29", "throughput": 1485.5, "total_tokens": 17468192} {"current_steps": 82775, "total_steps": 181800, "loss": 0.0086, "lr": 3.311423693283577e-05, "epoch": 9.106160616061606, "percentage": 45.53, "elapsed_time": "3:15:59", "remaining_time": "3:54:28", "throughput": 1485.49, "total_tokens": 17469184} {"current_steps": 82780, "total_steps": 181800, "loss": 0.0822, "lr": 3.3111966762925995e-05, "epoch": 9.106710671067107, "percentage": 45.53, "elapsed_time": "3:16:00", "remaining_time": "3:54:27", "throughput": 1485.5, "total_tokens": 17470272} {"current_steps": 82785, "total_steps": 181800, "loss": 0.0204, "lr": 3.310969651825211e-05, "epoch": 9.107260726072607, "percentage": 45.54, "elapsed_time": "3:16:01", "remaining_time": "3:54:27", "throughput": 1485.51, "total_tokens": 17471392} {"current_steps": 82790, "total_steps": 181800, "loss": 0.0258, "lr": 3.310742619883504e-05, "epoch": 9.107810781078108, "percentage": 45.54, "elapsed_time": "3:16:01", "remaining_time": "3:54:26", "throughput": 1485.51, "total_tokens": 17472448} {"current_steps": 82795, "total_steps": 181800, "loss": 0.0237, "lr": 3.310515580469572e-05, "epoch": 9.108360836083609, "percentage": 45.54, "elapsed_time": "3:16:02", "remaining_time": "3:54:25", "throughput": 1485.51, "total_tokens": 17473440} {"current_steps": 82800, "total_steps": 181800, "loss": 0.0103, "lr": 3.310288533585506e-05, "epoch": 9.108910891089108, "percentage": 45.54, "elapsed_time": "3:16:03", "remaining_time": "3:54:24", "throughput": 1485.51, "total_tokens": 17474528} {"current_steps": 82805, "total_steps": 181800, "loss": 0.0114, "lr": 3.3100614792334e-05, "epoch": 9.10946094609461, "percentage": 45.55, "elapsed_time": "3:16:03", "remaining_time": "3:54:24", "throughput": 1485.52, "total_tokens": 17475616} {"current_steps": 82810, "total_steps": 181800, "loss": 0.0798, "lr": 3.309834417415346e-05, "epoch": 9.11001100110011, "percentage": 45.55, "elapsed_time": "3:16:04", "remaining_time": "3:54:23", "throughput": 1485.52, "total_tokens": 17476704} {"current_steps": 82815, "total_steps": 181800, "loss": 0.019, "lr": 3.309607348133437e-05, "epoch": 9.110561056105611, "percentage": 45.55, "elapsed_time": "3:16:05", "remaining_time": "3:54:22", "throughput": 1485.53, "total_tokens": 17477760} {"current_steps": 82820, "total_steps": 181800, "loss": 0.0021, "lr": 3.309380271389764e-05, "epoch": 9.11111111111111, "percentage": 45.56, "elapsed_time": "3:16:06", "remaining_time": "3:54:21", "throughput": 1485.52, "total_tokens": 17478752} {"current_steps": 82825, "total_steps": 181800, "loss": 0.0409, "lr": 3.309153187186423e-05, "epoch": 9.111661166116612, "percentage": 45.56, "elapsed_time": "3:16:06", "remaining_time": "3:54:21", "throughput": 1485.52, "total_tokens": 17479776} {"current_steps": 82830, "total_steps": 181800, "loss": 0.0028, "lr": 3.308926095525505e-05, "epoch": 9.112211221122113, "percentage": 45.56, "elapsed_time": "3:16:07", "remaining_time": "3:54:20", "throughput": 1485.53, "total_tokens": 17480832} {"current_steps": 82835, "total_steps": 181800, "loss": 0.0376, "lr": 3.308698996409103e-05, "epoch": 9.112761276127612, "percentage": 45.56, "elapsed_time": "3:16:08", "remaining_time": "3:54:19", "throughput": 1485.54, "total_tokens": 17481952} {"current_steps": 82840, "total_steps": 181800, "loss": 0.1533, "lr": 3.3084718898393116e-05, "epoch": 9.113311331133113, "percentage": 45.57, "elapsed_time": "3:16:08", "remaining_time": "3:54:18", "throughput": 1485.54, "total_tokens": 17482976} {"current_steps": 82845, "total_steps": 181800, "loss": 0.0819, "lr": 3.308244775818221e-05, "epoch": 9.113861386138614, "percentage": 45.57, "elapsed_time": "3:16:09", "remaining_time": "3:54:18", "throughput": 1485.54, "total_tokens": 17484032} {"current_steps": 82850, "total_steps": 181800, "loss": 0.0416, "lr": 3.3080176543479266e-05, "epoch": 9.114411441144114, "percentage": 45.57, "elapsed_time": "3:16:10", "remaining_time": "3:54:17", "throughput": 1485.54, "total_tokens": 17485056} {"current_steps": 82855, "total_steps": 181800, "loss": 0.019, "lr": 3.307790525430522e-05, "epoch": 9.114961496149615, "percentage": 45.57, "elapsed_time": "3:16:10", "remaining_time": "3:54:16", "throughput": 1485.54, "total_tokens": 17486048} {"current_steps": 82860, "total_steps": 181800, "loss": 0.0057, "lr": 3.307563389068099e-05, "epoch": 9.115511551155116, "percentage": 45.58, "elapsed_time": "3:16:11", "remaining_time": "3:54:15", "throughput": 1485.54, "total_tokens": 17487168} {"current_steps": 82865, "total_steps": 181800, "loss": 0.0253, "lr": 3.307336245262752e-05, "epoch": 9.116061606160615, "percentage": 45.58, "elapsed_time": "3:16:12", "remaining_time": "3:54:15", "throughput": 1485.55, "total_tokens": 17488224} {"current_steps": 82870, "total_steps": 181800, "loss": 0.0561, "lr": 3.307109094016575e-05, "epoch": 9.116611661166116, "percentage": 45.58, "elapsed_time": "3:16:12", "remaining_time": "3:54:14", "throughput": 1485.55, "total_tokens": 17489312} {"current_steps": 82875, "total_steps": 181800, "loss": 0.0525, "lr": 3.30688193533166e-05, "epoch": 9.117161716171617, "percentage": 45.59, "elapsed_time": "3:16:13", "remaining_time": "3:54:13", "throughput": 1485.56, "total_tokens": 17490400} {"current_steps": 82880, "total_steps": 181800, "loss": 0.0038, "lr": 3.306654769210101e-05, "epoch": 9.117711771177119, "percentage": 45.59, "elapsed_time": "3:16:14", "remaining_time": "3:54:13", "throughput": 1485.56, "total_tokens": 17491456} {"current_steps": 82885, "total_steps": 181800, "loss": 0.015, "lr": 3.306427595653993e-05, "epoch": 9.118261826182618, "percentage": 45.59, "elapsed_time": "3:16:15", "remaining_time": "3:54:12", "throughput": 1485.56, "total_tokens": 17492480} {"current_steps": 82890, "total_steps": 181800, "loss": 0.0188, "lr": 3.306200414665428e-05, "epoch": 9.118811881188119, "percentage": 45.59, "elapsed_time": "3:16:15", "remaining_time": "3:54:11", "throughput": 1485.56, "total_tokens": 17493536} {"current_steps": 82895, "total_steps": 181800, "loss": 0.001, "lr": 3.3059732262465e-05, "epoch": 9.11936193619362, "percentage": 45.6, "elapsed_time": "3:16:16", "remaining_time": "3:54:10", "throughput": 1485.57, "total_tokens": 17494656} {"current_steps": 82900, "total_steps": 181800, "loss": 0.0391, "lr": 3.3057460303993054e-05, "epoch": 9.11991199119912, "percentage": 45.6, "elapsed_time": "3:16:17", "remaining_time": "3:54:10", "throughput": 1485.58, "total_tokens": 17495744} {"current_steps": 82905, "total_steps": 181800, "loss": 0.0992, "lr": 3.305518827125935e-05, "epoch": 9.12046204620462, "percentage": 45.6, "elapsed_time": "3:16:17", "remaining_time": "3:54:09", "throughput": 1485.58, "total_tokens": 17496768} {"current_steps": 82910, "total_steps": 181800, "loss": 0.0207, "lr": 3.3052916164284846e-05, "epoch": 9.121012101210122, "percentage": 45.61, "elapsed_time": "3:16:18", "remaining_time": "3:54:08", "throughput": 1485.58, "total_tokens": 17497856} {"current_steps": 82915, "total_steps": 181800, "loss": 0.0118, "lr": 3.305064398309048e-05, "epoch": 9.12156215621562, "percentage": 45.61, "elapsed_time": "3:16:19", "remaining_time": "3:54:07", "throughput": 1485.58, "total_tokens": 17498880} {"current_steps": 82920, "total_steps": 181800, "loss": 0.0802, "lr": 3.304837172769718e-05, "epoch": 9.122112211221122, "percentage": 45.61, "elapsed_time": "3:16:19", "remaining_time": "3:54:07", "throughput": 1485.59, "total_tokens": 17500000} {"current_steps": 82925, "total_steps": 181800, "loss": 0.0157, "lr": 3.304609939812591e-05, "epoch": 9.122662266226623, "percentage": 45.61, "elapsed_time": "3:16:20", "remaining_time": "3:54:06", "throughput": 1485.59, "total_tokens": 17501024} {"current_steps": 82930, "total_steps": 181800, "loss": 0.0277, "lr": 3.3043826994397606e-05, "epoch": 9.123212321232122, "percentage": 45.62, "elapsed_time": "3:16:21", "remaining_time": "3:54:05", "throughput": 1485.59, "total_tokens": 17502080} {"current_steps": 82935, "total_steps": 181800, "loss": 0.0692, "lr": 3.304155451653319e-05, "epoch": 9.123762376237623, "percentage": 45.62, "elapsed_time": "3:16:21", "remaining_time": "3:54:04", "throughput": 1485.6, "total_tokens": 17503168} {"current_steps": 82940, "total_steps": 181800, "loss": 0.0082, "lr": 3.303928196455364e-05, "epoch": 9.124312431243125, "percentage": 45.62, "elapsed_time": "3:16:22", "remaining_time": "3:54:04", "throughput": 1485.6, "total_tokens": 17504256} {"current_steps": 82945, "total_steps": 181800, "loss": 0.0112, "lr": 3.303700933847988e-05, "epoch": 9.124862486248626, "percentage": 45.62, "elapsed_time": "3:16:23", "remaining_time": "3:54:03", "throughput": 1485.61, "total_tokens": 17505312} {"current_steps": 82950, "total_steps": 181800, "loss": 0.0572, "lr": 3.303473663833286e-05, "epoch": 9.125412541254125, "percentage": 45.63, "elapsed_time": "3:16:23", "remaining_time": "3:54:02", "throughput": 1485.61, "total_tokens": 17506400} {"current_steps": 82955, "total_steps": 181800, "loss": 0.0022, "lr": 3.3032463864133544e-05, "epoch": 9.125962596259626, "percentage": 45.63, "elapsed_time": "3:16:24", "remaining_time": "3:54:02", "throughput": 1485.61, "total_tokens": 17507392} {"current_steps": 82960, "total_steps": 181800, "loss": 0.008, "lr": 3.303019101590286e-05, "epoch": 9.126512651265127, "percentage": 45.63, "elapsed_time": "3:16:25", "remaining_time": "3:54:01", "throughput": 1485.61, "total_tokens": 17508448} {"current_steps": 82965, "total_steps": 181800, "loss": 0.0185, "lr": 3.302791809366174e-05, "epoch": 9.127062706270626, "percentage": 45.64, "elapsed_time": "3:16:26", "remaining_time": "3:54:00", "throughput": 1485.62, "total_tokens": 17509568} {"current_steps": 82970, "total_steps": 181800, "loss": 0.0542, "lr": 3.302564509743116e-05, "epoch": 9.127612761276128, "percentage": 45.64, "elapsed_time": "3:16:26", "remaining_time": "3:53:59", "throughput": 1485.62, "total_tokens": 17510624} {"current_steps": 82975, "total_steps": 181800, "loss": 0.0364, "lr": 3.302337202723206e-05, "epoch": 9.128162816281629, "percentage": 45.64, "elapsed_time": "3:16:27", "remaining_time": "3:53:59", "throughput": 1485.63, "total_tokens": 17511712} {"current_steps": 82980, "total_steps": 181800, "loss": 0.059, "lr": 3.3021098883085396e-05, "epoch": 9.128712871287128, "percentage": 45.64, "elapsed_time": "3:16:28", "remaining_time": "3:53:58", "throughput": 1485.64, "total_tokens": 17512832} {"current_steps": 82985, "total_steps": 181800, "loss": 0.0025, "lr": 3.3018825665012104e-05, "epoch": 9.129262926292629, "percentage": 45.65, "elapsed_time": "3:16:28", "remaining_time": "3:53:57", "throughput": 1485.64, "total_tokens": 17513920} {"current_steps": 82990, "total_steps": 181800, "loss": 0.0098, "lr": 3.301655237303315e-05, "epoch": 9.12981298129813, "percentage": 45.65, "elapsed_time": "3:16:29", "remaining_time": "3:53:56", "throughput": 1485.64, "total_tokens": 17514944} {"current_steps": 82995, "total_steps": 181800, "loss": 0.0135, "lr": 3.3014279007169466e-05, "epoch": 9.130363036303631, "percentage": 45.65, "elapsed_time": "3:16:30", "remaining_time": "3:53:56", "throughput": 1485.64, "total_tokens": 17515968} {"current_steps": 83000, "total_steps": 181800, "loss": 0.0529, "lr": 3.301200556744204e-05, "epoch": 9.13091309130913, "percentage": 45.65, "elapsed_time": "3:16:30", "remaining_time": "3:53:55", "throughput": 1485.65, "total_tokens": 17517056} {"current_steps": 83005, "total_steps": 181800, "loss": 0.0036, "lr": 3.300973205387179e-05, "epoch": 9.131463146314632, "percentage": 45.66, "elapsed_time": "3:16:31", "remaining_time": "3:53:54", "throughput": 1485.65, "total_tokens": 17518080} {"current_steps": 83010, "total_steps": 181800, "loss": 0.0105, "lr": 3.300745846647968e-05, "epoch": 9.132013201320133, "percentage": 45.66, "elapsed_time": "3:16:32", "remaining_time": "3:53:53", "throughput": 1485.65, "total_tokens": 17519168} {"current_steps": 83015, "total_steps": 181800, "loss": 0.0052, "lr": 3.3005184805286674e-05, "epoch": 9.132563256325632, "percentage": 45.66, "elapsed_time": "3:16:32", "remaining_time": "3:53:53", "throughput": 1485.66, "total_tokens": 17520288} {"current_steps": 83020, "total_steps": 181800, "loss": 0.0161, "lr": 3.300291107031372e-05, "epoch": 9.133113311331133, "percentage": 45.67, "elapsed_time": "3:16:33", "remaining_time": "3:53:52", "throughput": 1485.67, "total_tokens": 17521408} {"current_steps": 83025, "total_steps": 181800, "loss": 0.0028, "lr": 3.300063726158178e-05, "epoch": 9.133663366336634, "percentage": 45.67, "elapsed_time": "3:16:34", "remaining_time": "3:53:51", "throughput": 1485.67, "total_tokens": 17522496} {"current_steps": 83030, "total_steps": 181800, "loss": 0.0047, "lr": 3.29983633791118e-05, "epoch": 9.134213421342134, "percentage": 45.67, "elapsed_time": "3:16:34", "remaining_time": "3:53:50", "throughput": 1485.68, "total_tokens": 17523616} {"current_steps": 83035, "total_steps": 181800, "loss": 0.0031, "lr": 3.2996089422924734e-05, "epoch": 9.134763476347635, "percentage": 45.67, "elapsed_time": "3:16:35", "remaining_time": "3:53:50", "throughput": 1485.68, "total_tokens": 17524640} {"current_steps": 83040, "total_steps": 181800, "loss": 0.0808, "lr": 3.299381539304156e-05, "epoch": 9.135313531353136, "percentage": 45.68, "elapsed_time": "3:16:36", "remaining_time": "3:53:49", "throughput": 1485.69, "total_tokens": 17525728} {"current_steps": 83045, "total_steps": 181800, "loss": 0.0238, "lr": 3.299154128948322e-05, "epoch": 9.135863586358635, "percentage": 45.68, "elapsed_time": "3:16:37", "remaining_time": "3:53:48", "throughput": 1485.69, "total_tokens": 17526784} {"current_steps": 83050, "total_steps": 181800, "loss": 0.0179, "lr": 3.298926711227068e-05, "epoch": 9.136413641364136, "percentage": 45.68, "elapsed_time": "3:16:37", "remaining_time": "3:53:48", "throughput": 1485.69, "total_tokens": 17527840} {"current_steps": 83055, "total_steps": 181800, "loss": 0.0807, "lr": 3.2986992861424904e-05, "epoch": 9.136963696369637, "percentage": 45.68, "elapsed_time": "3:16:38", "remaining_time": "3:53:47", "throughput": 1485.69, "total_tokens": 17528832} {"current_steps": 83060, "total_steps": 181800, "loss": 0.129, "lr": 3.2984718536966846e-05, "epoch": 9.137513751375138, "percentage": 45.69, "elapsed_time": "3:16:39", "remaining_time": "3:53:46", "throughput": 1485.7, "total_tokens": 17529920} {"current_steps": 83065, "total_steps": 181800, "loss": 0.0023, "lr": 3.298244413891746e-05, "epoch": 9.138063806380638, "percentage": 45.69, "elapsed_time": "3:16:39", "remaining_time": "3:53:45", "throughput": 1485.7, "total_tokens": 17530976} {"current_steps": 83070, "total_steps": 181800, "loss": 0.0094, "lr": 3.298016966729772e-05, "epoch": 9.138613861386139, "percentage": 45.69, "elapsed_time": "3:16:40", "remaining_time": "3:53:45", "throughput": 1485.7, "total_tokens": 17532000} {"current_steps": 83075, "total_steps": 181800, "loss": 0.0868, "lr": 3.29778951221286e-05, "epoch": 9.13916391639164, "percentage": 45.7, "elapsed_time": "3:16:41", "remaining_time": "3:53:44", "throughput": 1485.71, "total_tokens": 17533152} {"current_steps": 83080, "total_steps": 181800, "loss": 0.0092, "lr": 3.2975620503431035e-05, "epoch": 9.13971397139714, "percentage": 45.7, "elapsed_time": "3:16:41", "remaining_time": "3:53:43", "throughput": 1485.71, "total_tokens": 17534208} {"current_steps": 83085, "total_steps": 181800, "loss": 0.1647, "lr": 3.2973345811226006e-05, "epoch": 9.14026402640264, "percentage": 45.7, "elapsed_time": "3:16:42", "remaining_time": "3:53:42", "throughput": 1485.71, "total_tokens": 17535232} {"current_steps": 83090, "total_steps": 181800, "loss": 0.0743, "lr": 3.2971071045534466e-05, "epoch": 9.140814081408141, "percentage": 45.7, "elapsed_time": "3:16:43", "remaining_time": "3:53:42", "throughput": 1485.72, "total_tokens": 17536320} {"current_steps": 83095, "total_steps": 181800, "loss": 0.1532, "lr": 3.29687962063774e-05, "epoch": 9.14136413641364, "percentage": 45.71, "elapsed_time": "3:16:43", "remaining_time": "3:53:41", "throughput": 1485.72, "total_tokens": 17537408} {"current_steps": 83100, "total_steps": 181800, "loss": 0.0139, "lr": 3.296652129377576e-05, "epoch": 9.141914191419142, "percentage": 45.71, "elapsed_time": "3:16:44", "remaining_time": "3:53:40", "throughput": 1485.73, "total_tokens": 17538496} {"current_steps": 83105, "total_steps": 181800, "loss": 0.0714, "lr": 3.296424630775052e-05, "epoch": 9.142464246424643, "percentage": 45.71, "elapsed_time": "3:16:45", "remaining_time": "3:53:39", "throughput": 1485.73, "total_tokens": 17539520} {"current_steps": 83110, "total_steps": 181800, "loss": 0.0281, "lr": 3.296197124832263e-05, "epoch": 9.143014301430142, "percentage": 45.72, "elapsed_time": "3:16:46", "remaining_time": "3:53:39", "throughput": 1485.74, "total_tokens": 17540640} {"current_steps": 83115, "total_steps": 181800, "loss": 0.0219, "lr": 3.2959696115513086e-05, "epoch": 9.143564356435643, "percentage": 45.72, "elapsed_time": "3:16:46", "remaining_time": "3:53:38", "throughput": 1485.74, "total_tokens": 17541664} {"current_steps": 83120, "total_steps": 181800, "loss": 0.0451, "lr": 3.295742090934284e-05, "epoch": 9.144114411441144, "percentage": 45.72, "elapsed_time": "3:16:47", "remaining_time": "3:53:37", "throughput": 1485.74, "total_tokens": 17542720} {"current_steps": 83125, "total_steps": 181800, "loss": 0.0035, "lr": 3.295514562983286e-05, "epoch": 9.144664466446645, "percentage": 45.72, "elapsed_time": "3:16:48", "remaining_time": "3:53:36", "throughput": 1485.75, "total_tokens": 17543872} {"current_steps": 83130, "total_steps": 181800, "loss": 0.0233, "lr": 3.295287027700412e-05, "epoch": 9.145214521452145, "percentage": 45.73, "elapsed_time": "3:16:48", "remaining_time": "3:53:36", "throughput": 1485.76, "total_tokens": 17544960} {"current_steps": 83135, "total_steps": 181800, "loss": 0.0896, "lr": 3.295059485087759e-05, "epoch": 9.145764576457646, "percentage": 45.73, "elapsed_time": "3:16:49", "remaining_time": "3:53:35", "throughput": 1485.76, "total_tokens": 17546016} {"current_steps": 83140, "total_steps": 181800, "loss": 0.0256, "lr": 3.294831935147424e-05, "epoch": 9.146314631463147, "percentage": 45.73, "elapsed_time": "3:16:50", "remaining_time": "3:53:34", "throughput": 1485.76, "total_tokens": 17547104} {"current_steps": 83145, "total_steps": 181800, "loss": 0.003, "lr": 3.294604377881505e-05, "epoch": 9.146864686468646, "percentage": 45.73, "elapsed_time": "3:16:50", "remaining_time": "3:53:34", "throughput": 1485.76, "total_tokens": 17548128} {"current_steps": 83150, "total_steps": 181800, "loss": 0.0027, "lr": 3.294376813292099e-05, "epoch": 9.147414741474147, "percentage": 45.74, "elapsed_time": "3:16:51", "remaining_time": "3:53:33", "throughput": 1485.77, "total_tokens": 17549216} {"current_steps": 83155, "total_steps": 181800, "loss": 0.0096, "lr": 3.294149241381302e-05, "epoch": 9.147964796479648, "percentage": 45.74, "elapsed_time": "3:16:52", "remaining_time": "3:53:32", "throughput": 1485.77, "total_tokens": 17550272} {"current_steps": 83160, "total_steps": 181800, "loss": 0.0129, "lr": 3.2939216621512134e-05, "epoch": 9.148514851485148, "percentage": 45.74, "elapsed_time": "3:16:52", "remaining_time": "3:53:31", "throughput": 1485.78, "total_tokens": 17551328} {"current_steps": 83165, "total_steps": 181800, "loss": 0.0513, "lr": 3.29369407560393e-05, "epoch": 9.149064906490649, "percentage": 45.75, "elapsed_time": "3:16:53", "remaining_time": "3:53:31", "throughput": 1485.78, "total_tokens": 17552384} {"current_steps": 83170, "total_steps": 181800, "loss": 0.1161, "lr": 3.293466481741548e-05, "epoch": 9.14961496149615, "percentage": 45.75, "elapsed_time": "3:16:54", "remaining_time": "3:53:30", "throughput": 1485.78, "total_tokens": 17553472} {"current_steps": 83175, "total_steps": 181800, "loss": 0.0088, "lr": 3.293238880566167e-05, "epoch": 9.150165016501651, "percentage": 45.75, "elapsed_time": "3:16:54", "remaining_time": "3:53:29", "throughput": 1485.79, "total_tokens": 17554528} {"current_steps": 83180, "total_steps": 181800, "loss": 0.0224, "lr": 3.2930112720798846e-05, "epoch": 9.15071507150715, "percentage": 45.75, "elapsed_time": "3:16:55", "remaining_time": "3:53:28", "throughput": 1485.79, "total_tokens": 17555584} {"current_steps": 83185, "total_steps": 181800, "loss": 0.0098, "lr": 3.2927836562847964e-05, "epoch": 9.151265126512651, "percentage": 45.76, "elapsed_time": "3:16:56", "remaining_time": "3:53:28", "throughput": 1485.79, "total_tokens": 17556576} {"current_steps": 83190, "total_steps": 181800, "loss": 0.007, "lr": 3.292556033183003e-05, "epoch": 9.151815181518153, "percentage": 45.76, "elapsed_time": "3:16:57", "remaining_time": "3:53:27", "throughput": 1485.79, "total_tokens": 17557600} {"current_steps": 83195, "total_steps": 181800, "loss": 0.0091, "lr": 3.292328402776599e-05, "epoch": 9.152365236523652, "percentage": 45.76, "elapsed_time": "3:16:57", "remaining_time": "3:53:26", "throughput": 1485.79, "total_tokens": 17558656} {"current_steps": 83200, "total_steps": 181800, "loss": 0.0033, "lr": 3.292100765067686e-05, "epoch": 9.152915291529153, "percentage": 45.76, "elapsed_time": "3:16:58", "remaining_time": "3:53:25", "throughput": 1485.79, "total_tokens": 17559712} {"current_steps": 83205, "total_steps": 181800, "loss": 0.0989, "lr": 3.2918731200583594e-05, "epoch": 9.153465346534654, "percentage": 45.77, "elapsed_time": "3:16:59", "remaining_time": "3:53:25", "throughput": 1485.79, "total_tokens": 17560736} {"current_steps": 83210, "total_steps": 181800, "loss": 0.0068, "lr": 3.2916454677507194e-05, "epoch": 9.154015401540153, "percentage": 45.77, "elapsed_time": "3:16:59", "remaining_time": "3:53:24", "throughput": 1485.8, "total_tokens": 17561792} {"current_steps": 83215, "total_steps": 181800, "loss": 0.0094, "lr": 3.291417808146862e-05, "epoch": 9.154565456545654, "percentage": 45.77, "elapsed_time": "3:17:00", "remaining_time": "3:53:23", "throughput": 1485.79, "total_tokens": 17562752} {"current_steps": 83220, "total_steps": 181800, "loss": 0.0058, "lr": 3.291190141248887e-05, "epoch": 9.155115511551156, "percentage": 45.78, "elapsed_time": "3:17:01", "remaining_time": "3:53:23", "throughput": 1485.8, "total_tokens": 17563840} {"current_steps": 83225, "total_steps": 181800, "loss": 0.0069, "lr": 3.290962467058891e-05, "epoch": 9.155665566556655, "percentage": 45.78, "elapsed_time": "3:17:01", "remaining_time": "3:53:22", "throughput": 1485.79, "total_tokens": 17564832} {"current_steps": 83230, "total_steps": 181800, "loss": 0.0088, "lr": 3.290734785578975e-05, "epoch": 9.156215621562156, "percentage": 45.78, "elapsed_time": "3:17:02", "remaining_time": "3:53:21", "throughput": 1485.8, "total_tokens": 17565888} {"current_steps": 83235, "total_steps": 181800, "loss": 0.0976, "lr": 3.290507096811235e-05, "epoch": 9.156765676567657, "percentage": 45.78, "elapsed_time": "3:17:03", "remaining_time": "3:53:20", "throughput": 1485.8, "total_tokens": 17566944} {"current_steps": 83240, "total_steps": 181800, "loss": 0.0056, "lr": 3.290279400757771e-05, "epoch": 9.157315731573158, "percentage": 45.79, "elapsed_time": "3:17:03", "remaining_time": "3:53:20", "throughput": 1485.8, "total_tokens": 17568032} {"current_steps": 83245, "total_steps": 181800, "loss": 0.0099, "lr": 3.2900516974206804e-05, "epoch": 9.157865786578657, "percentage": 45.79, "elapsed_time": "3:17:04", "remaining_time": "3:53:19", "throughput": 1485.8, "total_tokens": 17568992} {"current_steps": 83250, "total_steps": 181800, "loss": 0.0846, "lr": 3.2898239868020624e-05, "epoch": 9.158415841584159, "percentage": 45.79, "elapsed_time": "3:17:05", "remaining_time": "3:53:18", "throughput": 1485.8, "total_tokens": 17569984} {"current_steps": 83255, "total_steps": 181800, "loss": 0.0492, "lr": 3.289596268904016e-05, "epoch": 9.15896589658966, "percentage": 45.79, "elapsed_time": "3:17:05", "remaining_time": "3:53:17", "throughput": 1485.8, "total_tokens": 17571104} {"current_steps": 83260, "total_steps": 181800, "loss": 0.0102, "lr": 3.2893685437286396e-05, "epoch": 9.159515951595159, "percentage": 45.8, "elapsed_time": "3:17:06", "remaining_time": "3:53:17", "throughput": 1485.8, "total_tokens": 17572128} {"current_steps": 83265, "total_steps": 181800, "loss": 0.0105, "lr": 3.2891408112780326e-05, "epoch": 9.16006600660066, "percentage": 45.8, "elapsed_time": "3:17:07", "remaining_time": "3:53:16", "throughput": 1485.81, "total_tokens": 17573184} {"current_steps": 83270, "total_steps": 181800, "loss": 0.0113, "lr": 3.2889130715542926e-05, "epoch": 9.160616061606161, "percentage": 45.8, "elapsed_time": "3:17:08", "remaining_time": "3:53:15", "throughput": 1485.81, "total_tokens": 17574240} {"current_steps": 83275, "total_steps": 181800, "loss": 0.0271, "lr": 3.2886853245595194e-05, "epoch": 9.16116611661166, "percentage": 45.81, "elapsed_time": "3:17:08", "remaining_time": "3:53:14", "throughput": 1485.81, "total_tokens": 17575328} {"current_steps": 83280, "total_steps": 181800, "loss": 0.1245, "lr": 3.288457570295812e-05, "epoch": 9.161716171617162, "percentage": 45.81, "elapsed_time": "3:17:09", "remaining_time": "3:53:14", "throughput": 1485.81, "total_tokens": 17576320} {"current_steps": 83285, "total_steps": 181800, "loss": 0.0494, "lr": 3.28822980876527e-05, "epoch": 9.162266226622663, "percentage": 45.81, "elapsed_time": "3:17:10", "remaining_time": "3:53:13", "throughput": 1485.81, "total_tokens": 17577312} {"current_steps": 83290, "total_steps": 181800, "loss": 0.0275, "lr": 3.2880020399699925e-05, "epoch": 9.162816281628162, "percentage": 45.81, "elapsed_time": "3:17:10", "remaining_time": "3:53:12", "throughput": 1485.81, "total_tokens": 17578400} {"current_steps": 83295, "total_steps": 181800, "loss": 0.0286, "lr": 3.2877742639120776e-05, "epoch": 9.163366336633663, "percentage": 45.82, "elapsed_time": "3:17:11", "remaining_time": "3:53:11", "throughput": 1485.81, "total_tokens": 17579392} {"current_steps": 83300, "total_steps": 181800, "loss": 0.2746, "lr": 3.287546480593625e-05, "epoch": 9.163916391639164, "percentage": 45.82, "elapsed_time": "3:17:12", "remaining_time": "3:53:11", "throughput": 1485.82, "total_tokens": 17580480} {"current_steps": 83305, "total_steps": 181800, "loss": 0.0073, "lr": 3.2873186900167355e-05, "epoch": 9.164466446644665, "percentage": 45.82, "elapsed_time": "3:17:12", "remaining_time": "3:53:10", "throughput": 1485.83, "total_tokens": 17581600} {"current_steps": 83310, "total_steps": 181800, "loss": 0.0744, "lr": 3.287090892183506e-05, "epoch": 9.165016501650165, "percentage": 45.83, "elapsed_time": "3:17:13", "remaining_time": "3:53:09", "throughput": 1485.83, "total_tokens": 17582688} {"current_steps": 83315, "total_steps": 181800, "loss": 0.0058, "lr": 3.286863087096038e-05, "epoch": 9.165566556655666, "percentage": 45.83, "elapsed_time": "3:17:14", "remaining_time": "3:53:09", "throughput": 1485.83, "total_tokens": 17583744} {"current_steps": 83320, "total_steps": 181800, "loss": 0.0034, "lr": 3.286635274756431e-05, "epoch": 9.166116611661167, "percentage": 45.83, "elapsed_time": "3:17:14", "remaining_time": "3:53:08", "throughput": 1485.84, "total_tokens": 17584832} {"current_steps": 83325, "total_steps": 181800, "loss": 0.0084, "lr": 3.286407455166784e-05, "epoch": 9.166666666666666, "percentage": 45.83, "elapsed_time": "3:17:15", "remaining_time": "3:53:07", "throughput": 1485.84, "total_tokens": 17585888} {"current_steps": 83330, "total_steps": 181800, "loss": 0.0205, "lr": 3.2861796283291965e-05, "epoch": 9.167216721672167, "percentage": 45.84, "elapsed_time": "3:17:16", "remaining_time": "3:53:06", "throughput": 1485.84, "total_tokens": 17586880} {"current_steps": 83335, "total_steps": 181800, "loss": 0.0326, "lr": 3.285951794245769e-05, "epoch": 9.167766776677668, "percentage": 45.84, "elapsed_time": "3:17:17", "remaining_time": "3:53:06", "throughput": 1485.84, "total_tokens": 17587968} {"current_steps": 83340, "total_steps": 181800, "loss": 0.0591, "lr": 3.2857239529186e-05, "epoch": 9.168316831683168, "percentage": 45.84, "elapsed_time": "3:17:17", "remaining_time": "3:53:05", "throughput": 1485.85, "total_tokens": 17589120} {"current_steps": 83345, "total_steps": 181800, "loss": 0.0096, "lr": 3.285496104349791e-05, "epoch": 9.168866886688669, "percentage": 45.84, "elapsed_time": "3:17:18", "remaining_time": "3:53:04", "throughput": 1485.86, "total_tokens": 17590208} {"current_steps": 83350, "total_steps": 181800, "loss": 0.0245, "lr": 3.285268248541442e-05, "epoch": 9.16941694169417, "percentage": 45.85, "elapsed_time": "3:17:19", "remaining_time": "3:53:03", "throughput": 1485.86, "total_tokens": 17591296} {"current_steps": 83355, "total_steps": 181800, "loss": 0.0426, "lr": 3.285040385495652e-05, "epoch": 9.16996699669967, "percentage": 45.85, "elapsed_time": "3:17:19", "remaining_time": "3:53:03", "throughput": 1485.87, "total_tokens": 17592352} {"current_steps": 83360, "total_steps": 181800, "loss": 0.1206, "lr": 3.2848125152145206e-05, "epoch": 9.17051705170517, "percentage": 45.85, "elapsed_time": "3:17:20", "remaining_time": "3:53:02", "throughput": 1485.87, "total_tokens": 17593376} {"current_steps": 83365, "total_steps": 181800, "loss": 0.0128, "lr": 3.28458463770015e-05, "epoch": 9.171067106710671, "percentage": 45.86, "elapsed_time": "3:17:21", "remaining_time": "3:53:01", "throughput": 1485.88, "total_tokens": 17594496} {"current_steps": 83370, "total_steps": 181800, "loss": 0.1319, "lr": 3.284356752954638e-05, "epoch": 9.171617161716172, "percentage": 45.86, "elapsed_time": "3:17:21", "remaining_time": "3:53:00", "throughput": 1485.88, "total_tokens": 17595520} {"current_steps": 83375, "total_steps": 181800, "loss": 0.0121, "lr": 3.284128860980087e-05, "epoch": 9.172167216721672, "percentage": 45.86, "elapsed_time": "3:17:22", "remaining_time": "3:53:00", "throughput": 1485.88, "total_tokens": 17596640} {"current_steps": 83380, "total_steps": 181800, "loss": 0.025, "lr": 3.2839009617785974e-05, "epoch": 9.172717271727173, "percentage": 45.86, "elapsed_time": "3:17:23", "remaining_time": "3:52:59", "throughput": 1485.89, "total_tokens": 17597696} {"current_steps": 83385, "total_steps": 181800, "loss": 0.0098, "lr": 3.2836730553522674e-05, "epoch": 9.173267326732674, "percentage": 45.87, "elapsed_time": "3:17:23", "remaining_time": "3:52:58", "throughput": 1485.89, "total_tokens": 17598784} {"current_steps": 83390, "total_steps": 181800, "loss": 0.0038, "lr": 3.2834451417031994e-05, "epoch": 9.173817381738173, "percentage": 45.87, "elapsed_time": "3:17:24", "remaining_time": "3:52:58", "throughput": 1485.89, "total_tokens": 17599808} {"current_steps": 83395, "total_steps": 181800, "loss": 0.0023, "lr": 3.2832172208334933e-05, "epoch": 9.174367436743674, "percentage": 45.87, "elapsed_time": "3:17:25", "remaining_time": "3:52:57", "throughput": 1485.9, "total_tokens": 17600896} {"current_steps": 83400, "total_steps": 181800, "loss": 0.029, "lr": 3.28298929274525e-05, "epoch": 9.174917491749175, "percentage": 45.87, "elapsed_time": "3:17:25", "remaining_time": "3:52:56", "throughput": 1485.9, "total_tokens": 17601920} {"current_steps": 83405, "total_steps": 181800, "loss": 0.0373, "lr": 3.28276135744057e-05, "epoch": 9.175467546754675, "percentage": 45.88, "elapsed_time": "3:17:26", "remaining_time": "3:52:55", "throughput": 1485.9, "total_tokens": 17602944} {"current_steps": 83410, "total_steps": 181800, "loss": 0.0069, "lr": 3.2825334149215545e-05, "epoch": 9.176017601760176, "percentage": 45.88, "elapsed_time": "3:17:27", "remaining_time": "3:52:55", "throughput": 1485.9, "total_tokens": 17604032} {"current_steps": 83415, "total_steps": 181800, "loss": 0.0026, "lr": 3.282305465190303e-05, "epoch": 9.176567656765677, "percentage": 45.88, "elapsed_time": "3:17:28", "remaining_time": "3:52:54", "throughput": 1485.91, "total_tokens": 17605120} {"current_steps": 83420, "total_steps": 181800, "loss": 0.0128, "lr": 3.2820775082489185e-05, "epoch": 9.177117711771178, "percentage": 45.89, "elapsed_time": "3:17:28", "remaining_time": "3:52:53", "throughput": 1485.91, "total_tokens": 17606176} {"current_steps": 83425, "total_steps": 181800, "loss": 0.0404, "lr": 3.281849544099501e-05, "epoch": 9.177667766776677, "percentage": 45.89, "elapsed_time": "3:17:29", "remaining_time": "3:52:52", "throughput": 1485.91, "total_tokens": 17607232} {"current_steps": 83430, "total_steps": 181800, "loss": 0.0882, "lr": 3.281621572744151e-05, "epoch": 9.178217821782178, "percentage": 45.89, "elapsed_time": "3:17:30", "remaining_time": "3:52:52", "throughput": 1485.92, "total_tokens": 17608352} {"current_steps": 83435, "total_steps": 181800, "loss": 0.0275, "lr": 3.28139359418497e-05, "epoch": 9.17876787678768, "percentage": 45.89, "elapsed_time": "3:17:30", "remaining_time": "3:52:51", "throughput": 1485.92, "total_tokens": 17609312} {"current_steps": 83440, "total_steps": 181800, "loss": 0.0261, "lr": 3.2811656084240594e-05, "epoch": 9.179317931793179, "percentage": 45.9, "elapsed_time": "3:17:31", "remaining_time": "3:52:50", "throughput": 1485.92, "total_tokens": 17610368} {"current_steps": 83445, "total_steps": 181800, "loss": 0.0853, "lr": 3.2809376154635194e-05, "epoch": 9.17986798679868, "percentage": 45.9, "elapsed_time": "3:17:32", "remaining_time": "3:52:49", "throughput": 1485.92, "total_tokens": 17611456} {"current_steps": 83450, "total_steps": 181800, "loss": 0.1036, "lr": 3.2807096153054526e-05, "epoch": 9.180418041804181, "percentage": 45.9, "elapsed_time": "3:17:32", "remaining_time": "3:52:49", "throughput": 1485.93, "total_tokens": 17612512} {"current_steps": 83455, "total_steps": 181800, "loss": 0.0338, "lr": 3.2804816079519614e-05, "epoch": 9.18096809680968, "percentage": 45.9, "elapsed_time": "3:17:33", "remaining_time": "3:52:48", "throughput": 1485.92, "total_tokens": 17613504} {"current_steps": 83460, "total_steps": 181800, "loss": 0.0485, "lr": 3.280253593405144e-05, "epoch": 9.181518151815181, "percentage": 45.91, "elapsed_time": "3:17:34", "remaining_time": "3:52:47", "throughput": 1485.93, "total_tokens": 17614560} {"current_steps": 83465, "total_steps": 181800, "loss": 0.1182, "lr": 3.2800255716671035e-05, "epoch": 9.182068206820682, "percentage": 45.91, "elapsed_time": "3:17:34", "remaining_time": "3:52:47", "throughput": 1485.93, "total_tokens": 17615616} {"current_steps": 83470, "total_steps": 181800, "loss": 0.0066, "lr": 3.279797542739943e-05, "epoch": 9.182618261826182, "percentage": 45.91, "elapsed_time": "3:17:35", "remaining_time": "3:52:46", "throughput": 1485.93, "total_tokens": 17616704} {"current_steps": 83475, "total_steps": 181800, "loss": 0.0134, "lr": 3.2795695066257616e-05, "epoch": 9.183168316831683, "percentage": 45.92, "elapsed_time": "3:17:36", "remaining_time": "3:52:45", "throughput": 1485.94, "total_tokens": 17617824} {"current_steps": 83480, "total_steps": 181800, "loss": 0.0072, "lr": 3.279341463326662e-05, "epoch": 9.183718371837184, "percentage": 45.92, "elapsed_time": "3:17:37", "remaining_time": "3:52:44", "throughput": 1485.95, "total_tokens": 17618880} {"current_steps": 83485, "total_steps": 181800, "loss": 0.0209, "lr": 3.279113412844746e-05, "epoch": 9.184268426842685, "percentage": 45.92, "elapsed_time": "3:17:37", "remaining_time": "3:52:44", "throughput": 1485.94, "total_tokens": 17619872} {"current_steps": 83490, "total_steps": 181800, "loss": 0.0227, "lr": 3.278885355182116e-05, "epoch": 9.184818481848184, "percentage": 45.92, "elapsed_time": "3:17:38", "remaining_time": "3:52:43", "throughput": 1485.95, "total_tokens": 17620960} {"current_steps": 83495, "total_steps": 181800, "loss": 0.0081, "lr": 3.278657290340874e-05, "epoch": 9.185368536853685, "percentage": 45.93, "elapsed_time": "3:17:39", "remaining_time": "3:52:42", "throughput": 1485.95, "total_tokens": 17621952} {"current_steps": 83500, "total_steps": 181800, "loss": 0.1278, "lr": 3.2784292183231206e-05, "epoch": 9.185918591859187, "percentage": 45.93, "elapsed_time": "3:17:39", "remaining_time": "3:52:41", "throughput": 1485.95, "total_tokens": 17623072} {"current_steps": 83505, "total_steps": 181800, "loss": 0.0359, "lr": 3.278201139130959e-05, "epoch": 9.186468646864686, "percentage": 45.93, "elapsed_time": "3:17:40", "remaining_time": "3:52:41", "throughput": 1485.95, "total_tokens": 17624096} {"current_steps": 83510, "total_steps": 181800, "loss": 0.0374, "lr": 3.277973052766491e-05, "epoch": 9.187018701870187, "percentage": 45.94, "elapsed_time": "3:17:41", "remaining_time": "3:52:40", "throughput": 1485.95, "total_tokens": 17625088} {"current_steps": 83515, "total_steps": 181800, "loss": 0.0212, "lr": 3.2777449592318176e-05, "epoch": 9.187568756875688, "percentage": 45.94, "elapsed_time": "3:17:41", "remaining_time": "3:52:39", "throughput": 1485.95, "total_tokens": 17626112} {"current_steps": 83520, "total_steps": 181800, "loss": 0.0072, "lr": 3.277516858529043e-05, "epoch": 9.188118811881187, "percentage": 45.94, "elapsed_time": "3:17:42", "remaining_time": "3:52:38", "throughput": 1485.95, "total_tokens": 17627168} {"current_steps": 83525, "total_steps": 181800, "loss": 0.0037, "lr": 3.27728875066027e-05, "epoch": 9.188668866886688, "percentage": 45.94, "elapsed_time": "3:17:43", "remaining_time": "3:52:38", "throughput": 1485.95, "total_tokens": 17628160} {"current_steps": 83530, "total_steps": 181800, "loss": 0.0056, "lr": 3.277060635627597e-05, "epoch": 9.18921892189219, "percentage": 45.95, "elapsed_time": "3:17:43", "remaining_time": "3:52:37", "throughput": 1485.95, "total_tokens": 17629184} {"current_steps": 83535, "total_steps": 181800, "loss": 0.0455, "lr": 3.27683251343313e-05, "epoch": 9.189768976897689, "percentage": 45.95, "elapsed_time": "3:17:44", "remaining_time": "3:52:36", "throughput": 1485.95, "total_tokens": 17630240} {"current_steps": 83540, "total_steps": 181800, "loss": 0.0237, "lr": 3.276604384078971e-05, "epoch": 9.19031903190319, "percentage": 45.95, "elapsed_time": "3:17:45", "remaining_time": "3:52:36", "throughput": 1485.96, "total_tokens": 17631328} {"current_steps": 83545, "total_steps": 181800, "loss": 0.0547, "lr": 3.276376247567221e-05, "epoch": 9.190869086908691, "percentage": 45.95, "elapsed_time": "3:17:45", "remaining_time": "3:52:35", "throughput": 1485.96, "total_tokens": 17632384} {"current_steps": 83550, "total_steps": 181800, "loss": 0.006, "lr": 3.276148103899985e-05, "epoch": 9.191419141914192, "percentage": 45.96, "elapsed_time": "3:17:46", "remaining_time": "3:52:34", "throughput": 1485.96, "total_tokens": 17633408} {"current_steps": 83555, "total_steps": 181800, "loss": 0.0119, "lr": 3.275919953079364e-05, "epoch": 9.191969196919691, "percentage": 45.96, "elapsed_time": "3:17:47", "remaining_time": "3:52:33", "throughput": 1485.96, "total_tokens": 17634496} {"current_steps": 83560, "total_steps": 181800, "loss": 0.0451, "lr": 3.2756917951074605e-05, "epoch": 9.192519251925193, "percentage": 45.96, "elapsed_time": "3:17:48", "remaining_time": "3:52:33", "throughput": 1485.97, "total_tokens": 17635616} {"current_steps": 83565, "total_steps": 181800, "loss": 0.0016, "lr": 3.275463629986378e-05, "epoch": 9.193069306930694, "percentage": 45.97, "elapsed_time": "3:17:48", "remaining_time": "3:52:32", "throughput": 1485.97, "total_tokens": 17636608} {"current_steps": 83570, "total_steps": 181800, "loss": 0.0035, "lr": 3.2752354577182205e-05, "epoch": 9.193619361936193, "percentage": 45.97, "elapsed_time": "3:17:49", "remaining_time": "3:52:31", "throughput": 1485.98, "total_tokens": 17637696} {"current_steps": 83575, "total_steps": 181800, "loss": 0.0789, "lr": 3.2750072783050884e-05, "epoch": 9.194169416941694, "percentage": 45.97, "elapsed_time": "3:17:50", "remaining_time": "3:52:30", "throughput": 1485.97, "total_tokens": 17638720} {"current_steps": 83580, "total_steps": 181800, "loss": 0.0494, "lr": 3.274779091749086e-05, "epoch": 9.194719471947195, "percentage": 45.97, "elapsed_time": "3:17:50", "remaining_time": "3:52:30", "throughput": 1485.98, "total_tokens": 17639840} {"current_steps": 83585, "total_steps": 181800, "loss": 0.011, "lr": 3.2745508980523173e-05, "epoch": 9.195269526952695, "percentage": 45.98, "elapsed_time": "3:17:51", "remaining_time": "3:52:29", "throughput": 1485.99, "total_tokens": 17640928} {"current_steps": 83590, "total_steps": 181800, "loss": 0.0035, "lr": 3.274322697216884e-05, "epoch": 9.195819581958196, "percentage": 45.98, "elapsed_time": "3:17:52", "remaining_time": "3:52:28", "throughput": 1485.99, "total_tokens": 17642016} {"current_steps": 83595, "total_steps": 181800, "loss": 0.0455, "lr": 3.274094489244891e-05, "epoch": 9.196369636963697, "percentage": 45.98, "elapsed_time": "3:17:52", "remaining_time": "3:52:27", "throughput": 1485.99, "total_tokens": 17643072} {"current_steps": 83600, "total_steps": 181800, "loss": 0.0139, "lr": 3.273866274138439e-05, "epoch": 9.196919691969198, "percentage": 45.98, "elapsed_time": "3:17:53", "remaining_time": "3:52:27", "throughput": 1486.0, "total_tokens": 17644160} {"current_steps": 83605, "total_steps": 181800, "loss": 0.0504, "lr": 3.2736380518996344e-05, "epoch": 9.197469746974697, "percentage": 45.99, "elapsed_time": "3:17:54", "remaining_time": "3:52:26", "throughput": 1486.0, "total_tokens": 17645152} {"current_steps": 83610, "total_steps": 181800, "loss": 0.0162, "lr": 3.273409822530578e-05, "epoch": 9.198019801980198, "percentage": 45.99, "elapsed_time": "3:17:54", "remaining_time": "3:52:25", "throughput": 1486.0, "total_tokens": 17646176} {"current_steps": 83615, "total_steps": 181800, "loss": 0.0606, "lr": 3.2731815860333755e-05, "epoch": 9.1985698569857, "percentage": 45.99, "elapsed_time": "3:17:55", "remaining_time": "3:52:25", "throughput": 1486.0, "total_tokens": 17647264} {"current_steps": 83620, "total_steps": 181800, "loss": 0.0039, "lr": 3.272953342410128e-05, "epoch": 9.199119911991199, "percentage": 46.0, "elapsed_time": "3:17:56", "remaining_time": "3:52:24", "throughput": 1486.01, "total_tokens": 17648384} {"current_steps": 83625, "total_steps": 181800, "loss": 0.0017, "lr": 3.2727250916629414e-05, "epoch": 9.1996699669967, "percentage": 46.0, "elapsed_time": "3:17:57", "remaining_time": "3:52:23", "throughput": 1486.01, "total_tokens": 17649472} {"current_steps": 83630, "total_steps": 181800, "loss": 0.0142, "lr": 3.2724968337939185e-05, "epoch": 9.2002200220022, "percentage": 46.0, "elapsed_time": "3:17:57", "remaining_time": "3:52:22", "throughput": 1486.02, "total_tokens": 17650560} {"current_steps": 83635, "total_steps": 181800, "loss": 0.0032, "lr": 3.272268568805162e-05, "epoch": 9.2007700770077, "percentage": 46.0, "elapsed_time": "3:17:58", "remaining_time": "3:52:22", "throughput": 1486.02, "total_tokens": 17651616} {"current_steps": 83640, "total_steps": 181800, "loss": 0.0199, "lr": 3.272040296698777e-05, "epoch": 9.201320132013201, "percentage": 46.01, "elapsed_time": "3:17:59", "remaining_time": "3:52:21", "throughput": 1486.02, "total_tokens": 17652672} {"current_steps": 83645, "total_steps": 181800, "loss": 0.0043, "lr": 3.2718120174768676e-05, "epoch": 9.201870187018702, "percentage": 46.01, "elapsed_time": "3:17:59", "remaining_time": "3:52:20", "throughput": 1486.02, "total_tokens": 17653696} {"current_steps": 83650, "total_steps": 181800, "loss": 0.1489, "lr": 3.2715837311415374e-05, "epoch": 9.202420242024202, "percentage": 46.01, "elapsed_time": "3:18:00", "remaining_time": "3:52:19", "throughput": 1486.02, "total_tokens": 17654688} {"current_steps": 83655, "total_steps": 181800, "loss": 0.0293, "lr": 3.27135543769489e-05, "epoch": 9.202970297029703, "percentage": 46.01, "elapsed_time": "3:18:01", "remaining_time": "3:52:19", "throughput": 1486.02, "total_tokens": 17655744} {"current_steps": 83660, "total_steps": 181800, "loss": 0.1425, "lr": 3.271127137139029e-05, "epoch": 9.203520352035204, "percentage": 46.02, "elapsed_time": "3:18:01", "remaining_time": "3:52:18", "throughput": 1486.03, "total_tokens": 17656832} {"current_steps": 83665, "total_steps": 181800, "loss": 0.0087, "lr": 3.2708988294760596e-05, "epoch": 9.204070407040705, "percentage": 46.02, "elapsed_time": "3:18:02", "remaining_time": "3:52:17", "throughput": 1486.03, "total_tokens": 17657856} {"current_steps": 83670, "total_steps": 181800, "loss": 0.0039, "lr": 3.270670514708086e-05, "epoch": 9.204620462046204, "percentage": 46.02, "elapsed_time": "3:18:03", "remaining_time": "3:52:16", "throughput": 1486.03, "total_tokens": 17658880} {"current_steps": 83675, "total_steps": 181800, "loss": 0.0938, "lr": 3.270442192837211e-05, "epoch": 9.205170517051705, "percentage": 46.03, "elapsed_time": "3:18:03", "remaining_time": "3:52:16", "throughput": 1486.03, "total_tokens": 17659936} {"current_steps": 83680, "total_steps": 181800, "loss": 0.0158, "lr": 3.2702138638655406e-05, "epoch": 9.205720572057206, "percentage": 46.03, "elapsed_time": "3:18:04", "remaining_time": "3:52:15", "throughput": 1486.03, "total_tokens": 17660992} {"current_steps": 83685, "total_steps": 181800, "loss": 0.0096, "lr": 3.269985527795179e-05, "epoch": 9.206270627062706, "percentage": 46.03, "elapsed_time": "3:18:05", "remaining_time": "3:52:14", "throughput": 1486.04, "total_tokens": 17662080} {"current_steps": 83690, "total_steps": 181800, "loss": 0.0211, "lr": 3.269757184628229e-05, "epoch": 9.206820682068207, "percentage": 46.03, "elapsed_time": "3:18:06", "remaining_time": "3:52:14", "throughput": 1486.05, "total_tokens": 17663168} {"current_steps": 83695, "total_steps": 181800, "loss": 0.0078, "lr": 3.269528834366798e-05, "epoch": 9.207370737073708, "percentage": 46.04, "elapsed_time": "3:18:06", "remaining_time": "3:52:13", "throughput": 1486.05, "total_tokens": 17664256} {"current_steps": 83700, "total_steps": 181800, "loss": 0.0016, "lr": 3.269300477012988e-05, "epoch": 9.207920792079207, "percentage": 46.04, "elapsed_time": "3:18:07", "remaining_time": "3:52:12", "throughput": 1486.05, "total_tokens": 17665280} {"current_steps": 83705, "total_steps": 181800, "loss": 0.0909, "lr": 3.269072112568905e-05, "epoch": 9.208470847084708, "percentage": 46.04, "elapsed_time": "3:18:08", "remaining_time": "3:52:11", "throughput": 1486.05, "total_tokens": 17666304} {"current_steps": 83710, "total_steps": 181800, "loss": 0.0212, "lr": 3.268843741036653e-05, "epoch": 9.20902090209021, "percentage": 46.05, "elapsed_time": "3:18:08", "remaining_time": "3:52:11", "throughput": 1486.06, "total_tokens": 17667424} {"current_steps": 83715, "total_steps": 181800, "loss": 0.0832, "lr": 3.268615362418338e-05, "epoch": 9.209570957095709, "percentage": 46.05, "elapsed_time": "3:18:09", "remaining_time": "3:52:10", "throughput": 1486.06, "total_tokens": 17668448} {"current_steps": 83720, "total_steps": 181800, "loss": 0.0135, "lr": 3.268386976716063e-05, "epoch": 9.21012101210121, "percentage": 46.05, "elapsed_time": "3:18:10", "remaining_time": "3:52:09", "throughput": 1486.06, "total_tokens": 17669504} {"current_steps": 83725, "total_steps": 181800, "loss": 0.0889, "lr": 3.2681585839319345e-05, "epoch": 9.210671067106711, "percentage": 46.05, "elapsed_time": "3:18:10", "remaining_time": "3:52:08", "throughput": 1486.06, "total_tokens": 17670496} {"current_steps": 83730, "total_steps": 181800, "loss": 0.0888, "lr": 3.267930184068057e-05, "epoch": 9.211221122112212, "percentage": 46.06, "elapsed_time": "3:18:11", "remaining_time": "3:52:08", "throughput": 1486.06, "total_tokens": 17671520} {"current_steps": 83735, "total_steps": 181800, "loss": 0.0213, "lr": 3.267701777126535e-05, "epoch": 9.211771177117711, "percentage": 46.06, "elapsed_time": "3:18:12", "remaining_time": "3:52:07", "throughput": 1486.06, "total_tokens": 17672512} {"current_steps": 83740, "total_steps": 181800, "loss": 0.0065, "lr": 3.267473363109475e-05, "epoch": 9.212321232123212, "percentage": 46.06, "elapsed_time": "3:18:12", "remaining_time": "3:52:06", "throughput": 1486.05, "total_tokens": 17673504} {"current_steps": 83745, "total_steps": 181800, "loss": 0.0433, "lr": 3.267244942018981e-05, "epoch": 9.212871287128714, "percentage": 46.06, "elapsed_time": "3:18:13", "remaining_time": "3:52:05", "throughput": 1486.05, "total_tokens": 17674528} {"current_steps": 83750, "total_steps": 181800, "loss": 0.0256, "lr": 3.267016513857158e-05, "epoch": 9.213421342134213, "percentage": 46.07, "elapsed_time": "3:18:14", "remaining_time": "3:52:05", "throughput": 1486.05, "total_tokens": 17675552} {"current_steps": 83755, "total_steps": 181800, "loss": 0.0017, "lr": 3.2667880786261116e-05, "epoch": 9.213971397139714, "percentage": 46.07, "elapsed_time": "3:18:14", "remaining_time": "3:52:04", "throughput": 1486.06, "total_tokens": 17676640} {"current_steps": 83760, "total_steps": 181800, "loss": 0.1962, "lr": 3.2665596363279485e-05, "epoch": 9.214521452145215, "percentage": 46.07, "elapsed_time": "3:18:15", "remaining_time": "3:52:03", "throughput": 1486.06, "total_tokens": 17677728} {"current_steps": 83765, "total_steps": 181800, "loss": 0.0239, "lr": 3.2663311869647724e-05, "epoch": 9.215071507150714, "percentage": 46.08, "elapsed_time": "3:18:16", "remaining_time": "3:52:03", "throughput": 1486.06, "total_tokens": 17678720} {"current_steps": 83770, "total_steps": 181800, "loss": 0.0014, "lr": 3.266102730538689e-05, "epoch": 9.215621562156215, "percentage": 46.08, "elapsed_time": "3:18:17", "remaining_time": "3:52:02", "throughput": 1486.06, "total_tokens": 17679776} {"current_steps": 83775, "total_steps": 181800, "loss": 0.0094, "lr": 3.265874267051806e-05, "epoch": 9.216171617161717, "percentage": 46.08, "elapsed_time": "3:18:17", "remaining_time": "3:52:01", "throughput": 1486.07, "total_tokens": 17680832} {"current_steps": 83780, "total_steps": 181800, "loss": 0.0387, "lr": 3.2656457965062256e-05, "epoch": 9.216721672167218, "percentage": 46.08, "elapsed_time": "3:18:18", "remaining_time": "3:52:00", "throughput": 1486.07, "total_tokens": 17681888} {"current_steps": 83785, "total_steps": 181800, "loss": 0.0294, "lr": 3.265417318904056e-05, "epoch": 9.217271727172717, "percentage": 46.09, "elapsed_time": "3:18:19", "remaining_time": "3:52:00", "throughput": 1486.08, "total_tokens": 17683008} {"current_steps": 83790, "total_steps": 181800, "loss": 0.021, "lr": 3.265188834247402e-05, "epoch": 9.217821782178218, "percentage": 46.09, "elapsed_time": "3:18:19", "remaining_time": "3:51:59", "throughput": 1486.08, "total_tokens": 17684064} {"current_steps": 83795, "total_steps": 181800, "loss": 0.0227, "lr": 3.26496034253837e-05, "epoch": 9.218371837183719, "percentage": 46.09, "elapsed_time": "3:18:20", "remaining_time": "3:51:58", "throughput": 1486.08, "total_tokens": 17685056} {"current_steps": 83800, "total_steps": 181800, "loss": 0.0023, "lr": 3.264731843779065e-05, "epoch": 9.218921892189218, "percentage": 46.09, "elapsed_time": "3:18:21", "remaining_time": "3:51:57", "throughput": 1486.08, "total_tokens": 17686144} {"current_steps": 83805, "total_steps": 181800, "loss": 0.0562, "lr": 3.2645033379715946e-05, "epoch": 9.21947194719472, "percentage": 46.1, "elapsed_time": "3:18:21", "remaining_time": "3:51:57", "throughput": 1486.08, "total_tokens": 17687168} {"current_steps": 83810, "total_steps": 181800, "loss": 0.054, "lr": 3.264274825118063e-05, "epoch": 9.22002200220022, "percentage": 46.1, "elapsed_time": "3:18:22", "remaining_time": "3:51:56", "throughput": 1486.08, "total_tokens": 17688160} {"current_steps": 83815, "total_steps": 181800, "loss": 0.0305, "lr": 3.264046305220578e-05, "epoch": 9.22057205720572, "percentage": 46.1, "elapsed_time": "3:18:23", "remaining_time": "3:51:55", "throughput": 1486.09, "total_tokens": 17689248} {"current_steps": 83820, "total_steps": 181800, "loss": 0.0503, "lr": 3.263817778281243e-05, "epoch": 9.221122112211221, "percentage": 46.11, "elapsed_time": "3:18:23", "remaining_time": "3:51:54", "throughput": 1486.09, "total_tokens": 17690272} {"current_steps": 83825, "total_steps": 181800, "loss": 0.026, "lr": 3.263589244302168e-05, "epoch": 9.221672167216722, "percentage": 46.11, "elapsed_time": "3:18:24", "remaining_time": "3:51:54", "throughput": 1486.09, "total_tokens": 17691328} {"current_steps": 83830, "total_steps": 181800, "loss": 0.1684, "lr": 3.263360703285456e-05, "epoch": 9.222222222222221, "percentage": 46.11, "elapsed_time": "3:18:25", "remaining_time": "3:51:53", "throughput": 1486.1, "total_tokens": 17692416} {"current_steps": 83835, "total_steps": 181800, "loss": 0.1229, "lr": 3.263132155233216e-05, "epoch": 9.222772277227723, "percentage": 46.11, "elapsed_time": "3:18:25", "remaining_time": "3:51:52", "throughput": 1486.1, "total_tokens": 17693472} {"current_steps": 83840, "total_steps": 181800, "loss": 0.0615, "lr": 3.262903600147552e-05, "epoch": 9.223322332233224, "percentage": 46.12, "elapsed_time": "3:18:26", "remaining_time": "3:51:51", "throughput": 1486.09, "total_tokens": 17694432} {"current_steps": 83845, "total_steps": 181800, "loss": 0.0755, "lr": 3.262675038030571e-05, "epoch": 9.223872387238725, "percentage": 46.12, "elapsed_time": "3:18:27", "remaining_time": "3:51:51", "throughput": 1486.09, "total_tokens": 17695424} {"current_steps": 83850, "total_steps": 181800, "loss": 0.0598, "lr": 3.262446468884381e-05, "epoch": 9.224422442244224, "percentage": 46.12, "elapsed_time": "3:18:28", "remaining_time": "3:51:50", "throughput": 1486.09, "total_tokens": 17696512} {"current_steps": 83855, "total_steps": 181800, "loss": 0.1091, "lr": 3.2622178927110894e-05, "epoch": 9.224972497249725, "percentage": 46.12, "elapsed_time": "3:18:28", "remaining_time": "3:51:49", "throughput": 1486.09, "total_tokens": 17697536} {"current_steps": 83860, "total_steps": 181800, "loss": 0.0337, "lr": 3.261989309512799e-05, "epoch": 9.225522552255226, "percentage": 46.13, "elapsed_time": "3:18:29", "remaining_time": "3:51:49", "throughput": 1486.1, "total_tokens": 17698592} {"current_steps": 83865, "total_steps": 181800, "loss": 0.0906, "lr": 3.261760719291619e-05, "epoch": 9.226072607260726, "percentage": 46.13, "elapsed_time": "3:18:30", "remaining_time": "3:51:48", "throughput": 1486.1, "total_tokens": 17699680} {"current_steps": 83870, "total_steps": 181800, "loss": 0.119, "lr": 3.2615321220496564e-05, "epoch": 9.226622662266227, "percentage": 46.13, "elapsed_time": "3:18:30", "remaining_time": "3:51:47", "throughput": 1486.1, "total_tokens": 17700704} {"current_steps": 83875, "total_steps": 181800, "loss": 0.0333, "lr": 3.261303517789018e-05, "epoch": 9.227172717271728, "percentage": 46.14, "elapsed_time": "3:18:31", "remaining_time": "3:51:46", "throughput": 1486.1, "total_tokens": 17701728} {"current_steps": 83880, "total_steps": 181800, "loss": 0.0127, "lr": 3.26107490651181e-05, "epoch": 9.227722772277227, "percentage": 46.14, "elapsed_time": "3:18:32", "remaining_time": "3:51:46", "throughput": 1486.1, "total_tokens": 17702784} {"current_steps": 83885, "total_steps": 181800, "loss": 0.0111, "lr": 3.26084628822014e-05, "epoch": 9.228272827282728, "percentage": 46.14, "elapsed_time": "3:18:32", "remaining_time": "3:51:45", "throughput": 1486.11, "total_tokens": 17703840} {"current_steps": 83890, "total_steps": 181800, "loss": 0.0055, "lr": 3.2606176629161146e-05, "epoch": 9.22882288228823, "percentage": 46.14, "elapsed_time": "3:18:33", "remaining_time": "3:51:44", "throughput": 1486.11, "total_tokens": 17704928} {"current_steps": 83895, "total_steps": 181800, "loss": 0.0307, "lr": 3.260389030601841e-05, "epoch": 9.229372937293729, "percentage": 46.15, "elapsed_time": "3:18:34", "remaining_time": "3:51:43", "throughput": 1486.11, "total_tokens": 17705952} {"current_steps": 83900, "total_steps": 181800, "loss": 0.0234, "lr": 3.2601603912794266e-05, "epoch": 9.22992299229923, "percentage": 46.15, "elapsed_time": "3:18:34", "remaining_time": "3:51:43", "throughput": 1486.12, "total_tokens": 17707104} {"current_steps": 83905, "total_steps": 181800, "loss": 0.0118, "lr": 3.259931744950979e-05, "epoch": 9.23047304730473, "percentage": 46.15, "elapsed_time": "3:18:35", "remaining_time": "3:51:42", "throughput": 1486.12, "total_tokens": 17708160} {"current_steps": 83910, "total_steps": 181800, "loss": 0.0215, "lr": 3.259703091618605e-05, "epoch": 9.231023102310232, "percentage": 46.16, "elapsed_time": "3:18:36", "remaining_time": "3:51:41", "throughput": 1486.12, "total_tokens": 17709184} {"current_steps": 83915, "total_steps": 181800, "loss": 0.0194, "lr": 3.259474431284412e-05, "epoch": 9.231573157315731, "percentage": 46.16, "elapsed_time": "3:18:37", "remaining_time": "3:51:40", "throughput": 1486.12, "total_tokens": 17710208} {"current_steps": 83920, "total_steps": 181800, "loss": 0.0316, "lr": 3.2592457639505083e-05, "epoch": 9.232123212321232, "percentage": 46.16, "elapsed_time": "3:18:37", "remaining_time": "3:51:40", "throughput": 1486.13, "total_tokens": 17711296} {"current_steps": 83925, "total_steps": 181800, "loss": 0.007, "lr": 3.259017089619e-05, "epoch": 9.232673267326733, "percentage": 46.16, "elapsed_time": "3:18:38", "remaining_time": "3:51:39", "throughput": 1486.14, "total_tokens": 17712416} {"current_steps": 83930, "total_steps": 181800, "loss": 0.0132, "lr": 3.2587884082919955e-05, "epoch": 9.233223322332233, "percentage": 46.17, "elapsed_time": "3:18:39", "remaining_time": "3:51:38", "throughput": 1486.14, "total_tokens": 17713440} {"current_steps": 83935, "total_steps": 181800, "loss": 0.0724, "lr": 3.258559719971603e-05, "epoch": 9.233773377337734, "percentage": 46.17, "elapsed_time": "3:18:39", "remaining_time": "3:51:38", "throughput": 1486.14, "total_tokens": 17714528} {"current_steps": 83940, "total_steps": 181800, "loss": 0.0115, "lr": 3.258331024659928e-05, "epoch": 9.234323432343235, "percentage": 46.17, "elapsed_time": "3:18:40", "remaining_time": "3:51:37", "throughput": 1486.15, "total_tokens": 17715616} {"current_steps": 83945, "total_steps": 181800, "loss": 0.0128, "lr": 3.2581023223590814e-05, "epoch": 9.234873487348734, "percentage": 46.17, "elapsed_time": "3:18:41", "remaining_time": "3:51:36", "throughput": 1486.15, "total_tokens": 17716704} {"current_steps": 83950, "total_steps": 181800, "loss": 0.0042, "lr": 3.2578736130711684e-05, "epoch": 9.235423542354235, "percentage": 46.18, "elapsed_time": "3:18:41", "remaining_time": "3:51:35", "throughput": 1486.15, "total_tokens": 17717728} {"current_steps": 83955, "total_steps": 181800, "loss": 0.1172, "lr": 3.2576448967982984e-05, "epoch": 9.235973597359736, "percentage": 46.18, "elapsed_time": "3:18:42", "remaining_time": "3:51:35", "throughput": 1486.16, "total_tokens": 17718784} {"current_steps": 83960, "total_steps": 181800, "loss": 0.002, "lr": 3.2574161735425796e-05, "epoch": 9.236523652365236, "percentage": 46.18, "elapsed_time": "3:18:43", "remaining_time": "3:51:34", "throughput": 1486.16, "total_tokens": 17719840} {"current_steps": 83965, "total_steps": 181800, "loss": 0.0106, "lr": 3.257187443306118e-05, "epoch": 9.237073707370737, "percentage": 46.19, "elapsed_time": "3:18:43", "remaining_time": "3:51:33", "throughput": 1486.16, "total_tokens": 17720896} {"current_steps": 83970, "total_steps": 181800, "loss": 0.015, "lr": 3.256958706091024e-05, "epoch": 9.237623762376238, "percentage": 46.19, "elapsed_time": "3:18:44", "remaining_time": "3:51:32", "throughput": 1486.16, "total_tokens": 17721952} {"current_steps": 83975, "total_steps": 181800, "loss": 0.01, "lr": 3.256729961899405e-05, "epoch": 9.238173817381739, "percentage": 46.19, "elapsed_time": "3:18:45", "remaining_time": "3:51:32", "throughput": 1486.17, "total_tokens": 17723040} {"current_steps": 83980, "total_steps": 181800, "loss": 0.0239, "lr": 3.256501210733368e-05, "epoch": 9.238723872387238, "percentage": 46.19, "elapsed_time": "3:18:46", "remaining_time": "3:51:31", "throughput": 1486.17, "total_tokens": 17724096} {"current_steps": 83985, "total_steps": 181800, "loss": 0.0317, "lr": 3.256272452595023e-05, "epoch": 9.23927392739274, "percentage": 46.2, "elapsed_time": "3:18:46", "remaining_time": "3:51:30", "throughput": 1486.18, "total_tokens": 17725184} {"current_steps": 83990, "total_steps": 181800, "loss": 0.029, "lr": 3.256043687486479e-05, "epoch": 9.23982398239824, "percentage": 46.2, "elapsed_time": "3:18:47", "remaining_time": "3:51:29", "throughput": 1486.18, "total_tokens": 17726272} {"current_steps": 83995, "total_steps": 181800, "loss": 0.0124, "lr": 3.255814915409841e-05, "epoch": 9.24037403740374, "percentage": 46.2, "elapsed_time": "3:18:48", "remaining_time": "3:51:29", "throughput": 1486.18, "total_tokens": 17727328} {"current_steps": 84000, "total_steps": 181800, "loss": 0.003, "lr": 3.2555861363672205e-05, "epoch": 9.24092409240924, "percentage": 46.2, "elapsed_time": "3:18:48", "remaining_time": "3:51:28", "throughput": 1486.18, "total_tokens": 17728352} {"current_steps": 84005, "total_steps": 181800, "loss": 0.0087, "lr": 3.255357350360725e-05, "epoch": 9.241474147414742, "percentage": 46.21, "elapsed_time": "3:18:49", "remaining_time": "3:51:27", "throughput": 1486.19, "total_tokens": 17729408} {"current_steps": 84010, "total_steps": 181800, "loss": 0.115, "lr": 3.2551285573924636e-05, "epoch": 9.242024202420241, "percentage": 46.21, "elapsed_time": "3:18:50", "remaining_time": "3:51:27", "throughput": 1486.18, "total_tokens": 17730400} {"current_steps": 84015, "total_steps": 181800, "loss": 0.0045, "lr": 3.254899757464545e-05, "epoch": 9.242574257425742, "percentage": 46.21, "elapsed_time": "3:18:50", "remaining_time": "3:51:26", "throughput": 1486.19, "total_tokens": 17731488} {"current_steps": 84020, "total_steps": 181800, "loss": 0.1036, "lr": 3.2546709505790765e-05, "epoch": 9.243124312431243, "percentage": 46.22, "elapsed_time": "3:18:51", "remaining_time": "3:51:25", "throughput": 1486.19, "total_tokens": 17732480} {"current_steps": 84025, "total_steps": 181800, "loss": 0.0905, "lr": 3.2544421367381686e-05, "epoch": 9.243674367436745, "percentage": 46.22, "elapsed_time": "3:18:52", "remaining_time": "3:51:24", "throughput": 1486.19, "total_tokens": 17733504} {"current_steps": 84030, "total_steps": 181800, "loss": 0.0076, "lr": 3.2542133159439294e-05, "epoch": 9.244224422442244, "percentage": 46.22, "elapsed_time": "3:18:52", "remaining_time": "3:51:24", "throughput": 1486.19, "total_tokens": 17734560} {"current_steps": 84035, "total_steps": 181800, "loss": 0.0434, "lr": 3.2539844881984674e-05, "epoch": 9.244774477447745, "percentage": 46.22, "elapsed_time": "3:18:53", "remaining_time": "3:51:23", "throughput": 1486.19, "total_tokens": 17735648} {"current_steps": 84040, "total_steps": 181800, "loss": 0.008, "lr": 3.253755653503893e-05, "epoch": 9.245324532453246, "percentage": 46.23, "elapsed_time": "3:18:54", "remaining_time": "3:51:22", "throughput": 1486.19, "total_tokens": 17736672} {"current_steps": 84045, "total_steps": 181800, "loss": 0.0136, "lr": 3.253526811862314e-05, "epoch": 9.245874587458745, "percentage": 46.23, "elapsed_time": "3:18:54", "remaining_time": "3:51:21", "throughput": 1486.2, "total_tokens": 17737792} {"current_steps": 84050, "total_steps": 181800, "loss": 0.0135, "lr": 3.253297963275841e-05, "epoch": 9.246424642464246, "percentage": 46.23, "elapsed_time": "3:18:55", "remaining_time": "3:51:21", "throughput": 1486.21, "total_tokens": 17738848} {"current_steps": 84055, "total_steps": 181800, "loss": 0.1885, "lr": 3.2530691077465804e-05, "epoch": 9.246974697469748, "percentage": 46.23, "elapsed_time": "3:18:56", "remaining_time": "3:51:20", "throughput": 1486.21, "total_tokens": 17739904} {"current_steps": 84060, "total_steps": 181800, "loss": 0.0043, "lr": 3.2528402452766436e-05, "epoch": 9.247524752475247, "percentage": 46.24, "elapsed_time": "3:18:57", "remaining_time": "3:51:19", "throughput": 1486.21, "total_tokens": 17740896} {"current_steps": 84065, "total_steps": 181800, "loss": 0.0463, "lr": 3.25261137586814e-05, "epoch": 9.248074807480748, "percentage": 46.24, "elapsed_time": "3:18:57", "remaining_time": "3:51:18", "throughput": 1486.21, "total_tokens": 17741920} {"current_steps": 84070, "total_steps": 181800, "loss": 0.0117, "lr": 3.252382499523179e-05, "epoch": 9.248624862486249, "percentage": 46.24, "elapsed_time": "3:18:58", "remaining_time": "3:51:18", "throughput": 1486.21, "total_tokens": 17742944} {"current_steps": 84075, "total_steps": 181800, "loss": 0.0083, "lr": 3.2521536162438695e-05, "epoch": 9.249174917491748, "percentage": 46.25, "elapsed_time": "3:18:59", "remaining_time": "3:51:17", "throughput": 1486.21, "total_tokens": 17744000} {"current_steps": 84080, "total_steps": 181800, "loss": 0.0083, "lr": 3.2519247260323203e-05, "epoch": 9.24972497249725, "percentage": 46.25, "elapsed_time": "3:18:59", "remaining_time": "3:51:16", "throughput": 1486.21, "total_tokens": 17745088} {"current_steps": 84085, "total_steps": 181800, "loss": 0.0056, "lr": 3.251695828890641e-05, "epoch": 9.25027502750275, "percentage": 46.25, "elapsed_time": "3:19:00", "remaining_time": "3:51:16", "throughput": 1486.21, "total_tokens": 17746112} {"current_steps": 84090, "total_steps": 181800, "loss": 0.0399, "lr": 3.2514669248209437e-05, "epoch": 9.250825082508252, "percentage": 46.25, "elapsed_time": "3:19:01", "remaining_time": "3:51:15", "throughput": 1486.21, "total_tokens": 17747168} {"current_steps": 84095, "total_steps": 181800, "loss": 0.0143, "lr": 3.251238013825335e-05, "epoch": 9.251375137513751, "percentage": 46.26, "elapsed_time": "3:19:01", "remaining_time": "3:51:14", "throughput": 1486.22, "total_tokens": 17748256} {"current_steps": 84100, "total_steps": 181800, "loss": 0.0088, "lr": 3.251009095905927e-05, "epoch": 9.251925192519252, "percentage": 46.26, "elapsed_time": "3:19:02", "remaining_time": "3:51:13", "throughput": 1486.23, "total_tokens": 17749376} {"current_steps": 84105, "total_steps": 181800, "loss": 0.0952, "lr": 3.250780171064828e-05, "epoch": 9.252475247524753, "percentage": 46.26, "elapsed_time": "3:19:03", "remaining_time": "3:51:13", "throughput": 1486.24, "total_tokens": 17750528} {"current_steps": 84110, "total_steps": 181800, "loss": 0.0382, "lr": 3.2505512393041484e-05, "epoch": 9.253025302530252, "percentage": 46.27, "elapsed_time": "3:19:03", "remaining_time": "3:51:12", "throughput": 1486.24, "total_tokens": 17751552} {"current_steps": 84115, "total_steps": 181800, "loss": 0.083, "lr": 3.2503223006259974e-05, "epoch": 9.253575357535754, "percentage": 46.27, "elapsed_time": "3:19:04", "remaining_time": "3:51:11", "throughput": 1486.24, "total_tokens": 17752576} {"current_steps": 84120, "total_steps": 181800, "loss": 0.0054, "lr": 3.250093355032488e-05, "epoch": 9.254125412541255, "percentage": 46.27, "elapsed_time": "3:19:05", "remaining_time": "3:51:10", "throughput": 1486.24, "total_tokens": 17753632} {"current_steps": 84125, "total_steps": 181800, "loss": 0.0113, "lr": 3.2498644025257257e-05, "epoch": 9.254675467546754, "percentage": 46.27, "elapsed_time": "3:19:06", "remaining_time": "3:51:10", "throughput": 1486.24, "total_tokens": 17754688} {"current_steps": 84130, "total_steps": 181800, "loss": 0.0372, "lr": 3.249635443107824e-05, "epoch": 9.255225522552255, "percentage": 46.28, "elapsed_time": "3:19:06", "remaining_time": "3:51:09", "throughput": 1486.24, "total_tokens": 17755744} {"current_steps": 84135, "total_steps": 181800, "loss": 0.0087, "lr": 3.2494064767808925e-05, "epoch": 9.255775577557756, "percentage": 46.28, "elapsed_time": "3:19:07", "remaining_time": "3:51:08", "throughput": 1486.25, "total_tokens": 17756832} {"current_steps": 84140, "total_steps": 181800, "loss": 0.0617, "lr": 3.2491775035470404e-05, "epoch": 9.256325632563255, "percentage": 46.28, "elapsed_time": "3:19:08", "remaining_time": "3:51:07", "throughput": 1486.24, "total_tokens": 17757792} {"current_steps": 84145, "total_steps": 181800, "loss": 0.0563, "lr": 3.2489485234083796e-05, "epoch": 9.256875687568757, "percentage": 46.28, "elapsed_time": "3:19:08", "remaining_time": "3:51:07", "throughput": 1486.25, "total_tokens": 17758944} {"current_steps": 84150, "total_steps": 181800, "loss": 0.1805, "lr": 3.248719536367019e-05, "epoch": 9.257425742574258, "percentage": 46.29, "elapsed_time": "3:19:09", "remaining_time": "3:51:06", "throughput": 1486.26, "total_tokens": 17760000} {"current_steps": 84155, "total_steps": 181800, "loss": 0.0201, "lr": 3.2484905424250694e-05, "epoch": 9.257975797579759, "percentage": 46.29, "elapsed_time": "3:19:10", "remaining_time": "3:51:05", "throughput": 1486.26, "total_tokens": 17761056} {"current_steps": 84160, "total_steps": 181800, "loss": 0.0064, "lr": 3.248261541584642e-05, "epoch": 9.258525852585258, "percentage": 46.29, "elapsed_time": "3:19:10", "remaining_time": "3:51:05", "throughput": 1486.26, "total_tokens": 17762048} {"current_steps": 84165, "total_steps": 181800, "loss": 0.1789, "lr": 3.248032533847848e-05, "epoch": 9.25907590759076, "percentage": 46.3, "elapsed_time": "3:19:11", "remaining_time": "3:51:04", "throughput": 1486.26, "total_tokens": 17763072} {"current_steps": 84170, "total_steps": 181800, "loss": 0.1031, "lr": 3.2478035192167956e-05, "epoch": 9.25962596259626, "percentage": 46.3, "elapsed_time": "3:19:12", "remaining_time": "3:51:03", "throughput": 1486.26, "total_tokens": 17764160} {"current_steps": 84175, "total_steps": 181800, "loss": 0.0823, "lr": 3.247574497693597e-05, "epoch": 9.26017601760176, "percentage": 46.3, "elapsed_time": "3:19:12", "remaining_time": "3:51:02", "throughput": 1486.26, "total_tokens": 17765216} {"current_steps": 84180, "total_steps": 181800, "loss": 0.0735, "lr": 3.247345469280364e-05, "epoch": 9.26072607260726, "percentage": 46.3, "elapsed_time": "3:19:13", "remaining_time": "3:51:02", "throughput": 1486.27, "total_tokens": 17766304} {"current_steps": 84185, "total_steps": 181800, "loss": 0.0328, "lr": 3.247116433979206e-05, "epoch": 9.261276127612762, "percentage": 46.31, "elapsed_time": "3:19:14", "remaining_time": "3:51:01", "throughput": 1486.27, "total_tokens": 17767360} {"current_steps": 84190, "total_steps": 181800, "loss": 0.0817, "lr": 3.246887391792235e-05, "epoch": 9.261826182618261, "percentage": 46.31, "elapsed_time": "3:19:15", "remaining_time": "3:51:00", "throughput": 1486.28, "total_tokens": 17768448} {"current_steps": 84195, "total_steps": 181800, "loss": 0.0183, "lr": 3.24665834272156e-05, "epoch": 9.262376237623762, "percentage": 46.31, "elapsed_time": "3:19:15", "remaining_time": "3:50:59", "throughput": 1486.28, "total_tokens": 17769504} {"current_steps": 84200, "total_steps": 181800, "loss": 0.0634, "lr": 3.246429286769293e-05, "epoch": 9.262926292629263, "percentage": 46.31, "elapsed_time": "3:19:16", "remaining_time": "3:50:59", "throughput": 1486.28, "total_tokens": 17770560} {"current_steps": 84205, "total_steps": 181800, "loss": 0.0528, "lr": 3.246200223937547e-05, "epoch": 9.263476347634764, "percentage": 46.32, "elapsed_time": "3:19:17", "remaining_time": "3:50:58", "throughput": 1486.29, "total_tokens": 17771680} {"current_steps": 84210, "total_steps": 181800, "loss": 0.021, "lr": 3.245971154228431e-05, "epoch": 9.264026402640264, "percentage": 46.32, "elapsed_time": "3:19:17", "remaining_time": "3:50:57", "throughput": 1486.29, "total_tokens": 17772768} {"current_steps": 84215, "total_steps": 181800, "loss": 0.0729, "lr": 3.245742077644057e-05, "epoch": 9.264576457645765, "percentage": 46.32, "elapsed_time": "3:19:18", "remaining_time": "3:50:57", "throughput": 1486.3, "total_tokens": 17773824} {"current_steps": 84220, "total_steps": 181800, "loss": 0.0057, "lr": 3.245512994186536e-05, "epoch": 9.265126512651266, "percentage": 46.33, "elapsed_time": "3:19:19", "remaining_time": "3:50:56", "throughput": 1486.3, "total_tokens": 17774880} {"current_steps": 84225, "total_steps": 181800, "loss": 0.0938, "lr": 3.24528390385798e-05, "epoch": 9.265676567656765, "percentage": 46.33, "elapsed_time": "3:19:19", "remaining_time": "3:50:55", "throughput": 1486.31, "total_tokens": 17776000} {"current_steps": 84230, "total_steps": 181800, "loss": 0.1078, "lr": 3.245054806660499e-05, "epoch": 9.266226622662266, "percentage": 46.33, "elapsed_time": "3:19:20", "remaining_time": "3:50:54", "throughput": 1486.31, "total_tokens": 17777024} {"current_steps": 84235, "total_steps": 181800, "loss": 0.0336, "lr": 3.244825702596205e-05, "epoch": 9.266776677667767, "percentage": 46.33, "elapsed_time": "3:19:21", "remaining_time": "3:50:54", "throughput": 1486.31, "total_tokens": 17778048} {"current_steps": 84240, "total_steps": 181800, "loss": 0.0049, "lr": 3.244596591667211e-05, "epoch": 9.267326732673267, "percentage": 46.34, "elapsed_time": "3:19:21", "remaining_time": "3:50:53", "throughput": 1486.3, "total_tokens": 17779008} {"current_steps": 84245, "total_steps": 181800, "loss": 0.0101, "lr": 3.244367473875627e-05, "epoch": 9.267876787678768, "percentage": 46.34, "elapsed_time": "3:19:22", "remaining_time": "3:50:52", "throughput": 1486.3, "total_tokens": 17780032} {"current_steps": 84250, "total_steps": 181800, "loss": 0.0454, "lr": 3.244138349223565e-05, "epoch": 9.268426842684269, "percentage": 46.34, "elapsed_time": "3:19:23", "remaining_time": "3:50:51", "throughput": 1486.3, "total_tokens": 17781088} {"current_steps": 84255, "total_steps": 181800, "loss": 0.0171, "lr": 3.243909217713137e-05, "epoch": 9.268976897689768, "percentage": 46.34, "elapsed_time": "3:19:23", "remaining_time": "3:50:51", "throughput": 1486.3, "total_tokens": 17782112} {"current_steps": 84260, "total_steps": 181800, "loss": 0.0333, "lr": 3.243680079346455e-05, "epoch": 9.26952695269527, "percentage": 46.35, "elapsed_time": "3:19:24", "remaining_time": "3:50:50", "throughput": 1486.3, "total_tokens": 17783136} {"current_steps": 84265, "total_steps": 181800, "loss": 0.0192, "lr": 3.24345093412563e-05, "epoch": 9.27007700770077, "percentage": 46.35, "elapsed_time": "3:19:25", "remaining_time": "3:50:49", "throughput": 1486.31, "total_tokens": 17784192} {"current_steps": 84270, "total_steps": 181800, "loss": 0.004, "lr": 3.243221782052775e-05, "epoch": 9.270627062706271, "percentage": 46.35, "elapsed_time": "3:19:26", "remaining_time": "3:50:48", "throughput": 1486.31, "total_tokens": 17785248} {"current_steps": 84275, "total_steps": 181800, "loss": 0.0628, "lr": 3.242992623130001e-05, "epoch": 9.27117711771177, "percentage": 46.36, "elapsed_time": "3:19:26", "remaining_time": "3:50:48", "throughput": 1486.31, "total_tokens": 17786304} {"current_steps": 84280, "total_steps": 181800, "loss": 0.0279, "lr": 3.242763457359421e-05, "epoch": 9.271727172717272, "percentage": 46.36, "elapsed_time": "3:19:27", "remaining_time": "3:50:47", "throughput": 1486.32, "total_tokens": 17787392} {"current_steps": 84285, "total_steps": 181800, "loss": 0.0119, "lr": 3.2425342847431464e-05, "epoch": 9.272277227722773, "percentage": 46.36, "elapsed_time": "3:19:28", "remaining_time": "3:50:46", "throughput": 1486.32, "total_tokens": 17788416} {"current_steps": 84290, "total_steps": 181800, "loss": 0.0085, "lr": 3.24230510528329e-05, "epoch": 9.272827282728272, "percentage": 46.36, "elapsed_time": "3:19:28", "remaining_time": "3:50:45", "throughput": 1486.33, "total_tokens": 17789568} {"current_steps": 84295, "total_steps": 181800, "loss": 0.0091, "lr": 3.242075918981963e-05, "epoch": 9.273377337733773, "percentage": 46.37, "elapsed_time": "3:19:29", "remaining_time": "3:50:45", "throughput": 1486.33, "total_tokens": 17790656} {"current_steps": 84300, "total_steps": 181800, "loss": 0.0204, "lr": 3.241846725841279e-05, "epoch": 9.273927392739274, "percentage": 46.37, "elapsed_time": "3:19:30", "remaining_time": "3:50:44", "throughput": 1486.34, "total_tokens": 17791776} {"current_steps": 84305, "total_steps": 181800, "loss": 0.0191, "lr": 3.241617525863349e-05, "epoch": 9.274477447744774, "percentage": 46.37, "elapsed_time": "3:19:30", "remaining_time": "3:50:43", "throughput": 1486.34, "total_tokens": 17792800} {"current_steps": 84310, "total_steps": 181800, "loss": 0.1198, "lr": 3.241388319050287e-05, "epoch": 9.275027502750275, "percentage": 46.38, "elapsed_time": "3:19:31", "remaining_time": "3:50:43", "throughput": 1486.34, "total_tokens": 17793792} {"current_steps": 84315, "total_steps": 181800, "loss": 0.0265, "lr": 3.241159105404203e-05, "epoch": 9.275577557755776, "percentage": 46.38, "elapsed_time": "3:19:32", "remaining_time": "3:50:42", "throughput": 1486.34, "total_tokens": 17794848} {"current_steps": 84320, "total_steps": 181800, "loss": 0.025, "lr": 3.240929884927213e-05, "epoch": 9.276127612761275, "percentage": 46.38, "elapsed_time": "3:19:32", "remaining_time": "3:50:41", "throughput": 1486.35, "total_tokens": 17795936} {"current_steps": 84325, "total_steps": 181800, "loss": 0.0773, "lr": 3.2407006576214274e-05, "epoch": 9.276677667766776, "percentage": 46.38, "elapsed_time": "3:19:33", "remaining_time": "3:50:40", "throughput": 1486.34, "total_tokens": 17796928} {"current_steps": 84330, "total_steps": 181800, "loss": 0.0048, "lr": 3.240471423488958e-05, "epoch": 9.277227722772277, "percentage": 46.39, "elapsed_time": "3:19:34", "remaining_time": "3:50:40", "throughput": 1486.35, "total_tokens": 17798080} {"current_steps": 84335, "total_steps": 181800, "loss": 0.0508, "lr": 3.24024218253192e-05, "epoch": 9.277777777777779, "percentage": 46.39, "elapsed_time": "3:19:35", "remaining_time": "3:50:39", "throughput": 1486.36, "total_tokens": 17799168} {"current_steps": 84340, "total_steps": 181800, "loss": 0.0191, "lr": 3.240012934752425e-05, "epoch": 9.278327832783278, "percentage": 46.39, "elapsed_time": "3:19:35", "remaining_time": "3:50:38", "throughput": 1486.36, "total_tokens": 17800160} {"current_steps": 84345, "total_steps": 181800, "loss": 0.0813, "lr": 3.2397836801525847e-05, "epoch": 9.278877887788779, "percentage": 46.39, "elapsed_time": "3:19:36", "remaining_time": "3:50:37", "throughput": 1486.36, "total_tokens": 17801216} {"current_steps": 84350, "total_steps": 181800, "loss": 0.0331, "lr": 3.239554418734515e-05, "epoch": 9.27942794279428, "percentage": 46.4, "elapsed_time": "3:19:37", "remaining_time": "3:50:37", "throughput": 1486.37, "total_tokens": 17802336} {"current_steps": 84355, "total_steps": 181800, "loss": 0.0735, "lr": 3.2393251505003265e-05, "epoch": 9.27997799779978, "percentage": 46.4, "elapsed_time": "3:19:37", "remaining_time": "3:50:36", "throughput": 1486.37, "total_tokens": 17803360} {"current_steps": 84360, "total_steps": 181800, "loss": 0.0575, "lr": 3.239095875452132e-05, "epoch": 9.28052805280528, "percentage": 46.4, "elapsed_time": "3:19:38", "remaining_time": "3:50:35", "throughput": 1486.37, "total_tokens": 17804416} {"current_steps": 84365, "total_steps": 181800, "loss": 0.0262, "lr": 3.238866593592046e-05, "epoch": 9.281078107810782, "percentage": 46.41, "elapsed_time": "3:19:39", "remaining_time": "3:50:34", "throughput": 1486.37, "total_tokens": 17805472} {"current_steps": 84370, "total_steps": 181800, "loss": 0.0402, "lr": 3.2386373049221815e-05, "epoch": 9.281628162816281, "percentage": 46.41, "elapsed_time": "3:19:39", "remaining_time": "3:50:34", "throughput": 1486.37, "total_tokens": 17806528} {"current_steps": 84375, "total_steps": 181800, "loss": 0.0058, "lr": 3.2384080094446504e-05, "epoch": 9.282178217821782, "percentage": 46.41, "elapsed_time": "3:19:40", "remaining_time": "3:50:33", "throughput": 1486.38, "total_tokens": 17807584} {"current_steps": 84380, "total_steps": 181800, "loss": 0.0231, "lr": 3.238178707161568e-05, "epoch": 9.282728272827283, "percentage": 46.41, "elapsed_time": "3:19:41", "remaining_time": "3:50:32", "throughput": 1486.37, "total_tokens": 17808576} {"current_steps": 84385, "total_steps": 181800, "loss": 0.0527, "lr": 3.2379493980750466e-05, "epoch": 9.283278327832782, "percentage": 46.42, "elapsed_time": "3:19:41", "remaining_time": "3:50:32", "throughput": 1486.38, "total_tokens": 17809664} {"current_steps": 84390, "total_steps": 181800, "loss": 0.0602, "lr": 3.237720082187199e-05, "epoch": 9.283828382838283, "percentage": 46.42, "elapsed_time": "3:19:42", "remaining_time": "3:50:31", "throughput": 1486.38, "total_tokens": 17810752} {"current_steps": 84395, "total_steps": 181800, "loss": 0.0464, "lr": 3.23749075950014e-05, "epoch": 9.284378437843785, "percentage": 46.42, "elapsed_time": "3:19:43", "remaining_time": "3:50:30", "throughput": 1486.38, "total_tokens": 17811776} {"current_steps": 84400, "total_steps": 181800, "loss": 0.0232, "lr": 3.237261430015982e-05, "epoch": 9.284928492849286, "percentage": 46.42, "elapsed_time": "3:19:43", "remaining_time": "3:50:29", "throughput": 1486.38, "total_tokens": 17812800} {"current_steps": 84405, "total_steps": 181800, "loss": 0.0063, "lr": 3.23703209373684e-05, "epoch": 9.285478547854785, "percentage": 46.43, "elapsed_time": "3:19:44", "remaining_time": "3:50:29", "throughput": 1486.38, "total_tokens": 17813824} {"current_steps": 84410, "total_steps": 181800, "loss": 0.158, "lr": 3.2368027506648264e-05, "epoch": 9.286028602860286, "percentage": 46.43, "elapsed_time": "3:19:45", "remaining_time": "3:50:28", "throughput": 1486.39, "total_tokens": 17814944} {"current_steps": 84415, "total_steps": 181800, "loss": 0.0082, "lr": 3.2365734008020555e-05, "epoch": 9.286578657865787, "percentage": 46.43, "elapsed_time": "3:19:46", "remaining_time": "3:50:27", "throughput": 1486.4, "total_tokens": 17816032} {"current_steps": 84420, "total_steps": 181800, "loss": 0.005, "lr": 3.23634404415064e-05, "epoch": 9.287128712871286, "percentage": 46.44, "elapsed_time": "3:19:46", "remaining_time": "3:50:26", "throughput": 1486.39, "total_tokens": 17817056} {"current_steps": 84425, "total_steps": 181800, "loss": 0.0127, "lr": 3.236114680712696e-05, "epoch": 9.287678767876788, "percentage": 46.44, "elapsed_time": "3:19:47", "remaining_time": "3:50:26", "throughput": 1486.39, "total_tokens": 17818048} {"current_steps": 84430, "total_steps": 181800, "loss": 0.0025, "lr": 3.235885310490336e-05, "epoch": 9.288228822882289, "percentage": 46.44, "elapsed_time": "3:19:48", "remaining_time": "3:50:25", "throughput": 1486.39, "total_tokens": 17819072} {"current_steps": 84435, "total_steps": 181800, "loss": 0.0119, "lr": 3.235655933485674e-05, "epoch": 9.288778877887788, "percentage": 46.44, "elapsed_time": "3:19:48", "remaining_time": "3:50:24", "throughput": 1486.39, "total_tokens": 17820096} {"current_steps": 84440, "total_steps": 181800, "loss": 0.068, "lr": 3.235426549700824e-05, "epoch": 9.289328932893289, "percentage": 46.45, "elapsed_time": "3:19:49", "remaining_time": "3:50:24", "throughput": 1486.39, "total_tokens": 17821120} {"current_steps": 84445, "total_steps": 181800, "loss": 0.0133, "lr": 3.235197159137901e-05, "epoch": 9.28987898789879, "percentage": 46.45, "elapsed_time": "3:19:50", "remaining_time": "3:50:23", "throughput": 1486.39, "total_tokens": 17822144} {"current_steps": 84450, "total_steps": 181800, "loss": 0.0293, "lr": 3.234967761799018e-05, "epoch": 9.290429042904291, "percentage": 46.45, "elapsed_time": "3:19:50", "remaining_time": "3:50:22", "throughput": 1486.4, "total_tokens": 17823232} {"current_steps": 84455, "total_steps": 181800, "loss": 0.0322, "lr": 3.2347383576862907e-05, "epoch": 9.29097909790979, "percentage": 46.45, "elapsed_time": "3:19:51", "remaining_time": "3:50:21", "throughput": 1486.4, "total_tokens": 17824256} {"current_steps": 84460, "total_steps": 181800, "loss": 0.0096, "lr": 3.234508946801831e-05, "epoch": 9.291529152915292, "percentage": 46.46, "elapsed_time": "3:19:52", "remaining_time": "3:50:21", "throughput": 1486.4, "total_tokens": 17825344} {"current_steps": 84465, "total_steps": 181800, "loss": 0.0167, "lr": 3.234279529147756e-05, "epoch": 9.292079207920793, "percentage": 46.46, "elapsed_time": "3:19:52", "remaining_time": "3:50:20", "throughput": 1486.4, "total_tokens": 17826336} {"current_steps": 84470, "total_steps": 181800, "loss": 0.0173, "lr": 3.234050104726179e-05, "epoch": 9.292629262926292, "percentage": 46.46, "elapsed_time": "3:19:53", "remaining_time": "3:50:19", "throughput": 1486.4, "total_tokens": 17827360} {"current_steps": 84475, "total_steps": 181800, "loss": 0.0145, "lr": 3.233820673539214e-05, "epoch": 9.293179317931793, "percentage": 46.47, "elapsed_time": "3:19:54", "remaining_time": "3:50:18", "throughput": 1486.4, "total_tokens": 17828384} {"current_steps": 84480, "total_steps": 181800, "loss": 0.006, "lr": 3.233591235588976e-05, "epoch": 9.293729372937294, "percentage": 46.47, "elapsed_time": "3:19:55", "remaining_time": "3:50:18", "throughput": 1486.4, "total_tokens": 17829440} {"current_steps": 84485, "total_steps": 181800, "loss": 0.0202, "lr": 3.23336179087758e-05, "epoch": 9.294279427942794, "percentage": 46.47, "elapsed_time": "3:19:55", "remaining_time": "3:50:17", "throughput": 1486.41, "total_tokens": 17830528} {"current_steps": 84490, "total_steps": 181800, "loss": 0.0675, "lr": 3.233132339407139e-05, "epoch": 9.294829482948295, "percentage": 46.47, "elapsed_time": "3:19:56", "remaining_time": "3:50:16", "throughput": 1486.41, "total_tokens": 17831552} {"current_steps": 84495, "total_steps": 181800, "loss": 0.0099, "lr": 3.23290288117977e-05, "epoch": 9.295379537953796, "percentage": 46.48, "elapsed_time": "3:19:57", "remaining_time": "3:50:15", "throughput": 1486.41, "total_tokens": 17832640} {"current_steps": 84500, "total_steps": 181800, "loss": 0.0173, "lr": 3.232673416197588e-05, "epoch": 9.295929592959295, "percentage": 46.48, "elapsed_time": "3:19:57", "remaining_time": "3:50:15", "throughput": 1486.41, "total_tokens": 17833664} {"current_steps": 84505, "total_steps": 181800, "loss": 0.0055, "lr": 3.232443944462704e-05, "epoch": 9.296479647964796, "percentage": 46.48, "elapsed_time": "3:19:58", "remaining_time": "3:50:14", "throughput": 1486.42, "total_tokens": 17834752} {"current_steps": 84510, "total_steps": 181800, "loss": 0.0078, "lr": 3.2322144659772374e-05, "epoch": 9.297029702970297, "percentage": 46.49, "elapsed_time": "3:19:59", "remaining_time": "3:50:13", "throughput": 1486.42, "total_tokens": 17835840} {"current_steps": 84515, "total_steps": 181800, "loss": 0.0548, "lr": 3.2319849807433014e-05, "epoch": 9.297579757975798, "percentage": 46.49, "elapsed_time": "3:19:59", "remaining_time": "3:50:12", "throughput": 1486.42, "total_tokens": 17836832} {"current_steps": 84520, "total_steps": 181800, "loss": 0.0299, "lr": 3.2317554887630096e-05, "epoch": 9.298129812981298, "percentage": 46.49, "elapsed_time": "3:20:00", "remaining_time": "3:50:12", "throughput": 1486.42, "total_tokens": 17837824} {"current_steps": 84525, "total_steps": 181800, "loss": 0.0042, "lr": 3.231525990038481e-05, "epoch": 9.298679867986799, "percentage": 46.49, "elapsed_time": "3:20:01", "remaining_time": "3:50:11", "throughput": 1486.41, "total_tokens": 17838784} {"current_steps": 84530, "total_steps": 181800, "loss": 0.0541, "lr": 3.2312964845718266e-05, "epoch": 9.2992299229923, "percentage": 46.5, "elapsed_time": "3:20:01", "remaining_time": "3:50:10", "throughput": 1486.42, "total_tokens": 17839840} {"current_steps": 84535, "total_steps": 181800, "loss": 0.0384, "lr": 3.231066972365164e-05, "epoch": 9.2997799779978, "percentage": 46.5, "elapsed_time": "3:20:02", "remaining_time": "3:50:10", "throughput": 1486.42, "total_tokens": 17840896} {"current_steps": 84540, "total_steps": 181800, "loss": 0.0185, "lr": 3.2308374534206075e-05, "epoch": 9.3003300330033, "percentage": 46.5, "elapsed_time": "3:20:03", "remaining_time": "3:50:09", "throughput": 1486.43, "total_tokens": 17842016} {"current_steps": 84545, "total_steps": 181800, "loss": 0.0965, "lr": 3.2306079277402736e-05, "epoch": 9.300880088008801, "percentage": 46.5, "elapsed_time": "3:20:03", "remaining_time": "3:50:08", "throughput": 1486.43, "total_tokens": 17843104} {"current_steps": 84550, "total_steps": 181800, "loss": 0.0627, "lr": 3.2303783953262765e-05, "epoch": 9.3014301430143, "percentage": 46.51, "elapsed_time": "3:20:04", "remaining_time": "3:50:07", "throughput": 1486.44, "total_tokens": 17844224} {"current_steps": 84555, "total_steps": 181800, "loss": 0.0114, "lr": 3.2301488561807324e-05, "epoch": 9.301980198019802, "percentage": 46.51, "elapsed_time": "3:20:05", "remaining_time": "3:50:07", "throughput": 1486.44, "total_tokens": 17845248} {"current_steps": 84560, "total_steps": 181800, "loss": 0.0016, "lr": 3.229919310305757e-05, "epoch": 9.302530253025303, "percentage": 46.51, "elapsed_time": "3:20:06", "remaining_time": "3:50:06", "throughput": 1486.45, "total_tokens": 17846336} {"current_steps": 84565, "total_steps": 181800, "loss": 0.0029, "lr": 3.229689757703465e-05, "epoch": 9.303080308030804, "percentage": 46.52, "elapsed_time": "3:20:06", "remaining_time": "3:50:05", "throughput": 1486.45, "total_tokens": 17847456} {"current_steps": 84570, "total_steps": 181800, "loss": 0.0102, "lr": 3.229460198375973e-05, "epoch": 9.303630363036303, "percentage": 46.52, "elapsed_time": "3:20:07", "remaining_time": "3:50:04", "throughput": 1486.46, "total_tokens": 17848512} {"current_steps": 84575, "total_steps": 181800, "loss": 0.0629, "lr": 3.229230632325395e-05, "epoch": 9.304180418041804, "percentage": 46.52, "elapsed_time": "3:20:08", "remaining_time": "3:50:04", "throughput": 1486.46, "total_tokens": 17849568} {"current_steps": 84580, "total_steps": 181800, "loss": 0.0268, "lr": 3.22900105955385e-05, "epoch": 9.304730473047305, "percentage": 46.52, "elapsed_time": "3:20:08", "remaining_time": "3:50:03", "throughput": 1486.46, "total_tokens": 17850656} {"current_steps": 84585, "total_steps": 181800, "loss": 0.0556, "lr": 3.228771480063451e-05, "epoch": 9.305280528052805, "percentage": 46.53, "elapsed_time": "3:20:09", "remaining_time": "3:50:02", "throughput": 1486.47, "total_tokens": 17851712} {"current_steps": 84590, "total_steps": 181800, "loss": 0.0025, "lr": 3.2285418938563155e-05, "epoch": 9.305830583058306, "percentage": 46.53, "elapsed_time": "3:20:10", "remaining_time": "3:50:01", "throughput": 1486.47, "total_tokens": 17852800} {"current_steps": 84595, "total_steps": 181800, "loss": 0.1553, "lr": 3.228312300934559e-05, "epoch": 9.306380638063807, "percentage": 46.53, "elapsed_time": "3:20:10", "remaining_time": "3:50:01", "throughput": 1486.47, "total_tokens": 17853856} {"current_steps": 84600, "total_steps": 181800, "loss": 0.0064, "lr": 3.228082701300297e-05, "epoch": 9.306930693069306, "percentage": 46.53, "elapsed_time": "3:20:11", "remaining_time": "3:50:00", "throughput": 1486.48, "total_tokens": 17854944} {"current_steps": 84605, "total_steps": 181800, "loss": 0.0039, "lr": 3.227853094955646e-05, "epoch": 9.307480748074807, "percentage": 46.54, "elapsed_time": "3:20:12", "remaining_time": "3:49:59", "throughput": 1486.48, "total_tokens": 17856032} {"current_steps": 84610, "total_steps": 181800, "loss": 0.0617, "lr": 3.227623481902723e-05, "epoch": 9.308030803080309, "percentage": 46.54, "elapsed_time": "3:20:12", "remaining_time": "3:49:59", "throughput": 1486.48, "total_tokens": 17857024} {"current_steps": 84615, "total_steps": 181800, "loss": 0.0055, "lr": 3.2273938621436435e-05, "epoch": 9.308580858085808, "percentage": 46.54, "elapsed_time": "3:20:13", "remaining_time": "3:49:58", "throughput": 1486.49, "total_tokens": 17858144} {"current_steps": 84620, "total_steps": 181800, "loss": 0.1066, "lr": 3.227164235680523e-05, "epoch": 9.309130913091309, "percentage": 46.55, "elapsed_time": "3:20:14", "remaining_time": "3:49:57", "throughput": 1486.49, "total_tokens": 17859200} {"current_steps": 84625, "total_steps": 181800, "loss": 0.0698, "lr": 3.22693460251548e-05, "epoch": 9.30968096809681, "percentage": 46.55, "elapsed_time": "3:20:15", "remaining_time": "3:49:56", "throughput": 1486.5, "total_tokens": 17860288} {"current_steps": 84630, "total_steps": 181800, "loss": 0.0915, "lr": 3.226704962650629e-05, "epoch": 9.310231023102311, "percentage": 46.55, "elapsed_time": "3:20:15", "remaining_time": "3:49:56", "throughput": 1486.5, "total_tokens": 17861312} {"current_steps": 84635, "total_steps": 181800, "loss": 0.0353, "lr": 3.226475316088086e-05, "epoch": 9.31078107810781, "percentage": 46.55, "elapsed_time": "3:20:16", "remaining_time": "3:49:55", "throughput": 1486.5, "total_tokens": 17862368} {"current_steps": 84640, "total_steps": 181800, "loss": 0.0109, "lr": 3.22624566282997e-05, "epoch": 9.311331133113312, "percentage": 46.56, "elapsed_time": "3:20:17", "remaining_time": "3:49:54", "throughput": 1486.5, "total_tokens": 17863392} {"current_steps": 84645, "total_steps": 181800, "loss": 0.0134, "lr": 3.226016002878396e-05, "epoch": 9.311881188118813, "percentage": 46.56, "elapsed_time": "3:20:17", "remaining_time": "3:49:53", "throughput": 1486.51, "total_tokens": 17864512} {"current_steps": 84650, "total_steps": 181800, "loss": 0.0783, "lr": 3.225786336235479e-05, "epoch": 9.312431243124312, "percentage": 46.56, "elapsed_time": "3:20:18", "remaining_time": "3:49:53", "throughput": 1486.51, "total_tokens": 17865600} {"current_steps": 84655, "total_steps": 181800, "loss": 0.0773, "lr": 3.22555666290334e-05, "epoch": 9.312981298129813, "percentage": 46.56, "elapsed_time": "3:20:19", "remaining_time": "3:49:52", "throughput": 1486.51, "total_tokens": 17866656} {"current_steps": 84660, "total_steps": 181800, "loss": 0.0573, "lr": 3.225326982884093e-05, "epoch": 9.313531353135314, "percentage": 46.57, "elapsed_time": "3:20:19", "remaining_time": "3:49:51", "throughput": 1486.51, "total_tokens": 17867680} {"current_steps": 84665, "total_steps": 181800, "loss": 0.0024, "lr": 3.225097296179854e-05, "epoch": 9.314081408140813, "percentage": 46.57, "elapsed_time": "3:20:20", "remaining_time": "3:49:51", "throughput": 1486.52, "total_tokens": 17868768} {"current_steps": 84670, "total_steps": 181800, "loss": 0.0244, "lr": 3.2248676027927424e-05, "epoch": 9.314631463146315, "percentage": 46.57, "elapsed_time": "3:20:21", "remaining_time": "3:49:50", "throughput": 1486.52, "total_tokens": 17869760} {"current_steps": 84675, "total_steps": 181800, "loss": 0.0098, "lr": 3.224637902724874e-05, "epoch": 9.315181518151816, "percentage": 46.58, "elapsed_time": "3:20:21", "remaining_time": "3:49:49", "throughput": 1486.52, "total_tokens": 17870784} {"current_steps": 84680, "total_steps": 181800, "loss": 0.0144, "lr": 3.2244081959783644e-05, "epoch": 9.315731573157315, "percentage": 46.58, "elapsed_time": "3:20:22", "remaining_time": "3:49:48", "throughput": 1486.52, "total_tokens": 17871808} {"current_steps": 84685, "total_steps": 181800, "loss": 0.0178, "lr": 3.2241784825553326e-05, "epoch": 9.316281628162816, "percentage": 46.58, "elapsed_time": "3:20:23", "remaining_time": "3:49:48", "throughput": 1486.52, "total_tokens": 17872896} {"current_steps": 84690, "total_steps": 181800, "loss": 0.0633, "lr": 3.223948762457896e-05, "epoch": 9.316831683168317, "percentage": 46.58, "elapsed_time": "3:20:24", "remaining_time": "3:49:47", "throughput": 1486.52, "total_tokens": 17873952} {"current_steps": 84695, "total_steps": 181800, "loss": 0.0036, "lr": 3.22371903568817e-05, "epoch": 9.317381738173818, "percentage": 46.59, "elapsed_time": "3:20:24", "remaining_time": "3:49:46", "throughput": 1486.53, "total_tokens": 17875072} {"current_steps": 84700, "total_steps": 181800, "loss": 0.0184, "lr": 3.2234893022482734e-05, "epoch": 9.317931793179318, "percentage": 46.59, "elapsed_time": "3:20:25", "remaining_time": "3:49:45", "throughput": 1486.54, "total_tokens": 17876160} {"current_steps": 84705, "total_steps": 181800, "loss": 0.0122, "lr": 3.223259562140324e-05, "epoch": 9.318481848184819, "percentage": 46.59, "elapsed_time": "3:20:26", "remaining_time": "3:49:45", "throughput": 1486.54, "total_tokens": 17877248} {"current_steps": 84710, "total_steps": 181800, "loss": 0.0883, "lr": 3.223029815366437e-05, "epoch": 9.31903190319032, "percentage": 46.6, "elapsed_time": "3:20:26", "remaining_time": "3:49:44", "throughput": 1486.54, "total_tokens": 17878272} {"current_steps": 84715, "total_steps": 181800, "loss": 0.0067, "lr": 3.222800061928732e-05, "epoch": 9.319581958195819, "percentage": 46.6, "elapsed_time": "3:20:27", "remaining_time": "3:49:43", "throughput": 1486.54, "total_tokens": 17879296} {"current_steps": 84720, "total_steps": 181800, "loss": 0.0052, "lr": 3.222570301829325e-05, "epoch": 9.32013201320132, "percentage": 46.6, "elapsed_time": "3:20:28", "remaining_time": "3:49:42", "throughput": 1486.54, "total_tokens": 17880320} {"current_steps": 84725, "total_steps": 181800, "loss": 0.0789, "lr": 3.222340535070334e-05, "epoch": 9.320682068206821, "percentage": 46.6, "elapsed_time": "3:20:28", "remaining_time": "3:49:42", "throughput": 1486.55, "total_tokens": 17881440} {"current_steps": 84730, "total_steps": 181800, "loss": 0.0075, "lr": 3.222110761653878e-05, "epoch": 9.32123212321232, "percentage": 46.61, "elapsed_time": "3:20:29", "remaining_time": "3:49:41", "throughput": 1486.55, "total_tokens": 17882528} {"current_steps": 84735, "total_steps": 181800, "loss": 0.0617, "lr": 3.221880981582073e-05, "epoch": 9.321782178217822, "percentage": 46.61, "elapsed_time": "3:20:30", "remaining_time": "3:49:40", "throughput": 1486.55, "total_tokens": 17883520} {"current_steps": 84740, "total_steps": 181800, "loss": 0.0096, "lr": 3.2216511948570374e-05, "epoch": 9.322332233223323, "percentage": 46.61, "elapsed_time": "3:20:30", "remaining_time": "3:49:40", "throughput": 1486.55, "total_tokens": 17884544} {"current_steps": 84745, "total_steps": 181800, "loss": 0.0124, "lr": 3.2214214014808886e-05, "epoch": 9.322882288228822, "percentage": 46.61, "elapsed_time": "3:20:31", "remaining_time": "3:49:39", "throughput": 1486.55, "total_tokens": 17885568} {"current_steps": 84750, "total_steps": 181800, "loss": 0.0039, "lr": 3.221191601455745e-05, "epoch": 9.323432343234323, "percentage": 46.62, "elapsed_time": "3:20:32", "remaining_time": "3:49:38", "throughput": 1486.53, "total_tokens": 17886624} {"current_steps": 84755, "total_steps": 181800, "loss": 0.1607, "lr": 3.2209617947837245e-05, "epoch": 9.323982398239824, "percentage": 46.62, "elapsed_time": "3:20:33", "remaining_time": "3:49:38", "throughput": 1486.53, "total_tokens": 17887680} {"current_steps": 84760, "total_steps": 181800, "loss": 0.0023, "lr": 3.220731981466946e-05, "epoch": 9.324532453245325, "percentage": 46.62, "elapsed_time": "3:20:33", "remaining_time": "3:49:37", "throughput": 1486.53, "total_tokens": 17888736} {"current_steps": 84765, "total_steps": 181800, "loss": 0.0107, "lr": 3.2205021615075256e-05, "epoch": 9.325082508250825, "percentage": 46.63, "elapsed_time": "3:20:34", "remaining_time": "3:49:36", "throughput": 1486.54, "total_tokens": 17889792} {"current_steps": 84770, "total_steps": 181800, "loss": 0.003, "lr": 3.220272334907583e-05, "epoch": 9.325632563256326, "percentage": 46.63, "elapsed_time": "3:20:35", "remaining_time": "3:49:35", "throughput": 1486.54, "total_tokens": 17890848} {"current_steps": 84775, "total_steps": 181800, "loss": 0.0293, "lr": 3.220042501669236e-05, "epoch": 9.326182618261827, "percentage": 46.63, "elapsed_time": "3:20:35", "remaining_time": "3:49:35", "throughput": 1486.55, "total_tokens": 17891936} {"current_steps": 84780, "total_steps": 181800, "loss": 0.0157, "lr": 3.2198126617946026e-05, "epoch": 9.326732673267326, "percentage": 46.63, "elapsed_time": "3:20:36", "remaining_time": "3:49:34", "throughput": 1486.55, "total_tokens": 17893024} {"current_steps": 84785, "total_steps": 181800, "loss": 0.0535, "lr": 3.2195828152858016e-05, "epoch": 9.327282728272827, "percentage": 46.64, "elapsed_time": "3:20:37", "remaining_time": "3:49:33", "throughput": 1486.55, "total_tokens": 17894080} {"current_steps": 84790, "total_steps": 181800, "loss": 0.0269, "lr": 3.219352962144951e-05, "epoch": 9.327832783278328, "percentage": 46.64, "elapsed_time": "3:20:37", "remaining_time": "3:49:32", "throughput": 1486.56, "total_tokens": 17895136} {"current_steps": 84795, "total_steps": 181800, "loss": 0.0043, "lr": 3.2191231023741686e-05, "epoch": 9.328382838283828, "percentage": 46.64, "elapsed_time": "3:20:38", "remaining_time": "3:49:32", "throughput": 1486.57, "total_tokens": 17896288} {"current_steps": 84800, "total_steps": 181800, "loss": 0.0221, "lr": 3.2188932359755744e-05, "epoch": 9.328932893289329, "percentage": 46.64, "elapsed_time": "3:20:39", "remaining_time": "3:49:31", "throughput": 1486.57, "total_tokens": 17897376} {"current_steps": 84805, "total_steps": 181800, "loss": 0.0618, "lr": 3.218663362951286e-05, "epoch": 9.32948294829483, "percentage": 46.65, "elapsed_time": "3:20:40", "remaining_time": "3:49:30", "throughput": 1486.58, "total_tokens": 17898464} {"current_steps": 84810, "total_steps": 181800, "loss": 0.0175, "lr": 3.218433483303422e-05, "epoch": 9.33003300330033, "percentage": 46.65, "elapsed_time": "3:20:40", "remaining_time": "3:49:29", "throughput": 1486.58, "total_tokens": 17899552} {"current_steps": 84815, "total_steps": 181800, "loss": 0.0384, "lr": 3.2182035970341016e-05, "epoch": 9.33058305830583, "percentage": 46.65, "elapsed_time": "3:20:41", "remaining_time": "3:49:29", "throughput": 1486.58, "total_tokens": 17900576} {"current_steps": 84820, "total_steps": 181800, "loss": 0.051, "lr": 3.217973704145443e-05, "epoch": 9.331133113311331, "percentage": 46.66, "elapsed_time": "3:20:42", "remaining_time": "3:49:28", "throughput": 1486.58, "total_tokens": 17901632} {"current_steps": 84825, "total_steps": 181800, "loss": 0.103, "lr": 3.217743804639565e-05, "epoch": 9.331683168316832, "percentage": 46.66, "elapsed_time": "3:20:42", "remaining_time": "3:49:27", "throughput": 1486.58, "total_tokens": 17902656} {"current_steps": 84830, "total_steps": 181800, "loss": 0.1923, "lr": 3.2175138985185885e-05, "epoch": 9.332233223322332, "percentage": 46.66, "elapsed_time": "3:20:43", "remaining_time": "3:49:27", "throughput": 1486.59, "total_tokens": 17903712} {"current_steps": 84835, "total_steps": 181800, "loss": 0.0092, "lr": 3.217283985784629e-05, "epoch": 9.332783278327833, "percentage": 46.66, "elapsed_time": "3:20:44", "remaining_time": "3:49:26", "throughput": 1486.58, "total_tokens": 17904704} {"current_steps": 84840, "total_steps": 181800, "loss": 0.0055, "lr": 3.217054066439807e-05, "epoch": 9.333333333333334, "percentage": 46.67, "elapsed_time": "3:20:44", "remaining_time": "3:49:25", "throughput": 1486.58, "total_tokens": 17905728} {"current_steps": 84845, "total_steps": 181800, "loss": 0.068, "lr": 3.216824140486242e-05, "epoch": 9.333883388338833, "percentage": 46.67, "elapsed_time": "3:20:45", "remaining_time": "3:49:24", "throughput": 1486.58, "total_tokens": 17906752} {"current_steps": 84850, "total_steps": 181800, "loss": 0.0194, "lr": 3.216594207926054e-05, "epoch": 9.334433443344334, "percentage": 46.67, "elapsed_time": "3:20:46", "remaining_time": "3:49:24", "throughput": 1486.59, "total_tokens": 17907840} {"current_steps": 84855, "total_steps": 181800, "loss": 0.0055, "lr": 3.21636426876136e-05, "epoch": 9.334983498349835, "percentage": 46.67, "elapsed_time": "3:20:46", "remaining_time": "3:49:23", "throughput": 1486.59, "total_tokens": 17908928} {"current_steps": 84860, "total_steps": 181800, "loss": 0.156, "lr": 3.216134322994281e-05, "epoch": 9.335533553355335, "percentage": 46.68, "elapsed_time": "3:20:47", "remaining_time": "3:49:22", "throughput": 1486.59, "total_tokens": 17909952} {"current_steps": 84865, "total_steps": 181800, "loss": 0.0247, "lr": 3.2159043706269345e-05, "epoch": 9.336083608360836, "percentage": 46.68, "elapsed_time": "3:20:48", "remaining_time": "3:49:21", "throughput": 1486.59, "total_tokens": 17910944} {"current_steps": 84870, "total_steps": 181800, "loss": 0.0102, "lr": 3.215674411661441e-05, "epoch": 9.336633663366337, "percentage": 46.68, "elapsed_time": "3:20:49", "remaining_time": "3:49:21", "throughput": 1486.59, "total_tokens": 17912000} {"current_steps": 84875, "total_steps": 181800, "loss": 0.064, "lr": 3.215444446099921e-05, "epoch": 9.337183718371838, "percentage": 46.69, "elapsed_time": "3:20:49", "remaining_time": "3:49:20", "throughput": 1486.6, "total_tokens": 17913120} {"current_steps": 84880, "total_steps": 181800, "loss": 0.0293, "lr": 3.215214473944492e-05, "epoch": 9.337733773377337, "percentage": 46.69, "elapsed_time": "3:20:50", "remaining_time": "3:49:19", "throughput": 1486.61, "total_tokens": 17914240} {"current_steps": 84885, "total_steps": 181800, "loss": 0.0054, "lr": 3.214984495197275e-05, "epoch": 9.338283828382838, "percentage": 46.69, "elapsed_time": "3:20:51", "remaining_time": "3:49:18", "throughput": 1486.61, "total_tokens": 17915264} {"current_steps": 84890, "total_steps": 181800, "loss": 0.0623, "lr": 3.2147545098603885e-05, "epoch": 9.33883388338834, "percentage": 46.69, "elapsed_time": "3:20:51", "remaining_time": "3:49:18", "throughput": 1486.62, "total_tokens": 17916352} {"current_steps": 84895, "total_steps": 181800, "loss": 0.002, "lr": 3.2145245179359526e-05, "epoch": 9.339383938393839, "percentage": 46.7, "elapsed_time": "3:20:52", "remaining_time": "3:49:17", "throughput": 1486.62, "total_tokens": 17917440} {"current_steps": 84900, "total_steps": 181800, "loss": 0.0051, "lr": 3.214294519426087e-05, "epoch": 9.33993399339934, "percentage": 46.7, "elapsed_time": "3:20:53", "remaining_time": "3:49:16", "throughput": 1486.62, "total_tokens": 17918496} {"current_steps": 84905, "total_steps": 181800, "loss": 0.0808, "lr": 3.214064514332913e-05, "epoch": 9.340484048404841, "percentage": 46.7, "elapsed_time": "3:20:53", "remaining_time": "3:49:16", "throughput": 1486.63, "total_tokens": 17919616} {"current_steps": 84910, "total_steps": 181800, "loss": 0.1135, "lr": 3.213834502658547e-05, "epoch": 9.34103410341034, "percentage": 46.71, "elapsed_time": "3:20:54", "remaining_time": "3:49:15", "throughput": 1486.64, "total_tokens": 17920672} {"current_steps": 84915, "total_steps": 181800, "loss": 0.027, "lr": 3.213604484405112e-05, "epoch": 9.341584158415841, "percentage": 46.71, "elapsed_time": "3:20:55", "remaining_time": "3:49:14", "throughput": 1486.64, "total_tokens": 17921792} {"current_steps": 84920, "total_steps": 181800, "loss": 0.0019, "lr": 3.213374459574727e-05, "epoch": 9.342134213421343, "percentage": 46.71, "elapsed_time": "3:20:55", "remaining_time": "3:49:13", "throughput": 1486.65, "total_tokens": 17922848} {"current_steps": 84925, "total_steps": 181800, "loss": 0.0958, "lr": 3.2131444281695114e-05, "epoch": 9.342684268426842, "percentage": 46.71, "elapsed_time": "3:20:56", "remaining_time": "3:49:13", "throughput": 1486.64, "total_tokens": 17923840} {"current_steps": 84930, "total_steps": 181800, "loss": 0.0087, "lr": 3.212914390191586e-05, "epoch": 9.343234323432343, "percentage": 46.72, "elapsed_time": "3:20:57", "remaining_time": "3:49:12", "throughput": 1486.65, "total_tokens": 17924896} {"current_steps": 84935, "total_steps": 181800, "loss": 0.0076, "lr": 3.2126843456430713e-05, "epoch": 9.343784378437844, "percentage": 46.72, "elapsed_time": "3:20:57", "remaining_time": "3:49:11", "throughput": 1486.65, "total_tokens": 17925920} {"current_steps": 84940, "total_steps": 181800, "loss": 0.0147, "lr": 3.212454294526085e-05, "epoch": 9.344334433443345, "percentage": 46.72, "elapsed_time": "3:20:58", "remaining_time": "3:49:10", "throughput": 1486.65, "total_tokens": 17926944} {"current_steps": 84945, "total_steps": 181800, "loss": 0.1025, "lr": 3.2122242368427515e-05, "epoch": 9.344884488448844, "percentage": 46.72, "elapsed_time": "3:20:59", "remaining_time": "3:49:10", "throughput": 1486.65, "total_tokens": 17927936} {"current_steps": 84950, "total_steps": 181800, "loss": 0.0083, "lr": 3.211994172595189e-05, "epoch": 9.345434543454346, "percentage": 46.73, "elapsed_time": "3:21:00", "remaining_time": "3:49:09", "throughput": 1486.65, "total_tokens": 17928960} {"current_steps": 84955, "total_steps": 181800, "loss": 0.0259, "lr": 3.211764101785516e-05, "epoch": 9.345984598459847, "percentage": 46.73, "elapsed_time": "3:21:00", "remaining_time": "3:49:08", "throughput": 1486.65, "total_tokens": 17930016} {"current_steps": 84960, "total_steps": 181800, "loss": 0.0299, "lr": 3.211534024415856e-05, "epoch": 9.346534653465346, "percentage": 46.73, "elapsed_time": "3:21:01", "remaining_time": "3:49:07", "throughput": 1486.65, "total_tokens": 17931040} {"current_steps": 84965, "total_steps": 181800, "loss": 0.0871, "lr": 3.211303940488328e-05, "epoch": 9.347084708470847, "percentage": 46.74, "elapsed_time": "3:21:02", "remaining_time": "3:49:07", "throughput": 1486.66, "total_tokens": 17932160} {"current_steps": 84970, "total_steps": 181800, "loss": 0.0234, "lr": 3.211073850005053e-05, "epoch": 9.347634763476348, "percentage": 46.74, "elapsed_time": "3:21:02", "remaining_time": "3:49:06", "throughput": 1486.66, "total_tokens": 17933184} {"current_steps": 84975, "total_steps": 181800, "loss": 0.0118, "lr": 3.2108437529681524e-05, "epoch": 9.348184818481847, "percentage": 46.74, "elapsed_time": "3:21:03", "remaining_time": "3:49:05", "throughput": 1486.65, "total_tokens": 17934176} {"current_steps": 84980, "total_steps": 181800, "loss": 0.0645, "lr": 3.210613649379745e-05, "epoch": 9.348734873487349, "percentage": 46.74, "elapsed_time": "3:21:04", "remaining_time": "3:49:04", "throughput": 1486.65, "total_tokens": 17935200} {"current_steps": 84985, "total_steps": 181800, "loss": 0.0319, "lr": 3.210383539241952e-05, "epoch": 9.34928492849285, "percentage": 46.75, "elapsed_time": "3:21:04", "remaining_time": "3:49:04", "throughput": 1486.66, "total_tokens": 17936320} {"current_steps": 84990, "total_steps": 181800, "loss": 0.0346, "lr": 3.2101534225568964e-05, "epoch": 9.34983498349835, "percentage": 46.75, "elapsed_time": "3:21:05", "remaining_time": "3:49:03", "throughput": 1486.67, "total_tokens": 17937440} {"current_steps": 84995, "total_steps": 181800, "loss": 0.0737, "lr": 3.2099232993266965e-05, "epoch": 9.35038503850385, "percentage": 46.75, "elapsed_time": "3:21:06", "remaining_time": "3:49:02", "throughput": 1486.67, "total_tokens": 17938432} {"current_steps": 85000, "total_steps": 181800, "loss": 0.0106, "lr": 3.209693169553474e-05, "epoch": 9.350935093509351, "percentage": 46.75, "elapsed_time": "3:21:06", "remaining_time": "3:49:02", "throughput": 1486.67, "total_tokens": 17939488} {"current_steps": 85005, "total_steps": 181800, "loss": 0.0785, "lr": 3.209463033239351e-05, "epoch": 9.351485148514852, "percentage": 46.76, "elapsed_time": "3:21:07", "remaining_time": "3:49:01", "throughput": 1486.67, "total_tokens": 17940512} {"current_steps": 85010, "total_steps": 181800, "loss": 0.1098, "lr": 3.2092328903864475e-05, "epoch": 9.352035203520352, "percentage": 46.76, "elapsed_time": "3:21:08", "remaining_time": "3:49:00", "throughput": 1486.67, "total_tokens": 17941568} {"current_steps": 85015, "total_steps": 181800, "loss": 0.0187, "lr": 3.209002740996884e-05, "epoch": 9.352585258525853, "percentage": 46.76, "elapsed_time": "3:21:08", "remaining_time": "3:48:59", "throughput": 1486.67, "total_tokens": 17942592} {"current_steps": 85020, "total_steps": 181800, "loss": 0.0055, "lr": 3.2087725850727837e-05, "epoch": 9.353135313531354, "percentage": 46.77, "elapsed_time": "3:21:09", "remaining_time": "3:48:59", "throughput": 1486.68, "total_tokens": 17943648} {"current_steps": 85025, "total_steps": 181800, "loss": 0.0055, "lr": 3.208542422616265e-05, "epoch": 9.353685368536853, "percentage": 46.77, "elapsed_time": "3:21:10", "remaining_time": "3:48:58", "throughput": 1486.67, "total_tokens": 17944640} {"current_steps": 85030, "total_steps": 181800, "loss": 0.0803, "lr": 3.208312253629451e-05, "epoch": 9.354235423542354, "percentage": 46.77, "elapsed_time": "3:21:11", "remaining_time": "3:48:57", "throughput": 1486.67, "total_tokens": 17945664} {"current_steps": 85035, "total_steps": 181800, "loss": 0.1115, "lr": 3.208082078114464e-05, "epoch": 9.354785478547855, "percentage": 46.77, "elapsed_time": "3:21:11", "remaining_time": "3:48:56", "throughput": 1486.68, "total_tokens": 17946720} {"current_steps": 85040, "total_steps": 181800, "loss": 0.0061, "lr": 3.2078518960734236e-05, "epoch": 9.355335533553355, "percentage": 46.78, "elapsed_time": "3:21:12", "remaining_time": "3:48:56", "throughput": 1486.68, "total_tokens": 17947808} {"current_steps": 85045, "total_steps": 181800, "loss": 0.0117, "lr": 3.207621707508452e-05, "epoch": 9.355885588558856, "percentage": 46.78, "elapsed_time": "3:21:13", "remaining_time": "3:48:55", "throughput": 1486.69, "total_tokens": 17948864} {"current_steps": 85050, "total_steps": 181800, "loss": 0.0079, "lr": 3.207391512421671e-05, "epoch": 9.356435643564357, "percentage": 46.78, "elapsed_time": "3:21:13", "remaining_time": "3:48:54", "throughput": 1486.69, "total_tokens": 17949920} {"current_steps": 85055, "total_steps": 181800, "loss": 0.0052, "lr": 3.207161310815201e-05, "epoch": 9.356985698569858, "percentage": 46.78, "elapsed_time": "3:21:14", "remaining_time": "3:48:53", "throughput": 1486.69, "total_tokens": 17950944} {"current_steps": 85060, "total_steps": 181800, "loss": 0.0061, "lr": 3.206931102691165e-05, "epoch": 9.357535753575357, "percentage": 46.79, "elapsed_time": "3:21:15", "remaining_time": "3:48:53", "throughput": 1486.69, "total_tokens": 17952000} {"current_steps": 85065, "total_steps": 181800, "loss": 0.0161, "lr": 3.206700888051685e-05, "epoch": 9.358085808580858, "percentage": 46.79, "elapsed_time": "3:21:15", "remaining_time": "3:48:52", "throughput": 1486.69, "total_tokens": 17953024} {"current_steps": 85070, "total_steps": 181800, "loss": 0.0107, "lr": 3.206470666898881e-05, "epoch": 9.35863586358636, "percentage": 46.79, "elapsed_time": "3:21:16", "remaining_time": "3:48:51", "throughput": 1486.69, "total_tokens": 17954080} {"current_steps": 85075, "total_steps": 181800, "loss": 0.0068, "lr": 3.206240439234876e-05, "epoch": 9.359185918591859, "percentage": 46.8, "elapsed_time": "3:21:17", "remaining_time": "3:48:51", "throughput": 1486.7, "total_tokens": 17955136} {"current_steps": 85080, "total_steps": 181800, "loss": 0.0252, "lr": 3.206010205061792e-05, "epoch": 9.35973597359736, "percentage": 46.8, "elapsed_time": "3:21:17", "remaining_time": "3:48:50", "throughput": 1486.7, "total_tokens": 17956160} {"current_steps": 85085, "total_steps": 181800, "loss": 0.0102, "lr": 3.20577996438175e-05, "epoch": 9.36028602860286, "percentage": 46.8, "elapsed_time": "3:21:18", "remaining_time": "3:48:49", "throughput": 1486.7, "total_tokens": 17957184} {"current_steps": 85090, "total_steps": 181800, "loss": 0.0333, "lr": 3.205549717196873e-05, "epoch": 9.36083608360836, "percentage": 46.8, "elapsed_time": "3:21:19", "remaining_time": "3:48:48", "throughput": 1486.7, "total_tokens": 17958208} {"current_steps": 85095, "total_steps": 181800, "loss": 0.0105, "lr": 3.205319463509284e-05, "epoch": 9.361386138613861, "percentage": 46.81, "elapsed_time": "3:21:19", "remaining_time": "3:48:48", "throughput": 1486.7, "total_tokens": 17959328} {"current_steps": 85100, "total_steps": 181800, "loss": 0.0638, "lr": 3.205089203321103e-05, "epoch": 9.361936193619362, "percentage": 46.81, "elapsed_time": "3:21:20", "remaining_time": "3:48:47", "throughput": 1486.71, "total_tokens": 17960448} {"current_steps": 85105, "total_steps": 181800, "loss": 0.0509, "lr": 3.2048589366344535e-05, "epoch": 9.362486248624862, "percentage": 46.81, "elapsed_time": "3:21:21", "remaining_time": "3:48:46", "throughput": 1486.72, "total_tokens": 17961536} {"current_steps": 85110, "total_steps": 181800, "loss": 0.0385, "lr": 3.204628663451457e-05, "epoch": 9.363036303630363, "percentage": 46.82, "elapsed_time": "3:21:22", "remaining_time": "3:48:45", "throughput": 1486.72, "total_tokens": 17962624} {"current_steps": 85115, "total_steps": 181800, "loss": 0.0879, "lr": 3.2043983837742365e-05, "epoch": 9.363586358635864, "percentage": 46.82, "elapsed_time": "3:21:22", "remaining_time": "3:48:45", "throughput": 1486.73, "total_tokens": 17963744} {"current_steps": 85120, "total_steps": 181800, "loss": 0.0984, "lr": 3.2041680976049144e-05, "epoch": 9.364136413641365, "percentage": 46.82, "elapsed_time": "3:21:23", "remaining_time": "3:48:44", "throughput": 1486.74, "total_tokens": 17964896} {"current_steps": 85125, "total_steps": 181800, "loss": 0.0175, "lr": 3.203937804945612e-05, "epoch": 9.364686468646864, "percentage": 46.82, "elapsed_time": "3:21:24", "remaining_time": "3:48:43", "throughput": 1486.75, "total_tokens": 17965984} {"current_steps": 85130, "total_steps": 181800, "loss": 0.0804, "lr": 3.203707505798453e-05, "epoch": 9.365236523652365, "percentage": 46.83, "elapsed_time": "3:21:24", "remaining_time": "3:48:42", "throughput": 1486.74, "total_tokens": 17966976} {"current_steps": 85135, "total_steps": 181800, "loss": 0.0099, "lr": 3.20347720016556e-05, "epoch": 9.365786578657866, "percentage": 46.83, "elapsed_time": "3:21:25", "remaining_time": "3:48:42", "throughput": 1486.75, "total_tokens": 17968032} {"current_steps": 85140, "total_steps": 181800, "loss": 0.0945, "lr": 3.203246888049055e-05, "epoch": 9.366336633663366, "percentage": 46.83, "elapsed_time": "3:21:26", "remaining_time": "3:48:41", "throughput": 1486.75, "total_tokens": 17969056} {"current_steps": 85145, "total_steps": 181800, "loss": 0.0199, "lr": 3.2030165694510606e-05, "epoch": 9.366886688668867, "percentage": 46.83, "elapsed_time": "3:21:26", "remaining_time": "3:48:40", "throughput": 1486.75, "total_tokens": 17970112} {"current_steps": 85150, "total_steps": 181800, "loss": 0.0069, "lr": 3.2027862443737e-05, "epoch": 9.367436743674368, "percentage": 46.84, "elapsed_time": "3:21:27", "remaining_time": "3:48:40", "throughput": 1486.75, "total_tokens": 17971200} {"current_steps": 85155, "total_steps": 181800, "loss": 0.0271, "lr": 3.2025559128190964e-05, "epoch": 9.367986798679867, "percentage": 46.84, "elapsed_time": "3:21:28", "remaining_time": "3:48:39", "throughput": 1486.76, "total_tokens": 17972288} {"current_steps": 85160, "total_steps": 181800, "loss": 0.0622, "lr": 3.20232557478937e-05, "epoch": 9.368536853685368, "percentage": 46.84, "elapsed_time": "3:21:28", "remaining_time": "3:48:38", "throughput": 1486.76, "total_tokens": 17973376} {"current_steps": 85165, "total_steps": 181800, "loss": 0.0114, "lr": 3.202095230286649e-05, "epoch": 9.36908690869087, "percentage": 46.85, "elapsed_time": "3:21:29", "remaining_time": "3:48:37", "throughput": 1486.77, "total_tokens": 17974464} {"current_steps": 85170, "total_steps": 181800, "loss": 0.0608, "lr": 3.201864879313051e-05, "epoch": 9.369636963696369, "percentage": 46.85, "elapsed_time": "3:21:30", "remaining_time": "3:48:37", "throughput": 1486.77, "total_tokens": 17975488} {"current_steps": 85175, "total_steps": 181800, "loss": 0.0061, "lr": 3.2016345218707014e-05, "epoch": 9.37018701870187, "percentage": 46.85, "elapsed_time": "3:21:31", "remaining_time": "3:48:36", "throughput": 1486.76, "total_tokens": 17976480} {"current_steps": 85180, "total_steps": 181800, "loss": 0.0695, "lr": 3.2014041579617234e-05, "epoch": 9.370737073707371, "percentage": 46.85, "elapsed_time": "3:21:31", "remaining_time": "3:48:35", "throughput": 1486.77, "total_tokens": 17977536} {"current_steps": 85185, "total_steps": 181800, "loss": 0.005, "lr": 3.20117378758824e-05, "epoch": 9.371287128712872, "percentage": 46.86, "elapsed_time": "3:21:32", "remaining_time": "3:48:34", "throughput": 1486.76, "total_tokens": 17978528} {"current_steps": 85190, "total_steps": 181800, "loss": 0.0045, "lr": 3.2009434107523736e-05, "epoch": 9.371837183718371, "percentage": 46.86, "elapsed_time": "3:21:33", "remaining_time": "3:48:34", "throughput": 1486.77, "total_tokens": 17979648} {"current_steps": 85195, "total_steps": 181800, "loss": 0.1184, "lr": 3.200713027456249e-05, "epoch": 9.372387238723872, "percentage": 46.86, "elapsed_time": "3:21:33", "remaining_time": "3:48:33", "throughput": 1486.78, "total_tokens": 17980768} {"current_steps": 85200, "total_steps": 181800, "loss": 0.0147, "lr": 3.200482637701988e-05, "epoch": 9.372937293729374, "percentage": 46.86, "elapsed_time": "3:21:34", "remaining_time": "3:48:32", "throughput": 1486.78, "total_tokens": 17981760} {"current_steps": 85205, "total_steps": 181800, "loss": 0.0812, "lr": 3.200252241491714e-05, "epoch": 9.373487348734873, "percentage": 46.87, "elapsed_time": "3:21:35", "remaining_time": "3:48:31", "throughput": 1486.78, "total_tokens": 17982816} {"current_steps": 85210, "total_steps": 181800, "loss": 0.0081, "lr": 3.200021838827553e-05, "epoch": 9.374037403740374, "percentage": 46.87, "elapsed_time": "3:21:35", "remaining_time": "3:48:31", "throughput": 1486.78, "total_tokens": 17983904} {"current_steps": 85215, "total_steps": 181800, "loss": 0.0041, "lr": 3.1997914297116246e-05, "epoch": 9.374587458745875, "percentage": 46.87, "elapsed_time": "3:21:36", "remaining_time": "3:48:30", "throughput": 1486.79, "total_tokens": 17984992} {"current_steps": 85220, "total_steps": 181800, "loss": 0.0054, "lr": 3.1995610141460557e-05, "epoch": 9.375137513751374, "percentage": 46.88, "elapsed_time": "3:21:37", "remaining_time": "3:48:29", "throughput": 1486.79, "total_tokens": 17985984} {"current_steps": 85225, "total_steps": 181800, "loss": 0.0364, "lr": 3.199330592132969e-05, "epoch": 9.375687568756875, "percentage": 46.88, "elapsed_time": "3:21:37", "remaining_time": "3:48:29", "throughput": 1486.79, "total_tokens": 17987072} {"current_steps": 85230, "total_steps": 181800, "loss": 0.024, "lr": 3.1991001636744863e-05, "epoch": 9.376237623762377, "percentage": 46.88, "elapsed_time": "3:21:38", "remaining_time": "3:48:28", "throughput": 1486.8, "total_tokens": 17988224} {"current_steps": 85235, "total_steps": 181800, "loss": 0.0087, "lr": 3.198869728772734e-05, "epoch": 9.376787678767876, "percentage": 46.88, "elapsed_time": "3:21:39", "remaining_time": "3:48:27", "throughput": 1486.81, "total_tokens": 17989280} {"current_steps": 85240, "total_steps": 181800, "loss": 0.012, "lr": 3.198639287429834e-05, "epoch": 9.377337733773377, "percentage": 46.89, "elapsed_time": "3:21:39", "remaining_time": "3:48:26", "throughput": 1486.81, "total_tokens": 17990304} {"current_steps": 85245, "total_steps": 181800, "loss": 0.0374, "lr": 3.198408839647911e-05, "epoch": 9.377887788778878, "percentage": 46.89, "elapsed_time": "3:21:40", "remaining_time": "3:48:26", "throughput": 1486.81, "total_tokens": 17991392} {"current_steps": 85250, "total_steps": 181800, "loss": 0.0038, "lr": 3.1981783854290894e-05, "epoch": 9.37843784378438, "percentage": 46.89, "elapsed_time": "3:21:41", "remaining_time": "3:48:25", "throughput": 1486.81, "total_tokens": 17992448} {"current_steps": 85255, "total_steps": 181800, "loss": 0.0511, "lr": 3.1979479247754925e-05, "epoch": 9.378987898789878, "percentage": 46.89, "elapsed_time": "3:21:42", "remaining_time": "3:48:24", "throughput": 1486.82, "total_tokens": 17993504} {"current_steps": 85260, "total_steps": 181800, "loss": 0.0385, "lr": 3.197717457689244e-05, "epoch": 9.37953795379538, "percentage": 46.9, "elapsed_time": "3:21:42", "remaining_time": "3:48:23", "throughput": 1486.83, "total_tokens": 17994624} {"current_steps": 85265, "total_steps": 181800, "loss": 0.1576, "lr": 3.19748698417247e-05, "epoch": 9.38008800880088, "percentage": 46.9, "elapsed_time": "3:21:43", "remaining_time": "3:48:23", "throughput": 1486.83, "total_tokens": 17995744} {"current_steps": 85270, "total_steps": 181800, "loss": 0.0566, "lr": 3.197256504227292e-05, "epoch": 9.38063806380638, "percentage": 46.9, "elapsed_time": "3:21:44", "remaining_time": "3:48:22", "throughput": 1486.83, "total_tokens": 17996768} {"current_steps": 85275, "total_steps": 181800, "loss": 0.0458, "lr": 3.1970260178558345e-05, "epoch": 9.381188118811881, "percentage": 46.91, "elapsed_time": "3:21:44", "remaining_time": "3:48:21", "throughput": 1486.83, "total_tokens": 17997824} {"current_steps": 85280, "total_steps": 181800, "loss": 0.0229, "lr": 3.196795525060223e-05, "epoch": 9.381738173817382, "percentage": 46.91, "elapsed_time": "3:21:45", "remaining_time": "3:48:20", "throughput": 1486.84, "total_tokens": 17998880} {"current_steps": 85285, "total_steps": 181800, "loss": 0.2458, "lr": 3.196565025842583e-05, "epoch": 9.382288228822881, "percentage": 46.91, "elapsed_time": "3:21:46", "remaining_time": "3:48:20", "throughput": 1486.85, "total_tokens": 18000032} {"current_steps": 85290, "total_steps": 181800, "loss": 0.0157, "lr": 3.196334520205037e-05, "epoch": 9.382838283828383, "percentage": 46.91, "elapsed_time": "3:21:46", "remaining_time": "3:48:19", "throughput": 1486.86, "total_tokens": 18001152} {"current_steps": 85295, "total_steps": 181800, "loss": 0.0318, "lr": 3.196104008149708e-05, "epoch": 9.383388338833884, "percentage": 46.92, "elapsed_time": "3:21:47", "remaining_time": "3:48:18", "throughput": 1486.86, "total_tokens": 18002208} {"current_steps": 85300, "total_steps": 181800, "loss": 0.0268, "lr": 3.1958734896787245e-05, "epoch": 9.383938393839385, "percentage": 46.92, "elapsed_time": "3:21:48", "remaining_time": "3:48:18", "throughput": 1486.87, "total_tokens": 18003328} {"current_steps": 85305, "total_steps": 181800, "loss": 0.0156, "lr": 3.1956429647942085e-05, "epoch": 9.384488448844884, "percentage": 46.92, "elapsed_time": "3:21:48", "remaining_time": "3:48:17", "throughput": 1486.87, "total_tokens": 18004384} {"current_steps": 85310, "total_steps": 181800, "loss": 0.0876, "lr": 3.195412433498284e-05, "epoch": 9.385038503850385, "percentage": 46.93, "elapsed_time": "3:21:49", "remaining_time": "3:48:16", "throughput": 1486.87, "total_tokens": 18005440} {"current_steps": 85315, "total_steps": 181800, "loss": 0.0071, "lr": 3.195181895793078e-05, "epoch": 9.385588558855886, "percentage": 46.93, "elapsed_time": "3:21:50", "remaining_time": "3:48:15", "throughput": 1486.87, "total_tokens": 18006496} {"current_steps": 85320, "total_steps": 181800, "loss": 0.0118, "lr": 3.1949513516807136e-05, "epoch": 9.386138613861386, "percentage": 46.93, "elapsed_time": "3:21:50", "remaining_time": "3:48:15", "throughput": 1486.87, "total_tokens": 18007488} {"current_steps": 85325, "total_steps": 181800, "loss": 0.0024, "lr": 3.194720801163316e-05, "epoch": 9.386688668866887, "percentage": 46.93, "elapsed_time": "3:21:51", "remaining_time": "3:48:14", "throughput": 1486.87, "total_tokens": 18008544} {"current_steps": 85330, "total_steps": 181800, "loss": 0.0213, "lr": 3.19449024424301e-05, "epoch": 9.387238723872388, "percentage": 46.94, "elapsed_time": "3:21:52", "remaining_time": "3:48:13", "throughput": 1486.87, "total_tokens": 18009536} {"current_steps": 85335, "total_steps": 181800, "loss": 0.0991, "lr": 3.194259680921921e-05, "epoch": 9.387788778877887, "percentage": 46.94, "elapsed_time": "3:21:53", "remaining_time": "3:48:12", "throughput": 1486.87, "total_tokens": 18010624} {"current_steps": 85340, "total_steps": 181800, "loss": 0.116, "lr": 3.194029111202174e-05, "epoch": 9.388338833883388, "percentage": 46.94, "elapsed_time": "3:21:53", "remaining_time": "3:48:12", "throughput": 1486.88, "total_tokens": 18011712} {"current_steps": 85345, "total_steps": 181800, "loss": 0.0661, "lr": 3.1937985350858926e-05, "epoch": 9.38888888888889, "percentage": 46.94, "elapsed_time": "3:21:54", "remaining_time": "3:48:11", "throughput": 1486.88, "total_tokens": 18012768} {"current_steps": 85350, "total_steps": 181800, "loss": 0.0248, "lr": 3.193567952575204e-05, "epoch": 9.389438943894389, "percentage": 46.95, "elapsed_time": "3:21:55", "remaining_time": "3:48:10", "throughput": 1486.89, "total_tokens": 18013824} {"current_steps": 85355, "total_steps": 181800, "loss": 0.0445, "lr": 3.193337363672232e-05, "epoch": 9.38998899889989, "percentage": 46.95, "elapsed_time": "3:21:55", "remaining_time": "3:48:10", "throughput": 1486.88, "total_tokens": 18014848} {"current_steps": 85360, "total_steps": 181800, "loss": 0.0041, "lr": 3.193106768379102e-05, "epoch": 9.39053905390539, "percentage": 46.95, "elapsed_time": "3:21:56", "remaining_time": "3:48:09", "throughput": 1486.89, "total_tokens": 18015904} {"current_steps": 85365, "total_steps": 181800, "loss": 0.0138, "lr": 3.19287616669794e-05, "epoch": 9.391089108910892, "percentage": 46.96, "elapsed_time": "3:21:57", "remaining_time": "3:48:08", "throughput": 1486.9, "total_tokens": 18017024} {"current_steps": 85370, "total_steps": 181800, "loss": 0.0046, "lr": 3.192645558630871e-05, "epoch": 9.391639163916391, "percentage": 46.96, "elapsed_time": "3:21:57", "remaining_time": "3:48:07", "throughput": 1486.9, "total_tokens": 18018080} {"current_steps": 85375, "total_steps": 181800, "loss": 0.0693, "lr": 3.19241494418002e-05, "epoch": 9.392189218921892, "percentage": 46.96, "elapsed_time": "3:21:58", "remaining_time": "3:48:07", "throughput": 1486.9, "total_tokens": 18019104} {"current_steps": 85380, "total_steps": 181800, "loss": 0.0352, "lr": 3.1921843233475126e-05, "epoch": 9.392739273927393, "percentage": 46.96, "elapsed_time": "3:21:59", "remaining_time": "3:48:06", "throughput": 1486.9, "total_tokens": 18020160} {"current_steps": 85385, "total_steps": 181800, "loss": 0.0431, "lr": 3.191953696135474e-05, "epoch": 9.393289328932893, "percentage": 46.97, "elapsed_time": "3:21:59", "remaining_time": "3:48:05", "throughput": 1486.9, "total_tokens": 18021184} {"current_steps": 85390, "total_steps": 181800, "loss": 0.0429, "lr": 3.1917230625460304e-05, "epoch": 9.393839383938394, "percentage": 46.97, "elapsed_time": "3:22:00", "remaining_time": "3:48:04", "throughput": 1486.9, "total_tokens": 18022208} {"current_steps": 85395, "total_steps": 181800, "loss": 0.0119, "lr": 3.191492422581307e-05, "epoch": 9.394389438943895, "percentage": 46.97, "elapsed_time": "3:22:01", "remaining_time": "3:48:04", "throughput": 1486.9, "total_tokens": 18023296} {"current_steps": 85400, "total_steps": 181800, "loss": 0.0393, "lr": 3.191261776243431e-05, "epoch": 9.394939493949394, "percentage": 46.97, "elapsed_time": "3:22:02", "remaining_time": "3:48:03", "throughput": 1486.91, "total_tokens": 18024352} {"current_steps": 85405, "total_steps": 181800, "loss": 0.1191, "lr": 3.191031123534526e-05, "epoch": 9.395489548954895, "percentage": 46.98, "elapsed_time": "3:22:02", "remaining_time": "3:48:02", "throughput": 1486.9, "total_tokens": 18025312} {"current_steps": 85410, "total_steps": 181800, "loss": 0.0858, "lr": 3.190800464456719e-05, "epoch": 9.396039603960396, "percentage": 46.98, "elapsed_time": "3:22:03", "remaining_time": "3:48:01", "throughput": 1486.9, "total_tokens": 18026336} {"current_steps": 85415, "total_steps": 181800, "loss": 0.0627, "lr": 3.1905697990121356e-05, "epoch": 9.396589658965897, "percentage": 46.98, "elapsed_time": "3:22:04", "remaining_time": "3:48:01", "throughput": 1486.91, "total_tokens": 18027392} {"current_steps": 85420, "total_steps": 181800, "loss": 0.0078, "lr": 3.190339127202901e-05, "epoch": 9.397139713971397, "percentage": 46.99, "elapsed_time": "3:22:04", "remaining_time": "3:48:00", "throughput": 1486.91, "total_tokens": 18028448} {"current_steps": 85425, "total_steps": 181800, "loss": 0.0306, "lr": 3.1901084490311427e-05, "epoch": 9.397689768976898, "percentage": 46.99, "elapsed_time": "3:22:05", "remaining_time": "3:47:59", "throughput": 1486.91, "total_tokens": 18029536} {"current_steps": 85430, "total_steps": 181800, "loss": 0.0185, "lr": 3.189877764498986e-05, "epoch": 9.398239823982399, "percentage": 46.99, "elapsed_time": "3:22:06", "remaining_time": "3:47:59", "throughput": 1486.92, "total_tokens": 18030624} {"current_steps": 85435, "total_steps": 181800, "loss": 0.0124, "lr": 3.189647073608556e-05, "epoch": 9.398789878987898, "percentage": 46.99, "elapsed_time": "3:22:06", "remaining_time": "3:47:58", "throughput": 1486.92, "total_tokens": 18031616} {"current_steps": 85440, "total_steps": 181800, "loss": 0.0521, "lr": 3.189416376361981e-05, "epoch": 9.3993399339934, "percentage": 47.0, "elapsed_time": "3:22:07", "remaining_time": "3:47:57", "throughput": 1486.92, "total_tokens": 18032672} {"current_steps": 85445, "total_steps": 181800, "loss": 0.1245, "lr": 3.1891856727613856e-05, "epoch": 9.3998899889989, "percentage": 47.0, "elapsed_time": "3:22:08", "remaining_time": "3:47:56", "throughput": 1486.92, "total_tokens": 18033728} {"current_steps": 85450, "total_steps": 181800, "loss": 0.0838, "lr": 3.1889549628088965e-05, "epoch": 9.4004400440044, "percentage": 47.0, "elapsed_time": "3:22:08", "remaining_time": "3:47:56", "throughput": 1486.92, "total_tokens": 18034784} {"current_steps": 85455, "total_steps": 181800, "loss": 0.0114, "lr": 3.1887242465066404e-05, "epoch": 9.400990099009901, "percentage": 47.0, "elapsed_time": "3:22:09", "remaining_time": "3:47:55", "throughput": 1486.93, "total_tokens": 18035872} {"current_steps": 85460, "total_steps": 181800, "loss": 0.0572, "lr": 3.188493523856744e-05, "epoch": 9.401540154015402, "percentage": 47.01, "elapsed_time": "3:22:10", "remaining_time": "3:47:54", "throughput": 1486.93, "total_tokens": 18036864} {"current_steps": 85465, "total_steps": 181800, "loss": 0.0297, "lr": 3.188262794861331e-05, "epoch": 9.402090209020901, "percentage": 47.01, "elapsed_time": "3:22:10", "remaining_time": "3:47:53", "throughput": 1486.93, "total_tokens": 18037952} {"current_steps": 85470, "total_steps": 181800, "loss": 0.0493, "lr": 3.188032059522532e-05, "epoch": 9.402640264026402, "percentage": 47.01, "elapsed_time": "3:22:11", "remaining_time": "3:47:53", "throughput": 1486.94, "total_tokens": 18039008} {"current_steps": 85475, "total_steps": 181800, "loss": 0.0095, "lr": 3.1878013178424716e-05, "epoch": 9.403190319031903, "percentage": 47.02, "elapsed_time": "3:22:12", "remaining_time": "3:47:52", "throughput": 1486.94, "total_tokens": 18040096} {"current_steps": 85480, "total_steps": 181800, "loss": 0.0351, "lr": 3.1875705698232756e-05, "epoch": 9.403740374037405, "percentage": 47.02, "elapsed_time": "3:22:13", "remaining_time": "3:47:51", "throughput": 1486.95, "total_tokens": 18041248} {"current_steps": 85485, "total_steps": 181800, "loss": 0.0621, "lr": 3.1873398154670717e-05, "epoch": 9.404290429042904, "percentage": 47.02, "elapsed_time": "3:22:13", "remaining_time": "3:47:50", "throughput": 1486.95, "total_tokens": 18042304} {"current_steps": 85490, "total_steps": 181800, "loss": 0.0474, "lr": 3.1871090547759876e-05, "epoch": 9.404840484048405, "percentage": 47.02, "elapsed_time": "3:22:14", "remaining_time": "3:47:50", "throughput": 1486.95, "total_tokens": 18043328} {"current_steps": 85495, "total_steps": 181800, "loss": 0.0661, "lr": 3.186878287752148e-05, "epoch": 9.405390539053906, "percentage": 47.03, "elapsed_time": "3:22:15", "remaining_time": "3:47:49", "throughput": 1486.96, "total_tokens": 18044384} {"current_steps": 85500, "total_steps": 181800, "loss": 0.1756, "lr": 3.186647514397681e-05, "epoch": 9.405940594059405, "percentage": 47.03, "elapsed_time": "3:22:15", "remaining_time": "3:47:48", "throughput": 1486.96, "total_tokens": 18045408} {"current_steps": 85505, "total_steps": 181800, "loss": 0.0913, "lr": 3.186416734714714e-05, "epoch": 9.406490649064907, "percentage": 47.03, "elapsed_time": "3:22:16", "remaining_time": "3:47:48", "throughput": 1486.96, "total_tokens": 18046464} {"current_steps": 85510, "total_steps": 181800, "loss": 0.0597, "lr": 3.1861859487053725e-05, "epoch": 9.407040704070408, "percentage": 47.04, "elapsed_time": "3:22:17", "remaining_time": "3:47:47", "throughput": 1486.96, "total_tokens": 18047520} {"current_steps": 85515, "total_steps": 181800, "loss": 0.0604, "lr": 3.185955156371784e-05, "epoch": 9.407590759075907, "percentage": 47.04, "elapsed_time": "3:22:17", "remaining_time": "3:47:46", "throughput": 1486.96, "total_tokens": 18048512} {"current_steps": 85520, "total_steps": 181800, "loss": 0.074, "lr": 3.185724357716077e-05, "epoch": 9.408140814081408, "percentage": 47.04, "elapsed_time": "3:22:18", "remaining_time": "3:47:45", "throughput": 1486.96, "total_tokens": 18049536} {"current_steps": 85525, "total_steps": 181800, "loss": 0.0365, "lr": 3.185493552740377e-05, "epoch": 9.408690869086909, "percentage": 47.04, "elapsed_time": "3:22:19", "remaining_time": "3:47:45", "throughput": 1486.96, "total_tokens": 18050592} {"current_steps": 85530, "total_steps": 181800, "loss": 0.0601, "lr": 3.185262741446813e-05, "epoch": 9.409240924092408, "percentage": 47.05, "elapsed_time": "3:22:19", "remaining_time": "3:47:44", "throughput": 1486.96, "total_tokens": 18051648} {"current_steps": 85535, "total_steps": 181800, "loss": 0.0183, "lr": 3.1850319238375096e-05, "epoch": 9.40979097909791, "percentage": 47.05, "elapsed_time": "3:22:20", "remaining_time": "3:47:43", "throughput": 1486.97, "total_tokens": 18052768} {"current_steps": 85540, "total_steps": 181800, "loss": 0.0403, "lr": 3.184801099914596e-05, "epoch": 9.41034103410341, "percentage": 47.05, "elapsed_time": "3:22:21", "remaining_time": "3:47:42", "throughput": 1486.98, "total_tokens": 18053856} {"current_steps": 85545, "total_steps": 181800, "loss": 0.0206, "lr": 3.1845702696802e-05, "epoch": 9.410891089108912, "percentage": 47.05, "elapsed_time": "3:22:22", "remaining_time": "3:47:42", "throughput": 1486.98, "total_tokens": 18054880} {"current_steps": 85550, "total_steps": 181800, "loss": 0.043, "lr": 3.184339433136448e-05, "epoch": 9.411441144114411, "percentage": 47.06, "elapsed_time": "3:22:22", "remaining_time": "3:47:41", "throughput": 1486.98, "total_tokens": 18056000} {"current_steps": 85555, "total_steps": 181800, "loss": 0.0687, "lr": 3.1841085902854676e-05, "epoch": 9.411991199119912, "percentage": 47.06, "elapsed_time": "3:22:23", "remaining_time": "3:47:40", "throughput": 1486.98, "total_tokens": 18056992} {"current_steps": 85560, "total_steps": 181800, "loss": 0.0267, "lr": 3.183877741129387e-05, "epoch": 9.412541254125413, "percentage": 47.06, "elapsed_time": "3:22:24", "remaining_time": "3:47:39", "throughput": 1486.98, "total_tokens": 18058048} {"current_steps": 85565, "total_steps": 181800, "loss": 0.0483, "lr": 3.183646885670333e-05, "epoch": 9.413091309130913, "percentage": 47.07, "elapsed_time": "3:22:24", "remaining_time": "3:47:39", "throughput": 1486.99, "total_tokens": 18059136} {"current_steps": 85570, "total_steps": 181800, "loss": 0.0489, "lr": 3.183416023910434e-05, "epoch": 9.413641364136414, "percentage": 47.07, "elapsed_time": "3:22:25", "remaining_time": "3:47:38", "throughput": 1486.99, "total_tokens": 18060160} {"current_steps": 85575, "total_steps": 181800, "loss": 0.01, "lr": 3.183185155851818e-05, "epoch": 9.414191419141915, "percentage": 47.07, "elapsed_time": "3:22:26", "remaining_time": "3:47:37", "throughput": 1486.99, "total_tokens": 18061184} {"current_steps": 85580, "total_steps": 181800, "loss": 0.0574, "lr": 3.182954281496611e-05, "epoch": 9.414741474147414, "percentage": 47.07, "elapsed_time": "3:22:26", "remaining_time": "3:47:37", "throughput": 1486.99, "total_tokens": 18062272} {"current_steps": 85585, "total_steps": 181800, "loss": 0.003, "lr": 3.182723400846942e-05, "epoch": 9.415291529152915, "percentage": 47.08, "elapsed_time": "3:22:27", "remaining_time": "3:47:36", "throughput": 1486.99, "total_tokens": 18063264} {"current_steps": 85590, "total_steps": 181800, "loss": 0.0099, "lr": 3.1824925139049406e-05, "epoch": 9.415841584158416, "percentage": 47.08, "elapsed_time": "3:22:28", "remaining_time": "3:47:35", "throughput": 1486.99, "total_tokens": 18064288} {"current_steps": 85595, "total_steps": 181800, "loss": 0.0108, "lr": 3.1822616206727315e-05, "epoch": 9.416391639163916, "percentage": 47.08, "elapsed_time": "3:22:28", "remaining_time": "3:47:34", "throughput": 1486.99, "total_tokens": 18065344} {"current_steps": 85600, "total_steps": 181800, "loss": 0.0331, "lr": 3.182030721152445e-05, "epoch": 9.416941694169417, "percentage": 47.08, "elapsed_time": "3:22:29", "remaining_time": "3:47:34", "throughput": 1487.0, "total_tokens": 18066400} {"current_steps": 85605, "total_steps": 181800, "loss": 0.0154, "lr": 3.181799815346209e-05, "epoch": 9.417491749174918, "percentage": 47.09, "elapsed_time": "3:22:30", "remaining_time": "3:47:33", "throughput": 1487.0, "total_tokens": 18067424} {"current_steps": 85610, "total_steps": 181800, "loss": 0.028, "lr": 3.181568903256151e-05, "epoch": 9.418041804180419, "percentage": 47.09, "elapsed_time": "3:22:30", "remaining_time": "3:47:32", "throughput": 1486.99, "total_tokens": 18068416} {"current_steps": 85615, "total_steps": 181800, "loss": 0.0176, "lr": 3.1813379848844e-05, "epoch": 9.418591859185918, "percentage": 47.09, "elapsed_time": "3:22:31", "remaining_time": "3:47:31", "throughput": 1487.0, "total_tokens": 18069472} {"current_steps": 85620, "total_steps": 181800, "loss": 0.0246, "lr": 3.181107060233084e-05, "epoch": 9.41914191419142, "percentage": 47.1, "elapsed_time": "3:22:32", "remaining_time": "3:47:31", "throughput": 1487.0, "total_tokens": 18070528} {"current_steps": 85625, "total_steps": 181800, "loss": 0.0075, "lr": 3.1808761293043285e-05, "epoch": 9.41969196919692, "percentage": 47.1, "elapsed_time": "3:22:33", "remaining_time": "3:47:30", "throughput": 1487.0, "total_tokens": 18071552} {"current_steps": 85630, "total_steps": 181800, "loss": 0.0755, "lr": 3.180645192100267e-05, "epoch": 9.42024202420242, "percentage": 47.1, "elapsed_time": "3:22:33", "remaining_time": "3:47:29", "throughput": 1487.0, "total_tokens": 18072576} {"current_steps": 85635, "total_steps": 181800, "loss": 0.0397, "lr": 3.180414248623025e-05, "epoch": 9.42079207920792, "percentage": 47.1, "elapsed_time": "3:22:34", "remaining_time": "3:47:28", "throughput": 1487.0, "total_tokens": 18073600} {"current_steps": 85640, "total_steps": 181800, "loss": 0.0134, "lr": 3.1801832988747304e-05, "epoch": 9.421342134213422, "percentage": 47.11, "elapsed_time": "3:22:35", "remaining_time": "3:47:28", "throughput": 1487.0, "total_tokens": 18074656} {"current_steps": 85645, "total_steps": 181800, "loss": 0.0132, "lr": 3.179952342857513e-05, "epoch": 9.421892189218921, "percentage": 47.11, "elapsed_time": "3:22:35", "remaining_time": "3:47:27", "throughput": 1487.01, "total_tokens": 18075744} {"current_steps": 85650, "total_steps": 181800, "loss": 0.0537, "lr": 3.179721380573502e-05, "epoch": 9.422442244224422, "percentage": 47.11, "elapsed_time": "3:22:36", "remaining_time": "3:47:26", "throughput": 1487.01, "total_tokens": 18076800} {"current_steps": 85655, "total_steps": 181800, "loss": 0.0121, "lr": 3.179490412024824e-05, "epoch": 9.422992299229923, "percentage": 47.11, "elapsed_time": "3:22:37", "remaining_time": "3:47:26", "throughput": 1487.01, "total_tokens": 18077856} {"current_steps": 85660, "total_steps": 181800, "loss": 0.0228, "lr": 3.17925943721361e-05, "epoch": 9.423542354235423, "percentage": 47.12, "elapsed_time": "3:22:37", "remaining_time": "3:47:25", "throughput": 1487.02, "total_tokens": 18078912} {"current_steps": 85665, "total_steps": 181800, "loss": 0.0098, "lr": 3.179028456141987e-05, "epoch": 9.424092409240924, "percentage": 47.12, "elapsed_time": "3:22:38", "remaining_time": "3:47:24", "throughput": 1487.02, "total_tokens": 18079936} {"current_steps": 85670, "total_steps": 181800, "loss": 0.0069, "lr": 3.178797468812085e-05, "epoch": 9.424642464246425, "percentage": 47.12, "elapsed_time": "3:22:39", "remaining_time": "3:47:23", "throughput": 1487.02, "total_tokens": 18081024} {"current_steps": 85675, "total_steps": 181800, "loss": 0.0307, "lr": 3.1785664752260326e-05, "epoch": 9.425192519251926, "percentage": 47.13, "elapsed_time": "3:22:39", "remaining_time": "3:47:23", "throughput": 1487.02, "total_tokens": 18082048} {"current_steps": 85680, "total_steps": 181800, "loss": 0.0133, "lr": 3.178335475385958e-05, "epoch": 9.425742574257425, "percentage": 47.13, "elapsed_time": "3:22:40", "remaining_time": "3:47:22", "throughput": 1487.02, "total_tokens": 18083104} {"current_steps": 85685, "total_steps": 181800, "loss": 0.053, "lr": 3.178104469293991e-05, "epoch": 9.426292629262926, "percentage": 47.13, "elapsed_time": "3:22:41", "remaining_time": "3:47:21", "throughput": 1487.03, "total_tokens": 18084160} {"current_steps": 85690, "total_steps": 181800, "loss": 0.0059, "lr": 3.1778734569522606e-05, "epoch": 9.426842684268427, "percentage": 47.13, "elapsed_time": "3:22:41", "remaining_time": "3:47:20", "throughput": 1487.03, "total_tokens": 18085248} {"current_steps": 85695, "total_steps": 181800, "loss": 0.0083, "lr": 3.1776424383628955e-05, "epoch": 9.427392739273927, "percentage": 47.14, "elapsed_time": "3:22:42", "remaining_time": "3:47:20", "throughput": 1487.04, "total_tokens": 18086304} {"current_steps": 85700, "total_steps": 181800, "loss": 0.0005, "lr": 3.177411413528025e-05, "epoch": 9.427942794279428, "percentage": 47.14, "elapsed_time": "3:22:43", "remaining_time": "3:47:19", "throughput": 1487.03, "total_tokens": 18087328} {"current_steps": 85705, "total_steps": 181800, "loss": 0.0059, "lr": 3.177180382449779e-05, "epoch": 9.428492849284929, "percentage": 47.14, "elapsed_time": "3:22:44", "remaining_time": "3:47:18", "throughput": 1487.04, "total_tokens": 18088416} {"current_steps": 85710, "total_steps": 181800, "loss": 0.0111, "lr": 3.176949345130287e-05, "epoch": 9.429042904290428, "percentage": 47.15, "elapsed_time": "3:22:44", "remaining_time": "3:47:17", "throughput": 1487.05, "total_tokens": 18089536} {"current_steps": 85715, "total_steps": 181800, "loss": 0.0042, "lr": 3.1767183015716774e-05, "epoch": 9.42959295929593, "percentage": 47.15, "elapsed_time": "3:22:45", "remaining_time": "3:47:17", "throughput": 1487.05, "total_tokens": 18090592} {"current_steps": 85720, "total_steps": 181800, "loss": 0.0468, "lr": 3.176487251776079e-05, "epoch": 9.43014301430143, "percentage": 47.15, "elapsed_time": "3:22:46", "remaining_time": "3:47:16", "throughput": 1487.05, "total_tokens": 18091616} {"current_steps": 85725, "total_steps": 181800, "loss": 0.0409, "lr": 3.176256195745623e-05, "epoch": 9.430693069306932, "percentage": 47.15, "elapsed_time": "3:22:46", "remaining_time": "3:47:15", "throughput": 1487.06, "total_tokens": 18092704} {"current_steps": 85730, "total_steps": 181800, "loss": 0.007, "lr": 3.176025133482437e-05, "epoch": 9.43124312431243, "percentage": 47.16, "elapsed_time": "3:22:47", "remaining_time": "3:47:15", "throughput": 1487.06, "total_tokens": 18093760} {"current_steps": 85735, "total_steps": 181800, "loss": 0.1267, "lr": 3.175794064988654e-05, "epoch": 9.431793179317932, "percentage": 47.16, "elapsed_time": "3:22:48", "remaining_time": "3:47:14", "throughput": 1487.06, "total_tokens": 18094784} {"current_steps": 85740, "total_steps": 181800, "loss": 0.0071, "lr": 3.1755629902663995e-05, "epoch": 9.432343234323433, "percentage": 47.16, "elapsed_time": "3:22:48", "remaining_time": "3:47:13", "throughput": 1487.07, "total_tokens": 18095904} {"current_steps": 85745, "total_steps": 181800, "loss": 0.0338, "lr": 3.175331909317806e-05, "epoch": 9.432893289328932, "percentage": 47.16, "elapsed_time": "3:22:49", "remaining_time": "3:47:12", "throughput": 1487.07, "total_tokens": 18096960} {"current_steps": 85750, "total_steps": 181800, "loss": 0.0504, "lr": 3.1751008221450025e-05, "epoch": 9.433443344334433, "percentage": 47.17, "elapsed_time": "3:22:50", "remaining_time": "3:47:12", "throughput": 1487.07, "total_tokens": 18098048} {"current_steps": 85755, "total_steps": 181800, "loss": 0.0357, "lr": 3.174869728750117e-05, "epoch": 9.433993399339935, "percentage": 47.17, "elapsed_time": "3:22:50", "remaining_time": "3:47:11", "throughput": 1487.08, "total_tokens": 18099136} {"current_steps": 85760, "total_steps": 181800, "loss": 0.1681, "lr": 3.174638629135284e-05, "epoch": 9.434543454345434, "percentage": 47.17, "elapsed_time": "3:22:51", "remaining_time": "3:47:10", "throughput": 1487.08, "total_tokens": 18100192} {"current_steps": 85765, "total_steps": 181800, "loss": 0.0582, "lr": 3.1744075233026284e-05, "epoch": 9.435093509350935, "percentage": 47.18, "elapsed_time": "3:22:52", "remaining_time": "3:47:09", "throughput": 1487.08, "total_tokens": 18101248} {"current_steps": 85770, "total_steps": 181800, "loss": 0.0599, "lr": 3.174176411254282e-05, "epoch": 9.435643564356436, "percentage": 47.18, "elapsed_time": "3:22:53", "remaining_time": "3:47:09", "throughput": 1487.09, "total_tokens": 18102336} {"current_steps": 85775, "total_steps": 181800, "loss": 0.0575, "lr": 3.173945292992376e-05, "epoch": 9.436193619361935, "percentage": 47.18, "elapsed_time": "3:22:53", "remaining_time": "3:47:08", "throughput": 1487.09, "total_tokens": 18103392} {"current_steps": 85780, "total_steps": 181800, "loss": 0.0224, "lr": 3.173714168519039e-05, "epoch": 9.436743674367436, "percentage": 47.18, "elapsed_time": "3:22:54", "remaining_time": "3:47:07", "throughput": 1487.1, "total_tokens": 18104480} {"current_steps": 85785, "total_steps": 181800, "loss": 0.0104, "lr": 3.173483037836402e-05, "epoch": 9.437293729372938, "percentage": 47.19, "elapsed_time": "3:22:55", "remaining_time": "3:47:06", "throughput": 1487.1, "total_tokens": 18105568} {"current_steps": 85790, "total_steps": 181800, "loss": 0.1081, "lr": 3.173251900946595e-05, "epoch": 9.437843784378439, "percentage": 47.19, "elapsed_time": "3:22:55", "remaining_time": "3:47:06", "throughput": 1487.1, "total_tokens": 18106624} {"current_steps": 85795, "total_steps": 181800, "loss": 0.0596, "lr": 3.173020757851749e-05, "epoch": 9.438393839383938, "percentage": 47.19, "elapsed_time": "3:22:56", "remaining_time": "3:47:05", "throughput": 1487.1, "total_tokens": 18107616} {"current_steps": 85800, "total_steps": 181800, "loss": 0.1187, "lr": 3.172789608553993e-05, "epoch": 9.438943894389439, "percentage": 47.19, "elapsed_time": "3:22:57", "remaining_time": "3:47:04", "throughput": 1487.1, "total_tokens": 18108640} {"current_steps": 85805, "total_steps": 181800, "loss": 0.0385, "lr": 3.172558453055459e-05, "epoch": 9.43949394939494, "percentage": 47.2, "elapsed_time": "3:22:57", "remaining_time": "3:47:04", "throughput": 1487.11, "total_tokens": 18109792} {"current_steps": 85810, "total_steps": 181800, "loss": 0.0366, "lr": 3.1723272913582745e-05, "epoch": 9.44004400440044, "percentage": 47.2, "elapsed_time": "3:22:58", "remaining_time": "3:47:03", "throughput": 1487.11, "total_tokens": 18110784} {"current_steps": 85815, "total_steps": 181800, "loss": 0.0046, "lr": 3.172096123464573e-05, "epoch": 9.44059405940594, "percentage": 47.2, "elapsed_time": "3:22:59", "remaining_time": "3:47:02", "throughput": 1487.11, "total_tokens": 18111872} {"current_steps": 85820, "total_steps": 181800, "loss": 0.0131, "lr": 3.171864949376484e-05, "epoch": 9.441144114411442, "percentage": 47.21, "elapsed_time": "3:22:59", "remaining_time": "3:47:01", "throughput": 1487.11, "total_tokens": 18112896} {"current_steps": 85825, "total_steps": 181800, "loss": 0.1384, "lr": 3.171633769096138e-05, "epoch": 9.441694169416941, "percentage": 47.21, "elapsed_time": "3:23:00", "remaining_time": "3:47:01", "throughput": 1487.12, "total_tokens": 18113952} {"current_steps": 85830, "total_steps": 181800, "loss": 0.014, "lr": 3.171402582625667e-05, "epoch": 9.442244224422442, "percentage": 47.21, "elapsed_time": "3:23:01", "remaining_time": "3:47:00", "throughput": 1487.12, "total_tokens": 18115040} {"current_steps": 85835, "total_steps": 181800, "loss": 0.0052, "lr": 3.171171389967199e-05, "epoch": 9.442794279427943, "percentage": 47.21, "elapsed_time": "3:23:01", "remaining_time": "3:46:59", "throughput": 1487.12, "total_tokens": 18116096} {"current_steps": 85840, "total_steps": 181800, "loss": 0.0693, "lr": 3.170940191122867e-05, "epoch": 9.443344334433444, "percentage": 47.22, "elapsed_time": "3:23:02", "remaining_time": "3:46:58", "throughput": 1487.13, "total_tokens": 18117152} {"current_steps": 85845, "total_steps": 181800, "loss": 0.0092, "lr": 3.170708986094801e-05, "epoch": 9.443894389438944, "percentage": 47.22, "elapsed_time": "3:23:03", "remaining_time": "3:46:58", "throughput": 1487.12, "total_tokens": 18118144} {"current_steps": 85850, "total_steps": 181800, "loss": 0.045, "lr": 3.1704777748851324e-05, "epoch": 9.444444444444445, "percentage": 47.22, "elapsed_time": "3:23:04", "remaining_time": "3:46:57", "throughput": 1487.12, "total_tokens": 18119168} {"current_steps": 85855, "total_steps": 181800, "loss": 0.0036, "lr": 3.1702465574959914e-05, "epoch": 9.444994499449946, "percentage": 47.22, "elapsed_time": "3:23:04", "remaining_time": "3:46:56", "throughput": 1487.13, "total_tokens": 18120256} {"current_steps": 85860, "total_steps": 181800, "loss": 0.0123, "lr": 3.17001533392951e-05, "epoch": 9.445544554455445, "percentage": 47.23, "elapsed_time": "3:23:05", "remaining_time": "3:46:55", "throughput": 1487.13, "total_tokens": 18121280} {"current_steps": 85865, "total_steps": 181800, "loss": 0.0027, "lr": 3.169784104187818e-05, "epoch": 9.446094609460946, "percentage": 47.23, "elapsed_time": "3:23:06", "remaining_time": "3:46:55", "throughput": 1487.14, "total_tokens": 18122400} {"current_steps": 85870, "total_steps": 181800, "loss": 0.089, "lr": 3.169552868273048e-05, "epoch": 9.446644664466447, "percentage": 47.23, "elapsed_time": "3:23:06", "remaining_time": "3:46:54", "throughput": 1487.14, "total_tokens": 18123424} {"current_steps": 85875, "total_steps": 181800, "loss": 0.0076, "lr": 3.16932162618733e-05, "epoch": 9.447194719471947, "percentage": 47.24, "elapsed_time": "3:23:07", "remaining_time": "3:46:53", "throughput": 1487.14, "total_tokens": 18124512} {"current_steps": 85880, "total_steps": 181800, "loss": 0.0321, "lr": 3.169090377932797e-05, "epoch": 9.447744774477448, "percentage": 47.24, "elapsed_time": "3:23:08", "remaining_time": "3:46:53", "throughput": 1487.14, "total_tokens": 18125568} {"current_steps": 85885, "total_steps": 181800, "loss": 0.029, "lr": 3.168859123511578e-05, "epoch": 9.448294829482949, "percentage": 47.24, "elapsed_time": "3:23:08", "remaining_time": "3:46:52", "throughput": 1487.15, "total_tokens": 18126656} {"current_steps": 85890, "total_steps": 181800, "loss": 0.0037, "lr": 3.168627862925806e-05, "epoch": 9.448844884488448, "percentage": 47.24, "elapsed_time": "3:23:09", "remaining_time": "3:46:51", "throughput": 1487.15, "total_tokens": 18127744} {"current_steps": 85895, "total_steps": 181800, "loss": 0.0478, "lr": 3.168396596177611e-05, "epoch": 9.44939493949395, "percentage": 47.25, "elapsed_time": "3:23:10", "remaining_time": "3:46:50", "throughput": 1487.16, "total_tokens": 18128800} {"current_steps": 85900, "total_steps": 181800, "loss": 0.0901, "lr": 3.1681653232691264e-05, "epoch": 9.44994499449945, "percentage": 47.25, "elapsed_time": "3:23:10", "remaining_time": "3:46:50", "throughput": 1487.16, "total_tokens": 18129888} {"current_steps": 85905, "total_steps": 181800, "loss": 0.0612, "lr": 3.167934044202482e-05, "epoch": 9.450495049504951, "percentage": 47.25, "elapsed_time": "3:23:11", "remaining_time": "3:46:49", "throughput": 1487.16, "total_tokens": 18130944} {"current_steps": 85910, "total_steps": 181800, "loss": 0.0565, "lr": 3.1677027589798097e-05, "epoch": 9.45104510451045, "percentage": 47.26, "elapsed_time": "3:23:12", "remaining_time": "3:46:48", "throughput": 1487.17, "total_tokens": 18132000} {"current_steps": 85915, "total_steps": 181800, "loss": 0.0248, "lr": 3.167471467603241e-05, "epoch": 9.451595159515952, "percentage": 47.26, "elapsed_time": "3:23:13", "remaining_time": "3:46:47", "throughput": 1487.17, "total_tokens": 18133088} {"current_steps": 85920, "total_steps": 181800, "loss": 0.0642, "lr": 3.167240170074909e-05, "epoch": 9.452145214521453, "percentage": 47.26, "elapsed_time": "3:23:13", "remaining_time": "3:46:47", "throughput": 1487.17, "total_tokens": 18134144} {"current_steps": 85925, "total_steps": 181800, "loss": 0.0024, "lr": 3.167008866396946e-05, "epoch": 9.452695269526952, "percentage": 47.26, "elapsed_time": "3:23:14", "remaining_time": "3:46:46", "throughput": 1487.18, "total_tokens": 18135232} {"current_steps": 85930, "total_steps": 181800, "loss": 0.0529, "lr": 3.16677755657148e-05, "epoch": 9.453245324532453, "percentage": 47.27, "elapsed_time": "3:23:15", "remaining_time": "3:46:45", "throughput": 1487.18, "total_tokens": 18136256} {"current_steps": 85935, "total_steps": 181800, "loss": 0.0182, "lr": 3.166546240600645e-05, "epoch": 9.453795379537954, "percentage": 47.27, "elapsed_time": "3:23:15", "remaining_time": "3:46:45", "throughput": 1487.18, "total_tokens": 18137312} {"current_steps": 85940, "total_steps": 181800, "loss": 0.0655, "lr": 3.1663149184865746e-05, "epoch": 9.454345434543454, "percentage": 47.27, "elapsed_time": "3:23:16", "remaining_time": "3:46:44", "throughput": 1487.19, "total_tokens": 18138400} {"current_steps": 85945, "total_steps": 181800, "loss": 0.0333, "lr": 3.166083590231398e-05, "epoch": 9.454895489548955, "percentage": 47.27, "elapsed_time": "3:23:17", "remaining_time": "3:46:43", "throughput": 1487.19, "total_tokens": 18139456} {"current_steps": 85950, "total_steps": 181800, "loss": 0.0736, "lr": 3.16585225583725e-05, "epoch": 9.455445544554456, "percentage": 47.28, "elapsed_time": "3:23:17", "remaining_time": "3:46:42", "throughput": 1487.19, "total_tokens": 18140544} {"current_steps": 85955, "total_steps": 181800, "loss": 0.101, "lr": 3.165620915306261e-05, "epoch": 9.455995599559955, "percentage": 47.28, "elapsed_time": "3:23:18", "remaining_time": "3:46:42", "throughput": 1487.2, "total_tokens": 18141632} {"current_steps": 85960, "total_steps": 181800, "loss": 0.0144, "lr": 3.165389568640562e-05, "epoch": 9.456545654565456, "percentage": 47.28, "elapsed_time": "3:23:19", "remaining_time": "3:46:41", "throughput": 1487.2, "total_tokens": 18142656} {"current_steps": 85965, "total_steps": 181800, "loss": 0.0207, "lr": 3.165158215842288e-05, "epoch": 9.457095709570957, "percentage": 47.29, "elapsed_time": "3:23:19", "remaining_time": "3:46:40", "throughput": 1487.21, "total_tokens": 18143776} {"current_steps": 85970, "total_steps": 181800, "loss": 0.041, "lr": 3.1649268569135696e-05, "epoch": 9.457645764576458, "percentage": 47.29, "elapsed_time": "3:23:20", "remaining_time": "3:46:39", "throughput": 1487.21, "total_tokens": 18144864} {"current_steps": 85975, "total_steps": 181800, "loss": 0.0599, "lr": 3.16469549185654e-05, "epoch": 9.458195819581958, "percentage": 47.29, "elapsed_time": "3:23:21", "remaining_time": "3:46:39", "throughput": 1487.21, "total_tokens": 18145856} {"current_steps": 85980, "total_steps": 181800, "loss": 0.0625, "lr": 3.16446412067333e-05, "epoch": 9.458745874587459, "percentage": 47.29, "elapsed_time": "3:23:21", "remaining_time": "3:46:38", "throughput": 1487.21, "total_tokens": 18146848} {"current_steps": 85985, "total_steps": 181800, "loss": 0.0221, "lr": 3.164232743366074e-05, "epoch": 9.45929592959296, "percentage": 47.3, "elapsed_time": "3:23:22", "remaining_time": "3:46:37", "throughput": 1487.21, "total_tokens": 18147904} {"current_steps": 85990, "total_steps": 181800, "loss": 0.0044, "lr": 3.164001359936902e-05, "epoch": 9.45984598459846, "percentage": 47.3, "elapsed_time": "3:23:23", "remaining_time": "3:46:36", "throughput": 1487.21, "total_tokens": 18148928} {"current_steps": 85995, "total_steps": 181800, "loss": 0.0332, "lr": 3.1637699703879494e-05, "epoch": 9.46039603960396, "percentage": 47.3, "elapsed_time": "3:23:24", "remaining_time": "3:46:36", "throughput": 1487.21, "total_tokens": 18149952} {"current_steps": 86000, "total_steps": 181800, "loss": 0.0537, "lr": 3.1635385747213466e-05, "epoch": 9.460946094609461, "percentage": 47.3, "elapsed_time": "3:23:24", "remaining_time": "3:46:35", "throughput": 1487.21, "total_tokens": 18151008} {"current_steps": 86005, "total_steps": 181800, "loss": 0.0226, "lr": 3.163307172939228e-05, "epoch": 9.46149614961496, "percentage": 47.31, "elapsed_time": "3:23:25", "remaining_time": "3:46:34", "throughput": 1487.22, "total_tokens": 18152096} {"current_steps": 86010, "total_steps": 181800, "loss": 0.0242, "lr": 3.1630757650437255e-05, "epoch": 9.462046204620462, "percentage": 47.31, "elapsed_time": "3:23:26", "remaining_time": "3:46:34", "throughput": 1487.22, "total_tokens": 18153184} {"current_steps": 86015, "total_steps": 181800, "loss": 0.0735, "lr": 3.162844351036971e-05, "epoch": 9.462596259625963, "percentage": 47.31, "elapsed_time": "3:23:26", "remaining_time": "3:46:33", "throughput": 1487.22, "total_tokens": 18154208} {"current_steps": 86020, "total_steps": 181800, "loss": 0.0139, "lr": 3.162612930921099e-05, "epoch": 9.463146314631462, "percentage": 47.32, "elapsed_time": "3:23:27", "remaining_time": "3:46:32", "throughput": 1487.23, "total_tokens": 18155264} {"current_steps": 86025, "total_steps": 181800, "loss": 0.0381, "lr": 3.162381504698241e-05, "epoch": 9.463696369636963, "percentage": 47.32, "elapsed_time": "3:23:28", "remaining_time": "3:46:31", "throughput": 1487.23, "total_tokens": 18156288} {"current_steps": 86030, "total_steps": 181800, "loss": 0.0229, "lr": 3.1621500723705305e-05, "epoch": 9.464246424642464, "percentage": 47.32, "elapsed_time": "3:23:28", "remaining_time": "3:46:31", "throughput": 1487.23, "total_tokens": 18157344} {"current_steps": 86035, "total_steps": 181800, "loss": 0.003, "lr": 3.1619186339401005e-05, "epoch": 9.464796479647966, "percentage": 47.32, "elapsed_time": "3:23:29", "remaining_time": "3:46:30", "throughput": 1487.23, "total_tokens": 18158368} {"current_steps": 86040, "total_steps": 181800, "loss": 0.0018, "lr": 3.161687189409085e-05, "epoch": 9.465346534653465, "percentage": 47.33, "elapsed_time": "3:23:30", "remaining_time": "3:46:29", "throughput": 1487.23, "total_tokens": 18159456} {"current_steps": 86045, "total_steps": 181800, "loss": 0.0189, "lr": 3.1614557387796155e-05, "epoch": 9.465896589658966, "percentage": 47.33, "elapsed_time": "3:23:30", "remaining_time": "3:46:28", "throughput": 1487.23, "total_tokens": 18160480} {"current_steps": 86050, "total_steps": 181800, "loss": 0.0212, "lr": 3.1612242820538255e-05, "epoch": 9.466446644664467, "percentage": 47.33, "elapsed_time": "3:23:31", "remaining_time": "3:46:28", "throughput": 1487.24, "total_tokens": 18161568} {"current_steps": 86055, "total_steps": 181800, "loss": 0.0065, "lr": 3.1609928192338496e-05, "epoch": 9.466996699669966, "percentage": 47.33, "elapsed_time": "3:23:32", "remaining_time": "3:46:27", "throughput": 1487.24, "total_tokens": 18162560} {"current_steps": 86060, "total_steps": 181800, "loss": 0.0191, "lr": 3.160761350321819e-05, "epoch": 9.467546754675467, "percentage": 47.34, "elapsed_time": "3:23:32", "remaining_time": "3:46:26", "throughput": 1487.24, "total_tokens": 18163680} {"current_steps": 86065, "total_steps": 181800, "loss": 0.0079, "lr": 3.1605298753198686e-05, "epoch": 9.468096809680969, "percentage": 47.34, "elapsed_time": "3:23:33", "remaining_time": "3:46:25", "throughput": 1487.24, "total_tokens": 18164704} {"current_steps": 86070, "total_steps": 181800, "loss": 0.0459, "lr": 3.160298394230132e-05, "epoch": 9.468646864686468, "percentage": 47.34, "elapsed_time": "3:23:34", "remaining_time": "3:46:25", "throughput": 1487.25, "total_tokens": 18165760} {"current_steps": 86075, "total_steps": 181800, "loss": 0.0788, "lr": 3.16006690705474e-05, "epoch": 9.469196919691969, "percentage": 47.35, "elapsed_time": "3:23:35", "remaining_time": "3:46:24", "throughput": 1487.25, "total_tokens": 18166880} {"current_steps": 86080, "total_steps": 181800, "loss": 0.0041, "lr": 3.1598354137958295e-05, "epoch": 9.46974697469747, "percentage": 47.35, "elapsed_time": "3:23:35", "remaining_time": "3:46:23", "throughput": 1487.26, "total_tokens": 18167936} {"current_steps": 86085, "total_steps": 181800, "loss": 0.0269, "lr": 3.159603914455532e-05, "epoch": 9.47029702970297, "percentage": 47.35, "elapsed_time": "3:23:36", "remaining_time": "3:46:23", "throughput": 1487.25, "total_tokens": 18168896} {"current_steps": 86090, "total_steps": 181800, "loss": 0.0039, "lr": 3.159372409035982e-05, "epoch": 9.47084708470847, "percentage": 47.35, "elapsed_time": "3:23:37", "remaining_time": "3:46:22", "throughput": 1487.26, "total_tokens": 18169984} {"current_steps": 86095, "total_steps": 181800, "loss": 0.0358, "lr": 3.159140897539313e-05, "epoch": 9.471397139713972, "percentage": 47.36, "elapsed_time": "3:23:37", "remaining_time": "3:46:21", "throughput": 1487.26, "total_tokens": 18171072} {"current_steps": 86100, "total_steps": 181800, "loss": 0.011, "lr": 3.1589093799676595e-05, "epoch": 9.471947194719473, "percentage": 47.36, "elapsed_time": "3:23:38", "remaining_time": "3:46:20", "throughput": 1487.26, "total_tokens": 18172064} {"current_steps": 86105, "total_steps": 181800, "loss": 0.0144, "lr": 3.158677856323153e-05, "epoch": 9.472497249724972, "percentage": 47.36, "elapsed_time": "3:23:39", "remaining_time": "3:46:20", "throughput": 1487.26, "total_tokens": 18173152} {"current_steps": 86110, "total_steps": 181800, "loss": 0.028, "lr": 3.158446326607929e-05, "epoch": 9.473047304730473, "percentage": 47.37, "elapsed_time": "3:23:39", "remaining_time": "3:46:19", "throughput": 1487.27, "total_tokens": 18174208} {"current_steps": 86115, "total_steps": 181800, "loss": 0.0375, "lr": 3.1582147908241214e-05, "epoch": 9.473597359735974, "percentage": 47.37, "elapsed_time": "3:23:40", "remaining_time": "3:46:18", "throughput": 1487.27, "total_tokens": 18175264} {"current_steps": 86120, "total_steps": 181800, "loss": 0.0109, "lr": 3.157983248973864e-05, "epoch": 9.474147414741473, "percentage": 47.37, "elapsed_time": "3:23:41", "remaining_time": "3:46:17", "throughput": 1487.27, "total_tokens": 18176256} {"current_steps": 86125, "total_steps": 181800, "loss": 0.0629, "lr": 3.1577517010592906e-05, "epoch": 9.474697469746975, "percentage": 47.37, "elapsed_time": "3:23:41", "remaining_time": "3:46:17", "throughput": 1487.27, "total_tokens": 18177344} {"current_steps": 86130, "total_steps": 181800, "loss": 0.095, "lr": 3.1575201470825356e-05, "epoch": 9.475247524752476, "percentage": 47.38, "elapsed_time": "3:23:42", "remaining_time": "3:46:16", "throughput": 1487.28, "total_tokens": 18178400} {"current_steps": 86135, "total_steps": 181800, "loss": 0.009, "lr": 3.157288587045733e-05, "epoch": 9.475797579757975, "percentage": 47.38, "elapsed_time": "3:23:43", "remaining_time": "3:46:15", "throughput": 1487.28, "total_tokens": 18179424} {"current_steps": 86140, "total_steps": 181800, "loss": 0.0007, "lr": 3.157057020951016e-05, "epoch": 9.476347634763476, "percentage": 47.38, "elapsed_time": "3:23:43", "remaining_time": "3:46:14", "throughput": 1487.28, "total_tokens": 18180512} {"current_steps": 86145, "total_steps": 181800, "loss": 0.0494, "lr": 3.1568254488005207e-05, "epoch": 9.476897689768977, "percentage": 47.38, "elapsed_time": "3:23:44", "remaining_time": "3:46:14", "throughput": 1487.29, "total_tokens": 18181600} {"current_steps": 86150, "total_steps": 181800, "loss": 0.0822, "lr": 3.15659387059638e-05, "epoch": 9.477447744774478, "percentage": 47.39, "elapsed_time": "3:23:45", "remaining_time": "3:46:13", "throughput": 1487.29, "total_tokens": 18182688} {"current_steps": 86155, "total_steps": 181800, "loss": 0.0009, "lr": 3.156362286340729e-05, "epoch": 9.477997799779978, "percentage": 47.39, "elapsed_time": "3:23:46", "remaining_time": "3:46:12", "throughput": 1487.29, "total_tokens": 18183680} {"current_steps": 86160, "total_steps": 181800, "loss": 0.0615, "lr": 3.156130696035702e-05, "epoch": 9.478547854785479, "percentage": 47.39, "elapsed_time": "3:23:46", "remaining_time": "3:46:12", "throughput": 1487.3, "total_tokens": 18184832} {"current_steps": 86165, "total_steps": 181800, "loss": 0.0201, "lr": 3.155899099683433e-05, "epoch": 9.47909790979098, "percentage": 47.4, "elapsed_time": "3:23:47", "remaining_time": "3:46:11", "throughput": 1487.3, "total_tokens": 18185856} {"current_steps": 86170, "total_steps": 181800, "loss": 0.0042, "lr": 3.155667497286056e-05, "epoch": 9.479647964796479, "percentage": 47.4, "elapsed_time": "3:23:48", "remaining_time": "3:46:10", "throughput": 1487.3, "total_tokens": 18186944} {"current_steps": 86175, "total_steps": 181800, "loss": 0.1869, "lr": 3.1554358888457055e-05, "epoch": 9.48019801980198, "percentage": 47.4, "elapsed_time": "3:23:48", "remaining_time": "3:46:09", "throughput": 1487.31, "total_tokens": 18188032} {"current_steps": 86180, "total_steps": 181800, "loss": 0.1401, "lr": 3.155204274364519e-05, "epoch": 9.480748074807481, "percentage": 47.4, "elapsed_time": "3:23:49", "remaining_time": "3:46:09", "throughput": 1487.31, "total_tokens": 18189056} {"current_steps": 86185, "total_steps": 181800, "loss": 0.0652, "lr": 3.1549726538446286e-05, "epoch": 9.48129812981298, "percentage": 47.41, "elapsed_time": "3:23:50", "remaining_time": "3:46:08", "throughput": 1487.31, "total_tokens": 18190176} {"current_steps": 86190, "total_steps": 181800, "loss": 0.0198, "lr": 3.154741027288169e-05, "epoch": 9.481848184818482, "percentage": 47.41, "elapsed_time": "3:23:50", "remaining_time": "3:46:07", "throughput": 1487.31, "total_tokens": 18191168} {"current_steps": 86195, "total_steps": 181800, "loss": 0.0021, "lr": 3.154509394697276e-05, "epoch": 9.482398239823983, "percentage": 47.41, "elapsed_time": "3:23:51", "remaining_time": "3:46:06", "throughput": 1487.31, "total_tokens": 18192192} {"current_steps": 86200, "total_steps": 181800, "loss": 0.0984, "lr": 3.1542777560740835e-05, "epoch": 9.482948294829482, "percentage": 47.41, "elapsed_time": "3:23:52", "remaining_time": "3:46:06", "throughput": 1487.32, "total_tokens": 18193280} {"current_steps": 86205, "total_steps": 181800, "loss": 0.0695, "lr": 3.154046111420726e-05, "epoch": 9.483498349834983, "percentage": 47.42, "elapsed_time": "3:23:52", "remaining_time": "3:46:05", "throughput": 1487.32, "total_tokens": 18194400} {"current_steps": 86210, "total_steps": 181800, "loss": 0.07, "lr": 3.153814460739342e-05, "epoch": 9.484048404840484, "percentage": 47.42, "elapsed_time": "3:23:53", "remaining_time": "3:46:04", "throughput": 1487.33, "total_tokens": 18195488} {"current_steps": 86215, "total_steps": 181800, "loss": 0.0547, "lr": 3.153582804032062e-05, "epoch": 9.484598459845985, "percentage": 47.42, "elapsed_time": "3:23:54", "remaining_time": "3:46:04", "throughput": 1487.33, "total_tokens": 18196576} {"current_steps": 86220, "total_steps": 181800, "loss": 0.1675, "lr": 3.1533511413010225e-05, "epoch": 9.485148514851485, "percentage": 47.43, "elapsed_time": "3:23:55", "remaining_time": "3:46:03", "throughput": 1487.33, "total_tokens": 18197600} {"current_steps": 86225, "total_steps": 181800, "loss": 0.0104, "lr": 3.1531194725483595e-05, "epoch": 9.485698569856986, "percentage": 47.43, "elapsed_time": "3:23:55", "remaining_time": "3:46:02", "throughput": 1487.34, "total_tokens": 18198720} {"current_steps": 86230, "total_steps": 181800, "loss": 0.0142, "lr": 3.152887797776208e-05, "epoch": 9.486248624862487, "percentage": 47.43, "elapsed_time": "3:23:56", "remaining_time": "3:46:01", "throughput": 1487.35, "total_tokens": 18199840} {"current_steps": 86235, "total_steps": 181800, "loss": 0.0507, "lr": 3.1526561169867034e-05, "epoch": 9.486798679867986, "percentage": 47.43, "elapsed_time": "3:23:57", "remaining_time": "3:46:01", "throughput": 1487.35, "total_tokens": 18200864} {"current_steps": 86240, "total_steps": 181800, "loss": 0.0103, "lr": 3.15242443018198e-05, "epoch": 9.487348734873487, "percentage": 47.44, "elapsed_time": "3:23:57", "remaining_time": "3:46:00", "throughput": 1487.36, "total_tokens": 18201984} {"current_steps": 86245, "total_steps": 181800, "loss": 0.0402, "lr": 3.152192737364174e-05, "epoch": 9.487898789878988, "percentage": 47.44, "elapsed_time": "3:23:58", "remaining_time": "3:45:59", "throughput": 1487.36, "total_tokens": 18203008} {"current_steps": 86250, "total_steps": 181800, "loss": 0.0727, "lr": 3.15196103853542e-05, "epoch": 9.488448844884488, "percentage": 47.44, "elapsed_time": "3:23:59", "remaining_time": "3:45:58", "throughput": 1487.36, "total_tokens": 18204064} {"current_steps": 86255, "total_steps": 181800, "loss": 0.0076, "lr": 3.151729333697854e-05, "epoch": 9.488998899889989, "percentage": 47.44, "elapsed_time": "3:23:59", "remaining_time": "3:45:58", "throughput": 1487.36, "total_tokens": 18205152} {"current_steps": 86260, "total_steps": 181800, "loss": 0.0357, "lr": 3.1514976228536116e-05, "epoch": 9.48954895489549, "percentage": 47.45, "elapsed_time": "3:24:00", "remaining_time": "3:45:57", "throughput": 1487.36, "total_tokens": 18206208} {"current_steps": 86265, "total_steps": 181800, "loss": 0.0033, "lr": 3.151265906004828e-05, "epoch": 9.490099009900991, "percentage": 47.45, "elapsed_time": "3:24:01", "remaining_time": "3:45:56", "throughput": 1487.37, "total_tokens": 18207296} {"current_steps": 86270, "total_steps": 181800, "loss": 0.0039, "lr": 3.15103418315364e-05, "epoch": 9.49064906490649, "percentage": 47.45, "elapsed_time": "3:24:01", "remaining_time": "3:45:55", "throughput": 1487.37, "total_tokens": 18208352} {"current_steps": 86275, "total_steps": 181800, "loss": 0.0069, "lr": 3.1508024543021814e-05, "epoch": 9.491199119911991, "percentage": 47.46, "elapsed_time": "3:24:02", "remaining_time": "3:45:55", "throughput": 1487.37, "total_tokens": 18209376} {"current_steps": 86280, "total_steps": 181800, "loss": 0.0084, "lr": 3.150570719452589e-05, "epoch": 9.491749174917492, "percentage": 47.46, "elapsed_time": "3:24:03", "remaining_time": "3:45:54", "throughput": 1487.38, "total_tokens": 18210560} {"current_steps": 86285, "total_steps": 181800, "loss": 0.0115, "lr": 3.150338978606999e-05, "epoch": 9.492299229922992, "percentage": 47.46, "elapsed_time": "3:24:04", "remaining_time": "3:45:53", "throughput": 1487.39, "total_tokens": 18211616} {"current_steps": 86290, "total_steps": 181800, "loss": 0.0042, "lr": 3.1501072317675464e-05, "epoch": 9.492849284928493, "percentage": 47.46, "elapsed_time": "3:24:04", "remaining_time": "3:45:53", "throughput": 1487.38, "total_tokens": 18212608} {"current_steps": 86295, "total_steps": 181800, "loss": 0.0304, "lr": 3.149875478936366e-05, "epoch": 9.493399339933994, "percentage": 47.47, "elapsed_time": "3:24:05", "remaining_time": "3:45:52", "throughput": 1487.39, "total_tokens": 18213664} {"current_steps": 86300, "total_steps": 181800, "loss": 0.0025, "lr": 3.149643720115597e-05, "epoch": 9.493949394939493, "percentage": 47.47, "elapsed_time": "3:24:06", "remaining_time": "3:45:51", "throughput": 1487.39, "total_tokens": 18214752} {"current_steps": 86305, "total_steps": 181800, "loss": 0.0714, "lr": 3.149411955307373e-05, "epoch": 9.494499449944994, "percentage": 47.47, "elapsed_time": "3:24:06", "remaining_time": "3:45:50", "throughput": 1487.4, "total_tokens": 18215872} {"current_steps": 86310, "total_steps": 181800, "loss": 0.0036, "lr": 3.149180184513831e-05, "epoch": 9.495049504950495, "percentage": 47.48, "elapsed_time": "3:24:07", "remaining_time": "3:45:50", "throughput": 1487.4, "total_tokens": 18216896} {"current_steps": 86315, "total_steps": 181800, "loss": 0.1889, "lr": 3.148948407737106e-05, "epoch": 9.495599559955995, "percentage": 47.48, "elapsed_time": "3:24:08", "remaining_time": "3:45:49", "throughput": 1487.4, "total_tokens": 18217920} {"current_steps": 86320, "total_steps": 181800, "loss": 0.0465, "lr": 3.1487166249793356e-05, "epoch": 9.496149614961496, "percentage": 47.48, "elapsed_time": "3:24:08", "remaining_time": "3:45:48", "throughput": 1487.41, "total_tokens": 18219040} {"current_steps": 86325, "total_steps": 181800, "loss": 0.0784, "lr": 3.1484848362426545e-05, "epoch": 9.496699669966997, "percentage": 47.48, "elapsed_time": "3:24:09", "remaining_time": "3:45:47", "throughput": 1487.41, "total_tokens": 18220096} {"current_steps": 86330, "total_steps": 181800, "loss": 0.0337, "lr": 3.148253041529201e-05, "epoch": 9.497249724972498, "percentage": 47.49, "elapsed_time": "3:24:10", "remaining_time": "3:45:47", "throughput": 1487.41, "total_tokens": 18221120} {"current_steps": 86335, "total_steps": 181800, "loss": 0.1186, "lr": 3.1480212408411095e-05, "epoch": 9.497799779977997, "percentage": 47.49, "elapsed_time": "3:24:10", "remaining_time": "3:45:46", "throughput": 1487.41, "total_tokens": 18222144} {"current_steps": 86340, "total_steps": 181800, "loss": 0.0076, "lr": 3.147789434180517e-05, "epoch": 9.498349834983498, "percentage": 47.49, "elapsed_time": "3:24:11", "remaining_time": "3:45:45", "throughput": 1487.41, "total_tokens": 18223168} {"current_steps": 86345, "total_steps": 181800, "loss": 0.0152, "lr": 3.1475576215495605e-05, "epoch": 9.498899889989, "percentage": 47.49, "elapsed_time": "3:24:12", "remaining_time": "3:45:45", "throughput": 1487.41, "total_tokens": 18224224} {"current_steps": 86350, "total_steps": 181800, "loss": 0.0351, "lr": 3.147325802950376e-05, "epoch": 9.499449944994499, "percentage": 47.5, "elapsed_time": "3:24:12", "remaining_time": "3:45:44", "throughput": 1487.41, "total_tokens": 18225280} {"current_steps": 86355, "total_steps": 181800, "loss": 0.0475, "lr": 3.147093978385101e-05, "epoch": 9.5, "percentage": 47.5, "elapsed_time": "3:24:13", "remaining_time": "3:45:43", "throughput": 1487.42, "total_tokens": 18226336} {"current_steps": 86360, "total_steps": 181800, "loss": 0.0769, "lr": 3.1468621478558704e-05, "epoch": 9.500550055005501, "percentage": 47.5, "elapsed_time": "3:24:14", "remaining_time": "3:45:42", "throughput": 1487.42, "total_tokens": 18227456} {"current_steps": 86365, "total_steps": 181800, "loss": 0.005, "lr": 3.146630311364821e-05, "epoch": 9.501100110011, "percentage": 47.51, "elapsed_time": "3:24:15", "remaining_time": "3:45:42", "throughput": 1487.43, "total_tokens": 18228576} {"current_steps": 86370, "total_steps": 181800, "loss": 0.0043, "lr": 3.1463984689140915e-05, "epoch": 9.501650165016502, "percentage": 47.51, "elapsed_time": "3:24:15", "remaining_time": "3:45:41", "throughput": 1487.43, "total_tokens": 18229600} {"current_steps": 86375, "total_steps": 181800, "loss": 0.1209, "lr": 3.146166620505818e-05, "epoch": 9.502200220022003, "percentage": 47.51, "elapsed_time": "3:24:16", "remaining_time": "3:45:40", "throughput": 1487.44, "total_tokens": 18230688} {"current_steps": 86380, "total_steps": 181800, "loss": 0.0217, "lr": 3.145934766142135e-05, "epoch": 9.502750275027502, "percentage": 47.51, "elapsed_time": "3:24:17", "remaining_time": "3:45:39", "throughput": 1487.44, "total_tokens": 18231744} {"current_steps": 86385, "total_steps": 181800, "loss": 0.1158, "lr": 3.1457029058251824e-05, "epoch": 9.503300330033003, "percentage": 47.52, "elapsed_time": "3:24:17", "remaining_time": "3:45:39", "throughput": 1487.44, "total_tokens": 18232832} {"current_steps": 86390, "total_steps": 181800, "loss": 0.0086, "lr": 3.145471039557096e-05, "epoch": 9.503850385038504, "percentage": 47.52, "elapsed_time": "3:24:18", "remaining_time": "3:45:38", "throughput": 1487.44, "total_tokens": 18233888} {"current_steps": 86395, "total_steps": 181800, "loss": 0.0116, "lr": 3.1452391673400123e-05, "epoch": 9.504400440044005, "percentage": 47.52, "elapsed_time": "3:24:19", "remaining_time": "3:45:37", "throughput": 1487.45, "total_tokens": 18234912} {"current_steps": 86400, "total_steps": 181800, "loss": 0.0034, "lr": 3.1450072891760694e-05, "epoch": 9.504950495049505, "percentage": 47.52, "elapsed_time": "3:24:19", "remaining_time": "3:45:36", "throughput": 1487.45, "total_tokens": 18235968} {"current_steps": 86405, "total_steps": 181800, "loss": 0.0122, "lr": 3.144775405067404e-05, "epoch": 9.505500550055006, "percentage": 47.53, "elapsed_time": "3:24:20", "remaining_time": "3:45:36", "throughput": 1487.45, "total_tokens": 18236992} {"current_steps": 86410, "total_steps": 181800, "loss": 0.0106, "lr": 3.144543515016152e-05, "epoch": 9.506050605060507, "percentage": 47.53, "elapsed_time": "3:24:21", "remaining_time": "3:45:35", "throughput": 1487.45, "total_tokens": 18238048} {"current_steps": 86415, "total_steps": 181800, "loss": 0.0542, "lr": 3.144311619024452e-05, "epoch": 9.506600660066006, "percentage": 47.53, "elapsed_time": "3:24:21", "remaining_time": "3:45:34", "throughput": 1487.46, "total_tokens": 18239136} {"current_steps": 86420, "total_steps": 181800, "loss": 0.0168, "lr": 3.144079717094441e-05, "epoch": 9.507150715071507, "percentage": 47.54, "elapsed_time": "3:24:22", "remaining_time": "3:45:34", "throughput": 1487.46, "total_tokens": 18240224} {"current_steps": 86425, "total_steps": 181800, "loss": 0.0303, "lr": 3.143847809228257e-05, "epoch": 9.507700770077008, "percentage": 47.54, "elapsed_time": "3:24:23", "remaining_time": "3:45:33", "throughput": 1487.46, "total_tokens": 18241248} {"current_steps": 86430, "total_steps": 181800, "loss": 0.0296, "lr": 3.1436158954280363e-05, "epoch": 9.508250825082508, "percentage": 47.54, "elapsed_time": "3:24:24", "remaining_time": "3:45:32", "throughput": 1487.46, "total_tokens": 18242272} {"current_steps": 86435, "total_steps": 181800, "loss": 0.0572, "lr": 3.143383975695917e-05, "epoch": 9.508800880088009, "percentage": 47.54, "elapsed_time": "3:24:24", "remaining_time": "3:45:31", "throughput": 1487.47, "total_tokens": 18243360} {"current_steps": 86440, "total_steps": 181800, "loss": 0.0092, "lr": 3.1431520500340356e-05, "epoch": 9.50935093509351, "percentage": 47.55, "elapsed_time": "3:24:25", "remaining_time": "3:45:31", "throughput": 1487.47, "total_tokens": 18244448} {"current_steps": 86445, "total_steps": 181800, "loss": 0.0164, "lr": 3.1429201184445304e-05, "epoch": 9.509900990099009, "percentage": 47.55, "elapsed_time": "3:24:26", "remaining_time": "3:45:30", "throughput": 1487.48, "total_tokens": 18245568} {"current_steps": 86450, "total_steps": 181800, "loss": 0.0334, "lr": 3.14268818092954e-05, "epoch": 9.51045104510451, "percentage": 47.55, "elapsed_time": "3:24:26", "remaining_time": "3:45:29", "throughput": 1487.49, "total_tokens": 18246688} {"current_steps": 86455, "total_steps": 181800, "loss": 0.0425, "lr": 3.1424562374912e-05, "epoch": 9.511001100110011, "percentage": 47.56, "elapsed_time": "3:24:27", "remaining_time": "3:45:28", "throughput": 1487.49, "total_tokens": 18247744} {"current_steps": 86460, "total_steps": 181800, "loss": 0.0714, "lr": 3.14222428813165e-05, "epoch": 9.511551155115512, "percentage": 47.56, "elapsed_time": "3:24:28", "remaining_time": "3:45:28", "throughput": 1487.49, "total_tokens": 18248800} {"current_steps": 86465, "total_steps": 181800, "loss": 0.0099, "lr": 3.141992332853026e-05, "epoch": 9.512101210121012, "percentage": 47.56, "elapsed_time": "3:24:28", "remaining_time": "3:45:27", "throughput": 1487.49, "total_tokens": 18249792} {"current_steps": 86470, "total_steps": 181800, "loss": 0.0175, "lr": 3.141760371657467e-05, "epoch": 9.512651265126513, "percentage": 47.56, "elapsed_time": "3:24:29", "remaining_time": "3:45:26", "throughput": 1487.49, "total_tokens": 18250816} {"current_steps": 86475, "total_steps": 181800, "loss": 0.0055, "lr": 3.1415284045471114e-05, "epoch": 9.513201320132014, "percentage": 47.57, "elapsed_time": "3:24:30", "remaining_time": "3:45:26", "throughput": 1487.49, "total_tokens": 18251904} {"current_steps": 86480, "total_steps": 181800, "loss": 0.0144, "lr": 3.141296431524095e-05, "epoch": 9.513751375137513, "percentage": 47.57, "elapsed_time": "3:24:30", "remaining_time": "3:45:25", "throughput": 1487.49, "total_tokens": 18252896} {"current_steps": 86485, "total_steps": 181800, "loss": 0.0788, "lr": 3.141064452590558e-05, "epoch": 9.514301430143014, "percentage": 47.57, "elapsed_time": "3:24:31", "remaining_time": "3:45:24", "throughput": 1487.5, "total_tokens": 18254016} {"current_steps": 86490, "total_steps": 181800, "loss": 0.0062, "lr": 3.1408324677486375e-05, "epoch": 9.514851485148515, "percentage": 47.57, "elapsed_time": "3:24:32", "remaining_time": "3:45:23", "throughput": 1487.5, "total_tokens": 18255072} {"current_steps": 86495, "total_steps": 181800, "loss": 0.0018, "lr": 3.1406004770004714e-05, "epoch": 9.515401540154015, "percentage": 47.58, "elapsed_time": "3:24:33", "remaining_time": "3:45:23", "throughput": 1487.5, "total_tokens": 18256128} {"current_steps": 86500, "total_steps": 181800, "loss": 0.0018, "lr": 3.140368480348198e-05, "epoch": 9.515951595159516, "percentage": 47.58, "elapsed_time": "3:24:33", "remaining_time": "3:45:22", "throughput": 1487.5, "total_tokens": 18257184} {"current_steps": 86505, "total_steps": 181800, "loss": 0.0453, "lr": 3.1401364777939564e-05, "epoch": 9.516501650165017, "percentage": 47.58, "elapsed_time": "3:24:34", "remaining_time": "3:45:21", "throughput": 1487.5, "total_tokens": 18258144} {"current_steps": 86510, "total_steps": 181800, "loss": 0.1452, "lr": 3.1399044693398825e-05, "epoch": 9.517051705170516, "percentage": 47.59, "elapsed_time": "3:24:35", "remaining_time": "3:45:20", "throughput": 1487.5, "total_tokens": 18259232} {"current_steps": 86515, "total_steps": 181800, "loss": 0.022, "lr": 3.1396724549881175e-05, "epoch": 9.517601760176017, "percentage": 47.59, "elapsed_time": "3:24:35", "remaining_time": "3:45:20", "throughput": 1487.5, "total_tokens": 18260256} {"current_steps": 86520, "total_steps": 181800, "loss": 0.1322, "lr": 3.1394404347407985e-05, "epoch": 9.518151815181518, "percentage": 47.59, "elapsed_time": "3:24:36", "remaining_time": "3:45:19", "throughput": 1487.51, "total_tokens": 18261312} {"current_steps": 86525, "total_steps": 181800, "loss": 0.0513, "lr": 3.139208408600063e-05, "epoch": 9.51870187018702, "percentage": 47.59, "elapsed_time": "3:24:37", "remaining_time": "3:45:18", "throughput": 1487.51, "total_tokens": 18262400} {"current_steps": 86530, "total_steps": 181800, "loss": 0.0033, "lr": 3.138976376568051e-05, "epoch": 9.519251925192519, "percentage": 47.6, "elapsed_time": "3:24:37", "remaining_time": "3:45:17", "throughput": 1487.51, "total_tokens": 18263424} {"current_steps": 86535, "total_steps": 181800, "loss": 0.0032, "lr": 3.1387443386468995e-05, "epoch": 9.51980198019802, "percentage": 47.6, "elapsed_time": "3:24:38", "remaining_time": "3:45:17", "throughput": 1487.52, "total_tokens": 18264512} {"current_steps": 86540, "total_steps": 181800, "loss": 0.0152, "lr": 3.1385122948387486e-05, "epoch": 9.520352035203521, "percentage": 47.6, "elapsed_time": "3:24:39", "remaining_time": "3:45:16", "throughput": 1487.52, "total_tokens": 18265568} {"current_steps": 86545, "total_steps": 181800, "loss": 0.0039, "lr": 3.1382802451457366e-05, "epoch": 9.52090209020902, "percentage": 47.6, "elapsed_time": "3:24:39", "remaining_time": "3:45:15", "throughput": 1487.53, "total_tokens": 18266688} {"current_steps": 86550, "total_steps": 181800, "loss": 0.0098, "lr": 3.1380481895700015e-05, "epoch": 9.521452145214521, "percentage": 47.61, "elapsed_time": "3:24:40", "remaining_time": "3:45:15", "throughput": 1487.54, "total_tokens": 18267808} {"current_steps": 86555, "total_steps": 181800, "loss": 0.0129, "lr": 3.137816128113682e-05, "epoch": 9.522002200220022, "percentage": 47.61, "elapsed_time": "3:24:41", "remaining_time": "3:45:14", "throughput": 1487.54, "total_tokens": 18268832} {"current_steps": 86560, "total_steps": 181800, "loss": 0.0462, "lr": 3.137584060778918e-05, "epoch": 9.522552255225522, "percentage": 47.61, "elapsed_time": "3:24:41", "remaining_time": "3:45:13", "throughput": 1487.54, "total_tokens": 18269888} {"current_steps": 86565, "total_steps": 181800, "loss": 0.0487, "lr": 3.137351987567847e-05, "epoch": 9.523102310231023, "percentage": 47.62, "elapsed_time": "3:24:42", "remaining_time": "3:45:12", "throughput": 1487.55, "total_tokens": 18271008} {"current_steps": 86570, "total_steps": 181800, "loss": 0.0063, "lr": 3.137119908482609e-05, "epoch": 9.523652365236524, "percentage": 47.62, "elapsed_time": "3:24:43", "remaining_time": "3:45:12", "throughput": 1487.55, "total_tokens": 18272064} {"current_steps": 86575, "total_steps": 181800, "loss": 0.0467, "lr": 3.1368878235253417e-05, "epoch": 9.524202420242025, "percentage": 47.62, "elapsed_time": "3:24:44", "remaining_time": "3:45:11", "throughput": 1487.55, "total_tokens": 18273056} {"current_steps": 86580, "total_steps": 181800, "loss": 0.0224, "lr": 3.136655732698186e-05, "epoch": 9.524752475247524, "percentage": 47.62, "elapsed_time": "3:24:44", "remaining_time": "3:45:10", "throughput": 1487.54, "total_tokens": 18274048} {"current_steps": 86585, "total_steps": 181800, "loss": 0.0133, "lr": 3.136423636003279e-05, "epoch": 9.525302530253025, "percentage": 47.63, "elapsed_time": "3:24:45", "remaining_time": "3:45:09", "throughput": 1487.55, "total_tokens": 18275104} {"current_steps": 86590, "total_steps": 181800, "loss": 0.0156, "lr": 3.136191533442762e-05, "epoch": 9.525852585258527, "percentage": 47.63, "elapsed_time": "3:24:46", "remaining_time": "3:45:09", "throughput": 1487.56, "total_tokens": 18276224} {"current_steps": 86595, "total_steps": 181800, "loss": 0.0467, "lr": 3.1359594250187716e-05, "epoch": 9.526402640264026, "percentage": 47.63, "elapsed_time": "3:24:46", "remaining_time": "3:45:08", "throughput": 1487.56, "total_tokens": 18277248} {"current_steps": 86600, "total_steps": 181800, "loss": 0.0432, "lr": 3.135727310733448e-05, "epoch": 9.526952695269527, "percentage": 47.63, "elapsed_time": "3:24:47", "remaining_time": "3:45:07", "throughput": 1487.55, "total_tokens": 18278240} {"current_steps": 86605, "total_steps": 181800, "loss": 0.0902, "lr": 3.135495190588932e-05, "epoch": 9.527502750275028, "percentage": 47.64, "elapsed_time": "3:24:48", "remaining_time": "3:45:06", "throughput": 1487.55, "total_tokens": 18279264} {"current_steps": 86610, "total_steps": 181800, "loss": 0.0865, "lr": 3.135263064587362e-05, "epoch": 9.528052805280527, "percentage": 47.64, "elapsed_time": "3:24:48", "remaining_time": "3:45:06", "throughput": 1487.56, "total_tokens": 18280320} {"current_steps": 86615, "total_steps": 181800, "loss": 0.0389, "lr": 3.135030932730877e-05, "epoch": 9.528602860286028, "percentage": 47.64, "elapsed_time": "3:24:49", "remaining_time": "3:45:05", "throughput": 1487.56, "total_tokens": 18281408} {"current_steps": 86620, "total_steps": 181800, "loss": 0.0049, "lr": 3.134798795021616e-05, "epoch": 9.52915291529153, "percentage": 47.65, "elapsed_time": "3:24:50", "remaining_time": "3:45:04", "throughput": 1487.56, "total_tokens": 18282432} {"current_steps": 86625, "total_steps": 181800, "loss": 0.1147, "lr": 3.134566651461719e-05, "epoch": 9.52970297029703, "percentage": 47.65, "elapsed_time": "3:24:50", "remaining_time": "3:45:04", "throughput": 1487.57, "total_tokens": 18283520} {"current_steps": 86630, "total_steps": 181800, "loss": 0.0685, "lr": 3.134334502053326e-05, "epoch": 9.53025302530253, "percentage": 47.65, "elapsed_time": "3:24:51", "remaining_time": "3:45:03", "throughput": 1487.56, "total_tokens": 18284512} {"current_steps": 86635, "total_steps": 181800, "loss": 0.0072, "lr": 3.1341023467985764e-05, "epoch": 9.530803080308031, "percentage": 47.65, "elapsed_time": "3:24:52", "remaining_time": "3:45:02", "throughput": 1487.57, "total_tokens": 18285600} {"current_steps": 86640, "total_steps": 181800, "loss": 0.1032, "lr": 3.13387018569961e-05, "epoch": 9.531353135313532, "percentage": 47.66, "elapsed_time": "3:24:52", "remaining_time": "3:45:01", "throughput": 1487.57, "total_tokens": 18286688} {"current_steps": 86645, "total_steps": 181800, "loss": 0.0691, "lr": 3.133638018758566e-05, "epoch": 9.531903190319031, "percentage": 47.66, "elapsed_time": "3:24:53", "remaining_time": "3:45:01", "throughput": 1487.57, "total_tokens": 18287712} {"current_steps": 86650, "total_steps": 181800, "loss": 0.0929, "lr": 3.133405845977584e-05, "epoch": 9.532453245324533, "percentage": 47.66, "elapsed_time": "3:24:54", "remaining_time": "3:45:00", "throughput": 1487.58, "total_tokens": 18288800} {"current_steps": 86655, "total_steps": 181800, "loss": 0.0245, "lr": 3.133173667358804e-05, "epoch": 9.533003300330034, "percentage": 47.67, "elapsed_time": "3:24:55", "remaining_time": "3:44:59", "throughput": 1487.58, "total_tokens": 18289888} {"current_steps": 86660, "total_steps": 181800, "loss": 0.0071, "lr": 3.132941482904367e-05, "epoch": 9.533553355335533, "percentage": 47.67, "elapsed_time": "3:24:55", "remaining_time": "3:44:58", "throughput": 1487.59, "total_tokens": 18290976} {"current_steps": 86665, "total_steps": 181800, "loss": 0.0102, "lr": 3.1327092926164126e-05, "epoch": 9.534103410341034, "percentage": 47.67, "elapsed_time": "3:24:56", "remaining_time": "3:44:58", "throughput": 1487.59, "total_tokens": 18292064} {"current_steps": 86670, "total_steps": 181800, "loss": 0.0124, "lr": 3.1324770964970786e-05, "epoch": 9.534653465346535, "percentage": 47.67, "elapsed_time": "3:24:57", "remaining_time": "3:44:57", "throughput": 1487.6, "total_tokens": 18293120} {"current_steps": 86675, "total_steps": 181800, "loss": 0.0118, "lr": 3.132244894548508e-05, "epoch": 9.535203520352034, "percentage": 47.68, "elapsed_time": "3:24:57", "remaining_time": "3:44:56", "throughput": 1487.6, "total_tokens": 18294144} {"current_steps": 86680, "total_steps": 181800, "loss": 0.0321, "lr": 3.132012686772839e-05, "epoch": 9.535753575357536, "percentage": 47.68, "elapsed_time": "3:24:58", "remaining_time": "3:44:55", "throughput": 1487.6, "total_tokens": 18295200} {"current_steps": 86685, "total_steps": 181800, "loss": 0.0026, "lr": 3.131780473172212e-05, "epoch": 9.536303630363037, "percentage": 47.68, "elapsed_time": "3:24:59", "remaining_time": "3:44:55", "throughput": 1487.61, "total_tokens": 18296352} {"current_steps": 86690, "total_steps": 181800, "loss": 0.0173, "lr": 3.131548253748768e-05, "epoch": 9.536853685368538, "percentage": 47.68, "elapsed_time": "3:24:59", "remaining_time": "3:44:54", "throughput": 1487.61, "total_tokens": 18297344} {"current_steps": 86695, "total_steps": 181800, "loss": 0.0027, "lr": 3.131316028504647e-05, "epoch": 9.537403740374037, "percentage": 47.69, "elapsed_time": "3:25:00", "remaining_time": "3:44:53", "throughput": 1487.61, "total_tokens": 18298432} {"current_steps": 86700, "total_steps": 181800, "loss": 0.0125, "lr": 3.1310837974419885e-05, "epoch": 9.537953795379538, "percentage": 47.69, "elapsed_time": "3:25:01", "remaining_time": "3:44:53", "throughput": 1487.62, "total_tokens": 18299520} {"current_steps": 86705, "total_steps": 181800, "loss": 0.0046, "lr": 3.130851560562934e-05, "epoch": 9.53850385038504, "percentage": 47.69, "elapsed_time": "3:25:01", "remaining_time": "3:44:52", "throughput": 1487.63, "total_tokens": 18300672} {"current_steps": 86710, "total_steps": 181800, "loss": 0.0238, "lr": 3.130619317869624e-05, "epoch": 9.539053905390539, "percentage": 47.7, "elapsed_time": "3:25:02", "remaining_time": "3:44:51", "throughput": 1487.63, "total_tokens": 18301728} {"current_steps": 86715, "total_steps": 181800, "loss": 0.0205, "lr": 3.130387069364197e-05, "epoch": 9.53960396039604, "percentage": 47.7, "elapsed_time": "3:25:03", "remaining_time": "3:44:50", "throughput": 1487.63, "total_tokens": 18302816} {"current_steps": 86720, "total_steps": 181800, "loss": 0.0884, "lr": 3.1301548150487956e-05, "epoch": 9.54015401540154, "percentage": 47.7, "elapsed_time": "3:25:03", "remaining_time": "3:44:50", "throughput": 1487.64, "total_tokens": 18303872} {"current_steps": 86725, "total_steps": 181800, "loss": 0.0218, "lr": 3.1299225549255596e-05, "epoch": 9.54070407040704, "percentage": 47.7, "elapsed_time": "3:25:04", "remaining_time": "3:44:49", "throughput": 1487.64, "total_tokens": 18304896} {"current_steps": 86730, "total_steps": 181800, "loss": 0.0056, "lr": 3.129690288996629e-05, "epoch": 9.541254125412541, "percentage": 47.71, "elapsed_time": "3:25:05", "remaining_time": "3:44:48", "throughput": 1487.64, "total_tokens": 18305984} {"current_steps": 86735, "total_steps": 181800, "loss": 0.0034, "lr": 3.1294580172641465e-05, "epoch": 9.541804180418042, "percentage": 47.71, "elapsed_time": "3:25:06", "remaining_time": "3:44:47", "throughput": 1487.64, "total_tokens": 18307008} {"current_steps": 86740, "total_steps": 181800, "loss": 0.0208, "lr": 3.1292257397302506e-05, "epoch": 9.542354235423542, "percentage": 47.71, "elapsed_time": "3:25:06", "remaining_time": "3:44:47", "throughput": 1487.65, "total_tokens": 18308064} {"current_steps": 86745, "total_steps": 181800, "loss": 0.0112, "lr": 3.1289934563970826e-05, "epoch": 9.542904290429043, "percentage": 47.71, "elapsed_time": "3:25:07", "remaining_time": "3:44:46", "throughput": 1487.65, "total_tokens": 18309120} {"current_steps": 86750, "total_steps": 181800, "loss": 0.0871, "lr": 3.1287611672667846e-05, "epoch": 9.543454345434544, "percentage": 47.72, "elapsed_time": "3:25:08", "remaining_time": "3:44:45", "throughput": 1487.64, "total_tokens": 18310112} {"current_steps": 86755, "total_steps": 181800, "loss": 0.0021, "lr": 3.1285288723414964e-05, "epoch": 9.544004400440045, "percentage": 47.72, "elapsed_time": "3:25:08", "remaining_time": "3:44:44", "throughput": 1487.66, "total_tokens": 18311264} {"current_steps": 86760, "total_steps": 181800, "loss": 0.0031, "lr": 3.1282965716233594e-05, "epoch": 9.544554455445544, "percentage": 47.72, "elapsed_time": "3:25:09", "remaining_time": "3:44:44", "throughput": 1487.66, "total_tokens": 18312384} {"current_steps": 86765, "total_steps": 181800, "loss": 0.006, "lr": 3.1280642651145135e-05, "epoch": 9.545104510451045, "percentage": 47.73, "elapsed_time": "3:25:10", "remaining_time": "3:44:43", "throughput": 1487.66, "total_tokens": 18313440} {"current_steps": 86770, "total_steps": 181800, "loss": 0.0053, "lr": 3.127831952817101e-05, "epoch": 9.545654565456546, "percentage": 47.73, "elapsed_time": "3:25:10", "remaining_time": "3:44:42", "throughput": 1487.66, "total_tokens": 18314464} {"current_steps": 86775, "total_steps": 181800, "loss": 0.0443, "lr": 3.127599634733263e-05, "epoch": 9.546204620462046, "percentage": 47.73, "elapsed_time": "3:25:11", "remaining_time": "3:44:42", "throughput": 1487.66, "total_tokens": 18315488} {"current_steps": 86780, "total_steps": 181800, "loss": 0.0204, "lr": 3.12736731086514e-05, "epoch": 9.546754675467547, "percentage": 47.73, "elapsed_time": "3:25:12", "remaining_time": "3:44:41", "throughput": 1487.66, "total_tokens": 18316512} {"current_steps": 86785, "total_steps": 181800, "loss": 0.1416, "lr": 3.1271349812148736e-05, "epoch": 9.547304730473048, "percentage": 47.74, "elapsed_time": "3:25:12", "remaining_time": "3:44:40", "throughput": 1487.66, "total_tokens": 18317536} {"current_steps": 86790, "total_steps": 181800, "loss": 0.0274, "lr": 3.1269026457846054e-05, "epoch": 9.547854785478547, "percentage": 47.74, "elapsed_time": "3:25:13", "remaining_time": "3:44:39", "throughput": 1487.66, "total_tokens": 18318560} {"current_steps": 86795, "total_steps": 181800, "loss": 0.0132, "lr": 3.126670304576476e-05, "epoch": 9.548404840484048, "percentage": 47.74, "elapsed_time": "3:25:14", "remaining_time": "3:44:39", "throughput": 1487.67, "total_tokens": 18319616} {"current_steps": 86800, "total_steps": 181800, "loss": 0.0119, "lr": 3.126437957592627e-05, "epoch": 9.54895489548955, "percentage": 47.74, "elapsed_time": "3:25:15", "remaining_time": "3:44:38", "throughput": 1487.67, "total_tokens": 18320704} {"current_steps": 86805, "total_steps": 181800, "loss": 0.1279, "lr": 3.126205604835201e-05, "epoch": 9.549504950495049, "percentage": 47.75, "elapsed_time": "3:25:15", "remaining_time": "3:44:37", "throughput": 1487.67, "total_tokens": 18321728} {"current_steps": 86810, "total_steps": 181800, "loss": 0.0033, "lr": 3.125973246306337e-05, "epoch": 9.55005500550055, "percentage": 47.75, "elapsed_time": "3:25:16", "remaining_time": "3:44:36", "throughput": 1487.67, "total_tokens": 18322720} {"current_steps": 86815, "total_steps": 181800, "loss": 0.0321, "lr": 3.125740882008178e-05, "epoch": 9.55060506050605, "percentage": 47.75, "elapsed_time": "3:25:17", "remaining_time": "3:44:36", "throughput": 1487.67, "total_tokens": 18323808} {"current_steps": 86820, "total_steps": 181800, "loss": 0.0023, "lr": 3.125508511942866e-05, "epoch": 9.551155115511552, "percentage": 47.76, "elapsed_time": "3:25:17", "remaining_time": "3:44:35", "throughput": 1487.67, "total_tokens": 18324832} {"current_steps": 86825, "total_steps": 181800, "loss": 0.1695, "lr": 3.125276136112542e-05, "epoch": 9.551705170517051, "percentage": 47.76, "elapsed_time": "3:25:18", "remaining_time": "3:44:34", "throughput": 1487.68, "total_tokens": 18325888} {"current_steps": 86830, "total_steps": 181800, "loss": 0.0337, "lr": 3.1250437545193484e-05, "epoch": 9.552255225522552, "percentage": 47.76, "elapsed_time": "3:25:19", "remaining_time": "3:44:34", "throughput": 1487.68, "total_tokens": 18326912} {"current_steps": 86835, "total_steps": 181800, "loss": 0.0191, "lr": 3.124811367165426e-05, "epoch": 9.552805280528053, "percentage": 47.76, "elapsed_time": "3:25:19", "remaining_time": "3:44:33", "throughput": 1487.69, "total_tokens": 18328064} {"current_steps": 86840, "total_steps": 181800, "loss": 0.0096, "lr": 3.1245789740529174e-05, "epoch": 9.553355335533553, "percentage": 47.77, "elapsed_time": "3:25:20", "remaining_time": "3:44:32", "throughput": 1487.68, "total_tokens": 18329056} {"current_steps": 86845, "total_steps": 181800, "loss": 0.0112, "lr": 3.1243465751839635e-05, "epoch": 9.553905390539054, "percentage": 47.77, "elapsed_time": "3:25:21", "remaining_time": "3:44:31", "throughput": 1487.68, "total_tokens": 18330080} {"current_steps": 86850, "total_steps": 181800, "loss": 0.008, "lr": 3.124114170560708e-05, "epoch": 9.554455445544555, "percentage": 47.77, "elapsed_time": "3:25:21", "remaining_time": "3:44:31", "throughput": 1487.69, "total_tokens": 18331168} {"current_steps": 86855, "total_steps": 181800, "loss": 0.0091, "lr": 3.123881760185291e-05, "epoch": 9.555005500550054, "percentage": 47.78, "elapsed_time": "3:25:22", "remaining_time": "3:44:30", "throughput": 1487.69, "total_tokens": 18332160} {"current_steps": 86860, "total_steps": 181800, "loss": 0.0282, "lr": 3.123649344059854e-05, "epoch": 9.555555555555555, "percentage": 47.78, "elapsed_time": "3:25:23", "remaining_time": "3:44:29", "throughput": 1487.69, "total_tokens": 18333184} {"current_steps": 86865, "total_steps": 181800, "loss": 0.2271, "lr": 3.1234169221865415e-05, "epoch": 9.556105610561056, "percentage": 47.78, "elapsed_time": "3:25:23", "remaining_time": "3:44:28", "throughput": 1487.69, "total_tokens": 18334240} {"current_steps": 86870, "total_steps": 181800, "loss": 0.0332, "lr": 3.1231844945674943e-05, "epoch": 9.556655665566556, "percentage": 47.78, "elapsed_time": "3:25:24", "remaining_time": "3:44:28", "throughput": 1487.7, "total_tokens": 18335328} {"current_steps": 86875, "total_steps": 181800, "loss": 0.004, "lr": 3.122952061204854e-05, "epoch": 9.557205720572057, "percentage": 47.79, "elapsed_time": "3:25:25", "remaining_time": "3:44:27", "throughput": 1487.7, "total_tokens": 18336416} {"current_steps": 86880, "total_steps": 181800, "loss": 0.0097, "lr": 3.122719622100765e-05, "epoch": 9.557755775577558, "percentage": 47.79, "elapsed_time": "3:25:26", "remaining_time": "3:44:26", "throughput": 1487.7, "total_tokens": 18337472} {"current_steps": 86885, "total_steps": 181800, "loss": 0.0819, "lr": 3.122487177257367e-05, "epoch": 9.558305830583059, "percentage": 47.79, "elapsed_time": "3:25:26", "remaining_time": "3:44:25", "throughput": 1487.71, "total_tokens": 18338528} {"current_steps": 86890, "total_steps": 181800, "loss": 0.0856, "lr": 3.122254726676803e-05, "epoch": 9.558855885588558, "percentage": 47.79, "elapsed_time": "3:25:27", "remaining_time": "3:44:25", "throughput": 1487.71, "total_tokens": 18339648} {"current_steps": 86895, "total_steps": 181800, "loss": 0.0545, "lr": 3.122022270361216e-05, "epoch": 9.55940594059406, "percentage": 47.8, "elapsed_time": "3:25:28", "remaining_time": "3:44:24", "throughput": 1487.71, "total_tokens": 18340672} {"current_steps": 86900, "total_steps": 181800, "loss": 0.0298, "lr": 3.121789808312748e-05, "epoch": 9.55995599559956, "percentage": 47.8, "elapsed_time": "3:25:28", "remaining_time": "3:44:23", "throughput": 1487.71, "total_tokens": 18341664} {"current_steps": 86905, "total_steps": 181800, "loss": 0.0252, "lr": 3.121557340533543e-05, "epoch": 9.56050605060506, "percentage": 47.8, "elapsed_time": "3:25:29", "remaining_time": "3:44:23", "throughput": 1487.71, "total_tokens": 18342720} {"current_steps": 86910, "total_steps": 181800, "loss": 0.0167, "lr": 3.1213248670257414e-05, "epoch": 9.561056105610561, "percentage": 47.81, "elapsed_time": "3:25:30", "remaining_time": "3:44:22", "throughput": 1487.72, "total_tokens": 18343808} {"current_steps": 86915, "total_steps": 181800, "loss": 0.0031, "lr": 3.1210923877914866e-05, "epoch": 9.561606160616062, "percentage": 47.81, "elapsed_time": "3:25:30", "remaining_time": "3:44:21", "throughput": 1487.72, "total_tokens": 18344832} {"current_steps": 86920, "total_steps": 181800, "loss": 0.0709, "lr": 3.12085990283292e-05, "epoch": 9.562156215621561, "percentage": 47.81, "elapsed_time": "3:25:31", "remaining_time": "3:44:20", "throughput": 1487.73, "total_tokens": 18345952} {"current_steps": 86925, "total_steps": 181800, "loss": 0.0413, "lr": 3.120627412152188e-05, "epoch": 9.562706270627062, "percentage": 47.81, "elapsed_time": "3:25:32", "remaining_time": "3:44:20", "throughput": 1487.73, "total_tokens": 18347008} {"current_steps": 86930, "total_steps": 181800, "loss": 0.0484, "lr": 3.1203949157514296e-05, "epoch": 9.563256325632564, "percentage": 47.82, "elapsed_time": "3:25:32", "remaining_time": "3:44:19", "throughput": 1487.73, "total_tokens": 18348096} {"current_steps": 86935, "total_steps": 181800, "loss": 0.0263, "lr": 3.120162413632789e-05, "epoch": 9.563806380638063, "percentage": 47.82, "elapsed_time": "3:25:33", "remaining_time": "3:44:18", "throughput": 1487.74, "total_tokens": 18349152} {"current_steps": 86940, "total_steps": 181800, "loss": 0.011, "lr": 3.1199299057984096e-05, "epoch": 9.564356435643564, "percentage": 47.82, "elapsed_time": "3:25:34", "remaining_time": "3:44:17", "throughput": 1487.74, "total_tokens": 18350208} {"current_steps": 86945, "total_steps": 181800, "loss": 0.0878, "lr": 3.119697392250433e-05, "epoch": 9.564906490649065, "percentage": 47.82, "elapsed_time": "3:25:34", "remaining_time": "3:44:17", "throughput": 1487.74, "total_tokens": 18351200} {"current_steps": 86950, "total_steps": 181800, "loss": 0.0388, "lr": 3.1194648729910035e-05, "epoch": 9.565456545654566, "percentage": 47.83, "elapsed_time": "3:25:35", "remaining_time": "3:44:16", "throughput": 1487.74, "total_tokens": 18352224} {"current_steps": 86955, "total_steps": 181800, "loss": 0.0086, "lr": 3.119232348022263e-05, "epoch": 9.566006600660065, "percentage": 47.83, "elapsed_time": "3:25:36", "remaining_time": "3:44:15", "throughput": 1487.74, "total_tokens": 18353248} {"current_steps": 86960, "total_steps": 181800, "loss": 0.0245, "lr": 3.118999817346355e-05, "epoch": 9.566556655665567, "percentage": 47.83, "elapsed_time": "3:25:37", "remaining_time": "3:44:14", "throughput": 1487.74, "total_tokens": 18354304} {"current_steps": 86965, "total_steps": 181800, "loss": 0.0669, "lr": 3.118767280965423e-05, "epoch": 9.567106710671068, "percentage": 47.84, "elapsed_time": "3:25:37", "remaining_time": "3:44:14", "throughput": 1487.74, "total_tokens": 18355360} {"current_steps": 86970, "total_steps": 181800, "loss": 0.021, "lr": 3.1185347388816105e-05, "epoch": 9.567656765676567, "percentage": 47.84, "elapsed_time": "3:25:38", "remaining_time": "3:44:13", "throughput": 1487.75, "total_tokens": 18356448} {"current_steps": 86975, "total_steps": 181800, "loss": 0.011, "lr": 3.1183021910970586e-05, "epoch": 9.568206820682068, "percentage": 47.84, "elapsed_time": "3:25:39", "remaining_time": "3:44:12", "throughput": 1487.75, "total_tokens": 18357504} {"current_steps": 86980, "total_steps": 181800, "loss": 0.062, "lr": 3.1180696376139136e-05, "epoch": 9.56875687568757, "percentage": 47.84, "elapsed_time": "3:25:39", "remaining_time": "3:44:12", "throughput": 1487.75, "total_tokens": 18358592} {"current_steps": 86985, "total_steps": 181800, "loss": 0.0308, "lr": 3.117837078434317e-05, "epoch": 9.569306930693068, "percentage": 47.85, "elapsed_time": "3:25:40", "remaining_time": "3:44:11", "throughput": 1487.75, "total_tokens": 18359616} {"current_steps": 86990, "total_steps": 181800, "loss": 0.0379, "lr": 3.117604513560412e-05, "epoch": 9.56985698569857, "percentage": 47.85, "elapsed_time": "3:25:41", "remaining_time": "3:44:10", "throughput": 1487.75, "total_tokens": 18360640} {"current_steps": 86995, "total_steps": 181800, "loss": 0.0074, "lr": 3.117371942994343e-05, "epoch": 9.57040704070407, "percentage": 47.85, "elapsed_time": "3:25:41", "remaining_time": "3:44:09", "throughput": 1487.76, "total_tokens": 18361728} {"current_steps": 87000, "total_steps": 181800, "loss": 0.0125, "lr": 3.117139366738253e-05, "epoch": 9.570957095709572, "percentage": 47.85, "elapsed_time": "3:25:42", "remaining_time": "3:44:09", "throughput": 1487.76, "total_tokens": 18362720} {"current_steps": 87005, "total_steps": 181800, "loss": 0.0022, "lr": 3.116906784794285e-05, "epoch": 9.571507150715071, "percentage": 47.86, "elapsed_time": "3:25:43", "remaining_time": "3:44:08", "throughput": 1487.76, "total_tokens": 18363840} {"current_steps": 87010, "total_steps": 181800, "loss": 0.0431, "lr": 3.116674197164583e-05, "epoch": 9.572057205720572, "percentage": 47.86, "elapsed_time": "3:25:43", "remaining_time": "3:44:07", "throughput": 1487.76, "total_tokens": 18364896} {"current_steps": 87015, "total_steps": 181800, "loss": 0.0768, "lr": 3.116441603851292e-05, "epoch": 9.572607260726073, "percentage": 47.86, "elapsed_time": "3:25:44", "remaining_time": "3:44:06", "throughput": 1487.77, "total_tokens": 18366016} {"current_steps": 87020, "total_steps": 181800, "loss": 0.0422, "lr": 3.1162090048565546e-05, "epoch": 9.573157315731573, "percentage": 47.87, "elapsed_time": "3:25:45", "remaining_time": "3:44:06", "throughput": 1487.77, "total_tokens": 18367008} {"current_steps": 87025, "total_steps": 181800, "loss": 0.0119, "lr": 3.115976400182514e-05, "epoch": 9.573707370737074, "percentage": 47.87, "elapsed_time": "3:25:46", "remaining_time": "3:44:05", "throughput": 1487.77, "total_tokens": 18368064} {"current_steps": 87030, "total_steps": 181800, "loss": 0.0255, "lr": 3.1157437898313144e-05, "epoch": 9.574257425742575, "percentage": 47.87, "elapsed_time": "3:25:46", "remaining_time": "3:44:04", "throughput": 1487.78, "total_tokens": 18369152} {"current_steps": 87035, "total_steps": 181800, "loss": 0.0176, "lr": 3.115511173805099e-05, "epoch": 9.574807480748074, "percentage": 47.87, "elapsed_time": "3:25:47", "remaining_time": "3:44:04", "throughput": 1487.77, "total_tokens": 18370144} {"current_steps": 87040, "total_steps": 181800, "loss": 0.0008, "lr": 3.115278552106014e-05, "epoch": 9.575357535753575, "percentage": 47.88, "elapsed_time": "3:25:48", "remaining_time": "3:44:03", "throughput": 1487.78, "total_tokens": 18371232} {"current_steps": 87045, "total_steps": 181800, "loss": 0.005, "lr": 3.115045924736201e-05, "epoch": 9.575907590759076, "percentage": 47.88, "elapsed_time": "3:25:48", "remaining_time": "3:44:02", "throughput": 1487.78, "total_tokens": 18372320} {"current_steps": 87050, "total_steps": 181800, "loss": 0.1052, "lr": 3.114813291697804e-05, "epoch": 9.576457645764577, "percentage": 47.88, "elapsed_time": "3:25:49", "remaining_time": "3:44:01", "throughput": 1487.79, "total_tokens": 18373376} {"current_steps": 87055, "total_steps": 181800, "loss": 0.003, "lr": 3.114580652992969e-05, "epoch": 9.577007700770077, "percentage": 47.89, "elapsed_time": "3:25:50", "remaining_time": "3:44:01", "throughput": 1487.78, "total_tokens": 18374368} {"current_steps": 87060, "total_steps": 181800, "loss": 0.2084, "lr": 3.114348008623839e-05, "epoch": 9.577557755775578, "percentage": 47.89, "elapsed_time": "3:25:50", "remaining_time": "3:44:00", "throughput": 1487.78, "total_tokens": 18375392} {"current_steps": 87065, "total_steps": 181800, "loss": 0.1, "lr": 3.114115358592558e-05, "epoch": 9.578107810781079, "percentage": 47.89, "elapsed_time": "3:25:51", "remaining_time": "3:43:59", "throughput": 1487.79, "total_tokens": 18376448} {"current_steps": 87070, "total_steps": 181800, "loss": 0.0043, "lr": 3.113882702901271e-05, "epoch": 9.578657865786578, "percentage": 47.89, "elapsed_time": "3:25:52", "remaining_time": "3:43:58", "throughput": 1487.78, "total_tokens": 18377408} {"current_steps": 87075, "total_steps": 181800, "loss": 0.0105, "lr": 3.113650041552121e-05, "epoch": 9.57920792079208, "percentage": 47.9, "elapsed_time": "3:25:52", "remaining_time": "3:43:58", "throughput": 1487.78, "total_tokens": 18378432} {"current_steps": 87080, "total_steps": 181800, "loss": 0.0035, "lr": 3.113417374547252e-05, "epoch": 9.57975797579758, "percentage": 47.9, "elapsed_time": "3:25:53", "remaining_time": "3:43:57", "throughput": 1487.78, "total_tokens": 18379488} {"current_steps": 87085, "total_steps": 181800, "loss": 0.0623, "lr": 3.113184701888811e-05, "epoch": 9.58030803080308, "percentage": 47.9, "elapsed_time": "3:25:54", "remaining_time": "3:43:56", "throughput": 1487.78, "total_tokens": 18380512} {"current_steps": 87090, "total_steps": 181800, "loss": 0.0135, "lr": 3.1129520235789404e-05, "epoch": 9.58085808580858, "percentage": 47.9, "elapsed_time": "3:25:54", "remaining_time": "3:43:55", "throughput": 1487.79, "total_tokens": 18381568} {"current_steps": 87095, "total_steps": 181800, "loss": 0.0172, "lr": 3.112719339619785e-05, "epoch": 9.581408140814082, "percentage": 47.91, "elapsed_time": "3:25:55", "remaining_time": "3:43:55", "throughput": 1487.79, "total_tokens": 18382592} {"current_steps": 87100, "total_steps": 181800, "loss": 0.0663, "lr": 3.11248665001349e-05, "epoch": 9.581958195819581, "percentage": 47.91, "elapsed_time": "3:25:56", "remaining_time": "3:43:54", "throughput": 1487.78, "total_tokens": 18383584} {"current_steps": 87105, "total_steps": 181800, "loss": 0.0074, "lr": 3.1122539547621985e-05, "epoch": 9.582508250825082, "percentage": 47.91, "elapsed_time": "3:25:57", "remaining_time": "3:43:53", "throughput": 1487.78, "total_tokens": 18384640} {"current_steps": 87110, "total_steps": 181800, "loss": 0.0141, "lr": 3.1120212538680564e-05, "epoch": 9.583058305830583, "percentage": 47.92, "elapsed_time": "3:25:57", "remaining_time": "3:43:53", "throughput": 1487.79, "total_tokens": 18385728} {"current_steps": 87115, "total_steps": 181800, "loss": 0.1294, "lr": 3.1117885473332095e-05, "epoch": 9.583608360836084, "percentage": 47.92, "elapsed_time": "3:25:58", "remaining_time": "3:43:52", "throughput": 1487.79, "total_tokens": 18386752} {"current_steps": 87120, "total_steps": 181800, "loss": 0.0025, "lr": 3.111555835159799e-05, "epoch": 9.584158415841584, "percentage": 47.92, "elapsed_time": "3:25:59", "remaining_time": "3:43:51", "throughput": 1487.79, "total_tokens": 18387744} {"current_steps": 87125, "total_steps": 181800, "loss": 0.0099, "lr": 3.111323117349973e-05, "epoch": 9.584708470847085, "percentage": 47.92, "elapsed_time": "3:25:59", "remaining_time": "3:43:50", "throughput": 1487.8, "total_tokens": 18388864} {"current_steps": 87130, "total_steps": 181800, "loss": 0.0316, "lr": 3.111090393905874e-05, "epoch": 9.585258525852586, "percentage": 47.93, "elapsed_time": "3:26:00", "remaining_time": "3:43:50", "throughput": 1487.8, "total_tokens": 18389920} {"current_steps": 87135, "total_steps": 181800, "loss": 0.0127, "lr": 3.11085766482965e-05, "epoch": 9.585808580858085, "percentage": 47.93, "elapsed_time": "3:26:01", "remaining_time": "3:43:49", "throughput": 1487.8, "total_tokens": 18390976} {"current_steps": 87140, "total_steps": 181800, "loss": 0.0126, "lr": 3.1106249301234424e-05, "epoch": 9.586358635863586, "percentage": 47.93, "elapsed_time": "3:26:01", "remaining_time": "3:43:48", "throughput": 1487.8, "total_tokens": 18392032} {"current_steps": 87145, "total_steps": 181800, "loss": 0.003, "lr": 3.110392189789399e-05, "epoch": 9.586908690869087, "percentage": 47.93, "elapsed_time": "3:26:02", "remaining_time": "3:43:47", "throughput": 1487.8, "total_tokens": 18393088} {"current_steps": 87150, "total_steps": 181800, "loss": 0.0752, "lr": 3.110159443829662e-05, "epoch": 9.587458745874587, "percentage": 47.94, "elapsed_time": "3:26:03", "remaining_time": "3:43:47", "throughput": 1487.81, "total_tokens": 18394144} {"current_steps": 87155, "total_steps": 181800, "loss": 0.0105, "lr": 3.10992669224638e-05, "epoch": 9.588008800880088, "percentage": 47.94, "elapsed_time": "3:26:03", "remaining_time": "3:43:46", "throughput": 1487.81, "total_tokens": 18395200} {"current_steps": 87160, "total_steps": 181800, "loss": 0.0777, "lr": 3.109693935041696e-05, "epoch": 9.588558855885589, "percentage": 47.94, "elapsed_time": "3:26:04", "remaining_time": "3:43:45", "throughput": 1487.81, "total_tokens": 18396256} {"current_steps": 87165, "total_steps": 181800, "loss": 0.0242, "lr": 3.109461172217755e-05, "epoch": 9.589108910891088, "percentage": 47.95, "elapsed_time": "3:26:05", "remaining_time": "3:43:45", "throughput": 1487.82, "total_tokens": 18397312} {"current_steps": 87170, "total_steps": 181800, "loss": 0.0032, "lr": 3.109228403776703e-05, "epoch": 9.58965896589659, "percentage": 47.95, "elapsed_time": "3:26:06", "remaining_time": "3:43:44", "throughput": 1487.82, "total_tokens": 18398368} {"current_steps": 87175, "total_steps": 181800, "loss": 0.0908, "lr": 3.1089956297206855e-05, "epoch": 9.59020902090209, "percentage": 47.95, "elapsed_time": "3:26:06", "remaining_time": "3:43:43", "throughput": 1487.82, "total_tokens": 18399456} {"current_steps": 87180, "total_steps": 181800, "loss": 0.0205, "lr": 3.1087628500518464e-05, "epoch": 9.590759075907592, "percentage": 47.95, "elapsed_time": "3:26:07", "remaining_time": "3:43:42", "throughput": 1487.83, "total_tokens": 18400512} {"current_steps": 87185, "total_steps": 181800, "loss": 0.0138, "lr": 3.1085300647723335e-05, "epoch": 9.591309130913091, "percentage": 47.96, "elapsed_time": "3:26:08", "remaining_time": "3:43:42", "throughput": 1487.83, "total_tokens": 18401568} {"current_steps": 87190, "total_steps": 181800, "loss": 0.0082, "lr": 3.10829727388429e-05, "epoch": 9.591859185918592, "percentage": 47.96, "elapsed_time": "3:26:08", "remaining_time": "3:43:41", "throughput": 1487.83, "total_tokens": 18402624} {"current_steps": 87195, "total_steps": 181800, "loss": 0.0091, "lr": 3.108064477389863e-05, "epoch": 9.592409240924093, "percentage": 47.96, "elapsed_time": "3:26:09", "remaining_time": "3:43:40", "throughput": 1487.84, "total_tokens": 18403712} {"current_steps": 87200, "total_steps": 181800, "loss": 0.0229, "lr": 3.1078316752911975e-05, "epoch": 9.592959295929592, "percentage": 47.96, "elapsed_time": "3:26:10", "remaining_time": "3:43:39", "throughput": 1487.84, "total_tokens": 18404736} {"current_steps": 87205, "total_steps": 181800, "loss": 0.0125, "lr": 3.1075988675904386e-05, "epoch": 9.593509350935093, "percentage": 47.97, "elapsed_time": "3:26:10", "remaining_time": "3:43:39", "throughput": 1487.84, "total_tokens": 18405760} {"current_steps": 87210, "total_steps": 181800, "loss": 0.0133, "lr": 3.107366054289733e-05, "epoch": 9.594059405940595, "percentage": 47.97, "elapsed_time": "3:26:11", "remaining_time": "3:43:38", "throughput": 1487.84, "total_tokens": 18406848} {"current_steps": 87215, "total_steps": 181800, "loss": 0.0027, "lr": 3.1071332353912255e-05, "epoch": 9.594609460946094, "percentage": 47.97, "elapsed_time": "3:26:12", "remaining_time": "3:43:37", "throughput": 1487.85, "total_tokens": 18407936} {"current_steps": 87220, "total_steps": 181800, "loss": 0.0033, "lr": 3.1069004108970634e-05, "epoch": 9.595159515951595, "percentage": 47.98, "elapsed_time": "3:26:12", "remaining_time": "3:43:36", "throughput": 1487.85, "total_tokens": 18408960} {"current_steps": 87225, "total_steps": 181800, "loss": 0.0388, "lr": 3.10666758080939e-05, "epoch": 9.595709570957096, "percentage": 47.98, "elapsed_time": "3:26:13", "remaining_time": "3:43:36", "throughput": 1487.86, "total_tokens": 18410112} {"current_steps": 87230, "total_steps": 181800, "loss": 0.0734, "lr": 3.106434745130354e-05, "epoch": 9.596259625962595, "percentage": 47.98, "elapsed_time": "3:26:14", "remaining_time": "3:43:35", "throughput": 1487.85, "total_tokens": 18411104} {"current_steps": 87235, "total_steps": 181800, "loss": 0.0605, "lr": 3.106201903862099e-05, "epoch": 9.596809680968097, "percentage": 47.98, "elapsed_time": "3:26:14", "remaining_time": "3:43:34", "throughput": 1487.86, "total_tokens": 18412192} {"current_steps": 87240, "total_steps": 181800, "loss": 0.123, "lr": 3.105969057006772e-05, "epoch": 9.597359735973598, "percentage": 47.99, "elapsed_time": "3:26:15", "remaining_time": "3:43:34", "throughput": 1487.86, "total_tokens": 18413216} {"current_steps": 87245, "total_steps": 181800, "loss": 0.0164, "lr": 3.105736204566519e-05, "epoch": 9.597909790979099, "percentage": 47.99, "elapsed_time": "3:26:16", "remaining_time": "3:43:33", "throughput": 1487.86, "total_tokens": 18414304} {"current_steps": 87250, "total_steps": 181800, "loss": 0.0054, "lr": 3.1055033465434864e-05, "epoch": 9.598459845984598, "percentage": 47.99, "elapsed_time": "3:26:17", "remaining_time": "3:43:32", "throughput": 1487.86, "total_tokens": 18415360} {"current_steps": 87255, "total_steps": 181800, "loss": 0.0026, "lr": 3.1052704829398195e-05, "epoch": 9.599009900990099, "percentage": 48.0, "elapsed_time": "3:26:17", "remaining_time": "3:43:31", "throughput": 1487.86, "total_tokens": 18416384} {"current_steps": 87260, "total_steps": 181800, "loss": 0.0626, "lr": 3.1050376137576654e-05, "epoch": 9.5995599559956, "percentage": 48.0, "elapsed_time": "3:26:18", "remaining_time": "3:43:31", "throughput": 1487.87, "total_tokens": 18417472} {"current_steps": 87265, "total_steps": 181800, "loss": 0.0095, "lr": 3.104804738999169e-05, "epoch": 9.6001100110011, "percentage": 48.0, "elapsed_time": "3:26:19", "remaining_time": "3:43:30", "throughput": 1487.87, "total_tokens": 18418496} {"current_steps": 87270, "total_steps": 181800, "loss": 0.0035, "lr": 3.1045718586664786e-05, "epoch": 9.6006600660066, "percentage": 48.0, "elapsed_time": "3:26:19", "remaining_time": "3:43:29", "throughput": 1487.85, "total_tokens": 18419520} {"current_steps": 87275, "total_steps": 181800, "loss": 0.004, "lr": 3.1043389727617393e-05, "epoch": 9.601210121012102, "percentage": 48.01, "elapsed_time": "3:26:20", "remaining_time": "3:43:29", "throughput": 1487.85, "total_tokens": 18420544} {"current_steps": 87280, "total_steps": 181800, "loss": 0.0861, "lr": 3.104106081287098e-05, "epoch": 9.601760176017601, "percentage": 48.01, "elapsed_time": "3:26:21", "remaining_time": "3:43:28", "throughput": 1487.85, "total_tokens": 18421568} {"current_steps": 87285, "total_steps": 181800, "loss": 0.0099, "lr": 3.1038731842447005e-05, "epoch": 9.602310231023102, "percentage": 48.01, "elapsed_time": "3:26:22", "remaining_time": "3:43:27", "throughput": 1487.85, "total_tokens": 18422656} {"current_steps": 87290, "total_steps": 181800, "loss": 0.0117, "lr": 3.103640281636693e-05, "epoch": 9.602860286028603, "percentage": 48.01, "elapsed_time": "3:26:22", "remaining_time": "3:43:26", "throughput": 1487.85, "total_tokens": 18423680} {"current_steps": 87295, "total_steps": 181800, "loss": 0.0037, "lr": 3.103407373465223e-05, "epoch": 9.603410341034103, "percentage": 48.02, "elapsed_time": "3:26:23", "remaining_time": "3:43:26", "throughput": 1487.85, "total_tokens": 18424736} {"current_steps": 87300, "total_steps": 181800, "loss": 0.0658, "lr": 3.103174459732437e-05, "epoch": 9.603960396039604, "percentage": 48.02, "elapsed_time": "3:26:24", "remaining_time": "3:43:25", "throughput": 1487.86, "total_tokens": 18425792} {"current_steps": 87305, "total_steps": 181800, "loss": 0.0499, "lr": 3.102941540440482e-05, "epoch": 9.604510451045105, "percentage": 48.02, "elapsed_time": "3:26:24", "remaining_time": "3:43:24", "throughput": 1487.86, "total_tokens": 18426816} {"current_steps": 87310, "total_steps": 181800, "loss": 0.0177, "lr": 3.102708615591504e-05, "epoch": 9.605060506050606, "percentage": 48.03, "elapsed_time": "3:26:25", "remaining_time": "3:43:24", "throughput": 1487.85, "total_tokens": 18427808} {"current_steps": 87315, "total_steps": 181800, "loss": 0.0199, "lr": 3.102475685187649e-05, "epoch": 9.605610561056105, "percentage": 48.03, "elapsed_time": "3:26:26", "remaining_time": "3:43:23", "throughput": 1487.86, "total_tokens": 18428864} {"current_steps": 87320, "total_steps": 181800, "loss": 0.0569, "lr": 3.102242749231065e-05, "epoch": 9.606160616061606, "percentage": 48.03, "elapsed_time": "3:26:26", "remaining_time": "3:43:22", "throughput": 1487.86, "total_tokens": 18429888} {"current_steps": 87325, "total_steps": 181800, "loss": 0.0042, "lr": 3.102009807723899e-05, "epoch": 9.606710671067107, "percentage": 48.03, "elapsed_time": "3:26:27", "remaining_time": "3:43:21", "throughput": 1487.86, "total_tokens": 18430912} {"current_steps": 87330, "total_steps": 181800, "loss": 0.0687, "lr": 3.101776860668297e-05, "epoch": 9.607260726072607, "percentage": 48.04, "elapsed_time": "3:26:28", "remaining_time": "3:43:21", "throughput": 1487.86, "total_tokens": 18431936} {"current_steps": 87335, "total_steps": 181800, "loss": 0.0058, "lr": 3.1015439080664074e-05, "epoch": 9.607810781078108, "percentage": 48.04, "elapsed_time": "3:26:28", "remaining_time": "3:43:20", "throughput": 1487.85, "total_tokens": 18432928} {"current_steps": 87340, "total_steps": 181800, "loss": 0.0092, "lr": 3.101310949920375e-05, "epoch": 9.608360836083609, "percentage": 48.04, "elapsed_time": "3:26:29", "remaining_time": "3:43:19", "throughput": 1487.85, "total_tokens": 18433952} {"current_steps": 87345, "total_steps": 181800, "loss": 0.0121, "lr": 3.1010779862323485e-05, "epoch": 9.608910891089108, "percentage": 48.04, "elapsed_time": "3:26:30", "remaining_time": "3:43:18", "throughput": 1487.85, "total_tokens": 18434976} {"current_steps": 87350, "total_steps": 181800, "loss": 0.1665, "lr": 3.1008450170044754e-05, "epoch": 9.60946094609461, "percentage": 48.05, "elapsed_time": "3:26:31", "remaining_time": "3:43:18", "throughput": 1487.85, "total_tokens": 18436032} {"current_steps": 87355, "total_steps": 181800, "loss": 0.0699, "lr": 3.100612042238901e-05, "epoch": 9.61001100110011, "percentage": 48.05, "elapsed_time": "3:26:31", "remaining_time": "3:43:17", "throughput": 1487.86, "total_tokens": 18437088} {"current_steps": 87360, "total_steps": 181800, "loss": 0.1387, "lr": 3.100379061937774e-05, "epoch": 9.61056105610561, "percentage": 48.05, "elapsed_time": "3:26:32", "remaining_time": "3:43:16", "throughput": 1487.86, "total_tokens": 18438176} {"current_steps": 87365, "total_steps": 181800, "loss": 0.003, "lr": 3.100146076103241e-05, "epoch": 9.61111111111111, "percentage": 48.06, "elapsed_time": "3:26:33", "remaining_time": "3:43:16", "throughput": 1487.86, "total_tokens": 18439232} {"current_steps": 87370, "total_steps": 181800, "loss": 0.0135, "lr": 3.09991308473745e-05, "epoch": 9.611661166116612, "percentage": 48.06, "elapsed_time": "3:26:33", "remaining_time": "3:43:15", "throughput": 1487.86, "total_tokens": 18440256} {"current_steps": 87375, "total_steps": 181800, "loss": 0.0058, "lr": 3.099680087842549e-05, "epoch": 9.612211221122113, "percentage": 48.06, "elapsed_time": "3:26:34", "remaining_time": "3:43:14", "throughput": 1487.87, "total_tokens": 18441344} {"current_steps": 87380, "total_steps": 181800, "loss": 0.0417, "lr": 3.099447085420682e-05, "epoch": 9.612761276127612, "percentage": 48.06, "elapsed_time": "3:26:35", "remaining_time": "3:43:13", "throughput": 1487.86, "total_tokens": 18442304} {"current_steps": 87385, "total_steps": 181800, "loss": 0.1042, "lr": 3.099214077474e-05, "epoch": 9.613311331133113, "percentage": 48.07, "elapsed_time": "3:26:35", "remaining_time": "3:43:13", "throughput": 1487.86, "total_tokens": 18443296} {"current_steps": 87390, "total_steps": 181800, "loss": 0.0249, "lr": 3.09898106400465e-05, "epoch": 9.613861386138614, "percentage": 48.07, "elapsed_time": "3:26:36", "remaining_time": "3:43:12", "throughput": 1487.86, "total_tokens": 18444288} {"current_steps": 87395, "total_steps": 181800, "loss": 0.094, "lr": 3.0987480450147785e-05, "epoch": 9.614411441144114, "percentage": 48.07, "elapsed_time": "3:26:37", "remaining_time": "3:43:11", "throughput": 1487.86, "total_tokens": 18445408} {"current_steps": 87400, "total_steps": 181800, "loss": 0.0067, "lr": 3.098515020506534e-05, "epoch": 9.614961496149615, "percentage": 48.07, "elapsed_time": "3:26:37", "remaining_time": "3:43:10", "throughput": 1487.87, "total_tokens": 18446464} {"current_steps": 87405, "total_steps": 181800, "loss": 0.0161, "lr": 3.0982819904820635e-05, "epoch": 9.615511551155116, "percentage": 48.08, "elapsed_time": "3:26:38", "remaining_time": "3:43:10", "throughput": 1487.86, "total_tokens": 18447456} {"current_steps": 87410, "total_steps": 181800, "loss": 0.0037, "lr": 3.098048954943514e-05, "epoch": 9.616061606160617, "percentage": 48.08, "elapsed_time": "3:26:39", "remaining_time": "3:43:09", "throughput": 1487.86, "total_tokens": 18448480} {"current_steps": 87415, "total_steps": 181800, "loss": 0.0346, "lr": 3.097815913893035e-05, "epoch": 9.616611661166116, "percentage": 48.08, "elapsed_time": "3:26:39", "remaining_time": "3:43:08", "throughput": 1487.87, "total_tokens": 18449568} {"current_steps": 87420, "total_steps": 181800, "loss": 0.126, "lr": 3.097582867332773e-05, "epoch": 9.617161716171617, "percentage": 48.09, "elapsed_time": "3:26:40", "remaining_time": "3:43:07", "throughput": 1487.87, "total_tokens": 18450624} {"current_steps": 87425, "total_steps": 181800, "loss": 0.0169, "lr": 3.097349815264878e-05, "epoch": 9.617711771177119, "percentage": 48.09, "elapsed_time": "3:26:41", "remaining_time": "3:43:07", "throughput": 1487.88, "total_tokens": 18451712} {"current_steps": 87430, "total_steps": 181800, "loss": 0.002, "lr": 3.097116757691495e-05, "epoch": 9.618261826182618, "percentage": 48.09, "elapsed_time": "3:26:42", "remaining_time": "3:43:06", "throughput": 1487.88, "total_tokens": 18452800} {"current_steps": 87435, "total_steps": 181800, "loss": 0.0691, "lr": 3.096883694614774e-05, "epoch": 9.618811881188119, "percentage": 48.09, "elapsed_time": "3:26:42", "remaining_time": "3:43:05", "throughput": 1487.89, "total_tokens": 18453920} {"current_steps": 87440, "total_steps": 181800, "loss": 0.0074, "lr": 3.096650626036862e-05, "epoch": 9.61936193619362, "percentage": 48.1, "elapsed_time": "3:26:43", "remaining_time": "3:43:05", "throughput": 1487.9, "total_tokens": 18455040} {"current_steps": 87445, "total_steps": 181800, "loss": 0.0025, "lr": 3.096417551959908e-05, "epoch": 9.61991199119912, "percentage": 48.1, "elapsed_time": "3:26:44", "remaining_time": "3:43:04", "throughput": 1487.9, "total_tokens": 18456128} {"current_steps": 87450, "total_steps": 181800, "loss": 0.0251, "lr": 3.0961844723860593e-05, "epoch": 9.62046204620462, "percentage": 48.1, "elapsed_time": "3:26:44", "remaining_time": "3:43:03", "throughput": 1487.9, "total_tokens": 18457152} {"current_steps": 87455, "total_steps": 181800, "loss": 0.0582, "lr": 3.095951387317464e-05, "epoch": 9.621012101210122, "percentage": 48.11, "elapsed_time": "3:26:45", "remaining_time": "3:43:02", "throughput": 1487.9, "total_tokens": 18458176} {"current_steps": 87460, "total_steps": 181800, "loss": 0.0534, "lr": 3.095718296756271e-05, "epoch": 9.62156215621562, "percentage": 48.11, "elapsed_time": "3:26:46", "remaining_time": "3:43:02", "throughput": 1487.9, "total_tokens": 18459264} {"current_steps": 87465, "total_steps": 181800, "loss": 0.0082, "lr": 3.0954852007046284e-05, "epoch": 9.622112211221122, "percentage": 48.11, "elapsed_time": "3:26:46", "remaining_time": "3:43:01", "throughput": 1487.9, "total_tokens": 18460288} {"current_steps": 87470, "total_steps": 181800, "loss": 0.0491, "lr": 3.095252099164685e-05, "epoch": 9.622662266226623, "percentage": 48.11, "elapsed_time": "3:26:47", "remaining_time": "3:43:00", "throughput": 1487.91, "total_tokens": 18461344} {"current_steps": 87475, "total_steps": 181800, "loss": 0.1479, "lr": 3.095018992138588e-05, "epoch": 9.623212321232124, "percentage": 48.12, "elapsed_time": "3:26:48", "remaining_time": "3:42:59", "throughput": 1487.91, "total_tokens": 18462368} {"current_steps": 87480, "total_steps": 181800, "loss": 0.0052, "lr": 3.0947858796284866e-05, "epoch": 9.623762376237623, "percentage": 48.12, "elapsed_time": "3:26:48", "remaining_time": "3:42:59", "throughput": 1487.91, "total_tokens": 18463456} {"current_steps": 87485, "total_steps": 181800, "loss": 0.004, "lr": 3.094552761636529e-05, "epoch": 9.624312431243125, "percentage": 48.12, "elapsed_time": "3:26:49", "remaining_time": "3:42:58", "throughput": 1487.92, "total_tokens": 18464544} {"current_steps": 87490, "total_steps": 181800, "loss": 0.0411, "lr": 3.0943196381648646e-05, "epoch": 9.624862486248626, "percentage": 48.12, "elapsed_time": "3:26:50", "remaining_time": "3:42:57", "throughput": 1487.93, "total_tokens": 18465664} {"current_steps": 87495, "total_steps": 181800, "loss": 0.0724, "lr": 3.094086509215641e-05, "epoch": 9.625412541254125, "percentage": 48.13, "elapsed_time": "3:26:51", "remaining_time": "3:42:57", "throughput": 1487.93, "total_tokens": 18466752} {"current_steps": 87500, "total_steps": 181800, "loss": 0.0746, "lr": 3.093853374791006e-05, "epoch": 9.625962596259626, "percentage": 48.13, "elapsed_time": "3:26:51", "remaining_time": "3:42:56", "throughput": 1487.93, "total_tokens": 18467808} {"current_steps": 87505, "total_steps": 181800, "loss": 0.0555, "lr": 3.0936202348931105e-05, "epoch": 9.626512651265127, "percentage": 48.13, "elapsed_time": "3:26:52", "remaining_time": "3:42:55", "throughput": 1487.94, "total_tokens": 18468864} {"current_steps": 87510, "total_steps": 181800, "loss": 0.017, "lr": 3.093387089524102e-05, "epoch": 9.627062706270626, "percentage": 48.14, "elapsed_time": "3:26:53", "remaining_time": "3:42:54", "throughput": 1487.93, "total_tokens": 18469856} {"current_steps": 87515, "total_steps": 181800, "loss": 0.0105, "lr": 3.0931539386861286e-05, "epoch": 9.627612761276128, "percentage": 48.14, "elapsed_time": "3:26:53", "remaining_time": "3:42:54", "throughput": 1487.94, "total_tokens": 18470976} {"current_steps": 87520, "total_steps": 181800, "loss": 0.1018, "lr": 3.092920782381342e-05, "epoch": 9.628162816281629, "percentage": 48.14, "elapsed_time": "3:26:54", "remaining_time": "3:42:53", "throughput": 1487.94, "total_tokens": 18472032} {"current_steps": 87525, "total_steps": 181800, "loss": 0.0367, "lr": 3.092687620611887e-05, "epoch": 9.628712871287128, "percentage": 48.14, "elapsed_time": "3:26:55", "remaining_time": "3:42:52", "throughput": 1487.94, "total_tokens": 18473024} {"current_steps": 87530, "total_steps": 181800, "loss": 0.0337, "lr": 3.0924544533799146e-05, "epoch": 9.629262926292629, "percentage": 48.15, "elapsed_time": "3:26:55", "remaining_time": "3:42:51", "throughput": 1487.94, "total_tokens": 18474048} {"current_steps": 87535, "total_steps": 181800, "loss": 0.0474, "lr": 3.092221280687575e-05, "epoch": 9.62981298129813, "percentage": 48.15, "elapsed_time": "3:26:56", "remaining_time": "3:42:51", "throughput": 1487.94, "total_tokens": 18475104} {"current_steps": 87540, "total_steps": 181800, "loss": 0.0839, "lr": 3.091988102537016e-05, "epoch": 9.630363036303631, "percentage": 48.15, "elapsed_time": "3:26:57", "remaining_time": "3:42:50", "throughput": 1487.95, "total_tokens": 18476192} {"current_steps": 87545, "total_steps": 181800, "loss": 0.0305, "lr": 3.0917549189303865e-05, "epoch": 9.63091309130913, "percentage": 48.15, "elapsed_time": "3:26:57", "remaining_time": "3:42:49", "throughput": 1487.95, "total_tokens": 18477312} {"current_steps": 87550, "total_steps": 181800, "loss": 0.0085, "lr": 3.0915217298698354e-05, "epoch": 9.631463146314632, "percentage": 48.16, "elapsed_time": "3:26:58", "remaining_time": "3:42:48", "throughput": 1487.96, "total_tokens": 18478400} {"current_steps": 87555, "total_steps": 181800, "loss": 0.0067, "lr": 3.0912885353575126e-05, "epoch": 9.632013201320133, "percentage": 48.16, "elapsed_time": "3:26:59", "remaining_time": "3:42:48", "throughput": 1487.96, "total_tokens": 18479456} {"current_steps": 87560, "total_steps": 181800, "loss": 0.047, "lr": 3.091055335395567e-05, "epoch": 9.632563256325632, "percentage": 48.16, "elapsed_time": "3:27:00", "remaining_time": "3:42:47", "throughput": 1487.96, "total_tokens": 18480512} {"current_steps": 87565, "total_steps": 181800, "loss": 0.0696, "lr": 3.090822129986148e-05, "epoch": 9.633113311331133, "percentage": 48.17, "elapsed_time": "3:27:00", "remaining_time": "3:42:46", "throughput": 1487.97, "total_tokens": 18481632} {"current_steps": 87570, "total_steps": 181800, "loss": 0.0072, "lr": 3.090588919131405e-05, "epoch": 9.633663366336634, "percentage": 48.17, "elapsed_time": "3:27:01", "remaining_time": "3:42:46", "throughput": 1487.97, "total_tokens": 18482688} {"current_steps": 87575, "total_steps": 181800, "loss": 0.0578, "lr": 3.0903557028334874e-05, "epoch": 9.634213421342134, "percentage": 48.17, "elapsed_time": "3:27:02", "remaining_time": "3:42:45", "throughput": 1487.97, "total_tokens": 18483744} {"current_steps": 87580, "total_steps": 181800, "loss": 0.0064, "lr": 3.090122481094545e-05, "epoch": 9.634763476347635, "percentage": 48.17, "elapsed_time": "3:27:02", "remaining_time": "3:42:44", "throughput": 1487.97, "total_tokens": 18484768} {"current_steps": 87585, "total_steps": 181800, "loss": 0.0818, "lr": 3.089889253916726e-05, "epoch": 9.635313531353136, "percentage": 48.18, "elapsed_time": "3:27:03", "remaining_time": "3:42:43", "throughput": 1487.97, "total_tokens": 18485792} {"current_steps": 87590, "total_steps": 181800, "loss": 0.0092, "lr": 3.0896560213021816e-05, "epoch": 9.635863586358635, "percentage": 48.18, "elapsed_time": "3:27:04", "remaining_time": "3:42:43", "throughput": 1487.97, "total_tokens": 18486784} {"current_steps": 87595, "total_steps": 181800, "loss": 0.0496, "lr": 3.08942278325306e-05, "epoch": 9.636413641364136, "percentage": 48.18, "elapsed_time": "3:27:04", "remaining_time": "3:42:42", "throughput": 1487.98, "total_tokens": 18487840} {"current_steps": 87600, "total_steps": 181800, "loss": 0.0479, "lr": 3.089189539771511e-05, "epoch": 9.636963696369637, "percentage": 48.18, "elapsed_time": "3:27:05", "remaining_time": "3:42:41", "throughput": 1487.98, "total_tokens": 18488928} {"current_steps": 87605, "total_steps": 181800, "loss": 0.0318, "lr": 3.088956290859685e-05, "epoch": 9.637513751375138, "percentage": 48.19, "elapsed_time": "3:27:06", "remaining_time": "3:42:40", "throughput": 1487.98, "total_tokens": 18489952} {"current_steps": 87610, "total_steps": 181800, "loss": 0.0157, "lr": 3.088723036519732e-05, "epoch": 9.638063806380638, "percentage": 48.19, "elapsed_time": "3:27:06", "remaining_time": "3:42:40", "throughput": 1487.98, "total_tokens": 18491008} {"current_steps": 87615, "total_steps": 181800, "loss": 0.0344, "lr": 3.0884897767538016e-05, "epoch": 9.638613861386139, "percentage": 48.19, "elapsed_time": "3:27:07", "remaining_time": "3:42:39", "throughput": 1487.99, "total_tokens": 18492160} {"current_steps": 87620, "total_steps": 181800, "loss": 0.0499, "lr": 3.088256511564043e-05, "epoch": 9.63916391639164, "percentage": 48.2, "elapsed_time": "3:27:08", "remaining_time": "3:42:38", "throughput": 1487.99, "total_tokens": 18493216} {"current_steps": 87625, "total_steps": 181800, "loss": 0.026, "lr": 3.088023240952606e-05, "epoch": 9.63971397139714, "percentage": 48.2, "elapsed_time": "3:27:08", "remaining_time": "3:42:38", "throughput": 1487.99, "total_tokens": 18494208} {"current_steps": 87630, "total_steps": 181800, "loss": 0.0264, "lr": 3.087789964921641e-05, "epoch": 9.64026402640264, "percentage": 48.2, "elapsed_time": "3:27:09", "remaining_time": "3:42:37", "throughput": 1487.99, "total_tokens": 18495232} {"current_steps": 87635, "total_steps": 181800, "loss": 0.1447, "lr": 3.0875566834732985e-05, "epoch": 9.640814081408141, "percentage": 48.2, "elapsed_time": "3:27:10", "remaining_time": "3:42:36", "throughput": 1487.99, "total_tokens": 18496256} {"current_steps": 87640, "total_steps": 181800, "loss": 0.0116, "lr": 3.087323396609728e-05, "epoch": 9.64136413641364, "percentage": 48.21, "elapsed_time": "3:27:11", "remaining_time": "3:42:35", "throughput": 1488.0, "total_tokens": 18497376} {"current_steps": 87645, "total_steps": 181800, "loss": 0.0548, "lr": 3.087090104333078e-05, "epoch": 9.641914191419142, "percentage": 48.21, "elapsed_time": "3:27:11", "remaining_time": "3:42:35", "throughput": 1488.0, "total_tokens": 18498432} {"current_steps": 87650, "total_steps": 181800, "loss": 0.0226, "lr": 3.086856806645502e-05, "epoch": 9.642464246424643, "percentage": 48.21, "elapsed_time": "3:27:12", "remaining_time": "3:42:34", "throughput": 1488.0, "total_tokens": 18499456} {"current_steps": 87655, "total_steps": 181800, "loss": 0.0687, "lr": 3.0866235035491475e-05, "epoch": 9.643014301430142, "percentage": 48.22, "elapsed_time": "3:27:13", "remaining_time": "3:42:33", "throughput": 1488.0, "total_tokens": 18500416} {"current_steps": 87660, "total_steps": 181800, "loss": 0.0168, "lr": 3.086390195046166e-05, "epoch": 9.643564356435643, "percentage": 48.22, "elapsed_time": "3:27:13", "remaining_time": "3:42:32", "throughput": 1488.0, "total_tokens": 18501504} {"current_steps": 87665, "total_steps": 181800, "loss": 0.005, "lr": 3.086156881138708e-05, "epoch": 9.644114411441144, "percentage": 48.22, "elapsed_time": "3:27:14", "remaining_time": "3:42:32", "throughput": 1488.0, "total_tokens": 18502528} {"current_steps": 87670, "total_steps": 181800, "loss": 0.0051, "lr": 3.085923561828922e-05, "epoch": 9.644664466446645, "percentage": 48.22, "elapsed_time": "3:27:15", "remaining_time": "3:42:31", "throughput": 1488.0, "total_tokens": 18503520} {"current_steps": 87675, "total_steps": 181800, "loss": 0.0017, "lr": 3.08569023711896e-05, "epoch": 9.645214521452145, "percentage": 48.23, "elapsed_time": "3:27:15", "remaining_time": "3:42:30", "throughput": 1488.0, "total_tokens": 18504608} {"current_steps": 87680, "total_steps": 181800, "loss": 0.0272, "lr": 3.0854569070109726e-05, "epoch": 9.645764576457646, "percentage": 48.23, "elapsed_time": "3:27:16", "remaining_time": "3:42:30", "throughput": 1488.0, "total_tokens": 18505600} {"current_steps": 87685, "total_steps": 181800, "loss": 0.0153, "lr": 3.08522357150711e-05, "epoch": 9.646314631463147, "percentage": 48.23, "elapsed_time": "3:27:17", "remaining_time": "3:42:29", "throughput": 1488.0, "total_tokens": 18506592} {"current_steps": 87690, "total_steps": 181800, "loss": 0.0629, "lr": 3.0849902306095227e-05, "epoch": 9.646864686468646, "percentage": 48.23, "elapsed_time": "3:27:17", "remaining_time": "3:42:28", "throughput": 1488.0, "total_tokens": 18507648} {"current_steps": 87695, "total_steps": 181800, "loss": 0.0852, "lr": 3.0847568843203605e-05, "epoch": 9.647414741474147, "percentage": 48.24, "elapsed_time": "3:27:18", "remaining_time": "3:42:27", "throughput": 1488.01, "total_tokens": 18508736} {"current_steps": 87700, "total_steps": 181800, "loss": 0.0051, "lr": 3.084523532641775e-05, "epoch": 9.647964796479648, "percentage": 48.24, "elapsed_time": "3:27:19", "remaining_time": "3:42:27", "throughput": 1488.0, "total_tokens": 18509760} {"current_steps": 87705, "total_steps": 181800, "loss": 0.0042, "lr": 3.0842901755759155e-05, "epoch": 9.648514851485148, "percentage": 48.24, "elapsed_time": "3:27:20", "remaining_time": "3:42:26", "throughput": 1488.01, "total_tokens": 18510848} {"current_steps": 87710, "total_steps": 181800, "loss": 0.0165, "lr": 3.084056813124936e-05, "epoch": 9.649064906490649, "percentage": 48.25, "elapsed_time": "3:27:20", "remaining_time": "3:42:25", "throughput": 1488.02, "total_tokens": 18511968} {"current_steps": 87715, "total_steps": 181800, "loss": 0.0292, "lr": 3.083823445290983e-05, "epoch": 9.64961496149615, "percentage": 48.25, "elapsed_time": "3:27:21", "remaining_time": "3:42:24", "throughput": 1488.02, "total_tokens": 18513024} {"current_steps": 87720, "total_steps": 181800, "loss": 0.0036, "lr": 3.083590072076211e-05, "epoch": 9.65016501650165, "percentage": 48.25, "elapsed_time": "3:27:22", "remaining_time": "3:42:24", "throughput": 1488.02, "total_tokens": 18514080} {"current_steps": 87725, "total_steps": 181800, "loss": 0.039, "lr": 3.0833566934827685e-05, "epoch": 9.65071507150715, "percentage": 48.25, "elapsed_time": "3:27:22", "remaining_time": "3:42:23", "throughput": 1488.02, "total_tokens": 18515104} {"current_steps": 87730, "total_steps": 181800, "loss": 0.0226, "lr": 3.0831233095128076e-05, "epoch": 9.651265126512651, "percentage": 48.26, "elapsed_time": "3:27:23", "remaining_time": "3:42:22", "throughput": 1488.02, "total_tokens": 18516160} {"current_steps": 87735, "total_steps": 181800, "loss": 0.004, "lr": 3.082889920168479e-05, "epoch": 9.651815181518153, "percentage": 48.26, "elapsed_time": "3:27:24", "remaining_time": "3:42:21", "throughput": 1488.02, "total_tokens": 18517184} {"current_steps": 87740, "total_steps": 181800, "loss": 0.0197, "lr": 3.082656525451934e-05, "epoch": 9.652365236523652, "percentage": 48.26, "elapsed_time": "3:27:24", "remaining_time": "3:42:21", "throughput": 1488.03, "total_tokens": 18518272} {"current_steps": 87745, "total_steps": 181800, "loss": 0.0363, "lr": 3.0824231253653225e-05, "epoch": 9.652915291529153, "percentage": 48.26, "elapsed_time": "3:27:25", "remaining_time": "3:42:20", "throughput": 1488.03, "total_tokens": 18519328} {"current_steps": 87750, "total_steps": 181800, "loss": 0.0039, "lr": 3.082189719910797e-05, "epoch": 9.653465346534654, "percentage": 48.27, "elapsed_time": "3:27:26", "remaining_time": "3:42:19", "throughput": 1488.03, "total_tokens": 18520384} {"current_steps": 87755, "total_steps": 181800, "loss": 0.043, "lr": 3.0819563090905085e-05, "epoch": 9.654015401540153, "percentage": 48.27, "elapsed_time": "3:27:26", "remaining_time": "3:42:19", "throughput": 1488.03, "total_tokens": 18521376} {"current_steps": 87760, "total_steps": 181800, "loss": 0.009, "lr": 3.081722892906607e-05, "epoch": 9.654565456545654, "percentage": 48.27, "elapsed_time": "3:27:27", "remaining_time": "3:42:18", "throughput": 1488.03, "total_tokens": 18522368} {"current_steps": 87765, "total_steps": 181800, "loss": 0.029, "lr": 3.081489471361246e-05, "epoch": 9.655115511551156, "percentage": 48.28, "elapsed_time": "3:27:28", "remaining_time": "3:42:17", "throughput": 1488.03, "total_tokens": 18523456} {"current_steps": 87770, "total_steps": 181800, "loss": 0.094, "lr": 3.0812560444565745e-05, "epoch": 9.655665566556655, "percentage": 48.28, "elapsed_time": "3:27:28", "remaining_time": "3:42:16", "throughput": 1488.04, "total_tokens": 18524512} {"current_steps": 87775, "total_steps": 181800, "loss": 0.0402, "lr": 3.081022612194745e-05, "epoch": 9.656215621562156, "percentage": 48.28, "elapsed_time": "3:27:29", "remaining_time": "3:42:16", "throughput": 1488.04, "total_tokens": 18525568} {"current_steps": 87780, "total_steps": 181800, "loss": 0.011, "lr": 3.08078917457791e-05, "epoch": 9.656765676567657, "percentage": 48.28, "elapsed_time": "3:27:30", "remaining_time": "3:42:15", "throughput": 1488.04, "total_tokens": 18526592} {"current_steps": 87785, "total_steps": 181800, "loss": 0.0389, "lr": 3.080555731608219e-05, "epoch": 9.657315731573158, "percentage": 48.29, "elapsed_time": "3:27:31", "remaining_time": "3:42:14", "throughput": 1488.04, "total_tokens": 18527648} {"current_steps": 87790, "total_steps": 181800, "loss": 0.0223, "lr": 3.0803222832878244e-05, "epoch": 9.657865786578657, "percentage": 48.29, "elapsed_time": "3:27:31", "remaining_time": "3:42:13", "throughput": 1488.04, "total_tokens": 18528704} {"current_steps": 87795, "total_steps": 181800, "loss": 0.0265, "lr": 3.080088829618878e-05, "epoch": 9.658415841584159, "percentage": 48.29, "elapsed_time": "3:27:32", "remaining_time": "3:42:13", "throughput": 1488.05, "total_tokens": 18529760} {"current_steps": 87800, "total_steps": 181800, "loss": 0.009, "lr": 3.079855370603531e-05, "epoch": 9.65896589658966, "percentage": 48.29, "elapsed_time": "3:27:33", "remaining_time": "3:42:12", "throughput": 1488.04, "total_tokens": 18530720} {"current_steps": 87805, "total_steps": 181800, "loss": 0.0135, "lr": 3.079621906243936e-05, "epoch": 9.659515951595159, "percentage": 48.3, "elapsed_time": "3:27:33", "remaining_time": "3:42:11", "throughput": 1488.04, "total_tokens": 18531744} {"current_steps": 87810, "total_steps": 181800, "loss": 0.0287, "lr": 3.0793884365422434e-05, "epoch": 9.66006600660066, "percentage": 48.3, "elapsed_time": "3:27:34", "remaining_time": "3:42:11", "throughput": 1488.04, "total_tokens": 18532800} {"current_steps": 87815, "total_steps": 181800, "loss": 0.0338, "lr": 3.079154961500605e-05, "epoch": 9.660616061606161, "percentage": 48.3, "elapsed_time": "3:27:35", "remaining_time": "3:42:10", "throughput": 1488.04, "total_tokens": 18533856} {"current_steps": 87820, "total_steps": 181800, "loss": 0.166, "lr": 3.078921481121174e-05, "epoch": 9.66116611661166, "percentage": 48.31, "elapsed_time": "3:27:35", "remaining_time": "3:42:09", "throughput": 1488.05, "total_tokens": 18534944} {"current_steps": 87825, "total_steps": 181800, "loss": 0.036, "lr": 3.078687995406102e-05, "epoch": 9.661716171617162, "percentage": 48.31, "elapsed_time": "3:27:36", "remaining_time": "3:42:08", "throughput": 1488.05, "total_tokens": 18536032} {"current_steps": 87830, "total_steps": 181800, "loss": 0.0291, "lr": 3.07845450435754e-05, "epoch": 9.662266226622663, "percentage": 48.31, "elapsed_time": "3:27:37", "remaining_time": "3:42:08", "throughput": 1488.05, "total_tokens": 18537056} {"current_steps": 87835, "total_steps": 181800, "loss": 0.1028, "lr": 3.0782210079776394e-05, "epoch": 9.662816281628164, "percentage": 48.31, "elapsed_time": "3:27:37", "remaining_time": "3:42:07", "throughput": 1488.05, "total_tokens": 18538080} {"current_steps": 87840, "total_steps": 181800, "loss": 0.0876, "lr": 3.0779875062685545e-05, "epoch": 9.663366336633663, "percentage": 48.32, "elapsed_time": "3:27:38", "remaining_time": "3:42:06", "throughput": 1488.05, "total_tokens": 18539104} {"current_steps": 87845, "total_steps": 181800, "loss": 0.005, "lr": 3.0777539992324354e-05, "epoch": 9.663916391639164, "percentage": 48.32, "elapsed_time": "3:27:39", "remaining_time": "3:42:05", "throughput": 1488.06, "total_tokens": 18540128} {"current_steps": 87850, "total_steps": 181800, "loss": 0.0115, "lr": 3.0775204868714355e-05, "epoch": 9.664466446644665, "percentage": 48.32, "elapsed_time": "3:27:39", "remaining_time": "3:42:05", "throughput": 1488.06, "total_tokens": 18541184} {"current_steps": 87855, "total_steps": 181800, "loss": 0.0406, "lr": 3.077286969187706e-05, "epoch": 9.665016501650165, "percentage": 48.33, "elapsed_time": "3:27:40", "remaining_time": "3:42:04", "throughput": 1488.06, "total_tokens": 18542272} {"current_steps": 87860, "total_steps": 181800, "loss": 0.0115, "lr": 3.0770534461833994e-05, "epoch": 9.665566556655666, "percentage": 48.33, "elapsed_time": "3:27:41", "remaining_time": "3:42:03", "throughput": 1488.06, "total_tokens": 18543296} {"current_steps": 87865, "total_steps": 181800, "loss": 0.036, "lr": 3.076819917860668e-05, "epoch": 9.666116611661167, "percentage": 48.33, "elapsed_time": "3:27:42", "remaining_time": "3:42:02", "throughput": 1488.07, "total_tokens": 18544384} {"current_steps": 87870, "total_steps": 181800, "loss": 0.0409, "lr": 3.0765863842216645e-05, "epoch": 9.666666666666666, "percentage": 48.33, "elapsed_time": "3:27:42", "remaining_time": "3:42:02", "throughput": 1488.07, "total_tokens": 18545408} {"current_steps": 87875, "total_steps": 181800, "loss": 0.0048, "lr": 3.076352845268541e-05, "epoch": 9.667216721672167, "percentage": 48.34, "elapsed_time": "3:27:43", "remaining_time": "3:42:01", "throughput": 1488.07, "total_tokens": 18546432} {"current_steps": 87880, "total_steps": 181800, "loss": 0.0376, "lr": 3.07611930100345e-05, "epoch": 9.667766776677668, "percentage": 48.34, "elapsed_time": "3:27:44", "remaining_time": "3:42:00", "throughput": 1488.07, "total_tokens": 18547456} {"current_steps": 87885, "total_steps": 181800, "loss": 0.0236, "lr": 3.0758857514285436e-05, "epoch": 9.668316831683168, "percentage": 48.34, "elapsed_time": "3:27:44", "remaining_time": "3:42:00", "throughput": 1488.08, "total_tokens": 18548640} {"current_steps": 87890, "total_steps": 181800, "loss": 0.0341, "lr": 3.075652196545975e-05, "epoch": 9.668866886688669, "percentage": 48.34, "elapsed_time": "3:27:45", "remaining_time": "3:41:59", "throughput": 1488.08, "total_tokens": 18549632} {"current_steps": 87895, "total_steps": 181800, "loss": 0.021, "lr": 3.075418636357895e-05, "epoch": 9.66941694169417, "percentage": 48.35, "elapsed_time": "3:27:46", "remaining_time": "3:41:58", "throughput": 1488.08, "total_tokens": 18550720} {"current_steps": 87900, "total_steps": 181800, "loss": 0.0362, "lr": 3.0751850708664595e-05, "epoch": 9.66996699669967, "percentage": 48.35, "elapsed_time": "3:27:46", "remaining_time": "3:41:57", "throughput": 1488.09, "total_tokens": 18551808} {"current_steps": 87905, "total_steps": 181800, "loss": 0.0191, "lr": 3.0749515000738174e-05, "epoch": 9.67051705170517, "percentage": 48.35, "elapsed_time": "3:27:47", "remaining_time": "3:41:57", "throughput": 1488.09, "total_tokens": 18552928} {"current_steps": 87910, "total_steps": 181800, "loss": 0.0434, "lr": 3.074717923982124e-05, "epoch": 9.671067106710671, "percentage": 48.36, "elapsed_time": "3:27:48", "remaining_time": "3:41:56", "throughput": 1488.1, "total_tokens": 18554016} {"current_steps": 87915, "total_steps": 181800, "loss": 0.1003, "lr": 3.074484342593532e-05, "epoch": 9.671617161716172, "percentage": 48.36, "elapsed_time": "3:27:48", "remaining_time": "3:41:55", "throughput": 1488.1, "total_tokens": 18555072} {"current_steps": 87920, "total_steps": 181800, "loss": 0.01, "lr": 3.0742507559101923e-05, "epoch": 9.672167216721672, "percentage": 48.36, "elapsed_time": "3:27:49", "remaining_time": "3:41:54", "throughput": 1488.1, "total_tokens": 18556128} {"current_steps": 87925, "total_steps": 181800, "loss": 0.0029, "lr": 3.07401716393426e-05, "epoch": 9.672717271727173, "percentage": 48.36, "elapsed_time": "3:27:50", "remaining_time": "3:41:54", "throughput": 1488.11, "total_tokens": 18557184} {"current_steps": 87930, "total_steps": 181800, "loss": 0.0021, "lr": 3.073783566667886e-05, "epoch": 9.673267326732674, "percentage": 48.37, "elapsed_time": "3:27:51", "remaining_time": "3:41:53", "throughput": 1488.11, "total_tokens": 18558240} {"current_steps": 87935, "total_steps": 181800, "loss": 0.0066, "lr": 3.073549964113224e-05, "epoch": 9.673817381738173, "percentage": 48.37, "elapsed_time": "3:27:51", "remaining_time": "3:41:52", "throughput": 1488.11, "total_tokens": 18559232} {"current_steps": 87940, "total_steps": 181800, "loss": 0.0384, "lr": 3.073316356272428e-05, "epoch": 9.674367436743674, "percentage": 48.37, "elapsed_time": "3:27:52", "remaining_time": "3:41:52", "throughput": 1488.11, "total_tokens": 18560288} {"current_steps": 87945, "total_steps": 181800, "loss": 0.01, "lr": 3.0730827431476504e-05, "epoch": 9.674917491749175, "percentage": 48.37, "elapsed_time": "3:27:53", "remaining_time": "3:41:51", "throughput": 1488.11, "total_tokens": 18561408} {"current_steps": 87950, "total_steps": 181800, "loss": 0.0373, "lr": 3.0728491247410434e-05, "epoch": 9.675467546754675, "percentage": 48.38, "elapsed_time": "3:27:53", "remaining_time": "3:41:50", "throughput": 1488.12, "total_tokens": 18562496} {"current_steps": 87955, "total_steps": 181800, "loss": 0.0041, "lr": 3.0726155010547614e-05, "epoch": 9.676017601760176, "percentage": 48.38, "elapsed_time": "3:27:54", "remaining_time": "3:41:49", "throughput": 1488.12, "total_tokens": 18563488} {"current_steps": 87960, "total_steps": 181800, "loss": 0.053, "lr": 3.072381872090957e-05, "epoch": 9.676567656765677, "percentage": 48.38, "elapsed_time": "3:27:55", "remaining_time": "3:41:49", "throughput": 1488.12, "total_tokens": 18564544} {"current_steps": 87965, "total_steps": 181800, "loss": 0.0292, "lr": 3.072148237851783e-05, "epoch": 9.677117711771178, "percentage": 48.39, "elapsed_time": "3:27:55", "remaining_time": "3:41:48", "throughput": 1488.12, "total_tokens": 18565600} {"current_steps": 87970, "total_steps": 181800, "loss": 0.09, "lr": 3.071914598339394e-05, "epoch": 9.677667766776677, "percentage": 48.39, "elapsed_time": "3:27:56", "remaining_time": "3:41:47", "throughput": 1488.12, "total_tokens": 18566656} {"current_steps": 87975, "total_steps": 181800, "loss": 0.0737, "lr": 3.0716809535559425e-05, "epoch": 9.678217821782178, "percentage": 48.39, "elapsed_time": "3:27:57", "remaining_time": "3:41:46", "throughput": 1488.13, "total_tokens": 18567744} {"current_steps": 87980, "total_steps": 181800, "loss": 0.0411, "lr": 3.0714473035035815e-05, "epoch": 9.67876787678768, "percentage": 48.39, "elapsed_time": "3:27:57", "remaining_time": "3:41:46", "throughput": 1488.13, "total_tokens": 18568768} {"current_steps": 87985, "total_steps": 181800, "loss": 0.0148, "lr": 3.071213648184465e-05, "epoch": 9.679317931793179, "percentage": 48.4, "elapsed_time": "3:27:58", "remaining_time": "3:41:45", "throughput": 1488.13, "total_tokens": 18569824} {"current_steps": 87990, "total_steps": 181800, "loss": 0.0872, "lr": 3.0709799876007463e-05, "epoch": 9.67986798679868, "percentage": 48.4, "elapsed_time": "3:27:59", "remaining_time": "3:41:44", "throughput": 1488.14, "total_tokens": 18570944} {"current_steps": 87995, "total_steps": 181800, "loss": 0.0434, "lr": 3.07074632175458e-05, "epoch": 9.680418041804181, "percentage": 48.4, "elapsed_time": "3:28:00", "remaining_time": "3:41:44", "throughput": 1488.14, "total_tokens": 18571968} {"current_steps": 88000, "total_steps": 181800, "loss": 0.0101, "lr": 3.070512650648118e-05, "epoch": 9.68096809680968, "percentage": 48.4, "elapsed_time": "3:28:00", "remaining_time": "3:41:43", "throughput": 1488.15, "total_tokens": 18573088} {"current_steps": 88005, "total_steps": 181800, "loss": 0.0078, "lr": 3.0702789742835145e-05, "epoch": 9.681518151815181, "percentage": 48.41, "elapsed_time": "3:28:01", "remaining_time": "3:41:42", "throughput": 1488.15, "total_tokens": 18574208} {"current_steps": 88010, "total_steps": 181800, "loss": 0.0036, "lr": 3.0700452926629234e-05, "epoch": 9.682068206820682, "percentage": 48.41, "elapsed_time": "3:28:02", "remaining_time": "3:41:41", "throughput": 1488.16, "total_tokens": 18575296} {"current_steps": 88015, "total_steps": 181800, "loss": 0.0067, "lr": 3.069811605788499e-05, "epoch": 9.682618261826182, "percentage": 48.41, "elapsed_time": "3:28:02", "remaining_time": "3:41:41", "throughput": 1488.16, "total_tokens": 18576352} {"current_steps": 88020, "total_steps": 181800, "loss": 0.0722, "lr": 3.0695779136623935e-05, "epoch": 9.683168316831683, "percentage": 48.42, "elapsed_time": "3:28:03", "remaining_time": "3:41:40", "throughput": 1488.17, "total_tokens": 18577440} {"current_steps": 88025, "total_steps": 181800, "loss": 0.0297, "lr": 3.069344216286762e-05, "epoch": 9.683718371837184, "percentage": 48.42, "elapsed_time": "3:28:04", "remaining_time": "3:41:39", "throughput": 1488.17, "total_tokens": 18578528} {"current_steps": 88030, "total_steps": 181800, "loss": 0.0021, "lr": 3.0691105136637584e-05, "epoch": 9.684268426842685, "percentage": 48.42, "elapsed_time": "3:28:04", "remaining_time": "3:41:38", "throughput": 1488.17, "total_tokens": 18579616} {"current_steps": 88035, "total_steps": 181800, "loss": 0.19, "lr": 3.068876805795536e-05, "epoch": 9.684818481848184, "percentage": 48.42, "elapsed_time": "3:28:05", "remaining_time": "3:41:38", "throughput": 1488.17, "total_tokens": 18580640} {"current_steps": 88040, "total_steps": 181800, "loss": 0.055, "lr": 3.068643092684249e-05, "epoch": 9.685368536853685, "percentage": 48.43, "elapsed_time": "3:28:06", "remaining_time": "3:41:37", "throughput": 1488.18, "total_tokens": 18581696} {"current_steps": 88045, "total_steps": 181800, "loss": 0.0087, "lr": 3.068409374332052e-05, "epoch": 9.685918591859187, "percentage": 48.43, "elapsed_time": "3:28:06", "remaining_time": "3:41:36", "throughput": 1488.18, "total_tokens": 18582752} {"current_steps": 88050, "total_steps": 181800, "loss": 0.0331, "lr": 3.0681756507410975e-05, "epoch": 9.686468646864686, "percentage": 48.43, "elapsed_time": "3:28:07", "remaining_time": "3:41:35", "throughput": 1488.18, "total_tokens": 18583776} {"current_steps": 88055, "total_steps": 181800, "loss": 0.1268, "lr": 3.0679419219135414e-05, "epoch": 9.687018701870187, "percentage": 48.44, "elapsed_time": "3:28:08", "remaining_time": "3:41:35", "throughput": 1488.18, "total_tokens": 18584800} {"current_steps": 88060, "total_steps": 181800, "loss": 0.0646, "lr": 3.067708187851537e-05, "epoch": 9.687568756875688, "percentage": 48.44, "elapsed_time": "3:28:08", "remaining_time": "3:41:34", "throughput": 1488.19, "total_tokens": 18585888} {"current_steps": 88065, "total_steps": 181800, "loss": 0.0655, "lr": 3.067474448557239e-05, "epoch": 9.688118811881187, "percentage": 48.44, "elapsed_time": "3:28:09", "remaining_time": "3:41:33", "throughput": 1488.19, "total_tokens": 18586912} {"current_steps": 88070, "total_steps": 181800, "loss": 0.1182, "lr": 3.067240704032801e-05, "epoch": 9.688668866886688, "percentage": 48.44, "elapsed_time": "3:28:10", "remaining_time": "3:41:33", "throughput": 1488.19, "total_tokens": 18587968} {"current_steps": 88075, "total_steps": 181800, "loss": 0.0205, "lr": 3.0670069542803776e-05, "epoch": 9.68921892189219, "percentage": 48.45, "elapsed_time": "3:28:11", "remaining_time": "3:41:32", "throughput": 1488.18, "total_tokens": 18588928} {"current_steps": 88080, "total_steps": 181800, "loss": 0.0574, "lr": 3.0667731993021226e-05, "epoch": 9.689768976897689, "percentage": 48.45, "elapsed_time": "3:28:11", "remaining_time": "3:41:31", "throughput": 1488.18, "total_tokens": 18589952} {"current_steps": 88085, "total_steps": 181800, "loss": 0.0811, "lr": 3.066539439100192e-05, "epoch": 9.69031903190319, "percentage": 48.45, "elapsed_time": "3:28:12", "remaining_time": "3:41:30", "throughput": 1488.18, "total_tokens": 18590976} {"current_steps": 88090, "total_steps": 181800, "loss": 0.0042, "lr": 3.066305673676739e-05, "epoch": 9.690869086908691, "percentage": 48.45, "elapsed_time": "3:28:13", "remaining_time": "3:41:30", "throughput": 1488.19, "total_tokens": 18592096} {"current_steps": 88095, "total_steps": 181800, "loss": 0.097, "lr": 3.066071903033918e-05, "epoch": 9.691419141914192, "percentage": 48.46, "elapsed_time": "3:28:13", "remaining_time": "3:41:29", "throughput": 1488.2, "total_tokens": 18593216} {"current_steps": 88100, "total_steps": 181800, "loss": 0.0627, "lr": 3.065838127173884e-05, "epoch": 9.691969196919691, "percentage": 48.46, "elapsed_time": "3:28:14", "remaining_time": "3:41:28", "throughput": 1488.2, "total_tokens": 18594272} {"current_steps": 88105, "total_steps": 181800, "loss": 0.0099, "lr": 3.0656043460987914e-05, "epoch": 9.692519251925193, "percentage": 48.46, "elapsed_time": "3:28:15", "remaining_time": "3:41:27", "throughput": 1488.21, "total_tokens": 18595360} {"current_steps": 88110, "total_steps": 181800, "loss": 0.0066, "lr": 3.065370559810795e-05, "epoch": 9.693069306930694, "percentage": 48.47, "elapsed_time": "3:28:15", "remaining_time": "3:41:27", "throughput": 1488.2, "total_tokens": 18596384} {"current_steps": 88115, "total_steps": 181800, "loss": 0.0172, "lr": 3.0651367683120504e-05, "epoch": 9.693619361936193, "percentage": 48.47, "elapsed_time": "3:28:16", "remaining_time": "3:41:26", "throughput": 1488.21, "total_tokens": 18597440} {"current_steps": 88120, "total_steps": 181800, "loss": 0.1024, "lr": 3.06490297160471e-05, "epoch": 9.694169416941694, "percentage": 48.47, "elapsed_time": "3:28:17", "remaining_time": "3:41:25", "throughput": 1488.22, "total_tokens": 18598592} {"current_steps": 88125, "total_steps": 181800, "loss": 0.0153, "lr": 3.06466916969093e-05, "epoch": 9.694719471947195, "percentage": 48.47, "elapsed_time": "3:28:17", "remaining_time": "3:41:25", "throughput": 1488.22, "total_tokens": 18599648} {"current_steps": 88130, "total_steps": 181800, "loss": 0.0483, "lr": 3.064435362572866e-05, "epoch": 9.695269526952695, "percentage": 48.48, "elapsed_time": "3:28:18", "remaining_time": "3:41:24", "throughput": 1488.22, "total_tokens": 18600672} {"current_steps": 88135, "total_steps": 181800, "loss": 0.0556, "lr": 3.064201550252672e-05, "epoch": 9.695819581958196, "percentage": 48.48, "elapsed_time": "3:28:19", "remaining_time": "3:41:23", "throughput": 1488.22, "total_tokens": 18601760} {"current_steps": 88140, "total_steps": 181800, "loss": 0.0467, "lr": 3.063967732732503e-05, "epoch": 9.696369636963697, "percentage": 48.48, "elapsed_time": "3:28:19", "remaining_time": "3:41:22", "throughput": 1488.23, "total_tokens": 18602880} {"current_steps": 88145, "total_steps": 181800, "loss": 0.0094, "lr": 3.063733910014514e-05, "epoch": 9.696919691969196, "percentage": 48.48, "elapsed_time": "3:28:20", "remaining_time": "3:41:22", "throughput": 1488.23, "total_tokens": 18603904} {"current_steps": 88150, "total_steps": 181800, "loss": 0.0021, "lr": 3.06350008210086e-05, "epoch": 9.697469746974697, "percentage": 48.49, "elapsed_time": "3:28:21", "remaining_time": "3:41:21", "throughput": 1488.23, "total_tokens": 18604960} {"current_steps": 88155, "total_steps": 181800, "loss": 0.0824, "lr": 3.0632662489936954e-05, "epoch": 9.698019801980198, "percentage": 48.49, "elapsed_time": "3:28:22", "remaining_time": "3:41:20", "throughput": 1488.23, "total_tokens": 18605984} {"current_steps": 88160, "total_steps": 181800, "loss": 0.0117, "lr": 3.063032410695178e-05, "epoch": 9.6985698569857, "percentage": 48.49, "elapsed_time": "3:28:22", "remaining_time": "3:41:19", "throughput": 1488.24, "total_tokens": 18607104} {"current_steps": 88165, "total_steps": 181800, "loss": 0.0072, "lr": 3.06279856720746e-05, "epoch": 9.699119911991199, "percentage": 48.5, "elapsed_time": "3:28:23", "remaining_time": "3:41:19", "throughput": 1488.25, "total_tokens": 18608192} {"current_steps": 88170, "total_steps": 181800, "loss": 0.0034, "lr": 3.062564718532696e-05, "epoch": 9.6996699669967, "percentage": 48.5, "elapsed_time": "3:28:24", "remaining_time": "3:41:18", "throughput": 1488.25, "total_tokens": 18609248} {"current_steps": 88175, "total_steps": 181800, "loss": 0.0065, "lr": 3.062330864673045e-05, "epoch": 9.7002200220022, "percentage": 48.5, "elapsed_time": "3:28:24", "remaining_time": "3:41:17", "throughput": 1488.24, "total_tokens": 18610208} {"current_steps": 88180, "total_steps": 181800, "loss": 0.0681, "lr": 3.06209700563066e-05, "epoch": 9.7007700770077, "percentage": 48.5, "elapsed_time": "3:28:25", "remaining_time": "3:41:16", "throughput": 1488.25, "total_tokens": 18611264} {"current_steps": 88185, "total_steps": 181800, "loss": 0.0607, "lr": 3.061863141407696e-05, "epoch": 9.701320132013201, "percentage": 48.51, "elapsed_time": "3:28:26", "remaining_time": "3:41:16", "throughput": 1488.25, "total_tokens": 18612320} {"current_steps": 88190, "total_steps": 181800, "loss": 0.0069, "lr": 3.0616292720063086e-05, "epoch": 9.701870187018702, "percentage": 48.51, "elapsed_time": "3:28:26", "remaining_time": "3:41:15", "throughput": 1488.25, "total_tokens": 18613344} {"current_steps": 88195, "total_steps": 181800, "loss": 0.0054, "lr": 3.061395397428655e-05, "epoch": 9.702420242024202, "percentage": 48.51, "elapsed_time": "3:28:27", "remaining_time": "3:41:14", "throughput": 1488.25, "total_tokens": 18614432} {"current_steps": 88200, "total_steps": 181800, "loss": 0.0097, "lr": 3.061161517676888e-05, "epoch": 9.702970297029703, "percentage": 48.51, "elapsed_time": "3:28:28", "remaining_time": "3:41:14", "throughput": 1488.25, "total_tokens": 18615424} {"current_steps": 88205, "total_steps": 181800, "loss": 0.1154, "lr": 3.060927632753166e-05, "epoch": 9.703520352035204, "percentage": 48.52, "elapsed_time": "3:28:28", "remaining_time": "3:41:13", "throughput": 1488.25, "total_tokens": 18616480} {"current_steps": 88210, "total_steps": 181800, "loss": 0.0061, "lr": 3.060693742659642e-05, "epoch": 9.704070407040705, "percentage": 48.52, "elapsed_time": "3:28:29", "remaining_time": "3:41:12", "throughput": 1488.26, "total_tokens": 18617568} {"current_steps": 88215, "total_steps": 181800, "loss": 0.0335, "lr": 3.060459847398473e-05, "epoch": 9.704620462046204, "percentage": 48.52, "elapsed_time": "3:28:30", "remaining_time": "3:41:11", "throughput": 1488.26, "total_tokens": 18618592} {"current_steps": 88220, "total_steps": 181800, "loss": 0.0101, "lr": 3.060225946971816e-05, "epoch": 9.705170517051705, "percentage": 48.53, "elapsed_time": "3:28:31", "remaining_time": "3:41:11", "throughput": 1488.26, "total_tokens": 18619680} {"current_steps": 88225, "total_steps": 181800, "loss": 0.0045, "lr": 3.059992041381824e-05, "epoch": 9.705720572057206, "percentage": 48.53, "elapsed_time": "3:28:31", "remaining_time": "3:41:10", "throughput": 1488.26, "total_tokens": 18620736} {"current_steps": 88230, "total_steps": 181800, "loss": 0.055, "lr": 3.059758130630654e-05, "epoch": 9.706270627062706, "percentage": 48.53, "elapsed_time": "3:28:32", "remaining_time": "3:41:09", "throughput": 1488.26, "total_tokens": 18621760} {"current_steps": 88235, "total_steps": 181800, "loss": 0.0484, "lr": 3.0595242147204626e-05, "epoch": 9.706820682068207, "percentage": 48.53, "elapsed_time": "3:28:33", "remaining_time": "3:41:08", "throughput": 1488.27, "total_tokens": 18622848} {"current_steps": 88240, "total_steps": 181800, "loss": 0.0703, "lr": 3.059290293653404e-05, "epoch": 9.707370737073708, "percentage": 48.54, "elapsed_time": "3:28:33", "remaining_time": "3:41:08", "throughput": 1488.27, "total_tokens": 18623872} {"current_steps": 88245, "total_steps": 181800, "loss": 0.0301, "lr": 3.059056367431635e-05, "epoch": 9.707920792079207, "percentage": 48.54, "elapsed_time": "3:28:34", "remaining_time": "3:41:07", "throughput": 1488.27, "total_tokens": 18624928} {"current_steps": 88250, "total_steps": 181800, "loss": 0.0218, "lr": 3.058822436057313e-05, "epoch": 9.708470847084708, "percentage": 48.54, "elapsed_time": "3:28:35", "remaining_time": "3:41:06", "throughput": 1488.27, "total_tokens": 18625984} {"current_steps": 88255, "total_steps": 181800, "loss": 0.0029, "lr": 3.058588499532592e-05, "epoch": 9.70902090209021, "percentage": 48.55, "elapsed_time": "3:28:35", "remaining_time": "3:41:06", "throughput": 1488.28, "total_tokens": 18627040} {"current_steps": 88260, "total_steps": 181800, "loss": 0.0186, "lr": 3.058354557859629e-05, "epoch": 9.70957095709571, "percentage": 48.55, "elapsed_time": "3:28:36", "remaining_time": "3:41:05", "throughput": 1488.28, "total_tokens": 18628096} {"current_steps": 88265, "total_steps": 181800, "loss": 0.0022, "lr": 3.05812061104058e-05, "epoch": 9.71012101210121, "percentage": 48.55, "elapsed_time": "3:28:37", "remaining_time": "3:41:04", "throughput": 1488.28, "total_tokens": 18629152} {"current_steps": 88270, "total_steps": 181800, "loss": 0.053, "lr": 3.0578866590776004e-05, "epoch": 9.710671067106711, "percentage": 48.55, "elapsed_time": "3:28:37", "remaining_time": "3:41:03", "throughput": 1488.28, "total_tokens": 18630176} {"current_steps": 88275, "total_steps": 181800, "loss": 0.0312, "lr": 3.057652701972848e-05, "epoch": 9.711221122112212, "percentage": 48.56, "elapsed_time": "3:28:38", "remaining_time": "3:41:03", "throughput": 1488.29, "total_tokens": 18631296} {"current_steps": 88280, "total_steps": 181800, "loss": 0.0386, "lr": 3.0574187397284785e-05, "epoch": 9.711771177117711, "percentage": 48.56, "elapsed_time": "3:28:39", "remaining_time": "3:41:02", "throughput": 1488.29, "total_tokens": 18632352} {"current_steps": 88285, "total_steps": 181800, "loss": 0.0268, "lr": 3.057184772346647e-05, "epoch": 9.712321232123212, "percentage": 48.56, "elapsed_time": "3:28:39", "remaining_time": "3:41:01", "throughput": 1488.3, "total_tokens": 18633440} {"current_steps": 88290, "total_steps": 181800, "loss": 0.1508, "lr": 3.056950799829512e-05, "epoch": 9.712871287128714, "percentage": 48.56, "elapsed_time": "3:28:40", "remaining_time": "3:41:00", "throughput": 1488.3, "total_tokens": 18634464} {"current_steps": 88295, "total_steps": 181800, "loss": 0.0212, "lr": 3.056716822179228e-05, "epoch": 9.713421342134213, "percentage": 48.57, "elapsed_time": "3:28:41", "remaining_time": "3:41:00", "throughput": 1488.29, "total_tokens": 18635424} {"current_steps": 88300, "total_steps": 181800, "loss": 0.0369, "lr": 3.056482839397952e-05, "epoch": 9.713971397139714, "percentage": 48.57, "elapsed_time": "3:28:42", "remaining_time": "3:40:59", "throughput": 1488.3, "total_tokens": 18636512} {"current_steps": 88305, "total_steps": 181800, "loss": 0.03, "lr": 3.0562488514878414e-05, "epoch": 9.714521452145215, "percentage": 48.57, "elapsed_time": "3:28:42", "remaining_time": "3:40:58", "throughput": 1488.3, "total_tokens": 18637632} {"current_steps": 88310, "total_steps": 181800, "loss": 0.0423, "lr": 3.056014858451052e-05, "epoch": 9.715071507150714, "percentage": 48.58, "elapsed_time": "3:28:43", "remaining_time": "3:40:58", "throughput": 1488.31, "total_tokens": 18638752} {"current_steps": 88315, "total_steps": 181800, "loss": 0.0257, "lr": 3.0557808602897394e-05, "epoch": 9.715621562156215, "percentage": 48.58, "elapsed_time": "3:28:44", "remaining_time": "3:40:57", "throughput": 1488.31, "total_tokens": 18639776} {"current_steps": 88320, "total_steps": 181800, "loss": 0.0234, "lr": 3.055546857006062e-05, "epoch": 9.716171617161717, "percentage": 48.58, "elapsed_time": "3:28:44", "remaining_time": "3:40:56", "throughput": 1488.31, "total_tokens": 18640800} {"current_steps": 88325, "total_steps": 181800, "loss": 0.0156, "lr": 3.055312848602175e-05, "epoch": 9.716721672167218, "percentage": 48.58, "elapsed_time": "3:28:45", "remaining_time": "3:40:55", "throughput": 1488.32, "total_tokens": 18641888} {"current_steps": 88330, "total_steps": 181800, "loss": 0.1405, "lr": 3.0550788350802374e-05, "epoch": 9.717271727172717, "percentage": 48.59, "elapsed_time": "3:28:46", "remaining_time": "3:40:55", "throughput": 1488.32, "total_tokens": 18642976} {"current_steps": 88335, "total_steps": 181800, "loss": 0.0361, "lr": 3.0548448164424035e-05, "epoch": 9.717821782178218, "percentage": 48.59, "elapsed_time": "3:28:46", "remaining_time": "3:40:54", "throughput": 1488.32, "total_tokens": 18643968} {"current_steps": 88340, "total_steps": 181800, "loss": 0.0119, "lr": 3.054610792690832e-05, "epoch": 9.718371837183719, "percentage": 48.59, "elapsed_time": "3:28:47", "remaining_time": "3:40:53", "throughput": 1488.32, "total_tokens": 18645024} {"current_steps": 88345, "total_steps": 181800, "loss": 0.0104, "lr": 3.054376763827678e-05, "epoch": 9.718921892189218, "percentage": 48.59, "elapsed_time": "3:28:48", "remaining_time": "3:40:52", "throughput": 1488.32, "total_tokens": 18646048} {"current_steps": 88350, "total_steps": 181800, "loss": 0.0028, "lr": 3.0541427298551e-05, "epoch": 9.71947194719472, "percentage": 48.6, "elapsed_time": "3:28:48", "remaining_time": "3:40:52", "throughput": 1488.32, "total_tokens": 18647136} {"current_steps": 88355, "total_steps": 181800, "loss": 0.0106, "lr": 3.053908690775254e-05, "epoch": 9.72002200220022, "percentage": 48.6, "elapsed_time": "3:28:49", "remaining_time": "3:40:51", "throughput": 1488.33, "total_tokens": 18648192} {"current_steps": 88360, "total_steps": 181800, "loss": 0.0057, "lr": 3.053674646590298e-05, "epoch": 9.72057205720572, "percentage": 48.6, "elapsed_time": "3:28:50", "remaining_time": "3:40:50", "throughput": 1488.33, "total_tokens": 18649248} {"current_steps": 88365, "total_steps": 181800, "loss": 0.0245, "lr": 3.053440597302388e-05, "epoch": 9.721122112211221, "percentage": 48.61, "elapsed_time": "3:28:51", "remaining_time": "3:40:49", "throughput": 1488.33, "total_tokens": 18650336} {"current_steps": 88370, "total_steps": 181800, "loss": 0.0067, "lr": 3.053206542913681e-05, "epoch": 9.721672167216722, "percentage": 48.61, "elapsed_time": "3:28:51", "remaining_time": "3:40:49", "throughput": 1488.34, "total_tokens": 18651392} {"current_steps": 88375, "total_steps": 181800, "loss": 0.0186, "lr": 3.0529724834263355e-05, "epoch": 9.722222222222221, "percentage": 48.61, "elapsed_time": "3:28:52", "remaining_time": "3:40:48", "throughput": 1488.34, "total_tokens": 18652448} {"current_steps": 88380, "total_steps": 181800, "loss": 0.1272, "lr": 3.0527384188425086e-05, "epoch": 9.722772277227723, "percentage": 48.61, "elapsed_time": "3:28:53", "remaining_time": "3:40:47", "throughput": 1488.35, "total_tokens": 18653600} {"current_steps": 88385, "total_steps": 181800, "loss": 0.0074, "lr": 3.052504349164355e-05, "epoch": 9.723322332233224, "percentage": 48.62, "elapsed_time": "3:28:53", "remaining_time": "3:40:47", "throughput": 1488.36, "total_tokens": 18654720} {"current_steps": 88390, "total_steps": 181800, "loss": 0.1011, "lr": 3.0522702743940354e-05, "epoch": 9.723872387238725, "percentage": 48.62, "elapsed_time": "3:28:54", "remaining_time": "3:40:46", "throughput": 1488.36, "total_tokens": 18655744} {"current_steps": 88395, "total_steps": 181800, "loss": 0.0452, "lr": 3.0520361945337064e-05, "epoch": 9.724422442244224, "percentage": 48.62, "elapsed_time": "3:28:55", "remaining_time": "3:40:45", "throughput": 1488.36, "total_tokens": 18656864} {"current_steps": 88400, "total_steps": 181800, "loss": 0.0707, "lr": 3.051802109585523e-05, "epoch": 9.724972497249725, "percentage": 48.62, "elapsed_time": "3:28:55", "remaining_time": "3:40:44", "throughput": 1488.37, "total_tokens": 18657920} {"current_steps": 88405, "total_steps": 181800, "loss": 0.005, "lr": 3.051568019551645e-05, "epoch": 9.725522552255226, "percentage": 48.63, "elapsed_time": "3:28:56", "remaining_time": "3:40:44", "throughput": 1488.37, "total_tokens": 18658944} {"current_steps": 88410, "total_steps": 181800, "loss": 0.0507, "lr": 3.051333924434229e-05, "epoch": 9.726072607260726, "percentage": 48.63, "elapsed_time": "3:28:57", "remaining_time": "3:40:43", "throughput": 1488.37, "total_tokens": 18660000} {"current_steps": 88415, "total_steps": 181800, "loss": 0.047, "lr": 3.0510998242354328e-05, "epoch": 9.726622662266227, "percentage": 48.63, "elapsed_time": "3:28:57", "remaining_time": "3:40:42", "throughput": 1488.37, "total_tokens": 18661120} {"current_steps": 88420, "total_steps": 181800, "loss": 0.1129, "lr": 3.0508657189574146e-05, "epoch": 9.727172717271728, "percentage": 48.64, "elapsed_time": "3:28:58", "remaining_time": "3:40:41", "throughput": 1488.37, "total_tokens": 18662144} {"current_steps": 88425, "total_steps": 181800, "loss": 0.0184, "lr": 3.050631608602331e-05, "epoch": 9.727722772277227, "percentage": 48.64, "elapsed_time": "3:28:59", "remaining_time": "3:40:41", "throughput": 1488.37, "total_tokens": 18663168} {"current_steps": 88430, "total_steps": 181800, "loss": 0.2007, "lr": 3.0503974931723394e-05, "epoch": 9.728272827282728, "percentage": 48.64, "elapsed_time": "3:28:59", "remaining_time": "3:40:40", "throughput": 1488.37, "total_tokens": 18664160} {"current_steps": 88435, "total_steps": 181800, "loss": 0.0255, "lr": 3.050163372669599e-05, "epoch": 9.72882288228823, "percentage": 48.64, "elapsed_time": "3:29:00", "remaining_time": "3:40:39", "throughput": 1488.37, "total_tokens": 18665184} {"current_steps": 88440, "total_steps": 181800, "loss": 0.1112, "lr": 3.049929247096267e-05, "epoch": 9.729372937293729, "percentage": 48.65, "elapsed_time": "3:29:01", "remaining_time": "3:40:39", "throughput": 1488.37, "total_tokens": 18666240} {"current_steps": 88445, "total_steps": 181800, "loss": 0.0447, "lr": 3.0496951164545005e-05, "epoch": 9.72992299229923, "percentage": 48.65, "elapsed_time": "3:29:02", "remaining_time": "3:40:38", "throughput": 1488.38, "total_tokens": 18667296} {"current_steps": 88450, "total_steps": 181800, "loss": 0.0061, "lr": 3.049460980746458e-05, "epoch": 9.73047304730473, "percentage": 48.65, "elapsed_time": "3:29:02", "remaining_time": "3:40:37", "throughput": 1488.38, "total_tokens": 18668384} {"current_steps": 88455, "total_steps": 181800, "loss": 0.0275, "lr": 3.0492268399742975e-05, "epoch": 9.731023102310232, "percentage": 48.66, "elapsed_time": "3:29:03", "remaining_time": "3:40:36", "throughput": 1488.39, "total_tokens": 18669504} {"current_steps": 88460, "total_steps": 181800, "loss": 0.0248, "lr": 3.0489926941401757e-05, "epoch": 9.731573157315731, "percentage": 48.66, "elapsed_time": "3:29:04", "remaining_time": "3:40:36", "throughput": 1488.39, "total_tokens": 18670560} {"current_steps": 88465, "total_steps": 181800, "loss": 0.002, "lr": 3.048758543246253e-05, "epoch": 9.732123212321232, "percentage": 48.66, "elapsed_time": "3:29:04", "remaining_time": "3:40:35", "throughput": 1488.39, "total_tokens": 18671616} {"current_steps": 88470, "total_steps": 181800, "loss": 0.0723, "lr": 3.048524387294686e-05, "epoch": 9.732673267326733, "percentage": 48.66, "elapsed_time": "3:29:05", "remaining_time": "3:40:34", "throughput": 1488.39, "total_tokens": 18672640} {"current_steps": 88475, "total_steps": 181800, "loss": 0.0083, "lr": 3.0482902262876324e-05, "epoch": 9.733223322332233, "percentage": 48.67, "elapsed_time": "3:29:06", "remaining_time": "3:40:33", "throughput": 1488.4, "total_tokens": 18673728} {"current_steps": 88480, "total_steps": 181800, "loss": 0.0804, "lr": 3.0480560602272513e-05, "epoch": 9.733773377337734, "percentage": 48.67, "elapsed_time": "3:29:06", "remaining_time": "3:40:33", "throughput": 1488.4, "total_tokens": 18674752} {"current_steps": 88485, "total_steps": 181800, "loss": 0.0093, "lr": 3.0478218891157003e-05, "epoch": 9.734323432343235, "percentage": 48.67, "elapsed_time": "3:29:07", "remaining_time": "3:40:32", "throughput": 1488.4, "total_tokens": 18675776} {"current_steps": 88490, "total_steps": 181800, "loss": 0.0074, "lr": 3.0475877129551376e-05, "epoch": 9.734873487348734, "percentage": 48.67, "elapsed_time": "3:29:08", "remaining_time": "3:40:31", "throughput": 1488.4, "total_tokens": 18676800} {"current_steps": 88495, "total_steps": 181800, "loss": 0.0134, "lr": 3.047353531747722e-05, "epoch": 9.735423542354235, "percentage": 48.68, "elapsed_time": "3:29:08", "remaining_time": "3:40:31", "throughput": 1488.41, "total_tokens": 18677920} {"current_steps": 88500, "total_steps": 181800, "loss": 0.0076, "lr": 3.047119345495611e-05, "epoch": 9.735973597359736, "percentage": 48.68, "elapsed_time": "3:29:09", "remaining_time": "3:40:30", "throughput": 1488.41, "total_tokens": 18679040} {"current_steps": 88505, "total_steps": 181800, "loss": 0.0521, "lr": 3.0468851542009642e-05, "epoch": 9.736523652365236, "percentage": 48.68, "elapsed_time": "3:29:10", "remaining_time": "3:40:29", "throughput": 1488.41, "total_tokens": 18680064} {"current_steps": 88510, "total_steps": 181800, "loss": 0.0685, "lr": 3.0466509578659393e-05, "epoch": 9.737073707370737, "percentage": 48.69, "elapsed_time": "3:29:11", "remaining_time": "3:40:28", "throughput": 1488.42, "total_tokens": 18681120} {"current_steps": 88515, "total_steps": 181800, "loss": 0.0042, "lr": 3.046416756492695e-05, "epoch": 9.737623762376238, "percentage": 48.69, "elapsed_time": "3:29:11", "remaining_time": "3:40:28", "throughput": 1488.42, "total_tokens": 18682208} {"current_steps": 88520, "total_steps": 181800, "loss": 0.0219, "lr": 3.046182550083389e-05, "epoch": 9.738173817381739, "percentage": 48.69, "elapsed_time": "3:29:12", "remaining_time": "3:40:27", "throughput": 1488.42, "total_tokens": 18683232} {"current_steps": 88525, "total_steps": 181800, "loss": 0.0058, "lr": 3.045948338640181e-05, "epoch": 9.738723872387238, "percentage": 48.69, "elapsed_time": "3:29:13", "remaining_time": "3:40:26", "throughput": 1488.42, "total_tokens": 18684224} {"current_steps": 88530, "total_steps": 181800, "loss": 0.0619, "lr": 3.0457141221652285e-05, "epoch": 9.73927392739274, "percentage": 48.7, "elapsed_time": "3:29:13", "remaining_time": "3:40:25", "throughput": 1488.42, "total_tokens": 18685248} {"current_steps": 88535, "total_steps": 181800, "loss": 0.0411, "lr": 3.045479900660691e-05, "epoch": 9.73982398239824, "percentage": 48.7, "elapsed_time": "3:29:14", "remaining_time": "3:40:25", "throughput": 1488.42, "total_tokens": 18686240} {"current_steps": 88540, "total_steps": 181800, "loss": 0.0152, "lr": 3.0452456741287284e-05, "epoch": 9.74037403740374, "percentage": 48.7, "elapsed_time": "3:29:15", "remaining_time": "3:40:24", "throughput": 1488.41, "total_tokens": 18687232} {"current_steps": 88545, "total_steps": 181800, "loss": 0.0029, "lr": 3.045011442571496e-05, "epoch": 9.74092409240924, "percentage": 48.7, "elapsed_time": "3:29:15", "remaining_time": "3:40:23", "throughput": 1488.41, "total_tokens": 18688288} {"current_steps": 88550, "total_steps": 181800, "loss": 0.0632, "lr": 3.0447772059911555e-05, "epoch": 9.741474147414742, "percentage": 48.71, "elapsed_time": "3:29:16", "remaining_time": "3:40:22", "throughput": 1488.42, "total_tokens": 18689408} {"current_steps": 88555, "total_steps": 181800, "loss": 0.116, "lr": 3.0445429643898655e-05, "epoch": 9.742024202420241, "percentage": 48.71, "elapsed_time": "3:29:17", "remaining_time": "3:40:22", "throughput": 1488.42, "total_tokens": 18690400} {"current_steps": 88560, "total_steps": 181800, "loss": 0.0035, "lr": 3.0443087177697834e-05, "epoch": 9.742574257425742, "percentage": 48.71, "elapsed_time": "3:29:17", "remaining_time": "3:40:21", "throughput": 1488.42, "total_tokens": 18691488} {"current_steps": 88565, "total_steps": 181800, "loss": 0.0648, "lr": 3.0440744661330696e-05, "epoch": 9.743124312431243, "percentage": 48.72, "elapsed_time": "3:29:18", "remaining_time": "3:40:20", "throughput": 1488.43, "total_tokens": 18692576} {"current_steps": 88570, "total_steps": 181800, "loss": 0.0047, "lr": 3.0438402094818825e-05, "epoch": 9.743674367436743, "percentage": 48.72, "elapsed_time": "3:29:19", "remaining_time": "3:40:20", "throughput": 1488.43, "total_tokens": 18693664} {"current_steps": 88575, "total_steps": 181800, "loss": 0.0509, "lr": 3.0436059478183803e-05, "epoch": 9.744224422442244, "percentage": 48.72, "elapsed_time": "3:29:19", "remaining_time": "3:40:19", "throughput": 1488.43, "total_tokens": 18694688} {"current_steps": 88580, "total_steps": 181800, "loss": 0.0167, "lr": 3.0433716811447237e-05, "epoch": 9.744774477447745, "percentage": 48.72, "elapsed_time": "3:29:20", "remaining_time": "3:40:18", "throughput": 1488.43, "total_tokens": 18695712} {"current_steps": 88585, "total_steps": 181800, "loss": 0.0101, "lr": 3.0431374094630714e-05, "epoch": 9.745324532453246, "percentage": 48.73, "elapsed_time": "3:29:21", "remaining_time": "3:40:17", "throughput": 1488.44, "total_tokens": 18696832} {"current_steps": 88590, "total_steps": 181800, "loss": 0.0084, "lr": 3.0429031327755815e-05, "epoch": 9.745874587458745, "percentage": 48.73, "elapsed_time": "3:29:22", "remaining_time": "3:40:17", "throughput": 1488.45, "total_tokens": 18697920} {"current_steps": 88595, "total_steps": 181800, "loss": 0.0445, "lr": 3.0426688510844142e-05, "epoch": 9.746424642464246, "percentage": 48.73, "elapsed_time": "3:29:22", "remaining_time": "3:40:16", "throughput": 1488.45, "total_tokens": 18698944} {"current_steps": 88600, "total_steps": 181800, "loss": 0.0184, "lr": 3.0424345643917285e-05, "epoch": 9.746974697469748, "percentage": 48.73, "elapsed_time": "3:29:23", "remaining_time": "3:40:15", "throughput": 1488.45, "total_tokens": 18699968} {"current_steps": 88605, "total_steps": 181800, "loss": 0.0259, "lr": 3.0422002726996835e-05, "epoch": 9.747524752475247, "percentage": 48.74, "elapsed_time": "3:29:24", "remaining_time": "3:40:14", "throughput": 1488.44, "total_tokens": 18700928} {"current_steps": 88610, "total_steps": 181800, "loss": 0.0133, "lr": 3.0419659760104396e-05, "epoch": 9.748074807480748, "percentage": 48.74, "elapsed_time": "3:29:24", "remaining_time": "3:40:14", "throughput": 1488.44, "total_tokens": 18702016} {"current_steps": 88615, "total_steps": 181800, "loss": 0.0956, "lr": 3.0417316743261546e-05, "epoch": 9.748624862486249, "percentage": 48.74, "elapsed_time": "3:29:25", "remaining_time": "3:40:13", "throughput": 1488.44, "total_tokens": 18703040} {"current_steps": 88620, "total_steps": 181800, "loss": 0.0026, "lr": 3.0414973676489882e-05, "epoch": 9.749174917491748, "percentage": 48.75, "elapsed_time": "3:29:26", "remaining_time": "3:40:12", "throughput": 1488.44, "total_tokens": 18704032} {"current_steps": 88625, "total_steps": 181800, "loss": 0.0067, "lr": 3.0412630559811013e-05, "epoch": 9.74972497249725, "percentage": 48.75, "elapsed_time": "3:29:26", "remaining_time": "3:40:12", "throughput": 1488.44, "total_tokens": 18705088} {"current_steps": 88630, "total_steps": 181800, "loss": 0.0043, "lr": 3.041028739324652e-05, "epoch": 9.75027502750275, "percentage": 48.75, "elapsed_time": "3:29:27", "remaining_time": "3:40:11", "throughput": 1488.45, "total_tokens": 18706176} {"current_steps": 88635, "total_steps": 181800, "loss": 0.1555, "lr": 3.040794417681801e-05, "epoch": 9.750825082508252, "percentage": 48.75, "elapsed_time": "3:29:28", "remaining_time": "3:40:10", "throughput": 1488.45, "total_tokens": 18707200} {"current_steps": 88640, "total_steps": 181800, "loss": 0.0041, "lr": 3.040560091054707e-05, "epoch": 9.751375137513751, "percentage": 48.76, "elapsed_time": "3:29:28", "remaining_time": "3:40:09", "throughput": 1488.44, "total_tokens": 18708192} {"current_steps": 88645, "total_steps": 181800, "loss": 0.1207, "lr": 3.0403257594455305e-05, "epoch": 9.751925192519252, "percentage": 48.76, "elapsed_time": "3:29:29", "remaining_time": "3:40:09", "throughput": 1488.45, "total_tokens": 18709248} {"current_steps": 88650, "total_steps": 181800, "loss": 0.0228, "lr": 3.04009142285643e-05, "epoch": 9.752475247524753, "percentage": 48.76, "elapsed_time": "3:29:30", "remaining_time": "3:40:08", "throughput": 1488.45, "total_tokens": 18710304} {"current_steps": 88655, "total_steps": 181800, "loss": 0.0132, "lr": 3.039857081289566e-05, "epoch": 9.753025302530252, "percentage": 48.77, "elapsed_time": "3:29:31", "remaining_time": "3:40:07", "throughput": 1488.45, "total_tokens": 18711392} {"current_steps": 88660, "total_steps": 181800, "loss": 0.09, "lr": 3.0396227347470983e-05, "epoch": 9.753575357535754, "percentage": 48.77, "elapsed_time": "3:29:31", "remaining_time": "3:40:06", "throughput": 1488.46, "total_tokens": 18712480} {"current_steps": 88665, "total_steps": 181800, "loss": 0.0127, "lr": 3.0393883832311874e-05, "epoch": 9.754125412541255, "percentage": 48.77, "elapsed_time": "3:29:32", "remaining_time": "3:40:06", "throughput": 1488.46, "total_tokens": 18713536} {"current_steps": 88670, "total_steps": 181800, "loss": 0.0025, "lr": 3.0391540267439928e-05, "epoch": 9.754675467546754, "percentage": 48.77, "elapsed_time": "3:29:33", "remaining_time": "3:40:05", "throughput": 1488.46, "total_tokens": 18714560} {"current_steps": 88675, "total_steps": 181800, "loss": 0.0499, "lr": 3.038919665287674e-05, "epoch": 9.755225522552255, "percentage": 48.78, "elapsed_time": "3:29:33", "remaining_time": "3:40:04", "throughput": 1488.47, "total_tokens": 18715680} {"current_steps": 88680, "total_steps": 181800, "loss": 0.0196, "lr": 3.038685298864391e-05, "epoch": 9.755775577557756, "percentage": 48.78, "elapsed_time": "3:29:34", "remaining_time": "3:40:04", "throughput": 1488.47, "total_tokens": 18716736} {"current_steps": 88685, "total_steps": 181800, "loss": 0.0415, "lr": 3.038450927476304e-05, "epoch": 9.756325632563257, "percentage": 48.78, "elapsed_time": "3:29:35", "remaining_time": "3:40:03", "throughput": 1488.48, "total_tokens": 18717824} {"current_steps": 88690, "total_steps": 181800, "loss": 0.0416, "lr": 3.0382165511255727e-05, "epoch": 9.756875687568757, "percentage": 48.78, "elapsed_time": "3:29:35", "remaining_time": "3:40:02", "throughput": 1488.48, "total_tokens": 18718912} {"current_steps": 88695, "total_steps": 181800, "loss": 0.0809, "lr": 3.0379821698143584e-05, "epoch": 9.757425742574258, "percentage": 48.79, "elapsed_time": "3:29:36", "remaining_time": "3:40:01", "throughput": 1488.48, "total_tokens": 18719968} {"current_steps": 88700, "total_steps": 181800, "loss": 0.0039, "lr": 3.0377477835448205e-05, "epoch": 9.757975797579759, "percentage": 48.79, "elapsed_time": "3:29:37", "remaining_time": "3:40:01", "throughput": 1488.48, "total_tokens": 18721024} {"current_steps": 88705, "total_steps": 181800, "loss": 0.0125, "lr": 3.0375133923191194e-05, "epoch": 9.758525852585258, "percentage": 48.79, "elapsed_time": "3:29:37", "remaining_time": "3:40:00", "throughput": 1488.49, "total_tokens": 18722112} {"current_steps": 88710, "total_steps": 181800, "loss": 0.0234, "lr": 3.0372789961394154e-05, "epoch": 9.75907590759076, "percentage": 48.8, "elapsed_time": "3:29:38", "remaining_time": "3:39:59", "throughput": 1488.49, "total_tokens": 18723168} {"current_steps": 88715, "total_steps": 181800, "loss": 0.0254, "lr": 3.0370445950078686e-05, "epoch": 9.75962596259626, "percentage": 48.8, "elapsed_time": "3:29:39", "remaining_time": "3:39:58", "throughput": 1488.49, "total_tokens": 18724224} {"current_steps": 88720, "total_steps": 181800, "loss": 0.0407, "lr": 3.0368101889266387e-05, "epoch": 9.76017601760176, "percentage": 48.8, "elapsed_time": "3:29:40", "remaining_time": "3:39:58", "throughput": 1488.49, "total_tokens": 18725248} {"current_steps": 88725, "total_steps": 181800, "loss": 0.0346, "lr": 3.0365757778978877e-05, "epoch": 9.76072607260726, "percentage": 48.8, "elapsed_time": "3:29:40", "remaining_time": "3:39:57", "throughput": 1488.49, "total_tokens": 18726272} {"current_steps": 88730, "total_steps": 181800, "loss": 0.0659, "lr": 3.0363413619237758e-05, "epoch": 9.761276127612762, "percentage": 48.81, "elapsed_time": "3:29:41", "remaining_time": "3:39:56", "throughput": 1488.49, "total_tokens": 18727232} {"current_steps": 88735, "total_steps": 181800, "loss": 0.0093, "lr": 3.0361069410064613e-05, "epoch": 9.761826182618261, "percentage": 48.81, "elapsed_time": "3:29:42", "remaining_time": "3:39:56", "throughput": 1488.49, "total_tokens": 18728256} {"current_steps": 88740, "total_steps": 181800, "loss": 0.0202, "lr": 3.0358725151481078e-05, "epoch": 9.762376237623762, "percentage": 48.81, "elapsed_time": "3:29:42", "remaining_time": "3:39:55", "throughput": 1488.49, "total_tokens": 18729376} {"current_steps": 88745, "total_steps": 181800, "loss": 0.005, "lr": 3.0356380843508736e-05, "epoch": 9.762926292629263, "percentage": 48.81, "elapsed_time": "3:29:43", "remaining_time": "3:39:54", "throughput": 1488.5, "total_tokens": 18730528} {"current_steps": 88750, "total_steps": 181800, "loss": 0.0364, "lr": 3.0354036486169203e-05, "epoch": 9.763476347634764, "percentage": 48.82, "elapsed_time": "3:29:44", "remaining_time": "3:39:53", "throughput": 1488.51, "total_tokens": 18731584} {"current_steps": 88755, "total_steps": 181800, "loss": 0.0767, "lr": 3.0351692079484095e-05, "epoch": 9.764026402640264, "percentage": 48.82, "elapsed_time": "3:29:44", "remaining_time": "3:39:53", "throughput": 1488.51, "total_tokens": 18732608} {"current_steps": 88760, "total_steps": 181800, "loss": 0.0735, "lr": 3.0349347623475e-05, "epoch": 9.764576457645765, "percentage": 48.82, "elapsed_time": "3:29:45", "remaining_time": "3:39:52", "throughput": 1488.51, "total_tokens": 18733664} {"current_steps": 88765, "total_steps": 181800, "loss": 0.0501, "lr": 3.034700311816353e-05, "epoch": 9.765126512651266, "percentage": 48.83, "elapsed_time": "3:29:46", "remaining_time": "3:39:51", "throughput": 1488.51, "total_tokens": 18734656} {"current_steps": 88770, "total_steps": 181800, "loss": 0.0089, "lr": 3.0344658563571304e-05, "epoch": 9.765676567656765, "percentage": 48.83, "elapsed_time": "3:29:46", "remaining_time": "3:39:50", "throughput": 1488.51, "total_tokens": 18735680} {"current_steps": 88775, "total_steps": 181800, "loss": 0.0117, "lr": 3.0342313959719925e-05, "epoch": 9.766226622662266, "percentage": 48.83, "elapsed_time": "3:29:47", "remaining_time": "3:39:50", "throughput": 1488.51, "total_tokens": 18736704} {"current_steps": 88780, "total_steps": 181800, "loss": 0.0042, "lr": 3.0339969306631005e-05, "epoch": 9.766776677667767, "percentage": 48.83, "elapsed_time": "3:29:48", "remaining_time": "3:39:49", "throughput": 1488.51, "total_tokens": 18737792} {"current_steps": 88785, "total_steps": 181800, "loss": 0.0816, "lr": 3.0337624604326147e-05, "epoch": 9.767326732673267, "percentage": 48.84, "elapsed_time": "3:29:48", "remaining_time": "3:39:48", "throughput": 1488.52, "total_tokens": 18738912} {"current_steps": 88790, "total_steps": 181800, "loss": 0.0493, "lr": 3.0335279852826964e-05, "epoch": 9.767876787678768, "percentage": 48.84, "elapsed_time": "3:29:49", "remaining_time": "3:39:48", "throughput": 1488.52, "total_tokens": 18740000} {"current_steps": 88795, "total_steps": 181800, "loss": 0.0876, "lr": 3.0332935052155066e-05, "epoch": 9.768426842684269, "percentage": 48.84, "elapsed_time": "3:29:50", "remaining_time": "3:39:47", "throughput": 1488.52, "total_tokens": 18741024} {"current_steps": 88800, "total_steps": 181800, "loss": 0.0077, "lr": 3.0330590202332064e-05, "epoch": 9.768976897689768, "percentage": 48.84, "elapsed_time": "3:29:51", "remaining_time": "3:39:46", "throughput": 1488.53, "total_tokens": 18742080} {"current_steps": 88805, "total_steps": 181800, "loss": 0.0064, "lr": 3.032824530337957e-05, "epoch": 9.76952695269527, "percentage": 48.85, "elapsed_time": "3:29:51", "remaining_time": "3:39:45", "throughput": 1488.52, "total_tokens": 18743072} {"current_steps": 88810, "total_steps": 181800, "loss": 0.0071, "lr": 3.03259003553192e-05, "epoch": 9.77007700770077, "percentage": 48.85, "elapsed_time": "3:29:52", "remaining_time": "3:39:45", "throughput": 1488.53, "total_tokens": 18744192} {"current_steps": 88815, "total_steps": 181800, "loss": 0.0122, "lr": 3.0323555358172556e-05, "epoch": 9.770627062706271, "percentage": 48.85, "elapsed_time": "3:29:53", "remaining_time": "3:39:44", "throughput": 1488.53, "total_tokens": 18745216} {"current_steps": 88820, "total_steps": 181800, "loss": 0.0123, "lr": 3.0321210311961263e-05, "epoch": 9.77117711771177, "percentage": 48.86, "elapsed_time": "3:29:53", "remaining_time": "3:39:43", "throughput": 1488.53, "total_tokens": 18746208} {"current_steps": 88825, "total_steps": 181800, "loss": 0.0128, "lr": 3.0318865216706928e-05, "epoch": 9.771727172717272, "percentage": 48.86, "elapsed_time": "3:29:54", "remaining_time": "3:39:42", "throughput": 1488.53, "total_tokens": 18747264} {"current_steps": 88830, "total_steps": 181800, "loss": 0.0018, "lr": 3.0316520072431158e-05, "epoch": 9.772277227722773, "percentage": 48.86, "elapsed_time": "3:29:55", "remaining_time": "3:39:42", "throughput": 1488.54, "total_tokens": 18748352} {"current_steps": 88835, "total_steps": 181800, "loss": 0.0039, "lr": 3.031417487915557e-05, "epoch": 9.772827282728272, "percentage": 48.86, "elapsed_time": "3:29:55", "remaining_time": "3:39:41", "throughput": 1488.54, "total_tokens": 18749344} {"current_steps": 88840, "total_steps": 181800, "loss": 0.009, "lr": 3.031182963690179e-05, "epoch": 9.773377337733773, "percentage": 48.87, "elapsed_time": "3:29:56", "remaining_time": "3:39:40", "throughput": 1488.54, "total_tokens": 18750368} {"current_steps": 88845, "total_steps": 181800, "loss": 0.1321, "lr": 3.0309484345691423e-05, "epoch": 9.773927392739274, "percentage": 48.87, "elapsed_time": "3:29:57", "remaining_time": "3:39:39", "throughput": 1488.54, "total_tokens": 18751392} {"current_steps": 88850, "total_steps": 181800, "loss": 0.0084, "lr": 3.0307139005546094e-05, "epoch": 9.774477447744774, "percentage": 48.87, "elapsed_time": "3:29:57", "remaining_time": "3:39:39", "throughput": 1488.54, "total_tokens": 18752480} {"current_steps": 88855, "total_steps": 181800, "loss": 0.0049, "lr": 3.0304793616487404e-05, "epoch": 9.775027502750275, "percentage": 48.88, "elapsed_time": "3:29:58", "remaining_time": "3:39:38", "throughput": 1488.55, "total_tokens": 18753568} {"current_steps": 88860, "total_steps": 181800, "loss": 0.1008, "lr": 3.030244817853698e-05, "epoch": 9.775577557755776, "percentage": 48.88, "elapsed_time": "3:29:59", "remaining_time": "3:39:37", "throughput": 1488.54, "total_tokens": 18754560} {"current_steps": 88865, "total_steps": 181800, "loss": 0.0751, "lr": 3.0300102691716426e-05, "epoch": 9.776127612761275, "percentage": 48.88, "elapsed_time": "3:29:59", "remaining_time": "3:39:37", "throughput": 1488.55, "total_tokens": 18755712} {"current_steps": 88870, "total_steps": 181800, "loss": 0.0315, "lr": 3.0297757156047385e-05, "epoch": 9.776677667766776, "percentage": 48.88, "elapsed_time": "3:30:00", "remaining_time": "3:39:36", "throughput": 1488.55, "total_tokens": 18756736} {"current_steps": 88875, "total_steps": 181800, "loss": 0.036, "lr": 3.0295411571551447e-05, "epoch": 9.777227722772277, "percentage": 48.89, "elapsed_time": "3:30:01", "remaining_time": "3:39:35", "throughput": 1488.56, "total_tokens": 18757856} {"current_steps": 88880, "total_steps": 181800, "loss": 0.1116, "lr": 3.029306593825024e-05, "epoch": 9.777777777777779, "percentage": 48.89, "elapsed_time": "3:30:02", "remaining_time": "3:39:34", "throughput": 1488.57, "total_tokens": 18758976} {"current_steps": 88885, "total_steps": 181800, "loss": 0.081, "lr": 3.029072025616539e-05, "epoch": 9.778327832783278, "percentage": 48.89, "elapsed_time": "3:30:02", "remaining_time": "3:39:34", "throughput": 1488.57, "total_tokens": 18760032} {"current_steps": 88890, "total_steps": 181800, "loss": 0.1286, "lr": 3.028837452531851e-05, "epoch": 9.778877887788779, "percentage": 48.89, "elapsed_time": "3:30:03", "remaining_time": "3:39:33", "throughput": 1488.58, "total_tokens": 18761152} {"current_steps": 88895, "total_steps": 181800, "loss": 0.0133, "lr": 3.0286028745731216e-05, "epoch": 9.77942794279428, "percentage": 48.9, "elapsed_time": "3:30:04", "remaining_time": "3:39:32", "throughput": 1488.58, "total_tokens": 18762272} {"current_steps": 88900, "total_steps": 181800, "loss": 0.0187, "lr": 3.0283682917425133e-05, "epoch": 9.77997799779978, "percentage": 48.9, "elapsed_time": "3:30:04", "remaining_time": "3:39:31", "throughput": 1488.59, "total_tokens": 18763328} {"current_steps": 88905, "total_steps": 181800, "loss": 0.0217, "lr": 3.028133704042188e-05, "epoch": 9.78052805280528, "percentage": 48.9, "elapsed_time": "3:30:05", "remaining_time": "3:39:31", "throughput": 1488.59, "total_tokens": 18764384} {"current_steps": 88910, "total_steps": 181800, "loss": 0.0524, "lr": 3.0278991114743076e-05, "epoch": 9.781078107810782, "percentage": 48.91, "elapsed_time": "3:30:06", "remaining_time": "3:39:30", "throughput": 1488.59, "total_tokens": 18765440} {"current_steps": 88915, "total_steps": 181800, "loss": 0.017, "lr": 3.0276645140410348e-05, "epoch": 9.781628162816281, "percentage": 48.91, "elapsed_time": "3:30:06", "remaining_time": "3:39:29", "throughput": 1488.6, "total_tokens": 18766528} {"current_steps": 88920, "total_steps": 181800, "loss": 0.0209, "lr": 3.0274299117445316e-05, "epoch": 9.782178217821782, "percentage": 48.91, "elapsed_time": "3:30:07", "remaining_time": "3:39:29", "throughput": 1488.6, "total_tokens": 18767552} {"current_steps": 88925, "total_steps": 181800, "loss": 0.087, "lr": 3.0271953045869588e-05, "epoch": 9.782728272827283, "percentage": 48.91, "elapsed_time": "3:30:08", "remaining_time": "3:39:28", "throughput": 1488.59, "total_tokens": 18768576} {"current_steps": 88930, "total_steps": 181800, "loss": 0.0097, "lr": 3.0269606925704807e-05, "epoch": 9.783278327832782, "percentage": 48.92, "elapsed_time": "3:30:08", "remaining_time": "3:39:27", "throughput": 1488.59, "total_tokens": 18769600} {"current_steps": 88935, "total_steps": 181800, "loss": 0.1025, "lr": 3.0267260756972587e-05, "epoch": 9.783828382838283, "percentage": 48.92, "elapsed_time": "3:30:09", "remaining_time": "3:39:26", "throughput": 1488.6, "total_tokens": 18770656} {"current_steps": 88940, "total_steps": 181800, "loss": 0.0239, "lr": 3.026491453969455e-05, "epoch": 9.784378437843785, "percentage": 48.92, "elapsed_time": "3:30:10", "remaining_time": "3:39:26", "throughput": 1488.6, "total_tokens": 18771712} {"current_steps": 88945, "total_steps": 181800, "loss": 0.0188, "lr": 3.0262568273892328e-05, "epoch": 9.784928492849286, "percentage": 48.92, "elapsed_time": "3:30:11", "remaining_time": "3:39:25", "throughput": 1488.61, "total_tokens": 18772832} {"current_steps": 88950, "total_steps": 181800, "loss": 0.1246, "lr": 3.026022195958754e-05, "epoch": 9.785478547854785, "percentage": 48.93, "elapsed_time": "3:30:11", "remaining_time": "3:39:24", "throughput": 1488.61, "total_tokens": 18773920} {"current_steps": 88955, "total_steps": 181800, "loss": 0.035, "lr": 3.02578755968018e-05, "epoch": 9.786028602860286, "percentage": 48.93, "elapsed_time": "3:30:12", "remaining_time": "3:39:23", "throughput": 1488.61, "total_tokens": 18774912} {"current_steps": 88960, "total_steps": 181800, "loss": 0.0071, "lr": 3.0255529185556748e-05, "epoch": 9.786578657865787, "percentage": 48.93, "elapsed_time": "3:30:13", "remaining_time": "3:39:23", "throughput": 1488.61, "total_tokens": 18775968} {"current_steps": 88965, "total_steps": 181800, "loss": 0.0218, "lr": 3.0253182725874006e-05, "epoch": 9.787128712871286, "percentage": 48.94, "elapsed_time": "3:30:13", "remaining_time": "3:39:22", "throughput": 1488.61, "total_tokens": 18777024} {"current_steps": 88970, "total_steps": 181800, "loss": 0.013, "lr": 3.0250836217775203e-05, "epoch": 9.787678767876788, "percentage": 48.94, "elapsed_time": "3:30:14", "remaining_time": "3:39:21", "throughput": 1488.62, "total_tokens": 18778112} {"current_steps": 88975, "total_steps": 181800, "loss": 0.0898, "lr": 3.024848966128196e-05, "epoch": 9.788228822882289, "percentage": 48.94, "elapsed_time": "3:30:15", "remaining_time": "3:39:21", "throughput": 1488.62, "total_tokens": 18779200} {"current_steps": 88980, "total_steps": 181800, "loss": 0.0209, "lr": 3.0246143056415904e-05, "epoch": 9.788778877887788, "percentage": 48.94, "elapsed_time": "3:30:15", "remaining_time": "3:39:20", "throughput": 1488.63, "total_tokens": 18780352} {"current_steps": 88985, "total_steps": 181800, "loss": 0.0332, "lr": 3.024379640319866e-05, "epoch": 9.789328932893289, "percentage": 48.95, "elapsed_time": "3:30:16", "remaining_time": "3:39:19", "throughput": 1488.64, "total_tokens": 18781472} {"current_steps": 88990, "total_steps": 181800, "loss": 0.016, "lr": 3.0241449701651874e-05, "epoch": 9.78987898789879, "percentage": 48.95, "elapsed_time": "3:30:17", "remaining_time": "3:39:18", "throughput": 1488.64, "total_tokens": 18782464} {"current_steps": 88995, "total_steps": 181800, "loss": 0.1138, "lr": 3.023910295179715e-05, "epoch": 9.79042904290429, "percentage": 48.95, "elapsed_time": "3:30:17", "remaining_time": "3:39:18", "throughput": 1488.64, "total_tokens": 18783552} {"current_steps": 89000, "total_steps": 181800, "loss": 0.0554, "lr": 3.023675615365613e-05, "epoch": 9.79097909790979, "percentage": 48.95, "elapsed_time": "3:30:18", "remaining_time": "3:39:17", "throughput": 1488.65, "total_tokens": 18784640} {"current_steps": 89005, "total_steps": 181800, "loss": 0.0327, "lr": 3.023440930725045e-05, "epoch": 9.791529152915292, "percentage": 48.96, "elapsed_time": "3:30:19", "remaining_time": "3:39:16", "throughput": 1488.65, "total_tokens": 18785696} {"current_steps": 89010, "total_steps": 181800, "loss": 0.0125, "lr": 3.0232062412601726e-05, "epoch": 9.792079207920793, "percentage": 48.96, "elapsed_time": "3:30:19", "remaining_time": "3:39:15", "throughput": 1488.65, "total_tokens": 18786784} {"current_steps": 89015, "total_steps": 181800, "loss": 0.0044, "lr": 3.022971546973159e-05, "epoch": 9.792629262926292, "percentage": 48.96, "elapsed_time": "3:30:20", "remaining_time": "3:39:15", "throughput": 1488.66, "total_tokens": 18787872} {"current_steps": 89020, "total_steps": 181800, "loss": 0.022, "lr": 3.0227368478661677e-05, "epoch": 9.793179317931793, "percentage": 48.97, "elapsed_time": "3:30:21", "remaining_time": "3:39:14", "throughput": 1488.66, "total_tokens": 18788960} {"current_steps": 89025, "total_steps": 181800, "loss": 0.0354, "lr": 3.0225021439413615e-05, "epoch": 9.793729372937294, "percentage": 48.97, "elapsed_time": "3:30:22", "remaining_time": "3:39:13", "throughput": 1488.67, "total_tokens": 18790016} {"current_steps": 89030, "total_steps": 181800, "loss": 0.0292, "lr": 3.022267435200904e-05, "epoch": 9.794279427942794, "percentage": 48.97, "elapsed_time": "3:30:22", "remaining_time": "3:39:13", "throughput": 1488.67, "total_tokens": 18791040} {"current_steps": 89035, "total_steps": 181800, "loss": 0.0231, "lr": 3.0220327216469586e-05, "epoch": 9.794829482948295, "percentage": 48.97, "elapsed_time": "3:30:23", "remaining_time": "3:39:12", "throughput": 1488.67, "total_tokens": 18792128} {"current_steps": 89040, "total_steps": 181800, "loss": 0.0028, "lr": 3.021798003281688e-05, "epoch": 9.795379537953796, "percentage": 48.98, "elapsed_time": "3:30:24", "remaining_time": "3:39:11", "throughput": 1488.66, "total_tokens": 18793088} {"current_steps": 89045, "total_steps": 181800, "loss": 0.0189, "lr": 3.0215632801072553e-05, "epoch": 9.795929592959295, "percentage": 48.98, "elapsed_time": "3:30:24", "remaining_time": "3:39:10", "throughput": 1488.67, "total_tokens": 18794208} {"current_steps": 89050, "total_steps": 181800, "loss": 0.0055, "lr": 3.0213285521258238e-05, "epoch": 9.796479647964796, "percentage": 48.98, "elapsed_time": "3:30:25", "remaining_time": "3:39:10", "throughput": 1488.68, "total_tokens": 18795296} {"current_steps": 89055, "total_steps": 181800, "loss": 0.0426, "lr": 3.0210938193395572e-05, "epoch": 9.797029702970297, "percentage": 48.99, "elapsed_time": "3:30:26", "remaining_time": "3:39:09", "throughput": 1488.68, "total_tokens": 18796320} {"current_steps": 89060, "total_steps": 181800, "loss": 0.0387, "lr": 3.0208590817506195e-05, "epoch": 9.797579757975798, "percentage": 48.99, "elapsed_time": "3:30:26", "remaining_time": "3:39:08", "throughput": 1488.68, "total_tokens": 18797440} {"current_steps": 89065, "total_steps": 181800, "loss": 0.0597, "lr": 3.0206243393611738e-05, "epoch": 9.798129812981298, "percentage": 48.99, "elapsed_time": "3:30:27", "remaining_time": "3:39:07", "throughput": 1488.68, "total_tokens": 18798464} {"current_steps": 89070, "total_steps": 181800, "loss": 0.0235, "lr": 3.020389592173382e-05, "epoch": 9.798679867986799, "percentage": 48.99, "elapsed_time": "3:30:28", "remaining_time": "3:39:07", "throughput": 1488.68, "total_tokens": 18799488} {"current_steps": 89075, "total_steps": 181800, "loss": 0.0524, "lr": 3.0201548401894104e-05, "epoch": 9.7992299229923, "percentage": 49.0, "elapsed_time": "3:30:28", "remaining_time": "3:39:06", "throughput": 1488.69, "total_tokens": 18800544} {"current_steps": 89080, "total_steps": 181800, "loss": 0.0248, "lr": 3.0199200834114205e-05, "epoch": 9.7997799779978, "percentage": 49.0, "elapsed_time": "3:30:29", "remaining_time": "3:39:05", "throughput": 1488.69, "total_tokens": 18801568} {"current_steps": 89085, "total_steps": 181800, "loss": 0.0484, "lr": 3.019685321841577e-05, "epoch": 9.8003300330033, "percentage": 49.0, "elapsed_time": "3:30:30", "remaining_time": "3:39:04", "throughput": 1488.69, "total_tokens": 18802688} {"current_steps": 89090, "total_steps": 181800, "loss": 0.0141, "lr": 3.0194505554820435e-05, "epoch": 9.800880088008801, "percentage": 49.0, "elapsed_time": "3:30:31", "remaining_time": "3:39:04", "throughput": 1488.7, "total_tokens": 18803776} {"current_steps": 89095, "total_steps": 181800, "loss": 0.0163, "lr": 3.0192157843349832e-05, "epoch": 9.8014301430143, "percentage": 49.01, "elapsed_time": "3:30:31", "remaining_time": "3:39:03", "throughput": 1488.69, "total_tokens": 18804768} {"current_steps": 89100, "total_steps": 181800, "loss": 0.0605, "lr": 3.0189810084025598e-05, "epoch": 9.801980198019802, "percentage": 49.01, "elapsed_time": "3:30:32", "remaining_time": "3:39:02", "throughput": 1488.7, "total_tokens": 18805856} {"current_steps": 89105, "total_steps": 181800, "loss": 0.0119, "lr": 3.0187462276869376e-05, "epoch": 9.802530253025303, "percentage": 49.01, "elapsed_time": "3:30:33", "remaining_time": "3:39:02", "throughput": 1488.7, "total_tokens": 18806880} {"current_steps": 89110, "total_steps": 181800, "loss": 0.0578, "lr": 3.018511442190281e-05, "epoch": 9.803080308030804, "percentage": 49.02, "elapsed_time": "3:30:33", "remaining_time": "3:39:01", "throughput": 1488.7, "total_tokens": 18807936} {"current_steps": 89115, "total_steps": 181800, "loss": 0.0058, "lr": 3.0182766519147525e-05, "epoch": 9.803630363036303, "percentage": 49.02, "elapsed_time": "3:30:34", "remaining_time": "3:39:00", "throughput": 1488.7, "total_tokens": 18808896} {"current_steps": 89120, "total_steps": 181800, "loss": 0.0082, "lr": 3.0180418568625173e-05, "epoch": 9.804180418041804, "percentage": 49.02, "elapsed_time": "3:30:35", "remaining_time": "3:38:59", "throughput": 1488.7, "total_tokens": 18809952} {"current_steps": 89125, "total_steps": 181800, "loss": 0.0202, "lr": 3.0178070570357387e-05, "epoch": 9.804730473047305, "percentage": 49.02, "elapsed_time": "3:30:35", "remaining_time": "3:38:59", "throughput": 1488.7, "total_tokens": 18811008} {"current_steps": 89130, "total_steps": 181800, "loss": 0.0776, "lr": 3.017572252436581e-05, "epoch": 9.805280528052805, "percentage": 49.03, "elapsed_time": "3:30:36", "remaining_time": "3:38:58", "throughput": 1488.7, "total_tokens": 18812064} {"current_steps": 89135, "total_steps": 181800, "loss": 0.0242, "lr": 3.0173374430672086e-05, "epoch": 9.805830583058306, "percentage": 49.03, "elapsed_time": "3:30:37", "remaining_time": "3:38:57", "throughput": 1488.7, "total_tokens": 18813088} {"current_steps": 89140, "total_steps": 181800, "loss": 0.0387, "lr": 3.017102628929784e-05, "epoch": 9.806380638063807, "percentage": 49.03, "elapsed_time": "3:30:37", "remaining_time": "3:38:56", "throughput": 1488.7, "total_tokens": 18814080} {"current_steps": 89145, "total_steps": 181800, "loss": 0.0207, "lr": 3.0168678100264734e-05, "epoch": 9.806930693069306, "percentage": 49.03, "elapsed_time": "3:30:38", "remaining_time": "3:38:56", "throughput": 1488.7, "total_tokens": 18815104} {"current_steps": 89150, "total_steps": 181800, "loss": 0.0098, "lr": 3.0166329863594402e-05, "epoch": 9.807480748074807, "percentage": 49.04, "elapsed_time": "3:30:39", "remaining_time": "3:38:55", "throughput": 1488.7, "total_tokens": 18816160} {"current_steps": 89155, "total_steps": 181800, "loss": 0.0043, "lr": 3.0163981579308488e-05, "epoch": 9.808030803080309, "percentage": 49.04, "elapsed_time": "3:30:39", "remaining_time": "3:38:54", "throughput": 1488.71, "total_tokens": 18817216} {"current_steps": 89160, "total_steps": 181800, "loss": 0.02, "lr": 3.0161633247428634e-05, "epoch": 9.808580858085808, "percentage": 49.04, "elapsed_time": "3:30:40", "remaining_time": "3:38:54", "throughput": 1488.71, "total_tokens": 18818304} {"current_steps": 89165, "total_steps": 181800, "loss": 0.0977, "lr": 3.0159284867976478e-05, "epoch": 9.809130913091309, "percentage": 49.05, "elapsed_time": "3:30:41", "remaining_time": "3:38:53", "throughput": 1488.71, "total_tokens": 18819360} {"current_steps": 89170, "total_steps": 181800, "loss": 0.0242, "lr": 3.015693644097367e-05, "epoch": 9.80968096809681, "percentage": 49.05, "elapsed_time": "3:30:42", "remaining_time": "3:38:52", "throughput": 1488.72, "total_tokens": 18820448} {"current_steps": 89175, "total_steps": 181800, "loss": 0.038, "lr": 3.0154587966441854e-05, "epoch": 9.810231023102311, "percentage": 49.05, "elapsed_time": "3:30:42", "remaining_time": "3:38:51", "throughput": 1488.72, "total_tokens": 18821472} {"current_steps": 89180, "total_steps": 181800, "loss": 0.0514, "lr": 3.0152239444402686e-05, "epoch": 9.81078107810781, "percentage": 49.05, "elapsed_time": "3:30:43", "remaining_time": "3:38:51", "throughput": 1488.72, "total_tokens": 18822496} {"current_steps": 89185, "total_steps": 181800, "loss": 0.0335, "lr": 3.014989087487778e-05, "epoch": 9.811331133113312, "percentage": 49.06, "elapsed_time": "3:30:44", "remaining_time": "3:38:50", "throughput": 1488.72, "total_tokens": 18823552} {"current_steps": 89190, "total_steps": 181800, "loss": 0.0079, "lr": 3.014754225788881e-05, "epoch": 9.811881188118813, "percentage": 49.06, "elapsed_time": "3:30:44", "remaining_time": "3:38:49", "throughput": 1488.72, "total_tokens": 18824576} {"current_steps": 89195, "total_steps": 181800, "loss": 0.0462, "lr": 3.0145193593457417e-05, "epoch": 9.812431243124312, "percentage": 49.06, "elapsed_time": "3:30:45", "remaining_time": "3:38:48", "throughput": 1488.72, "total_tokens": 18825664} {"current_steps": 89200, "total_steps": 181800, "loss": 0.0752, "lr": 3.014284488160523e-05, "epoch": 9.812981298129813, "percentage": 49.06, "elapsed_time": "3:30:46", "remaining_time": "3:38:48", "throughput": 1488.72, "total_tokens": 18826688} {"current_steps": 89205, "total_steps": 181800, "loss": 0.0372, "lr": 3.014049612235393e-05, "epoch": 9.813531353135314, "percentage": 49.07, "elapsed_time": "3:30:46", "remaining_time": "3:38:47", "throughput": 1488.72, "total_tokens": 18827680} {"current_steps": 89210, "total_steps": 181800, "loss": 0.1336, "lr": 3.0138147315725128e-05, "epoch": 9.814081408140813, "percentage": 49.07, "elapsed_time": "3:30:47", "remaining_time": "3:38:46", "throughput": 1488.72, "total_tokens": 18828736} {"current_steps": 89215, "total_steps": 181800, "loss": 0.1307, "lr": 3.0135798461740494e-05, "epoch": 9.814631463146315, "percentage": 49.07, "elapsed_time": "3:30:48", "remaining_time": "3:38:46", "throughput": 1488.72, "total_tokens": 18829760} {"current_steps": 89220, "total_steps": 181800, "loss": 0.107, "lr": 3.0133449560421666e-05, "epoch": 9.815181518151816, "percentage": 49.08, "elapsed_time": "3:30:48", "remaining_time": "3:38:45", "throughput": 1488.72, "total_tokens": 18830784} {"current_steps": 89225, "total_steps": 181800, "loss": 0.0043, "lr": 3.0131100611790302e-05, "epoch": 9.815731573157315, "percentage": 49.08, "elapsed_time": "3:30:49", "remaining_time": "3:38:44", "throughput": 1488.73, "total_tokens": 18831872} {"current_steps": 89230, "total_steps": 181800, "loss": 0.0026, "lr": 3.0128751615868045e-05, "epoch": 9.816281628162816, "percentage": 49.08, "elapsed_time": "3:30:50", "remaining_time": "3:38:43", "throughput": 1488.73, "total_tokens": 18832864} {"current_steps": 89235, "total_steps": 181800, "loss": 0.0408, "lr": 3.0126402572676542e-05, "epoch": 9.816831683168317, "percentage": 49.08, "elapsed_time": "3:30:51", "remaining_time": "3:38:43", "throughput": 1488.73, "total_tokens": 18833888} {"current_steps": 89240, "total_steps": 181800, "loss": 0.0499, "lr": 3.0124053482237446e-05, "epoch": 9.817381738173818, "percentage": 49.09, "elapsed_time": "3:30:51", "remaining_time": "3:38:42", "throughput": 1488.73, "total_tokens": 18834912} {"current_steps": 89245, "total_steps": 181800, "loss": 0.0286, "lr": 3.0121704344572404e-05, "epoch": 9.817931793179318, "percentage": 49.09, "elapsed_time": "3:30:52", "remaining_time": "3:38:41", "throughput": 1488.73, "total_tokens": 18836000} {"current_steps": 89250, "total_steps": 181800, "loss": 0.033, "lr": 3.0119355159703077e-05, "epoch": 9.818481848184819, "percentage": 49.09, "elapsed_time": "3:30:53", "remaining_time": "3:38:40", "throughput": 1488.74, "total_tokens": 18837120} {"current_steps": 89255, "total_steps": 181800, "loss": 0.1106, "lr": 3.011700592765112e-05, "epoch": 9.81903190319032, "percentage": 49.1, "elapsed_time": "3:30:53", "remaining_time": "3:38:40", "throughput": 1488.74, "total_tokens": 18838176} {"current_steps": 89260, "total_steps": 181800, "loss": 0.0064, "lr": 3.0114656648438156e-05, "epoch": 9.819581958195819, "percentage": 49.1, "elapsed_time": "3:30:54", "remaining_time": "3:38:39", "throughput": 1488.74, "total_tokens": 18839264} {"current_steps": 89265, "total_steps": 181800, "loss": 0.0122, "lr": 3.0112307322085863e-05, "epoch": 9.82013201320132, "percentage": 49.1, "elapsed_time": "3:30:55", "remaining_time": "3:38:38", "throughput": 1488.74, "total_tokens": 18840288} {"current_steps": 89270, "total_steps": 181800, "loss": 0.0064, "lr": 3.010995794861589e-05, "epoch": 9.820682068206821, "percentage": 49.1, "elapsed_time": "3:30:55", "remaining_time": "3:38:38", "throughput": 1488.74, "total_tokens": 18841280} {"current_steps": 89275, "total_steps": 181800, "loss": 0.0246, "lr": 3.0107608528049885e-05, "epoch": 9.82123212321232, "percentage": 49.11, "elapsed_time": "3:30:56", "remaining_time": "3:38:37", "throughput": 1488.74, "total_tokens": 18842336} {"current_steps": 89280, "total_steps": 181800, "loss": 0.0691, "lr": 3.01052590604095e-05, "epoch": 9.821782178217822, "percentage": 49.11, "elapsed_time": "3:30:57", "remaining_time": "3:38:36", "throughput": 1488.75, "total_tokens": 18843392} {"current_steps": 89285, "total_steps": 181800, "loss": 0.0065, "lr": 3.0102909545716396e-05, "epoch": 9.822332233223323, "percentage": 49.11, "elapsed_time": "3:30:57", "remaining_time": "3:38:35", "throughput": 1488.75, "total_tokens": 18844416} {"current_steps": 89290, "total_steps": 181800, "loss": 0.1118, "lr": 3.010055998399222e-05, "epoch": 9.822882288228822, "percentage": 49.11, "elapsed_time": "3:30:58", "remaining_time": "3:38:35", "throughput": 1488.75, "total_tokens": 18845472} {"current_steps": 89295, "total_steps": 181800, "loss": 0.029, "lr": 3.0098210375258628e-05, "epoch": 9.823432343234323, "percentage": 49.12, "elapsed_time": "3:30:59", "remaining_time": "3:38:34", "throughput": 1488.75, "total_tokens": 18846496} {"current_steps": 89300, "total_steps": 181800, "loss": 0.008, "lr": 3.0095860719537282e-05, "epoch": 9.823982398239824, "percentage": 49.12, "elapsed_time": "3:30:59", "remaining_time": "3:38:33", "throughput": 1488.75, "total_tokens": 18847552} {"current_steps": 89305, "total_steps": 181800, "loss": 0.0829, "lr": 3.0093511016849836e-05, "epoch": 9.824532453245325, "percentage": 49.12, "elapsed_time": "3:31:00", "remaining_time": "3:38:32", "throughput": 1488.75, "total_tokens": 18848608} {"current_steps": 89310, "total_steps": 181800, "loss": 0.0341, "lr": 3.0091161267217937e-05, "epoch": 9.825082508250825, "percentage": 49.13, "elapsed_time": "3:31:01", "remaining_time": "3:38:32", "throughput": 1488.75, "total_tokens": 18849664} {"current_steps": 89315, "total_steps": 181800, "loss": 0.1276, "lr": 3.0088811470663248e-05, "epoch": 9.825632563256326, "percentage": 49.13, "elapsed_time": "3:31:02", "remaining_time": "3:38:31", "throughput": 1488.75, "total_tokens": 18850656} {"current_steps": 89320, "total_steps": 181800, "loss": 0.003, "lr": 3.008646162720743e-05, "epoch": 9.826182618261827, "percentage": 49.13, "elapsed_time": "3:31:02", "remaining_time": "3:38:30", "throughput": 1488.75, "total_tokens": 18851712} {"current_steps": 89325, "total_steps": 181800, "loss": 0.0395, "lr": 3.0084111736872134e-05, "epoch": 9.826732673267326, "percentage": 49.13, "elapsed_time": "3:31:03", "remaining_time": "3:38:30", "throughput": 1488.75, "total_tokens": 18852736} {"current_steps": 89330, "total_steps": 181800, "loss": 0.0567, "lr": 3.0081761799679015e-05, "epoch": 9.827282728272827, "percentage": 49.14, "elapsed_time": "3:31:04", "remaining_time": "3:38:29", "throughput": 1488.76, "total_tokens": 18853856} {"current_steps": 89335, "total_steps": 181800, "loss": 0.0155, "lr": 3.007941181564974e-05, "epoch": 9.827832783278328, "percentage": 49.14, "elapsed_time": "3:31:04", "remaining_time": "3:38:28", "throughput": 1488.76, "total_tokens": 18854912} {"current_steps": 89340, "total_steps": 181800, "loss": 0.109, "lr": 3.0077061784805967e-05, "epoch": 9.828382838283828, "percentage": 49.14, "elapsed_time": "3:31:05", "remaining_time": "3:38:27", "throughput": 1488.76, "total_tokens": 18855968} {"current_steps": 89345, "total_steps": 181800, "loss": 0.0093, "lr": 3.007471170716934e-05, "epoch": 9.828932893289329, "percentage": 49.14, "elapsed_time": "3:31:06", "remaining_time": "3:38:27", "throughput": 1488.77, "total_tokens": 18857024} {"current_steps": 89350, "total_steps": 181800, "loss": 0.0083, "lr": 3.0072361582761544e-05, "epoch": 9.82948294829483, "percentage": 49.15, "elapsed_time": "3:31:06", "remaining_time": "3:38:26", "throughput": 1488.77, "total_tokens": 18858080} {"current_steps": 89355, "total_steps": 181800, "loss": 0.157, "lr": 3.007001141160422e-05, "epoch": 9.83003300330033, "percentage": 49.15, "elapsed_time": "3:31:07", "remaining_time": "3:38:25", "throughput": 1488.77, "total_tokens": 18859168} {"current_steps": 89360, "total_steps": 181800, "loss": 0.0532, "lr": 3.0067661193719034e-05, "epoch": 9.83058305830583, "percentage": 49.15, "elapsed_time": "3:31:08", "remaining_time": "3:38:24", "throughput": 1488.77, "total_tokens": 18860192} {"current_steps": 89365, "total_steps": 181800, "loss": 0.006, "lr": 3.0065310929127644e-05, "epoch": 9.831133113311331, "percentage": 49.16, "elapsed_time": "3:31:08", "remaining_time": "3:38:24", "throughput": 1488.77, "total_tokens": 18861216} {"current_steps": 89370, "total_steps": 181800, "loss": 0.0018, "lr": 3.006296061785172e-05, "epoch": 9.831683168316832, "percentage": 49.16, "elapsed_time": "3:31:09", "remaining_time": "3:38:23", "throughput": 1488.78, "total_tokens": 18862304} {"current_steps": 89375, "total_steps": 181800, "loss": 0.0083, "lr": 3.006061025991291e-05, "epoch": 9.832233223322332, "percentage": 49.16, "elapsed_time": "3:31:10", "remaining_time": "3:38:22", "throughput": 1488.78, "total_tokens": 18863296} {"current_steps": 89380, "total_steps": 181800, "loss": 0.0375, "lr": 3.0058259855332882e-05, "epoch": 9.832783278327833, "percentage": 49.16, "elapsed_time": "3:31:11", "remaining_time": "3:38:21", "throughput": 1488.78, "total_tokens": 18864352} {"current_steps": 89385, "total_steps": 181800, "loss": 0.0158, "lr": 3.005590940413331e-05, "epoch": 9.833333333333334, "percentage": 49.17, "elapsed_time": "3:31:11", "remaining_time": "3:38:21", "throughput": 1488.78, "total_tokens": 18865376} {"current_steps": 89390, "total_steps": 181800, "loss": 0.0753, "lr": 3.0053558906335833e-05, "epoch": 9.833883388338833, "percentage": 49.17, "elapsed_time": "3:31:12", "remaining_time": "3:38:20", "throughput": 1488.78, "total_tokens": 18866368} {"current_steps": 89395, "total_steps": 181800, "loss": 0.048, "lr": 3.0051208361962145e-05, "epoch": 9.834433443344334, "percentage": 49.17, "elapsed_time": "3:31:13", "remaining_time": "3:38:19", "throughput": 1488.78, "total_tokens": 18867392} {"current_steps": 89400, "total_steps": 181800, "loss": 0.0883, "lr": 3.0048857771033884e-05, "epoch": 9.834983498349835, "percentage": 49.17, "elapsed_time": "3:31:13", "remaining_time": "3:38:19", "throughput": 1488.78, "total_tokens": 18868416} {"current_steps": 89405, "total_steps": 181800, "loss": 0.027, "lr": 3.0046507133572722e-05, "epoch": 9.835533553355335, "percentage": 49.18, "elapsed_time": "3:31:14", "remaining_time": "3:38:18", "throughput": 1488.78, "total_tokens": 18869472} {"current_steps": 89410, "total_steps": 181800, "loss": 0.0499, "lr": 3.004415644960033e-05, "epoch": 9.836083608360836, "percentage": 49.18, "elapsed_time": "3:31:15", "remaining_time": "3:38:17", "throughput": 1488.78, "total_tokens": 18870528} {"current_steps": 89415, "total_steps": 181800, "loss": 0.0579, "lr": 3.0041805719138366e-05, "epoch": 9.836633663366337, "percentage": 49.18, "elapsed_time": "3:31:15", "remaining_time": "3:38:16", "throughput": 1488.78, "total_tokens": 18871584} {"current_steps": 89420, "total_steps": 181800, "loss": 0.0088, "lr": 3.00394549422085e-05, "epoch": 9.837183718371836, "percentage": 49.19, "elapsed_time": "3:31:16", "remaining_time": "3:38:16", "throughput": 1488.78, "total_tokens": 18872608} {"current_steps": 89425, "total_steps": 181800, "loss": 0.0111, "lr": 3.0037104118832392e-05, "epoch": 9.837733773377337, "percentage": 49.19, "elapsed_time": "3:31:17", "remaining_time": "3:38:15", "throughput": 1488.79, "total_tokens": 18873664} {"current_steps": 89430, "total_steps": 181800, "loss": 0.0144, "lr": 3.0034753249031716e-05, "epoch": 9.838283828382838, "percentage": 49.19, "elapsed_time": "3:31:17", "remaining_time": "3:38:14", "throughput": 1488.79, "total_tokens": 18874720} {"current_steps": 89435, "total_steps": 181800, "loss": 0.0241, "lr": 3.003240233282813e-05, "epoch": 9.83883388338834, "percentage": 49.19, "elapsed_time": "3:31:18", "remaining_time": "3:38:13", "throughput": 1488.79, "total_tokens": 18875744} {"current_steps": 89440, "total_steps": 181800, "loss": 0.0324, "lr": 3.003005137024331e-05, "epoch": 9.839383938393839, "percentage": 49.2, "elapsed_time": "3:31:19", "remaining_time": "3:38:13", "throughput": 1488.79, "total_tokens": 18876768} {"current_steps": 89445, "total_steps": 181800, "loss": 0.0526, "lr": 3.0027700361298926e-05, "epoch": 9.83993399339934, "percentage": 49.2, "elapsed_time": "3:31:19", "remaining_time": "3:38:12", "throughput": 1488.79, "total_tokens": 18877856} {"current_steps": 89450, "total_steps": 181800, "loss": 0.121, "lr": 3.002534930601664e-05, "epoch": 9.840484048404841, "percentage": 49.2, "elapsed_time": "3:31:20", "remaining_time": "3:38:11", "throughput": 1488.8, "total_tokens": 18878912} {"current_steps": 89455, "total_steps": 181800, "loss": 0.0132, "lr": 3.0022998204418112e-05, "epoch": 9.84103410341034, "percentage": 49.21, "elapsed_time": "3:31:21", "remaining_time": "3:38:11", "throughput": 1488.8, "total_tokens": 18879968} {"current_steps": 89460, "total_steps": 181800, "loss": 0.0107, "lr": 3.0020647056525026e-05, "epoch": 9.841584158415841, "percentage": 49.21, "elapsed_time": "3:31:22", "remaining_time": "3:38:10", "throughput": 1488.8, "total_tokens": 18881056} {"current_steps": 89465, "total_steps": 181800, "loss": 0.0411, "lr": 3.0018295862359043e-05, "epoch": 9.842134213421343, "percentage": 49.21, "elapsed_time": "3:31:22", "remaining_time": "3:38:09", "throughput": 1488.8, "total_tokens": 18882048} {"current_steps": 89470, "total_steps": 181800, "loss": 0.0088, "lr": 3.001594462194183e-05, "epoch": 9.842684268426842, "percentage": 49.21, "elapsed_time": "3:31:23", "remaining_time": "3:38:08", "throughput": 1488.81, "total_tokens": 18883136} {"current_steps": 89475, "total_steps": 181800, "loss": 0.0394, "lr": 3.0013593335295066e-05, "epoch": 9.843234323432343, "percentage": 49.22, "elapsed_time": "3:31:24", "remaining_time": "3:38:08", "throughput": 1488.8, "total_tokens": 18884128} {"current_steps": 89480, "total_steps": 181800, "loss": 0.0061, "lr": 3.001124200244042e-05, "epoch": 9.843784378437844, "percentage": 49.22, "elapsed_time": "3:31:24", "remaining_time": "3:38:07", "throughput": 1488.81, "total_tokens": 18885216} {"current_steps": 89485, "total_steps": 181800, "loss": 0.004, "lr": 3.0008890623399562e-05, "epoch": 9.844334433443345, "percentage": 49.22, "elapsed_time": "3:31:25", "remaining_time": "3:38:06", "throughput": 1488.8, "total_tokens": 18886208} {"current_steps": 89490, "total_steps": 181800, "loss": 0.1364, "lr": 3.000653919819416e-05, "epoch": 9.844884488448844, "percentage": 49.22, "elapsed_time": "3:31:26", "remaining_time": "3:38:05", "throughput": 1488.8, "total_tokens": 18887232} {"current_steps": 89495, "total_steps": 181800, "loss": 0.0678, "lr": 3.0004187726845895e-05, "epoch": 9.845434543454346, "percentage": 49.23, "elapsed_time": "3:31:26", "remaining_time": "3:38:05", "throughput": 1488.8, "total_tokens": 18888256} {"current_steps": 89500, "total_steps": 181800, "loss": 0.0063, "lr": 3.0001836209376427e-05, "epoch": 9.845984598459847, "percentage": 49.23, "elapsed_time": "3:31:27", "remaining_time": "3:38:04", "throughput": 1488.8, "total_tokens": 18889248} {"current_steps": 89505, "total_steps": 181800, "loss": 0.0539, "lr": 2.999948464580743e-05, "epoch": 9.846534653465346, "percentage": 49.23, "elapsed_time": "3:31:28", "remaining_time": "3:38:03", "throughput": 1488.8, "total_tokens": 18890240} {"current_steps": 89510, "total_steps": 181800, "loss": 0.0546, "lr": 2.9997133036160587e-05, "epoch": 9.847084708470847, "percentage": 49.24, "elapsed_time": "3:31:28", "remaining_time": "3:38:03", "throughput": 1488.8, "total_tokens": 18891264} {"current_steps": 89515, "total_steps": 181800, "loss": 0.0389, "lr": 2.9994781380457575e-05, "epoch": 9.847634763476348, "percentage": 49.24, "elapsed_time": "3:31:29", "remaining_time": "3:38:02", "throughput": 1488.8, "total_tokens": 18892288} {"current_steps": 89520, "total_steps": 181800, "loss": 0.0268, "lr": 2.9992429678720047e-05, "epoch": 9.848184818481847, "percentage": 49.24, "elapsed_time": "3:31:30", "remaining_time": "3:38:01", "throughput": 1488.8, "total_tokens": 18893408} {"current_steps": 89525, "total_steps": 181800, "loss": 0.0029, "lr": 2.9990077930969694e-05, "epoch": 9.848734873487349, "percentage": 49.24, "elapsed_time": "3:31:31", "remaining_time": "3:38:00", "throughput": 1488.81, "total_tokens": 18894464} {"current_steps": 89530, "total_steps": 181800, "loss": 0.0503, "lr": 2.998772613722819e-05, "epoch": 9.84928492849285, "percentage": 49.25, "elapsed_time": "3:31:31", "remaining_time": "3:38:00", "throughput": 1488.81, "total_tokens": 18895552} {"current_steps": 89535, "total_steps": 181800, "loss": 0.0129, "lr": 2.99853742975172e-05, "epoch": 9.84983498349835, "percentage": 49.25, "elapsed_time": "3:31:32", "remaining_time": "3:37:59", "throughput": 1488.82, "total_tokens": 18896640} {"current_steps": 89540, "total_steps": 181800, "loss": 0.0341, "lr": 2.9983022411858418e-05, "epoch": 9.85038503850385, "percentage": 49.25, "elapsed_time": "3:31:33", "remaining_time": "3:37:58", "throughput": 1488.82, "total_tokens": 18897696} {"current_steps": 89545, "total_steps": 181800, "loss": 0.0887, "lr": 2.998067048027351e-05, "epoch": 9.850935093509351, "percentage": 49.25, "elapsed_time": "3:31:33", "remaining_time": "3:37:57", "throughput": 1488.82, "total_tokens": 18898720} {"current_steps": 89550, "total_steps": 181800, "loss": 0.0071, "lr": 2.997831850278414e-05, "epoch": 9.851485148514852, "percentage": 49.26, "elapsed_time": "3:31:34", "remaining_time": "3:37:57", "throughput": 1488.82, "total_tokens": 18899712} {"current_steps": 89555, "total_steps": 181800, "loss": 0.0185, "lr": 2.9975966479412004e-05, "epoch": 9.852035203520352, "percentage": 49.26, "elapsed_time": "3:31:35", "remaining_time": "3:37:56", "throughput": 1488.81, "total_tokens": 18900736} {"current_steps": 89560, "total_steps": 181800, "loss": 0.0242, "lr": 2.9973614410178773e-05, "epoch": 9.852585258525853, "percentage": 49.26, "elapsed_time": "3:31:35", "remaining_time": "3:37:55", "throughput": 1488.82, "total_tokens": 18901824} {"current_steps": 89565, "total_steps": 181800, "loss": 0.0144, "lr": 2.9971262295106128e-05, "epoch": 9.853135313531354, "percentage": 49.27, "elapsed_time": "3:31:36", "remaining_time": "3:37:55", "throughput": 1488.82, "total_tokens": 18902816} {"current_steps": 89570, "total_steps": 181800, "loss": 0.0111, "lr": 2.996891013421574e-05, "epoch": 9.853685368536853, "percentage": 49.27, "elapsed_time": "3:31:37", "remaining_time": "3:37:54", "throughput": 1488.81, "total_tokens": 18903808} {"current_steps": 89575, "total_steps": 181800, "loss": 0.025, "lr": 2.996655792752929e-05, "epoch": 9.854235423542354, "percentage": 49.27, "elapsed_time": "3:31:37", "remaining_time": "3:37:53", "throughput": 1488.81, "total_tokens": 18904832} {"current_steps": 89580, "total_steps": 181800, "loss": 0.071, "lr": 2.9964205675068458e-05, "epoch": 9.854785478547855, "percentage": 49.27, "elapsed_time": "3:31:38", "remaining_time": "3:37:52", "throughput": 1488.82, "total_tokens": 18905888} {"current_steps": 89585, "total_steps": 181800, "loss": 0.0048, "lr": 2.9961853376854933e-05, "epoch": 9.855335533553355, "percentage": 49.28, "elapsed_time": "3:31:39", "remaining_time": "3:37:52", "throughput": 1488.81, "total_tokens": 18906880} {"current_steps": 89590, "total_steps": 181800, "loss": 0.0046, "lr": 2.9959501032910377e-05, "epoch": 9.855885588558856, "percentage": 49.28, "elapsed_time": "3:31:39", "remaining_time": "3:37:51", "throughput": 1488.81, "total_tokens": 18907904} {"current_steps": 89595, "total_steps": 181800, "loss": 0.0549, "lr": 2.9957148643256484e-05, "epoch": 9.856435643564357, "percentage": 49.28, "elapsed_time": "3:31:40", "remaining_time": "3:37:50", "throughput": 1488.82, "total_tokens": 18909024} {"current_steps": 89600, "total_steps": 181800, "loss": 0.0031, "lr": 2.9954796207914925e-05, "epoch": 9.856985698569858, "percentage": 49.28, "elapsed_time": "3:31:41", "remaining_time": "3:37:49", "throughput": 1488.82, "total_tokens": 18910080} {"current_steps": 89605, "total_steps": 181800, "loss": 0.0088, "lr": 2.995244372690739e-05, "epoch": 9.857535753575357, "percentage": 49.29, "elapsed_time": "3:31:42", "remaining_time": "3:37:49", "throughput": 1488.82, "total_tokens": 18911104} {"current_steps": 89610, "total_steps": 181800, "loss": 0.043, "lr": 2.9950091200255565e-05, "epoch": 9.858085808580858, "percentage": 49.29, "elapsed_time": "3:31:42", "remaining_time": "3:37:48", "throughput": 1488.82, "total_tokens": 18912096} {"current_steps": 89615, "total_steps": 181800, "loss": 0.0072, "lr": 2.9947738627981115e-05, "epoch": 9.85863586358636, "percentage": 49.29, "elapsed_time": "3:31:43", "remaining_time": "3:37:47", "throughput": 1488.81, "total_tokens": 18913056} {"current_steps": 89620, "total_steps": 181800, "loss": 0.124, "lr": 2.9945386010105735e-05, "epoch": 9.859185918591859, "percentage": 49.3, "elapsed_time": "3:31:44", "remaining_time": "3:37:47", "throughput": 1488.81, "total_tokens": 18914080} {"current_steps": 89625, "total_steps": 181800, "loss": 0.0097, "lr": 2.9943033346651105e-05, "epoch": 9.85973597359736, "percentage": 49.3, "elapsed_time": "3:31:44", "remaining_time": "3:37:46", "throughput": 1488.81, "total_tokens": 18915136} {"current_steps": 89630, "total_steps": 181800, "loss": 0.0027, "lr": 2.9940680637638913e-05, "epoch": 9.86028602860286, "percentage": 49.3, "elapsed_time": "3:31:45", "remaining_time": "3:37:45", "throughput": 1488.82, "total_tokens": 18916192} {"current_steps": 89635, "total_steps": 181800, "loss": 0.0107, "lr": 2.9938327883090833e-05, "epoch": 9.86083608360836, "percentage": 49.3, "elapsed_time": "3:31:46", "remaining_time": "3:37:44", "throughput": 1488.82, "total_tokens": 18917280} {"current_steps": 89640, "total_steps": 181800, "loss": 0.0695, "lr": 2.9935975083028556e-05, "epoch": 9.861386138613861, "percentage": 49.31, "elapsed_time": "3:31:46", "remaining_time": "3:37:44", "throughput": 1488.82, "total_tokens": 18918336} {"current_steps": 89645, "total_steps": 181800, "loss": 0.0118, "lr": 2.993362223747377e-05, "epoch": 9.861936193619362, "percentage": 49.31, "elapsed_time": "3:31:47", "remaining_time": "3:37:43", "throughput": 1488.82, "total_tokens": 18919360} {"current_steps": 89650, "total_steps": 181800, "loss": 0.0421, "lr": 2.9931269346448142e-05, "epoch": 9.862486248624862, "percentage": 49.31, "elapsed_time": "3:31:48", "remaining_time": "3:37:42", "throughput": 1488.83, "total_tokens": 18920416} {"current_steps": 89655, "total_steps": 181800, "loss": 0.0339, "lr": 2.992891640997339e-05, "epoch": 9.863036303630363, "percentage": 49.32, "elapsed_time": "3:31:48", "remaining_time": "3:37:41", "throughput": 1488.83, "total_tokens": 18921472} {"current_steps": 89660, "total_steps": 181800, "loss": 0.0966, "lr": 2.992656342807117e-05, "epoch": 9.863586358635864, "percentage": 49.32, "elapsed_time": "3:31:49", "remaining_time": "3:37:41", "throughput": 1488.83, "total_tokens": 18922528} {"current_steps": 89665, "total_steps": 181800, "loss": 0.0096, "lr": 2.9924210400763174e-05, "epoch": 9.864136413641365, "percentage": 49.32, "elapsed_time": "3:31:50", "remaining_time": "3:37:40", "throughput": 1488.84, "total_tokens": 18923616} {"current_steps": 89670, "total_steps": 181800, "loss": 0.0349, "lr": 2.99218573280711e-05, "epoch": 9.864686468646864, "percentage": 49.32, "elapsed_time": "3:31:51", "remaining_time": "3:37:39", "throughput": 1488.84, "total_tokens": 18924640} {"current_steps": 89675, "total_steps": 181800, "loss": 0.0027, "lr": 2.9919504210016623e-05, "epoch": 9.865236523652365, "percentage": 49.33, "elapsed_time": "3:31:51", "remaining_time": "3:37:39", "throughput": 1488.83, "total_tokens": 18925632} {"current_steps": 89680, "total_steps": 181800, "loss": 0.0132, "lr": 2.9917151046621444e-05, "epoch": 9.865786578657866, "percentage": 49.33, "elapsed_time": "3:31:52", "remaining_time": "3:37:38", "throughput": 1488.84, "total_tokens": 18926720} {"current_steps": 89685, "total_steps": 181800, "loss": 0.1044, "lr": 2.9914797837907243e-05, "epoch": 9.866336633663366, "percentage": 49.33, "elapsed_time": "3:31:53", "remaining_time": "3:37:37", "throughput": 1488.84, "total_tokens": 18927808} {"current_steps": 89690, "total_steps": 181800, "loss": 0.0107, "lr": 2.9912444583895703e-05, "epoch": 9.866886688668867, "percentage": 49.33, "elapsed_time": "3:31:53", "remaining_time": "3:37:36", "throughput": 1488.84, "total_tokens": 18928832} {"current_steps": 89695, "total_steps": 181800, "loss": 0.0558, "lr": 2.9910091284608517e-05, "epoch": 9.867436743674368, "percentage": 49.34, "elapsed_time": "3:31:54", "remaining_time": "3:37:36", "throughput": 1488.85, "total_tokens": 18929920} {"current_steps": 89700, "total_steps": 181800, "loss": 0.0071, "lr": 2.9907737940067383e-05, "epoch": 9.867986798679867, "percentage": 49.34, "elapsed_time": "3:31:55", "remaining_time": "3:37:35", "throughput": 1488.85, "total_tokens": 18930944} {"current_steps": 89705, "total_steps": 181800, "loss": 0.0058, "lr": 2.9905384550293985e-05, "epoch": 9.868536853685368, "percentage": 49.34, "elapsed_time": "3:31:55", "remaining_time": "3:37:34", "throughput": 1488.85, "total_tokens": 18932000} {"current_steps": 89710, "total_steps": 181800, "loss": 0.131, "lr": 2.9903031115310003e-05, "epoch": 9.86908690869087, "percentage": 49.35, "elapsed_time": "3:31:56", "remaining_time": "3:37:33", "throughput": 1488.84, "total_tokens": 18932992} {"current_steps": 89715, "total_steps": 181800, "loss": 0.038, "lr": 2.9900677635137142e-05, "epoch": 9.869636963696369, "percentage": 49.35, "elapsed_time": "3:31:57", "remaining_time": "3:37:33", "throughput": 1488.85, "total_tokens": 18934112} {"current_steps": 89720, "total_steps": 181800, "loss": 0.0057, "lr": 2.9898324109797083e-05, "epoch": 9.87018701870187, "percentage": 49.35, "elapsed_time": "3:31:57", "remaining_time": "3:37:32", "throughput": 1488.86, "total_tokens": 18935200} {"current_steps": 89725, "total_steps": 181800, "loss": 0.104, "lr": 2.989597053931152e-05, "epoch": 9.870737073707371, "percentage": 49.35, "elapsed_time": "3:31:58", "remaining_time": "3:37:31", "throughput": 1488.86, "total_tokens": 18936224} {"current_steps": 89730, "total_steps": 181800, "loss": 0.0722, "lr": 2.989361692370215e-05, "epoch": 9.871287128712872, "percentage": 49.36, "elapsed_time": "3:31:59", "remaining_time": "3:37:31", "throughput": 1488.86, "total_tokens": 18937248} {"current_steps": 89735, "total_steps": 181800, "loss": 0.0346, "lr": 2.989126326299066e-05, "epoch": 9.871837183718371, "percentage": 49.36, "elapsed_time": "3:32:00", "remaining_time": "3:37:30", "throughput": 1488.86, "total_tokens": 18938304} {"current_steps": 89740, "total_steps": 181800, "loss": 0.0502, "lr": 2.988890955719874e-05, "epoch": 9.872387238723872, "percentage": 49.36, "elapsed_time": "3:32:00", "remaining_time": "3:37:29", "throughput": 1488.86, "total_tokens": 18939360} {"current_steps": 89745, "total_steps": 181800, "loss": 0.0245, "lr": 2.9886555806348088e-05, "epoch": 9.872937293729374, "percentage": 49.36, "elapsed_time": "3:32:01", "remaining_time": "3:37:28", "throughput": 1488.86, "total_tokens": 18940416} {"current_steps": 89750, "total_steps": 181800, "loss": 0.0479, "lr": 2.98842020104604e-05, "epoch": 9.873487348734873, "percentage": 49.37, "elapsed_time": "3:32:02", "remaining_time": "3:37:28", "throughput": 1488.88, "total_tokens": 18941632} {"current_steps": 89755, "total_steps": 181800, "loss": 0.0825, "lr": 2.9881848169557365e-05, "epoch": 9.874037403740374, "percentage": 49.37, "elapsed_time": "3:32:02", "remaining_time": "3:37:27", "throughput": 1488.88, "total_tokens": 18942720} {"current_steps": 89760, "total_steps": 181800, "loss": 0.0305, "lr": 2.9879494283660676e-05, "epoch": 9.874587458745875, "percentage": 49.37, "elapsed_time": "3:32:03", "remaining_time": "3:37:26", "throughput": 1488.89, "total_tokens": 18943776} {"current_steps": 89765, "total_steps": 181800, "loss": 0.0048, "lr": 2.9877140352792033e-05, "epoch": 9.875137513751374, "percentage": 49.38, "elapsed_time": "3:32:04", "remaining_time": "3:37:25", "throughput": 1488.89, "total_tokens": 18944896} {"current_steps": 89770, "total_steps": 181800, "loss": 0.0037, "lr": 2.987478637697312e-05, "epoch": 9.875687568756875, "percentage": 49.38, "elapsed_time": "3:32:04", "remaining_time": "3:37:25", "throughput": 1488.89, "total_tokens": 18945920} {"current_steps": 89775, "total_steps": 181800, "loss": 0.0482, "lr": 2.987243235622565e-05, "epoch": 9.876237623762377, "percentage": 49.38, "elapsed_time": "3:32:05", "remaining_time": "3:37:24", "throughput": 1488.9, "total_tokens": 18946976} {"current_steps": 89780, "total_steps": 181800, "loss": 0.0082, "lr": 2.9870078290571295e-05, "epoch": 9.876787678767876, "percentage": 49.38, "elapsed_time": "3:32:06", "remaining_time": "3:37:23", "throughput": 1488.87, "total_tokens": 18948032} {"current_steps": 89785, "total_steps": 181800, "loss": 0.0834, "lr": 2.9867724180031775e-05, "epoch": 9.877337733773377, "percentage": 49.39, "elapsed_time": "3:32:07", "remaining_time": "3:37:23", "throughput": 1488.87, "total_tokens": 18949056} {"current_steps": 89790, "total_steps": 181800, "loss": 0.0161, "lr": 2.9865370024628775e-05, "epoch": 9.877887788778878, "percentage": 49.39, "elapsed_time": "3:32:07", "remaining_time": "3:37:22", "throughput": 1488.87, "total_tokens": 18950048} {"current_steps": 89795, "total_steps": 181800, "loss": 0.0658, "lr": 2.9863015824384e-05, "epoch": 9.87843784378438, "percentage": 49.39, "elapsed_time": "3:32:08", "remaining_time": "3:37:21", "throughput": 1488.87, "total_tokens": 18951072} {"current_steps": 89800, "total_steps": 181800, "loss": 0.018, "lr": 2.986066157931913e-05, "epoch": 9.878987898789878, "percentage": 49.39, "elapsed_time": "3:32:09", "remaining_time": "3:37:21", "throughput": 1488.88, "total_tokens": 18952192} {"current_steps": 89805, "total_steps": 181800, "loss": 0.0345, "lr": 2.985830728945589e-05, "epoch": 9.87953795379538, "percentage": 49.4, "elapsed_time": "3:32:09", "remaining_time": "3:37:20", "throughput": 1488.88, "total_tokens": 18953280} {"current_steps": 89810, "total_steps": 181800, "loss": 0.0123, "lr": 2.9855952954815947e-05, "epoch": 9.88008800880088, "percentage": 49.4, "elapsed_time": "3:32:10", "remaining_time": "3:37:19", "throughput": 1488.89, "total_tokens": 18954336} {"current_steps": 89815, "total_steps": 181800, "loss": 0.027, "lr": 2.985359857542102e-05, "epoch": 9.88063806380638, "percentage": 49.4, "elapsed_time": "3:32:11", "remaining_time": "3:37:18", "throughput": 1488.9, "total_tokens": 18955488} {"current_steps": 89820, "total_steps": 181800, "loss": 0.1066, "lr": 2.9851244151292814e-05, "epoch": 9.881188118811881, "percentage": 49.41, "elapsed_time": "3:32:11", "remaining_time": "3:37:18", "throughput": 1488.9, "total_tokens": 18956576} {"current_steps": 89825, "total_steps": 181800, "loss": 0.0871, "lr": 2.9848889682453007e-05, "epoch": 9.881738173817382, "percentage": 49.41, "elapsed_time": "3:32:12", "remaining_time": "3:37:17", "throughput": 1488.91, "total_tokens": 18957664} {"current_steps": 89830, "total_steps": 181800, "loss": 0.0458, "lr": 2.984653516892332e-05, "epoch": 9.882288228822881, "percentage": 49.41, "elapsed_time": "3:32:13", "remaining_time": "3:37:16", "throughput": 1488.9, "total_tokens": 18958656} {"current_steps": 89835, "total_steps": 181800, "loss": 0.003, "lr": 2.9844180610725436e-05, "epoch": 9.882838283828383, "percentage": 49.41, "elapsed_time": "3:32:14", "remaining_time": "3:37:15", "throughput": 1488.9, "total_tokens": 18959648} {"current_steps": 89840, "total_steps": 181800, "loss": 0.0591, "lr": 2.9841826007881063e-05, "epoch": 9.883388338833884, "percentage": 49.42, "elapsed_time": "3:32:14", "remaining_time": "3:37:15", "throughput": 1488.9, "total_tokens": 18960640} {"current_steps": 89845, "total_steps": 181800, "loss": 0.0614, "lr": 2.9839471360411908e-05, "epoch": 9.883938393839383, "percentage": 49.42, "elapsed_time": "3:32:15", "remaining_time": "3:37:14", "throughput": 1488.9, "total_tokens": 18961696} {"current_steps": 89850, "total_steps": 181800, "loss": 0.0533, "lr": 2.983711666833967e-05, "epoch": 9.884488448844884, "percentage": 49.42, "elapsed_time": "3:32:16", "remaining_time": "3:37:13", "throughput": 1488.9, "total_tokens": 18962720} {"current_steps": 89855, "total_steps": 181800, "loss": 0.0295, "lr": 2.983476193168604e-05, "epoch": 9.885038503850385, "percentage": 49.43, "elapsed_time": "3:32:16", "remaining_time": "3:37:13", "throughput": 1488.9, "total_tokens": 18963808} {"current_steps": 89860, "total_steps": 181800, "loss": 0.1212, "lr": 2.9832407150472735e-05, "epoch": 9.885588558855886, "percentage": 49.43, "elapsed_time": "3:32:17", "remaining_time": "3:37:12", "throughput": 1488.91, "total_tokens": 18964896} {"current_steps": 89865, "total_steps": 181800, "loss": 0.0051, "lr": 2.9830052324721454e-05, "epoch": 9.886138613861386, "percentage": 49.43, "elapsed_time": "3:32:18", "remaining_time": "3:37:11", "throughput": 1488.91, "total_tokens": 18965920} {"current_steps": 89870, "total_steps": 181800, "loss": 0.0065, "lr": 2.9827697454453895e-05, "epoch": 9.886688668866887, "percentage": 49.43, "elapsed_time": "3:32:18", "remaining_time": "3:37:10", "throughput": 1488.91, "total_tokens": 18967008} {"current_steps": 89875, "total_steps": 181800, "loss": 0.0707, "lr": 2.9825342539691764e-05, "epoch": 9.887238723872388, "percentage": 49.44, "elapsed_time": "3:32:19", "remaining_time": "3:37:10", "throughput": 1488.92, "total_tokens": 18968128} {"current_steps": 89880, "total_steps": 181800, "loss": 0.062, "lr": 2.9822987580456768e-05, "epoch": 9.887788778877887, "percentage": 49.44, "elapsed_time": "3:32:20", "remaining_time": "3:37:09", "throughput": 1488.92, "total_tokens": 18969152} {"current_steps": 89885, "total_steps": 181800, "loss": 0.0334, "lr": 2.9820632576770607e-05, "epoch": 9.888338833883388, "percentage": 49.44, "elapsed_time": "3:32:20", "remaining_time": "3:37:08", "throughput": 1488.92, "total_tokens": 18970208} {"current_steps": 89890, "total_steps": 181800, "loss": 0.1105, "lr": 2.9818277528654993e-05, "epoch": 9.88888888888889, "percentage": 49.44, "elapsed_time": "3:32:21", "remaining_time": "3:37:07", "throughput": 1488.92, "total_tokens": 18971232} {"current_steps": 89895, "total_steps": 181800, "loss": 0.0312, "lr": 2.9815922436131627e-05, "epoch": 9.88943894389439, "percentage": 49.45, "elapsed_time": "3:32:22", "remaining_time": "3:37:07", "throughput": 1488.93, "total_tokens": 18972384} {"current_steps": 89900, "total_steps": 181800, "loss": 0.0244, "lr": 2.981356729922221e-05, "epoch": 9.88998899889989, "percentage": 49.45, "elapsed_time": "3:32:22", "remaining_time": "3:37:06", "throughput": 1488.93, "total_tokens": 18973440} {"current_steps": 89905, "total_steps": 181800, "loss": 0.0831, "lr": 2.9811212117948457e-05, "epoch": 9.89053905390539, "percentage": 49.45, "elapsed_time": "3:32:23", "remaining_time": "3:37:05", "throughput": 1488.93, "total_tokens": 18974496} {"current_steps": 89910, "total_steps": 181800, "loss": 0.0249, "lr": 2.980885689233207e-05, "epoch": 9.891089108910892, "percentage": 49.46, "elapsed_time": "3:32:24", "remaining_time": "3:37:05", "throughput": 1488.94, "total_tokens": 18975552} {"current_steps": 89915, "total_steps": 181800, "loss": 0.0109, "lr": 2.9806501622394757e-05, "epoch": 9.891639163916391, "percentage": 49.46, "elapsed_time": "3:32:25", "remaining_time": "3:37:04", "throughput": 1488.93, "total_tokens": 18976544} {"current_steps": 89920, "total_steps": 181800, "loss": 0.0039, "lr": 2.9804146308158227e-05, "epoch": 9.892189218921892, "percentage": 49.46, "elapsed_time": "3:32:25", "remaining_time": "3:37:03", "throughput": 1488.94, "total_tokens": 18977664} {"current_steps": 89925, "total_steps": 181800, "loss": 0.1099, "lr": 2.9801790949644174e-05, "epoch": 9.892739273927393, "percentage": 49.46, "elapsed_time": "3:32:26", "remaining_time": "3:37:02", "throughput": 1488.94, "total_tokens": 18978688} {"current_steps": 89930, "total_steps": 181800, "loss": 0.0533, "lr": 2.9799435546874334e-05, "epoch": 9.893289328932893, "percentage": 49.47, "elapsed_time": "3:32:27", "remaining_time": "3:37:02", "throughput": 1488.94, "total_tokens": 18979744} {"current_steps": 89935, "total_steps": 181800, "loss": 0.0219, "lr": 2.979708009987039e-05, "epoch": 9.893839383938394, "percentage": 49.47, "elapsed_time": "3:32:27", "remaining_time": "3:37:01", "throughput": 1488.95, "total_tokens": 18980832} {"current_steps": 89940, "total_steps": 181800, "loss": 0.1032, "lr": 2.9794724608654068e-05, "epoch": 9.894389438943895, "percentage": 49.47, "elapsed_time": "3:32:28", "remaining_time": "3:37:00", "throughput": 1488.96, "total_tokens": 18981984} {"current_steps": 89945, "total_steps": 181800, "loss": 0.1176, "lr": 2.979236907324706e-05, "epoch": 9.894939493949394, "percentage": 49.47, "elapsed_time": "3:32:29", "remaining_time": "3:36:59", "throughput": 1488.96, "total_tokens": 18983072} {"current_steps": 89950, "total_steps": 181800, "loss": 0.0142, "lr": 2.9790013493671093e-05, "epoch": 9.895489548954895, "percentage": 49.48, "elapsed_time": "3:32:29", "remaining_time": "3:36:59", "throughput": 1488.96, "total_tokens": 18984096} {"current_steps": 89955, "total_steps": 181800, "loss": 0.0099, "lr": 2.9787657869947867e-05, "epoch": 9.896039603960396, "percentage": 49.48, "elapsed_time": "3:32:30", "remaining_time": "3:36:58", "throughput": 1488.97, "total_tokens": 18985152} {"current_steps": 89960, "total_steps": 181800, "loss": 0.0083, "lr": 2.9785302202099096e-05, "epoch": 9.896589658965897, "percentage": 49.48, "elapsed_time": "3:32:31", "remaining_time": "3:36:57", "throughput": 1488.97, "total_tokens": 18986240} {"current_steps": 89965, "total_steps": 181800, "loss": 0.009, "lr": 2.9782946490146496e-05, "epoch": 9.897139713971397, "percentage": 49.49, "elapsed_time": "3:32:31", "remaining_time": "3:36:56", "throughput": 1488.97, "total_tokens": 18987296} {"current_steps": 89970, "total_steps": 181800, "loss": 0.1405, "lr": 2.9780590734111763e-05, "epoch": 9.897689768976898, "percentage": 49.49, "elapsed_time": "3:32:32", "remaining_time": "3:36:56", "throughput": 1488.98, "total_tokens": 18988384} {"current_steps": 89975, "total_steps": 181800, "loss": 0.0815, "lr": 2.977823493401663e-05, "epoch": 9.898239823982399, "percentage": 49.49, "elapsed_time": "3:32:33", "remaining_time": "3:36:55", "throughput": 1488.97, "total_tokens": 18989344} {"current_steps": 89980, "total_steps": 181800, "loss": 0.0152, "lr": 2.9775879089882793e-05, "epoch": 9.898789878987898, "percentage": 49.49, "elapsed_time": "3:32:34", "remaining_time": "3:36:54", "throughput": 1488.98, "total_tokens": 18990400} {"current_steps": 89985, "total_steps": 181800, "loss": 0.0131, "lr": 2.9773523201731967e-05, "epoch": 9.8993399339934, "percentage": 49.5, "elapsed_time": "3:32:34", "remaining_time": "3:36:54", "throughput": 1488.98, "total_tokens": 18991424} {"current_steps": 89990, "total_steps": 181800, "loss": 0.0058, "lr": 2.9771167269585874e-05, "epoch": 9.8998899889989, "percentage": 49.5, "elapsed_time": "3:32:35", "remaining_time": "3:36:53", "throughput": 1488.98, "total_tokens": 18992448} {"current_steps": 89995, "total_steps": 181800, "loss": 0.051, "lr": 2.976881129346622e-05, "epoch": 9.9004400440044, "percentage": 49.5, "elapsed_time": "3:32:36", "remaining_time": "3:36:52", "throughput": 1488.98, "total_tokens": 18993536} {"current_steps": 90000, "total_steps": 181800, "loss": 0.0029, "lr": 2.9766455273394718e-05, "epoch": 9.900990099009901, "percentage": 49.5, "elapsed_time": "3:32:36", "remaining_time": "3:36:51", "throughput": 1488.99, "total_tokens": 18994624} {"current_steps": 90005, "total_steps": 181800, "loss": 0.0058, "lr": 2.9764099209393086e-05, "epoch": 9.901540154015402, "percentage": 49.51, "elapsed_time": "3:32:37", "remaining_time": "3:36:51", "throughput": 1488.99, "total_tokens": 18995680} {"current_steps": 90010, "total_steps": 181800, "loss": 0.1045, "lr": 2.9761743101483042e-05, "epoch": 9.902090209020901, "percentage": 49.51, "elapsed_time": "3:32:38", "remaining_time": "3:36:50", "throughput": 1488.99, "total_tokens": 18996704} {"current_steps": 90015, "total_steps": 181800, "loss": 0.008, "lr": 2.975938694968629e-05, "epoch": 9.902640264026402, "percentage": 49.51, "elapsed_time": "3:32:38", "remaining_time": "3:36:49", "throughput": 1488.98, "total_tokens": 18997696} {"current_steps": 90020, "total_steps": 181800, "loss": 0.0539, "lr": 2.975703075402456e-05, "epoch": 9.903190319031903, "percentage": 49.52, "elapsed_time": "3:32:39", "remaining_time": "3:36:48", "throughput": 1488.99, "total_tokens": 18998752} {"current_steps": 90025, "total_steps": 181800, "loss": 0.0052, "lr": 2.9754674514519553e-05, "epoch": 9.903740374037405, "percentage": 49.52, "elapsed_time": "3:32:40", "remaining_time": "3:36:48", "throughput": 1488.99, "total_tokens": 18999808} {"current_steps": 90030, "total_steps": 181800, "loss": 0.0283, "lr": 2.9752318231192993e-05, "epoch": 9.904290429042904, "percentage": 49.52, "elapsed_time": "3:32:40", "remaining_time": "3:36:47", "throughput": 1488.99, "total_tokens": 19000800} {"current_steps": 90035, "total_steps": 181800, "loss": 0.1216, "lr": 2.9749961904066604e-05, "epoch": 9.904840484048405, "percentage": 49.52, "elapsed_time": "3:32:41", "remaining_time": "3:36:46", "throughput": 1488.99, "total_tokens": 19001920} {"current_steps": 90040, "total_steps": 181800, "loss": 0.0243, "lr": 2.9747605533162093e-05, "epoch": 9.905390539053906, "percentage": 49.53, "elapsed_time": "3:32:42", "remaining_time": "3:36:46", "throughput": 1488.99, "total_tokens": 19002912} {"current_steps": 90045, "total_steps": 181800, "loss": 0.0326, "lr": 2.974524911850117e-05, "epoch": 9.905940594059405, "percentage": 49.53, "elapsed_time": "3:32:42", "remaining_time": "3:36:45", "throughput": 1488.99, "total_tokens": 19003968} {"current_steps": 90050, "total_steps": 181800, "loss": 0.0126, "lr": 2.974289266010557e-05, "epoch": 9.906490649064907, "percentage": 49.53, "elapsed_time": "3:32:43", "remaining_time": "3:36:44", "throughput": 1489.0, "total_tokens": 19005024} {"current_steps": 90055, "total_steps": 181800, "loss": 0.1432, "lr": 2.9740536157997008e-05, "epoch": 9.907040704070408, "percentage": 49.54, "elapsed_time": "3:32:44", "remaining_time": "3:36:43", "throughput": 1489.0, "total_tokens": 19006048} {"current_steps": 90060, "total_steps": 181800, "loss": 0.0604, "lr": 2.973817961219719e-05, "epoch": 9.907590759075907, "percentage": 49.54, "elapsed_time": "3:32:45", "remaining_time": "3:36:43", "throughput": 1489.0, "total_tokens": 19007072} {"current_steps": 90065, "total_steps": 181800, "loss": 0.0117, "lr": 2.9735823022727856e-05, "epoch": 9.908140814081408, "percentage": 49.54, "elapsed_time": "3:32:45", "remaining_time": "3:36:42", "throughput": 1489.0, "total_tokens": 19008096} {"current_steps": 90070, "total_steps": 181800, "loss": 0.0177, "lr": 2.9733466389610696e-05, "epoch": 9.908690869086909, "percentage": 49.54, "elapsed_time": "3:32:46", "remaining_time": "3:36:41", "throughput": 1488.99, "total_tokens": 19009120} {"current_steps": 90075, "total_steps": 181800, "loss": 0.0097, "lr": 2.973110971286746e-05, "epoch": 9.909240924092408, "percentage": 49.55, "elapsed_time": "3:32:47", "remaining_time": "3:36:40", "throughput": 1488.99, "total_tokens": 19010112} {"current_steps": 90080, "total_steps": 181800, "loss": 0.0649, "lr": 2.972875299251986e-05, "epoch": 9.90979097909791, "percentage": 49.55, "elapsed_time": "3:32:47", "remaining_time": "3:36:40", "throughput": 1489.0, "total_tokens": 19011200} {"current_steps": 90085, "total_steps": 181800, "loss": 0.0101, "lr": 2.9726396228589604e-05, "epoch": 9.91034103410341, "percentage": 49.55, "elapsed_time": "3:32:48", "remaining_time": "3:36:39", "throughput": 1489.0, "total_tokens": 19012256} {"current_steps": 90090, "total_steps": 181800, "loss": 0.0078, "lr": 2.9724039421098427e-05, "epoch": 9.910891089108912, "percentage": 49.55, "elapsed_time": "3:32:49", "remaining_time": "3:36:38", "throughput": 1489.0, "total_tokens": 19013344} {"current_steps": 90095, "total_steps": 181800, "loss": 0.0027, "lr": 2.9721682570068042e-05, "epoch": 9.911441144114411, "percentage": 49.56, "elapsed_time": "3:32:49", "remaining_time": "3:36:38", "throughput": 1489.0, "total_tokens": 19014336} {"current_steps": 90100, "total_steps": 181800, "loss": 0.0209, "lr": 2.971932567552017e-05, "epoch": 9.911991199119912, "percentage": 49.56, "elapsed_time": "3:32:50", "remaining_time": "3:36:37", "throughput": 1489.0, "total_tokens": 19015360} {"current_steps": 90105, "total_steps": 181800, "loss": 0.033, "lr": 2.9716968737476546e-05, "epoch": 9.912541254125413, "percentage": 49.56, "elapsed_time": "3:32:51", "remaining_time": "3:36:36", "throughput": 1489.0, "total_tokens": 19016384} {"current_steps": 90110, "total_steps": 181800, "loss": 0.0039, "lr": 2.971461175595889e-05, "epoch": 9.913091309130913, "percentage": 49.57, "elapsed_time": "3:32:51", "remaining_time": "3:36:35", "throughput": 1489.0, "total_tokens": 19017440} {"current_steps": 90115, "total_steps": 181800, "loss": 0.0103, "lr": 2.971225473098891e-05, "epoch": 9.913641364136414, "percentage": 49.57, "elapsed_time": "3:32:52", "remaining_time": "3:36:35", "throughput": 1489.0, "total_tokens": 19018464} {"current_steps": 90120, "total_steps": 181800, "loss": 0.0598, "lr": 2.9709897662588338e-05, "epoch": 9.914191419141915, "percentage": 49.57, "elapsed_time": "3:32:53", "remaining_time": "3:36:34", "throughput": 1489.0, "total_tokens": 19019488} {"current_steps": 90125, "total_steps": 181800, "loss": 0.0263, "lr": 2.9707540550778907e-05, "epoch": 9.914741474147414, "percentage": 49.57, "elapsed_time": "3:32:53", "remaining_time": "3:36:33", "throughput": 1489.01, "total_tokens": 19020576} {"current_steps": 90130, "total_steps": 181800, "loss": 0.009, "lr": 2.9705183395582325e-05, "epoch": 9.915291529152915, "percentage": 49.58, "elapsed_time": "3:32:54", "remaining_time": "3:36:32", "throughput": 1489.01, "total_tokens": 19021568} {"current_steps": 90135, "total_steps": 181800, "loss": 0.1022, "lr": 2.9702826197020335e-05, "epoch": 9.915841584158416, "percentage": 49.58, "elapsed_time": "3:32:55", "remaining_time": "3:36:32", "throughput": 1489.0, "total_tokens": 19022560} {"current_steps": 90140, "total_steps": 181800, "loss": 0.0755, "lr": 2.9700468955114647e-05, "epoch": 9.916391639163916, "percentage": 49.58, "elapsed_time": "3:32:56", "remaining_time": "3:36:31", "throughput": 1489.0, "total_tokens": 19023584} {"current_steps": 90145, "total_steps": 181800, "loss": 0.0245, "lr": 2.9698111669886987e-05, "epoch": 9.916941694169417, "percentage": 49.58, "elapsed_time": "3:32:56", "remaining_time": "3:36:30", "throughput": 1489.0, "total_tokens": 19024608} {"current_steps": 90150, "total_steps": 181800, "loss": 0.0051, "lr": 2.9695754341359094e-05, "epoch": 9.917491749174918, "percentage": 49.59, "elapsed_time": "3:32:57", "remaining_time": "3:36:30", "throughput": 1489.01, "total_tokens": 19025696} {"current_steps": 90155, "total_steps": 181800, "loss": 0.015, "lr": 2.969339696955269e-05, "epoch": 9.918041804180419, "percentage": 49.59, "elapsed_time": "3:32:58", "remaining_time": "3:36:29", "throughput": 1489.01, "total_tokens": 19026752} {"current_steps": 90160, "total_steps": 181800, "loss": 0.0165, "lr": 2.9691039554489486e-05, "epoch": 9.918591859185918, "percentage": 49.59, "elapsed_time": "3:32:58", "remaining_time": "3:36:28", "throughput": 1489.01, "total_tokens": 19027744} {"current_steps": 90165, "total_steps": 181800, "loss": 0.0588, "lr": 2.968868209619123e-05, "epoch": 9.91914191419142, "percentage": 49.6, "elapsed_time": "3:32:59", "remaining_time": "3:36:27", "throughput": 1489.01, "total_tokens": 19028832} {"current_steps": 90170, "total_steps": 181800, "loss": 0.0297, "lr": 2.9686324594679636e-05, "epoch": 9.91969196919692, "percentage": 49.6, "elapsed_time": "3:33:00", "remaining_time": "3:36:27", "throughput": 1489.01, "total_tokens": 19029888} {"current_steps": 90175, "total_steps": 181800, "loss": 0.0093, "lr": 2.9683967049976437e-05, "epoch": 9.92024202420242, "percentage": 49.6, "elapsed_time": "3:33:00", "remaining_time": "3:36:26", "throughput": 1489.01, "total_tokens": 19030912} {"current_steps": 90180, "total_steps": 181800, "loss": 0.0364, "lr": 2.9681609462103366e-05, "epoch": 9.92079207920792, "percentage": 49.6, "elapsed_time": "3:33:01", "remaining_time": "3:36:25", "throughput": 1489.02, "total_tokens": 19032000} {"current_steps": 90185, "total_steps": 181800, "loss": 0.0158, "lr": 2.967925183108215e-05, "epoch": 9.921342134213422, "percentage": 49.61, "elapsed_time": "3:33:02", "remaining_time": "3:36:24", "throughput": 1489.02, "total_tokens": 19033024} {"current_steps": 90190, "total_steps": 181800, "loss": 0.0676, "lr": 2.9676894156934504e-05, "epoch": 9.921892189218921, "percentage": 49.61, "elapsed_time": "3:33:02", "remaining_time": "3:36:24", "throughput": 1489.02, "total_tokens": 19034048} {"current_steps": 90195, "total_steps": 181800, "loss": 0.0376, "lr": 2.9674536439682176e-05, "epoch": 9.922442244224422, "percentage": 49.61, "elapsed_time": "3:33:03", "remaining_time": "3:36:23", "throughput": 1489.02, "total_tokens": 19035072} {"current_steps": 90200, "total_steps": 181800, "loss": 0.1258, "lr": 2.9672178679346885e-05, "epoch": 9.922992299229923, "percentage": 49.61, "elapsed_time": "3:33:04", "remaining_time": "3:36:22", "throughput": 1489.02, "total_tokens": 19036128} {"current_steps": 90205, "total_steps": 181800, "loss": 0.0048, "lr": 2.966982087595037e-05, "epoch": 9.923542354235423, "percentage": 49.62, "elapsed_time": "3:33:05", "remaining_time": "3:36:22", "throughput": 1489.03, "total_tokens": 19037248} {"current_steps": 90210, "total_steps": 181800, "loss": 0.0248, "lr": 2.9667463029514354e-05, "epoch": 9.924092409240924, "percentage": 49.62, "elapsed_time": "3:33:05", "remaining_time": "3:36:21", "throughput": 1489.02, "total_tokens": 19038272} {"current_steps": 90215, "total_steps": 181800, "loss": 0.031, "lr": 2.9665105140060573e-05, "epoch": 9.924642464246425, "percentage": 49.62, "elapsed_time": "3:33:06", "remaining_time": "3:36:20", "throughput": 1489.02, "total_tokens": 19039296} {"current_steps": 90220, "total_steps": 181800, "loss": 0.0018, "lr": 2.9662747207610752e-05, "epoch": 9.925192519251926, "percentage": 49.63, "elapsed_time": "3:33:07", "remaining_time": "3:36:19", "throughput": 1489.03, "total_tokens": 19040416} {"current_steps": 90225, "total_steps": 181800, "loss": 0.0044, "lr": 2.9660389232186637e-05, "epoch": 9.925742574257425, "percentage": 49.63, "elapsed_time": "3:33:07", "remaining_time": "3:36:19", "throughput": 1489.04, "total_tokens": 19041504} {"current_steps": 90230, "total_steps": 181800, "loss": 0.0029, "lr": 2.9658031213809935e-05, "epoch": 9.926292629262926, "percentage": 49.63, "elapsed_time": "3:33:08", "remaining_time": "3:36:18", "throughput": 1489.04, "total_tokens": 19042560} {"current_steps": 90235, "total_steps": 181800, "loss": 0.044, "lr": 2.9655673152502405e-05, "epoch": 9.926842684268427, "percentage": 49.63, "elapsed_time": "3:33:09", "remaining_time": "3:36:17", "throughput": 1489.04, "total_tokens": 19043616} {"current_steps": 90240, "total_steps": 181800, "loss": 0.0413, "lr": 2.9653315048285768e-05, "epoch": 9.927392739273927, "percentage": 49.64, "elapsed_time": "3:33:09", "remaining_time": "3:36:16", "throughput": 1489.04, "total_tokens": 19044672} {"current_steps": 90245, "total_steps": 181800, "loss": 0.0028, "lr": 2.965095690118176e-05, "epoch": 9.927942794279428, "percentage": 49.64, "elapsed_time": "3:33:10", "remaining_time": "3:36:16", "throughput": 1489.04, "total_tokens": 19045728} {"current_steps": 90250, "total_steps": 181800, "loss": 0.1422, "lr": 2.9648598711212116e-05, "epoch": 9.928492849284929, "percentage": 49.64, "elapsed_time": "3:33:11", "remaining_time": "3:36:15", "throughput": 1489.04, "total_tokens": 19046752} {"current_steps": 90255, "total_steps": 181800, "loss": 0.0029, "lr": 2.964624047839856e-05, "epoch": 9.929042904290428, "percentage": 49.65, "elapsed_time": "3:33:11", "remaining_time": "3:36:14", "throughput": 1489.05, "total_tokens": 19047872} {"current_steps": 90260, "total_steps": 181800, "loss": 0.0703, "lr": 2.9643882202762842e-05, "epoch": 9.92959295929593, "percentage": 49.65, "elapsed_time": "3:33:12", "remaining_time": "3:36:14", "throughput": 1489.06, "total_tokens": 19048960} {"current_steps": 90265, "total_steps": 181800, "loss": 0.0064, "lr": 2.964152388432669e-05, "epoch": 9.93014301430143, "percentage": 49.65, "elapsed_time": "3:33:13", "remaining_time": "3:36:13", "throughput": 1489.06, "total_tokens": 19049984} {"current_steps": 90270, "total_steps": 181800, "loss": 0.1588, "lr": 2.9639165523111834e-05, "epoch": 9.930693069306932, "percentage": 49.65, "elapsed_time": "3:33:14", "remaining_time": "3:36:12", "throughput": 1489.06, "total_tokens": 19051040} {"current_steps": 90275, "total_steps": 181800, "loss": 0.0451, "lr": 2.963680711914002e-05, "epoch": 9.93124312431243, "percentage": 49.66, "elapsed_time": "3:33:14", "remaining_time": "3:36:11", "throughput": 1489.06, "total_tokens": 19052064} {"current_steps": 90280, "total_steps": 181800, "loss": 0.0556, "lr": 2.963444867243298e-05, "epoch": 9.931793179317932, "percentage": 49.66, "elapsed_time": "3:33:15", "remaining_time": "3:36:11", "throughput": 1489.06, "total_tokens": 19053088} {"current_steps": 90285, "total_steps": 181800, "loss": 0.0295, "lr": 2.9632090183012452e-05, "epoch": 9.932343234323433, "percentage": 49.66, "elapsed_time": "3:33:16", "remaining_time": "3:36:10", "throughput": 1489.06, "total_tokens": 19054176} {"current_steps": 90290, "total_steps": 181800, "loss": 0.023, "lr": 2.962973165090016e-05, "epoch": 9.932893289328932, "percentage": 49.66, "elapsed_time": "3:33:16", "remaining_time": "3:36:09", "throughput": 1489.06, "total_tokens": 19055200} {"current_steps": 90295, "total_steps": 181800, "loss": 0.0279, "lr": 2.9627373076117863e-05, "epoch": 9.933443344334433, "percentage": 49.67, "elapsed_time": "3:33:17", "remaining_time": "3:36:08", "throughput": 1489.06, "total_tokens": 19056256} {"current_steps": 90300, "total_steps": 181800, "loss": 0.0746, "lr": 2.9625014458687294e-05, "epoch": 9.933993399339935, "percentage": 49.67, "elapsed_time": "3:33:18", "remaining_time": "3:36:08", "throughput": 1489.07, "total_tokens": 19057344} {"current_steps": 90305, "total_steps": 181800, "loss": 0.1569, "lr": 2.9622655798630178e-05, "epoch": 9.934543454345434, "percentage": 49.67, "elapsed_time": "3:33:18", "remaining_time": "3:36:07", "throughput": 1489.08, "total_tokens": 19058496} {"current_steps": 90310, "total_steps": 181800, "loss": 0.0086, "lr": 2.9620297095968264e-05, "epoch": 9.935093509350935, "percentage": 49.68, "elapsed_time": "3:33:19", "remaining_time": "3:36:06", "throughput": 1489.08, "total_tokens": 19059552} {"current_steps": 90315, "total_steps": 181800, "loss": 0.0066, "lr": 2.961793835072329e-05, "epoch": 9.935643564356436, "percentage": 49.68, "elapsed_time": "3:33:20", "remaining_time": "3:36:06", "throughput": 1489.08, "total_tokens": 19060640} {"current_steps": 90320, "total_steps": 181800, "loss": 0.1592, "lr": 2.961557956291699e-05, "epoch": 9.936193619361937, "percentage": 49.68, "elapsed_time": "3:33:20", "remaining_time": "3:36:05", "throughput": 1489.09, "total_tokens": 19061696} {"current_steps": 90325, "total_steps": 181800, "loss": 0.0045, "lr": 2.9613220732571113e-05, "epoch": 9.936743674367436, "percentage": 49.68, "elapsed_time": "3:33:21", "remaining_time": "3:36:04", "throughput": 1489.09, "total_tokens": 19062752} {"current_steps": 90330, "total_steps": 181800, "loss": 0.0318, "lr": 2.961086185970739e-05, "epoch": 9.937293729372938, "percentage": 49.69, "elapsed_time": "3:33:22", "remaining_time": "3:36:03", "throughput": 1489.09, "total_tokens": 19063744} {"current_steps": 90335, "total_steps": 181800, "loss": 0.0043, "lr": 2.960850294434756e-05, "epoch": 9.937843784378439, "percentage": 49.69, "elapsed_time": "3:33:23", "remaining_time": "3:36:03", "throughput": 1489.09, "total_tokens": 19064832} {"current_steps": 90340, "total_steps": 181800, "loss": 0.0037, "lr": 2.960614398651338e-05, "epoch": 9.938393839383938, "percentage": 49.69, "elapsed_time": "3:33:23", "remaining_time": "3:36:02", "throughput": 1489.09, "total_tokens": 19065888} {"current_steps": 90345, "total_steps": 181800, "loss": 0.059, "lr": 2.960378498622658e-05, "epoch": 9.938943894389439, "percentage": 49.69, "elapsed_time": "3:33:24", "remaining_time": "3:36:01", "throughput": 1489.09, "total_tokens": 19066944} {"current_steps": 90350, "total_steps": 181800, "loss": 0.0047, "lr": 2.9601425943508898e-05, "epoch": 9.93949394939494, "percentage": 49.7, "elapsed_time": "3:33:25", "remaining_time": "3:36:00", "throughput": 1489.1, "total_tokens": 19068000} {"current_steps": 90355, "total_steps": 181800, "loss": 0.0434, "lr": 2.9599066858382084e-05, "epoch": 9.94004400440044, "percentage": 49.7, "elapsed_time": "3:33:25", "remaining_time": "3:36:00", "throughput": 1489.1, "total_tokens": 19069056} {"current_steps": 90360, "total_steps": 181800, "loss": 0.0017, "lr": 2.9596707730867877e-05, "epoch": 9.94059405940594, "percentage": 49.7, "elapsed_time": "3:33:26", "remaining_time": "3:35:59", "throughput": 1489.1, "total_tokens": 19070144} {"current_steps": 90365, "total_steps": 181800, "loss": 0.0619, "lr": 2.9594348560988017e-05, "epoch": 9.941144114411442, "percentage": 49.71, "elapsed_time": "3:33:27", "remaining_time": "3:35:58", "throughput": 1489.11, "total_tokens": 19071232} {"current_steps": 90370, "total_steps": 181800, "loss": 0.1123, "lr": 2.9591989348764265e-05, "epoch": 9.941694169416941, "percentage": 49.71, "elapsed_time": "3:33:27", "remaining_time": "3:35:58", "throughput": 1489.11, "total_tokens": 19072256} {"current_steps": 90375, "total_steps": 181800, "loss": 0.0059, "lr": 2.9589630094218335e-05, "epoch": 9.942244224422442, "percentage": 49.71, "elapsed_time": "3:33:28", "remaining_time": "3:35:57", "throughput": 1489.11, "total_tokens": 19073280} {"current_steps": 90380, "total_steps": 181800, "loss": 0.0628, "lr": 2.958727079737199e-05, "epoch": 9.942794279427943, "percentage": 49.71, "elapsed_time": "3:33:29", "remaining_time": "3:35:56", "throughput": 1489.11, "total_tokens": 19074272} {"current_steps": 90385, "total_steps": 181800, "loss": 0.0188, "lr": 2.9584911458246978e-05, "epoch": 9.943344334433444, "percentage": 49.72, "elapsed_time": "3:33:29", "remaining_time": "3:35:55", "throughput": 1489.11, "total_tokens": 19075328} {"current_steps": 90390, "total_steps": 181800, "loss": 0.0416, "lr": 2.9582552076865034e-05, "epoch": 9.943894389438944, "percentage": 49.72, "elapsed_time": "3:33:30", "remaining_time": "3:35:55", "throughput": 1489.11, "total_tokens": 19076352} {"current_steps": 90395, "total_steps": 181800, "loss": 0.0213, "lr": 2.9580192653247906e-05, "epoch": 9.944444444444445, "percentage": 49.72, "elapsed_time": "3:33:31", "remaining_time": "3:35:54", "throughput": 1489.11, "total_tokens": 19077344} {"current_steps": 90400, "total_steps": 181800, "loss": 0.0089, "lr": 2.9577833187417336e-05, "epoch": 9.944994499449946, "percentage": 49.72, "elapsed_time": "3:33:31", "remaining_time": "3:35:53", "throughput": 1489.11, "total_tokens": 19078400} {"current_steps": 90405, "total_steps": 181800, "loss": 0.0092, "lr": 2.9575473679395072e-05, "epoch": 9.945544554455445, "percentage": 49.73, "elapsed_time": "3:33:32", "remaining_time": "3:35:52", "throughput": 1489.11, "total_tokens": 19079456} {"current_steps": 90410, "total_steps": 181800, "loss": 0.0064, "lr": 2.9573114129202873e-05, "epoch": 9.946094609460946, "percentage": 49.73, "elapsed_time": "3:33:33", "remaining_time": "3:35:52", "throughput": 1489.11, "total_tokens": 19080480} {"current_steps": 90415, "total_steps": 181800, "loss": 0.003, "lr": 2.9570754536862478e-05, "epoch": 9.946644664466447, "percentage": 49.73, "elapsed_time": "3:33:34", "remaining_time": "3:35:51", "throughput": 1489.11, "total_tokens": 19081504} {"current_steps": 90420, "total_steps": 181800, "loss": 0.1122, "lr": 2.9568394902395614e-05, "epoch": 9.947194719471947, "percentage": 49.74, "elapsed_time": "3:33:34", "remaining_time": "3:35:50", "throughput": 1489.11, "total_tokens": 19082528} {"current_steps": 90425, "total_steps": 181800, "loss": 0.0472, "lr": 2.9566035225824056e-05, "epoch": 9.947744774477448, "percentage": 49.74, "elapsed_time": "3:33:35", "remaining_time": "3:35:50", "throughput": 1489.11, "total_tokens": 19083584} {"current_steps": 90430, "total_steps": 181800, "loss": 0.0793, "lr": 2.9563675507169547e-05, "epoch": 9.948294829482949, "percentage": 49.74, "elapsed_time": "3:33:36", "remaining_time": "3:35:49", "throughput": 1489.11, "total_tokens": 19084640} {"current_steps": 90435, "total_steps": 181800, "loss": 0.0523, "lr": 2.956131574645382e-05, "epoch": 9.948844884488448, "percentage": 49.74, "elapsed_time": "3:33:36", "remaining_time": "3:35:48", "throughput": 1489.12, "total_tokens": 19085728} {"current_steps": 90440, "total_steps": 181800, "loss": 0.009, "lr": 2.9558955943698647e-05, "epoch": 9.94939493949395, "percentage": 49.75, "elapsed_time": "3:33:37", "remaining_time": "3:35:47", "throughput": 1489.12, "total_tokens": 19086784} {"current_steps": 90445, "total_steps": 181800, "loss": 0.0079, "lr": 2.955659609892576e-05, "epoch": 9.94994499449945, "percentage": 49.75, "elapsed_time": "3:33:38", "remaining_time": "3:35:47", "throughput": 1489.12, "total_tokens": 19087840} {"current_steps": 90450, "total_steps": 181800, "loss": 0.0492, "lr": 2.9554236212156906e-05, "epoch": 9.950495049504951, "percentage": 49.75, "elapsed_time": "3:33:38", "remaining_time": "3:35:46", "throughput": 1489.13, "total_tokens": 19088960} {"current_steps": 90455, "total_steps": 181800, "loss": 0.1059, "lr": 2.9551876283413848e-05, "epoch": 9.95104510451045, "percentage": 49.76, "elapsed_time": "3:33:39", "remaining_time": "3:35:45", "throughput": 1489.14, "total_tokens": 19090080} {"current_steps": 90460, "total_steps": 181800, "loss": 0.0094, "lr": 2.9549516312718333e-05, "epoch": 9.951595159515952, "percentage": 49.76, "elapsed_time": "3:33:40", "remaining_time": "3:35:44", "throughput": 1489.15, "total_tokens": 19091232} {"current_steps": 90465, "total_steps": 181800, "loss": 0.024, "lr": 2.9547156300092105e-05, "epoch": 9.952145214521453, "percentage": 49.76, "elapsed_time": "3:33:40", "remaining_time": "3:35:44", "throughput": 1489.15, "total_tokens": 19092288} {"current_steps": 90470, "total_steps": 181800, "loss": 0.0611, "lr": 2.9544796245556926e-05, "epoch": 9.952695269526952, "percentage": 49.76, "elapsed_time": "3:33:41", "remaining_time": "3:35:43", "throughput": 1489.15, "total_tokens": 19093376} {"current_steps": 90475, "total_steps": 181800, "loss": 0.1744, "lr": 2.9542436149134535e-05, "epoch": 9.953245324532453, "percentage": 49.77, "elapsed_time": "3:33:42", "remaining_time": "3:35:42", "throughput": 1489.16, "total_tokens": 19094432} {"current_steps": 90480, "total_steps": 181800, "loss": 0.0087, "lr": 2.9540076010846683e-05, "epoch": 9.953795379537954, "percentage": 49.77, "elapsed_time": "3:33:43", "remaining_time": "3:35:42", "throughput": 1489.16, "total_tokens": 19095488} {"current_steps": 90485, "total_steps": 181800, "loss": 0.057, "lr": 2.953771583071514e-05, "epoch": 9.954345434543454, "percentage": 49.77, "elapsed_time": "3:33:43", "remaining_time": "3:35:41", "throughput": 1489.16, "total_tokens": 19096512} {"current_steps": 90490, "total_steps": 181800, "loss": 0.0158, "lr": 2.953535560876165e-05, "epoch": 9.954895489548955, "percentage": 49.77, "elapsed_time": "3:33:44", "remaining_time": "3:35:40", "throughput": 1489.17, "total_tokens": 19097632} {"current_steps": 90495, "total_steps": 181800, "loss": 0.0377, "lr": 2.953299534500795e-05, "epoch": 9.955445544554456, "percentage": 49.78, "elapsed_time": "3:33:45", "remaining_time": "3:35:39", "throughput": 1489.17, "total_tokens": 19098688} {"current_steps": 90500, "total_steps": 181800, "loss": 0.0512, "lr": 2.953063503947582e-05, "epoch": 9.955995599559955, "percentage": 49.78, "elapsed_time": "3:33:45", "remaining_time": "3:35:39", "throughput": 1489.17, "total_tokens": 19099776} {"current_steps": 90505, "total_steps": 181800, "loss": 0.1172, "lr": 2.9528274692186995e-05, "epoch": 9.956545654565456, "percentage": 49.78, "elapsed_time": "3:33:46", "remaining_time": "3:35:38", "throughput": 1489.17, "total_tokens": 19100768} {"current_steps": 90510, "total_steps": 181800, "loss": 0.0493, "lr": 2.952591430316324e-05, "epoch": 9.957095709570957, "percentage": 49.79, "elapsed_time": "3:33:47", "remaining_time": "3:35:37", "throughput": 1489.17, "total_tokens": 19101824} {"current_steps": 90515, "total_steps": 181800, "loss": 0.0161, "lr": 2.9523553872426295e-05, "epoch": 9.957645764576458, "percentage": 49.79, "elapsed_time": "3:33:47", "remaining_time": "3:35:36", "throughput": 1489.18, "total_tokens": 19102912} {"current_steps": 90520, "total_steps": 181800, "loss": 0.0054, "lr": 2.952119339999793e-05, "epoch": 9.958195819581958, "percentage": 49.79, "elapsed_time": "3:33:48", "remaining_time": "3:35:36", "throughput": 1489.18, "total_tokens": 19103968} {"current_steps": 90525, "total_steps": 181800, "loss": 0.0411, "lr": 2.9518832885899895e-05, "epoch": 9.958745874587459, "percentage": 49.79, "elapsed_time": "3:33:49", "remaining_time": "3:35:35", "throughput": 1489.18, "total_tokens": 19105056} {"current_steps": 90530, "total_steps": 181800, "loss": 0.0034, "lr": 2.9516472330153945e-05, "epoch": 9.95929592959296, "percentage": 49.8, "elapsed_time": "3:33:49", "remaining_time": "3:35:34", "throughput": 1489.19, "total_tokens": 19106144} {"current_steps": 90535, "total_steps": 181800, "loss": 0.0203, "lr": 2.9514111732781836e-05, "epoch": 9.95984598459846, "percentage": 49.8, "elapsed_time": "3:33:50", "remaining_time": "3:35:34", "throughput": 1489.19, "total_tokens": 19107200} {"current_steps": 90540, "total_steps": 181800, "loss": 0.0078, "lr": 2.9511751093805328e-05, "epoch": 9.96039603960396, "percentage": 49.8, "elapsed_time": "3:33:51", "remaining_time": "3:35:33", "throughput": 1489.2, "total_tokens": 19108288} {"current_steps": 90545, "total_steps": 181800, "loss": 0.0603, "lr": 2.9509390413246174e-05, "epoch": 9.960946094609461, "percentage": 49.8, "elapsed_time": "3:33:51", "remaining_time": "3:35:32", "throughput": 1489.2, "total_tokens": 19109376} {"current_steps": 90550, "total_steps": 181800, "loss": 0.0521, "lr": 2.950702969112613e-05, "epoch": 9.96149614961496, "percentage": 49.81, "elapsed_time": "3:33:52", "remaining_time": "3:35:31", "throughput": 1489.2, "total_tokens": 19110400} {"current_steps": 90555, "total_steps": 181800, "loss": 0.0158, "lr": 2.9504668927466957e-05, "epoch": 9.962046204620462, "percentage": 49.81, "elapsed_time": "3:33:53", "remaining_time": "3:35:31", "throughput": 1489.2, "total_tokens": 19111424} {"current_steps": 90560, "total_steps": 181800, "loss": 0.0035, "lr": 2.9502308122290418e-05, "epoch": 9.962596259625963, "percentage": 49.81, "elapsed_time": "3:33:54", "remaining_time": "3:35:30", "throughput": 1489.2, "total_tokens": 19112448} {"current_steps": 90565, "total_steps": 181800, "loss": 0.0438, "lr": 2.9499947275618257e-05, "epoch": 9.963146314631462, "percentage": 49.82, "elapsed_time": "3:33:54", "remaining_time": "3:35:29", "throughput": 1489.2, "total_tokens": 19113472} {"current_steps": 90570, "total_steps": 181800, "loss": 0.0134, "lr": 2.9497586387472242e-05, "epoch": 9.963696369636963, "percentage": 49.82, "elapsed_time": "3:33:55", "remaining_time": "3:35:28", "throughput": 1489.2, "total_tokens": 19114560} {"current_steps": 90575, "total_steps": 181800, "loss": 0.0164, "lr": 2.9495225457874136e-05, "epoch": 9.964246424642464, "percentage": 49.82, "elapsed_time": "3:33:56", "remaining_time": "3:35:28", "throughput": 1489.21, "total_tokens": 19115680} {"current_steps": 90580, "total_steps": 181800, "loss": 0.0116, "lr": 2.9492864486845697e-05, "epoch": 9.964796479647966, "percentage": 49.82, "elapsed_time": "3:33:56", "remaining_time": "3:35:27", "throughput": 1489.21, "total_tokens": 19116736} {"current_steps": 90585, "total_steps": 181800, "loss": 0.0635, "lr": 2.9490503474408676e-05, "epoch": 9.965346534653465, "percentage": 49.83, "elapsed_time": "3:33:57", "remaining_time": "3:35:26", "throughput": 1489.22, "total_tokens": 19117792} {"current_steps": 90590, "total_steps": 181800, "loss": 0.088, "lr": 2.948814242058484e-05, "epoch": 9.965896589658966, "percentage": 49.83, "elapsed_time": "3:33:58", "remaining_time": "3:35:26", "throughput": 1489.22, "total_tokens": 19118848} {"current_steps": 90595, "total_steps": 181800, "loss": 0.0091, "lr": 2.9485781325395946e-05, "epoch": 9.966446644664467, "percentage": 49.83, "elapsed_time": "3:33:58", "remaining_time": "3:35:25", "throughput": 1489.22, "total_tokens": 19119904} {"current_steps": 90600, "total_steps": 181800, "loss": 0.022, "lr": 2.9483420188863757e-05, "epoch": 9.966996699669966, "percentage": 49.83, "elapsed_time": "3:33:59", "remaining_time": "3:35:24", "throughput": 1489.22, "total_tokens": 19120928} {"current_steps": 90605, "total_steps": 181800, "loss": 0.005, "lr": 2.948105901101005e-05, "epoch": 9.967546754675467, "percentage": 49.84, "elapsed_time": "3:34:00", "remaining_time": "3:35:23", "throughput": 1489.22, "total_tokens": 19121952} {"current_steps": 90610, "total_steps": 181800, "loss": 0.0042, "lr": 2.947869779185656e-05, "epoch": 9.968096809680969, "percentage": 49.84, "elapsed_time": "3:34:00", "remaining_time": "3:35:23", "throughput": 1489.21, "total_tokens": 19122912} {"current_steps": 90615, "total_steps": 181800, "loss": 0.0107, "lr": 2.947633653142506e-05, "epoch": 9.968646864686468, "percentage": 49.84, "elapsed_time": "3:34:01", "remaining_time": "3:35:22", "throughput": 1489.22, "total_tokens": 19123968} {"current_steps": 90620, "total_steps": 181800, "loss": 0.0056, "lr": 2.9473975229737315e-05, "epoch": 9.969196919691969, "percentage": 49.85, "elapsed_time": "3:34:02", "remaining_time": "3:35:21", "throughput": 1489.21, "total_tokens": 19124960} {"current_steps": 90625, "total_steps": 181800, "loss": 0.002, "lr": 2.9471613886815086e-05, "epoch": 9.96974697469747, "percentage": 49.85, "elapsed_time": "3:34:03", "remaining_time": "3:35:20", "throughput": 1489.22, "total_tokens": 19126016} {"current_steps": 90630, "total_steps": 181800, "loss": 0.0328, "lr": 2.946925250268015e-05, "epoch": 9.97029702970297, "percentage": 49.85, "elapsed_time": "3:34:03", "remaining_time": "3:35:20", "throughput": 1489.22, "total_tokens": 19127104} {"current_steps": 90635, "total_steps": 181800, "loss": 0.0084, "lr": 2.9466891077354247e-05, "epoch": 9.97084708470847, "percentage": 49.85, "elapsed_time": "3:34:04", "remaining_time": "3:35:19", "throughput": 1489.23, "total_tokens": 19128192} {"current_steps": 90640, "total_steps": 181800, "loss": 0.0872, "lr": 2.9464529610859153e-05, "epoch": 9.971397139713972, "percentage": 49.86, "elapsed_time": "3:34:05", "remaining_time": "3:35:18", "throughput": 1489.23, "total_tokens": 19129216} {"current_steps": 90645, "total_steps": 181800, "loss": 0.0196, "lr": 2.946216810321663e-05, "epoch": 9.971947194719473, "percentage": 49.86, "elapsed_time": "3:34:05", "remaining_time": "3:35:18", "throughput": 1489.23, "total_tokens": 19130272} {"current_steps": 90650, "total_steps": 181800, "loss": 0.1078, "lr": 2.9459806554448453e-05, "epoch": 9.972497249724972, "percentage": 49.86, "elapsed_time": "3:34:06", "remaining_time": "3:35:17", "throughput": 1489.23, "total_tokens": 19131392} {"current_steps": 90655, "total_steps": 181800, "loss": 0.0285, "lr": 2.9457444964576374e-05, "epoch": 9.973047304730473, "percentage": 49.87, "elapsed_time": "3:34:07", "remaining_time": "3:35:16", "throughput": 1489.24, "total_tokens": 19132448} {"current_steps": 90660, "total_steps": 181800, "loss": 0.0136, "lr": 2.9455083333622163e-05, "epoch": 9.973597359735974, "percentage": 49.87, "elapsed_time": "3:34:07", "remaining_time": "3:35:15", "throughput": 1489.24, "total_tokens": 19133504} {"current_steps": 90665, "total_steps": 181800, "loss": 0.0521, "lr": 2.945272166160759e-05, "epoch": 9.974147414741473, "percentage": 49.87, "elapsed_time": "3:34:08", "remaining_time": "3:35:15", "throughput": 1489.24, "total_tokens": 19134560} {"current_steps": 90670, "total_steps": 181800, "loss": 0.1037, "lr": 2.9450359948554413e-05, "epoch": 9.974697469746975, "percentage": 49.87, "elapsed_time": "3:34:09", "remaining_time": "3:35:14", "throughput": 1489.24, "total_tokens": 19135616} {"current_steps": 90675, "total_steps": 181800, "loss": 0.0025, "lr": 2.9447998194484404e-05, "epoch": 9.975247524752476, "percentage": 49.88, "elapsed_time": "3:34:09", "remaining_time": "3:35:13", "throughput": 1489.25, "total_tokens": 19136704} {"current_steps": 90680, "total_steps": 181800, "loss": 0.0598, "lr": 2.9445636399419335e-05, "epoch": 9.975797579757975, "percentage": 49.88, "elapsed_time": "3:34:10", "remaining_time": "3:35:12", "throughput": 1489.25, "total_tokens": 19137728} {"current_steps": 90685, "total_steps": 181800, "loss": 0.028, "lr": 2.9443274563380968e-05, "epoch": 9.976347634763476, "percentage": 49.88, "elapsed_time": "3:34:11", "remaining_time": "3:35:12", "throughput": 1489.25, "total_tokens": 19138752} {"current_steps": 90690, "total_steps": 181800, "loss": 0.0479, "lr": 2.944091268639107e-05, "epoch": 9.976897689768977, "percentage": 49.88, "elapsed_time": "3:34:11", "remaining_time": "3:35:11", "throughput": 1489.25, "total_tokens": 19139776} {"current_steps": 90695, "total_steps": 181800, "loss": 0.0461, "lr": 2.9438550768471413e-05, "epoch": 9.977447744774478, "percentage": 49.89, "elapsed_time": "3:34:12", "remaining_time": "3:35:10", "throughput": 1489.25, "total_tokens": 19140864} {"current_steps": 90700, "total_steps": 181800, "loss": 0.0024, "lr": 2.9436188809643756e-05, "epoch": 9.977997799779978, "percentage": 49.89, "elapsed_time": "3:34:13", "remaining_time": "3:35:10", "throughput": 1489.27, "total_tokens": 19142048} {"current_steps": 90705, "total_steps": 181800, "loss": 0.1428, "lr": 2.9433826809929882e-05, "epoch": 9.978547854785479, "percentage": 49.89, "elapsed_time": "3:34:14", "remaining_time": "3:35:09", "throughput": 1489.27, "total_tokens": 19143104} {"current_steps": 90710, "total_steps": 181800, "loss": 0.0726, "lr": 2.9431464769351548e-05, "epoch": 9.97909790979098, "percentage": 49.9, "elapsed_time": "3:34:14", "remaining_time": "3:35:08", "throughput": 1489.26, "total_tokens": 19144096} {"current_steps": 90715, "total_steps": 181800, "loss": 0.1769, "lr": 2.942910268793054e-05, "epoch": 9.979647964796479, "percentage": 49.9, "elapsed_time": "3:34:15", "remaining_time": "3:35:07", "throughput": 1489.26, "total_tokens": 19145120} {"current_steps": 90720, "total_steps": 181800, "loss": 0.0145, "lr": 2.942674056568861e-05, "epoch": 9.98019801980198, "percentage": 49.9, "elapsed_time": "3:34:16", "remaining_time": "3:35:07", "throughput": 1489.28, "total_tokens": 19146304} {"current_steps": 90725, "total_steps": 181800, "loss": 0.0696, "lr": 2.9424378402647536e-05, "epoch": 9.980748074807481, "percentage": 49.9, "elapsed_time": "3:34:16", "remaining_time": "3:35:06", "throughput": 1489.28, "total_tokens": 19147360} {"current_steps": 90730, "total_steps": 181800, "loss": 0.0074, "lr": 2.9422016198829093e-05, "epoch": 9.98129812981298, "percentage": 49.91, "elapsed_time": "3:34:17", "remaining_time": "3:35:05", "throughput": 1489.28, "total_tokens": 19148448} {"current_steps": 90735, "total_steps": 181800, "loss": 0.0361, "lr": 2.9419653954255044e-05, "epoch": 9.981848184818482, "percentage": 49.91, "elapsed_time": "3:34:18", "remaining_time": "3:35:04", "throughput": 1489.28, "total_tokens": 19149504} {"current_steps": 90740, "total_steps": 181800, "loss": 0.0353, "lr": 2.9417291668947166e-05, "epoch": 9.982398239823983, "percentage": 49.91, "elapsed_time": "3:34:18", "remaining_time": "3:35:04", "throughput": 1489.29, "total_tokens": 19150560} {"current_steps": 90745, "total_steps": 181800, "loss": 0.0993, "lr": 2.9414929342927233e-05, "epoch": 9.982948294829484, "percentage": 49.91, "elapsed_time": "3:34:19", "remaining_time": "3:35:03", "throughput": 1489.29, "total_tokens": 19151680} {"current_steps": 90750, "total_steps": 181800, "loss": 0.0107, "lr": 2.9412566976217022e-05, "epoch": 9.983498349834983, "percentage": 49.92, "elapsed_time": "3:34:20", "remaining_time": "3:35:02", "throughput": 1489.3, "total_tokens": 19152800} {"current_steps": 90755, "total_steps": 181800, "loss": 0.028, "lr": 2.9410204568838284e-05, "epoch": 9.984048404840484, "percentage": 49.92, "elapsed_time": "3:34:20", "remaining_time": "3:35:02", "throughput": 1489.31, "total_tokens": 19153888} {"current_steps": 90760, "total_steps": 181800, "loss": 0.0225, "lr": 2.9407842120812812e-05, "epoch": 9.984598459845985, "percentage": 49.92, "elapsed_time": "3:34:21", "remaining_time": "3:35:01", "throughput": 1489.31, "total_tokens": 19154944} {"current_steps": 90765, "total_steps": 181800, "loss": 0.0598, "lr": 2.940547963216238e-05, "epoch": 9.985148514851485, "percentage": 49.93, "elapsed_time": "3:34:22", "remaining_time": "3:35:00", "throughput": 1489.31, "total_tokens": 19156000} {"current_steps": 90770, "total_steps": 181800, "loss": 0.0416, "lr": 2.9403117102908746e-05, "epoch": 9.985698569856986, "percentage": 49.93, "elapsed_time": "3:34:23", "remaining_time": "3:34:59", "throughput": 1489.32, "total_tokens": 19157120} {"current_steps": 90775, "total_steps": 181800, "loss": 0.0264, "lr": 2.9400754533073703e-05, "epoch": 9.986248624862487, "percentage": 49.93, "elapsed_time": "3:34:23", "remaining_time": "3:34:59", "throughput": 1489.32, "total_tokens": 19158176} {"current_steps": 90780, "total_steps": 181800, "loss": 0.2603, "lr": 2.939839192267902e-05, "epoch": 9.986798679867986, "percentage": 49.93, "elapsed_time": "3:34:24", "remaining_time": "3:34:58", "throughput": 1489.32, "total_tokens": 19159200} {"current_steps": 90785, "total_steps": 181800, "loss": 0.09, "lr": 2.9396029271746456e-05, "epoch": 9.987348734873487, "percentage": 49.94, "elapsed_time": "3:34:25", "remaining_time": "3:34:57", "throughput": 1489.32, "total_tokens": 19160224} {"current_steps": 90790, "total_steps": 181800, "loss": 0.0023, "lr": 2.9393666580297806e-05, "epoch": 9.987898789878988, "percentage": 49.94, "elapsed_time": "3:34:25", "remaining_time": "3:34:56", "throughput": 1489.32, "total_tokens": 19161248} {"current_steps": 90795, "total_steps": 181800, "loss": 0.0563, "lr": 2.9391303848354846e-05, "epoch": 9.988448844884488, "percentage": 49.94, "elapsed_time": "3:34:26", "remaining_time": "3:34:56", "throughput": 1489.31, "total_tokens": 19162240} {"current_steps": 90800, "total_steps": 181800, "loss": 0.161, "lr": 2.9388941075939334e-05, "epoch": 9.988998899889989, "percentage": 49.94, "elapsed_time": "3:34:27", "remaining_time": "3:34:55", "throughput": 1489.32, "total_tokens": 19163296} {"current_steps": 90805, "total_steps": 181800, "loss": 0.0199, "lr": 2.9386578263073066e-05, "epoch": 9.98954895489549, "percentage": 49.95, "elapsed_time": "3:34:27", "remaining_time": "3:34:54", "throughput": 1489.32, "total_tokens": 19164320} {"current_steps": 90810, "total_steps": 181800, "loss": 0.0782, "lr": 2.9384215409777816e-05, "epoch": 9.990099009900991, "percentage": 49.95, "elapsed_time": "3:34:28", "remaining_time": "3:34:54", "throughput": 1489.32, "total_tokens": 19165376} {"current_steps": 90815, "total_steps": 181800, "loss": 0.0108, "lr": 2.938185251607534e-05, "epoch": 9.99064906490649, "percentage": 49.95, "elapsed_time": "3:34:29", "remaining_time": "3:34:53", "throughput": 1489.32, "total_tokens": 19166432} {"current_steps": 90820, "total_steps": 181800, "loss": 0.0188, "lr": 2.9379489581987453e-05, "epoch": 9.991199119911991, "percentage": 49.96, "elapsed_time": "3:34:29", "remaining_time": "3:34:52", "throughput": 1489.33, "total_tokens": 19167520} {"current_steps": 90825, "total_steps": 181800, "loss": 0.0473, "lr": 2.9377126607535897e-05, "epoch": 9.991749174917492, "percentage": 49.96, "elapsed_time": "3:34:30", "remaining_time": "3:34:51", "throughput": 1489.34, "total_tokens": 19168672} {"current_steps": 90830, "total_steps": 181800, "loss": 0.0036, "lr": 2.9374763592742466e-05, "epoch": 9.992299229922992, "percentage": 49.96, "elapsed_time": "3:34:31", "remaining_time": "3:34:51", "throughput": 1489.34, "total_tokens": 19169792} {"current_steps": 90835, "total_steps": 181800, "loss": 0.0233, "lr": 2.9372400537628942e-05, "epoch": 9.992849284928493, "percentage": 49.96, "elapsed_time": "3:34:31", "remaining_time": "3:34:50", "throughput": 1489.34, "total_tokens": 19170816} {"current_steps": 90840, "total_steps": 181800, "loss": 0.0071, "lr": 2.93700374422171e-05, "epoch": 9.993399339933994, "percentage": 49.97, "elapsed_time": "3:34:32", "remaining_time": "3:34:49", "throughput": 1489.34, "total_tokens": 19171872} {"current_steps": 90845, "total_steps": 181800, "loss": 0.0946, "lr": 2.936767430652872e-05, "epoch": 9.993949394939493, "percentage": 49.97, "elapsed_time": "3:34:33", "remaining_time": "3:34:48", "throughput": 1489.35, "total_tokens": 19172928} {"current_steps": 90850, "total_steps": 181800, "loss": 0.0392, "lr": 2.9365311130585584e-05, "epoch": 9.994499449944994, "percentage": 49.97, "elapsed_time": "3:34:34", "remaining_time": "3:34:48", "throughput": 1489.35, "total_tokens": 19173984} {"current_steps": 90855, "total_steps": 181800, "loss": 0.0301, "lr": 2.9362947914409466e-05, "epoch": 9.995049504950495, "percentage": 49.98, "elapsed_time": "3:34:34", "remaining_time": "3:34:47", "throughput": 1489.35, "total_tokens": 19175040} {"current_steps": 90860, "total_steps": 181800, "loss": 0.0063, "lr": 2.9360584658022144e-05, "epoch": 9.995599559955995, "percentage": 49.98, "elapsed_time": "3:34:35", "remaining_time": "3:34:46", "throughput": 1489.35, "total_tokens": 19176032} {"current_steps": 90865, "total_steps": 181800, "loss": 0.0783, "lr": 2.9358221361445415e-05, "epoch": 9.996149614961496, "percentage": 49.98, "elapsed_time": "3:34:36", "remaining_time": "3:34:46", "throughput": 1489.35, "total_tokens": 19177056} {"current_steps": 90870, "total_steps": 181800, "loss": 0.0359, "lr": 2.935585802470105e-05, "epoch": 9.996699669966997, "percentage": 49.98, "elapsed_time": "3:34:36", "remaining_time": "3:34:45", "throughput": 1489.35, "total_tokens": 19178112} {"current_steps": 90875, "total_steps": 181800, "loss": 0.0424, "lr": 2.935349464781083e-05, "epoch": 9.997249724972498, "percentage": 49.99, "elapsed_time": "3:34:37", "remaining_time": "3:34:44", "throughput": 1489.35, "total_tokens": 19179136} {"current_steps": 90880, "total_steps": 181800, "loss": 0.0059, "lr": 2.9351131230796548e-05, "epoch": 9.997799779977997, "percentage": 49.99, "elapsed_time": "3:34:38", "remaining_time": "3:34:43", "throughput": 1489.35, "total_tokens": 19180192} {"current_steps": 90885, "total_steps": 181800, "loss": 0.0089, "lr": 2.9348767773679957e-05, "epoch": 9.998349834983498, "percentage": 49.99, "elapsed_time": "3:34:38", "remaining_time": "3:34:43", "throughput": 1489.36, "total_tokens": 19181280} {"current_steps": 90890, "total_steps": 181800, "loss": 0.1048, "lr": 2.9346404276482875e-05, "epoch": 9.998899889989, "percentage": 49.99, "elapsed_time": "3:34:39", "remaining_time": "3:34:42", "throughput": 1489.36, "total_tokens": 19182272} {"current_steps": 90895, "total_steps": 181800, "loss": 0.0151, "lr": 2.9344040739227075e-05, "epoch": 9.999449944994499, "percentage": 50.0, "elapsed_time": "3:34:40", "remaining_time": "3:34:41", "throughput": 1489.36, "total_tokens": 19183328} {"current_steps": 90900, "total_steps": 181800, "loss": 0.0662, "lr": 2.9341677161934323e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "3:34:40", "remaining_time": "3:34:40", "throughput": 1489.34, "total_tokens": 19184224} {"current_steps": 90900, "total_steps": 181800, "eval_loss": 0.060428909957408905, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "3:35:17", "remaining_time": "3:35:17", "throughput": 1485.08, "total_tokens": 19184224} {"current_steps": 90905, "total_steps": 181800, "loss": 0.009, "lr": 2.9339313544626425e-05, "epoch": 10.000550055005501, "percentage": 50.0, "elapsed_time": "3:35:19", "remaining_time": "3:35:18", "throughput": 1484.93, "total_tokens": 19185312} {"current_steps": 90910, "total_steps": 181800, "loss": 0.1196, "lr": 2.9336949887325154e-05, "epoch": 10.001100110011, "percentage": 50.01, "elapsed_time": "3:35:20", "remaining_time": "3:35:17", "throughput": 1484.93, "total_tokens": 19186304} {"current_steps": 90915, "total_steps": 181800, "loss": 0.1014, "lr": 2.9334586190052293e-05, "epoch": 10.001650165016502, "percentage": 50.01, "elapsed_time": "3:35:21", "remaining_time": "3:35:17", "throughput": 1484.93, "total_tokens": 19187360} {"current_steps": 90920, "total_steps": 181800, "loss": 0.0639, "lr": 2.9332222452829638e-05, "epoch": 10.002200220022003, "percentage": 50.01, "elapsed_time": "3:35:22", "remaining_time": "3:35:16", "throughput": 1484.94, "total_tokens": 19188448} {"current_steps": 90925, "total_steps": 181800, "loss": 0.0617, "lr": 2.932985867567896e-05, "epoch": 10.002750275027502, "percentage": 50.01, "elapsed_time": "3:35:22", "remaining_time": "3:35:15", "throughput": 1484.94, "total_tokens": 19189504} {"current_steps": 90930, "total_steps": 181800, "loss": 0.0298, "lr": 2.9327494858622056e-05, "epoch": 10.003300330033003, "percentage": 50.02, "elapsed_time": "3:35:23", "remaining_time": "3:35:14", "throughput": 1484.94, "total_tokens": 19190560} {"current_steps": 90935, "total_steps": 181800, "loss": 0.0048, "lr": 2.9325131001680706e-05, "epoch": 10.003850385038504, "percentage": 50.02, "elapsed_time": "3:35:24", "remaining_time": "3:35:14", "throughput": 1484.94, "total_tokens": 19191680} {"current_steps": 90940, "total_steps": 181800, "loss": 0.0866, "lr": 2.932276710487671e-05, "epoch": 10.004400440044005, "percentage": 50.02, "elapsed_time": "3:35:24", "remaining_time": "3:35:13", "throughput": 1484.95, "total_tokens": 19192768} {"current_steps": 90945, "total_steps": 181800, "loss": 0.0391, "lr": 2.932040316823183e-05, "epoch": 10.004950495049505, "percentage": 50.02, "elapsed_time": "3:35:25", "remaining_time": "3:35:12", "throughput": 1484.94, "total_tokens": 19193888} {"current_steps": 90950, "total_steps": 181800, "loss": 0.0774, "lr": 2.9318039191767873e-05, "epoch": 10.005500550055006, "percentage": 50.03, "elapsed_time": "3:35:26", "remaining_time": "3:35:12", "throughput": 1484.94, "total_tokens": 19194944} {"current_steps": 90955, "total_steps": 181800, "loss": 0.0334, "lr": 2.931567517550662e-05, "epoch": 10.006050605060507, "percentage": 50.03, "elapsed_time": "3:35:27", "remaining_time": "3:35:11", "throughput": 1484.94, "total_tokens": 19196000} {"current_steps": 90960, "total_steps": 181800, "loss": 0.0575, "lr": 2.9313311119469856e-05, "epoch": 10.006600660066006, "percentage": 50.03, "elapsed_time": "3:35:27", "remaining_time": "3:35:10", "throughput": 1484.94, "total_tokens": 19197024} {"current_steps": 90965, "total_steps": 181800, "loss": 0.1829, "lr": 2.931094702367938e-05, "epoch": 10.007150715071507, "percentage": 50.04, "elapsed_time": "3:35:28", "remaining_time": "3:35:10", "throughput": 1484.94, "total_tokens": 19198080} {"current_steps": 90970, "total_steps": 181800, "loss": 0.0604, "lr": 2.9308582888156973e-05, "epoch": 10.007700770077008, "percentage": 50.04, "elapsed_time": "3:35:29", "remaining_time": "3:35:09", "throughput": 1484.94, "total_tokens": 19199200} {"current_steps": 90975, "total_steps": 181800, "loss": 0.0529, "lr": 2.9306218712924416e-05, "epoch": 10.008250825082508, "percentage": 50.04, "elapsed_time": "3:35:29", "remaining_time": "3:35:08", "throughput": 1484.95, "total_tokens": 19200320} {"current_steps": 90980, "total_steps": 181800, "loss": 0.0369, "lr": 2.9303854498003514e-05, "epoch": 10.008800880088009, "percentage": 50.04, "elapsed_time": "3:35:30", "remaining_time": "3:35:07", "throughput": 1484.95, "total_tokens": 19201408} {"current_steps": 90985, "total_steps": 181800, "loss": 0.0073, "lr": 2.9301490243416052e-05, "epoch": 10.00935093509351, "percentage": 50.05, "elapsed_time": "3:35:31", "remaining_time": "3:35:07", "throughput": 1484.96, "total_tokens": 19202560} {"current_steps": 90990, "total_steps": 181800, "loss": 0.0087, "lr": 2.929912594918382e-05, "epoch": 10.009900990099009, "percentage": 50.05, "elapsed_time": "3:35:32", "remaining_time": "3:35:06", "throughput": 1484.97, "total_tokens": 19203648} {"current_steps": 90995, "total_steps": 181800, "loss": 0.0259, "lr": 2.9296761615328606e-05, "epoch": 10.01045104510451, "percentage": 50.05, "elapsed_time": "3:35:32", "remaining_time": "3:35:05", "throughput": 1484.97, "total_tokens": 19204704} {"current_steps": 91000, "total_steps": 181800, "loss": 0.028, "lr": 2.9294397241872196e-05, "epoch": 10.011001100110011, "percentage": 50.06, "elapsed_time": "3:35:33", "remaining_time": "3:35:04", "throughput": 1484.97, "total_tokens": 19205728} {"current_steps": 91005, "total_steps": 181800, "loss": 0.0086, "lr": 2.9292032828836387e-05, "epoch": 10.011551155115512, "percentage": 50.06, "elapsed_time": "3:35:34", "remaining_time": "3:35:04", "throughput": 1484.97, "total_tokens": 19206784} {"current_steps": 91010, "total_steps": 181800, "loss": 0.0088, "lr": 2.928966837624298e-05, "epoch": 10.012101210121012, "percentage": 50.06, "elapsed_time": "3:35:34", "remaining_time": "3:35:03", "throughput": 1484.97, "total_tokens": 19207808} {"current_steps": 91015, "total_steps": 181800, "loss": 0.0183, "lr": 2.9287303884113747e-05, "epoch": 10.012651265126513, "percentage": 50.06, "elapsed_time": "3:35:35", "remaining_time": "3:35:02", "throughput": 1484.98, "total_tokens": 19208864} {"current_steps": 91020, "total_steps": 181800, "loss": 0.0131, "lr": 2.9284939352470502e-05, "epoch": 10.013201320132014, "percentage": 50.07, "elapsed_time": "3:35:36", "remaining_time": "3:35:02", "throughput": 1484.98, "total_tokens": 19209920} {"current_steps": 91025, "total_steps": 181800, "loss": 0.0394, "lr": 2.928257478133502e-05, "epoch": 10.013751375137513, "percentage": 50.07, "elapsed_time": "3:35:36", "remaining_time": "3:35:01", "throughput": 1484.97, "total_tokens": 19210912} {"current_steps": 91030, "total_steps": 181800, "loss": 0.0521, "lr": 2.9280210170729105e-05, "epoch": 10.014301430143014, "percentage": 50.07, "elapsed_time": "3:35:37", "remaining_time": "3:35:00", "throughput": 1484.97, "total_tokens": 19211936} {"current_steps": 91035, "total_steps": 181800, "loss": 0.1158, "lr": 2.9277845520674547e-05, "epoch": 10.014851485148515, "percentage": 50.07, "elapsed_time": "3:35:38", "remaining_time": "3:34:59", "throughput": 1484.98, "total_tokens": 19213056} {"current_steps": 91040, "total_steps": 181800, "loss": 0.0055, "lr": 2.9275480831193136e-05, "epoch": 10.015401540154015, "percentage": 50.08, "elapsed_time": "3:35:38", "remaining_time": "3:34:59", "throughput": 1484.99, "total_tokens": 19214144} {"current_steps": 91045, "total_steps": 181800, "loss": 0.019, "lr": 2.927311610230667e-05, "epoch": 10.015951595159516, "percentage": 50.08, "elapsed_time": "3:35:39", "remaining_time": "3:34:58", "throughput": 1484.99, "total_tokens": 19215232} {"current_steps": 91050, "total_steps": 181800, "loss": 0.028, "lr": 2.9270751334036943e-05, "epoch": 10.016501650165017, "percentage": 50.08, "elapsed_time": "3:35:40", "remaining_time": "3:34:57", "throughput": 1484.99, "total_tokens": 19216288} {"current_steps": 91055, "total_steps": 181800, "loss": 0.0574, "lr": 2.9268386526405756e-05, "epoch": 10.017051705170518, "percentage": 50.09, "elapsed_time": "3:35:41", "remaining_time": "3:34:56", "throughput": 1485.0, "total_tokens": 19217440} {"current_steps": 91060, "total_steps": 181800, "loss": 0.0104, "lr": 2.9266021679434897e-05, "epoch": 10.017601760176017, "percentage": 50.09, "elapsed_time": "3:35:41", "remaining_time": "3:34:56", "throughput": 1485.0, "total_tokens": 19218464} {"current_steps": 91065, "total_steps": 181800, "loss": 0.0588, "lr": 2.926365679314616e-05, "epoch": 10.018151815181518, "percentage": 50.09, "elapsed_time": "3:35:42", "remaining_time": "3:34:55", "throughput": 1485.01, "total_tokens": 19219552} {"current_steps": 91070, "total_steps": 181800, "loss": 0.0081, "lr": 2.9261291867561346e-05, "epoch": 10.01870187018702, "percentage": 50.09, "elapsed_time": "3:35:43", "remaining_time": "3:34:54", "throughput": 1485.01, "total_tokens": 19220608} {"current_steps": 91075, "total_steps": 181800, "loss": 0.0178, "lr": 2.9258926902702243e-05, "epoch": 10.019251925192519, "percentage": 50.1, "elapsed_time": "3:35:43", "remaining_time": "3:34:54", "throughput": 1485.01, "total_tokens": 19221696} {"current_steps": 91080, "total_steps": 181800, "loss": 0.0477, "lr": 2.925656189859066e-05, "epoch": 10.01980198019802, "percentage": 50.1, "elapsed_time": "3:35:44", "remaining_time": "3:34:53", "throughput": 1485.02, "total_tokens": 19222816} {"current_steps": 91085, "total_steps": 181800, "loss": 0.0084, "lr": 2.9254196855248395e-05, "epoch": 10.020352035203521, "percentage": 50.1, "elapsed_time": "3:35:45", "remaining_time": "3:34:52", "throughput": 1485.03, "total_tokens": 19223936} {"current_steps": 91090, "total_steps": 181800, "loss": 0.0219, "lr": 2.925183177269723e-05, "epoch": 10.02090209020902, "percentage": 50.1, "elapsed_time": "3:35:45", "remaining_time": "3:34:51", "throughput": 1485.04, "total_tokens": 19225056} {"current_steps": 91095, "total_steps": 181800, "loss": 0.0091, "lr": 2.9249466650958974e-05, "epoch": 10.021452145214521, "percentage": 50.11, "elapsed_time": "3:35:46", "remaining_time": "3:34:51", "throughput": 1485.03, "total_tokens": 19226048} {"current_steps": 91100, "total_steps": 181800, "loss": 0.0105, "lr": 2.9247101490055424e-05, "epoch": 10.022002200220022, "percentage": 50.11, "elapsed_time": "3:35:47", "remaining_time": "3:34:50", "throughput": 1485.03, "total_tokens": 19227072} {"current_steps": 91105, "total_steps": 181800, "loss": 0.0435, "lr": 2.924473629000838e-05, "epoch": 10.022552255225522, "percentage": 50.11, "elapsed_time": "3:35:47", "remaining_time": "3:34:49", "throughput": 1485.04, "total_tokens": 19228128} {"current_steps": 91110, "total_steps": 181800, "loss": 0.0042, "lr": 2.9242371050839633e-05, "epoch": 10.023102310231023, "percentage": 50.12, "elapsed_time": "3:35:48", "remaining_time": "3:34:48", "throughput": 1485.04, "total_tokens": 19229216} {"current_steps": 91115, "total_steps": 181800, "loss": 0.0195, "lr": 2.9240005772570994e-05, "epoch": 10.023652365236524, "percentage": 50.12, "elapsed_time": "3:35:49", "remaining_time": "3:34:48", "throughput": 1485.05, "total_tokens": 19230304} {"current_steps": 91120, "total_steps": 181800, "loss": 0.0833, "lr": 2.9237640455224246e-05, "epoch": 10.024202420242025, "percentage": 50.12, "elapsed_time": "3:35:49", "remaining_time": "3:34:47", "throughput": 1485.05, "total_tokens": 19231424} {"current_steps": 91125, "total_steps": 181800, "loss": 0.0079, "lr": 2.923527509882121e-05, "epoch": 10.024752475247524, "percentage": 50.12, "elapsed_time": "3:35:50", "remaining_time": "3:34:46", "throughput": 1485.06, "total_tokens": 19232544} {"current_steps": 91130, "total_steps": 181800, "loss": 0.0059, "lr": 2.923290970338367e-05, "epoch": 10.025302530253025, "percentage": 50.13, "elapsed_time": "3:35:51", "remaining_time": "3:34:46", "throughput": 1485.06, "total_tokens": 19233536} {"current_steps": 91135, "total_steps": 181800, "loss": 0.0477, "lr": 2.9230544268933436e-05, "epoch": 10.025852585258527, "percentage": 50.13, "elapsed_time": "3:35:52", "remaining_time": "3:34:45", "throughput": 1485.06, "total_tokens": 19234592} {"current_steps": 91140, "total_steps": 181800, "loss": 0.0273, "lr": 2.92281787954923e-05, "epoch": 10.026402640264026, "percentage": 50.13, "elapsed_time": "3:35:52", "remaining_time": "3:34:44", "throughput": 1485.06, "total_tokens": 19235680} {"current_steps": 91145, "total_steps": 181800, "loss": 0.0397, "lr": 2.9225813283082076e-05, "epoch": 10.026952695269527, "percentage": 50.13, "elapsed_time": "3:35:53", "remaining_time": "3:34:43", "throughput": 1485.07, "total_tokens": 19236704} {"current_steps": 91150, "total_steps": 181800, "loss": 0.0152, "lr": 2.922344773172455e-05, "epoch": 10.027502750275028, "percentage": 50.14, "elapsed_time": "3:35:54", "remaining_time": "3:34:43", "throughput": 1485.06, "total_tokens": 19237728} {"current_steps": 91155, "total_steps": 181800, "loss": 0.014, "lr": 2.922108214144154e-05, "epoch": 10.028052805280527, "percentage": 50.14, "elapsed_time": "3:35:54", "remaining_time": "3:34:42", "throughput": 1485.07, "total_tokens": 19238816} {"current_steps": 91160, "total_steps": 181800, "loss": 0.054, "lr": 2.9218716512254836e-05, "epoch": 10.028602860286028, "percentage": 50.14, "elapsed_time": "3:35:55", "remaining_time": "3:34:41", "throughput": 1485.08, "total_tokens": 19239968} {"current_steps": 91165, "total_steps": 181800, "loss": 0.0047, "lr": 2.9216350844186253e-05, "epoch": 10.02915291529153, "percentage": 50.15, "elapsed_time": "3:35:56", "remaining_time": "3:34:40", "throughput": 1485.08, "total_tokens": 19241024} {"current_steps": 91170, "total_steps": 181800, "loss": 0.1065, "lr": 2.9213985137257583e-05, "epoch": 10.029702970297029, "percentage": 50.15, "elapsed_time": "3:35:56", "remaining_time": "3:34:40", "throughput": 1485.09, "total_tokens": 19242080} {"current_steps": 91175, "total_steps": 181800, "loss": 0.0057, "lr": 2.9211619391490634e-05, "epoch": 10.03025302530253, "percentage": 50.15, "elapsed_time": "3:35:57", "remaining_time": "3:34:39", "throughput": 1485.08, "total_tokens": 19243072} {"current_steps": 91180, "total_steps": 181800, "loss": 0.009, "lr": 2.920925360690721e-05, "epoch": 10.030803080308031, "percentage": 50.15, "elapsed_time": "3:35:58", "remaining_time": "3:34:38", "throughput": 1485.09, "total_tokens": 19244128} {"current_steps": 91185, "total_steps": 181800, "loss": 0.0427, "lr": 2.920688778352912e-05, "epoch": 10.031353135313532, "percentage": 50.16, "elapsed_time": "3:35:58", "remaining_time": "3:34:37", "throughput": 1485.09, "total_tokens": 19245152} {"current_steps": 91190, "total_steps": 181800, "loss": 0.0074, "lr": 2.920452192137816e-05, "epoch": 10.031903190319031, "percentage": 50.16, "elapsed_time": "3:35:59", "remaining_time": "3:34:37", "throughput": 1485.09, "total_tokens": 19246240} {"current_steps": 91195, "total_steps": 181800, "loss": 0.0056, "lr": 2.9202156020476133e-05, "epoch": 10.032453245324533, "percentage": 50.16, "elapsed_time": "3:36:00", "remaining_time": "3:34:36", "throughput": 1485.1, "total_tokens": 19247360} {"current_steps": 91200, "total_steps": 181800, "loss": 0.0868, "lr": 2.9199790080844864e-05, "epoch": 10.033003300330034, "percentage": 50.17, "elapsed_time": "3:36:01", "remaining_time": "3:34:35", "throughput": 1485.1, "total_tokens": 19248416} {"current_steps": 91205, "total_steps": 181800, "loss": 0.0581, "lr": 2.9197424102506133e-05, "epoch": 10.033553355335533, "percentage": 50.17, "elapsed_time": "3:36:01", "remaining_time": "3:34:35", "throughput": 1485.11, "total_tokens": 19249504} {"current_steps": 91210, "total_steps": 181800, "loss": 0.0076, "lr": 2.9195058085481765e-05, "epoch": 10.034103410341034, "percentage": 50.17, "elapsed_time": "3:36:02", "remaining_time": "3:34:34", "throughput": 1485.11, "total_tokens": 19250592} {"current_steps": 91215, "total_steps": 181800, "loss": 0.0506, "lr": 2.9192692029793554e-05, "epoch": 10.034653465346535, "percentage": 50.17, "elapsed_time": "3:36:03", "remaining_time": "3:34:33", "throughput": 1485.11, "total_tokens": 19251616} {"current_steps": 91220, "total_steps": 181800, "loss": 0.0256, "lr": 2.9190325935463315e-05, "epoch": 10.035203520352034, "percentage": 50.18, "elapsed_time": "3:36:03", "remaining_time": "3:34:32", "throughput": 1485.12, "total_tokens": 19252736} {"current_steps": 91225, "total_steps": 181800, "loss": 0.0036, "lr": 2.918795980251286e-05, "epoch": 10.035753575357536, "percentage": 50.18, "elapsed_time": "3:36:04", "remaining_time": "3:34:32", "throughput": 1485.12, "total_tokens": 19253792} {"current_steps": 91230, "total_steps": 181800, "loss": 0.0073, "lr": 2.918559363096398e-05, "epoch": 10.036303630363037, "percentage": 50.18, "elapsed_time": "3:36:05", "remaining_time": "3:34:31", "throughput": 1485.13, "total_tokens": 19254880} {"current_steps": 91235, "total_steps": 181800, "loss": 0.0063, "lr": 2.9183227420838493e-05, "epoch": 10.036853685368538, "percentage": 50.18, "elapsed_time": "3:36:05", "remaining_time": "3:34:30", "throughput": 1485.13, "total_tokens": 19256000} {"current_steps": 91240, "total_steps": 181800, "loss": 0.0545, "lr": 2.9180861172158207e-05, "epoch": 10.037403740374037, "percentage": 50.19, "elapsed_time": "3:36:06", "remaining_time": "3:34:29", "throughput": 1485.14, "total_tokens": 19257088} {"current_steps": 91245, "total_steps": 181800, "loss": 0.0761, "lr": 2.9178494884944928e-05, "epoch": 10.037953795379538, "percentage": 50.19, "elapsed_time": "3:36:07", "remaining_time": "3:34:29", "throughput": 1485.14, "total_tokens": 19258112} {"current_steps": 91250, "total_steps": 181800, "loss": 0.0019, "lr": 2.9176128559220473e-05, "epoch": 10.03850385038504, "percentage": 50.19, "elapsed_time": "3:36:07", "remaining_time": "3:34:28", "throughput": 1485.15, "total_tokens": 19259232} {"current_steps": 91255, "total_steps": 181800, "loss": 0.0192, "lr": 2.9173762195006644e-05, "epoch": 10.039053905390539, "percentage": 50.2, "elapsed_time": "3:36:08", "remaining_time": "3:34:27", "throughput": 1485.15, "total_tokens": 19260320} {"current_steps": 91260, "total_steps": 181800, "loss": 0.0093, "lr": 2.9171395792325247e-05, "epoch": 10.03960396039604, "percentage": 50.2, "elapsed_time": "3:36:09", "remaining_time": "3:34:26", "throughput": 1485.15, "total_tokens": 19261376} {"current_steps": 91265, "total_steps": 181800, "loss": 0.0301, "lr": 2.9169029351198096e-05, "epoch": 10.04015401540154, "percentage": 50.2, "elapsed_time": "3:36:09", "remaining_time": "3:34:26", "throughput": 1485.16, "total_tokens": 19262432} {"current_steps": 91270, "total_steps": 181800, "loss": 0.0041, "lr": 2.9166662871647006e-05, "epoch": 10.04070407040704, "percentage": 50.2, "elapsed_time": "3:36:10", "remaining_time": "3:34:25", "throughput": 1485.16, "total_tokens": 19263488} {"current_steps": 91275, "total_steps": 181800, "loss": 0.0223, "lr": 2.9164296353693786e-05, "epoch": 10.041254125412541, "percentage": 50.21, "elapsed_time": "3:36:11", "remaining_time": "3:34:24", "throughput": 1485.16, "total_tokens": 19264576} {"current_steps": 91280, "total_steps": 181800, "loss": 0.0209, "lr": 2.9161929797360234e-05, "epoch": 10.041804180418042, "percentage": 50.21, "elapsed_time": "3:36:12", "remaining_time": "3:34:24", "throughput": 1485.16, "total_tokens": 19265600} {"current_steps": 91285, "total_steps": 181800, "loss": 0.0096, "lr": 2.9159563202668184e-05, "epoch": 10.042354235423542, "percentage": 50.21, "elapsed_time": "3:36:12", "remaining_time": "3:34:23", "throughput": 1485.16, "total_tokens": 19266592} {"current_steps": 91290, "total_steps": 181800, "loss": 0.004, "lr": 2.9157196569639427e-05, "epoch": 10.042904290429043, "percentage": 50.21, "elapsed_time": "3:36:13", "remaining_time": "3:34:22", "throughput": 1485.17, "total_tokens": 19267680} {"current_steps": 91295, "total_steps": 181800, "loss": 0.0043, "lr": 2.9154829898295788e-05, "epoch": 10.043454345434544, "percentage": 50.22, "elapsed_time": "3:36:14", "remaining_time": "3:34:21", "throughput": 1485.17, "total_tokens": 19268736} {"current_steps": 91300, "total_steps": 181800, "loss": 0.0958, "lr": 2.915246318865908e-05, "epoch": 10.044004400440045, "percentage": 50.22, "elapsed_time": "3:36:14", "remaining_time": "3:34:21", "throughput": 1485.17, "total_tokens": 19269760} {"current_steps": 91305, "total_steps": 181800, "loss": 0.087, "lr": 2.9150096440751107e-05, "epoch": 10.044554455445544, "percentage": 50.22, "elapsed_time": "3:36:15", "remaining_time": "3:34:20", "throughput": 1485.18, "total_tokens": 19270880} {"current_steps": 91310, "total_steps": 181800, "loss": 0.0409, "lr": 2.914772965459368e-05, "epoch": 10.045104510451045, "percentage": 50.23, "elapsed_time": "3:36:16", "remaining_time": "3:34:19", "throughput": 1485.18, "total_tokens": 19272000} {"current_steps": 91315, "total_steps": 181800, "loss": 0.0292, "lr": 2.9145362830208623e-05, "epoch": 10.045654565456546, "percentage": 50.23, "elapsed_time": "3:36:16", "remaining_time": "3:34:18", "throughput": 1485.19, "total_tokens": 19273056} {"current_steps": 91320, "total_steps": 181800, "loss": 0.0025, "lr": 2.914299596761775e-05, "epoch": 10.046204620462046, "percentage": 50.23, "elapsed_time": "3:36:17", "remaining_time": "3:34:18", "throughput": 1485.19, "total_tokens": 19274080} {"current_steps": 91325, "total_steps": 181800, "loss": 0.0104, "lr": 2.9140629066842873e-05, "epoch": 10.046754675467547, "percentage": 50.23, "elapsed_time": "3:36:18", "remaining_time": "3:34:17", "throughput": 1485.19, "total_tokens": 19275104} {"current_steps": 91330, "total_steps": 181800, "loss": 0.0628, "lr": 2.91382621279058e-05, "epoch": 10.047304730473048, "percentage": 50.24, "elapsed_time": "3:36:18", "remaining_time": "3:34:16", "throughput": 1485.19, "total_tokens": 19276224} {"current_steps": 91335, "total_steps": 181800, "loss": 0.0808, "lr": 2.913589515082835e-05, "epoch": 10.047854785478547, "percentage": 50.24, "elapsed_time": "3:36:19", "remaining_time": "3:34:15", "throughput": 1485.19, "total_tokens": 19277280} {"current_steps": 91340, "total_steps": 181800, "loss": 0.0028, "lr": 2.9133528135632338e-05, "epoch": 10.048404840484048, "percentage": 50.24, "elapsed_time": "3:36:20", "remaining_time": "3:34:15", "throughput": 1485.19, "total_tokens": 19278272} {"current_steps": 91345, "total_steps": 181800, "loss": 0.0486, "lr": 2.9131161082339585e-05, "epoch": 10.04895489548955, "percentage": 50.24, "elapsed_time": "3:36:21", "remaining_time": "3:34:14", "throughput": 1485.2, "total_tokens": 19279392} {"current_steps": 91350, "total_steps": 181800, "loss": 0.0246, "lr": 2.9128793990971904e-05, "epoch": 10.049504950495049, "percentage": 50.25, "elapsed_time": "3:36:21", "remaining_time": "3:34:13", "throughput": 1485.21, "total_tokens": 19280512} {"current_steps": 91355, "total_steps": 181800, "loss": 0.0284, "lr": 2.9126426861551103e-05, "epoch": 10.05005500550055, "percentage": 50.25, "elapsed_time": "3:36:22", "remaining_time": "3:34:13", "throughput": 1485.21, "total_tokens": 19281568} {"current_steps": 91360, "total_steps": 181800, "loss": 0.0481, "lr": 2.912405969409901e-05, "epoch": 10.05060506050605, "percentage": 50.25, "elapsed_time": "3:36:23", "remaining_time": "3:34:12", "throughput": 1485.22, "total_tokens": 19282688} {"current_steps": 91365, "total_steps": 181800, "loss": 0.0205, "lr": 2.912169248863744e-05, "epoch": 10.051155115511552, "percentage": 50.26, "elapsed_time": "3:36:23", "remaining_time": "3:34:11", "throughput": 1485.22, "total_tokens": 19283712} {"current_steps": 91370, "total_steps": 181800, "loss": 0.0449, "lr": 2.9119325245188207e-05, "epoch": 10.051705170517051, "percentage": 50.26, "elapsed_time": "3:36:24", "remaining_time": "3:34:10", "throughput": 1485.22, "total_tokens": 19284768} {"current_steps": 91375, "total_steps": 181800, "loss": 0.0073, "lr": 2.9116957963773127e-05, "epoch": 10.052255225522552, "percentage": 50.26, "elapsed_time": "3:36:25", "remaining_time": "3:34:10", "throughput": 1485.23, "total_tokens": 19285888} {"current_steps": 91380, "total_steps": 181800, "loss": 0.116, "lr": 2.911459064441402e-05, "epoch": 10.052805280528053, "percentage": 50.26, "elapsed_time": "3:36:25", "remaining_time": "3:34:09", "throughput": 1485.23, "total_tokens": 19286944} {"current_steps": 91385, "total_steps": 181800, "loss": 0.015, "lr": 2.9112223287132706e-05, "epoch": 10.053355335533553, "percentage": 50.27, "elapsed_time": "3:36:26", "remaining_time": "3:34:08", "throughput": 1485.24, "total_tokens": 19288032} {"current_steps": 91390, "total_steps": 181800, "loss": 0.0621, "lr": 2.910985589195101e-05, "epoch": 10.053905390539054, "percentage": 50.27, "elapsed_time": "3:36:27", "remaining_time": "3:34:07", "throughput": 1485.24, "total_tokens": 19289088} {"current_steps": 91395, "total_steps": 181800, "loss": 0.0022, "lr": 2.9107488458890737e-05, "epoch": 10.054455445544555, "percentage": 50.27, "elapsed_time": "3:36:27", "remaining_time": "3:34:07", "throughput": 1485.24, "total_tokens": 19290176} {"current_steps": 91400, "total_steps": 181800, "loss": 0.0438, "lr": 2.9105120987973715e-05, "epoch": 10.055005500550054, "percentage": 50.28, "elapsed_time": "3:36:28", "remaining_time": "3:34:06", "throughput": 1485.25, "total_tokens": 19291296} {"current_steps": 91405, "total_steps": 181800, "loss": 0.0083, "lr": 2.9102753479221768e-05, "epoch": 10.055555555555555, "percentage": 50.28, "elapsed_time": "3:36:29", "remaining_time": "3:34:05", "throughput": 1485.24, "total_tokens": 19292256} {"current_steps": 91410, "total_steps": 181800, "loss": 0.0111, "lr": 2.9100385932656698e-05, "epoch": 10.056105610561056, "percentage": 50.28, "elapsed_time": "3:36:29", "remaining_time": "3:34:05", "throughput": 1485.24, "total_tokens": 19293280} {"current_steps": 91415, "total_steps": 181800, "loss": 0.0134, "lr": 2.9098018348300355e-05, "epoch": 10.056655665566556, "percentage": 50.28, "elapsed_time": "3:36:30", "remaining_time": "3:34:04", "throughput": 1485.25, "total_tokens": 19294368} {"current_steps": 91420, "total_steps": 181800, "loss": 0.0022, "lr": 2.9095650726174532e-05, "epoch": 10.057205720572057, "percentage": 50.29, "elapsed_time": "3:36:31", "remaining_time": "3:34:03", "throughput": 1485.25, "total_tokens": 19295392} {"current_steps": 91425, "total_steps": 181800, "loss": 0.0251, "lr": 2.9093283066301065e-05, "epoch": 10.057755775577558, "percentage": 50.29, "elapsed_time": "3:36:32", "remaining_time": "3:34:02", "throughput": 1485.25, "total_tokens": 19296384} {"current_steps": 91430, "total_steps": 181800, "loss": 0.0022, "lr": 2.909091536870177e-05, "epoch": 10.058305830583059, "percentage": 50.29, "elapsed_time": "3:36:32", "remaining_time": "3:34:02", "throughput": 1485.24, "total_tokens": 19297376} {"current_steps": 91435, "total_steps": 181800, "loss": 0.0081, "lr": 2.908854763339847e-05, "epoch": 10.058855885588558, "percentage": 50.29, "elapsed_time": "3:36:33", "remaining_time": "3:34:01", "throughput": 1485.24, "total_tokens": 19298400} {"current_steps": 91440, "total_steps": 181800, "loss": 0.0124, "lr": 2.9086179860413e-05, "epoch": 10.05940594059406, "percentage": 50.3, "elapsed_time": "3:36:34", "remaining_time": "3:34:00", "throughput": 1485.25, "total_tokens": 19299488} {"current_steps": 91445, "total_steps": 181800, "loss": 0.1271, "lr": 2.9083812049767157e-05, "epoch": 10.05995599559956, "percentage": 50.3, "elapsed_time": "3:36:34", "remaining_time": "3:33:59", "throughput": 1485.25, "total_tokens": 19300512} {"current_steps": 91450, "total_steps": 181800, "loss": 0.0265, "lr": 2.9081444201482788e-05, "epoch": 10.06050605060506, "percentage": 50.3, "elapsed_time": "3:36:35", "remaining_time": "3:33:59", "throughput": 1485.25, "total_tokens": 19301568} {"current_steps": 91455, "total_steps": 181800, "loss": 0.0017, "lr": 2.9079076315581693e-05, "epoch": 10.061056105610561, "percentage": 50.31, "elapsed_time": "3:36:36", "remaining_time": "3:33:58", "throughput": 1485.25, "total_tokens": 19302624} {"current_steps": 91460, "total_steps": 181800, "loss": 0.0238, "lr": 2.907670839208572e-05, "epoch": 10.061606160616062, "percentage": 50.31, "elapsed_time": "3:36:36", "remaining_time": "3:33:57", "throughput": 1485.26, "total_tokens": 19303680} {"current_steps": 91465, "total_steps": 181800, "loss": 0.0483, "lr": 2.907434043101668e-05, "epoch": 10.062156215621561, "percentage": 50.31, "elapsed_time": "3:36:37", "remaining_time": "3:33:56", "throughput": 1485.26, "total_tokens": 19304736} {"current_steps": 91470, "total_steps": 181800, "loss": 0.0037, "lr": 2.90719724323964e-05, "epoch": 10.062706270627062, "percentage": 50.31, "elapsed_time": "3:36:38", "remaining_time": "3:33:56", "throughput": 1485.26, "total_tokens": 19305824} {"current_steps": 91475, "total_steps": 181800, "loss": 0.0049, "lr": 2.9069604396246703e-05, "epoch": 10.063256325632564, "percentage": 50.32, "elapsed_time": "3:36:38", "remaining_time": "3:33:55", "throughput": 1485.27, "total_tokens": 19306912} {"current_steps": 91480, "total_steps": 181800, "loss": 0.0269, "lr": 2.9067236322589415e-05, "epoch": 10.063806380638065, "percentage": 50.32, "elapsed_time": "3:36:39", "remaining_time": "3:33:54", "throughput": 1485.28, "total_tokens": 19308032} {"current_steps": 91485, "total_steps": 181800, "loss": 0.0579, "lr": 2.9064868211446362e-05, "epoch": 10.064356435643564, "percentage": 50.32, "elapsed_time": "3:36:40", "remaining_time": "3:33:54", "throughput": 1485.28, "total_tokens": 19309088} {"current_steps": 91490, "total_steps": 181800, "loss": 0.0206, "lr": 2.906250006283937e-05, "epoch": 10.064906490649065, "percentage": 50.32, "elapsed_time": "3:36:41", "remaining_time": "3:33:53", "throughput": 1485.28, "total_tokens": 19310112} {"current_steps": 91495, "total_steps": 181800, "loss": 0.0123, "lr": 2.906013187679026e-05, "epoch": 10.065456545654566, "percentage": 50.33, "elapsed_time": "3:36:41", "remaining_time": "3:33:52", "throughput": 1485.28, "total_tokens": 19311136} {"current_steps": 91500, "total_steps": 181800, "loss": 0.0133, "lr": 2.9057763653320863e-05, "epoch": 10.066006600660065, "percentage": 50.33, "elapsed_time": "3:36:42", "remaining_time": "3:33:51", "throughput": 1485.28, "total_tokens": 19312192} {"current_steps": 91505, "total_steps": 181800, "loss": 0.0016, "lr": 2.905539539245301e-05, "epoch": 10.066556655665567, "percentage": 50.33, "elapsed_time": "3:36:43", "remaining_time": "3:33:51", "throughput": 1485.28, "total_tokens": 19313184} {"current_steps": 91510, "total_steps": 181800, "loss": 0.0073, "lr": 2.9053027094208524e-05, "epoch": 10.067106710671068, "percentage": 50.34, "elapsed_time": "3:36:43", "remaining_time": "3:33:50", "throughput": 1485.27, "total_tokens": 19314144} {"current_steps": 91515, "total_steps": 181800, "loss": 0.0237, "lr": 2.9050658758609228e-05, "epoch": 10.067656765676567, "percentage": 50.34, "elapsed_time": "3:36:44", "remaining_time": "3:33:49", "throughput": 1485.27, "total_tokens": 19315168} {"current_steps": 91520, "total_steps": 181800, "loss": 0.0233, "lr": 2.9048290385676958e-05, "epoch": 10.068206820682068, "percentage": 50.34, "elapsed_time": "3:36:45", "remaining_time": "3:33:48", "throughput": 1485.28, "total_tokens": 19316256} {"current_steps": 91525, "total_steps": 181800, "loss": 0.0143, "lr": 2.9045921975433533e-05, "epoch": 10.06875687568757, "percentage": 50.34, "elapsed_time": "3:36:45", "remaining_time": "3:33:48", "throughput": 1485.28, "total_tokens": 19317312} {"current_steps": 91530, "total_steps": 181800, "loss": 0.0708, "lr": 2.9043553527900785e-05, "epoch": 10.069306930693068, "percentage": 50.35, "elapsed_time": "3:36:46", "remaining_time": "3:33:47", "throughput": 1485.28, "total_tokens": 19318336} {"current_steps": 91535, "total_steps": 181800, "loss": 0.0412, "lr": 2.9041185043100555e-05, "epoch": 10.06985698569857, "percentage": 50.35, "elapsed_time": "3:36:47", "remaining_time": "3:33:46", "throughput": 1485.28, "total_tokens": 19319392} {"current_steps": 91540, "total_steps": 181800, "loss": 0.039, "lr": 2.9038816521054653e-05, "epoch": 10.07040704070407, "percentage": 50.35, "elapsed_time": "3:36:47", "remaining_time": "3:33:46", "throughput": 1485.29, "total_tokens": 19320480} {"current_steps": 91545, "total_steps": 181800, "loss": 0.0716, "lr": 2.903644796178492e-05, "epoch": 10.070957095709572, "percentage": 50.35, "elapsed_time": "3:36:48", "remaining_time": "3:33:45", "throughput": 1485.29, "total_tokens": 19321568} {"current_steps": 91550, "total_steps": 181800, "loss": 0.0056, "lr": 2.9034079365313184e-05, "epoch": 10.071507150715071, "percentage": 50.36, "elapsed_time": "3:36:49", "remaining_time": "3:33:44", "throughput": 1485.3, "total_tokens": 19322688} {"current_steps": 91555, "total_steps": 181800, "loss": 0.0022, "lr": 2.9031710731661265e-05, "epoch": 10.072057205720572, "percentage": 50.36, "elapsed_time": "3:36:49", "remaining_time": "3:33:43", "throughput": 1485.31, "total_tokens": 19323840} {"current_steps": 91560, "total_steps": 181800, "loss": 0.0983, "lr": 2.9029342060851018e-05, "epoch": 10.072607260726073, "percentage": 50.36, "elapsed_time": "3:36:50", "remaining_time": "3:33:43", "throughput": 1485.32, "total_tokens": 19324992} {"current_steps": 91565, "total_steps": 181800, "loss": 0.0276, "lr": 2.902697335290425e-05, "epoch": 10.073157315731573, "percentage": 50.37, "elapsed_time": "3:36:51", "remaining_time": "3:33:42", "throughput": 1485.31, "total_tokens": 19325952} {"current_steps": 91570, "total_steps": 181800, "loss": 0.028, "lr": 2.9024604607842797e-05, "epoch": 10.073707370737074, "percentage": 50.37, "elapsed_time": "3:36:52", "remaining_time": "3:33:41", "throughput": 1485.32, "total_tokens": 19327008} {"current_steps": 91575, "total_steps": 181800, "loss": 0.0056, "lr": 2.9022235825688504e-05, "epoch": 10.074257425742575, "percentage": 50.37, "elapsed_time": "3:36:52", "remaining_time": "3:33:40", "throughput": 1485.32, "total_tokens": 19328096} {"current_steps": 91580, "total_steps": 181800, "loss": 0.0109, "lr": 2.9019867006463196e-05, "epoch": 10.074807480748074, "percentage": 50.37, "elapsed_time": "3:36:53", "remaining_time": "3:33:40", "throughput": 1485.33, "total_tokens": 19329184} {"current_steps": 91585, "total_steps": 181800, "loss": 0.0479, "lr": 2.9017498150188688e-05, "epoch": 10.075357535753575, "percentage": 50.38, "elapsed_time": "3:36:54", "remaining_time": "3:33:39", "throughput": 1485.34, "total_tokens": 19330336} {"current_steps": 91590, "total_steps": 181800, "loss": 0.0255, "lr": 2.9015129256886836e-05, "epoch": 10.075907590759076, "percentage": 50.38, "elapsed_time": "3:36:54", "remaining_time": "3:33:38", "throughput": 1485.34, "total_tokens": 19331456} {"current_steps": 91595, "total_steps": 181800, "loss": 0.0304, "lr": 2.9012760326579463e-05, "epoch": 10.076457645764576, "percentage": 50.38, "elapsed_time": "3:36:55", "remaining_time": "3:33:37", "throughput": 1485.35, "total_tokens": 19332512} {"current_steps": 91600, "total_steps": 181800, "loss": 0.0022, "lr": 2.9010391359288403e-05, "epoch": 10.077007700770077, "percentage": 50.39, "elapsed_time": "3:36:56", "remaining_time": "3:33:37", "throughput": 1485.35, "total_tokens": 19333536} {"current_steps": 91605, "total_steps": 181800, "loss": 0.0057, "lr": 2.9008022355035497e-05, "epoch": 10.077557755775578, "percentage": 50.39, "elapsed_time": "3:36:56", "remaining_time": "3:33:36", "throughput": 1485.35, "total_tokens": 19334560} {"current_steps": 91610, "total_steps": 181800, "loss": 0.2684, "lr": 2.9005653313842567e-05, "epoch": 10.078107810781079, "percentage": 50.39, "elapsed_time": "3:36:57", "remaining_time": "3:33:35", "throughput": 1485.35, "total_tokens": 19335648} {"current_steps": 91615, "total_steps": 181800, "loss": 0.068, "lr": 2.9003284235731448e-05, "epoch": 10.078657865786578, "percentage": 50.39, "elapsed_time": "3:36:58", "remaining_time": "3:33:35", "throughput": 1485.36, "total_tokens": 19336736} {"current_steps": 91620, "total_steps": 181800, "loss": 0.0298, "lr": 2.900091512072398e-05, "epoch": 10.07920792079208, "percentage": 50.4, "elapsed_time": "3:36:58", "remaining_time": "3:33:34", "throughput": 1485.36, "total_tokens": 19337792} {"current_steps": 91625, "total_steps": 181800, "loss": 0.0219, "lr": 2.8998545968842004e-05, "epoch": 10.07975797579758, "percentage": 50.4, "elapsed_time": "3:36:59", "remaining_time": "3:33:33", "throughput": 1485.36, "total_tokens": 19338816} {"current_steps": 91630, "total_steps": 181800, "loss": 0.0248, "lr": 2.8996176780107342e-05, "epoch": 10.08030803080308, "percentage": 50.4, "elapsed_time": "3:37:00", "remaining_time": "3:33:32", "throughput": 1485.36, "total_tokens": 19339872} {"current_steps": 91635, "total_steps": 181800, "loss": 0.1046, "lr": 2.899380755454184e-05, "epoch": 10.08085808580858, "percentage": 50.4, "elapsed_time": "3:37:01", "remaining_time": "3:33:32", "throughput": 1485.37, "total_tokens": 19340960} {"current_steps": 91640, "total_steps": 181800, "loss": 0.0015, "lr": 2.8991438292167334e-05, "epoch": 10.081408140814082, "percentage": 50.41, "elapsed_time": "3:37:01", "remaining_time": "3:33:31", "throughput": 1485.37, "total_tokens": 19342080} {"current_steps": 91645, "total_steps": 181800, "loss": 0.002, "lr": 2.8989068993005648e-05, "epoch": 10.081958195819581, "percentage": 50.41, "elapsed_time": "3:37:02", "remaining_time": "3:33:30", "throughput": 1485.38, "total_tokens": 19343168} {"current_steps": 91650, "total_steps": 181800, "loss": 0.0029, "lr": 2.898669965707863e-05, "epoch": 10.082508250825082, "percentage": 50.41, "elapsed_time": "3:37:03", "remaining_time": "3:33:29", "throughput": 1485.38, "total_tokens": 19344224} {"current_steps": 91655, "total_steps": 181800, "loss": 0.1502, "lr": 2.8984330284408112e-05, "epoch": 10.083058305830583, "percentage": 50.42, "elapsed_time": "3:37:03", "remaining_time": "3:33:29", "throughput": 1485.38, "total_tokens": 19345248} {"current_steps": 91660, "total_steps": 181800, "loss": 0.0014, "lr": 2.898196087501594e-05, "epoch": 10.083608360836084, "percentage": 50.42, "elapsed_time": "3:37:04", "remaining_time": "3:33:28", "throughput": 1485.38, "total_tokens": 19346240} {"current_steps": 91665, "total_steps": 181800, "loss": 0.0506, "lr": 2.897959142892394e-05, "epoch": 10.084158415841584, "percentage": 50.42, "elapsed_time": "3:37:05", "remaining_time": "3:33:27", "throughput": 1485.38, "total_tokens": 19347264} {"current_steps": 91670, "total_steps": 181800, "loss": 0.0589, "lr": 2.8977221946153954e-05, "epoch": 10.084708470847085, "percentage": 50.42, "elapsed_time": "3:37:05", "remaining_time": "3:33:27", "throughput": 1485.38, "total_tokens": 19348288} {"current_steps": 91675, "total_steps": 181800, "loss": 0.0105, "lr": 2.8974852426727834e-05, "epoch": 10.085258525852586, "percentage": 50.43, "elapsed_time": "3:37:06", "remaining_time": "3:33:26", "throughput": 1485.38, "total_tokens": 19349376} {"current_steps": 91680, "total_steps": 181800, "loss": 0.0191, "lr": 2.8972482870667394e-05, "epoch": 10.085808580858085, "percentage": 50.43, "elapsed_time": "3:37:07", "remaining_time": "3:33:25", "throughput": 1485.38, "total_tokens": 19350368} {"current_steps": 91685, "total_steps": 181800, "loss": 0.0528, "lr": 2.8970113277994487e-05, "epoch": 10.086358635863586, "percentage": 50.43, "elapsed_time": "3:37:07", "remaining_time": "3:33:24", "throughput": 1485.38, "total_tokens": 19351424} {"current_steps": 91690, "total_steps": 181800, "loss": 0.1579, "lr": 2.8967743648730955e-05, "epoch": 10.086908690869087, "percentage": 50.43, "elapsed_time": "3:37:08", "remaining_time": "3:33:24", "throughput": 1485.39, "total_tokens": 19352480} {"current_steps": 91695, "total_steps": 181800, "loss": 0.0152, "lr": 2.896537398289863e-05, "epoch": 10.087458745874587, "percentage": 50.44, "elapsed_time": "3:37:09", "remaining_time": "3:33:23", "throughput": 1485.38, "total_tokens": 19353472} {"current_steps": 91700, "total_steps": 181800, "loss": 0.0568, "lr": 2.8963004280519363e-05, "epoch": 10.088008800880088, "percentage": 50.44, "elapsed_time": "3:37:09", "remaining_time": "3:33:22", "throughput": 1485.39, "total_tokens": 19354528} {"current_steps": 91705, "total_steps": 181800, "loss": 0.022, "lr": 2.8960634541614982e-05, "epoch": 10.088558855885589, "percentage": 50.44, "elapsed_time": "3:37:10", "remaining_time": "3:33:21", "throughput": 1485.39, "total_tokens": 19355584} {"current_steps": 91710, "total_steps": 181800, "loss": 0.0075, "lr": 2.8958264766207334e-05, "epoch": 10.089108910891088, "percentage": 50.45, "elapsed_time": "3:37:11", "remaining_time": "3:33:21", "throughput": 1485.39, "total_tokens": 19356608} {"current_steps": 91715, "total_steps": 181800, "loss": 0.0043, "lr": 2.895589495431825e-05, "epoch": 10.08965896589659, "percentage": 50.45, "elapsed_time": "3:37:12", "remaining_time": "3:33:20", "throughput": 1485.39, "total_tokens": 19357664} {"current_steps": 91720, "total_steps": 181800, "loss": 0.0063, "lr": 2.8953525105969593e-05, "epoch": 10.09020902090209, "percentage": 50.45, "elapsed_time": "3:37:12", "remaining_time": "3:33:19", "throughput": 1485.4, "total_tokens": 19358752} {"current_steps": 91725, "total_steps": 181800, "loss": 0.1315, "lr": 2.895115522118319e-05, "epoch": 10.090759075907592, "percentage": 50.45, "elapsed_time": "3:37:13", "remaining_time": "3:33:18", "throughput": 1485.4, "total_tokens": 19359776} {"current_steps": 91730, "total_steps": 181800, "loss": 0.0157, "lr": 2.894878529998088e-05, "epoch": 10.091309130913091, "percentage": 50.46, "elapsed_time": "3:37:14", "remaining_time": "3:33:18", "throughput": 1485.4, "total_tokens": 19360800} {"current_steps": 91735, "total_steps": 181800, "loss": 0.0147, "lr": 2.8946415342384513e-05, "epoch": 10.091859185918592, "percentage": 50.46, "elapsed_time": "3:37:14", "remaining_time": "3:33:17", "throughput": 1485.4, "total_tokens": 19361856} {"current_steps": 91740, "total_steps": 181800, "loss": 0.0389, "lr": 2.8944045348415933e-05, "epoch": 10.092409240924093, "percentage": 50.46, "elapsed_time": "3:37:15", "remaining_time": "3:33:16", "throughput": 1485.4, "total_tokens": 19362912} {"current_steps": 91745, "total_steps": 181800, "loss": 0.0136, "lr": 2.894167531809697e-05, "epoch": 10.092959295929592, "percentage": 50.46, "elapsed_time": "3:37:16", "remaining_time": "3:33:16", "throughput": 1485.41, "total_tokens": 19364000} {"current_steps": 91750, "total_steps": 181800, "loss": 0.0026, "lr": 2.893930525144949e-05, "epoch": 10.093509350935093, "percentage": 50.47, "elapsed_time": "3:37:16", "remaining_time": "3:33:15", "throughput": 1485.41, "total_tokens": 19365152} {"current_steps": 91755, "total_steps": 181800, "loss": 0.0946, "lr": 2.893693514849532e-05, "epoch": 10.094059405940595, "percentage": 50.47, "elapsed_time": "3:37:17", "remaining_time": "3:33:14", "throughput": 1485.42, "total_tokens": 19366208} {"current_steps": 91760, "total_steps": 181800, "loss": 0.0049, "lr": 2.8934565009256298e-05, "epoch": 10.094609460946094, "percentage": 50.47, "elapsed_time": "3:37:18", "remaining_time": "3:33:13", "throughput": 1485.42, "total_tokens": 19367264} {"current_steps": 91765, "total_steps": 181800, "loss": 0.0032, "lr": 2.8932194833754284e-05, "epoch": 10.095159515951595, "percentage": 50.48, "elapsed_time": "3:37:18", "remaining_time": "3:33:13", "throughput": 1485.42, "total_tokens": 19368256} {"current_steps": 91770, "total_steps": 181800, "loss": 0.0073, "lr": 2.892982462201112e-05, "epoch": 10.095709570957096, "percentage": 50.48, "elapsed_time": "3:37:19", "remaining_time": "3:33:12", "throughput": 1485.42, "total_tokens": 19369344} {"current_steps": 91775, "total_steps": 181800, "loss": 0.0014, "lr": 2.8927454374048646e-05, "epoch": 10.096259625962595, "percentage": 50.48, "elapsed_time": "3:37:20", "remaining_time": "3:33:11", "throughput": 1485.42, "total_tokens": 19370400} {"current_steps": 91780, "total_steps": 181800, "loss": 0.0262, "lr": 2.8925084089888717e-05, "epoch": 10.096809680968097, "percentage": 50.48, "elapsed_time": "3:37:20", "remaining_time": "3:33:10", "throughput": 1485.43, "total_tokens": 19371456} {"current_steps": 91785, "total_steps": 181800, "loss": 0.0097, "lr": 2.8922713769553162e-05, "epoch": 10.097359735973598, "percentage": 50.49, "elapsed_time": "3:37:21", "remaining_time": "3:33:10", "throughput": 1485.43, "total_tokens": 19372544} {"current_steps": 91790, "total_steps": 181800, "loss": 0.0111, "lr": 2.8920343413063832e-05, "epoch": 10.097909790979099, "percentage": 50.49, "elapsed_time": "3:37:22", "remaining_time": "3:33:09", "throughput": 1485.43, "total_tokens": 19373600} {"current_steps": 91795, "total_steps": 181800, "loss": 0.0242, "lr": 2.8917973020442597e-05, "epoch": 10.098459845984598, "percentage": 50.49, "elapsed_time": "3:37:23", "remaining_time": "3:33:08", "throughput": 1485.44, "total_tokens": 19374688} {"current_steps": 91800, "total_steps": 181800, "loss": 0.119, "lr": 2.8915602591711267e-05, "epoch": 10.099009900990099, "percentage": 50.5, "elapsed_time": "3:37:23", "remaining_time": "3:33:07", "throughput": 1485.44, "total_tokens": 19375712} {"current_steps": 91805, "total_steps": 181800, "loss": 0.0331, "lr": 2.891323212689171e-05, "epoch": 10.0995599559956, "percentage": 50.5, "elapsed_time": "3:37:24", "remaining_time": "3:33:07", "throughput": 1485.44, "total_tokens": 19376768} {"current_steps": 91810, "total_steps": 181800, "loss": 0.0043, "lr": 2.8910861626005776e-05, "epoch": 10.1001100110011, "percentage": 50.5, "elapsed_time": "3:37:25", "remaining_time": "3:33:06", "throughput": 1485.45, "total_tokens": 19377856} {"current_steps": 91815, "total_steps": 181800, "loss": 0.0034, "lr": 2.89084910890753e-05, "epoch": 10.1006600660066, "percentage": 50.5, "elapsed_time": "3:37:25", "remaining_time": "3:33:05", "throughput": 1485.45, "total_tokens": 19378944} {"current_steps": 91820, "total_steps": 181800, "loss": 0.0096, "lr": 2.8906120516122144e-05, "epoch": 10.101210121012102, "percentage": 50.51, "elapsed_time": "3:37:26", "remaining_time": "3:33:05", "throughput": 1485.45, "total_tokens": 19379968} {"current_steps": 91825, "total_steps": 181800, "loss": 0.0242, "lr": 2.890374990716815e-05, "epoch": 10.101760176017601, "percentage": 50.51, "elapsed_time": "3:37:27", "remaining_time": "3:33:04", "throughput": 1485.46, "total_tokens": 19381024} {"current_steps": 91830, "total_steps": 181800, "loss": 0.0343, "lr": 2.8901379262235156e-05, "epoch": 10.102310231023102, "percentage": 50.51, "elapsed_time": "3:37:27", "remaining_time": "3:33:03", "throughput": 1485.46, "total_tokens": 19382112} {"current_steps": 91835, "total_steps": 181800, "loss": 0.0552, "lr": 2.8899008581345028e-05, "epoch": 10.102860286028603, "percentage": 50.51, "elapsed_time": "3:37:28", "remaining_time": "3:33:02", "throughput": 1485.46, "total_tokens": 19383104} {"current_steps": 91840, "total_steps": 181800, "loss": 0.0691, "lr": 2.889663786451961e-05, "epoch": 10.103410341034103, "percentage": 50.52, "elapsed_time": "3:37:29", "remaining_time": "3:33:02", "throughput": 1485.46, "total_tokens": 19384160} {"current_steps": 91845, "total_steps": 181800, "loss": 0.0208, "lr": 2.8894267111780748e-05, "epoch": 10.103960396039604, "percentage": 50.52, "elapsed_time": "3:37:29", "remaining_time": "3:33:01", "throughput": 1485.46, "total_tokens": 19385184} {"current_steps": 91850, "total_steps": 181800, "loss": 0.0196, "lr": 2.8891896323150302e-05, "epoch": 10.104510451045105, "percentage": 50.52, "elapsed_time": "3:37:30", "remaining_time": "3:33:00", "throughput": 1485.47, "total_tokens": 19386272} {"current_steps": 91855, "total_steps": 181800, "loss": 0.1011, "lr": 2.8889525498650105e-05, "epoch": 10.105060506050606, "percentage": 50.53, "elapsed_time": "3:37:31", "remaining_time": "3:32:59", "throughput": 1485.47, "total_tokens": 19387360} {"current_steps": 91860, "total_steps": 181800, "loss": 0.0685, "lr": 2.888715463830202e-05, "epoch": 10.105610561056105, "percentage": 50.53, "elapsed_time": "3:37:32", "remaining_time": "3:32:59", "throughput": 1485.47, "total_tokens": 19388384} {"current_steps": 91865, "total_steps": 181800, "loss": 0.0079, "lr": 2.888478374212791e-05, "epoch": 10.106160616061606, "percentage": 50.53, "elapsed_time": "3:37:32", "remaining_time": "3:32:58", "throughput": 1485.47, "total_tokens": 19389440} {"current_steps": 91870, "total_steps": 181800, "loss": 0.0014, "lr": 2.8882412810149595e-05, "epoch": 10.106710671067107, "percentage": 50.53, "elapsed_time": "3:37:33", "remaining_time": "3:32:57", "throughput": 1485.47, "total_tokens": 19390432} {"current_steps": 91875, "total_steps": 181800, "loss": 0.0095, "lr": 2.8880041842388944e-05, "epoch": 10.107260726072607, "percentage": 50.54, "elapsed_time": "3:37:34", "remaining_time": "3:32:57", "throughput": 1485.47, "total_tokens": 19391424} {"current_steps": 91880, "total_steps": 181800, "loss": 0.0726, "lr": 2.8877670838867815e-05, "epoch": 10.107810781078108, "percentage": 50.54, "elapsed_time": "3:37:34", "remaining_time": "3:32:56", "throughput": 1485.47, "total_tokens": 19392480} {"current_steps": 91885, "total_steps": 181800, "loss": 0.0467, "lr": 2.887529979960806e-05, "epoch": 10.108360836083609, "percentage": 50.54, "elapsed_time": "3:37:35", "remaining_time": "3:32:55", "throughput": 1485.48, "total_tokens": 19393600} {"current_steps": 91890, "total_steps": 181800, "loss": 0.021, "lr": 2.8872928724631522e-05, "epoch": 10.108910891089108, "percentage": 50.54, "elapsed_time": "3:37:36", "remaining_time": "3:32:54", "throughput": 1485.48, "total_tokens": 19394624} {"current_steps": 91895, "total_steps": 181800, "loss": 0.0165, "lr": 2.8870557613960055e-05, "epoch": 10.10946094609461, "percentage": 50.55, "elapsed_time": "3:37:36", "remaining_time": "3:32:54", "throughput": 1485.48, "total_tokens": 19395680} {"current_steps": 91900, "total_steps": 181800, "loss": 0.0436, "lr": 2.8868186467615517e-05, "epoch": 10.11001100110011, "percentage": 50.55, "elapsed_time": "3:37:37", "remaining_time": "3:32:53", "throughput": 1485.48, "total_tokens": 19396768} {"current_steps": 91905, "total_steps": 181800, "loss": 0.0048, "lr": 2.886581528561976e-05, "epoch": 10.110561056105611, "percentage": 50.55, "elapsed_time": "3:37:38", "remaining_time": "3:32:52", "throughput": 1485.49, "total_tokens": 19397824} {"current_steps": 91910, "total_steps": 181800, "loss": 0.0762, "lr": 2.8863444067994637e-05, "epoch": 10.11111111111111, "percentage": 50.56, "elapsed_time": "3:37:38", "remaining_time": "3:32:51", "throughput": 1485.49, "total_tokens": 19398944} {"current_steps": 91915, "total_steps": 181800, "loss": 0.0143, "lr": 2.886107281476201e-05, "epoch": 10.111661166116612, "percentage": 50.56, "elapsed_time": "3:37:39", "remaining_time": "3:32:51", "throughput": 1485.51, "total_tokens": 19400128} {"current_steps": 91920, "total_steps": 181800, "loss": 0.0183, "lr": 2.885870152594372e-05, "epoch": 10.112211221122113, "percentage": 50.56, "elapsed_time": "3:37:40", "remaining_time": "3:32:50", "throughput": 1485.51, "total_tokens": 19401184} {"current_steps": 91925, "total_steps": 181800, "loss": 0.03, "lr": 2.8856330201561636e-05, "epoch": 10.112761276127612, "percentage": 50.56, "elapsed_time": "3:37:40", "remaining_time": "3:32:49", "throughput": 1485.51, "total_tokens": 19402240} {"current_steps": 91930, "total_steps": 181800, "loss": 0.0324, "lr": 2.885395884163761e-05, "epoch": 10.113311331133113, "percentage": 50.57, "elapsed_time": "3:37:41", "remaining_time": "3:32:48", "throughput": 1485.52, "total_tokens": 19403328} {"current_steps": 91935, "total_steps": 181800, "loss": 0.0102, "lr": 2.8851587446193485e-05, "epoch": 10.113861386138614, "percentage": 50.57, "elapsed_time": "3:37:42", "remaining_time": "3:32:48", "throughput": 1485.52, "total_tokens": 19404320} {"current_steps": 91940, "total_steps": 181800, "loss": 0.0351, "lr": 2.8849216015251135e-05, "epoch": 10.114411441144114, "percentage": 50.57, "elapsed_time": "3:37:43", "remaining_time": "3:32:47", "throughput": 1485.52, "total_tokens": 19405376} {"current_steps": 91945, "total_steps": 181800, "loss": 0.0031, "lr": 2.8846844548832396e-05, "epoch": 10.114961496149615, "percentage": 50.57, "elapsed_time": "3:37:43", "remaining_time": "3:32:46", "throughput": 1485.52, "total_tokens": 19406464} {"current_steps": 91950, "total_steps": 181800, "loss": 0.0613, "lr": 2.884447304695915e-05, "epoch": 10.115511551155116, "percentage": 50.58, "elapsed_time": "3:37:44", "remaining_time": "3:32:46", "throughput": 1485.53, "total_tokens": 19407552} {"current_steps": 91955, "total_steps": 181800, "loss": 0.0172, "lr": 2.8842101509653235e-05, "epoch": 10.116061606160615, "percentage": 50.58, "elapsed_time": "3:37:45", "remaining_time": "3:32:45", "throughput": 1485.53, "total_tokens": 19408640} {"current_steps": 91960, "total_steps": 181800, "loss": 0.1094, "lr": 2.8839729936936516e-05, "epoch": 10.116611661166116, "percentage": 50.58, "elapsed_time": "3:37:45", "remaining_time": "3:32:44", "throughput": 1485.54, "total_tokens": 19409728} {"current_steps": 91965, "total_steps": 181800, "loss": 0.009, "lr": 2.8837358328830843e-05, "epoch": 10.117161716171617, "percentage": 50.59, "elapsed_time": "3:37:46", "remaining_time": "3:32:43", "throughput": 1485.54, "total_tokens": 19410752} {"current_steps": 91970, "total_steps": 181800, "loss": 0.005, "lr": 2.883498668535809e-05, "epoch": 10.117711771177119, "percentage": 50.59, "elapsed_time": "3:37:47", "remaining_time": "3:32:43", "throughput": 1485.53, "total_tokens": 19411712} {"current_steps": 91975, "total_steps": 181800, "loss": 0.0052, "lr": 2.8832615006540094e-05, "epoch": 10.118261826182618, "percentage": 50.59, "elapsed_time": "3:37:47", "remaining_time": "3:32:42", "throughput": 1485.53, "total_tokens": 19412704} {"current_steps": 91980, "total_steps": 181800, "loss": 0.0306, "lr": 2.883024329239873e-05, "epoch": 10.118811881188119, "percentage": 50.59, "elapsed_time": "3:37:48", "remaining_time": "3:32:41", "throughput": 1485.53, "total_tokens": 19413760} {"current_steps": 91985, "total_steps": 181800, "loss": 0.0136, "lr": 2.8827871542955854e-05, "epoch": 10.11936193619362, "percentage": 50.6, "elapsed_time": "3:37:49", "remaining_time": "3:32:40", "throughput": 1485.53, "total_tokens": 19414784} {"current_steps": 91990, "total_steps": 181800, "loss": 0.007, "lr": 2.8825499758233314e-05, "epoch": 10.11991199119912, "percentage": 50.6, "elapsed_time": "3:37:49", "remaining_time": "3:32:40", "throughput": 1485.54, "total_tokens": 19415872} {"current_steps": 91995, "total_steps": 181800, "loss": 0.0885, "lr": 2.8823127938252987e-05, "epoch": 10.12046204620462, "percentage": 50.6, "elapsed_time": "3:37:50", "remaining_time": "3:32:39", "throughput": 1485.54, "total_tokens": 19416896} {"current_steps": 92000, "total_steps": 181800, "loss": 0.0268, "lr": 2.882075608303672e-05, "epoch": 10.121012101210122, "percentage": 50.61, "elapsed_time": "3:37:51", "remaining_time": "3:32:38", "throughput": 1485.54, "total_tokens": 19417984} {"current_steps": 92005, "total_steps": 181800, "loss": 0.0902, "lr": 2.8818384192606373e-05, "epoch": 10.12156215621562, "percentage": 50.61, "elapsed_time": "3:37:52", "remaining_time": "3:32:38", "throughput": 1485.55, "total_tokens": 19419072} {"current_steps": 92010, "total_steps": 181800, "loss": 0.0018, "lr": 2.881601226698383e-05, "epoch": 10.122112211221122, "percentage": 50.61, "elapsed_time": "3:37:52", "remaining_time": "3:32:37", "throughput": 1485.55, "total_tokens": 19420160} {"current_steps": 92015, "total_steps": 181800, "loss": 0.0049, "lr": 2.8813640306190915e-05, "epoch": 10.122662266226623, "percentage": 50.61, "elapsed_time": "3:37:53", "remaining_time": "3:32:36", "throughput": 1485.55, "total_tokens": 19421216} {"current_steps": 92020, "total_steps": 181800, "loss": 0.0041, "lr": 2.8811268310249506e-05, "epoch": 10.123212321232122, "percentage": 50.62, "elapsed_time": "3:37:54", "remaining_time": "3:32:35", "throughput": 1485.56, "total_tokens": 19422304} {"current_steps": 92025, "total_steps": 181800, "loss": 0.0092, "lr": 2.8808896279181474e-05, "epoch": 10.123762376237623, "percentage": 50.62, "elapsed_time": "3:37:54", "remaining_time": "3:32:35", "throughput": 1485.56, "total_tokens": 19423328} {"current_steps": 92030, "total_steps": 181800, "loss": 0.0117, "lr": 2.8806524213008673e-05, "epoch": 10.124312431243125, "percentage": 50.62, "elapsed_time": "3:37:55", "remaining_time": "3:32:34", "throughput": 1485.56, "total_tokens": 19424384} {"current_steps": 92035, "total_steps": 181800, "loss": 0.2077, "lr": 2.8804152111752963e-05, "epoch": 10.124862486248626, "percentage": 50.62, "elapsed_time": "3:37:56", "remaining_time": "3:32:33", "throughput": 1485.56, "total_tokens": 19425472} {"current_steps": 92040, "total_steps": 181800, "loss": 0.0158, "lr": 2.8801779975436212e-05, "epoch": 10.125412541254125, "percentage": 50.63, "elapsed_time": "3:37:56", "remaining_time": "3:32:32", "throughput": 1485.56, "total_tokens": 19426464} {"current_steps": 92045, "total_steps": 181800, "loss": 0.0473, "lr": 2.8799407804080276e-05, "epoch": 10.125962596259626, "percentage": 50.63, "elapsed_time": "3:37:57", "remaining_time": "3:32:32", "throughput": 1485.56, "total_tokens": 19427488} {"current_steps": 92050, "total_steps": 181800, "loss": 0.0024, "lr": 2.879703559770701e-05, "epoch": 10.126512651265127, "percentage": 50.63, "elapsed_time": "3:37:58", "remaining_time": "3:32:31", "throughput": 1485.56, "total_tokens": 19428480} {"current_steps": 92055, "total_steps": 181800, "loss": 0.0377, "lr": 2.8794663356338307e-05, "epoch": 10.127062706270626, "percentage": 50.64, "elapsed_time": "3:37:58", "remaining_time": "3:32:30", "throughput": 1485.56, "total_tokens": 19429472} {"current_steps": 92060, "total_steps": 181800, "loss": 0.0763, "lr": 2.8792291079996008e-05, "epoch": 10.127612761276128, "percentage": 50.64, "elapsed_time": "3:37:59", "remaining_time": "3:32:29", "throughput": 1485.56, "total_tokens": 19430528} {"current_steps": 92065, "total_steps": 181800, "loss": 0.0084, "lr": 2.8789918768701972e-05, "epoch": 10.128162816281629, "percentage": 50.64, "elapsed_time": "3:38:00", "remaining_time": "3:32:29", "throughput": 1485.56, "total_tokens": 19431552} {"current_steps": 92070, "total_steps": 181800, "loss": 0.1693, "lr": 2.8787546422478083e-05, "epoch": 10.128712871287128, "percentage": 50.64, "elapsed_time": "3:38:00", "remaining_time": "3:32:28", "throughput": 1485.56, "total_tokens": 19432576} {"current_steps": 92075, "total_steps": 181800, "loss": 0.0041, "lr": 2.8785174041346198e-05, "epoch": 10.129262926292629, "percentage": 50.65, "elapsed_time": "3:38:01", "remaining_time": "3:32:27", "throughput": 1485.56, "total_tokens": 19433632} {"current_steps": 92080, "total_steps": 181800, "loss": 0.0058, "lr": 2.878280162532817e-05, "epoch": 10.12981298129813, "percentage": 50.65, "elapsed_time": "3:38:02", "remaining_time": "3:32:27", "throughput": 1485.56, "total_tokens": 19434688} {"current_steps": 92085, "total_steps": 181800, "loss": 0.033, "lr": 2.8780429174445882e-05, "epoch": 10.130363036303631, "percentage": 50.65, "elapsed_time": "3:38:03", "remaining_time": "3:32:26", "throughput": 1485.56, "total_tokens": 19435680} {"current_steps": 92090, "total_steps": 181800, "loss": 0.0019, "lr": 2.8778056688721193e-05, "epoch": 10.13091309130913, "percentage": 50.65, "elapsed_time": "3:38:03", "remaining_time": "3:32:25", "throughput": 1485.56, "total_tokens": 19436672} {"current_steps": 92095, "total_steps": 181800, "loss": 0.1012, "lr": 2.8775684168175958e-05, "epoch": 10.131463146314632, "percentage": 50.66, "elapsed_time": "3:38:04", "remaining_time": "3:32:24", "throughput": 1485.56, "total_tokens": 19437728} {"current_steps": 92100, "total_steps": 181800, "loss": 0.1222, "lr": 2.8773311612832066e-05, "epoch": 10.132013201320133, "percentage": 50.66, "elapsed_time": "3:38:05", "remaining_time": "3:32:24", "throughput": 1485.57, "total_tokens": 19438848} {"current_steps": 92105, "total_steps": 181800, "loss": 0.0028, "lr": 2.877093902271137e-05, "epoch": 10.132563256325632, "percentage": 50.66, "elapsed_time": "3:38:05", "remaining_time": "3:32:23", "throughput": 1485.57, "total_tokens": 19439840} {"current_steps": 92110, "total_steps": 181800, "loss": 0.0094, "lr": 2.8768566397835734e-05, "epoch": 10.133113311331133, "percentage": 50.67, "elapsed_time": "3:38:06", "remaining_time": "3:32:22", "throughput": 1485.57, "total_tokens": 19440960} {"current_steps": 92115, "total_steps": 181800, "loss": 0.1045, "lr": 2.8766193738227032e-05, "epoch": 10.133663366336634, "percentage": 50.67, "elapsed_time": "3:38:07", "remaining_time": "3:32:21", "throughput": 1485.58, "total_tokens": 19442016} {"current_steps": 92120, "total_steps": 181800, "loss": 0.017, "lr": 2.876382104390713e-05, "epoch": 10.134213421342134, "percentage": 50.67, "elapsed_time": "3:38:07", "remaining_time": "3:32:21", "throughput": 1485.58, "total_tokens": 19443104} {"current_steps": 92125, "total_steps": 181800, "loss": 0.0149, "lr": 2.8761448314897888e-05, "epoch": 10.134763476347635, "percentage": 50.67, "elapsed_time": "3:38:08", "remaining_time": "3:32:20", "throughput": 1485.58, "total_tokens": 19444160} {"current_steps": 92130, "total_steps": 181800, "loss": 0.012, "lr": 2.8759075551221194e-05, "epoch": 10.135313531353136, "percentage": 50.68, "elapsed_time": "3:38:09", "remaining_time": "3:32:19", "throughput": 1485.59, "total_tokens": 19445248} {"current_steps": 92135, "total_steps": 181800, "loss": 0.0159, "lr": 2.8756702752898897e-05, "epoch": 10.135863586358635, "percentage": 50.68, "elapsed_time": "3:38:09", "remaining_time": "3:32:19", "throughput": 1485.59, "total_tokens": 19446368} {"current_steps": 92140, "total_steps": 181800, "loss": 0.0252, "lr": 2.8754329919952878e-05, "epoch": 10.136413641364136, "percentage": 50.68, "elapsed_time": "3:38:10", "remaining_time": "3:32:18", "throughput": 1485.59, "total_tokens": 19447360} {"current_steps": 92145, "total_steps": 181800, "loss": 0.0825, "lr": 2.8751957052404998e-05, "epoch": 10.136963696369637, "percentage": 50.68, "elapsed_time": "3:38:11", "remaining_time": "3:32:17", "throughput": 1485.59, "total_tokens": 19448416} {"current_steps": 92150, "total_steps": 181800, "loss": 0.0108, "lr": 2.8749584150277133e-05, "epoch": 10.137513751375138, "percentage": 50.69, "elapsed_time": "3:38:12", "remaining_time": "3:32:16", "throughput": 1485.6, "total_tokens": 19449504} {"current_steps": 92155, "total_steps": 181800, "loss": 0.0243, "lr": 2.8747211213591147e-05, "epoch": 10.138063806380638, "percentage": 50.69, "elapsed_time": "3:38:12", "remaining_time": "3:32:16", "throughput": 1485.6, "total_tokens": 19450528} {"current_steps": 92160, "total_steps": 181800, "loss": 0.0475, "lr": 2.8744838242368917e-05, "epoch": 10.138613861386139, "percentage": 50.69, "elapsed_time": "3:38:13", "remaining_time": "3:32:15", "throughput": 1485.6, "total_tokens": 19451584} {"current_steps": 92165, "total_steps": 181800, "loss": 0.0261, "lr": 2.87424652366323e-05, "epoch": 10.13916391639164, "percentage": 50.7, "elapsed_time": "3:38:14", "remaining_time": "3:32:14", "throughput": 1485.61, "total_tokens": 19452640} {"current_steps": 92170, "total_steps": 181800, "loss": 0.0086, "lr": 2.8740092196403184e-05, "epoch": 10.13971397139714, "percentage": 50.7, "elapsed_time": "3:38:14", "remaining_time": "3:32:13", "throughput": 1485.61, "total_tokens": 19453760} {"current_steps": 92175, "total_steps": 181800, "loss": 0.0707, "lr": 2.873771912170344e-05, "epoch": 10.14026402640264, "percentage": 50.7, "elapsed_time": "3:38:15", "remaining_time": "3:32:13", "throughput": 1485.62, "total_tokens": 19454880} {"current_steps": 92180, "total_steps": 181800, "loss": 0.0265, "lr": 2.873534601255492e-05, "epoch": 10.140814081408141, "percentage": 50.7, "elapsed_time": "3:38:16", "remaining_time": "3:32:12", "throughput": 1485.62, "total_tokens": 19455968} {"current_steps": 92185, "total_steps": 181800, "loss": 0.0385, "lr": 2.8732972868979514e-05, "epoch": 10.14136413641364, "percentage": 50.71, "elapsed_time": "3:38:16", "remaining_time": "3:32:11", "throughput": 1485.62, "total_tokens": 19456992} {"current_steps": 92190, "total_steps": 181800, "loss": 0.2144, "lr": 2.8730599690999087e-05, "epoch": 10.141914191419142, "percentage": 50.71, "elapsed_time": "3:38:17", "remaining_time": "3:32:10", "throughput": 1485.62, "total_tokens": 19457984} {"current_steps": 92195, "total_steps": 181800, "loss": 0.0319, "lr": 2.872822647863551e-05, "epoch": 10.142464246424643, "percentage": 50.71, "elapsed_time": "3:38:18", "remaining_time": "3:32:10", "throughput": 1485.62, "total_tokens": 19459040} {"current_steps": 92200, "total_steps": 181800, "loss": 0.0432, "lr": 2.8725853231910672e-05, "epoch": 10.143014301430142, "percentage": 50.72, "elapsed_time": "3:38:18", "remaining_time": "3:32:09", "throughput": 1485.62, "total_tokens": 19460032} {"current_steps": 92205, "total_steps": 181800, "loss": 0.0051, "lr": 2.8723479950846423e-05, "epoch": 10.143564356435643, "percentage": 50.72, "elapsed_time": "3:38:19", "remaining_time": "3:32:08", "throughput": 1485.62, "total_tokens": 19461056} {"current_steps": 92210, "total_steps": 181800, "loss": 0.0562, "lr": 2.872110663546464e-05, "epoch": 10.144114411441144, "percentage": 50.72, "elapsed_time": "3:38:20", "remaining_time": "3:32:08", "throughput": 1485.62, "total_tokens": 19462112} {"current_steps": 92215, "total_steps": 181800, "loss": 0.0081, "lr": 2.871873328578721e-05, "epoch": 10.144664466446645, "percentage": 50.72, "elapsed_time": "3:38:20", "remaining_time": "3:32:07", "throughput": 1485.63, "total_tokens": 19463200} {"current_steps": 92220, "total_steps": 181800, "loss": 0.0164, "lr": 2.8716359901835992e-05, "epoch": 10.145214521452145, "percentage": 50.73, "elapsed_time": "3:38:21", "remaining_time": "3:32:06", "throughput": 1485.63, "total_tokens": 19464224} {"current_steps": 92225, "total_steps": 181800, "loss": 0.0011, "lr": 2.8713986483632877e-05, "epoch": 10.145764576457646, "percentage": 50.73, "elapsed_time": "3:38:22", "remaining_time": "3:32:05", "throughput": 1485.63, "total_tokens": 19465280} {"current_steps": 92230, "total_steps": 181800, "loss": 0.0013, "lr": 2.871161303119973e-05, "epoch": 10.146314631463147, "percentage": 50.73, "elapsed_time": "3:38:23", "remaining_time": "3:32:05", "throughput": 1485.64, "total_tokens": 19466368} {"current_steps": 92235, "total_steps": 181800, "loss": 0.0244, "lr": 2.8709239544558427e-05, "epoch": 10.146864686468646, "percentage": 50.73, "elapsed_time": "3:38:23", "remaining_time": "3:32:04", "throughput": 1485.64, "total_tokens": 19467456} {"current_steps": 92240, "total_steps": 181800, "loss": 0.0297, "lr": 2.8706866023730832e-05, "epoch": 10.147414741474147, "percentage": 50.74, "elapsed_time": "3:38:24", "remaining_time": "3:32:03", "throughput": 1485.62, "total_tokens": 19468512} {"current_steps": 92245, "total_steps": 181800, "loss": 0.0145, "lr": 2.870449246873885e-05, "epoch": 10.147964796479648, "percentage": 50.74, "elapsed_time": "3:38:25", "remaining_time": "3:32:03", "throughput": 1485.62, "total_tokens": 19469504} {"current_steps": 92250, "total_steps": 181800, "loss": 0.0419, "lr": 2.8702118879604322e-05, "epoch": 10.148514851485148, "percentage": 50.74, "elapsed_time": "3:38:26", "remaining_time": "3:32:02", "throughput": 1485.62, "total_tokens": 19470560} {"current_steps": 92255, "total_steps": 181800, "loss": 0.0035, "lr": 2.8699745256349147e-05, "epoch": 10.149064906490649, "percentage": 50.75, "elapsed_time": "3:38:26", "remaining_time": "3:32:01", "throughput": 1485.62, "total_tokens": 19471552} {"current_steps": 92260, "total_steps": 181800, "loss": 0.003, "lr": 2.86973715989952e-05, "epoch": 10.14961496149615, "percentage": 50.75, "elapsed_time": "3:38:27", "remaining_time": "3:32:00", "throughput": 1485.62, "total_tokens": 19472608} {"current_steps": 92265, "total_steps": 181800, "loss": 0.0209, "lr": 2.8694997907564348e-05, "epoch": 10.150165016501651, "percentage": 50.75, "elapsed_time": "3:38:28", "remaining_time": "3:32:00", "throughput": 1485.62, "total_tokens": 19473632} {"current_steps": 92270, "total_steps": 181800, "loss": 0.0022, "lr": 2.8692624182078476e-05, "epoch": 10.15071507150715, "percentage": 50.75, "elapsed_time": "3:38:28", "remaining_time": "3:31:59", "throughput": 1485.61, "total_tokens": 19474592} {"current_steps": 92275, "total_steps": 181800, "loss": 0.0308, "lr": 2.8690250422559457e-05, "epoch": 10.151265126512651, "percentage": 50.76, "elapsed_time": "3:38:29", "remaining_time": "3:31:58", "throughput": 1485.61, "total_tokens": 19475616} {"current_steps": 92280, "total_steps": 181800, "loss": 0.0809, "lr": 2.8687876629029165e-05, "epoch": 10.151815181518153, "percentage": 50.76, "elapsed_time": "3:38:30", "remaining_time": "3:31:58", "throughput": 1485.62, "total_tokens": 19476672} {"current_steps": 92285, "total_steps": 181800, "loss": 0.084, "lr": 2.868550280150949e-05, "epoch": 10.152365236523652, "percentage": 50.76, "elapsed_time": "3:38:30", "remaining_time": "3:31:57", "throughput": 1485.62, "total_tokens": 19477760} {"current_steps": 92290, "total_steps": 181800, "loss": 0.0013, "lr": 2.86831289400223e-05, "epoch": 10.152915291529153, "percentage": 50.76, "elapsed_time": "3:38:31", "remaining_time": "3:31:56", "throughput": 1485.62, "total_tokens": 19478816} {"current_steps": 92295, "total_steps": 181800, "loss": 0.0047, "lr": 2.8680755044589487e-05, "epoch": 10.153465346534654, "percentage": 50.77, "elapsed_time": "3:38:32", "remaining_time": "3:31:55", "throughput": 1485.62, "total_tokens": 19479840} {"current_steps": 92300, "total_steps": 181800, "loss": 0.0331, "lr": 2.8678381115232918e-05, "epoch": 10.154015401540153, "percentage": 50.77, "elapsed_time": "3:38:32", "remaining_time": "3:31:55", "throughput": 1485.63, "total_tokens": 19480928} {"current_steps": 92305, "total_steps": 181800, "loss": 0.0044, "lr": 2.8676007151974472e-05, "epoch": 10.154565456545654, "percentage": 50.77, "elapsed_time": "3:38:33", "remaining_time": "3:31:54", "throughput": 1485.63, "total_tokens": 19481984} {"current_steps": 92310, "total_steps": 181800, "loss": 0.0466, "lr": 2.8673633154836027e-05, "epoch": 10.155115511551156, "percentage": 50.78, "elapsed_time": "3:38:34", "remaining_time": "3:31:53", "throughput": 1485.64, "total_tokens": 19483072} {"current_steps": 92315, "total_steps": 181800, "loss": 0.3185, "lr": 2.8671259123839472e-05, "epoch": 10.155665566556655, "percentage": 50.78, "elapsed_time": "3:38:34", "remaining_time": "3:31:52", "throughput": 1485.64, "total_tokens": 19484096} {"current_steps": 92320, "total_steps": 181800, "loss": 0.0048, "lr": 2.866888505900669e-05, "epoch": 10.156215621562156, "percentage": 50.78, "elapsed_time": "3:38:35", "remaining_time": "3:31:52", "throughput": 1485.64, "total_tokens": 19485216} {"current_steps": 92325, "total_steps": 181800, "loss": 0.0331, "lr": 2.866651096035955e-05, "epoch": 10.156765676567657, "percentage": 50.78, "elapsed_time": "3:38:36", "remaining_time": "3:31:51", "throughput": 1485.64, "total_tokens": 19486208} {"current_steps": 92330, "total_steps": 181800, "loss": 0.1328, "lr": 2.8664136827919934e-05, "epoch": 10.157315731573158, "percentage": 50.79, "elapsed_time": "3:38:37", "remaining_time": "3:31:50", "throughput": 1485.65, "total_tokens": 19487328} {"current_steps": 92335, "total_steps": 181800, "loss": 0.08, "lr": 2.8661762661709735e-05, "epoch": 10.157865786578657, "percentage": 50.79, "elapsed_time": "3:38:37", "remaining_time": "3:31:50", "throughput": 1485.65, "total_tokens": 19488416} {"current_steps": 92340, "total_steps": 181800, "loss": 0.025, "lr": 2.8659388461750815e-05, "epoch": 10.158415841584159, "percentage": 50.79, "elapsed_time": "3:38:38", "remaining_time": "3:31:49", "throughput": 1485.65, "total_tokens": 19489408} {"current_steps": 92345, "total_steps": 181800, "loss": 0.0152, "lr": 2.8657014228065083e-05, "epoch": 10.15896589658966, "percentage": 50.79, "elapsed_time": "3:38:39", "remaining_time": "3:31:48", "throughput": 1485.66, "total_tokens": 19490496} {"current_steps": 92350, "total_steps": 181800, "loss": 0.094, "lr": 2.8654639960674396e-05, "epoch": 10.159515951595159, "percentage": 50.8, "elapsed_time": "3:38:39", "remaining_time": "3:31:47", "throughput": 1485.67, "total_tokens": 19491648} {"current_steps": 92355, "total_steps": 181800, "loss": 0.0091, "lr": 2.865226565960064e-05, "epoch": 10.16006600660066, "percentage": 50.8, "elapsed_time": "3:38:40", "remaining_time": "3:31:47", "throughput": 1485.67, "total_tokens": 19492672} {"current_steps": 92360, "total_steps": 181800, "loss": 0.0219, "lr": 2.8649891324865718e-05, "epoch": 10.160616061606161, "percentage": 50.8, "elapsed_time": "3:38:41", "remaining_time": "3:31:46", "throughput": 1485.67, "total_tokens": 19493760} {"current_steps": 92365, "total_steps": 181800, "loss": 0.0323, "lr": 2.8647516956491495e-05, "epoch": 10.16116611661166, "percentage": 50.81, "elapsed_time": "3:38:41", "remaining_time": "3:31:45", "throughput": 1485.67, "total_tokens": 19494784} {"current_steps": 92370, "total_steps": 181800, "loss": 0.0226, "lr": 2.8645142554499856e-05, "epoch": 10.161716171617162, "percentage": 50.81, "elapsed_time": "3:38:42", "remaining_time": "3:31:44", "throughput": 1485.67, "total_tokens": 19495776} {"current_steps": 92375, "total_steps": 181800, "loss": 0.0034, "lr": 2.8642768118912684e-05, "epoch": 10.162266226622663, "percentage": 50.81, "elapsed_time": "3:38:43", "remaining_time": "3:31:44", "throughput": 1485.67, "total_tokens": 19496800} {"current_steps": 92380, "total_steps": 181800, "loss": 0.0226, "lr": 2.8640393649751874e-05, "epoch": 10.162816281628162, "percentage": 50.81, "elapsed_time": "3:38:43", "remaining_time": "3:31:43", "throughput": 1485.67, "total_tokens": 19497824} {"current_steps": 92385, "total_steps": 181800, "loss": 0.0089, "lr": 2.863801914703929e-05, "epoch": 10.163366336633663, "percentage": 50.82, "elapsed_time": "3:38:44", "remaining_time": "3:31:42", "throughput": 1485.67, "total_tokens": 19498912} {"current_steps": 92390, "total_steps": 181800, "loss": 0.0148, "lr": 2.8635644610796842e-05, "epoch": 10.163916391639164, "percentage": 50.82, "elapsed_time": "3:38:45", "remaining_time": "3:31:41", "throughput": 1485.68, "total_tokens": 19499968} {"current_steps": 92395, "total_steps": 181800, "loss": 0.0609, "lr": 2.86332700410464e-05, "epoch": 10.164466446644665, "percentage": 50.82, "elapsed_time": "3:38:46", "remaining_time": "3:31:41", "throughput": 1485.68, "total_tokens": 19500992} {"current_steps": 92400, "total_steps": 181800, "loss": 0.0178, "lr": 2.8630895437809847e-05, "epoch": 10.165016501650165, "percentage": 50.83, "elapsed_time": "3:38:46", "remaining_time": "3:31:40", "throughput": 1485.68, "total_tokens": 19502048} {"current_steps": 92405, "total_steps": 181800, "loss": 0.0236, "lr": 2.862852080110907e-05, "epoch": 10.165566556655666, "percentage": 50.83, "elapsed_time": "3:38:47", "remaining_time": "3:31:39", "throughput": 1485.68, "total_tokens": 19503040} {"current_steps": 92410, "total_steps": 181800, "loss": 0.0183, "lr": 2.862614613096597e-05, "epoch": 10.166116611661167, "percentage": 50.83, "elapsed_time": "3:38:48", "remaining_time": "3:31:39", "throughput": 1485.67, "total_tokens": 19504032} {"current_steps": 92415, "total_steps": 181800, "loss": 0.0221, "lr": 2.8623771427402413e-05, "epoch": 10.166666666666666, "percentage": 50.83, "elapsed_time": "3:38:48", "remaining_time": "3:31:38", "throughput": 1485.68, "total_tokens": 19505088} {"current_steps": 92420, "total_steps": 181800, "loss": 0.0526, "lr": 2.8621396690440295e-05, "epoch": 10.167216721672167, "percentage": 50.84, "elapsed_time": "3:38:49", "remaining_time": "3:31:37", "throughput": 1485.68, "total_tokens": 19506112} {"current_steps": 92425, "total_steps": 181800, "loss": 0.0149, "lr": 2.86190219201015e-05, "epoch": 10.167766776677668, "percentage": 50.84, "elapsed_time": "3:38:50", "remaining_time": "3:31:36", "throughput": 1485.67, "total_tokens": 19507104} {"current_steps": 92430, "total_steps": 181800, "loss": 0.1241, "lr": 2.8616647116407912e-05, "epoch": 10.168316831683168, "percentage": 50.84, "elapsed_time": "3:38:50", "remaining_time": "3:31:36", "throughput": 1485.68, "total_tokens": 19508192} {"current_steps": 92435, "total_steps": 181800, "loss": 0.0111, "lr": 2.8614272279381432e-05, "epoch": 10.168866886688669, "percentage": 50.84, "elapsed_time": "3:38:51", "remaining_time": "3:31:35", "throughput": 1485.68, "total_tokens": 19509248} {"current_steps": 92440, "total_steps": 181800, "loss": 0.0063, "lr": 2.8611897409043935e-05, "epoch": 10.16941694169417, "percentage": 50.85, "elapsed_time": "3:38:52", "remaining_time": "3:31:34", "throughput": 1485.68, "total_tokens": 19510304} {"current_steps": 92445, "total_steps": 181800, "loss": 0.008, "lr": 2.8609522505417314e-05, "epoch": 10.16996699669967, "percentage": 50.85, "elapsed_time": "3:38:52", "remaining_time": "3:31:33", "throughput": 1485.69, "total_tokens": 19511360} {"current_steps": 92450, "total_steps": 181800, "loss": 0.1413, "lr": 2.860714756852345e-05, "epoch": 10.17051705170517, "percentage": 50.85, "elapsed_time": "3:38:53", "remaining_time": "3:31:33", "throughput": 1485.68, "total_tokens": 19512320} {"current_steps": 92455, "total_steps": 181800, "loss": 0.002, "lr": 2.8604772598384248e-05, "epoch": 10.171067106710671, "percentage": 50.86, "elapsed_time": "3:38:54", "remaining_time": "3:31:32", "throughput": 1485.68, "total_tokens": 19513312} {"current_steps": 92460, "total_steps": 181800, "loss": 0.0038, "lr": 2.8602397595021578e-05, "epoch": 10.171617161716172, "percentage": 50.86, "elapsed_time": "3:38:54", "remaining_time": "3:31:31", "throughput": 1485.67, "total_tokens": 19514304} {"current_steps": 92465, "total_steps": 181800, "loss": 0.004, "lr": 2.8600022558457344e-05, "epoch": 10.172167216721672, "percentage": 50.86, "elapsed_time": "3:38:55", "remaining_time": "3:31:31", "throughput": 1485.68, "total_tokens": 19515392} {"current_steps": 92470, "total_steps": 181800, "loss": 0.0452, "lr": 2.8597647488713424e-05, "epoch": 10.172717271727173, "percentage": 50.86, "elapsed_time": "3:38:56", "remaining_time": "3:31:30", "throughput": 1485.68, "total_tokens": 19516448} {"current_steps": 92475, "total_steps": 181800, "loss": 0.0178, "lr": 2.8595272385811717e-05, "epoch": 10.173267326732674, "percentage": 50.87, "elapsed_time": "3:38:57", "remaining_time": "3:31:29", "throughput": 1485.68, "total_tokens": 19517504} {"current_steps": 92480, "total_steps": 181800, "loss": 0.0071, "lr": 2.859289724977411e-05, "epoch": 10.173817381738173, "percentage": 50.87, "elapsed_time": "3:38:57", "remaining_time": "3:31:28", "throughput": 1485.69, "total_tokens": 19518592} {"current_steps": 92485, "total_steps": 181800, "loss": 0.0166, "lr": 2.8590522080622494e-05, "epoch": 10.174367436743674, "percentage": 50.87, "elapsed_time": "3:38:58", "remaining_time": "3:31:28", "throughput": 1485.69, "total_tokens": 19519648} {"current_steps": 92490, "total_steps": 181800, "loss": 0.0067, "lr": 2.8588146878378757e-05, "epoch": 10.174917491749175, "percentage": 50.87, "elapsed_time": "3:38:59", "remaining_time": "3:31:27", "throughput": 1485.69, "total_tokens": 19520704} {"current_steps": 92495, "total_steps": 181800, "loss": 0.0021, "lr": 2.8585771643064792e-05, "epoch": 10.175467546754675, "percentage": 50.88, "elapsed_time": "3:38:59", "remaining_time": "3:31:26", "throughput": 1485.69, "total_tokens": 19521728} {"current_steps": 92500, "total_steps": 181800, "loss": 0.0405, "lr": 2.8583396374702487e-05, "epoch": 10.176017601760176, "percentage": 50.88, "elapsed_time": "3:39:00", "remaining_time": "3:31:25", "throughput": 1485.7, "total_tokens": 19522784} {"current_steps": 92505, "total_steps": 181800, "loss": 0.0125, "lr": 2.858102107331374e-05, "epoch": 10.176567656765677, "percentage": 50.88, "elapsed_time": "3:39:01", "remaining_time": "3:31:25", "throughput": 1485.7, "total_tokens": 19523872} {"current_steps": 92510, "total_steps": 181800, "loss": 0.0936, "lr": 2.8578645738920444e-05, "epoch": 10.177117711771178, "percentage": 50.89, "elapsed_time": "3:39:01", "remaining_time": "3:31:24", "throughput": 1485.71, "total_tokens": 19524960} {"current_steps": 92515, "total_steps": 181800, "loss": 0.0063, "lr": 2.8576270371544484e-05, "epoch": 10.177667766776677, "percentage": 50.89, "elapsed_time": "3:39:02", "remaining_time": "3:31:23", "throughput": 1485.71, "total_tokens": 19526048} {"current_steps": 92520, "total_steps": 181800, "loss": 0.062, "lr": 2.8573894971207755e-05, "epoch": 10.178217821782178, "percentage": 50.89, "elapsed_time": "3:39:03", "remaining_time": "3:31:22", "throughput": 1485.71, "total_tokens": 19527104} {"current_steps": 92525, "total_steps": 181800, "loss": 0.1549, "lr": 2.857151953793215e-05, "epoch": 10.17876787678768, "percentage": 50.89, "elapsed_time": "3:39:03", "remaining_time": "3:31:22", "throughput": 1485.72, "total_tokens": 19528160} {"current_steps": 92530, "total_steps": 181800, "loss": 0.0678, "lr": 2.856914407173956e-05, "epoch": 10.179317931793179, "percentage": 50.9, "elapsed_time": "3:39:04", "remaining_time": "3:31:21", "throughput": 1485.71, "total_tokens": 19529152} {"current_steps": 92535, "total_steps": 181800, "loss": 0.0026, "lr": 2.8566768572651896e-05, "epoch": 10.17986798679868, "percentage": 50.9, "elapsed_time": "3:39:05", "remaining_time": "3:31:20", "throughput": 1485.71, "total_tokens": 19530176} {"current_steps": 92540, "total_steps": 181800, "loss": 0.0816, "lr": 2.8564393040691027e-05, "epoch": 10.180418041804181, "percentage": 50.9, "elapsed_time": "3:39:06", "remaining_time": "3:31:20", "throughput": 1485.72, "total_tokens": 19531232} {"current_steps": 92545, "total_steps": 181800, "loss": 0.0047, "lr": 2.8562017475878856e-05, "epoch": 10.18096809680968, "percentage": 50.9, "elapsed_time": "3:39:06", "remaining_time": "3:31:19", "throughput": 1485.72, "total_tokens": 19532288} {"current_steps": 92550, "total_steps": 181800, "loss": 0.0222, "lr": 2.855964187823728e-05, "epoch": 10.181518151815181, "percentage": 50.91, "elapsed_time": "3:39:07", "remaining_time": "3:31:18", "throughput": 1485.72, "total_tokens": 19533280} {"current_steps": 92555, "total_steps": 181800, "loss": 0.0845, "lr": 2.85572662477882e-05, "epoch": 10.182068206820682, "percentage": 50.91, "elapsed_time": "3:39:08", "remaining_time": "3:31:17", "throughput": 1485.72, "total_tokens": 19534400} {"current_steps": 92560, "total_steps": 181800, "loss": 0.1129, "lr": 2.8554890584553496e-05, "epoch": 10.182618261826182, "percentage": 50.91, "elapsed_time": "3:39:08", "remaining_time": "3:31:17", "throughput": 1485.72, "total_tokens": 19535424} {"current_steps": 92565, "total_steps": 181800, "loss": 0.0528, "lr": 2.8552514888555078e-05, "epoch": 10.183168316831683, "percentage": 50.92, "elapsed_time": "3:39:09", "remaining_time": "3:31:16", "throughput": 1485.72, "total_tokens": 19536448} {"current_steps": 92570, "total_steps": 181800, "loss": 0.0241, "lr": 2.8550139159814832e-05, "epoch": 10.183718371837184, "percentage": 50.92, "elapsed_time": "3:39:10", "remaining_time": "3:31:15", "throughput": 1485.73, "total_tokens": 19537536} {"current_steps": 92575, "total_steps": 181800, "loss": 0.0069, "lr": 2.854776339835465e-05, "epoch": 10.184268426842685, "percentage": 50.92, "elapsed_time": "3:39:10", "remaining_time": "3:31:14", "throughput": 1485.73, "total_tokens": 19538624} {"current_steps": 92580, "total_steps": 181800, "loss": 0.0847, "lr": 2.854538760419645e-05, "epoch": 10.184818481848184, "percentage": 50.92, "elapsed_time": "3:39:11", "remaining_time": "3:31:14", "throughput": 1485.73, "total_tokens": 19539680} {"current_steps": 92585, "total_steps": 181800, "loss": 0.0078, "lr": 2.85430117773621e-05, "epoch": 10.185368536853685, "percentage": 50.93, "elapsed_time": "3:39:12", "remaining_time": "3:31:13", "throughput": 1485.73, "total_tokens": 19540704} {"current_steps": 92590, "total_steps": 181800, "loss": 0.0064, "lr": 2.8540635917873516e-05, "epoch": 10.185918591859187, "percentage": 50.93, "elapsed_time": "3:39:12", "remaining_time": "3:31:12", "throughput": 1485.73, "total_tokens": 19541760} {"current_steps": 92595, "total_steps": 181800, "loss": 0.0133, "lr": 2.8538260025752588e-05, "epoch": 10.186468646864686, "percentage": 50.93, "elapsed_time": "3:39:13", "remaining_time": "3:31:12", "throughput": 1485.74, "total_tokens": 19542880} {"current_steps": 92600, "total_steps": 181800, "loss": 0.003, "lr": 2.853588410102122e-05, "epoch": 10.187018701870187, "percentage": 50.94, "elapsed_time": "3:39:14", "remaining_time": "3:31:11", "throughput": 1485.74, "total_tokens": 19543872} {"current_steps": 92605, "total_steps": 181800, "loss": 0.0933, "lr": 2.85335081437013e-05, "epoch": 10.187568756875688, "percentage": 50.94, "elapsed_time": "3:39:15", "remaining_time": "3:31:10", "throughput": 1485.74, "total_tokens": 19544928} {"current_steps": 92610, "total_steps": 181800, "loss": 0.0382, "lr": 2.8531132153814732e-05, "epoch": 10.188118811881187, "percentage": 50.94, "elapsed_time": "3:39:15", "remaining_time": "3:31:09", "throughput": 1485.74, "total_tokens": 19545920} {"current_steps": 92615, "total_steps": 181800, "loss": 0.0575, "lr": 2.852875613138341e-05, "epoch": 10.188668866886688, "percentage": 50.94, "elapsed_time": "3:39:16", "remaining_time": "3:31:09", "throughput": 1485.74, "total_tokens": 19546944} {"current_steps": 92620, "total_steps": 181800, "loss": 0.0474, "lr": 2.8526380076429244e-05, "epoch": 10.18921892189219, "percentage": 50.95, "elapsed_time": "3:39:17", "remaining_time": "3:31:08", "throughput": 1485.74, "total_tokens": 19548032} {"current_steps": 92625, "total_steps": 181800, "loss": 0.1688, "lr": 2.852400398897412e-05, "epoch": 10.189768976897689, "percentage": 50.95, "elapsed_time": "3:39:17", "remaining_time": "3:31:07", "throughput": 1485.75, "total_tokens": 19549120} {"current_steps": 92630, "total_steps": 181800, "loss": 0.0221, "lr": 2.852162786903994e-05, "epoch": 10.19031903190319, "percentage": 50.95, "elapsed_time": "3:39:18", "remaining_time": "3:31:06", "throughput": 1485.75, "total_tokens": 19550144} {"current_steps": 92635, "total_steps": 181800, "loss": 0.0143, "lr": 2.851925171664861e-05, "epoch": 10.190869086908691, "percentage": 50.95, "elapsed_time": "3:39:19", "remaining_time": "3:31:06", "throughput": 1485.75, "total_tokens": 19551232} {"current_steps": 92640, "total_steps": 181800, "loss": 0.0141, "lr": 2.851687553182203e-05, "epoch": 10.191419141914192, "percentage": 50.96, "elapsed_time": "3:39:19", "remaining_time": "3:31:05", "throughput": 1485.75, "total_tokens": 19552224} {"current_steps": 92645, "total_steps": 181800, "loss": 0.0059, "lr": 2.8514499314582084e-05, "epoch": 10.191969196919691, "percentage": 50.96, "elapsed_time": "3:39:20", "remaining_time": "3:31:04", "throughput": 1485.75, "total_tokens": 19553248} {"current_steps": 92650, "total_steps": 181800, "loss": 0.0703, "lr": 2.8512123064950697e-05, "epoch": 10.192519251925193, "percentage": 50.96, "elapsed_time": "3:39:21", "remaining_time": "3:31:04", "throughput": 1485.75, "total_tokens": 19554272} {"current_steps": 92655, "total_steps": 181800, "loss": 0.0074, "lr": 2.8509746782949746e-05, "epoch": 10.193069306930694, "percentage": 50.97, "elapsed_time": "3:39:21", "remaining_time": "3:31:03", "throughput": 1485.75, "total_tokens": 19555328} {"current_steps": 92660, "total_steps": 181800, "loss": 0.0612, "lr": 2.8507370468601146e-05, "epoch": 10.193619361936193, "percentage": 50.97, "elapsed_time": "3:39:22", "remaining_time": "3:31:02", "throughput": 1485.76, "total_tokens": 19556384} {"current_steps": 92665, "total_steps": 181800, "loss": 0.0462, "lr": 2.8504994121926797e-05, "epoch": 10.194169416941694, "percentage": 50.97, "elapsed_time": "3:39:23", "remaining_time": "3:31:01", "throughput": 1485.76, "total_tokens": 19557408} {"current_steps": 92670, "total_steps": 181800, "loss": 0.0222, "lr": 2.85026177429486e-05, "epoch": 10.194719471947195, "percentage": 50.97, "elapsed_time": "3:39:23", "remaining_time": "3:31:01", "throughput": 1485.76, "total_tokens": 19558432} {"current_steps": 92675, "total_steps": 181800, "loss": 0.0279, "lr": 2.8500241331688454e-05, "epoch": 10.195269526952695, "percentage": 50.98, "elapsed_time": "3:39:24", "remaining_time": "3:31:00", "throughput": 1485.76, "total_tokens": 19559552} {"current_steps": 92680, "total_steps": 181800, "loss": 0.0486, "lr": 2.8497864888168264e-05, "epoch": 10.195819581958196, "percentage": 50.98, "elapsed_time": "3:39:25", "remaining_time": "3:30:59", "throughput": 1485.77, "total_tokens": 19560672} {"current_steps": 92685, "total_steps": 181800, "loss": 0.0695, "lr": 2.8495488412409933e-05, "epoch": 10.196369636963697, "percentage": 50.98, "elapsed_time": "3:39:26", "remaining_time": "3:30:58", "throughput": 1485.78, "total_tokens": 19561792} {"current_steps": 92690, "total_steps": 181800, "loss": 0.0105, "lr": 2.8493111904435354e-05, "epoch": 10.196919691969198, "percentage": 50.98, "elapsed_time": "3:39:26", "remaining_time": "3:30:58", "throughput": 1485.78, "total_tokens": 19562848} {"current_steps": 92695, "total_steps": 181800, "loss": 0.0171, "lr": 2.8490735364266452e-05, "epoch": 10.197469746974697, "percentage": 50.99, "elapsed_time": "3:39:27", "remaining_time": "3:30:57", "throughput": 1485.78, "total_tokens": 19563936} {"current_steps": 92700, "total_steps": 181800, "loss": 0.0771, "lr": 2.8488358791925107e-05, "epoch": 10.198019801980198, "percentage": 50.99, "elapsed_time": "3:39:28", "remaining_time": "3:30:56", "throughput": 1485.79, "total_tokens": 19565024} {"current_steps": 92705, "total_steps": 181800, "loss": 0.0135, "lr": 2.848598218743324e-05, "epoch": 10.1985698569857, "percentage": 50.99, "elapsed_time": "3:39:28", "remaining_time": "3:30:56", "throughput": 1485.79, "total_tokens": 19566080} {"current_steps": 92710, "total_steps": 181800, "loss": 0.0113, "lr": 2.848360555081275e-05, "epoch": 10.199119911991199, "percentage": 51.0, "elapsed_time": "3:39:29", "remaining_time": "3:30:55", "throughput": 1485.79, "total_tokens": 19567136} {"current_steps": 92715, "total_steps": 181800, "loss": 0.0034, "lr": 2.848122888208553e-05, "epoch": 10.1996699669967, "percentage": 51.0, "elapsed_time": "3:39:30", "remaining_time": "3:30:54", "throughput": 1485.79, "total_tokens": 19568192} {"current_steps": 92720, "total_steps": 181800, "loss": 0.0076, "lr": 2.8478852181273495e-05, "epoch": 10.2002200220022, "percentage": 51.0, "elapsed_time": "3:39:30", "remaining_time": "3:30:53", "throughput": 1485.8, "total_tokens": 19569280} {"current_steps": 92725, "total_steps": 181800, "loss": 0.0141, "lr": 2.847647544839856e-05, "epoch": 10.2007700770077, "percentage": 51.0, "elapsed_time": "3:39:31", "remaining_time": "3:30:53", "throughput": 1485.8, "total_tokens": 19570336} {"current_steps": 92730, "total_steps": 181800, "loss": 0.0222, "lr": 2.84740986834826e-05, "epoch": 10.201320132013201, "percentage": 51.01, "elapsed_time": "3:39:32", "remaining_time": "3:30:52", "throughput": 1485.8, "total_tokens": 19571328} {"current_steps": 92735, "total_steps": 181800, "loss": 0.1933, "lr": 2.8471721886547554e-05, "epoch": 10.201870187018702, "percentage": 51.01, "elapsed_time": "3:39:32", "remaining_time": "3:30:51", "throughput": 1485.8, "total_tokens": 19572352} {"current_steps": 92740, "total_steps": 181800, "loss": 0.0048, "lr": 2.8469345057615308e-05, "epoch": 10.202420242024202, "percentage": 51.01, "elapsed_time": "3:39:33", "remaining_time": "3:30:50", "throughput": 1485.8, "total_tokens": 19573440} {"current_steps": 92745, "total_steps": 181800, "loss": 0.0114, "lr": 2.846696819670778e-05, "epoch": 10.202970297029703, "percentage": 51.01, "elapsed_time": "3:39:34", "remaining_time": "3:30:50", "throughput": 1485.8, "total_tokens": 19574432} {"current_steps": 92750, "total_steps": 181800, "loss": 0.0096, "lr": 2.8464591303846867e-05, "epoch": 10.203520352035204, "percentage": 51.02, "elapsed_time": "3:39:35", "remaining_time": "3:30:49", "throughput": 1485.8, "total_tokens": 19575488} {"current_steps": 92755, "total_steps": 181800, "loss": 0.0329, "lr": 2.8462214379054476e-05, "epoch": 10.204070407040705, "percentage": 51.02, "elapsed_time": "3:39:35", "remaining_time": "3:30:48", "throughput": 1485.8, "total_tokens": 19576512} {"current_steps": 92760, "total_steps": 181800, "loss": 0.0096, "lr": 2.8459837422352507e-05, "epoch": 10.204620462046204, "percentage": 51.02, "elapsed_time": "3:39:36", "remaining_time": "3:30:47", "throughput": 1485.81, "total_tokens": 19577600} {"current_steps": 92765, "total_steps": 181800, "loss": 0.0062, "lr": 2.845746043376289e-05, "epoch": 10.205170517051705, "percentage": 51.03, "elapsed_time": "3:39:37", "remaining_time": "3:30:47", "throughput": 1485.81, "total_tokens": 19578592} {"current_steps": 92770, "total_steps": 181800, "loss": 0.0082, "lr": 2.845508341330752e-05, "epoch": 10.205720572057206, "percentage": 51.03, "elapsed_time": "3:39:37", "remaining_time": "3:30:46", "throughput": 1485.81, "total_tokens": 19579680} {"current_steps": 92775, "total_steps": 181800, "loss": 0.0036, "lr": 2.8452706361008298e-05, "epoch": 10.206270627062706, "percentage": 51.03, "elapsed_time": "3:39:38", "remaining_time": "3:30:45", "throughput": 1485.81, "total_tokens": 19580704} {"current_steps": 92780, "total_steps": 181800, "loss": 0.053, "lr": 2.845032927688714e-05, "epoch": 10.206820682068207, "percentage": 51.03, "elapsed_time": "3:39:39", "remaining_time": "3:30:45", "throughput": 1485.81, "total_tokens": 19581696} {"current_steps": 92785, "total_steps": 181800, "loss": 0.0207, "lr": 2.844795216096595e-05, "epoch": 10.207370737073708, "percentage": 51.04, "elapsed_time": "3:39:39", "remaining_time": "3:30:44", "throughput": 1485.81, "total_tokens": 19582752} {"current_steps": 92790, "total_steps": 181800, "loss": 0.0286, "lr": 2.844557501326664e-05, "epoch": 10.207920792079207, "percentage": 51.04, "elapsed_time": "3:39:40", "remaining_time": "3:30:43", "throughput": 1485.82, "total_tokens": 19583840} {"current_steps": 92795, "total_steps": 181800, "loss": 0.014, "lr": 2.8443197833811126e-05, "epoch": 10.208470847084708, "percentage": 51.04, "elapsed_time": "3:39:41", "remaining_time": "3:30:42", "throughput": 1485.81, "total_tokens": 19584832} {"current_steps": 92800, "total_steps": 181800, "loss": 0.1328, "lr": 2.8440820622621307e-05, "epoch": 10.20902090209021, "percentage": 51.05, "elapsed_time": "3:39:41", "remaining_time": "3:30:42", "throughput": 1485.82, "total_tokens": 19585920} {"current_steps": 92805, "total_steps": 181800, "loss": 0.0482, "lr": 2.8438443379719086e-05, "epoch": 10.209570957095709, "percentage": 51.05, "elapsed_time": "3:39:42", "remaining_time": "3:30:41", "throughput": 1485.82, "total_tokens": 19586976} {"current_steps": 92810, "total_steps": 181800, "loss": 0.0162, "lr": 2.843606610512639e-05, "epoch": 10.21012101210121, "percentage": 51.05, "elapsed_time": "3:39:43", "remaining_time": "3:30:40", "throughput": 1485.83, "total_tokens": 19588096} {"current_steps": 92815, "total_steps": 181800, "loss": 0.0053, "lr": 2.843368879886512e-05, "epoch": 10.210671067106711, "percentage": 51.05, "elapsed_time": "3:39:43", "remaining_time": "3:30:39", "throughput": 1485.83, "total_tokens": 19589088} {"current_steps": 92820, "total_steps": 181800, "loss": 0.0117, "lr": 2.843131146095719e-05, "epoch": 10.211221122112212, "percentage": 51.06, "elapsed_time": "3:39:44", "remaining_time": "3:30:39", "throughput": 1485.83, "total_tokens": 19590112} {"current_steps": 92825, "total_steps": 181800, "loss": 0.026, "lr": 2.842893409142451e-05, "epoch": 10.211771177117711, "percentage": 51.06, "elapsed_time": "3:39:45", "remaining_time": "3:30:38", "throughput": 1485.83, "total_tokens": 19591168} {"current_steps": 92830, "total_steps": 181800, "loss": 0.0095, "lr": 2.8426556690288985e-05, "epoch": 10.212321232123212, "percentage": 51.06, "elapsed_time": "3:39:46", "remaining_time": "3:30:37", "throughput": 1485.83, "total_tokens": 19592192} {"current_steps": 92835, "total_steps": 181800, "loss": 0.0078, "lr": 2.8424179257572525e-05, "epoch": 10.212871287128714, "percentage": 51.06, "elapsed_time": "3:39:46", "remaining_time": "3:30:37", "throughput": 1485.83, "total_tokens": 19593184} {"current_steps": 92840, "total_steps": 181800, "loss": 0.0217, "lr": 2.8421801793297064e-05, "epoch": 10.213421342134213, "percentage": 51.07, "elapsed_time": "3:39:47", "remaining_time": "3:30:36", "throughput": 1485.83, "total_tokens": 19594272} {"current_steps": 92845, "total_steps": 181800, "loss": 0.0165, "lr": 2.8419424297484493e-05, "epoch": 10.213971397139714, "percentage": 51.07, "elapsed_time": "3:39:48", "remaining_time": "3:30:35", "throughput": 1485.83, "total_tokens": 19595232} {"current_steps": 92850, "total_steps": 181800, "loss": 0.0375, "lr": 2.841704677015672e-05, "epoch": 10.214521452145215, "percentage": 51.07, "elapsed_time": "3:39:48", "remaining_time": "3:30:34", "throughput": 1485.83, "total_tokens": 19596256} {"current_steps": 92855, "total_steps": 181800, "loss": 0.138, "lr": 2.8414669211335672e-05, "epoch": 10.215071507150714, "percentage": 51.08, "elapsed_time": "3:39:49", "remaining_time": "3:30:34", "throughput": 1485.83, "total_tokens": 19597280} {"current_steps": 92860, "total_steps": 181800, "loss": 0.0975, "lr": 2.8412291621043257e-05, "epoch": 10.215621562156215, "percentage": 51.08, "elapsed_time": "3:39:50", "remaining_time": "3:30:33", "throughput": 1485.83, "total_tokens": 19598336} {"current_steps": 92865, "total_steps": 181800, "loss": 0.0994, "lr": 2.840991399930139e-05, "epoch": 10.216171617161717, "percentage": 51.08, "elapsed_time": "3:39:50", "remaining_time": "3:30:32", "throughput": 1485.83, "total_tokens": 19599360} {"current_steps": 92870, "total_steps": 181800, "loss": 0.0078, "lr": 2.840753634613198e-05, "epoch": 10.216721672167218, "percentage": 51.08, "elapsed_time": "3:39:51", "remaining_time": "3:30:31", "throughput": 1485.83, "total_tokens": 19600384} {"current_steps": 92875, "total_steps": 181800, "loss": 0.0156, "lr": 2.8405158661556942e-05, "epoch": 10.217271727172717, "percentage": 51.09, "elapsed_time": "3:39:52", "remaining_time": "3:30:31", "throughput": 1485.83, "total_tokens": 19601408} {"current_steps": 92880, "total_steps": 181800, "loss": 0.1319, "lr": 2.8402780945598184e-05, "epoch": 10.217821782178218, "percentage": 51.09, "elapsed_time": "3:39:52", "remaining_time": "3:30:30", "throughput": 1485.83, "total_tokens": 19602464} {"current_steps": 92885, "total_steps": 181800, "loss": 0.0116, "lr": 2.8400403198277638e-05, "epoch": 10.218371837183719, "percentage": 51.09, "elapsed_time": "3:39:53", "remaining_time": "3:30:29", "throughput": 1485.83, "total_tokens": 19603456} {"current_steps": 92890, "total_steps": 181800, "loss": 0.0344, "lr": 2.83980254196172e-05, "epoch": 10.218921892189218, "percentage": 51.09, "elapsed_time": "3:39:54", "remaining_time": "3:30:28", "throughput": 1485.84, "total_tokens": 19604576} {"current_steps": 92895, "total_steps": 181800, "loss": 0.0253, "lr": 2.83956476096388e-05, "epoch": 10.21947194719472, "percentage": 51.1, "elapsed_time": "3:39:54", "remaining_time": "3:30:28", "throughput": 1485.84, "total_tokens": 19605696} {"current_steps": 92900, "total_steps": 181800, "loss": 0.0037, "lr": 2.839326976836434e-05, "epoch": 10.22002200220022, "percentage": 51.1, "elapsed_time": "3:39:55", "remaining_time": "3:30:27", "throughput": 1485.85, "total_tokens": 19606816} {"current_steps": 92905, "total_steps": 181800, "loss": 0.0323, "lr": 2.839089189581574e-05, "epoch": 10.22057205720572, "percentage": 51.1, "elapsed_time": "3:39:56", "remaining_time": "3:30:26", "throughput": 1485.86, "total_tokens": 19607904} {"current_steps": 92910, "total_steps": 181800, "loss": 0.021, "lr": 2.8388513992014908e-05, "epoch": 10.221122112211221, "percentage": 51.11, "elapsed_time": "3:39:57", "remaining_time": "3:30:26", "throughput": 1485.86, "total_tokens": 19608928} {"current_steps": 92915, "total_steps": 181800, "loss": 0.0048, "lr": 2.8386136056983787e-05, "epoch": 10.221672167216722, "percentage": 51.11, "elapsed_time": "3:39:57", "remaining_time": "3:30:25", "throughput": 1485.85, "total_tokens": 19609920} {"current_steps": 92920, "total_steps": 181800, "loss": 0.0489, "lr": 2.8383758090744262e-05, "epoch": 10.222222222222221, "percentage": 51.11, "elapsed_time": "3:39:58", "remaining_time": "3:30:24", "throughput": 1485.86, "total_tokens": 19611008} {"current_steps": 92925, "total_steps": 181800, "loss": 0.0162, "lr": 2.8381380093318265e-05, "epoch": 10.222772277227723, "percentage": 51.11, "elapsed_time": "3:39:59", "remaining_time": "3:30:23", "throughput": 1485.86, "total_tokens": 19612064} {"current_steps": 92930, "total_steps": 181800, "loss": 0.0463, "lr": 2.8379002064727713e-05, "epoch": 10.223322332233224, "percentage": 51.12, "elapsed_time": "3:39:59", "remaining_time": "3:30:23", "throughput": 1485.86, "total_tokens": 19613120} {"current_steps": 92935, "total_steps": 181800, "loss": 0.0427, "lr": 2.8376624004994517e-05, "epoch": 10.223872387238725, "percentage": 51.12, "elapsed_time": "3:40:00", "remaining_time": "3:30:22", "throughput": 1485.87, "total_tokens": 19614208} {"current_steps": 92940, "total_steps": 181800, "loss": 0.0045, "lr": 2.8374245914140603e-05, "epoch": 10.224422442244224, "percentage": 51.12, "elapsed_time": "3:40:01", "remaining_time": "3:30:21", "throughput": 1485.87, "total_tokens": 19615264} {"current_steps": 92945, "total_steps": 181800, "loss": 0.022, "lr": 2.8371867792187877e-05, "epoch": 10.224972497249725, "percentage": 51.12, "elapsed_time": "3:40:01", "remaining_time": "3:30:20", "throughput": 1485.87, "total_tokens": 19616320} {"current_steps": 92950, "total_steps": 181800, "loss": 0.1167, "lr": 2.8369489639158265e-05, "epoch": 10.225522552255226, "percentage": 51.13, "elapsed_time": "3:40:02", "remaining_time": "3:30:20", "throughput": 1485.88, "total_tokens": 19617408} {"current_steps": 92955, "total_steps": 181800, "loss": 0.0796, "lr": 2.8367111455073687e-05, "epoch": 10.226072607260726, "percentage": 51.13, "elapsed_time": "3:40:03", "remaining_time": "3:30:19", "throughput": 1485.89, "total_tokens": 19618528} {"current_steps": 92960, "total_steps": 181800, "loss": 0.127, "lr": 2.8364733239956065e-05, "epoch": 10.226622662266227, "percentage": 51.13, "elapsed_time": "3:40:03", "remaining_time": "3:30:18", "throughput": 1485.89, "total_tokens": 19619552} {"current_steps": 92965, "total_steps": 181800, "loss": 0.1015, "lr": 2.8362354993827296e-05, "epoch": 10.227172717271728, "percentage": 51.14, "elapsed_time": "3:40:04", "remaining_time": "3:30:18", "throughput": 1485.89, "total_tokens": 19620608} {"current_steps": 92970, "total_steps": 181800, "loss": 0.0795, "lr": 2.8359976716709326e-05, "epoch": 10.227722772277227, "percentage": 51.14, "elapsed_time": "3:40:05", "remaining_time": "3:30:17", "throughput": 1485.89, "total_tokens": 19621728} {"current_steps": 92975, "total_steps": 181800, "loss": 0.0484, "lr": 2.8357598408624054e-05, "epoch": 10.228272827282728, "percentage": 51.14, "elapsed_time": "3:40:06", "remaining_time": "3:30:16", "throughput": 1485.9, "total_tokens": 19622816} {"current_steps": 92980, "total_steps": 181800, "loss": 0.0075, "lr": 2.8355220069593407e-05, "epoch": 10.22882288228823, "percentage": 51.14, "elapsed_time": "3:40:06", "remaining_time": "3:30:15", "throughput": 1485.9, "total_tokens": 19623872} {"current_steps": 92985, "total_steps": 181800, "loss": 0.0153, "lr": 2.835284169963932e-05, "epoch": 10.229372937293729, "percentage": 51.15, "elapsed_time": "3:40:07", "remaining_time": "3:30:15", "throughput": 1485.91, "total_tokens": 19624960} {"current_steps": 92990, "total_steps": 181800, "loss": 0.0468, "lr": 2.8350463298783697e-05, "epoch": 10.22992299229923, "percentage": 51.15, "elapsed_time": "3:40:08", "remaining_time": "3:30:14", "throughput": 1485.91, "total_tokens": 19626016} {"current_steps": 92995, "total_steps": 181800, "loss": 0.1187, "lr": 2.834808486704845e-05, "epoch": 10.23047304730473, "percentage": 51.15, "elapsed_time": "3:40:08", "remaining_time": "3:30:13", "throughput": 1485.91, "total_tokens": 19627072} {"current_steps": 93000, "total_steps": 181800, "loss": 0.0634, "lr": 2.834570640445552e-05, "epoch": 10.231023102310232, "percentage": 51.16, "elapsed_time": "3:40:09", "remaining_time": "3:30:12", "throughput": 1485.91, "total_tokens": 19628096} {"current_steps": 93005, "total_steps": 181800, "loss": 0.0061, "lr": 2.834332791102682e-05, "epoch": 10.231573157315731, "percentage": 51.16, "elapsed_time": "3:40:10", "remaining_time": "3:30:12", "throughput": 1485.91, "total_tokens": 19629152} {"current_steps": 93010, "total_steps": 181800, "loss": 0.0612, "lr": 2.8340949386784265e-05, "epoch": 10.232123212321232, "percentage": 51.16, "elapsed_time": "3:40:10", "remaining_time": "3:30:11", "throughput": 1485.91, "total_tokens": 19630176} {"current_steps": 93015, "total_steps": 181800, "loss": 0.0306, "lr": 2.8338570831749787e-05, "epoch": 10.232673267326733, "percentage": 51.16, "elapsed_time": "3:40:11", "remaining_time": "3:30:10", "throughput": 1485.91, "total_tokens": 19631200} {"current_steps": 93020, "total_steps": 181800, "loss": 0.0314, "lr": 2.8336192245945303e-05, "epoch": 10.233223322332233, "percentage": 51.17, "elapsed_time": "3:40:12", "remaining_time": "3:30:09", "throughput": 1485.91, "total_tokens": 19632192} {"current_steps": 93025, "total_steps": 181800, "loss": 0.0057, "lr": 2.8333813629392736e-05, "epoch": 10.233773377337734, "percentage": 51.17, "elapsed_time": "3:40:12", "remaining_time": "3:30:09", "throughput": 1485.91, "total_tokens": 19633216} {"current_steps": 93030, "total_steps": 181800, "loss": 0.0022, "lr": 2.8331434982114012e-05, "epoch": 10.234323432343235, "percentage": 51.17, "elapsed_time": "3:40:13", "remaining_time": "3:30:08", "throughput": 1485.91, "total_tokens": 19634272} {"current_steps": 93035, "total_steps": 181800, "loss": 0.0136, "lr": 2.832905630413104e-05, "epoch": 10.234873487348734, "percentage": 51.17, "elapsed_time": "3:40:14", "remaining_time": "3:30:07", "throughput": 1485.91, "total_tokens": 19635296} {"current_steps": 93040, "total_steps": 181800, "loss": 0.0422, "lr": 2.8326677595465766e-05, "epoch": 10.235423542354235, "percentage": 51.18, "elapsed_time": "3:40:14", "remaining_time": "3:30:07", "throughput": 1485.91, "total_tokens": 19636320} {"current_steps": 93045, "total_steps": 181800, "loss": 0.0425, "lr": 2.8324298856140097e-05, "epoch": 10.235973597359736, "percentage": 51.18, "elapsed_time": "3:40:15", "remaining_time": "3:30:06", "throughput": 1485.92, "total_tokens": 19637408} {"current_steps": 93050, "total_steps": 181800, "loss": 0.0127, "lr": 2.832192008617596e-05, "epoch": 10.236523652365236, "percentage": 51.18, "elapsed_time": "3:40:16", "remaining_time": "3:30:05", "throughput": 1485.92, "total_tokens": 19638464} {"current_steps": 93055, "total_steps": 181800, "loss": 0.0376, "lr": 2.8319541285595276e-05, "epoch": 10.237073707370737, "percentage": 51.19, "elapsed_time": "3:40:17", "remaining_time": "3:30:04", "throughput": 1485.92, "total_tokens": 19639456} {"current_steps": 93060, "total_steps": 181800, "loss": 0.0261, "lr": 2.8317162454419976e-05, "epoch": 10.237623762376238, "percentage": 51.19, "elapsed_time": "3:40:17", "remaining_time": "3:30:04", "throughput": 1485.92, "total_tokens": 19640512} {"current_steps": 93065, "total_steps": 181800, "loss": 0.0053, "lr": 2.8314783592671978e-05, "epoch": 10.238173817381739, "percentage": 51.19, "elapsed_time": "3:40:18", "remaining_time": "3:30:03", "throughput": 1485.92, "total_tokens": 19641504} {"current_steps": 93070, "total_steps": 181800, "loss": 0.0718, "lr": 2.8312404700373212e-05, "epoch": 10.238723872387238, "percentage": 51.19, "elapsed_time": "3:40:19", "remaining_time": "3:30:02", "throughput": 1485.92, "total_tokens": 19642528} {"current_steps": 93075, "total_steps": 181800, "loss": 0.0061, "lr": 2.83100257775456e-05, "epoch": 10.23927392739274, "percentage": 51.2, "elapsed_time": "3:40:19", "remaining_time": "3:30:01", "throughput": 1485.92, "total_tokens": 19643584} {"current_steps": 93080, "total_steps": 181800, "loss": 0.0126, "lr": 2.8307646824211077e-05, "epoch": 10.23982398239824, "percentage": 51.2, "elapsed_time": "3:40:20", "remaining_time": "3:30:01", "throughput": 1485.93, "total_tokens": 19644672} {"current_steps": 93085, "total_steps": 181800, "loss": 0.0473, "lr": 2.8305267840391553e-05, "epoch": 10.24037403740374, "percentage": 51.2, "elapsed_time": "3:40:21", "remaining_time": "3:30:00", "throughput": 1485.93, "total_tokens": 19645728} {"current_steps": 93090, "total_steps": 181800, "loss": 0.0042, "lr": 2.8302888826108964e-05, "epoch": 10.24092409240924, "percentage": 51.2, "elapsed_time": "3:40:21", "remaining_time": "3:29:59", "throughput": 1485.94, "total_tokens": 19646848} {"current_steps": 93095, "total_steps": 181800, "loss": 0.0453, "lr": 2.8300509781385226e-05, "epoch": 10.241474147414742, "percentage": 51.21, "elapsed_time": "3:40:22", "remaining_time": "3:29:59", "throughput": 1485.94, "total_tokens": 19647904} {"current_steps": 93100, "total_steps": 181800, "loss": 0.0832, "lr": 2.8298130706242283e-05, "epoch": 10.242024202420241, "percentage": 51.21, "elapsed_time": "3:40:23", "remaining_time": "3:29:58", "throughput": 1485.94, "total_tokens": 19648960} {"current_steps": 93105, "total_steps": 181800, "loss": 0.0262, "lr": 2.829575160070205e-05, "epoch": 10.242574257425742, "percentage": 51.21, "elapsed_time": "3:40:23", "remaining_time": "3:29:57", "throughput": 1485.94, "total_tokens": 19649984} {"current_steps": 93110, "total_steps": 181800, "loss": 0.0056, "lr": 2.829337246478645e-05, "epoch": 10.243124312431243, "percentage": 51.22, "elapsed_time": "3:40:24", "remaining_time": "3:29:56", "throughput": 1485.94, "total_tokens": 19651072} {"current_steps": 93115, "total_steps": 181800, "loss": 0.0194, "lr": 2.829099329851742e-05, "epoch": 10.243674367436745, "percentage": 51.22, "elapsed_time": "3:40:25", "remaining_time": "3:29:56", "throughput": 1485.94, "total_tokens": 19652064} {"current_steps": 93120, "total_steps": 181800, "loss": 0.0182, "lr": 2.828861410191689e-05, "epoch": 10.244224422442244, "percentage": 51.22, "elapsed_time": "3:40:26", "remaining_time": "3:29:55", "throughput": 1485.94, "total_tokens": 19653088} {"current_steps": 93125, "total_steps": 181800, "loss": 0.0518, "lr": 2.8286234875006773e-05, "epoch": 10.244774477447745, "percentage": 51.22, "elapsed_time": "3:40:26", "remaining_time": "3:29:54", "throughput": 1485.94, "total_tokens": 19654112} {"current_steps": 93130, "total_steps": 181800, "loss": 0.005, "lr": 2.8283855617809012e-05, "epoch": 10.245324532453246, "percentage": 51.23, "elapsed_time": "3:40:27", "remaining_time": "3:29:53", "throughput": 1485.95, "total_tokens": 19655200} {"current_steps": 93135, "total_steps": 181800, "loss": 0.0079, "lr": 2.8281476330345524e-05, "epoch": 10.245874587458745, "percentage": 51.23, "elapsed_time": "3:40:28", "remaining_time": "3:29:53", "throughput": 1485.95, "total_tokens": 19656256} {"current_steps": 93140, "total_steps": 181800, "loss": 0.0692, "lr": 2.8279097012638243e-05, "epoch": 10.246424642464246, "percentage": 51.23, "elapsed_time": "3:40:28", "remaining_time": "3:29:52", "throughput": 1485.96, "total_tokens": 19657344} {"current_steps": 93145, "total_steps": 181800, "loss": 0.0089, "lr": 2.82767176647091e-05, "epoch": 10.246974697469748, "percentage": 51.23, "elapsed_time": "3:40:29", "remaining_time": "3:29:51", "throughput": 1485.95, "total_tokens": 19658336} {"current_steps": 93150, "total_steps": 181800, "loss": 0.0334, "lr": 2.8274338286580034e-05, "epoch": 10.247524752475247, "percentage": 51.24, "elapsed_time": "3:40:30", "remaining_time": "3:29:51", "throughput": 1485.96, "total_tokens": 19659456} {"current_steps": 93155, "total_steps": 181800, "loss": 0.0481, "lr": 2.8271958878272947e-05, "epoch": 10.248074807480748, "percentage": 51.24, "elapsed_time": "3:40:30", "remaining_time": "3:29:50", "throughput": 1485.97, "total_tokens": 19660576} {"current_steps": 93160, "total_steps": 181800, "loss": 0.1452, "lr": 2.826957943980979e-05, "epoch": 10.248624862486249, "percentage": 51.24, "elapsed_time": "3:40:31", "remaining_time": "3:29:49", "throughput": 1485.97, "total_tokens": 19661600} {"current_steps": 93165, "total_steps": 181800, "loss": 0.1073, "lr": 2.8267199971212494e-05, "epoch": 10.249174917491748, "percentage": 51.25, "elapsed_time": "3:40:32", "remaining_time": "3:29:48", "throughput": 1485.97, "total_tokens": 19662656} {"current_steps": 93170, "total_steps": 181800, "loss": 0.0083, "lr": 2.8264820472502973e-05, "epoch": 10.24972497249725, "percentage": 51.25, "elapsed_time": "3:40:32", "remaining_time": "3:29:48", "throughput": 1485.98, "total_tokens": 19663776} {"current_steps": 93175, "total_steps": 181800, "loss": 0.0591, "lr": 2.8262440943703183e-05, "epoch": 10.25027502750275, "percentage": 51.25, "elapsed_time": "3:40:33", "remaining_time": "3:29:47", "throughput": 1485.98, "total_tokens": 19664896} {"current_steps": 93180, "total_steps": 181800, "loss": 0.0046, "lr": 2.826006138483503e-05, "epoch": 10.250825082508252, "percentage": 51.25, "elapsed_time": "3:40:34", "remaining_time": "3:29:46", "throughput": 1485.98, "total_tokens": 19665952} {"current_steps": 93185, "total_steps": 181800, "loss": 0.0509, "lr": 2.8257681795920455e-05, "epoch": 10.251375137513751, "percentage": 51.26, "elapsed_time": "3:40:34", "remaining_time": "3:29:45", "throughput": 1485.99, "total_tokens": 19667008} {"current_steps": 93190, "total_steps": 181800, "loss": 0.1282, "lr": 2.825530217698139e-05, "epoch": 10.251925192519252, "percentage": 51.26, "elapsed_time": "3:40:35", "remaining_time": "3:29:45", "throughput": 1485.99, "total_tokens": 19668096} {"current_steps": 93195, "total_steps": 181800, "loss": 0.0031, "lr": 2.8252922528039772e-05, "epoch": 10.252475247524753, "percentage": 51.26, "elapsed_time": "3:40:36", "remaining_time": "3:29:44", "throughput": 1486.0, "total_tokens": 19669184} {"current_steps": 93200, "total_steps": 181800, "loss": 0.0065, "lr": 2.8250542849117524e-05, "epoch": 10.253025302530252, "percentage": 51.27, "elapsed_time": "3:40:37", "remaining_time": "3:29:43", "throughput": 1486.0, "total_tokens": 19670208} {"current_steps": 93205, "total_steps": 181800, "loss": 0.0509, "lr": 2.8248163140236584e-05, "epoch": 10.253575357535754, "percentage": 51.27, "elapsed_time": "3:40:37", "remaining_time": "3:29:42", "throughput": 1486.0, "total_tokens": 19671264} {"current_steps": 93210, "total_steps": 181800, "loss": 0.0087, "lr": 2.8245783401418885e-05, "epoch": 10.254125412541255, "percentage": 51.27, "elapsed_time": "3:40:38", "remaining_time": "3:29:42", "throughput": 1485.99, "total_tokens": 19672224} {"current_steps": 93215, "total_steps": 181800, "loss": 0.0057, "lr": 2.824340363268635e-05, "epoch": 10.254675467546754, "percentage": 51.27, "elapsed_time": "3:40:39", "remaining_time": "3:29:41", "throughput": 1485.99, "total_tokens": 19673248} {"current_steps": 93220, "total_steps": 181800, "loss": 0.0646, "lr": 2.824102383406093e-05, "epoch": 10.255225522552255, "percentage": 51.28, "elapsed_time": "3:40:39", "remaining_time": "3:29:40", "throughput": 1486.0, "total_tokens": 19674304} {"current_steps": 93225, "total_steps": 181800, "loss": 0.0193, "lr": 2.823864400556454e-05, "epoch": 10.255775577557756, "percentage": 51.28, "elapsed_time": "3:40:40", "remaining_time": "3:29:40", "throughput": 1486.0, "total_tokens": 19675360} {"current_steps": 93230, "total_steps": 181800, "loss": 0.0058, "lr": 2.8236264147219128e-05, "epoch": 10.256325632563255, "percentage": 51.28, "elapsed_time": "3:40:41", "remaining_time": "3:29:39", "throughput": 1486.0, "total_tokens": 19676352} {"current_steps": 93235, "total_steps": 181800, "loss": 0.0024, "lr": 2.8233884259046616e-05, "epoch": 10.256875687568757, "percentage": 51.28, "elapsed_time": "3:40:41", "remaining_time": "3:29:38", "throughput": 1486.0, "total_tokens": 19677408} {"current_steps": 93240, "total_steps": 181800, "loss": 0.0208, "lr": 2.8231504341068953e-05, "epoch": 10.257425742574258, "percentage": 51.29, "elapsed_time": "3:40:42", "remaining_time": "3:29:37", "throughput": 1486.01, "total_tokens": 19678528} {"current_steps": 93245, "total_steps": 181800, "loss": 0.0059, "lr": 2.822912439330806e-05, "epoch": 10.257975797579759, "percentage": 51.29, "elapsed_time": "3:40:43", "remaining_time": "3:29:37", "throughput": 1486.0, "total_tokens": 19679520} {"current_steps": 93250, "total_steps": 181800, "loss": 0.0791, "lr": 2.8226744415785877e-05, "epoch": 10.258525852585258, "percentage": 51.29, "elapsed_time": "3:40:43", "remaining_time": "3:29:36", "throughput": 1486.0, "total_tokens": 19680480} {"current_steps": 93255, "total_steps": 181800, "loss": 0.002, "lr": 2.822436440852434e-05, "epoch": 10.25907590759076, "percentage": 51.3, "elapsed_time": "3:40:44", "remaining_time": "3:29:35", "throughput": 1486.01, "total_tokens": 19681600} {"current_steps": 93260, "total_steps": 181800, "loss": 0.0252, "lr": 2.8221984371545386e-05, "epoch": 10.25962596259626, "percentage": 51.3, "elapsed_time": "3:40:45", "remaining_time": "3:29:34", "throughput": 1486.01, "total_tokens": 19682624} {"current_steps": 93265, "total_steps": 181800, "loss": 0.006, "lr": 2.8219604304870943e-05, "epoch": 10.26017601760176, "percentage": 51.3, "elapsed_time": "3:40:45", "remaining_time": "3:29:34", "throughput": 1486.01, "total_tokens": 19683616} {"current_steps": 93270, "total_steps": 181800, "loss": 0.0976, "lr": 2.8217224208522958e-05, "epoch": 10.26072607260726, "percentage": 51.3, "elapsed_time": "3:40:46", "remaining_time": "3:29:33", "throughput": 1486.01, "total_tokens": 19684672} {"current_steps": 93275, "total_steps": 181800, "loss": 0.0449, "lr": 2.8214844082523357e-05, "epoch": 10.261276127612762, "percentage": 51.31, "elapsed_time": "3:40:47", "remaining_time": "3:29:32", "throughput": 1486.01, "total_tokens": 19685664} {"current_steps": 93280, "total_steps": 181800, "loss": 0.0591, "lr": 2.8212463926894083e-05, "epoch": 10.261826182618261, "percentage": 51.31, "elapsed_time": "3:40:48", "remaining_time": "3:29:32", "throughput": 1486.01, "total_tokens": 19686720} {"current_steps": 93285, "total_steps": 181800, "loss": 0.0554, "lr": 2.821008374165706e-05, "epoch": 10.262376237623762, "percentage": 51.31, "elapsed_time": "3:40:48", "remaining_time": "3:29:31", "throughput": 1486.01, "total_tokens": 19687776} {"current_steps": 93290, "total_steps": 181800, "loss": 0.0129, "lr": 2.820770352683425e-05, "epoch": 10.262926292629263, "percentage": 51.31, "elapsed_time": "3:40:49", "remaining_time": "3:29:30", "throughput": 1486.02, "total_tokens": 19688896} {"current_steps": 93295, "total_steps": 181800, "loss": 0.0021, "lr": 2.8205323282447577e-05, "epoch": 10.263476347634764, "percentage": 51.32, "elapsed_time": "3:40:50", "remaining_time": "3:29:29", "throughput": 1486.02, "total_tokens": 19689952} {"current_steps": 93300, "total_steps": 181800, "loss": 0.0106, "lr": 2.820294300851896e-05, "epoch": 10.264026402640264, "percentage": 51.32, "elapsed_time": "3:40:50", "remaining_time": "3:29:29", "throughput": 1486.02, "total_tokens": 19691040} {"current_steps": 93305, "total_steps": 181800, "loss": 0.0139, "lr": 2.8200562705070373e-05, "epoch": 10.264576457645765, "percentage": 51.32, "elapsed_time": "3:40:51", "remaining_time": "3:29:28", "throughput": 1486.02, "total_tokens": 19692064} {"current_steps": 93310, "total_steps": 181800, "loss": 0.0417, "lr": 2.8198182372123727e-05, "epoch": 10.265126512651266, "percentage": 51.33, "elapsed_time": "3:40:52", "remaining_time": "3:29:27", "throughput": 1486.03, "total_tokens": 19693152} {"current_steps": 93315, "total_steps": 181800, "loss": 0.011, "lr": 2.8195802009700967e-05, "epoch": 10.265676567656765, "percentage": 51.33, "elapsed_time": "3:40:52", "remaining_time": "3:29:26", "throughput": 1486.03, "total_tokens": 19694208} {"current_steps": 93320, "total_steps": 181800, "loss": 0.0873, "lr": 2.8193421617824034e-05, "epoch": 10.266226622662266, "percentage": 51.33, "elapsed_time": "3:40:53", "remaining_time": "3:29:26", "throughput": 1486.04, "total_tokens": 19695328} {"current_steps": 93325, "total_steps": 181800, "loss": 0.0105, "lr": 2.8191041196514873e-05, "epoch": 10.266776677667767, "percentage": 51.33, "elapsed_time": "3:40:54", "remaining_time": "3:29:25", "throughput": 1486.04, "total_tokens": 19696448} {"current_steps": 93330, "total_steps": 181800, "loss": 0.049, "lr": 2.8188660745795404e-05, "epoch": 10.267326732673267, "percentage": 51.34, "elapsed_time": "3:40:54", "remaining_time": "3:29:24", "throughput": 1486.04, "total_tokens": 19697472} {"current_steps": 93335, "total_steps": 181800, "loss": 0.0139, "lr": 2.8186280265687588e-05, "epoch": 10.267876787678768, "percentage": 51.34, "elapsed_time": "3:40:55", "remaining_time": "3:29:24", "throughput": 1486.05, "total_tokens": 19698496} {"current_steps": 93340, "total_steps": 181800, "loss": 0.0605, "lr": 2.8183899756213357e-05, "epoch": 10.268426842684269, "percentage": 51.34, "elapsed_time": "3:40:56", "remaining_time": "3:29:23", "throughput": 1486.05, "total_tokens": 19699520} {"current_steps": 93345, "total_steps": 181800, "loss": 0.0031, "lr": 2.818151921739464e-05, "epoch": 10.268976897689768, "percentage": 51.34, "elapsed_time": "3:40:57", "remaining_time": "3:29:22", "throughput": 1486.04, "total_tokens": 19700544} {"current_steps": 93350, "total_steps": 181800, "loss": 0.0087, "lr": 2.81791386492534e-05, "epoch": 10.26952695269527, "percentage": 51.35, "elapsed_time": "3:40:57", "remaining_time": "3:29:21", "throughput": 1486.04, "total_tokens": 19701568} {"current_steps": 93355, "total_steps": 181800, "loss": 0.0072, "lr": 2.8176758051811558e-05, "epoch": 10.27007700770077, "percentage": 51.35, "elapsed_time": "3:40:58", "remaining_time": "3:29:21", "throughput": 1486.05, "total_tokens": 19702688} {"current_steps": 93360, "total_steps": 181800, "loss": 0.0056, "lr": 2.8174377425091053e-05, "epoch": 10.270627062706271, "percentage": 51.35, "elapsed_time": "3:40:59", "remaining_time": "3:29:20", "throughput": 1486.06, "total_tokens": 19703776} {"current_steps": 93365, "total_steps": 181800, "loss": 0.0018, "lr": 2.817199676911385e-05, "epoch": 10.27117711771177, "percentage": 51.36, "elapsed_time": "3:40:59", "remaining_time": "3:29:19", "throughput": 1486.06, "total_tokens": 19704800} {"current_steps": 93370, "total_steps": 181800, "loss": 0.0387, "lr": 2.8169616083901862e-05, "epoch": 10.271727172717272, "percentage": 51.36, "elapsed_time": "3:41:00", "remaining_time": "3:29:18", "throughput": 1486.06, "total_tokens": 19705888} {"current_steps": 93375, "total_steps": 181800, "loss": 0.0317, "lr": 2.816723536947705e-05, "epoch": 10.272277227722773, "percentage": 51.36, "elapsed_time": "3:41:01", "remaining_time": "3:29:18", "throughput": 1486.07, "total_tokens": 19707008} {"current_steps": 93380, "total_steps": 181800, "loss": 0.0173, "lr": 2.8164854625861355e-05, "epoch": 10.272827282728272, "percentage": 51.36, "elapsed_time": "3:41:01", "remaining_time": "3:29:17", "throughput": 1486.07, "total_tokens": 19708064} {"current_steps": 93385, "total_steps": 181800, "loss": 0.0358, "lr": 2.8162473853076703e-05, "epoch": 10.273377337733773, "percentage": 51.37, "elapsed_time": "3:41:02", "remaining_time": "3:29:16", "throughput": 1486.07, "total_tokens": 19709120} {"current_steps": 93390, "total_steps": 181800, "loss": 0.0417, "lr": 2.8160093051145055e-05, "epoch": 10.273927392739274, "percentage": 51.37, "elapsed_time": "3:41:03", "remaining_time": "3:29:15", "throughput": 1486.08, "total_tokens": 19710208} {"current_steps": 93395, "total_steps": 181800, "loss": 0.0061, "lr": 2.8157712220088338e-05, "epoch": 10.274477447744774, "percentage": 51.37, "elapsed_time": "3:41:03", "remaining_time": "3:29:15", "throughput": 1486.08, "total_tokens": 19711264} {"current_steps": 93400, "total_steps": 181800, "loss": 0.0057, "lr": 2.8155331359928503e-05, "epoch": 10.275027502750275, "percentage": 51.38, "elapsed_time": "3:41:04", "remaining_time": "3:29:14", "throughput": 1486.08, "total_tokens": 19712352} {"current_steps": 93405, "total_steps": 181800, "loss": 0.0581, "lr": 2.81529504706875e-05, "epoch": 10.275577557755776, "percentage": 51.38, "elapsed_time": "3:41:05", "remaining_time": "3:29:13", "throughput": 1486.09, "total_tokens": 19713408} {"current_steps": 93410, "total_steps": 181800, "loss": 0.0062, "lr": 2.8150569552387268e-05, "epoch": 10.276127612761275, "percentage": 51.38, "elapsed_time": "3:41:05", "remaining_time": "3:29:13", "throughput": 1486.09, "total_tokens": 19714496} {"current_steps": 93415, "total_steps": 181800, "loss": 0.059, "lr": 2.8148188605049742e-05, "epoch": 10.276677667766776, "percentage": 51.38, "elapsed_time": "3:41:06", "remaining_time": "3:29:12", "throughput": 1486.09, "total_tokens": 19715520} {"current_steps": 93420, "total_steps": 181800, "loss": 0.1325, "lr": 2.814580762869687e-05, "epoch": 10.277227722772277, "percentage": 51.39, "elapsed_time": "3:41:07", "remaining_time": "3:29:11", "throughput": 1486.09, "total_tokens": 19716544} {"current_steps": 93425, "total_steps": 181800, "loss": 0.0086, "lr": 2.81434266233506e-05, "epoch": 10.277777777777779, "percentage": 51.39, "elapsed_time": "3:41:08", "remaining_time": "3:29:10", "throughput": 1486.1, "total_tokens": 19717600} {"current_steps": 93430, "total_steps": 181800, "loss": 0.002, "lr": 2.814104558903287e-05, "epoch": 10.278327832783278, "percentage": 51.39, "elapsed_time": "3:41:08", "remaining_time": "3:29:10", "throughput": 1486.1, "total_tokens": 19718624} {"current_steps": 93435, "total_steps": 181800, "loss": 0.0029, "lr": 2.8138664525765646e-05, "epoch": 10.278877887788779, "percentage": 51.39, "elapsed_time": "3:41:09", "remaining_time": "3:29:09", "throughput": 1486.1, "total_tokens": 19719648} {"current_steps": 93440, "total_steps": 181800, "loss": 0.056, "lr": 2.8136283433570847e-05, "epoch": 10.27942794279428, "percentage": 51.4, "elapsed_time": "3:41:10", "remaining_time": "3:29:08", "throughput": 1486.1, "total_tokens": 19720768} {"current_steps": 93445, "total_steps": 181800, "loss": 0.0073, "lr": 2.8133902312470428e-05, "epoch": 10.27997799779978, "percentage": 51.4, "elapsed_time": "3:41:10", "remaining_time": "3:29:07", "throughput": 1486.11, "total_tokens": 19721856} {"current_steps": 93450, "total_steps": 181800, "loss": 0.0041, "lr": 2.8131521162486334e-05, "epoch": 10.28052805280528, "percentage": 51.4, "elapsed_time": "3:41:11", "remaining_time": "3:29:07", "throughput": 1486.1, "total_tokens": 19722848} {"current_steps": 93455, "total_steps": 181800, "loss": 0.1177, "lr": 2.812913998364052e-05, "epoch": 10.281078107810782, "percentage": 51.41, "elapsed_time": "3:41:12", "remaining_time": "3:29:06", "throughput": 1486.11, "total_tokens": 19723936} {"current_steps": 93460, "total_steps": 181800, "loss": 0.0217, "lr": 2.8126758775954914e-05, "epoch": 10.281628162816281, "percentage": 51.41, "elapsed_time": "3:41:12", "remaining_time": "3:29:05", "throughput": 1486.11, "total_tokens": 19725024} {"current_steps": 93465, "total_steps": 181800, "loss": 0.0469, "lr": 2.812437753945148e-05, "epoch": 10.282178217821782, "percentage": 51.41, "elapsed_time": "3:41:13", "remaining_time": "3:29:05", "throughput": 1486.11, "total_tokens": 19726016} {"current_steps": 93470, "total_steps": 181800, "loss": 0.0527, "lr": 2.8121996274152153e-05, "epoch": 10.282728272827283, "percentage": 51.41, "elapsed_time": "3:41:14", "remaining_time": "3:29:04", "throughput": 1486.12, "total_tokens": 19727104} {"current_steps": 93475, "total_steps": 181800, "loss": 0.0135, "lr": 2.8119614980078885e-05, "epoch": 10.283278327832782, "percentage": 51.42, "elapsed_time": "3:41:14", "remaining_time": "3:29:03", "throughput": 1486.12, "total_tokens": 19728192} {"current_steps": 93480, "total_steps": 181800, "loss": 0.0294, "lr": 2.8117233657253622e-05, "epoch": 10.283828382838283, "percentage": 51.42, "elapsed_time": "3:41:15", "remaining_time": "3:29:02", "throughput": 1486.13, "total_tokens": 19729312} {"current_steps": 93485, "total_steps": 181800, "loss": 0.1542, "lr": 2.811485230569832e-05, "epoch": 10.284378437843785, "percentage": 51.42, "elapsed_time": "3:41:16", "remaining_time": "3:29:02", "throughput": 1486.13, "total_tokens": 19730336} {"current_steps": 93490, "total_steps": 181800, "loss": 0.0752, "lr": 2.811247092543491e-05, "epoch": 10.284928492849286, "percentage": 51.42, "elapsed_time": "3:41:17", "remaining_time": "3:29:01", "throughput": 1486.13, "total_tokens": 19731360} {"current_steps": 93495, "total_steps": 181800, "loss": 0.0098, "lr": 2.811008951648535e-05, "epoch": 10.285478547854785, "percentage": 51.43, "elapsed_time": "3:41:17", "remaining_time": "3:29:00", "throughput": 1486.13, "total_tokens": 19732384} {"current_steps": 93500, "total_steps": 181800, "loss": 0.0128, "lr": 2.8107708078871592e-05, "epoch": 10.286028602860286, "percentage": 51.43, "elapsed_time": "3:41:18", "remaining_time": "3:28:59", "throughput": 1486.13, "total_tokens": 19733376} {"current_steps": 93505, "total_steps": 181800, "loss": 0.0856, "lr": 2.8105326612615577e-05, "epoch": 10.286578657865787, "percentage": 51.43, "elapsed_time": "3:41:19", "remaining_time": "3:28:59", "throughput": 1486.13, "total_tokens": 19734400} {"current_steps": 93510, "total_steps": 181800, "loss": 0.0923, "lr": 2.810294511773926e-05, "epoch": 10.287128712871286, "percentage": 51.44, "elapsed_time": "3:41:19", "remaining_time": "3:28:58", "throughput": 1486.13, "total_tokens": 19735424} {"current_steps": 93515, "total_steps": 181800, "loss": 0.0104, "lr": 2.810056359426458e-05, "epoch": 10.287678767876788, "percentage": 51.44, "elapsed_time": "3:41:20", "remaining_time": "3:28:57", "throughput": 1486.12, "total_tokens": 19736416} {"current_steps": 93520, "total_steps": 181800, "loss": 0.1431, "lr": 2.8098182042213495e-05, "epoch": 10.288228822882289, "percentage": 51.44, "elapsed_time": "3:41:21", "remaining_time": "3:28:57", "throughput": 1486.13, "total_tokens": 19737472} {"current_steps": 93525, "total_steps": 181800, "loss": 0.1024, "lr": 2.8095800461607958e-05, "epoch": 10.288778877887788, "percentage": 51.44, "elapsed_time": "3:41:21", "remaining_time": "3:28:56", "throughput": 1486.13, "total_tokens": 19738528} {"current_steps": 93530, "total_steps": 181800, "loss": 0.0147, "lr": 2.8093418852469906e-05, "epoch": 10.289328932893289, "percentage": 51.45, "elapsed_time": "3:41:22", "remaining_time": "3:28:55", "throughput": 1486.13, "total_tokens": 19739584} {"current_steps": 93535, "total_steps": 181800, "loss": 0.0551, "lr": 2.80910372148213e-05, "epoch": 10.28987898789879, "percentage": 51.45, "elapsed_time": "3:41:23", "remaining_time": "3:28:54", "throughput": 1486.13, "total_tokens": 19740608} {"current_steps": 93540, "total_steps": 181800, "loss": 0.0247, "lr": 2.808865554868409e-05, "epoch": 10.290429042904291, "percentage": 51.45, "elapsed_time": "3:41:23", "remaining_time": "3:28:54", "throughput": 1486.14, "total_tokens": 19741696} {"current_steps": 93545, "total_steps": 181800, "loss": 0.083, "lr": 2.808627385408022e-05, "epoch": 10.29097909790979, "percentage": 51.45, "elapsed_time": "3:41:24", "remaining_time": "3:28:53", "throughput": 1486.14, "total_tokens": 19742816} {"current_steps": 93550, "total_steps": 181800, "loss": 0.1096, "lr": 2.808389213103165e-05, "epoch": 10.291529152915292, "percentage": 51.46, "elapsed_time": "3:41:25", "remaining_time": "3:28:52", "throughput": 1486.14, "total_tokens": 19743840} {"current_steps": 93555, "total_steps": 181800, "loss": 0.0182, "lr": 2.808151037956033e-05, "epoch": 10.292079207920793, "percentage": 51.46, "elapsed_time": "3:41:25", "remaining_time": "3:28:51", "throughput": 1486.15, "total_tokens": 19744960} {"current_steps": 93560, "total_steps": 181800, "loss": 0.0615, "lr": 2.8079128599688193e-05, "epoch": 10.292629262926292, "percentage": 51.46, "elapsed_time": "3:41:26", "remaining_time": "3:28:51", "throughput": 1486.15, "total_tokens": 19746048} {"current_steps": 93565, "total_steps": 181800, "loss": 0.0481, "lr": 2.8076746791437216e-05, "epoch": 10.293179317931793, "percentage": 51.47, "elapsed_time": "3:41:27", "remaining_time": "3:28:50", "throughput": 1486.16, "total_tokens": 19747136} {"current_steps": 93570, "total_steps": 181800, "loss": 0.0102, "lr": 2.8074364954829337e-05, "epoch": 10.293729372937294, "percentage": 51.47, "elapsed_time": "3:41:28", "remaining_time": "3:28:49", "throughput": 1486.16, "total_tokens": 19748192} {"current_steps": 93575, "total_steps": 181800, "loss": 0.0046, "lr": 2.8071983089886505e-05, "epoch": 10.294279427942794, "percentage": 51.47, "elapsed_time": "3:41:28", "remaining_time": "3:28:48", "throughput": 1486.16, "total_tokens": 19749184} {"current_steps": 93580, "total_steps": 181800, "loss": 0.0109, "lr": 2.806960119663069e-05, "epoch": 10.294829482948295, "percentage": 51.47, "elapsed_time": "3:41:29", "remaining_time": "3:28:48", "throughput": 1486.16, "total_tokens": 19750208} {"current_steps": 93585, "total_steps": 181800, "loss": 0.0414, "lr": 2.806721927508383e-05, "epoch": 10.295379537953796, "percentage": 51.48, "elapsed_time": "3:41:30", "remaining_time": "3:28:47", "throughput": 1486.16, "total_tokens": 19751296} {"current_steps": 93590, "total_steps": 181800, "loss": 0.1333, "lr": 2.8064837325267872e-05, "epoch": 10.295929592959295, "percentage": 51.48, "elapsed_time": "3:41:30", "remaining_time": "3:28:46", "throughput": 1486.16, "total_tokens": 19752288} {"current_steps": 93595, "total_steps": 181800, "loss": 0.008, "lr": 2.806245534720479e-05, "epoch": 10.296479647964796, "percentage": 51.48, "elapsed_time": "3:41:31", "remaining_time": "3:28:46", "throughput": 1486.16, "total_tokens": 19753344} {"current_steps": 93600, "total_steps": 181800, "loss": 0.0068, "lr": 2.8060073340916533e-05, "epoch": 10.297029702970297, "percentage": 51.49, "elapsed_time": "3:41:32", "remaining_time": "3:28:45", "throughput": 1486.17, "total_tokens": 19754400} {"current_steps": 93605, "total_steps": 181800, "loss": 0.0707, "lr": 2.8057691306425034e-05, "epoch": 10.297579757975798, "percentage": 51.49, "elapsed_time": "3:41:32", "remaining_time": "3:28:44", "throughput": 1486.17, "total_tokens": 19755456} {"current_steps": 93610, "total_steps": 181800, "loss": 0.0041, "lr": 2.805530924375227e-05, "epoch": 10.298129812981298, "percentage": 51.49, "elapsed_time": "3:41:33", "remaining_time": "3:28:43", "throughput": 1486.18, "total_tokens": 19756576} {"current_steps": 93615, "total_steps": 181800, "loss": 0.0385, "lr": 2.805292715292018e-05, "epoch": 10.298679867986799, "percentage": 51.49, "elapsed_time": "3:41:34", "remaining_time": "3:28:43", "throughput": 1486.18, "total_tokens": 19757600} {"current_steps": 93620, "total_steps": 181800, "loss": 0.0123, "lr": 2.8050545033950725e-05, "epoch": 10.2992299229923, "percentage": 51.5, "elapsed_time": "3:41:34", "remaining_time": "3:28:42", "throughput": 1486.18, "total_tokens": 19758656} {"current_steps": 93625, "total_steps": 181800, "loss": 0.0358, "lr": 2.804816288686587e-05, "epoch": 10.2997799779978, "percentage": 51.5, "elapsed_time": "3:41:35", "remaining_time": "3:28:41", "throughput": 1486.18, "total_tokens": 19759680} {"current_steps": 93630, "total_steps": 181800, "loss": 0.012, "lr": 2.804578071168756e-05, "epoch": 10.3003300330033, "percentage": 51.5, "elapsed_time": "3:41:36", "remaining_time": "3:28:40", "throughput": 1486.18, "total_tokens": 19760672} {"current_steps": 93635, "total_steps": 181800, "loss": 0.0068, "lr": 2.804339850843774e-05, "epoch": 10.300880088008801, "percentage": 51.5, "elapsed_time": "3:41:37", "remaining_time": "3:28:40", "throughput": 1486.18, "total_tokens": 19761728} {"current_steps": 93640, "total_steps": 181800, "loss": 0.0123, "lr": 2.804101627713838e-05, "epoch": 10.3014301430143, "percentage": 51.51, "elapsed_time": "3:41:37", "remaining_time": "3:28:39", "throughput": 1486.18, "total_tokens": 19762752} {"current_steps": 93645, "total_steps": 181800, "loss": 0.0076, "lr": 2.803863401781144e-05, "epoch": 10.301980198019802, "percentage": 51.51, "elapsed_time": "3:41:38", "remaining_time": "3:28:38", "throughput": 1486.18, "total_tokens": 19763840} {"current_steps": 93650, "total_steps": 181800, "loss": 0.0268, "lr": 2.8036251730478856e-05, "epoch": 10.302530253025303, "percentage": 51.51, "elapsed_time": "3:41:39", "remaining_time": "3:28:38", "throughput": 1486.19, "total_tokens": 19764960} {"current_steps": 93655, "total_steps": 181800, "loss": 0.0424, "lr": 2.8033869415162606e-05, "epoch": 10.303080308030804, "percentage": 51.52, "elapsed_time": "3:41:39", "remaining_time": "3:28:37", "throughput": 1486.19, "total_tokens": 19766016} {"current_steps": 93660, "total_steps": 181800, "loss": 0.2851, "lr": 2.803148707188464e-05, "epoch": 10.303630363036303, "percentage": 51.52, "elapsed_time": "3:41:40", "remaining_time": "3:28:36", "throughput": 1486.2, "total_tokens": 19767072} {"current_steps": 93665, "total_steps": 181800, "loss": 0.0235, "lr": 2.8029104700666897e-05, "epoch": 10.304180418041804, "percentage": 51.52, "elapsed_time": "3:41:41", "remaining_time": "3:28:35", "throughput": 1486.19, "total_tokens": 19768064} {"current_steps": 93670, "total_steps": 181800, "loss": 0.0099, "lr": 2.802672230153136e-05, "epoch": 10.304730473047305, "percentage": 51.52, "elapsed_time": "3:41:41", "remaining_time": "3:28:35", "throughput": 1486.2, "total_tokens": 19769216} {"current_steps": 93675, "total_steps": 181800, "loss": 0.0118, "lr": 2.8024339874499978e-05, "epoch": 10.305280528052805, "percentage": 51.53, "elapsed_time": "3:41:42", "remaining_time": "3:28:34", "throughput": 1486.21, "total_tokens": 19770336} {"current_steps": 93680, "total_steps": 181800, "loss": 0.0401, "lr": 2.8021957419594704e-05, "epoch": 10.305830583058306, "percentage": 51.53, "elapsed_time": "3:41:43", "remaining_time": "3:28:33", "throughput": 1486.21, "total_tokens": 19771392} {"current_steps": 93685, "total_steps": 181800, "loss": 0.0798, "lr": 2.8019574936837502e-05, "epoch": 10.306380638063807, "percentage": 51.53, "elapsed_time": "3:41:43", "remaining_time": "3:28:32", "throughput": 1486.22, "total_tokens": 19772480} {"current_steps": 93690, "total_steps": 181800, "loss": 0.0334, "lr": 2.801719242625032e-05, "epoch": 10.306930693069306, "percentage": 51.53, "elapsed_time": "3:41:44", "remaining_time": "3:28:32", "throughput": 1486.22, "total_tokens": 19773504} {"current_steps": 93695, "total_steps": 181800, "loss": 0.0088, "lr": 2.8014809887855127e-05, "epoch": 10.307480748074807, "percentage": 51.54, "elapsed_time": "3:41:45", "remaining_time": "3:28:31", "throughput": 1486.22, "total_tokens": 19774528} {"current_steps": 93700, "total_steps": 181800, "loss": 0.041, "lr": 2.8012427321673877e-05, "epoch": 10.308030803080309, "percentage": 51.54, "elapsed_time": "3:41:45", "remaining_time": "3:28:30", "throughput": 1486.22, "total_tokens": 19775616} {"current_steps": 93705, "total_steps": 181800, "loss": 0.0917, "lr": 2.8010044727728524e-05, "epoch": 10.308580858085808, "percentage": 51.54, "elapsed_time": "3:41:46", "remaining_time": "3:28:30", "throughput": 1486.22, "total_tokens": 19776640} {"current_steps": 93710, "total_steps": 181800, "loss": 0.014, "lr": 2.8007662106041043e-05, "epoch": 10.309130913091309, "percentage": 51.55, "elapsed_time": "3:41:47", "remaining_time": "3:28:29", "throughput": 1486.22, "total_tokens": 19777696} {"current_steps": 93715, "total_steps": 181800, "loss": 0.1392, "lr": 2.8005279456633375e-05, "epoch": 10.30968096809681, "percentage": 51.55, "elapsed_time": "3:41:48", "remaining_time": "3:28:28", "throughput": 1486.22, "total_tokens": 19778688} {"current_steps": 93720, "total_steps": 181800, "loss": 0.0079, "lr": 2.80028967795275e-05, "epoch": 10.310231023102311, "percentage": 51.55, "elapsed_time": "3:41:48", "remaining_time": "3:28:27", "throughput": 1486.22, "total_tokens": 19779744} {"current_steps": 93725, "total_steps": 181800, "loss": 0.008, "lr": 2.8000514074745354e-05, "epoch": 10.31078107810781, "percentage": 51.55, "elapsed_time": "3:41:49", "remaining_time": "3:28:27", "throughput": 1486.22, "total_tokens": 19780736} {"current_steps": 93730, "total_steps": 181800, "loss": 0.0155, "lr": 2.799813134230892e-05, "epoch": 10.311331133113312, "percentage": 51.56, "elapsed_time": "3:41:50", "remaining_time": "3:28:26", "throughput": 1486.23, "total_tokens": 19781856} {"current_steps": 93735, "total_steps": 181800, "loss": 0.0835, "lr": 2.799574858224014e-05, "epoch": 10.311881188118813, "percentage": 51.56, "elapsed_time": "3:41:50", "remaining_time": "3:28:25", "throughput": 1486.23, "total_tokens": 19782880} {"current_steps": 93740, "total_steps": 181800, "loss": 0.0372, "lr": 2.7993365794560984e-05, "epoch": 10.312431243124312, "percentage": 51.56, "elapsed_time": "3:41:51", "remaining_time": "3:28:24", "throughput": 1486.23, "total_tokens": 19783904} {"current_steps": 93745, "total_steps": 181800, "loss": 0.0077, "lr": 2.7990982979293416e-05, "epoch": 10.312981298129813, "percentage": 51.56, "elapsed_time": "3:41:52", "remaining_time": "3:28:24", "throughput": 1486.23, "total_tokens": 19784960} {"current_steps": 93750, "total_steps": 181800, "loss": 0.0745, "lr": 2.7988600136459388e-05, "epoch": 10.313531353135314, "percentage": 51.57, "elapsed_time": "3:41:52", "remaining_time": "3:28:23", "throughput": 1486.23, "total_tokens": 19786016} {"current_steps": 93755, "total_steps": 181800, "loss": 0.028, "lr": 2.7986217266080872e-05, "epoch": 10.314081408140813, "percentage": 51.57, "elapsed_time": "3:41:53", "remaining_time": "3:28:22", "throughput": 1486.23, "total_tokens": 19787040} {"current_steps": 93760, "total_steps": 181800, "loss": 0.1488, "lr": 2.7983834368179822e-05, "epoch": 10.314631463146315, "percentage": 51.57, "elapsed_time": "3:41:54", "remaining_time": "3:28:21", "throughput": 1486.23, "total_tokens": 19788032} {"current_steps": 93765, "total_steps": 181800, "loss": 0.0648, "lr": 2.7981451442778195e-05, "epoch": 10.315181518151816, "percentage": 51.58, "elapsed_time": "3:41:54", "remaining_time": "3:28:21", "throughput": 1486.23, "total_tokens": 19789120} {"current_steps": 93770, "total_steps": 181800, "loss": 0.0089, "lr": 2.7979068489897975e-05, "epoch": 10.315731573157315, "percentage": 51.58, "elapsed_time": "3:41:55", "remaining_time": "3:28:20", "throughput": 1486.24, "total_tokens": 19790208} {"current_steps": 93775, "total_steps": 181800, "loss": 0.0042, "lr": 2.7976685509561108e-05, "epoch": 10.316281628162816, "percentage": 51.58, "elapsed_time": "3:41:56", "remaining_time": "3:28:19", "throughput": 1486.24, "total_tokens": 19791264} {"current_steps": 93780, "total_steps": 181800, "loss": 0.1283, "lr": 2.7974302501789544e-05, "epoch": 10.316831683168317, "percentage": 51.58, "elapsed_time": "3:41:57", "remaining_time": "3:28:19", "throughput": 1486.24, "total_tokens": 19792288} {"current_steps": 93785, "total_steps": 181800, "loss": 0.1552, "lr": 2.7971919466605274e-05, "epoch": 10.317381738173818, "percentage": 51.59, "elapsed_time": "3:41:57", "remaining_time": "3:28:18", "throughput": 1486.24, "total_tokens": 19793312} {"current_steps": 93790, "total_steps": 181800, "loss": 0.0154, "lr": 2.7969536404030246e-05, "epoch": 10.317931793179318, "percentage": 51.59, "elapsed_time": "3:41:58", "remaining_time": "3:28:17", "throughput": 1486.25, "total_tokens": 19794400} {"current_steps": 93795, "total_steps": 181800, "loss": 0.021, "lr": 2.7967153314086424e-05, "epoch": 10.318481848184819, "percentage": 51.59, "elapsed_time": "3:41:59", "remaining_time": "3:28:16", "throughput": 1486.25, "total_tokens": 19795424} {"current_steps": 93800, "total_steps": 181800, "loss": 0.0066, "lr": 2.7964770196795774e-05, "epoch": 10.31903190319032, "percentage": 51.6, "elapsed_time": "3:41:59", "remaining_time": "3:28:16", "throughput": 1486.25, "total_tokens": 19796480} {"current_steps": 93805, "total_steps": 181800, "loss": 0.0135, "lr": 2.7962387052180268e-05, "epoch": 10.319581958195819, "percentage": 51.6, "elapsed_time": "3:42:00", "remaining_time": "3:28:15", "throughput": 1486.25, "total_tokens": 19797504} {"current_steps": 93810, "total_steps": 181800, "loss": 0.0205, "lr": 2.7960003880261848e-05, "epoch": 10.32013201320132, "percentage": 51.6, "elapsed_time": "3:42:01", "remaining_time": "3:28:14", "throughput": 1486.25, "total_tokens": 19798528} {"current_steps": 93815, "total_steps": 181800, "loss": 0.0771, "lr": 2.7957620681062502e-05, "epoch": 10.320682068206821, "percentage": 51.6, "elapsed_time": "3:42:01", "remaining_time": "3:28:13", "throughput": 1486.25, "total_tokens": 19799616} {"current_steps": 93820, "total_steps": 181800, "loss": 0.0143, "lr": 2.7955237454604176e-05, "epoch": 10.32123212321232, "percentage": 51.61, "elapsed_time": "3:42:02", "remaining_time": "3:28:13", "throughput": 1486.26, "total_tokens": 19800704} {"current_steps": 93825, "total_steps": 181800, "loss": 0.0052, "lr": 2.7952854200908858e-05, "epoch": 10.321782178217822, "percentage": 51.61, "elapsed_time": "3:42:03", "remaining_time": "3:28:12", "throughput": 1486.26, "total_tokens": 19801728} {"current_steps": 93830, "total_steps": 181800, "loss": 0.0276, "lr": 2.795047091999849e-05, "epoch": 10.322332233223323, "percentage": 51.61, "elapsed_time": "3:42:03", "remaining_time": "3:28:11", "throughput": 1486.27, "total_tokens": 19802848} {"current_steps": 93835, "total_steps": 181800, "loss": 0.0046, "lr": 2.794808761189505e-05, "epoch": 10.322882288228822, "percentage": 51.61, "elapsed_time": "3:42:04", "remaining_time": "3:28:11", "throughput": 1486.27, "total_tokens": 19803968} {"current_steps": 93840, "total_steps": 181800, "loss": 0.0331, "lr": 2.7945704276620503e-05, "epoch": 10.323432343234323, "percentage": 51.62, "elapsed_time": "3:42:05", "remaining_time": "3:28:10", "throughput": 1486.27, "total_tokens": 19804992} {"current_steps": 93845, "total_steps": 181800, "loss": 0.0045, "lr": 2.7943320914196814e-05, "epoch": 10.323982398239824, "percentage": 51.62, "elapsed_time": "3:42:05", "remaining_time": "3:28:09", "throughput": 1486.27, "total_tokens": 19806016} {"current_steps": 93850, "total_steps": 181800, "loss": 0.0025, "lr": 2.794093752464594e-05, "epoch": 10.324532453245325, "percentage": 51.62, "elapsed_time": "3:42:06", "remaining_time": "3:28:08", "throughput": 1486.28, "total_tokens": 19807136} {"current_steps": 93855, "total_steps": 181800, "loss": 0.016, "lr": 2.793855410798986e-05, "epoch": 10.325082508250825, "percentage": 51.63, "elapsed_time": "3:42:07", "remaining_time": "3:28:08", "throughput": 1486.28, "total_tokens": 19808224} {"current_steps": 93860, "total_steps": 181800, "loss": 0.0163, "lr": 2.7936170664250545e-05, "epoch": 10.325632563256326, "percentage": 51.63, "elapsed_time": "3:42:08", "remaining_time": "3:28:07", "throughput": 1486.28, "total_tokens": 19809248} {"current_steps": 93865, "total_steps": 181800, "loss": 0.03, "lr": 2.7933787193449946e-05, "epoch": 10.326182618261827, "percentage": 51.63, "elapsed_time": "3:42:08", "remaining_time": "3:28:06", "throughput": 1486.29, "total_tokens": 19810336} {"current_steps": 93870, "total_steps": 181800, "loss": 0.0069, "lr": 2.7931403695610043e-05, "epoch": 10.326732673267326, "percentage": 51.63, "elapsed_time": "3:42:09", "remaining_time": "3:28:05", "throughput": 1486.29, "total_tokens": 19811424} {"current_steps": 93875, "total_steps": 181800, "loss": 0.0431, "lr": 2.7929020170752797e-05, "epoch": 10.327282728272827, "percentage": 51.64, "elapsed_time": "3:42:10", "remaining_time": "3:28:05", "throughput": 1486.3, "total_tokens": 19812480} {"current_steps": 93880, "total_steps": 181800, "loss": 0.0124, "lr": 2.792663661890017e-05, "epoch": 10.327832783278328, "percentage": 51.64, "elapsed_time": "3:42:10", "remaining_time": "3:28:04", "throughput": 1486.29, "total_tokens": 19813504} {"current_steps": 93885, "total_steps": 181800, "loss": 0.0074, "lr": 2.792425304007415e-05, "epoch": 10.328382838283828, "percentage": 51.64, "elapsed_time": "3:42:11", "remaining_time": "3:28:03", "throughput": 1486.3, "total_tokens": 19814560} {"current_steps": 93890, "total_steps": 181800, "loss": 0.0163, "lr": 2.792186943429669e-05, "epoch": 10.328932893289329, "percentage": 51.64, "elapsed_time": "3:42:12", "remaining_time": "3:28:03", "throughput": 1486.3, "total_tokens": 19815584} {"current_steps": 93895, "total_steps": 181800, "loss": 0.0043, "lr": 2.791948580158975e-05, "epoch": 10.32948294829483, "percentage": 51.65, "elapsed_time": "3:42:12", "remaining_time": "3:28:02", "throughput": 1486.3, "total_tokens": 19816640} {"current_steps": 93900, "total_steps": 181800, "loss": 0.0813, "lr": 2.7917102141975322e-05, "epoch": 10.33003300330033, "percentage": 51.65, "elapsed_time": "3:42:13", "remaining_time": "3:28:01", "throughput": 1486.31, "total_tokens": 19817760} {"current_steps": 93905, "total_steps": 181800, "loss": 0.0413, "lr": 2.7914718455475357e-05, "epoch": 10.33058305830583, "percentage": 51.65, "elapsed_time": "3:42:14", "remaining_time": "3:28:00", "throughput": 1486.3, "total_tokens": 19818720} {"current_steps": 93910, "total_steps": 181800, "loss": 0.0505, "lr": 2.7912334742111833e-05, "epoch": 10.331133113311331, "percentage": 51.66, "elapsed_time": "3:42:14", "remaining_time": "3:28:00", "throughput": 1486.3, "total_tokens": 19819744} {"current_steps": 93915, "total_steps": 181800, "loss": 0.0111, "lr": 2.790995100190672e-05, "epoch": 10.331683168316832, "percentage": 51.66, "elapsed_time": "3:42:15", "remaining_time": "3:27:59", "throughput": 1486.3, "total_tokens": 19820768} {"current_steps": 93920, "total_steps": 181800, "loss": 0.008, "lr": 2.7907567234881982e-05, "epoch": 10.332233223322332, "percentage": 51.66, "elapsed_time": "3:42:16", "remaining_time": "3:27:58", "throughput": 1486.3, "total_tokens": 19821824} {"current_steps": 93925, "total_steps": 181800, "loss": 0.0112, "lr": 2.7905183441059592e-05, "epoch": 10.332783278327833, "percentage": 51.66, "elapsed_time": "3:42:17", "remaining_time": "3:27:57", "throughput": 1486.3, "total_tokens": 19822848} {"current_steps": 93930, "total_steps": 181800, "loss": 0.0249, "lr": 2.7902799620461518e-05, "epoch": 10.333333333333334, "percentage": 51.67, "elapsed_time": "3:42:17", "remaining_time": "3:27:57", "throughput": 1486.3, "total_tokens": 19823872} {"current_steps": 93935, "total_steps": 181800, "loss": 0.1211, "lr": 2.7900415773109745e-05, "epoch": 10.333883388338833, "percentage": 51.67, "elapsed_time": "3:42:18", "remaining_time": "3:27:56", "throughput": 1486.3, "total_tokens": 19824896} {"current_steps": 93940, "total_steps": 181800, "loss": 0.0065, "lr": 2.7898031899026216e-05, "epoch": 10.334433443344334, "percentage": 51.67, "elapsed_time": "3:42:19", "remaining_time": "3:27:55", "throughput": 1486.31, "total_tokens": 19825984} {"current_steps": 93945, "total_steps": 181800, "loss": 0.0122, "lr": 2.7895647998232922e-05, "epoch": 10.334983498349835, "percentage": 51.67, "elapsed_time": "3:42:19", "remaining_time": "3:27:55", "throughput": 1486.32, "total_tokens": 19827104} {"current_steps": 93950, "total_steps": 181800, "loss": 0.0053, "lr": 2.7893264070751833e-05, "epoch": 10.335533553355335, "percentage": 51.68, "elapsed_time": "3:42:20", "remaining_time": "3:27:54", "throughput": 1486.32, "total_tokens": 19828160} {"current_steps": 93955, "total_steps": 181800, "loss": 0.0295, "lr": 2.7890880116604913e-05, "epoch": 10.336083608360836, "percentage": 51.68, "elapsed_time": "3:42:21", "remaining_time": "3:27:53", "throughput": 1486.32, "total_tokens": 19829152} {"current_steps": 93960, "total_steps": 181800, "loss": 0.2028, "lr": 2.7888496135814145e-05, "epoch": 10.336633663366337, "percentage": 51.68, "elapsed_time": "3:42:21", "remaining_time": "3:27:52", "throughput": 1486.31, "total_tokens": 19830176} {"current_steps": 93965, "total_steps": 181800, "loss": 0.0176, "lr": 2.7886112128401494e-05, "epoch": 10.337183718371838, "percentage": 51.69, "elapsed_time": "3:42:22", "remaining_time": "3:27:52", "throughput": 1486.32, "total_tokens": 19831264} {"current_steps": 93970, "total_steps": 181800, "loss": 0.0433, "lr": 2.7883728094388922e-05, "epoch": 10.337733773377337, "percentage": 51.69, "elapsed_time": "3:42:23", "remaining_time": "3:27:51", "throughput": 1486.32, "total_tokens": 19832288} {"current_steps": 93975, "total_steps": 181800, "loss": 0.0692, "lr": 2.7881344033798418e-05, "epoch": 10.338283828382838, "percentage": 51.69, "elapsed_time": "3:42:23", "remaining_time": "3:27:50", "throughput": 1486.32, "total_tokens": 19833344} {"current_steps": 93980, "total_steps": 181800, "loss": 0.0556, "lr": 2.787895994665195e-05, "epoch": 10.33883388338834, "percentage": 51.69, "elapsed_time": "3:42:24", "remaining_time": "3:27:49", "throughput": 1486.32, "total_tokens": 19834368} {"current_steps": 93985, "total_steps": 181800, "loss": 0.0096, "lr": 2.787657583297149e-05, "epoch": 10.339383938393839, "percentage": 51.7, "elapsed_time": "3:42:25", "remaining_time": "3:27:49", "throughput": 1486.32, "total_tokens": 19835392} {"current_steps": 93990, "total_steps": 181800, "loss": 0.0144, "lr": 2.7874191692779012e-05, "epoch": 10.33993399339934, "percentage": 51.7, "elapsed_time": "3:42:25", "remaining_time": "3:27:48", "throughput": 1486.32, "total_tokens": 19836352} {"current_steps": 93995, "total_steps": 181800, "loss": 0.0072, "lr": 2.787180752609649e-05, "epoch": 10.340484048404841, "percentage": 51.7, "elapsed_time": "3:42:26", "remaining_time": "3:27:47", "throughput": 1486.32, "total_tokens": 19837408} {"current_steps": 94000, "total_steps": 181800, "loss": 0.0088, "lr": 2.7869423332945887e-05, "epoch": 10.34103410341034, "percentage": 51.71, "elapsed_time": "3:42:27", "remaining_time": "3:27:46", "throughput": 1486.33, "total_tokens": 19838528} {"current_steps": 94005, "total_steps": 181800, "loss": 0.0305, "lr": 2.7867039113349196e-05, "epoch": 10.341584158415841, "percentage": 51.71, "elapsed_time": "3:42:28", "remaining_time": "3:27:46", "throughput": 1486.33, "total_tokens": 19839552} {"current_steps": 94010, "total_steps": 181800, "loss": 0.0747, "lr": 2.786465486732837e-05, "epoch": 10.342134213421343, "percentage": 51.71, "elapsed_time": "3:42:28", "remaining_time": "3:27:45", "throughput": 1486.33, "total_tokens": 19840576} {"current_steps": 94015, "total_steps": 181800, "loss": 0.0075, "lr": 2.7862270594905405e-05, "epoch": 10.342684268426842, "percentage": 51.71, "elapsed_time": "3:42:29", "remaining_time": "3:27:44", "throughput": 1486.33, "total_tokens": 19841600} {"current_steps": 94020, "total_steps": 181800, "loss": 0.1077, "lr": 2.785988629610226e-05, "epoch": 10.343234323432343, "percentage": 51.72, "elapsed_time": "3:42:30", "remaining_time": "3:27:44", "throughput": 1486.34, "total_tokens": 19842720} {"current_steps": 94025, "total_steps": 181800, "loss": 0.0401, "lr": 2.785750197094092e-05, "epoch": 10.343784378437844, "percentage": 51.72, "elapsed_time": "3:42:30", "remaining_time": "3:27:43", "throughput": 1486.34, "total_tokens": 19843744} {"current_steps": 94030, "total_steps": 181800, "loss": 0.0193, "lr": 2.785511761944335e-05, "epoch": 10.344334433443345, "percentage": 51.72, "elapsed_time": "3:42:31", "remaining_time": "3:27:42", "throughput": 1486.33, "total_tokens": 19844736} {"current_steps": 94035, "total_steps": 181800, "loss": 0.0972, "lr": 2.7852733241631536e-05, "epoch": 10.344884488448844, "percentage": 51.72, "elapsed_time": "3:42:32", "remaining_time": "3:27:41", "throughput": 1486.34, "total_tokens": 19845856} {"current_steps": 94040, "total_steps": 181800, "loss": 0.0065, "lr": 2.785034883752744e-05, "epoch": 10.345434543454346, "percentage": 51.73, "elapsed_time": "3:42:32", "remaining_time": "3:27:41", "throughput": 1486.34, "total_tokens": 19846912} {"current_steps": 94045, "total_steps": 181800, "loss": 0.1064, "lr": 2.7847964407153054e-05, "epoch": 10.345984598459847, "percentage": 51.73, "elapsed_time": "3:42:33", "remaining_time": "3:27:40", "throughput": 1486.34, "total_tokens": 19847872} {"current_steps": 94050, "total_steps": 181800, "loss": 0.0224, "lr": 2.7845579950530344e-05, "epoch": 10.346534653465346, "percentage": 51.73, "elapsed_time": "3:42:34", "remaining_time": "3:27:39", "throughput": 1486.34, "total_tokens": 19848864} {"current_steps": 94055, "total_steps": 181800, "loss": 0.1307, "lr": 2.7843195467681294e-05, "epoch": 10.347084708470847, "percentage": 51.74, "elapsed_time": "3:42:34", "remaining_time": "3:27:38", "throughput": 1486.34, "total_tokens": 19849888} {"current_steps": 94060, "total_steps": 181800, "loss": 0.0063, "lr": 2.784081095862787e-05, "epoch": 10.347634763476348, "percentage": 51.74, "elapsed_time": "3:42:35", "remaining_time": "3:27:38", "throughput": 1486.33, "total_tokens": 19850880} {"current_steps": 94065, "total_steps": 181800, "loss": 0.0018, "lr": 2.7838426423392057e-05, "epoch": 10.348184818481847, "percentage": 51.74, "elapsed_time": "3:42:36", "remaining_time": "3:27:37", "throughput": 1486.34, "total_tokens": 19851936} {"current_steps": 94070, "total_steps": 181800, "loss": 0.0508, "lr": 2.783604186199582e-05, "epoch": 10.348734873487349, "percentage": 51.74, "elapsed_time": "3:42:36", "remaining_time": "3:27:36", "throughput": 1486.33, "total_tokens": 19852928} {"current_steps": 94075, "total_steps": 181800, "loss": 0.0048, "lr": 2.7833657274461162e-05, "epoch": 10.34928492849285, "percentage": 51.75, "elapsed_time": "3:42:37", "remaining_time": "3:27:36", "throughput": 1486.33, "total_tokens": 19853952} {"current_steps": 94080, "total_steps": 181800, "loss": 0.0095, "lr": 2.7831272660810042e-05, "epoch": 10.34983498349835, "percentage": 51.75, "elapsed_time": "3:42:38", "remaining_time": "3:27:35", "throughput": 1486.33, "total_tokens": 19855008} {"current_steps": 94085, "total_steps": 181800, "loss": 0.0049, "lr": 2.782888802106443e-05, "epoch": 10.35038503850385, "percentage": 51.75, "elapsed_time": "3:42:39", "remaining_time": "3:27:34", "throughput": 1486.34, "total_tokens": 19856128} {"current_steps": 94090, "total_steps": 181800, "loss": 0.0075, "lr": 2.782650335524632e-05, "epoch": 10.350935093509351, "percentage": 51.75, "elapsed_time": "3:42:39", "remaining_time": "3:27:33", "throughput": 1486.34, "total_tokens": 19857184} {"current_steps": 94095, "total_steps": 181800, "loss": 0.0249, "lr": 2.7824118663377684e-05, "epoch": 10.351485148514852, "percentage": 51.76, "elapsed_time": "3:42:40", "remaining_time": "3:27:33", "throughput": 1486.35, "total_tokens": 19858336} {"current_steps": 94100, "total_steps": 181800, "loss": 0.0427, "lr": 2.7821733945480505e-05, "epoch": 10.352035203520352, "percentage": 51.76, "elapsed_time": "3:42:41", "remaining_time": "3:27:32", "throughput": 1486.35, "total_tokens": 19859360} {"current_steps": 94105, "total_steps": 181800, "loss": 0.0091, "lr": 2.7819349201576762e-05, "epoch": 10.352585258525853, "percentage": 51.76, "elapsed_time": "3:42:41", "remaining_time": "3:27:31", "throughput": 1486.36, "total_tokens": 19860448} {"current_steps": 94110, "total_steps": 181800, "loss": 0.1946, "lr": 2.781696443168842e-05, "epoch": 10.353135313531354, "percentage": 51.77, "elapsed_time": "3:42:42", "remaining_time": "3:27:30", "throughput": 1486.36, "total_tokens": 19861440} {"current_steps": 94115, "total_steps": 181800, "loss": 0.003, "lr": 2.7814579635837468e-05, "epoch": 10.353685368536853, "percentage": 51.77, "elapsed_time": "3:42:43", "remaining_time": "3:27:30", "throughput": 1486.35, "total_tokens": 19862400} {"current_steps": 94120, "total_steps": 181800, "loss": 0.0652, "lr": 2.7812194814045894e-05, "epoch": 10.354235423542354, "percentage": 51.77, "elapsed_time": "3:42:43", "remaining_time": "3:27:29", "throughput": 1486.35, "total_tokens": 19863456} {"current_steps": 94125, "total_steps": 181800, "loss": 0.0086, "lr": 2.7809809966335665e-05, "epoch": 10.354785478547855, "percentage": 51.77, "elapsed_time": "3:42:44", "remaining_time": "3:27:28", "throughput": 1486.35, "total_tokens": 19864480} {"current_steps": 94130, "total_steps": 181800, "loss": 0.0282, "lr": 2.7807425092728772e-05, "epoch": 10.355335533553355, "percentage": 51.78, "elapsed_time": "3:42:45", "remaining_time": "3:27:28", "throughput": 1486.36, "total_tokens": 19865600} {"current_steps": 94135, "total_steps": 181800, "loss": 0.0131, "lr": 2.7805040193247184e-05, "epoch": 10.355885588558856, "percentage": 51.78, "elapsed_time": "3:42:45", "remaining_time": "3:27:27", "throughput": 1486.36, "total_tokens": 19866624} {"current_steps": 94140, "total_steps": 181800, "loss": 0.0441, "lr": 2.7802655267912887e-05, "epoch": 10.356435643564357, "percentage": 51.78, "elapsed_time": "3:42:46", "remaining_time": "3:27:26", "throughput": 1486.36, "total_tokens": 19867648} {"current_steps": 94145, "total_steps": 181800, "loss": 0.012, "lr": 2.7800270316747855e-05, "epoch": 10.356985698569858, "percentage": 51.78, "elapsed_time": "3:42:47", "remaining_time": "3:27:25", "throughput": 1486.36, "total_tokens": 19868672} {"current_steps": 94150, "total_steps": 181800, "loss": 0.0913, "lr": 2.779788533977409e-05, "epoch": 10.357535753575357, "percentage": 51.79, "elapsed_time": "3:42:48", "remaining_time": "3:27:25", "throughput": 1486.36, "total_tokens": 19869728} {"current_steps": 94155, "total_steps": 181800, "loss": 0.0019, "lr": 2.7795500337013547e-05, "epoch": 10.358085808580858, "percentage": 51.79, "elapsed_time": "3:42:48", "remaining_time": "3:27:24", "throughput": 1486.36, "total_tokens": 19870752} {"current_steps": 94160, "total_steps": 181800, "loss": 0.0062, "lr": 2.779311530848822e-05, "epoch": 10.35863586358636, "percentage": 51.79, "elapsed_time": "3:42:49", "remaining_time": "3:27:23", "throughput": 1486.36, "total_tokens": 19871808} {"current_steps": 94165, "total_steps": 181800, "loss": 0.1093, "lr": 2.7790730254220093e-05, "epoch": 10.359185918591859, "percentage": 51.8, "elapsed_time": "3:42:50", "remaining_time": "3:27:22", "throughput": 1486.37, "total_tokens": 19872864} {"current_steps": 94170, "total_steps": 181800, "loss": 0.001, "lr": 2.7788345174231146e-05, "epoch": 10.35973597359736, "percentage": 51.8, "elapsed_time": "3:42:50", "remaining_time": "3:27:22", "throughput": 1486.37, "total_tokens": 19873984} {"current_steps": 94175, "total_steps": 181800, "loss": 0.0143, "lr": 2.7785960068543355e-05, "epoch": 10.36028602860286, "percentage": 51.8, "elapsed_time": "3:42:51", "remaining_time": "3:27:21", "throughput": 1486.37, "total_tokens": 19875008} {"current_steps": 94180, "total_steps": 181800, "loss": 0.0119, "lr": 2.7783574937178708e-05, "epoch": 10.36083608360836, "percentage": 51.8, "elapsed_time": "3:42:52", "remaining_time": "3:27:20", "throughput": 1486.38, "total_tokens": 19876064} {"current_steps": 94185, "total_steps": 181800, "loss": 0.0167, "lr": 2.778118978015918e-05, "epoch": 10.361386138613861, "percentage": 51.81, "elapsed_time": "3:42:52", "remaining_time": "3:27:20", "throughput": 1486.38, "total_tokens": 19877120} {"current_steps": 94190, "total_steps": 181800, "loss": 0.0099, "lr": 2.777880459750677e-05, "epoch": 10.361936193619362, "percentage": 51.81, "elapsed_time": "3:42:53", "remaining_time": "3:27:19", "throughput": 1486.38, "total_tokens": 19878208} {"current_steps": 94195, "total_steps": 181800, "loss": 0.0782, "lr": 2.7776419389243453e-05, "epoch": 10.362486248624862, "percentage": 51.81, "elapsed_time": "3:42:54", "remaining_time": "3:27:18", "throughput": 1486.38, "total_tokens": 19879232} {"current_steps": 94200, "total_steps": 181800, "loss": 0.002, "lr": 2.7774034155391198e-05, "epoch": 10.363036303630363, "percentage": 51.82, "elapsed_time": "3:42:54", "remaining_time": "3:27:17", "throughput": 1486.39, "total_tokens": 19880288} {"current_steps": 94205, "total_steps": 181800, "loss": 0.0031, "lr": 2.7771648895972012e-05, "epoch": 10.363586358635864, "percentage": 51.82, "elapsed_time": "3:42:55", "remaining_time": "3:27:17", "throughput": 1486.39, "total_tokens": 19881344} {"current_steps": 94210, "total_steps": 181800, "loss": 0.0149, "lr": 2.7769263611007868e-05, "epoch": 10.364136413641365, "percentage": 51.82, "elapsed_time": "3:42:56", "remaining_time": "3:27:16", "throughput": 1486.39, "total_tokens": 19882400} {"current_steps": 94215, "total_steps": 181800, "loss": 0.0207, "lr": 2.7766878300520744e-05, "epoch": 10.364686468646864, "percentage": 51.82, "elapsed_time": "3:42:56", "remaining_time": "3:27:15", "throughput": 1486.39, "total_tokens": 19883488} {"current_steps": 94220, "total_steps": 181800, "loss": 0.0258, "lr": 2.776449296453264e-05, "epoch": 10.365236523652365, "percentage": 51.83, "elapsed_time": "3:42:57", "remaining_time": "3:27:14", "throughput": 1486.4, "total_tokens": 19884544} {"current_steps": 94225, "total_steps": 181800, "loss": 0.0185, "lr": 2.7762107603065523e-05, "epoch": 10.365786578657866, "percentage": 51.83, "elapsed_time": "3:42:58", "remaining_time": "3:27:14", "throughput": 1486.39, "total_tokens": 19885536} {"current_steps": 94230, "total_steps": 181800, "loss": 0.1346, "lr": 2.7759722216141383e-05, "epoch": 10.366336633663366, "percentage": 51.83, "elapsed_time": "3:42:59", "remaining_time": "3:27:13", "throughput": 1486.4, "total_tokens": 19886592} {"current_steps": 94235, "total_steps": 181800, "loss": 0.0069, "lr": 2.7757336803782213e-05, "epoch": 10.366886688668867, "percentage": 51.83, "elapsed_time": "3:42:59", "remaining_time": "3:27:12", "throughput": 1486.4, "total_tokens": 19887712} {"current_steps": 94240, "total_steps": 181800, "loss": 0.0292, "lr": 2.775495136600999e-05, "epoch": 10.367436743674368, "percentage": 51.84, "elapsed_time": "3:43:00", "remaining_time": "3:27:12", "throughput": 1486.41, "total_tokens": 19888832} {"current_steps": 94245, "total_steps": 181800, "loss": 0.0751, "lr": 2.7752565902846706e-05, "epoch": 10.367986798679867, "percentage": 51.84, "elapsed_time": "3:43:01", "remaining_time": "3:27:11", "throughput": 1486.41, "total_tokens": 19889920} {"current_steps": 94250, "total_steps": 181800, "loss": 0.01, "lr": 2.775018041431434e-05, "epoch": 10.368536853685368, "percentage": 51.84, "elapsed_time": "3:43:01", "remaining_time": "3:27:10", "throughput": 1486.42, "total_tokens": 19890976} {"current_steps": 94255, "total_steps": 181800, "loss": 0.0224, "lr": 2.7747794900434887e-05, "epoch": 10.36908690869087, "percentage": 51.85, "elapsed_time": "3:43:02", "remaining_time": "3:27:09", "throughput": 1486.42, "total_tokens": 19892064} {"current_steps": 94260, "total_steps": 181800, "loss": 0.0511, "lr": 2.774540936123031e-05, "epoch": 10.369636963696369, "percentage": 51.85, "elapsed_time": "3:43:03", "remaining_time": "3:27:09", "throughput": 1486.42, "total_tokens": 19893056} {"current_steps": 94265, "total_steps": 181800, "loss": 0.1662, "lr": 2.7743023796722627e-05, "epoch": 10.37018701870187, "percentage": 51.85, "elapsed_time": "3:43:03", "remaining_time": "3:27:08", "throughput": 1486.43, "total_tokens": 19894240} {"current_steps": 94270, "total_steps": 181800, "loss": 0.0394, "lr": 2.7740638206933816e-05, "epoch": 10.370737073707371, "percentage": 51.85, "elapsed_time": "3:43:04", "remaining_time": "3:27:07", "throughput": 1486.43, "total_tokens": 19895264} {"current_steps": 94275, "total_steps": 181800, "loss": 0.0198, "lr": 2.7738252591885845e-05, "epoch": 10.371287128712872, "percentage": 51.86, "elapsed_time": "3:43:05", "remaining_time": "3:27:06", "throughput": 1486.43, "total_tokens": 19896288} {"current_steps": 94280, "total_steps": 181800, "loss": 0.0728, "lr": 2.7735866951600713e-05, "epoch": 10.371837183718371, "percentage": 51.86, "elapsed_time": "3:43:05", "remaining_time": "3:27:06", "throughput": 1486.43, "total_tokens": 19897344} {"current_steps": 94285, "total_steps": 181800, "loss": 0.0213, "lr": 2.7733481286100417e-05, "epoch": 10.372387238723872, "percentage": 51.86, "elapsed_time": "3:43:06", "remaining_time": "3:27:05", "throughput": 1486.44, "total_tokens": 19898432} {"current_steps": 94290, "total_steps": 181800, "loss": 0.012, "lr": 2.7731095595406932e-05, "epoch": 10.372937293729374, "percentage": 51.86, "elapsed_time": "3:43:07", "remaining_time": "3:27:04", "throughput": 1486.44, "total_tokens": 19899488} {"current_steps": 94295, "total_steps": 181800, "loss": 0.0022, "lr": 2.7728709879542247e-05, "epoch": 10.373487348734873, "percentage": 51.87, "elapsed_time": "3:43:08", "remaining_time": "3:27:03", "throughput": 1486.44, "total_tokens": 19900480} {"current_steps": 94300, "total_steps": 181800, "loss": 0.0022, "lr": 2.7726324138528347e-05, "epoch": 10.374037403740374, "percentage": 51.87, "elapsed_time": "3:43:08", "remaining_time": "3:27:03", "throughput": 1486.44, "total_tokens": 19901536} {"current_steps": 94305, "total_steps": 181800, "loss": 0.0164, "lr": 2.772393837238724e-05, "epoch": 10.374587458745875, "percentage": 51.87, "elapsed_time": "3:43:09", "remaining_time": "3:27:02", "throughput": 1486.44, "total_tokens": 19902560} {"current_steps": 94310, "total_steps": 181800, "loss": 0.0044, "lr": 2.7721552581140887e-05, "epoch": 10.375137513751374, "percentage": 51.88, "elapsed_time": "3:43:10", "remaining_time": "3:27:01", "throughput": 1486.44, "total_tokens": 19903616} {"current_steps": 94315, "total_steps": 181800, "loss": 0.0334, "lr": 2.77191667648113e-05, "epoch": 10.375687568756875, "percentage": 51.88, "elapsed_time": "3:43:10", "remaining_time": "3:27:01", "throughput": 1486.44, "total_tokens": 19904672} {"current_steps": 94320, "total_steps": 181800, "loss": 0.0275, "lr": 2.771678092342045e-05, "epoch": 10.376237623762377, "percentage": 51.88, "elapsed_time": "3:43:11", "remaining_time": "3:27:00", "throughput": 1486.44, "total_tokens": 19905664} {"current_steps": 94325, "total_steps": 181800, "loss": 0.007, "lr": 2.7714395056990338e-05, "epoch": 10.376787678767876, "percentage": 51.88, "elapsed_time": "3:43:12", "remaining_time": "3:26:59", "throughput": 1486.44, "total_tokens": 19906688} {"current_steps": 94330, "total_steps": 181800, "loss": 0.0058, "lr": 2.7712009165542946e-05, "epoch": 10.377337733773377, "percentage": 51.89, "elapsed_time": "3:43:12", "remaining_time": "3:26:58", "throughput": 1486.45, "total_tokens": 19907776} {"current_steps": 94335, "total_steps": 181800, "loss": 0.0158, "lr": 2.770962324910027e-05, "epoch": 10.377887788778878, "percentage": 51.89, "elapsed_time": "3:43:13", "remaining_time": "3:26:58", "throughput": 1486.44, "total_tokens": 19908768} {"current_steps": 94340, "total_steps": 181800, "loss": 0.0045, "lr": 2.7707237307684304e-05, "epoch": 10.37843784378438, "percentage": 51.89, "elapsed_time": "3:43:14", "remaining_time": "3:26:57", "throughput": 1486.45, "total_tokens": 19909856} {"current_steps": 94345, "total_steps": 181800, "loss": 0.0223, "lr": 2.770485134131701e-05, "epoch": 10.378987898789878, "percentage": 51.89, "elapsed_time": "3:43:14", "remaining_time": "3:26:56", "throughput": 1486.45, "total_tokens": 19910944} {"current_steps": 94350, "total_steps": 181800, "loss": 0.0519, "lr": 2.7702465350020416e-05, "epoch": 10.37953795379538, "percentage": 51.9, "elapsed_time": "3:43:15", "remaining_time": "3:26:55", "throughput": 1486.46, "total_tokens": 19912096} {"current_steps": 94355, "total_steps": 181800, "loss": 0.0454, "lr": 2.7700079333816493e-05, "epoch": 10.38008800880088, "percentage": 51.9, "elapsed_time": "3:43:16", "remaining_time": "3:26:55", "throughput": 1486.46, "total_tokens": 19913120} {"current_steps": 94360, "total_steps": 181800, "loss": 0.0109, "lr": 2.769769329272723e-05, "epoch": 10.38063806380638, "percentage": 51.9, "elapsed_time": "3:43:17", "remaining_time": "3:26:54", "throughput": 1486.47, "total_tokens": 19914272} {"current_steps": 94365, "total_steps": 181800, "loss": 0.1466, "lr": 2.769530722677463e-05, "epoch": 10.381188118811881, "percentage": 51.91, "elapsed_time": "3:43:17", "remaining_time": "3:26:53", "throughput": 1486.47, "total_tokens": 19915296} {"current_steps": 94370, "total_steps": 181800, "loss": 0.0188, "lr": 2.769292113598067e-05, "epoch": 10.381738173817382, "percentage": 51.91, "elapsed_time": "3:43:18", "remaining_time": "3:26:53", "throughput": 1486.47, "total_tokens": 19916320} {"current_steps": 94375, "total_steps": 181800, "loss": 0.0079, "lr": 2.769053502036735e-05, "epoch": 10.382288228822881, "percentage": 51.91, "elapsed_time": "3:43:19", "remaining_time": "3:26:52", "throughput": 1486.47, "total_tokens": 19917376} {"current_steps": 94380, "total_steps": 181800, "loss": 0.0046, "lr": 2.7688148879956655e-05, "epoch": 10.382838283828383, "percentage": 51.91, "elapsed_time": "3:43:19", "remaining_time": "3:26:51", "throughput": 1486.47, "total_tokens": 19918432} {"current_steps": 94385, "total_steps": 181800, "loss": 0.0065, "lr": 2.768576271477059e-05, "epoch": 10.383388338833884, "percentage": 51.92, "elapsed_time": "3:43:20", "remaining_time": "3:26:50", "throughput": 1486.48, "total_tokens": 19919488} {"current_steps": 94390, "total_steps": 181800, "loss": 0.0026, "lr": 2.7683376524831132e-05, "epoch": 10.383938393839385, "percentage": 51.92, "elapsed_time": "3:43:21", "remaining_time": "3:26:50", "throughput": 1486.47, "total_tokens": 19920480} {"current_steps": 94395, "total_steps": 181800, "loss": 0.0412, "lr": 2.7680990310160288e-05, "epoch": 10.384488448844884, "percentage": 51.92, "elapsed_time": "3:43:21", "remaining_time": "3:26:49", "throughput": 1486.48, "total_tokens": 19921568} {"current_steps": 94400, "total_steps": 181800, "loss": 0.0092, "lr": 2.7678604070780035e-05, "epoch": 10.385038503850385, "percentage": 51.93, "elapsed_time": "3:43:22", "remaining_time": "3:26:48", "throughput": 1486.48, "total_tokens": 19922560} {"current_steps": 94405, "total_steps": 181800, "loss": 0.0353, "lr": 2.7676217806712374e-05, "epoch": 10.385588558855886, "percentage": 51.93, "elapsed_time": "3:43:23", "remaining_time": "3:26:47", "throughput": 1486.48, "total_tokens": 19923616} {"current_steps": 94410, "total_steps": 181800, "loss": 0.0297, "lr": 2.7673831517979303e-05, "epoch": 10.386138613861386, "percentage": 51.93, "elapsed_time": "3:43:23", "remaining_time": "3:26:47", "throughput": 1486.48, "total_tokens": 19924672} {"current_steps": 94415, "total_steps": 181800, "loss": 0.0966, "lr": 2.7671445204602808e-05, "epoch": 10.386688668866887, "percentage": 51.93, "elapsed_time": "3:43:24", "remaining_time": "3:26:46", "throughput": 1486.49, "total_tokens": 19925760} {"current_steps": 94420, "total_steps": 181800, "loss": 0.0278, "lr": 2.766905886660488e-05, "epoch": 10.387238723872388, "percentage": 51.94, "elapsed_time": "3:43:25", "remaining_time": "3:26:45", "throughput": 1486.49, "total_tokens": 19926880} {"current_steps": 94425, "total_steps": 181800, "loss": 0.0339, "lr": 2.7666672504007525e-05, "epoch": 10.387788778877887, "percentage": 51.94, "elapsed_time": "3:43:25", "remaining_time": "3:26:45", "throughput": 1486.5, "total_tokens": 19927968} {"current_steps": 94430, "total_steps": 181800, "loss": 0.0202, "lr": 2.7664286116832722e-05, "epoch": 10.388338833883388, "percentage": 51.94, "elapsed_time": "3:43:26", "remaining_time": "3:26:44", "throughput": 1486.5, "total_tokens": 19929024} {"current_steps": 94435, "total_steps": 181800, "loss": 0.0021, "lr": 2.7661899705102478e-05, "epoch": 10.38888888888889, "percentage": 51.94, "elapsed_time": "3:43:27", "remaining_time": "3:26:43", "throughput": 1486.5, "total_tokens": 19930112} {"current_steps": 94440, "total_steps": 181800, "loss": 0.0225, "lr": 2.7659513268838778e-05, "epoch": 10.389438943894389, "percentage": 51.95, "elapsed_time": "3:43:28", "remaining_time": "3:26:42", "throughput": 1486.51, "total_tokens": 19931168} {"current_steps": 94445, "total_steps": 181800, "loss": 0.0781, "lr": 2.7657126808063622e-05, "epoch": 10.38998899889989, "percentage": 51.95, "elapsed_time": "3:43:28", "remaining_time": "3:26:42", "throughput": 1486.5, "total_tokens": 19932160} {"current_steps": 94450, "total_steps": 181800, "loss": 0.1063, "lr": 2.7654740322799e-05, "epoch": 10.39053905390539, "percentage": 51.95, "elapsed_time": "3:43:29", "remaining_time": "3:26:41", "throughput": 1486.51, "total_tokens": 19933248} {"current_steps": 94455, "total_steps": 181800, "loss": 0.0046, "lr": 2.765235381306691e-05, "epoch": 10.391089108910892, "percentage": 51.96, "elapsed_time": "3:43:30", "remaining_time": "3:26:40", "throughput": 1486.51, "total_tokens": 19934336} {"current_steps": 94460, "total_steps": 181800, "loss": 0.004, "lr": 2.7649967278889356e-05, "epoch": 10.391639163916391, "percentage": 51.96, "elapsed_time": "3:43:30", "remaining_time": "3:26:39", "throughput": 1486.52, "total_tokens": 19935392} {"current_steps": 94465, "total_steps": 181800, "loss": 0.0055, "lr": 2.764758072028832e-05, "epoch": 10.392189218921892, "percentage": 51.96, "elapsed_time": "3:43:31", "remaining_time": "3:26:39", "throughput": 1486.52, "total_tokens": 19936480} {"current_steps": 94470, "total_steps": 181800, "loss": 0.0086, "lr": 2.76451941372858e-05, "epoch": 10.392739273927393, "percentage": 51.96, "elapsed_time": "3:43:32", "remaining_time": "3:26:38", "throughput": 1486.52, "total_tokens": 19937536} {"current_steps": 94475, "total_steps": 181800, "loss": 0.0304, "lr": 2.7642807529903796e-05, "epoch": 10.393289328932893, "percentage": 51.97, "elapsed_time": "3:43:32", "remaining_time": "3:26:37", "throughput": 1486.53, "total_tokens": 19938624} {"current_steps": 94480, "total_steps": 181800, "loss": 0.0123, "lr": 2.764042089816431e-05, "epoch": 10.393839383938394, "percentage": 51.97, "elapsed_time": "3:43:33", "remaining_time": "3:26:37", "throughput": 1486.53, "total_tokens": 19939712} {"current_steps": 94485, "total_steps": 181800, "loss": 0.0068, "lr": 2.7638034242089326e-05, "epoch": 10.394389438943895, "percentage": 51.97, "elapsed_time": "3:43:34", "remaining_time": "3:26:36", "throughput": 1486.53, "total_tokens": 19940736} {"current_steps": 94490, "total_steps": 181800, "loss": 0.0423, "lr": 2.7635647561700838e-05, "epoch": 10.394939493949394, "percentage": 51.97, "elapsed_time": "3:43:34", "remaining_time": "3:26:35", "throughput": 1486.54, "total_tokens": 19941856} {"current_steps": 94495, "total_steps": 181800, "loss": 0.0275, "lr": 2.7633260857020864e-05, "epoch": 10.395489548954895, "percentage": 51.98, "elapsed_time": "3:43:35", "remaining_time": "3:26:34", "throughput": 1486.54, "total_tokens": 19942848} {"current_steps": 94500, "total_steps": 181800, "loss": 0.0382, "lr": 2.7630874128071384e-05, "epoch": 10.396039603960396, "percentage": 51.98, "elapsed_time": "3:43:36", "remaining_time": "3:26:34", "throughput": 1486.54, "total_tokens": 19943872} {"current_steps": 94505, "total_steps": 181800, "loss": 0.0109, "lr": 2.76284873748744e-05, "epoch": 10.396589658965897, "percentage": 51.98, "elapsed_time": "3:43:37", "remaining_time": "3:26:33", "throughput": 1486.54, "total_tokens": 19944928} {"current_steps": 94510, "total_steps": 181800, "loss": 0.019, "lr": 2.762610059745191e-05, "epoch": 10.397139713971397, "percentage": 51.99, "elapsed_time": "3:43:37", "remaining_time": "3:26:32", "throughput": 1486.54, "total_tokens": 19946016} {"current_steps": 94515, "total_steps": 181800, "loss": 0.0676, "lr": 2.7623713795825913e-05, "epoch": 10.397689768976898, "percentage": 51.99, "elapsed_time": "3:43:38", "remaining_time": "3:26:31", "throughput": 1486.55, "total_tokens": 19947072} {"current_steps": 94520, "total_steps": 181800, "loss": 0.113, "lr": 2.762132697001839e-05, "epoch": 10.398239823982399, "percentage": 51.99, "elapsed_time": "3:43:39", "remaining_time": "3:26:31", "throughput": 1486.55, "total_tokens": 19948128} {"current_steps": 94525, "total_steps": 181800, "loss": 0.0071, "lr": 2.761894012005137e-05, "epoch": 10.398789878987898, "percentage": 51.99, "elapsed_time": "3:43:39", "remaining_time": "3:26:30", "throughput": 1486.55, "total_tokens": 19949184} {"current_steps": 94530, "total_steps": 181800, "loss": 0.002, "lr": 2.7616553245946835e-05, "epoch": 10.3993399339934, "percentage": 52.0, "elapsed_time": "3:43:40", "remaining_time": "3:26:29", "throughput": 1486.55, "total_tokens": 19950240} {"current_steps": 94535, "total_steps": 181800, "loss": 0.0411, "lr": 2.761416634772678e-05, "epoch": 10.3998899889989, "percentage": 52.0, "elapsed_time": "3:43:41", "remaining_time": "3:26:29", "throughput": 1486.56, "total_tokens": 19951296} {"current_steps": 94540, "total_steps": 181800, "loss": 0.0217, "lr": 2.761177942541321e-05, "epoch": 10.4004400440044, "percentage": 52.0, "elapsed_time": "3:43:41", "remaining_time": "3:26:28", "throughput": 1486.56, "total_tokens": 19952320} {"current_steps": 94545, "total_steps": 181800, "loss": 0.0098, "lr": 2.7609392479028118e-05, "epoch": 10.400990099009901, "percentage": 52.0, "elapsed_time": "3:43:42", "remaining_time": "3:26:27", "throughput": 1486.56, "total_tokens": 19953376} {"current_steps": 94550, "total_steps": 181800, "loss": 0.0186, "lr": 2.7607005508593502e-05, "epoch": 10.401540154015402, "percentage": 52.01, "elapsed_time": "3:43:43", "remaining_time": "3:26:26", "throughput": 1486.56, "total_tokens": 19954400} {"current_steps": 94555, "total_steps": 181800, "loss": 0.0837, "lr": 2.7604618514131387e-05, "epoch": 10.402090209020901, "percentage": 52.01, "elapsed_time": "3:43:43", "remaining_time": "3:26:26", "throughput": 1486.55, "total_tokens": 19955360} {"current_steps": 94560, "total_steps": 181800, "loss": 0.0022, "lr": 2.7602231495663738e-05, "epoch": 10.402640264026402, "percentage": 52.01, "elapsed_time": "3:43:44", "remaining_time": "3:26:25", "throughput": 1486.56, "total_tokens": 19956416} {"current_steps": 94565, "total_steps": 181800, "loss": 0.0061, "lr": 2.759984445321257e-05, "epoch": 10.403190319031903, "percentage": 52.02, "elapsed_time": "3:43:45", "remaining_time": "3:26:24", "throughput": 1486.56, "total_tokens": 19957536} {"current_steps": 94570, "total_steps": 181800, "loss": 0.0561, "lr": 2.759745738679989e-05, "epoch": 10.403740374037405, "percentage": 52.02, "elapsed_time": "3:43:45", "remaining_time": "3:26:23", "throughput": 1486.56, "total_tokens": 19958560} {"current_steps": 94575, "total_steps": 181800, "loss": 0.0032, "lr": 2.759507029644769e-05, "epoch": 10.404290429042904, "percentage": 52.02, "elapsed_time": "3:43:46", "remaining_time": "3:26:23", "throughput": 1486.57, "total_tokens": 19959616} {"current_steps": 94580, "total_steps": 181800, "loss": 0.0224, "lr": 2.759268318217797e-05, "epoch": 10.404840484048405, "percentage": 52.02, "elapsed_time": "3:43:47", "remaining_time": "3:26:22", "throughput": 1486.57, "total_tokens": 19960736} {"current_steps": 94585, "total_steps": 181800, "loss": 0.0185, "lr": 2.7590296044012738e-05, "epoch": 10.405390539053906, "percentage": 52.03, "elapsed_time": "3:43:48", "remaining_time": "3:26:21", "throughput": 1486.57, "total_tokens": 19961728} {"current_steps": 94590, "total_steps": 181800, "loss": 0.0153, "lr": 2.7587908881973984e-05, "epoch": 10.405940594059405, "percentage": 52.03, "elapsed_time": "3:43:48", "remaining_time": "3:26:20", "throughput": 1486.58, "total_tokens": 19962848} {"current_steps": 94595, "total_steps": 181800, "loss": 0.0388, "lr": 2.758552169608371e-05, "epoch": 10.406490649064907, "percentage": 52.03, "elapsed_time": "3:43:49", "remaining_time": "3:26:20", "throughput": 1486.58, "total_tokens": 19963872} {"current_steps": 94600, "total_steps": 181800, "loss": 0.0027, "lr": 2.7583134486363936e-05, "epoch": 10.407040704070408, "percentage": 52.04, "elapsed_time": "3:43:50", "remaining_time": "3:26:19", "throughput": 1486.58, "total_tokens": 19964896} {"current_steps": 94605, "total_steps": 181800, "loss": 0.0024, "lr": 2.7580747252836648e-05, "epoch": 10.407590759075907, "percentage": 52.04, "elapsed_time": "3:43:50", "remaining_time": "3:26:18", "throughput": 1486.58, "total_tokens": 19965920} {"current_steps": 94610, "total_steps": 181800, "loss": 0.0193, "lr": 2.7578359995523845e-05, "epoch": 10.408140814081408, "percentage": 52.04, "elapsed_time": "3:43:51", "remaining_time": "3:26:18", "throughput": 1486.58, "total_tokens": 19966912} {"current_steps": 94615, "total_steps": 181800, "loss": 0.017, "lr": 2.757597271444754e-05, "epoch": 10.408690869086909, "percentage": 52.04, "elapsed_time": "3:43:52", "remaining_time": "3:26:17", "throughput": 1486.58, "total_tokens": 19968000} {"current_steps": 94620, "total_steps": 181800, "loss": 0.0032, "lr": 2.7573585409629733e-05, "epoch": 10.409240924092408, "percentage": 52.05, "elapsed_time": "3:43:52", "remaining_time": "3:26:16", "throughput": 1486.59, "total_tokens": 19969120} {"current_steps": 94625, "total_steps": 181800, "loss": 0.1222, "lr": 2.757119808109242e-05, "epoch": 10.40979097909791, "percentage": 52.05, "elapsed_time": "3:43:53", "remaining_time": "3:26:15", "throughput": 1486.59, "total_tokens": 19970176} {"current_steps": 94630, "total_steps": 181800, "loss": 0.1849, "lr": 2.7568810728857607e-05, "epoch": 10.41034103410341, "percentage": 52.05, "elapsed_time": "3:43:54", "remaining_time": "3:26:15", "throughput": 1486.59, "total_tokens": 19971200} {"current_steps": 94635, "total_steps": 181800, "loss": 0.0077, "lr": 2.7566423352947303e-05, "epoch": 10.410891089108912, "percentage": 52.05, "elapsed_time": "3:43:54", "remaining_time": "3:26:14", "throughput": 1486.59, "total_tokens": 19972224} {"current_steps": 94640, "total_steps": 181800, "loss": 0.1118, "lr": 2.75640359533835e-05, "epoch": 10.411441144114411, "percentage": 52.06, "elapsed_time": "3:43:55", "remaining_time": "3:26:13", "throughput": 1486.59, "total_tokens": 19973280} {"current_steps": 94645, "total_steps": 181800, "loss": 0.033, "lr": 2.756164853018821e-05, "epoch": 10.411991199119912, "percentage": 52.06, "elapsed_time": "3:43:56", "remaining_time": "3:26:12", "throughput": 1486.6, "total_tokens": 19974336} {"current_steps": 94650, "total_steps": 181800, "loss": 0.0208, "lr": 2.7559261083383437e-05, "epoch": 10.412541254125413, "percentage": 52.06, "elapsed_time": "3:43:56", "remaining_time": "3:26:12", "throughput": 1486.61, "total_tokens": 19975488} {"current_steps": 94655, "total_steps": 181800, "loss": 0.0504, "lr": 2.7556873612991184e-05, "epoch": 10.413091309130913, "percentage": 52.07, "elapsed_time": "3:43:57", "remaining_time": "3:26:11", "throughput": 1486.6, "total_tokens": 19976448} {"current_steps": 94660, "total_steps": 181800, "loss": 0.0219, "lr": 2.7554486119033452e-05, "epoch": 10.413641364136414, "percentage": 52.07, "elapsed_time": "3:43:58", "remaining_time": "3:26:10", "throughput": 1486.6, "total_tokens": 19977504} {"current_steps": 94665, "total_steps": 181800, "loss": 0.0318, "lr": 2.7552098601532246e-05, "epoch": 10.414191419141915, "percentage": 52.07, "elapsed_time": "3:43:59", "remaining_time": "3:26:10", "throughput": 1486.61, "total_tokens": 19978560} {"current_steps": 94670, "total_steps": 181800, "loss": 0.0519, "lr": 2.7549711060509576e-05, "epoch": 10.414741474147414, "percentage": 52.07, "elapsed_time": "3:43:59", "remaining_time": "3:26:09", "throughput": 1486.6, "total_tokens": 19979584} {"current_steps": 94675, "total_steps": 181800, "loss": 0.0981, "lr": 2.7547323495987443e-05, "epoch": 10.415291529152915, "percentage": 52.08, "elapsed_time": "3:44:00", "remaining_time": "3:26:08", "throughput": 1486.61, "total_tokens": 19980640} {"current_steps": 94680, "total_steps": 181800, "loss": 0.0738, "lr": 2.754493590798784e-05, "epoch": 10.415841584158416, "percentage": 52.08, "elapsed_time": "3:44:01", "remaining_time": "3:26:07", "throughput": 1486.61, "total_tokens": 19981664} {"current_steps": 94685, "total_steps": 181800, "loss": 0.0193, "lr": 2.7542548296532795e-05, "epoch": 10.416391639163916, "percentage": 52.08, "elapsed_time": "3:44:01", "remaining_time": "3:26:07", "throughput": 1486.61, "total_tokens": 19982688} {"current_steps": 94690, "total_steps": 181800, "loss": 0.0249, "lr": 2.7540160661644298e-05, "epoch": 10.416941694169417, "percentage": 52.08, "elapsed_time": "3:44:02", "remaining_time": "3:26:06", "throughput": 1486.61, "total_tokens": 19983776} {"current_steps": 94695, "total_steps": 181800, "loss": 0.057, "lr": 2.753777300334436e-05, "epoch": 10.417491749174918, "percentage": 52.09, "elapsed_time": "3:44:03", "remaining_time": "3:26:05", "throughput": 1486.61, "total_tokens": 19984832} {"current_steps": 94700, "total_steps": 181800, "loss": 0.104, "lr": 2.7535385321654988e-05, "epoch": 10.418041804180419, "percentage": 52.09, "elapsed_time": "3:44:03", "remaining_time": "3:26:04", "throughput": 1486.62, "total_tokens": 19985984} {"current_steps": 94705, "total_steps": 181800, "loss": 0.0443, "lr": 2.7532997616598183e-05, "epoch": 10.418591859185918, "percentage": 52.09, "elapsed_time": "3:44:04", "remaining_time": "3:26:04", "throughput": 1486.62, "total_tokens": 19987040} {"current_steps": 94710, "total_steps": 181800, "loss": 0.0813, "lr": 2.753060988819595e-05, "epoch": 10.41914191419142, "percentage": 52.1, "elapsed_time": "3:44:05", "remaining_time": "3:26:03", "throughput": 1486.63, "total_tokens": 19988096} {"current_steps": 94715, "total_steps": 181800, "loss": 0.1178, "lr": 2.752822213647031e-05, "epoch": 10.41969196919692, "percentage": 52.1, "elapsed_time": "3:44:05", "remaining_time": "3:26:02", "throughput": 1486.62, "total_tokens": 19989088} {"current_steps": 94720, "total_steps": 181800, "loss": 0.0106, "lr": 2.752583436144326e-05, "epoch": 10.42024202420242, "percentage": 52.1, "elapsed_time": "3:44:06", "remaining_time": "3:26:02", "throughput": 1486.63, "total_tokens": 19990176} {"current_steps": 94725, "total_steps": 181800, "loss": 0.0175, "lr": 2.75234465631368e-05, "epoch": 10.42079207920792, "percentage": 52.1, "elapsed_time": "3:44:07", "remaining_time": "3:26:01", "throughput": 1486.63, "total_tokens": 19991200} {"current_steps": 94730, "total_steps": 181800, "loss": 0.0238, "lr": 2.7521058741572946e-05, "epoch": 10.421342134213422, "percentage": 52.11, "elapsed_time": "3:44:08", "remaining_time": "3:26:00", "throughput": 1486.63, "total_tokens": 19992256} {"current_steps": 94735, "total_steps": 181800, "loss": 0.0112, "lr": 2.7518670896773703e-05, "epoch": 10.421892189218921, "percentage": 52.11, "elapsed_time": "3:44:08", "remaining_time": "3:26:00", "throughput": 1486.62, "total_tokens": 19993344} {"current_steps": 94740, "total_steps": 181800, "loss": 0.0489, "lr": 2.7516283028761074e-05, "epoch": 10.422442244224422, "percentage": 52.11, "elapsed_time": "3:44:09", "remaining_time": "3:25:59", "throughput": 1486.62, "total_tokens": 19994432} {"current_steps": 94745, "total_steps": 181800, "loss": 0.0043, "lr": 2.7513895137557084e-05, "epoch": 10.422992299229923, "percentage": 52.11, "elapsed_time": "3:44:10", "remaining_time": "3:25:58", "throughput": 1486.62, "total_tokens": 19995488} {"current_steps": 94750, "total_steps": 181800, "loss": 0.0135, "lr": 2.7511507223183724e-05, "epoch": 10.423542354235423, "percentage": 52.12, "elapsed_time": "3:44:10", "remaining_time": "3:25:57", "throughput": 1486.63, "total_tokens": 19996576} {"current_steps": 94755, "total_steps": 181800, "loss": 0.0441, "lr": 2.7509119285663e-05, "epoch": 10.424092409240924, "percentage": 52.12, "elapsed_time": "3:44:11", "remaining_time": "3:25:57", "throughput": 1486.63, "total_tokens": 19997696} {"current_steps": 94760, "total_steps": 181800, "loss": 0.0398, "lr": 2.7506731325016933e-05, "epoch": 10.424642464246425, "percentage": 52.12, "elapsed_time": "3:44:12", "remaining_time": "3:25:56", "throughput": 1486.64, "total_tokens": 19998784} {"current_steps": 94765, "total_steps": 181800, "loss": 0.0705, "lr": 2.7504343341267526e-05, "epoch": 10.425192519251926, "percentage": 52.13, "elapsed_time": "3:44:13", "remaining_time": "3:25:55", "throughput": 1486.64, "total_tokens": 19999872} {"current_steps": 94770, "total_steps": 181800, "loss": 0.0272, "lr": 2.7501955334436792e-05, "epoch": 10.425742574257425, "percentage": 52.13, "elapsed_time": "3:44:13", "remaining_time": "3:25:54", "throughput": 1486.64, "total_tokens": 20000896} {"current_steps": 94775, "total_steps": 181800, "loss": 0.0087, "lr": 2.7499567304546732e-05, "epoch": 10.426292629262926, "percentage": 52.13, "elapsed_time": "3:44:14", "remaining_time": "3:25:54", "throughput": 1486.65, "total_tokens": 20001952} {"current_steps": 94780, "total_steps": 181800, "loss": 0.0396, "lr": 2.749717925161936e-05, "epoch": 10.426842684268427, "percentage": 52.13, "elapsed_time": "3:44:15", "remaining_time": "3:25:53", "throughput": 1486.65, "total_tokens": 20002976} {"current_steps": 94785, "total_steps": 181800, "loss": 0.0102, "lr": 2.7494791175676675e-05, "epoch": 10.427392739273927, "percentage": 52.14, "elapsed_time": "3:44:15", "remaining_time": "3:25:52", "throughput": 1486.65, "total_tokens": 20004000} {"current_steps": 94790, "total_steps": 181800, "loss": 0.0054, "lr": 2.7492403076740714e-05, "epoch": 10.427942794279428, "percentage": 52.14, "elapsed_time": "3:44:16", "remaining_time": "3:25:52", "throughput": 1486.64, "total_tokens": 20005024} {"current_steps": 94795, "total_steps": 181800, "loss": 0.005, "lr": 2.749001495483346e-05, "epoch": 10.428492849284929, "percentage": 52.14, "elapsed_time": "3:44:17", "remaining_time": "3:25:51", "throughput": 1486.65, "total_tokens": 20006144} {"current_steps": 94800, "total_steps": 181800, "loss": 0.0035, "lr": 2.7487626809976935e-05, "epoch": 10.429042904290428, "percentage": 52.15, "elapsed_time": "3:44:17", "remaining_time": "3:25:50", "throughput": 1486.65, "total_tokens": 20007168} {"current_steps": 94805, "total_steps": 181800, "loss": 0.0079, "lr": 2.748523864219315e-05, "epoch": 10.42959295929593, "percentage": 52.15, "elapsed_time": "3:44:18", "remaining_time": "3:25:49", "throughput": 1486.66, "total_tokens": 20008288} {"current_steps": 94810, "total_steps": 181800, "loss": 0.0009, "lr": 2.748285045150411e-05, "epoch": 10.43014301430143, "percentage": 52.15, "elapsed_time": "3:44:19", "remaining_time": "3:25:49", "throughput": 1486.66, "total_tokens": 20009344} {"current_steps": 94815, "total_steps": 181800, "loss": 0.0062, "lr": 2.748046223793183e-05, "epoch": 10.430693069306932, "percentage": 52.15, "elapsed_time": "3:44:19", "remaining_time": "3:25:48", "throughput": 1486.67, "total_tokens": 20010464} {"current_steps": 94820, "total_steps": 181800, "loss": 0.0737, "lr": 2.7478074001498323e-05, "epoch": 10.43124312431243, "percentage": 52.16, "elapsed_time": "3:44:20", "remaining_time": "3:25:47", "throughput": 1486.67, "total_tokens": 20011488} {"current_steps": 94825, "total_steps": 181800, "loss": 0.1218, "lr": 2.7475685742225587e-05, "epoch": 10.431793179317932, "percentage": 52.16, "elapsed_time": "3:44:21", "remaining_time": "3:25:46", "throughput": 1486.67, "total_tokens": 20012480} {"current_steps": 94830, "total_steps": 181800, "loss": 0.0035, "lr": 2.747329746013565e-05, "epoch": 10.432343234323433, "percentage": 52.16, "elapsed_time": "3:44:22", "remaining_time": "3:25:46", "throughput": 1486.67, "total_tokens": 20013536} {"current_steps": 94835, "total_steps": 181800, "loss": 0.0142, "lr": 2.7470909155250517e-05, "epoch": 10.432893289328932, "percentage": 52.16, "elapsed_time": "3:44:22", "remaining_time": "3:25:45", "throughput": 1486.67, "total_tokens": 20014560} {"current_steps": 94840, "total_steps": 181800, "loss": 0.003, "lr": 2.7468520827592197e-05, "epoch": 10.433443344334433, "percentage": 52.17, "elapsed_time": "3:44:23", "remaining_time": "3:25:44", "throughput": 1486.67, "total_tokens": 20015616} {"current_steps": 94845, "total_steps": 181800, "loss": 0.0069, "lr": 2.746613247718271e-05, "epoch": 10.433993399339935, "percentage": 52.17, "elapsed_time": "3:44:24", "remaining_time": "3:25:44", "throughput": 1486.68, "total_tokens": 20016704} {"current_steps": 94850, "total_steps": 181800, "loss": 0.0638, "lr": 2.7463744104044065e-05, "epoch": 10.434543454345434, "percentage": 52.17, "elapsed_time": "3:44:24", "remaining_time": "3:25:43", "throughput": 1486.68, "total_tokens": 20017728} {"current_steps": 94855, "total_steps": 181800, "loss": 0.0065, "lr": 2.746135570819826e-05, "epoch": 10.435093509350935, "percentage": 52.18, "elapsed_time": "3:44:25", "remaining_time": "3:25:42", "throughput": 1486.68, "total_tokens": 20018752} {"current_steps": 94860, "total_steps": 181800, "loss": 0.0225, "lr": 2.7458967289667337e-05, "epoch": 10.435643564356436, "percentage": 52.18, "elapsed_time": "3:44:26", "remaining_time": "3:25:41", "throughput": 1486.68, "total_tokens": 20019808} {"current_steps": 94865, "total_steps": 181800, "loss": 0.0294, "lr": 2.7456578848473287e-05, "epoch": 10.436193619361935, "percentage": 52.18, "elapsed_time": "3:44:26", "remaining_time": "3:25:41", "throughput": 1486.68, "total_tokens": 20020832} {"current_steps": 94870, "total_steps": 181800, "loss": 0.0644, "lr": 2.7454190384638124e-05, "epoch": 10.436743674367436, "percentage": 52.18, "elapsed_time": "3:44:27", "remaining_time": "3:25:40", "throughput": 1486.68, "total_tokens": 20021920} {"current_steps": 94875, "total_steps": 181800, "loss": 0.0077, "lr": 2.7451801898183864e-05, "epoch": 10.437293729372938, "percentage": 52.19, "elapsed_time": "3:44:28", "remaining_time": "3:25:39", "throughput": 1486.68, "total_tokens": 20022944} {"current_steps": 94880, "total_steps": 181800, "loss": 0.0193, "lr": 2.7449413389132534e-05, "epoch": 10.437843784378439, "percentage": 52.19, "elapsed_time": "3:44:28", "remaining_time": "3:25:38", "throughput": 1486.69, "total_tokens": 20024032} {"current_steps": 94885, "total_steps": 181800, "loss": 0.0123, "lr": 2.7447024857506126e-05, "epoch": 10.438393839383938, "percentage": 52.19, "elapsed_time": "3:44:29", "remaining_time": "3:25:38", "throughput": 1486.69, "total_tokens": 20025120} {"current_steps": 94890, "total_steps": 181800, "loss": 0.003, "lr": 2.744463630332667e-05, "epoch": 10.438943894389439, "percentage": 52.19, "elapsed_time": "3:44:30", "remaining_time": "3:25:37", "throughput": 1486.69, "total_tokens": 20026144} {"current_steps": 94895, "total_steps": 181800, "loss": 0.0215, "lr": 2.744224772661617e-05, "epoch": 10.43949394939494, "percentage": 52.2, "elapsed_time": "3:44:30", "remaining_time": "3:25:36", "throughput": 1486.69, "total_tokens": 20027168} {"current_steps": 94900, "total_steps": 181800, "loss": 0.0475, "lr": 2.7439859127396638e-05, "epoch": 10.44004400440044, "percentage": 52.2, "elapsed_time": "3:44:31", "remaining_time": "3:25:36", "throughput": 1486.69, "total_tokens": 20028192} {"current_steps": 94905, "total_steps": 181800, "loss": 0.0465, "lr": 2.7437470505690105e-05, "epoch": 10.44059405940594, "percentage": 52.2, "elapsed_time": "3:44:32", "remaining_time": "3:25:35", "throughput": 1486.69, "total_tokens": 20029216} {"current_steps": 94910, "total_steps": 181800, "loss": 0.0149, "lr": 2.7435081861518575e-05, "epoch": 10.441144114411442, "percentage": 52.21, "elapsed_time": "3:44:33", "remaining_time": "3:25:34", "throughput": 1486.69, "total_tokens": 20030272} {"current_steps": 94915, "total_steps": 181800, "loss": 0.019, "lr": 2.7432693194904063e-05, "epoch": 10.441694169416941, "percentage": 52.21, "elapsed_time": "3:44:33", "remaining_time": "3:25:33", "throughput": 1486.7, "total_tokens": 20031360} {"current_steps": 94920, "total_steps": 181800, "loss": 0.0148, "lr": 2.7430304505868586e-05, "epoch": 10.442244224422442, "percentage": 52.21, "elapsed_time": "3:44:34", "remaining_time": "3:25:33", "throughput": 1486.7, "total_tokens": 20032416} {"current_steps": 94925, "total_steps": 181800, "loss": 0.1587, "lr": 2.7427915794434163e-05, "epoch": 10.442794279427943, "percentage": 52.21, "elapsed_time": "3:44:35", "remaining_time": "3:25:32", "throughput": 1486.7, "total_tokens": 20033472} {"current_steps": 94930, "total_steps": 181800, "loss": 0.0416, "lr": 2.7425527060622793e-05, "epoch": 10.443344334433444, "percentage": 52.22, "elapsed_time": "3:44:35", "remaining_time": "3:25:31", "throughput": 1486.71, "total_tokens": 20034528} {"current_steps": 94935, "total_steps": 181800, "loss": 0.0059, "lr": 2.7423138304456515e-05, "epoch": 10.443894389438944, "percentage": 52.22, "elapsed_time": "3:44:36", "remaining_time": "3:25:30", "throughput": 1486.71, "total_tokens": 20035616} {"current_steps": 94940, "total_steps": 181800, "loss": 0.1204, "lr": 2.7420749525957323e-05, "epoch": 10.444444444444445, "percentage": 52.22, "elapsed_time": "3:44:37", "remaining_time": "3:25:30", "throughput": 1486.71, "total_tokens": 20036672} {"current_steps": 94945, "total_steps": 181800, "loss": 0.0117, "lr": 2.7418360725147253e-05, "epoch": 10.444994499449946, "percentage": 52.22, "elapsed_time": "3:44:37", "remaining_time": "3:25:29", "throughput": 1486.71, "total_tokens": 20037728} {"current_steps": 94950, "total_steps": 181800, "loss": 0.0136, "lr": 2.7415971902048314e-05, "epoch": 10.445544554455445, "percentage": 52.23, "elapsed_time": "3:44:38", "remaining_time": "3:25:28", "throughput": 1486.72, "total_tokens": 20038784} {"current_steps": 94955, "total_steps": 181800, "loss": 0.036, "lr": 2.7413583056682518e-05, "epoch": 10.446094609460946, "percentage": 52.23, "elapsed_time": "3:44:39", "remaining_time": "3:25:27", "throughput": 1486.72, "total_tokens": 20039904} {"current_steps": 94960, "total_steps": 181800, "loss": 0.0805, "lr": 2.741119418907189e-05, "epoch": 10.446644664466447, "percentage": 52.23, "elapsed_time": "3:44:39", "remaining_time": "3:25:27", "throughput": 1486.73, "total_tokens": 20040992} {"current_steps": 94965, "total_steps": 181800, "loss": 0.0154, "lr": 2.7408805299238432e-05, "epoch": 10.447194719471947, "percentage": 52.24, "elapsed_time": "3:44:40", "remaining_time": "3:25:26", "throughput": 1486.73, "total_tokens": 20041984} {"current_steps": 94970, "total_steps": 181800, "loss": 0.038, "lr": 2.740641638720417e-05, "epoch": 10.447744774477448, "percentage": 52.24, "elapsed_time": "3:44:41", "remaining_time": "3:25:25", "throughput": 1486.73, "total_tokens": 20043008} {"current_steps": 94975, "total_steps": 181800, "loss": 0.018, "lr": 2.740402745299113e-05, "epoch": 10.448294829482949, "percentage": 52.24, "elapsed_time": "3:44:41", "remaining_time": "3:25:25", "throughput": 1486.73, "total_tokens": 20044096} {"current_steps": 94980, "total_steps": 181800, "loss": 0.052, "lr": 2.740163849662133e-05, "epoch": 10.448844884488448, "percentage": 52.24, "elapsed_time": "3:44:42", "remaining_time": "3:25:24", "throughput": 1486.73, "total_tokens": 20045120} {"current_steps": 94985, "total_steps": 181800, "loss": 0.0452, "lr": 2.739924951811677e-05, "epoch": 10.44939493949395, "percentage": 52.25, "elapsed_time": "3:44:43", "remaining_time": "3:25:23", "throughput": 1486.74, "total_tokens": 20046208} {"current_steps": 94990, "total_steps": 181800, "loss": 0.0133, "lr": 2.7396860517499478e-05, "epoch": 10.44994499449945, "percentage": 52.25, "elapsed_time": "3:44:44", "remaining_time": "3:25:22", "throughput": 1486.74, "total_tokens": 20047296} {"current_steps": 94995, "total_steps": 181800, "loss": 0.018, "lr": 2.7394471494791478e-05, "epoch": 10.450495049504951, "percentage": 52.25, "elapsed_time": "3:44:44", "remaining_time": "3:25:22", "throughput": 1486.75, "total_tokens": 20048416} {"current_steps": 95000, "total_steps": 181800, "loss": 0.0305, "lr": 2.7392082450014777e-05, "epoch": 10.45104510451045, "percentage": 52.26, "elapsed_time": "3:44:45", "remaining_time": "3:25:21", "throughput": 1486.74, "total_tokens": 20049408} {"current_steps": 95005, "total_steps": 181800, "loss": 0.0256, "lr": 2.738969338319141e-05, "epoch": 10.451595159515952, "percentage": 52.26, "elapsed_time": "3:44:46", "remaining_time": "3:25:20", "throughput": 1486.75, "total_tokens": 20050496} {"current_steps": 95010, "total_steps": 181800, "loss": 0.1642, "lr": 2.738730429434338e-05, "epoch": 10.452145214521453, "percentage": 52.26, "elapsed_time": "3:44:46", "remaining_time": "3:25:19", "throughput": 1486.75, "total_tokens": 20051584} {"current_steps": 95015, "total_steps": 181800, "loss": 0.0314, "lr": 2.7384915183492704e-05, "epoch": 10.452695269526952, "percentage": 52.26, "elapsed_time": "3:44:47", "remaining_time": "3:25:19", "throughput": 1486.75, "total_tokens": 20052608} {"current_steps": 95020, "total_steps": 181800, "loss": 0.234, "lr": 2.7382526050661415e-05, "epoch": 10.453245324532453, "percentage": 52.27, "elapsed_time": "3:44:48", "remaining_time": "3:25:18", "throughput": 1486.75, "total_tokens": 20053632} {"current_steps": 95025, "total_steps": 181800, "loss": 0.006, "lr": 2.7380136895871533e-05, "epoch": 10.453795379537954, "percentage": 52.27, "elapsed_time": "3:44:48", "remaining_time": "3:25:17", "throughput": 1486.76, "total_tokens": 20054688} {"current_steps": 95030, "total_steps": 181800, "loss": 0.0655, "lr": 2.7377747719145062e-05, "epoch": 10.454345434543454, "percentage": 52.27, "elapsed_time": "3:44:49", "remaining_time": "3:25:17", "throughput": 1486.76, "total_tokens": 20055712} {"current_steps": 95035, "total_steps": 181800, "loss": 0.0057, "lr": 2.737535852050404e-05, "epoch": 10.454895489548955, "percentage": 52.27, "elapsed_time": "3:44:50", "remaining_time": "3:25:16", "throughput": 1486.76, "total_tokens": 20056736} {"current_steps": 95040, "total_steps": 181800, "loss": 0.0481, "lr": 2.7372969299970476e-05, "epoch": 10.455445544554456, "percentage": 52.28, "elapsed_time": "3:44:50", "remaining_time": "3:25:15", "throughput": 1486.76, "total_tokens": 20057760} {"current_steps": 95045, "total_steps": 181800, "loss": 0.085, "lr": 2.7370580057566386e-05, "epoch": 10.455995599559955, "percentage": 52.28, "elapsed_time": "3:44:51", "remaining_time": "3:25:14", "throughput": 1486.76, "total_tokens": 20058816} {"current_steps": 95050, "total_steps": 181800, "loss": 0.0401, "lr": 2.736819079331381e-05, "epoch": 10.456545654565456, "percentage": 52.28, "elapsed_time": "3:44:52", "remaining_time": "3:25:14", "throughput": 1486.75, "total_tokens": 20059776} {"current_steps": 95055, "total_steps": 181800, "loss": 0.0049, "lr": 2.7365801507234744e-05, "epoch": 10.457095709570957, "percentage": 52.29, "elapsed_time": "3:44:53", "remaining_time": "3:25:13", "throughput": 1486.76, "total_tokens": 20060832} {"current_steps": 95060, "total_steps": 181800, "loss": 0.0274, "lr": 2.736341219935122e-05, "epoch": 10.457645764576458, "percentage": 52.29, "elapsed_time": "3:44:53", "remaining_time": "3:25:12", "throughput": 1486.76, "total_tokens": 20061920} {"current_steps": 95065, "total_steps": 181800, "loss": 0.0501, "lr": 2.7361022869685266e-05, "epoch": 10.458195819581958, "percentage": 52.29, "elapsed_time": "3:44:54", "remaining_time": "3:25:11", "throughput": 1486.76, "total_tokens": 20062976} {"current_steps": 95070, "total_steps": 181800, "loss": 0.0049, "lr": 2.7358633518258897e-05, "epoch": 10.458745874587459, "percentage": 52.29, "elapsed_time": "3:44:55", "remaining_time": "3:25:11", "throughput": 1486.77, "total_tokens": 20064096} {"current_steps": 95075, "total_steps": 181800, "loss": 0.1722, "lr": 2.7356244145094133e-05, "epoch": 10.45929592959296, "percentage": 52.3, "elapsed_time": "3:44:55", "remaining_time": "3:25:10", "throughput": 1486.78, "total_tokens": 20065216} {"current_steps": 95080, "total_steps": 181800, "loss": 0.0356, "lr": 2.7353854750213e-05, "epoch": 10.45984598459846, "percentage": 52.3, "elapsed_time": "3:44:56", "remaining_time": "3:25:09", "throughput": 1486.78, "total_tokens": 20066272} {"current_steps": 95085, "total_steps": 181800, "loss": 0.0059, "lr": 2.7351465333637504e-05, "epoch": 10.46039603960396, "percentage": 52.3, "elapsed_time": "3:44:57", "remaining_time": "3:25:09", "throughput": 1486.78, "total_tokens": 20067296} {"current_steps": 95090, "total_steps": 181800, "loss": 0.0371, "lr": 2.7349075895389693e-05, "epoch": 10.460946094609461, "percentage": 52.3, "elapsed_time": "3:44:57", "remaining_time": "3:25:08", "throughput": 1486.78, "total_tokens": 20068352} {"current_steps": 95095, "total_steps": 181800, "loss": 0.1364, "lr": 2.7346686435491577e-05, "epoch": 10.46149614961496, "percentage": 52.31, "elapsed_time": "3:44:58", "remaining_time": "3:25:07", "throughput": 1486.79, "total_tokens": 20069440} {"current_steps": 95100, "total_steps": 181800, "loss": 0.0075, "lr": 2.7344296953965176e-05, "epoch": 10.462046204620462, "percentage": 52.31, "elapsed_time": "3:44:59", "remaining_time": "3:25:06", "throughput": 1486.79, "total_tokens": 20070528} {"current_steps": 95105, "total_steps": 181800, "loss": 0.0232, "lr": 2.7341907450832516e-05, "epoch": 10.462596259625963, "percentage": 52.31, "elapsed_time": "3:44:59", "remaining_time": "3:25:06", "throughput": 1486.8, "total_tokens": 20071648} {"current_steps": 95110, "total_steps": 181800, "loss": 0.0079, "lr": 2.7339517926115614e-05, "epoch": 10.463146314631462, "percentage": 52.32, "elapsed_time": "3:45:00", "remaining_time": "3:25:05", "throughput": 1486.8, "total_tokens": 20072672} {"current_steps": 95115, "total_steps": 181800, "loss": 0.0357, "lr": 2.7337128379836495e-05, "epoch": 10.463696369636963, "percentage": 52.32, "elapsed_time": "3:45:01", "remaining_time": "3:25:04", "throughput": 1486.8, "total_tokens": 20073760} {"current_steps": 95120, "total_steps": 181800, "loss": 0.0506, "lr": 2.7334738812017196e-05, "epoch": 10.464246424642464, "percentage": 52.32, "elapsed_time": "3:45:01", "remaining_time": "3:25:03", "throughput": 1486.8, "total_tokens": 20074720} {"current_steps": 95125, "total_steps": 181800, "loss": 0.021, "lr": 2.733234922267973e-05, "epoch": 10.464796479647966, "percentage": 52.32, "elapsed_time": "3:45:02", "remaining_time": "3:25:03", "throughput": 1486.8, "total_tokens": 20075744} {"current_steps": 95130, "total_steps": 181800, "loss": 0.0047, "lr": 2.7329959611846113e-05, "epoch": 10.465346534653465, "percentage": 52.33, "elapsed_time": "3:45:03", "remaining_time": "3:25:02", "throughput": 1486.8, "total_tokens": 20076800} {"current_steps": 95135, "total_steps": 181800, "loss": 0.022, "lr": 2.732756997953838e-05, "epoch": 10.465896589658966, "percentage": 52.33, "elapsed_time": "3:45:04", "remaining_time": "3:25:01", "throughput": 1486.81, "total_tokens": 20077920} {"current_steps": 95140, "total_steps": 181800, "loss": 0.0097, "lr": 2.7325180325778547e-05, "epoch": 10.466446644664467, "percentage": 52.33, "elapsed_time": "3:45:04", "remaining_time": "3:25:01", "throughput": 1486.81, "total_tokens": 20078944} {"current_steps": 95145, "total_steps": 181800, "loss": 0.0971, "lr": 2.7322790650588647e-05, "epoch": 10.466996699669966, "percentage": 52.33, "elapsed_time": "3:45:05", "remaining_time": "3:25:00", "throughput": 1486.8, "total_tokens": 20079904} {"current_steps": 95150, "total_steps": 181800, "loss": 0.0368, "lr": 2.7320400953990698e-05, "epoch": 10.467546754675467, "percentage": 52.34, "elapsed_time": "3:45:06", "remaining_time": "3:24:59", "throughput": 1486.81, "total_tokens": 20081024} {"current_steps": 95155, "total_steps": 181800, "loss": 0.014, "lr": 2.731801123600673e-05, "epoch": 10.468096809680969, "percentage": 52.34, "elapsed_time": "3:45:06", "remaining_time": "3:24:58", "throughput": 1486.81, "total_tokens": 20082080} {"current_steps": 95160, "total_steps": 181800, "loss": 0.0085, "lr": 2.7315621496658762e-05, "epoch": 10.468646864686468, "percentage": 52.34, "elapsed_time": "3:45:07", "remaining_time": "3:24:58", "throughput": 1486.81, "total_tokens": 20083104} {"current_steps": 95165, "total_steps": 181800, "loss": 0.0338, "lr": 2.731323173596882e-05, "epoch": 10.469196919691969, "percentage": 52.35, "elapsed_time": "3:45:08", "remaining_time": "3:24:57", "throughput": 1486.81, "total_tokens": 20084128} {"current_steps": 95170, "total_steps": 181800, "loss": 0.0252, "lr": 2.7310841953958942e-05, "epoch": 10.46974697469747, "percentage": 52.35, "elapsed_time": "3:45:08", "remaining_time": "3:24:56", "throughput": 1486.81, "total_tokens": 20085120} {"current_steps": 95175, "total_steps": 181800, "loss": 0.0052, "lr": 2.7308452150651125e-05, "epoch": 10.47029702970297, "percentage": 52.35, "elapsed_time": "3:45:09", "remaining_time": "3:24:55", "throughput": 1486.81, "total_tokens": 20086176} {"current_steps": 95180, "total_steps": 181800, "loss": 0.1104, "lr": 2.730606232606743e-05, "epoch": 10.47084708470847, "percentage": 52.35, "elapsed_time": "3:45:10", "remaining_time": "3:24:55", "throughput": 1486.82, "total_tokens": 20087264} {"current_steps": 95185, "total_steps": 181800, "loss": 0.0023, "lr": 2.7303672480229854e-05, "epoch": 10.471397139713972, "percentage": 52.36, "elapsed_time": "3:45:10", "remaining_time": "3:24:54", "throughput": 1486.82, "total_tokens": 20088352} {"current_steps": 95190, "total_steps": 181800, "loss": 0.1656, "lr": 2.7301282613160428e-05, "epoch": 10.471947194719473, "percentage": 52.36, "elapsed_time": "3:45:11", "remaining_time": "3:24:53", "throughput": 1486.82, "total_tokens": 20089408} {"current_steps": 95195, "total_steps": 181800, "loss": 0.0275, "lr": 2.7298892724881196e-05, "epoch": 10.472497249724972, "percentage": 52.36, "elapsed_time": "3:45:12", "remaining_time": "3:24:53", "throughput": 1486.83, "total_tokens": 20090464} {"current_steps": 95200, "total_steps": 181800, "loss": 0.1494, "lr": 2.7296502815414177e-05, "epoch": 10.473047304730473, "percentage": 52.37, "elapsed_time": "3:45:12", "remaining_time": "3:24:52", "throughput": 1486.83, "total_tokens": 20091488} {"current_steps": 95205, "total_steps": 181800, "loss": 0.0308, "lr": 2.729411288478138e-05, "epoch": 10.473597359735974, "percentage": 52.37, "elapsed_time": "3:45:13", "remaining_time": "3:24:51", "throughput": 1486.83, "total_tokens": 20092576} {"current_steps": 95210, "total_steps": 181800, "loss": 0.0075, "lr": 2.7291722933004855e-05, "epoch": 10.474147414741473, "percentage": 52.37, "elapsed_time": "3:45:14", "remaining_time": "3:24:50", "throughput": 1486.84, "total_tokens": 20093696} {"current_steps": 95215, "total_steps": 181800, "loss": 0.1232, "lr": 2.728933296010661e-05, "epoch": 10.474697469746975, "percentage": 52.37, "elapsed_time": "3:45:15", "remaining_time": "3:24:50", "throughput": 1486.84, "total_tokens": 20094784} {"current_steps": 95220, "total_steps": 181800, "loss": 0.0748, "lr": 2.7286942966108693e-05, "epoch": 10.475247524752476, "percentage": 52.38, "elapsed_time": "3:45:15", "remaining_time": "3:24:49", "throughput": 1486.84, "total_tokens": 20095808} {"current_steps": 95225, "total_steps": 181800, "loss": 0.0019, "lr": 2.7284552951033114e-05, "epoch": 10.475797579757975, "percentage": 52.38, "elapsed_time": "3:45:16", "remaining_time": "3:24:48", "throughput": 1486.85, "total_tokens": 20096864} {"current_steps": 95230, "total_steps": 181800, "loss": 0.0226, "lr": 2.728216291490191e-05, "epoch": 10.476347634763476, "percentage": 52.38, "elapsed_time": "3:45:17", "remaining_time": "3:24:47", "throughput": 1486.85, "total_tokens": 20097952} {"current_steps": 95235, "total_steps": 181800, "loss": 0.0084, "lr": 2.7279772857737095e-05, "epoch": 10.476897689768977, "percentage": 52.38, "elapsed_time": "3:45:17", "remaining_time": "3:24:47", "throughput": 1486.85, "total_tokens": 20099008} {"current_steps": 95240, "total_steps": 181800, "loss": 0.056, "lr": 2.7277382779560723e-05, "epoch": 10.477447744774478, "percentage": 52.39, "elapsed_time": "3:45:18", "remaining_time": "3:24:46", "throughput": 1486.86, "total_tokens": 20100160} {"current_steps": 95245, "total_steps": 181800, "loss": 0.0031, "lr": 2.7274992680394794e-05, "epoch": 10.477997799779978, "percentage": 52.39, "elapsed_time": "3:45:19", "remaining_time": "3:24:45", "throughput": 1486.86, "total_tokens": 20101152} {"current_steps": 95250, "total_steps": 181800, "loss": 0.0108, "lr": 2.7272602560261357e-05, "epoch": 10.478547854785479, "percentage": 52.39, "elapsed_time": "3:45:19", "remaining_time": "3:24:44", "throughput": 1486.87, "total_tokens": 20102272} {"current_steps": 95255, "total_steps": 181800, "loss": 0.0087, "lr": 2.7270212419182428e-05, "epoch": 10.47909790979098, "percentage": 52.4, "elapsed_time": "3:45:20", "remaining_time": "3:24:44", "throughput": 1486.87, "total_tokens": 20103328} {"current_steps": 95260, "total_steps": 181800, "loss": 0.0034, "lr": 2.7267822257180043e-05, "epoch": 10.479647964796479, "percentage": 52.4, "elapsed_time": "3:45:21", "remaining_time": "3:24:43", "throughput": 1486.87, "total_tokens": 20104352} {"current_steps": 95265, "total_steps": 181800, "loss": 0.0771, "lr": 2.726543207427623e-05, "epoch": 10.48019801980198, "percentage": 52.4, "elapsed_time": "3:45:21", "remaining_time": "3:24:42", "throughput": 1486.87, "total_tokens": 20105440} {"current_steps": 95270, "total_steps": 181800, "loss": 0.009, "lr": 2.7263041870493017e-05, "epoch": 10.480748074807481, "percentage": 52.4, "elapsed_time": "3:45:22", "remaining_time": "3:24:42", "throughput": 1486.88, "total_tokens": 20106528} {"current_steps": 95275, "total_steps": 181800, "loss": 0.0036, "lr": 2.7260651645852425e-05, "epoch": 10.48129812981298, "percentage": 52.41, "elapsed_time": "3:45:23", "remaining_time": "3:24:41", "throughput": 1486.88, "total_tokens": 20107552} {"current_steps": 95280, "total_steps": 181800, "loss": 0.0148, "lr": 2.7258261400376495e-05, "epoch": 10.481848184818482, "percentage": 52.41, "elapsed_time": "3:45:24", "remaining_time": "3:24:40", "throughput": 1486.88, "total_tokens": 20108544} {"current_steps": 95285, "total_steps": 181800, "loss": 0.0258, "lr": 2.725587113408726e-05, "epoch": 10.482398239823983, "percentage": 52.41, "elapsed_time": "3:45:24", "remaining_time": "3:24:39", "throughput": 1486.88, "total_tokens": 20109632} {"current_steps": 95290, "total_steps": 181800, "loss": 0.0083, "lr": 2.7253480847006734e-05, "epoch": 10.482948294829482, "percentage": 52.41, "elapsed_time": "3:45:25", "remaining_time": "3:24:39", "throughput": 1486.88, "total_tokens": 20110688} {"current_steps": 95295, "total_steps": 181800, "loss": 0.0015, "lr": 2.7251090539156966e-05, "epoch": 10.483498349834983, "percentage": 52.42, "elapsed_time": "3:45:26", "remaining_time": "3:24:38", "throughput": 1486.88, "total_tokens": 20111680} {"current_steps": 95300, "total_steps": 181800, "loss": 0.0214, "lr": 2.724870021055997e-05, "epoch": 10.484048404840484, "percentage": 52.42, "elapsed_time": "3:45:26", "remaining_time": "3:24:37", "throughput": 1486.88, "total_tokens": 20112704} {"current_steps": 95305, "total_steps": 181800, "loss": 0.0401, "lr": 2.724630986123778e-05, "epoch": 10.484598459845985, "percentage": 52.42, "elapsed_time": "3:45:27", "remaining_time": "3:24:36", "throughput": 1486.88, "total_tokens": 20113760} {"current_steps": 95310, "total_steps": 181800, "loss": 0.0104, "lr": 2.7243919491212438e-05, "epoch": 10.485148514851485, "percentage": 52.43, "elapsed_time": "3:45:28", "remaining_time": "3:24:36", "throughput": 1486.89, "total_tokens": 20114848} {"current_steps": 95315, "total_steps": 181800, "loss": 0.0492, "lr": 2.7241529100505968e-05, "epoch": 10.485698569856986, "percentage": 52.43, "elapsed_time": "3:45:28", "remaining_time": "3:24:35", "throughput": 1486.9, "total_tokens": 20115968} {"current_steps": 95320, "total_steps": 181800, "loss": 0.0075, "lr": 2.723913868914039e-05, "epoch": 10.486248624862487, "percentage": 52.43, "elapsed_time": "3:45:29", "remaining_time": "3:24:34", "throughput": 1486.89, "total_tokens": 20116992} {"current_steps": 95325, "total_steps": 181800, "loss": 0.0165, "lr": 2.723674825713775e-05, "epoch": 10.486798679867986, "percentage": 52.43, "elapsed_time": "3:45:30", "remaining_time": "3:24:34", "throughput": 1486.89, "total_tokens": 20117984} {"current_steps": 95330, "total_steps": 181800, "loss": 0.1089, "lr": 2.7234357804520076e-05, "epoch": 10.487348734873487, "percentage": 52.44, "elapsed_time": "3:45:30", "remaining_time": "3:24:33", "throughput": 1486.89, "total_tokens": 20119008} {"current_steps": 95335, "total_steps": 181800, "loss": 0.0172, "lr": 2.7231967331309398e-05, "epoch": 10.487898789878988, "percentage": 52.44, "elapsed_time": "3:45:31", "remaining_time": "3:24:32", "throughput": 1486.9, "total_tokens": 20120128} {"current_steps": 95340, "total_steps": 181800, "loss": 0.0368, "lr": 2.722957683752775e-05, "epoch": 10.488448844884488, "percentage": 52.44, "elapsed_time": "3:45:32", "remaining_time": "3:24:31", "throughput": 1486.9, "total_tokens": 20121152} {"current_steps": 95345, "total_steps": 181800, "loss": 0.0122, "lr": 2.7227186323197162e-05, "epoch": 10.488998899889989, "percentage": 52.44, "elapsed_time": "3:45:32", "remaining_time": "3:24:31", "throughput": 1486.9, "total_tokens": 20122144} {"current_steps": 95350, "total_steps": 181800, "loss": 0.1345, "lr": 2.7224795788339656e-05, "epoch": 10.48954895489549, "percentage": 52.45, "elapsed_time": "3:45:33", "remaining_time": "3:24:30", "throughput": 1486.9, "total_tokens": 20123264} {"current_steps": 95355, "total_steps": 181800, "loss": 0.0819, "lr": 2.7222405232977282e-05, "epoch": 10.490099009900991, "percentage": 52.45, "elapsed_time": "3:45:34", "remaining_time": "3:24:29", "throughput": 1486.91, "total_tokens": 20124352} {"current_steps": 95360, "total_steps": 181800, "loss": 0.2329, "lr": 2.722001465713207e-05, "epoch": 10.49064906490649, "percentage": 52.45, "elapsed_time": "3:45:35", "remaining_time": "3:24:28", "throughput": 1486.91, "total_tokens": 20125472} {"current_steps": 95365, "total_steps": 181800, "loss": 0.0162, "lr": 2.7217624060826047e-05, "epoch": 10.491199119911991, "percentage": 52.46, "elapsed_time": "3:45:35", "remaining_time": "3:24:28", "throughput": 1486.92, "total_tokens": 20126528} {"current_steps": 95370, "total_steps": 181800, "loss": 0.0295, "lr": 2.7215233444081245e-05, "epoch": 10.491749174917492, "percentage": 52.46, "elapsed_time": "3:45:36", "remaining_time": "3:24:27", "throughput": 1486.92, "total_tokens": 20127552} {"current_steps": 95375, "total_steps": 181800, "loss": 0.0018, "lr": 2.7212842806919696e-05, "epoch": 10.492299229922992, "percentage": 52.46, "elapsed_time": "3:45:37", "remaining_time": "3:24:26", "throughput": 1486.92, "total_tokens": 20128608} {"current_steps": 95380, "total_steps": 181800, "loss": 0.0287, "lr": 2.7210452149363437e-05, "epoch": 10.492849284928493, "percentage": 52.46, "elapsed_time": "3:45:37", "remaining_time": "3:24:26", "throughput": 1486.92, "total_tokens": 20129664} {"current_steps": 95385, "total_steps": 181800, "loss": 0.0154, "lr": 2.720806147143451e-05, "epoch": 10.493399339933994, "percentage": 52.47, "elapsed_time": "3:45:38", "remaining_time": "3:24:25", "throughput": 1486.92, "total_tokens": 20130688} {"current_steps": 95390, "total_steps": 181800, "loss": 0.0625, "lr": 2.7205670773154927e-05, "epoch": 10.493949394939493, "percentage": 52.47, "elapsed_time": "3:45:39", "remaining_time": "3:24:24", "throughput": 1486.93, "total_tokens": 20131744} {"current_steps": 95395, "total_steps": 181800, "loss": 0.0036, "lr": 2.7203280054546743e-05, "epoch": 10.494499449944994, "percentage": 52.47, "elapsed_time": "3:45:39", "remaining_time": "3:24:23", "throughput": 1486.93, "total_tokens": 20132800} {"current_steps": 95400, "total_steps": 181800, "loss": 0.0645, "lr": 2.7200889315631983e-05, "epoch": 10.495049504950495, "percentage": 52.48, "elapsed_time": "3:45:40", "remaining_time": "3:24:23", "throughput": 1486.92, "total_tokens": 20133760} {"current_steps": 95405, "total_steps": 181800, "loss": 0.1046, "lr": 2.7198498556432682e-05, "epoch": 10.495599559955995, "percentage": 52.48, "elapsed_time": "3:45:41", "remaining_time": "3:24:22", "throughput": 1486.93, "total_tokens": 20134816} {"current_steps": 95410, "total_steps": 181800, "loss": 0.1555, "lr": 2.7196107776970876e-05, "epoch": 10.496149614961496, "percentage": 52.48, "elapsed_time": "3:45:41", "remaining_time": "3:24:21", "throughput": 1486.92, "total_tokens": 20135776} {"current_steps": 95415, "total_steps": 181800, "loss": 0.0132, "lr": 2.7193716977268597e-05, "epoch": 10.496699669966997, "percentage": 52.48, "elapsed_time": "3:45:42", "remaining_time": "3:24:20", "throughput": 1486.92, "total_tokens": 20136768} {"current_steps": 95420, "total_steps": 181800, "loss": 0.0962, "lr": 2.719132615734788e-05, "epoch": 10.497249724972498, "percentage": 52.49, "elapsed_time": "3:45:43", "remaining_time": "3:24:20", "throughput": 1486.92, "total_tokens": 20137792} {"current_steps": 95425, "total_steps": 181800, "loss": 0.0189, "lr": 2.718893531723076e-05, "epoch": 10.497799779977997, "percentage": 52.49, "elapsed_time": "3:45:43", "remaining_time": "3:24:19", "throughput": 1486.92, "total_tokens": 20138848} {"current_steps": 95430, "total_steps": 181800, "loss": 0.0059, "lr": 2.7186544456939284e-05, "epoch": 10.498349834983498, "percentage": 52.49, "elapsed_time": "3:45:44", "remaining_time": "3:24:18", "throughput": 1486.92, "total_tokens": 20139904} {"current_steps": 95435, "total_steps": 181800, "loss": 0.0052, "lr": 2.7184153576495463e-05, "epoch": 10.498899889989, "percentage": 52.49, "elapsed_time": "3:45:45", "remaining_time": "3:24:18", "throughput": 1486.92, "total_tokens": 20140896} {"current_steps": 95440, "total_steps": 181800, "loss": 0.0111, "lr": 2.7181762675921352e-05, "epoch": 10.499449944994499, "percentage": 52.5, "elapsed_time": "3:45:46", "remaining_time": "3:24:17", "throughput": 1486.92, "total_tokens": 20141920} {"current_steps": 95445, "total_steps": 181800, "loss": 0.0042, "lr": 2.7179371755238987e-05, "epoch": 10.5, "percentage": 52.5, "elapsed_time": "3:45:46", "remaining_time": "3:24:16", "throughput": 1486.93, "total_tokens": 20143040} {"current_steps": 95450, "total_steps": 181800, "loss": 0.0561, "lr": 2.7176980814470388e-05, "epoch": 10.500550055005501, "percentage": 52.5, "elapsed_time": "3:45:47", "remaining_time": "3:24:15", "throughput": 1486.93, "total_tokens": 20144096} {"current_steps": 95455, "total_steps": 181800, "loss": 0.0051, "lr": 2.717458985363761e-05, "epoch": 10.501100110011, "percentage": 52.51, "elapsed_time": "3:45:48", "remaining_time": "3:24:15", "throughput": 1486.93, "total_tokens": 20145152} {"current_steps": 95460, "total_steps": 181800, "loss": 0.057, "lr": 2.7172198872762676e-05, "epoch": 10.501650165016502, "percentage": 52.51, "elapsed_time": "3:45:48", "remaining_time": "3:24:14", "throughput": 1486.93, "total_tokens": 20146176} {"current_steps": 95465, "total_steps": 181800, "loss": 0.0212, "lr": 2.7169807871867626e-05, "epoch": 10.502200220022003, "percentage": 52.51, "elapsed_time": "3:45:49", "remaining_time": "3:24:13", "throughput": 1486.93, "total_tokens": 20147232} {"current_steps": 95470, "total_steps": 181800, "loss": 0.104, "lr": 2.7167416850974504e-05, "epoch": 10.502750275027502, "percentage": 52.51, "elapsed_time": "3:45:50", "remaining_time": "3:24:12", "throughput": 1486.94, "total_tokens": 20148320} {"current_steps": 95475, "total_steps": 181800, "loss": 0.0093, "lr": 2.7165025810105336e-05, "epoch": 10.503300330033003, "percentage": 52.52, "elapsed_time": "3:45:50", "remaining_time": "3:24:12", "throughput": 1486.94, "total_tokens": 20149376} {"current_steps": 95480, "total_steps": 181800, "loss": 0.1944, "lr": 2.7162634749282167e-05, "epoch": 10.503850385038504, "percentage": 52.52, "elapsed_time": "3:45:51", "remaining_time": "3:24:11", "throughput": 1486.95, "total_tokens": 20150496} {"current_steps": 95485, "total_steps": 181800, "loss": 0.0428, "lr": 2.716024366852703e-05, "epoch": 10.504400440044005, "percentage": 52.52, "elapsed_time": "3:45:52", "remaining_time": "3:24:10", "throughput": 1486.95, "total_tokens": 20151552} {"current_steps": 95490, "total_steps": 181800, "loss": 0.0038, "lr": 2.7157852567861962e-05, "epoch": 10.504950495049505, "percentage": 52.52, "elapsed_time": "3:45:52", "remaining_time": "3:24:10", "throughput": 1486.95, "total_tokens": 20152608} {"current_steps": 95495, "total_steps": 181800, "loss": 0.0095, "lr": 2.7155461447309e-05, "epoch": 10.505500550055006, "percentage": 52.53, "elapsed_time": "3:45:53", "remaining_time": "3:24:09", "throughput": 1486.96, "total_tokens": 20153664} {"current_steps": 95500, "total_steps": 181800, "loss": 0.0538, "lr": 2.7153070306890188e-05, "epoch": 10.506050605060507, "percentage": 52.53, "elapsed_time": "3:45:54", "remaining_time": "3:24:08", "throughput": 1486.95, "total_tokens": 20154656} {"current_steps": 95505, "total_steps": 181800, "loss": 0.0404, "lr": 2.7150679146627566e-05, "epoch": 10.506600660066006, "percentage": 52.53, "elapsed_time": "3:45:55", "remaining_time": "3:24:07", "throughput": 1486.96, "total_tokens": 20155744} {"current_steps": 95510, "total_steps": 181800, "loss": 0.0127, "lr": 2.7148287966543157e-05, "epoch": 10.507150715071507, "percentage": 52.54, "elapsed_time": "3:45:55", "remaining_time": "3:24:07", "throughput": 1486.96, "total_tokens": 20156800} {"current_steps": 95515, "total_steps": 181800, "loss": 0.0187, "lr": 2.7145896766659014e-05, "epoch": 10.507700770077008, "percentage": 52.54, "elapsed_time": "3:45:56", "remaining_time": "3:24:06", "throughput": 1486.96, "total_tokens": 20157888} {"current_steps": 95520, "total_steps": 181800, "loss": 0.0087, "lr": 2.7143505546997166e-05, "epoch": 10.508250825082508, "percentage": 52.54, "elapsed_time": "3:45:57", "remaining_time": "3:24:05", "throughput": 1486.96, "total_tokens": 20158880} {"current_steps": 95525, "total_steps": 181800, "loss": 0.0089, "lr": 2.7141114307579664e-05, "epoch": 10.508800880088009, "percentage": 52.54, "elapsed_time": "3:45:57", "remaining_time": "3:24:04", "throughput": 1486.97, "total_tokens": 20160000} {"current_steps": 95530, "total_steps": 181800, "loss": 0.0184, "lr": 2.7138723048428534e-05, "epoch": 10.50935093509351, "percentage": 52.55, "elapsed_time": "3:45:58", "remaining_time": "3:24:04", "throughput": 1486.97, "total_tokens": 20161088} {"current_steps": 95535, "total_steps": 181800, "loss": 0.0019, "lr": 2.7136331769565816e-05, "epoch": 10.509900990099009, "percentage": 52.55, "elapsed_time": "3:45:59", "remaining_time": "3:24:03", "throughput": 1486.98, "total_tokens": 20162144} {"current_steps": 95540, "total_steps": 181800, "loss": 0.018, "lr": 2.7133940471013552e-05, "epoch": 10.51045104510451, "percentage": 52.55, "elapsed_time": "3:45:59", "remaining_time": "3:24:02", "throughput": 1486.98, "total_tokens": 20163232} {"current_steps": 95545, "total_steps": 181800, "loss": 0.1108, "lr": 2.713154915279379e-05, "epoch": 10.511001100110011, "percentage": 52.56, "elapsed_time": "3:46:00", "remaining_time": "3:24:02", "throughput": 1486.99, "total_tokens": 20164320} {"current_steps": 95550, "total_steps": 181800, "loss": 0.1001, "lr": 2.712915781492856e-05, "epoch": 10.511551155115512, "percentage": 52.56, "elapsed_time": "3:46:01", "remaining_time": "3:24:01", "throughput": 1486.99, "total_tokens": 20165408} {"current_steps": 95555, "total_steps": 181800, "loss": 0.048, "lr": 2.7126766457439902e-05, "epoch": 10.512101210121012, "percentage": 52.56, "elapsed_time": "3:46:01", "remaining_time": "3:24:00", "throughput": 1486.99, "total_tokens": 20166432} {"current_steps": 95560, "total_steps": 181800, "loss": 0.1062, "lr": 2.7124375080349863e-05, "epoch": 10.512651265126513, "percentage": 52.56, "elapsed_time": "3:46:02", "remaining_time": "3:23:59", "throughput": 1487.0, "total_tokens": 20167552} {"current_steps": 95565, "total_steps": 181800, "loss": 0.0336, "lr": 2.7121983683680474e-05, "epoch": 10.513201320132014, "percentage": 52.57, "elapsed_time": "3:46:03", "remaining_time": "3:23:59", "throughput": 1487.0, "total_tokens": 20168576} {"current_steps": 95570, "total_steps": 181800, "loss": 0.0272, "lr": 2.7119592267453775e-05, "epoch": 10.513751375137513, "percentage": 52.57, "elapsed_time": "3:46:03", "remaining_time": "3:23:58", "throughput": 1487.0, "total_tokens": 20169696} {"current_steps": 95575, "total_steps": 181800, "loss": 0.0205, "lr": 2.711720083169182e-05, "epoch": 10.514301430143014, "percentage": 52.57, "elapsed_time": "3:46:04", "remaining_time": "3:23:57", "throughput": 1487.01, "total_tokens": 20170752} {"current_steps": 95580, "total_steps": 181800, "loss": 0.0206, "lr": 2.7114809376416632e-05, "epoch": 10.514851485148515, "percentage": 52.57, "elapsed_time": "3:46:05", "remaining_time": "3:23:56", "throughput": 1487.01, "total_tokens": 20171872} {"current_steps": 95585, "total_steps": 181800, "loss": 0.0211, "lr": 2.7112417901650267e-05, "epoch": 10.515401540154015, "percentage": 52.58, "elapsed_time": "3:46:06", "remaining_time": "3:23:56", "throughput": 1487.02, "total_tokens": 20172960} {"current_steps": 95590, "total_steps": 181800, "loss": 0.0053, "lr": 2.711002640741476e-05, "epoch": 10.515951595159516, "percentage": 52.58, "elapsed_time": "3:46:06", "remaining_time": "3:23:55", "throughput": 1487.02, "total_tokens": 20174016} {"current_steps": 95595, "total_steps": 181800, "loss": 0.0125, "lr": 2.7107634893732155e-05, "epoch": 10.516501650165017, "percentage": 52.58, "elapsed_time": "3:46:07", "remaining_time": "3:23:54", "throughput": 1487.02, "total_tokens": 20175072} {"current_steps": 95600, "total_steps": 181800, "loss": 0.0678, "lr": 2.7105243360624484e-05, "epoch": 10.517051705170516, "percentage": 52.59, "elapsed_time": "3:46:08", "remaining_time": "3:23:54", "throughput": 1487.03, "total_tokens": 20176192} {"current_steps": 95605, "total_steps": 181800, "loss": 0.0281, "lr": 2.71028518081138e-05, "epoch": 10.517601760176017, "percentage": 52.59, "elapsed_time": "3:46:08", "remaining_time": "3:23:53", "throughput": 1487.03, "total_tokens": 20177184} {"current_steps": 95610, "total_steps": 181800, "loss": 0.0242, "lr": 2.710046023622213e-05, "epoch": 10.518151815181518, "percentage": 52.59, "elapsed_time": "3:46:09", "remaining_time": "3:23:52", "throughput": 1487.03, "total_tokens": 20178272} {"current_steps": 95615, "total_steps": 181800, "loss": 0.0052, "lr": 2.7098068644971537e-05, "epoch": 10.51870187018702, "percentage": 52.59, "elapsed_time": "3:46:10", "remaining_time": "3:23:51", "throughput": 1487.03, "total_tokens": 20179264} {"current_steps": 95620, "total_steps": 181800, "loss": 0.0071, "lr": 2.7095677034384048e-05, "epoch": 10.519251925192519, "percentage": 52.6, "elapsed_time": "3:46:10", "remaining_time": "3:23:51", "throughput": 1487.04, "total_tokens": 20180352} {"current_steps": 95625, "total_steps": 181800, "loss": 0.0174, "lr": 2.709328540448171e-05, "epoch": 10.51980198019802, "percentage": 52.6, "elapsed_time": "3:46:11", "remaining_time": "3:23:50", "throughput": 1487.03, "total_tokens": 20181344} {"current_steps": 95630, "total_steps": 181800, "loss": 0.0038, "lr": 2.7090893755286566e-05, "epoch": 10.520352035203521, "percentage": 52.6, "elapsed_time": "3:46:12", "remaining_time": "3:23:49", "throughput": 1487.04, "total_tokens": 20182400} {"current_steps": 95635, "total_steps": 181800, "loss": 0.0083, "lr": 2.7088502086820656e-05, "epoch": 10.52090209020902, "percentage": 52.6, "elapsed_time": "3:46:12", "remaining_time": "3:23:48", "throughput": 1487.03, "total_tokens": 20183360} {"current_steps": 95640, "total_steps": 181800, "loss": 0.0511, "lr": 2.708611039910602e-05, "epoch": 10.521452145214521, "percentage": 52.61, "elapsed_time": "3:46:13", "remaining_time": "3:23:48", "throughput": 1487.04, "total_tokens": 20184480} {"current_steps": 95645, "total_steps": 181800, "loss": 0.0226, "lr": 2.7083718692164718e-05, "epoch": 10.522002200220022, "percentage": 52.61, "elapsed_time": "3:46:14", "remaining_time": "3:23:47", "throughput": 1487.04, "total_tokens": 20185536} {"current_steps": 95650, "total_steps": 181800, "loss": 0.0109, "lr": 2.708132696601877e-05, "epoch": 10.522552255225522, "percentage": 52.61, "elapsed_time": "3:46:15", "remaining_time": "3:23:46", "throughput": 1487.05, "total_tokens": 20186656} {"current_steps": 95655, "total_steps": 181800, "loss": 0.0022, "lr": 2.7078935220690228e-05, "epoch": 10.523102310231023, "percentage": 52.62, "elapsed_time": "3:46:15", "remaining_time": "3:23:46", "throughput": 1487.05, "total_tokens": 20187680} {"current_steps": 95660, "total_steps": 181800, "loss": 0.0168, "lr": 2.7076543456201142e-05, "epoch": 10.523652365236524, "percentage": 52.62, "elapsed_time": "3:46:16", "remaining_time": "3:23:45", "throughput": 1487.04, "total_tokens": 20188672} {"current_steps": 95665, "total_steps": 181800, "loss": 0.0156, "lr": 2.7074151672573554e-05, "epoch": 10.524202420242025, "percentage": 52.62, "elapsed_time": "3:46:17", "remaining_time": "3:23:44", "throughput": 1487.04, "total_tokens": 20189728} {"current_steps": 95670, "total_steps": 181800, "loss": 0.0318, "lr": 2.7071759869829506e-05, "epoch": 10.524752475247524, "percentage": 52.62, "elapsed_time": "3:46:17", "remaining_time": "3:23:43", "throughput": 1487.05, "total_tokens": 20190816} {"current_steps": 95675, "total_steps": 181800, "loss": 0.0799, "lr": 2.7069368047991038e-05, "epoch": 10.525302530253025, "percentage": 52.63, "elapsed_time": "3:46:18", "remaining_time": "3:23:43", "throughput": 1487.06, "total_tokens": 20191936} {"current_steps": 95680, "total_steps": 181800, "loss": 0.0569, "lr": 2.7066976207080197e-05, "epoch": 10.525852585258527, "percentage": 52.63, "elapsed_time": "3:46:19", "remaining_time": "3:23:42", "throughput": 1487.06, "total_tokens": 20192992} {"current_steps": 95685, "total_steps": 181800, "loss": 0.0226, "lr": 2.7064584347119026e-05, "epoch": 10.526402640264026, "percentage": 52.63, "elapsed_time": "3:46:19", "remaining_time": "3:23:41", "throughput": 1487.06, "total_tokens": 20194016} {"current_steps": 95690, "total_steps": 181800, "loss": 0.0039, "lr": 2.706219246812958e-05, "epoch": 10.526952695269527, "percentage": 52.63, "elapsed_time": "3:46:20", "remaining_time": "3:23:40", "throughput": 1487.06, "total_tokens": 20195072} {"current_steps": 95695, "total_steps": 181800, "loss": 0.0035, "lr": 2.7059800570133887e-05, "epoch": 10.527502750275028, "percentage": 52.64, "elapsed_time": "3:46:21", "remaining_time": "3:23:40", "throughput": 1487.06, "total_tokens": 20196064} {"current_steps": 95700, "total_steps": 181800, "loss": 0.015, "lr": 2.7057408653154005e-05, "epoch": 10.528052805280527, "percentage": 52.64, "elapsed_time": "3:46:21", "remaining_time": "3:23:39", "throughput": 1487.06, "total_tokens": 20197120} {"current_steps": 95705, "total_steps": 181800, "loss": 0.0093, "lr": 2.705501671721198e-05, "epoch": 10.528602860286028, "percentage": 52.64, "elapsed_time": "3:46:22", "remaining_time": "3:23:38", "throughput": 1487.06, "total_tokens": 20198176} {"current_steps": 95710, "total_steps": 181800, "loss": 0.0052, "lr": 2.7052624762329844e-05, "epoch": 10.52915291529153, "percentage": 52.65, "elapsed_time": "3:46:23", "remaining_time": "3:23:38", "throughput": 1487.06, "total_tokens": 20199232} {"current_steps": 95715, "total_steps": 181800, "loss": 0.0718, "lr": 2.7050232788529643e-05, "epoch": 10.52970297029703, "percentage": 52.65, "elapsed_time": "3:46:23", "remaining_time": "3:23:37", "throughput": 1487.07, "total_tokens": 20200320} {"current_steps": 95720, "total_steps": 181800, "loss": 0.021, "lr": 2.7047840795833453e-05, "epoch": 10.53025302530253, "percentage": 52.65, "elapsed_time": "3:46:24", "remaining_time": "3:23:36", "throughput": 1487.07, "total_tokens": 20201344} {"current_steps": 95725, "total_steps": 181800, "loss": 0.0702, "lr": 2.7045448784263278e-05, "epoch": 10.530803080308031, "percentage": 52.65, "elapsed_time": "3:46:25", "remaining_time": "3:23:35", "throughput": 1487.07, "total_tokens": 20202432} {"current_steps": 95730, "total_steps": 181800, "loss": 0.0107, "lr": 2.7043056753841188e-05, "epoch": 10.531353135313532, "percentage": 52.66, "elapsed_time": "3:46:26", "remaining_time": "3:23:35", "throughput": 1487.08, "total_tokens": 20203520} {"current_steps": 95735, "total_steps": 181800, "loss": 0.0766, "lr": 2.7040664704589224e-05, "epoch": 10.531903190319031, "percentage": 52.66, "elapsed_time": "3:46:26", "remaining_time": "3:23:34", "throughput": 1487.08, "total_tokens": 20204608} {"current_steps": 95740, "total_steps": 181800, "loss": 0.0228, "lr": 2.7038272636529432e-05, "epoch": 10.532453245324533, "percentage": 52.66, "elapsed_time": "3:46:27", "remaining_time": "3:23:33", "throughput": 1487.08, "total_tokens": 20205632} {"current_steps": 95745, "total_steps": 181800, "loss": 0.0542, "lr": 2.7035880549683862e-05, "epoch": 10.533003300330034, "percentage": 52.67, "elapsed_time": "3:46:28", "remaining_time": "3:23:32", "throughput": 1487.08, "total_tokens": 20206656} {"current_steps": 95750, "total_steps": 181800, "loss": 0.0201, "lr": 2.703348844407456e-05, "epoch": 10.533553355335533, "percentage": 52.67, "elapsed_time": "3:46:28", "remaining_time": "3:23:32", "throughput": 1487.09, "total_tokens": 20207712} {"current_steps": 95755, "total_steps": 181800, "loss": 0.0014, "lr": 2.7031096319723565e-05, "epoch": 10.534103410341034, "percentage": 52.67, "elapsed_time": "3:46:29", "remaining_time": "3:23:31", "throughput": 1487.08, "total_tokens": 20208704} {"current_steps": 95760, "total_steps": 181800, "loss": 0.0102, "lr": 2.702870417665293e-05, "epoch": 10.534653465346535, "percentage": 52.67, "elapsed_time": "3:46:30", "remaining_time": "3:23:30", "throughput": 1487.09, "total_tokens": 20209792} {"current_steps": 95765, "total_steps": 181800, "loss": 0.0698, "lr": 2.7026312014884715e-05, "epoch": 10.535203520352034, "percentage": 52.68, "elapsed_time": "3:46:30", "remaining_time": "3:23:30", "throughput": 1487.09, "total_tokens": 20210816} {"current_steps": 95770, "total_steps": 181800, "loss": 0.0126, "lr": 2.7023919834440938e-05, "epoch": 10.535753575357536, "percentage": 52.68, "elapsed_time": "3:46:31", "remaining_time": "3:23:29", "throughput": 1487.09, "total_tokens": 20211936} {"current_steps": 95775, "total_steps": 181800, "loss": 0.0056, "lr": 2.702152763534367e-05, "epoch": 10.536303630363037, "percentage": 52.68, "elapsed_time": "3:46:32", "remaining_time": "3:23:28", "throughput": 1487.1, "total_tokens": 20213024} {"current_steps": 95780, "total_steps": 181800, "loss": 0.0384, "lr": 2.701913541761495e-05, "epoch": 10.536853685368538, "percentage": 52.68, "elapsed_time": "3:46:32", "remaining_time": "3:23:27", "throughput": 1487.1, "total_tokens": 20214112} {"current_steps": 95785, "total_steps": 181800, "loss": 0.1237, "lr": 2.701674318127682e-05, "epoch": 10.537403740374037, "percentage": 52.69, "elapsed_time": "3:46:33", "remaining_time": "3:23:27", "throughput": 1487.11, "total_tokens": 20215168} {"current_steps": 95790, "total_steps": 181800, "loss": 0.0021, "lr": 2.7014350926351352e-05, "epoch": 10.537953795379538, "percentage": 52.69, "elapsed_time": "3:46:34", "remaining_time": "3:23:26", "throughput": 1487.11, "total_tokens": 20216224} {"current_steps": 95795, "total_steps": 181800, "loss": 0.0643, "lr": 2.7011958652860568e-05, "epoch": 10.53850385038504, "percentage": 52.69, "elapsed_time": "3:46:35", "remaining_time": "3:23:25", "throughput": 1487.11, "total_tokens": 20217312} {"current_steps": 95800, "total_steps": 181800, "loss": 0.0066, "lr": 2.700956636082653e-05, "epoch": 10.539053905390539, "percentage": 52.7, "elapsed_time": "3:46:35", "remaining_time": "3:23:24", "throughput": 1487.11, "total_tokens": 20218336} {"current_steps": 95805, "total_steps": 181800, "loss": 0.0294, "lr": 2.7007174050271277e-05, "epoch": 10.53960396039604, "percentage": 52.7, "elapsed_time": "3:46:36", "remaining_time": "3:23:24", "throughput": 1487.11, "total_tokens": 20219392} {"current_steps": 95810, "total_steps": 181800, "loss": 0.0382, "lr": 2.700478172121687e-05, "epoch": 10.54015401540154, "percentage": 52.7, "elapsed_time": "3:46:37", "remaining_time": "3:23:23", "throughput": 1487.12, "total_tokens": 20220448} {"current_steps": 95815, "total_steps": 181800, "loss": 0.0351, "lr": 2.7002389373685357e-05, "epoch": 10.54070407040704, "percentage": 52.7, "elapsed_time": "3:46:37", "remaining_time": "3:23:22", "throughput": 1487.12, "total_tokens": 20221472} {"current_steps": 95820, "total_steps": 181800, "loss": 0.0561, "lr": 2.6999997007698775e-05, "epoch": 10.541254125412541, "percentage": 52.71, "elapsed_time": "3:46:38", "remaining_time": "3:23:21", "throughput": 1487.12, "total_tokens": 20222528} {"current_steps": 95825, "total_steps": 181800, "loss": 0.0401, "lr": 2.6997604623279184e-05, "epoch": 10.541804180418042, "percentage": 52.71, "elapsed_time": "3:46:39", "remaining_time": "3:23:21", "throughput": 1487.12, "total_tokens": 20223552} {"current_steps": 95830, "total_steps": 181800, "loss": 0.0135, "lr": 2.6995212220448617e-05, "epoch": 10.542354235423542, "percentage": 52.71, "elapsed_time": "3:46:39", "remaining_time": "3:23:20", "throughput": 1487.12, "total_tokens": 20224544} {"current_steps": 95835, "total_steps": 181800, "loss": 0.143, "lr": 2.699281979922915e-05, "epoch": 10.542904290429043, "percentage": 52.71, "elapsed_time": "3:46:40", "remaining_time": "3:23:19", "throughput": 1487.12, "total_tokens": 20225600} {"current_steps": 95840, "total_steps": 181800, "loss": 0.042, "lr": 2.6990427359642822e-05, "epoch": 10.543454345434544, "percentage": 52.72, "elapsed_time": "3:46:41", "remaining_time": "3:23:19", "throughput": 1487.12, "total_tokens": 20226656} {"current_steps": 95845, "total_steps": 181800, "loss": 0.0031, "lr": 2.6988034901711668e-05, "epoch": 10.544004400440045, "percentage": 52.72, "elapsed_time": "3:46:41", "remaining_time": "3:23:18", "throughput": 1487.13, "total_tokens": 20227744} {"current_steps": 95850, "total_steps": 181800, "loss": 0.0074, "lr": 2.6985642425457757e-05, "epoch": 10.544554455445544, "percentage": 52.72, "elapsed_time": "3:46:42", "remaining_time": "3:23:17", "throughput": 1487.13, "total_tokens": 20228800} {"current_steps": 95855, "total_steps": 181800, "loss": 0.0056, "lr": 2.698324993090313e-05, "epoch": 10.545104510451045, "percentage": 52.73, "elapsed_time": "3:46:43", "remaining_time": "3:23:16", "throughput": 1487.13, "total_tokens": 20229856} {"current_steps": 95860, "total_steps": 181800, "loss": 0.0075, "lr": 2.6980857418069845e-05, "epoch": 10.545654565456546, "percentage": 52.73, "elapsed_time": "3:46:43", "remaining_time": "3:23:16", "throughput": 1487.13, "total_tokens": 20230880} {"current_steps": 95865, "total_steps": 181800, "loss": 0.0197, "lr": 2.6978464886979943e-05, "epoch": 10.546204620462046, "percentage": 52.73, "elapsed_time": "3:46:44", "remaining_time": "3:23:15", "throughput": 1487.13, "total_tokens": 20231936} {"current_steps": 95870, "total_steps": 181800, "loss": 0.0109, "lr": 2.697607233765548e-05, "epoch": 10.546754675467547, "percentage": 52.73, "elapsed_time": "3:46:45", "remaining_time": "3:23:14", "throughput": 1487.14, "total_tokens": 20233056} {"current_steps": 95875, "total_steps": 181800, "loss": 0.0475, "lr": 2.6973679770118505e-05, "epoch": 10.547304730473048, "percentage": 52.74, "elapsed_time": "3:46:46", "remaining_time": "3:23:13", "throughput": 1487.14, "total_tokens": 20234112} {"current_steps": 95880, "total_steps": 181800, "loss": 0.0923, "lr": 2.697128718439107e-05, "epoch": 10.547854785478547, "percentage": 52.74, "elapsed_time": "3:46:46", "remaining_time": "3:23:13", "throughput": 1487.15, "total_tokens": 20235232} {"current_steps": 95885, "total_steps": 181800, "loss": 0.0227, "lr": 2.696889458049523e-05, "epoch": 10.548404840484048, "percentage": 52.74, "elapsed_time": "3:46:47", "remaining_time": "3:23:12", "throughput": 1487.15, "total_tokens": 20236224} {"current_steps": 95890, "total_steps": 181800, "loss": 0.0117, "lr": 2.6966501958453033e-05, "epoch": 10.54895489548955, "percentage": 52.74, "elapsed_time": "3:46:48", "remaining_time": "3:23:11", "throughput": 1487.15, "total_tokens": 20237312} {"current_steps": 95895, "total_steps": 181800, "loss": 0.0168, "lr": 2.6964109318286534e-05, "epoch": 10.549504950495049, "percentage": 52.75, "elapsed_time": "3:46:48", "remaining_time": "3:23:11", "throughput": 1487.16, "total_tokens": 20238432} {"current_steps": 95900, "total_steps": 181800, "loss": 0.0035, "lr": 2.6961716660017773e-05, "epoch": 10.55005500550055, "percentage": 52.75, "elapsed_time": "3:46:49", "remaining_time": "3:23:10", "throughput": 1487.16, "total_tokens": 20239488} {"current_steps": 95905, "total_steps": 181800, "loss": 0.0031, "lr": 2.6959323983668815e-05, "epoch": 10.55060506050605, "percentage": 52.75, "elapsed_time": "3:46:50", "remaining_time": "3:23:09", "throughput": 1487.17, "total_tokens": 20240576} {"current_steps": 95910, "total_steps": 181800, "loss": 0.0076, "lr": 2.6956931289261715e-05, "epoch": 10.551155115511552, "percentage": 52.76, "elapsed_time": "3:46:50", "remaining_time": "3:23:08", "throughput": 1487.17, "total_tokens": 20241696} {"current_steps": 95915, "total_steps": 181800, "loss": 0.1429, "lr": 2.6954538576818512e-05, "epoch": 10.551705170517051, "percentage": 52.76, "elapsed_time": "3:46:51", "remaining_time": "3:23:08", "throughput": 1487.18, "total_tokens": 20242752} {"current_steps": 95920, "total_steps": 181800, "loss": 0.0193, "lr": 2.6952145846361266e-05, "epoch": 10.552255225522552, "percentage": 52.76, "elapsed_time": "3:46:52", "remaining_time": "3:23:07", "throughput": 1487.18, "total_tokens": 20243776} {"current_steps": 95925, "total_steps": 181800, "loss": 0.0026, "lr": 2.6949753097912027e-05, "epoch": 10.552805280528053, "percentage": 52.76, "elapsed_time": "3:46:52", "remaining_time": "3:23:06", "throughput": 1487.18, "total_tokens": 20244800} {"current_steps": 95930, "total_steps": 181800, "loss": 0.0091, "lr": 2.6947360331492855e-05, "epoch": 10.553355335533553, "percentage": 52.77, "elapsed_time": "3:46:53", "remaining_time": "3:23:05", "throughput": 1487.18, "total_tokens": 20245824} {"current_steps": 95935, "total_steps": 181800, "loss": 0.0401, "lr": 2.6944967547125794e-05, "epoch": 10.553905390539054, "percentage": 52.77, "elapsed_time": "3:46:54", "remaining_time": "3:23:05", "throughput": 1487.17, "total_tokens": 20246816} {"current_steps": 95940, "total_steps": 181800, "loss": 0.079, "lr": 2.69425747448329e-05, "epoch": 10.554455445544555, "percentage": 52.77, "elapsed_time": "3:46:54", "remaining_time": "3:23:04", "throughput": 1487.18, "total_tokens": 20247904} {"current_steps": 95945, "total_steps": 181800, "loss": 0.0112, "lr": 2.694018192463622e-05, "epoch": 10.555005500550054, "percentage": 52.78, "elapsed_time": "3:46:55", "remaining_time": "3:23:03", "throughput": 1487.18, "total_tokens": 20248928} {"current_steps": 95950, "total_steps": 181800, "loss": 0.0163, "lr": 2.6937789086557817e-05, "epoch": 10.555555555555555, "percentage": 52.78, "elapsed_time": "3:46:56", "remaining_time": "3:23:03", "throughput": 1487.18, "total_tokens": 20250016} {"current_steps": 95955, "total_steps": 181800, "loss": 0.0085, "lr": 2.6935396230619752e-05, "epoch": 10.556105610561056, "percentage": 52.78, "elapsed_time": "3:46:57", "remaining_time": "3:23:02", "throughput": 1487.18, "total_tokens": 20251040} {"current_steps": 95960, "total_steps": 181800, "loss": 0.0046, "lr": 2.693300335684406e-05, "epoch": 10.556655665566556, "percentage": 52.78, "elapsed_time": "3:46:57", "remaining_time": "3:23:01", "throughput": 1487.19, "total_tokens": 20252128} {"current_steps": 95965, "total_steps": 181800, "loss": 0.0061, "lr": 2.6930610465252802e-05, "epoch": 10.557205720572057, "percentage": 52.79, "elapsed_time": "3:46:58", "remaining_time": "3:23:00", "throughput": 1487.18, "total_tokens": 20253120} {"current_steps": 95970, "total_steps": 181800, "loss": 0.0086, "lr": 2.6928217555868042e-05, "epoch": 10.557755775577558, "percentage": 52.79, "elapsed_time": "3:46:59", "remaining_time": "3:23:00", "throughput": 1487.18, "total_tokens": 20254144} {"current_steps": 95975, "total_steps": 181800, "loss": 0.0026, "lr": 2.6925824628711816e-05, "epoch": 10.558305830583059, "percentage": 52.79, "elapsed_time": "3:46:59", "remaining_time": "3:22:59", "throughput": 1487.18, "total_tokens": 20255168} {"current_steps": 95980, "total_steps": 181800, "loss": 0.0093, "lr": 2.69234316838062e-05, "epoch": 10.558855885588558, "percentage": 52.79, "elapsed_time": "3:47:00", "remaining_time": "3:22:58", "throughput": 1487.18, "total_tokens": 20256192} {"current_steps": 95985, "total_steps": 181800, "loss": 0.0075, "lr": 2.6921038721173232e-05, "epoch": 10.55940594059406, "percentage": 52.8, "elapsed_time": "3:47:01", "remaining_time": "3:22:57", "throughput": 1487.18, "total_tokens": 20257216} {"current_steps": 95990, "total_steps": 181800, "loss": 0.0016, "lr": 2.6918645740834965e-05, "epoch": 10.55995599559956, "percentage": 52.8, "elapsed_time": "3:47:01", "remaining_time": "3:22:57", "throughput": 1487.19, "total_tokens": 20258304} {"current_steps": 95995, "total_steps": 181800, "loss": 0.0385, "lr": 2.691625274281347e-05, "epoch": 10.56050605060506, "percentage": 52.8, "elapsed_time": "3:47:02", "remaining_time": "3:22:56", "throughput": 1487.19, "total_tokens": 20259296} {"current_steps": 96000, "total_steps": 181800, "loss": 0.0089, "lr": 2.6913859727130786e-05, "epoch": 10.561056105610561, "percentage": 52.81, "elapsed_time": "3:47:03", "remaining_time": "3:22:55", "throughput": 1487.19, "total_tokens": 20260320} {"current_steps": 96005, "total_steps": 181800, "loss": 0.0025, "lr": 2.6911466693808978e-05, "epoch": 10.561606160616062, "percentage": 52.81, "elapsed_time": "3:47:03", "remaining_time": "3:22:55", "throughput": 1487.19, "total_tokens": 20261440} {"current_steps": 96010, "total_steps": 181800, "loss": 0.0017, "lr": 2.69090736428701e-05, "epoch": 10.562156215621561, "percentage": 52.81, "elapsed_time": "3:47:04", "remaining_time": "3:22:54", "throughput": 1487.19, "total_tokens": 20262464} {"current_steps": 96015, "total_steps": 181800, "loss": 0.0019, "lr": 2.690668057433621e-05, "epoch": 10.562706270627062, "percentage": 52.81, "elapsed_time": "3:47:05", "remaining_time": "3:22:53", "throughput": 1487.2, "total_tokens": 20263552} {"current_steps": 96020, "total_steps": 181800, "loss": 0.003, "lr": 2.690428748822935e-05, "epoch": 10.563256325632564, "percentage": 52.82, "elapsed_time": "3:47:06", "remaining_time": "3:22:52", "throughput": 1487.2, "total_tokens": 20264608} {"current_steps": 96025, "total_steps": 181800, "loss": 0.1902, "lr": 2.6901894384571597e-05, "epoch": 10.563806380638063, "percentage": 52.82, "elapsed_time": "3:47:06", "remaining_time": "3:22:52", "throughput": 1487.2, "total_tokens": 20265632} {"current_steps": 96030, "total_steps": 181800, "loss": 0.1202, "lr": 2.6899501263384985e-05, "epoch": 10.564356435643564, "percentage": 52.82, "elapsed_time": "3:47:07", "remaining_time": "3:22:51", "throughput": 1487.2, "total_tokens": 20266688} {"current_steps": 96035, "total_steps": 181800, "loss": 0.0366, "lr": 2.689710812469159e-05, "epoch": 10.564906490649065, "percentage": 52.82, "elapsed_time": "3:47:08", "remaining_time": "3:22:50", "throughput": 1487.21, "total_tokens": 20267808} {"current_steps": 96040, "total_steps": 181800, "loss": 0.0121, "lr": 2.6894714968513457e-05, "epoch": 10.565456545654566, "percentage": 52.83, "elapsed_time": "3:47:08", "remaining_time": "3:22:49", "throughput": 1487.21, "total_tokens": 20268928} {"current_steps": 96045, "total_steps": 181800, "loss": 0.0055, "lr": 2.689232179487265e-05, "epoch": 10.566006600660065, "percentage": 52.83, "elapsed_time": "3:47:09", "remaining_time": "3:22:49", "throughput": 1487.22, "total_tokens": 20270016} {"current_steps": 96050, "total_steps": 181800, "loss": 0.09, "lr": 2.6889928603791216e-05, "epoch": 10.566556655665567, "percentage": 52.83, "elapsed_time": "3:47:10", "remaining_time": "3:22:48", "throughput": 1487.22, "total_tokens": 20271040} {"current_steps": 96055, "total_steps": 181800, "loss": 0.0257, "lr": 2.6887535395291214e-05, "epoch": 10.567106710671068, "percentage": 52.84, "elapsed_time": "3:47:10", "remaining_time": "3:22:47", "throughput": 1487.21, "total_tokens": 20272032} {"current_steps": 96060, "total_steps": 181800, "loss": 0.0037, "lr": 2.6885142169394707e-05, "epoch": 10.567656765676567, "percentage": 52.84, "elapsed_time": "3:47:11", "remaining_time": "3:22:47", "throughput": 1487.21, "total_tokens": 20273056} {"current_steps": 96065, "total_steps": 181800, "loss": 0.0123, "lr": 2.6882748926123748e-05, "epoch": 10.568206820682068, "percentage": 52.84, "elapsed_time": "3:47:12", "remaining_time": "3:22:46", "throughput": 1487.21, "total_tokens": 20274048} {"current_steps": 96070, "total_steps": 181800, "loss": 0.0694, "lr": 2.6880355665500395e-05, "epoch": 10.56875687568757, "percentage": 52.84, "elapsed_time": "3:47:12", "remaining_time": "3:22:45", "throughput": 1487.22, "total_tokens": 20275168} {"current_steps": 96075, "total_steps": 181800, "loss": 0.0617, "lr": 2.6877962387546713e-05, "epoch": 10.569306930693068, "percentage": 52.85, "elapsed_time": "3:47:13", "remaining_time": "3:22:44", "throughput": 1487.22, "total_tokens": 20276224} {"current_steps": 96080, "total_steps": 181800, "loss": 0.0829, "lr": 2.6875569092284747e-05, "epoch": 10.56985698569857, "percentage": 52.85, "elapsed_time": "3:47:14", "remaining_time": "3:22:44", "throughput": 1487.23, "total_tokens": 20277312} {"current_steps": 96085, "total_steps": 181800, "loss": 0.0815, "lr": 2.687317577973656e-05, "epoch": 10.57040704070407, "percentage": 52.85, "elapsed_time": "3:47:15", "remaining_time": "3:22:43", "throughput": 1487.23, "total_tokens": 20278400} {"current_steps": 96090, "total_steps": 181800, "loss": 0.0063, "lr": 2.6870782449924207e-05, "epoch": 10.570957095709572, "percentage": 52.85, "elapsed_time": "3:47:15", "remaining_time": "3:22:42", "throughput": 1487.23, "total_tokens": 20279392} {"current_steps": 96095, "total_steps": 181800, "loss": 0.234, "lr": 2.6868389102869758e-05, "epoch": 10.571507150715071, "percentage": 52.86, "elapsed_time": "3:47:16", "remaining_time": "3:22:41", "throughput": 1487.23, "total_tokens": 20280416} {"current_steps": 96100, "total_steps": 181800, "loss": 0.0032, "lr": 2.6865995738595267e-05, "epoch": 10.572057205720572, "percentage": 52.86, "elapsed_time": "3:47:17", "remaining_time": "3:22:41", "throughput": 1487.23, "total_tokens": 20281504} {"current_steps": 96105, "total_steps": 181800, "loss": 0.0047, "lr": 2.6863602357122775e-05, "epoch": 10.572607260726073, "percentage": 52.86, "elapsed_time": "3:47:17", "remaining_time": "3:22:40", "throughput": 1487.24, "total_tokens": 20282560} {"current_steps": 96110, "total_steps": 181800, "loss": 0.004, "lr": 2.686120895847436e-05, "epoch": 10.573157315731573, "percentage": 52.87, "elapsed_time": "3:47:18", "remaining_time": "3:22:39", "throughput": 1487.24, "total_tokens": 20283648} {"current_steps": 96115, "total_steps": 181800, "loss": 0.0017, "lr": 2.6858815542672077e-05, "epoch": 10.573707370737074, "percentage": 52.87, "elapsed_time": "3:47:19", "remaining_time": "3:22:39", "throughput": 1487.24, "total_tokens": 20284704} {"current_steps": 96120, "total_steps": 181800, "loss": 0.0049, "lr": 2.685642210973799e-05, "epoch": 10.574257425742575, "percentage": 52.87, "elapsed_time": "3:47:19", "remaining_time": "3:22:38", "throughput": 1487.25, "total_tokens": 20285792} {"current_steps": 96125, "total_steps": 181800, "loss": 0.0264, "lr": 2.6854028659694142e-05, "epoch": 10.574807480748074, "percentage": 52.87, "elapsed_time": "3:47:20", "remaining_time": "3:22:37", "throughput": 1487.25, "total_tokens": 20286880} {"current_steps": 96130, "total_steps": 181800, "loss": 0.0551, "lr": 2.68516351925626e-05, "epoch": 10.575357535753575, "percentage": 52.88, "elapsed_time": "3:47:21", "remaining_time": "3:22:36", "throughput": 1487.25, "total_tokens": 20287936} {"current_steps": 96135, "total_steps": 181800, "loss": 0.0054, "lr": 2.6849241708365423e-05, "epoch": 10.575907590759076, "percentage": 52.88, "elapsed_time": "3:47:21", "remaining_time": "3:22:36", "throughput": 1487.26, "total_tokens": 20289024} {"current_steps": 96140, "total_steps": 181800, "loss": 0.1158, "lr": 2.6846848207124682e-05, "epoch": 10.576457645764577, "percentage": 52.88, "elapsed_time": "3:47:22", "remaining_time": "3:22:35", "throughput": 1487.26, "total_tokens": 20290016} {"current_steps": 96145, "total_steps": 181800, "loss": 0.0083, "lr": 2.684445468886242e-05, "epoch": 10.577007700770077, "percentage": 52.89, "elapsed_time": "3:47:23", "remaining_time": "3:22:34", "throughput": 1487.26, "total_tokens": 20291104} {"current_steps": 96150, "total_steps": 181800, "loss": 0.0713, "lr": 2.6842061153600712e-05, "epoch": 10.577557755775578, "percentage": 52.89, "elapsed_time": "3:47:23", "remaining_time": "3:22:33", "throughput": 1487.26, "total_tokens": 20292160} {"current_steps": 96155, "total_steps": 181800, "loss": 0.005, "lr": 2.6839667601361608e-05, "epoch": 10.578107810781079, "percentage": 52.89, "elapsed_time": "3:47:24", "remaining_time": "3:22:33", "throughput": 1487.26, "total_tokens": 20293216} {"current_steps": 96160, "total_steps": 181800, "loss": 0.0031, "lr": 2.6837274032167164e-05, "epoch": 10.578657865786578, "percentage": 52.89, "elapsed_time": "3:47:25", "remaining_time": "3:22:32", "throughput": 1487.26, "total_tokens": 20294240} {"current_steps": 96165, "total_steps": 181800, "loss": 0.0051, "lr": 2.6834880446039444e-05, "epoch": 10.57920792079208, "percentage": 52.9, "elapsed_time": "3:47:26", "remaining_time": "3:22:31", "throughput": 1487.27, "total_tokens": 20295296} {"current_steps": 96170, "total_steps": 181800, "loss": 0.0083, "lr": 2.6832486843000528e-05, "epoch": 10.57975797579758, "percentage": 52.9, "elapsed_time": "3:47:26", "remaining_time": "3:22:31", "throughput": 1487.27, "total_tokens": 20296320} {"current_steps": 96175, "total_steps": 181800, "loss": 0.0047, "lr": 2.6830093223072446e-05, "epoch": 10.58030803080308, "percentage": 52.9, "elapsed_time": "3:47:27", "remaining_time": "3:22:30", "throughput": 1487.27, "total_tokens": 20297376} {"current_steps": 96180, "total_steps": 181800, "loss": 0.0412, "lr": 2.6827699586277278e-05, "epoch": 10.58085808580858, "percentage": 52.9, "elapsed_time": "3:47:28", "remaining_time": "3:22:29", "throughput": 1487.27, "total_tokens": 20298432} {"current_steps": 96185, "total_steps": 181800, "loss": 0.0247, "lr": 2.6825305932637078e-05, "epoch": 10.581408140814082, "percentage": 52.91, "elapsed_time": "3:47:28", "remaining_time": "3:22:28", "throughput": 1487.27, "total_tokens": 20299488} {"current_steps": 96190, "total_steps": 181800, "loss": 0.0074, "lr": 2.6822912262173912e-05, "epoch": 10.581958195819581, "percentage": 52.91, "elapsed_time": "3:47:29", "remaining_time": "3:22:28", "throughput": 1487.28, "total_tokens": 20300576} {"current_steps": 96195, "total_steps": 181800, "loss": 0.0022, "lr": 2.6820518574909838e-05, "epoch": 10.582508250825082, "percentage": 52.91, "elapsed_time": "3:47:30", "remaining_time": "3:22:27", "throughput": 1487.28, "total_tokens": 20301632} {"current_steps": 96200, "total_steps": 181800, "loss": 0.0585, "lr": 2.681812487086691e-05, "epoch": 10.583058305830583, "percentage": 52.92, "elapsed_time": "3:47:30", "remaining_time": "3:22:26", "throughput": 1487.28, "total_tokens": 20302656} {"current_steps": 96205, "total_steps": 181800, "loss": 0.0074, "lr": 2.6815731150067204e-05, "epoch": 10.583608360836084, "percentage": 52.92, "elapsed_time": "3:47:31", "remaining_time": "3:22:25", "throughput": 1487.28, "total_tokens": 20303712} {"current_steps": 96210, "total_steps": 181800, "loss": 0.0009, "lr": 2.6813337412532775e-05, "epoch": 10.584158415841584, "percentage": 52.92, "elapsed_time": "3:47:32", "remaining_time": "3:22:25", "throughput": 1487.28, "total_tokens": 20304704} {"current_steps": 96215, "total_steps": 181800, "loss": 0.0727, "lr": 2.681094365828569e-05, "epoch": 10.584708470847085, "percentage": 52.92, "elapsed_time": "3:47:32", "remaining_time": "3:22:24", "throughput": 1487.28, "total_tokens": 20305728} {"current_steps": 96220, "total_steps": 181800, "loss": 0.0028, "lr": 2.6808549887348e-05, "epoch": 10.585258525852586, "percentage": 52.93, "elapsed_time": "3:47:33", "remaining_time": "3:22:23", "throughput": 1487.28, "total_tokens": 20306720} {"current_steps": 96225, "total_steps": 181800, "loss": 0.2429, "lr": 2.6806156099741776e-05, "epoch": 10.585808580858085, "percentage": 52.93, "elapsed_time": "3:47:34", "remaining_time": "3:22:23", "throughput": 1487.28, "total_tokens": 20307808} {"current_steps": 96230, "total_steps": 181800, "loss": 0.01, "lr": 2.6803762295489075e-05, "epoch": 10.586358635863586, "percentage": 52.93, "elapsed_time": "3:47:34", "remaining_time": "3:22:22", "throughput": 1487.29, "total_tokens": 20308896} {"current_steps": 96235, "total_steps": 181800, "loss": 0.024, "lr": 2.680136847461196e-05, "epoch": 10.586908690869087, "percentage": 52.93, "elapsed_time": "3:47:35", "remaining_time": "3:22:21", "throughput": 1487.29, "total_tokens": 20309952} {"current_steps": 96240, "total_steps": 181800, "loss": 0.0092, "lr": 2.6798974637132505e-05, "epoch": 10.587458745874587, "percentage": 52.94, "elapsed_time": "3:47:36", "remaining_time": "3:22:20", "throughput": 1487.29, "total_tokens": 20310944} {"current_steps": 96245, "total_steps": 181800, "loss": 0.0031, "lr": 2.679658078307276e-05, "epoch": 10.588008800880088, "percentage": 52.94, "elapsed_time": "3:47:37", "remaining_time": "3:22:20", "throughput": 1487.29, "total_tokens": 20312000} {"current_steps": 96250, "total_steps": 181800, "loss": 0.0096, "lr": 2.6794186912454787e-05, "epoch": 10.588558855885589, "percentage": 52.94, "elapsed_time": "3:47:37", "remaining_time": "3:22:19", "throughput": 1487.29, "total_tokens": 20313056} {"current_steps": 96255, "total_steps": 181800, "loss": 0.0141, "lr": 2.679179302530066e-05, "epoch": 10.589108910891088, "percentage": 52.95, "elapsed_time": "3:47:38", "remaining_time": "3:22:18", "throughput": 1487.3, "total_tokens": 20314208} {"current_steps": 96260, "total_steps": 181800, "loss": 0.0036, "lr": 2.6789399121632436e-05, "epoch": 10.58965896589659, "percentage": 52.95, "elapsed_time": "3:47:39", "remaining_time": "3:22:17", "throughput": 1487.3, "total_tokens": 20315296} {"current_steps": 96265, "total_steps": 181800, "loss": 0.0134, "lr": 2.678700520147218e-05, "epoch": 10.59020902090209, "percentage": 52.95, "elapsed_time": "3:47:39", "remaining_time": "3:22:17", "throughput": 1487.3, "total_tokens": 20316320} {"current_steps": 96270, "total_steps": 181800, "loss": 0.0015, "lr": 2.6784611264841952e-05, "epoch": 10.590759075907592, "percentage": 52.95, "elapsed_time": "3:47:40", "remaining_time": "3:22:16", "throughput": 1487.3, "total_tokens": 20317344} {"current_steps": 96275, "total_steps": 181800, "loss": 0.0064, "lr": 2.6782217311763824e-05, "epoch": 10.591309130913091, "percentage": 52.96, "elapsed_time": "3:47:41", "remaining_time": "3:22:15", "throughput": 1487.3, "total_tokens": 20318336} {"current_steps": 96280, "total_steps": 181800, "loss": 0.1163, "lr": 2.677982334225984e-05, "epoch": 10.591859185918592, "percentage": 52.96, "elapsed_time": "3:47:41", "remaining_time": "3:22:15", "throughput": 1487.3, "total_tokens": 20319328} {"current_steps": 96285, "total_steps": 181800, "loss": 0.0021, "lr": 2.6777429356352092e-05, "epoch": 10.592409240924093, "percentage": 52.96, "elapsed_time": "3:47:42", "remaining_time": "3:22:14", "throughput": 1487.3, "total_tokens": 20320384} {"current_steps": 96290, "total_steps": 181800, "loss": 0.0024, "lr": 2.6775035354062628e-05, "epoch": 10.592959295929592, "percentage": 52.96, "elapsed_time": "3:47:43", "remaining_time": "3:22:13", "throughput": 1487.31, "total_tokens": 20321504} {"current_steps": 96295, "total_steps": 181800, "loss": 0.0139, "lr": 2.677264133541351e-05, "epoch": 10.593509350935093, "percentage": 52.97, "elapsed_time": "3:47:43", "remaining_time": "3:22:12", "throughput": 1487.31, "total_tokens": 20322592} {"current_steps": 96300, "total_steps": 181800, "loss": 0.0033, "lr": 2.677024730042681e-05, "epoch": 10.594059405940595, "percentage": 52.97, "elapsed_time": "3:47:44", "remaining_time": "3:22:12", "throughput": 1487.32, "total_tokens": 20323648} {"current_steps": 96305, "total_steps": 181800, "loss": 0.0024, "lr": 2.676785324912459e-05, "epoch": 10.594609460946094, "percentage": 52.97, "elapsed_time": "3:47:45", "remaining_time": "3:22:11", "throughput": 1487.32, "total_tokens": 20324704} {"current_steps": 96310, "total_steps": 181800, "loss": 0.008, "lr": 2.676545918152892e-05, "epoch": 10.595159515951595, "percentage": 52.98, "elapsed_time": "3:47:46", "remaining_time": "3:22:10", "throughput": 1487.32, "total_tokens": 20325760} {"current_steps": 96315, "total_steps": 181800, "loss": 0.0076, "lr": 2.6763065097661854e-05, "epoch": 10.595709570957096, "percentage": 52.98, "elapsed_time": "3:47:46", "remaining_time": "3:22:09", "throughput": 1487.32, "total_tokens": 20326752} {"current_steps": 96320, "total_steps": 181800, "loss": 0.0038, "lr": 2.6760670997545468e-05, "epoch": 10.596259625962595, "percentage": 52.98, "elapsed_time": "3:47:47", "remaining_time": "3:22:09", "throughput": 1487.32, "total_tokens": 20327840} {"current_steps": 96325, "total_steps": 181800, "loss": 0.111, "lr": 2.675827688120181e-05, "epoch": 10.596809680968097, "percentage": 52.98, "elapsed_time": "3:47:48", "remaining_time": "3:22:08", "throughput": 1487.32, "total_tokens": 20328864} {"current_steps": 96330, "total_steps": 181800, "loss": 0.1177, "lr": 2.6755882748652967e-05, "epoch": 10.597359735973598, "percentage": 52.99, "elapsed_time": "3:47:48", "remaining_time": "3:22:07", "throughput": 1487.32, "total_tokens": 20329920} {"current_steps": 96335, "total_steps": 181800, "loss": 0.0401, "lr": 2.6753488599920996e-05, "epoch": 10.597909790979099, "percentage": 52.99, "elapsed_time": "3:47:49", "remaining_time": "3:22:07", "throughput": 1487.33, "total_tokens": 20330976} {"current_steps": 96340, "total_steps": 181800, "loss": 0.0027, "lr": 2.6751094435027962e-05, "epoch": 10.598459845984598, "percentage": 52.99, "elapsed_time": "3:47:50", "remaining_time": "3:22:06", "throughput": 1487.33, "total_tokens": 20332064} {"current_steps": 96345, "total_steps": 181800, "loss": 0.007, "lr": 2.6748700253995928e-05, "epoch": 10.599009900990099, "percentage": 53.0, "elapsed_time": "3:47:50", "remaining_time": "3:22:05", "throughput": 1487.33, "total_tokens": 20333120} {"current_steps": 96350, "total_steps": 181800, "loss": 0.1, "lr": 2.6746306056846964e-05, "epoch": 10.5995599559956, "percentage": 53.0, "elapsed_time": "3:47:51", "remaining_time": "3:22:04", "throughput": 1487.34, "total_tokens": 20334176} {"current_steps": 96355, "total_steps": 181800, "loss": 0.037, "lr": 2.674391184360313e-05, "epoch": 10.6001100110011, "percentage": 53.0, "elapsed_time": "3:47:52", "remaining_time": "3:22:04", "throughput": 1487.34, "total_tokens": 20335200} {"current_steps": 96360, "total_steps": 181800, "loss": 0.0644, "lr": 2.674151761428651e-05, "epoch": 10.6006600660066, "percentage": 53.0, "elapsed_time": "3:47:52", "remaining_time": "3:22:03", "throughput": 1487.34, "total_tokens": 20336256} {"current_steps": 96365, "total_steps": 181800, "loss": 0.0788, "lr": 2.6739123368919145e-05, "epoch": 10.601210121012102, "percentage": 53.01, "elapsed_time": "3:47:53", "remaining_time": "3:22:02", "throughput": 1487.34, "total_tokens": 20337312} {"current_steps": 96370, "total_steps": 181800, "loss": 0.0765, "lr": 2.673672910752312e-05, "epoch": 10.601760176017601, "percentage": 53.01, "elapsed_time": "3:47:54", "remaining_time": "3:22:01", "throughput": 1487.35, "total_tokens": 20338400} {"current_steps": 96375, "total_steps": 181800, "loss": 0.0246, "lr": 2.67343348301205e-05, "epoch": 10.602310231023102, "percentage": 53.01, "elapsed_time": "3:47:54", "remaining_time": "3:22:01", "throughput": 1487.35, "total_tokens": 20339552} {"current_steps": 96380, "total_steps": 181800, "loss": 0.0845, "lr": 2.673194053673334e-05, "epoch": 10.602860286028603, "percentage": 53.01, "elapsed_time": "3:47:55", "remaining_time": "3:22:00", "throughput": 1487.36, "total_tokens": 20340608} {"current_steps": 96385, "total_steps": 181800, "loss": 0.0469, "lr": 2.6729546227383723e-05, "epoch": 10.603410341034103, "percentage": 53.02, "elapsed_time": "3:47:56", "remaining_time": "3:21:59", "throughput": 1487.36, "total_tokens": 20341664} {"current_steps": 96390, "total_steps": 181800, "loss": 0.008, "lr": 2.6727151902093707e-05, "epoch": 10.603960396039604, "percentage": 53.02, "elapsed_time": "3:47:57", "remaining_time": "3:21:59", "throughput": 1487.36, "total_tokens": 20342720} {"current_steps": 96395, "total_steps": 181800, "loss": 0.1724, "lr": 2.672475756088535e-05, "epoch": 10.604510451045105, "percentage": 53.02, "elapsed_time": "3:47:57", "remaining_time": "3:21:58", "throughput": 1487.36, "total_tokens": 20343712} {"current_steps": 96400, "total_steps": 181800, "loss": 0.0338, "lr": 2.6722363203780744e-05, "epoch": 10.605060506050606, "percentage": 53.03, "elapsed_time": "3:47:58", "remaining_time": "3:21:57", "throughput": 1487.36, "total_tokens": 20344768} {"current_steps": 96405, "total_steps": 181800, "loss": 0.0911, "lr": 2.671996883080194e-05, "epoch": 10.605610561056105, "percentage": 53.03, "elapsed_time": "3:47:59", "remaining_time": "3:21:56", "throughput": 1487.36, "total_tokens": 20345824} {"current_steps": 96410, "total_steps": 181800, "loss": 0.0403, "lr": 2.6717574441971e-05, "epoch": 10.606160616061606, "percentage": 53.03, "elapsed_time": "3:47:59", "remaining_time": "3:21:56", "throughput": 1487.37, "total_tokens": 20346912} {"current_steps": 96415, "total_steps": 181800, "loss": 0.007, "lr": 2.6715180037310006e-05, "epoch": 10.606710671067107, "percentage": 53.03, "elapsed_time": "3:48:00", "remaining_time": "3:21:55", "throughput": 1487.37, "total_tokens": 20348000} {"current_steps": 96420, "total_steps": 181800, "loss": 0.0135, "lr": 2.6712785616841026e-05, "epoch": 10.607260726072607, "percentage": 53.04, "elapsed_time": "3:48:01", "remaining_time": "3:21:54", "throughput": 1487.38, "total_tokens": 20349120} {"current_steps": 96425, "total_steps": 181800, "loss": 0.1043, "lr": 2.671039118058611e-05, "epoch": 10.607810781078108, "percentage": 53.04, "elapsed_time": "3:48:01", "remaining_time": "3:21:53", "throughput": 1487.39, "total_tokens": 20350272} {"current_steps": 96430, "total_steps": 181800, "loss": 0.0362, "lr": 2.670799672856735e-05, "epoch": 10.608360836083609, "percentage": 53.04, "elapsed_time": "3:48:02", "remaining_time": "3:21:53", "throughput": 1487.39, "total_tokens": 20351296} {"current_steps": 96435, "total_steps": 181800, "loss": 0.0719, "lr": 2.6705602260806807e-05, "epoch": 10.608910891089108, "percentage": 53.04, "elapsed_time": "3:48:03", "remaining_time": "3:21:52", "throughput": 1487.4, "total_tokens": 20352416} {"current_steps": 96440, "total_steps": 181800, "loss": 0.0042, "lr": 2.6703207777326535e-05, "epoch": 10.60946094609461, "percentage": 53.05, "elapsed_time": "3:48:03", "remaining_time": "3:21:51", "throughput": 1487.4, "total_tokens": 20353536} {"current_steps": 96445, "total_steps": 181800, "loss": 0.0049, "lr": 2.6700813278148617e-05, "epoch": 10.61001100110011, "percentage": 53.05, "elapsed_time": "3:48:04", "remaining_time": "3:21:51", "throughput": 1487.41, "total_tokens": 20354656} {"current_steps": 96450, "total_steps": 181800, "loss": 0.0404, "lr": 2.6698418763295125e-05, "epoch": 10.61056105610561, "percentage": 53.05, "elapsed_time": "3:48:05", "remaining_time": "3:21:50", "throughput": 1487.41, "total_tokens": 20355744} {"current_steps": 96455, "total_steps": 181800, "loss": 0.032, "lr": 2.669602423278812e-05, "epoch": 10.61111111111111, "percentage": 53.06, "elapsed_time": "3:48:06", "remaining_time": "3:21:49", "throughput": 1487.42, "total_tokens": 20356800} {"current_steps": 96460, "total_steps": 181800, "loss": 0.023, "lr": 2.669362968664967e-05, "epoch": 10.611661166116612, "percentage": 53.06, "elapsed_time": "3:48:06", "remaining_time": "3:21:48", "throughput": 1487.42, "total_tokens": 20357824} {"current_steps": 96465, "total_steps": 181800, "loss": 0.0099, "lr": 2.6691235124901854e-05, "epoch": 10.612211221122113, "percentage": 53.06, "elapsed_time": "3:48:07", "remaining_time": "3:21:48", "throughput": 1487.41, "total_tokens": 20358816} {"current_steps": 96470, "total_steps": 181800, "loss": 0.0421, "lr": 2.6688840547566723e-05, "epoch": 10.612761276127612, "percentage": 53.06, "elapsed_time": "3:48:08", "remaining_time": "3:21:47", "throughput": 1487.42, "total_tokens": 20359872} {"current_steps": 96475, "total_steps": 181800, "loss": 0.0067, "lr": 2.6686445954666368e-05, "epoch": 10.613311331133113, "percentage": 53.07, "elapsed_time": "3:48:08", "remaining_time": "3:21:46", "throughput": 1487.42, "total_tokens": 20360928} {"current_steps": 96480, "total_steps": 181800, "loss": 0.0385, "lr": 2.668405134622285e-05, "epoch": 10.613861386138614, "percentage": 53.07, "elapsed_time": "3:48:09", "remaining_time": "3:21:45", "throughput": 1487.43, "total_tokens": 20362080} {"current_steps": 96485, "total_steps": 181800, "loss": 0.0082, "lr": 2.668165672225824e-05, "epoch": 10.614411441144114, "percentage": 53.07, "elapsed_time": "3:48:10", "remaining_time": "3:21:45", "throughput": 1487.43, "total_tokens": 20363104} {"current_steps": 96490, "total_steps": 181800, "loss": 0.006, "lr": 2.6679262082794604e-05, "epoch": 10.614961496149615, "percentage": 53.07, "elapsed_time": "3:48:10", "remaining_time": "3:21:44", "throughput": 1487.43, "total_tokens": 20364128} {"current_steps": 96495, "total_steps": 181800, "loss": 0.0677, "lr": 2.667686742785402e-05, "epoch": 10.615511551155116, "percentage": 53.08, "elapsed_time": "3:48:11", "remaining_time": "3:21:43", "throughput": 1487.43, "total_tokens": 20365152} {"current_steps": 96500, "total_steps": 181800, "loss": 0.0771, "lr": 2.6674472757458546e-05, "epoch": 10.616061606160617, "percentage": 53.08, "elapsed_time": "3:48:12", "remaining_time": "3:21:43", "throughput": 1487.43, "total_tokens": 20366208} {"current_steps": 96505, "total_steps": 181800, "loss": 0.1397, "lr": 2.6672078071630268e-05, "epoch": 10.616611661166116, "percentage": 53.08, "elapsed_time": "3:48:12", "remaining_time": "3:21:42", "throughput": 1487.43, "total_tokens": 20367264} {"current_steps": 96510, "total_steps": 181800, "loss": 0.0588, "lr": 2.666968337039124e-05, "epoch": 10.617161716171617, "percentage": 53.09, "elapsed_time": "3:48:13", "remaining_time": "3:21:41", "throughput": 1487.44, "total_tokens": 20368320} {"current_steps": 96515, "total_steps": 181800, "loss": 0.0439, "lr": 2.6667288653763544e-05, "epoch": 10.617711771177119, "percentage": 53.09, "elapsed_time": "3:48:14", "remaining_time": "3:21:40", "throughput": 1487.44, "total_tokens": 20369408} {"current_steps": 96520, "total_steps": 181800, "loss": 0.0856, "lr": 2.6664893921769253e-05, "epoch": 10.618261826182618, "percentage": 53.09, "elapsed_time": "3:48:14", "remaining_time": "3:21:40", "throughput": 1487.45, "total_tokens": 20370496} {"current_steps": 96525, "total_steps": 181800, "loss": 0.059, "lr": 2.666249917443043e-05, "epoch": 10.618811881188119, "percentage": 53.09, "elapsed_time": "3:48:15", "remaining_time": "3:21:39", "throughput": 1487.45, "total_tokens": 20371584} {"current_steps": 96530, "total_steps": 181800, "loss": 0.0201, "lr": 2.6660104411769153e-05, "epoch": 10.61936193619362, "percentage": 53.1, "elapsed_time": "3:48:16", "remaining_time": "3:21:38", "throughput": 1487.45, "total_tokens": 20372640} {"current_steps": 96535, "total_steps": 181800, "loss": 0.0823, "lr": 2.6657709633807492e-05, "epoch": 10.61991199119912, "percentage": 53.1, "elapsed_time": "3:48:17", "remaining_time": "3:21:37", "throughput": 1487.45, "total_tokens": 20373696} {"current_steps": 96540, "total_steps": 181800, "loss": 0.0199, "lr": 2.6655314840567508e-05, "epoch": 10.62046204620462, "percentage": 53.1, "elapsed_time": "3:48:17", "remaining_time": "3:21:37", "throughput": 1487.45, "total_tokens": 20374656} {"current_steps": 96545, "total_steps": 181800, "loss": 0.0267, "lr": 2.6652920032071288e-05, "epoch": 10.621012101210122, "percentage": 53.11, "elapsed_time": "3:48:18", "remaining_time": "3:21:36", "throughput": 1487.45, "total_tokens": 20375712} {"current_steps": 96550, "total_steps": 181800, "loss": 0.0068, "lr": 2.66505252083409e-05, "epoch": 10.62156215621562, "percentage": 53.11, "elapsed_time": "3:48:19", "remaining_time": "3:21:35", "throughput": 1487.46, "total_tokens": 20376832} {"current_steps": 96555, "total_steps": 181800, "loss": 0.0046, "lr": 2.6648130369398406e-05, "epoch": 10.622112211221122, "percentage": 53.11, "elapsed_time": "3:48:19", "remaining_time": "3:21:35", "throughput": 1487.46, "total_tokens": 20377920} {"current_steps": 96560, "total_steps": 181800, "loss": 0.0165, "lr": 2.664573551526589e-05, "epoch": 10.622662266226623, "percentage": 53.11, "elapsed_time": "3:48:20", "remaining_time": "3:21:34", "throughput": 1487.47, "total_tokens": 20378976} {"current_steps": 96565, "total_steps": 181800, "loss": 0.0284, "lr": 2.6643340645965414e-05, "epoch": 10.623212321232124, "percentage": 53.12, "elapsed_time": "3:48:21", "remaining_time": "3:21:33", "throughput": 1487.47, "total_tokens": 20380064} {"current_steps": 96570, "total_steps": 181800, "loss": 0.0115, "lr": 2.6640945761519053e-05, "epoch": 10.623762376237623, "percentage": 53.12, "elapsed_time": "3:48:21", "remaining_time": "3:21:32", "throughput": 1487.47, "total_tokens": 20381120} {"current_steps": 96575, "total_steps": 181800, "loss": 0.0061, "lr": 2.6638550861948895e-05, "epoch": 10.624312431243125, "percentage": 53.12, "elapsed_time": "3:48:22", "remaining_time": "3:21:32", "throughput": 1487.48, "total_tokens": 20382208} {"current_steps": 96580, "total_steps": 181800, "loss": 0.1312, "lr": 2.6636155947276997e-05, "epoch": 10.624862486248626, "percentage": 53.12, "elapsed_time": "3:48:23", "remaining_time": "3:21:31", "throughput": 1487.48, "total_tokens": 20383296} {"current_steps": 96585, "total_steps": 181800, "loss": 0.0088, "lr": 2.6633761017525426e-05, "epoch": 10.625412541254125, "percentage": 53.13, "elapsed_time": "3:48:23", "remaining_time": "3:21:30", "throughput": 1487.48, "total_tokens": 20384352} {"current_steps": 96590, "total_steps": 181800, "loss": 0.1002, "lr": 2.6631366072716275e-05, "epoch": 10.625962596259626, "percentage": 53.13, "elapsed_time": "3:48:24", "remaining_time": "3:21:29", "throughput": 1487.49, "total_tokens": 20385472} {"current_steps": 96595, "total_steps": 181800, "loss": 0.0035, "lr": 2.6628971112871605e-05, "epoch": 10.626512651265127, "percentage": 53.13, "elapsed_time": "3:48:25", "remaining_time": "3:21:29", "throughput": 1487.49, "total_tokens": 20386496} {"current_steps": 96600, "total_steps": 181800, "loss": 0.0055, "lr": 2.6626576138013476e-05, "epoch": 10.627062706270626, "percentage": 53.14, "elapsed_time": "3:48:25", "remaining_time": "3:21:28", "throughput": 1487.49, "total_tokens": 20387552} {"current_steps": 96605, "total_steps": 181800, "loss": 0.019, "lr": 2.6624181148163985e-05, "epoch": 10.627612761276128, "percentage": 53.14, "elapsed_time": "3:48:26", "remaining_time": "3:21:27", "throughput": 1487.49, "total_tokens": 20388608} {"current_steps": 96610, "total_steps": 181800, "loss": 0.0482, "lr": 2.6621786143345196e-05, "epoch": 10.628162816281629, "percentage": 53.14, "elapsed_time": "3:48:27", "remaining_time": "3:21:27", "throughput": 1487.5, "total_tokens": 20389664} {"current_steps": 96615, "total_steps": 181800, "loss": 0.1465, "lr": 2.661939112357918e-05, "epoch": 10.628712871287128, "percentage": 53.14, "elapsed_time": "3:48:28", "remaining_time": "3:21:26", "throughput": 1487.5, "total_tokens": 20390688} {"current_steps": 96620, "total_steps": 181800, "loss": 0.0352, "lr": 2.661699608888802e-05, "epoch": 10.629262926292629, "percentage": 53.15, "elapsed_time": "3:48:28", "remaining_time": "3:21:25", "throughput": 1487.5, "total_tokens": 20391776} {"current_steps": 96625, "total_steps": 181800, "loss": 0.0821, "lr": 2.6614601039293774e-05, "epoch": 10.62981298129813, "percentage": 53.15, "elapsed_time": "3:48:29", "remaining_time": "3:21:24", "throughput": 1487.5, "total_tokens": 20392832} {"current_steps": 96630, "total_steps": 181800, "loss": 0.0232, "lr": 2.6612205974818526e-05, "epoch": 10.630363036303631, "percentage": 53.15, "elapsed_time": "3:48:30", "remaining_time": "3:21:24", "throughput": 1487.5, "total_tokens": 20393824} {"current_steps": 96635, "total_steps": 181800, "loss": 0.0174, "lr": 2.6609810895484348e-05, "epoch": 10.63091309130913, "percentage": 53.15, "elapsed_time": "3:48:30", "remaining_time": "3:21:23", "throughput": 1487.51, "total_tokens": 20394944} {"current_steps": 96640, "total_steps": 181800, "loss": 0.0048, "lr": 2.6607415801313324e-05, "epoch": 10.631463146314632, "percentage": 53.16, "elapsed_time": "3:48:31", "remaining_time": "3:21:22", "throughput": 1487.51, "total_tokens": 20395936} {"current_steps": 96645, "total_steps": 181800, "loss": 0.018, "lr": 2.6605020692327514e-05, "epoch": 10.632013201320133, "percentage": 53.16, "elapsed_time": "3:48:32", "remaining_time": "3:21:21", "throughput": 1487.5, "total_tokens": 20396928} {"current_steps": 96650, "total_steps": 181800, "loss": 0.0062, "lr": 2.6602625568549e-05, "epoch": 10.632563256325632, "percentage": 53.16, "elapsed_time": "3:48:32", "remaining_time": "3:21:21", "throughput": 1487.51, "total_tokens": 20398016} {"current_steps": 96655, "total_steps": 181800, "loss": 0.0062, "lr": 2.6600230429999852e-05, "epoch": 10.633113311331133, "percentage": 53.17, "elapsed_time": "3:48:33", "remaining_time": "3:21:20", "throughput": 1487.51, "total_tokens": 20399072} {"current_steps": 96660, "total_steps": 181800, "loss": 0.07, "lr": 2.6597835276702147e-05, "epoch": 10.633663366336634, "percentage": 53.17, "elapsed_time": "3:48:34", "remaining_time": "3:21:19", "throughput": 1487.52, "total_tokens": 20400192} {"current_steps": 96665, "total_steps": 181800, "loss": 0.0044, "lr": 2.6595440108677965e-05, "epoch": 10.634213421342134, "percentage": 53.17, "elapsed_time": "3:48:34", "remaining_time": "3:21:19", "throughput": 1487.52, "total_tokens": 20401216} {"current_steps": 96670, "total_steps": 181800, "loss": 0.0421, "lr": 2.659304492594938e-05, "epoch": 10.634763476347635, "percentage": 53.17, "elapsed_time": "3:48:35", "remaining_time": "3:21:18", "throughput": 1487.52, "total_tokens": 20402304} {"current_steps": 96675, "total_steps": 181800, "loss": 0.0075, "lr": 2.659064972853846e-05, "epoch": 10.635313531353136, "percentage": 53.18, "elapsed_time": "3:48:36", "remaining_time": "3:21:17", "throughput": 1487.52, "total_tokens": 20403360} {"current_steps": 96680, "total_steps": 181800, "loss": 0.0342, "lr": 2.6588254516467282e-05, "epoch": 10.635863586358635, "percentage": 53.18, "elapsed_time": "3:48:37", "remaining_time": "3:21:16", "throughput": 1487.52, "total_tokens": 20404384} {"current_steps": 96685, "total_steps": 181800, "loss": 0.0069, "lr": 2.6585859289757927e-05, "epoch": 10.636413641364136, "percentage": 53.18, "elapsed_time": "3:48:37", "remaining_time": "3:21:16", "throughput": 1487.53, "total_tokens": 20405440} {"current_steps": 96690, "total_steps": 181800, "loss": 0.0296, "lr": 2.6583464048432472e-05, "epoch": 10.636963696369637, "percentage": 53.18, "elapsed_time": "3:48:38", "remaining_time": "3:21:15", "throughput": 1487.53, "total_tokens": 20406496} {"current_steps": 96695, "total_steps": 181800, "loss": 0.0334, "lr": 2.6581068792512985e-05, "epoch": 10.637513751375138, "percentage": 53.19, "elapsed_time": "3:48:39", "remaining_time": "3:21:14", "throughput": 1487.53, "total_tokens": 20407520} {"current_steps": 96700, "total_steps": 181800, "loss": 0.0039, "lr": 2.657867352202154e-05, "epoch": 10.638063806380638, "percentage": 53.19, "elapsed_time": "3:48:39", "remaining_time": "3:21:13", "throughput": 1487.53, "total_tokens": 20408576} {"current_steps": 96705, "total_steps": 181800, "loss": 0.0693, "lr": 2.657627823698023e-05, "epoch": 10.638613861386139, "percentage": 53.19, "elapsed_time": "3:48:40", "remaining_time": "3:21:13", "throughput": 1487.53, "total_tokens": 20409632} {"current_steps": 96710, "total_steps": 181800, "loss": 0.1643, "lr": 2.657388293741111e-05, "epoch": 10.63916391639164, "percentage": 53.2, "elapsed_time": "3:48:41", "remaining_time": "3:21:12", "throughput": 1487.53, "total_tokens": 20410688} {"current_steps": 96715, "total_steps": 181800, "loss": 0.0014, "lr": 2.657148762333627e-05, "epoch": 10.63971397139714, "percentage": 53.2, "elapsed_time": "3:48:41", "remaining_time": "3:21:11", "throughput": 1487.53, "total_tokens": 20411712} {"current_steps": 96720, "total_steps": 181800, "loss": 0.1058, "lr": 2.6569092294777787e-05, "epoch": 10.64026402640264, "percentage": 53.2, "elapsed_time": "3:48:42", "remaining_time": "3:21:11", "throughput": 1487.53, "total_tokens": 20412704} {"current_steps": 96725, "total_steps": 181800, "loss": 0.0092, "lr": 2.656669695175773e-05, "epoch": 10.640814081408141, "percentage": 53.2, "elapsed_time": "3:48:43", "remaining_time": "3:21:10", "throughput": 1487.53, "total_tokens": 20413760} {"current_steps": 96730, "total_steps": 181800, "loss": 0.002, "lr": 2.6564301594298175e-05, "epoch": 10.64136413641364, "percentage": 53.21, "elapsed_time": "3:48:43", "remaining_time": "3:21:09", "throughput": 1487.54, "total_tokens": 20414816} {"current_steps": 96735, "total_steps": 181800, "loss": 0.0536, "lr": 2.6561906222421206e-05, "epoch": 10.641914191419142, "percentage": 53.21, "elapsed_time": "3:48:44", "remaining_time": "3:21:08", "throughput": 1487.53, "total_tokens": 20415808} {"current_steps": 96740, "total_steps": 181800, "loss": 0.0983, "lr": 2.65595108361489e-05, "epoch": 10.642464246424643, "percentage": 53.21, "elapsed_time": "3:48:45", "remaining_time": "3:21:08", "throughput": 1487.53, "total_tokens": 20416832} {"current_steps": 96745, "total_steps": 181800, "loss": 0.0024, "lr": 2.6557115435503326e-05, "epoch": 10.643014301430142, "percentage": 53.22, "elapsed_time": "3:48:45", "remaining_time": "3:21:07", "throughput": 1487.54, "total_tokens": 20417888} {"current_steps": 96750, "total_steps": 181800, "loss": 0.0551, "lr": 2.655472002050657e-05, "epoch": 10.643564356435643, "percentage": 53.22, "elapsed_time": "3:48:46", "remaining_time": "3:21:06", "throughput": 1487.54, "total_tokens": 20418976} {"current_steps": 96755, "total_steps": 181800, "loss": 0.013, "lr": 2.6552324591180698e-05, "epoch": 10.644114411441144, "percentage": 53.22, "elapsed_time": "3:48:47", "remaining_time": "3:21:05", "throughput": 1487.54, "total_tokens": 20419968} {"current_steps": 96760, "total_steps": 181800, "loss": 0.0626, "lr": 2.6549929147547797e-05, "epoch": 10.644664466446645, "percentage": 53.22, "elapsed_time": "3:48:48", "remaining_time": "3:21:05", "throughput": 1487.54, "total_tokens": 20421024} {"current_steps": 96765, "total_steps": 181800, "loss": 0.0573, "lr": 2.6547533689629956e-05, "epoch": 10.645214521452145, "percentage": 53.23, "elapsed_time": "3:48:48", "remaining_time": "3:21:04", "throughput": 1487.55, "total_tokens": 20422144} {"current_steps": 96770, "total_steps": 181800, "loss": 0.0173, "lr": 2.654513821744923e-05, "epoch": 10.645764576457646, "percentage": 53.23, "elapsed_time": "3:48:49", "remaining_time": "3:21:03", "throughput": 1487.55, "total_tokens": 20423264} {"current_steps": 96775, "total_steps": 181800, "loss": 0.0234, "lr": 2.6542742731027703e-05, "epoch": 10.646314631463147, "percentage": 53.23, "elapsed_time": "3:48:50", "remaining_time": "3:21:03", "throughput": 1487.55, "total_tokens": 20424288} {"current_steps": 96780, "total_steps": 181800, "loss": 0.0115, "lr": 2.654034723038746e-05, "epoch": 10.646864686468646, "percentage": 53.23, "elapsed_time": "3:48:50", "remaining_time": "3:21:02", "throughput": 1487.55, "total_tokens": 20425280} {"current_steps": 96785, "total_steps": 181800, "loss": 0.0157, "lr": 2.6537951715550576e-05, "epoch": 10.647414741474147, "percentage": 53.24, "elapsed_time": "3:48:51", "remaining_time": "3:21:01", "throughput": 1487.55, "total_tokens": 20426368} {"current_steps": 96790, "total_steps": 181800, "loss": 0.0253, "lr": 2.653555618653913e-05, "epoch": 10.647964796479648, "percentage": 53.24, "elapsed_time": "3:48:52", "remaining_time": "3:21:00", "throughput": 1487.55, "total_tokens": 20427360} {"current_steps": 96795, "total_steps": 181800, "loss": 0.0386, "lr": 2.6533160643375197e-05, "epoch": 10.648514851485148, "percentage": 53.24, "elapsed_time": "3:48:52", "remaining_time": "3:21:00", "throughput": 1487.55, "total_tokens": 20428416} {"current_steps": 96800, "total_steps": 181800, "loss": 0.0102, "lr": 2.653076508608086e-05, "epoch": 10.649064906490649, "percentage": 53.25, "elapsed_time": "3:48:53", "remaining_time": "3:20:59", "throughput": 1487.55, "total_tokens": 20429440} {"current_steps": 96805, "total_steps": 181800, "loss": 0.0833, "lr": 2.652836951467819e-05, "epoch": 10.64961496149615, "percentage": 53.25, "elapsed_time": "3:48:54", "remaining_time": "3:20:58", "throughput": 1487.56, "total_tokens": 20430496} {"current_steps": 96810, "total_steps": 181800, "loss": 0.0117, "lr": 2.6525973929189284e-05, "epoch": 10.65016501650165, "percentage": 53.25, "elapsed_time": "3:48:54", "remaining_time": "3:20:57", "throughput": 1487.56, "total_tokens": 20431552} {"current_steps": 96815, "total_steps": 181800, "loss": 0.0187, "lr": 2.6523578329636195e-05, "epoch": 10.65071507150715, "percentage": 53.25, "elapsed_time": "3:48:55", "remaining_time": "3:20:57", "throughput": 1487.56, "total_tokens": 20432640} {"current_steps": 96820, "total_steps": 181800, "loss": 0.0265, "lr": 2.6521182716041027e-05, "epoch": 10.651265126512651, "percentage": 53.26, "elapsed_time": "3:48:56", "remaining_time": "3:20:56", "throughput": 1487.57, "total_tokens": 20433728} {"current_steps": 96825, "total_steps": 181800, "loss": 0.0332, "lr": 2.651878708842584e-05, "epoch": 10.651815181518153, "percentage": 53.26, "elapsed_time": "3:48:57", "remaining_time": "3:20:55", "throughput": 1487.57, "total_tokens": 20434784} {"current_steps": 96830, "total_steps": 181800, "loss": 0.0052, "lr": 2.6516391446812727e-05, "epoch": 10.652365236523652, "percentage": 53.26, "elapsed_time": "3:48:57", "remaining_time": "3:20:55", "throughput": 1487.57, "total_tokens": 20435776} {"current_steps": 96835, "total_steps": 181800, "loss": 0.0034, "lr": 2.6513995791223756e-05, "epoch": 10.652915291529153, "percentage": 53.26, "elapsed_time": "3:48:58", "remaining_time": "3:20:54", "throughput": 1487.57, "total_tokens": 20436800} {"current_steps": 96840, "total_steps": 181800, "loss": 0.0304, "lr": 2.6511600121681018e-05, "epoch": 10.653465346534654, "percentage": 53.27, "elapsed_time": "3:48:59", "remaining_time": "3:20:53", "throughput": 1487.58, "total_tokens": 20437952} {"current_steps": 96845, "total_steps": 181800, "loss": 0.0331, "lr": 2.6509204438206574e-05, "epoch": 10.654015401540153, "percentage": 53.27, "elapsed_time": "3:48:59", "remaining_time": "3:20:52", "throughput": 1487.58, "total_tokens": 20438976} {"current_steps": 96850, "total_steps": 181800, "loss": 0.0265, "lr": 2.650680874082253e-05, "epoch": 10.654565456545654, "percentage": 53.27, "elapsed_time": "3:49:00", "remaining_time": "3:20:52", "throughput": 1487.58, "total_tokens": 20440032} {"current_steps": 96855, "total_steps": 181800, "loss": 0.0804, "lr": 2.6504413029550952e-05, "epoch": 10.655115511551156, "percentage": 53.28, "elapsed_time": "3:49:01", "remaining_time": "3:20:51", "throughput": 1487.58, "total_tokens": 20441056} {"current_steps": 96860, "total_steps": 181800, "loss": 0.079, "lr": 2.650201730441392e-05, "epoch": 10.655665566556655, "percentage": 53.28, "elapsed_time": "3:49:01", "remaining_time": "3:20:50", "throughput": 1487.58, "total_tokens": 20442144} {"current_steps": 96865, "total_steps": 181800, "loss": 0.0079, "lr": 2.6499621565433514e-05, "epoch": 10.656215621562156, "percentage": 53.28, "elapsed_time": "3:49:02", "remaining_time": "3:20:49", "throughput": 1487.58, "total_tokens": 20443168} {"current_steps": 96870, "total_steps": 181800, "loss": 0.1053, "lr": 2.6497225812631815e-05, "epoch": 10.656765676567657, "percentage": 53.28, "elapsed_time": "3:49:03", "remaining_time": "3:20:49", "throughput": 1487.59, "total_tokens": 20444288} {"current_steps": 96875, "total_steps": 181800, "loss": 0.1484, "lr": 2.64948300460309e-05, "epoch": 10.657315731573158, "percentage": 53.29, "elapsed_time": "3:49:03", "remaining_time": "3:20:48", "throughput": 1487.59, "total_tokens": 20445344} {"current_steps": 96880, "total_steps": 181800, "loss": 0.0636, "lr": 2.6492434265652867e-05, "epoch": 10.657865786578657, "percentage": 53.29, "elapsed_time": "3:49:04", "remaining_time": "3:20:47", "throughput": 1487.6, "total_tokens": 20446464} {"current_steps": 96885, "total_steps": 181800, "loss": 0.1203, "lr": 2.6490038471519775e-05, "epoch": 10.658415841584159, "percentage": 53.29, "elapsed_time": "3:49:05", "remaining_time": "3:20:47", "throughput": 1487.6, "total_tokens": 20447488} {"current_steps": 96890, "total_steps": 181800, "loss": 0.0225, "lr": 2.6487642663653704e-05, "epoch": 10.65896589658966, "percentage": 53.29, "elapsed_time": "3:49:05", "remaining_time": "3:20:46", "throughput": 1487.6, "total_tokens": 20448544} {"current_steps": 96895, "total_steps": 181800, "loss": 0.0386, "lr": 2.6485246842076755e-05, "epoch": 10.659515951595159, "percentage": 53.3, "elapsed_time": "3:49:06", "remaining_time": "3:20:45", "throughput": 1487.6, "total_tokens": 20449568} {"current_steps": 96900, "total_steps": 181800, "loss": 0.0573, "lr": 2.6482851006810998e-05, "epoch": 10.66006600660066, "percentage": 53.3, "elapsed_time": "3:49:07", "remaining_time": "3:20:44", "throughput": 1487.61, "total_tokens": 20450688} {"current_steps": 96905, "total_steps": 181800, "loss": 0.0061, "lr": 2.6480455157878514e-05, "epoch": 10.660616061606161, "percentage": 53.3, "elapsed_time": "3:49:08", "remaining_time": "3:20:44", "throughput": 1487.61, "total_tokens": 20451776} {"current_steps": 96910, "total_steps": 181800, "loss": 0.0155, "lr": 2.647805929530139e-05, "epoch": 10.66116611661166, "percentage": 53.31, "elapsed_time": "3:49:08", "remaining_time": "3:20:43", "throughput": 1487.61, "total_tokens": 20452800} {"current_steps": 96915, "total_steps": 181800, "loss": 0.0438, "lr": 2.6475663419101697e-05, "epoch": 10.661716171617162, "percentage": 53.31, "elapsed_time": "3:49:09", "remaining_time": "3:20:42", "throughput": 1487.61, "total_tokens": 20453824} {"current_steps": 96920, "total_steps": 181800, "loss": 0.0168, "lr": 2.6473267529301516e-05, "epoch": 10.662266226622663, "percentage": 53.31, "elapsed_time": "3:49:10", "remaining_time": "3:20:41", "throughput": 1487.62, "total_tokens": 20454912} {"current_steps": 96925, "total_steps": 181800, "loss": 0.0093, "lr": 2.6470871625922943e-05, "epoch": 10.662816281628164, "percentage": 53.31, "elapsed_time": "3:49:10", "remaining_time": "3:20:41", "throughput": 1487.62, "total_tokens": 20455968} {"current_steps": 96930, "total_steps": 181800, "loss": 0.0183, "lr": 2.6468475708988055e-05, "epoch": 10.663366336633663, "percentage": 53.32, "elapsed_time": "3:49:11", "remaining_time": "3:20:40", "throughput": 1487.62, "total_tokens": 20456992} {"current_steps": 96935, "total_steps": 181800, "loss": 0.0086, "lr": 2.6466079778518925e-05, "epoch": 10.663916391639164, "percentage": 53.32, "elapsed_time": "3:49:12", "remaining_time": "3:20:39", "throughput": 1487.62, "total_tokens": 20458048} {"current_steps": 96940, "total_steps": 181800, "loss": 0.0043, "lr": 2.6463683834537645e-05, "epoch": 10.664466446644665, "percentage": 53.32, "elapsed_time": "3:49:12", "remaining_time": "3:20:39", "throughput": 1487.62, "total_tokens": 20459040} {"current_steps": 96945, "total_steps": 181800, "loss": 0.066, "lr": 2.6461287877066294e-05, "epoch": 10.665016501650165, "percentage": 53.33, "elapsed_time": "3:49:13", "remaining_time": "3:20:38", "throughput": 1487.63, "total_tokens": 20460160} {"current_steps": 96950, "total_steps": 181800, "loss": 0.0795, "lr": 2.6458891906126947e-05, "epoch": 10.665566556655666, "percentage": 53.33, "elapsed_time": "3:49:14", "remaining_time": "3:20:37", "throughput": 1487.63, "total_tokens": 20461184} {"current_steps": 96955, "total_steps": 181800, "loss": 0.0082, "lr": 2.6456495921741703e-05, "epoch": 10.666116611661167, "percentage": 53.33, "elapsed_time": "3:49:14", "remaining_time": "3:20:36", "throughput": 1487.63, "total_tokens": 20462272} {"current_steps": 96960, "total_steps": 181800, "loss": 0.0049, "lr": 2.6454099923932628e-05, "epoch": 10.666666666666666, "percentage": 53.33, "elapsed_time": "3:49:15", "remaining_time": "3:20:36", "throughput": 1487.63, "total_tokens": 20463328} {"current_steps": 96965, "total_steps": 181800, "loss": 0.0498, "lr": 2.6451703912721814e-05, "epoch": 10.667216721672167, "percentage": 53.34, "elapsed_time": "3:49:16", "remaining_time": "3:20:35", "throughput": 1487.63, "total_tokens": 20464352} {"current_steps": 96970, "total_steps": 181800, "loss": 0.1136, "lr": 2.6449307888131342e-05, "epoch": 10.667766776677668, "percentage": 53.34, "elapsed_time": "3:49:17", "remaining_time": "3:20:34", "throughput": 1487.64, "total_tokens": 20465440} {"current_steps": 96975, "total_steps": 181800, "loss": 0.0061, "lr": 2.6446911850183292e-05, "epoch": 10.668316831683168, "percentage": 53.34, "elapsed_time": "3:49:17", "remaining_time": "3:20:34", "throughput": 1487.63, "total_tokens": 20466432} {"current_steps": 96980, "total_steps": 181800, "loss": 0.0784, "lr": 2.6444515798899756e-05, "epoch": 10.668866886688669, "percentage": 53.34, "elapsed_time": "3:49:18", "remaining_time": "3:20:33", "throughput": 1487.64, "total_tokens": 20467520} {"current_steps": 96985, "total_steps": 181800, "loss": 0.0276, "lr": 2.6442119734302807e-05, "epoch": 10.66941694169417, "percentage": 53.35, "elapsed_time": "3:49:19", "remaining_time": "3:20:32", "throughput": 1487.64, "total_tokens": 20468608} {"current_steps": 96990, "total_steps": 181800, "loss": 0.0153, "lr": 2.643972365641453e-05, "epoch": 10.66996699669967, "percentage": 53.35, "elapsed_time": "3:49:19", "remaining_time": "3:20:31", "throughput": 1487.64, "total_tokens": 20469632} {"current_steps": 96995, "total_steps": 181800, "loss": 0.0254, "lr": 2.6437327565257008e-05, "epoch": 10.67051705170517, "percentage": 53.35, "elapsed_time": "3:49:20", "remaining_time": "3:20:31", "throughput": 1487.64, "total_tokens": 20470656} {"current_steps": 97000, "total_steps": 181800, "loss": 0.0019, "lr": 2.6434931460852342e-05, "epoch": 10.671067106710671, "percentage": 53.36, "elapsed_time": "3:49:21", "remaining_time": "3:20:30", "throughput": 1487.64, "total_tokens": 20471680} {"current_steps": 97005, "total_steps": 181800, "loss": 0.0073, "lr": 2.6432535343222586e-05, "epoch": 10.671617161716172, "percentage": 53.36, "elapsed_time": "3:49:21", "remaining_time": "3:20:29", "throughput": 1487.64, "total_tokens": 20472736} {"current_steps": 97010, "total_steps": 181800, "loss": 0.1032, "lr": 2.643013921238985e-05, "epoch": 10.672167216721672, "percentage": 53.36, "elapsed_time": "3:49:22", "remaining_time": "3:20:28", "throughput": 1487.65, "total_tokens": 20473824} {"current_steps": 97015, "total_steps": 181800, "loss": 0.0043, "lr": 2.6427743068376198e-05, "epoch": 10.672717271727173, "percentage": 53.36, "elapsed_time": "3:49:23", "remaining_time": "3:20:28", "throughput": 1487.65, "total_tokens": 20474880} {"current_steps": 97020, "total_steps": 181800, "loss": 0.0396, "lr": 2.6425346911203725e-05, "epoch": 10.673267326732674, "percentage": 53.37, "elapsed_time": "3:49:23", "remaining_time": "3:20:27", "throughput": 1487.65, "total_tokens": 20475936} {"current_steps": 97025, "total_steps": 181800, "loss": 0.0087, "lr": 2.642295074089452e-05, "epoch": 10.673817381738173, "percentage": 53.37, "elapsed_time": "3:49:24", "remaining_time": "3:20:26", "throughput": 1487.66, "total_tokens": 20476992} {"current_steps": 97030, "total_steps": 181800, "loss": 0.0043, "lr": 2.642055455747066e-05, "epoch": 10.674367436743674, "percentage": 53.37, "elapsed_time": "3:49:25", "remaining_time": "3:20:26", "throughput": 1487.66, "total_tokens": 20478048} {"current_steps": 97035, "total_steps": 181800, "loss": 0.0426, "lr": 2.641815836095422e-05, "epoch": 10.674917491749175, "percentage": 53.37, "elapsed_time": "3:49:25", "remaining_time": "3:20:25", "throughput": 1487.66, "total_tokens": 20479104} {"current_steps": 97040, "total_steps": 181800, "loss": 0.0095, "lr": 2.6415762151367307e-05, "epoch": 10.675467546754675, "percentage": 53.38, "elapsed_time": "3:49:26", "remaining_time": "3:20:24", "throughput": 1487.66, "total_tokens": 20480192} {"current_steps": 97045, "total_steps": 181800, "loss": 0.0048, "lr": 2.6413365928731987e-05, "epoch": 10.676017601760176, "percentage": 53.38, "elapsed_time": "3:49:27", "remaining_time": "3:20:23", "throughput": 1487.67, "total_tokens": 20481280} {"current_steps": 97050, "total_steps": 181800, "loss": 0.0044, "lr": 2.6410969693070354e-05, "epoch": 10.676567656765677, "percentage": 53.38, "elapsed_time": "3:49:28", "remaining_time": "3:20:23", "throughput": 1487.67, "total_tokens": 20482336} {"current_steps": 97055, "total_steps": 181800, "loss": 0.0015, "lr": 2.640857344440449e-05, "epoch": 10.677117711771178, "percentage": 53.39, "elapsed_time": "3:49:28", "remaining_time": "3:20:22", "throughput": 1487.68, "total_tokens": 20483424} {"current_steps": 97060, "total_steps": 181800, "loss": 0.1502, "lr": 2.640617718275648e-05, "epoch": 10.677667766776677, "percentage": 53.39, "elapsed_time": "3:49:29", "remaining_time": "3:20:21", "throughput": 1487.68, "total_tokens": 20484480} {"current_steps": 97065, "total_steps": 181800, "loss": 0.031, "lr": 2.6403780908148405e-05, "epoch": 10.678217821782178, "percentage": 53.39, "elapsed_time": "3:49:30", "remaining_time": "3:20:20", "throughput": 1487.68, "total_tokens": 20485536} {"current_steps": 97070, "total_steps": 181800, "loss": 0.0028, "lr": 2.6401384620602366e-05, "epoch": 10.67876787678768, "percentage": 53.39, "elapsed_time": "3:49:30", "remaining_time": "3:20:20", "throughput": 1487.69, "total_tokens": 20486624} {"current_steps": 97075, "total_steps": 181800, "loss": 0.0111, "lr": 2.6398988320140432e-05, "epoch": 10.679317931793179, "percentage": 53.4, "elapsed_time": "3:49:31", "remaining_time": "3:20:19", "throughput": 1487.69, "total_tokens": 20487680} {"current_steps": 97080, "total_steps": 181800, "loss": 0.0043, "lr": 2.639659200678469e-05, "epoch": 10.67986798679868, "percentage": 53.4, "elapsed_time": "3:49:32", "remaining_time": "3:20:18", "throughput": 1487.69, "total_tokens": 20488704} {"current_steps": 97085, "total_steps": 181800, "loss": 0.1152, "lr": 2.6394195680557233e-05, "epoch": 10.680418041804181, "percentage": 53.4, "elapsed_time": "3:49:32", "remaining_time": "3:20:18", "throughput": 1487.69, "total_tokens": 20489792} {"current_steps": 97090, "total_steps": 181800, "loss": 0.0163, "lr": 2.6391799341480144e-05, "epoch": 10.68096809680968, "percentage": 53.4, "elapsed_time": "3:49:33", "remaining_time": "3:20:17", "throughput": 1487.69, "total_tokens": 20490848} {"current_steps": 97095, "total_steps": 181800, "loss": 0.0137, "lr": 2.6389402989575508e-05, "epoch": 10.681518151815181, "percentage": 53.41, "elapsed_time": "3:49:34", "remaining_time": "3:20:16", "throughput": 1487.7, "total_tokens": 20491936} {"current_steps": 97100, "total_steps": 181800, "loss": 0.0016, "lr": 2.6387006624865407e-05, "epoch": 10.682068206820682, "percentage": 53.41, "elapsed_time": "3:49:34", "remaining_time": "3:20:15", "throughput": 1487.71, "total_tokens": 20493056} {"current_steps": 97105, "total_steps": 181800, "loss": 0.0217, "lr": 2.638461024737194e-05, "epoch": 10.682618261826182, "percentage": 53.41, "elapsed_time": "3:49:35", "remaining_time": "3:20:15", "throughput": 1487.71, "total_tokens": 20494112} {"current_steps": 97110, "total_steps": 181800, "loss": 0.0683, "lr": 2.638221385711717e-05, "epoch": 10.683168316831683, "percentage": 53.42, "elapsed_time": "3:49:36", "remaining_time": "3:20:14", "throughput": 1487.71, "total_tokens": 20495136} {"current_steps": 97115, "total_steps": 181800, "loss": 0.0066, "lr": 2.6379817454123214e-05, "epoch": 10.683718371837184, "percentage": 53.42, "elapsed_time": "3:49:37", "remaining_time": "3:20:13", "throughput": 1487.71, "total_tokens": 20496224} {"current_steps": 97120, "total_steps": 181800, "loss": 0.0117, "lr": 2.6377421038412138e-05, "epoch": 10.684268426842685, "percentage": 53.42, "elapsed_time": "3:49:37", "remaining_time": "3:20:12", "throughput": 1487.72, "total_tokens": 20497376} {"current_steps": 97125, "total_steps": 181800, "loss": 0.0026, "lr": 2.6375024610006033e-05, "epoch": 10.684818481848184, "percentage": 53.42, "elapsed_time": "3:49:38", "remaining_time": "3:20:12", "throughput": 1487.72, "total_tokens": 20498400} {"current_steps": 97130, "total_steps": 181800, "loss": 0.0036, "lr": 2.637262816892698e-05, "epoch": 10.685368536853685, "percentage": 53.43, "elapsed_time": "3:49:39", "remaining_time": "3:20:11", "throughput": 1487.73, "total_tokens": 20499488} {"current_steps": 97135, "total_steps": 181800, "loss": 0.0577, "lr": 2.637023171519708e-05, "epoch": 10.685918591859187, "percentage": 53.43, "elapsed_time": "3:49:39", "remaining_time": "3:20:10", "throughput": 1487.73, "total_tokens": 20500608} {"current_steps": 97140, "total_steps": 181800, "loss": 0.034, "lr": 2.6367835248838403e-05, "epoch": 10.686468646864686, "percentage": 53.43, "elapsed_time": "3:49:40", "remaining_time": "3:20:10", "throughput": 1487.73, "total_tokens": 20501600} {"current_steps": 97145, "total_steps": 181800, "loss": 0.0006, "lr": 2.6365438769873058e-05, "epoch": 10.687018701870187, "percentage": 53.44, "elapsed_time": "3:49:41", "remaining_time": "3:20:09", "throughput": 1487.73, "total_tokens": 20502656} {"current_steps": 97150, "total_steps": 181800, "loss": 0.0319, "lr": 2.6363042278323107e-05, "epoch": 10.687568756875688, "percentage": 53.44, "elapsed_time": "3:49:41", "remaining_time": "3:20:08", "throughput": 1487.73, "total_tokens": 20503680} {"current_steps": 97155, "total_steps": 181800, "loss": 0.0058, "lr": 2.636064577421065e-05, "epoch": 10.688118811881187, "percentage": 53.44, "elapsed_time": "3:49:42", "remaining_time": "3:20:07", "throughput": 1487.74, "total_tokens": 20504768} {"current_steps": 97160, "total_steps": 181800, "loss": 0.0116, "lr": 2.635824925755778e-05, "epoch": 10.688668866886688, "percentage": 53.44, "elapsed_time": "3:49:43", "remaining_time": "3:20:07", "throughput": 1487.74, "total_tokens": 20505824} {"current_steps": 97165, "total_steps": 181800, "loss": 0.0675, "lr": 2.6355852728386577e-05, "epoch": 10.68921892189219, "percentage": 53.45, "elapsed_time": "3:49:43", "remaining_time": "3:20:06", "throughput": 1487.74, "total_tokens": 20506880} {"current_steps": 97170, "total_steps": 181800, "loss": 0.0213, "lr": 2.6353456186719127e-05, "epoch": 10.689768976897689, "percentage": 53.45, "elapsed_time": "3:49:44", "remaining_time": "3:20:05", "throughput": 1487.75, "total_tokens": 20508000} {"current_steps": 97175, "total_steps": 181800, "loss": 0.0416, "lr": 2.635105963257753e-05, "epoch": 10.69031903190319, "percentage": 53.45, "elapsed_time": "3:49:45", "remaining_time": "3:20:04", "throughput": 1487.75, "total_tokens": 20508992} {"current_steps": 97180, "total_steps": 181800, "loss": 0.0603, "lr": 2.6348663065983846e-05, "epoch": 10.690869086908691, "percentage": 53.45, "elapsed_time": "3:49:45", "remaining_time": "3:20:04", "throughput": 1487.76, "total_tokens": 20510144} {"current_steps": 97185, "total_steps": 181800, "loss": 0.0414, "lr": 2.6346266486960196e-05, "epoch": 10.691419141914192, "percentage": 53.46, "elapsed_time": "3:49:46", "remaining_time": "3:20:03", "throughput": 1487.76, "total_tokens": 20511168} {"current_steps": 97190, "total_steps": 181800, "loss": 0.0059, "lr": 2.6343869895528655e-05, "epoch": 10.691969196919691, "percentage": 53.46, "elapsed_time": "3:49:47", "remaining_time": "3:20:02", "throughput": 1487.76, "total_tokens": 20512192} {"current_steps": 97195, "total_steps": 181800, "loss": 0.0097, "lr": 2.6341473291711304e-05, "epoch": 10.692519251925193, "percentage": 53.46, "elapsed_time": "3:49:48", "remaining_time": "3:20:02", "throughput": 1487.73, "total_tokens": 20513184} {"current_steps": 97200, "total_steps": 181800, "loss": 0.0061, "lr": 2.633907667553024e-05, "epoch": 10.693069306930694, "percentage": 53.47, "elapsed_time": "3:49:48", "remaining_time": "3:20:01", "throughput": 1487.74, "total_tokens": 20514240} {"current_steps": 97205, "total_steps": 181800, "loss": 0.104, "lr": 2.633668004700755e-05, "epoch": 10.693619361936193, "percentage": 53.47, "elapsed_time": "3:49:49", "remaining_time": "3:20:00", "throughput": 1487.74, "total_tokens": 20515360} {"current_steps": 97210, "total_steps": 181800, "loss": 0.003, "lr": 2.6334283406165312e-05, "epoch": 10.694169416941694, "percentage": 53.47, "elapsed_time": "3:49:50", "remaining_time": "3:19:59", "throughput": 1487.75, "total_tokens": 20516512} {"current_steps": 97215, "total_steps": 181800, "loss": 0.1126, "lr": 2.6331886753025635e-05, "epoch": 10.694719471947195, "percentage": 53.47, "elapsed_time": "3:49:50", "remaining_time": "3:19:59", "throughput": 1487.75, "total_tokens": 20517568} {"current_steps": 97220, "total_steps": 181800, "loss": 0.0294, "lr": 2.63294900876106e-05, "epoch": 10.695269526952695, "percentage": 53.48, "elapsed_time": "3:49:51", "remaining_time": "3:19:58", "throughput": 1487.75, "total_tokens": 20518560} {"current_steps": 97225, "total_steps": 181800, "loss": 0.0626, "lr": 2.6327093409942278e-05, "epoch": 10.695819581958196, "percentage": 53.48, "elapsed_time": "3:49:52", "remaining_time": "3:19:57", "throughput": 1487.75, "total_tokens": 20519616} {"current_steps": 97230, "total_steps": 181800, "loss": 0.1427, "lr": 2.6324696720042784e-05, "epoch": 10.696369636963697, "percentage": 53.48, "elapsed_time": "3:49:53", "remaining_time": "3:19:57", "throughput": 1487.75, "total_tokens": 20520640} {"current_steps": 97235, "total_steps": 181800, "loss": 0.013, "lr": 2.6322300017934192e-05, "epoch": 10.696919691969196, "percentage": 53.48, "elapsed_time": "3:49:53", "remaining_time": "3:19:56", "throughput": 1487.75, "total_tokens": 20521696} {"current_steps": 97240, "total_steps": 181800, "loss": 0.0853, "lr": 2.6319903303638598e-05, "epoch": 10.697469746974697, "percentage": 53.49, "elapsed_time": "3:49:54", "remaining_time": "3:19:55", "throughput": 1487.75, "total_tokens": 20522688} {"current_steps": 97245, "total_steps": 181800, "loss": 0.043, "lr": 2.6317506577178086e-05, "epoch": 10.698019801980198, "percentage": 53.49, "elapsed_time": "3:49:55", "remaining_time": "3:19:54", "throughput": 1487.75, "total_tokens": 20523744} {"current_steps": 97250, "total_steps": 181800, "loss": 0.0139, "lr": 2.6315109838574754e-05, "epoch": 10.6985698569857, "percentage": 53.49, "elapsed_time": "3:49:55", "remaining_time": "3:19:54", "throughput": 1487.76, "total_tokens": 20524832} {"current_steps": 97255, "total_steps": 181800, "loss": 0.0114, "lr": 2.631271308785067e-05, "epoch": 10.699119911991199, "percentage": 53.5, "elapsed_time": "3:49:56", "remaining_time": "3:19:53", "throughput": 1487.76, "total_tokens": 20525824} {"current_steps": 97260, "total_steps": 181800, "loss": 0.005, "lr": 2.6310316325027956e-05, "epoch": 10.6996699669967, "percentage": 53.5, "elapsed_time": "3:49:57", "remaining_time": "3:19:52", "throughput": 1487.76, "total_tokens": 20526912} {"current_steps": 97265, "total_steps": 181800, "loss": 0.0563, "lr": 2.630791955012868e-05, "epoch": 10.7002200220022, "percentage": 53.5, "elapsed_time": "3:49:57", "remaining_time": "3:19:52", "throughput": 1487.77, "total_tokens": 20528000} {"current_steps": 97270, "total_steps": 181800, "loss": 0.0067, "lr": 2.6305522763174935e-05, "epoch": 10.7007700770077, "percentage": 53.5, "elapsed_time": "3:49:58", "remaining_time": "3:19:51", "throughput": 1487.77, "total_tokens": 20529088} {"current_steps": 97275, "total_steps": 181800, "loss": 0.0041, "lr": 2.6303125964188812e-05, "epoch": 10.701320132013201, "percentage": 53.51, "elapsed_time": "3:49:59", "remaining_time": "3:19:50", "throughput": 1487.77, "total_tokens": 20530144} {"current_steps": 97280, "total_steps": 181800, "loss": 0.0407, "lr": 2.630072915319241e-05, "epoch": 10.701870187018702, "percentage": 53.51, "elapsed_time": "3:49:59", "remaining_time": "3:19:49", "throughput": 1487.77, "total_tokens": 20531104} {"current_steps": 97285, "total_steps": 181800, "loss": 0.067, "lr": 2.6298332330207805e-05, "epoch": 10.702420242024202, "percentage": 53.51, "elapsed_time": "3:50:00", "remaining_time": "3:19:49", "throughput": 1487.78, "total_tokens": 20532256} {"current_steps": 97290, "total_steps": 181800, "loss": 0.0279, "lr": 2.6295935495257097e-05, "epoch": 10.702970297029703, "percentage": 53.51, "elapsed_time": "3:50:01", "remaining_time": "3:19:48", "throughput": 1487.78, "total_tokens": 20533280} {"current_steps": 97295, "total_steps": 181800, "loss": 0.0047, "lr": 2.6293538648362364e-05, "epoch": 10.703520352035204, "percentage": 53.52, "elapsed_time": "3:50:01", "remaining_time": "3:19:47", "throughput": 1487.77, "total_tokens": 20534240} {"current_steps": 97300, "total_steps": 181800, "loss": 0.0721, "lr": 2.6291141789545714e-05, "epoch": 10.704070407040705, "percentage": 53.52, "elapsed_time": "3:50:02", "remaining_time": "3:19:46", "throughput": 1487.78, "total_tokens": 20535328} {"current_steps": 97305, "total_steps": 181800, "loss": 0.0689, "lr": 2.6288744918829233e-05, "epoch": 10.704620462046204, "percentage": 53.52, "elapsed_time": "3:50:03", "remaining_time": "3:19:46", "throughput": 1487.78, "total_tokens": 20536416} {"current_steps": 97310, "total_steps": 181800, "loss": 0.0201, "lr": 2.6286348036235003e-05, "epoch": 10.705170517051705, "percentage": 53.53, "elapsed_time": "3:50:04", "remaining_time": "3:19:45", "throughput": 1487.78, "total_tokens": 20537408} {"current_steps": 97315, "total_steps": 181800, "loss": 0.0152, "lr": 2.6283951141785123e-05, "epoch": 10.705720572057206, "percentage": 53.53, "elapsed_time": "3:50:04", "remaining_time": "3:19:44", "throughput": 1487.78, "total_tokens": 20538432} {"current_steps": 97320, "total_steps": 181800, "loss": 0.0026, "lr": 2.6281554235501682e-05, "epoch": 10.706270627062706, "percentage": 53.53, "elapsed_time": "3:50:05", "remaining_time": "3:19:44", "throughput": 1487.78, "total_tokens": 20539456} {"current_steps": 97325, "total_steps": 181800, "loss": 0.0329, "lr": 2.6279157317406766e-05, "epoch": 10.706820682068207, "percentage": 53.53, "elapsed_time": "3:50:06", "remaining_time": "3:19:43", "throughput": 1487.78, "total_tokens": 20540480} {"current_steps": 97330, "total_steps": 181800, "loss": 0.1091, "lr": 2.6276760387522475e-05, "epoch": 10.707370737073708, "percentage": 53.54, "elapsed_time": "3:50:06", "remaining_time": "3:19:42", "throughput": 1487.79, "total_tokens": 20541600} {"current_steps": 97335, "total_steps": 181800, "loss": 0.0165, "lr": 2.62743634458709e-05, "epoch": 10.707920792079207, "percentage": 53.54, "elapsed_time": "3:50:07", "remaining_time": "3:19:41", "throughput": 1487.79, "total_tokens": 20542656} {"current_steps": 97340, "total_steps": 181800, "loss": 0.0543, "lr": 2.627196649247412e-05, "epoch": 10.708470847084708, "percentage": 53.54, "elapsed_time": "3:50:08", "remaining_time": "3:19:41", "throughput": 1487.79, "total_tokens": 20543680} {"current_steps": 97345, "total_steps": 181800, "loss": 0.143, "lr": 2.6269569527354238e-05, "epoch": 10.70902090209021, "percentage": 53.55, "elapsed_time": "3:50:08", "remaining_time": "3:19:40", "throughput": 1487.8, "total_tokens": 20544800} {"current_steps": 97350, "total_steps": 181800, "loss": 0.0035, "lr": 2.626717255053334e-05, "epoch": 10.70957095709571, "percentage": 53.55, "elapsed_time": "3:50:09", "remaining_time": "3:19:39", "throughput": 1487.79, "total_tokens": 20545792} {"current_steps": 97355, "total_steps": 181800, "loss": 0.0062, "lr": 2.626477556203352e-05, "epoch": 10.71012101210121, "percentage": 53.55, "elapsed_time": "3:50:10", "remaining_time": "3:19:38", "throughput": 1487.8, "total_tokens": 20546848} {"current_steps": 97360, "total_steps": 181800, "loss": 0.0022, "lr": 2.6262378561876887e-05, "epoch": 10.710671067106711, "percentage": 53.55, "elapsed_time": "3:50:10", "remaining_time": "3:19:38", "throughput": 1487.8, "total_tokens": 20548000} {"current_steps": 97365, "total_steps": 181800, "loss": 0.0015, "lr": 2.6259981550085504e-05, "epoch": 10.711221122112212, "percentage": 53.56, "elapsed_time": "3:50:11", "remaining_time": "3:19:37", "throughput": 1487.81, "total_tokens": 20549088} {"current_steps": 97370, "total_steps": 181800, "loss": 0.1067, "lr": 2.6257584526681472e-05, "epoch": 10.711771177117711, "percentage": 53.56, "elapsed_time": "3:50:12", "remaining_time": "3:19:36", "throughput": 1487.81, "total_tokens": 20550112} {"current_steps": 97375, "total_steps": 181800, "loss": 0.0023, "lr": 2.6255187491686888e-05, "epoch": 10.712321232123212, "percentage": 53.56, "elapsed_time": "3:50:13", "remaining_time": "3:19:36", "throughput": 1487.82, "total_tokens": 20551232} {"current_steps": 97380, "total_steps": 181800, "loss": 0.0066, "lr": 2.6252790445123854e-05, "epoch": 10.712871287128714, "percentage": 53.56, "elapsed_time": "3:50:13", "remaining_time": "3:19:35", "throughput": 1487.82, "total_tokens": 20552288} {"current_steps": 97385, "total_steps": 181800, "loss": 0.0911, "lr": 2.625039338701444e-05, "epoch": 10.713421342134213, "percentage": 53.57, "elapsed_time": "3:50:14", "remaining_time": "3:19:34", "throughput": 1487.82, "total_tokens": 20553376} {"current_steps": 97390, "total_steps": 181800, "loss": 0.0633, "lr": 2.624799631738075e-05, "epoch": 10.713971397139714, "percentage": 53.57, "elapsed_time": "3:50:15", "remaining_time": "3:19:33", "throughput": 1487.83, "total_tokens": 20554464} {"current_steps": 97395, "total_steps": 181800, "loss": 0.0155, "lr": 2.6245599236244884e-05, "epoch": 10.714521452145215, "percentage": 53.57, "elapsed_time": "3:50:15", "remaining_time": "3:19:33", "throughput": 1487.82, "total_tokens": 20555456} {"current_steps": 97400, "total_steps": 181800, "loss": 0.0634, "lr": 2.624320214362892e-05, "epoch": 10.715071507150714, "percentage": 53.58, "elapsed_time": "3:50:16", "remaining_time": "3:19:32", "throughput": 1487.82, "total_tokens": 20556448} {"current_steps": 97405, "total_steps": 181800, "loss": 0.0022, "lr": 2.6240805039554973e-05, "epoch": 10.715621562156215, "percentage": 53.58, "elapsed_time": "3:50:17", "remaining_time": "3:19:31", "throughput": 1487.83, "total_tokens": 20557536} {"current_steps": 97410, "total_steps": 181800, "loss": 0.0305, "lr": 2.623840792404511e-05, "epoch": 10.716171617161717, "percentage": 53.58, "elapsed_time": "3:50:17", "remaining_time": "3:19:30", "throughput": 1487.82, "total_tokens": 20558528} {"current_steps": 97415, "total_steps": 181800, "loss": 0.0862, "lr": 2.623601079712143e-05, "epoch": 10.716721672167218, "percentage": 53.58, "elapsed_time": "3:50:18", "remaining_time": "3:19:30", "throughput": 1487.82, "total_tokens": 20559520} {"current_steps": 97420, "total_steps": 181800, "loss": 0.1358, "lr": 2.623361365880604e-05, "epoch": 10.717271727172717, "percentage": 53.59, "elapsed_time": "3:50:19", "remaining_time": "3:19:29", "throughput": 1487.82, "total_tokens": 20560576} {"current_steps": 97425, "total_steps": 181800, "loss": 0.0394, "lr": 2.623121650912102e-05, "epoch": 10.717821782178218, "percentage": 53.59, "elapsed_time": "3:50:19", "remaining_time": "3:19:28", "throughput": 1487.83, "total_tokens": 20561664} {"current_steps": 97430, "total_steps": 181800, "loss": 0.0591, "lr": 2.6228819348088475e-05, "epoch": 10.718371837183719, "percentage": 53.59, "elapsed_time": "3:50:20", "remaining_time": "3:19:28", "throughput": 1487.83, "total_tokens": 20562720} {"current_steps": 97435, "total_steps": 181800, "loss": 0.0322, "lr": 2.6226422175730487e-05, "epoch": 10.718921892189218, "percentage": 53.59, "elapsed_time": "3:50:21", "remaining_time": "3:19:27", "throughput": 1487.83, "total_tokens": 20563776} {"current_steps": 97440, "total_steps": 181800, "loss": 0.0041, "lr": 2.6224024992069156e-05, "epoch": 10.71947194719472, "percentage": 53.6, "elapsed_time": "3:50:21", "remaining_time": "3:19:26", "throughput": 1487.83, "total_tokens": 20564832} {"current_steps": 97445, "total_steps": 181800, "loss": 0.027, "lr": 2.622162779712657e-05, "epoch": 10.72002200220022, "percentage": 53.6, "elapsed_time": "3:50:22", "remaining_time": "3:19:25", "throughput": 1487.84, "total_tokens": 20565888} {"current_steps": 97450, "total_steps": 181800, "loss": 0.0659, "lr": 2.621923059092483e-05, "epoch": 10.72057205720572, "percentage": 53.6, "elapsed_time": "3:50:23", "remaining_time": "3:19:25", "throughput": 1487.84, "total_tokens": 20567008} {"current_steps": 97455, "total_steps": 181800, "loss": 0.0198, "lr": 2.621683337348603e-05, "epoch": 10.721122112211221, "percentage": 53.61, "elapsed_time": "3:50:24", "remaining_time": "3:19:24", "throughput": 1487.85, "total_tokens": 20568096} {"current_steps": 97460, "total_steps": 181800, "loss": 0.053, "lr": 2.6214436144832256e-05, "epoch": 10.721672167216722, "percentage": 53.61, "elapsed_time": "3:50:24", "remaining_time": "3:19:23", "throughput": 1487.85, "total_tokens": 20569120} {"current_steps": 97465, "total_steps": 181800, "loss": 0.0054, "lr": 2.621203890498561e-05, "epoch": 10.722222222222221, "percentage": 53.61, "elapsed_time": "3:50:25", "remaining_time": "3:19:22", "throughput": 1487.84, "total_tokens": 20570112} {"current_steps": 97470, "total_steps": 181800, "loss": 0.008, "lr": 2.620964165396818e-05, "epoch": 10.722772277227723, "percentage": 53.61, "elapsed_time": "3:50:26", "remaining_time": "3:19:22", "throughput": 1487.85, "total_tokens": 20571200} {"current_steps": 97475, "total_steps": 181800, "loss": 0.1194, "lr": 2.6207244391802065e-05, "epoch": 10.723322332233224, "percentage": 53.62, "elapsed_time": "3:50:26", "remaining_time": "3:19:21", "throughput": 1487.85, "total_tokens": 20572288} {"current_steps": 97480, "total_steps": 181800, "loss": 0.0056, "lr": 2.6204847118509358e-05, "epoch": 10.723872387238725, "percentage": 53.62, "elapsed_time": "3:50:27", "remaining_time": "3:19:20", "throughput": 1487.85, "total_tokens": 20573248} {"current_steps": 97485, "total_steps": 181800, "loss": 0.2115, "lr": 2.6202449834112147e-05, "epoch": 10.724422442244224, "percentage": 53.62, "elapsed_time": "3:50:28", "remaining_time": "3:19:20", "throughput": 1487.86, "total_tokens": 20574368} {"current_steps": 97490, "total_steps": 181800, "loss": 0.0586, "lr": 2.6200052538632543e-05, "epoch": 10.724972497249725, "percentage": 53.62, "elapsed_time": "3:50:28", "remaining_time": "3:19:19", "throughput": 1487.86, "total_tokens": 20575392} {"current_steps": 97495, "total_steps": 181800, "loss": 0.0118, "lr": 2.6197655232092623e-05, "epoch": 10.725522552255226, "percentage": 53.63, "elapsed_time": "3:50:29", "remaining_time": "3:19:18", "throughput": 1487.85, "total_tokens": 20576384} {"current_steps": 97500, "total_steps": 181800, "loss": 0.0091, "lr": 2.6195257914514492e-05, "epoch": 10.726072607260726, "percentage": 53.63, "elapsed_time": "3:50:30", "remaining_time": "3:19:17", "throughput": 1487.85, "total_tokens": 20577440} {"current_steps": 97505, "total_steps": 181800, "loss": 0.0112, "lr": 2.6192860585920244e-05, "epoch": 10.726622662266227, "percentage": 53.63, "elapsed_time": "3:50:30", "remaining_time": "3:19:17", "throughput": 1487.86, "total_tokens": 20578496} {"current_steps": 97510, "total_steps": 181800, "loss": 0.0058, "lr": 2.619046324633197e-05, "epoch": 10.727172717271728, "percentage": 53.64, "elapsed_time": "3:50:31", "remaining_time": "3:19:16", "throughput": 1487.86, "total_tokens": 20579584} {"current_steps": 97515, "total_steps": 181800, "loss": 0.0773, "lr": 2.6188065895771764e-05, "epoch": 10.727722772277227, "percentage": 53.64, "elapsed_time": "3:50:32", "remaining_time": "3:19:15", "throughput": 1487.87, "total_tokens": 20580672} {"current_steps": 97520, "total_steps": 181800, "loss": 0.0065, "lr": 2.618566853426173e-05, "epoch": 10.728272827282728, "percentage": 53.64, "elapsed_time": "3:50:33", "remaining_time": "3:19:14", "throughput": 1487.87, "total_tokens": 20581728} {"current_steps": 97525, "total_steps": 181800, "loss": 0.0105, "lr": 2.6183271161823962e-05, "epoch": 10.72882288228823, "percentage": 53.64, "elapsed_time": "3:50:33", "remaining_time": "3:19:14", "throughput": 1487.87, "total_tokens": 20582784} {"current_steps": 97530, "total_steps": 181800, "loss": 0.0341, "lr": 2.6180873778480543e-05, "epoch": 10.729372937293729, "percentage": 53.65, "elapsed_time": "3:50:34", "remaining_time": "3:19:13", "throughput": 1487.87, "total_tokens": 20583872} {"current_steps": 97535, "total_steps": 181800, "loss": 0.0368, "lr": 2.617847638425358e-05, "epoch": 10.72992299229923, "percentage": 53.65, "elapsed_time": "3:50:35", "remaining_time": "3:19:12", "throughput": 1487.88, "total_tokens": 20584992} {"current_steps": 97540, "total_steps": 181800, "loss": 0.0058, "lr": 2.617607897916517e-05, "epoch": 10.73047304730473, "percentage": 53.65, "elapsed_time": "3:50:35", "remaining_time": "3:19:12", "throughput": 1487.88, "total_tokens": 20586048} {"current_steps": 97545, "total_steps": 181800, "loss": 0.0134, "lr": 2.6173681563237395e-05, "epoch": 10.731023102310232, "percentage": 53.66, "elapsed_time": "3:50:36", "remaining_time": "3:19:11", "throughput": 1487.88, "total_tokens": 20587072} {"current_steps": 97550, "total_steps": 181800, "loss": 0.0028, "lr": 2.6171284136492374e-05, "epoch": 10.731573157315731, "percentage": 53.66, "elapsed_time": "3:50:37", "remaining_time": "3:19:10", "throughput": 1487.89, "total_tokens": 20588192} {"current_steps": 97555, "total_steps": 181800, "loss": 0.0162, "lr": 2.6168886698952182e-05, "epoch": 10.732123212321232, "percentage": 53.66, "elapsed_time": "3:50:37", "remaining_time": "3:19:09", "throughput": 1487.89, "total_tokens": 20589216} {"current_steps": 97560, "total_steps": 181800, "loss": 0.0019, "lr": 2.6166489250638913e-05, "epoch": 10.732673267326733, "percentage": 53.66, "elapsed_time": "3:50:38", "remaining_time": "3:19:09", "throughput": 1487.9, "total_tokens": 20590336} {"current_steps": 97565, "total_steps": 181800, "loss": 0.1016, "lr": 2.6164091791574686e-05, "epoch": 10.733223322332233, "percentage": 53.67, "elapsed_time": "3:50:39", "remaining_time": "3:19:08", "throughput": 1487.9, "total_tokens": 20591360} {"current_steps": 97570, "total_steps": 181800, "loss": 0.0025, "lr": 2.6161694321781577e-05, "epoch": 10.733773377337734, "percentage": 53.67, "elapsed_time": "3:50:39", "remaining_time": "3:19:07", "throughput": 1487.9, "total_tokens": 20592416} {"current_steps": 97575, "total_steps": 181800, "loss": 0.0228, "lr": 2.615929684128169e-05, "epoch": 10.734323432343235, "percentage": 53.67, "elapsed_time": "3:50:40", "remaining_time": "3:19:06", "throughput": 1487.9, "total_tokens": 20593408} {"current_steps": 97580, "total_steps": 181800, "loss": 0.0106, "lr": 2.615689935009712e-05, "epoch": 10.734873487348734, "percentage": 53.67, "elapsed_time": "3:50:41", "remaining_time": "3:19:06", "throughput": 1487.9, "total_tokens": 20594464} {"current_steps": 97585, "total_steps": 181800, "loss": 0.0526, "lr": 2.615450184824997e-05, "epoch": 10.735423542354235, "percentage": 53.68, "elapsed_time": "3:50:41", "remaining_time": "3:19:05", "throughput": 1487.9, "total_tokens": 20595488} {"current_steps": 97590, "total_steps": 181800, "loss": 0.0051, "lr": 2.6152104335762316e-05, "epoch": 10.735973597359736, "percentage": 53.68, "elapsed_time": "3:50:42", "remaining_time": "3:19:04", "throughput": 1487.91, "total_tokens": 20596576} {"current_steps": 97595, "total_steps": 181800, "loss": 0.0269, "lr": 2.6149706812656282e-05, "epoch": 10.736523652365236, "percentage": 53.68, "elapsed_time": "3:50:43", "remaining_time": "3:19:04", "throughput": 1487.91, "total_tokens": 20597664} {"current_steps": 97600, "total_steps": 181800, "loss": 0.149, "lr": 2.6147309278953947e-05, "epoch": 10.737073707370737, "percentage": 53.69, "elapsed_time": "3:50:44", "remaining_time": "3:19:03", "throughput": 1487.91, "total_tokens": 20598720} {"current_steps": 97605, "total_steps": 181800, "loss": 0.0043, "lr": 2.6144911734677413e-05, "epoch": 10.737623762376238, "percentage": 53.69, "elapsed_time": "3:50:44", "remaining_time": "3:19:02", "throughput": 1487.91, "total_tokens": 20599744} {"current_steps": 97610, "total_steps": 181800, "loss": 0.0662, "lr": 2.6142514179848775e-05, "epoch": 10.738173817381739, "percentage": 53.69, "elapsed_time": "3:50:45", "remaining_time": "3:19:01", "throughput": 1487.91, "total_tokens": 20600768} {"current_steps": 97615, "total_steps": 181800, "loss": 0.0159, "lr": 2.614011661449014e-05, "epoch": 10.738723872387238, "percentage": 53.69, "elapsed_time": "3:50:46", "remaining_time": "3:19:01", "throughput": 1487.92, "total_tokens": 20601856} {"current_steps": 97620, "total_steps": 181800, "loss": 0.0016, "lr": 2.6137719038623592e-05, "epoch": 10.73927392739274, "percentage": 53.7, "elapsed_time": "3:50:46", "remaining_time": "3:19:00", "throughput": 1487.92, "total_tokens": 20602912} {"current_steps": 97625, "total_steps": 181800, "loss": 0.0309, "lr": 2.6135321452271234e-05, "epoch": 10.73982398239824, "percentage": 53.7, "elapsed_time": "3:50:47", "remaining_time": "3:18:59", "throughput": 1487.92, "total_tokens": 20603904} {"current_steps": 97630, "total_steps": 181800, "loss": 0.101, "lr": 2.6132923855455153e-05, "epoch": 10.74037403740374, "percentage": 53.7, "elapsed_time": "3:50:48", "remaining_time": "3:18:58", "throughput": 1487.92, "total_tokens": 20604928} {"current_steps": 97635, "total_steps": 181800, "loss": 0.0024, "lr": 2.6130526248197467e-05, "epoch": 10.74092409240924, "percentage": 53.7, "elapsed_time": "3:50:48", "remaining_time": "3:18:58", "throughput": 1487.92, "total_tokens": 20605984} {"current_steps": 97640, "total_steps": 181800, "loss": 0.0628, "lr": 2.6128128630520265e-05, "epoch": 10.741474147414742, "percentage": 53.71, "elapsed_time": "3:50:49", "remaining_time": "3:18:57", "throughput": 1487.92, "total_tokens": 20607040} {"current_steps": 97645, "total_steps": 181800, "loss": 0.0569, "lr": 2.6125731002445643e-05, "epoch": 10.742024202420241, "percentage": 53.71, "elapsed_time": "3:50:50", "remaining_time": "3:18:56", "throughput": 1487.92, "total_tokens": 20608064} {"current_steps": 97650, "total_steps": 181800, "loss": 0.1105, "lr": 2.6123333363995693e-05, "epoch": 10.742574257425742, "percentage": 53.71, "elapsed_time": "3:50:50", "remaining_time": "3:18:56", "throughput": 1487.92, "total_tokens": 20609088} {"current_steps": 97655, "total_steps": 181800, "loss": 0.0039, "lr": 2.6120935715192525e-05, "epoch": 10.743124312431243, "percentage": 53.72, "elapsed_time": "3:50:51", "remaining_time": "3:18:55", "throughput": 1487.92, "total_tokens": 20610144} {"current_steps": 97660, "total_steps": 181800, "loss": 0.0045, "lr": 2.6118538056058217e-05, "epoch": 10.743674367436743, "percentage": 53.72, "elapsed_time": "3:50:52", "remaining_time": "3:18:54", "throughput": 1487.92, "total_tokens": 20611168} {"current_steps": 97665, "total_steps": 181800, "loss": 0.0042, "lr": 2.6116140386614895e-05, "epoch": 10.744224422442244, "percentage": 53.72, "elapsed_time": "3:50:52", "remaining_time": "3:18:53", "throughput": 1487.93, "total_tokens": 20612288} {"current_steps": 97670, "total_steps": 181800, "loss": 0.0152, "lr": 2.6113742706884643e-05, "epoch": 10.744774477447745, "percentage": 53.72, "elapsed_time": "3:50:53", "remaining_time": "3:18:53", "throughput": 1487.93, "total_tokens": 20613312} {"current_steps": 97675, "total_steps": 181800, "loss": 0.0105, "lr": 2.6111345016889544e-05, "epoch": 10.745324532453246, "percentage": 53.73, "elapsed_time": "3:50:54", "remaining_time": "3:18:52", "throughput": 1487.93, "total_tokens": 20614368} {"current_steps": 97680, "total_steps": 181800, "loss": 0.0046, "lr": 2.6108947316651723e-05, "epoch": 10.745874587458745, "percentage": 53.73, "elapsed_time": "3:50:55", "remaining_time": "3:18:51", "throughput": 1487.94, "total_tokens": 20615424} {"current_steps": 97685, "total_steps": 181800, "loss": 0.0428, "lr": 2.6106549606193266e-05, "epoch": 10.746424642464246, "percentage": 53.73, "elapsed_time": "3:50:55", "remaining_time": "3:18:50", "throughput": 1487.94, "total_tokens": 20616480} {"current_steps": 97690, "total_steps": 181800, "loss": 0.0319, "lr": 2.6104151885536266e-05, "epoch": 10.746974697469748, "percentage": 53.73, "elapsed_time": "3:50:56", "remaining_time": "3:18:50", "throughput": 1487.94, "total_tokens": 20617568} {"current_steps": 97695, "total_steps": 181800, "loss": 0.0246, "lr": 2.6101754154702835e-05, "epoch": 10.747524752475247, "percentage": 53.74, "elapsed_time": "3:50:57", "remaining_time": "3:18:49", "throughput": 1487.95, "total_tokens": 20618656} {"current_steps": 97700, "total_steps": 181800, "loss": 0.02, "lr": 2.6099356413715065e-05, "epoch": 10.748074807480748, "percentage": 53.74, "elapsed_time": "3:50:57", "remaining_time": "3:18:48", "throughput": 1487.94, "total_tokens": 20619648} {"current_steps": 97705, "total_steps": 181800, "loss": 0.117, "lr": 2.6096958662595046e-05, "epoch": 10.748624862486249, "percentage": 53.74, "elapsed_time": "3:50:58", "remaining_time": "3:18:48", "throughput": 1487.95, "total_tokens": 20620704} {"current_steps": 97710, "total_steps": 181800, "loss": 0.0456, "lr": 2.609456090136489e-05, "epoch": 10.749174917491748, "percentage": 53.75, "elapsed_time": "3:50:59", "remaining_time": "3:18:47", "throughput": 1487.95, "total_tokens": 20621792} {"current_steps": 97715, "total_steps": 181800, "loss": 0.0325, "lr": 2.6092163130046692e-05, "epoch": 10.74972497249725, "percentage": 53.75, "elapsed_time": "3:50:59", "remaining_time": "3:18:46", "throughput": 1487.95, "total_tokens": 20622816} {"current_steps": 97720, "total_steps": 181800, "loss": 0.0715, "lr": 2.608976534866255e-05, "epoch": 10.75027502750275, "percentage": 53.75, "elapsed_time": "3:51:00", "remaining_time": "3:18:45", "throughput": 1487.96, "total_tokens": 20623936} {"current_steps": 97725, "total_steps": 181800, "loss": 0.0556, "lr": 2.6087367557234567e-05, "epoch": 10.750825082508252, "percentage": 53.75, "elapsed_time": "3:51:01", "remaining_time": "3:18:45", "throughput": 1487.95, "total_tokens": 20624896} {"current_steps": 97730, "total_steps": 181800, "loss": 0.0367, "lr": 2.6084969755784833e-05, "epoch": 10.751375137513751, "percentage": 53.76, "elapsed_time": "3:51:01", "remaining_time": "3:18:44", "throughput": 1487.95, "total_tokens": 20625888} {"current_steps": 97735, "total_steps": 181800, "loss": 0.0376, "lr": 2.6082571944335455e-05, "epoch": 10.751925192519252, "percentage": 53.76, "elapsed_time": "3:51:02", "remaining_time": "3:18:43", "throughput": 1487.95, "total_tokens": 20626880} {"current_steps": 97740, "total_steps": 181800, "loss": 0.0088, "lr": 2.6080174122908537e-05, "epoch": 10.752475247524753, "percentage": 53.76, "elapsed_time": "3:51:03", "remaining_time": "3:18:42", "throughput": 1487.96, "total_tokens": 20628000} {"current_steps": 97745, "total_steps": 181800, "loss": 0.0711, "lr": 2.6077776291526163e-05, "epoch": 10.753025302530252, "percentage": 53.77, "elapsed_time": "3:51:04", "remaining_time": "3:18:42", "throughput": 1487.96, "total_tokens": 20629056} {"current_steps": 97750, "total_steps": 181800, "loss": 0.0188, "lr": 2.6075378450210447e-05, "epoch": 10.753575357535754, "percentage": 53.77, "elapsed_time": "3:51:04", "remaining_time": "3:18:41", "throughput": 1487.96, "total_tokens": 20630048} {"current_steps": 97755, "total_steps": 181800, "loss": 0.0373, "lr": 2.6072980598983487e-05, "epoch": 10.754125412541255, "percentage": 53.77, "elapsed_time": "3:51:05", "remaining_time": "3:18:40", "throughput": 1487.96, "total_tokens": 20631168} {"current_steps": 97760, "total_steps": 181800, "loss": 0.01, "lr": 2.6070582737867376e-05, "epoch": 10.754675467546754, "percentage": 53.77, "elapsed_time": "3:51:06", "remaining_time": "3:18:40", "throughput": 1487.96, "total_tokens": 20632224} {"current_steps": 97765, "total_steps": 181800, "loss": 0.0039, "lr": 2.606818486688422e-05, "epoch": 10.755225522552255, "percentage": 53.78, "elapsed_time": "3:51:06", "remaining_time": "3:18:39", "throughput": 1487.97, "total_tokens": 20633280} {"current_steps": 97770, "total_steps": 181800, "loss": 0.0047, "lr": 2.606578698605611e-05, "epoch": 10.755775577557756, "percentage": 53.78, "elapsed_time": "3:51:07", "remaining_time": "3:18:38", "throughput": 1487.97, "total_tokens": 20634368} {"current_steps": 97775, "total_steps": 181800, "loss": 0.0069, "lr": 2.6063389095405155e-05, "epoch": 10.756325632563257, "percentage": 53.78, "elapsed_time": "3:51:08", "remaining_time": "3:18:37", "throughput": 1487.98, "total_tokens": 20635488} {"current_steps": 97780, "total_steps": 181800, "loss": 0.0145, "lr": 2.606099119495346e-05, "epoch": 10.756875687568757, "percentage": 53.78, "elapsed_time": "3:51:08", "remaining_time": "3:18:37", "throughput": 1487.99, "total_tokens": 20636608} {"current_steps": 97785, "total_steps": 181800, "loss": 0.0406, "lr": 2.6058593284723114e-05, "epoch": 10.757425742574258, "percentage": 53.79, "elapsed_time": "3:51:09", "remaining_time": "3:18:36", "throughput": 1487.98, "total_tokens": 20637632} {"current_steps": 97790, "total_steps": 181800, "loss": 0.0949, "lr": 2.605619536473622e-05, "epoch": 10.757975797579759, "percentage": 53.79, "elapsed_time": "3:51:10", "remaining_time": "3:18:35", "throughput": 1487.98, "total_tokens": 20638656} {"current_steps": 97795, "total_steps": 181800, "loss": 0.0185, "lr": 2.605379743501488e-05, "epoch": 10.758525852585258, "percentage": 53.79, "elapsed_time": "3:51:10", "remaining_time": "3:18:34", "throughput": 1487.98, "total_tokens": 20639680} {"current_steps": 97800, "total_steps": 181800, "loss": 0.1192, "lr": 2.6051399495581196e-05, "epoch": 10.75907590759076, "percentage": 53.8, "elapsed_time": "3:51:11", "remaining_time": "3:18:34", "throughput": 1487.99, "total_tokens": 20640736} {"current_steps": 97805, "total_steps": 181800, "loss": 0.1083, "lr": 2.6049001546457265e-05, "epoch": 10.75962596259626, "percentage": 53.8, "elapsed_time": "3:51:12", "remaining_time": "3:18:33", "throughput": 1487.99, "total_tokens": 20641856} {"current_steps": 97810, "total_steps": 181800, "loss": 0.025, "lr": 2.6046603587665198e-05, "epoch": 10.76017601760176, "percentage": 53.8, "elapsed_time": "3:51:12", "remaining_time": "3:18:32", "throughput": 1488.0, "total_tokens": 20642944} {"current_steps": 97815, "total_steps": 181800, "loss": 0.0588, "lr": 2.6044205619227086e-05, "epoch": 10.76072607260726, "percentage": 53.8, "elapsed_time": "3:51:13", "remaining_time": "3:18:32", "throughput": 1488.0, "total_tokens": 20644000} {"current_steps": 97820, "total_steps": 181800, "loss": 0.0069, "lr": 2.6041807641165023e-05, "epoch": 10.761276127612762, "percentage": 53.81, "elapsed_time": "3:51:14", "remaining_time": "3:18:31", "throughput": 1488.0, "total_tokens": 20645024} {"current_steps": 97825, "total_steps": 181800, "loss": 0.0067, "lr": 2.6039409653501123e-05, "epoch": 10.761826182618261, "percentage": 53.81, "elapsed_time": "3:51:15", "remaining_time": "3:18:30", "throughput": 1488.0, "total_tokens": 20646016} {"current_steps": 97830, "total_steps": 181800, "loss": 0.0021, "lr": 2.6037011656257487e-05, "epoch": 10.762376237623762, "percentage": 53.81, "elapsed_time": "3:51:15", "remaining_time": "3:18:29", "throughput": 1488.0, "total_tokens": 20647008} {"current_steps": 97835, "total_steps": 181800, "loss": 0.0122, "lr": 2.603461364945621e-05, "epoch": 10.762926292629263, "percentage": 53.81, "elapsed_time": "3:51:16", "remaining_time": "3:18:29", "throughput": 1488.0, "total_tokens": 20648064} {"current_steps": 97840, "total_steps": 181800, "loss": 0.0167, "lr": 2.6032215633119393e-05, "epoch": 10.763476347634764, "percentage": 53.82, "elapsed_time": "3:51:17", "remaining_time": "3:18:28", "throughput": 1488.0, "total_tokens": 20649152} {"current_steps": 97845, "total_steps": 181800, "loss": 0.0113, "lr": 2.6029817607269147e-05, "epoch": 10.764026402640264, "percentage": 53.82, "elapsed_time": "3:51:17", "remaining_time": "3:18:27", "throughput": 1488.01, "total_tokens": 20650240} {"current_steps": 97850, "total_steps": 181800, "loss": 0.0214, "lr": 2.6027419571927552e-05, "epoch": 10.764576457645765, "percentage": 53.82, "elapsed_time": "3:51:18", "remaining_time": "3:18:26", "throughput": 1488.01, "total_tokens": 20651296} {"current_steps": 97855, "total_steps": 181800, "loss": 0.0015, "lr": 2.6025021527116745e-05, "epoch": 10.765126512651266, "percentage": 53.83, "elapsed_time": "3:51:19", "remaining_time": "3:18:26", "throughput": 1488.02, "total_tokens": 20652448} {"current_steps": 97860, "total_steps": 181800, "loss": 0.0096, "lr": 2.6022623472858792e-05, "epoch": 10.765676567656765, "percentage": 53.83, "elapsed_time": "3:51:19", "remaining_time": "3:18:25", "throughput": 1488.02, "total_tokens": 20653472} {"current_steps": 97865, "total_steps": 181800, "loss": 0.1186, "lr": 2.6020225409175806e-05, "epoch": 10.766226622662266, "percentage": 53.83, "elapsed_time": "3:51:20", "remaining_time": "3:18:24", "throughput": 1488.02, "total_tokens": 20654560} {"current_steps": 97870, "total_steps": 181800, "loss": 0.0088, "lr": 2.60178273360899e-05, "epoch": 10.766776677667767, "percentage": 53.83, "elapsed_time": "3:51:21", "remaining_time": "3:18:24", "throughput": 1488.03, "total_tokens": 20655648} {"current_steps": 97875, "total_steps": 181800, "loss": 0.0081, "lr": 2.6015429253623163e-05, "epoch": 10.767326732673267, "percentage": 53.84, "elapsed_time": "3:51:21", "remaining_time": "3:18:23", "throughput": 1488.03, "total_tokens": 20656768} {"current_steps": 97880, "total_steps": 181800, "loss": 0.017, "lr": 2.6013031161797707e-05, "epoch": 10.767876787678768, "percentage": 53.84, "elapsed_time": "3:51:22", "remaining_time": "3:18:22", "throughput": 1488.03, "total_tokens": 20657792} {"current_steps": 97885, "total_steps": 181800, "loss": 0.0386, "lr": 2.6010633060635624e-05, "epoch": 10.768426842684269, "percentage": 53.84, "elapsed_time": "3:51:23", "remaining_time": "3:18:21", "throughput": 1488.03, "total_tokens": 20658816} {"current_steps": 97890, "total_steps": 181800, "loss": 0.0194, "lr": 2.6008234950159028e-05, "epoch": 10.768976897689768, "percentage": 53.84, "elapsed_time": "3:51:24", "remaining_time": "3:18:21", "throughput": 1488.04, "total_tokens": 20659904} {"current_steps": 97895, "total_steps": 181800, "loss": 0.0269, "lr": 2.6005836830390003e-05, "epoch": 10.76952695269527, "percentage": 53.85, "elapsed_time": "3:51:24", "remaining_time": "3:18:20", "throughput": 1488.04, "total_tokens": 20660960} {"current_steps": 97900, "total_steps": 181800, "loss": 0.111, "lr": 2.600343870135067e-05, "epoch": 10.77007700770077, "percentage": 53.85, "elapsed_time": "3:51:25", "remaining_time": "3:18:19", "throughput": 1488.04, "total_tokens": 20662080} {"current_steps": 97905, "total_steps": 181800, "loss": 0.0033, "lr": 2.6001040563063122e-05, "epoch": 10.770627062706271, "percentage": 53.85, "elapsed_time": "3:51:26", "remaining_time": "3:18:19", "throughput": 1488.05, "total_tokens": 20663232} {"current_steps": 97910, "total_steps": 181800, "loss": 0.0759, "lr": 2.599864241554946e-05, "epoch": 10.77117711771177, "percentage": 53.86, "elapsed_time": "3:51:26", "remaining_time": "3:18:18", "throughput": 1488.05, "total_tokens": 20664256} {"current_steps": 97915, "total_steps": 181800, "loss": 0.0578, "lr": 2.59962442588318e-05, "epoch": 10.771727172717272, "percentage": 53.86, "elapsed_time": "3:51:27", "remaining_time": "3:18:17", "throughput": 1488.05, "total_tokens": 20665280} {"current_steps": 97920, "total_steps": 181800, "loss": 0.0197, "lr": 2.5993846092932227e-05, "epoch": 10.772277227722773, "percentage": 53.86, "elapsed_time": "3:51:28", "remaining_time": "3:18:16", "throughput": 1488.05, "total_tokens": 20666304} {"current_steps": 97925, "total_steps": 181800, "loss": 0.0734, "lr": 2.5991447917872852e-05, "epoch": 10.772827282728272, "percentage": 53.86, "elapsed_time": "3:51:28", "remaining_time": "3:18:16", "throughput": 1488.05, "total_tokens": 20667328} {"current_steps": 97930, "total_steps": 181800, "loss": 0.1554, "lr": 2.5989049733675787e-05, "epoch": 10.773377337733773, "percentage": 53.87, "elapsed_time": "3:51:29", "remaining_time": "3:18:15", "throughput": 1488.06, "total_tokens": 20668416} {"current_steps": 97935, "total_steps": 181800, "loss": 0.0251, "lr": 2.598665154036311e-05, "epoch": 10.773927392739274, "percentage": 53.87, "elapsed_time": "3:51:30", "remaining_time": "3:18:14", "throughput": 1488.06, "total_tokens": 20669472} {"current_steps": 97940, "total_steps": 181800, "loss": 0.1601, "lr": 2.5984253337956943e-05, "epoch": 10.774477447744774, "percentage": 53.87, "elapsed_time": "3:51:30", "remaining_time": "3:18:13", "throughput": 1488.06, "total_tokens": 20670560} {"current_steps": 97945, "total_steps": 181800, "loss": 0.1048, "lr": 2.5981855126479393e-05, "epoch": 10.775027502750275, "percentage": 53.88, "elapsed_time": "3:51:31", "remaining_time": "3:18:13", "throughput": 1488.07, "total_tokens": 20671680} {"current_steps": 97950, "total_steps": 181800, "loss": 0.007, "lr": 2.597945690595255e-05, "epoch": 10.775577557755776, "percentage": 53.88, "elapsed_time": "3:51:32", "remaining_time": "3:18:12", "throughput": 1488.07, "total_tokens": 20672704} {"current_steps": 97955, "total_steps": 181800, "loss": 0.003, "lr": 2.5977058676398523e-05, "epoch": 10.776127612761275, "percentage": 53.88, "elapsed_time": "3:51:32", "remaining_time": "3:18:11", "throughput": 1488.07, "total_tokens": 20673728} {"current_steps": 97960, "total_steps": 181800, "loss": 0.0094, "lr": 2.5974660437839416e-05, "epoch": 10.776677667766776, "percentage": 53.88, "elapsed_time": "3:51:33", "remaining_time": "3:18:11", "throughput": 1488.08, "total_tokens": 20674880} {"current_steps": 97965, "total_steps": 181800, "loss": 0.0425, "lr": 2.597226219029733e-05, "epoch": 10.777227722772277, "percentage": 53.89, "elapsed_time": "3:51:34", "remaining_time": "3:18:10", "throughput": 1488.08, "total_tokens": 20675936} {"current_steps": 97970, "total_steps": 181800, "loss": 0.0169, "lr": 2.596986393379437e-05, "epoch": 10.777777777777779, "percentage": 53.89, "elapsed_time": "3:51:35", "remaining_time": "3:18:09", "throughput": 1488.09, "total_tokens": 20677024} {"current_steps": 97975, "total_steps": 181800, "loss": 0.1104, "lr": 2.5967465668352647e-05, "epoch": 10.778327832783278, "percentage": 53.89, "elapsed_time": "3:51:35", "remaining_time": "3:18:08", "throughput": 1488.09, "total_tokens": 20678048} {"current_steps": 97980, "total_steps": 181800, "loss": 0.0258, "lr": 2.5965067393994248e-05, "epoch": 10.778877887788779, "percentage": 53.89, "elapsed_time": "3:51:36", "remaining_time": "3:18:08", "throughput": 1488.09, "total_tokens": 20679136} {"current_steps": 97985, "total_steps": 181800, "loss": 0.0088, "lr": 2.5962669110741287e-05, "epoch": 10.77942794279428, "percentage": 53.9, "elapsed_time": "3:51:37", "remaining_time": "3:18:07", "throughput": 1488.09, "total_tokens": 20680160} {"current_steps": 97990, "total_steps": 181800, "loss": 0.0232, "lr": 2.5960270818615867e-05, "epoch": 10.77997799779978, "percentage": 53.9, "elapsed_time": "3:51:37", "remaining_time": "3:18:06", "throughput": 1488.09, "total_tokens": 20681184} {"current_steps": 97995, "total_steps": 181800, "loss": 0.008, "lr": 2.595787251764009e-05, "epoch": 10.78052805280528, "percentage": 53.9, "elapsed_time": "3:51:38", "remaining_time": "3:18:05", "throughput": 1488.1, "total_tokens": 20682304} {"current_steps": 98000, "total_steps": 181800, "loss": 0.0092, "lr": 2.5955474207836072e-05, "epoch": 10.781078107810782, "percentage": 53.91, "elapsed_time": "3:51:39", "remaining_time": "3:18:05", "throughput": 1488.1, "total_tokens": 20683360} {"current_steps": 98005, "total_steps": 181800, "loss": 0.0162, "lr": 2.5953075889225897e-05, "epoch": 10.781628162816281, "percentage": 53.91, "elapsed_time": "3:51:39", "remaining_time": "3:18:04", "throughput": 1488.1, "total_tokens": 20684416} {"current_steps": 98010, "total_steps": 181800, "loss": 0.0135, "lr": 2.5950677561831678e-05, "epoch": 10.782178217821782, "percentage": 53.91, "elapsed_time": "3:51:40", "remaining_time": "3:18:03", "throughput": 1488.1, "total_tokens": 20685472} {"current_steps": 98015, "total_steps": 181800, "loss": 0.0068, "lr": 2.5948279225675526e-05, "epoch": 10.782728272827283, "percentage": 53.91, "elapsed_time": "3:51:41", "remaining_time": "3:18:03", "throughput": 1488.11, "total_tokens": 20686528} {"current_steps": 98020, "total_steps": 181800, "loss": 0.0186, "lr": 2.5945880880779533e-05, "epoch": 10.783278327832782, "percentage": 53.92, "elapsed_time": "3:51:41", "remaining_time": "3:18:02", "throughput": 1488.11, "total_tokens": 20687584} {"current_steps": 98025, "total_steps": 181800, "loss": 0.0214, "lr": 2.594348252716582e-05, "epoch": 10.783828382838283, "percentage": 53.92, "elapsed_time": "3:51:42", "remaining_time": "3:18:01", "throughput": 1488.11, "total_tokens": 20688640} {"current_steps": 98030, "total_steps": 181800, "loss": 0.0118, "lr": 2.5941084164856472e-05, "epoch": 10.784378437843785, "percentage": 53.92, "elapsed_time": "3:51:43", "remaining_time": "3:18:00", "throughput": 1488.11, "total_tokens": 20689632} {"current_steps": 98035, "total_steps": 181800, "loss": 0.0497, "lr": 2.593868579387361e-05, "epoch": 10.784928492849286, "percentage": 53.92, "elapsed_time": "3:51:44", "remaining_time": "3:18:00", "throughput": 1488.11, "total_tokens": 20690688} {"current_steps": 98040, "total_steps": 181800, "loss": 0.0112, "lr": 2.593628741423932e-05, "epoch": 10.785478547854785, "percentage": 53.93, "elapsed_time": "3:51:44", "remaining_time": "3:17:59", "throughput": 1488.11, "total_tokens": 20691712} {"current_steps": 98045, "total_steps": 181800, "loss": 0.0979, "lr": 2.5933889025975728e-05, "epoch": 10.786028602860286, "percentage": 53.93, "elapsed_time": "3:51:45", "remaining_time": "3:17:58", "throughput": 1488.11, "total_tokens": 20692768} {"current_steps": 98050, "total_steps": 181800, "loss": 0.0063, "lr": 2.5931490629104922e-05, "epoch": 10.786578657865787, "percentage": 53.93, "elapsed_time": "3:51:46", "remaining_time": "3:17:57", "throughput": 1488.11, "total_tokens": 20693824} {"current_steps": 98055, "total_steps": 181800, "loss": 0.0335, "lr": 2.592909222364902e-05, "epoch": 10.787128712871286, "percentage": 53.94, "elapsed_time": "3:51:46", "remaining_time": "3:17:57", "throughput": 1488.12, "total_tokens": 20694880} {"current_steps": 98060, "total_steps": 181800, "loss": 0.1123, "lr": 2.592669380963012e-05, "epoch": 10.787678767876788, "percentage": 53.94, "elapsed_time": "3:51:47", "remaining_time": "3:17:56", "throughput": 1488.12, "total_tokens": 20695936} {"current_steps": 98065, "total_steps": 181800, "loss": 0.0204, "lr": 2.5924295387070325e-05, "epoch": 10.788228822882289, "percentage": 53.94, "elapsed_time": "3:51:48", "remaining_time": "3:17:55", "throughput": 1488.12, "total_tokens": 20696960} {"current_steps": 98070, "total_steps": 181800, "loss": 0.0106, "lr": 2.5921896955991748e-05, "epoch": 10.788778877887788, "percentage": 53.94, "elapsed_time": "3:51:48", "remaining_time": "3:17:55", "throughput": 1488.12, "total_tokens": 20697952} {"current_steps": 98075, "total_steps": 181800, "loss": 0.0538, "lr": 2.5919498516416485e-05, "epoch": 10.789328932893289, "percentage": 53.95, "elapsed_time": "3:51:49", "remaining_time": "3:17:54", "throughput": 1488.12, "total_tokens": 20699008} {"current_steps": 98080, "total_steps": 181800, "loss": 0.0118, "lr": 2.591710006836664e-05, "epoch": 10.78987898789879, "percentage": 53.95, "elapsed_time": "3:51:50", "remaining_time": "3:17:53", "throughput": 1488.12, "total_tokens": 20700032} {"current_steps": 98085, "total_steps": 181800, "loss": 0.0049, "lr": 2.5914701611864333e-05, "epoch": 10.79042904290429, "percentage": 53.95, "elapsed_time": "3:51:50", "remaining_time": "3:17:52", "throughput": 1488.12, "total_tokens": 20701056} {"current_steps": 98090, "total_steps": 181800, "loss": 0.0125, "lr": 2.5912303146931655e-05, "epoch": 10.79097909790979, "percentage": 53.95, "elapsed_time": "3:51:51", "remaining_time": "3:17:52", "throughput": 1488.12, "total_tokens": 20702144} {"current_steps": 98095, "total_steps": 181800, "loss": 0.0034, "lr": 2.590990467359072e-05, "epoch": 10.791529152915292, "percentage": 53.96, "elapsed_time": "3:51:52", "remaining_time": "3:17:51", "throughput": 1488.13, "total_tokens": 20703200} {"current_steps": 98100, "total_steps": 181800, "loss": 0.0436, "lr": 2.5907506191863627e-05, "epoch": 10.792079207920793, "percentage": 53.96, "elapsed_time": "3:51:52", "remaining_time": "3:17:50", "throughput": 1488.13, "total_tokens": 20704224} {"current_steps": 98105, "total_steps": 181800, "loss": 0.0041, "lr": 2.5905107701772492e-05, "epoch": 10.792629262926292, "percentage": 53.96, "elapsed_time": "3:51:53", "remaining_time": "3:17:49", "throughput": 1488.13, "total_tokens": 20705280} {"current_steps": 98110, "total_steps": 181800, "loss": 0.0042, "lr": 2.5902709203339403e-05, "epoch": 10.793179317931793, "percentage": 53.97, "elapsed_time": "3:51:54", "remaining_time": "3:17:49", "throughput": 1488.13, "total_tokens": 20706368} {"current_steps": 98115, "total_steps": 181800, "loss": 0.0812, "lr": 2.5900310696586483e-05, "epoch": 10.793729372937294, "percentage": 53.97, "elapsed_time": "3:51:55", "remaining_time": "3:17:48", "throughput": 1488.13, "total_tokens": 20707392} {"current_steps": 98120, "total_steps": 181800, "loss": 0.0098, "lr": 2.589791218153583e-05, "epoch": 10.794279427942794, "percentage": 53.97, "elapsed_time": "3:51:55", "remaining_time": "3:17:47", "throughput": 1488.14, "total_tokens": 20708480} {"current_steps": 98125, "total_steps": 181800, "loss": 0.0523, "lr": 2.5895513658209552e-05, "epoch": 10.794829482948295, "percentage": 53.97, "elapsed_time": "3:51:56", "remaining_time": "3:17:47", "throughput": 1488.14, "total_tokens": 20709472} {"current_steps": 98130, "total_steps": 181800, "loss": 0.0574, "lr": 2.589311512662975e-05, "epoch": 10.795379537953796, "percentage": 53.98, "elapsed_time": "3:51:57", "remaining_time": "3:17:46", "throughput": 1488.14, "total_tokens": 20710496} {"current_steps": 98135, "total_steps": 181800, "loss": 0.0024, "lr": 2.589071658681854e-05, "epoch": 10.795929592959295, "percentage": 53.98, "elapsed_time": "3:51:57", "remaining_time": "3:17:45", "throughput": 1488.14, "total_tokens": 20711520} {"current_steps": 98140, "total_steps": 181800, "loss": 0.0678, "lr": 2.5888318038798026e-05, "epoch": 10.796479647964796, "percentage": 53.98, "elapsed_time": "3:51:58", "remaining_time": "3:17:44", "throughput": 1488.14, "total_tokens": 20712576} {"current_steps": 98145, "total_steps": 181800, "loss": 0.1302, "lr": 2.5885919482590304e-05, "epoch": 10.797029702970297, "percentage": 53.99, "elapsed_time": "3:51:59", "remaining_time": "3:17:44", "throughput": 1488.14, "total_tokens": 20713600} {"current_steps": 98150, "total_steps": 181800, "loss": 0.0275, "lr": 2.588352091821749e-05, "epoch": 10.797579757975798, "percentage": 53.99, "elapsed_time": "3:51:59", "remaining_time": "3:17:43", "throughput": 1488.14, "total_tokens": 20714688} {"current_steps": 98155, "total_steps": 181800, "loss": 0.0786, "lr": 2.588112234570168e-05, "epoch": 10.798129812981298, "percentage": 53.99, "elapsed_time": "3:52:00", "remaining_time": "3:17:42", "throughput": 1488.14, "total_tokens": 20715680} {"current_steps": 98160, "total_steps": 181800, "loss": 0.0045, "lr": 2.5878723765065e-05, "epoch": 10.798679867986799, "percentage": 53.99, "elapsed_time": "3:52:01", "remaining_time": "3:17:41", "throughput": 1488.14, "total_tokens": 20716736} {"current_steps": 98165, "total_steps": 181800, "loss": 0.0045, "lr": 2.5876325176329542e-05, "epoch": 10.7992299229923, "percentage": 54.0, "elapsed_time": "3:52:01", "remaining_time": "3:17:41", "throughput": 1488.15, "total_tokens": 20717824} {"current_steps": 98170, "total_steps": 181800, "loss": 0.153, "lr": 2.587392657951741e-05, "epoch": 10.7997799779978, "percentage": 54.0, "elapsed_time": "3:52:02", "remaining_time": "3:17:40", "throughput": 1488.15, "total_tokens": 20718848} {"current_steps": 98175, "total_steps": 181800, "loss": 0.1106, "lr": 2.5871527974650717e-05, "epoch": 10.8003300330033, "percentage": 54.0, "elapsed_time": "3:52:03", "remaining_time": "3:17:39", "throughput": 1488.15, "total_tokens": 20719936} {"current_steps": 98180, "total_steps": 181800, "loss": 0.0621, "lr": 2.5869129361751572e-05, "epoch": 10.800880088008801, "percentage": 54.0, "elapsed_time": "3:52:03", "remaining_time": "3:17:39", "throughput": 1488.16, "total_tokens": 20721056} {"current_steps": 98185, "total_steps": 181800, "loss": 0.0103, "lr": 2.586673074084207e-05, "epoch": 10.8014301430143, "percentage": 54.01, "elapsed_time": "3:52:04", "remaining_time": "3:17:38", "throughput": 1488.16, "total_tokens": 20722080} {"current_steps": 98190, "total_steps": 181800, "loss": 0.0185, "lr": 2.5864332111944345e-05, "epoch": 10.801980198019802, "percentage": 54.01, "elapsed_time": "3:52:05", "remaining_time": "3:17:37", "throughput": 1488.16, "total_tokens": 20723104} {"current_steps": 98195, "total_steps": 181800, "loss": 0.1216, "lr": 2.5861933475080476e-05, "epoch": 10.802530253025303, "percentage": 54.01, "elapsed_time": "3:52:06", "remaining_time": "3:17:36", "throughput": 1488.16, "total_tokens": 20724192} {"current_steps": 98200, "total_steps": 181800, "loss": 0.0529, "lr": 2.585953483027257e-05, "epoch": 10.803080308030804, "percentage": 54.02, "elapsed_time": "3:52:06", "remaining_time": "3:17:36", "throughput": 1488.17, "total_tokens": 20725280} {"current_steps": 98205, "total_steps": 181800, "loss": 0.0635, "lr": 2.5857136177542756e-05, "epoch": 10.803630363036303, "percentage": 54.02, "elapsed_time": "3:52:07", "remaining_time": "3:17:35", "throughput": 1488.17, "total_tokens": 20726400} {"current_steps": 98210, "total_steps": 181800, "loss": 0.0109, "lr": 2.5854737516913125e-05, "epoch": 10.804180418041804, "percentage": 54.02, "elapsed_time": "3:52:08", "remaining_time": "3:17:34", "throughput": 1488.18, "total_tokens": 20727456} {"current_steps": 98215, "total_steps": 181800, "loss": 0.1249, "lr": 2.5852338848405788e-05, "epoch": 10.804730473047305, "percentage": 54.02, "elapsed_time": "3:52:08", "remaining_time": "3:17:33", "throughput": 1488.18, "total_tokens": 20728576} {"current_steps": 98220, "total_steps": 181800, "loss": 0.0278, "lr": 2.5849940172042858e-05, "epoch": 10.805280528052805, "percentage": 54.03, "elapsed_time": "3:52:09", "remaining_time": "3:17:33", "throughput": 1488.19, "total_tokens": 20729664} {"current_steps": 98225, "total_steps": 181800, "loss": 0.0042, "lr": 2.5847541487846432e-05, "epoch": 10.805830583058306, "percentage": 54.03, "elapsed_time": "3:52:10", "remaining_time": "3:17:32", "throughput": 1488.19, "total_tokens": 20730688} {"current_steps": 98230, "total_steps": 181800, "loss": 0.1016, "lr": 2.5845142795838617e-05, "epoch": 10.806380638063807, "percentage": 54.03, "elapsed_time": "3:52:10", "remaining_time": "3:17:31", "throughput": 1488.19, "total_tokens": 20731776} {"current_steps": 98235, "total_steps": 181800, "loss": 0.0591, "lr": 2.5842744096041545e-05, "epoch": 10.806930693069306, "percentage": 54.03, "elapsed_time": "3:52:11", "remaining_time": "3:17:31", "throughput": 1488.19, "total_tokens": 20732832} {"current_steps": 98240, "total_steps": 181800, "loss": 0.0269, "lr": 2.5840345388477282e-05, "epoch": 10.807480748074807, "percentage": 54.04, "elapsed_time": "3:52:12", "remaining_time": "3:17:30", "throughput": 1488.19, "total_tokens": 20733856} {"current_steps": 98245, "total_steps": 181800, "loss": 0.0183, "lr": 2.5837946673167974e-05, "epoch": 10.808030803080309, "percentage": 54.04, "elapsed_time": "3:52:12", "remaining_time": "3:17:29", "throughput": 1488.19, "total_tokens": 20734848} {"current_steps": 98250, "total_steps": 181800, "loss": 0.0022, "lr": 2.5835547950135714e-05, "epoch": 10.808580858085808, "percentage": 54.04, "elapsed_time": "3:52:13", "remaining_time": "3:17:28", "throughput": 1488.2, "total_tokens": 20735936} {"current_steps": 98255, "total_steps": 181800, "loss": 0.0072, "lr": 2.5833149219402603e-05, "epoch": 10.809130913091309, "percentage": 54.05, "elapsed_time": "3:52:14", "remaining_time": "3:17:28", "throughput": 1488.2, "total_tokens": 20736992} {"current_steps": 98260, "total_steps": 181800, "loss": 0.0875, "lr": 2.5830750480990756e-05, "epoch": 10.80968096809681, "percentage": 54.05, "elapsed_time": "3:52:14", "remaining_time": "3:17:27", "throughput": 1488.2, "total_tokens": 20738080} {"current_steps": 98265, "total_steps": 181800, "loss": 0.003, "lr": 2.5828351734922286e-05, "epoch": 10.810231023102311, "percentage": 54.05, "elapsed_time": "3:52:15", "remaining_time": "3:17:26", "throughput": 1488.21, "total_tokens": 20739168} {"current_steps": 98270, "total_steps": 181800, "loss": 0.0065, "lr": 2.582595298121929e-05, "epoch": 10.81078107810781, "percentage": 54.05, "elapsed_time": "3:52:16", "remaining_time": "3:17:25", "throughput": 1488.21, "total_tokens": 20740224} {"current_steps": 98275, "total_steps": 181800, "loss": 0.0211, "lr": 2.5823554219903877e-05, "epoch": 10.811331133113312, "percentage": 54.06, "elapsed_time": "3:52:17", "remaining_time": "3:17:25", "throughput": 1488.21, "total_tokens": 20741312} {"current_steps": 98280, "total_steps": 181800, "loss": 0.0265, "lr": 2.582115545099817e-05, "epoch": 10.811881188118813, "percentage": 54.06, "elapsed_time": "3:52:17", "remaining_time": "3:17:24", "throughput": 1488.22, "total_tokens": 20742368} {"current_steps": 98285, "total_steps": 181800, "loss": 0.0125, "lr": 2.5818756674524263e-05, "epoch": 10.812431243124312, "percentage": 54.06, "elapsed_time": "3:52:18", "remaining_time": "3:17:23", "throughput": 1488.22, "total_tokens": 20743392} {"current_steps": 98290, "total_steps": 181800, "loss": 0.0091, "lr": 2.5816357890504272e-05, "epoch": 10.812981298129813, "percentage": 54.06, "elapsed_time": "3:52:19", "remaining_time": "3:17:23", "throughput": 1488.22, "total_tokens": 20744512} {"current_steps": 98295, "total_steps": 181800, "loss": 0.0162, "lr": 2.58139590989603e-05, "epoch": 10.813531353135314, "percentage": 54.07, "elapsed_time": "3:52:19", "remaining_time": "3:17:22", "throughput": 1488.23, "total_tokens": 20745600} {"current_steps": 98300, "total_steps": 181800, "loss": 0.0812, "lr": 2.581156029991445e-05, "epoch": 10.814081408140813, "percentage": 54.07, "elapsed_time": "3:52:20", "remaining_time": "3:17:21", "throughput": 1488.23, "total_tokens": 20746688} {"current_steps": 98305, "total_steps": 181800, "loss": 0.0025, "lr": 2.5809161493388845e-05, "epoch": 10.814631463146315, "percentage": 54.07, "elapsed_time": "3:52:21", "remaining_time": "3:17:20", "throughput": 1488.24, "total_tokens": 20747776} {"current_steps": 98310, "total_steps": 181800, "loss": 0.0349, "lr": 2.5806762679405592e-05, "epoch": 10.815181518151816, "percentage": 54.08, "elapsed_time": "3:52:21", "remaining_time": "3:17:20", "throughput": 1488.24, "total_tokens": 20748864} {"current_steps": 98315, "total_steps": 181800, "loss": 0.0285, "lr": 2.5804363857986786e-05, "epoch": 10.815731573157315, "percentage": 54.08, "elapsed_time": "3:52:22", "remaining_time": "3:17:19", "throughput": 1488.24, "total_tokens": 20749888} {"current_steps": 98320, "total_steps": 181800, "loss": 0.0085, "lr": 2.580196502915455e-05, "epoch": 10.816281628162816, "percentage": 54.08, "elapsed_time": "3:52:23", "remaining_time": "3:17:18", "throughput": 1488.25, "total_tokens": 20750976} {"current_steps": 98325, "total_steps": 181800, "loss": 0.014, "lr": 2.5799566192930985e-05, "epoch": 10.816831683168317, "percentage": 54.08, "elapsed_time": "3:52:23", "remaining_time": "3:17:17", "throughput": 1488.25, "total_tokens": 20752064} {"current_steps": 98330, "total_steps": 181800, "loss": 0.1587, "lr": 2.5797167349338204e-05, "epoch": 10.817381738173818, "percentage": 54.09, "elapsed_time": "3:52:24", "remaining_time": "3:17:17", "throughput": 1488.25, "total_tokens": 20753152} {"current_steps": 98335, "total_steps": 181800, "loss": 0.0605, "lr": 2.5794768498398308e-05, "epoch": 10.817931793179318, "percentage": 54.09, "elapsed_time": "3:52:25", "remaining_time": "3:17:16", "throughput": 1488.25, "total_tokens": 20754176} {"current_steps": 98340, "total_steps": 181800, "loss": 0.069, "lr": 2.579236964013342e-05, "epoch": 10.818481848184819, "percentage": 54.09, "elapsed_time": "3:52:25", "remaining_time": "3:17:15", "throughput": 1488.26, "total_tokens": 20755200} {"current_steps": 98345, "total_steps": 181800, "loss": 0.0162, "lr": 2.578997077456563e-05, "epoch": 10.81903190319032, "percentage": 54.1, "elapsed_time": "3:52:26", "remaining_time": "3:17:15", "throughput": 1488.26, "total_tokens": 20756288} {"current_steps": 98350, "total_steps": 181800, "loss": 0.0863, "lr": 2.5787571901717067e-05, "epoch": 10.819581958195819, "percentage": 54.1, "elapsed_time": "3:52:27", "remaining_time": "3:17:14", "throughput": 1488.26, "total_tokens": 20757344} {"current_steps": 98355, "total_steps": 181800, "loss": 0.0034, "lr": 2.578517302160983e-05, "epoch": 10.82013201320132, "percentage": 54.1, "elapsed_time": "3:52:28", "remaining_time": "3:17:13", "throughput": 1488.27, "total_tokens": 20758432} {"current_steps": 98360, "total_steps": 181800, "loss": 0.0885, "lr": 2.578277413426603e-05, "epoch": 10.820682068206821, "percentage": 54.1, "elapsed_time": "3:52:28", "remaining_time": "3:17:12", "throughput": 1488.27, "total_tokens": 20759488} {"current_steps": 98365, "total_steps": 181800, "loss": 0.0017, "lr": 2.5780375239707776e-05, "epoch": 10.82123212321232, "percentage": 54.11, "elapsed_time": "3:52:29", "remaining_time": "3:17:12", "throughput": 1488.27, "total_tokens": 20760576} {"current_steps": 98370, "total_steps": 181800, "loss": 0.0458, "lr": 2.577797633795718e-05, "epoch": 10.821782178217822, "percentage": 54.11, "elapsed_time": "3:52:30", "remaining_time": "3:17:11", "throughput": 1488.28, "total_tokens": 20761632} {"current_steps": 98375, "total_steps": 181800, "loss": 0.0141, "lr": 2.5775577429036345e-05, "epoch": 10.822332233223323, "percentage": 54.11, "elapsed_time": "3:52:30", "remaining_time": "3:17:10", "throughput": 1488.28, "total_tokens": 20762688} {"current_steps": 98380, "total_steps": 181800, "loss": 0.0251, "lr": 2.5773178512967394e-05, "epoch": 10.822882288228822, "percentage": 54.11, "elapsed_time": "3:52:31", "remaining_time": "3:17:09", "throughput": 1488.27, "total_tokens": 20763648} {"current_steps": 98385, "total_steps": 181800, "loss": 0.03, "lr": 2.577077958977242e-05, "epoch": 10.823432343234323, "percentage": 54.12, "elapsed_time": "3:52:32", "remaining_time": "3:17:09", "throughput": 1488.28, "total_tokens": 20764736} {"current_steps": 98390, "total_steps": 181800, "loss": 0.0247, "lr": 2.576838065947354e-05, "epoch": 10.823982398239824, "percentage": 54.12, "elapsed_time": "3:52:32", "remaining_time": "3:17:08", "throughput": 1488.27, "total_tokens": 20765728} {"current_steps": 98395, "total_steps": 181800, "loss": 0.033, "lr": 2.576598172209287e-05, "epoch": 10.824532453245325, "percentage": 54.12, "elapsed_time": "3:52:33", "remaining_time": "3:17:07", "throughput": 1488.27, "total_tokens": 20766688} {"current_steps": 98400, "total_steps": 181800, "loss": 0.0401, "lr": 2.5763582777652505e-05, "epoch": 10.825082508250825, "percentage": 54.13, "elapsed_time": "3:52:34", "remaining_time": "3:17:07", "throughput": 1488.27, "total_tokens": 20767776} {"current_steps": 98405, "total_steps": 181800, "loss": 0.1067, "lr": 2.5761183826174575e-05, "epoch": 10.825632563256326, "percentage": 54.13, "elapsed_time": "3:52:34", "remaining_time": "3:17:06", "throughput": 1488.28, "total_tokens": 20768832} {"current_steps": 98410, "total_steps": 181800, "loss": 0.0319, "lr": 2.5758784867681175e-05, "epoch": 10.826182618261827, "percentage": 54.13, "elapsed_time": "3:52:35", "remaining_time": "3:17:05", "throughput": 1488.28, "total_tokens": 20769888} {"current_steps": 98415, "total_steps": 181800, "loss": 0.0055, "lr": 2.5756385902194408e-05, "epoch": 10.826732673267326, "percentage": 54.13, "elapsed_time": "3:52:36", "remaining_time": "3:17:04", "throughput": 1488.28, "total_tokens": 20770944} {"current_steps": 98420, "total_steps": 181800, "loss": 0.0088, "lr": 2.5753986929736407e-05, "epoch": 10.827282728272827, "percentage": 54.14, "elapsed_time": "3:52:37", "remaining_time": "3:17:04", "throughput": 1488.29, "total_tokens": 20772032} {"current_steps": 98425, "total_steps": 181800, "loss": 0.0201, "lr": 2.575158795032927e-05, "epoch": 10.827832783278328, "percentage": 54.14, "elapsed_time": "3:52:37", "remaining_time": "3:17:03", "throughput": 1488.29, "total_tokens": 20773088} {"current_steps": 98430, "total_steps": 181800, "loss": 0.0768, "lr": 2.5749188963995103e-05, "epoch": 10.828382838283828, "percentage": 54.14, "elapsed_time": "3:52:38", "remaining_time": "3:17:02", "throughput": 1488.29, "total_tokens": 20774176} {"current_steps": 98435, "total_steps": 181800, "loss": 0.0039, "lr": 2.5746789970756023e-05, "epoch": 10.828932893289329, "percentage": 54.14, "elapsed_time": "3:52:39", "remaining_time": "3:17:02", "throughput": 1488.29, "total_tokens": 20775232} {"current_steps": 98440, "total_steps": 181800, "loss": 0.0051, "lr": 2.5744390970634136e-05, "epoch": 10.82948294829483, "percentage": 54.15, "elapsed_time": "3:52:39", "remaining_time": "3:17:01", "throughput": 1488.29, "total_tokens": 20776256} {"current_steps": 98445, "total_steps": 181800, "loss": 0.0678, "lr": 2.5741991963651553e-05, "epoch": 10.83003300330033, "percentage": 54.15, "elapsed_time": "3:52:40", "remaining_time": "3:17:00", "throughput": 1488.3, "total_tokens": 20777344} {"current_steps": 98450, "total_steps": 181800, "loss": 0.052, "lr": 2.57395929498304e-05, "epoch": 10.83058305830583, "percentage": 54.15, "elapsed_time": "3:52:41", "remaining_time": "3:16:59", "throughput": 1488.3, "total_tokens": 20778432} {"current_steps": 98455, "total_steps": 181800, "loss": 0.0408, "lr": 2.573719392919276e-05, "epoch": 10.831133113311331, "percentage": 54.16, "elapsed_time": "3:52:41", "remaining_time": "3:16:59", "throughput": 1488.3, "total_tokens": 20779456} {"current_steps": 98460, "total_steps": 181800, "loss": 0.0406, "lr": 2.5734794901760756e-05, "epoch": 10.831683168316832, "percentage": 54.16, "elapsed_time": "3:52:42", "remaining_time": "3:16:58", "throughput": 1488.31, "total_tokens": 20780512} {"current_steps": 98465, "total_steps": 181800, "loss": 0.0032, "lr": 2.573239586755651e-05, "epoch": 10.832233223322332, "percentage": 54.16, "elapsed_time": "3:52:43", "remaining_time": "3:16:57", "throughput": 1488.31, "total_tokens": 20781568} {"current_steps": 98470, "total_steps": 181800, "loss": 0.0064, "lr": 2.5729996826602114e-05, "epoch": 10.832783278327833, "percentage": 54.16, "elapsed_time": "3:52:43", "remaining_time": "3:16:56", "throughput": 1488.31, "total_tokens": 20782560} {"current_steps": 98475, "total_steps": 181800, "loss": 0.0248, "lr": 2.5727597778919693e-05, "epoch": 10.833333333333334, "percentage": 54.17, "elapsed_time": "3:52:44", "remaining_time": "3:16:56", "throughput": 1488.31, "total_tokens": 20783648} {"current_steps": 98480, "total_steps": 181800, "loss": 0.0099, "lr": 2.5725198724531346e-05, "epoch": 10.833883388338833, "percentage": 54.17, "elapsed_time": "3:52:45", "remaining_time": "3:16:55", "throughput": 1488.31, "total_tokens": 20784736} {"current_steps": 98485, "total_steps": 181800, "loss": 0.005, "lr": 2.5722799663459197e-05, "epoch": 10.834433443344334, "percentage": 54.17, "elapsed_time": "3:52:45", "remaining_time": "3:16:54", "throughput": 1488.31, "total_tokens": 20785728} {"current_steps": 98490, "total_steps": 181800, "loss": 0.0515, "lr": 2.5720400595725348e-05, "epoch": 10.834983498349835, "percentage": 54.17, "elapsed_time": "3:52:46", "remaining_time": "3:16:54", "throughput": 1488.32, "total_tokens": 20786880} {"current_steps": 98495, "total_steps": 181800, "loss": 0.015, "lr": 2.571800152135191e-05, "epoch": 10.835533553355335, "percentage": 54.18, "elapsed_time": "3:52:47", "remaining_time": "3:16:53", "throughput": 1488.32, "total_tokens": 20787936} {"current_steps": 98500, "total_steps": 181800, "loss": 0.0814, "lr": 2.5715602440361e-05, "epoch": 10.836083608360836, "percentage": 54.18, "elapsed_time": "3:52:48", "remaining_time": "3:16:52", "throughput": 1488.32, "total_tokens": 20788992} {"current_steps": 98505, "total_steps": 181800, "loss": 0.0835, "lr": 2.5713203352774723e-05, "epoch": 10.836633663366337, "percentage": 54.18, "elapsed_time": "3:52:48", "remaining_time": "3:16:51", "throughput": 1488.33, "total_tokens": 20790048} {"current_steps": 98510, "total_steps": 181800, "loss": 0.0173, "lr": 2.5710804258615197e-05, "epoch": 10.837183718371836, "percentage": 54.19, "elapsed_time": "3:52:49", "remaining_time": "3:16:51", "throughput": 1488.33, "total_tokens": 20791072} {"current_steps": 98515, "total_steps": 181800, "loss": 0.0056, "lr": 2.5708405157904525e-05, "epoch": 10.837733773377337, "percentage": 54.19, "elapsed_time": "3:52:50", "remaining_time": "3:16:50", "throughput": 1488.33, "total_tokens": 20792128} {"current_steps": 98520, "total_steps": 181800, "loss": 0.0118, "lr": 2.5706006050664826e-05, "epoch": 10.838283828382838, "percentage": 54.19, "elapsed_time": "3:52:50", "remaining_time": "3:16:49", "throughput": 1488.33, "total_tokens": 20793216} {"current_steps": 98525, "total_steps": 181800, "loss": 0.0431, "lr": 2.5703606936918205e-05, "epoch": 10.83883388338834, "percentage": 54.19, "elapsed_time": "3:52:51", "remaining_time": "3:16:48", "throughput": 1488.34, "total_tokens": 20794272} {"current_steps": 98530, "total_steps": 181800, "loss": 0.0191, "lr": 2.5701207816686772e-05, "epoch": 10.839383938393839, "percentage": 54.2, "elapsed_time": "3:52:52", "remaining_time": "3:16:48", "throughput": 1488.34, "total_tokens": 20795360} {"current_steps": 98535, "total_steps": 181800, "loss": 0.0019, "lr": 2.5698808689992653e-05, "epoch": 10.83993399339934, "percentage": 54.2, "elapsed_time": "3:52:52", "remaining_time": "3:16:47", "throughput": 1488.34, "total_tokens": 20796448} {"current_steps": 98540, "total_steps": 181800, "loss": 0.004, "lr": 2.5696409556857947e-05, "epoch": 10.840484048404841, "percentage": 54.2, "elapsed_time": "3:52:53", "remaining_time": "3:16:46", "throughput": 1488.35, "total_tokens": 20797536} {"current_steps": 98545, "total_steps": 181800, "loss": 0.005, "lr": 2.5694010417304763e-05, "epoch": 10.84103410341034, "percentage": 54.21, "elapsed_time": "3:52:54", "remaining_time": "3:16:46", "throughput": 1488.35, "total_tokens": 20798592} {"current_steps": 98550, "total_steps": 181800, "loss": 0.0042, "lr": 2.5691611271355228e-05, "epoch": 10.841584158415841, "percentage": 54.21, "elapsed_time": "3:52:54", "remaining_time": "3:16:45", "throughput": 1488.35, "total_tokens": 20799648} {"current_steps": 98555, "total_steps": 181800, "loss": 0.0426, "lr": 2.5689212119031437e-05, "epoch": 10.842134213421343, "percentage": 54.21, "elapsed_time": "3:52:55", "remaining_time": "3:16:44", "throughput": 1488.36, "total_tokens": 20800736} {"current_steps": 98560, "total_steps": 181800, "loss": 0.0839, "lr": 2.5686812960355506e-05, "epoch": 10.842684268426842, "percentage": 54.21, "elapsed_time": "3:52:56", "remaining_time": "3:16:43", "throughput": 1488.36, "total_tokens": 20801792} {"current_steps": 98565, "total_steps": 181800, "loss": 0.0416, "lr": 2.5684413795349548e-05, "epoch": 10.843234323432343, "percentage": 54.22, "elapsed_time": "3:52:57", "remaining_time": "3:16:43", "throughput": 1488.36, "total_tokens": 20802880} {"current_steps": 98570, "total_steps": 181800, "loss": 0.0751, "lr": 2.568201462403569e-05, "epoch": 10.843784378437844, "percentage": 54.22, "elapsed_time": "3:52:57", "remaining_time": "3:16:42", "throughput": 1488.37, "total_tokens": 20803936} {"current_steps": 98575, "total_steps": 181800, "loss": 0.0887, "lr": 2.5679615446436018e-05, "epoch": 10.844334433443345, "percentage": 54.22, "elapsed_time": "3:52:58", "remaining_time": "3:16:41", "throughput": 1488.36, "total_tokens": 20804928} {"current_steps": 98580, "total_steps": 181800, "loss": 0.0321, "lr": 2.5677216262572657e-05, "epoch": 10.844884488448844, "percentage": 54.22, "elapsed_time": "3:52:59", "remaining_time": "3:16:40", "throughput": 1488.37, "total_tokens": 20806016} {"current_steps": 98585, "total_steps": 181800, "loss": 0.0139, "lr": 2.567481707246772e-05, "epoch": 10.845434543454346, "percentage": 54.23, "elapsed_time": "3:52:59", "remaining_time": "3:16:40", "throughput": 1488.37, "total_tokens": 20807040} {"current_steps": 98590, "total_steps": 181800, "loss": 0.0749, "lr": 2.5672417876143316e-05, "epoch": 10.845984598459847, "percentage": 54.23, "elapsed_time": "3:53:00", "remaining_time": "3:16:39", "throughput": 1488.37, "total_tokens": 20808064} {"current_steps": 98595, "total_steps": 181800, "loss": 0.0177, "lr": 2.567001867362157e-05, "epoch": 10.846534653465346, "percentage": 54.23, "elapsed_time": "3:53:01", "remaining_time": "3:16:38", "throughput": 1488.37, "total_tokens": 20809152} {"current_steps": 98600, "total_steps": 181800, "loss": 0.0381, "lr": 2.566761946492458e-05, "epoch": 10.847084708470847, "percentage": 54.24, "elapsed_time": "3:53:01", "remaining_time": "3:16:38", "throughput": 1488.37, "total_tokens": 20810208} {"current_steps": 98605, "total_steps": 181800, "loss": 0.0949, "lr": 2.566522025007445e-05, "epoch": 10.847634763476348, "percentage": 54.24, "elapsed_time": "3:53:02", "remaining_time": "3:16:37", "throughput": 1488.37, "total_tokens": 20811264} {"current_steps": 98610, "total_steps": 181800, "loss": 0.0127, "lr": 2.5662821029093313e-05, "epoch": 10.848184818481847, "percentage": 54.24, "elapsed_time": "3:53:03", "remaining_time": "3:16:36", "throughput": 1488.37, "total_tokens": 20812288} {"current_steps": 98615, "total_steps": 181800, "loss": 0.0044, "lr": 2.5660421802003276e-05, "epoch": 10.848734873487349, "percentage": 54.24, "elapsed_time": "3:53:03", "remaining_time": "3:16:35", "throughput": 1488.38, "total_tokens": 20813344} {"current_steps": 98620, "total_steps": 181800, "loss": 0.0028, "lr": 2.565802256882644e-05, "epoch": 10.84928492849285, "percentage": 54.25, "elapsed_time": "3:53:04", "remaining_time": "3:16:35", "throughput": 1488.37, "total_tokens": 20814336} {"current_steps": 98625, "total_steps": 181800, "loss": 0.0819, "lr": 2.5655623329584933e-05, "epoch": 10.84983498349835, "percentage": 54.25, "elapsed_time": "3:53:05", "remaining_time": "3:16:34", "throughput": 1488.37, "total_tokens": 20815328} {"current_steps": 98630, "total_steps": 181800, "loss": 0.1029, "lr": 2.565322408430086e-05, "epoch": 10.85038503850385, "percentage": 54.25, "elapsed_time": "3:53:05", "remaining_time": "3:16:33", "throughput": 1488.38, "total_tokens": 20816416} {"current_steps": 98635, "total_steps": 181800, "loss": 0.0139, "lr": 2.5650824832996325e-05, "epoch": 10.850935093509351, "percentage": 54.25, "elapsed_time": "3:53:06", "remaining_time": "3:16:32", "throughput": 1488.38, "total_tokens": 20817504} {"current_steps": 98640, "total_steps": 181800, "loss": 0.0073, "lr": 2.564842557569346e-05, "epoch": 10.851485148514852, "percentage": 54.26, "elapsed_time": "3:53:07", "remaining_time": "3:16:32", "throughput": 1488.38, "total_tokens": 20818496} {"current_steps": 98645, "total_steps": 181800, "loss": 0.0036, "lr": 2.5646026312414363e-05, "epoch": 10.852035203520352, "percentage": 54.26, "elapsed_time": "3:53:08", "remaining_time": "3:16:31", "throughput": 1488.38, "total_tokens": 20819488} {"current_steps": 98650, "total_steps": 181800, "loss": 0.0255, "lr": 2.5643627043181147e-05, "epoch": 10.852585258525853, "percentage": 54.26, "elapsed_time": "3:53:08", "remaining_time": "3:16:30", "throughput": 1488.38, "total_tokens": 20820544} {"current_steps": 98655, "total_steps": 181800, "loss": 0.083, "lr": 2.5641227768015935e-05, "epoch": 10.853135313531354, "percentage": 54.27, "elapsed_time": "3:53:09", "remaining_time": "3:16:30", "throughput": 1488.38, "total_tokens": 20821632} {"current_steps": 98660, "total_steps": 181800, "loss": 0.0544, "lr": 2.5638828486940836e-05, "epoch": 10.853685368536853, "percentage": 54.27, "elapsed_time": "3:53:10", "remaining_time": "3:16:29", "throughput": 1488.38, "total_tokens": 20822688} {"current_steps": 98665, "total_steps": 181800, "loss": 0.0259, "lr": 2.5636429199977957e-05, "epoch": 10.854235423542354, "percentage": 54.27, "elapsed_time": "3:53:10", "remaining_time": "3:16:28", "throughput": 1488.39, "total_tokens": 20823776} {"current_steps": 98670, "total_steps": 181800, "loss": 0.0492, "lr": 2.563402990714942e-05, "epoch": 10.854785478547855, "percentage": 54.27, "elapsed_time": "3:53:11", "remaining_time": "3:16:27", "throughput": 1488.4, "total_tokens": 20824896} {"current_steps": 98675, "total_steps": 181800, "loss": 0.0291, "lr": 2.563163060847733e-05, "epoch": 10.855335533553355, "percentage": 54.28, "elapsed_time": "3:53:12", "remaining_time": "3:16:27", "throughput": 1488.4, "total_tokens": 20825984} {"current_steps": 98680, "total_steps": 181800, "loss": 0.0514, "lr": 2.5629231303983804e-05, "epoch": 10.855885588558856, "percentage": 54.28, "elapsed_time": "3:53:12", "remaining_time": "3:16:26", "throughput": 1488.4, "total_tokens": 20827072} {"current_steps": 98685, "total_steps": 181800, "loss": 0.0024, "lr": 2.5626831993690954e-05, "epoch": 10.856435643564357, "percentage": 54.28, "elapsed_time": "3:53:13", "remaining_time": "3:16:25", "throughput": 1488.4, "total_tokens": 20828064} {"current_steps": 98690, "total_steps": 181800, "loss": 0.0469, "lr": 2.5624432677620895e-05, "epoch": 10.856985698569858, "percentage": 54.28, "elapsed_time": "3:53:14", "remaining_time": "3:16:25", "throughput": 1488.41, "total_tokens": 20829152} {"current_steps": 98695, "total_steps": 181800, "loss": 0.0076, "lr": 2.5622033355795742e-05, "epoch": 10.857535753575357, "percentage": 54.29, "elapsed_time": "3:53:14", "remaining_time": "3:16:24", "throughput": 1488.42, "total_tokens": 20830304} {"current_steps": 98700, "total_steps": 181800, "loss": 0.0079, "lr": 2.5619634028237606e-05, "epoch": 10.858085808580858, "percentage": 54.29, "elapsed_time": "3:53:15", "remaining_time": "3:16:23", "throughput": 1488.41, "total_tokens": 20831296} {"current_steps": 98705, "total_steps": 181800, "loss": 0.0469, "lr": 2.56172346949686e-05, "epoch": 10.85863586358636, "percentage": 54.29, "elapsed_time": "3:53:16", "remaining_time": "3:16:22", "throughput": 1488.41, "total_tokens": 20832320} {"current_steps": 98710, "total_steps": 181800, "loss": 0.0117, "lr": 2.5614835356010834e-05, "epoch": 10.859185918591859, "percentage": 54.3, "elapsed_time": "3:53:17", "remaining_time": "3:16:22", "throughput": 1488.42, "total_tokens": 20833408} {"current_steps": 98715, "total_steps": 181800, "loss": 0.044, "lr": 2.561243601138643e-05, "epoch": 10.85973597359736, "percentage": 54.3, "elapsed_time": "3:53:17", "remaining_time": "3:16:21", "throughput": 1488.42, "total_tokens": 20834496} {"current_steps": 98720, "total_steps": 181800, "loss": 0.0069, "lr": 2.561003666111749e-05, "epoch": 10.86028602860286, "percentage": 54.3, "elapsed_time": "3:53:18", "remaining_time": "3:16:20", "throughput": 1488.42, "total_tokens": 20835584} {"current_steps": 98725, "total_steps": 181800, "loss": 0.0317, "lr": 2.5607637305226144e-05, "epoch": 10.86083608360836, "percentage": 54.3, "elapsed_time": "3:53:19", "remaining_time": "3:16:19", "throughput": 1488.43, "total_tokens": 20836672} {"current_steps": 98730, "total_steps": 181800, "loss": 0.0085, "lr": 2.5605237943734495e-05, "epoch": 10.861386138613861, "percentage": 54.31, "elapsed_time": "3:53:19", "remaining_time": "3:16:19", "throughput": 1488.43, "total_tokens": 20837696} {"current_steps": 98735, "total_steps": 181800, "loss": 0.0021, "lr": 2.5602838576664658e-05, "epoch": 10.861936193619362, "percentage": 54.31, "elapsed_time": "3:53:20", "remaining_time": "3:16:18", "throughput": 1488.43, "total_tokens": 20838752} {"current_steps": 98740, "total_steps": 181800, "loss": 0.0073, "lr": 2.5600439204038744e-05, "epoch": 10.862486248624862, "percentage": 54.31, "elapsed_time": "3:53:21", "remaining_time": "3:16:17", "throughput": 1488.43, "total_tokens": 20839744} {"current_steps": 98745, "total_steps": 181800, "loss": 0.0658, "lr": 2.5598039825878873e-05, "epoch": 10.863036303630363, "percentage": 54.32, "elapsed_time": "3:53:21", "remaining_time": "3:16:17", "throughput": 1488.43, "total_tokens": 20840768} {"current_steps": 98750, "total_steps": 181800, "loss": 0.0491, "lr": 2.5595640442207152e-05, "epoch": 10.863586358635864, "percentage": 54.32, "elapsed_time": "3:53:22", "remaining_time": "3:16:16", "throughput": 1488.43, "total_tokens": 20841856} {"current_steps": 98755, "total_steps": 181800, "loss": 0.003, "lr": 2.5593241053045702e-05, "epoch": 10.864136413641365, "percentage": 54.32, "elapsed_time": "3:53:23", "remaining_time": "3:16:15", "throughput": 1488.44, "total_tokens": 20842912} {"current_steps": 98760, "total_steps": 181800, "loss": 0.0491, "lr": 2.5590841658416638e-05, "epoch": 10.864686468646864, "percentage": 54.32, "elapsed_time": "3:53:23", "remaining_time": "3:16:14", "throughput": 1488.44, "total_tokens": 20843968} {"current_steps": 98765, "total_steps": 181800, "loss": 0.0536, "lr": 2.558844225834206e-05, "epoch": 10.865236523652365, "percentage": 54.33, "elapsed_time": "3:53:24", "remaining_time": "3:16:14", "throughput": 1488.44, "total_tokens": 20845024} {"current_steps": 98770, "total_steps": 181800, "loss": 0.0123, "lr": 2.55860428528441e-05, "epoch": 10.865786578657866, "percentage": 54.33, "elapsed_time": "3:53:25", "remaining_time": "3:16:13", "throughput": 1488.44, "total_tokens": 20846080} {"current_steps": 98775, "total_steps": 181800, "loss": 0.006, "lr": 2.558364344194486e-05, "epoch": 10.866336633663366, "percentage": 54.33, "elapsed_time": "3:53:25", "remaining_time": "3:16:12", "throughput": 1488.45, "total_tokens": 20847168} {"current_steps": 98780, "total_steps": 181800, "loss": 0.0395, "lr": 2.5581244025666456e-05, "epoch": 10.866886688668867, "percentage": 54.33, "elapsed_time": "3:53:26", "remaining_time": "3:16:11", "throughput": 1488.45, "total_tokens": 20848224} {"current_steps": 98785, "total_steps": 181800, "loss": 0.0298, "lr": 2.5578844604031016e-05, "epoch": 10.867436743674368, "percentage": 54.34, "elapsed_time": "3:53:27", "remaining_time": "3:16:11", "throughput": 1488.45, "total_tokens": 20849248} {"current_steps": 98790, "total_steps": 181800, "loss": 0.0356, "lr": 2.5576445177060638e-05, "epoch": 10.867986798679867, "percentage": 54.34, "elapsed_time": "3:53:28", "remaining_time": "3:16:10", "throughput": 1488.45, "total_tokens": 20850368} {"current_steps": 98795, "total_steps": 181800, "loss": 0.0687, "lr": 2.557404574477743e-05, "epoch": 10.868536853685368, "percentage": 54.34, "elapsed_time": "3:53:28", "remaining_time": "3:16:09", "throughput": 1488.46, "total_tokens": 20851424} {"current_steps": 98800, "total_steps": 181800, "loss": 0.0015, "lr": 2.557164630720353e-05, "epoch": 10.86908690869087, "percentage": 54.35, "elapsed_time": "3:53:29", "remaining_time": "3:16:09", "throughput": 1488.46, "total_tokens": 20852480} {"current_steps": 98805, "total_steps": 181800, "loss": 0.0175, "lr": 2.5569246864361034e-05, "epoch": 10.869636963696369, "percentage": 54.35, "elapsed_time": "3:53:30", "remaining_time": "3:16:08", "throughput": 1488.46, "total_tokens": 20853504} {"current_steps": 98810, "total_steps": 181800, "loss": 0.003, "lr": 2.556684741627207e-05, "epoch": 10.87018701870187, "percentage": 54.35, "elapsed_time": "3:53:30", "remaining_time": "3:16:07", "throughput": 1488.46, "total_tokens": 20854528} {"current_steps": 98815, "total_steps": 181800, "loss": 0.0015, "lr": 2.5564447962958744e-05, "epoch": 10.870737073707371, "percentage": 54.35, "elapsed_time": "3:53:31", "remaining_time": "3:16:06", "throughput": 1488.46, "total_tokens": 20855552} {"current_steps": 98820, "total_steps": 181800, "loss": 0.0223, "lr": 2.5562048504443165e-05, "epoch": 10.871287128712872, "percentage": 54.36, "elapsed_time": "3:53:32", "remaining_time": "3:16:06", "throughput": 1488.46, "total_tokens": 20856672} {"current_steps": 98825, "total_steps": 181800, "loss": 0.0038, "lr": 2.5559649040747458e-05, "epoch": 10.871837183718371, "percentage": 54.36, "elapsed_time": "3:53:32", "remaining_time": "3:16:05", "throughput": 1488.47, "total_tokens": 20857728} {"current_steps": 98830, "total_steps": 181800, "loss": 0.0629, "lr": 2.5557249571893736e-05, "epoch": 10.872387238723872, "percentage": 54.36, "elapsed_time": "3:53:33", "remaining_time": "3:16:04", "throughput": 1488.47, "total_tokens": 20858848} {"current_steps": 98835, "total_steps": 181800, "loss": 0.0132, "lr": 2.5554850097904108e-05, "epoch": 10.872937293729374, "percentage": 54.36, "elapsed_time": "3:53:34", "remaining_time": "3:16:03", "throughput": 1488.47, "total_tokens": 20859808} {"current_steps": 98840, "total_steps": 181800, "loss": 0.0077, "lr": 2.55524506188007e-05, "epoch": 10.873487348734873, "percentage": 54.37, "elapsed_time": "3:53:34", "remaining_time": "3:16:03", "throughput": 1488.47, "total_tokens": 20860864} {"current_steps": 98845, "total_steps": 181800, "loss": 0.002, "lr": 2.5550051134605618e-05, "epoch": 10.874037403740374, "percentage": 54.37, "elapsed_time": "3:53:35", "remaining_time": "3:16:02", "throughput": 1488.47, "total_tokens": 20861920} {"current_steps": 98850, "total_steps": 181800, "loss": 0.0804, "lr": 2.5547651645340974e-05, "epoch": 10.874587458745875, "percentage": 54.37, "elapsed_time": "3:53:36", "remaining_time": "3:16:01", "throughput": 1488.47, "total_tokens": 20862976} {"current_steps": 98855, "total_steps": 181800, "loss": 0.0451, "lr": 2.554525215102889e-05, "epoch": 10.875137513751374, "percentage": 54.38, "elapsed_time": "3:53:37", "remaining_time": "3:16:01", "throughput": 1488.47, "total_tokens": 20864000} {"current_steps": 98860, "total_steps": 181800, "loss": 0.029, "lr": 2.5542852651691484e-05, "epoch": 10.875687568756875, "percentage": 54.38, "elapsed_time": "3:53:37", "remaining_time": "3:16:00", "throughput": 1488.47, "total_tokens": 20865024} {"current_steps": 98865, "total_steps": 181800, "loss": 0.0015, "lr": 2.554045314735085e-05, "epoch": 10.876237623762377, "percentage": 54.38, "elapsed_time": "3:53:38", "remaining_time": "3:15:59", "throughput": 1488.47, "total_tokens": 20866016} {"current_steps": 98870, "total_steps": 181800, "loss": 0.0167, "lr": 2.5538053638029136e-05, "epoch": 10.876787678767876, "percentage": 54.38, "elapsed_time": "3:53:39", "remaining_time": "3:15:58", "throughput": 1488.47, "total_tokens": 20867008} {"current_steps": 98875, "total_steps": 181800, "loss": 0.0058, "lr": 2.553565412374843e-05, "epoch": 10.877337733773377, "percentage": 54.39, "elapsed_time": "3:53:39", "remaining_time": "3:15:58", "throughput": 1488.47, "total_tokens": 20868064} {"current_steps": 98880, "total_steps": 181800, "loss": 0.0152, "lr": 2.553325460453086e-05, "epoch": 10.877887788778878, "percentage": 54.39, "elapsed_time": "3:53:40", "remaining_time": "3:15:57", "throughput": 1488.48, "total_tokens": 20869216} {"current_steps": 98885, "total_steps": 181800, "loss": 0.0055, "lr": 2.553085508039854e-05, "epoch": 10.87843784378438, "percentage": 54.39, "elapsed_time": "3:53:41", "remaining_time": "3:15:56", "throughput": 1488.49, "total_tokens": 20870336} {"current_steps": 98890, "total_steps": 181800, "loss": 0.0491, "lr": 2.552845555137358e-05, "epoch": 10.878987898789878, "percentage": 54.39, "elapsed_time": "3:53:41", "remaining_time": "3:15:56", "throughput": 1488.49, "total_tokens": 20871360} {"current_steps": 98895, "total_steps": 181800, "loss": 0.0019, "lr": 2.55260560174781e-05, "epoch": 10.87953795379538, "percentage": 54.4, "elapsed_time": "3:53:42", "remaining_time": "3:15:55", "throughput": 1488.49, "total_tokens": 20872384} {"current_steps": 98900, "total_steps": 181800, "loss": 0.0149, "lr": 2.5523656478734213e-05, "epoch": 10.88008800880088, "percentage": 54.4, "elapsed_time": "3:53:43", "remaining_time": "3:15:54", "throughput": 1488.49, "total_tokens": 20873408} {"current_steps": 98905, "total_steps": 181800, "loss": 0.008, "lr": 2.5521256935164044e-05, "epoch": 10.88063806380638, "percentage": 54.4, "elapsed_time": "3:53:43", "remaining_time": "3:15:53", "throughput": 1488.49, "total_tokens": 20874464} {"current_steps": 98910, "total_steps": 181800, "loss": 0.0216, "lr": 2.5518857386789684e-05, "epoch": 10.881188118811881, "percentage": 54.41, "elapsed_time": "3:53:44", "remaining_time": "3:15:53", "throughput": 1488.49, "total_tokens": 20875456} {"current_steps": 98915, "total_steps": 181800, "loss": 0.0598, "lr": 2.5516457833633277e-05, "epoch": 10.881738173817382, "percentage": 54.41, "elapsed_time": "3:53:45", "remaining_time": "3:15:52", "throughput": 1488.49, "total_tokens": 20876512} {"current_steps": 98920, "total_steps": 181800, "loss": 0.0397, "lr": 2.5514058275716924e-05, "epoch": 10.882288228822881, "percentage": 54.41, "elapsed_time": "3:53:45", "remaining_time": "3:15:51", "throughput": 1488.49, "total_tokens": 20877568} {"current_steps": 98925, "total_steps": 181800, "loss": 0.0162, "lr": 2.551165871306274e-05, "epoch": 10.882838283828383, "percentage": 54.41, "elapsed_time": "3:53:46", "remaining_time": "3:15:50", "throughput": 1488.49, "total_tokens": 20878624} {"current_steps": 98930, "total_steps": 181800, "loss": 0.0361, "lr": 2.5509259145692843e-05, "epoch": 10.883388338833884, "percentage": 54.42, "elapsed_time": "3:53:47", "remaining_time": "3:15:50", "throughput": 1488.49, "total_tokens": 20879648} {"current_steps": 98935, "total_steps": 181800, "loss": 0.001, "lr": 2.5506859573629356e-05, "epoch": 10.883938393839383, "percentage": 54.42, "elapsed_time": "3:53:48", "remaining_time": "3:15:49", "throughput": 1488.5, "total_tokens": 20880704} {"current_steps": 98940, "total_steps": 181800, "loss": 0.0875, "lr": 2.5504459996894374e-05, "epoch": 10.884488448844884, "percentage": 54.42, "elapsed_time": "3:53:48", "remaining_time": "3:15:48", "throughput": 1488.49, "total_tokens": 20881696} {"current_steps": 98945, "total_steps": 181800, "loss": 0.0056, "lr": 2.5502060415510032e-05, "epoch": 10.885038503850385, "percentage": 54.43, "elapsed_time": "3:53:49", "remaining_time": "3:15:48", "throughput": 1488.49, "total_tokens": 20882720} {"current_steps": 98950, "total_steps": 181800, "loss": 0.0822, "lr": 2.549966082949845e-05, "epoch": 10.885588558855886, "percentage": 54.43, "elapsed_time": "3:53:50", "remaining_time": "3:15:47", "throughput": 1488.49, "total_tokens": 20883744} {"current_steps": 98955, "total_steps": 181800, "loss": 0.0543, "lr": 2.549726123888172e-05, "epoch": 10.886138613861386, "percentage": 54.43, "elapsed_time": "3:53:50", "remaining_time": "3:15:46", "throughput": 1488.49, "total_tokens": 20884800} {"current_steps": 98960, "total_steps": 181800, "loss": 0.0345, "lr": 2.549486164368198e-05, "epoch": 10.886688668866887, "percentage": 54.43, "elapsed_time": "3:53:51", "remaining_time": "3:15:45", "throughput": 1488.5, "total_tokens": 20885888} {"current_steps": 98965, "total_steps": 181800, "loss": 0.0053, "lr": 2.5492462043921335e-05, "epoch": 10.887238723872388, "percentage": 54.44, "elapsed_time": "3:53:52", "remaining_time": "3:15:45", "throughput": 1488.5, "total_tokens": 20886944} {"current_steps": 98970, "total_steps": 181800, "loss": 0.0132, "lr": 2.5490062439621898e-05, "epoch": 10.887788778877887, "percentage": 54.44, "elapsed_time": "3:53:52", "remaining_time": "3:15:44", "throughput": 1488.5, "total_tokens": 20887968} {"current_steps": 98975, "total_steps": 181800, "loss": 0.0541, "lr": 2.5487662830805804e-05, "epoch": 10.888338833883388, "percentage": 54.44, "elapsed_time": "3:53:53", "remaining_time": "3:15:43", "throughput": 1488.51, "total_tokens": 20889056} {"current_steps": 98980, "total_steps": 181800, "loss": 0.0259, "lr": 2.5485263217495147e-05, "epoch": 10.88888888888889, "percentage": 54.44, "elapsed_time": "3:53:54", "remaining_time": "3:15:42", "throughput": 1488.5, "total_tokens": 20890048} {"current_steps": 98985, "total_steps": 181800, "loss": 0.0976, "lr": 2.5482863599712047e-05, "epoch": 10.88943894389439, "percentage": 54.45, "elapsed_time": "3:53:54", "remaining_time": "3:15:42", "throughput": 1488.51, "total_tokens": 20891104} {"current_steps": 98990, "total_steps": 181800, "loss": 0.0123, "lr": 2.548046397747863e-05, "epoch": 10.88998899889989, "percentage": 54.45, "elapsed_time": "3:53:55", "remaining_time": "3:15:41", "throughput": 1488.5, "total_tokens": 20892096} {"current_steps": 98995, "total_steps": 181800, "loss": 0.0081, "lr": 2.547806435081701e-05, "epoch": 10.89053905390539, "percentage": 54.45, "elapsed_time": "3:53:56", "remaining_time": "3:15:40", "throughput": 1488.51, "total_tokens": 20893184} {"current_steps": 99000, "total_steps": 181800, "loss": 0.0699, "lr": 2.54756647197493e-05, "epoch": 10.891089108910892, "percentage": 54.46, "elapsed_time": "3:53:57", "remaining_time": "3:15:40", "throughput": 1488.52, "total_tokens": 20894304} {"current_steps": 99005, "total_steps": 181800, "loss": 0.0072, "lr": 2.5473265084297617e-05, "epoch": 10.891639163916391, "percentage": 54.46, "elapsed_time": "3:53:57", "remaining_time": "3:15:39", "throughput": 1488.52, "total_tokens": 20895392} {"current_steps": 99010, "total_steps": 181800, "loss": 0.0058, "lr": 2.547086544448407e-05, "epoch": 10.892189218921892, "percentage": 54.46, "elapsed_time": "3:53:58", "remaining_time": "3:15:38", "throughput": 1488.52, "total_tokens": 20896448} {"current_steps": 99015, "total_steps": 181800, "loss": 0.0772, "lr": 2.5468465800330782e-05, "epoch": 10.892739273927393, "percentage": 54.46, "elapsed_time": "3:53:59", "remaining_time": "3:15:37", "throughput": 1488.52, "total_tokens": 20897504} {"current_steps": 99020, "total_steps": 181800, "loss": 0.0206, "lr": 2.546606615185988e-05, "epoch": 10.893289328932893, "percentage": 54.47, "elapsed_time": "3:53:59", "remaining_time": "3:15:37", "throughput": 1488.53, "total_tokens": 20898560} {"current_steps": 99025, "total_steps": 181800, "loss": 0.0076, "lr": 2.5463666499093465e-05, "epoch": 10.893839383938394, "percentage": 54.47, "elapsed_time": "3:54:00", "remaining_time": "3:15:36", "throughput": 1488.53, "total_tokens": 20899648} {"current_steps": 99030, "total_steps": 181800, "loss": 0.0654, "lr": 2.5461266842053654e-05, "epoch": 10.894389438943895, "percentage": 54.47, "elapsed_time": "3:54:01", "remaining_time": "3:15:35", "throughput": 1488.53, "total_tokens": 20900736} {"current_steps": 99035, "total_steps": 181800, "loss": 0.0017, "lr": 2.5458867180762575e-05, "epoch": 10.894939493949394, "percentage": 54.47, "elapsed_time": "3:54:01", "remaining_time": "3:15:34", "throughput": 1488.54, "total_tokens": 20901792} {"current_steps": 99040, "total_steps": 181800, "loss": 0.001, "lr": 2.545646751524233e-05, "epoch": 10.895489548954895, "percentage": 54.48, "elapsed_time": "3:54:02", "remaining_time": "3:15:34", "throughput": 1488.54, "total_tokens": 20902816} {"current_steps": 99045, "total_steps": 181800, "loss": 0.0362, "lr": 2.545406784551505e-05, "epoch": 10.896039603960396, "percentage": 54.48, "elapsed_time": "3:54:03", "remaining_time": "3:15:33", "throughput": 1488.54, "total_tokens": 20903904} {"current_steps": 99050, "total_steps": 181800, "loss": 0.1118, "lr": 2.545166817160284e-05, "epoch": 10.896589658965897, "percentage": 54.48, "elapsed_time": "3:54:03", "remaining_time": "3:15:32", "throughput": 1488.54, "total_tokens": 20904896} {"current_steps": 99055, "total_steps": 181800, "loss": 0.2475, "lr": 2.5449268493527815e-05, "epoch": 10.897139713971397, "percentage": 54.49, "elapsed_time": "3:54:04", "remaining_time": "3:15:32", "throughput": 1488.54, "total_tokens": 20905952} {"current_steps": 99060, "total_steps": 181800, "loss": 0.0144, "lr": 2.544686881131211e-05, "epoch": 10.897689768976898, "percentage": 54.49, "elapsed_time": "3:54:05", "remaining_time": "3:15:31", "throughput": 1488.54, "total_tokens": 20906944} {"current_steps": 99065, "total_steps": 181800, "loss": 0.1547, "lr": 2.5444469124977823e-05, "epoch": 10.898239823982399, "percentage": 54.49, "elapsed_time": "3:54:05", "remaining_time": "3:15:30", "throughput": 1488.54, "total_tokens": 20908000} {"current_steps": 99070, "total_steps": 181800, "loss": 0.0723, "lr": 2.544206943454708e-05, "epoch": 10.898789878987898, "percentage": 54.49, "elapsed_time": "3:54:06", "remaining_time": "3:15:29", "throughput": 1488.54, "total_tokens": 20908992} {"current_steps": 99075, "total_steps": 181800, "loss": 0.1522, "lr": 2.5439669740041995e-05, "epoch": 10.8993399339934, "percentage": 54.5, "elapsed_time": "3:54:07", "remaining_time": "3:15:29", "throughput": 1488.54, "total_tokens": 20910080} {"current_steps": 99080, "total_steps": 181800, "loss": 0.199, "lr": 2.5437270041484685e-05, "epoch": 10.8998899889989, "percentage": 54.5, "elapsed_time": "3:54:08", "remaining_time": "3:15:28", "throughput": 1488.54, "total_tokens": 20911104} {"current_steps": 99085, "total_steps": 181800, "loss": 0.0169, "lr": 2.543487033889726e-05, "epoch": 10.9004400440044, "percentage": 54.5, "elapsed_time": "3:54:08", "remaining_time": "3:15:27", "throughput": 1488.54, "total_tokens": 20912128} {"current_steps": 99090, "total_steps": 181800, "loss": 0.0112, "lr": 2.5432470632301854e-05, "epoch": 10.900990099009901, "percentage": 54.5, "elapsed_time": "3:54:09", "remaining_time": "3:15:27", "throughput": 1488.54, "total_tokens": 20913184} {"current_steps": 99095, "total_steps": 181800, "loss": 0.0113, "lr": 2.5430070921720572e-05, "epoch": 10.901540154015402, "percentage": 54.51, "elapsed_time": "3:54:10", "remaining_time": "3:15:26", "throughput": 1488.55, "total_tokens": 20914272} {"current_steps": 99100, "total_steps": 181800, "loss": 0.0072, "lr": 2.5427671207175525e-05, "epoch": 10.902090209020901, "percentage": 54.51, "elapsed_time": "3:54:10", "remaining_time": "3:15:25", "throughput": 1488.55, "total_tokens": 20915296} {"current_steps": 99105, "total_steps": 181800, "loss": 0.0598, "lr": 2.5425271488688845e-05, "epoch": 10.902640264026402, "percentage": 54.51, "elapsed_time": "3:54:11", "remaining_time": "3:15:24", "throughput": 1488.55, "total_tokens": 20916320} {"current_steps": 99110, "total_steps": 181800, "loss": 0.0181, "lr": 2.542287176628264e-05, "epoch": 10.903190319031903, "percentage": 54.52, "elapsed_time": "3:54:12", "remaining_time": "3:15:24", "throughput": 1488.55, "total_tokens": 20917376} {"current_steps": 99115, "total_steps": 181800, "loss": 0.0018, "lr": 2.5420472039979032e-05, "epoch": 10.903740374037405, "percentage": 54.52, "elapsed_time": "3:54:12", "remaining_time": "3:15:23", "throughput": 1488.55, "total_tokens": 20918400} {"current_steps": 99120, "total_steps": 181800, "loss": 0.016, "lr": 2.541807230980013e-05, "epoch": 10.904290429042904, "percentage": 54.52, "elapsed_time": "3:54:13", "remaining_time": "3:15:22", "throughput": 1488.55, "total_tokens": 20919488} {"current_steps": 99125, "total_steps": 181800, "loss": 0.0123, "lr": 2.5415672575768055e-05, "epoch": 10.904840484048405, "percentage": 54.52, "elapsed_time": "3:54:14", "remaining_time": "3:15:21", "throughput": 1488.55, "total_tokens": 20920544} {"current_steps": 99130, "total_steps": 181800, "loss": 0.007, "lr": 2.5413272837904927e-05, "epoch": 10.905390539053906, "percentage": 54.53, "elapsed_time": "3:54:14", "remaining_time": "3:15:21", "throughput": 1488.56, "total_tokens": 20921600} {"current_steps": 99135, "total_steps": 181800, "loss": 0.0459, "lr": 2.5410873096232864e-05, "epoch": 10.905940594059405, "percentage": 54.53, "elapsed_time": "3:54:15", "remaining_time": "3:15:20", "throughput": 1488.56, "total_tokens": 20922688} {"current_steps": 99140, "total_steps": 181800, "loss": 0.0011, "lr": 2.5408473350773977e-05, "epoch": 10.906490649064907, "percentage": 54.53, "elapsed_time": "3:54:16", "remaining_time": "3:15:19", "throughput": 1488.56, "total_tokens": 20923744} {"current_steps": 99145, "total_steps": 181800, "loss": 0.0238, "lr": 2.540607360155039e-05, "epoch": 10.907040704070408, "percentage": 54.54, "elapsed_time": "3:54:17", "remaining_time": "3:15:19", "throughput": 1488.56, "total_tokens": 20924768} {"current_steps": 99150, "total_steps": 181800, "loss": 0.006, "lr": 2.540367384858422e-05, "epoch": 10.907590759075907, "percentage": 54.54, "elapsed_time": "3:54:17", "remaining_time": "3:15:18", "throughput": 1488.56, "total_tokens": 20925824} {"current_steps": 99155, "total_steps": 181800, "loss": 0.0797, "lr": 2.5401274091897575e-05, "epoch": 10.908140814081408, "percentage": 54.54, "elapsed_time": "3:54:18", "remaining_time": "3:15:17", "throughput": 1488.56, "total_tokens": 20926848} {"current_steps": 99160, "total_steps": 181800, "loss": 0.0027, "lr": 2.539887433151258e-05, "epoch": 10.908690869086909, "percentage": 54.54, "elapsed_time": "3:54:19", "remaining_time": "3:15:16", "throughput": 1488.57, "total_tokens": 20927904} {"current_steps": 99165, "total_steps": 181800, "loss": 0.0791, "lr": 2.539647456745136e-05, "epoch": 10.909240924092408, "percentage": 54.55, "elapsed_time": "3:54:19", "remaining_time": "3:15:16", "throughput": 1488.57, "total_tokens": 20928960} {"current_steps": 99170, "total_steps": 181800, "loss": 0.0294, "lr": 2.5394074799736017e-05, "epoch": 10.90979097909791, "percentage": 54.55, "elapsed_time": "3:54:20", "remaining_time": "3:15:15", "throughput": 1488.58, "total_tokens": 20930080} {"current_steps": 99175, "total_steps": 181800, "loss": 0.0239, "lr": 2.539167502838868e-05, "epoch": 10.91034103410341, "percentage": 54.55, "elapsed_time": "3:54:21", "remaining_time": "3:15:14", "throughput": 1488.58, "total_tokens": 20931136} {"current_steps": 99180, "total_steps": 181800, "loss": 0.0082, "lr": 2.5389275253431454e-05, "epoch": 10.910891089108912, "percentage": 54.55, "elapsed_time": "3:54:21", "remaining_time": "3:15:13", "throughput": 1488.58, "total_tokens": 20932160} {"current_steps": 99185, "total_steps": 181800, "loss": 0.0259, "lr": 2.5386875474886475e-05, "epoch": 10.911441144114411, "percentage": 54.56, "elapsed_time": "3:54:22", "remaining_time": "3:15:13", "throughput": 1488.58, "total_tokens": 20933184} {"current_steps": 99190, "total_steps": 181800, "loss": 0.04, "lr": 2.5384475692775846e-05, "epoch": 10.911991199119912, "percentage": 54.56, "elapsed_time": "3:54:23", "remaining_time": "3:15:12", "throughput": 1488.58, "total_tokens": 20934240} {"current_steps": 99195, "total_steps": 181800, "loss": 0.0131, "lr": 2.538207590712169e-05, "epoch": 10.912541254125413, "percentage": 54.56, "elapsed_time": "3:54:23", "remaining_time": "3:15:11", "throughput": 1488.58, "total_tokens": 20935328} {"current_steps": 99200, "total_steps": 181800, "loss": 0.0088, "lr": 2.5379676117946117e-05, "epoch": 10.913091309130913, "percentage": 54.57, "elapsed_time": "3:54:24", "remaining_time": "3:15:11", "throughput": 1488.59, "total_tokens": 20936448} {"current_steps": 99205, "total_steps": 181800, "loss": 0.0555, "lr": 2.537727632527126e-05, "epoch": 10.913641364136414, "percentage": 54.57, "elapsed_time": "3:54:25", "remaining_time": "3:15:10", "throughput": 1488.59, "total_tokens": 20937504} {"current_steps": 99210, "total_steps": 181800, "loss": 0.0093, "lr": 2.537487652911923e-05, "epoch": 10.914191419141915, "percentage": 54.57, "elapsed_time": "3:54:25", "remaining_time": "3:15:09", "throughput": 1488.6, "total_tokens": 20938592} {"current_steps": 99215, "total_steps": 181800, "loss": 0.0175, "lr": 2.5372476729512136e-05, "epoch": 10.914741474147414, "percentage": 54.57, "elapsed_time": "3:54:26", "remaining_time": "3:15:08", "throughput": 1488.6, "total_tokens": 20939680} {"current_steps": 99220, "total_steps": 181800, "loss": 0.0505, "lr": 2.5370076926472102e-05, "epoch": 10.915291529152915, "percentage": 54.58, "elapsed_time": "3:54:27", "remaining_time": "3:15:08", "throughput": 1488.6, "total_tokens": 20940704} {"current_steps": 99225, "total_steps": 181800, "loss": 0.1136, "lr": 2.536767712002125e-05, "epoch": 10.915841584158416, "percentage": 54.58, "elapsed_time": "3:54:28", "remaining_time": "3:15:07", "throughput": 1488.6, "total_tokens": 20941760} {"current_steps": 99230, "total_steps": 181800, "loss": 0.0019, "lr": 2.536527731018169e-05, "epoch": 10.916391639163916, "percentage": 54.58, "elapsed_time": "3:54:28", "remaining_time": "3:15:06", "throughput": 1488.6, "total_tokens": 20942752} {"current_steps": 99235, "total_steps": 181800, "loss": 0.0712, "lr": 2.5362877496975553e-05, "epoch": 10.916941694169417, "percentage": 54.58, "elapsed_time": "3:54:29", "remaining_time": "3:15:05", "throughput": 1488.6, "total_tokens": 20943776} {"current_steps": 99240, "total_steps": 181800, "loss": 0.0024, "lr": 2.5360477680424944e-05, "epoch": 10.917491749174918, "percentage": 54.59, "elapsed_time": "3:54:30", "remaining_time": "3:15:05", "throughput": 1488.6, "total_tokens": 20944832} {"current_steps": 99245, "total_steps": 181800, "loss": 0.0065, "lr": 2.5358077860551984e-05, "epoch": 10.918041804180419, "percentage": 54.59, "elapsed_time": "3:54:30", "remaining_time": "3:15:04", "throughput": 1488.6, "total_tokens": 20945824} {"current_steps": 99250, "total_steps": 181800, "loss": 0.0582, "lr": 2.535567803737879e-05, "epoch": 10.918591859185918, "percentage": 54.59, "elapsed_time": "3:54:31", "remaining_time": "3:15:03", "throughput": 1488.61, "total_tokens": 20946912} {"current_steps": 99255, "total_steps": 181800, "loss": 0.0043, "lr": 2.5353278210927484e-05, "epoch": 10.91914191419142, "percentage": 54.6, "elapsed_time": "3:54:32", "remaining_time": "3:15:03", "throughput": 1488.61, "total_tokens": 20947936} {"current_steps": 99260, "total_steps": 181800, "loss": 0.018, "lr": 2.5350878381220183e-05, "epoch": 10.91969196919692, "percentage": 54.6, "elapsed_time": "3:54:32", "remaining_time": "3:15:02", "throughput": 1488.6, "total_tokens": 20948928} {"current_steps": 99265, "total_steps": 181800, "loss": 0.069, "lr": 2.534847854827901e-05, "epoch": 10.92024202420242, "percentage": 54.6, "elapsed_time": "3:54:33", "remaining_time": "3:15:01", "throughput": 1488.61, "total_tokens": 20949984} {"current_steps": 99270, "total_steps": 181800, "loss": 0.0965, "lr": 2.5346078712126072e-05, "epoch": 10.92079207920792, "percentage": 54.6, "elapsed_time": "3:54:34", "remaining_time": "3:15:00", "throughput": 1488.6, "total_tokens": 20951008} {"current_steps": 99275, "total_steps": 181800, "loss": 0.0029, "lr": 2.5343678872783483e-05, "epoch": 10.921342134213422, "percentage": 54.61, "elapsed_time": "3:54:34", "remaining_time": "3:15:00", "throughput": 1488.61, "total_tokens": 20952096} {"current_steps": 99280, "total_steps": 181800, "loss": 0.0022, "lr": 2.5341279030273384e-05, "epoch": 10.921892189218921, "percentage": 54.61, "elapsed_time": "3:54:35", "remaining_time": "3:14:59", "throughput": 1488.61, "total_tokens": 20953088} {"current_steps": 99285, "total_steps": 181800, "loss": 0.1041, "lr": 2.533887918461788e-05, "epoch": 10.922442244224422, "percentage": 54.61, "elapsed_time": "3:54:36", "remaining_time": "3:14:58", "throughput": 1488.61, "total_tokens": 20954144} {"current_steps": 99290, "total_steps": 181800, "loss": 0.0052, "lr": 2.533647933583908e-05, "epoch": 10.922992299229923, "percentage": 54.61, "elapsed_time": "3:54:37", "remaining_time": "3:14:58", "throughput": 1488.61, "total_tokens": 20955264} {"current_steps": 99295, "total_steps": 181800, "loss": 0.0047, "lr": 2.5334079483959116e-05, "epoch": 10.923542354235423, "percentage": 54.62, "elapsed_time": "3:54:37", "remaining_time": "3:14:57", "throughput": 1488.62, "total_tokens": 20956320} {"current_steps": 99300, "total_steps": 181800, "loss": 0.0044, "lr": 2.5331679629000103e-05, "epoch": 10.924092409240924, "percentage": 54.62, "elapsed_time": "3:54:38", "remaining_time": "3:14:56", "throughput": 1488.62, "total_tokens": 20957408} {"current_steps": 99305, "total_steps": 181800, "loss": 0.1039, "lr": 2.532927977098416e-05, "epoch": 10.924642464246425, "percentage": 54.62, "elapsed_time": "3:54:39", "remaining_time": "3:14:55", "throughput": 1488.62, "total_tokens": 20958432} {"current_steps": 99310, "total_steps": 181800, "loss": 0.0072, "lr": 2.5326879909933403e-05, "epoch": 10.925192519251926, "percentage": 54.63, "elapsed_time": "3:54:39", "remaining_time": "3:14:55", "throughput": 1488.63, "total_tokens": 20959520} {"current_steps": 99315, "total_steps": 181800, "loss": 0.0036, "lr": 2.532448004586994e-05, "epoch": 10.925742574257425, "percentage": 54.63, "elapsed_time": "3:54:40", "remaining_time": "3:14:54", "throughput": 1488.63, "total_tokens": 20960608} {"current_steps": 99320, "total_steps": 181800, "loss": 0.0665, "lr": 2.532208017881591e-05, "epoch": 10.926292629262926, "percentage": 54.63, "elapsed_time": "3:54:41", "remaining_time": "3:14:53", "throughput": 1488.63, "total_tokens": 20961664} {"current_steps": 99325, "total_steps": 181800, "loss": 0.0099, "lr": 2.5319680308793426e-05, "epoch": 10.926842684268427, "percentage": 54.63, "elapsed_time": "3:54:41", "remaining_time": "3:14:52", "throughput": 1488.63, "total_tokens": 20962688} {"current_steps": 99330, "total_steps": 181800, "loss": 0.2046, "lr": 2.5317280435824592e-05, "epoch": 10.927392739273927, "percentage": 54.64, "elapsed_time": "3:54:42", "remaining_time": "3:14:52", "throughput": 1488.64, "total_tokens": 20963808} {"current_steps": 99335, "total_steps": 181800, "loss": 0.0018, "lr": 2.5314880559931542e-05, "epoch": 10.927942794279428, "percentage": 54.64, "elapsed_time": "3:54:43", "remaining_time": "3:14:51", "throughput": 1488.64, "total_tokens": 20964896} {"current_steps": 99340, "total_steps": 181800, "loss": 0.1302, "lr": 2.5312480681136392e-05, "epoch": 10.928492849284929, "percentage": 54.64, "elapsed_time": "3:54:43", "remaining_time": "3:14:50", "throughput": 1488.64, "total_tokens": 20965952} {"current_steps": 99345, "total_steps": 181800, "loss": 0.0052, "lr": 2.5310080799461245e-05, "epoch": 10.929042904290428, "percentage": 54.65, "elapsed_time": "3:54:44", "remaining_time": "3:14:50", "throughput": 1488.65, "total_tokens": 20967008} {"current_steps": 99350, "total_steps": 181800, "loss": 0.0517, "lr": 2.530768091492824e-05, "epoch": 10.92959295929593, "percentage": 54.65, "elapsed_time": "3:54:45", "remaining_time": "3:14:49", "throughput": 1488.65, "total_tokens": 20968064} {"current_steps": 99355, "total_steps": 181800, "loss": 0.0164, "lr": 2.5305281027559495e-05, "epoch": 10.93014301430143, "percentage": 54.65, "elapsed_time": "3:54:46", "remaining_time": "3:14:48", "throughput": 1488.65, "total_tokens": 20969152} {"current_steps": 99360, "total_steps": 181800, "loss": 0.0109, "lr": 2.5302881137377112e-05, "epoch": 10.930693069306932, "percentage": 54.65, "elapsed_time": "3:54:46", "remaining_time": "3:14:47", "throughput": 1488.65, "total_tokens": 20970176} {"current_steps": 99365, "total_steps": 181800, "loss": 0.0622, "lr": 2.530048124440322e-05, "epoch": 10.93124312431243, "percentage": 54.66, "elapsed_time": "3:54:47", "remaining_time": "3:14:47", "throughput": 1488.65, "total_tokens": 20971200} {"current_steps": 99370, "total_steps": 181800, "loss": 0.0058, "lr": 2.5298081348659936e-05, "epoch": 10.931793179317932, "percentage": 54.66, "elapsed_time": "3:54:48", "remaining_time": "3:14:46", "throughput": 1488.65, "total_tokens": 20972224} {"current_steps": 99375, "total_steps": 181800, "loss": 0.0024, "lr": 2.529568145016938e-05, "epoch": 10.932343234323433, "percentage": 54.66, "elapsed_time": "3:54:48", "remaining_time": "3:14:45", "throughput": 1488.65, "total_tokens": 20973216} {"current_steps": 99380, "total_steps": 181800, "loss": 0.0418, "lr": 2.5293281548953673e-05, "epoch": 10.932893289328932, "percentage": 54.66, "elapsed_time": "3:54:49", "remaining_time": "3:14:44", "throughput": 1488.65, "total_tokens": 20974304} {"current_steps": 99385, "total_steps": 181800, "loss": 0.0478, "lr": 2.5290881645034932e-05, "epoch": 10.933443344334433, "percentage": 54.67, "elapsed_time": "3:54:50", "remaining_time": "3:14:44", "throughput": 1488.65, "total_tokens": 20975328} {"current_steps": 99390, "total_steps": 181800, "loss": 0.0149, "lr": 2.5288481738435265e-05, "epoch": 10.933993399339935, "percentage": 54.67, "elapsed_time": "3:54:50", "remaining_time": "3:14:43", "throughput": 1488.65, "total_tokens": 20976352} {"current_steps": 99395, "total_steps": 181800, "loss": 0.0193, "lr": 2.5286081829176805e-05, "epoch": 10.934543454345434, "percentage": 54.67, "elapsed_time": "3:54:51", "remaining_time": "3:14:42", "throughput": 1488.66, "total_tokens": 20977472} {"current_steps": 99400, "total_steps": 181800, "loss": 0.0164, "lr": 2.5283681917281677e-05, "epoch": 10.935093509350935, "percentage": 54.68, "elapsed_time": "3:54:52", "remaining_time": "3:14:42", "throughput": 1488.66, "total_tokens": 20978496} {"current_steps": 99405, "total_steps": 181800, "loss": 0.0081, "lr": 2.528128200277197e-05, "epoch": 10.935643564356436, "percentage": 54.68, "elapsed_time": "3:54:52", "remaining_time": "3:14:41", "throughput": 1488.66, "total_tokens": 20979552} {"current_steps": 99410, "total_steps": 181800, "loss": 0.1379, "lr": 2.527888208566983e-05, "epoch": 10.936193619361937, "percentage": 54.68, "elapsed_time": "3:54:53", "remaining_time": "3:14:40", "throughput": 1488.66, "total_tokens": 20980576} {"current_steps": 99415, "total_steps": 181800, "loss": 0.0582, "lr": 2.5276482165997372e-05, "epoch": 10.936743674367436, "percentage": 54.68, "elapsed_time": "3:54:54", "remaining_time": "3:14:39", "throughput": 1488.67, "total_tokens": 20981664} {"current_steps": 99420, "total_steps": 181800, "loss": 0.0562, "lr": 2.5274082243776702e-05, "epoch": 10.937293729372938, "percentage": 54.69, "elapsed_time": "3:54:54", "remaining_time": "3:14:39", "throughput": 1488.67, "total_tokens": 20982752} {"current_steps": 99425, "total_steps": 181800, "loss": 0.0309, "lr": 2.527168231902996e-05, "epoch": 10.937843784378439, "percentage": 54.69, "elapsed_time": "3:54:55", "remaining_time": "3:14:38", "throughput": 1488.67, "total_tokens": 20983712} {"current_steps": 99430, "total_steps": 181800, "loss": 0.0058, "lr": 2.5269282391779243e-05, "epoch": 10.938393839383938, "percentage": 54.69, "elapsed_time": "3:54:56", "remaining_time": "3:14:37", "throughput": 1488.67, "total_tokens": 20984768} {"current_steps": 99435, "total_steps": 181800, "loss": 0.0167, "lr": 2.5266882462046675e-05, "epoch": 10.938943894389439, "percentage": 54.69, "elapsed_time": "3:54:57", "remaining_time": "3:14:36", "throughput": 1488.67, "total_tokens": 20985792} {"current_steps": 99440, "total_steps": 181800, "loss": 0.0061, "lr": 2.526448252985439e-05, "epoch": 10.93949394939494, "percentage": 54.7, "elapsed_time": "3:54:57", "remaining_time": "3:14:36", "throughput": 1488.67, "total_tokens": 20986784} {"current_steps": 99445, "total_steps": 181800, "loss": 0.0275, "lr": 2.526208259522449e-05, "epoch": 10.94004400440044, "percentage": 54.7, "elapsed_time": "3:54:58", "remaining_time": "3:14:35", "throughput": 1488.67, "total_tokens": 20987872} {"current_steps": 99450, "total_steps": 181800, "loss": 0.0132, "lr": 2.5259682658179107e-05, "epoch": 10.94059405940594, "percentage": 54.7, "elapsed_time": "3:54:59", "remaining_time": "3:14:34", "throughput": 1488.67, "total_tokens": 20988928} {"current_steps": 99455, "total_steps": 181800, "loss": 0.0431, "lr": 2.5257282718740348e-05, "epoch": 10.941144114411442, "percentage": 54.71, "elapsed_time": "3:54:59", "remaining_time": "3:14:34", "throughput": 1488.67, "total_tokens": 20989952} {"current_steps": 99460, "total_steps": 181800, "loss": 0.0141, "lr": 2.5254882776930337e-05, "epoch": 10.941694169416941, "percentage": 54.71, "elapsed_time": "3:55:00", "remaining_time": "3:14:33", "throughput": 1488.67, "total_tokens": 20990944} {"current_steps": 99465, "total_steps": 181800, "loss": 0.0613, "lr": 2.5252482832771196e-05, "epoch": 10.942244224422442, "percentage": 54.71, "elapsed_time": "3:55:01", "remaining_time": "3:14:32", "throughput": 1488.68, "total_tokens": 20992064} {"current_steps": 99470, "total_steps": 181800, "loss": 0.0096, "lr": 2.525008288628504e-05, "epoch": 10.942794279427943, "percentage": 54.71, "elapsed_time": "3:55:01", "remaining_time": "3:14:31", "throughput": 1488.68, "total_tokens": 20993088} {"current_steps": 99475, "total_steps": 181800, "loss": 0.0482, "lr": 2.5247682937493995e-05, "epoch": 10.943344334433444, "percentage": 54.72, "elapsed_time": "3:55:02", "remaining_time": "3:14:31", "throughput": 1488.68, "total_tokens": 20994208} {"current_steps": 99480, "total_steps": 181800, "loss": 0.0405, "lr": 2.5245282986420172e-05, "epoch": 10.943894389438944, "percentage": 54.72, "elapsed_time": "3:55:03", "remaining_time": "3:14:30", "throughput": 1488.69, "total_tokens": 20995296} {"current_steps": 99485, "total_steps": 181800, "loss": 0.0253, "lr": 2.5242883033085692e-05, "epoch": 10.944444444444445, "percentage": 54.72, "elapsed_time": "3:55:03", "remaining_time": "3:14:29", "throughput": 1488.69, "total_tokens": 20996384} {"current_steps": 99490, "total_steps": 181800, "loss": 0.1299, "lr": 2.5240483077512676e-05, "epoch": 10.944994499449946, "percentage": 54.72, "elapsed_time": "3:55:04", "remaining_time": "3:14:29", "throughput": 1488.7, "total_tokens": 20997440} {"current_steps": 99495, "total_steps": 181800, "loss": 0.003, "lr": 2.5238083119723243e-05, "epoch": 10.945544554455445, "percentage": 54.73, "elapsed_time": "3:55:05", "remaining_time": "3:14:28", "throughput": 1488.7, "total_tokens": 20998592} {"current_steps": 99500, "total_steps": 181800, "loss": 0.0556, "lr": 2.5235683159739514e-05, "epoch": 10.946094609460946, "percentage": 54.73, "elapsed_time": "3:55:05", "remaining_time": "3:14:27", "throughput": 1488.7, "total_tokens": 20999584} {"current_steps": 99505, "total_steps": 181800, "loss": 0.0076, "lr": 2.5233283197583603e-05, "epoch": 10.946644664466447, "percentage": 54.73, "elapsed_time": "3:55:06", "remaining_time": "3:14:26", "throughput": 1488.7, "total_tokens": 21000608} {"current_steps": 99510, "total_steps": 181800, "loss": 0.0475, "lr": 2.5230883233277637e-05, "epoch": 10.947194719471947, "percentage": 54.74, "elapsed_time": "3:55:07", "remaining_time": "3:14:26", "throughput": 1488.71, "total_tokens": 21001696} {"current_steps": 99515, "total_steps": 181800, "loss": 0.0223, "lr": 2.5228483266843728e-05, "epoch": 10.947744774477448, "percentage": 54.74, "elapsed_time": "3:55:08", "remaining_time": "3:14:25", "throughput": 1488.71, "total_tokens": 21002816} {"current_steps": 99520, "total_steps": 181800, "loss": 0.0279, "lr": 2.5226083298304e-05, "epoch": 10.948294829482949, "percentage": 54.74, "elapsed_time": "3:55:08", "remaining_time": "3:14:24", "throughput": 1488.72, "total_tokens": 21003872} {"current_steps": 99525, "total_steps": 181800, "loss": 0.0032, "lr": 2.5223683327680568e-05, "epoch": 10.948844884488448, "percentage": 54.74, "elapsed_time": "3:55:09", "remaining_time": "3:14:23", "throughput": 1488.72, "total_tokens": 21004896} {"current_steps": 99530, "total_steps": 181800, "loss": 0.1239, "lr": 2.5221283354995556e-05, "epoch": 10.94939493949395, "percentage": 54.75, "elapsed_time": "3:55:10", "remaining_time": "3:14:23", "throughput": 1488.72, "total_tokens": 21005952} {"current_steps": 99535, "total_steps": 181800, "loss": 0.0354, "lr": 2.521888338027108e-05, "epoch": 10.94994499449945, "percentage": 54.75, "elapsed_time": "3:55:10", "remaining_time": "3:14:22", "throughput": 1488.72, "total_tokens": 21007008} {"current_steps": 99540, "total_steps": 181800, "loss": 0.01, "lr": 2.5216483403529263e-05, "epoch": 10.950495049504951, "percentage": 54.75, "elapsed_time": "3:55:11", "remaining_time": "3:14:21", "throughput": 1488.72, "total_tokens": 21008032} {"current_steps": 99545, "total_steps": 181800, "loss": 0.0782, "lr": 2.5214083424792227e-05, "epoch": 10.95104510451045, "percentage": 54.76, "elapsed_time": "3:55:12", "remaining_time": "3:14:21", "throughput": 1488.72, "total_tokens": 21009056} {"current_steps": 99550, "total_steps": 181800, "loss": 0.0682, "lr": 2.521168344408208e-05, "epoch": 10.951595159515952, "percentage": 54.76, "elapsed_time": "3:55:12", "remaining_time": "3:14:20", "throughput": 1488.72, "total_tokens": 21010048} {"current_steps": 99555, "total_steps": 181800, "loss": 0.0016, "lr": 2.5209283461420947e-05, "epoch": 10.952145214521453, "percentage": 54.76, "elapsed_time": "3:55:13", "remaining_time": "3:14:19", "throughput": 1488.72, "total_tokens": 21011072} {"current_steps": 99560, "total_steps": 181800, "loss": 0.0141, "lr": 2.520688347683095e-05, "epoch": 10.952695269526952, "percentage": 54.76, "elapsed_time": "3:55:14", "remaining_time": "3:14:18", "throughput": 1488.72, "total_tokens": 21012096} {"current_steps": 99565, "total_steps": 181800, "loss": 0.0029, "lr": 2.5204483490334206e-05, "epoch": 10.953245324532453, "percentage": 54.77, "elapsed_time": "3:55:14", "remaining_time": "3:14:18", "throughput": 1488.72, "total_tokens": 21013184} {"current_steps": 99570, "total_steps": 181800, "loss": 0.0142, "lr": 2.5202083501952843e-05, "epoch": 10.953795379537954, "percentage": 54.77, "elapsed_time": "3:55:15", "remaining_time": "3:14:17", "throughput": 1488.72, "total_tokens": 21014208} {"current_steps": 99575, "total_steps": 181800, "loss": 0.0094, "lr": 2.519968351170897e-05, "epoch": 10.954345434543454, "percentage": 54.77, "elapsed_time": "3:55:16", "remaining_time": "3:14:16", "throughput": 1488.72, "total_tokens": 21015264} {"current_steps": 99580, "total_steps": 181800, "loss": 0.0122, "lr": 2.5197283519624705e-05, "epoch": 10.954895489548955, "percentage": 54.77, "elapsed_time": "3:55:16", "remaining_time": "3:14:15", "throughput": 1488.72, "total_tokens": 21016288} {"current_steps": 99585, "total_steps": 181800, "loss": 0.0211, "lr": 2.5194883525722178e-05, "epoch": 10.955445544554456, "percentage": 54.78, "elapsed_time": "3:55:17", "remaining_time": "3:14:15", "throughput": 1488.72, "total_tokens": 21017280} {"current_steps": 99590, "total_steps": 181800, "loss": 0.0029, "lr": 2.5192483530023504e-05, "epoch": 10.955995599559955, "percentage": 54.78, "elapsed_time": "3:55:18", "remaining_time": "3:14:14", "throughput": 1488.72, "total_tokens": 21018272} {"current_steps": 99595, "total_steps": 181800, "loss": 0.0575, "lr": 2.51900835325508e-05, "epoch": 10.956545654565456, "percentage": 54.78, "elapsed_time": "3:55:19", "remaining_time": "3:14:13", "throughput": 1488.71, "total_tokens": 21019232} {"current_steps": 99600, "total_steps": 181800, "loss": 0.0061, "lr": 2.5187683533326184e-05, "epoch": 10.957095709570957, "percentage": 54.79, "elapsed_time": "3:55:19", "remaining_time": "3:14:13", "throughput": 1488.72, "total_tokens": 21020288} {"current_steps": 99605, "total_steps": 181800, "loss": 0.0128, "lr": 2.5185283532371782e-05, "epoch": 10.957645764576458, "percentage": 54.79, "elapsed_time": "3:55:20", "remaining_time": "3:14:12", "throughput": 1488.72, "total_tokens": 21021344} {"current_steps": 99610, "total_steps": 181800, "loss": 0.1033, "lr": 2.5182883529709705e-05, "epoch": 10.958195819581958, "percentage": 54.79, "elapsed_time": "3:55:21", "remaining_time": "3:14:11", "throughput": 1488.72, "total_tokens": 21022400} {"current_steps": 99615, "total_steps": 181800, "loss": 0.095, "lr": 2.5180483525362093e-05, "epoch": 10.958745874587459, "percentage": 54.79, "elapsed_time": "3:55:21", "remaining_time": "3:14:10", "throughput": 1488.72, "total_tokens": 21023424} {"current_steps": 99620, "total_steps": 181800, "loss": 0.0105, "lr": 2.5178083519351037e-05, "epoch": 10.95929592959296, "percentage": 54.8, "elapsed_time": "3:55:22", "remaining_time": "3:14:10", "throughput": 1488.72, "total_tokens": 21024480} {"current_steps": 99625, "total_steps": 181800, "loss": 0.0071, "lr": 2.5175683511698672e-05, "epoch": 10.95984598459846, "percentage": 54.8, "elapsed_time": "3:55:23", "remaining_time": "3:14:09", "throughput": 1488.73, "total_tokens": 21025568} {"current_steps": 99630, "total_steps": 181800, "loss": 0.0054, "lr": 2.517328350242712e-05, "epoch": 10.96039603960396, "percentage": 54.8, "elapsed_time": "3:55:23", "remaining_time": "3:14:08", "throughput": 1488.73, "total_tokens": 21026656} {"current_steps": 99635, "total_steps": 181800, "loss": 0.0112, "lr": 2.51708834915585e-05, "epoch": 10.960946094609461, "percentage": 54.8, "elapsed_time": "3:55:24", "remaining_time": "3:14:07", "throughput": 1488.73, "total_tokens": 21027680} {"current_steps": 99640, "total_steps": 181800, "loss": 0.0023, "lr": 2.5168483479114925e-05, "epoch": 10.96149614961496, "percentage": 54.81, "elapsed_time": "3:55:25", "remaining_time": "3:14:07", "throughput": 1488.73, "total_tokens": 21028768} {"current_steps": 99645, "total_steps": 181800, "loss": 0.0885, "lr": 2.5166083465118517e-05, "epoch": 10.962046204620462, "percentage": 54.81, "elapsed_time": "3:55:25", "remaining_time": "3:14:06", "throughput": 1488.73, "total_tokens": 21029792} {"current_steps": 99650, "total_steps": 181800, "loss": 0.0035, "lr": 2.5163683449591398e-05, "epoch": 10.962596259625963, "percentage": 54.81, "elapsed_time": "3:55:26", "remaining_time": "3:14:05", "throughput": 1488.74, "total_tokens": 21030848} {"current_steps": 99655, "total_steps": 181800, "loss": 0.0497, "lr": 2.5161283432555687e-05, "epoch": 10.963146314631462, "percentage": 54.82, "elapsed_time": "3:55:27", "remaining_time": "3:14:05", "throughput": 1488.74, "total_tokens": 21031904} {"current_steps": 99660, "total_steps": 181800, "loss": 0.0925, "lr": 2.5158883414033507e-05, "epoch": 10.963696369636963, "percentage": 54.82, "elapsed_time": "3:55:28", "remaining_time": "3:14:04", "throughput": 1488.74, "total_tokens": 21032896} {"current_steps": 99665, "total_steps": 181800, "loss": 0.0164, "lr": 2.515648339404697e-05, "epoch": 10.964246424642464, "percentage": 54.82, "elapsed_time": "3:55:28", "remaining_time": "3:14:03", "throughput": 1488.74, "total_tokens": 21033952} {"current_steps": 99670, "total_steps": 181800, "loss": 0.0078, "lr": 2.515408337261821e-05, "epoch": 10.964796479647966, "percentage": 54.82, "elapsed_time": "3:55:29", "remaining_time": "3:14:02", "throughput": 1488.74, "total_tokens": 21034976} {"current_steps": 99675, "total_steps": 181800, "loss": 0.0688, "lr": 2.515168334976933e-05, "epoch": 10.965346534653465, "percentage": 54.83, "elapsed_time": "3:55:30", "remaining_time": "3:14:02", "throughput": 1488.74, "total_tokens": 21036000} {"current_steps": 99680, "total_steps": 181800, "loss": 0.081, "lr": 2.5149283325522456e-05, "epoch": 10.965896589658966, "percentage": 54.83, "elapsed_time": "3:55:30", "remaining_time": "3:14:01", "throughput": 1488.74, "total_tokens": 21037024} {"current_steps": 99685, "total_steps": 181800, "loss": 0.0029, "lr": 2.5146883299899714e-05, "epoch": 10.966446644664467, "percentage": 54.83, "elapsed_time": "3:55:31", "remaining_time": "3:14:00", "throughput": 1488.74, "total_tokens": 21038144} {"current_steps": 99690, "total_steps": 181800, "loss": 0.0077, "lr": 2.514448327292322e-05, "epoch": 10.966996699669966, "percentage": 54.83, "elapsed_time": "3:55:32", "remaining_time": "3:13:59", "throughput": 1488.74, "total_tokens": 21039168} {"current_steps": 99695, "total_steps": 181800, "loss": 0.0191, "lr": 2.5142083244615083e-05, "epoch": 10.967546754675467, "percentage": 54.84, "elapsed_time": "3:55:32", "remaining_time": "3:13:59", "throughput": 1488.75, "total_tokens": 21040224} {"current_steps": 99700, "total_steps": 181800, "loss": 0.0343, "lr": 2.513968321499744e-05, "epoch": 10.968096809680969, "percentage": 54.84, "elapsed_time": "3:55:33", "remaining_time": "3:13:58", "throughput": 1488.75, "total_tokens": 21041248} {"current_steps": 99705, "total_steps": 181800, "loss": 0.029, "lr": 2.5137283184092404e-05, "epoch": 10.968646864686468, "percentage": 54.84, "elapsed_time": "3:55:34", "remaining_time": "3:13:57", "throughput": 1488.76, "total_tokens": 21042400} {"current_steps": 99710, "total_steps": 181800, "loss": 0.0738, "lr": 2.5134883151922094e-05, "epoch": 10.969196919691969, "percentage": 54.85, "elapsed_time": "3:55:34", "remaining_time": "3:13:57", "throughput": 1488.75, "total_tokens": 21043424} {"current_steps": 99715, "total_steps": 181800, "loss": 0.1163, "lr": 2.513248311850863e-05, "epoch": 10.96974697469747, "percentage": 54.85, "elapsed_time": "3:55:35", "remaining_time": "3:13:56", "throughput": 1488.76, "total_tokens": 21044512} {"current_steps": 99720, "total_steps": 181800, "loss": 0.0023, "lr": 2.513008308387414e-05, "epoch": 10.97029702970297, "percentage": 54.85, "elapsed_time": "3:55:36", "remaining_time": "3:13:55", "throughput": 1488.76, "total_tokens": 21045536} {"current_steps": 99725, "total_steps": 181800, "loss": 0.0081, "lr": 2.5127683048040724e-05, "epoch": 10.97084708470847, "percentage": 54.85, "elapsed_time": "3:55:36", "remaining_time": "3:13:54", "throughput": 1488.77, "total_tokens": 21046656} {"current_steps": 99730, "total_steps": 181800, "loss": 0.0024, "lr": 2.512528301103052e-05, "epoch": 10.971397139713972, "percentage": 54.86, "elapsed_time": "3:55:37", "remaining_time": "3:13:54", "throughput": 1488.75, "total_tokens": 21047712} {"current_steps": 99735, "total_steps": 181800, "loss": 0.1048, "lr": 2.5122882972865652e-05, "epoch": 10.971947194719473, "percentage": 54.86, "elapsed_time": "3:55:38", "remaining_time": "3:13:53", "throughput": 1488.75, "total_tokens": 21048800} {"current_steps": 99740, "total_steps": 181800, "loss": 0.0407, "lr": 2.5120482933568217e-05, "epoch": 10.972497249724972, "percentage": 54.86, "elapsed_time": "3:55:39", "remaining_time": "3:13:52", "throughput": 1488.75, "total_tokens": 21049824} {"current_steps": 99745, "total_steps": 181800, "loss": 0.0219, "lr": 2.5118082893160356e-05, "epoch": 10.973047304730473, "percentage": 54.87, "elapsed_time": "3:55:39", "remaining_time": "3:13:52", "throughput": 1488.75, "total_tokens": 21050848} {"current_steps": 99750, "total_steps": 181800, "loss": 0.0828, "lr": 2.511568285166418e-05, "epoch": 10.973597359735974, "percentage": 54.87, "elapsed_time": "3:55:40", "remaining_time": "3:13:51", "throughput": 1488.75, "total_tokens": 21051872} {"current_steps": 99755, "total_steps": 181800, "loss": 0.0189, "lr": 2.5113282809101805e-05, "epoch": 10.974147414741473, "percentage": 54.87, "elapsed_time": "3:55:41", "remaining_time": "3:13:50", "throughput": 1488.76, "total_tokens": 21052960} {"current_steps": 99760, "total_steps": 181800, "loss": 0.0353, "lr": 2.5110882765495368e-05, "epoch": 10.974697469746975, "percentage": 54.87, "elapsed_time": "3:55:42", "remaining_time": "3:13:50", "throughput": 1488.76, "total_tokens": 21054048} {"current_steps": 99765, "total_steps": 181800, "loss": 0.0202, "lr": 2.5108482720866972e-05, "epoch": 10.975247524752476, "percentage": 54.88, "elapsed_time": "3:55:42", "remaining_time": "3:13:49", "throughput": 1488.76, "total_tokens": 21055136} {"current_steps": 99770, "total_steps": 181800, "loss": 0.0683, "lr": 2.510608267523874e-05, "epoch": 10.975797579757975, "percentage": 54.88, "elapsed_time": "3:55:43", "remaining_time": "3:13:48", "throughput": 1488.77, "total_tokens": 21056224} {"current_steps": 99775, "total_steps": 181800, "loss": 0.0039, "lr": 2.5103682628632795e-05, "epoch": 10.976347634763476, "percentage": 54.88, "elapsed_time": "3:55:44", "remaining_time": "3:13:47", "throughput": 1488.77, "total_tokens": 21057248} {"current_steps": 99780, "total_steps": 181800, "loss": 0.0035, "lr": 2.510128258107126e-05, "epoch": 10.976897689768977, "percentage": 54.88, "elapsed_time": "3:55:44", "remaining_time": "3:13:47", "throughput": 1488.77, "total_tokens": 21058368} {"current_steps": 99785, "total_steps": 181800, "loss": 0.0141, "lr": 2.509888253257625e-05, "epoch": 10.977447744774478, "percentage": 54.89, "elapsed_time": "3:55:45", "remaining_time": "3:13:46", "throughput": 1488.77, "total_tokens": 21059360} {"current_steps": 99790, "total_steps": 181800, "loss": 0.003, "lr": 2.509648248316989e-05, "epoch": 10.977997799779978, "percentage": 54.89, "elapsed_time": "3:55:46", "remaining_time": "3:13:45", "throughput": 1488.78, "total_tokens": 21060448} {"current_steps": 99795, "total_steps": 181800, "loss": 0.004, "lr": 2.50940824328743e-05, "epoch": 10.978547854785479, "percentage": 54.89, "elapsed_time": "3:55:46", "remaining_time": "3:13:44", "throughput": 1488.78, "total_tokens": 21061504} {"current_steps": 99800, "total_steps": 181800, "loss": 0.0478, "lr": 2.509168238171159e-05, "epoch": 10.97909790979098, "percentage": 54.9, "elapsed_time": "3:55:47", "remaining_time": "3:13:44", "throughput": 1488.78, "total_tokens": 21062560} {"current_steps": 99805, "total_steps": 181800, "loss": 0.0349, "lr": 2.5089282329703896e-05, "epoch": 10.979647964796479, "percentage": 54.9, "elapsed_time": "3:55:48", "remaining_time": "3:13:43", "throughput": 1488.79, "total_tokens": 21063680} {"current_steps": 99810, "total_steps": 181800, "loss": 0.0057, "lr": 2.5086882276873318e-05, "epoch": 10.98019801980198, "percentage": 54.9, "elapsed_time": "3:55:48", "remaining_time": "3:13:42", "throughput": 1488.79, "total_tokens": 21064736} {"current_steps": 99815, "total_steps": 181800, "loss": 0.0047, "lr": 2.5084482223241995e-05, "epoch": 10.980748074807481, "percentage": 54.9, "elapsed_time": "3:55:49", "remaining_time": "3:13:42", "throughput": 1488.79, "total_tokens": 21065824} {"current_steps": 99820, "total_steps": 181800, "loss": 0.0204, "lr": 2.508208216883204e-05, "epoch": 10.98129812981298, "percentage": 54.91, "elapsed_time": "3:55:50", "remaining_time": "3:13:41", "throughput": 1488.79, "total_tokens": 21066816} {"current_steps": 99825, "total_steps": 181800, "loss": 0.0627, "lr": 2.507968211366557e-05, "epoch": 10.981848184818482, "percentage": 54.91, "elapsed_time": "3:55:50", "remaining_time": "3:13:40", "throughput": 1488.79, "total_tokens": 21067840} {"current_steps": 99830, "total_steps": 181800, "loss": 0.0066, "lr": 2.507728205776471e-05, "epoch": 10.982398239823983, "percentage": 54.91, "elapsed_time": "3:55:51", "remaining_time": "3:13:39", "throughput": 1488.79, "total_tokens": 21068928} {"current_steps": 99835, "total_steps": 181800, "loss": 0.006, "lr": 2.5074882001151586e-05, "epoch": 10.982948294829484, "percentage": 54.91, "elapsed_time": "3:55:52", "remaining_time": "3:13:39", "throughput": 1488.79, "total_tokens": 21069952} {"current_steps": 99840, "total_steps": 181800, "loss": 0.0141, "lr": 2.507248194384829e-05, "epoch": 10.983498349834983, "percentage": 54.92, "elapsed_time": "3:55:53", "remaining_time": "3:13:38", "throughput": 1488.79, "total_tokens": 21070976} {"current_steps": 99845, "total_steps": 181800, "loss": 0.0438, "lr": 2.5070081885876977e-05, "epoch": 10.984048404840484, "percentage": 54.92, "elapsed_time": "3:55:53", "remaining_time": "3:13:37", "throughput": 1488.8, "total_tokens": 21072096} {"current_steps": 99850, "total_steps": 181800, "loss": 0.0108, "lr": 2.5067681827259754e-05, "epoch": 10.984598459845985, "percentage": 54.92, "elapsed_time": "3:55:54", "remaining_time": "3:13:36", "throughput": 1488.8, "total_tokens": 21073184} {"current_steps": 99855, "total_steps": 181800, "loss": 0.0216, "lr": 2.506528176801874e-05, "epoch": 10.985148514851485, "percentage": 54.93, "elapsed_time": "3:55:55", "remaining_time": "3:13:36", "throughput": 1488.8, "total_tokens": 21074208} {"current_steps": 99860, "total_steps": 181800, "loss": 0.0344, "lr": 2.5062881708176056e-05, "epoch": 10.985698569856986, "percentage": 54.93, "elapsed_time": "3:55:55", "remaining_time": "3:13:35", "throughput": 1488.81, "total_tokens": 21075264} {"current_steps": 99865, "total_steps": 181800, "loss": 0.0582, "lr": 2.506048164775382e-05, "epoch": 10.986248624862487, "percentage": 54.93, "elapsed_time": "3:55:56", "remaining_time": "3:13:34", "throughput": 1488.81, "total_tokens": 21076352} {"current_steps": 99870, "total_steps": 181800, "loss": 0.0243, "lr": 2.5058081586774147e-05, "epoch": 10.986798679867986, "percentage": 54.93, "elapsed_time": "3:55:57", "remaining_time": "3:13:34", "throughput": 1488.81, "total_tokens": 21077408} {"current_steps": 99875, "total_steps": 181800, "loss": 0.0041, "lr": 2.5055681525259174e-05, "epoch": 10.987348734873487, "percentage": 54.94, "elapsed_time": "3:55:57", "remaining_time": "3:13:33", "throughput": 1488.81, "total_tokens": 21078464} {"current_steps": 99880, "total_steps": 181800, "loss": 0.0521, "lr": 2.5053281463231003e-05, "epoch": 10.987898789878988, "percentage": 54.94, "elapsed_time": "3:55:58", "remaining_time": "3:13:32", "throughput": 1488.82, "total_tokens": 21079584} {"current_steps": 99885, "total_steps": 181800, "loss": 0.0607, "lr": 2.505088140071176e-05, "epoch": 10.988448844884488, "percentage": 54.94, "elapsed_time": "3:55:59", "remaining_time": "3:13:31", "throughput": 1488.83, "total_tokens": 21080672} {"current_steps": 99890, "total_steps": 181800, "loss": 0.1301, "lr": 2.504848133772358e-05, "epoch": 10.988998899889989, "percentage": 54.94, "elapsed_time": "3:55:59", "remaining_time": "3:13:31", "throughput": 1488.83, "total_tokens": 21081824} {"current_steps": 99895, "total_steps": 181800, "loss": 0.0074, "lr": 2.5046081274288562e-05, "epoch": 10.98954895489549, "percentage": 54.95, "elapsed_time": "3:56:00", "remaining_time": "3:13:30", "throughput": 1488.83, "total_tokens": 21082848} {"current_steps": 99900, "total_steps": 181800, "loss": 0.0758, "lr": 2.504368121042884e-05, "epoch": 10.990099009900991, "percentage": 54.95, "elapsed_time": "3:56:01", "remaining_time": "3:13:29", "throughput": 1488.84, "total_tokens": 21083904} {"current_steps": 99905, "total_steps": 181800, "loss": 0.0048, "lr": 2.5041281146166524e-05, "epoch": 10.99064906490649, "percentage": 54.95, "elapsed_time": "3:56:02", "remaining_time": "3:13:29", "throughput": 1488.84, "total_tokens": 21084928} {"current_steps": 99910, "total_steps": 181800, "loss": 0.0565, "lr": 2.503888108152374e-05, "epoch": 10.991199119911991, "percentage": 54.96, "elapsed_time": "3:56:02", "remaining_time": "3:13:28", "throughput": 1488.84, "total_tokens": 21086016} {"current_steps": 99915, "total_steps": 181800, "loss": 0.0286, "lr": 2.5036481016522605e-05, "epoch": 10.991749174917492, "percentage": 54.96, "elapsed_time": "3:56:03", "remaining_time": "3:13:27", "throughput": 1488.84, "total_tokens": 21087040} {"current_steps": 99920, "total_steps": 181800, "loss": 0.0041, "lr": 2.5034080951185247e-05, "epoch": 10.992299229922992, "percentage": 54.96, "elapsed_time": "3:56:04", "remaining_time": "3:13:26", "throughput": 1488.84, "total_tokens": 21088064} {"current_steps": 99925, "total_steps": 181800, "loss": 0.0075, "lr": 2.503168088553378e-05, "epoch": 10.992849284928493, "percentage": 54.96, "elapsed_time": "3:56:04", "remaining_time": "3:13:26", "throughput": 1488.85, "total_tokens": 21089152} {"current_steps": 99930, "total_steps": 181800, "loss": 0.0158, "lr": 2.502928081959033e-05, "epoch": 10.993399339933994, "percentage": 54.97, "elapsed_time": "3:56:05", "remaining_time": "3:13:25", "throughput": 1488.85, "total_tokens": 21090240} {"current_steps": 99935, "total_steps": 181800, "loss": 0.0682, "lr": 2.5026880753377007e-05, "epoch": 10.993949394939493, "percentage": 54.97, "elapsed_time": "3:56:06", "remaining_time": "3:13:24", "throughput": 1488.85, "total_tokens": 21091296} {"current_steps": 99940, "total_steps": 181800, "loss": 0.0355, "lr": 2.502448068691594e-05, "epoch": 10.994499449944994, "percentage": 54.97, "elapsed_time": "3:56:06", "remaining_time": "3:13:23", "throughput": 1488.86, "total_tokens": 21092416} {"current_steps": 99945, "total_steps": 181800, "loss": 0.009, "lr": 2.5022080620229238e-05, "epoch": 10.995049504950495, "percentage": 54.98, "elapsed_time": "3:56:07", "remaining_time": "3:13:23", "throughput": 1488.86, "total_tokens": 21093472} {"current_steps": 99950, "total_steps": 181800, "loss": 0.003, "lr": 2.501968055333904e-05, "epoch": 10.995599559955995, "percentage": 54.98, "elapsed_time": "3:56:08", "remaining_time": "3:13:22", "throughput": 1488.86, "total_tokens": 21094432} {"current_steps": 99955, "total_steps": 181800, "loss": 0.003, "lr": 2.5017280486267453e-05, "epoch": 10.996149614961496, "percentage": 54.98, "elapsed_time": "3:56:08", "remaining_time": "3:13:21", "throughput": 1488.87, "total_tokens": 21095552} {"current_steps": 99960, "total_steps": 181800, "loss": 0.0114, "lr": 2.5014880419036596e-05, "epoch": 10.996699669966997, "percentage": 54.98, "elapsed_time": "3:56:09", "remaining_time": "3:13:21", "throughput": 1488.87, "total_tokens": 21096576} {"current_steps": 99965, "total_steps": 181800, "loss": 0.0012, "lr": 2.5012480351668598e-05, "epoch": 10.997249724972498, "percentage": 54.99, "elapsed_time": "3:56:10", "remaining_time": "3:13:20", "throughput": 1488.87, "total_tokens": 21097696} {"current_steps": 99970, "total_steps": 181800, "loss": 0.0016, "lr": 2.5010080284185576e-05, "epoch": 10.997799779977997, "percentage": 54.99, "elapsed_time": "3:56:10", "remaining_time": "3:13:19", "throughput": 1488.88, "total_tokens": 21098784} {"current_steps": 99975, "total_steps": 181800, "loss": 0.0035, "lr": 2.5007680216609648e-05, "epoch": 10.998349834983498, "percentage": 54.99, "elapsed_time": "3:56:11", "remaining_time": "3:13:18", "throughput": 1488.88, "total_tokens": 21099840} {"current_steps": 99980, "total_steps": 181800, "loss": 0.0158, "lr": 2.5005280148962936e-05, "epoch": 10.998899889989, "percentage": 54.99, "elapsed_time": "3:56:12", "remaining_time": "3:13:18", "throughput": 1488.88, "total_tokens": 21100864} {"current_steps": 99985, "total_steps": 181800, "loss": 0.0078, "lr": 2.500288008126755e-05, "epoch": 10.999449944994499, "percentage": 55.0, "elapsed_time": "3:56:12", "remaining_time": "3:13:17", "throughput": 1488.88, "total_tokens": 21101952} {"current_steps": 99990, "total_steps": 181800, "loss": 0.0033, "lr": 2.5000480013545623e-05, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "3:56:13", "remaining_time": "3:13:16", "throughput": 1488.88, "total_tokens": 21102912} {"current_steps": 99990, "total_steps": 181800, "eval_loss": 0.068524569272995, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "3:56:50", "remaining_time": "3:13:46", "throughput": 1485.0, "total_tokens": 21102912} {"current_steps": 99995, "total_steps": 181800, "loss": 0.0948, "lr": 2.499807994581928e-05, "epoch": 11.000550055005501, "percentage": 55.0, "elapsed_time": "3:56:53", "remaining_time": "3:13:47", "throughput": 1484.83, "total_tokens": 21103936} {"current_steps": 100000, "total_steps": 181800, "loss": 0.0196, "lr": 2.4995679878110625e-05, "epoch": 11.001100110011, "percentage": 55.01, "elapsed_time": "3:56:53", "remaining_time": "3:13:46", "throughput": 1484.83, "total_tokens": 21105024} {"current_steps": 100005, "total_steps": 181800, "loss": 0.0036, "lr": 2.4993279810441787e-05, "epoch": 11.001650165016502, "percentage": 55.01, "elapsed_time": "3:56:54", "remaining_time": "3:13:46", "throughput": 1484.83, "total_tokens": 21106016} {"current_steps": 100010, "total_steps": 181800, "loss": 0.0193, "lr": 2.4990879742834895e-05, "epoch": 11.002200220022003, "percentage": 55.01, "elapsed_time": "3:56:55", "remaining_time": "3:13:45", "throughput": 1484.83, "total_tokens": 21107136} {"current_steps": 100015, "total_steps": 181800, "loss": 0.0019, "lr": 2.4988479675312053e-05, "epoch": 11.002750275027502, "percentage": 55.01, "elapsed_time": "3:56:55", "remaining_time": "3:13:44", "throughput": 1484.83, "total_tokens": 21108192} {"current_steps": 100020, "total_steps": 181800, "loss": 0.0471, "lr": 2.4986079607895384e-05, "epoch": 11.003300330033003, "percentage": 55.02, "elapsed_time": "3:56:56", "remaining_time": "3:13:43", "throughput": 1484.84, "total_tokens": 21109248} {"current_steps": 100025, "total_steps": 181800, "loss": 0.0908, "lr": 2.4983679540607024e-05, "epoch": 11.003850385038504, "percentage": 55.02, "elapsed_time": "3:56:57", "remaining_time": "3:13:43", "throughput": 1484.84, "total_tokens": 21110368} {"current_steps": 100030, "total_steps": 181800, "loss": 0.0608, "lr": 2.4981279473469076e-05, "epoch": 11.004400440044005, "percentage": 55.02, "elapsed_time": "3:56:57", "remaining_time": "3:13:42", "throughput": 1484.84, "total_tokens": 21111392} {"current_steps": 100035, "total_steps": 181800, "loss": 0.0836, "lr": 2.497887940650366e-05, "epoch": 11.004950495049505, "percentage": 55.02, "elapsed_time": "3:56:58", "remaining_time": "3:13:41", "throughput": 1484.85, "total_tokens": 21112512} {"current_steps": 100040, "total_steps": 181800, "loss": 0.0231, "lr": 2.4976479339732914e-05, "epoch": 11.005500550055006, "percentage": 55.03, "elapsed_time": "3:56:59", "remaining_time": "3:13:41", "throughput": 1484.84, "total_tokens": 21113632} {"current_steps": 100045, "total_steps": 181800, "loss": 0.0012, "lr": 2.4974079273178928e-05, "epoch": 11.006050605060507, "percentage": 55.03, "elapsed_time": "3:57:00", "remaining_time": "3:13:40", "throughput": 1484.84, "total_tokens": 21114720} {"current_steps": 100050, "total_steps": 181800, "loss": 0.0088, "lr": 2.4971679206863863e-05, "epoch": 11.006600660066006, "percentage": 55.03, "elapsed_time": "3:57:00", "remaining_time": "3:13:39", "throughput": 1484.84, "total_tokens": 21115776} {"current_steps": 100055, "total_steps": 181800, "loss": 0.0633, "lr": 2.4969279140809806e-05, "epoch": 11.007150715071507, "percentage": 55.04, "elapsed_time": "3:57:01", "remaining_time": "3:13:39", "throughput": 1484.84, "total_tokens": 21116864} {"current_steps": 100060, "total_steps": 181800, "loss": 0.0883, "lr": 2.496687907503889e-05, "epoch": 11.007700770077008, "percentage": 55.04, "elapsed_time": "3:57:02", "remaining_time": "3:13:38", "throughput": 1484.85, "total_tokens": 21117952} {"current_steps": 100065, "total_steps": 181800, "loss": 0.01, "lr": 2.4964479009573235e-05, "epoch": 11.008250825082508, "percentage": 55.04, "elapsed_time": "3:57:03", "remaining_time": "3:13:37", "throughput": 1484.85, "total_tokens": 21119008} {"current_steps": 100070, "total_steps": 181800, "loss": 0.0135, "lr": 2.4962078944434956e-05, "epoch": 11.008800880088009, "percentage": 55.04, "elapsed_time": "3:57:03", "remaining_time": "3:13:36", "throughput": 1484.85, "total_tokens": 21120032} {"current_steps": 100075, "total_steps": 181800, "loss": 0.0016, "lr": 2.495967887964618e-05, "epoch": 11.00935093509351, "percentage": 55.05, "elapsed_time": "3:57:04", "remaining_time": "3:13:36", "throughput": 1484.85, "total_tokens": 21121120} {"current_steps": 100080, "total_steps": 181800, "loss": 0.1091, "lr": 2.495727881522903e-05, "epoch": 11.009900990099009, "percentage": 55.05, "elapsed_time": "3:57:05", "remaining_time": "3:13:35", "throughput": 1484.85, "total_tokens": 21122176} {"current_steps": 100085, "total_steps": 181800, "loss": 0.057, "lr": 2.495487875120561e-05, "epoch": 11.01045104510451, "percentage": 55.05, "elapsed_time": "3:57:05", "remaining_time": "3:13:34", "throughput": 1484.85, "total_tokens": 21123168} {"current_steps": 100090, "total_steps": 181800, "loss": 0.0116, "lr": 2.4952478687598055e-05, "epoch": 11.011001100110011, "percentage": 55.06, "elapsed_time": "3:57:06", "remaining_time": "3:13:33", "throughput": 1484.85, "total_tokens": 21124192} {"current_steps": 100095, "total_steps": 181800, "loss": 0.0126, "lr": 2.4950078624428477e-05, "epoch": 11.011551155115512, "percentage": 55.06, "elapsed_time": "3:57:07", "remaining_time": "3:13:33", "throughput": 1484.86, "total_tokens": 21125280} {"current_steps": 100100, "total_steps": 181800, "loss": 0.0021, "lr": 2.4947678561719008e-05, "epoch": 11.012101210121012, "percentage": 55.06, "elapsed_time": "3:57:07", "remaining_time": "3:13:32", "throughput": 1484.86, "total_tokens": 21126336} {"current_steps": 100105, "total_steps": 181800, "loss": 0.0054, "lr": 2.494527849949176e-05, "epoch": 11.012651265126513, "percentage": 55.06, "elapsed_time": "3:57:08", "remaining_time": "3:13:31", "throughput": 1484.86, "total_tokens": 21127360} {"current_steps": 100110, "total_steps": 181800, "loss": 0.0047, "lr": 2.4942878437768848e-05, "epoch": 11.013201320132014, "percentage": 55.07, "elapsed_time": "3:57:09", "remaining_time": "3:13:31", "throughput": 1484.86, "total_tokens": 21128480} {"current_steps": 100115, "total_steps": 181800, "loss": 0.0142, "lr": 2.4940478376572403e-05, "epoch": 11.013751375137513, "percentage": 55.07, "elapsed_time": "3:57:09", "remaining_time": "3:13:30", "throughput": 1484.87, "total_tokens": 21129664} {"current_steps": 100120, "total_steps": 181800, "loss": 0.0081, "lr": 2.4938078315924533e-05, "epoch": 11.014301430143014, "percentage": 55.07, "elapsed_time": "3:57:10", "remaining_time": "3:13:29", "throughput": 1484.88, "total_tokens": 21130720} {"current_steps": 100125, "total_steps": 181800, "loss": 0.0968, "lr": 2.493567825584738e-05, "epoch": 11.014851485148515, "percentage": 55.07, "elapsed_time": "3:57:11", "remaining_time": "3:13:28", "throughput": 1484.87, "total_tokens": 21131712} {"current_steps": 100130, "total_steps": 181800, "loss": 0.0123, "lr": 2.493327819636304e-05, "epoch": 11.015401540154015, "percentage": 55.08, "elapsed_time": "3:57:12", "remaining_time": "3:13:28", "throughput": 1484.87, "total_tokens": 21132736} {"current_steps": 100135, "total_steps": 181800, "loss": 0.0398, "lr": 2.493087813749364e-05, "epoch": 11.015951595159516, "percentage": 55.08, "elapsed_time": "3:57:12", "remaining_time": "3:13:27", "throughput": 1484.88, "total_tokens": 21133824} {"current_steps": 100140, "total_steps": 181800, "loss": 0.0228, "lr": 2.4928478079261315e-05, "epoch": 11.016501650165017, "percentage": 55.08, "elapsed_time": "3:57:13", "remaining_time": "3:13:26", "throughput": 1484.88, "total_tokens": 21134848} {"current_steps": 100145, "total_steps": 181800, "loss": 0.0506, "lr": 2.4926078021688158e-05, "epoch": 11.017051705170518, "percentage": 55.09, "elapsed_time": "3:57:14", "remaining_time": "3:13:26", "throughput": 1484.88, "total_tokens": 21135936} {"current_steps": 100150, "total_steps": 181800, "loss": 0.0167, "lr": 2.4923677964796314e-05, "epoch": 11.017601760176017, "percentage": 55.09, "elapsed_time": "3:57:14", "remaining_time": "3:13:25", "throughput": 1484.89, "total_tokens": 21137024} {"current_steps": 100155, "total_steps": 181800, "loss": 0.0324, "lr": 2.4921277908607894e-05, "epoch": 11.018151815181518, "percentage": 55.09, "elapsed_time": "3:57:15", "remaining_time": "3:13:24", "throughput": 1484.89, "total_tokens": 21138080} {"current_steps": 100160, "total_steps": 181800, "loss": 0.002, "lr": 2.4918877853145005e-05, "epoch": 11.01870187018702, "percentage": 55.09, "elapsed_time": "3:57:16", "remaining_time": "3:13:23", "throughput": 1484.89, "total_tokens": 21139136} {"current_steps": 100165, "total_steps": 181800, "loss": 0.0164, "lr": 2.4916477798429795e-05, "epoch": 11.019251925192519, "percentage": 55.1, "elapsed_time": "3:57:16", "remaining_time": "3:13:23", "throughput": 1484.89, "total_tokens": 21140192} {"current_steps": 100170, "total_steps": 181800, "loss": 0.0848, "lr": 2.491407774448436e-05, "epoch": 11.01980198019802, "percentage": 55.1, "elapsed_time": "3:57:17", "remaining_time": "3:13:22", "throughput": 1484.89, "total_tokens": 21141184} {"current_steps": 100175, "total_steps": 181800, "loss": 0.0103, "lr": 2.4911677691330834e-05, "epoch": 11.020352035203521, "percentage": 55.1, "elapsed_time": "3:57:18", "remaining_time": "3:13:21", "throughput": 1484.89, "total_tokens": 21142208} {"current_steps": 100180, "total_steps": 181800, "loss": 0.0139, "lr": 2.4909277638991338e-05, "epoch": 11.02090209020902, "percentage": 55.1, "elapsed_time": "3:57:18", "remaining_time": "3:13:20", "throughput": 1484.89, "total_tokens": 21143232} {"current_steps": 100185, "total_steps": 181800, "loss": 0.0049, "lr": 2.4906877587487975e-05, "epoch": 11.021452145214521, "percentage": 55.11, "elapsed_time": "3:57:19", "remaining_time": "3:13:20", "throughput": 1484.89, "total_tokens": 21144288} {"current_steps": 100190, "total_steps": 181800, "loss": 0.0825, "lr": 2.490447753684288e-05, "epoch": 11.022002200220022, "percentage": 55.11, "elapsed_time": "3:57:20", "remaining_time": "3:13:19", "throughput": 1484.89, "total_tokens": 21145280} {"current_steps": 100195, "total_steps": 181800, "loss": 0.0479, "lr": 2.490207748707817e-05, "epoch": 11.022552255225522, "percentage": 55.11, "elapsed_time": "3:57:20", "remaining_time": "3:13:18", "throughput": 1484.89, "total_tokens": 21146272} {"current_steps": 100200, "total_steps": 181800, "loss": 0.2457, "lr": 2.489967743821597e-05, "epoch": 11.023102310231023, "percentage": 55.12, "elapsed_time": "3:57:21", "remaining_time": "3:13:18", "throughput": 1484.89, "total_tokens": 21147360} {"current_steps": 100205, "total_steps": 181800, "loss": 0.0009, "lr": 2.4897277390278393e-05, "epoch": 11.023652365236524, "percentage": 55.12, "elapsed_time": "3:57:22", "remaining_time": "3:13:17", "throughput": 1484.89, "total_tokens": 21148384} {"current_steps": 100210, "total_steps": 181800, "loss": 0.0053, "lr": 2.4894877343287554e-05, "epoch": 11.024202420242025, "percentage": 55.12, "elapsed_time": "3:57:23", "remaining_time": "3:13:16", "throughput": 1484.89, "total_tokens": 21149408} {"current_steps": 100215, "total_steps": 181800, "loss": 0.0029, "lr": 2.489247729726559e-05, "epoch": 11.024752475247524, "percentage": 55.12, "elapsed_time": "3:57:23", "remaining_time": "3:13:15", "throughput": 1484.9, "total_tokens": 21150528} {"current_steps": 100220, "total_steps": 181800, "loss": 0.0115, "lr": 2.4890077252234605e-05, "epoch": 11.025302530253025, "percentage": 55.13, "elapsed_time": "3:57:24", "remaining_time": "3:13:15", "throughput": 1484.9, "total_tokens": 21151552} {"current_steps": 100225, "total_steps": 181800, "loss": 0.0178, "lr": 2.4887677208216724e-05, "epoch": 11.025852585258527, "percentage": 55.13, "elapsed_time": "3:57:25", "remaining_time": "3:13:14", "throughput": 1484.9, "total_tokens": 21152576} {"current_steps": 100230, "total_steps": 181800, "loss": 0.1176, "lr": 2.488527716523407e-05, "epoch": 11.026402640264026, "percentage": 55.13, "elapsed_time": "3:57:25", "remaining_time": "3:13:13", "throughput": 1484.9, "total_tokens": 21153600} {"current_steps": 100235, "total_steps": 181800, "loss": 0.0385, "lr": 2.4882877123308755e-05, "epoch": 11.026952695269527, "percentage": 55.13, "elapsed_time": "3:57:26", "remaining_time": "3:13:12", "throughput": 1484.9, "total_tokens": 21154688} {"current_steps": 100240, "total_steps": 181800, "loss": 0.012, "lr": 2.4880477082462924e-05, "epoch": 11.027502750275028, "percentage": 55.14, "elapsed_time": "3:57:27", "remaining_time": "3:13:12", "throughput": 1484.9, "total_tokens": 21155744} {"current_steps": 100245, "total_steps": 181800, "loss": 0.1621, "lr": 2.4878077042718665e-05, "epoch": 11.028052805280527, "percentage": 55.14, "elapsed_time": "3:57:27", "remaining_time": "3:13:11", "throughput": 1484.91, "total_tokens": 21156800} {"current_steps": 100250, "total_steps": 181800, "loss": 0.0055, "lr": 2.4875677004098108e-05, "epoch": 11.028602860286028, "percentage": 55.14, "elapsed_time": "3:57:28", "remaining_time": "3:13:10", "throughput": 1484.91, "total_tokens": 21157856} {"current_steps": 100255, "total_steps": 181800, "loss": 0.0443, "lr": 2.4873276966623387e-05, "epoch": 11.02915291529153, "percentage": 55.15, "elapsed_time": "3:57:29", "remaining_time": "3:13:10", "throughput": 1484.91, "total_tokens": 21158816} {"current_steps": 100260, "total_steps": 181800, "loss": 0.0183, "lr": 2.48708769303166e-05, "epoch": 11.029702970297029, "percentage": 55.15, "elapsed_time": "3:57:29", "remaining_time": "3:13:09", "throughput": 1484.91, "total_tokens": 21159872} {"current_steps": 100265, "total_steps": 181800, "loss": 0.011, "lr": 2.4868476895199884e-05, "epoch": 11.03025302530253, "percentage": 55.15, "elapsed_time": "3:57:30", "remaining_time": "3:13:08", "throughput": 1484.9, "total_tokens": 21160832} {"current_steps": 100270, "total_steps": 181800, "loss": 0.016, "lr": 2.4866076861295363e-05, "epoch": 11.030803080308031, "percentage": 55.15, "elapsed_time": "3:57:31", "remaining_time": "3:13:07", "throughput": 1484.91, "total_tokens": 21161952} {"current_steps": 100275, "total_steps": 181800, "loss": 0.005, "lr": 2.486367682862513e-05, "epoch": 11.031353135313532, "percentage": 55.16, "elapsed_time": "3:57:32", "remaining_time": "3:13:07", "throughput": 1484.91, "total_tokens": 21163040} {"current_steps": 100280, "total_steps": 181800, "loss": 0.028, "lr": 2.486127679721133e-05, "epoch": 11.031903190319031, "percentage": 55.16, "elapsed_time": "3:57:32", "remaining_time": "3:13:06", "throughput": 1484.92, "total_tokens": 21164128} {"current_steps": 100285, "total_steps": 181800, "loss": 0.1056, "lr": 2.4858876767076074e-05, "epoch": 11.032453245324533, "percentage": 55.16, "elapsed_time": "3:57:33", "remaining_time": "3:13:05", "throughput": 1484.92, "total_tokens": 21165184} {"current_steps": 100290, "total_steps": 181800, "loss": 0.0245, "lr": 2.485647673824148e-05, "epoch": 11.033003300330034, "percentage": 55.17, "elapsed_time": "3:57:34", "remaining_time": "3:13:04", "throughput": 1484.93, "total_tokens": 21166304} {"current_steps": 100295, "total_steps": 181800, "loss": 0.0333, "lr": 2.4854076710729684e-05, "epoch": 11.033553355335533, "percentage": 55.17, "elapsed_time": "3:57:34", "remaining_time": "3:13:04", "throughput": 1484.93, "total_tokens": 21167296} {"current_steps": 100300, "total_steps": 181800, "loss": 0.0446, "lr": 2.485167668456278e-05, "epoch": 11.034103410341034, "percentage": 55.17, "elapsed_time": "3:57:35", "remaining_time": "3:13:03", "throughput": 1484.93, "total_tokens": 21168416} {"current_steps": 100305, "total_steps": 181800, "loss": 0.0353, "lr": 2.4849276659762904e-05, "epoch": 11.034653465346535, "percentage": 55.17, "elapsed_time": "3:57:36", "remaining_time": "3:13:02", "throughput": 1484.93, "total_tokens": 21169408} {"current_steps": 100310, "total_steps": 181800, "loss": 0.0359, "lr": 2.484687663635217e-05, "epoch": 11.035203520352034, "percentage": 55.18, "elapsed_time": "3:57:36", "remaining_time": "3:13:02", "throughput": 1484.93, "total_tokens": 21170496} {"current_steps": 100315, "total_steps": 181800, "loss": 0.0062, "lr": 2.484447661435271e-05, "epoch": 11.035753575357536, "percentage": 55.18, "elapsed_time": "3:57:37", "remaining_time": "3:13:01", "throughput": 1484.94, "total_tokens": 21171648} {"current_steps": 100320, "total_steps": 181800, "loss": 0.0243, "lr": 2.4842076593786632e-05, "epoch": 11.036303630363037, "percentage": 55.18, "elapsed_time": "3:57:38", "remaining_time": "3:13:00", "throughput": 1484.95, "total_tokens": 21172800} {"current_steps": 100325, "total_steps": 181800, "loss": 0.0028, "lr": 2.483967657467605e-05, "epoch": 11.036853685368538, "percentage": 55.18, "elapsed_time": "3:57:38", "remaining_time": "3:12:59", "throughput": 1484.96, "total_tokens": 21173856} {"current_steps": 100330, "total_steps": 181800, "loss": 0.0022, "lr": 2.48372765570431e-05, "epoch": 11.037403740374037, "percentage": 55.19, "elapsed_time": "3:57:39", "remaining_time": "3:12:59", "throughput": 1484.95, "total_tokens": 21174848} {"current_steps": 100335, "total_steps": 181800, "loss": 0.0061, "lr": 2.4834876540909886e-05, "epoch": 11.037953795379538, "percentage": 55.19, "elapsed_time": "3:57:40", "remaining_time": "3:12:58", "throughput": 1484.96, "total_tokens": 21176000} {"current_steps": 100340, "total_steps": 181800, "loss": 0.0303, "lr": 2.4832476526298546e-05, "epoch": 11.03850385038504, "percentage": 55.19, "elapsed_time": "3:57:40", "remaining_time": "3:12:57", "throughput": 1484.97, "total_tokens": 21177120} {"current_steps": 100345, "total_steps": 181800, "loss": 0.0211, "lr": 2.4830076513231184e-05, "epoch": 11.039053905390539, "percentage": 55.2, "elapsed_time": "3:57:41", "remaining_time": "3:12:56", "throughput": 1484.97, "total_tokens": 21178208} {"current_steps": 100350, "total_steps": 181800, "loss": 0.0036, "lr": 2.4827676501729918e-05, "epoch": 11.03960396039604, "percentage": 55.2, "elapsed_time": "3:57:42", "remaining_time": "3:12:56", "throughput": 1484.97, "total_tokens": 21179232} {"current_steps": 100355, "total_steps": 181800, "loss": 0.0034, "lr": 2.482527649181689e-05, "epoch": 11.04015401540154, "percentage": 55.2, "elapsed_time": "3:57:43", "remaining_time": "3:12:55", "throughput": 1484.98, "total_tokens": 21180288} {"current_steps": 100360, "total_steps": 181800, "loss": 0.0274, "lr": 2.4822876483514193e-05, "epoch": 11.04070407040704, "percentage": 55.2, "elapsed_time": "3:57:43", "remaining_time": "3:12:54", "throughput": 1484.98, "total_tokens": 21181312} {"current_steps": 100365, "total_steps": 181800, "loss": 0.0055, "lr": 2.4820476476843962e-05, "epoch": 11.041254125412541, "percentage": 55.21, "elapsed_time": "3:57:44", "remaining_time": "3:12:53", "throughput": 1484.98, "total_tokens": 21182432} {"current_steps": 100370, "total_steps": 181800, "loss": 0.005, "lr": 2.4818076471828322e-05, "epoch": 11.041804180418042, "percentage": 55.21, "elapsed_time": "3:57:45", "remaining_time": "3:12:53", "throughput": 1484.98, "total_tokens": 21183456} {"current_steps": 100375, "total_steps": 181800, "loss": 0.0104, "lr": 2.481567646848937e-05, "epoch": 11.042354235423542, "percentage": 55.21, "elapsed_time": "3:57:45", "remaining_time": "3:12:52", "throughput": 1484.99, "total_tokens": 21184544} {"current_steps": 100380, "total_steps": 181800, "loss": 0.0063, "lr": 2.4813276466849245e-05, "epoch": 11.042904290429043, "percentage": 55.21, "elapsed_time": "3:57:46", "remaining_time": "3:12:51", "throughput": 1484.99, "total_tokens": 21185664} {"current_steps": 100385, "total_steps": 181800, "loss": 0.0979, "lr": 2.4810876466930057e-05, "epoch": 11.043454345434544, "percentage": 55.22, "elapsed_time": "3:57:47", "remaining_time": "3:12:51", "throughput": 1485.0, "total_tokens": 21186720} {"current_steps": 100390, "total_steps": 181800, "loss": 0.0036, "lr": 2.480847646875394e-05, "epoch": 11.044004400440045, "percentage": 55.22, "elapsed_time": "3:57:47", "remaining_time": "3:12:50", "throughput": 1485.0, "total_tokens": 21187776} {"current_steps": 100395, "total_steps": 181800, "loss": 0.0027, "lr": 2.4806076472342997e-05, "epoch": 11.044554455445544, "percentage": 55.22, "elapsed_time": "3:57:48", "remaining_time": "3:12:49", "throughput": 1485.0, "total_tokens": 21188832} {"current_steps": 100400, "total_steps": 181800, "loss": 0.142, "lr": 2.4803676477719354e-05, "epoch": 11.045104510451045, "percentage": 55.23, "elapsed_time": "3:57:49", "remaining_time": "3:12:48", "throughput": 1485.0, "total_tokens": 21189856} {"current_steps": 100405, "total_steps": 181800, "loss": 0.1376, "lr": 2.4801276484905132e-05, "epoch": 11.045654565456546, "percentage": 55.23, "elapsed_time": "3:57:49", "remaining_time": "3:12:48", "throughput": 1485.0, "total_tokens": 21190816} {"current_steps": 100410, "total_steps": 181800, "loss": 0.0478, "lr": 2.4798876493922454e-05, "epoch": 11.046204620462046, "percentage": 55.23, "elapsed_time": "3:57:50", "remaining_time": "3:12:47", "throughput": 1485.0, "total_tokens": 21191840} {"current_steps": 100415, "total_steps": 181800, "loss": 0.0182, "lr": 2.4796476504793425e-05, "epoch": 11.046754675467547, "percentage": 55.23, "elapsed_time": "3:57:51", "remaining_time": "3:12:46", "throughput": 1484.99, "total_tokens": 21192832} {"current_steps": 100420, "total_steps": 181800, "loss": 0.0469, "lr": 2.4794076517540178e-05, "epoch": 11.047304730473048, "percentage": 55.24, "elapsed_time": "3:57:52", "remaining_time": "3:12:45", "throughput": 1484.99, "total_tokens": 21193856} {"current_steps": 100425, "total_steps": 181800, "loss": 0.0267, "lr": 2.4791676532184827e-05, "epoch": 11.047854785478547, "percentage": 55.24, "elapsed_time": "3:57:52", "remaining_time": "3:12:45", "throughput": 1485.0, "total_tokens": 21194912} {"current_steps": 100430, "total_steps": 181800, "loss": 0.0639, "lr": 2.4789276548749503e-05, "epoch": 11.048404840484048, "percentage": 55.24, "elapsed_time": "3:57:53", "remaining_time": "3:12:44", "throughput": 1485.0, "total_tokens": 21195936} {"current_steps": 100435, "total_steps": 181800, "loss": 0.137, "lr": 2.478687656725631e-05, "epoch": 11.04895489548955, "percentage": 55.24, "elapsed_time": "3:57:54", "remaining_time": "3:12:43", "throughput": 1485.0, "total_tokens": 21196960} {"current_steps": 100440, "total_steps": 181800, "loss": 0.1276, "lr": 2.4784476587727367e-05, "epoch": 11.049504950495049, "percentage": 55.25, "elapsed_time": "3:57:54", "remaining_time": "3:12:43", "throughput": 1485.0, "total_tokens": 21198048} {"current_steps": 100445, "total_steps": 181800, "loss": 0.0098, "lr": 2.478207661018481e-05, "epoch": 11.05005500550055, "percentage": 55.25, "elapsed_time": "3:57:55", "remaining_time": "3:12:42", "throughput": 1485.0, "total_tokens": 21199104} {"current_steps": 100450, "total_steps": 181800, "loss": 0.0485, "lr": 2.4779676634650742e-05, "epoch": 11.05060506050605, "percentage": 55.25, "elapsed_time": "3:57:56", "remaining_time": "3:12:41", "throughput": 1485.01, "total_tokens": 21200192} {"current_steps": 100455, "total_steps": 181800, "loss": 0.1227, "lr": 2.4777276661147293e-05, "epoch": 11.051155115511552, "percentage": 55.26, "elapsed_time": "3:57:56", "remaining_time": "3:12:40", "throughput": 1485.01, "total_tokens": 21201312} {"current_steps": 100460, "total_steps": 181800, "loss": 0.0586, "lr": 2.477487668969658e-05, "epoch": 11.051705170517051, "percentage": 55.26, "elapsed_time": "3:57:57", "remaining_time": "3:12:40", "throughput": 1485.02, "total_tokens": 21202400} {"current_steps": 100465, "total_steps": 181800, "loss": 0.0016, "lr": 2.4772476720320706e-05, "epoch": 11.052255225522552, "percentage": 55.26, "elapsed_time": "3:57:58", "remaining_time": "3:12:39", "throughput": 1485.02, "total_tokens": 21203456} {"current_steps": 100470, "total_steps": 181800, "loss": 0.0056, "lr": 2.477007675304182e-05, "epoch": 11.052805280528053, "percentage": 55.26, "elapsed_time": "3:57:58", "remaining_time": "3:12:38", "throughput": 1485.02, "total_tokens": 21204512} {"current_steps": 100475, "total_steps": 181800, "loss": 0.0579, "lr": 2.476767678788202e-05, "epoch": 11.053355335533553, "percentage": 55.27, "elapsed_time": "3:57:59", "remaining_time": "3:12:37", "throughput": 1485.02, "total_tokens": 21205536} {"current_steps": 100480, "total_steps": 181800, "loss": 0.0091, "lr": 2.476527682486343e-05, "epoch": 11.053905390539054, "percentage": 55.27, "elapsed_time": "3:58:00", "remaining_time": "3:12:37", "throughput": 1485.03, "total_tokens": 21206656} {"current_steps": 100485, "total_steps": 181800, "loss": 0.0077, "lr": 2.4762876864008183e-05, "epoch": 11.054455445544555, "percentage": 55.27, "elapsed_time": "3:58:00", "remaining_time": "3:12:36", "throughput": 1485.04, "total_tokens": 21207776} {"current_steps": 100490, "total_steps": 181800, "loss": 0.0048, "lr": 2.476047690533837e-05, "epoch": 11.055005500550054, "percentage": 55.28, "elapsed_time": "3:58:01", "remaining_time": "3:12:35", "throughput": 1485.04, "total_tokens": 21208832} {"current_steps": 100495, "total_steps": 181800, "loss": 0.0164, "lr": 2.4758076948876137e-05, "epoch": 11.055555555555555, "percentage": 55.28, "elapsed_time": "3:58:02", "remaining_time": "3:12:35", "throughput": 1485.04, "total_tokens": 21209920} {"current_steps": 100500, "total_steps": 181800, "loss": 0.0516, "lr": 2.4755676994643585e-05, "epoch": 11.056105610561056, "percentage": 55.28, "elapsed_time": "3:58:03", "remaining_time": "3:12:34", "throughput": 1485.04, "total_tokens": 21210976} {"current_steps": 100505, "total_steps": 181800, "loss": 0.0117, "lr": 2.475327704266285e-05, "epoch": 11.056655665566556, "percentage": 55.28, "elapsed_time": "3:58:03", "remaining_time": "3:12:33", "throughput": 1485.05, "total_tokens": 21212064} {"current_steps": 100510, "total_steps": 181800, "loss": 0.0297, "lr": 2.4750877092956036e-05, "epoch": 11.057205720572057, "percentage": 55.29, "elapsed_time": "3:58:04", "remaining_time": "3:12:32", "throughput": 1485.05, "total_tokens": 21213088} {"current_steps": 100515, "total_steps": 181800, "loss": 0.0009, "lr": 2.4748477145545264e-05, "epoch": 11.057755775577558, "percentage": 55.29, "elapsed_time": "3:58:05", "remaining_time": "3:12:32", "throughput": 1485.05, "total_tokens": 21214144} {"current_steps": 100520, "total_steps": 181800, "loss": 0.0189, "lr": 2.4746077200452672e-05, "epoch": 11.058305830583059, "percentage": 55.29, "elapsed_time": "3:58:05", "remaining_time": "3:12:31", "throughput": 1485.05, "total_tokens": 21215168} {"current_steps": 100525, "total_steps": 181800, "loss": 0.0032, "lr": 2.4743677257700347e-05, "epoch": 11.058855885588558, "percentage": 55.29, "elapsed_time": "3:58:06", "remaining_time": "3:12:30", "throughput": 1485.06, "total_tokens": 21216256} {"current_steps": 100530, "total_steps": 181800, "loss": 0.1397, "lr": 2.4741277317310438e-05, "epoch": 11.05940594059406, "percentage": 55.3, "elapsed_time": "3:58:07", "remaining_time": "3:12:29", "throughput": 1485.06, "total_tokens": 21217280} {"current_steps": 100535, "total_steps": 181800, "loss": 0.0052, "lr": 2.473887737930505e-05, "epoch": 11.05995599559956, "percentage": 55.3, "elapsed_time": "3:58:07", "remaining_time": "3:12:29", "throughput": 1485.06, "total_tokens": 21218336} {"current_steps": 100540, "total_steps": 181800, "loss": 0.0209, "lr": 2.4736477443706297e-05, "epoch": 11.06050605060506, "percentage": 55.3, "elapsed_time": "3:58:08", "remaining_time": "3:12:28", "throughput": 1485.06, "total_tokens": 21219424} {"current_steps": 100545, "total_steps": 181800, "loss": 0.0084, "lr": 2.4734077510536317e-05, "epoch": 11.061056105610561, "percentage": 55.31, "elapsed_time": "3:58:09", "remaining_time": "3:12:27", "throughput": 1485.06, "total_tokens": 21220448} {"current_steps": 100550, "total_steps": 181800, "loss": 0.0882, "lr": 2.4731677579817203e-05, "epoch": 11.061606160616062, "percentage": 55.31, "elapsed_time": "3:58:09", "remaining_time": "3:12:27", "throughput": 1485.06, "total_tokens": 21221472} {"current_steps": 100555, "total_steps": 181800, "loss": 0.0255, "lr": 2.4729277651571093e-05, "epoch": 11.062156215621561, "percentage": 55.31, "elapsed_time": "3:58:10", "remaining_time": "3:12:26", "throughput": 1485.06, "total_tokens": 21222432} {"current_steps": 100560, "total_steps": 181800, "loss": 0.0131, "lr": 2.4726877725820112e-05, "epoch": 11.062706270627062, "percentage": 55.31, "elapsed_time": "3:58:11", "remaining_time": "3:12:25", "throughput": 1485.06, "total_tokens": 21223488} {"current_steps": 100565, "total_steps": 181800, "loss": 0.0514, "lr": 2.4724477802586354e-05, "epoch": 11.063256325632564, "percentage": 55.32, "elapsed_time": "3:58:12", "remaining_time": "3:12:24", "throughput": 1485.06, "total_tokens": 21224544} {"current_steps": 100570, "total_steps": 181800, "loss": 0.0064, "lr": 2.472207788189196e-05, "epoch": 11.063806380638065, "percentage": 55.32, "elapsed_time": "3:58:12", "remaining_time": "3:12:24", "throughput": 1485.06, "total_tokens": 21225568} {"current_steps": 100575, "total_steps": 181800, "loss": 0.0068, "lr": 2.471967796375903e-05, "epoch": 11.064356435643564, "percentage": 55.32, "elapsed_time": "3:58:13", "remaining_time": "3:12:23", "throughput": 1485.06, "total_tokens": 21226624} {"current_steps": 100580, "total_steps": 181800, "loss": 0.0327, "lr": 2.4717278048209708e-05, "epoch": 11.064906490649065, "percentage": 55.32, "elapsed_time": "3:58:14", "remaining_time": "3:12:22", "throughput": 1485.07, "total_tokens": 21227680} {"current_steps": 100585, "total_steps": 181800, "loss": 0.0193, "lr": 2.4714878135266092e-05, "epoch": 11.065456545654566, "percentage": 55.33, "elapsed_time": "3:58:14", "remaining_time": "3:12:21", "throughput": 1485.06, "total_tokens": 21228672} {"current_steps": 100590, "total_steps": 181800, "loss": 0.0022, "lr": 2.47124782249503e-05, "epoch": 11.066006600660065, "percentage": 55.33, "elapsed_time": "3:58:15", "remaining_time": "3:12:21", "throughput": 1485.07, "total_tokens": 21229728} {"current_steps": 100595, "total_steps": 181800, "loss": 0.0084, "lr": 2.471007831728447e-05, "epoch": 11.066556655665567, "percentage": 55.33, "elapsed_time": "3:58:16", "remaining_time": "3:12:20", "throughput": 1485.07, "total_tokens": 21230784} {"current_steps": 100600, "total_steps": 181800, "loss": 0.0935, "lr": 2.470767841229071e-05, "epoch": 11.067106710671068, "percentage": 55.34, "elapsed_time": "3:58:16", "remaining_time": "3:12:19", "throughput": 1485.07, "total_tokens": 21231840} {"current_steps": 100605, "total_steps": 181800, "loss": 0.1413, "lr": 2.470527850999113e-05, "epoch": 11.067656765676567, "percentage": 55.34, "elapsed_time": "3:58:17", "remaining_time": "3:12:19", "throughput": 1485.08, "total_tokens": 21232960} {"current_steps": 100610, "total_steps": 181800, "loss": 0.0408, "lr": 2.4702878610407856e-05, "epoch": 11.068206820682068, "percentage": 55.34, "elapsed_time": "3:58:18", "remaining_time": "3:12:18", "throughput": 1485.08, "total_tokens": 21234016} {"current_steps": 100615, "total_steps": 181800, "loss": 0.1463, "lr": 2.4700478713563006e-05, "epoch": 11.06875687568757, "percentage": 55.34, "elapsed_time": "3:58:18", "remaining_time": "3:12:17", "throughput": 1485.08, "total_tokens": 21235104} {"current_steps": 100620, "total_steps": 181800, "loss": 0.01, "lr": 2.4698078819478708e-05, "epoch": 11.069306930693068, "percentage": 55.35, "elapsed_time": "3:58:19", "remaining_time": "3:12:16", "throughput": 1485.08, "total_tokens": 21236128} {"current_steps": 100625, "total_steps": 181800, "loss": 0.0248, "lr": 2.4695678928177072e-05, "epoch": 11.06985698569857, "percentage": 55.35, "elapsed_time": "3:58:20", "remaining_time": "3:12:16", "throughput": 1485.08, "total_tokens": 21237152} {"current_steps": 100630, "total_steps": 181800, "loss": 0.0728, "lr": 2.469327903968021e-05, "epoch": 11.07040704070407, "percentage": 55.35, "elapsed_time": "3:58:21", "remaining_time": "3:12:15", "throughput": 1485.09, "total_tokens": 21238304} {"current_steps": 100635, "total_steps": 181800, "loss": 0.1603, "lr": 2.4690879154010258e-05, "epoch": 11.070957095709572, "percentage": 55.35, "elapsed_time": "3:58:21", "remaining_time": "3:12:14", "throughput": 1485.09, "total_tokens": 21239328} {"current_steps": 100640, "total_steps": 181800, "loss": 0.0066, "lr": 2.4688479271189313e-05, "epoch": 11.071507150715071, "percentage": 55.36, "elapsed_time": "3:58:22", "remaining_time": "3:12:13", "throughput": 1485.1, "total_tokens": 21240448} {"current_steps": 100645, "total_steps": 181800, "loss": 0.0457, "lr": 2.468607939123951e-05, "epoch": 11.072057205720572, "percentage": 55.36, "elapsed_time": "3:58:23", "remaining_time": "3:12:13", "throughput": 1485.1, "total_tokens": 21241472} {"current_steps": 100650, "total_steps": 181800, "loss": 0.0842, "lr": 2.4683679514182963e-05, "epoch": 11.072607260726073, "percentage": 55.36, "elapsed_time": "3:58:23", "remaining_time": "3:12:12", "throughput": 1485.11, "total_tokens": 21242592} {"current_steps": 100655, "total_steps": 181800, "loss": 0.0044, "lr": 2.4681279640041788e-05, "epoch": 11.073157315731573, "percentage": 55.37, "elapsed_time": "3:58:24", "remaining_time": "3:12:11", "throughput": 1485.11, "total_tokens": 21243680} {"current_steps": 100660, "total_steps": 181800, "loss": 0.0134, "lr": 2.4678879768838116e-05, "epoch": 11.073707370737074, "percentage": 55.37, "elapsed_time": "3:58:25", "remaining_time": "3:12:11", "throughput": 1485.11, "total_tokens": 21244736} {"current_steps": 100665, "total_steps": 181800, "loss": 0.089, "lr": 2.467647990059404e-05, "epoch": 11.074257425742575, "percentage": 55.37, "elapsed_time": "3:58:25", "remaining_time": "3:12:10", "throughput": 1485.12, "total_tokens": 21245824} {"current_steps": 100670, "total_steps": 181800, "loss": 0.116, "lr": 2.46740800353317e-05, "epoch": 11.074807480748074, "percentage": 55.37, "elapsed_time": "3:58:26", "remaining_time": "3:12:09", "throughput": 1485.12, "total_tokens": 21246880} {"current_steps": 100675, "total_steps": 181800, "loss": 0.0841, "lr": 2.4671680173073217e-05, "epoch": 11.075357535753575, "percentage": 55.38, "elapsed_time": "3:58:27", "remaining_time": "3:12:08", "throughput": 1485.12, "total_tokens": 21247904} {"current_steps": 100680, "total_steps": 181800, "loss": 0.0285, "lr": 2.4669280313840686e-05, "epoch": 11.075907590759076, "percentage": 55.38, "elapsed_time": "3:58:27", "remaining_time": "3:12:08", "throughput": 1485.12, "total_tokens": 21248896} {"current_steps": 100685, "total_steps": 181800, "loss": 0.1058, "lr": 2.4666880457656246e-05, "epoch": 11.076457645764576, "percentage": 55.38, "elapsed_time": "3:58:28", "remaining_time": "3:12:07", "throughput": 1485.12, "total_tokens": 21250016} {"current_steps": 100690, "total_steps": 181800, "loss": 0.0095, "lr": 2.4664480604542003e-05, "epoch": 11.077007700770077, "percentage": 55.39, "elapsed_time": "3:58:29", "remaining_time": "3:12:06", "throughput": 1485.13, "total_tokens": 21251072} {"current_steps": 100695, "total_steps": 181800, "loss": 0.0533, "lr": 2.466208075452009e-05, "epoch": 11.077557755775578, "percentage": 55.39, "elapsed_time": "3:58:29", "remaining_time": "3:12:05", "throughput": 1485.13, "total_tokens": 21252160} {"current_steps": 100700, "total_steps": 181800, "loss": 0.023, "lr": 2.4659680907612617e-05, "epoch": 11.078107810781079, "percentage": 55.39, "elapsed_time": "3:58:30", "remaining_time": "3:12:05", "throughput": 1485.13, "total_tokens": 21253216} {"current_steps": 100705, "total_steps": 181800, "loss": 0.0762, "lr": 2.4657281063841693e-05, "epoch": 11.078657865786578, "percentage": 55.39, "elapsed_time": "3:58:31", "remaining_time": "3:12:04", "throughput": 1485.14, "total_tokens": 21254304} {"current_steps": 100710, "total_steps": 181800, "loss": 0.0283, "lr": 2.465488122322945e-05, "epoch": 11.07920792079208, "percentage": 55.4, "elapsed_time": "3:58:32", "remaining_time": "3:12:03", "throughput": 1485.14, "total_tokens": 21255328} {"current_steps": 100715, "total_steps": 181800, "loss": 0.0836, "lr": 2.4652481385797994e-05, "epoch": 11.07975797579758, "percentage": 55.4, "elapsed_time": "3:58:32", "remaining_time": "3:12:03", "throughput": 1485.14, "total_tokens": 21256384} {"current_steps": 100720, "total_steps": 181800, "loss": 0.0463, "lr": 2.465008155156947e-05, "epoch": 11.08030803080308, "percentage": 55.4, "elapsed_time": "3:58:33", "remaining_time": "3:12:02", "throughput": 1485.14, "total_tokens": 21257376} {"current_steps": 100725, "total_steps": 181800, "loss": 0.1349, "lr": 2.464768172056596e-05, "epoch": 11.08085808580858, "percentage": 55.4, "elapsed_time": "3:58:34", "remaining_time": "3:12:01", "throughput": 1485.14, "total_tokens": 21258400} {"current_steps": 100730, "total_steps": 181800, "loss": 0.0167, "lr": 2.46452818928096e-05, "epoch": 11.081408140814082, "percentage": 55.41, "elapsed_time": "3:58:34", "remaining_time": "3:12:00", "throughput": 1485.14, "total_tokens": 21259424} {"current_steps": 100735, "total_steps": 181800, "loss": 0.029, "lr": 2.4642882068322516e-05, "epoch": 11.081958195819581, "percentage": 55.41, "elapsed_time": "3:58:35", "remaining_time": "3:12:00", "throughput": 1485.14, "total_tokens": 21260448} {"current_steps": 100740, "total_steps": 181800, "loss": 0.1267, "lr": 2.4640482247126802e-05, "epoch": 11.082508250825082, "percentage": 55.41, "elapsed_time": "3:58:36", "remaining_time": "3:11:59", "throughput": 1485.14, "total_tokens": 21261536} {"current_steps": 100745, "total_steps": 181800, "loss": 0.0345, "lr": 2.46380824292446e-05, "epoch": 11.083058305830583, "percentage": 55.42, "elapsed_time": "3:58:36", "remaining_time": "3:11:58", "throughput": 1485.14, "total_tokens": 21262592} {"current_steps": 100750, "total_steps": 181800, "loss": 0.0103, "lr": 2.4635682614698023e-05, "epoch": 11.083608360836084, "percentage": 55.42, "elapsed_time": "3:58:37", "remaining_time": "3:11:58", "throughput": 1485.15, "total_tokens": 21263744} {"current_steps": 100755, "total_steps": 181800, "loss": 0.0117, "lr": 2.4633282803509173e-05, "epoch": 11.084158415841584, "percentage": 55.42, "elapsed_time": "3:58:38", "remaining_time": "3:11:57", "throughput": 1485.15, "total_tokens": 21264768} {"current_steps": 100760, "total_steps": 181800, "loss": 0.0081, "lr": 2.4630882995700185e-05, "epoch": 11.084708470847085, "percentage": 55.42, "elapsed_time": "3:58:38", "remaining_time": "3:11:56", "throughput": 1485.15, "total_tokens": 21265792} {"current_steps": 100765, "total_steps": 181800, "loss": 0.064, "lr": 2.4628483191293165e-05, "epoch": 11.085258525852586, "percentage": 55.43, "elapsed_time": "3:58:39", "remaining_time": "3:11:55", "throughput": 1485.15, "total_tokens": 21266816} {"current_steps": 100770, "total_steps": 181800, "loss": 0.037, "lr": 2.4626083390310246e-05, "epoch": 11.085808580858085, "percentage": 55.43, "elapsed_time": "3:58:40", "remaining_time": "3:11:55", "throughput": 1485.16, "total_tokens": 21267904} {"current_steps": 100775, "total_steps": 181800, "loss": 0.1046, "lr": 2.4623683592773538e-05, "epoch": 11.086358635863586, "percentage": 55.43, "elapsed_time": "3:58:41", "remaining_time": "3:11:54", "throughput": 1485.16, "total_tokens": 21268928} {"current_steps": 100780, "total_steps": 181800, "loss": 0.0157, "lr": 2.4621283798705148e-05, "epoch": 11.086908690869087, "percentage": 55.43, "elapsed_time": "3:58:41", "remaining_time": "3:11:53", "throughput": 1485.16, "total_tokens": 21270048} {"current_steps": 100785, "total_steps": 181800, "loss": 0.0031, "lr": 2.4618884008127212e-05, "epoch": 11.087458745874587, "percentage": 55.44, "elapsed_time": "3:58:42", "remaining_time": "3:11:52", "throughput": 1485.16, "total_tokens": 21271072} {"current_steps": 100790, "total_steps": 181800, "loss": 0.0064, "lr": 2.4616484221061844e-05, "epoch": 11.088008800880088, "percentage": 55.44, "elapsed_time": "3:58:43", "remaining_time": "3:11:52", "throughput": 1485.16, "total_tokens": 21272064} {"current_steps": 100795, "total_steps": 181800, "loss": 0.0151, "lr": 2.4614084437531144e-05, "epoch": 11.088558855885589, "percentage": 55.44, "elapsed_time": "3:58:43", "remaining_time": "3:11:51", "throughput": 1485.17, "total_tokens": 21273152} {"current_steps": 100800, "total_steps": 181800, "loss": 0.0701, "lr": 2.461168465755725e-05, "epoch": 11.089108910891088, "percentage": 55.45, "elapsed_time": "3:58:44", "remaining_time": "3:11:50", "throughput": 1485.17, "total_tokens": 21274208} {"current_steps": 100805, "total_steps": 181800, "loss": 0.0863, "lr": 2.4609284881162264e-05, "epoch": 11.08965896589659, "percentage": 55.45, "elapsed_time": "3:58:45", "remaining_time": "3:11:49", "throughput": 1485.17, "total_tokens": 21275328} {"current_steps": 100810, "total_steps": 181800, "loss": 0.0866, "lr": 2.4606885108368323e-05, "epoch": 11.09020902090209, "percentage": 55.45, "elapsed_time": "3:58:45", "remaining_time": "3:11:49", "throughput": 1485.17, "total_tokens": 21276320} {"current_steps": 100815, "total_steps": 181800, "loss": 0.0445, "lr": 2.460448533919753e-05, "epoch": 11.090759075907592, "percentage": 55.45, "elapsed_time": "3:58:46", "remaining_time": "3:11:48", "throughput": 1485.18, "total_tokens": 21277376} {"current_steps": 100820, "total_steps": 181800, "loss": 0.0172, "lr": 2.4602085573672e-05, "epoch": 11.091309130913091, "percentage": 55.46, "elapsed_time": "3:58:47", "remaining_time": "3:11:47", "throughput": 1485.18, "total_tokens": 21278464} {"current_steps": 100825, "total_steps": 181800, "loss": 0.024, "lr": 2.4599685811813866e-05, "epoch": 11.091859185918592, "percentage": 55.46, "elapsed_time": "3:58:47", "remaining_time": "3:11:47", "throughput": 1485.18, "total_tokens": 21279552} {"current_steps": 100830, "total_steps": 181800, "loss": 0.007, "lr": 2.4597286053645223e-05, "epoch": 11.092409240924093, "percentage": 55.46, "elapsed_time": "3:58:48", "remaining_time": "3:11:46", "throughput": 1485.19, "total_tokens": 21280608} {"current_steps": 100835, "total_steps": 181800, "loss": 0.0522, "lr": 2.4594886299188214e-05, "epoch": 11.092959295929592, "percentage": 55.46, "elapsed_time": "3:58:49", "remaining_time": "3:11:45", "throughput": 1485.19, "total_tokens": 21281632} {"current_steps": 100840, "total_steps": 181800, "loss": 0.0683, "lr": 2.4592486548464937e-05, "epoch": 11.093509350935093, "percentage": 55.47, "elapsed_time": "3:58:49", "remaining_time": "3:11:44", "throughput": 1485.2, "total_tokens": 21282784} {"current_steps": 100845, "total_steps": 181800, "loss": 0.0069, "lr": 2.4590086801497515e-05, "epoch": 11.094059405940595, "percentage": 55.47, "elapsed_time": "3:58:50", "remaining_time": "3:11:44", "throughput": 1485.19, "total_tokens": 21283776} {"current_steps": 100850, "total_steps": 181800, "loss": 0.0245, "lr": 2.4587687058308074e-05, "epoch": 11.094609460946094, "percentage": 55.47, "elapsed_time": "3:58:51", "remaining_time": "3:11:43", "throughput": 1485.2, "total_tokens": 21284832} {"current_steps": 100855, "total_steps": 181800, "loss": 0.0309, "lr": 2.4585287318918714e-05, "epoch": 11.095159515951595, "percentage": 55.48, "elapsed_time": "3:58:52", "remaining_time": "3:11:42", "throughput": 1485.2, "total_tokens": 21285888} {"current_steps": 100860, "total_steps": 181800, "loss": 0.0539, "lr": 2.4582887583351563e-05, "epoch": 11.095709570957096, "percentage": 55.48, "elapsed_time": "3:58:52", "remaining_time": "3:11:41", "throughput": 1485.2, "total_tokens": 21287008} {"current_steps": 100865, "total_steps": 181800, "loss": 0.0068, "lr": 2.458048785162875e-05, "epoch": 11.096259625962595, "percentage": 55.48, "elapsed_time": "3:58:53", "remaining_time": "3:11:41", "throughput": 1485.21, "total_tokens": 21288064} {"current_steps": 100870, "total_steps": 181800, "loss": 0.0161, "lr": 2.4578088123772362e-05, "epoch": 11.096809680968097, "percentage": 55.48, "elapsed_time": "3:58:54", "remaining_time": "3:11:40", "throughput": 1485.21, "total_tokens": 21289120} {"current_steps": 100875, "total_steps": 181800, "loss": 0.0052, "lr": 2.4575688399804538e-05, "epoch": 11.097359735973598, "percentage": 55.49, "elapsed_time": "3:58:54", "remaining_time": "3:11:39", "throughput": 1485.21, "total_tokens": 21290208} {"current_steps": 100880, "total_steps": 181800, "loss": 0.0088, "lr": 2.4573288679747387e-05, "epoch": 11.097909790979099, "percentage": 55.49, "elapsed_time": "3:58:55", "remaining_time": "3:11:39", "throughput": 1485.21, "total_tokens": 21291232} {"current_steps": 100885, "total_steps": 181800, "loss": 0.0254, "lr": 2.4570888963623044e-05, "epoch": 11.098459845984598, "percentage": 55.49, "elapsed_time": "3:58:56", "remaining_time": "3:11:38", "throughput": 1485.22, "total_tokens": 21292320} {"current_steps": 100890, "total_steps": 181800, "loss": 0.0809, "lr": 2.4568489251453603e-05, "epoch": 11.099009900990099, "percentage": 55.5, "elapsed_time": "3:58:56", "remaining_time": "3:11:37", "throughput": 1485.22, "total_tokens": 21293344} {"current_steps": 100895, "total_steps": 181800, "loss": 0.009, "lr": 2.4566089543261184e-05, "epoch": 11.0995599559956, "percentage": 55.5, "elapsed_time": "3:58:57", "remaining_time": "3:11:36", "throughput": 1485.22, "total_tokens": 21294400} {"current_steps": 100900, "total_steps": 181800, "loss": 0.0402, "lr": 2.4563689839067913e-05, "epoch": 11.1001100110011, "percentage": 55.5, "elapsed_time": "3:58:58", "remaining_time": "3:11:36", "throughput": 1485.23, "total_tokens": 21295520} {"current_steps": 100905, "total_steps": 181800, "loss": 0.0784, "lr": 2.45612901388959e-05, "epoch": 11.1006600660066, "percentage": 55.5, "elapsed_time": "3:58:58", "remaining_time": "3:11:35", "throughput": 1485.23, "total_tokens": 21296608} {"current_steps": 100910, "total_steps": 181800, "loss": 0.0473, "lr": 2.455889044276728e-05, "epoch": 11.101210121012102, "percentage": 55.51, "elapsed_time": "3:58:59", "remaining_time": "3:11:34", "throughput": 1485.23, "total_tokens": 21297632} {"current_steps": 100915, "total_steps": 181800, "loss": 0.0673, "lr": 2.4556490750704146e-05, "epoch": 11.101760176017601, "percentage": 55.51, "elapsed_time": "3:59:00", "remaining_time": "3:11:33", "throughput": 1485.23, "total_tokens": 21298624} {"current_steps": 100920, "total_steps": 181800, "loss": 0.0459, "lr": 2.4554091062728615e-05, "epoch": 11.102310231023102, "percentage": 55.51, "elapsed_time": "3:59:00", "remaining_time": "3:11:33", "throughput": 1485.24, "total_tokens": 21299744} {"current_steps": 100925, "total_steps": 181800, "loss": 0.0344, "lr": 2.4551691378862827e-05, "epoch": 11.102860286028603, "percentage": 55.51, "elapsed_time": "3:59:01", "remaining_time": "3:11:32", "throughput": 1485.24, "total_tokens": 21300800} {"current_steps": 100930, "total_steps": 181800, "loss": 0.002, "lr": 2.4549291699128873e-05, "epoch": 11.103410341034103, "percentage": 55.52, "elapsed_time": "3:59:02", "remaining_time": "3:11:31", "throughput": 1485.24, "total_tokens": 21301824} {"current_steps": 100935, "total_steps": 181800, "loss": 0.0043, "lr": 2.454689202354889e-05, "epoch": 11.103960396039604, "percentage": 55.52, "elapsed_time": "3:59:03", "remaining_time": "3:11:31", "throughput": 1485.24, "total_tokens": 21302848} {"current_steps": 100940, "total_steps": 181800, "loss": 0.0131, "lr": 2.4544492352144986e-05, "epoch": 11.104510451045105, "percentage": 55.52, "elapsed_time": "3:59:03", "remaining_time": "3:11:30", "throughput": 1485.24, "total_tokens": 21303936} {"current_steps": 100945, "total_steps": 181800, "loss": 0.0593, "lr": 2.4542092684939262e-05, "epoch": 11.105060506050606, "percentage": 55.53, "elapsed_time": "3:59:04", "remaining_time": "3:11:29", "throughput": 1485.24, "total_tokens": 21304960} {"current_steps": 100950, "total_steps": 181800, "loss": 0.0311, "lr": 2.4539693021953873e-05, "epoch": 11.105610561056105, "percentage": 55.53, "elapsed_time": "3:59:05", "remaining_time": "3:11:28", "throughput": 1485.25, "total_tokens": 21306016} {"current_steps": 100955, "total_steps": 181800, "loss": 0.0505, "lr": 2.4537293363210896e-05, "epoch": 11.106160616061606, "percentage": 55.53, "elapsed_time": "3:59:05", "remaining_time": "3:11:28", "throughput": 1485.25, "total_tokens": 21307072} {"current_steps": 100960, "total_steps": 181800, "loss": 0.0241, "lr": 2.453489370873247e-05, "epoch": 11.106710671067107, "percentage": 55.53, "elapsed_time": "3:59:06", "remaining_time": "3:11:27", "throughput": 1485.25, "total_tokens": 21308160} {"current_steps": 100965, "total_steps": 181800, "loss": 0.0605, "lr": 2.453249405854071e-05, "epoch": 11.107260726072607, "percentage": 55.54, "elapsed_time": "3:59:07", "remaining_time": "3:11:26", "throughput": 1485.25, "total_tokens": 21309184} {"current_steps": 100970, "total_steps": 181800, "loss": 0.0022, "lr": 2.4530094412657716e-05, "epoch": 11.107810781078108, "percentage": 55.54, "elapsed_time": "3:59:07", "remaining_time": "3:11:25", "throughput": 1485.25, "total_tokens": 21310208} {"current_steps": 100975, "total_steps": 181800, "loss": 0.0675, "lr": 2.4527694771105625e-05, "epoch": 11.108360836083609, "percentage": 55.54, "elapsed_time": "3:59:08", "remaining_time": "3:11:25", "throughput": 1485.25, "total_tokens": 21311232} {"current_steps": 100980, "total_steps": 181800, "loss": 0.0513, "lr": 2.4525295133906548e-05, "epoch": 11.108910891089108, "percentage": 55.54, "elapsed_time": "3:59:09", "remaining_time": "3:11:24", "throughput": 1485.25, "total_tokens": 21312256} {"current_steps": 100985, "total_steps": 181800, "loss": 0.0066, "lr": 2.452289550108259e-05, "epoch": 11.10946094609461, "percentage": 55.55, "elapsed_time": "3:59:09", "remaining_time": "3:11:23", "throughput": 1485.25, "total_tokens": 21313280} {"current_steps": 100990, "total_steps": 181800, "loss": 0.0188, "lr": 2.4520495872655877e-05, "epoch": 11.11001100110011, "percentage": 55.55, "elapsed_time": "3:59:10", "remaining_time": "3:11:23", "throughput": 1485.25, "total_tokens": 21314304} {"current_steps": 100995, "total_steps": 181800, "loss": 0.0244, "lr": 2.451809624864852e-05, "epoch": 11.110561056105611, "percentage": 55.55, "elapsed_time": "3:59:11", "remaining_time": "3:11:22", "throughput": 1485.25, "total_tokens": 21315360} {"current_steps": 101000, "total_steps": 181800, "loss": 0.0246, "lr": 2.4515696629082648e-05, "epoch": 11.11111111111111, "percentage": 55.56, "elapsed_time": "3:59:12", "remaining_time": "3:11:21", "throughput": 1485.26, "total_tokens": 21316448} {"current_steps": 101005, "total_steps": 181800, "loss": 0.1024, "lr": 2.4513297013980363e-05, "epoch": 11.111661166116612, "percentage": 55.56, "elapsed_time": "3:59:12", "remaining_time": "3:11:20", "throughput": 1485.26, "total_tokens": 21317536} {"current_steps": 101010, "total_steps": 181800, "loss": 0.0044, "lr": 2.4510897403363782e-05, "epoch": 11.112211221122113, "percentage": 55.56, "elapsed_time": "3:59:13", "remaining_time": "3:11:20", "throughput": 1485.26, "total_tokens": 21318560} {"current_steps": 101015, "total_steps": 181800, "loss": 0.0103, "lr": 2.450849779725503e-05, "epoch": 11.112761276127612, "percentage": 55.56, "elapsed_time": "3:59:14", "remaining_time": "3:11:19", "throughput": 1485.26, "total_tokens": 21319552} {"current_steps": 101020, "total_steps": 181800, "loss": 0.0049, "lr": 2.4506098195676212e-05, "epoch": 11.113311331133113, "percentage": 55.57, "elapsed_time": "3:59:14", "remaining_time": "3:11:18", "throughput": 1485.27, "total_tokens": 21320640} {"current_steps": 101025, "total_steps": 181800, "loss": 0.014, "lr": 2.450369859864946e-05, "epoch": 11.113861386138614, "percentage": 55.57, "elapsed_time": "3:59:15", "remaining_time": "3:11:17", "throughput": 1485.26, "total_tokens": 21321632} {"current_steps": 101030, "total_steps": 181800, "loss": 0.0182, "lr": 2.4501299006196872e-05, "epoch": 11.114411441144114, "percentage": 55.57, "elapsed_time": "3:59:16", "remaining_time": "3:11:17", "throughput": 1485.27, "total_tokens": 21322720} {"current_steps": 101035, "total_steps": 181800, "loss": 0.0572, "lr": 2.449889941834057e-05, "epoch": 11.114961496149615, "percentage": 55.57, "elapsed_time": "3:59:16", "remaining_time": "3:11:16", "throughput": 1485.27, "total_tokens": 21323744} {"current_steps": 101040, "total_steps": 181800, "loss": 0.0419, "lr": 2.4496499835102684e-05, "epoch": 11.115511551155116, "percentage": 55.58, "elapsed_time": "3:59:17", "remaining_time": "3:11:15", "throughput": 1485.27, "total_tokens": 21324768} {"current_steps": 101045, "total_steps": 181800, "loss": 0.0052, "lr": 2.4494100256505303e-05, "epoch": 11.116061606160615, "percentage": 55.58, "elapsed_time": "3:59:18", "remaining_time": "3:11:15", "throughput": 1485.27, "total_tokens": 21325856} {"current_steps": 101050, "total_steps": 181800, "loss": 0.0758, "lr": 2.4491700682570565e-05, "epoch": 11.116611661166116, "percentage": 55.58, "elapsed_time": "3:59:18", "remaining_time": "3:11:14", "throughput": 1485.27, "total_tokens": 21326880} {"current_steps": 101055, "total_steps": 181800, "loss": 0.0905, "lr": 2.4489301113320583e-05, "epoch": 11.117161716171617, "percentage": 55.59, "elapsed_time": "3:59:19", "remaining_time": "3:11:13", "throughput": 1485.27, "total_tokens": 21327904} {"current_steps": 101060, "total_steps": 181800, "loss": 0.015, "lr": 2.4486901548777455e-05, "epoch": 11.117711771177119, "percentage": 55.59, "elapsed_time": "3:59:20", "remaining_time": "3:11:12", "throughput": 1485.27, "total_tokens": 21328960} {"current_steps": 101065, "total_steps": 181800, "loss": 0.0059, "lr": 2.4484501988963314e-05, "epoch": 11.118261826182618, "percentage": 55.59, "elapsed_time": "3:59:20", "remaining_time": "3:11:12", "throughput": 1485.28, "total_tokens": 21330016} {"current_steps": 101070, "total_steps": 181800, "loss": 0.0495, "lr": 2.448210243390027e-05, "epoch": 11.118811881188119, "percentage": 55.59, "elapsed_time": "3:59:21", "remaining_time": "3:11:11", "throughput": 1485.27, "total_tokens": 21331008} {"current_steps": 101075, "total_steps": 181800, "loss": 0.0623, "lr": 2.4479702883610443e-05, "epoch": 11.11936193619362, "percentage": 55.6, "elapsed_time": "3:59:22", "remaining_time": "3:11:10", "throughput": 1485.28, "total_tokens": 21332128} {"current_steps": 101080, "total_steps": 181800, "loss": 0.0759, "lr": 2.4477303338115947e-05, "epoch": 11.11991199119912, "percentage": 55.6, "elapsed_time": "3:59:23", "remaining_time": "3:11:09", "throughput": 1485.28, "total_tokens": 21333152} {"current_steps": 101085, "total_steps": 181800, "loss": 0.0176, "lr": 2.4474903797438887e-05, "epoch": 11.12046204620462, "percentage": 55.6, "elapsed_time": "3:59:23", "remaining_time": "3:11:09", "throughput": 1485.28, "total_tokens": 21334144} {"current_steps": 101090, "total_steps": 181800, "loss": 0.0034, "lr": 2.4472504261601393e-05, "epoch": 11.121012101210122, "percentage": 55.61, "elapsed_time": "3:59:24", "remaining_time": "3:11:08", "throughput": 1485.28, "total_tokens": 21335200} {"current_steps": 101095, "total_steps": 181800, "loss": 0.019, "lr": 2.4470104730625564e-05, "epoch": 11.12156215621562, "percentage": 55.61, "elapsed_time": "3:59:25", "remaining_time": "3:11:07", "throughput": 1485.28, "total_tokens": 21336256} {"current_steps": 101100, "total_steps": 181800, "loss": 0.0031, "lr": 2.446770520453354e-05, "epoch": 11.122112211221122, "percentage": 55.61, "elapsed_time": "3:59:25", "remaining_time": "3:11:07", "throughput": 1485.29, "total_tokens": 21337344} {"current_steps": 101105, "total_steps": 181800, "loss": 0.0193, "lr": 2.4465305683347416e-05, "epoch": 11.122662266226623, "percentage": 55.61, "elapsed_time": "3:59:26", "remaining_time": "3:11:06", "throughput": 1485.29, "total_tokens": 21338368} {"current_steps": 101110, "total_steps": 181800, "loss": 0.0282, "lr": 2.446290616708931e-05, "epoch": 11.123212321232122, "percentage": 55.62, "elapsed_time": "3:59:27", "remaining_time": "3:11:05", "throughput": 1485.29, "total_tokens": 21339424} {"current_steps": 101115, "total_steps": 181800, "loss": 0.1004, "lr": 2.4460506655781348e-05, "epoch": 11.123762376237623, "percentage": 55.62, "elapsed_time": "3:59:27", "remaining_time": "3:11:04", "throughput": 1485.29, "total_tokens": 21340512} {"current_steps": 101120, "total_steps": 181800, "loss": 0.0033, "lr": 2.445810714944563e-05, "epoch": 11.124312431243125, "percentage": 55.62, "elapsed_time": "3:59:28", "remaining_time": "3:11:04", "throughput": 1485.3, "total_tokens": 21341568} {"current_steps": 101125, "total_steps": 181800, "loss": 0.0391, "lr": 2.4455707648104277e-05, "epoch": 11.124862486248626, "percentage": 55.62, "elapsed_time": "3:59:29", "remaining_time": "3:11:03", "throughput": 1485.29, "total_tokens": 21342560} {"current_steps": 101130, "total_steps": 181800, "loss": 0.0204, "lr": 2.4453308151779407e-05, "epoch": 11.125412541254125, "percentage": 55.63, "elapsed_time": "3:59:29", "remaining_time": "3:11:02", "throughput": 1485.3, "total_tokens": 21343616} {"current_steps": 101135, "total_steps": 181800, "loss": 0.021, "lr": 2.4450908660493133e-05, "epoch": 11.125962596259626, "percentage": 55.63, "elapsed_time": "3:59:30", "remaining_time": "3:11:01", "throughput": 1485.3, "total_tokens": 21344672} {"current_steps": 101140, "total_steps": 181800, "loss": 0.0499, "lr": 2.444850917426758e-05, "epoch": 11.126512651265127, "percentage": 55.63, "elapsed_time": "3:59:31", "remaining_time": "3:11:01", "throughput": 1485.3, "total_tokens": 21345792} {"current_steps": 101145, "total_steps": 181800, "loss": 0.0056, "lr": 2.444610969312484e-05, "epoch": 11.127062706270626, "percentage": 55.64, "elapsed_time": "3:59:32", "remaining_time": "3:11:00", "throughput": 1485.31, "total_tokens": 21346912} {"current_steps": 101150, "total_steps": 181800, "loss": 0.0157, "lr": 2.4443710217087045e-05, "epoch": 11.127612761276128, "percentage": 55.64, "elapsed_time": "3:59:32", "remaining_time": "3:10:59", "throughput": 1485.32, "total_tokens": 21348064} {"current_steps": 101155, "total_steps": 181800, "loss": 0.003, "lr": 2.4441310746176317e-05, "epoch": 11.128162816281629, "percentage": 55.64, "elapsed_time": "3:59:33", "remaining_time": "3:10:59", "throughput": 1485.32, "total_tokens": 21349152} {"current_steps": 101160, "total_steps": 181800, "loss": 0.0215, "lr": 2.4438911280414744e-05, "epoch": 11.128712871287128, "percentage": 55.64, "elapsed_time": "3:59:34", "remaining_time": "3:10:58", "throughput": 1485.32, "total_tokens": 21350176} {"current_steps": 101165, "total_steps": 181800, "loss": 0.0032, "lr": 2.4436511819824466e-05, "epoch": 11.129262926292629, "percentage": 55.65, "elapsed_time": "3:59:34", "remaining_time": "3:10:57", "throughput": 1485.33, "total_tokens": 21351264} {"current_steps": 101170, "total_steps": 181800, "loss": 0.0962, "lr": 2.4434112364427587e-05, "epoch": 11.12981298129813, "percentage": 55.65, "elapsed_time": "3:59:35", "remaining_time": "3:10:56", "throughput": 1485.33, "total_tokens": 21352352} {"current_steps": 101175, "total_steps": 181800, "loss": 0.0078, "lr": 2.443171291424622e-05, "epoch": 11.130363036303631, "percentage": 55.65, "elapsed_time": "3:59:36", "remaining_time": "3:10:56", "throughput": 1485.34, "total_tokens": 21353472} {"current_steps": 101180, "total_steps": 181800, "loss": 0.0028, "lr": 2.4429313469302483e-05, "epoch": 11.13091309130913, "percentage": 55.65, "elapsed_time": "3:59:36", "remaining_time": "3:10:55", "throughput": 1485.34, "total_tokens": 21354496} {"current_steps": 101185, "total_steps": 181800, "loss": 0.0037, "lr": 2.4426914029618485e-05, "epoch": 11.131463146314632, "percentage": 55.66, "elapsed_time": "3:59:37", "remaining_time": "3:10:54", "throughput": 1485.33, "total_tokens": 21355488} {"current_steps": 101190, "total_steps": 181800, "loss": 0.0849, "lr": 2.4424514595216352e-05, "epoch": 11.132013201320133, "percentage": 55.66, "elapsed_time": "3:59:38", "remaining_time": "3:10:54", "throughput": 1485.33, "total_tokens": 21356512} {"current_steps": 101195, "total_steps": 181800, "loss": 0.0112, "lr": 2.4422115166118196e-05, "epoch": 11.132563256325632, "percentage": 55.66, "elapsed_time": "3:59:38", "remaining_time": "3:10:53", "throughput": 1485.34, "total_tokens": 21357568} {"current_steps": 101200, "total_steps": 181800, "loss": 0.0063, "lr": 2.4419715742346116e-05, "epoch": 11.133113311331133, "percentage": 55.67, "elapsed_time": "3:59:39", "remaining_time": "3:10:52", "throughput": 1485.34, "total_tokens": 21358720} {"current_steps": 101205, "total_steps": 181800, "loss": 0.0126, "lr": 2.4417316323922246e-05, "epoch": 11.133663366336634, "percentage": 55.67, "elapsed_time": "3:59:40", "remaining_time": "3:10:51", "throughput": 1485.34, "total_tokens": 21359744} {"current_steps": 101210, "total_steps": 181800, "loss": 0.1063, "lr": 2.4414916910868683e-05, "epoch": 11.134213421342134, "percentage": 55.67, "elapsed_time": "3:59:41", "remaining_time": "3:10:51", "throughput": 1485.34, "total_tokens": 21360736} {"current_steps": 101215, "total_steps": 181800, "loss": 0.0485, "lr": 2.4412517503207563e-05, "epoch": 11.134763476347635, "percentage": 55.67, "elapsed_time": "3:59:41", "remaining_time": "3:10:50", "throughput": 1485.34, "total_tokens": 21361728} {"current_steps": 101220, "total_steps": 181800, "loss": 0.0323, "lr": 2.4410118100960982e-05, "epoch": 11.135313531353136, "percentage": 55.68, "elapsed_time": "3:59:42", "remaining_time": "3:10:49", "throughput": 1485.34, "total_tokens": 21362816} {"current_steps": 101225, "total_steps": 181800, "loss": 0.0522, "lr": 2.440771870415105e-05, "epoch": 11.135863586358635, "percentage": 55.68, "elapsed_time": "3:59:43", "remaining_time": "3:10:48", "throughput": 1485.35, "total_tokens": 21363904} {"current_steps": 101230, "total_steps": 181800, "loss": 0.0018, "lr": 2.4405319312799906e-05, "epoch": 11.136413641364136, "percentage": 55.68, "elapsed_time": "3:59:43", "remaining_time": "3:10:48", "throughput": 1485.35, "total_tokens": 21364896} {"current_steps": 101235, "total_steps": 181800, "loss": 0.0629, "lr": 2.4402919926929637e-05, "epoch": 11.136963696369637, "percentage": 55.68, "elapsed_time": "3:59:44", "remaining_time": "3:10:47", "throughput": 1485.35, "total_tokens": 21365920} {"current_steps": 101240, "total_steps": 181800, "loss": 0.0725, "lr": 2.440052054656237e-05, "epoch": 11.137513751375138, "percentage": 55.69, "elapsed_time": "3:59:45", "remaining_time": "3:10:46", "throughput": 1485.35, "total_tokens": 21367008} {"current_steps": 101245, "total_steps": 181800, "loss": 0.0929, "lr": 2.439812117172023e-05, "epoch": 11.138063806380638, "percentage": 55.69, "elapsed_time": "3:59:45", "remaining_time": "3:10:46", "throughput": 1485.35, "total_tokens": 21368032} {"current_steps": 101250, "total_steps": 181800, "loss": 0.0058, "lr": 2.4395721802425297e-05, "epoch": 11.138613861386139, "percentage": 55.69, "elapsed_time": "3:59:46", "remaining_time": "3:10:45", "throughput": 1485.35, "total_tokens": 21369088} {"current_steps": 101255, "total_steps": 181800, "loss": 0.0141, "lr": 2.439332243869972e-05, "epoch": 11.13916391639164, "percentage": 55.7, "elapsed_time": "3:59:47", "remaining_time": "3:10:44", "throughput": 1485.36, "total_tokens": 21370144} {"current_steps": 101260, "total_steps": 181800, "loss": 0.0056, "lr": 2.4390923080565593e-05, "epoch": 11.13971397139714, "percentage": 55.7, "elapsed_time": "3:59:47", "remaining_time": "3:10:43", "throughput": 1485.36, "total_tokens": 21371232} {"current_steps": 101265, "total_steps": 181800, "loss": 0.0951, "lr": 2.4388523728045044e-05, "epoch": 11.14026402640264, "percentage": 55.7, "elapsed_time": "3:59:48", "remaining_time": "3:10:43", "throughput": 1485.36, "total_tokens": 21372320} {"current_steps": 101270, "total_steps": 181800, "loss": 0.0504, "lr": 2.4386124381160177e-05, "epoch": 11.140814081408141, "percentage": 55.7, "elapsed_time": "3:59:49", "remaining_time": "3:10:42", "throughput": 1485.37, "total_tokens": 21373376} {"current_steps": 101275, "total_steps": 181800, "loss": 0.0165, "lr": 2.43837250399331e-05, "epoch": 11.14136413641364, "percentage": 55.71, "elapsed_time": "3:59:49", "remaining_time": "3:10:41", "throughput": 1485.37, "total_tokens": 21374400} {"current_steps": 101280, "total_steps": 181800, "loss": 0.0266, "lr": 2.438132570438594e-05, "epoch": 11.141914191419142, "percentage": 55.71, "elapsed_time": "3:59:50", "remaining_time": "3:10:40", "throughput": 1485.37, "total_tokens": 21375424} {"current_steps": 101285, "total_steps": 181800, "loss": 0.0294, "lr": 2.4378926374540794e-05, "epoch": 11.142464246424643, "percentage": 55.71, "elapsed_time": "3:59:51", "remaining_time": "3:10:40", "throughput": 1485.37, "total_tokens": 21376512} {"current_steps": 101290, "total_steps": 181800, "loss": 0.0243, "lr": 2.4376527050419802e-05, "epoch": 11.143014301430142, "percentage": 55.72, "elapsed_time": "3:59:52", "remaining_time": "3:10:39", "throughput": 1485.37, "total_tokens": 21377568} {"current_steps": 101295, "total_steps": 181800, "loss": 0.0122, "lr": 2.4374127732045048e-05, "epoch": 11.143564356435643, "percentage": 55.72, "elapsed_time": "3:59:52", "remaining_time": "3:10:38", "throughput": 1485.38, "total_tokens": 21378688} {"current_steps": 101300, "total_steps": 181800, "loss": 0.0152, "lr": 2.437172841943866e-05, "epoch": 11.144114411441144, "percentage": 55.72, "elapsed_time": "3:59:53", "remaining_time": "3:10:38", "throughput": 1485.38, "total_tokens": 21379744} {"current_steps": 101305, "total_steps": 181800, "loss": 0.1228, "lr": 2.4369329112622758e-05, "epoch": 11.144664466446645, "percentage": 55.72, "elapsed_time": "3:59:54", "remaining_time": "3:10:37", "throughput": 1485.39, "total_tokens": 21380832} {"current_steps": 101310, "total_steps": 181800, "loss": 0.037, "lr": 2.436692981161943e-05, "epoch": 11.145214521452145, "percentage": 55.73, "elapsed_time": "3:59:54", "remaining_time": "3:10:36", "throughput": 1485.39, "total_tokens": 21381888} {"current_steps": 101315, "total_steps": 181800, "loss": 0.0411, "lr": 2.4364530516450824e-05, "epoch": 11.145764576457646, "percentage": 55.73, "elapsed_time": "3:59:55", "remaining_time": "3:10:35", "throughput": 1485.39, "total_tokens": 21382976} {"current_steps": 101320, "total_steps": 181800, "loss": 0.0029, "lr": 2.436213122713903e-05, "epoch": 11.146314631463147, "percentage": 55.73, "elapsed_time": "3:59:56", "remaining_time": "3:10:35", "throughput": 1485.39, "total_tokens": 21384032} {"current_steps": 101325, "total_steps": 181800, "loss": 0.0401, "lr": 2.4359731943706157e-05, "epoch": 11.146864686468646, "percentage": 55.73, "elapsed_time": "3:59:56", "remaining_time": "3:10:34", "throughput": 1485.4, "total_tokens": 21385088} {"current_steps": 101330, "total_steps": 181800, "loss": 0.0027, "lr": 2.4357332666174343e-05, "epoch": 11.147414741474147, "percentage": 55.74, "elapsed_time": "3:59:57", "remaining_time": "3:10:33", "throughput": 1485.4, "total_tokens": 21386176} {"current_steps": 101335, "total_steps": 181800, "loss": 0.0137, "lr": 2.435493339456567e-05, "epoch": 11.147964796479648, "percentage": 55.74, "elapsed_time": "3:59:58", "remaining_time": "3:10:32", "throughput": 1485.4, "total_tokens": 21387200} {"current_steps": 101340, "total_steps": 181800, "loss": 0.0417, "lr": 2.4352534128902278e-05, "epoch": 11.148514851485148, "percentage": 55.74, "elapsed_time": "3:59:58", "remaining_time": "3:10:32", "throughput": 1485.41, "total_tokens": 21388288} {"current_steps": 101345, "total_steps": 181800, "loss": 0.0109, "lr": 2.435013486920627e-05, "epoch": 11.149064906490649, "percentage": 55.75, "elapsed_time": "3:59:59", "remaining_time": "3:10:31", "throughput": 1485.41, "total_tokens": 21389312} {"current_steps": 101350, "total_steps": 181800, "loss": 0.0815, "lr": 2.4347735615499743e-05, "epoch": 11.14961496149615, "percentage": 55.75, "elapsed_time": "4:00:00", "remaining_time": "3:10:30", "throughput": 1485.41, "total_tokens": 21390400} {"current_steps": 101355, "total_steps": 181800, "loss": 0.0021, "lr": 2.4345336367804837e-05, "epoch": 11.150165016501651, "percentage": 55.75, "elapsed_time": "4:00:01", "remaining_time": "3:10:30", "throughput": 1485.41, "total_tokens": 21391456} {"current_steps": 101360, "total_steps": 181800, "loss": 0.0058, "lr": 2.434293712614364e-05, "epoch": 11.15071507150715, "percentage": 55.75, "elapsed_time": "4:00:01", "remaining_time": "3:10:29", "throughput": 1485.42, "total_tokens": 21392576} {"current_steps": 101365, "total_steps": 181800, "loss": 0.064, "lr": 2.434053789053829e-05, "epoch": 11.151265126512651, "percentage": 55.76, "elapsed_time": "4:00:02", "remaining_time": "3:10:28", "throughput": 1485.43, "total_tokens": 21393696} {"current_steps": 101370, "total_steps": 181800, "loss": 0.065, "lr": 2.433813866101088e-05, "epoch": 11.151815181518153, "percentage": 55.76, "elapsed_time": "4:00:03", "remaining_time": "3:10:27", "throughput": 1485.43, "total_tokens": 21394784} {"current_steps": 101375, "total_steps": 181800, "loss": 0.0482, "lr": 2.433573943758352e-05, "epoch": 11.152365236523652, "percentage": 55.76, "elapsed_time": "4:00:03", "remaining_time": "3:10:27", "throughput": 1485.43, "total_tokens": 21395808} {"current_steps": 101380, "total_steps": 181800, "loss": 0.0026, "lr": 2.433334022027834e-05, "epoch": 11.152915291529153, "percentage": 55.76, "elapsed_time": "4:00:04", "remaining_time": "3:10:26", "throughput": 1485.43, "total_tokens": 21396896} {"current_steps": 101385, "total_steps": 181800, "loss": 0.0118, "lr": 2.4330941009117446e-05, "epoch": 11.153465346534654, "percentage": 55.77, "elapsed_time": "4:00:05", "remaining_time": "3:10:25", "throughput": 1485.44, "total_tokens": 21398016} {"current_steps": 101390, "total_steps": 181800, "loss": 0.0041, "lr": 2.432854180412294e-05, "epoch": 11.154015401540153, "percentage": 55.77, "elapsed_time": "4:00:05", "remaining_time": "3:10:24", "throughput": 1485.44, "total_tokens": 21399040} {"current_steps": 101395, "total_steps": 181800, "loss": 0.0079, "lr": 2.4326142605316946e-05, "epoch": 11.154565456545654, "percentage": 55.77, "elapsed_time": "4:00:06", "remaining_time": "3:10:24", "throughput": 1485.45, "total_tokens": 21400160} {"current_steps": 101400, "total_steps": 181800, "loss": 0.0233, "lr": 2.4323743412721564e-05, "epoch": 11.155115511551156, "percentage": 55.78, "elapsed_time": "4:00:07", "remaining_time": "3:10:23", "throughput": 1485.45, "total_tokens": 21401248} {"current_steps": 101405, "total_steps": 181800, "loss": 0.0271, "lr": 2.432134422635893e-05, "epoch": 11.155665566556655, "percentage": 55.78, "elapsed_time": "4:00:07", "remaining_time": "3:10:22", "throughput": 1485.46, "total_tokens": 21402304} {"current_steps": 101410, "total_steps": 181800, "loss": 0.0375, "lr": 2.431894504625113e-05, "epoch": 11.156215621562156, "percentage": 55.78, "elapsed_time": "4:00:08", "remaining_time": "3:10:22", "throughput": 1485.46, "total_tokens": 21403360} {"current_steps": 101415, "total_steps": 181800, "loss": 0.0035, "lr": 2.4316545872420286e-05, "epoch": 11.156765676567657, "percentage": 55.78, "elapsed_time": "4:00:09", "remaining_time": "3:10:21", "throughput": 1485.46, "total_tokens": 21404416} {"current_steps": 101420, "total_steps": 181800, "loss": 0.0905, "lr": 2.431414670488852e-05, "epoch": 11.157315731573158, "percentage": 55.79, "elapsed_time": "4:00:09", "remaining_time": "3:10:20", "throughput": 1485.46, "total_tokens": 21405472} {"current_steps": 101425, "total_steps": 181800, "loss": 0.0105, "lr": 2.4311747543677924e-05, "epoch": 11.157865786578657, "percentage": 55.79, "elapsed_time": "4:00:10", "remaining_time": "3:10:19", "throughput": 1485.46, "total_tokens": 21406528} {"current_steps": 101430, "total_steps": 181800, "loss": 0.0018, "lr": 2.4309348388810626e-05, "epoch": 11.158415841584159, "percentage": 55.79, "elapsed_time": "4:00:11", "remaining_time": "3:10:19", "throughput": 1485.47, "total_tokens": 21407648} {"current_steps": 101435, "total_steps": 181800, "loss": 0.0185, "lr": 2.4306949240308733e-05, "epoch": 11.15896589658966, "percentage": 55.79, "elapsed_time": "4:00:12", "remaining_time": "3:10:18", "throughput": 1485.47, "total_tokens": 21408736} {"current_steps": 101440, "total_steps": 181800, "loss": 0.0217, "lr": 2.430455009819435e-05, "epoch": 11.159515951595159, "percentage": 55.8, "elapsed_time": "4:00:12", "remaining_time": "3:10:17", "throughput": 1485.48, "total_tokens": 21409792} {"current_steps": 101445, "total_steps": 181800, "loss": 0.0153, "lr": 2.4302150962489605e-05, "epoch": 11.16006600660066, "percentage": 55.8, "elapsed_time": "4:00:13", "remaining_time": "3:10:16", "throughput": 1485.48, "total_tokens": 21410816} {"current_steps": 101450, "total_steps": 181800, "loss": 0.0161, "lr": 2.429975183321659e-05, "epoch": 11.160616061606161, "percentage": 55.8, "elapsed_time": "4:00:14", "remaining_time": "3:10:16", "throughput": 1485.49, "total_tokens": 21411968} {"current_steps": 101455, "total_steps": 181800, "loss": 0.1013, "lr": 2.429735271039743e-05, "epoch": 11.16116611661166, "percentage": 55.81, "elapsed_time": "4:00:14", "remaining_time": "3:10:15", "throughput": 1485.49, "total_tokens": 21413024} {"current_steps": 101460, "total_steps": 181800, "loss": 0.0047, "lr": 2.4294953594054243e-05, "epoch": 11.161716171617162, "percentage": 55.81, "elapsed_time": "4:00:15", "remaining_time": "3:10:14", "throughput": 1485.49, "total_tokens": 21414048} {"current_steps": 101465, "total_steps": 181800, "loss": 0.0241, "lr": 2.4292554484209114e-05, "epoch": 11.162266226622663, "percentage": 55.81, "elapsed_time": "4:00:16", "remaining_time": "3:10:14", "throughput": 1485.49, "total_tokens": 21415072} {"current_steps": 101470, "total_steps": 181800, "loss": 0.0029, "lr": 2.429015538088418e-05, "epoch": 11.162816281628162, "percentage": 55.81, "elapsed_time": "4:00:16", "remaining_time": "3:10:13", "throughput": 1485.49, "total_tokens": 21416096} {"current_steps": 101475, "total_steps": 181800, "loss": 0.0025, "lr": 2.4287756284101536e-05, "epoch": 11.163366336633663, "percentage": 55.82, "elapsed_time": "4:00:17", "remaining_time": "3:10:12", "throughput": 1485.49, "total_tokens": 21417152} {"current_steps": 101480, "total_steps": 181800, "loss": 0.0243, "lr": 2.4285357193883313e-05, "epoch": 11.163916391639164, "percentage": 55.82, "elapsed_time": "4:00:18", "remaining_time": "3:10:11", "throughput": 1485.5, "total_tokens": 21418272} {"current_steps": 101485, "total_steps": 181800, "loss": 0.0079, "lr": 2.4282958110251604e-05, "epoch": 11.164466446644665, "percentage": 55.82, "elapsed_time": "4:00:18", "remaining_time": "3:10:11", "throughput": 1485.5, "total_tokens": 21419328} {"current_steps": 101490, "total_steps": 181800, "loss": 0.046, "lr": 2.428055903322852e-05, "epoch": 11.165016501650165, "percentage": 55.83, "elapsed_time": "4:00:19", "remaining_time": "3:10:10", "throughput": 1485.5, "total_tokens": 21420384} {"current_steps": 101495, "total_steps": 181800, "loss": 0.0561, "lr": 2.4278159962836183e-05, "epoch": 11.165566556655666, "percentage": 55.83, "elapsed_time": "4:00:20", "remaining_time": "3:10:09", "throughput": 1485.5, "total_tokens": 21421376} {"current_steps": 101500, "total_steps": 181800, "loss": 0.0119, "lr": 2.4275760899096694e-05, "epoch": 11.166116611661167, "percentage": 55.83, "elapsed_time": "4:00:20", "remaining_time": "3:10:08", "throughput": 1485.5, "total_tokens": 21422432} {"current_steps": 101505, "total_steps": 181800, "loss": 0.0029, "lr": 2.427336184203218e-05, "epoch": 11.166666666666666, "percentage": 55.83, "elapsed_time": "4:00:21", "remaining_time": "3:10:08", "throughput": 1485.5, "total_tokens": 21423424} {"current_steps": 101510, "total_steps": 181800, "loss": 0.0635, "lr": 2.4270962791664736e-05, "epoch": 11.167216721672167, "percentage": 55.84, "elapsed_time": "4:00:22", "remaining_time": "3:10:07", "throughput": 1485.5, "total_tokens": 21424416} {"current_steps": 101515, "total_steps": 181800, "loss": 0.0057, "lr": 2.4268563748016475e-05, "epoch": 11.167766776677668, "percentage": 55.84, "elapsed_time": "4:00:23", "remaining_time": "3:10:06", "throughput": 1485.5, "total_tokens": 21425440} {"current_steps": 101520, "total_steps": 181800, "loss": 0.0035, "lr": 2.426616471110952e-05, "epoch": 11.168316831683168, "percentage": 55.84, "elapsed_time": "4:00:23", "remaining_time": "3:10:05", "throughput": 1485.51, "total_tokens": 21426592} {"current_steps": 101525, "total_steps": 181800, "loss": 0.0834, "lr": 2.4263765680965962e-05, "epoch": 11.168866886688669, "percentage": 55.84, "elapsed_time": "4:00:24", "remaining_time": "3:10:05", "throughput": 1485.51, "total_tokens": 21427616} {"current_steps": 101530, "total_steps": 181800, "loss": 0.0367, "lr": 2.4261366657607925e-05, "epoch": 11.16941694169417, "percentage": 55.85, "elapsed_time": "4:00:25", "remaining_time": "3:10:04", "throughput": 1485.51, "total_tokens": 21428672} {"current_steps": 101535, "total_steps": 181800, "loss": 0.0477, "lr": 2.4258967641057525e-05, "epoch": 11.16996699669967, "percentage": 55.85, "elapsed_time": "4:00:25", "remaining_time": "3:10:03", "throughput": 1485.51, "total_tokens": 21429728} {"current_steps": 101540, "total_steps": 181800, "loss": 0.0045, "lr": 2.4256568631336854e-05, "epoch": 11.17051705170517, "percentage": 55.85, "elapsed_time": "4:00:26", "remaining_time": "3:10:03", "throughput": 1485.52, "total_tokens": 21430784} {"current_steps": 101545, "total_steps": 181800, "loss": 0.0037, "lr": 2.425416962846804e-05, "epoch": 11.171067106710671, "percentage": 55.86, "elapsed_time": "4:00:27", "remaining_time": "3:10:02", "throughput": 1485.52, "total_tokens": 21431808} {"current_steps": 101550, "total_steps": 181800, "loss": 0.062, "lr": 2.4251770632473178e-05, "epoch": 11.171617161716172, "percentage": 55.86, "elapsed_time": "4:00:27", "remaining_time": "3:10:01", "throughput": 1485.52, "total_tokens": 21432832} {"current_steps": 101555, "total_steps": 181800, "loss": 0.0408, "lr": 2.4249371643374398e-05, "epoch": 11.172167216721672, "percentage": 55.86, "elapsed_time": "4:00:28", "remaining_time": "3:10:00", "throughput": 1485.52, "total_tokens": 21433888} {"current_steps": 101560, "total_steps": 181800, "loss": 0.0267, "lr": 2.4246972661193797e-05, "epoch": 11.172717271727173, "percentage": 55.86, "elapsed_time": "4:00:29", "remaining_time": "3:10:00", "throughput": 1485.52, "total_tokens": 21434944} {"current_steps": 101565, "total_steps": 181800, "loss": 0.003, "lr": 2.4244573685953482e-05, "epoch": 11.173267326732674, "percentage": 55.87, "elapsed_time": "4:00:29", "remaining_time": "3:09:59", "throughput": 1485.52, "total_tokens": 21435968} {"current_steps": 101570, "total_steps": 181800, "loss": 0.0229, "lr": 2.4242174717675572e-05, "epoch": 11.173817381738173, "percentage": 55.87, "elapsed_time": "4:00:30", "remaining_time": "3:09:58", "throughput": 1485.52, "total_tokens": 21436992} {"current_steps": 101575, "total_steps": 181800, "loss": 0.0038, "lr": 2.4239775756382183e-05, "epoch": 11.174367436743674, "percentage": 55.87, "elapsed_time": "4:00:31", "remaining_time": "3:09:57", "throughput": 1485.52, "total_tokens": 21438016} {"current_steps": 101580, "total_steps": 181800, "loss": 0.0066, "lr": 2.42373768020954e-05, "epoch": 11.174917491749175, "percentage": 55.87, "elapsed_time": "4:00:31", "remaining_time": "3:09:57", "throughput": 1485.53, "total_tokens": 21439104} {"current_steps": 101585, "total_steps": 181800, "loss": 0.0285, "lr": 2.423497785483736e-05, "epoch": 11.175467546754675, "percentage": 55.88, "elapsed_time": "4:00:32", "remaining_time": "3:09:56", "throughput": 1485.53, "total_tokens": 21440128} {"current_steps": 101590, "total_steps": 181800, "loss": 0.0584, "lr": 2.4232578914630153e-05, "epoch": 11.176017601760176, "percentage": 55.88, "elapsed_time": "4:00:33", "remaining_time": "3:09:55", "throughput": 1485.53, "total_tokens": 21441184} {"current_steps": 101595, "total_steps": 181800, "loss": 0.0303, "lr": 2.423017998149591e-05, "epoch": 11.176567656765677, "percentage": 55.88, "elapsed_time": "4:00:34", "remaining_time": "3:09:55", "throughput": 1485.53, "total_tokens": 21442240} {"current_steps": 101600, "total_steps": 181800, "loss": 0.0125, "lr": 2.422778105545672e-05, "epoch": 11.177117711771178, "percentage": 55.89, "elapsed_time": "4:00:34", "remaining_time": "3:09:54", "throughput": 1485.53, "total_tokens": 21443264} {"current_steps": 101605, "total_steps": 181800, "loss": 0.0045, "lr": 2.4225382136534702e-05, "epoch": 11.177667766776677, "percentage": 55.89, "elapsed_time": "4:00:35", "remaining_time": "3:09:53", "throughput": 1485.53, "total_tokens": 21444288} {"current_steps": 101610, "total_steps": 181800, "loss": 0.0351, "lr": 2.422298322475197e-05, "epoch": 11.178217821782178, "percentage": 55.89, "elapsed_time": "4:00:36", "remaining_time": "3:09:52", "throughput": 1485.53, "total_tokens": 21445280} {"current_steps": 101615, "total_steps": 181800, "loss": 0.007, "lr": 2.422058432013062e-05, "epoch": 11.17876787678768, "percentage": 55.89, "elapsed_time": "4:00:36", "remaining_time": "3:09:52", "throughput": 1485.53, "total_tokens": 21446336} {"current_steps": 101620, "total_steps": 181800, "loss": 0.077, "lr": 2.421818542269278e-05, "epoch": 11.179317931793179, "percentage": 55.9, "elapsed_time": "4:00:37", "remaining_time": "3:09:51", "throughput": 1485.53, "total_tokens": 21447328} {"current_steps": 101625, "total_steps": 181800, "loss": 0.0031, "lr": 2.4215786532460548e-05, "epoch": 11.17986798679868, "percentage": 55.9, "elapsed_time": "4:00:38", "remaining_time": "3:09:50", "throughput": 1485.53, "total_tokens": 21448416} {"current_steps": 101630, "total_steps": 181800, "loss": 0.0106, "lr": 2.4213387649456026e-05, "epoch": 11.180418041804181, "percentage": 55.9, "elapsed_time": "4:00:38", "remaining_time": "3:09:49", "throughput": 1485.54, "total_tokens": 21449472} {"current_steps": 101635, "total_steps": 181800, "loss": 0.0272, "lr": 2.4210988773701347e-05, "epoch": 11.18096809680968, "percentage": 55.9, "elapsed_time": "4:00:39", "remaining_time": "3:09:49", "throughput": 1485.54, "total_tokens": 21450496} {"current_steps": 101640, "total_steps": 181800, "loss": 0.0145, "lr": 2.4208589905218592e-05, "epoch": 11.181518151815181, "percentage": 55.91, "elapsed_time": "4:00:40", "remaining_time": "3:09:48", "throughput": 1485.54, "total_tokens": 21451584} {"current_steps": 101645, "total_steps": 181800, "loss": 0.0041, "lr": 2.420619104402989e-05, "epoch": 11.182068206820682, "percentage": 55.91, "elapsed_time": "4:00:40", "remaining_time": "3:09:47", "throughput": 1485.54, "total_tokens": 21452608} {"current_steps": 101650, "total_steps": 181800, "loss": 0.0127, "lr": 2.4203792190157353e-05, "epoch": 11.182618261826182, "percentage": 55.91, "elapsed_time": "4:00:41", "remaining_time": "3:09:47", "throughput": 1485.54, "total_tokens": 21453664} {"current_steps": 101655, "total_steps": 181800, "loss": 0.003, "lr": 2.4201393343623068e-05, "epoch": 11.183168316831683, "percentage": 55.92, "elapsed_time": "4:00:42", "remaining_time": "3:09:46", "throughput": 1485.54, "total_tokens": 21454688} {"current_steps": 101660, "total_steps": 181800, "loss": 0.0419, "lr": 2.4198994504449164e-05, "epoch": 11.183718371837184, "percentage": 55.92, "elapsed_time": "4:00:43", "remaining_time": "3:09:45", "throughput": 1485.55, "total_tokens": 21455808} {"current_steps": 101665, "total_steps": 181800, "loss": 0.0017, "lr": 2.4196595672657735e-05, "epoch": 11.184268426842685, "percentage": 55.92, "elapsed_time": "4:00:43", "remaining_time": "3:09:44", "throughput": 1485.55, "total_tokens": 21456800} {"current_steps": 101670, "total_steps": 181800, "loss": 0.0342, "lr": 2.419419684827091e-05, "epoch": 11.184818481848184, "percentage": 55.92, "elapsed_time": "4:00:44", "remaining_time": "3:09:44", "throughput": 1485.55, "total_tokens": 21457888} {"current_steps": 101675, "total_steps": 181800, "loss": 0.0054, "lr": 2.4191798031310782e-05, "epoch": 11.185368536853685, "percentage": 55.93, "elapsed_time": "4:00:45", "remaining_time": "3:09:43", "throughput": 1485.55, "total_tokens": 21458912} {"current_steps": 101680, "total_steps": 181800, "loss": 0.0383, "lr": 2.4189399221799456e-05, "epoch": 11.185918591859187, "percentage": 55.93, "elapsed_time": "4:00:45", "remaining_time": "3:09:42", "throughput": 1485.55, "total_tokens": 21459936} {"current_steps": 101685, "total_steps": 181800, "loss": 0.0126, "lr": 2.418700041975906e-05, "epoch": 11.186468646864686, "percentage": 55.93, "elapsed_time": "4:00:46", "remaining_time": "3:09:41", "throughput": 1485.55, "total_tokens": 21460992} {"current_steps": 101690, "total_steps": 181800, "loss": 0.0593, "lr": 2.418460162521168e-05, "epoch": 11.187018701870187, "percentage": 55.94, "elapsed_time": "4:00:47", "remaining_time": "3:09:41", "throughput": 1485.56, "total_tokens": 21462080} {"current_steps": 101695, "total_steps": 181800, "loss": 0.0397, "lr": 2.4182202838179446e-05, "epoch": 11.187568756875688, "percentage": 55.94, "elapsed_time": "4:00:47", "remaining_time": "3:09:40", "throughput": 1485.56, "total_tokens": 21463072} {"current_steps": 101700, "total_steps": 181800, "loss": 0.0014, "lr": 2.4179804058684455e-05, "epoch": 11.188118811881187, "percentage": 55.94, "elapsed_time": "4:00:48", "remaining_time": "3:09:39", "throughput": 1485.56, "total_tokens": 21464160} {"current_steps": 101705, "total_steps": 181800, "loss": 0.0101, "lr": 2.4177405286748805e-05, "epoch": 11.188668866886688, "percentage": 55.94, "elapsed_time": "4:00:49", "remaining_time": "3:09:39", "throughput": 1485.56, "total_tokens": 21465184} {"current_steps": 101710, "total_steps": 181800, "loss": 0.0044, "lr": 2.4175006522394632e-05, "epoch": 11.18921892189219, "percentage": 55.95, "elapsed_time": "4:00:49", "remaining_time": "3:09:38", "throughput": 1485.56, "total_tokens": 21466208} {"current_steps": 101715, "total_steps": 181800, "loss": 0.1214, "lr": 2.4172607765644013e-05, "epoch": 11.189768976897689, "percentage": 55.95, "elapsed_time": "4:00:50", "remaining_time": "3:09:37", "throughput": 1485.56, "total_tokens": 21467264} {"current_steps": 101720, "total_steps": 181800, "loss": 0.0043, "lr": 2.417020901651908e-05, "epoch": 11.19031903190319, "percentage": 55.95, "elapsed_time": "4:00:51", "remaining_time": "3:09:36", "throughput": 1485.56, "total_tokens": 21468320} {"current_steps": 101725, "total_steps": 181800, "loss": 0.0026, "lr": 2.4167810275041935e-05, "epoch": 11.190869086908691, "percentage": 55.95, "elapsed_time": "4:00:51", "remaining_time": "3:09:36", "throughput": 1485.57, "total_tokens": 21469376} {"current_steps": 101730, "total_steps": 181800, "loss": 0.0121, "lr": 2.416541154123467e-05, "epoch": 11.191419141914192, "percentage": 55.96, "elapsed_time": "4:00:52", "remaining_time": "3:09:35", "throughput": 1485.56, "total_tokens": 21470336} {"current_steps": 101735, "total_steps": 181800, "loss": 0.0342, "lr": 2.416301281511942e-05, "epoch": 11.191969196919691, "percentage": 55.96, "elapsed_time": "4:00:53", "remaining_time": "3:09:34", "throughput": 1485.56, "total_tokens": 21471392} {"current_steps": 101740, "total_steps": 181800, "loss": 0.002, "lr": 2.416061409671827e-05, "epoch": 11.192519251925193, "percentage": 55.96, "elapsed_time": "4:00:54", "remaining_time": "3:09:34", "throughput": 1485.56, "total_tokens": 21472416} {"current_steps": 101745, "total_steps": 181800, "loss": 0.0017, "lr": 2.4158215386053344e-05, "epoch": 11.193069306930694, "percentage": 55.97, "elapsed_time": "4:00:54", "remaining_time": "3:09:33", "throughput": 1485.56, "total_tokens": 21473472} {"current_steps": 101750, "total_steps": 181800, "loss": 0.1817, "lr": 2.4155816683146746e-05, "epoch": 11.193619361936193, "percentage": 55.97, "elapsed_time": "4:00:55", "remaining_time": "3:09:32", "throughput": 1485.56, "total_tokens": 21474464} {"current_steps": 101755, "total_steps": 181800, "loss": 0.0866, "lr": 2.415341798802057e-05, "epoch": 11.194169416941694, "percentage": 55.97, "elapsed_time": "4:00:56", "remaining_time": "3:09:31", "throughput": 1485.56, "total_tokens": 21475520} {"current_steps": 101760, "total_steps": 181800, "loss": 0.0373, "lr": 2.415101930069694e-05, "epoch": 11.194719471947195, "percentage": 55.97, "elapsed_time": "4:00:56", "remaining_time": "3:09:31", "throughput": 1485.57, "total_tokens": 21476576} {"current_steps": 101765, "total_steps": 181800, "loss": 0.0161, "lr": 2.414862062119796e-05, "epoch": 11.195269526952695, "percentage": 55.98, "elapsed_time": "4:00:57", "remaining_time": "3:09:30", "throughput": 1485.56, "total_tokens": 21477536} {"current_steps": 101770, "total_steps": 181800, "loss": 0.011, "lr": 2.4146221949545726e-05, "epoch": 11.195819581958196, "percentage": 55.98, "elapsed_time": "4:00:58", "remaining_time": "3:09:29", "throughput": 1485.56, "total_tokens": 21478528} {"current_steps": 101775, "total_steps": 181800, "loss": 0.0015, "lr": 2.4143823285762364e-05, "epoch": 11.196369636963697, "percentage": 55.98, "elapsed_time": "4:00:58", "remaining_time": "3:09:28", "throughput": 1485.56, "total_tokens": 21479584} {"current_steps": 101780, "total_steps": 181800, "loss": 0.002, "lr": 2.4141424629869964e-05, "epoch": 11.196919691969198, "percentage": 55.98, "elapsed_time": "4:00:59", "remaining_time": "3:09:28", "throughput": 1485.56, "total_tokens": 21480608} {"current_steps": 101785, "total_steps": 181800, "loss": 0.0052, "lr": 2.413902598189065e-05, "epoch": 11.197469746974697, "percentage": 55.99, "elapsed_time": "4:01:00", "remaining_time": "3:09:27", "throughput": 1485.56, "total_tokens": 21481632} {"current_steps": 101790, "total_steps": 181800, "loss": 0.2565, "lr": 2.4136627341846518e-05, "epoch": 11.198019801980198, "percentage": 55.99, "elapsed_time": "4:01:00", "remaining_time": "3:09:26", "throughput": 1485.56, "total_tokens": 21482624} {"current_steps": 101795, "total_steps": 181800, "loss": 0.0015, "lr": 2.413422870975967e-05, "epoch": 11.1985698569857, "percentage": 55.99, "elapsed_time": "4:01:01", "remaining_time": "3:09:26", "throughput": 1485.56, "total_tokens": 21483648} {"current_steps": 101800, "total_steps": 181800, "loss": 0.1099, "lr": 2.4131830085652226e-05, "epoch": 11.199119911991199, "percentage": 56.0, "elapsed_time": "4:01:02", "remaining_time": "3:09:25", "throughput": 1485.56, "total_tokens": 21484704} {"current_steps": 101805, "total_steps": 181800, "loss": 0.0833, "lr": 2.4129431469546285e-05, "epoch": 11.1996699669967, "percentage": 56.0, "elapsed_time": "4:01:03", "remaining_time": "3:09:24", "throughput": 1485.56, "total_tokens": 21485728} {"current_steps": 101810, "total_steps": 181800, "loss": 0.0091, "lr": 2.4127032861463965e-05, "epoch": 11.2002200220022, "percentage": 56.0, "elapsed_time": "4:01:03", "remaining_time": "3:09:23", "throughput": 1485.56, "total_tokens": 21486784} {"current_steps": 101815, "total_steps": 181800, "loss": 0.0062, "lr": 2.412463426142736e-05, "epoch": 11.2007700770077, "percentage": 56.0, "elapsed_time": "4:01:04", "remaining_time": "3:09:23", "throughput": 1485.57, "total_tokens": 21487872} {"current_steps": 101820, "total_steps": 181800, "loss": 0.0021, "lr": 2.4122235669458575e-05, "epoch": 11.201320132013201, "percentage": 56.01, "elapsed_time": "4:01:05", "remaining_time": "3:09:22", "throughput": 1485.56, "total_tokens": 21488832} {"current_steps": 101825, "total_steps": 181800, "loss": 0.0029, "lr": 2.411983708557973e-05, "epoch": 11.201870187018702, "percentage": 56.01, "elapsed_time": "4:01:05", "remaining_time": "3:09:21", "throughput": 1485.57, "total_tokens": 21489952} {"current_steps": 101830, "total_steps": 181800, "loss": 0.0106, "lr": 2.4117438509812917e-05, "epoch": 11.202420242024202, "percentage": 56.01, "elapsed_time": "4:01:06", "remaining_time": "3:09:20", "throughput": 1485.57, "total_tokens": 21491008} {"current_steps": 101835, "total_steps": 181800, "loss": 0.0732, "lr": 2.4115039942180255e-05, "epoch": 11.202970297029703, "percentage": 56.01, "elapsed_time": "4:01:07", "remaining_time": "3:09:20", "throughput": 1485.57, "total_tokens": 21492064} {"current_steps": 101840, "total_steps": 181800, "loss": 0.0129, "lr": 2.411264138270385e-05, "epoch": 11.203520352035204, "percentage": 56.02, "elapsed_time": "4:01:07", "remaining_time": "3:09:19", "throughput": 1485.58, "total_tokens": 21493152} {"current_steps": 101845, "total_steps": 181800, "loss": 0.0074, "lr": 2.4110242831405792e-05, "epoch": 11.204070407040705, "percentage": 56.02, "elapsed_time": "4:01:08", "remaining_time": "3:09:18", "throughput": 1485.58, "total_tokens": 21494272} {"current_steps": 101850, "total_steps": 181800, "loss": 0.0136, "lr": 2.4107844288308206e-05, "epoch": 11.204620462046204, "percentage": 56.02, "elapsed_time": "4:01:09", "remaining_time": "3:09:18", "throughput": 1485.59, "total_tokens": 21495392} {"current_steps": 101855, "total_steps": 181800, "loss": 0.1621, "lr": 2.4105445753433185e-05, "epoch": 11.205170517051705, "percentage": 56.03, "elapsed_time": "4:01:09", "remaining_time": "3:09:17", "throughput": 1485.59, "total_tokens": 21496352} {"current_steps": 101860, "total_steps": 181800, "loss": 0.0025, "lr": 2.4103047226802848e-05, "epoch": 11.205720572057206, "percentage": 56.03, "elapsed_time": "4:01:10", "remaining_time": "3:09:16", "throughput": 1485.59, "total_tokens": 21497376} {"current_steps": 101865, "total_steps": 181800, "loss": 0.0031, "lr": 2.4100648708439298e-05, "epoch": 11.206270627062706, "percentage": 56.03, "elapsed_time": "4:01:11", "remaining_time": "3:09:15", "throughput": 1485.59, "total_tokens": 21498464} {"current_steps": 101870, "total_steps": 181800, "loss": 0.0365, "lr": 2.4098250198364626e-05, "epoch": 11.206820682068207, "percentage": 56.03, "elapsed_time": "4:01:12", "remaining_time": "3:09:15", "throughput": 1485.59, "total_tokens": 21499520} {"current_steps": 101875, "total_steps": 181800, "loss": 0.0642, "lr": 2.4095851696600953e-05, "epoch": 11.207370737073708, "percentage": 56.04, "elapsed_time": "4:01:12", "remaining_time": "3:09:14", "throughput": 1485.6, "total_tokens": 21500608} {"current_steps": 101880, "total_steps": 181800, "loss": 0.0008, "lr": 2.409345320317038e-05, "epoch": 11.207920792079207, "percentage": 56.04, "elapsed_time": "4:01:13", "remaining_time": "3:09:13", "throughput": 1485.6, "total_tokens": 21501696} {"current_steps": 101885, "total_steps": 181800, "loss": 0.1922, "lr": 2.4091054718095022e-05, "epoch": 11.208470847084708, "percentage": 56.04, "elapsed_time": "4:01:14", "remaining_time": "3:09:12", "throughput": 1485.6, "total_tokens": 21502752} {"current_steps": 101890, "total_steps": 181800, "loss": 0.0047, "lr": 2.408865624139697e-05, "epoch": 11.20902090209021, "percentage": 56.05, "elapsed_time": "4:01:14", "remaining_time": "3:09:12", "throughput": 1485.61, "total_tokens": 21503840} {"current_steps": 101895, "total_steps": 181800, "loss": 0.1462, "lr": 2.4086257773098334e-05, "epoch": 11.209570957095709, "percentage": 56.05, "elapsed_time": "4:01:15", "remaining_time": "3:09:11", "throughput": 1485.6, "total_tokens": 21504832} {"current_steps": 101900, "total_steps": 181800, "loss": 0.0652, "lr": 2.408385931322123e-05, "epoch": 11.21012101210121, "percentage": 56.05, "elapsed_time": "4:01:16", "remaining_time": "3:09:10", "throughput": 1485.61, "total_tokens": 21505888} {"current_steps": 101905, "total_steps": 181800, "loss": 0.0028, "lr": 2.4081460861787747e-05, "epoch": 11.210671067106711, "percentage": 56.05, "elapsed_time": "4:01:16", "remaining_time": "3:09:10", "throughput": 1485.61, "total_tokens": 21506912} {"current_steps": 101910, "total_steps": 181800, "loss": 0.0114, "lr": 2.4079062418820002e-05, "epoch": 11.211221122112212, "percentage": 56.06, "elapsed_time": "4:01:17", "remaining_time": "3:09:09", "throughput": 1485.61, "total_tokens": 21508032} {"current_steps": 101915, "total_steps": 181800, "loss": 0.0064, "lr": 2.40766639843401e-05, "epoch": 11.211771177117711, "percentage": 56.06, "elapsed_time": "4:01:18", "remaining_time": "3:09:08", "throughput": 1485.62, "total_tokens": 21509088} {"current_steps": 101920, "total_steps": 181800, "loss": 0.0944, "lr": 2.4074265558370128e-05, "epoch": 11.212321232123212, "percentage": 56.06, "elapsed_time": "4:01:18", "remaining_time": "3:09:07", "throughput": 1485.62, "total_tokens": 21510144} {"current_steps": 101925, "total_steps": 181800, "loss": 0.045, "lr": 2.4071867140932224e-05, "epoch": 11.212871287128714, "percentage": 56.06, "elapsed_time": "4:01:19", "remaining_time": "3:09:07", "throughput": 1485.62, "total_tokens": 21511168} {"current_steps": 101930, "total_steps": 181800, "loss": 0.0766, "lr": 2.4069468732048468e-05, "epoch": 11.213421342134213, "percentage": 56.07, "elapsed_time": "4:01:20", "remaining_time": "3:09:06", "throughput": 1485.63, "total_tokens": 21512320} {"current_steps": 101935, "total_steps": 181800, "loss": 0.0225, "lr": 2.4067070331740972e-05, "epoch": 11.213971397139714, "percentage": 56.07, "elapsed_time": "4:01:20", "remaining_time": "3:09:05", "throughput": 1485.63, "total_tokens": 21513440} {"current_steps": 101940, "total_steps": 181800, "loss": 0.0055, "lr": 2.4064671940031846e-05, "epoch": 11.214521452145215, "percentage": 56.07, "elapsed_time": "4:01:21", "remaining_time": "3:09:04", "throughput": 1485.64, "total_tokens": 21514528} {"current_steps": 101945, "total_steps": 181800, "loss": 0.1312, "lr": 2.406227355694318e-05, "epoch": 11.215071507150714, "percentage": 56.08, "elapsed_time": "4:01:22", "remaining_time": "3:09:04", "throughput": 1485.64, "total_tokens": 21515584} {"current_steps": 101950, "total_steps": 181800, "loss": 0.0121, "lr": 2.4059875182497095e-05, "epoch": 11.215621562156215, "percentage": 56.08, "elapsed_time": "4:01:23", "remaining_time": "3:09:03", "throughput": 1485.64, "total_tokens": 21516672} {"current_steps": 101955, "total_steps": 181800, "loss": 0.0035, "lr": 2.4057476816715696e-05, "epoch": 11.216171617161717, "percentage": 56.08, "elapsed_time": "4:01:23", "remaining_time": "3:09:02", "throughput": 1485.65, "total_tokens": 21517728} {"current_steps": 101960, "total_steps": 181800, "loss": 0.0168, "lr": 2.405507845962107e-05, "epoch": 11.216721672167218, "percentage": 56.08, "elapsed_time": "4:01:24", "remaining_time": "3:09:02", "throughput": 1485.65, "total_tokens": 21518784} {"current_steps": 101965, "total_steps": 181800, "loss": 0.1147, "lr": 2.4052680111235338e-05, "epoch": 11.217271727172717, "percentage": 56.09, "elapsed_time": "4:01:25", "remaining_time": "3:09:01", "throughput": 1485.65, "total_tokens": 21519840} {"current_steps": 101970, "total_steps": 181800, "loss": 0.0803, "lr": 2.405028177158059e-05, "epoch": 11.217821782178218, "percentage": 56.09, "elapsed_time": "4:01:25", "remaining_time": "3:09:00", "throughput": 1485.65, "total_tokens": 21520832} {"current_steps": 101975, "total_steps": 181800, "loss": 0.0053, "lr": 2.4047883440678948e-05, "epoch": 11.218371837183719, "percentage": 56.09, "elapsed_time": "4:01:26", "remaining_time": "3:08:59", "throughput": 1485.66, "total_tokens": 21521952} {"current_steps": 101980, "total_steps": 181800, "loss": 0.0446, "lr": 2.404548511855251e-05, "epoch": 11.218921892189218, "percentage": 56.09, "elapsed_time": "4:01:27", "remaining_time": "3:08:59", "throughput": 1485.66, "total_tokens": 21523008} {"current_steps": 101985, "total_steps": 181800, "loss": 0.0084, "lr": 2.404308680522337e-05, "epoch": 11.21947194719472, "percentage": 56.1, "elapsed_time": "4:01:27", "remaining_time": "3:08:58", "throughput": 1485.66, "total_tokens": 21524064} {"current_steps": 101990, "total_steps": 181800, "loss": 0.0153, "lr": 2.4040688500713642e-05, "epoch": 11.22002200220022, "percentage": 56.1, "elapsed_time": "4:01:28", "remaining_time": "3:08:57", "throughput": 1485.67, "total_tokens": 21525184} {"current_steps": 101995, "total_steps": 181800, "loss": 0.0136, "lr": 2.4038290205045425e-05, "epoch": 11.22057205720572, "percentage": 56.1, "elapsed_time": "4:01:29", "remaining_time": "3:08:56", "throughput": 1485.67, "total_tokens": 21526240} {"current_steps": 102000, "total_steps": 181800, "loss": 0.1146, "lr": 2.4035891918240835e-05, "epoch": 11.221122112211221, "percentage": 56.11, "elapsed_time": "4:01:29", "remaining_time": "3:08:56", "throughput": 1485.67, "total_tokens": 21527328} {"current_steps": 102005, "total_steps": 181800, "loss": 0.0021, "lr": 2.403349364032196e-05, "epoch": 11.221672167216722, "percentage": 56.11, "elapsed_time": "4:01:30", "remaining_time": "3:08:55", "throughput": 1485.67, "total_tokens": 21528384} {"current_steps": 102010, "total_steps": 181800, "loss": 0.0123, "lr": 2.4031095371310906e-05, "epoch": 11.222222222222221, "percentage": 56.11, "elapsed_time": "4:01:31", "remaining_time": "3:08:54", "throughput": 1485.67, "total_tokens": 21529408} {"current_steps": 102015, "total_steps": 181800, "loss": 0.0117, "lr": 2.4028697111229796e-05, "epoch": 11.222772277227723, "percentage": 56.11, "elapsed_time": "4:01:32", "remaining_time": "3:08:54", "throughput": 1485.68, "total_tokens": 21530496} {"current_steps": 102020, "total_steps": 181800, "loss": 0.037, "lr": 2.4026298860100702e-05, "epoch": 11.223322332233224, "percentage": 56.12, "elapsed_time": "4:01:32", "remaining_time": "3:08:53", "throughput": 1485.68, "total_tokens": 21531552} {"current_steps": 102025, "total_steps": 181800, "loss": 0.05, "lr": 2.4023900617945753e-05, "epoch": 11.223872387238725, "percentage": 56.12, "elapsed_time": "4:01:33", "remaining_time": "3:08:52", "throughput": 1485.69, "total_tokens": 21532640} {"current_steps": 102030, "total_steps": 181800, "loss": 0.0387, "lr": 2.4021502384787047e-05, "epoch": 11.224422442244224, "percentage": 56.12, "elapsed_time": "4:01:34", "remaining_time": "3:08:51", "throughput": 1485.69, "total_tokens": 21533728} {"current_steps": 102035, "total_steps": 181800, "loss": 0.1616, "lr": 2.401910416064667e-05, "epoch": 11.224972497249725, "percentage": 56.12, "elapsed_time": "4:01:34", "remaining_time": "3:08:51", "throughput": 1485.69, "total_tokens": 21534752} {"current_steps": 102040, "total_steps": 181800, "loss": 0.0018, "lr": 2.4016705945546752e-05, "epoch": 11.225522552255226, "percentage": 56.13, "elapsed_time": "4:01:35", "remaining_time": "3:08:50", "throughput": 1485.69, "total_tokens": 21535840} {"current_steps": 102045, "total_steps": 181800, "loss": 0.0018, "lr": 2.4014307739509376e-05, "epoch": 11.226072607260726, "percentage": 56.13, "elapsed_time": "4:01:36", "remaining_time": "3:08:49", "throughput": 1485.69, "total_tokens": 21536832} {"current_steps": 102050, "total_steps": 181800, "loss": 0.0973, "lr": 2.4011909542556655e-05, "epoch": 11.226622662266227, "percentage": 56.13, "elapsed_time": "4:01:36", "remaining_time": "3:08:48", "throughput": 1485.7, "total_tokens": 21537888} {"current_steps": 102055, "total_steps": 181800, "loss": 0.0032, "lr": 2.4009511354710698e-05, "epoch": 11.227172717271728, "percentage": 56.14, "elapsed_time": "4:01:37", "remaining_time": "3:08:48", "throughput": 1485.7, "total_tokens": 21538976} {"current_steps": 102060, "total_steps": 181800, "loss": 0.0547, "lr": 2.4007113175993587e-05, "epoch": 11.227722772277227, "percentage": 56.14, "elapsed_time": "4:01:38", "remaining_time": "3:08:47", "throughput": 1485.7, "total_tokens": 21540064} {"current_steps": 102065, "total_steps": 181800, "loss": 0.0701, "lr": 2.4004715006427444e-05, "epoch": 11.228272827282728, "percentage": 56.14, "elapsed_time": "4:01:38", "remaining_time": "3:08:46", "throughput": 1485.71, "total_tokens": 21541152} {"current_steps": 102070, "total_steps": 181800, "loss": 0.0843, "lr": 2.400231684603436e-05, "epoch": 11.22882288228823, "percentage": 56.14, "elapsed_time": "4:01:39", "remaining_time": "3:08:46", "throughput": 1485.71, "total_tokens": 21542240} {"current_steps": 102075, "total_steps": 181800, "loss": 0.008, "lr": 2.399991869483645e-05, "epoch": 11.229372937293729, "percentage": 56.15, "elapsed_time": "4:01:40", "remaining_time": "3:08:45", "throughput": 1485.72, "total_tokens": 21543296} {"current_steps": 102080, "total_steps": 181800, "loss": 0.0054, "lr": 2.399752055285581e-05, "epoch": 11.22992299229923, "percentage": 56.15, "elapsed_time": "4:01:40", "remaining_time": "3:08:44", "throughput": 1485.71, "total_tokens": 21544288} {"current_steps": 102085, "total_steps": 181800, "loss": 0.0094, "lr": 2.3995122420114532e-05, "epoch": 11.23047304730473, "percentage": 56.15, "elapsed_time": "4:01:41", "remaining_time": "3:08:43", "throughput": 1485.71, "total_tokens": 21545280} {"current_steps": 102090, "total_steps": 181800, "loss": 0.0095, "lr": 2.399272429663474e-05, "epoch": 11.231023102310232, "percentage": 56.16, "elapsed_time": "4:01:42", "remaining_time": "3:08:43", "throughput": 1485.71, "total_tokens": 21546336} {"current_steps": 102095, "total_steps": 181800, "loss": 0.0122, "lr": 2.399032618243851e-05, "epoch": 11.231573157315731, "percentage": 56.16, "elapsed_time": "4:01:43", "remaining_time": "3:08:42", "throughput": 1485.71, "total_tokens": 21547360} {"current_steps": 102100, "total_steps": 181800, "loss": 0.0109, "lr": 2.3987928077547975e-05, "epoch": 11.232123212321232, "percentage": 56.16, "elapsed_time": "4:01:43", "remaining_time": "3:08:41", "throughput": 1485.72, "total_tokens": 21548416} {"current_steps": 102105, "total_steps": 181800, "loss": 0.0093, "lr": 2.3985529981985217e-05, "epoch": 11.232673267326733, "percentage": 56.16, "elapsed_time": "4:01:44", "remaining_time": "3:08:40", "throughput": 1485.72, "total_tokens": 21549504} {"current_steps": 102110, "total_steps": 181800, "loss": 0.0046, "lr": 2.3983131895772333e-05, "epoch": 11.233223322332233, "percentage": 56.17, "elapsed_time": "4:01:45", "remaining_time": "3:08:40", "throughput": 1485.72, "total_tokens": 21550560} {"current_steps": 102115, "total_steps": 181800, "loss": 0.0009, "lr": 2.398073381893145e-05, "epoch": 11.233773377337734, "percentage": 56.17, "elapsed_time": "4:01:45", "remaining_time": "3:08:39", "throughput": 1485.73, "total_tokens": 21551648} {"current_steps": 102120, "total_steps": 181800, "loss": 0.052, "lr": 2.397833575148464e-05, "epoch": 11.234323432343235, "percentage": 56.17, "elapsed_time": "4:01:46", "remaining_time": "3:08:38", "throughput": 1485.73, "total_tokens": 21552768} {"current_steps": 102125, "total_steps": 181800, "loss": 0.0044, "lr": 2.3975937693454025e-05, "epoch": 11.234873487348734, "percentage": 56.17, "elapsed_time": "4:01:47", "remaining_time": "3:08:38", "throughput": 1485.74, "total_tokens": 21553888} {"current_steps": 102130, "total_steps": 181800, "loss": 0.0127, "lr": 2.3973539644861707e-05, "epoch": 11.235423542354235, "percentage": 56.18, "elapsed_time": "4:01:47", "remaining_time": "3:08:37", "throughput": 1485.74, "total_tokens": 21554880} {"current_steps": 102135, "total_steps": 181800, "loss": 0.0042, "lr": 2.3971141605729775e-05, "epoch": 11.235973597359736, "percentage": 56.18, "elapsed_time": "4:01:48", "remaining_time": "3:08:36", "throughput": 1485.74, "total_tokens": 21555936} {"current_steps": 102140, "total_steps": 181800, "loss": 0.0011, "lr": 2.3968743576080335e-05, "epoch": 11.236523652365236, "percentage": 56.18, "elapsed_time": "4:01:49", "remaining_time": "3:08:35", "throughput": 1485.74, "total_tokens": 21556992} {"current_steps": 102145, "total_steps": 181800, "loss": 0.0043, "lr": 2.39663455559355e-05, "epoch": 11.237073707370737, "percentage": 56.19, "elapsed_time": "4:01:49", "remaining_time": "3:08:35", "throughput": 1485.75, "total_tokens": 21558080} {"current_steps": 102150, "total_steps": 181800, "loss": 0.0268, "lr": 2.396394754531735e-05, "epoch": 11.237623762376238, "percentage": 56.19, "elapsed_time": "4:01:50", "remaining_time": "3:08:34", "throughput": 1485.75, "total_tokens": 21559104} {"current_steps": 102155, "total_steps": 181800, "loss": 0.0122, "lr": 2.3961549544248005e-05, "epoch": 11.238173817381739, "percentage": 56.19, "elapsed_time": "4:01:51", "remaining_time": "3:08:33", "throughput": 1485.74, "total_tokens": 21560096} {"current_steps": 102160, "total_steps": 181800, "loss": 0.0061, "lr": 2.3959151552749553e-05, "epoch": 11.238723872387238, "percentage": 56.19, "elapsed_time": "4:01:52", "remaining_time": "3:08:33", "throughput": 1485.74, "total_tokens": 21561152} {"current_steps": 102165, "total_steps": 181800, "loss": 0.0737, "lr": 2.3956753570844108e-05, "epoch": 11.23927392739274, "percentage": 56.2, "elapsed_time": "4:01:52", "remaining_time": "3:08:32", "throughput": 1485.75, "total_tokens": 21562240} {"current_steps": 102170, "total_steps": 181800, "loss": 0.0174, "lr": 2.395435559855377e-05, "epoch": 11.23982398239824, "percentage": 56.2, "elapsed_time": "4:01:53", "remaining_time": "3:08:31", "throughput": 1485.75, "total_tokens": 21563296} {"current_steps": 102175, "total_steps": 181800, "loss": 0.011, "lr": 2.3951957635900623e-05, "epoch": 11.24037403740374, "percentage": 56.2, "elapsed_time": "4:01:54", "remaining_time": "3:08:30", "throughput": 1485.75, "total_tokens": 21564288} {"current_steps": 102180, "total_steps": 181800, "loss": 0.0081, "lr": 2.3949559682906785e-05, "epoch": 11.24092409240924, "percentage": 56.2, "elapsed_time": "4:01:54", "remaining_time": "3:08:30", "throughput": 1485.75, "total_tokens": 21565312} {"current_steps": 102185, "total_steps": 181800, "loss": 0.0094, "lr": 2.394716173959435e-05, "epoch": 11.241474147414742, "percentage": 56.21, "elapsed_time": "4:01:55", "remaining_time": "3:08:29", "throughput": 1485.75, "total_tokens": 21566368} {"current_steps": 102190, "total_steps": 181800, "loss": 0.0056, "lr": 2.3944763805985426e-05, "epoch": 11.242024202420241, "percentage": 56.21, "elapsed_time": "4:01:56", "remaining_time": "3:08:28", "throughput": 1485.76, "total_tokens": 21567456} {"current_steps": 102195, "total_steps": 181800, "loss": 0.0022, "lr": 2.3942365882102104e-05, "epoch": 11.242574257425742, "percentage": 56.21, "elapsed_time": "4:01:56", "remaining_time": "3:08:27", "throughput": 1485.75, "total_tokens": 21568480} {"current_steps": 102200, "total_steps": 181800, "loss": 0.0049, "lr": 2.393996796796648e-05, "epoch": 11.243124312431243, "percentage": 56.22, "elapsed_time": "4:01:57", "remaining_time": "3:08:27", "throughput": 1485.73, "total_tokens": 21569472} {"current_steps": 102205, "total_steps": 181800, "loss": 0.0418, "lr": 2.393757006360068e-05, "epoch": 11.243674367436745, "percentage": 56.22, "elapsed_time": "4:01:58", "remaining_time": "3:08:26", "throughput": 1485.74, "total_tokens": 21570592} {"current_steps": 102210, "total_steps": 181800, "loss": 0.01, "lr": 2.393517216902677e-05, "epoch": 11.244224422442244, "percentage": 56.22, "elapsed_time": "4:01:59", "remaining_time": "3:08:25", "throughput": 1485.74, "total_tokens": 21571616} {"current_steps": 102215, "total_steps": 181800, "loss": 0.0039, "lr": 2.3932774284266874e-05, "epoch": 11.244774477447745, "percentage": 56.22, "elapsed_time": "4:01:59", "remaining_time": "3:08:25", "throughput": 1485.74, "total_tokens": 21572672} {"current_steps": 102220, "total_steps": 181800, "loss": 0.0196, "lr": 2.3930376409343086e-05, "epoch": 11.245324532453246, "percentage": 56.23, "elapsed_time": "4:02:00", "remaining_time": "3:08:24", "throughput": 1485.74, "total_tokens": 21573664} {"current_steps": 102225, "total_steps": 181800, "loss": 0.1755, "lr": 2.39279785442775e-05, "epoch": 11.245874587458745, "percentage": 56.23, "elapsed_time": "4:02:01", "remaining_time": "3:08:23", "throughput": 1485.74, "total_tokens": 21574720} {"current_steps": 102230, "total_steps": 181800, "loss": 0.0021, "lr": 2.392558068909223e-05, "epoch": 11.246424642464246, "percentage": 56.23, "elapsed_time": "4:02:01", "remaining_time": "3:08:23", "throughput": 1485.74, "total_tokens": 21575808} {"current_steps": 102235, "total_steps": 181800, "loss": 0.0049, "lr": 2.3923182843809362e-05, "epoch": 11.246974697469748, "percentage": 56.23, "elapsed_time": "4:02:02", "remaining_time": "3:08:22", "throughput": 1485.75, "total_tokens": 21576896} {"current_steps": 102240, "total_steps": 181800, "loss": 0.0342, "lr": 2.3920785008451e-05, "epoch": 11.247524752475247, "percentage": 56.24, "elapsed_time": "4:02:03", "remaining_time": "3:08:21", "throughput": 1485.75, "total_tokens": 21577952} {"current_steps": 102245, "total_steps": 181800, "loss": 0.0026, "lr": 2.3918387183039255e-05, "epoch": 11.248074807480748, "percentage": 56.24, "elapsed_time": "4:02:03", "remaining_time": "3:08:20", "throughput": 1485.75, "total_tokens": 21579008} {"current_steps": 102250, "total_steps": 181800, "loss": 0.0049, "lr": 2.39159893675962e-05, "epoch": 11.248624862486249, "percentage": 56.24, "elapsed_time": "4:02:04", "remaining_time": "3:08:20", "throughput": 1485.75, "total_tokens": 21580064} {"current_steps": 102255, "total_steps": 181800, "loss": 0.1067, "lr": 2.3913591562143962e-05, "epoch": 11.249174917491748, "percentage": 56.25, "elapsed_time": "4:02:05", "remaining_time": "3:08:19", "throughput": 1485.75, "total_tokens": 21581088} {"current_steps": 102260, "total_steps": 181800, "loss": 0.032, "lr": 2.391119376670462e-05, "epoch": 11.24972497249725, "percentage": 56.25, "elapsed_time": "4:02:06", "remaining_time": "3:08:18", "throughput": 1485.76, "total_tokens": 21582144} {"current_steps": 102265, "total_steps": 181800, "loss": 0.0521, "lr": 2.3908795981300297e-05, "epoch": 11.25027502750275, "percentage": 56.25, "elapsed_time": "4:02:06", "remaining_time": "3:08:17", "throughput": 1485.76, "total_tokens": 21583200} {"current_steps": 102270, "total_steps": 181800, "loss": 0.0101, "lr": 2.390639820595307e-05, "epoch": 11.250825082508252, "percentage": 56.25, "elapsed_time": "4:02:07", "remaining_time": "3:08:17", "throughput": 1485.76, "total_tokens": 21584256} {"current_steps": 102275, "total_steps": 181800, "loss": 0.0496, "lr": 2.390400044068504e-05, "epoch": 11.251375137513751, "percentage": 56.26, "elapsed_time": "4:02:08", "remaining_time": "3:08:16", "throughput": 1485.76, "total_tokens": 21585312} {"current_steps": 102280, "total_steps": 181800, "loss": 0.006, "lr": 2.3901602685518317e-05, "epoch": 11.251925192519252, "percentage": 56.26, "elapsed_time": "4:02:08", "remaining_time": "3:08:15", "throughput": 1485.77, "total_tokens": 21586400} {"current_steps": 102285, "total_steps": 181800, "loss": 0.0025, "lr": 2.3899204940474994e-05, "epoch": 11.252475247524753, "percentage": 56.26, "elapsed_time": "4:02:09", "remaining_time": "3:08:15", "throughput": 1485.77, "total_tokens": 21587456} {"current_steps": 102290, "total_steps": 181800, "loss": 0.0078, "lr": 2.3896807205577177e-05, "epoch": 11.253025302530252, "percentage": 56.27, "elapsed_time": "4:02:10", "remaining_time": "3:08:14", "throughput": 1485.77, "total_tokens": 21588544} {"current_steps": 102295, "total_steps": 181800, "loss": 0.0082, "lr": 2.3894409480846954e-05, "epoch": 11.253575357535754, "percentage": 56.27, "elapsed_time": "4:02:10", "remaining_time": "3:08:13", "throughput": 1485.77, "total_tokens": 21589600} {"current_steps": 102300, "total_steps": 181800, "loss": 0.003, "lr": 2.3892011766306422e-05, "epoch": 11.254125412541255, "percentage": 56.27, "elapsed_time": "4:02:11", "remaining_time": "3:08:12", "throughput": 1485.78, "total_tokens": 21590720} {"current_steps": 102305, "total_steps": 181800, "loss": 0.0261, "lr": 2.38896140619777e-05, "epoch": 11.254675467546754, "percentage": 56.27, "elapsed_time": "4:02:12", "remaining_time": "3:08:12", "throughput": 1485.78, "total_tokens": 21591776} {"current_steps": 102310, "total_steps": 181800, "loss": 0.0706, "lr": 2.3887216367882863e-05, "epoch": 11.255225522552255, "percentage": 56.28, "elapsed_time": "4:02:12", "remaining_time": "3:08:11", "throughput": 1485.78, "total_tokens": 21592832} {"current_steps": 102315, "total_steps": 181800, "loss": 0.0011, "lr": 2.388481868404402e-05, "epoch": 11.255775577557756, "percentage": 56.28, "elapsed_time": "4:02:13", "remaining_time": "3:08:10", "throughput": 1485.79, "total_tokens": 21593952} {"current_steps": 102320, "total_steps": 181800, "loss": 0.0093, "lr": 2.3882421010483274e-05, "epoch": 11.256325632563255, "percentage": 56.28, "elapsed_time": "4:02:14", "remaining_time": "3:08:09", "throughput": 1485.8, "total_tokens": 21595072} {"current_steps": 102325, "total_steps": 181800, "loss": 0.036, "lr": 2.3880023347222706e-05, "epoch": 11.256875687568757, "percentage": 56.28, "elapsed_time": "4:02:15", "remaining_time": "3:08:09", "throughput": 1485.8, "total_tokens": 21596160} {"current_steps": 102330, "total_steps": 181800, "loss": 0.0013, "lr": 2.3877625694284435e-05, "epoch": 11.257425742574258, "percentage": 56.29, "elapsed_time": "4:02:15", "remaining_time": "3:08:08", "throughput": 1485.8, "total_tokens": 21597216} {"current_steps": 102335, "total_steps": 181800, "loss": 0.0057, "lr": 2.387522805169055e-05, "epoch": 11.257975797579759, "percentage": 56.29, "elapsed_time": "4:02:16", "remaining_time": "3:08:07", "throughput": 1485.81, "total_tokens": 21598272} {"current_steps": 102340, "total_steps": 181800, "loss": 0.0007, "lr": 2.387283041946313e-05, "epoch": 11.258525852585258, "percentage": 56.29, "elapsed_time": "4:02:17", "remaining_time": "3:08:07", "throughput": 1485.81, "total_tokens": 21599360} {"current_steps": 102345, "total_steps": 181800, "loss": 0.0022, "lr": 2.3870432797624315e-05, "epoch": 11.25907590759076, "percentage": 56.3, "elapsed_time": "4:02:17", "remaining_time": "3:08:06", "throughput": 1485.81, "total_tokens": 21600416} {"current_steps": 102350, "total_steps": 181800, "loss": 0.0116, "lr": 2.3868035186196163e-05, "epoch": 11.25962596259626, "percentage": 56.3, "elapsed_time": "4:02:18", "remaining_time": "3:08:05", "throughput": 1485.81, "total_tokens": 21601408} {"current_steps": 102355, "total_steps": 181800, "loss": 0.0951, "lr": 2.3865637585200794e-05, "epoch": 11.26017601760176, "percentage": 56.3, "elapsed_time": "4:02:19", "remaining_time": "3:08:04", "throughput": 1485.81, "total_tokens": 21602464} {"current_steps": 102360, "total_steps": 181800, "loss": 0.0027, "lr": 2.3863239994660306e-05, "epoch": 11.26072607260726, "percentage": 56.3, "elapsed_time": "4:02:19", "remaining_time": "3:08:04", "throughput": 1485.81, "total_tokens": 21603488} {"current_steps": 102365, "total_steps": 181800, "loss": 0.0036, "lr": 2.3860842414596775e-05, "epoch": 11.261276127612762, "percentage": 56.31, "elapsed_time": "4:02:20", "remaining_time": "3:08:03", "throughput": 1485.82, "total_tokens": 21604544} {"current_steps": 102370, "total_steps": 181800, "loss": 0.0083, "lr": 2.3858444845032322e-05, "epoch": 11.261826182618261, "percentage": 56.31, "elapsed_time": "4:02:21", "remaining_time": "3:08:02", "throughput": 1485.82, "total_tokens": 21605632} {"current_steps": 102375, "total_steps": 181800, "loss": 0.0119, "lr": 2.3856047285989028e-05, "epoch": 11.262376237623762, "percentage": 56.31, "elapsed_time": "4:02:21", "remaining_time": "3:08:01", "throughput": 1485.82, "total_tokens": 21606624} {"current_steps": 102380, "total_steps": 181800, "loss": 0.0032, "lr": 2.3853649737489007e-05, "epoch": 11.262926292629263, "percentage": 56.31, "elapsed_time": "4:02:22", "remaining_time": "3:08:01", "throughput": 1485.82, "total_tokens": 21607680} {"current_steps": 102385, "total_steps": 181800, "loss": 0.0755, "lr": 2.3851252199554344e-05, "epoch": 11.263476347634764, "percentage": 56.32, "elapsed_time": "4:02:23", "remaining_time": "3:08:00", "throughput": 1485.82, "total_tokens": 21608704} {"current_steps": 102390, "total_steps": 181800, "loss": 0.1124, "lr": 2.384885467220713e-05, "epoch": 11.264026402640264, "percentage": 56.32, "elapsed_time": "4:02:23", "remaining_time": "3:07:59", "throughput": 1485.82, "total_tokens": 21609792} {"current_steps": 102395, "total_steps": 181800, "loss": 0.0455, "lr": 2.384645715546948e-05, "epoch": 11.264576457645765, "percentage": 56.32, "elapsed_time": "4:02:24", "remaining_time": "3:07:59", "throughput": 1485.82, "total_tokens": 21610816} {"current_steps": 102400, "total_steps": 181800, "loss": 0.0014, "lr": 2.384405964936347e-05, "epoch": 11.265126512651266, "percentage": 56.33, "elapsed_time": "4:02:25", "remaining_time": "3:07:58", "throughput": 1485.83, "total_tokens": 21611904} {"current_steps": 102405, "total_steps": 181800, "loss": 0.0242, "lr": 2.384166215391122e-05, "epoch": 11.265676567656765, "percentage": 56.33, "elapsed_time": "4:02:26", "remaining_time": "3:07:57", "throughput": 1485.83, "total_tokens": 21612960} {"current_steps": 102410, "total_steps": 181800, "loss": 0.0043, "lr": 2.3839264669134807e-05, "epoch": 11.266226622662266, "percentage": 56.33, "elapsed_time": "4:02:26", "remaining_time": "3:07:56", "throughput": 1485.83, "total_tokens": 21613952} {"current_steps": 102415, "total_steps": 181800, "loss": 0.0665, "lr": 2.3836867195056335e-05, "epoch": 11.266776677667767, "percentage": 56.33, "elapsed_time": "4:02:27", "remaining_time": "3:07:56", "throughput": 1485.83, "total_tokens": 21614976} {"current_steps": 102420, "total_steps": 181800, "loss": 0.1268, "lr": 2.3834469731697908e-05, "epoch": 11.267326732673267, "percentage": 56.34, "elapsed_time": "4:02:28", "remaining_time": "3:07:55", "throughput": 1485.83, "total_tokens": 21615968} {"current_steps": 102425, "total_steps": 181800, "loss": 0.1991, "lr": 2.38320722790816e-05, "epoch": 11.267876787678768, "percentage": 56.34, "elapsed_time": "4:02:28", "remaining_time": "3:07:54", "throughput": 1485.83, "total_tokens": 21617056} {"current_steps": 102430, "total_steps": 181800, "loss": 0.0363, "lr": 2.382967483722953e-05, "epoch": 11.268426842684269, "percentage": 56.34, "elapsed_time": "4:02:29", "remaining_time": "3:07:53", "throughput": 1485.83, "total_tokens": 21618144} {"current_steps": 102435, "total_steps": 181800, "loss": 0.0085, "lr": 2.382727740616379e-05, "epoch": 11.268976897689768, "percentage": 56.34, "elapsed_time": "4:02:30", "remaining_time": "3:07:53", "throughput": 1485.83, "total_tokens": 21619136} {"current_steps": 102440, "total_steps": 181800, "loss": 0.0213, "lr": 2.382487998590646e-05, "epoch": 11.26952695269527, "percentage": 56.35, "elapsed_time": "4:02:30", "remaining_time": "3:07:52", "throughput": 1485.83, "total_tokens": 21620192} {"current_steps": 102445, "total_steps": 181800, "loss": 0.002, "lr": 2.382248257647965e-05, "epoch": 11.27007700770077, "percentage": 56.35, "elapsed_time": "4:02:31", "remaining_time": "3:07:51", "throughput": 1485.84, "total_tokens": 21621280} {"current_steps": 102450, "total_steps": 181800, "loss": 0.08, "lr": 2.3820085177905455e-05, "epoch": 11.270627062706271, "percentage": 56.35, "elapsed_time": "4:02:32", "remaining_time": "3:07:51", "throughput": 1485.84, "total_tokens": 21622304} {"current_steps": 102455, "total_steps": 181800, "loss": 0.0036, "lr": 2.3817687790205976e-05, "epoch": 11.27117711771177, "percentage": 56.36, "elapsed_time": "4:02:32", "remaining_time": "3:07:50", "throughput": 1485.84, "total_tokens": 21623360} {"current_steps": 102460, "total_steps": 181800, "loss": 0.0144, "lr": 2.3815290413403295e-05, "epoch": 11.271727172717272, "percentage": 56.36, "elapsed_time": "4:02:33", "remaining_time": "3:07:49", "throughput": 1485.84, "total_tokens": 21624384} {"current_steps": 102465, "total_steps": 181800, "loss": 0.0039, "lr": 2.381289304751951e-05, "epoch": 11.272277227722773, "percentage": 56.36, "elapsed_time": "4:02:34", "remaining_time": "3:07:48", "throughput": 1485.84, "total_tokens": 21625408} {"current_steps": 102470, "total_steps": 181800, "loss": 0.0275, "lr": 2.3810495692576725e-05, "epoch": 11.272827282728272, "percentage": 56.36, "elapsed_time": "4:02:35", "remaining_time": "3:07:48", "throughput": 1485.85, "total_tokens": 21626528} {"current_steps": 102475, "total_steps": 181800, "loss": 0.008, "lr": 2.380809834859702e-05, "epoch": 11.273377337733773, "percentage": 56.37, "elapsed_time": "4:02:35", "remaining_time": "3:07:47", "throughput": 1485.85, "total_tokens": 21627552} {"current_steps": 102480, "total_steps": 181800, "loss": 0.0016, "lr": 2.3805701015602517e-05, "epoch": 11.273927392739274, "percentage": 56.37, "elapsed_time": "4:02:36", "remaining_time": "3:07:46", "throughput": 1485.85, "total_tokens": 21628576} {"current_steps": 102485, "total_steps": 181800, "loss": 0.0654, "lr": 2.3803303693615288e-05, "epoch": 11.274477447744774, "percentage": 56.37, "elapsed_time": "4:02:37", "remaining_time": "3:07:45", "throughput": 1485.85, "total_tokens": 21629600} {"current_steps": 102490, "total_steps": 181800, "loss": 0.0079, "lr": 2.3800906382657428e-05, "epoch": 11.275027502750275, "percentage": 56.38, "elapsed_time": "4:02:37", "remaining_time": "3:07:45", "throughput": 1485.85, "total_tokens": 21630656} {"current_steps": 102495, "total_steps": 181800, "loss": 0.0019, "lr": 2.3798509082751054e-05, "epoch": 11.275577557755776, "percentage": 56.38, "elapsed_time": "4:02:38", "remaining_time": "3:07:44", "throughput": 1485.85, "total_tokens": 21631712} {"current_steps": 102500, "total_steps": 181800, "loss": 0.0062, "lr": 2.379611179391823e-05, "epoch": 11.276127612761275, "percentage": 56.38, "elapsed_time": "4:02:39", "remaining_time": "3:07:43", "throughput": 1485.85, "total_tokens": 21632736} {"current_steps": 102505, "total_steps": 181800, "loss": 0.0073, "lr": 2.379371451618107e-05, "epoch": 11.276677667766776, "percentage": 56.38, "elapsed_time": "4:02:39", "remaining_time": "3:07:43", "throughput": 1485.86, "total_tokens": 21633824} {"current_steps": 102510, "total_steps": 181800, "loss": 0.0088, "lr": 2.3791317249561673e-05, "epoch": 11.277227722772277, "percentage": 56.39, "elapsed_time": "4:02:40", "remaining_time": "3:07:42", "throughput": 1485.86, "total_tokens": 21634912} {"current_steps": 102515, "total_steps": 181800, "loss": 0.0037, "lr": 2.378891999408211e-05, "epoch": 11.277777777777779, "percentage": 56.39, "elapsed_time": "4:02:41", "remaining_time": "3:07:41", "throughput": 1485.86, "total_tokens": 21635968} {"current_steps": 102520, "total_steps": 181800, "loss": 0.0081, "lr": 2.3786522749764502e-05, "epoch": 11.278327832783278, "percentage": 56.39, "elapsed_time": "4:02:41", "remaining_time": "3:07:40", "throughput": 1485.86, "total_tokens": 21637024} {"current_steps": 102525, "total_steps": 181800, "loss": 0.0211, "lr": 2.3784125516630927e-05, "epoch": 11.278877887788779, "percentage": 56.39, "elapsed_time": "4:02:42", "remaining_time": "3:07:40", "throughput": 1485.87, "total_tokens": 21638112} {"current_steps": 102530, "total_steps": 181800, "loss": 0.0047, "lr": 2.378172829470348e-05, "epoch": 11.27942794279428, "percentage": 56.4, "elapsed_time": "4:02:43", "remaining_time": "3:07:39", "throughput": 1485.87, "total_tokens": 21639168} {"current_steps": 102535, "total_steps": 181800, "loss": 0.0401, "lr": 2.377933108400427e-05, "epoch": 11.27997799779978, "percentage": 56.4, "elapsed_time": "4:02:43", "remaining_time": "3:07:38", "throughput": 1485.87, "total_tokens": 21640192} {"current_steps": 102540, "total_steps": 181800, "loss": 0.0722, "lr": 2.3776933884555368e-05, "epoch": 11.28052805280528, "percentage": 56.4, "elapsed_time": "4:02:44", "remaining_time": "3:07:37", "throughput": 1485.87, "total_tokens": 21641184} {"current_steps": 102545, "total_steps": 181800, "loss": 0.0019, "lr": 2.3774536696378887e-05, "epoch": 11.281078107810782, "percentage": 56.41, "elapsed_time": "4:02:45", "remaining_time": "3:07:37", "throughput": 1485.87, "total_tokens": 21642240} {"current_steps": 102550, "total_steps": 181800, "loss": 0.052, "lr": 2.3772139519496917e-05, "epoch": 11.281628162816281, "percentage": 56.41, "elapsed_time": "4:02:46", "remaining_time": "3:07:36", "throughput": 1485.87, "total_tokens": 21643296} {"current_steps": 102555, "total_steps": 181800, "loss": 0.0918, "lr": 2.3769742353931537e-05, "epoch": 11.282178217821782, "percentage": 56.41, "elapsed_time": "4:02:46", "remaining_time": "3:07:35", "throughput": 1485.88, "total_tokens": 21644352} {"current_steps": 102560, "total_steps": 181800, "loss": 0.0019, "lr": 2.3767345199704858e-05, "epoch": 11.282728272827283, "percentage": 56.41, "elapsed_time": "4:02:47", "remaining_time": "3:07:35", "throughput": 1485.88, "total_tokens": 21645408} {"current_steps": 102565, "total_steps": 181800, "loss": 0.0561, "lr": 2.3764948056838958e-05, "epoch": 11.283278327832782, "percentage": 56.42, "elapsed_time": "4:02:48", "remaining_time": "3:07:34", "throughput": 1485.89, "total_tokens": 21646528} {"current_steps": 102570, "total_steps": 181800, "loss": 0.0532, "lr": 2.3762550925355954e-05, "epoch": 11.283828382838283, "percentage": 56.42, "elapsed_time": "4:02:48", "remaining_time": "3:07:33", "throughput": 1485.89, "total_tokens": 21647584} {"current_steps": 102575, "total_steps": 181800, "loss": 0.0319, "lr": 2.3760153805277914e-05, "epoch": 11.284378437843785, "percentage": 56.42, "elapsed_time": "4:02:49", "remaining_time": "3:07:32", "throughput": 1485.89, "total_tokens": 21648640} {"current_steps": 102580, "total_steps": 181800, "loss": 0.003, "lr": 2.375775669662694e-05, "epoch": 11.284928492849286, "percentage": 56.42, "elapsed_time": "4:02:50", "remaining_time": "3:07:32", "throughput": 1485.89, "total_tokens": 21649728} {"current_steps": 102585, "total_steps": 181800, "loss": 0.0061, "lr": 2.375535959942513e-05, "epoch": 11.285478547854785, "percentage": 56.43, "elapsed_time": "4:02:50", "remaining_time": "3:07:31", "throughput": 1485.89, "total_tokens": 21650752} {"current_steps": 102590, "total_steps": 181800, "loss": 0.061, "lr": 2.375296251369457e-05, "epoch": 11.286028602860286, "percentage": 56.43, "elapsed_time": "4:02:51", "remaining_time": "3:07:30", "throughput": 1485.89, "total_tokens": 21651776} {"current_steps": 102595, "total_steps": 181800, "loss": 0.0172, "lr": 2.3750565439457366e-05, "epoch": 11.286578657865787, "percentage": 56.43, "elapsed_time": "4:02:52", "remaining_time": "3:07:29", "throughput": 1485.9, "total_tokens": 21652832} {"current_steps": 102600, "total_steps": 181800, "loss": 0.0056, "lr": 2.3748168376735593e-05, "epoch": 11.287128712871286, "percentage": 56.44, "elapsed_time": "4:02:52", "remaining_time": "3:07:29", "throughput": 1485.9, "total_tokens": 21653920} {"current_steps": 102605, "total_steps": 181800, "loss": 0.0235, "lr": 2.374577132555135e-05, "epoch": 11.287678767876788, "percentage": 56.44, "elapsed_time": "4:02:53", "remaining_time": "3:07:28", "throughput": 1485.91, "total_tokens": 21655104} {"current_steps": 102610, "total_steps": 181800, "loss": 0.005, "lr": 2.3743374285926738e-05, "epoch": 11.288228822882289, "percentage": 56.44, "elapsed_time": "4:02:54", "remaining_time": "3:07:27", "throughput": 1485.91, "total_tokens": 21656128} {"current_steps": 102615, "total_steps": 181800, "loss": 0.0947, "lr": 2.3740977257883835e-05, "epoch": 11.288778877887788, "percentage": 56.44, "elapsed_time": "4:02:54", "remaining_time": "3:07:27", "throughput": 1485.91, "total_tokens": 21657184} {"current_steps": 102620, "total_steps": 181800, "loss": 0.0082, "lr": 2.3738580241444745e-05, "epoch": 11.289328932893289, "percentage": 56.45, "elapsed_time": "4:02:55", "remaining_time": "3:07:26", "throughput": 1485.91, "total_tokens": 21658208} {"current_steps": 102625, "total_steps": 181800, "loss": 0.0739, "lr": 2.3736183236631558e-05, "epoch": 11.28987898789879, "percentage": 56.45, "elapsed_time": "4:02:56", "remaining_time": "3:07:25", "throughput": 1485.92, "total_tokens": 21659328} {"current_steps": 102630, "total_steps": 181800, "loss": 0.0081, "lr": 2.3733786243466354e-05, "epoch": 11.290429042904291, "percentage": 56.45, "elapsed_time": "4:02:57", "remaining_time": "3:07:24", "throughput": 1485.92, "total_tokens": 21660416} {"current_steps": 102635, "total_steps": 181800, "loss": 0.0283, "lr": 2.373138926197124e-05, "epoch": 11.29097909790979, "percentage": 56.45, "elapsed_time": "4:02:57", "remaining_time": "3:07:24", "throughput": 1485.93, "total_tokens": 21661472} {"current_steps": 102640, "total_steps": 181800, "loss": 0.0464, "lr": 2.3728992292168302e-05, "epoch": 11.291529152915292, "percentage": 56.46, "elapsed_time": "4:02:58", "remaining_time": "3:07:23", "throughput": 1485.93, "total_tokens": 21662592} {"current_steps": 102645, "total_steps": 181800, "loss": 0.0243, "lr": 2.372659533407963e-05, "epoch": 11.292079207920793, "percentage": 56.46, "elapsed_time": "4:02:59", "remaining_time": "3:07:22", "throughput": 1485.93, "total_tokens": 21663584} {"current_steps": 102650, "total_steps": 181800, "loss": 0.0146, "lr": 2.372419838772733e-05, "epoch": 11.292629262926292, "percentage": 56.46, "elapsed_time": "4:02:59", "remaining_time": "3:07:22", "throughput": 1485.93, "total_tokens": 21664640} {"current_steps": 102655, "total_steps": 181800, "loss": 0.007, "lr": 2.372180145313346e-05, "epoch": 11.293179317931793, "percentage": 56.47, "elapsed_time": "4:03:00", "remaining_time": "3:07:21", "throughput": 1485.93, "total_tokens": 21665664} {"current_steps": 102660, "total_steps": 181800, "loss": 0.0262, "lr": 2.371940453032015e-05, "epoch": 11.293729372937294, "percentage": 56.47, "elapsed_time": "4:03:01", "remaining_time": "3:07:20", "throughput": 1485.94, "total_tokens": 21666784} {"current_steps": 102665, "total_steps": 181800, "loss": 0.0412, "lr": 2.3717007619309463e-05, "epoch": 11.294279427942794, "percentage": 56.47, "elapsed_time": "4:03:01", "remaining_time": "3:07:19", "throughput": 1485.94, "total_tokens": 21667808} {"current_steps": 102670, "total_steps": 181800, "loss": 0.014, "lr": 2.371461072012351e-05, "epoch": 11.294829482948295, "percentage": 56.47, "elapsed_time": "4:03:02", "remaining_time": "3:07:19", "throughput": 1485.94, "total_tokens": 21668832} {"current_steps": 102675, "total_steps": 181800, "loss": 0.0607, "lr": 2.3712213832784374e-05, "epoch": 11.295379537953796, "percentage": 56.48, "elapsed_time": "4:03:03", "remaining_time": "3:07:18", "throughput": 1485.94, "total_tokens": 21669856} {"current_steps": 102680, "total_steps": 181800, "loss": 0.0015, "lr": 2.3709816957314135e-05, "epoch": 11.295929592959295, "percentage": 56.48, "elapsed_time": "4:03:03", "remaining_time": "3:07:17", "throughput": 1485.94, "total_tokens": 21670848} {"current_steps": 102685, "total_steps": 181800, "loss": 0.0207, "lr": 2.3707420093734906e-05, "epoch": 11.296479647964796, "percentage": 56.48, "elapsed_time": "4:03:04", "remaining_time": "3:07:16", "throughput": 1485.94, "total_tokens": 21671872} {"current_steps": 102690, "total_steps": 181800, "loss": 0.0044, "lr": 2.3705023242068756e-05, "epoch": 11.297029702970297, "percentage": 56.49, "elapsed_time": "4:03:05", "remaining_time": "3:07:16", "throughput": 1485.94, "total_tokens": 21672960} {"current_steps": 102695, "total_steps": 181800, "loss": 0.0029, "lr": 2.3702626402337787e-05, "epoch": 11.297579757975798, "percentage": 56.49, "elapsed_time": "4:03:06", "remaining_time": "3:07:15", "throughput": 1485.95, "total_tokens": 21674048} {"current_steps": 102700, "total_steps": 181800, "loss": 0.0628, "lr": 2.3700229574564098e-05, "epoch": 11.298129812981298, "percentage": 56.49, "elapsed_time": "4:03:06", "remaining_time": "3:07:14", "throughput": 1485.95, "total_tokens": 21675136} {"current_steps": 102705, "total_steps": 181800, "loss": 0.0029, "lr": 2.369783275876975e-05, "epoch": 11.298679867986799, "percentage": 56.49, "elapsed_time": "4:03:07", "remaining_time": "3:07:14", "throughput": 1485.95, "total_tokens": 21676192} {"current_steps": 102710, "total_steps": 181800, "loss": 0.0066, "lr": 2.369543595497687e-05, "epoch": 11.2992299229923, "percentage": 56.5, "elapsed_time": "4:03:08", "remaining_time": "3:07:13", "throughput": 1485.96, "total_tokens": 21677280} {"current_steps": 102715, "total_steps": 181800, "loss": 0.0098, "lr": 2.369303916320753e-05, "epoch": 11.2997799779978, "percentage": 56.5, "elapsed_time": "4:03:08", "remaining_time": "3:07:12", "throughput": 1485.96, "total_tokens": 21678368} {"current_steps": 102720, "total_steps": 181800, "loss": 0.0146, "lr": 2.3690642383483807e-05, "epoch": 11.3003300330033, "percentage": 56.5, "elapsed_time": "4:03:09", "remaining_time": "3:07:11", "throughput": 1485.96, "total_tokens": 21679456} {"current_steps": 102725, "total_steps": 181800, "loss": 0.0197, "lr": 2.368824561582782e-05, "epoch": 11.300880088008801, "percentage": 56.5, "elapsed_time": "4:03:10", "remaining_time": "3:07:11", "throughput": 1485.97, "total_tokens": 21680512} {"current_steps": 102730, "total_steps": 181800, "loss": 0.048, "lr": 2.3685848860261634e-05, "epoch": 11.3014301430143, "percentage": 56.51, "elapsed_time": "4:03:10", "remaining_time": "3:07:10", "throughput": 1485.97, "total_tokens": 21681568} {"current_steps": 102735, "total_steps": 181800, "loss": 0.0066, "lr": 2.368345211680735e-05, "epoch": 11.301980198019802, "percentage": 56.51, "elapsed_time": "4:03:11", "remaining_time": "3:07:09", "throughput": 1485.97, "total_tokens": 21682656} {"current_steps": 102740, "total_steps": 181800, "loss": 0.0111, "lr": 2.3681055385487066e-05, "epoch": 11.302530253025303, "percentage": 56.51, "elapsed_time": "4:03:12", "remaining_time": "3:07:08", "throughput": 1485.98, "total_tokens": 21683712} {"current_steps": 102745, "total_steps": 181800, "loss": 0.0521, "lr": 2.3678658666322848e-05, "epoch": 11.303080308030804, "percentage": 56.52, "elapsed_time": "4:03:12", "remaining_time": "3:07:08", "throughput": 1485.98, "total_tokens": 21684864} {"current_steps": 102750, "total_steps": 181800, "loss": 0.1775, "lr": 2.3676261959336803e-05, "epoch": 11.303630363036303, "percentage": 56.52, "elapsed_time": "4:03:13", "remaining_time": "3:07:07", "throughput": 1485.99, "total_tokens": 21685952} {"current_steps": 102755, "total_steps": 181800, "loss": 0.0025, "lr": 2.3673865264551013e-05, "epoch": 11.304180418041804, "percentage": 56.52, "elapsed_time": "4:03:14", "remaining_time": "3:07:06", "throughput": 1485.99, "total_tokens": 21686976} {"current_steps": 102760, "total_steps": 181800, "loss": 0.0498, "lr": 2.3671468581987577e-05, "epoch": 11.304730473047305, "percentage": 56.52, "elapsed_time": "4:03:15", "remaining_time": "3:07:06", "throughput": 1485.99, "total_tokens": 21688064} {"current_steps": 102765, "total_steps": 181800, "loss": 0.0032, "lr": 2.3669071911668582e-05, "epoch": 11.305280528052805, "percentage": 56.53, "elapsed_time": "4:03:15", "remaining_time": "3:07:05", "throughput": 1485.99, "total_tokens": 21689120} {"current_steps": 102770, "total_steps": 181800, "loss": 0.0491, "lr": 2.36666752536161e-05, "epoch": 11.305830583058306, "percentage": 56.53, "elapsed_time": "4:03:16", "remaining_time": "3:07:04", "throughput": 1486.0, "total_tokens": 21690240} {"current_steps": 102775, "total_steps": 181800, "loss": 0.094, "lr": 2.3664278607852242e-05, "epoch": 11.306380638063807, "percentage": 56.53, "elapsed_time": "4:03:17", "remaining_time": "3:07:03", "throughput": 1486.0, "total_tokens": 21691296} {"current_steps": 102780, "total_steps": 181800, "loss": 0.0188, "lr": 2.3661881974399082e-05, "epoch": 11.306930693069306, "percentage": 56.53, "elapsed_time": "4:03:17", "remaining_time": "3:07:03", "throughput": 1486.0, "total_tokens": 21692320} {"current_steps": 102785, "total_steps": 181800, "loss": 0.025, "lr": 2.3659485353278718e-05, "epoch": 11.307480748074807, "percentage": 56.54, "elapsed_time": "4:03:18", "remaining_time": "3:07:02", "throughput": 1486.01, "total_tokens": 21693376} {"current_steps": 102790, "total_steps": 181800, "loss": 0.1447, "lr": 2.3657088744513234e-05, "epoch": 11.308030803080309, "percentage": 56.54, "elapsed_time": "4:03:19", "remaining_time": "3:07:01", "throughput": 1486.01, "total_tokens": 21694432} {"current_steps": 102795, "total_steps": 181800, "loss": 0.0022, "lr": 2.3654692148124714e-05, "epoch": 11.308580858085808, "percentage": 56.54, "elapsed_time": "4:03:19", "remaining_time": "3:07:00", "throughput": 1486.01, "total_tokens": 21695488} {"current_steps": 102800, "total_steps": 181800, "loss": 0.0032, "lr": 2.3652295564135256e-05, "epoch": 11.309130913091309, "percentage": 56.55, "elapsed_time": "4:03:20", "remaining_time": "3:07:00", "throughput": 1486.01, "total_tokens": 21696576} {"current_steps": 102805, "total_steps": 181800, "loss": 0.0206, "lr": 2.3649898992566936e-05, "epoch": 11.30968096809681, "percentage": 56.55, "elapsed_time": "4:03:21", "remaining_time": "3:06:59", "throughput": 1486.02, "total_tokens": 21697664} {"current_steps": 102810, "total_steps": 181800, "loss": 0.0133, "lr": 2.3647502433441856e-05, "epoch": 11.310231023102311, "percentage": 56.55, "elapsed_time": "4:03:21", "remaining_time": "3:06:58", "throughput": 1486.02, "total_tokens": 21698752} {"current_steps": 102815, "total_steps": 181800, "loss": 0.0018, "lr": 2.36451058867821e-05, "epoch": 11.31078107810781, "percentage": 56.55, "elapsed_time": "4:03:22", "remaining_time": "3:06:58", "throughput": 1486.02, "total_tokens": 21699744} {"current_steps": 102820, "total_steps": 181800, "loss": 0.0949, "lr": 2.3642709352609737e-05, "epoch": 11.311331133113312, "percentage": 56.56, "elapsed_time": "4:03:23", "remaining_time": "3:06:57", "throughput": 1486.01, "total_tokens": 21700704} {"current_steps": 102825, "total_steps": 181800, "loss": 0.0077, "lr": 2.364031283094689e-05, "epoch": 11.311881188118813, "percentage": 56.56, "elapsed_time": "4:03:23", "remaining_time": "3:06:56", "throughput": 1486.01, "total_tokens": 21701728} {"current_steps": 102830, "total_steps": 181800, "loss": 0.0028, "lr": 2.3637916321815613e-05, "epoch": 11.312431243124312, "percentage": 56.56, "elapsed_time": "4:03:24", "remaining_time": "3:06:55", "throughput": 1486.02, "total_tokens": 21702880} {"current_steps": 102835, "total_steps": 181800, "loss": 0.0949, "lr": 2.3635519825238013e-05, "epoch": 11.312981298129813, "percentage": 56.56, "elapsed_time": "4:03:25", "remaining_time": "3:06:55", "throughput": 1486.03, "total_tokens": 21703968} {"current_steps": 102840, "total_steps": 181800, "loss": 0.0217, "lr": 2.363312334123618e-05, "epoch": 11.313531353135314, "percentage": 56.57, "elapsed_time": "4:03:26", "remaining_time": "3:06:54", "throughput": 1486.03, "total_tokens": 21705024} {"current_steps": 102845, "total_steps": 181800, "loss": 0.0061, "lr": 2.363072686983218e-05, "epoch": 11.314081408140813, "percentage": 56.57, "elapsed_time": "4:03:26", "remaining_time": "3:06:53", "throughput": 1486.03, "total_tokens": 21706112} {"current_steps": 102850, "total_steps": 181800, "loss": 0.0359, "lr": 2.362833041104812e-05, "epoch": 11.314631463146315, "percentage": 56.57, "elapsed_time": "4:03:27", "remaining_time": "3:06:53", "throughput": 1486.03, "total_tokens": 21707168} {"current_steps": 102855, "total_steps": 181800, "loss": 0.1794, "lr": 2.3625933964906073e-05, "epoch": 11.315181518151816, "percentage": 56.58, "elapsed_time": "4:03:28", "remaining_time": "3:06:52", "throughput": 1486.04, "total_tokens": 21708256} {"current_steps": 102860, "total_steps": 181800, "loss": 0.0977, "lr": 2.3623537531428145e-05, "epoch": 11.315731573157315, "percentage": 56.58, "elapsed_time": "4:03:28", "remaining_time": "3:06:51", "throughput": 1486.04, "total_tokens": 21709312} {"current_steps": 102865, "total_steps": 181800, "loss": 0.021, "lr": 2.3621141110636406e-05, "epoch": 11.316281628162816, "percentage": 56.58, "elapsed_time": "4:03:29", "remaining_time": "3:06:50", "throughput": 1486.04, "total_tokens": 21710336} {"current_steps": 102870, "total_steps": 181800, "loss": 0.0814, "lr": 2.3618744702552943e-05, "epoch": 11.316831683168317, "percentage": 56.58, "elapsed_time": "4:03:30", "remaining_time": "3:06:50", "throughput": 1486.04, "total_tokens": 21711360} {"current_steps": 102875, "total_steps": 181800, "loss": 0.1986, "lr": 2.361634830719986e-05, "epoch": 11.317381738173818, "percentage": 56.59, "elapsed_time": "4:03:30", "remaining_time": "3:06:49", "throughput": 1486.04, "total_tokens": 21712416} {"current_steps": 102880, "total_steps": 181800, "loss": 0.0259, "lr": 2.361395192459921e-05, "epoch": 11.317931793179318, "percentage": 56.59, "elapsed_time": "4:03:31", "remaining_time": "3:06:48", "throughput": 1486.05, "total_tokens": 21713504} {"current_steps": 102885, "total_steps": 181800, "loss": 0.0031, "lr": 2.3611555554773122e-05, "epoch": 11.318481848184819, "percentage": 56.59, "elapsed_time": "4:03:32", "remaining_time": "3:06:47", "throughput": 1486.05, "total_tokens": 21714528} {"current_steps": 102890, "total_steps": 181800, "loss": 0.0104, "lr": 2.360915919774365e-05, "epoch": 11.31903190319032, "percentage": 56.6, "elapsed_time": "4:03:32", "remaining_time": "3:06:47", "throughput": 1486.05, "total_tokens": 21715584} {"current_steps": 102895, "total_steps": 181800, "loss": 0.0037, "lr": 2.3606762853532883e-05, "epoch": 11.319581958195819, "percentage": 56.6, "elapsed_time": "4:03:33", "remaining_time": "3:06:46", "throughput": 1486.05, "total_tokens": 21716672} {"current_steps": 102900, "total_steps": 181800, "loss": 0.0167, "lr": 2.360436652216293e-05, "epoch": 11.32013201320132, "percentage": 56.6, "elapsed_time": "4:03:34", "remaining_time": "3:06:45", "throughput": 1486.06, "total_tokens": 21717792} {"current_steps": 102905, "total_steps": 181800, "loss": 0.0016, "lr": 2.3601970203655855e-05, "epoch": 11.320682068206821, "percentage": 56.6, "elapsed_time": "4:03:35", "remaining_time": "3:06:45", "throughput": 1486.06, "total_tokens": 21718848} {"current_steps": 102910, "total_steps": 181800, "loss": 0.0374, "lr": 2.3599573898033746e-05, "epoch": 11.32123212321232, "percentage": 56.61, "elapsed_time": "4:03:35", "remaining_time": "3:06:44", "throughput": 1486.06, "total_tokens": 21719872} {"current_steps": 102915, "total_steps": 181800, "loss": 0.0316, "lr": 2.3597177605318698e-05, "epoch": 11.321782178217822, "percentage": 56.61, "elapsed_time": "4:03:36", "remaining_time": "3:06:43", "throughput": 1486.06, "total_tokens": 21720928} {"current_steps": 102920, "total_steps": 181800, "loss": 0.026, "lr": 2.3594781325532784e-05, "epoch": 11.322332233223323, "percentage": 56.61, "elapsed_time": "4:03:37", "remaining_time": "3:06:42", "throughput": 1486.07, "total_tokens": 21722016} {"current_steps": 102925, "total_steps": 181800, "loss": 0.0023, "lr": 2.35923850586981e-05, "epoch": 11.322882288228822, "percentage": 56.61, "elapsed_time": "4:03:37", "remaining_time": "3:06:42", "throughput": 1486.07, "total_tokens": 21723072} {"current_steps": 102930, "total_steps": 181800, "loss": 0.0011, "lr": 2.3589988804836734e-05, "epoch": 11.323432343234323, "percentage": 56.62, "elapsed_time": "4:03:38", "remaining_time": "3:06:41", "throughput": 1486.08, "total_tokens": 21724160} {"current_steps": 102935, "total_steps": 181800, "loss": 0.1957, "lr": 2.358759256397075e-05, "epoch": 11.323982398239824, "percentage": 56.62, "elapsed_time": "4:03:39", "remaining_time": "3:06:40", "throughput": 1486.08, "total_tokens": 21725184} {"current_steps": 102940, "total_steps": 181800, "loss": 0.1712, "lr": 2.3585196336122255e-05, "epoch": 11.324532453245325, "percentage": 56.62, "elapsed_time": "4:03:39", "remaining_time": "3:06:39", "throughput": 1486.08, "total_tokens": 21726240} {"current_steps": 102945, "total_steps": 181800, "loss": 0.0013, "lr": 2.3582800121313326e-05, "epoch": 11.325082508250825, "percentage": 56.63, "elapsed_time": "4:03:40", "remaining_time": "3:06:39", "throughput": 1486.07, "total_tokens": 21727200} {"current_steps": 102950, "total_steps": 181800, "loss": 0.0096, "lr": 2.3580403919566046e-05, "epoch": 11.325632563256326, "percentage": 56.63, "elapsed_time": "4:03:41", "remaining_time": "3:06:38", "throughput": 1486.07, "total_tokens": 21728192} {"current_steps": 102955, "total_steps": 181800, "loss": 0.0019, "lr": 2.3578007730902514e-05, "epoch": 11.326182618261827, "percentage": 56.63, "elapsed_time": "4:03:41", "remaining_time": "3:06:37", "throughput": 1486.07, "total_tokens": 21729216} {"current_steps": 102960, "total_steps": 181800, "loss": 0.0036, "lr": 2.3575611555344787e-05, "epoch": 11.326732673267326, "percentage": 56.63, "elapsed_time": "4:03:42", "remaining_time": "3:06:37", "throughput": 1486.07, "total_tokens": 21730240} {"current_steps": 102965, "total_steps": 181800, "loss": 0.094, "lr": 2.357321539291497e-05, "epoch": 11.327282728272827, "percentage": 56.64, "elapsed_time": "4:03:43", "remaining_time": "3:06:36", "throughput": 1486.07, "total_tokens": 21731296} {"current_steps": 102970, "total_steps": 181800, "loss": 0.0633, "lr": 2.357081924363514e-05, "epoch": 11.327832783278328, "percentage": 56.64, "elapsed_time": "4:03:43", "remaining_time": "3:06:35", "throughput": 1486.07, "total_tokens": 21732288} {"current_steps": 102975, "total_steps": 181800, "loss": 0.0163, "lr": 2.3568423107527393e-05, "epoch": 11.328382838283828, "percentage": 56.64, "elapsed_time": "4:03:44", "remaining_time": "3:06:34", "throughput": 1486.07, "total_tokens": 21733312} {"current_steps": 102980, "total_steps": 181800, "loss": 0.0092, "lr": 2.3566026984613797e-05, "epoch": 11.328932893289329, "percentage": 56.64, "elapsed_time": "4:03:45", "remaining_time": "3:06:34", "throughput": 1486.07, "total_tokens": 21734304} {"current_steps": 102985, "total_steps": 181800, "loss": 0.0337, "lr": 2.3563630874916436e-05, "epoch": 11.32948294829483, "percentage": 56.65, "elapsed_time": "4:03:46", "remaining_time": "3:06:33", "throughput": 1486.07, "total_tokens": 21735392} {"current_steps": 102990, "total_steps": 181800, "loss": 0.0026, "lr": 2.3561234778457414e-05, "epoch": 11.33003300330033, "percentage": 56.65, "elapsed_time": "4:03:46", "remaining_time": "3:06:32", "throughput": 1486.07, "total_tokens": 21736448} {"current_steps": 102995, "total_steps": 181800, "loss": 0.1019, "lr": 2.3558838695258788e-05, "epoch": 11.33058305830583, "percentage": 56.65, "elapsed_time": "4:03:47", "remaining_time": "3:06:31", "throughput": 1486.07, "total_tokens": 21737472} {"current_steps": 103000, "total_steps": 181800, "loss": 0.1037, "lr": 2.3556442625342658e-05, "epoch": 11.331133113311331, "percentage": 56.66, "elapsed_time": "4:03:48", "remaining_time": "3:06:31", "throughput": 1486.07, "total_tokens": 21738496} {"current_steps": 103005, "total_steps": 181800, "loss": 0.0038, "lr": 2.3554046568731105e-05, "epoch": 11.331683168316832, "percentage": 56.66, "elapsed_time": "4:03:48", "remaining_time": "3:06:30", "throughput": 1486.07, "total_tokens": 21739520} {"current_steps": 103010, "total_steps": 181800, "loss": 0.0473, "lr": 2.3551650525446206e-05, "epoch": 11.332233223322332, "percentage": 56.66, "elapsed_time": "4:03:49", "remaining_time": "3:06:29", "throughput": 1486.07, "total_tokens": 21740544} {"current_steps": 103015, "total_steps": 181800, "loss": 0.1001, "lr": 2.354925449551006e-05, "epoch": 11.332783278327833, "percentage": 56.66, "elapsed_time": "4:03:50", "remaining_time": "3:06:29", "throughput": 1486.08, "total_tokens": 21741600} {"current_steps": 103020, "total_steps": 181800, "loss": 0.0601, "lr": 2.354685847894473e-05, "epoch": 11.333333333333334, "percentage": 56.67, "elapsed_time": "4:03:50", "remaining_time": "3:06:28", "throughput": 1486.08, "total_tokens": 21742656} {"current_steps": 103025, "total_steps": 181800, "loss": 0.0696, "lr": 2.354446247577231e-05, "epoch": 11.333883388338833, "percentage": 56.67, "elapsed_time": "4:03:51", "remaining_time": "3:06:27", "throughput": 1486.08, "total_tokens": 21743744} {"current_steps": 103030, "total_steps": 181800, "loss": 0.0105, "lr": 2.3542066486014888e-05, "epoch": 11.334433443344334, "percentage": 56.67, "elapsed_time": "4:03:52", "remaining_time": "3:06:26", "throughput": 1486.08, "total_tokens": 21744736} {"current_steps": 103035, "total_steps": 181800, "loss": 0.0681, "lr": 2.353967050969453e-05, "epoch": 11.334983498349835, "percentage": 56.67, "elapsed_time": "4:03:52", "remaining_time": "3:06:26", "throughput": 1486.08, "total_tokens": 21745728} {"current_steps": 103040, "total_steps": 181800, "loss": 0.0442, "lr": 2.353727454683333e-05, "epoch": 11.335533553355335, "percentage": 56.68, "elapsed_time": "4:03:53", "remaining_time": "3:06:25", "throughput": 1486.08, "total_tokens": 21746784} {"current_steps": 103045, "total_steps": 181800, "loss": 0.0491, "lr": 2.3534878597453365e-05, "epoch": 11.336083608360836, "percentage": 56.68, "elapsed_time": "4:03:54", "remaining_time": "3:06:24", "throughput": 1486.08, "total_tokens": 21747840} {"current_steps": 103050, "total_steps": 181800, "loss": 0.002, "lr": 2.3532482661576733e-05, "epoch": 11.336633663366337, "percentage": 56.68, "elapsed_time": "4:03:55", "remaining_time": "3:06:23", "throughput": 1486.08, "total_tokens": 21748800} {"current_steps": 103055, "total_steps": 181800, "loss": 0.0492, "lr": 2.3530086739225496e-05, "epoch": 11.337183718371838, "percentage": 56.69, "elapsed_time": "4:03:55", "remaining_time": "3:06:23", "throughput": 1486.08, "total_tokens": 21749888} {"current_steps": 103060, "total_steps": 181800, "loss": 0.031, "lr": 2.352769083042174e-05, "epoch": 11.337733773377337, "percentage": 56.69, "elapsed_time": "4:03:56", "remaining_time": "3:06:22", "throughput": 1486.09, "total_tokens": 21751040} {"current_steps": 103065, "total_steps": 181800, "loss": 0.0084, "lr": 2.352529493518756e-05, "epoch": 11.338283828382838, "percentage": 56.69, "elapsed_time": "4:03:57", "remaining_time": "3:06:21", "throughput": 1486.09, "total_tokens": 21752064} {"current_steps": 103070, "total_steps": 181800, "loss": 0.0092, "lr": 2.352289905354502e-05, "epoch": 11.33883388338834, "percentage": 56.69, "elapsed_time": "4:03:57", "remaining_time": "3:06:21", "throughput": 1486.09, "total_tokens": 21753120} {"current_steps": 103075, "total_steps": 181800, "loss": 0.1113, "lr": 2.3520503185516222e-05, "epoch": 11.339383938393839, "percentage": 56.7, "elapsed_time": "4:03:58", "remaining_time": "3:06:20", "throughput": 1486.09, "total_tokens": 21754080} {"current_steps": 103080, "total_steps": 181800, "loss": 0.0813, "lr": 2.3518107331123228e-05, "epoch": 11.33993399339934, "percentage": 56.7, "elapsed_time": "4:03:59", "remaining_time": "3:06:19", "throughput": 1486.09, "total_tokens": 21755104} {"current_steps": 103085, "total_steps": 181800, "loss": 0.0072, "lr": 2.3515711490388125e-05, "epoch": 11.340484048404841, "percentage": 56.7, "elapsed_time": "4:03:59", "remaining_time": "3:06:18", "throughput": 1486.09, "total_tokens": 21756192} {"current_steps": 103090, "total_steps": 181800, "loss": 0.0119, "lr": 2.351331566333301e-05, "epoch": 11.34103410341034, "percentage": 56.71, "elapsed_time": "4:04:00", "remaining_time": "3:06:18", "throughput": 1486.09, "total_tokens": 21757216} {"current_steps": 103095, "total_steps": 181800, "loss": 0.0226, "lr": 2.351091984997994e-05, "epoch": 11.341584158415841, "percentage": 56.71, "elapsed_time": "4:04:01", "remaining_time": "3:06:17", "throughput": 1486.1, "total_tokens": 21758272} {"current_steps": 103100, "total_steps": 181800, "loss": 0.0631, "lr": 2.3508524050351012e-05, "epoch": 11.342134213421343, "percentage": 56.71, "elapsed_time": "4:04:01", "remaining_time": "3:06:16", "throughput": 1486.1, "total_tokens": 21759392} {"current_steps": 103105, "total_steps": 181800, "loss": 0.0202, "lr": 2.3506128264468306e-05, "epoch": 11.342684268426842, "percentage": 56.71, "elapsed_time": "4:04:02", "remaining_time": "3:06:15", "throughput": 1486.1, "total_tokens": 21760416} {"current_steps": 103110, "total_steps": 181800, "loss": 0.0026, "lr": 2.3503732492353887e-05, "epoch": 11.343234323432343, "percentage": 56.72, "elapsed_time": "4:04:03", "remaining_time": "3:06:15", "throughput": 1486.1, "total_tokens": 21761472} {"current_steps": 103115, "total_steps": 181800, "loss": 0.0043, "lr": 2.3501336734029855e-05, "epoch": 11.343784378437844, "percentage": 56.72, "elapsed_time": "4:04:03", "remaining_time": "3:06:14", "throughput": 1486.11, "total_tokens": 21762528} {"current_steps": 103120, "total_steps": 181800, "loss": 0.0294, "lr": 2.3498940989518288e-05, "epoch": 11.344334433443345, "percentage": 56.72, "elapsed_time": "4:04:04", "remaining_time": "3:06:13", "throughput": 1486.11, "total_tokens": 21763648} {"current_steps": 103125, "total_steps": 181800, "loss": 0.0021, "lr": 2.3496545258841245e-05, "epoch": 11.344884488448844, "percentage": 56.72, "elapsed_time": "4:04:05", "remaining_time": "3:06:13", "throughput": 1486.12, "total_tokens": 21764768} {"current_steps": 103130, "total_steps": 181800, "loss": 0.0321, "lr": 2.349414954202084e-05, "epoch": 11.345434543454346, "percentage": 56.73, "elapsed_time": "4:04:06", "remaining_time": "3:06:12", "throughput": 1486.12, "total_tokens": 21765824} {"current_steps": 103135, "total_steps": 181800, "loss": 0.0047, "lr": 2.3491753839079124e-05, "epoch": 11.345984598459847, "percentage": 56.73, "elapsed_time": "4:04:06", "remaining_time": "3:06:11", "throughput": 1486.12, "total_tokens": 21766848} {"current_steps": 103140, "total_steps": 181800, "loss": 0.0182, "lr": 2.3489358150038196e-05, "epoch": 11.346534653465346, "percentage": 56.73, "elapsed_time": "4:04:07", "remaining_time": "3:06:10", "throughput": 1486.12, "total_tokens": 21767872} {"current_steps": 103145, "total_steps": 181800, "loss": 0.0041, "lr": 2.3486962474920135e-05, "epoch": 11.347084708470847, "percentage": 56.74, "elapsed_time": "4:04:08", "remaining_time": "3:06:10", "throughput": 1486.12, "total_tokens": 21768960} {"current_steps": 103150, "total_steps": 181800, "loss": 0.0103, "lr": 2.3484566813747e-05, "epoch": 11.347634763476348, "percentage": 56.74, "elapsed_time": "4:04:08", "remaining_time": "3:06:09", "throughput": 1486.13, "total_tokens": 21770080} {"current_steps": 103155, "total_steps": 181800, "loss": 0.0046, "lr": 2.34821711665409e-05, "epoch": 11.348184818481847, "percentage": 56.74, "elapsed_time": "4:04:09", "remaining_time": "3:06:08", "throughput": 1486.13, "total_tokens": 21771104} {"current_steps": 103160, "total_steps": 181800, "loss": 0.0252, "lr": 2.3479775533323887e-05, "epoch": 11.348734873487349, "percentage": 56.74, "elapsed_time": "4:04:10", "remaining_time": "3:06:08", "throughput": 1486.13, "total_tokens": 21772192} {"current_steps": 103165, "total_steps": 181800, "loss": 0.0303, "lr": 2.3477379914118064e-05, "epoch": 11.34928492849285, "percentage": 56.75, "elapsed_time": "4:04:10", "remaining_time": "3:06:07", "throughput": 1486.14, "total_tokens": 21773280} {"current_steps": 103170, "total_steps": 181800, "loss": 0.0195, "lr": 2.3474984308945497e-05, "epoch": 11.34983498349835, "percentage": 56.75, "elapsed_time": "4:04:11", "remaining_time": "3:06:06", "throughput": 1486.14, "total_tokens": 21774336} {"current_steps": 103175, "total_steps": 181800, "loss": 0.0015, "lr": 2.3472588717828263e-05, "epoch": 11.35038503850385, "percentage": 56.75, "elapsed_time": "4:04:12", "remaining_time": "3:06:05", "throughput": 1486.14, "total_tokens": 21775360} {"current_steps": 103180, "total_steps": 181800, "loss": 0.1209, "lr": 2.3470193140788455e-05, "epoch": 11.350935093509351, "percentage": 56.75, "elapsed_time": "4:04:12", "remaining_time": "3:06:05", "throughput": 1486.15, "total_tokens": 21776448} {"current_steps": 103185, "total_steps": 181800, "loss": 0.0188, "lr": 2.3467797577848124e-05, "epoch": 11.351485148514852, "percentage": 56.76, "elapsed_time": "4:04:13", "remaining_time": "3:06:04", "throughput": 1486.15, "total_tokens": 21777536} {"current_steps": 103190, "total_steps": 181800, "loss": 0.0051, "lr": 2.3465402029029387e-05, "epoch": 11.352035203520352, "percentage": 56.76, "elapsed_time": "4:04:14", "remaining_time": "3:06:03", "throughput": 1486.15, "total_tokens": 21778528} {"current_steps": 103195, "total_steps": 181800, "loss": 0.0457, "lr": 2.34630064943543e-05, "epoch": 11.352585258525853, "percentage": 56.76, "elapsed_time": "4:04:15", "remaining_time": "3:06:02", "throughput": 1486.15, "total_tokens": 21779552} {"current_steps": 103200, "total_steps": 181800, "loss": 0.0028, "lr": 2.3460610973844934e-05, "epoch": 11.353135313531354, "percentage": 56.77, "elapsed_time": "4:04:15", "remaining_time": "3:06:02", "throughput": 1486.15, "total_tokens": 21780544} {"current_steps": 103205, "total_steps": 181800, "loss": 0.0942, "lr": 2.3458215467523392e-05, "epoch": 11.353685368536853, "percentage": 56.77, "elapsed_time": "4:04:16", "remaining_time": "3:06:01", "throughput": 1486.14, "total_tokens": 21781536} {"current_steps": 103210, "total_steps": 181800, "loss": 0.004, "lr": 2.3455819975411726e-05, "epoch": 11.354235423542354, "percentage": 56.77, "elapsed_time": "4:04:17", "remaining_time": "3:06:00", "throughput": 1486.14, "total_tokens": 21782560} {"current_steps": 103215, "total_steps": 181800, "loss": 0.0319, "lr": 2.3453424497532032e-05, "epoch": 11.354785478547855, "percentage": 56.77, "elapsed_time": "4:04:17", "remaining_time": "3:06:00", "throughput": 1486.15, "total_tokens": 21783616} {"current_steps": 103220, "total_steps": 181800, "loss": 0.0019, "lr": 2.345102903390639e-05, "epoch": 11.355335533553355, "percentage": 56.78, "elapsed_time": "4:04:18", "remaining_time": "3:05:59", "throughput": 1486.15, "total_tokens": 21784704} {"current_steps": 103225, "total_steps": 181800, "loss": 0.0323, "lr": 2.3448633584556856e-05, "epoch": 11.355885588558856, "percentage": 56.78, "elapsed_time": "4:04:19", "remaining_time": "3:05:58", "throughput": 1486.16, "total_tokens": 21785824} {"current_steps": 103230, "total_steps": 181800, "loss": 0.0023, "lr": 2.344623814950553e-05, "epoch": 11.356435643564357, "percentage": 56.78, "elapsed_time": "4:04:19", "remaining_time": "3:05:57", "throughput": 1486.16, "total_tokens": 21786848} {"current_steps": 103235, "total_steps": 181800, "loss": 0.0138, "lr": 2.3443842728774472e-05, "epoch": 11.356985698569858, "percentage": 56.78, "elapsed_time": "4:04:20", "remaining_time": "3:05:57", "throughput": 1486.17, "total_tokens": 21788000} {"current_steps": 103240, "total_steps": 181800, "loss": 0.1183, "lr": 2.3441447322385785e-05, "epoch": 11.357535753575357, "percentage": 56.79, "elapsed_time": "4:04:21", "remaining_time": "3:05:56", "throughput": 1486.17, "total_tokens": 21789024} {"current_steps": 103245, "total_steps": 181800, "loss": 0.071, "lr": 2.343905193036152e-05, "epoch": 11.358085808580858, "percentage": 56.79, "elapsed_time": "4:04:21", "remaining_time": "3:05:55", "throughput": 1486.17, "total_tokens": 21790048} {"current_steps": 103250, "total_steps": 181800, "loss": 0.0578, "lr": 2.3436656552723762e-05, "epoch": 11.35863586358636, "percentage": 56.79, "elapsed_time": "4:04:22", "remaining_time": "3:05:54", "throughput": 1486.17, "total_tokens": 21791072} {"current_steps": 103255, "total_steps": 181800, "loss": 0.0069, "lr": 2.3434261189494593e-05, "epoch": 11.359185918591859, "percentage": 56.8, "elapsed_time": "4:04:23", "remaining_time": "3:05:54", "throughput": 1486.17, "total_tokens": 21792160} {"current_steps": 103260, "total_steps": 181800, "loss": 0.0196, "lr": 2.3431865840696086e-05, "epoch": 11.35973597359736, "percentage": 56.8, "elapsed_time": "4:04:23", "remaining_time": "3:05:53", "throughput": 1486.17, "total_tokens": 21793216} {"current_steps": 103265, "total_steps": 181800, "loss": 0.016, "lr": 2.3429470506350327e-05, "epoch": 11.36028602860286, "percentage": 56.8, "elapsed_time": "4:04:24", "remaining_time": "3:05:52", "throughput": 1486.17, "total_tokens": 21794176} {"current_steps": 103270, "total_steps": 181800, "loss": 0.063, "lr": 2.3427075186479382e-05, "epoch": 11.36083608360836, "percentage": 56.8, "elapsed_time": "4:04:25", "remaining_time": "3:05:52", "throughput": 1486.18, "total_tokens": 21795296} {"current_steps": 103275, "total_steps": 181800, "loss": 0.0156, "lr": 2.342467988110532e-05, "epoch": 11.361386138613861, "percentage": 56.81, "elapsed_time": "4:04:26", "remaining_time": "3:05:51", "throughput": 1486.18, "total_tokens": 21796320} {"current_steps": 103280, "total_steps": 181800, "loss": 0.0015, "lr": 2.3422284590250244e-05, "epoch": 11.361936193619362, "percentage": 56.81, "elapsed_time": "4:04:26", "remaining_time": "3:05:50", "throughput": 1486.18, "total_tokens": 21797376} {"current_steps": 103285, "total_steps": 181800, "loss": 0.0623, "lr": 2.34198893139362e-05, "epoch": 11.362486248624862, "percentage": 56.81, "elapsed_time": "4:04:27", "remaining_time": "3:05:49", "throughput": 1486.18, "total_tokens": 21798432} {"current_steps": 103290, "total_steps": 181800, "loss": 0.0658, "lr": 2.341749405218528e-05, "epoch": 11.363036303630363, "percentage": 56.82, "elapsed_time": "4:04:28", "remaining_time": "3:05:49", "throughput": 1486.18, "total_tokens": 21799520} {"current_steps": 103295, "total_steps": 181800, "loss": 0.0026, "lr": 2.341509880501957e-05, "epoch": 11.363586358635864, "percentage": 56.82, "elapsed_time": "4:04:28", "remaining_time": "3:05:48", "throughput": 1486.19, "total_tokens": 21800576} {"current_steps": 103300, "total_steps": 181800, "loss": 0.1179, "lr": 2.3412703572461114e-05, "epoch": 11.364136413641365, "percentage": 56.82, "elapsed_time": "4:04:29", "remaining_time": "3:05:47", "throughput": 1486.19, "total_tokens": 21801600} {"current_steps": 103305, "total_steps": 181800, "loss": 0.0011, "lr": 2.3410308354532024e-05, "epoch": 11.364686468646864, "percentage": 56.82, "elapsed_time": "4:04:30", "remaining_time": "3:05:46", "throughput": 1486.19, "total_tokens": 21802624} {"current_steps": 103310, "total_steps": 181800, "loss": 0.0044, "lr": 2.3407913151254354e-05, "epoch": 11.365236523652365, "percentage": 56.83, "elapsed_time": "4:04:30", "remaining_time": "3:05:46", "throughput": 1486.19, "total_tokens": 21803648} {"current_steps": 103315, "total_steps": 181800, "loss": 0.0379, "lr": 2.3405517962650178e-05, "epoch": 11.365786578657866, "percentage": 56.83, "elapsed_time": "4:04:31", "remaining_time": "3:05:45", "throughput": 1486.19, "total_tokens": 21804704} {"current_steps": 103320, "total_steps": 181800, "loss": 0.0077, "lr": 2.340312278874159e-05, "epoch": 11.366336633663366, "percentage": 56.83, "elapsed_time": "4:04:32", "remaining_time": "3:05:44", "throughput": 1486.19, "total_tokens": 21805728} {"current_steps": 103325, "total_steps": 181800, "loss": 0.0071, "lr": 2.3400727629550643e-05, "epoch": 11.366886688668867, "percentage": 56.83, "elapsed_time": "4:04:32", "remaining_time": "3:05:44", "throughput": 1486.19, "total_tokens": 21806784} {"current_steps": 103330, "total_steps": 181800, "loss": 0.004, "lr": 2.3398332485099428e-05, "epoch": 11.367436743674368, "percentage": 56.84, "elapsed_time": "4:04:33", "remaining_time": "3:05:43", "throughput": 1486.2, "total_tokens": 21807904} {"current_steps": 103335, "total_steps": 181800, "loss": 0.0012, "lr": 2.3395937355410016e-05, "epoch": 11.367986798679867, "percentage": 56.84, "elapsed_time": "4:04:34", "remaining_time": "3:05:42", "throughput": 1486.2, "total_tokens": 21808992} {"current_steps": 103340, "total_steps": 181800, "loss": 0.0111, "lr": 2.3393542240504472e-05, "epoch": 11.368536853685368, "percentage": 56.84, "elapsed_time": "4:04:35", "remaining_time": "3:05:41", "throughput": 1486.2, "total_tokens": 21809984} {"current_steps": 103345, "total_steps": 181800, "loss": 0.0133, "lr": 2.339114714040488e-05, "epoch": 11.36908690869087, "percentage": 56.85, "elapsed_time": "4:04:35", "remaining_time": "3:05:41", "throughput": 1486.2, "total_tokens": 21811040} {"current_steps": 103350, "total_steps": 181800, "loss": 0.0036, "lr": 2.338875205513331e-05, "epoch": 11.369636963696369, "percentage": 56.85, "elapsed_time": "4:04:36", "remaining_time": "3:05:40", "throughput": 1486.2, "total_tokens": 21812128} {"current_steps": 103355, "total_steps": 181800, "loss": 0.0428, "lr": 2.338635698471185e-05, "epoch": 11.37018701870187, "percentage": 56.85, "elapsed_time": "4:04:37", "remaining_time": "3:05:39", "throughput": 1486.21, "total_tokens": 21813216} {"current_steps": 103360, "total_steps": 181800, "loss": 0.0119, "lr": 2.3383961929162558e-05, "epoch": 11.370737073707371, "percentage": 56.85, "elapsed_time": "4:04:37", "remaining_time": "3:05:38", "throughput": 1486.21, "total_tokens": 21814240} {"current_steps": 103365, "total_steps": 181800, "loss": 0.0993, "lr": 2.338156688850751e-05, "epoch": 11.371287128712872, "percentage": 56.86, "elapsed_time": "4:04:38", "remaining_time": "3:05:38", "throughput": 1486.21, "total_tokens": 21815296} {"current_steps": 103370, "total_steps": 181800, "loss": 0.0358, "lr": 2.3379171862768785e-05, "epoch": 11.371837183718371, "percentage": 56.86, "elapsed_time": "4:04:39", "remaining_time": "3:05:37", "throughput": 1486.21, "total_tokens": 21816352} {"current_steps": 103375, "total_steps": 181800, "loss": 0.0017, "lr": 2.3376776851968453e-05, "epoch": 11.372387238723872, "percentage": 56.86, "elapsed_time": "4:04:39", "remaining_time": "3:05:36", "throughput": 1486.22, "total_tokens": 21817472} {"current_steps": 103380, "total_steps": 181800, "loss": 0.0045, "lr": 2.3374381856128596e-05, "epoch": 11.372937293729374, "percentage": 56.86, "elapsed_time": "4:04:40", "remaining_time": "3:05:36", "throughput": 1486.21, "total_tokens": 21818432} {"current_steps": 103385, "total_steps": 181800, "loss": 0.0068, "lr": 2.337198687527128e-05, "epoch": 11.373487348734873, "percentage": 56.87, "elapsed_time": "4:04:41", "remaining_time": "3:05:35", "throughput": 1486.22, "total_tokens": 21819488} {"current_steps": 103390, "total_steps": 181800, "loss": 0.033, "lr": 2.3369591909418573e-05, "epoch": 11.374037403740374, "percentage": 56.87, "elapsed_time": "4:04:41", "remaining_time": "3:05:34", "throughput": 1486.22, "total_tokens": 21820480} {"current_steps": 103395, "total_steps": 181800, "loss": 0.1002, "lr": 2.3367196958592565e-05, "epoch": 11.374587458745875, "percentage": 56.87, "elapsed_time": "4:04:42", "remaining_time": "3:05:33", "throughput": 1486.22, "total_tokens": 21821536} {"current_steps": 103400, "total_steps": 181800, "loss": 0.0028, "lr": 2.336480202281531e-05, "epoch": 11.375137513751374, "percentage": 56.88, "elapsed_time": "4:04:43", "remaining_time": "3:05:33", "throughput": 1486.22, "total_tokens": 21822560} {"current_steps": 103405, "total_steps": 181800, "loss": 0.0684, "lr": 2.3362407102108898e-05, "epoch": 11.375687568756875, "percentage": 56.88, "elapsed_time": "4:04:43", "remaining_time": "3:05:32", "throughput": 1486.22, "total_tokens": 21823584} {"current_steps": 103410, "total_steps": 181800, "loss": 0.0202, "lr": 2.3360012196495397e-05, "epoch": 11.376237623762377, "percentage": 56.88, "elapsed_time": "4:04:44", "remaining_time": "3:05:31", "throughput": 1486.22, "total_tokens": 21824640} {"current_steps": 103415, "total_steps": 181800, "loss": 0.1039, "lr": 2.3357617305996864e-05, "epoch": 11.376787678767876, "percentage": 56.88, "elapsed_time": "4:04:45", "remaining_time": "3:05:31", "throughput": 1486.22, "total_tokens": 21825696} {"current_steps": 103420, "total_steps": 181800, "loss": 0.0076, "lr": 2.335522243063539e-05, "epoch": 11.377337733773377, "percentage": 56.89, "elapsed_time": "4:04:46", "remaining_time": "3:05:30", "throughput": 1486.22, "total_tokens": 21826784} {"current_steps": 103425, "total_steps": 181800, "loss": 0.0314, "lr": 2.3352827570433036e-05, "epoch": 11.377887788778878, "percentage": 56.89, "elapsed_time": "4:04:46", "remaining_time": "3:05:29", "throughput": 1486.22, "total_tokens": 21827744} {"current_steps": 103430, "total_steps": 181800, "loss": 0.0017, "lr": 2.3350432725411888e-05, "epoch": 11.37843784378438, "percentage": 56.89, "elapsed_time": "4:04:47", "remaining_time": "3:05:28", "throughput": 1486.22, "total_tokens": 21828800} {"current_steps": 103435, "total_steps": 181800, "loss": 0.0081, "lr": 2.3348037895594012e-05, "epoch": 11.378987898789878, "percentage": 56.89, "elapsed_time": "4:04:48", "remaining_time": "3:05:28", "throughput": 1486.22, "total_tokens": 21829824} {"current_steps": 103440, "total_steps": 181800, "loss": 0.01, "lr": 2.334564308100147e-05, "epoch": 11.37953795379538, "percentage": 56.9, "elapsed_time": "4:04:48", "remaining_time": "3:05:27", "throughput": 1486.23, "total_tokens": 21830944} {"current_steps": 103445, "total_steps": 181800, "loss": 0.0438, "lr": 2.3343248281656346e-05, "epoch": 11.38008800880088, "percentage": 56.9, "elapsed_time": "4:04:49", "remaining_time": "3:05:26", "throughput": 1486.23, "total_tokens": 21832064} {"current_steps": 103450, "total_steps": 181800, "loss": 0.0848, "lr": 2.33408534975807e-05, "epoch": 11.38063806380638, "percentage": 56.9, "elapsed_time": "4:04:50", "remaining_time": "3:05:25", "throughput": 1486.24, "total_tokens": 21833120} {"current_steps": 103455, "total_steps": 181800, "loss": 0.0049, "lr": 2.3338458728796626e-05, "epoch": 11.381188118811881, "percentage": 56.91, "elapsed_time": "4:04:50", "remaining_time": "3:05:25", "throughput": 1486.23, "total_tokens": 21834112} {"current_steps": 103460, "total_steps": 181800, "loss": 0.129, "lr": 2.333606397532617e-05, "epoch": 11.381738173817382, "percentage": 56.91, "elapsed_time": "4:04:51", "remaining_time": "3:05:24", "throughput": 1486.23, "total_tokens": 21835104} {"current_steps": 103465, "total_steps": 181800, "loss": 0.0011, "lr": 2.3333669237191416e-05, "epoch": 11.382288228822881, "percentage": 56.91, "elapsed_time": "4:04:52", "remaining_time": "3:05:23", "throughput": 1486.24, "total_tokens": 21836192} {"current_steps": 103470, "total_steps": 181800, "loss": 0.0993, "lr": 2.333127451441444e-05, "epoch": 11.382838283828383, "percentage": 56.91, "elapsed_time": "4:04:52", "remaining_time": "3:05:23", "throughput": 1486.24, "total_tokens": 21837216} {"current_steps": 103475, "total_steps": 181800, "loss": 0.0715, "lr": 2.3328879807017297e-05, "epoch": 11.383388338833884, "percentage": 56.92, "elapsed_time": "4:04:53", "remaining_time": "3:05:22", "throughput": 1486.24, "total_tokens": 21838240} {"current_steps": 103480, "total_steps": 181800, "loss": 0.0041, "lr": 2.3326485115022067e-05, "epoch": 11.383938393839385, "percentage": 56.92, "elapsed_time": "4:04:54", "remaining_time": "3:05:21", "throughput": 1486.24, "total_tokens": 21839264} {"current_steps": 103485, "total_steps": 181800, "loss": 0.0022, "lr": 2.3324090438450832e-05, "epoch": 11.384488448844884, "percentage": 56.92, "elapsed_time": "4:04:55", "remaining_time": "3:05:20", "throughput": 1486.24, "total_tokens": 21840320} {"current_steps": 103490, "total_steps": 181800, "loss": 0.0026, "lr": 2.332169577732563e-05, "epoch": 11.385038503850385, "percentage": 56.93, "elapsed_time": "4:04:55", "remaining_time": "3:05:20", "throughput": 1486.24, "total_tokens": 21841344} {"current_steps": 103495, "total_steps": 181800, "loss": 0.0329, "lr": 2.3319301131668576e-05, "epoch": 11.385588558855886, "percentage": 56.93, "elapsed_time": "4:04:56", "remaining_time": "3:05:19", "throughput": 1486.24, "total_tokens": 21842464} {"current_steps": 103500, "total_steps": 181800, "loss": 0.0043, "lr": 2.3316906501501706e-05, "epoch": 11.386138613861386, "percentage": 56.93, "elapsed_time": "4:04:57", "remaining_time": "3:05:18", "throughput": 1486.25, "total_tokens": 21843520} {"current_steps": 103505, "total_steps": 181800, "loss": 0.0071, "lr": 2.3314511886847096e-05, "epoch": 11.386688668866887, "percentage": 56.93, "elapsed_time": "4:04:57", "remaining_time": "3:05:17", "throughput": 1486.25, "total_tokens": 21844544} {"current_steps": 103510, "total_steps": 181800, "loss": 0.0022, "lr": 2.3312117287726833e-05, "epoch": 11.387238723872388, "percentage": 56.94, "elapsed_time": "4:04:58", "remaining_time": "3:05:17", "throughput": 1486.25, "total_tokens": 21845568} {"current_steps": 103515, "total_steps": 181800, "loss": 0.0369, "lr": 2.3309722704162963e-05, "epoch": 11.387788778877887, "percentage": 56.94, "elapsed_time": "4:04:59", "remaining_time": "3:05:16", "throughput": 1486.25, "total_tokens": 21846624} {"current_steps": 103520, "total_steps": 181800, "loss": 0.0272, "lr": 2.3307328136177575e-05, "epoch": 11.388338833883388, "percentage": 56.94, "elapsed_time": "4:04:59", "remaining_time": "3:05:15", "throughput": 1486.25, "total_tokens": 21847680} {"current_steps": 103525, "total_steps": 181800, "loss": 0.0088, "lr": 2.3304933583792737e-05, "epoch": 11.38888888888889, "percentage": 56.94, "elapsed_time": "4:05:00", "remaining_time": "3:05:15", "throughput": 1486.25, "total_tokens": 21848672} {"current_steps": 103530, "total_steps": 181800, "loss": 0.0138, "lr": 2.33025390470305e-05, "epoch": 11.389438943894389, "percentage": 56.95, "elapsed_time": "4:05:01", "remaining_time": "3:05:14", "throughput": 1486.25, "total_tokens": 21849760} {"current_steps": 103535, "total_steps": 181800, "loss": 0.0036, "lr": 2.3300144525912953e-05, "epoch": 11.38998899889989, "percentage": 56.95, "elapsed_time": "4:05:01", "remaining_time": "3:05:13", "throughput": 1486.25, "total_tokens": 21850784} {"current_steps": 103540, "total_steps": 181800, "loss": 0.0935, "lr": 2.3297750020462153e-05, "epoch": 11.39053905390539, "percentage": 56.95, "elapsed_time": "4:05:02", "remaining_time": "3:05:12", "throughput": 1486.25, "total_tokens": 21851840} {"current_steps": 103545, "total_steps": 181800, "loss": 0.0052, "lr": 2.3295355530700176e-05, "epoch": 11.391089108910892, "percentage": 56.96, "elapsed_time": "4:05:03", "remaining_time": "3:05:12", "throughput": 1486.25, "total_tokens": 21852864} {"current_steps": 103550, "total_steps": 181800, "loss": 0.0163, "lr": 2.3292961056649098e-05, "epoch": 11.391639163916391, "percentage": 56.96, "elapsed_time": "4:05:04", "remaining_time": "3:05:11", "throughput": 1486.25, "total_tokens": 21853888} {"current_steps": 103555, "total_steps": 181800, "loss": 0.0121, "lr": 2.329056659833097e-05, "epoch": 11.392189218921892, "percentage": 56.96, "elapsed_time": "4:05:04", "remaining_time": "3:05:10", "throughput": 1486.26, "total_tokens": 21854944} {"current_steps": 103560, "total_steps": 181800, "loss": 0.0858, "lr": 2.328817215576787e-05, "epoch": 11.392739273927393, "percentage": 56.96, "elapsed_time": "4:05:05", "remaining_time": "3:05:09", "throughput": 1486.26, "total_tokens": 21856032} {"current_steps": 103565, "total_steps": 181800, "loss": 0.0134, "lr": 2.3285777728981864e-05, "epoch": 11.393289328932893, "percentage": 56.97, "elapsed_time": "4:05:06", "remaining_time": "3:05:09", "throughput": 1486.26, "total_tokens": 21857024} {"current_steps": 103570, "total_steps": 181800, "loss": 0.0057, "lr": 2.3283383317995032e-05, "epoch": 11.393839383938394, "percentage": 56.97, "elapsed_time": "4:05:06", "remaining_time": "3:05:08", "throughput": 1486.26, "total_tokens": 21858080} {"current_steps": 103575, "total_steps": 181800, "loss": 0.003, "lr": 2.3280988922829426e-05, "epoch": 11.394389438943895, "percentage": 56.97, "elapsed_time": "4:05:07", "remaining_time": "3:05:07", "throughput": 1486.26, "total_tokens": 21859136} {"current_steps": 103580, "total_steps": 181800, "loss": 0.1272, "lr": 2.3278594543507115e-05, "epoch": 11.394939493949394, "percentage": 56.97, "elapsed_time": "4:05:08", "remaining_time": "3:05:07", "throughput": 1486.27, "total_tokens": 21860192} {"current_steps": 103585, "total_steps": 181800, "loss": 0.0185, "lr": 2.3276200180050184e-05, "epoch": 11.395489548954895, "percentage": 56.98, "elapsed_time": "4:05:08", "remaining_time": "3:05:06", "throughput": 1486.27, "total_tokens": 21861312} {"current_steps": 103590, "total_steps": 181800, "loss": 0.0021, "lr": 2.327380583248068e-05, "epoch": 11.396039603960396, "percentage": 56.98, "elapsed_time": "4:05:09", "remaining_time": "3:05:05", "throughput": 1486.27, "total_tokens": 21862336} {"current_steps": 103595, "total_steps": 181800, "loss": 0.0027, "lr": 2.3271411500820677e-05, "epoch": 11.396589658965897, "percentage": 56.98, "elapsed_time": "4:05:10", "remaining_time": "3:05:04", "throughput": 1486.27, "total_tokens": 21863328} {"current_steps": 103600, "total_steps": 181800, "loss": 0.0379, "lr": 2.3269017185092257e-05, "epoch": 11.397139713971397, "percentage": 56.99, "elapsed_time": "4:05:10", "remaining_time": "3:05:04", "throughput": 1486.27, "total_tokens": 21864384} {"current_steps": 103605, "total_steps": 181800, "loss": 0.0693, "lr": 2.3266622885317456e-05, "epoch": 11.397689768976898, "percentage": 56.99, "elapsed_time": "4:05:11", "remaining_time": "3:05:03", "throughput": 1486.27, "total_tokens": 21865440} {"current_steps": 103610, "total_steps": 181800, "loss": 0.0366, "lr": 2.3264228601518377e-05, "epoch": 11.398239823982399, "percentage": 56.99, "elapsed_time": "4:05:12", "remaining_time": "3:05:02", "throughput": 1486.28, "total_tokens": 21866496} {"current_steps": 103615, "total_steps": 181800, "loss": 0.0864, "lr": 2.326183433371706e-05, "epoch": 11.398789878987898, "percentage": 56.99, "elapsed_time": "4:05:12", "remaining_time": "3:05:01", "throughput": 1486.28, "total_tokens": 21867552} {"current_steps": 103620, "total_steps": 181800, "loss": 0.0052, "lr": 2.3259440081935586e-05, "epoch": 11.3993399339934, "percentage": 57.0, "elapsed_time": "4:05:13", "remaining_time": "3:05:01", "throughput": 1486.28, "total_tokens": 21868544} {"current_steps": 103625, "total_steps": 181800, "loss": 0.0012, "lr": 2.3257045846196025e-05, "epoch": 11.3998899889989, "percentage": 57.0, "elapsed_time": "4:05:14", "remaining_time": "3:05:00", "throughput": 1486.28, "total_tokens": 21869568} {"current_steps": 103630, "total_steps": 181800, "loss": 0.0078, "lr": 2.3254651626520424e-05, "epoch": 11.4004400440044, "percentage": 57.0, "elapsed_time": "4:05:15", "remaining_time": "3:04:59", "throughput": 1486.28, "total_tokens": 21870656} {"current_steps": 103635, "total_steps": 181800, "loss": 0.0073, "lr": 2.325225742293087e-05, "epoch": 11.400990099009901, "percentage": 57.0, "elapsed_time": "4:05:15", "remaining_time": "3:04:59", "throughput": 1486.28, "total_tokens": 21871680} {"current_steps": 103640, "total_steps": 181800, "loss": 0.0056, "lr": 2.324986323544941e-05, "epoch": 11.401540154015402, "percentage": 57.01, "elapsed_time": "4:05:16", "remaining_time": "3:04:58", "throughput": 1486.28, "total_tokens": 21872736} {"current_steps": 103645, "total_steps": 181800, "loss": 0.0211, "lr": 2.3247469064098133e-05, "epoch": 11.402090209020901, "percentage": 57.01, "elapsed_time": "4:05:17", "remaining_time": "3:04:57", "throughput": 1486.28, "total_tokens": 21873792} {"current_steps": 103650, "total_steps": 181800, "loss": 0.1041, "lr": 2.3245074908899086e-05, "epoch": 11.402640264026402, "percentage": 57.01, "elapsed_time": "4:05:17", "remaining_time": "3:04:56", "throughput": 1486.29, "total_tokens": 21874880} {"current_steps": 103655, "total_steps": 181800, "loss": 0.0467, "lr": 2.324268076987434e-05, "epoch": 11.403190319031903, "percentage": 57.02, "elapsed_time": "4:05:18", "remaining_time": "3:04:56", "throughput": 1486.29, "total_tokens": 21875936} {"current_steps": 103660, "total_steps": 181800, "loss": 0.0076, "lr": 2.3240286647045968e-05, "epoch": 11.403740374037405, "percentage": 57.02, "elapsed_time": "4:05:19", "remaining_time": "3:04:55", "throughput": 1486.29, "total_tokens": 21876960} {"current_steps": 103665, "total_steps": 181800, "loss": 0.007, "lr": 2.3237892540436017e-05, "epoch": 11.404290429042904, "percentage": 57.02, "elapsed_time": "4:05:19", "remaining_time": "3:04:54", "throughput": 1486.29, "total_tokens": 21877952} {"current_steps": 103670, "total_steps": 181800, "loss": 0.1345, "lr": 2.323549845006658e-05, "epoch": 11.404840484048405, "percentage": 57.02, "elapsed_time": "4:05:20", "remaining_time": "3:04:54", "throughput": 1486.29, "total_tokens": 21878976} {"current_steps": 103675, "total_steps": 181800, "loss": 0.0058, "lr": 2.3233104375959704e-05, "epoch": 11.405390539053906, "percentage": 57.03, "elapsed_time": "4:05:21", "remaining_time": "3:04:53", "throughput": 1486.29, "total_tokens": 21880064} {"current_steps": 103680, "total_steps": 181800, "loss": 0.0084, "lr": 2.323071031813745e-05, "epoch": 11.405940594059405, "percentage": 57.03, "elapsed_time": "4:05:21", "remaining_time": "3:04:52", "throughput": 1486.3, "total_tokens": 21881120} {"current_steps": 103685, "total_steps": 181800, "loss": 0.029, "lr": 2.3228316276621902e-05, "epoch": 11.406490649064907, "percentage": 57.03, "elapsed_time": "4:05:22", "remaining_time": "3:04:51", "throughput": 1486.3, "total_tokens": 21882176} {"current_steps": 103690, "total_steps": 181800, "loss": 0.0164, "lr": 2.3225922251435107e-05, "epoch": 11.407040704070408, "percentage": 57.04, "elapsed_time": "4:05:23", "remaining_time": "3:04:51", "throughput": 1486.3, "total_tokens": 21883200} {"current_steps": 103695, "total_steps": 181800, "loss": 0.0875, "lr": 2.3223528242599125e-05, "epoch": 11.407590759075907, "percentage": 57.04, "elapsed_time": "4:05:23", "remaining_time": "3:04:50", "throughput": 1486.3, "total_tokens": 21884288} {"current_steps": 103700, "total_steps": 181800, "loss": 0.0431, "lr": 2.322113425013605e-05, "epoch": 11.408140814081408, "percentage": 57.04, "elapsed_time": "4:05:24", "remaining_time": "3:04:49", "throughput": 1486.31, "total_tokens": 21885376} {"current_steps": 103705, "total_steps": 181800, "loss": 0.0079, "lr": 2.321874027406791e-05, "epoch": 11.408690869086909, "percentage": 57.04, "elapsed_time": "4:05:25", "remaining_time": "3:04:48", "throughput": 1486.31, "total_tokens": 21886432} {"current_steps": 103710, "total_steps": 181800, "loss": 0.0704, "lr": 2.3216346314416793e-05, "epoch": 11.409240924092408, "percentage": 57.05, "elapsed_time": "4:05:26", "remaining_time": "3:04:48", "throughput": 1486.31, "total_tokens": 21887488} {"current_steps": 103715, "total_steps": 181800, "loss": 0.0023, "lr": 2.3213952371204763e-05, "epoch": 11.40979097909791, "percentage": 57.05, "elapsed_time": "4:05:26", "remaining_time": "3:04:47", "throughput": 1486.31, "total_tokens": 21888512} {"current_steps": 103720, "total_steps": 181800, "loss": 0.0389, "lr": 2.3211558444453863e-05, "epoch": 11.41034103410341, "percentage": 57.05, "elapsed_time": "4:05:27", "remaining_time": "3:04:46", "throughput": 1486.31, "total_tokens": 21889600} {"current_steps": 103725, "total_steps": 181800, "loss": 0.0838, "lr": 2.320916453418618e-05, "epoch": 11.410891089108912, "percentage": 57.05, "elapsed_time": "4:05:28", "remaining_time": "3:04:46", "throughput": 1486.32, "total_tokens": 21890720} {"current_steps": 103730, "total_steps": 181800, "loss": 0.0077, "lr": 2.3206770640423757e-05, "epoch": 11.411441144114411, "percentage": 57.06, "elapsed_time": "4:05:28", "remaining_time": "3:04:45", "throughput": 1486.32, "total_tokens": 21891744} {"current_steps": 103735, "total_steps": 181800, "loss": 0.0443, "lr": 2.3204376763188678e-05, "epoch": 11.411991199119912, "percentage": 57.06, "elapsed_time": "4:05:29", "remaining_time": "3:04:44", "throughput": 1486.32, "total_tokens": 21892800} {"current_steps": 103740, "total_steps": 181800, "loss": 0.1114, "lr": 2.3201982902503007e-05, "epoch": 11.412541254125413, "percentage": 57.06, "elapsed_time": "4:05:30", "remaining_time": "3:04:43", "throughput": 1486.32, "total_tokens": 21893824} {"current_steps": 103745, "total_steps": 181800, "loss": 0.0039, "lr": 2.3199589058388777e-05, "epoch": 11.413091309130913, "percentage": 57.07, "elapsed_time": "4:05:30", "remaining_time": "3:04:43", "throughput": 1486.32, "total_tokens": 21894848} {"current_steps": 103750, "total_steps": 181800, "loss": 0.023, "lr": 2.319719523086808e-05, "epoch": 11.413641364136414, "percentage": 57.07, "elapsed_time": "4:05:31", "remaining_time": "3:04:42", "throughput": 1486.33, "total_tokens": 21895904} {"current_steps": 103755, "total_steps": 181800, "loss": 0.0321, "lr": 2.3194801419962963e-05, "epoch": 11.414191419141915, "percentage": 57.07, "elapsed_time": "4:05:32", "remaining_time": "3:04:41", "throughput": 1486.33, "total_tokens": 21896960} {"current_steps": 103760, "total_steps": 181800, "loss": 0.0707, "lr": 2.3192407625695507e-05, "epoch": 11.414741474147414, "percentage": 57.07, "elapsed_time": "4:05:32", "remaining_time": "3:04:40", "throughput": 1486.33, "total_tokens": 21897984} {"current_steps": 103765, "total_steps": 181800, "loss": 0.0369, "lr": 2.319001384808776e-05, "epoch": 11.415291529152915, "percentage": 57.08, "elapsed_time": "4:05:33", "remaining_time": "3:04:40", "throughput": 1486.33, "total_tokens": 21898976} {"current_steps": 103770, "total_steps": 181800, "loss": 0.0084, "lr": 2.3187620087161777e-05, "epoch": 11.415841584158416, "percentage": 57.08, "elapsed_time": "4:05:34", "remaining_time": "3:04:39", "throughput": 1486.33, "total_tokens": 21900000} {"current_steps": 103775, "total_steps": 181800, "loss": 0.1455, "lr": 2.3185226342939643e-05, "epoch": 11.416391639163916, "percentage": 57.08, "elapsed_time": "4:05:35", "remaining_time": "3:04:38", "throughput": 1486.33, "total_tokens": 21901024} {"current_steps": 103780, "total_steps": 181800, "loss": 0.0101, "lr": 2.3182832615443394e-05, "epoch": 11.416941694169417, "percentage": 57.08, "elapsed_time": "4:05:35", "remaining_time": "3:04:38", "throughput": 1486.33, "total_tokens": 21902080} {"current_steps": 103785, "total_steps": 181800, "loss": 0.1182, "lr": 2.318043890469511e-05, "epoch": 11.417491749174918, "percentage": 57.09, "elapsed_time": "4:05:36", "remaining_time": "3:04:37", "throughput": 1486.33, "total_tokens": 21903104} {"current_steps": 103790, "total_steps": 181800, "loss": 0.1003, "lr": 2.3178045210716854e-05, "epoch": 11.418041804180419, "percentage": 57.09, "elapsed_time": "4:05:37", "remaining_time": "3:04:36", "throughput": 1486.33, "total_tokens": 21904128} {"current_steps": 103795, "total_steps": 181800, "loss": 0.0295, "lr": 2.317565153353067e-05, "epoch": 11.418591859185918, "percentage": 57.09, "elapsed_time": "4:05:37", "remaining_time": "3:04:35", "throughput": 1486.33, "total_tokens": 21905216} {"current_steps": 103800, "total_steps": 181800, "loss": 0.2181, "lr": 2.317325787315864e-05, "epoch": 11.41914191419142, "percentage": 57.1, "elapsed_time": "4:05:38", "remaining_time": "3:04:35", "throughput": 1486.34, "total_tokens": 21906304} {"current_steps": 103805, "total_steps": 181800, "loss": 0.0038, "lr": 2.317086422962281e-05, "epoch": 11.41969196919692, "percentage": 57.1, "elapsed_time": "4:05:39", "remaining_time": "3:04:34", "throughput": 1486.34, "total_tokens": 21907328} {"current_steps": 103810, "total_steps": 181800, "loss": 0.0226, "lr": 2.3168470602945246e-05, "epoch": 11.42024202420242, "percentage": 57.1, "elapsed_time": "4:05:39", "remaining_time": "3:04:33", "throughput": 1486.34, "total_tokens": 21908384} {"current_steps": 103815, "total_steps": 181800, "loss": 0.024, "lr": 2.316607699314802e-05, "epoch": 11.42079207920792, "percentage": 57.1, "elapsed_time": "4:05:40", "remaining_time": "3:04:32", "throughput": 1486.34, "total_tokens": 21909376} {"current_steps": 103820, "total_steps": 181800, "loss": 0.0047, "lr": 2.3163683400253168e-05, "epoch": 11.421342134213422, "percentage": 57.11, "elapsed_time": "4:05:41", "remaining_time": "3:04:32", "throughput": 1486.34, "total_tokens": 21910400} {"current_steps": 103825, "total_steps": 181800, "loss": 0.0156, "lr": 2.3161289824282772e-05, "epoch": 11.421892189218921, "percentage": 57.11, "elapsed_time": "4:05:41", "remaining_time": "3:04:31", "throughput": 1486.35, "total_tokens": 21911584} {"current_steps": 103830, "total_steps": 181800, "loss": 0.0032, "lr": 2.315889626525888e-05, "epoch": 11.422442244224422, "percentage": 57.11, "elapsed_time": "4:05:42", "remaining_time": "3:04:30", "throughput": 1486.35, "total_tokens": 21912640} {"current_steps": 103835, "total_steps": 181800, "loss": 0.0581, "lr": 2.315650272320357e-05, "epoch": 11.422992299229923, "percentage": 57.11, "elapsed_time": "4:05:43", "remaining_time": "3:04:30", "throughput": 1486.35, "total_tokens": 21913696} {"current_steps": 103840, "total_steps": 181800, "loss": 0.0629, "lr": 2.3154109198138883e-05, "epoch": 11.423542354235423, "percentage": 57.12, "elapsed_time": "4:05:43", "remaining_time": "3:04:29", "throughput": 1486.35, "total_tokens": 21914656} {"current_steps": 103845, "total_steps": 181800, "loss": 0.0024, "lr": 2.315171569008688e-05, "epoch": 11.424092409240924, "percentage": 57.12, "elapsed_time": "4:05:44", "remaining_time": "3:04:28", "throughput": 1486.35, "total_tokens": 21915744} {"current_steps": 103850, "total_steps": 181800, "loss": 0.0348, "lr": 2.314932219906963e-05, "epoch": 11.424642464246425, "percentage": 57.12, "elapsed_time": "4:05:45", "remaining_time": "3:04:27", "throughput": 1486.35, "total_tokens": 21916832} {"current_steps": 103855, "total_steps": 181800, "loss": 0.0338, "lr": 2.314692872510919e-05, "epoch": 11.425192519251926, "percentage": 57.13, "elapsed_time": "4:05:46", "remaining_time": "3:04:27", "throughput": 1486.36, "total_tokens": 21917888} {"current_steps": 103860, "total_steps": 181800, "loss": 0.0879, "lr": 2.3144535268227624e-05, "epoch": 11.425742574257425, "percentage": 57.13, "elapsed_time": "4:05:46", "remaining_time": "3:04:26", "throughput": 1486.36, "total_tokens": 21918912} {"current_steps": 103865, "total_steps": 181800, "loss": 0.0068, "lr": 2.3142141828446983e-05, "epoch": 11.426292629262926, "percentage": 57.13, "elapsed_time": "4:05:47", "remaining_time": "3:04:25", "throughput": 1486.36, "total_tokens": 21919936} {"current_steps": 103870, "total_steps": 181800, "loss": 0.0587, "lr": 2.313974840578932e-05, "epoch": 11.426842684268427, "percentage": 57.13, "elapsed_time": "4:05:48", "remaining_time": "3:04:25", "throughput": 1486.36, "total_tokens": 21920960} {"current_steps": 103875, "total_steps": 181800, "loss": 0.0724, "lr": 2.313735500027672e-05, "epoch": 11.427392739273927, "percentage": 57.14, "elapsed_time": "4:05:48", "remaining_time": "3:04:24", "throughput": 1486.36, "total_tokens": 21922048} {"current_steps": 103880, "total_steps": 181800, "loss": 0.1032, "lr": 2.3134961611931215e-05, "epoch": 11.427942794279428, "percentage": 57.14, "elapsed_time": "4:05:49", "remaining_time": "3:04:23", "throughput": 1486.36, "total_tokens": 21923040} {"current_steps": 103885, "total_steps": 181800, "loss": 0.0023, "lr": 2.313256824077487e-05, "epoch": 11.428492849284929, "percentage": 57.14, "elapsed_time": "4:05:50", "remaining_time": "3:04:22", "throughput": 1486.36, "total_tokens": 21924096} {"current_steps": 103890, "total_steps": 181800, "loss": 0.1168, "lr": 2.313017488682976e-05, "epoch": 11.429042904290428, "percentage": 57.15, "elapsed_time": "4:05:50", "remaining_time": "3:04:22", "throughput": 1486.36, "total_tokens": 21925088} {"current_steps": 103895, "total_steps": 181800, "loss": 0.0308, "lr": 2.3127781550117918e-05, "epoch": 11.42959295929593, "percentage": 57.15, "elapsed_time": "4:05:51", "remaining_time": "3:04:21", "throughput": 1486.36, "total_tokens": 21926208} {"current_steps": 103900, "total_steps": 181800, "loss": 0.0218, "lr": 2.3125388230661425e-05, "epoch": 11.43014301430143, "percentage": 57.15, "elapsed_time": "4:05:52", "remaining_time": "3:04:20", "throughput": 1486.36, "total_tokens": 21927232} {"current_steps": 103905, "total_steps": 181800, "loss": 0.005, "lr": 2.312299492848233e-05, "epoch": 11.430693069306932, "percentage": 57.15, "elapsed_time": "4:05:52", "remaining_time": "3:04:19", "throughput": 1486.36, "total_tokens": 21928224} {"current_steps": 103910, "total_steps": 181800, "loss": 0.0032, "lr": 2.3120601643602674e-05, "epoch": 11.43124312431243, "percentage": 57.16, "elapsed_time": "4:05:53", "remaining_time": "3:04:19", "throughput": 1486.36, "total_tokens": 21929248} {"current_steps": 103915, "total_steps": 181800, "loss": 0.0275, "lr": 2.3118208376044546e-05, "epoch": 11.431793179317932, "percentage": 57.16, "elapsed_time": "4:05:54", "remaining_time": "3:04:18", "throughput": 1486.36, "total_tokens": 21930304} {"current_steps": 103920, "total_steps": 181800, "loss": 0.0135, "lr": 2.311581512582998e-05, "epoch": 11.432343234323433, "percentage": 57.16, "elapsed_time": "4:05:55", "remaining_time": "3:04:17", "throughput": 1486.37, "total_tokens": 21931360} {"current_steps": 103925, "total_steps": 181800, "loss": 0.0644, "lr": 2.3113421892981048e-05, "epoch": 11.432893289328932, "percentage": 57.16, "elapsed_time": "4:05:55", "remaining_time": "3:04:17", "throughput": 1486.37, "total_tokens": 21932384} {"current_steps": 103930, "total_steps": 181800, "loss": 0.0521, "lr": 2.3111028677519804e-05, "epoch": 11.433443344334433, "percentage": 57.17, "elapsed_time": "4:05:56", "remaining_time": "3:04:16", "throughput": 1486.36, "total_tokens": 21933376} {"current_steps": 103935, "total_steps": 181800, "loss": 0.04, "lr": 2.3108635479468292e-05, "epoch": 11.433993399339935, "percentage": 57.17, "elapsed_time": "4:05:57", "remaining_time": "3:04:15", "throughput": 1486.36, "total_tokens": 21934400} {"current_steps": 103940, "total_steps": 181800, "loss": 0.0227, "lr": 2.3106242298848586e-05, "epoch": 11.434543454345434, "percentage": 57.17, "elapsed_time": "4:05:57", "remaining_time": "3:04:14", "throughput": 1486.36, "total_tokens": 21935424} {"current_steps": 103945, "total_steps": 181800, "loss": 0.0516, "lr": 2.3103849135682733e-05, "epoch": 11.435093509350935, "percentage": 57.18, "elapsed_time": "4:05:58", "remaining_time": "3:04:14", "throughput": 1486.36, "total_tokens": 21936480} {"current_steps": 103950, "total_steps": 181800, "loss": 0.14, "lr": 2.31014559899928e-05, "epoch": 11.435643564356436, "percentage": 57.18, "elapsed_time": "4:05:59", "remaining_time": "3:04:13", "throughput": 1486.37, "total_tokens": 21937600} {"current_steps": 103955, "total_steps": 181800, "loss": 0.0163, "lr": 2.309906286180083e-05, "epoch": 11.436193619361935, "percentage": 57.18, "elapsed_time": "4:05:59", "remaining_time": "3:04:12", "throughput": 1486.37, "total_tokens": 21938656} {"current_steps": 103960, "total_steps": 181800, "loss": 0.033, "lr": 2.309666975112888e-05, "epoch": 11.436743674367436, "percentage": 57.18, "elapsed_time": "4:06:00", "remaining_time": "3:04:11", "throughput": 1486.37, "total_tokens": 21939680} {"current_steps": 103965, "total_steps": 181800, "loss": 0.0813, "lr": 2.3094276657999027e-05, "epoch": 11.437293729372938, "percentage": 57.19, "elapsed_time": "4:06:01", "remaining_time": "3:04:11", "throughput": 1486.38, "total_tokens": 21940768} {"current_steps": 103970, "total_steps": 181800, "loss": 0.0482, "lr": 2.3091883582433287e-05, "epoch": 11.437843784378439, "percentage": 57.19, "elapsed_time": "4:06:01", "remaining_time": "3:04:10", "throughput": 1486.38, "total_tokens": 21941824} {"current_steps": 103975, "total_steps": 181800, "loss": 0.0105, "lr": 2.3089490524453764e-05, "epoch": 11.438393839383938, "percentage": 57.19, "elapsed_time": "4:06:02", "remaining_time": "3:04:09", "throughput": 1486.38, "total_tokens": 21942880} {"current_steps": 103980, "total_steps": 181800, "loss": 0.085, "lr": 2.308709748408248e-05, "epoch": 11.438943894389439, "percentage": 57.19, "elapsed_time": "4:06:03", "remaining_time": "3:04:09", "throughput": 1486.38, "total_tokens": 21943904} {"current_steps": 103985, "total_steps": 181800, "loss": 0.0048, "lr": 2.30847044613415e-05, "epoch": 11.43949394939494, "percentage": 57.2, "elapsed_time": "4:06:03", "remaining_time": "3:04:08", "throughput": 1486.39, "total_tokens": 21944992} {"current_steps": 103990, "total_steps": 181800, "loss": 0.0835, "lr": 2.3082311456252885e-05, "epoch": 11.44004400440044, "percentage": 57.2, "elapsed_time": "4:06:04", "remaining_time": "3:04:07", "throughput": 1486.38, "total_tokens": 21945984} {"current_steps": 103995, "total_steps": 181800, "loss": 0.0298, "lr": 2.307991846883868e-05, "epoch": 11.44059405940594, "percentage": 57.2, "elapsed_time": "4:06:05", "remaining_time": "3:04:06", "throughput": 1486.39, "total_tokens": 21947104} {"current_steps": 104000, "total_steps": 181800, "loss": 0.0129, "lr": 2.3077525499120946e-05, "epoch": 11.441144114411442, "percentage": 57.21, "elapsed_time": "4:06:06", "remaining_time": "3:04:06", "throughput": 1486.39, "total_tokens": 21948192} {"current_steps": 104005, "total_steps": 181800, "loss": 0.0207, "lr": 2.3075132547121748e-05, "epoch": 11.441694169416941, "percentage": 57.21, "elapsed_time": "4:06:06", "remaining_time": "3:04:05", "throughput": 1486.4, "total_tokens": 21949248} {"current_steps": 104010, "total_steps": 181800, "loss": 0.0354, "lr": 2.3072739612863113e-05, "epoch": 11.442244224422442, "percentage": 57.21, "elapsed_time": "4:06:07", "remaining_time": "3:04:04", "throughput": 1486.4, "total_tokens": 21950304} {"current_steps": 104015, "total_steps": 181800, "loss": 0.011, "lr": 2.3070346696367122e-05, "epoch": 11.442794279427943, "percentage": 57.21, "elapsed_time": "4:06:08", "remaining_time": "3:04:03", "throughput": 1486.4, "total_tokens": 21951296} {"current_steps": 104020, "total_steps": 181800, "loss": 0.0033, "lr": 2.306795379765581e-05, "epoch": 11.443344334433444, "percentage": 57.22, "elapsed_time": "4:06:08", "remaining_time": "3:04:03", "throughput": 1486.39, "total_tokens": 21952288} {"current_steps": 104025, "total_steps": 181800, "loss": 0.0381, "lr": 2.3065560916751252e-05, "epoch": 11.443894389438944, "percentage": 57.22, "elapsed_time": "4:06:09", "remaining_time": "3:04:02", "throughput": 1486.39, "total_tokens": 21953312} {"current_steps": 104030, "total_steps": 181800, "loss": 0.0167, "lr": 2.3063168053675487e-05, "epoch": 11.444444444444445, "percentage": 57.22, "elapsed_time": "4:06:10", "remaining_time": "3:04:01", "throughput": 1486.4, "total_tokens": 21954336} {"current_steps": 104035, "total_steps": 181800, "loss": 0.0666, "lr": 2.306077520845057e-05, "epoch": 11.444994499449946, "percentage": 57.22, "elapsed_time": "4:06:10", "remaining_time": "3:04:01", "throughput": 1486.4, "total_tokens": 21955360} {"current_steps": 104040, "total_steps": 181800, "loss": 0.0563, "lr": 2.3058382381098558e-05, "epoch": 11.445544554455445, "percentage": 57.23, "elapsed_time": "4:06:11", "remaining_time": "3:04:00", "throughput": 1486.4, "total_tokens": 21956448} {"current_steps": 104045, "total_steps": 181800, "loss": 0.0082, "lr": 2.30559895716415e-05, "epoch": 11.446094609460946, "percentage": 57.23, "elapsed_time": "4:06:12", "remaining_time": "3:03:59", "throughput": 1486.4, "total_tokens": 21957504} {"current_steps": 104050, "total_steps": 181800, "loss": 0.0132, "lr": 2.3053596780101466e-05, "epoch": 11.446644664466447, "percentage": 57.23, "elapsed_time": "4:06:12", "remaining_time": "3:03:58", "throughput": 1486.41, "total_tokens": 21958624} {"current_steps": 104055, "total_steps": 181800, "loss": 0.0264, "lr": 2.305120400650049e-05, "epoch": 11.447194719471947, "percentage": 57.24, "elapsed_time": "4:06:13", "remaining_time": "3:03:58", "throughput": 1486.41, "total_tokens": 21959712} {"current_steps": 104060, "total_steps": 181800, "loss": 0.0266, "lr": 2.3048811250860624e-05, "epoch": 11.447744774477448, "percentage": 57.24, "elapsed_time": "4:06:14", "remaining_time": "3:03:57", "throughput": 1486.42, "total_tokens": 21960768} {"current_steps": 104065, "total_steps": 181800, "loss": 0.0063, "lr": 2.3046418513203943e-05, "epoch": 11.448294829482949, "percentage": 57.24, "elapsed_time": "4:06:15", "remaining_time": "3:03:56", "throughput": 1486.42, "total_tokens": 21961824} {"current_steps": 104070, "total_steps": 181800, "loss": 0.008, "lr": 2.3044025793552476e-05, "epoch": 11.448844884488448, "percentage": 57.24, "elapsed_time": "4:06:15", "remaining_time": "3:03:55", "throughput": 1486.42, "total_tokens": 21962880} {"current_steps": 104075, "total_steps": 181800, "loss": 0.0098, "lr": 2.3041633091928283e-05, "epoch": 11.44939493949395, "percentage": 57.25, "elapsed_time": "4:06:16", "remaining_time": "3:03:55", "throughput": 1486.42, "total_tokens": 21963936} {"current_steps": 104080, "total_steps": 181800, "loss": 0.0056, "lr": 2.3039240408353426e-05, "epoch": 11.44994499449945, "percentage": 57.25, "elapsed_time": "4:06:17", "remaining_time": "3:03:54", "throughput": 1486.42, "total_tokens": 21965024} {"current_steps": 104085, "total_steps": 181800, "loss": 0.0029, "lr": 2.3036847742849936e-05, "epoch": 11.450495049504951, "percentage": 57.25, "elapsed_time": "4:06:17", "remaining_time": "3:03:53", "throughput": 1486.43, "total_tokens": 21966080} {"current_steps": 104090, "total_steps": 181800, "loss": 0.0424, "lr": 2.3034455095439893e-05, "epoch": 11.45104510451045, "percentage": 57.26, "elapsed_time": "4:06:18", "remaining_time": "3:03:53", "throughput": 1486.43, "total_tokens": 21967136} {"current_steps": 104095, "total_steps": 181800, "loss": 0.0108, "lr": 2.3032062466145326e-05, "epoch": 11.451595159515952, "percentage": 57.26, "elapsed_time": "4:06:19", "remaining_time": "3:03:52", "throughput": 1486.43, "total_tokens": 21968224} {"current_steps": 104100, "total_steps": 181800, "loss": 0.0042, "lr": 2.3029669854988294e-05, "epoch": 11.452145214521453, "percentage": 57.26, "elapsed_time": "4:06:19", "remaining_time": "3:03:51", "throughput": 1486.44, "total_tokens": 21969312} {"current_steps": 104105, "total_steps": 181800, "loss": 0.0072, "lr": 2.3027277261990858e-05, "epoch": 11.452695269526952, "percentage": 57.26, "elapsed_time": "4:06:20", "remaining_time": "3:03:50", "throughput": 1486.44, "total_tokens": 21970432} {"current_steps": 104110, "total_steps": 181800, "loss": 0.0067, "lr": 2.3024884687175048e-05, "epoch": 11.453245324532453, "percentage": 57.27, "elapsed_time": "4:06:21", "remaining_time": "3:03:50", "throughput": 1486.45, "total_tokens": 21971520} {"current_steps": 104115, "total_steps": 181800, "loss": 0.0692, "lr": 2.3022492130562936e-05, "epoch": 11.453795379537954, "percentage": 57.27, "elapsed_time": "4:06:21", "remaining_time": "3:03:49", "throughput": 1486.45, "total_tokens": 21972608} {"current_steps": 104120, "total_steps": 181800, "loss": 0.0262, "lr": 2.3020099592176574e-05, "epoch": 11.454345434543454, "percentage": 57.27, "elapsed_time": "4:06:22", "remaining_time": "3:03:48", "throughput": 1486.45, "total_tokens": 21973600} {"current_steps": 104125, "total_steps": 181800, "loss": 0.003, "lr": 2.3017707072037988e-05, "epoch": 11.454895489548955, "percentage": 57.27, "elapsed_time": "4:06:23", "remaining_time": "3:03:48", "throughput": 1486.45, "total_tokens": 21974720} {"current_steps": 104130, "total_steps": 181800, "loss": 0.0735, "lr": 2.301531457016925e-05, "epoch": 11.455445544554456, "percentage": 57.28, "elapsed_time": "4:06:23", "remaining_time": "3:03:47", "throughput": 1486.45, "total_tokens": 21975744} {"current_steps": 104135, "total_steps": 181800, "loss": 0.1154, "lr": 2.3012922086592403e-05, "epoch": 11.455995599559955, "percentage": 57.28, "elapsed_time": "4:06:24", "remaining_time": "3:03:46", "throughput": 1486.46, "total_tokens": 21976800} {"current_steps": 104140, "total_steps": 181800, "loss": 0.0795, "lr": 2.3010529621329508e-05, "epoch": 11.456545654565456, "percentage": 57.28, "elapsed_time": "4:06:25", "remaining_time": "3:03:45", "throughput": 1486.46, "total_tokens": 21977824} {"current_steps": 104145, "total_steps": 181800, "loss": 0.0127, "lr": 2.3008137174402602e-05, "epoch": 11.457095709570957, "percentage": 57.29, "elapsed_time": "4:06:26", "remaining_time": "3:03:45", "throughput": 1486.46, "total_tokens": 21978880} {"current_steps": 104150, "total_steps": 181800, "loss": 0.0168, "lr": 2.3005744745833736e-05, "epoch": 11.457645764576458, "percentage": 57.29, "elapsed_time": "4:06:26", "remaining_time": "3:03:44", "throughput": 1486.46, "total_tokens": 21979904} {"current_steps": 104155, "total_steps": 181800, "loss": 0.0057, "lr": 2.3003352335644967e-05, "epoch": 11.458195819581958, "percentage": 57.29, "elapsed_time": "4:06:27", "remaining_time": "3:03:43", "throughput": 1486.46, "total_tokens": 21980992} {"current_steps": 104160, "total_steps": 181800, "loss": 0.0093, "lr": 2.3000959943858337e-05, "epoch": 11.458745874587459, "percentage": 57.29, "elapsed_time": "4:06:28", "remaining_time": "3:03:42", "throughput": 1486.46, "total_tokens": 21982016} {"current_steps": 104165, "total_steps": 181800, "loss": 0.002, "lr": 2.2998567570495914e-05, "epoch": 11.45929592959296, "percentage": 57.3, "elapsed_time": "4:06:28", "remaining_time": "3:03:42", "throughput": 1486.47, "total_tokens": 21983104} {"current_steps": 104170, "total_steps": 181800, "loss": 0.0219, "lr": 2.2996175215579724e-05, "epoch": 11.45984598459846, "percentage": 57.3, "elapsed_time": "4:06:29", "remaining_time": "3:03:41", "throughput": 1486.47, "total_tokens": 21984192} {"current_steps": 104175, "total_steps": 181800, "loss": 0.0244, "lr": 2.299378287913182e-05, "epoch": 11.46039603960396, "percentage": 57.3, "elapsed_time": "4:06:30", "remaining_time": "3:03:40", "throughput": 1486.47, "total_tokens": 21985248} {"current_steps": 104180, "total_steps": 181800, "loss": 0.0147, "lr": 2.2991390561174267e-05, "epoch": 11.460946094609461, "percentage": 57.3, "elapsed_time": "4:06:30", "remaining_time": "3:03:40", "throughput": 1486.47, "total_tokens": 21986272} {"current_steps": 104185, "total_steps": 181800, "loss": 0.0165, "lr": 2.2988998261729095e-05, "epoch": 11.46149614961496, "percentage": 57.31, "elapsed_time": "4:06:31", "remaining_time": "3:03:39", "throughput": 1486.48, "total_tokens": 21987328} {"current_steps": 104190, "total_steps": 181800, "loss": 0.0348, "lr": 2.2986605980818364e-05, "epoch": 11.462046204620462, "percentage": 57.31, "elapsed_time": "4:06:32", "remaining_time": "3:03:38", "throughput": 1486.48, "total_tokens": 21988448} {"current_steps": 104195, "total_steps": 181800, "loss": 0.0515, "lr": 2.2984213718464125e-05, "epoch": 11.462596259625963, "percentage": 57.31, "elapsed_time": "4:06:32", "remaining_time": "3:03:37", "throughput": 1486.48, "total_tokens": 21989504} {"current_steps": 104200, "total_steps": 181800, "loss": 0.0034, "lr": 2.2981821474688416e-05, "epoch": 11.463146314631462, "percentage": 57.32, "elapsed_time": "4:06:33", "remaining_time": "3:03:37", "throughput": 1486.49, "total_tokens": 21990560} {"current_steps": 104205, "total_steps": 181800, "loss": 0.0632, "lr": 2.297942924951329e-05, "epoch": 11.463696369636963, "percentage": 57.32, "elapsed_time": "4:06:34", "remaining_time": "3:03:36", "throughput": 1486.49, "total_tokens": 21991648} {"current_steps": 104210, "total_steps": 181800, "loss": 0.0675, "lr": 2.2977037042960788e-05, "epoch": 11.464246424642464, "percentage": 57.32, "elapsed_time": "4:06:35", "remaining_time": "3:03:35", "throughput": 1486.49, "total_tokens": 21992704} {"current_steps": 104215, "total_steps": 181800, "loss": 0.0094, "lr": 2.2974644855052973e-05, "epoch": 11.464796479647966, "percentage": 57.32, "elapsed_time": "4:06:35", "remaining_time": "3:03:34", "throughput": 1486.49, "total_tokens": 21993696} {"current_steps": 104220, "total_steps": 181800, "loss": 0.0101, "lr": 2.297225268581189e-05, "epoch": 11.465346534653465, "percentage": 57.33, "elapsed_time": "4:06:36", "remaining_time": "3:03:34", "throughput": 1486.49, "total_tokens": 21994752} {"current_steps": 104225, "total_steps": 181800, "loss": 0.0414, "lr": 2.296986053525957e-05, "epoch": 11.465896589658966, "percentage": 57.33, "elapsed_time": "4:06:37", "remaining_time": "3:03:33", "throughput": 1486.49, "total_tokens": 21995744} {"current_steps": 104230, "total_steps": 181800, "loss": 0.0393, "lr": 2.2967468403418075e-05, "epoch": 11.466446644664467, "percentage": 57.33, "elapsed_time": "4:06:37", "remaining_time": "3:03:32", "throughput": 1486.48, "total_tokens": 21996704} {"current_steps": 104235, "total_steps": 181800, "loss": 0.0053, "lr": 2.2965076290309446e-05, "epoch": 11.466996699669966, "percentage": 57.33, "elapsed_time": "4:06:38", "remaining_time": "3:03:32", "throughput": 1486.49, "total_tokens": 21997824} {"current_steps": 104240, "total_steps": 181800, "loss": 0.003, "lr": 2.2962684195955742e-05, "epoch": 11.467546754675467, "percentage": 57.34, "elapsed_time": "4:06:39", "remaining_time": "3:03:31", "throughput": 1486.49, "total_tokens": 21998848} {"current_steps": 104245, "total_steps": 181800, "loss": 0.0007, "lr": 2.2960292120378993e-05, "epoch": 11.468096809680969, "percentage": 57.34, "elapsed_time": "4:06:39", "remaining_time": "3:03:30", "throughput": 1486.5, "total_tokens": 21999936} {"current_steps": 104250, "total_steps": 181800, "loss": 0.0455, "lr": 2.2957900063601247e-05, "epoch": 11.468646864686468, "percentage": 57.34, "elapsed_time": "4:06:40", "remaining_time": "3:03:29", "throughput": 1486.5, "total_tokens": 22000992} {"current_steps": 104255, "total_steps": 181800, "loss": 0.0259, "lr": 2.295550802564457e-05, "epoch": 11.469196919691969, "percentage": 57.35, "elapsed_time": "4:06:41", "remaining_time": "3:03:29", "throughput": 1486.5, "total_tokens": 22002080} {"current_steps": 104260, "total_steps": 181800, "loss": 0.0037, "lr": 2.295311600653099e-05, "epoch": 11.46974697469747, "percentage": 57.35, "elapsed_time": "4:06:41", "remaining_time": "3:03:28", "throughput": 1486.5, "total_tokens": 22003040} {"current_steps": 104265, "total_steps": 181800, "loss": 0.0989, "lr": 2.2950724006282548e-05, "epoch": 11.47029702970297, "percentage": 57.35, "elapsed_time": "4:06:42", "remaining_time": "3:03:27", "throughput": 1486.5, "total_tokens": 22004160} {"current_steps": 104270, "total_steps": 181800, "loss": 0.1181, "lr": 2.294833202492131e-05, "epoch": 11.47084708470847, "percentage": 57.35, "elapsed_time": "4:06:43", "remaining_time": "3:03:27", "throughput": 1486.51, "total_tokens": 22005280} {"current_steps": 104275, "total_steps": 181800, "loss": 0.0029, "lr": 2.2945940062469303e-05, "epoch": 11.471397139713972, "percentage": 57.36, "elapsed_time": "4:06:44", "remaining_time": "3:03:26", "throughput": 1486.51, "total_tokens": 22006336} {"current_steps": 104280, "total_steps": 181800, "loss": 0.0213, "lr": 2.294354811894859e-05, "epoch": 11.471947194719473, "percentage": 57.36, "elapsed_time": "4:06:44", "remaining_time": "3:03:25", "throughput": 1486.51, "total_tokens": 22007392} {"current_steps": 104285, "total_steps": 181800, "loss": 0.0289, "lr": 2.2941156194381203e-05, "epoch": 11.472497249724972, "percentage": 57.36, "elapsed_time": "4:06:45", "remaining_time": "3:03:24", "throughput": 1486.52, "total_tokens": 22008448} {"current_steps": 104290, "total_steps": 181800, "loss": 0.0043, "lr": 2.2938764288789185e-05, "epoch": 11.473047304730473, "percentage": 57.37, "elapsed_time": "4:06:46", "remaining_time": "3:03:24", "throughput": 1486.52, "total_tokens": 22009472} {"current_steps": 104295, "total_steps": 181800, "loss": 0.0043, "lr": 2.29363724021946e-05, "epoch": 11.473597359735974, "percentage": 57.37, "elapsed_time": "4:06:46", "remaining_time": "3:03:23", "throughput": 1486.52, "total_tokens": 22010592} {"current_steps": 104300, "total_steps": 181800, "loss": 0.1341, "lr": 2.293398053461947e-05, "epoch": 11.474147414741473, "percentage": 57.37, "elapsed_time": "4:06:47", "remaining_time": "3:03:22", "throughput": 1486.52, "total_tokens": 22011648} {"current_steps": 104305, "total_steps": 181800, "loss": 0.0131, "lr": 2.293158868608585e-05, "epoch": 11.474697469746975, "percentage": 57.37, "elapsed_time": "4:06:48", "remaining_time": "3:03:21", "throughput": 1486.52, "total_tokens": 22012672} {"current_steps": 104310, "total_steps": 181800, "loss": 0.0023, "lr": 2.2929196856615797e-05, "epoch": 11.475247524752476, "percentage": 57.38, "elapsed_time": "4:06:48", "remaining_time": "3:03:21", "throughput": 1486.53, "total_tokens": 22013792} {"current_steps": 104315, "total_steps": 181800, "loss": 0.0033, "lr": 2.2926805046231332e-05, "epoch": 11.475797579757975, "percentage": 57.38, "elapsed_time": "4:06:49", "remaining_time": "3:03:20", "throughput": 1486.53, "total_tokens": 22014816} {"current_steps": 104320, "total_steps": 181800, "loss": 0.0087, "lr": 2.292441325495451e-05, "epoch": 11.476347634763476, "percentage": 57.38, "elapsed_time": "4:06:50", "remaining_time": "3:03:19", "throughput": 1486.53, "total_tokens": 22015872} {"current_steps": 104325, "total_steps": 181800, "loss": 0.0042, "lr": 2.2922021482807373e-05, "epoch": 11.476897689768977, "percentage": 57.38, "elapsed_time": "4:06:50", "remaining_time": "3:03:19", "throughput": 1486.54, "total_tokens": 22017024} {"current_steps": 104330, "total_steps": 181800, "loss": 0.0126, "lr": 2.2919629729811972e-05, "epoch": 11.477447744774478, "percentage": 57.39, "elapsed_time": "4:06:51", "remaining_time": "3:03:18", "throughput": 1486.54, "total_tokens": 22018048} {"current_steps": 104335, "total_steps": 181800, "loss": 0.0496, "lr": 2.291723799599035e-05, "epoch": 11.477997799779978, "percentage": 57.39, "elapsed_time": "4:06:52", "remaining_time": "3:03:17", "throughput": 1486.54, "total_tokens": 22019104} {"current_steps": 104340, "total_steps": 181800, "loss": 0.0046, "lr": 2.2914846281364537e-05, "epoch": 11.478547854785479, "percentage": 57.39, "elapsed_time": "4:06:52", "remaining_time": "3:03:16", "throughput": 1486.54, "total_tokens": 22020096} {"current_steps": 104345, "total_steps": 181800, "loss": 0.0063, "lr": 2.2912454585956592e-05, "epoch": 11.47909790979098, "percentage": 57.4, "elapsed_time": "4:06:53", "remaining_time": "3:03:16", "throughput": 1486.54, "total_tokens": 22021184} {"current_steps": 104350, "total_steps": 181800, "loss": 0.0083, "lr": 2.2910062909788543e-05, "epoch": 11.479647964796479, "percentage": 57.4, "elapsed_time": "4:06:54", "remaining_time": "3:03:15", "throughput": 1486.54, "total_tokens": 22022208} {"current_steps": 104355, "total_steps": 181800, "loss": 0.0051, "lr": 2.290767125288245e-05, "epoch": 11.48019801980198, "percentage": 57.4, "elapsed_time": "4:06:55", "remaining_time": "3:03:14", "throughput": 1486.55, "total_tokens": 22023328} {"current_steps": 104360, "total_steps": 181800, "loss": 0.0321, "lr": 2.2905279615260347e-05, "epoch": 11.480748074807481, "percentage": 57.4, "elapsed_time": "4:06:55", "remaining_time": "3:03:13", "throughput": 1486.55, "total_tokens": 22024352} {"current_steps": 104365, "total_steps": 181800, "loss": 0.0423, "lr": 2.290288799694427e-05, "epoch": 11.48129812981298, "percentage": 57.41, "elapsed_time": "4:06:56", "remaining_time": "3:03:13", "throughput": 1486.56, "total_tokens": 22025472} {"current_steps": 104370, "total_steps": 181800, "loss": 0.0668, "lr": 2.2900496397956276e-05, "epoch": 11.481848184818482, "percentage": 57.41, "elapsed_time": "4:06:57", "remaining_time": "3:03:12", "throughput": 1486.56, "total_tokens": 22026496} {"current_steps": 104375, "total_steps": 181800, "loss": 0.0412, "lr": 2.2898104818318393e-05, "epoch": 11.482398239823983, "percentage": 57.41, "elapsed_time": "4:06:57", "remaining_time": "3:03:11", "throughput": 1486.56, "total_tokens": 22027552} {"current_steps": 104380, "total_steps": 181800, "loss": 0.0027, "lr": 2.289571325805267e-05, "epoch": 11.482948294829482, "percentage": 57.41, "elapsed_time": "4:06:58", "remaining_time": "3:03:11", "throughput": 1486.56, "total_tokens": 22028640} {"current_steps": 104385, "total_steps": 181800, "loss": 0.0129, "lr": 2.2893321717181154e-05, "epoch": 11.483498349834983, "percentage": 57.42, "elapsed_time": "4:06:59", "remaining_time": "3:03:10", "throughput": 1486.57, "total_tokens": 22029696} {"current_steps": 104390, "total_steps": 181800, "loss": 0.0551, "lr": 2.2890930195725865e-05, "epoch": 11.484048404840484, "percentage": 57.42, "elapsed_time": "4:06:59", "remaining_time": "3:03:09", "throughput": 1486.57, "total_tokens": 22030720} {"current_steps": 104395, "total_steps": 181800, "loss": 0.0638, "lr": 2.288853869370888e-05, "epoch": 11.484598459845985, "percentage": 57.42, "elapsed_time": "4:07:00", "remaining_time": "3:03:08", "throughput": 1486.57, "total_tokens": 22031840} {"current_steps": 104400, "total_steps": 181800, "loss": 0.0061, "lr": 2.2886147211152205e-05, "epoch": 11.485148514851485, "percentage": 57.43, "elapsed_time": "4:07:01", "remaining_time": "3:03:08", "throughput": 1486.57, "total_tokens": 22032896} {"current_steps": 104405, "total_steps": 181800, "loss": 0.0805, "lr": 2.2883755748077906e-05, "epoch": 11.485698569856986, "percentage": 57.43, "elapsed_time": "4:07:01", "remaining_time": "3:03:07", "throughput": 1486.57, "total_tokens": 22033888} {"current_steps": 104410, "total_steps": 181800, "loss": 0.0981, "lr": 2.2881364304508018e-05, "epoch": 11.486248624862487, "percentage": 57.43, "elapsed_time": "4:07:02", "remaining_time": "3:03:06", "throughput": 1486.57, "total_tokens": 22034944} {"current_steps": 104415, "total_steps": 181800, "loss": 0.1976, "lr": 2.2878972880464568e-05, "epoch": 11.486798679867986, "percentage": 57.43, "elapsed_time": "4:07:03", "remaining_time": "3:03:05", "throughput": 1486.57, "total_tokens": 22035968} {"current_steps": 104420, "total_steps": 181800, "loss": 0.0108, "lr": 2.2876581475969618e-05, "epoch": 11.487348734873487, "percentage": 57.44, "elapsed_time": "4:07:04", "remaining_time": "3:03:05", "throughput": 1486.58, "total_tokens": 22037024} {"current_steps": 104425, "total_steps": 181800, "loss": 0.0016, "lr": 2.2874190091045184e-05, "epoch": 11.487898789878988, "percentage": 57.44, "elapsed_time": "4:07:04", "remaining_time": "3:03:04", "throughput": 1486.58, "total_tokens": 22038112} {"current_steps": 104430, "total_steps": 181800, "loss": 0.0037, "lr": 2.2871798725713334e-05, "epoch": 11.488448844884488, "percentage": 57.44, "elapsed_time": "4:07:05", "remaining_time": "3:03:03", "throughput": 1486.58, "total_tokens": 22039168} {"current_steps": 104435, "total_steps": 181800, "loss": 0.0093, "lr": 2.2869407379996088e-05, "epoch": 11.488998899889989, "percentage": 57.44, "elapsed_time": "4:07:06", "remaining_time": "3:03:03", "throughput": 1486.59, "total_tokens": 22040256} {"current_steps": 104440, "total_steps": 181800, "loss": 0.0063, "lr": 2.2867016053915487e-05, "epoch": 11.48954895489549, "percentage": 57.45, "elapsed_time": "4:07:06", "remaining_time": "3:03:02", "throughput": 1486.59, "total_tokens": 22041344} {"current_steps": 104445, "total_steps": 181800, "loss": 0.0376, "lr": 2.2864624747493586e-05, "epoch": 11.490099009900991, "percentage": 57.45, "elapsed_time": "4:07:07", "remaining_time": "3:03:01", "throughput": 1486.6, "total_tokens": 22042464} {"current_steps": 104450, "total_steps": 181800, "loss": 0.008, "lr": 2.286223346075241e-05, "epoch": 11.49064906490649, "percentage": 57.45, "elapsed_time": "4:07:08", "remaining_time": "3:03:00", "throughput": 1486.61, "total_tokens": 22043616} {"current_steps": 104455, "total_steps": 181800, "loss": 0.0515, "lr": 2.2859842193713995e-05, "epoch": 11.491199119911991, "percentage": 57.46, "elapsed_time": "4:07:08", "remaining_time": "3:03:00", "throughput": 1486.61, "total_tokens": 22044704} {"current_steps": 104460, "total_steps": 181800, "loss": 0.0036, "lr": 2.2857450946400397e-05, "epoch": 11.491749174917492, "percentage": 57.46, "elapsed_time": "4:07:09", "remaining_time": "3:02:59", "throughput": 1486.61, "total_tokens": 22045728} {"current_steps": 104465, "total_steps": 181800, "loss": 0.0025, "lr": 2.2855059718833635e-05, "epoch": 11.492299229922992, "percentage": 57.46, "elapsed_time": "4:07:10", "remaining_time": "3:02:58", "throughput": 1486.61, "total_tokens": 22046816} {"current_steps": 104470, "total_steps": 181800, "loss": 0.0113, "lr": 2.285266851103577e-05, "epoch": 11.492849284928493, "percentage": 57.46, "elapsed_time": "4:07:10", "remaining_time": "3:02:58", "throughput": 1486.62, "total_tokens": 22047840} {"current_steps": 104475, "total_steps": 181800, "loss": 0.0179, "lr": 2.2850277323028826e-05, "epoch": 11.493399339933994, "percentage": 57.47, "elapsed_time": "4:07:11", "remaining_time": "3:02:57", "throughput": 1486.62, "total_tokens": 22048864} {"current_steps": 104480, "total_steps": 181800, "loss": 0.1221, "lr": 2.2847886154834838e-05, "epoch": 11.493949394939493, "percentage": 57.47, "elapsed_time": "4:07:12", "remaining_time": "3:02:56", "throughput": 1486.62, "total_tokens": 22050016} {"current_steps": 104485, "total_steps": 181800, "loss": 0.0416, "lr": 2.284549500647586e-05, "epoch": 11.494499449944994, "percentage": 57.47, "elapsed_time": "4:07:12", "remaining_time": "3:02:55", "throughput": 1486.62, "total_tokens": 22051040} {"current_steps": 104490, "total_steps": 181800, "loss": 0.0021, "lr": 2.2843103877973912e-05, "epoch": 11.495049504950495, "percentage": 57.48, "elapsed_time": "4:07:13", "remaining_time": "3:02:55", "throughput": 1486.63, "total_tokens": 22052096} {"current_steps": 104495, "total_steps": 181800, "loss": 0.0056, "lr": 2.2840712769351047e-05, "epoch": 11.495599559955995, "percentage": 57.48, "elapsed_time": "4:07:14", "remaining_time": "3:02:54", "throughput": 1486.63, "total_tokens": 22053184} {"current_steps": 104500, "total_steps": 181800, "loss": 0.0853, "lr": 2.2838321680629298e-05, "epoch": 11.496149614961496, "percentage": 57.48, "elapsed_time": "4:07:15", "remaining_time": "3:02:53", "throughput": 1486.63, "total_tokens": 22054208} {"current_steps": 104505, "total_steps": 181800, "loss": 0.0046, "lr": 2.283593061183069e-05, "epoch": 11.496699669966997, "percentage": 57.48, "elapsed_time": "4:07:15", "remaining_time": "3:02:52", "throughput": 1486.63, "total_tokens": 22055264} {"current_steps": 104510, "total_steps": 181800, "loss": 0.0184, "lr": 2.283353956297728e-05, "epoch": 11.497249724972498, "percentage": 57.49, "elapsed_time": "4:07:16", "remaining_time": "3:02:52", "throughput": 1486.64, "total_tokens": 22056352} {"current_steps": 104515, "total_steps": 181800, "loss": 0.0033, "lr": 2.283114853409109e-05, "epoch": 11.497799779977997, "percentage": 57.49, "elapsed_time": "4:07:17", "remaining_time": "3:02:51", "throughput": 1486.64, "total_tokens": 22057376} {"current_steps": 104520, "total_steps": 181800, "loss": 0.1057, "lr": 2.2828757525194166e-05, "epoch": 11.498349834983498, "percentage": 57.49, "elapsed_time": "4:07:17", "remaining_time": "3:02:50", "throughput": 1486.64, "total_tokens": 22058432} {"current_steps": 104525, "total_steps": 181800, "loss": 0.0114, "lr": 2.2826366536308552e-05, "epoch": 11.498899889989, "percentage": 57.49, "elapsed_time": "4:07:18", "remaining_time": "3:02:50", "throughput": 1486.64, "total_tokens": 22059488} {"current_steps": 104530, "total_steps": 181800, "loss": 0.1094, "lr": 2.282397556745626e-05, "epoch": 11.499449944994499, "percentage": 57.5, "elapsed_time": "4:07:19", "remaining_time": "3:02:49", "throughput": 1486.65, "total_tokens": 22060608} {"current_steps": 104535, "total_steps": 181800, "loss": 0.0038, "lr": 2.2821584618659347e-05, "epoch": 11.5, "percentage": 57.5, "elapsed_time": "4:07:19", "remaining_time": "3:02:48", "throughput": 1486.65, "total_tokens": 22061664} {"current_steps": 104540, "total_steps": 181800, "loss": 0.0034, "lr": 2.281919368993984e-05, "epoch": 11.500550055005501, "percentage": 57.5, "elapsed_time": "4:07:20", "remaining_time": "3:02:47", "throughput": 1486.66, "total_tokens": 22062784} {"current_steps": 104545, "total_steps": 181800, "loss": 0.1914, "lr": 2.2816802781319786e-05, "epoch": 11.501100110011, "percentage": 57.51, "elapsed_time": "4:07:21", "remaining_time": "3:02:47", "throughput": 1486.66, "total_tokens": 22063840} {"current_steps": 104550, "total_steps": 181800, "loss": 0.0249, "lr": 2.2814411892821207e-05, "epoch": 11.501650165016502, "percentage": 57.51, "elapsed_time": "4:07:21", "remaining_time": "3:02:46", "throughput": 1486.66, "total_tokens": 22064896} {"current_steps": 104555, "total_steps": 181800, "loss": 0.0325, "lr": 2.2812021024466142e-05, "epoch": 11.502200220022003, "percentage": 57.51, "elapsed_time": "4:07:22", "remaining_time": "3:02:45", "throughput": 1486.67, "total_tokens": 22066016} {"current_steps": 104560, "total_steps": 181800, "loss": 0.0025, "lr": 2.280963017627664e-05, "epoch": 11.502750275027502, "percentage": 57.51, "elapsed_time": "4:07:23", "remaining_time": "3:02:44", "throughput": 1486.67, "total_tokens": 22067136} {"current_steps": 104565, "total_steps": 181800, "loss": 0.005, "lr": 2.2807239348274717e-05, "epoch": 11.503300330033003, "percentage": 57.52, "elapsed_time": "4:07:23", "remaining_time": "3:02:44", "throughput": 1486.67, "total_tokens": 22068192} {"current_steps": 104570, "total_steps": 181800, "loss": 0.0025, "lr": 2.2804848540482417e-05, "epoch": 11.503850385038504, "percentage": 57.52, "elapsed_time": "4:07:24", "remaining_time": "3:02:43", "throughput": 1486.67, "total_tokens": 22069216} {"current_steps": 104575, "total_steps": 181800, "loss": 0.0982, "lr": 2.280245775292178e-05, "epoch": 11.504400440044005, "percentage": 57.52, "elapsed_time": "4:07:25", "remaining_time": "3:02:42", "throughput": 1486.68, "total_tokens": 22070272} {"current_steps": 104580, "total_steps": 181800, "loss": 0.0088, "lr": 2.2800066985614828e-05, "epoch": 11.504950495049505, "percentage": 57.52, "elapsed_time": "4:07:26", "remaining_time": "3:02:42", "throughput": 1486.68, "total_tokens": 22071392} {"current_steps": 104585, "total_steps": 181800, "loss": 0.0029, "lr": 2.2797676238583612e-05, "epoch": 11.505500550055006, "percentage": 57.53, "elapsed_time": "4:07:26", "remaining_time": "3:02:41", "throughput": 1486.68, "total_tokens": 22072384} {"current_steps": 104590, "total_steps": 181800, "loss": 0.0073, "lr": 2.279528551185015e-05, "epoch": 11.506050605060507, "percentage": 57.53, "elapsed_time": "4:07:27", "remaining_time": "3:02:40", "throughput": 1486.69, "total_tokens": 22073472} {"current_steps": 104595, "total_steps": 181800, "loss": 0.0024, "lr": 2.2792894805436484e-05, "epoch": 11.506600660066006, "percentage": 57.53, "elapsed_time": "4:07:28", "remaining_time": "3:02:39", "throughput": 1486.69, "total_tokens": 22074560} {"current_steps": 104600, "total_steps": 181800, "loss": 0.0293, "lr": 2.2790504119364654e-05, "epoch": 11.507150715071507, "percentage": 57.54, "elapsed_time": "4:07:28", "remaining_time": "3:02:39", "throughput": 1486.69, "total_tokens": 22075616} {"current_steps": 104605, "total_steps": 181800, "loss": 0.0201, "lr": 2.278811345365668e-05, "epoch": 11.507700770077008, "percentage": 57.54, "elapsed_time": "4:07:29", "remaining_time": "3:02:38", "throughput": 1486.7, "total_tokens": 22076768} {"current_steps": 104610, "total_steps": 181800, "loss": 0.0087, "lr": 2.2785722808334605e-05, "epoch": 11.508250825082508, "percentage": 57.54, "elapsed_time": "4:07:30", "remaining_time": "3:02:37", "throughput": 1486.7, "total_tokens": 22077856} {"current_steps": 104615, "total_steps": 181800, "loss": 0.0046, "lr": 2.2783332183420458e-05, "epoch": 11.508800880088009, "percentage": 57.54, "elapsed_time": "4:07:30", "remaining_time": "3:02:36", "throughput": 1486.71, "total_tokens": 22078944} {"current_steps": 104620, "total_steps": 181800, "loss": 0.0435, "lr": 2.2780941578936282e-05, "epoch": 11.50935093509351, "percentage": 57.55, "elapsed_time": "4:07:31", "remaining_time": "3:02:36", "throughput": 1486.71, "total_tokens": 22080000} {"current_steps": 104625, "total_steps": 181800, "loss": 0.003, "lr": 2.27785509949041e-05, "epoch": 11.509900990099009, "percentage": 57.55, "elapsed_time": "4:07:32", "remaining_time": "3:02:35", "throughput": 1486.71, "total_tokens": 22081088} {"current_steps": 104630, "total_steps": 181800, "loss": 0.0057, "lr": 2.2776160431345943e-05, "epoch": 11.51045104510451, "percentage": 57.55, "elapsed_time": "4:07:32", "remaining_time": "3:02:34", "throughput": 1486.72, "total_tokens": 22082176} {"current_steps": 104635, "total_steps": 181800, "loss": 0.0027, "lr": 2.277376988828385e-05, "epoch": 11.511001100110011, "percentage": 57.56, "elapsed_time": "4:07:33", "remaining_time": "3:02:34", "throughput": 1486.72, "total_tokens": 22083200} {"current_steps": 104640, "total_steps": 181800, "loss": 0.0016, "lr": 2.2771379365739847e-05, "epoch": 11.511551155115512, "percentage": 57.56, "elapsed_time": "4:07:34", "remaining_time": "3:02:33", "throughput": 1486.72, "total_tokens": 22084256} {"current_steps": 104645, "total_steps": 181800, "loss": 0.0052, "lr": 2.2768988863735985e-05, "epoch": 11.512101210121012, "percentage": 57.56, "elapsed_time": "4:07:35", "remaining_time": "3:02:32", "throughput": 1486.72, "total_tokens": 22085248} {"current_steps": 104650, "total_steps": 181800, "loss": 0.0142, "lr": 2.2766598382294275e-05, "epoch": 11.512651265126513, "percentage": 57.56, "elapsed_time": "4:07:35", "remaining_time": "3:02:31", "throughput": 1486.72, "total_tokens": 22086336} {"current_steps": 104655, "total_steps": 181800, "loss": 0.0111, "lr": 2.276420792143675e-05, "epoch": 11.513201320132014, "percentage": 57.57, "elapsed_time": "4:07:36", "remaining_time": "3:02:31", "throughput": 1486.73, "total_tokens": 22087392} {"current_steps": 104660, "total_steps": 181800, "loss": 0.0129, "lr": 2.2761817481185458e-05, "epoch": 11.513751375137513, "percentage": 57.57, "elapsed_time": "4:07:37", "remaining_time": "3:02:30", "throughput": 1486.73, "total_tokens": 22088416} {"current_steps": 104665, "total_steps": 181800, "loss": 0.007, "lr": 2.2759427061562417e-05, "epoch": 11.514301430143014, "percentage": 57.57, "elapsed_time": "4:07:37", "remaining_time": "3:02:29", "throughput": 1486.73, "total_tokens": 22089440} {"current_steps": 104670, "total_steps": 181800, "loss": 0.0334, "lr": 2.2757036662589654e-05, "epoch": 11.514851485148515, "percentage": 57.57, "elapsed_time": "4:07:38", "remaining_time": "3:02:29", "throughput": 1486.73, "total_tokens": 22090464} {"current_steps": 104675, "total_steps": 181800, "loss": 0.1416, "lr": 2.2754646284289217e-05, "epoch": 11.515401540154015, "percentage": 57.58, "elapsed_time": "4:07:39", "remaining_time": "3:02:28", "throughput": 1486.73, "total_tokens": 22091488} {"current_steps": 104680, "total_steps": 181800, "loss": 0.0121, "lr": 2.275225592668312e-05, "epoch": 11.515951595159516, "percentage": 57.58, "elapsed_time": "4:07:39", "remaining_time": "3:02:27", "throughput": 1486.73, "total_tokens": 22092576} {"current_steps": 104685, "total_steps": 181800, "loss": 0.0094, "lr": 2.2749865589793407e-05, "epoch": 11.516501650165017, "percentage": 57.58, "elapsed_time": "4:07:40", "remaining_time": "3:02:26", "throughput": 1486.73, "total_tokens": 22093600} {"current_steps": 104690, "total_steps": 181800, "loss": 0.1317, "lr": 2.274747527364211e-05, "epoch": 11.517051705170516, "percentage": 57.59, "elapsed_time": "4:07:41", "remaining_time": "3:02:26", "throughput": 1486.73, "total_tokens": 22094688} {"current_steps": 104695, "total_steps": 181800, "loss": 0.0007, "lr": 2.2745084978251232e-05, "epoch": 11.517601760176017, "percentage": 57.59, "elapsed_time": "4:07:41", "remaining_time": "3:02:25", "throughput": 1486.73, "total_tokens": 22095712} {"current_steps": 104700, "total_steps": 181800, "loss": 0.0024, "lr": 2.274269470364284e-05, "epoch": 11.518151815181518, "percentage": 57.59, "elapsed_time": "4:07:42", "remaining_time": "3:02:24", "throughput": 1486.73, "total_tokens": 22096736} {"current_steps": 104705, "total_steps": 181800, "loss": 0.004, "lr": 2.2740304449838938e-05, "epoch": 11.51870187018702, "percentage": 57.59, "elapsed_time": "4:07:43", "remaining_time": "3:02:23", "throughput": 1486.73, "total_tokens": 22097696} {"current_steps": 104710, "total_steps": 181800, "loss": 0.0033, "lr": 2.2737914216861576e-05, "epoch": 11.519251925192519, "percentage": 57.6, "elapsed_time": "4:07:44", "remaining_time": "3:02:23", "throughput": 1486.71, "total_tokens": 22098720} {"current_steps": 104715, "total_steps": 181800, "loss": 0.0194, "lr": 2.2735524004732775e-05, "epoch": 11.51980198019802, "percentage": 57.6, "elapsed_time": "4:07:44", "remaining_time": "3:02:22", "throughput": 1486.72, "total_tokens": 22099872} {"current_steps": 104720, "total_steps": 181800, "loss": 0.0466, "lr": 2.273313381347455e-05, "epoch": 11.520352035203521, "percentage": 57.6, "elapsed_time": "4:07:45", "remaining_time": "3:02:21", "throughput": 1486.72, "total_tokens": 22100864} {"current_steps": 104725, "total_steps": 181800, "loss": 0.0329, "lr": 2.2730743643108952e-05, "epoch": 11.52090209020902, "percentage": 57.6, "elapsed_time": "4:07:46", "remaining_time": "3:02:21", "throughput": 1486.72, "total_tokens": 22101920} {"current_steps": 104730, "total_steps": 181800, "loss": 0.16, "lr": 2.272835349365799e-05, "epoch": 11.521452145214521, "percentage": 57.61, "elapsed_time": "4:07:46", "remaining_time": "3:02:20", "throughput": 1486.72, "total_tokens": 22103008} {"current_steps": 104735, "total_steps": 181800, "loss": 0.0369, "lr": 2.272596336514372e-05, "epoch": 11.522002200220022, "percentage": 57.61, "elapsed_time": "4:07:47", "remaining_time": "3:02:19", "throughput": 1486.72, "total_tokens": 22104032} {"current_steps": 104740, "total_steps": 181800, "loss": 0.0032, "lr": 2.2723573257588147e-05, "epoch": 11.522552255225522, "percentage": 57.61, "elapsed_time": "4:07:48", "remaining_time": "3:02:19", "throughput": 1486.72, "total_tokens": 22105024} {"current_steps": 104745, "total_steps": 181800, "loss": 0.0923, "lr": 2.27211831710133e-05, "epoch": 11.523102310231023, "percentage": 57.62, "elapsed_time": "4:07:48", "remaining_time": "3:02:18", "throughput": 1486.73, "total_tokens": 22106112} {"current_steps": 104750, "total_steps": 181800, "loss": 0.1191, "lr": 2.2718793105441227e-05, "epoch": 11.523652365236524, "percentage": 57.62, "elapsed_time": "4:07:49", "remaining_time": "3:02:17", "throughput": 1486.73, "total_tokens": 22107168} {"current_steps": 104755, "total_steps": 181800, "loss": 0.0048, "lr": 2.2716403060893927e-05, "epoch": 11.524202420242025, "percentage": 57.62, "elapsed_time": "4:07:50", "remaining_time": "3:02:16", "throughput": 1486.73, "total_tokens": 22108192} {"current_steps": 104760, "total_steps": 181800, "loss": 0.012, "lr": 2.271401303739346e-05, "epoch": 11.524752475247524, "percentage": 57.62, "elapsed_time": "4:07:51", "remaining_time": "3:02:16", "throughput": 1486.73, "total_tokens": 22109312} {"current_steps": 104765, "total_steps": 181800, "loss": 0.0015, "lr": 2.271162303496183e-05, "epoch": 11.525302530253025, "percentage": 57.63, "elapsed_time": "4:07:51", "remaining_time": "3:02:15", "throughput": 1486.74, "total_tokens": 22110368} {"current_steps": 104770, "total_steps": 181800, "loss": 0.1023, "lr": 2.2709233053621075e-05, "epoch": 11.525852585258527, "percentage": 57.63, "elapsed_time": "4:07:52", "remaining_time": "3:02:14", "throughput": 1486.73, "total_tokens": 22111328} {"current_steps": 104775, "total_steps": 181800, "loss": 0.0412, "lr": 2.2706843093393224e-05, "epoch": 11.526402640264026, "percentage": 57.63, "elapsed_time": "4:07:53", "remaining_time": "3:02:13", "throughput": 1486.73, "total_tokens": 22112384} {"current_steps": 104780, "total_steps": 181800, "loss": 0.0468, "lr": 2.270445315430029e-05, "epoch": 11.526952695269527, "percentage": 57.63, "elapsed_time": "4:07:53", "remaining_time": "3:02:13", "throughput": 1486.73, "total_tokens": 22113344} {"current_steps": 104785, "total_steps": 181800, "loss": 0.0306, "lr": 2.2702063236364316e-05, "epoch": 11.527502750275028, "percentage": 57.64, "elapsed_time": "4:07:54", "remaining_time": "3:02:12", "throughput": 1486.73, "total_tokens": 22114368} {"current_steps": 104790, "total_steps": 181800, "loss": 0.057, "lr": 2.2699673339607328e-05, "epoch": 11.528052805280527, "percentage": 57.64, "elapsed_time": "4:07:55", "remaining_time": "3:02:11", "throughput": 1486.74, "total_tokens": 22115520} {"current_steps": 104795, "total_steps": 181800, "loss": 0.1989, "lr": 2.2697283464051334e-05, "epoch": 11.528602860286028, "percentage": 57.64, "elapsed_time": "4:07:55", "remaining_time": "3:02:11", "throughput": 1486.74, "total_tokens": 22116576} {"current_steps": 104800, "total_steps": 181800, "loss": 0.0072, "lr": 2.2694893609718377e-05, "epoch": 11.52915291529153, "percentage": 57.65, "elapsed_time": "4:07:56", "remaining_time": "3:02:10", "throughput": 1486.74, "total_tokens": 22117632} {"current_steps": 104805, "total_steps": 181800, "loss": 0.0025, "lr": 2.269250377663048e-05, "epoch": 11.52970297029703, "percentage": 57.65, "elapsed_time": "4:07:57", "remaining_time": "3:02:09", "throughput": 1486.74, "total_tokens": 22118688} {"current_steps": 104810, "total_steps": 181800, "loss": 0.0248, "lr": 2.2690113964809677e-05, "epoch": 11.53025302530253, "percentage": 57.65, "elapsed_time": "4:07:57", "remaining_time": "3:02:08", "throughput": 1486.75, "total_tokens": 22119744} {"current_steps": 104815, "total_steps": 181800, "loss": 0.0509, "lr": 2.268772417427798e-05, "epoch": 11.530803080308031, "percentage": 57.65, "elapsed_time": "4:07:58", "remaining_time": "3:02:08", "throughput": 1486.75, "total_tokens": 22120768} {"current_steps": 104820, "total_steps": 181800, "loss": 0.0026, "lr": 2.268533440505741e-05, "epoch": 11.531353135313532, "percentage": 57.66, "elapsed_time": "4:07:59", "remaining_time": "3:02:07", "throughput": 1486.75, "total_tokens": 22121824} {"current_steps": 104825, "total_steps": 181800, "loss": 0.005, "lr": 2.2682944657170014e-05, "epoch": 11.531903190319031, "percentage": 57.66, "elapsed_time": "4:08:00", "remaining_time": "3:02:06", "throughput": 1486.76, "total_tokens": 22122944} {"current_steps": 104830, "total_steps": 181800, "loss": 0.0149, "lr": 2.2680554930637798e-05, "epoch": 11.532453245324533, "percentage": 57.66, "elapsed_time": "4:08:00", "remaining_time": "3:02:05", "throughput": 1486.75, "total_tokens": 22123968} {"current_steps": 104835, "total_steps": 181800, "loss": 0.0105, "lr": 2.2678165225482803e-05, "epoch": 11.533003300330034, "percentage": 57.67, "elapsed_time": "4:08:01", "remaining_time": "3:02:05", "throughput": 1486.76, "total_tokens": 22125088} {"current_steps": 104840, "total_steps": 181800, "loss": 0.0092, "lr": 2.2675775541727042e-05, "epoch": 11.533553355335533, "percentage": 57.67, "elapsed_time": "4:08:02", "remaining_time": "3:02:04", "throughput": 1486.76, "total_tokens": 22126176} {"current_steps": 104845, "total_steps": 181800, "loss": 0.0028, "lr": 2.2673385879392538e-05, "epoch": 11.534103410341034, "percentage": 57.67, "elapsed_time": "4:08:02", "remaining_time": "3:02:03", "throughput": 1486.76, "total_tokens": 22127200} {"current_steps": 104850, "total_steps": 181800, "loss": 0.009, "lr": 2.2670996238501326e-05, "epoch": 11.534653465346535, "percentage": 57.67, "elapsed_time": "4:08:03", "remaining_time": "3:02:03", "throughput": 1486.77, "total_tokens": 22128256} {"current_steps": 104855, "total_steps": 181800, "loss": 0.0526, "lr": 2.2668606619075424e-05, "epoch": 11.535203520352034, "percentage": 57.68, "elapsed_time": "4:08:04", "remaining_time": "3:02:02", "throughput": 1486.77, "total_tokens": 22129344} {"current_steps": 104860, "total_steps": 181800, "loss": 0.0165, "lr": 2.2666217021136846e-05, "epoch": 11.535753575357536, "percentage": 57.68, "elapsed_time": "4:08:04", "remaining_time": "3:02:01", "throughput": 1486.77, "total_tokens": 22130336} {"current_steps": 104865, "total_steps": 181800, "loss": 0.005, "lr": 2.2663827444707637e-05, "epoch": 11.536303630363037, "percentage": 57.68, "elapsed_time": "4:08:05", "remaining_time": "3:02:00", "throughput": 1486.77, "total_tokens": 22131360} {"current_steps": 104870, "total_steps": 181800, "loss": 0.0378, "lr": 2.2661437889809803e-05, "epoch": 11.536853685368538, "percentage": 57.68, "elapsed_time": "4:08:06", "remaining_time": "3:02:00", "throughput": 1486.77, "total_tokens": 22132384} {"current_steps": 104875, "total_steps": 181800, "loss": 0.0042, "lr": 2.2659048356465375e-05, "epoch": 11.537403740374037, "percentage": 57.69, "elapsed_time": "4:08:06", "remaining_time": "3:01:59", "throughput": 1486.77, "total_tokens": 22133504} {"current_steps": 104880, "total_steps": 181800, "loss": 0.0024, "lr": 2.2656658844696378e-05, "epoch": 11.537953795379538, "percentage": 57.69, "elapsed_time": "4:08:07", "remaining_time": "3:01:58", "throughput": 1486.77, "total_tokens": 22134496} {"current_steps": 104885, "total_steps": 181800, "loss": 0.1567, "lr": 2.2654269354524823e-05, "epoch": 11.53850385038504, "percentage": 57.69, "elapsed_time": "4:08:08", "remaining_time": "3:01:57", "throughput": 1486.77, "total_tokens": 22135552} {"current_steps": 104890, "total_steps": 181800, "loss": 0.0699, "lr": 2.2651879885972758e-05, "epoch": 11.539053905390539, "percentage": 57.7, "elapsed_time": "4:08:08", "remaining_time": "3:01:57", "throughput": 1486.77, "total_tokens": 22136544} {"current_steps": 104895, "total_steps": 181800, "loss": 0.0219, "lr": 2.2649490439062174e-05, "epoch": 11.53960396039604, "percentage": 57.7, "elapsed_time": "4:08:09", "remaining_time": "3:01:56", "throughput": 1486.77, "total_tokens": 22137568} {"current_steps": 104900, "total_steps": 181800, "loss": 0.002, "lr": 2.2647101013815116e-05, "epoch": 11.54015401540154, "percentage": 57.7, "elapsed_time": "4:08:10", "remaining_time": "3:01:55", "throughput": 1486.77, "total_tokens": 22138624} {"current_steps": 104905, "total_steps": 181800, "loss": 0.0053, "lr": 2.26447116102536e-05, "epoch": 11.54070407040704, "percentage": 57.7, "elapsed_time": "4:08:11", "remaining_time": "3:01:55", "throughput": 1486.78, "total_tokens": 22139680} {"current_steps": 104910, "total_steps": 181800, "loss": 0.0348, "lr": 2.2642322228399644e-05, "epoch": 11.541254125412541, "percentage": 57.71, "elapsed_time": "4:08:11", "remaining_time": "3:01:54", "throughput": 1486.78, "total_tokens": 22140736} {"current_steps": 104915, "total_steps": 181800, "loss": 0.0449, "lr": 2.2639932868275274e-05, "epoch": 11.541804180418042, "percentage": 57.71, "elapsed_time": "4:08:12", "remaining_time": "3:01:53", "throughput": 1486.78, "total_tokens": 22141792} {"current_steps": 104920, "total_steps": 181800, "loss": 0.0218, "lr": 2.2637543529902503e-05, "epoch": 11.542354235423542, "percentage": 57.71, "elapsed_time": "4:08:13", "remaining_time": "3:01:52", "throughput": 1486.78, "total_tokens": 22142848} {"current_steps": 104925, "total_steps": 181800, "loss": 0.014, "lr": 2.263515421330337e-05, "epoch": 11.542904290429043, "percentage": 57.71, "elapsed_time": "4:08:13", "remaining_time": "3:01:52", "throughput": 1486.78, "total_tokens": 22143872} {"current_steps": 104930, "total_steps": 181800, "loss": 0.069, "lr": 2.2632764918499885e-05, "epoch": 11.543454345434544, "percentage": 57.72, "elapsed_time": "4:08:14", "remaining_time": "3:01:51", "throughput": 1486.78, "total_tokens": 22144864} {"current_steps": 104935, "total_steps": 181800, "loss": 0.0219, "lr": 2.2630375645514062e-05, "epoch": 11.544004400440045, "percentage": 57.72, "elapsed_time": "4:08:15", "remaining_time": "3:01:50", "throughput": 1486.78, "total_tokens": 22145920} {"current_steps": 104940, "total_steps": 181800, "loss": 0.0857, "lr": 2.2627986394367938e-05, "epoch": 11.544554455445544, "percentage": 57.72, "elapsed_time": "4:08:15", "remaining_time": "3:01:50", "throughput": 1486.79, "total_tokens": 22146976} {"current_steps": 104945, "total_steps": 181800, "loss": 0.0701, "lr": 2.2625597165083514e-05, "epoch": 11.545104510451045, "percentage": 57.73, "elapsed_time": "4:08:16", "remaining_time": "3:01:49", "throughput": 1486.78, "total_tokens": 22147968} {"current_steps": 104950, "total_steps": 181800, "loss": 0.0189, "lr": 2.2623207957682836e-05, "epoch": 11.545654565456546, "percentage": 57.73, "elapsed_time": "4:08:17", "remaining_time": "3:01:48", "throughput": 1486.79, "total_tokens": 22149088} {"current_steps": 104955, "total_steps": 181800, "loss": 0.0215, "lr": 2.2620818772187904e-05, "epoch": 11.546204620462046, "percentage": 57.73, "elapsed_time": "4:08:17", "remaining_time": "3:01:47", "throughput": 1486.78, "total_tokens": 22150048} {"current_steps": 104960, "total_steps": 181800, "loss": 0.0095, "lr": 2.2618429608620738e-05, "epoch": 11.546754675467547, "percentage": 57.73, "elapsed_time": "4:08:18", "remaining_time": "3:01:47", "throughput": 1486.78, "total_tokens": 22151072} {"current_steps": 104965, "total_steps": 181800, "loss": 0.0008, "lr": 2.2616040467003373e-05, "epoch": 11.547304730473048, "percentage": 57.74, "elapsed_time": "4:08:19", "remaining_time": "3:01:46", "throughput": 1486.78, "total_tokens": 22152096} {"current_steps": 104970, "total_steps": 181800, "loss": 0.0036, "lr": 2.2613651347357813e-05, "epoch": 11.547854785478547, "percentage": 57.74, "elapsed_time": "4:08:20", "remaining_time": "3:01:45", "throughput": 1486.79, "total_tokens": 22153152} {"current_steps": 104975, "total_steps": 181800, "loss": 0.0311, "lr": 2.2611262249706083e-05, "epoch": 11.548404840484048, "percentage": 57.74, "elapsed_time": "4:08:20", "remaining_time": "3:01:44", "throughput": 1486.79, "total_tokens": 22154208} {"current_steps": 104980, "total_steps": 181800, "loss": 0.0226, "lr": 2.260887317407021e-05, "epoch": 11.54895489548955, "percentage": 57.74, "elapsed_time": "4:08:21", "remaining_time": "3:01:44", "throughput": 1486.79, "total_tokens": 22155232} {"current_steps": 104985, "total_steps": 181800, "loss": 0.0262, "lr": 2.2606484120472196e-05, "epoch": 11.549504950495049, "percentage": 57.75, "elapsed_time": "4:08:22", "remaining_time": "3:01:43", "throughput": 1486.79, "total_tokens": 22156352} {"current_steps": 104990, "total_steps": 181800, "loss": 0.0062, "lr": 2.2604095088934074e-05, "epoch": 11.55005500550055, "percentage": 57.75, "elapsed_time": "4:08:22", "remaining_time": "3:01:42", "throughput": 1486.8, "total_tokens": 22157408} {"current_steps": 104995, "total_steps": 181800, "loss": 0.0058, "lr": 2.260170607947785e-05, "epoch": 11.55060506050605, "percentage": 57.75, "elapsed_time": "4:08:23", "remaining_time": "3:01:42", "throughput": 1486.8, "total_tokens": 22158432} {"current_steps": 105000, "total_steps": 181800, "loss": 0.0098, "lr": 2.2599317092125562e-05, "epoch": 11.551155115511552, "percentage": 57.76, "elapsed_time": "4:08:24", "remaining_time": "3:01:41", "throughput": 1486.8, "total_tokens": 22159552} {"current_steps": 105005, "total_steps": 181800, "loss": 0.0402, "lr": 2.2596928126899217e-05, "epoch": 11.551705170517051, "percentage": 57.76, "elapsed_time": "4:08:24", "remaining_time": "3:01:40", "throughput": 1486.81, "total_tokens": 22160640} {"current_steps": 105010, "total_steps": 181800, "loss": 0.0412, "lr": 2.2594539183820822e-05, "epoch": 11.552255225522552, "percentage": 57.76, "elapsed_time": "4:08:25", "remaining_time": "3:01:39", "throughput": 1486.81, "total_tokens": 22161728} {"current_steps": 105015, "total_steps": 181800, "loss": 0.0344, "lr": 2.2592150262912413e-05, "epoch": 11.552805280528053, "percentage": 57.76, "elapsed_time": "4:08:26", "remaining_time": "3:01:39", "throughput": 1486.81, "total_tokens": 22162784} {"current_steps": 105020, "total_steps": 181800, "loss": 0.1362, "lr": 2.258976136419599e-05, "epoch": 11.553355335533553, "percentage": 57.77, "elapsed_time": "4:08:26", "remaining_time": "3:01:38", "throughput": 1486.82, "total_tokens": 22163872} {"current_steps": 105025, "total_steps": 181800, "loss": 0.0126, "lr": 2.2587372487693595e-05, "epoch": 11.553905390539054, "percentage": 57.77, "elapsed_time": "4:08:27", "remaining_time": "3:01:37", "throughput": 1486.82, "total_tokens": 22164864} {"current_steps": 105030, "total_steps": 181800, "loss": 0.013, "lr": 2.258498363342722e-05, "epoch": 11.554455445544555, "percentage": 57.77, "elapsed_time": "4:08:28", "remaining_time": "3:01:36", "throughput": 1486.82, "total_tokens": 22165888} {"current_steps": 105035, "total_steps": 181800, "loss": 0.0255, "lr": 2.258259480141889e-05, "epoch": 11.555005500550054, "percentage": 57.78, "elapsed_time": "4:08:28", "remaining_time": "3:01:36", "throughput": 1486.82, "total_tokens": 22166944} {"current_steps": 105040, "total_steps": 181800, "loss": 0.0173, "lr": 2.2580205991690638e-05, "epoch": 11.555555555555555, "percentage": 57.78, "elapsed_time": "4:08:29", "remaining_time": "3:01:35", "throughput": 1486.82, "total_tokens": 22168064} {"current_steps": 105045, "total_steps": 181800, "loss": 0.1748, "lr": 2.2577817204264454e-05, "epoch": 11.556105610561056, "percentage": 57.78, "elapsed_time": "4:08:30", "remaining_time": "3:01:34", "throughput": 1486.83, "total_tokens": 22169120} {"current_steps": 105050, "total_steps": 181800, "loss": 0.0106, "lr": 2.2575428439162362e-05, "epoch": 11.556655665566556, "percentage": 57.78, "elapsed_time": "4:08:31", "remaining_time": "3:01:34", "throughput": 1486.83, "total_tokens": 22170208} {"current_steps": 105055, "total_steps": 181800, "loss": 0.0023, "lr": 2.25730396964064e-05, "epoch": 11.557205720572057, "percentage": 57.79, "elapsed_time": "4:08:31", "remaining_time": "3:01:33", "throughput": 1486.83, "total_tokens": 22171168} {"current_steps": 105060, "total_steps": 181800, "loss": 0.0041, "lr": 2.2570650976018542e-05, "epoch": 11.557755775577558, "percentage": 57.79, "elapsed_time": "4:08:32", "remaining_time": "3:01:32", "throughput": 1486.83, "total_tokens": 22172224} {"current_steps": 105065, "total_steps": 181800, "loss": 0.0318, "lr": 2.256826227802085e-05, "epoch": 11.558305830583059, "percentage": 57.79, "elapsed_time": "4:08:33", "remaining_time": "3:01:31", "throughput": 1486.83, "total_tokens": 22173280} {"current_steps": 105070, "total_steps": 181800, "loss": 0.0281, "lr": 2.2565873602435307e-05, "epoch": 11.558855885588558, "percentage": 57.79, "elapsed_time": "4:08:33", "remaining_time": "3:01:31", "throughput": 1486.83, "total_tokens": 22174336} {"current_steps": 105075, "total_steps": 181800, "loss": 0.0406, "lr": 2.256348494928394e-05, "epoch": 11.55940594059406, "percentage": 57.8, "elapsed_time": "4:08:34", "remaining_time": "3:01:30", "throughput": 1486.84, "total_tokens": 22175456} {"current_steps": 105080, "total_steps": 181800, "loss": 0.0309, "lr": 2.256109631858877e-05, "epoch": 11.55995599559956, "percentage": 57.8, "elapsed_time": "4:08:35", "remaining_time": "3:01:29", "throughput": 1486.84, "total_tokens": 22176512} {"current_steps": 105085, "total_steps": 181800, "loss": 0.004, "lr": 2.2558707710371795e-05, "epoch": 11.56050605060506, "percentage": 57.8, "elapsed_time": "4:08:35", "remaining_time": "3:01:29", "throughput": 1486.84, "total_tokens": 22177536} {"current_steps": 105090, "total_steps": 181800, "loss": 0.0051, "lr": 2.2556319124655045e-05, "epoch": 11.561056105610561, "percentage": 57.81, "elapsed_time": "4:08:36", "remaining_time": "3:01:28", "throughput": 1486.84, "total_tokens": 22178528} {"current_steps": 105095, "total_steps": 181800, "loss": 0.147, "lr": 2.2553930561460536e-05, "epoch": 11.561606160616062, "percentage": 57.81, "elapsed_time": "4:08:37", "remaining_time": "3:01:27", "throughput": 1486.84, "total_tokens": 22179584} {"current_steps": 105100, "total_steps": 181800, "loss": 0.0044, "lr": 2.2551542020810262e-05, "epoch": 11.562156215621561, "percentage": 57.81, "elapsed_time": "4:08:37", "remaining_time": "3:01:26", "throughput": 1486.84, "total_tokens": 22180608} {"current_steps": 105105, "total_steps": 181800, "loss": 0.1558, "lr": 2.2549153502726257e-05, "epoch": 11.562706270627062, "percentage": 57.81, "elapsed_time": "4:08:38", "remaining_time": "3:01:26", "throughput": 1486.84, "total_tokens": 22181632} {"current_steps": 105110, "total_steps": 181800, "loss": 0.0065, "lr": 2.254676500723052e-05, "epoch": 11.563256325632564, "percentage": 57.82, "elapsed_time": "4:08:39", "remaining_time": "3:01:25", "throughput": 1486.84, "total_tokens": 22182688} {"current_steps": 105115, "total_steps": 181800, "loss": 0.0024, "lr": 2.254437653434508e-05, "epoch": 11.563806380638063, "percentage": 57.82, "elapsed_time": "4:08:40", "remaining_time": "3:01:24", "throughput": 1486.85, "total_tokens": 22183744} {"current_steps": 105120, "total_steps": 181800, "loss": 0.0254, "lr": 2.2541988084091953e-05, "epoch": 11.564356435643564, "percentage": 57.82, "elapsed_time": "4:08:40", "remaining_time": "3:01:23", "throughput": 1486.85, "total_tokens": 22184768} {"current_steps": 105125, "total_steps": 181800, "loss": 0.0039, "lr": 2.2539599656493127e-05, "epoch": 11.564906490649065, "percentage": 57.82, "elapsed_time": "4:08:41", "remaining_time": "3:01:23", "throughput": 1486.85, "total_tokens": 22185888} {"current_steps": 105130, "total_steps": 181800, "loss": 0.0042, "lr": 2.2537211251570637e-05, "epoch": 11.565456545654566, "percentage": 57.83, "elapsed_time": "4:08:42", "remaining_time": "3:01:22", "throughput": 1486.85, "total_tokens": 22186944} {"current_steps": 105135, "total_steps": 181800, "loss": 0.0013, "lr": 2.2534822869346482e-05, "epoch": 11.566006600660065, "percentage": 57.83, "elapsed_time": "4:08:42", "remaining_time": "3:01:21", "throughput": 1486.86, "total_tokens": 22188000} {"current_steps": 105140, "total_steps": 181800, "loss": 0.0916, "lr": 2.253243450984269e-05, "epoch": 11.566556655665567, "percentage": 57.83, "elapsed_time": "4:08:43", "remaining_time": "3:01:21", "throughput": 1486.86, "total_tokens": 22189120} {"current_steps": 105145, "total_steps": 181800, "loss": 0.0117, "lr": 2.2530046173081268e-05, "epoch": 11.567106710671068, "percentage": 57.84, "elapsed_time": "4:08:44", "remaining_time": "3:01:20", "throughput": 1486.86, "total_tokens": 22190176} {"current_steps": 105150, "total_steps": 181800, "loss": 0.012, "lr": 2.2527657859084214e-05, "epoch": 11.567656765676567, "percentage": 57.84, "elapsed_time": "4:08:44", "remaining_time": "3:01:19", "throughput": 1486.86, "total_tokens": 22191200} {"current_steps": 105155, "total_steps": 181800, "loss": 0.0246, "lr": 2.2525269567873562e-05, "epoch": 11.568206820682068, "percentage": 57.84, "elapsed_time": "4:08:45", "remaining_time": "3:01:18", "throughput": 1486.87, "total_tokens": 22192256} {"current_steps": 105160, "total_steps": 181800, "loss": 0.0145, "lr": 2.2522881299471306e-05, "epoch": 11.56875687568757, "percentage": 57.84, "elapsed_time": "4:08:46", "remaining_time": "3:01:18", "throughput": 1486.86, "total_tokens": 22193248} {"current_steps": 105165, "total_steps": 181800, "loss": 0.0081, "lr": 2.2520493053899468e-05, "epoch": 11.569306930693068, "percentage": 57.85, "elapsed_time": "4:08:46", "remaining_time": "3:01:17", "throughput": 1486.86, "total_tokens": 22194272} {"current_steps": 105170, "total_steps": 181800, "loss": 0.1029, "lr": 2.251810483118006e-05, "epoch": 11.56985698569857, "percentage": 57.85, "elapsed_time": "4:08:47", "remaining_time": "3:01:16", "throughput": 1486.87, "total_tokens": 22195328} {"current_steps": 105175, "total_steps": 181800, "loss": 0.0017, "lr": 2.251571663133507e-05, "epoch": 11.57040704070407, "percentage": 57.85, "elapsed_time": "4:08:48", "remaining_time": "3:01:15", "throughput": 1486.87, "total_tokens": 22196352} {"current_steps": 105180, "total_steps": 181800, "loss": 0.2051, "lr": 2.251332845438655e-05, "epoch": 11.570957095709572, "percentage": 57.85, "elapsed_time": "4:08:48", "remaining_time": "3:01:15", "throughput": 1486.87, "total_tokens": 22197408} {"current_steps": 105185, "total_steps": 181800, "loss": 0.0086, "lr": 2.251094030035647e-05, "epoch": 11.571507150715071, "percentage": 57.86, "elapsed_time": "4:08:49", "remaining_time": "3:01:14", "throughput": 1486.87, "total_tokens": 22198464} {"current_steps": 105190, "total_steps": 181800, "loss": 0.0241, "lr": 2.2508552169266868e-05, "epoch": 11.572057205720572, "percentage": 57.86, "elapsed_time": "4:08:50", "remaining_time": "3:01:13", "throughput": 1486.87, "total_tokens": 22199520} {"current_steps": 105195, "total_steps": 181800, "loss": 0.0208, "lr": 2.2506164061139753e-05, "epoch": 11.572607260726073, "percentage": 57.86, "elapsed_time": "4:08:51", "remaining_time": "3:01:13", "throughput": 1486.88, "total_tokens": 22200608} {"current_steps": 105200, "total_steps": 181800, "loss": 0.008, "lr": 2.2503775975997116e-05, "epoch": 11.573157315731573, "percentage": 57.87, "elapsed_time": "4:08:51", "remaining_time": "3:01:12", "throughput": 1486.88, "total_tokens": 22201632} {"current_steps": 105205, "total_steps": 181800, "loss": 0.0933, "lr": 2.250138791386098e-05, "epoch": 11.573707370737074, "percentage": 57.87, "elapsed_time": "4:08:52", "remaining_time": "3:01:11", "throughput": 1486.88, "total_tokens": 22202656} {"current_steps": 105210, "total_steps": 181800, "loss": 0.0723, "lr": 2.249899987475335e-05, "epoch": 11.574257425742575, "percentage": 57.87, "elapsed_time": "4:08:53", "remaining_time": "3:01:10", "throughput": 1486.88, "total_tokens": 22203744} {"current_steps": 105215, "total_steps": 181800, "loss": 0.0957, "lr": 2.249661185869625e-05, "epoch": 11.574807480748074, "percentage": 57.87, "elapsed_time": "4:08:53", "remaining_time": "3:01:10", "throughput": 1486.89, "total_tokens": 22204864} {"current_steps": 105220, "total_steps": 181800, "loss": 0.1087, "lr": 2.249422386571167e-05, "epoch": 11.575357535753575, "percentage": 57.88, "elapsed_time": "4:08:54", "remaining_time": "3:01:09", "throughput": 1486.89, "total_tokens": 22205888} {"current_steps": 105225, "total_steps": 181800, "loss": 0.0925, "lr": 2.249183589582162e-05, "epoch": 11.575907590759076, "percentage": 57.88, "elapsed_time": "4:08:55", "remaining_time": "3:01:08", "throughput": 1486.89, "total_tokens": 22207008} {"current_steps": 105230, "total_steps": 181800, "loss": 0.0027, "lr": 2.2489447949048125e-05, "epoch": 11.576457645764577, "percentage": 57.88, "elapsed_time": "4:08:55", "remaining_time": "3:01:07", "throughput": 1486.89, "total_tokens": 22208032} {"current_steps": 105235, "total_steps": 181800, "loss": 0.0541, "lr": 2.248706002541318e-05, "epoch": 11.577007700770077, "percentage": 57.89, "elapsed_time": "4:08:56", "remaining_time": "3:01:07", "throughput": 1486.89, "total_tokens": 22209056} {"current_steps": 105240, "total_steps": 181800, "loss": 0.0543, "lr": 2.248467212493879e-05, "epoch": 11.577557755775578, "percentage": 57.89, "elapsed_time": "4:08:57", "remaining_time": "3:01:06", "throughput": 1486.9, "total_tokens": 22210144} {"current_steps": 105245, "total_steps": 181800, "loss": 0.131, "lr": 2.2482284247646978e-05, "epoch": 11.578107810781079, "percentage": 57.89, "elapsed_time": "4:08:57", "remaining_time": "3:01:05", "throughput": 1486.9, "total_tokens": 22211232} {"current_steps": 105250, "total_steps": 181800, "loss": 0.0067, "lr": 2.2479896393559738e-05, "epoch": 11.578657865786578, "percentage": 57.89, "elapsed_time": "4:08:58", "remaining_time": "3:01:05", "throughput": 1486.9, "total_tokens": 22212224} {"current_steps": 105255, "total_steps": 181800, "loss": 0.0149, "lr": 2.2477508562699093e-05, "epoch": 11.57920792079208, "percentage": 57.9, "elapsed_time": "4:08:59", "remaining_time": "3:01:04", "throughput": 1486.9, "total_tokens": 22213216} {"current_steps": 105260, "total_steps": 181800, "loss": 0.0061, "lr": 2.2475120755087035e-05, "epoch": 11.57975797579758, "percentage": 57.9, "elapsed_time": "4:09:00", "remaining_time": "3:01:03", "throughput": 1486.9, "total_tokens": 22214304} {"current_steps": 105265, "total_steps": 181800, "loss": 0.0013, "lr": 2.2472732970745575e-05, "epoch": 11.58030803080308, "percentage": 57.9, "elapsed_time": "4:09:00", "remaining_time": "3:01:02", "throughput": 1486.9, "total_tokens": 22215360} {"current_steps": 105270, "total_steps": 181800, "loss": 0.0047, "lr": 2.2470345209696732e-05, "epoch": 11.58085808580858, "percentage": 57.9, "elapsed_time": "4:09:01", "remaining_time": "3:01:02", "throughput": 1486.91, "total_tokens": 22216512} {"current_steps": 105275, "total_steps": 181800, "loss": 0.0652, "lr": 2.2467957471962494e-05, "epoch": 11.581408140814082, "percentage": 57.91, "elapsed_time": "4:09:02", "remaining_time": "3:01:01", "throughput": 1486.91, "total_tokens": 22217536} {"current_steps": 105280, "total_steps": 181800, "loss": 0.0764, "lr": 2.246556975756488e-05, "epoch": 11.581958195819581, "percentage": 57.91, "elapsed_time": "4:09:02", "remaining_time": "3:01:00", "throughput": 1486.91, "total_tokens": 22218560} {"current_steps": 105285, "total_steps": 181800, "loss": 0.006, "lr": 2.24631820665259e-05, "epoch": 11.582508250825082, "percentage": 57.91, "elapsed_time": "4:09:03", "remaining_time": "3:01:00", "throughput": 1486.91, "total_tokens": 22219648} {"current_steps": 105290, "total_steps": 181800, "loss": 0.0112, "lr": 2.2460794398867544e-05, "epoch": 11.583058305830583, "percentage": 57.92, "elapsed_time": "4:09:04", "remaining_time": "3:00:59", "throughput": 1486.91, "total_tokens": 22220672} {"current_steps": 105295, "total_steps": 181800, "loss": 0.0563, "lr": 2.245840675461183e-05, "epoch": 11.583608360836084, "percentage": 57.92, "elapsed_time": "4:09:04", "remaining_time": "3:00:58", "throughput": 1486.92, "total_tokens": 22221856} {"current_steps": 105300, "total_steps": 181800, "loss": 0.0031, "lr": 2.2456019133780758e-05, "epoch": 11.584158415841584, "percentage": 57.92, "elapsed_time": "4:09:05", "remaining_time": "3:00:57", "throughput": 1486.92, "total_tokens": 22222880} {"current_steps": 105305, "total_steps": 181800, "loss": 0.0253, "lr": 2.2453631536396342e-05, "epoch": 11.584708470847085, "percentage": 57.92, "elapsed_time": "4:09:06", "remaining_time": "3:00:57", "throughput": 1486.93, "total_tokens": 22224000} {"current_steps": 105310, "total_steps": 181800, "loss": 0.0081, "lr": 2.2451243962480587e-05, "epoch": 11.585258525852586, "percentage": 57.93, "elapsed_time": "4:09:06", "remaining_time": "3:00:56", "throughput": 1486.93, "total_tokens": 22225088} {"current_steps": 105315, "total_steps": 181800, "loss": 0.1352, "lr": 2.244885641205548e-05, "epoch": 11.585808580858085, "percentage": 57.93, "elapsed_time": "4:09:07", "remaining_time": "3:00:55", "throughput": 1486.93, "total_tokens": 22226112} {"current_steps": 105320, "total_steps": 181800, "loss": 0.0058, "lr": 2.2446468885143052e-05, "epoch": 11.586358635863586, "percentage": 57.93, "elapsed_time": "4:09:08", "remaining_time": "3:00:54", "throughput": 1486.94, "total_tokens": 22227168} {"current_steps": 105325, "total_steps": 181800, "loss": 0.0372, "lr": 2.2444081381765283e-05, "epoch": 11.586908690869087, "percentage": 57.93, "elapsed_time": "4:09:08", "remaining_time": "3:00:54", "throughput": 1486.94, "total_tokens": 22228256} {"current_steps": 105330, "total_steps": 181800, "loss": 0.0053, "lr": 2.2441693901944202e-05, "epoch": 11.587458745874587, "percentage": 57.94, "elapsed_time": "4:09:09", "remaining_time": "3:00:53", "throughput": 1486.95, "total_tokens": 22229344} {"current_steps": 105335, "total_steps": 181800, "loss": 0.0735, "lr": 2.2439306445701798e-05, "epoch": 11.588008800880088, "percentage": 57.94, "elapsed_time": "4:09:10", "remaining_time": "3:00:52", "throughput": 1486.94, "total_tokens": 22230304} {"current_steps": 105340, "total_steps": 181800, "loss": 0.0195, "lr": 2.243691901306007e-05, "epoch": 11.588558855885589, "percentage": 57.94, "elapsed_time": "4:09:11", "remaining_time": "3:00:52", "throughput": 1486.94, "total_tokens": 22231360} {"current_steps": 105345, "total_steps": 181800, "loss": 0.0606, "lr": 2.243453160404104e-05, "epoch": 11.589108910891088, "percentage": 57.95, "elapsed_time": "4:09:11", "remaining_time": "3:00:51", "throughput": 1486.95, "total_tokens": 22232416} {"current_steps": 105350, "total_steps": 181800, "loss": 0.0497, "lr": 2.243214421866669e-05, "epoch": 11.58965896589659, "percentage": 57.95, "elapsed_time": "4:09:12", "remaining_time": "3:00:50", "throughput": 1486.95, "total_tokens": 22233504} {"current_steps": 105355, "total_steps": 181800, "loss": 0.0033, "lr": 2.242975685695904e-05, "epoch": 11.59020902090209, "percentage": 57.95, "elapsed_time": "4:09:13", "remaining_time": "3:00:49", "throughput": 1486.95, "total_tokens": 22234592} {"current_steps": 105360, "total_steps": 181800, "loss": 0.064, "lr": 2.2427369518940092e-05, "epoch": 11.590759075907592, "percentage": 57.95, "elapsed_time": "4:09:13", "remaining_time": "3:00:49", "throughput": 1486.96, "total_tokens": 22235648} {"current_steps": 105365, "total_steps": 181800, "loss": 0.0553, "lr": 2.2424982204631834e-05, "epoch": 11.591309130913091, "percentage": 57.96, "elapsed_time": "4:09:14", "remaining_time": "3:00:48", "throughput": 1486.96, "total_tokens": 22236736} {"current_steps": 105370, "total_steps": 181800, "loss": 0.0337, "lr": 2.2422594914056294e-05, "epoch": 11.591859185918592, "percentage": 57.96, "elapsed_time": "4:09:15", "remaining_time": "3:00:47", "throughput": 1486.97, "total_tokens": 22237856} {"current_steps": 105375, "total_steps": 181800, "loss": 0.0329, "lr": 2.2420207647235448e-05, "epoch": 11.592409240924093, "percentage": 57.96, "elapsed_time": "4:09:15", "remaining_time": "3:00:47", "throughput": 1486.97, "total_tokens": 22238976} {"current_steps": 105380, "total_steps": 181800, "loss": 0.0195, "lr": 2.2417820404191314e-05, "epoch": 11.592959295929592, "percentage": 57.96, "elapsed_time": "4:09:16", "remaining_time": "3:00:46", "throughput": 1486.97, "total_tokens": 22240000} {"current_steps": 105385, "total_steps": 181800, "loss": 0.0396, "lr": 2.2415433184945896e-05, "epoch": 11.593509350935093, "percentage": 57.97, "elapsed_time": "4:09:17", "remaining_time": "3:00:45", "throughput": 1486.97, "total_tokens": 22241024} {"current_steps": 105390, "total_steps": 181800, "loss": 0.051, "lr": 2.2413045989521182e-05, "epoch": 11.594059405940595, "percentage": 57.97, "elapsed_time": "4:09:17", "remaining_time": "3:00:44", "throughput": 1486.98, "total_tokens": 22242112} {"current_steps": 105395, "total_steps": 181800, "loss": 0.1649, "lr": 2.2410658817939185e-05, "epoch": 11.594609460946094, "percentage": 57.97, "elapsed_time": "4:09:18", "remaining_time": "3:00:44", "throughput": 1486.98, "total_tokens": 22243136} {"current_steps": 105400, "total_steps": 181800, "loss": 0.0072, "lr": 2.2408271670221895e-05, "epoch": 11.595159515951595, "percentage": 57.98, "elapsed_time": "4:09:19", "remaining_time": "3:00:43", "throughput": 1486.98, "total_tokens": 22244192} {"current_steps": 105405, "total_steps": 181800, "loss": 0.0044, "lr": 2.2405884546391337e-05, "epoch": 11.595709570957096, "percentage": 57.98, "elapsed_time": "4:09:20", "remaining_time": "3:00:42", "throughput": 1486.98, "total_tokens": 22245248} {"current_steps": 105410, "total_steps": 181800, "loss": 0.0039, "lr": 2.2403497446469486e-05, "epoch": 11.596259625962595, "percentage": 57.98, "elapsed_time": "4:09:20", "remaining_time": "3:00:41", "throughput": 1486.98, "total_tokens": 22246336} {"current_steps": 105415, "total_steps": 181800, "loss": 0.0056, "lr": 2.2401110370478352e-05, "epoch": 11.596809680968097, "percentage": 57.98, "elapsed_time": "4:09:21", "remaining_time": "3:00:41", "throughput": 1486.98, "total_tokens": 22247328} {"current_steps": 105420, "total_steps": 181800, "loss": 0.011, "lr": 2.2398723318439942e-05, "epoch": 11.597359735973598, "percentage": 57.99, "elapsed_time": "4:09:22", "remaining_time": "3:00:40", "throughput": 1486.99, "total_tokens": 22248416} {"current_steps": 105425, "total_steps": 181800, "loss": 0.0087, "lr": 2.2396336290376253e-05, "epoch": 11.597909790979099, "percentage": 57.99, "elapsed_time": "4:09:22", "remaining_time": "3:00:39", "throughput": 1487.0, "total_tokens": 22249600} {"current_steps": 105430, "total_steps": 181800, "loss": 0.0078, "lr": 2.2393949286309276e-05, "epoch": 11.598459845984598, "percentage": 57.99, "elapsed_time": "4:09:23", "remaining_time": "3:00:39", "throughput": 1487.0, "total_tokens": 22250624} {"current_steps": 105435, "total_steps": 181800, "loss": 0.0675, "lr": 2.2391562306261022e-05, "epoch": 11.599009900990099, "percentage": 58.0, "elapsed_time": "4:09:24", "remaining_time": "3:00:38", "throughput": 1487.0, "total_tokens": 22251648} {"current_steps": 105440, "total_steps": 181800, "loss": 0.0654, "lr": 2.238917535025348e-05, "epoch": 11.5995599559956, "percentage": 58.0, "elapsed_time": "4:09:24", "remaining_time": "3:00:37", "throughput": 1487.0, "total_tokens": 22252800} {"current_steps": 105445, "total_steps": 181800, "loss": 0.0026, "lr": 2.238678841830867e-05, "epoch": 11.6001100110011, "percentage": 58.0, "elapsed_time": "4:09:25", "remaining_time": "3:00:36", "throughput": 1487.01, "total_tokens": 22253856} {"current_steps": 105450, "total_steps": 181800, "loss": 0.0411, "lr": 2.2384401510448568e-05, "epoch": 11.6006600660066, "percentage": 58.0, "elapsed_time": "4:09:26", "remaining_time": "3:00:36", "throughput": 1487.01, "total_tokens": 22254944} {"current_steps": 105455, "total_steps": 181800, "loss": 0.003, "lr": 2.2382014626695177e-05, "epoch": 11.601210121012102, "percentage": 58.01, "elapsed_time": "4:09:26", "remaining_time": "3:00:35", "throughput": 1487.01, "total_tokens": 22256032} {"current_steps": 105460, "total_steps": 181800, "loss": 0.0179, "lr": 2.2379627767070512e-05, "epoch": 11.601760176017601, "percentage": 58.01, "elapsed_time": "4:09:27", "remaining_time": "3:00:34", "throughput": 1487.01, "total_tokens": 22257024} {"current_steps": 105465, "total_steps": 181800, "loss": 0.0086, "lr": 2.2377240931596552e-05, "epoch": 11.602310231023102, "percentage": 58.01, "elapsed_time": "4:09:28", "remaining_time": "3:00:33", "throughput": 1487.01, "total_tokens": 22258080} {"current_steps": 105470, "total_steps": 181800, "loss": 0.0644, "lr": 2.2374854120295306e-05, "epoch": 11.602860286028603, "percentage": 58.01, "elapsed_time": "4:09:29", "remaining_time": "3:00:33", "throughput": 1487.01, "total_tokens": 22259136} {"current_steps": 105475, "total_steps": 181800, "loss": 0.0376, "lr": 2.2372467333188778e-05, "epoch": 11.603410341034103, "percentage": 58.02, "elapsed_time": "4:09:29", "remaining_time": "3:00:32", "throughput": 1487.02, "total_tokens": 22260224} {"current_steps": 105480, "total_steps": 181800, "loss": 0.0027, "lr": 2.237008057029894e-05, "epoch": 11.603960396039604, "percentage": 58.02, "elapsed_time": "4:09:30", "remaining_time": "3:00:31", "throughput": 1487.02, "total_tokens": 22261248} {"current_steps": 105485, "total_steps": 181800, "loss": 0.0464, "lr": 2.2367693831647827e-05, "epoch": 11.604510451045105, "percentage": 58.02, "elapsed_time": "4:09:31", "remaining_time": "3:00:31", "throughput": 1487.01, "total_tokens": 22262208} {"current_steps": 105490, "total_steps": 181800, "loss": 0.0201, "lr": 2.2365307117257403e-05, "epoch": 11.605060506050606, "percentage": 58.03, "elapsed_time": "4:09:31", "remaining_time": "3:00:30", "throughput": 1487.02, "total_tokens": 22263296} {"current_steps": 105495, "total_steps": 181800, "loss": 0.0017, "lr": 2.2362920427149686e-05, "epoch": 11.605610561056105, "percentage": 58.03, "elapsed_time": "4:09:32", "remaining_time": "3:00:29", "throughput": 1487.02, "total_tokens": 22264320} {"current_steps": 105500, "total_steps": 181800, "loss": 0.011, "lr": 2.2360533761346668e-05, "epoch": 11.606160616061606, "percentage": 58.03, "elapsed_time": "4:09:33", "remaining_time": "3:00:28", "throughput": 1487.02, "total_tokens": 22265344} {"current_steps": 105505, "total_steps": 181800, "loss": 0.012, "lr": 2.2358147119870338e-05, "epoch": 11.606710671067107, "percentage": 58.03, "elapsed_time": "4:09:33", "remaining_time": "3:00:28", "throughput": 1487.02, "total_tokens": 22266400} {"current_steps": 105510, "total_steps": 181800, "loss": 0.0021, "lr": 2.2355760502742702e-05, "epoch": 11.607260726072607, "percentage": 58.04, "elapsed_time": "4:09:34", "remaining_time": "3:00:27", "throughput": 1487.03, "total_tokens": 22267488} {"current_steps": 105515, "total_steps": 181800, "loss": 0.0062, "lr": 2.2353373909985745e-05, "epoch": 11.607810781078108, "percentage": 58.04, "elapsed_time": "4:09:35", "remaining_time": "3:00:26", "throughput": 1487.03, "total_tokens": 22268544} {"current_steps": 105520, "total_steps": 181800, "loss": 0.0398, "lr": 2.235098734162148e-05, "epoch": 11.608360836083609, "percentage": 58.04, "elapsed_time": "4:09:35", "remaining_time": "3:00:26", "throughput": 1487.03, "total_tokens": 22269632} {"current_steps": 105525, "total_steps": 181800, "loss": 0.0142, "lr": 2.2348600797671894e-05, "epoch": 11.608910891089108, "percentage": 58.04, "elapsed_time": "4:09:36", "remaining_time": "3:00:25", "throughput": 1487.03, "total_tokens": 22270688} {"current_steps": 105530, "total_steps": 181800, "loss": 0.0129, "lr": 2.2346214278158974e-05, "epoch": 11.60946094609461, "percentage": 58.05, "elapsed_time": "4:09:37", "remaining_time": "3:00:24", "throughput": 1487.04, "total_tokens": 22271744} {"current_steps": 105535, "total_steps": 181800, "loss": 0.0716, "lr": 2.2343827783104733e-05, "epoch": 11.61001100110011, "percentage": 58.05, "elapsed_time": "4:09:37", "remaining_time": "3:00:23", "throughput": 1487.04, "total_tokens": 22272800} {"current_steps": 105540, "total_steps": 181800, "loss": 0.0125, "lr": 2.234144131253114e-05, "epoch": 11.61056105610561, "percentage": 58.05, "elapsed_time": "4:09:38", "remaining_time": "3:00:23", "throughput": 1487.04, "total_tokens": 22273856} {"current_steps": 105545, "total_steps": 181800, "loss": 0.0035, "lr": 2.2339054866460226e-05, "epoch": 11.61111111111111, "percentage": 58.06, "elapsed_time": "4:09:39", "remaining_time": "3:00:22", "throughput": 1487.04, "total_tokens": 22274944} {"current_steps": 105550, "total_steps": 181800, "loss": 0.0669, "lr": 2.233666844491396e-05, "epoch": 11.611661166116612, "percentage": 58.06, "elapsed_time": "4:09:40", "remaining_time": "3:00:21", "throughput": 1487.05, "total_tokens": 22276000} {"current_steps": 105555, "total_steps": 181800, "loss": 0.0588, "lr": 2.2334282047914338e-05, "epoch": 11.612211221122113, "percentage": 58.06, "elapsed_time": "4:09:40", "remaining_time": "3:00:20", "throughput": 1487.05, "total_tokens": 22277088} {"current_steps": 105560, "total_steps": 181800, "loss": 0.0146, "lr": 2.233189567548337e-05, "epoch": 11.612761276127612, "percentage": 58.06, "elapsed_time": "4:09:41", "remaining_time": "3:00:20", "throughput": 1487.05, "total_tokens": 22278144} {"current_steps": 105565, "total_steps": 181800, "loss": 0.0029, "lr": 2.2329509327643025e-05, "epoch": 11.613311331133113, "percentage": 58.07, "elapsed_time": "4:09:42", "remaining_time": "3:00:19", "throughput": 1487.06, "total_tokens": 22279264} {"current_steps": 105570, "total_steps": 181800, "loss": 0.0025, "lr": 2.232712300441532e-05, "epoch": 11.613861386138614, "percentage": 58.07, "elapsed_time": "4:09:42", "remaining_time": "3:00:18", "throughput": 1487.07, "total_tokens": 22280384} {"current_steps": 105575, "total_steps": 181800, "loss": 0.0012, "lr": 2.2324736705822243e-05, "epoch": 11.614411441144114, "percentage": 58.07, "elapsed_time": "4:09:43", "remaining_time": "3:00:18", "throughput": 1487.07, "total_tokens": 22281472} {"current_steps": 105580, "total_steps": 181800, "loss": 0.0682, "lr": 2.2322350431885774e-05, "epoch": 11.614961496149615, "percentage": 58.07, "elapsed_time": "4:09:44", "remaining_time": "3:00:17", "throughput": 1487.07, "total_tokens": 22282528} {"current_steps": 105585, "total_steps": 181800, "loss": 0.0037, "lr": 2.231996418262792e-05, "epoch": 11.615511551155116, "percentage": 58.08, "elapsed_time": "4:09:44", "remaining_time": "3:00:16", "throughput": 1487.07, "total_tokens": 22283584} {"current_steps": 105590, "total_steps": 181800, "loss": 0.0323, "lr": 2.231757795807067e-05, "epoch": 11.616061606160617, "percentage": 58.08, "elapsed_time": "4:09:45", "remaining_time": "3:00:15", "throughput": 1487.08, "total_tokens": 22284640} {"current_steps": 105595, "total_steps": 181800, "loss": 0.0059, "lr": 2.2315191758236025e-05, "epoch": 11.616611661166116, "percentage": 58.08, "elapsed_time": "4:09:46", "remaining_time": "3:00:15", "throughput": 1487.07, "total_tokens": 22285632} {"current_steps": 105600, "total_steps": 181800, "loss": 0.0193, "lr": 2.2312805583145963e-05, "epoch": 11.617161716171617, "percentage": 58.09, "elapsed_time": "4:09:46", "remaining_time": "3:00:14", "throughput": 1487.08, "total_tokens": 22286720} {"current_steps": 105605, "total_steps": 181800, "loss": 0.0831, "lr": 2.2310419432822477e-05, "epoch": 11.617711771177119, "percentage": 58.09, "elapsed_time": "4:09:47", "remaining_time": "3:00:13", "throughput": 1487.08, "total_tokens": 22287808} {"current_steps": 105610, "total_steps": 181800, "loss": 0.0011, "lr": 2.2308033307287572e-05, "epoch": 11.618261826182618, "percentage": 58.09, "elapsed_time": "4:09:48", "remaining_time": "3:00:12", "throughput": 1487.08, "total_tokens": 22288832} {"current_steps": 105615, "total_steps": 181800, "loss": 0.0243, "lr": 2.2305647206563235e-05, "epoch": 11.618811881188119, "percentage": 58.09, "elapsed_time": "4:09:48", "remaining_time": "3:00:12", "throughput": 1487.09, "total_tokens": 22289984} {"current_steps": 105620, "total_steps": 181800, "loss": 0.0576, "lr": 2.2303261130671445e-05, "epoch": 11.61936193619362, "percentage": 58.1, "elapsed_time": "4:09:49", "remaining_time": "3:00:11", "throughput": 1487.1, "total_tokens": 22291072} {"current_steps": 105625, "total_steps": 181800, "loss": 0.0208, "lr": 2.230087507963421e-05, "epoch": 11.61991199119912, "percentage": 58.1, "elapsed_time": "4:09:50", "remaining_time": "3:00:10", "throughput": 1487.09, "total_tokens": 22292064} {"current_steps": 105630, "total_steps": 181800, "loss": 0.0399, "lr": 2.2298489053473505e-05, "epoch": 11.62046204620462, "percentage": 58.1, "elapsed_time": "4:09:51", "remaining_time": "3:00:10", "throughput": 1487.09, "total_tokens": 22293088} {"current_steps": 105635, "total_steps": 181800, "loss": 0.0132, "lr": 2.2296103052211344e-05, "epoch": 11.621012101210122, "percentage": 58.11, "elapsed_time": "4:09:51", "remaining_time": "3:00:09", "throughput": 1487.1, "total_tokens": 22294176} {"current_steps": 105640, "total_steps": 181800, "loss": 0.0043, "lr": 2.22937170758697e-05, "epoch": 11.62156215621562, "percentage": 58.11, "elapsed_time": "4:09:52", "remaining_time": "3:00:08", "throughput": 1487.1, "total_tokens": 22295264} {"current_steps": 105645, "total_steps": 181800, "loss": 0.001, "lr": 2.229133112447056e-05, "epoch": 11.622112211221122, "percentage": 58.11, "elapsed_time": "4:09:53", "remaining_time": "3:00:07", "throughput": 1487.1, "total_tokens": 22296320} {"current_steps": 105650, "total_steps": 181800, "loss": 0.0494, "lr": 2.228894519803593e-05, "epoch": 11.622662266226623, "percentage": 58.11, "elapsed_time": "4:09:53", "remaining_time": "3:00:07", "throughput": 1487.11, "total_tokens": 22297376} {"current_steps": 105655, "total_steps": 181800, "loss": 0.0084, "lr": 2.228655929658778e-05, "epoch": 11.623212321232124, "percentage": 58.12, "elapsed_time": "4:09:54", "remaining_time": "3:00:06", "throughput": 1487.11, "total_tokens": 22298432} {"current_steps": 105660, "total_steps": 181800, "loss": 0.0392, "lr": 2.228417342014812e-05, "epoch": 11.623762376237623, "percentage": 58.12, "elapsed_time": "4:09:55", "remaining_time": "3:00:05", "throughput": 1487.11, "total_tokens": 22299552} {"current_steps": 105665, "total_steps": 181800, "loss": 0.0037, "lr": 2.2281787568738926e-05, "epoch": 11.624312431243125, "percentage": 58.12, "elapsed_time": "4:09:55", "remaining_time": "3:00:05", "throughput": 1487.12, "total_tokens": 22300672} {"current_steps": 105670, "total_steps": 181800, "loss": 0.0184, "lr": 2.227940174238219e-05, "epoch": 11.624862486248626, "percentage": 58.12, "elapsed_time": "4:09:56", "remaining_time": "3:00:04", "throughput": 1487.13, "total_tokens": 22301792} {"current_steps": 105675, "total_steps": 181800, "loss": 0.0054, "lr": 2.227701594109991e-05, "epoch": 11.625412541254125, "percentage": 58.13, "elapsed_time": "4:09:57", "remaining_time": "3:00:03", "throughput": 1487.13, "total_tokens": 22302784} {"current_steps": 105680, "total_steps": 181800, "loss": 0.1194, "lr": 2.2274630164914063e-05, "epoch": 11.625962596259626, "percentage": 58.13, "elapsed_time": "4:09:57", "remaining_time": "3:00:02", "throughput": 1487.13, "total_tokens": 22303840} {"current_steps": 105685, "total_steps": 181800, "loss": 0.0026, "lr": 2.2272244413846644e-05, "epoch": 11.626512651265127, "percentage": 58.13, "elapsed_time": "4:09:58", "remaining_time": "3:00:02", "throughput": 1487.13, "total_tokens": 22304896} {"current_steps": 105690, "total_steps": 181800, "loss": 0.1329, "lr": 2.226985868791964e-05, "epoch": 11.627062706270626, "percentage": 58.14, "elapsed_time": "4:09:59", "remaining_time": "3:00:01", "throughput": 1487.13, "total_tokens": 22305920} {"current_steps": 105695, "total_steps": 181800, "loss": 0.0207, "lr": 2.2267472987155033e-05, "epoch": 11.627612761276128, "percentage": 58.14, "elapsed_time": "4:09:59", "remaining_time": "3:00:00", "throughput": 1487.14, "total_tokens": 22307040} {"current_steps": 105700, "total_steps": 181800, "loss": 0.0521, "lr": 2.226508731157482e-05, "epoch": 11.628162816281629, "percentage": 58.14, "elapsed_time": "4:10:00", "remaining_time": "2:59:59", "throughput": 1487.14, "total_tokens": 22308096} {"current_steps": 105705, "total_steps": 181800, "loss": 0.0399, "lr": 2.2262701661200982e-05, "epoch": 11.628712871287128, "percentage": 58.14, "elapsed_time": "4:10:01", "remaining_time": "2:59:59", "throughput": 1487.14, "total_tokens": 22309184} {"current_steps": 105710, "total_steps": 181800, "loss": 0.0175, "lr": 2.2260316036055517e-05, "epoch": 11.629262926292629, "percentage": 58.15, "elapsed_time": "4:10:02", "remaining_time": "2:59:58", "throughput": 1487.14, "total_tokens": 22310176} {"current_steps": 105715, "total_steps": 181800, "loss": 0.0095, "lr": 2.22579304361604e-05, "epoch": 11.62981298129813, "percentage": 58.15, "elapsed_time": "4:10:02", "remaining_time": "2:59:57", "throughput": 1487.14, "total_tokens": 22311200} {"current_steps": 105720, "total_steps": 181800, "loss": 0.0008, "lr": 2.2255544861537615e-05, "epoch": 11.630363036303631, "percentage": 58.15, "elapsed_time": "4:10:03", "remaining_time": "2:59:57", "throughput": 1487.14, "total_tokens": 22312256} {"current_steps": 105725, "total_steps": 181800, "loss": 0.0893, "lr": 2.2253159312209165e-05, "epoch": 11.63091309130913, "percentage": 58.15, "elapsed_time": "4:10:04", "remaining_time": "2:59:56", "throughput": 1487.15, "total_tokens": 22313312} {"current_steps": 105730, "total_steps": 181800, "loss": 0.0328, "lr": 2.2250773788197022e-05, "epoch": 11.631463146314632, "percentage": 58.16, "elapsed_time": "4:10:04", "remaining_time": "2:59:55", "throughput": 1487.15, "total_tokens": 22314368} {"current_steps": 105735, "total_steps": 181800, "loss": 0.0969, "lr": 2.2248388289523186e-05, "epoch": 11.632013201320133, "percentage": 58.16, "elapsed_time": "4:10:05", "remaining_time": "2:59:54", "throughput": 1487.15, "total_tokens": 22315392} {"current_steps": 105740, "total_steps": 181800, "loss": 0.0045, "lr": 2.224600281620963e-05, "epoch": 11.632563256325632, "percentage": 58.16, "elapsed_time": "4:10:06", "remaining_time": "2:59:54", "throughput": 1487.15, "total_tokens": 22316480} {"current_steps": 105745, "total_steps": 181800, "loss": 0.0053, "lr": 2.224361736827834e-05, "epoch": 11.633113311331133, "percentage": 58.17, "elapsed_time": "4:10:06", "remaining_time": "2:59:53", "throughput": 1487.15, "total_tokens": 22317536} {"current_steps": 105750, "total_steps": 181800, "loss": 0.1265, "lr": 2.2241231945751318e-05, "epoch": 11.633663366336634, "percentage": 58.17, "elapsed_time": "4:10:07", "remaining_time": "2:59:52", "throughput": 1487.16, "total_tokens": 22318624} {"current_steps": 105755, "total_steps": 181800, "loss": 0.1091, "lr": 2.223884654865053e-05, "epoch": 11.634213421342134, "percentage": 58.17, "elapsed_time": "4:10:08", "remaining_time": "2:59:51", "throughput": 1487.17, "total_tokens": 22319744} {"current_steps": 105760, "total_steps": 181800, "loss": 0.1331, "lr": 2.2236461176997963e-05, "epoch": 11.634763476347635, "percentage": 58.17, "elapsed_time": "4:10:08", "remaining_time": "2:59:51", "throughput": 1487.17, "total_tokens": 22320800} {"current_steps": 105765, "total_steps": 181800, "loss": 0.0054, "lr": 2.223407583081562e-05, "epoch": 11.635313531353136, "percentage": 58.18, "elapsed_time": "4:10:09", "remaining_time": "2:59:50", "throughput": 1487.17, "total_tokens": 22321920} {"current_steps": 105770, "total_steps": 181800, "loss": 0.0156, "lr": 2.2231690510125462e-05, "epoch": 11.635863586358635, "percentage": 58.18, "elapsed_time": "4:10:10", "remaining_time": "2:59:49", "throughput": 1487.18, "total_tokens": 22323040} {"current_steps": 105775, "total_steps": 181800, "loss": 0.0031, "lr": 2.222930521494949e-05, "epoch": 11.636413641364136, "percentage": 58.18, "elapsed_time": "4:10:10", "remaining_time": "2:59:49", "throughput": 1487.18, "total_tokens": 22324096} {"current_steps": 105780, "total_steps": 181800, "loss": 0.0288, "lr": 2.2226919945309675e-05, "epoch": 11.636963696369637, "percentage": 58.18, "elapsed_time": "4:10:11", "remaining_time": "2:59:48", "throughput": 1487.18, "total_tokens": 22325120} {"current_steps": 105785, "total_steps": 181800, "loss": 0.0469, "lr": 2.2224534701228013e-05, "epoch": 11.637513751375138, "percentage": 58.19, "elapsed_time": "4:10:12", "remaining_time": "2:59:47", "throughput": 1487.18, "total_tokens": 22326144} {"current_steps": 105790, "total_steps": 181800, "loss": 0.1111, "lr": 2.2222149482726488e-05, "epoch": 11.638063806380638, "percentage": 58.19, "elapsed_time": "4:10:13", "remaining_time": "2:59:46", "throughput": 1487.19, "total_tokens": 22327264} {"current_steps": 105795, "total_steps": 181800, "loss": 0.011, "lr": 2.221976428982707e-05, "epoch": 11.638613861386139, "percentage": 58.19, "elapsed_time": "4:10:13", "remaining_time": "2:59:46", "throughput": 1487.2, "total_tokens": 22328384} {"current_steps": 105800, "total_steps": 181800, "loss": 0.0031, "lr": 2.2217379122551753e-05, "epoch": 11.63916391639164, "percentage": 58.2, "elapsed_time": "4:10:14", "remaining_time": "2:59:45", "throughput": 1487.2, "total_tokens": 22329408} {"current_steps": 105805, "total_steps": 181800, "loss": 0.0112, "lr": 2.2214993980922524e-05, "epoch": 11.63971397139714, "percentage": 58.2, "elapsed_time": "4:10:15", "remaining_time": "2:59:44", "throughput": 1487.2, "total_tokens": 22330496} {"current_steps": 105810, "total_steps": 181800, "loss": 0.0144, "lr": 2.2212608864961348e-05, "epoch": 11.64026402640264, "percentage": 58.2, "elapsed_time": "4:10:15", "remaining_time": "2:59:43", "throughput": 1487.2, "total_tokens": 22331520} {"current_steps": 105815, "total_steps": 181800, "loss": 0.014, "lr": 2.2210223774690224e-05, "epoch": 11.640814081408141, "percentage": 58.2, "elapsed_time": "4:10:16", "remaining_time": "2:59:43", "throughput": 1487.2, "total_tokens": 22332576} {"current_steps": 105820, "total_steps": 181800, "loss": 0.0232, "lr": 2.2207838710131127e-05, "epoch": 11.64136413641364, "percentage": 58.21, "elapsed_time": "4:10:17", "remaining_time": "2:59:42", "throughput": 1487.2, "total_tokens": 22333600} {"current_steps": 105825, "total_steps": 181800, "loss": 0.018, "lr": 2.220545367130605e-05, "epoch": 11.641914191419142, "percentage": 58.21, "elapsed_time": "4:10:17", "remaining_time": "2:59:41", "throughput": 1487.2, "total_tokens": 22334624} {"current_steps": 105830, "total_steps": 181800, "loss": 0.0365, "lr": 2.2203068658236957e-05, "epoch": 11.642464246424643, "percentage": 58.21, "elapsed_time": "4:10:18", "remaining_time": "2:59:41", "throughput": 1487.2, "total_tokens": 22335648} {"current_steps": 105835, "total_steps": 181800, "loss": 0.0123, "lr": 2.2200683670945835e-05, "epoch": 11.643014301430142, "percentage": 58.22, "elapsed_time": "4:10:19", "remaining_time": "2:59:40", "throughput": 1487.21, "total_tokens": 22336704} {"current_steps": 105840, "total_steps": 181800, "loss": 0.1457, "lr": 2.219829870945468e-05, "epoch": 11.643564356435643, "percentage": 58.22, "elapsed_time": "4:10:19", "remaining_time": "2:59:39", "throughput": 1487.21, "total_tokens": 22337760} {"current_steps": 105845, "total_steps": 181800, "loss": 0.0446, "lr": 2.2195913773785442e-05, "epoch": 11.644114411441144, "percentage": 58.22, "elapsed_time": "4:10:20", "remaining_time": "2:59:38", "throughput": 1487.21, "total_tokens": 22338848} {"current_steps": 105850, "total_steps": 181800, "loss": 0.0151, "lr": 2.219352886396014e-05, "epoch": 11.644664466446645, "percentage": 58.22, "elapsed_time": "4:10:21", "remaining_time": "2:59:38", "throughput": 1487.21, "total_tokens": 22339872} {"current_steps": 105855, "total_steps": 181800, "loss": 0.0684, "lr": 2.2191143980000727e-05, "epoch": 11.645214521452145, "percentage": 58.23, "elapsed_time": "4:10:21", "remaining_time": "2:59:37", "throughput": 1487.22, "total_tokens": 22341056} {"current_steps": 105860, "total_steps": 181800, "loss": 0.0805, "lr": 2.218875912192919e-05, "epoch": 11.645764576457646, "percentage": 58.23, "elapsed_time": "4:10:22", "remaining_time": "2:59:36", "throughput": 1487.22, "total_tokens": 22342080} {"current_steps": 105865, "total_steps": 181800, "loss": 0.1051, "lr": 2.2186374289767522e-05, "epoch": 11.646314631463147, "percentage": 58.23, "elapsed_time": "4:10:23", "remaining_time": "2:59:35", "throughput": 1487.22, "total_tokens": 22343104} {"current_steps": 105870, "total_steps": 181800, "loss": 0.047, "lr": 2.2183989483537682e-05, "epoch": 11.646864686468646, "percentage": 58.23, "elapsed_time": "4:10:24", "remaining_time": "2:59:35", "throughput": 1487.23, "total_tokens": 22344192} {"current_steps": 105875, "total_steps": 181800, "loss": 0.1015, "lr": 2.2181604703261663e-05, "epoch": 11.647414741474147, "percentage": 58.24, "elapsed_time": "4:10:24", "remaining_time": "2:59:34", "throughput": 1487.23, "total_tokens": 22345248} {"current_steps": 105880, "total_steps": 181800, "loss": 0.0026, "lr": 2.2179219948961448e-05, "epoch": 11.647964796479648, "percentage": 58.24, "elapsed_time": "4:10:25", "remaining_time": "2:59:33", "throughput": 1487.23, "total_tokens": 22346336} {"current_steps": 105885, "total_steps": 181800, "loss": 0.1406, "lr": 2.2176835220658998e-05, "epoch": 11.648514851485148, "percentage": 58.24, "elapsed_time": "4:10:26", "remaining_time": "2:59:33", "throughput": 1487.23, "total_tokens": 22347360} {"current_steps": 105890, "total_steps": 181800, "loss": 0.0079, "lr": 2.2174450518376306e-05, "epoch": 11.649064906490649, "percentage": 58.25, "elapsed_time": "4:10:26", "remaining_time": "2:59:32", "throughput": 1487.24, "total_tokens": 22348480} {"current_steps": 105895, "total_steps": 181800, "loss": 0.0815, "lr": 2.2172065842135343e-05, "epoch": 11.64961496149615, "percentage": 58.25, "elapsed_time": "4:10:27", "remaining_time": "2:59:31", "throughput": 1487.24, "total_tokens": 22349472} {"current_steps": 105900, "total_steps": 181800, "loss": 0.1747, "lr": 2.2169681191958107e-05, "epoch": 11.65016501650165, "percentage": 58.25, "elapsed_time": "4:10:28", "remaining_time": "2:59:30", "throughput": 1487.24, "total_tokens": 22350560} {"current_steps": 105905, "total_steps": 181800, "loss": 0.0054, "lr": 2.2167296567866554e-05, "epoch": 11.65071507150715, "percentage": 58.25, "elapsed_time": "4:10:28", "remaining_time": "2:59:30", "throughput": 1487.25, "total_tokens": 22351648} {"current_steps": 105910, "total_steps": 181800, "loss": 0.0397, "lr": 2.216491196988266e-05, "epoch": 11.651265126512651, "percentage": 58.26, "elapsed_time": "4:10:29", "remaining_time": "2:59:29", "throughput": 1487.25, "total_tokens": 22352704} {"current_steps": 105915, "total_steps": 181800, "loss": 0.011, "lr": 2.216252739802842e-05, "epoch": 11.651815181518153, "percentage": 58.26, "elapsed_time": "4:10:30", "remaining_time": "2:59:28", "throughput": 1487.25, "total_tokens": 22353792} {"current_steps": 105920, "total_steps": 181800, "loss": 0.0808, "lr": 2.21601428523258e-05, "epoch": 11.652365236523652, "percentage": 58.26, "elapsed_time": "4:10:30", "remaining_time": "2:59:28", "throughput": 1487.26, "total_tokens": 22354880} {"current_steps": 105925, "total_steps": 181800, "loss": 0.0213, "lr": 2.215775833279679e-05, "epoch": 11.652915291529153, "percentage": 58.26, "elapsed_time": "4:10:31", "remaining_time": "2:59:27", "throughput": 1487.26, "total_tokens": 22356000} {"current_steps": 105930, "total_steps": 181800, "loss": 0.0037, "lr": 2.2155373839463353e-05, "epoch": 11.653465346534654, "percentage": 58.27, "elapsed_time": "4:10:32", "remaining_time": "2:59:26", "throughput": 1487.26, "total_tokens": 22356992} {"current_steps": 105935, "total_steps": 181800, "loss": 0.0469, "lr": 2.2152989372347463e-05, "epoch": 11.654015401540153, "percentage": 58.27, "elapsed_time": "4:10:33", "remaining_time": "2:59:25", "throughput": 1487.26, "total_tokens": 22358048} {"current_steps": 105940, "total_steps": 181800, "loss": 0.0514, "lr": 2.2150604931471116e-05, "epoch": 11.654565456545654, "percentage": 58.27, "elapsed_time": "4:10:33", "remaining_time": "2:59:25", "throughput": 1487.26, "total_tokens": 22359072} {"current_steps": 105945, "total_steps": 181800, "loss": 0.0055, "lr": 2.2148220516856266e-05, "epoch": 11.655115511551156, "percentage": 58.28, "elapsed_time": "4:10:34", "remaining_time": "2:59:24", "throughput": 1487.27, "total_tokens": 22360128} {"current_steps": 105950, "total_steps": 181800, "loss": 0.0198, "lr": 2.2145836128524902e-05, "epoch": 11.655665566556655, "percentage": 58.28, "elapsed_time": "4:10:35", "remaining_time": "2:59:23", "throughput": 1487.26, "total_tokens": 22361120} {"current_steps": 105955, "total_steps": 181800, "loss": 0.0093, "lr": 2.2143451766499004e-05, "epoch": 11.656215621562156, "percentage": 58.28, "elapsed_time": "4:10:35", "remaining_time": "2:59:22", "throughput": 1487.26, "total_tokens": 22362144} {"current_steps": 105960, "total_steps": 181800, "loss": 0.039, "lr": 2.2141067430800524e-05, "epoch": 11.656765676567657, "percentage": 58.28, "elapsed_time": "4:10:36", "remaining_time": "2:59:22", "throughput": 1487.26, "total_tokens": 22363168} {"current_steps": 105965, "total_steps": 181800, "loss": 0.0188, "lr": 2.213868312145147e-05, "epoch": 11.657315731573158, "percentage": 58.29, "elapsed_time": "4:10:37", "remaining_time": "2:59:21", "throughput": 1487.26, "total_tokens": 22364192} {"current_steps": 105970, "total_steps": 181800, "loss": 0.0592, "lr": 2.213629883847379e-05, "epoch": 11.657865786578657, "percentage": 58.29, "elapsed_time": "4:10:37", "remaining_time": "2:59:20", "throughput": 1487.27, "total_tokens": 22365248} {"current_steps": 105975, "total_steps": 181800, "loss": 0.0037, "lr": 2.2133914581889476e-05, "epoch": 11.658415841584159, "percentage": 58.29, "elapsed_time": "4:10:38", "remaining_time": "2:59:20", "throughput": 1487.27, "total_tokens": 22366272} {"current_steps": 105980, "total_steps": 181800, "loss": 0.0103, "lr": 2.2131530351720496e-05, "epoch": 11.65896589658966, "percentage": 58.29, "elapsed_time": "4:10:39", "remaining_time": "2:59:19", "throughput": 1487.27, "total_tokens": 22367296} {"current_steps": 105985, "total_steps": 181800, "loss": 0.0122, "lr": 2.212914614798882e-05, "epoch": 11.659515951595159, "percentage": 58.3, "elapsed_time": "4:10:39", "remaining_time": "2:59:18", "throughput": 1487.27, "total_tokens": 22368352} {"current_steps": 105990, "total_steps": 181800, "loss": 0.0043, "lr": 2.2126761970716427e-05, "epoch": 11.66006600660066, "percentage": 58.3, "elapsed_time": "4:10:40", "remaining_time": "2:59:17", "throughput": 1487.27, "total_tokens": 22369440} {"current_steps": 105995, "total_steps": 181800, "loss": 0.0052, "lr": 2.21243778199253e-05, "epoch": 11.660616061606161, "percentage": 58.3, "elapsed_time": "4:10:41", "remaining_time": "2:59:17", "throughput": 1487.28, "total_tokens": 22370560} {"current_steps": 106000, "total_steps": 181800, "loss": 0.0555, "lr": 2.212199369563739e-05, "epoch": 11.66116611661166, "percentage": 58.31, "elapsed_time": "4:10:41", "remaining_time": "2:59:16", "throughput": 1487.28, "total_tokens": 22371552} {"current_steps": 106005, "total_steps": 181800, "loss": 0.0332, "lr": 2.2119609597874688e-05, "epoch": 11.661716171617162, "percentage": 58.31, "elapsed_time": "4:10:42", "remaining_time": "2:59:15", "throughput": 1487.27, "total_tokens": 22372544} {"current_steps": 106010, "total_steps": 181800, "loss": 0.0297, "lr": 2.2117225526659158e-05, "epoch": 11.662266226622663, "percentage": 58.31, "elapsed_time": "4:10:43", "remaining_time": "2:59:14", "throughput": 1487.27, "total_tokens": 22373568} {"current_steps": 106015, "total_steps": 181800, "loss": 0.013, "lr": 2.2114841482012785e-05, "epoch": 11.662816281628164, "percentage": 58.31, "elapsed_time": "4:10:44", "remaining_time": "2:59:14", "throughput": 1487.27, "total_tokens": 22374560} {"current_steps": 106020, "total_steps": 181800, "loss": 0.0054, "lr": 2.211245746395753e-05, "epoch": 11.663366336633663, "percentage": 58.32, "elapsed_time": "4:10:44", "remaining_time": "2:59:13", "throughput": 1487.27, "total_tokens": 22375648} {"current_steps": 106025, "total_steps": 181800, "loss": 0.0617, "lr": 2.2110073472515364e-05, "epoch": 11.663916391639164, "percentage": 58.32, "elapsed_time": "4:10:45", "remaining_time": "2:59:12", "throughput": 1487.28, "total_tokens": 22376704} {"current_steps": 106030, "total_steps": 181800, "loss": 0.0119, "lr": 2.210768950770827e-05, "epoch": 11.664466446644665, "percentage": 58.32, "elapsed_time": "4:10:46", "remaining_time": "2:59:12", "throughput": 1487.28, "total_tokens": 22377760} {"current_steps": 106035, "total_steps": 181800, "loss": 0.0825, "lr": 2.210530556955821e-05, "epoch": 11.665016501650165, "percentage": 58.33, "elapsed_time": "4:10:46", "remaining_time": "2:59:11", "throughput": 1487.28, "total_tokens": 22378816} {"current_steps": 106040, "total_steps": 181800, "loss": 0.1389, "lr": 2.2102921658087167e-05, "epoch": 11.665566556655666, "percentage": 58.33, "elapsed_time": "4:10:47", "remaining_time": "2:59:10", "throughput": 1487.28, "total_tokens": 22379872} {"current_steps": 106045, "total_steps": 181800, "loss": 0.0101, "lr": 2.2100537773317097e-05, "epoch": 11.666116611661167, "percentage": 58.33, "elapsed_time": "4:10:48", "remaining_time": "2:59:09", "throughput": 1487.29, "total_tokens": 22380992} {"current_steps": 106050, "total_steps": 181800, "loss": 0.0812, "lr": 2.209815391526998e-05, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "4:10:48", "remaining_time": "2:59:09", "throughput": 1487.29, "total_tokens": 22382112} {"current_steps": 106055, "total_steps": 181800, "loss": 0.0032, "lr": 2.2095770083967793e-05, "epoch": 11.667216721672167, "percentage": 58.34, "elapsed_time": "4:10:49", "remaining_time": "2:59:08", "throughput": 1487.3, "total_tokens": 22383200} {"current_steps": 106060, "total_steps": 181800, "loss": 0.0427, "lr": 2.209338627943249e-05, "epoch": 11.667766776677668, "percentage": 58.34, "elapsed_time": "4:10:50", "remaining_time": "2:59:07", "throughput": 1487.3, "total_tokens": 22384224} {"current_steps": 106065, "total_steps": 181800, "loss": 0.0577, "lr": 2.2091002501686056e-05, "epoch": 11.668316831683168, "percentage": 58.34, "elapsed_time": "4:10:50", "remaining_time": "2:59:07", "throughput": 1487.3, "total_tokens": 22385216} {"current_steps": 106070, "total_steps": 181800, "loss": 0.0045, "lr": 2.208861875075046e-05, "epoch": 11.668866886688669, "percentage": 58.34, "elapsed_time": "4:10:51", "remaining_time": "2:59:06", "throughput": 1487.3, "total_tokens": 22386272} {"current_steps": 106075, "total_steps": 181800, "loss": 0.0536, "lr": 2.208623502664766e-05, "epoch": 11.66941694169417, "percentage": 58.35, "elapsed_time": "4:10:52", "remaining_time": "2:59:05", "throughput": 1487.3, "total_tokens": 22387328} {"current_steps": 106080, "total_steps": 181800, "loss": 0.0304, "lr": 2.2083851329399637e-05, "epoch": 11.66996699669967, "percentage": 58.35, "elapsed_time": "4:10:53", "remaining_time": "2:59:04", "throughput": 1487.3, "total_tokens": 22388352} {"current_steps": 106085, "total_steps": 181800, "loss": 0.0029, "lr": 2.2081467659028355e-05, "epoch": 11.67051705170517, "percentage": 58.35, "elapsed_time": "4:10:53", "remaining_time": "2:59:04", "throughput": 1487.3, "total_tokens": 22389408} {"current_steps": 106090, "total_steps": 181800, "loss": 0.0641, "lr": 2.2079084015555787e-05, "epoch": 11.671067106710671, "percentage": 58.36, "elapsed_time": "4:10:54", "remaining_time": "2:59:03", "throughput": 1487.31, "total_tokens": 22390496} {"current_steps": 106095, "total_steps": 181800, "loss": 0.0053, "lr": 2.2076700399003904e-05, "epoch": 11.671617161716172, "percentage": 58.36, "elapsed_time": "4:10:55", "remaining_time": "2:59:02", "throughput": 1487.31, "total_tokens": 22391552} {"current_steps": 106100, "total_steps": 181800, "loss": 0.0139, "lr": 2.2074316809394662e-05, "epoch": 11.672167216721672, "percentage": 58.36, "elapsed_time": "4:10:55", "remaining_time": "2:59:01", "throughput": 1487.32, "total_tokens": 22392704} {"current_steps": 106105, "total_steps": 181800, "loss": 0.0042, "lr": 2.2071933246750047e-05, "epoch": 11.672717271727173, "percentage": 58.36, "elapsed_time": "4:10:56", "remaining_time": "2:59:01", "throughput": 1487.32, "total_tokens": 22393760} {"current_steps": 106110, "total_steps": 181800, "loss": 0.0083, "lr": 2.206954971109201e-05, "epoch": 11.673267326732674, "percentage": 58.37, "elapsed_time": "4:10:57", "remaining_time": "2:59:00", "throughput": 1487.32, "total_tokens": 22394816} {"current_steps": 106115, "total_steps": 181800, "loss": 0.1024, "lr": 2.2067166202442536e-05, "epoch": 11.673817381738173, "percentage": 58.37, "elapsed_time": "4:10:57", "remaining_time": "2:58:59", "throughput": 1487.32, "total_tokens": 22395872} {"current_steps": 106120, "total_steps": 181800, "loss": 0.0329, "lr": 2.2064782720823578e-05, "epoch": 11.674367436743674, "percentage": 58.37, "elapsed_time": "4:10:58", "remaining_time": "2:58:59", "throughput": 1487.32, "total_tokens": 22396896} {"current_steps": 106125, "total_steps": 181800, "loss": 0.0555, "lr": 2.2062399266257107e-05, "epoch": 11.674917491749175, "percentage": 58.37, "elapsed_time": "4:10:59", "remaining_time": "2:58:58", "throughput": 1487.32, "total_tokens": 22397920} {"current_steps": 106130, "total_steps": 181800, "loss": 0.0125, "lr": 2.2060015838765103e-05, "epoch": 11.675467546754675, "percentage": 58.38, "elapsed_time": "4:10:59", "remaining_time": "2:58:57", "throughput": 1487.32, "total_tokens": 22398976} {"current_steps": 106135, "total_steps": 181800, "loss": 0.0373, "lr": 2.205763243836951e-05, "epoch": 11.676017601760176, "percentage": 58.38, "elapsed_time": "4:11:00", "remaining_time": "2:58:56", "throughput": 1487.32, "total_tokens": 22399968} {"current_steps": 106140, "total_steps": 181800, "loss": 0.0322, "lr": 2.2055249065092313e-05, "epoch": 11.676567656765677, "percentage": 58.38, "elapsed_time": "4:11:01", "remaining_time": "2:58:56", "throughput": 1487.32, "total_tokens": 22400992} {"current_steps": 106145, "total_steps": 181800, "loss": 0.0029, "lr": 2.205286571895547e-05, "epoch": 11.677117711771178, "percentage": 58.39, "elapsed_time": "4:11:02", "remaining_time": "2:58:55", "throughput": 1487.32, "total_tokens": 22401952} {"current_steps": 106150, "total_steps": 181800, "loss": 0.0072, "lr": 2.2050482399980944e-05, "epoch": 11.677667766776677, "percentage": 58.39, "elapsed_time": "4:11:02", "remaining_time": "2:58:54", "throughput": 1487.32, "total_tokens": 22403040} {"current_steps": 106155, "total_steps": 181800, "loss": 0.0115, "lr": 2.2048099108190723e-05, "epoch": 11.678217821782178, "percentage": 58.39, "elapsed_time": "4:11:03", "remaining_time": "2:58:54", "throughput": 1487.32, "total_tokens": 22404032} {"current_steps": 106160, "total_steps": 181800, "loss": 0.0631, "lr": 2.204571584360674e-05, "epoch": 11.67876787678768, "percentage": 58.39, "elapsed_time": "4:11:04", "remaining_time": "2:58:53", "throughput": 1487.32, "total_tokens": 22405120} {"current_steps": 106165, "total_steps": 181800, "loss": 0.015, "lr": 2.204333260625098e-05, "epoch": 11.679317931793179, "percentage": 58.4, "elapsed_time": "4:11:04", "remaining_time": "2:58:52", "throughput": 1487.32, "total_tokens": 22406112} {"current_steps": 106170, "total_steps": 181800, "loss": 0.005, "lr": 2.2040949396145415e-05, "epoch": 11.67986798679868, "percentage": 58.4, "elapsed_time": "4:11:05", "remaining_time": "2:58:51", "throughput": 1487.33, "total_tokens": 22407232} {"current_steps": 106175, "total_steps": 181800, "loss": 0.0024, "lr": 2.203856621331199e-05, "epoch": 11.680418041804181, "percentage": 58.4, "elapsed_time": "4:11:06", "remaining_time": "2:58:51", "throughput": 1487.33, "total_tokens": 22408352} {"current_steps": 106180, "total_steps": 181800, "loss": 0.0263, "lr": 2.203618305777268e-05, "epoch": 11.68096809680968, "percentage": 58.4, "elapsed_time": "4:11:06", "remaining_time": "2:58:50", "throughput": 1487.34, "total_tokens": 22409504} {"current_steps": 106185, "total_steps": 181800, "loss": 0.1022, "lr": 2.2033799929549457e-05, "epoch": 11.681518151815181, "percentage": 58.41, "elapsed_time": "4:11:07", "remaining_time": "2:58:49", "throughput": 1487.34, "total_tokens": 22410496} {"current_steps": 106190, "total_steps": 181800, "loss": 0.067, "lr": 2.2031416828664263e-05, "epoch": 11.682068206820682, "percentage": 58.41, "elapsed_time": "4:11:08", "remaining_time": "2:58:48", "throughput": 1487.34, "total_tokens": 22411552} {"current_steps": 106195, "total_steps": 181800, "loss": 0.0038, "lr": 2.2029033755139084e-05, "epoch": 11.682618261826182, "percentage": 58.41, "elapsed_time": "4:11:08", "remaining_time": "2:58:48", "throughput": 1487.34, "total_tokens": 22412544} {"current_steps": 106200, "total_steps": 181800, "loss": 0.0259, "lr": 2.2026650708995868e-05, "epoch": 11.683168316831683, "percentage": 58.42, "elapsed_time": "4:11:09", "remaining_time": "2:58:47", "throughput": 1487.34, "total_tokens": 22413632} {"current_steps": 106205, "total_steps": 181800, "loss": 0.0023, "lr": 2.2024267690256593e-05, "epoch": 11.683718371837184, "percentage": 58.42, "elapsed_time": "4:11:10", "remaining_time": "2:58:46", "throughput": 1487.34, "total_tokens": 22414688} {"current_steps": 106210, "total_steps": 181800, "loss": 0.0074, "lr": 2.202188469894322e-05, "epoch": 11.684268426842685, "percentage": 58.42, "elapsed_time": "4:11:10", "remaining_time": "2:58:46", "throughput": 1487.34, "total_tokens": 22415680} {"current_steps": 106215, "total_steps": 181800, "loss": 0.0755, "lr": 2.201950173507769e-05, "epoch": 11.684818481848184, "percentage": 58.42, "elapsed_time": "4:11:11", "remaining_time": "2:58:45", "throughput": 1487.35, "total_tokens": 22416832} {"current_steps": 106220, "total_steps": 181800, "loss": 0.0072, "lr": 2.2017118798681995e-05, "epoch": 11.685368536853685, "percentage": 58.43, "elapsed_time": "4:11:12", "remaining_time": "2:58:44", "throughput": 1487.35, "total_tokens": 22417888} {"current_steps": 106225, "total_steps": 181800, "loss": 0.0124, "lr": 2.2014735889778076e-05, "epoch": 11.685918591859187, "percentage": 58.43, "elapsed_time": "4:11:13", "remaining_time": "2:58:43", "throughput": 1487.35, "total_tokens": 22418912} {"current_steps": 106230, "total_steps": 181800, "loss": 0.206, "lr": 2.2012353008387914e-05, "epoch": 11.686468646864686, "percentage": 58.43, "elapsed_time": "4:11:13", "remaining_time": "2:58:43", "throughput": 1487.36, "total_tokens": 22420000} {"current_steps": 106235, "total_steps": 181800, "loss": 0.0703, "lr": 2.200997015453346e-05, "epoch": 11.687018701870187, "percentage": 58.44, "elapsed_time": "4:11:14", "remaining_time": "2:58:42", "throughput": 1487.36, "total_tokens": 22420992} {"current_steps": 106240, "total_steps": 181800, "loss": 0.0218, "lr": 2.2007587328236665e-05, "epoch": 11.687568756875688, "percentage": 58.44, "elapsed_time": "4:11:15", "remaining_time": "2:58:41", "throughput": 1487.36, "total_tokens": 22422016} {"current_steps": 106245, "total_steps": 181800, "loss": 0.0043, "lr": 2.2005204529519515e-05, "epoch": 11.688118811881187, "percentage": 58.44, "elapsed_time": "4:11:15", "remaining_time": "2:58:40", "throughput": 1487.36, "total_tokens": 22423168} {"current_steps": 106250, "total_steps": 181800, "loss": 0.0063, "lr": 2.2002821758403946e-05, "epoch": 11.688668866886688, "percentage": 58.44, "elapsed_time": "4:11:16", "remaining_time": "2:58:40", "throughput": 1487.37, "total_tokens": 22424224} {"current_steps": 106255, "total_steps": 181800, "loss": 0.0695, "lr": 2.2000439014911937e-05, "epoch": 11.68921892189219, "percentage": 58.45, "elapsed_time": "4:11:17", "remaining_time": "2:58:39", "throughput": 1487.37, "total_tokens": 22425248} {"current_steps": 106260, "total_steps": 181800, "loss": 0.0234, "lr": 2.199805629906545e-05, "epoch": 11.689768976897689, "percentage": 58.45, "elapsed_time": "4:11:17", "remaining_time": "2:58:38", "throughput": 1487.37, "total_tokens": 22426368} {"current_steps": 106265, "total_steps": 181800, "loss": 0.0053, "lr": 2.199567361088642e-05, "epoch": 11.69031903190319, "percentage": 58.45, "elapsed_time": "4:11:18", "remaining_time": "2:58:38", "throughput": 1487.37, "total_tokens": 22427424} {"current_steps": 106270, "total_steps": 181800, "loss": 0.0047, "lr": 2.199329095039684e-05, "epoch": 11.690869086908691, "percentage": 58.45, "elapsed_time": "4:11:19", "remaining_time": "2:58:37", "throughput": 1487.38, "total_tokens": 22428544} {"current_steps": 106275, "total_steps": 181800, "loss": 0.0482, "lr": 2.199090831761864e-05, "epoch": 11.691419141914192, "percentage": 58.46, "elapsed_time": "4:11:19", "remaining_time": "2:58:36", "throughput": 1487.38, "total_tokens": 22429600} {"current_steps": 106280, "total_steps": 181800, "loss": 0.0053, "lr": 2.198852571257381e-05, "epoch": 11.691969196919691, "percentage": 58.46, "elapsed_time": "4:11:20", "remaining_time": "2:58:35", "throughput": 1487.39, "total_tokens": 22430688} {"current_steps": 106285, "total_steps": 181800, "loss": 0.0511, "lr": 2.1986143135284288e-05, "epoch": 11.692519251925193, "percentage": 58.46, "elapsed_time": "4:11:21", "remaining_time": "2:58:35", "throughput": 1487.38, "total_tokens": 22431680} {"current_steps": 106290, "total_steps": 181800, "loss": 0.0106, "lr": 2.198376058577203e-05, "epoch": 11.693069306930694, "percentage": 58.47, "elapsed_time": "4:11:21", "remaining_time": "2:58:34", "throughput": 1487.39, "total_tokens": 22432800} {"current_steps": 106295, "total_steps": 181800, "loss": 0.0513, "lr": 2.1981378064059014e-05, "epoch": 11.693619361936193, "percentage": 58.47, "elapsed_time": "4:11:22", "remaining_time": "2:58:33", "throughput": 1487.4, "total_tokens": 22433920} {"current_steps": 106300, "total_steps": 181800, "loss": 0.0724, "lr": 2.1978995570167178e-05, "epoch": 11.694169416941694, "percentage": 58.47, "elapsed_time": "4:11:23", "remaining_time": "2:58:33", "throughput": 1487.4, "total_tokens": 22434976} {"current_steps": 106305, "total_steps": 181800, "loss": 0.1169, "lr": 2.1976613104118504e-05, "epoch": 11.694719471947195, "percentage": 58.47, "elapsed_time": "4:11:24", "remaining_time": "2:58:32", "throughput": 1487.4, "total_tokens": 22436032} {"current_steps": 106310, "total_steps": 181800, "loss": 0.0021, "lr": 2.1974230665934927e-05, "epoch": 11.695269526952695, "percentage": 58.48, "elapsed_time": "4:11:24", "remaining_time": "2:58:31", "throughput": 1487.4, "total_tokens": 22437088} {"current_steps": 106315, "total_steps": 181800, "loss": 0.066, "lr": 2.197184825563841e-05, "epoch": 11.695819581958196, "percentage": 58.48, "elapsed_time": "4:11:25", "remaining_time": "2:58:30", "throughput": 1487.4, "total_tokens": 22438080} {"current_steps": 106320, "total_steps": 181800, "loss": 0.0509, "lr": 2.196946587325093e-05, "epoch": 11.696369636963697, "percentage": 58.48, "elapsed_time": "4:11:26", "remaining_time": "2:58:30", "throughput": 1487.41, "total_tokens": 22439200} {"current_steps": 106325, "total_steps": 181800, "loss": 0.052, "lr": 2.1967083518794407e-05, "epoch": 11.696919691969196, "percentage": 58.48, "elapsed_time": "4:11:26", "remaining_time": "2:58:29", "throughput": 1487.41, "total_tokens": 22440256} {"current_steps": 106330, "total_steps": 181800, "loss": 0.113, "lr": 2.1964701192290837e-05, "epoch": 11.697469746974697, "percentage": 58.49, "elapsed_time": "4:11:27", "remaining_time": "2:58:28", "throughput": 1487.41, "total_tokens": 22441312} {"current_steps": 106335, "total_steps": 181800, "loss": 0.0115, "lr": 2.1962318893762153e-05, "epoch": 11.698019801980198, "percentage": 58.49, "elapsed_time": "4:11:28", "remaining_time": "2:58:27", "throughput": 1487.41, "total_tokens": 22442368} {"current_steps": 106340, "total_steps": 181800, "loss": 0.0278, "lr": 2.1959936623230317e-05, "epoch": 11.6985698569857, "percentage": 58.49, "elapsed_time": "4:11:28", "remaining_time": "2:58:27", "throughput": 1487.41, "total_tokens": 22443360} {"current_steps": 106345, "total_steps": 181800, "loss": 0.0363, "lr": 2.1957554380717297e-05, "epoch": 11.699119911991199, "percentage": 58.5, "elapsed_time": "4:11:29", "remaining_time": "2:58:26", "throughput": 1487.41, "total_tokens": 22444384} {"current_steps": 106350, "total_steps": 181800, "loss": 0.0214, "lr": 2.1955172166245025e-05, "epoch": 11.6996699669967, "percentage": 58.5, "elapsed_time": "4:11:30", "remaining_time": "2:58:25", "throughput": 1487.41, "total_tokens": 22445408} {"current_steps": 106355, "total_steps": 181800, "loss": 0.0124, "lr": 2.1952789979835476e-05, "epoch": 11.7002200220022, "percentage": 58.5, "elapsed_time": "4:11:30", "remaining_time": "2:58:25", "throughput": 1487.41, "total_tokens": 22446432} {"current_steps": 106360, "total_steps": 181800, "loss": 0.0855, "lr": 2.1950407821510606e-05, "epoch": 11.7007700770077, "percentage": 58.5, "elapsed_time": "4:11:31", "remaining_time": "2:58:24", "throughput": 1487.42, "total_tokens": 22447552} {"current_steps": 106365, "total_steps": 181800, "loss": 0.0375, "lr": 2.1948025691292352e-05, "epoch": 11.701320132013201, "percentage": 58.51, "elapsed_time": "4:11:32", "remaining_time": "2:58:23", "throughput": 1487.42, "total_tokens": 22448544} {"current_steps": 106370, "total_steps": 181800, "loss": 0.0134, "lr": 2.1945643589202684e-05, "epoch": 11.701870187018702, "percentage": 58.51, "elapsed_time": "4:11:32", "remaining_time": "2:58:22", "throughput": 1487.42, "total_tokens": 22449600} {"current_steps": 106375, "total_steps": 181800, "loss": 0.0058, "lr": 2.194326151526355e-05, "epoch": 11.702420242024202, "percentage": 58.51, "elapsed_time": "4:11:33", "remaining_time": "2:58:22", "throughput": 1487.42, "total_tokens": 22450720} {"current_steps": 106380, "total_steps": 181800, "loss": 0.0044, "lr": 2.194087946949692e-05, "epoch": 11.702970297029703, "percentage": 58.51, "elapsed_time": "4:11:34", "remaining_time": "2:58:21", "throughput": 1487.43, "total_tokens": 22451808} {"current_steps": 106385, "total_steps": 181800, "loss": 0.0062, "lr": 2.1938497451924727e-05, "epoch": 11.703520352035204, "percentage": 58.52, "elapsed_time": "4:11:35", "remaining_time": "2:58:20", "throughput": 1487.44, "total_tokens": 22452928} {"current_steps": 106390, "total_steps": 181800, "loss": 0.0052, "lr": 2.193611546256893e-05, "epoch": 11.704070407040705, "percentage": 58.52, "elapsed_time": "4:11:35", "remaining_time": "2:58:19", "throughput": 1487.44, "total_tokens": 22454016} {"current_steps": 106395, "total_steps": 181800, "loss": 0.0026, "lr": 2.1933733501451494e-05, "epoch": 11.704620462046204, "percentage": 58.52, "elapsed_time": "4:11:36", "remaining_time": "2:58:19", "throughput": 1487.44, "total_tokens": 22455008} {"current_steps": 106400, "total_steps": 181800, "loss": 0.0118, "lr": 2.193135156859437e-05, "epoch": 11.705170517051705, "percentage": 58.53, "elapsed_time": "4:11:37", "remaining_time": "2:58:18", "throughput": 1487.44, "total_tokens": 22456064} {"current_steps": 106405, "total_steps": 181800, "loss": 0.0015, "lr": 2.1928969664019493e-05, "epoch": 11.705720572057206, "percentage": 58.53, "elapsed_time": "4:11:37", "remaining_time": "2:58:17", "throughput": 1487.44, "total_tokens": 22457088} {"current_steps": 106410, "total_steps": 181800, "loss": 0.0075, "lr": 2.192658778774884e-05, "epoch": 11.706270627062706, "percentage": 58.53, "elapsed_time": "4:11:38", "remaining_time": "2:58:17", "throughput": 1487.44, "total_tokens": 22458112} {"current_steps": 106415, "total_steps": 181800, "loss": 0.0604, "lr": 2.1924205939804342e-05, "epoch": 11.706820682068207, "percentage": 58.53, "elapsed_time": "4:11:39", "remaining_time": "2:58:16", "throughput": 1487.44, "total_tokens": 22459200} {"current_steps": 106420, "total_steps": 181800, "loss": 0.0073, "lr": 2.1921824120207975e-05, "epoch": 11.707370737073708, "percentage": 58.54, "elapsed_time": "4:11:39", "remaining_time": "2:58:15", "throughput": 1487.44, "total_tokens": 22460192} {"current_steps": 106425, "total_steps": 181800, "loss": 0.0633, "lr": 2.191944232898167e-05, "epoch": 11.707920792079207, "percentage": 58.54, "elapsed_time": "4:11:40", "remaining_time": "2:58:14", "throughput": 1487.45, "total_tokens": 22461280} {"current_steps": 106430, "total_steps": 181800, "loss": 0.0143, "lr": 2.1917060566147384e-05, "epoch": 11.708470847084708, "percentage": 58.54, "elapsed_time": "4:11:41", "remaining_time": "2:58:14", "throughput": 1487.45, "total_tokens": 22462304} {"current_steps": 106435, "total_steps": 181800, "loss": 0.1109, "lr": 2.191467883172708e-05, "epoch": 11.70902090209021, "percentage": 58.55, "elapsed_time": "4:11:41", "remaining_time": "2:58:13", "throughput": 1487.45, "total_tokens": 22463328} {"current_steps": 106440, "total_steps": 181800, "loss": 0.0015, "lr": 2.1912297125742694e-05, "epoch": 11.70957095709571, "percentage": 58.55, "elapsed_time": "4:11:42", "remaining_time": "2:58:12", "throughput": 1487.45, "total_tokens": 22464352} {"current_steps": 106445, "total_steps": 181800, "loss": 0.0173, "lr": 2.1909915448216184e-05, "epoch": 11.71012101210121, "percentage": 58.55, "elapsed_time": "4:11:43", "remaining_time": "2:58:12", "throughput": 1487.45, "total_tokens": 22465376} {"current_steps": 106450, "total_steps": 181800, "loss": 0.171, "lr": 2.19075337991695e-05, "epoch": 11.710671067106711, "percentage": 58.55, "elapsed_time": "4:11:44", "remaining_time": "2:58:11", "throughput": 1487.45, "total_tokens": 22466400} {"current_steps": 106455, "total_steps": 181800, "loss": 0.0064, "lr": 2.1905152178624595e-05, "epoch": 11.711221122112212, "percentage": 58.56, "elapsed_time": "4:11:44", "remaining_time": "2:58:10", "throughput": 1487.46, "total_tokens": 22467584} {"current_steps": 106460, "total_steps": 181800, "loss": 0.0738, "lr": 2.1902770586603422e-05, "epoch": 11.711771177117711, "percentage": 58.56, "elapsed_time": "4:11:45", "remaining_time": "2:58:09", "throughput": 1487.46, "total_tokens": 22468640} {"current_steps": 106465, "total_steps": 181800, "loss": 0.0105, "lr": 2.1900389023127917e-05, "epoch": 11.712321232123212, "percentage": 58.56, "elapsed_time": "4:11:46", "remaining_time": "2:58:09", "throughput": 1487.46, "total_tokens": 22469760} {"current_steps": 106470, "total_steps": 181800, "loss": 0.0139, "lr": 2.1898007488220045e-05, "epoch": 11.712871287128714, "percentage": 58.56, "elapsed_time": "4:11:46", "remaining_time": "2:58:08", "throughput": 1487.47, "total_tokens": 22470816} {"current_steps": 106475, "total_steps": 181800, "loss": 0.0097, "lr": 2.1895625981901754e-05, "epoch": 11.713421342134213, "percentage": 58.57, "elapsed_time": "4:11:47", "remaining_time": "2:58:07", "throughput": 1487.47, "total_tokens": 22471872} {"current_steps": 106480, "total_steps": 181800, "loss": 0.0045, "lr": 2.189324450419498e-05, "epoch": 11.713971397139714, "percentage": 58.57, "elapsed_time": "4:11:48", "remaining_time": "2:58:06", "throughput": 1487.47, "total_tokens": 22472928} {"current_steps": 106485, "total_steps": 181800, "loss": 0.041, "lr": 2.1890863055121685e-05, "epoch": 11.714521452145215, "percentage": 58.57, "elapsed_time": "4:11:48", "remaining_time": "2:58:06", "throughput": 1487.48, "total_tokens": 22474016} {"current_steps": 106490, "total_steps": 181800, "loss": 0.0051, "lr": 2.1888481634703807e-05, "epoch": 11.715071507150714, "percentage": 58.58, "elapsed_time": "4:11:49", "remaining_time": "2:58:05", "throughput": 1487.48, "total_tokens": 22475072} {"current_steps": 106495, "total_steps": 181800, "loss": 0.0064, "lr": 2.188610024296331e-05, "epoch": 11.715621562156215, "percentage": 58.58, "elapsed_time": "4:11:50", "remaining_time": "2:58:04", "throughput": 1487.47, "total_tokens": 22476064} {"current_steps": 106500, "total_steps": 181800, "loss": 0.0034, "lr": 2.188371887992213e-05, "epoch": 11.716171617161717, "percentage": 58.58, "elapsed_time": "4:11:50", "remaining_time": "2:58:04", "throughput": 1487.48, "total_tokens": 22477120} {"current_steps": 106505, "total_steps": 181800, "loss": 0.0033, "lr": 2.1881337545602213e-05, "epoch": 11.716721672167218, "percentage": 58.58, "elapsed_time": "4:11:51", "remaining_time": "2:58:03", "throughput": 1487.48, "total_tokens": 22478176} {"current_steps": 106510, "total_steps": 181800, "loss": 0.0462, "lr": 2.1878956240025513e-05, "epoch": 11.717271727172717, "percentage": 58.59, "elapsed_time": "4:11:52", "remaining_time": "2:58:02", "throughput": 1487.48, "total_tokens": 22479168} {"current_steps": 106515, "total_steps": 181800, "loss": 0.0096, "lr": 2.1876574963213974e-05, "epoch": 11.717821782178218, "percentage": 58.59, "elapsed_time": "4:11:52", "remaining_time": "2:58:01", "throughput": 1487.48, "total_tokens": 22480224} {"current_steps": 106520, "total_steps": 181800, "loss": 0.0119, "lr": 2.1874193715189557e-05, "epoch": 11.718371837183719, "percentage": 58.59, "elapsed_time": "4:11:53", "remaining_time": "2:58:01", "throughput": 1487.48, "total_tokens": 22481312} {"current_steps": 106525, "total_steps": 181800, "loss": 0.0027, "lr": 2.1871812495974185e-05, "epoch": 11.718921892189218, "percentage": 58.59, "elapsed_time": "4:11:54", "remaining_time": "2:58:00", "throughput": 1487.48, "total_tokens": 22482336} {"current_steps": 106530, "total_steps": 181800, "loss": 0.0043, "lr": 2.1869431305589815e-05, "epoch": 11.71947194719472, "percentage": 58.6, "elapsed_time": "4:11:55", "remaining_time": "2:57:59", "throughput": 1487.48, "total_tokens": 22483296} {"current_steps": 106535, "total_steps": 181800, "loss": 0.0845, "lr": 2.1867050144058403e-05, "epoch": 11.72002200220022, "percentage": 58.6, "elapsed_time": "4:11:55", "remaining_time": "2:57:58", "throughput": 1487.48, "total_tokens": 22484384} {"current_steps": 106540, "total_steps": 181800, "loss": 0.0048, "lr": 2.186466901140188e-05, "epoch": 11.72057205720572, "percentage": 58.6, "elapsed_time": "4:11:56", "remaining_time": "2:57:58", "throughput": 1487.48, "total_tokens": 22485376} {"current_steps": 106545, "total_steps": 181800, "loss": 0.0059, "lr": 2.18622879076422e-05, "epoch": 11.721122112211221, "percentage": 58.61, "elapsed_time": "4:11:57", "remaining_time": "2:57:57", "throughput": 1487.48, "total_tokens": 22486400} {"current_steps": 106550, "total_steps": 181800, "loss": 0.0117, "lr": 2.1859906832801313e-05, "epoch": 11.721672167216722, "percentage": 58.61, "elapsed_time": "4:11:57", "remaining_time": "2:57:56", "throughput": 1487.48, "total_tokens": 22487424} {"current_steps": 106555, "total_steps": 181800, "loss": 0.0664, "lr": 2.1857525786901147e-05, "epoch": 11.722222222222221, "percentage": 58.61, "elapsed_time": "4:11:58", "remaining_time": "2:57:56", "throughput": 1487.48, "total_tokens": 22488448} {"current_steps": 106560, "total_steps": 181800, "loss": 0.0039, "lr": 2.1855144769963666e-05, "epoch": 11.722772277227723, "percentage": 58.61, "elapsed_time": "4:11:59", "remaining_time": "2:57:55", "throughput": 1487.48, "total_tokens": 22489472} {"current_steps": 106565, "total_steps": 181800, "loss": 0.0272, "lr": 2.18527637820108e-05, "epoch": 11.723322332233224, "percentage": 58.62, "elapsed_time": "4:11:59", "remaining_time": "2:57:54", "throughput": 1487.48, "total_tokens": 22490528} {"current_steps": 106570, "total_steps": 181800, "loss": 0.0006, "lr": 2.18503828230645e-05, "epoch": 11.723872387238725, "percentage": 58.62, "elapsed_time": "4:12:00", "remaining_time": "2:57:53", "throughput": 1487.49, "total_tokens": 22491616} {"current_steps": 106575, "total_steps": 181800, "loss": 0.0011, "lr": 2.1848001893146723e-05, "epoch": 11.724422442244224, "percentage": 58.62, "elapsed_time": "4:12:01", "remaining_time": "2:57:53", "throughput": 1487.49, "total_tokens": 22492672} {"current_steps": 106580, "total_steps": 181800, "loss": 0.007, "lr": 2.1845620992279387e-05, "epoch": 11.724972497249725, "percentage": 58.62, "elapsed_time": "4:12:01", "remaining_time": "2:57:52", "throughput": 1487.49, "total_tokens": 22493760} {"current_steps": 106585, "total_steps": 181800, "loss": 0.0012, "lr": 2.184324012048445e-05, "epoch": 11.725522552255226, "percentage": 58.63, "elapsed_time": "4:12:02", "remaining_time": "2:57:51", "throughput": 1487.49, "total_tokens": 22494816} {"current_steps": 106590, "total_steps": 181800, "loss": 0.0566, "lr": 2.1840859277783866e-05, "epoch": 11.726072607260726, "percentage": 58.63, "elapsed_time": "4:12:03", "remaining_time": "2:57:51", "throughput": 1487.5, "total_tokens": 22495872} {"current_steps": 106595, "total_steps": 181800, "loss": 0.0895, "lr": 2.1838478464199548e-05, "epoch": 11.726622662266227, "percentage": 58.63, "elapsed_time": "4:12:04", "remaining_time": "2:57:50", "throughput": 1487.5, "total_tokens": 22496928} {"current_steps": 106600, "total_steps": 181800, "loss": 0.1029, "lr": 2.183609767975347e-05, "epoch": 11.727172717271728, "percentage": 58.64, "elapsed_time": "4:12:04", "remaining_time": "2:57:49", "throughput": 1487.5, "total_tokens": 22497984} {"current_steps": 106605, "total_steps": 181800, "loss": 0.0427, "lr": 2.1833716924467552e-05, "epoch": 11.727722772277227, "percentage": 58.64, "elapsed_time": "4:12:05", "remaining_time": "2:57:48", "throughput": 1487.5, "total_tokens": 22499008} {"current_steps": 106610, "total_steps": 181800, "loss": 0.0064, "lr": 2.1831336198363757e-05, "epoch": 11.728272827282728, "percentage": 58.64, "elapsed_time": "4:12:06", "remaining_time": "2:57:48", "throughput": 1487.5, "total_tokens": 22500032} {"current_steps": 106615, "total_steps": 181800, "loss": 0.1047, "lr": 2.182895550146401e-05, "epoch": 11.72882288228823, "percentage": 58.64, "elapsed_time": "4:12:06", "remaining_time": "2:57:47", "throughput": 1487.5, "total_tokens": 22501024} {"current_steps": 106620, "total_steps": 181800, "loss": 0.0405, "lr": 2.1826574833790252e-05, "epoch": 11.729372937293729, "percentage": 58.65, "elapsed_time": "4:12:07", "remaining_time": "2:57:46", "throughput": 1487.5, "total_tokens": 22502048} {"current_steps": 106625, "total_steps": 181800, "loss": 0.1189, "lr": 2.1824194195364443e-05, "epoch": 11.72992299229923, "percentage": 58.65, "elapsed_time": "4:12:08", "remaining_time": "2:57:45", "throughput": 1487.5, "total_tokens": 22503136} {"current_steps": 106630, "total_steps": 181800, "loss": 0.016, "lr": 2.1821813586208498e-05, "epoch": 11.73047304730473, "percentage": 58.65, "elapsed_time": "4:12:08", "remaining_time": "2:57:45", "throughput": 1487.5, "total_tokens": 22504128} {"current_steps": 106635, "total_steps": 181800, "loss": 0.0427, "lr": 2.1819433006344385e-05, "epoch": 11.731023102310232, "percentage": 58.66, "elapsed_time": "4:12:09", "remaining_time": "2:57:44", "throughput": 1487.5, "total_tokens": 22505152} {"current_steps": 106640, "total_steps": 181800, "loss": 0.0513, "lr": 2.181705245579403e-05, "epoch": 11.731573157315731, "percentage": 58.66, "elapsed_time": "4:12:10", "remaining_time": "2:57:43", "throughput": 1487.5, "total_tokens": 22506240} {"current_steps": 106645, "total_steps": 181800, "loss": 0.0085, "lr": 2.1814671934579366e-05, "epoch": 11.732123212321232, "percentage": 58.66, "elapsed_time": "4:12:10", "remaining_time": "2:57:43", "throughput": 1487.5, "total_tokens": 22507296} {"current_steps": 106650, "total_steps": 181800, "loss": 0.0548, "lr": 2.1812291442722356e-05, "epoch": 11.732673267326733, "percentage": 58.66, "elapsed_time": "4:12:11", "remaining_time": "2:57:42", "throughput": 1487.51, "total_tokens": 22508352} {"current_steps": 106655, "total_steps": 181800, "loss": 0.0601, "lr": 2.1809910980244914e-05, "epoch": 11.733223322332233, "percentage": 58.67, "elapsed_time": "4:12:12", "remaining_time": "2:57:41", "throughput": 1487.51, "total_tokens": 22509408} {"current_steps": 106660, "total_steps": 181800, "loss": 0.0721, "lr": 2.1807530547168996e-05, "epoch": 11.733773377337734, "percentage": 58.67, "elapsed_time": "4:12:12", "remaining_time": "2:57:40", "throughput": 1487.51, "total_tokens": 22510400} {"current_steps": 106665, "total_steps": 181800, "loss": 0.1043, "lr": 2.1805150143516545e-05, "epoch": 11.734323432343235, "percentage": 58.67, "elapsed_time": "4:12:13", "remaining_time": "2:57:40", "throughput": 1487.5, "total_tokens": 22511392} {"current_steps": 106670, "total_steps": 181800, "loss": 0.1279, "lr": 2.180276976930948e-05, "epoch": 11.734873487348734, "percentage": 58.67, "elapsed_time": "4:12:14", "remaining_time": "2:57:39", "throughput": 1487.51, "total_tokens": 22512544} {"current_steps": 106675, "total_steps": 181800, "loss": 0.0746, "lr": 2.1800389424569758e-05, "epoch": 11.735423542354235, "percentage": 58.68, "elapsed_time": "4:12:15", "remaining_time": "2:57:38", "throughput": 1487.52, "total_tokens": 22513664} {"current_steps": 106680, "total_steps": 181800, "loss": 0.0171, "lr": 2.1798009109319307e-05, "epoch": 11.735973597359736, "percentage": 58.68, "elapsed_time": "4:12:15", "remaining_time": "2:57:38", "throughput": 1487.52, "total_tokens": 22514720} {"current_steps": 106685, "total_steps": 181800, "loss": 0.0632, "lr": 2.1795628823580077e-05, "epoch": 11.736523652365236, "percentage": 58.68, "elapsed_time": "4:12:16", "remaining_time": "2:57:37", "throughput": 1487.52, "total_tokens": 22515712} {"current_steps": 106690, "total_steps": 181800, "loss": 0.0066, "lr": 2.1793248567373996e-05, "epoch": 11.737073707370737, "percentage": 58.69, "elapsed_time": "4:12:17", "remaining_time": "2:57:36", "throughput": 1487.52, "total_tokens": 22516800} {"current_steps": 106695, "total_steps": 181800, "loss": 0.075, "lr": 2.1790868340723e-05, "epoch": 11.737623762376238, "percentage": 58.69, "elapsed_time": "4:12:17", "remaining_time": "2:57:35", "throughput": 1487.52, "total_tokens": 22517856} {"current_steps": 106700, "total_steps": 181800, "loss": 0.0142, "lr": 2.178848814364903e-05, "epoch": 11.738173817381739, "percentage": 58.69, "elapsed_time": "4:12:18", "remaining_time": "2:57:35", "throughput": 1487.52, "total_tokens": 22518848} {"current_steps": 106705, "total_steps": 181800, "loss": 0.0025, "lr": 2.1786107976174024e-05, "epoch": 11.738723872387238, "percentage": 58.69, "elapsed_time": "4:12:19", "remaining_time": "2:57:34", "throughput": 1487.53, "total_tokens": 22519968} {"current_steps": 106710, "total_steps": 181800, "loss": 0.1333, "lr": 2.1783727838319926e-05, "epoch": 11.73927392739274, "percentage": 58.7, "elapsed_time": "4:12:19", "remaining_time": "2:57:33", "throughput": 1487.53, "total_tokens": 22521024} {"current_steps": 106715, "total_steps": 181800, "loss": 0.0349, "lr": 2.178134773010866e-05, "epoch": 11.73982398239824, "percentage": 58.7, "elapsed_time": "4:12:20", "remaining_time": "2:57:32", "throughput": 1487.53, "total_tokens": 22522048} {"current_steps": 106720, "total_steps": 181800, "loss": 0.1508, "lr": 2.1778967651562167e-05, "epoch": 11.74037403740374, "percentage": 58.7, "elapsed_time": "4:12:21", "remaining_time": "2:57:32", "throughput": 1487.53, "total_tokens": 22523104} {"current_steps": 106725, "total_steps": 181800, "loss": 0.0359, "lr": 2.177658760270239e-05, "epoch": 11.74092409240924, "percentage": 58.7, "elapsed_time": "4:12:21", "remaining_time": "2:57:31", "throughput": 1487.52, "total_tokens": 22524064} {"current_steps": 106730, "total_steps": 181800, "loss": 0.0024, "lr": 2.1774207583551245e-05, "epoch": 11.741474147414742, "percentage": 58.71, "elapsed_time": "4:12:22", "remaining_time": "2:57:30", "throughput": 1487.52, "total_tokens": 22525088} {"current_steps": 106735, "total_steps": 181800, "loss": 0.002, "lr": 2.177182759413069e-05, "epoch": 11.742024202420241, "percentage": 58.71, "elapsed_time": "4:12:23", "remaining_time": "2:57:30", "throughput": 1487.52, "total_tokens": 22526112} {"current_steps": 106740, "total_steps": 181800, "loss": 0.0134, "lr": 2.1769447634462657e-05, "epoch": 11.742574257425742, "percentage": 58.71, "elapsed_time": "4:12:24", "remaining_time": "2:57:29", "throughput": 1487.53, "total_tokens": 22527168} {"current_steps": 106745, "total_steps": 181800, "loss": 0.0043, "lr": 2.1767067704569056e-05, "epoch": 11.743124312431243, "percentage": 58.72, "elapsed_time": "4:12:24", "remaining_time": "2:57:28", "throughput": 1487.52, "total_tokens": 22528128} {"current_steps": 106750, "total_steps": 181800, "loss": 0.019, "lr": 2.1764687804471862e-05, "epoch": 11.743674367436743, "percentage": 58.72, "elapsed_time": "4:12:25", "remaining_time": "2:57:27", "throughput": 1487.52, "total_tokens": 22529152} {"current_steps": 106755, "total_steps": 181800, "loss": 0.0409, "lr": 2.1762307934192972e-05, "epoch": 11.744224422442244, "percentage": 58.72, "elapsed_time": "4:12:26", "remaining_time": "2:57:27", "throughput": 1487.53, "total_tokens": 22530240} {"current_steps": 106760, "total_steps": 181800, "loss": 0.0825, "lr": 2.1759928093754345e-05, "epoch": 11.744774477447745, "percentage": 58.72, "elapsed_time": "4:12:26", "remaining_time": "2:57:26", "throughput": 1487.53, "total_tokens": 22531296} {"current_steps": 106765, "total_steps": 181800, "loss": 0.0291, "lr": 2.1757548283177908e-05, "epoch": 11.745324532453246, "percentage": 58.73, "elapsed_time": "4:12:27", "remaining_time": "2:57:25", "throughput": 1487.54, "total_tokens": 22532448} {"current_steps": 106770, "total_steps": 181800, "loss": 0.0749, "lr": 2.1755168502485583e-05, "epoch": 11.745874587458745, "percentage": 58.73, "elapsed_time": "4:12:28", "remaining_time": "2:57:25", "throughput": 1487.54, "total_tokens": 22533536} {"current_steps": 106775, "total_steps": 181800, "loss": 0.0051, "lr": 2.175278875169932e-05, "epoch": 11.746424642464246, "percentage": 58.73, "elapsed_time": "4:12:28", "remaining_time": "2:57:24", "throughput": 1487.55, "total_tokens": 22534656} {"current_steps": 106780, "total_steps": 181800, "loss": 0.08, "lr": 2.1750409030841048e-05, "epoch": 11.746974697469748, "percentage": 58.73, "elapsed_time": "4:12:29", "remaining_time": "2:57:23", "throughput": 1487.55, "total_tokens": 22535744} {"current_steps": 106785, "total_steps": 181800, "loss": 0.0303, "lr": 2.1748029339932687e-05, "epoch": 11.747524752475247, "percentage": 58.74, "elapsed_time": "4:12:30", "remaining_time": "2:57:22", "throughput": 1487.56, "total_tokens": 22536832} {"current_steps": 106790, "total_steps": 181800, "loss": 0.0059, "lr": 2.1745649678996184e-05, "epoch": 11.748074807480748, "percentage": 58.74, "elapsed_time": "4:12:30", "remaining_time": "2:57:22", "throughput": 1487.56, "total_tokens": 22537856} {"current_steps": 106795, "total_steps": 181800, "loss": 0.0155, "lr": 2.1743270048053463e-05, "epoch": 11.748624862486249, "percentage": 58.74, "elapsed_time": "4:12:31", "remaining_time": "2:57:21", "throughput": 1487.56, "total_tokens": 22538912} {"current_steps": 106800, "total_steps": 181800, "loss": 0.0423, "lr": 2.174089044712647e-05, "epoch": 11.749174917491748, "percentage": 58.75, "elapsed_time": "4:12:32", "remaining_time": "2:57:20", "throughput": 1487.56, "total_tokens": 22539968} {"current_steps": 106805, "total_steps": 181800, "loss": 0.0026, "lr": 2.1738510876237118e-05, "epoch": 11.74972497249725, "percentage": 58.75, "elapsed_time": "4:12:32", "remaining_time": "2:57:19", "throughput": 1487.56, "total_tokens": 22541024} {"current_steps": 106810, "total_steps": 181800, "loss": 0.0779, "lr": 2.1736131335407342e-05, "epoch": 11.75027502750275, "percentage": 58.75, "elapsed_time": "4:12:33", "remaining_time": "2:57:19", "throughput": 1487.56, "total_tokens": 22542048} {"current_steps": 106815, "total_steps": 181800, "loss": 0.0272, "lr": 2.173375182465908e-05, "epoch": 11.750825082508252, "percentage": 58.75, "elapsed_time": "4:12:34", "remaining_time": "2:57:18", "throughput": 1487.56, "total_tokens": 22543104} {"current_steps": 106820, "total_steps": 181800, "loss": 0.0453, "lr": 2.173137234401426e-05, "epoch": 11.751375137513751, "percentage": 58.76, "elapsed_time": "4:12:35", "remaining_time": "2:57:17", "throughput": 1487.57, "total_tokens": 22544192} {"current_steps": 106825, "total_steps": 181800, "loss": 0.0088, "lr": 2.172899289349482e-05, "epoch": 11.751925192519252, "percentage": 58.76, "elapsed_time": "4:12:35", "remaining_time": "2:57:17", "throughput": 1487.57, "total_tokens": 22545248} {"current_steps": 106830, "total_steps": 181800, "loss": 0.0595, "lr": 2.172661347312268e-05, "epoch": 11.752475247524753, "percentage": 58.76, "elapsed_time": "4:12:36", "remaining_time": "2:57:16", "throughput": 1487.57, "total_tokens": 22546272} {"current_steps": 106835, "total_steps": 181800, "loss": 0.0679, "lr": 2.1724234082919766e-05, "epoch": 11.753025302530252, "percentage": 58.77, "elapsed_time": "4:12:37", "remaining_time": "2:57:15", "throughput": 1487.58, "total_tokens": 22547424} {"current_steps": 106840, "total_steps": 181800, "loss": 0.0376, "lr": 2.1721854722908025e-05, "epoch": 11.753575357535754, "percentage": 58.77, "elapsed_time": "4:12:37", "remaining_time": "2:57:14", "throughput": 1487.58, "total_tokens": 22548512} {"current_steps": 106845, "total_steps": 181800, "loss": 0.0032, "lr": 2.1719475393109362e-05, "epoch": 11.754125412541255, "percentage": 58.77, "elapsed_time": "4:12:38", "remaining_time": "2:57:14", "throughput": 1487.59, "total_tokens": 22549632} {"current_steps": 106850, "total_steps": 181800, "loss": 0.0461, "lr": 2.171709609354573e-05, "epoch": 11.754675467546754, "percentage": 58.77, "elapsed_time": "4:12:39", "remaining_time": "2:57:13", "throughput": 1487.59, "total_tokens": 22550720} {"current_steps": 106855, "total_steps": 181800, "loss": 0.0288, "lr": 2.1714716824239055e-05, "epoch": 11.755225522552255, "percentage": 58.78, "elapsed_time": "4:12:39", "remaining_time": "2:57:12", "throughput": 1487.6, "total_tokens": 22551872} {"current_steps": 106860, "total_steps": 181800, "loss": 0.0052, "lr": 2.171233758521124e-05, "epoch": 11.755775577557756, "percentage": 58.78, "elapsed_time": "4:12:40", "remaining_time": "2:57:11", "throughput": 1487.6, "total_tokens": 22552928} {"current_steps": 106865, "total_steps": 181800, "loss": 0.1024, "lr": 2.1709958376484246e-05, "epoch": 11.756325632563257, "percentage": 58.78, "elapsed_time": "4:12:41", "remaining_time": "2:57:11", "throughput": 1487.6, "total_tokens": 22553888} {"current_steps": 106870, "total_steps": 181800, "loss": 0.0324, "lr": 2.1707579198079977e-05, "epoch": 11.756875687568757, "percentage": 58.78, "elapsed_time": "4:12:41", "remaining_time": "2:57:10", "throughput": 1487.6, "total_tokens": 22554848} {"current_steps": 106875, "total_steps": 181800, "loss": 0.0048, "lr": 2.170520005002038e-05, "epoch": 11.757425742574258, "percentage": 58.79, "elapsed_time": "4:12:42", "remaining_time": "2:57:09", "throughput": 1487.6, "total_tokens": 22555872} {"current_steps": 106880, "total_steps": 181800, "loss": 0.0062, "lr": 2.1702820932327372e-05, "epoch": 11.757975797579759, "percentage": 58.79, "elapsed_time": "4:12:43", "remaining_time": "2:57:09", "throughput": 1487.6, "total_tokens": 22556960} {"current_steps": 106885, "total_steps": 181800, "loss": 0.0099, "lr": 2.1700441845022876e-05, "epoch": 11.758525852585258, "percentage": 58.79, "elapsed_time": "4:12:44", "remaining_time": "2:57:08", "throughput": 1487.6, "total_tokens": 22558016} {"current_steps": 106890, "total_steps": 181800, "loss": 0.0079, "lr": 2.1698062788128827e-05, "epoch": 11.75907590759076, "percentage": 58.8, "elapsed_time": "4:12:44", "remaining_time": "2:57:07", "throughput": 1487.61, "total_tokens": 22559104} {"current_steps": 106895, "total_steps": 181800, "loss": 0.0075, "lr": 2.1695683761667144e-05, "epoch": 11.75962596259626, "percentage": 58.8, "elapsed_time": "4:12:45", "remaining_time": "2:57:06", "throughput": 1487.61, "total_tokens": 22560192} {"current_steps": 106900, "total_steps": 181800, "loss": 0.0242, "lr": 2.1693304765659768e-05, "epoch": 11.76017601760176, "percentage": 58.8, "elapsed_time": "4:12:46", "remaining_time": "2:57:06", "throughput": 1487.61, "total_tokens": 22561216} {"current_steps": 106905, "total_steps": 181800, "loss": 0.0016, "lr": 2.1690925800128614e-05, "epoch": 11.76072607260726, "percentage": 58.8, "elapsed_time": "4:12:46", "remaining_time": "2:57:05", "throughput": 1487.61, "total_tokens": 22562272} {"current_steps": 106910, "total_steps": 181800, "loss": 0.0231, "lr": 2.16885468650956e-05, "epoch": 11.761276127612762, "percentage": 58.81, "elapsed_time": "4:12:47", "remaining_time": "2:57:04", "throughput": 1487.61, "total_tokens": 22563296} {"current_steps": 106915, "total_steps": 181800, "loss": 0.0477, "lr": 2.168616796058267e-05, "epoch": 11.761826182618261, "percentage": 58.81, "elapsed_time": "4:12:48", "remaining_time": "2:57:04", "throughput": 1487.62, "total_tokens": 22564448} {"current_steps": 106920, "total_steps": 181800, "loss": 0.0727, "lr": 2.168378908661173e-05, "epoch": 11.762376237623762, "percentage": 58.81, "elapsed_time": "4:12:48", "remaining_time": "2:57:03", "throughput": 1487.63, "total_tokens": 22565536} {"current_steps": 106925, "total_steps": 181800, "loss": 0.005, "lr": 2.1681410243204724e-05, "epoch": 11.762926292629263, "percentage": 58.81, "elapsed_time": "4:12:49", "remaining_time": "2:57:02", "throughput": 1487.62, "total_tokens": 22566528} {"current_steps": 106930, "total_steps": 181800, "loss": 0.0069, "lr": 2.167903143038357e-05, "epoch": 11.763476347634764, "percentage": 58.82, "elapsed_time": "4:12:50", "remaining_time": "2:57:01", "throughput": 1487.62, "total_tokens": 22567552} {"current_steps": 106935, "total_steps": 181800, "loss": 0.1176, "lr": 2.1676652648170175e-05, "epoch": 11.764026402640264, "percentage": 58.82, "elapsed_time": "4:12:50", "remaining_time": "2:57:01", "throughput": 1487.62, "total_tokens": 22568576} {"current_steps": 106940, "total_steps": 181800, "loss": 0.0534, "lr": 2.1674273896586492e-05, "epoch": 11.764576457645765, "percentage": 58.82, "elapsed_time": "4:12:51", "remaining_time": "2:57:00", "throughput": 1487.63, "total_tokens": 22569632} {"current_steps": 106945, "total_steps": 181800, "loss": 0.1142, "lr": 2.1671895175654418e-05, "epoch": 11.765126512651266, "percentage": 58.83, "elapsed_time": "4:12:52", "remaining_time": "2:56:59", "throughput": 1487.63, "total_tokens": 22570688} {"current_steps": 106950, "total_steps": 181800, "loss": 0.0111, "lr": 2.1669516485395897e-05, "epoch": 11.765676567656765, "percentage": 58.83, "elapsed_time": "4:12:52", "remaining_time": "2:56:58", "throughput": 1487.63, "total_tokens": 22571744} {"current_steps": 106955, "total_steps": 181800, "loss": 0.0115, "lr": 2.166713782583285e-05, "epoch": 11.766226622662266, "percentage": 58.83, "elapsed_time": "4:12:53", "remaining_time": "2:56:58", "throughput": 1487.63, "total_tokens": 22572832} {"current_steps": 106960, "total_steps": 181800, "loss": 0.0724, "lr": 2.1664759196987182e-05, "epoch": 11.766776677667767, "percentage": 58.83, "elapsed_time": "4:12:54", "remaining_time": "2:56:57", "throughput": 1487.64, "total_tokens": 22573952} {"current_steps": 106965, "total_steps": 181800, "loss": 0.0229, "lr": 2.166238059888084e-05, "epoch": 11.767326732673267, "percentage": 58.84, "elapsed_time": "4:12:55", "remaining_time": "2:56:56", "throughput": 1487.64, "total_tokens": 22574976} {"current_steps": 106970, "total_steps": 181800, "loss": 0.0179, "lr": 2.1660002031535733e-05, "epoch": 11.767876787678768, "percentage": 58.84, "elapsed_time": "4:12:55", "remaining_time": "2:56:56", "throughput": 1487.64, "total_tokens": 22576032} {"current_steps": 106975, "total_steps": 181800, "loss": 0.0034, "lr": 2.1657623494973776e-05, "epoch": 11.768426842684269, "percentage": 58.84, "elapsed_time": "4:12:56", "remaining_time": "2:56:55", "throughput": 1487.64, "total_tokens": 22577120} {"current_steps": 106980, "total_steps": 181800, "loss": 0.048, "lr": 2.1655244989216903e-05, "epoch": 11.768976897689768, "percentage": 58.84, "elapsed_time": "4:12:57", "remaining_time": "2:56:54", "throughput": 1487.65, "total_tokens": 22578208} {"current_steps": 106985, "total_steps": 181800, "loss": 0.0128, "lr": 2.165286651428703e-05, "epoch": 11.76952695269527, "percentage": 58.85, "elapsed_time": "4:12:57", "remaining_time": "2:56:53", "throughput": 1487.65, "total_tokens": 22579264} {"current_steps": 106990, "total_steps": 181800, "loss": 0.009, "lr": 2.165048807020608e-05, "epoch": 11.77007700770077, "percentage": 58.85, "elapsed_time": "4:12:58", "remaining_time": "2:56:53", "throughput": 1487.65, "total_tokens": 22580288} {"current_steps": 106995, "total_steps": 181800, "loss": 0.0173, "lr": 2.1648109656995984e-05, "epoch": 11.770627062706271, "percentage": 58.85, "elapsed_time": "4:12:59", "remaining_time": "2:56:52", "throughput": 1487.65, "total_tokens": 22581344} {"current_steps": 107000, "total_steps": 181800, "loss": 0.1509, "lr": 2.1645731274678643e-05, "epoch": 11.77117711771177, "percentage": 58.86, "elapsed_time": "4:12:59", "remaining_time": "2:56:51", "throughput": 1487.65, "total_tokens": 22582368} {"current_steps": 107005, "total_steps": 181800, "loss": 0.0861, "lr": 2.1643352923275988e-05, "epoch": 11.771727172717272, "percentage": 58.86, "elapsed_time": "4:13:00", "remaining_time": "2:56:51", "throughput": 1487.65, "total_tokens": 22583392} {"current_steps": 107010, "total_steps": 181800, "loss": 0.0294, "lr": 2.1640974602809937e-05, "epoch": 11.772277227722773, "percentage": 58.86, "elapsed_time": "4:13:01", "remaining_time": "2:56:50", "throughput": 1487.66, "total_tokens": 22584512} {"current_steps": 107015, "total_steps": 181800, "loss": 0.0908, "lr": 2.1638596313302422e-05, "epoch": 11.772827282728272, "percentage": 58.86, "elapsed_time": "4:13:01", "remaining_time": "2:56:49", "throughput": 1487.66, "total_tokens": 22585600} {"current_steps": 107020, "total_steps": 181800, "loss": 0.0616, "lr": 2.1636218054775344e-05, "epoch": 11.773377337733773, "percentage": 58.87, "elapsed_time": "4:13:02", "remaining_time": "2:56:48", "throughput": 1487.66, "total_tokens": 22586656} {"current_steps": 107025, "total_steps": 181800, "loss": 0.0085, "lr": 2.1633839827250628e-05, "epoch": 11.773927392739274, "percentage": 58.87, "elapsed_time": "4:13:03", "remaining_time": "2:56:48", "throughput": 1487.67, "total_tokens": 22587744} {"current_steps": 107030, "total_steps": 181800, "loss": 0.0067, "lr": 2.1631461630750204e-05, "epoch": 11.774477447744774, "percentage": 58.87, "elapsed_time": "4:13:04", "remaining_time": "2:56:47", "throughput": 1487.66, "total_tokens": 22588736} {"current_steps": 107035, "total_steps": 181800, "loss": 0.084, "lr": 2.162908346529597e-05, "epoch": 11.775027502750275, "percentage": 58.88, "elapsed_time": "4:13:04", "remaining_time": "2:56:46", "throughput": 1487.67, "total_tokens": 22589824} {"current_steps": 107040, "total_steps": 181800, "loss": 0.0028, "lr": 2.1626705330909865e-05, "epoch": 11.775577557755776, "percentage": 58.88, "elapsed_time": "4:13:05", "remaining_time": "2:56:45", "throughput": 1487.67, "total_tokens": 22590848} {"current_steps": 107045, "total_steps": 181800, "loss": 0.1872, "lr": 2.16243272276138e-05, "epoch": 11.776127612761275, "percentage": 58.88, "elapsed_time": "4:13:06", "remaining_time": "2:56:45", "throughput": 1487.67, "total_tokens": 22591904} {"current_steps": 107050, "total_steps": 181800, "loss": 0.0056, "lr": 2.1621949155429676e-05, "epoch": 11.776677667766776, "percentage": 58.88, "elapsed_time": "4:13:06", "remaining_time": "2:56:44", "throughput": 1487.67, "total_tokens": 22592928} {"current_steps": 107055, "total_steps": 181800, "loss": 0.0167, "lr": 2.1619571114379442e-05, "epoch": 11.777227722772277, "percentage": 58.89, "elapsed_time": "4:13:07", "remaining_time": "2:56:43", "throughput": 1487.67, "total_tokens": 22593952} {"current_steps": 107060, "total_steps": 181800, "loss": 0.0286, "lr": 2.1617193104484988e-05, "epoch": 11.777777777777779, "percentage": 58.89, "elapsed_time": "4:13:08", "remaining_time": "2:56:43", "throughput": 1487.67, "total_tokens": 22594976} {"current_steps": 107065, "total_steps": 181800, "loss": 0.0766, "lr": 2.1614815125768248e-05, "epoch": 11.778327832783278, "percentage": 58.89, "elapsed_time": "4:13:08", "remaining_time": "2:56:42", "throughput": 1487.67, "total_tokens": 22596032} {"current_steps": 107070, "total_steps": 181800, "loss": 0.0892, "lr": 2.161243717825114e-05, "epoch": 11.778877887788779, "percentage": 58.89, "elapsed_time": "4:13:09", "remaining_time": "2:56:41", "throughput": 1487.68, "total_tokens": 22597120} {"current_steps": 107075, "total_steps": 181800, "loss": 0.0204, "lr": 2.1610059261955557e-05, "epoch": 11.77942794279428, "percentage": 58.9, "elapsed_time": "4:13:10", "remaining_time": "2:56:40", "throughput": 1487.67, "total_tokens": 22598080} {"current_steps": 107080, "total_steps": 181800, "loss": 0.0037, "lr": 2.1607681376903442e-05, "epoch": 11.77997799779978, "percentage": 58.9, "elapsed_time": "4:13:10", "remaining_time": "2:56:40", "throughput": 1487.67, "total_tokens": 22599072} {"current_steps": 107085, "total_steps": 181800, "loss": 0.0065, "lr": 2.1605303523116692e-05, "epoch": 11.78052805280528, "percentage": 58.9, "elapsed_time": "4:13:11", "remaining_time": "2:56:39", "throughput": 1487.67, "total_tokens": 22600096} {"current_steps": 107090, "total_steps": 181800, "loss": 0.1228, "lr": 2.160292570061724e-05, "epoch": 11.781078107810782, "percentage": 58.91, "elapsed_time": "4:13:12", "remaining_time": "2:56:38", "throughput": 1487.67, "total_tokens": 22601088} {"current_steps": 107095, "total_steps": 181800, "loss": 0.0033, "lr": 2.160054790942699e-05, "epoch": 11.781628162816281, "percentage": 58.91, "elapsed_time": "4:13:13", "remaining_time": "2:56:38", "throughput": 1487.67, "total_tokens": 22602176} {"current_steps": 107100, "total_steps": 181800, "loss": 0.0326, "lr": 2.159817014956785e-05, "epoch": 11.782178217821782, "percentage": 58.91, "elapsed_time": "4:13:13", "remaining_time": "2:56:37", "throughput": 1487.67, "total_tokens": 22603200} {"current_steps": 107105, "total_steps": 181800, "loss": 0.0706, "lr": 2.1595792421061754e-05, "epoch": 11.782728272827283, "percentage": 58.91, "elapsed_time": "4:13:14", "remaining_time": "2:56:36", "throughput": 1487.67, "total_tokens": 22604288} {"current_steps": 107110, "total_steps": 181800, "loss": 0.0315, "lr": 2.1593414723930587e-05, "epoch": 11.783278327832782, "percentage": 58.92, "elapsed_time": "4:13:15", "remaining_time": "2:56:35", "throughput": 1487.67, "total_tokens": 22605280} {"current_steps": 107115, "total_steps": 181800, "loss": 0.1138, "lr": 2.1591037058196305e-05, "epoch": 11.783828382838283, "percentage": 58.92, "elapsed_time": "4:13:15", "remaining_time": "2:56:35", "throughput": 1487.68, "total_tokens": 22606400} {"current_steps": 107120, "total_steps": 181800, "loss": 0.0616, "lr": 2.158865942388079e-05, "epoch": 11.784378437843785, "percentage": 58.92, "elapsed_time": "4:13:16", "remaining_time": "2:56:34", "throughput": 1487.68, "total_tokens": 22607424} {"current_steps": 107125, "total_steps": 181800, "loss": 0.0566, "lr": 2.1586281821005958e-05, "epoch": 11.784928492849286, "percentage": 58.92, "elapsed_time": "4:13:17", "remaining_time": "2:56:33", "throughput": 1487.68, "total_tokens": 22608480} {"current_steps": 107130, "total_steps": 181800, "loss": 0.0101, "lr": 2.1583904249593738e-05, "epoch": 11.785478547854785, "percentage": 58.93, "elapsed_time": "4:13:17", "remaining_time": "2:56:32", "throughput": 1487.68, "total_tokens": 22609504} {"current_steps": 107135, "total_steps": 181800, "loss": 0.0736, "lr": 2.1581526709666024e-05, "epoch": 11.786028602860286, "percentage": 58.93, "elapsed_time": "4:13:18", "remaining_time": "2:56:32", "throughput": 1487.68, "total_tokens": 22610560} {"current_steps": 107140, "total_steps": 181800, "loss": 0.146, "lr": 2.1579149201244747e-05, "epoch": 11.786578657865787, "percentage": 58.93, "elapsed_time": "4:13:19", "remaining_time": "2:56:31", "throughput": 1487.67, "total_tokens": 22611520} {"current_steps": 107145, "total_steps": 181800, "loss": 0.012, "lr": 2.1576771724351813e-05, "epoch": 11.787128712871286, "percentage": 58.94, "elapsed_time": "4:13:19", "remaining_time": "2:56:30", "throughput": 1487.68, "total_tokens": 22612640} {"current_steps": 107150, "total_steps": 181800, "loss": 0.0066, "lr": 2.157439427900912e-05, "epoch": 11.787678767876788, "percentage": 58.94, "elapsed_time": "4:13:20", "remaining_time": "2:56:30", "throughput": 1487.68, "total_tokens": 22613728} {"current_steps": 107155, "total_steps": 181800, "loss": 0.0566, "lr": 2.1572016865238596e-05, "epoch": 11.788228822882289, "percentage": 58.94, "elapsed_time": "4:13:21", "remaining_time": "2:56:29", "throughput": 1487.69, "total_tokens": 22614848} {"current_steps": 107160, "total_steps": 181800, "loss": 0.1457, "lr": 2.1569639483062156e-05, "epoch": 11.788778877887788, "percentage": 58.94, "elapsed_time": "4:13:22", "remaining_time": "2:56:28", "throughput": 1487.69, "total_tokens": 22615840} {"current_steps": 107165, "total_steps": 181800, "loss": 0.0057, "lr": 2.1567262132501688e-05, "epoch": 11.789328932893289, "percentage": 58.95, "elapsed_time": "4:13:22", "remaining_time": "2:56:27", "throughput": 1487.69, "total_tokens": 22616832} {"current_steps": 107170, "total_steps": 181800, "loss": 0.1278, "lr": 2.1564884813579124e-05, "epoch": 11.78987898789879, "percentage": 58.95, "elapsed_time": "4:13:23", "remaining_time": "2:56:27", "throughput": 1487.69, "total_tokens": 22617920} {"current_steps": 107175, "total_steps": 181800, "loss": 0.0295, "lr": 2.1562507526316364e-05, "epoch": 11.79042904290429, "percentage": 58.95, "elapsed_time": "4:13:24", "remaining_time": "2:56:26", "throughput": 1487.69, "total_tokens": 22619008} {"current_steps": 107180, "total_steps": 181800, "loss": 0.005, "lr": 2.1560130270735327e-05, "epoch": 11.79097909790979, "percentage": 58.95, "elapsed_time": "4:13:24", "remaining_time": "2:56:25", "throughput": 1487.7, "total_tokens": 22620064} {"current_steps": 107185, "total_steps": 181800, "loss": 0.0492, "lr": 2.1557753046857927e-05, "epoch": 11.791529152915292, "percentage": 58.96, "elapsed_time": "4:13:25", "remaining_time": "2:56:25", "throughput": 1487.7, "total_tokens": 22621152} {"current_steps": 107190, "total_steps": 181800, "loss": 0.0439, "lr": 2.155537585470605e-05, "epoch": 11.792079207920793, "percentage": 58.96, "elapsed_time": "4:13:26", "remaining_time": "2:56:24", "throughput": 1487.7, "total_tokens": 22622240} {"current_steps": 107195, "total_steps": 181800, "loss": 0.0928, "lr": 2.155299869430163e-05, "epoch": 11.792629262926292, "percentage": 58.96, "elapsed_time": "4:13:26", "remaining_time": "2:56:23", "throughput": 1487.71, "total_tokens": 22623328} {"current_steps": 107200, "total_steps": 181800, "loss": 0.0718, "lr": 2.155062156566656e-05, "epoch": 11.793179317931793, "percentage": 58.97, "elapsed_time": "4:13:27", "remaining_time": "2:56:22", "throughput": 1487.71, "total_tokens": 22624352} {"current_steps": 107205, "total_steps": 181800, "loss": 0.0388, "lr": 2.1548244468822767e-05, "epoch": 11.793729372937294, "percentage": 58.97, "elapsed_time": "4:13:28", "remaining_time": "2:56:22", "throughput": 1487.71, "total_tokens": 22625408} {"current_steps": 107210, "total_steps": 181800, "loss": 0.0213, "lr": 2.1545867403792145e-05, "epoch": 11.794279427942794, "percentage": 58.97, "elapsed_time": "4:13:29", "remaining_time": "2:56:21", "throughput": 1487.69, "total_tokens": 22626496} {"current_steps": 107215, "total_steps": 181800, "loss": 0.0041, "lr": 2.1543490370596597e-05, "epoch": 11.794829482948295, "percentage": 58.97, "elapsed_time": "4:13:29", "remaining_time": "2:56:20", "throughput": 1487.69, "total_tokens": 22627520} {"current_steps": 107220, "total_steps": 181800, "loss": 0.0505, "lr": 2.1541113369258052e-05, "epoch": 11.795379537953796, "percentage": 58.98, "elapsed_time": "4:13:30", "remaining_time": "2:56:20", "throughput": 1487.7, "total_tokens": 22628608} {"current_steps": 107225, "total_steps": 181800, "loss": 0.0072, "lr": 2.1538736399798392e-05, "epoch": 11.795929592959295, "percentage": 58.98, "elapsed_time": "4:13:31", "remaining_time": "2:56:19", "throughput": 1487.69, "total_tokens": 22629568} {"current_steps": 107230, "total_steps": 181800, "loss": 0.0037, "lr": 2.1536359462239548e-05, "epoch": 11.796479647964796, "percentage": 58.98, "elapsed_time": "4:13:31", "remaining_time": "2:56:18", "throughput": 1487.69, "total_tokens": 22630592} {"current_steps": 107235, "total_steps": 181800, "loss": 0.0509, "lr": 2.1533982556603413e-05, "epoch": 11.797029702970297, "percentage": 58.99, "elapsed_time": "4:13:32", "remaining_time": "2:56:17", "throughput": 1487.69, "total_tokens": 22631616} {"current_steps": 107240, "total_steps": 181800, "loss": 0.0983, "lr": 2.1531605682911897e-05, "epoch": 11.797579757975798, "percentage": 58.99, "elapsed_time": "4:13:33", "remaining_time": "2:56:17", "throughput": 1487.7, "total_tokens": 22632704} {"current_steps": 107245, "total_steps": 181800, "loss": 0.0121, "lr": 2.1529228841186913e-05, "epoch": 11.798129812981298, "percentage": 58.99, "elapsed_time": "4:13:33", "remaining_time": "2:56:16", "throughput": 1487.69, "total_tokens": 22633696} {"current_steps": 107250, "total_steps": 181800, "loss": 0.0372, "lr": 2.152685203145035e-05, "epoch": 11.798679867986799, "percentage": 58.99, "elapsed_time": "4:13:34", "remaining_time": "2:56:15", "throughput": 1487.7, "total_tokens": 22634752} {"current_steps": 107255, "total_steps": 181800, "loss": 0.0071, "lr": 2.1524475253724134e-05, "epoch": 11.7992299229923, "percentage": 59.0, "elapsed_time": "4:13:35", "remaining_time": "2:56:15", "throughput": 1487.7, "total_tokens": 22635808} {"current_steps": 107260, "total_steps": 181800, "loss": 0.0075, "lr": 2.1522098508030168e-05, "epoch": 11.7997799779978, "percentage": 59.0, "elapsed_time": "4:13:36", "remaining_time": "2:56:14", "throughput": 1487.69, "total_tokens": 22636768} {"current_steps": 107265, "total_steps": 181800, "loss": 0.0494, "lr": 2.1519721794390335e-05, "epoch": 11.8003300330033, "percentage": 59.0, "elapsed_time": "4:13:36", "remaining_time": "2:56:13", "throughput": 1487.69, "total_tokens": 22637760} {"current_steps": 107270, "total_steps": 181800, "loss": 0.0082, "lr": 2.1517345112826565e-05, "epoch": 11.800880088008801, "percentage": 59.0, "elapsed_time": "4:13:37", "remaining_time": "2:56:12", "throughput": 1487.69, "total_tokens": 22638816} {"current_steps": 107275, "total_steps": 181800, "loss": 0.0072, "lr": 2.151496846336075e-05, "epoch": 11.8014301430143, "percentage": 59.01, "elapsed_time": "4:13:38", "remaining_time": "2:56:12", "throughput": 1487.7, "total_tokens": 22639904} {"current_steps": 107280, "total_steps": 181800, "loss": 0.0063, "lr": 2.1512591846014807e-05, "epoch": 11.801980198019802, "percentage": 59.01, "elapsed_time": "4:13:38", "remaining_time": "2:56:11", "throughput": 1487.7, "total_tokens": 22640928} {"current_steps": 107285, "total_steps": 181800, "loss": 0.1325, "lr": 2.151021526081063e-05, "epoch": 11.802530253025303, "percentage": 59.01, "elapsed_time": "4:13:39", "remaining_time": "2:56:10", "throughput": 1487.7, "total_tokens": 22641952} {"current_steps": 107290, "total_steps": 181800, "loss": 0.0181, "lr": 2.150783870777011e-05, "epoch": 11.803080308030804, "percentage": 59.02, "elapsed_time": "4:13:40", "remaining_time": "2:56:09", "throughput": 1487.7, "total_tokens": 22643008} {"current_steps": 107295, "total_steps": 181800, "loss": 0.0807, "lr": 2.150546218691518e-05, "epoch": 11.803630363036303, "percentage": 59.02, "elapsed_time": "4:13:40", "remaining_time": "2:56:09", "throughput": 1487.7, "total_tokens": 22644032} {"current_steps": 107300, "total_steps": 181800, "loss": 0.0049, "lr": 2.1503085698267717e-05, "epoch": 11.804180418041804, "percentage": 59.02, "elapsed_time": "4:13:41", "remaining_time": "2:56:08", "throughput": 1487.71, "total_tokens": 22645152} {"current_steps": 107305, "total_steps": 181800, "loss": 0.0105, "lr": 2.150070924184965e-05, "epoch": 11.804730473047305, "percentage": 59.02, "elapsed_time": "4:13:42", "remaining_time": "2:56:07", "throughput": 1487.71, "total_tokens": 22646240} {"current_steps": 107310, "total_steps": 181800, "loss": 0.0052, "lr": 2.149833281768286e-05, "epoch": 11.805280528052805, "percentage": 59.03, "elapsed_time": "4:13:42", "remaining_time": "2:56:07", "throughput": 1487.71, "total_tokens": 22647328} {"current_steps": 107315, "total_steps": 181800, "loss": 0.0232, "lr": 2.1495956425789248e-05, "epoch": 11.805830583058306, "percentage": 59.03, "elapsed_time": "4:13:43", "remaining_time": "2:56:06", "throughput": 1487.72, "total_tokens": 22648448} {"current_steps": 107320, "total_steps": 181800, "loss": 0.0728, "lr": 2.1493580066190738e-05, "epoch": 11.806380638063807, "percentage": 59.03, "elapsed_time": "4:13:44", "remaining_time": "2:56:05", "throughput": 1487.73, "total_tokens": 22649568} {"current_steps": 107325, "total_steps": 181800, "loss": 0.0037, "lr": 2.1491203738909205e-05, "epoch": 11.806930693069306, "percentage": 59.03, "elapsed_time": "4:13:44", "remaining_time": "2:56:04", "throughput": 1487.73, "total_tokens": 22650624} {"current_steps": 107330, "total_steps": 181800, "loss": 0.0053, "lr": 2.148882744396657e-05, "epoch": 11.807480748074807, "percentage": 59.04, "elapsed_time": "4:13:45", "remaining_time": "2:56:04", "throughput": 1487.73, "total_tokens": 22651712} {"current_steps": 107335, "total_steps": 181800, "loss": 0.0203, "lr": 2.1486451181384734e-05, "epoch": 11.808030803080309, "percentage": 59.04, "elapsed_time": "4:13:46", "remaining_time": "2:56:03", "throughput": 1487.74, "total_tokens": 22652800} {"current_steps": 107340, "total_steps": 181800, "loss": 0.0632, "lr": 2.1484074951185577e-05, "epoch": 11.808580858085808, "percentage": 59.04, "elapsed_time": "4:13:47", "remaining_time": "2:56:02", "throughput": 1487.74, "total_tokens": 22653888} {"current_steps": 107345, "total_steps": 181800, "loss": 0.0031, "lr": 2.1481698753391025e-05, "epoch": 11.809130913091309, "percentage": 59.05, "elapsed_time": "4:13:47", "remaining_time": "2:56:02", "throughput": 1487.74, "total_tokens": 22654912} {"current_steps": 107350, "total_steps": 181800, "loss": 0.0134, "lr": 2.147932258802297e-05, "epoch": 11.80968096809681, "percentage": 59.05, "elapsed_time": "4:13:48", "remaining_time": "2:56:01", "throughput": 1487.74, "total_tokens": 22655968} {"current_steps": 107355, "total_steps": 181800, "loss": 0.0156, "lr": 2.147694645510329e-05, "epoch": 11.810231023102311, "percentage": 59.05, "elapsed_time": "4:13:49", "remaining_time": "2:56:00", "throughput": 1487.74, "total_tokens": 22657024} {"current_steps": 107360, "total_steps": 181800, "loss": 0.0194, "lr": 2.147457035465393e-05, "epoch": 11.81078107810781, "percentage": 59.05, "elapsed_time": "4:13:49", "remaining_time": "2:55:59", "throughput": 1487.74, "total_tokens": 22658048} {"current_steps": 107365, "total_steps": 181800, "loss": 0.1391, "lr": 2.1472194286696744e-05, "epoch": 11.811331133113312, "percentage": 59.06, "elapsed_time": "4:13:50", "remaining_time": "2:55:59", "throughput": 1487.75, "total_tokens": 22659104} {"current_steps": 107370, "total_steps": 181800, "loss": 0.1058, "lr": 2.1469818251253657e-05, "epoch": 11.811881188118813, "percentage": 59.06, "elapsed_time": "4:13:51", "remaining_time": "2:55:58", "throughput": 1487.75, "total_tokens": 22660128} {"current_steps": 107375, "total_steps": 181800, "loss": 0.0074, "lr": 2.1467442248346566e-05, "epoch": 11.812431243124312, "percentage": 59.06, "elapsed_time": "4:13:51", "remaining_time": "2:55:57", "throughput": 1487.75, "total_tokens": 22661216} {"current_steps": 107380, "total_steps": 181800, "loss": 0.006, "lr": 2.1465066277997358e-05, "epoch": 11.812981298129813, "percentage": 59.06, "elapsed_time": "4:13:52", "remaining_time": "2:55:56", "throughput": 1487.75, "total_tokens": 22662240} {"current_steps": 107385, "total_steps": 181800, "loss": 0.0038, "lr": 2.146269034022794e-05, "epoch": 11.813531353135314, "percentage": 59.07, "elapsed_time": "4:13:53", "remaining_time": "2:55:56", "throughput": 1487.75, "total_tokens": 22663264} {"current_steps": 107390, "total_steps": 181800, "loss": 0.0036, "lr": 2.14603144350602e-05, "epoch": 11.814081408140813, "percentage": 59.07, "elapsed_time": "4:13:53", "remaining_time": "2:55:55", "throughput": 1487.75, "total_tokens": 22664352} {"current_steps": 107395, "total_steps": 181800, "loss": 0.0571, "lr": 2.1457938562516058e-05, "epoch": 11.814631463146315, "percentage": 59.07, "elapsed_time": "4:13:54", "remaining_time": "2:55:54", "throughput": 1487.75, "total_tokens": 22665344} {"current_steps": 107400, "total_steps": 181800, "loss": 0.0116, "lr": 2.1455562722617388e-05, "epoch": 11.815181518151816, "percentage": 59.08, "elapsed_time": "4:13:55", "remaining_time": "2:55:54", "throughput": 1487.75, "total_tokens": 22666368} {"current_steps": 107405, "total_steps": 181800, "loss": 0.0132, "lr": 2.1453186915386095e-05, "epoch": 11.815731573157315, "percentage": 59.08, "elapsed_time": "4:13:56", "remaining_time": "2:55:53", "throughput": 1487.76, "total_tokens": 22667520} {"current_steps": 107410, "total_steps": 181800, "loss": 0.1672, "lr": 2.1450811140844084e-05, "epoch": 11.816281628162816, "percentage": 59.08, "elapsed_time": "4:13:56", "remaining_time": "2:55:52", "throughput": 1487.76, "total_tokens": 22668640} {"current_steps": 107415, "total_steps": 181800, "loss": 0.0176, "lr": 2.144843539901323e-05, "epoch": 11.816831683168317, "percentage": 59.08, "elapsed_time": "4:13:57", "remaining_time": "2:55:51", "throughput": 1487.76, "total_tokens": 22669664} {"current_steps": 107420, "total_steps": 181800, "loss": 0.0031, "lr": 2.1446059689915456e-05, "epoch": 11.817381738173818, "percentage": 59.09, "elapsed_time": "4:13:58", "remaining_time": "2:55:51", "throughput": 1487.77, "total_tokens": 22670752} {"current_steps": 107425, "total_steps": 181800, "loss": 0.0036, "lr": 2.144368401357264e-05, "epoch": 11.817931793179318, "percentage": 59.09, "elapsed_time": "4:13:58", "remaining_time": "2:55:50", "throughput": 1487.77, "total_tokens": 22671840} {"current_steps": 107430, "total_steps": 181800, "loss": 0.009, "lr": 2.1441308370006678e-05, "epoch": 11.818481848184819, "percentage": 59.09, "elapsed_time": "4:13:59", "remaining_time": "2:55:49", "throughput": 1487.77, "total_tokens": 22672896} {"current_steps": 107435, "total_steps": 181800, "loss": 0.1234, "lr": 2.1438932759239476e-05, "epoch": 11.81903190319032, "percentage": 59.1, "elapsed_time": "4:14:00", "remaining_time": "2:55:49", "throughput": 1487.78, "total_tokens": 22673984} {"current_steps": 107440, "total_steps": 181800, "loss": 0.0033, "lr": 2.1436557181292914e-05, "epoch": 11.819581958195819, "percentage": 59.1, "elapsed_time": "4:14:00", "remaining_time": "2:55:48", "throughput": 1487.77, "total_tokens": 22674944} {"current_steps": 107445, "total_steps": 181800, "loss": 0.0025, "lr": 2.14341816361889e-05, "epoch": 11.82013201320132, "percentage": 59.1, "elapsed_time": "4:14:01", "remaining_time": "2:55:47", "throughput": 1487.77, "total_tokens": 22675968} {"current_steps": 107450, "total_steps": 181800, "loss": 0.0332, "lr": 2.1431806123949326e-05, "epoch": 11.820682068206821, "percentage": 59.1, "elapsed_time": "4:14:02", "remaining_time": "2:55:46", "throughput": 1487.78, "total_tokens": 22677056} {"current_steps": 107455, "total_steps": 181800, "loss": 0.0027, "lr": 2.1429430644596078e-05, "epoch": 11.82123212321232, "percentage": 59.11, "elapsed_time": "4:14:02", "remaining_time": "2:55:46", "throughput": 1487.78, "total_tokens": 22678112} {"current_steps": 107460, "total_steps": 181800, "loss": 0.0116, "lr": 2.1427055198151056e-05, "epoch": 11.821782178217822, "percentage": 59.11, "elapsed_time": "4:14:03", "remaining_time": "2:55:45", "throughput": 1487.78, "total_tokens": 22679136} {"current_steps": 107465, "total_steps": 181800, "loss": 0.047, "lr": 2.1424679784636144e-05, "epoch": 11.822332233223323, "percentage": 59.11, "elapsed_time": "4:14:04", "remaining_time": "2:55:44", "throughput": 1487.78, "total_tokens": 22680192} {"current_steps": 107470, "total_steps": 181800, "loss": 0.0021, "lr": 2.1422304404073257e-05, "epoch": 11.822882288228822, "percentage": 59.11, "elapsed_time": "4:14:04", "remaining_time": "2:55:43", "throughput": 1487.78, "total_tokens": 22681248} {"current_steps": 107475, "total_steps": 181800, "loss": 0.0419, "lr": 2.1419929056484267e-05, "epoch": 11.823432343234323, "percentage": 59.12, "elapsed_time": "4:14:05", "remaining_time": "2:55:43", "throughput": 1487.79, "total_tokens": 22682336} {"current_steps": 107480, "total_steps": 181800, "loss": 0.0051, "lr": 2.1417553741891067e-05, "epoch": 11.823982398239824, "percentage": 59.12, "elapsed_time": "4:14:06", "remaining_time": "2:55:42", "throughput": 1487.79, "total_tokens": 22683392} {"current_steps": 107485, "total_steps": 181800, "loss": 0.0031, "lr": 2.141517846031556e-05, "epoch": 11.824532453245325, "percentage": 59.12, "elapsed_time": "4:14:07", "remaining_time": "2:55:41", "throughput": 1487.79, "total_tokens": 22684416} {"current_steps": 107490, "total_steps": 181800, "loss": 0.0101, "lr": 2.141280321177963e-05, "epoch": 11.825082508250825, "percentage": 59.13, "elapsed_time": "4:14:07", "remaining_time": "2:55:41", "throughput": 1487.79, "total_tokens": 22685504} {"current_steps": 107495, "total_steps": 181800, "loss": 0.1044, "lr": 2.141042799630518e-05, "epoch": 11.825632563256326, "percentage": 59.13, "elapsed_time": "4:14:08", "remaining_time": "2:55:40", "throughput": 1487.8, "total_tokens": 22686592} {"current_steps": 107500, "total_steps": 181800, "loss": 0.0692, "lr": 2.1408052813914086e-05, "epoch": 11.826182618261827, "percentage": 59.13, "elapsed_time": "4:14:09", "remaining_time": "2:55:39", "throughput": 1487.8, "total_tokens": 22687616} {"current_steps": 107505, "total_steps": 181800, "loss": 0.0427, "lr": 2.1405677664628242e-05, "epoch": 11.826732673267326, "percentage": 59.13, "elapsed_time": "4:14:09", "remaining_time": "2:55:38", "throughput": 1487.8, "total_tokens": 22688640} {"current_steps": 107510, "total_steps": 181800, "loss": 0.0698, "lr": 2.1403302548469555e-05, "epoch": 11.827282728272827, "percentage": 59.14, "elapsed_time": "4:14:10", "remaining_time": "2:55:38", "throughput": 1487.8, "total_tokens": 22689696} {"current_steps": 107515, "total_steps": 181800, "loss": 0.0329, "lr": 2.1400927465459893e-05, "epoch": 11.827832783278328, "percentage": 59.14, "elapsed_time": "4:14:11", "remaining_time": "2:55:37", "throughput": 1487.8, "total_tokens": 22690688} {"current_steps": 107520, "total_steps": 181800, "loss": 0.0117, "lr": 2.1398552415621155e-05, "epoch": 11.828382838283828, "percentage": 59.14, "elapsed_time": "4:14:11", "remaining_time": "2:55:36", "throughput": 1487.8, "total_tokens": 22691744} {"current_steps": 107525, "total_steps": 181800, "loss": 0.0438, "lr": 2.1396177398975243e-05, "epoch": 11.828932893289329, "percentage": 59.14, "elapsed_time": "4:14:12", "remaining_time": "2:55:36", "throughput": 1487.8, "total_tokens": 22692704} {"current_steps": 107530, "total_steps": 181800, "loss": 0.0149, "lr": 2.139380241554401e-05, "epoch": 11.82948294829483, "percentage": 59.15, "elapsed_time": "4:14:13", "remaining_time": "2:55:35", "throughput": 1487.79, "total_tokens": 22693696} {"current_steps": 107535, "total_steps": 181800, "loss": 0.0575, "lr": 2.1391427465349395e-05, "epoch": 11.83003300330033, "percentage": 59.15, "elapsed_time": "4:14:13", "remaining_time": "2:55:34", "throughput": 1487.79, "total_tokens": 22694720} {"current_steps": 107540, "total_steps": 181800, "loss": 0.1341, "lr": 2.138905254841325e-05, "epoch": 11.83058305830583, "percentage": 59.15, "elapsed_time": "4:14:14", "remaining_time": "2:55:33", "throughput": 1487.8, "total_tokens": 22695808} {"current_steps": 107545, "total_steps": 181800, "loss": 0.04, "lr": 2.1386677664757474e-05, "epoch": 11.831133113311331, "percentage": 59.16, "elapsed_time": "4:14:15", "remaining_time": "2:55:33", "throughput": 1487.8, "total_tokens": 22696864} {"current_steps": 107550, "total_steps": 181800, "loss": 0.0844, "lr": 2.1384302814403964e-05, "epoch": 11.831683168316832, "percentage": 59.16, "elapsed_time": "4:14:16", "remaining_time": "2:55:32", "throughput": 1487.8, "total_tokens": 22697856} {"current_steps": 107555, "total_steps": 181800, "loss": 0.0034, "lr": 2.138192799737459e-05, "epoch": 11.832233223322332, "percentage": 59.16, "elapsed_time": "4:14:16", "remaining_time": "2:55:31", "throughput": 1487.8, "total_tokens": 22698880} {"current_steps": 107560, "total_steps": 181800, "loss": 0.0049, "lr": 2.1379553213691257e-05, "epoch": 11.832783278327833, "percentage": 59.16, "elapsed_time": "4:14:17", "remaining_time": "2:55:30", "throughput": 1487.8, "total_tokens": 22699904} {"current_steps": 107565, "total_steps": 181800, "loss": 0.0963, "lr": 2.1377178463375848e-05, "epoch": 11.833333333333334, "percentage": 59.17, "elapsed_time": "4:14:18", "remaining_time": "2:55:30", "throughput": 1487.8, "total_tokens": 22700928} {"current_steps": 107570, "total_steps": 181800, "loss": 0.005, "lr": 2.1374803746450233e-05, "epoch": 11.833883388338833, "percentage": 59.17, "elapsed_time": "4:14:18", "remaining_time": "2:55:29", "throughput": 1487.8, "total_tokens": 22701984} {"current_steps": 107575, "total_steps": 181800, "loss": 0.0259, "lr": 2.137242906293632e-05, "epoch": 11.834433443344334, "percentage": 59.17, "elapsed_time": "4:14:19", "remaining_time": "2:55:28", "throughput": 1487.8, "total_tokens": 22702976} {"current_steps": 107580, "total_steps": 181800, "loss": 0.0277, "lr": 2.1370054412855983e-05, "epoch": 11.834983498349835, "percentage": 59.17, "elapsed_time": "4:14:20", "remaining_time": "2:55:28", "throughput": 1487.79, "total_tokens": 22703968} {"current_steps": 107585, "total_steps": 181800, "loss": 0.0797, "lr": 2.1367679796231124e-05, "epoch": 11.835533553355335, "percentage": 59.18, "elapsed_time": "4:14:20", "remaining_time": "2:55:27", "throughput": 1487.8, "total_tokens": 22705024} {"current_steps": 107590, "total_steps": 181800, "loss": 0.0037, "lr": 2.136530521308361e-05, "epoch": 11.836083608360836, "percentage": 59.18, "elapsed_time": "4:14:21", "remaining_time": "2:55:26", "throughput": 1487.8, "total_tokens": 22706144} {"current_steps": 107595, "total_steps": 181800, "loss": 0.0042, "lr": 2.136293066343533e-05, "epoch": 11.836633663366337, "percentage": 59.18, "elapsed_time": "4:14:22", "remaining_time": "2:55:25", "throughput": 1487.8, "total_tokens": 22707168} {"current_steps": 107600, "total_steps": 181800, "loss": 0.0091, "lr": 2.136055614730818e-05, "epoch": 11.837183718371836, "percentage": 59.19, "elapsed_time": "4:14:22", "remaining_time": "2:55:25", "throughput": 1487.8, "total_tokens": 22708224} {"current_steps": 107605, "total_steps": 181800, "loss": 0.0076, "lr": 2.135818166472403e-05, "epoch": 11.837733773377337, "percentage": 59.19, "elapsed_time": "4:14:23", "remaining_time": "2:55:24", "throughput": 1487.81, "total_tokens": 22709280} {"current_steps": 107610, "total_steps": 181800, "loss": 0.0737, "lr": 2.1355807215704782e-05, "epoch": 11.838283828382838, "percentage": 59.19, "elapsed_time": "4:14:24", "remaining_time": "2:55:23", "throughput": 1487.81, "total_tokens": 22710336} {"current_steps": 107615, "total_steps": 181800, "loss": 0.1052, "lr": 2.1353432800272306e-05, "epoch": 11.83883388338834, "percentage": 59.19, "elapsed_time": "4:14:24", "remaining_time": "2:55:22", "throughput": 1487.82, "total_tokens": 22711488} {"current_steps": 107620, "total_steps": 181800, "loss": 0.0134, "lr": 2.1351058418448487e-05, "epoch": 11.839383938393839, "percentage": 59.2, "elapsed_time": "4:14:25", "remaining_time": "2:55:22", "throughput": 1487.82, "total_tokens": 22712640} {"current_steps": 107625, "total_steps": 181800, "loss": 0.075, "lr": 2.1348684070255217e-05, "epoch": 11.83993399339934, "percentage": 59.2, "elapsed_time": "4:14:26", "remaining_time": "2:55:21", "throughput": 1487.83, "total_tokens": 22713696} {"current_steps": 107630, "total_steps": 181800, "loss": 0.0116, "lr": 2.1346309755714366e-05, "epoch": 11.840484048404841, "percentage": 59.2, "elapsed_time": "4:14:27", "remaining_time": "2:55:20", "throughput": 1487.83, "total_tokens": 22714720} {"current_steps": 107635, "total_steps": 181800, "loss": 0.0331, "lr": 2.1343935474847832e-05, "epoch": 11.84103410341034, "percentage": 59.21, "elapsed_time": "4:14:27", "remaining_time": "2:55:20", "throughput": 1487.82, "total_tokens": 22715712} {"current_steps": 107640, "total_steps": 181800, "loss": 0.0027, "lr": 2.134156122767749e-05, "epoch": 11.841584158415841, "percentage": 59.21, "elapsed_time": "4:14:28", "remaining_time": "2:55:19", "throughput": 1487.82, "total_tokens": 22716704} {"current_steps": 107645, "total_steps": 181800, "loss": 0.0437, "lr": 2.133918701422522e-05, "epoch": 11.842134213421343, "percentage": 59.21, "elapsed_time": "4:14:29", "remaining_time": "2:55:18", "throughput": 1487.83, "total_tokens": 22717792} {"current_steps": 107650, "total_steps": 181800, "loss": 0.0055, "lr": 2.1336812834512907e-05, "epoch": 11.842684268426842, "percentage": 59.21, "elapsed_time": "4:14:29", "remaining_time": "2:55:17", "throughput": 1487.83, "total_tokens": 22718848} {"current_steps": 107655, "total_steps": 181800, "loss": 0.0645, "lr": 2.1334438688562428e-05, "epoch": 11.843234323432343, "percentage": 59.22, "elapsed_time": "4:14:30", "remaining_time": "2:55:17", "throughput": 1487.83, "total_tokens": 22719936} {"current_steps": 107660, "total_steps": 181800, "loss": 0.0107, "lr": 2.133206457639567e-05, "epoch": 11.843784378437844, "percentage": 59.22, "elapsed_time": "4:14:31", "remaining_time": "2:55:16", "throughput": 1487.84, "total_tokens": 22721024} {"current_steps": 107665, "total_steps": 181800, "loss": 0.0382, "lr": 2.1329690498034525e-05, "epoch": 11.844334433443345, "percentage": 59.22, "elapsed_time": "4:14:31", "remaining_time": "2:55:15", "throughput": 1487.84, "total_tokens": 22722112} {"current_steps": 107670, "total_steps": 181800, "loss": 0.0154, "lr": 2.132731645350085e-05, "epoch": 11.844884488448844, "percentage": 59.22, "elapsed_time": "4:14:32", "remaining_time": "2:55:15", "throughput": 1487.84, "total_tokens": 22723072} {"current_steps": 107675, "total_steps": 181800, "loss": 0.0023, "lr": 2.1324942442816537e-05, "epoch": 11.845434543454346, "percentage": 59.23, "elapsed_time": "4:14:33", "remaining_time": "2:55:14", "throughput": 1487.84, "total_tokens": 22724128} {"current_steps": 107680, "total_steps": 181800, "loss": 0.0951, "lr": 2.1322568466003464e-05, "epoch": 11.845984598459847, "percentage": 59.23, "elapsed_time": "4:14:33", "remaining_time": "2:55:13", "throughput": 1487.84, "total_tokens": 22725216} {"current_steps": 107685, "total_steps": 181800, "loss": 0.0083, "lr": 2.1320194523083526e-05, "epoch": 11.846534653465346, "percentage": 59.23, "elapsed_time": "4:14:34", "remaining_time": "2:55:12", "throughput": 1487.84, "total_tokens": 22726240} {"current_steps": 107690, "total_steps": 181800, "loss": 0.0249, "lr": 2.1317820614078577e-05, "epoch": 11.847084708470847, "percentage": 59.24, "elapsed_time": "4:14:35", "remaining_time": "2:55:12", "throughput": 1487.85, "total_tokens": 22727328} {"current_steps": 107695, "total_steps": 181800, "loss": 0.0046, "lr": 2.131544673901051e-05, "epoch": 11.847634763476348, "percentage": 59.24, "elapsed_time": "4:14:36", "remaining_time": "2:55:11", "throughput": 1487.85, "total_tokens": 22728384} {"current_steps": 107700, "total_steps": 181800, "loss": 0.0729, "lr": 2.131307289790121e-05, "epoch": 11.848184818481847, "percentage": 59.24, "elapsed_time": "4:14:36", "remaining_time": "2:55:10", "throughput": 1487.85, "total_tokens": 22729408} {"current_steps": 107705, "total_steps": 181800, "loss": 0.0039, "lr": 2.131069909077254e-05, "epoch": 11.848734873487349, "percentage": 59.24, "elapsed_time": "4:14:37", "remaining_time": "2:55:09", "throughput": 1487.85, "total_tokens": 22730464} {"current_steps": 107710, "total_steps": 181800, "loss": 0.0743, "lr": 2.1308325317646387e-05, "epoch": 11.84928492849285, "percentage": 59.25, "elapsed_time": "4:14:38", "remaining_time": "2:55:09", "throughput": 1487.85, "total_tokens": 22731456} {"current_steps": 107715, "total_steps": 181800, "loss": 0.005, "lr": 2.1305951578544636e-05, "epoch": 11.84983498349835, "percentage": 59.25, "elapsed_time": "4:14:38", "remaining_time": "2:55:08", "throughput": 1487.85, "total_tokens": 22732480} {"current_steps": 107720, "total_steps": 181800, "loss": 0.0053, "lr": 2.130357787348914e-05, "epoch": 11.85038503850385, "percentage": 59.25, "elapsed_time": "4:14:39", "remaining_time": "2:55:07", "throughput": 1487.85, "total_tokens": 22733504} {"current_steps": 107725, "total_steps": 181800, "loss": 0.0053, "lr": 2.1301204202501813e-05, "epoch": 11.850935093509351, "percentage": 59.25, "elapsed_time": "4:14:40", "remaining_time": "2:55:07", "throughput": 1487.85, "total_tokens": 22734592} {"current_steps": 107730, "total_steps": 181800, "loss": 0.0868, "lr": 2.12988305656045e-05, "epoch": 11.851485148514852, "percentage": 59.26, "elapsed_time": "4:14:40", "remaining_time": "2:55:06", "throughput": 1487.85, "total_tokens": 22735648} {"current_steps": 107735, "total_steps": 181800, "loss": 0.0294, "lr": 2.129645696281909e-05, "epoch": 11.852035203520352, "percentage": 59.26, "elapsed_time": "4:14:41", "remaining_time": "2:55:05", "throughput": 1487.86, "total_tokens": 22736736} {"current_steps": 107740, "total_steps": 181800, "loss": 0.0073, "lr": 2.1294083394167467e-05, "epoch": 11.852585258525853, "percentage": 59.26, "elapsed_time": "4:14:42", "remaining_time": "2:55:04", "throughput": 1487.86, "total_tokens": 22737856} {"current_steps": 107745, "total_steps": 181800, "loss": 0.0028, "lr": 2.1291709859671488e-05, "epoch": 11.853135313531354, "percentage": 59.27, "elapsed_time": "4:14:42", "remaining_time": "2:55:04", "throughput": 1487.87, "total_tokens": 22738912} {"current_steps": 107750, "total_steps": 181800, "loss": 0.0455, "lr": 2.1289336359353045e-05, "epoch": 11.853685368536853, "percentage": 59.27, "elapsed_time": "4:14:43", "remaining_time": "2:55:03", "throughput": 1487.87, "total_tokens": 22740000} {"current_steps": 107755, "total_steps": 181800, "loss": 0.0134, "lr": 2.1286962893234014e-05, "epoch": 11.854235423542354, "percentage": 59.27, "elapsed_time": "4:14:44", "remaining_time": "2:55:02", "throughput": 1487.87, "total_tokens": 22741088} {"current_steps": 107760, "total_steps": 181800, "loss": 0.0204, "lr": 2.1284589461336254e-05, "epoch": 11.854785478547855, "percentage": 59.27, "elapsed_time": "4:14:44", "remaining_time": "2:55:02", "throughput": 1487.87, "total_tokens": 22742112} {"current_steps": 107765, "total_steps": 181800, "loss": 0.0584, "lr": 2.1282216063681656e-05, "epoch": 11.855335533553355, "percentage": 59.28, "elapsed_time": "4:14:45", "remaining_time": "2:55:01", "throughput": 1487.88, "total_tokens": 22743232} {"current_steps": 107770, "total_steps": 181800, "loss": 0.006, "lr": 2.1279842700292083e-05, "epoch": 11.855885588558856, "percentage": 59.28, "elapsed_time": "4:14:46", "remaining_time": "2:55:00", "throughput": 1487.88, "total_tokens": 22744288} {"current_steps": 107775, "total_steps": 181800, "loss": 0.0155, "lr": 2.1277469371189417e-05, "epoch": 11.856435643564357, "percentage": 59.28, "elapsed_time": "4:14:47", "remaining_time": "2:54:59", "throughput": 1487.88, "total_tokens": 22745248} {"current_steps": 107780, "total_steps": 181800, "loss": 0.0667, "lr": 2.127509607639554e-05, "epoch": 11.856985698569858, "percentage": 59.28, "elapsed_time": "4:14:47", "remaining_time": "2:54:59", "throughput": 1487.87, "total_tokens": 22746240} {"current_steps": 107785, "total_steps": 181800, "loss": 0.0078, "lr": 2.1272722815932304e-05, "epoch": 11.857535753575357, "percentage": 59.29, "elapsed_time": "4:14:48", "remaining_time": "2:54:58", "throughput": 1487.87, "total_tokens": 22747264} {"current_steps": 107790, "total_steps": 181800, "loss": 0.0919, "lr": 2.1270349589821594e-05, "epoch": 11.858085808580858, "percentage": 59.29, "elapsed_time": "4:14:49", "remaining_time": "2:54:57", "throughput": 1487.88, "total_tokens": 22748352} {"current_steps": 107795, "total_steps": 181800, "loss": 0.0968, "lr": 2.126797639808528e-05, "epoch": 11.85863586358636, "percentage": 59.29, "elapsed_time": "4:14:49", "remaining_time": "2:54:56", "throughput": 1487.88, "total_tokens": 22749408} {"current_steps": 107800, "total_steps": 181800, "loss": 0.0827, "lr": 2.1265603240745246e-05, "epoch": 11.859185918591859, "percentage": 59.3, "elapsed_time": "4:14:50", "remaining_time": "2:54:56", "throughput": 1487.88, "total_tokens": 22750432} {"current_steps": 107805, "total_steps": 181800, "loss": 0.0104, "lr": 2.1263230117823352e-05, "epoch": 11.85973597359736, "percentage": 59.3, "elapsed_time": "4:14:51", "remaining_time": "2:54:55", "throughput": 1487.88, "total_tokens": 22751488} {"current_steps": 107810, "total_steps": 181800, "loss": 0.0683, "lr": 2.1260857029341466e-05, "epoch": 11.86028602860286, "percentage": 59.3, "elapsed_time": "4:14:51", "remaining_time": "2:54:54", "throughput": 1487.88, "total_tokens": 22752544} {"current_steps": 107815, "total_steps": 181800, "loss": 0.0881, "lr": 2.1258483975321478e-05, "epoch": 11.86083608360836, "percentage": 59.3, "elapsed_time": "4:14:52", "remaining_time": "2:54:54", "throughput": 1487.88, "total_tokens": 22753600} {"current_steps": 107820, "total_steps": 181800, "loss": 0.0823, "lr": 2.1256110955785234e-05, "epoch": 11.861386138613861, "percentage": 59.31, "elapsed_time": "4:14:53", "remaining_time": "2:54:53", "throughput": 1487.89, "total_tokens": 22754656} {"current_steps": 107825, "total_steps": 181800, "loss": 0.0026, "lr": 2.125373797075463e-05, "epoch": 11.861936193619362, "percentage": 59.31, "elapsed_time": "4:14:53", "remaining_time": "2:54:52", "throughput": 1487.89, "total_tokens": 22755680} {"current_steps": 107830, "total_steps": 181800, "loss": 0.0111, "lr": 2.1251365020251527e-05, "epoch": 11.862486248624862, "percentage": 59.31, "elapsed_time": "4:14:54", "remaining_time": "2:54:51", "throughput": 1487.89, "total_tokens": 22756704} {"current_steps": 107835, "total_steps": 181800, "loss": 0.0168, "lr": 2.1248992104297776e-05, "epoch": 11.863036303630363, "percentage": 59.32, "elapsed_time": "4:14:55", "remaining_time": "2:54:51", "throughput": 1487.89, "total_tokens": 22757760} {"current_steps": 107840, "total_steps": 181800, "loss": 0.0102, "lr": 2.1246619222915283e-05, "epoch": 11.863586358635864, "percentage": 59.32, "elapsed_time": "4:14:56", "remaining_time": "2:54:50", "throughput": 1487.89, "total_tokens": 22758880} {"current_steps": 107845, "total_steps": 181800, "loss": 0.0161, "lr": 2.1244246376125893e-05, "epoch": 11.864136413641365, "percentage": 59.32, "elapsed_time": "4:14:56", "remaining_time": "2:54:49", "throughput": 1487.9, "total_tokens": 22759968} {"current_steps": 107850, "total_steps": 181800, "loss": 0.1047, "lr": 2.124187356395148e-05, "epoch": 11.864686468646864, "percentage": 59.32, "elapsed_time": "4:14:57", "remaining_time": "2:54:49", "throughput": 1487.9, "total_tokens": 22760992} {"current_steps": 107855, "total_steps": 181800, "loss": 0.0122, "lr": 2.1239500786413925e-05, "epoch": 11.865236523652365, "percentage": 59.33, "elapsed_time": "4:14:58", "remaining_time": "2:54:48", "throughput": 1487.9, "total_tokens": 22762016} {"current_steps": 107860, "total_steps": 181800, "loss": 0.0033, "lr": 2.1237128043535075e-05, "epoch": 11.865786578657866, "percentage": 59.33, "elapsed_time": "4:14:58", "remaining_time": "2:54:47", "throughput": 1487.9, "total_tokens": 22763104} {"current_steps": 107865, "total_steps": 181800, "loss": 0.0014, "lr": 2.1234755335336816e-05, "epoch": 11.866336633663366, "percentage": 59.33, "elapsed_time": "4:14:59", "remaining_time": "2:54:46", "throughput": 1487.9, "total_tokens": 22764096} {"current_steps": 107870, "total_steps": 181800, "loss": 0.1024, "lr": 2.1232382661841005e-05, "epoch": 11.866886688668867, "percentage": 59.33, "elapsed_time": "4:15:00", "remaining_time": "2:54:46", "throughput": 1487.9, "total_tokens": 22765184} {"current_steps": 107875, "total_steps": 181800, "loss": 0.0149, "lr": 2.1230010023069524e-05, "epoch": 11.867436743674368, "percentage": 59.34, "elapsed_time": "4:15:00", "remaining_time": "2:54:45", "throughput": 1487.9, "total_tokens": 22766208} {"current_steps": 107880, "total_steps": 181800, "loss": 0.0025, "lr": 2.122763741904423e-05, "epoch": 11.867986798679867, "percentage": 59.34, "elapsed_time": "4:15:01", "remaining_time": "2:54:44", "throughput": 1487.9, "total_tokens": 22767264} {"current_steps": 107885, "total_steps": 181800, "loss": 0.0397, "lr": 2.1225264849786983e-05, "epoch": 11.868536853685368, "percentage": 59.34, "elapsed_time": "4:15:02", "remaining_time": "2:54:44", "throughput": 1487.91, "total_tokens": 22768320} {"current_steps": 107890, "total_steps": 181800, "loss": 0.0272, "lr": 2.122289231531967e-05, "epoch": 11.86908690869087, "percentage": 59.35, "elapsed_time": "4:15:02", "remaining_time": "2:54:43", "throughput": 1487.91, "total_tokens": 22769344} {"current_steps": 107895, "total_steps": 181800, "loss": 0.1022, "lr": 2.122051981566413e-05, "epoch": 11.869636963696369, "percentage": 59.35, "elapsed_time": "4:15:03", "remaining_time": "2:54:42", "throughput": 1487.91, "total_tokens": 22770464} {"current_steps": 107900, "total_steps": 181800, "loss": 0.013, "lr": 2.121814735084226e-05, "epoch": 11.87018701870187, "percentage": 59.35, "elapsed_time": "4:15:04", "remaining_time": "2:54:41", "throughput": 1487.91, "total_tokens": 22771488} {"current_steps": 107905, "total_steps": 181800, "loss": 0.004, "lr": 2.1215774920875907e-05, "epoch": 11.870737073707371, "percentage": 59.35, "elapsed_time": "4:15:05", "remaining_time": "2:54:41", "throughput": 1487.91, "total_tokens": 22772544} {"current_steps": 107910, "total_steps": 181800, "loss": 0.0045, "lr": 2.1213402525786938e-05, "epoch": 11.871287128712872, "percentage": 59.36, "elapsed_time": "4:15:05", "remaining_time": "2:54:40", "throughput": 1487.92, "total_tokens": 22773600} {"current_steps": 107915, "total_steps": 181800, "loss": 0.0544, "lr": 2.1211030165597228e-05, "epoch": 11.871837183718371, "percentage": 59.36, "elapsed_time": "4:15:06", "remaining_time": "2:54:39", "throughput": 1487.92, "total_tokens": 22774656} {"current_steps": 107920, "total_steps": 181800, "loss": 0.0287, "lr": 2.120865784032863e-05, "epoch": 11.872387238723872, "percentage": 59.36, "elapsed_time": "4:15:07", "remaining_time": "2:54:38", "throughput": 1487.92, "total_tokens": 22775744} {"current_steps": 107925, "total_steps": 181800, "loss": 0.0026, "lr": 2.1206285550003012e-05, "epoch": 11.872937293729374, "percentage": 59.36, "elapsed_time": "4:15:07", "remaining_time": "2:54:38", "throughput": 1487.92, "total_tokens": 22776800} {"current_steps": 107930, "total_steps": 181800, "loss": 0.0552, "lr": 2.1203913294642248e-05, "epoch": 11.873487348734873, "percentage": 59.37, "elapsed_time": "4:15:08", "remaining_time": "2:54:37", "throughput": 1487.93, "total_tokens": 22777856} {"current_steps": 107935, "total_steps": 181800, "loss": 0.0236, "lr": 2.120154107426818e-05, "epoch": 11.874037403740374, "percentage": 59.37, "elapsed_time": "4:15:09", "remaining_time": "2:54:36", "throughput": 1487.92, "total_tokens": 22778848} {"current_steps": 107940, "total_steps": 181800, "loss": 0.0951, "lr": 2.119916888890269e-05, "epoch": 11.874587458745875, "percentage": 59.37, "elapsed_time": "4:15:09", "remaining_time": "2:54:36", "throughput": 1487.93, "total_tokens": 22779904} {"current_steps": 107945, "total_steps": 181800, "loss": 0.0049, "lr": 2.1196796738567647e-05, "epoch": 11.875137513751374, "percentage": 59.38, "elapsed_time": "4:15:10", "remaining_time": "2:54:35", "throughput": 1487.93, "total_tokens": 22780928} {"current_steps": 107950, "total_steps": 181800, "loss": 0.0026, "lr": 2.1194424623284892e-05, "epoch": 11.875687568756875, "percentage": 59.38, "elapsed_time": "4:15:11", "remaining_time": "2:54:34", "throughput": 1487.93, "total_tokens": 22781984} {"current_steps": 107955, "total_steps": 181800, "loss": 0.0103, "lr": 2.1192052543076304e-05, "epoch": 11.876237623762377, "percentage": 59.38, "elapsed_time": "4:15:11", "remaining_time": "2:54:33", "throughput": 1487.93, "total_tokens": 22783072} {"current_steps": 107960, "total_steps": 181800, "loss": 0.0056, "lr": 2.1189680497963734e-05, "epoch": 11.876787678767876, "percentage": 59.38, "elapsed_time": "4:15:12", "remaining_time": "2:54:33", "throughput": 1487.93, "total_tokens": 22784096} {"current_steps": 107965, "total_steps": 181800, "loss": 0.0145, "lr": 2.118730848796906e-05, "epoch": 11.877337733773377, "percentage": 59.39, "elapsed_time": "4:15:13", "remaining_time": "2:54:32", "throughput": 1487.94, "total_tokens": 22785216} {"current_steps": 107970, "total_steps": 181800, "loss": 0.0106, "lr": 2.118493651311413e-05, "epoch": 11.877887788778878, "percentage": 59.39, "elapsed_time": "4:15:13", "remaining_time": "2:54:31", "throughput": 1487.94, "total_tokens": 22786272} {"current_steps": 107975, "total_steps": 181800, "loss": 0.0126, "lr": 2.1182564573420805e-05, "epoch": 11.87843784378438, "percentage": 59.39, "elapsed_time": "4:15:14", "remaining_time": "2:54:30", "throughput": 1487.94, "total_tokens": 22787360} {"current_steps": 107980, "total_steps": 181800, "loss": 0.0043, "lr": 2.1180192668910957e-05, "epoch": 11.878987898789878, "percentage": 59.39, "elapsed_time": "4:15:15", "remaining_time": "2:54:30", "throughput": 1487.95, "total_tokens": 22788416} {"current_steps": 107985, "total_steps": 181800, "loss": 0.0071, "lr": 2.117782079960643e-05, "epoch": 11.87953795379538, "percentage": 59.4, "elapsed_time": "4:15:16", "remaining_time": "2:54:29", "throughput": 1487.95, "total_tokens": 22789440} {"current_steps": 107990, "total_steps": 181800, "loss": 0.0261, "lr": 2.117544896552911e-05, "epoch": 11.88008800880088, "percentage": 59.4, "elapsed_time": "4:15:16", "remaining_time": "2:54:28", "throughput": 1487.95, "total_tokens": 22790528} {"current_steps": 107995, "total_steps": 181800, "loss": 0.01, "lr": 2.1173077166700837e-05, "epoch": 11.88063806380638, "percentage": 59.4, "elapsed_time": "4:15:17", "remaining_time": "2:54:28", "throughput": 1487.95, "total_tokens": 22791584} {"current_steps": 108000, "total_steps": 181800, "loss": 0.0046, "lr": 2.117070540314347e-05, "epoch": 11.881188118811881, "percentage": 59.41, "elapsed_time": "4:15:18", "remaining_time": "2:54:27", "throughput": 1487.95, "total_tokens": 22792608} {"current_steps": 108005, "total_steps": 181800, "loss": 0.0034, "lr": 2.116833367487888e-05, "epoch": 11.881738173817382, "percentage": 59.41, "elapsed_time": "4:15:18", "remaining_time": "2:54:26", "throughput": 1487.96, "total_tokens": 22793696} {"current_steps": 108010, "total_steps": 181800, "loss": 0.0167, "lr": 2.116596198192891e-05, "epoch": 11.882288228822881, "percentage": 59.41, "elapsed_time": "4:15:19", "remaining_time": "2:54:25", "throughput": 1487.96, "total_tokens": 22794720} {"current_steps": 108015, "total_steps": 181800, "loss": 0.0039, "lr": 2.1163590324315435e-05, "epoch": 11.882838283828383, "percentage": 59.41, "elapsed_time": "4:15:20", "remaining_time": "2:54:25", "throughput": 1487.96, "total_tokens": 22795776} {"current_steps": 108020, "total_steps": 181800, "loss": 0.0284, "lr": 2.116121870206031e-05, "epoch": 11.883388338833884, "percentage": 59.42, "elapsed_time": "4:15:20", "remaining_time": "2:54:24", "throughput": 1487.96, "total_tokens": 22796896} {"current_steps": 108025, "total_steps": 181800, "loss": 0.0617, "lr": 2.115884711518538e-05, "epoch": 11.883938393839383, "percentage": 59.42, "elapsed_time": "4:15:21", "remaining_time": "2:54:23", "throughput": 1487.96, "total_tokens": 22797920} {"current_steps": 108030, "total_steps": 181800, "loss": 0.0227, "lr": 2.115647556371253e-05, "epoch": 11.884488448844884, "percentage": 59.42, "elapsed_time": "4:15:22", "remaining_time": "2:54:23", "throughput": 1487.97, "total_tokens": 22799040} {"current_steps": 108035, "total_steps": 181800, "loss": 0.0784, "lr": 2.1154104047663583e-05, "epoch": 11.885038503850385, "percentage": 59.43, "elapsed_time": "4:15:22", "remaining_time": "2:54:22", "throughput": 1487.97, "total_tokens": 22800128} {"current_steps": 108040, "total_steps": 181800, "loss": 0.0088, "lr": 2.1151732567060423e-05, "epoch": 11.885588558855886, "percentage": 59.43, "elapsed_time": "4:15:23", "remaining_time": "2:54:21", "throughput": 1487.98, "total_tokens": 22801216} {"current_steps": 108045, "total_steps": 181800, "loss": 0.0138, "lr": 2.1149361121924902e-05, "epoch": 11.886138613861386, "percentage": 59.43, "elapsed_time": "4:15:24", "remaining_time": "2:54:20", "throughput": 1487.98, "total_tokens": 22802336} {"current_steps": 108050, "total_steps": 181800, "loss": 0.0179, "lr": 2.114698971227886e-05, "epoch": 11.886688668866887, "percentage": 59.43, "elapsed_time": "4:15:25", "remaining_time": "2:54:20", "throughput": 1487.99, "total_tokens": 22803424} {"current_steps": 108055, "total_steps": 181800, "loss": 0.0125, "lr": 2.1144618338144172e-05, "epoch": 11.887238723872388, "percentage": 59.44, "elapsed_time": "4:15:25", "remaining_time": "2:54:19", "throughput": 1487.99, "total_tokens": 22804512} {"current_steps": 108060, "total_steps": 181800, "loss": 0.0052, "lr": 2.114224699954268e-05, "epoch": 11.887788778877887, "percentage": 59.44, "elapsed_time": "4:15:26", "remaining_time": "2:54:18", "throughput": 1488.0, "total_tokens": 22805632} {"current_steps": 108065, "total_steps": 181800, "loss": 0.0056, "lr": 2.113987569649626e-05, "epoch": 11.888338833883388, "percentage": 59.44, "elapsed_time": "4:15:27", "remaining_time": "2:54:17", "throughput": 1488.0, "total_tokens": 22806720} {"current_steps": 108070, "total_steps": 181800, "loss": 0.0388, "lr": 2.1137504429026745e-05, "epoch": 11.88888888888889, "percentage": 59.44, "elapsed_time": "4:15:27", "remaining_time": "2:54:17", "throughput": 1488.01, "total_tokens": 22807776} {"current_steps": 108075, "total_steps": 181800, "loss": 0.0047, "lr": 2.1135133197155992e-05, "epoch": 11.88943894389439, "percentage": 59.45, "elapsed_time": "4:15:28", "remaining_time": "2:54:16", "throughput": 1488.01, "total_tokens": 22808864} {"current_steps": 108080, "total_steps": 181800, "loss": 0.0705, "lr": 2.1132762000905866e-05, "epoch": 11.88998899889989, "percentage": 59.45, "elapsed_time": "4:15:29", "remaining_time": "2:54:15", "throughput": 1488.01, "total_tokens": 22809952} {"current_steps": 108085, "total_steps": 181800, "loss": 0.003, "lr": 2.1130390840298218e-05, "epoch": 11.89053905390539, "percentage": 59.45, "elapsed_time": "4:15:29", "remaining_time": "2:54:15", "throughput": 1488.02, "total_tokens": 22811072} {"current_steps": 108090, "total_steps": 181800, "loss": 0.0286, "lr": 2.1128019715354906e-05, "epoch": 11.891089108910892, "percentage": 59.46, "elapsed_time": "4:15:30", "remaining_time": "2:54:14", "throughput": 1488.02, "total_tokens": 22812160} {"current_steps": 108095, "total_steps": 181800, "loss": 0.0573, "lr": 2.1125648626097774e-05, "epoch": 11.891639163916391, "percentage": 59.46, "elapsed_time": "4:15:31", "remaining_time": "2:54:13", "throughput": 1488.03, "total_tokens": 22813280} {"current_steps": 108100, "total_steps": 181800, "loss": 0.0016, "lr": 2.1123277572548673e-05, "epoch": 11.892189218921892, "percentage": 59.46, "elapsed_time": "4:15:31", "remaining_time": "2:54:12", "throughput": 1488.03, "total_tokens": 22814336} {"current_steps": 108105, "total_steps": 181800, "loss": 0.0022, "lr": 2.1120906554729476e-05, "epoch": 11.892739273927393, "percentage": 59.46, "elapsed_time": "4:15:32", "remaining_time": "2:54:12", "throughput": 1488.03, "total_tokens": 22815360} {"current_steps": 108110, "total_steps": 181800, "loss": 0.0089, "lr": 2.111853557266201e-05, "epoch": 11.893289328932893, "percentage": 59.47, "elapsed_time": "4:15:33", "remaining_time": "2:54:11", "throughput": 1488.04, "total_tokens": 22816480} {"current_steps": 108115, "total_steps": 181800, "loss": 0.0726, "lr": 2.1116164626368147e-05, "epoch": 11.893839383938394, "percentage": 59.47, "elapsed_time": "4:15:33", "remaining_time": "2:54:10", "throughput": 1488.04, "total_tokens": 22817536} {"current_steps": 108120, "total_steps": 181800, "loss": 0.0037, "lr": 2.1113793715869735e-05, "epoch": 11.894389438943895, "percentage": 59.47, "elapsed_time": "4:15:34", "remaining_time": "2:54:10", "throughput": 1488.05, "total_tokens": 22818656} {"current_steps": 108125, "total_steps": 181800, "loss": 0.0012, "lr": 2.111142284118861e-05, "epoch": 11.894939493949394, "percentage": 59.47, "elapsed_time": "4:15:35", "remaining_time": "2:54:09", "throughput": 1488.05, "total_tokens": 22819712} {"current_steps": 108130, "total_steps": 181800, "loss": 0.0981, "lr": 2.1109052002346637e-05, "epoch": 11.895489548954895, "percentage": 59.48, "elapsed_time": "4:15:36", "remaining_time": "2:54:08", "throughput": 1488.05, "total_tokens": 22820704} {"current_steps": 108135, "total_steps": 181800, "loss": 0.0061, "lr": 2.1106681199365674e-05, "epoch": 11.896039603960396, "percentage": 59.48, "elapsed_time": "4:15:36", "remaining_time": "2:54:07", "throughput": 1488.05, "total_tokens": 22821760} {"current_steps": 108140, "total_steps": 181800, "loss": 0.0145, "lr": 2.1104310432267545e-05, "epoch": 11.896589658965897, "percentage": 59.48, "elapsed_time": "4:15:37", "remaining_time": "2:54:07", "throughput": 1488.05, "total_tokens": 22822784} {"current_steps": 108145, "total_steps": 181800, "loss": 0.004, "lr": 2.1101939701074133e-05, "epoch": 11.897139713971397, "percentage": 59.49, "elapsed_time": "4:15:38", "remaining_time": "2:54:06", "throughput": 1488.05, "total_tokens": 22823776} {"current_steps": 108150, "total_steps": 181800, "loss": 0.0103, "lr": 2.1099569005807264e-05, "epoch": 11.897689768976898, "percentage": 59.49, "elapsed_time": "4:15:38", "remaining_time": "2:54:05", "throughput": 1488.05, "total_tokens": 22824800} {"current_steps": 108155, "total_steps": 181800, "loss": 0.0045, "lr": 2.1097198346488798e-05, "epoch": 11.898239823982399, "percentage": 59.49, "elapsed_time": "4:15:39", "remaining_time": "2:54:04", "throughput": 1488.05, "total_tokens": 22825856} {"current_steps": 108160, "total_steps": 181800, "loss": 0.0368, "lr": 2.109482772314059e-05, "epoch": 11.898789878987898, "percentage": 59.49, "elapsed_time": "4:15:40", "remaining_time": "2:54:04", "throughput": 1488.04, "total_tokens": 22826816} {"current_steps": 108165, "total_steps": 181800, "loss": 0.0877, "lr": 2.1092457135784468e-05, "epoch": 11.8993399339934, "percentage": 59.5, "elapsed_time": "4:15:40", "remaining_time": "2:54:03", "throughput": 1488.05, "total_tokens": 22827904} {"current_steps": 108170, "total_steps": 181800, "loss": 0.0046, "lr": 2.10900865844423e-05, "epoch": 11.8998899889989, "percentage": 59.5, "elapsed_time": "4:15:41", "remaining_time": "2:54:02", "throughput": 1488.05, "total_tokens": 22829024} {"current_steps": 108175, "total_steps": 181800, "loss": 0.0034, "lr": 2.1087716069135922e-05, "epoch": 11.9004400440044, "percentage": 59.5, "elapsed_time": "4:15:42", "remaining_time": "2:54:02", "throughput": 1488.05, "total_tokens": 22830048} {"current_steps": 108180, "total_steps": 181800, "loss": 0.0049, "lr": 2.1085345589887198e-05, "epoch": 11.900990099009901, "percentage": 59.5, "elapsed_time": "4:15:42", "remaining_time": "2:54:01", "throughput": 1488.05, "total_tokens": 22831104} {"current_steps": 108185, "total_steps": 181800, "loss": 0.1057, "lr": 2.108297514671796e-05, "epoch": 11.901540154015402, "percentage": 59.51, "elapsed_time": "4:15:43", "remaining_time": "2:54:00", "throughput": 1488.05, "total_tokens": 22832128} {"current_steps": 108190, "total_steps": 181800, "loss": 0.0028, "lr": 2.1080604739650058e-05, "epoch": 11.902090209020901, "percentage": 59.51, "elapsed_time": "4:15:44", "remaining_time": "2:53:59", "throughput": 1488.06, "total_tokens": 22833184} {"current_steps": 108195, "total_steps": 181800, "loss": 0.079, "lr": 2.1078234368705348e-05, "epoch": 11.902640264026402, "percentage": 59.51, "elapsed_time": "4:15:44", "remaining_time": "2:53:59", "throughput": 1488.06, "total_tokens": 22834208} {"current_steps": 108200, "total_steps": 181800, "loss": 0.0138, "lr": 2.1075864033905656e-05, "epoch": 11.903190319031903, "percentage": 59.52, "elapsed_time": "4:15:45", "remaining_time": "2:53:58", "throughput": 1488.07, "total_tokens": 22835360} {"current_steps": 108205, "total_steps": 181800, "loss": 0.0364, "lr": 2.107349373527286e-05, "epoch": 11.903740374037405, "percentage": 59.52, "elapsed_time": "4:15:46", "remaining_time": "2:53:57", "throughput": 1488.07, "total_tokens": 22836384} {"current_steps": 108210, "total_steps": 181800, "loss": 0.041, "lr": 2.107112347282878e-05, "epoch": 11.904290429042904, "percentage": 59.52, "elapsed_time": "4:15:47", "remaining_time": "2:53:57", "throughput": 1488.06, "total_tokens": 22837376} {"current_steps": 108215, "total_steps": 181800, "loss": 0.0069, "lr": 2.1068753246595267e-05, "epoch": 11.904840484048405, "percentage": 59.52, "elapsed_time": "4:15:47", "remaining_time": "2:53:56", "throughput": 1488.06, "total_tokens": 22838400} {"current_steps": 108220, "total_steps": 181800, "loss": 0.0513, "lr": 2.1066383056594177e-05, "epoch": 11.905390539053906, "percentage": 59.53, "elapsed_time": "4:15:48", "remaining_time": "2:53:55", "throughput": 1488.07, "total_tokens": 22839552} {"current_steps": 108225, "total_steps": 181800, "loss": 0.0032, "lr": 2.1064012902847336e-05, "epoch": 11.905940594059405, "percentage": 59.53, "elapsed_time": "4:15:49", "remaining_time": "2:53:54", "throughput": 1488.07, "total_tokens": 22840608} {"current_steps": 108230, "total_steps": 181800, "loss": 0.0392, "lr": 2.1061642785376606e-05, "epoch": 11.906490649064907, "percentage": 59.53, "elapsed_time": "4:15:49", "remaining_time": "2:53:54", "throughput": 1488.08, "total_tokens": 22841696} {"current_steps": 108235, "total_steps": 181800, "loss": 0.0205, "lr": 2.105927270420383e-05, "epoch": 11.907040704070408, "percentage": 59.54, "elapsed_time": "4:15:50", "remaining_time": "2:53:53", "throughput": 1488.08, "total_tokens": 22842752} {"current_steps": 108240, "total_steps": 181800, "loss": 0.0963, "lr": 2.1056902659350836e-05, "epoch": 11.907590759075907, "percentage": 59.54, "elapsed_time": "4:15:51", "remaining_time": "2:53:52", "throughput": 1488.08, "total_tokens": 22843808} {"current_steps": 108245, "total_steps": 181800, "loss": 0.001, "lr": 2.1054532650839484e-05, "epoch": 11.908140814081408, "percentage": 59.54, "elapsed_time": "4:15:51", "remaining_time": "2:53:51", "throughput": 1488.08, "total_tokens": 22844864} {"current_steps": 108250, "total_steps": 181800, "loss": 0.0458, "lr": 2.1052162678691604e-05, "epoch": 11.908690869086909, "percentage": 59.54, "elapsed_time": "4:15:52", "remaining_time": "2:53:51", "throughput": 1488.08, "total_tokens": 22845888} {"current_steps": 108255, "total_steps": 181800, "loss": 0.1, "lr": 2.104979274292906e-05, "epoch": 11.909240924092408, "percentage": 59.55, "elapsed_time": "4:15:53", "remaining_time": "2:53:50", "throughput": 1488.09, "total_tokens": 22846944} {"current_steps": 108260, "total_steps": 181800, "loss": 0.0256, "lr": 2.1047422843573673e-05, "epoch": 11.90979097909791, "percentage": 59.55, "elapsed_time": "4:15:53", "remaining_time": "2:53:49", "throughput": 1488.09, "total_tokens": 22848000} {"current_steps": 108265, "total_steps": 181800, "loss": 0.0943, "lr": 2.1045052980647287e-05, "epoch": 11.91034103410341, "percentage": 59.55, "elapsed_time": "4:15:54", "remaining_time": "2:53:49", "throughput": 1488.09, "total_tokens": 22849056} {"current_steps": 108270, "total_steps": 181800, "loss": 0.0089, "lr": 2.1042683154171754e-05, "epoch": 11.910891089108912, "percentage": 59.55, "elapsed_time": "4:15:55", "remaining_time": "2:53:48", "throughput": 1488.1, "total_tokens": 22850176} {"current_steps": 108275, "total_steps": 181800, "loss": 0.0067, "lr": 2.104031336416891e-05, "epoch": 11.911441144114411, "percentage": 59.56, "elapsed_time": "4:15:56", "remaining_time": "2:53:47", "throughput": 1488.09, "total_tokens": 22851136} {"current_steps": 108280, "total_steps": 181800, "loss": 0.0451, "lr": 2.1037943610660605e-05, "epoch": 11.911991199119912, "percentage": 59.56, "elapsed_time": "4:15:56", "remaining_time": "2:53:46", "throughput": 1488.09, "total_tokens": 22852192} {"current_steps": 108285, "total_steps": 181800, "loss": 0.0961, "lr": 2.1035573893668672e-05, "epoch": 11.912541254125413, "percentage": 59.56, "elapsed_time": "4:15:57", "remaining_time": "2:53:46", "throughput": 1488.1, "total_tokens": 22853280} {"current_steps": 108290, "total_steps": 181800, "loss": 0.0018, "lr": 2.1033204213214945e-05, "epoch": 11.913091309130913, "percentage": 59.57, "elapsed_time": "4:15:58", "remaining_time": "2:53:45", "throughput": 1488.1, "total_tokens": 22854304} {"current_steps": 108295, "total_steps": 181800, "loss": 0.0124, "lr": 2.1030834569321278e-05, "epoch": 11.913641364136414, "percentage": 59.57, "elapsed_time": "4:15:58", "remaining_time": "2:53:44", "throughput": 1488.09, "total_tokens": 22855296} {"current_steps": 108300, "total_steps": 181800, "loss": 0.0239, "lr": 2.1028464962009496e-05, "epoch": 11.914191419141915, "percentage": 59.57, "elapsed_time": "4:15:59", "remaining_time": "2:53:44", "throughput": 1488.09, "total_tokens": 22856320} {"current_steps": 108305, "total_steps": 181800, "loss": 0.0836, "lr": 2.1026095391301454e-05, "epoch": 11.914741474147414, "percentage": 59.57, "elapsed_time": "4:16:00", "remaining_time": "2:53:43", "throughput": 1488.1, "total_tokens": 22857376} {"current_steps": 108310, "total_steps": 181800, "loss": 0.1208, "lr": 2.1023725857218988e-05, "epoch": 11.915291529152915, "percentage": 59.58, "elapsed_time": "4:16:00", "remaining_time": "2:53:42", "throughput": 1488.1, "total_tokens": 22858464} {"current_steps": 108315, "total_steps": 181800, "loss": 0.0732, "lr": 2.1021356359783917e-05, "epoch": 11.915841584158416, "percentage": 59.58, "elapsed_time": "4:16:01", "remaining_time": "2:53:41", "throughput": 1488.1, "total_tokens": 22859520} {"current_steps": 108320, "total_steps": 181800, "loss": 0.0124, "lr": 2.1018986899018112e-05, "epoch": 11.916391639163916, "percentage": 59.58, "elapsed_time": "4:16:02", "remaining_time": "2:53:41", "throughput": 1488.1, "total_tokens": 22860544} {"current_steps": 108325, "total_steps": 181800, "loss": 0.0022, "lr": 2.1016617474943386e-05, "epoch": 11.916941694169417, "percentage": 59.58, "elapsed_time": "4:16:02", "remaining_time": "2:53:40", "throughput": 1488.1, "total_tokens": 22861568} {"current_steps": 108330, "total_steps": 181800, "loss": 0.0146, "lr": 2.101424808758158e-05, "epoch": 11.917491749174918, "percentage": 59.59, "elapsed_time": "4:16:03", "remaining_time": "2:53:39", "throughput": 1488.1, "total_tokens": 22862592} {"current_steps": 108335, "total_steps": 181800, "loss": 0.0241, "lr": 2.1011878736954552e-05, "epoch": 11.918041804180419, "percentage": 59.59, "elapsed_time": "4:16:04", "remaining_time": "2:53:38", "throughput": 1488.1, "total_tokens": 22863648} {"current_steps": 108340, "total_steps": 181800, "loss": 0.0032, "lr": 2.1009509423084108e-05, "epoch": 11.918591859185918, "percentage": 59.59, "elapsed_time": "4:16:04", "remaining_time": "2:53:38", "throughput": 1488.11, "total_tokens": 22864768} {"current_steps": 108345, "total_steps": 181800, "loss": 0.1305, "lr": 2.100714014599211e-05, "epoch": 11.91914191419142, "percentage": 59.6, "elapsed_time": "4:16:05", "remaining_time": "2:53:37", "throughput": 1488.11, "total_tokens": 22865856} {"current_steps": 108350, "total_steps": 181800, "loss": 0.0569, "lr": 2.1004770905700388e-05, "epoch": 11.91969196919692, "percentage": 59.6, "elapsed_time": "4:16:06", "remaining_time": "2:53:36", "throughput": 1488.11, "total_tokens": 22866880} {"current_steps": 108355, "total_steps": 181800, "loss": 0.0031, "lr": 2.1002401702230768e-05, "epoch": 11.92024202420242, "percentage": 59.6, "elapsed_time": "4:16:07", "remaining_time": "2:53:36", "throughput": 1488.11, "total_tokens": 22867872} {"current_steps": 108360, "total_steps": 181800, "loss": 0.0042, "lr": 2.1000032535605095e-05, "epoch": 11.92079207920792, "percentage": 59.6, "elapsed_time": "4:16:07", "remaining_time": "2:53:35", "throughput": 1488.11, "total_tokens": 22868896} {"current_steps": 108365, "total_steps": 181800, "loss": 0.004, "lr": 2.0997663405845204e-05, "epoch": 11.921342134213422, "percentage": 59.61, "elapsed_time": "4:16:08", "remaining_time": "2:53:34", "throughput": 1488.12, "total_tokens": 22869984} {"current_steps": 108370, "total_steps": 181800, "loss": 0.1241, "lr": 2.0995294312972933e-05, "epoch": 11.921892189218921, "percentage": 59.61, "elapsed_time": "4:16:09", "remaining_time": "2:53:33", "throughput": 1488.12, "total_tokens": 22871040} {"current_steps": 108375, "total_steps": 181800, "loss": 0.017, "lr": 2.099292525701011e-05, "epoch": 11.922442244224422, "percentage": 59.61, "elapsed_time": "4:16:09", "remaining_time": "2:53:33", "throughput": 1488.12, "total_tokens": 22872128} {"current_steps": 108380, "total_steps": 181800, "loss": 0.003, "lr": 2.0990556237978563e-05, "epoch": 11.922992299229923, "percentage": 59.61, "elapsed_time": "4:16:10", "remaining_time": "2:53:32", "throughput": 1488.12, "total_tokens": 22873184} {"current_steps": 108385, "total_steps": 181800, "loss": 0.0012, "lr": 2.0988187255900144e-05, "epoch": 11.923542354235423, "percentage": 59.62, "elapsed_time": "4:16:11", "remaining_time": "2:53:31", "throughput": 1488.13, "total_tokens": 22874240} {"current_steps": 108390, "total_steps": 181800, "loss": 0.0124, "lr": 2.0985818310796674e-05, "epoch": 11.924092409240924, "percentage": 59.62, "elapsed_time": "4:16:11", "remaining_time": "2:53:30", "throughput": 1488.13, "total_tokens": 22875392} {"current_steps": 108395, "total_steps": 181800, "loss": 0.0087, "lr": 2.0983449402689997e-05, "epoch": 11.924642464246425, "percentage": 59.62, "elapsed_time": "4:16:12", "remaining_time": "2:53:30", "throughput": 1488.13, "total_tokens": 22876384} {"current_steps": 108400, "total_steps": 181800, "loss": 0.0112, "lr": 2.0981080531601937e-05, "epoch": 11.925192519251926, "percentage": 59.63, "elapsed_time": "4:16:13", "remaining_time": "2:53:29", "throughput": 1488.14, "total_tokens": 22877440} {"current_steps": 108405, "total_steps": 181800, "loss": 0.0024, "lr": 2.0978711697554322e-05, "epoch": 11.925742574257425, "percentage": 59.63, "elapsed_time": "4:16:13", "remaining_time": "2:53:28", "throughput": 1488.14, "total_tokens": 22878528} {"current_steps": 108410, "total_steps": 181800, "loss": 0.0243, "lr": 2.0976342900569007e-05, "epoch": 11.926292629262926, "percentage": 59.63, "elapsed_time": "4:16:14", "remaining_time": "2:53:28", "throughput": 1488.14, "total_tokens": 22879584} {"current_steps": 108415, "total_steps": 181800, "loss": 0.0065, "lr": 2.0973974140667793e-05, "epoch": 11.926842684268427, "percentage": 59.63, "elapsed_time": "4:16:15", "remaining_time": "2:53:27", "throughput": 1488.14, "total_tokens": 22880640} {"current_steps": 108420, "total_steps": 181800, "loss": 0.0062, "lr": 2.0971605417872535e-05, "epoch": 11.927392739273927, "percentage": 59.64, "elapsed_time": "4:16:15", "remaining_time": "2:53:26", "throughput": 1488.15, "total_tokens": 22881696} {"current_steps": 108425, "total_steps": 181800, "loss": 0.005, "lr": 2.0969236732205062e-05, "epoch": 11.927942794279428, "percentage": 59.64, "elapsed_time": "4:16:16", "remaining_time": "2:53:25", "throughput": 1488.15, "total_tokens": 22882848} {"current_steps": 108430, "total_steps": 181800, "loss": 0.0072, "lr": 2.096686808368719e-05, "epoch": 11.928492849284929, "percentage": 59.64, "elapsed_time": "4:16:17", "remaining_time": "2:53:25", "throughput": 1488.16, "total_tokens": 22884032} {"current_steps": 108435, "total_steps": 181800, "loss": 0.0044, "lr": 2.0964499472340763e-05, "epoch": 11.929042904290428, "percentage": 59.65, "elapsed_time": "4:16:18", "remaining_time": "2:53:24", "throughput": 1488.17, "total_tokens": 22885088} {"current_steps": 108440, "total_steps": 181800, "loss": 0.0045, "lr": 2.0962130898187604e-05, "epoch": 11.92959295929593, "percentage": 59.65, "elapsed_time": "4:16:18", "remaining_time": "2:53:23", "throughput": 1488.16, "total_tokens": 22886080} {"current_steps": 108445, "total_steps": 181800, "loss": 0.078, "lr": 2.0959762361249552e-05, "epoch": 11.93014301430143, "percentage": 59.65, "elapsed_time": "4:16:19", "remaining_time": "2:53:23", "throughput": 1488.16, "total_tokens": 22887136} {"current_steps": 108450, "total_steps": 181800, "loss": 0.0457, "lr": 2.0957393861548437e-05, "epoch": 11.930693069306932, "percentage": 59.65, "elapsed_time": "4:16:20", "remaining_time": "2:53:22", "throughput": 1488.16, "total_tokens": 22888160} {"current_steps": 108455, "total_steps": 181800, "loss": 0.0518, "lr": 2.0955025399106072e-05, "epoch": 11.93124312431243, "percentage": 59.66, "elapsed_time": "4:16:20", "remaining_time": "2:53:21", "throughput": 1488.16, "total_tokens": 22889152} {"current_steps": 108460, "total_steps": 181800, "loss": 0.043, "lr": 2.09526569739443e-05, "epoch": 11.931793179317932, "percentage": 59.66, "elapsed_time": "4:16:21", "remaining_time": "2:53:20", "throughput": 1488.17, "total_tokens": 22890240} {"current_steps": 108465, "total_steps": 181800, "loss": 0.002, "lr": 2.0950288586084945e-05, "epoch": 11.932343234323433, "percentage": 59.66, "elapsed_time": "4:16:22", "remaining_time": "2:53:20", "throughput": 1488.17, "total_tokens": 22891328} {"current_steps": 108470, "total_steps": 181800, "loss": 0.0039, "lr": 2.094792023554985e-05, "epoch": 11.932893289328932, "percentage": 59.66, "elapsed_time": "4:16:22", "remaining_time": "2:53:19", "throughput": 1488.17, "total_tokens": 22892384} {"current_steps": 108475, "total_steps": 181800, "loss": 0.0064, "lr": 2.0945551922360818e-05, "epoch": 11.933443344334433, "percentage": 59.67, "elapsed_time": "4:16:23", "remaining_time": "2:53:18", "throughput": 1488.18, "total_tokens": 22893472} {"current_steps": 108480, "total_steps": 181800, "loss": 0.0144, "lr": 2.0943183646539686e-05, "epoch": 11.933993399339935, "percentage": 59.67, "elapsed_time": "4:16:24", "remaining_time": "2:53:17", "throughput": 1488.18, "total_tokens": 22894496} {"current_steps": 108485, "total_steps": 181800, "loss": 0.0269, "lr": 2.0940815408108293e-05, "epoch": 11.934543454345434, "percentage": 59.67, "elapsed_time": "4:16:24", "remaining_time": "2:53:17", "throughput": 1488.18, "total_tokens": 22895584} {"current_steps": 108490, "total_steps": 181800, "loss": 0.0012, "lr": 2.0938447207088447e-05, "epoch": 11.935093509350935, "percentage": 59.68, "elapsed_time": "4:16:25", "remaining_time": "2:53:16", "throughput": 1488.18, "total_tokens": 22896608} {"current_steps": 108495, "total_steps": 181800, "loss": 0.0102, "lr": 2.093607904350199e-05, "epoch": 11.935643564356436, "percentage": 59.68, "elapsed_time": "4:16:26", "remaining_time": "2:53:15", "throughput": 1488.18, "total_tokens": 22897664} {"current_steps": 108500, "total_steps": 181800, "loss": 0.012, "lr": 2.0933710917370746e-05, "epoch": 11.936193619361937, "percentage": 59.68, "elapsed_time": "4:16:27", "remaining_time": "2:53:15", "throughput": 1488.18, "total_tokens": 22898688} {"current_steps": 108505, "total_steps": 181800, "loss": 0.0759, "lr": 2.0931342828716523e-05, "epoch": 11.936743674367436, "percentage": 59.68, "elapsed_time": "4:16:27", "remaining_time": "2:53:14", "throughput": 1488.18, "total_tokens": 22899712} {"current_steps": 108510, "total_steps": 181800, "loss": 0.1734, "lr": 2.0928974777561176e-05, "epoch": 11.937293729372938, "percentage": 59.69, "elapsed_time": "4:16:28", "remaining_time": "2:53:13", "throughput": 1488.19, "total_tokens": 22900800} {"current_steps": 108515, "total_steps": 181800, "loss": 0.0095, "lr": 2.0926606763926513e-05, "epoch": 11.937843784378439, "percentage": 59.69, "elapsed_time": "4:16:29", "remaining_time": "2:53:12", "throughput": 1488.18, "total_tokens": 22901792} {"current_steps": 108520, "total_steps": 181800, "loss": 0.0215, "lr": 2.0924238787834353e-05, "epoch": 11.938393839383938, "percentage": 59.69, "elapsed_time": "4:16:29", "remaining_time": "2:53:12", "throughput": 1488.18, "total_tokens": 22902816} {"current_steps": 108525, "total_steps": 181800, "loss": 0.0012, "lr": 2.0921870849306534e-05, "epoch": 11.938943894389439, "percentage": 59.69, "elapsed_time": "4:16:30", "remaining_time": "2:53:11", "throughput": 1488.19, "total_tokens": 22903872} {"current_steps": 108530, "total_steps": 181800, "loss": 0.0167, "lr": 2.091950294836487e-05, "epoch": 11.93949394939494, "percentage": 59.7, "elapsed_time": "4:16:31", "remaining_time": "2:53:10", "throughput": 1488.19, "total_tokens": 22904896} {"current_steps": 108535, "total_steps": 181800, "loss": 0.0021, "lr": 2.0917135085031194e-05, "epoch": 11.94004400440044, "percentage": 59.7, "elapsed_time": "4:16:31", "remaining_time": "2:53:10", "throughput": 1488.19, "total_tokens": 22905952} {"current_steps": 108540, "total_steps": 181800, "loss": 0.1741, "lr": 2.0914767259327327e-05, "epoch": 11.94059405940594, "percentage": 59.7, "elapsed_time": "4:16:32", "remaining_time": "2:53:09", "throughput": 1488.19, "total_tokens": 22907008} {"current_steps": 108545, "total_steps": 181800, "loss": 0.0512, "lr": 2.0912399471275085e-05, "epoch": 11.941144114411442, "percentage": 59.71, "elapsed_time": "4:16:33", "remaining_time": "2:53:08", "throughput": 1488.19, "total_tokens": 22908064} {"current_steps": 108550, "total_steps": 181800, "loss": 0.069, "lr": 2.0910031720896293e-05, "epoch": 11.941694169416941, "percentage": 59.71, "elapsed_time": "4:16:33", "remaining_time": "2:53:07", "throughput": 1488.19, "total_tokens": 22909088} {"current_steps": 108555, "total_steps": 181800, "loss": 0.0122, "lr": 2.090766400821278e-05, "epoch": 11.942244224422442, "percentage": 59.71, "elapsed_time": "4:16:34", "remaining_time": "2:53:07", "throughput": 1488.19, "total_tokens": 22910144} {"current_steps": 108560, "total_steps": 181800, "loss": 0.0316, "lr": 2.0905296333246363e-05, "epoch": 11.942794279427943, "percentage": 59.71, "elapsed_time": "4:16:35", "remaining_time": "2:53:06", "throughput": 1488.19, "total_tokens": 22911136} {"current_steps": 108565, "total_steps": 181800, "loss": 0.0367, "lr": 2.090292869601887e-05, "epoch": 11.943344334433444, "percentage": 59.72, "elapsed_time": "4:16:35", "remaining_time": "2:53:05", "throughput": 1488.19, "total_tokens": 22912160} {"current_steps": 108570, "total_steps": 181800, "loss": 0.0058, "lr": 2.090056109655211e-05, "epoch": 11.943894389438944, "percentage": 59.72, "elapsed_time": "4:16:36", "remaining_time": "2:53:04", "throughput": 1488.2, "total_tokens": 22913248} {"current_steps": 108575, "total_steps": 181800, "loss": 0.0274, "lr": 2.0898193534867916e-05, "epoch": 11.944444444444445, "percentage": 59.72, "elapsed_time": "4:16:37", "remaining_time": "2:53:04", "throughput": 1488.2, "total_tokens": 22914272} {"current_steps": 108580, "total_steps": 181800, "loss": 0.0054, "lr": 2.0895826010988096e-05, "epoch": 11.944994499449946, "percentage": 59.72, "elapsed_time": "4:16:38", "remaining_time": "2:53:03", "throughput": 1488.2, "total_tokens": 22915328} {"current_steps": 108585, "total_steps": 181800, "loss": 0.0088, "lr": 2.089345852493449e-05, "epoch": 11.945544554455445, "percentage": 59.73, "elapsed_time": "4:16:38", "remaining_time": "2:53:02", "throughput": 1488.2, "total_tokens": 22916384} {"current_steps": 108590, "total_steps": 181800, "loss": 0.0243, "lr": 2.0891091076728902e-05, "epoch": 11.946094609460946, "percentage": 59.73, "elapsed_time": "4:16:39", "remaining_time": "2:53:02", "throughput": 1488.2, "total_tokens": 22917440} {"current_steps": 108595, "total_steps": 181800, "loss": 0.0286, "lr": 2.088872366639315e-05, "epoch": 11.946644664466447, "percentage": 59.73, "elapsed_time": "4:16:40", "remaining_time": "2:53:01", "throughput": 1488.21, "total_tokens": 22918528} {"current_steps": 108600, "total_steps": 181800, "loss": 0.002, "lr": 2.088635629394907e-05, "epoch": 11.947194719471947, "percentage": 59.74, "elapsed_time": "4:16:40", "remaining_time": "2:53:00", "throughput": 1488.21, "total_tokens": 22919552} {"current_steps": 108605, "total_steps": 181800, "loss": 0.0062, "lr": 2.088398895941846e-05, "epoch": 11.947744774477448, "percentage": 59.74, "elapsed_time": "4:16:41", "remaining_time": "2:52:59", "throughput": 1488.21, "total_tokens": 22920640} {"current_steps": 108610, "total_steps": 181800, "loss": 0.0111, "lr": 2.0881621662823154e-05, "epoch": 11.948294829482949, "percentage": 59.74, "elapsed_time": "4:16:42", "remaining_time": "2:52:59", "throughput": 1488.22, "total_tokens": 22921760} {"current_steps": 108615, "total_steps": 181800, "loss": 0.0502, "lr": 2.0879254404184965e-05, "epoch": 11.948844884488448, "percentage": 59.74, "elapsed_time": "4:16:42", "remaining_time": "2:52:58", "throughput": 1488.22, "total_tokens": 22922848} {"current_steps": 108620, "total_steps": 181800, "loss": 0.0093, "lr": 2.0876887183525705e-05, "epoch": 11.94939493949395, "percentage": 59.75, "elapsed_time": "4:16:43", "remaining_time": "2:52:57", "throughput": 1488.22, "total_tokens": 22923840} {"current_steps": 108625, "total_steps": 181800, "loss": 0.0246, "lr": 2.0874520000867205e-05, "epoch": 11.94994499449945, "percentage": 59.75, "elapsed_time": "4:16:44", "remaining_time": "2:52:57", "throughput": 1488.22, "total_tokens": 22924864} {"current_steps": 108630, "total_steps": 181800, "loss": 0.0246, "lr": 2.0872152856231266e-05, "epoch": 11.950495049504951, "percentage": 59.75, "elapsed_time": "4:16:44", "remaining_time": "2:52:56", "throughput": 1488.22, "total_tokens": 22925856} {"current_steps": 108635, "total_steps": 181800, "loss": 0.1338, "lr": 2.086978574963972e-05, "epoch": 11.95104510451045, "percentage": 59.76, "elapsed_time": "4:16:45", "remaining_time": "2:52:55", "throughput": 1488.22, "total_tokens": 22926944} {"current_steps": 108640, "total_steps": 181800, "loss": 0.0009, "lr": 2.086741868111438e-05, "epoch": 11.951595159515952, "percentage": 59.76, "elapsed_time": "4:16:46", "remaining_time": "2:52:54", "throughput": 1488.22, "total_tokens": 22928032} {"current_steps": 108645, "total_steps": 181800, "loss": 0.0047, "lr": 2.0865051650677053e-05, "epoch": 11.952145214521453, "percentage": 59.76, "elapsed_time": "4:16:46", "remaining_time": "2:52:54", "throughput": 1488.23, "total_tokens": 22929120} {"current_steps": 108650, "total_steps": 181800, "loss": 0.0012, "lr": 2.0862684658349564e-05, "epoch": 11.952695269526952, "percentage": 59.76, "elapsed_time": "4:16:47", "remaining_time": "2:52:53", "throughput": 1488.23, "total_tokens": 22930208} {"current_steps": 108655, "total_steps": 181800, "loss": 0.0454, "lr": 2.0860317704153716e-05, "epoch": 11.953245324532453, "percentage": 59.77, "elapsed_time": "4:16:48", "remaining_time": "2:52:52", "throughput": 1488.24, "total_tokens": 22931296} {"current_steps": 108660, "total_steps": 181800, "loss": 0.0987, "lr": 2.085795078811135e-05, "epoch": 11.953795379537954, "percentage": 59.77, "elapsed_time": "4:16:49", "remaining_time": "2:52:51", "throughput": 1488.24, "total_tokens": 22932384} {"current_steps": 108665, "total_steps": 181800, "loss": 0.0034, "lr": 2.0855583910244252e-05, "epoch": 11.954345434543454, "percentage": 59.77, "elapsed_time": "4:16:49", "remaining_time": "2:52:51", "throughput": 1488.24, "total_tokens": 22933408} {"current_steps": 108670, "total_steps": 181800, "loss": 0.0294, "lr": 2.085321707057425e-05, "epoch": 11.954895489548955, "percentage": 59.77, "elapsed_time": "4:16:50", "remaining_time": "2:52:50", "throughput": 1488.24, "total_tokens": 22934496} {"current_steps": 108675, "total_steps": 181800, "loss": 0.003, "lr": 2.085085026912316e-05, "epoch": 11.955445544554456, "percentage": 59.78, "elapsed_time": "4:16:51", "remaining_time": "2:52:49", "throughput": 1488.25, "total_tokens": 22935584} {"current_steps": 108680, "total_steps": 181800, "loss": 0.001, "lr": 2.084848350591278e-05, "epoch": 11.955995599559955, "percentage": 59.78, "elapsed_time": "4:16:51", "remaining_time": "2:52:49", "throughput": 1488.25, "total_tokens": 22936640} {"current_steps": 108685, "total_steps": 181800, "loss": 0.0023, "lr": 2.0846116780964954e-05, "epoch": 11.956545654565456, "percentage": 59.78, "elapsed_time": "4:16:52", "remaining_time": "2:52:48", "throughput": 1488.25, "total_tokens": 22937696} {"current_steps": 108690, "total_steps": 181800, "loss": 0.0905, "lr": 2.0843750094301467e-05, "epoch": 11.957095709570957, "percentage": 59.79, "elapsed_time": "4:16:53", "remaining_time": "2:52:47", "throughput": 1488.25, "total_tokens": 22938752} {"current_steps": 108695, "total_steps": 181800, "loss": 0.0041, "lr": 2.084138344594414e-05, "epoch": 11.957645764576458, "percentage": 59.79, "elapsed_time": "4:16:53", "remaining_time": "2:52:46", "throughput": 1488.26, "total_tokens": 22939808} {"current_steps": 108700, "total_steps": 181800, "loss": 0.0056, "lr": 2.083901683591479e-05, "epoch": 11.958195819581958, "percentage": 59.79, "elapsed_time": "4:16:54", "remaining_time": "2:52:46", "throughput": 1488.26, "total_tokens": 22940832} {"current_steps": 108705, "total_steps": 181800, "loss": 0.0009, "lr": 2.0836650264235228e-05, "epoch": 11.958745874587459, "percentage": 59.79, "elapsed_time": "4:16:55", "remaining_time": "2:52:45", "throughput": 1488.26, "total_tokens": 22941888} {"current_steps": 108710, "total_steps": 181800, "loss": 0.0047, "lr": 2.083428373092725e-05, "epoch": 11.95929592959296, "percentage": 59.8, "elapsed_time": "4:16:55", "remaining_time": "2:52:44", "throughput": 1488.26, "total_tokens": 22942944} {"current_steps": 108715, "total_steps": 181800, "loss": 0.186, "lr": 2.0831917236012696e-05, "epoch": 11.95984598459846, "percentage": 59.8, "elapsed_time": "4:16:56", "remaining_time": "2:52:44", "throughput": 1488.26, "total_tokens": 22943968} {"current_steps": 108720, "total_steps": 181800, "loss": 0.1577, "lr": 2.082955077951335e-05, "epoch": 11.96039603960396, "percentage": 59.8, "elapsed_time": "4:16:57", "remaining_time": "2:52:43", "throughput": 1488.26, "total_tokens": 22945024} {"current_steps": 108725, "total_steps": 181800, "loss": 0.0252, "lr": 2.0827184361451035e-05, "epoch": 11.960946094609461, "percentage": 59.8, "elapsed_time": "4:16:58", "remaining_time": "2:52:42", "throughput": 1488.26, "total_tokens": 22946016} {"current_steps": 108730, "total_steps": 181800, "loss": 0.0164, "lr": 2.0824817981847566e-05, "epoch": 11.96149614961496, "percentage": 59.81, "elapsed_time": "4:16:58", "remaining_time": "2:52:41", "throughput": 1488.26, "total_tokens": 22947104} {"current_steps": 108735, "total_steps": 181800, "loss": 0.0047, "lr": 2.082245164072474e-05, "epoch": 11.962046204620462, "percentage": 59.81, "elapsed_time": "4:16:59", "remaining_time": "2:52:41", "throughput": 1488.26, "total_tokens": 22948096} {"current_steps": 108740, "total_steps": 181800, "loss": 0.0035, "lr": 2.082008533810437e-05, "epoch": 11.962596259625963, "percentage": 59.81, "elapsed_time": "4:17:00", "remaining_time": "2:52:40", "throughput": 1488.26, "total_tokens": 22949152} {"current_steps": 108745, "total_steps": 181800, "loss": 0.0095, "lr": 2.0817719074008268e-05, "epoch": 11.963146314631462, "percentage": 59.82, "elapsed_time": "4:17:00", "remaining_time": "2:52:39", "throughput": 1488.27, "total_tokens": 22950240} {"current_steps": 108750, "total_steps": 181800, "loss": 0.0116, "lr": 2.0815352848458246e-05, "epoch": 11.963696369636963, "percentage": 59.82, "elapsed_time": "4:17:01", "remaining_time": "2:52:38", "throughput": 1488.27, "total_tokens": 22951264} {"current_steps": 108755, "total_steps": 181800, "loss": 0.0047, "lr": 2.0812986661476113e-05, "epoch": 11.964246424642464, "percentage": 59.82, "elapsed_time": "4:17:02", "remaining_time": "2:52:38", "throughput": 1488.27, "total_tokens": 22952256} {"current_steps": 108760, "total_steps": 181800, "loss": 0.0714, "lr": 2.0810620513083664e-05, "epoch": 11.964796479647966, "percentage": 59.82, "elapsed_time": "4:17:02", "remaining_time": "2:52:37", "throughput": 1488.27, "total_tokens": 22953280} {"current_steps": 108765, "total_steps": 181800, "loss": 0.0022, "lr": 2.080825440330272e-05, "epoch": 11.965346534653465, "percentage": 59.83, "elapsed_time": "4:17:03", "remaining_time": "2:52:36", "throughput": 1488.27, "total_tokens": 22954336} {"current_steps": 108770, "total_steps": 181800, "loss": 0.05, "lr": 2.080588833215508e-05, "epoch": 11.965896589658966, "percentage": 59.83, "elapsed_time": "4:17:04", "remaining_time": "2:52:36", "throughput": 1488.26, "total_tokens": 22955328} {"current_steps": 108775, "total_steps": 181800, "loss": 0.009, "lr": 2.0803522299662566e-05, "epoch": 11.966446644664467, "percentage": 59.83, "elapsed_time": "4:17:04", "remaining_time": "2:52:35", "throughput": 1488.26, "total_tokens": 22956352} {"current_steps": 108780, "total_steps": 181800, "loss": 0.0135, "lr": 2.0801156305846965e-05, "epoch": 11.966996699669966, "percentage": 59.83, "elapsed_time": "4:17:05", "remaining_time": "2:52:34", "throughput": 1488.27, "total_tokens": 22957408} {"current_steps": 108785, "total_steps": 181800, "loss": 0.0066, "lr": 2.0798790350730086e-05, "epoch": 11.967546754675467, "percentage": 59.84, "elapsed_time": "4:17:06", "remaining_time": "2:52:33", "throughput": 1488.27, "total_tokens": 22958432} {"current_steps": 108790, "total_steps": 181800, "loss": 0.0155, "lr": 2.0796424434333754e-05, "epoch": 11.968096809680969, "percentage": 59.84, "elapsed_time": "4:17:06", "remaining_time": "2:52:33", "throughput": 1488.27, "total_tokens": 22959488} {"current_steps": 108795, "total_steps": 181800, "loss": 0.0345, "lr": 2.0794058556679746e-05, "epoch": 11.968646864686468, "percentage": 59.84, "elapsed_time": "4:17:07", "remaining_time": "2:52:32", "throughput": 1488.27, "total_tokens": 22960512} {"current_steps": 108800, "total_steps": 181800, "loss": 0.0107, "lr": 2.079169271778989e-05, "epoch": 11.969196919691969, "percentage": 59.85, "elapsed_time": "4:17:08", "remaining_time": "2:52:31", "throughput": 1488.28, "total_tokens": 22961664} {"current_steps": 108805, "total_steps": 181800, "loss": 0.0125, "lr": 2.0789326917685983e-05, "epoch": 11.96974697469747, "percentage": 59.85, "elapsed_time": "4:17:09", "remaining_time": "2:52:31", "throughput": 1488.28, "total_tokens": 22962720} {"current_steps": 108810, "total_steps": 181800, "loss": 0.2466, "lr": 2.0786961156389827e-05, "epoch": 11.97029702970297, "percentage": 59.85, "elapsed_time": "4:17:09", "remaining_time": "2:52:30", "throughput": 1488.28, "total_tokens": 22963840} {"current_steps": 108815, "total_steps": 181800, "loss": 0.0061, "lr": 2.0784595433923236e-05, "epoch": 11.97084708470847, "percentage": 59.85, "elapsed_time": "4:17:10", "remaining_time": "2:52:29", "throughput": 1488.29, "total_tokens": 22964960} {"current_steps": 108820, "total_steps": 181800, "loss": 0.072, "lr": 2.0782229750307993e-05, "epoch": 11.971397139713972, "percentage": 59.86, "elapsed_time": "4:17:11", "remaining_time": "2:52:28", "throughput": 1488.29, "total_tokens": 22966016} {"current_steps": 108825, "total_steps": 181800, "loss": 0.0335, "lr": 2.0779864105565922e-05, "epoch": 11.971947194719473, "percentage": 59.86, "elapsed_time": "4:17:11", "remaining_time": "2:52:28", "throughput": 1488.3, "total_tokens": 22967104} {"current_steps": 108830, "total_steps": 181800, "loss": 0.007, "lr": 2.0777498499718824e-05, "epoch": 11.972497249724972, "percentage": 59.86, "elapsed_time": "4:17:12", "remaining_time": "2:52:27", "throughput": 1488.29, "total_tokens": 22968096} {"current_steps": 108835, "total_steps": 181800, "loss": 0.0115, "lr": 2.0775132932788485e-05, "epoch": 11.973047304730473, "percentage": 59.87, "elapsed_time": "4:17:13", "remaining_time": "2:52:26", "throughput": 1488.3, "total_tokens": 22969184} {"current_steps": 108840, "total_steps": 181800, "loss": 0.011, "lr": 2.0772767404796725e-05, "epoch": 11.973597359735974, "percentage": 59.87, "elapsed_time": "4:17:13", "remaining_time": "2:52:25", "throughput": 1488.3, "total_tokens": 22970240} {"current_steps": 108845, "total_steps": 181800, "loss": 0.0091, "lr": 2.0770401915765334e-05, "epoch": 11.974147414741473, "percentage": 59.87, "elapsed_time": "4:17:14", "remaining_time": "2:52:25", "throughput": 1488.3, "total_tokens": 22971264} {"current_steps": 108850, "total_steps": 181800, "loss": 0.0097, "lr": 2.076803646571613e-05, "epoch": 11.974697469746975, "percentage": 59.87, "elapsed_time": "4:17:15", "remaining_time": "2:52:24", "throughput": 1488.3, "total_tokens": 22972384} {"current_steps": 108855, "total_steps": 181800, "loss": 0.0176, "lr": 2.0765671054670895e-05, "epoch": 11.975247524752476, "percentage": 59.88, "elapsed_time": "4:17:15", "remaining_time": "2:52:23", "throughput": 1488.3, "total_tokens": 22973408} {"current_steps": 108860, "total_steps": 181800, "loss": 0.0454, "lr": 2.0763305682651434e-05, "epoch": 11.975797579757975, "percentage": 59.88, "elapsed_time": "4:17:16", "remaining_time": "2:52:23", "throughput": 1488.31, "total_tokens": 22974496} {"current_steps": 108865, "total_steps": 181800, "loss": 0.0033, "lr": 2.0760940349679557e-05, "epoch": 11.976347634763476, "percentage": 59.88, "elapsed_time": "4:17:17", "remaining_time": "2:52:22", "throughput": 1488.31, "total_tokens": 22975584} {"current_steps": 108870, "total_steps": 181800, "loss": 0.0403, "lr": 2.0758575055777058e-05, "epoch": 11.976897689768977, "percentage": 59.88, "elapsed_time": "4:17:18", "remaining_time": "2:52:21", "throughput": 1488.31, "total_tokens": 22976640} {"current_steps": 108875, "total_steps": 181800, "loss": 0.0017, "lr": 2.0756209800965743e-05, "epoch": 11.977447744774478, "percentage": 59.89, "elapsed_time": "4:17:18", "remaining_time": "2:52:20", "throughput": 1488.32, "total_tokens": 22977728} {"current_steps": 108880, "total_steps": 181800, "loss": 0.0653, "lr": 2.07538445852674e-05, "epoch": 11.977997799779978, "percentage": 59.89, "elapsed_time": "4:17:19", "remaining_time": "2:52:20", "throughput": 1488.32, "total_tokens": 22978848} {"current_steps": 108885, "total_steps": 181800, "loss": 0.054, "lr": 2.0751479408703835e-05, "epoch": 11.978547854785479, "percentage": 59.89, "elapsed_time": "4:17:20", "remaining_time": "2:52:19", "throughput": 1488.33, "total_tokens": 22979904} {"current_steps": 108890, "total_steps": 181800, "loss": 0.0331, "lr": 2.074911427129685e-05, "epoch": 11.97909790979098, "percentage": 59.9, "elapsed_time": "4:17:20", "remaining_time": "2:52:18", "throughput": 1488.33, "total_tokens": 22981024} {"current_steps": 108895, "total_steps": 181800, "loss": 0.0027, "lr": 2.0746749173068235e-05, "epoch": 11.979647964796479, "percentage": 59.9, "elapsed_time": "4:17:21", "remaining_time": "2:52:18", "throughput": 1488.33, "total_tokens": 22982080} {"current_steps": 108900, "total_steps": 181800, "loss": 0.0041, "lr": 2.0744384114039787e-05, "epoch": 11.98019801980198, "percentage": 59.9, "elapsed_time": "4:17:22", "remaining_time": "2:52:17", "throughput": 1488.34, "total_tokens": 22983200} {"current_steps": 108905, "total_steps": 181800, "loss": 0.0047, "lr": 2.0742019094233318e-05, "epoch": 11.980748074807481, "percentage": 59.9, "elapsed_time": "4:17:22", "remaining_time": "2:52:16", "throughput": 1488.34, "total_tokens": 22984224} {"current_steps": 108910, "total_steps": 181800, "loss": 0.0098, "lr": 2.0739654113670607e-05, "epoch": 11.98129812981298, "percentage": 59.91, "elapsed_time": "4:17:23", "remaining_time": "2:52:15", "throughput": 1488.34, "total_tokens": 22985248} {"current_steps": 108915, "total_steps": 181800, "loss": 0.0049, "lr": 2.0737289172373463e-05, "epoch": 11.981848184818482, "percentage": 59.91, "elapsed_time": "4:17:24", "remaining_time": "2:52:15", "throughput": 1488.35, "total_tokens": 22986368} {"current_steps": 108920, "total_steps": 181800, "loss": 0.0014, "lr": 2.0734924270363687e-05, "epoch": 11.982398239823983, "percentage": 59.91, "elapsed_time": "4:17:24", "remaining_time": "2:52:14", "throughput": 1488.35, "total_tokens": 22987424} {"current_steps": 108925, "total_steps": 181800, "loss": 0.0037, "lr": 2.073255940766305e-05, "epoch": 11.982948294829484, "percentage": 59.91, "elapsed_time": "4:17:25", "remaining_time": "2:52:13", "throughput": 1488.35, "total_tokens": 22988448} {"current_steps": 108930, "total_steps": 181800, "loss": 0.017, "lr": 2.0730194584293383e-05, "epoch": 11.983498349834983, "percentage": 59.92, "elapsed_time": "4:17:26", "remaining_time": "2:52:12", "throughput": 1488.35, "total_tokens": 22989536} {"current_steps": 108935, "total_steps": 181800, "loss": 0.0884, "lr": 2.072782980027645e-05, "epoch": 11.984048404840484, "percentage": 59.92, "elapsed_time": "4:17:26", "remaining_time": "2:52:12", "throughput": 1488.35, "total_tokens": 22990592} {"current_steps": 108940, "total_steps": 181800, "loss": 0.0874, "lr": 2.0725465055634067e-05, "epoch": 11.984598459845985, "percentage": 59.92, "elapsed_time": "4:17:27", "remaining_time": "2:52:11", "throughput": 1488.35, "total_tokens": 22991616} {"current_steps": 108945, "total_steps": 181800, "loss": 0.0186, "lr": 2.0723100350388028e-05, "epoch": 11.985148514851485, "percentage": 59.93, "elapsed_time": "4:17:28", "remaining_time": "2:52:10", "throughput": 1488.36, "total_tokens": 22992704} {"current_steps": 108950, "total_steps": 181800, "loss": 0.0034, "lr": 2.0720735684560107e-05, "epoch": 11.985698569856986, "percentage": 59.93, "elapsed_time": "4:17:29", "remaining_time": "2:52:10", "throughput": 1488.36, "total_tokens": 22993792} {"current_steps": 108955, "total_steps": 181800, "loss": 0.1241, "lr": 2.071837105817212e-05, "epoch": 11.986248624862487, "percentage": 59.93, "elapsed_time": "4:17:29", "remaining_time": "2:52:09", "throughput": 1488.37, "total_tokens": 22994880} {"current_steps": 108960, "total_steps": 181800, "loss": 0.0762, "lr": 2.0716006471245844e-05, "epoch": 11.986798679867986, "percentage": 59.93, "elapsed_time": "4:17:30", "remaining_time": "2:52:08", "throughput": 1488.37, "total_tokens": 22995936} {"current_steps": 108965, "total_steps": 181800, "loss": 0.0051, "lr": 2.0713641923803094e-05, "epoch": 11.987348734873487, "percentage": 59.94, "elapsed_time": "4:17:31", "remaining_time": "2:52:07", "throughput": 1488.37, "total_tokens": 22997024} {"current_steps": 108970, "total_steps": 181800, "loss": 0.0725, "lr": 2.071127741586564e-05, "epoch": 11.987898789878988, "percentage": 59.94, "elapsed_time": "4:17:31", "remaining_time": "2:52:07", "throughput": 1488.37, "total_tokens": 22998080} {"current_steps": 108975, "total_steps": 181800, "loss": 0.0567, "lr": 2.0708912947455287e-05, "epoch": 11.988448844884488, "percentage": 59.94, "elapsed_time": "4:17:32", "remaining_time": "2:52:06", "throughput": 1488.38, "total_tokens": 22999200} {"current_steps": 108980, "total_steps": 181800, "loss": 0.0014, "lr": 2.070654851859383e-05, "epoch": 11.988998899889989, "percentage": 59.94, "elapsed_time": "4:17:33", "remaining_time": "2:52:05", "throughput": 1488.38, "total_tokens": 23000192} {"current_steps": 108985, "total_steps": 181800, "loss": 0.0672, "lr": 2.070418412930304e-05, "epoch": 11.98954895489549, "percentage": 59.95, "elapsed_time": "4:17:33", "remaining_time": "2:52:05", "throughput": 1488.38, "total_tokens": 23001280} {"current_steps": 108990, "total_steps": 181800, "loss": 0.0079, "lr": 2.0701819779604738e-05, "epoch": 11.990099009900991, "percentage": 59.95, "elapsed_time": "4:17:34", "remaining_time": "2:52:04", "throughput": 1488.39, "total_tokens": 23002400} {"current_steps": 108995, "total_steps": 181800, "loss": 0.0037, "lr": 2.0699455469520694e-05, "epoch": 11.99064906490649, "percentage": 59.95, "elapsed_time": "4:17:35", "remaining_time": "2:52:03", "throughput": 1488.39, "total_tokens": 23003456} {"current_steps": 109000, "total_steps": 181800, "loss": 0.0496, "lr": 2.0697091199072703e-05, "epoch": 11.991199119911991, "percentage": 59.96, "elapsed_time": "4:17:35", "remaining_time": "2:52:02", "throughput": 1488.39, "total_tokens": 23004512} {"current_steps": 109005, "total_steps": 181800, "loss": 0.0329, "lr": 2.0694726968282567e-05, "epoch": 11.991749174917492, "percentage": 59.96, "elapsed_time": "4:17:36", "remaining_time": "2:52:02", "throughput": 1488.39, "total_tokens": 23005600} {"current_steps": 109010, "total_steps": 181800, "loss": 0.0368, "lr": 2.069236277717206e-05, "epoch": 11.992299229922992, "percentage": 59.96, "elapsed_time": "4:17:37", "remaining_time": "2:52:01", "throughput": 1488.4, "total_tokens": 23006656} {"current_steps": 109015, "total_steps": 181800, "loss": 0.0183, "lr": 2.068999862576298e-05, "epoch": 11.992849284928493, "percentage": 59.96, "elapsed_time": "4:17:38", "remaining_time": "2:52:00", "throughput": 1488.4, "total_tokens": 23007680} {"current_steps": 109020, "total_steps": 181800, "loss": 0.0792, "lr": 2.068763451407712e-05, "epoch": 11.993399339933994, "percentage": 59.97, "elapsed_time": "4:17:38", "remaining_time": "2:52:00", "throughput": 1488.4, "total_tokens": 23008736} {"current_steps": 109025, "total_steps": 181800, "loss": 0.0399, "lr": 2.068527044213625e-05, "epoch": 11.993949394939493, "percentage": 59.97, "elapsed_time": "4:17:39", "remaining_time": "2:51:59", "throughput": 1488.4, "total_tokens": 23009792} {"current_steps": 109030, "total_steps": 181800, "loss": 0.0049, "lr": 2.0682906409962182e-05, "epoch": 11.994499449944994, "percentage": 59.97, "elapsed_time": "4:17:40", "remaining_time": "2:51:58", "throughput": 1488.4, "total_tokens": 23010816} {"current_steps": 109035, "total_steps": 181800, "loss": 0.0081, "lr": 2.0680542417576687e-05, "epoch": 11.995049504950495, "percentage": 59.98, "elapsed_time": "4:17:40", "remaining_time": "2:51:57", "throughput": 1488.4, "total_tokens": 23011904} {"current_steps": 109040, "total_steps": 181800, "loss": 0.0107, "lr": 2.067817846500157e-05, "epoch": 11.995599559955995, "percentage": 59.98, "elapsed_time": "4:17:41", "remaining_time": "2:51:57", "throughput": 1488.4, "total_tokens": 23012928} {"current_steps": 109045, "total_steps": 181800, "loss": 0.0019, "lr": 2.06758145522586e-05, "epoch": 11.996149614961496, "percentage": 59.98, "elapsed_time": "4:17:42", "remaining_time": "2:51:56", "throughput": 1488.41, "total_tokens": 23013984} {"current_steps": 109050, "total_steps": 181800, "loss": 0.0495, "lr": 2.0673450679369573e-05, "epoch": 11.996699669966997, "percentage": 59.98, "elapsed_time": "4:17:42", "remaining_time": "2:51:55", "throughput": 1488.4, "total_tokens": 23015008} {"current_steps": 109055, "total_steps": 181800, "loss": 0.0246, "lr": 2.0671086846356277e-05, "epoch": 11.997249724972498, "percentage": 59.99, "elapsed_time": "4:17:43", "remaining_time": "2:51:54", "throughput": 1488.4, "total_tokens": 23016032} {"current_steps": 109060, "total_steps": 181800, "loss": 0.0091, "lr": 2.066872305324049e-05, "epoch": 11.997799779977997, "percentage": 59.99, "elapsed_time": "4:17:44", "remaining_time": "2:51:54", "throughput": 1488.41, "total_tokens": 23017120} {"current_steps": 109065, "total_steps": 181800, "loss": 0.0178, "lr": 2.066635930004402e-05, "epoch": 11.998349834983498, "percentage": 59.99, "elapsed_time": "4:17:44", "remaining_time": "2:51:53", "throughput": 1488.41, "total_tokens": 23018144} {"current_steps": 109070, "total_steps": 181800, "loss": 0.0063, "lr": 2.0663995586788627e-05, "epoch": 11.998899889989, "percentage": 59.99, "elapsed_time": "4:17:45", "remaining_time": "2:51:52", "throughput": 1488.41, "total_tokens": 23019232} {"current_steps": 109075, "total_steps": 181800, "loss": 0.0055, "lr": 2.0661631913496103e-05, "epoch": 11.999449944994499, "percentage": 60.0, "elapsed_time": "4:17:46", "remaining_time": "2:51:52", "throughput": 1488.41, "total_tokens": 23020320} {"current_steps": 109080, "total_steps": 181800, "loss": 0.0008, "lr": 2.0659268280188243e-05, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "4:17:47", "remaining_time": "2:51:51", "throughput": 1488.41, "total_tokens": 23021312} {"current_steps": 109080, "total_steps": 181800, "eval_loss": 0.07049336284399033, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "4:18:24", "remaining_time": "2:52:16", "throughput": 1484.86, "total_tokens": 23021312} {"current_steps": 109085, "total_steps": 181800, "loss": 0.1471, "lr": 2.0656904686886823e-05, "epoch": 12.000550055005501, "percentage": 60.0, "elapsed_time": "4:18:26", "remaining_time": "2:52:16", "throughput": 1484.71, "total_tokens": 23022368} {"current_steps": 109090, "total_steps": 181800, "loss": 0.0099, "lr": 2.065454113361362e-05, "epoch": 12.001100110011, "percentage": 60.01, "elapsed_time": "4:18:27", "remaining_time": "2:52:15", "throughput": 1484.71, "total_tokens": 23023488} {"current_steps": 109095, "total_steps": 181800, "loss": 0.0881, "lr": 2.065217762039044e-05, "epoch": 12.001650165016502, "percentage": 60.01, "elapsed_time": "4:18:27", "remaining_time": "2:52:14", "throughput": 1484.71, "total_tokens": 23024448} {"current_steps": 109100, "total_steps": 181800, "loss": 0.0954, "lr": 2.0649814147239034e-05, "epoch": 12.002200220022003, "percentage": 60.01, "elapsed_time": "4:18:28", "remaining_time": "2:52:14", "throughput": 1484.71, "total_tokens": 23025568} {"current_steps": 109105, "total_steps": 181800, "loss": 0.0094, "lr": 2.064745071418122e-05, "epoch": 12.002750275027502, "percentage": 60.01, "elapsed_time": "4:18:29", "remaining_time": "2:52:13", "throughput": 1484.72, "total_tokens": 23026688} {"current_steps": 109110, "total_steps": 181800, "loss": 0.1536, "lr": 2.064508732123876e-05, "epoch": 12.003300330033003, "percentage": 60.02, "elapsed_time": "4:18:29", "remaining_time": "2:52:12", "throughput": 1484.72, "total_tokens": 23027744} {"current_steps": 109115, "total_steps": 181800, "loss": 0.0041, "lr": 2.0642723968433434e-05, "epoch": 12.003850385038504, "percentage": 60.02, "elapsed_time": "4:18:30", "remaining_time": "2:52:12", "throughput": 1484.72, "total_tokens": 23028800} {"current_steps": 109120, "total_steps": 181800, "loss": 0.0031, "lr": 2.064036065578704e-05, "epoch": 12.004400440044005, "percentage": 60.02, "elapsed_time": "4:18:31", "remaining_time": "2:52:11", "throughput": 1484.72, "total_tokens": 23029824} {"current_steps": 109125, "total_steps": 181800, "loss": 0.0929, "lr": 2.063799738332134e-05, "epoch": 12.004950495049505, "percentage": 60.02, "elapsed_time": "4:18:32", "remaining_time": "2:52:10", "throughput": 1484.71, "total_tokens": 23030880} {"current_steps": 109130, "total_steps": 181800, "loss": 0.0168, "lr": 2.0635634151058134e-05, "epoch": 12.005500550055006, "percentage": 60.03, "elapsed_time": "4:18:32", "remaining_time": "2:52:10", "throughput": 1484.71, "total_tokens": 23031904} {"current_steps": 109135, "total_steps": 181800, "loss": 0.0212, "lr": 2.0633270959019196e-05, "epoch": 12.006050605060507, "percentage": 60.03, "elapsed_time": "4:18:33", "remaining_time": "2:52:09", "throughput": 1484.71, "total_tokens": 23032960} {"current_steps": 109140, "total_steps": 181800, "loss": 0.0242, "lr": 2.0630907807226293e-05, "epoch": 12.006600660066006, "percentage": 60.03, "elapsed_time": "4:18:34", "remaining_time": "2:52:08", "throughput": 1484.7, "total_tokens": 23033952} {"current_steps": 109145, "total_steps": 181800, "loss": 0.0954, "lr": 2.0628544695701226e-05, "epoch": 12.007150715071507, "percentage": 60.04, "elapsed_time": "4:18:34", "remaining_time": "2:52:07", "throughput": 1484.7, "total_tokens": 23035008} {"current_steps": 109150, "total_steps": 181800, "loss": 0.0184, "lr": 2.062618162446575e-05, "epoch": 12.007700770077008, "percentage": 60.04, "elapsed_time": "4:18:35", "remaining_time": "2:52:07", "throughput": 1484.7, "total_tokens": 23036032} {"current_steps": 109155, "total_steps": 181800, "loss": 0.0049, "lr": 2.062381859354168e-05, "epoch": 12.008250825082508, "percentage": 60.04, "elapsed_time": "4:18:36", "remaining_time": "2:52:06", "throughput": 1484.7, "total_tokens": 23037088} {"current_steps": 109160, "total_steps": 181800, "loss": 0.0264, "lr": 2.0621455602950763e-05, "epoch": 12.008800880088009, "percentage": 60.04, "elapsed_time": "4:18:36", "remaining_time": "2:52:05", "throughput": 1484.7, "total_tokens": 23038144} {"current_steps": 109165, "total_steps": 181800, "loss": 0.0033, "lr": 2.0619092652714785e-05, "epoch": 12.00935093509351, "percentage": 60.05, "elapsed_time": "4:18:37", "remaining_time": "2:52:04", "throughput": 1484.7, "total_tokens": 23039168} {"current_steps": 109170, "total_steps": 181800, "loss": 0.0987, "lr": 2.0616729742855533e-05, "epoch": 12.009900990099009, "percentage": 60.05, "elapsed_time": "4:18:38", "remaining_time": "2:52:04", "throughput": 1484.71, "total_tokens": 23040224} {"current_steps": 109175, "total_steps": 181800, "loss": 0.0044, "lr": 2.0614366873394775e-05, "epoch": 12.01045104510451, "percentage": 60.05, "elapsed_time": "4:18:39", "remaining_time": "2:52:03", "throughput": 1484.71, "total_tokens": 23041248} {"current_steps": 109180, "total_steps": 181800, "loss": 0.003, "lr": 2.0612004044354304e-05, "epoch": 12.011001100110011, "percentage": 60.06, "elapsed_time": "4:18:39", "remaining_time": "2:52:02", "throughput": 1484.71, "total_tokens": 23042304} {"current_steps": 109185, "total_steps": 181800, "loss": 0.0093, "lr": 2.0609641255755878e-05, "epoch": 12.011551155115512, "percentage": 60.06, "elapsed_time": "4:18:40", "remaining_time": "2:52:02", "throughput": 1484.71, "total_tokens": 23043296} {"current_steps": 109190, "total_steps": 181800, "loss": 0.0022, "lr": 2.060727850762128e-05, "epoch": 12.012101210121012, "percentage": 60.06, "elapsed_time": "4:18:41", "remaining_time": "2:52:01", "throughput": 1484.71, "total_tokens": 23044384} {"current_steps": 109195, "total_steps": 181800, "loss": 0.0017, "lr": 2.0604915799972296e-05, "epoch": 12.012651265126513, "percentage": 60.06, "elapsed_time": "4:18:41", "remaining_time": "2:52:00", "throughput": 1484.71, "total_tokens": 23045472} {"current_steps": 109200, "total_steps": 181800, "loss": 0.1107, "lr": 2.0602553132830687e-05, "epoch": 12.013201320132014, "percentage": 60.07, "elapsed_time": "4:18:42", "remaining_time": "2:51:59", "throughput": 1484.71, "total_tokens": 23046496} {"current_steps": 109205, "total_steps": 181800, "loss": 0.0556, "lr": 2.060019050621824e-05, "epoch": 12.013751375137513, "percentage": 60.07, "elapsed_time": "4:18:43", "remaining_time": "2:51:59", "throughput": 1484.72, "total_tokens": 23047648} {"current_steps": 109210, "total_steps": 181800, "loss": 0.0024, "lr": 2.0597827920156727e-05, "epoch": 12.014301430143014, "percentage": 60.07, "elapsed_time": "4:18:43", "remaining_time": "2:51:58", "throughput": 1484.72, "total_tokens": 23048672} {"current_steps": 109215, "total_steps": 181800, "loss": 0.0147, "lr": 2.0595465374667915e-05, "epoch": 12.014851485148515, "percentage": 60.07, "elapsed_time": "4:18:44", "remaining_time": "2:51:57", "throughput": 1484.72, "total_tokens": 23049664} {"current_steps": 109220, "total_steps": 181800, "loss": 0.0193, "lr": 2.059310286977359e-05, "epoch": 12.015401540154015, "percentage": 60.08, "elapsed_time": "4:18:45", "remaining_time": "2:51:57", "throughput": 1484.72, "total_tokens": 23050720} {"current_steps": 109225, "total_steps": 181800, "loss": 0.0153, "lr": 2.0590740405495514e-05, "epoch": 12.015951595159516, "percentage": 60.08, "elapsed_time": "4:18:46", "remaining_time": "2:51:56", "throughput": 1484.72, "total_tokens": 23051744} {"current_steps": 109230, "total_steps": 181800, "loss": 0.1641, "lr": 2.0588377981855478e-05, "epoch": 12.016501650165017, "percentage": 60.08, "elapsed_time": "4:18:46", "remaining_time": "2:51:55", "throughput": 1484.72, "total_tokens": 23052736} {"current_steps": 109235, "total_steps": 181800, "loss": 0.0025, "lr": 2.058601559887525e-05, "epoch": 12.017051705170518, "percentage": 60.09, "elapsed_time": "4:18:47", "remaining_time": "2:51:54", "throughput": 1484.72, "total_tokens": 23053792} {"current_steps": 109240, "total_steps": 181800, "loss": 0.0386, "lr": 2.058365325657658e-05, "epoch": 12.017601760176017, "percentage": 60.09, "elapsed_time": "4:18:48", "remaining_time": "2:51:54", "throughput": 1484.72, "total_tokens": 23054848} {"current_steps": 109245, "total_steps": 181800, "loss": 0.0024, "lr": 2.058129095498127e-05, "epoch": 12.018151815181518, "percentage": 60.09, "elapsed_time": "4:18:48", "remaining_time": "2:51:53", "throughput": 1484.72, "total_tokens": 23055904} {"current_steps": 109250, "total_steps": 181800, "loss": 0.0091, "lr": 2.0578928694111073e-05, "epoch": 12.01870187018702, "percentage": 60.09, "elapsed_time": "4:18:49", "remaining_time": "2:51:52", "throughput": 1484.72, "total_tokens": 23056928} {"current_steps": 109255, "total_steps": 181800, "loss": 0.0096, "lr": 2.057656647398778e-05, "epoch": 12.019251925192519, "percentage": 60.1, "elapsed_time": "4:18:50", "remaining_time": "2:51:51", "throughput": 1484.72, "total_tokens": 23057984} {"current_steps": 109260, "total_steps": 181800, "loss": 0.0322, "lr": 2.0574204294633148e-05, "epoch": 12.01980198019802, "percentage": 60.1, "elapsed_time": "4:18:50", "remaining_time": "2:51:51", "throughput": 1484.73, "total_tokens": 23059072} {"current_steps": 109265, "total_steps": 181800, "loss": 0.0035, "lr": 2.0571842156068948e-05, "epoch": 12.020352035203521, "percentage": 60.1, "elapsed_time": "4:18:51", "remaining_time": "2:51:50", "throughput": 1484.73, "total_tokens": 23060128} {"current_steps": 109270, "total_steps": 181800, "loss": 0.0135, "lr": 2.056948005831696e-05, "epoch": 12.02090209020902, "percentage": 60.1, "elapsed_time": "4:18:52", "remaining_time": "2:51:49", "throughput": 1484.73, "total_tokens": 23061184} {"current_steps": 109275, "total_steps": 181800, "loss": 0.0065, "lr": 2.0567118001398944e-05, "epoch": 12.021452145214521, "percentage": 60.11, "elapsed_time": "4:18:52", "remaining_time": "2:51:49", "throughput": 1484.73, "total_tokens": 23062240} {"current_steps": 109280, "total_steps": 181800, "loss": 0.0157, "lr": 2.056475598533667e-05, "epoch": 12.022002200220022, "percentage": 60.11, "elapsed_time": "4:18:53", "remaining_time": "2:51:48", "throughput": 1484.74, "total_tokens": 23063296} {"current_steps": 109285, "total_steps": 181800, "loss": 0.0444, "lr": 2.0562394010151922e-05, "epoch": 12.022552255225522, "percentage": 60.11, "elapsed_time": "4:18:54", "remaining_time": "2:51:47", "throughput": 1484.74, "total_tokens": 23064352} {"current_steps": 109290, "total_steps": 181800, "loss": 0.0391, "lr": 2.056003207586644e-05, "epoch": 12.023102310231023, "percentage": 60.12, "elapsed_time": "4:18:54", "remaining_time": "2:51:46", "throughput": 1484.74, "total_tokens": 23065472} {"current_steps": 109295, "total_steps": 181800, "loss": 0.0979, "lr": 2.0557670182502033e-05, "epoch": 12.023652365236524, "percentage": 60.12, "elapsed_time": "4:18:55", "remaining_time": "2:51:46", "throughput": 1484.75, "total_tokens": 23066560} {"current_steps": 109300, "total_steps": 181800, "loss": 0.0876, "lr": 2.055530833008044e-05, "epoch": 12.024202420242025, "percentage": 60.12, "elapsed_time": "4:18:56", "remaining_time": "2:51:45", "throughput": 1484.75, "total_tokens": 23067648} {"current_steps": 109305, "total_steps": 181800, "loss": 0.0037, "lr": 2.0552946518623434e-05, "epoch": 12.024752475247524, "percentage": 60.12, "elapsed_time": "4:18:57", "remaining_time": "2:51:44", "throughput": 1484.75, "total_tokens": 23068704} {"current_steps": 109310, "total_steps": 181800, "loss": 0.013, "lr": 2.0550584748152797e-05, "epoch": 12.025302530253025, "percentage": 60.13, "elapsed_time": "4:18:57", "remaining_time": "2:51:44", "throughput": 1484.75, "total_tokens": 23069760} {"current_steps": 109315, "total_steps": 181800, "loss": 0.0666, "lr": 2.054822301869027e-05, "epoch": 12.025852585258527, "percentage": 60.13, "elapsed_time": "4:18:58", "remaining_time": "2:51:43", "throughput": 1484.75, "total_tokens": 23070784} {"current_steps": 109320, "total_steps": 181800, "loss": 0.0439, "lr": 2.0545861330257647e-05, "epoch": 12.026402640264026, "percentage": 60.13, "elapsed_time": "4:18:59", "remaining_time": "2:51:42", "throughput": 1484.75, "total_tokens": 23071808} {"current_steps": 109325, "total_steps": 181800, "loss": 0.0032, "lr": 2.0543499682876686e-05, "epoch": 12.026952695269527, "percentage": 60.13, "elapsed_time": "4:18:59", "remaining_time": "2:51:41", "throughput": 1484.75, "total_tokens": 23072768} {"current_steps": 109330, "total_steps": 181800, "loss": 0.045, "lr": 2.0541138076569135e-05, "epoch": 12.027502750275028, "percentage": 60.14, "elapsed_time": "4:19:00", "remaining_time": "2:51:41", "throughput": 1484.76, "total_tokens": 23073888} {"current_steps": 109335, "total_steps": 181800, "loss": 0.0275, "lr": 2.0538776511356787e-05, "epoch": 12.028052805280527, "percentage": 60.14, "elapsed_time": "4:19:01", "remaining_time": "2:51:40", "throughput": 1484.76, "total_tokens": 23074912} {"current_steps": 109340, "total_steps": 181800, "loss": 0.0034, "lr": 2.0536414987261383e-05, "epoch": 12.028602860286028, "percentage": 60.14, "elapsed_time": "4:19:01", "remaining_time": "2:51:39", "throughput": 1484.76, "total_tokens": 23076000} {"current_steps": 109345, "total_steps": 181800, "loss": 0.0084, "lr": 2.053405350430471e-05, "epoch": 12.02915291529153, "percentage": 60.15, "elapsed_time": "4:19:02", "remaining_time": "2:51:38", "throughput": 1484.76, "total_tokens": 23076992} {"current_steps": 109350, "total_steps": 181800, "loss": 0.0738, "lr": 2.0531692062508528e-05, "epoch": 12.029702970297029, "percentage": 60.15, "elapsed_time": "4:19:03", "remaining_time": "2:51:38", "throughput": 1484.76, "total_tokens": 23078048} {"current_steps": 109355, "total_steps": 181800, "loss": 0.011, "lr": 2.0529330661894586e-05, "epoch": 12.03025302530253, "percentage": 60.15, "elapsed_time": "4:19:03", "remaining_time": "2:51:37", "throughput": 1484.76, "total_tokens": 23079072} {"current_steps": 109360, "total_steps": 181800, "loss": 0.0361, "lr": 2.052696930248466e-05, "epoch": 12.030803080308031, "percentage": 60.15, "elapsed_time": "4:19:04", "remaining_time": "2:51:36", "throughput": 1484.76, "total_tokens": 23080064} {"current_steps": 109365, "total_steps": 181800, "loss": 0.0025, "lr": 2.052460798430051e-05, "epoch": 12.031353135313532, "percentage": 60.16, "elapsed_time": "4:19:05", "remaining_time": "2:51:36", "throughput": 1484.76, "total_tokens": 23081088} {"current_steps": 109370, "total_steps": 181800, "loss": 0.013, "lr": 2.0522246707363906e-05, "epoch": 12.031903190319031, "percentage": 60.16, "elapsed_time": "4:19:06", "remaining_time": "2:51:35", "throughput": 1484.76, "total_tokens": 23082144} {"current_steps": 109375, "total_steps": 181800, "loss": 0.0194, "lr": 2.0519885471696608e-05, "epoch": 12.032453245324533, "percentage": 60.16, "elapsed_time": "4:19:06", "remaining_time": "2:51:34", "throughput": 1484.76, "total_tokens": 23083200} {"current_steps": 109380, "total_steps": 181800, "loss": 0.091, "lr": 2.0517524277320363e-05, "epoch": 12.033003300330034, "percentage": 60.17, "elapsed_time": "4:19:07", "remaining_time": "2:51:33", "throughput": 1484.76, "total_tokens": 23084224} {"current_steps": 109385, "total_steps": 181800, "loss": 0.0026, "lr": 2.051516312425696e-05, "epoch": 12.033553355335533, "percentage": 60.17, "elapsed_time": "4:19:08", "remaining_time": "2:51:33", "throughput": 1484.76, "total_tokens": 23085312} {"current_steps": 109390, "total_steps": 181800, "loss": 0.0685, "lr": 2.0512802012528136e-05, "epoch": 12.034103410341034, "percentage": 60.17, "elapsed_time": "4:19:08", "remaining_time": "2:51:32", "throughput": 1484.76, "total_tokens": 23086336} {"current_steps": 109395, "total_steps": 181800, "loss": 0.0216, "lr": 2.0510440942155668e-05, "epoch": 12.034653465346535, "percentage": 60.17, "elapsed_time": "4:19:09", "remaining_time": "2:51:31", "throughput": 1484.77, "total_tokens": 23087392} {"current_steps": 109400, "total_steps": 181800, "loss": 0.0584, "lr": 2.0508079913161315e-05, "epoch": 12.035203520352034, "percentage": 60.18, "elapsed_time": "4:19:10", "remaining_time": "2:51:30", "throughput": 1484.77, "total_tokens": 23088416} {"current_steps": 109405, "total_steps": 181800, "loss": 0.0628, "lr": 2.050571892556682e-05, "epoch": 12.035753575357536, "percentage": 60.18, "elapsed_time": "4:19:10", "remaining_time": "2:51:30", "throughput": 1484.77, "total_tokens": 23089472} {"current_steps": 109410, "total_steps": 181800, "loss": 0.0072, "lr": 2.050335797939397e-05, "epoch": 12.036303630363037, "percentage": 60.18, "elapsed_time": "4:19:11", "remaining_time": "2:51:29", "throughput": 1484.77, "total_tokens": 23090464} {"current_steps": 109415, "total_steps": 181800, "loss": 0.0759, "lr": 2.050099707466451e-05, "epoch": 12.036853685368538, "percentage": 60.18, "elapsed_time": "4:19:12", "remaining_time": "2:51:28", "throughput": 1484.77, "total_tokens": 23091488} {"current_steps": 109420, "total_steps": 181800, "loss": 0.0077, "lr": 2.0498636211400195e-05, "epoch": 12.037403740374037, "percentage": 60.19, "elapsed_time": "4:19:12", "remaining_time": "2:51:28", "throughput": 1484.77, "total_tokens": 23092512} {"current_steps": 109425, "total_steps": 181800, "loss": 0.0101, "lr": 2.0496275389622803e-05, "epoch": 12.037953795379538, "percentage": 60.19, "elapsed_time": "4:19:13", "remaining_time": "2:51:27", "throughput": 1484.77, "total_tokens": 23093600} {"current_steps": 109430, "total_steps": 181800, "loss": 0.0118, "lr": 2.0493914609354064e-05, "epoch": 12.03850385038504, "percentage": 60.19, "elapsed_time": "4:19:14", "remaining_time": "2:51:26", "throughput": 1484.77, "total_tokens": 23094656} {"current_steps": 109435, "total_steps": 181800, "loss": 0.0016, "lr": 2.049155387061576e-05, "epoch": 12.039053905390539, "percentage": 60.2, "elapsed_time": "4:19:15", "remaining_time": "2:51:25", "throughput": 1484.77, "total_tokens": 23095648} {"current_steps": 109440, "total_steps": 181800, "loss": 0.0202, "lr": 2.0489193173429635e-05, "epoch": 12.03960396039604, "percentage": 60.2, "elapsed_time": "4:19:15", "remaining_time": "2:51:25", "throughput": 1484.77, "total_tokens": 23096672} {"current_steps": 109445, "total_steps": 181800, "loss": 0.0093, "lr": 2.0486832517817464e-05, "epoch": 12.04015401540154, "percentage": 60.2, "elapsed_time": "4:19:16", "remaining_time": "2:51:24", "throughput": 1484.77, "total_tokens": 23097760} {"current_steps": 109450, "total_steps": 181800, "loss": 0.0028, "lr": 2.0484471903800984e-05, "epoch": 12.04070407040704, "percentage": 60.2, "elapsed_time": "4:19:17", "remaining_time": "2:51:23", "throughput": 1484.77, "total_tokens": 23098752} {"current_steps": 109455, "total_steps": 181800, "loss": 0.0047, "lr": 2.0482111331401957e-05, "epoch": 12.041254125412541, "percentage": 60.21, "elapsed_time": "4:19:17", "remaining_time": "2:51:23", "throughput": 1484.78, "total_tokens": 23099872} {"current_steps": 109460, "total_steps": 181800, "loss": 0.0033, "lr": 2.047975080064215e-05, "epoch": 12.041804180418042, "percentage": 60.21, "elapsed_time": "4:19:18", "remaining_time": "2:51:22", "throughput": 1484.78, "total_tokens": 23100928} {"current_steps": 109465, "total_steps": 181800, "loss": 0.0032, "lr": 2.0477390311543306e-05, "epoch": 12.042354235423542, "percentage": 60.21, "elapsed_time": "4:19:19", "remaining_time": "2:51:21", "throughput": 1484.78, "total_tokens": 23101984} {"current_steps": 109470, "total_steps": 181800, "loss": 0.0059, "lr": 2.0475029864127182e-05, "epoch": 12.042904290429043, "percentage": 60.21, "elapsed_time": "4:19:19", "remaining_time": "2:51:20", "throughput": 1484.79, "total_tokens": 23103072} {"current_steps": 109475, "total_steps": 181800, "loss": 0.0032, "lr": 2.0472669458415542e-05, "epoch": 12.043454345434544, "percentage": 60.22, "elapsed_time": "4:19:20", "remaining_time": "2:51:20", "throughput": 1484.78, "total_tokens": 23104064} {"current_steps": 109480, "total_steps": 181800, "loss": 0.0078, "lr": 2.047030909443013e-05, "epoch": 12.044004400440045, "percentage": 60.22, "elapsed_time": "4:19:21", "remaining_time": "2:51:19", "throughput": 1484.78, "total_tokens": 23105088} {"current_steps": 109485, "total_steps": 181800, "loss": 0.0215, "lr": 2.0467948772192713e-05, "epoch": 12.044554455445544, "percentage": 60.22, "elapsed_time": "4:19:21", "remaining_time": "2:51:18", "throughput": 1484.78, "total_tokens": 23106112} {"current_steps": 109490, "total_steps": 181800, "loss": 0.0035, "lr": 2.046558849172503e-05, "epoch": 12.045104510451045, "percentage": 60.23, "elapsed_time": "4:19:22", "remaining_time": "2:51:17", "throughput": 1484.79, "total_tokens": 23107168} {"current_steps": 109495, "total_steps": 181800, "loss": 0.1202, "lr": 2.0463228253048844e-05, "epoch": 12.045654565456546, "percentage": 60.23, "elapsed_time": "4:19:23", "remaining_time": "2:51:17", "throughput": 1484.79, "total_tokens": 23108192} {"current_steps": 109500, "total_steps": 181800, "loss": 0.0257, "lr": 2.046086805618591e-05, "epoch": 12.046204620462046, "percentage": 60.23, "elapsed_time": "4:19:23", "remaining_time": "2:51:16", "throughput": 1484.8, "total_tokens": 23109376} {"current_steps": 109505, "total_steps": 181800, "loss": 0.0044, "lr": 2.0458507901157973e-05, "epoch": 12.046754675467547, "percentage": 60.23, "elapsed_time": "4:19:24", "remaining_time": "2:51:15", "throughput": 1484.8, "total_tokens": 23110368} {"current_steps": 109510, "total_steps": 181800, "loss": 0.1445, "lr": 2.045614778798679e-05, "epoch": 12.047304730473048, "percentage": 60.24, "elapsed_time": "4:19:25", "remaining_time": "2:51:15", "throughput": 1484.8, "total_tokens": 23111456} {"current_steps": 109515, "total_steps": 181800, "loss": 0.0036, "lr": 2.045378771669412e-05, "epoch": 12.047854785478547, "percentage": 60.24, "elapsed_time": "4:19:26", "remaining_time": "2:51:14", "throughput": 1484.8, "total_tokens": 23112448} {"current_steps": 109520, "total_steps": 181800, "loss": 0.048, "lr": 2.0451427687301696e-05, "epoch": 12.048404840484048, "percentage": 60.24, "elapsed_time": "4:19:26", "remaining_time": "2:51:13", "throughput": 1484.8, "total_tokens": 23113536} {"current_steps": 109525, "total_steps": 181800, "loss": 0.0007, "lr": 2.0449067699831286e-05, "epoch": 12.04895489548955, "percentage": 60.24, "elapsed_time": "4:19:27", "remaining_time": "2:51:12", "throughput": 1484.8, "total_tokens": 23114560} {"current_steps": 109530, "total_steps": 181800, "loss": 0.0606, "lr": 2.044670775430463e-05, "epoch": 12.049504950495049, "percentage": 60.25, "elapsed_time": "4:19:28", "remaining_time": "2:51:12", "throughput": 1484.81, "total_tokens": 23115648} {"current_steps": 109535, "total_steps": 181800, "loss": 0.0028, "lr": 2.044434785074349e-05, "epoch": 12.05005500550055, "percentage": 60.25, "elapsed_time": "4:19:28", "remaining_time": "2:51:11", "throughput": 1484.81, "total_tokens": 23116704} {"current_steps": 109540, "total_steps": 181800, "loss": 0.0301, "lr": 2.0441987989169612e-05, "epoch": 12.05060506050605, "percentage": 60.25, "elapsed_time": "4:19:29", "remaining_time": "2:51:10", "throughput": 1484.81, "total_tokens": 23117728} {"current_steps": 109545, "total_steps": 181800, "loss": 0.0026, "lr": 2.0439628169604734e-05, "epoch": 12.051155115511552, "percentage": 60.26, "elapsed_time": "4:19:30", "remaining_time": "2:51:09", "throughput": 1484.81, "total_tokens": 23118816} {"current_steps": 109550, "total_steps": 181800, "loss": 0.0189, "lr": 2.043726839207062e-05, "epoch": 12.051705170517051, "percentage": 60.26, "elapsed_time": "4:19:30", "remaining_time": "2:51:09", "throughput": 1484.82, "total_tokens": 23119904} {"current_steps": 109555, "total_steps": 181800, "loss": 0.0073, "lr": 2.0434908656589012e-05, "epoch": 12.052255225522552, "percentage": 60.26, "elapsed_time": "4:19:31", "remaining_time": "2:51:08", "throughput": 1484.82, "total_tokens": 23120928} {"current_steps": 109560, "total_steps": 181800, "loss": 0.0465, "lr": 2.0432548963181665e-05, "epoch": 12.052805280528053, "percentage": 60.26, "elapsed_time": "4:19:32", "remaining_time": "2:51:07", "throughput": 1484.82, "total_tokens": 23122016} {"current_steps": 109565, "total_steps": 181800, "loss": 0.0776, "lr": 2.0430189311870324e-05, "epoch": 12.053355335533553, "percentage": 60.27, "elapsed_time": "4:19:32", "remaining_time": "2:51:07", "throughput": 1484.82, "total_tokens": 23123040} {"current_steps": 109570, "total_steps": 181800, "loss": 0.0026, "lr": 2.0427829702676728e-05, "epoch": 12.053905390539054, "percentage": 60.27, "elapsed_time": "4:19:33", "remaining_time": "2:51:06", "throughput": 1484.82, "total_tokens": 23124064} {"current_steps": 109575, "total_steps": 181800, "loss": 0.0398, "lr": 2.0425470135622637e-05, "epoch": 12.054455445544555, "percentage": 60.27, "elapsed_time": "4:19:34", "remaining_time": "2:51:05", "throughput": 1484.82, "total_tokens": 23125152} {"current_steps": 109580, "total_steps": 181800, "loss": 0.0048, "lr": 2.0423110610729788e-05, "epoch": 12.055005500550054, "percentage": 60.28, "elapsed_time": "4:19:35", "remaining_time": "2:51:04", "throughput": 1484.83, "total_tokens": 23126240} {"current_steps": 109585, "total_steps": 181800, "loss": 0.004, "lr": 2.0420751128019935e-05, "epoch": 12.055555555555555, "percentage": 60.28, "elapsed_time": "4:19:35", "remaining_time": "2:51:04", "throughput": 1484.83, "total_tokens": 23127296} {"current_steps": 109590, "total_steps": 181800, "loss": 0.0087, "lr": 2.041839168751482e-05, "epoch": 12.056105610561056, "percentage": 60.28, "elapsed_time": "4:19:36", "remaining_time": "2:51:03", "throughput": 1484.83, "total_tokens": 23128288} {"current_steps": 109595, "total_steps": 181800, "loss": 0.0309, "lr": 2.0416032289236188e-05, "epoch": 12.056655665566556, "percentage": 60.28, "elapsed_time": "4:19:37", "remaining_time": "2:51:02", "throughput": 1484.83, "total_tokens": 23129408} {"current_steps": 109600, "total_steps": 181800, "loss": 0.1445, "lr": 2.0413672933205798e-05, "epoch": 12.057205720572057, "percentage": 60.29, "elapsed_time": "4:19:37", "remaining_time": "2:51:02", "throughput": 1484.83, "total_tokens": 23130432} {"current_steps": 109605, "total_steps": 181800, "loss": 0.0719, "lr": 2.041131361944537e-05, "epoch": 12.057755775577558, "percentage": 60.29, "elapsed_time": "4:19:38", "remaining_time": "2:51:01", "throughput": 1484.83, "total_tokens": 23131520} {"current_steps": 109610, "total_steps": 181800, "loss": 0.0078, "lr": 2.040895434797667e-05, "epoch": 12.058305830583059, "percentage": 60.29, "elapsed_time": "4:19:39", "remaining_time": "2:51:00", "throughput": 1484.83, "total_tokens": 23132544} {"current_steps": 109615, "total_steps": 181800, "loss": 0.0041, "lr": 2.0406595118821438e-05, "epoch": 12.058855885588558, "percentage": 60.29, "elapsed_time": "4:19:39", "remaining_time": "2:50:59", "throughput": 1484.83, "total_tokens": 23133568} {"current_steps": 109620, "total_steps": 181800, "loss": 0.1222, "lr": 2.040423593200141e-05, "epoch": 12.05940594059406, "percentage": 60.3, "elapsed_time": "4:19:40", "remaining_time": "2:50:59", "throughput": 1484.83, "total_tokens": 23134560} {"current_steps": 109625, "total_steps": 181800, "loss": 0.0011, "lr": 2.0401876787538332e-05, "epoch": 12.05995599559956, "percentage": 60.3, "elapsed_time": "4:19:41", "remaining_time": "2:50:58", "throughput": 1484.83, "total_tokens": 23135616} {"current_steps": 109630, "total_steps": 181800, "loss": 0.1926, "lr": 2.039951768545395e-05, "epoch": 12.06050605060506, "percentage": 60.3, "elapsed_time": "4:19:41", "remaining_time": "2:50:57", "throughput": 1484.83, "total_tokens": 23136640} {"current_steps": 109635, "total_steps": 181800, "loss": 0.0483, "lr": 2.039715862577001e-05, "epoch": 12.061056105610561, "percentage": 60.31, "elapsed_time": "4:19:42", "remaining_time": "2:50:56", "throughput": 1484.84, "total_tokens": 23137696} {"current_steps": 109640, "total_steps": 181800, "loss": 0.0095, "lr": 2.039479960850825e-05, "epoch": 12.061606160616062, "percentage": 60.31, "elapsed_time": "4:19:43", "remaining_time": "2:50:56", "throughput": 1484.84, "total_tokens": 23138720} {"current_steps": 109645, "total_steps": 181800, "loss": 0.0414, "lr": 2.0392440633690407e-05, "epoch": 12.062156215621561, "percentage": 60.31, "elapsed_time": "4:19:44", "remaining_time": "2:50:55", "throughput": 1484.84, "total_tokens": 23139744} {"current_steps": 109650, "total_steps": 181800, "loss": 0.0633, "lr": 2.0390081701338233e-05, "epoch": 12.062706270627062, "percentage": 60.31, "elapsed_time": "4:19:44", "remaining_time": "2:50:54", "throughput": 1484.82, "total_tokens": 23140864} {"current_steps": 109655, "total_steps": 181800, "loss": 0.0204, "lr": 2.0387722811473452e-05, "epoch": 12.063256325632564, "percentage": 60.32, "elapsed_time": "4:19:45", "remaining_time": "2:50:54", "throughput": 1484.83, "total_tokens": 23142048} {"current_steps": 109660, "total_steps": 181800, "loss": 0.0238, "lr": 2.0385363964117836e-05, "epoch": 12.063806380638065, "percentage": 60.32, "elapsed_time": "4:19:46", "remaining_time": "2:50:53", "throughput": 1484.83, "total_tokens": 23143040} {"current_steps": 109665, "total_steps": 181800, "loss": 0.0396, "lr": 2.0383005159293096e-05, "epoch": 12.064356435643564, "percentage": 60.32, "elapsed_time": "4:19:47", "remaining_time": "2:50:52", "throughput": 1484.83, "total_tokens": 23144064} {"current_steps": 109670, "total_steps": 181800, "loss": 0.0594, "lr": 2.0380646397020977e-05, "epoch": 12.064906490649065, "percentage": 60.32, "elapsed_time": "4:19:47", "remaining_time": "2:50:52", "throughput": 1484.83, "total_tokens": 23145152} {"current_steps": 109675, "total_steps": 181800, "loss": 0.1785, "lr": 2.0378287677323237e-05, "epoch": 12.065456545654566, "percentage": 60.33, "elapsed_time": "4:19:48", "remaining_time": "2:50:51", "throughput": 1484.83, "total_tokens": 23146176} {"current_steps": 109680, "total_steps": 181800, "loss": 0.0022, "lr": 2.0375929000221592e-05, "epoch": 12.066006600660065, "percentage": 60.33, "elapsed_time": "4:19:49", "remaining_time": "2:50:50", "throughput": 1484.83, "total_tokens": 23147200} {"current_steps": 109685, "total_steps": 181800, "loss": 0.0088, "lr": 2.037357036573779e-05, "epoch": 12.066556655665567, "percentage": 60.33, "elapsed_time": "4:19:49", "remaining_time": "2:50:49", "throughput": 1484.84, "total_tokens": 23148288} {"current_steps": 109690, "total_steps": 181800, "loss": 0.0042, "lr": 2.037121177389358e-05, "epoch": 12.067106710671068, "percentage": 60.34, "elapsed_time": "4:19:50", "remaining_time": "2:50:49", "throughput": 1484.84, "total_tokens": 23149376} {"current_steps": 109695, "total_steps": 181800, "loss": 0.0035, "lr": 2.0368853224710677e-05, "epoch": 12.067656765676567, "percentage": 60.34, "elapsed_time": "4:19:51", "remaining_time": "2:50:48", "throughput": 1484.84, "total_tokens": 23150368} {"current_steps": 109700, "total_steps": 181800, "loss": 0.0022, "lr": 2.036649471821084e-05, "epoch": 12.068206820682068, "percentage": 60.34, "elapsed_time": "4:19:51", "remaining_time": "2:50:47", "throughput": 1484.84, "total_tokens": 23151456} {"current_steps": 109705, "total_steps": 181800, "loss": 0.0049, "lr": 2.0364136254415797e-05, "epoch": 12.06875687568757, "percentage": 60.34, "elapsed_time": "4:19:52", "remaining_time": "2:50:46", "throughput": 1484.84, "total_tokens": 23152512} {"current_steps": 109710, "total_steps": 181800, "loss": 0.0082, "lr": 2.0361777833347272e-05, "epoch": 12.069306930693068, "percentage": 60.35, "elapsed_time": "4:19:53", "remaining_time": "2:50:46", "throughput": 1484.85, "total_tokens": 23153600} {"current_steps": 109715, "total_steps": 181800, "loss": 0.0833, "lr": 2.0359419455027033e-05, "epoch": 12.06985698569857, "percentage": 60.35, "elapsed_time": "4:19:53", "remaining_time": "2:50:45", "throughput": 1484.85, "total_tokens": 23154688} {"current_steps": 109720, "total_steps": 181800, "loss": 0.0334, "lr": 2.0357061119476788e-05, "epoch": 12.07040704070407, "percentage": 60.35, "elapsed_time": "4:19:54", "remaining_time": "2:50:44", "throughput": 1484.85, "total_tokens": 23155776} {"current_steps": 109725, "total_steps": 181800, "loss": 0.0438, "lr": 2.0354702826718287e-05, "epoch": 12.070957095709572, "percentage": 60.35, "elapsed_time": "4:19:55", "remaining_time": "2:50:44", "throughput": 1484.86, "total_tokens": 23156864} {"current_steps": 109730, "total_steps": 181800, "loss": 0.0028, "lr": 2.0352344576773267e-05, "epoch": 12.071507150715071, "percentage": 60.36, "elapsed_time": "4:19:56", "remaining_time": "2:50:43", "throughput": 1484.86, "total_tokens": 23157952} {"current_steps": 109735, "total_steps": 181800, "loss": 0.0065, "lr": 2.0349986369663445e-05, "epoch": 12.072057205720572, "percentage": 60.36, "elapsed_time": "4:19:56", "remaining_time": "2:50:42", "throughput": 1484.87, "total_tokens": 23159072} {"current_steps": 109740, "total_steps": 181800, "loss": 0.0667, "lr": 2.0347628205410573e-05, "epoch": 12.072607260726073, "percentage": 60.36, "elapsed_time": "4:19:57", "remaining_time": "2:50:41", "throughput": 1484.88, "total_tokens": 23160256} {"current_steps": 109745, "total_steps": 181800, "loss": 0.1722, "lr": 2.0345270084036376e-05, "epoch": 12.073157315731573, "percentage": 60.37, "elapsed_time": "4:19:58", "remaining_time": "2:50:41", "throughput": 1484.89, "total_tokens": 23161408} {"current_steps": 109750, "total_steps": 181800, "loss": 0.0056, "lr": 2.03429120055626e-05, "epoch": 12.073707370737074, "percentage": 60.37, "elapsed_time": "4:19:58", "remaining_time": "2:50:40", "throughput": 1484.89, "total_tokens": 23162400} {"current_steps": 109755, "total_steps": 181800, "loss": 0.0079, "lr": 2.034055397001096e-05, "epoch": 12.074257425742575, "percentage": 60.37, "elapsed_time": "4:19:59", "remaining_time": "2:50:39", "throughput": 1484.89, "total_tokens": 23163456} {"current_steps": 109760, "total_steps": 181800, "loss": 0.1378, "lr": 2.03381959774032e-05, "epoch": 12.074807480748074, "percentage": 60.37, "elapsed_time": "4:20:00", "remaining_time": "2:50:39", "throughput": 1484.89, "total_tokens": 23164544} {"current_steps": 109765, "total_steps": 181800, "loss": 0.0088, "lr": 2.0335838027761058e-05, "epoch": 12.075357535753575, "percentage": 60.38, "elapsed_time": "4:20:00", "remaining_time": "2:50:38", "throughput": 1484.89, "total_tokens": 23165600} {"current_steps": 109770, "total_steps": 181800, "loss": 0.0114, "lr": 2.0333480121106243e-05, "epoch": 12.075907590759076, "percentage": 60.38, "elapsed_time": "4:20:01", "remaining_time": "2:50:37", "throughput": 1484.9, "total_tokens": 23166656} {"current_steps": 109775, "total_steps": 181800, "loss": 0.0211, "lr": 2.033112225746052e-05, "epoch": 12.076457645764576, "percentage": 60.38, "elapsed_time": "4:20:02", "remaining_time": "2:50:36", "throughput": 1484.9, "total_tokens": 23167712} {"current_steps": 109780, "total_steps": 181800, "loss": 0.0024, "lr": 2.0328764436845597e-05, "epoch": 12.077007700770077, "percentage": 60.39, "elapsed_time": "4:20:02", "remaining_time": "2:50:36", "throughput": 1484.9, "total_tokens": 23168768} {"current_steps": 109785, "total_steps": 181800, "loss": 0.0633, "lr": 2.0326406659283204e-05, "epoch": 12.077557755775578, "percentage": 60.39, "elapsed_time": "4:20:03", "remaining_time": "2:50:35", "throughput": 1484.9, "total_tokens": 23169760} {"current_steps": 109790, "total_steps": 181800, "loss": 0.007, "lr": 2.032404892479509e-05, "epoch": 12.078107810781079, "percentage": 60.39, "elapsed_time": "4:20:04", "remaining_time": "2:50:34", "throughput": 1484.9, "total_tokens": 23170848} {"current_steps": 109795, "total_steps": 181800, "loss": 0.0134, "lr": 2.0321691233402962e-05, "epoch": 12.078657865786578, "percentage": 60.39, "elapsed_time": "4:20:04", "remaining_time": "2:50:33", "throughput": 1484.9, "total_tokens": 23171904} {"current_steps": 109800, "total_steps": 181800, "loss": 0.0438, "lr": 2.0319333585128565e-05, "epoch": 12.07920792079208, "percentage": 60.4, "elapsed_time": "4:20:05", "remaining_time": "2:50:33", "throughput": 1484.9, "total_tokens": 23172928} {"current_steps": 109805, "total_steps": 181800, "loss": 0.0025, "lr": 2.031697597999363e-05, "epoch": 12.07975797579758, "percentage": 60.4, "elapsed_time": "4:20:06", "remaining_time": "2:50:32", "throughput": 1484.91, "total_tokens": 23174016} {"current_steps": 109810, "total_steps": 181800, "loss": 0.0054, "lr": 2.031461841801987e-05, "epoch": 12.08030803080308, "percentage": 60.4, "elapsed_time": "4:20:07", "remaining_time": "2:50:31", "throughput": 1484.91, "total_tokens": 23175072} {"current_steps": 109815, "total_steps": 181800, "loss": 0.0383, "lr": 2.031226089922903e-05, "epoch": 12.08085808580858, "percentage": 60.4, "elapsed_time": "4:20:07", "remaining_time": "2:50:31", "throughput": 1484.92, "total_tokens": 23176192} {"current_steps": 109820, "total_steps": 181800, "loss": 0.0082, "lr": 2.030990342364283e-05, "epoch": 12.081408140814082, "percentage": 60.41, "elapsed_time": "4:20:08", "remaining_time": "2:50:30", "throughput": 1484.92, "total_tokens": 23177248} {"current_steps": 109825, "total_steps": 181800, "loss": 0.0061, "lr": 2.0307545991283005e-05, "epoch": 12.081958195819581, "percentage": 60.41, "elapsed_time": "4:20:09", "remaining_time": "2:50:29", "throughput": 1484.92, "total_tokens": 23178272} {"current_steps": 109830, "total_steps": 181800, "loss": 0.0166, "lr": 2.0305188602171274e-05, "epoch": 12.082508250825082, "percentage": 60.41, "elapsed_time": "4:20:09", "remaining_time": "2:50:28", "throughput": 1484.92, "total_tokens": 23179360} {"current_steps": 109835, "total_steps": 181800, "loss": 0.0032, "lr": 2.030283125632936e-05, "epoch": 12.083058305830583, "percentage": 60.42, "elapsed_time": "4:20:10", "remaining_time": "2:50:28", "throughput": 1484.92, "total_tokens": 23180384} {"current_steps": 109840, "total_steps": 181800, "loss": 0.0737, "lr": 2.0300473953779003e-05, "epoch": 12.083608360836084, "percentage": 60.42, "elapsed_time": "4:20:11", "remaining_time": "2:50:27", "throughput": 1484.93, "total_tokens": 23181504} {"current_steps": 109845, "total_steps": 181800, "loss": 0.0072, "lr": 2.0298116694541916e-05, "epoch": 12.084158415841584, "percentage": 60.42, "elapsed_time": "4:20:11", "remaining_time": "2:50:26", "throughput": 1484.93, "total_tokens": 23182528} {"current_steps": 109850, "total_steps": 181800, "loss": 0.0847, "lr": 2.029575947863984e-05, "epoch": 12.084708470847085, "percentage": 60.42, "elapsed_time": "4:20:12", "remaining_time": "2:50:26", "throughput": 1484.93, "total_tokens": 23183552} {"current_steps": 109855, "total_steps": 181800, "loss": 0.012, "lr": 2.029340230609449e-05, "epoch": 12.085258525852586, "percentage": 60.43, "elapsed_time": "4:20:13", "remaining_time": "2:50:25", "throughput": 1484.93, "total_tokens": 23184576} {"current_steps": 109860, "total_steps": 181800, "loss": 0.0209, "lr": 2.0291045176927587e-05, "epoch": 12.085808580858085, "percentage": 60.43, "elapsed_time": "4:20:13", "remaining_time": "2:50:24", "throughput": 1484.93, "total_tokens": 23185664} {"current_steps": 109865, "total_steps": 181800, "loss": 0.0994, "lr": 2.0288688091160872e-05, "epoch": 12.086358635863586, "percentage": 60.43, "elapsed_time": "4:20:14", "remaining_time": "2:50:23", "throughput": 1484.93, "total_tokens": 23186720} {"current_steps": 109870, "total_steps": 181800, "loss": 0.0498, "lr": 2.028633104881605e-05, "epoch": 12.086908690869087, "percentage": 60.43, "elapsed_time": "4:20:15", "remaining_time": "2:50:23", "throughput": 1484.93, "total_tokens": 23187744} {"current_steps": 109875, "total_steps": 181800, "loss": 0.0028, "lr": 2.028397404991485e-05, "epoch": 12.087458745874587, "percentage": 60.44, "elapsed_time": "4:20:16", "remaining_time": "2:50:22", "throughput": 1484.93, "total_tokens": 23188768} {"current_steps": 109880, "total_steps": 181800, "loss": 0.0035, "lr": 2.028161709447901e-05, "epoch": 12.088008800880088, "percentage": 60.44, "elapsed_time": "4:20:16", "remaining_time": "2:50:21", "throughput": 1484.93, "total_tokens": 23189824} {"current_steps": 109885, "total_steps": 181800, "loss": 0.0079, "lr": 2.0279260182530228e-05, "epoch": 12.088558855885589, "percentage": 60.44, "elapsed_time": "4:20:17", "remaining_time": "2:50:20", "throughput": 1484.94, "total_tokens": 23190912} {"current_steps": 109890, "total_steps": 181800, "loss": 0.033, "lr": 2.0276903314090246e-05, "epoch": 12.089108910891088, "percentage": 60.45, "elapsed_time": "4:20:18", "remaining_time": "2:50:20", "throughput": 1484.94, "total_tokens": 23191936} {"current_steps": 109895, "total_steps": 181800, "loss": 0.0042, "lr": 2.0274546489180778e-05, "epoch": 12.08965896589659, "percentage": 60.45, "elapsed_time": "4:20:18", "remaining_time": "2:50:19", "throughput": 1484.94, "total_tokens": 23192992} {"current_steps": 109900, "total_steps": 181800, "loss": 0.0158, "lr": 2.0272189707823545e-05, "epoch": 12.09020902090209, "percentage": 60.45, "elapsed_time": "4:20:19", "remaining_time": "2:50:18", "throughput": 1484.94, "total_tokens": 23194048} {"current_steps": 109905, "total_steps": 181800, "loss": 0.0114, "lr": 2.026983297004028e-05, "epoch": 12.090759075907592, "percentage": 60.45, "elapsed_time": "4:20:20", "remaining_time": "2:50:18", "throughput": 1484.94, "total_tokens": 23195072} {"current_steps": 109910, "total_steps": 181800, "loss": 0.0979, "lr": 2.026747627585268e-05, "epoch": 12.091309130913091, "percentage": 60.46, "elapsed_time": "4:20:20", "remaining_time": "2:50:17", "throughput": 1484.94, "total_tokens": 23196128} {"current_steps": 109915, "total_steps": 181800, "loss": 0.0038, "lr": 2.0265119625282492e-05, "epoch": 12.091859185918592, "percentage": 60.46, "elapsed_time": "4:20:21", "remaining_time": "2:50:16", "throughput": 1484.94, "total_tokens": 23197152} {"current_steps": 109920, "total_steps": 181800, "loss": 0.0046, "lr": 2.0262763018351427e-05, "epoch": 12.092409240924093, "percentage": 60.46, "elapsed_time": "4:20:22", "remaining_time": "2:50:15", "throughput": 1484.94, "total_tokens": 23198208} {"current_steps": 109925, "total_steps": 181800, "loss": 0.0065, "lr": 2.0260406455081193e-05, "epoch": 12.092959295929592, "percentage": 60.46, "elapsed_time": "4:20:22", "remaining_time": "2:50:15", "throughput": 1484.95, "total_tokens": 23199328} {"current_steps": 109930, "total_steps": 181800, "loss": 0.1095, "lr": 2.0258049935493523e-05, "epoch": 12.093509350935093, "percentage": 60.47, "elapsed_time": "4:20:23", "remaining_time": "2:50:14", "throughput": 1484.95, "total_tokens": 23200352} {"current_steps": 109935, "total_steps": 181800, "loss": 0.1009, "lr": 2.0255693459610127e-05, "epoch": 12.094059405940595, "percentage": 60.47, "elapsed_time": "4:20:24", "remaining_time": "2:50:13", "throughput": 1484.95, "total_tokens": 23201440} {"current_steps": 109940, "total_steps": 181800, "loss": 0.011, "lr": 2.0253337027452733e-05, "epoch": 12.094609460946094, "percentage": 60.47, "elapsed_time": "4:20:25", "remaining_time": "2:50:12", "throughput": 1484.96, "total_tokens": 23202496} {"current_steps": 109945, "total_steps": 181800, "loss": 0.003, "lr": 2.0250980639043053e-05, "epoch": 12.095159515951595, "percentage": 60.48, "elapsed_time": "4:20:25", "remaining_time": "2:50:12", "throughput": 1484.95, "total_tokens": 23203456} {"current_steps": 109950, "total_steps": 181800, "loss": 0.0273, "lr": 2.02486242944028e-05, "epoch": 12.095709570957096, "percentage": 60.48, "elapsed_time": "4:20:26", "remaining_time": "2:50:11", "throughput": 1484.96, "total_tokens": 23204544} {"current_steps": 109955, "total_steps": 181800, "loss": 0.0027, "lr": 2.0246267993553702e-05, "epoch": 12.096259625962595, "percentage": 60.48, "elapsed_time": "4:20:27", "remaining_time": "2:50:10", "throughput": 1484.96, "total_tokens": 23205632} {"current_steps": 109960, "total_steps": 181800, "loss": 0.0467, "lr": 2.0243911736517466e-05, "epoch": 12.096809680968097, "percentage": 60.48, "elapsed_time": "4:20:27", "remaining_time": "2:50:10", "throughput": 1484.96, "total_tokens": 23206656} {"current_steps": 109965, "total_steps": 181800, "loss": 0.1575, "lr": 2.0241555523315826e-05, "epoch": 12.097359735973598, "percentage": 60.49, "elapsed_time": "4:20:28", "remaining_time": "2:50:09", "throughput": 1484.96, "total_tokens": 23207712} {"current_steps": 109970, "total_steps": 181800, "loss": 0.0034, "lr": 2.023919935397048e-05, "epoch": 12.097909790979099, "percentage": 60.49, "elapsed_time": "4:20:29", "remaining_time": "2:50:08", "throughput": 1484.96, "total_tokens": 23208768} {"current_steps": 109975, "total_steps": 181800, "loss": 0.0018, "lr": 2.023684322850314e-05, "epoch": 12.098459845984598, "percentage": 60.49, "elapsed_time": "4:20:29", "remaining_time": "2:50:07", "throughput": 1484.97, "total_tokens": 23209824} {"current_steps": 109980, "total_steps": 181800, "loss": 0.0065, "lr": 2.023448714693554e-05, "epoch": 12.099009900990099, "percentage": 60.5, "elapsed_time": "4:20:30", "remaining_time": "2:50:07", "throughput": 1484.97, "total_tokens": 23210912} {"current_steps": 109985, "total_steps": 181800, "loss": 0.0037, "lr": 2.023213110928938e-05, "epoch": 12.0995599559956, "percentage": 60.5, "elapsed_time": "4:20:31", "remaining_time": "2:50:06", "throughput": 1484.98, "total_tokens": 23212032} {"current_steps": 109990, "total_steps": 181800, "loss": 0.0365, "lr": 2.022977511558638e-05, "epoch": 12.1001100110011, "percentage": 60.5, "elapsed_time": "4:20:31", "remaining_time": "2:50:05", "throughput": 1484.98, "total_tokens": 23213120} {"current_steps": 109995, "total_steps": 181800, "loss": 0.0266, "lr": 2.0227419165848262e-05, "epoch": 12.1006600660066, "percentage": 60.5, "elapsed_time": "4:20:32", "remaining_time": "2:50:05", "throughput": 1484.99, "total_tokens": 23214272} {"current_steps": 110000, "total_steps": 181800, "loss": 0.0764, "lr": 2.0225063260096723e-05, "epoch": 12.101210121012102, "percentage": 60.51, "elapsed_time": "4:20:33", "remaining_time": "2:50:04", "throughput": 1484.99, "total_tokens": 23215296} {"current_steps": 110005, "total_steps": 181800, "loss": 0.0954, "lr": 2.0222707398353484e-05, "epoch": 12.101760176017601, "percentage": 60.51, "elapsed_time": "4:20:33", "remaining_time": "2:50:03", "throughput": 1484.99, "total_tokens": 23216352} {"current_steps": 110010, "total_steps": 181800, "loss": 0.0473, "lr": 2.0220351580640255e-05, "epoch": 12.102310231023102, "percentage": 60.51, "elapsed_time": "4:20:34", "remaining_time": "2:50:02", "throughput": 1485.0, "total_tokens": 23217440} {"current_steps": 110015, "total_steps": 181800, "loss": 0.0407, "lr": 2.0217995806978763e-05, "epoch": 12.102860286028603, "percentage": 60.51, "elapsed_time": "4:20:35", "remaining_time": "2:50:02", "throughput": 1484.99, "total_tokens": 23218432} {"current_steps": 110020, "total_steps": 181800, "loss": 0.0675, "lr": 2.0215640077390706e-05, "epoch": 12.103410341034103, "percentage": 60.52, "elapsed_time": "4:20:36", "remaining_time": "2:50:01", "throughput": 1484.99, "total_tokens": 23219424} {"current_steps": 110025, "total_steps": 181800, "loss": 0.0367, "lr": 2.0213284391897792e-05, "epoch": 12.103960396039604, "percentage": 60.52, "elapsed_time": "4:20:36", "remaining_time": "2:50:00", "throughput": 1484.99, "total_tokens": 23220416} {"current_steps": 110030, "total_steps": 181800, "loss": 0.0023, "lr": 2.0210928750521745e-05, "epoch": 12.104510451045105, "percentage": 60.52, "elapsed_time": "4:20:37", "remaining_time": "2:49:59", "throughput": 1484.99, "total_tokens": 23221472} {"current_steps": 110035, "total_steps": 181800, "loss": 0.0469, "lr": 2.0208573153284267e-05, "epoch": 12.105060506050606, "percentage": 60.53, "elapsed_time": "4:20:38", "remaining_time": "2:49:59", "throughput": 1484.99, "total_tokens": 23222432} {"current_steps": 110040, "total_steps": 181800, "loss": 0.0033, "lr": 2.020621760020708e-05, "epoch": 12.105610561056105, "percentage": 60.53, "elapsed_time": "4:20:38", "remaining_time": "2:49:58", "throughput": 1484.99, "total_tokens": 23223456} {"current_steps": 110045, "total_steps": 181800, "loss": 0.0085, "lr": 2.0203862091311877e-05, "epoch": 12.106160616061606, "percentage": 60.53, "elapsed_time": "4:20:39", "remaining_time": "2:49:57", "throughput": 1484.99, "total_tokens": 23224544} {"current_steps": 110050, "total_steps": 181800, "loss": 0.0332, "lr": 2.020150662662037e-05, "epoch": 12.106710671067107, "percentage": 60.53, "elapsed_time": "4:20:40", "remaining_time": "2:49:57", "throughput": 1485.0, "total_tokens": 23225600} {"current_steps": 110055, "total_steps": 181800, "loss": 0.0101, "lr": 2.0199151206154288e-05, "epoch": 12.107260726072607, "percentage": 60.54, "elapsed_time": "4:20:40", "remaining_time": "2:49:56", "throughput": 1485.0, "total_tokens": 23226688} {"current_steps": 110060, "total_steps": 181800, "loss": 0.0051, "lr": 2.0196795829935315e-05, "epoch": 12.107810781078108, "percentage": 60.54, "elapsed_time": "4:20:41", "remaining_time": "2:49:55", "throughput": 1485.0, "total_tokens": 23227712} {"current_steps": 110065, "total_steps": 181800, "loss": 0.0437, "lr": 2.019444049798517e-05, "epoch": 12.108360836083609, "percentage": 60.54, "elapsed_time": "4:20:42", "remaining_time": "2:49:54", "throughput": 1485.0, "total_tokens": 23228736} {"current_steps": 110070, "total_steps": 181800, "loss": 0.0899, "lr": 2.019208521032557e-05, "epoch": 12.108910891089108, "percentage": 60.54, "elapsed_time": "4:20:42", "remaining_time": "2:49:54", "throughput": 1485.0, "total_tokens": 23229824} {"current_steps": 110075, "total_steps": 181800, "loss": 0.1891, "lr": 2.0189729966978196e-05, "epoch": 12.10946094609461, "percentage": 60.55, "elapsed_time": "4:20:43", "remaining_time": "2:49:53", "throughput": 1485.01, "total_tokens": 23230944} {"current_steps": 110080, "total_steps": 181800, "loss": 0.1967, "lr": 2.0187374767964788e-05, "epoch": 12.11001100110011, "percentage": 60.55, "elapsed_time": "4:20:44", "remaining_time": "2:49:52", "throughput": 1485.01, "total_tokens": 23231968} {"current_steps": 110085, "total_steps": 181800, "loss": 0.0428, "lr": 2.018501961330704e-05, "epoch": 12.110561056105611, "percentage": 60.55, "elapsed_time": "4:20:45", "remaining_time": "2:49:51", "throughput": 1485.01, "total_tokens": 23233056} {"current_steps": 110090, "total_steps": 181800, "loss": 0.0304, "lr": 2.018266450302664e-05, "epoch": 12.11111111111111, "percentage": 60.56, "elapsed_time": "4:20:45", "remaining_time": "2:49:51", "throughput": 1485.02, "total_tokens": 23234112} {"current_steps": 110095, "total_steps": 181800, "loss": 0.0022, "lr": 2.0180309437145327e-05, "epoch": 12.111661166116612, "percentage": 60.56, "elapsed_time": "4:20:46", "remaining_time": "2:49:50", "throughput": 1485.02, "total_tokens": 23235168} {"current_steps": 110100, "total_steps": 181800, "loss": 0.0075, "lr": 2.0177954415684776e-05, "epoch": 12.112211221122113, "percentage": 60.56, "elapsed_time": "4:20:47", "remaining_time": "2:49:49", "throughput": 1485.02, "total_tokens": 23236256} {"current_steps": 110105, "total_steps": 181800, "loss": 0.0024, "lr": 2.0175599438666713e-05, "epoch": 12.112761276127612, "percentage": 60.56, "elapsed_time": "4:20:47", "remaining_time": "2:49:49", "throughput": 1485.02, "total_tokens": 23237280} {"current_steps": 110110, "total_steps": 181800, "loss": 0.0024, "lr": 2.0173244506112837e-05, "epoch": 12.113311331133113, "percentage": 60.57, "elapsed_time": "4:20:48", "remaining_time": "2:49:48", "throughput": 1485.02, "total_tokens": 23238304} {"current_steps": 110115, "total_steps": 181800, "loss": 0.1236, "lr": 2.017088961804484e-05, "epoch": 12.113861386138614, "percentage": 60.57, "elapsed_time": "4:20:49", "remaining_time": "2:49:47", "throughput": 1485.02, "total_tokens": 23239328} {"current_steps": 110120, "total_steps": 181800, "loss": 0.0092, "lr": 2.0168534774484445e-05, "epoch": 12.114411441144114, "percentage": 60.57, "elapsed_time": "4:20:49", "remaining_time": "2:49:46", "throughput": 1485.02, "total_tokens": 23240320} {"current_steps": 110125, "total_steps": 181800, "loss": 0.0709, "lr": 2.0166179975453336e-05, "epoch": 12.114961496149615, "percentage": 60.57, "elapsed_time": "4:20:50", "remaining_time": "2:49:46", "throughput": 1485.02, "total_tokens": 23241280} {"current_steps": 110130, "total_steps": 181800, "loss": 0.0025, "lr": 2.0163825220973237e-05, "epoch": 12.115511551155116, "percentage": 60.58, "elapsed_time": "4:20:51", "remaining_time": "2:49:45", "throughput": 1485.01, "total_tokens": 23242272} {"current_steps": 110135, "total_steps": 181800, "loss": 0.0461, "lr": 2.0161470511065844e-05, "epoch": 12.116061606160615, "percentage": 60.58, "elapsed_time": "4:20:51", "remaining_time": "2:49:44", "throughput": 1485.02, "total_tokens": 23243328} {"current_steps": 110140, "total_steps": 181800, "loss": 0.0128, "lr": 2.0159115845752842e-05, "epoch": 12.116611661166116, "percentage": 60.58, "elapsed_time": "4:20:52", "remaining_time": "2:49:43", "throughput": 1485.02, "total_tokens": 23244352} {"current_steps": 110145, "total_steps": 181800, "loss": 0.0626, "lr": 2.0156761225055956e-05, "epoch": 12.117161716171617, "percentage": 60.59, "elapsed_time": "4:20:53", "remaining_time": "2:49:43", "throughput": 1485.02, "total_tokens": 23245472} {"current_steps": 110150, "total_steps": 181800, "loss": 0.177, "lr": 2.0154406648996872e-05, "epoch": 12.117711771177119, "percentage": 60.59, "elapsed_time": "4:20:53", "remaining_time": "2:49:42", "throughput": 1485.03, "total_tokens": 23246560} {"current_steps": 110155, "total_steps": 181800, "loss": 0.0541, "lr": 2.0152052117597303e-05, "epoch": 12.118261826182618, "percentage": 60.59, "elapsed_time": "4:20:54", "remaining_time": "2:49:41", "throughput": 1485.02, "total_tokens": 23247552} {"current_steps": 110160, "total_steps": 181800, "loss": 0.1811, "lr": 2.014969763087894e-05, "epoch": 12.118811881188119, "percentage": 60.59, "elapsed_time": "4:20:55", "remaining_time": "2:49:41", "throughput": 1485.03, "total_tokens": 23248672} {"current_steps": 110165, "total_steps": 181800, "loss": 0.0756, "lr": 2.0147343188863485e-05, "epoch": 12.11936193619362, "percentage": 60.6, "elapsed_time": "4:20:56", "remaining_time": "2:49:40", "throughput": 1485.02, "total_tokens": 23249632} {"current_steps": 110170, "total_steps": 181800, "loss": 0.0193, "lr": 2.0144988791572647e-05, "epoch": 12.11991199119912, "percentage": 60.6, "elapsed_time": "4:20:56", "remaining_time": "2:49:39", "throughput": 1485.02, "total_tokens": 23250656} {"current_steps": 110175, "total_steps": 181800, "loss": 0.0235, "lr": 2.014263443902811e-05, "epoch": 12.12046204620462, "percentage": 60.6, "elapsed_time": "4:20:57", "remaining_time": "2:49:38", "throughput": 1485.03, "total_tokens": 23251712} {"current_steps": 110180, "total_steps": 181800, "loss": 0.0046, "lr": 2.014028013125158e-05, "epoch": 12.121012101210122, "percentage": 60.61, "elapsed_time": "4:20:58", "remaining_time": "2:49:38", "throughput": 1485.03, "total_tokens": 23252800} {"current_steps": 110185, "total_steps": 181800, "loss": 0.0114, "lr": 2.0137925868264764e-05, "epoch": 12.12156215621562, "percentage": 60.61, "elapsed_time": "4:20:58", "remaining_time": "2:49:37", "throughput": 1485.03, "total_tokens": 23253824} {"current_steps": 110190, "total_steps": 181800, "loss": 0.0229, "lr": 2.013557165008934e-05, "epoch": 12.122112211221122, "percentage": 60.61, "elapsed_time": "4:20:59", "remaining_time": "2:49:36", "throughput": 1485.04, "total_tokens": 23254944} {"current_steps": 110195, "total_steps": 181800, "loss": 0.0252, "lr": 2.0133217476747028e-05, "epoch": 12.122662266226623, "percentage": 60.61, "elapsed_time": "4:21:00", "remaining_time": "2:49:36", "throughput": 1485.04, "total_tokens": 23256000} {"current_steps": 110200, "total_steps": 181800, "loss": 0.0639, "lr": 2.0130863348259507e-05, "epoch": 12.123212321232122, "percentage": 60.62, "elapsed_time": "4:21:00", "remaining_time": "2:49:35", "throughput": 1485.04, "total_tokens": 23257024} {"current_steps": 110205, "total_steps": 181800, "loss": 0.0329, "lr": 2.012850926464849e-05, "epoch": 12.123762376237623, "percentage": 60.62, "elapsed_time": "4:21:01", "remaining_time": "2:49:34", "throughput": 1485.04, "total_tokens": 23258080} {"current_steps": 110210, "total_steps": 181800, "loss": 0.0646, "lr": 2.012615522593567e-05, "epoch": 12.124312431243125, "percentage": 60.62, "elapsed_time": "4:21:02", "remaining_time": "2:49:33", "throughput": 1485.04, "total_tokens": 23259136} {"current_steps": 110215, "total_steps": 181800, "loss": 0.1254, "lr": 2.0123801232142723e-05, "epoch": 12.124862486248626, "percentage": 60.62, "elapsed_time": "4:21:02", "remaining_time": "2:49:33", "throughput": 1485.05, "total_tokens": 23260224} {"current_steps": 110220, "total_steps": 181800, "loss": 0.0883, "lr": 2.012144728329137e-05, "epoch": 12.125412541254125, "percentage": 60.63, "elapsed_time": "4:21:03", "remaining_time": "2:49:32", "throughput": 1485.05, "total_tokens": 23261312} {"current_steps": 110225, "total_steps": 181800, "loss": 0.0348, "lr": 2.011909337940329e-05, "epoch": 12.125962596259626, "percentage": 60.63, "elapsed_time": "4:21:04", "remaining_time": "2:49:31", "throughput": 1485.05, "total_tokens": 23262336} {"current_steps": 110230, "total_steps": 181800, "loss": 0.0094, "lr": 2.0116739520500194e-05, "epoch": 12.126512651265127, "percentage": 60.63, "elapsed_time": "4:21:05", "remaining_time": "2:49:30", "throughput": 1485.05, "total_tokens": 23263392} {"current_steps": 110235, "total_steps": 181800, "loss": 0.0194, "lr": 2.0114385706603762e-05, "epoch": 12.127062706270626, "percentage": 60.64, "elapsed_time": "4:21:05", "remaining_time": "2:49:30", "throughput": 1485.05, "total_tokens": 23264416} {"current_steps": 110240, "total_steps": 181800, "loss": 0.0068, "lr": 2.0112031937735686e-05, "epoch": 12.127612761276128, "percentage": 60.64, "elapsed_time": "4:21:06", "remaining_time": "2:49:29", "throughput": 1485.06, "total_tokens": 23265504} {"current_steps": 110245, "total_steps": 181800, "loss": 0.0075, "lr": 2.010967821391768e-05, "epoch": 12.128162816281629, "percentage": 60.64, "elapsed_time": "4:21:07", "remaining_time": "2:49:28", "throughput": 1485.06, "total_tokens": 23266560} {"current_steps": 110250, "total_steps": 181800, "loss": 0.0418, "lr": 2.0107324535171417e-05, "epoch": 12.128712871287128, "percentage": 60.64, "elapsed_time": "4:21:07", "remaining_time": "2:49:28", "throughput": 1485.06, "total_tokens": 23267616} {"current_steps": 110255, "total_steps": 181800, "loss": 0.0538, "lr": 2.0104970901518588e-05, "epoch": 12.129262926292629, "percentage": 60.65, "elapsed_time": "4:21:08", "remaining_time": "2:49:27", "throughput": 1485.06, "total_tokens": 23268640} {"current_steps": 110260, "total_steps": 181800, "loss": 0.0726, "lr": 2.0102617312980903e-05, "epoch": 12.12981298129813, "percentage": 60.65, "elapsed_time": "4:21:09", "remaining_time": "2:49:26", "throughput": 1485.07, "total_tokens": 23269728} {"current_steps": 110265, "total_steps": 181800, "loss": 0.0739, "lr": 2.0100263769580034e-05, "epoch": 12.130363036303631, "percentage": 60.65, "elapsed_time": "4:21:09", "remaining_time": "2:49:25", "throughput": 1485.07, "total_tokens": 23270784} {"current_steps": 110270, "total_steps": 181800, "loss": 0.0241, "lr": 2.0097910271337698e-05, "epoch": 12.13091309130913, "percentage": 60.65, "elapsed_time": "4:21:10", "remaining_time": "2:49:25", "throughput": 1485.07, "total_tokens": 23271840} {"current_steps": 110275, "total_steps": 181800, "loss": 0.0089, "lr": 2.0095556818275563e-05, "epoch": 12.131463146314632, "percentage": 60.66, "elapsed_time": "4:21:11", "remaining_time": "2:49:24", "throughput": 1485.07, "total_tokens": 23272928} {"current_steps": 110280, "total_steps": 181800, "loss": 0.0207, "lr": 2.0093203410415324e-05, "epoch": 12.132013201320133, "percentage": 60.66, "elapsed_time": "4:21:11", "remaining_time": "2:49:23", "throughput": 1485.07, "total_tokens": 23273984} {"current_steps": 110285, "total_steps": 181800, "loss": 0.0062, "lr": 2.0090850047778683e-05, "epoch": 12.132563256325632, "percentage": 60.66, "elapsed_time": "4:21:12", "remaining_time": "2:49:23", "throughput": 1485.08, "total_tokens": 23275040} {"current_steps": 110290, "total_steps": 181800, "loss": 0.0091, "lr": 2.0088496730387313e-05, "epoch": 12.133113311331133, "percentage": 60.67, "elapsed_time": "4:21:13", "remaining_time": "2:49:22", "throughput": 1485.08, "total_tokens": 23276096} {"current_steps": 110295, "total_steps": 181800, "loss": 0.0856, "lr": 2.0086143458262912e-05, "epoch": 12.133663366336634, "percentage": 60.67, "elapsed_time": "4:21:14", "remaining_time": "2:49:21", "throughput": 1485.08, "total_tokens": 23277184} {"current_steps": 110300, "total_steps": 181800, "loss": 0.0949, "lr": 2.008379023142718e-05, "epoch": 12.134213421342134, "percentage": 60.67, "elapsed_time": "4:21:14", "remaining_time": "2:49:20", "throughput": 1485.08, "total_tokens": 23278240} {"current_steps": 110305, "total_steps": 181800, "loss": 0.0234, "lr": 2.0081437049901782e-05, "epoch": 12.134763476347635, "percentage": 60.67, "elapsed_time": "4:21:15", "remaining_time": "2:49:20", "throughput": 1485.08, "total_tokens": 23279264} {"current_steps": 110310, "total_steps": 181800, "loss": 0.0317, "lr": 2.0079083913708425e-05, "epoch": 12.135313531353136, "percentage": 60.68, "elapsed_time": "4:21:16", "remaining_time": "2:49:19", "throughput": 1485.09, "total_tokens": 23280320} {"current_steps": 110315, "total_steps": 181800, "loss": 0.0149, "lr": 2.0076730822868784e-05, "epoch": 12.135863586358635, "percentage": 60.68, "elapsed_time": "4:21:16", "remaining_time": "2:49:18", "throughput": 1485.09, "total_tokens": 23281408} {"current_steps": 110320, "total_steps": 181800, "loss": 0.029, "lr": 2.0074377777404558e-05, "epoch": 12.136413641364136, "percentage": 60.68, "elapsed_time": "4:21:17", "remaining_time": "2:49:17", "throughput": 1485.09, "total_tokens": 23282464} {"current_steps": 110325, "total_steps": 181800, "loss": 0.0057, "lr": 2.0072024777337432e-05, "epoch": 12.136963696369637, "percentage": 60.68, "elapsed_time": "4:21:18", "remaining_time": "2:49:17", "throughput": 1485.09, "total_tokens": 23283488} {"current_steps": 110330, "total_steps": 181800, "loss": 0.1, "lr": 2.0069671822689077e-05, "epoch": 12.137513751375138, "percentage": 60.69, "elapsed_time": "4:21:18", "remaining_time": "2:49:16", "throughput": 1485.1, "total_tokens": 23284544} {"current_steps": 110335, "total_steps": 181800, "loss": 0.1397, "lr": 2.00673189134812e-05, "epoch": 12.138063806380638, "percentage": 60.69, "elapsed_time": "4:21:19", "remaining_time": "2:49:15", "throughput": 1485.1, "total_tokens": 23285664} {"current_steps": 110340, "total_steps": 181800, "loss": 0.0181, "lr": 2.0064966049735473e-05, "epoch": 12.138613861386139, "percentage": 60.69, "elapsed_time": "4:21:20", "remaining_time": "2:49:15", "throughput": 1485.1, "total_tokens": 23286688} {"current_steps": 110345, "total_steps": 181800, "loss": 0.1415, "lr": 2.006261323147359e-05, "epoch": 12.13916391639164, "percentage": 60.7, "elapsed_time": "4:21:20", "remaining_time": "2:49:14", "throughput": 1485.1, "total_tokens": 23287712} {"current_steps": 110350, "total_steps": 181800, "loss": 0.0234, "lr": 2.0060260458717234e-05, "epoch": 12.13971397139714, "percentage": 60.7, "elapsed_time": "4:21:21", "remaining_time": "2:49:13", "throughput": 1485.1, "total_tokens": 23288768} {"current_steps": 110355, "total_steps": 181800, "loss": 0.0124, "lr": 2.005790773148808e-05, "epoch": 12.14026402640264, "percentage": 60.7, "elapsed_time": "4:21:22", "remaining_time": "2:49:12", "throughput": 1485.1, "total_tokens": 23289824} {"current_steps": 110360, "total_steps": 181800, "loss": 0.0119, "lr": 2.005555504980783e-05, "epoch": 12.140814081408141, "percentage": 60.7, "elapsed_time": "4:21:22", "remaining_time": "2:49:12", "throughput": 1485.11, "total_tokens": 23291008} {"current_steps": 110365, "total_steps": 181800, "loss": 0.0135, "lr": 2.005320241369814e-05, "epoch": 12.14136413641364, "percentage": 60.71, "elapsed_time": "4:21:23", "remaining_time": "2:49:11", "throughput": 1485.12, "total_tokens": 23292096} {"current_steps": 110370, "total_steps": 181800, "loss": 0.0069, "lr": 2.005084982318072e-05, "epoch": 12.141914191419142, "percentage": 60.71, "elapsed_time": "4:21:24", "remaining_time": "2:49:10", "throughput": 1485.12, "total_tokens": 23293120} {"current_steps": 110375, "total_steps": 181800, "loss": 0.0026, "lr": 2.0048497278277247e-05, "epoch": 12.142464246424643, "percentage": 60.71, "elapsed_time": "4:21:25", "remaining_time": "2:49:09", "throughput": 1485.12, "total_tokens": 23294240} {"current_steps": 110380, "total_steps": 181800, "loss": 0.017, "lr": 2.0046144779009386e-05, "epoch": 12.143014301430142, "percentage": 60.72, "elapsed_time": "4:21:25", "remaining_time": "2:49:09", "throughput": 1485.12, "total_tokens": 23295232} {"current_steps": 110385, "total_steps": 181800, "loss": 0.0791, "lr": 2.004379232539884e-05, "epoch": 12.143564356435643, "percentage": 60.72, "elapsed_time": "4:21:26", "remaining_time": "2:49:08", "throughput": 1485.13, "total_tokens": 23296352} {"current_steps": 110390, "total_steps": 181800, "loss": 0.0186, "lr": 2.004143991746728e-05, "epoch": 12.144114411441144, "percentage": 60.72, "elapsed_time": "4:21:27", "remaining_time": "2:49:07", "throughput": 1485.13, "total_tokens": 23297440} {"current_steps": 110395, "total_steps": 181800, "loss": 0.0314, "lr": 2.003908755523639e-05, "epoch": 12.144664466446645, "percentage": 60.72, "elapsed_time": "4:21:27", "remaining_time": "2:49:07", "throughput": 1485.14, "total_tokens": 23298592} {"current_steps": 110400, "total_steps": 181800, "loss": 0.017, "lr": 2.0036735238727854e-05, "epoch": 12.145214521452145, "percentage": 60.73, "elapsed_time": "4:21:28", "remaining_time": "2:49:06", "throughput": 1485.14, "total_tokens": 23299680} {"current_steps": 110405, "total_steps": 181800, "loss": 0.0925, "lr": 2.0034382967963336e-05, "epoch": 12.145764576457646, "percentage": 60.73, "elapsed_time": "4:21:29", "remaining_time": "2:49:05", "throughput": 1485.15, "total_tokens": 23300736} {"current_steps": 110410, "total_steps": 181800, "loss": 0.0314, "lr": 2.0032030742964537e-05, "epoch": 12.146314631463147, "percentage": 60.73, "elapsed_time": "4:21:29", "remaining_time": "2:49:04", "throughput": 1485.15, "total_tokens": 23301824} {"current_steps": 110415, "total_steps": 181800, "loss": 0.0685, "lr": 2.0029678563753114e-05, "epoch": 12.146864686468646, "percentage": 60.73, "elapsed_time": "4:21:30", "remaining_time": "2:49:04", "throughput": 1485.15, "total_tokens": 23302880} {"current_steps": 110420, "total_steps": 181800, "loss": 0.0104, "lr": 2.0027326430350778e-05, "epoch": 12.147414741474147, "percentage": 60.74, "elapsed_time": "4:21:31", "remaining_time": "2:49:03", "throughput": 1485.16, "total_tokens": 23303968} {"current_steps": 110425, "total_steps": 181800, "loss": 0.0643, "lr": 2.0024974342779178e-05, "epoch": 12.147964796479648, "percentage": 60.74, "elapsed_time": "4:21:31", "remaining_time": "2:49:02", "throughput": 1485.16, "total_tokens": 23305088} {"current_steps": 110430, "total_steps": 181800, "loss": 0.0019, "lr": 2.0022622301059996e-05, "epoch": 12.148514851485148, "percentage": 60.74, "elapsed_time": "4:21:32", "remaining_time": "2:49:02", "throughput": 1485.17, "total_tokens": 23306176} {"current_steps": 110435, "total_steps": 181800, "loss": 0.0459, "lr": 2.0020270305214926e-05, "epoch": 12.149064906490649, "percentage": 60.75, "elapsed_time": "4:21:33", "remaining_time": "2:49:01", "throughput": 1485.17, "total_tokens": 23307232} {"current_steps": 110440, "total_steps": 181800, "loss": 0.0177, "lr": 2.0017918355265635e-05, "epoch": 12.14961496149615, "percentage": 60.75, "elapsed_time": "4:21:34", "remaining_time": "2:49:00", "throughput": 1485.17, "total_tokens": 23308288} {"current_steps": 110445, "total_steps": 181800, "loss": 0.0084, "lr": 2.0015566451233793e-05, "epoch": 12.150165016501651, "percentage": 60.75, "elapsed_time": "4:21:34", "remaining_time": "2:48:59", "throughput": 1485.17, "total_tokens": 23309376} {"current_steps": 110450, "total_steps": 181800, "loss": 0.1087, "lr": 2.0013214593141084e-05, "epoch": 12.15071507150715, "percentage": 60.75, "elapsed_time": "4:21:35", "remaining_time": "2:48:59", "throughput": 1485.18, "total_tokens": 23310464} {"current_steps": 110455, "total_steps": 181800, "loss": 0.0443, "lr": 2.0010862781009183e-05, "epoch": 12.151265126512651, "percentage": 60.76, "elapsed_time": "4:21:36", "remaining_time": "2:48:58", "throughput": 1485.19, "total_tokens": 23311616} {"current_steps": 110460, "total_steps": 181800, "loss": 0.0056, "lr": 2.0008511014859777e-05, "epoch": 12.151815181518153, "percentage": 60.76, "elapsed_time": "4:21:36", "remaining_time": "2:48:57", "throughput": 1485.18, "total_tokens": 23312608} {"current_steps": 110465, "total_steps": 181800, "loss": 0.0353, "lr": 2.0006159294714522e-05, "epoch": 12.152365236523652, "percentage": 60.76, "elapsed_time": "4:21:37", "remaining_time": "2:48:56", "throughput": 1485.19, "total_tokens": 23313696} {"current_steps": 110470, "total_steps": 181800, "loss": 0.0357, "lr": 2.0003807620595093e-05, "epoch": 12.152915291529153, "percentage": 60.76, "elapsed_time": "4:21:38", "remaining_time": "2:48:56", "throughput": 1485.19, "total_tokens": 23314784} {"current_steps": 110475, "total_steps": 181800, "loss": 0.0151, "lr": 2.0001455992523184e-05, "epoch": 12.153465346534654, "percentage": 60.77, "elapsed_time": "4:21:38", "remaining_time": "2:48:55", "throughput": 1485.19, "total_tokens": 23315808} {"current_steps": 110480, "total_steps": 181800, "loss": 0.0059, "lr": 1.9999104410520448e-05, "epoch": 12.154015401540153, "percentage": 60.77, "elapsed_time": "4:21:39", "remaining_time": "2:48:54", "throughput": 1485.2, "total_tokens": 23316960} {"current_steps": 110485, "total_steps": 181800, "loss": 0.1461, "lr": 1.9996752874608572e-05, "epoch": 12.154565456545654, "percentage": 60.77, "elapsed_time": "4:21:40", "remaining_time": "2:48:54", "throughput": 1485.2, "total_tokens": 23318048} {"current_steps": 110490, "total_steps": 181800, "loss": 0.0556, "lr": 1.999440138480923e-05, "epoch": 12.155115511551156, "percentage": 60.78, "elapsed_time": "4:21:40", "remaining_time": "2:48:53", "throughput": 1485.2, "total_tokens": 23319072} {"current_steps": 110495, "total_steps": 181800, "loss": 0.009, "lr": 1.9992049941144066e-05, "epoch": 12.155665566556655, "percentage": 60.78, "elapsed_time": "4:21:41", "remaining_time": "2:48:52", "throughput": 1485.21, "total_tokens": 23320160} {"current_steps": 110500, "total_steps": 181800, "loss": 0.0135, "lr": 1.9989698543634796e-05, "epoch": 12.156215621562156, "percentage": 60.78, "elapsed_time": "4:21:42", "remaining_time": "2:48:51", "throughput": 1485.21, "total_tokens": 23321184} {"current_steps": 110505, "total_steps": 181800, "loss": 0.0057, "lr": 1.9987347192303062e-05, "epoch": 12.156765676567657, "percentage": 60.78, "elapsed_time": "4:21:42", "remaining_time": "2:48:51", "throughput": 1485.21, "total_tokens": 23322240} {"current_steps": 110510, "total_steps": 181800, "loss": 0.0495, "lr": 1.9984995887170544e-05, "epoch": 12.157315731573158, "percentage": 60.79, "elapsed_time": "4:21:43", "remaining_time": "2:48:50", "throughput": 1485.22, "total_tokens": 23323360} {"current_steps": 110515, "total_steps": 181800, "loss": 0.0101, "lr": 1.998264462825892e-05, "epoch": 12.157865786578657, "percentage": 60.79, "elapsed_time": "4:21:44", "remaining_time": "2:48:49", "throughput": 1485.22, "total_tokens": 23324448} {"current_steps": 110520, "total_steps": 181800, "loss": 0.0044, "lr": 1.998029341558984e-05, "epoch": 12.158415841584159, "percentage": 60.79, "elapsed_time": "4:21:45", "remaining_time": "2:48:49", "throughput": 1485.22, "total_tokens": 23325472} {"current_steps": 110525, "total_steps": 181800, "loss": 0.0108, "lr": 1.9977942249184993e-05, "epoch": 12.15896589658966, "percentage": 60.79, "elapsed_time": "4:21:45", "remaining_time": "2:48:48", "throughput": 1485.21, "total_tokens": 23326432} {"current_steps": 110530, "total_steps": 181800, "loss": 0.0414, "lr": 1.997559112906604e-05, "epoch": 12.159515951595159, "percentage": 60.8, "elapsed_time": "4:21:46", "remaining_time": "2:48:47", "throughput": 1485.22, "total_tokens": 23327520} {"current_steps": 110535, "total_steps": 181800, "loss": 0.0119, "lr": 1.9973240055254663e-05, "epoch": 12.16006600660066, "percentage": 60.8, "elapsed_time": "4:21:47", "remaining_time": "2:48:46", "throughput": 1485.22, "total_tokens": 23328544} {"current_steps": 110540, "total_steps": 181800, "loss": 0.0672, "lr": 1.997088902777251e-05, "epoch": 12.160616061606161, "percentage": 60.8, "elapsed_time": "4:21:47", "remaining_time": "2:48:46", "throughput": 1485.22, "total_tokens": 23329632} {"current_steps": 110545, "total_steps": 181800, "loss": 0.036, "lr": 1.996853804664126e-05, "epoch": 12.16116611661166, "percentage": 60.81, "elapsed_time": "4:21:48", "remaining_time": "2:48:45", "throughput": 1485.22, "total_tokens": 23330688} {"current_steps": 110550, "total_steps": 181800, "loss": 0.0509, "lr": 1.996618711188259e-05, "epoch": 12.161716171617162, "percentage": 60.81, "elapsed_time": "4:21:49", "remaining_time": "2:48:44", "throughput": 1485.22, "total_tokens": 23331712} {"current_steps": 110555, "total_steps": 181800, "loss": 0.0324, "lr": 1.996383622351814e-05, "epoch": 12.162266226622663, "percentage": 60.81, "elapsed_time": "4:21:49", "remaining_time": "2:48:43", "throughput": 1485.23, "total_tokens": 23332832} {"current_steps": 110560, "total_steps": 181800, "loss": 0.011, "lr": 1.9961485381569614e-05, "epoch": 12.162816281628162, "percentage": 60.81, "elapsed_time": "4:21:50", "remaining_time": "2:48:43", "throughput": 1485.23, "total_tokens": 23333856} {"current_steps": 110565, "total_steps": 181800, "loss": 0.0041, "lr": 1.9959134586058654e-05, "epoch": 12.163366336633663, "percentage": 60.82, "elapsed_time": "4:21:51", "remaining_time": "2:48:42", "throughput": 1485.23, "total_tokens": 23334880} {"current_steps": 110570, "total_steps": 181800, "loss": 0.0084, "lr": 1.9956783837006922e-05, "epoch": 12.163916391639164, "percentage": 60.82, "elapsed_time": "4:21:51", "remaining_time": "2:48:41", "throughput": 1485.23, "total_tokens": 23335872} {"current_steps": 110575, "total_steps": 181800, "loss": 0.0149, "lr": 1.9954433134436106e-05, "epoch": 12.164466446644665, "percentage": 60.82, "elapsed_time": "4:21:52", "remaining_time": "2:48:41", "throughput": 1485.23, "total_tokens": 23336896} {"current_steps": 110580, "total_steps": 181800, "loss": 0.0488, "lr": 1.995208247836785e-05, "epoch": 12.165016501650165, "percentage": 60.83, "elapsed_time": "4:21:53", "remaining_time": "2:48:40", "throughput": 1485.23, "total_tokens": 23337952} {"current_steps": 110585, "total_steps": 181800, "loss": 0.0432, "lr": 1.994973186882383e-05, "epoch": 12.165566556655666, "percentage": 60.83, "elapsed_time": "4:21:54", "remaining_time": "2:48:39", "throughput": 1485.23, "total_tokens": 23339008} {"current_steps": 110590, "total_steps": 181800, "loss": 0.0746, "lr": 1.9947381305825717e-05, "epoch": 12.166116611661167, "percentage": 60.83, "elapsed_time": "4:21:54", "remaining_time": "2:48:38", "throughput": 1485.24, "total_tokens": 23340096} {"current_steps": 110595, "total_steps": 181800, "loss": 0.0834, "lr": 1.9945030789395152e-05, "epoch": 12.166666666666666, "percentage": 60.83, "elapsed_time": "4:21:55", "remaining_time": "2:48:38", "throughput": 1485.23, "total_tokens": 23341088} {"current_steps": 110600, "total_steps": 181800, "loss": 0.0504, "lr": 1.9942680319553818e-05, "epoch": 12.167216721672167, "percentage": 60.84, "elapsed_time": "4:21:56", "remaining_time": "2:48:37", "throughput": 1485.24, "total_tokens": 23342144} {"current_steps": 110605, "total_steps": 181800, "loss": 0.0479, "lr": 1.994032989632337e-05, "epoch": 12.167766776677668, "percentage": 60.84, "elapsed_time": "4:21:56", "remaining_time": "2:48:36", "throughput": 1485.23, "total_tokens": 23343136} {"current_steps": 110610, "total_steps": 181800, "loss": 0.0841, "lr": 1.9937979519725485e-05, "epoch": 12.168316831683168, "percentage": 60.84, "elapsed_time": "4:21:57", "remaining_time": "2:48:35", "throughput": 1485.23, "total_tokens": 23344160} {"current_steps": 110615, "total_steps": 181800, "loss": 0.0467, "lr": 1.9935629189781803e-05, "epoch": 12.168866886688669, "percentage": 60.84, "elapsed_time": "4:21:58", "remaining_time": "2:48:35", "throughput": 1485.23, "total_tokens": 23345152} {"current_steps": 110620, "total_steps": 181800, "loss": 0.0398, "lr": 1.9933278906513997e-05, "epoch": 12.16941694169417, "percentage": 60.85, "elapsed_time": "4:21:58", "remaining_time": "2:48:34", "throughput": 1485.24, "total_tokens": 23346240} {"current_steps": 110625, "total_steps": 181800, "loss": 0.0234, "lr": 1.993092866994373e-05, "epoch": 12.16996699669967, "percentage": 60.85, "elapsed_time": "4:21:59", "remaining_time": "2:48:33", "throughput": 1485.24, "total_tokens": 23347296} {"current_steps": 110630, "total_steps": 181800, "loss": 0.004, "lr": 1.9928578480092665e-05, "epoch": 12.17051705170517, "percentage": 60.85, "elapsed_time": "4:22:00", "remaining_time": "2:48:33", "throughput": 1485.24, "total_tokens": 23348352} {"current_steps": 110635, "total_steps": 181800, "loss": 0.0039, "lr": 1.992622833698245e-05, "epoch": 12.171067106710671, "percentage": 60.86, "elapsed_time": "4:22:00", "remaining_time": "2:48:32", "throughput": 1485.24, "total_tokens": 23349376} {"current_steps": 110640, "total_steps": 181800, "loss": 0.0075, "lr": 1.992387824063476e-05, "epoch": 12.171617161716172, "percentage": 60.86, "elapsed_time": "4:22:01", "remaining_time": "2:48:31", "throughput": 1485.24, "total_tokens": 23350432} {"current_steps": 110645, "total_steps": 181800, "loss": 0.0348, "lr": 1.992152819107124e-05, "epoch": 12.172167216721672, "percentage": 60.86, "elapsed_time": "4:22:02", "remaining_time": "2:48:30", "throughput": 1485.25, "total_tokens": 23351520} {"current_steps": 110650, "total_steps": 181800, "loss": 0.0039, "lr": 1.9919178188313575e-05, "epoch": 12.172717271727173, "percentage": 60.86, "elapsed_time": "4:22:03", "remaining_time": "2:48:30", "throughput": 1485.25, "total_tokens": 23352576} {"current_steps": 110655, "total_steps": 181800, "loss": 0.0065, "lr": 1.9916828232383396e-05, "epoch": 12.173267326732674, "percentage": 60.87, "elapsed_time": "4:22:03", "remaining_time": "2:48:29", "throughput": 1485.25, "total_tokens": 23353600} {"current_steps": 110660, "total_steps": 181800, "loss": 0.0072, "lr": 1.991447832330237e-05, "epoch": 12.173817381738173, "percentage": 60.87, "elapsed_time": "4:22:04", "remaining_time": "2:48:28", "throughput": 1485.25, "total_tokens": 23354688} {"current_steps": 110665, "total_steps": 181800, "loss": 0.0164, "lr": 1.9912128461092165e-05, "epoch": 12.174367436743674, "percentage": 60.87, "elapsed_time": "4:22:05", "remaining_time": "2:48:28", "throughput": 1485.26, "total_tokens": 23355776} {"current_steps": 110670, "total_steps": 181800, "loss": 0.0112, "lr": 1.990977864577442e-05, "epoch": 12.174917491749175, "percentage": 60.87, "elapsed_time": "4:22:05", "remaining_time": "2:48:27", "throughput": 1485.26, "total_tokens": 23356832} {"current_steps": 110675, "total_steps": 181800, "loss": 0.005, "lr": 1.990742887737081e-05, "epoch": 12.175467546754675, "percentage": 60.88, "elapsed_time": "4:22:06", "remaining_time": "2:48:26", "throughput": 1485.26, "total_tokens": 23357920} {"current_steps": 110680, "total_steps": 181800, "loss": 0.0069, "lr": 1.990507915590298e-05, "epoch": 12.176017601760176, "percentage": 60.88, "elapsed_time": "4:22:07", "remaining_time": "2:48:25", "throughput": 1485.26, "total_tokens": 23358944} {"current_steps": 110685, "total_steps": 181800, "loss": 0.0104, "lr": 1.990272948139259e-05, "epoch": 12.176567656765677, "percentage": 60.88, "elapsed_time": "4:22:07", "remaining_time": "2:48:25", "throughput": 1485.26, "total_tokens": 23360000} {"current_steps": 110690, "total_steps": 181800, "loss": 0.0039, "lr": 1.9900379853861306e-05, "epoch": 12.177117711771178, "percentage": 60.89, "elapsed_time": "4:22:08", "remaining_time": "2:48:24", "throughput": 1485.27, "total_tokens": 23361056} {"current_steps": 110695, "total_steps": 181800, "loss": 0.0788, "lr": 1.9898030273330763e-05, "epoch": 12.177667766776677, "percentage": 60.89, "elapsed_time": "4:22:09", "remaining_time": "2:48:23", "throughput": 1485.27, "total_tokens": 23362112} {"current_steps": 110700, "total_steps": 181800, "loss": 0.0061, "lr": 1.989568073982263e-05, "epoch": 12.178217821782178, "percentage": 60.89, "elapsed_time": "4:22:09", "remaining_time": "2:48:22", "throughput": 1485.27, "total_tokens": 23363168} {"current_steps": 110705, "total_steps": 181800, "loss": 0.0113, "lr": 1.9893331253358566e-05, "epoch": 12.17876787678768, "percentage": 60.89, "elapsed_time": "4:22:10", "remaining_time": "2:48:22", "throughput": 1485.27, "total_tokens": 23364224} {"current_steps": 110710, "total_steps": 181800, "loss": 0.007, "lr": 1.9890981813960208e-05, "epoch": 12.179317931793179, "percentage": 60.9, "elapsed_time": "4:22:11", "remaining_time": "2:48:21", "throughput": 1485.27, "total_tokens": 23365216} {"current_steps": 110715, "total_steps": 181800, "loss": 0.0502, "lr": 1.9888632421649222e-05, "epoch": 12.17986798679868, "percentage": 60.9, "elapsed_time": "4:22:11", "remaining_time": "2:48:20", "throughput": 1485.27, "total_tokens": 23366304} {"current_steps": 110720, "total_steps": 181800, "loss": 0.0385, "lr": 1.9886283076447254e-05, "epoch": 12.180418041804181, "percentage": 60.9, "elapsed_time": "4:22:12", "remaining_time": "2:48:20", "throughput": 1485.28, "total_tokens": 23367392} {"current_steps": 110725, "total_steps": 181800, "loss": 0.0085, "lr": 1.9883933778375968e-05, "epoch": 12.18096809680968, "percentage": 60.9, "elapsed_time": "4:22:13", "remaining_time": "2:48:19", "throughput": 1485.28, "total_tokens": 23368416} {"current_steps": 110730, "total_steps": 181800, "loss": 0.0376, "lr": 1.988158452745701e-05, "epoch": 12.181518151815181, "percentage": 60.91, "elapsed_time": "4:22:14", "remaining_time": "2:48:18", "throughput": 1485.28, "total_tokens": 23369472} {"current_steps": 110735, "total_steps": 181800, "loss": 0.013, "lr": 1.987923532371202e-05, "epoch": 12.182068206820682, "percentage": 60.91, "elapsed_time": "4:22:14", "remaining_time": "2:48:17", "throughput": 1485.28, "total_tokens": 23370560} {"current_steps": 110740, "total_steps": 181800, "loss": 0.134, "lr": 1.987688616716267e-05, "epoch": 12.182618261826182, "percentage": 60.91, "elapsed_time": "4:22:15", "remaining_time": "2:48:17", "throughput": 1485.28, "total_tokens": 23371584} {"current_steps": 110745, "total_steps": 181800, "loss": 0.004, "lr": 1.98745370578306e-05, "epoch": 12.183168316831683, "percentage": 60.92, "elapsed_time": "4:22:16", "remaining_time": "2:48:16", "throughput": 1485.28, "total_tokens": 23372640} {"current_steps": 110750, "total_steps": 181800, "loss": 0.0729, "lr": 1.987218799573747e-05, "epoch": 12.183718371837184, "percentage": 60.92, "elapsed_time": "4:22:16", "remaining_time": "2:48:15", "throughput": 1485.29, "total_tokens": 23373696} {"current_steps": 110755, "total_steps": 181800, "loss": 0.0039, "lr": 1.9869838980904914e-05, "epoch": 12.184268426842685, "percentage": 60.92, "elapsed_time": "4:22:17", "remaining_time": "2:48:14", "throughput": 1485.28, "total_tokens": 23374688} {"current_steps": 110760, "total_steps": 181800, "loss": 0.0645, "lr": 1.986749001335459e-05, "epoch": 12.184818481848184, "percentage": 60.92, "elapsed_time": "4:22:18", "remaining_time": "2:48:14", "throughput": 1485.29, "total_tokens": 23375744} {"current_steps": 110765, "total_steps": 181800, "loss": 0.0085, "lr": 1.9865141093108155e-05, "epoch": 12.185368536853685, "percentage": 60.93, "elapsed_time": "4:22:18", "remaining_time": "2:48:13", "throughput": 1485.29, "total_tokens": 23376864} {"current_steps": 110770, "total_steps": 181800, "loss": 0.0546, "lr": 1.986279222018724e-05, "epoch": 12.185918591859187, "percentage": 60.93, "elapsed_time": "4:22:19", "remaining_time": "2:48:12", "throughput": 1485.29, "total_tokens": 23377888} {"current_steps": 110775, "total_steps": 181800, "loss": 0.0684, "lr": 1.986044339461351e-05, "epoch": 12.186468646864686, "percentage": 60.93, "elapsed_time": "4:22:20", "remaining_time": "2:48:12", "throughput": 1485.29, "total_tokens": 23378912} {"current_steps": 110780, "total_steps": 181800, "loss": 0.0016, "lr": 1.9858094616408613e-05, "epoch": 12.187018701870187, "percentage": 60.94, "elapsed_time": "4:22:20", "remaining_time": "2:48:11", "throughput": 1485.29, "total_tokens": 23379968} {"current_steps": 110785, "total_steps": 181800, "loss": 0.0022, "lr": 1.985574588559418e-05, "epoch": 12.187568756875688, "percentage": 60.94, "elapsed_time": "4:22:21", "remaining_time": "2:48:10", "throughput": 1485.3, "total_tokens": 23381024} {"current_steps": 110790, "total_steps": 181800, "loss": 0.0028, "lr": 1.9853397202191874e-05, "epoch": 12.188118811881187, "percentage": 60.94, "elapsed_time": "4:22:22", "remaining_time": "2:48:09", "throughput": 1485.29, "total_tokens": 23382016} {"current_steps": 110795, "total_steps": 181800, "loss": 0.0031, "lr": 1.9851048566223332e-05, "epoch": 12.188668866886688, "percentage": 60.94, "elapsed_time": "4:22:23", "remaining_time": "2:48:09", "throughput": 1485.29, "total_tokens": 23383040} {"current_steps": 110800, "total_steps": 181800, "loss": 0.0692, "lr": 1.9848699977710208e-05, "epoch": 12.18921892189219, "percentage": 60.95, "elapsed_time": "4:22:23", "remaining_time": "2:48:08", "throughput": 1485.3, "total_tokens": 23384160} {"current_steps": 110805, "total_steps": 181800, "loss": 0.0082, "lr": 1.984635143667415e-05, "epoch": 12.189768976897689, "percentage": 60.95, "elapsed_time": "4:22:24", "remaining_time": "2:48:07", "throughput": 1485.3, "total_tokens": 23385216} {"current_steps": 110810, "total_steps": 181800, "loss": 0.0112, "lr": 1.9844002943136788e-05, "epoch": 12.19031903190319, "percentage": 60.95, "elapsed_time": "4:22:25", "remaining_time": "2:48:07", "throughput": 1485.3, "total_tokens": 23386240} {"current_steps": 110815, "total_steps": 181800, "loss": 0.1652, "lr": 1.9841654497119782e-05, "epoch": 12.190869086908691, "percentage": 60.95, "elapsed_time": "4:22:25", "remaining_time": "2:48:06", "throughput": 1485.3, "total_tokens": 23387232} {"current_steps": 110820, "total_steps": 181800, "loss": 0.0015, "lr": 1.9839306098644777e-05, "epoch": 12.191419141914192, "percentage": 60.96, "elapsed_time": "4:22:26", "remaining_time": "2:48:05", "throughput": 1485.3, "total_tokens": 23388288} {"current_steps": 110825, "total_steps": 181800, "loss": 0.0035, "lr": 1.98369577477334e-05, "epoch": 12.191969196919691, "percentage": 60.96, "elapsed_time": "4:22:27", "remaining_time": "2:48:04", "throughput": 1485.3, "total_tokens": 23389312} {"current_steps": 110830, "total_steps": 181800, "loss": 0.0061, "lr": 1.983460944440731e-05, "epoch": 12.192519251925193, "percentage": 60.96, "elapsed_time": "4:22:27", "remaining_time": "2:48:04", "throughput": 1485.31, "total_tokens": 23390400} {"current_steps": 110835, "total_steps": 181800, "loss": 0.0023, "lr": 1.9832261188688146e-05, "epoch": 12.193069306930694, "percentage": 60.97, "elapsed_time": "4:22:28", "remaining_time": "2:48:03", "throughput": 1485.31, "total_tokens": 23391456} {"current_steps": 110840, "total_steps": 181800, "loss": 0.0084, "lr": 1.9829912980597555e-05, "epoch": 12.193619361936193, "percentage": 60.97, "elapsed_time": "4:22:29", "remaining_time": "2:48:02", "throughput": 1485.31, "total_tokens": 23392512} {"current_steps": 110845, "total_steps": 181800, "loss": 0.0747, "lr": 1.9827564820157172e-05, "epoch": 12.194169416941694, "percentage": 60.97, "elapsed_time": "4:22:29", "remaining_time": "2:48:01", "throughput": 1485.31, "total_tokens": 23393600} {"current_steps": 110850, "total_steps": 181800, "loss": 0.0521, "lr": 1.9825216707388637e-05, "epoch": 12.194719471947195, "percentage": 60.97, "elapsed_time": "4:22:30", "remaining_time": "2:48:01", "throughput": 1485.32, "total_tokens": 23394656} {"current_steps": 110855, "total_steps": 181800, "loss": 0.0018, "lr": 1.982286864231361e-05, "epoch": 12.195269526952695, "percentage": 60.98, "elapsed_time": "4:22:31", "remaining_time": "2:48:00", "throughput": 1485.31, "total_tokens": 23395648} {"current_steps": 110860, "total_steps": 181800, "loss": 0.0354, "lr": 1.98205206249537e-05, "epoch": 12.195819581958196, "percentage": 60.98, "elapsed_time": "4:22:32", "remaining_time": "2:47:59", "throughput": 1485.32, "total_tokens": 23396704} {"current_steps": 110865, "total_steps": 181800, "loss": 0.0088, "lr": 1.9818172655330583e-05, "epoch": 12.196369636963697, "percentage": 60.98, "elapsed_time": "4:22:32", "remaining_time": "2:47:59", "throughput": 1485.32, "total_tokens": 23397792} {"current_steps": 110870, "total_steps": 181800, "loss": 0.1486, "lr": 1.9815824733465876e-05, "epoch": 12.196919691969198, "percentage": 60.98, "elapsed_time": "4:22:33", "remaining_time": "2:47:58", "throughput": 1485.32, "total_tokens": 23398848} {"current_steps": 110875, "total_steps": 181800, "loss": 0.0034, "lr": 1.981347685938122e-05, "epoch": 12.197469746974697, "percentage": 60.99, "elapsed_time": "4:22:34", "remaining_time": "2:47:57", "throughput": 1485.32, "total_tokens": 23399840} {"current_steps": 110880, "total_steps": 181800, "loss": 0.0394, "lr": 1.981112903309827e-05, "epoch": 12.198019801980198, "percentage": 60.99, "elapsed_time": "4:22:34", "remaining_time": "2:47:56", "throughput": 1485.32, "total_tokens": 23400928} {"current_steps": 110885, "total_steps": 181800, "loss": 0.0667, "lr": 1.9808781254638643e-05, "epoch": 12.1985698569857, "percentage": 60.99, "elapsed_time": "4:22:35", "remaining_time": "2:47:56", "throughput": 1485.33, "total_tokens": 23402080} {"current_steps": 110890, "total_steps": 181800, "loss": 0.0446, "lr": 1.980643352402399e-05, "epoch": 12.199119911991199, "percentage": 61.0, "elapsed_time": "4:22:36", "remaining_time": "2:47:55", "throughput": 1485.33, "total_tokens": 23403072} {"current_steps": 110895, "total_steps": 181800, "loss": 0.0107, "lr": 1.9804085841275957e-05, "epoch": 12.1996699669967, "percentage": 61.0, "elapsed_time": "4:22:36", "remaining_time": "2:47:54", "throughput": 1485.33, "total_tokens": 23404128} {"current_steps": 110900, "total_steps": 181800, "loss": 0.0677, "lr": 1.980173820641616e-05, "epoch": 12.2002200220022, "percentage": 61.0, "elapsed_time": "4:22:37", "remaining_time": "2:47:54", "throughput": 1485.33, "total_tokens": 23405184} {"current_steps": 110905, "total_steps": 181800, "loss": 0.0605, "lr": 1.979939061946625e-05, "epoch": 12.2007700770077, "percentage": 61.0, "elapsed_time": "4:22:38", "remaining_time": "2:47:53", "throughput": 1485.34, "total_tokens": 23406240} {"current_steps": 110910, "total_steps": 181800, "loss": 0.0032, "lr": 1.979704308044786e-05, "epoch": 12.201320132013201, "percentage": 61.01, "elapsed_time": "4:22:38", "remaining_time": "2:47:52", "throughput": 1485.34, "total_tokens": 23407296} {"current_steps": 110915, "total_steps": 181800, "loss": 0.0776, "lr": 1.9794695589382637e-05, "epoch": 12.201870187018702, "percentage": 61.01, "elapsed_time": "4:22:39", "remaining_time": "2:47:51", "throughput": 1485.34, "total_tokens": 23408352} {"current_steps": 110920, "total_steps": 181800, "loss": 0.0267, "lr": 1.97923481462922e-05, "epoch": 12.202420242024202, "percentage": 61.01, "elapsed_time": "4:22:40", "remaining_time": "2:47:51", "throughput": 1485.35, "total_tokens": 23409440} {"current_steps": 110925, "total_steps": 181800, "loss": 0.0023, "lr": 1.9790000751198188e-05, "epoch": 12.202970297029703, "percentage": 61.01, "elapsed_time": "4:22:40", "remaining_time": "2:47:50", "throughput": 1485.35, "total_tokens": 23410496} {"current_steps": 110930, "total_steps": 181800, "loss": 0.0196, "lr": 1.9787653404122243e-05, "epoch": 12.203520352035204, "percentage": 61.02, "elapsed_time": "4:22:41", "remaining_time": "2:47:49", "throughput": 1485.35, "total_tokens": 23411552} {"current_steps": 110935, "total_steps": 181800, "loss": 0.0053, "lr": 1.978530610508599e-05, "epoch": 12.204070407040705, "percentage": 61.02, "elapsed_time": "4:22:42", "remaining_time": "2:47:48", "throughput": 1485.35, "total_tokens": 23412576} {"current_steps": 110940, "total_steps": 181800, "loss": 0.0206, "lr": 1.978295885411108e-05, "epoch": 12.204620462046204, "percentage": 61.02, "elapsed_time": "4:22:43", "remaining_time": "2:47:48", "throughput": 1485.35, "total_tokens": 23413600} {"current_steps": 110945, "total_steps": 181800, "loss": 0.0048, "lr": 1.9780611651219128e-05, "epoch": 12.205170517051705, "percentage": 61.03, "elapsed_time": "4:22:43", "remaining_time": "2:47:47", "throughput": 1485.35, "total_tokens": 23414624} {"current_steps": 110950, "total_steps": 181800, "loss": 0.0159, "lr": 1.9778264496431768e-05, "epoch": 12.205720572057206, "percentage": 61.03, "elapsed_time": "4:22:44", "remaining_time": "2:47:46", "throughput": 1485.35, "total_tokens": 23415744} {"current_steps": 110955, "total_steps": 181800, "loss": 0.0178, "lr": 1.9775917389770652e-05, "epoch": 12.206270627062706, "percentage": 61.03, "elapsed_time": "4:22:45", "remaining_time": "2:47:46", "throughput": 1485.36, "total_tokens": 23416832} {"current_steps": 110960, "total_steps": 181800, "loss": 0.0035, "lr": 1.9773570331257385e-05, "epoch": 12.206820682068207, "percentage": 61.03, "elapsed_time": "4:22:45", "remaining_time": "2:47:45", "throughput": 1485.36, "total_tokens": 23417856} {"current_steps": 110965, "total_steps": 181800, "loss": 0.0504, "lr": 1.977122332091362e-05, "epoch": 12.207370737073708, "percentage": 61.04, "elapsed_time": "4:22:46", "remaining_time": "2:47:44", "throughput": 1485.36, "total_tokens": 23418912} {"current_steps": 110970, "total_steps": 181800, "loss": 0.0626, "lr": 1.9768876358760985e-05, "epoch": 12.207920792079207, "percentage": 61.04, "elapsed_time": "4:22:47", "remaining_time": "2:47:43", "throughput": 1485.36, "total_tokens": 23419968} {"current_steps": 110975, "total_steps": 181800, "loss": 0.1287, "lr": 1.976652944482109e-05, "epoch": 12.208470847084708, "percentage": 61.04, "elapsed_time": "4:22:47", "remaining_time": "2:47:43", "throughput": 1485.36, "total_tokens": 23421024} {"current_steps": 110980, "total_steps": 181800, "loss": 0.0323, "lr": 1.9764182579115596e-05, "epoch": 12.20902090209021, "percentage": 61.05, "elapsed_time": "4:22:48", "remaining_time": "2:47:42", "throughput": 1485.37, "total_tokens": 23422080} {"current_steps": 110985, "total_steps": 181800, "loss": 0.0075, "lr": 1.9761835761666114e-05, "epoch": 12.209570957095709, "percentage": 61.05, "elapsed_time": "4:22:49", "remaining_time": "2:47:41", "throughput": 1485.37, "total_tokens": 23423136} {"current_steps": 110990, "total_steps": 181800, "loss": 0.0269, "lr": 1.9759488992494278e-05, "epoch": 12.21012101210121, "percentage": 61.05, "elapsed_time": "4:22:49", "remaining_time": "2:47:40", "throughput": 1485.37, "total_tokens": 23424192} {"current_steps": 110995, "total_steps": 181800, "loss": 0.0507, "lr": 1.9757142271621727e-05, "epoch": 12.210671067106711, "percentage": 61.05, "elapsed_time": "4:22:50", "remaining_time": "2:47:40", "throughput": 1485.37, "total_tokens": 23425248} {"current_steps": 111000, "total_steps": 181800, "loss": 0.0884, "lr": 1.9754795599070068e-05, "epoch": 12.211221122112212, "percentage": 61.06, "elapsed_time": "4:22:51", "remaining_time": "2:47:39", "throughput": 1485.37, "total_tokens": 23426272} {"current_steps": 111005, "total_steps": 181800, "loss": 0.0062, "lr": 1.9752448974860945e-05, "epoch": 12.211771177117711, "percentage": 61.06, "elapsed_time": "4:22:52", "remaining_time": "2:47:38", "throughput": 1485.37, "total_tokens": 23427328} {"current_steps": 111010, "total_steps": 181800, "loss": 0.1225, "lr": 1.9750102399015986e-05, "epoch": 12.212321232123212, "percentage": 61.06, "elapsed_time": "4:22:52", "remaining_time": "2:47:38", "throughput": 1485.38, "total_tokens": 23428416} {"current_steps": 111015, "total_steps": 181800, "loss": 0.0018, "lr": 1.9747755871556805e-05, "epoch": 12.212871287128714, "percentage": 61.06, "elapsed_time": "4:22:53", "remaining_time": "2:47:37", "throughput": 1485.38, "total_tokens": 23429472} {"current_steps": 111020, "total_steps": 181800, "loss": 0.0486, "lr": 1.9745409392505043e-05, "epoch": 12.213421342134213, "percentage": 61.07, "elapsed_time": "4:22:54", "remaining_time": "2:47:36", "throughput": 1485.38, "total_tokens": 23430528} {"current_steps": 111025, "total_steps": 181800, "loss": 0.03, "lr": 1.9743062961882318e-05, "epoch": 12.213971397139714, "percentage": 61.07, "elapsed_time": "4:22:54", "remaining_time": "2:47:35", "throughput": 1485.39, "total_tokens": 23431616} {"current_steps": 111030, "total_steps": 181800, "loss": 0.0065, "lr": 1.9740716579710267e-05, "epoch": 12.214521452145215, "percentage": 61.07, "elapsed_time": "4:22:55", "remaining_time": "2:47:35", "throughput": 1485.39, "total_tokens": 23432640} {"current_steps": 111035, "total_steps": 181800, "loss": 0.0081, "lr": 1.9738370246010503e-05, "epoch": 12.215071507150714, "percentage": 61.08, "elapsed_time": "4:22:56", "remaining_time": "2:47:34", "throughput": 1485.39, "total_tokens": 23433696} {"current_steps": 111040, "total_steps": 181800, "loss": 0.0355, "lr": 1.973602396080465e-05, "epoch": 12.215621562156215, "percentage": 61.08, "elapsed_time": "4:22:56", "remaining_time": "2:47:33", "throughput": 1485.39, "total_tokens": 23434752} {"current_steps": 111045, "total_steps": 181800, "loss": 0.05, "lr": 1.9733677724114342e-05, "epoch": 12.216171617161717, "percentage": 61.08, "elapsed_time": "4:22:57", "remaining_time": "2:47:33", "throughput": 1485.39, "total_tokens": 23435776} {"current_steps": 111050, "total_steps": 181800, "loss": 0.03, "lr": 1.97313315359612e-05, "epoch": 12.216721672167218, "percentage": 61.08, "elapsed_time": "4:22:58", "remaining_time": "2:47:32", "throughput": 1485.4, "total_tokens": 23436896} {"current_steps": 111055, "total_steps": 181800, "loss": 0.0196, "lr": 1.972898539636685e-05, "epoch": 12.217271727172717, "percentage": 61.09, "elapsed_time": "4:22:58", "remaining_time": "2:47:31", "throughput": 1485.4, "total_tokens": 23438048} {"current_steps": 111060, "total_steps": 181800, "loss": 0.0907, "lr": 1.9726639305352913e-05, "epoch": 12.217821782178218, "percentage": 61.09, "elapsed_time": "4:22:59", "remaining_time": "2:47:30", "throughput": 1485.4, "total_tokens": 23439072} {"current_steps": 111065, "total_steps": 181800, "loss": 0.1159, "lr": 1.9724293262941003e-05, "epoch": 12.218371837183719, "percentage": 61.09, "elapsed_time": "4:23:00", "remaining_time": "2:47:30", "throughput": 1485.41, "total_tokens": 23440160} {"current_steps": 111070, "total_steps": 181800, "loss": 0.0111, "lr": 1.9721947269152763e-05, "epoch": 12.218921892189218, "percentage": 61.09, "elapsed_time": "4:23:00", "remaining_time": "2:47:29", "throughput": 1485.41, "total_tokens": 23441248} {"current_steps": 111075, "total_steps": 181800, "loss": 0.0368, "lr": 1.971960132400979e-05, "epoch": 12.21947194719472, "percentage": 61.1, "elapsed_time": "4:23:01", "remaining_time": "2:47:28", "throughput": 1485.41, "total_tokens": 23442304} {"current_steps": 111080, "total_steps": 181800, "loss": 0.0571, "lr": 1.9717255427533723e-05, "epoch": 12.22002200220022, "percentage": 61.1, "elapsed_time": "4:23:02", "remaining_time": "2:47:27", "throughput": 1485.41, "total_tokens": 23443296} {"current_steps": 111085, "total_steps": 181800, "loss": 0.0186, "lr": 1.9714909579746186e-05, "epoch": 12.22057205720572, "percentage": 61.1, "elapsed_time": "4:23:03", "remaining_time": "2:47:27", "throughput": 1485.41, "total_tokens": 23444352} {"current_steps": 111090, "total_steps": 181800, "loss": 0.0051, "lr": 1.9712563780668777e-05, "epoch": 12.221122112211221, "percentage": 61.11, "elapsed_time": "4:23:03", "remaining_time": "2:47:26", "throughput": 1485.42, "total_tokens": 23445408} {"current_steps": 111095, "total_steps": 181800, "loss": 0.0044, "lr": 1.9710218030323138e-05, "epoch": 12.221672167216722, "percentage": 61.11, "elapsed_time": "4:23:04", "remaining_time": "2:47:25", "throughput": 1485.42, "total_tokens": 23446496} {"current_steps": 111100, "total_steps": 181800, "loss": 0.0069, "lr": 1.9707872328730876e-05, "epoch": 12.222222222222221, "percentage": 61.11, "elapsed_time": "4:23:05", "remaining_time": "2:47:25", "throughput": 1485.42, "total_tokens": 23447552} {"current_steps": 111105, "total_steps": 181800, "loss": 0.0534, "lr": 1.9705526675913617e-05, "epoch": 12.222772277227723, "percentage": 61.11, "elapsed_time": "4:23:05", "remaining_time": "2:47:24", "throughput": 1485.42, "total_tokens": 23448576} {"current_steps": 111110, "total_steps": 181800, "loss": 0.001, "lr": 1.9703181071892988e-05, "epoch": 12.223322332233224, "percentage": 61.12, "elapsed_time": "4:23:06", "remaining_time": "2:47:23", "throughput": 1485.42, "total_tokens": 23449600} {"current_steps": 111115, "total_steps": 181800, "loss": 0.0591, "lr": 1.9700835516690584e-05, "epoch": 12.223872387238725, "percentage": 61.12, "elapsed_time": "4:23:07", "remaining_time": "2:47:22", "throughput": 1485.42, "total_tokens": 23450624} {"current_steps": 111120, "total_steps": 181800, "loss": 0.0067, "lr": 1.9698490010328043e-05, "epoch": 12.224422442244224, "percentage": 61.12, "elapsed_time": "4:23:07", "remaining_time": "2:47:22", "throughput": 1485.43, "total_tokens": 23451680} {"current_steps": 111125, "total_steps": 181800, "loss": 0.0021, "lr": 1.969614455282697e-05, "epoch": 12.224972497249725, "percentage": 61.12, "elapsed_time": "4:23:08", "remaining_time": "2:47:21", "throughput": 1485.43, "total_tokens": 23452800} {"current_steps": 111130, "total_steps": 181800, "loss": 0.0663, "lr": 1.9693799144208997e-05, "epoch": 12.225522552255226, "percentage": 61.13, "elapsed_time": "4:23:09", "remaining_time": "2:47:20", "throughput": 1485.44, "total_tokens": 23453856} {"current_steps": 111135, "total_steps": 181800, "loss": 0.0263, "lr": 1.969145378449573e-05, "epoch": 12.226072607260726, "percentage": 61.13, "elapsed_time": "4:23:09", "remaining_time": "2:47:19", "throughput": 1485.44, "total_tokens": 23454944} {"current_steps": 111140, "total_steps": 181800, "loss": 0.0066, "lr": 1.9689108473708776e-05, "epoch": 12.226622662266227, "percentage": 61.13, "elapsed_time": "4:23:10", "remaining_time": "2:47:19", "throughput": 1485.44, "total_tokens": 23456032} {"current_steps": 111145, "total_steps": 181800, "loss": 0.0059, "lr": 1.9686763211869776e-05, "epoch": 12.227172717271728, "percentage": 61.14, "elapsed_time": "4:23:11", "remaining_time": "2:47:18", "throughput": 1485.45, "total_tokens": 23457152} {"current_steps": 111150, "total_steps": 181800, "loss": 0.0144, "lr": 1.968441799900031e-05, "epoch": 12.227722772277227, "percentage": 61.14, "elapsed_time": "4:23:11", "remaining_time": "2:47:17", "throughput": 1485.45, "total_tokens": 23458240} {"current_steps": 111155, "total_steps": 181800, "loss": 0.0075, "lr": 1.968207283512203e-05, "epoch": 12.228272827282728, "percentage": 61.14, "elapsed_time": "4:23:12", "remaining_time": "2:47:17", "throughput": 1485.45, "total_tokens": 23459232} {"current_steps": 111160, "total_steps": 181800, "loss": 0.0021, "lr": 1.9679727720256524e-05, "epoch": 12.22882288228823, "percentage": 61.14, "elapsed_time": "4:23:13", "remaining_time": "2:47:16", "throughput": 1485.46, "total_tokens": 23460288} {"current_steps": 111165, "total_steps": 181800, "loss": 0.0052, "lr": 1.9677382654425414e-05, "epoch": 12.229372937293729, "percentage": 61.15, "elapsed_time": "4:23:14", "remaining_time": "2:47:15", "throughput": 1485.46, "total_tokens": 23461408} {"current_steps": 111170, "total_steps": 181800, "loss": 0.0077, "lr": 1.9675037637650325e-05, "epoch": 12.22992299229923, "percentage": 61.15, "elapsed_time": "4:23:14", "remaining_time": "2:47:14", "throughput": 1485.46, "total_tokens": 23462464} {"current_steps": 111175, "total_steps": 181800, "loss": 0.058, "lr": 1.9672692669952843e-05, "epoch": 12.23047304730473, "percentage": 61.15, "elapsed_time": "4:23:15", "remaining_time": "2:47:14", "throughput": 1485.47, "total_tokens": 23463520} {"current_steps": 111180, "total_steps": 181800, "loss": 0.0226, "lr": 1.9670347751354605e-05, "epoch": 12.231023102310232, "percentage": 61.16, "elapsed_time": "4:23:16", "remaining_time": "2:47:13", "throughput": 1485.47, "total_tokens": 23464608} {"current_steps": 111185, "total_steps": 181800, "loss": 0.0272, "lr": 1.9668002881877224e-05, "epoch": 12.231573157315731, "percentage": 61.16, "elapsed_time": "4:23:16", "remaining_time": "2:47:12", "throughput": 1485.47, "total_tokens": 23465568} {"current_steps": 111190, "total_steps": 181800, "loss": 0.0071, "lr": 1.9665658061542286e-05, "epoch": 12.232123212321232, "percentage": 61.16, "elapsed_time": "4:23:17", "remaining_time": "2:47:12", "throughput": 1485.47, "total_tokens": 23466624} {"current_steps": 111195, "total_steps": 181800, "loss": 0.0083, "lr": 1.9663313290371423e-05, "epoch": 12.232673267326733, "percentage": 61.16, "elapsed_time": "4:23:18", "remaining_time": "2:47:11", "throughput": 1485.47, "total_tokens": 23467680} {"current_steps": 111200, "total_steps": 181800, "loss": 0.0568, "lr": 1.966096856838624e-05, "epoch": 12.233223322332233, "percentage": 61.17, "elapsed_time": "4:23:18", "remaining_time": "2:47:10", "throughput": 1485.47, "total_tokens": 23468768} {"current_steps": 111205, "total_steps": 181800, "loss": 0.0103, "lr": 1.9658623895608354e-05, "epoch": 12.233773377337734, "percentage": 61.17, "elapsed_time": "4:23:19", "remaining_time": "2:47:09", "throughput": 1485.48, "total_tokens": 23469856} {"current_steps": 111210, "total_steps": 181800, "loss": 0.0049, "lr": 1.9656279272059362e-05, "epoch": 12.234323432343235, "percentage": 61.17, "elapsed_time": "4:23:20", "remaining_time": "2:47:09", "throughput": 1485.48, "total_tokens": 23470880} {"current_steps": 111215, "total_steps": 181800, "loss": 0.0034, "lr": 1.9653934697760878e-05, "epoch": 12.234873487348734, "percentage": 61.17, "elapsed_time": "4:23:20", "remaining_time": "2:47:08", "throughput": 1485.48, "total_tokens": 23471872} {"current_steps": 111220, "total_steps": 181800, "loss": 0.0416, "lr": 1.965159017273452e-05, "epoch": 12.235423542354235, "percentage": 61.18, "elapsed_time": "4:23:21", "remaining_time": "2:47:07", "throughput": 1485.47, "total_tokens": 23472864} {"current_steps": 111225, "total_steps": 181800, "loss": 0.0507, "lr": 1.964924569700189e-05, "epoch": 12.235973597359736, "percentage": 61.18, "elapsed_time": "4:23:22", "remaining_time": "2:47:06", "throughput": 1485.47, "total_tokens": 23473856} {"current_steps": 111230, "total_steps": 181800, "loss": 0.004, "lr": 1.9646901270584583e-05, "epoch": 12.236523652365236, "percentage": 61.18, "elapsed_time": "4:23:22", "remaining_time": "2:47:06", "throughput": 1485.48, "total_tokens": 23474976} {"current_steps": 111235, "total_steps": 181800, "loss": 0.0108, "lr": 1.964455689350423e-05, "epoch": 12.237073707370737, "percentage": 61.19, "elapsed_time": "4:23:23", "remaining_time": "2:47:05", "throughput": 1485.48, "total_tokens": 23476032} {"current_steps": 111240, "total_steps": 181800, "loss": 0.1404, "lr": 1.9642212565782416e-05, "epoch": 12.237623762376238, "percentage": 61.19, "elapsed_time": "4:23:24", "remaining_time": "2:47:04", "throughput": 1485.48, "total_tokens": 23477056} {"current_steps": 111245, "total_steps": 181800, "loss": 0.0118, "lr": 1.963986828744077e-05, "epoch": 12.238173817381739, "percentage": 61.19, "elapsed_time": "4:23:25", "remaining_time": "2:47:04", "throughput": 1485.48, "total_tokens": 23478144} {"current_steps": 111250, "total_steps": 181800, "loss": 0.0423, "lr": 1.9637524058500878e-05, "epoch": 12.238723872387238, "percentage": 61.19, "elapsed_time": "4:23:25", "remaining_time": "2:47:03", "throughput": 1485.49, "total_tokens": 23479264} {"current_steps": 111255, "total_steps": 181800, "loss": 0.0348, "lr": 1.963517987898435e-05, "epoch": 12.23927392739274, "percentage": 61.2, "elapsed_time": "4:23:26", "remaining_time": "2:47:02", "throughput": 1485.49, "total_tokens": 23480320} {"current_steps": 111260, "total_steps": 181800, "loss": 0.0267, "lr": 1.963283574891281e-05, "epoch": 12.23982398239824, "percentage": 61.2, "elapsed_time": "4:23:27", "remaining_time": "2:47:01", "throughput": 1485.5, "total_tokens": 23481408} {"current_steps": 111265, "total_steps": 181800, "loss": 0.0125, "lr": 1.963049166830783e-05, "epoch": 12.24037403740374, "percentage": 61.2, "elapsed_time": "4:23:27", "remaining_time": "2:47:01", "throughput": 1485.5, "total_tokens": 23482496} {"current_steps": 111270, "total_steps": 181800, "loss": 0.0064, "lr": 1.9628147637191042e-05, "epoch": 12.24092409240924, "percentage": 61.2, "elapsed_time": "4:23:28", "remaining_time": "2:47:00", "throughput": 1485.5, "total_tokens": 23483552} {"current_steps": 111275, "total_steps": 181800, "loss": 0.0249, "lr": 1.9625803655584042e-05, "epoch": 12.241474147414742, "percentage": 61.21, "elapsed_time": "4:23:29", "remaining_time": "2:46:59", "throughput": 1485.51, "total_tokens": 23484640} {"current_steps": 111280, "total_steps": 181800, "loss": 0.0419, "lr": 1.9623459723508415e-05, "epoch": 12.242024202420241, "percentage": 61.21, "elapsed_time": "4:23:29", "remaining_time": "2:46:58", "throughput": 1485.51, "total_tokens": 23485728} {"current_steps": 111285, "total_steps": 181800, "loss": 0.0013, "lr": 1.9621115840985795e-05, "epoch": 12.242574257425742, "percentage": 61.21, "elapsed_time": "4:23:30", "remaining_time": "2:46:58", "throughput": 1485.51, "total_tokens": 23486752} {"current_steps": 111290, "total_steps": 181800, "loss": 0.1254, "lr": 1.9618772008037763e-05, "epoch": 12.243124312431243, "percentage": 61.22, "elapsed_time": "4:23:31", "remaining_time": "2:46:57", "throughput": 1485.52, "total_tokens": 23487872} {"current_steps": 111295, "total_steps": 181800, "loss": 0.028, "lr": 1.961642822468593e-05, "epoch": 12.243674367436745, "percentage": 61.22, "elapsed_time": "4:23:31", "remaining_time": "2:46:56", "throughput": 1485.52, "total_tokens": 23488896} {"current_steps": 111300, "total_steps": 181800, "loss": 0.0854, "lr": 1.96140844909519e-05, "epoch": 12.244224422442244, "percentage": 61.22, "elapsed_time": "4:23:32", "remaining_time": "2:46:56", "throughput": 1485.52, "total_tokens": 23489920} {"current_steps": 111305, "total_steps": 181800, "loss": 0.1432, "lr": 1.9611740806857253e-05, "epoch": 12.244774477447745, "percentage": 61.22, "elapsed_time": "4:23:33", "remaining_time": "2:46:55", "throughput": 1485.52, "total_tokens": 23491008} {"current_steps": 111310, "total_steps": 181800, "loss": 0.154, "lr": 1.9609397172423617e-05, "epoch": 12.245324532453246, "percentage": 61.23, "elapsed_time": "4:23:34", "remaining_time": "2:46:54", "throughput": 1485.53, "total_tokens": 23492128} {"current_steps": 111315, "total_steps": 181800, "loss": 0.0199, "lr": 1.9607053587672576e-05, "epoch": 12.245874587458745, "percentage": 61.23, "elapsed_time": "4:23:34", "remaining_time": "2:46:53", "throughput": 1485.53, "total_tokens": 23493184} {"current_steps": 111320, "total_steps": 181800, "loss": 0.0052, "lr": 1.960471005262574e-05, "epoch": 12.246424642464246, "percentage": 61.23, "elapsed_time": "4:23:35", "remaining_time": "2:46:53", "throughput": 1485.53, "total_tokens": 23494176} {"current_steps": 111325, "total_steps": 181800, "loss": 0.0765, "lr": 1.96023665673047e-05, "epoch": 12.246974697469748, "percentage": 61.23, "elapsed_time": "4:23:36", "remaining_time": "2:46:52", "throughput": 1485.53, "total_tokens": 23495200} {"current_steps": 111330, "total_steps": 181800, "loss": 0.0819, "lr": 1.9600023131731054e-05, "epoch": 12.247524752475247, "percentage": 61.24, "elapsed_time": "4:23:36", "remaining_time": "2:46:51", "throughput": 1485.53, "total_tokens": 23496256} {"current_steps": 111335, "total_steps": 181800, "loss": 0.0031, "lr": 1.9597679745926412e-05, "epoch": 12.248074807480748, "percentage": 61.24, "elapsed_time": "4:23:37", "remaining_time": "2:46:51", "throughput": 1485.53, "total_tokens": 23497280} {"current_steps": 111340, "total_steps": 181800, "loss": 0.0096, "lr": 1.9595336409912346e-05, "epoch": 12.248624862486249, "percentage": 61.24, "elapsed_time": "4:23:38", "remaining_time": "2:46:50", "throughput": 1485.53, "total_tokens": 23498304} {"current_steps": 111345, "total_steps": 181800, "loss": 0.1033, "lr": 1.959299312371049e-05, "epoch": 12.249174917491748, "percentage": 61.25, "elapsed_time": "4:23:38", "remaining_time": "2:46:49", "throughput": 1485.53, "total_tokens": 23499392} {"current_steps": 111350, "total_steps": 181800, "loss": 0.0227, "lr": 1.9590649887342418e-05, "epoch": 12.24972497249725, "percentage": 61.25, "elapsed_time": "4:23:39", "remaining_time": "2:46:48", "throughput": 1485.53, "total_tokens": 23500384} {"current_steps": 111355, "total_steps": 181800, "loss": 0.0043, "lr": 1.958830670082972e-05, "epoch": 12.25027502750275, "percentage": 61.25, "elapsed_time": "4:23:40", "remaining_time": "2:46:48", "throughput": 1485.54, "total_tokens": 23501504} {"current_steps": 111360, "total_steps": 181800, "loss": 0.0216, "lr": 1.9585963564194017e-05, "epoch": 12.250825082508252, "percentage": 61.25, "elapsed_time": "4:23:40", "remaining_time": "2:46:47", "throughput": 1485.54, "total_tokens": 23502528} {"current_steps": 111365, "total_steps": 181800, "loss": 0.002, "lr": 1.9583620477456878e-05, "epoch": 12.251375137513751, "percentage": 61.26, "elapsed_time": "4:23:41", "remaining_time": "2:46:46", "throughput": 1485.54, "total_tokens": 23503584} {"current_steps": 111370, "total_steps": 181800, "loss": 0.0421, "lr": 1.958127744063991e-05, "epoch": 12.251925192519252, "percentage": 61.26, "elapsed_time": "4:23:42", "remaining_time": "2:46:45", "throughput": 1485.54, "total_tokens": 23504640} {"current_steps": 111375, "total_steps": 181800, "loss": 0.0043, "lr": 1.9578934453764718e-05, "epoch": 12.252475247524753, "percentage": 61.26, "elapsed_time": "4:23:42", "remaining_time": "2:46:45", "throughput": 1485.54, "total_tokens": 23505664} {"current_steps": 111380, "total_steps": 181800, "loss": 0.119, "lr": 1.9576591516852878e-05, "epoch": 12.253025302530252, "percentage": 61.27, "elapsed_time": "4:23:43", "remaining_time": "2:46:44", "throughput": 1485.54, "total_tokens": 23506752} {"current_steps": 111385, "total_steps": 181800, "loss": 0.052, "lr": 1.9574248629925993e-05, "epoch": 12.253575357535754, "percentage": 61.27, "elapsed_time": "4:23:44", "remaining_time": "2:46:43", "throughput": 1485.54, "total_tokens": 23507744} {"current_steps": 111390, "total_steps": 181800, "loss": 0.0338, "lr": 1.957190579300565e-05, "epoch": 12.254125412541255, "percentage": 61.27, "elapsed_time": "4:23:45", "remaining_time": "2:46:43", "throughput": 1485.54, "total_tokens": 23508768} {"current_steps": 111395, "total_steps": 181800, "loss": 0.0351, "lr": 1.956956300611346e-05, "epoch": 12.254675467546754, "percentage": 61.27, "elapsed_time": "4:23:45", "remaining_time": "2:46:42", "throughput": 1485.55, "total_tokens": 23509856} {"current_steps": 111400, "total_steps": 181800, "loss": 0.0761, "lr": 1.956722026927099e-05, "epoch": 12.255225522552255, "percentage": 61.28, "elapsed_time": "4:23:46", "remaining_time": "2:46:41", "throughput": 1485.55, "total_tokens": 23510912} {"current_steps": 111405, "total_steps": 181800, "loss": 0.0103, "lr": 1.9564877582499845e-05, "epoch": 12.255775577557756, "percentage": 61.28, "elapsed_time": "4:23:47", "remaining_time": "2:46:40", "throughput": 1485.55, "total_tokens": 23511968} {"current_steps": 111410, "total_steps": 181800, "loss": 0.081, "lr": 1.956253494582162e-05, "epoch": 12.256325632563255, "percentage": 61.28, "elapsed_time": "4:23:47", "remaining_time": "2:46:40", "throughput": 1485.55, "total_tokens": 23512992} {"current_steps": 111415, "total_steps": 181800, "loss": 0.0079, "lr": 1.9560192359257906e-05, "epoch": 12.256875687568757, "percentage": 61.28, "elapsed_time": "4:23:48", "remaining_time": "2:46:39", "throughput": 1485.55, "total_tokens": 23513984} {"current_steps": 111420, "total_steps": 181800, "loss": 0.0158, "lr": 1.9557849822830277e-05, "epoch": 12.257425742574258, "percentage": 61.29, "elapsed_time": "4:23:49", "remaining_time": "2:46:38", "throughput": 1485.55, "total_tokens": 23515072} {"current_steps": 111425, "total_steps": 181800, "loss": 0.0378, "lr": 1.955550733656034e-05, "epoch": 12.257975797579759, "percentage": 61.29, "elapsed_time": "4:23:49", "remaining_time": "2:46:38", "throughput": 1485.55, "total_tokens": 23516128} {"current_steps": 111430, "total_steps": 181800, "loss": 0.0029, "lr": 1.9553164900469677e-05, "epoch": 12.258525852585258, "percentage": 61.29, "elapsed_time": "4:23:50", "remaining_time": "2:46:37", "throughput": 1485.56, "total_tokens": 23517216} {"current_steps": 111435, "total_steps": 181800, "loss": 0.0045, "lr": 1.9550822514579887e-05, "epoch": 12.25907590759076, "percentage": 61.3, "elapsed_time": "4:23:51", "remaining_time": "2:46:36", "throughput": 1485.56, "total_tokens": 23518240} {"current_steps": 111440, "total_steps": 181800, "loss": 0.0426, "lr": 1.9548480178912545e-05, "epoch": 12.25962596259626, "percentage": 61.3, "elapsed_time": "4:23:51", "remaining_time": "2:46:35", "throughput": 1485.56, "total_tokens": 23519264} {"current_steps": 111445, "total_steps": 181800, "loss": 0.0097, "lr": 1.9546137893489242e-05, "epoch": 12.26017601760176, "percentage": 61.3, "elapsed_time": "4:23:52", "remaining_time": "2:46:35", "throughput": 1485.56, "total_tokens": 23520288} {"current_steps": 111450, "total_steps": 181800, "loss": 0.0023, "lr": 1.9543795658331578e-05, "epoch": 12.26072607260726, "percentage": 61.3, "elapsed_time": "4:23:53", "remaining_time": "2:46:34", "throughput": 1485.56, "total_tokens": 23521344} {"current_steps": 111455, "total_steps": 181800, "loss": 0.0942, "lr": 1.954145347346112e-05, "epoch": 12.261276127612762, "percentage": 61.31, "elapsed_time": "4:23:54", "remaining_time": "2:46:33", "throughput": 1485.56, "total_tokens": 23522400} {"current_steps": 111460, "total_steps": 181800, "loss": 0.0693, "lr": 1.9539111338899475e-05, "epoch": 12.261826182618261, "percentage": 61.31, "elapsed_time": "4:23:54", "remaining_time": "2:46:32", "throughput": 1485.56, "total_tokens": 23523424} {"current_steps": 111465, "total_steps": 181800, "loss": 0.0091, "lr": 1.953676925466822e-05, "epoch": 12.262376237623762, "percentage": 61.31, "elapsed_time": "4:23:55", "remaining_time": "2:46:32", "throughput": 1485.57, "total_tokens": 23524512} {"current_steps": 111470, "total_steps": 181800, "loss": 0.0029, "lr": 1.953442722078893e-05, "epoch": 12.262926292629263, "percentage": 61.31, "elapsed_time": "4:23:56", "remaining_time": "2:46:31", "throughput": 1485.56, "total_tokens": 23525504} {"current_steps": 111475, "total_steps": 181800, "loss": 0.05, "lr": 1.953208523728322e-05, "epoch": 12.263476347634764, "percentage": 61.32, "elapsed_time": "4:23:56", "remaining_time": "2:46:30", "throughput": 1485.56, "total_tokens": 23526528} {"current_steps": 111480, "total_steps": 181800, "loss": 0.0496, "lr": 1.9529743304172643e-05, "epoch": 12.264026402640264, "percentage": 61.32, "elapsed_time": "4:23:57", "remaining_time": "2:46:30", "throughput": 1485.57, "total_tokens": 23527616} {"current_steps": 111485, "total_steps": 181800, "loss": 0.0936, "lr": 1.9527401421478802e-05, "epoch": 12.264576457645765, "percentage": 61.32, "elapsed_time": "4:23:58", "remaining_time": "2:46:29", "throughput": 1485.57, "total_tokens": 23528640} {"current_steps": 111490, "total_steps": 181800, "loss": 0.0966, "lr": 1.952505958922328e-05, "epoch": 12.265126512651266, "percentage": 61.33, "elapsed_time": "4:23:58", "remaining_time": "2:46:28", "throughput": 1485.57, "total_tokens": 23529696} {"current_steps": 111495, "total_steps": 181800, "loss": 0.0114, "lr": 1.9522717807427647e-05, "epoch": 12.265676567656765, "percentage": 61.33, "elapsed_time": "4:23:59", "remaining_time": "2:46:27", "throughput": 1485.57, "total_tokens": 23530720} {"current_steps": 111500, "total_steps": 181800, "loss": 0.0021, "lr": 1.9520376076113504e-05, "epoch": 12.266226622662266, "percentage": 61.33, "elapsed_time": "4:24:00", "remaining_time": "2:46:27", "throughput": 1485.57, "total_tokens": 23531776} {"current_steps": 111505, "total_steps": 181800, "loss": 0.044, "lr": 1.9518034395302414e-05, "epoch": 12.266776677667767, "percentage": 61.33, "elapsed_time": "4:24:00", "remaining_time": "2:46:26", "throughput": 1485.57, "total_tokens": 23532832} {"current_steps": 111510, "total_steps": 181800, "loss": 0.0018, "lr": 1.9515692765015985e-05, "epoch": 12.267326732673267, "percentage": 61.34, "elapsed_time": "4:24:01", "remaining_time": "2:46:25", "throughput": 1485.57, "total_tokens": 23533856} {"current_steps": 111515, "total_steps": 181800, "loss": 0.0061, "lr": 1.951335118527578e-05, "epoch": 12.267876787678768, "percentage": 61.34, "elapsed_time": "4:24:02", "remaining_time": "2:46:24", "throughput": 1485.57, "total_tokens": 23534880} {"current_steps": 111520, "total_steps": 181800, "loss": 0.0543, "lr": 1.9511009656103377e-05, "epoch": 12.268426842684269, "percentage": 61.34, "elapsed_time": "4:24:02", "remaining_time": "2:46:24", "throughput": 1485.57, "total_tokens": 23535904} {"current_steps": 111525, "total_steps": 181800, "loss": 0.0105, "lr": 1.950866817752037e-05, "epoch": 12.268976897689768, "percentage": 61.34, "elapsed_time": "4:24:03", "remaining_time": "2:46:23", "throughput": 1485.57, "total_tokens": 23536928} {"current_steps": 111530, "total_steps": 181800, "loss": 0.0232, "lr": 1.950632674954833e-05, "epoch": 12.26952695269527, "percentage": 61.35, "elapsed_time": "4:24:04", "remaining_time": "2:46:22", "throughput": 1485.57, "total_tokens": 23537920} {"current_steps": 111535, "total_steps": 181800, "loss": 0.0302, "lr": 1.950398537220885e-05, "epoch": 12.27007700770077, "percentage": 61.35, "elapsed_time": "4:24:05", "remaining_time": "2:46:22", "throughput": 1485.58, "total_tokens": 23539040} {"current_steps": 111540, "total_steps": 181800, "loss": 0.125, "lr": 1.950164404552349e-05, "epoch": 12.270627062706271, "percentage": 61.35, "elapsed_time": "4:24:05", "remaining_time": "2:46:21", "throughput": 1485.58, "total_tokens": 23540096} {"current_steps": 111545, "total_steps": 181800, "loss": 0.087, "lr": 1.9499302769513837e-05, "epoch": 12.27117711771177, "percentage": 61.36, "elapsed_time": "4:24:06", "remaining_time": "2:46:20", "throughput": 1485.58, "total_tokens": 23541088} {"current_steps": 111550, "total_steps": 181800, "loss": 0.0701, "lr": 1.949696154420148e-05, "epoch": 12.271727172717272, "percentage": 61.36, "elapsed_time": "4:24:07", "remaining_time": "2:46:19", "throughput": 1485.58, "total_tokens": 23542112} {"current_steps": 111555, "total_steps": 181800, "loss": 0.029, "lr": 1.949462036960798e-05, "epoch": 12.272277227722773, "percentage": 61.36, "elapsed_time": "4:24:07", "remaining_time": "2:46:19", "throughput": 1485.58, "total_tokens": 23543168} {"current_steps": 111560, "total_steps": 181800, "loss": 0.0877, "lr": 1.9492279245754923e-05, "epoch": 12.272827282728272, "percentage": 61.36, "elapsed_time": "4:24:08", "remaining_time": "2:46:18", "throughput": 1485.58, "total_tokens": 23544224} {"current_steps": 111565, "total_steps": 181800, "loss": 0.0014, "lr": 1.9489938172663897e-05, "epoch": 12.273377337733773, "percentage": 61.37, "elapsed_time": "4:24:09", "remaining_time": "2:46:17", "throughput": 1485.58, "total_tokens": 23545248} {"current_steps": 111570, "total_steps": 181800, "loss": 0.0354, "lr": 1.948759715035645e-05, "epoch": 12.273927392739274, "percentage": 61.37, "elapsed_time": "4:24:09", "remaining_time": "2:46:17", "throughput": 1485.58, "total_tokens": 23546240} {"current_steps": 111575, "total_steps": 181800, "loss": 0.0464, "lr": 1.9485256178854182e-05, "epoch": 12.274477447744774, "percentage": 61.37, "elapsed_time": "4:24:10", "remaining_time": "2:46:16", "throughput": 1485.58, "total_tokens": 23547328} {"current_steps": 111580, "total_steps": 181800, "loss": 0.0538, "lr": 1.9482915258178658e-05, "epoch": 12.275027502750275, "percentage": 61.38, "elapsed_time": "4:24:11", "remaining_time": "2:46:15", "throughput": 1485.58, "total_tokens": 23548352} {"current_steps": 111585, "total_steps": 181800, "loss": 0.0094, "lr": 1.9480574388351464e-05, "epoch": 12.275577557755776, "percentage": 61.38, "elapsed_time": "4:24:11", "remaining_time": "2:46:14", "throughput": 1485.59, "total_tokens": 23549408} {"current_steps": 111590, "total_steps": 181800, "loss": 0.0089, "lr": 1.9478233569394168e-05, "epoch": 12.276127612761275, "percentage": 61.38, "elapsed_time": "4:24:12", "remaining_time": "2:46:14", "throughput": 1485.59, "total_tokens": 23550432} {"current_steps": 111595, "total_steps": 181800, "loss": 0.0015, "lr": 1.9475892801328336e-05, "epoch": 12.276677667766776, "percentage": 61.38, "elapsed_time": "4:24:13", "remaining_time": "2:46:13", "throughput": 1485.58, "total_tokens": 23551392} {"current_steps": 111600, "total_steps": 181800, "loss": 0.1733, "lr": 1.9473552084175554e-05, "epoch": 12.277227722772277, "percentage": 61.39, "elapsed_time": "4:24:14", "remaining_time": "2:46:12", "throughput": 1485.58, "total_tokens": 23552416} {"current_steps": 111605, "total_steps": 181800, "loss": 0.0491, "lr": 1.9471211417957394e-05, "epoch": 12.277777777777779, "percentage": 61.39, "elapsed_time": "4:24:14", "remaining_time": "2:46:11", "throughput": 1485.59, "total_tokens": 23553536} {"current_steps": 111610, "total_steps": 181800, "loss": 0.0238, "lr": 1.9468870802695415e-05, "epoch": 12.278327832783278, "percentage": 61.39, "elapsed_time": "4:24:15", "remaining_time": "2:46:11", "throughput": 1485.59, "total_tokens": 23554528} {"current_steps": 111615, "total_steps": 181800, "loss": 0.1534, "lr": 1.9466530238411205e-05, "epoch": 12.278877887788779, "percentage": 61.39, "elapsed_time": "4:24:16", "remaining_time": "2:46:10", "throughput": 1485.59, "total_tokens": 23555616} {"current_steps": 111620, "total_steps": 181800, "loss": 0.0807, "lr": 1.9464189725126328e-05, "epoch": 12.27942794279428, "percentage": 61.4, "elapsed_time": "4:24:16", "remaining_time": "2:46:09", "throughput": 1485.59, "total_tokens": 23556704} {"current_steps": 111625, "total_steps": 181800, "loss": 0.0904, "lr": 1.9461849262862365e-05, "epoch": 12.27997799779978, "percentage": 61.4, "elapsed_time": "4:24:17", "remaining_time": "2:46:09", "throughput": 1485.6, "total_tokens": 23557824} {"current_steps": 111630, "total_steps": 181800, "loss": 0.2218, "lr": 1.945950885164088e-05, "epoch": 12.28052805280528, "percentage": 61.4, "elapsed_time": "4:24:18", "remaining_time": "2:46:08", "throughput": 1485.6, "total_tokens": 23558912} {"current_steps": 111635, "total_steps": 181800, "loss": 0.0183, "lr": 1.9457168491483434e-05, "epoch": 12.281078107810782, "percentage": 61.41, "elapsed_time": "4:24:18", "remaining_time": "2:46:07", "throughput": 1485.6, "total_tokens": 23559936} {"current_steps": 111640, "total_steps": 181800, "loss": 0.0293, "lr": 1.9454828182411617e-05, "epoch": 12.281628162816281, "percentage": 61.41, "elapsed_time": "4:24:19", "remaining_time": "2:46:06", "throughput": 1485.6, "total_tokens": 23560928} {"current_steps": 111645, "total_steps": 181800, "loss": 0.007, "lr": 1.9452487924446973e-05, "epoch": 12.282178217821782, "percentage": 61.41, "elapsed_time": "4:24:20", "remaining_time": "2:46:06", "throughput": 1485.6, "total_tokens": 23561952} {"current_steps": 111650, "total_steps": 181800, "loss": 0.0033, "lr": 1.94501477176111e-05, "epoch": 12.282728272827283, "percentage": 61.41, "elapsed_time": "4:24:20", "remaining_time": "2:46:05", "throughput": 1485.6, "total_tokens": 23563008} {"current_steps": 111655, "total_steps": 181800, "loss": 0.004, "lr": 1.944780756192555e-05, "epoch": 12.283278327832782, "percentage": 61.42, "elapsed_time": "4:24:21", "remaining_time": "2:46:04", "throughput": 1485.6, "total_tokens": 23564032} {"current_steps": 111660, "total_steps": 181800, "loss": 0.0093, "lr": 1.9445467457411888e-05, "epoch": 12.283828382838283, "percentage": 61.42, "elapsed_time": "4:24:22", "remaining_time": "2:46:03", "throughput": 1485.61, "total_tokens": 23565120} {"current_steps": 111665, "total_steps": 181800, "loss": 0.0517, "lr": 1.9443127404091695e-05, "epoch": 12.284378437843785, "percentage": 61.42, "elapsed_time": "4:24:22", "remaining_time": "2:46:03", "throughput": 1485.61, "total_tokens": 23566112} {"current_steps": 111670, "total_steps": 181800, "loss": 0.0102, "lr": 1.944078740198652e-05, "epoch": 12.284928492849286, "percentage": 61.42, "elapsed_time": "4:24:23", "remaining_time": "2:46:02", "throughput": 1485.61, "total_tokens": 23567200} {"current_steps": 111675, "total_steps": 181800, "loss": 0.0029, "lr": 1.9438447451117945e-05, "epoch": 12.285478547854785, "percentage": 61.43, "elapsed_time": "4:24:24", "remaining_time": "2:46:01", "throughput": 1485.61, "total_tokens": 23568256} {"current_steps": 111680, "total_steps": 181800, "loss": 0.0058, "lr": 1.9436107551507537e-05, "epoch": 12.286028602860286, "percentage": 61.43, "elapsed_time": "4:24:25", "remaining_time": "2:46:01", "throughput": 1485.61, "total_tokens": 23569312} {"current_steps": 111685, "total_steps": 181800, "loss": 0.0028, "lr": 1.9433767703176846e-05, "epoch": 12.286578657865787, "percentage": 61.43, "elapsed_time": "4:24:25", "remaining_time": "2:46:00", "throughput": 1485.62, "total_tokens": 23570400} {"current_steps": 111690, "total_steps": 181800, "loss": 0.0505, "lr": 1.9431427906147453e-05, "epoch": 12.287128712871286, "percentage": 61.44, "elapsed_time": "4:24:26", "remaining_time": "2:45:59", "throughput": 1485.62, "total_tokens": 23571488} {"current_steps": 111695, "total_steps": 181800, "loss": 0.0041, "lr": 1.9429088160440912e-05, "epoch": 12.287678767876788, "percentage": 61.44, "elapsed_time": "4:24:27", "remaining_time": "2:45:58", "throughput": 1485.62, "total_tokens": 23572512} {"current_steps": 111700, "total_steps": 181800, "loss": 0.037, "lr": 1.94267484660788e-05, "epoch": 12.288228822882289, "percentage": 61.44, "elapsed_time": "4:24:27", "remaining_time": "2:45:58", "throughput": 1485.62, "total_tokens": 23573600} {"current_steps": 111705, "total_steps": 181800, "loss": 0.007, "lr": 1.9424408823082672e-05, "epoch": 12.288778877887788, "percentage": 61.44, "elapsed_time": "4:24:28", "remaining_time": "2:45:57", "throughput": 1485.63, "total_tokens": 23574688} {"current_steps": 111710, "total_steps": 181800, "loss": 0.0068, "lr": 1.9422069231474084e-05, "epoch": 12.289328932893289, "percentage": 61.45, "elapsed_time": "4:24:29", "remaining_time": "2:45:56", "throughput": 1485.63, "total_tokens": 23575744} {"current_steps": 111715, "total_steps": 181800, "loss": 0.1276, "lr": 1.9419729691274612e-05, "epoch": 12.28987898789879, "percentage": 61.45, "elapsed_time": "4:24:29", "remaining_time": "2:45:56", "throughput": 1485.63, "total_tokens": 23576736} {"current_steps": 111720, "total_steps": 181800, "loss": 0.0536, "lr": 1.941739020250581e-05, "epoch": 12.290429042904291, "percentage": 61.45, "elapsed_time": "4:24:30", "remaining_time": "2:45:55", "throughput": 1485.63, "total_tokens": 23577760} {"current_steps": 111725, "total_steps": 181800, "loss": 0.0162, "lr": 1.9415050765189252e-05, "epoch": 12.29097909790979, "percentage": 61.45, "elapsed_time": "4:24:31", "remaining_time": "2:45:54", "throughput": 1485.63, "total_tokens": 23578784} {"current_steps": 111730, "total_steps": 181800, "loss": 0.0077, "lr": 1.9412711379346492e-05, "epoch": 12.291529152915292, "percentage": 61.46, "elapsed_time": "4:24:31", "remaining_time": "2:45:53", "throughput": 1485.63, "total_tokens": 23579808} {"current_steps": 111735, "total_steps": 181800, "loss": 0.0273, "lr": 1.941037204499908e-05, "epoch": 12.292079207920793, "percentage": 61.46, "elapsed_time": "4:24:32", "remaining_time": "2:45:53", "throughput": 1485.63, "total_tokens": 23580832} {"current_steps": 111740, "total_steps": 181800, "loss": 0.092, "lr": 1.9408032762168596e-05, "epoch": 12.292629262926292, "percentage": 61.46, "elapsed_time": "4:24:33", "remaining_time": "2:45:52", "throughput": 1485.63, "total_tokens": 23581856} {"current_steps": 111745, "total_steps": 181800, "loss": 0.0035, "lr": 1.9405693530876586e-05, "epoch": 12.293179317931793, "percentage": 61.47, "elapsed_time": "4:24:34", "remaining_time": "2:45:51", "throughput": 1485.63, "total_tokens": 23582880} {"current_steps": 111750, "total_steps": 181800, "loss": 0.0025, "lr": 1.9403354351144612e-05, "epoch": 12.293729372937294, "percentage": 61.47, "elapsed_time": "4:24:34", "remaining_time": "2:45:50", "throughput": 1485.63, "total_tokens": 23583968} {"current_steps": 111755, "total_steps": 181800, "loss": 0.0097, "lr": 1.9401015222994245e-05, "epoch": 12.294279427942794, "percentage": 61.47, "elapsed_time": "4:24:35", "remaining_time": "2:45:50", "throughput": 1485.63, "total_tokens": 23584992} {"current_steps": 111760, "total_steps": 181800, "loss": 0.0509, "lr": 1.9398676146447018e-05, "epoch": 12.294829482948295, "percentage": 61.47, "elapsed_time": "4:24:36", "remaining_time": "2:45:49", "throughput": 1485.63, "total_tokens": 23585952} {"current_steps": 111765, "total_steps": 181800, "loss": 0.005, "lr": 1.9396337121524522e-05, "epoch": 12.295379537953796, "percentage": 61.48, "elapsed_time": "4:24:36", "remaining_time": "2:45:48", "throughput": 1485.63, "total_tokens": 23587008} {"current_steps": 111770, "total_steps": 181800, "loss": 0.0082, "lr": 1.9393998148248285e-05, "epoch": 12.295929592959295, "percentage": 61.48, "elapsed_time": "4:24:37", "remaining_time": "2:45:48", "throughput": 1485.63, "total_tokens": 23588064} {"current_steps": 111775, "total_steps": 181800, "loss": 0.0078, "lr": 1.939165922663988e-05, "epoch": 12.296479647964796, "percentage": 61.48, "elapsed_time": "4:24:38", "remaining_time": "2:45:47", "throughput": 1485.64, "total_tokens": 23589152} {"current_steps": 111780, "total_steps": 181800, "loss": 0.0077, "lr": 1.9389320356720874e-05, "epoch": 12.297029702970297, "percentage": 61.49, "elapsed_time": "4:24:38", "remaining_time": "2:45:46", "throughput": 1485.63, "total_tokens": 23590144} {"current_steps": 111785, "total_steps": 181800, "loss": 0.051, "lr": 1.9386981538512794e-05, "epoch": 12.297579757975798, "percentage": 61.49, "elapsed_time": "4:24:39", "remaining_time": "2:45:45", "throughput": 1485.64, "total_tokens": 23591232} {"current_steps": 111790, "total_steps": 181800, "loss": 0.0024, "lr": 1.9384642772037218e-05, "epoch": 12.298129812981298, "percentage": 61.49, "elapsed_time": "4:24:40", "remaining_time": "2:45:45", "throughput": 1485.64, "total_tokens": 23592320} {"current_steps": 111795, "total_steps": 181800, "loss": 0.0565, "lr": 1.93823040573157e-05, "epoch": 12.298679867986799, "percentage": 61.49, "elapsed_time": "4:24:40", "remaining_time": "2:45:44", "throughput": 1485.64, "total_tokens": 23593312} {"current_steps": 111800, "total_steps": 181800, "loss": 0.0098, "lr": 1.937996539436978e-05, "epoch": 12.2992299229923, "percentage": 61.5, "elapsed_time": "4:24:41", "remaining_time": "2:45:43", "throughput": 1485.64, "total_tokens": 23594368} {"current_steps": 111805, "total_steps": 181800, "loss": 0.1354, "lr": 1.9377626783221026e-05, "epoch": 12.2997799779978, "percentage": 61.5, "elapsed_time": "4:24:42", "remaining_time": "2:45:43", "throughput": 1485.64, "total_tokens": 23595392} {"current_steps": 111810, "total_steps": 181800, "loss": 0.0135, "lr": 1.9375288223890985e-05, "epoch": 12.3003300330033, "percentage": 61.5, "elapsed_time": "4:24:42", "remaining_time": "2:45:42", "throughput": 1485.65, "total_tokens": 23596480} {"current_steps": 111815, "total_steps": 181800, "loss": 0.0149, "lr": 1.9372949716401222e-05, "epoch": 12.300880088008801, "percentage": 61.5, "elapsed_time": "4:24:43", "remaining_time": "2:45:41", "throughput": 1485.65, "total_tokens": 23597536} {"current_steps": 111820, "total_steps": 181800, "loss": 0.014, "lr": 1.9370611260773276e-05, "epoch": 12.3014301430143, "percentage": 61.51, "elapsed_time": "4:24:44", "remaining_time": "2:45:40", "throughput": 1485.65, "total_tokens": 23598624} {"current_steps": 111825, "total_steps": 181800, "loss": 0.0398, "lr": 1.93682728570287e-05, "epoch": 12.301980198019802, "percentage": 61.51, "elapsed_time": "4:24:45", "remaining_time": "2:45:40", "throughput": 1485.66, "total_tokens": 23599680} {"current_steps": 111830, "total_steps": 181800, "loss": 0.0297, "lr": 1.936593450518906e-05, "epoch": 12.302530253025303, "percentage": 61.51, "elapsed_time": "4:24:45", "remaining_time": "2:45:39", "throughput": 1485.65, "total_tokens": 23600672} {"current_steps": 111835, "total_steps": 181800, "loss": 0.028, "lr": 1.9363596205275888e-05, "epoch": 12.303080308030804, "percentage": 61.52, "elapsed_time": "4:24:46", "remaining_time": "2:45:38", "throughput": 1485.66, "total_tokens": 23601728} {"current_steps": 111840, "total_steps": 181800, "loss": 0.0047, "lr": 1.9361257957310758e-05, "epoch": 12.303630363036303, "percentage": 61.52, "elapsed_time": "4:24:47", "remaining_time": "2:45:37", "throughput": 1485.66, "total_tokens": 23602752} {"current_steps": 111845, "total_steps": 181800, "loss": 0.0201, "lr": 1.93589197613152e-05, "epoch": 12.304180418041804, "percentage": 61.52, "elapsed_time": "4:24:47", "remaining_time": "2:45:37", "throughput": 1485.66, "total_tokens": 23603808} {"current_steps": 111850, "total_steps": 181800, "loss": 0.0809, "lr": 1.9356581617310766e-05, "epoch": 12.304730473047305, "percentage": 61.52, "elapsed_time": "4:24:48", "remaining_time": "2:45:36", "throughput": 1485.67, "total_tokens": 23604960} {"current_steps": 111855, "total_steps": 181800, "loss": 0.004, "lr": 1.9354243525319025e-05, "epoch": 12.305280528052805, "percentage": 61.53, "elapsed_time": "4:24:49", "remaining_time": "2:45:35", "throughput": 1485.67, "total_tokens": 23606048} {"current_steps": 111860, "total_steps": 181800, "loss": 0.0019, "lr": 1.93519054853615e-05, "epoch": 12.305830583058306, "percentage": 61.53, "elapsed_time": "4:24:49", "remaining_time": "2:45:35", "throughput": 1485.67, "total_tokens": 23607104} {"current_steps": 111865, "total_steps": 181800, "loss": 0.0027, "lr": 1.9349567497459758e-05, "epoch": 12.306380638063807, "percentage": 61.53, "elapsed_time": "4:24:50", "remaining_time": "2:45:34", "throughput": 1485.67, "total_tokens": 23608128} {"current_steps": 111870, "total_steps": 181800, "loss": 0.0048, "lr": 1.9347229561635346e-05, "epoch": 12.306930693069306, "percentage": 61.53, "elapsed_time": "4:24:51", "remaining_time": "2:45:33", "throughput": 1485.68, "total_tokens": 23609216} {"current_steps": 111875, "total_steps": 181800, "loss": 0.0412, "lr": 1.93448916779098e-05, "epoch": 12.307480748074807, "percentage": 61.54, "elapsed_time": "4:24:51", "remaining_time": "2:45:32", "throughput": 1485.68, "total_tokens": 23610240} {"current_steps": 111880, "total_steps": 181800, "loss": 0.0131, "lr": 1.9342553846304673e-05, "epoch": 12.308030803080309, "percentage": 61.54, "elapsed_time": "4:24:52", "remaining_time": "2:45:32", "throughput": 1485.68, "total_tokens": 23611296} {"current_steps": 111885, "total_steps": 181800, "loss": 0.0374, "lr": 1.934021606684151e-05, "epoch": 12.308580858085808, "percentage": 61.54, "elapsed_time": "4:24:53", "remaining_time": "2:45:31", "throughput": 1485.68, "total_tokens": 23612384} {"current_steps": 111890, "total_steps": 181800, "loss": 0.0049, "lr": 1.933787833954186e-05, "epoch": 12.309130913091309, "percentage": 61.55, "elapsed_time": "4:24:53", "remaining_time": "2:45:30", "throughput": 1485.68, "total_tokens": 23613408} {"current_steps": 111895, "total_steps": 181800, "loss": 0.0783, "lr": 1.933554066442728e-05, "epoch": 12.30968096809681, "percentage": 61.55, "elapsed_time": "4:24:54", "remaining_time": "2:45:29", "throughput": 1485.68, "total_tokens": 23614464} {"current_steps": 111900, "total_steps": 181800, "loss": 0.0067, "lr": 1.9333203041519293e-05, "epoch": 12.310231023102311, "percentage": 61.55, "elapsed_time": "4:24:55", "remaining_time": "2:45:29", "throughput": 1485.69, "total_tokens": 23615520} {"current_steps": 111905, "total_steps": 181800, "loss": 0.1526, "lr": 1.9330865470839458e-05, "epoch": 12.31078107810781, "percentage": 61.55, "elapsed_time": "4:24:56", "remaining_time": "2:45:28", "throughput": 1485.69, "total_tokens": 23616544} {"current_steps": 111910, "total_steps": 181800, "loss": 0.0367, "lr": 1.9328527952409308e-05, "epoch": 12.311331133113312, "percentage": 61.56, "elapsed_time": "4:24:56", "remaining_time": "2:45:27", "throughput": 1485.69, "total_tokens": 23617568} {"current_steps": 111915, "total_steps": 181800, "loss": 0.0267, "lr": 1.9326190486250408e-05, "epoch": 12.311881188118813, "percentage": 61.56, "elapsed_time": "4:24:57", "remaining_time": "2:45:27", "throughput": 1485.69, "total_tokens": 23618592} {"current_steps": 111920, "total_steps": 181800, "loss": 0.0931, "lr": 1.9323853072384283e-05, "epoch": 12.312431243124312, "percentage": 61.56, "elapsed_time": "4:24:58", "remaining_time": "2:45:26", "throughput": 1485.69, "total_tokens": 23619648} {"current_steps": 111925, "total_steps": 181800, "loss": 0.0048, "lr": 1.932151571083247e-05, "epoch": 12.312981298129813, "percentage": 61.56, "elapsed_time": "4:24:58", "remaining_time": "2:45:25", "throughput": 1485.69, "total_tokens": 23620672} {"current_steps": 111930, "total_steps": 181800, "loss": 0.1134, "lr": 1.9319178401616538e-05, "epoch": 12.313531353135314, "percentage": 61.57, "elapsed_time": "4:24:59", "remaining_time": "2:45:24", "throughput": 1485.69, "total_tokens": 23621696} {"current_steps": 111935, "total_steps": 181800, "loss": 0.0053, "lr": 1.9316841144758002e-05, "epoch": 12.314081408140813, "percentage": 61.57, "elapsed_time": "4:25:00", "remaining_time": "2:45:24", "throughput": 1485.7, "total_tokens": 23622816} {"current_steps": 111940, "total_steps": 181800, "loss": 0.064, "lr": 1.9314503940278418e-05, "epoch": 12.314631463146315, "percentage": 61.57, "elapsed_time": "4:25:00", "remaining_time": "2:45:23", "throughput": 1485.7, "total_tokens": 23623904} {"current_steps": 111945, "total_steps": 181800, "loss": 0.0258, "lr": 1.9312166788199328e-05, "epoch": 12.315181518151816, "percentage": 61.58, "elapsed_time": "4:25:01", "remaining_time": "2:45:22", "throughput": 1485.7, "total_tokens": 23624992} {"current_steps": 111950, "total_steps": 181800, "loss": 0.0147, "lr": 1.9309829688542253e-05, "epoch": 12.315731573157315, "percentage": 61.58, "elapsed_time": "4:25:02", "remaining_time": "2:45:22", "throughput": 1485.7, "total_tokens": 23626048} {"current_steps": 111955, "total_steps": 181800, "loss": 0.0197, "lr": 1.9307492641328762e-05, "epoch": 12.316281628162816, "percentage": 61.58, "elapsed_time": "4:25:02", "remaining_time": "2:45:21", "throughput": 1485.7, "total_tokens": 23627072} {"current_steps": 111960, "total_steps": 181800, "loss": 0.0099, "lr": 1.9305155646580367e-05, "epoch": 12.316831683168317, "percentage": 61.58, "elapsed_time": "4:25:03", "remaining_time": "2:45:20", "throughput": 1485.71, "total_tokens": 23628192} {"current_steps": 111965, "total_steps": 181800, "loss": 0.0246, "lr": 1.9302818704318626e-05, "epoch": 12.317381738173818, "percentage": 61.59, "elapsed_time": "4:25:04", "remaining_time": "2:45:19", "throughput": 1485.71, "total_tokens": 23629216} {"current_steps": 111970, "total_steps": 181800, "loss": 0.0305, "lr": 1.930048181456508e-05, "epoch": 12.317931793179318, "percentage": 61.59, "elapsed_time": "4:25:05", "remaining_time": "2:45:19", "throughput": 1485.71, "total_tokens": 23630208} {"current_steps": 111975, "total_steps": 181800, "loss": 0.0075, "lr": 1.9298144977341242e-05, "epoch": 12.318481848184819, "percentage": 61.59, "elapsed_time": "4:25:05", "remaining_time": "2:45:18", "throughput": 1485.71, "total_tokens": 23631200} {"current_steps": 111980, "total_steps": 181800, "loss": 0.0173, "lr": 1.9295808192668677e-05, "epoch": 12.31903190319032, "percentage": 61.6, "elapsed_time": "4:25:06", "remaining_time": "2:45:17", "throughput": 1485.71, "total_tokens": 23632224} {"current_steps": 111985, "total_steps": 181800, "loss": 0.0474, "lr": 1.929347146056891e-05, "epoch": 12.319581958195819, "percentage": 61.6, "elapsed_time": "4:25:07", "remaining_time": "2:45:16", "throughput": 1485.71, "total_tokens": 23633280} {"current_steps": 111990, "total_steps": 181800, "loss": 0.0874, "lr": 1.9291134781063475e-05, "epoch": 12.32013201320132, "percentage": 61.6, "elapsed_time": "4:25:07", "remaining_time": "2:45:16", "throughput": 1485.71, "total_tokens": 23634304} {"current_steps": 111995, "total_steps": 181800, "loss": 0.016, "lr": 1.9288798154173913e-05, "epoch": 12.320682068206821, "percentage": 61.6, "elapsed_time": "4:25:08", "remaining_time": "2:45:15", "throughput": 1485.71, "total_tokens": 23635360} {"current_steps": 112000, "total_steps": 181800, "loss": 0.0394, "lr": 1.928646157992175e-05, "epoch": 12.32123212321232, "percentage": 61.61, "elapsed_time": "4:25:09", "remaining_time": "2:45:14", "throughput": 1485.71, "total_tokens": 23636416} {"current_steps": 112005, "total_steps": 181800, "loss": 0.0548, "lr": 1.928412505832854e-05, "epoch": 12.321782178217822, "percentage": 61.61, "elapsed_time": "4:25:09", "remaining_time": "2:45:14", "throughput": 1485.72, "total_tokens": 23637536} {"current_steps": 112010, "total_steps": 181800, "loss": 0.009, "lr": 1.9281788589415804e-05, "epoch": 12.322332233223323, "percentage": 61.61, "elapsed_time": "4:25:10", "remaining_time": "2:45:13", "throughput": 1485.72, "total_tokens": 23638560} {"current_steps": 112015, "total_steps": 181800, "loss": 0.0014, "lr": 1.9279452173205078e-05, "epoch": 12.322882288228822, "percentage": 61.61, "elapsed_time": "4:25:11", "remaining_time": "2:45:12", "throughput": 1485.71, "total_tokens": 23639552} {"current_steps": 112020, "total_steps": 181800, "loss": 0.1523, "lr": 1.9277115809717893e-05, "epoch": 12.323432343234323, "percentage": 61.62, "elapsed_time": "4:25:11", "remaining_time": "2:45:11", "throughput": 1485.71, "total_tokens": 23640544} {"current_steps": 112025, "total_steps": 181800, "loss": 0.0037, "lr": 1.9274779498975782e-05, "epoch": 12.323982398239824, "percentage": 61.62, "elapsed_time": "4:25:12", "remaining_time": "2:45:11", "throughput": 1485.72, "total_tokens": 23641632} {"current_steps": 112030, "total_steps": 181800, "loss": 0.0155, "lr": 1.9272443241000297e-05, "epoch": 12.324532453245325, "percentage": 61.62, "elapsed_time": "4:25:13", "remaining_time": "2:45:10", "throughput": 1485.72, "total_tokens": 23642720} {"current_steps": 112035, "total_steps": 181800, "loss": 0.002, "lr": 1.9270107035812942e-05, "epoch": 12.325082508250825, "percentage": 61.63, "elapsed_time": "4:25:13", "remaining_time": "2:45:09", "throughput": 1485.72, "total_tokens": 23643776} {"current_steps": 112040, "total_steps": 181800, "loss": 0.0067, "lr": 1.926777088343526e-05, "epoch": 12.325632563256326, "percentage": 61.63, "elapsed_time": "4:25:14", "remaining_time": "2:45:09", "throughput": 1485.73, "total_tokens": 23644864} {"current_steps": 112045, "total_steps": 181800, "loss": 0.0088, "lr": 1.9265434783888792e-05, "epoch": 12.326182618261827, "percentage": 61.63, "elapsed_time": "4:25:15", "remaining_time": "2:45:08", "throughput": 1485.73, "total_tokens": 23645984} {"current_steps": 112050, "total_steps": 181800, "loss": 0.0096, "lr": 1.926309873719505e-05, "epoch": 12.326732673267326, "percentage": 61.63, "elapsed_time": "4:25:16", "remaining_time": "2:45:07", "throughput": 1485.74, "total_tokens": 23647104} {"current_steps": 112055, "total_steps": 181800, "loss": 0.0012, "lr": 1.926076274337558e-05, "epoch": 12.327282728272827, "percentage": 61.64, "elapsed_time": "4:25:16", "remaining_time": "2:45:06", "throughput": 1485.74, "total_tokens": 23648128} {"current_steps": 112060, "total_steps": 181800, "loss": 0.0219, "lr": 1.9258426802451912e-05, "epoch": 12.327832783278328, "percentage": 61.64, "elapsed_time": "4:25:17", "remaining_time": "2:45:06", "throughput": 1485.74, "total_tokens": 23649184} {"current_steps": 112065, "total_steps": 181800, "loss": 0.0038, "lr": 1.925609091444555e-05, "epoch": 12.328382838283828, "percentage": 61.64, "elapsed_time": "4:25:18", "remaining_time": "2:45:05", "throughput": 1485.74, "total_tokens": 23650176} {"current_steps": 112070, "total_steps": 181800, "loss": 0.0184, "lr": 1.9253755079378062e-05, "epoch": 12.328932893289329, "percentage": 61.64, "elapsed_time": "4:25:18", "remaining_time": "2:45:04", "throughput": 1485.74, "total_tokens": 23651200} {"current_steps": 112075, "total_steps": 181800, "loss": 0.023, "lr": 1.9251419297270938e-05, "epoch": 12.32948294829483, "percentage": 61.65, "elapsed_time": "4:25:19", "remaining_time": "2:45:03", "throughput": 1485.74, "total_tokens": 23652288} {"current_steps": 112080, "total_steps": 181800, "loss": 0.1128, "lr": 1.924908356814574e-05, "epoch": 12.33003300330033, "percentage": 61.65, "elapsed_time": "4:25:20", "remaining_time": "2:45:03", "throughput": 1485.74, "total_tokens": 23653312} {"current_steps": 112085, "total_steps": 181800, "loss": 0.0073, "lr": 1.9246747892023975e-05, "epoch": 12.33058305830583, "percentage": 61.65, "elapsed_time": "4:25:20", "remaining_time": "2:45:02", "throughput": 1485.74, "total_tokens": 23654368} {"current_steps": 112090, "total_steps": 181800, "loss": 0.0191, "lr": 1.9244412268927168e-05, "epoch": 12.331133113311331, "percentage": 61.66, "elapsed_time": "4:25:21", "remaining_time": "2:45:01", "throughput": 1485.75, "total_tokens": 23655456} {"current_steps": 112095, "total_steps": 181800, "loss": 0.0034, "lr": 1.9242076698876854e-05, "epoch": 12.331683168316832, "percentage": 61.66, "elapsed_time": "4:25:22", "remaining_time": "2:45:01", "throughput": 1485.75, "total_tokens": 23656512} {"current_steps": 112100, "total_steps": 181800, "loss": 0.0053, "lr": 1.9239741181894556e-05, "epoch": 12.332233223322332, "percentage": 61.66, "elapsed_time": "4:25:22", "remaining_time": "2:45:00", "throughput": 1485.76, "total_tokens": 23657632} {"current_steps": 112105, "total_steps": 181800, "loss": 0.0839, "lr": 1.9237405718001806e-05, "epoch": 12.332783278327833, "percentage": 61.66, "elapsed_time": "4:25:23", "remaining_time": "2:44:59", "throughput": 1485.76, "total_tokens": 23658656} {"current_steps": 112110, "total_steps": 181800, "loss": 0.0134, "lr": 1.9235070307220117e-05, "epoch": 12.333333333333334, "percentage": 61.67, "elapsed_time": "4:25:24", "remaining_time": "2:44:58", "throughput": 1485.76, "total_tokens": 23659712} {"current_steps": 112115, "total_steps": 181800, "loss": 0.003, "lr": 1.923273494957101e-05, "epoch": 12.333883388338833, "percentage": 61.67, "elapsed_time": "4:25:25", "remaining_time": "2:44:58", "throughput": 1485.76, "total_tokens": 23660768} {"current_steps": 112120, "total_steps": 181800, "loss": 0.0038, "lr": 1.9230399645076036e-05, "epoch": 12.334433443344334, "percentage": 61.67, "elapsed_time": "4:25:25", "remaining_time": "2:44:57", "throughput": 1485.77, "total_tokens": 23661888} {"current_steps": 112125, "total_steps": 181800, "loss": 0.0053, "lr": 1.9228064393756677e-05, "epoch": 12.334983498349835, "percentage": 61.67, "elapsed_time": "4:25:26", "remaining_time": "2:44:56", "throughput": 1485.76, "total_tokens": 23662880} {"current_steps": 112130, "total_steps": 181800, "loss": 0.0045, "lr": 1.92257291956345e-05, "epoch": 12.335533553355335, "percentage": 61.68, "elapsed_time": "4:25:27", "remaining_time": "2:44:56", "throughput": 1485.77, "total_tokens": 23663936} {"current_steps": 112135, "total_steps": 181800, "loss": 0.0213, "lr": 1.9223394050731e-05, "epoch": 12.336083608360836, "percentage": 61.68, "elapsed_time": "4:25:27", "remaining_time": "2:44:55", "throughput": 1485.77, "total_tokens": 23664992} {"current_steps": 112140, "total_steps": 181800, "loss": 0.0071, "lr": 1.9221058959067698e-05, "epoch": 12.336633663366337, "percentage": 61.68, "elapsed_time": "4:25:28", "remaining_time": "2:44:54", "throughput": 1485.77, "total_tokens": 23666016} {"current_steps": 112145, "total_steps": 181800, "loss": 0.0545, "lr": 1.9218723920666134e-05, "epoch": 12.337183718371838, "percentage": 61.69, "elapsed_time": "4:25:29", "remaining_time": "2:44:53", "throughput": 1485.77, "total_tokens": 23667072} {"current_steps": 112150, "total_steps": 181800, "loss": 0.0105, "lr": 1.9216388935547807e-05, "epoch": 12.337733773377337, "percentage": 61.69, "elapsed_time": "4:25:29", "remaining_time": "2:44:53", "throughput": 1485.77, "total_tokens": 23668192} {"current_steps": 112155, "total_steps": 181800, "loss": 0.0122, "lr": 1.9214054003734254e-05, "epoch": 12.338283828382838, "percentage": 61.69, "elapsed_time": "4:25:30", "remaining_time": "2:44:52", "throughput": 1485.78, "total_tokens": 23669248} {"current_steps": 112160, "total_steps": 181800, "loss": 0.0126, "lr": 1.921171912524699e-05, "epoch": 12.33883388338834, "percentage": 61.69, "elapsed_time": "4:25:31", "remaining_time": "2:44:51", "throughput": 1485.78, "total_tokens": 23670368} {"current_steps": 112165, "total_steps": 181800, "loss": 0.0019, "lr": 1.9209384300107526e-05, "epoch": 12.339383938393839, "percentage": 61.7, "elapsed_time": "4:25:31", "remaining_time": "2:44:50", "throughput": 1485.78, "total_tokens": 23671424} {"current_steps": 112170, "total_steps": 181800, "loss": 0.0082, "lr": 1.9207049528337395e-05, "epoch": 12.33993399339934, "percentage": 61.7, "elapsed_time": "4:25:32", "remaining_time": "2:44:50", "throughput": 1485.79, "total_tokens": 23672512} {"current_steps": 112175, "total_steps": 181800, "loss": 0.1133, "lr": 1.9204714809958113e-05, "epoch": 12.340484048404841, "percentage": 61.7, "elapsed_time": "4:25:33", "remaining_time": "2:44:49", "throughput": 1485.79, "total_tokens": 23673504} {"current_steps": 112180, "total_steps": 181800, "loss": 0.0017, "lr": 1.9202380144991183e-05, "epoch": 12.34103410341034, "percentage": 61.71, "elapsed_time": "4:25:34", "remaining_time": "2:44:48", "throughput": 1485.77, "total_tokens": 23674560} {"current_steps": 112185, "total_steps": 181800, "loss": 0.0019, "lr": 1.9200045533458137e-05, "epoch": 12.341584158415841, "percentage": 61.71, "elapsed_time": "4:25:34", "remaining_time": "2:44:48", "throughput": 1485.77, "total_tokens": 23675552} {"current_steps": 112190, "total_steps": 181800, "loss": 0.0023, "lr": 1.9197710975380487e-05, "epoch": 12.342134213421343, "percentage": 61.71, "elapsed_time": "4:25:35", "remaining_time": "2:44:47", "throughput": 1485.77, "total_tokens": 23676608} {"current_steps": 112195, "total_steps": 181800, "loss": 0.0027, "lr": 1.9195376470779754e-05, "epoch": 12.342684268426842, "percentage": 61.71, "elapsed_time": "4:25:36", "remaining_time": "2:44:46", "throughput": 1485.77, "total_tokens": 23677696} {"current_steps": 112200, "total_steps": 181800, "loss": 0.0022, "lr": 1.9193042019677455e-05, "epoch": 12.343234323432343, "percentage": 61.72, "elapsed_time": "4:25:36", "remaining_time": "2:44:46", "throughput": 1485.78, "total_tokens": 23678752} {"current_steps": 112205, "total_steps": 181800, "loss": 0.1247, "lr": 1.919070762209509e-05, "epoch": 12.343784378437844, "percentage": 61.72, "elapsed_time": "4:25:37", "remaining_time": "2:44:45", "throughput": 1485.78, "total_tokens": 23679808} {"current_steps": 112210, "total_steps": 181800, "loss": 0.0361, "lr": 1.918837327805419e-05, "epoch": 12.344334433443345, "percentage": 61.72, "elapsed_time": "4:25:38", "remaining_time": "2:44:44", "throughput": 1485.78, "total_tokens": 23680800} {"current_steps": 112215, "total_steps": 181800, "loss": 0.0166, "lr": 1.9186038987576262e-05, "epoch": 12.344884488448844, "percentage": 61.72, "elapsed_time": "4:25:39", "remaining_time": "2:44:43", "throughput": 1485.78, "total_tokens": 23681888} {"current_steps": 112220, "total_steps": 181800, "loss": 0.0097, "lr": 1.9183704750682833e-05, "epoch": 12.345434543454346, "percentage": 61.73, "elapsed_time": "4:25:39", "remaining_time": "2:44:43", "throughput": 1485.78, "total_tokens": 23682912} {"current_steps": 112225, "total_steps": 181800, "loss": 0.117, "lr": 1.91813705673954e-05, "epoch": 12.345984598459847, "percentage": 61.73, "elapsed_time": "4:25:40", "remaining_time": "2:44:42", "throughput": 1485.78, "total_tokens": 23683936} {"current_steps": 112230, "total_steps": 181800, "loss": 0.0205, "lr": 1.917903643773548e-05, "epoch": 12.346534653465346, "percentage": 61.73, "elapsed_time": "4:25:41", "remaining_time": "2:44:41", "throughput": 1485.78, "total_tokens": 23684960} {"current_steps": 112235, "total_steps": 181800, "loss": 0.0154, "lr": 1.9176702361724594e-05, "epoch": 12.347084708470847, "percentage": 61.74, "elapsed_time": "4:25:41", "remaining_time": "2:44:40", "throughput": 1485.78, "total_tokens": 23686016} {"current_steps": 112240, "total_steps": 181800, "loss": 0.0059, "lr": 1.917436833938424e-05, "epoch": 12.347634763476348, "percentage": 61.74, "elapsed_time": "4:25:42", "remaining_time": "2:44:40", "throughput": 1485.78, "total_tokens": 23687040} {"current_steps": 112245, "total_steps": 181800, "loss": 0.0019, "lr": 1.917203437073594e-05, "epoch": 12.348184818481847, "percentage": 61.74, "elapsed_time": "4:25:43", "remaining_time": "2:44:39", "throughput": 1485.78, "total_tokens": 23688064} {"current_steps": 112250, "total_steps": 181800, "loss": 0.0073, "lr": 1.916970045580121e-05, "epoch": 12.348734873487349, "percentage": 61.74, "elapsed_time": "4:25:43", "remaining_time": "2:44:38", "throughput": 1485.78, "total_tokens": 23689120} {"current_steps": 112255, "total_steps": 181800, "loss": 0.1209, "lr": 1.916736659460154e-05, "epoch": 12.34928492849285, "percentage": 61.75, "elapsed_time": "4:25:44", "remaining_time": "2:44:38", "throughput": 1485.78, "total_tokens": 23690112} {"current_steps": 112260, "total_steps": 181800, "loss": 0.0012, "lr": 1.916503278715847e-05, "epoch": 12.34983498349835, "percentage": 61.75, "elapsed_time": "4:25:45", "remaining_time": "2:44:37", "throughput": 1485.78, "total_tokens": 23691200} {"current_steps": 112265, "total_steps": 181800, "loss": 0.0436, "lr": 1.9162699033493478e-05, "epoch": 12.35038503850385, "percentage": 61.75, "elapsed_time": "4:25:45", "remaining_time": "2:44:36", "throughput": 1485.79, "total_tokens": 23692256} {"current_steps": 112270, "total_steps": 181800, "loss": 0.0088, "lr": 1.9160365333628095e-05, "epoch": 12.350935093509351, "percentage": 61.75, "elapsed_time": "4:25:46", "remaining_time": "2:44:35", "throughput": 1485.78, "total_tokens": 23693216} {"current_steps": 112275, "total_steps": 181800, "loss": 0.0466, "lr": 1.9158031687583826e-05, "epoch": 12.351485148514852, "percentage": 61.76, "elapsed_time": "4:25:47", "remaining_time": "2:44:35", "throughput": 1485.79, "total_tokens": 23694304} {"current_steps": 112280, "total_steps": 181800, "loss": 0.0093, "lr": 1.915569809538217e-05, "epoch": 12.352035203520352, "percentage": 61.76, "elapsed_time": "4:25:48", "remaining_time": "2:44:34", "throughput": 1485.79, "total_tokens": 23695328} {"current_steps": 112285, "total_steps": 181800, "loss": 0.0159, "lr": 1.9153364557044638e-05, "epoch": 12.352585258525853, "percentage": 61.76, "elapsed_time": "4:25:48", "remaining_time": "2:44:33", "throughput": 1485.79, "total_tokens": 23696352} {"current_steps": 112290, "total_steps": 181800, "loss": 0.069, "lr": 1.915103107259274e-05, "epoch": 12.353135313531354, "percentage": 61.77, "elapsed_time": "4:25:49", "remaining_time": "2:44:33", "throughput": 1485.79, "total_tokens": 23697408} {"current_steps": 112295, "total_steps": 181800, "loss": 0.0064, "lr": 1.9148697642047993e-05, "epoch": 12.353685368536853, "percentage": 61.77, "elapsed_time": "4:25:50", "remaining_time": "2:44:32", "throughput": 1485.79, "total_tokens": 23698400} {"current_steps": 112300, "total_steps": 181800, "loss": 0.0659, "lr": 1.9146364265431884e-05, "epoch": 12.354235423542354, "percentage": 61.77, "elapsed_time": "4:25:50", "remaining_time": "2:44:31", "throughput": 1485.79, "total_tokens": 23699456} {"current_steps": 112305, "total_steps": 181800, "loss": 0.0892, "lr": 1.9144030942765923e-05, "epoch": 12.354785478547855, "percentage": 61.77, "elapsed_time": "4:25:51", "remaining_time": "2:44:30", "throughput": 1485.78, "total_tokens": 23700416} {"current_steps": 112310, "total_steps": 181800, "loss": 0.0353, "lr": 1.9141697674071623e-05, "epoch": 12.355335533553355, "percentage": 61.78, "elapsed_time": "4:25:52", "remaining_time": "2:44:30", "throughput": 1485.79, "total_tokens": 23701504} {"current_steps": 112315, "total_steps": 181800, "loss": 0.0262, "lr": 1.913936445937048e-05, "epoch": 12.355885588558856, "percentage": 61.78, "elapsed_time": "4:25:52", "remaining_time": "2:44:29", "throughput": 1485.79, "total_tokens": 23702592} {"current_steps": 112320, "total_steps": 181800, "loss": 0.0036, "lr": 1.9137031298684012e-05, "epoch": 12.356435643564357, "percentage": 61.78, "elapsed_time": "4:25:53", "remaining_time": "2:44:28", "throughput": 1485.79, "total_tokens": 23703648} {"current_steps": 112325, "total_steps": 181800, "loss": 0.0283, "lr": 1.913469819203371e-05, "epoch": 12.356985698569858, "percentage": 61.78, "elapsed_time": "4:25:54", "remaining_time": "2:44:27", "throughput": 1485.8, "total_tokens": 23704768} {"current_steps": 112330, "total_steps": 181800, "loss": 0.0495, "lr": 1.9132365139441072e-05, "epoch": 12.357535753575357, "percentage": 61.79, "elapsed_time": "4:25:54", "remaining_time": "2:44:27", "throughput": 1485.8, "total_tokens": 23705760} {"current_steps": 112335, "total_steps": 181800, "loss": 0.0285, "lr": 1.9130032140927623e-05, "epoch": 12.358085808580858, "percentage": 61.79, "elapsed_time": "4:25:55", "remaining_time": "2:44:26", "throughput": 1485.81, "total_tokens": 23706912} {"current_steps": 112340, "total_steps": 181800, "loss": 0.0021, "lr": 1.9127699196514836e-05, "epoch": 12.35863586358636, "percentage": 61.79, "elapsed_time": "4:25:56", "remaining_time": "2:44:25", "throughput": 1485.81, "total_tokens": 23708000} {"current_steps": 112345, "total_steps": 181800, "loss": 0.0012, "lr": 1.912536630622424e-05, "epoch": 12.359185918591859, "percentage": 61.8, "elapsed_time": "4:25:56", "remaining_time": "2:44:25", "throughput": 1485.81, "total_tokens": 23709024} {"current_steps": 112350, "total_steps": 181800, "loss": 0.0078, "lr": 1.9123033470077322e-05, "epoch": 12.35973597359736, "percentage": 61.8, "elapsed_time": "4:25:57", "remaining_time": "2:44:24", "throughput": 1485.81, "total_tokens": 23710048} {"current_steps": 112355, "total_steps": 181800, "loss": 0.0045, "lr": 1.9120700688095578e-05, "epoch": 12.36028602860286, "percentage": 61.8, "elapsed_time": "4:25:58", "remaining_time": "2:44:23", "throughput": 1485.82, "total_tokens": 23711200} {"current_steps": 112360, "total_steps": 181800, "loss": 0.005, "lr": 1.9118367960300517e-05, "epoch": 12.36083608360836, "percentage": 61.8, "elapsed_time": "4:25:59", "remaining_time": "2:44:22", "throughput": 1485.82, "total_tokens": 23712224} {"current_steps": 112365, "total_steps": 181800, "loss": 0.0024, "lr": 1.9116035286713643e-05, "epoch": 12.361386138613861, "percentage": 61.81, "elapsed_time": "4:25:59", "remaining_time": "2:44:22", "throughput": 1485.82, "total_tokens": 23713280} {"current_steps": 112370, "total_steps": 181800, "loss": 0.1458, "lr": 1.911370266735643e-05, "epoch": 12.361936193619362, "percentage": 61.81, "elapsed_time": "4:26:00", "remaining_time": "2:44:21", "throughput": 1485.82, "total_tokens": 23714336} {"current_steps": 112375, "total_steps": 181800, "loss": 0.0134, "lr": 1.911137010225042e-05, "epoch": 12.362486248624862, "percentage": 61.81, "elapsed_time": "4:26:01", "remaining_time": "2:44:20", "throughput": 1485.83, "total_tokens": 23715456} {"current_steps": 112380, "total_steps": 181800, "loss": 0.0061, "lr": 1.9109037591417063e-05, "epoch": 12.363036303630363, "percentage": 61.82, "elapsed_time": "4:26:01", "remaining_time": "2:44:20", "throughput": 1485.83, "total_tokens": 23716576} {"current_steps": 112385, "total_steps": 181800, "loss": 0.0287, "lr": 1.9106705134877896e-05, "epoch": 12.363586358635864, "percentage": 61.82, "elapsed_time": "4:26:02", "remaining_time": "2:44:19", "throughput": 1485.83, "total_tokens": 23717600} {"current_steps": 112390, "total_steps": 181800, "loss": 0.0963, "lr": 1.9104372732654395e-05, "epoch": 12.364136413641365, "percentage": 61.82, "elapsed_time": "4:26:03", "remaining_time": "2:44:18", "throughput": 1485.84, "total_tokens": 23718688} {"current_steps": 112395, "total_steps": 181800, "loss": 0.0108, "lr": 1.9102040384768057e-05, "epoch": 12.364686468646864, "percentage": 61.82, "elapsed_time": "4:26:03", "remaining_time": "2:44:17", "throughput": 1485.83, "total_tokens": 23719680} {"current_steps": 112400, "total_steps": 181800, "loss": 0.0023, "lr": 1.909970809124039e-05, "epoch": 12.365236523652365, "percentage": 61.83, "elapsed_time": "4:26:04", "remaining_time": "2:44:17", "throughput": 1485.84, "total_tokens": 23720768} {"current_steps": 112405, "total_steps": 181800, "loss": 0.0718, "lr": 1.909737585209287e-05, "epoch": 12.365786578657866, "percentage": 61.83, "elapsed_time": "4:26:05", "remaining_time": "2:44:16", "throughput": 1485.84, "total_tokens": 23721824} {"current_steps": 112410, "total_steps": 181800, "loss": 0.0034, "lr": 1.9095043667347024e-05, "epoch": 12.366336633663366, "percentage": 61.83, "elapsed_time": "4:26:05", "remaining_time": "2:44:15", "throughput": 1485.84, "total_tokens": 23722912} {"current_steps": 112415, "total_steps": 181800, "loss": 0.027, "lr": 1.9092711537024317e-05, "epoch": 12.366886688668867, "percentage": 61.83, "elapsed_time": "4:26:06", "remaining_time": "2:44:14", "throughput": 1485.85, "total_tokens": 23724000} {"current_steps": 112420, "total_steps": 181800, "loss": 0.1493, "lr": 1.9090379461146246e-05, "epoch": 12.367436743674368, "percentage": 61.84, "elapsed_time": "4:26:07", "remaining_time": "2:44:14", "throughput": 1485.85, "total_tokens": 23724992} {"current_steps": 112425, "total_steps": 181800, "loss": 0.0016, "lr": 1.9088047439734325e-05, "epoch": 12.367986798679867, "percentage": 61.84, "elapsed_time": "4:26:08", "remaining_time": "2:44:13", "throughput": 1485.85, "total_tokens": 23726048} {"current_steps": 112430, "total_steps": 181800, "loss": 0.0025, "lr": 1.9085715472810017e-05, "epoch": 12.368536853685368, "percentage": 61.84, "elapsed_time": "4:26:08", "remaining_time": "2:44:12", "throughput": 1485.85, "total_tokens": 23727072} {"current_steps": 112435, "total_steps": 181800, "loss": 0.0896, "lr": 1.9083383560394848e-05, "epoch": 12.36908690869087, "percentage": 61.85, "elapsed_time": "4:26:09", "remaining_time": "2:44:12", "throughput": 1485.85, "total_tokens": 23728096} {"current_steps": 112440, "total_steps": 181800, "loss": 0.033, "lr": 1.9081051702510287e-05, "epoch": 12.369636963696369, "percentage": 61.85, "elapsed_time": "4:26:10", "remaining_time": "2:44:11", "throughput": 1485.85, "total_tokens": 23729120} {"current_steps": 112445, "total_steps": 181800, "loss": 0.0015, "lr": 1.9078719899177826e-05, "epoch": 12.37018701870187, "percentage": 61.85, "elapsed_time": "4:26:10", "remaining_time": "2:44:10", "throughput": 1485.85, "total_tokens": 23730208} {"current_steps": 112450, "total_steps": 181800, "loss": 0.0057, "lr": 1.9076388150418977e-05, "epoch": 12.370737073707371, "percentage": 61.85, "elapsed_time": "4:26:11", "remaining_time": "2:44:09", "throughput": 1485.85, "total_tokens": 23731232} {"current_steps": 112455, "total_steps": 181800, "loss": 0.0065, "lr": 1.9074056456255202e-05, "epoch": 12.371287128712872, "percentage": 61.86, "elapsed_time": "4:26:12", "remaining_time": "2:44:09", "throughput": 1485.85, "total_tokens": 23732256} {"current_steps": 112460, "total_steps": 181800, "loss": 0.0024, "lr": 1.907172481670801e-05, "epoch": 12.371837183718371, "percentage": 61.86, "elapsed_time": "4:26:12", "remaining_time": "2:44:08", "throughput": 1485.86, "total_tokens": 23733344} {"current_steps": 112465, "total_steps": 181800, "loss": 0.0009, "lr": 1.9069393231798896e-05, "epoch": 12.372387238723872, "percentage": 61.86, "elapsed_time": "4:26:13", "remaining_time": "2:44:07", "throughput": 1485.86, "total_tokens": 23734432} {"current_steps": 112470, "total_steps": 181800, "loss": 0.0032, "lr": 1.9067061701549325e-05, "epoch": 12.372937293729374, "percentage": 61.86, "elapsed_time": "4:26:14", "remaining_time": "2:44:07", "throughput": 1485.86, "total_tokens": 23735488} {"current_steps": 112475, "total_steps": 181800, "loss": 0.0027, "lr": 1.9064730225980804e-05, "epoch": 12.373487348734873, "percentage": 61.87, "elapsed_time": "4:26:14", "remaining_time": "2:44:06", "throughput": 1485.86, "total_tokens": 23736480} {"current_steps": 112480, "total_steps": 181800, "loss": 0.0692, "lr": 1.906239880511481e-05, "epoch": 12.374037403740374, "percentage": 61.87, "elapsed_time": "4:26:15", "remaining_time": "2:44:05", "throughput": 1485.86, "total_tokens": 23737568} {"current_steps": 112485, "total_steps": 181800, "loss": 0.0539, "lr": 1.906006743897285e-05, "epoch": 12.374587458745875, "percentage": 61.87, "elapsed_time": "4:26:16", "remaining_time": "2:44:04", "throughput": 1485.87, "total_tokens": 23738624} {"current_steps": 112490, "total_steps": 181800, "loss": 0.0074, "lr": 1.9057736127576393e-05, "epoch": 12.375137513751374, "percentage": 61.88, "elapsed_time": "4:26:16", "remaining_time": "2:44:04", "throughput": 1485.87, "total_tokens": 23739648} {"current_steps": 112495, "total_steps": 181800, "loss": 0.0036, "lr": 1.9055404870946925e-05, "epoch": 12.375687568756875, "percentage": 61.88, "elapsed_time": "4:26:17", "remaining_time": "2:44:03", "throughput": 1485.87, "total_tokens": 23740672} {"current_steps": 112500, "total_steps": 181800, "loss": 0.0666, "lr": 1.9053073669105943e-05, "epoch": 12.376237623762377, "percentage": 61.88, "elapsed_time": "4:26:18", "remaining_time": "2:44:02", "throughput": 1485.87, "total_tokens": 23741760} {"current_steps": 112505, "total_steps": 181800, "loss": 0.0048, "lr": 1.9050742522074922e-05, "epoch": 12.376787678767876, "percentage": 61.88, "elapsed_time": "4:26:19", "remaining_time": "2:44:01", "throughput": 1485.87, "total_tokens": 23742816} {"current_steps": 112510, "total_steps": 181800, "loss": 0.0066, "lr": 1.9048411429875362e-05, "epoch": 12.377337733773377, "percentage": 61.89, "elapsed_time": "4:26:19", "remaining_time": "2:44:01", "throughput": 1485.87, "total_tokens": 23743872} {"current_steps": 112515, "total_steps": 181800, "loss": 0.0004, "lr": 1.9046080392528735e-05, "epoch": 12.377887788778878, "percentage": 61.89, "elapsed_time": "4:26:20", "remaining_time": "2:44:00", "throughput": 1485.87, "total_tokens": 23744896} {"current_steps": 112520, "total_steps": 181800, "loss": 0.0267, "lr": 1.9043749410056523e-05, "epoch": 12.37843784378438, "percentage": 61.89, "elapsed_time": "4:26:21", "remaining_time": "2:43:59", "throughput": 1485.87, "total_tokens": 23745920} {"current_steps": 112525, "total_steps": 181800, "loss": 0.032, "lr": 1.9041418482480222e-05, "epoch": 12.378987898789878, "percentage": 61.89, "elapsed_time": "4:26:21", "remaining_time": "2:43:59", "throughput": 1485.88, "total_tokens": 23747008} {"current_steps": 112530, "total_steps": 181800, "loss": 0.0556, "lr": 1.90390876098213e-05, "epoch": 12.37953795379538, "percentage": 61.9, "elapsed_time": "4:26:22", "remaining_time": "2:43:58", "throughput": 1485.88, "total_tokens": 23748128} {"current_steps": 112535, "total_steps": 181800, "loss": 0.0753, "lr": 1.9036756792101248e-05, "epoch": 12.38008800880088, "percentage": 61.9, "elapsed_time": "4:26:23", "remaining_time": "2:43:57", "throughput": 1485.89, "total_tokens": 23749248} {"current_steps": 112540, "total_steps": 181800, "loss": 0.0458, "lr": 1.9034426029341556e-05, "epoch": 12.38063806380638, "percentage": 61.9, "elapsed_time": "4:26:23", "remaining_time": "2:43:56", "throughput": 1485.89, "total_tokens": 23750336} {"current_steps": 112545, "total_steps": 181800, "loss": 0.0513, "lr": 1.903209532156368e-05, "epoch": 12.381188118811881, "percentage": 61.91, "elapsed_time": "4:26:24", "remaining_time": "2:43:56", "throughput": 1485.9, "total_tokens": 23751392} {"current_steps": 112550, "total_steps": 181800, "loss": 0.0081, "lr": 1.9029764668789134e-05, "epoch": 12.381738173817382, "percentage": 61.91, "elapsed_time": "4:26:25", "remaining_time": "2:43:55", "throughput": 1485.9, "total_tokens": 23752416} {"current_steps": 112555, "total_steps": 181800, "loss": 0.0012, "lr": 1.902743407103938e-05, "epoch": 12.382288228822881, "percentage": 61.91, "elapsed_time": "4:26:25", "remaining_time": "2:43:54", "throughput": 1485.89, "total_tokens": 23753408} {"current_steps": 112560, "total_steps": 181800, "loss": 0.0538, "lr": 1.9025103528335893e-05, "epoch": 12.382838283828383, "percentage": 61.91, "elapsed_time": "4:26:26", "remaining_time": "2:43:53", "throughput": 1485.89, "total_tokens": 23754400} {"current_steps": 112565, "total_steps": 181800, "loss": 0.0154, "lr": 1.9022773040700167e-05, "epoch": 12.383388338833884, "percentage": 61.92, "elapsed_time": "4:26:27", "remaining_time": "2:43:53", "throughput": 1485.89, "total_tokens": 23755456} {"current_steps": 112570, "total_steps": 181800, "loss": 0.0115, "lr": 1.9020442608153664e-05, "epoch": 12.383938393839385, "percentage": 61.92, "elapsed_time": "4:26:28", "remaining_time": "2:43:52", "throughput": 1485.89, "total_tokens": 23756448} {"current_steps": 112575, "total_steps": 181800, "loss": 0.0043, "lr": 1.901811223071788e-05, "epoch": 12.384488448844884, "percentage": 61.92, "elapsed_time": "4:26:28", "remaining_time": "2:43:51", "throughput": 1485.89, "total_tokens": 23757504} {"current_steps": 112580, "total_steps": 181800, "loss": 0.0034, "lr": 1.901578190841429e-05, "epoch": 12.385038503850385, "percentage": 61.93, "elapsed_time": "4:26:29", "remaining_time": "2:43:51", "throughput": 1485.89, "total_tokens": 23758528} {"current_steps": 112585, "total_steps": 181800, "loss": 0.0137, "lr": 1.9013451641264354e-05, "epoch": 12.385588558855886, "percentage": 61.93, "elapsed_time": "4:26:30", "remaining_time": "2:43:50", "throughput": 1485.9, "total_tokens": 23759648} {"current_steps": 112590, "total_steps": 181800, "loss": 0.0261, "lr": 1.9011121429289568e-05, "epoch": 12.386138613861386, "percentage": 61.93, "elapsed_time": "4:26:30", "remaining_time": "2:43:49", "throughput": 1485.9, "total_tokens": 23760768} {"current_steps": 112595, "total_steps": 181800, "loss": 0.0106, "lr": 1.90087912725114e-05, "epoch": 12.386688668866887, "percentage": 61.93, "elapsed_time": "4:26:31", "remaining_time": "2:43:48", "throughput": 1485.91, "total_tokens": 23761856} {"current_steps": 112600, "total_steps": 181800, "loss": 0.0988, "lr": 1.9006461170951335e-05, "epoch": 12.387238723872388, "percentage": 61.94, "elapsed_time": "4:26:32", "remaining_time": "2:43:48", "throughput": 1485.91, "total_tokens": 23762912} {"current_steps": 112605, "total_steps": 181800, "loss": 0.0074, "lr": 1.9004131124630837e-05, "epoch": 12.387788778877887, "percentage": 61.94, "elapsed_time": "4:26:32", "remaining_time": "2:43:47", "throughput": 1485.91, "total_tokens": 23764000} {"current_steps": 112610, "total_steps": 181800, "loss": 0.0158, "lr": 1.9001801133571378e-05, "epoch": 12.388338833883388, "percentage": 61.94, "elapsed_time": "4:26:33", "remaining_time": "2:43:46", "throughput": 1485.92, "total_tokens": 23765088} {"current_steps": 112615, "total_steps": 181800, "loss": 0.0208, "lr": 1.899947119779445e-05, "epoch": 12.38888888888889, "percentage": 61.94, "elapsed_time": "4:26:34", "remaining_time": "2:43:46", "throughput": 1485.92, "total_tokens": 23766144} {"current_steps": 112620, "total_steps": 181800, "loss": 0.0075, "lr": 1.8997141317321507e-05, "epoch": 12.389438943894389, "percentage": 61.95, "elapsed_time": "4:26:34", "remaining_time": "2:43:45", "throughput": 1485.92, "total_tokens": 23767200} {"current_steps": 112625, "total_steps": 181800, "loss": 0.0029, "lr": 1.8994811492174044e-05, "epoch": 12.38998899889989, "percentage": 61.95, "elapsed_time": "4:26:35", "remaining_time": "2:43:44", "throughput": 1485.92, "total_tokens": 23768256} {"current_steps": 112630, "total_steps": 181800, "loss": 0.0038, "lr": 1.899248172237352e-05, "epoch": 12.39053905390539, "percentage": 61.95, "elapsed_time": "4:26:36", "remaining_time": "2:43:43", "throughput": 1485.93, "total_tokens": 23769312} {"current_steps": 112635, "total_steps": 181800, "loss": 0.0032, "lr": 1.8990152007941397e-05, "epoch": 12.391089108910892, "percentage": 61.96, "elapsed_time": "4:26:36", "remaining_time": "2:43:43", "throughput": 1485.93, "total_tokens": 23770400} {"current_steps": 112640, "total_steps": 181800, "loss": 0.1765, "lr": 1.8987822348899174e-05, "epoch": 12.391639163916391, "percentage": 61.96, "elapsed_time": "4:26:37", "remaining_time": "2:43:42", "throughput": 1485.93, "total_tokens": 23771424} {"current_steps": 112645, "total_steps": 181800, "loss": 0.0061, "lr": 1.8985492745268296e-05, "epoch": 12.392189218921892, "percentage": 61.96, "elapsed_time": "4:26:38", "remaining_time": "2:43:41", "throughput": 1485.93, "total_tokens": 23772512} {"current_steps": 112650, "total_steps": 181800, "loss": 0.0015, "lr": 1.898316319707025e-05, "epoch": 12.392739273927393, "percentage": 61.96, "elapsed_time": "4:26:39", "remaining_time": "2:43:40", "throughput": 1485.94, "total_tokens": 23773568} {"current_steps": 112655, "total_steps": 181800, "loss": 0.0381, "lr": 1.8980833704326507e-05, "epoch": 12.393289328932893, "percentage": 61.97, "elapsed_time": "4:26:39", "remaining_time": "2:43:40", "throughput": 1485.94, "total_tokens": 23774592} {"current_steps": 112660, "total_steps": 181800, "loss": 0.0057, "lr": 1.8978504267058523e-05, "epoch": 12.393839383938394, "percentage": 61.97, "elapsed_time": "4:26:40", "remaining_time": "2:43:39", "throughput": 1485.94, "total_tokens": 23775616} {"current_steps": 112665, "total_steps": 181800, "loss": 0.0183, "lr": 1.897617488528778e-05, "epoch": 12.394389438943895, "percentage": 61.97, "elapsed_time": "4:26:41", "remaining_time": "2:43:38", "throughput": 1485.94, "total_tokens": 23776672} {"current_steps": 112670, "total_steps": 181800, "loss": 0.0032, "lr": 1.8973845559035736e-05, "epoch": 12.394939493949394, "percentage": 61.97, "elapsed_time": "4:26:41", "remaining_time": "2:43:38", "throughput": 1485.94, "total_tokens": 23777760} {"current_steps": 112675, "total_steps": 181800, "loss": 0.1575, "lr": 1.897151628832387e-05, "epoch": 12.395489548954895, "percentage": 61.98, "elapsed_time": "4:26:42", "remaining_time": "2:43:37", "throughput": 1485.94, "total_tokens": 23778784} {"current_steps": 112680, "total_steps": 181800, "loss": 0.0088, "lr": 1.8969187073173654e-05, "epoch": 12.396039603960396, "percentage": 61.98, "elapsed_time": "4:26:43", "remaining_time": "2:43:36", "throughput": 1485.94, "total_tokens": 23779872} {"current_steps": 112685, "total_steps": 181800, "loss": 0.0741, "lr": 1.8966857913606534e-05, "epoch": 12.396589658965897, "percentage": 61.98, "elapsed_time": "4:26:43", "remaining_time": "2:43:35", "throughput": 1485.95, "total_tokens": 23780960} {"current_steps": 112690, "total_steps": 181800, "loss": 0.0017, "lr": 1.8964528809643996e-05, "epoch": 12.397139713971397, "percentage": 61.99, "elapsed_time": "4:26:44", "remaining_time": "2:43:35", "throughput": 1485.95, "total_tokens": 23781984} {"current_steps": 112695, "total_steps": 181800, "loss": 0.0174, "lr": 1.8962199761307497e-05, "epoch": 12.397689768976898, "percentage": 61.99, "elapsed_time": "4:26:45", "remaining_time": "2:43:34", "throughput": 1485.95, "total_tokens": 23783104} {"current_steps": 112700, "total_steps": 181800, "loss": 0.0102, "lr": 1.8959870768618516e-05, "epoch": 12.398239823982399, "percentage": 61.99, "elapsed_time": "4:26:45", "remaining_time": "2:43:33", "throughput": 1485.96, "total_tokens": 23784192} {"current_steps": 112705, "total_steps": 181800, "loss": 0.0176, "lr": 1.8957541831598497e-05, "epoch": 12.398789878987898, "percentage": 61.99, "elapsed_time": "4:26:46", "remaining_time": "2:43:33", "throughput": 1485.96, "total_tokens": 23785248} {"current_steps": 112710, "total_steps": 181800, "loss": 0.0217, "lr": 1.8955212950268913e-05, "epoch": 12.3993399339934, "percentage": 62.0, "elapsed_time": "4:26:47", "remaining_time": "2:43:32", "throughput": 1485.97, "total_tokens": 23786368} {"current_steps": 112715, "total_steps": 181800, "loss": 0.0758, "lr": 1.8952884124651245e-05, "epoch": 12.3998899889989, "percentage": 62.0, "elapsed_time": "4:26:48", "remaining_time": "2:43:31", "throughput": 1485.97, "total_tokens": 23787392} {"current_steps": 112720, "total_steps": 181800, "loss": 0.188, "lr": 1.8950555354766927e-05, "epoch": 12.4004400440044, "percentage": 62.0, "elapsed_time": "4:26:48", "remaining_time": "2:43:30", "throughput": 1485.97, "total_tokens": 23788416} {"current_steps": 112725, "total_steps": 181800, "loss": 0.0027, "lr": 1.8948226640637446e-05, "epoch": 12.400990099009901, "percentage": 62.0, "elapsed_time": "4:26:49", "remaining_time": "2:43:30", "throughput": 1485.97, "total_tokens": 23789472} {"current_steps": 112730, "total_steps": 181800, "loss": 0.0176, "lr": 1.8945897982284257e-05, "epoch": 12.401540154015402, "percentage": 62.01, "elapsed_time": "4:26:50", "remaining_time": "2:43:29", "throughput": 1485.97, "total_tokens": 23790496} {"current_steps": 112735, "total_steps": 181800, "loss": 0.0007, "lr": 1.894356937972881e-05, "epoch": 12.402090209020901, "percentage": 62.01, "elapsed_time": "4:26:50", "remaining_time": "2:43:28", "throughput": 1485.97, "total_tokens": 23791584} {"current_steps": 112740, "total_steps": 181800, "loss": 0.0108, "lr": 1.894124083299259e-05, "epoch": 12.402640264026402, "percentage": 62.01, "elapsed_time": "4:26:51", "remaining_time": "2:43:27", "throughput": 1485.97, "total_tokens": 23792640} {"current_steps": 112745, "total_steps": 181800, "loss": 0.072, "lr": 1.8938912342097043e-05, "epoch": 12.403190319031903, "percentage": 62.02, "elapsed_time": "4:26:52", "remaining_time": "2:43:27", "throughput": 1485.97, "total_tokens": 23793664} {"current_steps": 112750, "total_steps": 181800, "loss": 0.064, "lr": 1.8936583907063627e-05, "epoch": 12.403740374037405, "percentage": 62.02, "elapsed_time": "4:26:52", "remaining_time": "2:43:26", "throughput": 1485.98, "total_tokens": 23794720} {"current_steps": 112755, "total_steps": 181800, "loss": 0.0072, "lr": 1.893425552791382e-05, "epoch": 12.404290429042904, "percentage": 62.02, "elapsed_time": "4:26:53", "remaining_time": "2:43:25", "throughput": 1485.98, "total_tokens": 23795776} {"current_steps": 112760, "total_steps": 181800, "loss": 0.0093, "lr": 1.8931927204669057e-05, "epoch": 12.404840484048405, "percentage": 62.02, "elapsed_time": "4:26:54", "remaining_time": "2:43:25", "throughput": 1485.98, "total_tokens": 23796864} {"current_steps": 112765, "total_steps": 181800, "loss": 0.0114, "lr": 1.892959893735081e-05, "epoch": 12.405390539053906, "percentage": 62.03, "elapsed_time": "4:26:54", "remaining_time": "2:43:24", "throughput": 1485.98, "total_tokens": 23797888} {"current_steps": 112770, "total_steps": 181800, "loss": 0.0086, "lr": 1.892727072598055e-05, "epoch": 12.405940594059405, "percentage": 62.03, "elapsed_time": "4:26:55", "remaining_time": "2:43:23", "throughput": 1485.98, "total_tokens": 23798944} {"current_steps": 112775, "total_steps": 181800, "loss": 0.0528, "lr": 1.8924942570579707e-05, "epoch": 12.406490649064907, "percentage": 62.03, "elapsed_time": "4:26:56", "remaining_time": "2:43:22", "throughput": 1485.99, "total_tokens": 23800000} {"current_steps": 112780, "total_steps": 181800, "loss": 0.0018, "lr": 1.8922614471169757e-05, "epoch": 12.407040704070408, "percentage": 62.04, "elapsed_time": "4:26:56", "remaining_time": "2:43:22", "throughput": 1485.99, "total_tokens": 23801024} {"current_steps": 112785, "total_steps": 181800, "loss": 0.0014, "lr": 1.8920286427772148e-05, "epoch": 12.407590759075907, "percentage": 62.04, "elapsed_time": "4:26:57", "remaining_time": "2:43:21", "throughput": 1485.99, "total_tokens": 23802112} {"current_steps": 112790, "total_steps": 181800, "loss": 0.0229, "lr": 1.891795844040835e-05, "epoch": 12.408140814081408, "percentage": 62.04, "elapsed_time": "4:26:58", "remaining_time": "2:43:20", "throughput": 1485.99, "total_tokens": 23803168} {"current_steps": 112795, "total_steps": 181800, "loss": 0.0308, "lr": 1.8915630509099816e-05, "epoch": 12.408690869086909, "percentage": 62.04, "elapsed_time": "4:26:59", "remaining_time": "2:43:20", "throughput": 1485.99, "total_tokens": 23804224} {"current_steps": 112800, "total_steps": 181800, "loss": 0.0044, "lr": 1.8913302633867985e-05, "epoch": 12.409240924092408, "percentage": 62.05, "elapsed_time": "4:26:59", "remaining_time": "2:43:19", "throughput": 1485.99, "total_tokens": 23805216} {"current_steps": 112805, "total_steps": 181800, "loss": 0.0028, "lr": 1.891097481473433e-05, "epoch": 12.40979097909791, "percentage": 62.05, "elapsed_time": "4:27:00", "remaining_time": "2:43:18", "throughput": 1485.99, "total_tokens": 23806208} {"current_steps": 112810, "total_steps": 181800, "loss": 0.007, "lr": 1.8908647051720285e-05, "epoch": 12.41034103410341, "percentage": 62.05, "elapsed_time": "4:27:01", "remaining_time": "2:43:17", "throughput": 1485.99, "total_tokens": 23807200} {"current_steps": 112815, "total_steps": 181800, "loss": 0.0057, "lr": 1.8906319344847334e-05, "epoch": 12.410891089108912, "percentage": 62.05, "elapsed_time": "4:27:01", "remaining_time": "2:43:17", "throughput": 1485.99, "total_tokens": 23808288} {"current_steps": 112820, "total_steps": 181800, "loss": 0.0027, "lr": 1.8903991694136906e-05, "epoch": 12.411441144114411, "percentage": 62.06, "elapsed_time": "4:27:02", "remaining_time": "2:43:16", "throughput": 1485.99, "total_tokens": 23809344} {"current_steps": 112825, "total_steps": 181800, "loss": 0.0057, "lr": 1.8901664099610462e-05, "epoch": 12.411991199119912, "percentage": 62.06, "elapsed_time": "4:27:03", "remaining_time": "2:43:15", "throughput": 1486.0, "total_tokens": 23810432} {"current_steps": 112830, "total_steps": 181800, "loss": 0.0131, "lr": 1.8899336561289458e-05, "epoch": 12.412541254125413, "percentage": 62.06, "elapsed_time": "4:27:03", "remaining_time": "2:43:14", "throughput": 1486.0, "total_tokens": 23811488} {"current_steps": 112835, "total_steps": 181800, "loss": 0.0328, "lr": 1.889700907919533e-05, "epoch": 12.413091309130913, "percentage": 62.07, "elapsed_time": "4:27:04", "remaining_time": "2:43:14", "throughput": 1486.0, "total_tokens": 23812544} {"current_steps": 112840, "total_steps": 181800, "loss": 0.0162, "lr": 1.889468165334955e-05, "epoch": 12.413641364136414, "percentage": 62.07, "elapsed_time": "4:27:05", "remaining_time": "2:43:13", "throughput": 1486.01, "total_tokens": 23813632} {"current_steps": 112845, "total_steps": 181800, "loss": 0.0093, "lr": 1.8892354283773567e-05, "epoch": 12.414191419141915, "percentage": 62.07, "elapsed_time": "4:27:05", "remaining_time": "2:43:12", "throughput": 1486.01, "total_tokens": 23814688} {"current_steps": 112850, "total_steps": 181800, "loss": 0.1014, "lr": 1.8890026970488804e-05, "epoch": 12.414741474147414, "percentage": 62.07, "elapsed_time": "4:27:06", "remaining_time": "2:43:12", "throughput": 1486.01, "total_tokens": 23815680} {"current_steps": 112855, "total_steps": 181800, "loss": 0.0011, "lr": 1.8887699713516746e-05, "epoch": 12.415291529152915, "percentage": 62.08, "elapsed_time": "4:27:07", "remaining_time": "2:43:11", "throughput": 1486.01, "total_tokens": 23816736} {"current_steps": 112860, "total_steps": 181800, "loss": 0.0274, "lr": 1.888537251287882e-05, "epoch": 12.415841584158416, "percentage": 62.08, "elapsed_time": "4:27:08", "remaining_time": "2:43:10", "throughput": 1486.01, "total_tokens": 23817792} {"current_steps": 112865, "total_steps": 181800, "loss": 0.0142, "lr": 1.8883045368596482e-05, "epoch": 12.416391639163916, "percentage": 62.08, "elapsed_time": "4:27:08", "remaining_time": "2:43:09", "throughput": 1486.02, "total_tokens": 23818880} {"current_steps": 112870, "total_steps": 181800, "loss": 0.0008, "lr": 1.8880718280691187e-05, "epoch": 12.416941694169417, "percentage": 62.08, "elapsed_time": "4:27:09", "remaining_time": "2:43:09", "throughput": 1486.02, "total_tokens": 23819936} {"current_steps": 112875, "total_steps": 181800, "loss": 0.0736, "lr": 1.887839124918436e-05, "epoch": 12.417491749174918, "percentage": 62.09, "elapsed_time": "4:27:10", "remaining_time": "2:43:08", "throughput": 1486.02, "total_tokens": 23821024} {"current_steps": 112880, "total_steps": 181800, "loss": 0.1484, "lr": 1.887606427409748e-05, "epoch": 12.418041804180419, "percentage": 62.09, "elapsed_time": "4:27:10", "remaining_time": "2:43:07", "throughput": 1486.02, "total_tokens": 23822048} {"current_steps": 112885, "total_steps": 181800, "loss": 0.1117, "lr": 1.8873737355451962e-05, "epoch": 12.418591859185918, "percentage": 62.09, "elapsed_time": "4:27:11", "remaining_time": "2:43:07", "throughput": 1486.02, "total_tokens": 23823072} {"current_steps": 112890, "total_steps": 181800, "loss": 0.0018, "lr": 1.8871410493269282e-05, "epoch": 12.41914191419142, "percentage": 62.1, "elapsed_time": "4:27:12", "remaining_time": "2:43:06", "throughput": 1486.03, "total_tokens": 23824160} {"current_steps": 112895, "total_steps": 181800, "loss": 0.013, "lr": 1.8869083687570866e-05, "epoch": 12.41969196919692, "percentage": 62.1, "elapsed_time": "4:27:12", "remaining_time": "2:43:05", "throughput": 1486.03, "total_tokens": 23825248} {"current_steps": 112900, "total_steps": 181800, "loss": 0.004, "lr": 1.8866756938378156e-05, "epoch": 12.42024202420242, "percentage": 62.1, "elapsed_time": "4:27:13", "remaining_time": "2:43:04", "throughput": 1486.03, "total_tokens": 23826336} {"current_steps": 112905, "total_steps": 181800, "loss": 0.038, "lr": 1.8864430245712617e-05, "epoch": 12.42079207920792, "percentage": 62.1, "elapsed_time": "4:27:14", "remaining_time": "2:43:04", "throughput": 1486.03, "total_tokens": 23827392} {"current_steps": 112910, "total_steps": 181800, "loss": 0.0099, "lr": 1.886210360959566e-05, "epoch": 12.421342134213422, "percentage": 62.11, "elapsed_time": "4:27:14", "remaining_time": "2:43:03", "throughput": 1486.03, "total_tokens": 23828384} {"current_steps": 112915, "total_steps": 181800, "loss": 0.0191, "lr": 1.885977703004877e-05, "epoch": 12.421892189218921, "percentage": 62.11, "elapsed_time": "4:27:15", "remaining_time": "2:43:02", "throughput": 1486.04, "total_tokens": 23829472} {"current_steps": 112920, "total_steps": 181800, "loss": 0.0036, "lr": 1.885745050709336e-05, "epoch": 12.422442244224422, "percentage": 62.11, "elapsed_time": "4:27:16", "remaining_time": "2:43:01", "throughput": 1486.04, "total_tokens": 23830496} {"current_steps": 112925, "total_steps": 181800, "loss": 0.0015, "lr": 1.8855124040750878e-05, "epoch": 12.422992299229923, "percentage": 62.11, "elapsed_time": "4:27:16", "remaining_time": "2:43:01", "throughput": 1486.04, "total_tokens": 23831520} {"current_steps": 112930, "total_steps": 181800, "loss": 0.0017, "lr": 1.885279763104278e-05, "epoch": 12.423542354235423, "percentage": 62.12, "elapsed_time": "4:27:17", "remaining_time": "2:43:00", "throughput": 1486.04, "total_tokens": 23832672} {"current_steps": 112935, "total_steps": 181800, "loss": 0.0043, "lr": 1.8850471277990483e-05, "epoch": 12.424092409240924, "percentage": 62.12, "elapsed_time": "4:27:18", "remaining_time": "2:42:59", "throughput": 1486.05, "total_tokens": 23833728} {"current_steps": 112940, "total_steps": 181800, "loss": 0.0351, "lr": 1.8848144981615448e-05, "epoch": 12.424642464246425, "percentage": 62.12, "elapsed_time": "4:27:19", "remaining_time": "2:42:59", "throughput": 1486.04, "total_tokens": 23834720} {"current_steps": 112945, "total_steps": 181800, "loss": 0.0174, "lr": 1.8845818741939114e-05, "epoch": 12.425192519251926, "percentage": 62.13, "elapsed_time": "4:27:19", "remaining_time": "2:42:58", "throughput": 1486.04, "total_tokens": 23835744} {"current_steps": 112950, "total_steps": 181800, "loss": 0.059, "lr": 1.8843492558982905e-05, "epoch": 12.425742574257425, "percentage": 62.13, "elapsed_time": "4:27:20", "remaining_time": "2:42:57", "throughput": 1486.04, "total_tokens": 23836736} {"current_steps": 112955, "total_steps": 181800, "loss": 0.0056, "lr": 1.8841166432768278e-05, "epoch": 12.426292629262926, "percentage": 62.13, "elapsed_time": "4:27:21", "remaining_time": "2:42:56", "throughput": 1486.04, "total_tokens": 23837792} {"current_steps": 112960, "total_steps": 181800, "loss": 0.1577, "lr": 1.883884036331667e-05, "epoch": 12.426842684268427, "percentage": 62.13, "elapsed_time": "4:27:21", "remaining_time": "2:42:56", "throughput": 1486.04, "total_tokens": 23838816} {"current_steps": 112965, "total_steps": 181800, "loss": 0.064, "lr": 1.8836514350649502e-05, "epoch": 12.427392739273927, "percentage": 62.14, "elapsed_time": "4:27:22", "remaining_time": "2:42:55", "throughput": 1486.04, "total_tokens": 23839840} {"current_steps": 112970, "total_steps": 181800, "loss": 0.0658, "lr": 1.8834188394788227e-05, "epoch": 12.427942794279428, "percentage": 62.14, "elapsed_time": "4:27:23", "remaining_time": "2:42:54", "throughput": 1486.05, "total_tokens": 23840896} {"current_steps": 112975, "total_steps": 181800, "loss": 0.0913, "lr": 1.8831862495754277e-05, "epoch": 12.428492849284929, "percentage": 62.14, "elapsed_time": "4:27:23", "remaining_time": "2:42:54", "throughput": 1486.04, "total_tokens": 23841888} {"current_steps": 112980, "total_steps": 181800, "loss": 0.0017, "lr": 1.8829536653569092e-05, "epoch": 12.429042904290428, "percentage": 62.15, "elapsed_time": "4:27:24", "remaining_time": "2:42:53", "throughput": 1486.05, "total_tokens": 23842944} {"current_steps": 112985, "total_steps": 181800, "loss": 0.0014, "lr": 1.8827210868254117e-05, "epoch": 12.42959295929593, "percentage": 62.15, "elapsed_time": "4:27:25", "remaining_time": "2:42:52", "throughput": 1486.05, "total_tokens": 23844000} {"current_steps": 112990, "total_steps": 181800, "loss": 0.0301, "lr": 1.8824885139830763e-05, "epoch": 12.43014301430143, "percentage": 62.15, "elapsed_time": "4:27:25", "remaining_time": "2:42:51", "throughput": 1486.05, "total_tokens": 23845088} {"current_steps": 112995, "total_steps": 181800, "loss": 0.0413, "lr": 1.8822559468320488e-05, "epoch": 12.430693069306932, "percentage": 62.15, "elapsed_time": "4:27:26", "remaining_time": "2:42:51", "throughput": 1486.05, "total_tokens": 23846176} {"current_steps": 113000, "total_steps": 181800, "loss": 0.0133, "lr": 1.8820233853744708e-05, "epoch": 12.43124312431243, "percentage": 62.16, "elapsed_time": "4:27:27", "remaining_time": "2:42:50", "throughput": 1486.06, "total_tokens": 23847232} {"current_steps": 113005, "total_steps": 181800, "loss": 0.0012, "lr": 1.8817908296124883e-05, "epoch": 12.431793179317932, "percentage": 62.16, "elapsed_time": "4:27:28", "remaining_time": "2:42:49", "throughput": 1486.06, "total_tokens": 23848256} {"current_steps": 113010, "total_steps": 181800, "loss": 0.0562, "lr": 1.881558279548242e-05, "epoch": 12.432343234323433, "percentage": 62.16, "elapsed_time": "4:27:28", "remaining_time": "2:42:48", "throughput": 1486.06, "total_tokens": 23849312} {"current_steps": 113015, "total_steps": 181800, "loss": 0.0139, "lr": 1.8813257351838764e-05, "epoch": 12.432893289328932, "percentage": 62.16, "elapsed_time": "4:27:29", "remaining_time": "2:42:48", "throughput": 1486.06, "total_tokens": 23850336} {"current_steps": 113020, "total_steps": 181800, "loss": 0.0545, "lr": 1.8810931965215356e-05, "epoch": 12.433443344334433, "percentage": 62.17, "elapsed_time": "4:27:30", "remaining_time": "2:42:47", "throughput": 1486.06, "total_tokens": 23851392} {"current_steps": 113025, "total_steps": 181800, "loss": 0.0074, "lr": 1.8808606635633606e-05, "epoch": 12.433993399339935, "percentage": 62.17, "elapsed_time": "4:27:30", "remaining_time": "2:42:46", "throughput": 1486.06, "total_tokens": 23852448} {"current_steps": 113030, "total_steps": 181800, "loss": 0.0353, "lr": 1.8806281363114962e-05, "epoch": 12.434543454345434, "percentage": 62.17, "elapsed_time": "4:27:31", "remaining_time": "2:42:46", "throughput": 1486.07, "total_tokens": 23853600} {"current_steps": 113035, "total_steps": 181800, "loss": 0.0358, "lr": 1.8803956147680853e-05, "epoch": 12.435093509350935, "percentage": 62.18, "elapsed_time": "4:27:32", "remaining_time": "2:42:45", "throughput": 1486.07, "total_tokens": 23854656} {"current_steps": 113040, "total_steps": 181800, "loss": 0.1054, "lr": 1.88016309893527e-05, "epoch": 12.435643564356436, "percentage": 62.18, "elapsed_time": "4:27:32", "remaining_time": "2:42:44", "throughput": 1486.07, "total_tokens": 23855680} {"current_steps": 113045, "total_steps": 181800, "loss": 0.0171, "lr": 1.8799305888151947e-05, "epoch": 12.436193619361935, "percentage": 62.18, "elapsed_time": "4:27:33", "remaining_time": "2:42:43", "throughput": 1486.07, "total_tokens": 23856736} {"current_steps": 113050, "total_steps": 181800, "loss": 0.0568, "lr": 1.879698084410001e-05, "epoch": 12.436743674367436, "percentage": 62.18, "elapsed_time": "4:27:34", "remaining_time": "2:42:43", "throughput": 1486.07, "total_tokens": 23857760} {"current_steps": 113055, "total_steps": 181800, "loss": 0.0545, "lr": 1.879465585721833e-05, "epoch": 12.437293729372938, "percentage": 62.19, "elapsed_time": "4:27:34", "remaining_time": "2:42:42", "throughput": 1486.08, "total_tokens": 23858816} {"current_steps": 113060, "total_steps": 181800, "loss": 0.0039, "lr": 1.8792330927528333e-05, "epoch": 12.437843784378439, "percentage": 62.19, "elapsed_time": "4:27:35", "remaining_time": "2:42:41", "throughput": 1486.07, "total_tokens": 23859808} {"current_steps": 113065, "total_steps": 181800, "loss": 0.0036, "lr": 1.879000605505143e-05, "epoch": 12.438393839383938, "percentage": 62.19, "elapsed_time": "4:27:36", "remaining_time": "2:42:41", "throughput": 1486.08, "total_tokens": 23860864} {"current_steps": 113070, "total_steps": 181800, "loss": 0.0541, "lr": 1.8787681239809072e-05, "epoch": 12.438943894389439, "percentage": 62.19, "elapsed_time": "4:27:36", "remaining_time": "2:42:40", "throughput": 1486.08, "total_tokens": 23861952} {"current_steps": 113075, "total_steps": 181800, "loss": 0.0112, "lr": 1.8785356481822665e-05, "epoch": 12.43949394939494, "percentage": 62.2, "elapsed_time": "4:27:37", "remaining_time": "2:42:39", "throughput": 1486.08, "total_tokens": 23862976} {"current_steps": 113080, "total_steps": 181800, "loss": 0.0144, "lr": 1.878303178111366e-05, "epoch": 12.44004400440044, "percentage": 62.2, "elapsed_time": "4:27:38", "remaining_time": "2:42:38", "throughput": 1486.08, "total_tokens": 23864032} {"current_steps": 113085, "total_steps": 181800, "loss": 0.0557, "lr": 1.878070713770346e-05, "epoch": 12.44059405940594, "percentage": 62.2, "elapsed_time": "4:27:39", "remaining_time": "2:42:38", "throughput": 1486.08, "total_tokens": 23865056} {"current_steps": 113090, "total_steps": 181800, "loss": 0.0036, "lr": 1.8778382551613494e-05, "epoch": 12.441144114411442, "percentage": 62.21, "elapsed_time": "4:27:39", "remaining_time": "2:42:37", "throughput": 1486.09, "total_tokens": 23866144} {"current_steps": 113095, "total_steps": 181800, "loss": 0.0038, "lr": 1.8776058022865193e-05, "epoch": 12.441694169416941, "percentage": 62.21, "elapsed_time": "4:27:40", "remaining_time": "2:42:36", "throughput": 1486.09, "total_tokens": 23867168} {"current_steps": 113100, "total_steps": 181800, "loss": 0.0011, "lr": 1.8773733551479977e-05, "epoch": 12.442244224422442, "percentage": 62.21, "elapsed_time": "4:27:41", "remaining_time": "2:42:35", "throughput": 1486.09, "total_tokens": 23868192} {"current_steps": 113105, "total_steps": 181800, "loss": 0.001, "lr": 1.8771409137479277e-05, "epoch": 12.442794279427943, "percentage": 62.21, "elapsed_time": "4:27:41", "remaining_time": "2:42:35", "throughput": 1486.09, "total_tokens": 23869280} {"current_steps": 113110, "total_steps": 181800, "loss": 0.0312, "lr": 1.876908478088451e-05, "epoch": 12.443344334433444, "percentage": 62.22, "elapsed_time": "4:27:42", "remaining_time": "2:42:34", "throughput": 1486.1, "total_tokens": 23870368} {"current_steps": 113115, "total_steps": 181800, "loss": 0.0438, "lr": 1.8766760481717092e-05, "epoch": 12.443894389438944, "percentage": 62.22, "elapsed_time": "4:27:43", "remaining_time": "2:42:33", "throughput": 1486.1, "total_tokens": 23871424} {"current_steps": 113120, "total_steps": 181800, "loss": 0.0083, "lr": 1.8764436239998462e-05, "epoch": 12.444444444444445, "percentage": 62.22, "elapsed_time": "4:27:43", "remaining_time": "2:42:33", "throughput": 1486.11, "total_tokens": 23872544} {"current_steps": 113125, "total_steps": 181800, "loss": 0.067, "lr": 1.876211205575002e-05, "epoch": 12.444994499449946, "percentage": 62.22, "elapsed_time": "4:27:44", "remaining_time": "2:42:32", "throughput": 1486.11, "total_tokens": 23873600} {"current_steps": 113130, "total_steps": 181800, "loss": 0.0088, "lr": 1.8759787928993204e-05, "epoch": 12.445544554455445, "percentage": 62.23, "elapsed_time": "4:27:45", "remaining_time": "2:42:31", "throughput": 1486.11, "total_tokens": 23874656} {"current_steps": 113135, "total_steps": 181800, "loss": 0.0062, "lr": 1.8757463859749433e-05, "epoch": 12.446094609460946, "percentage": 62.23, "elapsed_time": "4:27:45", "remaining_time": "2:42:30", "throughput": 1486.12, "total_tokens": 23875808} {"current_steps": 113140, "total_steps": 181800, "loss": 0.0185, "lr": 1.875513984804011e-05, "epoch": 12.446644664466447, "percentage": 62.23, "elapsed_time": "4:27:46", "remaining_time": "2:42:30", "throughput": 1486.12, "total_tokens": 23876864} {"current_steps": 113145, "total_steps": 181800, "loss": 0.0027, "lr": 1.8752815893886675e-05, "epoch": 12.447194719471947, "percentage": 62.24, "elapsed_time": "4:27:47", "remaining_time": "2:42:29", "throughput": 1486.12, "total_tokens": 23877920} {"current_steps": 113150, "total_steps": 181800, "loss": 0.0055, "lr": 1.8750491997310543e-05, "epoch": 12.447744774477448, "percentage": 62.24, "elapsed_time": "4:27:47", "remaining_time": "2:42:28", "throughput": 1486.12, "total_tokens": 23878912} {"current_steps": 113155, "total_steps": 181800, "loss": 0.0018, "lr": 1.8748168158333108e-05, "epoch": 12.448294829482949, "percentage": 62.24, "elapsed_time": "4:27:48", "remaining_time": "2:42:27", "throughput": 1486.12, "total_tokens": 23879936} {"current_steps": 113160, "total_steps": 181800, "loss": 0.0955, "lr": 1.8745844376975828e-05, "epoch": 12.448844884488448, "percentage": 62.24, "elapsed_time": "4:27:49", "remaining_time": "2:42:27", "throughput": 1486.12, "total_tokens": 23880960} {"current_steps": 113165, "total_steps": 181800, "loss": 0.0359, "lr": 1.8743520653260082e-05, "epoch": 12.44939493949395, "percentage": 62.25, "elapsed_time": "4:27:50", "remaining_time": "2:42:26", "throughput": 1486.12, "total_tokens": 23882016} {"current_steps": 113170, "total_steps": 181800, "loss": 0.059, "lr": 1.8741196987207317e-05, "epoch": 12.44994499449945, "percentage": 62.25, "elapsed_time": "4:27:50", "remaining_time": "2:42:25", "throughput": 1486.13, "total_tokens": 23883136} {"current_steps": 113175, "total_steps": 181800, "loss": 0.0841, "lr": 1.873887337883894e-05, "epoch": 12.450495049504951, "percentage": 62.25, "elapsed_time": "4:27:51", "remaining_time": "2:42:25", "throughput": 1486.13, "total_tokens": 23884160} {"current_steps": 113180, "total_steps": 181800, "loss": 0.0012, "lr": 1.8736549828176347e-05, "epoch": 12.45104510451045, "percentage": 62.26, "elapsed_time": "4:27:52", "remaining_time": "2:42:24", "throughput": 1486.13, "total_tokens": 23885216} {"current_steps": 113185, "total_steps": 181800, "loss": 0.0157, "lr": 1.873422633524098e-05, "epoch": 12.451595159515952, "percentage": 62.26, "elapsed_time": "4:27:52", "remaining_time": "2:42:23", "throughput": 1486.13, "total_tokens": 23886208} {"current_steps": 113190, "total_steps": 181800, "loss": 0.1013, "lr": 1.8731902900054233e-05, "epoch": 12.452145214521453, "percentage": 62.26, "elapsed_time": "4:27:53", "remaining_time": "2:42:22", "throughput": 1486.13, "total_tokens": 23887296} {"current_steps": 113195, "total_steps": 181800, "loss": 0.0286, "lr": 1.872957952263754e-05, "epoch": 12.452695269526952, "percentage": 62.26, "elapsed_time": "4:27:54", "remaining_time": "2:42:22", "throughput": 1486.14, "total_tokens": 23888384} {"current_steps": 113200, "total_steps": 181800, "loss": 0.0011, "lr": 1.87272562030123e-05, "epoch": 12.453245324532453, "percentage": 62.27, "elapsed_time": "4:27:54", "remaining_time": "2:42:21", "throughput": 1486.14, "total_tokens": 23889440} {"current_steps": 113205, "total_steps": 181800, "loss": 0.0495, "lr": 1.8724932941199923e-05, "epoch": 12.453795379537954, "percentage": 62.27, "elapsed_time": "4:27:55", "remaining_time": "2:42:20", "throughput": 1486.14, "total_tokens": 23890528} {"current_steps": 113210, "total_steps": 181800, "loss": 0.0248, "lr": 1.8722609737221838e-05, "epoch": 12.454345434543454, "percentage": 62.27, "elapsed_time": "4:27:56", "remaining_time": "2:42:20", "throughput": 1486.15, "total_tokens": 23891616} {"current_steps": 113215, "total_steps": 181800, "loss": 0.0041, "lr": 1.8720286591099434e-05, "epoch": 12.454895489548955, "percentage": 62.27, "elapsed_time": "4:27:56", "remaining_time": "2:42:19", "throughput": 1486.15, "total_tokens": 23892704} {"current_steps": 113220, "total_steps": 181800, "loss": 0.0149, "lr": 1.8717963502854148e-05, "epoch": 12.455445544554456, "percentage": 62.28, "elapsed_time": "4:27:57", "remaining_time": "2:42:18", "throughput": 1486.15, "total_tokens": 23893792} {"current_steps": 113225, "total_steps": 181800, "loss": 0.0073, "lr": 1.8715640472507372e-05, "epoch": 12.455995599559955, "percentage": 62.28, "elapsed_time": "4:27:58", "remaining_time": "2:42:17", "throughput": 1486.16, "total_tokens": 23894848} {"current_steps": 113230, "total_steps": 181800, "loss": 0.0039, "lr": 1.8713317500080523e-05, "epoch": 12.456545654565456, "percentage": 62.28, "elapsed_time": "4:27:58", "remaining_time": "2:42:17", "throughput": 1486.16, "total_tokens": 23895872} {"current_steps": 113235, "total_steps": 181800, "loss": 0.013, "lr": 1.8710994585595016e-05, "epoch": 12.457095709570957, "percentage": 62.29, "elapsed_time": "4:27:59", "remaining_time": "2:42:16", "throughput": 1486.15, "total_tokens": 23896864} {"current_steps": 113240, "total_steps": 181800, "loss": 0.0078, "lr": 1.8708671729072242e-05, "epoch": 12.457645764576458, "percentage": 62.29, "elapsed_time": "4:28:00", "remaining_time": "2:42:15", "throughput": 1486.15, "total_tokens": 23897920} {"current_steps": 113245, "total_steps": 181800, "loss": 0.0769, "lr": 1.870634893053363e-05, "epoch": 12.458195819581958, "percentage": 62.29, "elapsed_time": "4:28:01", "remaining_time": "2:42:14", "throughput": 1486.16, "total_tokens": 23899072} {"current_steps": 113250, "total_steps": 181800, "loss": 0.0032, "lr": 1.8704026190000583e-05, "epoch": 12.458745874587459, "percentage": 62.29, "elapsed_time": "4:28:01", "remaining_time": "2:42:14", "throughput": 1486.16, "total_tokens": 23900128} {"current_steps": 113255, "total_steps": 181800, "loss": 0.0019, "lr": 1.8701703507494497e-05, "epoch": 12.45929592959296, "percentage": 62.3, "elapsed_time": "4:28:02", "remaining_time": "2:42:13", "throughput": 1486.17, "total_tokens": 23901280} {"current_steps": 113260, "total_steps": 181800, "loss": 0.0289, "lr": 1.8699380883036792e-05, "epoch": 12.45984598459846, "percentage": 62.3, "elapsed_time": "4:28:03", "remaining_time": "2:42:12", "throughput": 1486.17, "total_tokens": 23902304} {"current_steps": 113265, "total_steps": 181800, "loss": 0.0465, "lr": 1.8697058316648864e-05, "epoch": 12.46039603960396, "percentage": 62.3, "elapsed_time": "4:28:03", "remaining_time": "2:42:12", "throughput": 1486.18, "total_tokens": 23903424} {"current_steps": 113270, "total_steps": 181800, "loss": 0.0009, "lr": 1.869473580835214e-05, "epoch": 12.460946094609461, "percentage": 62.3, "elapsed_time": "4:28:04", "remaining_time": "2:42:11", "throughput": 1486.18, "total_tokens": 23904480} {"current_steps": 113275, "total_steps": 181800, "loss": 0.0143, "lr": 1.8692413358168e-05, "epoch": 12.46149614961496, "percentage": 62.31, "elapsed_time": "4:28:05", "remaining_time": "2:42:10", "throughput": 1486.18, "total_tokens": 23905568} {"current_steps": 113280, "total_steps": 181800, "loss": 0.0013, "lr": 1.8690090966117857e-05, "epoch": 12.462046204620462, "percentage": 62.31, "elapsed_time": "4:28:05", "remaining_time": "2:42:09", "throughput": 1486.18, "total_tokens": 23906624} {"current_steps": 113285, "total_steps": 181800, "loss": 0.0984, "lr": 1.868776863222312e-05, "epoch": 12.462596259625963, "percentage": 62.31, "elapsed_time": "4:28:06", "remaining_time": "2:42:09", "throughput": 1486.19, "total_tokens": 23907712} {"current_steps": 113290, "total_steps": 181800, "loss": 0.0698, "lr": 1.8685446356505188e-05, "epoch": 12.463146314631462, "percentage": 62.32, "elapsed_time": "4:28:07", "remaining_time": "2:42:08", "throughput": 1486.19, "total_tokens": 23908704} {"current_steps": 113295, "total_steps": 181800, "loss": 0.0815, "lr": 1.8683124138985475e-05, "epoch": 12.463696369636963, "percentage": 62.32, "elapsed_time": "4:28:07", "remaining_time": "2:42:07", "throughput": 1486.19, "total_tokens": 23909824} {"current_steps": 113300, "total_steps": 181800, "loss": 0.0289, "lr": 1.8680801979685373e-05, "epoch": 12.464246424642464, "percentage": 62.32, "elapsed_time": "4:28:08", "remaining_time": "2:42:07", "throughput": 1486.19, "total_tokens": 23910912} {"current_steps": 113305, "total_steps": 181800, "loss": 0.0193, "lr": 1.867847987862628e-05, "epoch": 12.464796479647966, "percentage": 62.32, "elapsed_time": "4:28:09", "remaining_time": "2:42:06", "throughput": 1486.2, "total_tokens": 23912000} {"current_steps": 113310, "total_steps": 181800, "loss": 0.0233, "lr": 1.8676157835829617e-05, "epoch": 12.465346534653465, "percentage": 62.33, "elapsed_time": "4:28:10", "remaining_time": "2:42:05", "throughput": 1486.2, "total_tokens": 23913088} {"current_steps": 113315, "total_steps": 181800, "loss": 0.0074, "lr": 1.8673835851316762e-05, "epoch": 12.465896589658966, "percentage": 62.33, "elapsed_time": "4:28:10", "remaining_time": "2:42:04", "throughput": 1486.21, "total_tokens": 23914176} {"current_steps": 113320, "total_steps": 181800, "loss": 0.0448, "lr": 1.867151392510913e-05, "epoch": 12.466446644664467, "percentage": 62.33, "elapsed_time": "4:28:11", "remaining_time": "2:42:04", "throughput": 1486.21, "total_tokens": 23915296} {"current_steps": 113325, "total_steps": 181800, "loss": 0.1105, "lr": 1.8669192057228123e-05, "epoch": 12.466996699669966, "percentage": 62.33, "elapsed_time": "4:28:12", "remaining_time": "2:42:03", "throughput": 1486.21, "total_tokens": 23916352} {"current_steps": 113330, "total_steps": 181800, "loss": 0.0022, "lr": 1.8666870247695118e-05, "epoch": 12.467546754675467, "percentage": 62.34, "elapsed_time": "4:28:12", "remaining_time": "2:42:02", "throughput": 1486.21, "total_tokens": 23917408} {"current_steps": 113335, "total_steps": 181800, "loss": 0.0936, "lr": 1.866454849653155e-05, "epoch": 12.468096809680969, "percentage": 62.34, "elapsed_time": "4:28:13", "remaining_time": "2:42:02", "throughput": 1486.22, "total_tokens": 23918496} {"current_steps": 113340, "total_steps": 181800, "loss": 0.0026, "lr": 1.8662226803758793e-05, "epoch": 12.468646864686468, "percentage": 62.34, "elapsed_time": "4:28:14", "remaining_time": "2:42:01", "throughput": 1486.22, "total_tokens": 23919488} {"current_steps": 113345, "total_steps": 181800, "loss": 0.1167, "lr": 1.8659905169398242e-05, "epoch": 12.469196919691969, "percentage": 62.35, "elapsed_time": "4:28:14", "remaining_time": "2:42:00", "throughput": 1486.22, "total_tokens": 23920544} {"current_steps": 113350, "total_steps": 181800, "loss": 0.0057, "lr": 1.8657583593471316e-05, "epoch": 12.46974697469747, "percentage": 62.35, "elapsed_time": "4:28:15", "remaining_time": "2:41:59", "throughput": 1486.22, "total_tokens": 23921600} {"current_steps": 113355, "total_steps": 181800, "loss": 0.0258, "lr": 1.8655262075999384e-05, "epoch": 12.47029702970297, "percentage": 62.35, "elapsed_time": "4:28:16", "remaining_time": "2:41:59", "throughput": 1486.22, "total_tokens": 23922656} {"current_steps": 113360, "total_steps": 181800, "loss": 0.0444, "lr": 1.8652940617003866e-05, "epoch": 12.47084708470847, "percentage": 62.35, "elapsed_time": "4:28:16", "remaining_time": "2:41:58", "throughput": 1486.22, "total_tokens": 23923712} {"current_steps": 113365, "total_steps": 181800, "loss": 0.0406, "lr": 1.8650619216506154e-05, "epoch": 12.471397139713972, "percentage": 62.36, "elapsed_time": "4:28:17", "remaining_time": "2:41:57", "throughput": 1486.22, "total_tokens": 23924704} {"current_steps": 113370, "total_steps": 181800, "loss": 0.1044, "lr": 1.8648297874527627e-05, "epoch": 12.471947194719473, "percentage": 62.36, "elapsed_time": "4:28:18", "remaining_time": "2:41:56", "throughput": 1486.23, "total_tokens": 23925824} {"current_steps": 113375, "total_steps": 181800, "loss": 0.0512, "lr": 1.86459765910897e-05, "epoch": 12.472497249724972, "percentage": 62.36, "elapsed_time": "4:28:19", "remaining_time": "2:41:56", "throughput": 1486.23, "total_tokens": 23926880} {"current_steps": 113380, "total_steps": 181800, "loss": 0.0008, "lr": 1.8643655366213745e-05, "epoch": 12.473047304730473, "percentage": 62.37, "elapsed_time": "4:28:19", "remaining_time": "2:41:55", "throughput": 1486.23, "total_tokens": 23927936} {"current_steps": 113385, "total_steps": 181800, "loss": 0.002, "lr": 1.8641334199921182e-05, "epoch": 12.473597359735974, "percentage": 62.37, "elapsed_time": "4:28:20", "remaining_time": "2:41:54", "throughput": 1486.24, "total_tokens": 23929056} {"current_steps": 113390, "total_steps": 181800, "loss": 0.0057, "lr": 1.863901309223339e-05, "epoch": 12.474147414741473, "percentage": 62.37, "elapsed_time": "4:28:21", "remaining_time": "2:41:54", "throughput": 1486.24, "total_tokens": 23930112} {"current_steps": 113395, "total_steps": 181800, "loss": 0.0045, "lr": 1.8636692043171747e-05, "epoch": 12.474697469746975, "percentage": 62.37, "elapsed_time": "4:28:21", "remaining_time": "2:41:53", "throughput": 1486.24, "total_tokens": 23931104} {"current_steps": 113400, "total_steps": 181800, "loss": 0.1735, "lr": 1.863437105275767e-05, "epoch": 12.475247524752476, "percentage": 62.38, "elapsed_time": "4:28:22", "remaining_time": "2:41:52", "throughput": 1486.24, "total_tokens": 23932160} {"current_steps": 113405, "total_steps": 181800, "loss": 0.1212, "lr": 1.8632050121012538e-05, "epoch": 12.475797579757975, "percentage": 62.38, "elapsed_time": "4:28:23", "remaining_time": "2:41:51", "throughput": 1486.24, "total_tokens": 23933216} {"current_steps": 113410, "total_steps": 181800, "loss": 0.0096, "lr": 1.862972924795775e-05, "epoch": 12.476347634763476, "percentage": 62.38, "elapsed_time": "4:28:23", "remaining_time": "2:41:51", "throughput": 1486.24, "total_tokens": 23934304} {"current_steps": 113415, "total_steps": 181800, "loss": 0.0066, "lr": 1.862740843361469e-05, "epoch": 12.476897689768977, "percentage": 62.38, "elapsed_time": "4:28:24", "remaining_time": "2:41:50", "throughput": 1486.24, "total_tokens": 23935328} {"current_steps": 113420, "total_steps": 181800, "loss": 0.0119, "lr": 1.862508767800474e-05, "epoch": 12.477447744774478, "percentage": 62.39, "elapsed_time": "4:28:25", "remaining_time": "2:41:49", "throughput": 1486.25, "total_tokens": 23936384} {"current_steps": 113425, "total_steps": 181800, "loss": 0.0044, "lr": 1.862276698114931e-05, "epoch": 12.477997799779978, "percentage": 62.39, "elapsed_time": "4:28:25", "remaining_time": "2:41:49", "throughput": 1486.25, "total_tokens": 23937440} {"current_steps": 113430, "total_steps": 181800, "loss": 0.0085, "lr": 1.8620446343069768e-05, "epoch": 12.478547854785479, "percentage": 62.39, "elapsed_time": "4:28:26", "remaining_time": "2:41:48", "throughput": 1486.25, "total_tokens": 23938496} {"current_steps": 113435, "total_steps": 181800, "loss": 0.1412, "lr": 1.8618125763787514e-05, "epoch": 12.47909790979098, "percentage": 62.4, "elapsed_time": "4:28:27", "remaining_time": "2:41:47", "throughput": 1486.25, "total_tokens": 23939552} {"current_steps": 113440, "total_steps": 181800, "loss": 0.003, "lr": 1.8615805243323935e-05, "epoch": 12.479647964796479, "percentage": 62.4, "elapsed_time": "4:28:28", "remaining_time": "2:41:46", "throughput": 1486.25, "total_tokens": 23940576} {"current_steps": 113445, "total_steps": 181800, "loss": 0.0239, "lr": 1.861348478170041e-05, "epoch": 12.48019801980198, "percentage": 62.4, "elapsed_time": "4:28:28", "remaining_time": "2:41:46", "throughput": 1486.25, "total_tokens": 23941664} {"current_steps": 113450, "total_steps": 181800, "loss": 0.0807, "lr": 1.8611164378938333e-05, "epoch": 12.480748074807481, "percentage": 62.4, "elapsed_time": "4:28:29", "remaining_time": "2:41:45", "throughput": 1486.26, "total_tokens": 23942720} {"current_steps": 113455, "total_steps": 181800, "loss": 0.003, "lr": 1.8608844035059088e-05, "epoch": 12.48129812981298, "percentage": 62.41, "elapsed_time": "4:28:30", "remaining_time": "2:41:44", "throughput": 1486.26, "total_tokens": 23943808} {"current_steps": 113460, "total_steps": 181800, "loss": 0.0318, "lr": 1.860652375008406e-05, "epoch": 12.481848184818482, "percentage": 62.41, "elapsed_time": "4:28:30", "remaining_time": "2:41:43", "throughput": 1486.26, "total_tokens": 23944832} {"current_steps": 113465, "total_steps": 181800, "loss": 0.001, "lr": 1.860420352403464e-05, "epoch": 12.482398239823983, "percentage": 62.41, "elapsed_time": "4:28:31", "remaining_time": "2:41:43", "throughput": 1486.26, "total_tokens": 23945920} {"current_steps": 113470, "total_steps": 181800, "loss": 0.0248, "lr": 1.8601883356932202e-05, "epoch": 12.482948294829482, "percentage": 62.41, "elapsed_time": "4:28:32", "remaining_time": "2:41:42", "throughput": 1486.27, "total_tokens": 23947008} {"current_steps": 113475, "total_steps": 181800, "loss": 0.0319, "lr": 1.8599563248798137e-05, "epoch": 12.483498349834983, "percentage": 62.42, "elapsed_time": "4:28:32", "remaining_time": "2:41:41", "throughput": 1486.27, "total_tokens": 23948032} {"current_steps": 113480, "total_steps": 181800, "loss": 0.0088, "lr": 1.8597243199653817e-05, "epoch": 12.484048404840484, "percentage": 62.42, "elapsed_time": "4:28:33", "remaining_time": "2:41:41", "throughput": 1486.27, "total_tokens": 23949120} {"current_steps": 113485, "total_steps": 181800, "loss": 0.0425, "lr": 1.8594923209520654e-05, "epoch": 12.484598459845985, "percentage": 62.42, "elapsed_time": "4:28:34", "remaining_time": "2:41:40", "throughput": 1486.27, "total_tokens": 23950144} {"current_steps": 113490, "total_steps": 181800, "loss": 0.0087, "lr": 1.8592603278419998e-05, "epoch": 12.485148514851485, "percentage": 62.43, "elapsed_time": "4:28:34", "remaining_time": "2:41:39", "throughput": 1486.27, "total_tokens": 23951200} {"current_steps": 113495, "total_steps": 181800, "loss": 0.0039, "lr": 1.859028340637324e-05, "epoch": 12.485698569856986, "percentage": 62.43, "elapsed_time": "4:28:35", "remaining_time": "2:41:38", "throughput": 1486.28, "total_tokens": 23952256} {"current_steps": 113500, "total_steps": 181800, "loss": 0.0037, "lr": 1.8587963593401773e-05, "epoch": 12.486248624862487, "percentage": 62.43, "elapsed_time": "4:28:36", "remaining_time": "2:41:38", "throughput": 1486.28, "total_tokens": 23953344} {"current_steps": 113505, "total_steps": 181800, "loss": 0.0541, "lr": 1.8585643839526963e-05, "epoch": 12.486798679867986, "percentage": 62.43, "elapsed_time": "4:28:36", "remaining_time": "2:41:37", "throughput": 1486.28, "total_tokens": 23954368} {"current_steps": 113510, "total_steps": 181800, "loss": 0.0057, "lr": 1.8583324144770197e-05, "epoch": 12.487348734873487, "percentage": 62.44, "elapsed_time": "4:28:37", "remaining_time": "2:41:36", "throughput": 1486.28, "total_tokens": 23955456} {"current_steps": 113515, "total_steps": 181800, "loss": 0.0031, "lr": 1.858100450915286e-05, "epoch": 12.487898789878988, "percentage": 62.44, "elapsed_time": "4:28:38", "remaining_time": "2:41:36", "throughput": 1486.29, "total_tokens": 23956544} {"current_steps": 113520, "total_steps": 181800, "loss": 0.0849, "lr": 1.8578684932696305e-05, "epoch": 12.488448844884488, "percentage": 62.44, "elapsed_time": "4:28:39", "remaining_time": "2:41:35", "throughput": 1486.29, "total_tokens": 23957536} {"current_steps": 113525, "total_steps": 181800, "loss": 0.0701, "lr": 1.857636541542195e-05, "epoch": 12.488998899889989, "percentage": 62.44, "elapsed_time": "4:28:39", "remaining_time": "2:41:34", "throughput": 1486.29, "total_tokens": 23958592} {"current_steps": 113530, "total_steps": 181800, "loss": 0.001, "lr": 1.8574045957351144e-05, "epoch": 12.48954895489549, "percentage": 62.45, "elapsed_time": "4:28:40", "remaining_time": "2:41:33", "throughput": 1486.29, "total_tokens": 23959712} {"current_steps": 113535, "total_steps": 181800, "loss": 0.0097, "lr": 1.857172655850527e-05, "epoch": 12.490099009900991, "percentage": 62.45, "elapsed_time": "4:28:41", "remaining_time": "2:41:33", "throughput": 1486.29, "total_tokens": 23960768} {"current_steps": 113540, "total_steps": 181800, "loss": 0.0332, "lr": 1.856940721890572e-05, "epoch": 12.49064906490649, "percentage": 62.45, "elapsed_time": "4:28:41", "remaining_time": "2:41:32", "throughput": 1486.3, "total_tokens": 23961824} {"current_steps": 113545, "total_steps": 181800, "loss": 0.0153, "lr": 1.8567087938573843e-05, "epoch": 12.491199119911991, "percentage": 62.46, "elapsed_time": "4:28:42", "remaining_time": "2:41:31", "throughput": 1486.3, "total_tokens": 23962912} {"current_steps": 113550, "total_steps": 181800, "loss": 0.016, "lr": 1.856476871753104e-05, "epoch": 12.491749174917492, "percentage": 62.46, "elapsed_time": "4:28:43", "remaining_time": "2:41:30", "throughput": 1486.3, "total_tokens": 23964000} {"current_steps": 113555, "total_steps": 181800, "loss": 0.0296, "lr": 1.8562449555798677e-05, "epoch": 12.492299229922992, "percentage": 62.46, "elapsed_time": "4:28:43", "remaining_time": "2:41:30", "throughput": 1486.3, "total_tokens": 23964992} {"current_steps": 113560, "total_steps": 181800, "loss": 0.0036, "lr": 1.8560130453398116e-05, "epoch": 12.492849284928493, "percentage": 62.46, "elapsed_time": "4:28:44", "remaining_time": "2:41:29", "throughput": 1486.3, "total_tokens": 23966048} {"current_steps": 113565, "total_steps": 181800, "loss": 0.0455, "lr": 1.855781141035075e-05, "epoch": 12.493399339933994, "percentage": 62.47, "elapsed_time": "4:28:45", "remaining_time": "2:41:28", "throughput": 1486.31, "total_tokens": 23967136} {"current_steps": 113570, "total_steps": 181800, "loss": 0.0559, "lr": 1.855549242667794e-05, "epoch": 12.493949394939493, "percentage": 62.47, "elapsed_time": "4:28:45", "remaining_time": "2:41:28", "throughput": 1486.31, "total_tokens": 23968192} {"current_steps": 113575, "total_steps": 181800, "loss": 0.0692, "lr": 1.8553173502401065e-05, "epoch": 12.494499449944994, "percentage": 62.47, "elapsed_time": "4:28:46", "remaining_time": "2:41:27", "throughput": 1486.31, "total_tokens": 23969216} {"current_steps": 113580, "total_steps": 181800, "loss": 0.0894, "lr": 1.855085463754151e-05, "epoch": 12.495049504950495, "percentage": 62.48, "elapsed_time": "4:28:47", "remaining_time": "2:41:26", "throughput": 1486.32, "total_tokens": 23970336} {"current_steps": 113585, "total_steps": 181800, "loss": 0.0941, "lr": 1.8548535832120617e-05, "epoch": 12.495599559955995, "percentage": 62.48, "elapsed_time": "4:28:48", "remaining_time": "2:41:25", "throughput": 1486.32, "total_tokens": 23971392} {"current_steps": 113590, "total_steps": 181800, "loss": 0.0095, "lr": 1.854621708615978e-05, "epoch": 12.496149614961496, "percentage": 62.48, "elapsed_time": "4:28:48", "remaining_time": "2:41:25", "throughput": 1486.33, "total_tokens": 23972544} {"current_steps": 113595, "total_steps": 181800, "loss": 0.0605, "lr": 1.8543898399680358e-05, "epoch": 12.496699669966997, "percentage": 62.48, "elapsed_time": "4:28:49", "remaining_time": "2:41:24", "throughput": 1486.33, "total_tokens": 23973600} {"current_steps": 113600, "total_steps": 181800, "loss": 0.0027, "lr": 1.8541579772703737e-05, "epoch": 12.497249724972498, "percentage": 62.49, "elapsed_time": "4:28:50", "remaining_time": "2:41:23", "throughput": 1486.33, "total_tokens": 23974656} {"current_steps": 113605, "total_steps": 181800, "loss": 0.0542, "lr": 1.853926120525127e-05, "epoch": 12.497799779977997, "percentage": 62.49, "elapsed_time": "4:28:50", "remaining_time": "2:41:23", "throughput": 1486.33, "total_tokens": 23975712} {"current_steps": 113610, "total_steps": 181800, "loss": 0.0027, "lr": 1.853694269734433e-05, "epoch": 12.498349834983498, "percentage": 62.49, "elapsed_time": "4:28:51", "remaining_time": "2:41:22", "throughput": 1486.33, "total_tokens": 23976736} {"current_steps": 113615, "total_steps": 181800, "loss": 0.0442, "lr": 1.8534624249004294e-05, "epoch": 12.498899889989, "percentage": 62.49, "elapsed_time": "4:28:52", "remaining_time": "2:41:21", "throughput": 1486.33, "total_tokens": 23977728} {"current_steps": 113620, "total_steps": 181800, "loss": 0.0041, "lr": 1.8532305860252515e-05, "epoch": 12.499449944994499, "percentage": 62.5, "elapsed_time": "4:28:52", "remaining_time": "2:41:20", "throughput": 1486.33, "total_tokens": 23978784} {"current_steps": 113625, "total_steps": 181800, "loss": 0.0111, "lr": 1.8529987531110378e-05, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "4:28:53", "remaining_time": "2:41:20", "throughput": 1486.33, "total_tokens": 23979808} {"current_steps": 113630, "total_steps": 181800, "loss": 0.0883, "lr": 1.852766926159924e-05, "epoch": 12.500550055005501, "percentage": 62.5, "elapsed_time": "4:28:54", "remaining_time": "2:41:19", "throughput": 1486.33, "total_tokens": 23980832} {"current_steps": 113635, "total_steps": 181800, "loss": 0.0462, "lr": 1.852535105174046e-05, "epoch": 12.501100110011, "percentage": 62.51, "elapsed_time": "4:28:54", "remaining_time": "2:41:18", "throughput": 1486.33, "total_tokens": 23981856} {"current_steps": 113640, "total_steps": 181800, "loss": 0.0045, "lr": 1.852303290155542e-05, "epoch": 12.501650165016502, "percentage": 62.51, "elapsed_time": "4:28:55", "remaining_time": "2:41:17", "throughput": 1486.33, "total_tokens": 23982880} {"current_steps": 113645, "total_steps": 181800, "loss": 0.0489, "lr": 1.8520714811065477e-05, "epoch": 12.502200220022003, "percentage": 62.51, "elapsed_time": "4:28:56", "remaining_time": "2:41:17", "throughput": 1486.34, "total_tokens": 23983968} {"current_steps": 113650, "total_steps": 181800, "loss": 0.0026, "lr": 1.8518396780291994e-05, "epoch": 12.502750275027502, "percentage": 62.51, "elapsed_time": "4:28:56", "remaining_time": "2:41:16", "throughput": 1486.34, "total_tokens": 23984992} {"current_steps": 113655, "total_steps": 181800, "loss": 0.1707, "lr": 1.8516078809256345e-05, "epoch": 12.503300330033003, "percentage": 62.52, "elapsed_time": "4:28:57", "remaining_time": "2:41:15", "throughput": 1486.34, "total_tokens": 23986048} {"current_steps": 113660, "total_steps": 181800, "loss": 0.0061, "lr": 1.8513760897979874e-05, "epoch": 12.503850385038504, "percentage": 62.52, "elapsed_time": "4:28:58", "remaining_time": "2:41:15", "throughput": 1486.34, "total_tokens": 23987040} {"current_steps": 113665, "total_steps": 181800, "loss": 0.0064, "lr": 1.8511443046483967e-05, "epoch": 12.504400440044005, "percentage": 62.52, "elapsed_time": "4:28:59", "remaining_time": "2:41:14", "throughput": 1486.34, "total_tokens": 23988096} {"current_steps": 113670, "total_steps": 181800, "loss": 0.0021, "lr": 1.850912525478997e-05, "epoch": 12.504950495049505, "percentage": 62.52, "elapsed_time": "4:28:59", "remaining_time": "2:41:13", "throughput": 1486.34, "total_tokens": 23989088} {"current_steps": 113675, "total_steps": 181800, "loss": 0.0239, "lr": 1.850680752291926e-05, "epoch": 12.505500550055006, "percentage": 62.53, "elapsed_time": "4:29:00", "remaining_time": "2:41:12", "throughput": 1486.34, "total_tokens": 23990112} {"current_steps": 113680, "total_steps": 181800, "loss": 0.0068, "lr": 1.850448985089318e-05, "epoch": 12.506050605060507, "percentage": 62.53, "elapsed_time": "4:29:01", "remaining_time": "2:41:12", "throughput": 1486.34, "total_tokens": 23991136} {"current_steps": 113685, "total_steps": 181800, "loss": 0.0472, "lr": 1.85021722387331e-05, "epoch": 12.506600660066006, "percentage": 62.53, "elapsed_time": "4:29:01", "remaining_time": "2:41:11", "throughput": 1486.34, "total_tokens": 23992192} {"current_steps": 113690, "total_steps": 181800, "loss": 0.0028, "lr": 1.8499854686460393e-05, "epoch": 12.507150715071507, "percentage": 62.54, "elapsed_time": "4:29:02", "remaining_time": "2:41:10", "throughput": 1486.34, "total_tokens": 23993216} {"current_steps": 113695, "total_steps": 181800, "loss": 0.1224, "lr": 1.8497537194096385e-05, "epoch": 12.507700770077008, "percentage": 62.54, "elapsed_time": "4:29:03", "remaining_time": "2:41:10", "throughput": 1486.34, "total_tokens": 23994240} {"current_steps": 113700, "total_steps": 181800, "loss": 0.0011, "lr": 1.8495219761662476e-05, "epoch": 12.508250825082508, "percentage": 62.54, "elapsed_time": "4:29:03", "remaining_time": "2:41:09", "throughput": 1486.34, "total_tokens": 23995296} {"current_steps": 113705, "total_steps": 181800, "loss": 0.0094, "lr": 1.8492902389179993e-05, "epoch": 12.508800880088009, "percentage": 62.54, "elapsed_time": "4:29:04", "remaining_time": "2:41:08", "throughput": 1486.34, "total_tokens": 23996320} {"current_steps": 113710, "total_steps": 181800, "loss": 0.0377, "lr": 1.849058507667031e-05, "epoch": 12.50935093509351, "percentage": 62.55, "elapsed_time": "4:29:05", "remaining_time": "2:41:07", "throughput": 1486.34, "total_tokens": 23997312} {"current_steps": 113715, "total_steps": 181800, "loss": 0.0019, "lr": 1.8488267824154787e-05, "epoch": 12.509900990099009, "percentage": 62.55, "elapsed_time": "4:29:05", "remaining_time": "2:41:07", "throughput": 1486.35, "total_tokens": 23998464} {"current_steps": 113720, "total_steps": 181800, "loss": 0.0447, "lr": 1.8485950631654768e-05, "epoch": 12.51045104510451, "percentage": 62.55, "elapsed_time": "4:29:06", "remaining_time": "2:41:06", "throughput": 1486.34, "total_tokens": 23999456} {"current_steps": 113725, "total_steps": 181800, "loss": 0.1062, "lr": 1.8483633499191618e-05, "epoch": 12.511001100110011, "percentage": 62.56, "elapsed_time": "4:29:07", "remaining_time": "2:41:05", "throughput": 1486.35, "total_tokens": 24000512} {"current_steps": 113730, "total_steps": 181800, "loss": 0.0132, "lr": 1.8481316426786694e-05, "epoch": 12.511551155115512, "percentage": 62.56, "elapsed_time": "4:29:08", "remaining_time": "2:41:04", "throughput": 1486.35, "total_tokens": 24001568} {"current_steps": 113735, "total_steps": 181800, "loss": 0.1102, "lr": 1.847899941446134e-05, "epoch": 12.512101210121012, "percentage": 62.56, "elapsed_time": "4:29:08", "remaining_time": "2:41:04", "throughput": 1486.35, "total_tokens": 24002656} {"current_steps": 113740, "total_steps": 181800, "loss": 0.0035, "lr": 1.8476682462236928e-05, "epoch": 12.512651265126513, "percentage": 62.56, "elapsed_time": "4:29:09", "remaining_time": "2:41:03", "throughput": 1486.35, "total_tokens": 24003712} {"current_steps": 113745, "total_steps": 181800, "loss": 0.0276, "lr": 1.8474365570134805e-05, "epoch": 12.513201320132014, "percentage": 62.57, "elapsed_time": "4:29:10", "remaining_time": "2:41:02", "throughput": 1486.36, "total_tokens": 24004864} {"current_steps": 113750, "total_steps": 181800, "loss": 0.005, "lr": 1.847204873817631e-05, "epoch": 12.513751375137513, "percentage": 62.57, "elapsed_time": "4:29:10", "remaining_time": "2:41:02", "throughput": 1486.36, "total_tokens": 24005920} {"current_steps": 113755, "total_steps": 181800, "loss": 0.0035, "lr": 1.8469731966382822e-05, "epoch": 12.514301430143014, "percentage": 62.57, "elapsed_time": "4:29:11", "remaining_time": "2:41:01", "throughput": 1486.36, "total_tokens": 24006976} {"current_steps": 113760, "total_steps": 181800, "loss": 0.0055, "lr": 1.8467415254775672e-05, "epoch": 12.514851485148515, "percentage": 62.57, "elapsed_time": "4:29:12", "remaining_time": "2:41:00", "throughput": 1486.37, "total_tokens": 24008096} {"current_steps": 113765, "total_steps": 181800, "loss": 0.0048, "lr": 1.8465098603376227e-05, "epoch": 12.515401540154015, "percentage": 62.58, "elapsed_time": "4:29:12", "remaining_time": "2:40:59", "throughput": 1486.37, "total_tokens": 24009120} {"current_steps": 113770, "total_steps": 181800, "loss": 0.028, "lr": 1.8462782012205836e-05, "epoch": 12.515951595159516, "percentage": 62.58, "elapsed_time": "4:29:13", "remaining_time": "2:40:59", "throughput": 1486.37, "total_tokens": 24010208} {"current_steps": 113775, "total_steps": 181800, "loss": 0.0041, "lr": 1.8460465481285837e-05, "epoch": 12.516501650165017, "percentage": 62.58, "elapsed_time": "4:29:14", "remaining_time": "2:40:58", "throughput": 1486.37, "total_tokens": 24011200} {"current_steps": 113780, "total_steps": 181800, "loss": 0.0019, "lr": 1.8458149010637595e-05, "epoch": 12.517051705170516, "percentage": 62.59, "elapsed_time": "4:29:14", "remaining_time": "2:40:57", "throughput": 1486.38, "total_tokens": 24012320} {"current_steps": 113785, "total_steps": 181800, "loss": 0.0024, "lr": 1.845583260028245e-05, "epoch": 12.517601760176017, "percentage": 62.59, "elapsed_time": "4:29:15", "remaining_time": "2:40:57", "throughput": 1486.38, "total_tokens": 24013440} {"current_steps": 113790, "total_steps": 181800, "loss": 0.0151, "lr": 1.8453516250241765e-05, "epoch": 12.518151815181518, "percentage": 62.59, "elapsed_time": "4:29:16", "remaining_time": "2:40:56", "throughput": 1486.39, "total_tokens": 24014496} {"current_steps": 113795, "total_steps": 181800, "loss": 0.0047, "lr": 1.8451199960536874e-05, "epoch": 12.51870187018702, "percentage": 62.59, "elapsed_time": "4:29:16", "remaining_time": "2:40:55", "throughput": 1486.39, "total_tokens": 24015520} {"current_steps": 113800, "total_steps": 181800, "loss": 0.006, "lr": 1.8448883731189126e-05, "epoch": 12.519251925192519, "percentage": 62.6, "elapsed_time": "4:29:17", "remaining_time": "2:40:54", "throughput": 1486.39, "total_tokens": 24016672} {"current_steps": 113805, "total_steps": 181800, "loss": 0.0204, "lr": 1.8446567562219884e-05, "epoch": 12.51980198019802, "percentage": 62.6, "elapsed_time": "4:29:18", "remaining_time": "2:40:54", "throughput": 1486.39, "total_tokens": 24017728} {"current_steps": 113810, "total_steps": 181800, "loss": 0.0138, "lr": 1.8444251453650475e-05, "epoch": 12.520352035203521, "percentage": 62.6, "elapsed_time": "4:29:19", "remaining_time": "2:40:53", "throughput": 1486.39, "total_tokens": 24018752} {"current_steps": 113815, "total_steps": 181800, "loss": 0.0024, "lr": 1.8441935405502257e-05, "epoch": 12.52090209020902, "percentage": 62.6, "elapsed_time": "4:29:19", "remaining_time": "2:40:52", "throughput": 1486.39, "total_tokens": 24019744} {"current_steps": 113820, "total_steps": 181800, "loss": 0.0545, "lr": 1.8439619417796573e-05, "epoch": 12.521452145214521, "percentage": 62.61, "elapsed_time": "4:29:20", "remaining_time": "2:40:51", "throughput": 1486.39, "total_tokens": 24020800} {"current_steps": 113825, "total_steps": 181800, "loss": 0.0361, "lr": 1.8437303490554763e-05, "epoch": 12.522002200220022, "percentage": 62.61, "elapsed_time": "4:29:21", "remaining_time": "2:40:51", "throughput": 1486.4, "total_tokens": 24021888} {"current_steps": 113830, "total_steps": 181800, "loss": 0.0089, "lr": 1.8434987623798193e-05, "epoch": 12.522552255225522, "percentage": 62.61, "elapsed_time": "4:29:21", "remaining_time": "2:40:50", "throughput": 1486.4, "total_tokens": 24022912} {"current_steps": 113835, "total_steps": 181800, "loss": 0.0086, "lr": 1.843267181754818e-05, "epoch": 12.523102310231023, "percentage": 62.62, "elapsed_time": "4:29:22", "remaining_time": "2:40:49", "throughput": 1486.4, "total_tokens": 24023968} {"current_steps": 113840, "total_steps": 181800, "loss": 0.0302, "lr": 1.8430356071826082e-05, "epoch": 12.523652365236524, "percentage": 62.62, "elapsed_time": "4:29:23", "remaining_time": "2:40:49", "throughput": 1486.4, "total_tokens": 24024992} {"current_steps": 113845, "total_steps": 181800, "loss": 0.0287, "lr": 1.8428040386653244e-05, "epoch": 12.524202420242025, "percentage": 62.62, "elapsed_time": "4:29:23", "remaining_time": "2:40:48", "throughput": 1486.4, "total_tokens": 24026016} {"current_steps": 113850, "total_steps": 181800, "loss": 0.0178, "lr": 1.8425724762051e-05, "epoch": 12.524752475247524, "percentage": 62.62, "elapsed_time": "4:29:24", "remaining_time": "2:40:47", "throughput": 1486.4, "total_tokens": 24027072} {"current_steps": 113855, "total_steps": 181800, "loss": 0.0039, "lr": 1.8423409198040696e-05, "epoch": 12.525302530253025, "percentage": 62.63, "elapsed_time": "4:29:25", "remaining_time": "2:40:46", "throughput": 1486.4, "total_tokens": 24028096} {"current_steps": 113860, "total_steps": 181800, "loss": 0.0141, "lr": 1.842109369464367e-05, "epoch": 12.525852585258527, "percentage": 62.63, "elapsed_time": "4:29:25", "remaining_time": "2:40:46", "throughput": 1486.4, "total_tokens": 24029088} {"current_steps": 113865, "total_steps": 181800, "loss": 0.0229, "lr": 1.8418778251881273e-05, "epoch": 12.526402640264026, "percentage": 62.63, "elapsed_time": "4:29:26", "remaining_time": "2:40:45", "throughput": 1486.41, "total_tokens": 24030208} {"current_steps": 113870, "total_steps": 181800, "loss": 0.0019, "lr": 1.841646286977484e-05, "epoch": 12.526952695269527, "percentage": 62.63, "elapsed_time": "4:29:27", "remaining_time": "2:40:44", "throughput": 1486.41, "total_tokens": 24031328} {"current_steps": 113875, "total_steps": 181800, "loss": 0.0333, "lr": 1.8414147548345703e-05, "epoch": 12.527502750275028, "percentage": 62.64, "elapsed_time": "4:29:28", "remaining_time": "2:40:44", "throughput": 1486.42, "total_tokens": 24032416} {"current_steps": 113880, "total_steps": 181800, "loss": 0.0016, "lr": 1.841183228761521e-05, "epoch": 12.528052805280527, "percentage": 62.64, "elapsed_time": "4:29:28", "remaining_time": "2:40:43", "throughput": 1486.41, "total_tokens": 24033440} {"current_steps": 113885, "total_steps": 181800, "loss": 0.062, "lr": 1.8409517087604695e-05, "epoch": 12.528602860286028, "percentage": 62.64, "elapsed_time": "4:29:29", "remaining_time": "2:40:42", "throughput": 1486.42, "total_tokens": 24034592} {"current_steps": 113890, "total_steps": 181800, "loss": 0.0408, "lr": 1.8407201948335508e-05, "epoch": 12.52915291529153, "percentage": 62.65, "elapsed_time": "4:29:30", "remaining_time": "2:40:41", "throughput": 1486.43, "total_tokens": 24035680} {"current_steps": 113895, "total_steps": 181800, "loss": 0.0068, "lr": 1.8404886869828974e-05, "epoch": 12.52970297029703, "percentage": 62.65, "elapsed_time": "4:29:30", "remaining_time": "2:40:41", "throughput": 1486.43, "total_tokens": 24036704} {"current_steps": 113900, "total_steps": 181800, "loss": 0.0559, "lr": 1.8402571852106427e-05, "epoch": 12.53025302530253, "percentage": 62.65, "elapsed_time": "4:29:31", "remaining_time": "2:40:40", "throughput": 1486.43, "total_tokens": 24037760} {"current_steps": 113905, "total_steps": 181800, "loss": 0.0025, "lr": 1.8400256895189217e-05, "epoch": 12.530803080308031, "percentage": 62.65, "elapsed_time": "4:29:32", "remaining_time": "2:40:39", "throughput": 1486.43, "total_tokens": 24038816} {"current_steps": 113910, "total_steps": 181800, "loss": 0.0121, "lr": 1.839794199909867e-05, "epoch": 12.531353135313532, "percentage": 62.66, "elapsed_time": "4:29:32", "remaining_time": "2:40:38", "throughput": 1486.43, "total_tokens": 24039872} {"current_steps": 113915, "total_steps": 181800, "loss": 0.0908, "lr": 1.8395627163856116e-05, "epoch": 12.531903190319031, "percentage": 62.66, "elapsed_time": "4:29:33", "remaining_time": "2:40:38", "throughput": 1486.44, "total_tokens": 24040992} {"current_steps": 113920, "total_steps": 181800, "loss": 0.002, "lr": 1.8393312389482912e-05, "epoch": 12.532453245324533, "percentage": 62.66, "elapsed_time": "4:29:34", "remaining_time": "2:40:37", "throughput": 1486.44, "total_tokens": 24042048} {"current_steps": 113925, "total_steps": 181800, "loss": 0.021, "lr": 1.8390997676000362e-05, "epoch": 12.533003300330034, "percentage": 62.67, "elapsed_time": "4:29:34", "remaining_time": "2:40:36", "throughput": 1486.44, "total_tokens": 24043136} {"current_steps": 113930, "total_steps": 181800, "loss": 0.0027, "lr": 1.8388683023429825e-05, "epoch": 12.533553355335533, "percentage": 62.67, "elapsed_time": "4:29:35", "remaining_time": "2:40:36", "throughput": 1486.44, "total_tokens": 24044192} {"current_steps": 113935, "total_steps": 181800, "loss": 0.0038, "lr": 1.838636843179263e-05, "epoch": 12.534103410341034, "percentage": 62.67, "elapsed_time": "4:29:36", "remaining_time": "2:40:35", "throughput": 1486.45, "total_tokens": 24045248} {"current_steps": 113940, "total_steps": 181800, "loss": 0.0273, "lr": 1.8384053901110082e-05, "epoch": 12.534653465346535, "percentage": 62.67, "elapsed_time": "4:29:37", "remaining_time": "2:40:34", "throughput": 1486.45, "total_tokens": 24046368} {"current_steps": 113945, "total_steps": 181800, "loss": 0.0137, "lr": 1.8381739431403554e-05, "epoch": 12.535203520352034, "percentage": 62.68, "elapsed_time": "4:29:37", "remaining_time": "2:40:33", "throughput": 1486.45, "total_tokens": 24047392} {"current_steps": 113950, "total_steps": 181800, "loss": 0.0022, "lr": 1.8379425022694348e-05, "epoch": 12.535753575357536, "percentage": 62.68, "elapsed_time": "4:29:38", "remaining_time": "2:40:33", "throughput": 1486.46, "total_tokens": 24048544} {"current_steps": 113955, "total_steps": 181800, "loss": 0.0087, "lr": 1.8377110675003806e-05, "epoch": 12.536303630363037, "percentage": 62.68, "elapsed_time": "4:29:39", "remaining_time": "2:40:32", "throughput": 1486.46, "total_tokens": 24049632} {"current_steps": 113960, "total_steps": 181800, "loss": 0.0533, "lr": 1.8374796388353264e-05, "epoch": 12.536853685368538, "percentage": 62.68, "elapsed_time": "4:29:39", "remaining_time": "2:40:31", "throughput": 1486.46, "total_tokens": 24050688} {"current_steps": 113965, "total_steps": 181800, "loss": 0.0369, "lr": 1.8372482162764033e-05, "epoch": 12.537403740374037, "percentage": 62.69, "elapsed_time": "4:29:40", "remaining_time": "2:40:31", "throughput": 1486.46, "total_tokens": 24051680} {"current_steps": 113970, "total_steps": 181800, "loss": 0.0866, "lr": 1.8370167998257465e-05, "epoch": 12.537953795379538, "percentage": 62.69, "elapsed_time": "4:29:41", "remaining_time": "2:40:30", "throughput": 1486.46, "total_tokens": 24052736} {"current_steps": 113975, "total_steps": 181800, "loss": 0.0907, "lr": 1.8367853894854868e-05, "epoch": 12.53850385038504, "percentage": 62.69, "elapsed_time": "4:29:41", "remaining_time": "2:40:29", "throughput": 1486.46, "total_tokens": 24053760} {"current_steps": 113980, "total_steps": 181800, "loss": 0.0527, "lr": 1.8365539852577587e-05, "epoch": 12.539053905390539, "percentage": 62.7, "elapsed_time": "4:29:42", "remaining_time": "2:40:28", "throughput": 1486.46, "total_tokens": 24054720} {"current_steps": 113985, "total_steps": 181800, "loss": 0.0069, "lr": 1.836322587144694e-05, "epoch": 12.53960396039604, "percentage": 62.7, "elapsed_time": "4:29:43", "remaining_time": "2:40:28", "throughput": 1486.46, "total_tokens": 24055712} {"current_steps": 113990, "total_steps": 181800, "loss": 0.0771, "lr": 1.836091195148425e-05, "epoch": 12.54015401540154, "percentage": 62.7, "elapsed_time": "4:29:43", "remaining_time": "2:40:27", "throughput": 1486.46, "total_tokens": 24056800} {"current_steps": 113995, "total_steps": 181800, "loss": 0.0875, "lr": 1.8358598092710858e-05, "epoch": 12.54070407040704, "percentage": 62.7, "elapsed_time": "4:29:44", "remaining_time": "2:40:26", "throughput": 1486.46, "total_tokens": 24057824} {"current_steps": 114000, "total_steps": 181800, "loss": 0.0026, "lr": 1.8356284295148067e-05, "epoch": 12.541254125412541, "percentage": 62.71, "elapsed_time": "4:29:45", "remaining_time": "2:40:26", "throughput": 1486.46, "total_tokens": 24058880} {"current_steps": 114005, "total_steps": 181800, "loss": 0.0288, "lr": 1.835397055881723e-05, "epoch": 12.541804180418042, "percentage": 62.71, "elapsed_time": "4:29:46", "remaining_time": "2:40:25", "throughput": 1486.46, "total_tokens": 24059904} {"current_steps": 114010, "total_steps": 181800, "loss": 0.0392, "lr": 1.8351656883739647e-05, "epoch": 12.542354235423542, "percentage": 62.71, "elapsed_time": "4:29:46", "remaining_time": "2:40:24", "throughput": 1486.46, "total_tokens": 24060960} {"current_steps": 114015, "total_steps": 181800, "loss": 0.0027, "lr": 1.8349343269936652e-05, "epoch": 12.542904290429043, "percentage": 62.71, "elapsed_time": "4:29:47", "remaining_time": "2:40:23", "throughput": 1486.47, "total_tokens": 24062048} {"current_steps": 114020, "total_steps": 181800, "loss": 0.0076, "lr": 1.8347029717429583e-05, "epoch": 12.543454345434544, "percentage": 62.72, "elapsed_time": "4:29:48", "remaining_time": "2:40:23", "throughput": 1486.47, "total_tokens": 24063168} {"current_steps": 114025, "total_steps": 181800, "loss": 0.0018, "lr": 1.8344716226239733e-05, "epoch": 12.544004400440045, "percentage": 62.72, "elapsed_time": "4:29:48", "remaining_time": "2:40:22", "throughput": 1486.48, "total_tokens": 24064224} {"current_steps": 114030, "total_steps": 181800, "loss": 0.0021, "lr": 1.8342402796388445e-05, "epoch": 12.544554455445544, "percentage": 62.72, "elapsed_time": "4:29:49", "remaining_time": "2:40:21", "throughput": 1486.48, "total_tokens": 24065248} {"current_steps": 114035, "total_steps": 181800, "loss": 0.0056, "lr": 1.8340089427897044e-05, "epoch": 12.545104510451045, "percentage": 62.73, "elapsed_time": "4:29:50", "remaining_time": "2:40:20", "throughput": 1486.48, "total_tokens": 24066304} {"current_steps": 114040, "total_steps": 181800, "loss": 0.0203, "lr": 1.833777612078683e-05, "epoch": 12.545654565456546, "percentage": 62.73, "elapsed_time": "4:29:50", "remaining_time": "2:40:20", "throughput": 1486.48, "total_tokens": 24067360} {"current_steps": 114045, "total_steps": 181800, "loss": 0.1133, "lr": 1.8335462875079147e-05, "epoch": 12.546204620462046, "percentage": 62.73, "elapsed_time": "4:29:51", "remaining_time": "2:40:19", "throughput": 1486.48, "total_tokens": 24068416} {"current_steps": 114050, "total_steps": 181800, "loss": 0.0766, "lr": 1.8333149690795294e-05, "epoch": 12.546754675467547, "percentage": 62.73, "elapsed_time": "4:29:52", "remaining_time": "2:40:18", "throughput": 1486.48, "total_tokens": 24069504} {"current_steps": 114055, "total_steps": 181800, "loss": 0.0792, "lr": 1.8330836567956614e-05, "epoch": 12.547304730473048, "percentage": 62.74, "elapsed_time": "4:29:52", "remaining_time": "2:40:18", "throughput": 1486.49, "total_tokens": 24070624} {"current_steps": 114060, "total_steps": 181800, "loss": 0.0064, "lr": 1.8328523506584404e-05, "epoch": 12.547854785478547, "percentage": 62.74, "elapsed_time": "4:29:53", "remaining_time": "2:40:17", "throughput": 1486.49, "total_tokens": 24071648} {"current_steps": 114065, "total_steps": 181800, "loss": 0.0056, "lr": 1.8326210506699993e-05, "epoch": 12.548404840484048, "percentage": 62.74, "elapsed_time": "4:29:54", "remaining_time": "2:40:16", "throughput": 1486.49, "total_tokens": 24072736} {"current_steps": 114070, "total_steps": 181800, "loss": 0.0106, "lr": 1.83238975683247e-05, "epoch": 12.54895489548955, "percentage": 62.74, "elapsed_time": "4:29:55", "remaining_time": "2:40:15", "throughput": 1486.5, "total_tokens": 24073856} {"current_steps": 114075, "total_steps": 181800, "loss": 0.0095, "lr": 1.8321584691479833e-05, "epoch": 12.549504950495049, "percentage": 62.75, "elapsed_time": "4:29:55", "remaining_time": "2:40:15", "throughput": 1486.5, "total_tokens": 24074912} {"current_steps": 114080, "total_steps": 181800, "loss": 0.0114, "lr": 1.8319271876186723e-05, "epoch": 12.55005500550055, "percentage": 62.75, "elapsed_time": "4:29:56", "remaining_time": "2:40:14", "throughput": 1486.5, "total_tokens": 24075968} {"current_steps": 114085, "total_steps": 181800, "loss": 0.0308, "lr": 1.831695912246668e-05, "epoch": 12.55060506050605, "percentage": 62.75, "elapsed_time": "4:29:57", "remaining_time": "2:40:13", "throughput": 1486.5, "total_tokens": 24076992} {"current_steps": 114090, "total_steps": 181800, "loss": 0.0027, "lr": 1.831464643034101e-05, "epoch": 12.551155115511552, "percentage": 62.76, "elapsed_time": "4:29:57", "remaining_time": "2:40:13", "throughput": 1486.5, "total_tokens": 24077984} {"current_steps": 114095, "total_steps": 181800, "loss": 0.0015, "lr": 1.8312333799831045e-05, "epoch": 12.551705170517051, "percentage": 62.76, "elapsed_time": "4:29:58", "remaining_time": "2:40:12", "throughput": 1486.5, "total_tokens": 24079072} {"current_steps": 114100, "total_steps": 181800, "loss": 0.0257, "lr": 1.8310021230958085e-05, "epoch": 12.552255225522552, "percentage": 62.76, "elapsed_time": "4:29:59", "remaining_time": "2:40:11", "throughput": 1486.51, "total_tokens": 24080160} {"current_steps": 114105, "total_steps": 181800, "loss": 0.1063, "lr": 1.8307708723743446e-05, "epoch": 12.552805280528053, "percentage": 62.76, "elapsed_time": "4:29:59", "remaining_time": "2:40:10", "throughput": 1486.51, "total_tokens": 24081216} {"current_steps": 114110, "total_steps": 181800, "loss": 0.0706, "lr": 1.8305396278208454e-05, "epoch": 12.553355335533553, "percentage": 62.77, "elapsed_time": "4:30:00", "remaining_time": "2:40:10", "throughput": 1486.51, "total_tokens": 24082240} {"current_steps": 114115, "total_steps": 181800, "loss": 0.0603, "lr": 1.8303083894374392e-05, "epoch": 12.553905390539054, "percentage": 62.77, "elapsed_time": "4:30:01", "remaining_time": "2:40:09", "throughput": 1486.51, "total_tokens": 24083264} {"current_steps": 114120, "total_steps": 181800, "loss": 0.0384, "lr": 1.8300771572262615e-05, "epoch": 12.554455445544555, "percentage": 62.77, "elapsed_time": "4:30:01", "remaining_time": "2:40:08", "throughput": 1486.51, "total_tokens": 24084288} {"current_steps": 114125, "total_steps": 181800, "loss": 0.1024, "lr": 1.82984593118944e-05, "epoch": 12.555005500550054, "percentage": 62.78, "elapsed_time": "4:30:02", "remaining_time": "2:40:07", "throughput": 1486.51, "total_tokens": 24085344} {"current_steps": 114130, "total_steps": 181800, "loss": 0.0157, "lr": 1.8296147113291068e-05, "epoch": 12.555555555555555, "percentage": 62.78, "elapsed_time": "4:30:03", "remaining_time": "2:40:07", "throughput": 1486.51, "total_tokens": 24086400} {"current_steps": 114135, "total_steps": 181800, "loss": 0.1496, "lr": 1.8293834976473944e-05, "epoch": 12.556105610561056, "percentage": 62.78, "elapsed_time": "4:30:03", "remaining_time": "2:40:06", "throughput": 1486.51, "total_tokens": 24087424} {"current_steps": 114140, "total_steps": 181800, "loss": 0.0524, "lr": 1.829152290146431e-05, "epoch": 12.556655665566556, "percentage": 62.78, "elapsed_time": "4:30:04", "remaining_time": "2:40:05", "throughput": 1486.51, "total_tokens": 24088480} {"current_steps": 114145, "total_steps": 181800, "loss": 0.0833, "lr": 1.8289210888283498e-05, "epoch": 12.557205720572057, "percentage": 62.79, "elapsed_time": "4:30:05", "remaining_time": "2:40:05", "throughput": 1486.51, "total_tokens": 24089472} {"current_steps": 114150, "total_steps": 181800, "loss": 0.0862, "lr": 1.8286898936952817e-05, "epoch": 12.557755775577558, "percentage": 62.79, "elapsed_time": "4:30:06", "remaining_time": "2:40:04", "throughput": 1486.51, "total_tokens": 24090464} {"current_steps": 114155, "total_steps": 181800, "loss": 0.0061, "lr": 1.828458704749355e-05, "epoch": 12.558305830583059, "percentage": 62.79, "elapsed_time": "4:30:06", "remaining_time": "2:40:03", "throughput": 1486.51, "total_tokens": 24091456} {"current_steps": 114160, "total_steps": 181800, "loss": 0.0064, "lr": 1.8282275219927034e-05, "epoch": 12.558855885588558, "percentage": 62.79, "elapsed_time": "4:30:07", "remaining_time": "2:40:02", "throughput": 1486.51, "total_tokens": 24092544} {"current_steps": 114165, "total_steps": 181800, "loss": 0.0813, "lr": 1.8279963454274557e-05, "epoch": 12.55940594059406, "percentage": 62.8, "elapsed_time": "4:30:08", "remaining_time": "2:40:02", "throughput": 1486.51, "total_tokens": 24093536} {"current_steps": 114170, "total_steps": 181800, "loss": 0.0981, "lr": 1.827765175055744e-05, "epoch": 12.55995599559956, "percentage": 62.8, "elapsed_time": "4:30:08", "remaining_time": "2:40:01", "throughput": 1486.51, "total_tokens": 24094624} {"current_steps": 114175, "total_steps": 181800, "loss": 0.0912, "lr": 1.8275340108796978e-05, "epoch": 12.56050605060506, "percentage": 62.8, "elapsed_time": "4:30:09", "remaining_time": "2:40:00", "throughput": 1486.52, "total_tokens": 24095680} {"current_steps": 114180, "total_steps": 181800, "loss": 0.0034, "lr": 1.8273028529014474e-05, "epoch": 12.561056105610561, "percentage": 62.81, "elapsed_time": "4:30:10", "remaining_time": "2:40:00", "throughput": 1486.52, "total_tokens": 24096736} {"current_steps": 114185, "total_steps": 181800, "loss": 0.0039, "lr": 1.827071701123124e-05, "epoch": 12.561606160616062, "percentage": 62.81, "elapsed_time": "4:30:10", "remaining_time": "2:39:59", "throughput": 1486.52, "total_tokens": 24097728} {"current_steps": 114190, "total_steps": 181800, "loss": 0.0132, "lr": 1.8268405555468577e-05, "epoch": 12.562156215621561, "percentage": 62.81, "elapsed_time": "4:30:11", "remaining_time": "2:39:58", "throughput": 1486.52, "total_tokens": 24098816} {"current_steps": 114195, "total_steps": 181800, "loss": 0.0503, "lr": 1.82660941617478e-05, "epoch": 12.562706270627062, "percentage": 62.81, "elapsed_time": "4:30:12", "remaining_time": "2:39:57", "throughput": 1486.53, "total_tokens": 24099936} {"current_steps": 114200, "total_steps": 181800, "loss": 0.0634, "lr": 1.8263782830090195e-05, "epoch": 12.563256325632564, "percentage": 62.82, "elapsed_time": "4:30:12", "remaining_time": "2:39:57", "throughput": 1486.53, "total_tokens": 24101056} {"current_steps": 114205, "total_steps": 181800, "loss": 0.0064, "lr": 1.826147156051707e-05, "epoch": 12.563806380638063, "percentage": 62.82, "elapsed_time": "4:30:13", "remaining_time": "2:39:56", "throughput": 1486.53, "total_tokens": 24102112} {"current_steps": 114210, "total_steps": 181800, "loss": 0.0342, "lr": 1.8259160353049733e-05, "epoch": 12.564356435643564, "percentage": 62.82, "elapsed_time": "4:30:14", "remaining_time": "2:39:55", "throughput": 1486.53, "total_tokens": 24103136} {"current_steps": 114215, "total_steps": 181800, "loss": 0.065, "lr": 1.825684920770947e-05, "epoch": 12.564906490649065, "percentage": 62.82, "elapsed_time": "4:30:15", "remaining_time": "2:39:54", "throughput": 1486.54, "total_tokens": 24104192} {"current_steps": 114220, "total_steps": 181800, "loss": 0.0038, "lr": 1.82545381245176e-05, "epoch": 12.565456545654566, "percentage": 62.83, "elapsed_time": "4:30:15", "remaining_time": "2:39:54", "throughput": 1486.54, "total_tokens": 24105344} {"current_steps": 114225, "total_steps": 181800, "loss": 0.0068, "lr": 1.8252227103495424e-05, "epoch": 12.566006600660065, "percentage": 62.83, "elapsed_time": "4:30:16", "remaining_time": "2:39:53", "throughput": 1486.55, "total_tokens": 24106400} {"current_steps": 114230, "total_steps": 181800, "loss": 0.0017, "lr": 1.824991614466422e-05, "epoch": 12.566556655665567, "percentage": 62.83, "elapsed_time": "4:30:17", "remaining_time": "2:39:52", "throughput": 1486.55, "total_tokens": 24107456} {"current_steps": 114235, "total_steps": 181800, "loss": 0.0428, "lr": 1.8247605248045303e-05, "epoch": 12.567106710671068, "percentage": 62.84, "elapsed_time": "4:30:17", "remaining_time": "2:39:52", "throughput": 1486.55, "total_tokens": 24108576} {"current_steps": 114240, "total_steps": 181800, "loss": 0.0446, "lr": 1.8245294413659964e-05, "epoch": 12.567656765676567, "percentage": 62.84, "elapsed_time": "4:30:18", "remaining_time": "2:39:51", "throughput": 1486.55, "total_tokens": 24109600} {"current_steps": 114245, "total_steps": 181800, "loss": 0.0044, "lr": 1.8242983641529508e-05, "epoch": 12.568206820682068, "percentage": 62.84, "elapsed_time": "4:30:19", "remaining_time": "2:39:50", "throughput": 1486.56, "total_tokens": 24110656} {"current_steps": 114250, "total_steps": 181800, "loss": 0.0102, "lr": 1.824067293167524e-05, "epoch": 12.56875687568757, "percentage": 62.84, "elapsed_time": "4:30:19", "remaining_time": "2:39:49", "throughput": 1486.56, "total_tokens": 24111712} {"current_steps": 114255, "total_steps": 181800, "loss": 0.0161, "lr": 1.8238362284118433e-05, "epoch": 12.569306930693068, "percentage": 62.85, "elapsed_time": "4:30:20", "remaining_time": "2:39:49", "throughput": 1486.56, "total_tokens": 24112832} {"current_steps": 114260, "total_steps": 181800, "loss": 0.061, "lr": 1.82360516988804e-05, "epoch": 12.56985698569857, "percentage": 62.85, "elapsed_time": "4:30:21", "remaining_time": "2:39:48", "throughput": 1486.56, "total_tokens": 24113888} {"current_steps": 114265, "total_steps": 181800, "loss": 0.0314, "lr": 1.8233741175982428e-05, "epoch": 12.57040704070407, "percentage": 62.85, "elapsed_time": "4:30:21", "remaining_time": "2:39:47", "throughput": 1486.57, "total_tokens": 24115008} {"current_steps": 114270, "total_steps": 181800, "loss": 0.0724, "lr": 1.823143071544583e-05, "epoch": 12.570957095709572, "percentage": 62.85, "elapsed_time": "4:30:22", "remaining_time": "2:39:47", "throughput": 1486.57, "total_tokens": 24116032} {"current_steps": 114275, "total_steps": 181800, "loss": 0.075, "lr": 1.8229120317291877e-05, "epoch": 12.571507150715071, "percentage": 62.86, "elapsed_time": "4:30:23", "remaining_time": "2:39:46", "throughput": 1486.57, "total_tokens": 24117088} {"current_steps": 114280, "total_steps": 181800, "loss": 0.0093, "lr": 1.8226809981541872e-05, "epoch": 12.572057205720572, "percentage": 62.86, "elapsed_time": "4:30:23", "remaining_time": "2:39:45", "throughput": 1486.57, "total_tokens": 24118112} {"current_steps": 114285, "total_steps": 181800, "loss": 0.0112, "lr": 1.8224499708217117e-05, "epoch": 12.572607260726073, "percentage": 62.86, "elapsed_time": "4:30:24", "remaining_time": "2:39:44", "throughput": 1486.57, "total_tokens": 24119168} {"current_steps": 114290, "total_steps": 181800, "loss": 0.1433, "lr": 1.8222189497338895e-05, "epoch": 12.573157315731573, "percentage": 62.87, "elapsed_time": "4:30:25", "remaining_time": "2:39:44", "throughput": 1486.57, "total_tokens": 24120160} {"current_steps": 114295, "total_steps": 181800, "loss": 0.0011, "lr": 1.821987934892849e-05, "epoch": 12.573707370737074, "percentage": 62.87, "elapsed_time": "4:30:26", "remaining_time": "2:39:43", "throughput": 1486.58, "total_tokens": 24121248} {"current_steps": 114300, "total_steps": 181800, "loss": 0.0388, "lr": 1.821756926300722e-05, "epoch": 12.574257425742575, "percentage": 62.87, "elapsed_time": "4:30:26", "remaining_time": "2:39:42", "throughput": 1486.57, "total_tokens": 24122240} {"current_steps": 114305, "total_steps": 181800, "loss": 0.0149, "lr": 1.8215259239596343e-05, "epoch": 12.574807480748074, "percentage": 62.87, "elapsed_time": "4:30:27", "remaining_time": "2:39:42", "throughput": 1486.58, "total_tokens": 24123360} {"current_steps": 114310, "total_steps": 181800, "loss": 0.0052, "lr": 1.8212949278717178e-05, "epoch": 12.575357535753575, "percentage": 62.88, "elapsed_time": "4:30:28", "remaining_time": "2:39:41", "throughput": 1486.58, "total_tokens": 24124448} {"current_steps": 114315, "total_steps": 181800, "loss": 0.0635, "lr": 1.8210639380391002e-05, "epoch": 12.575907590759076, "percentage": 62.88, "elapsed_time": "4:30:28", "remaining_time": "2:39:40", "throughput": 1486.59, "total_tokens": 24125568} {"current_steps": 114320, "total_steps": 181800, "loss": 0.0051, "lr": 1.8208329544639098e-05, "epoch": 12.576457645764577, "percentage": 62.88, "elapsed_time": "4:30:29", "remaining_time": "2:39:39", "throughput": 1486.59, "total_tokens": 24126624} {"current_steps": 114325, "total_steps": 181800, "loss": 0.0718, "lr": 1.8206019771482772e-05, "epoch": 12.577007700770077, "percentage": 62.89, "elapsed_time": "4:30:30", "remaining_time": "2:39:39", "throughput": 1486.59, "total_tokens": 24127648} {"current_steps": 114330, "total_steps": 181800, "loss": 0.0117, "lr": 1.820371006094329e-05, "epoch": 12.577557755775578, "percentage": 62.89, "elapsed_time": "4:30:30", "remaining_time": "2:39:38", "throughput": 1486.59, "total_tokens": 24128736} {"current_steps": 114335, "total_steps": 181800, "loss": 0.045, "lr": 1.8201400413041957e-05, "epoch": 12.578107810781079, "percentage": 62.89, "elapsed_time": "4:30:31", "remaining_time": "2:39:37", "throughput": 1486.59, "total_tokens": 24129728} {"current_steps": 114340, "total_steps": 181800, "loss": 0.0207, "lr": 1.8199090827800057e-05, "epoch": 12.578657865786578, "percentage": 62.89, "elapsed_time": "4:30:32", "remaining_time": "2:39:36", "throughput": 1486.6, "total_tokens": 24130816} {"current_steps": 114345, "total_steps": 181800, "loss": 0.0216, "lr": 1.819678130523887e-05, "epoch": 12.57920792079208, "percentage": 62.9, "elapsed_time": "4:30:32", "remaining_time": "2:39:36", "throughput": 1486.6, "total_tokens": 24131840} {"current_steps": 114350, "total_steps": 181800, "loss": 0.0482, "lr": 1.8194471845379685e-05, "epoch": 12.57975797579758, "percentage": 62.9, "elapsed_time": "4:30:33", "remaining_time": "2:39:35", "throughput": 1486.6, "total_tokens": 24132896} {"current_steps": 114355, "total_steps": 181800, "loss": 0.0093, "lr": 1.8192162448243782e-05, "epoch": 12.58030803080308, "percentage": 62.9, "elapsed_time": "4:30:34", "remaining_time": "2:39:34", "throughput": 1486.6, "total_tokens": 24133952} {"current_steps": 114360, "total_steps": 181800, "loss": 0.0061, "lr": 1.8189853113852458e-05, "epoch": 12.58085808580858, "percentage": 62.9, "elapsed_time": "4:30:35", "remaining_time": "2:39:34", "throughput": 1486.6, "total_tokens": 24135008} {"current_steps": 114365, "total_steps": 181800, "loss": 0.0098, "lr": 1.8187543842226993e-05, "epoch": 12.581408140814082, "percentage": 62.91, "elapsed_time": "4:30:35", "remaining_time": "2:39:33", "throughput": 1486.61, "total_tokens": 24136128} {"current_steps": 114370, "total_steps": 181800, "loss": 0.0209, "lr": 1.818523463338866e-05, "epoch": 12.581958195819581, "percentage": 62.91, "elapsed_time": "4:30:36", "remaining_time": "2:39:32", "throughput": 1486.61, "total_tokens": 24137216} {"current_steps": 114375, "total_steps": 181800, "loss": 0.0024, "lr": 1.818292548735875e-05, "epoch": 12.582508250825082, "percentage": 62.91, "elapsed_time": "4:30:37", "remaining_time": "2:39:31", "throughput": 1486.61, "total_tokens": 24138208} {"current_steps": 114380, "total_steps": 181800, "loss": 0.0028, "lr": 1.8180616404158546e-05, "epoch": 12.583058305830583, "percentage": 62.92, "elapsed_time": "4:30:37", "remaining_time": "2:39:31", "throughput": 1486.61, "total_tokens": 24139264} {"current_steps": 114385, "total_steps": 181800, "loss": 0.0119, "lr": 1.8178307383809335e-05, "epoch": 12.583608360836084, "percentage": 62.92, "elapsed_time": "4:30:38", "remaining_time": "2:39:30", "throughput": 1486.61, "total_tokens": 24140288} {"current_steps": 114390, "total_steps": 181800, "loss": 0.0065, "lr": 1.8175998426332385e-05, "epoch": 12.584158415841584, "percentage": 62.92, "elapsed_time": "4:30:39", "remaining_time": "2:39:29", "throughput": 1486.62, "total_tokens": 24141408} {"current_steps": 114395, "total_steps": 181800, "loss": 0.0028, "lr": 1.8173689531748977e-05, "epoch": 12.584708470847085, "percentage": 62.92, "elapsed_time": "4:30:39", "remaining_time": "2:39:29", "throughput": 1486.62, "total_tokens": 24142464} {"current_steps": 114400, "total_steps": 181800, "loss": 0.0016, "lr": 1.817138070008041e-05, "epoch": 12.585258525852586, "percentage": 62.93, "elapsed_time": "4:30:40", "remaining_time": "2:39:28", "throughput": 1486.62, "total_tokens": 24143488} {"current_steps": 114405, "total_steps": 181800, "loss": 0.0575, "lr": 1.816907193134794e-05, "epoch": 12.585808580858085, "percentage": 62.93, "elapsed_time": "4:30:41", "remaining_time": "2:39:27", "throughput": 1486.62, "total_tokens": 24144608} {"current_steps": 114410, "total_steps": 181800, "loss": 0.008, "lr": 1.8166763225572862e-05, "epoch": 12.586358635863586, "percentage": 62.93, "elapsed_time": "4:30:41", "remaining_time": "2:39:26", "throughput": 1486.63, "total_tokens": 24145728} {"current_steps": 114415, "total_steps": 181800, "loss": 0.0027, "lr": 1.816445458277645e-05, "epoch": 12.586908690869087, "percentage": 62.93, "elapsed_time": "4:30:42", "remaining_time": "2:39:26", "throughput": 1486.63, "total_tokens": 24146720} {"current_steps": 114420, "total_steps": 181800, "loss": 0.0044, "lr": 1.816214600297997e-05, "epoch": 12.587458745874587, "percentage": 62.94, "elapsed_time": "4:30:43", "remaining_time": "2:39:25", "throughput": 1486.63, "total_tokens": 24147776} {"current_steps": 114425, "total_steps": 181800, "loss": 0.007, "lr": 1.815983748620472e-05, "epoch": 12.588008800880088, "percentage": 62.94, "elapsed_time": "4:30:43", "remaining_time": "2:39:24", "throughput": 1486.63, "total_tokens": 24148864} {"current_steps": 114430, "total_steps": 181800, "loss": 0.0308, "lr": 1.815752903247196e-05, "epoch": 12.588558855885589, "percentage": 62.94, "elapsed_time": "4:30:44", "remaining_time": "2:39:23", "throughput": 1486.63, "total_tokens": 24149888} {"current_steps": 114435, "total_steps": 181800, "loss": 0.0672, "lr": 1.8155220641802973e-05, "epoch": 12.589108910891088, "percentage": 62.95, "elapsed_time": "4:30:45", "remaining_time": "2:39:23", "throughput": 1486.63, "total_tokens": 24150880} {"current_steps": 114440, "total_steps": 181800, "loss": 0.1027, "lr": 1.815291231421904e-05, "epoch": 12.58965896589659, "percentage": 62.95, "elapsed_time": "4:30:46", "remaining_time": "2:39:22", "throughput": 1486.63, "total_tokens": 24151968} {"current_steps": 114445, "total_steps": 181800, "loss": 0.1016, "lr": 1.8150604049741417e-05, "epoch": 12.59020902090209, "percentage": 62.95, "elapsed_time": "4:30:46", "remaining_time": "2:39:21", "throughput": 1486.63, "total_tokens": 24152992} {"current_steps": 114450, "total_steps": 181800, "loss": 0.0665, "lr": 1.8148295848391395e-05, "epoch": 12.590759075907592, "percentage": 62.95, "elapsed_time": "4:30:47", "remaining_time": "2:39:21", "throughput": 1486.64, "total_tokens": 24154080} {"current_steps": 114455, "total_steps": 181800, "loss": 0.0817, "lr": 1.8145987710190238e-05, "epoch": 12.591309130913091, "percentage": 62.96, "elapsed_time": "4:30:48", "remaining_time": "2:39:20", "throughput": 1486.64, "total_tokens": 24155136} {"current_steps": 114460, "total_steps": 181800, "loss": 0.0075, "lr": 1.8143679635159232e-05, "epoch": 12.591859185918592, "percentage": 62.96, "elapsed_time": "4:30:48", "remaining_time": "2:39:19", "throughput": 1486.64, "total_tokens": 24156224} {"current_steps": 114465, "total_steps": 181800, "loss": 0.0859, "lr": 1.814137162331964e-05, "epoch": 12.592409240924093, "percentage": 62.96, "elapsed_time": "4:30:49", "remaining_time": "2:39:18", "throughput": 1486.65, "total_tokens": 24157344} {"current_steps": 114470, "total_steps": 181800, "loss": 0.0018, "lr": 1.8139063674692723e-05, "epoch": 12.592959295929592, "percentage": 62.96, "elapsed_time": "4:30:50", "remaining_time": "2:39:18", "throughput": 1486.65, "total_tokens": 24158400} {"current_steps": 114475, "total_steps": 181800, "loss": 0.001, "lr": 1.813675578929978e-05, "epoch": 12.593509350935093, "percentage": 62.97, "elapsed_time": "4:30:50", "remaining_time": "2:39:17", "throughput": 1486.65, "total_tokens": 24159456} {"current_steps": 114480, "total_steps": 181800, "loss": 0.0529, "lr": 1.813444796716205e-05, "epoch": 12.594059405940595, "percentage": 62.97, "elapsed_time": "4:30:51", "remaining_time": "2:39:16", "throughput": 1486.65, "total_tokens": 24160480} {"current_steps": 114485, "total_steps": 181800, "loss": 0.0815, "lr": 1.813214020830083e-05, "epoch": 12.594609460946094, "percentage": 62.97, "elapsed_time": "4:30:52", "remaining_time": "2:39:16", "throughput": 1486.66, "total_tokens": 24161536} {"current_steps": 114490, "total_steps": 181800, "loss": 0.0688, "lr": 1.8129832512737376e-05, "epoch": 12.595159515951595, "percentage": 62.98, "elapsed_time": "4:30:52", "remaining_time": "2:39:15", "throughput": 1486.66, "total_tokens": 24162624} {"current_steps": 114495, "total_steps": 181800, "loss": 0.0021, "lr": 1.8127524880492952e-05, "epoch": 12.595709570957096, "percentage": 62.98, "elapsed_time": "4:30:53", "remaining_time": "2:39:14", "throughput": 1486.66, "total_tokens": 24163680} {"current_steps": 114500, "total_steps": 181800, "loss": 0.083, "lr": 1.8125217311588846e-05, "epoch": 12.596259625962595, "percentage": 62.98, "elapsed_time": "4:30:54", "remaining_time": "2:39:13", "throughput": 1486.66, "total_tokens": 24164672} {"current_steps": 114505, "total_steps": 181800, "loss": 0.0065, "lr": 1.8122909806046307e-05, "epoch": 12.596809680968097, "percentage": 62.98, "elapsed_time": "4:30:55", "remaining_time": "2:39:13", "throughput": 1486.66, "total_tokens": 24165696} {"current_steps": 114510, "total_steps": 181800, "loss": 0.0039, "lr": 1.81206023638866e-05, "epoch": 12.597359735973598, "percentage": 62.99, "elapsed_time": "4:30:55", "remaining_time": "2:39:12", "throughput": 1486.66, "total_tokens": 24166784} {"current_steps": 114515, "total_steps": 181800, "loss": 0.0225, "lr": 1.811829498513102e-05, "epoch": 12.597909790979099, "percentage": 62.99, "elapsed_time": "4:30:56", "remaining_time": "2:39:11", "throughput": 1486.67, "total_tokens": 24167872} {"current_steps": 114520, "total_steps": 181800, "loss": 0.037, "lr": 1.8115987669800795e-05, "epoch": 12.598459845984598, "percentage": 62.99, "elapsed_time": "4:30:57", "remaining_time": "2:39:10", "throughput": 1486.67, "total_tokens": 24168960} {"current_steps": 114525, "total_steps": 181800, "loss": 0.0539, "lr": 1.811368041791721e-05, "epoch": 12.599009900990099, "percentage": 63.0, "elapsed_time": "4:30:57", "remaining_time": "2:39:10", "throughput": 1486.67, "total_tokens": 24169952} {"current_steps": 114530, "total_steps": 181800, "loss": 0.0019, "lr": 1.8111373229501538e-05, "epoch": 12.5995599559956, "percentage": 63.0, "elapsed_time": "4:30:58", "remaining_time": "2:39:09", "throughput": 1486.67, "total_tokens": 24171008} {"current_steps": 114535, "total_steps": 181800, "loss": 0.0231, "lr": 1.8109066104575023e-05, "epoch": 12.6001100110011, "percentage": 63.0, "elapsed_time": "4:30:59", "remaining_time": "2:39:08", "throughput": 1486.68, "total_tokens": 24172160} {"current_steps": 114540, "total_steps": 181800, "loss": 0.0066, "lr": 1.8106759043158943e-05, "epoch": 12.6006600660066, "percentage": 63.0, "elapsed_time": "4:30:59", "remaining_time": "2:39:08", "throughput": 1486.68, "total_tokens": 24173216} {"current_steps": 114545, "total_steps": 181800, "loss": 0.0042, "lr": 1.8104452045274556e-05, "epoch": 12.601210121012102, "percentage": 63.01, "elapsed_time": "4:31:00", "remaining_time": "2:39:07", "throughput": 1486.68, "total_tokens": 24174272} {"current_steps": 114550, "total_steps": 181800, "loss": 0.0086, "lr": 1.810214511094313e-05, "epoch": 12.601760176017601, "percentage": 63.01, "elapsed_time": "4:31:01", "remaining_time": "2:39:06", "throughput": 1486.68, "total_tokens": 24175360} {"current_steps": 114555, "total_steps": 181800, "loss": 0.0568, "lr": 1.8099838240185923e-05, "epoch": 12.602310231023102, "percentage": 63.01, "elapsed_time": "4:31:01", "remaining_time": "2:39:05", "throughput": 1486.69, "total_tokens": 24176448} {"current_steps": 114560, "total_steps": 181800, "loss": 0.0129, "lr": 1.809753143302419e-05, "epoch": 12.602860286028603, "percentage": 63.01, "elapsed_time": "4:31:02", "remaining_time": "2:39:05", "throughput": 1486.69, "total_tokens": 24177504} {"current_steps": 114565, "total_steps": 181800, "loss": 0.0079, "lr": 1.80952246894792e-05, "epoch": 12.603410341034103, "percentage": 63.02, "elapsed_time": "4:31:03", "remaining_time": "2:39:04", "throughput": 1486.69, "total_tokens": 24178560} {"current_steps": 114570, "total_steps": 181800, "loss": 0.0101, "lr": 1.8092918009572208e-05, "epoch": 12.603960396039604, "percentage": 63.02, "elapsed_time": "4:31:04", "remaining_time": "2:39:03", "throughput": 1486.69, "total_tokens": 24179616} {"current_steps": 114575, "total_steps": 181800, "loss": 0.0295, "lr": 1.8090611393324485e-05, "epoch": 12.604510451045105, "percentage": 63.02, "elapsed_time": "4:31:04", "remaining_time": "2:39:03", "throughput": 1486.7, "total_tokens": 24180768} {"current_steps": 114580, "total_steps": 181800, "loss": 0.0487, "lr": 1.8088304840757275e-05, "epoch": 12.605060506050606, "percentage": 63.03, "elapsed_time": "4:31:05", "remaining_time": "2:39:02", "throughput": 1486.7, "total_tokens": 24181856} {"current_steps": 114585, "total_steps": 181800, "loss": 0.0012, "lr": 1.8085998351891842e-05, "epoch": 12.605610561056105, "percentage": 63.03, "elapsed_time": "4:31:06", "remaining_time": "2:39:01", "throughput": 1486.7, "total_tokens": 24182880} {"current_steps": 114590, "total_steps": 181800, "loss": 0.0686, "lr": 1.808369192674945e-05, "epoch": 12.606160616061606, "percentage": 63.03, "elapsed_time": "4:31:06", "remaining_time": "2:39:00", "throughput": 1486.7, "total_tokens": 24183904} {"current_steps": 114595, "total_steps": 181800, "loss": 0.1085, "lr": 1.8081385565351343e-05, "epoch": 12.606710671067107, "percentage": 63.03, "elapsed_time": "4:31:07", "remaining_time": "2:39:00", "throughput": 1486.71, "total_tokens": 24184992} {"current_steps": 114600, "total_steps": 181800, "loss": 0.0387, "lr": 1.807907926771879e-05, "epoch": 12.607260726072607, "percentage": 63.04, "elapsed_time": "4:31:08", "remaining_time": "2:38:59", "throughput": 1486.71, "total_tokens": 24186080} {"current_steps": 114605, "total_steps": 181800, "loss": 0.1355, "lr": 1.8076773033873046e-05, "epoch": 12.607810781078108, "percentage": 63.04, "elapsed_time": "4:31:08", "remaining_time": "2:38:58", "throughput": 1486.71, "total_tokens": 24187136} {"current_steps": 114610, "total_steps": 181800, "loss": 0.0045, "lr": 1.8074466863835355e-05, "epoch": 12.608360836083609, "percentage": 63.04, "elapsed_time": "4:31:09", "remaining_time": "2:38:58", "throughput": 1486.71, "total_tokens": 24188192} {"current_steps": 114615, "total_steps": 181800, "loss": 0.002, "lr": 1.8072160757626987e-05, "epoch": 12.608910891089108, "percentage": 63.04, "elapsed_time": "4:31:10", "remaining_time": "2:38:57", "throughput": 1486.71, "total_tokens": 24189216} {"current_steps": 114620, "total_steps": 181800, "loss": 0.0297, "lr": 1.806985471526918e-05, "epoch": 12.60946094609461, "percentage": 63.05, "elapsed_time": "4:31:10", "remaining_time": "2:38:56", "throughput": 1486.72, "total_tokens": 24190272} {"current_steps": 114625, "total_steps": 181800, "loss": 0.0041, "lr": 1.8067548736783204e-05, "epoch": 12.61001100110011, "percentage": 63.05, "elapsed_time": "4:31:11", "remaining_time": "2:38:55", "throughput": 1486.72, "total_tokens": 24191328} {"current_steps": 114630, "total_steps": 181800, "loss": 0.023, "lr": 1.806524282219031e-05, "epoch": 12.61056105610561, "percentage": 63.05, "elapsed_time": "4:31:12", "remaining_time": "2:38:55", "throughput": 1486.72, "total_tokens": 24192384} {"current_steps": 114635, "total_steps": 181800, "loss": 0.0077, "lr": 1.8062936971511735e-05, "epoch": 12.61111111111111, "percentage": 63.06, "elapsed_time": "4:31:13", "remaining_time": "2:38:54", "throughput": 1486.72, "total_tokens": 24193440} {"current_steps": 114640, "total_steps": 181800, "loss": 0.0044, "lr": 1.8060631184768744e-05, "epoch": 12.611661166116612, "percentage": 63.06, "elapsed_time": "4:31:13", "remaining_time": "2:38:53", "throughput": 1486.73, "total_tokens": 24194528} {"current_steps": 114645, "total_steps": 181800, "loss": 0.0168, "lr": 1.8058325461982582e-05, "epoch": 12.612211221122113, "percentage": 63.06, "elapsed_time": "4:31:14", "remaining_time": "2:38:52", "throughput": 1486.73, "total_tokens": 24195616} {"current_steps": 114650, "total_steps": 181800, "loss": 0.0084, "lr": 1.8056019803174513e-05, "epoch": 12.612761276127612, "percentage": 63.06, "elapsed_time": "4:31:15", "remaining_time": "2:38:52", "throughput": 1486.73, "total_tokens": 24196704} {"current_steps": 114655, "total_steps": 181800, "loss": 0.0104, "lr": 1.8053714208365773e-05, "epoch": 12.613311331133113, "percentage": 63.07, "elapsed_time": "4:31:15", "remaining_time": "2:38:51", "throughput": 1486.73, "total_tokens": 24197760} {"current_steps": 114660, "total_steps": 181800, "loss": 0.0317, "lr": 1.805140867757761e-05, "epoch": 12.613861386138614, "percentage": 63.07, "elapsed_time": "4:31:16", "remaining_time": "2:38:50", "throughput": 1486.74, "total_tokens": 24198784} {"current_steps": 114665, "total_steps": 181800, "loss": 0.0017, "lr": 1.804910321083128e-05, "epoch": 12.614411441144114, "percentage": 63.07, "elapsed_time": "4:31:17", "remaining_time": "2:38:50", "throughput": 1486.74, "total_tokens": 24199872} {"current_steps": 114670, "total_steps": 181800, "loss": 0.01, "lr": 1.804679780814803e-05, "epoch": 12.614961496149615, "percentage": 63.07, "elapsed_time": "4:31:17", "remaining_time": "2:38:49", "throughput": 1486.75, "total_tokens": 24201024} {"current_steps": 114675, "total_steps": 181800, "loss": 0.0065, "lr": 1.804449246954912e-05, "epoch": 12.615511551155116, "percentage": 63.08, "elapsed_time": "4:31:18", "remaining_time": "2:38:48", "throughput": 1486.75, "total_tokens": 24202112} {"current_steps": 114680, "total_steps": 181800, "loss": 0.0082, "lr": 1.8042187195055776e-05, "epoch": 12.616061606160617, "percentage": 63.08, "elapsed_time": "4:31:19", "remaining_time": "2:38:47", "throughput": 1486.75, "total_tokens": 24203200} {"current_steps": 114685, "total_steps": 181800, "loss": 0.0419, "lr": 1.8039881984689253e-05, "epoch": 12.616611661166116, "percentage": 63.08, "elapsed_time": "4:31:19", "remaining_time": "2:38:47", "throughput": 1486.75, "total_tokens": 24204224} {"current_steps": 114690, "total_steps": 181800, "loss": 0.015, "lr": 1.803757683847081e-05, "epoch": 12.617161716171617, "percentage": 63.09, "elapsed_time": "4:31:20", "remaining_time": "2:38:46", "throughput": 1486.76, "total_tokens": 24205312} {"current_steps": 114695, "total_steps": 181800, "loss": 0.0048, "lr": 1.8035271756421666e-05, "epoch": 12.617711771177119, "percentage": 63.09, "elapsed_time": "4:31:21", "remaining_time": "2:38:45", "throughput": 1486.76, "total_tokens": 24206432} {"current_steps": 114700, "total_steps": 181800, "loss": 0.1352, "lr": 1.8032966738563086e-05, "epoch": 12.618261826182618, "percentage": 63.09, "elapsed_time": "4:31:21", "remaining_time": "2:38:45", "throughput": 1486.77, "total_tokens": 24207520} {"current_steps": 114705, "total_steps": 181800, "loss": 0.0557, "lr": 1.8030661784916308e-05, "epoch": 12.618811881188119, "percentage": 63.09, "elapsed_time": "4:31:22", "remaining_time": "2:38:44", "throughput": 1486.77, "total_tokens": 24208576} {"current_steps": 114710, "total_steps": 181800, "loss": 0.1141, "lr": 1.8028356895502573e-05, "epoch": 12.61936193619362, "percentage": 63.1, "elapsed_time": "4:31:23", "remaining_time": "2:38:43", "throughput": 1486.77, "total_tokens": 24209696} {"current_steps": 114715, "total_steps": 181800, "loss": 0.0309, "lr": 1.802605207034313e-05, "epoch": 12.61991199119912, "percentage": 63.1, "elapsed_time": "4:31:24", "remaining_time": "2:38:42", "throughput": 1486.76, "total_tokens": 24210752} {"current_steps": 114720, "total_steps": 181800, "loss": 0.0281, "lr": 1.8023747309459225e-05, "epoch": 12.62046204620462, "percentage": 63.1, "elapsed_time": "4:31:24", "remaining_time": "2:38:42", "throughput": 1486.75, "total_tokens": 24211712} {"current_steps": 114725, "total_steps": 181800, "loss": 0.0028, "lr": 1.8021442612872076e-05, "epoch": 12.621012101210122, "percentage": 63.11, "elapsed_time": "4:31:25", "remaining_time": "2:38:41", "throughput": 1486.76, "total_tokens": 24212832} {"current_steps": 114730, "total_steps": 181800, "loss": 0.0033, "lr": 1.801913798060296e-05, "epoch": 12.62156215621562, "percentage": 63.11, "elapsed_time": "4:31:26", "remaining_time": "2:38:40", "throughput": 1486.76, "total_tokens": 24213920} {"current_steps": 114735, "total_steps": 181800, "loss": 0.0037, "lr": 1.8016833412673087e-05, "epoch": 12.622112211221122, "percentage": 63.11, "elapsed_time": "4:31:27", "remaining_time": "2:38:40", "throughput": 1486.76, "total_tokens": 24214944} {"current_steps": 114740, "total_steps": 181800, "loss": 0.0151, "lr": 1.8014528909103716e-05, "epoch": 12.622662266226623, "percentage": 63.11, "elapsed_time": "4:31:27", "remaining_time": "2:38:39", "throughput": 1486.76, "total_tokens": 24215936} {"current_steps": 114745, "total_steps": 181800, "loss": 0.0027, "lr": 1.8012224469916084e-05, "epoch": 12.623212321232124, "percentage": 63.12, "elapsed_time": "4:31:28", "remaining_time": "2:38:38", "throughput": 1486.77, "total_tokens": 24217024} {"current_steps": 114750, "total_steps": 181800, "loss": 0.007, "lr": 1.8009920095131415e-05, "epoch": 12.623762376237623, "percentage": 63.12, "elapsed_time": "4:31:29", "remaining_time": "2:38:37", "throughput": 1486.77, "total_tokens": 24218048} {"current_steps": 114755, "total_steps": 181800, "loss": 0.0055, "lr": 1.8007615784770965e-05, "epoch": 12.624312431243125, "percentage": 63.12, "elapsed_time": "4:31:29", "remaining_time": "2:38:37", "throughput": 1486.77, "total_tokens": 24219072} {"current_steps": 114760, "total_steps": 181800, "loss": 0.0975, "lr": 1.8005311538855963e-05, "epoch": 12.624862486248626, "percentage": 63.12, "elapsed_time": "4:31:30", "remaining_time": "2:38:36", "throughput": 1486.77, "total_tokens": 24220160} {"current_steps": 114765, "total_steps": 181800, "loss": 0.0068, "lr": 1.8003007357407652e-05, "epoch": 12.625412541254125, "percentage": 63.13, "elapsed_time": "4:31:31", "remaining_time": "2:38:35", "throughput": 1486.77, "total_tokens": 24221248} {"current_steps": 114770, "total_steps": 181800, "loss": 0.0021, "lr": 1.8000703240447263e-05, "epoch": 12.625962596259626, "percentage": 63.13, "elapsed_time": "4:31:31", "remaining_time": "2:38:35", "throughput": 1486.78, "total_tokens": 24222304} {"current_steps": 114775, "total_steps": 181800, "loss": 0.0025, "lr": 1.799839918799603e-05, "epoch": 12.626512651265127, "percentage": 63.13, "elapsed_time": "4:31:32", "remaining_time": "2:38:34", "throughput": 1486.78, "total_tokens": 24223328} {"current_steps": 114780, "total_steps": 181800, "loss": 0.0704, "lr": 1.79960952000752e-05, "epoch": 12.627062706270626, "percentage": 63.14, "elapsed_time": "4:31:33", "remaining_time": "2:38:33", "throughput": 1486.78, "total_tokens": 24224416} {"current_steps": 114785, "total_steps": 181800, "loss": 0.0053, "lr": 1.7993791276705985e-05, "epoch": 12.627612761276128, "percentage": 63.14, "elapsed_time": "4:31:33", "remaining_time": "2:38:32", "throughput": 1486.78, "total_tokens": 24225472} {"current_steps": 114790, "total_steps": 181800, "loss": 0.0089, "lr": 1.7991487417909647e-05, "epoch": 12.628162816281629, "percentage": 63.14, "elapsed_time": "4:31:34", "remaining_time": "2:38:32", "throughput": 1486.79, "total_tokens": 24226560} {"current_steps": 114795, "total_steps": 181800, "loss": 0.0221, "lr": 1.7989183623707406e-05, "epoch": 12.628712871287128, "percentage": 63.14, "elapsed_time": "4:31:35", "remaining_time": "2:38:31", "throughput": 1486.79, "total_tokens": 24227648} {"current_steps": 114800, "total_steps": 181800, "loss": 0.0731, "lr": 1.7986879894120486e-05, "epoch": 12.629262926292629, "percentage": 63.15, "elapsed_time": "4:31:35", "remaining_time": "2:38:30", "throughput": 1486.79, "total_tokens": 24228672} {"current_steps": 114805, "total_steps": 181800, "loss": 0.0943, "lr": 1.7984576229170142e-05, "epoch": 12.62981298129813, "percentage": 63.15, "elapsed_time": "4:31:36", "remaining_time": "2:38:29", "throughput": 1486.79, "total_tokens": 24229664} {"current_steps": 114810, "total_steps": 181800, "loss": 0.0375, "lr": 1.798227262887758e-05, "epoch": 12.630363036303631, "percentage": 63.15, "elapsed_time": "4:31:37", "remaining_time": "2:38:29", "throughput": 1486.79, "total_tokens": 24230720} {"current_steps": 114815, "total_steps": 181800, "loss": 0.0032, "lr": 1.7979969093264053e-05, "epoch": 12.63091309130913, "percentage": 63.15, "elapsed_time": "4:31:38", "remaining_time": "2:38:28", "throughput": 1486.79, "total_tokens": 24231776} {"current_steps": 114820, "total_steps": 181800, "loss": 0.0045, "lr": 1.797766562235078e-05, "epoch": 12.631463146314632, "percentage": 63.16, "elapsed_time": "4:31:38", "remaining_time": "2:38:27", "throughput": 1486.8, "total_tokens": 24232832} {"current_steps": 114825, "total_steps": 181800, "loss": 0.0783, "lr": 1.7975362216158993e-05, "epoch": 12.632013201320133, "percentage": 63.16, "elapsed_time": "4:31:39", "remaining_time": "2:38:27", "throughput": 1486.8, "total_tokens": 24233888} {"current_steps": 114830, "total_steps": 181800, "loss": 0.0032, "lr": 1.797305887470992e-05, "epoch": 12.632563256325632, "percentage": 63.16, "elapsed_time": "4:31:40", "remaining_time": "2:38:26", "throughput": 1486.8, "total_tokens": 24234944} {"current_steps": 114835, "total_steps": 181800, "loss": 0.0515, "lr": 1.7970755598024784e-05, "epoch": 12.633113311331133, "percentage": 63.17, "elapsed_time": "4:31:40", "remaining_time": "2:38:25", "throughput": 1486.8, "total_tokens": 24236032} {"current_steps": 114840, "total_steps": 181800, "loss": 0.009, "lr": 1.7968452386124836e-05, "epoch": 12.633663366336634, "percentage": 63.17, "elapsed_time": "4:31:41", "remaining_time": "2:38:24", "throughput": 1486.81, "total_tokens": 24237152} {"current_steps": 114845, "total_steps": 181800, "loss": 0.0076, "lr": 1.7966149239031283e-05, "epoch": 12.634213421342134, "percentage": 63.17, "elapsed_time": "4:31:42", "remaining_time": "2:38:24", "throughput": 1486.81, "total_tokens": 24238208} {"current_steps": 114850, "total_steps": 181800, "loss": 0.1149, "lr": 1.7963846156765353e-05, "epoch": 12.634763476347635, "percentage": 63.17, "elapsed_time": "4:31:42", "remaining_time": "2:38:23", "throughput": 1486.81, "total_tokens": 24239264} {"current_steps": 114855, "total_steps": 181800, "loss": 0.0022, "lr": 1.796154313934828e-05, "epoch": 12.635313531353136, "percentage": 63.18, "elapsed_time": "4:31:43", "remaining_time": "2:38:22", "throughput": 1486.82, "total_tokens": 24240320} {"current_steps": 114860, "total_steps": 181800, "loss": 0.0052, "lr": 1.795924018680128e-05, "epoch": 12.635863586358635, "percentage": 63.18, "elapsed_time": "4:31:44", "remaining_time": "2:38:22", "throughput": 1486.81, "total_tokens": 24241280} {"current_steps": 114865, "total_steps": 181800, "loss": 0.0403, "lr": 1.7956937299145595e-05, "epoch": 12.636413641364136, "percentage": 63.18, "elapsed_time": "4:31:44", "remaining_time": "2:38:21", "throughput": 1486.82, "total_tokens": 24242368} {"current_steps": 114870, "total_steps": 181800, "loss": 0.01, "lr": 1.7954634476402438e-05, "epoch": 12.636963696369637, "percentage": 63.18, "elapsed_time": "4:31:45", "remaining_time": "2:38:20", "throughput": 1486.82, "total_tokens": 24243456} {"current_steps": 114875, "total_steps": 181800, "loss": 0.0353, "lr": 1.7952331718593024e-05, "epoch": 12.637513751375138, "percentage": 63.19, "elapsed_time": "4:31:46", "remaining_time": "2:38:19", "throughput": 1486.82, "total_tokens": 24244544} {"current_steps": 114880, "total_steps": 181800, "loss": 0.017, "lr": 1.7950029025738602e-05, "epoch": 12.638063806380638, "percentage": 63.19, "elapsed_time": "4:31:46", "remaining_time": "2:38:19", "throughput": 1486.83, "total_tokens": 24245632} {"current_steps": 114885, "total_steps": 181800, "loss": 0.0035, "lr": 1.794772639786037e-05, "epoch": 12.638613861386139, "percentage": 63.19, "elapsed_time": "4:31:47", "remaining_time": "2:38:18", "throughput": 1486.83, "total_tokens": 24246624} {"current_steps": 114890, "total_steps": 181800, "loss": 0.0116, "lr": 1.794542383497956e-05, "epoch": 12.63916391639164, "percentage": 63.2, "elapsed_time": "4:31:48", "remaining_time": "2:38:17", "throughput": 1486.83, "total_tokens": 24247648} {"current_steps": 114895, "total_steps": 181800, "loss": 0.0503, "lr": 1.7943121337117397e-05, "epoch": 12.63971397139714, "percentage": 63.2, "elapsed_time": "4:31:49", "remaining_time": "2:38:16", "throughput": 1486.82, "total_tokens": 24248640} {"current_steps": 114900, "total_steps": 181800, "loss": 0.0229, "lr": 1.7940818904295094e-05, "epoch": 12.64026402640264, "percentage": 63.2, "elapsed_time": "4:31:49", "remaining_time": "2:38:16", "throughput": 1486.83, "total_tokens": 24249760} {"current_steps": 114905, "total_steps": 181800, "loss": 0.0071, "lr": 1.7938516536533876e-05, "epoch": 12.640814081408141, "percentage": 63.2, "elapsed_time": "4:31:50", "remaining_time": "2:38:15", "throughput": 1486.83, "total_tokens": 24250784} {"current_steps": 114910, "total_steps": 181800, "loss": 0.0034, "lr": 1.7936214233854966e-05, "epoch": 12.64136413641364, "percentage": 63.21, "elapsed_time": "4:31:51", "remaining_time": "2:38:14", "throughput": 1486.83, "total_tokens": 24251840} {"current_steps": 114915, "total_steps": 181800, "loss": 0.0176, "lr": 1.7933911996279574e-05, "epoch": 12.641914191419142, "percentage": 63.21, "elapsed_time": "4:31:51", "remaining_time": "2:38:14", "throughput": 1486.83, "total_tokens": 24252864} {"current_steps": 114920, "total_steps": 181800, "loss": 0.0164, "lr": 1.793160982382893e-05, "epoch": 12.642464246424643, "percentage": 63.21, "elapsed_time": "4:31:52", "remaining_time": "2:38:13", "throughput": 1486.84, "total_tokens": 24253984} {"current_steps": 114925, "total_steps": 181800, "loss": 0.1025, "lr": 1.7929307716524246e-05, "epoch": 12.643014301430142, "percentage": 63.22, "elapsed_time": "4:31:53", "remaining_time": "2:38:12", "throughput": 1486.84, "total_tokens": 24255072} {"current_steps": 114930, "total_steps": 181800, "loss": 0.069, "lr": 1.7927005674386738e-05, "epoch": 12.643564356435643, "percentage": 63.22, "elapsed_time": "4:31:53", "remaining_time": "2:38:11", "throughput": 1486.84, "total_tokens": 24256064} {"current_steps": 114935, "total_steps": 181800, "loss": 0.0068, "lr": 1.7924703697437635e-05, "epoch": 12.644114411441144, "percentage": 63.22, "elapsed_time": "4:31:54", "remaining_time": "2:38:11", "throughput": 1486.84, "total_tokens": 24257088} {"current_steps": 114940, "total_steps": 181800, "loss": 0.1696, "lr": 1.792240178569813e-05, "epoch": 12.644664466446645, "percentage": 63.22, "elapsed_time": "4:31:55", "remaining_time": "2:38:10", "throughput": 1486.84, "total_tokens": 24258208} {"current_steps": 114945, "total_steps": 181800, "loss": 0.0923, "lr": 1.7920099939189453e-05, "epoch": 12.645214521452145, "percentage": 63.23, "elapsed_time": "4:31:55", "remaining_time": "2:38:09", "throughput": 1486.84, "total_tokens": 24259232} {"current_steps": 114950, "total_steps": 181800, "loss": 0.0354, "lr": 1.7917798157932814e-05, "epoch": 12.645764576457646, "percentage": 63.23, "elapsed_time": "4:31:56", "remaining_time": "2:38:09", "throughput": 1486.84, "total_tokens": 24260288} {"current_steps": 114955, "total_steps": 181800, "loss": 0.008, "lr": 1.7915496441949446e-05, "epoch": 12.646314631463147, "percentage": 63.23, "elapsed_time": "4:31:57", "remaining_time": "2:38:08", "throughput": 1486.85, "total_tokens": 24261344} {"current_steps": 114960, "total_steps": 181800, "loss": 0.0392, "lr": 1.791319479126054e-05, "epoch": 12.646864686468646, "percentage": 63.23, "elapsed_time": "4:31:58", "remaining_time": "2:38:07", "throughput": 1486.84, "total_tokens": 24262336} {"current_steps": 114965, "total_steps": 181800, "loss": 0.0486, "lr": 1.7910893205887308e-05, "epoch": 12.647414741474147, "percentage": 63.24, "elapsed_time": "4:31:58", "remaining_time": "2:38:06", "throughput": 1486.85, "total_tokens": 24263456} {"current_steps": 114970, "total_steps": 181800, "loss": 0.0064, "lr": 1.7908591685850985e-05, "epoch": 12.647964796479648, "percentage": 63.24, "elapsed_time": "4:31:59", "remaining_time": "2:38:06", "throughput": 1486.85, "total_tokens": 24264480} {"current_steps": 114975, "total_steps": 181800, "loss": 0.0176, "lr": 1.7906290231172758e-05, "epoch": 12.648514851485148, "percentage": 63.24, "elapsed_time": "4:32:00", "remaining_time": "2:38:05", "throughput": 1486.85, "total_tokens": 24265536} {"current_steps": 114980, "total_steps": 181800, "loss": 0.0063, "lr": 1.7903988841873863e-05, "epoch": 12.649064906490649, "percentage": 63.25, "elapsed_time": "4:32:00", "remaining_time": "2:38:04", "throughput": 1486.85, "total_tokens": 24266592} {"current_steps": 114985, "total_steps": 181800, "loss": 0.0365, "lr": 1.790168751797549e-05, "epoch": 12.64961496149615, "percentage": 63.25, "elapsed_time": "4:32:01", "remaining_time": "2:38:04", "throughput": 1486.85, "total_tokens": 24267584} {"current_steps": 114990, "total_steps": 181800, "loss": 0.0023, "lr": 1.7899386259498852e-05, "epoch": 12.65016501650165, "percentage": 63.25, "elapsed_time": "4:32:02", "remaining_time": "2:38:03", "throughput": 1486.85, "total_tokens": 24268640} {"current_steps": 114995, "total_steps": 181800, "loss": 0.0066, "lr": 1.789708506646518e-05, "epoch": 12.65071507150715, "percentage": 63.25, "elapsed_time": "4:32:02", "remaining_time": "2:38:02", "throughput": 1486.85, "total_tokens": 24269632} {"current_steps": 115000, "total_steps": 181800, "loss": 0.1238, "lr": 1.789478393889565e-05, "epoch": 12.651265126512651, "percentage": 63.26, "elapsed_time": "4:32:03", "remaining_time": "2:38:01", "throughput": 1486.85, "total_tokens": 24270688} {"current_steps": 115005, "total_steps": 181800, "loss": 0.0084, "lr": 1.7892482876811494e-05, "epoch": 12.651815181518153, "percentage": 63.26, "elapsed_time": "4:32:04", "remaining_time": "2:38:01", "throughput": 1486.86, "total_tokens": 24271776} {"current_steps": 115010, "total_steps": 181800, "loss": 0.0102, "lr": 1.789018188023392e-05, "epoch": 12.652365236523652, "percentage": 63.26, "elapsed_time": "4:32:04", "remaining_time": "2:38:00", "throughput": 1486.86, "total_tokens": 24272832} {"current_steps": 115015, "total_steps": 181800, "loss": 0.0023, "lr": 1.788788094918411e-05, "epoch": 12.652915291529153, "percentage": 63.26, "elapsed_time": "4:32:05", "remaining_time": "2:37:59", "throughput": 1486.86, "total_tokens": 24273888} {"current_steps": 115020, "total_steps": 181800, "loss": 0.014, "lr": 1.78855800836833e-05, "epoch": 12.653465346534654, "percentage": 63.27, "elapsed_time": "4:32:06", "remaining_time": "2:37:58", "throughput": 1486.86, "total_tokens": 24274976} {"current_steps": 115025, "total_steps": 181800, "loss": 0.0034, "lr": 1.788327928375268e-05, "epoch": 12.654015401540153, "percentage": 63.27, "elapsed_time": "4:32:06", "remaining_time": "2:37:58", "throughput": 1486.86, "total_tokens": 24275968} {"current_steps": 115030, "total_steps": 181800, "loss": 0.1155, "lr": 1.7880978549413464e-05, "epoch": 12.654565456545654, "percentage": 63.27, "elapsed_time": "4:32:07", "remaining_time": "2:37:57", "throughput": 1486.86, "total_tokens": 24276960} {"current_steps": 115035, "total_steps": 181800, "loss": 0.0178, "lr": 1.7878677880686863e-05, "epoch": 12.655115511551156, "percentage": 63.28, "elapsed_time": "4:32:08", "remaining_time": "2:37:56", "throughput": 1486.86, "total_tokens": 24277952} {"current_steps": 115040, "total_steps": 181800, "loss": 0.0018, "lr": 1.7876377277594053e-05, "epoch": 12.655665566556655, "percentage": 63.28, "elapsed_time": "4:32:09", "remaining_time": "2:37:56", "throughput": 1486.86, "total_tokens": 24279008} {"current_steps": 115045, "total_steps": 181800, "loss": 0.0678, "lr": 1.787407674015626e-05, "epoch": 12.656215621562156, "percentage": 63.28, "elapsed_time": "4:32:09", "remaining_time": "2:37:55", "throughput": 1486.86, "total_tokens": 24280000} {"current_steps": 115050, "total_steps": 181800, "loss": 0.007, "lr": 1.787177626839468e-05, "epoch": 12.656765676567657, "percentage": 63.28, "elapsed_time": "4:32:10", "remaining_time": "2:37:54", "throughput": 1486.86, "total_tokens": 24281024} {"current_steps": 115055, "total_steps": 181800, "loss": 0.0073, "lr": 1.7869475862330532e-05, "epoch": 12.657315731573158, "percentage": 63.29, "elapsed_time": "4:32:11", "remaining_time": "2:37:53", "throughput": 1486.86, "total_tokens": 24282080} {"current_steps": 115060, "total_steps": 181800, "loss": 0.0308, "lr": 1.786717552198499e-05, "epoch": 12.657865786578657, "percentage": 63.29, "elapsed_time": "4:32:11", "remaining_time": "2:37:53", "throughput": 1486.86, "total_tokens": 24283136} {"current_steps": 115065, "total_steps": 181800, "loss": 0.0128, "lr": 1.786487524737927e-05, "epoch": 12.658415841584159, "percentage": 63.29, "elapsed_time": "4:32:12", "remaining_time": "2:37:52", "throughput": 1486.86, "total_tokens": 24284160} {"current_steps": 115070, "total_steps": 181800, "loss": 0.0672, "lr": 1.786257503853458e-05, "epoch": 12.65896589658966, "percentage": 63.29, "elapsed_time": "4:32:13", "remaining_time": "2:37:51", "throughput": 1486.87, "total_tokens": 24285248} {"current_steps": 115075, "total_steps": 181800, "loss": 0.0841, "lr": 1.7860274895472103e-05, "epoch": 12.659515951595159, "percentage": 63.3, "elapsed_time": "4:32:13", "remaining_time": "2:37:51", "throughput": 1486.87, "total_tokens": 24286272} {"current_steps": 115080, "total_steps": 181800, "loss": 0.0044, "lr": 1.7857974818213044e-05, "epoch": 12.66006600660066, "percentage": 63.3, "elapsed_time": "4:32:14", "remaining_time": "2:37:50", "throughput": 1486.86, "total_tokens": 24287264} {"current_steps": 115085, "total_steps": 181800, "loss": 0.0361, "lr": 1.7855674806778612e-05, "epoch": 12.660616061606161, "percentage": 63.3, "elapsed_time": "4:32:15", "remaining_time": "2:37:49", "throughput": 1486.87, "total_tokens": 24288352} {"current_steps": 115090, "total_steps": 181800, "loss": 0.0012, "lr": 1.7853374861189988e-05, "epoch": 12.66116611661166, "percentage": 63.31, "elapsed_time": "4:32:15", "remaining_time": "2:37:48", "throughput": 1486.87, "total_tokens": 24289408} {"current_steps": 115095, "total_steps": 181800, "loss": 0.0133, "lr": 1.7851074981468384e-05, "epoch": 12.661716171617162, "percentage": 63.31, "elapsed_time": "4:32:16", "remaining_time": "2:37:48", "throughput": 1486.87, "total_tokens": 24290400} {"current_steps": 115100, "total_steps": 181800, "loss": 0.0079, "lr": 1.7848775167634992e-05, "epoch": 12.662266226622663, "percentage": 63.31, "elapsed_time": "4:32:17", "remaining_time": "2:37:47", "throughput": 1486.87, "total_tokens": 24291520} {"current_steps": 115105, "total_steps": 181800, "loss": 0.0015, "lr": 1.7846475419711003e-05, "epoch": 12.662816281628164, "percentage": 63.31, "elapsed_time": "4:32:18", "remaining_time": "2:37:46", "throughput": 1486.88, "total_tokens": 24292640} {"current_steps": 115110, "total_steps": 181800, "loss": 0.0048, "lr": 1.784417573771763e-05, "epoch": 12.663366336633663, "percentage": 63.32, "elapsed_time": "4:32:18", "remaining_time": "2:37:45", "throughput": 1486.88, "total_tokens": 24293696} {"current_steps": 115115, "total_steps": 181800, "loss": 0.0408, "lr": 1.784187612167604e-05, "epoch": 12.663916391639164, "percentage": 63.32, "elapsed_time": "4:32:19", "remaining_time": "2:37:45", "throughput": 1486.89, "total_tokens": 24294816} {"current_steps": 115120, "total_steps": 181800, "loss": 0.0137, "lr": 1.783957657160745e-05, "epoch": 12.664466446644665, "percentage": 63.32, "elapsed_time": "4:32:20", "remaining_time": "2:37:44", "throughput": 1486.89, "total_tokens": 24295872} {"current_steps": 115125, "total_steps": 181800, "loss": 0.0018, "lr": 1.7837277087533052e-05, "epoch": 12.665016501650165, "percentage": 63.33, "elapsed_time": "4:32:20", "remaining_time": "2:37:43", "throughput": 1486.89, "total_tokens": 24296896} {"current_steps": 115130, "total_steps": 181800, "loss": 0.0007, "lr": 1.7834977669474023e-05, "epoch": 12.665566556655666, "percentage": 63.33, "elapsed_time": "4:32:21", "remaining_time": "2:37:43", "throughput": 1486.89, "total_tokens": 24297920} {"current_steps": 115135, "total_steps": 181800, "loss": 0.0022, "lr": 1.7832678317451573e-05, "epoch": 12.666116611661167, "percentage": 63.33, "elapsed_time": "4:32:22", "remaining_time": "2:37:42", "throughput": 1486.89, "total_tokens": 24299008} {"current_steps": 115140, "total_steps": 181800, "loss": 0.0011, "lr": 1.783037903148688e-05, "epoch": 12.666666666666666, "percentage": 63.33, "elapsed_time": "4:32:22", "remaining_time": "2:37:41", "throughput": 1486.89, "total_tokens": 24300032} {"current_steps": 115145, "total_steps": 181800, "loss": 0.204, "lr": 1.7828079811601155e-05, "epoch": 12.667216721672167, "percentage": 63.34, "elapsed_time": "4:32:23", "remaining_time": "2:37:40", "throughput": 1486.89, "total_tokens": 24301088} {"current_steps": 115150, "total_steps": 181800, "loss": 0.003, "lr": 1.782578065781558e-05, "epoch": 12.667766776677668, "percentage": 63.34, "elapsed_time": "4:32:24", "remaining_time": "2:37:40", "throughput": 1486.9, "total_tokens": 24302304} {"current_steps": 115155, "total_steps": 181800, "loss": 0.015, "lr": 1.782348157015133e-05, "epoch": 12.668316831683168, "percentage": 63.34, "elapsed_time": "4:32:24", "remaining_time": "2:37:39", "throughput": 1486.91, "total_tokens": 24303360} {"current_steps": 115160, "total_steps": 181800, "loss": 0.0184, "lr": 1.782118254862961e-05, "epoch": 12.668866886688669, "percentage": 63.34, "elapsed_time": "4:32:25", "remaining_time": "2:37:38", "throughput": 1486.91, "total_tokens": 24304384} {"current_steps": 115165, "total_steps": 181800, "loss": 0.0074, "lr": 1.78188835932716e-05, "epoch": 12.66941694169417, "percentage": 63.35, "elapsed_time": "4:32:26", "remaining_time": "2:37:38", "throughput": 1486.91, "total_tokens": 24305408} {"current_steps": 115170, "total_steps": 181800, "loss": 0.0045, "lr": 1.7816584704098507e-05, "epoch": 12.66996699669967, "percentage": 63.35, "elapsed_time": "4:32:26", "remaining_time": "2:37:37", "throughput": 1486.91, "total_tokens": 24306432} {"current_steps": 115175, "total_steps": 181800, "loss": 0.0655, "lr": 1.78142858811315e-05, "epoch": 12.67051705170517, "percentage": 63.35, "elapsed_time": "4:32:27", "remaining_time": "2:37:36", "throughput": 1486.9, "total_tokens": 24307424} {"current_steps": 115180, "total_steps": 181800, "loss": 0.0048, "lr": 1.7811987124391768e-05, "epoch": 12.671067106710671, "percentage": 63.36, "elapsed_time": "4:32:28", "remaining_time": "2:37:35", "throughput": 1486.9, "total_tokens": 24308448} {"current_steps": 115185, "total_steps": 181800, "loss": 0.0993, "lr": 1.7809688433900512e-05, "epoch": 12.671617161716172, "percentage": 63.36, "elapsed_time": "4:32:29", "remaining_time": "2:37:35", "throughput": 1486.9, "total_tokens": 24309440} {"current_steps": 115190, "total_steps": 181800, "loss": 0.1025, "lr": 1.7807389809678894e-05, "epoch": 12.672167216721672, "percentage": 63.36, "elapsed_time": "4:32:29", "remaining_time": "2:37:34", "throughput": 1486.9, "total_tokens": 24310528} {"current_steps": 115195, "total_steps": 181800, "loss": 0.0427, "lr": 1.780509125174812e-05, "epoch": 12.672717271727173, "percentage": 63.36, "elapsed_time": "4:32:30", "remaining_time": "2:37:33", "throughput": 1486.91, "total_tokens": 24311584} {"current_steps": 115200, "total_steps": 181800, "loss": 0.0054, "lr": 1.7802792760129372e-05, "epoch": 12.673267326732674, "percentage": 63.37, "elapsed_time": "4:32:31", "remaining_time": "2:37:33", "throughput": 1486.91, "total_tokens": 24312640} {"current_steps": 115205, "total_steps": 181800, "loss": 0.0068, "lr": 1.7800494334843813e-05, "epoch": 12.673817381738173, "percentage": 63.37, "elapsed_time": "4:32:31", "remaining_time": "2:37:32", "throughput": 1486.91, "total_tokens": 24313696} {"current_steps": 115210, "total_steps": 181800, "loss": 0.0046, "lr": 1.7798195975912664e-05, "epoch": 12.674367436743674, "percentage": 63.37, "elapsed_time": "4:32:32", "remaining_time": "2:37:31", "throughput": 1486.92, "total_tokens": 24314816} {"current_steps": 115215, "total_steps": 181800, "loss": 0.0027, "lr": 1.779589768335707e-05, "epoch": 12.674917491749175, "percentage": 63.37, "elapsed_time": "4:32:33", "remaining_time": "2:37:30", "throughput": 1486.92, "total_tokens": 24315840} {"current_steps": 115220, "total_steps": 181800, "loss": 0.0122, "lr": 1.779359945719824e-05, "epoch": 12.675467546754675, "percentage": 63.38, "elapsed_time": "4:32:33", "remaining_time": "2:37:30", "throughput": 1486.92, "total_tokens": 24316864} {"current_steps": 115225, "total_steps": 181800, "loss": 0.0717, "lr": 1.7791301297457354e-05, "epoch": 12.676017601760176, "percentage": 63.38, "elapsed_time": "4:32:34", "remaining_time": "2:37:29", "throughput": 1486.92, "total_tokens": 24317920} {"current_steps": 115230, "total_steps": 181800, "loss": 0.0504, "lr": 1.7789003204155567e-05, "epoch": 12.676567656765677, "percentage": 63.38, "elapsed_time": "4:32:35", "remaining_time": "2:37:28", "throughput": 1486.92, "total_tokens": 24318944} {"current_steps": 115235, "total_steps": 181800, "loss": 0.0347, "lr": 1.7786705177314083e-05, "epoch": 12.677117711771178, "percentage": 63.39, "elapsed_time": "4:32:35", "remaining_time": "2:37:27", "throughput": 1486.92, "total_tokens": 24320032} {"current_steps": 115240, "total_steps": 181800, "loss": 0.0529, "lr": 1.7784407216954074e-05, "epoch": 12.677667766776677, "percentage": 63.39, "elapsed_time": "4:32:36", "remaining_time": "2:37:27", "throughput": 1486.92, "total_tokens": 24321056} {"current_steps": 115245, "total_steps": 181800, "loss": 0.0017, "lr": 1.7782109323096728e-05, "epoch": 12.678217821782178, "percentage": 63.39, "elapsed_time": "4:32:37", "remaining_time": "2:37:26", "throughput": 1486.92, "total_tokens": 24322016} {"current_steps": 115250, "total_steps": 181800, "loss": 0.0031, "lr": 1.777981149576322e-05, "epoch": 12.67876787678768, "percentage": 63.39, "elapsed_time": "4:32:38", "remaining_time": "2:37:25", "throughput": 1486.92, "total_tokens": 24323072} {"current_steps": 115255, "total_steps": 181800, "loss": 0.0218, "lr": 1.7777513734974713e-05, "epoch": 12.679317931793179, "percentage": 63.4, "elapsed_time": "4:32:38", "remaining_time": "2:37:25", "throughput": 1486.92, "total_tokens": 24324096} {"current_steps": 115260, "total_steps": 181800, "loss": 0.0021, "lr": 1.7775216040752408e-05, "epoch": 12.67986798679868, "percentage": 63.4, "elapsed_time": "4:32:39", "remaining_time": "2:37:24", "throughput": 1486.92, "total_tokens": 24325184} {"current_steps": 115265, "total_steps": 181800, "loss": 0.0178, "lr": 1.7772918413117463e-05, "epoch": 12.680418041804181, "percentage": 63.4, "elapsed_time": "4:32:40", "remaining_time": "2:37:23", "throughput": 1486.93, "total_tokens": 24326272} {"current_steps": 115270, "total_steps": 181800, "loss": 0.0136, "lr": 1.777062085209106e-05, "epoch": 12.68096809680968, "percentage": 63.4, "elapsed_time": "4:32:40", "remaining_time": "2:37:22", "throughput": 1486.93, "total_tokens": 24327328} {"current_steps": 115275, "total_steps": 181800, "loss": 0.0098, "lr": 1.7768323357694377e-05, "epoch": 12.681518151815181, "percentage": 63.41, "elapsed_time": "4:32:41", "remaining_time": "2:37:22", "throughput": 1486.93, "total_tokens": 24328288} {"current_steps": 115280, "total_steps": 181800, "loss": 0.0145, "lr": 1.7766025929948583e-05, "epoch": 12.682068206820682, "percentage": 63.41, "elapsed_time": "4:32:42", "remaining_time": "2:37:21", "throughput": 1486.93, "total_tokens": 24329344} {"current_steps": 115285, "total_steps": 181800, "loss": 0.003, "lr": 1.776372856887487e-05, "epoch": 12.682618261826182, "percentage": 63.41, "elapsed_time": "4:32:42", "remaining_time": "2:37:20", "throughput": 1486.93, "total_tokens": 24330368} {"current_steps": 115290, "total_steps": 181800, "loss": 0.0914, "lr": 1.776143127449439e-05, "epoch": 12.683168316831683, "percentage": 63.42, "elapsed_time": "4:32:43", "remaining_time": "2:37:20", "throughput": 1486.93, "total_tokens": 24331424} {"current_steps": 115295, "total_steps": 181800, "loss": 0.0401, "lr": 1.775913404682832e-05, "epoch": 12.683718371837184, "percentage": 63.42, "elapsed_time": "4:32:44", "remaining_time": "2:37:19", "throughput": 1486.93, "total_tokens": 24332480} {"current_steps": 115300, "total_steps": 181800, "loss": 0.064, "lr": 1.775683688589785e-05, "epoch": 12.684268426842685, "percentage": 63.42, "elapsed_time": "4:32:44", "remaining_time": "2:37:18", "throughput": 1486.93, "total_tokens": 24333536} {"current_steps": 115305, "total_steps": 181800, "loss": 0.0044, "lr": 1.7754539791724123e-05, "epoch": 12.684818481848184, "percentage": 63.42, "elapsed_time": "4:32:45", "remaining_time": "2:37:17", "throughput": 1486.94, "total_tokens": 24334624} {"current_steps": 115310, "total_steps": 181800, "loss": 0.0015, "lr": 1.7752242764328336e-05, "epoch": 12.685368536853685, "percentage": 63.43, "elapsed_time": "4:32:46", "remaining_time": "2:37:17", "throughput": 1486.93, "total_tokens": 24335616} {"current_steps": 115315, "total_steps": 181800, "loss": 0.0029, "lr": 1.7749945803731655e-05, "epoch": 12.685918591859187, "percentage": 63.43, "elapsed_time": "4:32:46", "remaining_time": "2:37:16", "throughput": 1486.94, "total_tokens": 24336672} {"current_steps": 115320, "total_steps": 181800, "loss": 0.0041, "lr": 1.774764890995523e-05, "epoch": 12.686468646864686, "percentage": 63.43, "elapsed_time": "4:32:47", "remaining_time": "2:37:15", "throughput": 1486.94, "total_tokens": 24337792} {"current_steps": 115325, "total_steps": 181800, "loss": 0.0015, "lr": 1.7745352083020254e-05, "epoch": 12.687018701870187, "percentage": 63.44, "elapsed_time": "4:32:48", "remaining_time": "2:37:14", "throughput": 1486.95, "total_tokens": 24338976} {"current_steps": 115330, "total_steps": 181800, "loss": 0.001, "lr": 1.774305532294788e-05, "epoch": 12.687568756875688, "percentage": 63.44, "elapsed_time": "4:32:49", "remaining_time": "2:37:14", "throughput": 1486.95, "total_tokens": 24340000} {"current_steps": 115335, "total_steps": 181800, "loss": 0.0055, "lr": 1.7740758629759286e-05, "epoch": 12.688118811881187, "percentage": 63.44, "elapsed_time": "4:32:49", "remaining_time": "2:37:13", "throughput": 1486.95, "total_tokens": 24340992} {"current_steps": 115340, "total_steps": 181800, "loss": 0.0026, "lr": 1.7738462003475646e-05, "epoch": 12.688668866886688, "percentage": 63.44, "elapsed_time": "4:32:50", "remaining_time": "2:37:12", "throughput": 1486.95, "total_tokens": 24342080} {"current_steps": 115345, "total_steps": 181800, "loss": 0.0016, "lr": 1.7736165444118103e-05, "epoch": 12.68921892189219, "percentage": 63.45, "elapsed_time": "4:32:51", "remaining_time": "2:37:12", "throughput": 1486.96, "total_tokens": 24343104} {"current_steps": 115350, "total_steps": 181800, "loss": 0.0009, "lr": 1.7733868951707845e-05, "epoch": 12.689768976897689, "percentage": 63.45, "elapsed_time": "4:32:51", "remaining_time": "2:37:11", "throughput": 1486.96, "total_tokens": 24344160} {"current_steps": 115355, "total_steps": 181800, "loss": 0.0046, "lr": 1.7731572526266027e-05, "epoch": 12.69031903190319, "percentage": 63.45, "elapsed_time": "4:32:52", "remaining_time": "2:37:10", "throughput": 1486.96, "total_tokens": 24345248} {"current_steps": 115360, "total_steps": 181800, "loss": 0.0029, "lr": 1.7729276167813823e-05, "epoch": 12.690869086908691, "percentage": 63.45, "elapsed_time": "4:32:53", "remaining_time": "2:37:09", "throughput": 1486.96, "total_tokens": 24346304} {"current_steps": 115365, "total_steps": 181800, "loss": 0.0019, "lr": 1.772697987637239e-05, "epoch": 12.691419141914192, "percentage": 63.46, "elapsed_time": "4:32:53", "remaining_time": "2:37:09", "throughput": 1486.96, "total_tokens": 24347296} {"current_steps": 115370, "total_steps": 181800, "loss": 0.0156, "lr": 1.7724683651962886e-05, "epoch": 12.691969196919691, "percentage": 63.46, "elapsed_time": "4:32:54", "remaining_time": "2:37:08", "throughput": 1486.96, "total_tokens": 24348320} {"current_steps": 115375, "total_steps": 181800, "loss": 0.0019, "lr": 1.7722387494606495e-05, "epoch": 12.692519251925193, "percentage": 63.46, "elapsed_time": "4:32:55", "remaining_time": "2:37:07", "throughput": 1486.97, "total_tokens": 24349408} {"current_steps": 115380, "total_steps": 181800, "loss": 0.1277, "lr": 1.7720091404324352e-05, "epoch": 12.693069306930694, "percentage": 63.47, "elapsed_time": "4:32:55", "remaining_time": "2:37:07", "throughput": 1486.97, "total_tokens": 24350496} {"current_steps": 115385, "total_steps": 181800, "loss": 0.1119, "lr": 1.771779538113764e-05, "epoch": 12.693619361936193, "percentage": 63.47, "elapsed_time": "4:32:56", "remaining_time": "2:37:06", "throughput": 1486.97, "total_tokens": 24351488} {"current_steps": 115390, "total_steps": 181800, "loss": 0.0144, "lr": 1.7715499425067517e-05, "epoch": 12.694169416941694, "percentage": 63.47, "elapsed_time": "4:32:57", "remaining_time": "2:37:05", "throughput": 1486.97, "total_tokens": 24352576} {"current_steps": 115395, "total_steps": 181800, "loss": 0.0048, "lr": 1.771320353613513e-05, "epoch": 12.694719471947195, "percentage": 63.47, "elapsed_time": "4:32:57", "remaining_time": "2:37:04", "throughput": 1486.97, "total_tokens": 24353600} {"current_steps": 115400, "total_steps": 181800, "loss": 0.0215, "lr": 1.7710907714361664e-05, "epoch": 12.695269526952695, "percentage": 63.48, "elapsed_time": "4:32:58", "remaining_time": "2:37:04", "throughput": 1486.97, "total_tokens": 24354624} {"current_steps": 115405, "total_steps": 181800, "loss": 0.016, "lr": 1.770861195976825e-05, "epoch": 12.695819581958196, "percentage": 63.48, "elapsed_time": "4:32:59", "remaining_time": "2:37:03", "throughput": 1486.97, "total_tokens": 24355680} {"current_steps": 115410, "total_steps": 181800, "loss": 0.0953, "lr": 1.770631627237607e-05, "epoch": 12.696369636963697, "percentage": 63.48, "elapsed_time": "4:33:00", "remaining_time": "2:37:02", "throughput": 1486.97, "total_tokens": 24356704} {"current_steps": 115415, "total_steps": 181800, "loss": 0.1028, "lr": 1.7704020652206276e-05, "epoch": 12.696919691969196, "percentage": 63.48, "elapsed_time": "4:33:00", "remaining_time": "2:37:01", "throughput": 1486.97, "total_tokens": 24357760} {"current_steps": 115420, "total_steps": 181800, "loss": 0.0209, "lr": 1.7701725099280015e-05, "epoch": 12.697469746974697, "percentage": 63.49, "elapsed_time": "4:33:01", "remaining_time": "2:37:01", "throughput": 1486.97, "total_tokens": 24358720} {"current_steps": 115425, "total_steps": 181800, "loss": 0.0014, "lr": 1.769942961361845e-05, "epoch": 12.698019801980198, "percentage": 63.49, "elapsed_time": "4:33:02", "remaining_time": "2:37:00", "throughput": 1486.97, "total_tokens": 24359808} {"current_steps": 115430, "total_steps": 181800, "loss": 0.0045, "lr": 1.769713419524274e-05, "epoch": 12.6985698569857, "percentage": 63.49, "elapsed_time": "4:33:02", "remaining_time": "2:36:59", "throughput": 1486.98, "total_tokens": 24360960} {"current_steps": 115435, "total_steps": 181800, "loss": 0.0016, "lr": 1.769483884417405e-05, "epoch": 12.699119911991199, "percentage": 63.5, "elapsed_time": "4:33:03", "remaining_time": "2:36:59", "throughput": 1486.98, "total_tokens": 24361984} {"current_steps": 115440, "total_steps": 181800, "loss": 0.0617, "lr": 1.7692543560433517e-05, "epoch": 12.6996699669967, "percentage": 63.5, "elapsed_time": "4:33:04", "remaining_time": "2:36:58", "throughput": 1486.98, "total_tokens": 24363008} {"current_steps": 115445, "total_steps": 181800, "loss": 0.0061, "lr": 1.76902483440423e-05, "epoch": 12.7002200220022, "percentage": 63.5, "elapsed_time": "4:33:04", "remaining_time": "2:36:57", "throughput": 1486.98, "total_tokens": 24364000} {"current_steps": 115450, "total_steps": 181800, "loss": 0.0075, "lr": 1.7687953195021563e-05, "epoch": 12.7007700770077, "percentage": 63.5, "elapsed_time": "4:33:05", "remaining_time": "2:36:56", "throughput": 1486.98, "total_tokens": 24365056} {"current_steps": 115455, "total_steps": 181800, "loss": 0.0069, "lr": 1.7685658113392457e-05, "epoch": 12.701320132013201, "percentage": 63.51, "elapsed_time": "4:33:06", "remaining_time": "2:36:56", "throughput": 1486.98, "total_tokens": 24366112} {"current_steps": 115460, "total_steps": 181800, "loss": 0.0481, "lr": 1.7683363099176116e-05, "epoch": 12.701870187018702, "percentage": 63.51, "elapsed_time": "4:33:06", "remaining_time": "2:36:55", "throughput": 1486.99, "total_tokens": 24367264} {"current_steps": 115465, "total_steps": 181800, "loss": 0.0027, "lr": 1.7681068152393714e-05, "epoch": 12.702420242024202, "percentage": 63.51, "elapsed_time": "4:33:07", "remaining_time": "2:36:54", "throughput": 1487.0, "total_tokens": 24368384} {"current_steps": 115470, "total_steps": 181800, "loss": 0.0385, "lr": 1.7678773273066394e-05, "epoch": 12.702970297029703, "percentage": 63.51, "elapsed_time": "4:33:08", "remaining_time": "2:36:54", "throughput": 1487.0, "total_tokens": 24369472} {"current_steps": 115475, "total_steps": 181800, "loss": 0.0117, "lr": 1.7676478461215314e-05, "epoch": 12.703520352035204, "percentage": 63.52, "elapsed_time": "4:33:09", "remaining_time": "2:36:53", "throughput": 1487.0, "total_tokens": 24370528} {"current_steps": 115480, "total_steps": 181800, "loss": 0.1001, "lr": 1.7674183716861613e-05, "epoch": 12.704070407040705, "percentage": 63.52, "elapsed_time": "4:33:09", "remaining_time": "2:36:52", "throughput": 1487.0, "total_tokens": 24371552} {"current_steps": 115485, "total_steps": 181800, "loss": 0.025, "lr": 1.767188904002644e-05, "epoch": 12.704620462046204, "percentage": 63.52, "elapsed_time": "4:33:10", "remaining_time": "2:36:51", "throughput": 1487.01, "total_tokens": 24372608} {"current_steps": 115490, "total_steps": 181800, "loss": 0.0721, "lr": 1.7669594430730963e-05, "epoch": 12.705170517051705, "percentage": 63.53, "elapsed_time": "4:33:11", "remaining_time": "2:36:51", "throughput": 1487.01, "total_tokens": 24373632} {"current_steps": 115495, "total_steps": 181800, "loss": 0.0761, "lr": 1.76672998889963e-05, "epoch": 12.705720572057206, "percentage": 63.53, "elapsed_time": "4:33:11", "remaining_time": "2:36:50", "throughput": 1487.0, "total_tokens": 24374624} {"current_steps": 115500, "total_steps": 181800, "loss": 0.1249, "lr": 1.7665005414843627e-05, "epoch": 12.706270627062706, "percentage": 63.53, "elapsed_time": "4:33:12", "remaining_time": "2:36:49", "throughput": 1487.0, "total_tokens": 24375648} {"current_steps": 115505, "total_steps": 181800, "loss": 0.0428, "lr": 1.7662711008294082e-05, "epoch": 12.706820682068207, "percentage": 63.53, "elapsed_time": "4:33:13", "remaining_time": "2:36:48", "throughput": 1487.01, "total_tokens": 24376704} {"current_steps": 115510, "total_steps": 181800, "loss": 0.009, "lr": 1.766041666936879e-05, "epoch": 12.707370737073708, "percentage": 63.54, "elapsed_time": "4:33:13", "remaining_time": "2:36:48", "throughput": 1487.01, "total_tokens": 24377856} {"current_steps": 115515, "total_steps": 181800, "loss": 0.0035, "lr": 1.7658122398088937e-05, "epoch": 12.707920792079207, "percentage": 63.54, "elapsed_time": "4:33:14", "remaining_time": "2:36:47", "throughput": 1487.01, "total_tokens": 24378880} {"current_steps": 115520, "total_steps": 181800, "loss": 0.0246, "lr": 1.7655828194475632e-05, "epoch": 12.708470847084708, "percentage": 63.54, "elapsed_time": "4:33:15", "remaining_time": "2:36:46", "throughput": 1487.01, "total_tokens": 24379872} {"current_steps": 115525, "total_steps": 181800, "loss": 0.0089, "lr": 1.765353405855004e-05, "epoch": 12.70902090209021, "percentage": 63.55, "elapsed_time": "4:33:15", "remaining_time": "2:36:46", "throughput": 1487.01, "total_tokens": 24380928} {"current_steps": 115530, "total_steps": 181800, "loss": 0.0463, "lr": 1.765123999033331e-05, "epoch": 12.70957095709571, "percentage": 63.55, "elapsed_time": "4:33:16", "remaining_time": "2:36:45", "throughput": 1487.02, "total_tokens": 24381984} {"current_steps": 115535, "total_steps": 181800, "loss": 0.139, "lr": 1.764894598984656e-05, "epoch": 12.71012101210121, "percentage": 63.55, "elapsed_time": "4:33:17", "remaining_time": "2:36:44", "throughput": 1487.02, "total_tokens": 24383008} {"current_steps": 115540, "total_steps": 181800, "loss": 0.0026, "lr": 1.7646652057110953e-05, "epoch": 12.710671067106711, "percentage": 63.55, "elapsed_time": "4:33:17", "remaining_time": "2:36:43", "throughput": 1487.02, "total_tokens": 24384032} {"current_steps": 115545, "total_steps": 181800, "loss": 0.0012, "lr": 1.764435819214762e-05, "epoch": 12.711221122112212, "percentage": 63.56, "elapsed_time": "4:33:18", "remaining_time": "2:36:43", "throughput": 1487.02, "total_tokens": 24385088} {"current_steps": 115550, "total_steps": 181800, "loss": 0.0732, "lr": 1.764206439497772e-05, "epoch": 12.711771177117711, "percentage": 63.56, "elapsed_time": "4:33:19", "remaining_time": "2:36:42", "throughput": 1487.02, "total_tokens": 24386112} {"current_steps": 115555, "total_steps": 181800, "loss": 0.0425, "lr": 1.7639770665622374e-05, "epoch": 12.712321232123212, "percentage": 63.56, "elapsed_time": "4:33:20", "remaining_time": "2:36:41", "throughput": 1487.02, "total_tokens": 24387168} {"current_steps": 115560, "total_steps": 181800, "loss": 0.001, "lr": 1.7637477004102725e-05, "epoch": 12.712871287128714, "percentage": 63.56, "elapsed_time": "4:33:20", "remaining_time": "2:36:41", "throughput": 1487.02, "total_tokens": 24388192} {"current_steps": 115565, "total_steps": 181800, "loss": 0.1008, "lr": 1.7635183410439932e-05, "epoch": 12.713421342134213, "percentage": 63.57, "elapsed_time": "4:33:21", "remaining_time": "2:36:40", "throughput": 1487.02, "total_tokens": 24389248} {"current_steps": 115570, "total_steps": 181800, "loss": 0.0327, "lr": 1.76328898846551e-05, "epoch": 12.713971397139714, "percentage": 63.57, "elapsed_time": "4:33:22", "remaining_time": "2:36:39", "throughput": 1487.03, "total_tokens": 24390368} {"current_steps": 115575, "total_steps": 181800, "loss": 0.0018, "lr": 1.76305964267694e-05, "epoch": 12.714521452145215, "percentage": 63.57, "elapsed_time": "4:33:22", "remaining_time": "2:36:38", "throughput": 1487.03, "total_tokens": 24391424} {"current_steps": 115580, "total_steps": 181800, "loss": 0.0421, "lr": 1.7628303036803954e-05, "epoch": 12.715071507150714, "percentage": 63.58, "elapsed_time": "4:33:23", "remaining_time": "2:36:38", "throughput": 1487.03, "total_tokens": 24392512} {"current_steps": 115585, "total_steps": 181800, "loss": 0.0018, "lr": 1.76260097147799e-05, "epoch": 12.715621562156215, "percentage": 63.58, "elapsed_time": "4:33:24", "remaining_time": "2:36:37", "throughput": 1487.04, "total_tokens": 24393632} {"current_steps": 115590, "total_steps": 181800, "loss": 0.0102, "lr": 1.7623716460718383e-05, "epoch": 12.716171617161717, "percentage": 63.58, "elapsed_time": "4:33:24", "remaining_time": "2:36:36", "throughput": 1487.04, "total_tokens": 24394656} {"current_steps": 115595, "total_steps": 181800, "loss": 0.0088, "lr": 1.7621423274640526e-05, "epoch": 12.716721672167218, "percentage": 63.58, "elapsed_time": "4:33:25", "remaining_time": "2:36:36", "throughput": 1487.04, "total_tokens": 24395712} {"current_steps": 115600, "total_steps": 181800, "loss": 0.0059, "lr": 1.761913015656747e-05, "epoch": 12.717271727172717, "percentage": 63.59, "elapsed_time": "4:33:26", "remaining_time": "2:36:35", "throughput": 1487.04, "total_tokens": 24396800} {"current_steps": 115605, "total_steps": 181800, "loss": 0.0849, "lr": 1.7616837106520358e-05, "epoch": 12.717821782178218, "percentage": 63.59, "elapsed_time": "4:33:26", "remaining_time": "2:36:34", "throughput": 1487.05, "total_tokens": 24397888} {"current_steps": 115610, "total_steps": 181800, "loss": 0.0086, "lr": 1.76145441245203e-05, "epoch": 12.718371837183719, "percentage": 63.59, "elapsed_time": "4:33:27", "remaining_time": "2:36:33", "throughput": 1487.05, "total_tokens": 24398944} {"current_steps": 115615, "total_steps": 181800, "loss": 0.0118, "lr": 1.7612251210588454e-05, "epoch": 12.718921892189218, "percentage": 63.59, "elapsed_time": "4:33:28", "remaining_time": "2:36:33", "throughput": 1487.05, "total_tokens": 24400032} {"current_steps": 115620, "total_steps": 181800, "loss": 0.0075, "lr": 1.7609958364745937e-05, "epoch": 12.71947194719472, "percentage": 63.6, "elapsed_time": "4:33:29", "remaining_time": "2:36:32", "throughput": 1487.05, "total_tokens": 24401120} {"current_steps": 115625, "total_steps": 181800, "loss": 0.0021, "lr": 1.76076655870139e-05, "epoch": 12.72002200220022, "percentage": 63.6, "elapsed_time": "4:33:29", "remaining_time": "2:36:31", "throughput": 1487.06, "total_tokens": 24402208} {"current_steps": 115630, "total_steps": 181800, "loss": 0.0063, "lr": 1.7605372877413457e-05, "epoch": 12.72057205720572, "percentage": 63.6, "elapsed_time": "4:33:30", "remaining_time": "2:36:30", "throughput": 1487.06, "total_tokens": 24403264} {"current_steps": 115635, "total_steps": 181800, "loss": 0.0106, "lr": 1.7603080235965737e-05, "epoch": 12.721122112211221, "percentage": 63.61, "elapsed_time": "4:33:31", "remaining_time": "2:36:30", "throughput": 1487.06, "total_tokens": 24404288} {"current_steps": 115640, "total_steps": 181800, "loss": 0.0009, "lr": 1.7600787662691883e-05, "epoch": 12.721672167216722, "percentage": 63.61, "elapsed_time": "4:33:31", "remaining_time": "2:36:29", "throughput": 1487.06, "total_tokens": 24405376} {"current_steps": 115645, "total_steps": 181800, "loss": 0.0419, "lr": 1.7598495157613025e-05, "epoch": 12.722222222222221, "percentage": 63.61, "elapsed_time": "4:33:32", "remaining_time": "2:36:28", "throughput": 1487.06, "total_tokens": 24406400} {"current_steps": 115650, "total_steps": 181800, "loss": 0.0065, "lr": 1.759620272075027e-05, "epoch": 12.722772277227723, "percentage": 63.61, "elapsed_time": "4:33:33", "remaining_time": "2:36:28", "throughput": 1487.07, "total_tokens": 24407456} {"current_steps": 115655, "total_steps": 181800, "loss": 0.002, "lr": 1.7593910352124778e-05, "epoch": 12.723322332233224, "percentage": 63.62, "elapsed_time": "4:33:33", "remaining_time": "2:36:27", "throughput": 1487.07, "total_tokens": 24408512} {"current_steps": 115660, "total_steps": 181800, "loss": 0.0083, "lr": 1.7591618051757645e-05, "epoch": 12.723872387238725, "percentage": 63.62, "elapsed_time": "4:33:34", "remaining_time": "2:36:26", "throughput": 1487.07, "total_tokens": 24409536} {"current_steps": 115665, "total_steps": 181800, "loss": 0.0563, "lr": 1.758932581967003e-05, "epoch": 12.724422442244224, "percentage": 63.62, "elapsed_time": "4:33:35", "remaining_time": "2:36:25", "throughput": 1487.07, "total_tokens": 24410592} {"current_steps": 115670, "total_steps": 181800, "loss": 0.0017, "lr": 1.7587033655883032e-05, "epoch": 12.724972497249725, "percentage": 63.62, "elapsed_time": "4:33:35", "remaining_time": "2:36:25", "throughput": 1487.07, "total_tokens": 24411584} {"current_steps": 115675, "total_steps": 181800, "loss": 0.0076, "lr": 1.7584741560417784e-05, "epoch": 12.725522552255226, "percentage": 63.63, "elapsed_time": "4:33:36", "remaining_time": "2:36:24", "throughput": 1487.07, "total_tokens": 24412672} {"current_steps": 115680, "total_steps": 181800, "loss": 0.0807, "lr": 1.7582449533295427e-05, "epoch": 12.726072607260726, "percentage": 63.63, "elapsed_time": "4:33:37", "remaining_time": "2:36:23", "throughput": 1487.07, "total_tokens": 24413760} {"current_steps": 115685, "total_steps": 181800, "loss": 0.0041, "lr": 1.7580157574537065e-05, "epoch": 12.726622662266227, "percentage": 63.63, "elapsed_time": "4:33:38", "remaining_time": "2:36:23", "throughput": 1487.08, "total_tokens": 24414816} {"current_steps": 115690, "total_steps": 181800, "loss": 0.0169, "lr": 1.757786568416383e-05, "epoch": 12.727172717271728, "percentage": 63.64, "elapsed_time": "4:33:38", "remaining_time": "2:36:22", "throughput": 1487.08, "total_tokens": 24415904} {"current_steps": 115695, "total_steps": 181800, "loss": 0.0273, "lr": 1.757557386219685e-05, "epoch": 12.727722772277227, "percentage": 63.64, "elapsed_time": "4:33:39", "remaining_time": "2:36:21", "throughput": 1487.08, "total_tokens": 24416896} {"current_steps": 115700, "total_steps": 181800, "loss": 0.0954, "lr": 1.7573282108657235e-05, "epoch": 12.728272827282728, "percentage": 63.64, "elapsed_time": "4:33:40", "remaining_time": "2:36:20", "throughput": 1487.08, "total_tokens": 24417984} {"current_steps": 115705, "total_steps": 181800, "loss": 0.0181, "lr": 1.757099042356613e-05, "epoch": 12.72882288228823, "percentage": 63.64, "elapsed_time": "4:33:40", "remaining_time": "2:36:20", "throughput": 1487.08, "total_tokens": 24419040} {"current_steps": 115710, "total_steps": 181800, "loss": 0.0006, "lr": 1.7568698806944627e-05, "epoch": 12.729372937293729, "percentage": 63.65, "elapsed_time": "4:33:41", "remaining_time": "2:36:19", "throughput": 1487.08, "total_tokens": 24420096} {"current_steps": 115715, "total_steps": 181800, "loss": 0.1029, "lr": 1.7566407258813866e-05, "epoch": 12.72992299229923, "percentage": 63.65, "elapsed_time": "4:33:42", "remaining_time": "2:36:18", "throughput": 1487.09, "total_tokens": 24421184} {"current_steps": 115720, "total_steps": 181800, "loss": 0.0039, "lr": 1.7564115779194974e-05, "epoch": 12.73047304730473, "percentage": 63.65, "elapsed_time": "4:33:42", "remaining_time": "2:36:17", "throughput": 1487.09, "total_tokens": 24422240} {"current_steps": 115725, "total_steps": 181800, "loss": 0.0062, "lr": 1.756182436810904e-05, "epoch": 12.731023102310232, "percentage": 63.66, "elapsed_time": "4:33:43", "remaining_time": "2:36:17", "throughput": 1487.09, "total_tokens": 24423264} {"current_steps": 115730, "total_steps": 181800, "loss": 0.0445, "lr": 1.7559533025577214e-05, "epoch": 12.731573157315731, "percentage": 63.66, "elapsed_time": "4:33:44", "remaining_time": "2:36:16", "throughput": 1487.09, "total_tokens": 24424384} {"current_steps": 115735, "total_steps": 181800, "loss": 0.078, "lr": 1.755724175162059e-05, "epoch": 12.732123212321232, "percentage": 63.66, "elapsed_time": "4:33:44", "remaining_time": "2:36:15", "throughput": 1487.1, "total_tokens": 24425536} {"current_steps": 115740, "total_steps": 181800, "loss": 0.0259, "lr": 1.7554950546260313e-05, "epoch": 12.732673267326733, "percentage": 63.66, "elapsed_time": "4:33:45", "remaining_time": "2:36:15", "throughput": 1487.1, "total_tokens": 24426592} {"current_steps": 115745, "total_steps": 181800, "loss": 0.1059, "lr": 1.7552659409517475e-05, "epoch": 12.733223322332233, "percentage": 63.67, "elapsed_time": "4:33:46", "remaining_time": "2:36:14", "throughput": 1487.1, "total_tokens": 24427584} {"current_steps": 115750, "total_steps": 181800, "loss": 0.0523, "lr": 1.7550368341413197e-05, "epoch": 12.733773377337734, "percentage": 63.67, "elapsed_time": "4:33:46", "remaining_time": "2:36:13", "throughput": 1487.11, "total_tokens": 24428672} {"current_steps": 115755, "total_steps": 181800, "loss": 0.0041, "lr": 1.7548077341968606e-05, "epoch": 12.734323432343235, "percentage": 63.67, "elapsed_time": "4:33:47", "remaining_time": "2:36:12", "throughput": 1487.11, "total_tokens": 24429728} {"current_steps": 115760, "total_steps": 181800, "loss": 0.0107, "lr": 1.7545786411204808e-05, "epoch": 12.734873487348734, "percentage": 63.67, "elapsed_time": "4:33:48", "remaining_time": "2:36:12", "throughput": 1487.11, "total_tokens": 24430784} {"current_steps": 115765, "total_steps": 181800, "loss": 0.0049, "lr": 1.7543495549142924e-05, "epoch": 12.735423542354235, "percentage": 63.68, "elapsed_time": "4:33:49", "remaining_time": "2:36:11", "throughput": 1487.11, "total_tokens": 24431904} {"current_steps": 115770, "total_steps": 181800, "loss": 0.0042, "lr": 1.7541204755804065e-05, "epoch": 12.735973597359736, "percentage": 63.68, "elapsed_time": "4:33:49", "remaining_time": "2:36:10", "throughput": 1487.12, "total_tokens": 24432960} {"current_steps": 115775, "total_steps": 181800, "loss": 0.0186, "lr": 1.753891403120933e-05, "epoch": 12.736523652365236, "percentage": 63.68, "elapsed_time": "4:33:50", "remaining_time": "2:36:10", "throughput": 1487.11, "total_tokens": 24433920} {"current_steps": 115780, "total_steps": 181800, "loss": 0.0492, "lr": 1.753662337537986e-05, "epoch": 12.737073707370737, "percentage": 63.69, "elapsed_time": "4:33:51", "remaining_time": "2:36:09", "throughput": 1487.12, "total_tokens": 24435008} {"current_steps": 115785, "total_steps": 181800, "loss": 0.092, "lr": 1.753433278833674e-05, "epoch": 12.737623762376238, "percentage": 63.69, "elapsed_time": "4:33:51", "remaining_time": "2:36:08", "throughput": 1487.11, "total_tokens": 24436000} {"current_steps": 115790, "total_steps": 181800, "loss": 0.0624, "lr": 1.7532042270101096e-05, "epoch": 12.738173817381739, "percentage": 63.69, "elapsed_time": "4:33:52", "remaining_time": "2:36:07", "throughput": 1487.12, "total_tokens": 24437056} {"current_steps": 115795, "total_steps": 181800, "loss": 0.0146, "lr": 1.752975182069404e-05, "epoch": 12.738723872387238, "percentage": 63.69, "elapsed_time": "4:33:53", "remaining_time": "2:36:07", "throughput": 1487.12, "total_tokens": 24438112} {"current_steps": 115800, "total_steps": 181800, "loss": 0.0255, "lr": 1.7527461440136667e-05, "epoch": 12.73927392739274, "percentage": 63.7, "elapsed_time": "4:33:53", "remaining_time": "2:36:06", "throughput": 1487.12, "total_tokens": 24439168} {"current_steps": 115805, "total_steps": 181800, "loss": 0.0204, "lr": 1.75251711284501e-05, "epoch": 12.73982398239824, "percentage": 63.7, "elapsed_time": "4:33:54", "remaining_time": "2:36:05", "throughput": 1487.12, "total_tokens": 24440256} {"current_steps": 115810, "total_steps": 181800, "loss": 0.0005, "lr": 1.7522880885655444e-05, "epoch": 12.74037403740374, "percentage": 63.7, "elapsed_time": "4:33:55", "remaining_time": "2:36:05", "throughput": 1487.13, "total_tokens": 24441312} {"current_steps": 115815, "total_steps": 181800, "loss": 0.0046, "lr": 1.7520590711773806e-05, "epoch": 12.74092409240924, "percentage": 63.7, "elapsed_time": "4:33:55", "remaining_time": "2:36:04", "throughput": 1487.13, "total_tokens": 24442336} {"current_steps": 115820, "total_steps": 181800, "loss": 0.0236, "lr": 1.7518300606826304e-05, "epoch": 12.741474147414742, "percentage": 63.71, "elapsed_time": "4:33:56", "remaining_time": "2:36:03", "throughput": 1487.13, "total_tokens": 24443360} {"current_steps": 115825, "total_steps": 181800, "loss": 0.0738, "lr": 1.7516010570834023e-05, "epoch": 12.742024202420241, "percentage": 63.71, "elapsed_time": "4:33:57", "remaining_time": "2:36:02", "throughput": 1487.13, "total_tokens": 24444416} {"current_steps": 115830, "total_steps": 181800, "loss": 0.0094, "lr": 1.7513720603818088e-05, "epoch": 12.742574257425742, "percentage": 63.71, "elapsed_time": "4:33:58", "remaining_time": "2:36:02", "throughput": 1487.13, "total_tokens": 24445472} {"current_steps": 115835, "total_steps": 181800, "loss": 0.0125, "lr": 1.7511430705799604e-05, "epoch": 12.743124312431243, "percentage": 63.72, "elapsed_time": "4:33:58", "remaining_time": "2:36:01", "throughput": 1487.13, "total_tokens": 24446528} {"current_steps": 115840, "total_steps": 181800, "loss": 0.0496, "lr": 1.7509140876799654e-05, "epoch": 12.743674367436743, "percentage": 63.72, "elapsed_time": "4:33:59", "remaining_time": "2:36:00", "throughput": 1487.13, "total_tokens": 24447584} {"current_steps": 115845, "total_steps": 181800, "loss": 0.0613, "lr": 1.750685111683937e-05, "epoch": 12.744224422442244, "percentage": 63.72, "elapsed_time": "4:34:00", "remaining_time": "2:35:59", "throughput": 1487.13, "total_tokens": 24448608} {"current_steps": 115850, "total_steps": 181800, "loss": 0.0058, "lr": 1.750456142593983e-05, "epoch": 12.744774477447745, "percentage": 63.72, "elapsed_time": "4:34:00", "remaining_time": "2:35:59", "throughput": 1487.13, "total_tokens": 24449632} {"current_steps": 115855, "total_steps": 181800, "loss": 0.0041, "lr": 1.7502271804122167e-05, "epoch": 12.745324532453246, "percentage": 63.73, "elapsed_time": "4:34:01", "remaining_time": "2:35:58", "throughput": 1487.13, "total_tokens": 24450656} {"current_steps": 115860, "total_steps": 181800, "loss": 0.006, "lr": 1.7499982251407462e-05, "epoch": 12.745874587458745, "percentage": 63.73, "elapsed_time": "4:34:02", "remaining_time": "2:35:57", "throughput": 1487.14, "total_tokens": 24451744} {"current_steps": 115865, "total_steps": 181800, "loss": 0.0081, "lr": 1.7497692767816815e-05, "epoch": 12.746424642464246, "percentage": 63.73, "elapsed_time": "4:34:02", "remaining_time": "2:35:57", "throughput": 1487.14, "total_tokens": 24452832} {"current_steps": 115870, "total_steps": 181800, "loss": 0.0026, "lr": 1.7495403353371348e-05, "epoch": 12.746974697469748, "percentage": 63.73, "elapsed_time": "4:34:03", "remaining_time": "2:35:56", "throughput": 1487.14, "total_tokens": 24453920} {"current_steps": 115875, "total_steps": 181800, "loss": 0.0019, "lr": 1.7493114008092128e-05, "epoch": 12.747524752475247, "percentage": 63.74, "elapsed_time": "4:34:04", "remaining_time": "2:35:55", "throughput": 1487.15, "total_tokens": 24455008} {"current_steps": 115880, "total_steps": 181800, "loss": 0.0147, "lr": 1.7490824732000287e-05, "epoch": 12.748074807480748, "percentage": 63.74, "elapsed_time": "4:34:04", "remaining_time": "2:35:54", "throughput": 1487.15, "total_tokens": 24456064} {"current_steps": 115885, "total_steps": 181800, "loss": 0.0345, "lr": 1.7488535525116913e-05, "epoch": 12.748624862486249, "percentage": 63.74, "elapsed_time": "4:34:05", "remaining_time": "2:35:54", "throughput": 1487.15, "total_tokens": 24457056} {"current_steps": 115890, "total_steps": 181800, "loss": 0.0027, "lr": 1.748624638746309e-05, "epoch": 12.749174917491748, "percentage": 63.75, "elapsed_time": "4:34:06", "remaining_time": "2:35:53", "throughput": 1487.15, "total_tokens": 24458144} {"current_steps": 115895, "total_steps": 181800, "loss": 0.042, "lr": 1.7483957319059943e-05, "epoch": 12.74972497249725, "percentage": 63.75, "elapsed_time": "4:34:06", "remaining_time": "2:35:52", "throughput": 1487.15, "total_tokens": 24459168} {"current_steps": 115900, "total_steps": 181800, "loss": 0.0016, "lr": 1.7481668319928547e-05, "epoch": 12.75027502750275, "percentage": 63.75, "elapsed_time": "4:34:07", "remaining_time": "2:35:52", "throughput": 1487.15, "total_tokens": 24460224} {"current_steps": 115905, "total_steps": 181800, "loss": 0.0247, "lr": 1.7479379390090006e-05, "epoch": 12.750825082508252, "percentage": 63.75, "elapsed_time": "4:34:08", "remaining_time": "2:35:51", "throughput": 1487.16, "total_tokens": 24461280} {"current_steps": 115910, "total_steps": 181800, "loss": 0.0041, "lr": 1.7477090529565427e-05, "epoch": 12.751375137513751, "percentage": 63.76, "elapsed_time": "4:34:09", "remaining_time": "2:35:50", "throughput": 1487.16, "total_tokens": 24462400} {"current_steps": 115915, "total_steps": 181800, "loss": 0.005, "lr": 1.747480173837588e-05, "epoch": 12.751925192519252, "percentage": 63.76, "elapsed_time": "4:34:09", "remaining_time": "2:35:49", "throughput": 1487.16, "total_tokens": 24463456} {"current_steps": 115920, "total_steps": 181800, "loss": 0.0899, "lr": 1.747251301654248e-05, "epoch": 12.752475247524753, "percentage": 63.76, "elapsed_time": "4:34:10", "remaining_time": "2:35:49", "throughput": 1487.16, "total_tokens": 24464512} {"current_steps": 115925, "total_steps": 181800, "loss": 0.0016, "lr": 1.7470224364086314e-05, "epoch": 12.753025302530252, "percentage": 63.77, "elapsed_time": "4:34:11", "remaining_time": "2:35:48", "throughput": 1487.16, "total_tokens": 24465504} {"current_steps": 115930, "total_steps": 181800, "loss": 0.0013, "lr": 1.7467935781028483e-05, "epoch": 12.753575357535754, "percentage": 63.77, "elapsed_time": "4:34:11", "remaining_time": "2:35:47", "throughput": 1487.17, "total_tokens": 24466656} {"current_steps": 115935, "total_steps": 181800, "loss": 0.0547, "lr": 1.746564726739007e-05, "epoch": 12.754125412541255, "percentage": 63.77, "elapsed_time": "4:34:12", "remaining_time": "2:35:47", "throughput": 1487.17, "total_tokens": 24467680} {"current_steps": 115940, "total_steps": 181800, "loss": 0.0334, "lr": 1.7463358823192166e-05, "epoch": 12.754675467546754, "percentage": 63.77, "elapsed_time": "4:34:13", "remaining_time": "2:35:46", "throughput": 1487.18, "total_tokens": 24468832} {"current_steps": 115945, "total_steps": 181800, "loss": 0.004, "lr": 1.7461070448455874e-05, "epoch": 12.755225522552255, "percentage": 63.78, "elapsed_time": "4:34:13", "remaining_time": "2:35:45", "throughput": 1487.18, "total_tokens": 24469856} {"current_steps": 115950, "total_steps": 181800, "loss": 0.0017, "lr": 1.7458782143202267e-05, "epoch": 12.755775577557756, "percentage": 63.78, "elapsed_time": "4:34:14", "remaining_time": "2:35:44", "throughput": 1487.18, "total_tokens": 24470912} {"current_steps": 115955, "total_steps": 181800, "loss": 0.0029, "lr": 1.7456493907452463e-05, "epoch": 12.756325632563257, "percentage": 63.78, "elapsed_time": "4:34:15", "remaining_time": "2:35:44", "throughput": 1487.18, "total_tokens": 24471904} {"current_steps": 115960, "total_steps": 181800, "loss": 0.0064, "lr": 1.7454205741227528e-05, "epoch": 12.756875687568757, "percentage": 63.78, "elapsed_time": "4:34:15", "remaining_time": "2:35:43", "throughput": 1487.18, "total_tokens": 24473024} {"current_steps": 115965, "total_steps": 181800, "loss": 0.0686, "lr": 1.7451917644548554e-05, "epoch": 12.757425742574258, "percentage": 63.79, "elapsed_time": "4:34:16", "remaining_time": "2:35:42", "throughput": 1487.18, "total_tokens": 24474016} {"current_steps": 115970, "total_steps": 181800, "loss": 0.0074, "lr": 1.7449629617436643e-05, "epoch": 12.757975797579759, "percentage": 63.79, "elapsed_time": "4:34:17", "remaining_time": "2:35:41", "throughput": 1487.18, "total_tokens": 24475008} {"current_steps": 115975, "total_steps": 181800, "loss": 0.011, "lr": 1.744734165991286e-05, "epoch": 12.758525852585258, "percentage": 63.79, "elapsed_time": "4:34:18", "remaining_time": "2:35:41", "throughput": 1487.18, "total_tokens": 24476064} {"current_steps": 115980, "total_steps": 181800, "loss": 0.0329, "lr": 1.7445053771998308e-05, "epoch": 12.75907590759076, "percentage": 63.8, "elapsed_time": "4:34:18", "remaining_time": "2:35:40", "throughput": 1487.19, "total_tokens": 24477152} {"current_steps": 115985, "total_steps": 181800, "loss": 0.0451, "lr": 1.744276595371408e-05, "epoch": 12.75962596259626, "percentage": 63.8, "elapsed_time": "4:34:19", "remaining_time": "2:35:39", "throughput": 1487.19, "total_tokens": 24478240} {"current_steps": 115990, "total_steps": 181800, "loss": 0.0838, "lr": 1.744047820508124e-05, "epoch": 12.76017601760176, "percentage": 63.8, "elapsed_time": "4:34:20", "remaining_time": "2:35:39", "throughput": 1487.19, "total_tokens": 24479296} {"current_steps": 115995, "total_steps": 181800, "loss": 0.014, "lr": 1.7438190526120893e-05, "epoch": 12.76072607260726, "percentage": 63.8, "elapsed_time": "4:34:20", "remaining_time": "2:35:38", "throughput": 1487.19, "total_tokens": 24480288} {"current_steps": 116000, "total_steps": 181800, "loss": 0.0635, "lr": 1.743590291685411e-05, "epoch": 12.761276127612762, "percentage": 63.81, "elapsed_time": "4:34:21", "remaining_time": "2:35:37", "throughput": 1487.19, "total_tokens": 24481376} {"current_steps": 116005, "total_steps": 181800, "loss": 0.0066, "lr": 1.7433615377301983e-05, "epoch": 12.761826182618261, "percentage": 63.81, "elapsed_time": "4:34:22", "remaining_time": "2:35:36", "throughput": 1487.19, "total_tokens": 24482400} {"current_steps": 116010, "total_steps": 181800, "loss": 0.0046, "lr": 1.7431327907485595e-05, "epoch": 12.762376237623762, "percentage": 63.81, "elapsed_time": "4:34:22", "remaining_time": "2:35:36", "throughput": 1487.19, "total_tokens": 24483424} {"current_steps": 116015, "total_steps": 181800, "loss": 0.0134, "lr": 1.742904050742602e-05, "epoch": 12.762926292629263, "percentage": 63.81, "elapsed_time": "4:34:23", "remaining_time": "2:35:35", "throughput": 1487.19, "total_tokens": 24484416} {"current_steps": 116020, "total_steps": 181800, "loss": 0.2018, "lr": 1.7426753177144346e-05, "epoch": 12.763476347634764, "percentage": 63.82, "elapsed_time": "4:34:24", "remaining_time": "2:35:34", "throughput": 1487.2, "total_tokens": 24485568} {"current_steps": 116025, "total_steps": 181800, "loss": 0.0949, "lr": 1.7424465916661664e-05, "epoch": 12.764026402640264, "percentage": 63.82, "elapsed_time": "4:34:24", "remaining_time": "2:35:34", "throughput": 1487.2, "total_tokens": 24486592} {"current_steps": 116030, "total_steps": 181800, "loss": 0.0716, "lr": 1.7422178725999034e-05, "epoch": 12.764576457645765, "percentage": 63.82, "elapsed_time": "4:34:25", "remaining_time": "2:35:33", "throughput": 1487.21, "total_tokens": 24487712} {"current_steps": 116035, "total_steps": 181800, "loss": 0.0263, "lr": 1.7419891605177547e-05, "epoch": 12.765126512651266, "percentage": 63.83, "elapsed_time": "4:34:26", "remaining_time": "2:35:32", "throughput": 1487.21, "total_tokens": 24488736} {"current_steps": 116040, "total_steps": 181800, "loss": 0.0455, "lr": 1.741760455421828e-05, "epoch": 12.765676567656765, "percentage": 63.83, "elapsed_time": "4:34:26", "remaining_time": "2:35:31", "throughput": 1487.21, "total_tokens": 24489824} {"current_steps": 116045, "total_steps": 181800, "loss": 0.0173, "lr": 1.7415317573142325e-05, "epoch": 12.766226622662266, "percentage": 63.83, "elapsed_time": "4:34:27", "remaining_time": "2:35:31", "throughput": 1487.21, "total_tokens": 24490816} {"current_steps": 116050, "total_steps": 181800, "loss": 0.0231, "lr": 1.7413030661970742e-05, "epoch": 12.766776677667767, "percentage": 63.83, "elapsed_time": "4:34:28", "remaining_time": "2:35:30", "throughput": 1487.21, "total_tokens": 24491904} {"current_steps": 116055, "total_steps": 181800, "loss": 0.0625, "lr": 1.7410743820724606e-05, "epoch": 12.767326732673267, "percentage": 63.84, "elapsed_time": "4:34:29", "remaining_time": "2:35:29", "throughput": 1487.21, "total_tokens": 24492928} {"current_steps": 116060, "total_steps": 181800, "loss": 0.0075, "lr": 1.7408457049425013e-05, "epoch": 12.767876787678768, "percentage": 63.84, "elapsed_time": "4:34:29", "remaining_time": "2:35:28", "throughput": 1487.21, "total_tokens": 24493984} {"current_steps": 116065, "total_steps": 181800, "loss": 0.0663, "lr": 1.7406170348093022e-05, "epoch": 12.768426842684269, "percentage": 63.84, "elapsed_time": "4:34:30", "remaining_time": "2:35:28", "throughput": 1487.22, "total_tokens": 24495072} {"current_steps": 116070, "total_steps": 181800, "loss": 0.1266, "lr": 1.7403883716749723e-05, "epoch": 12.768976897689768, "percentage": 63.84, "elapsed_time": "4:34:31", "remaining_time": "2:35:27", "throughput": 1487.21, "total_tokens": 24496064} {"current_steps": 116075, "total_steps": 181800, "loss": 0.0025, "lr": 1.740159715541618e-05, "epoch": 12.76952695269527, "percentage": 63.85, "elapsed_time": "4:34:31", "remaining_time": "2:35:26", "throughput": 1487.22, "total_tokens": 24497120} {"current_steps": 116080, "total_steps": 181800, "loss": 0.0029, "lr": 1.7399310664113467e-05, "epoch": 12.77007700770077, "percentage": 63.85, "elapsed_time": "4:34:32", "remaining_time": "2:35:26", "throughput": 1487.22, "total_tokens": 24498208} {"current_steps": 116085, "total_steps": 181800, "loss": 0.1194, "lr": 1.7397024242862668e-05, "epoch": 12.770627062706271, "percentage": 63.85, "elapsed_time": "4:34:33", "remaining_time": "2:35:25", "throughput": 1487.22, "total_tokens": 24499264} {"current_steps": 116090, "total_steps": 181800, "loss": 0.0112, "lr": 1.7394737891684837e-05, "epoch": 12.77117711771177, "percentage": 63.86, "elapsed_time": "4:34:33", "remaining_time": "2:35:24", "throughput": 1487.22, "total_tokens": 24500352} {"current_steps": 116095, "total_steps": 181800, "loss": 0.0244, "lr": 1.7392451610601063e-05, "epoch": 12.771727172717272, "percentage": 63.86, "elapsed_time": "4:34:34", "remaining_time": "2:35:23", "throughput": 1487.23, "total_tokens": 24501408} {"current_steps": 116100, "total_steps": 181800, "loss": 0.0402, "lr": 1.7390165399632417e-05, "epoch": 12.772277227722773, "percentage": 63.86, "elapsed_time": "4:34:35", "remaining_time": "2:35:23", "throughput": 1487.23, "total_tokens": 24502432} {"current_steps": 116105, "total_steps": 181800, "loss": 0.0402, "lr": 1.7387879258799956e-05, "epoch": 12.772827282728272, "percentage": 63.86, "elapsed_time": "4:34:35", "remaining_time": "2:35:22", "throughput": 1487.23, "total_tokens": 24503520} {"current_steps": 116110, "total_steps": 181800, "loss": 0.0086, "lr": 1.7385593188124767e-05, "epoch": 12.773377337733773, "percentage": 63.87, "elapsed_time": "4:34:36", "remaining_time": "2:35:21", "throughput": 1487.23, "total_tokens": 24504544} {"current_steps": 116115, "total_steps": 181800, "loss": 0.1143, "lr": 1.73833071876279e-05, "epoch": 12.773927392739274, "percentage": 63.87, "elapsed_time": "4:34:37", "remaining_time": "2:35:21", "throughput": 1487.23, "total_tokens": 24505632} {"current_steps": 116120, "total_steps": 181800, "loss": 0.0678, "lr": 1.738102125733044e-05, "epoch": 12.774477447744774, "percentage": 63.87, "elapsed_time": "4:34:38", "remaining_time": "2:35:20", "throughput": 1487.23, "total_tokens": 24506688} {"current_steps": 116125, "total_steps": 181800, "loss": 0.0078, "lr": 1.7378735397253464e-05, "epoch": 12.775027502750275, "percentage": 63.88, "elapsed_time": "4:34:38", "remaining_time": "2:35:19", "throughput": 1487.23, "total_tokens": 24507712} {"current_steps": 116130, "total_steps": 181800, "loss": 0.0102, "lr": 1.7376449607418015e-05, "epoch": 12.775577557755776, "percentage": 63.88, "elapsed_time": "4:34:39", "remaining_time": "2:35:18", "throughput": 1487.24, "total_tokens": 24508800} {"current_steps": 116135, "total_steps": 181800, "loss": 0.1353, "lr": 1.7374163887845172e-05, "epoch": 12.776127612761275, "percentage": 63.88, "elapsed_time": "4:34:40", "remaining_time": "2:35:18", "throughput": 1487.24, "total_tokens": 24509856} {"current_steps": 116140, "total_steps": 181800, "loss": 0.0107, "lr": 1.7371878238556003e-05, "epoch": 12.776677667766776, "percentage": 63.88, "elapsed_time": "4:34:40", "remaining_time": "2:35:17", "throughput": 1487.24, "total_tokens": 24510944} {"current_steps": 116145, "total_steps": 181800, "loss": 0.0045, "lr": 1.7369592659571578e-05, "epoch": 12.777227722772277, "percentage": 63.89, "elapsed_time": "4:34:41", "remaining_time": "2:35:16", "throughput": 1487.25, "total_tokens": 24512064} {"current_steps": 116150, "total_steps": 181800, "loss": 0.0178, "lr": 1.7367307150912955e-05, "epoch": 12.777777777777779, "percentage": 63.89, "elapsed_time": "4:34:42", "remaining_time": "2:35:16", "throughput": 1487.25, "total_tokens": 24513120} {"current_steps": 116155, "total_steps": 181800, "loss": 0.089, "lr": 1.7365021712601186e-05, "epoch": 12.778327832783278, "percentage": 63.89, "elapsed_time": "4:34:42", "remaining_time": "2:35:15", "throughput": 1487.25, "total_tokens": 24514176} {"current_steps": 116160, "total_steps": 181800, "loss": 0.154, "lr": 1.7362736344657365e-05, "epoch": 12.778877887788779, "percentage": 63.89, "elapsed_time": "4:34:43", "remaining_time": "2:35:14", "throughput": 1487.26, "total_tokens": 24515232} {"current_steps": 116165, "total_steps": 181800, "loss": 0.0039, "lr": 1.7360451047102527e-05, "epoch": 12.77942794279428, "percentage": 63.9, "elapsed_time": "4:34:44", "remaining_time": "2:35:13", "throughput": 1487.26, "total_tokens": 24516288} {"current_steps": 116170, "total_steps": 181800, "loss": 0.0765, "lr": 1.735816581995775e-05, "epoch": 12.77997799779978, "percentage": 63.9, "elapsed_time": "4:34:44", "remaining_time": "2:35:13", "throughput": 1487.26, "total_tokens": 24517280} {"current_steps": 116175, "total_steps": 181800, "loss": 0.0049, "lr": 1.7355880663244094e-05, "epoch": 12.78052805280528, "percentage": 63.9, "elapsed_time": "4:34:45", "remaining_time": "2:35:12", "throughput": 1487.26, "total_tokens": 24518368} {"current_steps": 116180, "total_steps": 181800, "loss": 0.0017, "lr": 1.735359557698261e-05, "epoch": 12.781078107810782, "percentage": 63.91, "elapsed_time": "4:34:46", "remaining_time": "2:35:11", "throughput": 1487.26, "total_tokens": 24519424} {"current_steps": 116185, "total_steps": 181800, "loss": 0.1089, "lr": 1.735131056119438e-05, "epoch": 12.781628162816281, "percentage": 63.91, "elapsed_time": "4:34:46", "remaining_time": "2:35:10", "throughput": 1487.26, "total_tokens": 24520448} {"current_steps": 116190, "total_steps": 181800, "loss": 0.0775, "lr": 1.7349025615900436e-05, "epoch": 12.782178217821782, "percentage": 63.91, "elapsed_time": "4:34:47", "remaining_time": "2:35:10", "throughput": 1487.26, "total_tokens": 24521440} {"current_steps": 116195, "total_steps": 181800, "loss": 0.0052, "lr": 1.734674074112186e-05, "epoch": 12.782728272827283, "percentage": 63.91, "elapsed_time": "4:34:48", "remaining_time": "2:35:09", "throughput": 1487.26, "total_tokens": 24522464} {"current_steps": 116200, "total_steps": 181800, "loss": 0.0129, "lr": 1.7344455936879704e-05, "epoch": 12.783278327832782, "percentage": 63.92, "elapsed_time": "4:34:49", "remaining_time": "2:35:08", "throughput": 1487.26, "total_tokens": 24523584} {"current_steps": 116205, "total_steps": 181800, "loss": 0.0036, "lr": 1.7342171203195014e-05, "epoch": 12.783828382838283, "percentage": 63.92, "elapsed_time": "4:34:49", "remaining_time": "2:35:08", "throughput": 1487.26, "total_tokens": 24524608} {"current_steps": 116210, "total_steps": 181800, "loss": 0.0047, "lr": 1.7339886540088866e-05, "epoch": 12.784378437843785, "percentage": 63.92, "elapsed_time": "4:34:50", "remaining_time": "2:35:07", "throughput": 1487.26, "total_tokens": 24525632} {"current_steps": 116215, "total_steps": 181800, "loss": 0.0525, "lr": 1.7337601947582298e-05, "epoch": 12.784928492849286, "percentage": 63.92, "elapsed_time": "4:34:51", "remaining_time": "2:35:06", "throughput": 1487.27, "total_tokens": 24526688} {"current_steps": 116220, "total_steps": 181800, "loss": 0.0234, "lr": 1.7335317425696394e-05, "epoch": 12.785478547854785, "percentage": 63.93, "elapsed_time": "4:34:51", "remaining_time": "2:35:05", "throughput": 1487.27, "total_tokens": 24527744} {"current_steps": 116225, "total_steps": 181800, "loss": 0.0193, "lr": 1.733303297445218e-05, "epoch": 12.786028602860286, "percentage": 63.93, "elapsed_time": "4:34:52", "remaining_time": "2:35:05", "throughput": 1487.27, "total_tokens": 24528800} {"current_steps": 116230, "total_steps": 181800, "loss": 0.084, "lr": 1.733074859387072e-05, "epoch": 12.786578657865787, "percentage": 63.93, "elapsed_time": "4:34:53", "remaining_time": "2:35:04", "throughput": 1487.27, "total_tokens": 24529856} {"current_steps": 116235, "total_steps": 181800, "loss": 0.0086, "lr": 1.7328464283973074e-05, "epoch": 12.787128712871286, "percentage": 63.94, "elapsed_time": "4:34:53", "remaining_time": "2:35:03", "throughput": 1487.27, "total_tokens": 24530880} {"current_steps": 116240, "total_steps": 181800, "loss": 0.0432, "lr": 1.7326180044780296e-05, "epoch": 12.787678767876788, "percentage": 63.94, "elapsed_time": "4:34:54", "remaining_time": "2:35:03", "throughput": 1487.27, "total_tokens": 24531904} {"current_steps": 116245, "total_steps": 181800, "loss": 0.0427, "lr": 1.7323895876313424e-05, "epoch": 12.788228822882289, "percentage": 63.94, "elapsed_time": "4:34:55", "remaining_time": "2:35:02", "throughput": 1487.28, "total_tokens": 24532992} {"current_steps": 116250, "total_steps": 181800, "loss": 0.0034, "lr": 1.7321611778593526e-05, "epoch": 12.788778877887788, "percentage": 63.94, "elapsed_time": "4:34:55", "remaining_time": "2:35:01", "throughput": 1487.28, "total_tokens": 24534048} {"current_steps": 116255, "total_steps": 181800, "loss": 0.0214, "lr": 1.7319327751641644e-05, "epoch": 12.789328932893289, "percentage": 63.95, "elapsed_time": "4:34:56", "remaining_time": "2:35:00", "throughput": 1487.28, "total_tokens": 24535136} {"current_steps": 116260, "total_steps": 181800, "loss": 0.0363, "lr": 1.7317043795478844e-05, "epoch": 12.78987898789879, "percentage": 63.95, "elapsed_time": "4:34:57", "remaining_time": "2:35:00", "throughput": 1487.29, "total_tokens": 24536224} {"current_steps": 116265, "total_steps": 181800, "loss": 0.074, "lr": 1.7314759910126155e-05, "epoch": 12.79042904290429, "percentage": 63.95, "elapsed_time": "4:34:58", "remaining_time": "2:34:59", "throughput": 1487.29, "total_tokens": 24537312} {"current_steps": 116270, "total_steps": 181800, "loss": 0.0088, "lr": 1.7312476095604634e-05, "epoch": 12.79097909790979, "percentage": 63.95, "elapsed_time": "4:34:58", "remaining_time": "2:34:58", "throughput": 1487.29, "total_tokens": 24538336} {"current_steps": 116275, "total_steps": 181800, "loss": 0.0858, "lr": 1.7310192351935343e-05, "epoch": 12.791529152915292, "percentage": 63.96, "elapsed_time": "4:34:59", "remaining_time": "2:34:57", "throughput": 1487.29, "total_tokens": 24539328} {"current_steps": 116280, "total_steps": 181800, "loss": 0.006, "lr": 1.7307908679139307e-05, "epoch": 12.792079207920793, "percentage": 63.96, "elapsed_time": "4:35:00", "remaining_time": "2:34:57", "throughput": 1487.29, "total_tokens": 24540384} {"current_steps": 116285, "total_steps": 181800, "loss": 0.0161, "lr": 1.730562507723759e-05, "epoch": 12.792629262926292, "percentage": 63.96, "elapsed_time": "4:35:00", "remaining_time": "2:34:56", "throughput": 1487.29, "total_tokens": 24541440} {"current_steps": 116290, "total_steps": 181800, "loss": 0.0187, "lr": 1.7303341546251242e-05, "epoch": 12.793179317931793, "percentage": 63.97, "elapsed_time": "4:35:01", "remaining_time": "2:34:55", "throughput": 1487.29, "total_tokens": 24542432} {"current_steps": 116295, "total_steps": 181800, "loss": 0.0667, "lr": 1.7301058086201284e-05, "epoch": 12.793729372937294, "percentage": 63.97, "elapsed_time": "4:35:02", "remaining_time": "2:34:55", "throughput": 1487.29, "total_tokens": 24543488} {"current_steps": 116300, "total_steps": 181800, "loss": 0.0074, "lr": 1.72987746971088e-05, "epoch": 12.794279427942794, "percentage": 63.97, "elapsed_time": "4:35:02", "remaining_time": "2:34:54", "throughput": 1487.29, "total_tokens": 24544512} {"current_steps": 116305, "total_steps": 181800, "loss": 0.027, "lr": 1.7296491378994797e-05, "epoch": 12.794829482948295, "percentage": 63.97, "elapsed_time": "4:35:03", "remaining_time": "2:34:53", "throughput": 1487.29, "total_tokens": 24545600} {"current_steps": 116310, "total_steps": 181800, "loss": 0.0453, "lr": 1.7294208131880346e-05, "epoch": 12.795379537953796, "percentage": 63.98, "elapsed_time": "4:35:04", "remaining_time": "2:34:52", "throughput": 1487.3, "total_tokens": 24546656} {"current_steps": 116315, "total_steps": 181800, "loss": 0.0021, "lr": 1.7291924955786484e-05, "epoch": 12.795929592959295, "percentage": 63.98, "elapsed_time": "4:35:04", "remaining_time": "2:34:52", "throughput": 1487.3, "total_tokens": 24547744} {"current_steps": 116320, "total_steps": 181800, "loss": 0.0078, "lr": 1.728964185073424e-05, "epoch": 12.796479647964796, "percentage": 63.98, "elapsed_time": "4:35:05", "remaining_time": "2:34:51", "throughput": 1487.3, "total_tokens": 24548768} {"current_steps": 116325, "total_steps": 181800, "loss": 0.0295, "lr": 1.7287358816744677e-05, "epoch": 12.797029702970297, "percentage": 63.99, "elapsed_time": "4:35:06", "remaining_time": "2:34:50", "throughput": 1487.3, "total_tokens": 24549856} {"current_steps": 116330, "total_steps": 181800, "loss": 0.0034, "lr": 1.7285075853838816e-05, "epoch": 12.797579757975798, "percentage": 63.99, "elapsed_time": "4:35:06", "remaining_time": "2:34:50", "throughput": 1487.31, "total_tokens": 24550944} {"current_steps": 116335, "total_steps": 181800, "loss": 0.1081, "lr": 1.7282792962037726e-05, "epoch": 12.798129812981298, "percentage": 63.99, "elapsed_time": "4:35:07", "remaining_time": "2:34:49", "throughput": 1487.31, "total_tokens": 24552032} {"current_steps": 116340, "total_steps": 181800, "loss": 0.0044, "lr": 1.728051014136242e-05, "epoch": 12.798679867986799, "percentage": 63.99, "elapsed_time": "4:35:08", "remaining_time": "2:34:48", "throughput": 1487.31, "total_tokens": 24553088} {"current_steps": 116345, "total_steps": 181800, "loss": 0.0153, "lr": 1.7278227391833942e-05, "epoch": 12.7992299229923, "percentage": 64.0, "elapsed_time": "4:35:09", "remaining_time": "2:34:47", "throughput": 1487.32, "total_tokens": 24554144} {"current_steps": 116350, "total_steps": 181800, "loss": 0.0419, "lr": 1.727594471347335e-05, "epoch": 12.7997799779978, "percentage": 64.0, "elapsed_time": "4:35:09", "remaining_time": "2:34:47", "throughput": 1487.32, "total_tokens": 24555168} {"current_steps": 116355, "total_steps": 181800, "loss": 0.0296, "lr": 1.7273662106301652e-05, "epoch": 12.8003300330033, "percentage": 64.0, "elapsed_time": "4:35:10", "remaining_time": "2:34:46", "throughput": 1487.32, "total_tokens": 24556320} {"current_steps": 116360, "total_steps": 181800, "loss": 0.0052, "lr": 1.727137957033992e-05, "epoch": 12.800880088008801, "percentage": 64.0, "elapsed_time": "4:35:11", "remaining_time": "2:34:45", "throughput": 1487.33, "total_tokens": 24557408} {"current_steps": 116365, "total_steps": 181800, "loss": 0.0087, "lr": 1.7269097105609168e-05, "epoch": 12.8014301430143, "percentage": 64.01, "elapsed_time": "4:35:11", "remaining_time": "2:34:45", "throughput": 1487.33, "total_tokens": 24558464} {"current_steps": 116370, "total_steps": 181800, "loss": 0.0438, "lr": 1.726681471213043e-05, "epoch": 12.801980198019802, "percentage": 64.01, "elapsed_time": "4:35:12", "remaining_time": "2:34:44", "throughput": 1487.33, "total_tokens": 24559520} {"current_steps": 116375, "total_steps": 181800, "loss": 0.0042, "lr": 1.7264532389924764e-05, "epoch": 12.802530253025303, "percentage": 64.01, "elapsed_time": "4:35:13", "remaining_time": "2:34:43", "throughput": 1487.33, "total_tokens": 24560608} {"current_steps": 116380, "total_steps": 181800, "loss": 0.0022, "lr": 1.726225013901318e-05, "epoch": 12.803080308030804, "percentage": 64.02, "elapsed_time": "4:35:13", "remaining_time": "2:34:42", "throughput": 1487.34, "total_tokens": 24561696} {"current_steps": 116385, "total_steps": 181800, "loss": 0.1032, "lr": 1.7259967959416727e-05, "epoch": 12.803630363036303, "percentage": 64.02, "elapsed_time": "4:35:14", "remaining_time": "2:34:42", "throughput": 1487.34, "total_tokens": 24562752} {"current_steps": 116390, "total_steps": 181800, "loss": 0.0514, "lr": 1.7257685851156447e-05, "epoch": 12.804180418041804, "percentage": 64.02, "elapsed_time": "4:35:15", "remaining_time": "2:34:41", "throughput": 1487.34, "total_tokens": 24563808} {"current_steps": 116395, "total_steps": 181800, "loss": 0.0067, "lr": 1.7255403814253347e-05, "epoch": 12.804730473047305, "percentage": 64.02, "elapsed_time": "4:35:15", "remaining_time": "2:34:40", "throughput": 1487.34, "total_tokens": 24564864} {"current_steps": 116400, "total_steps": 181800, "loss": 0.0074, "lr": 1.7253121848728477e-05, "epoch": 12.805280528052805, "percentage": 64.03, "elapsed_time": "4:35:16", "remaining_time": "2:34:39", "throughput": 1487.35, "total_tokens": 24565920} {"current_steps": 116405, "total_steps": 181800, "loss": 0.0283, "lr": 1.725083995460286e-05, "epoch": 12.805830583058306, "percentage": 64.03, "elapsed_time": "4:35:17", "remaining_time": "2:34:39", "throughput": 1487.35, "total_tokens": 24566976} {"current_steps": 116410, "total_steps": 181800, "loss": 0.0024, "lr": 1.7248558131897546e-05, "epoch": 12.806380638063807, "percentage": 64.03, "elapsed_time": "4:35:17", "remaining_time": "2:34:38", "throughput": 1487.35, "total_tokens": 24568000} {"current_steps": 116415, "total_steps": 181800, "loss": 0.0267, "lr": 1.7246276380633546e-05, "epoch": 12.806930693069306, "percentage": 64.03, "elapsed_time": "4:35:18", "remaining_time": "2:34:37", "throughput": 1487.35, "total_tokens": 24569056} {"current_steps": 116420, "total_steps": 181800, "loss": 0.0045, "lr": 1.724399470083189e-05, "epoch": 12.807480748074807, "percentage": 64.04, "elapsed_time": "4:35:19", "remaining_time": "2:34:37", "throughput": 1487.35, "total_tokens": 24570080} {"current_steps": 116425, "total_steps": 181800, "loss": 0.0805, "lr": 1.7241713092513616e-05, "epoch": 12.808030803080309, "percentage": 64.04, "elapsed_time": "4:35:20", "remaining_time": "2:34:36", "throughput": 1487.35, "total_tokens": 24571136} {"current_steps": 116430, "total_steps": 181800, "loss": 0.0445, "lr": 1.7239431555699757e-05, "epoch": 12.808580858085808, "percentage": 64.04, "elapsed_time": "4:35:20", "remaining_time": "2:34:35", "throughput": 1487.35, "total_tokens": 24572160} {"current_steps": 116435, "total_steps": 181800, "loss": 0.0569, "lr": 1.7237150090411326e-05, "epoch": 12.809130913091309, "percentage": 64.05, "elapsed_time": "4:35:21", "remaining_time": "2:34:34", "throughput": 1487.35, "total_tokens": 24573184} {"current_steps": 116440, "total_steps": 181800, "loss": 0.0045, "lr": 1.7234868696669362e-05, "epoch": 12.80968096809681, "percentage": 64.05, "elapsed_time": "4:35:22", "remaining_time": "2:34:34", "throughput": 1487.35, "total_tokens": 24574240} {"current_steps": 116445, "total_steps": 181800, "loss": 0.0048, "lr": 1.7232587374494878e-05, "epoch": 12.810231023102311, "percentage": 64.05, "elapsed_time": "4:35:22", "remaining_time": "2:34:33", "throughput": 1487.36, "total_tokens": 24575296} {"current_steps": 116450, "total_steps": 181800, "loss": 0.0022, "lr": 1.7230306123908923e-05, "epoch": 12.81078107810781, "percentage": 64.05, "elapsed_time": "4:35:23", "remaining_time": "2:34:32", "throughput": 1487.35, "total_tokens": 24576320} {"current_steps": 116455, "total_steps": 181800, "loss": 0.0042, "lr": 1.72280249449325e-05, "epoch": 12.811331133113312, "percentage": 64.06, "elapsed_time": "4:35:24", "remaining_time": "2:34:32", "throughput": 1487.36, "total_tokens": 24577376} {"current_steps": 116460, "total_steps": 181800, "loss": 0.0042, "lr": 1.722574383758664e-05, "epoch": 12.811881188118813, "percentage": 64.06, "elapsed_time": "4:35:24", "remaining_time": "2:34:31", "throughput": 1487.36, "total_tokens": 24578464} {"current_steps": 116465, "total_steps": 181800, "loss": 0.0505, "lr": 1.722346280189238e-05, "epoch": 12.812431243124312, "percentage": 64.06, "elapsed_time": "4:35:25", "remaining_time": "2:34:30", "throughput": 1487.36, "total_tokens": 24579552} {"current_steps": 116470, "total_steps": 181800, "loss": 0.0034, "lr": 1.722118183787072e-05, "epoch": 12.812981298129813, "percentage": 64.06, "elapsed_time": "4:35:26", "remaining_time": "2:34:29", "throughput": 1487.36, "total_tokens": 24580576} {"current_steps": 116475, "total_steps": 181800, "loss": 0.0577, "lr": 1.7218900945542698e-05, "epoch": 12.813531353135314, "percentage": 64.07, "elapsed_time": "4:35:26", "remaining_time": "2:34:29", "throughput": 1487.36, "total_tokens": 24581536} {"current_steps": 116480, "total_steps": 181800, "loss": 0.0098, "lr": 1.7216620124929335e-05, "epoch": 12.814081408140813, "percentage": 64.07, "elapsed_time": "4:35:27", "remaining_time": "2:34:28", "throughput": 1487.36, "total_tokens": 24582592} {"current_steps": 116485, "total_steps": 181800, "loss": 0.0214, "lr": 1.721433937605164e-05, "epoch": 12.814631463146315, "percentage": 64.07, "elapsed_time": "4:35:28", "remaining_time": "2:34:27", "throughput": 1487.36, "total_tokens": 24583584} {"current_steps": 116490, "total_steps": 181800, "loss": 0.0623, "lr": 1.7212058698930655e-05, "epoch": 12.815181518151816, "percentage": 64.08, "elapsed_time": "4:35:29", "remaining_time": "2:34:26", "throughput": 1487.36, "total_tokens": 24584640} {"current_steps": 116495, "total_steps": 181800, "loss": 0.0089, "lr": 1.720977809358738e-05, "epoch": 12.815731573157315, "percentage": 64.08, "elapsed_time": "4:35:29", "remaining_time": "2:34:26", "throughput": 1487.36, "total_tokens": 24585664} {"current_steps": 116500, "total_steps": 181800, "loss": 0.0025, "lr": 1.7207497560042843e-05, "epoch": 12.816281628162816, "percentage": 64.08, "elapsed_time": "4:35:30", "remaining_time": "2:34:25", "throughput": 1487.37, "total_tokens": 24586752} {"current_steps": 116505, "total_steps": 181800, "loss": 0.0752, "lr": 1.720521709831807e-05, "epoch": 12.816831683168317, "percentage": 64.08, "elapsed_time": "4:35:31", "remaining_time": "2:34:24", "throughput": 1487.36, "total_tokens": 24587776} {"current_steps": 116510, "total_steps": 181800, "loss": 0.0031, "lr": 1.720293670843406e-05, "epoch": 12.817381738173818, "percentage": 64.09, "elapsed_time": "4:35:31", "remaining_time": "2:34:24", "throughput": 1487.36, "total_tokens": 24588800} {"current_steps": 116515, "total_steps": 181800, "loss": 0.0297, "lr": 1.7200656390411847e-05, "epoch": 12.817931793179318, "percentage": 64.09, "elapsed_time": "4:35:32", "remaining_time": "2:34:23", "throughput": 1487.36, "total_tokens": 24589792} {"current_steps": 116520, "total_steps": 181800, "loss": 0.008, "lr": 1.719837614427243e-05, "epoch": 12.818481848184819, "percentage": 64.09, "elapsed_time": "4:35:33", "remaining_time": "2:34:22", "throughput": 1487.36, "total_tokens": 24590816} {"current_steps": 116525, "total_steps": 181800, "loss": 0.0043, "lr": 1.719609597003686e-05, "epoch": 12.81903190319032, "percentage": 64.1, "elapsed_time": "4:35:33", "remaining_time": "2:34:21", "throughput": 1487.37, "total_tokens": 24591936} {"current_steps": 116530, "total_steps": 181800, "loss": 0.0573, "lr": 1.7193815867726114e-05, "epoch": 12.819581958195819, "percentage": 64.1, "elapsed_time": "4:35:34", "remaining_time": "2:34:21", "throughput": 1487.37, "total_tokens": 24592928} {"current_steps": 116535, "total_steps": 181800, "loss": 0.0406, "lr": 1.7191535837361215e-05, "epoch": 12.82013201320132, "percentage": 64.1, "elapsed_time": "4:35:35", "remaining_time": "2:34:20", "throughput": 1487.37, "total_tokens": 24594016} {"current_steps": 116540, "total_steps": 181800, "loss": 0.0296, "lr": 1.718925587896319e-05, "epoch": 12.820682068206821, "percentage": 64.1, "elapsed_time": "4:35:35", "remaining_time": "2:34:19", "throughput": 1487.37, "total_tokens": 24595072} {"current_steps": 116545, "total_steps": 181800, "loss": 0.0073, "lr": 1.7186975992553047e-05, "epoch": 12.82123212321232, "percentage": 64.11, "elapsed_time": "4:35:36", "remaining_time": "2:34:19", "throughput": 1487.37, "total_tokens": 24596096} {"current_steps": 116550, "total_steps": 181800, "loss": 0.0023, "lr": 1.71846961781518e-05, "epoch": 12.821782178217822, "percentage": 64.11, "elapsed_time": "4:35:37", "remaining_time": "2:34:18", "throughput": 1487.37, "total_tokens": 24597152} {"current_steps": 116555, "total_steps": 181800, "loss": 0.0178, "lr": 1.7182416435780454e-05, "epoch": 12.822332233223323, "percentage": 64.11, "elapsed_time": "4:35:37", "remaining_time": "2:34:17", "throughput": 1487.37, "total_tokens": 24598176} {"current_steps": 116560, "total_steps": 181800, "loss": 0.0263, "lr": 1.718013676546002e-05, "epoch": 12.822882288228822, "percentage": 64.11, "elapsed_time": "4:35:38", "remaining_time": "2:34:16", "throughput": 1487.38, "total_tokens": 24599232} {"current_steps": 116565, "total_steps": 181800, "loss": 0.0796, "lr": 1.7177857167211527e-05, "epoch": 12.823432343234323, "percentage": 64.12, "elapsed_time": "4:35:39", "remaining_time": "2:34:16", "throughput": 1487.37, "total_tokens": 24600224} {"current_steps": 116570, "total_steps": 181800, "loss": 0.0074, "lr": 1.7175577641055957e-05, "epoch": 12.823982398239824, "percentage": 64.12, "elapsed_time": "4:35:40", "remaining_time": "2:34:15", "throughput": 1487.37, "total_tokens": 24601248} {"current_steps": 116575, "total_steps": 181800, "loss": 0.2243, "lr": 1.717329818701434e-05, "epoch": 12.824532453245325, "percentage": 64.12, "elapsed_time": "4:35:40", "remaining_time": "2:34:14", "throughput": 1487.37, "total_tokens": 24602272} {"current_steps": 116580, "total_steps": 181800, "loss": 0.0635, "lr": 1.717101880510768e-05, "epoch": 12.825082508250825, "percentage": 64.13, "elapsed_time": "4:35:41", "remaining_time": "2:34:14", "throughput": 1487.38, "total_tokens": 24603360} {"current_steps": 116585, "total_steps": 181800, "loss": 0.0025, "lr": 1.7168739495356977e-05, "epoch": 12.825632563256326, "percentage": 64.13, "elapsed_time": "4:35:42", "remaining_time": "2:34:13", "throughput": 1487.38, "total_tokens": 24604448} {"current_steps": 116590, "total_steps": 181800, "loss": 0.0397, "lr": 1.716646025778325e-05, "epoch": 12.826182618261827, "percentage": 64.13, "elapsed_time": "4:35:42", "remaining_time": "2:34:12", "throughput": 1487.38, "total_tokens": 24605536} {"current_steps": 116595, "total_steps": 181800, "loss": 0.113, "lr": 1.716418109240749e-05, "epoch": 12.826732673267326, "percentage": 64.13, "elapsed_time": "4:35:43", "remaining_time": "2:34:11", "throughput": 1487.39, "total_tokens": 24606656} {"current_steps": 116600, "total_steps": 181800, "loss": 0.0249, "lr": 1.716190199925072e-05, "epoch": 12.827282728272827, "percentage": 64.14, "elapsed_time": "4:35:44", "remaining_time": "2:34:11", "throughput": 1487.39, "total_tokens": 24607712} {"current_steps": 116605, "total_steps": 181800, "loss": 0.0085, "lr": 1.7159622978333945e-05, "epoch": 12.827832783278328, "percentage": 64.14, "elapsed_time": "4:35:44", "remaining_time": "2:34:10", "throughput": 1487.39, "total_tokens": 24608768} {"current_steps": 116610, "total_steps": 181800, "loss": 0.0815, "lr": 1.715734402967815e-05, "epoch": 12.828382838283828, "percentage": 64.14, "elapsed_time": "4:35:45", "remaining_time": "2:34:09", "throughput": 1487.4, "total_tokens": 24609824} {"current_steps": 116615, "total_steps": 181800, "loss": 0.0298, "lr": 1.715506515330436e-05, "epoch": 12.828932893289329, "percentage": 64.14, "elapsed_time": "4:35:46", "remaining_time": "2:34:08", "throughput": 1487.39, "total_tokens": 24610816} {"current_steps": 116620, "total_steps": 181800, "loss": 0.1381, "lr": 1.7152786349233573e-05, "epoch": 12.82948294829483, "percentage": 64.15, "elapsed_time": "4:35:46", "remaining_time": "2:34:08", "throughput": 1487.39, "total_tokens": 24611808} {"current_steps": 116625, "total_steps": 181800, "loss": 0.0295, "lr": 1.715050761748678e-05, "epoch": 12.83003300330033, "percentage": 64.15, "elapsed_time": "4:35:47", "remaining_time": "2:34:07", "throughput": 1487.39, "total_tokens": 24612832} {"current_steps": 116630, "total_steps": 181800, "loss": 0.2167, "lr": 1.7148228958084994e-05, "epoch": 12.83058305830583, "percentage": 64.15, "elapsed_time": "4:35:48", "remaining_time": "2:34:06", "throughput": 1487.39, "total_tokens": 24613888} {"current_steps": 116635, "total_steps": 181800, "loss": 0.0484, "lr": 1.7145950371049215e-05, "epoch": 12.831133113311331, "percentage": 64.16, "elapsed_time": "4:35:49", "remaining_time": "2:34:06", "throughput": 1487.4, "total_tokens": 24614976} {"current_steps": 116640, "total_steps": 181800, "loss": 0.0774, "lr": 1.7143671856400444e-05, "epoch": 12.831683168316832, "percentage": 64.16, "elapsed_time": "4:35:49", "remaining_time": "2:34:05", "throughput": 1487.4, "total_tokens": 24616032} {"current_steps": 116645, "total_steps": 181800, "loss": 0.0368, "lr": 1.714139341415968e-05, "epoch": 12.832233223322332, "percentage": 64.16, "elapsed_time": "4:35:50", "remaining_time": "2:34:04", "throughput": 1487.4, "total_tokens": 24617088} {"current_steps": 116650, "total_steps": 181800, "loss": 0.0111, "lr": 1.713911504434792e-05, "epoch": 12.832783278327833, "percentage": 64.16, "elapsed_time": "4:35:51", "remaining_time": "2:34:03", "throughput": 1487.4, "total_tokens": 24618176} {"current_steps": 116655, "total_steps": 181800, "loss": 0.0025, "lr": 1.713683674698617e-05, "epoch": 12.833333333333334, "percentage": 64.17, "elapsed_time": "4:35:51", "remaining_time": "2:34:03", "throughput": 1487.41, "total_tokens": 24619232} {"current_steps": 116660, "total_steps": 181800, "loss": 0.0048, "lr": 1.7134558522095407e-05, "epoch": 12.833883388338833, "percentage": 64.17, "elapsed_time": "4:35:52", "remaining_time": "2:34:02", "throughput": 1487.41, "total_tokens": 24620320} {"current_steps": 116665, "total_steps": 181800, "loss": 0.0306, "lr": 1.713228036969666e-05, "epoch": 12.834433443344334, "percentage": 64.17, "elapsed_time": "4:35:53", "remaining_time": "2:34:01", "throughput": 1487.42, "total_tokens": 24621440} {"current_steps": 116670, "total_steps": 181800, "loss": 0.0964, "lr": 1.7130002289810902e-05, "epoch": 12.834983498349835, "percentage": 64.17, "elapsed_time": "4:35:53", "remaining_time": "2:34:01", "throughput": 1487.42, "total_tokens": 24622464} {"current_steps": 116675, "total_steps": 181800, "loss": 0.0321, "lr": 1.7127724282459136e-05, "epoch": 12.835533553355335, "percentage": 64.18, "elapsed_time": "4:35:54", "remaining_time": "2:34:00", "throughput": 1487.42, "total_tokens": 24623488} {"current_steps": 116680, "total_steps": 181800, "loss": 0.022, "lr": 1.7125446347662365e-05, "epoch": 12.836083608360836, "percentage": 64.18, "elapsed_time": "4:35:55", "remaining_time": "2:33:59", "throughput": 1487.41, "total_tokens": 24624480} {"current_steps": 116685, "total_steps": 181800, "loss": 0.0044, "lr": 1.712316848544157e-05, "epoch": 12.836633663366337, "percentage": 64.18, "elapsed_time": "4:35:55", "remaining_time": "2:33:58", "throughput": 1487.42, "total_tokens": 24625568} {"current_steps": 116690, "total_steps": 181800, "loss": 0.0371, "lr": 1.7120890695817752e-05, "epoch": 12.837183718371836, "percentage": 64.19, "elapsed_time": "4:35:56", "remaining_time": "2:33:58", "throughput": 1487.42, "total_tokens": 24626624} {"current_steps": 116695, "total_steps": 181800, "loss": 0.0583, "lr": 1.7118612978811913e-05, "epoch": 12.837733773377337, "percentage": 64.19, "elapsed_time": "4:35:57", "remaining_time": "2:33:57", "throughput": 1487.42, "total_tokens": 24627680} {"current_steps": 116700, "total_steps": 181800, "loss": 0.0053, "lr": 1.7116335334445023e-05, "epoch": 12.838283828382838, "percentage": 64.19, "elapsed_time": "4:35:57", "remaining_time": "2:33:56", "throughput": 1487.43, "total_tokens": 24628768} {"current_steps": 116705, "total_steps": 181800, "loss": 0.04, "lr": 1.7114057762738094e-05, "epoch": 12.83883388338834, "percentage": 64.19, "elapsed_time": "4:35:58", "remaining_time": "2:33:55", "throughput": 1487.43, "total_tokens": 24629792} {"current_steps": 116710, "total_steps": 181800, "loss": 0.0123, "lr": 1.7111780263712103e-05, "epoch": 12.839383938393839, "percentage": 64.2, "elapsed_time": "4:35:59", "remaining_time": "2:33:55", "throughput": 1487.43, "total_tokens": 24630880} {"current_steps": 116715, "total_steps": 181800, "loss": 0.0143, "lr": 1.7109502837388062e-05, "epoch": 12.83993399339934, "percentage": 64.2, "elapsed_time": "4:36:00", "remaining_time": "2:33:54", "throughput": 1487.43, "total_tokens": 24631968} {"current_steps": 116720, "total_steps": 181800, "loss": 0.0148, "lr": 1.710722548378694e-05, "epoch": 12.840484048404841, "percentage": 64.2, "elapsed_time": "4:36:00", "remaining_time": "2:33:53", "throughput": 1487.43, "total_tokens": 24632960} {"current_steps": 116725, "total_steps": 181800, "loss": 0.1276, "lr": 1.710494820292973e-05, "epoch": 12.84103410341034, "percentage": 64.21, "elapsed_time": "4:36:01", "remaining_time": "2:33:53", "throughput": 1487.43, "total_tokens": 24634016} {"current_steps": 116730, "total_steps": 181800, "loss": 0.0696, "lr": 1.7102670994837428e-05, "epoch": 12.841584158415841, "percentage": 64.21, "elapsed_time": "4:36:02", "remaining_time": "2:33:52", "throughput": 1487.43, "total_tokens": 24635040} {"current_steps": 116735, "total_steps": 181800, "loss": 0.0459, "lr": 1.710039385953101e-05, "epoch": 12.842134213421343, "percentage": 64.21, "elapsed_time": "4:36:02", "remaining_time": "2:33:51", "throughput": 1487.44, "total_tokens": 24636128} {"current_steps": 116740, "total_steps": 181800, "loss": 0.0662, "lr": 1.7098116797031483e-05, "epoch": 12.842684268426842, "percentage": 64.21, "elapsed_time": "4:36:03", "remaining_time": "2:33:50", "throughput": 1487.44, "total_tokens": 24637184} {"current_steps": 116745, "total_steps": 181800, "loss": 0.0052, "lr": 1.709583980735982e-05, "epoch": 12.843234323432343, "percentage": 64.22, "elapsed_time": "4:36:04", "remaining_time": "2:33:50", "throughput": 1487.44, "total_tokens": 24638176} {"current_steps": 116750, "total_steps": 181800, "loss": 0.0295, "lr": 1.7093562890537e-05, "epoch": 12.843784378437844, "percentage": 64.22, "elapsed_time": "4:36:04", "remaining_time": "2:33:49", "throughput": 1487.44, "total_tokens": 24639168} {"current_steps": 116755, "total_steps": 181800, "loss": 0.003, "lr": 1.7091286046584026e-05, "epoch": 12.844334433443345, "percentage": 64.22, "elapsed_time": "4:36:05", "remaining_time": "2:33:48", "throughput": 1487.44, "total_tokens": 24640192} {"current_steps": 116760, "total_steps": 181800, "loss": 0.009, "lr": 1.7089009275521867e-05, "epoch": 12.844884488448844, "percentage": 64.22, "elapsed_time": "4:36:06", "remaining_time": "2:33:48", "throughput": 1487.44, "total_tokens": 24641280} {"current_steps": 116765, "total_steps": 181800, "loss": 0.0418, "lr": 1.7086732577371516e-05, "epoch": 12.845434543454346, "percentage": 64.23, "elapsed_time": "4:36:06", "remaining_time": "2:33:47", "throughput": 1487.44, "total_tokens": 24642336} {"current_steps": 116770, "total_steps": 181800, "loss": 0.1166, "lr": 1.708445595215396e-05, "epoch": 12.845984598459847, "percentage": 64.23, "elapsed_time": "4:36:07", "remaining_time": "2:33:46", "throughput": 1487.44, "total_tokens": 24643360} {"current_steps": 116775, "total_steps": 181800, "loss": 0.0364, "lr": 1.708217939989016e-05, "epoch": 12.846534653465346, "percentage": 64.23, "elapsed_time": "4:36:08", "remaining_time": "2:33:45", "throughput": 1487.44, "total_tokens": 24644416} {"current_steps": 116780, "total_steps": 181800, "loss": 0.0914, "lr": 1.707990292060113e-05, "epoch": 12.847084708470847, "percentage": 64.24, "elapsed_time": "4:36:08", "remaining_time": "2:33:45", "throughput": 1487.44, "total_tokens": 24645408} {"current_steps": 116785, "total_steps": 181800, "loss": 0.0019, "lr": 1.707762651430782e-05, "epoch": 12.847634763476348, "percentage": 64.24, "elapsed_time": "4:36:09", "remaining_time": "2:33:44", "throughput": 1487.45, "total_tokens": 24646528} {"current_steps": 116790, "total_steps": 181800, "loss": 0.0466, "lr": 1.7075350181031235e-05, "epoch": 12.848184818481847, "percentage": 64.24, "elapsed_time": "4:36:10", "remaining_time": "2:33:43", "throughput": 1487.45, "total_tokens": 24647616} {"current_steps": 116795, "total_steps": 181800, "loss": 0.0558, "lr": 1.707307392079235e-05, "epoch": 12.848734873487349, "percentage": 64.24, "elapsed_time": "4:36:11", "remaining_time": "2:33:43", "throughput": 1487.45, "total_tokens": 24648672} {"current_steps": 116800, "total_steps": 181800, "loss": 0.0067, "lr": 1.7070797733612123e-05, "epoch": 12.84928492849285, "percentage": 64.25, "elapsed_time": "4:36:11", "remaining_time": "2:33:42", "throughput": 1487.45, "total_tokens": 24649696} {"current_steps": 116805, "total_steps": 181800, "loss": 0.0073, "lr": 1.7068521619511558e-05, "epoch": 12.84983498349835, "percentage": 64.25, "elapsed_time": "4:36:12", "remaining_time": "2:33:41", "throughput": 1487.45, "total_tokens": 24650688} {"current_steps": 116810, "total_steps": 181800, "loss": 0.0041, "lr": 1.7066245578511623e-05, "epoch": 12.85038503850385, "percentage": 64.25, "elapsed_time": "4:36:13", "remaining_time": "2:33:40", "throughput": 1487.45, "total_tokens": 24651744} {"current_steps": 116815, "total_steps": 181800, "loss": 0.0376, "lr": 1.7063969610633292e-05, "epoch": 12.850935093509351, "percentage": 64.25, "elapsed_time": "4:36:13", "remaining_time": "2:33:40", "throughput": 1487.45, "total_tokens": 24652736} {"current_steps": 116820, "total_steps": 181800, "loss": 0.0062, "lr": 1.7061693715897546e-05, "epoch": 12.851485148514852, "percentage": 64.26, "elapsed_time": "4:36:14", "remaining_time": "2:33:39", "throughput": 1487.45, "total_tokens": 24653760} {"current_steps": 116825, "total_steps": 181800, "loss": 0.0091, "lr": 1.705941789432536e-05, "epoch": 12.852035203520352, "percentage": 64.26, "elapsed_time": "4:36:15", "remaining_time": "2:33:38", "throughput": 1487.45, "total_tokens": 24654848} {"current_steps": 116830, "total_steps": 181800, "loss": 0.0247, "lr": 1.7057142145937717e-05, "epoch": 12.852585258525853, "percentage": 64.26, "elapsed_time": "4:36:15", "remaining_time": "2:33:37", "throughput": 1487.45, "total_tokens": 24655840} {"current_steps": 116835, "total_steps": 181800, "loss": 0.0367, "lr": 1.7054866470755574e-05, "epoch": 12.853135313531354, "percentage": 64.27, "elapsed_time": "4:36:16", "remaining_time": "2:33:37", "throughput": 1487.45, "total_tokens": 24656896} {"current_steps": 116840, "total_steps": 181800, "loss": 0.0041, "lr": 1.705259086879991e-05, "epoch": 12.853685368536853, "percentage": 64.27, "elapsed_time": "4:36:17", "remaining_time": "2:33:36", "throughput": 1487.46, "total_tokens": 24657984} {"current_steps": 116845, "total_steps": 181800, "loss": 0.0204, "lr": 1.705031534009171e-05, "epoch": 12.854235423542354, "percentage": 64.27, "elapsed_time": "4:36:17", "remaining_time": "2:33:35", "throughput": 1487.46, "total_tokens": 24659040} {"current_steps": 116850, "total_steps": 181800, "loss": 0.0321, "lr": 1.7048039884651934e-05, "epoch": 12.854785478547855, "percentage": 64.27, "elapsed_time": "4:36:18", "remaining_time": "2:33:35", "throughput": 1487.46, "total_tokens": 24660096} {"current_steps": 116855, "total_steps": 181800, "loss": 0.1316, "lr": 1.7045764502501568e-05, "epoch": 12.855335533553355, "percentage": 64.28, "elapsed_time": "4:36:19", "remaining_time": "2:33:34", "throughput": 1487.46, "total_tokens": 24661184} {"current_steps": 116860, "total_steps": 181800, "loss": 0.11, "lr": 1.704348919366157e-05, "epoch": 12.855885588558856, "percentage": 64.28, "elapsed_time": "4:36:20", "remaining_time": "2:33:33", "throughput": 1487.47, "total_tokens": 24662240} {"current_steps": 116865, "total_steps": 181800, "loss": 0.0303, "lr": 1.7041213958152907e-05, "epoch": 12.856435643564357, "percentage": 64.28, "elapsed_time": "4:36:20", "remaining_time": "2:33:32", "throughput": 1487.46, "total_tokens": 24663200} {"current_steps": 116870, "total_steps": 181800, "loss": 0.0076, "lr": 1.7038938795996567e-05, "epoch": 12.856985698569858, "percentage": 64.28, "elapsed_time": "4:36:21", "remaining_time": "2:33:32", "throughput": 1487.46, "total_tokens": 24664224} {"current_steps": 116875, "total_steps": 181800, "loss": 0.071, "lr": 1.7036663707213498e-05, "epoch": 12.857535753575357, "percentage": 64.29, "elapsed_time": "4:36:22", "remaining_time": "2:33:31", "throughput": 1487.46, "total_tokens": 24665248} {"current_steps": 116880, "total_steps": 181800, "loss": 0.0093, "lr": 1.7034388691824684e-05, "epoch": 12.858085808580858, "percentage": 64.29, "elapsed_time": "4:36:22", "remaining_time": "2:33:30", "throughput": 1487.46, "total_tokens": 24666272} {"current_steps": 116885, "total_steps": 181800, "loss": 0.0012, "lr": 1.7032113749851093e-05, "epoch": 12.85863586358636, "percentage": 64.29, "elapsed_time": "4:36:23", "remaining_time": "2:33:30", "throughput": 1487.46, "total_tokens": 24667296} {"current_steps": 116890, "total_steps": 181800, "loss": 0.0092, "lr": 1.7029838881313677e-05, "epoch": 12.859185918591859, "percentage": 64.3, "elapsed_time": "4:36:24", "remaining_time": "2:33:29", "throughput": 1487.46, "total_tokens": 24668352} {"current_steps": 116895, "total_steps": 181800, "loss": 0.0628, "lr": 1.702756408623341e-05, "epoch": 12.85973597359736, "percentage": 64.3, "elapsed_time": "4:36:24", "remaining_time": "2:33:28", "throughput": 1487.46, "total_tokens": 24669408} {"current_steps": 116900, "total_steps": 181800, "loss": 0.0105, "lr": 1.702528936463126e-05, "epoch": 12.86028602860286, "percentage": 64.3, "elapsed_time": "4:36:25", "remaining_time": "2:33:27", "throughput": 1487.47, "total_tokens": 24670496} {"current_steps": 116905, "total_steps": 181800, "loss": 0.0015, "lr": 1.7023014716528197e-05, "epoch": 12.86083608360836, "percentage": 64.3, "elapsed_time": "4:36:26", "remaining_time": "2:33:27", "throughput": 1487.47, "total_tokens": 24671520} {"current_steps": 116910, "total_steps": 181800, "loss": 0.0021, "lr": 1.702074014194518e-05, "epoch": 12.861386138613861, "percentage": 64.31, "elapsed_time": "4:36:26", "remaining_time": "2:33:26", "throughput": 1487.47, "total_tokens": 24672576} {"current_steps": 116915, "total_steps": 181800, "loss": 0.1369, "lr": 1.7018465640903164e-05, "epoch": 12.861936193619362, "percentage": 64.31, "elapsed_time": "4:36:27", "remaining_time": "2:33:25", "throughput": 1487.47, "total_tokens": 24673664} {"current_steps": 116920, "total_steps": 181800, "loss": 0.005, "lr": 1.7016191213423128e-05, "epoch": 12.862486248624862, "percentage": 64.31, "elapsed_time": "4:36:28", "remaining_time": "2:33:25", "throughput": 1487.47, "total_tokens": 24674688} {"current_steps": 116925, "total_steps": 181800, "loss": 0.0009, "lr": 1.701391685952602e-05, "epoch": 12.863036303630363, "percentage": 64.32, "elapsed_time": "4:36:29", "remaining_time": "2:33:24", "throughput": 1487.47, "total_tokens": 24675712} {"current_steps": 116930, "total_steps": 181800, "loss": 0.0064, "lr": 1.701164257923282e-05, "epoch": 12.863586358635864, "percentage": 64.32, "elapsed_time": "4:36:29", "remaining_time": "2:33:23", "throughput": 1487.47, "total_tokens": 24676736} {"current_steps": 116935, "total_steps": 181800, "loss": 0.0161, "lr": 1.7009368372564466e-05, "epoch": 12.864136413641365, "percentage": 64.32, "elapsed_time": "4:36:30", "remaining_time": "2:33:22", "throughput": 1487.48, "total_tokens": 24677824} {"current_steps": 116940, "total_steps": 181800, "loss": 0.0129, "lr": 1.7007094239541933e-05, "epoch": 12.864686468646864, "percentage": 64.32, "elapsed_time": "4:36:31", "remaining_time": "2:33:22", "throughput": 1487.48, "total_tokens": 24678880} {"current_steps": 116945, "total_steps": 181800, "loss": 0.0125, "lr": 1.7004820180186183e-05, "epoch": 12.865236523652365, "percentage": 64.33, "elapsed_time": "4:36:31", "remaining_time": "2:33:21", "throughput": 1487.48, "total_tokens": 24679936} {"current_steps": 116950, "total_steps": 181800, "loss": 0.0009, "lr": 1.7002546194518153e-05, "epoch": 12.865786578657866, "percentage": 64.33, "elapsed_time": "4:36:32", "remaining_time": "2:33:20", "throughput": 1487.48, "total_tokens": 24680928} {"current_steps": 116955, "total_steps": 181800, "loss": 0.0766, "lr": 1.7000272282558828e-05, "epoch": 12.866336633663366, "percentage": 64.33, "elapsed_time": "4:36:33", "remaining_time": "2:33:19", "throughput": 1487.48, "total_tokens": 24682016} {"current_steps": 116960, "total_steps": 181800, "loss": 0.0036, "lr": 1.699799844432916e-05, "epoch": 12.866886688668867, "percentage": 64.33, "elapsed_time": "4:36:33", "remaining_time": "2:33:19", "throughput": 1487.49, "total_tokens": 24683168} {"current_steps": 116965, "total_steps": 181800, "loss": 0.001, "lr": 1.6995724679850087e-05, "epoch": 12.867436743674368, "percentage": 64.34, "elapsed_time": "4:36:34", "remaining_time": "2:33:18", "throughput": 1487.49, "total_tokens": 24684224} {"current_steps": 116970, "total_steps": 181800, "loss": 0.0187, "lr": 1.699345098914259e-05, "epoch": 12.867986798679867, "percentage": 64.34, "elapsed_time": "4:36:35", "remaining_time": "2:33:17", "throughput": 1487.49, "total_tokens": 24685312} {"current_steps": 116975, "total_steps": 181800, "loss": 0.0328, "lr": 1.6991177372227607e-05, "epoch": 12.868536853685368, "percentage": 64.34, "elapsed_time": "4:36:35", "remaining_time": "2:33:17", "throughput": 1487.49, "total_tokens": 24686336} {"current_steps": 116980, "total_steps": 181800, "loss": 0.0048, "lr": 1.6988903829126102e-05, "epoch": 12.86908690869087, "percentage": 64.35, "elapsed_time": "4:36:36", "remaining_time": "2:33:16", "throughput": 1487.5, "total_tokens": 24687392} {"current_steps": 116985, "total_steps": 181800, "loss": 0.0035, "lr": 1.6986630359859034e-05, "epoch": 12.869636963696369, "percentage": 64.35, "elapsed_time": "4:36:37", "remaining_time": "2:33:15", "throughput": 1487.5, "total_tokens": 24688480} {"current_steps": 116990, "total_steps": 181800, "loss": 0.0114, "lr": 1.6984356964447336e-05, "epoch": 12.87018701870187, "percentage": 64.35, "elapsed_time": "4:36:38", "remaining_time": "2:33:14", "throughput": 1487.5, "total_tokens": 24689504} {"current_steps": 116995, "total_steps": 181800, "loss": 0.1269, "lr": 1.6982083642911978e-05, "epoch": 12.870737073707371, "percentage": 64.35, "elapsed_time": "4:36:38", "remaining_time": "2:33:14", "throughput": 1487.5, "total_tokens": 24690496} {"current_steps": 117000, "total_steps": 181800, "loss": 0.0016, "lr": 1.6979810395273912e-05, "epoch": 12.871287128712872, "percentage": 64.36, "elapsed_time": "4:36:39", "remaining_time": "2:33:13", "throughput": 1487.5, "total_tokens": 24691520} {"current_steps": 117005, "total_steps": 181800, "loss": 0.0102, "lr": 1.6977537221554077e-05, "epoch": 12.871837183718371, "percentage": 64.36, "elapsed_time": "4:36:40", "remaining_time": "2:33:12", "throughput": 1487.5, "total_tokens": 24692544} {"current_steps": 117010, "total_steps": 181800, "loss": 0.1227, "lr": 1.697526412177344e-05, "epoch": 12.872387238723872, "percentage": 64.36, "elapsed_time": "4:36:40", "remaining_time": "2:33:12", "throughput": 1487.5, "total_tokens": 24693600} {"current_steps": 117015, "total_steps": 181800, "loss": 0.0034, "lr": 1.697299109595293e-05, "epoch": 12.872937293729374, "percentage": 64.36, "elapsed_time": "4:36:41", "remaining_time": "2:33:11", "throughput": 1487.5, "total_tokens": 24694656} {"current_steps": 117020, "total_steps": 181800, "loss": 0.0042, "lr": 1.697071814411352e-05, "epoch": 12.873487348734873, "percentage": 64.37, "elapsed_time": "4:36:42", "remaining_time": "2:33:10", "throughput": 1487.5, "total_tokens": 24695712} {"current_steps": 117025, "total_steps": 181800, "loss": 0.0104, "lr": 1.6968445266276152e-05, "epoch": 12.874037403740374, "percentage": 64.37, "elapsed_time": "4:36:42", "remaining_time": "2:33:09", "throughput": 1487.5, "total_tokens": 24696768} {"current_steps": 117030, "total_steps": 181800, "loss": 0.0145, "lr": 1.696617246246176e-05, "epoch": 12.874587458745875, "percentage": 64.37, "elapsed_time": "4:36:43", "remaining_time": "2:33:09", "throughput": 1487.51, "total_tokens": 24697856} {"current_steps": 117035, "total_steps": 181800, "loss": 0.0011, "lr": 1.6963899732691308e-05, "epoch": 12.875137513751374, "percentage": 64.38, "elapsed_time": "4:36:44", "remaining_time": "2:33:08", "throughput": 1487.51, "total_tokens": 24698912} {"current_steps": 117040, "total_steps": 181800, "loss": 0.0626, "lr": 1.6961627076985728e-05, "epoch": 12.875687568756875, "percentage": 64.38, "elapsed_time": "4:36:44", "remaining_time": "2:33:07", "throughput": 1487.51, "total_tokens": 24699936} {"current_steps": 117045, "total_steps": 181800, "loss": 0.1096, "lr": 1.6959354495365986e-05, "epoch": 12.876237623762377, "percentage": 64.38, "elapsed_time": "4:36:45", "remaining_time": "2:33:07", "throughput": 1487.51, "total_tokens": 24700928} {"current_steps": 117050, "total_steps": 181800, "loss": 0.0121, "lr": 1.695708198785301e-05, "epoch": 12.876787678767876, "percentage": 64.38, "elapsed_time": "4:36:46", "remaining_time": "2:33:06", "throughput": 1487.51, "total_tokens": 24702016} {"current_steps": 117055, "total_steps": 181800, "loss": 0.0204, "lr": 1.6954809554467744e-05, "epoch": 12.877337733773377, "percentage": 64.39, "elapsed_time": "4:36:46", "remaining_time": "2:33:05", "throughput": 1487.51, "total_tokens": 24703008} {"current_steps": 117060, "total_steps": 181800, "loss": 0.0052, "lr": 1.695253719523115e-05, "epoch": 12.877887788778878, "percentage": 64.39, "elapsed_time": "4:36:47", "remaining_time": "2:33:04", "throughput": 1487.51, "total_tokens": 24704064} {"current_steps": 117065, "total_steps": 181800, "loss": 0.0588, "lr": 1.695026491016415e-05, "epoch": 12.87843784378438, "percentage": 64.39, "elapsed_time": "4:36:48", "remaining_time": "2:33:04", "throughput": 1487.51, "total_tokens": 24705120} {"current_steps": 117070, "total_steps": 181800, "loss": 0.0075, "lr": 1.6947992699287697e-05, "epoch": 12.878987898789878, "percentage": 64.39, "elapsed_time": "4:36:49", "remaining_time": "2:33:03", "throughput": 1487.51, "total_tokens": 24706144} {"current_steps": 117075, "total_steps": 181800, "loss": 0.0015, "lr": 1.6945720562622737e-05, "epoch": 12.87953795379538, "percentage": 64.4, "elapsed_time": "4:36:49", "remaining_time": "2:33:02", "throughput": 1487.51, "total_tokens": 24707200} {"current_steps": 117080, "total_steps": 181800, "loss": 0.0763, "lr": 1.6943448500190193e-05, "epoch": 12.88008800880088, "percentage": 64.4, "elapsed_time": "4:36:50", "remaining_time": "2:33:01", "throughput": 1487.51, "total_tokens": 24708192} {"current_steps": 117085, "total_steps": 181800, "loss": 0.0013, "lr": 1.694117651201103e-05, "epoch": 12.88063806380638, "percentage": 64.4, "elapsed_time": "4:36:51", "remaining_time": "2:33:01", "throughput": 1487.51, "total_tokens": 24709248} {"current_steps": 117090, "total_steps": 181800, "loss": 0.0756, "lr": 1.693890459810617e-05, "epoch": 12.881188118811881, "percentage": 64.41, "elapsed_time": "4:36:51", "remaining_time": "2:33:00", "throughput": 1487.52, "total_tokens": 24710368} {"current_steps": 117095, "total_steps": 181800, "loss": 0.0369, "lr": 1.693663275849656e-05, "epoch": 12.881738173817382, "percentage": 64.41, "elapsed_time": "4:36:52", "remaining_time": "2:32:59", "throughput": 1487.53, "total_tokens": 24711520} {"current_steps": 117100, "total_steps": 181800, "loss": 0.1924, "lr": 1.6934360993203145e-05, "epoch": 12.882288228822881, "percentage": 64.41, "elapsed_time": "4:36:53", "remaining_time": "2:32:59", "throughput": 1487.52, "total_tokens": 24712512} {"current_steps": 117105, "total_steps": 181800, "loss": 0.1194, "lr": 1.693208930224684e-05, "epoch": 12.882838283828383, "percentage": 64.41, "elapsed_time": "4:36:53", "remaining_time": "2:32:58", "throughput": 1487.53, "total_tokens": 24713568} {"current_steps": 117110, "total_steps": 181800, "loss": 0.008, "lr": 1.692981768564861e-05, "epoch": 12.883388338833884, "percentage": 64.42, "elapsed_time": "4:36:54", "remaining_time": "2:32:57", "throughput": 1487.53, "total_tokens": 24714624} {"current_steps": 117115, "total_steps": 181800, "loss": 0.0255, "lr": 1.6927546143429362e-05, "epoch": 12.883938393839383, "percentage": 64.42, "elapsed_time": "4:36:55", "remaining_time": "2:32:56", "throughput": 1487.53, "total_tokens": 24715680} {"current_steps": 117120, "total_steps": 181800, "loss": 0.0087, "lr": 1.6925274675610065e-05, "epoch": 12.884488448844884, "percentage": 64.42, "elapsed_time": "4:36:55", "remaining_time": "2:32:56", "throughput": 1487.53, "total_tokens": 24716736} {"current_steps": 117125, "total_steps": 181800, "loss": 0.0079, "lr": 1.692300328221163e-05, "epoch": 12.885038503850385, "percentage": 64.43, "elapsed_time": "4:36:56", "remaining_time": "2:32:55", "throughput": 1487.53, "total_tokens": 24717760} {"current_steps": 117130, "total_steps": 181800, "loss": 0.0074, "lr": 1.6920731963254992e-05, "epoch": 12.885588558855886, "percentage": 64.43, "elapsed_time": "4:36:57", "remaining_time": "2:32:54", "throughput": 1487.53, "total_tokens": 24718816} {"current_steps": 117135, "total_steps": 181800, "loss": 0.0038, "lr": 1.69184607187611e-05, "epoch": 12.886138613861386, "percentage": 64.43, "elapsed_time": "4:36:58", "remaining_time": "2:32:54", "throughput": 1487.54, "total_tokens": 24719904} {"current_steps": 117140, "total_steps": 181800, "loss": 0.0052, "lr": 1.6916189548750863e-05, "epoch": 12.886688668866887, "percentage": 64.43, "elapsed_time": "4:36:58", "remaining_time": "2:32:53", "throughput": 1487.54, "total_tokens": 24720992} {"current_steps": 117145, "total_steps": 181800, "loss": 0.0432, "lr": 1.6913918453245246e-05, "epoch": 12.887238723872388, "percentage": 64.44, "elapsed_time": "4:36:59", "remaining_time": "2:32:52", "throughput": 1487.54, "total_tokens": 24721984} {"current_steps": 117150, "total_steps": 181800, "loss": 0.0597, "lr": 1.6911647432265153e-05, "epoch": 12.887788778877887, "percentage": 64.44, "elapsed_time": "4:37:00", "remaining_time": "2:32:51", "throughput": 1487.54, "total_tokens": 24723040} {"current_steps": 117155, "total_steps": 181800, "loss": 0.0049, "lr": 1.6909376485831524e-05, "epoch": 12.888338833883388, "percentage": 64.44, "elapsed_time": "4:37:00", "remaining_time": "2:32:51", "throughput": 1487.54, "total_tokens": 24724096} {"current_steps": 117160, "total_steps": 181800, "loss": 0.0146, "lr": 1.6907105613965296e-05, "epoch": 12.88888888888889, "percentage": 64.44, "elapsed_time": "4:37:01", "remaining_time": "2:32:50", "throughput": 1487.55, "total_tokens": 24725184} {"current_steps": 117165, "total_steps": 181800, "loss": 0.0013, "lr": 1.6904834816687383e-05, "epoch": 12.88943894389439, "percentage": 64.45, "elapsed_time": "4:37:02", "remaining_time": "2:32:49", "throughput": 1487.55, "total_tokens": 24726240} {"current_steps": 117170, "total_steps": 181800, "loss": 0.1717, "lr": 1.690256409401873e-05, "epoch": 12.88998899889989, "percentage": 64.45, "elapsed_time": "4:37:02", "remaining_time": "2:32:49", "throughput": 1487.55, "total_tokens": 24727296} {"current_steps": 117175, "total_steps": 181800, "loss": 0.1153, "lr": 1.690029344598026e-05, "epoch": 12.89053905390539, "percentage": 64.45, "elapsed_time": "4:37:03", "remaining_time": "2:32:48", "throughput": 1487.55, "total_tokens": 24728352} {"current_steps": 117180, "total_steps": 181800, "loss": 0.0453, "lr": 1.689802287259289e-05, "epoch": 12.891089108910892, "percentage": 64.46, "elapsed_time": "4:37:04", "remaining_time": "2:32:47", "throughput": 1487.56, "total_tokens": 24729440} {"current_steps": 117185, "total_steps": 181800, "loss": 0.0023, "lr": 1.6895752373877562e-05, "epoch": 12.891639163916391, "percentage": 64.46, "elapsed_time": "4:37:04", "remaining_time": "2:32:46", "throughput": 1487.56, "total_tokens": 24730496} {"current_steps": 117190, "total_steps": 181800, "loss": 0.006, "lr": 1.68934819498552e-05, "epoch": 12.892189218921892, "percentage": 64.46, "elapsed_time": "4:37:05", "remaining_time": "2:32:46", "throughput": 1487.56, "total_tokens": 24731584} {"current_steps": 117195, "total_steps": 181800, "loss": 0.0031, "lr": 1.6891211600546714e-05, "epoch": 12.892739273927393, "percentage": 64.46, "elapsed_time": "4:37:06", "remaining_time": "2:32:45", "throughput": 1487.57, "total_tokens": 24732704} {"current_steps": 117200, "total_steps": 181800, "loss": 0.0338, "lr": 1.6888941325973046e-05, "epoch": 12.893289328932893, "percentage": 64.47, "elapsed_time": "4:37:06", "remaining_time": "2:32:44", "throughput": 1487.58, "total_tokens": 24733888} {"current_steps": 117205, "total_steps": 181800, "loss": 0.0125, "lr": 1.6886671126155108e-05, "epoch": 12.893839383938394, "percentage": 64.47, "elapsed_time": "4:37:07", "remaining_time": "2:32:43", "throughput": 1487.58, "total_tokens": 24734944} {"current_steps": 117210, "total_steps": 181800, "loss": 0.0073, "lr": 1.6884401001113838e-05, "epoch": 12.894389438943895, "percentage": 64.47, "elapsed_time": "4:37:08", "remaining_time": "2:32:43", "throughput": 1487.58, "total_tokens": 24736000} {"current_steps": 117215, "total_steps": 181800, "loss": 0.0068, "lr": 1.6882130950870148e-05, "epoch": 12.894939493949394, "percentage": 64.47, "elapsed_time": "4:37:09", "remaining_time": "2:32:42", "throughput": 1487.58, "total_tokens": 24737056} {"current_steps": 117220, "total_steps": 181800, "loss": 0.0135, "lr": 1.6879860975444956e-05, "epoch": 12.895489548954895, "percentage": 64.48, "elapsed_time": "4:37:09", "remaining_time": "2:32:41", "throughput": 1487.58, "total_tokens": 24738112} {"current_steps": 117225, "total_steps": 181800, "loss": 0.0127, "lr": 1.687759107485919e-05, "epoch": 12.896039603960396, "percentage": 64.48, "elapsed_time": "4:37:10", "remaining_time": "2:32:41", "throughput": 1487.57, "total_tokens": 24739168} {"current_steps": 117230, "total_steps": 181800, "loss": 0.0205, "lr": 1.6875321249133767e-05, "epoch": 12.896589658965897, "percentage": 64.48, "elapsed_time": "4:37:11", "remaining_time": "2:32:40", "throughput": 1487.57, "total_tokens": 24740224} {"current_steps": 117235, "total_steps": 181800, "loss": 0.0066, "lr": 1.687305149828962e-05, "epoch": 12.897139713971397, "percentage": 64.49, "elapsed_time": "4:37:11", "remaining_time": "2:32:39", "throughput": 1487.57, "total_tokens": 24741216} {"current_steps": 117240, "total_steps": 181800, "loss": 0.0019, "lr": 1.6870781822347652e-05, "epoch": 12.897689768976898, "percentage": 64.49, "elapsed_time": "4:37:12", "remaining_time": "2:32:39", "throughput": 1487.57, "total_tokens": 24742304} {"current_steps": 117245, "total_steps": 181800, "loss": 0.0622, "lr": 1.686851222132878e-05, "epoch": 12.898239823982399, "percentage": 64.49, "elapsed_time": "4:37:13", "remaining_time": "2:32:38", "throughput": 1487.58, "total_tokens": 24743456} {"current_steps": 117250, "total_steps": 181800, "loss": 0.0016, "lr": 1.6866242695253943e-05, "epoch": 12.898789878987898, "percentage": 64.49, "elapsed_time": "4:37:14", "remaining_time": "2:32:37", "throughput": 1487.58, "total_tokens": 24744448} {"current_steps": 117255, "total_steps": 181800, "loss": 0.0541, "lr": 1.6863973244144033e-05, "epoch": 12.8993399339934, "percentage": 64.5, "elapsed_time": "4:37:14", "remaining_time": "2:32:36", "throughput": 1487.57, "total_tokens": 24745408} {"current_steps": 117260, "total_steps": 181800, "loss": 0.0168, "lr": 1.686170386801998e-05, "epoch": 12.8998899889989, "percentage": 64.5, "elapsed_time": "4:37:15", "remaining_time": "2:32:36", "throughput": 1487.57, "total_tokens": 24746464} {"current_steps": 117265, "total_steps": 181800, "loss": 0.0222, "lr": 1.6859434566902702e-05, "epoch": 12.9004400440044, "percentage": 64.5, "elapsed_time": "4:37:16", "remaining_time": "2:32:35", "throughput": 1487.58, "total_tokens": 24747552} {"current_steps": 117270, "total_steps": 181800, "loss": 0.0039, "lr": 1.68571653408131e-05, "epoch": 12.900990099009901, "percentage": 64.5, "elapsed_time": "4:37:16", "remaining_time": "2:32:34", "throughput": 1487.58, "total_tokens": 24748608} {"current_steps": 117275, "total_steps": 181800, "loss": 0.0032, "lr": 1.6854896189772114e-05, "epoch": 12.901540154015402, "percentage": 64.51, "elapsed_time": "4:37:17", "remaining_time": "2:32:33", "throughput": 1487.58, "total_tokens": 24749696} {"current_steps": 117280, "total_steps": 181800, "loss": 0.0992, "lr": 1.6852627113800624e-05, "epoch": 12.902090209020901, "percentage": 64.51, "elapsed_time": "4:37:18", "remaining_time": "2:32:33", "throughput": 1487.59, "total_tokens": 24750784} {"current_steps": 117285, "total_steps": 181800, "loss": 0.0241, "lr": 1.6850358112919567e-05, "epoch": 12.902640264026402, "percentage": 64.51, "elapsed_time": "4:37:18", "remaining_time": "2:32:32", "throughput": 1487.59, "total_tokens": 24751808} {"current_steps": 117290, "total_steps": 181800, "loss": 0.0246, "lr": 1.6848089187149858e-05, "epoch": 12.903190319031903, "percentage": 64.52, "elapsed_time": "4:37:19", "remaining_time": "2:32:31", "throughput": 1487.59, "total_tokens": 24752864} {"current_steps": 117295, "total_steps": 181800, "loss": 0.0646, "lr": 1.6845820336512385e-05, "epoch": 12.903740374037405, "percentage": 64.52, "elapsed_time": "4:37:20", "remaining_time": "2:32:31", "throughput": 1487.59, "total_tokens": 24753888} {"current_steps": 117300, "total_steps": 181800, "loss": 0.0011, "lr": 1.684355156102808e-05, "epoch": 12.904290429042904, "percentage": 64.52, "elapsed_time": "4:37:20", "remaining_time": "2:32:30", "throughput": 1487.59, "total_tokens": 24754944} {"current_steps": 117305, "total_steps": 181800, "loss": 0.0016, "lr": 1.684128286071784e-05, "epoch": 12.904840484048405, "percentage": 64.52, "elapsed_time": "4:37:21", "remaining_time": "2:32:29", "throughput": 1487.59, "total_tokens": 24756000} {"current_steps": 117310, "total_steps": 181800, "loss": 0.0814, "lr": 1.683901423560259e-05, "epoch": 12.905390539053906, "percentage": 64.53, "elapsed_time": "4:37:22", "remaining_time": "2:32:28", "throughput": 1487.59, "total_tokens": 24757056} {"current_steps": 117315, "total_steps": 181800, "loss": 0.0029, "lr": 1.6836745685703224e-05, "epoch": 12.905940594059405, "percentage": 64.53, "elapsed_time": "4:37:23", "remaining_time": "2:32:28", "throughput": 1487.6, "total_tokens": 24758144} {"current_steps": 117320, "total_steps": 181800, "loss": 0.011, "lr": 1.6834477211040654e-05, "epoch": 12.906490649064907, "percentage": 64.53, "elapsed_time": "4:37:23", "remaining_time": "2:32:27", "throughput": 1487.6, "total_tokens": 24759232} {"current_steps": 117325, "total_steps": 181800, "loss": 0.0027, "lr": 1.6832208811635796e-05, "epoch": 12.907040704070408, "percentage": 64.54, "elapsed_time": "4:37:24", "remaining_time": "2:32:26", "throughput": 1487.6, "total_tokens": 24760288} {"current_steps": 117330, "total_steps": 181800, "loss": 0.0028, "lr": 1.6829940487509544e-05, "epoch": 12.907590759075907, "percentage": 64.54, "elapsed_time": "4:37:25", "remaining_time": "2:32:26", "throughput": 1487.6, "total_tokens": 24761280} {"current_steps": 117335, "total_steps": 181800, "loss": 0.2039, "lr": 1.6827672238682817e-05, "epoch": 12.908140814081408, "percentage": 64.54, "elapsed_time": "4:37:25", "remaining_time": "2:32:25", "throughput": 1487.6, "total_tokens": 24762336} {"current_steps": 117340, "total_steps": 181800, "loss": 0.0237, "lr": 1.6825404065176513e-05, "epoch": 12.908690869086909, "percentage": 64.54, "elapsed_time": "4:37:26", "remaining_time": "2:32:24", "throughput": 1487.6, "total_tokens": 24763360} {"current_steps": 117345, "total_steps": 181800, "loss": 0.0048, "lr": 1.6823135967011526e-05, "epoch": 12.909240924092408, "percentage": 64.55, "elapsed_time": "4:37:27", "remaining_time": "2:32:23", "throughput": 1487.6, "total_tokens": 24764384} {"current_steps": 117350, "total_steps": 181800, "loss": 0.0061, "lr": 1.6820867944208792e-05, "epoch": 12.90979097909791, "percentage": 64.55, "elapsed_time": "4:37:27", "remaining_time": "2:32:23", "throughput": 1487.61, "total_tokens": 24765440} {"current_steps": 117355, "total_steps": 181800, "loss": 0.0182, "lr": 1.681859999678917e-05, "epoch": 12.91034103410341, "percentage": 64.55, "elapsed_time": "4:37:28", "remaining_time": "2:32:22", "throughput": 1487.61, "total_tokens": 24766592} {"current_steps": 117360, "total_steps": 181800, "loss": 0.0033, "lr": 1.68163321247736e-05, "epoch": 12.910891089108912, "percentage": 64.55, "elapsed_time": "4:37:29", "remaining_time": "2:32:21", "throughput": 1487.61, "total_tokens": 24767616} {"current_steps": 117365, "total_steps": 181800, "loss": 0.2461, "lr": 1.681406432818297e-05, "epoch": 12.911441144114411, "percentage": 64.56, "elapsed_time": "4:37:29", "remaining_time": "2:32:21", "throughput": 1487.62, "total_tokens": 24768704} {"current_steps": 117370, "total_steps": 181800, "loss": 0.0015, "lr": 1.6811796607038176e-05, "epoch": 12.911991199119912, "percentage": 64.56, "elapsed_time": "4:37:30", "remaining_time": "2:32:20", "throughput": 1487.62, "total_tokens": 24769792} {"current_steps": 117375, "total_steps": 181800, "loss": 0.0064, "lr": 1.6809528961360127e-05, "epoch": 12.912541254125413, "percentage": 64.56, "elapsed_time": "4:37:31", "remaining_time": "2:32:19", "throughput": 1487.62, "total_tokens": 24770816} {"current_steps": 117380, "total_steps": 181800, "loss": 0.0054, "lr": 1.680726139116972e-05, "epoch": 12.913091309130913, "percentage": 64.57, "elapsed_time": "4:37:32", "remaining_time": "2:32:18", "throughput": 1487.62, "total_tokens": 24771904} {"current_steps": 117385, "total_steps": 181800, "loss": 0.0341, "lr": 1.680499389648784e-05, "epoch": 12.913641364136414, "percentage": 64.57, "elapsed_time": "4:37:32", "remaining_time": "2:32:18", "throughput": 1487.63, "total_tokens": 24772992} {"current_steps": 117390, "total_steps": 181800, "loss": 0.0681, "lr": 1.6802726477335418e-05, "epoch": 12.914191419141915, "percentage": 64.57, "elapsed_time": "4:37:33", "remaining_time": "2:32:17", "throughput": 1487.63, "total_tokens": 24774080} {"current_steps": 117395, "total_steps": 181800, "loss": 0.0065, "lr": 1.680045913373332e-05, "epoch": 12.914741474147414, "percentage": 64.57, "elapsed_time": "4:37:34", "remaining_time": "2:32:16", "throughput": 1487.64, "total_tokens": 24775168} {"current_steps": 117400, "total_steps": 181800, "loss": 0.0016, "lr": 1.679819186570246e-05, "epoch": 12.915291529152915, "percentage": 64.58, "elapsed_time": "4:37:34", "remaining_time": "2:32:15", "throughput": 1487.63, "total_tokens": 24776160} {"current_steps": 117405, "total_steps": 181800, "loss": 0.0039, "lr": 1.6795924673263737e-05, "epoch": 12.915841584158416, "percentage": 64.58, "elapsed_time": "4:37:35", "remaining_time": "2:32:15", "throughput": 1487.64, "total_tokens": 24777216} {"current_steps": 117410, "total_steps": 181800, "loss": 0.0613, "lr": 1.679365755643803e-05, "epoch": 12.916391639163916, "percentage": 64.58, "elapsed_time": "4:37:36", "remaining_time": "2:32:14", "throughput": 1487.64, "total_tokens": 24778304} {"current_steps": 117415, "total_steps": 181800, "loss": 0.0008, "lr": 1.6791390515246248e-05, "epoch": 12.916941694169417, "percentage": 64.58, "elapsed_time": "4:37:36", "remaining_time": "2:32:13", "throughput": 1487.64, "total_tokens": 24779264} {"current_steps": 117420, "total_steps": 181800, "loss": 0.0402, "lr": 1.6789123549709273e-05, "epoch": 12.917491749174918, "percentage": 64.59, "elapsed_time": "4:37:37", "remaining_time": "2:32:13", "throughput": 1487.63, "total_tokens": 24780256} {"current_steps": 117425, "total_steps": 181800, "loss": 0.0707, "lr": 1.678685665984802e-05, "epoch": 12.918041804180419, "percentage": 64.59, "elapsed_time": "4:37:38", "remaining_time": "2:32:12", "throughput": 1487.64, "total_tokens": 24781344} {"current_steps": 117430, "total_steps": 181800, "loss": 0.1152, "lr": 1.678458984568336e-05, "epoch": 12.918591859185918, "percentage": 64.59, "elapsed_time": "4:37:38", "remaining_time": "2:32:11", "throughput": 1487.64, "total_tokens": 24782464} {"current_steps": 117435, "total_steps": 181800, "loss": 0.0006, "lr": 1.678232310723619e-05, "epoch": 12.91914191419142, "percentage": 64.6, "elapsed_time": "4:37:39", "remaining_time": "2:32:10", "throughput": 1487.64, "total_tokens": 24783488} {"current_steps": 117440, "total_steps": 181800, "loss": 0.0162, "lr": 1.6780056444527416e-05, "epoch": 12.91969196919692, "percentage": 64.6, "elapsed_time": "4:37:40", "remaining_time": "2:32:10", "throughput": 1487.64, "total_tokens": 24784512} {"current_steps": 117445, "total_steps": 181800, "loss": 0.0203, "lr": 1.6777789857577898e-05, "epoch": 12.92024202420242, "percentage": 64.6, "elapsed_time": "4:37:40", "remaining_time": "2:32:09", "throughput": 1487.65, "total_tokens": 24785600} {"current_steps": 117450, "total_steps": 181800, "loss": 0.0073, "lr": 1.6775523346408566e-05, "epoch": 12.92079207920792, "percentage": 64.6, "elapsed_time": "4:37:41", "remaining_time": "2:32:08", "throughput": 1487.65, "total_tokens": 24786624} {"current_steps": 117455, "total_steps": 181800, "loss": 0.0037, "lr": 1.677325691104028e-05, "epoch": 12.921342134213422, "percentage": 64.61, "elapsed_time": "4:37:42", "remaining_time": "2:32:08", "throughput": 1487.65, "total_tokens": 24787680} {"current_steps": 117460, "total_steps": 181800, "loss": 0.0084, "lr": 1.677099055149393e-05, "epoch": 12.921892189218921, "percentage": 64.61, "elapsed_time": "4:37:43", "remaining_time": "2:32:07", "throughput": 1487.65, "total_tokens": 24788736} {"current_steps": 117465, "total_steps": 181800, "loss": 0.0436, "lr": 1.6768724267790425e-05, "epoch": 12.922442244224422, "percentage": 64.61, "elapsed_time": "4:37:43", "remaining_time": "2:32:06", "throughput": 1487.65, "total_tokens": 24789696} {"current_steps": 117470, "total_steps": 181800, "loss": 0.0506, "lr": 1.676645805995063e-05, "epoch": 12.922992299229923, "percentage": 64.61, "elapsed_time": "4:37:44", "remaining_time": "2:32:05", "throughput": 1487.65, "total_tokens": 24790720} {"current_steps": 117475, "total_steps": 181800, "loss": 0.0153, "lr": 1.6764191927995443e-05, "epoch": 12.923542354235423, "percentage": 64.62, "elapsed_time": "4:37:45", "remaining_time": "2:32:05", "throughput": 1487.65, "total_tokens": 24791744} {"current_steps": 117480, "total_steps": 181800, "loss": 0.0361, "lr": 1.6761925871945756e-05, "epoch": 12.924092409240924, "percentage": 64.62, "elapsed_time": "4:37:45", "remaining_time": "2:32:04", "throughput": 1487.65, "total_tokens": 24792832} {"current_steps": 117485, "total_steps": 181800, "loss": 0.0222, "lr": 1.675965989182243e-05, "epoch": 12.924642464246425, "percentage": 64.62, "elapsed_time": "4:37:46", "remaining_time": "2:32:03", "throughput": 1487.65, "total_tokens": 24793856} {"current_steps": 117490, "total_steps": 181800, "loss": 0.087, "lr": 1.6757393987646374e-05, "epoch": 12.925192519251926, "percentage": 64.63, "elapsed_time": "4:37:47", "remaining_time": "2:32:03", "throughput": 1487.65, "total_tokens": 24794944} {"current_steps": 117495, "total_steps": 181800, "loss": 0.1392, "lr": 1.6755128159438453e-05, "epoch": 12.925742574257425, "percentage": 64.63, "elapsed_time": "4:37:47", "remaining_time": "2:32:02", "throughput": 1487.66, "total_tokens": 24796032} {"current_steps": 117500, "total_steps": 181800, "loss": 0.0044, "lr": 1.6752862407219573e-05, "epoch": 12.926292629262926, "percentage": 64.63, "elapsed_time": "4:37:48", "remaining_time": "2:32:01", "throughput": 1487.66, "total_tokens": 24797056} {"current_steps": 117505, "total_steps": 181800, "loss": 0.0049, "lr": 1.6750596731010593e-05, "epoch": 12.926842684268427, "percentage": 64.63, "elapsed_time": "4:37:49", "remaining_time": "2:32:00", "throughput": 1487.66, "total_tokens": 24798112} {"current_steps": 117510, "total_steps": 181800, "loss": 0.0012, "lr": 1.6748331130832402e-05, "epoch": 12.927392739273927, "percentage": 64.64, "elapsed_time": "4:37:49", "remaining_time": "2:32:00", "throughput": 1487.66, "total_tokens": 24799136} {"current_steps": 117515, "total_steps": 181800, "loss": 0.0242, "lr": 1.674606560670589e-05, "epoch": 12.927942794279428, "percentage": 64.64, "elapsed_time": "4:37:50", "remaining_time": "2:31:59", "throughput": 1487.66, "total_tokens": 24800128} {"current_steps": 117520, "total_steps": 181800, "loss": 0.1871, "lr": 1.6743800158651924e-05, "epoch": 12.928492849284929, "percentage": 64.64, "elapsed_time": "4:37:51", "remaining_time": "2:31:58", "throughput": 1487.66, "total_tokens": 24801248} {"current_steps": 117525, "total_steps": 181800, "loss": 0.0018, "lr": 1.6741534786691403e-05, "epoch": 12.929042904290428, "percentage": 64.65, "elapsed_time": "4:37:51", "remaining_time": "2:31:57", "throughput": 1487.66, "total_tokens": 24802336} {"current_steps": 117530, "total_steps": 181800, "loss": 0.0699, "lr": 1.6739269490845187e-05, "epoch": 12.92959295929593, "percentage": 64.65, "elapsed_time": "4:37:52", "remaining_time": "2:31:57", "throughput": 1487.67, "total_tokens": 24803424} {"current_steps": 117535, "total_steps": 181800, "loss": 0.0623, "lr": 1.6737004271134156e-05, "epoch": 12.93014301430143, "percentage": 64.65, "elapsed_time": "4:37:53", "remaining_time": "2:31:56", "throughput": 1487.67, "total_tokens": 24804544} {"current_steps": 117540, "total_steps": 181800, "loss": 0.0027, "lr": 1.67347391275792e-05, "epoch": 12.930693069306932, "percentage": 64.65, "elapsed_time": "4:37:54", "remaining_time": "2:31:55", "throughput": 1487.68, "total_tokens": 24805600} {"current_steps": 117545, "total_steps": 181800, "loss": 0.0011, "lr": 1.6732474060201174e-05, "epoch": 12.93124312431243, "percentage": 64.66, "elapsed_time": "4:37:54", "remaining_time": "2:31:55", "throughput": 1487.68, "total_tokens": 24806656} {"current_steps": 117550, "total_steps": 181800, "loss": 0.0071, "lr": 1.673020906902098e-05, "epoch": 12.931793179317932, "percentage": 64.66, "elapsed_time": "4:37:55", "remaining_time": "2:31:54", "throughput": 1487.68, "total_tokens": 24807680} {"current_steps": 117555, "total_steps": 181800, "loss": 0.0525, "lr": 1.6727944154059484e-05, "epoch": 12.932343234323433, "percentage": 64.66, "elapsed_time": "4:37:56", "remaining_time": "2:31:53", "throughput": 1487.68, "total_tokens": 24808768} {"current_steps": 117560, "total_steps": 181800, "loss": 0.1739, "lr": 1.6725679315337536e-05, "epoch": 12.932893289328932, "percentage": 64.66, "elapsed_time": "4:37:56", "remaining_time": "2:31:52", "throughput": 1487.68, "total_tokens": 24809824} {"current_steps": 117565, "total_steps": 181800, "loss": 0.0808, "lr": 1.672341455287605e-05, "epoch": 12.933443344334433, "percentage": 64.67, "elapsed_time": "4:37:57", "remaining_time": "2:31:52", "throughput": 1487.68, "total_tokens": 24810848} {"current_steps": 117570, "total_steps": 181800, "loss": 0.0919, "lr": 1.6721149866695878e-05, "epoch": 12.933993399339935, "percentage": 64.67, "elapsed_time": "4:37:58", "remaining_time": "2:31:51", "throughput": 1487.68, "total_tokens": 24811936} {"current_steps": 117575, "total_steps": 181800, "loss": 0.0009, "lr": 1.6718885256817888e-05, "epoch": 12.934543454345434, "percentage": 64.67, "elapsed_time": "4:37:58", "remaining_time": "2:31:50", "throughput": 1487.68, "total_tokens": 24812928} {"current_steps": 117580, "total_steps": 181800, "loss": 0.0036, "lr": 1.671662072326297e-05, "epoch": 12.935093509350935, "percentage": 64.68, "elapsed_time": "4:37:59", "remaining_time": "2:31:50", "throughput": 1487.69, "total_tokens": 24814048} {"current_steps": 117585, "total_steps": 181800, "loss": 0.1577, "lr": 1.671435626605197e-05, "epoch": 12.935643564356436, "percentage": 64.68, "elapsed_time": "4:38:00", "remaining_time": "2:31:49", "throughput": 1487.69, "total_tokens": 24815104} {"current_steps": 117590, "total_steps": 181800, "loss": 0.0135, "lr": 1.6712091885205782e-05, "epoch": 12.936193619361937, "percentage": 64.68, "elapsed_time": "4:38:00", "remaining_time": "2:31:48", "throughput": 1487.69, "total_tokens": 24816192} {"current_steps": 117595, "total_steps": 181800, "loss": 0.0044, "lr": 1.670982758074527e-05, "epoch": 12.936743674367436, "percentage": 64.68, "elapsed_time": "4:38:01", "remaining_time": "2:31:47", "throughput": 1487.69, "total_tokens": 24817248} {"current_steps": 117600, "total_steps": 181800, "loss": 0.0028, "lr": 1.670756335269129e-05, "epoch": 12.937293729372938, "percentage": 64.69, "elapsed_time": "4:38:02", "remaining_time": "2:31:47", "throughput": 1487.7, "total_tokens": 24818304} {"current_steps": 117605, "total_steps": 181800, "loss": 0.0049, "lr": 1.6705299201064722e-05, "epoch": 12.937843784378439, "percentage": 64.69, "elapsed_time": "4:38:03", "remaining_time": "2:31:46", "throughput": 1487.7, "total_tokens": 24819392} {"current_steps": 117610, "total_steps": 181800, "loss": 0.015, "lr": 1.6703035125886428e-05, "epoch": 12.938393839383938, "percentage": 64.69, "elapsed_time": "4:38:03", "remaining_time": "2:31:45", "throughput": 1487.7, "total_tokens": 24820416} {"current_steps": 117615, "total_steps": 181800, "loss": 0.1029, "lr": 1.670077112717729e-05, "epoch": 12.938943894389439, "percentage": 64.69, "elapsed_time": "4:38:04", "remaining_time": "2:31:45", "throughput": 1487.7, "total_tokens": 24821472} {"current_steps": 117620, "total_steps": 181800, "loss": 0.0034, "lr": 1.6698507204958153e-05, "epoch": 12.93949394939494, "percentage": 64.7, "elapsed_time": "4:38:05", "remaining_time": "2:31:44", "throughput": 1487.7, "total_tokens": 24822528} {"current_steps": 117625, "total_steps": 181800, "loss": 0.124, "lr": 1.6696243359249887e-05, "epoch": 12.94004400440044, "percentage": 64.7, "elapsed_time": "4:38:05", "remaining_time": "2:31:43", "throughput": 1487.71, "total_tokens": 24823584} {"current_steps": 117630, "total_steps": 181800, "loss": 0.0025, "lr": 1.669397959007337e-05, "epoch": 12.94059405940594, "percentage": 64.7, "elapsed_time": "4:38:06", "remaining_time": "2:31:42", "throughput": 1487.71, "total_tokens": 24824672} {"current_steps": 117635, "total_steps": 181800, "loss": 0.0015, "lr": 1.6691715897449452e-05, "epoch": 12.941144114411442, "percentage": 64.71, "elapsed_time": "4:38:07", "remaining_time": "2:31:42", "throughput": 1487.71, "total_tokens": 24825728} {"current_steps": 117640, "total_steps": 181800, "loss": 0.0083, "lr": 1.668945228139901e-05, "epoch": 12.941694169416941, "percentage": 64.71, "elapsed_time": "4:38:07", "remaining_time": "2:31:41", "throughput": 1487.71, "total_tokens": 24826752} {"current_steps": 117645, "total_steps": 181800, "loss": 0.0021, "lr": 1.668718874194289e-05, "epoch": 12.942244224422442, "percentage": 64.71, "elapsed_time": "4:38:08", "remaining_time": "2:31:40", "throughput": 1487.71, "total_tokens": 24827808} {"current_steps": 117650, "total_steps": 181800, "loss": 0.0105, "lr": 1.6684925279101962e-05, "epoch": 12.942794279427943, "percentage": 64.71, "elapsed_time": "4:38:09", "remaining_time": "2:31:40", "throughput": 1487.72, "total_tokens": 24828928} {"current_steps": 117655, "total_steps": 181800, "loss": 0.0845, "lr": 1.6682661892897097e-05, "epoch": 12.943344334433444, "percentage": 64.72, "elapsed_time": "4:38:09", "remaining_time": "2:31:39", "throughput": 1487.72, "total_tokens": 24829920} {"current_steps": 117660, "total_steps": 181800, "loss": 0.0031, "lr": 1.668039858334914e-05, "epoch": 12.943894389438944, "percentage": 64.72, "elapsed_time": "4:38:10", "remaining_time": "2:31:38", "throughput": 1487.71, "total_tokens": 24830912} {"current_steps": 117665, "total_steps": 181800, "loss": 0.0073, "lr": 1.667813535047896e-05, "epoch": 12.944444444444445, "percentage": 64.72, "elapsed_time": "4:38:11", "remaining_time": "2:31:37", "throughput": 1487.72, "total_tokens": 24832064} {"current_steps": 117670, "total_steps": 181800, "loss": 0.145, "lr": 1.6675872194307414e-05, "epoch": 12.944994499449946, "percentage": 64.72, "elapsed_time": "4:38:12", "remaining_time": "2:31:37", "throughput": 1487.72, "total_tokens": 24833120} {"current_steps": 117675, "total_steps": 181800, "loss": 0.003, "lr": 1.6673609114855347e-05, "epoch": 12.945544554455445, "percentage": 64.73, "elapsed_time": "4:38:12", "remaining_time": "2:31:36", "throughput": 1487.73, "total_tokens": 24834208} {"current_steps": 117680, "total_steps": 181800, "loss": 0.0692, "lr": 1.6671346112143642e-05, "epoch": 12.946094609460946, "percentage": 64.73, "elapsed_time": "4:38:13", "remaining_time": "2:31:35", "throughput": 1487.73, "total_tokens": 24835232} {"current_steps": 117685, "total_steps": 181800, "loss": 0.0071, "lr": 1.6669083186193135e-05, "epoch": 12.946644664466447, "percentage": 64.73, "elapsed_time": "4:38:14", "remaining_time": "2:31:34", "throughput": 1487.73, "total_tokens": 24836288} {"current_steps": 117690, "total_steps": 181800, "loss": 0.007, "lr": 1.6666820337024695e-05, "epoch": 12.947194719471947, "percentage": 64.74, "elapsed_time": "4:38:14", "remaining_time": "2:31:34", "throughput": 1487.73, "total_tokens": 24837344} {"current_steps": 117695, "total_steps": 181800, "loss": 0.0104, "lr": 1.6664557564659185e-05, "epoch": 12.947744774477448, "percentage": 64.74, "elapsed_time": "4:38:15", "remaining_time": "2:31:33", "throughput": 1487.74, "total_tokens": 24838464} {"current_steps": 117700, "total_steps": 181800, "loss": 0.0071, "lr": 1.6662294869117436e-05, "epoch": 12.948294829482949, "percentage": 64.74, "elapsed_time": "4:38:16", "remaining_time": "2:31:32", "throughput": 1487.74, "total_tokens": 24839488} {"current_steps": 117705, "total_steps": 181800, "loss": 0.0352, "lr": 1.6660032250420314e-05, "epoch": 12.948844884488448, "percentage": 64.74, "elapsed_time": "4:38:16", "remaining_time": "2:31:32", "throughput": 1487.74, "total_tokens": 24840544} {"current_steps": 117710, "total_steps": 181800, "loss": 0.0956, "lr": 1.6657769708588668e-05, "epoch": 12.94939493949395, "percentage": 64.75, "elapsed_time": "4:38:17", "remaining_time": "2:31:31", "throughput": 1487.74, "total_tokens": 24841568} {"current_steps": 117715, "total_steps": 181800, "loss": 0.0386, "lr": 1.665550724364337e-05, "epoch": 12.94994499449945, "percentage": 64.75, "elapsed_time": "4:38:18", "remaining_time": "2:31:30", "throughput": 1487.74, "total_tokens": 24842624} {"current_steps": 117720, "total_steps": 181800, "loss": 0.0153, "lr": 1.6653244855605248e-05, "epoch": 12.950495049504951, "percentage": 64.75, "elapsed_time": "4:38:18", "remaining_time": "2:31:29", "throughput": 1487.74, "total_tokens": 24843648} {"current_steps": 117725, "total_steps": 181800, "loss": 0.1672, "lr": 1.6650982544495165e-05, "epoch": 12.95104510451045, "percentage": 64.76, "elapsed_time": "4:38:19", "remaining_time": "2:31:29", "throughput": 1487.74, "total_tokens": 24844640} {"current_steps": 117730, "total_steps": 181800, "loss": 0.0039, "lr": 1.6648720310333973e-05, "epoch": 12.951595159515952, "percentage": 64.76, "elapsed_time": "4:38:20", "remaining_time": "2:31:28", "throughput": 1487.74, "total_tokens": 24845696} {"current_steps": 117735, "total_steps": 181800, "loss": 0.0025, "lr": 1.6646458153142512e-05, "epoch": 12.952145214521453, "percentage": 64.76, "elapsed_time": "4:38:21", "remaining_time": "2:31:27", "throughput": 1487.74, "total_tokens": 24846752} {"current_steps": 117740, "total_steps": 181800, "loss": 0.0069, "lr": 1.6644196072941644e-05, "epoch": 12.952695269526952, "percentage": 64.76, "elapsed_time": "4:38:21", "remaining_time": "2:31:27", "throughput": 1487.74, "total_tokens": 24847872} {"current_steps": 117745, "total_steps": 181800, "loss": 0.0907, "lr": 1.664193406975221e-05, "epoch": 12.953245324532453, "percentage": 64.77, "elapsed_time": "4:38:22", "remaining_time": "2:31:26", "throughput": 1487.74, "total_tokens": 24848896} {"current_steps": 117750, "total_steps": 181800, "loss": 0.0216, "lr": 1.663967214359505e-05, "epoch": 12.953795379537954, "percentage": 64.77, "elapsed_time": "4:38:23", "remaining_time": "2:31:25", "throughput": 1487.75, "total_tokens": 24850016} {"current_steps": 117755, "total_steps": 181800, "loss": 0.0019, "lr": 1.6637410294491036e-05, "epoch": 12.954345434543454, "percentage": 64.77, "elapsed_time": "4:38:23", "remaining_time": "2:31:24", "throughput": 1487.75, "total_tokens": 24851008} {"current_steps": 117760, "total_steps": 181800, "loss": 0.0059, "lr": 1.6635148522460985e-05, "epoch": 12.954895489548955, "percentage": 64.77, "elapsed_time": "4:38:24", "remaining_time": "2:31:24", "throughput": 1487.75, "total_tokens": 24852064} {"current_steps": 117765, "total_steps": 181800, "loss": 0.1126, "lr": 1.6632886827525758e-05, "epoch": 12.955445544554456, "percentage": 64.78, "elapsed_time": "4:38:25", "remaining_time": "2:31:23", "throughput": 1487.75, "total_tokens": 24853056} {"current_steps": 117770, "total_steps": 181800, "loss": 0.0048, "lr": 1.6630625209706206e-05, "epoch": 12.955995599559955, "percentage": 64.78, "elapsed_time": "4:38:25", "remaining_time": "2:31:22", "throughput": 1487.75, "total_tokens": 24854112} {"current_steps": 117775, "total_steps": 181800, "loss": 0.0035, "lr": 1.6628363669023163e-05, "epoch": 12.956545654565456, "percentage": 64.78, "elapsed_time": "4:38:26", "remaining_time": "2:31:22", "throughput": 1487.75, "total_tokens": 24855104} {"current_steps": 117780, "total_steps": 181800, "loss": 0.0179, "lr": 1.662610220549747e-05, "epoch": 12.957095709570957, "percentage": 64.79, "elapsed_time": "4:38:27", "remaining_time": "2:31:21", "throughput": 1487.75, "total_tokens": 24856128} {"current_steps": 117785, "total_steps": 181800, "loss": 0.0113, "lr": 1.6623840819149982e-05, "epoch": 12.957645764576458, "percentage": 64.79, "elapsed_time": "4:38:27", "remaining_time": "2:31:20", "throughput": 1487.75, "total_tokens": 24857216} {"current_steps": 117790, "total_steps": 181800, "loss": 0.0094, "lr": 1.662157951000153e-05, "epoch": 12.958195819581958, "percentage": 64.79, "elapsed_time": "4:38:28", "remaining_time": "2:31:19", "throughput": 1487.75, "total_tokens": 24858240} {"current_steps": 117795, "total_steps": 181800, "loss": 0.0502, "lr": 1.6619318278072956e-05, "epoch": 12.958745874587459, "percentage": 64.79, "elapsed_time": "4:38:29", "remaining_time": "2:31:19", "throughput": 1487.75, "total_tokens": 24859232} {"current_steps": 117800, "total_steps": 181800, "loss": 0.003, "lr": 1.6617057123385104e-05, "epoch": 12.95929592959296, "percentage": 64.8, "elapsed_time": "4:38:29", "remaining_time": "2:31:18", "throughput": 1487.75, "total_tokens": 24860352} {"current_steps": 117805, "total_steps": 181800, "loss": 0.0022, "lr": 1.6614796045958816e-05, "epoch": 12.95984598459846, "percentage": 64.8, "elapsed_time": "4:38:30", "remaining_time": "2:31:17", "throughput": 1487.75, "total_tokens": 24861376} {"current_steps": 117810, "total_steps": 181800, "loss": 0.0009, "lr": 1.6612535045814938e-05, "epoch": 12.96039603960396, "percentage": 64.8, "elapsed_time": "4:38:31", "remaining_time": "2:31:16", "throughput": 1487.75, "total_tokens": 24862432} {"current_steps": 117815, "total_steps": 181800, "loss": 0.0112, "lr": 1.6610274122974288e-05, "epoch": 12.960946094609461, "percentage": 64.8, "elapsed_time": "4:38:32", "remaining_time": "2:31:16", "throughput": 1487.75, "total_tokens": 24863456} {"current_steps": 117820, "total_steps": 181800, "loss": 0.072, "lr": 1.6608013277457717e-05, "epoch": 12.96149614961496, "percentage": 64.81, "elapsed_time": "4:38:32", "remaining_time": "2:31:15", "throughput": 1487.76, "total_tokens": 24864576} {"current_steps": 117825, "total_steps": 181800, "loss": 0.0104, "lr": 1.660575250928606e-05, "epoch": 12.962046204620462, "percentage": 64.81, "elapsed_time": "4:38:33", "remaining_time": "2:31:14", "throughput": 1487.76, "total_tokens": 24865632} {"current_steps": 117830, "total_steps": 181800, "loss": 0.0029, "lr": 1.6603491818480164e-05, "epoch": 12.962596259625963, "percentage": 64.81, "elapsed_time": "4:38:34", "remaining_time": "2:31:14", "throughput": 1487.77, "total_tokens": 24866752} {"current_steps": 117835, "total_steps": 181800, "loss": 0.1025, "lr": 1.660123120506085e-05, "epoch": 12.963146314631462, "percentage": 64.82, "elapsed_time": "4:38:34", "remaining_time": "2:31:13", "throughput": 1487.77, "total_tokens": 24867808} {"current_steps": 117840, "total_steps": 181800, "loss": 0.0146, "lr": 1.6598970669048953e-05, "epoch": 12.963696369636963, "percentage": 64.82, "elapsed_time": "4:38:35", "remaining_time": "2:31:12", "throughput": 1487.77, "total_tokens": 24868896} {"current_steps": 117845, "total_steps": 181800, "loss": 0.0022, "lr": 1.659671021046532e-05, "epoch": 12.964246424642464, "percentage": 64.82, "elapsed_time": "4:38:36", "remaining_time": "2:31:11", "throughput": 1487.78, "total_tokens": 24870048} {"current_steps": 117850, "total_steps": 181800, "loss": 0.0024, "lr": 1.6594449829330767e-05, "epoch": 12.964796479647966, "percentage": 64.82, "elapsed_time": "4:38:36", "remaining_time": "2:31:11", "throughput": 1487.78, "total_tokens": 24871072} {"current_steps": 117855, "total_steps": 181800, "loss": 0.0383, "lr": 1.659218952566614e-05, "epoch": 12.965346534653465, "percentage": 64.83, "elapsed_time": "4:38:37", "remaining_time": "2:31:10", "throughput": 1487.79, "total_tokens": 24872160} {"current_steps": 117860, "total_steps": 181800, "loss": 0.0698, "lr": 1.6589929299492278e-05, "epoch": 12.965896589658966, "percentage": 64.83, "elapsed_time": "4:38:38", "remaining_time": "2:31:09", "throughput": 1487.79, "total_tokens": 24873248} {"current_steps": 117865, "total_steps": 181800, "loss": 0.0476, "lr": 1.6587669150829984e-05, "epoch": 12.966446644664467, "percentage": 64.83, "elapsed_time": "4:38:38", "remaining_time": "2:31:09", "throughput": 1487.79, "total_tokens": 24874304} {"current_steps": 117870, "total_steps": 181800, "loss": 0.0115, "lr": 1.6585409079700122e-05, "epoch": 12.966996699669966, "percentage": 64.83, "elapsed_time": "4:38:39", "remaining_time": "2:31:08", "throughput": 1487.79, "total_tokens": 24875328} {"current_steps": 117875, "total_steps": 181800, "loss": 0.004, "lr": 1.6583149086123496e-05, "epoch": 12.967546754675467, "percentage": 64.84, "elapsed_time": "4:38:40", "remaining_time": "2:31:07", "throughput": 1487.79, "total_tokens": 24876384} {"current_steps": 117880, "total_steps": 181800, "loss": 0.0231, "lr": 1.658088917012095e-05, "epoch": 12.968096809680969, "percentage": 64.84, "elapsed_time": "4:38:41", "remaining_time": "2:31:06", "throughput": 1487.8, "total_tokens": 24877472} {"current_steps": 117885, "total_steps": 181800, "loss": 0.0722, "lr": 1.657862933171332e-05, "epoch": 12.968646864686468, "percentage": 64.84, "elapsed_time": "4:38:41", "remaining_time": "2:31:06", "throughput": 1487.8, "total_tokens": 24878464} {"current_steps": 117890, "total_steps": 181800, "loss": 0.0278, "lr": 1.6576369570921404e-05, "epoch": 12.969196919691969, "percentage": 64.85, "elapsed_time": "4:38:42", "remaining_time": "2:31:05", "throughput": 1487.79, "total_tokens": 24879424} {"current_steps": 117895, "total_steps": 181800, "loss": 0.0026, "lr": 1.6574109887766056e-05, "epoch": 12.96974697469747, "percentage": 64.85, "elapsed_time": "4:38:43", "remaining_time": "2:31:04", "throughput": 1487.8, "total_tokens": 24880512} {"current_steps": 117900, "total_steps": 181800, "loss": 0.0105, "lr": 1.657185028226809e-05, "epoch": 12.97029702970297, "percentage": 64.85, "elapsed_time": "4:38:43", "remaining_time": "2:31:04", "throughput": 1487.8, "total_tokens": 24881568} {"current_steps": 117905, "total_steps": 181800, "loss": 0.0137, "lr": 1.6569590754448344e-05, "epoch": 12.97084708470847, "percentage": 64.85, "elapsed_time": "4:38:44", "remaining_time": "2:31:03", "throughput": 1487.8, "total_tokens": 24882560} {"current_steps": 117910, "total_steps": 181800, "loss": 0.0044, "lr": 1.6567331304327633e-05, "epoch": 12.971397139713972, "percentage": 64.86, "elapsed_time": "4:38:45", "remaining_time": "2:31:02", "throughput": 1487.8, "total_tokens": 24883584} {"current_steps": 117915, "total_steps": 181800, "loss": 0.0683, "lr": 1.6565071931926776e-05, "epoch": 12.971947194719473, "percentage": 64.86, "elapsed_time": "4:38:45", "remaining_time": "2:31:01", "throughput": 1487.8, "total_tokens": 24884640} {"current_steps": 117920, "total_steps": 181800, "loss": 0.016, "lr": 1.6562812637266613e-05, "epoch": 12.972497249724972, "percentage": 64.86, "elapsed_time": "4:38:46", "remaining_time": "2:31:01", "throughput": 1487.8, "total_tokens": 24885728} {"current_steps": 117925, "total_steps": 181800, "loss": 0.0106, "lr": 1.656055342036794e-05, "epoch": 12.973047304730473, "percentage": 64.87, "elapsed_time": "4:38:47", "remaining_time": "2:31:00", "throughput": 1487.8, "total_tokens": 24886688} {"current_steps": 117930, "total_steps": 181800, "loss": 0.0557, "lr": 1.655829428125162e-05, "epoch": 12.973597359735974, "percentage": 64.87, "elapsed_time": "4:38:47", "remaining_time": "2:30:59", "throughput": 1487.8, "total_tokens": 24887744} {"current_steps": 117935, "total_steps": 181800, "loss": 0.0852, "lr": 1.655603521993844e-05, "epoch": 12.974147414741473, "percentage": 64.87, "elapsed_time": "4:38:48", "remaining_time": "2:30:58", "throughput": 1487.8, "total_tokens": 24888864} {"current_steps": 117940, "total_steps": 181800, "loss": 0.0373, "lr": 1.6553776236449225e-05, "epoch": 12.974697469746975, "percentage": 64.87, "elapsed_time": "4:38:49", "remaining_time": "2:30:58", "throughput": 1487.81, "total_tokens": 24889920} {"current_steps": 117945, "total_steps": 181800, "loss": 0.0069, "lr": 1.655151733080481e-05, "epoch": 12.975247524752476, "percentage": 64.88, "elapsed_time": "4:38:49", "remaining_time": "2:30:57", "throughput": 1487.81, "total_tokens": 24891040} {"current_steps": 117950, "total_steps": 181800, "loss": 0.008, "lr": 1.6549258503026002e-05, "epoch": 12.975797579757975, "percentage": 64.88, "elapsed_time": "4:38:50", "remaining_time": "2:30:56", "throughput": 1487.81, "total_tokens": 24892064} {"current_steps": 117955, "total_steps": 181800, "loss": 0.035, "lr": 1.6546999753133622e-05, "epoch": 12.976347634763476, "percentage": 64.88, "elapsed_time": "4:38:51", "remaining_time": "2:30:56", "throughput": 1487.82, "total_tokens": 24893152} {"current_steps": 117960, "total_steps": 181800, "loss": 0.0038, "lr": 1.65447410811485e-05, "epoch": 12.976897689768977, "percentage": 64.88, "elapsed_time": "4:38:52", "remaining_time": "2:30:55", "throughput": 1487.82, "total_tokens": 24894240} {"current_steps": 117965, "total_steps": 181800, "loss": 0.006, "lr": 1.6542482487091433e-05, "epoch": 12.977447744774478, "percentage": 64.89, "elapsed_time": "4:38:52", "remaining_time": "2:30:54", "throughput": 1487.83, "total_tokens": 24895360} {"current_steps": 117970, "total_steps": 181800, "loss": 0.0041, "lr": 1.6540223970983247e-05, "epoch": 12.977997799779978, "percentage": 64.89, "elapsed_time": "4:38:53", "remaining_time": "2:30:53", "throughput": 1487.83, "total_tokens": 24896416} {"current_steps": 117975, "total_steps": 181800, "loss": 0.0155, "lr": 1.6537965532844762e-05, "epoch": 12.978547854785479, "percentage": 64.89, "elapsed_time": "4:38:54", "remaining_time": "2:30:53", "throughput": 1487.83, "total_tokens": 24897440} {"current_steps": 117980, "total_steps": 181800, "loss": 0.0048, "lr": 1.6535707172696778e-05, "epoch": 12.97909790979098, "percentage": 64.9, "elapsed_time": "4:38:54", "remaining_time": "2:30:52", "throughput": 1487.83, "total_tokens": 24898496} {"current_steps": 117985, "total_steps": 181800, "loss": 0.0755, "lr": 1.653344889056013e-05, "epoch": 12.979647964796479, "percentage": 64.9, "elapsed_time": "4:38:55", "remaining_time": "2:30:51", "throughput": 1487.83, "total_tokens": 24899520} {"current_steps": 117990, "total_steps": 181800, "loss": 0.0012, "lr": 1.653119068645561e-05, "epoch": 12.98019801980198, "percentage": 64.9, "elapsed_time": "4:38:56", "remaining_time": "2:30:51", "throughput": 1487.83, "total_tokens": 24900576} {"current_steps": 117995, "total_steps": 181800, "loss": 0.0111, "lr": 1.6528932560404046e-05, "epoch": 12.980748074807481, "percentage": 64.9, "elapsed_time": "4:38:56", "remaining_time": "2:30:50", "throughput": 1487.83, "total_tokens": 24901632} {"current_steps": 118000, "total_steps": 181800, "loss": 0.0588, "lr": 1.6526674512426257e-05, "epoch": 12.98129812981298, "percentage": 64.91, "elapsed_time": "4:38:57", "remaining_time": "2:30:49", "throughput": 1487.84, "total_tokens": 24902784} {"current_steps": 118005, "total_steps": 181800, "loss": 0.1058, "lr": 1.6524416542543032e-05, "epoch": 12.981848184818482, "percentage": 64.91, "elapsed_time": "4:38:58", "remaining_time": "2:30:48", "throughput": 1487.84, "total_tokens": 24903872} {"current_steps": 118010, "total_steps": 181800, "loss": 0.0016, "lr": 1.6522158650775194e-05, "epoch": 12.982398239823983, "percentage": 64.91, "elapsed_time": "4:38:58", "remaining_time": "2:30:48", "throughput": 1487.85, "total_tokens": 24905024} {"current_steps": 118015, "total_steps": 181800, "loss": 0.0732, "lr": 1.6519900837143547e-05, "epoch": 12.982948294829484, "percentage": 64.91, "elapsed_time": "4:38:59", "remaining_time": "2:30:47", "throughput": 1487.85, "total_tokens": 24906048} {"current_steps": 118020, "total_steps": 181800, "loss": 0.0728, "lr": 1.6517643101668918e-05, "epoch": 12.983498349834983, "percentage": 64.92, "elapsed_time": "4:39:00", "remaining_time": "2:30:46", "throughput": 1487.85, "total_tokens": 24907040} {"current_steps": 118025, "total_steps": 181800, "loss": 0.0051, "lr": 1.6515385444372095e-05, "epoch": 12.984048404840484, "percentage": 64.92, "elapsed_time": "4:39:01", "remaining_time": "2:30:46", "throughput": 1487.85, "total_tokens": 24908128} {"current_steps": 118030, "total_steps": 181800, "loss": 0.0027, "lr": 1.6513127865273887e-05, "epoch": 12.984598459845985, "percentage": 64.92, "elapsed_time": "4:39:01", "remaining_time": "2:30:45", "throughput": 1487.86, "total_tokens": 24909216} {"current_steps": 118035, "total_steps": 181800, "loss": 0.0114, "lr": 1.651087036439512e-05, "epoch": 12.985148514851485, "percentage": 64.93, "elapsed_time": "4:39:02", "remaining_time": "2:30:44", "throughput": 1487.86, "total_tokens": 24910304} {"current_steps": 118040, "total_steps": 181800, "loss": 0.0627, "lr": 1.6508612941756573e-05, "epoch": 12.985698569856986, "percentage": 64.93, "elapsed_time": "4:39:03", "remaining_time": "2:30:43", "throughput": 1487.86, "total_tokens": 24911328} {"current_steps": 118045, "total_steps": 181800, "loss": 0.0019, "lr": 1.6506355597379075e-05, "epoch": 12.986248624862487, "percentage": 64.93, "elapsed_time": "4:39:03", "remaining_time": "2:30:43", "throughput": 1487.87, "total_tokens": 24912480} {"current_steps": 118050, "total_steps": 181800, "loss": 0.0023, "lr": 1.650409833128342e-05, "epoch": 12.986798679867986, "percentage": 64.93, "elapsed_time": "4:39:04", "remaining_time": "2:30:42", "throughput": 1487.87, "total_tokens": 24913600} {"current_steps": 118055, "total_steps": 181800, "loss": 0.0022, "lr": 1.650184114349041e-05, "epoch": 12.987348734873487, "percentage": 64.94, "elapsed_time": "4:39:05", "remaining_time": "2:30:41", "throughput": 1487.87, "total_tokens": 24914656} {"current_steps": 118060, "total_steps": 181800, "loss": 0.0026, "lr": 1.6499584034020865e-05, "epoch": 12.987898789878988, "percentage": 64.94, "elapsed_time": "4:39:05", "remaining_time": "2:30:40", "throughput": 1487.88, "total_tokens": 24915776} {"current_steps": 118065, "total_steps": 181800, "loss": 0.0038, "lr": 1.649732700289556e-05, "epoch": 12.988448844884488, "percentage": 64.94, "elapsed_time": "4:39:06", "remaining_time": "2:30:40", "throughput": 1487.88, "total_tokens": 24916832} {"current_steps": 118070, "total_steps": 181800, "loss": 0.0035, "lr": 1.649507005013532e-05, "epoch": 12.988998899889989, "percentage": 64.94, "elapsed_time": "4:39:07", "remaining_time": "2:30:39", "throughput": 1487.88, "total_tokens": 24917856} {"current_steps": 118075, "total_steps": 181800, "loss": 0.0011, "lr": 1.649281317576094e-05, "epoch": 12.98954895489549, "percentage": 64.95, "elapsed_time": "4:39:07", "remaining_time": "2:30:38", "throughput": 1487.88, "total_tokens": 24918848} {"current_steps": 118080, "total_steps": 181800, "loss": 0.0206, "lr": 1.6490556379793213e-05, "epoch": 12.990099009900991, "percentage": 64.95, "elapsed_time": "4:39:08", "remaining_time": "2:30:38", "throughput": 1487.88, "total_tokens": 24919968} {"current_steps": 118085, "total_steps": 181800, "loss": 0.0122, "lr": 1.6488299662252947e-05, "epoch": 12.99064906490649, "percentage": 64.95, "elapsed_time": "4:39:09", "remaining_time": "2:30:37", "throughput": 1487.88, "total_tokens": 24920992} {"current_steps": 118090, "total_steps": 181800, "loss": 0.0091, "lr": 1.6486043023160936e-05, "epoch": 12.991199119911991, "percentage": 64.96, "elapsed_time": "4:39:09", "remaining_time": "2:30:36", "throughput": 1487.89, "total_tokens": 24922144} {"current_steps": 118095, "total_steps": 181800, "loss": 0.0682, "lr": 1.6483786462537985e-05, "epoch": 12.991749174917492, "percentage": 64.96, "elapsed_time": "4:39:10", "remaining_time": "2:30:35", "throughput": 1487.89, "total_tokens": 24923232} {"current_steps": 118100, "total_steps": 181800, "loss": 0.0123, "lr": 1.6481529980404892e-05, "epoch": 12.992299229922992, "percentage": 64.96, "elapsed_time": "4:39:11", "remaining_time": "2:30:35", "throughput": 1487.89, "total_tokens": 24924256} {"current_steps": 118105, "total_steps": 181800, "loss": 0.0602, "lr": 1.647927357678244e-05, "epoch": 12.992849284928493, "percentage": 64.96, "elapsed_time": "4:39:12", "remaining_time": "2:30:34", "throughput": 1487.9, "total_tokens": 24925312} {"current_steps": 118110, "total_steps": 181800, "loss": 0.0048, "lr": 1.647701725169144e-05, "epoch": 12.993399339933994, "percentage": 64.97, "elapsed_time": "4:39:12", "remaining_time": "2:30:33", "throughput": 1487.89, "total_tokens": 24926272} {"current_steps": 118115, "total_steps": 181800, "loss": 0.0043, "lr": 1.6474761005152674e-05, "epoch": 12.993949394939493, "percentage": 64.97, "elapsed_time": "4:39:13", "remaining_time": "2:30:33", "throughput": 1487.89, "total_tokens": 24927328} {"current_steps": 118120, "total_steps": 181800, "loss": 0.0099, "lr": 1.6472504837186958e-05, "epoch": 12.994499449944994, "percentage": 64.97, "elapsed_time": "4:39:14", "remaining_time": "2:30:32", "throughput": 1487.89, "total_tokens": 24928352} {"current_steps": 118125, "total_steps": 181800, "loss": 0.0064, "lr": 1.647024874781507e-05, "epoch": 12.995049504950495, "percentage": 64.98, "elapsed_time": "4:39:14", "remaining_time": "2:30:31", "throughput": 1487.9, "total_tokens": 24929440} {"current_steps": 118130, "total_steps": 181800, "loss": 0.0632, "lr": 1.6467992737057798e-05, "epoch": 12.995599559955995, "percentage": 64.98, "elapsed_time": "4:39:15", "remaining_time": "2:30:30", "throughput": 1487.9, "total_tokens": 24930560} {"current_steps": 118135, "total_steps": 181800, "loss": 0.005, "lr": 1.6465736804935954e-05, "epoch": 12.996149614961496, "percentage": 64.98, "elapsed_time": "4:39:16", "remaining_time": "2:30:30", "throughput": 1487.9, "total_tokens": 24931584} {"current_steps": 118140, "total_steps": 181800, "loss": 0.1665, "lr": 1.646348095147031e-05, "epoch": 12.996699669966997, "percentage": 64.98, "elapsed_time": "4:39:16", "remaining_time": "2:30:29", "throughput": 1487.9, "total_tokens": 24932544} {"current_steps": 118145, "total_steps": 181800, "loss": 0.1612, "lr": 1.646122517668167e-05, "epoch": 12.997249724972498, "percentage": 64.99, "elapsed_time": "4:39:17", "remaining_time": "2:30:28", "throughput": 1487.9, "total_tokens": 24933632} {"current_steps": 118150, "total_steps": 181800, "loss": 0.0041, "lr": 1.6458969480590826e-05, "epoch": 12.997799779977997, "percentage": 64.99, "elapsed_time": "4:39:18", "remaining_time": "2:30:28", "throughput": 1487.9, "total_tokens": 24934656} {"current_steps": 118155, "total_steps": 181800, "loss": 0.1046, "lr": 1.6456713863218548e-05, "epoch": 12.998349834983498, "percentage": 64.99, "elapsed_time": "4:39:18", "remaining_time": "2:30:27", "throughput": 1487.9, "total_tokens": 24935680} {"current_steps": 118160, "total_steps": 181800, "loss": 0.0011, "lr": 1.6454458324585646e-05, "epoch": 12.998899889989, "percentage": 64.99, "elapsed_time": "4:39:19", "remaining_time": "2:30:26", "throughput": 1487.9, "total_tokens": 24936704} {"current_steps": 118165, "total_steps": 181800, "loss": 0.0735, "lr": 1.6452202864712907e-05, "epoch": 12.999449944994499, "percentage": 65.0, "elapsed_time": "4:39:20", "remaining_time": "2:30:25", "throughput": 1487.91, "total_tokens": 24937792} {"current_steps": 118170, "total_steps": 181800, "loss": 0.002, "lr": 1.6449947483621096e-05, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "4:39:21", "remaining_time": "2:30:25", "throughput": 1487.89, "total_tokens": 24938688} {"current_steps": 118170, "total_steps": 181800, "eval_loss": 0.07189643383026123, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "4:39:58", "remaining_time": "2:30:45", "throughput": 1484.62, "total_tokens": 24938688} {"current_steps": 118175, "total_steps": 181800, "loss": 0.0299, "lr": 1.6447692181331038e-05, "epoch": 13.000550055005501, "percentage": 65.0, "elapsed_time": "4:40:00", "remaining_time": "2:30:45", "throughput": 1484.48, "total_tokens": 24939744} {"current_steps": 118180, "total_steps": 181800, "loss": 0.0982, "lr": 1.644543695786348e-05, "epoch": 13.001100110011, "percentage": 65.01, "elapsed_time": "4:40:01", "remaining_time": "2:30:44", "throughput": 1484.47, "total_tokens": 24940736} {"current_steps": 118185, "total_steps": 181800, "loss": 0.0205, "lr": 1.644318181323923e-05, "epoch": 13.001650165016502, "percentage": 65.01, "elapsed_time": "4:40:01", "remaining_time": "2:30:43", "throughput": 1484.48, "total_tokens": 24941824} {"current_steps": 118190, "total_steps": 181800, "loss": 0.002, "lr": 1.6440926747479073e-05, "epoch": 13.002200220022003, "percentage": 65.01, "elapsed_time": "4:40:02", "remaining_time": "2:30:43", "throughput": 1484.47, "total_tokens": 24942848} {"current_steps": 118195, "total_steps": 181800, "loss": 0.0082, "lr": 1.643867176060378e-05, "epoch": 13.002750275027502, "percentage": 65.01, "elapsed_time": "4:40:03", "remaining_time": "2:30:42", "throughput": 1484.48, "total_tokens": 24943904} {"current_steps": 118200, "total_steps": 181800, "loss": 0.0127, "lr": 1.6436416852634147e-05, "epoch": 13.003300330033003, "percentage": 65.02, "elapsed_time": "4:40:03", "remaining_time": "2:30:41", "throughput": 1484.48, "total_tokens": 24944960} {"current_steps": 118205, "total_steps": 181800, "loss": 0.0041, "lr": 1.643416202359094e-05, "epoch": 13.003850385038504, "percentage": 65.02, "elapsed_time": "4:40:04", "remaining_time": "2:30:40", "throughput": 1484.48, "total_tokens": 24946016} {"current_steps": 118210, "total_steps": 181800, "loss": 0.0302, "lr": 1.6431907273494965e-05, "epoch": 13.004400440044005, "percentage": 65.02, "elapsed_time": "4:40:05", "remaining_time": "2:30:40", "throughput": 1484.48, "total_tokens": 24947072} {"current_steps": 118215, "total_steps": 181800, "loss": 0.0329, "lr": 1.6429652602366984e-05, "epoch": 13.004950495049505, "percentage": 65.02, "elapsed_time": "4:40:06", "remaining_time": "2:30:39", "throughput": 1484.47, "total_tokens": 24948096} {"current_steps": 118220, "total_steps": 181800, "loss": 0.0126, "lr": 1.6427398010227776e-05, "epoch": 13.005500550055006, "percentage": 65.03, "elapsed_time": "4:40:06", "remaining_time": "2:30:38", "throughput": 1484.47, "total_tokens": 24949184} {"current_steps": 118225, "total_steps": 181800, "loss": 0.0109, "lr": 1.6425143497098138e-05, "epoch": 13.006050605060507, "percentage": 65.03, "elapsed_time": "4:40:07", "remaining_time": "2:30:38", "throughput": 1484.47, "total_tokens": 24950176} {"current_steps": 118230, "total_steps": 181800, "loss": 0.0074, "lr": 1.6422889062998826e-05, "epoch": 13.006600660066006, "percentage": 65.03, "elapsed_time": "4:40:08", "remaining_time": "2:30:37", "throughput": 1484.47, "total_tokens": 24951296} {"current_steps": 118235, "total_steps": 181800, "loss": 0.0589, "lr": 1.642063470795064e-05, "epoch": 13.007150715071507, "percentage": 65.04, "elapsed_time": "4:40:08", "remaining_time": "2:30:36", "throughput": 1484.47, "total_tokens": 24952352} {"current_steps": 118240, "total_steps": 181800, "loss": 0.0342, "lr": 1.6418380431974345e-05, "epoch": 13.007700770077008, "percentage": 65.04, "elapsed_time": "4:40:09", "remaining_time": "2:30:36", "throughput": 1484.47, "total_tokens": 24953408} {"current_steps": 118245, "total_steps": 181800, "loss": 0.0304, "lr": 1.6416126235090713e-05, "epoch": 13.008250825082508, "percentage": 65.04, "elapsed_time": "4:40:10", "remaining_time": "2:30:35", "throughput": 1484.47, "total_tokens": 24954432} {"current_steps": 118250, "total_steps": 181800, "loss": 0.1179, "lr": 1.6413872117320537e-05, "epoch": 13.008800880088009, "percentage": 65.04, "elapsed_time": "4:40:11", "remaining_time": "2:30:34", "throughput": 1484.48, "total_tokens": 24955552} {"current_steps": 118255, "total_steps": 181800, "loss": 0.0162, "lr": 1.641161807868457e-05, "epoch": 13.00935093509351, "percentage": 65.05, "elapsed_time": "4:40:11", "remaining_time": "2:30:33", "throughput": 1484.48, "total_tokens": 24956608} {"current_steps": 118260, "total_steps": 181800, "loss": 0.0094, "lr": 1.6409364119203608e-05, "epoch": 13.009900990099009, "percentage": 65.05, "elapsed_time": "4:40:12", "remaining_time": "2:30:33", "throughput": 1484.47, "total_tokens": 24957600} {"current_steps": 118265, "total_steps": 181800, "loss": 0.0179, "lr": 1.6407110238898414e-05, "epoch": 13.01045104510451, "percentage": 65.05, "elapsed_time": "4:40:13", "remaining_time": "2:30:32", "throughput": 1484.47, "total_tokens": 24958624} {"current_steps": 118270, "total_steps": 181800, "loss": 0.0072, "lr": 1.6404856437789757e-05, "epoch": 13.011001100110011, "percentage": 65.06, "elapsed_time": "4:40:13", "remaining_time": "2:30:31", "throughput": 1484.48, "total_tokens": 24959680} {"current_steps": 118275, "total_steps": 181800, "loss": 0.0643, "lr": 1.6402602715898413e-05, "epoch": 13.011551155115512, "percentage": 65.06, "elapsed_time": "4:40:14", "remaining_time": "2:30:30", "throughput": 1484.48, "total_tokens": 24960704} {"current_steps": 118280, "total_steps": 181800, "loss": 0.0056, "lr": 1.640034907324515e-05, "epoch": 13.012101210121012, "percentage": 65.06, "elapsed_time": "4:40:15", "remaining_time": "2:30:30", "throughput": 1484.48, "total_tokens": 24961824} {"current_steps": 118285, "total_steps": 181800, "loss": 0.0007, "lr": 1.639809550985076e-05, "epoch": 13.012651265126513, "percentage": 65.06, "elapsed_time": "4:40:15", "remaining_time": "2:30:29", "throughput": 1484.49, "total_tokens": 24962944} {"current_steps": 118290, "total_steps": 181800, "loss": 0.0636, "lr": 1.6395842025735986e-05, "epoch": 13.013201320132014, "percentage": 65.07, "elapsed_time": "4:40:16", "remaining_time": "2:30:28", "throughput": 1484.49, "total_tokens": 24964000} {"current_steps": 118295, "total_steps": 181800, "loss": 0.0139, "lr": 1.63935886209216e-05, "epoch": 13.013751375137513, "percentage": 65.07, "elapsed_time": "4:40:17", "remaining_time": "2:30:28", "throughput": 1484.49, "total_tokens": 24965056} {"current_steps": 118300, "total_steps": 181800, "loss": 0.0269, "lr": 1.639133529542839e-05, "epoch": 13.014301430143014, "percentage": 65.07, "elapsed_time": "4:40:17", "remaining_time": "2:30:27", "throughput": 1484.49, "total_tokens": 24966144} {"current_steps": 118305, "total_steps": 181800, "loss": 0.0079, "lr": 1.63890820492771e-05, "epoch": 13.014851485148515, "percentage": 65.07, "elapsed_time": "4:40:18", "remaining_time": "2:30:26", "throughput": 1484.49, "total_tokens": 24967168} {"current_steps": 118310, "total_steps": 181800, "loss": 0.0065, "lr": 1.6386828882488524e-05, "epoch": 13.015401540154015, "percentage": 65.08, "elapsed_time": "4:40:19", "remaining_time": "2:30:25", "throughput": 1484.49, "total_tokens": 24968224} {"current_steps": 118315, "total_steps": 181800, "loss": 0.0647, "lr": 1.6384575795083404e-05, "epoch": 13.015951595159516, "percentage": 65.08, "elapsed_time": "4:40:20", "remaining_time": "2:30:25", "throughput": 1484.49, "total_tokens": 24969248} {"current_steps": 118320, "total_steps": 181800, "loss": 0.0006, "lr": 1.638232278708251e-05, "epoch": 13.016501650165017, "percentage": 65.08, "elapsed_time": "4:40:20", "remaining_time": "2:30:24", "throughput": 1484.5, "total_tokens": 24970336} {"current_steps": 118325, "total_steps": 181800, "loss": 0.0217, "lr": 1.6380069858506626e-05, "epoch": 13.017051705170518, "percentage": 65.09, "elapsed_time": "4:40:21", "remaining_time": "2:30:23", "throughput": 1484.5, "total_tokens": 24971392} {"current_steps": 118330, "total_steps": 181800, "loss": 0.0033, "lr": 1.637781700937649e-05, "epoch": 13.017601760176017, "percentage": 65.09, "elapsed_time": "4:40:22", "remaining_time": "2:30:23", "throughput": 1484.5, "total_tokens": 24972512} {"current_steps": 118335, "total_steps": 181800, "loss": 0.0056, "lr": 1.637556423971288e-05, "epoch": 13.018151815181518, "percentage": 65.09, "elapsed_time": "4:40:22", "remaining_time": "2:30:22", "throughput": 1484.51, "total_tokens": 24973600} {"current_steps": 118340, "total_steps": 181800, "loss": 0.0417, "lr": 1.6373311549536563e-05, "epoch": 13.01870187018702, "percentage": 65.09, "elapsed_time": "4:40:23", "remaining_time": "2:30:21", "throughput": 1484.5, "total_tokens": 24974560} {"current_steps": 118345, "total_steps": 181800, "loss": 0.0072, "lr": 1.6371058938868278e-05, "epoch": 13.019251925192519, "percentage": 65.1, "elapsed_time": "4:40:24", "remaining_time": "2:30:20", "throughput": 1484.5, "total_tokens": 24975584} {"current_steps": 118350, "total_steps": 181800, "loss": 0.1085, "lr": 1.6368806407728814e-05, "epoch": 13.01980198019802, "percentage": 65.1, "elapsed_time": "4:40:24", "remaining_time": "2:30:20", "throughput": 1484.5, "total_tokens": 24976640} {"current_steps": 118355, "total_steps": 181800, "loss": 0.0088, "lr": 1.636655395613892e-05, "epoch": 13.020352035203521, "percentage": 65.1, "elapsed_time": "4:40:25", "remaining_time": "2:30:19", "throughput": 1484.5, "total_tokens": 24977664} {"current_steps": 118360, "total_steps": 181800, "loss": 0.0105, "lr": 1.636430158411935e-05, "epoch": 13.02090209020902, "percentage": 65.1, "elapsed_time": "4:40:26", "remaining_time": "2:30:18", "throughput": 1484.51, "total_tokens": 24978720} {"current_steps": 118365, "total_steps": 181800, "loss": 0.0658, "lr": 1.6362049291690877e-05, "epoch": 13.021452145214521, "percentage": 65.11, "elapsed_time": "4:40:26", "remaining_time": "2:30:18", "throughput": 1484.51, "total_tokens": 24979776} {"current_steps": 118370, "total_steps": 181800, "loss": 0.0057, "lr": 1.6359797078874238e-05, "epoch": 13.022002200220022, "percentage": 65.11, "elapsed_time": "4:40:27", "remaining_time": "2:30:17", "throughput": 1484.51, "total_tokens": 24980832} {"current_steps": 118375, "total_steps": 181800, "loss": 0.0233, "lr": 1.6357544945690213e-05, "epoch": 13.022552255225522, "percentage": 65.11, "elapsed_time": "4:40:28", "remaining_time": "2:30:16", "throughput": 1484.51, "total_tokens": 24981856} {"current_steps": 118380, "total_steps": 181800, "loss": 0.0432, "lr": 1.6355292892159553e-05, "epoch": 13.023102310231023, "percentage": 65.12, "elapsed_time": "4:40:29", "remaining_time": "2:30:15", "throughput": 1484.51, "total_tokens": 24982912} {"current_steps": 118385, "total_steps": 181800, "loss": 0.0973, "lr": 1.6353040918303e-05, "epoch": 13.023652365236524, "percentage": 65.12, "elapsed_time": "4:40:29", "remaining_time": "2:30:15", "throughput": 1484.52, "total_tokens": 24984000} {"current_steps": 118390, "total_steps": 181800, "loss": 0.0352, "lr": 1.6350789024141326e-05, "epoch": 13.024202420242025, "percentage": 65.12, "elapsed_time": "4:40:30", "remaining_time": "2:30:14", "throughput": 1484.52, "total_tokens": 24985088} {"current_steps": 118395, "total_steps": 181800, "loss": 0.0537, "lr": 1.634853720969527e-05, "epoch": 13.024752475247524, "percentage": 65.12, "elapsed_time": "4:40:31", "remaining_time": "2:30:13", "throughput": 1484.52, "total_tokens": 24986080} {"current_steps": 118400, "total_steps": 181800, "loss": 0.0403, "lr": 1.634628547498561e-05, "epoch": 13.025302530253025, "percentage": 65.13, "elapsed_time": "4:40:31", "remaining_time": "2:30:12", "throughput": 1484.52, "total_tokens": 24987168} {"current_steps": 118405, "total_steps": 181800, "loss": 0.03, "lr": 1.634403382003308e-05, "epoch": 13.025852585258527, "percentage": 65.13, "elapsed_time": "4:40:32", "remaining_time": "2:30:12", "throughput": 1484.52, "total_tokens": 24988192} {"current_steps": 118410, "total_steps": 181800, "loss": 0.0111, "lr": 1.6341782244858425e-05, "epoch": 13.026402640264026, "percentage": 65.13, "elapsed_time": "4:40:33", "remaining_time": "2:30:11", "throughput": 1484.52, "total_tokens": 24989216} {"current_steps": 118415, "total_steps": 181800, "loss": 0.0071, "lr": 1.6339530749482416e-05, "epoch": 13.026952695269527, "percentage": 65.13, "elapsed_time": "4:40:33", "remaining_time": "2:30:10", "throughput": 1484.52, "total_tokens": 24990272} {"current_steps": 118420, "total_steps": 181800, "loss": 0.1192, "lr": 1.633727933392579e-05, "epoch": 13.027502750275028, "percentage": 65.14, "elapsed_time": "4:40:34", "remaining_time": "2:30:10", "throughput": 1484.52, "total_tokens": 24991328} {"current_steps": 118425, "total_steps": 181800, "loss": 0.0035, "lr": 1.6335027998209317e-05, "epoch": 13.028052805280527, "percentage": 65.14, "elapsed_time": "4:40:35", "remaining_time": "2:30:09", "throughput": 1484.53, "total_tokens": 24992480} {"current_steps": 118430, "total_steps": 181800, "loss": 0.0049, "lr": 1.633277674235373e-05, "epoch": 13.028602860286028, "percentage": 65.14, "elapsed_time": "4:40:35", "remaining_time": "2:30:08", "throughput": 1484.53, "total_tokens": 24993568} {"current_steps": 118435, "total_steps": 181800, "loss": 0.0175, "lr": 1.6330525566379772e-05, "epoch": 13.02915291529153, "percentage": 65.15, "elapsed_time": "4:40:36", "remaining_time": "2:30:07", "throughput": 1484.54, "total_tokens": 24994624} {"current_steps": 118440, "total_steps": 181800, "loss": 0.0597, "lr": 1.6328274470308213e-05, "epoch": 13.029702970297029, "percentage": 65.15, "elapsed_time": "4:40:37", "remaining_time": "2:30:07", "throughput": 1484.53, "total_tokens": 24995616} {"current_steps": 118445, "total_steps": 181800, "loss": 0.0994, "lr": 1.6326023454159776e-05, "epoch": 13.03025302530253, "percentage": 65.15, "elapsed_time": "4:40:38", "remaining_time": "2:30:06", "throughput": 1484.54, "total_tokens": 24996736} {"current_steps": 118450, "total_steps": 181800, "loss": 0.0958, "lr": 1.632377251795522e-05, "epoch": 13.030803080308031, "percentage": 65.15, "elapsed_time": "4:40:38", "remaining_time": "2:30:05", "throughput": 1484.54, "total_tokens": 24997792} {"current_steps": 118455, "total_steps": 181800, "loss": 0.0614, "lr": 1.63215216617153e-05, "epoch": 13.031353135313532, "percentage": 65.16, "elapsed_time": "4:40:39", "remaining_time": "2:30:05", "throughput": 1484.55, "total_tokens": 24998880} {"current_steps": 118460, "total_steps": 181800, "loss": 0.0719, "lr": 1.6319270885460734e-05, "epoch": 13.031903190319031, "percentage": 65.16, "elapsed_time": "4:40:40", "remaining_time": "2:30:04", "throughput": 1484.55, "total_tokens": 24999968} {"current_steps": 118465, "total_steps": 181800, "loss": 0.0096, "lr": 1.6317020189212294e-05, "epoch": 13.032453245324533, "percentage": 65.16, "elapsed_time": "4:40:40", "remaining_time": "2:30:03", "throughput": 1484.55, "total_tokens": 25000992} {"current_steps": 118470, "total_steps": 181800, "loss": 0.0032, "lr": 1.6314769572990708e-05, "epoch": 13.033003300330034, "percentage": 65.17, "elapsed_time": "4:40:41", "remaining_time": "2:30:02", "throughput": 1484.55, "total_tokens": 25002080} {"current_steps": 118475, "total_steps": 181800, "loss": 0.005, "lr": 1.631251903681672e-05, "epoch": 13.033553355335533, "percentage": 65.17, "elapsed_time": "4:40:42", "remaining_time": "2:30:02", "throughput": 1484.55, "total_tokens": 25003072} {"current_steps": 118480, "total_steps": 181800, "loss": 0.0422, "lr": 1.631026858071109e-05, "epoch": 13.034103410341034, "percentage": 65.17, "elapsed_time": "4:40:42", "remaining_time": "2:30:01", "throughput": 1484.56, "total_tokens": 25004160} {"current_steps": 118485, "total_steps": 181800, "loss": 0.0071, "lr": 1.6308018204694527e-05, "epoch": 13.034653465346535, "percentage": 65.17, "elapsed_time": "4:40:43", "remaining_time": "2:30:00", "throughput": 1484.56, "total_tokens": 25005248} {"current_steps": 118490, "total_steps": 181800, "loss": 0.1128, "lr": 1.63057679087878e-05, "epoch": 13.035203520352034, "percentage": 65.18, "elapsed_time": "4:40:44", "remaining_time": "2:29:59", "throughput": 1484.56, "total_tokens": 25006304} {"current_steps": 118495, "total_steps": 181800, "loss": 0.0027, "lr": 1.630351769301163e-05, "epoch": 13.035753575357536, "percentage": 65.18, "elapsed_time": "4:40:44", "remaining_time": "2:29:59", "throughput": 1484.56, "total_tokens": 25007360} {"current_steps": 118500, "total_steps": 181800, "loss": 0.0024, "lr": 1.6301267557386777e-05, "epoch": 13.036303630363037, "percentage": 65.18, "elapsed_time": "4:40:45", "remaining_time": "2:29:58", "throughput": 1484.57, "total_tokens": 25008416} {"current_steps": 118505, "total_steps": 181800, "loss": 0.0072, "lr": 1.629901750193396e-05, "epoch": 13.036853685368538, "percentage": 65.18, "elapsed_time": "4:40:46", "remaining_time": "2:29:57", "throughput": 1484.57, "total_tokens": 25009440} {"current_steps": 118510, "total_steps": 181800, "loss": 0.0921, "lr": 1.629676752667392e-05, "epoch": 13.037403740374037, "percentage": 65.19, "elapsed_time": "4:40:46", "remaining_time": "2:29:57", "throughput": 1484.57, "total_tokens": 25010464} {"current_steps": 118515, "total_steps": 181800, "loss": 0.0458, "lr": 1.6294517631627405e-05, "epoch": 13.037953795379538, "percentage": 65.19, "elapsed_time": "4:40:47", "remaining_time": "2:29:56", "throughput": 1484.57, "total_tokens": 25011520} {"current_steps": 118520, "total_steps": 181800, "loss": 0.0214, "lr": 1.6292267816815135e-05, "epoch": 13.03850385038504, "percentage": 65.19, "elapsed_time": "4:40:48", "remaining_time": "2:29:55", "throughput": 1484.57, "total_tokens": 25012608} {"current_steps": 118525, "total_steps": 181800, "loss": 0.0529, "lr": 1.6290018082257857e-05, "epoch": 13.039053905390539, "percentage": 65.2, "elapsed_time": "4:40:49", "remaining_time": "2:29:54", "throughput": 1484.57, "total_tokens": 25013664} {"current_steps": 118530, "total_steps": 181800, "loss": 0.0037, "lr": 1.6287768427976315e-05, "epoch": 13.03960396039604, "percentage": 65.2, "elapsed_time": "4:40:49", "remaining_time": "2:29:54", "throughput": 1484.57, "total_tokens": 25014720} {"current_steps": 118535, "total_steps": 181800, "loss": 0.1915, "lr": 1.628551885399121e-05, "epoch": 13.04015401540154, "percentage": 65.2, "elapsed_time": "4:40:50", "remaining_time": "2:29:53", "throughput": 1484.58, "total_tokens": 25015808} {"current_steps": 118540, "total_steps": 181800, "loss": 0.151, "lr": 1.6283269360323312e-05, "epoch": 13.04070407040704, "percentage": 65.2, "elapsed_time": "4:40:51", "remaining_time": "2:29:52", "throughput": 1484.58, "total_tokens": 25016800} {"current_steps": 118545, "total_steps": 181800, "loss": 0.0008, "lr": 1.6281019946993332e-05, "epoch": 13.041254125412541, "percentage": 65.21, "elapsed_time": "4:40:51", "remaining_time": "2:29:52", "throughput": 1484.58, "total_tokens": 25017888} {"current_steps": 118550, "total_steps": 181800, "loss": 0.0128, "lr": 1.6278770614022002e-05, "epoch": 13.041804180418042, "percentage": 65.21, "elapsed_time": "4:40:52", "remaining_time": "2:29:51", "throughput": 1484.58, "total_tokens": 25018912} {"current_steps": 118555, "total_steps": 181800, "loss": 0.0203, "lr": 1.627652136143007e-05, "epoch": 13.042354235423542, "percentage": 65.21, "elapsed_time": "4:40:53", "remaining_time": "2:29:50", "throughput": 1484.58, "total_tokens": 25020000} {"current_steps": 118560, "total_steps": 181800, "loss": 0.0099, "lr": 1.6274272189238244e-05, "epoch": 13.042904290429043, "percentage": 65.21, "elapsed_time": "4:40:53", "remaining_time": "2:29:49", "throughput": 1484.58, "total_tokens": 25021056} {"current_steps": 118565, "total_steps": 181800, "loss": 0.0028, "lr": 1.627202309746727e-05, "epoch": 13.043454345434544, "percentage": 65.22, "elapsed_time": "4:40:54", "remaining_time": "2:29:49", "throughput": 1484.59, "total_tokens": 25022112} {"current_steps": 118570, "total_steps": 181800, "loss": 0.0309, "lr": 1.6269774086137874e-05, "epoch": 13.044004400440045, "percentage": 65.22, "elapsed_time": "4:40:55", "remaining_time": "2:29:48", "throughput": 1484.59, "total_tokens": 25023168} {"current_steps": 118575, "total_steps": 181800, "loss": 0.0022, "lr": 1.6267525155270773e-05, "epoch": 13.044554455445544, "percentage": 65.22, "elapsed_time": "4:40:55", "remaining_time": "2:29:47", "throughput": 1484.59, "total_tokens": 25024224} {"current_steps": 118580, "total_steps": 181800, "loss": 0.1849, "lr": 1.6265276304886707e-05, "epoch": 13.045104510451045, "percentage": 65.23, "elapsed_time": "4:40:56", "remaining_time": "2:29:47", "throughput": 1484.59, "total_tokens": 25025280} {"current_steps": 118585, "total_steps": 181800, "loss": 0.0992, "lr": 1.6263027535006393e-05, "epoch": 13.045654565456546, "percentage": 65.23, "elapsed_time": "4:40:57", "remaining_time": "2:29:46", "throughput": 1484.59, "total_tokens": 25026368} {"current_steps": 118590, "total_steps": 181800, "loss": 0.0508, "lr": 1.6260778845650564e-05, "epoch": 13.046204620462046, "percentage": 65.23, "elapsed_time": "4:40:58", "remaining_time": "2:29:45", "throughput": 1484.6, "total_tokens": 25027456} {"current_steps": 118595, "total_steps": 181800, "loss": 0.0053, "lr": 1.6258530236839952e-05, "epoch": 13.046754675467547, "percentage": 65.23, "elapsed_time": "4:40:58", "remaining_time": "2:29:44", "throughput": 1484.6, "total_tokens": 25028448} {"current_steps": 118600, "total_steps": 181800, "loss": 0.0028, "lr": 1.625628170859526e-05, "epoch": 13.047304730473048, "percentage": 65.24, "elapsed_time": "4:40:59", "remaining_time": "2:29:44", "throughput": 1484.6, "total_tokens": 25029504} {"current_steps": 118605, "total_steps": 181800, "loss": 0.0044, "lr": 1.625403326093723e-05, "epoch": 13.047854785478547, "percentage": 65.24, "elapsed_time": "4:41:00", "remaining_time": "2:29:43", "throughput": 1484.6, "total_tokens": 25030592} {"current_steps": 118610, "total_steps": 181800, "loss": 0.0108, "lr": 1.6251784893886573e-05, "epoch": 13.048404840484048, "percentage": 65.24, "elapsed_time": "4:41:00", "remaining_time": "2:29:42", "throughput": 1484.6, "total_tokens": 25031680} {"current_steps": 118615, "total_steps": 181800, "loss": 0.0093, "lr": 1.6249536607464026e-05, "epoch": 13.04895489548955, "percentage": 65.24, "elapsed_time": "4:41:01", "remaining_time": "2:29:41", "throughput": 1484.61, "total_tokens": 25032704} {"current_steps": 118620, "total_steps": 181800, "loss": 0.0032, "lr": 1.62472884016903e-05, "epoch": 13.049504950495049, "percentage": 65.25, "elapsed_time": "4:41:02", "remaining_time": "2:29:41", "throughput": 1484.61, "total_tokens": 25033792} {"current_steps": 118625, "total_steps": 181800, "loss": 0.0027, "lr": 1.624504027658611e-05, "epoch": 13.05005500550055, "percentage": 65.25, "elapsed_time": "4:41:02", "remaining_time": "2:29:40", "throughput": 1484.61, "total_tokens": 25034848} {"current_steps": 118630, "total_steps": 181800, "loss": 0.0019, "lr": 1.6242792232172193e-05, "epoch": 13.05060506050605, "percentage": 65.25, "elapsed_time": "4:41:04", "remaining_time": "2:29:40", "throughput": 1484.54, "total_tokens": 25035904} {"current_steps": 118635, "total_steps": 181800, "loss": 0.0472, "lr": 1.6240544268469246e-05, "epoch": 13.051155115511552, "percentage": 65.26, "elapsed_time": "4:41:05", "remaining_time": "2:29:39", "throughput": 1484.54, "total_tokens": 25036960} {"current_steps": 118640, "total_steps": 181800, "loss": 0.0025, "lr": 1.6238296385498002e-05, "epoch": 13.051705170517051, "percentage": 65.26, "elapsed_time": "4:41:05", "remaining_time": "2:29:38", "throughput": 1484.55, "total_tokens": 25038016} {"current_steps": 118645, "total_steps": 181800, "loss": 0.0098, "lr": 1.6236048583279186e-05, "epoch": 13.052255225522552, "percentage": 65.26, "elapsed_time": "4:41:06", "remaining_time": "2:29:38", "throughput": 1484.55, "total_tokens": 25039040} {"current_steps": 118650, "total_steps": 181800, "loss": 0.0059, "lr": 1.6233800861833486e-05, "epoch": 13.052805280528053, "percentage": 65.26, "elapsed_time": "4:41:07", "remaining_time": "2:29:37", "throughput": 1484.55, "total_tokens": 25040096} {"current_steps": 118655, "total_steps": 181800, "loss": 0.0014, "lr": 1.6231553221181655e-05, "epoch": 13.053355335533553, "percentage": 65.27, "elapsed_time": "4:41:07", "remaining_time": "2:29:36", "throughput": 1484.54, "total_tokens": 25041056} {"current_steps": 118660, "total_steps": 181800, "loss": 0.0044, "lr": 1.622930566134438e-05, "epoch": 13.053905390539054, "percentage": 65.27, "elapsed_time": "4:41:08", "remaining_time": "2:29:35", "throughput": 1484.55, "total_tokens": 25042112} {"current_steps": 118665, "total_steps": 181800, "loss": 0.0204, "lr": 1.6227058182342393e-05, "epoch": 13.054455445544555, "percentage": 65.27, "elapsed_time": "4:41:09", "remaining_time": "2:29:35", "throughput": 1484.55, "total_tokens": 25043200} {"current_steps": 118670, "total_steps": 181800, "loss": 0.1177, "lr": 1.6224810784196403e-05, "epoch": 13.055005500550054, "percentage": 65.28, "elapsed_time": "4:41:09", "remaining_time": "2:29:34", "throughput": 1484.55, "total_tokens": 25044256} {"current_steps": 118675, "total_steps": 181800, "loss": 0.0129, "lr": 1.622256346692711e-05, "epoch": 13.055555555555555, "percentage": 65.28, "elapsed_time": "4:41:10", "remaining_time": "2:29:33", "throughput": 1484.55, "total_tokens": 25045312} {"current_steps": 118680, "total_steps": 181800, "loss": 0.1899, "lr": 1.6220316230555245e-05, "epoch": 13.056105610561056, "percentage": 65.28, "elapsed_time": "4:41:11", "remaining_time": "2:29:33", "throughput": 1484.56, "total_tokens": 25046368} {"current_steps": 118685, "total_steps": 181800, "loss": 0.0798, "lr": 1.6218069075101507e-05, "epoch": 13.056655665566556, "percentage": 65.28, "elapsed_time": "4:41:11", "remaining_time": "2:29:32", "throughput": 1484.56, "total_tokens": 25047456} {"current_steps": 118690, "total_steps": 181800, "loss": 0.0079, "lr": 1.6215822000586623e-05, "epoch": 13.057205720572057, "percentage": 65.29, "elapsed_time": "4:41:12", "remaining_time": "2:29:31", "throughput": 1484.56, "total_tokens": 25048544} {"current_steps": 118695, "total_steps": 181800, "loss": 0.0103, "lr": 1.6213575007031287e-05, "epoch": 13.057755775577558, "percentage": 65.29, "elapsed_time": "4:41:13", "remaining_time": "2:29:30", "throughput": 1484.57, "total_tokens": 25049600} {"current_steps": 118700, "total_steps": 181800, "loss": 0.0027, "lr": 1.6211328094456207e-05, "epoch": 13.058305830583059, "percentage": 65.29, "elapsed_time": "4:41:14", "remaining_time": "2:29:30", "throughput": 1484.57, "total_tokens": 25050688} {"current_steps": 118705, "total_steps": 181800, "loss": 0.034, "lr": 1.6209081262882115e-05, "epoch": 13.058855885588558, "percentage": 65.29, "elapsed_time": "4:41:14", "remaining_time": "2:29:29", "throughput": 1484.57, "total_tokens": 25051744} {"current_steps": 118710, "total_steps": 181800, "loss": 0.0073, "lr": 1.620683451232968e-05, "epoch": 13.05940594059406, "percentage": 65.3, "elapsed_time": "4:41:15", "remaining_time": "2:29:28", "throughput": 1484.57, "total_tokens": 25052768} {"current_steps": 118715, "total_steps": 181800, "loss": 0.014, "lr": 1.620458784281965e-05, "epoch": 13.05995599559956, "percentage": 65.3, "elapsed_time": "4:41:16", "remaining_time": "2:29:27", "throughput": 1484.57, "total_tokens": 25053792} {"current_steps": 118720, "total_steps": 181800, "loss": 0.0024, "lr": 1.620234125437271e-05, "epoch": 13.06050605060506, "percentage": 65.3, "elapsed_time": "4:41:16", "remaining_time": "2:29:27", "throughput": 1484.58, "total_tokens": 25054880} {"current_steps": 118725, "total_steps": 181800, "loss": 0.0305, "lr": 1.6200094747009565e-05, "epoch": 13.061056105610561, "percentage": 65.31, "elapsed_time": "4:41:17", "remaining_time": "2:29:26", "throughput": 1484.58, "total_tokens": 25056000} {"current_steps": 118730, "total_steps": 181800, "loss": 0.0923, "lr": 1.619784832075093e-05, "epoch": 13.061606160616062, "percentage": 65.31, "elapsed_time": "4:41:18", "remaining_time": "2:29:25", "throughput": 1484.58, "total_tokens": 25057056} {"current_steps": 118735, "total_steps": 181800, "loss": 0.0087, "lr": 1.61956019756175e-05, "epoch": 13.062156215621561, "percentage": 65.31, "elapsed_time": "4:41:18", "remaining_time": "2:29:25", "throughput": 1484.59, "total_tokens": 25058112} {"current_steps": 118740, "total_steps": 181800, "loss": 0.001, "lr": 1.6193355711629977e-05, "epoch": 13.062706270627062, "percentage": 65.31, "elapsed_time": "4:41:19", "remaining_time": "2:29:24", "throughput": 1484.59, "total_tokens": 25059136} {"current_steps": 118745, "total_steps": 181800, "loss": 0.0119, "lr": 1.619110952880908e-05, "epoch": 13.063256325632564, "percentage": 65.32, "elapsed_time": "4:41:20", "remaining_time": "2:29:23", "throughput": 1484.59, "total_tokens": 25060224} {"current_steps": 118750, "total_steps": 181800, "loss": 0.0312, "lr": 1.618886342717549e-05, "epoch": 13.063806380638065, "percentage": 65.32, "elapsed_time": "4:41:20", "remaining_time": "2:29:22", "throughput": 1484.59, "total_tokens": 25061184} {"current_steps": 118755, "total_steps": 181800, "loss": 0.0053, "lr": 1.618661740674992e-05, "epoch": 13.064356435643564, "percentage": 65.32, "elapsed_time": "4:41:21", "remaining_time": "2:29:22", "throughput": 1484.58, "total_tokens": 25062176} {"current_steps": 118760, "total_steps": 181800, "loss": 0.0851, "lr": 1.618437146755307e-05, "epoch": 13.064906490649065, "percentage": 65.32, "elapsed_time": "4:41:22", "remaining_time": "2:29:21", "throughput": 1484.58, "total_tokens": 25063168} {"current_steps": 118765, "total_steps": 181800, "loss": 0.0109, "lr": 1.6182125609605635e-05, "epoch": 13.065456545654566, "percentage": 65.33, "elapsed_time": "4:41:22", "remaining_time": "2:29:20", "throughput": 1484.58, "total_tokens": 25064224} {"current_steps": 118770, "total_steps": 181800, "loss": 0.0021, "lr": 1.6179879832928317e-05, "epoch": 13.066006600660065, "percentage": 65.33, "elapsed_time": "4:41:23", "remaining_time": "2:29:19", "throughput": 1484.59, "total_tokens": 25065312} {"current_steps": 118775, "total_steps": 181800, "loss": 0.1123, "lr": 1.6177634137541815e-05, "epoch": 13.066556655665567, "percentage": 65.33, "elapsed_time": "4:41:24", "remaining_time": "2:29:19", "throughput": 1484.59, "total_tokens": 25066400} {"current_steps": 118780, "total_steps": 181800, "loss": 0.0047, "lr": 1.6175388523466824e-05, "epoch": 13.067106710671068, "percentage": 65.34, "elapsed_time": "4:41:25", "remaining_time": "2:29:18", "throughput": 1484.59, "total_tokens": 25067456} {"current_steps": 118785, "total_steps": 181800, "loss": 0.0033, "lr": 1.617314299072405e-05, "epoch": 13.067656765676567, "percentage": 65.34, "elapsed_time": "4:41:25", "remaining_time": "2:29:17", "throughput": 1484.6, "total_tokens": 25068544} {"current_steps": 118790, "total_steps": 181800, "loss": 0.0779, "lr": 1.6170897539334175e-05, "epoch": 13.068206820682068, "percentage": 65.34, "elapsed_time": "4:41:26", "remaining_time": "2:29:17", "throughput": 1484.6, "total_tokens": 25069568} {"current_steps": 118795, "total_steps": 181800, "loss": 0.0164, "lr": 1.6168652169317904e-05, "epoch": 13.06875687568757, "percentage": 65.34, "elapsed_time": "4:41:27", "remaining_time": "2:29:16", "throughput": 1484.6, "total_tokens": 25070560} {"current_steps": 118800, "total_steps": 181800, "loss": 0.0025, "lr": 1.6166406880695922e-05, "epoch": 13.069306930693068, "percentage": 65.35, "elapsed_time": "4:41:27", "remaining_time": "2:29:15", "throughput": 1484.6, "total_tokens": 25071648} {"current_steps": 118805, "total_steps": 181800, "loss": 0.0529, "lr": 1.616416167348894e-05, "epoch": 13.06985698569857, "percentage": 65.35, "elapsed_time": "4:41:28", "remaining_time": "2:29:14", "throughput": 1484.6, "total_tokens": 25072704} {"current_steps": 118810, "total_steps": 181800, "loss": 0.0084, "lr": 1.6161916547717635e-05, "epoch": 13.07040704070407, "percentage": 65.35, "elapsed_time": "4:41:29", "remaining_time": "2:29:14", "throughput": 1484.6, "total_tokens": 25073696} {"current_steps": 118815, "total_steps": 181800, "loss": 0.1257, "lr": 1.6159671503402697e-05, "epoch": 13.070957095709572, "percentage": 65.35, "elapsed_time": "4:41:29", "remaining_time": "2:29:13", "throughput": 1484.61, "total_tokens": 25074816} {"current_steps": 118820, "total_steps": 181800, "loss": 0.0088, "lr": 1.615742654056484e-05, "epoch": 13.071507150715071, "percentage": 65.36, "elapsed_time": "4:41:30", "remaining_time": "2:29:12", "throughput": 1484.61, "total_tokens": 25075904} {"current_steps": 118825, "total_steps": 181800, "loss": 0.0219, "lr": 1.615518165922472e-05, "epoch": 13.072057205720572, "percentage": 65.36, "elapsed_time": "4:41:31", "remaining_time": "2:29:12", "throughput": 1484.61, "total_tokens": 25076992} {"current_steps": 118830, "total_steps": 181800, "loss": 0.0035, "lr": 1.615293685940306e-05, "epoch": 13.072607260726073, "percentage": 65.36, "elapsed_time": "4:41:31", "remaining_time": "2:29:11", "throughput": 1484.62, "total_tokens": 25078080} {"current_steps": 118835, "total_steps": 181800, "loss": 0.0315, "lr": 1.6150692141120533e-05, "epoch": 13.073157315731573, "percentage": 65.37, "elapsed_time": "4:41:32", "remaining_time": "2:29:10", "throughput": 1484.62, "total_tokens": 25079136} {"current_steps": 118840, "total_steps": 181800, "loss": 0.0233, "lr": 1.6148447504397825e-05, "epoch": 13.073707370737074, "percentage": 65.37, "elapsed_time": "4:41:33", "remaining_time": "2:29:09", "throughput": 1484.62, "total_tokens": 25080128} {"current_steps": 118845, "total_steps": 181800, "loss": 0.0811, "lr": 1.614620294925564e-05, "epoch": 13.074257425742575, "percentage": 65.37, "elapsed_time": "4:41:34", "remaining_time": "2:29:09", "throughput": 1484.62, "total_tokens": 25081184} {"current_steps": 118850, "total_steps": 181800, "loss": 0.0041, "lr": 1.6143958475714644e-05, "epoch": 13.074807480748074, "percentage": 65.37, "elapsed_time": "4:41:34", "remaining_time": "2:29:08", "throughput": 1484.62, "total_tokens": 25082272} {"current_steps": 118855, "total_steps": 181800, "loss": 0.0018, "lr": 1.614171408379554e-05, "epoch": 13.075357535753575, "percentage": 65.38, "elapsed_time": "4:41:35", "remaining_time": "2:29:07", "throughput": 1484.62, "total_tokens": 25083296} {"current_steps": 118860, "total_steps": 181800, "loss": 0.022, "lr": 1.6139469773519007e-05, "epoch": 13.075907590759076, "percentage": 65.38, "elapsed_time": "4:41:36", "remaining_time": "2:29:07", "throughput": 1484.62, "total_tokens": 25084288} {"current_steps": 118865, "total_steps": 181800, "loss": 0.0456, "lr": 1.613722554490572e-05, "epoch": 13.076457645764576, "percentage": 65.38, "elapsed_time": "4:41:36", "remaining_time": "2:29:06", "throughput": 1484.62, "total_tokens": 25085344} {"current_steps": 118870, "total_steps": 181800, "loss": 0.0471, "lr": 1.613498139797638e-05, "epoch": 13.077007700770077, "percentage": 65.39, "elapsed_time": "4:41:37", "remaining_time": "2:29:05", "throughput": 1484.62, "total_tokens": 25086400} {"current_steps": 118875, "total_steps": 181800, "loss": 0.0086, "lr": 1.613273733275166e-05, "epoch": 13.077557755775578, "percentage": 65.39, "elapsed_time": "4:41:38", "remaining_time": "2:29:04", "throughput": 1484.63, "total_tokens": 25087488} {"current_steps": 118880, "total_steps": 181800, "loss": 0.012, "lr": 1.613049334925225e-05, "epoch": 13.078107810781079, "percentage": 65.39, "elapsed_time": "4:41:38", "remaining_time": "2:29:04", "throughput": 1484.63, "total_tokens": 25088512} {"current_steps": 118885, "total_steps": 181800, "loss": 0.0012, "lr": 1.6128249447498822e-05, "epoch": 13.078657865786578, "percentage": 65.39, "elapsed_time": "4:41:39", "remaining_time": "2:29:03", "throughput": 1484.63, "total_tokens": 25089536} {"current_steps": 118890, "total_steps": 181800, "loss": 0.0506, "lr": 1.6126005627512058e-05, "epoch": 13.07920792079208, "percentage": 65.4, "elapsed_time": "4:41:40", "remaining_time": "2:29:02", "throughput": 1484.62, "total_tokens": 25090528} {"current_steps": 118895, "total_steps": 181800, "loss": 0.0088, "lr": 1.612376188931265e-05, "epoch": 13.07975797579758, "percentage": 65.4, "elapsed_time": "4:41:40", "remaining_time": "2:29:01", "throughput": 1484.63, "total_tokens": 25091616} {"current_steps": 118900, "total_steps": 181800, "loss": 0.0017, "lr": 1.612151823292126e-05, "epoch": 13.08030803080308, "percentage": 65.4, "elapsed_time": "4:41:41", "remaining_time": "2:29:01", "throughput": 1484.63, "total_tokens": 25092640} {"current_steps": 118905, "total_steps": 181800, "loss": 0.0058, "lr": 1.6119274658358586e-05, "epoch": 13.08085808580858, "percentage": 65.4, "elapsed_time": "4:41:42", "remaining_time": "2:29:00", "throughput": 1484.63, "total_tokens": 25093760} {"current_steps": 118910, "total_steps": 181800, "loss": 0.0521, "lr": 1.6117031165645295e-05, "epoch": 13.081408140814082, "percentage": 65.41, "elapsed_time": "4:41:43", "remaining_time": "2:28:59", "throughput": 1484.64, "total_tokens": 25094816} {"current_steps": 118915, "total_steps": 181800, "loss": 0.0446, "lr": 1.611478775480206e-05, "epoch": 13.081958195819581, "percentage": 65.41, "elapsed_time": "4:41:43", "remaining_time": "2:28:59", "throughput": 1484.63, "total_tokens": 25095776} {"current_steps": 118920, "total_steps": 181800, "loss": 0.043, "lr": 1.6112544425849567e-05, "epoch": 13.082508250825082, "percentage": 65.41, "elapsed_time": "4:41:44", "remaining_time": "2:28:58", "throughput": 1484.63, "total_tokens": 25096832} {"current_steps": 118925, "total_steps": 181800, "loss": 0.0098, "lr": 1.6110301178808486e-05, "epoch": 13.083058305830583, "percentage": 65.42, "elapsed_time": "4:41:45", "remaining_time": "2:28:57", "throughput": 1484.63, "total_tokens": 25097888} {"current_steps": 118930, "total_steps": 181800, "loss": 0.0542, "lr": 1.610805801369949e-05, "epoch": 13.083608360836084, "percentage": 65.42, "elapsed_time": "4:41:45", "remaining_time": "2:28:56", "throughput": 1484.63, "total_tokens": 25098880} {"current_steps": 118935, "total_steps": 181800, "loss": 0.0032, "lr": 1.6105814930543266e-05, "epoch": 13.084158415841584, "percentage": 65.42, "elapsed_time": "4:41:46", "remaining_time": "2:28:56", "throughput": 1484.63, "total_tokens": 25099904} {"current_steps": 118940, "total_steps": 181800, "loss": 0.0165, "lr": 1.6103571929360467e-05, "epoch": 13.084708470847085, "percentage": 65.42, "elapsed_time": "4:41:47", "remaining_time": "2:28:55", "throughput": 1484.64, "total_tokens": 25100992} {"current_steps": 118945, "total_steps": 181800, "loss": 0.1103, "lr": 1.6101329010171782e-05, "epoch": 13.085258525852586, "percentage": 65.43, "elapsed_time": "4:41:47", "remaining_time": "2:28:54", "throughput": 1484.64, "total_tokens": 25102016} {"current_steps": 118950, "total_steps": 181800, "loss": 0.038, "lr": 1.6099086172997882e-05, "epoch": 13.085808580858085, "percentage": 65.43, "elapsed_time": "4:41:48", "remaining_time": "2:28:54", "throughput": 1484.64, "total_tokens": 25103072} {"current_steps": 118955, "total_steps": 181800, "loss": 0.0026, "lr": 1.609684341785942e-05, "epoch": 13.086358635863586, "percentage": 65.43, "elapsed_time": "4:41:49", "remaining_time": "2:28:53", "throughput": 1484.64, "total_tokens": 25104160} {"current_steps": 118960, "total_steps": 181800, "loss": 0.0929, "lr": 1.6094600744777094e-05, "epoch": 13.086908690869087, "percentage": 65.43, "elapsed_time": "4:41:49", "remaining_time": "2:28:52", "throughput": 1484.64, "total_tokens": 25105216} {"current_steps": 118965, "total_steps": 181800, "loss": 0.0092, "lr": 1.6092358153771547e-05, "epoch": 13.087458745874587, "percentage": 65.44, "elapsed_time": "4:41:50", "remaining_time": "2:28:51", "throughput": 1484.64, "total_tokens": 25106272} {"current_steps": 118970, "total_steps": 181800, "loss": 0.0022, "lr": 1.6090115644863467e-05, "epoch": 13.088008800880088, "percentage": 65.44, "elapsed_time": "4:41:51", "remaining_time": "2:28:51", "throughput": 1484.65, "total_tokens": 25107328} {"current_steps": 118975, "total_steps": 181800, "loss": 0.0051, "lr": 1.6087873218073523e-05, "epoch": 13.088558855885589, "percentage": 65.44, "elapsed_time": "4:41:52", "remaining_time": "2:28:50", "throughput": 1484.65, "total_tokens": 25108352} {"current_steps": 118980, "total_steps": 181800, "loss": 0.0374, "lr": 1.6085630873422363e-05, "epoch": 13.089108910891088, "percentage": 65.45, "elapsed_time": "4:41:52", "remaining_time": "2:28:49", "throughput": 1484.65, "total_tokens": 25109376} {"current_steps": 118985, "total_steps": 181800, "loss": 0.0869, "lr": 1.608338861093067e-05, "epoch": 13.08965896589659, "percentage": 65.45, "elapsed_time": "4:41:53", "remaining_time": "2:28:48", "throughput": 1484.65, "total_tokens": 25110432} {"current_steps": 118990, "total_steps": 181800, "loss": 0.0637, "lr": 1.6081146430619102e-05, "epoch": 13.09020902090209, "percentage": 65.45, "elapsed_time": "4:41:54", "remaining_time": "2:28:48", "throughput": 1484.65, "total_tokens": 25111520} {"current_steps": 118995, "total_steps": 181800, "loss": 0.0466, "lr": 1.6078904332508344e-05, "epoch": 13.090759075907592, "percentage": 65.45, "elapsed_time": "4:41:54", "remaining_time": "2:28:47", "throughput": 1484.65, "total_tokens": 25112544} {"current_steps": 119000, "total_steps": 181800, "loss": 0.0722, "lr": 1.6076662316619033e-05, "epoch": 13.091309130913091, "percentage": 65.46, "elapsed_time": "4:41:55", "remaining_time": "2:28:46", "throughput": 1484.66, "total_tokens": 25113664} {"current_steps": 119005, "total_steps": 181800, "loss": 0.0014, "lr": 1.607442038297184e-05, "epoch": 13.091859185918592, "percentage": 65.46, "elapsed_time": "4:41:56", "remaining_time": "2:28:46", "throughput": 1484.66, "total_tokens": 25114688} {"current_steps": 119010, "total_steps": 181800, "loss": 0.0607, "lr": 1.6072178531587437e-05, "epoch": 13.092409240924093, "percentage": 65.46, "elapsed_time": "4:41:56", "remaining_time": "2:28:45", "throughput": 1484.65, "total_tokens": 25115680} {"current_steps": 119015, "total_steps": 181800, "loss": 0.0604, "lr": 1.6069936762486467e-05, "epoch": 13.092959295929592, "percentage": 65.46, "elapsed_time": "4:41:57", "remaining_time": "2:28:44", "throughput": 1484.66, "total_tokens": 25116736} {"current_steps": 119020, "total_steps": 181800, "loss": 0.0093, "lr": 1.6067695075689622e-05, "epoch": 13.093509350935093, "percentage": 65.47, "elapsed_time": "4:41:58", "remaining_time": "2:28:43", "throughput": 1484.66, "total_tokens": 25117760} {"current_steps": 119025, "total_steps": 181800, "loss": 0.0299, "lr": 1.606545347121754e-05, "epoch": 13.094059405940595, "percentage": 65.47, "elapsed_time": "4:41:58", "remaining_time": "2:28:43", "throughput": 1484.66, "total_tokens": 25118816} {"current_steps": 119030, "total_steps": 181800, "loss": 0.1727, "lr": 1.6063211949090882e-05, "epoch": 13.094609460946094, "percentage": 65.47, "elapsed_time": "4:41:59", "remaining_time": "2:28:42", "throughput": 1484.66, "total_tokens": 25119872} {"current_steps": 119035, "total_steps": 181800, "loss": 0.0201, "lr": 1.606097050933032e-05, "epoch": 13.095159515951595, "percentage": 65.48, "elapsed_time": "4:42:00", "remaining_time": "2:28:41", "throughput": 1484.66, "total_tokens": 25120864} {"current_steps": 119040, "total_steps": 181800, "loss": 0.0087, "lr": 1.6058729151956493e-05, "epoch": 13.095709570957096, "percentage": 65.48, "elapsed_time": "4:42:00", "remaining_time": "2:28:41", "throughput": 1484.66, "total_tokens": 25121856} {"current_steps": 119045, "total_steps": 181800, "loss": 0.0029, "lr": 1.6056487876990072e-05, "epoch": 13.096259625962595, "percentage": 65.48, "elapsed_time": "4:42:01", "remaining_time": "2:28:40", "throughput": 1484.66, "total_tokens": 25122912} {"current_steps": 119050, "total_steps": 181800, "loss": 0.0028, "lr": 1.605424668445172e-05, "epoch": 13.096809680968097, "percentage": 65.48, "elapsed_time": "4:42:02", "remaining_time": "2:28:39", "throughput": 1484.66, "total_tokens": 25123904} {"current_steps": 119055, "total_steps": 181800, "loss": 0.0965, "lr": 1.6052005574362073e-05, "epoch": 13.097359735973598, "percentage": 65.49, "elapsed_time": "4:42:03", "remaining_time": "2:28:38", "throughput": 1484.66, "total_tokens": 25125056} {"current_steps": 119060, "total_steps": 181800, "loss": 0.0475, "lr": 1.60497645467418e-05, "epoch": 13.097909790979099, "percentage": 65.49, "elapsed_time": "4:42:03", "remaining_time": "2:28:38", "throughput": 1484.66, "total_tokens": 25126112} {"current_steps": 119065, "total_steps": 181800, "loss": 0.0049, "lr": 1.6047523601611546e-05, "epoch": 13.098459845984598, "percentage": 65.49, "elapsed_time": "4:42:04", "remaining_time": "2:28:37", "throughput": 1484.66, "total_tokens": 25127136} {"current_steps": 119070, "total_steps": 181800, "loss": 0.0105, "lr": 1.6045282738991985e-05, "epoch": 13.099009900990099, "percentage": 65.5, "elapsed_time": "4:42:05", "remaining_time": "2:28:36", "throughput": 1484.67, "total_tokens": 25128224} {"current_steps": 119075, "total_steps": 181800, "loss": 0.0027, "lr": 1.6043041958903747e-05, "epoch": 13.0995599559956, "percentage": 65.5, "elapsed_time": "4:42:05", "remaining_time": "2:28:36", "throughput": 1484.67, "total_tokens": 25129248} {"current_steps": 119080, "total_steps": 181800, "loss": 0.0552, "lr": 1.6040801261367493e-05, "epoch": 13.1001100110011, "percentage": 65.5, "elapsed_time": "4:42:06", "remaining_time": "2:28:35", "throughput": 1484.67, "total_tokens": 25130304} {"current_steps": 119085, "total_steps": 181800, "loss": 0.0083, "lr": 1.6038560646403876e-05, "epoch": 13.1006600660066, "percentage": 65.5, "elapsed_time": "4:42:07", "remaining_time": "2:28:34", "throughput": 1484.67, "total_tokens": 25131360} {"current_steps": 119090, "total_steps": 181800, "loss": 0.1131, "lr": 1.6036320114033544e-05, "epoch": 13.101210121012102, "percentage": 65.51, "elapsed_time": "4:42:07", "remaining_time": "2:28:33", "throughput": 1484.67, "total_tokens": 25132416} {"current_steps": 119095, "total_steps": 181800, "loss": 0.002, "lr": 1.6034079664277158e-05, "epoch": 13.101760176017601, "percentage": 65.51, "elapsed_time": "4:42:08", "remaining_time": "2:28:33", "throughput": 1484.68, "total_tokens": 25133536} {"current_steps": 119100, "total_steps": 181800, "loss": 0.0731, "lr": 1.6031839297155348e-05, "epoch": 13.102310231023102, "percentage": 65.51, "elapsed_time": "4:42:09", "remaining_time": "2:28:32", "throughput": 1484.68, "total_tokens": 25134560} {"current_steps": 119105, "total_steps": 181800, "loss": 0.0502, "lr": 1.6029599012688774e-05, "epoch": 13.102860286028603, "percentage": 65.51, "elapsed_time": "4:42:09", "remaining_time": "2:28:31", "throughput": 1484.68, "total_tokens": 25135584} {"current_steps": 119110, "total_steps": 181800, "loss": 0.0042, "lr": 1.6027358810898085e-05, "epoch": 13.103410341034103, "percentage": 65.52, "elapsed_time": "4:42:10", "remaining_time": "2:28:30", "throughput": 1484.68, "total_tokens": 25136640} {"current_steps": 119115, "total_steps": 181800, "loss": 0.0901, "lr": 1.602511869180392e-05, "epoch": 13.103960396039604, "percentage": 65.52, "elapsed_time": "4:42:11", "remaining_time": "2:28:30", "throughput": 1484.68, "total_tokens": 25137696} {"current_steps": 119120, "total_steps": 181800, "loss": 0.0871, "lr": 1.6022878655426927e-05, "epoch": 13.104510451045105, "percentage": 65.52, "elapsed_time": "4:42:12", "remaining_time": "2:28:29", "throughput": 1484.69, "total_tokens": 25138816} {"current_steps": 119125, "total_steps": 181800, "loss": 0.0031, "lr": 1.6020638701787764e-05, "epoch": 13.105060506050606, "percentage": 65.53, "elapsed_time": "4:42:12", "remaining_time": "2:28:28", "throughput": 1484.69, "total_tokens": 25139808} {"current_steps": 119130, "total_steps": 181800, "loss": 0.0021, "lr": 1.6018398830907046e-05, "epoch": 13.105610561056105, "percentage": 65.53, "elapsed_time": "4:42:13", "remaining_time": "2:28:28", "throughput": 1484.69, "total_tokens": 25140864} {"current_steps": 119135, "total_steps": 181800, "loss": 0.0021, "lr": 1.6016159042805456e-05, "epoch": 13.106160616061606, "percentage": 65.53, "elapsed_time": "4:42:14", "remaining_time": "2:28:27", "throughput": 1484.69, "total_tokens": 25141888} {"current_steps": 119140, "total_steps": 181800, "loss": 0.039, "lr": 1.6013919337503606e-05, "epoch": 13.106710671067107, "percentage": 65.53, "elapsed_time": "4:42:14", "remaining_time": "2:28:26", "throughput": 1484.69, "total_tokens": 25142912} {"current_steps": 119145, "total_steps": 181800, "loss": 0.1431, "lr": 1.6011679715022155e-05, "epoch": 13.107260726072607, "percentage": 65.54, "elapsed_time": "4:42:15", "remaining_time": "2:28:25", "throughput": 1484.69, "total_tokens": 25143872} {"current_steps": 119150, "total_steps": 181800, "loss": 0.0034, "lr": 1.6009440175381742e-05, "epoch": 13.107810781078108, "percentage": 65.54, "elapsed_time": "4:42:16", "remaining_time": "2:28:25", "throughput": 1484.69, "total_tokens": 25144928} {"current_steps": 119155, "total_steps": 181800, "loss": 0.0378, "lr": 1.6007200718602994e-05, "epoch": 13.108360836083609, "percentage": 65.54, "elapsed_time": "4:42:16", "remaining_time": "2:28:24", "throughput": 1484.69, "total_tokens": 25145984} {"current_steps": 119160, "total_steps": 181800, "loss": 0.0016, "lr": 1.600496134470657e-05, "epoch": 13.108910891089108, "percentage": 65.54, "elapsed_time": "4:42:17", "remaining_time": "2:28:23", "throughput": 1484.69, "total_tokens": 25147040} {"current_steps": 119165, "total_steps": 181800, "loss": 0.0023, "lr": 1.6002722053713106e-05, "epoch": 13.10946094609461, "percentage": 65.55, "elapsed_time": "4:42:18", "remaining_time": "2:28:23", "throughput": 1484.69, "total_tokens": 25148096} {"current_steps": 119170, "total_steps": 181800, "loss": 0.0368, "lr": 1.600048284564322e-05, "epoch": 13.11001100110011, "percentage": 65.55, "elapsed_time": "4:42:18", "remaining_time": "2:28:22", "throughput": 1484.7, "total_tokens": 25149152} {"current_steps": 119175, "total_steps": 181800, "loss": 0.0594, "lr": 1.5998243720517575e-05, "epoch": 13.110561056105611, "percentage": 65.55, "elapsed_time": "4:42:19", "remaining_time": "2:28:21", "throughput": 1484.7, "total_tokens": 25150208} {"current_steps": 119180, "total_steps": 181800, "loss": 0.0085, "lr": 1.5996004678356793e-05, "epoch": 13.11111111111111, "percentage": 65.56, "elapsed_time": "4:42:20", "remaining_time": "2:28:20", "throughput": 1484.7, "total_tokens": 25151296} {"current_steps": 119185, "total_steps": 181800, "loss": 0.0138, "lr": 1.5993765719181523e-05, "epoch": 13.111661166116612, "percentage": 65.56, "elapsed_time": "4:42:20", "remaining_time": "2:28:20", "throughput": 1484.7, "total_tokens": 25152352} {"current_steps": 119190, "total_steps": 181800, "loss": 0.0596, "lr": 1.5991526843012396e-05, "epoch": 13.112211221122113, "percentage": 65.56, "elapsed_time": "4:42:21", "remaining_time": "2:28:19", "throughput": 1484.7, "total_tokens": 25153344} {"current_steps": 119195, "total_steps": 181800, "loss": 0.0542, "lr": 1.5989288049870027e-05, "epoch": 13.112761276127612, "percentage": 65.56, "elapsed_time": "4:42:22", "remaining_time": "2:28:18", "throughput": 1484.71, "total_tokens": 25154464} {"current_steps": 119200, "total_steps": 181800, "loss": 0.0984, "lr": 1.5987049339775078e-05, "epoch": 13.113311331133113, "percentage": 65.57, "elapsed_time": "4:42:23", "remaining_time": "2:28:17", "throughput": 1484.71, "total_tokens": 25155520} {"current_steps": 119205, "total_steps": 181800, "loss": 0.0028, "lr": 1.5984810712748163e-05, "epoch": 13.113861386138614, "percentage": 65.57, "elapsed_time": "4:42:23", "remaining_time": "2:28:17", "throughput": 1484.71, "total_tokens": 25156576} {"current_steps": 119210, "total_steps": 181800, "loss": 0.055, "lr": 1.5982572168809935e-05, "epoch": 13.114411441144114, "percentage": 65.57, "elapsed_time": "4:42:24", "remaining_time": "2:28:16", "throughput": 1484.71, "total_tokens": 25157664} {"current_steps": 119215, "total_steps": 181800, "loss": 0.0058, "lr": 1.5980333707981004e-05, "epoch": 13.114961496149615, "percentage": 65.57, "elapsed_time": "4:42:25", "remaining_time": "2:28:15", "throughput": 1484.71, "total_tokens": 25158688} {"current_steps": 119220, "total_steps": 181800, "loss": 0.0056, "lr": 1.5978095330282007e-05, "epoch": 13.115511551155116, "percentage": 65.58, "elapsed_time": "4:42:25", "remaining_time": "2:28:15", "throughput": 1484.72, "total_tokens": 25159744} {"current_steps": 119225, "total_steps": 181800, "loss": 0.0182, "lr": 1.5975857035733582e-05, "epoch": 13.116061606160615, "percentage": 65.58, "elapsed_time": "4:42:26", "remaining_time": "2:28:14", "throughput": 1484.72, "total_tokens": 25160896} {"current_steps": 119230, "total_steps": 181800, "loss": 0.0382, "lr": 1.5973618824356345e-05, "epoch": 13.116611661166116, "percentage": 65.58, "elapsed_time": "4:42:27", "remaining_time": "2:28:13", "throughput": 1484.73, "total_tokens": 25162016} {"current_steps": 119235, "total_steps": 181800, "loss": 0.1041, "lr": 1.5971380696170934e-05, "epoch": 13.117161716171617, "percentage": 65.59, "elapsed_time": "4:42:27", "remaining_time": "2:28:12", "throughput": 1484.73, "total_tokens": 25163104} {"current_steps": 119240, "total_steps": 181800, "loss": 0.0128, "lr": 1.5969142651197985e-05, "epoch": 13.117711771177119, "percentage": 65.59, "elapsed_time": "4:42:28", "remaining_time": "2:28:12", "throughput": 1484.74, "total_tokens": 25164160} {"current_steps": 119245, "total_steps": 181800, "loss": 0.1285, "lr": 1.5966904689458102e-05, "epoch": 13.118261826182618, "percentage": 65.59, "elapsed_time": "4:42:29", "remaining_time": "2:28:11", "throughput": 1484.74, "total_tokens": 25165184} {"current_steps": 119250, "total_steps": 181800, "loss": 0.142, "lr": 1.596466681097193e-05, "epoch": 13.118811881188119, "percentage": 65.59, "elapsed_time": "4:42:29", "remaining_time": "2:28:10", "throughput": 1484.74, "total_tokens": 25166272} {"current_steps": 119255, "total_steps": 181800, "loss": 0.0325, "lr": 1.5962429015760082e-05, "epoch": 13.11936193619362, "percentage": 65.6, "elapsed_time": "4:42:30", "remaining_time": "2:28:10", "throughput": 1484.74, "total_tokens": 25167360} {"current_steps": 119260, "total_steps": 181800, "loss": 0.0898, "lr": 1.5960191303843195e-05, "epoch": 13.11991199119912, "percentage": 65.6, "elapsed_time": "4:42:31", "remaining_time": "2:28:09", "throughput": 1484.74, "total_tokens": 25168384} {"current_steps": 119265, "total_steps": 181800, "loss": 0.0273, "lr": 1.5957953675241892e-05, "epoch": 13.12046204620462, "percentage": 65.6, "elapsed_time": "4:42:32", "remaining_time": "2:28:08", "throughput": 1484.75, "total_tokens": 25169472} {"current_steps": 119270, "total_steps": 181800, "loss": 0.0116, "lr": 1.595571612997678e-05, "epoch": 13.121012101210122, "percentage": 65.61, "elapsed_time": "4:42:32", "remaining_time": "2:28:07", "throughput": 1484.75, "total_tokens": 25170464} {"current_steps": 119275, "total_steps": 181800, "loss": 0.0033, "lr": 1.59534786680685e-05, "epoch": 13.12156215621562, "percentage": 65.61, "elapsed_time": "4:42:33", "remaining_time": "2:28:07", "throughput": 1484.75, "total_tokens": 25171520} {"current_steps": 119280, "total_steps": 181800, "loss": 0.0777, "lr": 1.595124128953766e-05, "epoch": 13.122112211221122, "percentage": 65.61, "elapsed_time": "4:42:34", "remaining_time": "2:28:06", "throughput": 1484.75, "total_tokens": 25172640} {"current_steps": 119285, "total_steps": 181800, "loss": 0.0075, "lr": 1.5949003994404897e-05, "epoch": 13.122662266226623, "percentage": 65.61, "elapsed_time": "4:42:34", "remaining_time": "2:28:05", "throughput": 1484.76, "total_tokens": 25173728} {"current_steps": 119290, "total_steps": 181800, "loss": 0.0078, "lr": 1.5946766782690815e-05, "epoch": 13.123212321232122, "percentage": 65.62, "elapsed_time": "4:42:35", "remaining_time": "2:28:04", "throughput": 1484.76, "total_tokens": 25174752} {"current_steps": 119295, "total_steps": 181800, "loss": 0.01, "lr": 1.5944529654416034e-05, "epoch": 13.123762376237623, "percentage": 65.62, "elapsed_time": "4:42:36", "remaining_time": "2:28:04", "throughput": 1484.76, "total_tokens": 25175776} {"current_steps": 119300, "total_steps": 181800, "loss": 0.0883, "lr": 1.594229260960119e-05, "epoch": 13.124312431243125, "percentage": 65.62, "elapsed_time": "4:42:36", "remaining_time": "2:28:03", "throughput": 1484.76, "total_tokens": 25176832} {"current_steps": 119305, "total_steps": 181800, "loss": 0.0033, "lr": 1.5940055648266878e-05, "epoch": 13.124862486248626, "percentage": 65.62, "elapsed_time": "4:42:37", "remaining_time": "2:28:02", "throughput": 1484.76, "total_tokens": 25177920} {"current_steps": 119310, "total_steps": 181800, "loss": 0.0261, "lr": 1.5937818770433733e-05, "epoch": 13.125412541254125, "percentage": 65.63, "elapsed_time": "4:42:38", "remaining_time": "2:28:02", "throughput": 1484.77, "total_tokens": 25178976} {"current_steps": 119315, "total_steps": 181800, "loss": 0.0077, "lr": 1.5935581976122366e-05, "epoch": 13.125962596259626, "percentage": 65.63, "elapsed_time": "4:42:38", "remaining_time": "2:28:01", "throughput": 1484.77, "total_tokens": 25180064} {"current_steps": 119320, "total_steps": 181800, "loss": 0.0073, "lr": 1.593334526535337e-05, "epoch": 13.126512651265127, "percentage": 65.63, "elapsed_time": "4:42:39", "remaining_time": "2:28:00", "throughput": 1484.77, "total_tokens": 25181120} {"current_steps": 119325, "total_steps": 181800, "loss": 0.0047, "lr": 1.593110863814741e-05, "epoch": 13.127062706270626, "percentage": 65.64, "elapsed_time": "4:42:40", "remaining_time": "2:27:59", "throughput": 1484.77, "total_tokens": 25182112} {"current_steps": 119330, "total_steps": 181800, "loss": 0.0062, "lr": 1.592887209452505e-05, "epoch": 13.127612761276128, "percentage": 65.64, "elapsed_time": "4:42:40", "remaining_time": "2:27:59", "throughput": 1484.77, "total_tokens": 25183200} {"current_steps": 119335, "total_steps": 181800, "loss": 0.0019, "lr": 1.5926635634506926e-05, "epoch": 13.128162816281629, "percentage": 65.64, "elapsed_time": "4:42:41", "remaining_time": "2:27:58", "throughput": 1484.77, "total_tokens": 25184224} {"current_steps": 119340, "total_steps": 181800, "loss": 0.0057, "lr": 1.5924399258113653e-05, "epoch": 13.128712871287128, "percentage": 65.64, "elapsed_time": "4:42:42", "remaining_time": "2:27:57", "throughput": 1484.77, "total_tokens": 25185248} {"current_steps": 119345, "total_steps": 181800, "loss": 0.0023, "lr": 1.5922162965365833e-05, "epoch": 13.129262926292629, "percentage": 65.65, "elapsed_time": "4:42:43", "remaining_time": "2:27:57", "throughput": 1484.77, "total_tokens": 25186272} {"current_steps": 119350, "total_steps": 181800, "loss": 0.0682, "lr": 1.591992675628408e-05, "epoch": 13.12981298129813, "percentage": 65.65, "elapsed_time": "4:42:43", "remaining_time": "2:27:56", "throughput": 1484.77, "total_tokens": 25187264} {"current_steps": 119355, "total_steps": 181800, "loss": 0.0052, "lr": 1.5917690630889015e-05, "epoch": 13.130363036303631, "percentage": 65.65, "elapsed_time": "4:42:44", "remaining_time": "2:27:55", "throughput": 1484.78, "total_tokens": 25188352} {"current_steps": 119360, "total_steps": 181800, "loss": 0.0123, "lr": 1.5915454589201222e-05, "epoch": 13.13091309130913, "percentage": 65.65, "elapsed_time": "4:42:45", "remaining_time": "2:27:54", "throughput": 1484.78, "total_tokens": 25189440} {"current_steps": 119365, "total_steps": 181800, "loss": 0.0038, "lr": 1.5913218631241337e-05, "epoch": 13.131463146314632, "percentage": 65.66, "elapsed_time": "4:42:45", "remaining_time": "2:27:54", "throughput": 1484.78, "total_tokens": 25190496} {"current_steps": 119370, "total_steps": 181800, "loss": 0.0595, "lr": 1.5910982757029945e-05, "epoch": 13.132013201320133, "percentage": 65.66, "elapsed_time": "4:42:46", "remaining_time": "2:27:53", "throughput": 1484.78, "total_tokens": 25191552} {"current_steps": 119375, "total_steps": 181800, "loss": 0.0585, "lr": 1.590874696658767e-05, "epoch": 13.132563256325632, "percentage": 65.66, "elapsed_time": "4:42:47", "remaining_time": "2:27:52", "throughput": 1484.79, "total_tokens": 25192640} {"current_steps": 119380, "total_steps": 181800, "loss": 0.0029, "lr": 1.590651125993512e-05, "epoch": 13.133113311331133, "percentage": 65.67, "elapsed_time": "4:42:47", "remaining_time": "2:27:51", "throughput": 1484.79, "total_tokens": 25193664} {"current_steps": 119385, "total_steps": 181800, "loss": 0.003, "lr": 1.5904275637092878e-05, "epoch": 13.133663366336634, "percentage": 65.67, "elapsed_time": "4:42:48", "remaining_time": "2:27:51", "throughput": 1484.79, "total_tokens": 25194688} {"current_steps": 119390, "total_steps": 181800, "loss": 0.0517, "lr": 1.590204009808157e-05, "epoch": 13.134213421342134, "percentage": 65.67, "elapsed_time": "4:42:49", "remaining_time": "2:27:50", "throughput": 1484.79, "total_tokens": 25195712} {"current_steps": 119395, "total_steps": 181800, "loss": 0.0069, "lr": 1.5899804642921786e-05, "epoch": 13.134763476347635, "percentage": 65.67, "elapsed_time": "4:42:49", "remaining_time": "2:27:49", "throughput": 1484.79, "total_tokens": 25196832} {"current_steps": 119400, "total_steps": 181800, "loss": 0.0051, "lr": 1.5897569271634146e-05, "epoch": 13.135313531353136, "percentage": 65.68, "elapsed_time": "4:42:50", "remaining_time": "2:27:49", "throughput": 1484.8, "total_tokens": 25197952} {"current_steps": 119405, "total_steps": 181800, "loss": 0.0165, "lr": 1.5895333984239237e-05, "epoch": 13.135863586358635, "percentage": 65.68, "elapsed_time": "4:42:51", "remaining_time": "2:27:48", "throughput": 1484.8, "total_tokens": 25198912} {"current_steps": 119410, "total_steps": 181800, "loss": 0.0298, "lr": 1.5893098780757664e-05, "epoch": 13.136413641364136, "percentage": 65.68, "elapsed_time": "4:42:51", "remaining_time": "2:27:47", "throughput": 1484.8, "total_tokens": 25200032} {"current_steps": 119415, "total_steps": 181800, "loss": 0.099, "lr": 1.5890863661210035e-05, "epoch": 13.136963696369637, "percentage": 65.68, "elapsed_time": "4:42:52", "remaining_time": "2:27:46", "throughput": 1484.8, "total_tokens": 25201056} {"current_steps": 119420, "total_steps": 181800, "loss": 0.0052, "lr": 1.588862862561694e-05, "epoch": 13.137513751375138, "percentage": 65.69, "elapsed_time": "4:42:53", "remaining_time": "2:27:46", "throughput": 1484.8, "total_tokens": 25202112} {"current_steps": 119425, "total_steps": 181800, "loss": 0.0032, "lr": 1.5886393673998985e-05, "epoch": 13.138063806380638, "percentage": 65.69, "elapsed_time": "4:42:54", "remaining_time": "2:27:45", "throughput": 1484.81, "total_tokens": 25203200} {"current_steps": 119430, "total_steps": 181800, "loss": 0.0042, "lr": 1.588415880637677e-05, "epoch": 13.138613861386139, "percentage": 65.69, "elapsed_time": "4:42:54", "remaining_time": "2:27:44", "throughput": 1484.81, "total_tokens": 25204224} {"current_steps": 119435, "total_steps": 181800, "loss": 0.0036, "lr": 1.588192402277088e-05, "epoch": 13.13916391639164, "percentage": 65.7, "elapsed_time": "4:42:55", "remaining_time": "2:27:44", "throughput": 1484.81, "total_tokens": 25205280} {"current_steps": 119440, "total_steps": 181800, "loss": 0.0083, "lr": 1.587968932320193e-05, "epoch": 13.13971397139714, "percentage": 65.7, "elapsed_time": "4:42:56", "remaining_time": "2:27:43", "throughput": 1484.81, "total_tokens": 25206336} {"current_steps": 119445, "total_steps": 181800, "loss": 0.0081, "lr": 1.5877454707690497e-05, "epoch": 13.14026402640264, "percentage": 65.7, "elapsed_time": "4:42:56", "remaining_time": "2:27:42", "throughput": 1484.81, "total_tokens": 25207360} {"current_steps": 119450, "total_steps": 181800, "loss": 0.0544, "lr": 1.5875220176257193e-05, "epoch": 13.140814081408141, "percentage": 65.7, "elapsed_time": "4:42:57", "remaining_time": "2:27:41", "throughput": 1484.81, "total_tokens": 25208352} {"current_steps": 119455, "total_steps": 181800, "loss": 0.0812, "lr": 1.5872985728922613e-05, "epoch": 13.14136413641364, "percentage": 65.71, "elapsed_time": "4:42:58", "remaining_time": "2:27:41", "throughput": 1484.8, "total_tokens": 25209312} {"current_steps": 119460, "total_steps": 181800, "loss": 0.0034, "lr": 1.5870751365707332e-05, "epoch": 13.141914191419142, "percentage": 65.71, "elapsed_time": "4:42:58", "remaining_time": "2:27:40", "throughput": 1484.8, "total_tokens": 25210336} {"current_steps": 119465, "total_steps": 181800, "loss": 0.0068, "lr": 1.586851708663196e-05, "epoch": 13.142464246424643, "percentage": 65.71, "elapsed_time": "4:42:59", "remaining_time": "2:27:39", "throughput": 1484.81, "total_tokens": 25211488} {"current_steps": 119470, "total_steps": 181800, "loss": 0.0033, "lr": 1.586628289171708e-05, "epoch": 13.143014301430142, "percentage": 65.72, "elapsed_time": "4:43:00", "remaining_time": "2:27:38", "throughput": 1484.81, "total_tokens": 25212576} {"current_steps": 119475, "total_steps": 181800, "loss": 0.0138, "lr": 1.5864048780983297e-05, "epoch": 13.143564356435643, "percentage": 65.72, "elapsed_time": "4:43:00", "remaining_time": "2:27:38", "throughput": 1484.82, "total_tokens": 25213664} {"current_steps": 119480, "total_steps": 181800, "loss": 0.0019, "lr": 1.586181475445119e-05, "epoch": 13.144114411441144, "percentage": 65.72, "elapsed_time": "4:43:01", "remaining_time": "2:27:37", "throughput": 1484.82, "total_tokens": 25214720} {"current_steps": 119485, "total_steps": 181800, "loss": 0.002, "lr": 1.5859580812141344e-05, "epoch": 13.144664466446645, "percentage": 65.72, "elapsed_time": "4:43:02", "remaining_time": "2:27:36", "throughput": 1484.82, "total_tokens": 25215744} {"current_steps": 119490, "total_steps": 181800, "loss": 0.059, "lr": 1.5857346954074365e-05, "epoch": 13.145214521452145, "percentage": 65.73, "elapsed_time": "4:43:03", "remaining_time": "2:27:36", "throughput": 1484.82, "total_tokens": 25216800} {"current_steps": 119495, "total_steps": 181800, "loss": 0.0016, "lr": 1.585511318027082e-05, "epoch": 13.145764576457646, "percentage": 65.73, "elapsed_time": "4:43:03", "remaining_time": "2:27:35", "throughput": 1484.82, "total_tokens": 25217824} {"current_steps": 119500, "total_steps": 181800, "loss": 0.0469, "lr": 1.585287949075132e-05, "epoch": 13.146314631463147, "percentage": 65.73, "elapsed_time": "4:43:04", "remaining_time": "2:27:34", "throughput": 1484.83, "total_tokens": 25218912} {"current_steps": 119505, "total_steps": 181800, "loss": 0.0722, "lr": 1.5850645885536436e-05, "epoch": 13.146864686468646, "percentage": 65.73, "elapsed_time": "4:43:05", "remaining_time": "2:27:33", "throughput": 1484.83, "total_tokens": 25220000} {"current_steps": 119510, "total_steps": 181800, "loss": 0.0149, "lr": 1.5848412364646757e-05, "epoch": 13.147414741474147, "percentage": 65.74, "elapsed_time": "4:43:05", "remaining_time": "2:27:33", "throughput": 1484.83, "total_tokens": 25220992} {"current_steps": 119515, "total_steps": 181800, "loss": 0.0202, "lr": 1.5846178928102878e-05, "epoch": 13.147964796479648, "percentage": 65.74, "elapsed_time": "4:43:06", "remaining_time": "2:27:32", "throughput": 1484.83, "total_tokens": 25222080} {"current_steps": 119520, "total_steps": 181800, "loss": 0.0215, "lr": 1.584394557592537e-05, "epoch": 13.148514851485148, "percentage": 65.74, "elapsed_time": "4:43:07", "remaining_time": "2:27:31", "throughput": 1484.84, "total_tokens": 25223168} {"current_steps": 119525, "total_steps": 181800, "loss": 0.0819, "lr": 1.584171230813482e-05, "epoch": 13.149064906490649, "percentage": 65.75, "elapsed_time": "4:43:07", "remaining_time": "2:27:31", "throughput": 1484.84, "total_tokens": 25224288} {"current_steps": 119530, "total_steps": 181800, "loss": 0.0012, "lr": 1.5839479124751818e-05, "epoch": 13.14961496149615, "percentage": 65.75, "elapsed_time": "4:43:08", "remaining_time": "2:27:30", "throughput": 1484.84, "total_tokens": 25225312} {"current_steps": 119535, "total_steps": 181800, "loss": 0.0034, "lr": 1.5837246025796934e-05, "epoch": 13.150165016501651, "percentage": 65.75, "elapsed_time": "4:43:09", "remaining_time": "2:27:29", "throughput": 1484.84, "total_tokens": 25226304} {"current_steps": 119540, "total_steps": 181800, "loss": 0.0361, "lr": 1.5835013011290762e-05, "epoch": 13.15071507150715, "percentage": 65.75, "elapsed_time": "4:43:09", "remaining_time": "2:27:28", "throughput": 1484.84, "total_tokens": 25227328} {"current_steps": 119545, "total_steps": 181800, "loss": 0.0159, "lr": 1.5832780081253882e-05, "epoch": 13.151265126512651, "percentage": 65.76, "elapsed_time": "4:43:10", "remaining_time": "2:27:28", "throughput": 1484.84, "total_tokens": 25228352} {"current_steps": 119550, "total_steps": 181800, "loss": 0.004, "lr": 1.583054723570686e-05, "epoch": 13.151815181518153, "percentage": 65.76, "elapsed_time": "4:43:11", "remaining_time": "2:27:27", "throughput": 1484.84, "total_tokens": 25229472} {"current_steps": 119555, "total_steps": 181800, "loss": 0.0358, "lr": 1.5828314474670285e-05, "epoch": 13.152365236523652, "percentage": 65.76, "elapsed_time": "4:43:12", "remaining_time": "2:27:26", "throughput": 1484.85, "total_tokens": 25230528} {"current_steps": 119560, "total_steps": 181800, "loss": 0.0061, "lr": 1.5826081798164732e-05, "epoch": 13.152915291529153, "percentage": 65.76, "elapsed_time": "4:43:12", "remaining_time": "2:27:25", "throughput": 1484.85, "total_tokens": 25231680} {"current_steps": 119565, "total_steps": 181800, "loss": 0.0054, "lr": 1.5823849206210788e-05, "epoch": 13.153465346534654, "percentage": 65.77, "elapsed_time": "4:43:13", "remaining_time": "2:27:25", "throughput": 1484.86, "total_tokens": 25232736} {"current_steps": 119570, "total_steps": 181800, "loss": 0.0389, "lr": 1.5821616698829027e-05, "epoch": 13.154015401540153, "percentage": 65.77, "elapsed_time": "4:43:14", "remaining_time": "2:27:24", "throughput": 1484.86, "total_tokens": 25233856} {"current_steps": 119575, "total_steps": 181800, "loss": 0.0173, "lr": 1.581938427604001e-05, "epoch": 13.154565456545654, "percentage": 65.77, "elapsed_time": "4:43:14", "remaining_time": "2:27:23", "throughput": 1484.86, "total_tokens": 25234912} {"current_steps": 119580, "total_steps": 181800, "loss": 0.0241, "lr": 1.5817151937864326e-05, "epoch": 13.155115511551156, "percentage": 65.78, "elapsed_time": "4:43:15", "remaining_time": "2:27:23", "throughput": 1484.87, "total_tokens": 25235968} {"current_steps": 119585, "total_steps": 181800, "loss": 0.0027, "lr": 1.5814919684322545e-05, "epoch": 13.155665566556655, "percentage": 65.78, "elapsed_time": "4:43:16", "remaining_time": "2:27:22", "throughput": 1484.87, "total_tokens": 25236992} {"current_steps": 119590, "total_steps": 181800, "loss": 0.0046, "lr": 1.581268751543525e-05, "epoch": 13.156215621562156, "percentage": 65.78, "elapsed_time": "4:43:16", "remaining_time": "2:27:21", "throughput": 1484.87, "total_tokens": 25238144} {"current_steps": 119595, "total_steps": 181800, "loss": 0.005, "lr": 1.5810455431222997e-05, "epoch": 13.156765676567657, "percentage": 65.78, "elapsed_time": "4:43:17", "remaining_time": "2:27:20", "throughput": 1484.87, "total_tokens": 25239200} {"current_steps": 119600, "total_steps": 181800, "loss": 0.0036, "lr": 1.580822343170637e-05, "epoch": 13.157315731573158, "percentage": 65.79, "elapsed_time": "4:43:18", "remaining_time": "2:27:20", "throughput": 1484.88, "total_tokens": 25240256} {"current_steps": 119605, "total_steps": 181800, "loss": 0.0752, "lr": 1.5805991516905938e-05, "epoch": 13.157865786578657, "percentage": 65.79, "elapsed_time": "4:43:18", "remaining_time": "2:27:19", "throughput": 1484.88, "total_tokens": 25241280} {"current_steps": 119610, "total_steps": 181800, "loss": 0.0178, "lr": 1.5803759686842267e-05, "epoch": 13.158415841584159, "percentage": 65.79, "elapsed_time": "4:43:19", "remaining_time": "2:27:18", "throughput": 1484.88, "total_tokens": 25242368} {"current_steps": 119615, "total_steps": 181800, "loss": 0.009, "lr": 1.580152794153593e-05, "epoch": 13.15896589658966, "percentage": 65.79, "elapsed_time": "4:43:20", "remaining_time": "2:27:18", "throughput": 1484.88, "total_tokens": 25243424} {"current_steps": 119620, "total_steps": 181800, "loss": 0.0082, "lr": 1.5799296281007502e-05, "epoch": 13.159515951595159, "percentage": 65.8, "elapsed_time": "4:43:20", "remaining_time": "2:27:17", "throughput": 1484.88, "total_tokens": 25244480} {"current_steps": 119625, "total_steps": 181800, "loss": 0.0254, "lr": 1.5797064705277538e-05, "epoch": 13.16006600660066, "percentage": 65.8, "elapsed_time": "4:43:21", "remaining_time": "2:27:16", "throughput": 1484.88, "total_tokens": 25245504} {"current_steps": 119630, "total_steps": 181800, "loss": 0.0187, "lr": 1.579483321436662e-05, "epoch": 13.160616061606161, "percentage": 65.8, "elapsed_time": "4:43:22", "remaining_time": "2:27:15", "throughput": 1484.88, "total_tokens": 25246528} {"current_steps": 119635, "total_steps": 181800, "loss": 0.0057, "lr": 1.57926018082953e-05, "epoch": 13.16116611661166, "percentage": 65.81, "elapsed_time": "4:43:23", "remaining_time": "2:27:15", "throughput": 1484.89, "total_tokens": 25247648} {"current_steps": 119640, "total_steps": 181800, "loss": 0.0584, "lr": 1.5790370487084157e-05, "epoch": 13.161716171617162, "percentage": 65.81, "elapsed_time": "4:43:23", "remaining_time": "2:27:14", "throughput": 1484.89, "total_tokens": 25248672} {"current_steps": 119645, "total_steps": 181800, "loss": 0.0044, "lr": 1.578813925075375e-05, "epoch": 13.162266226622663, "percentage": 65.81, "elapsed_time": "4:43:24", "remaining_time": "2:27:13", "throughput": 1484.89, "total_tokens": 25249728} {"current_steps": 119650, "total_steps": 181800, "loss": 0.045, "lr": 1.5785908099324638e-05, "epoch": 13.162816281628162, "percentage": 65.81, "elapsed_time": "4:43:25", "remaining_time": "2:27:12", "throughput": 1484.89, "total_tokens": 25250720} {"current_steps": 119655, "total_steps": 181800, "loss": 0.0038, "lr": 1.578367703281739e-05, "epoch": 13.163366336633663, "percentage": 65.82, "elapsed_time": "4:43:25", "remaining_time": "2:27:12", "throughput": 1484.89, "total_tokens": 25251744} {"current_steps": 119660, "total_steps": 181800, "loss": 0.0054, "lr": 1.5781446051252568e-05, "epoch": 13.163916391639164, "percentage": 65.82, "elapsed_time": "4:43:26", "remaining_time": "2:27:11", "throughput": 1484.89, "total_tokens": 25252800} {"current_steps": 119665, "total_steps": 181800, "loss": 0.0037, "lr": 1.577921515465074e-05, "epoch": 13.164466446644665, "percentage": 65.82, "elapsed_time": "4:43:27", "remaining_time": "2:27:10", "throughput": 1484.89, "total_tokens": 25253856} {"current_steps": 119670, "total_steps": 181800, "loss": 0.0147, "lr": 1.5776984343032465e-05, "epoch": 13.165016501650165, "percentage": 65.83, "elapsed_time": "4:43:27", "remaining_time": "2:27:10", "throughput": 1484.89, "total_tokens": 25254880} {"current_steps": 119675, "total_steps": 181800, "loss": 0.0677, "lr": 1.5774753616418285e-05, "epoch": 13.165566556655666, "percentage": 65.83, "elapsed_time": "4:43:28", "remaining_time": "2:27:09", "throughput": 1484.89, "total_tokens": 25255904} {"current_steps": 119680, "total_steps": 181800, "loss": 0.0081, "lr": 1.5772522974828784e-05, "epoch": 13.166116611661167, "percentage": 65.83, "elapsed_time": "4:43:29", "remaining_time": "2:27:08", "throughput": 1484.89, "total_tokens": 25256928} {"current_steps": 119685, "total_steps": 181800, "loss": 0.1271, "lr": 1.5770292418284505e-05, "epoch": 13.166666666666666, "percentage": 65.83, "elapsed_time": "4:43:29", "remaining_time": "2:27:07", "throughput": 1484.9, "total_tokens": 25258016} {"current_steps": 119690, "total_steps": 181800, "loss": 0.0099, "lr": 1.576806194680602e-05, "epoch": 13.167216721672167, "percentage": 65.84, "elapsed_time": "4:43:30", "remaining_time": "2:27:07", "throughput": 1484.9, "total_tokens": 25259136} {"current_steps": 119695, "total_steps": 181800, "loss": 0.0044, "lr": 1.5765831560413873e-05, "epoch": 13.167766776677668, "percentage": 65.84, "elapsed_time": "4:43:31", "remaining_time": "2:27:06", "throughput": 1484.9, "total_tokens": 25260160} {"current_steps": 119700, "total_steps": 181800, "loss": 0.1117, "lr": 1.5763601259128624e-05, "epoch": 13.168316831683168, "percentage": 65.84, "elapsed_time": "4:43:32", "remaining_time": "2:27:05", "throughput": 1484.9, "total_tokens": 25261248} {"current_steps": 119705, "total_steps": 181800, "loss": 0.1426, "lr": 1.576137104297084e-05, "epoch": 13.168866886688669, "percentage": 65.84, "elapsed_time": "4:43:32", "remaining_time": "2:27:05", "throughput": 1484.9, "total_tokens": 25262240} {"current_steps": 119710, "total_steps": 181800, "loss": 0.0006, "lr": 1.575914091196106e-05, "epoch": 13.16941694169417, "percentage": 65.85, "elapsed_time": "4:43:33", "remaining_time": "2:27:04", "throughput": 1484.89, "total_tokens": 25263328} {"current_steps": 119715, "total_steps": 181800, "loss": 0.0337, "lr": 1.575691086611984e-05, "epoch": 13.16996699669967, "percentage": 65.85, "elapsed_time": "4:43:34", "remaining_time": "2:27:03", "throughput": 1484.89, "total_tokens": 25264352} {"current_steps": 119720, "total_steps": 181800, "loss": 0.0629, "lr": 1.5754680905467743e-05, "epoch": 13.17051705170517, "percentage": 65.85, "elapsed_time": "4:43:35", "remaining_time": "2:27:03", "throughput": 1484.88, "total_tokens": 25265312} {"current_steps": 119725, "total_steps": 181800, "loss": 0.0261, "lr": 1.575245103002531e-05, "epoch": 13.171067106710671, "percentage": 65.86, "elapsed_time": "4:43:35", "remaining_time": "2:27:02", "throughput": 1484.88, "total_tokens": 25266336} {"current_steps": 119730, "total_steps": 181800, "loss": 0.1622, "lr": 1.57502212398131e-05, "epoch": 13.171617161716172, "percentage": 65.86, "elapsed_time": "4:43:36", "remaining_time": "2:27:01", "throughput": 1484.88, "total_tokens": 25267360} {"current_steps": 119735, "total_steps": 181800, "loss": 0.0044, "lr": 1.5747991534851668e-05, "epoch": 13.172167216721672, "percentage": 65.86, "elapsed_time": "4:43:37", "remaining_time": "2:27:00", "throughput": 1484.89, "total_tokens": 25268416} {"current_steps": 119740, "total_steps": 181800, "loss": 0.0022, "lr": 1.5745761915161546e-05, "epoch": 13.172717271727173, "percentage": 65.86, "elapsed_time": "4:43:37", "remaining_time": "2:27:00", "throughput": 1484.88, "total_tokens": 25269440} {"current_steps": 119745, "total_steps": 181800, "loss": 0.0992, "lr": 1.574353238076331e-05, "epoch": 13.173267326732674, "percentage": 65.87, "elapsed_time": "4:43:38", "remaining_time": "2:26:59", "throughput": 1484.89, "total_tokens": 25270496} {"current_steps": 119750, "total_steps": 181800, "loss": 0.1163, "lr": 1.5741302931677485e-05, "epoch": 13.173817381738173, "percentage": 65.87, "elapsed_time": "4:43:39", "remaining_time": "2:26:58", "throughput": 1484.89, "total_tokens": 25271520} {"current_steps": 119755, "total_steps": 181800, "loss": 0.0011, "lr": 1.5739073567924633e-05, "epoch": 13.174367436743674, "percentage": 65.87, "elapsed_time": "4:43:39", "remaining_time": "2:26:57", "throughput": 1484.89, "total_tokens": 25272544} {"current_steps": 119760, "total_steps": 181800, "loss": 0.0038, "lr": 1.57368442895253e-05, "epoch": 13.174917491749175, "percentage": 65.87, "elapsed_time": "4:43:40", "remaining_time": "2:26:57", "throughput": 1484.89, "total_tokens": 25273664} {"current_steps": 119765, "total_steps": 181800, "loss": 0.0466, "lr": 1.5734615096500015e-05, "epoch": 13.175467546754675, "percentage": 65.88, "elapsed_time": "4:43:41", "remaining_time": "2:26:56", "throughput": 1484.9, "total_tokens": 25274784} {"current_steps": 119770, "total_steps": 181800, "loss": 0.0099, "lr": 1.5732385988869347e-05, "epoch": 13.176017601760176, "percentage": 65.88, "elapsed_time": "4:43:41", "remaining_time": "2:26:55", "throughput": 1484.9, "total_tokens": 25275840} {"current_steps": 119775, "total_steps": 181800, "loss": 0.0037, "lr": 1.5730156966653824e-05, "epoch": 13.176567656765677, "percentage": 65.88, "elapsed_time": "4:43:42", "remaining_time": "2:26:55", "throughput": 1484.9, "total_tokens": 25276928} {"current_steps": 119780, "total_steps": 181800, "loss": 0.0766, "lr": 1.5727928029874007e-05, "epoch": 13.177117711771178, "percentage": 65.89, "elapsed_time": "4:43:43", "remaining_time": "2:26:54", "throughput": 1484.9, "total_tokens": 25277920} {"current_steps": 119785, "total_steps": 181800, "loss": 0.2713, "lr": 1.572569917855042e-05, "epoch": 13.177667766776677, "percentage": 65.89, "elapsed_time": "4:43:43", "remaining_time": "2:26:53", "throughput": 1484.9, "total_tokens": 25278976} {"current_steps": 119790, "total_steps": 181800, "loss": 0.0047, "lr": 1.572347041270361e-05, "epoch": 13.178217821782178, "percentage": 65.89, "elapsed_time": "4:43:44", "remaining_time": "2:26:52", "throughput": 1484.9, "total_tokens": 25280032} {"current_steps": 119795, "total_steps": 181800, "loss": 0.0078, "lr": 1.5721241732354132e-05, "epoch": 13.17876787678768, "percentage": 65.89, "elapsed_time": "4:43:45", "remaining_time": "2:26:52", "throughput": 1484.9, "total_tokens": 25281056} {"current_steps": 119800, "total_steps": 181800, "loss": 0.0036, "lr": 1.5719013137522503e-05, "epoch": 13.179317931793179, "percentage": 65.9, "elapsed_time": "4:43:46", "remaining_time": "2:26:51", "throughput": 1484.9, "total_tokens": 25282048} {"current_steps": 119805, "total_steps": 181800, "loss": 0.0839, "lr": 1.571678462822929e-05, "epoch": 13.17986798679868, "percentage": 65.9, "elapsed_time": "4:43:46", "remaining_time": "2:26:50", "throughput": 1484.9, "total_tokens": 25283072} {"current_steps": 119810, "total_steps": 181800, "loss": 0.0233, "lr": 1.5714556204495014e-05, "epoch": 13.180418041804181, "percentage": 65.9, "elapsed_time": "4:43:47", "remaining_time": "2:26:50", "throughput": 1484.9, "total_tokens": 25284096} {"current_steps": 119815, "total_steps": 181800, "loss": 0.0068, "lr": 1.5712327866340212e-05, "epoch": 13.18096809680968, "percentage": 65.9, "elapsed_time": "4:43:48", "remaining_time": "2:26:49", "throughput": 1484.9, "total_tokens": 25285120} {"current_steps": 119820, "total_steps": 181800, "loss": 0.0081, "lr": 1.571009961378544e-05, "epoch": 13.181518151815181, "percentage": 65.91, "elapsed_time": "4:43:48", "remaining_time": "2:26:48", "throughput": 1484.91, "total_tokens": 25286208} {"current_steps": 119825, "total_steps": 181800, "loss": 0.0261, "lr": 1.5707871446851208e-05, "epoch": 13.182068206820682, "percentage": 65.91, "elapsed_time": "4:43:49", "remaining_time": "2:26:47", "throughput": 1484.9, "total_tokens": 25287200} {"current_steps": 119830, "total_steps": 181800, "loss": 0.0012, "lr": 1.5705643365558077e-05, "epoch": 13.182618261826182, "percentage": 65.91, "elapsed_time": "4:43:50", "remaining_time": "2:26:47", "throughput": 1484.91, "total_tokens": 25288256} {"current_steps": 119835, "total_steps": 181800, "loss": 0.0058, "lr": 1.5703415369926573e-05, "epoch": 13.183168316831683, "percentage": 65.92, "elapsed_time": "4:43:50", "remaining_time": "2:26:46", "throughput": 1484.91, "total_tokens": 25289280} {"current_steps": 119840, "total_steps": 181800, "loss": 0.0035, "lr": 1.5701187459977216e-05, "epoch": 13.183718371837184, "percentage": 65.92, "elapsed_time": "4:43:51", "remaining_time": "2:26:45", "throughput": 1484.91, "total_tokens": 25290336} {"current_steps": 119845, "total_steps": 181800, "loss": 0.0869, "lr": 1.5698959635730558e-05, "epoch": 13.184268426842685, "percentage": 65.92, "elapsed_time": "4:43:52", "remaining_time": "2:26:44", "throughput": 1484.9, "total_tokens": 25291296} {"current_steps": 119850, "total_steps": 181800, "loss": 0.0677, "lr": 1.5696731897207123e-05, "epoch": 13.184818481848184, "percentage": 65.92, "elapsed_time": "4:43:52", "remaining_time": "2:26:44", "throughput": 1484.9, "total_tokens": 25292288} {"current_steps": 119855, "total_steps": 181800, "loss": 0.0037, "lr": 1.5694504244427455e-05, "epoch": 13.185368536853685, "percentage": 65.93, "elapsed_time": "4:43:53", "remaining_time": "2:26:43", "throughput": 1484.91, "total_tokens": 25293376} {"current_steps": 119860, "total_steps": 181800, "loss": 0.0397, "lr": 1.5692276677412072e-05, "epoch": 13.185918591859187, "percentage": 65.93, "elapsed_time": "4:43:54", "remaining_time": "2:26:42", "throughput": 1484.9, "total_tokens": 25294368} {"current_steps": 119865, "total_steps": 181800, "loss": 0.1648, "lr": 1.56900491961815e-05, "epoch": 13.186468646864686, "percentage": 65.93, "elapsed_time": "4:43:55", "remaining_time": "2:26:42", "throughput": 1484.9, "total_tokens": 25295360} {"current_steps": 119870, "total_steps": 181800, "loss": 0.0029, "lr": 1.5687821800756285e-05, "epoch": 13.187018701870187, "percentage": 65.94, "elapsed_time": "4:43:55", "remaining_time": "2:26:41", "throughput": 1484.9, "total_tokens": 25296416} {"current_steps": 119875, "total_steps": 181800, "loss": 0.0815, "lr": 1.5685594491156945e-05, "epoch": 13.187568756875688, "percentage": 65.94, "elapsed_time": "4:43:56", "remaining_time": "2:26:40", "throughput": 1484.91, "total_tokens": 25297504} {"current_steps": 119880, "total_steps": 181800, "loss": 0.0084, "lr": 1.568336726740402e-05, "epoch": 13.188118811881187, "percentage": 65.94, "elapsed_time": "4:43:57", "remaining_time": "2:26:39", "throughput": 1484.91, "total_tokens": 25298528} {"current_steps": 119885, "total_steps": 181800, "loss": 0.0594, "lr": 1.5681140129518023e-05, "epoch": 13.188668866886688, "percentage": 65.94, "elapsed_time": "4:43:57", "remaining_time": "2:26:39", "throughput": 1484.91, "total_tokens": 25299552} {"current_steps": 119890, "total_steps": 181800, "loss": 0.1366, "lr": 1.5678913077519482e-05, "epoch": 13.18921892189219, "percentage": 65.95, "elapsed_time": "4:43:58", "remaining_time": "2:26:38", "throughput": 1484.91, "total_tokens": 25300640} {"current_steps": 119895, "total_steps": 181800, "loss": 0.0482, "lr": 1.5676686111428933e-05, "epoch": 13.189768976897689, "percentage": 65.95, "elapsed_time": "4:43:59", "remaining_time": "2:26:37", "throughput": 1484.91, "total_tokens": 25301664} {"current_steps": 119900, "total_steps": 181800, "loss": 0.0787, "lr": 1.567445923126689e-05, "epoch": 13.19031903190319, "percentage": 65.95, "elapsed_time": "4:43:59", "remaining_time": "2:26:37", "throughput": 1484.92, "total_tokens": 25302784} {"current_steps": 119905, "total_steps": 181800, "loss": 0.0024, "lr": 1.567223243705388e-05, "epoch": 13.190869086908691, "percentage": 65.95, "elapsed_time": "4:44:00", "remaining_time": "2:26:36", "throughput": 1484.92, "total_tokens": 25303872} {"current_steps": 119910, "total_steps": 181800, "loss": 0.0128, "lr": 1.5670005728810432e-05, "epoch": 13.191419141914192, "percentage": 65.96, "elapsed_time": "4:44:01", "remaining_time": "2:26:35", "throughput": 1484.92, "total_tokens": 25304928} {"current_steps": 119915, "total_steps": 181800, "loss": 0.0058, "lr": 1.5667779106557055e-05, "epoch": 13.191969196919691, "percentage": 65.96, "elapsed_time": "4:44:01", "remaining_time": "2:26:34", "throughput": 1484.92, "total_tokens": 25305952} {"current_steps": 119920, "total_steps": 181800, "loss": 0.008, "lr": 1.566555257031429e-05, "epoch": 13.192519251925193, "percentage": 65.96, "elapsed_time": "4:44:02", "remaining_time": "2:26:34", "throughput": 1484.93, "total_tokens": 25307104} {"current_steps": 119925, "total_steps": 181800, "loss": 0.0363, "lr": 1.566332612010265e-05, "epoch": 13.193069306930694, "percentage": 65.97, "elapsed_time": "4:44:03", "remaining_time": "2:26:33", "throughput": 1484.93, "total_tokens": 25308192} {"current_steps": 119930, "total_steps": 181800, "loss": 0.0045, "lr": 1.566109975594264e-05, "epoch": 13.193619361936193, "percentage": 65.97, "elapsed_time": "4:44:04", "remaining_time": "2:26:32", "throughput": 1484.94, "total_tokens": 25309312} {"current_steps": 119935, "total_steps": 181800, "loss": 0.0084, "lr": 1.565887347785481e-05, "epoch": 13.194169416941694, "percentage": 65.97, "elapsed_time": "4:44:04", "remaining_time": "2:26:32", "throughput": 1484.94, "total_tokens": 25310400} {"current_steps": 119940, "total_steps": 181800, "loss": 0.0018, "lr": 1.5656647285859644e-05, "epoch": 13.194719471947195, "percentage": 65.97, "elapsed_time": "4:44:05", "remaining_time": "2:26:31", "throughput": 1484.94, "total_tokens": 25311392} {"current_steps": 119945, "total_steps": 181800, "loss": 0.0369, "lr": 1.5654421179977684e-05, "epoch": 13.195269526952695, "percentage": 65.98, "elapsed_time": "4:44:06", "remaining_time": "2:26:30", "throughput": 1484.94, "total_tokens": 25312448} {"current_steps": 119950, "total_steps": 181800, "loss": 0.0723, "lr": 1.5652195160229443e-05, "epoch": 13.195819581958196, "percentage": 65.98, "elapsed_time": "4:44:06", "remaining_time": "2:26:29", "throughput": 1484.95, "total_tokens": 25313568} {"current_steps": 119955, "total_steps": 181800, "loss": 0.0309, "lr": 1.5649969226635425e-05, "epoch": 13.196369636963697, "percentage": 65.98, "elapsed_time": "4:44:07", "remaining_time": "2:26:29", "throughput": 1484.94, "total_tokens": 25314528} {"current_steps": 119960, "total_steps": 181800, "loss": 0.2125, "lr": 1.5647743379216163e-05, "epoch": 13.196919691969198, "percentage": 65.98, "elapsed_time": "4:44:08", "remaining_time": "2:26:28", "throughput": 1484.94, "total_tokens": 25315552} {"current_steps": 119965, "total_steps": 181800, "loss": 0.0566, "lr": 1.564551761799215e-05, "epoch": 13.197469746974697, "percentage": 65.99, "elapsed_time": "4:44:08", "remaining_time": "2:26:27", "throughput": 1484.95, "total_tokens": 25316608} {"current_steps": 119970, "total_steps": 181800, "loss": 0.0523, "lr": 1.564329194298393e-05, "epoch": 13.198019801980198, "percentage": 65.99, "elapsed_time": "4:44:09", "remaining_time": "2:26:26", "throughput": 1484.95, "total_tokens": 25317696} {"current_steps": 119975, "total_steps": 181800, "loss": 0.0087, "lr": 1.5641066354211986e-05, "epoch": 13.1985698569857, "percentage": 65.99, "elapsed_time": "4:44:10", "remaining_time": "2:26:26", "throughput": 1484.95, "total_tokens": 25318752} {"current_steps": 119980, "total_steps": 181800, "loss": 0.0065, "lr": 1.5638840851696846e-05, "epoch": 13.199119911991199, "percentage": 66.0, "elapsed_time": "4:44:10", "remaining_time": "2:26:25", "throughput": 1484.96, "total_tokens": 25319872} {"current_steps": 119985, "total_steps": 181800, "loss": 0.0103, "lr": 1.5636615435459018e-05, "epoch": 13.1996699669967, "percentage": 66.0, "elapsed_time": "4:44:11", "remaining_time": "2:26:24", "throughput": 1484.96, "total_tokens": 25320928} {"current_steps": 119990, "total_steps": 181800, "loss": 0.1086, "lr": 1.5634390105519007e-05, "epoch": 13.2002200220022, "percentage": 66.0, "elapsed_time": "4:44:12", "remaining_time": "2:26:24", "throughput": 1484.95, "total_tokens": 25321888} {"current_steps": 119995, "total_steps": 181800, "loss": 0.0828, "lr": 1.5632164861897336e-05, "epoch": 13.2007700770077, "percentage": 66.0, "elapsed_time": "4:44:12", "remaining_time": "2:26:23", "throughput": 1484.96, "total_tokens": 25322944} {"current_steps": 120000, "total_steps": 181800, "loss": 0.0134, "lr": 1.5629939704614506e-05, "epoch": 13.201320132013201, "percentage": 66.01, "elapsed_time": "4:44:13", "remaining_time": "2:26:22", "throughput": 1484.96, "total_tokens": 25324000} {"current_steps": 120005, "total_steps": 181800, "loss": 0.0067, "lr": 1.562771463369102e-05, "epoch": 13.201870187018702, "percentage": 66.01, "elapsed_time": "4:44:14", "remaining_time": "2:26:21", "throughput": 1484.96, "total_tokens": 25325024} {"current_steps": 120010, "total_steps": 181800, "loss": 0.0025, "lr": 1.56254896491474e-05, "epoch": 13.202420242024202, "percentage": 66.01, "elapsed_time": "4:44:15", "remaining_time": "2:26:21", "throughput": 1484.96, "total_tokens": 25326048} {"current_steps": 120015, "total_steps": 181800, "loss": 0.0651, "lr": 1.5623264751004136e-05, "epoch": 13.202970297029703, "percentage": 66.01, "elapsed_time": "4:44:15", "remaining_time": "2:26:20", "throughput": 1484.96, "total_tokens": 25327136} {"current_steps": 120020, "total_steps": 181800, "loss": 0.0033, "lr": 1.562103993928174e-05, "epoch": 13.203520352035204, "percentage": 66.02, "elapsed_time": "4:44:16", "remaining_time": "2:26:19", "throughput": 1484.96, "total_tokens": 25328128} {"current_steps": 120025, "total_steps": 181800, "loss": 0.0075, "lr": 1.5618815214000727e-05, "epoch": 13.204070407040705, "percentage": 66.02, "elapsed_time": "4:44:17", "remaining_time": "2:26:19", "throughput": 1484.96, "total_tokens": 25329184} {"current_steps": 120030, "total_steps": 181800, "loss": 0.0867, "lr": 1.5616590575181583e-05, "epoch": 13.204620462046204, "percentage": 66.02, "elapsed_time": "4:44:17", "remaining_time": "2:26:18", "throughput": 1484.96, "total_tokens": 25330240} {"current_steps": 120035, "total_steps": 181800, "loss": 0.0016, "lr": 1.561436602284483e-05, "epoch": 13.205170517051705, "percentage": 66.03, "elapsed_time": "4:44:18", "remaining_time": "2:26:17", "throughput": 1484.97, "total_tokens": 25331296} {"current_steps": 120040, "total_steps": 181800, "loss": 0.0107, "lr": 1.561214155701095e-05, "epoch": 13.205720572057206, "percentage": 66.03, "elapsed_time": "4:44:19", "remaining_time": "2:26:16", "throughput": 1484.97, "total_tokens": 25332320} {"current_steps": 120045, "total_steps": 181800, "loss": 0.0246, "lr": 1.5609917177700466e-05, "epoch": 13.206270627062706, "percentage": 66.03, "elapsed_time": "4:44:19", "remaining_time": "2:26:16", "throughput": 1484.97, "total_tokens": 25333376} {"current_steps": 120050, "total_steps": 181800, "loss": 0.008, "lr": 1.560769288493387e-05, "epoch": 13.206820682068207, "percentage": 66.03, "elapsed_time": "4:44:20", "remaining_time": "2:26:15", "throughput": 1484.97, "total_tokens": 25334464} {"current_steps": 120055, "total_steps": 181800, "loss": 0.0074, "lr": 1.560546867873166e-05, "epoch": 13.207370737073708, "percentage": 66.04, "elapsed_time": "4:44:21", "remaining_time": "2:26:14", "throughput": 1484.97, "total_tokens": 25335552} {"current_steps": 120060, "total_steps": 181800, "loss": 0.0063, "lr": 1.5603244559114333e-05, "epoch": 13.207920792079207, "percentage": 66.04, "elapsed_time": "4:44:21", "remaining_time": "2:26:13", "throughput": 1484.97, "total_tokens": 25336576} {"current_steps": 120065, "total_steps": 181800, "loss": 0.0185, "lr": 1.5601020526102392e-05, "epoch": 13.208470847084708, "percentage": 66.04, "elapsed_time": "4:44:22", "remaining_time": "2:26:13", "throughput": 1484.98, "total_tokens": 25337664} {"current_steps": 120070, "total_steps": 181800, "loss": 0.0077, "lr": 1.5598796579716345e-05, "epoch": 13.20902090209021, "percentage": 66.05, "elapsed_time": "4:44:23", "remaining_time": "2:26:12", "throughput": 1484.98, "total_tokens": 25338688} {"current_steps": 120075, "total_steps": 181800, "loss": 0.0422, "lr": 1.559657271997667e-05, "epoch": 13.209570957095709, "percentage": 66.05, "elapsed_time": "4:44:24", "remaining_time": "2:26:11", "throughput": 1484.98, "total_tokens": 25339776} {"current_steps": 120080, "total_steps": 181800, "loss": 0.0062, "lr": 1.559434894690387e-05, "epoch": 13.21012101210121, "percentage": 66.05, "elapsed_time": "4:44:24", "remaining_time": "2:26:11", "throughput": 1484.98, "total_tokens": 25340864} {"current_steps": 120085, "total_steps": 181800, "loss": 0.0051, "lr": 1.5592125260518452e-05, "epoch": 13.210671067106711, "percentage": 66.05, "elapsed_time": "4:44:25", "remaining_time": "2:26:10", "throughput": 1484.98, "total_tokens": 25341888} {"current_steps": 120090, "total_steps": 181800, "loss": 0.0289, "lr": 1.5589901660840896e-05, "epoch": 13.211221122112212, "percentage": 66.06, "elapsed_time": "4:44:26", "remaining_time": "2:26:09", "throughput": 1484.98, "total_tokens": 25342912} {"current_steps": 120095, "total_steps": 181800, "loss": 0.0148, "lr": 1.5587678147891698e-05, "epoch": 13.211771177117711, "percentage": 66.06, "elapsed_time": "4:44:26", "remaining_time": "2:26:08", "throughput": 1484.99, "total_tokens": 25343968} {"current_steps": 120100, "total_steps": 181800, "loss": 0.0549, "lr": 1.5585454721691362e-05, "epoch": 13.212321232123212, "percentage": 66.06, "elapsed_time": "4:44:27", "remaining_time": "2:26:08", "throughput": 1484.99, "total_tokens": 25345088} {"current_steps": 120105, "total_steps": 181800, "loss": 0.0148, "lr": 1.5583231382260357e-05, "epoch": 13.212871287128714, "percentage": 66.06, "elapsed_time": "4:44:28", "remaining_time": "2:26:07", "throughput": 1485.0, "total_tokens": 25346208} {"current_steps": 120110, "total_steps": 181800, "loss": 0.0114, "lr": 1.5581008129619206e-05, "epoch": 13.213421342134213, "percentage": 66.07, "elapsed_time": "4:44:28", "remaining_time": "2:26:06", "throughput": 1485.0, "total_tokens": 25347232} {"current_steps": 120115, "total_steps": 181800, "loss": 0.004, "lr": 1.557878496378838e-05, "epoch": 13.213971397139714, "percentage": 66.07, "elapsed_time": "4:44:29", "remaining_time": "2:26:06", "throughput": 1485.0, "total_tokens": 25348288} {"current_steps": 120120, "total_steps": 181800, "loss": 0.0082, "lr": 1.557656188478836e-05, "epoch": 13.214521452145215, "percentage": 66.07, "elapsed_time": "4:44:30", "remaining_time": "2:26:05", "throughput": 1485.0, "total_tokens": 25349312} {"current_steps": 120125, "total_steps": 181800, "loss": 0.0017, "lr": 1.5574338892639666e-05, "epoch": 13.215071507150714, "percentage": 66.08, "elapsed_time": "4:44:30", "remaining_time": "2:26:04", "throughput": 1485.0, "total_tokens": 25350368} {"current_steps": 120130, "total_steps": 181800, "loss": 0.0634, "lr": 1.557211598736275e-05, "epoch": 13.215621562156215, "percentage": 66.08, "elapsed_time": "4:44:31", "remaining_time": "2:26:03", "throughput": 1485.0, "total_tokens": 25351392} {"current_steps": 120135, "total_steps": 181800, "loss": 0.0143, "lr": 1.556989316897813e-05, "epoch": 13.216171617161717, "percentage": 66.08, "elapsed_time": "4:44:32", "remaining_time": "2:26:03", "throughput": 1485.0, "total_tokens": 25352416} {"current_steps": 120140, "total_steps": 181800, "loss": 0.0507, "lr": 1.5567670437506278e-05, "epoch": 13.216721672167218, "percentage": 66.08, "elapsed_time": "4:44:33", "remaining_time": "2:26:02", "throughput": 1485.0, "total_tokens": 25353472} {"current_steps": 120145, "total_steps": 181800, "loss": 0.0016, "lr": 1.5565447792967675e-05, "epoch": 13.217271727172717, "percentage": 66.09, "elapsed_time": "4:44:33", "remaining_time": "2:26:01", "throughput": 1485.0, "total_tokens": 25354496} {"current_steps": 120150, "total_steps": 181800, "loss": 0.0087, "lr": 1.5563225235382818e-05, "epoch": 13.217821782178218, "percentage": 66.09, "elapsed_time": "4:44:34", "remaining_time": "2:26:01", "throughput": 1485.01, "total_tokens": 25355584} {"current_steps": 120155, "total_steps": 181800, "loss": 0.0062, "lr": 1.5561002764772175e-05, "epoch": 13.218371837183719, "percentage": 66.09, "elapsed_time": "4:44:35", "remaining_time": "2:26:00", "throughput": 1485.01, "total_tokens": 25356640} {"current_steps": 120160, "total_steps": 181800, "loss": 0.0028, "lr": 1.555878038115625e-05, "epoch": 13.218921892189218, "percentage": 66.09, "elapsed_time": "4:44:35", "remaining_time": "2:25:59", "throughput": 1485.01, "total_tokens": 25357664} {"current_steps": 120165, "total_steps": 181800, "loss": 0.0082, "lr": 1.5556558084555523e-05, "epoch": 13.21947194719472, "percentage": 66.1, "elapsed_time": "4:44:36", "remaining_time": "2:25:58", "throughput": 1485.01, "total_tokens": 25358688} {"current_steps": 120170, "total_steps": 181800, "loss": 0.0268, "lr": 1.5554335874990456e-05, "epoch": 13.22002200220022, "percentage": 66.1, "elapsed_time": "4:44:37", "remaining_time": "2:25:58", "throughput": 1485.01, "total_tokens": 25359680} {"current_steps": 120175, "total_steps": 181800, "loss": 0.1329, "lr": 1.5552113752481545e-05, "epoch": 13.22057205720572, "percentage": 66.1, "elapsed_time": "4:44:37", "remaining_time": "2:25:57", "throughput": 1485.0, "total_tokens": 25360672} {"current_steps": 120180, "total_steps": 181800, "loss": 0.0281, "lr": 1.5549891717049267e-05, "epoch": 13.221122112211221, "percentage": 66.11, "elapsed_time": "4:44:38", "remaining_time": "2:25:56", "throughput": 1485.01, "total_tokens": 25361728} {"current_steps": 120185, "total_steps": 181800, "loss": 0.0167, "lr": 1.554766976871411e-05, "epoch": 13.221672167216722, "percentage": 66.11, "elapsed_time": "4:44:39", "remaining_time": "2:25:55", "throughput": 1485.01, "total_tokens": 25362784} {"current_steps": 120190, "total_steps": 181800, "loss": 0.108, "lr": 1.5545447907496545e-05, "epoch": 13.222222222222221, "percentage": 66.11, "elapsed_time": "4:44:39", "remaining_time": "2:25:55", "throughput": 1485.01, "total_tokens": 25363840} {"current_steps": 120195, "total_steps": 181800, "loss": 0.0045, "lr": 1.554322613341704e-05, "epoch": 13.222772277227723, "percentage": 66.11, "elapsed_time": "4:44:40", "remaining_time": "2:25:54", "throughput": 1485.01, "total_tokens": 25364896} {"current_steps": 120200, "total_steps": 181800, "loss": 0.0028, "lr": 1.5541004446496095e-05, "epoch": 13.223322332233224, "percentage": 66.12, "elapsed_time": "4:44:41", "remaining_time": "2:25:53", "throughput": 1485.01, "total_tokens": 25365984} {"current_steps": 120205, "total_steps": 181800, "loss": 0.0041, "lr": 1.5538782846754157e-05, "epoch": 13.223872387238725, "percentage": 66.12, "elapsed_time": "4:44:41", "remaining_time": "2:25:53", "throughput": 1485.02, "total_tokens": 25367040} {"current_steps": 120210, "total_steps": 181800, "loss": 0.1251, "lr": 1.553656133421173e-05, "epoch": 13.224422442244224, "percentage": 66.12, "elapsed_time": "4:44:42", "remaining_time": "2:25:52", "throughput": 1485.01, "total_tokens": 25368032} {"current_steps": 120215, "total_steps": 181800, "loss": 0.0389, "lr": 1.5534339908889278e-05, "epoch": 13.224972497249725, "percentage": 66.12, "elapsed_time": "4:44:43", "remaining_time": "2:25:51", "throughput": 1485.01, "total_tokens": 25369024} {"current_steps": 120220, "total_steps": 181800, "loss": 0.0034, "lr": 1.553211857080726e-05, "epoch": 13.225522552255226, "percentage": 66.13, "elapsed_time": "4:44:44", "remaining_time": "2:25:50", "throughput": 1485.01, "total_tokens": 25370048} {"current_steps": 120225, "total_steps": 181800, "loss": 0.017, "lr": 1.552989731998617e-05, "epoch": 13.226072607260726, "percentage": 66.13, "elapsed_time": "4:44:44", "remaining_time": "2:25:50", "throughput": 1485.02, "total_tokens": 25371104} {"current_steps": 120230, "total_steps": 181800, "loss": 0.0678, "lr": 1.552767615644647e-05, "epoch": 13.226622662266227, "percentage": 66.13, "elapsed_time": "4:44:45", "remaining_time": "2:25:49", "throughput": 1485.02, "total_tokens": 25372192} {"current_steps": 120235, "total_steps": 181800, "loss": 0.0826, "lr": 1.5525455080208636e-05, "epoch": 13.227172717271728, "percentage": 66.14, "elapsed_time": "4:44:46", "remaining_time": "2:25:48", "throughput": 1485.03, "total_tokens": 25373344} {"current_steps": 120240, "total_steps": 181800, "loss": 0.0269, "lr": 1.5523234091293144e-05, "epoch": 13.227722772277227, "percentage": 66.14, "elapsed_time": "4:44:46", "remaining_time": "2:25:48", "throughput": 1485.03, "total_tokens": 25374400} {"current_steps": 120245, "total_steps": 181800, "loss": 0.0457, "lr": 1.552101318972044e-05, "epoch": 13.228272827282728, "percentage": 66.14, "elapsed_time": "4:44:47", "remaining_time": "2:25:47", "throughput": 1485.03, "total_tokens": 25375456} {"current_steps": 120250, "total_steps": 181800, "loss": 0.1131, "lr": 1.5518792375511016e-05, "epoch": 13.22882288228823, "percentage": 66.14, "elapsed_time": "4:44:48", "remaining_time": "2:25:46", "throughput": 1485.03, "total_tokens": 25376544} {"current_steps": 120255, "total_steps": 181800, "loss": 0.0073, "lr": 1.551657164868533e-05, "epoch": 13.229372937293729, "percentage": 66.15, "elapsed_time": "4:44:48", "remaining_time": "2:25:45", "throughput": 1485.04, "total_tokens": 25377600} {"current_steps": 120260, "total_steps": 181800, "loss": 0.1307, "lr": 1.551435100926386e-05, "epoch": 13.22992299229923, "percentage": 66.15, "elapsed_time": "4:44:49", "remaining_time": "2:25:45", "throughput": 1485.04, "total_tokens": 25378624} {"current_steps": 120265, "total_steps": 181800, "loss": 0.0005, "lr": 1.5512130457267066e-05, "epoch": 13.23047304730473, "percentage": 66.15, "elapsed_time": "4:44:50", "remaining_time": "2:25:44", "throughput": 1485.04, "total_tokens": 25379680} {"current_steps": 120270, "total_steps": 181800, "loss": 0.0029, "lr": 1.55099099927154e-05, "epoch": 13.231023102310232, "percentage": 66.16, "elapsed_time": "4:44:50", "remaining_time": "2:25:43", "throughput": 1485.04, "total_tokens": 25380736} {"current_steps": 120275, "total_steps": 181800, "loss": 0.0221, "lr": 1.5507689615629357e-05, "epoch": 13.231573157315731, "percentage": 66.16, "elapsed_time": "4:44:51", "remaining_time": "2:25:42", "throughput": 1485.04, "total_tokens": 25381792} {"current_steps": 120280, "total_steps": 181800, "loss": 0.1601, "lr": 1.5505469326029372e-05, "epoch": 13.232123212321232, "percentage": 66.16, "elapsed_time": "4:44:52", "remaining_time": "2:25:42", "throughput": 1485.04, "total_tokens": 25382848} {"current_steps": 120285, "total_steps": 181800, "loss": 0.0895, "lr": 1.550324912393592e-05, "epoch": 13.232673267326733, "percentage": 66.16, "elapsed_time": "4:44:53", "remaining_time": "2:25:41", "throughput": 1485.04, "total_tokens": 25383904} {"current_steps": 120290, "total_steps": 181800, "loss": 0.0029, "lr": 1.5501029009369467e-05, "epoch": 13.233223322332233, "percentage": 66.17, "elapsed_time": "4:44:53", "remaining_time": "2:25:40", "throughput": 1485.04, "total_tokens": 25384896} {"current_steps": 120295, "total_steps": 181800, "loss": 0.003, "lr": 1.549880898235047e-05, "epoch": 13.233773377337734, "percentage": 66.17, "elapsed_time": "4:44:54", "remaining_time": "2:25:40", "throughput": 1485.05, "total_tokens": 25385952} {"current_steps": 120300, "total_steps": 181800, "loss": 0.0049, "lr": 1.5496589042899396e-05, "epoch": 13.234323432343235, "percentage": 66.17, "elapsed_time": "4:44:55", "remaining_time": "2:25:39", "throughput": 1485.05, "total_tokens": 25387008} {"current_steps": 120305, "total_steps": 181800, "loss": 0.0065, "lr": 1.54943691910367e-05, "epoch": 13.234873487348734, "percentage": 66.17, "elapsed_time": "4:44:55", "remaining_time": "2:25:38", "throughput": 1485.05, "total_tokens": 25388000} {"current_steps": 120310, "total_steps": 181800, "loss": 0.0716, "lr": 1.5492149426782834e-05, "epoch": 13.235423542354235, "percentage": 66.18, "elapsed_time": "4:44:56", "remaining_time": "2:25:37", "throughput": 1485.05, "total_tokens": 25389024} {"current_steps": 120315, "total_steps": 181800, "loss": 0.0283, "lr": 1.548992975015828e-05, "epoch": 13.235973597359736, "percentage": 66.18, "elapsed_time": "4:44:57", "remaining_time": "2:25:37", "throughput": 1485.04, "total_tokens": 25390016} {"current_steps": 120320, "total_steps": 181800, "loss": 0.0125, "lr": 1.548771016118346e-05, "epoch": 13.236523652365236, "percentage": 66.18, "elapsed_time": "4:44:57", "remaining_time": "2:25:36", "throughput": 1485.05, "total_tokens": 25391072} {"current_steps": 120325, "total_steps": 181800, "loss": 0.0683, "lr": 1.5485490659878865e-05, "epoch": 13.237073707370737, "percentage": 66.19, "elapsed_time": "4:44:58", "remaining_time": "2:25:35", "throughput": 1485.05, "total_tokens": 25392096} {"current_steps": 120330, "total_steps": 181800, "loss": 0.0189, "lr": 1.5483271246264938e-05, "epoch": 13.237623762376238, "percentage": 66.19, "elapsed_time": "4:44:59", "remaining_time": "2:25:35", "throughput": 1485.05, "total_tokens": 25393152} {"current_steps": 120335, "total_steps": 181800, "loss": 0.0587, "lr": 1.5481051920362123e-05, "epoch": 13.238173817381739, "percentage": 66.19, "elapsed_time": "4:44:59", "remaining_time": "2:25:34", "throughput": 1485.05, "total_tokens": 25394176} {"current_steps": 120340, "total_steps": 181800, "loss": 0.0028, "lr": 1.5478832682190892e-05, "epoch": 13.238723872387238, "percentage": 66.19, "elapsed_time": "4:45:00", "remaining_time": "2:25:33", "throughput": 1485.05, "total_tokens": 25395200} {"current_steps": 120345, "total_steps": 181800, "loss": 0.0441, "lr": 1.5476613531771685e-05, "epoch": 13.23927392739274, "percentage": 66.2, "elapsed_time": "4:45:01", "remaining_time": "2:25:32", "throughput": 1485.05, "total_tokens": 25396288} {"current_steps": 120350, "total_steps": 181800, "loss": 0.0135, "lr": 1.547439446912497e-05, "epoch": 13.23982398239824, "percentage": 66.2, "elapsed_time": "4:45:01", "remaining_time": "2:25:32", "throughput": 1485.05, "total_tokens": 25397344} {"current_steps": 120355, "total_steps": 181800, "loss": 0.0378, "lr": 1.547217549427119e-05, "epoch": 13.24037403740374, "percentage": 66.2, "elapsed_time": "4:45:02", "remaining_time": "2:25:31", "throughput": 1485.05, "total_tokens": 25398336} {"current_steps": 120360, "total_steps": 181800, "loss": 0.0018, "lr": 1.5469956607230787e-05, "epoch": 13.24092409240924, "percentage": 66.2, "elapsed_time": "4:45:03", "remaining_time": "2:25:30", "throughput": 1485.05, "total_tokens": 25399392} {"current_steps": 120365, "total_steps": 181800, "loss": 0.0935, "lr": 1.546773780802423e-05, "epoch": 13.241474147414742, "percentage": 66.21, "elapsed_time": "4:45:04", "remaining_time": "2:25:30", "throughput": 1485.05, "total_tokens": 25400384} {"current_steps": 120370, "total_steps": 181800, "loss": 0.0756, "lr": 1.546551909667195e-05, "epoch": 13.242024202420241, "percentage": 66.21, "elapsed_time": "4:45:04", "remaining_time": "2:25:29", "throughput": 1485.05, "total_tokens": 25401440} {"current_steps": 120375, "total_steps": 181800, "loss": 0.0319, "lr": 1.546330047319442e-05, "epoch": 13.242574257425742, "percentage": 66.21, "elapsed_time": "4:45:05", "remaining_time": "2:25:28", "throughput": 1485.06, "total_tokens": 25402528} {"current_steps": 120380, "total_steps": 181800, "loss": 0.0058, "lr": 1.5461081937612064e-05, "epoch": 13.243124312431243, "percentage": 66.22, "elapsed_time": "4:45:06", "remaining_time": "2:25:27", "throughput": 1485.06, "total_tokens": 25403584} {"current_steps": 120385, "total_steps": 181800, "loss": 0.0508, "lr": 1.5458863489945335e-05, "epoch": 13.243674367436745, "percentage": 66.22, "elapsed_time": "4:45:06", "remaining_time": "2:25:27", "throughput": 1485.06, "total_tokens": 25404640} {"current_steps": 120390, "total_steps": 181800, "loss": 0.0127, "lr": 1.5456645130214694e-05, "epoch": 13.244224422442244, "percentage": 66.22, "elapsed_time": "4:45:07", "remaining_time": "2:25:26", "throughput": 1485.06, "total_tokens": 25405728} {"current_steps": 120395, "total_steps": 181800, "loss": 0.0771, "lr": 1.5454426858440567e-05, "epoch": 13.244774477447745, "percentage": 66.22, "elapsed_time": "4:45:08", "remaining_time": "2:25:25", "throughput": 1485.07, "total_tokens": 25406816} {"current_steps": 120400, "total_steps": 181800, "loss": 0.0137, "lr": 1.545220867464341e-05, "epoch": 13.245324532453246, "percentage": 66.23, "elapsed_time": "4:45:08", "remaining_time": "2:25:24", "throughput": 1485.07, "total_tokens": 25407904} {"current_steps": 120405, "total_steps": 181800, "loss": 0.1254, "lr": 1.5449990578843667e-05, "epoch": 13.245874587458745, "percentage": 66.23, "elapsed_time": "4:45:09", "remaining_time": "2:25:24", "throughput": 1485.07, "total_tokens": 25408960} {"current_steps": 120410, "total_steps": 181800, "loss": 0.006, "lr": 1.544777257106177e-05, "epoch": 13.246424642464246, "percentage": 66.23, "elapsed_time": "4:45:10", "remaining_time": "2:25:23", "throughput": 1485.07, "total_tokens": 25409984} {"current_steps": 120415, "total_steps": 181800, "loss": 0.0202, "lr": 1.544555465131818e-05, "epoch": 13.246974697469748, "percentage": 66.23, "elapsed_time": "4:45:10", "remaining_time": "2:25:22", "throughput": 1485.08, "total_tokens": 25411040} {"current_steps": 120420, "total_steps": 181800, "loss": 0.0426, "lr": 1.5443336819633315e-05, "epoch": 13.247524752475247, "percentage": 66.24, "elapsed_time": "4:45:11", "remaining_time": "2:25:22", "throughput": 1485.08, "total_tokens": 25412064} {"current_steps": 120425, "total_steps": 181800, "loss": 0.0262, "lr": 1.5441119076027637e-05, "epoch": 13.248074807480748, "percentage": 66.24, "elapsed_time": "4:45:12", "remaining_time": "2:25:21", "throughput": 1485.08, "total_tokens": 25413184} {"current_steps": 120430, "total_steps": 181800, "loss": 0.0064, "lr": 1.5438901420521584e-05, "epoch": 13.248624862486249, "percentage": 66.24, "elapsed_time": "4:45:12", "remaining_time": "2:25:20", "throughput": 1485.08, "total_tokens": 25414208} {"current_steps": 120435, "total_steps": 181800, "loss": 0.0043, "lr": 1.5436683853135577e-05, "epoch": 13.249174917491748, "percentage": 66.25, "elapsed_time": "4:45:13", "remaining_time": "2:25:19", "throughput": 1485.08, "total_tokens": 25415232} {"current_steps": 120440, "total_steps": 181800, "loss": 0.0016, "lr": 1.5434466373890073e-05, "epoch": 13.24972497249725, "percentage": 66.25, "elapsed_time": "4:45:14", "remaining_time": "2:25:19", "throughput": 1485.08, "total_tokens": 25416224} {"current_steps": 120445, "total_steps": 181800, "loss": 0.0603, "lr": 1.5432248982805497e-05, "epoch": 13.25027502750275, "percentage": 66.25, "elapsed_time": "4:45:15", "remaining_time": "2:25:18", "throughput": 1485.08, "total_tokens": 25417216} {"current_steps": 120450, "total_steps": 181800, "loss": 0.1349, "lr": 1.5430031679902303e-05, "epoch": 13.250825082508252, "percentage": 66.25, "elapsed_time": "4:45:15", "remaining_time": "2:25:17", "throughput": 1485.08, "total_tokens": 25418336} {"current_steps": 120455, "total_steps": 181800, "loss": 0.0236, "lr": 1.5427814465200903e-05, "epoch": 13.251375137513751, "percentage": 66.26, "elapsed_time": "4:45:16", "remaining_time": "2:25:17", "throughput": 1485.09, "total_tokens": 25419424} {"current_steps": 120460, "total_steps": 181800, "loss": 0.0165, "lr": 1.5425597338721742e-05, "epoch": 13.251925192519252, "percentage": 66.26, "elapsed_time": "4:45:17", "remaining_time": "2:25:16", "throughput": 1485.09, "total_tokens": 25420416} {"current_steps": 120465, "total_steps": 181800, "loss": 0.0527, "lr": 1.5423380300485264e-05, "epoch": 13.252475247524753, "percentage": 66.26, "elapsed_time": "4:45:17", "remaining_time": "2:25:15", "throughput": 1485.09, "total_tokens": 25421472} {"current_steps": 120470, "total_steps": 181800, "loss": 0.0234, "lr": 1.5421163350511896e-05, "epoch": 13.253025302530252, "percentage": 66.27, "elapsed_time": "4:45:18", "remaining_time": "2:25:14", "throughput": 1485.09, "total_tokens": 25422464} {"current_steps": 120475, "total_steps": 181800, "loss": 0.066, "lr": 1.541894648882206e-05, "epoch": 13.253575357535754, "percentage": 66.27, "elapsed_time": "4:45:19", "remaining_time": "2:25:14", "throughput": 1485.09, "total_tokens": 25423488} {"current_steps": 120480, "total_steps": 181800, "loss": 0.0066, "lr": 1.5416729715436205e-05, "epoch": 13.254125412541255, "percentage": 66.27, "elapsed_time": "4:45:19", "remaining_time": "2:25:13", "throughput": 1485.09, "total_tokens": 25424576} {"current_steps": 120485, "total_steps": 181800, "loss": 0.0038, "lr": 1.5414513030374746e-05, "epoch": 13.254675467546754, "percentage": 66.27, "elapsed_time": "4:45:20", "remaining_time": "2:25:12", "throughput": 1485.09, "total_tokens": 25425664} {"current_steps": 120490, "total_steps": 181800, "loss": 0.007, "lr": 1.541229643365813e-05, "epoch": 13.255225522552255, "percentage": 66.28, "elapsed_time": "4:45:21", "remaining_time": "2:25:11", "throughput": 1485.1, "total_tokens": 25426752} {"current_steps": 120495, "total_steps": 181800, "loss": 0.0053, "lr": 1.5410079925306777e-05, "epoch": 13.255775577557756, "percentage": 66.28, "elapsed_time": "4:45:21", "remaining_time": "2:25:11", "throughput": 1485.1, "total_tokens": 25427744} {"current_steps": 120500, "total_steps": 181800, "loss": 0.0566, "lr": 1.5407863505341104e-05, "epoch": 13.256325632563255, "percentage": 66.28, "elapsed_time": "4:45:22", "remaining_time": "2:25:10", "throughput": 1485.1, "total_tokens": 25428864} {"current_steps": 120505, "total_steps": 181800, "loss": 0.0028, "lr": 1.540564717378156e-05, "epoch": 13.256875687568757, "percentage": 66.28, "elapsed_time": "4:45:23", "remaining_time": "2:25:09", "throughput": 1485.1, "total_tokens": 25429888} {"current_steps": 120510, "total_steps": 181800, "loss": 0.0219, "lr": 1.5403430930648558e-05, "epoch": 13.257425742574258, "percentage": 66.29, "elapsed_time": "4:45:24", "remaining_time": "2:25:09", "throughput": 1485.11, "total_tokens": 25430976} {"current_steps": 120515, "total_steps": 181800, "loss": 0.0089, "lr": 1.5401214775962532e-05, "epoch": 13.257975797579759, "percentage": 66.29, "elapsed_time": "4:45:24", "remaining_time": "2:25:08", "throughput": 1485.11, "total_tokens": 25432000} {"current_steps": 120520, "total_steps": 181800, "loss": 0.0062, "lr": 1.5398998709743906e-05, "epoch": 13.258525852585258, "percentage": 66.29, "elapsed_time": "4:45:25", "remaining_time": "2:25:07", "throughput": 1485.11, "total_tokens": 25433056} {"current_steps": 120525, "total_steps": 181800, "loss": 0.0067, "lr": 1.539678273201309e-05, "epoch": 13.25907590759076, "percentage": 66.3, "elapsed_time": "4:45:26", "remaining_time": "2:25:06", "throughput": 1485.11, "total_tokens": 25434112} {"current_steps": 120530, "total_steps": 181800, "loss": 0.0127, "lr": 1.539456684279053e-05, "epoch": 13.25962596259626, "percentage": 66.3, "elapsed_time": "4:45:26", "remaining_time": "2:25:06", "throughput": 1485.11, "total_tokens": 25435168} {"current_steps": 120535, "total_steps": 181800, "loss": 0.0092, "lr": 1.5392351042096627e-05, "epoch": 13.26017601760176, "percentage": 66.3, "elapsed_time": "4:45:27", "remaining_time": "2:25:05", "throughput": 1485.12, "total_tokens": 25436256} {"current_steps": 120540, "total_steps": 181800, "loss": 0.0858, "lr": 1.5390135329951824e-05, "epoch": 13.26072607260726, "percentage": 66.3, "elapsed_time": "4:45:28", "remaining_time": "2:25:04", "throughput": 1485.12, "total_tokens": 25437312} {"current_steps": 120545, "total_steps": 181800, "loss": 0.0096, "lr": 1.5387919706376537e-05, "epoch": 13.261276127612762, "percentage": 66.31, "elapsed_time": "4:45:28", "remaining_time": "2:25:04", "throughput": 1485.12, "total_tokens": 25438368} {"current_steps": 120550, "total_steps": 181800, "loss": 0.016, "lr": 1.538570417139117e-05, "epoch": 13.261826182618261, "percentage": 66.31, "elapsed_time": "4:45:29", "remaining_time": "2:25:03", "throughput": 1485.12, "total_tokens": 25439424} {"current_steps": 120555, "total_steps": 181800, "loss": 0.0043, "lr": 1.538348872501616e-05, "epoch": 13.262376237623762, "percentage": 66.31, "elapsed_time": "4:45:30", "remaining_time": "2:25:02", "throughput": 1485.12, "total_tokens": 25440480} {"current_steps": 120560, "total_steps": 181800, "loss": 0.0023, "lr": 1.5381273367271915e-05, "epoch": 13.262926292629263, "percentage": 66.31, "elapsed_time": "4:45:30", "remaining_time": "2:25:01", "throughput": 1485.13, "total_tokens": 25441536} {"current_steps": 120565, "total_steps": 181800, "loss": 0.0077, "lr": 1.537905809817887e-05, "epoch": 13.263476347634764, "percentage": 66.32, "elapsed_time": "4:45:31", "remaining_time": "2:25:01", "throughput": 1485.13, "total_tokens": 25442592} {"current_steps": 120570, "total_steps": 181800, "loss": 0.0293, "lr": 1.5376842917757423e-05, "epoch": 13.264026402640264, "percentage": 66.32, "elapsed_time": "4:45:32", "remaining_time": "2:25:00", "throughput": 1485.13, "total_tokens": 25443648} {"current_steps": 120575, "total_steps": 181800, "loss": 0.0091, "lr": 1.5374627826027995e-05, "epoch": 13.264576457645765, "percentage": 66.32, "elapsed_time": "4:45:32", "remaining_time": "2:24:59", "throughput": 1485.14, "total_tokens": 25444768} {"current_steps": 120580, "total_steps": 181800, "loss": 0.0823, "lr": 1.5372412823011006e-05, "epoch": 13.265126512651266, "percentage": 66.33, "elapsed_time": "4:45:33", "remaining_time": "2:24:58", "throughput": 1485.14, "total_tokens": 25445856} {"current_steps": 120585, "total_steps": 181800, "loss": 0.0058, "lr": 1.537019790872686e-05, "epoch": 13.265676567656765, "percentage": 66.33, "elapsed_time": "4:45:34", "remaining_time": "2:24:58", "throughput": 1485.14, "total_tokens": 25446880} {"current_steps": 120590, "total_steps": 181800, "loss": 0.0029, "lr": 1.5367983083195992e-05, "epoch": 13.266226622662266, "percentage": 66.33, "elapsed_time": "4:45:35", "remaining_time": "2:24:57", "throughput": 1485.14, "total_tokens": 25447968} {"current_steps": 120595, "total_steps": 181800, "loss": 0.0087, "lr": 1.5365768346438797e-05, "epoch": 13.266776677667767, "percentage": 66.33, "elapsed_time": "4:45:35", "remaining_time": "2:24:56", "throughput": 1485.15, "total_tokens": 25449088} {"current_steps": 120600, "total_steps": 181800, "loss": 0.0028, "lr": 1.5363553698475685e-05, "epoch": 13.267326732673267, "percentage": 66.34, "elapsed_time": "4:45:36", "remaining_time": "2:24:56", "throughput": 1485.15, "total_tokens": 25450112} {"current_steps": 120605, "total_steps": 181800, "loss": 0.0244, "lr": 1.536133913932709e-05, "epoch": 13.267876787678768, "percentage": 66.34, "elapsed_time": "4:45:37", "remaining_time": "2:24:55", "throughput": 1485.15, "total_tokens": 25451136} {"current_steps": 120610, "total_steps": 181800, "loss": 0.0058, "lr": 1.535912466901339e-05, "epoch": 13.268426842684269, "percentage": 66.34, "elapsed_time": "4:45:37", "remaining_time": "2:24:54", "throughput": 1485.16, "total_tokens": 25452288} {"current_steps": 120615, "total_steps": 181800, "loss": 0.0063, "lr": 1.535691028755502e-05, "epoch": 13.268976897689768, "percentage": 66.34, "elapsed_time": "4:45:38", "remaining_time": "2:24:53", "throughput": 1485.16, "total_tokens": 25453344} {"current_steps": 120620, "total_steps": 181800, "loss": 0.0046, "lr": 1.535469599497239e-05, "epoch": 13.26952695269527, "percentage": 66.35, "elapsed_time": "4:45:39", "remaining_time": "2:24:53", "throughput": 1485.16, "total_tokens": 25454336} {"current_steps": 120625, "total_steps": 181800, "loss": 0.0477, "lr": 1.5352481791285884e-05, "epoch": 13.27007700770077, "percentage": 66.35, "elapsed_time": "4:45:39", "remaining_time": "2:24:52", "throughput": 1485.16, "total_tokens": 25455424} {"current_steps": 120630, "total_steps": 181800, "loss": 0.0028, "lr": 1.535026767651593e-05, "epoch": 13.270627062706271, "percentage": 66.35, "elapsed_time": "4:45:40", "remaining_time": "2:24:51", "throughput": 1485.16, "total_tokens": 25456544} {"current_steps": 120635, "total_steps": 181800, "loss": 0.0022, "lr": 1.5348053650682925e-05, "epoch": 13.27117711771177, "percentage": 66.36, "elapsed_time": "4:45:41", "remaining_time": "2:24:51", "throughput": 1485.16, "total_tokens": 25457568} {"current_steps": 120640, "total_steps": 181800, "loss": 0.0024, "lr": 1.5345839713807287e-05, "epoch": 13.271727172717272, "percentage": 66.36, "elapsed_time": "4:45:41", "remaining_time": "2:24:50", "throughput": 1485.17, "total_tokens": 25458624} {"current_steps": 120645, "total_steps": 181800, "loss": 0.0583, "lr": 1.5343625865909407e-05, "epoch": 13.272277227722773, "percentage": 66.36, "elapsed_time": "4:45:42", "remaining_time": "2:24:49", "throughput": 1485.17, "total_tokens": 25459712} {"current_steps": 120650, "total_steps": 181800, "loss": 0.0036, "lr": 1.5341412107009685e-05, "epoch": 13.272827282728272, "percentage": 66.36, "elapsed_time": "4:45:43", "remaining_time": "2:24:48", "throughput": 1485.17, "total_tokens": 25460800} {"current_steps": 120655, "total_steps": 181800, "loss": 0.0039, "lr": 1.5339198437128542e-05, "epoch": 13.273377337733773, "percentage": 66.37, "elapsed_time": "4:45:44", "remaining_time": "2:24:48", "throughput": 1485.17, "total_tokens": 25461856} {"current_steps": 120660, "total_steps": 181800, "loss": 0.0011, "lr": 1.5336984856286374e-05, "epoch": 13.273927392739274, "percentage": 66.37, "elapsed_time": "4:45:44", "remaining_time": "2:24:47", "throughput": 1485.18, "total_tokens": 25462944} {"current_steps": 120665, "total_steps": 181800, "loss": 0.1265, "lr": 1.533477136450357e-05, "epoch": 13.274477447744774, "percentage": 66.37, "elapsed_time": "4:45:45", "remaining_time": "2:24:46", "throughput": 1485.18, "total_tokens": 25464032} {"current_steps": 120670, "total_steps": 181800, "loss": 0.0109, "lr": 1.533255796180055e-05, "epoch": 13.275027502750275, "percentage": 66.38, "elapsed_time": "4:45:46", "remaining_time": "2:24:46", "throughput": 1485.18, "total_tokens": 25465056} {"current_steps": 120675, "total_steps": 181800, "loss": 0.0686, "lr": 1.5330344648197697e-05, "epoch": 13.275577557755776, "percentage": 66.38, "elapsed_time": "4:45:46", "remaining_time": "2:24:45", "throughput": 1485.19, "total_tokens": 25466176} {"current_steps": 120680, "total_steps": 181800, "loss": 0.0073, "lr": 1.5328131423715426e-05, "epoch": 13.276127612761275, "percentage": 66.38, "elapsed_time": "4:45:47", "remaining_time": "2:24:44", "throughput": 1485.19, "total_tokens": 25467232} {"current_steps": 120685, "total_steps": 181800, "loss": 0.0429, "lr": 1.5325918288374123e-05, "epoch": 13.276677667766776, "percentage": 66.38, "elapsed_time": "4:45:48", "remaining_time": "2:24:43", "throughput": 1485.19, "total_tokens": 25468352} {"current_steps": 120690, "total_steps": 181800, "loss": 0.1123, "lr": 1.532370524219418e-05, "epoch": 13.277227722772277, "percentage": 66.39, "elapsed_time": "4:45:48", "remaining_time": "2:24:43", "throughput": 1485.19, "total_tokens": 25469408} {"current_steps": 120695, "total_steps": 181800, "loss": 0.103, "lr": 1.5321492285196017e-05, "epoch": 13.277777777777779, "percentage": 66.39, "elapsed_time": "4:45:49", "remaining_time": "2:24:42", "throughput": 1485.19, "total_tokens": 25470400} {"current_steps": 120700, "total_steps": 181800, "loss": 0.0021, "lr": 1.5319279417400008e-05, "epoch": 13.278327832783278, "percentage": 66.39, "elapsed_time": "4:45:50", "remaining_time": "2:24:41", "throughput": 1485.19, "total_tokens": 25471456} {"current_steps": 120705, "total_steps": 181800, "loss": 0.0016, "lr": 1.5317066638826557e-05, "epoch": 13.278877887788779, "percentage": 66.39, "elapsed_time": "4:45:50", "remaining_time": "2:24:40", "throughput": 1485.19, "total_tokens": 25472480} {"current_steps": 120710, "total_steps": 181800, "loss": 0.0093, "lr": 1.5314853949496056e-05, "epoch": 13.27942794279428, "percentage": 66.4, "elapsed_time": "4:45:51", "remaining_time": "2:24:40", "throughput": 1485.19, "total_tokens": 25473472} {"current_steps": 120715, "total_steps": 181800, "loss": 0.0471, "lr": 1.5312641349428892e-05, "epoch": 13.27997799779978, "percentage": 66.4, "elapsed_time": "4:45:52", "remaining_time": "2:24:39", "throughput": 1485.2, "total_tokens": 25474624} {"current_steps": 120720, "total_steps": 181800, "loss": 0.0689, "lr": 1.5310428838645473e-05, "epoch": 13.28052805280528, "percentage": 66.4, "elapsed_time": "4:45:53", "remaining_time": "2:24:38", "throughput": 1485.2, "total_tokens": 25475680} {"current_steps": 120725, "total_steps": 181800, "loss": 0.0053, "lr": 1.5308216417166177e-05, "epoch": 13.281078107810782, "percentage": 66.41, "elapsed_time": "4:45:53", "remaining_time": "2:24:38", "throughput": 1485.2, "total_tokens": 25476736} {"current_steps": 120730, "total_steps": 181800, "loss": 0.0413, "lr": 1.5306004085011404e-05, "epoch": 13.281628162816281, "percentage": 66.41, "elapsed_time": "4:45:54", "remaining_time": "2:24:37", "throughput": 1485.2, "total_tokens": 25477728} {"current_steps": 120735, "total_steps": 181800, "loss": 0.003, "lr": 1.5303791842201542e-05, "epoch": 13.282178217821782, "percentage": 66.41, "elapsed_time": "4:45:55", "remaining_time": "2:24:36", "throughput": 1485.2, "total_tokens": 25478816} {"current_steps": 120740, "total_steps": 181800, "loss": 0.0042, "lr": 1.530157968875697e-05, "epoch": 13.282728272827283, "percentage": 66.41, "elapsed_time": "4:45:55", "remaining_time": "2:24:35", "throughput": 1485.2, "total_tokens": 25479840} {"current_steps": 120745, "total_steps": 181800, "loss": 0.0213, "lr": 1.5299367624698092e-05, "epoch": 13.283278327832782, "percentage": 66.42, "elapsed_time": "4:45:56", "remaining_time": "2:24:35", "throughput": 1485.21, "total_tokens": 25480896} {"current_steps": 120750, "total_steps": 181800, "loss": 0.015, "lr": 1.5297155650045274e-05, "epoch": 13.283828382838283, "percentage": 66.42, "elapsed_time": "4:45:57", "remaining_time": "2:24:34", "throughput": 1485.21, "total_tokens": 25481920} {"current_steps": 120755, "total_steps": 181800, "loss": 0.046, "lr": 1.5294943764818936e-05, "epoch": 13.284378437843785, "percentage": 66.42, "elapsed_time": "4:45:57", "remaining_time": "2:24:33", "throughput": 1485.21, "total_tokens": 25483008} {"current_steps": 120760, "total_steps": 181800, "loss": 0.0106, "lr": 1.5292731969039432e-05, "epoch": 13.284928492849286, "percentage": 66.42, "elapsed_time": "4:45:58", "remaining_time": "2:24:33", "throughput": 1485.21, "total_tokens": 25484032} {"current_steps": 120765, "total_steps": 181800, "loss": 0.046, "lr": 1.529052026272716e-05, "epoch": 13.285478547854785, "percentage": 66.43, "elapsed_time": "4:45:59", "remaining_time": "2:24:32", "throughput": 1485.21, "total_tokens": 25485120} {"current_steps": 120770, "total_steps": 181800, "loss": 0.0835, "lr": 1.5288308645902507e-05, "epoch": 13.286028602860286, "percentage": 66.43, "elapsed_time": "4:45:59", "remaining_time": "2:24:31", "throughput": 1485.21, "total_tokens": 25486144} {"current_steps": 120775, "total_steps": 181800, "loss": 0.0214, "lr": 1.5286097118585847e-05, "epoch": 13.286578657865787, "percentage": 66.43, "elapsed_time": "4:46:00", "remaining_time": "2:24:30", "throughput": 1485.22, "total_tokens": 25487232} {"current_steps": 120780, "total_steps": 181800, "loss": 0.0077, "lr": 1.5283885680797578e-05, "epoch": 13.287128712871286, "percentage": 66.44, "elapsed_time": "4:46:01", "remaining_time": "2:24:30", "throughput": 1485.22, "total_tokens": 25488352} {"current_steps": 120785, "total_steps": 181800, "loss": 0.0114, "lr": 1.5281674332558073e-05, "epoch": 13.287678767876788, "percentage": 66.44, "elapsed_time": "4:46:02", "remaining_time": "2:24:29", "throughput": 1485.23, "total_tokens": 25489440} {"current_steps": 120790, "total_steps": 181800, "loss": 0.0014, "lr": 1.52794630738877e-05, "epoch": 13.288228822882289, "percentage": 66.44, "elapsed_time": "4:46:02", "remaining_time": "2:24:28", "throughput": 1485.23, "total_tokens": 25490528} {"current_steps": 120795, "total_steps": 181800, "loss": 0.0405, "lr": 1.5277251904806865e-05, "epoch": 13.288778877887788, "percentage": 66.44, "elapsed_time": "4:46:03", "remaining_time": "2:24:28", "throughput": 1485.23, "total_tokens": 25491616} {"current_steps": 120800, "total_steps": 181800, "loss": 0.01, "lr": 1.5275040825335922e-05, "epoch": 13.289328932893289, "percentage": 66.45, "elapsed_time": "4:46:04", "remaining_time": "2:24:27", "throughput": 1485.24, "total_tokens": 25492736} {"current_steps": 120805, "total_steps": 181800, "loss": 0.1441, "lr": 1.5272829835495267e-05, "epoch": 13.28987898789879, "percentage": 66.45, "elapsed_time": "4:46:04", "remaining_time": "2:24:26", "throughput": 1485.24, "total_tokens": 25493728} {"current_steps": 120810, "total_steps": 181800, "loss": 0.0643, "lr": 1.5270618935305278e-05, "epoch": 13.290429042904291, "percentage": 66.45, "elapsed_time": "4:46:05", "remaining_time": "2:24:25", "throughput": 1485.24, "total_tokens": 25494752} {"current_steps": 120815, "total_steps": 181800, "loss": 0.081, "lr": 1.5268408124786316e-05, "epoch": 13.29097909790979, "percentage": 66.45, "elapsed_time": "4:46:06", "remaining_time": "2:24:25", "throughput": 1485.24, "total_tokens": 25495808} {"current_steps": 120820, "total_steps": 181800, "loss": 0.006, "lr": 1.5266197403958772e-05, "epoch": 13.291529152915292, "percentage": 66.46, "elapsed_time": "4:46:06", "remaining_time": "2:24:24", "throughput": 1485.24, "total_tokens": 25496896} {"current_steps": 120825, "total_steps": 181800, "loss": 0.0088, "lr": 1.526398677284301e-05, "epoch": 13.292079207920793, "percentage": 66.46, "elapsed_time": "4:46:07", "remaining_time": "2:24:23", "throughput": 1485.24, "total_tokens": 25497952} {"current_steps": 120830, "total_steps": 181800, "loss": 0.0029, "lr": 1.526177623145941e-05, "epoch": 13.292629262926292, "percentage": 66.46, "elapsed_time": "4:46:08", "remaining_time": "2:24:22", "throughput": 1485.25, "total_tokens": 25499008} {"current_steps": 120835, "total_steps": 181800, "loss": 0.0233, "lr": 1.5259565779828357e-05, "epoch": 13.293179317931793, "percentage": 66.47, "elapsed_time": "4:46:08", "remaining_time": "2:24:22", "throughput": 1485.24, "total_tokens": 25500000} {"current_steps": 120840, "total_steps": 181800, "loss": 0.0053, "lr": 1.5257355417970201e-05, "epoch": 13.293729372937294, "percentage": 66.47, "elapsed_time": "4:46:09", "remaining_time": "2:24:21", "throughput": 1485.25, "total_tokens": 25501056} {"current_steps": 120845, "total_steps": 181800, "loss": 0.0174, "lr": 1.525514514590533e-05, "epoch": 13.294279427942794, "percentage": 66.47, "elapsed_time": "4:46:10", "remaining_time": "2:24:20", "throughput": 1485.25, "total_tokens": 25502080} {"current_steps": 120850, "total_steps": 181800, "loss": 0.0162, "lr": 1.5252934963654114e-05, "epoch": 13.294829482948295, "percentage": 66.47, "elapsed_time": "4:46:10", "remaining_time": "2:24:20", "throughput": 1485.25, "total_tokens": 25503136} {"current_steps": 120855, "total_steps": 181800, "loss": 0.0037, "lr": 1.525072487123691e-05, "epoch": 13.295379537953796, "percentage": 66.48, "elapsed_time": "4:46:11", "remaining_time": "2:24:19", "throughput": 1485.25, "total_tokens": 25504128} {"current_steps": 120860, "total_steps": 181800, "loss": 0.0072, "lr": 1.5248514868674102e-05, "epoch": 13.295929592959295, "percentage": 66.48, "elapsed_time": "4:46:12", "remaining_time": "2:24:18", "throughput": 1485.25, "total_tokens": 25505152} {"current_steps": 120865, "total_steps": 181800, "loss": 0.003, "lr": 1.5246304955986046e-05, "epoch": 13.296479647964796, "percentage": 66.48, "elapsed_time": "4:46:13", "remaining_time": "2:24:17", "throughput": 1485.25, "total_tokens": 25506240} {"current_steps": 120870, "total_steps": 181800, "loss": 0.0293, "lr": 1.524409513319313e-05, "epoch": 13.297029702970297, "percentage": 66.49, "elapsed_time": "4:46:13", "remaining_time": "2:24:17", "throughput": 1485.25, "total_tokens": 25507296} {"current_steps": 120875, "total_steps": 181800, "loss": 0.0829, "lr": 1.5241885400315704e-05, "epoch": 13.297579757975798, "percentage": 66.49, "elapsed_time": "4:46:14", "remaining_time": "2:24:16", "throughput": 1485.25, "total_tokens": 25508320} {"current_steps": 120880, "total_steps": 181800, "loss": 0.0747, "lr": 1.5239675757374128e-05, "epoch": 13.298129812981298, "percentage": 66.49, "elapsed_time": "4:46:15", "remaining_time": "2:24:15", "throughput": 1485.25, "total_tokens": 25509408} {"current_steps": 120885, "total_steps": 181800, "loss": 0.0035, "lr": 1.5237466204388789e-05, "epoch": 13.298679867986799, "percentage": 66.49, "elapsed_time": "4:46:15", "remaining_time": "2:24:15", "throughput": 1485.26, "total_tokens": 25510464} {"current_steps": 120890, "total_steps": 181800, "loss": 0.0324, "lr": 1.5235256741380027e-05, "epoch": 13.2992299229923, "percentage": 66.5, "elapsed_time": "4:46:16", "remaining_time": "2:24:14", "throughput": 1485.26, "total_tokens": 25511552} {"current_steps": 120895, "total_steps": 181800, "loss": 0.1104, "lr": 1.523304736836823e-05, "epoch": 13.2997799779978, "percentage": 66.5, "elapsed_time": "4:46:17", "remaining_time": "2:24:13", "throughput": 1485.27, "total_tokens": 25512704} {"current_steps": 120900, "total_steps": 181800, "loss": 0.0338, "lr": 1.5230838085373747e-05, "epoch": 13.3003300330033, "percentage": 66.5, "elapsed_time": "4:46:17", "remaining_time": "2:24:12", "throughput": 1485.27, "total_tokens": 25513792} {"current_steps": 120905, "total_steps": 181800, "loss": 0.0042, "lr": 1.5228628892416935e-05, "epoch": 13.300880088008801, "percentage": 66.5, "elapsed_time": "4:46:18", "remaining_time": "2:24:12", "throughput": 1485.27, "total_tokens": 25514848} {"current_steps": 120910, "total_steps": 181800, "loss": 0.0029, "lr": 1.522641978951817e-05, "epoch": 13.3014301430143, "percentage": 66.51, "elapsed_time": "4:46:19", "remaining_time": "2:24:11", "throughput": 1485.28, "total_tokens": 25515936} {"current_steps": 120915, "total_steps": 181800, "loss": 0.0916, "lr": 1.5224210776697794e-05, "epoch": 13.301980198019802, "percentage": 66.51, "elapsed_time": "4:46:19", "remaining_time": "2:24:10", "throughput": 1485.28, "total_tokens": 25516960} {"current_steps": 120920, "total_steps": 181800, "loss": 0.0339, "lr": 1.5222001853976187e-05, "epoch": 13.302530253025303, "percentage": 66.51, "elapsed_time": "4:46:20", "remaining_time": "2:24:09", "throughput": 1485.28, "total_tokens": 25518048} {"current_steps": 120925, "total_steps": 181800, "loss": 0.0221, "lr": 1.5219793021373696e-05, "epoch": 13.303080308030804, "percentage": 66.52, "elapsed_time": "4:46:21", "remaining_time": "2:24:09", "throughput": 1485.29, "total_tokens": 25519168} {"current_steps": 120930, "total_steps": 181800, "loss": 0.0036, "lr": 1.5217584278910674e-05, "epoch": 13.303630363036303, "percentage": 66.52, "elapsed_time": "4:46:22", "remaining_time": "2:24:08", "throughput": 1485.29, "total_tokens": 25520224} {"current_steps": 120935, "total_steps": 181800, "loss": 0.013, "lr": 1.5215375626607483e-05, "epoch": 13.304180418041804, "percentage": 66.52, "elapsed_time": "4:46:22", "remaining_time": "2:24:07", "throughput": 1485.29, "total_tokens": 25521312} {"current_steps": 120940, "total_steps": 181800, "loss": 0.006, "lr": 1.521316706448448e-05, "epoch": 13.304730473047305, "percentage": 66.52, "elapsed_time": "4:46:23", "remaining_time": "2:24:07", "throughput": 1485.29, "total_tokens": 25522336} {"current_steps": 120945, "total_steps": 181800, "loss": 0.0062, "lr": 1.5210958592562021e-05, "epoch": 13.305280528052805, "percentage": 66.53, "elapsed_time": "4:46:24", "remaining_time": "2:24:06", "throughput": 1485.29, "total_tokens": 25523424} {"current_steps": 120950, "total_steps": 181800, "loss": 0.0099, "lr": 1.5208750210860467e-05, "epoch": 13.305830583058306, "percentage": 66.53, "elapsed_time": "4:46:24", "remaining_time": "2:24:05", "throughput": 1485.29, "total_tokens": 25524448} {"current_steps": 120955, "total_steps": 181800, "loss": 0.0031, "lr": 1.5206541919400152e-05, "epoch": 13.306380638063807, "percentage": 66.53, "elapsed_time": "4:46:25", "remaining_time": "2:24:04", "throughput": 1485.3, "total_tokens": 25525504} {"current_steps": 120960, "total_steps": 181800, "loss": 0.021, "lr": 1.5204333718201446e-05, "epoch": 13.306930693069306, "percentage": 66.53, "elapsed_time": "4:46:26", "remaining_time": "2:24:04", "throughput": 1485.3, "total_tokens": 25526560} {"current_steps": 120965, "total_steps": 181800, "loss": 0.0074, "lr": 1.5202125607284694e-05, "epoch": 13.307480748074807, "percentage": 66.54, "elapsed_time": "4:46:26", "remaining_time": "2:24:03", "throughput": 1485.3, "total_tokens": 25527584} {"current_steps": 120970, "total_steps": 181800, "loss": 0.1107, "lr": 1.5199917586670257e-05, "epoch": 13.308030803080309, "percentage": 66.54, "elapsed_time": "4:46:27", "remaining_time": "2:24:02", "throughput": 1485.3, "total_tokens": 25528672} {"current_steps": 120975, "total_steps": 181800, "loss": 0.0056, "lr": 1.5197709656378473e-05, "epoch": 13.308580858085808, "percentage": 66.54, "elapsed_time": "4:46:28", "remaining_time": "2:24:02", "throughput": 1485.31, "total_tokens": 25529760} {"current_steps": 120980, "total_steps": 181800, "loss": 0.1075, "lr": 1.5195501816429686e-05, "epoch": 13.309130913091309, "percentage": 66.55, "elapsed_time": "4:46:28", "remaining_time": "2:24:01", "throughput": 1485.31, "total_tokens": 25530848} {"current_steps": 120985, "total_steps": 181800, "loss": 0.0083, "lr": 1.5193294066844268e-05, "epoch": 13.30968096809681, "percentage": 66.55, "elapsed_time": "4:46:29", "remaining_time": "2:24:00", "throughput": 1485.31, "total_tokens": 25531936} {"current_steps": 120990, "total_steps": 181800, "loss": 0.1361, "lr": 1.519108640764254e-05, "epoch": 13.310231023102311, "percentage": 66.55, "elapsed_time": "4:46:30", "remaining_time": "2:23:59", "throughput": 1485.31, "total_tokens": 25532928} {"current_steps": 120995, "total_steps": 181800, "loss": 0.0704, "lr": 1.5188878838844872e-05, "epoch": 13.31078107810781, "percentage": 66.55, "elapsed_time": "4:46:30", "remaining_time": "2:23:59", "throughput": 1485.31, "total_tokens": 25533952} {"current_steps": 121000, "total_steps": 181800, "loss": 0.0666, "lr": 1.5186671360471602e-05, "epoch": 13.311331133113312, "percentage": 66.56, "elapsed_time": "4:46:31", "remaining_time": "2:23:58", "throughput": 1485.32, "total_tokens": 25535072} {"current_steps": 121005, "total_steps": 181800, "loss": 0.0653, "lr": 1.5184463972543056e-05, "epoch": 13.311881188118813, "percentage": 66.56, "elapsed_time": "4:46:32", "remaining_time": "2:23:57", "throughput": 1485.32, "total_tokens": 25536096} {"current_steps": 121010, "total_steps": 181800, "loss": 0.0017, "lr": 1.5182256675079614e-05, "epoch": 13.312431243124312, "percentage": 66.56, "elapsed_time": "4:46:33", "remaining_time": "2:23:57", "throughput": 1485.32, "total_tokens": 25537184} {"current_steps": 121015, "total_steps": 181800, "loss": 0.0665, "lr": 1.518004946810159e-05, "epoch": 13.312981298129813, "percentage": 66.56, "elapsed_time": "4:46:33", "remaining_time": "2:23:56", "throughput": 1485.32, "total_tokens": 25538176} {"current_steps": 121020, "total_steps": 181800, "loss": 0.0068, "lr": 1.5177842351629344e-05, "epoch": 13.313531353135314, "percentage": 66.57, "elapsed_time": "4:46:34", "remaining_time": "2:23:55", "throughput": 1485.32, "total_tokens": 25539232} {"current_steps": 121025, "total_steps": 181800, "loss": 0.113, "lr": 1.5175635325683213e-05, "epoch": 13.314081408140813, "percentage": 66.57, "elapsed_time": "4:46:35", "remaining_time": "2:23:54", "throughput": 1485.32, "total_tokens": 25540288} {"current_steps": 121030, "total_steps": 181800, "loss": 0.0431, "lr": 1.5173428390283532e-05, "epoch": 13.314631463146315, "percentage": 66.57, "elapsed_time": "4:46:35", "remaining_time": "2:23:54", "throughput": 1485.33, "total_tokens": 25541376} {"current_steps": 121035, "total_steps": 181800, "loss": 0.0144, "lr": 1.5171221545450648e-05, "epoch": 13.315181518151816, "percentage": 66.58, "elapsed_time": "4:46:36", "remaining_time": "2:23:53", "throughput": 1485.33, "total_tokens": 25542400} {"current_steps": 121040, "total_steps": 181800, "loss": 0.008, "lr": 1.5169014791204894e-05, "epoch": 13.315731573157315, "percentage": 66.58, "elapsed_time": "4:46:37", "remaining_time": "2:23:52", "throughput": 1485.32, "total_tokens": 25543392} {"current_steps": 121045, "total_steps": 181800, "loss": 0.003, "lr": 1.5166808127566625e-05, "epoch": 13.316281628162816, "percentage": 66.58, "elapsed_time": "4:46:37", "remaining_time": "2:23:51", "throughput": 1485.32, "total_tokens": 25544416} {"current_steps": 121050, "total_steps": 181800, "loss": 0.0367, "lr": 1.5164601554556162e-05, "epoch": 13.316831683168317, "percentage": 66.58, "elapsed_time": "4:46:38", "remaining_time": "2:23:51", "throughput": 1485.32, "total_tokens": 25545408} {"current_steps": 121055, "total_steps": 181800, "loss": 0.0054, "lr": 1.5162395072193842e-05, "epoch": 13.317381738173818, "percentage": 66.59, "elapsed_time": "4:46:39", "remaining_time": "2:23:50", "throughput": 1485.32, "total_tokens": 25546464} {"current_steps": 121060, "total_steps": 181800, "loss": 0.0032, "lr": 1.5160188680500015e-05, "epoch": 13.317931793179318, "percentage": 66.59, "elapsed_time": "4:46:39", "remaining_time": "2:23:49", "throughput": 1485.33, "total_tokens": 25547584} {"current_steps": 121065, "total_steps": 181800, "loss": 0.0094, "lr": 1.5157982379495001e-05, "epoch": 13.318481848184819, "percentage": 66.59, "elapsed_time": "4:46:40", "remaining_time": "2:23:49", "throughput": 1485.33, "total_tokens": 25548640} {"current_steps": 121070, "total_steps": 181800, "loss": 0.0051, "lr": 1.5155776169199137e-05, "epoch": 13.31903190319032, "percentage": 66.6, "elapsed_time": "4:46:41", "remaining_time": "2:23:48", "throughput": 1485.33, "total_tokens": 25549600} {"current_steps": 121075, "total_steps": 181800, "loss": 0.0242, "lr": 1.5153570049632764e-05, "epoch": 13.319581958195819, "percentage": 66.6, "elapsed_time": "4:46:42", "remaining_time": "2:23:47", "throughput": 1485.33, "total_tokens": 25550624} {"current_steps": 121080, "total_steps": 181800, "loss": 0.0026, "lr": 1.5151364020816211e-05, "epoch": 13.32013201320132, "percentage": 66.6, "elapsed_time": "4:46:42", "remaining_time": "2:23:46", "throughput": 1485.33, "total_tokens": 25551744} {"current_steps": 121085, "total_steps": 181800, "loss": 0.0055, "lr": 1.5149158082769816e-05, "epoch": 13.320682068206821, "percentage": 66.6, "elapsed_time": "4:46:43", "remaining_time": "2:23:46", "throughput": 1485.33, "total_tokens": 25552768} {"current_steps": 121090, "total_steps": 181800, "loss": 0.0061, "lr": 1.51469522355139e-05, "epoch": 13.32123212321232, "percentage": 66.61, "elapsed_time": "4:46:44", "remaining_time": "2:23:45", "throughput": 1485.33, "total_tokens": 25553792} {"current_steps": 121095, "total_steps": 181800, "loss": 0.0243, "lr": 1.5144746479068789e-05, "epoch": 13.321782178217822, "percentage": 66.61, "elapsed_time": "4:46:44", "remaining_time": "2:23:44", "throughput": 1485.34, "total_tokens": 25554880} {"current_steps": 121100, "total_steps": 181800, "loss": 0.0039, "lr": 1.5142540813454836e-05, "epoch": 13.322332233223323, "percentage": 66.61, "elapsed_time": "4:46:45", "remaining_time": "2:23:44", "throughput": 1485.34, "total_tokens": 25555904} {"current_steps": 121105, "total_steps": 181800, "loss": 0.0009, "lr": 1.514033523869234e-05, "epoch": 13.322882288228822, "percentage": 66.61, "elapsed_time": "4:46:46", "remaining_time": "2:23:43", "throughput": 1485.34, "total_tokens": 25556896} {"current_steps": 121110, "total_steps": 181800, "loss": 0.0061, "lr": 1.513812975480165e-05, "epoch": 13.323432343234323, "percentage": 66.62, "elapsed_time": "4:46:46", "remaining_time": "2:23:42", "throughput": 1485.34, "total_tokens": 25557984} {"current_steps": 121115, "total_steps": 181800, "loss": 0.0058, "lr": 1.5135924361803092e-05, "epoch": 13.323982398239824, "percentage": 66.62, "elapsed_time": "4:46:47", "remaining_time": "2:23:41", "throughput": 1485.34, "total_tokens": 25559072} {"current_steps": 121120, "total_steps": 181800, "loss": 0.0154, "lr": 1.5133719059716976e-05, "epoch": 13.324532453245325, "percentage": 66.62, "elapsed_time": "4:46:48", "remaining_time": "2:23:41", "throughput": 1485.34, "total_tokens": 25560096} {"current_steps": 121125, "total_steps": 181800, "loss": 0.0221, "lr": 1.5131513848563639e-05, "epoch": 13.325082508250825, "percentage": 66.63, "elapsed_time": "4:46:48", "remaining_time": "2:23:40", "throughput": 1485.35, "total_tokens": 25561184} {"current_steps": 121130, "total_steps": 181800, "loss": 0.1125, "lr": 1.51293087283634e-05, "epoch": 13.325632563256326, "percentage": 66.63, "elapsed_time": "4:46:49", "remaining_time": "2:23:39", "throughput": 1485.35, "total_tokens": 25562208} {"current_steps": 121135, "total_steps": 181800, "loss": 0.0082, "lr": 1.5127103699136591e-05, "epoch": 13.326182618261827, "percentage": 66.63, "elapsed_time": "4:46:50", "remaining_time": "2:23:38", "throughput": 1485.34, "total_tokens": 25563200} {"current_steps": 121140, "total_steps": 181800, "loss": 0.0291, "lr": 1.5124898760903536e-05, "epoch": 13.326732673267326, "percentage": 66.63, "elapsed_time": "4:46:50", "remaining_time": "2:23:38", "throughput": 1485.35, "total_tokens": 25564288} {"current_steps": 121145, "total_steps": 181800, "loss": 0.0259, "lr": 1.5122693913684538e-05, "epoch": 13.327282728272827, "percentage": 66.64, "elapsed_time": "4:46:51", "remaining_time": "2:23:37", "throughput": 1485.35, "total_tokens": 25565280} {"current_steps": 121150, "total_steps": 181800, "loss": 0.0078, "lr": 1.5120489157499939e-05, "epoch": 13.327832783278328, "percentage": 66.64, "elapsed_time": "4:46:52", "remaining_time": "2:23:36", "throughput": 1485.34, "total_tokens": 25566272} {"current_steps": 121155, "total_steps": 181800, "loss": 0.0795, "lr": 1.5118284492370044e-05, "epoch": 13.328382838283828, "percentage": 66.64, "elapsed_time": "4:46:53", "remaining_time": "2:23:36", "throughput": 1485.35, "total_tokens": 25567392} {"current_steps": 121160, "total_steps": 181800, "loss": 0.0799, "lr": 1.511607991831519e-05, "epoch": 13.328932893289329, "percentage": 66.64, "elapsed_time": "4:46:53", "remaining_time": "2:23:35", "throughput": 1485.35, "total_tokens": 25568512} {"current_steps": 121165, "total_steps": 181800, "loss": 0.0346, "lr": 1.511387543535568e-05, "epoch": 13.32948294829483, "percentage": 66.65, "elapsed_time": "4:46:54", "remaining_time": "2:23:34", "throughput": 1485.36, "total_tokens": 25569568} {"current_steps": 121170, "total_steps": 181800, "loss": 0.0042, "lr": 1.5111671043511827e-05, "epoch": 13.33003300330033, "percentage": 66.65, "elapsed_time": "4:46:55", "remaining_time": "2:23:33", "throughput": 1485.36, "total_tokens": 25570624} {"current_steps": 121175, "total_steps": 181800, "loss": 0.0017, "lr": 1.5109466742803971e-05, "epoch": 13.33058305830583, "percentage": 66.65, "elapsed_time": "4:46:55", "remaining_time": "2:23:33", "throughput": 1485.36, "total_tokens": 25571648} {"current_steps": 121180, "total_steps": 181800, "loss": 0.0392, "lr": 1.5107262533252404e-05, "epoch": 13.331133113311331, "percentage": 66.66, "elapsed_time": "4:46:56", "remaining_time": "2:23:32", "throughput": 1485.36, "total_tokens": 25572736} {"current_steps": 121185, "total_steps": 181800, "loss": 0.0007, "lr": 1.5105058414877455e-05, "epoch": 13.331683168316832, "percentage": 66.66, "elapsed_time": "4:46:57", "remaining_time": "2:23:31", "throughput": 1485.37, "total_tokens": 25573856} {"current_steps": 121190, "total_steps": 181800, "loss": 0.1529, "lr": 1.5102854387699436e-05, "epoch": 13.332233223322332, "percentage": 66.66, "elapsed_time": "4:46:57", "remaining_time": "2:23:31", "throughput": 1485.37, "total_tokens": 25574912} {"current_steps": 121195, "total_steps": 181800, "loss": 0.0009, "lr": 1.5100650451738652e-05, "epoch": 13.332783278327833, "percentage": 66.66, "elapsed_time": "4:46:58", "remaining_time": "2:23:30", "throughput": 1485.37, "total_tokens": 25575968} {"current_steps": 121200, "total_steps": 181800, "loss": 0.1967, "lr": 1.5098446607015435e-05, "epoch": 13.333333333333334, "percentage": 66.67, "elapsed_time": "4:46:59", "remaining_time": "2:23:29", "throughput": 1485.37, "total_tokens": 25577024} {"current_steps": 121205, "total_steps": 181800, "loss": 0.0035, "lr": 1.5096242853550072e-05, "epoch": 13.333883388338833, "percentage": 66.67, "elapsed_time": "4:46:59", "remaining_time": "2:23:28", "throughput": 1485.37, "total_tokens": 25578016} {"current_steps": 121210, "total_steps": 181800, "loss": 0.058, "lr": 1.5094039191362891e-05, "epoch": 13.334433443344334, "percentage": 66.67, "elapsed_time": "4:47:00", "remaining_time": "2:23:28", "throughput": 1485.37, "total_tokens": 25579104} {"current_steps": 121215, "total_steps": 181800, "loss": 0.0301, "lr": 1.5091835620474205e-05, "epoch": 13.334983498349835, "percentage": 66.67, "elapsed_time": "4:47:01", "remaining_time": "2:23:27", "throughput": 1485.38, "total_tokens": 25580160} {"current_steps": 121220, "total_steps": 181800, "loss": 0.0014, "lr": 1.5089632140904306e-05, "epoch": 13.335533553355335, "percentage": 66.68, "elapsed_time": "4:47:02", "remaining_time": "2:23:26", "throughput": 1485.38, "total_tokens": 25581184} {"current_steps": 121225, "total_steps": 181800, "loss": 0.0011, "lr": 1.5087428752673516e-05, "epoch": 13.336083608360836, "percentage": 66.68, "elapsed_time": "4:47:02", "remaining_time": "2:23:26", "throughput": 1485.38, "total_tokens": 25582240} {"current_steps": 121230, "total_steps": 181800, "loss": 0.0215, "lr": 1.5085225455802131e-05, "epoch": 13.336633663366337, "percentage": 66.68, "elapsed_time": "4:47:03", "remaining_time": "2:23:25", "throughput": 1485.38, "total_tokens": 25583360} {"current_steps": 121235, "total_steps": 181800, "loss": 0.0096, "lr": 1.508302225031048e-05, "epoch": 13.337183718371838, "percentage": 66.69, "elapsed_time": "4:47:04", "remaining_time": "2:23:24", "throughput": 1485.38, "total_tokens": 25584352} {"current_steps": 121240, "total_steps": 181800, "loss": 0.0022, "lr": 1.5080819136218846e-05, "epoch": 13.337733773377337, "percentage": 66.69, "elapsed_time": "4:47:04", "remaining_time": "2:23:23", "throughput": 1485.38, "total_tokens": 25585408} {"current_steps": 121245, "total_steps": 181800, "loss": 0.036, "lr": 1.5078616113547538e-05, "epoch": 13.338283828382838, "percentage": 66.69, "elapsed_time": "4:47:05", "remaining_time": "2:23:23", "throughput": 1485.39, "total_tokens": 25586496} {"current_steps": 121250, "total_steps": 181800, "loss": 0.0024, "lr": 1.507641318231687e-05, "epoch": 13.33883388338834, "percentage": 66.69, "elapsed_time": "4:47:06", "remaining_time": "2:23:22", "throughput": 1485.39, "total_tokens": 25587584} {"current_steps": 121255, "total_steps": 181800, "loss": 0.0028, "lr": 1.5074210342547145e-05, "epoch": 13.339383938393839, "percentage": 66.7, "elapsed_time": "4:47:06", "remaining_time": "2:23:21", "throughput": 1485.39, "total_tokens": 25588608} {"current_steps": 121260, "total_steps": 181800, "loss": 0.0218, "lr": 1.507200759425865e-05, "epoch": 13.33993399339934, "percentage": 66.7, "elapsed_time": "4:47:07", "remaining_time": "2:23:20", "throughput": 1485.39, "total_tokens": 25589664} {"current_steps": 121265, "total_steps": 181800, "loss": 0.0754, "lr": 1.5069804937471702e-05, "epoch": 13.340484048404841, "percentage": 66.7, "elapsed_time": "4:47:08", "remaining_time": "2:23:20", "throughput": 1485.4, "total_tokens": 25590752} {"current_steps": 121270, "total_steps": 181800, "loss": 0.0052, "lr": 1.506760237220659e-05, "epoch": 13.34103410341034, "percentage": 66.71, "elapsed_time": "4:47:08", "remaining_time": "2:23:19", "throughput": 1485.4, "total_tokens": 25591840} {"current_steps": 121275, "total_steps": 181800, "loss": 0.0036, "lr": 1.5065399898483635e-05, "epoch": 13.341584158415841, "percentage": 66.71, "elapsed_time": "4:47:09", "remaining_time": "2:23:18", "throughput": 1485.4, "total_tokens": 25592864} {"current_steps": 121280, "total_steps": 181800, "loss": 0.0036, "lr": 1.5063197516323116e-05, "epoch": 13.342134213421343, "percentage": 66.71, "elapsed_time": "4:47:10", "remaining_time": "2:23:18", "throughput": 1485.4, "total_tokens": 25593920} {"current_steps": 121285, "total_steps": 181800, "loss": 0.0022, "lr": 1.506099522574533e-05, "epoch": 13.342684268426842, "percentage": 66.71, "elapsed_time": "4:47:10", "remaining_time": "2:23:17", "throughput": 1485.4, "total_tokens": 25594944} {"current_steps": 121290, "total_steps": 181800, "loss": 0.0032, "lr": 1.5058793026770596e-05, "epoch": 13.343234323432343, "percentage": 66.72, "elapsed_time": "4:47:11", "remaining_time": "2:23:16", "throughput": 1485.4, "total_tokens": 25596000} {"current_steps": 121295, "total_steps": 181800, "loss": 0.0051, "lr": 1.5056590919419184e-05, "epoch": 13.343784378437844, "percentage": 66.72, "elapsed_time": "4:47:12", "remaining_time": "2:23:15", "throughput": 1485.41, "total_tokens": 25597056} {"current_steps": 121300, "total_steps": 181800, "loss": 0.002, "lr": 1.5054388903711406e-05, "epoch": 13.344334433443345, "percentage": 66.72, "elapsed_time": "4:47:13", "remaining_time": "2:23:15", "throughput": 1485.41, "total_tokens": 25598112} {"current_steps": 121305, "total_steps": 181800, "loss": 0.0114, "lr": 1.505218697966756e-05, "epoch": 13.344884488448844, "percentage": 66.72, "elapsed_time": "4:47:13", "remaining_time": "2:23:14", "throughput": 1485.41, "total_tokens": 25599200} {"current_steps": 121310, "total_steps": 181800, "loss": 0.0058, "lr": 1.5049985147307915e-05, "epoch": 13.345434543454346, "percentage": 66.73, "elapsed_time": "4:47:14", "remaining_time": "2:23:13", "throughput": 1485.41, "total_tokens": 25600224} {"current_steps": 121315, "total_steps": 181800, "loss": 0.0044, "lr": 1.5047783406652798e-05, "epoch": 13.345984598459847, "percentage": 66.73, "elapsed_time": "4:47:15", "remaining_time": "2:23:13", "throughput": 1485.41, "total_tokens": 25601216} {"current_steps": 121320, "total_steps": 181800, "loss": 0.013, "lr": 1.504558175772248e-05, "epoch": 13.346534653465346, "percentage": 66.73, "elapsed_time": "4:47:15", "remaining_time": "2:23:12", "throughput": 1485.41, "total_tokens": 25602240} {"current_steps": 121325, "total_steps": 181800, "loss": 0.2078, "lr": 1.504338020053726e-05, "epoch": 13.347084708470847, "percentage": 66.74, "elapsed_time": "4:47:16", "remaining_time": "2:23:11", "throughput": 1485.41, "total_tokens": 25603328} {"current_steps": 121330, "total_steps": 181800, "loss": 0.0496, "lr": 1.5041178735117434e-05, "epoch": 13.347634763476348, "percentage": 66.74, "elapsed_time": "4:47:17", "remaining_time": "2:23:10", "throughput": 1485.42, "total_tokens": 25604416} {"current_steps": 121335, "total_steps": 181800, "loss": 0.0011, "lr": 1.5038977361483272e-05, "epoch": 13.348184818481847, "percentage": 66.74, "elapsed_time": "4:47:17", "remaining_time": "2:23:10", "throughput": 1485.42, "total_tokens": 25605408} {"current_steps": 121340, "total_steps": 181800, "loss": 0.0406, "lr": 1.5036776079655084e-05, "epoch": 13.348734873487349, "percentage": 66.74, "elapsed_time": "4:47:18", "remaining_time": "2:23:09", "throughput": 1485.42, "total_tokens": 25606464} {"current_steps": 121345, "total_steps": 181800, "loss": 0.0028, "lr": 1.5034574889653142e-05, "epoch": 13.34928492849285, "percentage": 66.75, "elapsed_time": "4:47:19", "remaining_time": "2:23:08", "throughput": 1485.42, "total_tokens": 25607584} {"current_steps": 121350, "total_steps": 181800, "loss": 0.0294, "lr": 1.5032373791497754e-05, "epoch": 13.34983498349835, "percentage": 66.75, "elapsed_time": "4:47:19", "remaining_time": "2:23:08", "throughput": 1485.43, "total_tokens": 25608672} {"current_steps": 121355, "total_steps": 181800, "loss": 0.0043, "lr": 1.5030172785209187e-05, "epoch": 13.35038503850385, "percentage": 66.75, "elapsed_time": "4:47:20", "remaining_time": "2:23:07", "throughput": 1485.43, "total_tokens": 25609696} {"current_steps": 121360, "total_steps": 181800, "loss": 0.0495, "lr": 1.5027971870807727e-05, "epoch": 13.350935093509351, "percentage": 66.75, "elapsed_time": "4:47:21", "remaining_time": "2:23:06", "throughput": 1485.43, "total_tokens": 25610752} {"current_steps": 121365, "total_steps": 181800, "loss": 0.0014, "lr": 1.502577104831368e-05, "epoch": 13.351485148514852, "percentage": 66.76, "elapsed_time": "4:47:22", "remaining_time": "2:23:05", "throughput": 1485.43, "total_tokens": 25611808} {"current_steps": 121370, "total_steps": 181800, "loss": 0.0006, "lr": 1.50235703177473e-05, "epoch": 13.352035203520352, "percentage": 66.76, "elapsed_time": "4:47:22", "remaining_time": "2:23:05", "throughput": 1485.44, "total_tokens": 25612928} {"current_steps": 121375, "total_steps": 181800, "loss": 0.0008, "lr": 1.5021369679128894e-05, "epoch": 13.352585258525853, "percentage": 66.76, "elapsed_time": "4:47:23", "remaining_time": "2:23:04", "throughput": 1485.44, "total_tokens": 25613984} {"current_steps": 121380, "total_steps": 181800, "loss": 0.0031, "lr": 1.5019169132478737e-05, "epoch": 13.353135313531354, "percentage": 66.77, "elapsed_time": "4:47:24", "remaining_time": "2:23:03", "throughput": 1485.44, "total_tokens": 25615008} {"current_steps": 121385, "total_steps": 181800, "loss": 0.0043, "lr": 1.50169686778171e-05, "epoch": 13.353685368536853, "percentage": 66.77, "elapsed_time": "4:47:24", "remaining_time": "2:23:02", "throughput": 1485.44, "total_tokens": 25616000} {"current_steps": 121390, "total_steps": 181800, "loss": 0.0428, "lr": 1.5014768315164285e-05, "epoch": 13.354235423542354, "percentage": 66.77, "elapsed_time": "4:47:25", "remaining_time": "2:23:02", "throughput": 1485.44, "total_tokens": 25617088} {"current_steps": 121395, "total_steps": 181800, "loss": 0.0495, "lr": 1.5012568044540548e-05, "epoch": 13.354785478547855, "percentage": 66.77, "elapsed_time": "4:47:26", "remaining_time": "2:23:01", "throughput": 1485.44, "total_tokens": 25618112} {"current_steps": 121400, "total_steps": 181800, "loss": 0.1431, "lr": 1.5010367865966183e-05, "epoch": 13.355335533553355, "percentage": 66.78, "elapsed_time": "4:47:26", "remaining_time": "2:23:00", "throughput": 1485.44, "total_tokens": 25619168} {"current_steps": 121405, "total_steps": 181800, "loss": 0.0009, "lr": 1.5008167779461468e-05, "epoch": 13.355885588558856, "percentage": 66.78, "elapsed_time": "4:47:27", "remaining_time": "2:23:00", "throughput": 1485.45, "total_tokens": 25620288} {"current_steps": 121410, "total_steps": 181800, "loss": 0.0106, "lr": 1.5005967785046668e-05, "epoch": 13.356435643564357, "percentage": 66.78, "elapsed_time": "4:47:28", "remaining_time": "2:22:59", "throughput": 1485.45, "total_tokens": 25621344} {"current_steps": 121415, "total_steps": 181800, "loss": 0.0106, "lr": 1.500376788274207e-05, "epoch": 13.356985698569858, "percentage": 66.78, "elapsed_time": "4:47:28", "remaining_time": "2:22:58", "throughput": 1485.45, "total_tokens": 25622432} {"current_steps": 121420, "total_steps": 181800, "loss": 0.0465, "lr": 1.5001568072567945e-05, "epoch": 13.357535753575357, "percentage": 66.79, "elapsed_time": "4:47:29", "remaining_time": "2:22:57", "throughput": 1485.45, "total_tokens": 25623456} {"current_steps": 121425, "total_steps": 181800, "loss": 0.0016, "lr": 1.499936835454458e-05, "epoch": 13.358085808580858, "percentage": 66.79, "elapsed_time": "4:47:30", "remaining_time": "2:22:57", "throughput": 1485.45, "total_tokens": 25624480} {"current_steps": 121430, "total_steps": 181800, "loss": 0.0068, "lr": 1.499716872869223e-05, "epoch": 13.35863586358636, "percentage": 66.79, "elapsed_time": "4:47:30", "remaining_time": "2:22:56", "throughput": 1485.45, "total_tokens": 25625504} {"current_steps": 121435, "total_steps": 181800, "loss": 0.011, "lr": 1.4994969195031172e-05, "epoch": 13.359185918591859, "percentage": 66.8, "elapsed_time": "4:47:31", "remaining_time": "2:22:55", "throughput": 1485.45, "total_tokens": 25626560} {"current_steps": 121440, "total_steps": 181800, "loss": 0.0894, "lr": 1.4992769753581688e-05, "epoch": 13.35973597359736, "percentage": 66.8, "elapsed_time": "4:47:32", "remaining_time": "2:22:55", "throughput": 1485.46, "total_tokens": 25627648} {"current_steps": 121445, "total_steps": 181800, "loss": 0.129, "lr": 1.4990570404364045e-05, "epoch": 13.36028602860286, "percentage": 66.8, "elapsed_time": "4:47:33", "remaining_time": "2:22:54", "throughput": 1485.46, "total_tokens": 25628640} {"current_steps": 121450, "total_steps": 181800, "loss": 0.0395, "lr": 1.4988371147398506e-05, "epoch": 13.36083608360836, "percentage": 66.8, "elapsed_time": "4:47:33", "remaining_time": "2:22:53", "throughput": 1485.46, "total_tokens": 25629728} {"current_steps": 121455, "total_steps": 181800, "loss": 0.0089, "lr": 1.4986171982705346e-05, "epoch": 13.361386138613861, "percentage": 66.81, "elapsed_time": "4:47:34", "remaining_time": "2:22:52", "throughput": 1485.46, "total_tokens": 25630784} {"current_steps": 121460, "total_steps": 181800, "loss": 0.1135, "lr": 1.4983972910304834e-05, "epoch": 13.361936193619362, "percentage": 66.81, "elapsed_time": "4:47:35", "remaining_time": "2:22:52", "throughput": 1485.46, "total_tokens": 25631808} {"current_steps": 121465, "total_steps": 181800, "loss": 0.0037, "lr": 1.4981773930217243e-05, "epoch": 13.362486248624862, "percentage": 66.81, "elapsed_time": "4:47:35", "remaining_time": "2:22:51", "throughput": 1485.46, "total_tokens": 25632832} {"current_steps": 121470, "total_steps": 181800, "loss": 0.03, "lr": 1.4979575042462835e-05, "epoch": 13.363036303630363, "percentage": 66.82, "elapsed_time": "4:47:36", "remaining_time": "2:22:50", "throughput": 1485.47, "total_tokens": 25633920} {"current_steps": 121475, "total_steps": 181800, "loss": 0.0296, "lr": 1.4977376247061865e-05, "epoch": 13.363586358635864, "percentage": 66.82, "elapsed_time": "4:47:37", "remaining_time": "2:22:49", "throughput": 1485.47, "total_tokens": 25635008} {"current_steps": 121480, "total_steps": 181800, "loss": 0.0082, "lr": 1.497517754403462e-05, "epoch": 13.364136413641365, "percentage": 66.82, "elapsed_time": "4:47:37", "remaining_time": "2:22:49", "throughput": 1485.47, "total_tokens": 25636032} {"current_steps": 121485, "total_steps": 181800, "loss": 0.009, "lr": 1.4972978933401343e-05, "epoch": 13.364686468646864, "percentage": 66.82, "elapsed_time": "4:47:38", "remaining_time": "2:22:48", "throughput": 1485.47, "total_tokens": 25637088} {"current_steps": 121490, "total_steps": 181800, "loss": 0.0441, "lr": 1.4970780415182318e-05, "epoch": 13.365236523652365, "percentage": 66.83, "elapsed_time": "4:47:39", "remaining_time": "2:22:47", "throughput": 1485.47, "total_tokens": 25638176} {"current_steps": 121495, "total_steps": 181800, "loss": 0.017, "lr": 1.496858198939779e-05, "epoch": 13.365786578657866, "percentage": 66.83, "elapsed_time": "4:47:39", "remaining_time": "2:22:47", "throughput": 1485.48, "total_tokens": 25639328} {"current_steps": 121500, "total_steps": 181800, "loss": 0.0697, "lr": 1.4966383656068029e-05, "epoch": 13.366336633663366, "percentage": 66.83, "elapsed_time": "4:47:40", "remaining_time": "2:22:46", "throughput": 1485.49, "total_tokens": 25640448} {"current_steps": 121505, "total_steps": 181800, "loss": 0.0033, "lr": 1.4964185415213303e-05, "epoch": 13.366886688668867, "percentage": 66.83, "elapsed_time": "4:47:41", "remaining_time": "2:22:45", "throughput": 1485.49, "total_tokens": 25641472} {"current_steps": 121510, "total_steps": 181800, "loss": 0.0022, "lr": 1.4961987266853855e-05, "epoch": 13.367436743674368, "percentage": 66.84, "elapsed_time": "4:47:42", "remaining_time": "2:22:44", "throughput": 1485.49, "total_tokens": 25642528} {"current_steps": 121515, "total_steps": 181800, "loss": 0.0024, "lr": 1.4959789211009956e-05, "epoch": 13.367986798679867, "percentage": 66.84, "elapsed_time": "4:47:42", "remaining_time": "2:22:44", "throughput": 1485.49, "total_tokens": 25643552} {"current_steps": 121520, "total_steps": 181800, "loss": 0.0026, "lr": 1.4957591247701869e-05, "epoch": 13.368536853685368, "percentage": 66.84, "elapsed_time": "4:47:43", "remaining_time": "2:22:43", "throughput": 1485.49, "total_tokens": 25644576} {"current_steps": 121525, "total_steps": 181800, "loss": 0.001, "lr": 1.4955393376949833e-05, "epoch": 13.36908690869087, "percentage": 66.85, "elapsed_time": "4:47:44", "remaining_time": "2:22:42", "throughput": 1485.49, "total_tokens": 25645568} {"current_steps": 121530, "total_steps": 181800, "loss": 0.0661, "lr": 1.4953195598774125e-05, "epoch": 13.369636963696369, "percentage": 66.85, "elapsed_time": "4:47:44", "remaining_time": "2:22:42", "throughput": 1485.49, "total_tokens": 25646592} {"current_steps": 121535, "total_steps": 181800, "loss": 0.2027, "lr": 1.4950997913194987e-05, "epoch": 13.37018701870187, "percentage": 66.85, "elapsed_time": "4:47:45", "remaining_time": "2:22:41", "throughput": 1485.49, "total_tokens": 25647584} {"current_steps": 121540, "total_steps": 181800, "loss": 0.0076, "lr": 1.4948800320232686e-05, "epoch": 13.370737073707371, "percentage": 66.85, "elapsed_time": "4:47:46", "remaining_time": "2:22:40", "throughput": 1485.49, "total_tokens": 25648608} {"current_steps": 121545, "total_steps": 181800, "loss": 0.0239, "lr": 1.4946602819907468e-05, "epoch": 13.371287128712872, "percentage": 66.86, "elapsed_time": "4:47:46", "remaining_time": "2:22:39", "throughput": 1485.49, "total_tokens": 25649664} {"current_steps": 121550, "total_steps": 181800, "loss": 0.007, "lr": 1.494440541223958e-05, "epoch": 13.371837183718371, "percentage": 66.86, "elapsed_time": "4:47:47", "remaining_time": "2:22:39", "throughput": 1485.49, "total_tokens": 25650720} {"current_steps": 121555, "total_steps": 181800, "loss": 0.0532, "lr": 1.4942208097249288e-05, "epoch": 13.372387238723872, "percentage": 66.86, "elapsed_time": "4:47:48", "remaining_time": "2:22:38", "throughput": 1485.49, "total_tokens": 25651776} {"current_steps": 121560, "total_steps": 181800, "loss": 0.0231, "lr": 1.494001087495683e-05, "epoch": 13.372937293729374, "percentage": 66.86, "elapsed_time": "4:47:48", "remaining_time": "2:22:37", "throughput": 1485.49, "total_tokens": 25652832} {"current_steps": 121565, "total_steps": 181800, "loss": 0.0019, "lr": 1.4937813745382478e-05, "epoch": 13.373487348734873, "percentage": 66.87, "elapsed_time": "4:47:49", "remaining_time": "2:22:37", "throughput": 1485.5, "total_tokens": 25653920} {"current_steps": 121570, "total_steps": 181800, "loss": 0.0037, "lr": 1.4935616708546462e-05, "epoch": 13.374037403740374, "percentage": 66.87, "elapsed_time": "4:47:50", "remaining_time": "2:22:36", "throughput": 1485.5, "total_tokens": 25654976} {"current_steps": 121575, "total_steps": 181800, "loss": 0.004, "lr": 1.4933419764469034e-05, "epoch": 13.374587458745875, "percentage": 66.87, "elapsed_time": "4:47:50", "remaining_time": "2:22:35", "throughput": 1485.5, "total_tokens": 25655968} {"current_steps": 121580, "total_steps": 181800, "loss": 0.0454, "lr": 1.4931222913170456e-05, "epoch": 13.375137513751374, "percentage": 66.88, "elapsed_time": "4:47:51", "remaining_time": "2:22:34", "throughput": 1485.5, "total_tokens": 25656992} {"current_steps": 121585, "total_steps": 181800, "loss": 0.1798, "lr": 1.4929026154670952e-05, "epoch": 13.375687568756875, "percentage": 66.88, "elapsed_time": "4:47:52", "remaining_time": "2:22:34", "throughput": 1485.5, "total_tokens": 25658048} {"current_steps": 121590, "total_steps": 181800, "loss": 0.008, "lr": 1.492682948899079e-05, "epoch": 13.376237623762377, "percentage": 66.88, "elapsed_time": "4:47:53", "remaining_time": "2:22:33", "throughput": 1485.5, "total_tokens": 25659104} {"current_steps": 121595, "total_steps": 181800, "loss": 0.0013, "lr": 1.4924632916150208e-05, "epoch": 13.376787678767876, "percentage": 66.88, "elapsed_time": "4:47:53", "remaining_time": "2:22:32", "throughput": 1485.51, "total_tokens": 25660192} {"current_steps": 121600, "total_steps": 181800, "loss": 0.005, "lr": 1.492243643616944e-05, "epoch": 13.377337733773377, "percentage": 66.89, "elapsed_time": "4:47:54", "remaining_time": "2:22:31", "throughput": 1485.51, "total_tokens": 25661216} {"current_steps": 121605, "total_steps": 181800, "loss": 0.0198, "lr": 1.4920240049068748e-05, "epoch": 13.377887788778878, "percentage": 66.89, "elapsed_time": "4:47:55", "remaining_time": "2:22:31", "throughput": 1485.5, "total_tokens": 25662240} {"current_steps": 121610, "total_steps": 181800, "loss": 0.0492, "lr": 1.491804375486836e-05, "epoch": 13.37843784378438, "percentage": 66.89, "elapsed_time": "4:47:55", "remaining_time": "2:22:30", "throughput": 1485.51, "total_tokens": 25663296} {"current_steps": 121615, "total_steps": 181800, "loss": 0.0076, "lr": 1.491584755358853e-05, "epoch": 13.378987898789878, "percentage": 66.89, "elapsed_time": "4:47:56", "remaining_time": "2:22:29", "throughput": 1485.51, "total_tokens": 25664352} {"current_steps": 121620, "total_steps": 181800, "loss": 0.0038, "lr": 1.49136514452495e-05, "epoch": 13.37953795379538, "percentage": 66.9, "elapsed_time": "4:47:57", "remaining_time": "2:22:29", "throughput": 1485.51, "total_tokens": 25665376} {"current_steps": 121625, "total_steps": 181800, "loss": 0.0512, "lr": 1.4911455429871496e-05, "epoch": 13.38008800880088, "percentage": 66.9, "elapsed_time": "4:47:57", "remaining_time": "2:22:28", "throughput": 1485.51, "total_tokens": 25666464} {"current_steps": 121630, "total_steps": 181800, "loss": 0.0478, "lr": 1.4909259507474765e-05, "epoch": 13.38063806380638, "percentage": 66.9, "elapsed_time": "4:47:58", "remaining_time": "2:22:27", "throughput": 1485.51, "total_tokens": 25667520} {"current_steps": 121635, "total_steps": 181800, "loss": 0.0046, "lr": 1.4907063678079558e-05, "epoch": 13.381188118811881, "percentage": 66.91, "elapsed_time": "4:47:59", "remaining_time": "2:22:26", "throughput": 1485.51, "total_tokens": 25668512} {"current_steps": 121640, "total_steps": 181800, "loss": 0.0453, "lr": 1.490486794170609e-05, "epoch": 13.381738173817382, "percentage": 66.91, "elapsed_time": "4:47:59", "remaining_time": "2:22:26", "throughput": 1485.52, "total_tokens": 25669664} {"current_steps": 121645, "total_steps": 181800, "loss": 0.1394, "lr": 1.4902672298374617e-05, "epoch": 13.382288228822881, "percentage": 66.91, "elapsed_time": "4:48:00", "remaining_time": "2:22:25", "throughput": 1485.53, "total_tokens": 25670816} {"current_steps": 121650, "total_steps": 181800, "loss": 0.0635, "lr": 1.4900476748105362e-05, "epoch": 13.382838283828383, "percentage": 66.91, "elapsed_time": "4:48:01", "remaining_time": "2:22:24", "throughput": 1485.53, "total_tokens": 25671840} {"current_steps": 121655, "total_steps": 181800, "loss": 0.0361, "lr": 1.4898281290918576e-05, "epoch": 13.383388338833884, "percentage": 66.92, "elapsed_time": "4:48:02", "remaining_time": "2:22:24", "throughput": 1485.53, "total_tokens": 25673024} {"current_steps": 121660, "total_steps": 181800, "loss": 0.0038, "lr": 1.489608592683448e-05, "epoch": 13.383938393839385, "percentage": 66.92, "elapsed_time": "4:48:02", "remaining_time": "2:22:23", "throughput": 1485.54, "total_tokens": 25674112} {"current_steps": 121665, "total_steps": 181800, "loss": 0.0041, "lr": 1.4893890655873306e-05, "epoch": 13.384488448844884, "percentage": 66.92, "elapsed_time": "4:48:03", "remaining_time": "2:22:22", "throughput": 1485.54, "total_tokens": 25675168} {"current_steps": 121670, "total_steps": 181800, "loss": 0.0484, "lr": 1.4891695478055304e-05, "epoch": 13.385038503850385, "percentage": 66.93, "elapsed_time": "4:48:04", "remaining_time": "2:22:21", "throughput": 1485.54, "total_tokens": 25676192} {"current_steps": 121675, "total_steps": 181800, "loss": 0.0117, "lr": 1.4889500393400677e-05, "epoch": 13.385588558855886, "percentage": 66.93, "elapsed_time": "4:48:04", "remaining_time": "2:22:21", "throughput": 1485.54, "total_tokens": 25677216} {"current_steps": 121680, "total_steps": 181800, "loss": 0.0014, "lr": 1.488730540192969e-05, "epoch": 13.386138613861386, "percentage": 66.93, "elapsed_time": "4:48:05", "remaining_time": "2:22:20", "throughput": 1485.54, "total_tokens": 25678304} {"current_steps": 121685, "total_steps": 181800, "loss": 0.0182, "lr": 1.488511050366255e-05, "epoch": 13.386688668866887, "percentage": 66.93, "elapsed_time": "4:48:06", "remaining_time": "2:22:19", "throughput": 1485.55, "total_tokens": 25679360} {"current_steps": 121690, "total_steps": 181800, "loss": 0.0785, "lr": 1.4882915698619487e-05, "epoch": 13.387238723872388, "percentage": 66.94, "elapsed_time": "4:48:06", "remaining_time": "2:22:19", "throughput": 1485.55, "total_tokens": 25680448} {"current_steps": 121695, "total_steps": 181800, "loss": 0.0956, "lr": 1.488072098682075e-05, "epoch": 13.387788778877887, "percentage": 66.94, "elapsed_time": "4:48:07", "remaining_time": "2:22:18", "throughput": 1485.55, "total_tokens": 25681504} {"current_steps": 121700, "total_steps": 181800, "loss": 0.01, "lr": 1.4878526368286538e-05, "epoch": 13.388338833883388, "percentage": 66.94, "elapsed_time": "4:48:08", "remaining_time": "2:22:17", "throughput": 1485.55, "total_tokens": 25682528} {"current_steps": 121705, "total_steps": 181800, "loss": 0.0277, "lr": 1.48763318430371e-05, "epoch": 13.38888888888889, "percentage": 66.94, "elapsed_time": "4:48:08", "remaining_time": "2:22:16", "throughput": 1485.56, "total_tokens": 25683616} {"current_steps": 121710, "total_steps": 181800, "loss": 0.0783, "lr": 1.4874137411092653e-05, "epoch": 13.389438943894389, "percentage": 66.95, "elapsed_time": "4:48:09", "remaining_time": "2:22:16", "throughput": 1485.56, "total_tokens": 25684640} {"current_steps": 121715, "total_steps": 181800, "loss": 0.0404, "lr": 1.4871943072473418e-05, "epoch": 13.38998899889989, "percentage": 66.95, "elapsed_time": "4:48:10", "remaining_time": "2:22:15", "throughput": 1485.56, "total_tokens": 25685664} {"current_steps": 121720, "total_steps": 181800, "loss": 0.0036, "lr": 1.4869748827199626e-05, "epoch": 13.39053905390539, "percentage": 66.95, "elapsed_time": "4:48:10", "remaining_time": "2:22:14", "throughput": 1485.56, "total_tokens": 25686752} {"current_steps": 121725, "total_steps": 181800, "loss": 0.0466, "lr": 1.4867554675291495e-05, "epoch": 13.391089108910892, "percentage": 66.96, "elapsed_time": "4:48:11", "remaining_time": "2:22:13", "throughput": 1485.56, "total_tokens": 25687808} {"current_steps": 121730, "total_steps": 181800, "loss": 0.0011, "lr": 1.4865360616769259e-05, "epoch": 13.391639163916391, "percentage": 66.96, "elapsed_time": "4:48:12", "remaining_time": "2:22:13", "throughput": 1485.56, "total_tokens": 25688864} {"current_steps": 121735, "total_steps": 181800, "loss": 0.0018, "lr": 1.4863166651653126e-05, "epoch": 13.392189218921892, "percentage": 66.96, "elapsed_time": "4:48:13", "remaining_time": "2:22:12", "throughput": 1485.56, "total_tokens": 25689856} {"current_steps": 121740, "total_steps": 181800, "loss": 0.03, "lr": 1.4860972779963317e-05, "epoch": 13.392739273927393, "percentage": 66.96, "elapsed_time": "4:48:13", "remaining_time": "2:22:11", "throughput": 1485.56, "total_tokens": 25690912} {"current_steps": 121745, "total_steps": 181800, "loss": 0.0321, "lr": 1.4858779001720063e-05, "epoch": 13.393289328932893, "percentage": 66.97, "elapsed_time": "4:48:14", "remaining_time": "2:22:11", "throughput": 1485.56, "total_tokens": 25691872} {"current_steps": 121750, "total_steps": 181800, "loss": 0.0011, "lr": 1.4856585316943573e-05, "epoch": 13.393839383938394, "percentage": 66.97, "elapsed_time": "4:48:15", "remaining_time": "2:22:10", "throughput": 1485.56, "total_tokens": 25692928} {"current_steps": 121755, "total_steps": 181800, "loss": 0.0974, "lr": 1.4854391725654076e-05, "epoch": 13.394389438943895, "percentage": 66.97, "elapsed_time": "4:48:15", "remaining_time": "2:22:09", "throughput": 1485.56, "total_tokens": 25693952} {"current_steps": 121760, "total_steps": 181800, "loss": 0.0023, "lr": 1.4852198227871778e-05, "epoch": 13.394939493949394, "percentage": 66.97, "elapsed_time": "4:48:16", "remaining_time": "2:22:08", "throughput": 1485.56, "total_tokens": 25695040} {"current_steps": 121765, "total_steps": 181800, "loss": 0.0437, "lr": 1.4850004823616892e-05, "epoch": 13.395489548954895, "percentage": 66.98, "elapsed_time": "4:48:17", "remaining_time": "2:22:08", "throughput": 1485.57, "total_tokens": 25696096} {"current_steps": 121770, "total_steps": 181800, "loss": 0.0009, "lr": 1.4847811512909655e-05, "epoch": 13.396039603960396, "percentage": 66.98, "elapsed_time": "4:48:17", "remaining_time": "2:22:07", "throughput": 1485.57, "total_tokens": 25697152} {"current_steps": 121775, "total_steps": 181800, "loss": 0.064, "lr": 1.4845618295770256e-05, "epoch": 13.396589658965897, "percentage": 66.98, "elapsed_time": "4:48:18", "remaining_time": "2:22:06", "throughput": 1485.57, "total_tokens": 25698272} {"current_steps": 121780, "total_steps": 181800, "loss": 0.1227, "lr": 1.4843425172218928e-05, "epoch": 13.397139713971397, "percentage": 66.99, "elapsed_time": "4:48:19", "remaining_time": "2:22:06", "throughput": 1485.58, "total_tokens": 25699360} {"current_steps": 121785, "total_steps": 181800, "loss": 0.0055, "lr": 1.4841232142275879e-05, "epoch": 13.397689768976898, "percentage": 66.99, "elapsed_time": "4:48:19", "remaining_time": "2:22:05", "throughput": 1485.58, "total_tokens": 25700352} {"current_steps": 121790, "total_steps": 181800, "loss": 0.0051, "lr": 1.4839039205961302e-05, "epoch": 13.398239823982399, "percentage": 66.99, "elapsed_time": "4:48:20", "remaining_time": "2:22:04", "throughput": 1485.58, "total_tokens": 25701408} {"current_steps": 121795, "total_steps": 181800, "loss": 0.0053, "lr": 1.4836846363295442e-05, "epoch": 13.398789878987898, "percentage": 66.99, "elapsed_time": "4:48:21", "remaining_time": "2:22:03", "throughput": 1485.58, "total_tokens": 25702432} {"current_steps": 121800, "total_steps": 181800, "loss": 0.0188, "lr": 1.4834653614298482e-05, "epoch": 13.3993399339934, "percentage": 67.0, "elapsed_time": "4:48:22", "remaining_time": "2:22:03", "throughput": 1485.58, "total_tokens": 25703456} {"current_steps": 121805, "total_steps": 181800, "loss": 0.0738, "lr": 1.4832460958990648e-05, "epoch": 13.3998899889989, "percentage": 67.0, "elapsed_time": "4:48:22", "remaining_time": "2:22:02", "throughput": 1485.58, "total_tokens": 25704544} {"current_steps": 121810, "total_steps": 181800, "loss": 0.0246, "lr": 1.4830268397392146e-05, "epoch": 13.4004400440044, "percentage": 67.0, "elapsed_time": "4:48:23", "remaining_time": "2:22:01", "throughput": 1485.58, "total_tokens": 25705632} {"current_steps": 121815, "total_steps": 181800, "loss": 0.0108, "lr": 1.4828075929523171e-05, "epoch": 13.400990099009901, "percentage": 67.0, "elapsed_time": "4:48:24", "remaining_time": "2:22:00", "throughput": 1485.58, "total_tokens": 25706656} {"current_steps": 121820, "total_steps": 181800, "loss": 0.0011, "lr": 1.4825883555403947e-05, "epoch": 13.401540154015402, "percentage": 67.01, "elapsed_time": "4:48:24", "remaining_time": "2:22:00", "throughput": 1485.59, "total_tokens": 25707744} {"current_steps": 121825, "total_steps": 181800, "loss": 0.0983, "lr": 1.4823691275054675e-05, "epoch": 13.402090209020901, "percentage": 67.01, "elapsed_time": "4:48:25", "remaining_time": "2:21:59", "throughput": 1485.59, "total_tokens": 25708800} {"current_steps": 121830, "total_steps": 181800, "loss": 0.0047, "lr": 1.4821499088495543e-05, "epoch": 13.402640264026402, "percentage": 67.01, "elapsed_time": "4:48:26", "remaining_time": "2:21:58", "throughput": 1485.59, "total_tokens": 25709888} {"current_steps": 121835, "total_steps": 181800, "loss": 0.0031, "lr": 1.481930699574678e-05, "epoch": 13.403190319031903, "percentage": 67.02, "elapsed_time": "4:48:26", "remaining_time": "2:21:58", "throughput": 1485.6, "total_tokens": 25711008} {"current_steps": 121840, "total_steps": 181800, "loss": 0.0225, "lr": 1.4817114996828573e-05, "epoch": 13.403740374037405, "percentage": 67.02, "elapsed_time": "4:48:27", "remaining_time": "2:21:57", "throughput": 1485.6, "total_tokens": 25712032} {"current_steps": 121845, "total_steps": 181800, "loss": 0.0173, "lr": 1.481492309176114e-05, "epoch": 13.404290429042904, "percentage": 67.02, "elapsed_time": "4:48:28", "remaining_time": "2:21:56", "throughput": 1485.6, "total_tokens": 25713088} {"current_steps": 121850, "total_steps": 181800, "loss": 0.0007, "lr": 1.481273128056467e-05, "epoch": 13.404840484048405, "percentage": 67.02, "elapsed_time": "4:48:28", "remaining_time": "2:21:55", "throughput": 1485.6, "total_tokens": 25714112} {"current_steps": 121855, "total_steps": 181800, "loss": 0.0045, "lr": 1.4810539563259363e-05, "epoch": 13.405390539053906, "percentage": 67.03, "elapsed_time": "4:48:29", "remaining_time": "2:21:55", "throughput": 1485.6, "total_tokens": 25715200} {"current_steps": 121860, "total_steps": 181800, "loss": 0.004, "lr": 1.4808347939865428e-05, "epoch": 13.405940594059405, "percentage": 67.03, "elapsed_time": "4:48:30", "remaining_time": "2:21:54", "throughput": 1485.6, "total_tokens": 25716256} {"current_steps": 121865, "total_steps": 181800, "loss": 0.0032, "lr": 1.4806156410403055e-05, "epoch": 13.406490649064907, "percentage": 67.03, "elapsed_time": "4:48:31", "remaining_time": "2:21:53", "throughput": 1485.61, "total_tokens": 25717376} {"current_steps": 121870, "total_steps": 181800, "loss": 0.0231, "lr": 1.4803964974892453e-05, "epoch": 13.407040704070408, "percentage": 67.04, "elapsed_time": "4:48:31", "remaining_time": "2:21:53", "throughput": 1485.61, "total_tokens": 25718464} {"current_steps": 121875, "total_steps": 181800, "loss": 0.0016, "lr": 1.480177363335381e-05, "epoch": 13.407590759075907, "percentage": 67.04, "elapsed_time": "4:48:32", "remaining_time": "2:21:52", "throughput": 1485.62, "total_tokens": 25719584} {"current_steps": 121880, "total_steps": 181800, "loss": 0.005, "lr": 1.4799582385807326e-05, "epoch": 13.408140814081408, "percentage": 67.04, "elapsed_time": "4:48:33", "remaining_time": "2:21:51", "throughput": 1485.62, "total_tokens": 25720608} {"current_steps": 121885, "total_steps": 181800, "loss": 0.0135, "lr": 1.47973912322732e-05, "epoch": 13.408690869086909, "percentage": 67.04, "elapsed_time": "4:48:33", "remaining_time": "2:21:50", "throughput": 1485.62, "total_tokens": 25721632} {"current_steps": 121890, "total_steps": 181800, "loss": 0.0171, "lr": 1.4795200172771618e-05, "epoch": 13.409240924092408, "percentage": 67.05, "elapsed_time": "4:48:34", "remaining_time": "2:21:50", "throughput": 1485.62, "total_tokens": 25722720} {"current_steps": 121895, "total_steps": 181800, "loss": 0.0151, "lr": 1.4793009207322781e-05, "epoch": 13.40979097909791, "percentage": 67.05, "elapsed_time": "4:48:35", "remaining_time": "2:21:49", "throughput": 1485.62, "total_tokens": 25723776} {"current_steps": 121900, "total_steps": 181800, "loss": 0.002, "lr": 1.4790818335946885e-05, "epoch": 13.41034103410341, "percentage": 67.05, "elapsed_time": "4:48:35", "remaining_time": "2:21:48", "throughput": 1485.62, "total_tokens": 25724832} {"current_steps": 121905, "total_steps": 181800, "loss": 0.0026, "lr": 1.4788627558664109e-05, "epoch": 13.410891089108912, "percentage": 67.05, "elapsed_time": "4:48:36", "remaining_time": "2:21:48", "throughput": 1485.63, "total_tokens": 25725888} {"current_steps": 121910, "total_steps": 181800, "loss": 0.0053, "lr": 1.4786436875494658e-05, "epoch": 13.411441144114411, "percentage": 67.06, "elapsed_time": "4:48:37", "remaining_time": "2:21:47", "throughput": 1485.63, "total_tokens": 25726976} {"current_steps": 121915, "total_steps": 181800, "loss": 0.0018, "lr": 1.4784246286458713e-05, "epoch": 13.411991199119912, "percentage": 67.06, "elapsed_time": "4:48:37", "remaining_time": "2:21:46", "throughput": 1485.63, "total_tokens": 25727968} {"current_steps": 121920, "total_steps": 181800, "loss": 0.0163, "lr": 1.4782055791576471e-05, "epoch": 13.412541254125413, "percentage": 67.06, "elapsed_time": "4:48:38", "remaining_time": "2:21:45", "throughput": 1485.63, "total_tokens": 25729120} {"current_steps": 121925, "total_steps": 181800, "loss": 0.0488, "lr": 1.4779865390868126e-05, "epoch": 13.413091309130913, "percentage": 67.07, "elapsed_time": "4:48:39", "remaining_time": "2:21:45", "throughput": 1485.63, "total_tokens": 25730144} {"current_steps": 121930, "total_steps": 181800, "loss": 0.0294, "lr": 1.4777675084353842e-05, "epoch": 13.413641364136414, "percentage": 67.07, "elapsed_time": "4:48:39", "remaining_time": "2:21:44", "throughput": 1485.64, "total_tokens": 25731200} {"current_steps": 121935, "total_steps": 181800, "loss": 0.0043, "lr": 1.4775484872053832e-05, "epoch": 13.414191419141915, "percentage": 67.07, "elapsed_time": "4:48:40", "remaining_time": "2:21:43", "throughput": 1485.64, "total_tokens": 25732256} {"current_steps": 121940, "total_steps": 181800, "loss": 0.0053, "lr": 1.4773294753988265e-05, "epoch": 13.414741474147414, "percentage": 67.07, "elapsed_time": "4:48:41", "remaining_time": "2:21:43", "throughput": 1485.64, "total_tokens": 25733312} {"current_steps": 121945, "total_steps": 181800, "loss": 0.0046, "lr": 1.4771104730177343e-05, "epoch": 13.415291529152915, "percentage": 67.08, "elapsed_time": "4:48:42", "remaining_time": "2:21:42", "throughput": 1485.64, "total_tokens": 25734368} {"current_steps": 121950, "total_steps": 181800, "loss": 0.0395, "lr": 1.4768914800641237e-05, "epoch": 13.415841584158416, "percentage": 67.08, "elapsed_time": "4:48:42", "remaining_time": "2:21:41", "throughput": 1485.64, "total_tokens": 25735424} {"current_steps": 121955, "total_steps": 181800, "loss": 0.0037, "lr": 1.4766724965400124e-05, "epoch": 13.416391639163916, "percentage": 67.08, "elapsed_time": "4:48:43", "remaining_time": "2:21:40", "throughput": 1485.64, "total_tokens": 25736448} {"current_steps": 121960, "total_steps": 181800, "loss": 0.0008, "lr": 1.4764535224474214e-05, "epoch": 13.416941694169417, "percentage": 67.08, "elapsed_time": "4:48:44", "remaining_time": "2:21:40", "throughput": 1485.65, "total_tokens": 25737504} {"current_steps": 121965, "total_steps": 181800, "loss": 0.002, "lr": 1.4762345577883655e-05, "epoch": 13.417491749174918, "percentage": 67.09, "elapsed_time": "4:48:44", "remaining_time": "2:21:39", "throughput": 1485.65, "total_tokens": 25738560} {"current_steps": 121970, "total_steps": 181800, "loss": 0.0036, "lr": 1.4760156025648653e-05, "epoch": 13.418041804180419, "percentage": 67.09, "elapsed_time": "4:48:45", "remaining_time": "2:21:38", "throughput": 1485.65, "total_tokens": 25739680} {"current_steps": 121975, "total_steps": 181800, "loss": 0.0611, "lr": 1.4757966567789378e-05, "epoch": 13.418591859185918, "percentage": 67.09, "elapsed_time": "4:48:46", "remaining_time": "2:21:37", "throughput": 1485.66, "total_tokens": 25740768} {"current_steps": 121980, "total_steps": 181800, "loss": 0.0056, "lr": 1.4755777204326004e-05, "epoch": 13.41914191419142, "percentage": 67.1, "elapsed_time": "4:48:46", "remaining_time": "2:21:37", "throughput": 1485.66, "total_tokens": 25741856} {"current_steps": 121985, "total_steps": 181800, "loss": 0.0045, "lr": 1.4753587935278725e-05, "epoch": 13.41969196919692, "percentage": 67.1, "elapsed_time": "4:48:47", "remaining_time": "2:21:36", "throughput": 1485.66, "total_tokens": 25742848} {"current_steps": 121990, "total_steps": 181800, "loss": 0.0092, "lr": 1.4751398760667703e-05, "epoch": 13.42024202420242, "percentage": 67.1, "elapsed_time": "4:48:48", "remaining_time": "2:21:35", "throughput": 1485.66, "total_tokens": 25743904} {"current_steps": 121995, "total_steps": 181800, "loss": 0.0037, "lr": 1.4749209680513123e-05, "epoch": 13.42079207920792, "percentage": 67.1, "elapsed_time": "4:48:48", "remaining_time": "2:21:35", "throughput": 1485.66, "total_tokens": 25744992} {"current_steps": 122000, "total_steps": 181800, "loss": 0.0017, "lr": 1.4747020694835168e-05, "epoch": 13.421342134213422, "percentage": 67.11, "elapsed_time": "4:48:49", "remaining_time": "2:21:34", "throughput": 1485.66, "total_tokens": 25746016} {"current_steps": 122005, "total_steps": 181800, "loss": 0.0084, "lr": 1.474483180365399e-05, "epoch": 13.421892189218921, "percentage": 67.11, "elapsed_time": "4:48:50", "remaining_time": "2:21:33", "throughput": 1485.67, "total_tokens": 25747104} {"current_steps": 122010, "total_steps": 181800, "loss": 0.0619, "lr": 1.4742643006989781e-05, "epoch": 13.422442244224422, "percentage": 67.11, "elapsed_time": "4:48:51", "remaining_time": "2:21:32", "throughput": 1485.67, "total_tokens": 25748192} {"current_steps": 122015, "total_steps": 181800, "loss": 0.0036, "lr": 1.4740454304862716e-05, "epoch": 13.422992299229923, "percentage": 67.11, "elapsed_time": "4:48:51", "remaining_time": "2:21:32", "throughput": 1485.68, "total_tokens": 25749280} {"current_steps": 122020, "total_steps": 181800, "loss": 0.0934, "lr": 1.4738265697292947e-05, "epoch": 13.423542354235423, "percentage": 67.12, "elapsed_time": "4:48:52", "remaining_time": "2:21:31", "throughput": 1485.68, "total_tokens": 25750368} {"current_steps": 122025, "total_steps": 181800, "loss": 0.0028, "lr": 1.4736077184300668e-05, "epoch": 13.424092409240924, "percentage": 67.12, "elapsed_time": "4:48:53", "remaining_time": "2:21:30", "throughput": 1485.68, "total_tokens": 25751392} {"current_steps": 122030, "total_steps": 181800, "loss": 0.0011, "lr": 1.4733888765906034e-05, "epoch": 13.424642464246425, "percentage": 67.12, "elapsed_time": "4:48:53", "remaining_time": "2:21:30", "throughput": 1485.68, "total_tokens": 25752448} {"current_steps": 122035, "total_steps": 181800, "loss": 0.0797, "lr": 1.4731700442129226e-05, "epoch": 13.425192519251926, "percentage": 67.13, "elapsed_time": "4:48:54", "remaining_time": "2:21:29", "throughput": 1485.68, "total_tokens": 25753504} {"current_steps": 122040, "total_steps": 181800, "loss": 0.0694, "lr": 1.4729512212990415e-05, "epoch": 13.425742574257425, "percentage": 67.13, "elapsed_time": "4:48:55", "remaining_time": "2:21:28", "throughput": 1485.68, "total_tokens": 25754528} {"current_steps": 122045, "total_steps": 181800, "loss": 0.0021, "lr": 1.4727324078509749e-05, "epoch": 13.426292629262926, "percentage": 67.13, "elapsed_time": "4:48:55", "remaining_time": "2:21:27", "throughput": 1485.68, "total_tokens": 25755584} {"current_steps": 122050, "total_steps": 181800, "loss": 0.0017, "lr": 1.4725136038707413e-05, "epoch": 13.426842684268427, "percentage": 67.13, "elapsed_time": "4:48:56", "remaining_time": "2:21:27", "throughput": 1485.69, "total_tokens": 25756640} {"current_steps": 122055, "total_steps": 181800, "loss": 0.0054, "lr": 1.4722948093603563e-05, "epoch": 13.427392739273927, "percentage": 67.14, "elapsed_time": "4:48:57", "remaining_time": "2:21:26", "throughput": 1485.68, "total_tokens": 25757664} {"current_steps": 122060, "total_steps": 181800, "loss": 0.1184, "lr": 1.4720760243218379e-05, "epoch": 13.427942794279428, "percentage": 67.14, "elapsed_time": "4:48:57", "remaining_time": "2:21:25", "throughput": 1485.68, "total_tokens": 25758688} {"current_steps": 122065, "total_steps": 181800, "loss": 0.009, "lr": 1.4718572487572014e-05, "epoch": 13.428492849284929, "percentage": 67.14, "elapsed_time": "4:48:58", "remaining_time": "2:21:25", "throughput": 1485.69, "total_tokens": 25759776} {"current_steps": 122070, "total_steps": 181800, "loss": 0.065, "lr": 1.471638482668462e-05, "epoch": 13.429042904290428, "percentage": 67.15, "elapsed_time": "4:48:59", "remaining_time": "2:21:24", "throughput": 1485.69, "total_tokens": 25760864} {"current_steps": 122075, "total_steps": 181800, "loss": 0.0405, "lr": 1.471419726057639e-05, "epoch": 13.42959295929593, "percentage": 67.15, "elapsed_time": "4:48:59", "remaining_time": "2:21:23", "throughput": 1485.69, "total_tokens": 25761888} {"current_steps": 122080, "total_steps": 181800, "loss": 0.0967, "lr": 1.4712009789267455e-05, "epoch": 13.43014301430143, "percentage": 67.15, "elapsed_time": "4:49:00", "remaining_time": "2:21:22", "throughput": 1485.7, "total_tokens": 25762976} {"current_steps": 122085, "total_steps": 181800, "loss": 0.0203, "lr": 1.4709822412777996e-05, "epoch": 13.430693069306932, "percentage": 67.15, "elapsed_time": "4:49:01", "remaining_time": "2:21:22", "throughput": 1485.7, "total_tokens": 25764000} {"current_steps": 122090, "total_steps": 181800, "loss": 0.1114, "lr": 1.4707635131128166e-05, "epoch": 13.43124312431243, "percentage": 67.16, "elapsed_time": "4:49:02", "remaining_time": "2:21:21", "throughput": 1485.7, "total_tokens": 25765056} {"current_steps": 122095, "total_steps": 181800, "loss": 0.0014, "lr": 1.4705447944338114e-05, "epoch": 13.431793179317932, "percentage": 67.16, "elapsed_time": "4:49:02", "remaining_time": "2:21:20", "throughput": 1485.7, "total_tokens": 25766144} {"current_steps": 122100, "total_steps": 181800, "loss": 0.0418, "lr": 1.4703260852428025e-05, "epoch": 13.432343234323433, "percentage": 67.16, "elapsed_time": "4:49:03", "remaining_time": "2:21:19", "throughput": 1485.71, "total_tokens": 25767232} {"current_steps": 122105, "total_steps": 181800, "loss": 0.0101, "lr": 1.4701073855418025e-05, "epoch": 13.432893289328932, "percentage": 67.16, "elapsed_time": "4:49:04", "remaining_time": "2:21:19", "throughput": 1485.71, "total_tokens": 25768320} {"current_steps": 122110, "total_steps": 181800, "loss": 0.0154, "lr": 1.4698886953328292e-05, "epoch": 13.433443344334433, "percentage": 67.17, "elapsed_time": "4:49:04", "remaining_time": "2:21:18", "throughput": 1485.71, "total_tokens": 25769376} {"current_steps": 122115, "total_steps": 181800, "loss": 0.0028, "lr": 1.4696700146178982e-05, "epoch": 13.433993399339935, "percentage": 67.17, "elapsed_time": "4:49:05", "remaining_time": "2:21:17", "throughput": 1485.71, "total_tokens": 25770400} {"current_steps": 122120, "total_steps": 181800, "loss": 0.0177, "lr": 1.4694513433990231e-05, "epoch": 13.434543454345434, "percentage": 67.17, "elapsed_time": "4:49:06", "remaining_time": "2:21:17", "throughput": 1485.71, "total_tokens": 25771456} {"current_steps": 122125, "total_steps": 181800, "loss": 0.0034, "lr": 1.4692326816782208e-05, "epoch": 13.435093509350935, "percentage": 67.18, "elapsed_time": "4:49:06", "remaining_time": "2:21:16", "throughput": 1485.72, "total_tokens": 25772544} {"current_steps": 122130, "total_steps": 181800, "loss": 0.1495, "lr": 1.4690140294575062e-05, "epoch": 13.435643564356436, "percentage": 67.18, "elapsed_time": "4:49:07", "remaining_time": "2:21:15", "throughput": 1485.72, "total_tokens": 25773568} {"current_steps": 122135, "total_steps": 181800, "loss": 0.0168, "lr": 1.4687953867388952e-05, "epoch": 13.436193619361935, "percentage": 67.18, "elapsed_time": "4:49:08", "remaining_time": "2:21:14", "throughput": 1485.72, "total_tokens": 25774624} {"current_steps": 122140, "total_steps": 181800, "loss": 0.0349, "lr": 1.4685767535244018e-05, "epoch": 13.436743674367436, "percentage": 67.18, "elapsed_time": "4:49:08", "remaining_time": "2:21:14", "throughput": 1485.72, "total_tokens": 25775680} {"current_steps": 122145, "total_steps": 181800, "loss": 0.0023, "lr": 1.4683581298160413e-05, "epoch": 13.437293729372938, "percentage": 67.19, "elapsed_time": "4:49:09", "remaining_time": "2:21:13", "throughput": 1485.72, "total_tokens": 25776736} {"current_steps": 122150, "total_steps": 181800, "loss": 0.0102, "lr": 1.4681395156158296e-05, "epoch": 13.437843784378439, "percentage": 67.19, "elapsed_time": "4:49:10", "remaining_time": "2:21:12", "throughput": 1485.73, "total_tokens": 25777856} {"current_steps": 122155, "total_steps": 181800, "loss": 0.013, "lr": 1.4679209109257797e-05, "epoch": 13.438393839383938, "percentage": 67.19, "elapsed_time": "4:49:11", "remaining_time": "2:21:12", "throughput": 1485.73, "total_tokens": 25778912} {"current_steps": 122160, "total_steps": 181800, "loss": 0.0269, "lr": 1.4677023157479086e-05, "epoch": 13.438943894389439, "percentage": 67.19, "elapsed_time": "4:49:11", "remaining_time": "2:21:11", "throughput": 1485.73, "total_tokens": 25779872} {"current_steps": 122165, "total_steps": 181800, "loss": 0.1824, "lr": 1.4674837300842298e-05, "epoch": 13.43949394939494, "percentage": 67.2, "elapsed_time": "4:49:12", "remaining_time": "2:21:10", "throughput": 1485.72, "total_tokens": 25780864} {"current_steps": 122170, "total_steps": 181800, "loss": 0.0006, "lr": 1.467265153936757e-05, "epoch": 13.44004400440044, "percentage": 67.2, "elapsed_time": "4:49:13", "remaining_time": "2:21:09", "throughput": 1485.72, "total_tokens": 25781888} {"current_steps": 122175, "total_steps": 181800, "loss": 0.0041, "lr": 1.4670465873075074e-05, "epoch": 13.44059405940594, "percentage": 67.2, "elapsed_time": "4:49:13", "remaining_time": "2:21:09", "throughput": 1485.72, "total_tokens": 25782912} {"current_steps": 122180, "total_steps": 181800, "loss": 0.0787, "lr": 1.4668280301984923e-05, "epoch": 13.441144114411442, "percentage": 67.21, "elapsed_time": "4:49:14", "remaining_time": "2:21:08", "throughput": 1485.73, "total_tokens": 25784000} {"current_steps": 122185, "total_steps": 181800, "loss": 0.0082, "lr": 1.4666094826117283e-05, "epoch": 13.441694169416941, "percentage": 67.21, "elapsed_time": "4:49:15", "remaining_time": "2:21:07", "throughput": 1485.73, "total_tokens": 25785056} {"current_steps": 122190, "total_steps": 181800, "loss": 0.0146, "lr": 1.4663909445492291e-05, "epoch": 13.442244224422442, "percentage": 67.21, "elapsed_time": "4:49:15", "remaining_time": "2:21:06", "throughput": 1485.73, "total_tokens": 25786112} {"current_steps": 122195, "total_steps": 181800, "loss": 0.0016, "lr": 1.4661724160130076e-05, "epoch": 13.442794279427943, "percentage": 67.21, "elapsed_time": "4:49:16", "remaining_time": "2:21:06", "throughput": 1485.73, "total_tokens": 25787168} {"current_steps": 122200, "total_steps": 181800, "loss": 0.031, "lr": 1.4659538970050793e-05, "epoch": 13.443344334433444, "percentage": 67.22, "elapsed_time": "4:49:17", "remaining_time": "2:21:05", "throughput": 1485.73, "total_tokens": 25788224} {"current_steps": 122205, "total_steps": 181800, "loss": 0.0082, "lr": 1.4657353875274582e-05, "epoch": 13.443894389438944, "percentage": 67.22, "elapsed_time": "4:49:17", "remaining_time": "2:21:04", "throughput": 1485.74, "total_tokens": 25789312} {"current_steps": 122210, "total_steps": 181800, "loss": 0.0008, "lr": 1.465516887582157e-05, "epoch": 13.444444444444445, "percentage": 67.22, "elapsed_time": "4:49:18", "remaining_time": "2:21:04", "throughput": 1485.74, "total_tokens": 25790400} {"current_steps": 122215, "total_steps": 181800, "loss": 0.0401, "lr": 1.4652983971711906e-05, "epoch": 13.444994499449946, "percentage": 67.22, "elapsed_time": "4:49:19", "remaining_time": "2:21:03", "throughput": 1485.75, "total_tokens": 25791488} {"current_steps": 122220, "total_steps": 181800, "loss": 0.1802, "lr": 1.465079916296572e-05, "epoch": 13.445544554455445, "percentage": 67.23, "elapsed_time": "4:49:19", "remaining_time": "2:21:02", "throughput": 1485.75, "total_tokens": 25792544} {"current_steps": 122225, "total_steps": 181800, "loss": 0.1226, "lr": 1.4648614449603154e-05, "epoch": 13.446094609460946, "percentage": 67.23, "elapsed_time": "4:49:20", "remaining_time": "2:21:01", "throughput": 1485.75, "total_tokens": 25793632} {"current_steps": 122230, "total_steps": 181800, "loss": 0.0041, "lr": 1.4646429831644348e-05, "epoch": 13.446644664466447, "percentage": 67.23, "elapsed_time": "4:49:21", "remaining_time": "2:21:01", "throughput": 1485.74, "total_tokens": 25794688} {"current_steps": 122235, "total_steps": 181800, "loss": 0.0311, "lr": 1.4644245309109422e-05, "epoch": 13.447194719471947, "percentage": 67.24, "elapsed_time": "4:49:22", "remaining_time": "2:21:00", "throughput": 1485.74, "total_tokens": 25795808} {"current_steps": 122240, "total_steps": 181800, "loss": 0.0287, "lr": 1.464206088201852e-05, "epoch": 13.447744774477448, "percentage": 67.24, "elapsed_time": "4:49:22", "remaining_time": "2:20:59", "throughput": 1485.75, "total_tokens": 25796928} {"current_steps": 122245, "total_steps": 181800, "loss": 0.0064, "lr": 1.4639876550391773e-05, "epoch": 13.448294829482949, "percentage": 67.24, "elapsed_time": "4:49:23", "remaining_time": "2:20:59", "throughput": 1485.75, "total_tokens": 25798048} {"current_steps": 122250, "total_steps": 181800, "loss": 0.0064, "lr": 1.4637692314249319e-05, "epoch": 13.448844884488448, "percentage": 67.24, "elapsed_time": "4:49:24", "remaining_time": "2:20:58", "throughput": 1485.75, "total_tokens": 25799072} {"current_steps": 122255, "total_steps": 181800, "loss": 0.1983, "lr": 1.4635508173611276e-05, "epoch": 13.44939493949395, "percentage": 67.25, "elapsed_time": "4:49:25", "remaining_time": "2:20:57", "throughput": 1485.75, "total_tokens": 25800128} {"current_steps": 122260, "total_steps": 181800, "loss": 0.0674, "lr": 1.4633324128497778e-05, "epoch": 13.44994499449945, "percentage": 67.25, "elapsed_time": "4:49:25", "remaining_time": "2:20:57", "throughput": 1485.76, "total_tokens": 25801216} {"current_steps": 122265, "total_steps": 181800, "loss": 0.041, "lr": 1.4631140178928965e-05, "epoch": 13.450495049504951, "percentage": 67.25, "elapsed_time": "4:49:26", "remaining_time": "2:20:56", "throughput": 1485.76, "total_tokens": 25802240} {"current_steps": 122270, "total_steps": 181800, "loss": 0.0213, "lr": 1.4628956324924947e-05, "epoch": 13.45104510451045, "percentage": 67.26, "elapsed_time": "4:49:27", "remaining_time": "2:20:55", "throughput": 1485.76, "total_tokens": 25803232} {"current_steps": 122275, "total_steps": 181800, "loss": 0.0037, "lr": 1.462677256650587e-05, "epoch": 13.451595159515952, "percentage": 67.26, "elapsed_time": "4:49:27", "remaining_time": "2:20:54", "throughput": 1485.76, "total_tokens": 25804256} {"current_steps": 122280, "total_steps": 181800, "loss": 0.0122, "lr": 1.4624588903691853e-05, "epoch": 13.452145214521453, "percentage": 67.26, "elapsed_time": "4:49:28", "remaining_time": "2:20:54", "throughput": 1485.76, "total_tokens": 25805312} {"current_steps": 122285, "total_steps": 181800, "loss": 0.0776, "lr": 1.4622405336503015e-05, "epoch": 13.452695269526952, "percentage": 67.26, "elapsed_time": "4:49:29", "remaining_time": "2:20:53", "throughput": 1485.76, "total_tokens": 25806368} {"current_steps": 122290, "total_steps": 181800, "loss": 0.003, "lr": 1.4620221864959497e-05, "epoch": 13.453245324532453, "percentage": 67.27, "elapsed_time": "4:49:29", "remaining_time": "2:20:52", "throughput": 1485.76, "total_tokens": 25807488} {"current_steps": 122295, "total_steps": 181800, "loss": 0.094, "lr": 1.4618038489081403e-05, "epoch": 13.453795379537954, "percentage": 67.27, "elapsed_time": "4:49:30", "remaining_time": "2:20:51", "throughput": 1485.76, "total_tokens": 25808480} {"current_steps": 122300, "total_steps": 181800, "loss": 0.0082, "lr": 1.4615855208888874e-05, "epoch": 13.454345434543454, "percentage": 67.27, "elapsed_time": "4:49:31", "remaining_time": "2:20:51", "throughput": 1485.77, "total_tokens": 25809568} {"current_steps": 122305, "total_steps": 181800, "loss": 0.1737, "lr": 1.4613672024402025e-05, "epoch": 13.454895489548955, "percentage": 67.27, "elapsed_time": "4:49:31", "remaining_time": "2:20:50", "throughput": 1485.77, "total_tokens": 25810656} {"current_steps": 122310, "total_steps": 181800, "loss": 0.0039, "lr": 1.4611488935640972e-05, "epoch": 13.455445544554456, "percentage": 67.28, "elapsed_time": "4:49:32", "remaining_time": "2:20:49", "throughput": 1485.77, "total_tokens": 25811744} {"current_steps": 122315, "total_steps": 181800, "loss": 0.0177, "lr": 1.4609305942625843e-05, "epoch": 13.455995599559955, "percentage": 67.28, "elapsed_time": "4:49:33", "remaining_time": "2:20:49", "throughput": 1485.78, "total_tokens": 25812832} {"current_steps": 122320, "total_steps": 181800, "loss": 0.022, "lr": 1.4607123045376753e-05, "epoch": 13.456545654565456, "percentage": 67.28, "elapsed_time": "4:49:33", "remaining_time": "2:20:48", "throughput": 1485.78, "total_tokens": 25813920} {"current_steps": 122325, "total_steps": 181800, "loss": 0.0442, "lr": 1.4604940243913828e-05, "epoch": 13.457095709570957, "percentage": 67.29, "elapsed_time": "4:49:34", "remaining_time": "2:20:47", "throughput": 1485.78, "total_tokens": 25815008} {"current_steps": 122330, "total_steps": 181800, "loss": 0.0334, "lr": 1.4602757538257179e-05, "epoch": 13.457645764576458, "percentage": 67.29, "elapsed_time": "4:49:35", "remaining_time": "2:20:46", "throughput": 1485.78, "total_tokens": 25816064} {"current_steps": 122335, "total_steps": 181800, "loss": 0.078, "lr": 1.4600574928426919e-05, "epoch": 13.458195819581958, "percentage": 67.29, "elapsed_time": "4:49:36", "remaining_time": "2:20:46", "throughput": 1485.78, "total_tokens": 25817088} {"current_steps": 122340, "total_steps": 181800, "loss": 0.0041, "lr": 1.4598392414443174e-05, "epoch": 13.458745874587459, "percentage": 67.29, "elapsed_time": "4:49:36", "remaining_time": "2:20:45", "throughput": 1485.79, "total_tokens": 25818144} {"current_steps": 122345, "total_steps": 181800, "loss": 0.0424, "lr": 1.4596209996326052e-05, "epoch": 13.45929592959296, "percentage": 67.3, "elapsed_time": "4:49:37", "remaining_time": "2:20:44", "throughput": 1485.79, "total_tokens": 25819232} {"current_steps": 122350, "total_steps": 181800, "loss": 0.0927, "lr": 1.4594027674095679e-05, "epoch": 13.45984598459846, "percentage": 67.3, "elapsed_time": "4:49:38", "remaining_time": "2:20:44", "throughput": 1485.79, "total_tokens": 25820320} {"current_steps": 122355, "total_steps": 181800, "loss": 0.0359, "lr": 1.459184544777216e-05, "epoch": 13.46039603960396, "percentage": 67.3, "elapsed_time": "4:49:38", "remaining_time": "2:20:43", "throughput": 1485.79, "total_tokens": 25821376} {"current_steps": 122360, "total_steps": 181800, "loss": 0.007, "lr": 1.4589663317375596e-05, "epoch": 13.460946094609461, "percentage": 67.3, "elapsed_time": "4:49:39", "remaining_time": "2:20:42", "throughput": 1485.8, "total_tokens": 25822464} {"current_steps": 122365, "total_steps": 181800, "loss": 0.0059, "lr": 1.4587481282926113e-05, "epoch": 13.46149614961496, "percentage": 67.31, "elapsed_time": "4:49:40", "remaining_time": "2:20:41", "throughput": 1485.8, "total_tokens": 25823456} {"current_steps": 122370, "total_steps": 181800, "loss": 0.001, "lr": 1.4585299344443815e-05, "epoch": 13.462046204620462, "percentage": 67.31, "elapsed_time": "4:49:40", "remaining_time": "2:20:41", "throughput": 1485.8, "total_tokens": 25824544} {"current_steps": 122375, "total_steps": 181800, "loss": 0.0032, "lr": 1.4583117501948825e-05, "epoch": 13.462596259625963, "percentage": 67.31, "elapsed_time": "4:49:41", "remaining_time": "2:20:40", "throughput": 1485.8, "total_tokens": 25825536} {"current_steps": 122380, "total_steps": 181800, "loss": 0.0768, "lr": 1.4580935755461244e-05, "epoch": 13.463146314631462, "percentage": 67.32, "elapsed_time": "4:49:42", "remaining_time": "2:20:39", "throughput": 1485.8, "total_tokens": 25826592} {"current_steps": 122385, "total_steps": 181800, "loss": 0.0457, "lr": 1.457875410500117e-05, "epoch": 13.463696369636963, "percentage": 67.32, "elapsed_time": "4:49:42", "remaining_time": "2:20:39", "throughput": 1485.81, "total_tokens": 25827712} {"current_steps": 122390, "total_steps": 181800, "loss": 0.07, "lr": 1.457657255058873e-05, "epoch": 13.464246424642464, "percentage": 67.32, "elapsed_time": "4:49:43", "remaining_time": "2:20:38", "throughput": 1485.81, "total_tokens": 25828736} {"current_steps": 122395, "total_steps": 181800, "loss": 0.0068, "lr": 1.4574391092244005e-05, "epoch": 13.464796479647966, "percentage": 67.32, "elapsed_time": "4:49:44", "remaining_time": "2:20:37", "throughput": 1485.81, "total_tokens": 25829760} {"current_steps": 122400, "total_steps": 181800, "loss": 0.0717, "lr": 1.4572209729987118e-05, "epoch": 13.465346534653465, "percentage": 67.33, "elapsed_time": "4:49:45", "remaining_time": "2:20:36", "throughput": 1485.81, "total_tokens": 25830848} {"current_steps": 122405, "total_steps": 181800, "loss": 0.1016, "lr": 1.4570028463838175e-05, "epoch": 13.465896589658966, "percentage": 67.33, "elapsed_time": "4:49:45", "remaining_time": "2:20:36", "throughput": 1485.81, "total_tokens": 25831904} {"current_steps": 122410, "total_steps": 181800, "loss": 0.0045, "lr": 1.4567847293817272e-05, "epoch": 13.466446644664467, "percentage": 67.33, "elapsed_time": "4:49:46", "remaining_time": "2:20:35", "throughput": 1485.81, "total_tokens": 25832992} {"current_steps": 122415, "total_steps": 181800, "loss": 0.0067, "lr": 1.4565666219944521e-05, "epoch": 13.466996699669966, "percentage": 67.33, "elapsed_time": "4:49:47", "remaining_time": "2:20:34", "throughput": 1485.82, "total_tokens": 25834080} {"current_steps": 122420, "total_steps": 181800, "loss": 0.1521, "lr": 1.4563485242240008e-05, "epoch": 13.467546754675467, "percentage": 67.34, "elapsed_time": "4:49:47", "remaining_time": "2:20:33", "throughput": 1485.82, "total_tokens": 25835136} {"current_steps": 122425, "total_steps": 181800, "loss": 0.0027, "lr": 1.4561304360723843e-05, "epoch": 13.468096809680969, "percentage": 67.34, "elapsed_time": "4:49:48", "remaining_time": "2:20:33", "throughput": 1485.82, "total_tokens": 25836192} {"current_steps": 122430, "total_steps": 181800, "loss": 0.0054, "lr": 1.4559123575416136e-05, "epoch": 13.468646864686468, "percentage": 67.34, "elapsed_time": "4:49:49", "remaining_time": "2:20:32", "throughput": 1485.82, "total_tokens": 25837248} {"current_steps": 122435, "total_steps": 181800, "loss": 0.0061, "lr": 1.455694288633697e-05, "epoch": 13.469196919691969, "percentage": 67.35, "elapsed_time": "4:49:49", "remaining_time": "2:20:31", "throughput": 1485.82, "total_tokens": 25838304} {"current_steps": 122440, "total_steps": 181800, "loss": 0.0797, "lr": 1.4554762293506458e-05, "epoch": 13.46974697469747, "percentage": 67.35, "elapsed_time": "4:49:50", "remaining_time": "2:20:31", "throughput": 1485.83, "total_tokens": 25839392} {"current_steps": 122445, "total_steps": 181800, "loss": 0.0041, "lr": 1.4552581796944689e-05, "epoch": 13.47029702970297, "percentage": 67.35, "elapsed_time": "4:49:51", "remaining_time": "2:20:30", "throughput": 1485.83, "total_tokens": 25840448} {"current_steps": 122450, "total_steps": 181800, "loss": 0.0021, "lr": 1.4550401396671753e-05, "epoch": 13.47084708470847, "percentage": 67.35, "elapsed_time": "4:49:51", "remaining_time": "2:20:29", "throughput": 1485.83, "total_tokens": 25841472} {"current_steps": 122455, "total_steps": 181800, "loss": 0.0337, "lr": 1.454822109270775e-05, "epoch": 13.471397139713972, "percentage": 67.36, "elapsed_time": "4:49:52", "remaining_time": "2:20:28", "throughput": 1485.83, "total_tokens": 25842560} {"current_steps": 122460, "total_steps": 181800, "loss": 0.0035, "lr": 1.454604088507278e-05, "epoch": 13.471947194719473, "percentage": 67.36, "elapsed_time": "4:49:53", "remaining_time": "2:20:28", "throughput": 1485.83, "total_tokens": 25843616} {"current_steps": 122465, "total_steps": 181800, "loss": 0.0183, "lr": 1.4543860773786944e-05, "epoch": 13.472497249724972, "percentage": 67.36, "elapsed_time": "4:49:54", "remaining_time": "2:20:27", "throughput": 1485.83, "total_tokens": 25844576} {"current_steps": 122470, "total_steps": 181800, "loss": 0.015, "lr": 1.454168075887033e-05, "epoch": 13.473047304730473, "percentage": 67.37, "elapsed_time": "4:49:54", "remaining_time": "2:20:26", "throughput": 1485.83, "total_tokens": 25845664} {"current_steps": 122475, "total_steps": 181800, "loss": 0.0041, "lr": 1.4539500840343012e-05, "epoch": 13.473597359735974, "percentage": 67.37, "elapsed_time": "4:49:55", "remaining_time": "2:20:26", "throughput": 1485.84, "total_tokens": 25846720} {"current_steps": 122480, "total_steps": 181800, "loss": 0.0712, "lr": 1.4537321018225094e-05, "epoch": 13.474147414741473, "percentage": 67.37, "elapsed_time": "4:49:56", "remaining_time": "2:20:25", "throughput": 1485.83, "total_tokens": 25847712} {"current_steps": 122485, "total_steps": 181800, "loss": 0.1718, "lr": 1.4535141292536668e-05, "epoch": 13.474697469746975, "percentage": 67.37, "elapsed_time": "4:49:56", "remaining_time": "2:20:24", "throughput": 1485.84, "total_tokens": 25848800} {"current_steps": 122490, "total_steps": 181800, "loss": 0.1343, "lr": 1.4532961663297836e-05, "epoch": 13.475247524752476, "percentage": 67.38, "elapsed_time": "4:49:57", "remaining_time": "2:20:23", "throughput": 1485.84, "total_tokens": 25849856} {"current_steps": 122495, "total_steps": 181800, "loss": 0.0229, "lr": 1.4530782130528672e-05, "epoch": 13.475797579757975, "percentage": 67.38, "elapsed_time": "4:49:58", "remaining_time": "2:20:23", "throughput": 1485.84, "total_tokens": 25850880} {"current_steps": 122500, "total_steps": 181800, "loss": 0.0434, "lr": 1.4528602694249258e-05, "epoch": 13.476347634763476, "percentage": 67.38, "elapsed_time": "4:49:58", "remaining_time": "2:20:22", "throughput": 1485.84, "total_tokens": 25851968} {"current_steps": 122505, "total_steps": 181800, "loss": 0.0404, "lr": 1.4526423354479695e-05, "epoch": 13.476897689768977, "percentage": 67.38, "elapsed_time": "4:49:59", "remaining_time": "2:20:21", "throughput": 1485.84, "total_tokens": 25852992} {"current_steps": 122510, "total_steps": 181800, "loss": 0.0068, "lr": 1.4524244111240054e-05, "epoch": 13.477447744774478, "percentage": 67.39, "elapsed_time": "4:50:00", "remaining_time": "2:20:21", "throughput": 1485.84, "total_tokens": 25854048} {"current_steps": 122515, "total_steps": 181800, "loss": 0.0763, "lr": 1.4522064964550428e-05, "epoch": 13.477997799779978, "percentage": 67.39, "elapsed_time": "4:50:00", "remaining_time": "2:20:20", "throughput": 1485.84, "total_tokens": 25855040} {"current_steps": 122520, "total_steps": 181800, "loss": 0.0781, "lr": 1.4519885914430912e-05, "epoch": 13.478547854785479, "percentage": 67.39, "elapsed_time": "4:50:01", "remaining_time": "2:20:19", "throughput": 1485.84, "total_tokens": 25856064} {"current_steps": 122525, "total_steps": 181800, "loss": 0.006, "lr": 1.4517706960901566e-05, "epoch": 13.47909790979098, "percentage": 67.4, "elapsed_time": "4:50:02", "remaining_time": "2:20:18", "throughput": 1485.84, "total_tokens": 25857120} {"current_steps": 122530, "total_steps": 181800, "loss": 0.0365, "lr": 1.4515528103982498e-05, "epoch": 13.479647964796479, "percentage": 67.4, "elapsed_time": "4:50:03", "remaining_time": "2:20:18", "throughput": 1485.85, "total_tokens": 25858208} {"current_steps": 122535, "total_steps": 181800, "loss": 0.0058, "lr": 1.4513349343693767e-05, "epoch": 13.48019801980198, "percentage": 67.4, "elapsed_time": "4:50:03", "remaining_time": "2:20:17", "throughput": 1485.85, "total_tokens": 25859232} {"current_steps": 122540, "total_steps": 181800, "loss": 0.0032, "lr": 1.4511170680055457e-05, "epoch": 13.480748074807481, "percentage": 67.4, "elapsed_time": "4:50:04", "remaining_time": "2:20:16", "throughput": 1485.85, "total_tokens": 25860256} {"current_steps": 122545, "total_steps": 181800, "loss": 0.0177, "lr": 1.4508992113087671e-05, "epoch": 13.48129812981298, "percentage": 67.41, "elapsed_time": "4:50:05", "remaining_time": "2:20:15", "throughput": 1485.85, "total_tokens": 25861280} {"current_steps": 122550, "total_steps": 181800, "loss": 0.0055, "lr": 1.4506813642810458e-05, "epoch": 13.481848184818482, "percentage": 67.41, "elapsed_time": "4:50:05", "remaining_time": "2:20:15", "throughput": 1485.85, "total_tokens": 25862336} {"current_steps": 122555, "total_steps": 181800, "loss": 0.0484, "lr": 1.450463526924392e-05, "epoch": 13.482398239823983, "percentage": 67.41, "elapsed_time": "4:50:06", "remaining_time": "2:20:14", "throughput": 1485.86, "total_tokens": 25863488} {"current_steps": 122560, "total_steps": 181800, "loss": 0.0877, "lr": 1.450245699240811e-05, "epoch": 13.482948294829482, "percentage": 67.41, "elapsed_time": "4:50:07", "remaining_time": "2:20:13", "throughput": 1485.86, "total_tokens": 25864512} {"current_steps": 122565, "total_steps": 181800, "loss": 0.0064, "lr": 1.4500278812323127e-05, "epoch": 13.483498349834983, "percentage": 67.42, "elapsed_time": "4:50:07", "remaining_time": "2:20:13", "throughput": 1485.86, "total_tokens": 25865600} {"current_steps": 122570, "total_steps": 181800, "loss": 0.0048, "lr": 1.4498100729009029e-05, "epoch": 13.484048404840484, "percentage": 67.42, "elapsed_time": "4:50:08", "remaining_time": "2:20:12", "throughput": 1485.87, "total_tokens": 25866720} {"current_steps": 122575, "total_steps": 181800, "loss": 0.0386, "lr": 1.4495922742485893e-05, "epoch": 13.484598459845985, "percentage": 67.42, "elapsed_time": "4:50:09", "remaining_time": "2:20:11", "throughput": 1485.86, "total_tokens": 25867712} {"current_steps": 122580, "total_steps": 181800, "loss": 0.0472, "lr": 1.4493744852773812e-05, "epoch": 13.485148514851485, "percentage": 67.43, "elapsed_time": "4:50:09", "remaining_time": "2:20:10", "throughput": 1485.86, "total_tokens": 25868736} {"current_steps": 122585, "total_steps": 181800, "loss": 0.0034, "lr": 1.4491567059892827e-05, "epoch": 13.485698569856986, "percentage": 67.43, "elapsed_time": "4:50:10", "remaining_time": "2:20:10", "throughput": 1485.87, "total_tokens": 25869792} {"current_steps": 122590, "total_steps": 181800, "loss": 0.0322, "lr": 1.4489389363863037e-05, "epoch": 13.486248624862487, "percentage": 67.43, "elapsed_time": "4:50:11", "remaining_time": "2:20:09", "throughput": 1485.87, "total_tokens": 25870880} {"current_steps": 122595, "total_steps": 181800, "loss": 0.0744, "lr": 1.4487211764704495e-05, "epoch": 13.486798679867986, "percentage": 67.43, "elapsed_time": "4:50:11", "remaining_time": "2:20:08", "throughput": 1485.88, "total_tokens": 25872064} {"current_steps": 122600, "total_steps": 181800, "loss": 0.0573, "lr": 1.4485034262437278e-05, "epoch": 13.487348734873487, "percentage": 67.44, "elapsed_time": "4:50:12", "remaining_time": "2:20:08", "throughput": 1485.88, "total_tokens": 25873056} {"current_steps": 122605, "total_steps": 181800, "loss": 0.0054, "lr": 1.4482856857081461e-05, "epoch": 13.487898789878988, "percentage": 67.44, "elapsed_time": "4:50:13", "remaining_time": "2:20:07", "throughput": 1485.88, "total_tokens": 25874112} {"current_steps": 122610, "total_steps": 181800, "loss": 0.1484, "lr": 1.448067954865711e-05, "epoch": 13.488448844884488, "percentage": 67.44, "elapsed_time": "4:50:14", "remaining_time": "2:20:06", "throughput": 1485.88, "total_tokens": 25875168} {"current_steps": 122615, "total_steps": 181800, "loss": 0.021, "lr": 1.4478502337184274e-05, "epoch": 13.488998899889989, "percentage": 67.44, "elapsed_time": "4:50:14", "remaining_time": "2:20:05", "throughput": 1485.88, "total_tokens": 25876192} {"current_steps": 122620, "total_steps": 181800, "loss": 0.0036, "lr": 1.4476325222683047e-05, "epoch": 13.48954895489549, "percentage": 67.45, "elapsed_time": "4:50:15", "remaining_time": "2:20:05", "throughput": 1485.88, "total_tokens": 25877248} {"current_steps": 122625, "total_steps": 181800, "loss": 0.007, "lr": 1.4474148205173468e-05, "epoch": 13.490099009900991, "percentage": 67.45, "elapsed_time": "4:50:16", "remaining_time": "2:20:04", "throughput": 1485.89, "total_tokens": 25878336} {"current_steps": 122630, "total_steps": 181800, "loss": 0.0066, "lr": 1.4471971284675614e-05, "epoch": 13.49064906490649, "percentage": 67.45, "elapsed_time": "4:50:16", "remaining_time": "2:20:03", "throughput": 1485.89, "total_tokens": 25879360} {"current_steps": 122635, "total_steps": 181800, "loss": 0.018, "lr": 1.446979446120956e-05, "epoch": 13.491199119911991, "percentage": 67.46, "elapsed_time": "4:50:17", "remaining_time": "2:20:03", "throughput": 1485.89, "total_tokens": 25880448} {"current_steps": 122640, "total_steps": 181800, "loss": 0.002, "lr": 1.4467617734795347e-05, "epoch": 13.491749174917492, "percentage": 67.46, "elapsed_time": "4:50:18", "remaining_time": "2:20:02", "throughput": 1485.89, "total_tokens": 25881504} {"current_steps": 122645, "total_steps": 181800, "loss": 0.0034, "lr": 1.4465441105453058e-05, "epoch": 13.492299229922992, "percentage": 67.46, "elapsed_time": "4:50:18", "remaining_time": "2:20:01", "throughput": 1485.89, "total_tokens": 25882560} {"current_steps": 122650, "total_steps": 181800, "loss": 0.0015, "lr": 1.4463264573202734e-05, "epoch": 13.492849284928493, "percentage": 67.46, "elapsed_time": "4:50:19", "remaining_time": "2:20:00", "throughput": 1485.89, "total_tokens": 25883552} {"current_steps": 122655, "total_steps": 181800, "loss": 0.0879, "lr": 1.4461088138064444e-05, "epoch": 13.493399339933994, "percentage": 67.47, "elapsed_time": "4:50:20", "remaining_time": "2:20:00", "throughput": 1485.89, "total_tokens": 25884576} {"current_steps": 122660, "total_steps": 181800, "loss": 0.0025, "lr": 1.4458911800058257e-05, "epoch": 13.493949394939493, "percentage": 67.47, "elapsed_time": "4:50:20", "remaining_time": "2:19:59", "throughput": 1485.9, "total_tokens": 25885664} {"current_steps": 122665, "total_steps": 181800, "loss": 0.0037, "lr": 1.445673555920421e-05, "epoch": 13.494499449944994, "percentage": 67.47, "elapsed_time": "4:50:21", "remaining_time": "2:19:58", "throughput": 1485.89, "total_tokens": 25886656} {"current_steps": 122670, "total_steps": 181800, "loss": 0.0228, "lr": 1.4454559415522383e-05, "epoch": 13.495049504950495, "percentage": 67.48, "elapsed_time": "4:50:22", "remaining_time": "2:19:57", "throughput": 1485.89, "total_tokens": 25887680} {"current_steps": 122675, "total_steps": 181800, "loss": 0.0371, "lr": 1.4452383369032813e-05, "epoch": 13.495599559955995, "percentage": 67.48, "elapsed_time": "4:50:22", "remaining_time": "2:19:57", "throughput": 1485.9, "total_tokens": 25888736} {"current_steps": 122680, "total_steps": 181800, "loss": 0.1, "lr": 1.4450207419755573e-05, "epoch": 13.496149614961496, "percentage": 67.48, "elapsed_time": "4:50:23", "remaining_time": "2:19:56", "throughput": 1485.9, "total_tokens": 25889760} {"current_steps": 122685, "total_steps": 181800, "loss": 0.007, "lr": 1.4448031567710702e-05, "epoch": 13.496699669966997, "percentage": 67.48, "elapsed_time": "4:50:24", "remaining_time": "2:19:55", "throughput": 1485.9, "total_tokens": 25890784} {"current_steps": 122690, "total_steps": 181800, "loss": 0.0239, "lr": 1.4445855812918257e-05, "epoch": 13.497249724972498, "percentage": 67.49, "elapsed_time": "4:50:25", "remaining_time": "2:19:55", "throughput": 1485.9, "total_tokens": 25891872} {"current_steps": 122695, "total_steps": 181800, "loss": 0.1061, "lr": 1.444368015539831e-05, "epoch": 13.497799779977997, "percentage": 67.49, "elapsed_time": "4:50:25", "remaining_time": "2:19:54", "throughput": 1485.9, "total_tokens": 25892960} {"current_steps": 122700, "total_steps": 181800, "loss": 0.1343, "lr": 1.4441504595170882e-05, "epoch": 13.498349834983498, "percentage": 67.49, "elapsed_time": "4:50:26", "remaining_time": "2:19:53", "throughput": 1485.9, "total_tokens": 25893984} {"current_steps": 122705, "total_steps": 181800, "loss": 0.0681, "lr": 1.4439329132256051e-05, "epoch": 13.498899889989, "percentage": 67.49, "elapsed_time": "4:50:27", "remaining_time": "2:19:52", "throughput": 1485.91, "total_tokens": 25895072} {"current_steps": 122710, "total_steps": 181800, "loss": 0.0014, "lr": 1.4437153766673847e-05, "epoch": 13.499449944994499, "percentage": 67.5, "elapsed_time": "4:50:27", "remaining_time": "2:19:52", "throughput": 1485.91, "total_tokens": 25896128} {"current_steps": 122715, "total_steps": 181800, "loss": 0.0253, "lr": 1.4434978498444327e-05, "epoch": 13.5, "percentage": 67.5, "elapsed_time": "4:50:28", "remaining_time": "2:19:51", "throughput": 1485.91, "total_tokens": 25897216} {"current_steps": 122720, "total_steps": 181800, "loss": 0.0911, "lr": 1.4432803327587551e-05, "epoch": 13.500550055005501, "percentage": 67.5, "elapsed_time": "4:50:29", "remaining_time": "2:19:50", "throughput": 1485.91, "total_tokens": 25898272} {"current_steps": 122725, "total_steps": 181800, "loss": 0.0297, "lr": 1.4430628254123545e-05, "epoch": 13.501100110011, "percentage": 67.51, "elapsed_time": "4:50:29", "remaining_time": "2:19:50", "throughput": 1485.92, "total_tokens": 25899328} {"current_steps": 122730, "total_steps": 181800, "loss": 0.0049, "lr": 1.4428453278072379e-05, "epoch": 13.501650165016502, "percentage": 67.51, "elapsed_time": "4:50:30", "remaining_time": "2:19:49", "throughput": 1485.92, "total_tokens": 25900384} {"current_steps": 122735, "total_steps": 181800, "loss": 0.0114, "lr": 1.4426278399454085e-05, "epoch": 13.502200220022003, "percentage": 67.51, "elapsed_time": "4:50:31", "remaining_time": "2:19:48", "throughput": 1485.92, "total_tokens": 25901536} {"current_steps": 122740, "total_steps": 181800, "loss": 0.0031, "lr": 1.4424103618288701e-05, "epoch": 13.502750275027502, "percentage": 67.51, "elapsed_time": "4:50:31", "remaining_time": "2:19:47", "throughput": 1485.92, "total_tokens": 25902528} {"current_steps": 122745, "total_steps": 181800, "loss": 0.021, "lr": 1.4421928934596277e-05, "epoch": 13.503300330033003, "percentage": 67.52, "elapsed_time": "4:50:32", "remaining_time": "2:19:47", "throughput": 1485.93, "total_tokens": 25903616} {"current_steps": 122750, "total_steps": 181800, "loss": 0.0043, "lr": 1.4419754348396858e-05, "epoch": 13.503850385038504, "percentage": 67.52, "elapsed_time": "4:50:33", "remaining_time": "2:19:46", "throughput": 1485.93, "total_tokens": 25904640} {"current_steps": 122755, "total_steps": 181800, "loss": 0.0107, "lr": 1.4417579859710498e-05, "epoch": 13.504400440044005, "percentage": 67.52, "elapsed_time": "4:50:34", "remaining_time": "2:19:45", "throughput": 1485.93, "total_tokens": 25905696} {"current_steps": 122760, "total_steps": 181800, "loss": 0.0276, "lr": 1.4415405468557225e-05, "epoch": 13.504950495049505, "percentage": 67.52, "elapsed_time": "4:50:34", "remaining_time": "2:19:45", "throughput": 1485.93, "total_tokens": 25906752} {"current_steps": 122765, "total_steps": 181800, "loss": 0.0025, "lr": 1.441323117495707e-05, "epoch": 13.505500550055006, "percentage": 67.53, "elapsed_time": "4:50:35", "remaining_time": "2:19:44", "throughput": 1485.93, "total_tokens": 25907776} {"current_steps": 122770, "total_steps": 181800, "loss": 0.001, "lr": 1.4411056978930088e-05, "epoch": 13.506050605060507, "percentage": 67.53, "elapsed_time": "4:50:36", "remaining_time": "2:19:43", "throughput": 1485.93, "total_tokens": 25908800} {"current_steps": 122775, "total_steps": 181800, "loss": 0.0143, "lr": 1.4408882880496308e-05, "epoch": 13.506600660066006, "percentage": 67.53, "elapsed_time": "4:50:36", "remaining_time": "2:19:42", "throughput": 1485.93, "total_tokens": 25909856} {"current_steps": 122780, "total_steps": 181800, "loss": 0.0893, "lr": 1.4406708879675785e-05, "epoch": 13.507150715071507, "percentage": 67.54, "elapsed_time": "4:50:37", "remaining_time": "2:19:42", "throughput": 1485.93, "total_tokens": 25910880} {"current_steps": 122785, "total_steps": 181800, "loss": 0.0416, "lr": 1.4404534976488542e-05, "epoch": 13.507700770077008, "percentage": 67.54, "elapsed_time": "4:50:38", "remaining_time": "2:19:41", "throughput": 1485.93, "total_tokens": 25911936} {"current_steps": 122790, "total_steps": 181800, "loss": 0.0114, "lr": 1.4402361170954604e-05, "epoch": 13.508250825082508, "percentage": 67.54, "elapsed_time": "4:50:38", "remaining_time": "2:19:40", "throughput": 1485.94, "total_tokens": 25912992} {"current_steps": 122795, "total_steps": 181800, "loss": 0.0024, "lr": 1.4400187463094031e-05, "epoch": 13.508800880088009, "percentage": 67.54, "elapsed_time": "4:50:39", "remaining_time": "2:19:39", "throughput": 1485.94, "total_tokens": 25914048} {"current_steps": 122800, "total_steps": 181800, "loss": 0.0071, "lr": 1.4398013852926834e-05, "epoch": 13.50935093509351, "percentage": 67.55, "elapsed_time": "4:50:40", "remaining_time": "2:19:39", "throughput": 1485.94, "total_tokens": 25915072} {"current_steps": 122805, "total_steps": 181800, "loss": 0.1357, "lr": 1.4395840340473055e-05, "epoch": 13.509900990099009, "percentage": 67.55, "elapsed_time": "4:50:40", "remaining_time": "2:19:38", "throughput": 1485.94, "total_tokens": 25916160} {"current_steps": 122810, "total_steps": 181800, "loss": 0.0029, "lr": 1.4393666925752736e-05, "epoch": 13.51045104510451, "percentage": 67.55, "elapsed_time": "4:50:41", "remaining_time": "2:19:37", "throughput": 1485.95, "total_tokens": 25917248} {"current_steps": 122815, "total_steps": 181800, "loss": 0.0011, "lr": 1.4391493608785888e-05, "epoch": 13.511001100110011, "percentage": 67.56, "elapsed_time": "4:50:42", "remaining_time": "2:19:37", "throughput": 1485.95, "total_tokens": 25918400} {"current_steps": 122820, "total_steps": 181800, "loss": 0.0946, "lr": 1.4389320389592565e-05, "epoch": 13.511551155115512, "percentage": 67.56, "elapsed_time": "4:50:42", "remaining_time": "2:19:36", "throughput": 1485.96, "total_tokens": 25919488} {"current_steps": 122825, "total_steps": 181800, "loss": 0.0678, "lr": 1.4387147268192774e-05, "epoch": 13.512101210121012, "percentage": 67.56, "elapsed_time": "4:50:43", "remaining_time": "2:19:35", "throughput": 1485.95, "total_tokens": 25920480} {"current_steps": 122830, "total_steps": 181800, "loss": 0.017, "lr": 1.4384974244606558e-05, "epoch": 13.512651265126513, "percentage": 67.56, "elapsed_time": "4:50:44", "remaining_time": "2:19:34", "throughput": 1485.95, "total_tokens": 25921504} {"current_steps": 122835, "total_steps": 181800, "loss": 0.1109, "lr": 1.4382801318853945e-05, "epoch": 13.513201320132014, "percentage": 67.57, "elapsed_time": "4:50:45", "remaining_time": "2:19:34", "throughput": 1485.95, "total_tokens": 25922528} {"current_steps": 122840, "total_steps": 181800, "loss": 0.0519, "lr": 1.438062849095495e-05, "epoch": 13.513751375137513, "percentage": 67.57, "elapsed_time": "4:50:45", "remaining_time": "2:19:33", "throughput": 1485.95, "total_tokens": 25923552} {"current_steps": 122845, "total_steps": 181800, "loss": 0.0063, "lr": 1.4378455760929619e-05, "epoch": 13.514301430143014, "percentage": 67.57, "elapsed_time": "4:50:46", "remaining_time": "2:19:32", "throughput": 1485.96, "total_tokens": 25924640} {"current_steps": 122850, "total_steps": 181800, "loss": 0.0576, "lr": 1.4376283128797963e-05, "epoch": 13.514851485148515, "percentage": 67.57, "elapsed_time": "4:50:47", "remaining_time": "2:19:32", "throughput": 1485.96, "total_tokens": 25925696} {"current_steps": 122855, "total_steps": 181800, "loss": 0.0446, "lr": 1.4374110594579996e-05, "epoch": 13.515401540154015, "percentage": 67.58, "elapsed_time": "4:50:47", "remaining_time": "2:19:31", "throughput": 1485.96, "total_tokens": 25926784} {"current_steps": 122860, "total_steps": 181800, "loss": 0.0048, "lr": 1.4371938158295753e-05, "epoch": 13.515951595159516, "percentage": 67.58, "elapsed_time": "4:50:48", "remaining_time": "2:19:30", "throughput": 1485.97, "total_tokens": 25927872} {"current_steps": 122865, "total_steps": 181800, "loss": 0.0644, "lr": 1.4369765819965259e-05, "epoch": 13.516501650165017, "percentage": 67.58, "elapsed_time": "4:50:49", "remaining_time": "2:19:29", "throughput": 1485.97, "total_tokens": 25928928} {"current_steps": 122870, "total_steps": 181800, "loss": 0.0684, "lr": 1.436759357960854e-05, "epoch": 13.517051705170516, "percentage": 67.59, "elapsed_time": "4:50:49", "remaining_time": "2:19:29", "throughput": 1485.96, "total_tokens": 25929888} {"current_steps": 122875, "total_steps": 181800, "loss": 0.0064, "lr": 1.4365421437245608e-05, "epoch": 13.517601760176017, "percentage": 67.59, "elapsed_time": "4:50:50", "remaining_time": "2:19:28", "throughput": 1485.97, "total_tokens": 25931040} {"current_steps": 122880, "total_steps": 181800, "loss": 0.0624, "lr": 1.4363249392896477e-05, "epoch": 13.518151815181518, "percentage": 67.59, "elapsed_time": "4:50:51", "remaining_time": "2:19:27", "throughput": 1485.97, "total_tokens": 25932096} {"current_steps": 122885, "total_steps": 181800, "loss": 0.0869, "lr": 1.4361077446581166e-05, "epoch": 13.51870187018702, "percentage": 67.59, "elapsed_time": "4:50:51", "remaining_time": "2:19:27", "throughput": 1485.98, "total_tokens": 25933216} {"current_steps": 122890, "total_steps": 181800, "loss": 0.0442, "lr": 1.4358905598319706e-05, "epoch": 13.519251925192519, "percentage": 67.6, "elapsed_time": "4:50:52", "remaining_time": "2:19:26", "throughput": 1485.98, "total_tokens": 25934240} {"current_steps": 122895, "total_steps": 181800, "loss": 0.0496, "lr": 1.4356733848132114e-05, "epoch": 13.51980198019802, "percentage": 67.6, "elapsed_time": "4:50:53", "remaining_time": "2:19:25", "throughput": 1485.98, "total_tokens": 25935264} {"current_steps": 122900, "total_steps": 181800, "loss": 0.0074, "lr": 1.4354562196038402e-05, "epoch": 13.520352035203521, "percentage": 67.6, "elapsed_time": "4:50:54", "remaining_time": "2:19:24", "throughput": 1485.98, "total_tokens": 25936288} {"current_steps": 122905, "total_steps": 181800, "loss": 0.0049, "lr": 1.435239064205857e-05, "epoch": 13.52090209020902, "percentage": 67.6, "elapsed_time": "4:50:54", "remaining_time": "2:19:24", "throughput": 1485.98, "total_tokens": 25937312} {"current_steps": 122910, "total_steps": 181800, "loss": 0.0204, "lr": 1.4350219186212654e-05, "epoch": 13.521452145214521, "percentage": 67.61, "elapsed_time": "4:50:55", "remaining_time": "2:19:23", "throughput": 1485.97, "total_tokens": 25938272} {"current_steps": 122915, "total_steps": 181800, "loss": 0.002, "lr": 1.4348047828520645e-05, "epoch": 13.522002200220022, "percentage": 67.61, "elapsed_time": "4:50:56", "remaining_time": "2:19:22", "throughput": 1485.98, "total_tokens": 25939328} {"current_steps": 122920, "total_steps": 181800, "loss": 0.0209, "lr": 1.434587656900257e-05, "epoch": 13.522552255225522, "percentage": 67.61, "elapsed_time": "4:50:56", "remaining_time": "2:19:21", "throughput": 1485.98, "total_tokens": 25940352} {"current_steps": 122925, "total_steps": 181800, "loss": 0.0012, "lr": 1.4343705407678448e-05, "epoch": 13.523102310231023, "percentage": 67.62, "elapsed_time": "4:50:57", "remaining_time": "2:19:21", "throughput": 1485.98, "total_tokens": 25941440} {"current_steps": 122930, "total_steps": 181800, "loss": 0.0065, "lr": 1.4341534344568273e-05, "epoch": 13.523652365236524, "percentage": 67.62, "elapsed_time": "4:50:58", "remaining_time": "2:19:20", "throughput": 1485.98, "total_tokens": 25942496} {"current_steps": 122935, "total_steps": 181800, "loss": 0.0364, "lr": 1.4339363379692067e-05, "epoch": 13.524202420242025, "percentage": 67.62, "elapsed_time": "4:50:58", "remaining_time": "2:19:19", "throughput": 1485.98, "total_tokens": 25943552} {"current_steps": 122940, "total_steps": 181800, "loss": 0.0189, "lr": 1.4337192513069827e-05, "epoch": 13.524752475247524, "percentage": 67.62, "elapsed_time": "4:50:59", "remaining_time": "2:19:19", "throughput": 1485.98, "total_tokens": 25944608} {"current_steps": 122945, "total_steps": 181800, "loss": 0.003, "lr": 1.4335021744721565e-05, "epoch": 13.525302530253025, "percentage": 67.63, "elapsed_time": "4:51:00", "remaining_time": "2:19:18", "throughput": 1485.99, "total_tokens": 25945664} {"current_steps": 122950, "total_steps": 181800, "loss": 0.0382, "lr": 1.43328510746673e-05, "epoch": 13.525852585258527, "percentage": 67.63, "elapsed_time": "4:51:00", "remaining_time": "2:19:17", "throughput": 1485.99, "total_tokens": 25946720} {"current_steps": 122955, "total_steps": 181800, "loss": 0.0435, "lr": 1.4330680502927019e-05, "epoch": 13.526402640264026, "percentage": 67.63, "elapsed_time": "4:51:01", "remaining_time": "2:19:16", "throughput": 1485.99, "total_tokens": 25947808} {"current_steps": 122960, "total_steps": 181800, "loss": 0.0042, "lr": 1.4328510029520747e-05, "epoch": 13.526952695269527, "percentage": 67.63, "elapsed_time": "4:51:02", "remaining_time": "2:19:16", "throughput": 1485.99, "total_tokens": 25948832} {"current_steps": 122965, "total_steps": 181800, "loss": 0.0981, "lr": 1.4326339654468466e-05, "epoch": 13.527502750275028, "percentage": 67.64, "elapsed_time": "4:51:02", "remaining_time": "2:19:15", "throughput": 1485.99, "total_tokens": 25949888} {"current_steps": 122970, "total_steps": 181800, "loss": 0.0012, "lr": 1.4324169377790197e-05, "epoch": 13.528052805280527, "percentage": 67.64, "elapsed_time": "4:51:03", "remaining_time": "2:19:14", "throughput": 1486.0, "total_tokens": 25951008} {"current_steps": 122975, "total_steps": 181800, "loss": 0.0103, "lr": 1.432199919950593e-05, "epoch": 13.528602860286028, "percentage": 67.64, "elapsed_time": "4:51:04", "remaining_time": "2:19:14", "throughput": 1486.0, "total_tokens": 25952032} {"current_steps": 122980, "total_steps": 181800, "loss": 0.0403, "lr": 1.4319829119635674e-05, "epoch": 13.52915291529153, "percentage": 67.65, "elapsed_time": "4:51:05", "remaining_time": "2:19:13", "throughput": 1486.0, "total_tokens": 25953088} {"current_steps": 122985, "total_steps": 181800, "loss": 0.0033, "lr": 1.4317659138199436e-05, "epoch": 13.52970297029703, "percentage": 67.65, "elapsed_time": "4:51:05", "remaining_time": "2:19:12", "throughput": 1486.0, "total_tokens": 25954144} {"current_steps": 122990, "total_steps": 181800, "loss": 0.0103, "lr": 1.431548925521721e-05, "epoch": 13.53025302530253, "percentage": 67.65, "elapsed_time": "4:51:06", "remaining_time": "2:19:11", "throughput": 1486.0, "total_tokens": 25955200} {"current_steps": 122995, "total_steps": 181800, "loss": 0.0109, "lr": 1.431331947070898e-05, "epoch": 13.530803080308031, "percentage": 67.65, "elapsed_time": "4:51:07", "remaining_time": "2:19:11", "throughput": 1486.01, "total_tokens": 25956256} {"current_steps": 123000, "total_steps": 181800, "loss": 0.0042, "lr": 1.4311149784694766e-05, "epoch": 13.531353135313532, "percentage": 67.66, "elapsed_time": "4:51:07", "remaining_time": "2:19:10", "throughput": 1486.01, "total_tokens": 25957312} {"current_steps": 123005, "total_steps": 181800, "loss": 0.0149, "lr": 1.4308980197194539e-05, "epoch": 13.531903190319031, "percentage": 67.66, "elapsed_time": "4:51:08", "remaining_time": "2:19:09", "throughput": 1486.01, "total_tokens": 25958400} {"current_steps": 123010, "total_steps": 181800, "loss": 0.0659, "lr": 1.4306810708228329e-05, "epoch": 13.532453245324533, "percentage": 67.66, "elapsed_time": "4:51:09", "remaining_time": "2:19:09", "throughput": 1486.01, "total_tokens": 25959424} {"current_steps": 123015, "total_steps": 181800, "loss": 0.0029, "lr": 1.4304641317816114e-05, "epoch": 13.533003300330034, "percentage": 67.67, "elapsed_time": "4:51:09", "remaining_time": "2:19:08", "throughput": 1486.01, "total_tokens": 25960480} {"current_steps": 123020, "total_steps": 181800, "loss": 0.0049, "lr": 1.4302472025977876e-05, "epoch": 13.533553355335533, "percentage": 67.67, "elapsed_time": "4:51:10", "remaining_time": "2:19:07", "throughput": 1486.02, "total_tokens": 25961600} {"current_steps": 123025, "total_steps": 181800, "loss": 0.0061, "lr": 1.4300302832733633e-05, "epoch": 13.534103410341034, "percentage": 67.67, "elapsed_time": "4:51:11", "remaining_time": "2:19:06", "throughput": 1486.02, "total_tokens": 25962624} {"current_steps": 123030, "total_steps": 181800, "loss": 0.005, "lr": 1.4298133738103353e-05, "epoch": 13.534653465346535, "percentage": 67.67, "elapsed_time": "4:51:11", "remaining_time": "2:19:06", "throughput": 1486.02, "total_tokens": 25963648} {"current_steps": 123035, "total_steps": 181800, "loss": 0.0073, "lr": 1.429596474210704e-05, "epoch": 13.535203520352034, "percentage": 67.68, "elapsed_time": "4:51:12", "remaining_time": "2:19:05", "throughput": 1486.02, "total_tokens": 25964672} {"current_steps": 123040, "total_steps": 181800, "loss": 0.0105, "lr": 1.4293795844764693e-05, "epoch": 13.535753575357536, "percentage": 67.68, "elapsed_time": "4:51:13", "remaining_time": "2:19:04", "throughput": 1486.02, "total_tokens": 25965760} {"current_steps": 123045, "total_steps": 181800, "loss": 0.0058, "lr": 1.4291627046096285e-05, "epoch": 13.536303630363037, "percentage": 67.68, "elapsed_time": "4:51:14", "remaining_time": "2:19:03", "throughput": 1486.02, "total_tokens": 25966784} {"current_steps": 123050, "total_steps": 181800, "loss": 0.0051, "lr": 1.428945834612182e-05, "epoch": 13.536853685368538, "percentage": 67.68, "elapsed_time": "4:51:14", "remaining_time": "2:19:03", "throughput": 1486.02, "total_tokens": 25967744} {"current_steps": 123055, "total_steps": 181800, "loss": 0.1851, "lr": 1.4287289744861264e-05, "epoch": 13.537403740374037, "percentage": 67.69, "elapsed_time": "4:51:15", "remaining_time": "2:19:02", "throughput": 1486.02, "total_tokens": 25968832} {"current_steps": 123060, "total_steps": 181800, "loss": 0.1109, "lr": 1.4285121242334622e-05, "epoch": 13.537953795379538, "percentage": 67.69, "elapsed_time": "4:51:16", "remaining_time": "2:19:01", "throughput": 1486.02, "total_tokens": 25969856} {"current_steps": 123065, "total_steps": 181800, "loss": 0.0615, "lr": 1.4282952838561887e-05, "epoch": 13.53850385038504, "percentage": 67.69, "elapsed_time": "4:51:16", "remaining_time": "2:19:01", "throughput": 1486.02, "total_tokens": 25970848} {"current_steps": 123070, "total_steps": 181800, "loss": 0.0122, "lr": 1.4280784533563025e-05, "epoch": 13.539053905390539, "percentage": 67.7, "elapsed_time": "4:51:17", "remaining_time": "2:19:00", "throughput": 1486.02, "total_tokens": 25971936} {"current_steps": 123075, "total_steps": 181800, "loss": 0.0082, "lr": 1.4278616327358032e-05, "epoch": 13.53960396039604, "percentage": 67.7, "elapsed_time": "4:51:18", "remaining_time": "2:18:59", "throughput": 1486.03, "total_tokens": 25972992} {"current_steps": 123080, "total_steps": 181800, "loss": 0.0133, "lr": 1.4276448219966881e-05, "epoch": 13.54015401540154, "percentage": 67.7, "elapsed_time": "4:51:18", "remaining_time": "2:18:58", "throughput": 1486.03, "total_tokens": 25974112} {"current_steps": 123085, "total_steps": 181800, "loss": 0.0553, "lr": 1.4274280211409571e-05, "epoch": 13.54070407040704, "percentage": 67.7, "elapsed_time": "4:51:19", "remaining_time": "2:18:58", "throughput": 1486.03, "total_tokens": 25975136} {"current_steps": 123090, "total_steps": 181800, "loss": 0.0624, "lr": 1.4272112301706064e-05, "epoch": 13.541254125412541, "percentage": 67.71, "elapsed_time": "4:51:20", "remaining_time": "2:18:57", "throughput": 1486.03, "total_tokens": 25976160} {"current_steps": 123095, "total_steps": 181800, "loss": 0.0343, "lr": 1.426994449087635e-05, "epoch": 13.541804180418042, "percentage": 67.71, "elapsed_time": "4:51:20", "remaining_time": "2:18:56", "throughput": 1486.03, "total_tokens": 25977216} {"current_steps": 123100, "total_steps": 181800, "loss": 0.0074, "lr": 1.4267776778940418e-05, "epoch": 13.542354235423542, "percentage": 67.71, "elapsed_time": "4:51:21", "remaining_time": "2:18:56", "throughput": 1486.03, "total_tokens": 25978240} {"current_steps": 123105, "total_steps": 181800, "loss": 0.0439, "lr": 1.4265609165918229e-05, "epoch": 13.542904290429043, "percentage": 67.71, "elapsed_time": "4:51:22", "remaining_time": "2:18:55", "throughput": 1486.04, "total_tokens": 25979328} {"current_steps": 123110, "total_steps": 181800, "loss": 0.08, "lr": 1.4263441651829778e-05, "epoch": 13.543454345434544, "percentage": 67.72, "elapsed_time": "4:51:22", "remaining_time": "2:18:54", "throughput": 1486.04, "total_tokens": 25980384} {"current_steps": 123115, "total_steps": 181800, "loss": 0.0048, "lr": 1.4261274236695035e-05, "epoch": 13.544004400440045, "percentage": 67.72, "elapsed_time": "4:51:23", "remaining_time": "2:18:53", "throughput": 1486.04, "total_tokens": 25981408} {"current_steps": 123120, "total_steps": 181800, "loss": 0.0052, "lr": 1.4259106920533955e-05, "epoch": 13.544554455445544, "percentage": 67.72, "elapsed_time": "4:51:24", "remaining_time": "2:18:53", "throughput": 1486.04, "total_tokens": 25982496} {"current_steps": 123125, "total_steps": 181800, "loss": 0.1014, "lr": 1.4256939703366551e-05, "epoch": 13.545104510451045, "percentage": 67.73, "elapsed_time": "4:51:25", "remaining_time": "2:18:52", "throughput": 1486.05, "total_tokens": 25983552} {"current_steps": 123130, "total_steps": 181800, "loss": 0.0062, "lr": 1.4254772585212767e-05, "epoch": 13.545654565456546, "percentage": 67.73, "elapsed_time": "4:51:25", "remaining_time": "2:18:51", "throughput": 1486.05, "total_tokens": 25984640} {"current_steps": 123135, "total_steps": 181800, "loss": 0.0013, "lr": 1.42526055660926e-05, "epoch": 13.546204620462046, "percentage": 67.73, "elapsed_time": "4:51:26", "remaining_time": "2:18:51", "throughput": 1486.05, "total_tokens": 25985664} {"current_steps": 123140, "total_steps": 181800, "loss": 0.0004, "lr": 1.425043864602601e-05, "epoch": 13.546754675467547, "percentage": 67.73, "elapsed_time": "4:51:27", "remaining_time": "2:18:50", "throughput": 1486.05, "total_tokens": 25986784} {"current_steps": 123145, "total_steps": 181800, "loss": 0.0033, "lr": 1.424827182503296e-05, "epoch": 13.547304730473048, "percentage": 67.74, "elapsed_time": "4:51:27", "remaining_time": "2:18:49", "throughput": 1486.06, "total_tokens": 25987840} {"current_steps": 123150, "total_steps": 181800, "loss": 0.0081, "lr": 1.4246105103133428e-05, "epoch": 13.547854785478547, "percentage": 67.74, "elapsed_time": "4:51:28", "remaining_time": "2:18:48", "throughput": 1486.06, "total_tokens": 25988896} {"current_steps": 123155, "total_steps": 181800, "loss": 0.0366, "lr": 1.4243938480347385e-05, "epoch": 13.548404840484048, "percentage": 67.74, "elapsed_time": "4:51:29", "remaining_time": "2:18:48", "throughput": 1486.06, "total_tokens": 25989888} {"current_steps": 123160, "total_steps": 181800, "loss": 0.0057, "lr": 1.424177195669481e-05, "epoch": 13.54895489548955, "percentage": 67.74, "elapsed_time": "4:51:29", "remaining_time": "2:18:47", "throughput": 1486.06, "total_tokens": 25991008} {"current_steps": 123165, "total_steps": 181800, "loss": 0.0059, "lr": 1.423960553219566e-05, "epoch": 13.549504950495049, "percentage": 67.75, "elapsed_time": "4:51:30", "remaining_time": "2:18:46", "throughput": 1486.06, "total_tokens": 25992064} {"current_steps": 123170, "total_steps": 181800, "loss": 0.0321, "lr": 1.4237439206869896e-05, "epoch": 13.55005500550055, "percentage": 67.75, "elapsed_time": "4:51:31", "remaining_time": "2:18:45", "throughput": 1486.07, "total_tokens": 25993120} {"current_steps": 123175, "total_steps": 181800, "loss": 0.0917, "lr": 1.4235272980737497e-05, "epoch": 13.55060506050605, "percentage": 67.75, "elapsed_time": "4:51:31", "remaining_time": "2:18:45", "throughput": 1486.07, "total_tokens": 25994208} {"current_steps": 123180, "total_steps": 181800, "loss": 0.0038, "lr": 1.4233106853818412e-05, "epoch": 13.551155115511552, "percentage": 67.76, "elapsed_time": "4:51:32", "remaining_time": "2:18:44", "throughput": 1486.07, "total_tokens": 25995200} {"current_steps": 123185, "total_steps": 181800, "loss": 0.0015, "lr": 1.4230940826132617e-05, "epoch": 13.551705170517051, "percentage": 67.76, "elapsed_time": "4:51:33", "remaining_time": "2:18:43", "throughput": 1486.07, "total_tokens": 25996288} {"current_steps": 123190, "total_steps": 181800, "loss": 0.0112, "lr": 1.4228774897700079e-05, "epoch": 13.552255225522552, "percentage": 67.76, "elapsed_time": "4:51:33", "remaining_time": "2:18:43", "throughput": 1486.07, "total_tokens": 25997312} {"current_steps": 123195, "total_steps": 181800, "loss": 0.0145, "lr": 1.4226609068540747e-05, "epoch": 13.552805280528053, "percentage": 67.76, "elapsed_time": "4:51:34", "remaining_time": "2:18:42", "throughput": 1486.08, "total_tokens": 25998432} {"current_steps": 123200, "total_steps": 181800, "loss": 0.0633, "lr": 1.4224443338674597e-05, "epoch": 13.553355335533553, "percentage": 67.77, "elapsed_time": "4:51:35", "remaining_time": "2:18:41", "throughput": 1486.08, "total_tokens": 25999488} {"current_steps": 123205, "total_steps": 181800, "loss": 0.0787, "lr": 1.4222277708121573e-05, "epoch": 13.553905390539054, "percentage": 67.77, "elapsed_time": "4:51:36", "remaining_time": "2:18:40", "throughput": 1486.08, "total_tokens": 26000544} {"current_steps": 123210, "total_steps": 181800, "loss": 0.0526, "lr": 1.4220112176901646e-05, "epoch": 13.554455445544555, "percentage": 67.77, "elapsed_time": "4:51:36", "remaining_time": "2:18:40", "throughput": 1486.08, "total_tokens": 26001600} {"current_steps": 123215, "total_steps": 181800, "loss": 0.0017, "lr": 1.4217946745034782e-05, "epoch": 13.555005500550054, "percentage": 67.78, "elapsed_time": "4:51:37", "remaining_time": "2:18:39", "throughput": 1486.08, "total_tokens": 26002656} {"current_steps": 123220, "total_steps": 181800, "loss": 0.0042, "lr": 1.4215781412540919e-05, "epoch": 13.555555555555555, "percentage": 67.78, "elapsed_time": "4:51:38", "remaining_time": "2:18:38", "throughput": 1486.08, "total_tokens": 26003680} {"current_steps": 123225, "total_steps": 181800, "loss": 0.0097, "lr": 1.4213616179440031e-05, "epoch": 13.556105610561056, "percentage": 67.78, "elapsed_time": "4:51:38", "remaining_time": "2:18:38", "throughput": 1486.09, "total_tokens": 26004768} {"current_steps": 123230, "total_steps": 181800, "loss": 0.0013, "lr": 1.421145104575207e-05, "epoch": 13.556655665566556, "percentage": 67.78, "elapsed_time": "4:51:39", "remaining_time": "2:18:37", "throughput": 1486.09, "total_tokens": 26005792} {"current_steps": 123235, "total_steps": 181800, "loss": 0.0133, "lr": 1.4209286011496974e-05, "epoch": 13.557205720572057, "percentage": 67.79, "elapsed_time": "4:51:40", "remaining_time": "2:18:36", "throughput": 1486.09, "total_tokens": 26006784} {"current_steps": 123240, "total_steps": 181800, "loss": 0.005, "lr": 1.4207121076694716e-05, "epoch": 13.557755775577558, "percentage": 67.79, "elapsed_time": "4:51:40", "remaining_time": "2:18:35", "throughput": 1486.09, "total_tokens": 26007840} {"current_steps": 123245, "total_steps": 181800, "loss": 0.0033, "lr": 1.4204956241365242e-05, "epoch": 13.558305830583059, "percentage": 67.79, "elapsed_time": "4:51:41", "remaining_time": "2:18:35", "throughput": 1486.09, "total_tokens": 26008960} {"current_steps": 123250, "total_steps": 181800, "loss": 0.0022, "lr": 1.4202791505528515e-05, "epoch": 13.558855885588558, "percentage": 67.79, "elapsed_time": "4:51:42", "remaining_time": "2:18:34", "throughput": 1486.09, "total_tokens": 26010016} {"current_steps": 123255, "total_steps": 181800, "loss": 0.0025, "lr": 1.420062686920448e-05, "epoch": 13.55940594059406, "percentage": 67.8, "elapsed_time": "4:51:42", "remaining_time": "2:18:33", "throughput": 1486.1, "total_tokens": 26011136} {"current_steps": 123260, "total_steps": 181800, "loss": 0.002, "lr": 1.4198462332413073e-05, "epoch": 13.55995599559956, "percentage": 67.8, "elapsed_time": "4:51:43", "remaining_time": "2:18:33", "throughput": 1486.11, "total_tokens": 26012256} {"current_steps": 123265, "total_steps": 181800, "loss": 0.0812, "lr": 1.4196297895174256e-05, "epoch": 13.56050605060506, "percentage": 67.8, "elapsed_time": "4:51:44", "remaining_time": "2:18:32", "throughput": 1486.11, "total_tokens": 26013344} {"current_steps": 123270, "total_steps": 181800, "loss": 0.0159, "lr": 1.4194133557507977e-05, "epoch": 13.561056105610561, "percentage": 67.81, "elapsed_time": "4:51:45", "remaining_time": "2:18:31", "throughput": 1486.11, "total_tokens": 26014432} {"current_steps": 123275, "total_steps": 181800, "loss": 0.0085, "lr": 1.4191969319434196e-05, "epoch": 13.561606160616062, "percentage": 67.81, "elapsed_time": "4:51:45", "remaining_time": "2:18:30", "throughput": 1486.11, "total_tokens": 26015456} {"current_steps": 123280, "total_steps": 181800, "loss": 0.0024, "lr": 1.4189805180972848e-05, "epoch": 13.562156215621561, "percentage": 67.81, "elapsed_time": "4:51:46", "remaining_time": "2:18:30", "throughput": 1486.11, "total_tokens": 26016512} {"current_steps": 123285, "total_steps": 181800, "loss": 0.1016, "lr": 1.4187641142143865e-05, "epoch": 13.562706270627062, "percentage": 67.81, "elapsed_time": "4:51:47", "remaining_time": "2:18:29", "throughput": 1486.11, "total_tokens": 26017536} {"current_steps": 123290, "total_steps": 181800, "loss": 0.0463, "lr": 1.4185477202967218e-05, "epoch": 13.563256325632564, "percentage": 67.82, "elapsed_time": "4:51:47", "remaining_time": "2:18:28", "throughput": 1486.12, "total_tokens": 26018592} {"current_steps": 123295, "total_steps": 181800, "loss": 0.0016, "lr": 1.4183313363462824e-05, "epoch": 13.563806380638063, "percentage": 67.82, "elapsed_time": "4:51:48", "remaining_time": "2:18:27", "throughput": 1486.12, "total_tokens": 26019648} {"current_steps": 123300, "total_steps": 181800, "loss": 0.0025, "lr": 1.4181149623650646e-05, "epoch": 13.564356435643564, "percentage": 67.82, "elapsed_time": "4:51:49", "remaining_time": "2:18:27", "throughput": 1486.12, "total_tokens": 26020736} {"current_steps": 123305, "total_steps": 181800, "loss": 0.0297, "lr": 1.4178985983550628e-05, "epoch": 13.564906490649065, "percentage": 67.82, "elapsed_time": "4:51:49", "remaining_time": "2:18:26", "throughput": 1486.13, "total_tokens": 26021888} {"current_steps": 123310, "total_steps": 181800, "loss": 0.0223, "lr": 1.4176822443182695e-05, "epoch": 13.565456545654566, "percentage": 67.83, "elapsed_time": "4:51:50", "remaining_time": "2:18:25", "throughput": 1486.13, "total_tokens": 26022944} {"current_steps": 123315, "total_steps": 181800, "loss": 0.0284, "lr": 1.4174659002566804e-05, "epoch": 13.566006600660065, "percentage": 67.83, "elapsed_time": "4:51:51", "remaining_time": "2:18:25", "throughput": 1486.13, "total_tokens": 26024032} {"current_steps": 123320, "total_steps": 181800, "loss": 0.0039, "lr": 1.4172495661722879e-05, "epoch": 13.566556655665567, "percentage": 67.83, "elapsed_time": "4:51:51", "remaining_time": "2:18:24", "throughput": 1486.13, "total_tokens": 26025056} {"current_steps": 123325, "total_steps": 181800, "loss": 0.0913, "lr": 1.4170332420670863e-05, "epoch": 13.567106710671068, "percentage": 67.84, "elapsed_time": "4:51:52", "remaining_time": "2:18:23", "throughput": 1486.13, "total_tokens": 26026080} {"current_steps": 123330, "total_steps": 181800, "loss": 0.0935, "lr": 1.4168169279430707e-05, "epoch": 13.567656765676567, "percentage": 67.84, "elapsed_time": "4:51:53", "remaining_time": "2:18:22", "throughput": 1486.13, "total_tokens": 26027136} {"current_steps": 123335, "total_steps": 181800, "loss": 0.0153, "lr": 1.4166006238022327e-05, "epoch": 13.568206820682068, "percentage": 67.84, "elapsed_time": "4:51:54", "remaining_time": "2:18:22", "throughput": 1486.14, "total_tokens": 26028224} {"current_steps": 123340, "total_steps": 181800, "loss": 0.0309, "lr": 1.4163843296465681e-05, "epoch": 13.56875687568757, "percentage": 67.84, "elapsed_time": "4:51:54", "remaining_time": "2:18:21", "throughput": 1486.14, "total_tokens": 26029248} {"current_steps": 123345, "total_steps": 181800, "loss": 0.0031, "lr": 1.4161680454780679e-05, "epoch": 13.569306930693068, "percentage": 67.85, "elapsed_time": "4:51:55", "remaining_time": "2:18:20", "throughput": 1486.14, "total_tokens": 26030368} {"current_steps": 123350, "total_steps": 181800, "loss": 0.0148, "lr": 1.415951771298728e-05, "epoch": 13.56985698569857, "percentage": 67.85, "elapsed_time": "4:51:56", "remaining_time": "2:18:20", "throughput": 1486.14, "total_tokens": 26031392} {"current_steps": 123355, "total_steps": 181800, "loss": 0.0094, "lr": 1.4157355071105393e-05, "epoch": 13.57040704070407, "percentage": 67.85, "elapsed_time": "4:51:56", "remaining_time": "2:18:19", "throughput": 1486.14, "total_tokens": 26032416} {"current_steps": 123360, "total_steps": 181800, "loss": 0.0231, "lr": 1.4155192529154965e-05, "epoch": 13.570957095709572, "percentage": 67.85, "elapsed_time": "4:51:57", "remaining_time": "2:18:18", "throughput": 1486.14, "total_tokens": 26033472} {"current_steps": 123365, "total_steps": 181800, "loss": 0.0073, "lr": 1.4153030087155928e-05, "epoch": 13.571507150715071, "percentage": 67.86, "elapsed_time": "4:51:58", "remaining_time": "2:18:17", "throughput": 1486.15, "total_tokens": 26034528} {"current_steps": 123370, "total_steps": 181800, "loss": 0.0093, "lr": 1.415086774512821e-05, "epoch": 13.572057205720572, "percentage": 67.86, "elapsed_time": "4:51:58", "remaining_time": "2:18:17", "throughput": 1486.15, "total_tokens": 26035584} {"current_steps": 123375, "total_steps": 181800, "loss": 0.0018, "lr": 1.414870550309173e-05, "epoch": 13.572607260726073, "percentage": 67.86, "elapsed_time": "4:51:59", "remaining_time": "2:18:16", "throughput": 1486.15, "total_tokens": 26036608} {"current_steps": 123380, "total_steps": 181800, "loss": 0.0053, "lr": 1.4146543361066422e-05, "epoch": 13.573157315731573, "percentage": 67.87, "elapsed_time": "4:52:00", "remaining_time": "2:18:15", "throughput": 1486.15, "total_tokens": 26037696} {"current_steps": 123385, "total_steps": 181800, "loss": 0.1048, "lr": 1.4144381319072216e-05, "epoch": 13.573707370737074, "percentage": 67.87, "elapsed_time": "4:52:00", "remaining_time": "2:18:15", "throughput": 1486.15, "total_tokens": 26038752} {"current_steps": 123390, "total_steps": 181800, "loss": 0.0212, "lr": 1.4142219377129052e-05, "epoch": 13.574257425742575, "percentage": 67.87, "elapsed_time": "4:52:01", "remaining_time": "2:18:14", "throughput": 1486.16, "total_tokens": 26039840} {"current_steps": 123395, "total_steps": 181800, "loss": 0.009, "lr": 1.4140057535256837e-05, "epoch": 13.574807480748074, "percentage": 67.87, "elapsed_time": "4:52:02", "remaining_time": "2:18:13", "throughput": 1486.16, "total_tokens": 26040896} {"current_steps": 123400, "total_steps": 181800, "loss": 0.0005, "lr": 1.4137895793475491e-05, "epoch": 13.575357535753575, "percentage": 67.88, "elapsed_time": "4:52:02", "remaining_time": "2:18:12", "throughput": 1486.16, "total_tokens": 26041984} {"current_steps": 123405, "total_steps": 181800, "loss": 0.0057, "lr": 1.413573415180496e-05, "epoch": 13.575907590759076, "percentage": 67.88, "elapsed_time": "4:52:03", "remaining_time": "2:18:12", "throughput": 1486.16, "total_tokens": 26043040} {"current_steps": 123410, "total_steps": 181800, "loss": 0.0091, "lr": 1.4133572610265144e-05, "epoch": 13.576457645764577, "percentage": 67.88, "elapsed_time": "4:52:04", "remaining_time": "2:18:11", "throughput": 1486.16, "total_tokens": 26044064} {"current_steps": 123415, "total_steps": 181800, "loss": 0.0037, "lr": 1.4131411168875974e-05, "epoch": 13.577007700770077, "percentage": 67.89, "elapsed_time": "4:52:05", "remaining_time": "2:18:10", "throughput": 1486.17, "total_tokens": 26045152} {"current_steps": 123420, "total_steps": 181800, "loss": 0.0521, "lr": 1.4129249827657381e-05, "epoch": 13.577557755775578, "percentage": 67.89, "elapsed_time": "4:52:05", "remaining_time": "2:18:10", "throughput": 1486.17, "total_tokens": 26046144} {"current_steps": 123425, "total_steps": 181800, "loss": 0.0044, "lr": 1.4127088586629267e-05, "epoch": 13.578107810781079, "percentage": 67.89, "elapsed_time": "4:52:06", "remaining_time": "2:18:09", "throughput": 1486.17, "total_tokens": 26047232} {"current_steps": 123430, "total_steps": 181800, "loss": 0.0875, "lr": 1.412492744581157e-05, "epoch": 13.578657865786578, "percentage": 67.89, "elapsed_time": "4:52:07", "remaining_time": "2:18:08", "throughput": 1486.17, "total_tokens": 26048352} {"current_steps": 123435, "total_steps": 181800, "loss": 0.0127, "lr": 1.412276640522419e-05, "epoch": 13.57920792079208, "percentage": 67.9, "elapsed_time": "4:52:07", "remaining_time": "2:18:07", "throughput": 1486.17, "total_tokens": 26049376} {"current_steps": 123440, "total_steps": 181800, "loss": 0.1447, "lr": 1.4120605464887052e-05, "epoch": 13.57975797579758, "percentage": 67.9, "elapsed_time": "4:52:08", "remaining_time": "2:18:07", "throughput": 1486.17, "total_tokens": 26050368} {"current_steps": 123445, "total_steps": 181800, "loss": 0.0021, "lr": 1.4118444624820082e-05, "epoch": 13.58030803080308, "percentage": 67.9, "elapsed_time": "4:52:09", "remaining_time": "2:18:06", "throughput": 1486.17, "total_tokens": 26051424} {"current_steps": 123450, "total_steps": 181800, "loss": 0.0351, "lr": 1.4116283885043174e-05, "epoch": 13.58085808580858, "percentage": 67.9, "elapsed_time": "4:52:09", "remaining_time": "2:18:05", "throughput": 1486.17, "total_tokens": 26052448} {"current_steps": 123455, "total_steps": 181800, "loss": 0.164, "lr": 1.4114123245576272e-05, "epoch": 13.581408140814082, "percentage": 67.91, "elapsed_time": "4:52:10", "remaining_time": "2:18:04", "throughput": 1486.18, "total_tokens": 26053536} {"current_steps": 123460, "total_steps": 181800, "loss": 0.015, "lr": 1.4111962706439258e-05, "epoch": 13.581958195819581, "percentage": 67.91, "elapsed_time": "4:52:11", "remaining_time": "2:18:04", "throughput": 1486.18, "total_tokens": 26054624} {"current_steps": 123465, "total_steps": 181800, "loss": 0.0273, "lr": 1.4109802267652066e-05, "epoch": 13.582508250825082, "percentage": 67.91, "elapsed_time": "4:52:11", "remaining_time": "2:18:03", "throughput": 1486.18, "total_tokens": 26055648} {"current_steps": 123470, "total_steps": 181800, "loss": 0.033, "lr": 1.4107641929234594e-05, "epoch": 13.583058305830583, "percentage": 67.92, "elapsed_time": "4:52:12", "remaining_time": "2:18:02", "throughput": 1486.18, "total_tokens": 26056704} {"current_steps": 123475, "total_steps": 181800, "loss": 0.0185, "lr": 1.4105481691206763e-05, "epoch": 13.583608360836084, "percentage": 67.92, "elapsed_time": "4:52:13", "remaining_time": "2:18:02", "throughput": 1486.18, "total_tokens": 26057760} {"current_steps": 123480, "total_steps": 181800, "loss": 0.0626, "lr": 1.4103321553588483e-05, "epoch": 13.584158415841584, "percentage": 67.92, "elapsed_time": "4:52:14", "remaining_time": "2:18:01", "throughput": 1486.19, "total_tokens": 26058912} {"current_steps": 123485, "total_steps": 181800, "loss": 0.0242, "lr": 1.4101161516399655e-05, "epoch": 13.584708470847085, "percentage": 67.92, "elapsed_time": "4:52:14", "remaining_time": "2:18:00", "throughput": 1486.19, "total_tokens": 26059904} {"current_steps": 123490, "total_steps": 181800, "loss": 0.0128, "lr": 1.4099001579660199e-05, "epoch": 13.585258525852586, "percentage": 67.93, "elapsed_time": "4:52:15", "remaining_time": "2:17:59", "throughput": 1486.19, "total_tokens": 26060992} {"current_steps": 123495, "total_steps": 181800, "loss": 0.0038, "lr": 1.4096841743390005e-05, "epoch": 13.585808580858085, "percentage": 67.93, "elapsed_time": "4:52:16", "remaining_time": "2:17:59", "throughput": 1486.2, "total_tokens": 26062080} {"current_steps": 123500, "total_steps": 181800, "loss": 0.0068, "lr": 1.409468200760899e-05, "epoch": 13.586358635863586, "percentage": 67.93, "elapsed_time": "4:52:16", "remaining_time": "2:17:58", "throughput": 1486.2, "total_tokens": 26063104} {"current_steps": 123505, "total_steps": 181800, "loss": 0.0203, "lr": 1.4092522372337067e-05, "epoch": 13.586908690869087, "percentage": 67.93, "elapsed_time": "4:52:17", "remaining_time": "2:17:57", "throughput": 1486.2, "total_tokens": 26064160} {"current_steps": 123510, "total_steps": 181800, "loss": 0.0106, "lr": 1.4090362837594121e-05, "epoch": 13.587458745874587, "percentage": 67.94, "elapsed_time": "4:52:18", "remaining_time": "2:17:57", "throughput": 1486.2, "total_tokens": 26065248} {"current_steps": 123515, "total_steps": 181800, "loss": 0.0159, "lr": 1.4088203403400075e-05, "epoch": 13.588008800880088, "percentage": 67.94, "elapsed_time": "4:52:18", "remaining_time": "2:17:56", "throughput": 1486.2, "total_tokens": 26066336} {"current_steps": 123520, "total_steps": 181800, "loss": 0.0832, "lr": 1.4086044069774823e-05, "epoch": 13.588558855885589, "percentage": 67.94, "elapsed_time": "4:52:19", "remaining_time": "2:17:55", "throughput": 1486.2, "total_tokens": 26067328} {"current_steps": 123525, "total_steps": 181800, "loss": 0.0017, "lr": 1.4083884836738257e-05, "epoch": 13.589108910891088, "percentage": 67.95, "elapsed_time": "4:52:20", "remaining_time": "2:17:54", "throughput": 1486.2, "total_tokens": 26068320} {"current_steps": 123530, "total_steps": 181800, "loss": 0.0219, "lr": 1.4081725704310284e-05, "epoch": 13.58965896589659, "percentage": 67.95, "elapsed_time": "4:52:20", "remaining_time": "2:17:54", "throughput": 1486.2, "total_tokens": 26069376} {"current_steps": 123535, "total_steps": 181800, "loss": 0.0459, "lr": 1.4079566672510808e-05, "epoch": 13.59020902090209, "percentage": 67.95, "elapsed_time": "4:52:21", "remaining_time": "2:17:53", "throughput": 1486.2, "total_tokens": 26070400} {"current_steps": 123540, "total_steps": 181800, "loss": 0.0761, "lr": 1.4077407741359738e-05, "epoch": 13.590759075907592, "percentage": 67.95, "elapsed_time": "4:52:22", "remaining_time": "2:17:52", "throughput": 1486.2, "total_tokens": 26071392} {"current_steps": 123545, "total_steps": 181800, "loss": 0.0035, "lr": 1.4075248910876953e-05, "epoch": 13.591309130913091, "percentage": 67.96, "elapsed_time": "4:52:23", "remaining_time": "2:17:52", "throughput": 1486.2, "total_tokens": 26072416} {"current_steps": 123550, "total_steps": 181800, "loss": 0.0067, "lr": 1.4073090181082354e-05, "epoch": 13.591859185918592, "percentage": 67.96, "elapsed_time": "4:52:23", "remaining_time": "2:17:51", "throughput": 1486.2, "total_tokens": 26073472} {"current_steps": 123555, "total_steps": 181800, "loss": 0.0437, "lr": 1.4070931551995836e-05, "epoch": 13.592409240924093, "percentage": 67.96, "elapsed_time": "4:52:24", "remaining_time": "2:17:50", "throughput": 1486.2, "total_tokens": 26074560} {"current_steps": 123560, "total_steps": 181800, "loss": 0.0064, "lr": 1.4068773023637308e-05, "epoch": 13.592959295929592, "percentage": 67.96, "elapsed_time": "4:52:25", "remaining_time": "2:17:49", "throughput": 1486.21, "total_tokens": 26075616} {"current_steps": 123565, "total_steps": 181800, "loss": 0.0087, "lr": 1.4066614596026644e-05, "epoch": 13.593509350935093, "percentage": 67.97, "elapsed_time": "4:52:25", "remaining_time": "2:17:49", "throughput": 1486.21, "total_tokens": 26076640} {"current_steps": 123570, "total_steps": 181800, "loss": 0.0182, "lr": 1.4064456269183757e-05, "epoch": 13.594059405940595, "percentage": 67.97, "elapsed_time": "4:52:26", "remaining_time": "2:17:48", "throughput": 1486.21, "total_tokens": 26077696} {"current_steps": 123575, "total_steps": 181800, "loss": 0.0105, "lr": 1.406229804312852e-05, "epoch": 13.594609460946094, "percentage": 67.97, "elapsed_time": "4:52:27", "remaining_time": "2:17:47", "throughput": 1486.21, "total_tokens": 26078752} {"current_steps": 123580, "total_steps": 181800, "loss": 0.0038, "lr": 1.4060139917880837e-05, "epoch": 13.595159515951595, "percentage": 67.98, "elapsed_time": "4:52:27", "remaining_time": "2:17:46", "throughput": 1486.21, "total_tokens": 26079776} {"current_steps": 123585, "total_steps": 181800, "loss": 0.0267, "lr": 1.4057981893460593e-05, "epoch": 13.595709570957096, "percentage": 67.98, "elapsed_time": "4:52:28", "remaining_time": "2:17:46", "throughput": 1486.21, "total_tokens": 26080832} {"current_steps": 123590, "total_steps": 181800, "loss": 0.0025, "lr": 1.4055823969887676e-05, "epoch": 13.596259625962595, "percentage": 67.98, "elapsed_time": "4:52:29", "remaining_time": "2:17:45", "throughput": 1486.21, "total_tokens": 26081920} {"current_steps": 123595, "total_steps": 181800, "loss": 0.0713, "lr": 1.4053666147181987e-05, "epoch": 13.596809680968097, "percentage": 67.98, "elapsed_time": "4:52:29", "remaining_time": "2:17:44", "throughput": 1486.21, "total_tokens": 26082944} {"current_steps": 123600, "total_steps": 181800, "loss": 0.0462, "lr": 1.4051508425363396e-05, "epoch": 13.597359735973598, "percentage": 67.99, "elapsed_time": "4:52:30", "remaining_time": "2:17:44", "throughput": 1486.21, "total_tokens": 26083936} {"current_steps": 123605, "total_steps": 181800, "loss": 0.0198, "lr": 1.4049350804451811e-05, "epoch": 13.597909790979099, "percentage": 67.99, "elapsed_time": "4:52:31", "remaining_time": "2:17:43", "throughput": 1486.21, "total_tokens": 26084960} {"current_steps": 123610, "total_steps": 181800, "loss": 0.0075, "lr": 1.4047193284467092e-05, "epoch": 13.598459845984598, "percentage": 67.99, "elapsed_time": "4:52:31", "remaining_time": "2:17:42", "throughput": 1486.22, "total_tokens": 26086048} {"current_steps": 123615, "total_steps": 181800, "loss": 0.0017, "lr": 1.4045035865429135e-05, "epoch": 13.599009900990099, "percentage": 68.0, "elapsed_time": "4:52:32", "remaining_time": "2:17:41", "throughput": 1486.21, "total_tokens": 26087040} {"current_steps": 123620, "total_steps": 181800, "loss": 0.0336, "lr": 1.4042878547357841e-05, "epoch": 13.5995599559956, "percentage": 68.0, "elapsed_time": "4:52:33", "remaining_time": "2:17:41", "throughput": 1486.22, "total_tokens": 26088128} {"current_steps": 123625, "total_steps": 181800, "loss": 0.113, "lr": 1.4040721330273062e-05, "epoch": 13.6001100110011, "percentage": 68.0, "elapsed_time": "4:52:34", "remaining_time": "2:17:40", "throughput": 1486.22, "total_tokens": 26089152} {"current_steps": 123630, "total_steps": 181800, "loss": 0.0366, "lr": 1.403856421419471e-05, "epoch": 13.6006600660066, "percentage": 68.0, "elapsed_time": "4:52:34", "remaining_time": "2:17:39", "throughput": 1486.22, "total_tokens": 26090208} {"current_steps": 123635, "total_steps": 181800, "loss": 0.0075, "lr": 1.4036407199142647e-05, "epoch": 13.601210121012102, "percentage": 68.01, "elapsed_time": "4:52:35", "remaining_time": "2:17:39", "throughput": 1486.22, "total_tokens": 26091232} {"current_steps": 123640, "total_steps": 181800, "loss": 0.0834, "lr": 1.4034250285136752e-05, "epoch": 13.601760176017601, "percentage": 68.01, "elapsed_time": "4:52:36", "remaining_time": "2:17:38", "throughput": 1486.22, "total_tokens": 26092320} {"current_steps": 123645, "total_steps": 181800, "loss": 0.0075, "lr": 1.403209347219691e-05, "epoch": 13.602310231023102, "percentage": 68.01, "elapsed_time": "4:52:36", "remaining_time": "2:17:37", "throughput": 1486.23, "total_tokens": 26093440} {"current_steps": 123650, "total_steps": 181800, "loss": 0.0808, "lr": 1.4029936760342999e-05, "epoch": 13.602860286028603, "percentage": 68.01, "elapsed_time": "4:52:37", "remaining_time": "2:17:36", "throughput": 1486.23, "total_tokens": 26094528} {"current_steps": 123655, "total_steps": 181800, "loss": 0.0025, "lr": 1.4027780149594907e-05, "epoch": 13.603410341034103, "percentage": 68.02, "elapsed_time": "4:52:38", "remaining_time": "2:17:36", "throughput": 1486.23, "total_tokens": 26095552} {"current_steps": 123660, "total_steps": 181800, "loss": 0.0412, "lr": 1.4025623639972502e-05, "epoch": 13.603960396039604, "percentage": 68.02, "elapsed_time": "4:52:38", "remaining_time": "2:17:35", "throughput": 1486.23, "total_tokens": 26096544} {"current_steps": 123665, "total_steps": 181800, "loss": 0.0132, "lr": 1.4023467231495646e-05, "epoch": 13.604510451045105, "percentage": 68.02, "elapsed_time": "4:52:39", "remaining_time": "2:17:34", "throughput": 1486.23, "total_tokens": 26097632} {"current_steps": 123670, "total_steps": 181800, "loss": 0.0613, "lr": 1.4021310924184223e-05, "epoch": 13.605060506050606, "percentage": 68.03, "elapsed_time": "4:52:40", "remaining_time": "2:17:34", "throughput": 1486.23, "total_tokens": 26098656} {"current_steps": 123675, "total_steps": 181800, "loss": 0.0031, "lr": 1.4019154718058114e-05, "epoch": 13.605610561056105, "percentage": 68.03, "elapsed_time": "4:52:40", "remaining_time": "2:17:33", "throughput": 1486.24, "total_tokens": 26099776} {"current_steps": 123680, "total_steps": 181800, "loss": 0.0027, "lr": 1.4016998613137194e-05, "epoch": 13.606160616061606, "percentage": 68.03, "elapsed_time": "4:52:41", "remaining_time": "2:17:32", "throughput": 1486.24, "total_tokens": 26100864} {"current_steps": 123685, "total_steps": 181800, "loss": 0.0766, "lr": 1.4014842609441325e-05, "epoch": 13.606710671067107, "percentage": 68.03, "elapsed_time": "4:52:42", "remaining_time": "2:17:31", "throughput": 1486.24, "total_tokens": 26101888} {"current_steps": 123690, "total_steps": 181800, "loss": 0.0244, "lr": 1.4012686706990375e-05, "epoch": 13.607260726072607, "percentage": 68.04, "elapsed_time": "4:52:43", "remaining_time": "2:17:31", "throughput": 1486.24, "total_tokens": 26102944} {"current_steps": 123695, "total_steps": 181800, "loss": 0.0152, "lr": 1.4010530905804228e-05, "epoch": 13.607810781078108, "percentage": 68.04, "elapsed_time": "4:52:43", "remaining_time": "2:17:30", "throughput": 1486.25, "total_tokens": 26104000} {"current_steps": 123700, "total_steps": 181800, "loss": 0.1451, "lr": 1.4008375205902735e-05, "epoch": 13.608360836083609, "percentage": 68.04, "elapsed_time": "4:52:44", "remaining_time": "2:17:29", "throughput": 1486.25, "total_tokens": 26105056} {"current_steps": 123705, "total_steps": 181800, "loss": 0.017, "lr": 1.4006219607305774e-05, "epoch": 13.608910891089108, "percentage": 68.04, "elapsed_time": "4:52:45", "remaining_time": "2:17:29", "throughput": 1486.25, "total_tokens": 26106176} {"current_steps": 123710, "total_steps": 181800, "loss": 0.002, "lr": 1.4004064110033222e-05, "epoch": 13.60946094609461, "percentage": 68.05, "elapsed_time": "4:52:45", "remaining_time": "2:17:28", "throughput": 1486.25, "total_tokens": 26107200} {"current_steps": 123715, "total_steps": 181800, "loss": 0.0053, "lr": 1.4001908714104922e-05, "epoch": 13.61001100110011, "percentage": 68.05, "elapsed_time": "4:52:46", "remaining_time": "2:17:27", "throughput": 1486.25, "total_tokens": 26108224} {"current_steps": 123720, "total_steps": 181800, "loss": 0.0028, "lr": 1.3999753419540763e-05, "epoch": 13.61056105610561, "percentage": 68.05, "elapsed_time": "4:52:47", "remaining_time": "2:17:26", "throughput": 1486.25, "total_tokens": 26109280} {"current_steps": 123725, "total_steps": 181800, "loss": 0.0055, "lr": 1.3997598226360586e-05, "epoch": 13.61111111111111, "percentage": 68.06, "elapsed_time": "4:52:47", "remaining_time": "2:17:26", "throughput": 1486.25, "total_tokens": 26110240} {"current_steps": 123730, "total_steps": 181800, "loss": 0.1379, "lr": 1.3995443134584268e-05, "epoch": 13.611661166116612, "percentage": 68.06, "elapsed_time": "4:52:48", "remaining_time": "2:17:25", "throughput": 1486.25, "total_tokens": 26111296} {"current_steps": 123735, "total_steps": 181800, "loss": 0.044, "lr": 1.3993288144231684e-05, "epoch": 13.612211221122113, "percentage": 68.06, "elapsed_time": "4:52:49", "remaining_time": "2:17:24", "throughput": 1486.26, "total_tokens": 26112448} {"current_steps": 123740, "total_steps": 181800, "loss": 0.0017, "lr": 1.3991133255322669e-05, "epoch": 13.612761276127612, "percentage": 68.06, "elapsed_time": "4:52:49", "remaining_time": "2:17:23", "throughput": 1486.26, "total_tokens": 26113472} {"current_steps": 123745, "total_steps": 181800, "loss": 0.0074, "lr": 1.3988978467877106e-05, "epoch": 13.613311331133113, "percentage": 68.07, "elapsed_time": "4:52:50", "remaining_time": "2:17:23", "throughput": 1486.27, "total_tokens": 26114592} {"current_steps": 123750, "total_steps": 181800, "loss": 0.0048, "lr": 1.3986823781914842e-05, "epoch": 13.613861386138614, "percentage": 68.07, "elapsed_time": "4:52:51", "remaining_time": "2:17:22", "throughput": 1486.26, "total_tokens": 26115584} {"current_steps": 123755, "total_steps": 181800, "loss": 0.0033, "lr": 1.3984669197455735e-05, "epoch": 13.614411441144114, "percentage": 68.07, "elapsed_time": "4:52:51", "remaining_time": "2:17:21", "throughput": 1486.26, "total_tokens": 26116608} {"current_steps": 123760, "total_steps": 181800, "loss": 0.0093, "lr": 1.398251471451964e-05, "epoch": 13.614961496149615, "percentage": 68.07, "elapsed_time": "4:52:52", "remaining_time": "2:17:21", "throughput": 1486.27, "total_tokens": 26117760} {"current_steps": 123765, "total_steps": 181800, "loss": 0.0156, "lr": 1.3980360333126425e-05, "epoch": 13.615511551155116, "percentage": 68.08, "elapsed_time": "4:52:53", "remaining_time": "2:17:20", "throughput": 1486.27, "total_tokens": 26118784} {"current_steps": 123770, "total_steps": 181800, "loss": 0.0467, "lr": 1.3978206053295951e-05, "epoch": 13.616061606160617, "percentage": 68.08, "elapsed_time": "4:52:54", "remaining_time": "2:17:19", "throughput": 1486.27, "total_tokens": 26119840} {"current_steps": 123775, "total_steps": 181800, "loss": 0.0032, "lr": 1.3976051875048058e-05, "epoch": 13.616611661166116, "percentage": 68.08, "elapsed_time": "4:52:54", "remaining_time": "2:17:18", "throughput": 1486.27, "total_tokens": 26120864} {"current_steps": 123780, "total_steps": 181800, "loss": 0.0359, "lr": 1.3973897798402599e-05, "epoch": 13.617161716171617, "percentage": 68.09, "elapsed_time": "4:52:55", "remaining_time": "2:17:18", "throughput": 1486.28, "total_tokens": 26121952} {"current_steps": 123785, "total_steps": 181800, "loss": 0.0042, "lr": 1.397174382337944e-05, "epoch": 13.617711771177119, "percentage": 68.09, "elapsed_time": "4:52:56", "remaining_time": "2:17:17", "throughput": 1486.28, "total_tokens": 26123040} {"current_steps": 123790, "total_steps": 181800, "loss": 0.0009, "lr": 1.3969589949998412e-05, "epoch": 13.618261826182618, "percentage": 68.09, "elapsed_time": "4:52:56", "remaining_time": "2:17:16", "throughput": 1486.28, "total_tokens": 26124096} {"current_steps": 123795, "total_steps": 181800, "loss": 0.0035, "lr": 1.3967436178279396e-05, "epoch": 13.618811881188119, "percentage": 68.09, "elapsed_time": "4:52:57", "remaining_time": "2:17:16", "throughput": 1486.28, "total_tokens": 26125152} {"current_steps": 123800, "total_steps": 181800, "loss": 0.0014, "lr": 1.3965282508242227e-05, "epoch": 13.61936193619362, "percentage": 68.1, "elapsed_time": "4:52:58", "remaining_time": "2:17:15", "throughput": 1486.29, "total_tokens": 26126208} {"current_steps": 123805, "total_steps": 181800, "loss": 0.1463, "lr": 1.3963128939906744e-05, "epoch": 13.61991199119912, "percentage": 68.1, "elapsed_time": "4:52:58", "remaining_time": "2:17:14", "throughput": 1486.29, "total_tokens": 26127232} {"current_steps": 123810, "total_steps": 181800, "loss": 0.0625, "lr": 1.396097547329282e-05, "epoch": 13.62046204620462, "percentage": 68.1, "elapsed_time": "4:52:59", "remaining_time": "2:17:13", "throughput": 1486.29, "total_tokens": 26128320} {"current_steps": 123815, "total_steps": 181800, "loss": 0.0585, "lr": 1.3958822108420273e-05, "epoch": 13.621012101210122, "percentage": 68.11, "elapsed_time": "4:53:00", "remaining_time": "2:17:13", "throughput": 1486.29, "total_tokens": 26129408} {"current_steps": 123820, "total_steps": 181800, "loss": 0.0094, "lr": 1.3956668845308968e-05, "epoch": 13.62156215621562, "percentage": 68.11, "elapsed_time": "4:53:00", "remaining_time": "2:17:12", "throughput": 1486.3, "total_tokens": 26130496} {"current_steps": 123825, "total_steps": 181800, "loss": 0.0157, "lr": 1.3954515683978754e-05, "epoch": 13.622112211221122, "percentage": 68.11, "elapsed_time": "4:53:01", "remaining_time": "2:17:11", "throughput": 1486.3, "total_tokens": 26131552} {"current_steps": 123830, "total_steps": 181800, "loss": 0.0024, "lr": 1.3952362624449461e-05, "epoch": 13.622662266226623, "percentage": 68.11, "elapsed_time": "4:53:02", "remaining_time": "2:17:11", "throughput": 1486.3, "total_tokens": 26132576} {"current_steps": 123835, "total_steps": 181800, "loss": 0.0045, "lr": 1.3950209666740948e-05, "epoch": 13.623212321232124, "percentage": 68.12, "elapsed_time": "4:53:03", "remaining_time": "2:17:10", "throughput": 1486.3, "total_tokens": 26133632} {"current_steps": 123840, "total_steps": 181800, "loss": 0.0273, "lr": 1.3948056810873045e-05, "epoch": 13.623762376237623, "percentage": 68.12, "elapsed_time": "4:53:03", "remaining_time": "2:17:09", "throughput": 1486.3, "total_tokens": 26134688} {"current_steps": 123845, "total_steps": 181800, "loss": 0.0166, "lr": 1.3945904056865605e-05, "epoch": 13.624312431243125, "percentage": 68.12, "elapsed_time": "4:53:04", "remaining_time": "2:17:08", "throughput": 1486.31, "total_tokens": 26135776} {"current_steps": 123850, "total_steps": 181800, "loss": 0.0134, "lr": 1.3943751404738454e-05, "epoch": 13.624862486248626, "percentage": 68.12, "elapsed_time": "4:53:05", "remaining_time": "2:17:08", "throughput": 1486.31, "total_tokens": 26136864} {"current_steps": 123855, "total_steps": 181800, "loss": 0.0056, "lr": 1.394159885451144e-05, "epoch": 13.625412541254125, "percentage": 68.13, "elapsed_time": "4:53:05", "remaining_time": "2:17:07", "throughput": 1486.31, "total_tokens": 26137888} {"current_steps": 123860, "total_steps": 181800, "loss": 0.0026, "lr": 1.3939446406204414e-05, "epoch": 13.625962596259626, "percentage": 68.13, "elapsed_time": "4:53:06", "remaining_time": "2:17:06", "throughput": 1486.31, "total_tokens": 26138944} {"current_steps": 123865, "total_steps": 181800, "loss": 0.045, "lr": 1.3937294059837194e-05, "epoch": 13.626512651265127, "percentage": 68.13, "elapsed_time": "4:53:07", "remaining_time": "2:17:05", "throughput": 1486.31, "total_tokens": 26139968} {"current_steps": 123870, "total_steps": 181800, "loss": 0.0424, "lr": 1.3935141815429637e-05, "epoch": 13.627062706270626, "percentage": 68.14, "elapsed_time": "4:53:07", "remaining_time": "2:17:05", "throughput": 1486.31, "total_tokens": 26141024} {"current_steps": 123875, "total_steps": 181800, "loss": 0.0471, "lr": 1.3932989673001556e-05, "epoch": 13.627612761276128, "percentage": 68.14, "elapsed_time": "4:53:08", "remaining_time": "2:17:04", "throughput": 1486.31, "total_tokens": 26142016} {"current_steps": 123880, "total_steps": 181800, "loss": 0.0081, "lr": 1.3930837632572799e-05, "epoch": 13.628162816281629, "percentage": 68.14, "elapsed_time": "4:53:09", "remaining_time": "2:17:03", "throughput": 1486.31, "total_tokens": 26142976} {"current_steps": 123885, "total_steps": 181800, "loss": 0.0027, "lr": 1.3928685694163212e-05, "epoch": 13.628712871287128, "percentage": 68.14, "elapsed_time": "4:53:09", "remaining_time": "2:17:03", "throughput": 1486.31, "total_tokens": 26144064} {"current_steps": 123890, "total_steps": 181800, "loss": 0.0895, "lr": 1.3926533857792607e-05, "epoch": 13.629262926292629, "percentage": 68.15, "elapsed_time": "4:53:10", "remaining_time": "2:17:02", "throughput": 1486.31, "total_tokens": 26145120} {"current_steps": 123895, "total_steps": 181800, "loss": 0.0018, "lr": 1.3924382123480833e-05, "epoch": 13.62981298129813, "percentage": 68.15, "elapsed_time": "4:53:11", "remaining_time": "2:17:01", "throughput": 1486.32, "total_tokens": 26146208} {"current_steps": 123900, "total_steps": 181800, "loss": 0.1096, "lr": 1.3922230491247712e-05, "epoch": 13.630363036303631, "percentage": 68.15, "elapsed_time": "4:53:11", "remaining_time": "2:17:00", "throughput": 1486.32, "total_tokens": 26147264} {"current_steps": 123905, "total_steps": 181800, "loss": 0.0019, "lr": 1.3920078961113065e-05, "epoch": 13.63091309130913, "percentage": 68.15, "elapsed_time": "4:53:12", "remaining_time": "2:17:00", "throughput": 1486.32, "total_tokens": 26148320} {"current_steps": 123910, "total_steps": 181800, "loss": 0.1587, "lr": 1.3917927533096748e-05, "epoch": 13.631463146314632, "percentage": 68.16, "elapsed_time": "4:53:13", "remaining_time": "2:16:59", "throughput": 1486.32, "total_tokens": 26149376} {"current_steps": 123915, "total_steps": 181800, "loss": 0.0435, "lr": 1.3915776207218565e-05, "epoch": 13.632013201320133, "percentage": 68.16, "elapsed_time": "4:53:14", "remaining_time": "2:16:58", "throughput": 1486.33, "total_tokens": 26150432} {"current_steps": 123920, "total_steps": 181800, "loss": 0.0884, "lr": 1.3913624983498363e-05, "epoch": 13.632563256325632, "percentage": 68.16, "elapsed_time": "4:53:14", "remaining_time": "2:16:58", "throughput": 1486.33, "total_tokens": 26151520} {"current_steps": 123925, "total_steps": 181800, "loss": 0.0073, "lr": 1.3911473861955965e-05, "epoch": 13.633113311331133, "percentage": 68.17, "elapsed_time": "4:53:15", "remaining_time": "2:16:57", "throughput": 1486.33, "total_tokens": 26152544} {"current_steps": 123930, "total_steps": 181800, "loss": 0.0173, "lr": 1.3909322842611177e-05, "epoch": 13.633663366336634, "percentage": 68.17, "elapsed_time": "4:53:16", "remaining_time": "2:16:56", "throughput": 1486.33, "total_tokens": 26153536} {"current_steps": 123935, "total_steps": 181800, "loss": 0.0061, "lr": 1.3907171925483841e-05, "epoch": 13.634213421342134, "percentage": 68.17, "elapsed_time": "4:53:16", "remaining_time": "2:16:55", "throughput": 1486.33, "total_tokens": 26154592} {"current_steps": 123940, "total_steps": 181800, "loss": 0.0059, "lr": 1.3905021110593786e-05, "epoch": 13.634763476347635, "percentage": 68.17, "elapsed_time": "4:53:17", "remaining_time": "2:16:55", "throughput": 1486.33, "total_tokens": 26155616} {"current_steps": 123945, "total_steps": 181800, "loss": 0.0045, "lr": 1.390287039796082e-05, "epoch": 13.635313531353136, "percentage": 68.18, "elapsed_time": "4:53:18", "remaining_time": "2:16:54", "throughput": 1486.33, "total_tokens": 26156672} {"current_steps": 123950, "total_steps": 181800, "loss": 0.0019, "lr": 1.3900719787604783e-05, "epoch": 13.635863586358635, "percentage": 68.18, "elapsed_time": "4:53:18", "remaining_time": "2:16:53", "throughput": 1486.34, "total_tokens": 26157792} {"current_steps": 123955, "total_steps": 181800, "loss": 0.0692, "lr": 1.3898569279545473e-05, "epoch": 13.636413641364136, "percentage": 68.18, "elapsed_time": "4:53:19", "remaining_time": "2:16:53", "throughput": 1486.34, "total_tokens": 26158848} {"current_steps": 123960, "total_steps": 181800, "loss": 0.0016, "lr": 1.3896418873802736e-05, "epoch": 13.636963696369637, "percentage": 68.18, "elapsed_time": "4:53:20", "remaining_time": "2:16:52", "throughput": 1486.34, "total_tokens": 26159840} {"current_steps": 123965, "total_steps": 181800, "loss": 0.0127, "lr": 1.3894268570396365e-05, "epoch": 13.637513751375138, "percentage": 68.19, "elapsed_time": "4:53:20", "remaining_time": "2:16:51", "throughput": 1486.34, "total_tokens": 26160864} {"current_steps": 123970, "total_steps": 181800, "loss": 0.0168, "lr": 1.3892118369346194e-05, "epoch": 13.638063806380638, "percentage": 68.19, "elapsed_time": "4:53:21", "remaining_time": "2:16:50", "throughput": 1486.34, "total_tokens": 26161952} {"current_steps": 123975, "total_steps": 181800, "loss": 0.0014, "lr": 1.3889968270672046e-05, "epoch": 13.638613861386139, "percentage": 68.19, "elapsed_time": "4:53:22", "remaining_time": "2:16:50", "throughput": 1486.34, "total_tokens": 26163040} {"current_steps": 123980, "total_steps": 181800, "loss": 0.078, "lr": 1.3887818274393722e-05, "epoch": 13.63916391639164, "percentage": 68.2, "elapsed_time": "4:53:22", "remaining_time": "2:16:49", "throughput": 1486.34, "total_tokens": 26164096} {"current_steps": 123985, "total_steps": 181800, "loss": 0.017, "lr": 1.3885668380531053e-05, "epoch": 13.63971397139714, "percentage": 68.2, "elapsed_time": "4:53:23", "remaining_time": "2:16:48", "throughput": 1486.35, "total_tokens": 26165152} {"current_steps": 123990, "total_steps": 181800, "loss": 0.0193, "lr": 1.3883518589103833e-05, "epoch": 13.64026402640264, "percentage": 68.2, "elapsed_time": "4:53:24", "remaining_time": "2:16:47", "throughput": 1486.35, "total_tokens": 26166176} {"current_steps": 123995, "total_steps": 181800, "loss": 0.0872, "lr": 1.388136890013189e-05, "epoch": 13.640814081408141, "percentage": 68.2, "elapsed_time": "4:53:25", "remaining_time": "2:16:47", "throughput": 1486.35, "total_tokens": 26167328} {"current_steps": 124000, "total_steps": 181800, "loss": 0.0009, "lr": 1.3879219313635048e-05, "epoch": 13.64136413641364, "percentage": 68.21, "elapsed_time": "4:53:25", "remaining_time": "2:16:46", "throughput": 1486.35, "total_tokens": 26168352} {"current_steps": 124005, "total_steps": 181800, "loss": 0.0944, "lr": 1.3877069829633093e-05, "epoch": 13.641914191419142, "percentage": 68.21, "elapsed_time": "4:53:26", "remaining_time": "2:16:45", "throughput": 1486.35, "total_tokens": 26169408} {"current_steps": 124010, "total_steps": 181800, "loss": 0.0124, "lr": 1.3874920448145857e-05, "epoch": 13.642464246424643, "percentage": 68.21, "elapsed_time": "4:53:27", "remaining_time": "2:16:45", "throughput": 1486.35, "total_tokens": 26170432} {"current_steps": 124015, "total_steps": 181800, "loss": 0.0852, "lr": 1.3872771169193142e-05, "epoch": 13.643014301430142, "percentage": 68.22, "elapsed_time": "4:53:27", "remaining_time": "2:16:44", "throughput": 1486.36, "total_tokens": 26171520} {"current_steps": 124020, "total_steps": 181800, "loss": 0.0045, "lr": 1.3870621992794744e-05, "epoch": 13.643564356435643, "percentage": 68.22, "elapsed_time": "4:53:28", "remaining_time": "2:16:43", "throughput": 1486.36, "total_tokens": 26172640} {"current_steps": 124025, "total_steps": 181800, "loss": 0.0793, "lr": 1.3868472918970484e-05, "epoch": 13.644114411441144, "percentage": 68.22, "elapsed_time": "4:53:29", "remaining_time": "2:16:42", "throughput": 1486.37, "total_tokens": 26173696} {"current_steps": 124030, "total_steps": 181800, "loss": 0.0364, "lr": 1.3866323947740168e-05, "epoch": 13.644664466446645, "percentage": 68.22, "elapsed_time": "4:53:29", "remaining_time": "2:16:42", "throughput": 1486.37, "total_tokens": 26174752} {"current_steps": 124035, "total_steps": 181800, "loss": 0.0499, "lr": 1.386417507912361e-05, "epoch": 13.645214521452145, "percentage": 68.23, "elapsed_time": "4:53:30", "remaining_time": "2:16:41", "throughput": 1486.37, "total_tokens": 26175744} {"current_steps": 124040, "total_steps": 181800, "loss": 0.0061, "lr": 1.3862026313140608e-05, "epoch": 13.645764576457646, "percentage": 68.23, "elapsed_time": "4:53:31", "remaining_time": "2:16:40", "throughput": 1486.37, "total_tokens": 26176864} {"current_steps": 124045, "total_steps": 181800, "loss": 0.1234, "lr": 1.3859877649810956e-05, "epoch": 13.646314631463147, "percentage": 68.23, "elapsed_time": "4:53:31", "remaining_time": "2:16:40", "throughput": 1486.38, "total_tokens": 26178016} {"current_steps": 124050, "total_steps": 181800, "loss": 0.0013, "lr": 1.3857729089154464e-05, "epoch": 13.646864686468646, "percentage": 68.23, "elapsed_time": "4:53:32", "remaining_time": "2:16:39", "throughput": 1486.38, "total_tokens": 26179072} {"current_steps": 124055, "total_steps": 181800, "loss": 0.0042, "lr": 1.385558063119094e-05, "epoch": 13.647414741474147, "percentage": 68.24, "elapsed_time": "4:53:33", "remaining_time": "2:16:38", "throughput": 1486.38, "total_tokens": 26180128} {"current_steps": 124060, "total_steps": 181800, "loss": 0.0075, "lr": 1.3853432275940188e-05, "epoch": 13.647964796479648, "percentage": 68.24, "elapsed_time": "4:53:34", "remaining_time": "2:16:37", "throughput": 1486.38, "total_tokens": 26181184} {"current_steps": 124065, "total_steps": 181800, "loss": 0.0326, "lr": 1.3851284023422005e-05, "epoch": 13.648514851485148, "percentage": 68.24, "elapsed_time": "4:53:34", "remaining_time": "2:16:37", "throughput": 1486.38, "total_tokens": 26182176} {"current_steps": 124070, "total_steps": 181800, "loss": 0.0102, "lr": 1.3849135873656177e-05, "epoch": 13.649064906490649, "percentage": 68.25, "elapsed_time": "4:53:35", "remaining_time": "2:16:36", "throughput": 1486.38, "total_tokens": 26183264} {"current_steps": 124075, "total_steps": 181800, "loss": 0.0586, "lr": 1.3846987826662522e-05, "epoch": 13.64961496149615, "percentage": 68.25, "elapsed_time": "4:53:36", "remaining_time": "2:16:35", "throughput": 1486.38, "total_tokens": 26184320} {"current_steps": 124080, "total_steps": 181800, "loss": 0.0082, "lr": 1.3844839882460817e-05, "epoch": 13.65016501650165, "percentage": 68.25, "elapsed_time": "4:53:36", "remaining_time": "2:16:35", "throughput": 1486.39, "total_tokens": 26185376} {"current_steps": 124085, "total_steps": 181800, "loss": 0.0047, "lr": 1.3842692041070871e-05, "epoch": 13.65071507150715, "percentage": 68.25, "elapsed_time": "4:53:37", "remaining_time": "2:16:34", "throughput": 1486.38, "total_tokens": 26186368} {"current_steps": 124090, "total_steps": 181800, "loss": 0.0087, "lr": 1.3840544302512487e-05, "epoch": 13.651265126512651, "percentage": 68.26, "elapsed_time": "4:53:38", "remaining_time": "2:16:33", "throughput": 1486.39, "total_tokens": 26187456} {"current_steps": 124095, "total_steps": 181800, "loss": 0.01, "lr": 1.3838396666805444e-05, "epoch": 13.651815181518153, "percentage": 68.26, "elapsed_time": "4:53:38", "remaining_time": "2:16:32", "throughput": 1486.39, "total_tokens": 26188448} {"current_steps": 124100, "total_steps": 181800, "loss": 0.0478, "lr": 1.3836249133969554e-05, "epoch": 13.652365236523652, "percentage": 68.26, "elapsed_time": "4:53:39", "remaining_time": "2:16:32", "throughput": 1486.39, "total_tokens": 26189536} {"current_steps": 124105, "total_steps": 181800, "loss": 0.0594, "lr": 1.3834101704024588e-05, "epoch": 13.652915291529153, "percentage": 68.26, "elapsed_time": "4:53:40", "remaining_time": "2:16:31", "throughput": 1486.4, "total_tokens": 26190656} {"current_steps": 124110, "total_steps": 181800, "loss": 0.086, "lr": 1.3831954376990346e-05, "epoch": 13.653465346534654, "percentage": 68.27, "elapsed_time": "4:53:40", "remaining_time": "2:16:30", "throughput": 1486.4, "total_tokens": 26191776} {"current_steps": 124115, "total_steps": 181800, "loss": 0.08, "lr": 1.3829807152886633e-05, "epoch": 13.654015401540153, "percentage": 68.27, "elapsed_time": "4:53:41", "remaining_time": "2:16:30", "throughput": 1486.4, "total_tokens": 26192832} {"current_steps": 124120, "total_steps": 181800, "loss": 0.0734, "lr": 1.3827660031733219e-05, "epoch": 13.654565456545654, "percentage": 68.27, "elapsed_time": "4:53:42", "remaining_time": "2:16:29", "throughput": 1486.4, "total_tokens": 26193856} {"current_steps": 124125, "total_steps": 181800, "loss": 0.0251, "lr": 1.3825513013549912e-05, "epoch": 13.655115511551156, "percentage": 68.28, "elapsed_time": "4:53:43", "remaining_time": "2:16:28", "throughput": 1486.4, "total_tokens": 26194912} {"current_steps": 124130, "total_steps": 181800, "loss": 0.0997, "lr": 1.3823366098356487e-05, "epoch": 13.655665566556655, "percentage": 68.28, "elapsed_time": "4:53:43", "remaining_time": "2:16:27", "throughput": 1486.41, "total_tokens": 26195968} {"current_steps": 124135, "total_steps": 181800, "loss": 0.0078, "lr": 1.3821219286172727e-05, "epoch": 13.656215621562156, "percentage": 68.28, "elapsed_time": "4:53:44", "remaining_time": "2:16:27", "throughput": 1486.4, "total_tokens": 26196960} {"current_steps": 124140, "total_steps": 181800, "loss": 0.0081, "lr": 1.3819072577018422e-05, "epoch": 13.656765676567657, "percentage": 68.28, "elapsed_time": "4:53:45", "remaining_time": "2:16:26", "throughput": 1486.41, "total_tokens": 26198048} {"current_steps": 124145, "total_steps": 181800, "loss": 0.0012, "lr": 1.3816925970913359e-05, "epoch": 13.657315731573158, "percentage": 68.29, "elapsed_time": "4:53:45", "remaining_time": "2:16:25", "throughput": 1486.41, "total_tokens": 26199072} {"current_steps": 124150, "total_steps": 181800, "loss": 0.0791, "lr": 1.3814779467877333e-05, "epoch": 13.657865786578657, "percentage": 68.29, "elapsed_time": "4:53:46", "remaining_time": "2:16:24", "throughput": 1486.41, "total_tokens": 26200192} {"current_steps": 124155, "total_steps": 181800, "loss": 0.0637, "lr": 1.381263306793012e-05, "epoch": 13.658415841584159, "percentage": 68.29, "elapsed_time": "4:53:47", "remaining_time": "2:16:24", "throughput": 1486.42, "total_tokens": 26201248} {"current_steps": 124160, "total_steps": 181800, "loss": 0.01, "lr": 1.3810486771091488e-05, "epoch": 13.65896589658966, "percentage": 68.29, "elapsed_time": "4:53:47", "remaining_time": "2:16:23", "throughput": 1486.42, "total_tokens": 26202368} {"current_steps": 124165, "total_steps": 181800, "loss": 0.0125, "lr": 1.3808340577381229e-05, "epoch": 13.659515951595159, "percentage": 68.3, "elapsed_time": "4:53:48", "remaining_time": "2:16:22", "throughput": 1486.42, "total_tokens": 26203424} {"current_steps": 124170, "total_steps": 181800, "loss": 0.006, "lr": 1.3806194486819129e-05, "epoch": 13.66006600660066, "percentage": 68.3, "elapsed_time": "4:53:49", "remaining_time": "2:16:22", "throughput": 1486.43, "total_tokens": 26204512} {"current_steps": 124175, "total_steps": 181800, "loss": 0.0531, "lr": 1.3804048499424971e-05, "epoch": 13.660616061606161, "percentage": 68.3, "elapsed_time": "4:53:49", "remaining_time": "2:16:21", "throughput": 1486.43, "total_tokens": 26205600} {"current_steps": 124180, "total_steps": 181800, "loss": 0.1134, "lr": 1.3801902615218527e-05, "epoch": 13.66116611661166, "percentage": 68.31, "elapsed_time": "4:53:50", "remaining_time": "2:16:20", "throughput": 1486.43, "total_tokens": 26206560} {"current_steps": 124185, "total_steps": 181800, "loss": 0.0097, "lr": 1.3799756834219557e-05, "epoch": 13.661716171617162, "percentage": 68.31, "elapsed_time": "4:53:51", "remaining_time": "2:16:19", "throughput": 1486.43, "total_tokens": 26207616} {"current_steps": 124190, "total_steps": 181800, "loss": 0.0379, "lr": 1.3797611156447871e-05, "epoch": 13.662266226622663, "percentage": 68.31, "elapsed_time": "4:53:51", "remaining_time": "2:16:19", "throughput": 1486.43, "total_tokens": 26208736} {"current_steps": 124195, "total_steps": 181800, "loss": 0.0044, "lr": 1.3795465581923215e-05, "epoch": 13.662816281628164, "percentage": 68.31, "elapsed_time": "4:53:52", "remaining_time": "2:16:18", "throughput": 1486.43, "total_tokens": 26209728} {"current_steps": 124200, "total_steps": 181800, "loss": 0.0057, "lr": 1.3793320110665375e-05, "epoch": 13.663366336633663, "percentage": 68.32, "elapsed_time": "4:53:53", "remaining_time": "2:16:17", "throughput": 1486.44, "total_tokens": 26210848} {"current_steps": 124205, "total_steps": 181800, "loss": 0.1078, "lr": 1.3791174742694134e-05, "epoch": 13.663916391639164, "percentage": 68.32, "elapsed_time": "4:53:54", "remaining_time": "2:16:17", "throughput": 1486.44, "total_tokens": 26211872} {"current_steps": 124210, "total_steps": 181800, "loss": 0.1036, "lr": 1.3789029478029253e-05, "epoch": 13.664466446644665, "percentage": 68.32, "elapsed_time": "4:53:54", "remaining_time": "2:16:16", "throughput": 1486.44, "total_tokens": 26212928} {"current_steps": 124215, "total_steps": 181800, "loss": 0.0029, "lr": 1.3786884316690516e-05, "epoch": 13.665016501650165, "percentage": 68.33, "elapsed_time": "4:53:55", "remaining_time": "2:16:15", "throughput": 1486.44, "total_tokens": 26213920} {"current_steps": 124220, "total_steps": 181800, "loss": 0.0061, "lr": 1.3784739258697674e-05, "epoch": 13.665566556655666, "percentage": 68.33, "elapsed_time": "4:53:56", "remaining_time": "2:16:14", "throughput": 1486.44, "total_tokens": 26214912} {"current_steps": 124225, "total_steps": 181800, "loss": 0.0036, "lr": 1.378259430407051e-05, "epoch": 13.666116611661167, "percentage": 68.33, "elapsed_time": "4:53:56", "remaining_time": "2:16:14", "throughput": 1486.44, "total_tokens": 26215968} {"current_steps": 124230, "total_steps": 181800, "loss": 0.0034, "lr": 1.3780449452828798e-05, "epoch": 13.666666666666666, "percentage": 68.33, "elapsed_time": "4:53:57", "remaining_time": "2:16:13", "throughput": 1486.44, "total_tokens": 26216992} {"current_steps": 124235, "total_steps": 181800, "loss": 0.0235, "lr": 1.3778304704992296e-05, "epoch": 13.667216721672167, "percentage": 68.34, "elapsed_time": "4:53:58", "remaining_time": "2:16:12", "throughput": 1486.44, "total_tokens": 26218016} {"current_steps": 124240, "total_steps": 181800, "loss": 0.0185, "lr": 1.3776160060580778e-05, "epoch": 13.667766776677668, "percentage": 68.34, "elapsed_time": "4:53:58", "remaining_time": "2:16:12", "throughput": 1486.44, "total_tokens": 26219040} {"current_steps": 124245, "total_steps": 181800, "loss": 0.0489, "lr": 1.3774015519614003e-05, "epoch": 13.668316831683168, "percentage": 68.34, "elapsed_time": "4:53:59", "remaining_time": "2:16:11", "throughput": 1486.44, "total_tokens": 26220096} {"current_steps": 124250, "total_steps": 181800, "loss": 0.0969, "lr": 1.3771871082111748e-05, "epoch": 13.668866886688669, "percentage": 68.34, "elapsed_time": "4:54:00", "remaining_time": "2:16:10", "throughput": 1486.44, "total_tokens": 26221120} {"current_steps": 124255, "total_steps": 181800, "loss": 0.0863, "lr": 1.3769726748093759e-05, "epoch": 13.66941694169417, "percentage": 68.35, "elapsed_time": "4:54:00", "remaining_time": "2:16:09", "throughput": 1486.44, "total_tokens": 26222176} {"current_steps": 124260, "total_steps": 181800, "loss": 0.0541, "lr": 1.3767582517579809e-05, "epoch": 13.66996699669967, "percentage": 68.35, "elapsed_time": "4:54:01", "remaining_time": "2:16:09", "throughput": 1486.44, "total_tokens": 26223232} {"current_steps": 124265, "total_steps": 181800, "loss": 0.0497, "lr": 1.376543839058967e-05, "epoch": 13.67051705170517, "percentage": 68.35, "elapsed_time": "4:54:02", "remaining_time": "2:16:08", "throughput": 1486.44, "total_tokens": 26224256} {"current_steps": 124270, "total_steps": 181800, "loss": 0.1336, "lr": 1.3763294367143086e-05, "epoch": 13.671067106710671, "percentage": 68.36, "elapsed_time": "4:54:03", "remaining_time": "2:16:07", "throughput": 1486.44, "total_tokens": 26225344} {"current_steps": 124275, "total_steps": 181800, "loss": 0.0082, "lr": 1.3761150447259838e-05, "epoch": 13.671617161716172, "percentage": 68.36, "elapsed_time": "4:54:03", "remaining_time": "2:16:07", "throughput": 1486.45, "total_tokens": 26226432} {"current_steps": 124280, "total_steps": 181800, "loss": 0.0081, "lr": 1.3759006630959662e-05, "epoch": 13.672167216721672, "percentage": 68.36, "elapsed_time": "4:54:04", "remaining_time": "2:16:06", "throughput": 1486.45, "total_tokens": 26227456} {"current_steps": 124285, "total_steps": 181800, "loss": 0.0657, "lr": 1.3756862918262326e-05, "epoch": 13.672717271727173, "percentage": 68.36, "elapsed_time": "4:54:05", "remaining_time": "2:16:05", "throughput": 1486.45, "total_tokens": 26228480} {"current_steps": 124290, "total_steps": 181800, "loss": 0.0597, "lr": 1.3754719309187603e-05, "epoch": 13.673267326732674, "percentage": 68.37, "elapsed_time": "4:54:05", "remaining_time": "2:16:04", "throughput": 1486.45, "total_tokens": 26229504} {"current_steps": 124295, "total_steps": 181800, "loss": 0.0022, "lr": 1.3752575803755225e-05, "epoch": 13.673817381738173, "percentage": 68.37, "elapsed_time": "4:54:06", "remaining_time": "2:16:04", "throughput": 1486.45, "total_tokens": 26230592} {"current_steps": 124300, "total_steps": 181800, "loss": 0.0134, "lr": 1.3750432401984966e-05, "epoch": 13.674367436743674, "percentage": 68.37, "elapsed_time": "4:54:07", "remaining_time": "2:16:03", "throughput": 1486.46, "total_tokens": 26231744} {"current_steps": 124305, "total_steps": 181800, "loss": 0.0018, "lr": 1.3748289103896579e-05, "epoch": 13.674917491749175, "percentage": 68.37, "elapsed_time": "4:54:07", "remaining_time": "2:16:02", "throughput": 1486.46, "total_tokens": 26232768} {"current_steps": 124310, "total_steps": 181800, "loss": 0.0033, "lr": 1.3746145909509794e-05, "epoch": 13.675467546754675, "percentage": 68.38, "elapsed_time": "4:54:08", "remaining_time": "2:16:01", "throughput": 1486.46, "total_tokens": 26233760} {"current_steps": 124315, "total_steps": 181800, "loss": 0.1512, "lr": 1.3744002818844387e-05, "epoch": 13.676017601760176, "percentage": 68.38, "elapsed_time": "4:54:09", "remaining_time": "2:16:01", "throughput": 1486.46, "total_tokens": 26234880} {"current_steps": 124320, "total_steps": 181800, "loss": 0.0589, "lr": 1.3741859831920107e-05, "epoch": 13.676567656765677, "percentage": 68.38, "elapsed_time": "4:54:09", "remaining_time": "2:16:00", "throughput": 1486.47, "total_tokens": 26236000} {"current_steps": 124325, "total_steps": 181800, "loss": 0.0019, "lr": 1.3739716948756709e-05, "epoch": 13.677117711771178, "percentage": 68.39, "elapsed_time": "4:54:10", "remaining_time": "2:15:59", "throughput": 1486.47, "total_tokens": 26237120} {"current_steps": 124330, "total_steps": 181800, "loss": 0.0339, "lr": 1.373757416937394e-05, "epoch": 13.677667766776677, "percentage": 68.39, "elapsed_time": "4:54:11", "remaining_time": "2:15:59", "throughput": 1486.48, "total_tokens": 26238208} {"current_steps": 124335, "total_steps": 181800, "loss": 0.0465, "lr": 1.3735431493791532e-05, "epoch": 13.678217821782178, "percentage": 68.39, "elapsed_time": "4:54:11", "remaining_time": "2:15:58", "throughput": 1486.48, "total_tokens": 26239296} {"current_steps": 124340, "total_steps": 181800, "loss": 0.037, "lr": 1.3733288922029248e-05, "epoch": 13.67876787678768, "percentage": 68.39, "elapsed_time": "4:54:12", "remaining_time": "2:15:57", "throughput": 1486.48, "total_tokens": 26240352} {"current_steps": 124345, "total_steps": 181800, "loss": 0.0136, "lr": 1.3731146454106844e-05, "epoch": 13.679317931793179, "percentage": 68.4, "elapsed_time": "4:54:13", "remaining_time": "2:15:56", "throughput": 1486.48, "total_tokens": 26241440} {"current_steps": 124350, "total_steps": 181800, "loss": 0.002, "lr": 1.3729004090044045e-05, "epoch": 13.67986798679868, "percentage": 68.4, "elapsed_time": "4:54:14", "remaining_time": "2:15:56", "throughput": 1486.49, "total_tokens": 26242496} {"current_steps": 124355, "total_steps": 181800, "loss": 0.0037, "lr": 1.372686182986062e-05, "epoch": 13.680418041804181, "percentage": 68.4, "elapsed_time": "4:54:14", "remaining_time": "2:15:55", "throughput": 1486.49, "total_tokens": 26243584} {"current_steps": 124360, "total_steps": 181800, "loss": 0.0325, "lr": 1.3724719673576286e-05, "epoch": 13.68096809680968, "percentage": 68.4, "elapsed_time": "4:54:15", "remaining_time": "2:15:54", "throughput": 1486.49, "total_tokens": 26244608} {"current_steps": 124365, "total_steps": 181800, "loss": 0.0882, "lr": 1.3722577621210814e-05, "epoch": 13.681518151815181, "percentage": 68.41, "elapsed_time": "4:54:16", "remaining_time": "2:15:54", "throughput": 1486.49, "total_tokens": 26245664} {"current_steps": 124370, "total_steps": 181800, "loss": 0.007, "lr": 1.3720435672783922e-05, "epoch": 13.682068206820682, "percentage": 68.41, "elapsed_time": "4:54:16", "remaining_time": "2:15:53", "throughput": 1486.5, "total_tokens": 26246784} {"current_steps": 124375, "total_steps": 181800, "loss": 0.0013, "lr": 1.371829382831536e-05, "epoch": 13.682618261826182, "percentage": 68.41, "elapsed_time": "4:54:17", "remaining_time": "2:15:52", "throughput": 1486.5, "total_tokens": 26247840} {"current_steps": 124380, "total_steps": 181800, "loss": 0.0038, "lr": 1.371615208782488e-05, "epoch": 13.683168316831683, "percentage": 68.42, "elapsed_time": "4:54:18", "remaining_time": "2:15:51", "throughput": 1486.5, "total_tokens": 26248864} {"current_steps": 124385, "total_steps": 181800, "loss": 0.0029, "lr": 1.3714010451332204e-05, "epoch": 13.683718371837184, "percentage": 68.42, "elapsed_time": "4:54:18", "remaining_time": "2:15:51", "throughput": 1486.5, "total_tokens": 26249952} {"current_steps": 124390, "total_steps": 181800, "loss": 0.0571, "lr": 1.3711868918857085e-05, "epoch": 13.684268426842685, "percentage": 68.42, "elapsed_time": "4:54:19", "remaining_time": "2:15:50", "throughput": 1486.5, "total_tokens": 26251008} {"current_steps": 124395, "total_steps": 181800, "loss": 0.0365, "lr": 1.3709727490419246e-05, "epoch": 13.684818481848184, "percentage": 68.42, "elapsed_time": "4:54:20", "remaining_time": "2:15:49", "throughput": 1486.5, "total_tokens": 26252032} {"current_steps": 124400, "total_steps": 181800, "loss": 0.0217, "lr": 1.3707586166038433e-05, "epoch": 13.685368536853685, "percentage": 68.43, "elapsed_time": "4:54:20", "remaining_time": "2:15:49", "throughput": 1486.5, "total_tokens": 26253088} {"current_steps": 124405, "total_steps": 181800, "loss": 0.0016, "lr": 1.3705444945734386e-05, "epoch": 13.685918591859187, "percentage": 68.43, "elapsed_time": "4:54:21", "remaining_time": "2:15:48", "throughput": 1486.51, "total_tokens": 26254144} {"current_steps": 124410, "total_steps": 181800, "loss": 0.0065, "lr": 1.3703303829526826e-05, "epoch": 13.686468646864686, "percentage": 68.43, "elapsed_time": "4:54:22", "remaining_time": "2:15:47", "throughput": 1486.51, "total_tokens": 26255200} {"current_steps": 124415, "total_steps": 181800, "loss": 0.0546, "lr": 1.3701162817435503e-05, "epoch": 13.687018701870187, "percentage": 68.44, "elapsed_time": "4:54:23", "remaining_time": "2:15:46", "throughput": 1486.51, "total_tokens": 26256288} {"current_steps": 124420, "total_steps": 181800, "loss": 0.073, "lr": 1.3699021909480136e-05, "epoch": 13.687568756875688, "percentage": 68.44, "elapsed_time": "4:54:23", "remaining_time": "2:15:46", "throughput": 1486.51, "total_tokens": 26257376} {"current_steps": 124425, "total_steps": 181800, "loss": 0.1176, "lr": 1.369688110568046e-05, "epoch": 13.688118811881187, "percentage": 68.44, "elapsed_time": "4:54:24", "remaining_time": "2:15:45", "throughput": 1486.52, "total_tokens": 26258432} {"current_steps": 124430, "total_steps": 181800, "loss": 0.0082, "lr": 1.36947404060562e-05, "epoch": 13.688668866886688, "percentage": 68.44, "elapsed_time": "4:54:25", "remaining_time": "2:15:44", "throughput": 1486.51, "total_tokens": 26259424} {"current_steps": 124435, "total_steps": 181800, "loss": 0.044, "lr": 1.3692599810627096e-05, "epoch": 13.68921892189219, "percentage": 68.45, "elapsed_time": "4:54:25", "remaining_time": "2:15:44", "throughput": 1486.51, "total_tokens": 26260416} {"current_steps": 124440, "total_steps": 181800, "loss": 0.0327, "lr": 1.3690459319412885e-05, "epoch": 13.689768976897689, "percentage": 68.45, "elapsed_time": "4:54:26", "remaining_time": "2:15:43", "throughput": 1486.51, "total_tokens": 26261472} {"current_steps": 124445, "total_steps": 181800, "loss": 0.0067, "lr": 1.368831893243328e-05, "epoch": 13.69031903190319, "percentage": 68.45, "elapsed_time": "4:54:27", "remaining_time": "2:15:42", "throughput": 1486.51, "total_tokens": 26262528} {"current_steps": 124450, "total_steps": 181800, "loss": 0.0204, "lr": 1.3686178649708004e-05, "epoch": 13.690869086908691, "percentage": 68.45, "elapsed_time": "4:54:27", "remaining_time": "2:15:41", "throughput": 1486.52, "total_tokens": 26263584} {"current_steps": 124455, "total_steps": 181800, "loss": 0.0146, "lr": 1.3684038471256787e-05, "epoch": 13.691419141914192, "percentage": 68.46, "elapsed_time": "4:54:28", "remaining_time": "2:15:41", "throughput": 1486.52, "total_tokens": 26264672} {"current_steps": 124460, "total_steps": 181800, "loss": 0.0299, "lr": 1.3681898397099362e-05, "epoch": 13.691969196919691, "percentage": 68.46, "elapsed_time": "4:54:29", "remaining_time": "2:15:40", "throughput": 1486.52, "total_tokens": 26265792} {"current_steps": 124465, "total_steps": 181800, "loss": 0.0595, "lr": 1.3679758427255457e-05, "epoch": 13.692519251925193, "percentage": 68.46, "elapsed_time": "4:54:29", "remaining_time": "2:15:39", "throughput": 1486.53, "total_tokens": 26266848} {"current_steps": 124470, "total_steps": 181800, "loss": 0.053, "lr": 1.3677618561744787e-05, "epoch": 13.693069306930694, "percentage": 68.47, "elapsed_time": "4:54:30", "remaining_time": "2:15:38", "throughput": 1486.53, "total_tokens": 26267904} {"current_steps": 124475, "total_steps": 181800, "loss": 0.0079, "lr": 1.3675478800587062e-05, "epoch": 13.693619361936193, "percentage": 68.47, "elapsed_time": "4:54:31", "remaining_time": "2:15:38", "throughput": 1486.53, "total_tokens": 26268960} {"current_steps": 124480, "total_steps": 181800, "loss": 0.1172, "lr": 1.3673339143802027e-05, "epoch": 13.694169416941694, "percentage": 68.47, "elapsed_time": "4:54:32", "remaining_time": "2:15:37", "throughput": 1486.53, "total_tokens": 26270048} {"current_steps": 124485, "total_steps": 181800, "loss": 0.0451, "lr": 1.3671199591409379e-05, "epoch": 13.694719471947195, "percentage": 68.47, "elapsed_time": "4:54:32", "remaining_time": "2:15:36", "throughput": 1486.54, "total_tokens": 26271168} {"current_steps": 124490, "total_steps": 181800, "loss": 0.0277, "lr": 1.366906014342885e-05, "epoch": 13.695269526952695, "percentage": 68.48, "elapsed_time": "4:54:33", "remaining_time": "2:15:36", "throughput": 1486.54, "total_tokens": 26272256} {"current_steps": 124495, "total_steps": 181800, "loss": 0.0543, "lr": 1.3666920799880162e-05, "epoch": 13.695819581958196, "percentage": 68.48, "elapsed_time": "4:54:34", "remaining_time": "2:15:35", "throughput": 1486.54, "total_tokens": 26273312} {"current_steps": 124500, "total_steps": 181800, "loss": 0.0007, "lr": 1.3664781560783021e-05, "epoch": 13.696369636963697, "percentage": 68.48, "elapsed_time": "4:54:34", "remaining_time": "2:15:34", "throughput": 1486.55, "total_tokens": 26274400} {"current_steps": 124505, "total_steps": 181800, "loss": 0.0041, "lr": 1.3662642426157157e-05, "epoch": 13.696919691969196, "percentage": 68.48, "elapsed_time": "4:54:35", "remaining_time": "2:15:33", "throughput": 1486.54, "total_tokens": 26275392} {"current_steps": 124510, "total_steps": 181800, "loss": 0.0693, "lr": 1.366050339602227e-05, "epoch": 13.697469746974697, "percentage": 68.49, "elapsed_time": "4:54:36", "remaining_time": "2:15:33", "throughput": 1486.54, "total_tokens": 26276416} {"current_steps": 124515, "total_steps": 181800, "loss": 0.0045, "lr": 1.365836447039808e-05, "epoch": 13.698019801980198, "percentage": 68.49, "elapsed_time": "4:54:36", "remaining_time": "2:15:32", "throughput": 1486.54, "total_tokens": 26277472} {"current_steps": 124520, "total_steps": 181800, "loss": 0.0073, "lr": 1.3656225649304314e-05, "epoch": 13.6985698569857, "percentage": 68.49, "elapsed_time": "4:54:37", "remaining_time": "2:15:31", "throughput": 1486.55, "total_tokens": 26278560} {"current_steps": 124525, "total_steps": 181800, "loss": 0.0589, "lr": 1.3654086932760663e-05, "epoch": 13.699119911991199, "percentage": 68.5, "elapsed_time": "4:54:38", "remaining_time": "2:15:31", "throughput": 1486.55, "total_tokens": 26279648} {"current_steps": 124530, "total_steps": 181800, "loss": 0.0356, "lr": 1.3651948320786856e-05, "epoch": 13.6996699669967, "percentage": 68.5, "elapsed_time": "4:54:38", "remaining_time": "2:15:30", "throughput": 1486.56, "total_tokens": 26280800} {"current_steps": 124535, "total_steps": 181800, "loss": 0.0169, "lr": 1.3649809813402597e-05, "epoch": 13.7002200220022, "percentage": 68.5, "elapsed_time": "4:54:39", "remaining_time": "2:15:29", "throughput": 1486.56, "total_tokens": 26281856} {"current_steps": 124540, "total_steps": 181800, "loss": 0.011, "lr": 1.3647671410627582e-05, "epoch": 13.7007700770077, "percentage": 68.5, "elapsed_time": "4:54:40", "remaining_time": "2:15:28", "throughput": 1486.56, "total_tokens": 26282912} {"current_steps": 124545, "total_steps": 181800, "loss": 0.0047, "lr": 1.3645533112481537e-05, "epoch": 13.701320132013201, "percentage": 68.51, "elapsed_time": "4:54:41", "remaining_time": "2:15:28", "throughput": 1486.57, "total_tokens": 26284000} {"current_steps": 124550, "total_steps": 181800, "loss": 0.0259, "lr": 1.3643394918984165e-05, "epoch": 13.701870187018702, "percentage": 68.51, "elapsed_time": "4:54:41", "remaining_time": "2:15:27", "throughput": 1486.57, "total_tokens": 26285056} {"current_steps": 124555, "total_steps": 181800, "loss": 0.02, "lr": 1.364125683015518e-05, "epoch": 13.702420242024202, "percentage": 68.51, "elapsed_time": "4:54:42", "remaining_time": "2:15:26", "throughput": 1486.57, "total_tokens": 26286176} {"current_steps": 124560, "total_steps": 181800, "loss": 0.1207, "lr": 1.3639118846014282e-05, "epoch": 13.702970297029703, "percentage": 68.51, "elapsed_time": "4:54:43", "remaining_time": "2:15:26", "throughput": 1486.57, "total_tokens": 26287232} {"current_steps": 124565, "total_steps": 181800, "loss": 0.087, "lr": 1.3636980966581162e-05, "epoch": 13.703520352035204, "percentage": 68.52, "elapsed_time": "4:54:43", "remaining_time": "2:15:25", "throughput": 1486.57, "total_tokens": 26288256} {"current_steps": 124570, "total_steps": 181800, "loss": 0.0609, "lr": 1.3634843191875546e-05, "epoch": 13.704070407040705, "percentage": 68.52, "elapsed_time": "4:54:44", "remaining_time": "2:15:24", "throughput": 1486.58, "total_tokens": 26289312} {"current_steps": 124575, "total_steps": 181800, "loss": 0.0355, "lr": 1.3632705521917107e-05, "epoch": 13.704620462046204, "percentage": 68.52, "elapsed_time": "4:54:45", "remaining_time": "2:15:23", "throughput": 1486.58, "total_tokens": 26290400} {"current_steps": 124580, "total_steps": 181800, "loss": 0.0584, "lr": 1.3630567956725587e-05, "epoch": 13.705170517051705, "percentage": 68.53, "elapsed_time": "4:54:45", "remaining_time": "2:15:23", "throughput": 1486.58, "total_tokens": 26291488} {"current_steps": 124585, "total_steps": 181800, "loss": 0.0133, "lr": 1.3628430496320668e-05, "epoch": 13.705720572057206, "percentage": 68.53, "elapsed_time": "4:54:46", "remaining_time": "2:15:22", "throughput": 1486.58, "total_tokens": 26292544} {"current_steps": 124590, "total_steps": 181800, "loss": 0.0054, "lr": 1.3626293140722038e-05, "epoch": 13.706270627062706, "percentage": 68.53, "elapsed_time": "4:54:47", "remaining_time": "2:15:21", "throughput": 1486.59, "total_tokens": 26293600} {"current_steps": 124595, "total_steps": 181800, "loss": 0.0778, "lr": 1.3624155889949416e-05, "epoch": 13.706820682068207, "percentage": 68.53, "elapsed_time": "4:54:47", "remaining_time": "2:15:21", "throughput": 1486.59, "total_tokens": 26294720} {"current_steps": 124600, "total_steps": 181800, "loss": 0.0077, "lr": 1.362201874402248e-05, "epoch": 13.707370737073708, "percentage": 68.54, "elapsed_time": "4:54:48", "remaining_time": "2:15:20", "throughput": 1486.59, "total_tokens": 26295776} {"current_steps": 124605, "total_steps": 181800, "loss": 0.0028, "lr": 1.361988170296094e-05, "epoch": 13.707920792079207, "percentage": 68.54, "elapsed_time": "4:54:49", "remaining_time": "2:15:19", "throughput": 1486.6, "total_tokens": 26296864} {"current_steps": 124610, "total_steps": 181800, "loss": 0.1982, "lr": 1.3617744766784496e-05, "epoch": 13.708470847084708, "percentage": 68.54, "elapsed_time": "4:54:50", "remaining_time": "2:15:18", "throughput": 1486.6, "total_tokens": 26297984} {"current_steps": 124615, "total_steps": 181800, "loss": 0.0019, "lr": 1.3615607935512828e-05, "epoch": 13.70902090209021, "percentage": 68.55, "elapsed_time": "4:54:50", "remaining_time": "2:15:18", "throughput": 1486.61, "total_tokens": 26299136} {"current_steps": 124620, "total_steps": 181800, "loss": 0.069, "lr": 1.3613471209165652e-05, "epoch": 13.70957095709571, "percentage": 68.55, "elapsed_time": "4:54:51", "remaining_time": "2:15:17", "throughput": 1486.61, "total_tokens": 26300160} {"current_steps": 124625, "total_steps": 181800, "loss": 0.0081, "lr": 1.3611334587762634e-05, "epoch": 13.71012101210121, "percentage": 68.55, "elapsed_time": "4:54:52", "remaining_time": "2:15:16", "throughput": 1486.61, "total_tokens": 26301184} {"current_steps": 124630, "total_steps": 181800, "loss": 0.2321, "lr": 1.3609198071323492e-05, "epoch": 13.710671067106711, "percentage": 68.55, "elapsed_time": "4:54:52", "remaining_time": "2:15:15", "throughput": 1486.61, "total_tokens": 26302240} {"current_steps": 124635, "total_steps": 181800, "loss": 0.0219, "lr": 1.3607061659867892e-05, "epoch": 13.711221122112212, "percentage": 68.56, "elapsed_time": "4:54:53", "remaining_time": "2:15:15", "throughput": 1486.61, "total_tokens": 26303328} {"current_steps": 124640, "total_steps": 181800, "loss": 0.0588, "lr": 1.3604925353415543e-05, "epoch": 13.711771177117711, "percentage": 68.56, "elapsed_time": "4:54:54", "remaining_time": "2:15:14", "throughput": 1486.62, "total_tokens": 26304480} {"current_steps": 124645, "total_steps": 181800, "loss": 0.04, "lr": 1.3602789151986137e-05, "epoch": 13.712321232123212, "percentage": 68.56, "elapsed_time": "4:54:54", "remaining_time": "2:15:13", "throughput": 1486.62, "total_tokens": 26305504} {"current_steps": 124650, "total_steps": 181800, "loss": 0.0304, "lr": 1.3600653055599344e-05, "epoch": 13.712871287128714, "percentage": 68.56, "elapsed_time": "4:54:55", "remaining_time": "2:15:13", "throughput": 1486.62, "total_tokens": 26306560} {"current_steps": 124655, "total_steps": 181800, "loss": 0.0064, "lr": 1.3598517064274874e-05, "epoch": 13.713421342134213, "percentage": 68.57, "elapsed_time": "4:54:56", "remaining_time": "2:15:12", "throughput": 1486.62, "total_tokens": 26307616} {"current_steps": 124660, "total_steps": 181800, "loss": 0.0449, "lr": 1.3596381178032389e-05, "epoch": 13.713971397139714, "percentage": 68.57, "elapsed_time": "4:54:56", "remaining_time": "2:15:11", "throughput": 1486.62, "total_tokens": 26308640} {"current_steps": 124665, "total_steps": 181800, "loss": 0.0183, "lr": 1.3594245396891586e-05, "epoch": 13.714521452145215, "percentage": 68.57, "elapsed_time": "4:54:57", "remaining_time": "2:15:10", "throughput": 1486.63, "total_tokens": 26309760} {"current_steps": 124670, "total_steps": 181800, "loss": 0.0665, "lr": 1.3592109720872161e-05, "epoch": 13.715071507150714, "percentage": 68.58, "elapsed_time": "4:54:58", "remaining_time": "2:15:10", "throughput": 1486.63, "total_tokens": 26310816} {"current_steps": 124675, "total_steps": 181800, "loss": 0.0251, "lr": 1.3589974149993778e-05, "epoch": 13.715621562156215, "percentage": 68.58, "elapsed_time": "4:54:58", "remaining_time": "2:15:09", "throughput": 1486.63, "total_tokens": 26311840} {"current_steps": 124680, "total_steps": 181800, "loss": 0.0061, "lr": 1.3587838684276139e-05, "epoch": 13.716171617161717, "percentage": 68.58, "elapsed_time": "4:54:59", "remaining_time": "2:15:08", "throughput": 1486.63, "total_tokens": 26312864} {"current_steps": 124685, "total_steps": 181800, "loss": 0.0042, "lr": 1.3585703323738912e-05, "epoch": 13.716721672167218, "percentage": 68.58, "elapsed_time": "4:55:00", "remaining_time": "2:15:08", "throughput": 1486.63, "total_tokens": 26313920} {"current_steps": 124690, "total_steps": 181800, "loss": 0.0476, "lr": 1.3583568068401763e-05, "epoch": 13.717271727172717, "percentage": 68.59, "elapsed_time": "4:55:01", "remaining_time": "2:15:07", "throughput": 1486.64, "total_tokens": 26315040} {"current_steps": 124695, "total_steps": 181800, "loss": 0.0795, "lr": 1.3581432918284406e-05, "epoch": 13.717821782178218, "percentage": 68.59, "elapsed_time": "4:55:01", "remaining_time": "2:15:06", "throughput": 1486.64, "total_tokens": 26316128} {"current_steps": 124700, "total_steps": 181800, "loss": 0.0671, "lr": 1.3579297873406493e-05, "epoch": 13.718371837183719, "percentage": 68.59, "elapsed_time": "4:55:02", "remaining_time": "2:15:05", "throughput": 1486.65, "total_tokens": 26317248} {"current_steps": 124705, "total_steps": 181800, "loss": 0.0092, "lr": 1.3577162933787724e-05, "epoch": 13.718921892189218, "percentage": 68.59, "elapsed_time": "4:55:03", "remaining_time": "2:15:05", "throughput": 1486.65, "total_tokens": 26318336} {"current_steps": 124710, "total_steps": 181800, "loss": 0.0997, "lr": 1.3575028099447761e-05, "epoch": 13.71947194719472, "percentage": 68.6, "elapsed_time": "4:55:03", "remaining_time": "2:15:04", "throughput": 1486.65, "total_tokens": 26319392} {"current_steps": 124715, "total_steps": 181800, "loss": 0.0175, "lr": 1.3572893370406272e-05, "epoch": 13.72002200220022, "percentage": 68.6, "elapsed_time": "4:55:04", "remaining_time": "2:15:03", "throughput": 1486.65, "total_tokens": 26320384} {"current_steps": 124720, "total_steps": 181800, "loss": 0.0081, "lr": 1.3570758746682944e-05, "epoch": 13.72057205720572, "percentage": 68.6, "elapsed_time": "4:55:05", "remaining_time": "2:15:03", "throughput": 1486.66, "total_tokens": 26321504} {"current_steps": 124725, "total_steps": 181800, "loss": 0.0088, "lr": 1.3568624228297454e-05, "epoch": 13.721122112211221, "percentage": 68.61, "elapsed_time": "4:55:05", "remaining_time": "2:15:02", "throughput": 1486.66, "total_tokens": 26322496} {"current_steps": 124730, "total_steps": 181800, "loss": 0.0048, "lr": 1.3566489815269462e-05, "epoch": 13.721672167216722, "percentage": 68.61, "elapsed_time": "4:55:06", "remaining_time": "2:15:01", "throughput": 1486.66, "total_tokens": 26323520} {"current_steps": 124735, "total_steps": 181800, "loss": 0.0394, "lr": 1.3564355507618657e-05, "epoch": 13.722222222222221, "percentage": 68.61, "elapsed_time": "4:55:07", "remaining_time": "2:15:00", "throughput": 1486.66, "total_tokens": 26324608} {"current_steps": 124740, "total_steps": 181800, "loss": 0.0103, "lr": 1.356222130536469e-05, "epoch": 13.722772277227723, "percentage": 68.61, "elapsed_time": "4:55:07", "remaining_time": "2:15:00", "throughput": 1486.66, "total_tokens": 26325696} {"current_steps": 124745, "total_steps": 181800, "loss": 0.0615, "lr": 1.356008720852725e-05, "epoch": 13.723322332233224, "percentage": 68.62, "elapsed_time": "4:55:08", "remaining_time": "2:14:59", "throughput": 1486.67, "total_tokens": 26326816} {"current_steps": 124750, "total_steps": 181800, "loss": 0.0335, "lr": 1.3557953217125986e-05, "epoch": 13.723872387238725, "percentage": 68.62, "elapsed_time": "4:55:09", "remaining_time": "2:14:58", "throughput": 1486.65, "total_tokens": 26327840} {"current_steps": 124755, "total_steps": 181800, "loss": 0.0111, "lr": 1.3555819331180577e-05, "epoch": 13.724422442244224, "percentage": 68.62, "elapsed_time": "4:55:10", "remaining_time": "2:14:58", "throughput": 1486.65, "total_tokens": 26328896} {"current_steps": 124760, "total_steps": 181800, "loss": 0.0064, "lr": 1.3553685550710701e-05, "epoch": 13.724972497249725, "percentage": 68.62, "elapsed_time": "4:55:10", "remaining_time": "2:14:57", "throughput": 1486.66, "total_tokens": 26329984} {"current_steps": 124765, "total_steps": 181800, "loss": 0.0039, "lr": 1.3551551875736002e-05, "epoch": 13.725522552255226, "percentage": 68.63, "elapsed_time": "4:55:11", "remaining_time": "2:14:56", "throughput": 1486.66, "total_tokens": 26331040} {"current_steps": 124770, "total_steps": 181800, "loss": 0.0066, "lr": 1.3549418306276169e-05, "epoch": 13.726072607260726, "percentage": 68.63, "elapsed_time": "4:55:12", "remaining_time": "2:14:55", "throughput": 1486.67, "total_tokens": 26332160} {"current_steps": 124775, "total_steps": 181800, "loss": 0.0029, "lr": 1.3547284842350838e-05, "epoch": 13.726622662266227, "percentage": 68.63, "elapsed_time": "4:55:12", "remaining_time": "2:14:55", "throughput": 1486.67, "total_tokens": 26333248} {"current_steps": 124780, "total_steps": 181800, "loss": 0.0187, "lr": 1.354515148397969e-05, "epoch": 13.727172717271728, "percentage": 68.64, "elapsed_time": "4:55:13", "remaining_time": "2:14:54", "throughput": 1486.67, "total_tokens": 26334240} {"current_steps": 124785, "total_steps": 181800, "loss": 0.003, "lr": 1.3543018231182391e-05, "epoch": 13.727722772277227, "percentage": 68.64, "elapsed_time": "4:55:14", "remaining_time": "2:14:53", "throughput": 1486.67, "total_tokens": 26335328} {"current_steps": 124790, "total_steps": 181800, "loss": 0.0719, "lr": 1.3540885083978589e-05, "epoch": 13.728272827282728, "percentage": 68.64, "elapsed_time": "4:55:14", "remaining_time": "2:14:53", "throughput": 1486.67, "total_tokens": 26336384} {"current_steps": 124795, "total_steps": 181800, "loss": 0.0131, "lr": 1.3538752042387958e-05, "epoch": 13.72882288228823, "percentage": 68.64, "elapsed_time": "4:55:15", "remaining_time": "2:14:52", "throughput": 1486.67, "total_tokens": 26337408} {"current_steps": 124800, "total_steps": 181800, "loss": 0.0229, "lr": 1.3536619106430154e-05, "epoch": 13.729372937293729, "percentage": 68.65, "elapsed_time": "4:55:16", "remaining_time": "2:14:51", "throughput": 1486.67, "total_tokens": 26338432} {"current_steps": 124805, "total_steps": 181800, "loss": 0.0872, "lr": 1.3534486276124817e-05, "epoch": 13.72992299229923, "percentage": 68.65, "elapsed_time": "4:55:17", "remaining_time": "2:14:50", "throughput": 1486.67, "total_tokens": 26339456} {"current_steps": 124810, "total_steps": 181800, "loss": 0.0556, "lr": 1.353235355149162e-05, "epoch": 13.73047304730473, "percentage": 68.65, "elapsed_time": "4:55:17", "remaining_time": "2:14:50", "throughput": 1486.67, "total_tokens": 26340448} {"current_steps": 124815, "total_steps": 181800, "loss": 0.0052, "lr": 1.3530220932550216e-05, "epoch": 13.731023102310232, "percentage": 68.66, "elapsed_time": "4:55:18", "remaining_time": "2:14:49", "throughput": 1486.68, "total_tokens": 26341536} {"current_steps": 124820, "total_steps": 181800, "loss": 0.009, "lr": 1.3528088419320273e-05, "epoch": 13.731573157315731, "percentage": 68.66, "elapsed_time": "4:55:19", "remaining_time": "2:14:48", "throughput": 1486.67, "total_tokens": 26342528} {"current_steps": 124825, "total_steps": 181800, "loss": 0.0417, "lr": 1.3525956011821434e-05, "epoch": 13.732123212321232, "percentage": 68.66, "elapsed_time": "4:55:19", "remaining_time": "2:14:47", "throughput": 1486.68, "total_tokens": 26343616} {"current_steps": 124830, "total_steps": 181800, "loss": 0.008, "lr": 1.3523823710073344e-05, "epoch": 13.732673267326733, "percentage": 68.66, "elapsed_time": "4:55:20", "remaining_time": "2:14:47", "throughput": 1486.68, "total_tokens": 26344640} {"current_steps": 124835, "total_steps": 181800, "loss": 0.0029, "lr": 1.3521691514095663e-05, "epoch": 13.733223322332233, "percentage": 68.67, "elapsed_time": "4:55:21", "remaining_time": "2:14:46", "throughput": 1486.68, "total_tokens": 26345696} {"current_steps": 124840, "total_steps": 181800, "loss": 0.0294, "lr": 1.3519559423908043e-05, "epoch": 13.733773377337734, "percentage": 68.67, "elapsed_time": "4:55:21", "remaining_time": "2:14:45", "throughput": 1486.68, "total_tokens": 26346720} {"current_steps": 124845, "total_steps": 181800, "loss": 0.0053, "lr": 1.3517427439530144e-05, "epoch": 13.734323432343235, "percentage": 68.67, "elapsed_time": "4:55:22", "remaining_time": "2:14:45", "throughput": 1486.69, "total_tokens": 26347840} {"current_steps": 124850, "total_steps": 181800, "loss": 0.0356, "lr": 1.3515295560981609e-05, "epoch": 13.734873487348734, "percentage": 68.67, "elapsed_time": "4:55:23", "remaining_time": "2:14:44", "throughput": 1486.69, "total_tokens": 26348896} {"current_steps": 124855, "total_steps": 181800, "loss": 0.0095, "lr": 1.3513163788282075e-05, "epoch": 13.735423542354235, "percentage": 68.68, "elapsed_time": "4:55:23", "remaining_time": "2:14:43", "throughput": 1486.69, "total_tokens": 26349952} {"current_steps": 124860, "total_steps": 181800, "loss": 0.0706, "lr": 1.3511032121451203e-05, "epoch": 13.735973597359736, "percentage": 68.68, "elapsed_time": "4:55:24", "remaining_time": "2:14:42", "throughput": 1486.69, "total_tokens": 26351008} {"current_steps": 124865, "total_steps": 181800, "loss": 0.0111, "lr": 1.350890056050863e-05, "epoch": 13.736523652365236, "percentage": 68.68, "elapsed_time": "4:55:25", "remaining_time": "2:14:42", "throughput": 1486.69, "total_tokens": 26352064} {"current_steps": 124870, "total_steps": 181800, "loss": 0.0061, "lr": 1.3506769105474004e-05, "epoch": 13.737073707370737, "percentage": 68.69, "elapsed_time": "4:55:25", "remaining_time": "2:14:41", "throughput": 1486.7, "total_tokens": 26353120} {"current_steps": 124875, "total_steps": 181800, "loss": 0.0025, "lr": 1.3504637756366983e-05, "epoch": 13.737623762376238, "percentage": 68.69, "elapsed_time": "4:55:26", "remaining_time": "2:14:40", "throughput": 1486.69, "total_tokens": 26354112} {"current_steps": 124880, "total_steps": 181800, "loss": 0.0075, "lr": 1.350250651320719e-05, "epoch": 13.738173817381739, "percentage": 68.69, "elapsed_time": "4:55:27", "remaining_time": "2:14:40", "throughput": 1486.7, "total_tokens": 26355168} {"current_steps": 124885, "total_steps": 181800, "loss": 0.0507, "lr": 1.3500375376014285e-05, "epoch": 13.738723872387238, "percentage": 68.69, "elapsed_time": "4:55:28", "remaining_time": "2:14:39", "throughput": 1486.69, "total_tokens": 26356160} {"current_steps": 124890, "total_steps": 181800, "loss": 0.0217, "lr": 1.3498244344807895e-05, "epoch": 13.73927392739274, "percentage": 68.7, "elapsed_time": "4:55:28", "remaining_time": "2:14:38", "throughput": 1486.7, "total_tokens": 26357248} {"current_steps": 124895, "total_steps": 181800, "loss": 0.0128, "lr": 1.3496113419607667e-05, "epoch": 13.73982398239824, "percentage": 68.7, "elapsed_time": "4:55:29", "remaining_time": "2:14:37", "throughput": 1486.7, "total_tokens": 26358304} {"current_steps": 124900, "total_steps": 181800, "loss": 0.0265, "lr": 1.3493982600433253e-05, "epoch": 13.74037403740374, "percentage": 68.7, "elapsed_time": "4:55:30", "remaining_time": "2:14:37", "throughput": 1486.7, "total_tokens": 26359360} {"current_steps": 124905, "total_steps": 181800, "loss": 0.0049, "lr": 1.349185188730427e-05, "epoch": 13.74092409240924, "percentage": 68.7, "elapsed_time": "4:55:30", "remaining_time": "2:14:36", "throughput": 1486.71, "total_tokens": 26360480} {"current_steps": 124910, "total_steps": 181800, "loss": 0.0016, "lr": 1.3489721280240373e-05, "epoch": 13.741474147414742, "percentage": 68.71, "elapsed_time": "4:55:31", "remaining_time": "2:14:35", "throughput": 1486.71, "total_tokens": 26361568} {"current_steps": 124915, "total_steps": 181800, "loss": 0.1408, "lr": 1.3487590779261194e-05, "epoch": 13.742024202420241, "percentage": 68.71, "elapsed_time": "4:55:32", "remaining_time": "2:14:35", "throughput": 1486.71, "total_tokens": 26362656} {"current_steps": 124920, "total_steps": 181800, "loss": 0.0021, "lr": 1.3485460384386356e-05, "epoch": 13.742574257425742, "percentage": 68.71, "elapsed_time": "4:55:32", "remaining_time": "2:14:34", "throughput": 1486.72, "total_tokens": 26363776} {"current_steps": 124925, "total_steps": 181800, "loss": 0.0103, "lr": 1.3483330095635504e-05, "epoch": 13.743124312431243, "percentage": 68.72, "elapsed_time": "4:55:33", "remaining_time": "2:14:33", "throughput": 1486.72, "total_tokens": 26364800} {"current_steps": 124930, "total_steps": 181800, "loss": 0.1152, "lr": 1.3481199913028272e-05, "epoch": 13.743674367436743, "percentage": 68.72, "elapsed_time": "4:55:34", "remaining_time": "2:14:32", "throughput": 1486.72, "total_tokens": 26365888} {"current_steps": 124935, "total_steps": 181800, "loss": 0.0126, "lr": 1.3479069836584304e-05, "epoch": 13.744224422442244, "percentage": 68.72, "elapsed_time": "4:55:34", "remaining_time": "2:14:32", "throughput": 1486.73, "total_tokens": 26366976} {"current_steps": 124940, "total_steps": 181800, "loss": 0.0018, "lr": 1.3476939866323221e-05, "epoch": 13.744774477447745, "percentage": 68.72, "elapsed_time": "4:55:35", "remaining_time": "2:14:31", "throughput": 1486.73, "total_tokens": 26368000} {"current_steps": 124945, "total_steps": 181800, "loss": 0.0044, "lr": 1.3474810002264643e-05, "epoch": 13.745324532453246, "percentage": 68.73, "elapsed_time": "4:55:36", "remaining_time": "2:14:30", "throughput": 1486.73, "total_tokens": 26369024} {"current_steps": 124950, "total_steps": 181800, "loss": 0.0111, "lr": 1.3472680244428215e-05, "epoch": 13.745874587458745, "percentage": 68.73, "elapsed_time": "4:55:36", "remaining_time": "2:14:29", "throughput": 1486.73, "total_tokens": 26370080} {"current_steps": 124955, "total_steps": 181800, "loss": 0.0112, "lr": 1.3470550592833558e-05, "epoch": 13.746424642464246, "percentage": 68.73, "elapsed_time": "4:55:37", "remaining_time": "2:14:29", "throughput": 1486.73, "total_tokens": 26371168} {"current_steps": 124960, "total_steps": 181800, "loss": 0.1287, "lr": 1.3468421047500312e-05, "epoch": 13.746974697469748, "percentage": 68.73, "elapsed_time": "4:55:38", "remaining_time": "2:14:28", "throughput": 1486.73, "total_tokens": 26372160} {"current_steps": 124965, "total_steps": 181800, "loss": 0.0029, "lr": 1.34662916084481e-05, "epoch": 13.747524752475247, "percentage": 68.74, "elapsed_time": "4:55:39", "remaining_time": "2:14:27", "throughput": 1486.73, "total_tokens": 26373216} {"current_steps": 124970, "total_steps": 181800, "loss": 0.0125, "lr": 1.3464162275696532e-05, "epoch": 13.748074807480748, "percentage": 68.74, "elapsed_time": "4:55:39", "remaining_time": "2:14:27", "throughput": 1486.73, "total_tokens": 26374272} {"current_steps": 124975, "total_steps": 181800, "loss": 0.0104, "lr": 1.3462033049265255e-05, "epoch": 13.748624862486249, "percentage": 68.74, "elapsed_time": "4:55:40", "remaining_time": "2:14:26", "throughput": 1486.73, "total_tokens": 26375296} {"current_steps": 124980, "total_steps": 181800, "loss": 0.0023, "lr": 1.3459903929173872e-05, "epoch": 13.749174917491748, "percentage": 68.75, "elapsed_time": "4:55:41", "remaining_time": "2:14:25", "throughput": 1486.73, "total_tokens": 26376320} {"current_steps": 124985, "total_steps": 181800, "loss": 0.0037, "lr": 1.3457774915442017e-05, "epoch": 13.74972497249725, "percentage": 68.75, "elapsed_time": "4:55:41", "remaining_time": "2:14:24", "throughput": 1486.74, "total_tokens": 26377408} {"current_steps": 124990, "total_steps": 181800, "loss": 0.0063, "lr": 1.3455646008089325e-05, "epoch": 13.75027502750275, "percentage": 68.75, "elapsed_time": "4:55:42", "remaining_time": "2:14:24", "throughput": 1486.74, "total_tokens": 26378464} {"current_steps": 124995, "total_steps": 181800, "loss": 0.0163, "lr": 1.3453517207135391e-05, "epoch": 13.750825082508252, "percentage": 68.75, "elapsed_time": "4:55:43", "remaining_time": "2:14:23", "throughput": 1486.74, "total_tokens": 26379584} {"current_steps": 125000, "total_steps": 181800, "loss": 0.0891, "lr": 1.345138851259986e-05, "epoch": 13.751375137513751, "percentage": 68.76, "elapsed_time": "4:55:43", "remaining_time": "2:14:22", "throughput": 1486.75, "total_tokens": 26380640} {"current_steps": 125005, "total_steps": 181800, "loss": 0.0014, "lr": 1.3449259924502331e-05, "epoch": 13.751925192519252, "percentage": 68.76, "elapsed_time": "4:55:44", "remaining_time": "2:14:22", "throughput": 1486.75, "total_tokens": 26381664} {"current_steps": 125010, "total_steps": 181800, "loss": 0.064, "lr": 1.3447131442862429e-05, "epoch": 13.752475247524753, "percentage": 68.76, "elapsed_time": "4:55:45", "remaining_time": "2:14:21", "throughput": 1486.75, "total_tokens": 26382720} {"current_steps": 125015, "total_steps": 181800, "loss": 0.0027, "lr": 1.3445003067699782e-05, "epoch": 13.753025302530252, "percentage": 68.77, "elapsed_time": "4:55:45", "remaining_time": "2:14:20", "throughput": 1486.76, "total_tokens": 26383872} {"current_steps": 125020, "total_steps": 181800, "loss": 0.0055, "lr": 1.3442874799033989e-05, "epoch": 13.753575357535754, "percentage": 68.77, "elapsed_time": "4:55:46", "remaining_time": "2:14:19", "throughput": 1486.76, "total_tokens": 26384928} {"current_steps": 125025, "total_steps": 181800, "loss": 0.0523, "lr": 1.3440746636884682e-05, "epoch": 13.754125412541255, "percentage": 68.77, "elapsed_time": "4:55:47", "remaining_time": "2:14:19", "throughput": 1486.76, "total_tokens": 26385952} {"current_steps": 125030, "total_steps": 181800, "loss": 0.0024, "lr": 1.3438618581271455e-05, "epoch": 13.754675467546754, "percentage": 68.77, "elapsed_time": "4:55:48", "remaining_time": "2:14:18", "throughput": 1486.76, "total_tokens": 26386944} {"current_steps": 125035, "total_steps": 181800, "loss": 0.0083, "lr": 1.3436490632213943e-05, "epoch": 13.755225522552255, "percentage": 68.78, "elapsed_time": "4:55:48", "remaining_time": "2:14:17", "throughput": 1486.76, "total_tokens": 26388064} {"current_steps": 125040, "total_steps": 181800, "loss": 0.0051, "lr": 1.3434362789731742e-05, "epoch": 13.755775577557756, "percentage": 68.78, "elapsed_time": "4:55:49", "remaining_time": "2:14:17", "throughput": 1486.76, "total_tokens": 26389120} {"current_steps": 125045, "total_steps": 181800, "loss": 0.0038, "lr": 1.3432235053844467e-05, "epoch": 13.756325632563257, "percentage": 68.78, "elapsed_time": "4:55:50", "remaining_time": "2:14:16", "throughput": 1486.77, "total_tokens": 26390208} {"current_steps": 125050, "total_steps": 181800, "loss": 0.0025, "lr": 1.3430107424571742e-05, "epoch": 13.756875687568757, "percentage": 68.78, "elapsed_time": "4:55:50", "remaining_time": "2:14:15", "throughput": 1486.77, "total_tokens": 26391264} {"current_steps": 125055, "total_steps": 181800, "loss": 0.0487, "lr": 1.3427979901933152e-05, "epoch": 13.757425742574258, "percentage": 68.79, "elapsed_time": "4:55:51", "remaining_time": "2:14:14", "throughput": 1486.77, "total_tokens": 26392352} {"current_steps": 125060, "total_steps": 181800, "loss": 0.0386, "lr": 1.3425852485948331e-05, "epoch": 13.757975797579759, "percentage": 68.79, "elapsed_time": "4:55:52", "remaining_time": "2:14:14", "throughput": 1486.77, "total_tokens": 26393376} {"current_steps": 125065, "total_steps": 181800, "loss": 0.008, "lr": 1.3423725176636864e-05, "epoch": 13.758525852585258, "percentage": 68.79, "elapsed_time": "4:55:52", "remaining_time": "2:14:13", "throughput": 1486.77, "total_tokens": 26394400} {"current_steps": 125070, "total_steps": 181800, "loss": 0.0013, "lr": 1.3421597974018369e-05, "epoch": 13.75907590759076, "percentage": 68.8, "elapsed_time": "4:55:53", "remaining_time": "2:14:12", "throughput": 1486.77, "total_tokens": 26395456} {"current_steps": 125075, "total_steps": 181800, "loss": 0.0161, "lr": 1.3419470878112455e-05, "epoch": 13.75962596259626, "percentage": 68.8, "elapsed_time": "4:55:54", "remaining_time": "2:14:12", "throughput": 1486.77, "total_tokens": 26396480} {"current_steps": 125080, "total_steps": 181800, "loss": 0.1057, "lr": 1.3417343888938713e-05, "epoch": 13.76017601760176, "percentage": 68.8, "elapsed_time": "4:55:54", "remaining_time": "2:14:11", "throughput": 1486.77, "total_tokens": 26397472} {"current_steps": 125085, "total_steps": 181800, "loss": 0.0018, "lr": 1.3415217006516765e-05, "epoch": 13.76072607260726, "percentage": 68.8, "elapsed_time": "4:55:55", "remaining_time": "2:14:10", "throughput": 1486.77, "total_tokens": 26398528} {"current_steps": 125090, "total_steps": 181800, "loss": 0.0403, "lr": 1.3413090230866204e-05, "epoch": 13.761276127612762, "percentage": 68.81, "elapsed_time": "4:55:56", "remaining_time": "2:14:09", "throughput": 1486.78, "total_tokens": 26399648} {"current_steps": 125095, "total_steps": 181800, "loss": 0.0025, "lr": 1.3410963562006618e-05, "epoch": 13.761826182618261, "percentage": 68.81, "elapsed_time": "4:55:56", "remaining_time": "2:14:09", "throughput": 1486.78, "total_tokens": 26400704} {"current_steps": 125100, "total_steps": 181800, "loss": 0.0113, "lr": 1.3408836999957619e-05, "epoch": 13.762376237623762, "percentage": 68.81, "elapsed_time": "4:55:57", "remaining_time": "2:14:08", "throughput": 1486.78, "total_tokens": 26401728} {"current_steps": 125105, "total_steps": 181800, "loss": 0.0647, "lr": 1.340671054473882e-05, "epoch": 13.762926292629263, "percentage": 68.81, "elapsed_time": "4:55:58", "remaining_time": "2:14:07", "throughput": 1486.78, "total_tokens": 26402816} {"current_steps": 125110, "total_steps": 181800, "loss": 0.015, "lr": 1.3404584196369796e-05, "epoch": 13.763476347634764, "percentage": 68.82, "elapsed_time": "4:55:59", "remaining_time": "2:14:07", "throughput": 1486.79, "total_tokens": 26403936} {"current_steps": 125115, "total_steps": 181800, "loss": 0.0793, "lr": 1.3402457954870169e-05, "epoch": 13.764026402640264, "percentage": 68.82, "elapsed_time": "4:55:59", "remaining_time": "2:14:06", "throughput": 1486.79, "total_tokens": 26404928} {"current_steps": 125120, "total_steps": 181800, "loss": 0.0068, "lr": 1.3400331820259504e-05, "epoch": 13.764576457645765, "percentage": 68.82, "elapsed_time": "4:56:00", "remaining_time": "2:14:05", "throughput": 1486.78, "total_tokens": 26405952} {"current_steps": 125125, "total_steps": 181800, "loss": 0.0284, "lr": 1.3398205792557423e-05, "epoch": 13.765126512651266, "percentage": 68.83, "elapsed_time": "4:56:01", "remaining_time": "2:14:04", "throughput": 1486.78, "total_tokens": 26406976} {"current_steps": 125130, "total_steps": 181800, "loss": 0.0227, "lr": 1.3396079871783517e-05, "epoch": 13.765676567656765, "percentage": 68.83, "elapsed_time": "4:56:01", "remaining_time": "2:14:04", "throughput": 1486.78, "total_tokens": 26408000} {"current_steps": 125135, "total_steps": 181800, "loss": 0.0022, "lr": 1.3393954057957364e-05, "epoch": 13.766226622662266, "percentage": 68.83, "elapsed_time": "4:56:02", "remaining_time": "2:14:03", "throughput": 1486.79, "total_tokens": 26409088} {"current_steps": 125140, "total_steps": 181800, "loss": 0.1293, "lr": 1.3391828351098578e-05, "epoch": 13.766776677667767, "percentage": 68.83, "elapsed_time": "4:56:03", "remaining_time": "2:14:02", "throughput": 1486.79, "total_tokens": 26410112} {"current_steps": 125145, "total_steps": 181800, "loss": 0.0084, "lr": 1.3389702751226735e-05, "epoch": 13.767326732673267, "percentage": 68.84, "elapsed_time": "4:56:03", "remaining_time": "2:14:01", "throughput": 1486.79, "total_tokens": 26411168} {"current_steps": 125150, "total_steps": 181800, "loss": 0.003, "lr": 1.3387577258361436e-05, "epoch": 13.767876787678768, "percentage": 68.84, "elapsed_time": "4:56:04", "remaining_time": "2:14:01", "throughput": 1486.79, "total_tokens": 26412160} {"current_steps": 125155, "total_steps": 181800, "loss": 0.0076, "lr": 1.3385451872522256e-05, "epoch": 13.768426842684269, "percentage": 68.84, "elapsed_time": "4:56:05", "remaining_time": "2:14:00", "throughput": 1486.79, "total_tokens": 26413184} {"current_steps": 125160, "total_steps": 181800, "loss": 0.0481, "lr": 1.3383326593728794e-05, "epoch": 13.768976897689768, "percentage": 68.84, "elapsed_time": "4:56:05", "remaining_time": "2:13:59", "throughput": 1486.79, "total_tokens": 26414176} {"current_steps": 125165, "total_steps": 181800, "loss": 0.0028, "lr": 1.3381201422000645e-05, "epoch": 13.76952695269527, "percentage": 68.85, "elapsed_time": "4:56:06", "remaining_time": "2:13:59", "throughput": 1486.79, "total_tokens": 26415232} {"current_steps": 125170, "total_steps": 181800, "loss": 0.0284, "lr": 1.337907635735738e-05, "epoch": 13.77007700770077, "percentage": 68.85, "elapsed_time": "4:56:07", "remaining_time": "2:13:58", "throughput": 1486.79, "total_tokens": 26416320} {"current_steps": 125175, "total_steps": 181800, "loss": 0.0865, "lr": 1.3376951399818596e-05, "epoch": 13.770627062706271, "percentage": 68.85, "elapsed_time": "4:56:08", "remaining_time": "2:13:57", "throughput": 1486.8, "total_tokens": 26417440} {"current_steps": 125180, "total_steps": 181800, "loss": 0.0025, "lr": 1.3374826549403868e-05, "epoch": 13.77117711771177, "percentage": 68.86, "elapsed_time": "4:56:08", "remaining_time": "2:13:56", "throughput": 1486.8, "total_tokens": 26418560} {"current_steps": 125185, "total_steps": 181800, "loss": 0.0156, "lr": 1.3372701806132787e-05, "epoch": 13.771727172717272, "percentage": 68.86, "elapsed_time": "4:56:09", "remaining_time": "2:13:56", "throughput": 1486.8, "total_tokens": 26419616} {"current_steps": 125190, "total_steps": 181800, "loss": 0.0038, "lr": 1.337057717002494e-05, "epoch": 13.772277227722773, "percentage": 68.86, "elapsed_time": "4:56:10", "remaining_time": "2:13:55", "throughput": 1486.81, "total_tokens": 26420704} {"current_steps": 125195, "total_steps": 181800, "loss": 0.1314, "lr": 1.3368452641099893e-05, "epoch": 13.772827282728272, "percentage": 68.86, "elapsed_time": "4:56:10", "remaining_time": "2:13:54", "throughput": 1486.8, "total_tokens": 26421696} {"current_steps": 125200, "total_steps": 181800, "loss": 0.0049, "lr": 1.336632821937725e-05, "epoch": 13.773377337733773, "percentage": 68.87, "elapsed_time": "4:56:11", "remaining_time": "2:13:54", "throughput": 1486.81, "total_tokens": 26422752} {"current_steps": 125205, "total_steps": 181800, "loss": 0.0904, "lr": 1.3364203904876576e-05, "epoch": 13.773927392739274, "percentage": 68.87, "elapsed_time": "4:56:12", "remaining_time": "2:13:53", "throughput": 1486.81, "total_tokens": 26423776} {"current_steps": 125210, "total_steps": 181800, "loss": 0.0108, "lr": 1.3362079697617441e-05, "epoch": 13.774477447744774, "percentage": 68.87, "elapsed_time": "4:56:12", "remaining_time": "2:13:52", "throughput": 1486.81, "total_tokens": 26424928} {"current_steps": 125215, "total_steps": 181800, "loss": 0.0016, "lr": 1.3359955597619433e-05, "epoch": 13.775027502750275, "percentage": 68.88, "elapsed_time": "4:56:13", "remaining_time": "2:13:51", "throughput": 1486.82, "total_tokens": 26426016} {"current_steps": 125220, "total_steps": 181800, "loss": 0.0161, "lr": 1.335783160490213e-05, "epoch": 13.775577557755776, "percentage": 68.88, "elapsed_time": "4:56:14", "remaining_time": "2:13:51", "throughput": 1486.81, "total_tokens": 26427008} {"current_steps": 125225, "total_steps": 181800, "loss": 0.0045, "lr": 1.3355707719485117e-05, "epoch": 13.776127612761275, "percentage": 68.88, "elapsed_time": "4:56:14", "remaining_time": "2:13:50", "throughput": 1486.82, "total_tokens": 26428064} {"current_steps": 125230, "total_steps": 181800, "loss": 0.0143, "lr": 1.3353583941387954e-05, "epoch": 13.776677667766776, "percentage": 68.88, "elapsed_time": "4:56:15", "remaining_time": "2:13:49", "throughput": 1486.81, "total_tokens": 26429056} {"current_steps": 125235, "total_steps": 181800, "loss": 0.0038, "lr": 1.3351460270630211e-05, "epoch": 13.777227722772277, "percentage": 68.89, "elapsed_time": "4:56:16", "remaining_time": "2:13:49", "throughput": 1486.82, "total_tokens": 26430176} {"current_steps": 125240, "total_steps": 181800, "loss": 0.0282, "lr": 1.3349336707231475e-05, "epoch": 13.777777777777779, "percentage": 68.89, "elapsed_time": "4:56:17", "remaining_time": "2:13:48", "throughput": 1486.82, "total_tokens": 26431200} {"current_steps": 125245, "total_steps": 181800, "loss": 0.0033, "lr": 1.3347213251211304e-05, "epoch": 13.778327832783278, "percentage": 68.89, "elapsed_time": "4:56:17", "remaining_time": "2:13:47", "throughput": 1486.82, "total_tokens": 26432256} {"current_steps": 125250, "total_steps": 181800, "loss": 0.0169, "lr": 1.3345089902589291e-05, "epoch": 13.778877887788779, "percentage": 68.89, "elapsed_time": "4:56:18", "remaining_time": "2:13:46", "throughput": 1486.82, "total_tokens": 26433216} {"current_steps": 125255, "total_steps": 181800, "loss": 0.0017, "lr": 1.3342966661384992e-05, "epoch": 13.77942794279428, "percentage": 68.9, "elapsed_time": "4:56:19", "remaining_time": "2:13:46", "throughput": 1486.82, "total_tokens": 26434304} {"current_steps": 125260, "total_steps": 181800, "loss": 0.0035, "lr": 1.3340843527617963e-05, "epoch": 13.77997799779978, "percentage": 68.9, "elapsed_time": "4:56:19", "remaining_time": "2:13:45", "throughput": 1486.82, "total_tokens": 26435328} {"current_steps": 125265, "total_steps": 181800, "loss": 0.0404, "lr": 1.33387205013078e-05, "epoch": 13.78052805280528, "percentage": 68.9, "elapsed_time": "4:56:20", "remaining_time": "2:13:44", "throughput": 1486.83, "total_tokens": 26436448} {"current_steps": 125270, "total_steps": 181800, "loss": 0.0076, "lr": 1.333659758247404e-05, "epoch": 13.781078107810782, "percentage": 68.91, "elapsed_time": "4:56:21", "remaining_time": "2:13:44", "throughput": 1486.83, "total_tokens": 26437504} {"current_steps": 125275, "total_steps": 181800, "loss": 0.151, "lr": 1.3334474771136262e-05, "epoch": 13.781628162816281, "percentage": 68.91, "elapsed_time": "4:56:21", "remaining_time": "2:13:43", "throughput": 1486.83, "total_tokens": 26438560} {"current_steps": 125280, "total_steps": 181800, "loss": 0.0594, "lr": 1.3332352067314047e-05, "epoch": 13.782178217821782, "percentage": 68.91, "elapsed_time": "4:56:22", "remaining_time": "2:13:42", "throughput": 1486.83, "total_tokens": 26439520} {"current_steps": 125285, "total_steps": 181800, "loss": 0.0311, "lr": 1.3330229471026934e-05, "epoch": 13.782728272827283, "percentage": 68.91, "elapsed_time": "4:56:23", "remaining_time": "2:13:41", "throughput": 1486.83, "total_tokens": 26440544} {"current_steps": 125290, "total_steps": 181800, "loss": 0.1349, "lr": 1.3328106982294502e-05, "epoch": 13.783278327832782, "percentage": 68.92, "elapsed_time": "4:56:23", "remaining_time": "2:13:41", "throughput": 1486.83, "total_tokens": 26441632} {"current_steps": 125295, "total_steps": 181800, "loss": 0.0019, "lr": 1.332598460113631e-05, "epoch": 13.783828382838283, "percentage": 68.92, "elapsed_time": "4:56:24", "remaining_time": "2:13:40", "throughput": 1486.83, "total_tokens": 26442624} {"current_steps": 125300, "total_steps": 181800, "loss": 0.0034, "lr": 1.3323862327571895e-05, "epoch": 13.784378437843785, "percentage": 68.92, "elapsed_time": "4:56:25", "remaining_time": "2:13:39", "throughput": 1486.83, "total_tokens": 26443712} {"current_steps": 125305, "total_steps": 181800, "loss": 0.0113, "lr": 1.332174016162086e-05, "epoch": 13.784928492849286, "percentage": 68.92, "elapsed_time": "4:56:25", "remaining_time": "2:13:38", "throughput": 1486.83, "total_tokens": 26444768} {"current_steps": 125310, "total_steps": 181800, "loss": 0.0716, "lr": 1.3319618103302733e-05, "epoch": 13.785478547854785, "percentage": 68.93, "elapsed_time": "4:56:26", "remaining_time": "2:13:38", "throughput": 1486.83, "total_tokens": 26445792} {"current_steps": 125315, "total_steps": 181800, "loss": 0.001, "lr": 1.3317496152637089e-05, "epoch": 13.786028602860286, "percentage": 68.93, "elapsed_time": "4:56:27", "remaining_time": "2:13:37", "throughput": 1486.83, "total_tokens": 26446848} {"current_steps": 125320, "total_steps": 181800, "loss": 0.009, "lr": 1.3315374309643475e-05, "epoch": 13.786578657865787, "percentage": 68.93, "elapsed_time": "4:56:28", "remaining_time": "2:13:36", "throughput": 1486.83, "total_tokens": 26447872} {"current_steps": 125325, "total_steps": 181800, "loss": 0.0032, "lr": 1.3313252574341444e-05, "epoch": 13.787128712871286, "percentage": 68.94, "elapsed_time": "4:56:28", "remaining_time": "2:13:36", "throughput": 1486.84, "total_tokens": 26448960} {"current_steps": 125330, "total_steps": 181800, "loss": 0.0656, "lr": 1.3311130946750556e-05, "epoch": 13.787678767876788, "percentage": 68.94, "elapsed_time": "4:56:29", "remaining_time": "2:13:35", "throughput": 1486.84, "total_tokens": 26450016} {"current_steps": 125335, "total_steps": 181800, "loss": 0.026, "lr": 1.3309009426890362e-05, "epoch": 13.788228822882289, "percentage": 68.94, "elapsed_time": "4:56:30", "remaining_time": "2:13:34", "throughput": 1486.84, "total_tokens": 26451040} {"current_steps": 125340, "total_steps": 181800, "loss": 0.0257, "lr": 1.3306888014780427e-05, "epoch": 13.788778877887788, "percentage": 68.94, "elapsed_time": "4:56:30", "remaining_time": "2:13:33", "throughput": 1486.84, "total_tokens": 26452032} {"current_steps": 125345, "total_steps": 181800, "loss": 0.0384, "lr": 1.3304766710440298e-05, "epoch": 13.789328932893289, "percentage": 68.95, "elapsed_time": "4:56:31", "remaining_time": "2:13:33", "throughput": 1486.84, "total_tokens": 26453056} {"current_steps": 125350, "total_steps": 181800, "loss": 0.0078, "lr": 1.330264551388951e-05, "epoch": 13.78987898789879, "percentage": 68.95, "elapsed_time": "4:56:32", "remaining_time": "2:13:32", "throughput": 1486.84, "total_tokens": 26454112} {"current_steps": 125355, "total_steps": 181800, "loss": 0.0015, "lr": 1.3300524425147637e-05, "epoch": 13.79042904290429, "percentage": 68.95, "elapsed_time": "4:56:32", "remaining_time": "2:13:31", "throughput": 1486.84, "total_tokens": 26455168} {"current_steps": 125360, "total_steps": 181800, "loss": 0.0082, "lr": 1.3298403444234194e-05, "epoch": 13.79097909790979, "percentage": 68.95, "elapsed_time": "4:56:33", "remaining_time": "2:13:31", "throughput": 1486.84, "total_tokens": 26456192} {"current_steps": 125365, "total_steps": 181800, "loss": 0.0143, "lr": 1.3296282571168773e-05, "epoch": 13.791529152915292, "percentage": 68.96, "elapsed_time": "4:56:34", "remaining_time": "2:13:30", "throughput": 1486.84, "total_tokens": 26457280} {"current_steps": 125370, "total_steps": 181800, "loss": 0.0368, "lr": 1.3294161805970901e-05, "epoch": 13.792079207920793, "percentage": 68.96, "elapsed_time": "4:56:34", "remaining_time": "2:13:29", "throughput": 1486.84, "total_tokens": 26458272} {"current_steps": 125375, "total_steps": 181800, "loss": 0.0661, "lr": 1.3292041148660111e-05, "epoch": 13.792629262926292, "percentage": 68.96, "elapsed_time": "4:56:35", "remaining_time": "2:13:28", "throughput": 1486.85, "total_tokens": 26459424} {"current_steps": 125380, "total_steps": 181800, "loss": 0.0309, "lr": 1.328992059925597e-05, "epoch": 13.793179317931793, "percentage": 68.97, "elapsed_time": "4:56:36", "remaining_time": "2:13:28", "throughput": 1486.85, "total_tokens": 26460512} {"current_steps": 125385, "total_steps": 181800, "loss": 0.001, "lr": 1.3287800157778003e-05, "epoch": 13.793729372937294, "percentage": 68.97, "elapsed_time": "4:56:36", "remaining_time": "2:13:27", "throughput": 1486.86, "total_tokens": 26461600} {"current_steps": 125390, "total_steps": 181800, "loss": 0.0097, "lr": 1.3285679824245762e-05, "epoch": 13.794279427942794, "percentage": 68.97, "elapsed_time": "4:56:37", "remaining_time": "2:13:26", "throughput": 1486.86, "total_tokens": 26462688} {"current_steps": 125395, "total_steps": 181800, "loss": 0.0048, "lr": 1.3283559598678796e-05, "epoch": 13.794829482948295, "percentage": 68.97, "elapsed_time": "4:56:38", "remaining_time": "2:13:26", "throughput": 1486.86, "total_tokens": 26463744} {"current_steps": 125400, "total_steps": 181800, "loss": 0.0075, "lr": 1.328143948109663e-05, "epoch": 13.795379537953796, "percentage": 68.98, "elapsed_time": "4:56:39", "remaining_time": "2:13:25", "throughput": 1486.87, "total_tokens": 26464832} {"current_steps": 125405, "total_steps": 181800, "loss": 0.0131, "lr": 1.3279319471518826e-05, "epoch": 13.795929592959295, "percentage": 68.98, "elapsed_time": "4:56:39", "remaining_time": "2:13:24", "throughput": 1486.87, "total_tokens": 26465888} {"current_steps": 125410, "total_steps": 181800, "loss": 0.0041, "lr": 1.3277199569964895e-05, "epoch": 13.796479647964796, "percentage": 68.98, "elapsed_time": "4:56:40", "remaining_time": "2:13:23", "throughput": 1486.87, "total_tokens": 26467008} {"current_steps": 125415, "total_steps": 181800, "loss": 0.068, "lr": 1.3275079776454405e-05, "epoch": 13.797029702970297, "percentage": 68.99, "elapsed_time": "4:56:41", "remaining_time": "2:13:23", "throughput": 1486.88, "total_tokens": 26468096} {"current_steps": 125420, "total_steps": 181800, "loss": 0.0168, "lr": 1.3272960091006867e-05, "epoch": 13.797579757975798, "percentage": 68.99, "elapsed_time": "4:56:41", "remaining_time": "2:13:22", "throughput": 1486.88, "total_tokens": 26469120} {"current_steps": 125425, "total_steps": 181800, "loss": 0.0251, "lr": 1.327084051364183e-05, "epoch": 13.798129812981298, "percentage": 68.99, "elapsed_time": "4:56:42", "remaining_time": "2:13:21", "throughput": 1486.88, "total_tokens": 26470144} {"current_steps": 125430, "total_steps": 181800, "loss": 0.0037, "lr": 1.3268721044378834e-05, "epoch": 13.798679867986799, "percentage": 68.99, "elapsed_time": "4:56:43", "remaining_time": "2:13:21", "throughput": 1486.88, "total_tokens": 26471232} {"current_steps": 125435, "total_steps": 181800, "loss": 0.0575, "lr": 1.3266601683237401e-05, "epoch": 13.7992299229923, "percentage": 69.0, "elapsed_time": "4:56:43", "remaining_time": "2:13:20", "throughput": 1486.88, "total_tokens": 26472320} {"current_steps": 125440, "total_steps": 181800, "loss": 0.1637, "lr": 1.326448243023708e-05, "epoch": 13.7997799779978, "percentage": 69.0, "elapsed_time": "4:56:44", "remaining_time": "2:13:19", "throughput": 1486.88, "total_tokens": 26473344} {"current_steps": 125445, "total_steps": 181800, "loss": 0.0029, "lr": 1.3262363285397381e-05, "epoch": 13.8003300330033, "percentage": 69.0, "elapsed_time": "4:56:45", "remaining_time": "2:13:18", "throughput": 1486.89, "total_tokens": 26474432} {"current_steps": 125450, "total_steps": 181800, "loss": 0.0032, "lr": 1.3260244248737846e-05, "epoch": 13.800880088008801, "percentage": 69.0, "elapsed_time": "4:56:45", "remaining_time": "2:13:18", "throughput": 1486.89, "total_tokens": 26475488} {"current_steps": 125455, "total_steps": 181800, "loss": 0.1331, "lr": 1.325812532027802e-05, "epoch": 13.8014301430143, "percentage": 69.01, "elapsed_time": "4:56:46", "remaining_time": "2:13:17", "throughput": 1486.89, "total_tokens": 26476544} {"current_steps": 125460, "total_steps": 181800, "loss": 0.0829, "lr": 1.3256006500037408e-05, "epoch": 13.801980198019802, "percentage": 69.01, "elapsed_time": "4:56:47", "remaining_time": "2:13:16", "throughput": 1486.89, "total_tokens": 26477600} {"current_steps": 125465, "total_steps": 181800, "loss": 0.0894, "lr": 1.3253887788035557e-05, "epoch": 13.802530253025303, "percentage": 69.01, "elapsed_time": "4:56:48", "remaining_time": "2:13:15", "throughput": 1486.89, "total_tokens": 26478624} {"current_steps": 125470, "total_steps": 181800, "loss": 0.0465, "lr": 1.3251769184291987e-05, "epoch": 13.803080308030804, "percentage": 69.02, "elapsed_time": "4:56:48", "remaining_time": "2:13:15", "throughput": 1486.89, "total_tokens": 26479584} {"current_steps": 125475, "total_steps": 181800, "loss": 0.0031, "lr": 1.3249650688826205e-05, "epoch": 13.803630363036303, "percentage": 69.02, "elapsed_time": "4:56:49", "remaining_time": "2:13:14", "throughput": 1486.89, "total_tokens": 26480608} {"current_steps": 125480, "total_steps": 181800, "loss": 0.0033, "lr": 1.3247532301657773e-05, "epoch": 13.804180418041804, "percentage": 69.02, "elapsed_time": "4:56:50", "remaining_time": "2:13:13", "throughput": 1486.9, "total_tokens": 26481728} {"current_steps": 125485, "total_steps": 181800, "loss": 0.17, "lr": 1.3245414022806193e-05, "epoch": 13.804730473047305, "percentage": 69.02, "elapsed_time": "4:56:50", "remaining_time": "2:13:13", "throughput": 1486.9, "total_tokens": 26482816} {"current_steps": 125490, "total_steps": 181800, "loss": 0.1243, "lr": 1.3243295852290984e-05, "epoch": 13.805280528052805, "percentage": 69.03, "elapsed_time": "4:56:51", "remaining_time": "2:13:12", "throughput": 1486.9, "total_tokens": 26483840} {"current_steps": 125495, "total_steps": 181800, "loss": 0.0072, "lr": 1.3241177790131686e-05, "epoch": 13.805830583058306, "percentage": 69.03, "elapsed_time": "4:56:52", "remaining_time": "2:13:11", "throughput": 1486.9, "total_tokens": 26484864} {"current_steps": 125500, "total_steps": 181800, "loss": 0.067, "lr": 1.32390598363478e-05, "epoch": 13.806380638063807, "percentage": 69.03, "elapsed_time": "4:56:52", "remaining_time": "2:13:10", "throughput": 1486.9, "total_tokens": 26485920} {"current_steps": 125505, "total_steps": 181800, "loss": 0.0334, "lr": 1.3236941990958857e-05, "epoch": 13.806930693069306, "percentage": 69.03, "elapsed_time": "4:56:53", "remaining_time": "2:13:10", "throughput": 1486.91, "total_tokens": 26487040} {"current_steps": 125510, "total_steps": 181800, "loss": 0.0026, "lr": 1.3234824253984384e-05, "epoch": 13.807480748074807, "percentage": 69.04, "elapsed_time": "4:56:54", "remaining_time": "2:13:09", "throughput": 1486.91, "total_tokens": 26488128} {"current_steps": 125515, "total_steps": 181800, "loss": 0.0588, "lr": 1.3232706625443881e-05, "epoch": 13.808030803080309, "percentage": 69.04, "elapsed_time": "4:56:54", "remaining_time": "2:13:08", "throughput": 1486.91, "total_tokens": 26489152} {"current_steps": 125520, "total_steps": 181800, "loss": 0.0041, "lr": 1.3230589105356884e-05, "epoch": 13.808580858085808, "percentage": 69.04, "elapsed_time": "4:56:55", "remaining_time": "2:13:08", "throughput": 1486.91, "total_tokens": 26490240} {"current_steps": 125525, "total_steps": 181800, "loss": 0.0037, "lr": 1.3228471693742889e-05, "epoch": 13.809130913091309, "percentage": 69.05, "elapsed_time": "4:56:56", "remaining_time": "2:13:07", "throughput": 1486.92, "total_tokens": 26491360} {"current_steps": 125530, "total_steps": 181800, "loss": 0.0027, "lr": 1.3226354390621431e-05, "epoch": 13.80968096809681, "percentage": 69.05, "elapsed_time": "4:56:56", "remaining_time": "2:13:06", "throughput": 1486.92, "total_tokens": 26492384} {"current_steps": 125535, "total_steps": 181800, "loss": 0.1223, "lr": 1.3224237196012007e-05, "epoch": 13.810231023102311, "percentage": 69.05, "elapsed_time": "4:56:57", "remaining_time": "2:13:05", "throughput": 1486.92, "total_tokens": 26493376} {"current_steps": 125540, "total_steps": 181800, "loss": 0.0499, "lr": 1.322212010993414e-05, "epoch": 13.81078107810781, "percentage": 69.05, "elapsed_time": "4:56:58", "remaining_time": "2:13:05", "throughput": 1486.92, "total_tokens": 26494400} {"current_steps": 125545, "total_steps": 181800, "loss": 0.0429, "lr": 1.3220003132407347e-05, "epoch": 13.811331133113312, "percentage": 69.06, "elapsed_time": "4:56:59", "remaining_time": "2:13:04", "throughput": 1486.92, "total_tokens": 26495424} {"current_steps": 125550, "total_steps": 181800, "loss": 0.0283, "lr": 1.3217886263451124e-05, "epoch": 13.811881188118813, "percentage": 69.06, "elapsed_time": "4:56:59", "remaining_time": "2:13:03", "throughput": 1486.92, "total_tokens": 26496512} {"current_steps": 125555, "total_steps": 181800, "loss": 0.0069, "lr": 1.3215769503084995e-05, "epoch": 13.812431243124312, "percentage": 69.06, "elapsed_time": "4:57:00", "remaining_time": "2:13:03", "throughput": 1486.92, "total_tokens": 26497536} {"current_steps": 125560, "total_steps": 181800, "loss": 0.01, "lr": 1.3213652851328462e-05, "epoch": 13.812981298129813, "percentage": 69.06, "elapsed_time": "4:57:01", "remaining_time": "2:13:02", "throughput": 1486.92, "total_tokens": 26498560} {"current_steps": 125565, "total_steps": 181800, "loss": 0.0121, "lr": 1.3211536308201031e-05, "epoch": 13.813531353135314, "percentage": 69.07, "elapsed_time": "4:57:01", "remaining_time": "2:13:01", "throughput": 1486.92, "total_tokens": 26499584} {"current_steps": 125570, "total_steps": 181800, "loss": 0.0622, "lr": 1.3209419873722223e-05, "epoch": 13.814081408140813, "percentage": 69.07, "elapsed_time": "4:57:02", "remaining_time": "2:13:00", "throughput": 1486.92, "total_tokens": 26500640} {"current_steps": 125575, "total_steps": 181800, "loss": 0.0374, "lr": 1.3207303547911525e-05, "epoch": 13.814631463146315, "percentage": 69.07, "elapsed_time": "4:57:03", "remaining_time": "2:13:00", "throughput": 1486.92, "total_tokens": 26501696} {"current_steps": 125580, "total_steps": 181800, "loss": 0.0822, "lr": 1.320518733078846e-05, "epoch": 13.815181518151816, "percentage": 69.08, "elapsed_time": "4:57:03", "remaining_time": "2:12:59", "throughput": 1486.92, "total_tokens": 26502720} {"current_steps": 125585, "total_steps": 181800, "loss": 0.0318, "lr": 1.3203071222372527e-05, "epoch": 13.815731573157315, "percentage": 69.08, "elapsed_time": "4:57:04", "remaining_time": "2:12:58", "throughput": 1486.92, "total_tokens": 26503744} {"current_steps": 125590, "total_steps": 181800, "loss": 0.1033, "lr": 1.3200955222683215e-05, "epoch": 13.816281628162816, "percentage": 69.08, "elapsed_time": "4:57:05", "remaining_time": "2:12:58", "throughput": 1486.92, "total_tokens": 26504800} {"current_steps": 125595, "total_steps": 181800, "loss": 0.0051, "lr": 1.3198839331740035e-05, "epoch": 13.816831683168317, "percentage": 69.08, "elapsed_time": "4:57:05", "remaining_time": "2:12:57", "throughput": 1486.92, "total_tokens": 26505792} {"current_steps": 125600, "total_steps": 181800, "loss": 0.106, "lr": 1.3196723549562489e-05, "epoch": 13.817381738173818, "percentage": 69.09, "elapsed_time": "4:57:06", "remaining_time": "2:12:56", "throughput": 1486.92, "total_tokens": 26506784} {"current_steps": 125605, "total_steps": 181800, "loss": 0.0033, "lr": 1.319460787617009e-05, "epoch": 13.817931793179318, "percentage": 69.09, "elapsed_time": "4:57:07", "remaining_time": "2:12:55", "throughput": 1486.92, "total_tokens": 26507808} {"current_steps": 125610, "total_steps": 181800, "loss": 0.0067, "lr": 1.3192492311582328e-05, "epoch": 13.818481848184819, "percentage": 69.09, "elapsed_time": "4:57:08", "remaining_time": "2:12:55", "throughput": 1486.92, "total_tokens": 26508864} {"current_steps": 125615, "total_steps": 181800, "loss": 0.0989, "lr": 1.3190376855818684e-05, "epoch": 13.81903190319032, "percentage": 69.1, "elapsed_time": "4:57:08", "remaining_time": "2:12:54", "throughput": 1486.92, "total_tokens": 26509952} {"current_steps": 125620, "total_steps": 181800, "loss": 0.002, "lr": 1.3188261508898672e-05, "epoch": 13.819581958195819, "percentage": 69.1, "elapsed_time": "4:57:09", "remaining_time": "2:12:53", "throughput": 1486.93, "total_tokens": 26511008} {"current_steps": 125625, "total_steps": 181800, "loss": 0.0161, "lr": 1.3186146270841787e-05, "epoch": 13.82013201320132, "percentage": 69.1, "elapsed_time": "4:57:10", "remaining_time": "2:12:52", "throughput": 1486.93, "total_tokens": 26512064} {"current_steps": 125630, "total_steps": 181800, "loss": 0.0472, "lr": 1.318403114166753e-05, "epoch": 13.820682068206821, "percentage": 69.1, "elapsed_time": "4:57:10", "remaining_time": "2:12:52", "throughput": 1486.93, "total_tokens": 26513152} {"current_steps": 125635, "total_steps": 181800, "loss": 0.0068, "lr": 1.318191612139539e-05, "epoch": 13.82123212321232, "percentage": 69.11, "elapsed_time": "4:57:11", "remaining_time": "2:12:51", "throughput": 1486.93, "total_tokens": 26514144} {"current_steps": 125640, "total_steps": 181800, "loss": 0.0354, "lr": 1.3179801210044852e-05, "epoch": 13.821782178217822, "percentage": 69.11, "elapsed_time": "4:57:12", "remaining_time": "2:12:50", "throughput": 1486.93, "total_tokens": 26515200} {"current_steps": 125645, "total_steps": 181800, "loss": 0.0046, "lr": 1.3177686407635417e-05, "epoch": 13.822332233223323, "percentage": 69.11, "elapsed_time": "4:57:12", "remaining_time": "2:12:50", "throughput": 1486.93, "total_tokens": 26516224} {"current_steps": 125650, "total_steps": 181800, "loss": 0.1039, "lr": 1.3175571714186569e-05, "epoch": 13.822882288228822, "percentage": 69.11, "elapsed_time": "4:57:13", "remaining_time": "2:12:49", "throughput": 1486.94, "total_tokens": 26517312} {"current_steps": 125655, "total_steps": 181800, "loss": 0.0469, "lr": 1.3173457129717798e-05, "epoch": 13.823432343234323, "percentage": 69.12, "elapsed_time": "4:57:14", "remaining_time": "2:12:48", "throughput": 1486.94, "total_tokens": 26518368} {"current_steps": 125660, "total_steps": 181800, "loss": 0.0311, "lr": 1.3171342654248611e-05, "epoch": 13.823982398239824, "percentage": 69.12, "elapsed_time": "4:57:14", "remaining_time": "2:12:47", "throughput": 1486.94, "total_tokens": 26519424} {"current_steps": 125665, "total_steps": 181800, "loss": 0.052, "lr": 1.3169228287798474e-05, "epoch": 13.824532453245325, "percentage": 69.12, "elapsed_time": "4:57:15", "remaining_time": "2:12:47", "throughput": 1486.94, "total_tokens": 26520512} {"current_steps": 125670, "total_steps": 181800, "loss": 0.0301, "lr": 1.316711403038689e-05, "epoch": 13.825082508250825, "percentage": 69.13, "elapsed_time": "4:57:16", "remaining_time": "2:12:46", "throughput": 1486.94, "total_tokens": 26521536} {"current_steps": 125675, "total_steps": 181800, "loss": 0.0191, "lr": 1.316499988203333e-05, "epoch": 13.825632563256326, "percentage": 69.13, "elapsed_time": "4:57:16", "remaining_time": "2:12:45", "throughput": 1486.94, "total_tokens": 26522592} {"current_steps": 125680, "total_steps": 181800, "loss": 0.0045, "lr": 1.3162885842757284e-05, "epoch": 13.826182618261827, "percentage": 69.13, "elapsed_time": "4:57:17", "remaining_time": "2:12:45", "throughput": 1486.95, "total_tokens": 26523712} {"current_steps": 125685, "total_steps": 181800, "loss": 0.0013, "lr": 1.316077191257825e-05, "epoch": 13.826732673267326, "percentage": 69.13, "elapsed_time": "4:57:18", "remaining_time": "2:12:44", "throughput": 1486.95, "total_tokens": 26524736} {"current_steps": 125690, "total_steps": 181800, "loss": 0.0056, "lr": 1.3158658091515694e-05, "epoch": 13.827282728272827, "percentage": 69.14, "elapsed_time": "4:57:19", "remaining_time": "2:12:43", "throughput": 1486.95, "total_tokens": 26525760} {"current_steps": 125695, "total_steps": 181800, "loss": 0.0766, "lr": 1.3156544379589112e-05, "epoch": 13.827832783278328, "percentage": 69.14, "elapsed_time": "4:57:19", "remaining_time": "2:12:42", "throughput": 1486.95, "total_tokens": 26526784} {"current_steps": 125700, "total_steps": 181800, "loss": 0.0394, "lr": 1.3154430776817978e-05, "epoch": 13.828382838283828, "percentage": 69.14, "elapsed_time": "4:57:20", "remaining_time": "2:12:42", "throughput": 1486.95, "total_tokens": 26527872} {"current_steps": 125705, "total_steps": 181800, "loss": 0.04, "lr": 1.315231728322176e-05, "epoch": 13.828932893289329, "percentage": 69.14, "elapsed_time": "4:57:21", "remaining_time": "2:12:41", "throughput": 1486.95, "total_tokens": 26528928} {"current_steps": 125710, "total_steps": 181800, "loss": 0.0576, "lr": 1.3150203898819948e-05, "epoch": 13.82948294829483, "percentage": 69.15, "elapsed_time": "4:57:21", "remaining_time": "2:12:40", "throughput": 1486.96, "total_tokens": 26530016} {"current_steps": 125715, "total_steps": 181800, "loss": 0.015, "lr": 1.3148090623632022e-05, "epoch": 13.83003300330033, "percentage": 69.15, "elapsed_time": "4:57:22", "remaining_time": "2:12:40", "throughput": 1486.96, "total_tokens": 26531072} {"current_steps": 125720, "total_steps": 181800, "loss": 0.0015, "lr": 1.3145977457677466e-05, "epoch": 13.83058305830583, "percentage": 69.15, "elapsed_time": "4:57:23", "remaining_time": "2:12:39", "throughput": 1486.96, "total_tokens": 26532128} {"current_steps": 125725, "total_steps": 181800, "loss": 0.0061, "lr": 1.3143864400975752e-05, "epoch": 13.831133113311331, "percentage": 69.16, "elapsed_time": "4:57:23", "remaining_time": "2:12:38", "throughput": 1486.96, "total_tokens": 26533120} {"current_steps": 125730, "total_steps": 181800, "loss": 0.0017, "lr": 1.3141751453546335e-05, "epoch": 13.831683168316832, "percentage": 69.16, "elapsed_time": "4:57:24", "remaining_time": "2:12:37", "throughput": 1486.96, "total_tokens": 26534144} {"current_steps": 125735, "total_steps": 181800, "loss": 0.0028, "lr": 1.313963861540871e-05, "epoch": 13.832233223322332, "percentage": 69.16, "elapsed_time": "4:57:25", "remaining_time": "2:12:37", "throughput": 1486.96, "total_tokens": 26535104} {"current_steps": 125740, "total_steps": 181800, "loss": 0.0816, "lr": 1.3137525886582341e-05, "epoch": 13.832783278327833, "percentage": 69.16, "elapsed_time": "4:57:25", "remaining_time": "2:12:36", "throughput": 1486.96, "total_tokens": 26536224} {"current_steps": 125745, "total_steps": 181800, "loss": 0.0953, "lr": 1.3135413267086715e-05, "epoch": 13.833333333333334, "percentage": 69.17, "elapsed_time": "4:57:26", "remaining_time": "2:12:35", "throughput": 1486.96, "total_tokens": 26537280} {"current_steps": 125750, "total_steps": 181800, "loss": 0.0194, "lr": 1.3133300756941292e-05, "epoch": 13.833883388338833, "percentage": 69.17, "elapsed_time": "4:57:27", "remaining_time": "2:12:35", "throughput": 1486.97, "total_tokens": 26538336} {"current_steps": 125755, "total_steps": 181800, "loss": 0.0215, "lr": 1.3131188356165533e-05, "epoch": 13.834433443344334, "percentage": 69.17, "elapsed_time": "4:57:28", "remaining_time": "2:12:34", "throughput": 1486.97, "total_tokens": 26539456} {"current_steps": 125760, "total_steps": 181800, "loss": 0.0058, "lr": 1.3129076064778922e-05, "epoch": 13.834983498349835, "percentage": 69.17, "elapsed_time": "4:57:28", "remaining_time": "2:12:33", "throughput": 1486.97, "total_tokens": 26540544} {"current_steps": 125765, "total_steps": 181800, "loss": 0.0864, "lr": 1.3126963882800913e-05, "epoch": 13.835533553355335, "percentage": 69.18, "elapsed_time": "4:57:29", "remaining_time": "2:12:32", "throughput": 1486.97, "total_tokens": 26541568} {"current_steps": 125770, "total_steps": 181800, "loss": 0.0613, "lr": 1.3124851810250982e-05, "epoch": 13.836083608360836, "percentage": 69.18, "elapsed_time": "4:57:30", "remaining_time": "2:12:32", "throughput": 1486.97, "total_tokens": 26542592} {"current_steps": 125775, "total_steps": 181800, "loss": 0.0405, "lr": 1.3122739847148602e-05, "epoch": 13.836633663366337, "percentage": 69.18, "elapsed_time": "4:57:30", "remaining_time": "2:12:31", "throughput": 1486.98, "total_tokens": 26543680} {"current_steps": 125780, "total_steps": 181800, "loss": 0.0195, "lr": 1.3120627993513218e-05, "epoch": 13.837183718371836, "percentage": 69.19, "elapsed_time": "4:57:31", "remaining_time": "2:12:30", "throughput": 1486.98, "total_tokens": 26544800} {"current_steps": 125785, "total_steps": 181800, "loss": 0.0462, "lr": 1.3118516249364321e-05, "epoch": 13.837733773377337, "percentage": 69.19, "elapsed_time": "4:57:32", "remaining_time": "2:12:29", "throughput": 1486.99, "total_tokens": 26545888} {"current_steps": 125790, "total_steps": 181800, "loss": 0.0035, "lr": 1.3116404614721345e-05, "epoch": 13.838283828382838, "percentage": 69.19, "elapsed_time": "4:57:32", "remaining_time": "2:12:29", "throughput": 1486.99, "total_tokens": 26546944} {"current_steps": 125795, "total_steps": 181800, "loss": 0.0045, "lr": 1.3114293089603763e-05, "epoch": 13.83883388338834, "percentage": 69.19, "elapsed_time": "4:57:33", "remaining_time": "2:12:28", "throughput": 1486.99, "total_tokens": 26547968} {"current_steps": 125800, "total_steps": 181800, "loss": 0.0023, "lr": 1.311218167403105e-05, "epoch": 13.839383938393839, "percentage": 69.2, "elapsed_time": "4:57:34", "remaining_time": "2:12:27", "throughput": 1486.99, "total_tokens": 26549024} {"current_steps": 125805, "total_steps": 181800, "loss": 0.0097, "lr": 1.3110070368022646e-05, "epoch": 13.83993399339934, "percentage": 69.2, "elapsed_time": "4:57:34", "remaining_time": "2:12:27", "throughput": 1486.99, "total_tokens": 26550016} {"current_steps": 125810, "total_steps": 181800, "loss": 0.0027, "lr": 1.3107959171598025e-05, "epoch": 13.840484048404841, "percentage": 69.2, "elapsed_time": "4:57:35", "remaining_time": "2:12:26", "throughput": 1486.99, "total_tokens": 26551072} {"current_steps": 125815, "total_steps": 181800, "loss": 0.0127, "lr": 1.3105848084776628e-05, "epoch": 13.84103410341034, "percentage": 69.21, "elapsed_time": "4:57:36", "remaining_time": "2:12:25", "throughput": 1486.99, "total_tokens": 26552064} {"current_steps": 125820, "total_steps": 181800, "loss": 0.0024, "lr": 1.3103737107577935e-05, "epoch": 13.841584158415841, "percentage": 69.21, "elapsed_time": "4:57:36", "remaining_time": "2:12:24", "throughput": 1486.99, "total_tokens": 26553088} {"current_steps": 125825, "total_steps": 181800, "loss": 0.0053, "lr": 1.3101626240021378e-05, "epoch": 13.842134213421343, "percentage": 69.21, "elapsed_time": "4:57:37", "remaining_time": "2:12:24", "throughput": 1486.99, "total_tokens": 26554144} {"current_steps": 125830, "total_steps": 181800, "loss": 0.0098, "lr": 1.3099515482126424e-05, "epoch": 13.842684268426842, "percentage": 69.21, "elapsed_time": "4:57:38", "remaining_time": "2:12:23", "throughput": 1486.99, "total_tokens": 26555232} {"current_steps": 125835, "total_steps": 181800, "loss": 0.0126, "lr": 1.3097404833912529e-05, "epoch": 13.843234323432343, "percentage": 69.22, "elapsed_time": "4:57:39", "remaining_time": "2:12:22", "throughput": 1487.0, "total_tokens": 26556320} {"current_steps": 125840, "total_steps": 181800, "loss": 0.0017, "lr": 1.3095294295399139e-05, "epoch": 13.843784378437844, "percentage": 69.22, "elapsed_time": "4:57:39", "remaining_time": "2:12:22", "throughput": 1487.0, "total_tokens": 26557376} {"current_steps": 125845, "total_steps": 181800, "loss": 0.0724, "lr": 1.3093183866605712e-05, "epoch": 13.844334433443345, "percentage": 69.22, "elapsed_time": "4:57:40", "remaining_time": "2:12:21", "throughput": 1487.0, "total_tokens": 26558496} {"current_steps": 125850, "total_steps": 181800, "loss": 0.0024, "lr": 1.3091073547551691e-05, "epoch": 13.844884488448844, "percentage": 69.22, "elapsed_time": "4:57:41", "remaining_time": "2:12:20", "throughput": 1487.01, "total_tokens": 26559584} {"current_steps": 125855, "total_steps": 181800, "loss": 0.0044, "lr": 1.3088963338256533e-05, "epoch": 13.845434543454346, "percentage": 69.23, "elapsed_time": "4:57:41", "remaining_time": "2:12:19", "throughput": 1487.01, "total_tokens": 26560640} {"current_steps": 125860, "total_steps": 181800, "loss": 0.0754, "lr": 1.3086853238739688e-05, "epoch": 13.845984598459847, "percentage": 69.23, "elapsed_time": "4:57:42", "remaining_time": "2:12:19", "throughput": 1487.01, "total_tokens": 26561760} {"current_steps": 125865, "total_steps": 181800, "loss": 0.024, "lr": 1.3084743249020595e-05, "epoch": 13.846534653465346, "percentage": 69.23, "elapsed_time": "4:57:43", "remaining_time": "2:12:18", "throughput": 1487.01, "total_tokens": 26562784} {"current_steps": 125870, "total_steps": 181800, "loss": 0.0406, "lr": 1.3082633369118713e-05, "epoch": 13.847084708470847, "percentage": 69.24, "elapsed_time": "4:57:43", "remaining_time": "2:12:17", "throughput": 1487.01, "total_tokens": 26563808} {"current_steps": 125875, "total_steps": 181800, "loss": 0.0044, "lr": 1.3080523599053485e-05, "epoch": 13.847634763476348, "percentage": 69.24, "elapsed_time": "4:57:44", "remaining_time": "2:12:17", "throughput": 1487.02, "total_tokens": 26564928} {"current_steps": 125880, "total_steps": 181800, "loss": 0.0027, "lr": 1.3078413938844336e-05, "epoch": 13.848184818481847, "percentage": 69.24, "elapsed_time": "4:57:45", "remaining_time": "2:12:16", "throughput": 1487.02, "total_tokens": 26565952} {"current_steps": 125885, "total_steps": 181800, "loss": 0.0408, "lr": 1.307630438851073e-05, "epoch": 13.848734873487349, "percentage": 69.24, "elapsed_time": "4:57:45", "remaining_time": "2:12:15", "throughput": 1487.01, "total_tokens": 26566944} {"current_steps": 125890, "total_steps": 181800, "loss": 0.0926, "lr": 1.307419494807211e-05, "epoch": 13.84928492849285, "percentage": 69.25, "elapsed_time": "4:57:46", "remaining_time": "2:12:14", "throughput": 1487.01, "total_tokens": 26567968} {"current_steps": 125895, "total_steps": 181800, "loss": 0.1321, "lr": 1.3072085617547907e-05, "epoch": 13.84983498349835, "percentage": 69.25, "elapsed_time": "4:57:47", "remaining_time": "2:12:14", "throughput": 1487.01, "total_tokens": 26568992} {"current_steps": 125900, "total_steps": 181800, "loss": 0.0052, "lr": 1.3069976396957576e-05, "epoch": 13.85038503850385, "percentage": 69.25, "elapsed_time": "4:57:48", "remaining_time": "2:12:13", "throughput": 1487.02, "total_tokens": 26570048} {"current_steps": 125905, "total_steps": 181800, "loss": 0.0035, "lr": 1.3067867286320537e-05, "epoch": 13.850935093509351, "percentage": 69.25, "elapsed_time": "4:57:48", "remaining_time": "2:12:12", "throughput": 1487.02, "total_tokens": 26571136} {"current_steps": 125910, "total_steps": 181800, "loss": 0.0855, "lr": 1.306575828565624e-05, "epoch": 13.851485148514852, "percentage": 69.26, "elapsed_time": "4:57:49", "remaining_time": "2:12:12", "throughput": 1487.02, "total_tokens": 26572192} {"current_steps": 125915, "total_steps": 181800, "loss": 0.1314, "lr": 1.3063649394984134e-05, "epoch": 13.852035203520352, "percentage": 69.26, "elapsed_time": "4:57:50", "remaining_time": "2:12:11", "throughput": 1487.02, "total_tokens": 26573184} {"current_steps": 125920, "total_steps": 181800, "loss": 0.0052, "lr": 1.3061540614323631e-05, "epoch": 13.852585258525853, "percentage": 69.26, "elapsed_time": "4:57:50", "remaining_time": "2:12:10", "throughput": 1487.03, "total_tokens": 26574304} {"current_steps": 125925, "total_steps": 181800, "loss": 0.0017, "lr": 1.3059431943694191e-05, "epoch": 13.853135313531354, "percentage": 69.27, "elapsed_time": "4:57:51", "remaining_time": "2:12:09", "throughput": 1487.03, "total_tokens": 26575392} {"current_steps": 125930, "total_steps": 181800, "loss": 0.122, "lr": 1.3057323383115227e-05, "epoch": 13.853685368536853, "percentage": 69.27, "elapsed_time": "4:57:52", "remaining_time": "2:12:09", "throughput": 1487.03, "total_tokens": 26576448} {"current_steps": 125935, "total_steps": 181800, "loss": 0.0192, "lr": 1.305521493260619e-05, "epoch": 13.854235423542354, "percentage": 69.27, "elapsed_time": "4:57:52", "remaining_time": "2:12:08", "throughput": 1487.03, "total_tokens": 26577440} {"current_steps": 125940, "total_steps": 181800, "loss": 0.1292, "lr": 1.30531065921865e-05, "epoch": 13.854785478547855, "percentage": 69.27, "elapsed_time": "4:57:53", "remaining_time": "2:12:07", "throughput": 1487.03, "total_tokens": 26578560} {"current_steps": 125945, "total_steps": 181800, "loss": 0.0099, "lr": 1.3050998361875594e-05, "epoch": 13.855335533553355, "percentage": 69.28, "elapsed_time": "4:57:54", "remaining_time": "2:12:06", "throughput": 1487.03, "total_tokens": 26579552} {"current_steps": 125950, "total_steps": 181800, "loss": 0.0359, "lr": 1.304889024169291e-05, "epoch": 13.855885588558856, "percentage": 69.28, "elapsed_time": "4:57:54", "remaining_time": "2:12:06", "throughput": 1487.03, "total_tokens": 26580608} {"current_steps": 125955, "total_steps": 181800, "loss": 0.0947, "lr": 1.304678223165786e-05, "epoch": 13.856435643564357, "percentage": 69.28, "elapsed_time": "4:57:55", "remaining_time": "2:12:05", "throughput": 1487.03, "total_tokens": 26581632} {"current_steps": 125960, "total_steps": 181800, "loss": 0.0046, "lr": 1.3044674331789891e-05, "epoch": 13.856985698569858, "percentage": 69.28, "elapsed_time": "4:57:56", "remaining_time": "2:12:04", "throughput": 1487.04, "total_tokens": 26582720} {"current_steps": 125965, "total_steps": 181800, "loss": 0.1147, "lr": 1.3042566542108415e-05, "epoch": 13.857535753575357, "percentage": 69.29, "elapsed_time": "4:57:56", "remaining_time": "2:12:04", "throughput": 1487.04, "total_tokens": 26583744} {"current_steps": 125970, "total_steps": 181800, "loss": 0.0026, "lr": 1.3040458862632865e-05, "epoch": 13.858085808580858, "percentage": 69.29, "elapsed_time": "4:57:57", "remaining_time": "2:12:03", "throughput": 1487.04, "total_tokens": 26584832} {"current_steps": 125975, "total_steps": 181800, "loss": 0.1467, "lr": 1.3038351293382675e-05, "epoch": 13.85863586358636, "percentage": 69.29, "elapsed_time": "4:57:58", "remaining_time": "2:12:02", "throughput": 1487.04, "total_tokens": 26585856} {"current_steps": 125980, "total_steps": 181800, "loss": 0.0023, "lr": 1.3036243834377253e-05, "epoch": 13.859185918591859, "percentage": 69.3, "elapsed_time": "4:57:59", "remaining_time": "2:12:01", "throughput": 1487.04, "total_tokens": 26586880} {"current_steps": 125985, "total_steps": 181800, "loss": 0.0154, "lr": 1.303413648563604e-05, "epoch": 13.85973597359736, "percentage": 69.3, "elapsed_time": "4:57:59", "remaining_time": "2:12:01", "throughput": 1487.04, "total_tokens": 26587904} {"current_steps": 125990, "total_steps": 181800, "loss": 0.0025, "lr": 1.3032029247178452e-05, "epoch": 13.86028602860286, "percentage": 69.3, "elapsed_time": "4:58:00", "remaining_time": "2:12:00", "throughput": 1487.04, "total_tokens": 26588928} {"current_steps": 125995, "total_steps": 181800, "loss": 0.0029, "lr": 1.3029922119023893e-05, "epoch": 13.86083608360836, "percentage": 69.3, "elapsed_time": "4:58:01", "remaining_time": "2:11:59", "throughput": 1487.04, "total_tokens": 26589984} {"current_steps": 126000, "total_steps": 181800, "loss": 0.0074, "lr": 1.3027815101191801e-05, "epoch": 13.861386138613861, "percentage": 69.31, "elapsed_time": "4:58:01", "remaining_time": "2:11:59", "throughput": 1487.04, "total_tokens": 26591040} {"current_steps": 126005, "total_steps": 181800, "loss": 0.1302, "lr": 1.3025708193701592e-05, "epoch": 13.861936193619362, "percentage": 69.31, "elapsed_time": "4:58:02", "remaining_time": "2:11:58", "throughput": 1487.05, "total_tokens": 26592128} {"current_steps": 126010, "total_steps": 181800, "loss": 0.0699, "lr": 1.3023601396572694e-05, "epoch": 13.862486248624862, "percentage": 69.31, "elapsed_time": "4:58:03", "remaining_time": "2:11:57", "throughput": 1487.05, "total_tokens": 26593184} {"current_steps": 126015, "total_steps": 181800, "loss": 0.0032, "lr": 1.3021494709824514e-05, "epoch": 13.863036303630363, "percentage": 69.32, "elapsed_time": "4:58:03", "remaining_time": "2:11:56", "throughput": 1487.05, "total_tokens": 26594208} {"current_steps": 126020, "total_steps": 181800, "loss": 0.0066, "lr": 1.3019388133476463e-05, "epoch": 13.863586358635864, "percentage": 69.32, "elapsed_time": "4:58:04", "remaining_time": "2:11:56", "throughput": 1487.05, "total_tokens": 26595232} {"current_steps": 126025, "total_steps": 181800, "loss": 0.0115, "lr": 1.301728166754796e-05, "epoch": 13.864136413641365, "percentage": 69.32, "elapsed_time": "4:58:05", "remaining_time": "2:11:55", "throughput": 1487.05, "total_tokens": 26596288} {"current_steps": 126030, "total_steps": 181800, "loss": 0.0178, "lr": 1.301517531205842e-05, "epoch": 13.864686468646864, "percentage": 69.32, "elapsed_time": "4:58:05", "remaining_time": "2:11:54", "throughput": 1487.05, "total_tokens": 26597376} {"current_steps": 126035, "total_steps": 181800, "loss": 0.0042, "lr": 1.3013069067027273e-05, "epoch": 13.865236523652365, "percentage": 69.33, "elapsed_time": "4:58:06", "remaining_time": "2:11:54", "throughput": 1487.06, "total_tokens": 26598432} {"current_steps": 126040, "total_steps": 181800, "loss": 0.0045, "lr": 1.3010962932473913e-05, "epoch": 13.865786578657866, "percentage": 69.33, "elapsed_time": "4:58:07", "remaining_time": "2:11:53", "throughput": 1487.06, "total_tokens": 26599488} {"current_steps": 126045, "total_steps": 181800, "loss": 0.004, "lr": 1.3008856908417747e-05, "epoch": 13.866336633663366, "percentage": 69.33, "elapsed_time": "4:58:08", "remaining_time": "2:11:52", "throughput": 1487.06, "total_tokens": 26600480} {"current_steps": 126050, "total_steps": 181800, "loss": 0.0378, "lr": 1.3006750994878203e-05, "epoch": 13.866886688668867, "percentage": 69.33, "elapsed_time": "4:58:08", "remaining_time": "2:11:51", "throughput": 1487.06, "total_tokens": 26601536} {"current_steps": 126055, "total_steps": 181800, "loss": 0.0036, "lr": 1.3004645191874668e-05, "epoch": 13.867436743674368, "percentage": 69.34, "elapsed_time": "4:58:09", "remaining_time": "2:11:51", "throughput": 1487.06, "total_tokens": 26602592} {"current_steps": 126060, "total_steps": 181800, "loss": 0.055, "lr": 1.3002539499426563e-05, "epoch": 13.867986798679867, "percentage": 69.34, "elapsed_time": "4:58:10", "remaining_time": "2:11:50", "throughput": 1487.06, "total_tokens": 26603616} {"current_steps": 126065, "total_steps": 181800, "loss": 0.0021, "lr": 1.3000433917553306e-05, "epoch": 13.868536853685368, "percentage": 69.34, "elapsed_time": "4:58:10", "remaining_time": "2:11:49", "throughput": 1487.06, "total_tokens": 26604672} {"current_steps": 126070, "total_steps": 181800, "loss": 0.0371, "lr": 1.299832844627428e-05, "epoch": 13.86908690869087, "percentage": 69.35, "elapsed_time": "4:58:11", "remaining_time": "2:11:49", "throughput": 1487.06, "total_tokens": 26605696} {"current_steps": 126075, "total_steps": 181800, "loss": 0.0025, "lr": 1.299622308560891e-05, "epoch": 13.869636963696369, "percentage": 69.35, "elapsed_time": "4:58:12", "remaining_time": "2:11:48", "throughput": 1487.07, "total_tokens": 26606816} {"current_steps": 126080, "total_steps": 181800, "loss": 0.0045, "lr": 1.2994117835576598e-05, "epoch": 13.87018701870187, "percentage": 69.35, "elapsed_time": "4:58:12", "remaining_time": "2:11:47", "throughput": 1487.07, "total_tokens": 26607840} {"current_steps": 126085, "total_steps": 181800, "loss": 0.0727, "lr": 1.2992012696196715e-05, "epoch": 13.870737073707371, "percentage": 69.35, "elapsed_time": "4:58:13", "remaining_time": "2:11:46", "throughput": 1487.07, "total_tokens": 26608896} {"current_steps": 126090, "total_steps": 181800, "loss": 0.0233, "lr": 1.2989907667488713e-05, "epoch": 13.871287128712872, "percentage": 69.36, "elapsed_time": "4:58:14", "remaining_time": "2:11:46", "throughput": 1487.07, "total_tokens": 26609920} {"current_steps": 126095, "total_steps": 181800, "loss": 0.0047, "lr": 1.2987802749471955e-05, "epoch": 13.871837183718371, "percentage": 69.36, "elapsed_time": "4:58:14", "remaining_time": "2:11:45", "throughput": 1487.07, "total_tokens": 26610944} {"current_steps": 126100, "total_steps": 181800, "loss": 0.0298, "lr": 1.2985697942165869e-05, "epoch": 13.872387238723872, "percentage": 69.36, "elapsed_time": "4:58:15", "remaining_time": "2:11:44", "throughput": 1487.07, "total_tokens": 26612000} {"current_steps": 126105, "total_steps": 181800, "loss": 0.0092, "lr": 1.2983593245589837e-05, "epoch": 13.872937293729374, "percentage": 69.36, "elapsed_time": "4:58:16", "remaining_time": "2:11:44", "throughput": 1487.07, "total_tokens": 26613056} {"current_steps": 126110, "total_steps": 181800, "loss": 0.0027, "lr": 1.2981488659763253e-05, "epoch": 13.873487348734873, "percentage": 69.37, "elapsed_time": "4:58:16", "remaining_time": "2:11:43", "throughput": 1487.07, "total_tokens": 26614048} {"current_steps": 126115, "total_steps": 181800, "loss": 0.0667, "lr": 1.2979384184705518e-05, "epoch": 13.874037403740374, "percentage": 69.37, "elapsed_time": "4:58:17", "remaining_time": "2:11:42", "throughput": 1487.07, "total_tokens": 26615136} {"current_steps": 126120, "total_steps": 181800, "loss": 0.0309, "lr": 1.2977279820436034e-05, "epoch": 13.874587458745875, "percentage": 69.37, "elapsed_time": "4:58:18", "remaining_time": "2:11:41", "throughput": 1487.08, "total_tokens": 26616224} {"current_steps": 126125, "total_steps": 181800, "loss": 0.0438, "lr": 1.2975175566974201e-05, "epoch": 13.875137513751374, "percentage": 69.38, "elapsed_time": "4:58:19", "remaining_time": "2:11:41", "throughput": 1487.08, "total_tokens": 26617280} {"current_steps": 126130, "total_steps": 181800, "loss": 0.0017, "lr": 1.2973071424339404e-05, "epoch": 13.875687568756875, "percentage": 69.38, "elapsed_time": "4:58:19", "remaining_time": "2:11:40", "throughput": 1487.08, "total_tokens": 26618368} {"current_steps": 126135, "total_steps": 181800, "loss": 0.0075, "lr": 1.2970967392551026e-05, "epoch": 13.876237623762377, "percentage": 69.38, "elapsed_time": "4:58:20", "remaining_time": "2:11:39", "throughput": 1487.08, "total_tokens": 26619424} {"current_steps": 126140, "total_steps": 181800, "loss": 0.0748, "lr": 1.2968863471628481e-05, "epoch": 13.876787678767876, "percentage": 69.38, "elapsed_time": "4:58:21", "remaining_time": "2:11:38", "throughput": 1487.08, "total_tokens": 26620480} {"current_steps": 126145, "total_steps": 181800, "loss": 0.0038, "lr": 1.296675966159113e-05, "epoch": 13.877337733773377, "percentage": 69.39, "elapsed_time": "4:58:21", "remaining_time": "2:11:38", "throughput": 1487.08, "total_tokens": 26621504} {"current_steps": 126150, "total_steps": 181800, "loss": 0.0039, "lr": 1.29646559624584e-05, "epoch": 13.877887788778878, "percentage": 69.39, "elapsed_time": "4:58:22", "remaining_time": "2:11:37", "throughput": 1487.08, "total_tokens": 26622560} {"current_steps": 126155, "total_steps": 181800, "loss": 0.0733, "lr": 1.2962552374249658e-05, "epoch": 13.87843784378438, "percentage": 69.39, "elapsed_time": "4:58:23", "remaining_time": "2:11:36", "throughput": 1487.09, "total_tokens": 26623616} {"current_steps": 126160, "total_steps": 181800, "loss": 0.0653, "lr": 1.2960448896984286e-05, "epoch": 13.878987898789878, "percentage": 69.39, "elapsed_time": "4:58:23", "remaining_time": "2:11:36", "throughput": 1487.09, "total_tokens": 26624672} {"current_steps": 126165, "total_steps": 181800, "loss": 0.0019, "lr": 1.2958345530681692e-05, "epoch": 13.87953795379538, "percentage": 69.4, "elapsed_time": "4:58:24", "remaining_time": "2:11:35", "throughput": 1487.09, "total_tokens": 26625728} {"current_steps": 126170, "total_steps": 181800, "loss": 0.0052, "lr": 1.2956242275361236e-05, "epoch": 13.88008800880088, "percentage": 69.4, "elapsed_time": "4:58:25", "remaining_time": "2:11:34", "throughput": 1487.09, "total_tokens": 26626784} {"current_steps": 126175, "total_steps": 181800, "loss": 0.0104, "lr": 1.2954139131042318e-05, "epoch": 13.88063806380638, "percentage": 69.4, "elapsed_time": "4:58:25", "remaining_time": "2:11:33", "throughput": 1487.09, "total_tokens": 26627840} {"current_steps": 126180, "total_steps": 181800, "loss": 0.0023, "lr": 1.2952036097744327e-05, "epoch": 13.881188118811881, "percentage": 69.41, "elapsed_time": "4:58:26", "remaining_time": "2:11:33", "throughput": 1487.09, "total_tokens": 26628896} {"current_steps": 126185, "total_steps": 181800, "loss": 0.0025, "lr": 1.2949933175486629e-05, "epoch": 13.881738173817382, "percentage": 69.41, "elapsed_time": "4:58:27", "remaining_time": "2:11:32", "throughput": 1487.1, "total_tokens": 26629952} {"current_steps": 126190, "total_steps": 181800, "loss": 0.0637, "lr": 1.2947830364288627e-05, "epoch": 13.882288228822881, "percentage": 69.41, "elapsed_time": "4:58:28", "remaining_time": "2:11:31", "throughput": 1487.1, "total_tokens": 26631008} {"current_steps": 126195, "total_steps": 181800, "loss": 0.0466, "lr": 1.2945727664169677e-05, "epoch": 13.882838283828383, "percentage": 69.41, "elapsed_time": "4:58:28", "remaining_time": "2:11:31", "throughput": 1487.1, "total_tokens": 26632128} {"current_steps": 126200, "total_steps": 181800, "loss": 0.1794, "lr": 1.2943625075149179e-05, "epoch": 13.883388338833884, "percentage": 69.42, "elapsed_time": "4:58:29", "remaining_time": "2:11:30", "throughput": 1487.11, "total_tokens": 26633216} {"current_steps": 126205, "total_steps": 181800, "loss": 0.0021, "lr": 1.2941522597246497e-05, "epoch": 13.883938393839383, "percentage": 69.42, "elapsed_time": "4:58:30", "remaining_time": "2:11:29", "throughput": 1487.11, "total_tokens": 26634336} {"current_steps": 126210, "total_steps": 181800, "loss": 0.0063, "lr": 1.2939420230481014e-05, "epoch": 13.884488448844884, "percentage": 69.42, "elapsed_time": "4:58:30", "remaining_time": "2:11:28", "throughput": 1487.11, "total_tokens": 26635360} {"current_steps": 126215, "total_steps": 181800, "loss": 0.0443, "lr": 1.293731797487212e-05, "epoch": 13.885038503850385, "percentage": 69.43, "elapsed_time": "4:58:31", "remaining_time": "2:11:28", "throughput": 1487.11, "total_tokens": 26636416} {"current_steps": 126220, "total_steps": 181800, "loss": 0.0025, "lr": 1.2935215830439166e-05, "epoch": 13.885588558855886, "percentage": 69.43, "elapsed_time": "4:58:32", "remaining_time": "2:11:27", "throughput": 1487.11, "total_tokens": 26637440} {"current_steps": 126225, "total_steps": 181800, "loss": 0.0515, "lr": 1.2933113797201545e-05, "epoch": 13.886138613861386, "percentage": 69.43, "elapsed_time": "4:58:32", "remaining_time": "2:11:26", "throughput": 1487.11, "total_tokens": 26638432} {"current_steps": 126230, "total_steps": 181800, "loss": 0.0314, "lr": 1.2931011875178618e-05, "epoch": 13.886688668866887, "percentage": 69.43, "elapsed_time": "4:58:33", "remaining_time": "2:11:26", "throughput": 1487.11, "total_tokens": 26639488} {"current_steps": 126235, "total_steps": 181800, "loss": 0.0172, "lr": 1.2928910064389762e-05, "epoch": 13.887238723872388, "percentage": 69.44, "elapsed_time": "4:58:34", "remaining_time": "2:11:25", "throughput": 1487.11, "total_tokens": 26640512} {"current_steps": 126240, "total_steps": 181800, "loss": 0.078, "lr": 1.292680836485436e-05, "epoch": 13.887788778877887, "percentage": 69.44, "elapsed_time": "4:58:34", "remaining_time": "2:11:24", "throughput": 1487.11, "total_tokens": 26641600} {"current_steps": 126245, "total_steps": 181800, "loss": 0.0077, "lr": 1.2924706776591761e-05, "epoch": 13.888338833883388, "percentage": 69.44, "elapsed_time": "4:58:35", "remaining_time": "2:11:23", "throughput": 1487.12, "total_tokens": 26642656} {"current_steps": 126250, "total_steps": 181800, "loss": 0.0031, "lr": 1.2922605299621357e-05, "epoch": 13.88888888888889, "percentage": 69.44, "elapsed_time": "4:58:36", "remaining_time": "2:11:23", "throughput": 1487.12, "total_tokens": 26643680} {"current_steps": 126255, "total_steps": 181800, "loss": 0.0095, "lr": 1.2920503933962503e-05, "epoch": 13.88943894389439, "percentage": 69.45, "elapsed_time": "4:58:37", "remaining_time": "2:11:22", "throughput": 1487.12, "total_tokens": 26644672} {"current_steps": 126260, "total_steps": 181800, "loss": 0.0048, "lr": 1.291840267963455e-05, "epoch": 13.88998899889989, "percentage": 69.45, "elapsed_time": "4:58:37", "remaining_time": "2:11:21", "throughput": 1487.12, "total_tokens": 26645792} {"current_steps": 126265, "total_steps": 181800, "loss": 0.0562, "lr": 1.29163015366569e-05, "epoch": 13.89053905390539, "percentage": 69.45, "elapsed_time": "4:58:38", "remaining_time": "2:11:21", "throughput": 1487.12, "total_tokens": 26646816} {"current_steps": 126270, "total_steps": 181800, "loss": 0.021, "lr": 1.2914200505048901e-05, "epoch": 13.891089108910892, "percentage": 69.46, "elapsed_time": "4:58:39", "remaining_time": "2:11:20", "throughput": 1487.12, "total_tokens": 26647904} {"current_steps": 126275, "total_steps": 181800, "loss": 0.0119, "lr": 1.2912099584829906e-05, "epoch": 13.891639163916391, "percentage": 69.46, "elapsed_time": "4:58:39", "remaining_time": "2:11:19", "throughput": 1487.13, "total_tokens": 26648960} {"current_steps": 126280, "total_steps": 181800, "loss": 0.1094, "lr": 1.29099987760193e-05, "epoch": 13.892189218921892, "percentage": 69.46, "elapsed_time": "4:58:40", "remaining_time": "2:11:18", "throughput": 1487.13, "total_tokens": 26650016} {"current_steps": 126285, "total_steps": 181800, "loss": 0.0146, "lr": 1.2907898078636426e-05, "epoch": 13.892739273927393, "percentage": 69.46, "elapsed_time": "4:58:41", "remaining_time": "2:11:18", "throughput": 1487.13, "total_tokens": 26651040} {"current_steps": 126290, "total_steps": 181800, "loss": 0.0022, "lr": 1.290579749270065e-05, "epoch": 13.893289328932893, "percentage": 69.47, "elapsed_time": "4:58:41", "remaining_time": "2:11:17", "throughput": 1487.13, "total_tokens": 26652160} {"current_steps": 126295, "total_steps": 181800, "loss": 0.0447, "lr": 1.2903697018231347e-05, "epoch": 13.893839383938394, "percentage": 69.47, "elapsed_time": "4:58:42", "remaining_time": "2:11:16", "throughput": 1487.13, "total_tokens": 26653184} {"current_steps": 126300, "total_steps": 181800, "loss": 0.0007, "lr": 1.2901596655247852e-05, "epoch": 13.894389438943895, "percentage": 69.47, "elapsed_time": "4:58:43", "remaining_time": "2:11:15", "throughput": 1487.14, "total_tokens": 26654272} {"current_steps": 126305, "total_steps": 181800, "loss": 0.0316, "lr": 1.2899496403769545e-05, "epoch": 13.894939493949394, "percentage": 69.47, "elapsed_time": "4:58:43", "remaining_time": "2:11:15", "throughput": 1487.14, "total_tokens": 26655360} {"current_steps": 126310, "total_steps": 181800, "loss": 0.0052, "lr": 1.2897396263815764e-05, "epoch": 13.895489548954895, "percentage": 69.48, "elapsed_time": "4:58:44", "remaining_time": "2:11:14", "throughput": 1487.14, "total_tokens": 26656448} {"current_steps": 126315, "total_steps": 181800, "loss": 0.1169, "lr": 1.2895296235405885e-05, "epoch": 13.896039603960396, "percentage": 69.48, "elapsed_time": "4:58:45", "remaining_time": "2:11:13", "throughput": 1487.15, "total_tokens": 26657536} {"current_steps": 126320, "total_steps": 181800, "loss": 0.0325, "lr": 1.2893196318559242e-05, "epoch": 13.896589658965897, "percentage": 69.48, "elapsed_time": "4:58:45", "remaining_time": "2:11:13", "throughput": 1487.15, "total_tokens": 26658560} {"current_steps": 126325, "total_steps": 181800, "loss": 0.0134, "lr": 1.28910965132952e-05, "epoch": 13.897139713971397, "percentage": 69.49, "elapsed_time": "4:58:46", "remaining_time": "2:11:12", "throughput": 1487.15, "total_tokens": 26659648} {"current_steps": 126330, "total_steps": 181800, "loss": 0.0176, "lr": 1.2888996819633121e-05, "epoch": 13.897689768976898, "percentage": 69.49, "elapsed_time": "4:58:47", "remaining_time": "2:11:11", "throughput": 1487.16, "total_tokens": 26660768} {"current_steps": 126335, "total_steps": 181800, "loss": 0.0036, "lr": 1.2886897237592337e-05, "epoch": 13.898239823982399, "percentage": 69.49, "elapsed_time": "4:58:48", "remaining_time": "2:11:10", "throughput": 1487.16, "total_tokens": 26661824} {"current_steps": 126340, "total_steps": 181800, "loss": 0.0087, "lr": 1.2884797767192217e-05, "epoch": 13.898789878987898, "percentage": 69.49, "elapsed_time": "4:58:48", "remaining_time": "2:11:10", "throughput": 1487.16, "total_tokens": 26662880} {"current_steps": 126345, "total_steps": 181800, "loss": 0.003, "lr": 1.2882698408452093e-05, "epoch": 13.8993399339934, "percentage": 69.5, "elapsed_time": "4:58:49", "remaining_time": "2:11:09", "throughput": 1487.16, "total_tokens": 26663968} {"current_steps": 126350, "total_steps": 181800, "loss": 0.0285, "lr": 1.2880599161391324e-05, "epoch": 13.8998899889989, "percentage": 69.5, "elapsed_time": "4:58:50", "remaining_time": "2:11:08", "throughput": 1487.17, "total_tokens": 26665056} {"current_steps": 126355, "total_steps": 181800, "loss": 0.0049, "lr": 1.2878500026029267e-05, "epoch": 13.9004400440044, "percentage": 69.5, "elapsed_time": "4:58:50", "remaining_time": "2:11:08", "throughput": 1487.17, "total_tokens": 26666144} {"current_steps": 126360, "total_steps": 181800, "loss": 0.0549, "lr": 1.2876401002385247e-05, "epoch": 13.900990099009901, "percentage": 69.5, "elapsed_time": "4:58:51", "remaining_time": "2:11:07", "throughput": 1487.17, "total_tokens": 26667200} {"current_steps": 126365, "total_steps": 181800, "loss": 0.0025, "lr": 1.2874302090478635e-05, "epoch": 13.901540154015402, "percentage": 69.51, "elapsed_time": "4:58:52", "remaining_time": "2:11:06", "throughput": 1487.17, "total_tokens": 26668224} {"current_steps": 126370, "total_steps": 181800, "loss": 0.0013, "lr": 1.287220329032876e-05, "epoch": 13.902090209020901, "percentage": 69.51, "elapsed_time": "4:58:52", "remaining_time": "2:11:05", "throughput": 1487.17, "total_tokens": 26669280} {"current_steps": 126375, "total_steps": 181800, "loss": 0.0101, "lr": 1.2870104601954958e-05, "epoch": 13.902640264026402, "percentage": 69.51, "elapsed_time": "4:58:53", "remaining_time": "2:11:05", "throughput": 1487.18, "total_tokens": 26670368} {"current_steps": 126380, "total_steps": 181800, "loss": 0.003, "lr": 1.2868006025376581e-05, "epoch": 13.903190319031903, "percentage": 69.52, "elapsed_time": "4:58:54", "remaining_time": "2:11:04", "throughput": 1487.18, "total_tokens": 26671456} {"current_steps": 126385, "total_steps": 181800, "loss": 0.0028, "lr": 1.2865907560612972e-05, "epoch": 13.903740374037405, "percentage": 69.52, "elapsed_time": "4:58:54", "remaining_time": "2:11:03", "throughput": 1487.19, "total_tokens": 26672576} {"current_steps": 126390, "total_steps": 181800, "loss": 0.0982, "lr": 1.286380920768348e-05, "epoch": 13.904290429042904, "percentage": 69.52, "elapsed_time": "4:58:55", "remaining_time": "2:11:03", "throughput": 1487.19, "total_tokens": 26673696} {"current_steps": 126395, "total_steps": 181800, "loss": 0.0054, "lr": 1.2861710966607431e-05, "epoch": 13.904840484048405, "percentage": 69.52, "elapsed_time": "4:58:56", "remaining_time": "2:11:02", "throughput": 1487.2, "total_tokens": 26674784} {"current_steps": 126400, "total_steps": 181800, "loss": 0.0029, "lr": 1.2859612837404164e-05, "epoch": 13.905390539053906, "percentage": 69.53, "elapsed_time": "4:58:56", "remaining_time": "2:11:01", "throughput": 1487.2, "total_tokens": 26675840} {"current_steps": 126405, "total_steps": 181800, "loss": 0.0705, "lr": 1.2857514820093019e-05, "epoch": 13.905940594059405, "percentage": 69.53, "elapsed_time": "4:58:57", "remaining_time": "2:11:00", "throughput": 1487.2, "total_tokens": 26676928} {"current_steps": 126410, "total_steps": 181800, "loss": 0.0012, "lr": 1.285541691469333e-05, "epoch": 13.906490649064907, "percentage": 69.53, "elapsed_time": "4:58:58", "remaining_time": "2:11:00", "throughput": 1487.2, "total_tokens": 26677984} {"current_steps": 126415, "total_steps": 181800, "loss": 0.0021, "lr": 1.285331912122445e-05, "epoch": 13.907040704070408, "percentage": 69.54, "elapsed_time": "4:58:59", "remaining_time": "2:10:59", "throughput": 1487.2, "total_tokens": 26679008} {"current_steps": 126420, "total_steps": 181800, "loss": 0.0154, "lr": 1.2851221439705696e-05, "epoch": 13.907590759075907, "percentage": 69.54, "elapsed_time": "4:58:59", "remaining_time": "2:10:58", "throughput": 1487.2, "total_tokens": 26680032} {"current_steps": 126425, "total_steps": 181800, "loss": 0.0069, "lr": 1.2849123870156393e-05, "epoch": 13.908140814081408, "percentage": 69.54, "elapsed_time": "4:59:00", "remaining_time": "2:10:58", "throughput": 1487.21, "total_tokens": 26681152} {"current_steps": 126430, "total_steps": 181800, "loss": 0.0016, "lr": 1.2847026412595897e-05, "epoch": 13.908690869086909, "percentage": 69.54, "elapsed_time": "4:59:01", "remaining_time": "2:10:57", "throughput": 1487.21, "total_tokens": 26682272} {"current_steps": 126435, "total_steps": 181800, "loss": 0.0069, "lr": 1.2844929067043516e-05, "epoch": 13.909240924092408, "percentage": 69.55, "elapsed_time": "4:59:01", "remaining_time": "2:10:56", "throughput": 1487.22, "total_tokens": 26683360} {"current_steps": 126440, "total_steps": 181800, "loss": 0.0014, "lr": 1.2842831833518592e-05, "epoch": 13.90979097909791, "percentage": 69.55, "elapsed_time": "4:59:02", "remaining_time": "2:10:55", "throughput": 1487.22, "total_tokens": 26684384} {"current_steps": 126445, "total_steps": 181800, "loss": 0.0056, "lr": 1.2840734712040465e-05, "epoch": 13.91034103410341, "percentage": 69.55, "elapsed_time": "4:59:03", "remaining_time": "2:10:55", "throughput": 1487.22, "total_tokens": 26685408} {"current_steps": 126450, "total_steps": 181800, "loss": 0.0137, "lr": 1.283863770262844e-05, "epoch": 13.910891089108912, "percentage": 69.55, "elapsed_time": "4:59:03", "remaining_time": "2:10:54", "throughput": 1487.22, "total_tokens": 26686432} {"current_steps": 126455, "total_steps": 181800, "loss": 0.0374, "lr": 1.2836540805301866e-05, "epoch": 13.911441144114411, "percentage": 69.56, "elapsed_time": "4:59:04", "remaining_time": "2:10:53", "throughput": 1487.22, "total_tokens": 26687456} {"current_steps": 126460, "total_steps": 181800, "loss": 0.0487, "lr": 1.2834444020080047e-05, "epoch": 13.911991199119912, "percentage": 69.56, "elapsed_time": "4:59:05", "remaining_time": "2:10:52", "throughput": 1487.22, "total_tokens": 26688480} {"current_steps": 126465, "total_steps": 181800, "loss": 0.0014, "lr": 1.2832347346982321e-05, "epoch": 13.912541254125413, "percentage": 69.56, "elapsed_time": "4:59:05", "remaining_time": "2:10:52", "throughput": 1487.22, "total_tokens": 26689568} {"current_steps": 126470, "total_steps": 181800, "loss": 0.002, "lr": 1.2830250786028023e-05, "epoch": 13.913091309130913, "percentage": 69.57, "elapsed_time": "4:59:06", "remaining_time": "2:10:51", "throughput": 1487.22, "total_tokens": 26690592} {"current_steps": 126475, "total_steps": 181800, "loss": 0.0425, "lr": 1.282815433723645e-05, "epoch": 13.913641364136414, "percentage": 69.57, "elapsed_time": "4:59:07", "remaining_time": "2:10:50", "throughput": 1487.22, "total_tokens": 26691616} {"current_steps": 126480, "total_steps": 181800, "loss": 0.0032, "lr": 1.2826058000626951e-05, "epoch": 13.914191419141915, "percentage": 69.57, "elapsed_time": "4:59:08", "remaining_time": "2:10:50", "throughput": 1487.22, "total_tokens": 26692704} {"current_steps": 126485, "total_steps": 181800, "loss": 0.0036, "lr": 1.2823961776218832e-05, "epoch": 13.914741474147414, "percentage": 69.57, "elapsed_time": "4:59:08", "remaining_time": "2:10:49", "throughput": 1487.23, "total_tokens": 26693792} {"current_steps": 126490, "total_steps": 181800, "loss": 0.0016, "lr": 1.2821865664031407e-05, "epoch": 13.915291529152915, "percentage": 69.58, "elapsed_time": "4:59:09", "remaining_time": "2:10:48", "throughput": 1487.23, "total_tokens": 26694816} {"current_steps": 126495, "total_steps": 181800, "loss": 0.0817, "lr": 1.2819769664083999e-05, "epoch": 13.915841584158416, "percentage": 69.58, "elapsed_time": "4:59:10", "remaining_time": "2:10:47", "throughput": 1487.23, "total_tokens": 26695904} {"current_steps": 126500, "total_steps": 181800, "loss": 0.0122, "lr": 1.2817673776395933e-05, "epoch": 13.916391639163916, "percentage": 69.58, "elapsed_time": "4:59:10", "remaining_time": "2:10:47", "throughput": 1487.23, "total_tokens": 26696928} {"current_steps": 126505, "total_steps": 181800, "loss": 0.0051, "lr": 1.2815578000986529e-05, "epoch": 13.916941694169417, "percentage": 69.58, "elapsed_time": "4:59:11", "remaining_time": "2:10:46", "throughput": 1487.23, "total_tokens": 26697952} {"current_steps": 126510, "total_steps": 181800, "loss": 0.0307, "lr": 1.28134823378751e-05, "epoch": 13.917491749174918, "percentage": 69.59, "elapsed_time": "4:59:12", "remaining_time": "2:10:45", "throughput": 1487.23, "total_tokens": 26698976} {"current_steps": 126515, "total_steps": 181800, "loss": 0.0052, "lr": 1.2811386787080942e-05, "epoch": 13.918041804180419, "percentage": 69.59, "elapsed_time": "4:59:12", "remaining_time": "2:10:45", "throughput": 1487.23, "total_tokens": 26700000} {"current_steps": 126520, "total_steps": 181800, "loss": 0.0079, "lr": 1.2809291348623387e-05, "epoch": 13.918591859185918, "percentage": 69.59, "elapsed_time": "4:59:13", "remaining_time": "2:10:44", "throughput": 1487.24, "total_tokens": 26701120} {"current_steps": 126525, "total_steps": 181800, "loss": 0.0492, "lr": 1.280719602252174e-05, "epoch": 13.91914191419142, "percentage": 69.6, "elapsed_time": "4:59:14", "remaining_time": "2:10:43", "throughput": 1487.24, "total_tokens": 26702176} {"current_steps": 126530, "total_steps": 181800, "loss": 0.0211, "lr": 1.280510080879533e-05, "epoch": 13.91969196919692, "percentage": 69.6, "elapsed_time": "4:59:14", "remaining_time": "2:10:42", "throughput": 1487.24, "total_tokens": 26703200} {"current_steps": 126535, "total_steps": 181800, "loss": 0.0357, "lr": 1.2803005707463454e-05, "epoch": 13.92024202420242, "percentage": 69.6, "elapsed_time": "4:59:15", "remaining_time": "2:10:42", "throughput": 1487.24, "total_tokens": 26704288} {"current_steps": 126540, "total_steps": 181800, "loss": 0.0651, "lr": 1.2800910718545412e-05, "epoch": 13.92079207920792, "percentage": 69.6, "elapsed_time": "4:59:16", "remaining_time": "2:10:41", "throughput": 1487.24, "total_tokens": 26705344} {"current_steps": 126545, "total_steps": 181800, "loss": 0.0052, "lr": 1.279881584206053e-05, "epoch": 13.921342134213422, "percentage": 69.61, "elapsed_time": "4:59:16", "remaining_time": "2:10:40", "throughput": 1487.25, "total_tokens": 26706432} {"current_steps": 126550, "total_steps": 181800, "loss": 0.0237, "lr": 1.2796721078028095e-05, "epoch": 13.921892189218921, "percentage": 69.61, "elapsed_time": "4:59:17", "remaining_time": "2:10:40", "throughput": 1487.25, "total_tokens": 26707488} {"current_steps": 126555, "total_steps": 181800, "loss": 0.0033, "lr": 1.2794626426467432e-05, "epoch": 13.922442244224422, "percentage": 69.61, "elapsed_time": "4:59:18", "remaining_time": "2:10:39", "throughput": 1487.25, "total_tokens": 26708544} {"current_steps": 126560, "total_steps": 181800, "loss": 0.0762, "lr": 1.2792531887397846e-05, "epoch": 13.922992299229923, "percentage": 69.61, "elapsed_time": "4:59:19", "remaining_time": "2:10:38", "throughput": 1487.25, "total_tokens": 26709600} {"current_steps": 126565, "total_steps": 181800, "loss": 0.0718, "lr": 1.279043746083863e-05, "epoch": 13.923542354235423, "percentage": 69.62, "elapsed_time": "4:59:19", "remaining_time": "2:10:37", "throughput": 1487.25, "total_tokens": 26710656} {"current_steps": 126570, "total_steps": 181800, "loss": 0.0037, "lr": 1.27883431468091e-05, "epoch": 13.924092409240924, "percentage": 69.62, "elapsed_time": "4:59:20", "remaining_time": "2:10:37", "throughput": 1487.25, "total_tokens": 26711680} {"current_steps": 126575, "total_steps": 181800, "loss": 0.0007, "lr": 1.2786248945328543e-05, "epoch": 13.924642464246425, "percentage": 69.62, "elapsed_time": "4:59:21", "remaining_time": "2:10:36", "throughput": 1487.26, "total_tokens": 26712768} {"current_steps": 126580, "total_steps": 181800, "loss": 0.0035, "lr": 1.278415485641627e-05, "epoch": 13.925192519251926, "percentage": 69.63, "elapsed_time": "4:59:21", "remaining_time": "2:10:35", "throughput": 1487.25, "total_tokens": 26713760} {"current_steps": 126585, "total_steps": 181800, "loss": 0.0013, "lr": 1.278206088009159e-05, "epoch": 13.925742574257425, "percentage": 69.63, "elapsed_time": "4:59:22", "remaining_time": "2:10:35", "throughput": 1487.26, "total_tokens": 26714816} {"current_steps": 126590, "total_steps": 181800, "loss": 0.0068, "lr": 1.2779967016373778e-05, "epoch": 13.926292629262926, "percentage": 69.63, "elapsed_time": "4:59:23", "remaining_time": "2:10:34", "throughput": 1487.26, "total_tokens": 26715840} {"current_steps": 126595, "total_steps": 181800, "loss": 0.0737, "lr": 1.2777873265282159e-05, "epoch": 13.926842684268427, "percentage": 69.63, "elapsed_time": "4:59:23", "remaining_time": "2:10:33", "throughput": 1487.26, "total_tokens": 26716896} {"current_steps": 126600, "total_steps": 181800, "loss": 0.1216, "lr": 1.2775779626836009e-05, "epoch": 13.927392739273927, "percentage": 69.64, "elapsed_time": "4:59:24", "remaining_time": "2:10:32", "throughput": 1487.26, "total_tokens": 26717984} {"current_steps": 126605, "total_steps": 181800, "loss": 0.002, "lr": 1.2773686101054642e-05, "epoch": 13.927942794279428, "percentage": 69.64, "elapsed_time": "4:59:25", "remaining_time": "2:10:32", "throughput": 1487.26, "total_tokens": 26719072} {"current_steps": 126610, "total_steps": 181800, "loss": 0.0085, "lr": 1.2771592687957329e-05, "epoch": 13.928492849284929, "percentage": 69.64, "elapsed_time": "4:59:25", "remaining_time": "2:10:31", "throughput": 1487.27, "total_tokens": 26720160} {"current_steps": 126615, "total_steps": 181800, "loss": 0.0075, "lr": 1.2769499387563384e-05, "epoch": 13.929042904290428, "percentage": 69.65, "elapsed_time": "4:59:26", "remaining_time": "2:10:30", "throughput": 1487.27, "total_tokens": 26721216} {"current_steps": 126620, "total_steps": 181800, "loss": 0.013, "lr": 1.2767406199892102e-05, "epoch": 13.92959295929593, "percentage": 69.65, "elapsed_time": "4:59:27", "remaining_time": "2:10:30", "throughput": 1487.27, "total_tokens": 26722336} {"current_steps": 126625, "total_steps": 181800, "loss": 0.0775, "lr": 1.2765313124962757e-05, "epoch": 13.93014301430143, "percentage": 69.65, "elapsed_time": "4:59:28", "remaining_time": "2:10:29", "throughput": 1487.28, "total_tokens": 26723392} {"current_steps": 126630, "total_steps": 181800, "loss": 0.0139, "lr": 1.2763220162794658e-05, "epoch": 13.930693069306932, "percentage": 69.65, "elapsed_time": "4:59:28", "remaining_time": "2:10:28", "throughput": 1487.28, "total_tokens": 26724416} {"current_steps": 126635, "total_steps": 181800, "loss": 0.0428, "lr": 1.276112731340708e-05, "epoch": 13.93124312431243, "percentage": 69.66, "elapsed_time": "4:59:29", "remaining_time": "2:10:27", "throughput": 1487.28, "total_tokens": 26725440} {"current_steps": 126640, "total_steps": 181800, "loss": 0.0342, "lr": 1.275903457681932e-05, "epoch": 13.931793179317932, "percentage": 69.66, "elapsed_time": "4:59:30", "remaining_time": "2:10:27", "throughput": 1487.28, "total_tokens": 26726496} {"current_steps": 126645, "total_steps": 181800, "loss": 0.0015, "lr": 1.2756941953050671e-05, "epoch": 13.932343234323433, "percentage": 69.66, "elapsed_time": "4:59:30", "remaining_time": "2:10:26", "throughput": 1487.28, "total_tokens": 26727520} {"current_steps": 126650, "total_steps": 181800, "loss": 0.0011, "lr": 1.2754849442120417e-05, "epoch": 13.932893289328932, "percentage": 69.66, "elapsed_time": "4:59:31", "remaining_time": "2:10:25", "throughput": 1487.28, "total_tokens": 26728512} {"current_steps": 126655, "total_steps": 181800, "loss": 0.0011, "lr": 1.2752757044047827e-05, "epoch": 13.933443344334433, "percentage": 69.67, "elapsed_time": "4:59:32", "remaining_time": "2:10:24", "throughput": 1487.28, "total_tokens": 26729632} {"current_steps": 126660, "total_steps": 181800, "loss": 0.105, "lr": 1.275066475885221e-05, "epoch": 13.933993399339935, "percentage": 69.67, "elapsed_time": "4:59:32", "remaining_time": "2:10:24", "throughput": 1487.28, "total_tokens": 26730688} {"current_steps": 126665, "total_steps": 181800, "loss": 0.1203, "lr": 1.2748572586552827e-05, "epoch": 13.934543454345434, "percentage": 69.67, "elapsed_time": "4:59:33", "remaining_time": "2:10:23", "throughput": 1487.29, "total_tokens": 26731776} {"current_steps": 126670, "total_steps": 181800, "loss": 0.0017, "lr": 1.2746480527168975e-05, "epoch": 13.935093509350935, "percentage": 69.68, "elapsed_time": "4:59:34", "remaining_time": "2:10:22", "throughput": 1487.29, "total_tokens": 26732800} {"current_steps": 126675, "total_steps": 181800, "loss": 0.0041, "lr": 1.2744388580719937e-05, "epoch": 13.935643564356436, "percentage": 69.68, "elapsed_time": "4:59:34", "remaining_time": "2:10:22", "throughput": 1487.29, "total_tokens": 26733824} {"current_steps": 126680, "total_steps": 181800, "loss": 0.0328, "lr": 1.274229674722498e-05, "epoch": 13.936193619361937, "percentage": 69.68, "elapsed_time": "4:59:35", "remaining_time": "2:10:21", "throughput": 1487.29, "total_tokens": 26734880} {"current_steps": 126685, "total_steps": 181800, "loss": 0.0095, "lr": 1.2740205026703406e-05, "epoch": 13.936743674367436, "percentage": 69.68, "elapsed_time": "4:59:36", "remaining_time": "2:10:20", "throughput": 1487.29, "total_tokens": 26735936} {"current_steps": 126690, "total_steps": 181800, "loss": 0.0555, "lr": 1.2738113419174464e-05, "epoch": 13.937293729372938, "percentage": 69.69, "elapsed_time": "4:59:36", "remaining_time": "2:10:19", "throughput": 1487.29, "total_tokens": 26736960} {"current_steps": 126695, "total_steps": 181800, "loss": 0.029, "lr": 1.273602192465745e-05, "epoch": 13.937843784378439, "percentage": 69.69, "elapsed_time": "4:59:37", "remaining_time": "2:10:19", "throughput": 1487.28, "total_tokens": 26737920} {"current_steps": 126700, "total_steps": 181800, "loss": 0.0284, "lr": 1.2733930543171647e-05, "epoch": 13.938393839383938, "percentage": 69.69, "elapsed_time": "4:59:38", "remaining_time": "2:10:18", "throughput": 1487.29, "total_tokens": 26738976} {"current_steps": 126705, "total_steps": 181800, "loss": 0.0632, "lr": 1.273183927473631e-05, "epoch": 13.938943894389439, "percentage": 69.69, "elapsed_time": "4:59:39", "remaining_time": "2:10:17", "throughput": 1487.29, "total_tokens": 26740000} {"current_steps": 126710, "total_steps": 181800, "loss": 0.0065, "lr": 1.2729748119370733e-05, "epoch": 13.93949394939494, "percentage": 69.7, "elapsed_time": "4:59:39", "remaining_time": "2:10:17", "throughput": 1487.29, "total_tokens": 26741088} {"current_steps": 126715, "total_steps": 181800, "loss": 0.0131, "lr": 1.2727657077094168e-05, "epoch": 13.94004400440044, "percentage": 69.7, "elapsed_time": "4:59:40", "remaining_time": "2:10:16", "throughput": 1487.29, "total_tokens": 26742112} {"current_steps": 126720, "total_steps": 181800, "loss": 0.0022, "lr": 1.2725566147925911e-05, "epoch": 13.94059405940594, "percentage": 69.7, "elapsed_time": "4:59:41", "remaining_time": "2:10:15", "throughput": 1487.29, "total_tokens": 26743168} {"current_steps": 126725, "total_steps": 181800, "loss": 0.0128, "lr": 1.2723475331885213e-05, "epoch": 13.941144114411442, "percentage": 69.71, "elapsed_time": "4:59:41", "remaining_time": "2:10:14", "throughput": 1487.29, "total_tokens": 26744160} {"current_steps": 126730, "total_steps": 181800, "loss": 0.0014, "lr": 1.272138462899135e-05, "epoch": 13.941694169416941, "percentage": 69.71, "elapsed_time": "4:59:42", "remaining_time": "2:10:14", "throughput": 1487.29, "total_tokens": 26745216} {"current_steps": 126735, "total_steps": 181800, "loss": 0.0509, "lr": 1.2719294039263601e-05, "epoch": 13.942244224422442, "percentage": 69.71, "elapsed_time": "4:59:43", "remaining_time": "2:10:13", "throughput": 1487.3, "total_tokens": 26746304} {"current_steps": 126740, "total_steps": 181800, "loss": 0.01, "lr": 1.271720356272122e-05, "epoch": 13.942794279427943, "percentage": 69.71, "elapsed_time": "4:59:43", "remaining_time": "2:10:12", "throughput": 1487.3, "total_tokens": 26747360} {"current_steps": 126745, "total_steps": 181800, "loss": 0.1179, "lr": 1.2715113199383489e-05, "epoch": 13.943344334433444, "percentage": 69.72, "elapsed_time": "4:59:44", "remaining_time": "2:10:12", "throughput": 1487.3, "total_tokens": 26748416} {"current_steps": 126750, "total_steps": 181800, "loss": 0.0009, "lr": 1.2713022949269651e-05, "epoch": 13.943894389438944, "percentage": 69.72, "elapsed_time": "4:59:45", "remaining_time": "2:10:11", "throughput": 1487.3, "total_tokens": 26749440} {"current_steps": 126755, "total_steps": 181800, "loss": 0.0013, "lr": 1.2710932812398988e-05, "epoch": 13.944444444444445, "percentage": 69.72, "elapsed_time": "4:59:45", "remaining_time": "2:10:10", "throughput": 1487.3, "total_tokens": 26750496} {"current_steps": 126760, "total_steps": 181800, "loss": 0.003, "lr": 1.270884278879077e-05, "epoch": 13.944994499449946, "percentage": 69.72, "elapsed_time": "4:59:46", "remaining_time": "2:10:09", "throughput": 1487.3, "total_tokens": 26751520} {"current_steps": 126765, "total_steps": 181800, "loss": 0.0012, "lr": 1.270675287846424e-05, "epoch": 13.945544554455445, "percentage": 69.73, "elapsed_time": "4:59:47", "remaining_time": "2:10:09", "throughput": 1487.3, "total_tokens": 26752544} {"current_steps": 126770, "total_steps": 181800, "loss": 0.0046, "lr": 1.2704663081438678e-05, "epoch": 13.946094609460946, "percentage": 69.73, "elapsed_time": "4:59:48", "remaining_time": "2:10:08", "throughput": 1487.3, "total_tokens": 26753568} {"current_steps": 126775, "total_steps": 181800, "loss": 0.0055, "lr": 1.2702573397733338e-05, "epoch": 13.946644664466447, "percentage": 69.73, "elapsed_time": "4:59:48", "remaining_time": "2:10:07", "throughput": 1487.3, "total_tokens": 26754560} {"current_steps": 126780, "total_steps": 181800, "loss": 0.1009, "lr": 1.2700483827367468e-05, "epoch": 13.947194719471947, "percentage": 69.74, "elapsed_time": "4:59:49", "remaining_time": "2:10:07", "throughput": 1487.3, "total_tokens": 26755712} {"current_steps": 126785, "total_steps": 181800, "loss": 0.0033, "lr": 1.2698394370360339e-05, "epoch": 13.947744774477448, "percentage": 69.74, "elapsed_time": "4:59:50", "remaining_time": "2:10:06", "throughput": 1487.31, "total_tokens": 26756768} {"current_steps": 126790, "total_steps": 181800, "loss": 0.0621, "lr": 1.2696305026731204e-05, "epoch": 13.948294829482949, "percentage": 69.74, "elapsed_time": "4:59:50", "remaining_time": "2:10:05", "throughput": 1487.31, "total_tokens": 26757824} {"current_steps": 126795, "total_steps": 181800, "loss": 0.0008, "lr": 1.2694215796499331e-05, "epoch": 13.948844884488448, "percentage": 69.74, "elapsed_time": "4:59:51", "remaining_time": "2:10:04", "throughput": 1487.31, "total_tokens": 26758912} {"current_steps": 126800, "total_steps": 181800, "loss": 0.0273, "lr": 1.2692126679683966e-05, "epoch": 13.94939493949395, "percentage": 69.75, "elapsed_time": "4:59:52", "remaining_time": "2:10:04", "throughput": 1487.31, "total_tokens": 26759936} {"current_steps": 126805, "total_steps": 181800, "loss": 0.0685, "lr": 1.2690037676304356e-05, "epoch": 13.94994499449945, "percentage": 69.75, "elapsed_time": "4:59:52", "remaining_time": "2:10:03", "throughput": 1487.31, "total_tokens": 26760960} {"current_steps": 126810, "total_steps": 181800, "loss": 0.0031, "lr": 1.2687948786379761e-05, "epoch": 13.950495049504951, "percentage": 69.75, "elapsed_time": "4:59:53", "remaining_time": "2:10:02", "throughput": 1487.31, "total_tokens": 26762048} {"current_steps": 126815, "total_steps": 181800, "loss": 0.009, "lr": 1.2685860009929432e-05, "epoch": 13.95104510451045, "percentage": 69.76, "elapsed_time": "4:59:54", "remaining_time": "2:10:02", "throughput": 1487.32, "total_tokens": 26763104} {"current_steps": 126820, "total_steps": 181800, "loss": 0.0084, "lr": 1.2683771346972633e-05, "epoch": 13.951595159515952, "percentage": 69.76, "elapsed_time": "4:59:54", "remaining_time": "2:10:01", "throughput": 1487.32, "total_tokens": 26764128} {"current_steps": 126825, "total_steps": 181800, "loss": 0.0032, "lr": 1.2681682797528605e-05, "epoch": 13.952145214521453, "percentage": 69.76, "elapsed_time": "4:59:55", "remaining_time": "2:10:00", "throughput": 1487.32, "total_tokens": 26765184} {"current_steps": 126830, "total_steps": 181800, "loss": 0.018, "lr": 1.2679594361616585e-05, "epoch": 13.952695269526952, "percentage": 69.76, "elapsed_time": "4:59:56", "remaining_time": "2:09:59", "throughput": 1487.32, "total_tokens": 26766208} {"current_steps": 126835, "total_steps": 181800, "loss": 0.0194, "lr": 1.2677506039255843e-05, "epoch": 13.953245324532453, "percentage": 69.77, "elapsed_time": "4:59:56", "remaining_time": "2:09:59", "throughput": 1487.32, "total_tokens": 26767328} {"current_steps": 126840, "total_steps": 181800, "loss": 0.2018, "lr": 1.2675417830465602e-05, "epoch": 13.953795379537954, "percentage": 69.77, "elapsed_time": "4:59:57", "remaining_time": "2:09:58", "throughput": 1487.33, "total_tokens": 26768416} {"current_steps": 126845, "total_steps": 181800, "loss": 0.0987, "lr": 1.2673329735265124e-05, "epoch": 13.954345434543454, "percentage": 69.77, "elapsed_time": "4:59:58", "remaining_time": "2:09:57", "throughput": 1487.33, "total_tokens": 26769472} {"current_steps": 126850, "total_steps": 181800, "loss": 0.0754, "lr": 1.2671241753673657e-05, "epoch": 13.954895489548955, "percentage": 69.77, "elapsed_time": "4:59:59", "remaining_time": "2:09:56", "throughput": 1487.33, "total_tokens": 26770496} {"current_steps": 126855, "total_steps": 181800, "loss": 0.013, "lr": 1.2669153885710434e-05, "epoch": 13.955445544554456, "percentage": 69.78, "elapsed_time": "4:59:59", "remaining_time": "2:09:56", "throughput": 1487.33, "total_tokens": 26771584} {"current_steps": 126860, "total_steps": 181800, "loss": 0.0492, "lr": 1.2667066131394712e-05, "epoch": 13.955995599559955, "percentage": 69.78, "elapsed_time": "5:00:00", "remaining_time": "2:09:55", "throughput": 1487.33, "total_tokens": 26772576} {"current_steps": 126865, "total_steps": 181800, "loss": 0.0035, "lr": 1.266497849074572e-05, "epoch": 13.956545654565456, "percentage": 69.78, "elapsed_time": "5:00:01", "remaining_time": "2:09:54", "throughput": 1487.33, "total_tokens": 26773568} {"current_steps": 126870, "total_steps": 181800, "loss": 0.1703, "lr": 1.2662890963782686e-05, "epoch": 13.957095709570957, "percentage": 69.79, "elapsed_time": "5:00:01", "remaining_time": "2:09:54", "throughput": 1487.33, "total_tokens": 26774560} {"current_steps": 126875, "total_steps": 181800, "loss": 0.0902, "lr": 1.2660803550524882e-05, "epoch": 13.957645764576458, "percentage": 69.79, "elapsed_time": "5:00:02", "remaining_time": "2:09:53", "throughput": 1487.33, "total_tokens": 26775616} {"current_steps": 126880, "total_steps": 181800, "loss": 0.0041, "lr": 1.2658716250991526e-05, "epoch": 13.958195819581958, "percentage": 69.79, "elapsed_time": "5:00:03", "remaining_time": "2:09:52", "throughput": 1487.33, "total_tokens": 26776640} {"current_steps": 126885, "total_steps": 181800, "loss": 0.0261, "lr": 1.2656629065201863e-05, "epoch": 13.958745874587459, "percentage": 69.79, "elapsed_time": "5:00:03", "remaining_time": "2:09:51", "throughput": 1487.33, "total_tokens": 26777664} {"current_steps": 126890, "total_steps": 181800, "loss": 0.0927, "lr": 1.2654541993175134e-05, "epoch": 13.95929592959296, "percentage": 69.8, "elapsed_time": "5:00:04", "remaining_time": "2:09:51", "throughput": 1487.33, "total_tokens": 26778656} {"current_steps": 126895, "total_steps": 181800, "loss": 0.1109, "lr": 1.2652455034930554e-05, "epoch": 13.95984598459846, "percentage": 69.8, "elapsed_time": "5:00:05", "remaining_time": "2:09:50", "throughput": 1487.33, "total_tokens": 26779744} {"current_steps": 126900, "total_steps": 181800, "loss": 0.0099, "lr": 1.2650368190487372e-05, "epoch": 13.96039603960396, "percentage": 69.8, "elapsed_time": "5:00:05", "remaining_time": "2:09:49", "throughput": 1487.33, "total_tokens": 26780832} {"current_steps": 126905, "total_steps": 181800, "loss": 0.0014, "lr": 1.264828145986482e-05, "epoch": 13.960946094609461, "percentage": 69.8, "elapsed_time": "5:00:06", "remaining_time": "2:09:49", "throughput": 1487.33, "total_tokens": 26781856} {"current_steps": 126910, "total_steps": 181800, "loss": 0.0047, "lr": 1.2646194843082143e-05, "epoch": 13.96149614961496, "percentage": 69.81, "elapsed_time": "5:00:07", "remaining_time": "2:09:48", "throughput": 1487.34, "total_tokens": 26782912} {"current_steps": 126915, "total_steps": 181800, "loss": 0.0073, "lr": 1.2644108340158555e-05, "epoch": 13.962046204620462, "percentage": 69.81, "elapsed_time": "5:00:07", "remaining_time": "2:09:47", "throughput": 1487.34, "total_tokens": 26783936} {"current_steps": 126920, "total_steps": 181800, "loss": 0.0031, "lr": 1.2642021951113287e-05, "epoch": 13.962596259625963, "percentage": 69.81, "elapsed_time": "5:00:08", "remaining_time": "2:09:46", "throughput": 1487.34, "total_tokens": 26785024} {"current_steps": 126925, "total_steps": 181800, "loss": 0.112, "lr": 1.263993567596558e-05, "epoch": 13.963146314631462, "percentage": 69.82, "elapsed_time": "5:00:09", "remaining_time": "2:09:46", "throughput": 1487.34, "total_tokens": 26786080} {"current_steps": 126930, "total_steps": 181800, "loss": 0.0015, "lr": 1.2637849514734638e-05, "epoch": 13.963696369636963, "percentage": 69.82, "elapsed_time": "5:00:10", "remaining_time": "2:09:45", "throughput": 1487.34, "total_tokens": 26787136} {"current_steps": 126935, "total_steps": 181800, "loss": 0.0048, "lr": 1.263576346743972e-05, "epoch": 13.964246424642464, "percentage": 69.82, "elapsed_time": "5:00:10", "remaining_time": "2:09:44", "throughput": 1487.35, "total_tokens": 26788224} {"current_steps": 126940, "total_steps": 181800, "loss": 0.144, "lr": 1.2633677534100041e-05, "epoch": 13.964796479647966, "percentage": 69.82, "elapsed_time": "5:00:11", "remaining_time": "2:09:44", "throughput": 1487.35, "total_tokens": 26789312} {"current_steps": 126945, "total_steps": 181800, "loss": 0.0662, "lr": 1.2631591714734812e-05, "epoch": 13.965346534653465, "percentage": 69.83, "elapsed_time": "5:00:12", "remaining_time": "2:09:43", "throughput": 1487.35, "total_tokens": 26790400} {"current_steps": 126950, "total_steps": 181800, "loss": 0.0043, "lr": 1.2629506009363276e-05, "epoch": 13.965896589658966, "percentage": 69.83, "elapsed_time": "5:00:12", "remaining_time": "2:09:42", "throughput": 1487.36, "total_tokens": 26791456} {"current_steps": 126955, "total_steps": 181800, "loss": 0.0066, "lr": 1.2627420418004637e-05, "epoch": 13.966446644664467, "percentage": 69.83, "elapsed_time": "5:00:13", "remaining_time": "2:09:41", "throughput": 1487.36, "total_tokens": 26792480} {"current_steps": 126960, "total_steps": 181800, "loss": 0.0542, "lr": 1.2625334940678129e-05, "epoch": 13.966996699669966, "percentage": 69.83, "elapsed_time": "5:00:14", "remaining_time": "2:09:41", "throughput": 1487.36, "total_tokens": 26793632} {"current_steps": 126965, "total_steps": 181800, "loss": 0.0515, "lr": 1.2623249577402979e-05, "epoch": 13.967546754675467, "percentage": 69.84, "elapsed_time": "5:00:14", "remaining_time": "2:09:40", "throughput": 1487.36, "total_tokens": 26794688} {"current_steps": 126970, "total_steps": 181800, "loss": 0.0179, "lr": 1.2621164328198388e-05, "epoch": 13.968096809680969, "percentage": 69.84, "elapsed_time": "5:00:15", "remaining_time": "2:09:39", "throughput": 1487.37, "total_tokens": 26795776} {"current_steps": 126975, "total_steps": 181800, "loss": 0.0678, "lr": 1.2619079193083596e-05, "epoch": 13.968646864686468, "percentage": 69.84, "elapsed_time": "5:00:16", "remaining_time": "2:09:39", "throughput": 1487.37, "total_tokens": 26796832} {"current_steps": 126980, "total_steps": 181800, "loss": 0.0054, "lr": 1.2616994172077801e-05, "epoch": 13.969196919691969, "percentage": 69.85, "elapsed_time": "5:00:16", "remaining_time": "2:09:38", "throughput": 1487.37, "total_tokens": 26797920} {"current_steps": 126985, "total_steps": 181800, "loss": 0.0474, "lr": 1.2614909265200239e-05, "epoch": 13.96974697469747, "percentage": 69.85, "elapsed_time": "5:00:17", "remaining_time": "2:09:37", "throughput": 1487.37, "total_tokens": 26798976} {"current_steps": 126990, "total_steps": 181800, "loss": 0.0024, "lr": 1.2612824472470105e-05, "epoch": 13.97029702970297, "percentage": 69.85, "elapsed_time": "5:00:18", "remaining_time": "2:09:36", "throughput": 1487.38, "total_tokens": 26800064} {"current_steps": 126995, "total_steps": 181800, "loss": 0.0026, "lr": 1.2610739793906623e-05, "epoch": 13.97084708470847, "percentage": 69.85, "elapsed_time": "5:00:19", "remaining_time": "2:09:36", "throughput": 1487.38, "total_tokens": 26801216} {"current_steps": 127000, "total_steps": 181800, "loss": 0.0028, "lr": 1.260865522952902e-05, "epoch": 13.971397139713972, "percentage": 69.86, "elapsed_time": "5:00:19", "remaining_time": "2:09:35", "throughput": 1487.39, "total_tokens": 26802272} {"current_steps": 127005, "total_steps": 181800, "loss": 0.0313, "lr": 1.2606570779356484e-05, "epoch": 13.971947194719473, "percentage": 69.86, "elapsed_time": "5:00:20", "remaining_time": "2:09:34", "throughput": 1487.39, "total_tokens": 26803392} {"current_steps": 127010, "total_steps": 181800, "loss": 0.0443, "lr": 1.2604486443408247e-05, "epoch": 13.972497249724972, "percentage": 69.86, "elapsed_time": "5:00:21", "remaining_time": "2:09:33", "throughput": 1487.4, "total_tokens": 26804544} {"current_steps": 127015, "total_steps": 181800, "loss": 0.0128, "lr": 1.2602402221703502e-05, "epoch": 13.973047304730473, "percentage": 69.87, "elapsed_time": "5:00:21", "remaining_time": "2:09:33", "throughput": 1487.4, "total_tokens": 26805600} {"current_steps": 127020, "total_steps": 181800, "loss": 0.0045, "lr": 1.2600318114261466e-05, "epoch": 13.973597359735974, "percentage": 69.87, "elapsed_time": "5:00:22", "remaining_time": "2:09:32", "throughput": 1487.4, "total_tokens": 26806592} {"current_steps": 127025, "total_steps": 181800, "loss": 0.0057, "lr": 1.259823412110136e-05, "epoch": 13.974147414741473, "percentage": 69.87, "elapsed_time": "5:00:23", "remaining_time": "2:09:31", "throughput": 1487.4, "total_tokens": 26807648} {"current_steps": 127030, "total_steps": 181800, "loss": 0.0054, "lr": 1.2596150242242378e-05, "epoch": 13.974697469746975, "percentage": 69.87, "elapsed_time": "5:00:23", "remaining_time": "2:09:31", "throughput": 1487.4, "total_tokens": 26808640} {"current_steps": 127035, "total_steps": 181800, "loss": 0.0021, "lr": 1.2594066477703715e-05, "epoch": 13.975247524752476, "percentage": 69.88, "elapsed_time": "5:00:24", "remaining_time": "2:09:30", "throughput": 1487.4, "total_tokens": 26809664} {"current_steps": 127040, "total_steps": 181800, "loss": 0.0119, "lr": 1.25919828275046e-05, "epoch": 13.975797579757975, "percentage": 69.88, "elapsed_time": "5:00:25", "remaining_time": "2:09:29", "throughput": 1487.4, "total_tokens": 26810720} {"current_steps": 127045, "total_steps": 181800, "loss": 0.0024, "lr": 1.2589899291664206e-05, "epoch": 13.976347634763476, "percentage": 69.88, "elapsed_time": "5:00:25", "remaining_time": "2:09:28", "throughput": 1487.4, "total_tokens": 26811776} {"current_steps": 127050, "total_steps": 181800, "loss": 0.005, "lr": 1.2587815870201774e-05, "epoch": 13.976897689768977, "percentage": 69.88, "elapsed_time": "5:00:26", "remaining_time": "2:09:28", "throughput": 1487.4, "total_tokens": 26812800} {"current_steps": 127055, "total_steps": 181800, "loss": 0.0014, "lr": 1.2585732563136487e-05, "epoch": 13.977447744774478, "percentage": 69.89, "elapsed_time": "5:00:27", "remaining_time": "2:09:27", "throughput": 1487.4, "total_tokens": 26813888} {"current_steps": 127060, "total_steps": 181800, "loss": 0.0015, "lr": 1.2583649370487537e-05, "epoch": 13.977997799779978, "percentage": 69.89, "elapsed_time": "5:00:27", "remaining_time": "2:09:26", "throughput": 1487.41, "total_tokens": 26814944} {"current_steps": 127065, "total_steps": 181800, "loss": 0.0021, "lr": 1.2581566292274143e-05, "epoch": 13.978547854785479, "percentage": 69.89, "elapsed_time": "5:00:28", "remaining_time": "2:09:26", "throughput": 1487.41, "total_tokens": 26815968} {"current_steps": 127070, "total_steps": 181800, "loss": 0.0577, "lr": 1.2579483328515485e-05, "epoch": 13.97909790979098, "percentage": 69.9, "elapsed_time": "5:00:29", "remaining_time": "2:09:25", "throughput": 1487.4, "total_tokens": 26816960} {"current_steps": 127075, "total_steps": 181800, "loss": 0.0023, "lr": 1.2577400479230766e-05, "epoch": 13.979647964796479, "percentage": 69.9, "elapsed_time": "5:00:30", "remaining_time": "2:09:24", "throughput": 1487.41, "total_tokens": 26818016} {"current_steps": 127080, "total_steps": 181800, "loss": 0.0223, "lr": 1.25753177444392e-05, "epoch": 13.98019801980198, "percentage": 69.9, "elapsed_time": "5:00:30", "remaining_time": "2:09:23", "throughput": 1487.4, "total_tokens": 26819008} {"current_steps": 127085, "total_steps": 181800, "loss": 0.002, "lr": 1.2573235124159954e-05, "epoch": 13.980748074807481, "percentage": 69.9, "elapsed_time": "5:00:31", "remaining_time": "2:09:23", "throughput": 1487.41, "total_tokens": 26820064} {"current_steps": 127090, "total_steps": 181800, "loss": 0.0753, "lr": 1.2571152618412249e-05, "epoch": 13.98129812981298, "percentage": 69.91, "elapsed_time": "5:00:32", "remaining_time": "2:09:22", "throughput": 1487.41, "total_tokens": 26821184} {"current_steps": 127095, "total_steps": 181800, "loss": 0.005, "lr": 1.2569070227215258e-05, "epoch": 13.981848184818482, "percentage": 69.91, "elapsed_time": "5:00:32", "remaining_time": "2:09:21", "throughput": 1487.41, "total_tokens": 26822176} {"current_steps": 127100, "total_steps": 181800, "loss": 0.0109, "lr": 1.2566987950588188e-05, "epoch": 13.982398239823983, "percentage": 69.91, "elapsed_time": "5:00:33", "remaining_time": "2:09:21", "throughput": 1487.41, "total_tokens": 26823264} {"current_steps": 127105, "total_steps": 181800, "loss": 0.1422, "lr": 1.2564905788550219e-05, "epoch": 13.982948294829484, "percentage": 69.91, "elapsed_time": "5:00:34", "remaining_time": "2:09:20", "throughput": 1487.41, "total_tokens": 26824256} {"current_steps": 127110, "total_steps": 181800, "loss": 0.0029, "lr": 1.2562823741120541e-05, "epoch": 13.983498349834983, "percentage": 69.92, "elapsed_time": "5:00:34", "remaining_time": "2:09:19", "throughput": 1487.41, "total_tokens": 26825344} {"current_steps": 127115, "total_steps": 181800, "loss": 0.004, "lr": 1.256074180831836e-05, "epoch": 13.984048404840484, "percentage": 69.92, "elapsed_time": "5:00:35", "remaining_time": "2:09:18", "throughput": 1487.42, "total_tokens": 26826400} {"current_steps": 127120, "total_steps": 181800, "loss": 0.0039, "lr": 1.2558659990162847e-05, "epoch": 13.984598459845985, "percentage": 69.92, "elapsed_time": "5:00:36", "remaining_time": "2:09:18", "throughput": 1487.42, "total_tokens": 26827520} {"current_steps": 127125, "total_steps": 181800, "loss": 0.007, "lr": 1.2556578286673198e-05, "epoch": 13.985148514851485, "percentage": 69.93, "elapsed_time": "5:00:36", "remaining_time": "2:09:17", "throughput": 1487.42, "total_tokens": 26828480} {"current_steps": 127130, "total_steps": 181800, "loss": 0.0366, "lr": 1.2554496697868592e-05, "epoch": 13.985698569856986, "percentage": 69.93, "elapsed_time": "5:00:37", "remaining_time": "2:09:16", "throughput": 1487.42, "total_tokens": 26829568} {"current_steps": 127135, "total_steps": 181800, "loss": 0.0052, "lr": 1.2552415223768215e-05, "epoch": 13.986248624862487, "percentage": 69.93, "elapsed_time": "5:00:38", "remaining_time": "2:09:16", "throughput": 1487.42, "total_tokens": 26830592} {"current_steps": 127140, "total_steps": 181800, "loss": 0.0012, "lr": 1.2550333864391267e-05, "epoch": 13.986798679867986, "percentage": 69.93, "elapsed_time": "5:00:39", "remaining_time": "2:09:15", "throughput": 1487.42, "total_tokens": 26831648} {"current_steps": 127145, "total_steps": 181800, "loss": 0.0034, "lr": 1.2548252619756906e-05, "epoch": 13.987348734873487, "percentage": 69.94, "elapsed_time": "5:00:39", "remaining_time": "2:09:14", "throughput": 1487.43, "total_tokens": 26832736} {"current_steps": 127150, "total_steps": 181800, "loss": 0.0358, "lr": 1.2546171489884333e-05, "epoch": 13.987898789878988, "percentage": 69.94, "elapsed_time": "5:00:40", "remaining_time": "2:09:13", "throughput": 1487.43, "total_tokens": 26833792} {"current_steps": 127155, "total_steps": 181800, "loss": 0.0029, "lr": 1.2544090474792724e-05, "epoch": 13.988448844884488, "percentage": 69.94, "elapsed_time": "5:00:41", "remaining_time": "2:09:13", "throughput": 1487.43, "total_tokens": 26834880} {"current_steps": 127160, "total_steps": 181800, "loss": 0.0309, "lr": 1.2542009574501246e-05, "epoch": 13.988998899889989, "percentage": 69.94, "elapsed_time": "5:00:41", "remaining_time": "2:09:12", "throughput": 1487.43, "total_tokens": 26835936} {"current_steps": 127165, "total_steps": 181800, "loss": 0.0186, "lr": 1.2539928789029088e-05, "epoch": 13.98954895489549, "percentage": 69.95, "elapsed_time": "5:00:42", "remaining_time": "2:09:11", "throughput": 1487.44, "total_tokens": 26837024} {"current_steps": 127170, "total_steps": 181800, "loss": 0.0135, "lr": 1.253784811839543e-05, "epoch": 13.990099009900991, "percentage": 69.95, "elapsed_time": "5:00:43", "remaining_time": "2:09:11", "throughput": 1487.44, "total_tokens": 26838144} {"current_steps": 127175, "total_steps": 181800, "loss": 0.0576, "lr": 1.2535767562619449e-05, "epoch": 13.99064906490649, "percentage": 69.95, "elapsed_time": "5:00:43", "remaining_time": "2:09:10", "throughput": 1487.44, "total_tokens": 26839200} {"current_steps": 127180, "total_steps": 181800, "loss": 0.0011, "lr": 1.2533687121720323e-05, "epoch": 13.991199119911991, "percentage": 69.96, "elapsed_time": "5:00:44", "remaining_time": "2:09:09", "throughput": 1487.45, "total_tokens": 26840288} {"current_steps": 127185, "total_steps": 181800, "loss": 0.0923, "lr": 1.253160679571721e-05, "epoch": 13.991749174917492, "percentage": 69.96, "elapsed_time": "5:00:45", "remaining_time": "2:09:08", "throughput": 1487.45, "total_tokens": 26841312} {"current_steps": 127190, "total_steps": 181800, "loss": 0.1781, "lr": 1.2529526584629291e-05, "epoch": 13.992299229922992, "percentage": 69.96, "elapsed_time": "5:00:45", "remaining_time": "2:09:08", "throughput": 1487.44, "total_tokens": 26842304} {"current_steps": 127195, "total_steps": 181800, "loss": 0.0438, "lr": 1.2527446488475748e-05, "epoch": 13.992849284928493, "percentage": 69.96, "elapsed_time": "5:00:46", "remaining_time": "2:09:07", "throughput": 1487.45, "total_tokens": 26843392} {"current_steps": 127200, "total_steps": 181800, "loss": 0.0011, "lr": 1.252536650727575e-05, "epoch": 13.993399339933994, "percentage": 69.97, "elapsed_time": "5:00:47", "remaining_time": "2:09:06", "throughput": 1487.45, "total_tokens": 26844448} {"current_steps": 127205, "total_steps": 181800, "loss": 0.0077, "lr": 1.2523286641048466e-05, "epoch": 13.993949394939493, "percentage": 69.97, "elapsed_time": "5:00:48", "remaining_time": "2:09:06", "throughput": 1487.45, "total_tokens": 26845568} {"current_steps": 127210, "total_steps": 181800, "loss": 0.0037, "lr": 1.252120688981305e-05, "epoch": 13.994499449944994, "percentage": 69.97, "elapsed_time": "5:00:48", "remaining_time": "2:09:05", "throughput": 1487.46, "total_tokens": 26846656} {"current_steps": 127215, "total_steps": 181800, "loss": 0.0182, "lr": 1.2519127253588692e-05, "epoch": 13.995049504950495, "percentage": 69.98, "elapsed_time": "5:00:49", "remaining_time": "2:09:04", "throughput": 1487.46, "total_tokens": 26847744} {"current_steps": 127220, "total_steps": 181800, "loss": 0.0043, "lr": 1.2517047732394543e-05, "epoch": 13.995599559955995, "percentage": 69.98, "elapsed_time": "5:00:50", "remaining_time": "2:09:03", "throughput": 1487.46, "total_tokens": 26848832} {"current_steps": 127225, "total_steps": 181800, "loss": 0.1004, "lr": 1.2514968326249772e-05, "epoch": 13.996149614961496, "percentage": 69.98, "elapsed_time": "5:00:50", "remaining_time": "2:09:03", "throughput": 1487.47, "total_tokens": 26849920} {"current_steps": 127230, "total_steps": 181800, "loss": 0.0085, "lr": 1.2512889035173558e-05, "epoch": 13.996699669966997, "percentage": 69.98, "elapsed_time": "5:00:51", "remaining_time": "2:09:02", "throughput": 1487.47, "total_tokens": 26850976} {"current_steps": 127235, "total_steps": 181800, "loss": 0.0148, "lr": 1.2510809859185043e-05, "epoch": 13.997249724972498, "percentage": 69.99, "elapsed_time": "5:00:52", "remaining_time": "2:09:01", "throughput": 1487.47, "total_tokens": 26851968} {"current_steps": 127240, "total_steps": 181800, "loss": 0.0417, "lr": 1.2508730798303411e-05, "epoch": 13.997799779977997, "percentage": 69.99, "elapsed_time": "5:00:52", "remaining_time": "2:09:00", "throughput": 1487.46, "total_tokens": 26852960} {"current_steps": 127245, "total_steps": 181800, "loss": 0.0073, "lr": 1.2506651852547804e-05, "epoch": 13.998349834983498, "percentage": 69.99, "elapsed_time": "5:00:53", "remaining_time": "2:09:00", "throughput": 1487.46, "total_tokens": 26853984} {"current_steps": 127250, "total_steps": 181800, "loss": 0.149, "lr": 1.2504573021937394e-05, "epoch": 13.998899889989, "percentage": 69.99, "elapsed_time": "5:00:54", "remaining_time": "2:08:59", "throughput": 1487.47, "total_tokens": 26855104} {"current_steps": 127255, "total_steps": 181800, "loss": 0.0161, "lr": 1.2502494306491345e-05, "epoch": 13.999449944994499, "percentage": 70.0, "elapsed_time": "5:00:54", "remaining_time": "2:08:58", "throughput": 1487.47, "total_tokens": 26856160} {"current_steps": 127260, "total_steps": 181800, "loss": 0.0553, "lr": 1.25004157062288e-05, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "5:00:55", "remaining_time": "2:08:58", "throughput": 1487.45, "total_tokens": 26857088} {"current_steps": 127260, "total_steps": 181800, "eval_loss": 0.07163964956998825, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "5:01:32", "remaining_time": "2:09:14", "throughput": 1484.4, "total_tokens": 26857088} {"current_steps": 127265, "total_steps": 181800, "loss": 0.0517, "lr": 1.2498337221168935e-05, "epoch": 14.000550055005501, "percentage": 70.0, "elapsed_time": "5:01:35", "remaining_time": "2:09:14", "throughput": 1484.26, "total_tokens": 26858208} {"current_steps": 127270, "total_steps": 181800, "loss": 0.0822, "lr": 1.2496258851330897e-05, "epoch": 14.001100110011, "percentage": 70.01, "elapsed_time": "5:01:36", "remaining_time": "2:09:13", "throughput": 1484.26, "total_tokens": 26859232} {"current_steps": 127275, "total_steps": 181800, "loss": 0.002, "lr": 1.2494180596733832e-05, "epoch": 14.001650165016502, "percentage": 70.01, "elapsed_time": "5:01:36", "remaining_time": "2:09:12", "throughput": 1484.26, "total_tokens": 26860288} {"current_steps": 127280, "total_steps": 181800, "loss": 0.0051, "lr": 1.2492102457396903e-05, "epoch": 14.002200220022003, "percentage": 70.01, "elapsed_time": "5:01:37", "remaining_time": "2:09:11", "throughput": 1484.26, "total_tokens": 26861312} {"current_steps": 127285, "total_steps": 181800, "loss": 0.0368, "lr": 1.2490024433339265e-05, "epoch": 14.002750275027502, "percentage": 70.01, "elapsed_time": "5:01:38", "remaining_time": "2:09:11", "throughput": 1484.26, "total_tokens": 26862400} {"current_steps": 127290, "total_steps": 181800, "loss": 0.1252, "lr": 1.248794652458008e-05, "epoch": 14.003300330033003, "percentage": 70.02, "elapsed_time": "5:01:38", "remaining_time": "2:09:10", "throughput": 1484.26, "total_tokens": 26863456} {"current_steps": 127295, "total_steps": 181800, "loss": 0.1081, "lr": 1.2485868731138483e-05, "epoch": 14.003850385038504, "percentage": 70.02, "elapsed_time": "5:01:39", "remaining_time": "2:09:09", "throughput": 1484.26, "total_tokens": 26864512} {"current_steps": 127300, "total_steps": 181800, "loss": 0.0016, "lr": 1.2483791053033625e-05, "epoch": 14.004400440044005, "percentage": 70.02, "elapsed_time": "5:01:40", "remaining_time": "2:09:09", "throughput": 1484.27, "total_tokens": 26865600} {"current_steps": 127305, "total_steps": 181800, "loss": 0.004, "lr": 1.2481713490284655e-05, "epoch": 14.004950495049505, "percentage": 70.02, "elapsed_time": "5:01:41", "remaining_time": "2:09:08", "throughput": 1484.25, "total_tokens": 26866592} {"current_steps": 127310, "total_steps": 181800, "loss": 0.0767, "lr": 1.2479636042910728e-05, "epoch": 14.005500550055006, "percentage": 70.03, "elapsed_time": "5:01:41", "remaining_time": "2:09:07", "throughput": 1484.25, "total_tokens": 26867680} {"current_steps": 127315, "total_steps": 181800, "loss": 0.0035, "lr": 1.2477558710930994e-05, "epoch": 14.006050605060507, "percentage": 70.03, "elapsed_time": "5:01:42", "remaining_time": "2:09:07", "throughput": 1484.25, "total_tokens": 26868736} {"current_steps": 127320, "total_steps": 181800, "loss": 0.0024, "lr": 1.2475481494364597e-05, "epoch": 14.006600660066006, "percentage": 70.03, "elapsed_time": "5:01:43", "remaining_time": "2:09:06", "throughput": 1484.25, "total_tokens": 26869792} {"current_steps": 127325, "total_steps": 181800, "loss": 0.1199, "lr": 1.2473404393230664e-05, "epoch": 14.007150715071507, "percentage": 70.04, "elapsed_time": "5:01:43", "remaining_time": "2:09:05", "throughput": 1484.26, "total_tokens": 26870944} {"current_steps": 127330, "total_steps": 181800, "loss": 0.0481, "lr": 1.2471327407548362e-05, "epoch": 14.007700770077008, "percentage": 70.04, "elapsed_time": "5:01:44", "remaining_time": "2:09:04", "throughput": 1484.26, "total_tokens": 26871968} {"current_steps": 127335, "total_steps": 181800, "loss": 0.003, "lr": 1.2469250537336813e-05, "epoch": 14.008250825082508, "percentage": 70.04, "elapsed_time": "5:01:45", "remaining_time": "2:09:04", "throughput": 1484.25, "total_tokens": 26872960} {"current_steps": 127340, "total_steps": 181800, "loss": 0.0043, "lr": 1.2467173782615171e-05, "epoch": 14.008800880088009, "percentage": 70.04, "elapsed_time": "5:01:46", "remaining_time": "2:09:03", "throughput": 1484.25, "total_tokens": 26873920} {"current_steps": 127345, "total_steps": 181800, "loss": 0.0964, "lr": 1.2465097143402582e-05, "epoch": 14.00935093509351, "percentage": 70.05, "elapsed_time": "5:01:46", "remaining_time": "2:09:02", "throughput": 1484.25, "total_tokens": 26875040} {"current_steps": 127350, "total_steps": 181800, "loss": 0.027, "lr": 1.2463020619718172e-05, "epoch": 14.009900990099009, "percentage": 70.05, "elapsed_time": "5:01:47", "remaining_time": "2:09:02", "throughput": 1484.25, "total_tokens": 26876032} {"current_steps": 127355, "total_steps": 181800, "loss": 0.0369, "lr": 1.2460944211581092e-05, "epoch": 14.01045104510451, "percentage": 70.05, "elapsed_time": "5:01:48", "remaining_time": "2:09:01", "throughput": 1484.25, "total_tokens": 26876992} {"current_steps": 127360, "total_steps": 181800, "loss": 0.0132, "lr": 1.2458867919010461e-05, "epoch": 14.011001100110011, "percentage": 70.06, "elapsed_time": "5:01:48", "remaining_time": "2:09:00", "throughput": 1484.25, "total_tokens": 26877984} {"current_steps": 127365, "total_steps": 181800, "loss": 0.0113, "lr": 1.2456791742025429e-05, "epoch": 14.011551155115512, "percentage": 70.06, "elapsed_time": "5:01:49", "remaining_time": "2:08:59", "throughput": 1484.25, "total_tokens": 26879008} {"current_steps": 127370, "total_steps": 181800, "loss": 0.0077, "lr": 1.2454715680645138e-05, "epoch": 14.012101210121012, "percentage": 70.06, "elapsed_time": "5:01:50", "remaining_time": "2:08:59", "throughput": 1484.25, "total_tokens": 26880064} {"current_steps": 127375, "total_steps": 181800, "loss": 0.0337, "lr": 1.2452639734888702e-05, "epoch": 14.012651265126513, "percentage": 70.06, "elapsed_time": "5:01:50", "remaining_time": "2:08:58", "throughput": 1484.25, "total_tokens": 26881120} {"current_steps": 127380, "total_steps": 181800, "loss": 0.0523, "lr": 1.2450563904775276e-05, "epoch": 14.013201320132014, "percentage": 70.07, "elapsed_time": "5:01:51", "remaining_time": "2:08:57", "throughput": 1484.25, "total_tokens": 26882176} {"current_steps": 127385, "total_steps": 181800, "loss": 0.0028, "lr": 1.244848819032397e-05, "epoch": 14.013751375137513, "percentage": 70.07, "elapsed_time": "5:01:52", "remaining_time": "2:08:57", "throughput": 1484.25, "total_tokens": 26883200} {"current_steps": 127390, "total_steps": 181800, "loss": 0.0313, "lr": 1.2446412591553935e-05, "epoch": 14.014301430143014, "percentage": 70.07, "elapsed_time": "5:01:53", "remaining_time": "2:08:56", "throughput": 1484.25, "total_tokens": 26884256} {"current_steps": 127395, "total_steps": 181800, "loss": 0.0027, "lr": 1.2444337108484283e-05, "epoch": 14.014851485148515, "percentage": 70.07, "elapsed_time": "5:01:53", "remaining_time": "2:08:55", "throughput": 1484.25, "total_tokens": 26885312} {"current_steps": 127400, "total_steps": 181800, "loss": 0.0395, "lr": 1.244226174113415e-05, "epoch": 14.015401540154015, "percentage": 70.08, "elapsed_time": "5:01:54", "remaining_time": "2:08:54", "throughput": 1484.25, "total_tokens": 26886336} {"current_steps": 127405, "total_steps": 181800, "loss": 0.11, "lr": 1.2440186489522676e-05, "epoch": 14.015951595159516, "percentage": 70.08, "elapsed_time": "5:01:55", "remaining_time": "2:08:54", "throughput": 1484.25, "total_tokens": 26887392} {"current_steps": 127410, "total_steps": 181800, "loss": 0.0026, "lr": 1.2438111353668973e-05, "epoch": 14.016501650165017, "percentage": 70.08, "elapsed_time": "5:01:55", "remaining_time": "2:08:53", "throughput": 1484.25, "total_tokens": 26888384} {"current_steps": 127415, "total_steps": 181800, "loss": 0.0782, "lr": 1.2436036333592164e-05, "epoch": 14.017051705170518, "percentage": 70.09, "elapsed_time": "5:01:56", "remaining_time": "2:08:52", "throughput": 1484.25, "total_tokens": 26889440} {"current_steps": 127420, "total_steps": 181800, "loss": 0.044, "lr": 1.2433961429311378e-05, "epoch": 14.017601760176017, "percentage": 70.09, "elapsed_time": "5:01:57", "remaining_time": "2:08:52", "throughput": 1484.25, "total_tokens": 26890496} {"current_steps": 127425, "total_steps": 181800, "loss": 0.0921, "lr": 1.2431886640845738e-05, "epoch": 14.018151815181518, "percentage": 70.09, "elapsed_time": "5:01:57", "remaining_time": "2:08:51", "throughput": 1484.25, "total_tokens": 26891520} {"current_steps": 127430, "total_steps": 181800, "loss": 0.0068, "lr": 1.2429811968214377e-05, "epoch": 14.01870187018702, "percentage": 70.09, "elapsed_time": "5:01:58", "remaining_time": "2:08:50", "throughput": 1484.25, "total_tokens": 26892544} {"current_steps": 127435, "total_steps": 181800, "loss": 0.0106, "lr": 1.242773741143641e-05, "epoch": 14.019251925192519, "percentage": 70.1, "elapsed_time": "5:01:59", "remaining_time": "2:08:49", "throughput": 1484.26, "total_tokens": 26893664} {"current_steps": 127440, "total_steps": 181800, "loss": 0.0569, "lr": 1.2425662970530947e-05, "epoch": 14.01980198019802, "percentage": 70.1, "elapsed_time": "5:01:59", "remaining_time": "2:08:49", "throughput": 1484.26, "total_tokens": 26894720} {"current_steps": 127445, "total_steps": 181800, "loss": 0.0031, "lr": 1.242358864551712e-05, "epoch": 14.020352035203521, "percentage": 70.1, "elapsed_time": "5:02:00", "remaining_time": "2:08:48", "throughput": 1484.26, "total_tokens": 26895712} {"current_steps": 127450, "total_steps": 181800, "loss": 0.0032, "lr": 1.2421514436414034e-05, "epoch": 14.02090209020902, "percentage": 70.1, "elapsed_time": "5:02:01", "remaining_time": "2:08:47", "throughput": 1484.26, "total_tokens": 26896736} {"current_steps": 127455, "total_steps": 181800, "loss": 0.0229, "lr": 1.2419440343240813e-05, "epoch": 14.021452145214521, "percentage": 70.11, "elapsed_time": "5:02:02", "remaining_time": "2:08:46", "throughput": 1484.26, "total_tokens": 26897792} {"current_steps": 127460, "total_steps": 181800, "loss": 0.003, "lr": 1.2417366366016583e-05, "epoch": 14.022002200220022, "percentage": 70.11, "elapsed_time": "5:02:02", "remaining_time": "2:08:46", "throughput": 1484.26, "total_tokens": 26898880} {"current_steps": 127465, "total_steps": 181800, "loss": 0.161, "lr": 1.241529250476044e-05, "epoch": 14.022552255225522, "percentage": 70.11, "elapsed_time": "5:02:03", "remaining_time": "2:08:45", "throughput": 1484.26, "total_tokens": 26899936} {"current_steps": 127470, "total_steps": 181800, "loss": 0.1456, "lr": 1.2413218759491519e-05, "epoch": 14.023102310231023, "percentage": 70.12, "elapsed_time": "5:02:04", "remaining_time": "2:08:44", "throughput": 1484.27, "total_tokens": 26900992} {"current_steps": 127475, "total_steps": 181800, "loss": 0.0057, "lr": 1.2411145130228907e-05, "epoch": 14.023652365236524, "percentage": 70.12, "elapsed_time": "5:02:04", "remaining_time": "2:08:44", "throughput": 1484.27, "total_tokens": 26902112} {"current_steps": 127480, "total_steps": 181800, "loss": 0.074, "lr": 1.2409071616991733e-05, "epoch": 14.024202420242025, "percentage": 70.12, "elapsed_time": "5:02:05", "remaining_time": "2:08:43", "throughput": 1484.27, "total_tokens": 26903168} {"current_steps": 127485, "total_steps": 181800, "loss": 0.1068, "lr": 1.2406998219799113e-05, "epoch": 14.024752475247524, "percentage": 70.12, "elapsed_time": "5:02:06", "remaining_time": "2:08:42", "throughput": 1484.28, "total_tokens": 26904224} {"current_steps": 127490, "total_steps": 181800, "loss": 0.0423, "lr": 1.240492493867014e-05, "epoch": 14.025302530253025, "percentage": 70.13, "elapsed_time": "5:02:06", "remaining_time": "2:08:41", "throughput": 1484.28, "total_tokens": 26905344} {"current_steps": 127495, "total_steps": 181800, "loss": 0.0054, "lr": 1.2402851773623936e-05, "epoch": 14.025852585258527, "percentage": 70.13, "elapsed_time": "5:02:07", "remaining_time": "2:08:41", "throughput": 1484.28, "total_tokens": 26906400} {"current_steps": 127500, "total_steps": 181800, "loss": 0.0047, "lr": 1.2400778724679595e-05, "epoch": 14.026402640264026, "percentage": 70.13, "elapsed_time": "5:02:08", "remaining_time": "2:08:40", "throughput": 1484.29, "total_tokens": 26907520} {"current_steps": 127505, "total_steps": 181800, "loss": 0.0121, "lr": 1.2398705791856241e-05, "epoch": 14.026952695269527, "percentage": 70.13, "elapsed_time": "5:02:08", "remaining_time": "2:08:39", "throughput": 1484.29, "total_tokens": 26908544} {"current_steps": 127510, "total_steps": 181800, "loss": 0.0102, "lr": 1.2396632975172959e-05, "epoch": 14.027502750275028, "percentage": 70.14, "elapsed_time": "5:02:09", "remaining_time": "2:08:39", "throughput": 1484.29, "total_tokens": 26909568} {"current_steps": 127515, "total_steps": 181800, "loss": 0.0193, "lr": 1.2394560274648862e-05, "epoch": 14.028052805280527, "percentage": 70.14, "elapsed_time": "5:02:10", "remaining_time": "2:08:38", "throughput": 1484.29, "total_tokens": 26910560} {"current_steps": 127520, "total_steps": 181800, "loss": 0.0028, "lr": 1.2392487690303065e-05, "epoch": 14.028602860286028, "percentage": 70.14, "elapsed_time": "5:02:11", "remaining_time": "2:08:37", "throughput": 1484.28, "total_tokens": 26911552} {"current_steps": 127525, "total_steps": 181800, "loss": 0.0012, "lr": 1.239041522215465e-05, "epoch": 14.02915291529153, "percentage": 70.15, "elapsed_time": "5:02:11", "remaining_time": "2:08:36", "throughput": 1484.28, "total_tokens": 26912512} {"current_steps": 127530, "total_steps": 181800, "loss": 0.0043, "lr": 1.2388342870222735e-05, "epoch": 14.029702970297029, "percentage": 70.15, "elapsed_time": "5:02:12", "remaining_time": "2:08:36", "throughput": 1484.28, "total_tokens": 26913568} {"current_steps": 127535, "total_steps": 181800, "loss": 0.1191, "lr": 1.2386270634526404e-05, "epoch": 14.03025302530253, "percentage": 70.15, "elapsed_time": "5:02:13", "remaining_time": "2:08:35", "throughput": 1484.28, "total_tokens": 26914528} {"current_steps": 127540, "total_steps": 181800, "loss": 0.0035, "lr": 1.2384198515084764e-05, "epoch": 14.030803080308031, "percentage": 70.15, "elapsed_time": "5:02:13", "remaining_time": "2:08:34", "throughput": 1484.28, "total_tokens": 26915552} {"current_steps": 127545, "total_steps": 181800, "loss": 0.0019, "lr": 1.2382126511916922e-05, "epoch": 14.031353135313532, "percentage": 70.16, "elapsed_time": "5:02:14", "remaining_time": "2:08:34", "throughput": 1484.28, "total_tokens": 26916544} {"current_steps": 127550, "total_steps": 181800, "loss": 0.0054, "lr": 1.2380054625041954e-05, "epoch": 14.031903190319031, "percentage": 70.16, "elapsed_time": "5:02:15", "remaining_time": "2:08:33", "throughput": 1484.28, "total_tokens": 26917632} {"current_steps": 127555, "total_steps": 181800, "loss": 0.0115, "lr": 1.2377982854478978e-05, "epoch": 14.032453245324533, "percentage": 70.16, "elapsed_time": "5:02:15", "remaining_time": "2:08:32", "throughput": 1484.28, "total_tokens": 26918720} {"current_steps": 127560, "total_steps": 181800, "loss": 0.0796, "lr": 1.2375911200247079e-05, "epoch": 14.033003300330034, "percentage": 70.17, "elapsed_time": "5:02:16", "remaining_time": "2:08:31", "throughput": 1484.28, "total_tokens": 26919776} {"current_steps": 127565, "total_steps": 181800, "loss": 0.0462, "lr": 1.2373839662365336e-05, "epoch": 14.033553355335533, "percentage": 70.17, "elapsed_time": "5:02:17", "remaining_time": "2:08:31", "throughput": 1484.28, "total_tokens": 26920768} {"current_steps": 127570, "total_steps": 181800, "loss": 0.007, "lr": 1.2371768240852858e-05, "epoch": 14.034103410341034, "percentage": 70.17, "elapsed_time": "5:02:17", "remaining_time": "2:08:30", "throughput": 1484.28, "total_tokens": 26921856} {"current_steps": 127575, "total_steps": 181800, "loss": 0.0289, "lr": 1.2369696935728729e-05, "epoch": 14.034653465346535, "percentage": 70.17, "elapsed_time": "5:02:18", "remaining_time": "2:08:29", "throughput": 1484.29, "total_tokens": 26922976} {"current_steps": 127580, "total_steps": 181800, "loss": 0.0449, "lr": 1.2367625747012054e-05, "epoch": 14.035203520352034, "percentage": 70.18, "elapsed_time": "5:02:19", "remaining_time": "2:08:28", "throughput": 1484.29, "total_tokens": 26924032} {"current_steps": 127585, "total_steps": 181800, "loss": 0.0228, "lr": 1.236555467472191e-05, "epoch": 14.035753575357536, "percentage": 70.18, "elapsed_time": "5:02:19", "remaining_time": "2:08:28", "throughput": 1484.29, "total_tokens": 26925024} {"current_steps": 127590, "total_steps": 181800, "loss": 0.0065, "lr": 1.2363483718877377e-05, "epoch": 14.036303630363037, "percentage": 70.18, "elapsed_time": "5:02:20", "remaining_time": "2:08:27", "throughput": 1484.29, "total_tokens": 26926048} {"current_steps": 127595, "total_steps": 181800, "loss": 0.0028, "lr": 1.236141287949755e-05, "epoch": 14.036853685368538, "percentage": 70.18, "elapsed_time": "5:02:21", "remaining_time": "2:08:26", "throughput": 1484.29, "total_tokens": 26927040} {"current_steps": 127600, "total_steps": 181800, "loss": 0.0814, "lr": 1.2359342156601517e-05, "epoch": 14.037403740374037, "percentage": 70.19, "elapsed_time": "5:02:22", "remaining_time": "2:08:26", "throughput": 1484.29, "total_tokens": 26928128} {"current_steps": 127605, "total_steps": 181800, "loss": 0.1182, "lr": 1.235727155020837e-05, "epoch": 14.037953795379538, "percentage": 70.19, "elapsed_time": "5:02:22", "remaining_time": "2:08:25", "throughput": 1484.29, "total_tokens": 26929152} {"current_steps": 127610, "total_steps": 181800, "loss": 0.0922, "lr": 1.2355201060337187e-05, "epoch": 14.03850385038504, "percentage": 70.19, "elapsed_time": "5:02:23", "remaining_time": "2:08:24", "throughput": 1484.29, "total_tokens": 26930240} {"current_steps": 127615, "total_steps": 181800, "loss": 0.0066, "lr": 1.2353130687007037e-05, "epoch": 14.039053905390539, "percentage": 70.2, "elapsed_time": "5:02:24", "remaining_time": "2:08:23", "throughput": 1484.3, "total_tokens": 26931296} {"current_steps": 127620, "total_steps": 181800, "loss": 0.0092, "lr": 1.2351060430237024e-05, "epoch": 14.03960396039604, "percentage": 70.2, "elapsed_time": "5:02:24", "remaining_time": "2:08:23", "throughput": 1484.3, "total_tokens": 26932352} {"current_steps": 127625, "total_steps": 181800, "loss": 0.0172, "lr": 1.2348990290046206e-05, "epoch": 14.04015401540154, "percentage": 70.2, "elapsed_time": "5:02:25", "remaining_time": "2:08:22", "throughput": 1484.3, "total_tokens": 26933376} {"current_steps": 127630, "total_steps": 181800, "loss": 0.0357, "lr": 1.2346920266453673e-05, "epoch": 14.04070407040704, "percentage": 70.2, "elapsed_time": "5:02:26", "remaining_time": "2:08:21", "throughput": 1484.3, "total_tokens": 26934432} {"current_steps": 127635, "total_steps": 181800, "loss": 0.1033, "lr": 1.2344850359478515e-05, "epoch": 14.041254125412541, "percentage": 70.21, "elapsed_time": "5:02:26", "remaining_time": "2:08:21", "throughput": 1484.3, "total_tokens": 26935456} {"current_steps": 127640, "total_steps": 181800, "loss": 0.0167, "lr": 1.2342780569139793e-05, "epoch": 14.041804180418042, "percentage": 70.21, "elapsed_time": "5:02:27", "remaining_time": "2:08:20", "throughput": 1484.3, "total_tokens": 26936544} {"current_steps": 127645, "total_steps": 181800, "loss": 0.0018, "lr": 1.2340710895456595e-05, "epoch": 14.042354235423542, "percentage": 70.21, "elapsed_time": "5:02:28", "remaining_time": "2:08:19", "throughput": 1484.3, "total_tokens": 26937600} {"current_steps": 127650, "total_steps": 181800, "loss": 0.0031, "lr": 1.233864133844799e-05, "epoch": 14.042904290429043, "percentage": 70.21, "elapsed_time": "5:02:28", "remaining_time": "2:08:18", "throughput": 1484.3, "total_tokens": 26938624} {"current_steps": 127655, "total_steps": 181800, "loss": 0.0105, "lr": 1.2336571898133034e-05, "epoch": 14.043454345434544, "percentage": 70.22, "elapsed_time": "5:02:29", "remaining_time": "2:08:18", "throughput": 1484.3, "total_tokens": 26939616} {"current_steps": 127660, "total_steps": 181800, "loss": 0.006, "lr": 1.2334502574530838e-05, "epoch": 14.044004400440045, "percentage": 70.22, "elapsed_time": "5:02:30", "remaining_time": "2:08:17", "throughput": 1484.3, "total_tokens": 26940672} {"current_steps": 127665, "total_steps": 181800, "loss": 0.008, "lr": 1.2332433367660442e-05, "epoch": 14.044554455445544, "percentage": 70.22, "elapsed_time": "5:02:31", "remaining_time": "2:08:16", "throughput": 1484.31, "total_tokens": 26941728} {"current_steps": 127670, "total_steps": 181800, "loss": 0.005, "lr": 1.233036427754094e-05, "epoch": 14.045104510451045, "percentage": 70.23, "elapsed_time": "5:02:31", "remaining_time": "2:08:16", "throughput": 1484.31, "total_tokens": 26942784} {"current_steps": 127675, "total_steps": 181800, "loss": 0.0076, "lr": 1.2328295304191393e-05, "epoch": 14.045654565456546, "percentage": 70.23, "elapsed_time": "5:02:32", "remaining_time": "2:08:15", "throughput": 1484.31, "total_tokens": 26943840} {"current_steps": 127680, "total_steps": 181800, "loss": 0.0328, "lr": 1.2326226447630856e-05, "epoch": 14.046204620462046, "percentage": 70.23, "elapsed_time": "5:02:33", "remaining_time": "2:08:14", "throughput": 1484.31, "total_tokens": 26944896} {"current_steps": 127685, "total_steps": 181800, "loss": 0.01, "lr": 1.232415770787841e-05, "epoch": 14.046754675467547, "percentage": 70.23, "elapsed_time": "5:02:33", "remaining_time": "2:08:13", "throughput": 1484.31, "total_tokens": 26945984} {"current_steps": 127690, "total_steps": 181800, "loss": 0.0406, "lr": 1.2322089084953117e-05, "epoch": 14.047304730473048, "percentage": 70.24, "elapsed_time": "5:02:34", "remaining_time": "2:08:13", "throughput": 1484.31, "total_tokens": 26946976} {"current_steps": 127695, "total_steps": 181800, "loss": 0.073, "lr": 1.2320020578874058e-05, "epoch": 14.047854785478547, "percentage": 70.24, "elapsed_time": "5:02:35", "remaining_time": "2:08:12", "throughput": 1484.31, "total_tokens": 26948000} {"current_steps": 127700, "total_steps": 181800, "loss": 0.0034, "lr": 1.2317952189660284e-05, "epoch": 14.048404840484048, "percentage": 70.24, "elapsed_time": "5:02:35", "remaining_time": "2:08:11", "throughput": 1484.31, "total_tokens": 26949024} {"current_steps": 127705, "total_steps": 181800, "loss": 0.0027, "lr": 1.2315883917330848e-05, "epoch": 14.04895489548955, "percentage": 70.24, "elapsed_time": "5:02:36", "remaining_time": "2:08:11", "throughput": 1484.31, "total_tokens": 26950080} {"current_steps": 127710, "total_steps": 181800, "loss": 0.002, "lr": 1.2313815761904835e-05, "epoch": 14.049504950495049, "percentage": 70.25, "elapsed_time": "5:02:37", "remaining_time": "2:08:10", "throughput": 1484.32, "total_tokens": 26951136} {"current_steps": 127715, "total_steps": 181800, "loss": 0.0495, "lr": 1.2311747723401277e-05, "epoch": 14.05005500550055, "percentage": 70.25, "elapsed_time": "5:02:37", "remaining_time": "2:08:09", "throughput": 1484.32, "total_tokens": 26952256} {"current_steps": 127720, "total_steps": 181800, "loss": 0.0115, "lr": 1.2309679801839266e-05, "epoch": 14.05060506050605, "percentage": 70.25, "elapsed_time": "5:02:38", "remaining_time": "2:08:08", "throughput": 1484.32, "total_tokens": 26953312} {"current_steps": 127725, "total_steps": 181800, "loss": 0.0143, "lr": 1.230761199723785e-05, "epoch": 14.051155115511552, "percentage": 70.26, "elapsed_time": "5:02:39", "remaining_time": "2:08:08", "throughput": 1484.32, "total_tokens": 26954368} {"current_steps": 127730, "total_steps": 181800, "loss": 0.005, "lr": 1.2305544309616077e-05, "epoch": 14.051705170517051, "percentage": 70.26, "elapsed_time": "5:02:40", "remaining_time": "2:08:07", "throughput": 1484.33, "total_tokens": 26955424} {"current_steps": 127735, "total_steps": 181800, "loss": 0.0109, "lr": 1.2303476738993017e-05, "epoch": 14.052255225522552, "percentage": 70.26, "elapsed_time": "5:02:40", "remaining_time": "2:08:06", "throughput": 1484.32, "total_tokens": 26956448} {"current_steps": 127740, "total_steps": 181800, "loss": 0.0997, "lr": 1.2301409285387711e-05, "epoch": 14.052805280528053, "percentage": 70.26, "elapsed_time": "5:02:41", "remaining_time": "2:08:05", "throughput": 1484.33, "total_tokens": 26957504} {"current_steps": 127745, "total_steps": 181800, "loss": 0.0043, "lr": 1.2299341948819221e-05, "epoch": 14.053355335533553, "percentage": 70.27, "elapsed_time": "5:02:42", "remaining_time": "2:08:05", "throughput": 1484.33, "total_tokens": 26958528} {"current_steps": 127750, "total_steps": 181800, "loss": 0.0022, "lr": 1.229727472930661e-05, "epoch": 14.053905390539054, "percentage": 70.27, "elapsed_time": "5:02:42", "remaining_time": "2:08:04", "throughput": 1484.33, "total_tokens": 26959616} {"current_steps": 127755, "total_steps": 181800, "loss": 0.0276, "lr": 1.2295207626868916e-05, "epoch": 14.054455445544555, "percentage": 70.27, "elapsed_time": "5:02:43", "remaining_time": "2:08:03", "throughput": 1484.33, "total_tokens": 26960704} {"current_steps": 127760, "total_steps": 181800, "loss": 0.0554, "lr": 1.2293140641525206e-05, "epoch": 14.055005500550054, "percentage": 70.28, "elapsed_time": "5:02:44", "remaining_time": "2:08:03", "throughput": 1484.34, "total_tokens": 26961792} {"current_steps": 127765, "total_steps": 181800, "loss": 0.0079, "lr": 1.2291073773294512e-05, "epoch": 14.055555555555555, "percentage": 70.28, "elapsed_time": "5:02:44", "remaining_time": "2:08:02", "throughput": 1484.34, "total_tokens": 26962848} {"current_steps": 127770, "total_steps": 181800, "loss": 0.0021, "lr": 1.22890070221959e-05, "epoch": 14.056105610561056, "percentage": 70.28, "elapsed_time": "5:02:45", "remaining_time": "2:08:01", "throughput": 1484.34, "total_tokens": 26963840} {"current_steps": 127775, "total_steps": 181800, "loss": 0.003, "lr": 1.2286940388248402e-05, "epoch": 14.056655665566556, "percentage": 70.28, "elapsed_time": "5:02:46", "remaining_time": "2:08:00", "throughput": 1484.34, "total_tokens": 26964832} {"current_steps": 127780, "total_steps": 181800, "loss": 0.0032, "lr": 1.2284873871471075e-05, "epoch": 14.057205720572057, "percentage": 70.29, "elapsed_time": "5:02:46", "remaining_time": "2:08:00", "throughput": 1484.34, "total_tokens": 26965888} {"current_steps": 127785, "total_steps": 181800, "loss": 0.0013, "lr": 1.2282807471882976e-05, "epoch": 14.057755775577558, "percentage": 70.29, "elapsed_time": "5:02:47", "remaining_time": "2:07:59", "throughput": 1484.34, "total_tokens": 26966944} {"current_steps": 127790, "total_steps": 181800, "loss": 0.0537, "lr": 1.2280741189503125e-05, "epoch": 14.058305830583059, "percentage": 70.29, "elapsed_time": "5:02:48", "remaining_time": "2:07:58", "throughput": 1484.34, "total_tokens": 26968000} {"current_steps": 127795, "total_steps": 181800, "loss": 0.0109, "lr": 1.2278675024350591e-05, "epoch": 14.058855885588558, "percentage": 70.29, "elapsed_time": "5:02:49", "remaining_time": "2:07:58", "throughput": 1484.34, "total_tokens": 26969056} {"current_steps": 127800, "total_steps": 181800, "loss": 0.0084, "lr": 1.2276608976444395e-05, "epoch": 14.05940594059406, "percentage": 70.3, "elapsed_time": "5:02:49", "remaining_time": "2:07:57", "throughput": 1484.35, "total_tokens": 26970112} {"current_steps": 127805, "total_steps": 181800, "loss": 0.0016, "lr": 1.2274543045803588e-05, "epoch": 14.05995599559956, "percentage": 70.3, "elapsed_time": "5:02:50", "remaining_time": "2:07:56", "throughput": 1484.35, "total_tokens": 26971136} {"current_steps": 127810, "total_steps": 181800, "loss": 0.2352, "lr": 1.2272477232447222e-05, "epoch": 14.06050605060506, "percentage": 70.3, "elapsed_time": "5:02:51", "remaining_time": "2:07:55", "throughput": 1484.35, "total_tokens": 26972160} {"current_steps": 127815, "total_steps": 181800, "loss": 0.1142, "lr": 1.2270411536394324e-05, "epoch": 14.061056105610561, "percentage": 70.31, "elapsed_time": "5:02:51", "remaining_time": "2:07:55", "throughput": 1484.35, "total_tokens": 26973248} {"current_steps": 127820, "total_steps": 181800, "loss": 0.0011, "lr": 1.2268345957663926e-05, "epoch": 14.061606160616062, "percentage": 70.31, "elapsed_time": "5:02:52", "remaining_time": "2:07:54", "throughput": 1484.35, "total_tokens": 26974304} {"current_steps": 127825, "total_steps": 181800, "loss": 0.0117, "lr": 1.2266280496275084e-05, "epoch": 14.062156215621561, "percentage": 70.31, "elapsed_time": "5:02:53", "remaining_time": "2:07:53", "throughput": 1484.35, "total_tokens": 26975264} {"current_steps": 127830, "total_steps": 181800, "loss": 0.0168, "lr": 1.2264215152246816e-05, "epoch": 14.062706270627062, "percentage": 70.31, "elapsed_time": "5:02:53", "remaining_time": "2:07:53", "throughput": 1484.35, "total_tokens": 26976288} {"current_steps": 127835, "total_steps": 181800, "loss": 0.0893, "lr": 1.2262149925598165e-05, "epoch": 14.063256325632564, "percentage": 70.32, "elapsed_time": "5:02:54", "remaining_time": "2:07:52", "throughput": 1484.35, "total_tokens": 26977408} {"current_steps": 127840, "total_steps": 181800, "loss": 0.0266, "lr": 1.2260084816348177e-05, "epoch": 14.063806380638065, "percentage": 70.32, "elapsed_time": "5:02:55", "remaining_time": "2:07:51", "throughput": 1484.35, "total_tokens": 26978464} {"current_steps": 127845, "total_steps": 181800, "loss": 0.0164, "lr": 1.2258019824515863e-05, "epoch": 14.064356435643564, "percentage": 70.32, "elapsed_time": "5:02:55", "remaining_time": "2:07:50", "throughput": 1484.35, "total_tokens": 26979488} {"current_steps": 127850, "total_steps": 181800, "loss": 0.0053, "lr": 1.2255954950120274e-05, "epoch": 14.064906490649065, "percentage": 70.32, "elapsed_time": "5:02:56", "remaining_time": "2:07:50", "throughput": 1484.36, "total_tokens": 26980544} {"current_steps": 127855, "total_steps": 181800, "loss": 0.0032, "lr": 1.2253890193180425e-05, "epoch": 14.065456545654566, "percentage": 70.33, "elapsed_time": "5:02:57", "remaining_time": "2:07:49", "throughput": 1484.36, "total_tokens": 26981664} {"current_steps": 127860, "total_steps": 181800, "loss": 0.0062, "lr": 1.2251825553715355e-05, "epoch": 14.066006600660065, "percentage": 70.33, "elapsed_time": "5:02:57", "remaining_time": "2:07:48", "throughput": 1484.36, "total_tokens": 26982720} {"current_steps": 127865, "total_steps": 181800, "loss": 0.0409, "lr": 1.22497610317441e-05, "epoch": 14.066556655665567, "percentage": 70.33, "elapsed_time": "5:02:58", "remaining_time": "2:07:47", "throughput": 1484.37, "total_tokens": 26983776} {"current_steps": 127870, "total_steps": 181800, "loss": 0.0027, "lr": 1.2247696627285669e-05, "epoch": 14.067106710671068, "percentage": 70.34, "elapsed_time": "5:02:59", "remaining_time": "2:07:47", "throughput": 1484.37, "total_tokens": 26984832} {"current_steps": 127875, "total_steps": 181800, "loss": 0.0059, "lr": 1.2245632340359108e-05, "epoch": 14.067656765676567, "percentage": 70.34, "elapsed_time": "5:03:00", "remaining_time": "2:07:46", "throughput": 1484.37, "total_tokens": 26985856} {"current_steps": 127880, "total_steps": 181800, "loss": 0.0048, "lr": 1.2243568170983428e-05, "epoch": 14.068206820682068, "percentage": 70.34, "elapsed_time": "5:03:00", "remaining_time": "2:07:45", "throughput": 1484.37, "total_tokens": 26986976} {"current_steps": 127885, "total_steps": 181800, "loss": 0.0366, "lr": 1.2241504119177665e-05, "epoch": 14.06875687568757, "percentage": 70.34, "elapsed_time": "5:03:01", "remaining_time": "2:07:45", "throughput": 1484.37, "total_tokens": 26988000} {"current_steps": 127890, "total_steps": 181800, "loss": 0.0121, "lr": 1.223944018496083e-05, "epoch": 14.069306930693068, "percentage": 70.35, "elapsed_time": "5:03:02", "remaining_time": "2:07:44", "throughput": 1484.37, "total_tokens": 26989056} {"current_steps": 127895, "total_steps": 181800, "loss": 0.0013, "lr": 1.2237376368351949e-05, "epoch": 14.06985698569857, "percentage": 70.35, "elapsed_time": "5:03:02", "remaining_time": "2:07:43", "throughput": 1484.38, "total_tokens": 26990144} {"current_steps": 127900, "total_steps": 181800, "loss": 0.0034, "lr": 1.2235312669370056e-05, "epoch": 14.07040704070407, "percentage": 70.35, "elapsed_time": "5:03:03", "remaining_time": "2:07:42", "throughput": 1484.38, "total_tokens": 26991200} {"current_steps": 127905, "total_steps": 181800, "loss": 0.0381, "lr": 1.2233249088034151e-05, "epoch": 14.070957095709572, "percentage": 70.35, "elapsed_time": "5:03:04", "remaining_time": "2:07:42", "throughput": 1484.38, "total_tokens": 26992224} {"current_steps": 127910, "total_steps": 181800, "loss": 0.0253, "lr": 1.2231185624363272e-05, "epoch": 14.071507150715071, "percentage": 70.36, "elapsed_time": "5:03:04", "remaining_time": "2:07:41", "throughput": 1484.38, "total_tokens": 26993184} {"current_steps": 127915, "total_steps": 181800, "loss": 0.2294, "lr": 1.222912227837642e-05, "epoch": 14.072057205720572, "percentage": 70.36, "elapsed_time": "5:03:05", "remaining_time": "2:07:40", "throughput": 1484.38, "total_tokens": 26994208} {"current_steps": 127920, "total_steps": 181800, "loss": 0.0099, "lr": 1.222705905009262e-05, "epoch": 14.072607260726073, "percentage": 70.36, "elapsed_time": "5:03:06", "remaining_time": "2:07:40", "throughput": 1484.38, "total_tokens": 26995328} {"current_steps": 127925, "total_steps": 181800, "loss": 0.0243, "lr": 1.2224995939530897e-05, "epoch": 14.073157315731573, "percentage": 70.37, "elapsed_time": "5:03:06", "remaining_time": "2:07:39", "throughput": 1484.38, "total_tokens": 26996384} {"current_steps": 127930, "total_steps": 181800, "loss": 0.0073, "lr": 1.2222932946710247e-05, "epoch": 14.073707370737074, "percentage": 70.37, "elapsed_time": "5:03:07", "remaining_time": "2:07:38", "throughput": 1484.39, "total_tokens": 26997472} {"current_steps": 127935, "total_steps": 181800, "loss": 0.004, "lr": 1.2220870071649704e-05, "epoch": 14.074257425742575, "percentage": 70.37, "elapsed_time": "5:03:08", "remaining_time": "2:07:37", "throughput": 1484.38, "total_tokens": 26998464} {"current_steps": 127940, "total_steps": 181800, "loss": 0.0012, "lr": 1.2218807314368267e-05, "epoch": 14.074807480748074, "percentage": 70.37, "elapsed_time": "5:03:09", "remaining_time": "2:07:37", "throughput": 1484.39, "total_tokens": 26999520} {"current_steps": 127945, "total_steps": 181800, "loss": 0.0047, "lr": 1.2216744674884942e-05, "epoch": 14.075357535753575, "percentage": 70.38, "elapsed_time": "5:03:09", "remaining_time": "2:07:36", "throughput": 1484.39, "total_tokens": 27000608} {"current_steps": 127950, "total_steps": 181800, "loss": 0.0078, "lr": 1.2214682153218745e-05, "epoch": 14.075907590759076, "percentage": 70.38, "elapsed_time": "5:03:10", "remaining_time": "2:07:35", "throughput": 1484.39, "total_tokens": 27001696} {"current_steps": 127955, "total_steps": 181800, "loss": 0.0037, "lr": 1.2212619749388691e-05, "epoch": 14.076457645764576, "percentage": 70.38, "elapsed_time": "5:03:11", "remaining_time": "2:07:35", "throughput": 1484.39, "total_tokens": 27002752} {"current_steps": 127960, "total_steps": 181800, "loss": 0.088, "lr": 1.221055746341379e-05, "epoch": 14.077007700770077, "percentage": 70.39, "elapsed_time": "5:03:11", "remaining_time": "2:07:34", "throughput": 1484.39, "total_tokens": 27003776} {"current_steps": 127965, "total_steps": 181800, "loss": 0.0254, "lr": 1.2208495295313046e-05, "epoch": 14.077557755775578, "percentage": 70.39, "elapsed_time": "5:03:12", "remaining_time": "2:07:33", "throughput": 1484.4, "total_tokens": 27004864} {"current_steps": 127970, "total_steps": 181800, "loss": 0.0076, "lr": 1.2206433245105456e-05, "epoch": 14.078107810781079, "percentage": 70.39, "elapsed_time": "5:03:13", "remaining_time": "2:07:32", "throughput": 1484.4, "total_tokens": 27005920} {"current_steps": 127975, "total_steps": 181800, "loss": 0.0676, "lr": 1.2204371312810028e-05, "epoch": 14.078657865786578, "percentage": 70.39, "elapsed_time": "5:03:13", "remaining_time": "2:07:32", "throughput": 1484.4, "total_tokens": 27007008} {"current_steps": 127980, "total_steps": 181800, "loss": 0.0107, "lr": 1.2202309498445772e-05, "epoch": 14.07920792079208, "percentage": 70.4, "elapsed_time": "5:03:14", "remaining_time": "2:07:31", "throughput": 1484.41, "total_tokens": 27008096} {"current_steps": 127985, "total_steps": 181800, "loss": 0.0384, "lr": 1.2200247802031697e-05, "epoch": 14.07975797579758, "percentage": 70.4, "elapsed_time": "5:03:15", "remaining_time": "2:07:30", "throughput": 1484.4, "total_tokens": 27009120} {"current_steps": 127990, "total_steps": 181800, "loss": 0.0123, "lr": 1.2198186223586797e-05, "epoch": 14.08030803080308, "percentage": 70.4, "elapsed_time": "5:03:15", "remaining_time": "2:07:30", "throughput": 1484.41, "total_tokens": 27010240} {"current_steps": 127995, "total_steps": 181800, "loss": 0.0326, "lr": 1.2196124763130062e-05, "epoch": 14.08085808580858, "percentage": 70.4, "elapsed_time": "5:03:16", "remaining_time": "2:07:29", "throughput": 1484.41, "total_tokens": 27011328} {"current_steps": 128000, "total_steps": 181800, "loss": 0.0022, "lr": 1.219406342068051e-05, "epoch": 14.081408140814082, "percentage": 70.41, "elapsed_time": "5:03:17", "remaining_time": "2:07:28", "throughput": 1484.41, "total_tokens": 27012320} {"current_steps": 128005, "total_steps": 181800, "loss": 0.039, "lr": 1.219200219625712e-05, "epoch": 14.081958195819581, "percentage": 70.41, "elapsed_time": "5:03:18", "remaining_time": "2:07:27", "throughput": 1484.41, "total_tokens": 27013408} {"current_steps": 128010, "total_steps": 181800, "loss": 0.0322, "lr": 1.21899410898789e-05, "epoch": 14.082508250825082, "percentage": 70.41, "elapsed_time": "5:03:18", "remaining_time": "2:07:27", "throughput": 1484.41, "total_tokens": 27014400} {"current_steps": 128015, "total_steps": 181800, "loss": 0.0032, "lr": 1.2187880101564859e-05, "epoch": 14.083058305830583, "percentage": 70.42, "elapsed_time": "5:03:19", "remaining_time": "2:07:26", "throughput": 1484.41, "total_tokens": 27015424} {"current_steps": 128020, "total_steps": 181800, "loss": 0.0013, "lr": 1.2185819231333968e-05, "epoch": 14.083608360836084, "percentage": 70.42, "elapsed_time": "5:03:20", "remaining_time": "2:07:25", "throughput": 1484.42, "total_tokens": 27016512} {"current_steps": 128025, "total_steps": 181800, "loss": 0.0032, "lr": 1.218375847920524e-05, "epoch": 14.084158415841584, "percentage": 70.42, "elapsed_time": "5:03:20", "remaining_time": "2:07:24", "throughput": 1484.42, "total_tokens": 27017600} {"current_steps": 128030, "total_steps": 181800, "loss": 0.0058, "lr": 1.2181697845197651e-05, "epoch": 14.084708470847085, "percentage": 70.42, "elapsed_time": "5:03:21", "remaining_time": "2:07:24", "throughput": 1484.42, "total_tokens": 27018592} {"current_steps": 128035, "total_steps": 181800, "loss": 0.0065, "lr": 1.2179637329330204e-05, "epoch": 14.085258525852586, "percentage": 70.43, "elapsed_time": "5:03:22", "remaining_time": "2:07:23", "throughput": 1484.42, "total_tokens": 27019648} {"current_steps": 128040, "total_steps": 181800, "loss": 0.0306, "lr": 1.2177576931621895e-05, "epoch": 14.085808580858085, "percentage": 70.43, "elapsed_time": "5:03:22", "remaining_time": "2:07:22", "throughput": 1484.42, "total_tokens": 27020640} {"current_steps": 128045, "total_steps": 181800, "loss": 0.0031, "lr": 1.21755166520917e-05, "epoch": 14.086358635863586, "percentage": 70.43, "elapsed_time": "5:03:23", "remaining_time": "2:07:22", "throughput": 1484.41, "total_tokens": 27021600} {"current_steps": 128050, "total_steps": 181800, "loss": 0.0009, "lr": 1.2173456490758622e-05, "epoch": 14.086908690869087, "percentage": 70.43, "elapsed_time": "5:03:24", "remaining_time": "2:07:21", "throughput": 1484.42, "total_tokens": 27022688} {"current_steps": 128055, "total_steps": 181800, "loss": 0.007, "lr": 1.2171396447641641e-05, "epoch": 14.087458745874587, "percentage": 70.44, "elapsed_time": "5:03:24", "remaining_time": "2:07:20", "throughput": 1484.42, "total_tokens": 27023712} {"current_steps": 128060, "total_steps": 181800, "loss": 0.1096, "lr": 1.2169336522759733e-05, "epoch": 14.088008800880088, "percentage": 70.44, "elapsed_time": "5:03:25", "remaining_time": "2:07:19", "throughput": 1484.42, "total_tokens": 27024832} {"current_steps": 128065, "total_steps": 181800, "loss": 0.0941, "lr": 1.2167276716131895e-05, "epoch": 14.088558855885589, "percentage": 70.44, "elapsed_time": "5:03:26", "remaining_time": "2:07:19", "throughput": 1484.43, "total_tokens": 27025952} {"current_steps": 128070, "total_steps": 181800, "loss": 0.0021, "lr": 1.2165217027777109e-05, "epoch": 14.089108910891088, "percentage": 70.45, "elapsed_time": "5:03:26", "remaining_time": "2:07:18", "throughput": 1484.43, "total_tokens": 27027008} {"current_steps": 128075, "total_steps": 181800, "loss": 0.0019, "lr": 1.216315745771437e-05, "epoch": 14.08965896589659, "percentage": 70.45, "elapsed_time": "5:03:27", "remaining_time": "2:07:17", "throughput": 1484.43, "total_tokens": 27028000} {"current_steps": 128080, "total_steps": 181800, "loss": 0.0416, "lr": 1.2161098005962648e-05, "epoch": 14.09020902090209, "percentage": 70.45, "elapsed_time": "5:03:28", "remaining_time": "2:07:17", "throughput": 1484.43, "total_tokens": 27029024} {"current_steps": 128085, "total_steps": 181800, "loss": 0.002, "lr": 1.2159038672540915e-05, "epoch": 14.090759075907592, "percentage": 70.45, "elapsed_time": "5:03:29", "remaining_time": "2:07:16", "throughput": 1484.43, "total_tokens": 27030080} {"current_steps": 128090, "total_steps": 181800, "loss": 0.0235, "lr": 1.215697945746816e-05, "epoch": 14.091309130913091, "percentage": 70.46, "elapsed_time": "5:03:29", "remaining_time": "2:07:15", "throughput": 1484.43, "total_tokens": 27031136} {"current_steps": 128095, "total_steps": 181800, "loss": 0.0983, "lr": 1.2154920360763364e-05, "epoch": 14.091859185918592, "percentage": 70.46, "elapsed_time": "5:03:30", "remaining_time": "2:07:14", "throughput": 1484.44, "total_tokens": 27032256} {"current_steps": 128100, "total_steps": 181800, "loss": 0.035, "lr": 1.2152861382445513e-05, "epoch": 14.092409240924093, "percentage": 70.46, "elapsed_time": "5:03:31", "remaining_time": "2:07:14", "throughput": 1484.44, "total_tokens": 27033248} {"current_steps": 128105, "total_steps": 181800, "loss": 0.0321, "lr": 1.2150802522533573e-05, "epoch": 14.092959295929592, "percentage": 70.46, "elapsed_time": "5:03:31", "remaining_time": "2:07:13", "throughput": 1484.44, "total_tokens": 27034336} {"current_steps": 128110, "total_steps": 181800, "loss": 0.0698, "lr": 1.2148743781046513e-05, "epoch": 14.093509350935093, "percentage": 70.47, "elapsed_time": "5:03:32", "remaining_time": "2:07:12", "throughput": 1484.44, "total_tokens": 27035360} {"current_steps": 128115, "total_steps": 181800, "loss": 0.0057, "lr": 1.2146685158003321e-05, "epoch": 14.094059405940595, "percentage": 70.47, "elapsed_time": "5:03:33", "remaining_time": "2:07:12", "throughput": 1484.44, "total_tokens": 27036352} {"current_steps": 128120, "total_steps": 181800, "loss": 0.2122, "lr": 1.2144626653422955e-05, "epoch": 14.094609460946094, "percentage": 70.47, "elapsed_time": "5:03:33", "remaining_time": "2:07:11", "throughput": 1484.44, "total_tokens": 27037408} {"current_steps": 128125, "total_steps": 181800, "loss": 0.0034, "lr": 1.21425682673244e-05, "epoch": 14.095159515951595, "percentage": 70.48, "elapsed_time": "5:03:34", "remaining_time": "2:07:10", "throughput": 1484.44, "total_tokens": 27038464} {"current_steps": 128130, "total_steps": 181800, "loss": 0.0069, "lr": 1.2140509999726633e-05, "epoch": 14.095709570957096, "percentage": 70.48, "elapsed_time": "5:03:35", "remaining_time": "2:07:09", "throughput": 1484.45, "total_tokens": 27039552} {"current_steps": 128135, "total_steps": 181800, "loss": 0.0155, "lr": 1.2138451850648602e-05, "epoch": 14.096259625962595, "percentage": 70.48, "elapsed_time": "5:03:35", "remaining_time": "2:07:09", "throughput": 1484.45, "total_tokens": 27040608} {"current_steps": 128140, "total_steps": 181800, "loss": 0.0425, "lr": 1.2136393820109299e-05, "epoch": 14.096809680968097, "percentage": 70.48, "elapsed_time": "5:03:36", "remaining_time": "2:07:08", "throughput": 1484.45, "total_tokens": 27041632} {"current_steps": 128145, "total_steps": 181800, "loss": 0.0118, "lr": 1.2134335908127673e-05, "epoch": 14.097359735973598, "percentage": 70.49, "elapsed_time": "5:03:37", "remaining_time": "2:07:07", "throughput": 1484.45, "total_tokens": 27042656} {"current_steps": 128150, "total_steps": 181800, "loss": 0.0621, "lr": 1.21322781147227e-05, "epoch": 14.097909790979099, "percentage": 70.49, "elapsed_time": "5:03:38", "remaining_time": "2:07:06", "throughput": 1484.45, "total_tokens": 27043744} {"current_steps": 128155, "total_steps": 181800, "loss": 0.0083, "lr": 1.2130220439913354e-05, "epoch": 14.098459845984598, "percentage": 70.49, "elapsed_time": "5:03:38", "remaining_time": "2:07:06", "throughput": 1484.45, "total_tokens": 27044800} {"current_steps": 128160, "total_steps": 181800, "loss": 0.1267, "lr": 1.212816288371858e-05, "epoch": 14.099009900990099, "percentage": 70.5, "elapsed_time": "5:03:39", "remaining_time": "2:07:05", "throughput": 1484.45, "total_tokens": 27045856} {"current_steps": 128165, "total_steps": 181800, "loss": 0.0105, "lr": 1.2126105446157362e-05, "epoch": 14.0995599559956, "percentage": 70.5, "elapsed_time": "5:03:40", "remaining_time": "2:07:04", "throughput": 1484.45, "total_tokens": 27046880} {"current_steps": 128170, "total_steps": 181800, "loss": 0.0013, "lr": 1.2124048127248644e-05, "epoch": 14.1001100110011, "percentage": 70.5, "elapsed_time": "5:03:40", "remaining_time": "2:07:04", "throughput": 1484.46, "total_tokens": 27047936} {"current_steps": 128175, "total_steps": 181800, "loss": 0.0019, "lr": 1.2121990927011407e-05, "epoch": 14.1006600660066, "percentage": 70.5, "elapsed_time": "5:03:41", "remaining_time": "2:07:03", "throughput": 1484.46, "total_tokens": 27049024} {"current_steps": 128180, "total_steps": 181800, "loss": 0.0007, "lr": 1.2119933845464587e-05, "epoch": 14.101210121012102, "percentage": 70.51, "elapsed_time": "5:03:42", "remaining_time": "2:07:02", "throughput": 1484.46, "total_tokens": 27050080} {"current_steps": 128185, "total_steps": 181800, "loss": 0.0037, "lr": 1.2117876882627161e-05, "epoch": 14.101760176017601, "percentage": 70.51, "elapsed_time": "5:03:42", "remaining_time": "2:07:01", "throughput": 1484.46, "total_tokens": 27051104} {"current_steps": 128190, "total_steps": 181800, "loss": 0.0026, "lr": 1.2115820038518088e-05, "epoch": 14.102310231023102, "percentage": 70.51, "elapsed_time": "5:03:43", "remaining_time": "2:07:01", "throughput": 1484.46, "total_tokens": 27052192} {"current_steps": 128195, "total_steps": 181800, "loss": 0.0031, "lr": 1.211376331315632e-05, "epoch": 14.102860286028603, "percentage": 70.51, "elapsed_time": "5:03:44", "remaining_time": "2:07:00", "throughput": 1484.47, "total_tokens": 27053248} {"current_steps": 128200, "total_steps": 181800, "loss": 0.0198, "lr": 1.2111706706560803e-05, "epoch": 14.103410341034103, "percentage": 70.52, "elapsed_time": "5:03:44", "remaining_time": "2:06:59", "throughput": 1484.47, "total_tokens": 27054368} {"current_steps": 128205, "total_steps": 181800, "loss": 0.0092, "lr": 1.21096502187505e-05, "epoch": 14.103960396039604, "percentage": 70.52, "elapsed_time": "5:03:45", "remaining_time": "2:06:59", "throughput": 1484.47, "total_tokens": 27055424} {"current_steps": 128210, "total_steps": 181800, "loss": 0.0039, "lr": 1.2107593849744367e-05, "epoch": 14.104510451045105, "percentage": 70.52, "elapsed_time": "5:03:46", "remaining_time": "2:06:58", "throughput": 1484.48, "total_tokens": 27056512} {"current_steps": 128215, "total_steps": 181800, "loss": 0.0035, "lr": 1.2105537599561364e-05, "epoch": 14.105060506050606, "percentage": 70.53, "elapsed_time": "5:03:46", "remaining_time": "2:06:57", "throughput": 1484.48, "total_tokens": 27057536} {"current_steps": 128220, "total_steps": 181800, "loss": 0.0077, "lr": 1.2103481468220435e-05, "epoch": 14.105610561056105, "percentage": 70.53, "elapsed_time": "5:03:47", "remaining_time": "2:06:56", "throughput": 1484.48, "total_tokens": 27058624} {"current_steps": 128225, "total_steps": 181800, "loss": 0.0104, "lr": 1.2101425455740516e-05, "epoch": 14.106160616061606, "percentage": 70.53, "elapsed_time": "5:03:48", "remaining_time": "2:06:56", "throughput": 1484.48, "total_tokens": 27059648} {"current_steps": 128230, "total_steps": 181800, "loss": 0.0114, "lr": 1.2099369562140581e-05, "epoch": 14.106710671067107, "percentage": 70.53, "elapsed_time": "5:03:49", "remaining_time": "2:06:55", "throughput": 1484.48, "total_tokens": 27060768} {"current_steps": 128235, "total_steps": 181800, "loss": 0.0195, "lr": 1.2097313787439557e-05, "epoch": 14.107260726072607, "percentage": 70.54, "elapsed_time": "5:03:49", "remaining_time": "2:06:54", "throughput": 1484.48, "total_tokens": 27061792} {"current_steps": 128240, "total_steps": 181800, "loss": 0.0219, "lr": 1.20952581316564e-05, "epoch": 14.107810781078108, "percentage": 70.54, "elapsed_time": "5:03:50", "remaining_time": "2:06:54", "throughput": 1484.49, "total_tokens": 27062848} {"current_steps": 128245, "total_steps": 181800, "loss": 0.061, "lr": 1.2093202594810066e-05, "epoch": 14.108360836083609, "percentage": 70.54, "elapsed_time": "5:03:51", "remaining_time": "2:06:53", "throughput": 1484.49, "total_tokens": 27063904} {"current_steps": 128250, "total_steps": 181800, "loss": 0.0133, "lr": 1.2091147176919482e-05, "epoch": 14.108910891089108, "percentage": 70.54, "elapsed_time": "5:03:51", "remaining_time": "2:06:52", "throughput": 1484.5, "total_tokens": 27065088} {"current_steps": 128255, "total_steps": 181800, "loss": 0.0733, "lr": 1.2089091878003609e-05, "epoch": 14.10946094609461, "percentage": 70.55, "elapsed_time": "5:03:52", "remaining_time": "2:06:51", "throughput": 1484.5, "total_tokens": 27066144} {"current_steps": 128260, "total_steps": 181800, "loss": 0.0353, "lr": 1.208703669808137e-05, "epoch": 14.11001100110011, "percentage": 70.55, "elapsed_time": "5:03:53", "remaining_time": "2:06:51", "throughput": 1484.5, "total_tokens": 27067168} {"current_steps": 128265, "total_steps": 181800, "loss": 0.0512, "lr": 1.2084981637171719e-05, "epoch": 14.110561056105611, "percentage": 70.55, "elapsed_time": "5:03:53", "remaining_time": "2:06:50", "throughput": 1484.5, "total_tokens": 27068256} {"current_steps": 128270, "total_steps": 181800, "loss": 0.0012, "lr": 1.2082926695293605e-05, "epoch": 14.11111111111111, "percentage": 70.56, "elapsed_time": "5:03:54", "remaining_time": "2:06:49", "throughput": 1484.5, "total_tokens": 27069312} {"current_steps": 128275, "total_steps": 181800, "loss": 0.06, "lr": 1.2080871872465945e-05, "epoch": 14.111661166116612, "percentage": 70.56, "elapsed_time": "5:03:55", "remaining_time": "2:06:48", "throughput": 1484.5, "total_tokens": 27070304} {"current_steps": 128280, "total_steps": 181800, "loss": 0.0024, "lr": 1.2078817168707704e-05, "epoch": 14.112211221122113, "percentage": 70.56, "elapsed_time": "5:03:55", "remaining_time": "2:06:48", "throughput": 1484.5, "total_tokens": 27071360} {"current_steps": 128285, "total_steps": 181800, "loss": 0.0088, "lr": 1.2076762584037793e-05, "epoch": 14.112761276127612, "percentage": 70.56, "elapsed_time": "5:03:56", "remaining_time": "2:06:47", "throughput": 1484.51, "total_tokens": 27072448} {"current_steps": 128290, "total_steps": 181800, "loss": 0.0007, "lr": 1.207470811847517e-05, "epoch": 14.113311331133113, "percentage": 70.57, "elapsed_time": "5:03:57", "remaining_time": "2:06:46", "throughput": 1484.51, "total_tokens": 27073536} {"current_steps": 128295, "total_steps": 181800, "loss": 0.0243, "lr": 1.207265377203875e-05, "epoch": 14.113861386138614, "percentage": 70.57, "elapsed_time": "5:03:58", "remaining_time": "2:06:46", "throughput": 1484.51, "total_tokens": 27074624} {"current_steps": 128300, "total_steps": 181800, "loss": 0.055, "lr": 1.2070599544747476e-05, "epoch": 14.114411441144114, "percentage": 70.57, "elapsed_time": "5:03:58", "remaining_time": "2:06:45", "throughput": 1484.51, "total_tokens": 27075616} {"current_steps": 128305, "total_steps": 181800, "loss": 0.001, "lr": 1.2068545436620293e-05, "epoch": 14.114961496149615, "percentage": 70.57, "elapsed_time": "5:03:59", "remaining_time": "2:06:44", "throughput": 1484.51, "total_tokens": 27076640} {"current_steps": 128310, "total_steps": 181800, "loss": 0.006, "lr": 1.2066491447676112e-05, "epoch": 14.115511551155116, "percentage": 70.58, "elapsed_time": "5:04:00", "remaining_time": "2:06:43", "throughput": 1484.51, "total_tokens": 27077632} {"current_steps": 128315, "total_steps": 181800, "loss": 0.1007, "lr": 1.2064437577933882e-05, "epoch": 14.116061606160615, "percentage": 70.58, "elapsed_time": "5:04:00", "remaining_time": "2:06:43", "throughput": 1484.52, "total_tokens": 27078720} {"current_steps": 128320, "total_steps": 181800, "loss": 0.02, "lr": 1.2062383827412513e-05, "epoch": 14.116611661166116, "percentage": 70.58, "elapsed_time": "5:04:01", "remaining_time": "2:06:42", "throughput": 1484.52, "total_tokens": 27079808} {"current_steps": 128325, "total_steps": 181800, "loss": 0.0077, "lr": 1.2060330196130947e-05, "epoch": 14.117161716171617, "percentage": 70.59, "elapsed_time": "5:04:02", "remaining_time": "2:06:41", "throughput": 1484.52, "total_tokens": 27080864} {"current_steps": 128330, "total_steps": 181800, "loss": 0.006, "lr": 1.2058276684108117e-05, "epoch": 14.117711771177119, "percentage": 70.59, "elapsed_time": "5:04:02", "remaining_time": "2:06:41", "throughput": 1484.52, "total_tokens": 27081952} {"current_steps": 128335, "total_steps": 181800, "loss": 0.0109, "lr": 1.2056223291362931e-05, "epoch": 14.118261826182618, "percentage": 70.59, "elapsed_time": "5:04:03", "remaining_time": "2:06:40", "throughput": 1484.52, "total_tokens": 27082976} {"current_steps": 128340, "total_steps": 181800, "loss": 0.0014, "lr": 1.2054170017914332e-05, "epoch": 14.118811881188119, "percentage": 70.59, "elapsed_time": "5:04:04", "remaining_time": "2:06:39", "throughput": 1484.52, "total_tokens": 27084032} {"current_steps": 128345, "total_steps": 181800, "loss": 0.0154, "lr": 1.2052116863781238e-05, "epoch": 14.11936193619362, "percentage": 70.6, "elapsed_time": "5:04:04", "remaining_time": "2:06:38", "throughput": 1484.53, "total_tokens": 27085120} {"current_steps": 128350, "total_steps": 181800, "loss": 0.1888, "lr": 1.205006382898256e-05, "epoch": 14.11991199119912, "percentage": 70.6, "elapsed_time": "5:04:05", "remaining_time": "2:06:38", "throughput": 1484.53, "total_tokens": 27086208} {"current_steps": 128355, "total_steps": 181800, "loss": 0.0576, "lr": 1.204801091353723e-05, "epoch": 14.12046204620462, "percentage": 70.6, "elapsed_time": "5:04:06", "remaining_time": "2:06:37", "throughput": 1484.53, "total_tokens": 27087232} {"current_steps": 128360, "total_steps": 181800, "loss": 0.0112, "lr": 1.2045958117464167e-05, "epoch": 14.121012101210122, "percentage": 70.61, "elapsed_time": "5:04:06", "remaining_time": "2:06:36", "throughput": 1484.53, "total_tokens": 27088256} {"current_steps": 128365, "total_steps": 181800, "loss": 0.0196, "lr": 1.2043905440782302e-05, "epoch": 14.12156215621562, "percentage": 70.61, "elapsed_time": "5:04:07", "remaining_time": "2:06:36", "throughput": 1484.53, "total_tokens": 27089280} {"current_steps": 128370, "total_steps": 181800, "loss": 0.001, "lr": 1.2041852883510546e-05, "epoch": 14.122112211221122, "percentage": 70.61, "elapsed_time": "5:04:08", "remaining_time": "2:06:35", "throughput": 1484.54, "total_tokens": 27090368} {"current_steps": 128375, "total_steps": 181800, "loss": 0.001, "lr": 1.2039800445667801e-05, "epoch": 14.122662266226623, "percentage": 70.61, "elapsed_time": "5:04:09", "remaining_time": "2:06:34", "throughput": 1484.53, "total_tokens": 27091360} {"current_steps": 128380, "total_steps": 181800, "loss": 0.0011, "lr": 1.2037748127272998e-05, "epoch": 14.123212321232122, "percentage": 70.62, "elapsed_time": "5:04:09", "remaining_time": "2:06:33", "throughput": 1484.54, "total_tokens": 27092416} {"current_steps": 128385, "total_steps": 181800, "loss": 0.0051, "lr": 1.2035695928345061e-05, "epoch": 14.123762376237623, "percentage": 70.62, "elapsed_time": "5:04:10", "remaining_time": "2:06:33", "throughput": 1484.54, "total_tokens": 27093472} {"current_steps": 128390, "total_steps": 181800, "loss": 0.0112, "lr": 1.2033643848902885e-05, "epoch": 14.124312431243125, "percentage": 70.62, "elapsed_time": "5:04:11", "remaining_time": "2:06:32", "throughput": 1484.54, "total_tokens": 27094592} {"current_steps": 128395, "total_steps": 181800, "loss": 0.0032, "lr": 1.2031591888965399e-05, "epoch": 14.124862486248626, "percentage": 70.62, "elapsed_time": "5:04:11", "remaining_time": "2:06:31", "throughput": 1484.54, "total_tokens": 27095616} {"current_steps": 128400, "total_steps": 181800, "loss": 0.0909, "lr": 1.20295400485515e-05, "epoch": 14.125412541254125, "percentage": 70.63, "elapsed_time": "5:04:12", "remaining_time": "2:06:30", "throughput": 1484.55, "total_tokens": 27096704} {"current_steps": 128405, "total_steps": 181800, "loss": 0.0044, "lr": 1.2027488327680112e-05, "epoch": 14.125962596259626, "percentage": 70.63, "elapsed_time": "5:04:13", "remaining_time": "2:06:30", "throughput": 1484.55, "total_tokens": 27097792} {"current_steps": 128410, "total_steps": 181800, "loss": 0.0487, "lr": 1.2025436726370134e-05, "epoch": 14.126512651265127, "percentage": 70.63, "elapsed_time": "5:04:13", "remaining_time": "2:06:29", "throughput": 1484.55, "total_tokens": 27098816} {"current_steps": 128415, "total_steps": 181800, "loss": 0.0125, "lr": 1.2023385244640477e-05, "epoch": 14.127062706270626, "percentage": 70.64, "elapsed_time": "5:04:14", "remaining_time": "2:06:28", "throughput": 1484.55, "total_tokens": 27099872} {"current_steps": 128420, "total_steps": 181800, "loss": 0.0429, "lr": 1.2021333882510063e-05, "epoch": 14.127612761276128, "percentage": 70.64, "elapsed_time": "5:04:15", "remaining_time": "2:06:28", "throughput": 1484.55, "total_tokens": 27100896} {"current_steps": 128425, "total_steps": 181800, "loss": 0.01, "lr": 1.2019282639997777e-05, "epoch": 14.128162816281629, "percentage": 70.64, "elapsed_time": "5:04:15", "remaining_time": "2:06:27", "throughput": 1484.56, "total_tokens": 27102016} {"current_steps": 128430, "total_steps": 181800, "loss": 0.1345, "lr": 1.2017231517122543e-05, "epoch": 14.128712871287128, "percentage": 70.64, "elapsed_time": "5:04:16", "remaining_time": "2:06:26", "throughput": 1484.56, "total_tokens": 27103072} {"current_steps": 128435, "total_steps": 181800, "loss": 0.0501, "lr": 1.2015180513903256e-05, "epoch": 14.129262926292629, "percentage": 70.65, "elapsed_time": "5:04:17", "remaining_time": "2:06:25", "throughput": 1484.56, "total_tokens": 27104160} {"current_steps": 128440, "total_steps": 181800, "loss": 0.0014, "lr": 1.2013129630358802e-05, "epoch": 14.12981298129813, "percentage": 70.65, "elapsed_time": "5:04:18", "remaining_time": "2:06:25", "throughput": 1484.56, "total_tokens": 27105184} {"current_steps": 128445, "total_steps": 181800, "loss": 0.0783, "lr": 1.201107886650812e-05, "epoch": 14.130363036303631, "percentage": 70.65, "elapsed_time": "5:04:18", "remaining_time": "2:06:24", "throughput": 1484.57, "total_tokens": 27106272} {"current_steps": 128450, "total_steps": 181800, "loss": 0.0262, "lr": 1.200902822237008e-05, "epoch": 14.13091309130913, "percentage": 70.65, "elapsed_time": "5:04:19", "remaining_time": "2:06:23", "throughput": 1484.57, "total_tokens": 27107360} {"current_steps": 128455, "total_steps": 181800, "loss": 0.1153, "lr": 1.2006977697963603e-05, "epoch": 14.131463146314632, "percentage": 70.66, "elapsed_time": "5:04:20", "remaining_time": "2:06:23", "throughput": 1484.57, "total_tokens": 27108480} {"current_steps": 128460, "total_steps": 181800, "loss": 0.1316, "lr": 1.200492729330758e-05, "epoch": 14.132013201320133, "percentage": 70.66, "elapsed_time": "5:04:20", "remaining_time": "2:06:22", "throughput": 1484.57, "total_tokens": 27109472} {"current_steps": 128465, "total_steps": 181800, "loss": 0.0071, "lr": 1.2002877008420895e-05, "epoch": 14.132563256325632, "percentage": 70.66, "elapsed_time": "5:04:21", "remaining_time": "2:06:21", "throughput": 1484.57, "total_tokens": 27110528} {"current_steps": 128470, "total_steps": 181800, "loss": 0.0021, "lr": 1.2000826843322458e-05, "epoch": 14.133113311331133, "percentage": 70.67, "elapsed_time": "5:04:22", "remaining_time": "2:06:20", "throughput": 1484.57, "total_tokens": 27111552} {"current_steps": 128475, "total_steps": 181800, "loss": 0.0206, "lr": 1.1998776798031158e-05, "epoch": 14.133663366336634, "percentage": 70.67, "elapsed_time": "5:04:22", "remaining_time": "2:06:20", "throughput": 1484.57, "total_tokens": 27112544} {"current_steps": 128480, "total_steps": 181800, "loss": 0.0189, "lr": 1.1996726872565906e-05, "epoch": 14.134213421342134, "percentage": 70.67, "elapsed_time": "5:04:23", "remaining_time": "2:06:19", "throughput": 1484.58, "total_tokens": 27113632} {"current_steps": 128485, "total_steps": 181800, "loss": 0.0059, "lr": 1.1994677066945584e-05, "epoch": 14.134763476347635, "percentage": 70.67, "elapsed_time": "5:04:24", "remaining_time": "2:06:18", "throughput": 1484.58, "total_tokens": 27114752} {"current_steps": 128490, "total_steps": 181800, "loss": 0.0064, "lr": 1.1992627381189073e-05, "epoch": 14.135313531353136, "percentage": 70.68, "elapsed_time": "5:04:24", "remaining_time": "2:06:18", "throughput": 1484.58, "total_tokens": 27115840} {"current_steps": 128495, "total_steps": 181800, "loss": 0.0931, "lr": 1.1990577815315282e-05, "epoch": 14.135863586358635, "percentage": 70.68, "elapsed_time": "5:04:25", "remaining_time": "2:06:17", "throughput": 1484.58, "total_tokens": 27116864} {"current_steps": 128500, "total_steps": 181800, "loss": 0.0012, "lr": 1.1988528369343074e-05, "epoch": 14.136413641364136, "percentage": 70.68, "elapsed_time": "5:04:26", "remaining_time": "2:06:16", "throughput": 1484.59, "total_tokens": 27117920} {"current_steps": 128505, "total_steps": 181800, "loss": 0.0157, "lr": 1.1986479043291373e-05, "epoch": 14.136963696369637, "percentage": 70.68, "elapsed_time": "5:04:27", "remaining_time": "2:06:15", "throughput": 1484.59, "total_tokens": 27119040} {"current_steps": 128510, "total_steps": 181800, "loss": 0.0023, "lr": 1.1984429837179053e-05, "epoch": 14.137513751375138, "percentage": 70.69, "elapsed_time": "5:04:27", "remaining_time": "2:06:15", "throughput": 1484.59, "total_tokens": 27120096} {"current_steps": 128515, "total_steps": 181800, "loss": 0.1894, "lr": 1.1982380751024991e-05, "epoch": 14.138063806380638, "percentage": 70.69, "elapsed_time": "5:04:28", "remaining_time": "2:06:14", "throughput": 1484.59, "total_tokens": 27121152} {"current_steps": 128520, "total_steps": 181800, "loss": 0.063, "lr": 1.1980331784848084e-05, "epoch": 14.138613861386139, "percentage": 70.69, "elapsed_time": "5:04:29", "remaining_time": "2:06:13", "throughput": 1484.6, "total_tokens": 27122240} {"current_steps": 128525, "total_steps": 181800, "loss": 0.0041, "lr": 1.1978282938667204e-05, "epoch": 14.13916391639164, "percentage": 70.7, "elapsed_time": "5:04:29", "remaining_time": "2:06:13", "throughput": 1484.59, "total_tokens": 27123232} {"current_steps": 128530, "total_steps": 181800, "loss": 0.0131, "lr": 1.1976234212501241e-05, "epoch": 14.13971397139714, "percentage": 70.7, "elapsed_time": "5:04:30", "remaining_time": "2:06:12", "throughput": 1484.59, "total_tokens": 27124256} {"current_steps": 128535, "total_steps": 181800, "loss": 0.0044, "lr": 1.197418560636909e-05, "epoch": 14.14026402640264, "percentage": 70.7, "elapsed_time": "5:04:31", "remaining_time": "2:06:11", "throughput": 1484.59, "total_tokens": 27125248} {"current_steps": 128540, "total_steps": 181800, "loss": 0.0136, "lr": 1.1972137120289607e-05, "epoch": 14.140814081408141, "percentage": 70.7, "elapsed_time": "5:04:31", "remaining_time": "2:06:10", "throughput": 1484.6, "total_tokens": 27126336} {"current_steps": 128545, "total_steps": 181800, "loss": 0.0018, "lr": 1.1970088754281694e-05, "epoch": 14.14136413641364, "percentage": 70.71, "elapsed_time": "5:04:32", "remaining_time": "2:06:10", "throughput": 1484.6, "total_tokens": 27127392} {"current_steps": 128550, "total_steps": 181800, "loss": 0.0928, "lr": 1.1968040508364214e-05, "epoch": 14.141914191419142, "percentage": 70.71, "elapsed_time": "5:04:33", "remaining_time": "2:06:09", "throughput": 1484.6, "total_tokens": 27128448} {"current_steps": 128555, "total_steps": 181800, "loss": 0.0328, "lr": 1.196599238255606e-05, "epoch": 14.142464246424643, "percentage": 70.71, "elapsed_time": "5:04:33", "remaining_time": "2:06:08", "throughput": 1484.6, "total_tokens": 27129504} {"current_steps": 128560, "total_steps": 181800, "loss": 0.0139, "lr": 1.1963944376876088e-05, "epoch": 14.143014301430142, "percentage": 70.72, "elapsed_time": "5:04:34", "remaining_time": "2:06:07", "throughput": 1484.6, "total_tokens": 27130528} {"current_steps": 128565, "total_steps": 181800, "loss": 0.0121, "lr": 1.1961896491343188e-05, "epoch": 14.143564356435643, "percentage": 70.72, "elapsed_time": "5:04:35", "remaining_time": "2:06:07", "throughput": 1484.61, "total_tokens": 27131616} {"current_steps": 128570, "total_steps": 181800, "loss": 0.096, "lr": 1.1959848725976242e-05, "epoch": 14.144114411441144, "percentage": 70.72, "elapsed_time": "5:04:35", "remaining_time": "2:06:06", "throughput": 1484.61, "total_tokens": 27132640} {"current_steps": 128575, "total_steps": 181800, "loss": 0.0042, "lr": 1.195780108079411e-05, "epoch": 14.144664466446645, "percentage": 70.72, "elapsed_time": "5:04:36", "remaining_time": "2:06:05", "throughput": 1484.61, "total_tokens": 27133728} {"current_steps": 128580, "total_steps": 181800, "loss": 0.0369, "lr": 1.195575355581566e-05, "epoch": 14.145214521452145, "percentage": 70.73, "elapsed_time": "5:04:37", "remaining_time": "2:06:05", "throughput": 1484.61, "total_tokens": 27134784} {"current_steps": 128585, "total_steps": 181800, "loss": 0.0045, "lr": 1.1953706151059768e-05, "epoch": 14.145764576457646, "percentage": 70.73, "elapsed_time": "5:04:38", "remaining_time": "2:06:04", "throughput": 1484.61, "total_tokens": 27135776} {"current_steps": 128590, "total_steps": 181800, "loss": 0.0656, "lr": 1.195165886654531e-05, "epoch": 14.146314631463147, "percentage": 70.73, "elapsed_time": "5:04:38", "remaining_time": "2:06:03", "throughput": 1484.61, "total_tokens": 27136832} {"current_steps": 128595, "total_steps": 181800, "loss": 0.0331, "lr": 1.1949611702291156e-05, "epoch": 14.146864686468646, "percentage": 70.73, "elapsed_time": "5:04:39", "remaining_time": "2:06:02", "throughput": 1484.61, "total_tokens": 27137888} {"current_steps": 128600, "total_steps": 181800, "loss": 0.0047, "lr": 1.194756465831617e-05, "epoch": 14.147414741474147, "percentage": 70.74, "elapsed_time": "5:04:40", "remaining_time": "2:06:02", "throughput": 1484.61, "total_tokens": 27138944} {"current_steps": 128605, "total_steps": 181800, "loss": 0.0049, "lr": 1.1945517734639208e-05, "epoch": 14.147964796479648, "percentage": 70.74, "elapsed_time": "5:04:40", "remaining_time": "2:06:01", "throughput": 1484.61, "total_tokens": 27139968} {"current_steps": 128610, "total_steps": 181800, "loss": 0.0108, "lr": 1.1943470931279157e-05, "epoch": 14.148514851485148, "percentage": 70.74, "elapsed_time": "5:04:41", "remaining_time": "2:06:00", "throughput": 1484.62, "total_tokens": 27141024} {"current_steps": 128615, "total_steps": 181800, "loss": 0.0568, "lr": 1.1941424248254857e-05, "epoch": 14.149064906490649, "percentage": 70.75, "elapsed_time": "5:04:42", "remaining_time": "2:06:00", "throughput": 1484.62, "total_tokens": 27142080} {"current_steps": 128620, "total_steps": 181800, "loss": 0.0886, "lr": 1.1939377685585184e-05, "epoch": 14.14961496149615, "percentage": 70.75, "elapsed_time": "5:04:42", "remaining_time": "2:05:59", "throughput": 1484.62, "total_tokens": 27143136} {"current_steps": 128625, "total_steps": 181800, "loss": 0.054, "lr": 1.193733124328901e-05, "epoch": 14.150165016501651, "percentage": 70.75, "elapsed_time": "5:04:43", "remaining_time": "2:05:58", "throughput": 1484.62, "total_tokens": 27144224} {"current_steps": 128630, "total_steps": 181800, "loss": 0.0356, "lr": 1.1935284921385176e-05, "epoch": 14.15071507150715, "percentage": 70.75, "elapsed_time": "5:04:44", "remaining_time": "2:05:57", "throughput": 1484.62, "total_tokens": 27145280} {"current_steps": 128635, "total_steps": 181800, "loss": 0.0127, "lr": 1.1933238719892562e-05, "epoch": 14.151265126512651, "percentage": 70.76, "elapsed_time": "5:04:44", "remaining_time": "2:05:57", "throughput": 1484.62, "total_tokens": 27146304} {"current_steps": 128640, "total_steps": 181800, "loss": 0.0016, "lr": 1.1931192638830008e-05, "epoch": 14.151815181518153, "percentage": 70.76, "elapsed_time": "5:04:45", "remaining_time": "2:05:56", "throughput": 1484.63, "total_tokens": 27147392} {"current_steps": 128645, "total_steps": 181800, "loss": 0.01, "lr": 1.1929146678216377e-05, "epoch": 14.152365236523652, "percentage": 70.76, "elapsed_time": "5:04:46", "remaining_time": "2:05:55", "throughput": 1484.63, "total_tokens": 27148384} {"current_steps": 128650, "total_steps": 181800, "loss": 0.0086, "lr": 1.192710083807054e-05, "epoch": 14.152915291529153, "percentage": 70.76, "elapsed_time": "5:04:47", "remaining_time": "2:05:55", "throughput": 1484.62, "total_tokens": 27149344} {"current_steps": 128655, "total_steps": 181800, "loss": 0.0082, "lr": 1.1925055118411336e-05, "epoch": 14.153465346534654, "percentage": 70.77, "elapsed_time": "5:04:47", "remaining_time": "2:05:54", "throughput": 1484.63, "total_tokens": 27150432} {"current_steps": 128660, "total_steps": 181800, "loss": 0.1297, "lr": 1.192300951925763e-05, "epoch": 14.154015401540153, "percentage": 70.77, "elapsed_time": "5:04:48", "remaining_time": "2:05:53", "throughput": 1484.63, "total_tokens": 27151520} {"current_steps": 128665, "total_steps": 181800, "loss": 0.0328, "lr": 1.192096404062826e-05, "epoch": 14.154565456545654, "percentage": 70.77, "elapsed_time": "5:04:49", "remaining_time": "2:05:52", "throughput": 1484.63, "total_tokens": 27152576} {"current_steps": 128670, "total_steps": 181800, "loss": 0.0195, "lr": 1.1918918682542101e-05, "epoch": 14.155115511551156, "percentage": 70.78, "elapsed_time": "5:04:49", "remaining_time": "2:05:52", "throughput": 1484.63, "total_tokens": 27153664} {"current_steps": 128675, "total_steps": 181800, "loss": 0.0041, "lr": 1.1916873445017982e-05, "epoch": 14.155665566556655, "percentage": 70.78, "elapsed_time": "5:04:50", "remaining_time": "2:05:51", "throughput": 1484.64, "total_tokens": 27154816} {"current_steps": 128680, "total_steps": 181800, "loss": 0.2577, "lr": 1.1914828328074763e-05, "epoch": 14.156215621562156, "percentage": 70.78, "elapsed_time": "5:04:51", "remaining_time": "2:05:50", "throughput": 1484.65, "total_tokens": 27155904} {"current_steps": 128685, "total_steps": 181800, "loss": 0.0079, "lr": 1.1912783331731298e-05, "epoch": 14.156765676567657, "percentage": 70.78, "elapsed_time": "5:04:51", "remaining_time": "2:05:50", "throughput": 1484.64, "total_tokens": 27156928} {"current_steps": 128690, "total_steps": 181800, "loss": 0.0116, "lr": 1.1910738456006423e-05, "epoch": 14.157315731573158, "percentage": 70.79, "elapsed_time": "5:04:52", "remaining_time": "2:05:49", "throughput": 1484.64, "total_tokens": 27157952} {"current_steps": 128695, "total_steps": 181800, "loss": 0.028, "lr": 1.1908693700918999e-05, "epoch": 14.157865786578657, "percentage": 70.79, "elapsed_time": "5:04:53", "remaining_time": "2:05:48", "throughput": 1484.64, "total_tokens": 27158944} {"current_steps": 128700, "total_steps": 181800, "loss": 0.0025, "lr": 1.1906649066487854e-05, "epoch": 14.158415841584159, "percentage": 70.79, "elapsed_time": "5:04:53", "remaining_time": "2:05:47", "throughput": 1484.65, "total_tokens": 27160000} {"current_steps": 128705, "total_steps": 181800, "loss": 0.0053, "lr": 1.1904604552731843e-05, "epoch": 14.15896589658966, "percentage": 70.79, "elapsed_time": "5:04:54", "remaining_time": "2:05:47", "throughput": 1484.65, "total_tokens": 27161088} {"current_steps": 128710, "total_steps": 181800, "loss": 0.0086, "lr": 1.1902560159669814e-05, "epoch": 14.159515951595159, "percentage": 70.8, "elapsed_time": "5:04:55", "remaining_time": "2:05:46", "throughput": 1484.65, "total_tokens": 27162112} {"current_steps": 128715, "total_steps": 181800, "loss": 0.0089, "lr": 1.1900515887320599e-05, "epoch": 14.16006600660066, "percentage": 70.8, "elapsed_time": "5:04:56", "remaining_time": "2:05:45", "throughput": 1484.65, "total_tokens": 27163200} {"current_steps": 128720, "total_steps": 181800, "loss": 0.0739, "lr": 1.1898471735703052e-05, "epoch": 14.160616061606161, "percentage": 70.8, "elapsed_time": "5:04:56", "remaining_time": "2:05:44", "throughput": 1484.65, "total_tokens": 27164224} {"current_steps": 128725, "total_steps": 181800, "loss": 0.0013, "lr": 1.1896427704836e-05, "epoch": 14.16116611661166, "percentage": 70.81, "elapsed_time": "5:04:57", "remaining_time": "2:05:44", "throughput": 1484.66, "total_tokens": 27165344} {"current_steps": 128730, "total_steps": 181800, "loss": 0.0061, "lr": 1.189438379473828e-05, "epoch": 14.161716171617162, "percentage": 70.81, "elapsed_time": "5:04:58", "remaining_time": "2:05:43", "throughput": 1484.66, "total_tokens": 27166368} {"current_steps": 128735, "total_steps": 181800, "loss": 0.0058, "lr": 1.1892340005428735e-05, "epoch": 14.162266226622663, "percentage": 70.81, "elapsed_time": "5:04:58", "remaining_time": "2:05:42", "throughput": 1484.66, "total_tokens": 27167424} {"current_steps": 128740, "total_steps": 181800, "loss": 0.1403, "lr": 1.1890296336926202e-05, "epoch": 14.162816281628162, "percentage": 70.81, "elapsed_time": "5:04:59", "remaining_time": "2:05:42", "throughput": 1484.66, "total_tokens": 27168544} {"current_steps": 128745, "total_steps": 181800, "loss": 0.0029, "lr": 1.1888252789249526e-05, "epoch": 14.163366336633663, "percentage": 70.82, "elapsed_time": "5:05:00", "remaining_time": "2:05:41", "throughput": 1484.67, "total_tokens": 27169632} {"current_steps": 128750, "total_steps": 181800, "loss": 0.0046, "lr": 1.1886209362417535e-05, "epoch": 14.163916391639164, "percentage": 70.82, "elapsed_time": "5:05:00", "remaining_time": "2:05:40", "throughput": 1484.67, "total_tokens": 27170624} {"current_steps": 128755, "total_steps": 181800, "loss": 0.079, "lr": 1.1884166056449048e-05, "epoch": 14.164466446644665, "percentage": 70.82, "elapsed_time": "5:05:01", "remaining_time": "2:05:39", "throughput": 1484.67, "total_tokens": 27171648} {"current_steps": 128760, "total_steps": 181800, "loss": 0.0479, "lr": 1.1882122871362911e-05, "epoch": 14.165016501650165, "percentage": 70.83, "elapsed_time": "5:05:02", "remaining_time": "2:05:39", "throughput": 1484.67, "total_tokens": 27172640} {"current_steps": 128765, "total_steps": 181800, "loss": 0.0144, "lr": 1.1880079807177961e-05, "epoch": 14.165566556655666, "percentage": 70.83, "elapsed_time": "5:05:02", "remaining_time": "2:05:38", "throughput": 1484.67, "total_tokens": 27173728} {"current_steps": 128770, "total_steps": 181800, "loss": 0.0039, "lr": 1.1878036863913008e-05, "epoch": 14.166116611661167, "percentage": 70.83, "elapsed_time": "5:05:03", "remaining_time": "2:05:37", "throughput": 1484.67, "total_tokens": 27174720} {"current_steps": 128775, "total_steps": 181800, "loss": 0.012, "lr": 1.1875994041586905e-05, "epoch": 14.166666666666666, "percentage": 70.83, "elapsed_time": "5:05:04", "remaining_time": "2:05:37", "throughput": 1484.67, "total_tokens": 27175840} {"current_steps": 128780, "total_steps": 181800, "loss": 0.0792, "lr": 1.1873951340218459e-05, "epoch": 14.167216721672167, "percentage": 70.84, "elapsed_time": "5:05:04", "remaining_time": "2:05:36", "throughput": 1484.67, "total_tokens": 27176896} {"current_steps": 128785, "total_steps": 181800, "loss": 0.0812, "lr": 1.1871908759826512e-05, "epoch": 14.167766776677668, "percentage": 70.84, "elapsed_time": "5:05:05", "remaining_time": "2:05:35", "throughput": 1484.67, "total_tokens": 27177888} {"current_steps": 128790, "total_steps": 181800, "loss": 0.0026, "lr": 1.1869866300429874e-05, "epoch": 14.168316831683168, "percentage": 70.84, "elapsed_time": "5:05:06", "remaining_time": "2:05:34", "throughput": 1484.67, "total_tokens": 27178912} {"current_steps": 128795, "total_steps": 181800, "loss": 0.0354, "lr": 1.1867823962047378e-05, "epoch": 14.168866886688669, "percentage": 70.84, "elapsed_time": "5:05:07", "remaining_time": "2:05:34", "throughput": 1484.67, "total_tokens": 27179936} {"current_steps": 128800, "total_steps": 181800, "loss": 0.062, "lr": 1.1865781744697858e-05, "epoch": 14.16941694169417, "percentage": 70.85, "elapsed_time": "5:05:07", "remaining_time": "2:05:33", "throughput": 1484.68, "total_tokens": 27181120} {"current_steps": 128805, "total_steps": 181800, "loss": 0.003, "lr": 1.1863739648400112e-05, "epoch": 14.16996699669967, "percentage": 70.85, "elapsed_time": "5:05:08", "remaining_time": "2:05:32", "throughput": 1484.68, "total_tokens": 27182176} {"current_steps": 128810, "total_steps": 181800, "loss": 0.0029, "lr": 1.1861697673172986e-05, "epoch": 14.17051705170517, "percentage": 70.85, "elapsed_time": "5:05:09", "remaining_time": "2:05:32", "throughput": 1484.68, "total_tokens": 27183200} {"current_steps": 128815, "total_steps": 181800, "loss": 0.0726, "lr": 1.1859655819035279e-05, "epoch": 14.171067106710671, "percentage": 70.86, "elapsed_time": "5:05:09", "remaining_time": "2:05:31", "throughput": 1484.69, "total_tokens": 27184320} {"current_steps": 128820, "total_steps": 181800, "loss": 0.0582, "lr": 1.185761408600582e-05, "epoch": 14.171617161716172, "percentage": 70.86, "elapsed_time": "5:05:10", "remaining_time": "2:05:30", "throughput": 1484.69, "total_tokens": 27185376} {"current_steps": 128825, "total_steps": 181800, "loss": 0.0015, "lr": 1.1855572474103433e-05, "epoch": 14.172167216721672, "percentage": 70.86, "elapsed_time": "5:05:11", "remaining_time": "2:05:29", "throughput": 1484.69, "total_tokens": 27186464} {"current_steps": 128830, "total_steps": 181800, "loss": 0.0016, "lr": 1.1853530983346916e-05, "epoch": 14.172717271727173, "percentage": 70.86, "elapsed_time": "5:05:11", "remaining_time": "2:05:29", "throughput": 1484.7, "total_tokens": 27187520} {"current_steps": 128835, "total_steps": 181800, "loss": 0.0648, "lr": 1.185148961375511e-05, "epoch": 14.173267326732674, "percentage": 70.87, "elapsed_time": "5:05:12", "remaining_time": "2:05:28", "throughput": 1484.7, "total_tokens": 27188672} {"current_steps": 128840, "total_steps": 181800, "loss": 0.0044, "lr": 1.1849448365346813e-05, "epoch": 14.173817381738173, "percentage": 70.87, "elapsed_time": "5:05:13", "remaining_time": "2:05:27", "throughput": 1484.7, "total_tokens": 27189696} {"current_steps": 128845, "total_steps": 181800, "loss": 0.0016, "lr": 1.1847407238140828e-05, "epoch": 14.174367436743674, "percentage": 70.87, "elapsed_time": "5:05:13", "remaining_time": "2:05:26", "throughput": 1484.71, "total_tokens": 27190784} {"current_steps": 128850, "total_steps": 181800, "loss": 0.0394, "lr": 1.1845366232155983e-05, "epoch": 14.174917491749175, "percentage": 70.87, "elapsed_time": "5:05:14", "remaining_time": "2:05:26", "throughput": 1484.7, "total_tokens": 27191744} {"current_steps": 128855, "total_steps": 181800, "loss": 0.0049, "lr": 1.1843325347411082e-05, "epoch": 14.175467546754675, "percentage": 70.88, "elapsed_time": "5:05:15", "remaining_time": "2:05:25", "throughput": 1484.71, "total_tokens": 27192832} {"current_steps": 128860, "total_steps": 181800, "loss": 0.1626, "lr": 1.184128458392495e-05, "epoch": 14.176017601760176, "percentage": 70.88, "elapsed_time": "5:05:15", "remaining_time": "2:05:24", "throughput": 1484.71, "total_tokens": 27193856} {"current_steps": 128865, "total_steps": 181800, "loss": 0.0063, "lr": 1.1839243941716383e-05, "epoch": 14.176567656765677, "percentage": 70.88, "elapsed_time": "5:05:16", "remaining_time": "2:05:24", "throughput": 1484.71, "total_tokens": 27194912} {"current_steps": 128870, "total_steps": 181800, "loss": 0.0022, "lr": 1.183720342080418e-05, "epoch": 14.177117711771178, "percentage": 70.89, "elapsed_time": "5:05:17", "remaining_time": "2:05:23", "throughput": 1484.71, "total_tokens": 27195936} {"current_steps": 128875, "total_steps": 181800, "loss": 0.0028, "lr": 1.1835163021207157e-05, "epoch": 14.177667766776677, "percentage": 70.89, "elapsed_time": "5:05:18", "remaining_time": "2:05:22", "throughput": 1484.71, "total_tokens": 27197088} {"current_steps": 128880, "total_steps": 181800, "loss": 0.0087, "lr": 1.183312274294412e-05, "epoch": 14.178217821782178, "percentage": 70.89, "elapsed_time": "5:05:18", "remaining_time": "2:05:21", "throughput": 1484.72, "total_tokens": 27198176} {"current_steps": 128885, "total_steps": 181800, "loss": 0.0117, "lr": 1.1831082586033882e-05, "epoch": 14.17876787678768, "percentage": 70.89, "elapsed_time": "5:05:19", "remaining_time": "2:05:21", "throughput": 1484.72, "total_tokens": 27199264} {"current_steps": 128890, "total_steps": 181800, "loss": 0.0009, "lr": 1.1829042550495233e-05, "epoch": 14.179317931793179, "percentage": 70.9, "elapsed_time": "5:05:20", "remaining_time": "2:05:20", "throughput": 1484.72, "total_tokens": 27200288} {"current_steps": 128895, "total_steps": 181800, "loss": 0.076, "lr": 1.1827002636346974e-05, "epoch": 14.17986798679868, "percentage": 70.9, "elapsed_time": "5:05:20", "remaining_time": "2:05:19", "throughput": 1484.72, "total_tokens": 27201344} {"current_steps": 128900, "total_steps": 181800, "loss": 0.0056, "lr": 1.1824962843607921e-05, "epoch": 14.180418041804181, "percentage": 70.9, "elapsed_time": "5:05:21", "remaining_time": "2:05:19", "throughput": 1484.72, "total_tokens": 27202368} {"current_steps": 128905, "total_steps": 181800, "loss": 0.0033, "lr": 1.1822923172296848e-05, "epoch": 14.18096809680968, "percentage": 70.9, "elapsed_time": "5:05:22", "remaining_time": "2:05:18", "throughput": 1484.72, "total_tokens": 27203392} {"current_steps": 128910, "total_steps": 181800, "loss": 0.0112, "lr": 1.1820883622432574e-05, "epoch": 14.181518151815181, "percentage": 70.91, "elapsed_time": "5:05:22", "remaining_time": "2:05:17", "throughput": 1484.72, "total_tokens": 27204416} {"current_steps": 128915, "total_steps": 181800, "loss": 0.0038, "lr": 1.1818844194033901e-05, "epoch": 14.182068206820682, "percentage": 70.91, "elapsed_time": "5:05:23", "remaining_time": "2:05:16", "throughput": 1484.73, "total_tokens": 27205504} {"current_steps": 128920, "total_steps": 181800, "loss": 0.0717, "lr": 1.1816804887119604e-05, "epoch": 14.182618261826182, "percentage": 70.91, "elapsed_time": "5:05:24", "remaining_time": "2:05:16", "throughput": 1484.73, "total_tokens": 27206560} {"current_steps": 128925, "total_steps": 181800, "loss": 0.0032, "lr": 1.1814765701708502e-05, "epoch": 14.183168316831683, "percentage": 70.92, "elapsed_time": "5:05:24", "remaining_time": "2:05:15", "throughput": 1484.73, "total_tokens": 27207648} {"current_steps": 128930, "total_steps": 181800, "loss": 0.0037, "lr": 1.181272663781937e-05, "epoch": 14.183718371837184, "percentage": 70.92, "elapsed_time": "5:05:25", "remaining_time": "2:05:14", "throughput": 1484.73, "total_tokens": 27208704} {"current_steps": 128935, "total_steps": 181800, "loss": 0.0063, "lr": 1.1810687695471004e-05, "epoch": 14.184268426842685, "percentage": 70.92, "elapsed_time": "5:05:26", "remaining_time": "2:05:14", "throughput": 1484.74, "total_tokens": 27209824} {"current_steps": 128940, "total_steps": 181800, "loss": 0.0491, "lr": 1.1808648874682212e-05, "epoch": 14.184818481848184, "percentage": 70.92, "elapsed_time": "5:05:27", "remaining_time": "2:05:13", "throughput": 1484.74, "total_tokens": 27210880} {"current_steps": 128945, "total_steps": 181800, "loss": 0.0219, "lr": 1.1806610175471766e-05, "epoch": 14.185368536853685, "percentage": 70.93, "elapsed_time": "5:05:27", "remaining_time": "2:05:12", "throughput": 1484.74, "total_tokens": 27211968} {"current_steps": 128950, "total_steps": 181800, "loss": 0.0033, "lr": 1.1804571597858471e-05, "epoch": 14.185918591859187, "percentage": 70.93, "elapsed_time": "5:05:28", "remaining_time": "2:05:11", "throughput": 1484.75, "total_tokens": 27213056} {"current_steps": 128955, "total_steps": 181800, "loss": 0.0731, "lr": 1.1802533141861108e-05, "epoch": 14.186468646864686, "percentage": 70.93, "elapsed_time": "5:05:29", "remaining_time": "2:05:11", "throughput": 1484.75, "total_tokens": 27214112} {"current_steps": 128960, "total_steps": 181800, "loss": 0.0092, "lr": 1.1800494807498455e-05, "epoch": 14.187018701870187, "percentage": 70.94, "elapsed_time": "5:05:29", "remaining_time": "2:05:10", "throughput": 1484.75, "total_tokens": 27215104} {"current_steps": 128965, "total_steps": 181800, "loss": 0.0061, "lr": 1.1798456594789306e-05, "epoch": 14.187568756875688, "percentage": 70.94, "elapsed_time": "5:05:30", "remaining_time": "2:05:09", "throughput": 1484.75, "total_tokens": 27216160} {"current_steps": 128970, "total_steps": 181800, "loss": 0.0072, "lr": 1.179641850375245e-05, "epoch": 14.188118811881187, "percentage": 70.94, "elapsed_time": "5:05:31", "remaining_time": "2:05:08", "throughput": 1484.75, "total_tokens": 27217280} {"current_steps": 128975, "total_steps": 181800, "loss": 0.0305, "lr": 1.1794380534406677e-05, "epoch": 14.188668866886688, "percentage": 70.94, "elapsed_time": "5:05:31", "remaining_time": "2:05:08", "throughput": 1484.75, "total_tokens": 27218272} {"current_steps": 128980, "total_steps": 181800, "loss": 0.0027, "lr": 1.1792342686770763e-05, "epoch": 14.18921892189219, "percentage": 70.95, "elapsed_time": "5:05:32", "remaining_time": "2:05:07", "throughput": 1484.75, "total_tokens": 27219328} {"current_steps": 128985, "total_steps": 181800, "loss": 0.0053, "lr": 1.179030496086348e-05, "epoch": 14.189768976897689, "percentage": 70.95, "elapsed_time": "5:05:33", "remaining_time": "2:05:06", "throughput": 1484.76, "total_tokens": 27220384} {"current_steps": 128990, "total_steps": 181800, "loss": 0.0153, "lr": 1.1788267356703616e-05, "epoch": 14.19031903190319, "percentage": 70.95, "elapsed_time": "5:05:33", "remaining_time": "2:05:06", "throughput": 1484.75, "total_tokens": 27221376} {"current_steps": 128995, "total_steps": 181800, "loss": 0.0794, "lr": 1.1786229874309951e-05, "epoch": 14.190869086908691, "percentage": 70.95, "elapsed_time": "5:05:34", "remaining_time": "2:05:05", "throughput": 1484.75, "total_tokens": 27222368} {"current_steps": 129000, "total_steps": 181800, "loss": 0.0277, "lr": 1.1784192513701279e-05, "epoch": 14.191419141914192, "percentage": 70.96, "elapsed_time": "5:05:35", "remaining_time": "2:05:04", "throughput": 1484.75, "total_tokens": 27223360} {"current_steps": 129005, "total_steps": 181800, "loss": 0.0612, "lr": 1.1782155274896358e-05, "epoch": 14.191969196919691, "percentage": 70.96, "elapsed_time": "5:05:36", "remaining_time": "2:05:03", "throughput": 1484.75, "total_tokens": 27224448} {"current_steps": 129010, "total_steps": 181800, "loss": 0.0605, "lr": 1.178011815791396e-05, "epoch": 14.192519251925193, "percentage": 70.96, "elapsed_time": "5:05:36", "remaining_time": "2:05:03", "throughput": 1484.75, "total_tokens": 27225472} {"current_steps": 129015, "total_steps": 181800, "loss": 0.006, "lr": 1.1778081162772883e-05, "epoch": 14.193069306930694, "percentage": 70.97, "elapsed_time": "5:05:37", "remaining_time": "2:05:02", "throughput": 1484.75, "total_tokens": 27226496} {"current_steps": 129020, "total_steps": 181800, "loss": 0.004, "lr": 1.1776044289491874e-05, "epoch": 14.193619361936193, "percentage": 70.97, "elapsed_time": "5:05:38", "remaining_time": "2:05:01", "throughput": 1484.76, "total_tokens": 27227584} {"current_steps": 129025, "total_steps": 181800, "loss": 0.0035, "lr": 1.1774007538089721e-05, "epoch": 14.194169416941694, "percentage": 70.97, "elapsed_time": "5:05:38", "remaining_time": "2:05:01", "throughput": 1484.76, "total_tokens": 27228736} {"current_steps": 129030, "total_steps": 181800, "loss": 0.0102, "lr": 1.1771970908585203e-05, "epoch": 14.194719471947195, "percentage": 70.97, "elapsed_time": "5:05:39", "remaining_time": "2:05:00", "throughput": 1484.76, "total_tokens": 27229760} {"current_steps": 129035, "total_steps": 181800, "loss": 0.0162, "lr": 1.1769934400997073e-05, "epoch": 14.195269526952695, "percentage": 70.98, "elapsed_time": "5:05:40", "remaining_time": "2:04:59", "throughput": 1484.77, "total_tokens": 27230816} {"current_steps": 129040, "total_steps": 181800, "loss": 0.0045, "lr": 1.176789801534412e-05, "epoch": 14.195819581958196, "percentage": 70.98, "elapsed_time": "5:05:40", "remaining_time": "2:04:58", "throughput": 1484.77, "total_tokens": 27231872} {"current_steps": 129045, "total_steps": 181800, "loss": 0.0131, "lr": 1.1765861751645088e-05, "epoch": 14.196369636963697, "percentage": 70.98, "elapsed_time": "5:05:41", "remaining_time": "2:04:58", "throughput": 1484.77, "total_tokens": 27232928} {"current_steps": 129050, "total_steps": 181800, "loss": 0.0025, "lr": 1.176382560991876e-05, "epoch": 14.196919691969198, "percentage": 70.98, "elapsed_time": "5:05:42", "remaining_time": "2:04:57", "throughput": 1484.77, "total_tokens": 27234016} {"current_steps": 129055, "total_steps": 181800, "loss": 0.0012, "lr": 1.176178959018391e-05, "epoch": 14.197469746974697, "percentage": 70.99, "elapsed_time": "5:05:42", "remaining_time": "2:04:56", "throughput": 1484.77, "total_tokens": 27235040} {"current_steps": 129060, "total_steps": 181800, "loss": 0.0177, "lr": 1.1759753692459286e-05, "epoch": 14.198019801980198, "percentage": 70.99, "elapsed_time": "5:05:43", "remaining_time": "2:04:56", "throughput": 1484.77, "total_tokens": 27236064} {"current_steps": 129065, "total_steps": 181800, "loss": 0.014, "lr": 1.1757717916763663e-05, "epoch": 14.1985698569857, "percentage": 70.99, "elapsed_time": "5:05:44", "remaining_time": "2:04:55", "throughput": 1484.77, "total_tokens": 27237088} {"current_steps": 129070, "total_steps": 181800, "loss": 0.003, "lr": 1.1755682263115795e-05, "epoch": 14.199119911991199, "percentage": 71.0, "elapsed_time": "5:05:44", "remaining_time": "2:04:54", "throughput": 1484.77, "total_tokens": 27238112} {"current_steps": 129075, "total_steps": 181800, "loss": 0.0012, "lr": 1.1753646731534455e-05, "epoch": 14.1996699669967, "percentage": 71.0, "elapsed_time": "5:05:45", "remaining_time": "2:04:53", "throughput": 1484.77, "total_tokens": 27239104} {"current_steps": 129080, "total_steps": 181800, "loss": 0.0084, "lr": 1.1751611322038389e-05, "epoch": 14.2002200220022, "percentage": 71.0, "elapsed_time": "5:05:46", "remaining_time": "2:04:53", "throughput": 1484.77, "total_tokens": 27240128} {"current_steps": 129085, "total_steps": 181800, "loss": 0.0814, "lr": 1.1749576034646363e-05, "epoch": 14.2007700770077, "percentage": 71.0, "elapsed_time": "5:05:47", "remaining_time": "2:04:52", "throughput": 1484.77, "total_tokens": 27241184} {"current_steps": 129090, "total_steps": 181800, "loss": 0.0406, "lr": 1.1747540869377146e-05, "epoch": 14.201320132013201, "percentage": 71.01, "elapsed_time": "5:05:47", "remaining_time": "2:04:51", "throughput": 1484.77, "total_tokens": 27242208} {"current_steps": 129095, "total_steps": 181800, "loss": 0.0023, "lr": 1.1745505826249476e-05, "epoch": 14.201870187018702, "percentage": 71.01, "elapsed_time": "5:05:48", "remaining_time": "2:04:51", "throughput": 1484.77, "total_tokens": 27243264} {"current_steps": 129100, "total_steps": 181800, "loss": 0.0572, "lr": 1.174347090528213e-05, "epoch": 14.202420242024202, "percentage": 71.01, "elapsed_time": "5:05:49", "remaining_time": "2:04:50", "throughput": 1484.78, "total_tokens": 27244352} {"current_steps": 129105, "total_steps": 181800, "loss": 0.0124, "lr": 1.1741436106493842e-05, "epoch": 14.202970297029703, "percentage": 71.01, "elapsed_time": "5:05:49", "remaining_time": "2:04:49", "throughput": 1484.78, "total_tokens": 27245408} {"current_steps": 129110, "total_steps": 181800, "loss": 0.0082, "lr": 1.1739401429903374e-05, "epoch": 14.203520352035204, "percentage": 71.02, "elapsed_time": "5:05:50", "remaining_time": "2:04:48", "throughput": 1484.78, "total_tokens": 27246464} {"current_steps": 129115, "total_steps": 181800, "loss": 0.0196, "lr": 1.1737366875529488e-05, "epoch": 14.204070407040705, "percentage": 71.02, "elapsed_time": "5:05:51", "remaining_time": "2:04:48", "throughput": 1484.78, "total_tokens": 27247520} {"current_steps": 129120, "total_steps": 181800, "loss": 0.0041, "lr": 1.173533244339092e-05, "epoch": 14.204620462046204, "percentage": 71.02, "elapsed_time": "5:05:51", "remaining_time": "2:04:47", "throughput": 1484.78, "total_tokens": 27248544} {"current_steps": 129125, "total_steps": 181800, "loss": 0.0882, "lr": 1.1733298133506437e-05, "epoch": 14.205170517051705, "percentage": 71.03, "elapsed_time": "5:05:52", "remaining_time": "2:04:46", "throughput": 1484.78, "total_tokens": 27249600} {"current_steps": 129130, "total_steps": 181800, "loss": 0.1527, "lr": 1.173126394589478e-05, "epoch": 14.205720572057206, "percentage": 71.03, "elapsed_time": "5:05:53", "remaining_time": "2:04:45", "throughput": 1484.79, "total_tokens": 27250688} {"current_steps": 129135, "total_steps": 181800, "loss": 0.0043, "lr": 1.1729229880574685e-05, "epoch": 14.206270627062706, "percentage": 71.03, "elapsed_time": "5:05:53", "remaining_time": "2:04:45", "throughput": 1484.79, "total_tokens": 27251744} {"current_steps": 129140, "total_steps": 181800, "loss": 0.1482, "lr": 1.1727195937564911e-05, "epoch": 14.206820682068207, "percentage": 71.03, "elapsed_time": "5:05:54", "remaining_time": "2:04:44", "throughput": 1484.79, "total_tokens": 27252832} {"current_steps": 129145, "total_steps": 181800, "loss": 0.0804, "lr": 1.1725162116884203e-05, "epoch": 14.207370737073708, "percentage": 71.04, "elapsed_time": "5:05:55", "remaining_time": "2:04:43", "throughput": 1484.79, "total_tokens": 27253824} {"current_steps": 129150, "total_steps": 181800, "loss": 0.0055, "lr": 1.1723128418551315e-05, "epoch": 14.207920792079207, "percentage": 71.04, "elapsed_time": "5:05:56", "remaining_time": "2:04:43", "throughput": 1484.79, "total_tokens": 27254816} {"current_steps": 129155, "total_steps": 181800, "loss": 0.0799, "lr": 1.1721094842584985e-05, "epoch": 14.208470847084708, "percentage": 71.04, "elapsed_time": "5:05:56", "remaining_time": "2:04:42", "throughput": 1484.79, "total_tokens": 27255840} {"current_steps": 129160, "total_steps": 181800, "loss": 0.0018, "lr": 1.1719061389003938e-05, "epoch": 14.20902090209021, "percentage": 71.05, "elapsed_time": "5:05:57", "remaining_time": "2:04:41", "throughput": 1484.79, "total_tokens": 27256896} {"current_steps": 129165, "total_steps": 181800, "loss": 0.094, "lr": 1.1717028057826932e-05, "epoch": 14.209570957095709, "percentage": 71.05, "elapsed_time": "5:05:58", "remaining_time": "2:04:40", "throughput": 1484.79, "total_tokens": 27257888} {"current_steps": 129170, "total_steps": 181800, "loss": 0.0521, "lr": 1.171499484907271e-05, "epoch": 14.21012101210121, "percentage": 71.05, "elapsed_time": "5:05:58", "remaining_time": "2:04:40", "throughput": 1484.79, "total_tokens": 27258944} {"current_steps": 129175, "total_steps": 181800, "loss": 0.0013, "lr": 1.1712961762759999e-05, "epoch": 14.210671067106711, "percentage": 71.05, "elapsed_time": "5:05:59", "remaining_time": "2:04:39", "throughput": 1484.79, "total_tokens": 27259904} {"current_steps": 129180, "total_steps": 181800, "loss": 0.0478, "lr": 1.1710928798907556e-05, "epoch": 14.211221122112212, "percentage": 71.06, "elapsed_time": "5:06:00", "remaining_time": "2:04:38", "throughput": 1484.79, "total_tokens": 27260992} {"current_steps": 129185, "total_steps": 181800, "loss": 0.0029, "lr": 1.1708895957534094e-05, "epoch": 14.211771177117711, "percentage": 71.06, "elapsed_time": "5:06:00", "remaining_time": "2:04:38", "throughput": 1484.79, "total_tokens": 27262080} {"current_steps": 129190, "total_steps": 181800, "loss": 0.127, "lr": 1.1706863238658369e-05, "epoch": 14.212321232123212, "percentage": 71.06, "elapsed_time": "5:06:01", "remaining_time": "2:04:37", "throughput": 1484.79, "total_tokens": 27263136} {"current_steps": 129195, "total_steps": 181800, "loss": 0.0069, "lr": 1.1704830642299098e-05, "epoch": 14.212871287128714, "percentage": 71.06, "elapsed_time": "5:06:02", "remaining_time": "2:04:36", "throughput": 1484.79, "total_tokens": 27264160} {"current_steps": 129200, "total_steps": 181800, "loss": 0.0234, "lr": 1.1702798168475021e-05, "epoch": 14.213421342134213, "percentage": 71.07, "elapsed_time": "5:06:02", "remaining_time": "2:04:35", "throughput": 1484.8, "total_tokens": 27265248} {"current_steps": 129205, "total_steps": 181800, "loss": 0.0065, "lr": 1.1700765817204884e-05, "epoch": 14.213971397139714, "percentage": 71.07, "elapsed_time": "5:06:03", "remaining_time": "2:04:35", "throughput": 1484.8, "total_tokens": 27266272} {"current_steps": 129210, "total_steps": 181800, "loss": 0.0011, "lr": 1.16987335885074e-05, "epoch": 14.214521452145215, "percentage": 71.07, "elapsed_time": "5:06:04", "remaining_time": "2:04:34", "throughput": 1484.8, "total_tokens": 27267360} {"current_steps": 129215, "total_steps": 181800, "loss": 0.0019, "lr": 1.1696701482401312e-05, "epoch": 14.215071507150714, "percentage": 71.08, "elapsed_time": "5:06:05", "remaining_time": "2:04:33", "throughput": 1484.8, "total_tokens": 27268352} {"current_steps": 129220, "total_steps": 181800, "loss": 0.012, "lr": 1.1694669498905345e-05, "epoch": 14.215621562156215, "percentage": 71.08, "elapsed_time": "5:06:05", "remaining_time": "2:04:33", "throughput": 1484.8, "total_tokens": 27269408} {"current_steps": 129225, "total_steps": 181800, "loss": 0.0051, "lr": 1.1692637638038203e-05, "epoch": 14.216171617161717, "percentage": 71.08, "elapsed_time": "5:06:06", "remaining_time": "2:04:32", "throughput": 1484.8, "total_tokens": 27270400} {"current_steps": 129230, "total_steps": 181800, "loss": 0.0021, "lr": 1.1690605899818655e-05, "epoch": 14.216721672167218, "percentage": 71.08, "elapsed_time": "5:06:07", "remaining_time": "2:04:31", "throughput": 1484.8, "total_tokens": 27271456} {"current_steps": 129235, "total_steps": 181800, "loss": 0.0092, "lr": 1.1688574284265396e-05, "epoch": 14.217271727172717, "percentage": 71.09, "elapsed_time": "5:06:07", "remaining_time": "2:04:30", "throughput": 1484.8, "total_tokens": 27272512} {"current_steps": 129240, "total_steps": 181800, "loss": 0.0008, "lr": 1.1686542791397171e-05, "epoch": 14.217821782178218, "percentage": 71.09, "elapsed_time": "5:06:08", "remaining_time": "2:04:30", "throughput": 1484.81, "total_tokens": 27273600} {"current_steps": 129245, "total_steps": 181800, "loss": 0.0022, "lr": 1.1684511421232691e-05, "epoch": 14.218371837183719, "percentage": 71.09, "elapsed_time": "5:06:09", "remaining_time": "2:04:29", "throughput": 1484.81, "total_tokens": 27274656} {"current_steps": 129250, "total_steps": 181800, "loss": 0.0893, "lr": 1.1682480173790672e-05, "epoch": 14.218921892189218, "percentage": 71.09, "elapsed_time": "5:06:09", "remaining_time": "2:04:28", "throughput": 1484.81, "total_tokens": 27275712} {"current_steps": 129255, "total_steps": 181800, "loss": 0.0039, "lr": 1.1680449049089842e-05, "epoch": 14.21947194719472, "percentage": 71.1, "elapsed_time": "5:06:10", "remaining_time": "2:04:28", "throughput": 1484.81, "total_tokens": 27276800} {"current_steps": 129260, "total_steps": 181800, "loss": 0.0038, "lr": 1.1678418047148923e-05, "epoch": 14.22002200220022, "percentage": 71.1, "elapsed_time": "5:06:11", "remaining_time": "2:04:27", "throughput": 1484.82, "total_tokens": 27277920} {"current_steps": 129265, "total_steps": 181800, "loss": 0.0018, "lr": 1.167638716798664e-05, "epoch": 14.22057205720572, "percentage": 71.1, "elapsed_time": "5:06:11", "remaining_time": "2:04:26", "throughput": 1484.82, "total_tokens": 27279008} {"current_steps": 129270, "total_steps": 181800, "loss": 0.0045, "lr": 1.1674356411621704e-05, "epoch": 14.221122112211221, "percentage": 71.11, "elapsed_time": "5:06:12", "remaining_time": "2:04:25", "throughput": 1484.82, "total_tokens": 27280096} {"current_steps": 129275, "total_steps": 181800, "loss": 0.1827, "lr": 1.167232577807282e-05, "epoch": 14.221672167216722, "percentage": 71.11, "elapsed_time": "5:06:13", "remaining_time": "2:04:25", "throughput": 1484.83, "total_tokens": 27281184} {"current_steps": 129280, "total_steps": 181800, "loss": 0.0026, "lr": 1.1670295267358727e-05, "epoch": 14.222222222222221, "percentage": 71.11, "elapsed_time": "5:06:13", "remaining_time": "2:04:24", "throughput": 1484.83, "total_tokens": 27282208} {"current_steps": 129285, "total_steps": 181800, "loss": 0.075, "lr": 1.1668264879498105e-05, "epoch": 14.222772277227723, "percentage": 71.11, "elapsed_time": "5:06:14", "remaining_time": "2:04:23", "throughput": 1484.83, "total_tokens": 27283296} {"current_steps": 129290, "total_steps": 181800, "loss": 0.0037, "lr": 1.1666234614509708e-05, "epoch": 14.223322332233224, "percentage": 71.12, "elapsed_time": "5:06:15", "remaining_time": "2:04:22", "throughput": 1484.83, "total_tokens": 27284384} {"current_steps": 129295, "total_steps": 181800, "loss": 0.001, "lr": 1.1664204472412227e-05, "epoch": 14.223872387238725, "percentage": 71.12, "elapsed_time": "5:06:16", "remaining_time": "2:04:22", "throughput": 1484.83, "total_tokens": 27285376} {"current_steps": 129300, "total_steps": 181800, "loss": 0.0018, "lr": 1.1662174453224367e-05, "epoch": 14.224422442244224, "percentage": 71.12, "elapsed_time": "5:06:16", "remaining_time": "2:04:21", "throughput": 1484.84, "total_tokens": 27286464} {"current_steps": 129305, "total_steps": 181800, "loss": 0.1667, "lr": 1.1660144556964853e-05, "epoch": 14.224972497249725, "percentage": 71.12, "elapsed_time": "5:06:17", "remaining_time": "2:04:20", "throughput": 1484.84, "total_tokens": 27287552} {"current_steps": 129310, "total_steps": 181800, "loss": 0.0018, "lr": 1.1658114783652376e-05, "epoch": 14.225522552255226, "percentage": 71.13, "elapsed_time": "5:06:18", "remaining_time": "2:04:20", "throughput": 1484.84, "total_tokens": 27288608} {"current_steps": 129315, "total_steps": 181800, "loss": 0.0044, "lr": 1.1656085133305653e-05, "epoch": 14.226072607260726, "percentage": 71.13, "elapsed_time": "5:06:18", "remaining_time": "2:04:19", "throughput": 1484.84, "total_tokens": 27289664} {"current_steps": 129320, "total_steps": 181800, "loss": 0.0021, "lr": 1.16540556059434e-05, "epoch": 14.226622662266227, "percentage": 71.13, "elapsed_time": "5:06:19", "remaining_time": "2:04:18", "throughput": 1484.85, "total_tokens": 27290752} {"current_steps": 129325, "total_steps": 181800, "loss": 0.004, "lr": 1.1652026201584305e-05, "epoch": 14.227172717271728, "percentage": 71.14, "elapsed_time": "5:06:20", "remaining_time": "2:04:17", "throughput": 1484.85, "total_tokens": 27291840} {"current_steps": 129330, "total_steps": 181800, "loss": 0.0884, "lr": 1.1649996920247086e-05, "epoch": 14.227722772277227, "percentage": 71.14, "elapsed_time": "5:06:20", "remaining_time": "2:04:17", "throughput": 1484.85, "total_tokens": 27292896} {"current_steps": 129335, "total_steps": 181800, "loss": 0.0062, "lr": 1.1647967761950431e-05, "epoch": 14.228272827282728, "percentage": 71.14, "elapsed_time": "5:06:21", "remaining_time": "2:04:16", "throughput": 1484.85, "total_tokens": 27293888} {"current_steps": 129340, "total_steps": 181800, "loss": 0.0665, "lr": 1.164593872671306e-05, "epoch": 14.22882288228823, "percentage": 71.14, "elapsed_time": "5:06:22", "remaining_time": "2:04:15", "throughput": 1484.86, "total_tokens": 27295008} {"current_steps": 129345, "total_steps": 181800, "loss": 0.0722, "lr": 1.1643909814553652e-05, "epoch": 14.229372937293729, "percentage": 71.15, "elapsed_time": "5:06:22", "remaining_time": "2:04:15", "throughput": 1484.85, "total_tokens": 27296000} {"current_steps": 129350, "total_steps": 181800, "loss": 0.0031, "lr": 1.1641881025490922e-05, "epoch": 14.22992299229923, "percentage": 71.15, "elapsed_time": "5:06:23", "remaining_time": "2:04:14", "throughput": 1484.85, "total_tokens": 27297024} {"current_steps": 129355, "total_steps": 181800, "loss": 0.0006, "lr": 1.163985235954357e-05, "epoch": 14.23047304730473, "percentage": 71.15, "elapsed_time": "5:06:24", "remaining_time": "2:04:13", "throughput": 1484.85, "total_tokens": 27298080} {"current_steps": 129360, "total_steps": 181800, "loss": 0.0026, "lr": 1.1637823816730293e-05, "epoch": 14.231023102310232, "percentage": 71.16, "elapsed_time": "5:06:25", "remaining_time": "2:04:12", "throughput": 1484.85, "total_tokens": 27299104} {"current_steps": 129365, "total_steps": 181800, "loss": 0.0021, "lr": 1.1635795397069772e-05, "epoch": 14.231573157315731, "percentage": 71.16, "elapsed_time": "5:06:25", "remaining_time": "2:04:12", "throughput": 1484.86, "total_tokens": 27300160} {"current_steps": 129370, "total_steps": 181800, "loss": 0.001, "lr": 1.1633767100580709e-05, "epoch": 14.232123212321232, "percentage": 71.16, "elapsed_time": "5:06:26", "remaining_time": "2:04:11", "throughput": 1484.86, "total_tokens": 27301248} {"current_steps": 129375, "total_steps": 181800, "loss": 0.0969, "lr": 1.1631738927281802e-05, "epoch": 14.232673267326733, "percentage": 71.16, "elapsed_time": "5:06:27", "remaining_time": "2:04:10", "throughput": 1484.86, "total_tokens": 27302272} {"current_steps": 129380, "total_steps": 181800, "loss": 0.0027, "lr": 1.1629710877191752e-05, "epoch": 14.233223322332233, "percentage": 71.17, "elapsed_time": "5:06:27", "remaining_time": "2:04:10", "throughput": 1484.86, "total_tokens": 27303328} {"current_steps": 129385, "total_steps": 181800, "loss": 0.0156, "lr": 1.1627682950329242e-05, "epoch": 14.233773377337734, "percentage": 71.17, "elapsed_time": "5:06:28", "remaining_time": "2:04:09", "throughput": 1484.86, "total_tokens": 27304384} {"current_steps": 129390, "total_steps": 181800, "loss": 0.0012, "lr": 1.1625655146712952e-05, "epoch": 14.234323432343235, "percentage": 71.17, "elapsed_time": "5:06:29", "remaining_time": "2:04:08", "throughput": 1484.86, "total_tokens": 27305440} {"current_steps": 129395, "total_steps": 181800, "loss": 0.0478, "lr": 1.162362746636159e-05, "epoch": 14.234873487348734, "percentage": 71.17, "elapsed_time": "5:06:29", "remaining_time": "2:04:07", "throughput": 1484.86, "total_tokens": 27306464} {"current_steps": 129400, "total_steps": 181800, "loss": 0.0182, "lr": 1.1621599909293822e-05, "epoch": 14.235423542354235, "percentage": 71.18, "elapsed_time": "5:06:30", "remaining_time": "2:04:07", "throughput": 1484.86, "total_tokens": 27307456} {"current_steps": 129405, "total_steps": 181800, "loss": 0.0053, "lr": 1.1619572475528354e-05, "epoch": 14.235973597359736, "percentage": 71.18, "elapsed_time": "5:06:31", "remaining_time": "2:04:06", "throughput": 1484.87, "total_tokens": 27308544} {"current_steps": 129410, "total_steps": 181800, "loss": 0.0496, "lr": 1.1617545165083874e-05, "epoch": 14.236523652365236, "percentage": 71.18, "elapsed_time": "5:06:31", "remaining_time": "2:04:05", "throughput": 1484.87, "total_tokens": 27309568} {"current_steps": 129415, "total_steps": 181800, "loss": 0.002, "lr": 1.1615517977979046e-05, "epoch": 14.237073707370737, "percentage": 71.19, "elapsed_time": "5:06:32", "remaining_time": "2:04:05", "throughput": 1484.87, "total_tokens": 27310592} {"current_steps": 129420, "total_steps": 181800, "loss": 0.0364, "lr": 1.1613490914232578e-05, "epoch": 14.237623762376238, "percentage": 71.19, "elapsed_time": "5:06:33", "remaining_time": "2:04:04", "throughput": 1484.87, "total_tokens": 27311616} {"current_steps": 129425, "total_steps": 181800, "loss": 0.0242, "lr": 1.1611463973863132e-05, "epoch": 14.238173817381739, "percentage": 71.19, "elapsed_time": "5:06:34", "remaining_time": "2:04:03", "throughput": 1484.87, "total_tokens": 27312736} {"current_steps": 129430, "total_steps": 181800, "loss": 0.0041, "lr": 1.1609437156889396e-05, "epoch": 14.238723872387238, "percentage": 71.19, "elapsed_time": "5:06:34", "remaining_time": "2:04:02", "throughput": 1484.87, "total_tokens": 27313824} {"current_steps": 129435, "total_steps": 181800, "loss": 0.0093, "lr": 1.1607410463330065e-05, "epoch": 14.23927392739274, "percentage": 71.2, "elapsed_time": "5:06:35", "remaining_time": "2:04:02", "throughput": 1484.88, "total_tokens": 27314880} {"current_steps": 129440, "total_steps": 181800, "loss": 0.0027, "lr": 1.1605383893203793e-05, "epoch": 14.23982398239824, "percentage": 71.2, "elapsed_time": "5:06:36", "remaining_time": "2:04:01", "throughput": 1484.88, "total_tokens": 27315936} {"current_steps": 129445, "total_steps": 181800, "loss": 0.1001, "lr": 1.1603357446529282e-05, "epoch": 14.24037403740374, "percentage": 71.2, "elapsed_time": "5:06:36", "remaining_time": "2:04:00", "throughput": 1484.88, "total_tokens": 27316928} {"current_steps": 129450, "total_steps": 181800, "loss": 0.0065, "lr": 1.1601331123325185e-05, "epoch": 14.24092409240924, "percentage": 71.2, "elapsed_time": "5:06:37", "remaining_time": "2:03:59", "throughput": 1484.88, "total_tokens": 27317952} {"current_steps": 129455, "total_steps": 181800, "loss": 0.0113, "lr": 1.15993049236102e-05, "epoch": 14.241474147414742, "percentage": 71.21, "elapsed_time": "5:06:38", "remaining_time": "2:03:59", "throughput": 1484.88, "total_tokens": 27319008} {"current_steps": 129460, "total_steps": 181800, "loss": 0.0044, "lr": 1.1597278847402983e-05, "epoch": 14.242024202420241, "percentage": 71.21, "elapsed_time": "5:06:38", "remaining_time": "2:03:58", "throughput": 1484.87, "total_tokens": 27319968} {"current_steps": 129465, "total_steps": 181800, "loss": 0.005, "lr": 1.1595252894722214e-05, "epoch": 14.242574257425742, "percentage": 71.21, "elapsed_time": "5:06:39", "remaining_time": "2:03:57", "throughput": 1484.88, "total_tokens": 27321120} {"current_steps": 129470, "total_steps": 181800, "loss": 0.0008, "lr": 1.159322706558658e-05, "epoch": 14.243124312431243, "percentage": 71.22, "elapsed_time": "5:06:40", "remaining_time": "2:03:57", "throughput": 1484.88, "total_tokens": 27322144} {"current_steps": 129475, "total_steps": 181800, "loss": 0.0007, "lr": 1.1591201360014725e-05, "epoch": 14.243674367436745, "percentage": 71.22, "elapsed_time": "5:06:40", "remaining_time": "2:03:56", "throughput": 1484.88, "total_tokens": 27323200} {"current_steps": 129480, "total_steps": 181800, "loss": 0.0838, "lr": 1.1589175778025343e-05, "epoch": 14.244224422442244, "percentage": 71.22, "elapsed_time": "5:06:41", "remaining_time": "2:03:55", "throughput": 1484.88, "total_tokens": 27324192} {"current_steps": 129485, "total_steps": 181800, "loss": 0.0799, "lr": 1.1587150319637086e-05, "epoch": 14.244774477447745, "percentage": 71.22, "elapsed_time": "5:06:42", "remaining_time": "2:03:54", "throughput": 1484.89, "total_tokens": 27325280} {"current_steps": 129490, "total_steps": 181800, "loss": 0.0315, "lr": 1.1585124984868626e-05, "epoch": 14.245324532453246, "percentage": 71.23, "elapsed_time": "5:06:42", "remaining_time": "2:03:54", "throughput": 1484.89, "total_tokens": 27326432} {"current_steps": 129495, "total_steps": 181800, "loss": 0.0389, "lr": 1.1583099773738642e-05, "epoch": 14.245874587458745, "percentage": 71.23, "elapsed_time": "5:06:43", "remaining_time": "2:03:53", "throughput": 1484.89, "total_tokens": 27327424} {"current_steps": 129500, "total_steps": 181800, "loss": 0.0729, "lr": 1.1581074686265781e-05, "epoch": 14.246424642464246, "percentage": 71.23, "elapsed_time": "5:06:44", "remaining_time": "2:03:52", "throughput": 1484.9, "total_tokens": 27328512} {"current_steps": 129505, "total_steps": 181800, "loss": 0.0027, "lr": 1.1579049722468724e-05, "epoch": 14.246974697469748, "percentage": 71.23, "elapsed_time": "5:06:45", "remaining_time": "2:03:52", "throughput": 1484.9, "total_tokens": 27329568} {"current_steps": 129510, "total_steps": 181800, "loss": 0.0665, "lr": 1.1577024882366125e-05, "epoch": 14.247524752475247, "percentage": 71.24, "elapsed_time": "5:06:45", "remaining_time": "2:03:51", "throughput": 1484.9, "total_tokens": 27330624} {"current_steps": 129515, "total_steps": 181800, "loss": 0.0363, "lr": 1.1575000165976638e-05, "epoch": 14.248074807480748, "percentage": 71.24, "elapsed_time": "5:06:46", "remaining_time": "2:03:50", "throughput": 1484.9, "total_tokens": 27331712} {"current_steps": 129520, "total_steps": 181800, "loss": 0.0088, "lr": 1.1572975573318932e-05, "epoch": 14.248624862486249, "percentage": 71.24, "elapsed_time": "5:06:47", "remaining_time": "2:03:49", "throughput": 1484.9, "total_tokens": 27332768} {"current_steps": 129525, "total_steps": 181800, "loss": 0.1857, "lr": 1.1570951104411667e-05, "epoch": 14.249174917491748, "percentage": 71.25, "elapsed_time": "5:06:47", "remaining_time": "2:03:49", "throughput": 1484.91, "total_tokens": 27333856} {"current_steps": 129530, "total_steps": 181800, "loss": 0.0429, "lr": 1.1568926759273513e-05, "epoch": 14.24972497249725, "percentage": 71.25, "elapsed_time": "5:06:48", "remaining_time": "2:03:48", "throughput": 1484.91, "total_tokens": 27334912} {"current_steps": 129535, "total_steps": 181800, "loss": 0.1083, "lr": 1.1566902537923116e-05, "epoch": 14.25027502750275, "percentage": 71.25, "elapsed_time": "5:06:49", "remaining_time": "2:03:47", "throughput": 1484.91, "total_tokens": 27335936} {"current_steps": 129540, "total_steps": 181800, "loss": 0.0846, "lr": 1.156487844037912e-05, "epoch": 14.250825082508252, "percentage": 71.25, "elapsed_time": "5:06:49", "remaining_time": "2:03:47", "throughput": 1484.91, "total_tokens": 27336992} {"current_steps": 129545, "total_steps": 181800, "loss": 0.0027, "lr": 1.1562854466660197e-05, "epoch": 14.251375137513751, "percentage": 71.26, "elapsed_time": "5:06:50", "remaining_time": "2:03:46", "throughput": 1484.91, "total_tokens": 27338048} {"current_steps": 129550, "total_steps": 181800, "loss": 0.0126, "lr": 1.1560830616785004e-05, "epoch": 14.251925192519252, "percentage": 71.26, "elapsed_time": "5:06:51", "remaining_time": "2:03:45", "throughput": 1484.91, "total_tokens": 27339040} {"current_steps": 129555, "total_steps": 181800, "loss": 0.0065, "lr": 1.1558806890772175e-05, "epoch": 14.252475247524753, "percentage": 71.26, "elapsed_time": "5:06:51", "remaining_time": "2:03:44", "throughput": 1484.91, "total_tokens": 27340128} {"current_steps": 129560, "total_steps": 181800, "loss": 0.0351, "lr": 1.1556783288640386e-05, "epoch": 14.253025302530252, "percentage": 71.27, "elapsed_time": "5:06:52", "remaining_time": "2:03:44", "throughput": 1484.91, "total_tokens": 27341120} {"current_steps": 129565, "total_steps": 181800, "loss": 0.0145, "lr": 1.1554759810408264e-05, "epoch": 14.253575357535754, "percentage": 71.27, "elapsed_time": "5:06:53", "remaining_time": "2:03:43", "throughput": 1484.91, "total_tokens": 27342144} {"current_steps": 129570, "total_steps": 181800, "loss": 0.0149, "lr": 1.1552736456094476e-05, "epoch": 14.254125412541255, "percentage": 71.27, "elapsed_time": "5:06:53", "remaining_time": "2:03:42", "throughput": 1484.91, "total_tokens": 27343200} {"current_steps": 129575, "total_steps": 181800, "loss": 0.0265, "lr": 1.1550713225717658e-05, "epoch": 14.254675467546754, "percentage": 71.27, "elapsed_time": "5:06:54", "remaining_time": "2:03:42", "throughput": 1484.91, "total_tokens": 27344224} {"current_steps": 129580, "total_steps": 181800, "loss": 0.0034, "lr": 1.154869011929646e-05, "epoch": 14.255225522552255, "percentage": 71.28, "elapsed_time": "5:06:55", "remaining_time": "2:03:41", "throughput": 1484.92, "total_tokens": 27345280} {"current_steps": 129585, "total_steps": 181800, "loss": 0.0078, "lr": 1.1546667136849542e-05, "epoch": 14.255775577557756, "percentage": 71.28, "elapsed_time": "5:06:56", "remaining_time": "2:03:40", "throughput": 1484.92, "total_tokens": 27346432} {"current_steps": 129590, "total_steps": 181800, "loss": 0.0493, "lr": 1.1544644278395528e-05, "epoch": 14.256325632563255, "percentage": 71.28, "elapsed_time": "5:06:56", "remaining_time": "2:03:39", "throughput": 1484.92, "total_tokens": 27347456} {"current_steps": 129595, "total_steps": 181800, "loss": 0.0011, "lr": 1.1542621543953077e-05, "epoch": 14.256875687568757, "percentage": 71.28, "elapsed_time": "5:06:57", "remaining_time": "2:03:39", "throughput": 1484.93, "total_tokens": 27348640} {"current_steps": 129600, "total_steps": 181800, "loss": 0.0155, "lr": 1.1540598933540822e-05, "epoch": 14.257425742574258, "percentage": 71.29, "elapsed_time": "5:06:58", "remaining_time": "2:03:38", "throughput": 1484.93, "total_tokens": 27349728} {"current_steps": 129605, "total_steps": 181800, "loss": 0.0261, "lr": 1.1538576447177405e-05, "epoch": 14.257975797579759, "percentage": 71.29, "elapsed_time": "5:06:58", "remaining_time": "2:03:37", "throughput": 1484.93, "total_tokens": 27350752} {"current_steps": 129610, "total_steps": 181800, "loss": 0.0023, "lr": 1.153655408488148e-05, "epoch": 14.258525852585258, "percentage": 71.29, "elapsed_time": "5:06:59", "remaining_time": "2:03:36", "throughput": 1484.94, "total_tokens": 27351840} {"current_steps": 129615, "total_steps": 181800, "loss": 0.0019, "lr": 1.1534531846671665e-05, "epoch": 14.25907590759076, "percentage": 71.3, "elapsed_time": "5:07:00", "remaining_time": "2:03:36", "throughput": 1484.94, "total_tokens": 27352896} {"current_steps": 129620, "total_steps": 181800, "loss": 0.001, "lr": 1.1532509732566619e-05, "epoch": 14.25962596259626, "percentage": 71.3, "elapsed_time": "5:07:00", "remaining_time": "2:03:35", "throughput": 1484.94, "total_tokens": 27353984} {"current_steps": 129625, "total_steps": 181800, "loss": 0.0006, "lr": 1.1530487742584967e-05, "epoch": 14.26017601760176, "percentage": 71.3, "elapsed_time": "5:07:01", "remaining_time": "2:03:34", "throughput": 1484.94, "total_tokens": 27355040} {"current_steps": 129630, "total_steps": 181800, "loss": 0.1004, "lr": 1.1528465876745337e-05, "epoch": 14.26072607260726, "percentage": 71.3, "elapsed_time": "5:07:02", "remaining_time": "2:03:34", "throughput": 1484.94, "total_tokens": 27356064} {"current_steps": 129635, "total_steps": 181800, "loss": 0.0268, "lr": 1.1526444135066372e-05, "epoch": 14.261276127612762, "percentage": 71.31, "elapsed_time": "5:07:02", "remaining_time": "2:03:33", "throughput": 1484.95, "total_tokens": 27357184} {"current_steps": 129640, "total_steps": 181800, "loss": 0.0108, "lr": 1.1524422517566707e-05, "epoch": 14.261826182618261, "percentage": 71.31, "elapsed_time": "5:07:03", "remaining_time": "2:03:32", "throughput": 1484.95, "total_tokens": 27358240} {"current_steps": 129645, "total_steps": 181800, "loss": 0.0043, "lr": 1.1522401024264984e-05, "epoch": 14.262376237623762, "percentage": 71.31, "elapsed_time": "5:07:04", "remaining_time": "2:03:31", "throughput": 1484.96, "total_tokens": 27359328} {"current_steps": 129650, "total_steps": 181800, "loss": 0.0041, "lr": 1.1520379655179825e-05, "epoch": 14.262926292629263, "percentage": 71.31, "elapsed_time": "5:07:05", "remaining_time": "2:03:31", "throughput": 1484.96, "total_tokens": 27360384} {"current_steps": 129655, "total_steps": 181800, "loss": 0.1388, "lr": 1.1518358410329846e-05, "epoch": 14.263476347634764, "percentage": 71.32, "elapsed_time": "5:07:05", "remaining_time": "2:03:30", "throughput": 1484.96, "total_tokens": 27361472} {"current_steps": 129660, "total_steps": 181800, "loss": 0.002, "lr": 1.151633728973369e-05, "epoch": 14.264026402640264, "percentage": 71.32, "elapsed_time": "5:07:06", "remaining_time": "2:03:29", "throughput": 1484.96, "total_tokens": 27362496} {"current_steps": 129665, "total_steps": 181800, "loss": 0.001, "lr": 1.1514316293409983e-05, "epoch": 14.264576457645765, "percentage": 71.32, "elapsed_time": "5:07:07", "remaining_time": "2:03:29", "throughput": 1484.96, "total_tokens": 27363520} {"current_steps": 129670, "total_steps": 181800, "loss": 0.0009, "lr": 1.151229542137736e-05, "epoch": 14.265126512651266, "percentage": 71.33, "elapsed_time": "5:07:07", "remaining_time": "2:03:28", "throughput": 1484.96, "total_tokens": 27364608} {"current_steps": 129675, "total_steps": 181800, "loss": 0.0099, "lr": 1.1510274673654438e-05, "epoch": 14.265676567656765, "percentage": 71.33, "elapsed_time": "5:07:08", "remaining_time": "2:03:27", "throughput": 1484.96, "total_tokens": 27365600} {"current_steps": 129680, "total_steps": 181800, "loss": 0.0055, "lr": 1.1508254050259834e-05, "epoch": 14.266226622662266, "percentage": 71.33, "elapsed_time": "5:07:09", "remaining_time": "2:03:26", "throughput": 1484.96, "total_tokens": 27366656} {"current_steps": 129685, "total_steps": 181800, "loss": 0.0392, "lr": 1.1506233551212186e-05, "epoch": 14.266776677667767, "percentage": 71.33, "elapsed_time": "5:07:09", "remaining_time": "2:03:26", "throughput": 1484.96, "total_tokens": 27367680} {"current_steps": 129690, "total_steps": 181800, "loss": 0.004, "lr": 1.1504213176530099e-05, "epoch": 14.267326732673267, "percentage": 71.34, "elapsed_time": "5:07:10", "remaining_time": "2:03:25", "throughput": 1484.97, "total_tokens": 27368800} {"current_steps": 129695, "total_steps": 181800, "loss": 0.0032, "lr": 1.1502192926232203e-05, "epoch": 14.267876787678768, "percentage": 71.34, "elapsed_time": "5:07:11", "remaining_time": "2:03:24", "throughput": 1484.97, "total_tokens": 27369888} {"current_steps": 129700, "total_steps": 181800, "loss": 0.0877, "lr": 1.1500172800337128e-05, "epoch": 14.268426842684269, "percentage": 71.34, "elapsed_time": "5:07:11", "remaining_time": "2:03:24", "throughput": 1484.97, "total_tokens": 27370944} {"current_steps": 129705, "total_steps": 181800, "loss": 0.0046, "lr": 1.1498152798863474e-05, "epoch": 14.268976897689768, "percentage": 71.34, "elapsed_time": "5:07:12", "remaining_time": "2:03:23", "throughput": 1484.97, "total_tokens": 27371936} {"current_steps": 129710, "total_steps": 181800, "loss": 0.0061, "lr": 1.1496132921829874e-05, "epoch": 14.26952695269527, "percentage": 71.35, "elapsed_time": "5:07:13", "remaining_time": "2:03:22", "throughput": 1484.97, "total_tokens": 27372992} {"current_steps": 129715, "total_steps": 181800, "loss": 0.0277, "lr": 1.1494113169254931e-05, "epoch": 14.27007700770077, "percentage": 71.35, "elapsed_time": "5:07:14", "remaining_time": "2:03:21", "throughput": 1484.97, "total_tokens": 27373984} {"current_steps": 129720, "total_steps": 181800, "loss": 0.0353, "lr": 1.1492093541157265e-05, "epoch": 14.270627062706271, "percentage": 71.35, "elapsed_time": "5:07:14", "remaining_time": "2:03:21", "throughput": 1484.97, "total_tokens": 27375040} {"current_steps": 129725, "total_steps": 181800, "loss": 0.1105, "lr": 1.1490074037555499e-05, "epoch": 14.27117711771177, "percentage": 71.36, "elapsed_time": "5:07:15", "remaining_time": "2:03:20", "throughput": 1484.97, "total_tokens": 27376032} {"current_steps": 129730, "total_steps": 181800, "loss": 0.0056, "lr": 1.1488054658468228e-05, "epoch": 14.271727172717272, "percentage": 71.36, "elapsed_time": "5:07:16", "remaining_time": "2:03:19", "throughput": 1484.98, "total_tokens": 27377152} {"current_steps": 129735, "total_steps": 181800, "loss": 0.0104, "lr": 1.1486035403914085e-05, "epoch": 14.272277227722773, "percentage": 71.36, "elapsed_time": "5:07:16", "remaining_time": "2:03:19", "throughput": 1484.98, "total_tokens": 27378176} {"current_steps": 129740, "total_steps": 181800, "loss": 0.0042, "lr": 1.1484016273911669e-05, "epoch": 14.272827282728272, "percentage": 71.36, "elapsed_time": "5:07:17", "remaining_time": "2:03:18", "throughput": 1484.98, "total_tokens": 27379232} {"current_steps": 129745, "total_steps": 181800, "loss": 0.0346, "lr": 1.1481997268479578e-05, "epoch": 14.273377337733773, "percentage": 71.37, "elapsed_time": "5:07:18", "remaining_time": "2:03:17", "throughput": 1484.96, "total_tokens": 27380288} {"current_steps": 129750, "total_steps": 181800, "loss": 0.0008, "lr": 1.1479978387636434e-05, "epoch": 14.273927392739274, "percentage": 71.37, "elapsed_time": "5:07:19", "remaining_time": "2:03:16", "throughput": 1484.96, "total_tokens": 27381344} {"current_steps": 129755, "total_steps": 181800, "loss": 0.0013, "lr": 1.147795963140084e-05, "epoch": 14.274477447744774, "percentage": 71.37, "elapsed_time": "5:07:19", "remaining_time": "2:03:16", "throughput": 1484.97, "total_tokens": 27382400} {"current_steps": 129760, "total_steps": 181800, "loss": 0.0499, "lr": 1.1475940999791413e-05, "epoch": 14.275027502750275, "percentage": 71.38, "elapsed_time": "5:07:20", "remaining_time": "2:03:15", "throughput": 1484.97, "total_tokens": 27383424} {"current_steps": 129765, "total_steps": 181800, "loss": 0.0052, "lr": 1.147392249282675e-05, "epoch": 14.275577557755776, "percentage": 71.38, "elapsed_time": "5:07:21", "remaining_time": "2:03:14", "throughput": 1484.97, "total_tokens": 27384448} {"current_steps": 129770, "total_steps": 181800, "loss": 0.0862, "lr": 1.1471904110525442e-05, "epoch": 14.276127612761275, "percentage": 71.38, "elapsed_time": "5:07:21", "remaining_time": "2:03:14", "throughput": 1484.96, "total_tokens": 27385440} {"current_steps": 129775, "total_steps": 181800, "loss": 0.0119, "lr": 1.1469885852906102e-05, "epoch": 14.276677667766776, "percentage": 71.38, "elapsed_time": "5:07:22", "remaining_time": "2:03:13", "throughput": 1484.97, "total_tokens": 27386560} {"current_steps": 129780, "total_steps": 181800, "loss": 0.0024, "lr": 1.1467867719987333e-05, "epoch": 14.277227722772277, "percentage": 71.39, "elapsed_time": "5:07:23", "remaining_time": "2:03:12", "throughput": 1484.97, "total_tokens": 27387616} {"current_steps": 129785, "total_steps": 181800, "loss": 0.0506, "lr": 1.1465849711787744e-05, "epoch": 14.277777777777779, "percentage": 71.39, "elapsed_time": "5:07:23", "remaining_time": "2:03:11", "throughput": 1484.97, "total_tokens": 27388704} {"current_steps": 129790, "total_steps": 181800, "loss": 0.043, "lr": 1.1463831828325921e-05, "epoch": 14.278327832783278, "percentage": 71.39, "elapsed_time": "5:07:24", "remaining_time": "2:03:11", "throughput": 1484.98, "total_tokens": 27389792} {"current_steps": 129795, "total_steps": 181800, "loss": 0.0061, "lr": 1.1461814069620458e-05, "epoch": 14.278877887788779, "percentage": 71.39, "elapsed_time": "5:07:25", "remaining_time": "2:03:10", "throughput": 1484.98, "total_tokens": 27390880} {"current_steps": 129800, "total_steps": 181800, "loss": 0.063, "lr": 1.1459796435689966e-05, "epoch": 14.27942794279428, "percentage": 71.4, "elapsed_time": "5:07:25", "remaining_time": "2:03:09", "throughput": 1484.98, "total_tokens": 27391936} {"current_steps": 129805, "total_steps": 181800, "loss": 0.0064, "lr": 1.1457778926553026e-05, "epoch": 14.27997799779978, "percentage": 71.4, "elapsed_time": "5:07:26", "remaining_time": "2:03:09", "throughput": 1484.99, "total_tokens": 27393024} {"current_steps": 129810, "total_steps": 181800, "loss": 0.016, "lr": 1.1455761542228236e-05, "epoch": 14.28052805280528, "percentage": 71.4, "elapsed_time": "5:07:27", "remaining_time": "2:03:08", "throughput": 1484.99, "total_tokens": 27394080} {"current_steps": 129815, "total_steps": 181800, "loss": 0.1159, "lr": 1.1453744282734204e-05, "epoch": 14.281078107810782, "percentage": 71.41, "elapsed_time": "5:07:28", "remaining_time": "2:03:07", "throughput": 1484.99, "total_tokens": 27395072} {"current_steps": 129820, "total_steps": 181800, "loss": 0.0039, "lr": 1.1451727148089502e-05, "epoch": 14.281628162816281, "percentage": 71.41, "elapsed_time": "5:07:28", "remaining_time": "2:03:06", "throughput": 1484.99, "total_tokens": 27396128} {"current_steps": 129825, "total_steps": 181800, "loss": 0.0046, "lr": 1.1449710138312739e-05, "epoch": 14.282178217821782, "percentage": 71.41, "elapsed_time": "5:07:29", "remaining_time": "2:03:06", "throughput": 1484.99, "total_tokens": 27397184} {"current_steps": 129830, "total_steps": 181800, "loss": 0.0183, "lr": 1.1447693253422484e-05, "epoch": 14.282728272827283, "percentage": 71.41, "elapsed_time": "5:07:30", "remaining_time": "2:03:05", "throughput": 1484.99, "total_tokens": 27398240} {"current_steps": 129835, "total_steps": 181800, "loss": 0.0055, "lr": 1.1445676493437341e-05, "epoch": 14.283278327832782, "percentage": 71.42, "elapsed_time": "5:07:30", "remaining_time": "2:03:04", "throughput": 1484.99, "total_tokens": 27399296} {"current_steps": 129840, "total_steps": 181800, "loss": 0.0364, "lr": 1.1443659858375899e-05, "epoch": 14.283828382838283, "percentage": 71.42, "elapsed_time": "5:07:31", "remaining_time": "2:03:04", "throughput": 1485.0, "total_tokens": 27400480} {"current_steps": 129845, "total_steps": 181800, "loss": 0.0631, "lr": 1.1441643348256734e-05, "epoch": 14.284378437843785, "percentage": 71.42, "elapsed_time": "5:07:32", "remaining_time": "2:03:03", "throughput": 1485.0, "total_tokens": 27401536} {"current_steps": 129850, "total_steps": 181800, "loss": 0.0049, "lr": 1.1439626963098442e-05, "epoch": 14.284928492849286, "percentage": 71.42, "elapsed_time": "5:07:32", "remaining_time": "2:03:02", "throughput": 1485.01, "total_tokens": 27402624} {"current_steps": 129855, "total_steps": 181800, "loss": 0.0013, "lr": 1.1437610702919596e-05, "epoch": 14.285478547854785, "percentage": 71.43, "elapsed_time": "5:07:33", "remaining_time": "2:03:01", "throughput": 1485.01, "total_tokens": 27403712} {"current_steps": 129860, "total_steps": 181800, "loss": 0.0015, "lr": 1.1435594567738791e-05, "epoch": 14.286028602860286, "percentage": 71.43, "elapsed_time": "5:07:34", "remaining_time": "2:03:01", "throughput": 1485.01, "total_tokens": 27404832} {"current_steps": 129865, "total_steps": 181800, "loss": 0.0012, "lr": 1.1433578557574593e-05, "epoch": 14.286578657865787, "percentage": 71.43, "elapsed_time": "5:07:34", "remaining_time": "2:03:00", "throughput": 1485.02, "total_tokens": 27405888} {"current_steps": 129870, "total_steps": 181800, "loss": 0.0886, "lr": 1.1431562672445593e-05, "epoch": 14.287128712871286, "percentage": 71.44, "elapsed_time": "5:07:35", "remaining_time": "2:02:59", "throughput": 1485.02, "total_tokens": 27406944} {"current_steps": 129875, "total_steps": 181800, "loss": 0.0015, "lr": 1.1429546912370376e-05, "epoch": 14.287678767876788, "percentage": 71.44, "elapsed_time": "5:07:36", "remaining_time": "2:02:58", "throughput": 1485.02, "total_tokens": 27407968} {"current_steps": 129880, "total_steps": 181800, "loss": 0.0834, "lr": 1.1427531277367503e-05, "epoch": 14.288228822882289, "percentage": 71.44, "elapsed_time": "5:07:37", "remaining_time": "2:02:58", "throughput": 1485.02, "total_tokens": 27409024} {"current_steps": 129885, "total_steps": 181800, "loss": 0.0042, "lr": 1.1425515767455574e-05, "epoch": 14.288778877887788, "percentage": 71.44, "elapsed_time": "5:07:37", "remaining_time": "2:02:57", "throughput": 1485.02, "total_tokens": 27410144} {"current_steps": 129890, "total_steps": 181800, "loss": 0.0249, "lr": 1.1423500382653151e-05, "epoch": 14.289328932893289, "percentage": 71.45, "elapsed_time": "5:07:38", "remaining_time": "2:02:56", "throughput": 1485.03, "total_tokens": 27411200} {"current_steps": 129895, "total_steps": 181800, "loss": 0.0629, "lr": 1.1421485122978792e-05, "epoch": 14.28987898789879, "percentage": 71.45, "elapsed_time": "5:07:39", "remaining_time": "2:02:56", "throughput": 1485.03, "total_tokens": 27412256} {"current_steps": 129900, "total_steps": 181800, "loss": 0.0246, "lr": 1.141946998845111e-05, "epoch": 14.290429042904291, "percentage": 71.45, "elapsed_time": "5:07:39", "remaining_time": "2:02:55", "throughput": 1485.03, "total_tokens": 27413248} {"current_steps": 129905, "total_steps": 181800, "loss": 0.0013, "lr": 1.1417454979088643e-05, "epoch": 14.29097909790979, "percentage": 71.45, "elapsed_time": "5:07:40", "remaining_time": "2:02:54", "throughput": 1485.03, "total_tokens": 27414304} {"current_steps": 129910, "total_steps": 181800, "loss": 0.0018, "lr": 1.1415440094909988e-05, "epoch": 14.291529152915292, "percentage": 71.46, "elapsed_time": "5:07:41", "remaining_time": "2:02:53", "throughput": 1485.03, "total_tokens": 27415392} {"current_steps": 129915, "total_steps": 181800, "loss": 0.0024, "lr": 1.1413425335933702e-05, "epoch": 14.292079207920793, "percentage": 71.46, "elapsed_time": "5:07:41", "remaining_time": "2:02:53", "throughput": 1485.03, "total_tokens": 27416416} {"current_steps": 129920, "total_steps": 181800, "loss": 0.0085, "lr": 1.1411410702178346e-05, "epoch": 14.292629262926292, "percentage": 71.46, "elapsed_time": "5:07:42", "remaining_time": "2:02:52", "throughput": 1485.03, "total_tokens": 27417504} {"current_steps": 129925, "total_steps": 181800, "loss": 0.0027, "lr": 1.1409396193662498e-05, "epoch": 14.293179317931793, "percentage": 71.47, "elapsed_time": "5:07:43", "remaining_time": "2:02:51", "throughput": 1485.03, "total_tokens": 27418528} {"current_steps": 129930, "total_steps": 181800, "loss": 0.0104, "lr": 1.1407381810404732e-05, "epoch": 14.293729372937294, "percentage": 71.47, "elapsed_time": "5:07:43", "remaining_time": "2:02:51", "throughput": 1485.04, "total_tokens": 27419648} {"current_steps": 129935, "total_steps": 181800, "loss": 0.0034, "lr": 1.1405367552423596e-05, "epoch": 14.294279427942794, "percentage": 71.47, "elapsed_time": "5:07:44", "remaining_time": "2:02:50", "throughput": 1485.04, "total_tokens": 27420704} {"current_steps": 129940, "total_steps": 181800, "loss": 0.0126, "lr": 1.1403353419737675e-05, "epoch": 14.294829482948295, "percentage": 71.47, "elapsed_time": "5:07:45", "remaining_time": "2:02:49", "throughput": 1485.05, "total_tokens": 27421824} {"current_steps": 129945, "total_steps": 181800, "loss": 0.0022, "lr": 1.140133941236551e-05, "epoch": 14.295379537953796, "percentage": 71.48, "elapsed_time": "5:07:45", "remaining_time": "2:02:48", "throughput": 1485.05, "total_tokens": 27422976} {"current_steps": 129950, "total_steps": 181800, "loss": 0.0643, "lr": 1.1399325530325678e-05, "epoch": 14.295929592959295, "percentage": 71.48, "elapsed_time": "5:07:46", "remaining_time": "2:02:48", "throughput": 1485.05, "total_tokens": 27424000} {"current_steps": 129955, "total_steps": 181800, "loss": 0.0012, "lr": 1.139731177363674e-05, "epoch": 14.296479647964796, "percentage": 71.48, "elapsed_time": "5:07:47", "remaining_time": "2:02:47", "throughput": 1485.05, "total_tokens": 27425024} {"current_steps": 129960, "total_steps": 181800, "loss": 0.0024, "lr": 1.1395298142317248e-05, "epoch": 14.297029702970297, "percentage": 71.49, "elapsed_time": "5:07:48", "remaining_time": "2:02:46", "throughput": 1485.05, "total_tokens": 27426080} {"current_steps": 129965, "total_steps": 181800, "loss": 0.0099, "lr": 1.139328463638577e-05, "epoch": 14.297579757975798, "percentage": 71.49, "elapsed_time": "5:07:48", "remaining_time": "2:02:46", "throughput": 1485.06, "total_tokens": 27427200} {"current_steps": 129970, "total_steps": 181800, "loss": 0.0449, "lr": 1.1391271255860853e-05, "epoch": 14.298129812981298, "percentage": 71.49, "elapsed_time": "5:07:49", "remaining_time": "2:02:45", "throughput": 1485.06, "total_tokens": 27428288} {"current_steps": 129975, "total_steps": 181800, "loss": 0.0489, "lr": 1.1389258000761066e-05, "epoch": 14.298679867986799, "percentage": 71.49, "elapsed_time": "5:07:50", "remaining_time": "2:02:44", "throughput": 1485.07, "total_tokens": 27429376} {"current_steps": 129980, "total_steps": 181800, "loss": 0.0008, "lr": 1.1387244871104946e-05, "epoch": 14.2992299229923, "percentage": 71.5, "elapsed_time": "5:07:50", "remaining_time": "2:02:43", "throughput": 1485.07, "total_tokens": 27430464} {"current_steps": 129985, "total_steps": 181800, "loss": 0.0027, "lr": 1.1385231866911061e-05, "epoch": 14.2997799779978, "percentage": 71.5, "elapsed_time": "5:07:51", "remaining_time": "2:02:43", "throughput": 1485.07, "total_tokens": 27431584} {"current_steps": 129990, "total_steps": 181800, "loss": 0.0505, "lr": 1.138321898819797e-05, "epoch": 14.3003300330033, "percentage": 71.5, "elapsed_time": "5:07:52", "remaining_time": "2:02:42", "throughput": 1485.07, "total_tokens": 27432608} {"current_steps": 129995, "total_steps": 181800, "loss": 0.2808, "lr": 1.1381206234984204e-05, "epoch": 14.300880088008801, "percentage": 71.5, "elapsed_time": "5:07:52", "remaining_time": "2:02:41", "throughput": 1485.08, "total_tokens": 27433632} {"current_steps": 130000, "total_steps": 181800, "loss": 0.0046, "lr": 1.1379193607288336e-05, "epoch": 14.3014301430143, "percentage": 71.51, "elapsed_time": "5:07:53", "remaining_time": "2:02:41", "throughput": 1485.08, "total_tokens": 27434656} {"current_steps": 130005, "total_steps": 181800, "loss": 0.008, "lr": 1.1377181105128903e-05, "epoch": 14.301980198019802, "percentage": 71.51, "elapsed_time": "5:07:54", "remaining_time": "2:02:40", "throughput": 1485.08, "total_tokens": 27435712} {"current_steps": 130010, "total_steps": 181800, "loss": 0.0395, "lr": 1.1375168728524439e-05, "epoch": 14.302530253025303, "percentage": 71.51, "elapsed_time": "5:07:54", "remaining_time": "2:02:39", "throughput": 1485.08, "total_tokens": 27436704} {"current_steps": 130015, "total_steps": 181800, "loss": 0.0114, "lr": 1.1373156477493524e-05, "epoch": 14.303080308030804, "percentage": 71.52, "elapsed_time": "5:07:55", "remaining_time": "2:02:38", "throughput": 1485.08, "total_tokens": 27437728} {"current_steps": 130020, "total_steps": 181800, "loss": 0.0044, "lr": 1.1371144352054678e-05, "epoch": 14.303630363036303, "percentage": 71.52, "elapsed_time": "5:07:56", "remaining_time": "2:02:38", "throughput": 1485.08, "total_tokens": 27438784} {"current_steps": 130025, "total_steps": 181800, "loss": 0.0964, "lr": 1.1369132352226464e-05, "epoch": 14.304180418041804, "percentage": 71.52, "elapsed_time": "5:07:57", "remaining_time": "2:02:37", "throughput": 1485.08, "total_tokens": 27439840} {"current_steps": 130030, "total_steps": 181800, "loss": 0.1104, "lr": 1.1367120478027416e-05, "epoch": 14.304730473047305, "percentage": 71.52, "elapsed_time": "5:07:57", "remaining_time": "2:02:36", "throughput": 1485.08, "total_tokens": 27440864} {"current_steps": 130035, "total_steps": 181800, "loss": 0.0014, "lr": 1.1365108729476068e-05, "epoch": 14.305280528052805, "percentage": 71.53, "elapsed_time": "5:07:58", "remaining_time": "2:02:35", "throughput": 1485.08, "total_tokens": 27441888} {"current_steps": 130040, "total_steps": 181800, "loss": 0.016, "lr": 1.136309710659097e-05, "epoch": 14.305830583058306, "percentage": 71.53, "elapsed_time": "5:07:59", "remaining_time": "2:02:35", "throughput": 1485.08, "total_tokens": 27442944} {"current_steps": 130045, "total_steps": 181800, "loss": 0.0025, "lr": 1.1361085609390662e-05, "epoch": 14.306380638063807, "percentage": 71.53, "elapsed_time": "5:07:59", "remaining_time": "2:02:34", "throughput": 1485.08, "total_tokens": 27444000} {"current_steps": 130050, "total_steps": 181800, "loss": 0.0816, "lr": 1.1359074237893694e-05, "epoch": 14.306930693069306, "percentage": 71.53, "elapsed_time": "5:08:00", "remaining_time": "2:02:33", "throughput": 1485.08, "total_tokens": 27445056} {"current_steps": 130055, "total_steps": 181800, "loss": 0.0026, "lr": 1.1357062992118591e-05, "epoch": 14.307480748074807, "percentage": 71.54, "elapsed_time": "5:08:01", "remaining_time": "2:02:33", "throughput": 1485.09, "total_tokens": 27446176} {"current_steps": 130060, "total_steps": 181800, "loss": 0.0016, "lr": 1.1355051872083886e-05, "epoch": 14.308030803080309, "percentage": 71.54, "elapsed_time": "5:08:01", "remaining_time": "2:02:32", "throughput": 1485.09, "total_tokens": 27447232} {"current_steps": 130065, "total_steps": 181800, "loss": 0.002, "lr": 1.1353040877808127e-05, "epoch": 14.308580858085808, "percentage": 71.54, "elapsed_time": "5:08:02", "remaining_time": "2:02:31", "throughput": 1485.09, "total_tokens": 27448256} {"current_steps": 130070, "total_steps": 181800, "loss": 0.0018, "lr": 1.1351030009309824e-05, "epoch": 14.309130913091309, "percentage": 71.55, "elapsed_time": "5:08:03", "remaining_time": "2:02:30", "throughput": 1485.1, "total_tokens": 27449376} {"current_steps": 130075, "total_steps": 181800, "loss": 0.0661, "lr": 1.1349019266607543e-05, "epoch": 14.30968096809681, "percentage": 71.55, "elapsed_time": "5:08:03", "remaining_time": "2:02:30", "throughput": 1485.1, "total_tokens": 27450496} {"current_steps": 130080, "total_steps": 181800, "loss": 0.1071, "lr": 1.1347008649719807e-05, "epoch": 14.310231023102311, "percentage": 71.55, "elapsed_time": "5:08:04", "remaining_time": "2:02:29", "throughput": 1485.1, "total_tokens": 27451488} {"current_steps": 130085, "total_steps": 181800, "loss": 0.003, "lr": 1.134499815866513e-05, "epoch": 14.31078107810781, "percentage": 71.55, "elapsed_time": "5:08:05", "remaining_time": "2:02:28", "throughput": 1485.1, "total_tokens": 27452512} {"current_steps": 130090, "total_steps": 181800, "loss": 0.0529, "lr": 1.134298779346206e-05, "epoch": 14.311331133113312, "percentage": 71.56, "elapsed_time": "5:08:05", "remaining_time": "2:02:28", "throughput": 1485.1, "total_tokens": 27453600} {"current_steps": 130095, "total_steps": 181800, "loss": 0.0188, "lr": 1.1340977554129109e-05, "epoch": 14.311881188118813, "percentage": 71.56, "elapsed_time": "5:08:06", "remaining_time": "2:02:27", "throughput": 1485.11, "total_tokens": 27454688} {"current_steps": 130100, "total_steps": 181800, "loss": 0.0028, "lr": 1.1338967440684814e-05, "epoch": 14.312431243124312, "percentage": 71.56, "elapsed_time": "5:08:07", "remaining_time": "2:02:26", "throughput": 1485.11, "total_tokens": 27455744} {"current_steps": 130105, "total_steps": 181800, "loss": 0.1043, "lr": 1.1336957453147711e-05, "epoch": 14.312981298129813, "percentage": 71.56, "elapsed_time": "5:08:08", "remaining_time": "2:02:25", "throughput": 1485.11, "total_tokens": 27456800} {"current_steps": 130110, "total_steps": 181800, "loss": 0.0197, "lr": 1.1334947591536305e-05, "epoch": 14.313531353135314, "percentage": 71.57, "elapsed_time": "5:08:08", "remaining_time": "2:02:25", "throughput": 1485.11, "total_tokens": 27457760} {"current_steps": 130115, "total_steps": 181800, "loss": 0.0229, "lr": 1.1332937855869142e-05, "epoch": 14.314081408140813, "percentage": 71.57, "elapsed_time": "5:08:09", "remaining_time": "2:02:24", "throughput": 1485.1, "total_tokens": 27458752} {"current_steps": 130120, "total_steps": 181800, "loss": 0.0311, "lr": 1.1330928246164729e-05, "epoch": 14.314631463146315, "percentage": 71.57, "elapsed_time": "5:08:10", "remaining_time": "2:02:23", "throughput": 1485.11, "total_tokens": 27459808} {"current_steps": 130125, "total_steps": 181800, "loss": 0.0041, "lr": 1.1328918762441581e-05, "epoch": 14.315181518151816, "percentage": 71.58, "elapsed_time": "5:08:10", "remaining_time": "2:02:23", "throughput": 1485.11, "total_tokens": 27460864} {"current_steps": 130130, "total_steps": 181800, "loss": 0.0089, "lr": 1.1326909404718234e-05, "epoch": 14.315731573157315, "percentage": 71.58, "elapsed_time": "5:08:11", "remaining_time": "2:02:22", "throughput": 1485.11, "total_tokens": 27461952} {"current_steps": 130135, "total_steps": 181800, "loss": 0.0052, "lr": 1.1324900173013197e-05, "epoch": 14.316281628162816, "percentage": 71.58, "elapsed_time": "5:08:12", "remaining_time": "2:02:21", "throughput": 1485.11, "total_tokens": 27462976} {"current_steps": 130140, "total_steps": 181800, "loss": 0.0558, "lr": 1.1322891067345006e-05, "epoch": 14.316831683168317, "percentage": 71.58, "elapsed_time": "5:08:12", "remaining_time": "2:02:20", "throughput": 1485.11, "total_tokens": 27464032} {"current_steps": 130145, "total_steps": 181800, "loss": 0.0022, "lr": 1.1320882087732162e-05, "epoch": 14.317381738173818, "percentage": 71.59, "elapsed_time": "5:08:13", "remaining_time": "2:02:20", "throughput": 1485.12, "total_tokens": 27465088} {"current_steps": 130150, "total_steps": 181800, "loss": 0.0021, "lr": 1.1318873234193179e-05, "epoch": 14.317931793179318, "percentage": 71.59, "elapsed_time": "5:08:14", "remaining_time": "2:02:19", "throughput": 1485.12, "total_tokens": 27466176} {"current_steps": 130155, "total_steps": 181800, "loss": 0.0015, "lr": 1.1316864506746571e-05, "epoch": 14.318481848184819, "percentage": 71.59, "elapsed_time": "5:08:14", "remaining_time": "2:02:18", "throughput": 1485.12, "total_tokens": 27467264} {"current_steps": 130160, "total_steps": 181800, "loss": 0.0051, "lr": 1.1314855905410862e-05, "epoch": 14.31903190319032, "percentage": 71.6, "elapsed_time": "5:08:15", "remaining_time": "2:02:18", "throughput": 1485.12, "total_tokens": 27468288} {"current_steps": 130165, "total_steps": 181800, "loss": 0.0175, "lr": 1.1312847430204566e-05, "epoch": 14.319581958195819, "percentage": 71.6, "elapsed_time": "5:08:16", "remaining_time": "2:02:17", "throughput": 1485.12, "total_tokens": 27469280} {"current_steps": 130170, "total_steps": 181800, "loss": 0.057, "lr": 1.1310839081146189e-05, "epoch": 14.32013201320132, "percentage": 71.6, "elapsed_time": "5:08:17", "remaining_time": "2:02:16", "throughput": 1485.13, "total_tokens": 27470368} {"current_steps": 130175, "total_steps": 181800, "loss": 0.051, "lr": 1.1308830858254228e-05, "epoch": 14.320682068206821, "percentage": 71.6, "elapsed_time": "5:08:17", "remaining_time": "2:02:15", "throughput": 1485.13, "total_tokens": 27471488} {"current_steps": 130180, "total_steps": 181800, "loss": 0.0075, "lr": 1.1306822761547214e-05, "epoch": 14.32123212321232, "percentage": 71.61, "elapsed_time": "5:08:18", "remaining_time": "2:02:15", "throughput": 1485.14, "total_tokens": 27472608} {"current_steps": 130185, "total_steps": 181800, "loss": 0.0938, "lr": 1.1304814791043633e-05, "epoch": 14.321782178217822, "percentage": 71.61, "elapsed_time": "5:08:19", "remaining_time": "2:02:14", "throughput": 1485.14, "total_tokens": 27473664} {"current_steps": 130190, "total_steps": 181800, "loss": 0.0171, "lr": 1.1302806946762004e-05, "epoch": 14.322332233223323, "percentage": 71.61, "elapsed_time": "5:08:19", "remaining_time": "2:02:13", "throughput": 1485.14, "total_tokens": 27474752} {"current_steps": 130195, "total_steps": 181800, "loss": 0.0016, "lr": 1.130079922872084e-05, "epoch": 14.322882288228822, "percentage": 71.61, "elapsed_time": "5:08:20", "remaining_time": "2:02:12", "throughput": 1485.14, "total_tokens": 27475840} {"current_steps": 130200, "total_steps": 181800, "loss": 0.0344, "lr": 1.1298791636938627e-05, "epoch": 14.323432343234323, "percentage": 71.62, "elapsed_time": "5:08:21", "remaining_time": "2:02:12", "throughput": 1485.15, "total_tokens": 27476896} {"current_steps": 130205, "total_steps": 181800, "loss": 0.0006, "lr": 1.1296784171433888e-05, "epoch": 14.323982398239824, "percentage": 71.62, "elapsed_time": "5:08:21", "remaining_time": "2:02:11", "throughput": 1485.15, "total_tokens": 27478016} {"current_steps": 130210, "total_steps": 181800, "loss": 0.0252, "lr": 1.1294776832225102e-05, "epoch": 14.324532453245325, "percentage": 71.62, "elapsed_time": "5:08:22", "remaining_time": "2:02:10", "throughput": 1485.15, "total_tokens": 27479104} {"current_steps": 130215, "total_steps": 181800, "loss": 0.0315, "lr": 1.1292769619330782e-05, "epoch": 14.325082508250825, "percentage": 71.63, "elapsed_time": "5:08:23", "remaining_time": "2:02:10", "throughput": 1485.16, "total_tokens": 27480192} {"current_steps": 130220, "total_steps": 181800, "loss": 0.1298, "lr": 1.1290762532769436e-05, "epoch": 14.325632563256326, "percentage": 71.63, "elapsed_time": "5:08:23", "remaining_time": "2:02:09", "throughput": 1485.16, "total_tokens": 27481216} {"current_steps": 130225, "total_steps": 181800, "loss": 0.0065, "lr": 1.1288755572559545e-05, "epoch": 14.326182618261827, "percentage": 71.63, "elapsed_time": "5:08:24", "remaining_time": "2:02:08", "throughput": 1485.16, "total_tokens": 27482368} {"current_steps": 130230, "total_steps": 181800, "loss": 0.0728, "lr": 1.1286748738719623e-05, "epoch": 14.326732673267326, "percentage": 71.63, "elapsed_time": "5:08:25", "remaining_time": "2:02:07", "throughput": 1485.17, "total_tokens": 27483424} {"current_steps": 130235, "total_steps": 181800, "loss": 0.1199, "lr": 1.128474203126815e-05, "epoch": 14.327282728272827, "percentage": 71.64, "elapsed_time": "5:08:25", "remaining_time": "2:02:07", "throughput": 1485.17, "total_tokens": 27484480} {"current_steps": 130240, "total_steps": 181800, "loss": 0.0629, "lr": 1.1282735450223636e-05, "epoch": 14.327832783278328, "percentage": 71.64, "elapsed_time": "5:08:26", "remaining_time": "2:02:06", "throughput": 1485.17, "total_tokens": 27485536} {"current_steps": 130245, "total_steps": 181800, "loss": 0.0016, "lr": 1.128072899560456e-05, "epoch": 14.328382838283828, "percentage": 71.64, "elapsed_time": "5:08:27", "remaining_time": "2:02:05", "throughput": 1485.17, "total_tokens": 27486624} {"current_steps": 130250, "total_steps": 181800, "loss": 0.1081, "lr": 1.127872266742942e-05, "epoch": 14.328932893289329, "percentage": 71.64, "elapsed_time": "5:08:28", "remaining_time": "2:02:05", "throughput": 1485.17, "total_tokens": 27487648} {"current_steps": 130255, "total_steps": 181800, "loss": 0.0106, "lr": 1.127671646571672e-05, "epoch": 14.32948294829483, "percentage": 71.65, "elapsed_time": "5:08:28", "remaining_time": "2:02:04", "throughput": 1485.17, "total_tokens": 27488704} {"current_steps": 130260, "total_steps": 181800, "loss": 0.0021, "lr": 1.1274710390484928e-05, "epoch": 14.33003300330033, "percentage": 71.65, "elapsed_time": "5:08:29", "remaining_time": "2:02:03", "throughput": 1485.18, "total_tokens": 27489792} {"current_steps": 130265, "total_steps": 181800, "loss": 0.0055, "lr": 1.1272704441752551e-05, "epoch": 14.33058305830583, "percentage": 71.65, "elapsed_time": "5:08:30", "remaining_time": "2:02:02", "throughput": 1485.18, "total_tokens": 27490880} {"current_steps": 130270, "total_steps": 181800, "loss": 0.0021, "lr": 1.1270698619538065e-05, "epoch": 14.331133113311331, "percentage": 71.66, "elapsed_time": "5:08:30", "remaining_time": "2:02:02", "throughput": 1485.18, "total_tokens": 27491968} {"current_steps": 130275, "total_steps": 181800, "loss": 0.0015, "lr": 1.1268692923859961e-05, "epoch": 14.331683168316832, "percentage": 71.66, "elapsed_time": "5:08:31", "remaining_time": "2:02:01", "throughput": 1485.19, "total_tokens": 27493056} {"current_steps": 130280, "total_steps": 181800, "loss": 0.0026, "lr": 1.1266687354736735e-05, "epoch": 14.332233223322332, "percentage": 71.66, "elapsed_time": "5:08:32", "remaining_time": "2:02:00", "throughput": 1485.19, "total_tokens": 27494144} {"current_steps": 130285, "total_steps": 181800, "loss": 0.0429, "lr": 1.1264681912186852e-05, "epoch": 14.332783278327833, "percentage": 71.66, "elapsed_time": "5:08:32", "remaining_time": "2:02:00", "throughput": 1485.19, "total_tokens": 27495232} {"current_steps": 130290, "total_steps": 181800, "loss": 0.089, "lr": 1.1262676596228813e-05, "epoch": 14.333333333333334, "percentage": 71.67, "elapsed_time": "5:08:33", "remaining_time": "2:01:59", "throughput": 1485.2, "total_tokens": 27496320} {"current_steps": 130295, "total_steps": 181800, "loss": 0.0073, "lr": 1.1260671406881093e-05, "epoch": 14.333883388338833, "percentage": 71.67, "elapsed_time": "5:08:34", "remaining_time": "2:01:58", "throughput": 1485.2, "total_tokens": 27497312} {"current_steps": 130300, "total_steps": 181800, "loss": 0.1227, "lr": 1.1258666344162163e-05, "epoch": 14.334433443344334, "percentage": 71.67, "elapsed_time": "5:08:34", "remaining_time": "2:01:57", "throughput": 1485.2, "total_tokens": 27498400} {"current_steps": 130305, "total_steps": 181800, "loss": 0.0564, "lr": 1.1256661408090513e-05, "epoch": 14.334983498349835, "percentage": 71.67, "elapsed_time": "5:08:35", "remaining_time": "2:01:57", "throughput": 1485.2, "total_tokens": 27499488} {"current_steps": 130310, "total_steps": 181800, "loss": 0.0143, "lr": 1.1254656598684626e-05, "epoch": 14.335533553355335, "percentage": 71.68, "elapsed_time": "5:08:36", "remaining_time": "2:01:56", "throughput": 1485.2, "total_tokens": 27500512} {"current_steps": 130315, "total_steps": 181800, "loss": 0.0046, "lr": 1.1252651915962966e-05, "epoch": 14.336083608360836, "percentage": 71.68, "elapsed_time": "5:08:37", "remaining_time": "2:01:55", "throughput": 1485.2, "total_tokens": 27501536} {"current_steps": 130320, "total_steps": 181800, "loss": 0.0053, "lr": 1.1250647359944027e-05, "epoch": 14.336633663366337, "percentage": 71.68, "elapsed_time": "5:08:37", "remaining_time": "2:01:55", "throughput": 1485.21, "total_tokens": 27502624} {"current_steps": 130325, "total_steps": 181800, "loss": 0.0038, "lr": 1.1248642930646264e-05, "epoch": 14.337183718371838, "percentage": 71.69, "elapsed_time": "5:08:38", "remaining_time": "2:01:54", "throughput": 1485.2, "total_tokens": 27503616} {"current_steps": 130330, "total_steps": 181800, "loss": 0.0029, "lr": 1.124663862808816e-05, "epoch": 14.337733773377337, "percentage": 71.69, "elapsed_time": "5:08:39", "remaining_time": "2:01:53", "throughput": 1485.2, "total_tokens": 27504608} {"current_steps": 130335, "total_steps": 181800, "loss": 0.0051, "lr": 1.1244634452288196e-05, "epoch": 14.338283828382838, "percentage": 71.69, "elapsed_time": "5:08:39", "remaining_time": "2:01:52", "throughput": 1485.2, "total_tokens": 27505664} {"current_steps": 130340, "total_steps": 181800, "loss": 0.1373, "lr": 1.1242630403264829e-05, "epoch": 14.33883388338834, "percentage": 71.69, "elapsed_time": "5:08:40", "remaining_time": "2:01:52", "throughput": 1485.21, "total_tokens": 27506752} {"current_steps": 130345, "total_steps": 181800, "loss": 0.0724, "lr": 1.1240626481036545e-05, "epoch": 14.339383938393839, "percentage": 71.7, "elapsed_time": "5:08:41", "remaining_time": "2:01:51", "throughput": 1485.21, "total_tokens": 27507840} {"current_steps": 130350, "total_steps": 181800, "loss": 0.0276, "lr": 1.1238622685621794e-05, "epoch": 14.33993399339934, "percentage": 71.7, "elapsed_time": "5:08:41", "remaining_time": "2:01:50", "throughput": 1485.21, "total_tokens": 27508864} {"current_steps": 130355, "total_steps": 181800, "loss": 0.0076, "lr": 1.1236619017039066e-05, "epoch": 14.340484048404841, "percentage": 71.7, "elapsed_time": "5:08:42", "remaining_time": "2:01:49", "throughput": 1485.21, "total_tokens": 27509952} {"current_steps": 130360, "total_steps": 181800, "loss": 0.0047, "lr": 1.1234615475306804e-05, "epoch": 14.34103410341034, "percentage": 71.71, "elapsed_time": "5:08:43", "remaining_time": "2:01:49", "throughput": 1485.22, "total_tokens": 27511040} {"current_steps": 130365, "total_steps": 181800, "loss": 0.0032, "lr": 1.1232612060443488e-05, "epoch": 14.341584158415841, "percentage": 71.71, "elapsed_time": "5:08:43", "remaining_time": "2:01:48", "throughput": 1485.22, "total_tokens": 27512128} {"current_steps": 130370, "total_steps": 181800, "loss": 0.127, "lr": 1.1230608772467587e-05, "epoch": 14.342134213421343, "percentage": 71.71, "elapsed_time": "5:08:44", "remaining_time": "2:01:47", "throughput": 1485.22, "total_tokens": 27513184} {"current_steps": 130375, "total_steps": 181800, "loss": 0.0173, "lr": 1.122860561139755e-05, "epoch": 14.342684268426842, "percentage": 71.71, "elapsed_time": "5:08:45", "remaining_time": "2:01:47", "throughput": 1485.22, "total_tokens": 27514208} {"current_steps": 130380, "total_steps": 181800, "loss": 0.0298, "lr": 1.1226602577251858e-05, "epoch": 14.343234323432343, "percentage": 71.72, "elapsed_time": "5:08:46", "remaining_time": "2:01:46", "throughput": 1485.22, "total_tokens": 27515296} {"current_steps": 130385, "total_steps": 181800, "loss": 0.0037, "lr": 1.122459967004895e-05, "epoch": 14.343784378437844, "percentage": 71.72, "elapsed_time": "5:08:46", "remaining_time": "2:01:45", "throughput": 1485.23, "total_tokens": 27516352} {"current_steps": 130390, "total_steps": 181800, "loss": 0.0489, "lr": 1.1222596889807297e-05, "epoch": 14.344334433443345, "percentage": 71.72, "elapsed_time": "5:08:47", "remaining_time": "2:01:44", "throughput": 1485.23, "total_tokens": 27517376} {"current_steps": 130395, "total_steps": 181800, "loss": 0.0395, "lr": 1.1220594236545364e-05, "epoch": 14.344884488448844, "percentage": 71.72, "elapsed_time": "5:08:48", "remaining_time": "2:01:44", "throughput": 1485.23, "total_tokens": 27518400} {"current_steps": 130400, "total_steps": 181800, "loss": 0.0027, "lr": 1.1218591710281596e-05, "epoch": 14.345434543454346, "percentage": 71.73, "elapsed_time": "5:08:48", "remaining_time": "2:01:43", "throughput": 1485.23, "total_tokens": 27519488} {"current_steps": 130405, "total_steps": 181800, "loss": 0.0412, "lr": 1.1216589311034464e-05, "epoch": 14.345984598459847, "percentage": 71.73, "elapsed_time": "5:08:49", "remaining_time": "2:01:42", "throughput": 1485.23, "total_tokens": 27520544} {"current_steps": 130410, "total_steps": 181800, "loss": 0.1144, "lr": 1.1214587038822414e-05, "epoch": 14.346534653465346, "percentage": 71.73, "elapsed_time": "5:08:50", "remaining_time": "2:01:42", "throughput": 1485.23, "total_tokens": 27521536} {"current_steps": 130415, "total_steps": 181800, "loss": 0.1667, "lr": 1.1212584893663891e-05, "epoch": 14.347084708470847, "percentage": 71.74, "elapsed_time": "5:08:50", "remaining_time": "2:01:41", "throughput": 1485.23, "total_tokens": 27522592} {"current_steps": 130420, "total_steps": 181800, "loss": 0.0014, "lr": 1.1210582875577358e-05, "epoch": 14.347634763476348, "percentage": 71.74, "elapsed_time": "5:08:51", "remaining_time": "2:01:40", "throughput": 1485.23, "total_tokens": 27523584} {"current_steps": 130425, "total_steps": 181800, "loss": 0.0042, "lr": 1.1208580984581262e-05, "epoch": 14.348184818481847, "percentage": 71.74, "elapsed_time": "5:08:52", "remaining_time": "2:01:39", "throughput": 1485.23, "total_tokens": 27524640} {"current_steps": 130430, "total_steps": 181800, "loss": 0.0263, "lr": 1.1206579220694071e-05, "epoch": 14.348734873487349, "percentage": 71.74, "elapsed_time": "5:08:52", "remaining_time": "2:01:39", "throughput": 1485.23, "total_tokens": 27525664} {"current_steps": 130435, "total_steps": 181800, "loss": 0.0417, "lr": 1.120457758393422e-05, "epoch": 14.34928492849285, "percentage": 71.75, "elapsed_time": "5:08:53", "remaining_time": "2:01:38", "throughput": 1485.23, "total_tokens": 27526720} {"current_steps": 130440, "total_steps": 181800, "loss": 0.0062, "lr": 1.1202576074320147e-05, "epoch": 14.34983498349835, "percentage": 71.75, "elapsed_time": "5:08:54", "remaining_time": "2:01:37", "throughput": 1485.23, "total_tokens": 27527776} {"current_steps": 130445, "total_steps": 181800, "loss": 0.0037, "lr": 1.120057469187031e-05, "epoch": 14.35038503850385, "percentage": 71.75, "elapsed_time": "5:08:54", "remaining_time": "2:01:37", "throughput": 1485.24, "total_tokens": 27528832} {"current_steps": 130450, "total_steps": 181800, "loss": 0.0013, "lr": 1.1198573436603154e-05, "epoch": 14.350935093509351, "percentage": 71.75, "elapsed_time": "5:08:55", "remaining_time": "2:01:36", "throughput": 1485.24, "total_tokens": 27529856} {"current_steps": 130455, "total_steps": 181800, "loss": 0.0137, "lr": 1.1196572308537137e-05, "epoch": 14.351485148514852, "percentage": 71.76, "elapsed_time": "5:08:56", "remaining_time": "2:01:35", "throughput": 1485.24, "total_tokens": 27530880} {"current_steps": 130460, "total_steps": 181800, "loss": 0.0199, "lr": 1.1194571307690685e-05, "epoch": 14.352035203520352, "percentage": 71.76, "elapsed_time": "5:08:57", "remaining_time": "2:01:34", "throughput": 1485.24, "total_tokens": 27531936} {"current_steps": 130465, "total_steps": 181800, "loss": 0.0033, "lr": 1.1192570434082239e-05, "epoch": 14.352585258525853, "percentage": 71.76, "elapsed_time": "5:08:57", "remaining_time": "2:01:34", "throughput": 1485.24, "total_tokens": 27533024} {"current_steps": 130470, "total_steps": 181800, "loss": 0.0188, "lr": 1.119056968773025e-05, "epoch": 14.353135313531354, "percentage": 71.77, "elapsed_time": "5:08:58", "remaining_time": "2:01:33", "throughput": 1485.24, "total_tokens": 27534016} {"current_steps": 130475, "total_steps": 181800, "loss": 0.0679, "lr": 1.1188569068653152e-05, "epoch": 14.353685368536853, "percentage": 71.77, "elapsed_time": "5:08:59", "remaining_time": "2:01:32", "throughput": 1485.24, "total_tokens": 27535104} {"current_steps": 130480, "total_steps": 181800, "loss": 0.0062, "lr": 1.118656857686938e-05, "epoch": 14.354235423542354, "percentage": 71.77, "elapsed_time": "5:08:59", "remaining_time": "2:01:32", "throughput": 1485.24, "total_tokens": 27536192} {"current_steps": 130485, "total_steps": 181800, "loss": 0.0447, "lr": 1.1184568212397386e-05, "epoch": 14.354785478547855, "percentage": 71.77, "elapsed_time": "5:09:00", "remaining_time": "2:01:31", "throughput": 1485.24, "total_tokens": 27537216} {"current_steps": 130490, "total_steps": 181800, "loss": 0.0045, "lr": 1.1182567975255592e-05, "epoch": 14.355335533553355, "percentage": 71.78, "elapsed_time": "5:09:01", "remaining_time": "2:01:30", "throughput": 1485.25, "total_tokens": 27538304} {"current_steps": 130495, "total_steps": 181800, "loss": 0.0194, "lr": 1.1180567865462447e-05, "epoch": 14.355885588558856, "percentage": 71.78, "elapsed_time": "5:09:01", "remaining_time": "2:01:29", "throughput": 1485.26, "total_tokens": 27539456} {"current_steps": 130500, "total_steps": 181800, "loss": 0.0096, "lr": 1.1178567883036364e-05, "epoch": 14.356435643564357, "percentage": 71.78, "elapsed_time": "5:09:02", "remaining_time": "2:01:29", "throughput": 1485.26, "total_tokens": 27540544} {"current_steps": 130505, "total_steps": 181800, "loss": 0.0047, "lr": 1.117656802799579e-05, "epoch": 14.356985698569858, "percentage": 71.78, "elapsed_time": "5:09:03", "remaining_time": "2:01:28", "throughput": 1485.26, "total_tokens": 27541600} {"current_steps": 130510, "total_steps": 181800, "loss": 0.0028, "lr": 1.1174568300359168e-05, "epoch": 14.357535753575357, "percentage": 71.79, "elapsed_time": "5:09:03", "remaining_time": "2:01:27", "throughput": 1485.27, "total_tokens": 27542720} {"current_steps": 130515, "total_steps": 181800, "loss": 0.0043, "lr": 1.1172568700144903e-05, "epoch": 14.358085808580858, "percentage": 71.79, "elapsed_time": "5:09:04", "remaining_time": "2:01:27", "throughput": 1485.27, "total_tokens": 27543840} {"current_steps": 130520, "total_steps": 181800, "loss": 0.0025, "lr": 1.1170569227371449e-05, "epoch": 14.35863586358636, "percentage": 71.79, "elapsed_time": "5:09:05", "remaining_time": "2:01:26", "throughput": 1485.27, "total_tokens": 27544928} {"current_steps": 130525, "total_steps": 181800, "loss": 0.0167, "lr": 1.116856988205722e-05, "epoch": 14.359185918591859, "percentage": 71.8, "elapsed_time": "5:09:06", "remaining_time": "2:01:25", "throughput": 1485.28, "total_tokens": 27546048} {"current_steps": 130530, "total_steps": 181800, "loss": 0.0012, "lr": 1.1166570664220639e-05, "epoch": 14.35973597359736, "percentage": 71.8, "elapsed_time": "5:09:06", "remaining_time": "2:01:24", "throughput": 1485.28, "total_tokens": 27547072} {"current_steps": 130535, "total_steps": 181800, "loss": 0.0008, "lr": 1.1164571573880137e-05, "epoch": 14.36028602860286, "percentage": 71.8, "elapsed_time": "5:09:07", "remaining_time": "2:01:24", "throughput": 1485.28, "total_tokens": 27548192} {"current_steps": 130540, "total_steps": 181800, "loss": 0.003, "lr": 1.116257261105414e-05, "epoch": 14.36083608360836, "percentage": 71.8, "elapsed_time": "5:09:08", "remaining_time": "2:01:23", "throughput": 1485.28, "total_tokens": 27549184} {"current_steps": 130545, "total_steps": 181800, "loss": 0.0557, "lr": 1.116057377576108e-05, "epoch": 14.361386138613861, "percentage": 71.81, "elapsed_time": "5:09:08", "remaining_time": "2:01:22", "throughput": 1485.28, "total_tokens": 27550240} {"current_steps": 130550, "total_steps": 181800, "loss": 0.052, "lr": 1.115857506801937e-05, "epoch": 14.361936193619362, "percentage": 71.81, "elapsed_time": "5:09:09", "remaining_time": "2:01:21", "throughput": 1485.28, "total_tokens": 27551296} {"current_steps": 130555, "total_steps": 181800, "loss": 0.1638, "lr": 1.1156576487847423e-05, "epoch": 14.362486248624862, "percentage": 71.81, "elapsed_time": "5:09:10", "remaining_time": "2:01:21", "throughput": 1485.28, "total_tokens": 27552320} {"current_steps": 130560, "total_steps": 181800, "loss": 0.0032, "lr": 1.1154578035263669e-05, "epoch": 14.363036303630363, "percentage": 71.82, "elapsed_time": "5:09:10", "remaining_time": "2:01:20", "throughput": 1485.29, "total_tokens": 27553408} {"current_steps": 130565, "total_steps": 181800, "loss": 0.0015, "lr": 1.1152579710286527e-05, "epoch": 14.363586358635864, "percentage": 71.82, "elapsed_time": "5:09:11", "remaining_time": "2:01:19", "throughput": 1485.29, "total_tokens": 27554432} {"current_steps": 130570, "total_steps": 181800, "loss": 0.0269, "lr": 1.1150581512934419e-05, "epoch": 14.364136413641365, "percentage": 71.82, "elapsed_time": "5:09:12", "remaining_time": "2:01:19", "throughput": 1485.29, "total_tokens": 27555520} {"current_steps": 130575, "total_steps": 181800, "loss": 0.0393, "lr": 1.1148583443225755e-05, "epoch": 14.364686468646864, "percentage": 71.82, "elapsed_time": "5:09:12", "remaining_time": "2:01:18", "throughput": 1485.29, "total_tokens": 27556576} {"current_steps": 130580, "total_steps": 181800, "loss": 0.004, "lr": 1.1146585501178944e-05, "epoch": 14.365236523652365, "percentage": 71.83, "elapsed_time": "5:09:13", "remaining_time": "2:01:17", "throughput": 1485.29, "total_tokens": 27557600} {"current_steps": 130585, "total_steps": 181800, "loss": 0.0891, "lr": 1.1144587686812416e-05, "epoch": 14.365786578657866, "percentage": 71.83, "elapsed_time": "5:09:14", "remaining_time": "2:01:16", "throughput": 1485.29, "total_tokens": 27558656} {"current_steps": 130590, "total_steps": 181800, "loss": 0.1734, "lr": 1.1142590000144565e-05, "epoch": 14.366336633663366, "percentage": 71.83, "elapsed_time": "5:09:15", "remaining_time": "2:01:16", "throughput": 1485.3, "total_tokens": 27559712} {"current_steps": 130595, "total_steps": 181800, "loss": 0.0056, "lr": 1.1140592441193815e-05, "epoch": 14.366886688668867, "percentage": 71.83, "elapsed_time": "5:09:15", "remaining_time": "2:01:15", "throughput": 1485.3, "total_tokens": 27560800} {"current_steps": 130600, "total_steps": 181800, "loss": 0.0019, "lr": 1.113859500997858e-05, "epoch": 14.367436743674368, "percentage": 71.84, "elapsed_time": "5:09:16", "remaining_time": "2:01:14", "throughput": 1485.3, "total_tokens": 27561792} {"current_steps": 130605, "total_steps": 181800, "loss": 0.0085, "lr": 1.1136597706517255e-05, "epoch": 14.367986798679867, "percentage": 71.84, "elapsed_time": "5:09:17", "remaining_time": "2:01:14", "throughput": 1485.3, "total_tokens": 27562816} {"current_steps": 130610, "total_steps": 181800, "loss": 0.0381, "lr": 1.1134600530828265e-05, "epoch": 14.368536853685368, "percentage": 71.84, "elapsed_time": "5:09:17", "remaining_time": "2:01:13", "throughput": 1485.3, "total_tokens": 27563872} {"current_steps": 130615, "total_steps": 181800, "loss": 0.0944, "lr": 1.1132603482930001e-05, "epoch": 14.36908690869087, "percentage": 71.85, "elapsed_time": "5:09:18", "remaining_time": "2:01:12", "throughput": 1485.3, "total_tokens": 27564992} {"current_steps": 130620, "total_steps": 181800, "loss": 0.1012, "lr": 1.1130606562840876e-05, "epoch": 14.369636963696369, "percentage": 71.85, "elapsed_time": "5:09:19", "remaining_time": "2:01:11", "throughput": 1485.31, "total_tokens": 27566048} {"current_steps": 130625, "total_steps": 181800, "loss": 0.0074, "lr": 1.1128609770579305e-05, "epoch": 14.37018701870187, "percentage": 71.85, "elapsed_time": "5:09:19", "remaining_time": "2:01:11", "throughput": 1485.31, "total_tokens": 27567104} {"current_steps": 130630, "total_steps": 181800, "loss": 0.0328, "lr": 1.1126613106163672e-05, "epoch": 14.370737073707371, "percentage": 71.85, "elapsed_time": "5:09:20", "remaining_time": "2:01:10", "throughput": 1485.31, "total_tokens": 27568128} {"current_steps": 130635, "total_steps": 181800, "loss": 0.0009, "lr": 1.1124616569612399e-05, "epoch": 14.371287128712872, "percentage": 71.86, "elapsed_time": "5:09:21", "remaining_time": "2:01:09", "throughput": 1485.31, "total_tokens": 27569152} {"current_steps": 130640, "total_steps": 181800, "loss": 0.0178, "lr": 1.1122620160943867e-05, "epoch": 14.371837183718371, "percentage": 71.86, "elapsed_time": "5:09:21", "remaining_time": "2:01:09", "throughput": 1485.31, "total_tokens": 27570208} {"current_steps": 130645, "total_steps": 181800, "loss": 0.0183, "lr": 1.1120623880176496e-05, "epoch": 14.372387238723872, "percentage": 71.86, "elapsed_time": "5:09:22", "remaining_time": "2:01:08", "throughput": 1485.31, "total_tokens": 27571264} {"current_steps": 130650, "total_steps": 181800, "loss": 0.003, "lr": 1.1118627727328662e-05, "epoch": 14.372937293729374, "percentage": 71.86, "elapsed_time": "5:09:23", "remaining_time": "2:01:07", "throughput": 1485.31, "total_tokens": 27572288} {"current_steps": 130655, "total_steps": 181800, "loss": 0.0051, "lr": 1.1116631702418778e-05, "epoch": 14.373487348734873, "percentage": 71.87, "elapsed_time": "5:09:23", "remaining_time": "2:01:06", "throughput": 1485.32, "total_tokens": 27573376} {"current_steps": 130660, "total_steps": 181800, "loss": 0.1328, "lr": 1.1114635805465245e-05, "epoch": 14.374037403740374, "percentage": 71.87, "elapsed_time": "5:09:24", "remaining_time": "2:01:06", "throughput": 1485.32, "total_tokens": 27574464} {"current_steps": 130665, "total_steps": 181800, "loss": 0.0067, "lr": 1.1112640036486446e-05, "epoch": 14.374587458745875, "percentage": 71.87, "elapsed_time": "5:09:25", "remaining_time": "2:01:05", "throughput": 1485.32, "total_tokens": 27575520} {"current_steps": 130670, "total_steps": 181800, "loss": 0.0023, "lr": 1.1110644395500785e-05, "epoch": 14.375137513751374, "percentage": 71.88, "elapsed_time": "5:09:26", "remaining_time": "2:01:04", "throughput": 1485.32, "total_tokens": 27576576} {"current_steps": 130675, "total_steps": 181800, "loss": 0.0359, "lr": 1.110864888252665e-05, "epoch": 14.375687568756875, "percentage": 71.88, "elapsed_time": "5:09:26", "remaining_time": "2:01:04", "throughput": 1485.32, "total_tokens": 27577600} {"current_steps": 130680, "total_steps": 181800, "loss": 0.0364, "lr": 1.1106653497582417e-05, "epoch": 14.376237623762377, "percentage": 71.88, "elapsed_time": "5:09:27", "remaining_time": "2:01:03", "throughput": 1485.32, "total_tokens": 27578688} {"current_steps": 130685, "total_steps": 181800, "loss": 0.0373, "lr": 1.110465824068651e-05, "epoch": 14.376787678767876, "percentage": 71.88, "elapsed_time": "5:09:28", "remaining_time": "2:01:02", "throughput": 1485.33, "total_tokens": 27579776} {"current_steps": 130690, "total_steps": 181800, "loss": 0.0108, "lr": 1.11026631118573e-05, "epoch": 14.377337733773377, "percentage": 71.89, "elapsed_time": "5:09:28", "remaining_time": "2:01:01", "throughput": 1485.33, "total_tokens": 27580768} {"current_steps": 130695, "total_steps": 181800, "loss": 0.0781, "lr": 1.1100668111113166e-05, "epoch": 14.377887788778878, "percentage": 71.89, "elapsed_time": "5:09:29", "remaining_time": "2:01:01", "throughput": 1485.33, "total_tokens": 27581824} {"current_steps": 130700, "total_steps": 181800, "loss": 0.0035, "lr": 1.1098673238472513e-05, "epoch": 14.37843784378438, "percentage": 71.89, "elapsed_time": "5:09:30", "remaining_time": "2:01:00", "throughput": 1485.33, "total_tokens": 27582848} {"current_steps": 130705, "total_steps": 181800, "loss": 0.0019, "lr": 1.1096678493953707e-05, "epoch": 14.378987898789878, "percentage": 71.89, "elapsed_time": "5:09:30", "remaining_time": "2:00:59", "throughput": 1485.33, "total_tokens": 27583840} {"current_steps": 130710, "total_steps": 181800, "loss": 0.0782, "lr": 1.1094683877575149e-05, "epoch": 14.37953795379538, "percentage": 71.9, "elapsed_time": "5:09:31", "remaining_time": "2:00:58", "throughput": 1485.33, "total_tokens": 27584864} {"current_steps": 130715, "total_steps": 181800, "loss": 0.0189, "lr": 1.1092689389355223e-05, "epoch": 14.38008800880088, "percentage": 71.9, "elapsed_time": "5:09:32", "remaining_time": "2:00:58", "throughput": 1485.33, "total_tokens": 27585920} {"current_steps": 130720, "total_steps": 181800, "loss": 0.0327, "lr": 1.1090695029312299e-05, "epoch": 14.38063806380638, "percentage": 71.9, "elapsed_time": "5:09:32", "remaining_time": "2:00:57", "throughput": 1485.33, "total_tokens": 27586976} {"current_steps": 130725, "total_steps": 181800, "loss": 0.0904, "lr": 1.1088700797464772e-05, "epoch": 14.381188118811881, "percentage": 71.91, "elapsed_time": "5:09:33", "remaining_time": "2:00:56", "throughput": 1485.33, "total_tokens": 27588032} {"current_steps": 130730, "total_steps": 181800, "loss": 0.02, "lr": 1.1086706693831003e-05, "epoch": 14.381738173817382, "percentage": 71.91, "elapsed_time": "5:09:34", "remaining_time": "2:00:56", "throughput": 1485.33, "total_tokens": 27589056} {"current_steps": 130735, "total_steps": 181800, "loss": 0.01, "lr": 1.1084712718429385e-05, "epoch": 14.382288228822881, "percentage": 71.91, "elapsed_time": "5:09:35", "remaining_time": "2:00:55", "throughput": 1485.33, "total_tokens": 27590048} {"current_steps": 130740, "total_steps": 181800, "loss": 0.0193, "lr": 1.10827188712783e-05, "epoch": 14.382838283828383, "percentage": 71.91, "elapsed_time": "5:09:35", "remaining_time": "2:00:54", "throughput": 1485.33, "total_tokens": 27591136} {"current_steps": 130745, "total_steps": 181800, "loss": 0.006, "lr": 1.108072515239611e-05, "epoch": 14.383388338833884, "percentage": 71.92, "elapsed_time": "5:09:36", "remaining_time": "2:00:53", "throughput": 1485.33, "total_tokens": 27592128} {"current_steps": 130750, "total_steps": 181800, "loss": 0.0064, "lr": 1.1078731561801203e-05, "epoch": 14.383938393839385, "percentage": 71.92, "elapsed_time": "5:09:37", "remaining_time": "2:00:53", "throughput": 1485.33, "total_tokens": 27593152} {"current_steps": 130755, "total_steps": 181800, "loss": 0.0153, "lr": 1.107673809951194e-05, "epoch": 14.384488448844884, "percentage": 71.92, "elapsed_time": "5:09:37", "remaining_time": "2:00:52", "throughput": 1485.33, "total_tokens": 27594176} {"current_steps": 130760, "total_steps": 181800, "loss": 0.0015, "lr": 1.1074744765546714e-05, "epoch": 14.385038503850385, "percentage": 71.93, "elapsed_time": "5:09:38", "remaining_time": "2:00:51", "throughput": 1485.33, "total_tokens": 27595200} {"current_steps": 130765, "total_steps": 181800, "loss": 0.0009, "lr": 1.1072751559923868e-05, "epoch": 14.385588558855886, "percentage": 71.93, "elapsed_time": "5:09:39", "remaining_time": "2:00:51", "throughput": 1485.33, "total_tokens": 27596256} {"current_steps": 130770, "total_steps": 181800, "loss": 0.0102, "lr": 1.1070758482661792e-05, "epoch": 14.386138613861386, "percentage": 71.93, "elapsed_time": "5:09:39", "remaining_time": "2:00:50", "throughput": 1485.34, "total_tokens": 27597344} {"current_steps": 130775, "total_steps": 181800, "loss": 0.072, "lr": 1.1068765533778858e-05, "epoch": 14.386688668866887, "percentage": 71.93, "elapsed_time": "5:09:40", "remaining_time": "2:00:49", "throughput": 1485.34, "total_tokens": 27598432} {"current_steps": 130780, "total_steps": 181800, "loss": 0.0279, "lr": 1.1066772713293418e-05, "epoch": 14.387238723872388, "percentage": 71.94, "elapsed_time": "5:09:41", "remaining_time": "2:00:48", "throughput": 1485.34, "total_tokens": 27599424} {"current_steps": 130785, "total_steps": 181800, "loss": 0.0076, "lr": 1.1064780021223859e-05, "epoch": 14.387788778877887, "percentage": 71.94, "elapsed_time": "5:09:41", "remaining_time": "2:00:48", "throughput": 1485.34, "total_tokens": 27600480} {"current_steps": 130790, "total_steps": 181800, "loss": 0.0033, "lr": 1.1062787457588536e-05, "epoch": 14.388338833883388, "percentage": 71.94, "elapsed_time": "5:09:42", "remaining_time": "2:00:47", "throughput": 1485.34, "total_tokens": 27601504} {"current_steps": 130795, "total_steps": 181800, "loss": 0.0502, "lr": 1.1060795022405792e-05, "epoch": 14.38888888888889, "percentage": 71.94, "elapsed_time": "5:09:43", "remaining_time": "2:00:46", "throughput": 1485.34, "total_tokens": 27602496} {"current_steps": 130800, "total_steps": 181800, "loss": 0.0027, "lr": 1.1058802715694033e-05, "epoch": 14.389438943894389, "percentage": 71.95, "elapsed_time": "5:09:43", "remaining_time": "2:00:46", "throughput": 1485.34, "total_tokens": 27603616} {"current_steps": 130805, "total_steps": 181800, "loss": 0.0028, "lr": 1.105681053747159e-05, "epoch": 14.38998899889989, "percentage": 71.95, "elapsed_time": "5:09:44", "remaining_time": "2:00:45", "throughput": 1485.35, "total_tokens": 27604672} {"current_steps": 130810, "total_steps": 181800, "loss": 0.0276, "lr": 1.105481848775684e-05, "epoch": 14.39053905390539, "percentage": 71.95, "elapsed_time": "5:09:45", "remaining_time": "2:00:44", "throughput": 1485.35, "total_tokens": 27605728} {"current_steps": 130815, "total_steps": 181800, "loss": 0.0103, "lr": 1.1052826566568143e-05, "epoch": 14.391089108910892, "percentage": 71.96, "elapsed_time": "5:09:46", "remaining_time": "2:00:43", "throughput": 1485.35, "total_tokens": 27606816} {"current_steps": 130820, "total_steps": 181800, "loss": 0.003, "lr": 1.1050834773923835e-05, "epoch": 14.391639163916391, "percentage": 71.96, "elapsed_time": "5:09:46", "remaining_time": "2:00:43", "throughput": 1485.35, "total_tokens": 27607904} {"current_steps": 130825, "total_steps": 181800, "loss": 0.0262, "lr": 1.1048843109842292e-05, "epoch": 14.392189218921892, "percentage": 71.96, "elapsed_time": "5:09:47", "remaining_time": "2:00:42", "throughput": 1485.35, "total_tokens": 27608928} {"current_steps": 130830, "total_steps": 181800, "loss": 0.1049, "lr": 1.1046851574341868e-05, "epoch": 14.392739273927393, "percentage": 71.96, "elapsed_time": "5:09:48", "remaining_time": "2:00:41", "throughput": 1485.35, "total_tokens": 27609952} {"current_steps": 130835, "total_steps": 181800, "loss": 0.0049, "lr": 1.1044860167440926e-05, "epoch": 14.393289328932893, "percentage": 71.97, "elapsed_time": "5:09:48", "remaining_time": "2:00:41", "throughput": 1485.35, "total_tokens": 27610944} {"current_steps": 130840, "total_steps": 181800, "loss": 0.0315, "lr": 1.1042868889157811e-05, "epoch": 14.393839383938394, "percentage": 71.97, "elapsed_time": "5:09:49", "remaining_time": "2:00:40", "throughput": 1485.35, "total_tokens": 27611968} {"current_steps": 130845, "total_steps": 181800, "loss": 0.0178, "lr": 1.1040877739510868e-05, "epoch": 14.394389438943895, "percentage": 71.97, "elapsed_time": "5:09:50", "remaining_time": "2:00:39", "throughput": 1485.35, "total_tokens": 27613024} {"current_steps": 130850, "total_steps": 181800, "loss": 0.0148, "lr": 1.1038886718518468e-05, "epoch": 14.394939493949394, "percentage": 71.97, "elapsed_time": "5:09:50", "remaining_time": "2:00:38", "throughput": 1485.36, "total_tokens": 27614112} {"current_steps": 130855, "total_steps": 181800, "loss": 0.0115, "lr": 1.1036895826198929e-05, "epoch": 14.395489548954895, "percentage": 71.98, "elapsed_time": "5:09:51", "remaining_time": "2:00:38", "throughput": 1485.36, "total_tokens": 27615168} {"current_steps": 130860, "total_steps": 181800, "loss": 0.0075, "lr": 1.103490506257064e-05, "epoch": 14.396039603960396, "percentage": 71.98, "elapsed_time": "5:09:52", "remaining_time": "2:00:37", "throughput": 1485.36, "total_tokens": 27616224} {"current_steps": 130865, "total_steps": 181800, "loss": 0.0215, "lr": 1.103291442765193e-05, "epoch": 14.396589658965897, "percentage": 71.98, "elapsed_time": "5:09:52", "remaining_time": "2:00:36", "throughput": 1485.36, "total_tokens": 27617312} {"current_steps": 130870, "total_steps": 181800, "loss": 0.0046, "lr": 1.1030923921461137e-05, "epoch": 14.397139713971397, "percentage": 71.99, "elapsed_time": "5:09:53", "remaining_time": "2:00:35", "throughput": 1485.36, "total_tokens": 27618336} {"current_steps": 130875, "total_steps": 181800, "loss": 0.1055, "lr": 1.1028933544016623e-05, "epoch": 14.397689768976898, "percentage": 71.99, "elapsed_time": "5:09:54", "remaining_time": "2:00:35", "throughput": 1485.36, "total_tokens": 27619360} {"current_steps": 130880, "total_steps": 181800, "loss": 0.0442, "lr": 1.1026943295336715e-05, "epoch": 14.398239823982399, "percentage": 71.99, "elapsed_time": "5:09:55", "remaining_time": "2:00:34", "throughput": 1485.37, "total_tokens": 27620448} {"current_steps": 130885, "total_steps": 181800, "loss": 0.0423, "lr": 1.1024953175439768e-05, "epoch": 14.398789878987898, "percentage": 71.99, "elapsed_time": "5:09:55", "remaining_time": "2:00:33", "throughput": 1485.37, "total_tokens": 27621440} {"current_steps": 130890, "total_steps": 181800, "loss": 0.009, "lr": 1.1022963184344129e-05, "epoch": 14.3993399339934, "percentage": 72.0, "elapsed_time": "5:09:56", "remaining_time": "2:00:33", "throughput": 1485.37, "total_tokens": 27622528} {"current_steps": 130895, "total_steps": 181800, "loss": 0.0662, "lr": 1.102097332206812e-05, "epoch": 14.3998899889989, "percentage": 72.0, "elapsed_time": "5:09:57", "remaining_time": "2:00:32", "throughput": 1485.37, "total_tokens": 27623552} {"current_steps": 130900, "total_steps": 181800, "loss": 0.148, "lr": 1.1018983588630104e-05, "epoch": 14.4004400440044, "percentage": 72.0, "elapsed_time": "5:09:57", "remaining_time": "2:00:31", "throughput": 1485.37, "total_tokens": 27624640} {"current_steps": 130905, "total_steps": 181800, "loss": 0.0027, "lr": 1.101699398404841e-05, "epoch": 14.400990099009901, "percentage": 72.0, "elapsed_time": "5:09:58", "remaining_time": "2:00:30", "throughput": 1485.37, "total_tokens": 27625664} {"current_steps": 130910, "total_steps": 181800, "loss": 0.1002, "lr": 1.1015004508341361e-05, "epoch": 14.401540154015402, "percentage": 72.01, "elapsed_time": "5:09:59", "remaining_time": "2:00:30", "throughput": 1485.37, "total_tokens": 27626688} {"current_steps": 130915, "total_steps": 181800, "loss": 0.1134, "lr": 1.1013015161527305e-05, "epoch": 14.402090209020901, "percentage": 72.01, "elapsed_time": "5:09:59", "remaining_time": "2:00:29", "throughput": 1485.37, "total_tokens": 27627712} {"current_steps": 130920, "total_steps": 181800, "loss": 0.0122, "lr": 1.1011025943624575e-05, "epoch": 14.402640264026402, "percentage": 72.01, "elapsed_time": "5:10:00", "remaining_time": "2:00:28", "throughput": 1485.37, "total_tokens": 27628768} {"current_steps": 130925, "total_steps": 181800, "loss": 0.0027, "lr": 1.100903685465152e-05, "epoch": 14.403190319031903, "percentage": 72.02, "elapsed_time": "5:10:01", "remaining_time": "2:00:28", "throughput": 1485.37, "total_tokens": 27629792} {"current_steps": 130930, "total_steps": 181800, "loss": 0.004, "lr": 1.1007047894626455e-05, "epoch": 14.403740374037405, "percentage": 72.02, "elapsed_time": "5:10:01", "remaining_time": "2:00:27", "throughput": 1485.37, "total_tokens": 27630848} {"current_steps": 130935, "total_steps": 181800, "loss": 0.0713, "lr": 1.1005059063567707e-05, "epoch": 14.404290429042904, "percentage": 72.02, "elapsed_time": "5:10:02", "remaining_time": "2:00:26", "throughput": 1485.37, "total_tokens": 27631872} {"current_steps": 130940, "total_steps": 181800, "loss": 0.1084, "lr": 1.1003070361493614e-05, "epoch": 14.404840484048405, "percentage": 72.02, "elapsed_time": "5:10:03", "remaining_time": "2:00:25", "throughput": 1485.38, "total_tokens": 27632928} {"current_steps": 130945, "total_steps": 181800, "loss": 0.0062, "lr": 1.1001081788422504e-05, "epoch": 14.405390539053906, "percentage": 72.03, "elapsed_time": "5:10:04", "remaining_time": "2:00:25", "throughput": 1485.37, "total_tokens": 27633888} {"current_steps": 130950, "total_steps": 181800, "loss": 0.0672, "lr": 1.0999093344372716e-05, "epoch": 14.405940594059405, "percentage": 72.03, "elapsed_time": "5:10:04", "remaining_time": "2:00:24", "throughput": 1485.37, "total_tokens": 27634912} {"current_steps": 130955, "total_steps": 181800, "loss": 0.0773, "lr": 1.0997105029362567e-05, "epoch": 14.406490649064907, "percentage": 72.03, "elapsed_time": "5:10:05", "remaining_time": "2:00:23", "throughput": 1485.37, "total_tokens": 27635968} {"current_steps": 130960, "total_steps": 181800, "loss": 0.0026, "lr": 1.0995116843410372e-05, "epoch": 14.407040704070408, "percentage": 72.04, "elapsed_time": "5:10:06", "remaining_time": "2:00:23", "throughput": 1485.37, "total_tokens": 27636992} {"current_steps": 130965, "total_steps": 181800, "loss": 0.008, "lr": 1.0993128786534474e-05, "epoch": 14.407590759075907, "percentage": 72.04, "elapsed_time": "5:10:06", "remaining_time": "2:00:22", "throughput": 1485.37, "total_tokens": 27637952} {"current_steps": 130970, "total_steps": 181800, "loss": 0.0819, "lr": 1.0991140858753176e-05, "epoch": 14.408140814081408, "percentage": 72.04, "elapsed_time": "5:10:07", "remaining_time": "2:00:21", "throughput": 1485.37, "total_tokens": 27639040} {"current_steps": 130975, "total_steps": 181800, "loss": 0.0131, "lr": 1.0989153060084814e-05, "epoch": 14.408690869086909, "percentage": 72.04, "elapsed_time": "5:10:08", "remaining_time": "2:00:20", "throughput": 1485.38, "total_tokens": 27640096} {"current_steps": 130980, "total_steps": 181800, "loss": 0.0248, "lr": 1.0987165390547713e-05, "epoch": 14.409240924092408, "percentage": 72.05, "elapsed_time": "5:10:08", "remaining_time": "2:00:20", "throughput": 1485.38, "total_tokens": 27641152} {"current_steps": 130985, "total_steps": 181800, "loss": 0.0024, "lr": 1.0985177850160174e-05, "epoch": 14.40979097909791, "percentage": 72.05, "elapsed_time": "5:10:09", "remaining_time": "2:00:19", "throughput": 1485.38, "total_tokens": 27642176} {"current_steps": 130990, "total_steps": 181800, "loss": 0.0073, "lr": 1.0983190438940538e-05, "epoch": 14.41034103410341, "percentage": 72.05, "elapsed_time": "5:10:10", "remaining_time": "2:00:18", "throughput": 1485.38, "total_tokens": 27643296} {"current_steps": 130995, "total_steps": 181800, "loss": 0.0202, "lr": 1.0981203156907096e-05, "epoch": 14.410891089108912, "percentage": 72.05, "elapsed_time": "5:10:10", "remaining_time": "2:00:18", "throughput": 1485.38, "total_tokens": 27644384} {"current_steps": 131000, "total_steps": 181800, "loss": 0.0262, "lr": 1.0979216004078183e-05, "epoch": 14.411441144114411, "percentage": 72.06, "elapsed_time": "5:10:11", "remaining_time": "2:00:17", "throughput": 1485.38, "total_tokens": 27645408} {"current_steps": 131005, "total_steps": 181800, "loss": 0.0026, "lr": 1.0977228980472114e-05, "epoch": 14.411991199119912, "percentage": 72.06, "elapsed_time": "5:10:12", "remaining_time": "2:00:16", "throughput": 1485.39, "total_tokens": 27646528} {"current_steps": 131010, "total_steps": 181800, "loss": 0.0623, "lr": 1.0975242086107187e-05, "epoch": 14.412541254125413, "percentage": 72.06, "elapsed_time": "5:10:13", "remaining_time": "2:00:15", "throughput": 1485.39, "total_tokens": 27647520} {"current_steps": 131015, "total_steps": 181800, "loss": 0.1223, "lr": 1.0973255321001735e-05, "epoch": 14.413091309130913, "percentage": 72.07, "elapsed_time": "5:10:13", "remaining_time": "2:00:15", "throughput": 1485.39, "total_tokens": 27648608} {"current_steps": 131020, "total_steps": 181800, "loss": 0.001, "lr": 1.0971268685174048e-05, "epoch": 14.413641364136414, "percentage": 72.07, "elapsed_time": "5:10:14", "remaining_time": "2:00:14", "throughput": 1485.39, "total_tokens": 27649600} {"current_steps": 131025, "total_steps": 181800, "loss": 0.0833, "lr": 1.0969282178642456e-05, "epoch": 14.414191419141915, "percentage": 72.07, "elapsed_time": "5:10:15", "remaining_time": "2:00:13", "throughput": 1485.39, "total_tokens": 27650656} {"current_steps": 131030, "total_steps": 181800, "loss": 0.037, "lr": 1.0967295801425248e-05, "epoch": 14.414741474147414, "percentage": 72.07, "elapsed_time": "5:10:15", "remaining_time": "2:00:13", "throughput": 1485.39, "total_tokens": 27651680} {"current_steps": 131035, "total_steps": 181800, "loss": 0.0206, "lr": 1.096530955354074e-05, "epoch": 14.415291529152915, "percentage": 72.08, "elapsed_time": "5:10:16", "remaining_time": "2:00:12", "throughput": 1485.39, "total_tokens": 27652736} {"current_steps": 131040, "total_steps": 181800, "loss": 0.078, "lr": 1.096332343500725e-05, "epoch": 14.415841584158416, "percentage": 72.08, "elapsed_time": "5:10:17", "remaining_time": "2:00:11", "throughput": 1485.39, "total_tokens": 27653792} {"current_steps": 131045, "total_steps": 181800, "loss": 0.0064, "lr": 1.0961337445843062e-05, "epoch": 14.416391639163916, "percentage": 72.08, "elapsed_time": "5:10:17", "remaining_time": "2:00:10", "throughput": 1485.39, "total_tokens": 27654816} {"current_steps": 131050, "total_steps": 181800, "loss": 0.0261, "lr": 1.0959351586066499e-05, "epoch": 14.416941694169417, "percentage": 72.08, "elapsed_time": "5:10:18", "remaining_time": "2:00:10", "throughput": 1485.4, "total_tokens": 27655872} {"current_steps": 131055, "total_steps": 181800, "loss": 0.0072, "lr": 1.0957365855695847e-05, "epoch": 14.417491749174918, "percentage": 72.09, "elapsed_time": "5:10:19", "remaining_time": "2:00:09", "throughput": 1485.4, "total_tokens": 27656928} {"current_steps": 131060, "total_steps": 181800, "loss": 0.028, "lr": 1.0955380254749417e-05, "epoch": 14.418041804180419, "percentage": 72.09, "elapsed_time": "5:10:19", "remaining_time": "2:00:08", "throughput": 1485.4, "total_tokens": 27657952} {"current_steps": 131065, "total_steps": 181800, "loss": 0.0023, "lr": 1.0953394783245516e-05, "epoch": 14.418591859185918, "percentage": 72.09, "elapsed_time": "5:10:20", "remaining_time": "2:00:07", "throughput": 1485.4, "total_tokens": 27659072} {"current_steps": 131070, "total_steps": 181800, "loss": 0.0103, "lr": 1.0951409441202426e-05, "epoch": 14.41914191419142, "percentage": 72.1, "elapsed_time": "5:10:21", "remaining_time": "2:00:07", "throughput": 1485.41, "total_tokens": 27660160} {"current_steps": 131075, "total_steps": 181800, "loss": 0.0499, "lr": 1.0949424228638461e-05, "epoch": 14.41969196919692, "percentage": 72.1, "elapsed_time": "5:10:21", "remaining_time": "2:00:06", "throughput": 1485.41, "total_tokens": 27661216} {"current_steps": 131080, "total_steps": 181800, "loss": 0.0127, "lr": 1.0947439145571914e-05, "epoch": 14.42024202420242, "percentage": 72.1, "elapsed_time": "5:10:22", "remaining_time": "2:00:05", "throughput": 1485.41, "total_tokens": 27662176} {"current_steps": 131085, "total_steps": 181800, "loss": 0.0657, "lr": 1.0945454192021064e-05, "epoch": 14.42079207920792, "percentage": 72.1, "elapsed_time": "5:10:23", "remaining_time": "2:00:05", "throughput": 1485.41, "total_tokens": 27663232} {"current_steps": 131090, "total_steps": 181800, "loss": 0.001, "lr": 1.0943469368004223e-05, "epoch": 14.421342134213422, "percentage": 72.11, "elapsed_time": "5:10:24", "remaining_time": "2:00:04", "throughput": 1485.41, "total_tokens": 27664288} {"current_steps": 131095, "total_steps": 181800, "loss": 0.0123, "lr": 1.0941484673539686e-05, "epoch": 14.421892189218921, "percentage": 72.11, "elapsed_time": "5:10:24", "remaining_time": "2:00:03", "throughput": 1485.41, "total_tokens": 27665408} {"current_steps": 131100, "total_steps": 181800, "loss": 0.0198, "lr": 1.0939500108645734e-05, "epoch": 14.422442244224422, "percentage": 72.11, "elapsed_time": "5:10:25", "remaining_time": "2:00:02", "throughput": 1485.42, "total_tokens": 27666496} {"current_steps": 131105, "total_steps": 181800, "loss": 0.0035, "lr": 1.0937515673340667e-05, "epoch": 14.422992299229923, "percentage": 72.11, "elapsed_time": "5:10:26", "remaining_time": "2:00:02", "throughput": 1485.42, "total_tokens": 27667584} {"current_steps": 131110, "total_steps": 181800, "loss": 0.0114, "lr": 1.0935531367642762e-05, "epoch": 14.423542354235423, "percentage": 72.12, "elapsed_time": "5:10:26", "remaining_time": "2:00:01", "throughput": 1485.42, "total_tokens": 27668640} {"current_steps": 131115, "total_steps": 181800, "loss": 0.0061, "lr": 1.0933547191570318e-05, "epoch": 14.424092409240924, "percentage": 72.12, "elapsed_time": "5:10:27", "remaining_time": "2:00:00", "throughput": 1485.43, "total_tokens": 27669760} {"current_steps": 131120, "total_steps": 181800, "loss": 0.0546, "lr": 1.0931563145141627e-05, "epoch": 14.424642464246425, "percentage": 72.12, "elapsed_time": "5:10:28", "remaining_time": "2:00:00", "throughput": 1485.43, "total_tokens": 27670752} {"current_steps": 131125, "total_steps": 181800, "loss": 0.0043, "lr": 1.0929579228374959e-05, "epoch": 14.425192519251926, "percentage": 72.13, "elapsed_time": "5:10:28", "remaining_time": "1:59:59", "throughput": 1485.43, "total_tokens": 27671840} {"current_steps": 131130, "total_steps": 181800, "loss": 0.1421, "lr": 1.0927595441288619e-05, "epoch": 14.425742574257425, "percentage": 72.13, "elapsed_time": "5:10:29", "remaining_time": "1:59:58", "throughput": 1485.43, "total_tokens": 27672928} {"current_steps": 131135, "total_steps": 181800, "loss": 0.0288, "lr": 1.0925611783900865e-05, "epoch": 14.426292629262926, "percentage": 72.13, "elapsed_time": "5:10:30", "remaining_time": "1:59:57", "throughput": 1485.43, "total_tokens": 27674016} {"current_steps": 131140, "total_steps": 181800, "loss": 0.018, "lr": 1.0923628256230006e-05, "epoch": 14.426842684268427, "percentage": 72.13, "elapsed_time": "5:10:30", "remaining_time": "1:59:57", "throughput": 1485.44, "total_tokens": 27675072} {"current_steps": 131145, "total_steps": 181800, "loss": 0.0472, "lr": 1.0921644858294302e-05, "epoch": 14.427392739273927, "percentage": 72.14, "elapsed_time": "5:10:31", "remaining_time": "1:59:56", "throughput": 1485.44, "total_tokens": 27676096} {"current_steps": 131150, "total_steps": 181800, "loss": 0.0013, "lr": 1.091966159011204e-05, "epoch": 14.427942794279428, "percentage": 72.14, "elapsed_time": "5:10:32", "remaining_time": "1:59:55", "throughput": 1485.44, "total_tokens": 27677152} {"current_steps": 131155, "total_steps": 181800, "loss": 0.0041, "lr": 1.0917678451701512e-05, "epoch": 14.428492849284929, "percentage": 72.14, "elapsed_time": "5:10:33", "remaining_time": "1:59:55", "throughput": 1485.44, "total_tokens": 27678272} {"current_steps": 131160, "total_steps": 181800, "loss": 0.1396, "lr": 1.0915695443080976e-05, "epoch": 14.429042904290428, "percentage": 72.15, "elapsed_time": "5:10:33", "remaining_time": "1:59:54", "throughput": 1485.44, "total_tokens": 27679328} {"current_steps": 131165, "total_steps": 181800, "loss": 0.1842, "lr": 1.0913712564268724e-05, "epoch": 14.42959295929593, "percentage": 72.15, "elapsed_time": "5:10:34", "remaining_time": "1:59:53", "throughput": 1485.45, "total_tokens": 27680384} {"current_steps": 131170, "total_steps": 181800, "loss": 0.0422, "lr": 1.0911729815283015e-05, "epoch": 14.43014301430143, "percentage": 72.15, "elapsed_time": "5:10:35", "remaining_time": "1:59:52", "throughput": 1485.45, "total_tokens": 27681440} {"current_steps": 131175, "total_steps": 181800, "loss": 0.0073, "lr": 1.0909747196142131e-05, "epoch": 14.430693069306932, "percentage": 72.15, "elapsed_time": "5:10:35", "remaining_time": "1:59:52", "throughput": 1485.45, "total_tokens": 27682528} {"current_steps": 131180, "total_steps": 181800, "loss": 0.0481, "lr": 1.0907764706864357e-05, "epoch": 14.43124312431243, "percentage": 72.16, "elapsed_time": "5:10:36", "remaining_time": "1:59:51", "throughput": 1485.45, "total_tokens": 27683584} {"current_steps": 131185, "total_steps": 181800, "loss": 0.0417, "lr": 1.0905782347467944e-05, "epoch": 14.431793179317932, "percentage": 72.16, "elapsed_time": "5:10:37", "remaining_time": "1:59:50", "throughput": 1485.45, "total_tokens": 27684608} {"current_steps": 131190, "total_steps": 181800, "loss": 0.1444, "lr": 1.090380011797118e-05, "epoch": 14.432343234323433, "percentage": 72.16, "elapsed_time": "5:10:37", "remaining_time": "1:59:50", "throughput": 1485.46, "total_tokens": 27685696} {"current_steps": 131195, "total_steps": 181800, "loss": 0.0073, "lr": 1.090181801839233e-05, "epoch": 14.432893289328932, "percentage": 72.16, "elapsed_time": "5:10:38", "remaining_time": "1:59:49", "throughput": 1485.45, "total_tokens": 27686688} {"current_steps": 131200, "total_steps": 181800, "loss": 0.0017, "lr": 1.0899836048749645e-05, "epoch": 14.433443344334433, "percentage": 72.17, "elapsed_time": "5:10:39", "remaining_time": "1:59:48", "throughput": 1485.46, "total_tokens": 27687776} {"current_steps": 131205, "total_steps": 181800, "loss": 0.0033, "lr": 1.0897854209061406e-05, "epoch": 14.433993399339935, "percentage": 72.17, "elapsed_time": "5:10:39", "remaining_time": "1:59:47", "throughput": 1485.46, "total_tokens": 27688832} {"current_steps": 131210, "total_steps": 181800, "loss": 0.0209, "lr": 1.089587249934588e-05, "epoch": 14.434543454345434, "percentage": 72.17, "elapsed_time": "5:10:40", "remaining_time": "1:59:47", "throughput": 1485.46, "total_tokens": 27689920} {"current_steps": 131215, "total_steps": 181800, "loss": 0.0054, "lr": 1.0893890919621335e-05, "epoch": 14.435093509350935, "percentage": 72.18, "elapsed_time": "5:10:41", "remaining_time": "1:59:46", "throughput": 1485.46, "total_tokens": 27690976} {"current_steps": 131220, "total_steps": 181800, "loss": 0.0538, "lr": 1.0891909469906032e-05, "epoch": 14.435643564356436, "percentage": 72.18, "elapsed_time": "5:10:41", "remaining_time": "1:59:45", "throughput": 1485.46, "total_tokens": 27692000} {"current_steps": 131225, "total_steps": 181800, "loss": 0.0397, "lr": 1.088992815021822e-05, "epoch": 14.436193619361935, "percentage": 72.18, "elapsed_time": "5:10:42", "remaining_time": "1:59:45", "throughput": 1485.47, "total_tokens": 27693120} {"current_steps": 131230, "total_steps": 181800, "loss": 0.0056, "lr": 1.0887946960576168e-05, "epoch": 14.436743674367436, "percentage": 72.18, "elapsed_time": "5:10:43", "remaining_time": "1:59:44", "throughput": 1485.47, "total_tokens": 27694176} {"current_steps": 131235, "total_steps": 181800, "loss": 0.0022, "lr": 1.0885965900998138e-05, "epoch": 14.437293729372938, "percentage": 72.19, "elapsed_time": "5:10:44", "remaining_time": "1:59:43", "throughput": 1485.47, "total_tokens": 27695232} {"current_steps": 131240, "total_steps": 181800, "loss": 0.0091, "lr": 1.0883984971502398e-05, "epoch": 14.437843784378439, "percentage": 72.19, "elapsed_time": "5:10:44", "remaining_time": "1:59:42", "throughput": 1485.47, "total_tokens": 27696288} {"current_steps": 131245, "total_steps": 181800, "loss": 0.0755, "lr": 1.0882004172107194e-05, "epoch": 14.438393839383938, "percentage": 72.19, "elapsed_time": "5:10:45", "remaining_time": "1:59:42", "throughput": 1485.48, "total_tokens": 27697344} {"current_steps": 131250, "total_steps": 181800, "loss": 0.0497, "lr": 1.0880023502830772e-05, "epoch": 14.438943894389439, "percentage": 72.19, "elapsed_time": "5:10:46", "remaining_time": "1:59:41", "throughput": 1485.48, "total_tokens": 27698400} {"current_steps": 131255, "total_steps": 181800, "loss": 0.0117, "lr": 1.087804296369141e-05, "epoch": 14.43949394939494, "percentage": 72.2, "elapsed_time": "5:10:46", "remaining_time": "1:59:40", "throughput": 1485.48, "total_tokens": 27699456} {"current_steps": 131260, "total_steps": 181800, "loss": 0.0278, "lr": 1.0876062554707339e-05, "epoch": 14.44004400440044, "percentage": 72.2, "elapsed_time": "5:10:47", "remaining_time": "1:59:39", "throughput": 1485.48, "total_tokens": 27700576} {"current_steps": 131265, "total_steps": 181800, "loss": 0.0095, "lr": 1.087408227589682e-05, "epoch": 14.44059405940594, "percentage": 72.2, "elapsed_time": "5:10:48", "remaining_time": "1:59:39", "throughput": 1485.48, "total_tokens": 27701568} {"current_steps": 131270, "total_steps": 181800, "loss": 0.0053, "lr": 1.0872102127278123e-05, "epoch": 14.441144114411442, "percentage": 72.21, "elapsed_time": "5:10:48", "remaining_time": "1:59:38", "throughput": 1485.48, "total_tokens": 27702656} {"current_steps": 131275, "total_steps": 181800, "loss": 0.0125, "lr": 1.0870122108869466e-05, "epoch": 14.441694169416941, "percentage": 72.21, "elapsed_time": "5:10:49", "remaining_time": "1:59:37", "throughput": 1485.49, "total_tokens": 27703744} {"current_steps": 131280, "total_steps": 181800, "loss": 0.0541, "lr": 1.0868142220689124e-05, "epoch": 14.442244224422442, "percentage": 72.21, "elapsed_time": "5:10:50", "remaining_time": "1:59:37", "throughput": 1485.49, "total_tokens": 27704832} {"current_steps": 131285, "total_steps": 181800, "loss": 0.0795, "lr": 1.0866162462755325e-05, "epoch": 14.442794279427943, "percentage": 72.21, "elapsed_time": "5:10:50", "remaining_time": "1:59:36", "throughput": 1485.49, "total_tokens": 27705920} {"current_steps": 131290, "total_steps": 181800, "loss": 0.0008, "lr": 1.0864182835086323e-05, "epoch": 14.443344334433444, "percentage": 72.22, "elapsed_time": "5:10:51", "remaining_time": "1:59:35", "throughput": 1485.5, "total_tokens": 27706976} {"current_steps": 131295, "total_steps": 181800, "loss": 0.1682, "lr": 1.0862203337700375e-05, "epoch": 14.443894389438944, "percentage": 72.22, "elapsed_time": "5:10:52", "remaining_time": "1:59:34", "throughput": 1485.49, "total_tokens": 27707968} {"current_steps": 131300, "total_steps": 181800, "loss": 0.1252, "lr": 1.0860223970615708e-05, "epoch": 14.444444444444445, "percentage": 72.22, "elapsed_time": "5:10:53", "remaining_time": "1:59:34", "throughput": 1485.5, "total_tokens": 27709024} {"current_steps": 131305, "total_steps": 181800, "loss": 0.011, "lr": 1.0858244733850578e-05, "epoch": 14.444994499449946, "percentage": 72.22, "elapsed_time": "5:10:53", "remaining_time": "1:59:33", "throughput": 1485.5, "total_tokens": 27710080} {"current_steps": 131310, "total_steps": 181800, "loss": 0.0752, "lr": 1.085626562742322e-05, "epoch": 14.445544554455445, "percentage": 72.23, "elapsed_time": "5:10:54", "remaining_time": "1:59:32", "throughput": 1485.5, "total_tokens": 27711168} {"current_steps": 131315, "total_steps": 181800, "loss": 0.0702, "lr": 1.0854286651351867e-05, "epoch": 14.446094609460946, "percentage": 72.23, "elapsed_time": "5:10:55", "remaining_time": "1:59:32", "throughput": 1485.5, "total_tokens": 27712224} {"current_steps": 131320, "total_steps": 181800, "loss": 0.048, "lr": 1.0852307805654766e-05, "epoch": 14.446644664466447, "percentage": 72.23, "elapsed_time": "5:10:55", "remaining_time": "1:59:31", "throughput": 1485.51, "total_tokens": 27713280} {"current_steps": 131325, "total_steps": 181800, "loss": 0.0066, "lr": 1.0850329090350156e-05, "epoch": 14.447194719471947, "percentage": 72.24, "elapsed_time": "5:10:56", "remaining_time": "1:59:30", "throughput": 1485.51, "total_tokens": 27714368} {"current_steps": 131330, "total_steps": 181800, "loss": 0.1592, "lr": 1.0848350505456282e-05, "epoch": 14.447744774477448, "percentage": 72.24, "elapsed_time": "5:10:57", "remaining_time": "1:59:29", "throughput": 1485.51, "total_tokens": 27715424} {"current_steps": 131335, "total_steps": 181800, "loss": 0.0406, "lr": 1.0846372050991372e-05, "epoch": 14.448294829482949, "percentage": 72.24, "elapsed_time": "5:10:57", "remaining_time": "1:59:29", "throughput": 1485.51, "total_tokens": 27716416} {"current_steps": 131340, "total_steps": 181800, "loss": 0.0502, "lr": 1.0844393726973645e-05, "epoch": 14.448844884488448, "percentage": 72.24, "elapsed_time": "5:10:58", "remaining_time": "1:59:28", "throughput": 1485.51, "total_tokens": 27717408} {"current_steps": 131345, "total_steps": 181800, "loss": 0.0056, "lr": 1.0842415533421354e-05, "epoch": 14.44939493949395, "percentage": 72.25, "elapsed_time": "5:10:59", "remaining_time": "1:59:27", "throughput": 1485.5, "total_tokens": 27718368} {"current_steps": 131350, "total_steps": 181800, "loss": 0.0047, "lr": 1.0840437470352723e-05, "epoch": 14.44994499449945, "percentage": 72.25, "elapsed_time": "5:10:59", "remaining_time": "1:59:27", "throughput": 1485.5, "total_tokens": 27719392} {"current_steps": 131355, "total_steps": 181800, "loss": 0.0119, "lr": 1.0838459537785995e-05, "epoch": 14.450495049504951, "percentage": 72.25, "elapsed_time": "5:11:00", "remaining_time": "1:59:26", "throughput": 1485.5, "total_tokens": 27720448} {"current_steps": 131360, "total_steps": 181800, "loss": 0.0963, "lr": 1.083648173573939e-05, "epoch": 14.45104510451045, "percentage": 72.26, "elapsed_time": "5:11:01", "remaining_time": "1:59:25", "throughput": 1485.51, "total_tokens": 27721536} {"current_steps": 131365, "total_steps": 181800, "loss": 0.1327, "lr": 1.0834504064231127e-05, "epoch": 14.451595159515952, "percentage": 72.26, "elapsed_time": "5:11:02", "remaining_time": "1:59:24", "throughput": 1485.51, "total_tokens": 27722688} {"current_steps": 131370, "total_steps": 181800, "loss": 0.0596, "lr": 1.0832526523279455e-05, "epoch": 14.452145214521453, "percentage": 72.26, "elapsed_time": "5:11:02", "remaining_time": "1:59:24", "throughput": 1485.52, "total_tokens": 27723744} {"current_steps": 131375, "total_steps": 181800, "loss": 0.002, "lr": 1.0830549112902575e-05, "epoch": 14.452695269526952, "percentage": 72.26, "elapsed_time": "5:11:03", "remaining_time": "1:59:23", "throughput": 1485.52, "total_tokens": 27724832} {"current_steps": 131380, "total_steps": 181800, "loss": 0.0076, "lr": 1.0828571833118726e-05, "epoch": 14.453245324532453, "percentage": 72.27, "elapsed_time": "5:11:04", "remaining_time": "1:59:22", "throughput": 1485.52, "total_tokens": 27725920} {"current_steps": 131385, "total_steps": 181800, "loss": 0.0126, "lr": 1.082659468394614e-05, "epoch": 14.453795379537954, "percentage": 72.27, "elapsed_time": "5:11:04", "remaining_time": "1:59:22", "throughput": 1485.52, "total_tokens": 27726976} {"current_steps": 131390, "total_steps": 181800, "loss": 0.0108, "lr": 1.082461766540302e-05, "epoch": 14.454345434543454, "percentage": 72.27, "elapsed_time": "5:11:05", "remaining_time": "1:59:21", "throughput": 1485.52, "total_tokens": 27727968} {"current_steps": 131395, "total_steps": 181800, "loss": 0.0081, "lr": 1.0822640777507603e-05, "epoch": 14.454895489548955, "percentage": 72.27, "elapsed_time": "5:11:06", "remaining_time": "1:59:20", "throughput": 1485.52, "total_tokens": 27728928} {"current_steps": 131400, "total_steps": 181800, "loss": 0.0111, "lr": 1.0820664020278099e-05, "epoch": 14.455445544554456, "percentage": 72.28, "elapsed_time": "5:11:06", "remaining_time": "1:59:19", "throughput": 1485.52, "total_tokens": 27730016} {"current_steps": 131405, "total_steps": 181800, "loss": 0.0077, "lr": 1.0818687393732726e-05, "epoch": 14.455995599559955, "percentage": 72.28, "elapsed_time": "5:11:07", "remaining_time": "1:59:19", "throughput": 1485.52, "total_tokens": 27731072} {"current_steps": 131410, "total_steps": 181800, "loss": 0.1013, "lr": 1.081671089788972e-05, "epoch": 14.456545654565456, "percentage": 72.28, "elapsed_time": "5:11:08", "remaining_time": "1:59:18", "throughput": 1485.53, "total_tokens": 27732160} {"current_steps": 131415, "total_steps": 181800, "loss": 0.0039, "lr": 1.0814734532767274e-05, "epoch": 14.457095709570957, "percentage": 72.29, "elapsed_time": "5:11:08", "remaining_time": "1:59:17", "throughput": 1485.53, "total_tokens": 27733216} {"current_steps": 131420, "total_steps": 181800, "loss": 0.0095, "lr": 1.0812758298383621e-05, "epoch": 14.457645764576458, "percentage": 72.29, "elapsed_time": "5:11:09", "remaining_time": "1:59:17", "throughput": 1485.53, "total_tokens": 27734304} {"current_steps": 131425, "total_steps": 181800, "loss": 0.0666, "lr": 1.0810782194756958e-05, "epoch": 14.458195819581958, "percentage": 72.29, "elapsed_time": "5:11:10", "remaining_time": "1:59:16", "throughput": 1485.54, "total_tokens": 27735392} {"current_steps": 131430, "total_steps": 181800, "loss": 0.0076, "lr": 1.0808806221905516e-05, "epoch": 14.458745874587459, "percentage": 72.29, "elapsed_time": "5:11:10", "remaining_time": "1:59:15", "throughput": 1485.54, "total_tokens": 27736416} {"current_steps": 131435, "total_steps": 181800, "loss": 0.0132, "lr": 1.0806830379847488e-05, "epoch": 14.45929592959296, "percentage": 72.3, "elapsed_time": "5:11:11", "remaining_time": "1:59:14", "throughput": 1485.54, "total_tokens": 27737504} {"current_steps": 131440, "total_steps": 181800, "loss": 0.1254, "lr": 1.0804854668601094e-05, "epoch": 14.45984598459846, "percentage": 72.3, "elapsed_time": "5:11:12", "remaining_time": "1:59:14", "throughput": 1485.54, "total_tokens": 27738624} {"current_steps": 131445, "total_steps": 181800, "loss": 0.0067, "lr": 1.0802879088184553e-05, "epoch": 14.46039603960396, "percentage": 72.3, "elapsed_time": "5:11:13", "remaining_time": "1:59:13", "throughput": 1485.55, "total_tokens": 27739680} {"current_steps": 131450, "total_steps": 181800, "loss": 0.0041, "lr": 1.0800903638616052e-05, "epoch": 14.460946094609461, "percentage": 72.3, "elapsed_time": "5:11:13", "remaining_time": "1:59:12", "throughput": 1485.55, "total_tokens": 27740800} {"current_steps": 131455, "total_steps": 181800, "loss": 0.0042, "lr": 1.079892831991382e-05, "epoch": 14.46149614961496, "percentage": 72.31, "elapsed_time": "5:11:14", "remaining_time": "1:59:11", "throughput": 1485.55, "total_tokens": 27741888} {"current_steps": 131460, "total_steps": 181800, "loss": 0.0328, "lr": 1.079695313209605e-05, "epoch": 14.462046204620462, "percentage": 72.31, "elapsed_time": "5:11:15", "remaining_time": "1:59:11", "throughput": 1485.56, "total_tokens": 27743040} {"current_steps": 131465, "total_steps": 181800, "loss": 0.1501, "lr": 1.079497807518093e-05, "epoch": 14.462596259625963, "percentage": 72.31, "elapsed_time": "5:11:15", "remaining_time": "1:59:10", "throughput": 1485.57, "total_tokens": 27744160} {"current_steps": 131470, "total_steps": 181800, "loss": 0.0026, "lr": 1.0793003149186698e-05, "epoch": 14.463146314631462, "percentage": 72.32, "elapsed_time": "5:11:16", "remaining_time": "1:59:09", "throughput": 1485.57, "total_tokens": 27745184} {"current_steps": 131475, "total_steps": 181800, "loss": 0.013, "lr": 1.0791028354131542e-05, "epoch": 14.463696369636963, "percentage": 72.32, "elapsed_time": "5:11:17", "remaining_time": "1:59:09", "throughput": 1485.56, "total_tokens": 27746176} {"current_steps": 131480, "total_steps": 181800, "loss": 0.0038, "lr": 1.0789053690033645e-05, "epoch": 14.464246424642464, "percentage": 72.32, "elapsed_time": "5:11:17", "remaining_time": "1:59:08", "throughput": 1485.57, "total_tokens": 27747296} {"current_steps": 131485, "total_steps": 181800, "loss": 0.102, "lr": 1.0787079156911234e-05, "epoch": 14.464796479647966, "percentage": 72.32, "elapsed_time": "5:11:18", "remaining_time": "1:59:07", "throughput": 1485.57, "total_tokens": 27748384} {"current_steps": 131490, "total_steps": 181800, "loss": 0.0048, "lr": 1.0785104754782484e-05, "epoch": 14.465346534653465, "percentage": 72.33, "elapsed_time": "5:11:19", "remaining_time": "1:59:06", "throughput": 1485.58, "total_tokens": 27749504} {"current_steps": 131495, "total_steps": 181800, "loss": 0.1304, "lr": 1.0783130483665605e-05, "epoch": 14.465896589658966, "percentage": 72.33, "elapsed_time": "5:11:19", "remaining_time": "1:59:06", "throughput": 1485.58, "total_tokens": 27750624} {"current_steps": 131500, "total_steps": 181800, "loss": 0.0041, "lr": 1.0781156343578797e-05, "epoch": 14.466446644664467, "percentage": 72.33, "elapsed_time": "5:11:20", "remaining_time": "1:59:05", "throughput": 1485.58, "total_tokens": 27751648} {"current_steps": 131505, "total_steps": 181800, "loss": 0.0024, "lr": 1.077918233454024e-05, "epoch": 14.466996699669966, "percentage": 72.33, "elapsed_time": "5:11:21", "remaining_time": "1:59:04", "throughput": 1485.59, "total_tokens": 27752736} {"current_steps": 131510, "total_steps": 181800, "loss": 0.0077, "lr": 1.0777208456568144e-05, "epoch": 14.467546754675467, "percentage": 72.34, "elapsed_time": "5:11:22", "remaining_time": "1:59:04", "throughput": 1485.59, "total_tokens": 27753824} {"current_steps": 131515, "total_steps": 181800, "loss": 0.0434, "lr": 1.0775234709680684e-05, "epoch": 14.468096809680969, "percentage": 72.34, "elapsed_time": "5:11:22", "remaining_time": "1:59:03", "throughput": 1485.59, "total_tokens": 27754848} {"current_steps": 131520, "total_steps": 181800, "loss": 0.0065, "lr": 1.0773261093896061e-05, "epoch": 14.468646864686468, "percentage": 72.34, "elapsed_time": "5:11:23", "remaining_time": "1:59:02", "throughput": 1485.59, "total_tokens": 27755936} {"current_steps": 131525, "total_steps": 181800, "loss": 0.1113, "lr": 1.0771287609232472e-05, "epoch": 14.469196919691969, "percentage": 72.35, "elapsed_time": "5:11:24", "remaining_time": "1:59:01", "throughput": 1485.6, "total_tokens": 27757056} {"current_steps": 131530, "total_steps": 181800, "loss": 0.0027, "lr": 1.0769314255708088e-05, "epoch": 14.46974697469747, "percentage": 72.35, "elapsed_time": "5:11:24", "remaining_time": "1:59:01", "throughput": 1485.6, "total_tokens": 27758112} {"current_steps": 131535, "total_steps": 181800, "loss": 0.0426, "lr": 1.0767341033341116e-05, "epoch": 14.47029702970297, "percentage": 72.35, "elapsed_time": "5:11:25", "remaining_time": "1:59:00", "throughput": 1485.6, "total_tokens": 27759200} {"current_steps": 131540, "total_steps": 181800, "loss": 0.0015, "lr": 1.0765367942149723e-05, "epoch": 14.47084708470847, "percentage": 72.35, "elapsed_time": "5:11:26", "remaining_time": "1:58:59", "throughput": 1485.6, "total_tokens": 27760256} {"current_steps": 131545, "total_steps": 181800, "loss": 0.0422, "lr": 1.0763394982152112e-05, "epoch": 14.471397139713972, "percentage": 72.36, "elapsed_time": "5:11:26", "remaining_time": "1:58:59", "throughput": 1485.6, "total_tokens": 27761312} {"current_steps": 131550, "total_steps": 181800, "loss": 0.0023, "lr": 1.0761422153366449e-05, "epoch": 14.471947194719473, "percentage": 72.36, "elapsed_time": "5:11:27", "remaining_time": "1:58:58", "throughput": 1485.61, "total_tokens": 27762400} {"current_steps": 131555, "total_steps": 181800, "loss": 0.0136, "lr": 1.0759449455810928e-05, "epoch": 14.472497249724972, "percentage": 72.36, "elapsed_time": "5:11:28", "remaining_time": "1:58:57", "throughput": 1485.61, "total_tokens": 27763456} {"current_steps": 131560, "total_steps": 181800, "loss": 0.016, "lr": 1.0757476889503734e-05, "epoch": 14.473047304730473, "percentage": 72.37, "elapsed_time": "5:11:28", "remaining_time": "1:58:56", "throughput": 1485.61, "total_tokens": 27764512} {"current_steps": 131565, "total_steps": 181800, "loss": 0.0172, "lr": 1.075550445446303e-05, "epoch": 14.473597359735974, "percentage": 72.37, "elapsed_time": "5:11:29", "remaining_time": "1:58:56", "throughput": 1485.61, "total_tokens": 27765536} {"current_steps": 131570, "total_steps": 181800, "loss": 0.1217, "lr": 1.0753532150707021e-05, "epoch": 14.474147414741473, "percentage": 72.37, "elapsed_time": "5:11:30", "remaining_time": "1:58:55", "throughput": 1485.61, "total_tokens": 27766592} {"current_steps": 131575, "total_steps": 181800, "loss": 0.0227, "lr": 1.0751559978253867e-05, "epoch": 14.474697469746975, "percentage": 72.37, "elapsed_time": "5:11:31", "remaining_time": "1:58:54", "throughput": 1485.61, "total_tokens": 27767616} {"current_steps": 131580, "total_steps": 181800, "loss": 0.0144, "lr": 1.074958793712173e-05, "epoch": 14.475247524752476, "percentage": 72.38, "elapsed_time": "5:11:31", "remaining_time": "1:58:54", "throughput": 1485.61, "total_tokens": 27768672} {"current_steps": 131585, "total_steps": 181800, "loss": 0.083, "lr": 1.0747616027328822e-05, "epoch": 14.475797579757975, "percentage": 72.38, "elapsed_time": "5:11:32", "remaining_time": "1:58:53", "throughput": 1485.61, "total_tokens": 27769728} {"current_steps": 131590, "total_steps": 181800, "loss": 0.057, "lr": 1.0745644248893286e-05, "epoch": 14.476347634763476, "percentage": 72.38, "elapsed_time": "5:11:33", "remaining_time": "1:58:52", "throughput": 1485.62, "total_tokens": 27770784} {"current_steps": 131595, "total_steps": 181800, "loss": 0.0037, "lr": 1.0743672601833318e-05, "epoch": 14.476897689768977, "percentage": 72.38, "elapsed_time": "5:11:33", "remaining_time": "1:58:51", "throughput": 1485.62, "total_tokens": 27771808} {"current_steps": 131600, "total_steps": 181800, "loss": 0.0031, "lr": 1.074170108616708e-05, "epoch": 14.477447744774478, "percentage": 72.39, "elapsed_time": "5:11:34", "remaining_time": "1:58:51", "throughput": 1485.62, "total_tokens": 27772864} {"current_steps": 131605, "total_steps": 181800, "loss": 0.0224, "lr": 1.0739729701912731e-05, "epoch": 14.477997799779978, "percentage": 72.39, "elapsed_time": "5:11:35", "remaining_time": "1:58:50", "throughput": 1485.62, "total_tokens": 27773888} {"current_steps": 131610, "total_steps": 181800, "loss": 0.0049, "lr": 1.073775844908845e-05, "epoch": 14.478547854785479, "percentage": 72.39, "elapsed_time": "5:11:35", "remaining_time": "1:58:49", "throughput": 1485.62, "total_tokens": 27774912} {"current_steps": 131615, "total_steps": 181800, "loss": 0.0725, "lr": 1.0735787327712406e-05, "epoch": 14.47909790979098, "percentage": 72.4, "elapsed_time": "5:11:36", "remaining_time": "1:58:49", "throughput": 1485.62, "total_tokens": 27776000} {"current_steps": 131620, "total_steps": 181800, "loss": 0.01, "lr": 1.0733816337802776e-05, "epoch": 14.479647964796479, "percentage": 72.4, "elapsed_time": "5:11:37", "remaining_time": "1:58:48", "throughput": 1485.62, "total_tokens": 27777056} {"current_steps": 131625, "total_steps": 181800, "loss": 0.0073, "lr": 1.0731845479377715e-05, "epoch": 14.48019801980198, "percentage": 72.4, "elapsed_time": "5:11:37", "remaining_time": "1:58:47", "throughput": 1485.63, "total_tokens": 27778144} {"current_steps": 131630, "total_steps": 181800, "loss": 0.0048, "lr": 1.0729874752455377e-05, "epoch": 14.480748074807481, "percentage": 72.4, "elapsed_time": "5:11:38", "remaining_time": "1:58:46", "throughput": 1485.63, "total_tokens": 27779200} {"current_steps": 131635, "total_steps": 181800, "loss": 0.1084, "lr": 1.0727904157053947e-05, "epoch": 14.48129812981298, "percentage": 72.41, "elapsed_time": "5:11:39", "remaining_time": "1:58:46", "throughput": 1485.63, "total_tokens": 27780256} {"current_steps": 131640, "total_steps": 181800, "loss": 0.0335, "lr": 1.0725933693191556e-05, "epoch": 14.481848184818482, "percentage": 72.41, "elapsed_time": "5:11:39", "remaining_time": "1:58:45", "throughput": 1485.63, "total_tokens": 27781312} {"current_steps": 131645, "total_steps": 181800, "loss": 0.0024, "lr": 1.0723963360886405e-05, "epoch": 14.482398239823983, "percentage": 72.41, "elapsed_time": "5:11:40", "remaining_time": "1:58:44", "throughput": 1485.63, "total_tokens": 27782336} {"current_steps": 131650, "total_steps": 181800, "loss": 0.0121, "lr": 1.0721993160156631e-05, "epoch": 14.482948294829482, "percentage": 72.41, "elapsed_time": "5:11:41", "remaining_time": "1:58:43", "throughput": 1485.63, "total_tokens": 27783392} {"current_steps": 131655, "total_steps": 181800, "loss": 0.0046, "lr": 1.0720023091020387e-05, "epoch": 14.483498349834983, "percentage": 72.42, "elapsed_time": "5:11:42", "remaining_time": "1:58:43", "throughput": 1485.64, "total_tokens": 27784480} {"current_steps": 131660, "total_steps": 181800, "loss": 0.0027, "lr": 1.0718053153495846e-05, "epoch": 14.484048404840484, "percentage": 72.42, "elapsed_time": "5:11:42", "remaining_time": "1:58:42", "throughput": 1485.64, "total_tokens": 27785536} {"current_steps": 131665, "total_steps": 181800, "loss": 0.0148, "lr": 1.071608334760115e-05, "epoch": 14.484598459845985, "percentage": 72.42, "elapsed_time": "5:11:43", "remaining_time": "1:58:41", "throughput": 1485.64, "total_tokens": 27786656} {"current_steps": 131670, "total_steps": 181800, "loss": 0.0645, "lr": 1.0714113673354456e-05, "epoch": 14.485148514851485, "percentage": 72.43, "elapsed_time": "5:11:44", "remaining_time": "1:58:41", "throughput": 1485.64, "total_tokens": 27787616} {"current_steps": 131675, "total_steps": 181800, "loss": 0.1003, "lr": 1.0712144130773932e-05, "epoch": 14.485698569856986, "percentage": 72.43, "elapsed_time": "5:11:44", "remaining_time": "1:58:40", "throughput": 1485.65, "total_tokens": 27788736} {"current_steps": 131680, "total_steps": 181800, "loss": 0.0037, "lr": 1.0710174719877711e-05, "epoch": 14.486248624862487, "percentage": 72.43, "elapsed_time": "5:11:45", "remaining_time": "1:58:39", "throughput": 1485.65, "total_tokens": 27789824} {"current_steps": 131685, "total_steps": 181800, "loss": 0.0016, "lr": 1.070820544068396e-05, "epoch": 14.486798679867986, "percentage": 72.43, "elapsed_time": "5:11:46", "remaining_time": "1:58:38", "throughput": 1485.65, "total_tokens": 27790880} {"current_steps": 131690, "total_steps": 181800, "loss": 0.0105, "lr": 1.0706236293210822e-05, "epoch": 14.487348734873487, "percentage": 72.44, "elapsed_time": "5:11:46", "remaining_time": "1:58:38", "throughput": 1485.65, "total_tokens": 27791968} {"current_steps": 131695, "total_steps": 181800, "loss": 0.0404, "lr": 1.0704267277476438e-05, "epoch": 14.487898789878988, "percentage": 72.44, "elapsed_time": "5:11:47", "remaining_time": "1:58:37", "throughput": 1485.65, "total_tokens": 27793024} {"current_steps": 131700, "total_steps": 181800, "loss": 0.0321, "lr": 1.0702298393498961e-05, "epoch": 14.488448844884488, "percentage": 72.44, "elapsed_time": "5:11:48", "remaining_time": "1:58:36", "throughput": 1485.66, "total_tokens": 27794080} {"current_steps": 131705, "total_steps": 181800, "loss": 0.0075, "lr": 1.0700329641296541e-05, "epoch": 14.488998899889989, "percentage": 72.44, "elapsed_time": "5:11:48", "remaining_time": "1:58:36", "throughput": 1485.66, "total_tokens": 27795104} {"current_steps": 131710, "total_steps": 181800, "loss": 0.0524, "lr": 1.0698361020887328e-05, "epoch": 14.48954895489549, "percentage": 72.45, "elapsed_time": "5:11:49", "remaining_time": "1:58:35", "throughput": 1485.66, "total_tokens": 27796256} {"current_steps": 131715, "total_steps": 181800, "loss": 0.0391, "lr": 1.069639253228946e-05, "epoch": 14.490099009900991, "percentage": 72.45, "elapsed_time": "5:11:50", "remaining_time": "1:58:34", "throughput": 1485.67, "total_tokens": 27797344} {"current_steps": 131720, "total_steps": 181800, "loss": 0.1874, "lr": 1.0694424175521067e-05, "epoch": 14.49064906490649, "percentage": 72.45, "elapsed_time": "5:11:51", "remaining_time": "1:58:33", "throughput": 1485.67, "total_tokens": 27798432} {"current_steps": 131725, "total_steps": 181800, "loss": 0.0143, "lr": 1.0692455950600306e-05, "epoch": 14.491199119911991, "percentage": 72.46, "elapsed_time": "5:11:51", "remaining_time": "1:58:33", "throughput": 1485.67, "total_tokens": 27799552} {"current_steps": 131730, "total_steps": 181800, "loss": 0.015, "lr": 1.0690487857545309e-05, "epoch": 14.491749174917492, "percentage": 72.46, "elapsed_time": "5:11:52", "remaining_time": "1:58:32", "throughput": 1485.67, "total_tokens": 27800576} {"current_steps": 131735, "total_steps": 181800, "loss": 0.0023, "lr": 1.068851989637423e-05, "epoch": 14.492299229922992, "percentage": 72.46, "elapsed_time": "5:11:53", "remaining_time": "1:58:31", "throughput": 1485.67, "total_tokens": 27801632} {"current_steps": 131740, "total_steps": 181800, "loss": 0.001, "lr": 1.0686552067105197e-05, "epoch": 14.492849284928493, "percentage": 72.46, "elapsed_time": "5:11:53", "remaining_time": "1:58:31", "throughput": 1485.68, "total_tokens": 27802752} {"current_steps": 131745, "total_steps": 181800, "loss": 0.0943, "lr": 1.0684584369756335e-05, "epoch": 14.493399339933994, "percentage": 72.47, "elapsed_time": "5:11:54", "remaining_time": "1:58:30", "throughput": 1485.68, "total_tokens": 27803808} {"current_steps": 131750, "total_steps": 181800, "loss": 0.0423, "lr": 1.0682616804345799e-05, "epoch": 14.493949394939493, "percentage": 72.47, "elapsed_time": "5:11:55", "remaining_time": "1:58:29", "throughput": 1485.68, "total_tokens": 27804864} {"current_steps": 131755, "total_steps": 181800, "loss": 0.0024, "lr": 1.0680649370891704e-05, "epoch": 14.494499449944994, "percentage": 72.47, "elapsed_time": "5:11:55", "remaining_time": "1:58:28", "throughput": 1485.69, "total_tokens": 27805952} {"current_steps": 131760, "total_steps": 181800, "loss": 0.0046, "lr": 1.0678682069412194e-05, "epoch": 14.495049504950495, "percentage": 72.48, "elapsed_time": "5:11:56", "remaining_time": "1:58:28", "throughput": 1485.68, "total_tokens": 27806944} {"current_steps": 131765, "total_steps": 181800, "loss": 0.0078, "lr": 1.0676714899925409e-05, "epoch": 14.495599559955995, "percentage": 72.48, "elapsed_time": "5:11:57", "remaining_time": "1:58:27", "throughput": 1485.69, "total_tokens": 27808000} {"current_steps": 131770, "total_steps": 181800, "loss": 0.0129, "lr": 1.0674747862449458e-05, "epoch": 14.496149614961496, "percentage": 72.48, "elapsed_time": "5:11:57", "remaining_time": "1:58:26", "throughput": 1485.69, "total_tokens": 27809024} {"current_steps": 131775, "total_steps": 181800, "loss": 0.0314, "lr": 1.0672780957002494e-05, "epoch": 14.496699669966997, "percentage": 72.48, "elapsed_time": "5:11:58", "remaining_time": "1:58:26", "throughput": 1485.68, "total_tokens": 27810016} {"current_steps": 131780, "total_steps": 181800, "loss": 0.0182, "lr": 1.067081418360262e-05, "epoch": 14.497249724972498, "percentage": 72.49, "elapsed_time": "5:11:59", "remaining_time": "1:58:25", "throughput": 1485.68, "total_tokens": 27811040} {"current_steps": 131785, "total_steps": 181800, "loss": 0.0101, "lr": 1.066884754226798e-05, "epoch": 14.497799779977997, "percentage": 72.49, "elapsed_time": "5:12:00", "remaining_time": "1:58:24", "throughput": 1485.69, "total_tokens": 27812160} {"current_steps": 131790, "total_steps": 181800, "loss": 0.002, "lr": 1.0666881033016701e-05, "epoch": 14.498349834983498, "percentage": 72.49, "elapsed_time": "5:12:00", "remaining_time": "1:58:23", "throughput": 1485.69, "total_tokens": 27813152} {"current_steps": 131795, "total_steps": 181800, "loss": 0.0043, "lr": 1.0664914655866895e-05, "epoch": 14.498899889989, "percentage": 72.49, "elapsed_time": "5:12:01", "remaining_time": "1:58:23", "throughput": 1485.69, "total_tokens": 27814240} {"current_steps": 131800, "total_steps": 181800, "loss": 0.0877, "lr": 1.0662948410836701e-05, "epoch": 14.499449944994499, "percentage": 72.5, "elapsed_time": "5:12:02", "remaining_time": "1:58:22", "throughput": 1485.69, "total_tokens": 27815232} {"current_steps": 131805, "total_steps": 181800, "loss": 0.0486, "lr": 1.0660982297944221e-05, "epoch": 14.5, "percentage": 72.5, "elapsed_time": "5:12:02", "remaining_time": "1:58:21", "throughput": 1485.7, "total_tokens": 27816384} {"current_steps": 131810, "total_steps": 181800, "loss": 0.0357, "lr": 1.0659016317207599e-05, "epoch": 14.500550055005501, "percentage": 72.5, "elapsed_time": "5:12:03", "remaining_time": "1:58:21", "throughput": 1485.7, "total_tokens": 27817472} {"current_steps": 131815, "total_steps": 181800, "loss": 0.045, "lr": 1.065705046864493e-05, "epoch": 14.501100110011, "percentage": 72.51, "elapsed_time": "5:12:04", "remaining_time": "1:58:20", "throughput": 1485.7, "total_tokens": 27818528} {"current_steps": 131820, "total_steps": 181800, "loss": 0.0055, "lr": 1.0655084752274347e-05, "epoch": 14.501650165016502, "percentage": 72.51, "elapsed_time": "5:12:04", "remaining_time": "1:58:19", "throughput": 1485.7, "total_tokens": 27819552} {"current_steps": 131825, "total_steps": 181800, "loss": 0.0011, "lr": 1.065311916811397e-05, "epoch": 14.502200220022003, "percentage": 72.51, "elapsed_time": "5:12:05", "remaining_time": "1:58:18", "throughput": 1485.7, "total_tokens": 27820608} {"current_steps": 131830, "total_steps": 181800, "loss": 0.0023, "lr": 1.0651153716181902e-05, "epoch": 14.502750275027502, "percentage": 72.51, "elapsed_time": "5:12:06", "remaining_time": "1:58:18", "throughput": 1485.7, "total_tokens": 27821632} {"current_steps": 131835, "total_steps": 181800, "loss": 0.026, "lr": 1.0649188396496277e-05, "epoch": 14.503300330033003, "percentage": 72.52, "elapsed_time": "5:12:06", "remaining_time": "1:58:17", "throughput": 1485.71, "total_tokens": 27822720} {"current_steps": 131840, "total_steps": 181800, "loss": 0.0196, "lr": 1.0647223209075184e-05, "epoch": 14.503850385038504, "percentage": 72.52, "elapsed_time": "5:12:07", "remaining_time": "1:58:16", "throughput": 1485.71, "total_tokens": 27823776} {"current_steps": 131845, "total_steps": 181800, "loss": 0.084, "lr": 1.0645258153936747e-05, "epoch": 14.504400440044005, "percentage": 72.52, "elapsed_time": "5:12:08", "remaining_time": "1:58:16", "throughput": 1485.71, "total_tokens": 27824800} {"current_steps": 131850, "total_steps": 181800, "loss": 0.0076, "lr": 1.0643293231099088e-05, "epoch": 14.504950495049505, "percentage": 72.52, "elapsed_time": "5:12:08", "remaining_time": "1:58:15", "throughput": 1485.71, "total_tokens": 27825792} {"current_steps": 131855, "total_steps": 181800, "loss": 0.0269, "lr": 1.0641328440580306e-05, "epoch": 14.505500550055006, "percentage": 72.53, "elapsed_time": "5:12:09", "remaining_time": "1:58:14", "throughput": 1485.7, "total_tokens": 27826784} {"current_steps": 131860, "total_steps": 181800, "loss": 0.0041, "lr": 1.0639363782398501e-05, "epoch": 14.506050605060507, "percentage": 72.53, "elapsed_time": "5:12:10", "remaining_time": "1:58:13", "throughput": 1485.7, "total_tokens": 27827808} {"current_steps": 131865, "total_steps": 181800, "loss": 0.0016, "lr": 1.0637399256571797e-05, "epoch": 14.506600660066006, "percentage": 72.53, "elapsed_time": "5:12:11", "remaining_time": "1:58:13", "throughput": 1485.71, "total_tokens": 27828896} {"current_steps": 131870, "total_steps": 181800, "loss": 0.0101, "lr": 1.0635434863118285e-05, "epoch": 14.507150715071507, "percentage": 72.54, "elapsed_time": "5:12:11", "remaining_time": "1:58:12", "throughput": 1485.71, "total_tokens": 27830048} {"current_steps": 131875, "total_steps": 181800, "loss": 0.0135, "lr": 1.0633470602056076e-05, "epoch": 14.507700770077008, "percentage": 72.54, "elapsed_time": "5:12:12", "remaining_time": "1:58:11", "throughput": 1485.72, "total_tokens": 27831136} {"current_steps": 131880, "total_steps": 181800, "loss": 0.0516, "lr": 1.0631506473403285e-05, "epoch": 14.508250825082508, "percentage": 72.54, "elapsed_time": "5:12:13", "remaining_time": "1:58:10", "throughput": 1485.72, "total_tokens": 27832160} {"current_steps": 131885, "total_steps": 181800, "loss": 0.0015, "lr": 1.0629542477177992e-05, "epoch": 14.508800880088009, "percentage": 72.54, "elapsed_time": "5:12:13", "remaining_time": "1:58:10", "throughput": 1485.72, "total_tokens": 27833216} {"current_steps": 131890, "total_steps": 181800, "loss": 0.0553, "lr": 1.0627578613398322e-05, "epoch": 14.50935093509351, "percentage": 72.55, "elapsed_time": "5:12:14", "remaining_time": "1:58:09", "throughput": 1485.72, "total_tokens": 27834240} {"current_steps": 131895, "total_steps": 181800, "loss": 0.001, "lr": 1.0625614882082354e-05, "epoch": 14.509900990099009, "percentage": 72.55, "elapsed_time": "5:12:15", "remaining_time": "1:58:08", "throughput": 1485.72, "total_tokens": 27835232} {"current_steps": 131900, "total_steps": 181800, "loss": 0.0048, "lr": 1.0623651283248198e-05, "epoch": 14.51045104510451, "percentage": 72.55, "elapsed_time": "5:12:15", "remaining_time": "1:58:08", "throughput": 1485.72, "total_tokens": 27836256} {"current_steps": 131905, "total_steps": 181800, "loss": 0.1249, "lr": 1.0621687816913956e-05, "epoch": 14.511001100110011, "percentage": 72.56, "elapsed_time": "5:12:16", "remaining_time": "1:58:07", "throughput": 1485.72, "total_tokens": 27837280} {"current_steps": 131910, "total_steps": 181800, "loss": 0.0696, "lr": 1.061972448309771e-05, "epoch": 14.511551155115512, "percentage": 72.56, "elapsed_time": "5:12:17", "remaining_time": "1:58:06", "throughput": 1485.72, "total_tokens": 27838368} {"current_steps": 131915, "total_steps": 181800, "loss": 0.004, "lr": 1.061776128181757e-05, "epoch": 14.512101210121012, "percentage": 72.56, "elapsed_time": "5:12:17", "remaining_time": "1:58:05", "throughput": 1485.72, "total_tokens": 27839456} {"current_steps": 131920, "total_steps": 181800, "loss": 0.0199, "lr": 1.0615798213091616e-05, "epoch": 14.512651265126513, "percentage": 72.56, "elapsed_time": "5:12:18", "remaining_time": "1:58:05", "throughput": 1485.72, "total_tokens": 27840448} {"current_steps": 131925, "total_steps": 181800, "loss": 0.0468, "lr": 1.0613835276937958e-05, "epoch": 14.513201320132014, "percentage": 72.57, "elapsed_time": "5:12:19", "remaining_time": "1:58:04", "throughput": 1485.72, "total_tokens": 27841504} {"current_steps": 131930, "total_steps": 181800, "loss": 0.0277, "lr": 1.0611872473374665e-05, "epoch": 14.513751375137513, "percentage": 72.57, "elapsed_time": "5:12:20", "remaining_time": "1:58:03", "throughput": 1485.72, "total_tokens": 27842528} {"current_steps": 131935, "total_steps": 181800, "loss": 0.0738, "lr": 1.0609909802419843e-05, "epoch": 14.514301430143014, "percentage": 72.57, "elapsed_time": "5:12:20", "remaining_time": "1:58:03", "throughput": 1485.73, "total_tokens": 27843584} {"current_steps": 131940, "total_steps": 181800, "loss": 0.0055, "lr": 1.0607947264091584e-05, "epoch": 14.514851485148515, "percentage": 72.57, "elapsed_time": "5:12:21", "remaining_time": "1:58:02", "throughput": 1485.73, "total_tokens": 27844640} {"current_steps": 131945, "total_steps": 181800, "loss": 0.003, "lr": 1.0605984858407959e-05, "epoch": 14.515401540154015, "percentage": 72.58, "elapsed_time": "5:12:22", "remaining_time": "1:58:01", "throughput": 1485.73, "total_tokens": 27845664} {"current_steps": 131950, "total_steps": 181800, "loss": 0.1442, "lr": 1.0604022585387074e-05, "epoch": 14.515951595159516, "percentage": 72.58, "elapsed_time": "5:12:22", "remaining_time": "1:58:00", "throughput": 1485.73, "total_tokens": 27846688} {"current_steps": 131955, "total_steps": 181800, "loss": 0.0068, "lr": 1.0602060445047e-05, "epoch": 14.516501650165017, "percentage": 72.58, "elapsed_time": "5:12:23", "remaining_time": "1:58:00", "throughput": 1485.73, "total_tokens": 27847776} {"current_steps": 131960, "total_steps": 181800, "loss": 0.008, "lr": 1.060009843740582e-05, "epoch": 14.517051705170516, "percentage": 72.59, "elapsed_time": "5:12:24", "remaining_time": "1:57:59", "throughput": 1485.73, "total_tokens": 27848832} {"current_steps": 131965, "total_steps": 181800, "loss": 0.0121, "lr": 1.0598136562481637e-05, "epoch": 14.517601760176017, "percentage": 72.59, "elapsed_time": "5:12:24", "remaining_time": "1:57:58", "throughput": 1485.74, "total_tokens": 27849952} {"current_steps": 131970, "total_steps": 181800, "loss": 0.0085, "lr": 1.0596174820292506e-05, "epoch": 14.518151815181518, "percentage": 72.59, "elapsed_time": "5:12:25", "remaining_time": "1:57:58", "throughput": 1485.74, "total_tokens": 27851008} {"current_steps": 131975, "total_steps": 181800, "loss": 0.0031, "lr": 1.0594213210856533e-05, "epoch": 14.51870187018702, "percentage": 72.59, "elapsed_time": "5:12:26", "remaining_time": "1:57:57", "throughput": 1485.74, "total_tokens": 27852064} {"current_steps": 131980, "total_steps": 181800, "loss": 0.004, "lr": 1.059225173419178e-05, "epoch": 14.519251925192519, "percentage": 72.6, "elapsed_time": "5:12:26", "remaining_time": "1:57:56", "throughput": 1485.74, "total_tokens": 27853152} {"current_steps": 131985, "total_steps": 181800, "loss": 0.0118, "lr": 1.0590290390316321e-05, "epoch": 14.51980198019802, "percentage": 72.6, "elapsed_time": "5:12:27", "remaining_time": "1:57:55", "throughput": 1485.74, "total_tokens": 27854208} {"current_steps": 131990, "total_steps": 181800, "loss": 0.0539, "lr": 1.0588329179248244e-05, "epoch": 14.520352035203521, "percentage": 72.6, "elapsed_time": "5:12:28", "remaining_time": "1:57:55", "throughput": 1485.75, "total_tokens": 27855296} {"current_steps": 131995, "total_steps": 181800, "loss": 0.047, "lr": 1.058636810100562e-05, "epoch": 14.52090209020902, "percentage": 72.6, "elapsed_time": "5:12:29", "remaining_time": "1:57:54", "throughput": 1485.75, "total_tokens": 27856384} {"current_steps": 132000, "total_steps": 181800, "loss": 0.0465, "lr": 1.0584407155606533e-05, "epoch": 14.521452145214521, "percentage": 72.61, "elapsed_time": "5:12:29", "remaining_time": "1:57:53", "throughput": 1485.75, "total_tokens": 27857376} {"current_steps": 132005, "total_steps": 181800, "loss": 0.0013, "lr": 1.058244634306905e-05, "epoch": 14.522002200220022, "percentage": 72.61, "elapsed_time": "5:12:30", "remaining_time": "1:57:53", "throughput": 1485.75, "total_tokens": 27858432} {"current_steps": 132010, "total_steps": 181800, "loss": 0.0325, "lr": 1.058048566341123e-05, "epoch": 14.522552255225522, "percentage": 72.61, "elapsed_time": "5:12:31", "remaining_time": "1:57:52", "throughput": 1485.75, "total_tokens": 27859520} {"current_steps": 132015, "total_steps": 181800, "loss": 0.0047, "lr": 1.0578525116651154e-05, "epoch": 14.523102310231023, "percentage": 72.62, "elapsed_time": "5:12:31", "remaining_time": "1:57:51", "throughput": 1485.76, "total_tokens": 27860608} {"current_steps": 132020, "total_steps": 181800, "loss": 0.0069, "lr": 1.0576564702806893e-05, "epoch": 14.523652365236524, "percentage": 72.62, "elapsed_time": "5:12:32", "remaining_time": "1:57:50", "throughput": 1485.76, "total_tokens": 27861632} {"current_steps": 132025, "total_steps": 181800, "loss": 0.0025, "lr": 1.0574604421896523e-05, "epoch": 14.524202420242025, "percentage": 72.62, "elapsed_time": "5:12:33", "remaining_time": "1:57:50", "throughput": 1485.76, "total_tokens": 27862720} {"current_steps": 132030, "total_steps": 181800, "loss": 0.0047, "lr": 1.05726442739381e-05, "epoch": 14.524752475247524, "percentage": 72.62, "elapsed_time": "5:12:33", "remaining_time": "1:57:49", "throughput": 1485.76, "total_tokens": 27863744} {"current_steps": 132035, "total_steps": 181800, "loss": 0.0295, "lr": 1.0570684258949686e-05, "epoch": 14.525302530253025, "percentage": 72.63, "elapsed_time": "5:12:34", "remaining_time": "1:57:48", "throughput": 1485.76, "total_tokens": 27864864} {"current_steps": 132040, "total_steps": 181800, "loss": 0.0072, "lr": 1.056872437694936e-05, "epoch": 14.525852585258527, "percentage": 72.63, "elapsed_time": "5:12:35", "remaining_time": "1:57:48", "throughput": 1485.77, "total_tokens": 27865984} {"current_steps": 132045, "total_steps": 181800, "loss": 0.05, "lr": 1.0566764627955167e-05, "epoch": 14.526402640264026, "percentage": 72.63, "elapsed_time": "5:12:35", "remaining_time": "1:57:47", "throughput": 1485.77, "total_tokens": 27867040} {"current_steps": 132050, "total_steps": 181800, "loss": 0.0076, "lr": 1.0564805011985177e-05, "epoch": 14.526952695269527, "percentage": 72.63, "elapsed_time": "5:12:36", "remaining_time": "1:57:46", "throughput": 1485.77, "total_tokens": 27868096} {"current_steps": 132055, "total_steps": 181800, "loss": 0.0575, "lr": 1.0562845529057463e-05, "epoch": 14.527502750275028, "percentage": 72.64, "elapsed_time": "5:12:37", "remaining_time": "1:57:45", "throughput": 1485.77, "total_tokens": 27869088} {"current_steps": 132060, "total_steps": 181800, "loss": 0.0007, "lr": 1.0560886179190066e-05, "epoch": 14.528052805280527, "percentage": 72.64, "elapsed_time": "5:12:38", "remaining_time": "1:57:45", "throughput": 1485.77, "total_tokens": 27870176} {"current_steps": 132065, "total_steps": 181800, "loss": 0.0022, "lr": 1.0558926962401058e-05, "epoch": 14.528602860286028, "percentage": 72.64, "elapsed_time": "5:12:38", "remaining_time": "1:57:44", "throughput": 1485.78, "total_tokens": 27871232} {"current_steps": 132070, "total_steps": 181800, "loss": 0.004, "lr": 1.0556967878708485e-05, "epoch": 14.52915291529153, "percentage": 72.65, "elapsed_time": "5:12:39", "remaining_time": "1:57:43", "throughput": 1485.77, "total_tokens": 27872224} {"current_steps": 132075, "total_steps": 181800, "loss": 0.0047, "lr": 1.0555008928130407e-05, "epoch": 14.52970297029703, "percentage": 72.65, "elapsed_time": "5:12:40", "remaining_time": "1:57:42", "throughput": 1485.78, "total_tokens": 27873248} {"current_steps": 132080, "total_steps": 181800, "loss": 0.028, "lr": 1.0553050110684893e-05, "epoch": 14.53025302530253, "percentage": 72.65, "elapsed_time": "5:12:40", "remaining_time": "1:57:42", "throughput": 1485.78, "total_tokens": 27874304} {"current_steps": 132085, "total_steps": 181800, "loss": 0.0271, "lr": 1.055109142638997e-05, "epoch": 14.530803080308031, "percentage": 72.65, "elapsed_time": "5:12:41", "remaining_time": "1:57:41", "throughput": 1485.78, "total_tokens": 27875328} {"current_steps": 132090, "total_steps": 181800, "loss": 0.0119, "lr": 1.0549132875263715e-05, "epoch": 14.531353135313532, "percentage": 72.66, "elapsed_time": "5:12:42", "remaining_time": "1:57:40", "throughput": 1485.77, "total_tokens": 27876320} {"current_steps": 132095, "total_steps": 181800, "loss": 0.0051, "lr": 1.054717445732417e-05, "epoch": 14.531903190319031, "percentage": 72.66, "elapsed_time": "5:12:42", "remaining_time": "1:57:40", "throughput": 1485.78, "total_tokens": 27877376} {"current_steps": 132100, "total_steps": 181800, "loss": 0.0152, "lr": 1.054521617258937e-05, "epoch": 14.532453245324533, "percentage": 72.66, "elapsed_time": "5:12:43", "remaining_time": "1:57:39", "throughput": 1485.78, "total_tokens": 27878400} {"current_steps": 132105, "total_steps": 181800, "loss": 0.0339, "lr": 1.054325802107738e-05, "epoch": 14.533003300330034, "percentage": 72.67, "elapsed_time": "5:12:44", "remaining_time": "1:57:38", "throughput": 1485.78, "total_tokens": 27879488} {"current_steps": 132110, "total_steps": 181800, "loss": 0.0187, "lr": 1.0541300002806242e-05, "epoch": 14.533553355335533, "percentage": 72.67, "elapsed_time": "5:12:44", "remaining_time": "1:57:37", "throughput": 1485.78, "total_tokens": 27880480} {"current_steps": 132115, "total_steps": 181800, "loss": 0.0017, "lr": 1.0539342117794013e-05, "epoch": 14.534103410341034, "percentage": 72.67, "elapsed_time": "5:12:45", "remaining_time": "1:57:37", "throughput": 1485.78, "total_tokens": 27881568} {"current_steps": 132120, "total_steps": 181800, "loss": 0.0091, "lr": 1.0537384366058729e-05, "epoch": 14.534653465346535, "percentage": 72.67, "elapsed_time": "5:12:46", "remaining_time": "1:57:36", "throughput": 1485.79, "total_tokens": 27882688} {"current_steps": 132125, "total_steps": 181800, "loss": 0.0616, "lr": 1.0535426747618424e-05, "epoch": 14.535203520352034, "percentage": 72.68, "elapsed_time": "5:12:46", "remaining_time": "1:57:35", "throughput": 1485.79, "total_tokens": 27883744} {"current_steps": 132130, "total_steps": 181800, "loss": 0.0115, "lr": 1.0533469262491152e-05, "epoch": 14.535753575357536, "percentage": 72.68, "elapsed_time": "5:12:47", "remaining_time": "1:57:35", "throughput": 1485.79, "total_tokens": 27884768} {"current_steps": 132135, "total_steps": 181800, "loss": 0.0026, "lr": 1.053151191069495e-05, "epoch": 14.536303630363037, "percentage": 72.68, "elapsed_time": "5:12:48", "remaining_time": "1:57:34", "throughput": 1485.79, "total_tokens": 27885856} {"current_steps": 132140, "total_steps": 181800, "loss": 0.0108, "lr": 1.052955469224787e-05, "epoch": 14.536853685368538, "percentage": 72.68, "elapsed_time": "5:12:49", "remaining_time": "1:57:33", "throughput": 1485.8, "total_tokens": 27887008} {"current_steps": 132145, "total_steps": 181800, "loss": 0.059, "lr": 1.0527597607167939e-05, "epoch": 14.537403740374037, "percentage": 72.69, "elapsed_time": "5:12:49", "remaining_time": "1:57:32", "throughput": 1485.8, "total_tokens": 27888128} {"current_steps": 132150, "total_steps": 181800, "loss": 0.0055, "lr": 1.052564065547319e-05, "epoch": 14.537953795379538, "percentage": 72.69, "elapsed_time": "5:12:50", "remaining_time": "1:57:32", "throughput": 1485.8, "total_tokens": 27889184} {"current_steps": 132155, "total_steps": 181800, "loss": 0.0044, "lr": 1.0523683837181672e-05, "epoch": 14.53850385038504, "percentage": 72.69, "elapsed_time": "5:12:51", "remaining_time": "1:57:31", "throughput": 1485.8, "total_tokens": 27890208} {"current_steps": 132160, "total_steps": 181800, "loss": 0.0536, "lr": 1.0521727152311406e-05, "epoch": 14.539053905390539, "percentage": 72.7, "elapsed_time": "5:12:51", "remaining_time": "1:57:30", "throughput": 1485.81, "total_tokens": 27891360} {"current_steps": 132165, "total_steps": 181800, "loss": 0.052, "lr": 1.0519770600880433e-05, "epoch": 14.53960396039604, "percentage": 72.7, "elapsed_time": "5:12:52", "remaining_time": "1:57:30", "throughput": 1485.81, "total_tokens": 27892416} {"current_steps": 132170, "total_steps": 181800, "loss": 0.0055, "lr": 1.0517814182906797e-05, "epoch": 14.54015401540154, "percentage": 72.7, "elapsed_time": "5:12:53", "remaining_time": "1:57:29", "throughput": 1485.82, "total_tokens": 27893600} {"current_steps": 132175, "total_steps": 181800, "loss": 0.166, "lr": 1.0515857898408507e-05, "epoch": 14.54070407040704, "percentage": 72.7, "elapsed_time": "5:12:53", "remaining_time": "1:57:28", "throughput": 1485.82, "total_tokens": 27894624} {"current_steps": 132180, "total_steps": 181800, "loss": 0.0125, "lr": 1.0513901747403615e-05, "epoch": 14.541254125412541, "percentage": 72.71, "elapsed_time": "5:12:54", "remaining_time": "1:57:27", "throughput": 1485.82, "total_tokens": 27895744} {"current_steps": 132185, "total_steps": 181800, "loss": 0.0172, "lr": 1.051194572991013e-05, "epoch": 14.541804180418042, "percentage": 72.71, "elapsed_time": "5:12:55", "remaining_time": "1:57:27", "throughput": 1485.83, "total_tokens": 27896864} {"current_steps": 132190, "total_steps": 181800, "loss": 0.0378, "lr": 1.0509989845946088e-05, "epoch": 14.542354235423542, "percentage": 72.71, "elapsed_time": "5:12:55", "remaining_time": "1:57:26", "throughput": 1485.83, "total_tokens": 27897888} {"current_steps": 132195, "total_steps": 181800, "loss": 0.0048, "lr": 1.0508034095529529e-05, "epoch": 14.542904290429043, "percentage": 72.71, "elapsed_time": "5:12:56", "remaining_time": "1:57:25", "throughput": 1485.83, "total_tokens": 27898944} {"current_steps": 132200, "total_steps": 181800, "loss": 0.1154, "lr": 1.0506078478678452e-05, "epoch": 14.543454345434544, "percentage": 72.72, "elapsed_time": "5:12:57", "remaining_time": "1:57:25", "throughput": 1485.83, "total_tokens": 27900000} {"current_steps": 132205, "total_steps": 181800, "loss": 0.0654, "lr": 1.0504122995410909e-05, "epoch": 14.544004400440045, "percentage": 72.72, "elapsed_time": "5:12:58", "remaining_time": "1:57:24", "throughput": 1485.83, "total_tokens": 27901088} {"current_steps": 132210, "total_steps": 181800, "loss": 0.0513, "lr": 1.0502167645744895e-05, "epoch": 14.544554455445544, "percentage": 72.72, "elapsed_time": "5:12:58", "remaining_time": "1:57:23", "throughput": 1485.84, "total_tokens": 27902144} {"current_steps": 132215, "total_steps": 181800, "loss": 0.007, "lr": 1.0500212429698455e-05, "epoch": 14.545104510451045, "percentage": 72.73, "elapsed_time": "5:12:59", "remaining_time": "1:57:22", "throughput": 1485.84, "total_tokens": 27903232} {"current_steps": 132220, "total_steps": 181800, "loss": 0.0052, "lr": 1.0498257347289592e-05, "epoch": 14.545654565456546, "percentage": 72.73, "elapsed_time": "5:13:00", "remaining_time": "1:57:22", "throughput": 1485.84, "total_tokens": 27904320} {"current_steps": 132225, "total_steps": 181800, "loss": 0.0793, "lr": 1.0496302398536334e-05, "epoch": 14.546204620462046, "percentage": 72.73, "elapsed_time": "5:13:00", "remaining_time": "1:57:21", "throughput": 1485.85, "total_tokens": 27905408} {"current_steps": 132230, "total_steps": 181800, "loss": 0.0829, "lr": 1.0494347583456703e-05, "epoch": 14.546754675467547, "percentage": 72.73, "elapsed_time": "5:13:01", "remaining_time": "1:57:20", "throughput": 1485.84, "total_tokens": 27906400} {"current_steps": 132235, "total_steps": 181800, "loss": 0.0049, "lr": 1.049239290206871e-05, "epoch": 14.547304730473048, "percentage": 72.74, "elapsed_time": "5:13:02", "remaining_time": "1:57:20", "throughput": 1485.85, "total_tokens": 27907456} {"current_steps": 132240, "total_steps": 181800, "loss": 0.0413, "lr": 1.0490438354390363e-05, "epoch": 14.547854785478547, "percentage": 72.74, "elapsed_time": "5:13:02", "remaining_time": "1:57:19", "throughput": 1485.85, "total_tokens": 27908480} {"current_steps": 132245, "total_steps": 181800, "loss": 0.0494, "lr": 1.0488483940439692e-05, "epoch": 14.548404840484048, "percentage": 72.74, "elapsed_time": "5:13:03", "remaining_time": "1:57:18", "throughput": 1485.85, "total_tokens": 27909664} {"current_steps": 132250, "total_steps": 181800, "loss": 0.0012, "lr": 1.048652966023468e-05, "epoch": 14.54895489548955, "percentage": 72.74, "elapsed_time": "5:13:04", "remaining_time": "1:57:17", "throughput": 1485.86, "total_tokens": 27910752} {"current_steps": 132255, "total_steps": 181800, "loss": 0.0497, "lr": 1.0484575513793382e-05, "epoch": 14.549504950495049, "percentage": 72.75, "elapsed_time": "5:13:04", "remaining_time": "1:57:17", "throughput": 1485.86, "total_tokens": 27911776} {"current_steps": 132260, "total_steps": 181800, "loss": 0.002, "lr": 1.0482621501133785e-05, "epoch": 14.55005500550055, "percentage": 72.75, "elapsed_time": "5:13:05", "remaining_time": "1:57:16", "throughput": 1485.86, "total_tokens": 27912800} {"current_steps": 132265, "total_steps": 181800, "loss": 0.0495, "lr": 1.048066762227389e-05, "epoch": 14.55060506050605, "percentage": 72.75, "elapsed_time": "5:13:06", "remaining_time": "1:57:15", "throughput": 1485.85, "total_tokens": 27913952} {"current_steps": 132270, "total_steps": 181800, "loss": 0.0086, "lr": 1.0478713877231724e-05, "epoch": 14.551155115511552, "percentage": 72.76, "elapsed_time": "5:13:07", "remaining_time": "1:57:15", "throughput": 1485.85, "total_tokens": 27915040} {"current_steps": 132275, "total_steps": 181800, "loss": 0.0268, "lr": 1.0476760266025276e-05, "epoch": 14.551705170517051, "percentage": 72.76, "elapsed_time": "5:13:07", "remaining_time": "1:57:14", "throughput": 1485.85, "total_tokens": 27916064} {"current_steps": 132280, "total_steps": 181800, "loss": 0.0791, "lr": 1.0474806788672558e-05, "epoch": 14.552255225522552, "percentage": 72.76, "elapsed_time": "5:13:08", "remaining_time": "1:57:13", "throughput": 1485.85, "total_tokens": 27917120} {"current_steps": 132285, "total_steps": 181800, "loss": 0.0098, "lr": 1.0472853445191585e-05, "epoch": 14.552805280528053, "percentage": 72.76, "elapsed_time": "5:13:09", "remaining_time": "1:57:12", "throughput": 1485.85, "total_tokens": 27918144} {"current_steps": 132290, "total_steps": 181800, "loss": 0.0174, "lr": 1.0470900235600342e-05, "epoch": 14.553355335533553, "percentage": 72.77, "elapsed_time": "5:13:09", "remaining_time": "1:57:12", "throughput": 1485.86, "total_tokens": 27919232} {"current_steps": 132295, "total_steps": 181800, "loss": 0.004, "lr": 1.046894715991685e-05, "epoch": 14.553905390539054, "percentage": 72.77, "elapsed_time": "5:13:10", "remaining_time": "1:57:11", "throughput": 1485.86, "total_tokens": 27920320} {"current_steps": 132300, "total_steps": 181800, "loss": 0.049, "lr": 1.046699421815909e-05, "epoch": 14.554455445544555, "percentage": 72.77, "elapsed_time": "5:13:11", "remaining_time": "1:57:10", "throughput": 1485.86, "total_tokens": 27921344} {"current_steps": 132305, "total_steps": 181800, "loss": 0.0021, "lr": 1.0465041410345072e-05, "epoch": 14.555005500550054, "percentage": 72.78, "elapsed_time": "5:13:12", "remaining_time": "1:57:10", "throughput": 1485.86, "total_tokens": 27922368} {"current_steps": 132310, "total_steps": 181800, "loss": 0.0037, "lr": 1.0463088736492798e-05, "epoch": 14.555555555555555, "percentage": 72.78, "elapsed_time": "5:13:12", "remaining_time": "1:57:09", "throughput": 1485.86, "total_tokens": 27923424} {"current_steps": 132315, "total_steps": 181800, "loss": 0.3168, "lr": 1.0461136196620256e-05, "epoch": 14.556105610561056, "percentage": 72.78, "elapsed_time": "5:13:13", "remaining_time": "1:57:08", "throughput": 1485.86, "total_tokens": 27924448} {"current_steps": 132320, "total_steps": 181800, "loss": 0.0016, "lr": 1.045918379074545e-05, "epoch": 14.556655665566556, "percentage": 72.78, "elapsed_time": "5:13:14", "remaining_time": "1:57:07", "throughput": 1485.86, "total_tokens": 27925504} {"current_steps": 132325, "total_steps": 181800, "loss": 0.0196, "lr": 1.0457231518886363e-05, "epoch": 14.557205720572057, "percentage": 72.79, "elapsed_time": "5:13:14", "remaining_time": "1:57:07", "throughput": 1485.86, "total_tokens": 27926560} {"current_steps": 132330, "total_steps": 181800, "loss": 0.0066, "lr": 1.0455279381061001e-05, "epoch": 14.557755775577558, "percentage": 72.79, "elapsed_time": "5:13:15", "remaining_time": "1:57:06", "throughput": 1485.87, "total_tokens": 27927616} {"current_steps": 132335, "total_steps": 181800, "loss": 0.0662, "lr": 1.0453327377287342e-05, "epoch": 14.558305830583059, "percentage": 72.79, "elapsed_time": "5:13:16", "remaining_time": "1:57:05", "throughput": 1485.87, "total_tokens": 27928736} {"current_steps": 132340, "total_steps": 181800, "loss": 0.0857, "lr": 1.0451375507583385e-05, "epoch": 14.558855885588558, "percentage": 72.79, "elapsed_time": "5:13:16", "remaining_time": "1:57:05", "throughput": 1485.88, "total_tokens": 27929888} {"current_steps": 132345, "total_steps": 181800, "loss": 0.0067, "lr": 1.0449423771967125e-05, "epoch": 14.55940594059406, "percentage": 72.8, "elapsed_time": "5:13:17", "remaining_time": "1:57:04", "throughput": 1485.88, "total_tokens": 27930976} {"current_steps": 132350, "total_steps": 181800, "loss": 0.0485, "lr": 1.044747217045654e-05, "epoch": 14.55995599559956, "percentage": 72.8, "elapsed_time": "5:13:18", "remaining_time": "1:57:03", "throughput": 1485.88, "total_tokens": 27932032} {"current_steps": 132355, "total_steps": 181800, "loss": 0.0042, "lr": 1.0445520703069628e-05, "epoch": 14.56050605060506, "percentage": 72.8, "elapsed_time": "5:13:18", "remaining_time": "1:57:02", "throughput": 1485.88, "total_tokens": 27933024} {"current_steps": 132360, "total_steps": 181800, "loss": 0.012, "lr": 1.0443569369824366e-05, "epoch": 14.561056105610561, "percentage": 72.81, "elapsed_time": "5:13:19", "remaining_time": "1:57:02", "throughput": 1485.88, "total_tokens": 27934080} {"current_steps": 132365, "total_steps": 181800, "loss": 0.0871, "lr": 1.0441618170738723e-05, "epoch": 14.561606160616062, "percentage": 72.81, "elapsed_time": "5:13:20", "remaining_time": "1:57:01", "throughput": 1485.88, "total_tokens": 27935168} {"current_steps": 132370, "total_steps": 181800, "loss": 0.0028, "lr": 1.043966710583072e-05, "epoch": 14.562156215621561, "percentage": 72.81, "elapsed_time": "5:13:21", "remaining_time": "1:57:00", "throughput": 1485.89, "total_tokens": 27936224} {"current_steps": 132375, "total_steps": 181800, "loss": 0.0025, "lr": 1.0437716175118306e-05, "epoch": 14.562706270627062, "percentage": 72.81, "elapsed_time": "5:13:21", "remaining_time": "1:57:00", "throughput": 1485.89, "total_tokens": 27937344} {"current_steps": 132380, "total_steps": 181800, "loss": 0.0957, "lr": 1.0435765378619486e-05, "epoch": 14.563256325632564, "percentage": 72.82, "elapsed_time": "5:13:22", "remaining_time": "1:56:59", "throughput": 1485.89, "total_tokens": 27938400} {"current_steps": 132385, "total_steps": 181800, "loss": 0.0142, "lr": 1.0433814716352228e-05, "epoch": 14.563806380638063, "percentage": 72.82, "elapsed_time": "5:13:23", "remaining_time": "1:56:58", "throughput": 1485.89, "total_tokens": 27939424} {"current_steps": 132390, "total_steps": 181800, "loss": 0.0942, "lr": 1.0431864188334497e-05, "epoch": 14.564356435643564, "percentage": 72.82, "elapsed_time": "5:13:23", "remaining_time": "1:56:57", "throughput": 1485.89, "total_tokens": 27940448} {"current_steps": 132395, "total_steps": 181800, "loss": 0.0097, "lr": 1.042991379458429e-05, "epoch": 14.564906490649065, "percentage": 72.82, "elapsed_time": "5:13:24", "remaining_time": "1:56:57", "throughput": 1485.9, "total_tokens": 27941536} {"current_steps": 132400, "total_steps": 181800, "loss": 0.0028, "lr": 1.042796353511957e-05, "epoch": 14.565456545654566, "percentage": 72.83, "elapsed_time": "5:13:25", "remaining_time": "1:56:56", "throughput": 1485.9, "total_tokens": 27942624} {"current_steps": 132405, "total_steps": 181800, "loss": 0.0735, "lr": 1.042601340995833e-05, "epoch": 14.566006600660065, "percentage": 72.83, "elapsed_time": "5:13:25", "remaining_time": "1:56:55", "throughput": 1485.9, "total_tokens": 27943680} {"current_steps": 132410, "total_steps": 181800, "loss": 0.0631, "lr": 1.0424063419118532e-05, "epoch": 14.566556655665567, "percentage": 72.83, "elapsed_time": "5:13:26", "remaining_time": "1:56:55", "throughput": 1485.9, "total_tokens": 27944672} {"current_steps": 132415, "total_steps": 181800, "loss": 0.0027, "lr": 1.0422113562618135e-05, "epoch": 14.567106710671068, "percentage": 72.84, "elapsed_time": "5:13:27", "remaining_time": "1:56:54", "throughput": 1485.9, "total_tokens": 27945792} {"current_steps": 132420, "total_steps": 181800, "loss": 0.0013, "lr": 1.0420163840475133e-05, "epoch": 14.567656765676567, "percentage": 72.84, "elapsed_time": "5:13:27", "remaining_time": "1:56:53", "throughput": 1485.9, "total_tokens": 27946816} {"current_steps": 132425, "total_steps": 181800, "loss": 0.0218, "lr": 1.0418214252707467e-05, "epoch": 14.568206820682068, "percentage": 72.84, "elapsed_time": "5:13:28", "remaining_time": "1:56:52", "throughput": 1485.9, "total_tokens": 27947808} {"current_steps": 132430, "total_steps": 181800, "loss": 0.0069, "lr": 1.0416264799333143e-05, "epoch": 14.56875687568757, "percentage": 72.84, "elapsed_time": "5:13:29", "remaining_time": "1:56:52", "throughput": 1485.9, "total_tokens": 27948832} {"current_steps": 132435, "total_steps": 181800, "loss": 0.0036, "lr": 1.0414315480370105e-05, "epoch": 14.569306930693068, "percentage": 72.85, "elapsed_time": "5:13:30", "remaining_time": "1:56:51", "throughput": 1485.9, "total_tokens": 27949888} {"current_steps": 132440, "total_steps": 181800, "loss": 0.0053, "lr": 1.0412366295836315e-05, "epoch": 14.56985698569857, "percentage": 72.85, "elapsed_time": "5:13:30", "remaining_time": "1:56:50", "throughput": 1485.91, "total_tokens": 27950944} {"current_steps": 132445, "total_steps": 181800, "loss": 0.0173, "lr": 1.0410417245749751e-05, "epoch": 14.57040704070407, "percentage": 72.85, "elapsed_time": "5:13:31", "remaining_time": "1:56:49", "throughput": 1485.91, "total_tokens": 27952032} {"current_steps": 132450, "total_steps": 181800, "loss": 0.0018, "lr": 1.0408468330128365e-05, "epoch": 14.570957095709572, "percentage": 72.85, "elapsed_time": "5:13:32", "remaining_time": "1:56:49", "throughput": 1485.91, "total_tokens": 27953120} {"current_steps": 132455, "total_steps": 181800, "loss": 0.0012, "lr": 1.0406519548990123e-05, "epoch": 14.571507150715071, "percentage": 72.86, "elapsed_time": "5:13:32", "remaining_time": "1:56:48", "throughput": 1485.92, "total_tokens": 27954272} {"current_steps": 132460, "total_steps": 181800, "loss": 0.0462, "lr": 1.0404570902352998e-05, "epoch": 14.572057205720572, "percentage": 72.86, "elapsed_time": "5:13:33", "remaining_time": "1:56:47", "throughput": 1485.92, "total_tokens": 27955264} {"current_steps": 132465, "total_steps": 181800, "loss": 0.0085, "lr": 1.040262239023493e-05, "epoch": 14.572607260726073, "percentage": 72.86, "elapsed_time": "5:13:34", "remaining_time": "1:56:47", "throughput": 1485.92, "total_tokens": 27956320} {"current_steps": 132470, "total_steps": 181800, "loss": 0.0014, "lr": 1.0400674012653897e-05, "epoch": 14.573157315731573, "percentage": 72.87, "elapsed_time": "5:13:34", "remaining_time": "1:56:46", "throughput": 1485.92, "total_tokens": 27957344} {"current_steps": 132475, "total_steps": 181800, "loss": 0.0902, "lr": 1.0398725769627845e-05, "epoch": 14.573707370737074, "percentage": 72.87, "elapsed_time": "5:13:35", "remaining_time": "1:56:45", "throughput": 1485.92, "total_tokens": 27958400} {"current_steps": 132480, "total_steps": 181800, "loss": 0.0236, "lr": 1.0396777661174722e-05, "epoch": 14.574257425742575, "percentage": 72.87, "elapsed_time": "5:13:36", "remaining_time": "1:56:44", "throughput": 1485.93, "total_tokens": 27959520} {"current_steps": 132485, "total_steps": 181800, "loss": 0.0076, "lr": 1.0394829687312491e-05, "epoch": 14.574807480748074, "percentage": 72.87, "elapsed_time": "5:13:36", "remaining_time": "1:56:44", "throughput": 1485.93, "total_tokens": 27960640} {"current_steps": 132490, "total_steps": 181800, "loss": 0.0041, "lr": 1.0392881848059107e-05, "epoch": 14.575357535753575, "percentage": 72.88, "elapsed_time": "5:13:37", "remaining_time": "1:56:43", "throughput": 1485.94, "total_tokens": 27961760} {"current_steps": 132495, "total_steps": 181800, "loss": 0.12, "lr": 1.0390934143432535e-05, "epoch": 14.575907590759076, "percentage": 72.88, "elapsed_time": "5:13:38", "remaining_time": "1:56:42", "throughput": 1485.94, "total_tokens": 27962816} {"current_steps": 132500, "total_steps": 181800, "loss": 0.117, "lr": 1.0388986573450707e-05, "epoch": 14.576457645764577, "percentage": 72.88, "elapsed_time": "5:13:38", "remaining_time": "1:56:42", "throughput": 1485.94, "total_tokens": 27963840} {"current_steps": 132505, "total_steps": 181800, "loss": 0.0011, "lr": 1.0387039138131574e-05, "epoch": 14.577007700770077, "percentage": 72.89, "elapsed_time": "5:13:39", "remaining_time": "1:56:41", "throughput": 1485.94, "total_tokens": 27964928} {"current_steps": 132510, "total_steps": 181800, "loss": 0.0042, "lr": 1.0385091837493085e-05, "epoch": 14.577557755775578, "percentage": 72.89, "elapsed_time": "5:13:40", "remaining_time": "1:56:40", "throughput": 1485.94, "total_tokens": 27965920} {"current_steps": 132515, "total_steps": 181800, "loss": 0.0028, "lr": 1.0383144671553197e-05, "epoch": 14.578107810781079, "percentage": 72.89, "elapsed_time": "5:13:41", "remaining_time": "1:56:39", "throughput": 1485.94, "total_tokens": 27966912} {"current_steps": 132520, "total_steps": 181800, "loss": 0.0044, "lr": 1.0381197640329857e-05, "epoch": 14.578657865786578, "percentage": 72.89, "elapsed_time": "5:13:41", "remaining_time": "1:56:39", "throughput": 1485.94, "total_tokens": 27967936} {"current_steps": 132525, "total_steps": 181800, "loss": 0.009, "lr": 1.0379250743841e-05, "epoch": 14.57920792079208, "percentage": 72.9, "elapsed_time": "5:13:42", "remaining_time": "1:56:38", "throughput": 1485.94, "total_tokens": 27968992} {"current_steps": 132530, "total_steps": 181800, "loss": 0.0138, "lr": 1.037730398210457e-05, "epoch": 14.57975797579758, "percentage": 72.9, "elapsed_time": "5:13:43", "remaining_time": "1:56:37", "throughput": 1485.94, "total_tokens": 27970048} {"current_steps": 132535, "total_steps": 181800, "loss": 0.0044, "lr": 1.0375357355138517e-05, "epoch": 14.58030803080308, "percentage": 72.9, "elapsed_time": "5:13:43", "remaining_time": "1:56:37", "throughput": 1485.94, "total_tokens": 27971104} {"current_steps": 132540, "total_steps": 181800, "loss": 0.0016, "lr": 1.0373410862960772e-05, "epoch": 14.58085808580858, "percentage": 72.9, "elapsed_time": "5:13:44", "remaining_time": "1:56:36", "throughput": 1485.94, "total_tokens": 27972160} {"current_steps": 132545, "total_steps": 181800, "loss": 0.0349, "lr": 1.037146450558928e-05, "epoch": 14.581408140814082, "percentage": 72.91, "elapsed_time": "5:13:45", "remaining_time": "1:56:35", "throughput": 1485.95, "total_tokens": 27973280} {"current_steps": 132550, "total_steps": 181800, "loss": 0.043, "lr": 1.0369518283041987e-05, "epoch": 14.581958195819581, "percentage": 72.91, "elapsed_time": "5:13:45", "remaining_time": "1:56:34", "throughput": 1485.95, "total_tokens": 27974304} {"current_steps": 132555, "total_steps": 181800, "loss": 0.1127, "lr": 1.0367572195336816e-05, "epoch": 14.582508250825082, "percentage": 72.91, "elapsed_time": "5:13:46", "remaining_time": "1:56:34", "throughput": 1485.95, "total_tokens": 27975328} {"current_steps": 132560, "total_steps": 181800, "loss": 0.029, "lr": 1.0365626242491722e-05, "epoch": 14.583058305830583, "percentage": 72.92, "elapsed_time": "5:13:47", "remaining_time": "1:56:33", "throughput": 1485.95, "total_tokens": 27976352} {"current_steps": 132565, "total_steps": 181800, "loss": 0.0011, "lr": 1.0363680424524616e-05, "epoch": 14.583608360836084, "percentage": 72.92, "elapsed_time": "5:13:47", "remaining_time": "1:56:32", "throughput": 1485.95, "total_tokens": 27977376} {"current_steps": 132570, "total_steps": 181800, "loss": 0.0081, "lr": 1.0361734741453447e-05, "epoch": 14.584158415841584, "percentage": 72.92, "elapsed_time": "5:13:48", "remaining_time": "1:56:32", "throughput": 1485.95, "total_tokens": 27978464} {"current_steps": 132575, "total_steps": 181800, "loss": 0.0351, "lr": 1.0359789193296151e-05, "epoch": 14.584708470847085, "percentage": 72.92, "elapsed_time": "5:13:49", "remaining_time": "1:56:31", "throughput": 1485.95, "total_tokens": 27979488} {"current_steps": 132580, "total_steps": 181800, "loss": 0.0742, "lr": 1.0357843780070648e-05, "epoch": 14.585258525852586, "percentage": 72.93, "elapsed_time": "5:13:50", "remaining_time": "1:56:30", "throughput": 1485.95, "total_tokens": 27980512} {"current_steps": 132585, "total_steps": 181800, "loss": 0.0082, "lr": 1.0355898501794878e-05, "epoch": 14.585808580858085, "percentage": 72.93, "elapsed_time": "5:13:50", "remaining_time": "1:56:29", "throughput": 1485.95, "total_tokens": 27981568} {"current_steps": 132590, "total_steps": 181800, "loss": 0.0916, "lr": 1.0353953358486757e-05, "epoch": 14.586358635863586, "percentage": 72.93, "elapsed_time": "5:13:51", "remaining_time": "1:56:29", "throughput": 1485.96, "total_tokens": 27982688} {"current_steps": 132595, "total_steps": 181800, "loss": 0.0016, "lr": 1.035200835016423e-05, "epoch": 14.586908690869087, "percentage": 72.93, "elapsed_time": "5:13:52", "remaining_time": "1:56:28", "throughput": 1485.96, "total_tokens": 27983776} {"current_steps": 132600, "total_steps": 181800, "loss": 0.0032, "lr": 1.0350063476845204e-05, "epoch": 14.587458745874587, "percentage": 72.94, "elapsed_time": "5:13:52", "remaining_time": "1:56:27", "throughput": 1485.96, "total_tokens": 27984832} {"current_steps": 132605, "total_steps": 181800, "loss": 0.004, "lr": 1.0348118738547611e-05, "epoch": 14.588008800880088, "percentage": 72.94, "elapsed_time": "5:13:53", "remaining_time": "1:56:27", "throughput": 1485.96, "total_tokens": 27985888} {"current_steps": 132610, "total_steps": 181800, "loss": 0.0181, "lr": 1.0346174135289388e-05, "epoch": 14.588558855885589, "percentage": 72.94, "elapsed_time": "5:13:54", "remaining_time": "1:56:26", "throughput": 1485.97, "total_tokens": 27987040} {"current_steps": 132615, "total_steps": 181800, "loss": 0.0326, "lr": 1.0344229667088437e-05, "epoch": 14.589108910891088, "percentage": 72.95, "elapsed_time": "5:13:54", "remaining_time": "1:56:25", "throughput": 1485.97, "total_tokens": 27988128} {"current_steps": 132620, "total_steps": 181800, "loss": 0.0021, "lr": 1.0342285333962697e-05, "epoch": 14.58965896589659, "percentage": 72.95, "elapsed_time": "5:13:55", "remaining_time": "1:56:24", "throughput": 1485.98, "total_tokens": 27989184} {"current_steps": 132625, "total_steps": 181800, "loss": 0.0333, "lr": 1.034034113593007e-05, "epoch": 14.59020902090209, "percentage": 72.95, "elapsed_time": "5:13:56", "remaining_time": "1:56:24", "throughput": 1485.98, "total_tokens": 27990240} {"current_steps": 132630, "total_steps": 181800, "loss": 0.0128, "lr": 1.0338397073008488e-05, "epoch": 14.590759075907592, "percentage": 72.95, "elapsed_time": "5:13:56", "remaining_time": "1:56:23", "throughput": 1485.98, "total_tokens": 27991264} {"current_steps": 132635, "total_steps": 181800, "loss": 0.0028, "lr": 1.0336453145215869e-05, "epoch": 14.591309130913091, "percentage": 72.96, "elapsed_time": "5:13:57", "remaining_time": "1:56:22", "throughput": 1485.98, "total_tokens": 27992352} {"current_steps": 132640, "total_steps": 181800, "loss": 0.0158, "lr": 1.033450935257013e-05, "epoch": 14.591859185918592, "percentage": 72.96, "elapsed_time": "5:13:58", "remaining_time": "1:56:21", "throughput": 1485.98, "total_tokens": 27993440} {"current_steps": 132645, "total_steps": 181800, "loss": 0.0276, "lr": 1.033256569508917e-05, "epoch": 14.592409240924093, "percentage": 72.96, "elapsed_time": "5:13:58", "remaining_time": "1:56:21", "throughput": 1485.99, "total_tokens": 27994496} {"current_steps": 132650, "total_steps": 181800, "loss": 0.0383, "lr": 1.033062217279092e-05, "epoch": 14.592959295929592, "percentage": 72.96, "elapsed_time": "5:13:59", "remaining_time": "1:56:20", "throughput": 1485.99, "total_tokens": 27995584} {"current_steps": 132655, "total_steps": 181800, "loss": 0.0027, "lr": 1.0328678785693279e-05, "epoch": 14.593509350935093, "percentage": 72.97, "elapsed_time": "5:14:00", "remaining_time": "1:56:19", "throughput": 1485.99, "total_tokens": 27996576} {"current_steps": 132660, "total_steps": 181800, "loss": 0.0022, "lr": 1.0326735533814166e-05, "epoch": 14.594059405940595, "percentage": 72.97, "elapsed_time": "5:14:01", "remaining_time": "1:56:19", "throughput": 1485.99, "total_tokens": 27997696} {"current_steps": 132665, "total_steps": 181800, "loss": 0.0025, "lr": 1.0324792417171502e-05, "epoch": 14.594609460946094, "percentage": 72.97, "elapsed_time": "5:14:01", "remaining_time": "1:56:18", "throughput": 1485.99, "total_tokens": 27998720} {"current_steps": 132670, "total_steps": 181800, "loss": 0.0076, "lr": 1.0322849435783174e-05, "epoch": 14.595159515951595, "percentage": 72.98, "elapsed_time": "5:14:02", "remaining_time": "1:56:17", "throughput": 1485.99, "total_tokens": 27999776} {"current_steps": 132675, "total_steps": 181800, "loss": 0.0914, "lr": 1.0320906589667109e-05, "epoch": 14.595709570957096, "percentage": 72.98, "elapsed_time": "5:14:03", "remaining_time": "1:56:16", "throughput": 1486.0, "total_tokens": 28000832} {"current_steps": 132680, "total_steps": 181800, "loss": 0.0162, "lr": 1.0318963878841192e-05, "epoch": 14.596259625962595, "percentage": 72.98, "elapsed_time": "5:14:03", "remaining_time": "1:56:16", "throughput": 1486.0, "total_tokens": 28001888} {"current_steps": 132685, "total_steps": 181800, "loss": 0.0588, "lr": 1.0317021303323346e-05, "epoch": 14.596809680968097, "percentage": 72.98, "elapsed_time": "5:14:04", "remaining_time": "1:56:15", "throughput": 1486.0, "total_tokens": 28002944} {"current_steps": 132690, "total_steps": 181800, "loss": 0.0017, "lr": 1.0315078863131475e-05, "epoch": 14.597359735973598, "percentage": 72.99, "elapsed_time": "5:14:05", "remaining_time": "1:56:14", "throughput": 1486.0, "total_tokens": 28004000} {"current_steps": 132695, "total_steps": 181800, "loss": 0.0038, "lr": 1.0313136558283466e-05, "epoch": 14.597909790979099, "percentage": 72.99, "elapsed_time": "5:14:05", "remaining_time": "1:56:14", "throughput": 1486.0, "total_tokens": 28005088} {"current_steps": 132700, "total_steps": 181800, "loss": 0.0283, "lr": 1.0311194388797241e-05, "epoch": 14.598459845984598, "percentage": 72.99, "elapsed_time": "5:14:06", "remaining_time": "1:56:13", "throughput": 1486.01, "total_tokens": 28006176} {"current_steps": 132705, "total_steps": 181800, "loss": 0.0016, "lr": 1.0309252354690676e-05, "epoch": 14.599009900990099, "percentage": 73.0, "elapsed_time": "5:14:07", "remaining_time": "1:56:12", "throughput": 1486.01, "total_tokens": 28007328} {"current_steps": 132710, "total_steps": 181800, "loss": 0.0716, "lr": 1.0307310455981694e-05, "epoch": 14.5995599559956, "percentage": 73.0, "elapsed_time": "5:14:07", "remaining_time": "1:56:11", "throughput": 1486.02, "total_tokens": 28008448} {"current_steps": 132715, "total_steps": 181800, "loss": 0.0072, "lr": 1.0305368692688174e-05, "epoch": 14.6001100110011, "percentage": 73.0, "elapsed_time": "5:14:08", "remaining_time": "1:56:11", "throughput": 1486.02, "total_tokens": 28009472} {"current_steps": 132720, "total_steps": 181800, "loss": 0.0576, "lr": 1.030342706482802e-05, "epoch": 14.6006600660066, "percentage": 73.0, "elapsed_time": "5:14:09", "remaining_time": "1:56:10", "throughput": 1486.02, "total_tokens": 28010464} {"current_steps": 132725, "total_steps": 181800, "loss": 0.0014, "lr": 1.0301485572419132e-05, "epoch": 14.601210121012102, "percentage": 73.01, "elapsed_time": "5:14:10", "remaining_time": "1:56:09", "throughput": 1486.02, "total_tokens": 28011488} {"current_steps": 132730, "total_steps": 181800, "loss": 0.006, "lr": 1.0299544215479392e-05, "epoch": 14.601760176017601, "percentage": 73.01, "elapsed_time": "5:14:10", "remaining_time": "1:56:09", "throughput": 1486.02, "total_tokens": 28012576} {"current_steps": 132735, "total_steps": 181800, "loss": 0.002, "lr": 1.0297602994026706e-05, "epoch": 14.602310231023102, "percentage": 73.01, "elapsed_time": "5:14:11", "remaining_time": "1:56:08", "throughput": 1486.02, "total_tokens": 28013664} {"current_steps": 132740, "total_steps": 181800, "loss": 0.0018, "lr": 1.0295661908078953e-05, "epoch": 14.602860286028603, "percentage": 73.01, "elapsed_time": "5:14:12", "remaining_time": "1:56:07", "throughput": 1486.02, "total_tokens": 28014720} {"current_steps": 132745, "total_steps": 181800, "loss": 0.0806, "lr": 1.0293720957654025e-05, "epoch": 14.603410341034103, "percentage": 73.02, "elapsed_time": "5:14:12", "remaining_time": "1:56:06", "throughput": 1486.02, "total_tokens": 28015712} {"current_steps": 132750, "total_steps": 181800, "loss": 0.0281, "lr": 1.0291780142769825e-05, "epoch": 14.603960396039604, "percentage": 73.02, "elapsed_time": "5:14:13", "remaining_time": "1:56:06", "throughput": 1486.02, "total_tokens": 28016800} {"current_steps": 132755, "total_steps": 181800, "loss": 0.0159, "lr": 1.0289839463444217e-05, "epoch": 14.604510451045105, "percentage": 73.02, "elapsed_time": "5:14:14", "remaining_time": "1:56:05", "throughput": 1486.03, "total_tokens": 28017856} {"current_steps": 132760, "total_steps": 181800, "loss": 0.0254, "lr": 1.0287898919695113e-05, "epoch": 14.605060506050606, "percentage": 73.03, "elapsed_time": "5:14:14", "remaining_time": "1:56:04", "throughput": 1486.03, "total_tokens": 28018976} {"current_steps": 132765, "total_steps": 181800, "loss": 0.0735, "lr": 1.0285958511540383e-05, "epoch": 14.605610561056105, "percentage": 73.03, "elapsed_time": "5:14:15", "remaining_time": "1:56:04", "throughput": 1486.03, "total_tokens": 28020064} {"current_steps": 132770, "total_steps": 181800, "loss": 0.0127, "lr": 1.0284018238997906e-05, "epoch": 14.606160616061606, "percentage": 73.03, "elapsed_time": "5:14:16", "remaining_time": "1:56:03", "throughput": 1486.03, "total_tokens": 28021056} {"current_steps": 132775, "total_steps": 181800, "loss": 0.1031, "lr": 1.028207810208557e-05, "epoch": 14.606710671067107, "percentage": 73.03, "elapsed_time": "5:14:16", "remaining_time": "1:56:02", "throughput": 1486.03, "total_tokens": 28022112} {"current_steps": 132780, "total_steps": 181800, "loss": 0.094, "lr": 1.028013810082126e-05, "epoch": 14.607260726072607, "percentage": 73.04, "elapsed_time": "5:14:17", "remaining_time": "1:56:01", "throughput": 1486.03, "total_tokens": 28023136} {"current_steps": 132785, "total_steps": 181800, "loss": 0.0166, "lr": 1.0278198235222861e-05, "epoch": 14.607810781078108, "percentage": 73.04, "elapsed_time": "5:14:18", "remaining_time": "1:56:01", "throughput": 1486.03, "total_tokens": 28024128} {"current_steps": 132790, "total_steps": 181800, "loss": 0.0606, "lr": 1.0276258505308245e-05, "epoch": 14.608360836083609, "percentage": 73.04, "elapsed_time": "5:14:19", "remaining_time": "1:56:00", "throughput": 1486.03, "total_tokens": 28025184} {"current_steps": 132795, "total_steps": 181800, "loss": 0.0921, "lr": 1.0274318911095279e-05, "epoch": 14.608910891089108, "percentage": 73.04, "elapsed_time": "5:14:19", "remaining_time": "1:55:59", "throughput": 1486.04, "total_tokens": 28026272} {"current_steps": 132800, "total_steps": 181800, "loss": 0.002, "lr": 1.027237945260185e-05, "epoch": 14.60946094609461, "percentage": 73.05, "elapsed_time": "5:14:20", "remaining_time": "1:55:59", "throughput": 1486.04, "total_tokens": 28027328} {"current_steps": 132805, "total_steps": 181800, "loss": 0.0017, "lr": 1.0270440129845835e-05, "epoch": 14.61001100110011, "percentage": 73.05, "elapsed_time": "5:14:21", "remaining_time": "1:55:58", "throughput": 1486.04, "total_tokens": 28028352} {"current_steps": 132810, "total_steps": 181800, "loss": 0.0127, "lr": 1.0268500942845111e-05, "epoch": 14.61056105610561, "percentage": 73.05, "elapsed_time": "5:14:21", "remaining_time": "1:55:57", "throughput": 1486.04, "total_tokens": 28029408} {"current_steps": 132815, "total_steps": 181800, "loss": 0.0372, "lr": 1.0266561891617545e-05, "epoch": 14.61111111111111, "percentage": 73.06, "elapsed_time": "5:14:22", "remaining_time": "1:55:56", "throughput": 1486.04, "total_tokens": 28030400} {"current_steps": 132820, "total_steps": 181800, "loss": 0.0021, "lr": 1.0264622976181001e-05, "epoch": 14.611661166116612, "percentage": 73.06, "elapsed_time": "5:14:23", "remaining_time": "1:55:56", "throughput": 1486.04, "total_tokens": 28031456} {"current_steps": 132825, "total_steps": 181800, "loss": 0.0062, "lr": 1.0262684196553366e-05, "epoch": 14.612211221122113, "percentage": 73.06, "elapsed_time": "5:14:23", "remaining_time": "1:55:55", "throughput": 1486.04, "total_tokens": 28032512} {"current_steps": 132830, "total_steps": 181800, "loss": 0.0923, "lr": 1.0260745552752488e-05, "epoch": 14.612761276127612, "percentage": 73.06, "elapsed_time": "5:14:24", "remaining_time": "1:55:54", "throughput": 1486.04, "total_tokens": 28033504} {"current_steps": 132835, "total_steps": 181800, "loss": 0.125, "lr": 1.0258807044796249e-05, "epoch": 14.613311331133113, "percentage": 73.07, "elapsed_time": "5:14:25", "remaining_time": "1:55:54", "throughput": 1486.04, "total_tokens": 28034528} {"current_steps": 132840, "total_steps": 181800, "loss": 0.0585, "lr": 1.0256868672702515e-05, "epoch": 14.613861386138614, "percentage": 73.07, "elapsed_time": "5:14:25", "remaining_time": "1:55:53", "throughput": 1486.04, "total_tokens": 28035616} {"current_steps": 132845, "total_steps": 181800, "loss": 0.004, "lr": 1.0254930436489147e-05, "epoch": 14.614411441144114, "percentage": 73.07, "elapsed_time": "5:14:26", "remaining_time": "1:55:52", "throughput": 1486.04, "total_tokens": 28036672} {"current_steps": 132850, "total_steps": 181800, "loss": 0.0028, "lr": 1.0252992336174014e-05, "epoch": 14.614961496149615, "percentage": 73.07, "elapsed_time": "5:14:27", "remaining_time": "1:55:51", "throughput": 1486.04, "total_tokens": 28037728} {"current_steps": 132855, "total_steps": 181800, "loss": 0.0028, "lr": 1.0251054371774965e-05, "epoch": 14.615511551155116, "percentage": 73.08, "elapsed_time": "5:14:28", "remaining_time": "1:55:51", "throughput": 1486.05, "total_tokens": 28038784} {"current_steps": 132860, "total_steps": 181800, "loss": 0.0151, "lr": 1.024911654330987e-05, "epoch": 14.616061606160617, "percentage": 73.08, "elapsed_time": "5:14:28", "remaining_time": "1:55:50", "throughput": 1486.05, "total_tokens": 28039840} {"current_steps": 132865, "total_steps": 181800, "loss": 0.0045, "lr": 1.0247178850796602e-05, "epoch": 14.616611661166116, "percentage": 73.08, "elapsed_time": "5:14:29", "remaining_time": "1:55:49", "throughput": 1486.05, "total_tokens": 28040896} {"current_steps": 132870, "total_steps": 181800, "loss": 0.1172, "lr": 1.0245241294252993e-05, "epoch": 14.617161716171617, "percentage": 73.09, "elapsed_time": "5:14:30", "remaining_time": "1:55:49", "throughput": 1486.05, "total_tokens": 28041888} {"current_steps": 132875, "total_steps": 181800, "loss": 0.0028, "lr": 1.024330387369693e-05, "epoch": 14.617711771177119, "percentage": 73.09, "elapsed_time": "5:14:30", "remaining_time": "1:55:48", "throughput": 1486.05, "total_tokens": 28042912} {"current_steps": 132880, "total_steps": 181800, "loss": 0.0108, "lr": 1.024136658914625e-05, "epoch": 14.618261826182618, "percentage": 73.09, "elapsed_time": "5:14:31", "remaining_time": "1:55:47", "throughput": 1486.05, "total_tokens": 28044000} {"current_steps": 132885, "total_steps": 181800, "loss": 0.1242, "lr": 1.0239429440618806e-05, "epoch": 14.618811881188119, "percentage": 73.09, "elapsed_time": "5:14:32", "remaining_time": "1:55:46", "throughput": 1486.05, "total_tokens": 28045088} {"current_steps": 132890, "total_steps": 181800, "loss": 0.1278, "lr": 1.0237492428132459e-05, "epoch": 14.61936193619362, "percentage": 73.1, "elapsed_time": "5:14:32", "remaining_time": "1:55:46", "throughput": 1486.05, "total_tokens": 28046080} {"current_steps": 132895, "total_steps": 181800, "loss": 0.0062, "lr": 1.0235555551705057e-05, "epoch": 14.61991199119912, "percentage": 73.1, "elapsed_time": "5:14:33", "remaining_time": "1:55:45", "throughput": 1486.05, "total_tokens": 28047136} {"current_steps": 132900, "total_steps": 181800, "loss": 0.1041, "lr": 1.0233618811354465e-05, "epoch": 14.62046204620462, "percentage": 73.1, "elapsed_time": "5:14:34", "remaining_time": "1:55:44", "throughput": 1486.06, "total_tokens": 28048224} {"current_steps": 132905, "total_steps": 181800, "loss": 0.0015, "lr": 1.0231682207098525e-05, "epoch": 14.621012101210122, "percentage": 73.11, "elapsed_time": "5:14:34", "remaining_time": "1:55:43", "throughput": 1486.06, "total_tokens": 28049280} {"current_steps": 132910, "total_steps": 181800, "loss": 0.0021, "lr": 1.0229745738955071e-05, "epoch": 14.62156215621562, "percentage": 73.11, "elapsed_time": "5:14:35", "remaining_time": "1:55:43", "throughput": 1486.06, "total_tokens": 28050336} {"current_steps": 132915, "total_steps": 181800, "loss": 0.0064, "lr": 1.0227809406941965e-05, "epoch": 14.622112211221122, "percentage": 73.11, "elapsed_time": "5:14:36", "remaining_time": "1:55:42", "throughput": 1486.06, "total_tokens": 28051424} {"current_steps": 132920, "total_steps": 181800, "loss": 0.0781, "lr": 1.0225873211077052e-05, "epoch": 14.622662266226623, "percentage": 73.11, "elapsed_time": "5:14:37", "remaining_time": "1:55:41", "throughput": 1486.06, "total_tokens": 28052480} {"current_steps": 132925, "total_steps": 181800, "loss": 0.0649, "lr": 1.0223937151378184e-05, "epoch": 14.623212321232124, "percentage": 73.12, "elapsed_time": "5:14:37", "remaining_time": "1:55:41", "throughput": 1486.06, "total_tokens": 28053504} {"current_steps": 132930, "total_steps": 181800, "loss": 0.0165, "lr": 1.0222001227863199e-05, "epoch": 14.623762376237623, "percentage": 73.12, "elapsed_time": "5:14:38", "remaining_time": "1:55:40", "throughput": 1486.06, "total_tokens": 28054528} {"current_steps": 132935, "total_steps": 181800, "loss": 0.0061, "lr": 1.0220065440549925e-05, "epoch": 14.624312431243125, "percentage": 73.12, "elapsed_time": "5:14:39", "remaining_time": "1:55:39", "throughput": 1486.07, "total_tokens": 28055584} {"current_steps": 132940, "total_steps": 181800, "loss": 0.071, "lr": 1.0218129789456227e-05, "epoch": 14.624862486248626, "percentage": 73.12, "elapsed_time": "5:14:39", "remaining_time": "1:55:38", "throughput": 1486.07, "total_tokens": 28056704} {"current_steps": 132945, "total_steps": 181800, "loss": 0.1087, "lr": 1.0216194274599924e-05, "epoch": 14.625412541254125, "percentage": 73.13, "elapsed_time": "5:14:40", "remaining_time": "1:55:38", "throughput": 1486.07, "total_tokens": 28057792} {"current_steps": 132950, "total_steps": 181800, "loss": 0.0072, "lr": 1.0214258895998865e-05, "epoch": 14.625962596259626, "percentage": 73.13, "elapsed_time": "5:14:41", "remaining_time": "1:55:37", "throughput": 1486.07, "total_tokens": 28058848} {"current_steps": 132955, "total_steps": 181800, "loss": 0.0102, "lr": 1.0212323653670897e-05, "epoch": 14.626512651265127, "percentage": 73.13, "elapsed_time": "5:14:41", "remaining_time": "1:55:36", "throughput": 1486.08, "total_tokens": 28059904} {"current_steps": 132960, "total_steps": 181800, "loss": 0.0019, "lr": 1.0210388547633836e-05, "epoch": 14.627062706270626, "percentage": 73.14, "elapsed_time": "5:14:42", "remaining_time": "1:55:36", "throughput": 1486.08, "total_tokens": 28060928} {"current_steps": 132965, "total_steps": 181800, "loss": 0.0209, "lr": 1.0208453577905535e-05, "epoch": 14.627612761276128, "percentage": 73.14, "elapsed_time": "5:14:43", "remaining_time": "1:55:35", "throughput": 1486.08, "total_tokens": 28062016} {"current_steps": 132970, "total_steps": 181800, "loss": 0.0037, "lr": 1.0206518744503812e-05, "epoch": 14.628162816281629, "percentage": 73.14, "elapsed_time": "5:14:43", "remaining_time": "1:55:34", "throughput": 1486.08, "total_tokens": 28063008} {"current_steps": 132975, "total_steps": 181800, "loss": 0.0366, "lr": 1.0204584047446505e-05, "epoch": 14.628712871287128, "percentage": 73.14, "elapsed_time": "5:14:44", "remaining_time": "1:55:33", "throughput": 1486.08, "total_tokens": 28064032} {"current_steps": 132980, "total_steps": 181800, "loss": 0.1001, "lr": 1.020264948675146e-05, "epoch": 14.629262926292629, "percentage": 73.15, "elapsed_time": "5:14:45", "remaining_time": "1:55:33", "throughput": 1486.08, "total_tokens": 28065088} {"current_steps": 132985, "total_steps": 181800, "loss": 0.0026, "lr": 1.0200715062436484e-05, "epoch": 14.62981298129813, "percentage": 73.15, "elapsed_time": "5:14:46", "remaining_time": "1:55:32", "throughput": 1486.08, "total_tokens": 28066176} {"current_steps": 132990, "total_steps": 181800, "loss": 0.0314, "lr": 1.0198780774519422e-05, "epoch": 14.630363036303631, "percentage": 73.15, "elapsed_time": "5:14:46", "remaining_time": "1:55:31", "throughput": 1486.09, "total_tokens": 28067264} {"current_steps": 132995, "total_steps": 181800, "loss": 0.0251, "lr": 1.0196846623018089e-05, "epoch": 14.63091309130913, "percentage": 73.15, "elapsed_time": "5:14:47", "remaining_time": "1:55:31", "throughput": 1486.09, "total_tokens": 28068352} {"current_steps": 133000, "total_steps": 181800, "loss": 0.056, "lr": 1.0194912607950324e-05, "epoch": 14.631463146314632, "percentage": 73.16, "elapsed_time": "5:14:48", "remaining_time": "1:55:30", "throughput": 1486.1, "total_tokens": 28069504} {"current_steps": 133005, "total_steps": 181800, "loss": 0.0067, "lr": 1.019297872933394e-05, "epoch": 14.632013201320133, "percentage": 73.16, "elapsed_time": "5:14:48", "remaining_time": "1:55:29", "throughput": 1486.1, "total_tokens": 28070528} {"current_steps": 133010, "total_steps": 181800, "loss": 0.0014, "lr": 1.0191044987186762e-05, "epoch": 14.632563256325632, "percentage": 73.16, "elapsed_time": "5:14:49", "remaining_time": "1:55:28", "throughput": 1486.1, "total_tokens": 28071552} {"current_steps": 133015, "total_steps": 181800, "loss": 0.0422, "lr": 1.0189111381526628e-05, "epoch": 14.633113311331133, "percentage": 73.17, "elapsed_time": "5:14:50", "remaining_time": "1:55:28", "throughput": 1486.1, "total_tokens": 28072640} {"current_steps": 133020, "total_steps": 181800, "loss": 0.0034, "lr": 1.0187177912371348e-05, "epoch": 14.633663366336634, "percentage": 73.17, "elapsed_time": "5:14:50", "remaining_time": "1:55:27", "throughput": 1486.1, "total_tokens": 28073728} {"current_steps": 133025, "total_steps": 181800, "loss": 0.0115, "lr": 1.0185244579738732e-05, "epoch": 14.634213421342134, "percentage": 73.17, "elapsed_time": "5:14:51", "remaining_time": "1:55:26", "throughput": 1486.11, "total_tokens": 28074848} {"current_steps": 133030, "total_steps": 181800, "loss": 0.0011, "lr": 1.0183311383646616e-05, "epoch": 14.634763476347635, "percentage": 73.17, "elapsed_time": "5:14:52", "remaining_time": "1:55:26", "throughput": 1486.11, "total_tokens": 28075968} {"current_steps": 133035, "total_steps": 181800, "loss": 0.05, "lr": 1.0181378324112789e-05, "epoch": 14.635313531353136, "percentage": 73.18, "elapsed_time": "5:14:52", "remaining_time": "1:55:25", "throughput": 1486.11, "total_tokens": 28077024} {"current_steps": 133040, "total_steps": 181800, "loss": 0.0777, "lr": 1.0179445401155108e-05, "epoch": 14.635863586358635, "percentage": 73.18, "elapsed_time": "5:14:53", "remaining_time": "1:55:24", "throughput": 1486.12, "total_tokens": 28078112} {"current_steps": 133045, "total_steps": 181800, "loss": 0.0026, "lr": 1.0177512614791368e-05, "epoch": 14.636413641364136, "percentage": 73.18, "elapsed_time": "5:14:54", "remaining_time": "1:55:23", "throughput": 1486.12, "total_tokens": 28079168} {"current_steps": 133050, "total_steps": 181800, "loss": 0.0586, "lr": 1.0175579965039369e-05, "epoch": 14.636963696369637, "percentage": 73.18, "elapsed_time": "5:14:54", "remaining_time": "1:55:23", "throughput": 1486.12, "total_tokens": 28080256} {"current_steps": 133055, "total_steps": 181800, "loss": 0.0806, "lr": 1.0173647451916948e-05, "epoch": 14.637513751375138, "percentage": 73.19, "elapsed_time": "5:14:55", "remaining_time": "1:55:22", "throughput": 1486.13, "total_tokens": 28081344} {"current_steps": 133060, "total_steps": 181800, "loss": 0.0817, "lr": 1.0171715075441895e-05, "epoch": 14.638063806380638, "percentage": 73.19, "elapsed_time": "5:14:56", "remaining_time": "1:55:21", "throughput": 1486.13, "total_tokens": 28082400} {"current_steps": 133065, "total_steps": 181800, "loss": 0.0009, "lr": 1.016978283563203e-05, "epoch": 14.638613861386139, "percentage": 73.19, "elapsed_time": "5:14:57", "remaining_time": "1:55:21", "throughput": 1486.13, "total_tokens": 28083520} {"current_steps": 133070, "total_steps": 181800, "loss": 0.0006, "lr": 1.0167850732505166e-05, "epoch": 14.63916391639164, "percentage": 73.2, "elapsed_time": "5:14:57", "remaining_time": "1:55:20", "throughput": 1486.13, "total_tokens": 28084544} {"current_steps": 133075, "total_steps": 181800, "loss": 0.0157, "lr": 1.01659187660791e-05, "epoch": 14.63971397139714, "percentage": 73.2, "elapsed_time": "5:14:58", "remaining_time": "1:55:19", "throughput": 1486.13, "total_tokens": 28085600} {"current_steps": 133080, "total_steps": 181800, "loss": 0.0071, "lr": 1.0163986936371648e-05, "epoch": 14.64026402640264, "percentage": 73.2, "elapsed_time": "5:14:59", "remaining_time": "1:55:18", "throughput": 1486.14, "total_tokens": 28086656} {"current_steps": 133085, "total_steps": 181800, "loss": 0.004, "lr": 1.01620552434006e-05, "epoch": 14.640814081408141, "percentage": 73.2, "elapsed_time": "5:14:59", "remaining_time": "1:55:18", "throughput": 1486.14, "total_tokens": 28087680} {"current_steps": 133090, "total_steps": 181800, "loss": 0.002, "lr": 1.016012368718377e-05, "epoch": 14.64136413641364, "percentage": 73.21, "elapsed_time": "5:15:00", "remaining_time": "1:55:17", "throughput": 1486.14, "total_tokens": 28088768} {"current_steps": 133095, "total_steps": 181800, "loss": 0.0535, "lr": 1.015819226773897e-05, "epoch": 14.641914191419142, "percentage": 73.21, "elapsed_time": "5:15:01", "remaining_time": "1:55:16", "throughput": 1486.14, "total_tokens": 28089856} {"current_steps": 133100, "total_steps": 181800, "loss": 0.0037, "lr": 1.015626098508398e-05, "epoch": 14.642464246424643, "percentage": 73.21, "elapsed_time": "5:15:01", "remaining_time": "1:55:16", "throughput": 1486.14, "total_tokens": 28090912} {"current_steps": 133105, "total_steps": 181800, "loss": 0.0015, "lr": 1.0154329839236617e-05, "epoch": 14.643014301430142, "percentage": 73.22, "elapsed_time": "5:15:02", "remaining_time": "1:55:15", "throughput": 1486.14, "total_tokens": 28091936} {"current_steps": 133110, "total_steps": 181800, "loss": 0.0026, "lr": 1.0152398830214665e-05, "epoch": 14.643564356435643, "percentage": 73.22, "elapsed_time": "5:15:03", "remaining_time": "1:55:14", "throughput": 1486.14, "total_tokens": 28092928} {"current_steps": 133115, "total_steps": 181800, "loss": 0.1379, "lr": 1.0150467958035936e-05, "epoch": 14.644114411441144, "percentage": 73.22, "elapsed_time": "5:15:03", "remaining_time": "1:55:13", "throughput": 1486.14, "total_tokens": 28094016} {"current_steps": 133120, "total_steps": 181800, "loss": 0.0454, "lr": 1.014853722271821e-05, "epoch": 14.644664466446645, "percentage": 73.22, "elapsed_time": "5:15:04", "remaining_time": "1:55:13", "throughput": 1486.14, "total_tokens": 28095008} {"current_steps": 133125, "total_steps": 181800, "loss": 0.0982, "lr": 1.014660662427929e-05, "epoch": 14.645214521452145, "percentage": 73.23, "elapsed_time": "5:15:05", "remaining_time": "1:55:12", "throughput": 1486.14, "total_tokens": 28096032} {"current_steps": 133130, "total_steps": 181800, "loss": 0.0686, "lr": 1.014467616273698e-05, "epoch": 14.645764576457646, "percentage": 73.23, "elapsed_time": "5:15:06", "remaining_time": "1:55:11", "throughput": 1486.15, "total_tokens": 28097088} {"current_steps": 133135, "total_steps": 181800, "loss": 0.0554, "lr": 1.014274583810905e-05, "epoch": 14.646314631463147, "percentage": 73.23, "elapsed_time": "5:15:06", "remaining_time": "1:55:10", "throughput": 1486.15, "total_tokens": 28098144} {"current_steps": 133140, "total_steps": 181800, "loss": 0.0176, "lr": 1.0140815650413312e-05, "epoch": 14.646864686468646, "percentage": 73.23, "elapsed_time": "5:15:07", "remaining_time": "1:55:10", "throughput": 1486.15, "total_tokens": 28099232} {"current_steps": 133145, "total_steps": 181800, "loss": 0.0092, "lr": 1.0138885599667547e-05, "epoch": 14.647414741474147, "percentage": 73.24, "elapsed_time": "5:15:08", "remaining_time": "1:55:09", "throughput": 1486.16, "total_tokens": 28100352} {"current_steps": 133150, "total_steps": 181800, "loss": 0.0831, "lr": 1.0136955685889523e-05, "epoch": 14.647964796479648, "percentage": 73.24, "elapsed_time": "5:15:08", "remaining_time": "1:55:08", "throughput": 1486.16, "total_tokens": 28101408} {"current_steps": 133155, "total_steps": 181800, "loss": 0.005, "lr": 1.0135025909097068e-05, "epoch": 14.648514851485148, "percentage": 73.24, "elapsed_time": "5:15:09", "remaining_time": "1:55:08", "throughput": 1486.16, "total_tokens": 28102464} {"current_steps": 133160, "total_steps": 181800, "loss": 0.1132, "lr": 1.0133096269307934e-05, "epoch": 14.649064906490649, "percentage": 73.25, "elapsed_time": "5:15:10", "remaining_time": "1:55:07", "throughput": 1486.16, "total_tokens": 28103456} {"current_steps": 133165, "total_steps": 181800, "loss": 0.0468, "lr": 1.0131166766539926e-05, "epoch": 14.64961496149615, "percentage": 73.25, "elapsed_time": "5:15:10", "remaining_time": "1:55:06", "throughput": 1486.16, "total_tokens": 28104448} {"current_steps": 133170, "total_steps": 181800, "loss": 0.0057, "lr": 1.0129237400810821e-05, "epoch": 14.65016501650165, "percentage": 73.25, "elapsed_time": "5:15:11", "remaining_time": "1:55:05", "throughput": 1486.16, "total_tokens": 28105472} {"current_steps": 133175, "total_steps": 181800, "loss": 0.0208, "lr": 1.0127308172138392e-05, "epoch": 14.65071507150715, "percentage": 73.25, "elapsed_time": "5:15:12", "remaining_time": "1:55:05", "throughput": 1486.15, "total_tokens": 28106464} {"current_steps": 133180, "total_steps": 181800, "loss": 0.1007, "lr": 1.0125379080540423e-05, "epoch": 14.651265126512651, "percentage": 73.26, "elapsed_time": "5:15:12", "remaining_time": "1:55:04", "throughput": 1486.16, "total_tokens": 28107520} {"current_steps": 133185, "total_steps": 181800, "loss": 0.1025, "lr": 1.01234501260347e-05, "epoch": 14.651815181518153, "percentage": 73.26, "elapsed_time": "5:15:13", "remaining_time": "1:55:03", "throughput": 1486.16, "total_tokens": 28108704} {"current_steps": 133190, "total_steps": 181800, "loss": 0.0088, "lr": 1.0121521308639006e-05, "epoch": 14.652365236523652, "percentage": 73.26, "elapsed_time": "5:15:14", "remaining_time": "1:55:03", "throughput": 1486.17, "total_tokens": 28109792} {"current_steps": 133195, "total_steps": 181800, "loss": 0.0069, "lr": 1.0119592628371113e-05, "epoch": 14.652915291529153, "percentage": 73.26, "elapsed_time": "5:15:14", "remaining_time": "1:55:02", "throughput": 1486.17, "total_tokens": 28110848} {"current_steps": 133200, "total_steps": 181800, "loss": 0.0392, "lr": 1.0117664085248785e-05, "epoch": 14.653465346534654, "percentage": 73.27, "elapsed_time": "5:15:15", "remaining_time": "1:55:01", "throughput": 1486.17, "total_tokens": 28111936} {"current_steps": 133205, "total_steps": 181800, "loss": 0.0952, "lr": 1.0115735679289811e-05, "epoch": 14.654015401540153, "percentage": 73.27, "elapsed_time": "5:15:16", "remaining_time": "1:55:00", "throughput": 1486.17, "total_tokens": 28112992} {"current_steps": 133210, "total_steps": 181800, "loss": 0.0258, "lr": 1.0113807410511955e-05, "epoch": 14.654565456545654, "percentage": 73.27, "elapsed_time": "5:15:17", "remaining_time": "1:55:00", "throughput": 1486.17, "total_tokens": 28114016} {"current_steps": 133215, "total_steps": 181800, "loss": 0.0165, "lr": 1.0111879278932989e-05, "epoch": 14.655115511551156, "percentage": 73.28, "elapsed_time": "5:15:17", "remaining_time": "1:54:59", "throughput": 1486.18, "total_tokens": 28115104} {"current_steps": 133220, "total_steps": 181800, "loss": 0.0457, "lr": 1.01099512845707e-05, "epoch": 14.655665566556655, "percentage": 73.28, "elapsed_time": "5:15:18", "remaining_time": "1:54:58", "throughput": 1486.18, "total_tokens": 28116160} {"current_steps": 133225, "total_steps": 181800, "loss": 0.0111, "lr": 1.0108023427442837e-05, "epoch": 14.656215621562156, "percentage": 73.28, "elapsed_time": "5:15:19", "remaining_time": "1:54:58", "throughput": 1486.18, "total_tokens": 28117184} {"current_steps": 133230, "total_steps": 181800, "loss": 0.0093, "lr": 1.0106095707567181e-05, "epoch": 14.656765676567657, "percentage": 73.28, "elapsed_time": "5:15:19", "remaining_time": "1:54:57", "throughput": 1486.18, "total_tokens": 28118272} {"current_steps": 133235, "total_steps": 181800, "loss": 0.0105, "lr": 1.0104168124961488e-05, "epoch": 14.657315731573158, "percentage": 73.29, "elapsed_time": "5:15:20", "remaining_time": "1:54:56", "throughput": 1486.18, "total_tokens": 28119360} {"current_steps": 133240, "total_steps": 181800, "loss": 0.0301, "lr": 1.0102240679643529e-05, "epoch": 14.657865786578657, "percentage": 73.29, "elapsed_time": "5:15:21", "remaining_time": "1:54:55", "throughput": 1486.19, "total_tokens": 28120448} {"current_steps": 133245, "total_steps": 181800, "loss": 0.0126, "lr": 1.0100313371631077e-05, "epoch": 14.658415841584159, "percentage": 73.29, "elapsed_time": "5:15:21", "remaining_time": "1:54:55", "throughput": 1486.19, "total_tokens": 28121536} {"current_steps": 133250, "total_steps": 181800, "loss": 0.0824, "lr": 1.0098386200941878e-05, "epoch": 14.65896589658966, "percentage": 73.29, "elapsed_time": "5:15:22", "remaining_time": "1:54:54", "throughput": 1486.19, "total_tokens": 28122592} {"current_steps": 133255, "total_steps": 181800, "loss": 0.0095, "lr": 1.0096459167593714e-05, "epoch": 14.659515951595159, "percentage": 73.3, "elapsed_time": "5:15:23", "remaining_time": "1:54:53", "throughput": 1486.19, "total_tokens": 28123648} {"current_steps": 133260, "total_steps": 181800, "loss": 0.0197, "lr": 1.0094532271604334e-05, "epoch": 14.66006600660066, "percentage": 73.3, "elapsed_time": "5:15:23", "remaining_time": "1:54:53", "throughput": 1486.2, "total_tokens": 28124800} {"current_steps": 133265, "total_steps": 181800, "loss": 0.0045, "lr": 1.0092605512991487e-05, "epoch": 14.660616061606161, "percentage": 73.3, "elapsed_time": "5:15:24", "remaining_time": "1:54:52", "throughput": 1486.2, "total_tokens": 28125856} {"current_steps": 133270, "total_steps": 181800, "loss": 0.0349, "lr": 1.0090678891772943e-05, "epoch": 14.66116611661166, "percentage": 73.31, "elapsed_time": "5:15:25", "remaining_time": "1:54:51", "throughput": 1486.2, "total_tokens": 28126912} {"current_steps": 133275, "total_steps": 181800, "loss": 0.0824, "lr": 1.0088752407966456e-05, "epoch": 14.661716171617162, "percentage": 73.31, "elapsed_time": "5:15:26", "remaining_time": "1:54:50", "throughput": 1486.21, "total_tokens": 28127968} {"current_steps": 133280, "total_steps": 181800, "loss": 0.0034, "lr": 1.0086826061589794e-05, "epoch": 14.662266226622663, "percentage": 73.31, "elapsed_time": "5:15:26", "remaining_time": "1:54:50", "throughput": 1486.21, "total_tokens": 28129056} {"current_steps": 133285, "total_steps": 181800, "loss": 0.0473, "lr": 1.0084899852660701e-05, "epoch": 14.662816281628164, "percentage": 73.31, "elapsed_time": "5:15:27", "remaining_time": "1:54:49", "throughput": 1486.21, "total_tokens": 28130080} {"current_steps": 133290, "total_steps": 181800, "loss": 0.0027, "lr": 1.0082973781196916e-05, "epoch": 14.663366336633663, "percentage": 73.32, "elapsed_time": "5:15:28", "remaining_time": "1:54:48", "throughput": 1486.21, "total_tokens": 28131104} {"current_steps": 133295, "total_steps": 181800, "loss": 0.0156, "lr": 1.0081047847216207e-05, "epoch": 14.663916391639164, "percentage": 73.32, "elapsed_time": "5:15:28", "remaining_time": "1:54:48", "throughput": 1486.22, "total_tokens": 28132256} {"current_steps": 133300, "total_steps": 181800, "loss": 0.0016, "lr": 1.007912205073632e-05, "epoch": 14.664466446644665, "percentage": 73.32, "elapsed_time": "5:15:29", "remaining_time": "1:54:47", "throughput": 1486.22, "total_tokens": 28133312} {"current_steps": 133305, "total_steps": 181800, "loss": 0.0514, "lr": 1.0077196391775015e-05, "epoch": 14.665016501650165, "percentage": 73.33, "elapsed_time": "5:15:30", "remaining_time": "1:54:46", "throughput": 1486.22, "total_tokens": 28134368} {"current_steps": 133310, "total_steps": 181800, "loss": 0.0621, "lr": 1.007527087035003e-05, "epoch": 14.665566556655666, "percentage": 73.33, "elapsed_time": "5:15:30", "remaining_time": "1:54:45", "throughput": 1486.22, "total_tokens": 28135392} {"current_steps": 133315, "total_steps": 181800, "loss": 0.0631, "lr": 1.0073345486479103e-05, "epoch": 14.666116611661167, "percentage": 73.33, "elapsed_time": "5:15:31", "remaining_time": "1:54:45", "throughput": 1486.22, "total_tokens": 28136480} {"current_steps": 133320, "total_steps": 181800, "loss": 0.0209, "lr": 1.0071420240179997e-05, "epoch": 14.666666666666666, "percentage": 73.33, "elapsed_time": "5:15:32", "remaining_time": "1:54:44", "throughput": 1486.22, "total_tokens": 28137440} {"current_steps": 133325, "total_steps": 181800, "loss": 0.0015, "lr": 1.0069495131470439e-05, "epoch": 14.667216721672167, "percentage": 73.34, "elapsed_time": "5:15:32", "remaining_time": "1:54:43", "throughput": 1486.22, "total_tokens": 28138592} {"current_steps": 133330, "total_steps": 181800, "loss": 0.0041, "lr": 1.0067570160368178e-05, "epoch": 14.667766776677668, "percentage": 73.34, "elapsed_time": "5:15:33", "remaining_time": "1:54:43", "throughput": 1486.22, "total_tokens": 28139584} {"current_steps": 133335, "total_steps": 181800, "loss": 0.0017, "lr": 1.0065645326890969e-05, "epoch": 14.668316831683168, "percentage": 73.34, "elapsed_time": "5:15:34", "remaining_time": "1:54:42", "throughput": 1486.23, "total_tokens": 28140704} {"current_steps": 133340, "total_steps": 181800, "loss": 0.0015, "lr": 1.0063720631056528e-05, "epoch": 14.668866886688669, "percentage": 73.34, "elapsed_time": "5:15:35", "remaining_time": "1:54:41", "throughput": 1486.23, "total_tokens": 28141792} {"current_steps": 133345, "total_steps": 181800, "loss": 0.0026, "lr": 1.0061796072882618e-05, "epoch": 14.66941694169417, "percentage": 73.35, "elapsed_time": "5:15:35", "remaining_time": "1:54:40", "throughput": 1486.23, "total_tokens": 28142880} {"current_steps": 133350, "total_steps": 181800, "loss": 0.0045, "lr": 1.0059871652386957e-05, "epoch": 14.66996699669967, "percentage": 73.35, "elapsed_time": "5:15:36", "remaining_time": "1:54:40", "throughput": 1486.23, "total_tokens": 28143904} {"current_steps": 133355, "total_steps": 181800, "loss": 0.0214, "lr": 1.005794736958729e-05, "epoch": 14.67051705170517, "percentage": 73.35, "elapsed_time": "5:15:37", "remaining_time": "1:54:39", "throughput": 1486.24, "total_tokens": 28145024} {"current_steps": 133360, "total_steps": 181800, "loss": 0.0721, "lr": 1.0056023224501363e-05, "epoch": 14.671067106710671, "percentage": 73.36, "elapsed_time": "5:15:37", "remaining_time": "1:54:38", "throughput": 1486.24, "total_tokens": 28146080} {"current_steps": 133365, "total_steps": 181800, "loss": 0.0086, "lr": 1.0054099217146887e-05, "epoch": 14.671617161716172, "percentage": 73.36, "elapsed_time": "5:15:38", "remaining_time": "1:54:38", "throughput": 1486.24, "total_tokens": 28147072} {"current_steps": 133370, "total_steps": 181800, "loss": 0.0018, "lr": 1.0052175347541618e-05, "epoch": 14.672167216721672, "percentage": 73.36, "elapsed_time": "5:15:39", "remaining_time": "1:54:37", "throughput": 1486.24, "total_tokens": 28148064} {"current_steps": 133375, "total_steps": 181800, "loss": 0.0127, "lr": 1.0050251615703266e-05, "epoch": 14.672717271727173, "percentage": 73.36, "elapsed_time": "5:15:39", "remaining_time": "1:54:36", "throughput": 1486.24, "total_tokens": 28149152} {"current_steps": 133380, "total_steps": 181800, "loss": 0.0022, "lr": 1.0048328021649578e-05, "epoch": 14.673267326732674, "percentage": 73.37, "elapsed_time": "5:15:40", "remaining_time": "1:54:35", "throughput": 1486.24, "total_tokens": 28150240} {"current_steps": 133385, "total_steps": 181800, "loss": 0.002, "lr": 1.004640456539827e-05, "epoch": 14.673817381738173, "percentage": 73.37, "elapsed_time": "5:15:41", "remaining_time": "1:54:35", "throughput": 1486.24, "total_tokens": 28151264} {"current_steps": 133390, "total_steps": 181800, "loss": 0.0066, "lr": 1.0044481246967075e-05, "epoch": 14.674367436743674, "percentage": 73.37, "elapsed_time": "5:15:41", "remaining_time": "1:54:34", "throughput": 1486.24, "total_tokens": 28152288} {"current_steps": 133395, "total_steps": 181800, "loss": 0.0778, "lr": 1.004255806637373e-05, "epoch": 14.674917491749175, "percentage": 73.37, "elapsed_time": "5:15:42", "remaining_time": "1:54:33", "throughput": 1486.25, "total_tokens": 28153376} {"current_steps": 133400, "total_steps": 181800, "loss": 0.0017, "lr": 1.004063502363595e-05, "epoch": 14.675467546754675, "percentage": 73.38, "elapsed_time": "5:15:43", "remaining_time": "1:54:32", "throughput": 1486.25, "total_tokens": 28154496} {"current_steps": 133405, "total_steps": 181800, "loss": 0.0035, "lr": 1.0038712118771448e-05, "epoch": 14.676017601760176, "percentage": 73.38, "elapsed_time": "5:15:43", "remaining_time": "1:54:32", "throughput": 1486.25, "total_tokens": 28155584} {"current_steps": 133410, "total_steps": 181800, "loss": 0.0332, "lr": 1.0036789351797957e-05, "epoch": 14.676567656765677, "percentage": 73.38, "elapsed_time": "5:15:44", "remaining_time": "1:54:31", "throughput": 1486.25, "total_tokens": 28156608} {"current_steps": 133415, "total_steps": 181800, "loss": 0.0273, "lr": 1.00348667227332e-05, "epoch": 14.677117711771178, "percentage": 73.39, "elapsed_time": "5:15:45", "remaining_time": "1:54:30", "throughput": 1486.26, "total_tokens": 28157664} {"current_steps": 133420, "total_steps": 181800, "loss": 0.0554, "lr": 1.0032944231594904e-05, "epoch": 14.677667766776677, "percentage": 73.39, "elapsed_time": "5:15:46", "remaining_time": "1:54:30", "throughput": 1486.26, "total_tokens": 28158720} {"current_steps": 133425, "total_steps": 181800, "loss": 0.0044, "lr": 1.0031021878400781e-05, "epoch": 14.678217821782178, "percentage": 73.39, "elapsed_time": "5:15:46", "remaining_time": "1:54:29", "throughput": 1486.26, "total_tokens": 28159776} {"current_steps": 133430, "total_steps": 181800, "loss": 0.0122, "lr": 1.0029099663168535e-05, "epoch": 14.67876787678768, "percentage": 73.39, "elapsed_time": "5:15:47", "remaining_time": "1:54:28", "throughput": 1486.26, "total_tokens": 28160896} {"current_steps": 133435, "total_steps": 181800, "loss": 0.0867, "lr": 1.0027177585915903e-05, "epoch": 14.679317931793179, "percentage": 73.4, "elapsed_time": "5:15:48", "remaining_time": "1:54:27", "throughput": 1486.26, "total_tokens": 28161888} {"current_steps": 133440, "total_steps": 181800, "loss": 0.0067, "lr": 1.0025255646660584e-05, "epoch": 14.67986798679868, "percentage": 73.4, "elapsed_time": "5:15:48", "remaining_time": "1:54:27", "throughput": 1486.26, "total_tokens": 28162912} {"current_steps": 133445, "total_steps": 181800, "loss": 0.0039, "lr": 1.0023333845420293e-05, "epoch": 14.680418041804181, "percentage": 73.4, "elapsed_time": "5:15:49", "remaining_time": "1:54:26", "throughput": 1486.26, "total_tokens": 28164000} {"current_steps": 133450, "total_steps": 181800, "loss": 0.002, "lr": 1.0021412182212762e-05, "epoch": 14.68096809680968, "percentage": 73.4, "elapsed_time": "5:15:50", "remaining_time": "1:54:25", "throughput": 1486.27, "total_tokens": 28165056} {"current_steps": 133455, "total_steps": 181800, "loss": 0.0109, "lr": 1.0019490657055675e-05, "epoch": 14.681518151815181, "percentage": 73.41, "elapsed_time": "5:15:50", "remaining_time": "1:54:25", "throughput": 1486.27, "total_tokens": 28166112} {"current_steps": 133460, "total_steps": 181800, "loss": 0.0318, "lr": 1.0017569269966765e-05, "epoch": 14.682068206820682, "percentage": 73.41, "elapsed_time": "5:15:51", "remaining_time": "1:54:24", "throughput": 1486.27, "total_tokens": 28167104} {"current_steps": 133465, "total_steps": 181800, "loss": 0.0247, "lr": 1.0015648020963719e-05, "epoch": 14.682618261826182, "percentage": 73.41, "elapsed_time": "5:15:52", "remaining_time": "1:54:23", "throughput": 1486.27, "total_tokens": 28168224} {"current_steps": 133470, "total_steps": 181800, "loss": 0.1112, "lr": 1.0013726910064255e-05, "epoch": 14.683168316831683, "percentage": 73.42, "elapsed_time": "5:15:52", "remaining_time": "1:54:22", "throughput": 1486.27, "total_tokens": 28169248} {"current_steps": 133475, "total_steps": 181800, "loss": 0.0144, "lr": 1.001180593728609e-05, "epoch": 14.683718371837184, "percentage": 73.42, "elapsed_time": "5:15:53", "remaining_time": "1:54:22", "throughput": 1486.28, "total_tokens": 28170368} {"current_steps": 133480, "total_steps": 181800, "loss": 0.0072, "lr": 1.000988510264691e-05, "epoch": 14.684268426842685, "percentage": 73.42, "elapsed_time": "5:15:54", "remaining_time": "1:54:21", "throughput": 1486.28, "total_tokens": 28171424} {"current_steps": 133485, "total_steps": 181800, "loss": 0.053, "lr": 1.000796440616443e-05, "epoch": 14.684818481848184, "percentage": 73.42, "elapsed_time": "5:15:55", "remaining_time": "1:54:20", "throughput": 1486.27, "total_tokens": 28172384} {"current_steps": 133490, "total_steps": 181800, "loss": 0.0095, "lr": 1.0006043847856344e-05, "epoch": 14.685368536853685, "percentage": 73.43, "elapsed_time": "5:15:55", "remaining_time": "1:54:20", "throughput": 1486.27, "total_tokens": 28173408} {"current_steps": 133495, "total_steps": 181800, "loss": 0.0106, "lr": 1.0004123427740364e-05, "epoch": 14.685918591859187, "percentage": 73.43, "elapsed_time": "5:15:56", "remaining_time": "1:54:19", "throughput": 1486.28, "total_tokens": 28174528} {"current_steps": 133500, "total_steps": 181800, "loss": 0.0876, "lr": 1.0002203145834175e-05, "epoch": 14.686468646864686, "percentage": 73.43, "elapsed_time": "5:15:57", "remaining_time": "1:54:18", "throughput": 1486.28, "total_tokens": 28175520} {"current_steps": 133505, "total_steps": 181800, "loss": 0.0104, "lr": 1.000028300215548e-05, "epoch": 14.687018701870187, "percentage": 73.44, "elapsed_time": "5:15:57", "remaining_time": "1:54:17", "throughput": 1486.28, "total_tokens": 28176576} {"current_steps": 133510, "total_steps": 181800, "loss": 0.0016, "lr": 9.998362996721989e-06, "epoch": 14.687568756875688, "percentage": 73.44, "elapsed_time": "5:15:58", "remaining_time": "1:54:17", "throughput": 1486.28, "total_tokens": 28177696} {"current_steps": 133515, "total_steps": 181800, "loss": 0.0032, "lr": 9.996443129551381e-06, "epoch": 14.688118811881187, "percentage": 73.44, "elapsed_time": "5:15:59", "remaining_time": "1:54:16", "throughput": 1486.29, "total_tokens": 28178784} {"current_steps": 133520, "total_steps": 181800, "loss": 0.1207, "lr": 9.994523400661363e-06, "epoch": 14.688668866886688, "percentage": 73.44, "elapsed_time": "5:15:59", "remaining_time": "1:54:15", "throughput": 1486.29, "total_tokens": 28179808} {"current_steps": 133525, "total_steps": 181800, "loss": 0.0073, "lr": 9.992603810069615e-06, "epoch": 14.68921892189219, "percentage": 73.45, "elapsed_time": "5:16:00", "remaining_time": "1:54:15", "throughput": 1486.29, "total_tokens": 28180928} {"current_steps": 133530, "total_steps": 181800, "loss": 0.0213, "lr": 9.990684357793836e-06, "epoch": 14.689768976897689, "percentage": 73.45, "elapsed_time": "5:16:01", "remaining_time": "1:54:14", "throughput": 1486.29, "total_tokens": 28181984} {"current_steps": 133535, "total_steps": 181800, "loss": 0.0166, "lr": 9.988765043851728e-06, "epoch": 14.69031903190319, "percentage": 73.45, "elapsed_time": "5:16:01", "remaining_time": "1:54:13", "throughput": 1486.3, "total_tokens": 28183104} {"current_steps": 133540, "total_steps": 181800, "loss": 0.001, "lr": 9.986845868260957e-06, "epoch": 14.690869086908691, "percentage": 73.45, "elapsed_time": "5:16:02", "remaining_time": "1:54:12", "throughput": 1486.3, "total_tokens": 28184192} {"current_steps": 133545, "total_steps": 181800, "loss": 0.0313, "lr": 9.984926831039237e-06, "epoch": 14.691419141914192, "percentage": 73.46, "elapsed_time": "5:16:03", "remaining_time": "1:54:12", "throughput": 1486.3, "total_tokens": 28185216} {"current_steps": 133550, "total_steps": 181800, "loss": 0.0031, "lr": 9.983007932204238e-06, "epoch": 14.691969196919691, "percentage": 73.46, "elapsed_time": "5:16:04", "remaining_time": "1:54:11", "throughput": 1486.3, "total_tokens": 28186240} {"current_steps": 133555, "total_steps": 181800, "loss": 0.0023, "lr": 9.981089171773642e-06, "epoch": 14.692519251925193, "percentage": 73.46, "elapsed_time": "5:16:04", "remaining_time": "1:54:10", "throughput": 1486.3, "total_tokens": 28187264} {"current_steps": 133560, "total_steps": 181800, "loss": 0.0088, "lr": 9.97917054976514e-06, "epoch": 14.693069306930694, "percentage": 73.47, "elapsed_time": "5:16:05", "remaining_time": "1:54:10", "throughput": 1486.3, "total_tokens": 28188320} {"current_steps": 133565, "total_steps": 181800, "loss": 0.0034, "lr": 9.977252066196416e-06, "epoch": 14.693619361936193, "percentage": 73.47, "elapsed_time": "5:16:06", "remaining_time": "1:54:09", "throughput": 1486.31, "total_tokens": 28189472} {"current_steps": 133570, "total_steps": 181800, "loss": 0.005, "lr": 9.97533372108516e-06, "epoch": 14.694169416941694, "percentage": 73.47, "elapsed_time": "5:16:06", "remaining_time": "1:54:08", "throughput": 1486.31, "total_tokens": 28190560} {"current_steps": 133575, "total_steps": 181800, "loss": 0.0327, "lr": 9.973415514449041e-06, "epoch": 14.694719471947195, "percentage": 73.47, "elapsed_time": "5:16:07", "remaining_time": "1:54:07", "throughput": 1486.31, "total_tokens": 28191552} {"current_steps": 133580, "total_steps": 181800, "loss": 0.0015, "lr": 9.971497446305734e-06, "epoch": 14.695269526952695, "percentage": 73.48, "elapsed_time": "5:16:08", "remaining_time": "1:54:07", "throughput": 1486.31, "total_tokens": 28192640} {"current_steps": 133585, "total_steps": 181800, "loss": 0.01, "lr": 9.969579516672923e-06, "epoch": 14.695819581958196, "percentage": 73.48, "elapsed_time": "5:16:08", "remaining_time": "1:54:06", "throughput": 1486.32, "total_tokens": 28193728} {"current_steps": 133590, "total_steps": 181800, "loss": 0.0675, "lr": 9.967661725568292e-06, "epoch": 14.696369636963697, "percentage": 73.48, "elapsed_time": "5:16:09", "remaining_time": "1:54:05", "throughput": 1486.32, "total_tokens": 28194752} {"current_steps": 133595, "total_steps": 181800, "loss": 0.0078, "lr": 9.965744073009502e-06, "epoch": 14.696919691969196, "percentage": 73.48, "elapsed_time": "5:16:10", "remaining_time": "1:54:05", "throughput": 1486.32, "total_tokens": 28195840} {"current_steps": 133600, "total_steps": 181800, "loss": 0.0913, "lr": 9.963826559014248e-06, "epoch": 14.697469746974697, "percentage": 73.49, "elapsed_time": "5:16:10", "remaining_time": "1:54:04", "throughput": 1486.32, "total_tokens": 28196864} {"current_steps": 133605, "total_steps": 181800, "loss": 0.0784, "lr": 9.961909183600176e-06, "epoch": 14.698019801980198, "percentage": 73.49, "elapsed_time": "5:16:11", "remaining_time": "1:54:03", "throughput": 1486.32, "total_tokens": 28197952} {"current_steps": 133610, "total_steps": 181800, "loss": 0.0318, "lr": 9.95999194678498e-06, "epoch": 14.6985698569857, "percentage": 73.49, "elapsed_time": "5:16:12", "remaining_time": "1:54:02", "throughput": 1486.33, "total_tokens": 28199008} {"current_steps": 133615, "total_steps": 181800, "loss": 0.0072, "lr": 9.958074848586315e-06, "epoch": 14.699119911991199, "percentage": 73.5, "elapsed_time": "5:16:12", "remaining_time": "1:54:02", "throughput": 1486.33, "total_tokens": 28200032} {"current_steps": 133620, "total_steps": 181800, "loss": 0.016, "lr": 9.956157889021855e-06, "epoch": 14.6996699669967, "percentage": 73.5, "elapsed_time": "5:16:13", "remaining_time": "1:54:01", "throughput": 1486.33, "total_tokens": 28201152} {"current_steps": 133625, "total_steps": 181800, "loss": 0.0093, "lr": 9.954241068109276e-06, "epoch": 14.7002200220022, "percentage": 73.5, "elapsed_time": "5:16:14", "remaining_time": "1:54:00", "throughput": 1486.33, "total_tokens": 28202208} {"current_steps": 133630, "total_steps": 181800, "loss": 0.0172, "lr": 9.952324385866232e-06, "epoch": 14.7007700770077, "percentage": 73.5, "elapsed_time": "5:16:15", "remaining_time": "1:53:59", "throughput": 1486.33, "total_tokens": 28203168} {"current_steps": 133635, "total_steps": 181800, "loss": 0.0047, "lr": 9.950407842310403e-06, "epoch": 14.701320132013201, "percentage": 73.51, "elapsed_time": "5:16:15", "remaining_time": "1:53:59", "throughput": 1486.33, "total_tokens": 28204224} {"current_steps": 133640, "total_steps": 181800, "loss": 0.1298, "lr": 9.94849143745943e-06, "epoch": 14.701870187018702, "percentage": 73.51, "elapsed_time": "5:16:16", "remaining_time": "1:53:58", "throughput": 1486.33, "total_tokens": 28205216} {"current_steps": 133645, "total_steps": 181800, "loss": 0.0561, "lr": 9.946575171330993e-06, "epoch": 14.702420242024202, "percentage": 73.51, "elapsed_time": "5:16:17", "remaining_time": "1:53:57", "throughput": 1486.33, "total_tokens": 28206304} {"current_steps": 133650, "total_steps": 181800, "loss": 0.0273, "lr": 9.944659043942756e-06, "epoch": 14.702970297029703, "percentage": 73.51, "elapsed_time": "5:16:17", "remaining_time": "1:53:57", "throughput": 1486.33, "total_tokens": 28207392} {"current_steps": 133655, "total_steps": 181800, "loss": 0.021, "lr": 9.942743055312364e-06, "epoch": 14.703520352035204, "percentage": 73.52, "elapsed_time": "5:16:18", "remaining_time": "1:53:56", "throughput": 1486.33, "total_tokens": 28208416} {"current_steps": 133660, "total_steps": 181800, "loss": 0.0263, "lr": 9.940827205457493e-06, "epoch": 14.704070407040705, "percentage": 73.52, "elapsed_time": "5:16:19", "remaining_time": "1:53:55", "throughput": 1486.34, "total_tokens": 28209472} {"current_steps": 133665, "total_steps": 181800, "loss": 0.1292, "lr": 9.938911494395792e-06, "epoch": 14.704620462046204, "percentage": 73.52, "elapsed_time": "5:16:19", "remaining_time": "1:53:54", "throughput": 1486.34, "total_tokens": 28210592} {"current_steps": 133670, "total_steps": 181800, "loss": 0.0038, "lr": 9.936995922144906e-06, "epoch": 14.705170517051705, "percentage": 73.53, "elapsed_time": "5:16:20", "remaining_time": "1:53:54", "throughput": 1486.34, "total_tokens": 28211616} {"current_steps": 133675, "total_steps": 181800, "loss": 0.0042, "lr": 9.935080488722504e-06, "epoch": 14.705720572057206, "percentage": 73.53, "elapsed_time": "5:16:21", "remaining_time": "1:53:53", "throughput": 1486.34, "total_tokens": 28212672} {"current_steps": 133680, "total_steps": 181800, "loss": 0.0019, "lr": 9.933165194146236e-06, "epoch": 14.706270627062706, "percentage": 73.53, "elapsed_time": "5:16:21", "remaining_time": "1:53:52", "throughput": 1486.34, "total_tokens": 28213728} {"current_steps": 133685, "total_steps": 181800, "loss": 0.0098, "lr": 9.93125003843376e-06, "epoch": 14.706820682068207, "percentage": 73.53, "elapsed_time": "5:16:22", "remaining_time": "1:53:52", "throughput": 1486.34, "total_tokens": 28214752} {"current_steps": 133690, "total_steps": 181800, "loss": 0.0033, "lr": 9.929335021602724e-06, "epoch": 14.707370737073708, "percentage": 73.54, "elapsed_time": "5:16:23", "remaining_time": "1:53:51", "throughput": 1486.34, "total_tokens": 28215808} {"current_steps": 133695, "total_steps": 181800, "loss": 0.0033, "lr": 9.927420143670766e-06, "epoch": 14.707920792079207, "percentage": 73.54, "elapsed_time": "5:16:24", "remaining_time": "1:53:50", "throughput": 1486.35, "total_tokens": 28216864} {"current_steps": 133700, "total_steps": 181800, "loss": 0.0008, "lr": 9.925505404655544e-06, "epoch": 14.708470847084708, "percentage": 73.54, "elapsed_time": "5:16:24", "remaining_time": "1:53:49", "throughput": 1486.35, "total_tokens": 28217920} {"current_steps": 133705, "total_steps": 181800, "loss": 0.0739, "lr": 9.923590804574706e-06, "epoch": 14.70902090209021, "percentage": 73.55, "elapsed_time": "5:16:25", "remaining_time": "1:53:49", "throughput": 1486.35, "total_tokens": 28218912} {"current_steps": 133710, "total_steps": 181800, "loss": 0.0028, "lr": 9.921676343445905e-06, "epoch": 14.70957095709571, "percentage": 73.55, "elapsed_time": "5:16:26", "remaining_time": "1:53:48", "throughput": 1486.35, "total_tokens": 28220000} {"current_steps": 133715, "total_steps": 181800, "loss": 0.1026, "lr": 9.919762021286777e-06, "epoch": 14.71012101210121, "percentage": 73.55, "elapsed_time": "5:16:26", "remaining_time": "1:53:47", "throughput": 1486.35, "total_tokens": 28221120} {"current_steps": 133720, "total_steps": 181800, "loss": 0.0626, "lr": 9.91784783811496e-06, "epoch": 14.710671067106711, "percentage": 73.55, "elapsed_time": "5:16:27", "remaining_time": "1:53:47", "throughput": 1486.36, "total_tokens": 28222208} {"current_steps": 133725, "total_steps": 181800, "loss": 0.0045, "lr": 9.91593379394811e-06, "epoch": 14.711221122112212, "percentage": 73.56, "elapsed_time": "5:16:28", "remaining_time": "1:53:46", "throughput": 1486.36, "total_tokens": 28223264} {"current_steps": 133730, "total_steps": 181800, "loss": 0.0055, "lr": 9.914019888803852e-06, "epoch": 14.711771177117711, "percentage": 73.56, "elapsed_time": "5:16:28", "remaining_time": "1:53:45", "throughput": 1486.36, "total_tokens": 28224288} {"current_steps": 133735, "total_steps": 181800, "loss": 0.0022, "lr": 9.912106122699832e-06, "epoch": 14.712321232123212, "percentage": 73.56, "elapsed_time": "5:16:29", "remaining_time": "1:53:44", "throughput": 1486.36, "total_tokens": 28225312} {"current_steps": 133740, "total_steps": 181800, "loss": 0.003, "lr": 9.9101924956537e-06, "epoch": 14.712871287128714, "percentage": 73.56, "elapsed_time": "5:16:30", "remaining_time": "1:53:44", "throughput": 1486.36, "total_tokens": 28226368} {"current_steps": 133745, "total_steps": 181800, "loss": 0.0016, "lr": 9.908279007683074e-06, "epoch": 14.713421342134213, "percentage": 73.57, "elapsed_time": "5:16:30", "remaining_time": "1:53:43", "throughput": 1486.36, "total_tokens": 28227392} {"current_steps": 133750, "total_steps": 181800, "loss": 0.0057, "lr": 9.906365658805607e-06, "epoch": 14.713971397139714, "percentage": 73.57, "elapsed_time": "5:16:31", "remaining_time": "1:53:42", "throughput": 1486.36, "total_tokens": 28228416} {"current_steps": 133755, "total_steps": 181800, "loss": 0.0011, "lr": 9.904452449038918e-06, "epoch": 14.714521452145215, "percentage": 73.57, "elapsed_time": "5:16:32", "remaining_time": "1:53:42", "throughput": 1486.36, "total_tokens": 28229504} {"current_steps": 133760, "total_steps": 181800, "loss": 0.0696, "lr": 9.902539378400647e-06, "epoch": 14.715071507150714, "percentage": 73.58, "elapsed_time": "5:16:33", "remaining_time": "1:53:41", "throughput": 1486.37, "total_tokens": 28230592} {"current_steps": 133765, "total_steps": 181800, "loss": 0.0099, "lr": 9.900626446908431e-06, "epoch": 14.715621562156215, "percentage": 73.58, "elapsed_time": "5:16:33", "remaining_time": "1:53:40", "throughput": 1486.37, "total_tokens": 28231744} {"current_steps": 133770, "total_steps": 181800, "loss": 0.0377, "lr": 9.898713654579892e-06, "epoch": 14.716171617161717, "percentage": 73.58, "elapsed_time": "5:16:34", "remaining_time": "1:53:39", "throughput": 1486.37, "total_tokens": 28232736} {"current_steps": 133775, "total_steps": 181800, "loss": 0.0089, "lr": 9.896801001432667e-06, "epoch": 14.716721672167218, "percentage": 73.58, "elapsed_time": "5:16:35", "remaining_time": "1:53:39", "throughput": 1486.37, "total_tokens": 28233792} {"current_steps": 133780, "total_steps": 181800, "loss": 0.0047, "lr": 9.894888487484386e-06, "epoch": 14.717271727172717, "percentage": 73.59, "elapsed_time": "5:16:35", "remaining_time": "1:53:38", "throughput": 1486.37, "total_tokens": 28234816} {"current_steps": 133785, "total_steps": 181800, "loss": 0.1011, "lr": 9.892976112752656e-06, "epoch": 14.717821782178218, "percentage": 73.59, "elapsed_time": "5:16:36", "remaining_time": "1:53:37", "throughput": 1486.37, "total_tokens": 28235776} {"current_steps": 133790, "total_steps": 181800, "loss": 0.0467, "lr": 9.891063877255116e-06, "epoch": 14.718371837183719, "percentage": 73.59, "elapsed_time": "5:16:37", "remaining_time": "1:53:37", "throughput": 1486.37, "total_tokens": 28236832} {"current_steps": 133795, "total_steps": 181800, "loss": 0.0029, "lr": 9.889151781009393e-06, "epoch": 14.718921892189218, "percentage": 73.59, "elapsed_time": "5:16:37", "remaining_time": "1:53:36", "throughput": 1486.37, "total_tokens": 28237888} {"current_steps": 133800, "total_steps": 181800, "loss": 0.0036, "lr": 9.887239824033115e-06, "epoch": 14.71947194719472, "percentage": 73.6, "elapsed_time": "5:16:38", "remaining_time": "1:53:35", "throughput": 1486.38, "total_tokens": 28238976} {"current_steps": 133805, "total_steps": 181800, "loss": 0.0242, "lr": 9.885328006343894e-06, "epoch": 14.72002200220022, "percentage": 73.6, "elapsed_time": "5:16:39", "remaining_time": "1:53:34", "throughput": 1486.37, "total_tokens": 28239968} {"current_steps": 133810, "total_steps": 181800, "loss": 0.0038, "lr": 9.883416327959346e-06, "epoch": 14.72057205720572, "percentage": 73.6, "elapsed_time": "5:16:39", "remaining_time": "1:53:34", "throughput": 1486.37, "total_tokens": 28240960} {"current_steps": 133815, "total_steps": 181800, "loss": 0.0079, "lr": 9.881504788897103e-06, "epoch": 14.721122112211221, "percentage": 73.61, "elapsed_time": "5:16:40", "remaining_time": "1:53:33", "throughput": 1486.38, "total_tokens": 28242112} {"current_steps": 133820, "total_steps": 181800, "loss": 0.0035, "lr": 9.87959338917476e-06, "epoch": 14.721672167216722, "percentage": 73.61, "elapsed_time": "5:16:41", "remaining_time": "1:53:32", "throughput": 1486.38, "total_tokens": 28243136} {"current_steps": 133825, "total_steps": 181800, "loss": 0.0025, "lr": 9.877682128809965e-06, "epoch": 14.722222222222221, "percentage": 73.61, "elapsed_time": "5:16:41", "remaining_time": "1:53:32", "throughput": 1486.38, "total_tokens": 28244160} {"current_steps": 133830, "total_steps": 181800, "loss": 0.0013, "lr": 9.875771007820317e-06, "epoch": 14.722772277227723, "percentage": 73.61, "elapsed_time": "5:16:42", "remaining_time": "1:53:31", "throughput": 1486.38, "total_tokens": 28245216} {"current_steps": 133835, "total_steps": 181800, "loss": 0.0061, "lr": 9.873860026223423e-06, "epoch": 14.723322332233224, "percentage": 73.62, "elapsed_time": "5:16:43", "remaining_time": "1:53:30", "throughput": 1486.38, "total_tokens": 28246272} {"current_steps": 133840, "total_steps": 181800, "loss": 0.0563, "lr": 9.87194918403691e-06, "epoch": 14.723872387238725, "percentage": 73.62, "elapsed_time": "5:16:44", "remaining_time": "1:53:29", "throughput": 1486.39, "total_tokens": 28247360} {"current_steps": 133845, "total_steps": 181800, "loss": 0.0153, "lr": 9.870038481278377e-06, "epoch": 14.724422442244224, "percentage": 73.62, "elapsed_time": "5:16:44", "remaining_time": "1:53:29", "throughput": 1486.39, "total_tokens": 28248416} {"current_steps": 133850, "total_steps": 181800, "loss": 0.0318, "lr": 9.868127917965436e-06, "epoch": 14.724972497249725, "percentage": 73.62, "elapsed_time": "5:16:45", "remaining_time": "1:53:28", "throughput": 1486.38, "total_tokens": 28249408} {"current_steps": 133855, "total_steps": 181800, "loss": 0.0696, "lr": 9.86621749411571e-06, "epoch": 14.725522552255226, "percentage": 73.63, "elapsed_time": "5:16:46", "remaining_time": "1:53:27", "throughput": 1486.39, "total_tokens": 28250496} {"current_steps": 133860, "total_steps": 181800, "loss": 0.141, "lr": 9.864307209746785e-06, "epoch": 14.726072607260726, "percentage": 73.63, "elapsed_time": "5:16:46", "remaining_time": "1:53:27", "throughput": 1486.39, "total_tokens": 28251520} {"current_steps": 133865, "total_steps": 181800, "loss": 0.0028, "lr": 9.862397064876285e-06, "epoch": 14.726622662266227, "percentage": 73.63, "elapsed_time": "5:16:47", "remaining_time": "1:53:26", "throughput": 1486.39, "total_tokens": 28252576} {"current_steps": 133870, "total_steps": 181800, "loss": 0.0052, "lr": 9.8604870595218e-06, "epoch": 14.727172717271728, "percentage": 73.64, "elapsed_time": "5:16:48", "remaining_time": "1:53:25", "throughput": 1486.39, "total_tokens": 28253664} {"current_steps": 133875, "total_steps": 181800, "loss": 0.0905, "lr": 9.858577193700952e-06, "epoch": 14.727722772277227, "percentage": 73.64, "elapsed_time": "5:16:48", "remaining_time": "1:53:24", "throughput": 1486.39, "total_tokens": 28254720} {"current_steps": 133880, "total_steps": 181800, "loss": 0.0018, "lr": 9.856667467431322e-06, "epoch": 14.728272827282728, "percentage": 73.64, "elapsed_time": "5:16:49", "remaining_time": "1:53:24", "throughput": 1486.4, "total_tokens": 28255776} {"current_steps": 133885, "total_steps": 181800, "loss": 0.0742, "lr": 9.854757880730522e-06, "epoch": 14.72882288228823, "percentage": 73.64, "elapsed_time": "5:16:50", "remaining_time": "1:53:23", "throughput": 1486.4, "total_tokens": 28256832} {"current_steps": 133890, "total_steps": 181800, "loss": 0.0397, "lr": 9.85284843361616e-06, "epoch": 14.729372937293729, "percentage": 73.65, "elapsed_time": "5:16:50", "remaining_time": "1:53:22", "throughput": 1486.4, "total_tokens": 28257888} {"current_steps": 133895, "total_steps": 181800, "loss": 0.0044, "lr": 9.850939126105815e-06, "epoch": 14.72992299229923, "percentage": 73.65, "elapsed_time": "5:16:51", "remaining_time": "1:53:21", "throughput": 1486.4, "total_tokens": 28258944} {"current_steps": 133900, "total_steps": 181800, "loss": 0.039, "lr": 9.849029958217107e-06, "epoch": 14.73047304730473, "percentage": 73.65, "elapsed_time": "5:16:52", "remaining_time": "1:53:21", "throughput": 1486.41, "total_tokens": 28260032} {"current_steps": 133905, "total_steps": 181800, "loss": 0.0367, "lr": 9.847120929967607e-06, "epoch": 14.731023102310232, "percentage": 73.66, "elapsed_time": "5:16:53", "remaining_time": "1:53:20", "throughput": 1486.41, "total_tokens": 28261152} {"current_steps": 133910, "total_steps": 181800, "loss": 0.0024, "lr": 9.845212041374927e-06, "epoch": 14.731573157315731, "percentage": 73.66, "elapsed_time": "5:16:53", "remaining_time": "1:53:19", "throughput": 1486.41, "total_tokens": 28262208} {"current_steps": 133915, "total_steps": 181800, "loss": 0.002, "lr": 9.843303292456659e-06, "epoch": 14.732123212321232, "percentage": 73.66, "elapsed_time": "5:16:54", "remaining_time": "1:53:19", "throughput": 1486.41, "total_tokens": 28263264} {"current_steps": 133920, "total_steps": 181800, "loss": 0.2093, "lr": 9.841394683230388e-06, "epoch": 14.732673267326733, "percentage": 73.66, "elapsed_time": "5:16:55", "remaining_time": "1:53:18", "throughput": 1486.41, "total_tokens": 28264320} {"current_steps": 133925, "total_steps": 181800, "loss": 0.0633, "lr": 9.839486213713714e-06, "epoch": 14.733223322332233, "percentage": 73.67, "elapsed_time": "5:16:55", "remaining_time": "1:53:17", "throughput": 1486.42, "total_tokens": 28265376} {"current_steps": 133930, "total_steps": 181800, "loss": 0.0252, "lr": 9.837577883924221e-06, "epoch": 14.733773377337734, "percentage": 73.67, "elapsed_time": "5:16:56", "remaining_time": "1:53:16", "throughput": 1486.42, "total_tokens": 28266432} {"current_steps": 133935, "total_steps": 181800, "loss": 0.0045, "lr": 9.835669693879482e-06, "epoch": 14.734323432343235, "percentage": 73.67, "elapsed_time": "5:16:57", "remaining_time": "1:53:16", "throughput": 1486.42, "total_tokens": 28267456} {"current_steps": 133940, "total_steps": 181800, "loss": 0.0981, "lr": 9.833761643597115e-06, "epoch": 14.734873487348734, "percentage": 73.67, "elapsed_time": "5:16:57", "remaining_time": "1:53:15", "throughput": 1486.42, "total_tokens": 28268512} {"current_steps": 133945, "total_steps": 181800, "loss": 0.0042, "lr": 9.83185373309468e-06, "epoch": 14.735423542354235, "percentage": 73.68, "elapsed_time": "5:16:58", "remaining_time": "1:53:14", "throughput": 1486.42, "total_tokens": 28269536} {"current_steps": 133950, "total_steps": 181800, "loss": 0.0102, "lr": 9.829945962389778e-06, "epoch": 14.735973597359736, "percentage": 73.68, "elapsed_time": "5:16:59", "remaining_time": "1:53:14", "throughput": 1486.42, "total_tokens": 28270592} {"current_steps": 133955, "total_steps": 181800, "loss": 0.0031, "lr": 9.828038331499987e-06, "epoch": 14.736523652365236, "percentage": 73.68, "elapsed_time": "5:16:59", "remaining_time": "1:53:13", "throughput": 1486.42, "total_tokens": 28271616} {"current_steps": 133960, "total_steps": 181800, "loss": 0.0736, "lr": 9.826130840442876e-06, "epoch": 14.737073707370737, "percentage": 73.69, "elapsed_time": "5:17:00", "remaining_time": "1:53:12", "throughput": 1486.42, "total_tokens": 28272704} {"current_steps": 133965, "total_steps": 181800, "loss": 0.0011, "lr": 9.82422348923604e-06, "epoch": 14.737623762376238, "percentage": 73.69, "elapsed_time": "5:17:01", "remaining_time": "1:53:11", "throughput": 1486.43, "total_tokens": 28273792} {"current_steps": 133970, "total_steps": 181800, "loss": 0.0037, "lr": 9.82231627789706e-06, "epoch": 14.738173817381739, "percentage": 73.69, "elapsed_time": "5:17:02", "remaining_time": "1:53:11", "throughput": 1486.43, "total_tokens": 28274848} {"current_steps": 133975, "total_steps": 181800, "loss": 0.0155, "lr": 9.820409206443498e-06, "epoch": 14.738723872387238, "percentage": 73.69, "elapsed_time": "5:17:02", "remaining_time": "1:53:10", "throughput": 1486.43, "total_tokens": 28275936} {"current_steps": 133980, "total_steps": 181800, "loss": 0.0019, "lr": 9.818502274892949e-06, "epoch": 14.73927392739274, "percentage": 73.7, "elapsed_time": "5:17:03", "remaining_time": "1:53:09", "throughput": 1486.43, "total_tokens": 28276960} {"current_steps": 133985, "total_steps": 181800, "loss": 0.1075, "lr": 9.816595483262974e-06, "epoch": 14.73982398239824, "percentage": 73.7, "elapsed_time": "5:17:04", "remaining_time": "1:53:09", "throughput": 1486.43, "total_tokens": 28277920} {"current_steps": 133990, "total_steps": 181800, "loss": 0.0159, "lr": 9.814688831571159e-06, "epoch": 14.74037403740374, "percentage": 73.7, "elapsed_time": "5:17:04", "remaining_time": "1:53:08", "throughput": 1486.43, "total_tokens": 28278976} {"current_steps": 133995, "total_steps": 181800, "loss": 0.0376, "lr": 9.812782319835063e-06, "epoch": 14.74092409240924, "percentage": 73.7, "elapsed_time": "5:17:05", "remaining_time": "1:53:07", "throughput": 1486.43, "total_tokens": 28280000} {"current_steps": 134000, "total_steps": 181800, "loss": 0.001, "lr": 9.810875948072265e-06, "epoch": 14.741474147414742, "percentage": 73.71, "elapsed_time": "5:17:06", "remaining_time": "1:53:06", "throughput": 1486.43, "total_tokens": 28281024} {"current_steps": 134005, "total_steps": 181800, "loss": 0.0182, "lr": 9.808969716300343e-06, "epoch": 14.742024202420241, "percentage": 73.71, "elapsed_time": "5:17:06", "remaining_time": "1:53:06", "throughput": 1486.43, "total_tokens": 28282080} {"current_steps": 134010, "total_steps": 181800, "loss": 0.0638, "lr": 9.807063624536847e-06, "epoch": 14.742574257425742, "percentage": 73.71, "elapsed_time": "5:17:07", "remaining_time": "1:53:05", "throughput": 1486.43, "total_tokens": 28283072} {"current_steps": 134015, "total_steps": 181800, "loss": 0.002, "lr": 9.805157672799367e-06, "epoch": 14.743124312431243, "percentage": 73.72, "elapsed_time": "5:17:08", "remaining_time": "1:53:04", "throughput": 1486.42, "total_tokens": 28284032} {"current_steps": 134020, "total_steps": 181800, "loss": 0.0735, "lr": 9.803251861105447e-06, "epoch": 14.743674367436743, "percentage": 73.72, "elapsed_time": "5:17:08", "remaining_time": "1:53:04", "throughput": 1486.42, "total_tokens": 28285024} {"current_steps": 134025, "total_steps": 181800, "loss": 0.0031, "lr": 9.801346189472666e-06, "epoch": 14.744224422442244, "percentage": 73.72, "elapsed_time": "5:17:09", "remaining_time": "1:53:03", "throughput": 1486.43, "total_tokens": 28286144} {"current_steps": 134030, "total_steps": 181800, "loss": 0.095, "lr": 9.799440657918587e-06, "epoch": 14.744774477447745, "percentage": 73.72, "elapsed_time": "5:17:10", "remaining_time": "1:53:02", "throughput": 1486.43, "total_tokens": 28287200} {"current_steps": 134035, "total_steps": 181800, "loss": 0.002, "lr": 9.797535266460766e-06, "epoch": 14.745324532453246, "percentage": 73.73, "elapsed_time": "5:17:11", "remaining_time": "1:53:01", "throughput": 1486.43, "total_tokens": 28288224} {"current_steps": 134040, "total_steps": 181800, "loss": 0.1108, "lr": 9.795630015116775e-06, "epoch": 14.745874587458745, "percentage": 73.73, "elapsed_time": "5:17:11", "remaining_time": "1:53:01", "throughput": 1486.43, "total_tokens": 28289280} {"current_steps": 134045, "total_steps": 181800, "loss": 0.1123, "lr": 9.793724903904164e-06, "epoch": 14.746424642464246, "percentage": 73.73, "elapsed_time": "5:17:12", "remaining_time": "1:53:00", "throughput": 1486.43, "total_tokens": 28290304} {"current_steps": 134050, "total_steps": 181800, "loss": 0.0089, "lr": 9.791819932840487e-06, "epoch": 14.746974697469748, "percentage": 73.73, "elapsed_time": "5:17:13", "remaining_time": "1:52:59", "throughput": 1486.43, "total_tokens": 28291328} {"current_steps": 134055, "total_steps": 181800, "loss": 0.08, "lr": 9.789915101943309e-06, "epoch": 14.747524752475247, "percentage": 73.74, "elapsed_time": "5:17:13", "remaining_time": "1:52:59", "throughput": 1486.43, "total_tokens": 28292384} {"current_steps": 134060, "total_steps": 181800, "loss": 0.0011, "lr": 9.788010411230184e-06, "epoch": 14.748074807480748, "percentage": 73.74, "elapsed_time": "5:17:14", "remaining_time": "1:52:58", "throughput": 1486.43, "total_tokens": 28293472} {"current_steps": 134065, "total_steps": 181800, "loss": 0.0266, "lr": 9.786105860718675e-06, "epoch": 14.748624862486249, "percentage": 73.74, "elapsed_time": "5:17:15", "remaining_time": "1:52:57", "throughput": 1486.43, "total_tokens": 28294496} {"current_steps": 134070, "total_steps": 181800, "loss": 0.003, "lr": 9.78420145042633e-06, "epoch": 14.749174917491748, "percentage": 73.75, "elapsed_time": "5:17:15", "remaining_time": "1:52:56", "throughput": 1486.44, "total_tokens": 28295552} {"current_steps": 134075, "total_steps": 181800, "loss": 0.0323, "lr": 9.782297180370689e-06, "epoch": 14.74972497249725, "percentage": 73.75, "elapsed_time": "5:17:16", "remaining_time": "1:52:56", "throughput": 1486.44, "total_tokens": 28296608} {"current_steps": 134080, "total_steps": 181800, "loss": 0.0031, "lr": 9.780393050569315e-06, "epoch": 14.75027502750275, "percentage": 73.75, "elapsed_time": "5:17:17", "remaining_time": "1:52:55", "throughput": 1486.43, "total_tokens": 28297568} {"current_steps": 134085, "total_steps": 181800, "loss": 0.0054, "lr": 9.778489061039753e-06, "epoch": 14.750825082508252, "percentage": 73.75, "elapsed_time": "5:17:17", "remaining_time": "1:52:54", "throughput": 1486.44, "total_tokens": 28298624} {"current_steps": 134090, "total_steps": 181800, "loss": 0.1306, "lr": 9.776585211799563e-06, "epoch": 14.751375137513751, "percentage": 73.76, "elapsed_time": "5:17:18", "remaining_time": "1:52:54", "throughput": 1486.44, "total_tokens": 28299712} {"current_steps": 134095, "total_steps": 181800, "loss": 0.0442, "lr": 9.77468150286628e-06, "epoch": 14.751925192519252, "percentage": 73.76, "elapsed_time": "5:17:19", "remaining_time": "1:52:53", "throughput": 1486.44, "total_tokens": 28300736} {"current_steps": 134100, "total_steps": 181800, "loss": 0.0055, "lr": 9.772777934257447e-06, "epoch": 14.752475247524753, "percentage": 73.76, "elapsed_time": "5:17:19", "remaining_time": "1:52:52", "throughput": 1486.44, "total_tokens": 28301792} {"current_steps": 134105, "total_steps": 181800, "loss": 0.0683, "lr": 9.770874505990619e-06, "epoch": 14.753025302530252, "percentage": 73.77, "elapsed_time": "5:17:20", "remaining_time": "1:52:51", "throughput": 1486.44, "total_tokens": 28302848} {"current_steps": 134110, "total_steps": 181800, "loss": 0.1533, "lr": 9.768971218083325e-06, "epoch": 14.753575357535754, "percentage": 73.77, "elapsed_time": "5:17:21", "remaining_time": "1:52:51", "throughput": 1486.44, "total_tokens": 28303904} {"current_steps": 134115, "total_steps": 181800, "loss": 0.0053, "lr": 9.767068070553116e-06, "epoch": 14.754125412541255, "percentage": 73.77, "elapsed_time": "5:17:22", "remaining_time": "1:52:50", "throughput": 1486.44, "total_tokens": 28304928} {"current_steps": 134120, "total_steps": 181800, "loss": 0.0024, "lr": 9.765165063417537e-06, "epoch": 14.754675467546754, "percentage": 73.77, "elapsed_time": "5:17:22", "remaining_time": "1:52:49", "throughput": 1486.44, "total_tokens": 28305920} {"current_steps": 134125, "total_steps": 181800, "loss": 0.061, "lr": 9.763262196694111e-06, "epoch": 14.755225522552255, "percentage": 73.78, "elapsed_time": "5:17:23", "remaining_time": "1:52:49", "throughput": 1486.44, "total_tokens": 28306976} {"current_steps": 134130, "total_steps": 181800, "loss": 0.0029, "lr": 9.7613594704004e-06, "epoch": 14.755775577557756, "percentage": 73.78, "elapsed_time": "5:17:24", "remaining_time": "1:52:48", "throughput": 1486.45, "total_tokens": 28308064} {"current_steps": 134135, "total_steps": 181800, "loss": 0.0034, "lr": 9.759456884553913e-06, "epoch": 14.756325632563257, "percentage": 73.78, "elapsed_time": "5:17:24", "remaining_time": "1:52:47", "throughput": 1486.45, "total_tokens": 28309088} {"current_steps": 134140, "total_steps": 181800, "loss": 0.007, "lr": 9.757554439172203e-06, "epoch": 14.756875687568757, "percentage": 73.78, "elapsed_time": "5:17:25", "remaining_time": "1:52:46", "throughput": 1486.45, "total_tokens": 28310176} {"current_steps": 134145, "total_steps": 181800, "loss": 0.059, "lr": 9.755652134272809e-06, "epoch": 14.757425742574258, "percentage": 73.79, "elapsed_time": "5:17:26", "remaining_time": "1:52:46", "throughput": 1486.45, "total_tokens": 28311200} {"current_steps": 134150, "total_steps": 181800, "loss": 0.056, "lr": 9.753749969873242e-06, "epoch": 14.757975797579759, "percentage": 73.79, "elapsed_time": "5:17:26", "remaining_time": "1:52:45", "throughput": 1486.45, "total_tokens": 28312224} {"current_steps": 134155, "total_steps": 181800, "loss": 0.0022, "lr": 9.751847945991055e-06, "epoch": 14.758525852585258, "percentage": 73.79, "elapsed_time": "5:17:27", "remaining_time": "1:52:44", "throughput": 1486.45, "total_tokens": 28313280} {"current_steps": 134160, "total_steps": 181800, "loss": 0.0472, "lr": 9.74994606264376e-06, "epoch": 14.75907590759076, "percentage": 73.8, "elapsed_time": "5:17:28", "remaining_time": "1:52:44", "throughput": 1486.45, "total_tokens": 28314304} {"current_steps": 134165, "total_steps": 181800, "loss": 0.0038, "lr": 9.748044319848903e-06, "epoch": 14.75962596259626, "percentage": 73.8, "elapsed_time": "5:17:28", "remaining_time": "1:52:43", "throughput": 1486.45, "total_tokens": 28315296} {"current_steps": 134170, "total_steps": 181800, "loss": 0.0626, "lr": 9.746142717623997e-06, "epoch": 14.76017601760176, "percentage": 73.8, "elapsed_time": "5:17:29", "remaining_time": "1:52:42", "throughput": 1486.45, "total_tokens": 28316384} {"current_steps": 134175, "total_steps": 181800, "loss": 0.0055, "lr": 9.744241255986572e-06, "epoch": 14.76072607260726, "percentage": 73.8, "elapsed_time": "5:17:30", "remaining_time": "1:52:41", "throughput": 1486.45, "total_tokens": 28317408} {"current_steps": 134180, "total_steps": 181800, "loss": 0.0417, "lr": 9.742339934954164e-06, "epoch": 14.761276127612762, "percentage": 73.81, "elapsed_time": "5:17:31", "remaining_time": "1:52:41", "throughput": 1486.45, "total_tokens": 28318432} {"current_steps": 134185, "total_steps": 181800, "loss": 0.0026, "lr": 9.740438754544288e-06, "epoch": 14.761826182618261, "percentage": 73.81, "elapsed_time": "5:17:31", "remaining_time": "1:52:40", "throughput": 1486.45, "total_tokens": 28319488} {"current_steps": 134190, "total_steps": 181800, "loss": 0.0024, "lr": 9.738537714774454e-06, "epoch": 14.762376237623762, "percentage": 73.81, "elapsed_time": "5:17:32", "remaining_time": "1:52:39", "throughput": 1486.45, "total_tokens": 28320544} {"current_steps": 134195, "total_steps": 181800, "loss": 0.0438, "lr": 9.736636815662197e-06, "epoch": 14.762926292629263, "percentage": 73.81, "elapsed_time": "5:17:33", "remaining_time": "1:52:38", "throughput": 1486.46, "total_tokens": 28321728} {"current_steps": 134200, "total_steps": 181800, "loss": 0.0085, "lr": 9.734736057225036e-06, "epoch": 14.763476347634764, "percentage": 73.82, "elapsed_time": "5:17:33", "remaining_time": "1:52:38", "throughput": 1486.46, "total_tokens": 28322784} {"current_steps": 134205, "total_steps": 181800, "loss": 0.0037, "lr": 9.732835439480492e-06, "epoch": 14.764026402640264, "percentage": 73.82, "elapsed_time": "5:17:34", "remaining_time": "1:52:37", "throughput": 1486.46, "total_tokens": 28323744} {"current_steps": 134210, "total_steps": 181800, "loss": 0.0037, "lr": 9.73093496244608e-06, "epoch": 14.764576457645765, "percentage": 73.82, "elapsed_time": "5:17:35", "remaining_time": "1:52:36", "throughput": 1486.46, "total_tokens": 28324800} {"current_steps": 134215, "total_steps": 181800, "loss": 0.0786, "lr": 9.729034626139309e-06, "epoch": 14.765126512651266, "percentage": 73.83, "elapsed_time": "5:17:35", "remaining_time": "1:52:36", "throughput": 1486.47, "total_tokens": 28325888} {"current_steps": 134220, "total_steps": 181800, "loss": 0.0116, "lr": 9.727134430577703e-06, "epoch": 14.765676567656765, "percentage": 73.83, "elapsed_time": "5:17:36", "remaining_time": "1:52:35", "throughput": 1486.47, "total_tokens": 28326944} {"current_steps": 134225, "total_steps": 181800, "loss": 0.0051, "lr": 9.72523437577876e-06, "epoch": 14.766226622662266, "percentage": 73.83, "elapsed_time": "5:17:37", "remaining_time": "1:52:34", "throughput": 1486.47, "total_tokens": 28328000} {"current_steps": 134230, "total_steps": 181800, "loss": 0.002, "lr": 9.723334461760006e-06, "epoch": 14.766776677667767, "percentage": 73.83, "elapsed_time": "5:17:37", "remaining_time": "1:52:33", "throughput": 1486.47, "total_tokens": 28329056} {"current_steps": 134235, "total_steps": 181800, "loss": 0.0046, "lr": 9.721434688538955e-06, "epoch": 14.767326732673267, "percentage": 73.84, "elapsed_time": "5:17:38", "remaining_time": "1:52:33", "throughput": 1486.47, "total_tokens": 28330112} {"current_steps": 134240, "total_steps": 181800, "loss": 0.0157, "lr": 9.7195350561331e-06, "epoch": 14.767876787678768, "percentage": 73.84, "elapsed_time": "5:17:39", "remaining_time": "1:52:32", "throughput": 1486.47, "total_tokens": 28331136} {"current_steps": 134245, "total_steps": 181800, "loss": 0.0017, "lr": 9.717635564559966e-06, "epoch": 14.768426842684269, "percentage": 73.84, "elapsed_time": "5:17:40", "remaining_time": "1:52:31", "throughput": 1486.47, "total_tokens": 28332160} {"current_steps": 134250, "total_steps": 181800, "loss": 0.0436, "lr": 9.715736213837046e-06, "epoch": 14.768976897689768, "percentage": 73.84, "elapsed_time": "5:17:40", "remaining_time": "1:52:31", "throughput": 1486.47, "total_tokens": 28333216} {"current_steps": 134255, "total_steps": 181800, "loss": 0.0952, "lr": 9.713837003981849e-06, "epoch": 14.76952695269527, "percentage": 73.85, "elapsed_time": "5:17:41", "remaining_time": "1:52:30", "throughput": 1486.47, "total_tokens": 28334240} {"current_steps": 134260, "total_steps": 181800, "loss": 0.0793, "lr": 9.711937935011888e-06, "epoch": 14.77007700770077, "percentage": 73.85, "elapsed_time": "5:17:42", "remaining_time": "1:52:29", "throughput": 1486.47, "total_tokens": 28335264} {"current_steps": 134265, "total_steps": 181800, "loss": 0.0054, "lr": 9.710039006944654e-06, "epoch": 14.770627062706271, "percentage": 73.85, "elapsed_time": "5:17:42", "remaining_time": "1:52:28", "throughput": 1486.48, "total_tokens": 28336352} {"current_steps": 134270, "total_steps": 181800, "loss": 0.0424, "lr": 9.708140219797663e-06, "epoch": 14.77117711771177, "percentage": 73.86, "elapsed_time": "5:17:43", "remaining_time": "1:52:28", "throughput": 1486.48, "total_tokens": 28337408} {"current_steps": 134275, "total_steps": 181800, "loss": 0.0052, "lr": 9.706241573588393e-06, "epoch": 14.771727172717272, "percentage": 73.86, "elapsed_time": "5:17:44", "remaining_time": "1:52:27", "throughput": 1486.48, "total_tokens": 28338496} {"current_steps": 134280, "total_steps": 181800, "loss": 0.0891, "lr": 9.704343068334368e-06, "epoch": 14.772277227722773, "percentage": 73.86, "elapsed_time": "5:17:44", "remaining_time": "1:52:26", "throughput": 1486.48, "total_tokens": 28339552} {"current_steps": 134285, "total_steps": 181800, "loss": 0.0261, "lr": 9.702444704053063e-06, "epoch": 14.772827282728272, "percentage": 73.86, "elapsed_time": "5:17:45", "remaining_time": "1:52:26", "throughput": 1486.48, "total_tokens": 28340576} {"current_steps": 134290, "total_steps": 181800, "loss": 0.0393, "lr": 9.700546480761985e-06, "epoch": 14.773377337733773, "percentage": 73.87, "elapsed_time": "5:17:46", "remaining_time": "1:52:25", "throughput": 1486.48, "total_tokens": 28341632} {"current_steps": 134295, "total_steps": 181800, "loss": 0.0058, "lr": 9.698648398478637e-06, "epoch": 14.773927392739274, "percentage": 73.87, "elapsed_time": "5:17:46", "remaining_time": "1:52:24", "throughput": 1486.49, "total_tokens": 28342816} {"current_steps": 134300, "total_steps": 181800, "loss": 0.0036, "lr": 9.696750457220497e-06, "epoch": 14.774477447744774, "percentage": 73.87, "elapsed_time": "5:17:47", "remaining_time": "1:52:23", "throughput": 1486.49, "total_tokens": 28343808} {"current_steps": 134305, "total_steps": 181800, "loss": 0.003, "lr": 9.694852657005071e-06, "epoch": 14.775027502750275, "percentage": 73.88, "elapsed_time": "5:17:48", "remaining_time": "1:52:23", "throughput": 1486.49, "total_tokens": 28344864} {"current_steps": 134310, "total_steps": 181800, "loss": 0.0053, "lr": 9.692954997849838e-06, "epoch": 14.775577557755776, "percentage": 73.88, "elapsed_time": "5:17:48", "remaining_time": "1:52:22", "throughput": 1486.5, "total_tokens": 28345952} {"current_steps": 134315, "total_steps": 181800, "loss": 0.0011, "lr": 9.691057479772292e-06, "epoch": 14.776127612761275, "percentage": 73.88, "elapsed_time": "5:17:49", "remaining_time": "1:52:21", "throughput": 1486.5, "total_tokens": 28347008} {"current_steps": 134320, "total_steps": 181800, "loss": 0.006, "lr": 9.689160102789933e-06, "epoch": 14.776677667766776, "percentage": 73.88, "elapsed_time": "5:17:50", "remaining_time": "1:52:21", "throughput": 1486.5, "total_tokens": 28348096} {"current_steps": 134325, "total_steps": 181800, "loss": 0.0127, "lr": 9.68726286692023e-06, "epoch": 14.777227722772277, "percentage": 73.89, "elapsed_time": "5:17:51", "remaining_time": "1:52:20", "throughput": 1486.5, "total_tokens": 28349120} {"current_steps": 134330, "total_steps": 181800, "loss": 0.0044, "lr": 9.685365772180684e-06, "epoch": 14.777777777777779, "percentage": 73.89, "elapsed_time": "5:17:51", "remaining_time": "1:52:19", "throughput": 1486.5, "total_tokens": 28350176} {"current_steps": 134335, "total_steps": 181800, "loss": 0.0636, "lr": 9.683468818588775e-06, "epoch": 14.778327832783278, "percentage": 73.89, "elapsed_time": "5:17:52", "remaining_time": "1:52:18", "throughput": 1486.51, "total_tokens": 28351296} {"current_steps": 134340, "total_steps": 181800, "loss": 0.0014, "lr": 9.681572006161976e-06, "epoch": 14.778877887788779, "percentage": 73.89, "elapsed_time": "5:17:53", "remaining_time": "1:52:18", "throughput": 1486.51, "total_tokens": 28352352} {"current_steps": 134345, "total_steps": 181800, "loss": 0.1232, "lr": 9.679675334917776e-06, "epoch": 14.77942794279428, "percentage": 73.9, "elapsed_time": "5:17:53", "remaining_time": "1:52:17", "throughput": 1486.51, "total_tokens": 28353440} {"current_steps": 134350, "total_steps": 181800, "loss": 0.0039, "lr": 9.677778804873658e-06, "epoch": 14.77997799779978, "percentage": 73.9, "elapsed_time": "5:17:54", "remaining_time": "1:52:16", "throughput": 1486.51, "total_tokens": 28354496} {"current_steps": 134355, "total_steps": 181800, "loss": 0.0015, "lr": 9.675882416047107e-06, "epoch": 14.78052805280528, "percentage": 73.9, "elapsed_time": "5:17:55", "remaining_time": "1:52:16", "throughput": 1486.52, "total_tokens": 28355616} {"current_steps": 134360, "total_steps": 181800, "loss": 0.0557, "lr": 9.673986168455598e-06, "epoch": 14.781078107810782, "percentage": 73.91, "elapsed_time": "5:17:55", "remaining_time": "1:52:15", "throughput": 1486.52, "total_tokens": 28356672} {"current_steps": 134365, "total_steps": 181800, "loss": 0.0039, "lr": 9.672090062116593e-06, "epoch": 14.781628162816281, "percentage": 73.91, "elapsed_time": "5:17:56", "remaining_time": "1:52:14", "throughput": 1486.53, "total_tokens": 28357792} {"current_steps": 134370, "total_steps": 181800, "loss": 0.005, "lr": 9.67019409704758e-06, "epoch": 14.782178217821782, "percentage": 73.91, "elapsed_time": "5:17:57", "remaining_time": "1:52:13", "throughput": 1486.53, "total_tokens": 28358880} {"current_steps": 134375, "total_steps": 181800, "loss": 0.0044, "lr": 9.66829827326604e-06, "epoch": 14.782728272827283, "percentage": 73.91, "elapsed_time": "5:17:57", "remaining_time": "1:52:13", "throughput": 1486.53, "total_tokens": 28359904} {"current_steps": 134380, "total_steps": 181800, "loss": 0.0194, "lr": 9.666402590789431e-06, "epoch": 14.783278327832782, "percentage": 73.92, "elapsed_time": "5:17:58", "remaining_time": "1:52:12", "throughput": 1486.53, "total_tokens": 28360992} {"current_steps": 134385, "total_steps": 181800, "loss": 0.0465, "lr": 9.664507049635237e-06, "epoch": 14.783828382838283, "percentage": 73.92, "elapsed_time": "5:17:59", "remaining_time": "1:52:11", "throughput": 1486.53, "total_tokens": 28361984} {"current_steps": 134390, "total_steps": 181800, "loss": 0.003, "lr": 9.662611649820915e-06, "epoch": 14.784378437843785, "percentage": 73.92, "elapsed_time": "5:17:59", "remaining_time": "1:52:11", "throughput": 1486.53, "total_tokens": 28362944} {"current_steps": 134395, "total_steps": 181800, "loss": 0.0947, "lr": 9.660716391363953e-06, "epoch": 14.784928492849286, "percentage": 73.92, "elapsed_time": "5:18:00", "remaining_time": "1:52:10", "throughput": 1486.53, "total_tokens": 28363936} {"current_steps": 134400, "total_steps": 181800, "loss": 0.0086, "lr": 9.658821274281798e-06, "epoch": 14.785478547854785, "percentage": 73.93, "elapsed_time": "5:18:01", "remaining_time": "1:52:09", "throughput": 1486.53, "total_tokens": 28364960} {"current_steps": 134405, "total_steps": 181800, "loss": 0.0034, "lr": 9.656926298591926e-06, "epoch": 14.786028602860286, "percentage": 73.93, "elapsed_time": "5:18:02", "remaining_time": "1:52:08", "throughput": 1486.53, "total_tokens": 28366016} {"current_steps": 134410, "total_steps": 181800, "loss": 0.0355, "lr": 9.65503146431181e-06, "epoch": 14.786578657865787, "percentage": 73.93, "elapsed_time": "5:18:02", "remaining_time": "1:52:08", "throughput": 1486.53, "total_tokens": 28367072} {"current_steps": 134415, "total_steps": 181800, "loss": 0.0048, "lr": 9.653136771458895e-06, "epoch": 14.787128712871286, "percentage": 73.94, "elapsed_time": "5:18:03", "remaining_time": "1:52:07", "throughput": 1486.53, "total_tokens": 28368128} {"current_steps": 134420, "total_steps": 181800, "loss": 0.0014, "lr": 9.651242220050666e-06, "epoch": 14.787678767876788, "percentage": 73.94, "elapsed_time": "5:18:04", "remaining_time": "1:52:06", "throughput": 1486.54, "total_tokens": 28369216} {"current_steps": 134425, "total_steps": 181800, "loss": 0.0015, "lr": 9.649347810104562e-06, "epoch": 14.788228822882289, "percentage": 73.94, "elapsed_time": "5:18:04", "remaining_time": "1:52:06", "throughput": 1486.54, "total_tokens": 28370336} {"current_steps": 134430, "total_steps": 181800, "loss": 0.0027, "lr": 9.647453541638054e-06, "epoch": 14.788778877887788, "percentage": 73.94, "elapsed_time": "5:18:05", "remaining_time": "1:52:05", "throughput": 1486.54, "total_tokens": 28371328} {"current_steps": 134435, "total_steps": 181800, "loss": 0.047, "lr": 9.645559414668609e-06, "epoch": 14.789328932893289, "percentage": 73.95, "elapsed_time": "5:18:06", "remaining_time": "1:52:04", "throughput": 1486.54, "total_tokens": 28372352} {"current_steps": 134440, "total_steps": 181800, "loss": 0.0052, "lr": 9.643665429213666e-06, "epoch": 14.78987898789879, "percentage": 73.95, "elapsed_time": "5:18:06", "remaining_time": "1:52:03", "throughput": 1486.54, "total_tokens": 28373376} {"current_steps": 134445, "total_steps": 181800, "loss": 0.0045, "lr": 9.641771585290699e-06, "epoch": 14.79042904290429, "percentage": 73.95, "elapsed_time": "5:18:07", "remaining_time": "1:52:03", "throughput": 1486.54, "total_tokens": 28374496} {"current_steps": 134450, "total_steps": 181800, "loss": 0.0297, "lr": 9.639877882917154e-06, "epoch": 14.79097909790979, "percentage": 73.95, "elapsed_time": "5:18:08", "remaining_time": "1:52:02", "throughput": 1486.54, "total_tokens": 28375456} {"current_steps": 134455, "total_steps": 181800, "loss": 0.031, "lr": 9.637984322110475e-06, "epoch": 14.791529152915292, "percentage": 73.96, "elapsed_time": "5:18:08", "remaining_time": "1:52:01", "throughput": 1486.54, "total_tokens": 28376448} {"current_steps": 134460, "total_steps": 181800, "loss": 0.0469, "lr": 9.636090902888121e-06, "epoch": 14.792079207920793, "percentage": 73.96, "elapsed_time": "5:18:09", "remaining_time": "1:52:00", "throughput": 1486.54, "total_tokens": 28377472} {"current_steps": 134465, "total_steps": 181800, "loss": 0.0042, "lr": 9.634197625267547e-06, "epoch": 14.792629262926292, "percentage": 73.96, "elapsed_time": "5:18:10", "remaining_time": "1:52:00", "throughput": 1486.54, "total_tokens": 28378528} {"current_steps": 134470, "total_steps": 181800, "loss": 0.1325, "lr": 9.632304489266209e-06, "epoch": 14.793179317931793, "percentage": 73.97, "elapsed_time": "5:18:11", "remaining_time": "1:51:59", "throughput": 1486.54, "total_tokens": 28379552} {"current_steps": 134475, "total_steps": 181800, "loss": 0.0018, "lr": 9.630411494901544e-06, "epoch": 14.793729372937294, "percentage": 73.97, "elapsed_time": "5:18:11", "remaining_time": "1:51:58", "throughput": 1486.54, "total_tokens": 28380544} {"current_steps": 134480, "total_steps": 181800, "loss": 0.0129, "lr": 9.628518642190996e-06, "epoch": 14.794279427942794, "percentage": 73.97, "elapsed_time": "5:18:12", "remaining_time": "1:51:58", "throughput": 1486.54, "total_tokens": 28381632} {"current_steps": 134485, "total_steps": 181800, "loss": 0.0034, "lr": 9.626625931152013e-06, "epoch": 14.794829482948295, "percentage": 73.97, "elapsed_time": "5:18:13", "remaining_time": "1:51:57", "throughput": 1486.54, "total_tokens": 28382720} {"current_steps": 134490, "total_steps": 181800, "loss": 0.0754, "lr": 9.624733361802044e-06, "epoch": 14.795379537953796, "percentage": 73.98, "elapsed_time": "5:18:13", "remaining_time": "1:51:56", "throughput": 1486.54, "total_tokens": 28383712} {"current_steps": 134495, "total_steps": 181800, "loss": 0.0046, "lr": 9.62284093415854e-06, "epoch": 14.795929592959295, "percentage": 73.98, "elapsed_time": "5:18:14", "remaining_time": "1:51:55", "throughput": 1486.54, "total_tokens": 28384736} {"current_steps": 134500, "total_steps": 181800, "loss": 0.0255, "lr": 9.620948648238928e-06, "epoch": 14.796479647964796, "percentage": 73.98, "elapsed_time": "5:18:15", "remaining_time": "1:51:55", "throughput": 1486.54, "total_tokens": 28385760} {"current_steps": 134505, "total_steps": 181800, "loss": 0.0013, "lr": 9.619056504060647e-06, "epoch": 14.797029702970297, "percentage": 73.99, "elapsed_time": "5:18:15", "remaining_time": "1:51:54", "throughput": 1486.54, "total_tokens": 28386816} {"current_steps": 134510, "total_steps": 181800, "loss": 0.0035, "lr": 9.61716450164115e-06, "epoch": 14.797579757975798, "percentage": 73.99, "elapsed_time": "5:18:16", "remaining_time": "1:51:53", "throughput": 1486.55, "total_tokens": 28387904} {"current_steps": 134515, "total_steps": 181800, "loss": 0.0419, "lr": 9.615272640997856e-06, "epoch": 14.798129812981298, "percentage": 73.99, "elapsed_time": "5:18:17", "remaining_time": "1:51:53", "throughput": 1486.54, "total_tokens": 28388896} {"current_steps": 134520, "total_steps": 181800, "loss": 0.0083, "lr": 9.613380922148212e-06, "epoch": 14.798679867986799, "percentage": 73.99, "elapsed_time": "5:18:17", "remaining_time": "1:51:52", "throughput": 1486.55, "total_tokens": 28389952} {"current_steps": 134525, "total_steps": 181800, "loss": 0.0049, "lr": 9.611489345109664e-06, "epoch": 14.7992299229923, "percentage": 74.0, "elapsed_time": "5:18:18", "remaining_time": "1:51:51", "throughput": 1486.55, "total_tokens": 28390976} {"current_steps": 134530, "total_steps": 181800, "loss": 0.004, "lr": 9.609597909899623e-06, "epoch": 14.7997799779978, "percentage": 74.0, "elapsed_time": "5:18:19", "remaining_time": "1:51:50", "throughput": 1486.55, "total_tokens": 28392160} {"current_steps": 134535, "total_steps": 181800, "loss": 0.1283, "lr": 9.607706616535544e-06, "epoch": 14.8003300330033, "percentage": 74.0, "elapsed_time": "5:18:19", "remaining_time": "1:51:50", "throughput": 1486.55, "total_tokens": 28393184} {"current_steps": 134540, "total_steps": 181800, "loss": 0.001, "lr": 9.605815465034837e-06, "epoch": 14.800880088008801, "percentage": 74.0, "elapsed_time": "5:18:20", "remaining_time": "1:51:49", "throughput": 1486.55, "total_tokens": 28394208} {"current_steps": 134545, "total_steps": 181800, "loss": 0.0302, "lr": 9.603924455414942e-06, "epoch": 14.8014301430143, "percentage": 74.01, "elapsed_time": "5:18:21", "remaining_time": "1:51:48", "throughput": 1486.56, "total_tokens": 28395264} {"current_steps": 134550, "total_steps": 181800, "loss": 0.1578, "lr": 9.6020335876933e-06, "epoch": 14.801980198019802, "percentage": 74.01, "elapsed_time": "5:18:22", "remaining_time": "1:51:48", "throughput": 1486.56, "total_tokens": 28396320} {"current_steps": 134555, "total_steps": 181800, "loss": 0.0218, "lr": 9.600142861887313e-06, "epoch": 14.802530253025303, "percentage": 74.01, "elapsed_time": "5:18:22", "remaining_time": "1:51:47", "throughput": 1486.56, "total_tokens": 28397376} {"current_steps": 134560, "total_steps": 181800, "loss": 0.046, "lr": 9.598252278014427e-06, "epoch": 14.803080308030804, "percentage": 74.02, "elapsed_time": "5:18:23", "remaining_time": "1:51:46", "throughput": 1486.56, "total_tokens": 28398400} {"current_steps": 134565, "total_steps": 181800, "loss": 0.0054, "lr": 9.596361836092063e-06, "epoch": 14.803630363036303, "percentage": 74.02, "elapsed_time": "5:18:24", "remaining_time": "1:51:45", "throughput": 1486.56, "total_tokens": 28399424} {"current_steps": 134570, "total_steps": 181800, "loss": 0.1904, "lr": 9.59447153613763e-06, "epoch": 14.804180418041804, "percentage": 74.02, "elapsed_time": "5:18:24", "remaining_time": "1:51:45", "throughput": 1486.56, "total_tokens": 28400480} {"current_steps": 134575, "total_steps": 181800, "loss": 0.0026, "lr": 9.59258137816856e-06, "epoch": 14.804730473047305, "percentage": 74.02, "elapsed_time": "5:18:25", "remaining_time": "1:51:44", "throughput": 1486.56, "total_tokens": 28401472} {"current_steps": 134580, "total_steps": 181800, "loss": 0.0474, "lr": 9.590691362202276e-06, "epoch": 14.805280528052805, "percentage": 74.03, "elapsed_time": "5:18:26", "remaining_time": "1:51:43", "throughput": 1486.56, "total_tokens": 28402560} {"current_steps": 134585, "total_steps": 181800, "loss": 0.002, "lr": 9.588801488256203e-06, "epoch": 14.805830583058306, "percentage": 74.03, "elapsed_time": "5:18:26", "remaining_time": "1:51:43", "throughput": 1486.56, "total_tokens": 28403584} {"current_steps": 134590, "total_steps": 181800, "loss": 0.0064, "lr": 9.586911756347753e-06, "epoch": 14.806380638063807, "percentage": 74.03, "elapsed_time": "5:18:27", "remaining_time": "1:51:42", "throughput": 1486.56, "total_tokens": 28404608} {"current_steps": 134595, "total_steps": 181800, "loss": 0.0508, "lr": 9.585022166494332e-06, "epoch": 14.806930693069306, "percentage": 74.03, "elapsed_time": "5:18:28", "remaining_time": "1:51:41", "throughput": 1486.56, "total_tokens": 28405632} {"current_steps": 134600, "total_steps": 181800, "loss": 0.0036, "lr": 9.583132718713372e-06, "epoch": 14.807480748074807, "percentage": 74.04, "elapsed_time": "5:18:28", "remaining_time": "1:51:40", "throughput": 1486.57, "total_tokens": 28406720} {"current_steps": 134605, "total_steps": 181800, "loss": 0.002, "lr": 9.581243413022264e-06, "epoch": 14.808030803080309, "percentage": 74.04, "elapsed_time": "5:18:29", "remaining_time": "1:51:40", "throughput": 1486.56, "total_tokens": 28407712} {"current_steps": 134610, "total_steps": 181800, "loss": 0.0055, "lr": 9.579354249438454e-06, "epoch": 14.808580858085808, "percentage": 74.04, "elapsed_time": "5:18:30", "remaining_time": "1:51:39", "throughput": 1486.56, "total_tokens": 28408704} {"current_steps": 134615, "total_steps": 181800, "loss": 0.0076, "lr": 9.577465227979338e-06, "epoch": 14.809130913091309, "percentage": 74.05, "elapsed_time": "5:18:31", "remaining_time": "1:51:38", "throughput": 1486.56, "total_tokens": 28409696} {"current_steps": 134620, "total_steps": 181800, "loss": 0.0784, "lr": 9.575576348662313e-06, "epoch": 14.80968096809681, "percentage": 74.05, "elapsed_time": "5:18:31", "remaining_time": "1:51:38", "throughput": 1486.56, "total_tokens": 28410816} {"current_steps": 134625, "total_steps": 181800, "loss": 0.0485, "lr": 9.573687611504812e-06, "epoch": 14.810231023102311, "percentage": 74.05, "elapsed_time": "5:18:32", "remaining_time": "1:51:37", "throughput": 1486.57, "total_tokens": 28411872} {"current_steps": 134630, "total_steps": 181800, "loss": 0.0035, "lr": 9.57179901652422e-06, "epoch": 14.81078107810781, "percentage": 74.05, "elapsed_time": "5:18:33", "remaining_time": "1:51:36", "throughput": 1486.57, "total_tokens": 28412896} {"current_steps": 134635, "total_steps": 181800, "loss": 0.0123, "lr": 9.569910563737949e-06, "epoch": 14.811331133113312, "percentage": 74.06, "elapsed_time": "5:18:33", "remaining_time": "1:51:35", "throughput": 1486.57, "total_tokens": 28413984} {"current_steps": 134640, "total_steps": 181800, "loss": 0.012, "lr": 9.568022253163422e-06, "epoch": 14.811881188118813, "percentage": 74.06, "elapsed_time": "5:18:34", "remaining_time": "1:51:35", "throughput": 1486.57, "total_tokens": 28415040} {"current_steps": 134645, "total_steps": 181800, "loss": 0.0096, "lr": 9.566134084818018e-06, "epoch": 14.812431243124312, "percentage": 74.06, "elapsed_time": "5:18:35", "remaining_time": "1:51:34", "throughput": 1486.57, "total_tokens": 28416032} {"current_steps": 134650, "total_steps": 181800, "loss": 0.0276, "lr": 9.56424605871916e-06, "epoch": 14.812981298129813, "percentage": 74.06, "elapsed_time": "5:18:35", "remaining_time": "1:51:33", "throughput": 1486.57, "total_tokens": 28417088} {"current_steps": 134655, "total_steps": 181800, "loss": 0.0152, "lr": 9.562358174884228e-06, "epoch": 14.813531353135314, "percentage": 74.07, "elapsed_time": "5:18:36", "remaining_time": "1:51:33", "throughput": 1486.57, "total_tokens": 28418176} {"current_steps": 134660, "total_steps": 181800, "loss": 0.0052, "lr": 9.560470433330645e-06, "epoch": 14.814081408140813, "percentage": 74.07, "elapsed_time": "5:18:37", "remaining_time": "1:51:32", "throughput": 1486.57, "total_tokens": 28419168} {"current_steps": 134665, "total_steps": 181800, "loss": 0.0068, "lr": 9.558582834075785e-06, "epoch": 14.814631463146315, "percentage": 74.07, "elapsed_time": "5:18:37", "remaining_time": "1:51:31", "throughput": 1486.57, "total_tokens": 28420160} {"current_steps": 134670, "total_steps": 181800, "loss": 0.002, "lr": 9.556695377137062e-06, "epoch": 14.815181518151816, "percentage": 74.08, "elapsed_time": "5:18:38", "remaining_time": "1:51:30", "throughput": 1486.57, "total_tokens": 28421216} {"current_steps": 134675, "total_steps": 181800, "loss": 0.0006, "lr": 9.554808062531873e-06, "epoch": 14.815731573157315, "percentage": 74.08, "elapsed_time": "5:18:39", "remaining_time": "1:51:30", "throughput": 1486.58, "total_tokens": 28422336} {"current_steps": 134680, "total_steps": 181800, "loss": 0.0299, "lr": 9.5529208902776e-06, "epoch": 14.816281628162816, "percentage": 74.08, "elapsed_time": "5:18:40", "remaining_time": "1:51:29", "throughput": 1486.58, "total_tokens": 28423424} {"current_steps": 134685, "total_steps": 181800, "loss": 0.0442, "lr": 9.55103386039165e-06, "epoch": 14.816831683168317, "percentage": 74.08, "elapsed_time": "5:18:40", "remaining_time": "1:51:28", "throughput": 1486.58, "total_tokens": 28424512} {"current_steps": 134690, "total_steps": 181800, "loss": 0.0032, "lr": 9.549146972891398e-06, "epoch": 14.817381738173818, "percentage": 74.09, "elapsed_time": "5:18:41", "remaining_time": "1:51:28", "throughput": 1486.58, "total_tokens": 28425536} {"current_steps": 134695, "total_steps": 181800, "loss": 0.0069, "lr": 9.547260227794247e-06, "epoch": 14.817931793179318, "percentage": 74.09, "elapsed_time": "5:18:42", "remaining_time": "1:51:27", "throughput": 1486.59, "total_tokens": 28426624} {"current_steps": 134700, "total_steps": 181800, "loss": 0.0669, "lr": 9.54537362511759e-06, "epoch": 14.818481848184819, "percentage": 74.09, "elapsed_time": "5:18:42", "remaining_time": "1:51:26", "throughput": 1486.59, "total_tokens": 28427648} {"current_steps": 134705, "total_steps": 181800, "loss": 0.1006, "lr": 9.543487164878802e-06, "epoch": 14.81903190319032, "percentage": 74.1, "elapsed_time": "5:18:43", "remaining_time": "1:51:25", "throughput": 1486.59, "total_tokens": 28428704} {"current_steps": 134710, "total_steps": 181800, "loss": 0.0077, "lr": 9.541600847095284e-06, "epoch": 14.819581958195819, "percentage": 74.1, "elapsed_time": "5:18:44", "remaining_time": "1:51:25", "throughput": 1486.59, "total_tokens": 28429824} {"current_steps": 134715, "total_steps": 181800, "loss": 0.0894, "lr": 9.539714671784413e-06, "epoch": 14.82013201320132, "percentage": 74.1, "elapsed_time": "5:18:44", "remaining_time": "1:51:24", "throughput": 1486.59, "total_tokens": 28430880} {"current_steps": 134720, "total_steps": 181800, "loss": 0.0038, "lr": 9.537828638963556e-06, "epoch": 14.820682068206821, "percentage": 74.1, "elapsed_time": "5:18:45", "remaining_time": "1:51:23", "throughput": 1486.6, "total_tokens": 28431968} {"current_steps": 134725, "total_steps": 181800, "loss": 0.0031, "lr": 9.53594274865013e-06, "epoch": 14.82123212321232, "percentage": 74.11, "elapsed_time": "5:18:46", "remaining_time": "1:51:23", "throughput": 1486.6, "total_tokens": 28433024} {"current_steps": 134730, "total_steps": 181800, "loss": 0.0016, "lr": 9.53405700086149e-06, "epoch": 14.821782178217822, "percentage": 74.11, "elapsed_time": "5:18:46", "remaining_time": "1:51:22", "throughput": 1486.6, "total_tokens": 28434080} {"current_steps": 134735, "total_steps": 181800, "loss": 0.0503, "lr": 9.532171395615036e-06, "epoch": 14.822332233223323, "percentage": 74.11, "elapsed_time": "5:18:47", "remaining_time": "1:51:21", "throughput": 1486.6, "total_tokens": 28435168} {"current_steps": 134740, "total_steps": 181800, "loss": 0.0076, "lr": 9.530285932928134e-06, "epoch": 14.822882288228822, "percentage": 74.11, "elapsed_time": "5:18:48", "remaining_time": "1:51:20", "throughput": 1486.61, "total_tokens": 28436224} {"current_steps": 134745, "total_steps": 181800, "loss": 0.0199, "lr": 9.528400612818156e-06, "epoch": 14.823432343234323, "percentage": 74.12, "elapsed_time": "5:18:48", "remaining_time": "1:51:20", "throughput": 1486.61, "total_tokens": 28437312} {"current_steps": 134750, "total_steps": 181800, "loss": 0.0752, "lr": 9.526515435302485e-06, "epoch": 14.823982398239824, "percentage": 74.12, "elapsed_time": "5:18:49", "remaining_time": "1:51:19", "throughput": 1486.61, "total_tokens": 28438400} {"current_steps": 134755, "total_steps": 181800, "loss": 0.0043, "lr": 9.524630400398504e-06, "epoch": 14.824532453245325, "percentage": 74.12, "elapsed_time": "5:18:50", "remaining_time": "1:51:18", "throughput": 1486.61, "total_tokens": 28439488} {"current_steps": 134760, "total_steps": 181800, "loss": 0.0031, "lr": 9.522745508123573e-06, "epoch": 14.825082508250825, "percentage": 74.13, "elapsed_time": "5:18:51", "remaining_time": "1:51:17", "throughput": 1486.62, "total_tokens": 28440576} {"current_steps": 134765, "total_steps": 181800, "loss": 0.0525, "lr": 9.520860758495076e-06, "epoch": 14.825632563256326, "percentage": 74.13, "elapsed_time": "5:18:51", "remaining_time": "1:51:17", "throughput": 1486.62, "total_tokens": 28441632} {"current_steps": 134770, "total_steps": 181800, "loss": 0.0544, "lr": 9.51897615153037e-06, "epoch": 14.826182618261827, "percentage": 74.13, "elapsed_time": "5:18:52", "remaining_time": "1:51:16", "throughput": 1486.62, "total_tokens": 28442720} {"current_steps": 134775, "total_steps": 181800, "loss": 0.0114, "lr": 9.517091687246842e-06, "epoch": 14.826732673267326, "percentage": 74.13, "elapsed_time": "5:18:53", "remaining_time": "1:51:15", "throughput": 1486.62, "total_tokens": 28443744} {"current_steps": 134780, "total_steps": 181800, "loss": 0.0133, "lr": 9.51520736566184e-06, "epoch": 14.827282728272827, "percentage": 74.14, "elapsed_time": "5:18:53", "remaining_time": "1:51:15", "throughput": 1486.63, "total_tokens": 28444800} {"current_steps": 134785, "total_steps": 181800, "loss": 0.009, "lr": 9.513323186792744e-06, "epoch": 14.827832783278328, "percentage": 74.14, "elapsed_time": "5:18:54", "remaining_time": "1:51:14", "throughput": 1486.63, "total_tokens": 28445856} {"current_steps": 134790, "total_steps": 181800, "loss": 0.002, "lr": 9.511439150656922e-06, "epoch": 14.828382838283828, "percentage": 74.14, "elapsed_time": "5:18:55", "remaining_time": "1:51:13", "throughput": 1486.61, "total_tokens": 28446912} {"current_steps": 134795, "total_steps": 181800, "loss": 0.0067, "lr": 9.509555257271728e-06, "epoch": 14.828932893289329, "percentage": 74.14, "elapsed_time": "5:18:56", "remaining_time": "1:51:13", "throughput": 1486.61, "total_tokens": 28447936} {"current_steps": 134800, "total_steps": 181800, "loss": 0.0318, "lr": 9.507671506654536e-06, "epoch": 14.82948294829483, "percentage": 74.15, "elapsed_time": "5:18:56", "remaining_time": "1:51:12", "throughput": 1486.62, "total_tokens": 28449024} {"current_steps": 134805, "total_steps": 181800, "loss": 0.1027, "lr": 9.505787898822696e-06, "epoch": 14.83003300330033, "percentage": 74.15, "elapsed_time": "5:18:57", "remaining_time": "1:51:11", "throughput": 1486.62, "total_tokens": 28450048} {"current_steps": 134810, "total_steps": 181800, "loss": 0.0014, "lr": 9.503904433793573e-06, "epoch": 14.83058305830583, "percentage": 74.15, "elapsed_time": "5:18:58", "remaining_time": "1:51:10", "throughput": 1486.62, "total_tokens": 28451104} {"current_steps": 134815, "total_steps": 181800, "loss": 0.0153, "lr": 9.502021111584533e-06, "epoch": 14.831133113311331, "percentage": 74.16, "elapsed_time": "5:18:58", "remaining_time": "1:51:10", "throughput": 1486.62, "total_tokens": 28452128} {"current_steps": 134820, "total_steps": 181800, "loss": 0.0232, "lr": 9.500137932212922e-06, "epoch": 14.831683168316832, "percentage": 74.16, "elapsed_time": "5:18:59", "remaining_time": "1:51:09", "throughput": 1486.62, "total_tokens": 28453184} {"current_steps": 134825, "total_steps": 181800, "loss": 0.0523, "lr": 9.49825489569611e-06, "epoch": 14.832233223322332, "percentage": 74.16, "elapsed_time": "5:19:00", "remaining_time": "1:51:08", "throughput": 1486.62, "total_tokens": 28454304} {"current_steps": 134830, "total_steps": 181800, "loss": 0.0026, "lr": 9.496372002051446e-06, "epoch": 14.832783278327833, "percentage": 74.16, "elapsed_time": "5:19:00", "remaining_time": "1:51:08", "throughput": 1486.63, "total_tokens": 28455360} {"current_steps": 134835, "total_steps": 181800, "loss": 0.0022, "lr": 9.494489251296271e-06, "epoch": 14.833333333333334, "percentage": 74.17, "elapsed_time": "5:19:01", "remaining_time": "1:51:07", "throughput": 1486.62, "total_tokens": 28456352} {"current_steps": 134840, "total_steps": 181800, "loss": 0.0204, "lr": 9.49260664344795e-06, "epoch": 14.833883388338833, "percentage": 74.17, "elapsed_time": "5:19:02", "remaining_time": "1:51:06", "throughput": 1486.63, "total_tokens": 28457440} {"current_steps": 134845, "total_steps": 181800, "loss": 0.0796, "lr": 9.49072417852383e-06, "epoch": 14.834433443344334, "percentage": 74.17, "elapsed_time": "5:19:02", "remaining_time": "1:51:05", "throughput": 1486.63, "total_tokens": 28458432} {"current_steps": 134850, "total_steps": 181800, "loss": 0.003, "lr": 9.488841856541272e-06, "epoch": 14.834983498349835, "percentage": 74.17, "elapsed_time": "5:19:03", "remaining_time": "1:51:05", "throughput": 1486.63, "total_tokens": 28459552} {"current_steps": 134855, "total_steps": 181800, "loss": 0.0026, "lr": 9.486959677517618e-06, "epoch": 14.835533553355335, "percentage": 74.18, "elapsed_time": "5:19:04", "remaining_time": "1:51:04", "throughput": 1486.63, "total_tokens": 28460608} {"current_steps": 134860, "total_steps": 181800, "loss": 0.048, "lr": 9.485077641470203e-06, "epoch": 14.836083608360836, "percentage": 74.18, "elapsed_time": "5:19:05", "remaining_time": "1:51:03", "throughput": 1486.64, "total_tokens": 28461696} {"current_steps": 134865, "total_steps": 181800, "loss": 0.0106, "lr": 9.483195748416381e-06, "epoch": 14.836633663366337, "percentage": 74.18, "elapsed_time": "5:19:05", "remaining_time": "1:51:02", "throughput": 1486.64, "total_tokens": 28462784} {"current_steps": 134870, "total_steps": 181800, "loss": 0.0906, "lr": 9.4813139983735e-06, "epoch": 14.837183718371836, "percentage": 74.19, "elapsed_time": "5:19:06", "remaining_time": "1:51:02", "throughput": 1486.64, "total_tokens": 28463872} {"current_steps": 134875, "total_steps": 181800, "loss": 0.0499, "lr": 9.479432391358909e-06, "epoch": 14.837733773377337, "percentage": 74.19, "elapsed_time": "5:19:07", "remaining_time": "1:51:01", "throughput": 1486.65, "total_tokens": 28464992} {"current_steps": 134880, "total_steps": 181800, "loss": 0.1041, "lr": 9.477550927389942e-06, "epoch": 14.838283828382838, "percentage": 74.19, "elapsed_time": "5:19:07", "remaining_time": "1:51:00", "throughput": 1486.65, "total_tokens": 28466048} {"current_steps": 134885, "total_steps": 181800, "loss": 0.0155, "lr": 9.475669606483933e-06, "epoch": 14.83883388338834, "percentage": 74.19, "elapsed_time": "5:19:08", "remaining_time": "1:51:00", "throughput": 1486.65, "total_tokens": 28467168} {"current_steps": 134890, "total_steps": 181800, "loss": 0.0049, "lr": 9.473788428658234e-06, "epoch": 14.839383938393839, "percentage": 74.2, "elapsed_time": "5:19:09", "remaining_time": "1:50:59", "throughput": 1486.66, "total_tokens": 28468224} {"current_steps": 134895, "total_steps": 181800, "loss": 0.0053, "lr": 9.471907393930171e-06, "epoch": 14.83993399339934, "percentage": 74.2, "elapsed_time": "5:19:09", "remaining_time": "1:50:58", "throughput": 1486.66, "total_tokens": 28469280} {"current_steps": 134900, "total_steps": 181800, "loss": 0.006, "lr": 9.470026502317084e-06, "epoch": 14.840484048404841, "percentage": 74.2, "elapsed_time": "5:19:10", "remaining_time": "1:50:57", "throughput": 1486.66, "total_tokens": 28470336} {"current_steps": 134905, "total_steps": 181800, "loss": 0.0072, "lr": 9.468145753836319e-06, "epoch": 14.84103410341034, "percentage": 74.21, "elapsed_time": "5:19:11", "remaining_time": "1:50:57", "throughput": 1486.66, "total_tokens": 28471360} {"current_steps": 134910, "total_steps": 181800, "loss": 0.01, "lr": 9.466265148505196e-06, "epoch": 14.841584158415841, "percentage": 74.21, "elapsed_time": "5:19:11", "remaining_time": "1:50:56", "throughput": 1486.66, "total_tokens": 28472384} {"current_steps": 134915, "total_steps": 181800, "loss": 0.0026, "lr": 9.46438468634106e-06, "epoch": 14.842134213421343, "percentage": 74.21, "elapsed_time": "5:19:12", "remaining_time": "1:50:55", "throughput": 1486.66, "total_tokens": 28473408} {"current_steps": 134920, "total_steps": 181800, "loss": 0.0013, "lr": 9.462504367361227e-06, "epoch": 14.842684268426842, "percentage": 74.21, "elapsed_time": "5:19:13", "remaining_time": "1:50:55", "throughput": 1486.66, "total_tokens": 28474464} {"current_steps": 134925, "total_steps": 181800, "loss": 0.018, "lr": 9.460624191583036e-06, "epoch": 14.843234323432343, "percentage": 74.22, "elapsed_time": "5:19:13", "remaining_time": "1:50:54", "throughput": 1486.66, "total_tokens": 28475520} {"current_steps": 134930, "total_steps": 181800, "loss": 0.0896, "lr": 9.458744159023824e-06, "epoch": 14.843784378437844, "percentage": 74.22, "elapsed_time": "5:19:14", "remaining_time": "1:50:53", "throughput": 1486.66, "total_tokens": 28476544} {"current_steps": 134935, "total_steps": 181800, "loss": 0.0414, "lr": 9.456864269700899e-06, "epoch": 14.844334433443345, "percentage": 74.22, "elapsed_time": "5:19:15", "remaining_time": "1:50:52", "throughput": 1486.66, "total_tokens": 28477536} {"current_steps": 134940, "total_steps": 181800, "loss": 0.0526, "lr": 9.45498452363161e-06, "epoch": 14.844884488448844, "percentage": 74.22, "elapsed_time": "5:19:16", "remaining_time": "1:50:52", "throughput": 1486.66, "total_tokens": 28478656} {"current_steps": 134945, "total_steps": 181800, "loss": 0.0877, "lr": 9.453104920833266e-06, "epoch": 14.845434543454346, "percentage": 74.23, "elapsed_time": "5:19:16", "remaining_time": "1:50:51", "throughput": 1486.67, "total_tokens": 28479744} {"current_steps": 134950, "total_steps": 181800, "loss": 0.001, "lr": 9.451225461323188e-06, "epoch": 14.845984598459847, "percentage": 74.23, "elapsed_time": "5:19:17", "remaining_time": "1:50:50", "throughput": 1486.67, "total_tokens": 28480832} {"current_steps": 134955, "total_steps": 181800, "loss": 0.0761, "lr": 9.449346145118704e-06, "epoch": 14.846534653465346, "percentage": 74.23, "elapsed_time": "5:19:18", "remaining_time": "1:50:50", "throughput": 1486.67, "total_tokens": 28481920} {"current_steps": 134960, "total_steps": 181800, "loss": 0.062, "lr": 9.447466972237132e-06, "epoch": 14.847084708470847, "percentage": 74.24, "elapsed_time": "5:19:18", "remaining_time": "1:50:49", "throughput": 1486.68, "total_tokens": 28483008} {"current_steps": 134965, "total_steps": 181800, "loss": 0.047, "lr": 9.445587942695806e-06, "epoch": 14.847634763476348, "percentage": 74.24, "elapsed_time": "5:19:19", "remaining_time": "1:50:48", "throughput": 1486.68, "total_tokens": 28484128} {"current_steps": 134970, "total_steps": 181800, "loss": 0.0067, "lr": 9.44370905651203e-06, "epoch": 14.848184818481847, "percentage": 74.24, "elapsed_time": "5:19:20", "remaining_time": "1:50:47", "throughput": 1486.68, "total_tokens": 28485184} {"current_steps": 134975, "total_steps": 181800, "loss": 0.026, "lr": 9.441830313703113e-06, "epoch": 14.848734873487349, "percentage": 74.24, "elapsed_time": "5:19:20", "remaining_time": "1:50:47", "throughput": 1486.68, "total_tokens": 28486208} {"current_steps": 134980, "total_steps": 181800, "loss": 0.0946, "lr": 9.439951714286383e-06, "epoch": 14.84928492849285, "percentage": 74.25, "elapsed_time": "5:19:21", "remaining_time": "1:50:46", "throughput": 1486.69, "total_tokens": 28487264} {"current_steps": 134985, "total_steps": 181800, "loss": 0.0017, "lr": 9.438073258279151e-06, "epoch": 14.84983498349835, "percentage": 74.25, "elapsed_time": "5:19:22", "remaining_time": "1:50:45", "throughput": 1486.69, "total_tokens": 28488288} {"current_steps": 134990, "total_steps": 181800, "loss": 0.0391, "lr": 9.436194945698736e-06, "epoch": 14.85038503850385, "percentage": 74.25, "elapsed_time": "5:19:22", "remaining_time": "1:50:45", "throughput": 1486.68, "total_tokens": 28489248} {"current_steps": 134995, "total_steps": 181800, "loss": 0.0812, "lr": 9.43431677656245e-06, "epoch": 14.850935093509351, "percentage": 74.25, "elapsed_time": "5:19:23", "remaining_time": "1:50:44", "throughput": 1486.68, "total_tokens": 28490304} {"current_steps": 135000, "total_steps": 181800, "loss": 0.0349, "lr": 9.432438750887584e-06, "epoch": 14.851485148514852, "percentage": 74.26, "elapsed_time": "5:19:24", "remaining_time": "1:50:43", "throughput": 1486.69, "total_tokens": 28491360} {"current_steps": 135005, "total_steps": 181800, "loss": 0.1142, "lr": 9.430560868691468e-06, "epoch": 14.852035203520352, "percentage": 74.26, "elapsed_time": "5:19:25", "remaining_time": "1:50:42", "throughput": 1486.69, "total_tokens": 28492416} {"current_steps": 135010, "total_steps": 181800, "loss": 0.0091, "lr": 9.428683129991395e-06, "epoch": 14.852585258525853, "percentage": 74.26, "elapsed_time": "5:19:25", "remaining_time": "1:50:42", "throughput": 1486.69, "total_tokens": 28493504} {"current_steps": 135015, "total_steps": 181800, "loss": 0.1254, "lr": 9.426805534804678e-06, "epoch": 14.853135313531354, "percentage": 74.27, "elapsed_time": "5:19:26", "remaining_time": "1:50:41", "throughput": 1486.7, "total_tokens": 28494656} {"current_steps": 135020, "total_steps": 181800, "loss": 0.0563, "lr": 9.424928083148629e-06, "epoch": 14.853685368536853, "percentage": 74.27, "elapsed_time": "5:19:27", "remaining_time": "1:50:40", "throughput": 1486.7, "total_tokens": 28495744} {"current_steps": 135025, "total_steps": 181800, "loss": 0.0819, "lr": 9.423050775040537e-06, "epoch": 14.854235423542354, "percentage": 74.27, "elapsed_time": "5:19:27", "remaining_time": "1:50:40", "throughput": 1486.7, "total_tokens": 28496832} {"current_steps": 135030, "total_steps": 181800, "loss": 0.0393, "lr": 9.42117361049772e-06, "epoch": 14.854785478547855, "percentage": 74.27, "elapsed_time": "5:19:28", "remaining_time": "1:50:39", "throughput": 1486.7, "total_tokens": 28497888} {"current_steps": 135035, "total_steps": 181800, "loss": 0.0121, "lr": 9.419296589537461e-06, "epoch": 14.855335533553355, "percentage": 74.28, "elapsed_time": "5:19:29", "remaining_time": "1:50:38", "throughput": 1486.71, "total_tokens": 28498944} {"current_steps": 135040, "total_steps": 181800, "loss": 0.0021, "lr": 9.41741971217707e-06, "epoch": 14.855885588558856, "percentage": 74.28, "elapsed_time": "5:19:29", "remaining_time": "1:50:37", "throughput": 1486.71, "total_tokens": 28499968} {"current_steps": 135045, "total_steps": 181800, "loss": 0.004, "lr": 9.415542978433851e-06, "epoch": 14.856435643564357, "percentage": 74.28, "elapsed_time": "5:19:30", "remaining_time": "1:50:37", "throughput": 1486.71, "total_tokens": 28501024} {"current_steps": 135050, "total_steps": 181800, "loss": 0.0027, "lr": 9.413666388325087e-06, "epoch": 14.856985698569858, "percentage": 74.28, "elapsed_time": "5:19:31", "remaining_time": "1:50:36", "throughput": 1486.71, "total_tokens": 28502112} {"current_steps": 135055, "total_steps": 181800, "loss": 0.0594, "lr": 9.411789941868088e-06, "epoch": 14.857535753575357, "percentage": 74.29, "elapsed_time": "5:19:31", "remaining_time": "1:50:35", "throughput": 1486.71, "total_tokens": 28503168} {"current_steps": 135060, "total_steps": 181800, "loss": 0.065, "lr": 9.409913639080135e-06, "epoch": 14.858085808580858, "percentage": 74.29, "elapsed_time": "5:19:32", "remaining_time": "1:50:35", "throughput": 1486.71, "total_tokens": 28504224} {"current_steps": 135065, "total_steps": 181800, "loss": 0.0037, "lr": 9.408037479978534e-06, "epoch": 14.85863586358636, "percentage": 74.29, "elapsed_time": "5:19:33", "remaining_time": "1:50:34", "throughput": 1486.72, "total_tokens": 28505312} {"current_steps": 135070, "total_steps": 181800, "loss": 0.0029, "lr": 9.406161464580563e-06, "epoch": 14.859185918591859, "percentage": 74.3, "elapsed_time": "5:19:34", "remaining_time": "1:50:33", "throughput": 1486.72, "total_tokens": 28506400} {"current_steps": 135075, "total_steps": 181800, "loss": 0.0094, "lr": 9.404285592903517e-06, "epoch": 14.85973597359736, "percentage": 74.3, "elapsed_time": "5:19:34", "remaining_time": "1:50:32", "throughput": 1486.72, "total_tokens": 28507424} {"current_steps": 135080, "total_steps": 181800, "loss": 0.0315, "lr": 9.402409864964695e-06, "epoch": 14.86028602860286, "percentage": 74.3, "elapsed_time": "5:19:35", "remaining_time": "1:50:32", "throughput": 1486.72, "total_tokens": 28508416} {"current_steps": 135085, "total_steps": 181800, "loss": 0.0019, "lr": 9.40053428078137e-06, "epoch": 14.86083608360836, "percentage": 74.3, "elapsed_time": "5:19:36", "remaining_time": "1:50:31", "throughput": 1486.72, "total_tokens": 28509472} {"current_steps": 135090, "total_steps": 181800, "loss": 0.0027, "lr": 9.398658840370844e-06, "epoch": 14.861386138613861, "percentage": 74.31, "elapsed_time": "5:19:36", "remaining_time": "1:50:30", "throughput": 1486.72, "total_tokens": 28510496} {"current_steps": 135095, "total_steps": 181800, "loss": 0.0027, "lr": 9.396783543750384e-06, "epoch": 14.861936193619362, "percentage": 74.31, "elapsed_time": "5:19:37", "remaining_time": "1:50:30", "throughput": 1486.73, "total_tokens": 28511616} {"current_steps": 135100, "total_steps": 181800, "loss": 0.0313, "lr": 9.394908390937282e-06, "epoch": 14.862486248624862, "percentage": 74.31, "elapsed_time": "5:19:38", "remaining_time": "1:50:29", "throughput": 1486.73, "total_tokens": 28512672} {"current_steps": 135105, "total_steps": 181800, "loss": 0.2129, "lr": 9.393033381948831e-06, "epoch": 14.863036303630363, "percentage": 74.32, "elapsed_time": "5:19:38", "remaining_time": "1:50:28", "throughput": 1486.73, "total_tokens": 28513696} {"current_steps": 135110, "total_steps": 181800, "loss": 0.0007, "lr": 9.391158516802295e-06, "epoch": 14.863586358635864, "percentage": 74.32, "elapsed_time": "5:19:39", "remaining_time": "1:50:27", "throughput": 1486.73, "total_tokens": 28514752} {"current_steps": 135115, "total_steps": 181800, "loss": 0.0193, "lr": 9.389283795514967e-06, "epoch": 14.864136413641365, "percentage": 74.32, "elapsed_time": "5:19:40", "remaining_time": "1:50:27", "throughput": 1486.74, "total_tokens": 28515936} {"current_steps": 135120, "total_steps": 181800, "loss": 0.0573, "lr": 9.38740921810412e-06, "epoch": 14.864686468646864, "percentage": 74.32, "elapsed_time": "5:19:40", "remaining_time": "1:50:26", "throughput": 1486.74, "total_tokens": 28516992} {"current_steps": 135125, "total_steps": 181800, "loss": 0.0023, "lr": 9.385534784587025e-06, "epoch": 14.865236523652365, "percentage": 74.33, "elapsed_time": "5:19:41", "remaining_time": "1:50:25", "throughput": 1486.74, "total_tokens": 28518016} {"current_steps": 135130, "total_steps": 181800, "loss": 0.0107, "lr": 9.383660494980962e-06, "epoch": 14.865786578657866, "percentage": 74.33, "elapsed_time": "5:19:42", "remaining_time": "1:50:25", "throughput": 1486.74, "total_tokens": 28519072} {"current_steps": 135135, "total_steps": 181800, "loss": 0.0558, "lr": 9.381786349303212e-06, "epoch": 14.866336633663366, "percentage": 74.33, "elapsed_time": "5:19:42", "remaining_time": "1:50:24", "throughput": 1486.74, "total_tokens": 28520128} {"current_steps": 135140, "total_steps": 181800, "loss": 0.0034, "lr": 9.379912347571038e-06, "epoch": 14.866886688668867, "percentage": 74.33, "elapsed_time": "5:19:43", "remaining_time": "1:50:23", "throughput": 1486.74, "total_tokens": 28521216} {"current_steps": 135145, "total_steps": 181800, "loss": 0.1033, "lr": 9.378038489801724e-06, "epoch": 14.867436743674368, "percentage": 74.34, "elapsed_time": "5:19:44", "remaining_time": "1:50:22", "throughput": 1486.75, "total_tokens": 28522336} {"current_steps": 135150, "total_steps": 181800, "loss": 0.0664, "lr": 9.376164776012524e-06, "epoch": 14.867986798679867, "percentage": 74.34, "elapsed_time": "5:19:45", "remaining_time": "1:50:22", "throughput": 1486.75, "total_tokens": 28523360} {"current_steps": 135155, "total_steps": 181800, "loss": 0.0029, "lr": 9.374291206220718e-06, "epoch": 14.868536853685368, "percentage": 74.34, "elapsed_time": "5:19:45", "remaining_time": "1:50:21", "throughput": 1486.75, "total_tokens": 28524416} {"current_steps": 135160, "total_steps": 181800, "loss": 0.0103, "lr": 9.37241778044358e-06, "epoch": 14.86908690869087, "percentage": 74.35, "elapsed_time": "5:19:46", "remaining_time": "1:50:20", "throughput": 1486.75, "total_tokens": 28525504} {"current_steps": 135165, "total_steps": 181800, "loss": 0.0057, "lr": 9.370544498698359e-06, "epoch": 14.869636963696369, "percentage": 74.35, "elapsed_time": "5:19:47", "remaining_time": "1:50:19", "throughput": 1486.75, "total_tokens": 28526528} {"current_steps": 135170, "total_steps": 181800, "loss": 0.2002, "lr": 9.368671361002338e-06, "epoch": 14.87018701870187, "percentage": 74.35, "elapsed_time": "5:19:47", "remaining_time": "1:50:19", "throughput": 1486.76, "total_tokens": 28527616} {"current_steps": 135175, "total_steps": 181800, "loss": 0.012, "lr": 9.366798367372764e-06, "epoch": 14.870737073707371, "percentage": 74.35, "elapsed_time": "5:19:48", "remaining_time": "1:50:18", "throughput": 1486.76, "total_tokens": 28528640} {"current_steps": 135180, "total_steps": 181800, "loss": 0.0659, "lr": 9.364925517826917e-06, "epoch": 14.871287128712872, "percentage": 74.36, "elapsed_time": "5:19:49", "remaining_time": "1:50:17", "throughput": 1486.76, "total_tokens": 28529696} {"current_steps": 135185, "total_steps": 181800, "loss": 0.0052, "lr": 9.36305281238204e-06, "epoch": 14.871837183718371, "percentage": 74.36, "elapsed_time": "5:19:49", "remaining_time": "1:50:17", "throughput": 1486.76, "total_tokens": 28530720} {"current_steps": 135190, "total_steps": 181800, "loss": 0.002, "lr": 9.361180251055402e-06, "epoch": 14.872387238723872, "percentage": 74.36, "elapsed_time": "5:19:50", "remaining_time": "1:50:16", "throughput": 1486.76, "total_tokens": 28531776} {"current_steps": 135195, "total_steps": 181800, "loss": 0.019, "lr": 9.35930783386427e-06, "epoch": 14.872937293729374, "percentage": 74.36, "elapsed_time": "5:19:51", "remaining_time": "1:50:15", "throughput": 1486.76, "total_tokens": 28532800} {"current_steps": 135200, "total_steps": 181800, "loss": 0.0066, "lr": 9.357435560825883e-06, "epoch": 14.873487348734873, "percentage": 74.37, "elapsed_time": "5:19:51", "remaining_time": "1:50:14", "throughput": 1486.76, "total_tokens": 28533824} {"current_steps": 135205, "total_steps": 181800, "loss": 0.0338, "lr": 9.355563431957517e-06, "epoch": 14.874037403740374, "percentage": 74.37, "elapsed_time": "5:19:52", "remaining_time": "1:50:14", "throughput": 1486.76, "total_tokens": 28534912} {"current_steps": 135210, "total_steps": 181800, "loss": 0.0038, "lr": 9.353691447276409e-06, "epoch": 14.874587458745875, "percentage": 74.37, "elapsed_time": "5:19:53", "remaining_time": "1:50:13", "throughput": 1486.77, "total_tokens": 28536000} {"current_steps": 135215, "total_steps": 181800, "loss": 0.0086, "lr": 9.351819606799814e-06, "epoch": 14.875137513751374, "percentage": 74.38, "elapsed_time": "5:19:54", "remaining_time": "1:50:12", "throughput": 1486.77, "total_tokens": 28537088} {"current_steps": 135220, "total_steps": 181800, "loss": 0.0738, "lr": 9.349947910545001e-06, "epoch": 14.875687568756875, "percentage": 74.38, "elapsed_time": "5:19:54", "remaining_time": "1:50:12", "throughput": 1486.77, "total_tokens": 28538176} {"current_steps": 135225, "total_steps": 181800, "loss": 0.003, "lr": 9.348076358529198e-06, "epoch": 14.876237623762377, "percentage": 74.38, "elapsed_time": "5:19:55", "remaining_time": "1:50:11", "throughput": 1486.78, "total_tokens": 28539232} {"current_steps": 135230, "total_steps": 181800, "loss": 0.0029, "lr": 9.346204950769673e-06, "epoch": 14.876787678767876, "percentage": 74.38, "elapsed_time": "5:19:56", "remaining_time": "1:50:10", "throughput": 1486.78, "total_tokens": 28540256} {"current_steps": 135235, "total_steps": 181800, "loss": 0.0252, "lr": 9.344333687283668e-06, "epoch": 14.877337733773377, "percentage": 74.39, "elapsed_time": "5:19:56", "remaining_time": "1:50:09", "throughput": 1486.78, "total_tokens": 28541376} {"current_steps": 135240, "total_steps": 181800, "loss": 0.0055, "lr": 9.342462568088416e-06, "epoch": 14.877887788778878, "percentage": 74.39, "elapsed_time": "5:19:57", "remaining_time": "1:50:09", "throughput": 1486.78, "total_tokens": 28542432} {"current_steps": 135245, "total_steps": 181800, "loss": 0.0015, "lr": 9.340591593201175e-06, "epoch": 14.87843784378438, "percentage": 74.39, "elapsed_time": "5:19:58", "remaining_time": "1:50:08", "throughput": 1486.78, "total_tokens": 28543488} {"current_steps": 135250, "total_steps": 181800, "loss": 0.0027, "lr": 9.33872076263919e-06, "epoch": 14.878987898789878, "percentage": 74.39, "elapsed_time": "5:19:58", "remaining_time": "1:50:07", "throughput": 1486.79, "total_tokens": 28544608} {"current_steps": 135255, "total_steps": 181800, "loss": 0.066, "lr": 9.336850076419704e-06, "epoch": 14.87953795379538, "percentage": 74.4, "elapsed_time": "5:19:59", "remaining_time": "1:50:07", "throughput": 1486.79, "total_tokens": 28545696} {"current_steps": 135260, "total_steps": 181800, "loss": 0.091, "lr": 9.334979534559957e-06, "epoch": 14.88008800880088, "percentage": 74.4, "elapsed_time": "5:20:00", "remaining_time": "1:50:06", "throughput": 1486.79, "total_tokens": 28546752} {"current_steps": 135265, "total_steps": 181800, "loss": 0.0554, "lr": 9.333109137077178e-06, "epoch": 14.88063806380638, "percentage": 74.4, "elapsed_time": "5:20:00", "remaining_time": "1:50:05", "throughput": 1486.79, "total_tokens": 28547744} {"current_steps": 135270, "total_steps": 181800, "loss": 0.0582, "lr": 9.331238883988616e-06, "epoch": 14.881188118811881, "percentage": 74.41, "elapsed_time": "5:20:01", "remaining_time": "1:50:04", "throughput": 1486.79, "total_tokens": 28548768} {"current_steps": 135275, "total_steps": 181800, "loss": 0.1058, "lr": 9.329368775311503e-06, "epoch": 14.881738173817382, "percentage": 74.41, "elapsed_time": "5:20:02", "remaining_time": "1:50:04", "throughput": 1486.79, "total_tokens": 28549856} {"current_steps": 135280, "total_steps": 181800, "loss": 0.0178, "lr": 9.32749881106309e-06, "epoch": 14.882288228822881, "percentage": 74.41, "elapsed_time": "5:20:02", "remaining_time": "1:50:03", "throughput": 1486.8, "total_tokens": 28550976} {"current_steps": 135285, "total_steps": 181800, "loss": 0.0097, "lr": 9.325628991260602e-06, "epoch": 14.882838283828383, "percentage": 74.41, "elapsed_time": "5:20:03", "remaining_time": "1:50:02", "throughput": 1486.8, "total_tokens": 28552032} {"current_steps": 135290, "total_steps": 181800, "loss": 0.1113, "lr": 9.323759315921258e-06, "epoch": 14.883388338833884, "percentage": 74.42, "elapsed_time": "5:20:04", "remaining_time": "1:50:02", "throughput": 1486.8, "total_tokens": 28553088} {"current_steps": 135295, "total_steps": 181800, "loss": 0.004, "lr": 9.321889785062312e-06, "epoch": 14.883938393839383, "percentage": 74.42, "elapsed_time": "5:20:05", "remaining_time": "1:50:01", "throughput": 1486.81, "total_tokens": 28554208} {"current_steps": 135300, "total_steps": 181800, "loss": 0.0035, "lr": 9.320020398700977e-06, "epoch": 14.884488448844884, "percentage": 74.42, "elapsed_time": "5:20:05", "remaining_time": "1:50:00", "throughput": 1486.81, "total_tokens": 28555232} {"current_steps": 135305, "total_steps": 181800, "loss": 0.0365, "lr": 9.318151156854487e-06, "epoch": 14.885038503850385, "percentage": 74.43, "elapsed_time": "5:20:06", "remaining_time": "1:49:59", "throughput": 1486.81, "total_tokens": 28556352} {"current_steps": 135310, "total_steps": 181800, "loss": 0.1481, "lr": 9.316282059540085e-06, "epoch": 14.885588558855886, "percentage": 74.43, "elapsed_time": "5:20:07", "remaining_time": "1:49:59", "throughput": 1486.81, "total_tokens": 28557408} {"current_steps": 135315, "total_steps": 181800, "loss": 0.0453, "lr": 9.314413106774975e-06, "epoch": 14.886138613861386, "percentage": 74.43, "elapsed_time": "5:20:07", "remaining_time": "1:49:58", "throughput": 1486.81, "total_tokens": 28558432} {"current_steps": 135320, "total_steps": 181800, "loss": 0.0091, "lr": 9.3125442985764e-06, "epoch": 14.886688668866887, "percentage": 74.43, "elapsed_time": "5:20:08", "remaining_time": "1:49:57", "throughput": 1486.81, "total_tokens": 28559488} {"current_steps": 135325, "total_steps": 181800, "loss": 0.0827, "lr": 9.31067563496158e-06, "epoch": 14.887238723872388, "percentage": 74.44, "elapsed_time": "5:20:09", "remaining_time": "1:49:57", "throughput": 1486.81, "total_tokens": 28560480} {"current_steps": 135330, "total_steps": 181800, "loss": 0.0684, "lr": 9.308807115947715e-06, "epoch": 14.887788778877887, "percentage": 74.44, "elapsed_time": "5:20:09", "remaining_time": "1:49:56", "throughput": 1486.81, "total_tokens": 28561536} {"current_steps": 135335, "total_steps": 181800, "loss": 0.03, "lr": 9.306938741552063e-06, "epoch": 14.888338833883388, "percentage": 74.44, "elapsed_time": "5:20:10", "remaining_time": "1:49:55", "throughput": 1486.82, "total_tokens": 28562624} {"current_steps": 135340, "total_steps": 181800, "loss": 0.0038, "lr": 9.305070511791816e-06, "epoch": 14.88888888888889, "percentage": 74.44, "elapsed_time": "5:20:11", "remaining_time": "1:49:54", "throughput": 1486.82, "total_tokens": 28563712} {"current_steps": 135345, "total_steps": 181800, "loss": 0.0326, "lr": 9.303202426684216e-06, "epoch": 14.88943894389439, "percentage": 74.45, "elapsed_time": "5:20:11", "remaining_time": "1:49:54", "throughput": 1486.82, "total_tokens": 28564736} {"current_steps": 135350, "total_steps": 181800, "loss": 0.0027, "lr": 9.301334486246463e-06, "epoch": 14.88998899889989, "percentage": 74.45, "elapsed_time": "5:20:12", "remaining_time": "1:49:53", "throughput": 1486.82, "total_tokens": 28565760} {"current_steps": 135355, "total_steps": 181800, "loss": 0.1045, "lr": 9.29946669049577e-06, "epoch": 14.89053905390539, "percentage": 74.45, "elapsed_time": "5:20:13", "remaining_time": "1:49:52", "throughput": 1486.82, "total_tokens": 28566816} {"current_steps": 135360, "total_steps": 181800, "loss": 0.0332, "lr": 9.29759903944936e-06, "epoch": 14.891089108910892, "percentage": 74.46, "elapsed_time": "5:20:14", "remaining_time": "1:49:52", "throughput": 1486.83, "total_tokens": 28567936} {"current_steps": 135365, "total_steps": 181800, "loss": 0.0253, "lr": 9.295731533124444e-06, "epoch": 14.891639163916391, "percentage": 74.46, "elapsed_time": "5:20:14", "remaining_time": "1:49:51", "throughput": 1486.83, "total_tokens": 28568960} {"current_steps": 135370, "total_steps": 181800, "loss": 0.0047, "lr": 9.293864171538242e-06, "epoch": 14.892189218921892, "percentage": 74.46, "elapsed_time": "5:20:15", "remaining_time": "1:49:50", "throughput": 1486.83, "total_tokens": 28569984} {"current_steps": 135375, "total_steps": 181800, "loss": 0.0046, "lr": 9.291996954707958e-06, "epoch": 14.892739273927393, "percentage": 74.46, "elapsed_time": "5:20:16", "remaining_time": "1:49:49", "throughput": 1486.82, "total_tokens": 28570976} {"current_steps": 135380, "total_steps": 181800, "loss": 0.0036, "lr": 9.290129882650791e-06, "epoch": 14.893289328932893, "percentage": 74.47, "elapsed_time": "5:20:16", "remaining_time": "1:49:49", "throughput": 1486.82, "total_tokens": 28572000} {"current_steps": 135385, "total_steps": 181800, "loss": 0.0084, "lr": 9.28826295538397e-06, "epoch": 14.893839383938394, "percentage": 74.47, "elapsed_time": "5:20:17", "remaining_time": "1:49:48", "throughput": 1486.83, "total_tokens": 28573088} {"current_steps": 135390, "total_steps": 181800, "loss": 0.0024, "lr": 9.286396172924672e-06, "epoch": 14.894389438943895, "percentage": 74.47, "elapsed_time": "5:20:18", "remaining_time": "1:49:47", "throughput": 1486.83, "total_tokens": 28574144} {"current_steps": 135395, "total_steps": 181800, "loss": 0.0426, "lr": 9.284529535290137e-06, "epoch": 14.894939493949394, "percentage": 74.47, "elapsed_time": "5:20:18", "remaining_time": "1:49:47", "throughput": 1486.83, "total_tokens": 28575104} {"current_steps": 135400, "total_steps": 181800, "loss": 0.0439, "lr": 9.282663042497553e-06, "epoch": 14.895489548954895, "percentage": 74.48, "elapsed_time": "5:20:19", "remaining_time": "1:49:46", "throughput": 1486.83, "total_tokens": 28576224} {"current_steps": 135405, "total_steps": 181800, "loss": 0.0009, "lr": 9.280796694564111e-06, "epoch": 14.896039603960396, "percentage": 74.48, "elapsed_time": "5:20:20", "remaining_time": "1:49:45", "throughput": 1486.83, "total_tokens": 28577216} {"current_steps": 135410, "total_steps": 181800, "loss": 0.0283, "lr": 9.278930491507031e-06, "epoch": 14.896589658965897, "percentage": 74.48, "elapsed_time": "5:20:20", "remaining_time": "1:49:44", "throughput": 1486.83, "total_tokens": 28578304} {"current_steps": 135415, "total_steps": 181800, "loss": 0.0294, "lr": 9.277064433343502e-06, "epoch": 14.897139713971397, "percentage": 74.49, "elapsed_time": "5:20:21", "remaining_time": "1:49:44", "throughput": 1486.83, "total_tokens": 28579264} {"current_steps": 135420, "total_steps": 181800, "loss": 0.0024, "lr": 9.27519852009072e-06, "epoch": 14.897689768976898, "percentage": 74.49, "elapsed_time": "5:20:22", "remaining_time": "1:49:43", "throughput": 1486.83, "total_tokens": 28580320} {"current_steps": 135425, "total_steps": 181800, "loss": 0.0084, "lr": 9.273332751765899e-06, "epoch": 14.898239823982399, "percentage": 74.49, "elapsed_time": "5:20:22", "remaining_time": "1:49:42", "throughput": 1486.83, "total_tokens": 28581344} {"current_steps": 135430, "total_steps": 181800, "loss": 0.0123, "lr": 9.271467128386213e-06, "epoch": 14.898789878987898, "percentage": 74.49, "elapsed_time": "5:20:23", "remaining_time": "1:49:42", "throughput": 1486.84, "total_tokens": 28582464} {"current_steps": 135435, "total_steps": 181800, "loss": 0.0024, "lr": 9.269601649968878e-06, "epoch": 14.8993399339934, "percentage": 74.5, "elapsed_time": "5:20:24", "remaining_time": "1:49:41", "throughput": 1486.84, "total_tokens": 28583520} {"current_steps": 135440, "total_steps": 181800, "loss": 0.0083, "lr": 9.267736316531067e-06, "epoch": 14.8998899889989, "percentage": 74.5, "elapsed_time": "5:20:25", "remaining_time": "1:49:40", "throughput": 1486.84, "total_tokens": 28584544} {"current_steps": 135445, "total_steps": 181800, "loss": 0.0081, "lr": 9.265871128089989e-06, "epoch": 14.9004400440044, "percentage": 74.5, "elapsed_time": "5:20:25", "remaining_time": "1:49:39", "throughput": 1486.84, "total_tokens": 28585600} {"current_steps": 135450, "total_steps": 181800, "loss": 0.0496, "lr": 9.264006084662821e-06, "epoch": 14.900990099009901, "percentage": 74.5, "elapsed_time": "5:20:26", "remaining_time": "1:49:39", "throughput": 1486.84, "total_tokens": 28586624} {"current_steps": 135455, "total_steps": 181800, "loss": 0.0138, "lr": 9.262141186266756e-06, "epoch": 14.901540154015402, "percentage": 74.51, "elapsed_time": "5:20:27", "remaining_time": "1:49:38", "throughput": 1486.84, "total_tokens": 28587648} {"current_steps": 135460, "total_steps": 181800, "loss": 0.0167, "lr": 9.260276432918993e-06, "epoch": 14.902090209020901, "percentage": 74.51, "elapsed_time": "5:20:27", "remaining_time": "1:49:37", "throughput": 1486.84, "total_tokens": 28588736} {"current_steps": 135465, "total_steps": 181800, "loss": 0.0111, "lr": 9.258411824636701e-06, "epoch": 14.902640264026402, "percentage": 74.51, "elapsed_time": "5:20:28", "remaining_time": "1:49:36", "throughput": 1486.84, "total_tokens": 28589760} {"current_steps": 135470, "total_steps": 181800, "loss": 0.0692, "lr": 9.256547361437082e-06, "epoch": 14.903190319031903, "percentage": 74.52, "elapsed_time": "5:20:29", "remaining_time": "1:49:36", "throughput": 1486.84, "total_tokens": 28590784} {"current_steps": 135475, "total_steps": 181800, "loss": 0.0458, "lr": 9.2546830433373e-06, "epoch": 14.903740374037405, "percentage": 74.52, "elapsed_time": "5:20:29", "remaining_time": "1:49:35", "throughput": 1486.84, "total_tokens": 28591840} {"current_steps": 135480, "total_steps": 181800, "loss": 0.0393, "lr": 9.252818870354554e-06, "epoch": 14.904290429042904, "percentage": 74.52, "elapsed_time": "5:20:30", "remaining_time": "1:49:34", "throughput": 1486.84, "total_tokens": 28592832} {"current_steps": 135485, "total_steps": 181800, "loss": 0.0025, "lr": 9.250954842506026e-06, "epoch": 14.904840484048405, "percentage": 74.52, "elapsed_time": "5:20:31", "remaining_time": "1:49:34", "throughput": 1486.84, "total_tokens": 28593792} {"current_steps": 135490, "total_steps": 181800, "loss": 0.0043, "lr": 9.249090959808881e-06, "epoch": 14.905390539053906, "percentage": 74.53, "elapsed_time": "5:20:31", "remaining_time": "1:49:33", "throughput": 1486.84, "total_tokens": 28594880} {"current_steps": 135495, "total_steps": 181800, "loss": 0.0197, "lr": 9.24722722228032e-06, "epoch": 14.905940594059405, "percentage": 74.53, "elapsed_time": "5:20:32", "remaining_time": "1:49:32", "throughput": 1486.84, "total_tokens": 28595872} {"current_steps": 135500, "total_steps": 181800, "loss": 0.0019, "lr": 9.2453636299375e-06, "epoch": 14.906490649064907, "percentage": 74.53, "elapsed_time": "5:20:33", "remaining_time": "1:49:31", "throughput": 1486.84, "total_tokens": 28596864} {"current_steps": 135505, "total_steps": 181800, "loss": 0.002, "lr": 9.24350018279759e-06, "epoch": 14.907040704070408, "percentage": 74.54, "elapsed_time": "5:20:34", "remaining_time": "1:49:31", "throughput": 1486.83, "total_tokens": 28597824} {"current_steps": 135510, "total_steps": 181800, "loss": 0.0021, "lr": 9.241636880877797e-06, "epoch": 14.907590759075907, "percentage": 74.54, "elapsed_time": "5:20:34", "remaining_time": "1:49:30", "throughput": 1486.84, "total_tokens": 28598880} {"current_steps": 135515, "total_steps": 181800, "loss": 0.0625, "lr": 9.239773724195272e-06, "epoch": 14.908140814081408, "percentage": 74.54, "elapsed_time": "5:20:35", "remaining_time": "1:49:29", "throughput": 1486.84, "total_tokens": 28599904} {"current_steps": 135520, "total_steps": 181800, "loss": 0.0331, "lr": 9.23791071276718e-06, "epoch": 14.908690869086909, "percentage": 74.54, "elapsed_time": "5:20:36", "remaining_time": "1:49:29", "throughput": 1486.84, "total_tokens": 28600992} {"current_steps": 135525, "total_steps": 181800, "loss": 0.0706, "lr": 9.236047846610716e-06, "epoch": 14.909240924092408, "percentage": 74.55, "elapsed_time": "5:20:36", "remaining_time": "1:49:28", "throughput": 1486.84, "total_tokens": 28602048} {"current_steps": 135530, "total_steps": 181800, "loss": 0.0126, "lr": 9.234185125743023e-06, "epoch": 14.90979097909791, "percentage": 74.55, "elapsed_time": "5:20:37", "remaining_time": "1:49:27", "throughput": 1486.85, "total_tokens": 28603168} {"current_steps": 135535, "total_steps": 181800, "loss": 0.0221, "lr": 9.23232255018128e-06, "epoch": 14.91034103410341, "percentage": 74.55, "elapsed_time": "5:20:38", "remaining_time": "1:49:26", "throughput": 1486.85, "total_tokens": 28604320} {"current_steps": 135540, "total_steps": 181800, "loss": 0.0097, "lr": 9.230460119942664e-06, "epoch": 14.910891089108912, "percentage": 74.55, "elapsed_time": "5:20:38", "remaining_time": "1:49:26", "throughput": 1486.86, "total_tokens": 28605440} {"current_steps": 135545, "total_steps": 181800, "loss": 0.0244, "lr": 9.22859783504432e-06, "epoch": 14.911441144114411, "percentage": 74.56, "elapsed_time": "5:20:39", "remaining_time": "1:49:25", "throughput": 1486.86, "total_tokens": 28606464} {"current_steps": 135550, "total_steps": 181800, "loss": 0.0561, "lr": 9.22673569550343e-06, "epoch": 14.911991199119912, "percentage": 74.56, "elapsed_time": "5:20:40", "remaining_time": "1:49:24", "throughput": 1486.86, "total_tokens": 28607584} {"current_steps": 135555, "total_steps": 181800, "loss": 0.0042, "lr": 9.224873701337141e-06, "epoch": 14.912541254125413, "percentage": 74.56, "elapsed_time": "5:20:40", "remaining_time": "1:49:24", "throughput": 1486.86, "total_tokens": 28608640} {"current_steps": 135560, "total_steps": 181800, "loss": 0.0676, "lr": 9.22301185256263e-06, "epoch": 14.913091309130913, "percentage": 74.57, "elapsed_time": "5:20:41", "remaining_time": "1:49:23", "throughput": 1486.86, "total_tokens": 28609696} {"current_steps": 135565, "total_steps": 181800, "loss": 0.0535, "lr": 9.221150149197038e-06, "epoch": 14.913641364136414, "percentage": 74.57, "elapsed_time": "5:20:42", "remaining_time": "1:49:22", "throughput": 1486.86, "total_tokens": 28610688} {"current_steps": 135570, "total_steps": 181800, "loss": 0.0009, "lr": 9.219288591257536e-06, "epoch": 14.914191419141915, "percentage": 74.57, "elapsed_time": "5:20:43", "remaining_time": "1:49:21", "throughput": 1486.86, "total_tokens": 28611712} {"current_steps": 135575, "total_steps": 181800, "loss": 0.0078, "lr": 9.217427178761287e-06, "epoch": 14.914741474147414, "percentage": 74.57, "elapsed_time": "5:20:43", "remaining_time": "1:49:21", "throughput": 1486.86, "total_tokens": 28612736} {"current_steps": 135580, "total_steps": 181800, "loss": 0.0546, "lr": 9.215565911725429e-06, "epoch": 14.915291529152915, "percentage": 74.58, "elapsed_time": "5:20:44", "remaining_time": "1:49:20", "throughput": 1486.87, "total_tokens": 28613888} {"current_steps": 135585, "total_steps": 181800, "loss": 0.0006, "lr": 9.213704790167135e-06, "epoch": 14.915841584158416, "percentage": 74.58, "elapsed_time": "5:20:45", "remaining_time": "1:49:19", "throughput": 1486.87, "total_tokens": 28614944} {"current_steps": 135590, "total_steps": 181800, "loss": 0.0738, "lr": 9.21184381410354e-06, "epoch": 14.916391639163916, "percentage": 74.58, "elapsed_time": "5:20:45", "remaining_time": "1:49:19", "throughput": 1486.88, "total_tokens": 28616064} {"current_steps": 135595, "total_steps": 181800, "loss": 0.0067, "lr": 9.209982983551804e-06, "epoch": 14.916941694169417, "percentage": 74.58, "elapsed_time": "5:20:46", "remaining_time": "1:49:18", "throughput": 1486.88, "total_tokens": 28617184} {"current_steps": 135600, "total_steps": 181800, "loss": 0.0018, "lr": 9.208122298529087e-06, "epoch": 14.917491749174918, "percentage": 74.59, "elapsed_time": "5:20:47", "remaining_time": "1:49:17", "throughput": 1486.89, "total_tokens": 28618304} {"current_steps": 135605, "total_steps": 181800, "loss": 0.0404, "lr": 9.206261759052523e-06, "epoch": 14.918041804180419, "percentage": 74.59, "elapsed_time": "5:20:47", "remaining_time": "1:49:16", "throughput": 1486.89, "total_tokens": 28619424} {"current_steps": 135610, "total_steps": 181800, "loss": 0.048, "lr": 9.20440136513927e-06, "epoch": 14.918591859185918, "percentage": 74.59, "elapsed_time": "5:20:48", "remaining_time": "1:49:16", "throughput": 1486.89, "total_tokens": 28620448} {"current_steps": 135615, "total_steps": 181800, "loss": 0.0466, "lr": 9.202541116806473e-06, "epoch": 14.91914191419142, "percentage": 74.6, "elapsed_time": "5:20:49", "remaining_time": "1:49:15", "throughput": 1486.89, "total_tokens": 28621408} {"current_steps": 135620, "total_steps": 181800, "loss": 0.0054, "lr": 9.200681014071267e-06, "epoch": 14.91969196919692, "percentage": 74.6, "elapsed_time": "5:20:49", "remaining_time": "1:49:14", "throughput": 1486.89, "total_tokens": 28622432} {"current_steps": 135625, "total_steps": 181800, "loss": 0.0013, "lr": 9.198821056950799e-06, "epoch": 14.92024202420242, "percentage": 74.6, "elapsed_time": "5:20:50", "remaining_time": "1:49:14", "throughput": 1486.89, "total_tokens": 28623456} {"current_steps": 135630, "total_steps": 181800, "loss": 0.0882, "lr": 9.196961245462218e-06, "epoch": 14.92079207920792, "percentage": 74.6, "elapsed_time": "5:20:51", "remaining_time": "1:49:13", "throughput": 1486.88, "total_tokens": 28624448} {"current_steps": 135635, "total_steps": 181800, "loss": 0.0024, "lr": 9.19510157962267e-06, "epoch": 14.921342134213422, "percentage": 74.61, "elapsed_time": "5:20:51", "remaining_time": "1:49:12", "throughput": 1486.88, "total_tokens": 28625472} {"current_steps": 135640, "total_steps": 181800, "loss": 0.0151, "lr": 9.193242059449285e-06, "epoch": 14.921892189218921, "percentage": 74.61, "elapsed_time": "5:20:52", "remaining_time": "1:49:11", "throughput": 1486.88, "total_tokens": 28626464} {"current_steps": 135645, "total_steps": 181800, "loss": 0.1109, "lr": 9.191382684959199e-06, "epoch": 14.922442244224422, "percentage": 74.61, "elapsed_time": "5:20:53", "remaining_time": "1:49:11", "throughput": 1486.88, "total_tokens": 28627488} {"current_steps": 135650, "total_steps": 181800, "loss": 0.033, "lr": 9.18952345616955e-06, "epoch": 14.922992299229923, "percentage": 74.61, "elapsed_time": "5:20:54", "remaining_time": "1:49:10", "throughput": 1486.88, "total_tokens": 28628544} {"current_steps": 135655, "total_steps": 181800, "loss": 0.0076, "lr": 9.187664373097476e-06, "epoch": 14.923542354235423, "percentage": 74.62, "elapsed_time": "5:20:54", "remaining_time": "1:49:09", "throughput": 1486.88, "total_tokens": 28629568} {"current_steps": 135660, "total_steps": 181800, "loss": 0.0022, "lr": 9.185805435760123e-06, "epoch": 14.924092409240924, "percentage": 74.62, "elapsed_time": "5:20:55", "remaining_time": "1:49:09", "throughput": 1486.88, "total_tokens": 28630592} {"current_steps": 135665, "total_steps": 181800, "loss": 0.1272, "lr": 9.18394664417461e-06, "epoch": 14.924642464246425, "percentage": 74.62, "elapsed_time": "5:20:56", "remaining_time": "1:49:08", "throughput": 1486.89, "total_tokens": 28631680} {"current_steps": 135670, "total_steps": 181800, "loss": 0.0028, "lr": 9.182087998358062e-06, "epoch": 14.925192519251926, "percentage": 74.63, "elapsed_time": "5:20:56", "remaining_time": "1:49:07", "throughput": 1486.89, "total_tokens": 28632768} {"current_steps": 135675, "total_steps": 181800, "loss": 0.0196, "lr": 9.180229498327633e-06, "epoch": 14.925742574257425, "percentage": 74.63, "elapsed_time": "5:20:57", "remaining_time": "1:49:06", "throughput": 1486.89, "total_tokens": 28633792} {"current_steps": 135680, "total_steps": 181800, "loss": 0.003, "lr": 9.178371144100426e-06, "epoch": 14.926292629262926, "percentage": 74.63, "elapsed_time": "5:20:58", "remaining_time": "1:49:06", "throughput": 1486.89, "total_tokens": 28634784} {"current_steps": 135685, "total_steps": 181800, "loss": 0.0973, "lr": 9.176512935693579e-06, "epoch": 14.926842684268427, "percentage": 74.63, "elapsed_time": "5:20:58", "remaining_time": "1:49:05", "throughput": 1486.89, "total_tokens": 28635872} {"current_steps": 135690, "total_steps": 181800, "loss": 0.0117, "lr": 9.174654873124228e-06, "epoch": 14.927392739273927, "percentage": 74.64, "elapsed_time": "5:20:59", "remaining_time": "1:49:04", "throughput": 1486.89, "total_tokens": 28636896} {"current_steps": 135695, "total_steps": 181800, "loss": 0.0486, "lr": 9.172796956409482e-06, "epoch": 14.927942794279428, "percentage": 74.64, "elapsed_time": "5:21:00", "remaining_time": "1:49:04", "throughput": 1486.89, "total_tokens": 28637920} {"current_steps": 135700, "total_steps": 181800, "loss": 0.0015, "lr": 9.17093918556648e-06, "epoch": 14.928492849284929, "percentage": 74.64, "elapsed_time": "5:21:00", "remaining_time": "1:49:03", "throughput": 1486.89, "total_tokens": 28639008} {"current_steps": 135705, "total_steps": 181800, "loss": 0.0675, "lr": 9.169081560612327e-06, "epoch": 14.929042904290428, "percentage": 74.65, "elapsed_time": "5:21:01", "remaining_time": "1:49:02", "throughput": 1486.9, "total_tokens": 28640064} {"current_steps": 135710, "total_steps": 181800, "loss": 0.029, "lr": 9.167224081564155e-06, "epoch": 14.92959295929593, "percentage": 74.65, "elapsed_time": "5:21:02", "remaining_time": "1:49:01", "throughput": 1486.9, "total_tokens": 28641120} {"current_steps": 135715, "total_steps": 181800, "loss": 0.0085, "lr": 9.165366748439089e-06, "epoch": 14.93014301430143, "percentage": 74.65, "elapsed_time": "5:21:03", "remaining_time": "1:49:01", "throughput": 1486.9, "total_tokens": 28642144} {"current_steps": 135720, "total_steps": 181800, "loss": 0.0457, "lr": 9.16350956125423e-06, "epoch": 14.930693069306932, "percentage": 74.65, "elapsed_time": "5:21:03", "remaining_time": "1:49:00", "throughput": 1486.9, "total_tokens": 28643136} {"current_steps": 135725, "total_steps": 181800, "loss": 0.0044, "lr": 9.161652520026712e-06, "epoch": 14.93124312431243, "percentage": 74.66, "elapsed_time": "5:21:04", "remaining_time": "1:48:59", "throughput": 1486.9, "total_tokens": 28644224} {"current_steps": 135730, "total_steps": 181800, "loss": 0.0017, "lr": 9.159795624773643e-06, "epoch": 14.931793179317932, "percentage": 74.66, "elapsed_time": "5:21:05", "remaining_time": "1:48:59", "throughput": 1486.9, "total_tokens": 28645312} {"current_steps": 135735, "total_steps": 181800, "loss": 0.11, "lr": 9.157938875512131e-06, "epoch": 14.932343234323433, "percentage": 74.66, "elapsed_time": "5:21:05", "remaining_time": "1:48:58", "throughput": 1486.9, "total_tokens": 28646368} {"current_steps": 135740, "total_steps": 181800, "loss": 0.0162, "lr": 9.156082272259292e-06, "epoch": 14.932893289328932, "percentage": 74.66, "elapsed_time": "5:21:06", "remaining_time": "1:48:57", "throughput": 1486.9, "total_tokens": 28647424} {"current_steps": 135745, "total_steps": 181800, "loss": 0.0051, "lr": 9.154225815032242e-06, "epoch": 14.933443344334433, "percentage": 74.67, "elapsed_time": "5:21:07", "remaining_time": "1:48:56", "throughput": 1486.9, "total_tokens": 28648448} {"current_steps": 135750, "total_steps": 181800, "loss": 0.002, "lr": 9.152369503848097e-06, "epoch": 14.933993399339935, "percentage": 74.67, "elapsed_time": "5:21:07", "remaining_time": "1:48:56", "throughput": 1486.9, "total_tokens": 28649440} {"current_steps": 135755, "total_steps": 181800, "loss": 0.008, "lr": 9.150513338723956e-06, "epoch": 14.934543454345434, "percentage": 74.67, "elapsed_time": "5:21:08", "remaining_time": "1:48:55", "throughput": 1486.91, "total_tokens": 28650560} {"current_steps": 135760, "total_steps": 181800, "loss": 0.0056, "lr": 9.14865731967692e-06, "epoch": 14.935093509350935, "percentage": 74.68, "elapsed_time": "5:21:09", "remaining_time": "1:48:54", "throughput": 1486.91, "total_tokens": 28651616} {"current_steps": 135765, "total_steps": 181800, "loss": 0.0063, "lr": 9.146801446724104e-06, "epoch": 14.935643564356436, "percentage": 74.68, "elapsed_time": "5:21:09", "remaining_time": "1:48:54", "throughput": 1486.91, "total_tokens": 28652704} {"current_steps": 135770, "total_steps": 181800, "loss": 0.0054, "lr": 9.144945719882613e-06, "epoch": 14.936193619361937, "percentage": 74.68, "elapsed_time": "5:21:10", "remaining_time": "1:48:53", "throughput": 1486.91, "total_tokens": 28653728} {"current_steps": 135775, "total_steps": 181800, "loss": 0.0289, "lr": 9.143090139169558e-06, "epoch": 14.936743674367436, "percentage": 74.68, "elapsed_time": "5:21:11", "remaining_time": "1:48:52", "throughput": 1486.91, "total_tokens": 28654720} {"current_steps": 135780, "total_steps": 181800, "loss": 0.0016, "lr": 9.14123470460203e-06, "epoch": 14.937293729372938, "percentage": 74.69, "elapsed_time": "5:21:11", "remaining_time": "1:48:51", "throughput": 1486.92, "total_tokens": 28655840} {"current_steps": 135785, "total_steps": 181800, "loss": 0.0238, "lr": 9.139379416197125e-06, "epoch": 14.937843784378439, "percentage": 74.69, "elapsed_time": "5:21:12", "remaining_time": "1:48:51", "throughput": 1486.92, "total_tokens": 28656928} {"current_steps": 135790, "total_steps": 181800, "loss": 0.0033, "lr": 9.137524273971956e-06, "epoch": 14.938393839383938, "percentage": 74.69, "elapsed_time": "5:21:13", "remaining_time": "1:48:50", "throughput": 1486.92, "total_tokens": 28657984} {"current_steps": 135795, "total_steps": 181800, "loss": 0.0015, "lr": 9.135669277943609e-06, "epoch": 14.938943894389439, "percentage": 74.69, "elapsed_time": "5:21:14", "remaining_time": "1:48:49", "throughput": 1486.92, "total_tokens": 28659040} {"current_steps": 135800, "total_steps": 181800, "loss": 0.0066, "lr": 9.133814428129183e-06, "epoch": 14.93949394939494, "percentage": 74.7, "elapsed_time": "5:21:14", "remaining_time": "1:48:48", "throughput": 1486.93, "total_tokens": 28660160} {"current_steps": 135805, "total_steps": 181800, "loss": 0.0104, "lr": 9.131959724545786e-06, "epoch": 14.94004400440044, "percentage": 74.7, "elapsed_time": "5:21:15", "remaining_time": "1:48:48", "throughput": 1486.93, "total_tokens": 28661216} {"current_steps": 135810, "total_steps": 181800, "loss": 0.0021, "lr": 9.130105167210492e-06, "epoch": 14.94059405940594, "percentage": 74.7, "elapsed_time": "5:21:16", "remaining_time": "1:48:47", "throughput": 1486.93, "total_tokens": 28662208} {"current_steps": 135815, "total_steps": 181800, "loss": 0.0585, "lr": 9.128250756140414e-06, "epoch": 14.941144114411442, "percentage": 74.71, "elapsed_time": "5:21:16", "remaining_time": "1:48:46", "throughput": 1486.93, "total_tokens": 28663328} {"current_steps": 135820, "total_steps": 181800, "loss": 0.0829, "lr": 9.126396491352624e-06, "epoch": 14.941694169416941, "percentage": 74.71, "elapsed_time": "5:21:17", "remaining_time": "1:48:46", "throughput": 1486.94, "total_tokens": 28664384} {"current_steps": 135825, "total_steps": 181800, "loss": 0.0408, "lr": 9.12454237286422e-06, "epoch": 14.942244224422442, "percentage": 74.71, "elapsed_time": "5:21:18", "remaining_time": "1:48:45", "throughput": 1486.94, "total_tokens": 28665472} {"current_steps": 135830, "total_steps": 181800, "loss": 0.0021, "lr": 9.1226884006923e-06, "epoch": 14.942794279427943, "percentage": 74.71, "elapsed_time": "5:21:18", "remaining_time": "1:48:44", "throughput": 1486.94, "total_tokens": 28666496} {"current_steps": 135835, "total_steps": 181800, "loss": 0.0261, "lr": 9.120834574853935e-06, "epoch": 14.943344334433444, "percentage": 74.72, "elapsed_time": "5:21:19", "remaining_time": "1:48:43", "throughput": 1486.94, "total_tokens": 28667616} {"current_steps": 135840, "total_steps": 181800, "loss": 0.001, "lr": 9.118980895366225e-06, "epoch": 14.943894389438944, "percentage": 74.72, "elapsed_time": "5:21:20", "remaining_time": "1:48:43", "throughput": 1486.94, "total_tokens": 28668672} {"current_steps": 135845, "total_steps": 181800, "loss": 0.0077, "lr": 9.117127362246239e-06, "epoch": 14.944444444444445, "percentage": 74.72, "elapsed_time": "5:21:20", "remaining_time": "1:48:42", "throughput": 1486.95, "total_tokens": 28669792} {"current_steps": 135850, "total_steps": 181800, "loss": 0.002, "lr": 9.115273975511076e-06, "epoch": 14.944994499449946, "percentage": 74.72, "elapsed_time": "5:21:21", "remaining_time": "1:48:41", "throughput": 1486.95, "total_tokens": 28670784} {"current_steps": 135855, "total_steps": 181800, "loss": 0.0013, "lr": 9.113420735177804e-06, "epoch": 14.945544554455445, "percentage": 74.73, "elapsed_time": "5:21:22", "remaining_time": "1:48:41", "throughput": 1486.95, "total_tokens": 28671872} {"current_steps": 135860, "total_steps": 181800, "loss": 0.0051, "lr": 9.11156764126351e-06, "epoch": 14.946094609460946, "percentage": 74.73, "elapsed_time": "5:21:23", "remaining_time": "1:48:40", "throughput": 1486.95, "total_tokens": 28672928} {"current_steps": 135865, "total_steps": 181800, "loss": 0.0096, "lr": 9.109714693785282e-06, "epoch": 14.946644664466447, "percentage": 74.73, "elapsed_time": "5:21:23", "remaining_time": "1:48:39", "throughput": 1486.96, "total_tokens": 28674016} {"current_steps": 135870, "total_steps": 181800, "loss": 0.0666, "lr": 9.107861892760178e-06, "epoch": 14.947194719471947, "percentage": 74.74, "elapsed_time": "5:21:24", "remaining_time": "1:48:38", "throughput": 1486.96, "total_tokens": 28675040} {"current_steps": 135875, "total_steps": 181800, "loss": 0.0064, "lr": 9.106009238205296e-06, "epoch": 14.947744774477448, "percentage": 74.74, "elapsed_time": "5:21:25", "remaining_time": "1:48:38", "throughput": 1486.96, "total_tokens": 28676096} {"current_steps": 135880, "total_steps": 181800, "loss": 0.0008, "lr": 9.104156730137692e-06, "epoch": 14.948294829482949, "percentage": 74.74, "elapsed_time": "5:21:25", "remaining_time": "1:48:37", "throughput": 1486.95, "total_tokens": 28677056} {"current_steps": 135885, "total_steps": 181800, "loss": 0.005, "lr": 9.102304368574446e-06, "epoch": 14.948844884488448, "percentage": 74.74, "elapsed_time": "5:21:26", "remaining_time": "1:48:36", "throughput": 1486.96, "total_tokens": 28678080} {"current_steps": 135890, "total_steps": 181800, "loss": 0.0036, "lr": 9.10045215353264e-06, "epoch": 14.94939493949395, "percentage": 74.75, "elapsed_time": "5:21:27", "remaining_time": "1:48:36", "throughput": 1486.96, "total_tokens": 28679168} {"current_steps": 135895, "total_steps": 181800, "loss": 0.0451, "lr": 9.09860008502933e-06, "epoch": 14.94994499449945, "percentage": 74.75, "elapsed_time": "5:21:27", "remaining_time": "1:48:35", "throughput": 1486.96, "total_tokens": 28680192} {"current_steps": 135900, "total_steps": 181800, "loss": 0.0017, "lr": 9.096748163081603e-06, "epoch": 14.950495049504951, "percentage": 74.75, "elapsed_time": "5:21:28", "remaining_time": "1:48:34", "throughput": 1486.96, "total_tokens": 28681184} {"current_steps": 135905, "total_steps": 181800, "loss": 0.036, "lr": 9.094896387706515e-06, "epoch": 14.95104510451045, "percentage": 74.76, "elapsed_time": "5:21:29", "remaining_time": "1:48:33", "throughput": 1486.96, "total_tokens": 28682272} {"current_steps": 135910, "total_steps": 181800, "loss": 0.0043, "lr": 9.093044758921127e-06, "epoch": 14.951595159515952, "percentage": 74.76, "elapsed_time": "5:21:29", "remaining_time": "1:48:33", "throughput": 1486.96, "total_tokens": 28683264} {"current_steps": 135915, "total_steps": 181800, "loss": 0.0691, "lr": 9.091193276742513e-06, "epoch": 14.952145214521453, "percentage": 74.76, "elapsed_time": "5:21:30", "remaining_time": "1:48:32", "throughput": 1486.96, "total_tokens": 28684288} {"current_steps": 135920, "total_steps": 181800, "loss": 0.016, "lr": 9.089341941187742e-06, "epoch": 14.952695269526952, "percentage": 74.76, "elapsed_time": "5:21:31", "remaining_time": "1:48:31", "throughput": 1486.96, "total_tokens": 28685344} {"current_steps": 135925, "total_steps": 181800, "loss": 0.0059, "lr": 9.087490752273867e-06, "epoch": 14.953245324532453, "percentage": 74.77, "elapsed_time": "5:21:31", "remaining_time": "1:48:31", "throughput": 1486.96, "total_tokens": 28686368} {"current_steps": 135930, "total_steps": 181800, "loss": 0.1295, "lr": 9.085639710017963e-06, "epoch": 14.953795379537954, "percentage": 74.77, "elapsed_time": "5:21:32", "remaining_time": "1:48:30", "throughput": 1486.96, "total_tokens": 28687424} {"current_steps": 135935, "total_steps": 181800, "loss": 0.0012, "lr": 9.08378881443707e-06, "epoch": 14.954345434543454, "percentage": 74.77, "elapsed_time": "5:21:33", "remaining_time": "1:48:29", "throughput": 1486.96, "total_tokens": 28688448} {"current_steps": 135940, "total_steps": 181800, "loss": 0.067, "lr": 9.081938065548259e-06, "epoch": 14.954895489548955, "percentage": 74.77, "elapsed_time": "5:21:34", "remaining_time": "1:48:28", "throughput": 1486.96, "total_tokens": 28689568} {"current_steps": 135945, "total_steps": 181800, "loss": 0.0036, "lr": 9.080087463368595e-06, "epoch": 14.955445544554456, "percentage": 74.78, "elapsed_time": "5:21:34", "remaining_time": "1:48:28", "throughput": 1486.97, "total_tokens": 28690624} {"current_steps": 135950, "total_steps": 181800, "loss": 0.0024, "lr": 9.07823700791512e-06, "epoch": 14.955995599559955, "percentage": 74.78, "elapsed_time": "5:21:35", "remaining_time": "1:48:27", "throughput": 1486.96, "total_tokens": 28691616} {"current_steps": 135955, "total_steps": 181800, "loss": 0.002, "lr": 9.0763866992049e-06, "epoch": 14.956545654565456, "percentage": 74.78, "elapsed_time": "5:21:36", "remaining_time": "1:48:26", "throughput": 1486.97, "total_tokens": 28692704} {"current_steps": 135960, "total_steps": 181800, "loss": 0.0028, "lr": 9.074536537254975e-06, "epoch": 14.957095709570957, "percentage": 74.79, "elapsed_time": "5:21:36", "remaining_time": "1:48:26", "throughput": 1486.97, "total_tokens": 28693760} {"current_steps": 135965, "total_steps": 181800, "loss": 0.037, "lr": 9.072686522082413e-06, "epoch": 14.957645764576458, "percentage": 74.79, "elapsed_time": "5:21:37", "remaining_time": "1:48:25", "throughput": 1486.97, "total_tokens": 28694880} {"current_steps": 135970, "total_steps": 181800, "loss": 0.0533, "lr": 9.070836653704248e-06, "epoch": 14.958195819581958, "percentage": 74.79, "elapsed_time": "5:21:38", "remaining_time": "1:48:24", "throughput": 1486.98, "total_tokens": 28695936} {"current_steps": 135975, "total_steps": 181800, "loss": 0.0986, "lr": 9.068986932137542e-06, "epoch": 14.958745874587459, "percentage": 74.79, "elapsed_time": "5:21:38", "remaining_time": "1:48:23", "throughput": 1486.98, "total_tokens": 28696992} {"current_steps": 135980, "total_steps": 181800, "loss": 0.1077, "lr": 9.067137357399341e-06, "epoch": 14.95929592959296, "percentage": 74.8, "elapsed_time": "5:21:39", "remaining_time": "1:48:23", "throughput": 1486.98, "total_tokens": 28698016} {"current_steps": 135985, "total_steps": 181800, "loss": 0.0039, "lr": 9.065287929506686e-06, "epoch": 14.95984598459846, "percentage": 74.8, "elapsed_time": "5:21:40", "remaining_time": "1:48:22", "throughput": 1486.98, "total_tokens": 28699040} {"current_steps": 135990, "total_steps": 181800, "loss": 0.0668, "lr": 9.063438648476633e-06, "epoch": 14.96039603960396, "percentage": 74.8, "elapsed_time": "5:21:40", "remaining_time": "1:48:21", "throughput": 1486.98, "total_tokens": 28700064} {"current_steps": 135995, "total_steps": 181800, "loss": 0.0348, "lr": 9.06158951432621e-06, "epoch": 14.960946094609461, "percentage": 74.8, "elapsed_time": "5:21:41", "remaining_time": "1:48:21", "throughput": 1486.98, "total_tokens": 28701152} {"current_steps": 136000, "total_steps": 181800, "loss": 0.0072, "lr": 9.059740527072469e-06, "epoch": 14.96149614961496, "percentage": 74.81, "elapsed_time": "5:21:42", "remaining_time": "1:48:20", "throughput": 1486.98, "total_tokens": 28702208} {"current_steps": 136005, "total_steps": 181800, "loss": 0.0335, "lr": 9.057891686732459e-06, "epoch": 14.962046204620462, "percentage": 74.81, "elapsed_time": "5:21:43", "remaining_time": "1:48:19", "throughput": 1486.99, "total_tokens": 28703328} {"current_steps": 136010, "total_steps": 181800, "loss": 0.0023, "lr": 9.056042993323202e-06, "epoch": 14.962596259625963, "percentage": 74.81, "elapsed_time": "5:21:43", "remaining_time": "1:48:18", "throughput": 1486.99, "total_tokens": 28704384} {"current_steps": 136015, "total_steps": 181800, "loss": 0.0498, "lr": 9.054194446861754e-06, "epoch": 14.963146314631462, "percentage": 74.82, "elapsed_time": "5:21:44", "remaining_time": "1:48:18", "throughput": 1486.99, "total_tokens": 28705440} {"current_steps": 136020, "total_steps": 181800, "loss": 0.0052, "lr": 9.052346047365148e-06, "epoch": 14.963696369636963, "percentage": 74.82, "elapsed_time": "5:21:45", "remaining_time": "1:48:17", "throughput": 1486.99, "total_tokens": 28706528} {"current_steps": 136025, "total_steps": 181800, "loss": 0.0791, "lr": 9.050497794850404e-06, "epoch": 14.964246424642464, "percentage": 74.82, "elapsed_time": "5:21:45", "remaining_time": "1:48:16", "throughput": 1486.99, "total_tokens": 28707488} {"current_steps": 136030, "total_steps": 181800, "loss": 0.1651, "lr": 9.048649689334571e-06, "epoch": 14.964796479647966, "percentage": 74.82, "elapsed_time": "5:21:46", "remaining_time": "1:48:16", "throughput": 1486.99, "total_tokens": 28708512} {"current_steps": 136035, "total_steps": 181800, "loss": 0.0075, "lr": 9.046801730834678e-06, "epoch": 14.965346534653465, "percentage": 74.83, "elapsed_time": "5:21:47", "remaining_time": "1:48:15", "throughput": 1486.99, "total_tokens": 28709568} {"current_steps": 136040, "total_steps": 181800, "loss": 0.0051, "lr": 9.044953919367769e-06, "epoch": 14.965896589658966, "percentage": 74.83, "elapsed_time": "5:21:47", "remaining_time": "1:48:14", "throughput": 1486.99, "total_tokens": 28710624} {"current_steps": 136045, "total_steps": 181800, "loss": 0.0007, "lr": 9.043106254950862e-06, "epoch": 14.966446644664467, "percentage": 74.83, "elapsed_time": "5:21:48", "remaining_time": "1:48:13", "throughput": 1487.0, "total_tokens": 28711712} {"current_steps": 136050, "total_steps": 181800, "loss": 0.0688, "lr": 9.041258737600977e-06, "epoch": 14.966996699669966, "percentage": 74.83, "elapsed_time": "5:21:49", "remaining_time": "1:48:13", "throughput": 1487.0, "total_tokens": 28712736} {"current_steps": 136055, "total_steps": 181800, "loss": 0.0282, "lr": 9.039411367335157e-06, "epoch": 14.967546754675467, "percentage": 74.84, "elapsed_time": "5:21:49", "remaining_time": "1:48:12", "throughput": 1487.0, "total_tokens": 28713824} {"current_steps": 136060, "total_steps": 181800, "loss": 0.0011, "lr": 9.037564144170421e-06, "epoch": 14.968096809680969, "percentage": 74.84, "elapsed_time": "5:21:50", "remaining_time": "1:48:11", "throughput": 1487.0, "total_tokens": 28714912} {"current_steps": 136065, "total_steps": 181800, "loss": 0.0027, "lr": 9.035717068123806e-06, "epoch": 14.968646864686468, "percentage": 74.84, "elapsed_time": "5:21:51", "remaining_time": "1:48:11", "throughput": 1487.0, "total_tokens": 28715936} {"current_steps": 136070, "total_steps": 181800, "loss": 0.0014, "lr": 9.033870139212324e-06, "epoch": 14.969196919691969, "percentage": 74.85, "elapsed_time": "5:21:51", "remaining_time": "1:48:10", "throughput": 1487.0, "total_tokens": 28716992} {"current_steps": 136075, "total_steps": 181800, "loss": 0.0666, "lr": 9.032023357452995e-06, "epoch": 14.96974697469747, "percentage": 74.85, "elapsed_time": "5:21:52", "remaining_time": "1:48:09", "throughput": 1487.01, "total_tokens": 28718080} {"current_steps": 136080, "total_steps": 181800, "loss": 0.0522, "lr": 9.030176722862852e-06, "epoch": 14.97029702970297, "percentage": 74.85, "elapsed_time": "5:21:53", "remaining_time": "1:48:08", "throughput": 1487.01, "total_tokens": 28719072} {"current_steps": 136085, "total_steps": 181800, "loss": 0.0108, "lr": 9.028330235458898e-06, "epoch": 14.97084708470847, "percentage": 74.85, "elapsed_time": "5:21:54", "remaining_time": "1:48:08", "throughput": 1487.01, "total_tokens": 28720192} {"current_steps": 136090, "total_steps": 181800, "loss": 0.0334, "lr": 9.026483895258159e-06, "epoch": 14.971397139713972, "percentage": 74.86, "elapsed_time": "5:21:54", "remaining_time": "1:48:07", "throughput": 1487.01, "total_tokens": 28721248} {"current_steps": 136095, "total_steps": 181800, "loss": 0.0026, "lr": 9.024637702277664e-06, "epoch": 14.971947194719473, "percentage": 74.86, "elapsed_time": "5:21:55", "remaining_time": "1:48:06", "throughput": 1487.01, "total_tokens": 28722272} {"current_steps": 136100, "total_steps": 181800, "loss": 0.002, "lr": 9.022791656534407e-06, "epoch": 14.972497249724972, "percentage": 74.86, "elapsed_time": "5:21:56", "remaining_time": "1:48:06", "throughput": 1487.01, "total_tokens": 28723328} {"current_steps": 136105, "total_steps": 181800, "loss": 0.0048, "lr": 9.020945758045424e-06, "epoch": 14.973047304730473, "percentage": 74.87, "elapsed_time": "5:21:56", "remaining_time": "1:48:05", "throughput": 1487.02, "total_tokens": 28724416} {"current_steps": 136110, "total_steps": 181800, "loss": 0.0521, "lr": 9.019100006827714e-06, "epoch": 14.973597359735974, "percentage": 74.87, "elapsed_time": "5:21:57", "remaining_time": "1:48:04", "throughput": 1487.02, "total_tokens": 28725472} {"current_steps": 136115, "total_steps": 181800, "loss": 0.0042, "lr": 9.017254402898274e-06, "epoch": 14.974147414741473, "percentage": 74.87, "elapsed_time": "5:21:58", "remaining_time": "1:48:03", "throughput": 1487.02, "total_tokens": 28726560} {"current_steps": 136120, "total_steps": 181800, "loss": 0.0068, "lr": 9.015408946274148e-06, "epoch": 14.974697469746975, "percentage": 74.87, "elapsed_time": "5:21:58", "remaining_time": "1:48:03", "throughput": 1487.02, "total_tokens": 28727584} {"current_steps": 136125, "total_steps": 181800, "loss": 0.0134, "lr": 9.013563636972319e-06, "epoch": 14.975247524752476, "percentage": 74.88, "elapsed_time": "5:21:59", "remaining_time": "1:48:02", "throughput": 1487.02, "total_tokens": 28728576} {"current_steps": 136130, "total_steps": 181800, "loss": 0.1542, "lr": 9.011718475009812e-06, "epoch": 14.975797579757975, "percentage": 74.88, "elapsed_time": "5:22:00", "remaining_time": "1:48:01", "throughput": 1487.02, "total_tokens": 28729664} {"current_steps": 136135, "total_steps": 181800, "loss": 0.0027, "lr": 9.009873460403626e-06, "epoch": 14.976347634763476, "percentage": 74.88, "elapsed_time": "5:22:00", "remaining_time": "1:48:01", "throughput": 1487.02, "total_tokens": 28730720} {"current_steps": 136140, "total_steps": 181800, "loss": 0.0011, "lr": 9.00802859317075e-06, "epoch": 14.976897689768977, "percentage": 74.88, "elapsed_time": "5:22:01", "remaining_time": "1:48:00", "throughput": 1487.02, "total_tokens": 28731712} {"current_steps": 136145, "total_steps": 181800, "loss": 0.1272, "lr": 9.006183873328206e-06, "epoch": 14.977447744774478, "percentage": 74.89, "elapsed_time": "5:22:02", "remaining_time": "1:47:59", "throughput": 1487.02, "total_tokens": 28732768} {"current_steps": 136150, "total_steps": 181800, "loss": 0.0925, "lr": 9.004339300892986e-06, "epoch": 14.977997799779978, "percentage": 74.89, "elapsed_time": "5:22:03", "remaining_time": "1:47:58", "throughput": 1487.02, "total_tokens": 28733792} {"current_steps": 136155, "total_steps": 181800, "loss": 0.0101, "lr": 9.002494875882106e-06, "epoch": 14.978547854785479, "percentage": 74.89, "elapsed_time": "5:22:03", "remaining_time": "1:47:58", "throughput": 1487.02, "total_tokens": 28734816} {"current_steps": 136160, "total_steps": 181800, "loss": 0.0482, "lr": 9.000650598312554e-06, "epoch": 14.97909790979098, "percentage": 74.9, "elapsed_time": "5:22:04", "remaining_time": "1:47:57", "throughput": 1487.02, "total_tokens": 28735808} {"current_steps": 136165, "total_steps": 181800, "loss": 0.0027, "lr": 8.998806468201321e-06, "epoch": 14.979647964796479, "percentage": 74.9, "elapsed_time": "5:22:05", "remaining_time": "1:47:56", "throughput": 1487.02, "total_tokens": 28736896} {"current_steps": 136170, "total_steps": 181800, "loss": 0.0821, "lr": 8.99696248556542e-06, "epoch": 14.98019801980198, "percentage": 74.9, "elapsed_time": "5:22:05", "remaining_time": "1:47:55", "throughput": 1487.02, "total_tokens": 28737920} {"current_steps": 136175, "total_steps": 181800, "loss": 0.0031, "lr": 8.995118650421817e-06, "epoch": 14.980748074807481, "percentage": 74.9, "elapsed_time": "5:22:06", "remaining_time": "1:47:55", "throughput": 1487.03, "total_tokens": 28738976} {"current_steps": 136180, "total_steps": 181800, "loss": 0.0326, "lr": 8.993274962787543e-06, "epoch": 14.98129812981298, "percentage": 74.91, "elapsed_time": "5:22:07", "remaining_time": "1:47:54", "throughput": 1487.03, "total_tokens": 28740032} {"current_steps": 136185, "total_steps": 181800, "loss": 0.0611, "lr": 8.991431422679573e-06, "epoch": 14.981848184818482, "percentage": 74.91, "elapsed_time": "5:22:07", "remaining_time": "1:47:53", "throughput": 1487.03, "total_tokens": 28741088} {"current_steps": 136190, "total_steps": 181800, "loss": 0.0017, "lr": 8.98958803011489e-06, "epoch": 14.982398239823983, "percentage": 74.91, "elapsed_time": "5:22:08", "remaining_time": "1:47:53", "throughput": 1487.03, "total_tokens": 28742176} {"current_steps": 136195, "total_steps": 181800, "loss": 0.0039, "lr": 8.9877447851105e-06, "epoch": 14.982948294829484, "percentage": 74.91, "elapsed_time": "5:22:09", "remaining_time": "1:47:52", "throughput": 1487.03, "total_tokens": 28743168} {"current_steps": 136200, "total_steps": 181800, "loss": 0.0375, "lr": 8.985901687683374e-06, "epoch": 14.983498349834983, "percentage": 74.92, "elapsed_time": "5:22:09", "remaining_time": "1:47:51", "throughput": 1487.03, "total_tokens": 28744224} {"current_steps": 136205, "total_steps": 181800, "loss": 0.0173, "lr": 8.984058737850506e-06, "epoch": 14.984048404840484, "percentage": 74.92, "elapsed_time": "5:22:10", "remaining_time": "1:47:50", "throughput": 1487.03, "total_tokens": 28745280} {"current_steps": 136210, "total_steps": 181800, "loss": 0.1429, "lr": 8.982215935628897e-06, "epoch": 14.984598459845985, "percentage": 74.92, "elapsed_time": "5:22:11", "remaining_time": "1:47:50", "throughput": 1487.03, "total_tokens": 28746304} {"current_steps": 136215, "total_steps": 181800, "loss": 0.005, "lr": 8.980373281035504e-06, "epoch": 14.985148514851485, "percentage": 74.93, "elapsed_time": "5:22:12", "remaining_time": "1:47:49", "throughput": 1487.04, "total_tokens": 28747392} {"current_steps": 136220, "total_steps": 181800, "loss": 0.0507, "lr": 8.978530774087335e-06, "epoch": 14.985698569856986, "percentage": 74.93, "elapsed_time": "5:22:12", "remaining_time": "1:47:48", "throughput": 1487.04, "total_tokens": 28748448} {"current_steps": 136225, "total_steps": 181800, "loss": 0.0399, "lr": 8.976688414801349e-06, "epoch": 14.986248624862487, "percentage": 74.93, "elapsed_time": "5:22:13", "remaining_time": "1:47:48", "throughput": 1487.04, "total_tokens": 28749568} {"current_steps": 136230, "total_steps": 181800, "loss": 0.1159, "lr": 8.974846203194547e-06, "epoch": 14.986798679867986, "percentage": 74.93, "elapsed_time": "5:22:14", "remaining_time": "1:47:47", "throughput": 1487.04, "total_tokens": 28750624} {"current_steps": 136235, "total_steps": 181800, "loss": 0.0873, "lr": 8.973004139283892e-06, "epoch": 14.987348734873487, "percentage": 74.94, "elapsed_time": "5:22:14", "remaining_time": "1:47:46", "throughput": 1487.04, "total_tokens": 28751648} {"current_steps": 136240, "total_steps": 181800, "loss": 0.0977, "lr": 8.971162223086363e-06, "epoch": 14.987898789878988, "percentage": 74.94, "elapsed_time": "5:22:15", "remaining_time": "1:47:45", "throughput": 1487.05, "total_tokens": 28752736} {"current_steps": 136245, "total_steps": 181800, "loss": 0.0109, "lr": 8.969320454618951e-06, "epoch": 14.988448844884488, "percentage": 74.94, "elapsed_time": "5:22:16", "remaining_time": "1:47:45", "throughput": 1487.05, "total_tokens": 28753792} {"current_steps": 136250, "total_steps": 181800, "loss": 0.0118, "lr": 8.967478833898612e-06, "epoch": 14.988998899889989, "percentage": 74.94, "elapsed_time": "5:22:16", "remaining_time": "1:47:44", "throughput": 1487.05, "total_tokens": 28754880} {"current_steps": 136255, "total_steps": 181800, "loss": 0.0015, "lr": 8.965637360942335e-06, "epoch": 14.98954895489549, "percentage": 74.95, "elapsed_time": "5:22:17", "remaining_time": "1:47:43", "throughput": 1487.05, "total_tokens": 28755936} {"current_steps": 136260, "total_steps": 181800, "loss": 0.0028, "lr": 8.963796035767077e-06, "epoch": 14.990099009900991, "percentage": 74.95, "elapsed_time": "5:22:18", "remaining_time": "1:47:43", "throughput": 1487.06, "total_tokens": 28757024} {"current_steps": 136265, "total_steps": 181800, "loss": 0.0051, "lr": 8.961954858389815e-06, "epoch": 14.99064906490649, "percentage": 74.95, "elapsed_time": "5:22:18", "remaining_time": "1:47:42", "throughput": 1487.06, "total_tokens": 28758080} {"current_steps": 136270, "total_steps": 181800, "loss": 0.0084, "lr": 8.960113828827529e-06, "epoch": 14.991199119911991, "percentage": 74.96, "elapsed_time": "5:22:19", "remaining_time": "1:47:41", "throughput": 1487.06, "total_tokens": 28759136} {"current_steps": 136275, "total_steps": 181800, "loss": 0.0072, "lr": 8.958272947097168e-06, "epoch": 14.991749174917492, "percentage": 74.96, "elapsed_time": "5:22:20", "remaining_time": "1:47:40", "throughput": 1487.06, "total_tokens": 28760224} {"current_steps": 136280, "total_steps": 181800, "loss": 0.0838, "lr": 8.956432213215715e-06, "epoch": 14.992299229922992, "percentage": 74.96, "elapsed_time": "5:22:20", "remaining_time": "1:47:40", "throughput": 1487.06, "total_tokens": 28761280} {"current_steps": 136285, "total_steps": 181800, "loss": 0.0949, "lr": 8.95459162720013e-06, "epoch": 14.992849284928493, "percentage": 74.96, "elapsed_time": "5:22:21", "remaining_time": "1:47:39", "throughput": 1487.07, "total_tokens": 28762368} {"current_steps": 136290, "total_steps": 181800, "loss": 0.0114, "lr": 8.952751189067355e-06, "epoch": 14.993399339933994, "percentage": 74.97, "elapsed_time": "5:22:22", "remaining_time": "1:47:38", "throughput": 1487.07, "total_tokens": 28763456} {"current_steps": 136295, "total_steps": 181800, "loss": 0.0798, "lr": 8.950910898834392e-06, "epoch": 14.993949394939493, "percentage": 74.97, "elapsed_time": "5:22:23", "remaining_time": "1:47:38", "throughput": 1487.07, "total_tokens": 28764544} {"current_steps": 136300, "total_steps": 181800, "loss": 0.0021, "lr": 8.94907075651818e-06, "epoch": 14.994499449944994, "percentage": 74.97, "elapsed_time": "5:22:23", "remaining_time": "1:47:37", "throughput": 1487.07, "total_tokens": 28765600} {"current_steps": 136305, "total_steps": 181800, "loss": 0.0009, "lr": 8.947230762135672e-06, "epoch": 14.995049504950495, "percentage": 74.98, "elapsed_time": "5:22:24", "remaining_time": "1:47:36", "throughput": 1487.07, "total_tokens": 28766592} {"current_steps": 136310, "total_steps": 181800, "loss": 0.0229, "lr": 8.945390915703845e-06, "epoch": 14.995599559955995, "percentage": 74.98, "elapsed_time": "5:22:25", "remaining_time": "1:47:35", "throughput": 1487.07, "total_tokens": 28767584} {"current_steps": 136315, "total_steps": 181800, "loss": 0.0568, "lr": 8.943551217239637e-06, "epoch": 14.996149614961496, "percentage": 74.98, "elapsed_time": "5:22:25", "remaining_time": "1:47:35", "throughput": 1487.07, "total_tokens": 28768608} {"current_steps": 136320, "total_steps": 181800, "loss": 0.0031, "lr": 8.941711666760014e-06, "epoch": 14.996699669966997, "percentage": 74.98, "elapsed_time": "5:22:26", "remaining_time": "1:47:34", "throughput": 1487.07, "total_tokens": 28769664} {"current_steps": 136325, "total_steps": 181800, "loss": 0.0025, "lr": 8.939872264281937e-06, "epoch": 14.997249724972498, "percentage": 74.99, "elapsed_time": "5:22:27", "remaining_time": "1:47:33", "throughput": 1487.08, "total_tokens": 28770752} {"current_steps": 136330, "total_steps": 181800, "loss": 0.0043, "lr": 8.938033009822342e-06, "epoch": 14.997799779977997, "percentage": 74.99, "elapsed_time": "5:22:27", "remaining_time": "1:47:33", "throughput": 1487.08, "total_tokens": 28771776} {"current_steps": 136335, "total_steps": 181800, "loss": 0.0103, "lr": 8.9361939033982e-06, "epoch": 14.998349834983498, "percentage": 74.99, "elapsed_time": "5:22:28", "remaining_time": "1:47:32", "throughput": 1487.07, "total_tokens": 28772768} {"current_steps": 136340, "total_steps": 181800, "loss": 0.0241, "lr": 8.934354945026437e-06, "epoch": 14.998899889989, "percentage": 74.99, "elapsed_time": "5:22:29", "remaining_time": "1:47:31", "throughput": 1487.08, "total_tokens": 28773888} {"current_steps": 136345, "total_steps": 181800, "loss": 0.0035, "lr": 8.932516134724028e-06, "epoch": 14.999449944994499, "percentage": 75.0, "elapsed_time": "5:22:29", "remaining_time": "1:47:30", "throughput": 1487.08, "total_tokens": 28774880} {"current_steps": 136350, "total_steps": 181800, "loss": 0.0197, "lr": 8.930677472507898e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "5:22:30", "remaining_time": "1:47:30", "throughput": 1487.07, "total_tokens": 28775840} {"current_steps": 136350, "total_steps": 181800, "eval_loss": 0.07325445860624313, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "5:23:07", "remaining_time": "1:47:42", "throughput": 1484.23, "total_tokens": 28775840} {"current_steps": 136355, "total_steps": 181800, "loss": 0.0133, "lr": 8.928838958395005e-06, "epoch": 15.000550055005501, "percentage": 75.0, "elapsed_time": "5:23:09", "remaining_time": "1:47:42", "throughput": 1484.11, "total_tokens": 28776896} {"current_steps": 136360, "total_steps": 181800, "loss": 0.0076, "lr": 8.927000592402298e-06, "epoch": 15.001100110011, "percentage": 75.01, "elapsed_time": "5:23:10", "remaining_time": "1:47:41", "throughput": 1484.11, "total_tokens": 28777952} {"current_steps": 136365, "total_steps": 181800, "loss": 0.044, "lr": 8.925162374546705e-06, "epoch": 15.001650165016502, "percentage": 75.01, "elapsed_time": "5:23:11", "remaining_time": "1:47:40", "throughput": 1484.11, "total_tokens": 28778912} {"current_steps": 136370, "total_steps": 181800, "loss": 0.0018, "lr": 8.923324304845188e-06, "epoch": 15.002200220022003, "percentage": 75.01, "elapsed_time": "5:23:12", "remaining_time": "1:47:40", "throughput": 1484.11, "total_tokens": 28780000} {"current_steps": 136375, "total_steps": 181800, "loss": 0.0495, "lr": 8.921486383314668e-06, "epoch": 15.002750275027502, "percentage": 75.01, "elapsed_time": "5:23:12", "remaining_time": "1:47:39", "throughput": 1484.11, "total_tokens": 28781088} {"current_steps": 136380, "total_steps": 181800, "loss": 0.04, "lr": 8.91964860997209e-06, "epoch": 15.003300330033003, "percentage": 75.02, "elapsed_time": "5:23:13", "remaining_time": "1:47:38", "throughput": 1484.11, "total_tokens": 28782144} {"current_steps": 136385, "total_steps": 181800, "loss": 0.0026, "lr": 8.917810984834405e-06, "epoch": 15.003850385038504, "percentage": 75.02, "elapsed_time": "5:23:14", "remaining_time": "1:47:38", "throughput": 1484.12, "total_tokens": 28783200} {"current_steps": 136390, "total_steps": 181800, "loss": 0.0478, "lr": 8.91597350791853e-06, "epoch": 15.004400440044005, "percentage": 75.02, "elapsed_time": "5:23:14", "remaining_time": "1:47:37", "throughput": 1484.11, "total_tokens": 28784288} {"current_steps": 136395, "total_steps": 181800, "loss": 0.037, "lr": 8.914136179241416e-06, "epoch": 15.004950495049505, "percentage": 75.02, "elapsed_time": "5:23:15", "remaining_time": "1:47:36", "throughput": 1484.11, "total_tokens": 28785344} {"current_steps": 136400, "total_steps": 181800, "loss": 0.0044, "lr": 8.912298998819993e-06, "epoch": 15.005500550055006, "percentage": 75.03, "elapsed_time": "5:23:16", "remaining_time": "1:47:35", "throughput": 1484.11, "total_tokens": 28786400} {"current_steps": 136405, "total_steps": 181800, "loss": 0.007, "lr": 8.91046196667118e-06, "epoch": 15.006050605060507, "percentage": 75.03, "elapsed_time": "5:23:17", "remaining_time": "1:47:35", "throughput": 1484.11, "total_tokens": 28787488} {"current_steps": 136410, "total_steps": 181800, "loss": 0.0088, "lr": 8.908625082811919e-06, "epoch": 15.006600660066006, "percentage": 75.03, "elapsed_time": "5:23:17", "remaining_time": "1:47:34", "throughput": 1484.1, "total_tokens": 28788480} {"current_steps": 136415, "total_steps": 181800, "loss": 0.007, "lr": 8.90678834725914e-06, "epoch": 15.007150715071507, "percentage": 75.04, "elapsed_time": "5:23:18", "remaining_time": "1:47:33", "throughput": 1484.11, "total_tokens": 28789600} {"current_steps": 136420, "total_steps": 181800, "loss": 0.0037, "lr": 8.904951760029781e-06, "epoch": 15.007700770077008, "percentage": 75.04, "elapsed_time": "5:23:19", "remaining_time": "1:47:33", "throughput": 1484.11, "total_tokens": 28790592} {"current_steps": 136425, "total_steps": 181800, "loss": 0.0053, "lr": 8.903115321140757e-06, "epoch": 15.008250825082508, "percentage": 75.04, "elapsed_time": "5:23:19", "remaining_time": "1:47:32", "throughput": 1484.1, "total_tokens": 28791584} {"current_steps": 136430, "total_steps": 181800, "loss": 0.0051, "lr": 8.901279030608984e-06, "epoch": 15.008800880088009, "percentage": 75.04, "elapsed_time": "5:23:20", "remaining_time": "1:47:31", "throughput": 1484.11, "total_tokens": 28792704} {"current_steps": 136435, "total_steps": 181800, "loss": 0.1257, "lr": 8.899442888451401e-06, "epoch": 15.00935093509351, "percentage": 75.05, "elapsed_time": "5:23:21", "remaining_time": "1:47:30", "throughput": 1484.11, "total_tokens": 28793728} {"current_steps": 136440, "total_steps": 181800, "loss": 0.0987, "lr": 8.897606894684923e-06, "epoch": 15.009900990099009, "percentage": 75.05, "elapsed_time": "5:23:22", "remaining_time": "1:47:30", "throughput": 1484.11, "total_tokens": 28794720} {"current_steps": 136445, "total_steps": 181800, "loss": 0.0056, "lr": 8.895771049326487e-06, "epoch": 15.01045104510451, "percentage": 75.05, "elapsed_time": "5:23:22", "remaining_time": "1:47:29", "throughput": 1484.11, "total_tokens": 28795776} {"current_steps": 136450, "total_steps": 181800, "loss": 0.0034, "lr": 8.893935352393001e-06, "epoch": 15.011001100110011, "percentage": 75.06, "elapsed_time": "5:23:23", "remaining_time": "1:47:28", "throughput": 1484.11, "total_tokens": 28796864} {"current_steps": 136455, "total_steps": 181800, "loss": 0.0396, "lr": 8.892099803901377e-06, "epoch": 15.011551155115512, "percentage": 75.06, "elapsed_time": "5:23:24", "remaining_time": "1:47:28", "throughput": 1484.11, "total_tokens": 28797888} {"current_steps": 136460, "total_steps": 181800, "loss": 0.0183, "lr": 8.890264403868545e-06, "epoch": 15.012101210121012, "percentage": 75.06, "elapsed_time": "5:23:24", "remaining_time": "1:47:27", "throughput": 1484.12, "total_tokens": 28799008} {"current_steps": 136465, "total_steps": 181800, "loss": 0.0058, "lr": 8.888429152311412e-06, "epoch": 15.012651265126513, "percentage": 75.06, "elapsed_time": "5:23:25", "remaining_time": "1:47:26", "throughput": 1484.12, "total_tokens": 28800096} {"current_steps": 136470, "total_steps": 181800, "loss": 0.0037, "lr": 8.886594049246893e-06, "epoch": 15.013201320132014, "percentage": 75.07, "elapsed_time": "5:23:26", "remaining_time": "1:47:25", "throughput": 1484.12, "total_tokens": 28801152} {"current_steps": 136475, "total_steps": 181800, "loss": 0.0051, "lr": 8.884759094691913e-06, "epoch": 15.013751375137513, "percentage": 75.07, "elapsed_time": "5:23:26", "remaining_time": "1:47:25", "throughput": 1484.12, "total_tokens": 28802176} {"current_steps": 136480, "total_steps": 181800, "loss": 0.0052, "lr": 8.882924288663368e-06, "epoch": 15.014301430143014, "percentage": 75.07, "elapsed_time": "5:23:27", "remaining_time": "1:47:24", "throughput": 1484.12, "total_tokens": 28803232} {"current_steps": 136485, "total_steps": 181800, "loss": 0.0036, "lr": 8.881089631178185e-06, "epoch": 15.014851485148515, "percentage": 75.07, "elapsed_time": "5:23:28", "remaining_time": "1:47:23", "throughput": 1484.12, "total_tokens": 28804288} {"current_steps": 136490, "total_steps": 181800, "loss": 0.0038, "lr": 8.879255122253255e-06, "epoch": 15.015401540154015, "percentage": 75.08, "elapsed_time": "5:23:28", "remaining_time": "1:47:23", "throughput": 1484.12, "total_tokens": 28805344} {"current_steps": 136495, "total_steps": 181800, "loss": 0.1273, "lr": 8.877420761905498e-06, "epoch": 15.015951595159516, "percentage": 75.08, "elapsed_time": "5:23:29", "remaining_time": "1:47:22", "throughput": 1484.12, "total_tokens": 28806336} {"current_steps": 136500, "total_steps": 181800, "loss": 0.0042, "lr": 8.875586550151821e-06, "epoch": 15.016501650165017, "percentage": 75.08, "elapsed_time": "5:23:30", "remaining_time": "1:47:21", "throughput": 1484.12, "total_tokens": 28807424} {"current_steps": 136505, "total_steps": 181800, "loss": 0.0185, "lr": 8.873752487009121e-06, "epoch": 15.017051705170518, "percentage": 75.09, "elapsed_time": "5:23:31", "remaining_time": "1:47:20", "throughput": 1484.12, "total_tokens": 28808416} {"current_steps": 136510, "total_steps": 181800, "loss": 0.0017, "lr": 8.871918572494314e-06, "epoch": 15.017601760176017, "percentage": 75.09, "elapsed_time": "5:23:31", "remaining_time": "1:47:20", "throughput": 1484.13, "total_tokens": 28809504} {"current_steps": 136515, "total_steps": 181800, "loss": 0.1168, "lr": 8.870084806624293e-06, "epoch": 15.018151815181518, "percentage": 75.09, "elapsed_time": "5:23:32", "remaining_time": "1:47:19", "throughput": 1484.13, "total_tokens": 28810528} {"current_steps": 136520, "total_steps": 181800, "loss": 0.0014, "lr": 8.868251189415953e-06, "epoch": 15.01870187018702, "percentage": 75.09, "elapsed_time": "5:23:33", "remaining_time": "1:47:18", "throughput": 1484.12, "total_tokens": 28811520} {"current_steps": 136525, "total_steps": 181800, "loss": 0.0011, "lr": 8.8664177208862e-06, "epoch": 15.019251925192519, "percentage": 75.1, "elapsed_time": "5:23:33", "remaining_time": "1:47:18", "throughput": 1484.13, "total_tokens": 28812672} {"current_steps": 136530, "total_steps": 181800, "loss": 0.0151, "lr": 8.864584401051934e-06, "epoch": 15.01980198019802, "percentage": 75.1, "elapsed_time": "5:23:34", "remaining_time": "1:47:17", "throughput": 1484.13, "total_tokens": 28813664} {"current_steps": 136535, "total_steps": 181800, "loss": 0.0621, "lr": 8.86275122993006e-06, "epoch": 15.020352035203521, "percentage": 75.1, "elapsed_time": "5:23:35", "remaining_time": "1:47:16", "throughput": 1484.13, "total_tokens": 28814656} {"current_steps": 136540, "total_steps": 181800, "loss": 0.0019, "lr": 8.860918207537464e-06, "epoch": 15.02090209020902, "percentage": 75.1, "elapsed_time": "5:23:35", "remaining_time": "1:47:15", "throughput": 1484.13, "total_tokens": 28815712} {"current_steps": 136545, "total_steps": 181800, "loss": 0.0054, "lr": 8.859085333891032e-06, "epoch": 15.021452145214521, "percentage": 75.11, "elapsed_time": "5:23:36", "remaining_time": "1:47:15", "throughput": 1484.13, "total_tokens": 28816832} {"current_steps": 136550, "total_steps": 181800, "loss": 0.0096, "lr": 8.857252609007666e-06, "epoch": 15.022002200220022, "percentage": 75.11, "elapsed_time": "5:23:37", "remaining_time": "1:47:14", "throughput": 1484.13, "total_tokens": 28817856} {"current_steps": 136555, "total_steps": 181800, "loss": 0.0048, "lr": 8.855420032904255e-06, "epoch": 15.022552255225522, "percentage": 75.11, "elapsed_time": "5:23:37", "remaining_time": "1:47:13", "throughput": 1484.13, "total_tokens": 28818880} {"current_steps": 136560, "total_steps": 181800, "loss": 0.0102, "lr": 8.853587605597702e-06, "epoch": 15.023102310231023, "percentage": 75.12, "elapsed_time": "5:23:38", "remaining_time": "1:47:13", "throughput": 1484.14, "total_tokens": 28819968} {"current_steps": 136565, "total_steps": 181800, "loss": 0.0043, "lr": 8.851755327104882e-06, "epoch": 15.023652365236524, "percentage": 75.12, "elapsed_time": "5:23:39", "remaining_time": "1:47:12", "throughput": 1484.13, "total_tokens": 28820928} {"current_steps": 136570, "total_steps": 181800, "loss": 0.0505, "lr": 8.849923197442675e-06, "epoch": 15.024202420242025, "percentage": 75.12, "elapsed_time": "5:23:40", "remaining_time": "1:47:11", "throughput": 1484.13, "total_tokens": 28821920} {"current_steps": 136575, "total_steps": 181800, "loss": 0.0358, "lr": 8.848091216627988e-06, "epoch": 15.024752475247524, "percentage": 75.12, "elapsed_time": "5:23:40", "remaining_time": "1:47:10", "throughput": 1484.13, "total_tokens": 28822944} {"current_steps": 136580, "total_steps": 181800, "loss": 0.0051, "lr": 8.846259384677682e-06, "epoch": 15.025302530253025, "percentage": 75.13, "elapsed_time": "5:23:41", "remaining_time": "1:47:10", "throughput": 1484.13, "total_tokens": 28823968} {"current_steps": 136585, "total_steps": 181800, "loss": 0.0022, "lr": 8.844427701608654e-06, "epoch": 15.025852585258527, "percentage": 75.13, "elapsed_time": "5:23:42", "remaining_time": "1:47:09", "throughput": 1484.13, "total_tokens": 28825024} {"current_steps": 136590, "total_steps": 181800, "loss": 0.0088, "lr": 8.842596167437792e-06, "epoch": 15.026402640264026, "percentage": 75.13, "elapsed_time": "5:23:42", "remaining_time": "1:47:08", "throughput": 1484.13, "total_tokens": 28826080} {"current_steps": 136595, "total_steps": 181800, "loss": 0.0125, "lr": 8.84076478218196e-06, "epoch": 15.026952695269527, "percentage": 75.13, "elapsed_time": "5:23:43", "remaining_time": "1:47:08", "throughput": 1484.14, "total_tokens": 28827136} {"current_steps": 136600, "total_steps": 181800, "loss": 0.059, "lr": 8.838933545858053e-06, "epoch": 15.027502750275028, "percentage": 75.14, "elapsed_time": "5:23:44", "remaining_time": "1:47:07", "throughput": 1484.14, "total_tokens": 28828224} {"current_steps": 136605, "total_steps": 181800, "loss": 0.0052, "lr": 8.837102458482931e-06, "epoch": 15.028052805280527, "percentage": 75.14, "elapsed_time": "5:23:44", "remaining_time": "1:47:06", "throughput": 1484.14, "total_tokens": 28829248} {"current_steps": 136610, "total_steps": 181800, "loss": 0.017, "lr": 8.83527152007348e-06, "epoch": 15.028602860286028, "percentage": 75.14, "elapsed_time": "5:23:45", "remaining_time": "1:47:05", "throughput": 1484.14, "total_tokens": 28830240} {"current_steps": 136615, "total_steps": 181800, "loss": 0.0062, "lr": 8.833440730646585e-06, "epoch": 15.02915291529153, "percentage": 75.15, "elapsed_time": "5:23:46", "remaining_time": "1:47:05", "throughput": 1484.14, "total_tokens": 28831328} {"current_steps": 136620, "total_steps": 181800, "loss": 0.0453, "lr": 8.8316100902191e-06, "epoch": 15.029702970297029, "percentage": 75.15, "elapsed_time": "5:23:46", "remaining_time": "1:47:04", "throughput": 1484.14, "total_tokens": 28832384} {"current_steps": 136625, "total_steps": 181800, "loss": 0.0128, "lr": 8.829779598807913e-06, "epoch": 15.03025302530253, "percentage": 75.15, "elapsed_time": "5:23:47", "remaining_time": "1:47:03", "throughput": 1484.14, "total_tokens": 28833408} {"current_steps": 136630, "total_steps": 181800, "loss": 0.134, "lr": 8.827949256429882e-06, "epoch": 15.030803080308031, "percentage": 75.15, "elapsed_time": "5:23:48", "remaining_time": "1:47:03", "throughput": 1484.14, "total_tokens": 28834464} {"current_steps": 136635, "total_steps": 181800, "loss": 0.0012, "lr": 8.826119063101893e-06, "epoch": 15.031353135313532, "percentage": 75.16, "elapsed_time": "5:23:49", "remaining_time": "1:47:02", "throughput": 1484.14, "total_tokens": 28835488} {"current_steps": 136640, "total_steps": 181800, "loss": 0.0749, "lr": 8.824289018840792e-06, "epoch": 15.031903190319031, "percentage": 75.16, "elapsed_time": "5:23:49", "remaining_time": "1:47:01", "throughput": 1484.15, "total_tokens": 28836576} {"current_steps": 136645, "total_steps": 181800, "loss": 0.0042, "lr": 8.82245912366346e-06, "epoch": 15.032453245324533, "percentage": 75.16, "elapsed_time": "5:23:50", "remaining_time": "1:47:00", "throughput": 1484.15, "total_tokens": 28837664} {"current_steps": 136650, "total_steps": 181800, "loss": 0.0044, "lr": 8.820629377586765e-06, "epoch": 15.033003300330034, "percentage": 75.17, "elapsed_time": "5:23:51", "remaining_time": "1:47:00", "throughput": 1484.15, "total_tokens": 28838720} {"current_steps": 136655, "total_steps": 181800, "loss": 0.1636, "lr": 8.818799780627556e-06, "epoch": 15.033553355335533, "percentage": 75.17, "elapsed_time": "5:23:51", "remaining_time": "1:46:59", "throughput": 1484.15, "total_tokens": 28839776} {"current_steps": 136660, "total_steps": 181800, "loss": 0.0033, "lr": 8.816970332802718e-06, "epoch": 15.034103410341034, "percentage": 75.17, "elapsed_time": "5:23:52", "remaining_time": "1:46:58", "throughput": 1484.15, "total_tokens": 28840800} {"current_steps": 136665, "total_steps": 181800, "loss": 0.0163, "lr": 8.815141034129087e-06, "epoch": 15.034653465346535, "percentage": 75.17, "elapsed_time": "5:23:53", "remaining_time": "1:46:58", "throughput": 1484.15, "total_tokens": 28841888} {"current_steps": 136670, "total_steps": 181800, "loss": 0.0669, "lr": 8.813311884623535e-06, "epoch": 15.035203520352034, "percentage": 75.18, "elapsed_time": "5:23:53", "remaining_time": "1:46:57", "throughput": 1484.16, "total_tokens": 28842944} {"current_steps": 136675, "total_steps": 181800, "loss": 0.0212, "lr": 8.81148288430293e-06, "epoch": 15.035753575357536, "percentage": 75.18, "elapsed_time": "5:23:54", "remaining_time": "1:46:56", "throughput": 1484.16, "total_tokens": 28844000} {"current_steps": 136680, "total_steps": 181800, "loss": 0.0424, "lr": 8.80965403318412e-06, "epoch": 15.036303630363037, "percentage": 75.18, "elapsed_time": "5:23:55", "remaining_time": "1:46:55", "throughput": 1484.16, "total_tokens": 28845024} {"current_steps": 136685, "total_steps": 181800, "loss": 0.0012, "lr": 8.807825331283951e-06, "epoch": 15.036853685368538, "percentage": 75.18, "elapsed_time": "5:23:55", "remaining_time": "1:46:55", "throughput": 1484.16, "total_tokens": 28846112} {"current_steps": 136690, "total_steps": 181800, "loss": 0.0032, "lr": 8.805996778619293e-06, "epoch": 15.037403740374037, "percentage": 75.19, "elapsed_time": "5:23:56", "remaining_time": "1:46:54", "throughput": 1484.16, "total_tokens": 28847104} {"current_steps": 136695, "total_steps": 181800, "loss": 0.0104, "lr": 8.804168375206983e-06, "epoch": 15.037953795379538, "percentage": 75.19, "elapsed_time": "5:23:57", "remaining_time": "1:46:53", "throughput": 1484.16, "total_tokens": 28848160} {"current_steps": 136700, "total_steps": 181800, "loss": 0.0259, "lr": 8.802340121063885e-06, "epoch": 15.03850385038504, "percentage": 75.19, "elapsed_time": "5:23:58", "remaining_time": "1:46:52", "throughput": 1484.16, "total_tokens": 28849152} {"current_steps": 136705, "total_steps": 181800, "loss": 0.0667, "lr": 8.800512016206852e-06, "epoch": 15.039053905390539, "percentage": 75.2, "elapsed_time": "5:23:58", "remaining_time": "1:46:52", "throughput": 1484.16, "total_tokens": 28850272} {"current_steps": 136710, "total_steps": 181800, "loss": 0.029, "lr": 8.798684060652718e-06, "epoch": 15.03960396039604, "percentage": 75.2, "elapsed_time": "5:23:59", "remaining_time": "1:46:51", "throughput": 1484.16, "total_tokens": 28851296} {"current_steps": 136715, "total_steps": 181800, "loss": 0.0622, "lr": 8.796856254418348e-06, "epoch": 15.04015401540154, "percentage": 75.2, "elapsed_time": "5:24:00", "remaining_time": "1:46:50", "throughput": 1484.16, "total_tokens": 28852320} {"current_steps": 136720, "total_steps": 181800, "loss": 0.0026, "lr": 8.79502859752057e-06, "epoch": 15.04070407040704, "percentage": 75.2, "elapsed_time": "5:24:00", "remaining_time": "1:46:50", "throughput": 1484.16, "total_tokens": 28853376} {"current_steps": 136725, "total_steps": 181800, "loss": 0.0565, "lr": 8.793201089976236e-06, "epoch": 15.041254125412541, "percentage": 75.21, "elapsed_time": "5:24:01", "remaining_time": "1:46:49", "throughput": 1484.16, "total_tokens": 28854400} {"current_steps": 136730, "total_steps": 181800, "loss": 0.0011, "lr": 8.791373731802202e-06, "epoch": 15.041804180418042, "percentage": 75.21, "elapsed_time": "5:24:02", "remaining_time": "1:46:48", "throughput": 1484.16, "total_tokens": 28855424} {"current_steps": 136735, "total_steps": 181800, "loss": 0.0017, "lr": 8.789546523015288e-06, "epoch": 15.042354235423542, "percentage": 75.21, "elapsed_time": "5:24:02", "remaining_time": "1:46:47", "throughput": 1484.17, "total_tokens": 28856480} {"current_steps": 136740, "total_steps": 181800, "loss": 0.1008, "lr": 8.787719463632355e-06, "epoch": 15.042904290429043, "percentage": 75.21, "elapsed_time": "5:24:03", "remaining_time": "1:46:47", "throughput": 1484.17, "total_tokens": 28857568} {"current_steps": 136745, "total_steps": 181800, "loss": 0.0075, "lr": 8.785892553670225e-06, "epoch": 15.043454345434544, "percentage": 75.22, "elapsed_time": "5:24:04", "remaining_time": "1:46:46", "throughput": 1484.17, "total_tokens": 28858688} {"current_steps": 136750, "total_steps": 181800, "loss": 0.0013, "lr": 8.784065793145748e-06, "epoch": 15.044004400440045, "percentage": 75.22, "elapsed_time": "5:24:04", "remaining_time": "1:46:45", "throughput": 1484.17, "total_tokens": 28859712} {"current_steps": 136755, "total_steps": 181800, "loss": 0.0259, "lr": 8.78223918207575e-06, "epoch": 15.044554455445544, "percentage": 75.22, "elapsed_time": "5:24:05", "remaining_time": "1:46:45", "throughput": 1484.18, "total_tokens": 28860800} {"current_steps": 136760, "total_steps": 181800, "loss": 0.0436, "lr": 8.780412720477068e-06, "epoch": 15.045104510451045, "percentage": 75.23, "elapsed_time": "5:24:06", "remaining_time": "1:46:44", "throughput": 1484.18, "total_tokens": 28861824} {"current_steps": 136765, "total_steps": 181800, "loss": 0.0084, "lr": 8.778586408366552e-06, "epoch": 15.045654565456546, "percentage": 75.23, "elapsed_time": "5:24:07", "remaining_time": "1:46:43", "throughput": 1484.18, "total_tokens": 28862880} {"current_steps": 136770, "total_steps": 181800, "loss": 0.0053, "lr": 8.77676024576101e-06, "epoch": 15.046204620462046, "percentage": 75.23, "elapsed_time": "5:24:07", "remaining_time": "1:46:42", "throughput": 1484.18, "total_tokens": 28863936} {"current_steps": 136775, "total_steps": 181800, "loss": 0.043, "lr": 8.774934232677292e-06, "epoch": 15.046754675467547, "percentage": 75.23, "elapsed_time": "5:24:08", "remaining_time": "1:46:42", "throughput": 1484.19, "total_tokens": 28865056} {"current_steps": 136780, "total_steps": 181800, "loss": 0.0437, "lr": 8.773108369132213e-06, "epoch": 15.047304730473048, "percentage": 75.24, "elapsed_time": "5:24:09", "remaining_time": "1:46:41", "throughput": 1484.18, "total_tokens": 28866048} {"current_steps": 136785, "total_steps": 181800, "loss": 0.0069, "lr": 8.771282655142606e-06, "epoch": 15.047854785478547, "percentage": 75.24, "elapsed_time": "5:24:09", "remaining_time": "1:46:40", "throughput": 1484.18, "total_tokens": 28867072} {"current_steps": 136790, "total_steps": 181800, "loss": 0.1026, "lr": 8.769457090725311e-06, "epoch": 15.048404840484048, "percentage": 75.24, "elapsed_time": "5:24:10", "remaining_time": "1:46:40", "throughput": 1484.19, "total_tokens": 28868128} {"current_steps": 136795, "total_steps": 181800, "loss": 0.0712, "lr": 8.767631675897132e-06, "epoch": 15.04895489548955, "percentage": 75.24, "elapsed_time": "5:24:11", "remaining_time": "1:46:39", "throughput": 1484.19, "total_tokens": 28869152} {"current_steps": 136800, "total_steps": 181800, "loss": 0.0028, "lr": 8.76580641067491e-06, "epoch": 15.049504950495049, "percentage": 75.25, "elapsed_time": "5:24:11", "remaining_time": "1:46:38", "throughput": 1484.19, "total_tokens": 28870240} {"current_steps": 136805, "total_steps": 181800, "loss": 0.0336, "lr": 8.76398129507546e-06, "epoch": 15.05005500550055, "percentage": 75.25, "elapsed_time": "5:24:12", "remaining_time": "1:46:37", "throughput": 1484.19, "total_tokens": 28871264} {"current_steps": 136810, "total_steps": 181800, "loss": 0.0042, "lr": 8.762156329115597e-06, "epoch": 15.05060506050605, "percentage": 75.25, "elapsed_time": "5:24:13", "remaining_time": "1:46:37", "throughput": 1484.19, "total_tokens": 28872288} {"current_steps": 136815, "total_steps": 181800, "loss": 0.0781, "lr": 8.760331512812148e-06, "epoch": 15.051155115511552, "percentage": 75.26, "elapsed_time": "5:24:13", "remaining_time": "1:46:36", "throughput": 1484.19, "total_tokens": 28873280} {"current_steps": 136820, "total_steps": 181800, "loss": 0.0088, "lr": 8.75850684618193e-06, "epoch": 15.051705170517051, "percentage": 75.26, "elapsed_time": "5:24:14", "remaining_time": "1:46:35", "throughput": 1484.19, "total_tokens": 28874304} {"current_steps": 136825, "total_steps": 181800, "loss": 0.0036, "lr": 8.756682329241767e-06, "epoch": 15.052255225522552, "percentage": 75.26, "elapsed_time": "5:24:15", "remaining_time": "1:46:35", "throughput": 1484.19, "total_tokens": 28875328} {"current_steps": 136830, "total_steps": 181800, "loss": 0.0056, "lr": 8.754857962008473e-06, "epoch": 15.052805280528053, "percentage": 75.26, "elapsed_time": "5:24:15", "remaining_time": "1:46:34", "throughput": 1484.19, "total_tokens": 28876448} {"current_steps": 136835, "total_steps": 181800, "loss": 0.0214, "lr": 8.753033744498846e-06, "epoch": 15.053355335533553, "percentage": 75.27, "elapsed_time": "5:24:16", "remaining_time": "1:46:33", "throughput": 1484.19, "total_tokens": 28877504} {"current_steps": 136840, "total_steps": 181800, "loss": 0.1478, "lr": 8.751209676729712e-06, "epoch": 15.053905390539054, "percentage": 75.27, "elapsed_time": "5:24:17", "remaining_time": "1:46:32", "throughput": 1484.2, "total_tokens": 28878624} {"current_steps": 136845, "total_steps": 181800, "loss": 0.0035, "lr": 8.749385758717882e-06, "epoch": 15.054455445544555, "percentage": 75.27, "elapsed_time": "5:24:18", "remaining_time": "1:46:32", "throughput": 1484.2, "total_tokens": 28879648} {"current_steps": 136850, "total_steps": 181800, "loss": 0.004, "lr": 8.747561990480175e-06, "epoch": 15.055005500550054, "percentage": 75.28, "elapsed_time": "5:24:18", "remaining_time": "1:46:31", "throughput": 1484.2, "total_tokens": 28880672} {"current_steps": 136855, "total_steps": 181800, "loss": 0.0035, "lr": 8.745738372033388e-06, "epoch": 15.055555555555555, "percentage": 75.28, "elapsed_time": "5:24:19", "remaining_time": "1:46:30", "throughput": 1484.2, "total_tokens": 28881728} {"current_steps": 136860, "total_steps": 181800, "loss": 0.0062, "lr": 8.743914903394324e-06, "epoch": 15.056105610561056, "percentage": 75.28, "elapsed_time": "5:24:20", "remaining_time": "1:46:30", "throughput": 1484.2, "total_tokens": 28882816} {"current_steps": 136865, "total_steps": 181800, "loss": 0.008, "lr": 8.742091584579803e-06, "epoch": 15.056655665566556, "percentage": 75.28, "elapsed_time": "5:24:20", "remaining_time": "1:46:29", "throughput": 1484.21, "total_tokens": 28883904} {"current_steps": 136870, "total_steps": 181800, "loss": 0.0351, "lr": 8.740268415606615e-06, "epoch": 15.057205720572057, "percentage": 75.29, "elapsed_time": "5:24:21", "remaining_time": "1:46:28", "throughput": 1484.21, "total_tokens": 28885024} {"current_steps": 136875, "total_steps": 181800, "loss": 0.0102, "lr": 8.738445396491571e-06, "epoch": 15.057755775577558, "percentage": 75.29, "elapsed_time": "5:24:22", "remaining_time": "1:46:27", "throughput": 1484.21, "total_tokens": 28886080} {"current_steps": 136880, "total_steps": 181800, "loss": 0.0264, "lr": 8.736622527251481e-06, "epoch": 15.058305830583059, "percentage": 75.29, "elapsed_time": "5:24:22", "remaining_time": "1:46:27", "throughput": 1484.22, "total_tokens": 28887136} {"current_steps": 136885, "total_steps": 181800, "loss": 0.0031, "lr": 8.734799807903129e-06, "epoch": 15.058855885588558, "percentage": 75.29, "elapsed_time": "5:24:23", "remaining_time": "1:46:26", "throughput": 1484.22, "total_tokens": 28888256} {"current_steps": 136890, "total_steps": 181800, "loss": 0.1101, "lr": 8.73297723846333e-06, "epoch": 15.05940594059406, "percentage": 75.3, "elapsed_time": "5:24:24", "remaining_time": "1:46:25", "throughput": 1484.22, "total_tokens": 28889344} {"current_steps": 136895, "total_steps": 181800, "loss": 0.0023, "lr": 8.731154818948875e-06, "epoch": 15.05995599559956, "percentage": 75.3, "elapsed_time": "5:24:24", "remaining_time": "1:46:24", "throughput": 1484.23, "total_tokens": 28890432} {"current_steps": 136900, "total_steps": 181800, "loss": 0.0093, "lr": 8.729332549376542e-06, "epoch": 15.06050605060506, "percentage": 75.3, "elapsed_time": "5:24:25", "remaining_time": "1:46:24", "throughput": 1484.23, "total_tokens": 28891488} {"current_steps": 136905, "total_steps": 181800, "loss": 0.1048, "lr": 8.727510429763162e-06, "epoch": 15.061056105610561, "percentage": 75.31, "elapsed_time": "5:24:26", "remaining_time": "1:46:23", "throughput": 1484.23, "total_tokens": 28892544} {"current_steps": 136910, "total_steps": 181800, "loss": 0.1324, "lr": 8.725688460125501e-06, "epoch": 15.061606160616062, "percentage": 75.31, "elapsed_time": "5:24:27", "remaining_time": "1:46:22", "throughput": 1484.23, "total_tokens": 28893632} {"current_steps": 136915, "total_steps": 181800, "loss": 0.0069, "lr": 8.723866640480366e-06, "epoch": 15.062156215621561, "percentage": 75.31, "elapsed_time": "5:24:27", "remaining_time": "1:46:22", "throughput": 1484.24, "total_tokens": 28894720} {"current_steps": 136920, "total_steps": 181800, "loss": 0.0087, "lr": 8.722044970844545e-06, "epoch": 15.062706270627062, "percentage": 75.31, "elapsed_time": "5:24:28", "remaining_time": "1:46:21", "throughput": 1484.24, "total_tokens": 28895776} {"current_steps": 136925, "total_steps": 181800, "loss": 0.0327, "lr": 8.720223451234817e-06, "epoch": 15.063256325632564, "percentage": 75.32, "elapsed_time": "5:24:29", "remaining_time": "1:46:20", "throughput": 1484.24, "total_tokens": 28896864} {"current_steps": 136930, "total_steps": 181800, "loss": 0.001, "lr": 8.718402081667976e-06, "epoch": 15.063806380638065, "percentage": 75.32, "elapsed_time": "5:24:29", "remaining_time": "1:46:19", "throughput": 1484.24, "total_tokens": 28897888} {"current_steps": 136935, "total_steps": 181800, "loss": 0.009, "lr": 8.716580862160809e-06, "epoch": 15.064356435643564, "percentage": 75.32, "elapsed_time": "5:24:30", "remaining_time": "1:46:19", "throughput": 1484.24, "total_tokens": 28898912} {"current_steps": 136940, "total_steps": 181800, "loss": 0.002, "lr": 8.714759792730112e-06, "epoch": 15.064906490649065, "percentage": 75.32, "elapsed_time": "5:24:31", "remaining_time": "1:46:18", "throughput": 1484.24, "total_tokens": 28900000} {"current_steps": 136945, "total_steps": 181800, "loss": 0.1118, "lr": 8.71293887339266e-06, "epoch": 15.065456545654566, "percentage": 75.33, "elapsed_time": "5:24:31", "remaining_time": "1:46:17", "throughput": 1484.25, "total_tokens": 28901088} {"current_steps": 136950, "total_steps": 181800, "loss": 0.011, "lr": 8.711118104165228e-06, "epoch": 15.066006600660065, "percentage": 75.33, "elapsed_time": "5:24:32", "remaining_time": "1:46:17", "throughput": 1484.25, "total_tokens": 28902144} {"current_steps": 136955, "total_steps": 181800, "loss": 0.0174, "lr": 8.70929748506461e-06, "epoch": 15.066556655665567, "percentage": 75.33, "elapsed_time": "5:24:33", "remaining_time": "1:46:16", "throughput": 1484.25, "total_tokens": 28903136} {"current_steps": 136960, "total_steps": 181800, "loss": 0.0024, "lr": 8.707477016107566e-06, "epoch": 15.067106710671068, "percentage": 75.34, "elapsed_time": "5:24:33", "remaining_time": "1:46:15", "throughput": 1484.25, "total_tokens": 28904256} {"current_steps": 136965, "total_steps": 181800, "loss": 0.0049, "lr": 8.705656697310904e-06, "epoch": 15.067656765676567, "percentage": 75.34, "elapsed_time": "5:24:34", "remaining_time": "1:46:14", "throughput": 1484.25, "total_tokens": 28905312} {"current_steps": 136970, "total_steps": 181800, "loss": 0.0023, "lr": 8.703836528691384e-06, "epoch": 15.068206820682068, "percentage": 75.34, "elapsed_time": "5:24:35", "remaining_time": "1:46:14", "throughput": 1484.26, "total_tokens": 28906368} {"current_steps": 136975, "total_steps": 181800, "loss": 0.0905, "lr": 8.702016510265776e-06, "epoch": 15.06875687568757, "percentage": 75.34, "elapsed_time": "5:24:36", "remaining_time": "1:46:13", "throughput": 1484.26, "total_tokens": 28907424} {"current_steps": 136980, "total_steps": 181800, "loss": 0.0084, "lr": 8.70019664205087e-06, "epoch": 15.069306930693068, "percentage": 75.35, "elapsed_time": "5:24:36", "remaining_time": "1:46:12", "throughput": 1484.26, "total_tokens": 28908416} {"current_steps": 136985, "total_steps": 181800, "loss": 0.0717, "lr": 8.698376924063423e-06, "epoch": 15.06985698569857, "percentage": 75.35, "elapsed_time": "5:24:37", "remaining_time": "1:46:12", "throughput": 1484.25, "total_tokens": 28909408} {"current_steps": 136990, "total_steps": 181800, "loss": 0.0034, "lr": 8.696557356320211e-06, "epoch": 15.07040704070407, "percentage": 75.35, "elapsed_time": "5:24:38", "remaining_time": "1:46:11", "throughput": 1484.26, "total_tokens": 28910496} {"current_steps": 136995, "total_steps": 181800, "loss": 0.1047, "lr": 8.694737938838016e-06, "epoch": 15.070957095709572, "percentage": 75.35, "elapsed_time": "5:24:38", "remaining_time": "1:46:10", "throughput": 1484.26, "total_tokens": 28911552} {"current_steps": 137000, "total_steps": 181800, "loss": 0.0328, "lr": 8.692918671633588e-06, "epoch": 15.071507150715071, "percentage": 75.36, "elapsed_time": "5:24:39", "remaining_time": "1:46:09", "throughput": 1484.26, "total_tokens": 28912576} {"current_steps": 137005, "total_steps": 181800, "loss": 0.0748, "lr": 8.691099554723715e-06, "epoch": 15.072057205720572, "percentage": 75.36, "elapsed_time": "5:24:40", "remaining_time": "1:46:09", "throughput": 1484.26, "total_tokens": 28913600} {"current_steps": 137010, "total_steps": 181800, "loss": 0.0027, "lr": 8.68928058812514e-06, "epoch": 15.072607260726073, "percentage": 75.36, "elapsed_time": "5:24:40", "remaining_time": "1:46:08", "throughput": 1484.26, "total_tokens": 28914688} {"current_steps": 137015, "total_steps": 181800, "loss": 0.0588, "lr": 8.68746177185465e-06, "epoch": 15.073157315731573, "percentage": 75.37, "elapsed_time": "5:24:41", "remaining_time": "1:46:07", "throughput": 1484.26, "total_tokens": 28915712} {"current_steps": 137020, "total_steps": 181800, "loss": 0.0044, "lr": 8.685643105928986e-06, "epoch": 15.073707370737074, "percentage": 75.37, "elapsed_time": "5:24:42", "remaining_time": "1:46:07", "throughput": 1484.27, "total_tokens": 28916800} {"current_steps": 137025, "total_steps": 181800, "loss": 0.0552, "lr": 8.683824590364926e-06, "epoch": 15.074257425742575, "percentage": 75.37, "elapsed_time": "5:24:42", "remaining_time": "1:46:06", "throughput": 1484.27, "total_tokens": 28917888} {"current_steps": 137030, "total_steps": 181800, "loss": 0.0545, "lr": 8.682006225179229e-06, "epoch": 15.074807480748074, "percentage": 75.37, "elapsed_time": "5:24:43", "remaining_time": "1:46:05", "throughput": 1484.27, "total_tokens": 28918976} {"current_steps": 137035, "total_steps": 181800, "loss": 0.0461, "lr": 8.680188010388643e-06, "epoch": 15.075357535753575, "percentage": 75.38, "elapsed_time": "5:24:44", "remaining_time": "1:46:04", "throughput": 1484.27, "total_tokens": 28920032} {"current_steps": 137040, "total_steps": 181800, "loss": 0.0018, "lr": 8.678369946009943e-06, "epoch": 15.075907590759076, "percentage": 75.38, "elapsed_time": "5:24:44", "remaining_time": "1:46:04", "throughput": 1484.27, "total_tokens": 28921088} {"current_steps": 137045, "total_steps": 181800, "loss": 0.0229, "lr": 8.676552032059868e-06, "epoch": 15.076457645764576, "percentage": 75.38, "elapsed_time": "5:24:45", "remaining_time": "1:46:03", "throughput": 1484.28, "total_tokens": 28922176} {"current_steps": 137050, "total_steps": 181800, "loss": 0.0401, "lr": 8.674734268555179e-06, "epoch": 15.077007700770077, "percentage": 75.39, "elapsed_time": "5:24:46", "remaining_time": "1:46:02", "throughput": 1484.28, "total_tokens": 28923296} {"current_steps": 137055, "total_steps": 181800, "loss": 0.0124, "lr": 8.672916655512637e-06, "epoch": 15.077557755775578, "percentage": 75.39, "elapsed_time": "5:24:47", "remaining_time": "1:46:02", "throughput": 1484.28, "total_tokens": 28924320} {"current_steps": 137060, "total_steps": 181800, "loss": 0.0817, "lr": 8.671099192948989e-06, "epoch": 15.078107810781079, "percentage": 75.39, "elapsed_time": "5:24:47", "remaining_time": "1:46:01", "throughput": 1484.28, "total_tokens": 28925344} {"current_steps": 137065, "total_steps": 181800, "loss": 0.037, "lr": 8.669281880880978e-06, "epoch": 15.078657865786578, "percentage": 75.39, "elapsed_time": "5:24:48", "remaining_time": "1:46:00", "throughput": 1484.28, "total_tokens": 28926400} {"current_steps": 137070, "total_steps": 181800, "loss": 0.0045, "lr": 8.667464719325366e-06, "epoch": 15.07920792079208, "percentage": 75.4, "elapsed_time": "5:24:49", "remaining_time": "1:45:59", "throughput": 1484.28, "total_tokens": 28927424} {"current_steps": 137075, "total_steps": 181800, "loss": 0.0702, "lr": 8.665647708298877e-06, "epoch": 15.07975797579758, "percentage": 75.4, "elapsed_time": "5:24:49", "remaining_time": "1:45:59", "throughput": 1484.29, "total_tokens": 28928544} {"current_steps": 137080, "total_steps": 181800, "loss": 0.0107, "lr": 8.663830847818295e-06, "epoch": 15.08030803080308, "percentage": 75.4, "elapsed_time": "5:24:50", "remaining_time": "1:45:58", "throughput": 1484.29, "total_tokens": 28929568} {"current_steps": 137085, "total_steps": 181800, "loss": 0.0034, "lr": 8.662014137900343e-06, "epoch": 15.08085808580858, "percentage": 75.4, "elapsed_time": "5:24:51", "remaining_time": "1:45:57", "throughput": 1484.29, "total_tokens": 28930688} {"current_steps": 137090, "total_steps": 181800, "loss": 0.0135, "lr": 8.660197578561757e-06, "epoch": 15.081408140814082, "percentage": 75.41, "elapsed_time": "5:24:51", "remaining_time": "1:45:57", "throughput": 1484.3, "total_tokens": 28931808} {"current_steps": 137095, "total_steps": 181800, "loss": 0.0017, "lr": 8.658381169819299e-06, "epoch": 15.081958195819581, "percentage": 75.41, "elapsed_time": "5:24:52", "remaining_time": "1:45:56", "throughput": 1484.3, "total_tokens": 28932768} {"current_steps": 137100, "total_steps": 181800, "loss": 0.0026, "lr": 8.656564911689694e-06, "epoch": 15.082508250825082, "percentage": 75.41, "elapsed_time": "5:24:53", "remaining_time": "1:45:55", "throughput": 1484.3, "total_tokens": 28933856} {"current_steps": 137105, "total_steps": 181800, "loss": 0.1105, "lr": 8.654748804189685e-06, "epoch": 15.083058305830583, "percentage": 75.42, "elapsed_time": "5:24:53", "remaining_time": "1:45:54", "throughput": 1484.3, "total_tokens": 28934912} {"current_steps": 137110, "total_steps": 181800, "loss": 0.0042, "lr": 8.652932847336023e-06, "epoch": 15.083608360836084, "percentage": 75.42, "elapsed_time": "5:24:54", "remaining_time": "1:45:54", "throughput": 1484.3, "total_tokens": 28936000} {"current_steps": 137115, "total_steps": 181800, "loss": 0.0097, "lr": 8.651117041145426e-06, "epoch": 15.084158415841584, "percentage": 75.42, "elapsed_time": "5:24:55", "remaining_time": "1:45:53", "throughput": 1484.31, "total_tokens": 28937088} {"current_steps": 137120, "total_steps": 181800, "loss": 0.0042, "lr": 8.649301385634648e-06, "epoch": 15.084708470847085, "percentage": 75.42, "elapsed_time": "5:24:56", "remaining_time": "1:45:52", "throughput": 1484.31, "total_tokens": 28938144} {"current_steps": 137125, "total_steps": 181800, "loss": 0.0122, "lr": 8.647485880820402e-06, "epoch": 15.085258525852586, "percentage": 75.43, "elapsed_time": "5:24:56", "remaining_time": "1:45:51", "throughput": 1484.31, "total_tokens": 28939168} {"current_steps": 137130, "total_steps": 181800, "loss": 0.0038, "lr": 8.645670526719443e-06, "epoch": 15.085808580858085, "percentage": 75.43, "elapsed_time": "5:24:57", "remaining_time": "1:45:51", "throughput": 1484.31, "total_tokens": 28940288} {"current_steps": 137135, "total_steps": 181800, "loss": 0.0027, "lr": 8.643855323348482e-06, "epoch": 15.086358635863586, "percentage": 75.43, "elapsed_time": "5:24:58", "remaining_time": "1:45:50", "throughput": 1484.32, "total_tokens": 28941408} {"current_steps": 137140, "total_steps": 181800, "loss": 0.0756, "lr": 8.642040270724258e-06, "epoch": 15.086908690869087, "percentage": 75.43, "elapsed_time": "5:24:58", "remaining_time": "1:45:49", "throughput": 1484.32, "total_tokens": 28942496} {"current_steps": 137145, "total_steps": 181800, "loss": 0.0404, "lr": 8.640225368863508e-06, "epoch": 15.087458745874587, "percentage": 75.44, "elapsed_time": "5:24:59", "remaining_time": "1:45:49", "throughput": 1484.32, "total_tokens": 28943520} {"current_steps": 137150, "total_steps": 181800, "loss": 0.0743, "lr": 8.63841061778294e-06, "epoch": 15.088008800880088, "percentage": 75.44, "elapsed_time": "5:25:00", "remaining_time": "1:45:48", "throughput": 1484.32, "total_tokens": 28944544} {"current_steps": 137155, "total_steps": 181800, "loss": 0.0753, "lr": 8.636596017499301e-06, "epoch": 15.088558855885589, "percentage": 75.44, "elapsed_time": "5:25:00", "remaining_time": "1:45:47", "throughput": 1484.32, "total_tokens": 28945568} {"current_steps": 137160, "total_steps": 181800, "loss": 0.0078, "lr": 8.634781568029299e-06, "epoch": 15.089108910891088, "percentage": 75.45, "elapsed_time": "5:25:01", "remaining_time": "1:45:46", "throughput": 1484.32, "total_tokens": 28946624} {"current_steps": 137165, "total_steps": 181800, "loss": 0.0507, "lr": 8.632967269389657e-06, "epoch": 15.08965896589659, "percentage": 75.45, "elapsed_time": "5:25:02", "remaining_time": "1:45:46", "throughput": 1484.33, "total_tokens": 28947712} {"current_steps": 137170, "total_steps": 181800, "loss": 0.142, "lr": 8.631153121597113e-06, "epoch": 15.09020902090209, "percentage": 75.45, "elapsed_time": "5:25:02", "remaining_time": "1:45:45", "throughput": 1484.33, "total_tokens": 28948800} {"current_steps": 137175, "total_steps": 181800, "loss": 0.0337, "lr": 8.629339124668368e-06, "epoch": 15.090759075907592, "percentage": 75.45, "elapsed_time": "5:25:03", "remaining_time": "1:45:44", "throughput": 1484.33, "total_tokens": 28949888} {"current_steps": 137180, "total_steps": 181800, "loss": 0.0216, "lr": 8.627525278620158e-06, "epoch": 15.091309130913091, "percentage": 75.46, "elapsed_time": "5:25:04", "remaining_time": "1:45:44", "throughput": 1484.34, "total_tokens": 28951008} {"current_steps": 137185, "total_steps": 181800, "loss": 0.0047, "lr": 8.62571158346919e-06, "epoch": 15.091859185918592, "percentage": 75.46, "elapsed_time": "5:25:05", "remaining_time": "1:45:43", "throughput": 1484.34, "total_tokens": 28952096} {"current_steps": 137190, "total_steps": 181800, "loss": 0.0286, "lr": 8.623898039232172e-06, "epoch": 15.092409240924093, "percentage": 75.46, "elapsed_time": "5:25:05", "remaining_time": "1:45:42", "throughput": 1484.34, "total_tokens": 28953184} {"current_steps": 137195, "total_steps": 181800, "loss": 0.0683, "lr": 8.622084645925829e-06, "epoch": 15.092959295929592, "percentage": 75.46, "elapsed_time": "5:25:06", "remaining_time": "1:45:41", "throughput": 1484.35, "total_tokens": 28954240} {"current_steps": 137200, "total_steps": 181800, "loss": 0.0099, "lr": 8.620271403566871e-06, "epoch": 15.093509350935093, "percentage": 75.47, "elapsed_time": "5:25:07", "remaining_time": "1:45:41", "throughput": 1484.35, "total_tokens": 28955264} {"current_steps": 137205, "total_steps": 181800, "loss": 0.0025, "lr": 8.618458312172023e-06, "epoch": 15.094059405940595, "percentage": 75.47, "elapsed_time": "5:25:07", "remaining_time": "1:45:40", "throughput": 1484.35, "total_tokens": 28956320} {"current_steps": 137210, "total_steps": 181800, "loss": 0.1008, "lr": 8.616645371757985e-06, "epoch": 15.094609460946094, "percentage": 75.47, "elapsed_time": "5:25:08", "remaining_time": "1:45:39", "throughput": 1484.35, "total_tokens": 28957408} {"current_steps": 137215, "total_steps": 181800, "loss": 0.0036, "lr": 8.61483258234145e-06, "epoch": 15.095159515951595, "percentage": 75.48, "elapsed_time": "5:25:09", "remaining_time": "1:45:39", "throughput": 1484.35, "total_tokens": 28958496} {"current_steps": 137220, "total_steps": 181800, "loss": 0.0029, "lr": 8.613019943939146e-06, "epoch": 15.095709570957096, "percentage": 75.48, "elapsed_time": "5:25:09", "remaining_time": "1:45:38", "throughput": 1484.35, "total_tokens": 28959520} {"current_steps": 137225, "total_steps": 181800, "loss": 0.0619, "lr": 8.611207456567774e-06, "epoch": 15.096259625962595, "percentage": 75.48, "elapsed_time": "5:25:10", "remaining_time": "1:45:37", "throughput": 1484.35, "total_tokens": 28960544} {"current_steps": 137230, "total_steps": 181800, "loss": 0.0686, "lr": 8.609395120244046e-06, "epoch": 15.096809680968097, "percentage": 75.48, "elapsed_time": "5:25:11", "remaining_time": "1:45:36", "throughput": 1484.36, "total_tokens": 28961600} {"current_steps": 137235, "total_steps": 181800, "loss": 0.0951, "lr": 8.607582934984659e-06, "epoch": 15.097359735973598, "percentage": 75.49, "elapsed_time": "5:25:11", "remaining_time": "1:45:36", "throughput": 1484.36, "total_tokens": 28962688} {"current_steps": 137240, "total_steps": 181800, "loss": 0.0053, "lr": 8.605770900806306e-06, "epoch": 15.097909790979099, "percentage": 75.49, "elapsed_time": "5:25:12", "remaining_time": "1:45:35", "throughput": 1484.36, "total_tokens": 28963744} {"current_steps": 137245, "total_steps": 181800, "loss": 0.008, "lr": 8.603959017725701e-06, "epoch": 15.098459845984598, "percentage": 75.49, "elapsed_time": "5:25:13", "remaining_time": "1:45:34", "throughput": 1484.36, "total_tokens": 28964832} {"current_steps": 137250, "total_steps": 181800, "loss": 0.0018, "lr": 8.602147285759535e-06, "epoch": 15.099009900990099, "percentage": 75.5, "elapsed_time": "5:25:13", "remaining_time": "1:45:34", "throughput": 1484.36, "total_tokens": 28965888} {"current_steps": 137255, "total_steps": 181800, "loss": 0.004, "lr": 8.600335704924506e-06, "epoch": 15.0995599559956, "percentage": 75.5, "elapsed_time": "5:25:14", "remaining_time": "1:45:33", "throughput": 1484.37, "total_tokens": 28966976} {"current_steps": 137260, "total_steps": 181800, "loss": 0.0295, "lr": 8.598524275237322e-06, "epoch": 15.1001100110011, "percentage": 75.5, "elapsed_time": "5:25:15", "remaining_time": "1:45:32", "throughput": 1484.35, "total_tokens": 28968032} {"current_steps": 137265, "total_steps": 181800, "loss": 0.0023, "lr": 8.596712996714662e-06, "epoch": 15.1006600660066, "percentage": 75.5, "elapsed_time": "5:25:16", "remaining_time": "1:45:31", "throughput": 1484.35, "total_tokens": 28969120} {"current_steps": 137270, "total_steps": 181800, "loss": 0.005, "lr": 8.594901869373234e-06, "epoch": 15.101210121012102, "percentage": 75.51, "elapsed_time": "5:25:17", "remaining_time": "1:45:31", "throughput": 1484.36, "total_tokens": 28970208} {"current_steps": 137275, "total_steps": 181800, "loss": 0.0202, "lr": 8.593090893229716e-06, "epoch": 15.101760176017601, "percentage": 75.51, "elapsed_time": "5:25:17", "remaining_time": "1:45:30", "throughput": 1484.36, "total_tokens": 28971264} {"current_steps": 137280, "total_steps": 181800, "loss": 0.1006, "lr": 8.591280068300809e-06, "epoch": 15.102310231023102, "percentage": 75.51, "elapsed_time": "5:25:18", "remaining_time": "1:45:29", "throughput": 1484.36, "total_tokens": 28972320} {"current_steps": 137285, "total_steps": 181800, "loss": 0.0219, "lr": 8.589469394603202e-06, "epoch": 15.102860286028603, "percentage": 75.51, "elapsed_time": "5:25:19", "remaining_time": "1:45:29", "throughput": 1484.37, "total_tokens": 28973440} {"current_steps": 137290, "total_steps": 181800, "loss": 0.0084, "lr": 8.587658872153579e-06, "epoch": 15.103410341034103, "percentage": 75.52, "elapsed_time": "5:25:19", "remaining_time": "1:45:28", "throughput": 1484.37, "total_tokens": 28974496} {"current_steps": 137295, "total_steps": 181800, "loss": 0.0135, "lr": 8.585848500968636e-06, "epoch": 15.103960396039604, "percentage": 75.52, "elapsed_time": "5:25:20", "remaining_time": "1:45:27", "throughput": 1484.37, "total_tokens": 28975520} {"current_steps": 137300, "total_steps": 181800, "loss": 0.0831, "lr": 8.58403828106505e-06, "epoch": 15.104510451045105, "percentage": 75.52, "elapsed_time": "5:25:21", "remaining_time": "1:45:26", "throughput": 1484.37, "total_tokens": 28976512} {"current_steps": 137305, "total_steps": 181800, "loss": 0.0139, "lr": 8.582228212459494e-06, "epoch": 15.105060506050606, "percentage": 75.53, "elapsed_time": "5:25:21", "remaining_time": "1:45:26", "throughput": 1484.36, "total_tokens": 28977472} {"current_steps": 137310, "total_steps": 181800, "loss": 0.0137, "lr": 8.580418295168669e-06, "epoch": 15.105610561056105, "percentage": 75.53, "elapsed_time": "5:25:22", "remaining_time": "1:45:25", "throughput": 1484.37, "total_tokens": 28978560} {"current_steps": 137315, "total_steps": 181800, "loss": 0.0619, "lr": 8.578608529209244e-06, "epoch": 15.106160616061606, "percentage": 75.53, "elapsed_time": "5:25:23", "remaining_time": "1:45:24", "throughput": 1484.36, "total_tokens": 28979552} {"current_steps": 137320, "total_steps": 181800, "loss": 0.0018, "lr": 8.576798914597916e-06, "epoch": 15.106710671067107, "percentage": 75.53, "elapsed_time": "5:25:23", "remaining_time": "1:45:24", "throughput": 1484.36, "total_tokens": 28980544} {"current_steps": 137325, "total_steps": 181800, "loss": 0.0087, "lr": 8.574989451351354e-06, "epoch": 15.107260726072607, "percentage": 75.54, "elapsed_time": "5:25:24", "remaining_time": "1:45:23", "throughput": 1484.36, "total_tokens": 28981600} {"current_steps": 137330, "total_steps": 181800, "loss": 0.0149, "lr": 8.57318013948622e-06, "epoch": 15.107810781078108, "percentage": 75.54, "elapsed_time": "5:25:25", "remaining_time": "1:45:22", "throughput": 1484.36, "total_tokens": 28982624} {"current_steps": 137335, "total_steps": 181800, "loss": 0.0219, "lr": 8.571370979019205e-06, "epoch": 15.108360836083609, "percentage": 75.54, "elapsed_time": "5:25:25", "remaining_time": "1:45:21", "throughput": 1484.36, "total_tokens": 28983648} {"current_steps": 137340, "total_steps": 181800, "loss": 0.0682, "lr": 8.56956196996698e-06, "epoch": 15.108910891089108, "percentage": 75.54, "elapsed_time": "5:25:26", "remaining_time": "1:45:21", "throughput": 1484.36, "total_tokens": 28984704} {"current_steps": 137345, "total_steps": 181800, "loss": 0.1735, "lr": 8.567753112346224e-06, "epoch": 15.10946094609461, "percentage": 75.55, "elapsed_time": "5:25:27", "remaining_time": "1:45:20", "throughput": 1484.37, "total_tokens": 28985792} {"current_steps": 137350, "total_steps": 181800, "loss": 0.0104, "lr": 8.565944406173607e-06, "epoch": 15.11001100110011, "percentage": 75.55, "elapsed_time": "5:25:28", "remaining_time": "1:45:19", "throughput": 1484.37, "total_tokens": 28986880} {"current_steps": 137355, "total_steps": 181800, "loss": 0.0685, "lr": 8.564135851465781e-06, "epoch": 15.110561056105611, "percentage": 75.55, "elapsed_time": "5:25:28", "remaining_time": "1:45:19", "throughput": 1484.37, "total_tokens": 28987904} {"current_steps": 137360, "total_steps": 181800, "loss": 0.0076, "lr": 8.56232744823944e-06, "epoch": 15.11111111111111, "percentage": 75.56, "elapsed_time": "5:25:29", "remaining_time": "1:45:18", "throughput": 1484.37, "total_tokens": 28989024} {"current_steps": 137365, "total_steps": 181800, "loss": 0.0557, "lr": 8.560519196511233e-06, "epoch": 15.111661166116612, "percentage": 75.56, "elapsed_time": "5:25:30", "remaining_time": "1:45:17", "throughput": 1484.38, "total_tokens": 28990144} {"current_steps": 137370, "total_steps": 181800, "loss": 0.0042, "lr": 8.558711096297827e-06, "epoch": 15.112211221122113, "percentage": 75.56, "elapsed_time": "5:25:30", "remaining_time": "1:45:16", "throughput": 1484.38, "total_tokens": 28991200} {"current_steps": 137375, "total_steps": 181800, "loss": 0.0011, "lr": 8.556903147615902e-06, "epoch": 15.112761276127612, "percentage": 75.56, "elapsed_time": "5:25:31", "remaining_time": "1:45:16", "throughput": 1484.38, "total_tokens": 28992256} {"current_steps": 137380, "total_steps": 181800, "loss": 0.0315, "lr": 8.555095350482103e-06, "epoch": 15.113311331133113, "percentage": 75.57, "elapsed_time": "5:25:32", "remaining_time": "1:45:15", "throughput": 1484.39, "total_tokens": 28993376} {"current_steps": 137385, "total_steps": 181800, "loss": 0.0944, "lr": 8.553287704913107e-06, "epoch": 15.113861386138614, "percentage": 75.57, "elapsed_time": "5:25:32", "remaining_time": "1:45:14", "throughput": 1484.39, "total_tokens": 28994432} {"current_steps": 137390, "total_steps": 181800, "loss": 0.0022, "lr": 8.551480210925557e-06, "epoch": 15.114411441144114, "percentage": 75.57, "elapsed_time": "5:25:33", "remaining_time": "1:45:14", "throughput": 1484.39, "total_tokens": 28995456} {"current_steps": 137395, "total_steps": 181800, "loss": 0.0196, "lr": 8.549672868536124e-06, "epoch": 15.114961496149615, "percentage": 75.57, "elapsed_time": "5:25:34", "remaining_time": "1:45:13", "throughput": 1484.39, "total_tokens": 28996512} {"current_steps": 137400, "total_steps": 181800, "loss": 0.1243, "lr": 8.547865677761469e-06, "epoch": 15.115511551155116, "percentage": 75.58, "elapsed_time": "5:25:34", "remaining_time": "1:45:12", "throughput": 1484.39, "total_tokens": 28997568} {"current_steps": 137405, "total_steps": 181800, "loss": 0.0082, "lr": 8.546058638618235e-06, "epoch": 15.116061606160615, "percentage": 75.58, "elapsed_time": "5:25:35", "remaining_time": "1:45:11", "throughput": 1484.39, "total_tokens": 28998592} {"current_steps": 137410, "total_steps": 181800, "loss": 0.0031, "lr": 8.54425175112309e-06, "epoch": 15.116611661166116, "percentage": 75.58, "elapsed_time": "5:25:36", "remaining_time": "1:45:11", "throughput": 1484.39, "total_tokens": 28999680} {"current_steps": 137415, "total_steps": 181800, "loss": 0.005, "lr": 8.542445015292671e-06, "epoch": 15.117161716171617, "percentage": 75.59, "elapsed_time": "5:25:37", "remaining_time": "1:45:10", "throughput": 1484.4, "total_tokens": 29000736} {"current_steps": 137420, "total_steps": 181800, "loss": 0.1275, "lr": 8.540638431143646e-06, "epoch": 15.117711771177119, "percentage": 75.59, "elapsed_time": "5:25:37", "remaining_time": "1:45:09", "throughput": 1484.4, "total_tokens": 29001760} {"current_steps": 137425, "total_steps": 181800, "loss": 0.0101, "lr": 8.538831998692653e-06, "epoch": 15.118261826182618, "percentage": 75.59, "elapsed_time": "5:25:38", "remaining_time": "1:45:09", "throughput": 1484.4, "total_tokens": 29002848} {"current_steps": 137430, "total_steps": 181800, "loss": 0.0615, "lr": 8.537025717956349e-06, "epoch": 15.118811881188119, "percentage": 75.59, "elapsed_time": "5:25:39", "remaining_time": "1:45:08", "throughput": 1484.4, "total_tokens": 29003872} {"current_steps": 137435, "total_steps": 181800, "loss": 0.0008, "lr": 8.535219588951384e-06, "epoch": 15.11936193619362, "percentage": 75.6, "elapsed_time": "5:25:39", "remaining_time": "1:45:07", "throughput": 1484.4, "total_tokens": 29004896} {"current_steps": 137440, "total_steps": 181800, "loss": 0.0107, "lr": 8.533413611694392e-06, "epoch": 15.11991199119912, "percentage": 75.6, "elapsed_time": "5:25:40", "remaining_time": "1:45:06", "throughput": 1484.4, "total_tokens": 29005984} {"current_steps": 137445, "total_steps": 181800, "loss": 0.0071, "lr": 8.531607786202033e-06, "epoch": 15.12046204620462, "percentage": 75.6, "elapsed_time": "5:25:41", "remaining_time": "1:45:06", "throughput": 1484.4, "total_tokens": 29006976} {"current_steps": 137450, "total_steps": 181800, "loss": 0.0283, "lr": 8.529802112490934e-06, "epoch": 15.121012101210122, "percentage": 75.61, "elapsed_time": "5:25:41", "remaining_time": "1:45:05", "throughput": 1484.41, "total_tokens": 29008064} {"current_steps": 137455, "total_steps": 181800, "loss": 0.0048, "lr": 8.527996590577747e-06, "epoch": 15.12156215621562, "percentage": 75.61, "elapsed_time": "5:25:42", "remaining_time": "1:45:04", "throughput": 1484.41, "total_tokens": 29009120} {"current_steps": 137460, "total_steps": 181800, "loss": 0.0381, "lr": 8.52619122047912e-06, "epoch": 15.122112211221122, "percentage": 75.61, "elapsed_time": "5:25:43", "remaining_time": "1:45:04", "throughput": 1484.4, "total_tokens": 29010080} {"current_steps": 137465, "total_steps": 181800, "loss": 0.0264, "lr": 8.524386002211685e-06, "epoch": 15.122662266226623, "percentage": 75.61, "elapsed_time": "5:25:43", "remaining_time": "1:45:03", "throughput": 1484.41, "total_tokens": 29011200} {"current_steps": 137470, "total_steps": 181800, "loss": 0.0205, "lr": 8.522580935792065e-06, "epoch": 15.123212321232122, "percentage": 75.62, "elapsed_time": "5:25:44", "remaining_time": "1:45:02", "throughput": 1484.41, "total_tokens": 29012256} {"current_steps": 137475, "total_steps": 181800, "loss": 0.0014, "lr": 8.520776021236923e-06, "epoch": 15.123762376237623, "percentage": 75.62, "elapsed_time": "5:25:45", "remaining_time": "1:45:01", "throughput": 1484.41, "total_tokens": 29013312} {"current_steps": 137480, "total_steps": 181800, "loss": 0.0016, "lr": 8.518971258562872e-06, "epoch": 15.124312431243125, "percentage": 75.62, "elapsed_time": "5:25:46", "remaining_time": "1:45:01", "throughput": 1484.41, "total_tokens": 29014368} {"current_steps": 137485, "total_steps": 181800, "loss": 0.002, "lr": 8.517166647786553e-06, "epoch": 15.124862486248626, "percentage": 75.62, "elapsed_time": "5:25:46", "remaining_time": "1:45:00", "throughput": 1484.42, "total_tokens": 29015520} {"current_steps": 137490, "total_steps": 181800, "loss": 0.0263, "lr": 8.515362188924608e-06, "epoch": 15.125412541254125, "percentage": 75.63, "elapsed_time": "5:25:47", "remaining_time": "1:44:59", "throughput": 1484.42, "total_tokens": 29016576} {"current_steps": 137495, "total_steps": 181800, "loss": 0.017, "lr": 8.513557881993653e-06, "epoch": 15.125962596259626, "percentage": 75.63, "elapsed_time": "5:25:48", "remaining_time": "1:44:58", "throughput": 1484.42, "total_tokens": 29017632} {"current_steps": 137500, "total_steps": 181800, "loss": 0.0039, "lr": 8.51175372701033e-06, "epoch": 15.126512651265127, "percentage": 75.63, "elapsed_time": "5:25:48", "remaining_time": "1:44:58", "throughput": 1484.43, "total_tokens": 29018720} {"current_steps": 137505, "total_steps": 181800, "loss": 0.0415, "lr": 8.509949723991253e-06, "epoch": 15.127062706270626, "percentage": 75.64, "elapsed_time": "5:25:49", "remaining_time": "1:44:57", "throughput": 1484.43, "total_tokens": 29019744} {"current_steps": 137510, "total_steps": 181800, "loss": 0.0026, "lr": 8.50814587295306e-06, "epoch": 15.127612761276128, "percentage": 75.64, "elapsed_time": "5:25:50", "remaining_time": "1:44:56", "throughput": 1484.43, "total_tokens": 29020800} {"current_steps": 137515, "total_steps": 181800, "loss": 0.0597, "lr": 8.50634217391238e-06, "epoch": 15.128162816281629, "percentage": 75.64, "elapsed_time": "5:25:50", "remaining_time": "1:44:56", "throughput": 1484.43, "total_tokens": 29021856} {"current_steps": 137520, "total_steps": 181800, "loss": 0.0056, "lr": 8.504538626885818e-06, "epoch": 15.128712871287128, "percentage": 75.64, "elapsed_time": "5:25:51", "remaining_time": "1:44:55", "throughput": 1484.43, "total_tokens": 29022944} {"current_steps": 137525, "total_steps": 181800, "loss": 0.0018, "lr": 8.50273523189002e-06, "epoch": 15.129262926292629, "percentage": 75.65, "elapsed_time": "5:25:52", "remaining_time": "1:44:54", "throughput": 1484.44, "total_tokens": 29024064} {"current_steps": 137530, "total_steps": 181800, "loss": 0.0615, "lr": 8.500931988941584e-06, "epoch": 15.12981298129813, "percentage": 75.65, "elapsed_time": "5:25:52", "remaining_time": "1:44:53", "throughput": 1484.44, "total_tokens": 29025152} {"current_steps": 137535, "total_steps": 181800, "loss": 0.0014, "lr": 8.499128898057151e-06, "epoch": 15.130363036303631, "percentage": 75.65, "elapsed_time": "5:25:53", "remaining_time": "1:44:53", "throughput": 1484.44, "total_tokens": 29026208} {"current_steps": 137540, "total_steps": 181800, "loss": 0.0317, "lr": 8.497325959253321e-06, "epoch": 15.13091309130913, "percentage": 75.65, "elapsed_time": "5:25:54", "remaining_time": "1:44:52", "throughput": 1484.44, "total_tokens": 29027264} {"current_steps": 137545, "total_steps": 181800, "loss": 0.0046, "lr": 8.495523172546722e-06, "epoch": 15.131463146314632, "percentage": 75.66, "elapsed_time": "5:25:54", "remaining_time": "1:44:51", "throughput": 1484.44, "total_tokens": 29028256} {"current_steps": 137550, "total_steps": 181800, "loss": 0.0767, "lr": 8.49372053795397e-06, "epoch": 15.132013201320133, "percentage": 75.66, "elapsed_time": "5:25:55", "remaining_time": "1:44:51", "throughput": 1484.44, "total_tokens": 29029280} {"current_steps": 137555, "total_steps": 181800, "loss": 0.0009, "lr": 8.491918055491668e-06, "epoch": 15.132563256325632, "percentage": 75.66, "elapsed_time": "5:25:56", "remaining_time": "1:44:50", "throughput": 1484.44, "total_tokens": 29030304} {"current_steps": 137560, "total_steps": 181800, "loss": 0.0707, "lr": 8.490115725176446e-06, "epoch": 15.133113311331133, "percentage": 75.67, "elapsed_time": "5:25:57", "remaining_time": "1:44:49", "throughput": 1484.44, "total_tokens": 29031360} {"current_steps": 137565, "total_steps": 181800, "loss": 0.0943, "lr": 8.488313547024892e-06, "epoch": 15.133663366336634, "percentage": 75.67, "elapsed_time": "5:25:57", "remaining_time": "1:44:48", "throughput": 1484.45, "total_tokens": 29032448} {"current_steps": 137570, "total_steps": 181800, "loss": 0.0066, "lr": 8.486511521053633e-06, "epoch": 15.134213421342134, "percentage": 75.67, "elapsed_time": "5:25:58", "remaining_time": "1:44:48", "throughput": 1484.45, "total_tokens": 29033472} {"current_steps": 137575, "total_steps": 181800, "loss": 0.0022, "lr": 8.484709647279281e-06, "epoch": 15.134763476347635, "percentage": 75.67, "elapsed_time": "5:25:59", "remaining_time": "1:44:47", "throughput": 1484.45, "total_tokens": 29034496} {"current_steps": 137580, "total_steps": 181800, "loss": 0.0357, "lr": 8.482907925718427e-06, "epoch": 15.135313531353136, "percentage": 75.68, "elapsed_time": "5:25:59", "remaining_time": "1:44:46", "throughput": 1484.44, "total_tokens": 29035456} {"current_steps": 137585, "total_steps": 181800, "loss": 0.0028, "lr": 8.481106356387694e-06, "epoch": 15.135863586358635, "percentage": 75.68, "elapsed_time": "5:26:00", "remaining_time": "1:44:46", "throughput": 1484.45, "total_tokens": 29036512} {"current_steps": 137590, "total_steps": 181800, "loss": 0.0016, "lr": 8.479304939303676e-06, "epoch": 15.136413641364136, "percentage": 75.68, "elapsed_time": "5:26:01", "remaining_time": "1:44:45", "throughput": 1484.45, "total_tokens": 29037536} {"current_steps": 137595, "total_steps": 181800, "loss": 0.0046, "lr": 8.47750367448297e-06, "epoch": 15.136963696369637, "percentage": 75.68, "elapsed_time": "5:26:01", "remaining_time": "1:44:44", "throughput": 1484.45, "total_tokens": 29038656} {"current_steps": 137600, "total_steps": 181800, "loss": 0.0048, "lr": 8.475702561942184e-06, "epoch": 15.137513751375138, "percentage": 75.69, "elapsed_time": "5:26:02", "remaining_time": "1:44:43", "throughput": 1484.45, "total_tokens": 29039680} {"current_steps": 137605, "total_steps": 181800, "loss": 0.0011, "lr": 8.473901601697918e-06, "epoch": 15.138063806380638, "percentage": 75.69, "elapsed_time": "5:26:03", "remaining_time": "1:44:43", "throughput": 1484.45, "total_tokens": 29040768} {"current_steps": 137610, "total_steps": 181800, "loss": 0.0012, "lr": 8.472100793766777e-06, "epoch": 15.138613861386139, "percentage": 75.69, "elapsed_time": "5:26:03", "remaining_time": "1:44:42", "throughput": 1484.45, "total_tokens": 29041792} {"current_steps": 137615, "total_steps": 181800, "loss": 0.0398, "lr": 8.470300138165354e-06, "epoch": 15.13916391639164, "percentage": 75.7, "elapsed_time": "5:26:04", "remaining_time": "1:44:41", "throughput": 1484.46, "total_tokens": 29042848} {"current_steps": 137620, "total_steps": 181800, "loss": 0.0257, "lr": 8.468499634910235e-06, "epoch": 15.13971397139714, "percentage": 75.7, "elapsed_time": "5:26:05", "remaining_time": "1:44:41", "throughput": 1484.46, "total_tokens": 29043904} {"current_steps": 137625, "total_steps": 181800, "loss": 0.0714, "lr": 8.466699284018023e-06, "epoch": 15.14026402640264, "percentage": 75.7, "elapsed_time": "5:26:06", "remaining_time": "1:44:40", "throughput": 1484.46, "total_tokens": 29044896} {"current_steps": 137630, "total_steps": 181800, "loss": 0.0043, "lr": 8.46489908550531e-06, "epoch": 15.140814081408141, "percentage": 75.7, "elapsed_time": "5:26:06", "remaining_time": "1:44:39", "throughput": 1484.46, "total_tokens": 29046016} {"current_steps": 137635, "total_steps": 181800, "loss": 0.0315, "lr": 8.463099039388695e-06, "epoch": 15.14136413641364, "percentage": 75.71, "elapsed_time": "5:26:07", "remaining_time": "1:44:38", "throughput": 1484.46, "total_tokens": 29047040} {"current_steps": 137640, "total_steps": 181800, "loss": 0.0018, "lr": 8.461299145684761e-06, "epoch": 15.141914191419142, "percentage": 75.71, "elapsed_time": "5:26:08", "remaining_time": "1:44:38", "throughput": 1484.46, "total_tokens": 29048096} {"current_steps": 137645, "total_steps": 181800, "loss": 0.0125, "lr": 8.45949940441009e-06, "epoch": 15.142464246424643, "percentage": 75.71, "elapsed_time": "5:26:08", "remaining_time": "1:44:37", "throughput": 1484.46, "total_tokens": 29049152} {"current_steps": 137650, "total_steps": 181800, "loss": 0.0038, "lr": 8.457699815581283e-06, "epoch": 15.143014301430142, "percentage": 75.72, "elapsed_time": "5:26:09", "remaining_time": "1:44:36", "throughput": 1484.46, "total_tokens": 29050176} {"current_steps": 137655, "total_steps": 181800, "loss": 0.0019, "lr": 8.455900379214909e-06, "epoch": 15.143564356435643, "percentage": 75.72, "elapsed_time": "5:26:10", "remaining_time": "1:44:36", "throughput": 1484.46, "total_tokens": 29051200} {"current_steps": 137660, "total_steps": 181800, "loss": 0.0667, "lr": 8.454101095327565e-06, "epoch": 15.144114411441144, "percentage": 75.72, "elapsed_time": "5:26:10", "remaining_time": "1:44:35", "throughput": 1484.47, "total_tokens": 29052256} {"current_steps": 137665, "total_steps": 181800, "loss": 0.0107, "lr": 8.45230196393584e-06, "epoch": 15.144664466446645, "percentage": 75.72, "elapsed_time": "5:26:11", "remaining_time": "1:44:34", "throughput": 1484.47, "total_tokens": 29053312} {"current_steps": 137670, "total_steps": 181800, "loss": 0.0464, "lr": 8.450502985056299e-06, "epoch": 15.145214521452145, "percentage": 75.73, "elapsed_time": "5:26:12", "remaining_time": "1:44:33", "throughput": 1484.47, "total_tokens": 29054400} {"current_steps": 137675, "total_steps": 181800, "loss": 0.0076, "lr": 8.44870415870554e-06, "epoch": 15.145764576457646, "percentage": 75.73, "elapsed_time": "5:26:12", "remaining_time": "1:44:33", "throughput": 1484.47, "total_tokens": 29055456} {"current_steps": 137680, "total_steps": 181800, "loss": 0.0227, "lr": 8.44690548490013e-06, "epoch": 15.146314631463147, "percentage": 75.73, "elapsed_time": "5:26:13", "remaining_time": "1:44:32", "throughput": 1484.47, "total_tokens": 29056512} {"current_steps": 137685, "total_steps": 181800, "loss": 0.0356, "lr": 8.445106963656634e-06, "epoch": 15.146864686468646, "percentage": 75.73, "elapsed_time": "5:26:14", "remaining_time": "1:44:31", "throughput": 1484.48, "total_tokens": 29057568} {"current_steps": 137690, "total_steps": 181800, "loss": 0.0123, "lr": 8.443308594991661e-06, "epoch": 15.147414741474147, "percentage": 75.74, "elapsed_time": "5:26:14", "remaining_time": "1:44:30", "throughput": 1484.48, "total_tokens": 29058592} {"current_steps": 137695, "total_steps": 181800, "loss": 0.0057, "lr": 8.441510378921757e-06, "epoch": 15.147964796479648, "percentage": 75.74, "elapsed_time": "5:26:15", "remaining_time": "1:44:30", "throughput": 1484.48, "total_tokens": 29059648} {"current_steps": 137700, "total_steps": 181800, "loss": 0.0269, "lr": 8.439712315463519e-06, "epoch": 15.148514851485148, "percentage": 75.74, "elapsed_time": "5:26:16", "remaining_time": "1:44:29", "throughput": 1484.48, "total_tokens": 29060736} {"current_steps": 137705, "total_steps": 181800, "loss": 0.0715, "lr": 8.437914404633501e-06, "epoch": 15.149064906490649, "percentage": 75.75, "elapsed_time": "5:26:17", "remaining_time": "1:44:28", "throughput": 1484.48, "total_tokens": 29061792} {"current_steps": 137710, "total_steps": 181800, "loss": 0.0027, "lr": 8.436116646448275e-06, "epoch": 15.14961496149615, "percentage": 75.75, "elapsed_time": "5:26:17", "remaining_time": "1:44:28", "throughput": 1484.48, "total_tokens": 29062848} {"current_steps": 137715, "total_steps": 181800, "loss": 0.0013, "lr": 8.43431904092441e-06, "epoch": 15.150165016501651, "percentage": 75.75, "elapsed_time": "5:26:18", "remaining_time": "1:44:27", "throughput": 1484.48, "total_tokens": 29063872} {"current_steps": 137720, "total_steps": 181800, "loss": 0.0026, "lr": 8.432521588078479e-06, "epoch": 15.15071507150715, "percentage": 75.75, "elapsed_time": "5:26:19", "remaining_time": "1:44:26", "throughput": 1484.49, "total_tokens": 29064960} {"current_steps": 137725, "total_steps": 181800, "loss": 0.0036, "lr": 8.430724287927056e-06, "epoch": 15.151265126512651, "percentage": 75.76, "elapsed_time": "5:26:19", "remaining_time": "1:44:25", "throughput": 1484.49, "total_tokens": 29065984} {"current_steps": 137730, "total_steps": 181800, "loss": 0.0024, "lr": 8.428927140486695e-06, "epoch": 15.151815181518153, "percentage": 75.76, "elapsed_time": "5:26:20", "remaining_time": "1:44:25", "throughput": 1484.49, "total_tokens": 29067072} {"current_steps": 137735, "total_steps": 181800, "loss": 0.0122, "lr": 8.427130145773953e-06, "epoch": 15.152365236523652, "percentage": 75.76, "elapsed_time": "5:26:21", "remaining_time": "1:44:24", "throughput": 1484.49, "total_tokens": 29068032} {"current_steps": 137740, "total_steps": 181800, "loss": 0.0019, "lr": 8.425333303805411e-06, "epoch": 15.152915291529153, "percentage": 75.76, "elapsed_time": "5:26:21", "remaining_time": "1:44:23", "throughput": 1484.49, "total_tokens": 29069152} {"current_steps": 137745, "total_steps": 181800, "loss": 0.0021, "lr": 8.4235366145976e-06, "epoch": 15.153465346534654, "percentage": 75.77, "elapsed_time": "5:26:22", "remaining_time": "1:44:23", "throughput": 1484.5, "total_tokens": 29070272} {"current_steps": 137750, "total_steps": 181800, "loss": 0.0831, "lr": 8.421740078167111e-06, "epoch": 15.154015401540153, "percentage": 75.77, "elapsed_time": "5:26:23", "remaining_time": "1:44:22", "throughput": 1484.5, "total_tokens": 29071328} {"current_steps": 137755, "total_steps": 181800, "loss": 0.0924, "lr": 8.419943694530494e-06, "epoch": 15.154565456545654, "percentage": 75.77, "elapsed_time": "5:26:23", "remaining_time": "1:44:21", "throughput": 1484.5, "total_tokens": 29072352} {"current_steps": 137760, "total_steps": 181800, "loss": 0.1126, "lr": 8.418147463704287e-06, "epoch": 15.155115511551156, "percentage": 75.78, "elapsed_time": "5:26:24", "remaining_time": "1:44:20", "throughput": 1484.5, "total_tokens": 29073440} {"current_steps": 137765, "total_steps": 181800, "loss": 0.0139, "lr": 8.41635138570507e-06, "epoch": 15.155665566556655, "percentage": 75.78, "elapsed_time": "5:26:25", "remaining_time": "1:44:20", "throughput": 1484.51, "total_tokens": 29074528} {"current_steps": 137770, "total_steps": 181800, "loss": 0.0051, "lr": 8.414555460549375e-06, "epoch": 15.156215621562156, "percentage": 75.78, "elapsed_time": "5:26:26", "remaining_time": "1:44:19", "throughput": 1484.51, "total_tokens": 29075616} {"current_steps": 137775, "total_steps": 181800, "loss": 0.157, "lr": 8.412759688253763e-06, "epoch": 15.156765676567657, "percentage": 75.78, "elapsed_time": "5:26:26", "remaining_time": "1:44:18", "throughput": 1484.51, "total_tokens": 29076640} {"current_steps": 137780, "total_steps": 181800, "loss": 0.0019, "lr": 8.410964068834796e-06, "epoch": 15.157315731573158, "percentage": 75.79, "elapsed_time": "5:26:27", "remaining_time": "1:44:18", "throughput": 1484.51, "total_tokens": 29077664} {"current_steps": 137785, "total_steps": 181800, "loss": 0.1111, "lr": 8.409168602309003e-06, "epoch": 15.157865786578657, "percentage": 75.79, "elapsed_time": "5:26:28", "remaining_time": "1:44:17", "throughput": 1484.51, "total_tokens": 29078720} {"current_steps": 137790, "total_steps": 181800, "loss": 0.0011, "lr": 8.407373288692952e-06, "epoch": 15.158415841584159, "percentage": 75.79, "elapsed_time": "5:26:28", "remaining_time": "1:44:16", "throughput": 1484.51, "total_tokens": 29079776} {"current_steps": 137795, "total_steps": 181800, "loss": 0.0054, "lr": 8.40557812800317e-06, "epoch": 15.15896589658966, "percentage": 75.79, "elapsed_time": "5:26:29", "remaining_time": "1:44:15", "throughput": 1484.51, "total_tokens": 29080832} {"current_steps": 137800, "total_steps": 181800, "loss": 0.0146, "lr": 8.40378312025622e-06, "epoch": 15.159515951595159, "percentage": 75.8, "elapsed_time": "5:26:30", "remaining_time": "1:44:15", "throughput": 1484.52, "total_tokens": 29081952} {"current_steps": 137805, "total_steps": 181800, "loss": 0.0011, "lr": 8.40198826546863e-06, "epoch": 15.16006600660066, "percentage": 75.8, "elapsed_time": "5:26:30", "remaining_time": "1:44:14", "throughput": 1484.52, "total_tokens": 29083040} {"current_steps": 137810, "total_steps": 181800, "loss": 0.0024, "lr": 8.400193563656947e-06, "epoch": 15.160616061606161, "percentage": 75.8, "elapsed_time": "5:26:31", "remaining_time": "1:44:13", "throughput": 1484.52, "total_tokens": 29084064} {"current_steps": 137815, "total_steps": 181800, "loss": 0.006, "lr": 8.398399014837727e-06, "epoch": 15.16116611661166, "percentage": 75.81, "elapsed_time": "5:26:32", "remaining_time": "1:44:13", "throughput": 1484.52, "total_tokens": 29085088} {"current_steps": 137820, "total_steps": 181800, "loss": 0.1268, "lr": 8.396604619027485e-06, "epoch": 15.161716171617162, "percentage": 75.81, "elapsed_time": "5:26:32", "remaining_time": "1:44:12", "throughput": 1484.52, "total_tokens": 29086112} {"current_steps": 137825, "total_steps": 181800, "loss": 0.006, "lr": 8.39481037624278e-06, "epoch": 15.162266226622663, "percentage": 75.81, "elapsed_time": "5:26:33", "remaining_time": "1:44:11", "throughput": 1484.52, "total_tokens": 29087168} {"current_steps": 137830, "total_steps": 181800, "loss": 0.0006, "lr": 8.393016286500132e-06, "epoch": 15.162816281628162, "percentage": 75.81, "elapsed_time": "5:26:34", "remaining_time": "1:44:10", "throughput": 1484.52, "total_tokens": 29088192} {"current_steps": 137835, "total_steps": 181800, "loss": 0.0259, "lr": 8.391222349816086e-06, "epoch": 15.163366336633663, "percentage": 75.82, "elapsed_time": "5:26:34", "remaining_time": "1:44:10", "throughput": 1484.52, "total_tokens": 29089184} {"current_steps": 137840, "total_steps": 181800, "loss": 0.0074, "lr": 8.389428566207181e-06, "epoch": 15.163916391639164, "percentage": 75.82, "elapsed_time": "5:26:35", "remaining_time": "1:44:09", "throughput": 1484.52, "total_tokens": 29090176} {"current_steps": 137845, "total_steps": 181800, "loss": 0.0604, "lr": 8.387634935689942e-06, "epoch": 15.164466446644665, "percentage": 75.82, "elapsed_time": "5:26:36", "remaining_time": "1:44:08", "throughput": 1484.52, "total_tokens": 29091200} {"current_steps": 137850, "total_steps": 181800, "loss": 0.0314, "lr": 8.38584145828089e-06, "epoch": 15.165016501650165, "percentage": 75.83, "elapsed_time": "5:26:37", "remaining_time": "1:44:08", "throughput": 1484.52, "total_tokens": 29092224} {"current_steps": 137855, "total_steps": 181800, "loss": 0.0138, "lr": 8.384048133996578e-06, "epoch": 15.165566556655666, "percentage": 75.83, "elapsed_time": "5:26:37", "remaining_time": "1:44:07", "throughput": 1484.52, "total_tokens": 29093216} {"current_steps": 137860, "total_steps": 181800, "loss": 0.058, "lr": 8.382254962853509e-06, "epoch": 15.166116611661167, "percentage": 75.83, "elapsed_time": "5:26:38", "remaining_time": "1:44:06", "throughput": 1484.52, "total_tokens": 29094272} {"current_steps": 137865, "total_steps": 181800, "loss": 0.0486, "lr": 8.380461944868223e-06, "epoch": 15.166666666666666, "percentage": 75.83, "elapsed_time": "5:26:39", "remaining_time": "1:44:05", "throughput": 1484.53, "total_tokens": 29095392} {"current_steps": 137870, "total_steps": 181800, "loss": 0.003, "lr": 8.378669080057253e-06, "epoch": 15.167216721672167, "percentage": 75.84, "elapsed_time": "5:26:39", "remaining_time": "1:44:05", "throughput": 1484.53, "total_tokens": 29096416} {"current_steps": 137875, "total_steps": 181800, "loss": 0.0029, "lr": 8.376876368437106e-06, "epoch": 15.167766776677668, "percentage": 75.84, "elapsed_time": "5:26:40", "remaining_time": "1:44:04", "throughput": 1484.53, "total_tokens": 29097504} {"current_steps": 137880, "total_steps": 181800, "loss": 0.0333, "lr": 8.375083810024323e-06, "epoch": 15.168316831683168, "percentage": 75.84, "elapsed_time": "5:26:41", "remaining_time": "1:44:03", "throughput": 1484.53, "total_tokens": 29098496} {"current_steps": 137885, "total_steps": 181800, "loss": 0.0053, "lr": 8.373291404835405e-06, "epoch": 15.168866886688669, "percentage": 75.84, "elapsed_time": "5:26:41", "remaining_time": "1:44:03", "throughput": 1484.53, "total_tokens": 29099520} {"current_steps": 137890, "total_steps": 181800, "loss": 0.0037, "lr": 8.37149915288688e-06, "epoch": 15.16941694169417, "percentage": 75.85, "elapsed_time": "5:26:42", "remaining_time": "1:44:02", "throughput": 1484.53, "total_tokens": 29100608} {"current_steps": 137895, "total_steps": 181800, "loss": 0.0046, "lr": 8.36970705419528e-06, "epoch": 15.16996699669967, "percentage": 75.85, "elapsed_time": "5:26:43", "remaining_time": "1:44:01", "throughput": 1484.53, "total_tokens": 29101632} {"current_steps": 137900, "total_steps": 181800, "loss": 0.0242, "lr": 8.3679151087771e-06, "epoch": 15.17051705170517, "percentage": 75.85, "elapsed_time": "5:26:43", "remaining_time": "1:44:00", "throughput": 1484.53, "total_tokens": 29102656} {"current_steps": 137905, "total_steps": 181800, "loss": 0.0112, "lr": 8.366123316648875e-06, "epoch": 15.171067106710671, "percentage": 75.86, "elapsed_time": "5:26:44", "remaining_time": "1:44:00", "throughput": 1484.53, "total_tokens": 29103648} {"current_steps": 137910, "total_steps": 181800, "loss": 0.0015, "lr": 8.3643316778271e-06, "epoch": 15.171617161716172, "percentage": 75.86, "elapsed_time": "5:26:45", "remaining_time": "1:43:59", "throughput": 1484.53, "total_tokens": 29104640} {"current_steps": 137915, "total_steps": 181800, "loss": 0.0033, "lr": 8.362540192328308e-06, "epoch": 15.172167216721672, "percentage": 75.86, "elapsed_time": "5:26:46", "remaining_time": "1:43:58", "throughput": 1484.53, "total_tokens": 29105696} {"current_steps": 137920, "total_steps": 181800, "loss": 0.0445, "lr": 8.360748860168987e-06, "epoch": 15.172717271727173, "percentage": 75.86, "elapsed_time": "5:26:46", "remaining_time": "1:43:57", "throughput": 1484.53, "total_tokens": 29106784} {"current_steps": 137925, "total_steps": 181800, "loss": 0.0161, "lr": 8.358957681365664e-06, "epoch": 15.173267326732674, "percentage": 75.87, "elapsed_time": "5:26:47", "remaining_time": "1:43:57", "throughput": 1484.53, "total_tokens": 29107808} {"current_steps": 137930, "total_steps": 181800, "loss": 0.006, "lr": 8.357166655934847e-06, "epoch": 15.173817381738173, "percentage": 75.87, "elapsed_time": "5:26:48", "remaining_time": "1:43:56", "throughput": 1484.53, "total_tokens": 29108800} {"current_steps": 137935, "total_steps": 181800, "loss": 0.0034, "lr": 8.355375783893036e-06, "epoch": 15.174367436743674, "percentage": 75.87, "elapsed_time": "5:26:48", "remaining_time": "1:43:55", "throughput": 1484.53, "total_tokens": 29109792} {"current_steps": 137940, "total_steps": 181800, "loss": 0.0029, "lr": 8.353585065256744e-06, "epoch": 15.174917491749175, "percentage": 75.87, "elapsed_time": "5:26:49", "remaining_time": "1:43:55", "throughput": 1484.53, "total_tokens": 29110784} {"current_steps": 137945, "total_steps": 181800, "loss": 0.0142, "lr": 8.351794500042462e-06, "epoch": 15.175467546754675, "percentage": 75.88, "elapsed_time": "5:26:50", "remaining_time": "1:43:54", "throughput": 1484.53, "total_tokens": 29111872} {"current_steps": 137950, "total_steps": 181800, "loss": 0.0053, "lr": 8.350004088266702e-06, "epoch": 15.176017601760176, "percentage": 75.88, "elapsed_time": "5:26:50", "remaining_time": "1:43:53", "throughput": 1484.53, "total_tokens": 29112928} {"current_steps": 137955, "total_steps": 181800, "loss": 0.0082, "lr": 8.348213829945975e-06, "epoch": 15.176567656765677, "percentage": 75.88, "elapsed_time": "5:26:51", "remaining_time": "1:43:52", "throughput": 1484.53, "total_tokens": 29114016} {"current_steps": 137960, "total_steps": 181800, "loss": 0.1029, "lr": 8.34642372509676e-06, "epoch": 15.177117711771178, "percentage": 75.89, "elapsed_time": "5:26:52", "remaining_time": "1:43:52", "throughput": 1484.54, "total_tokens": 29115040} {"current_steps": 137965, "total_steps": 181800, "loss": 0.0023, "lr": 8.344633773735578e-06, "epoch": 15.177667766776677, "percentage": 75.89, "elapsed_time": "5:26:52", "remaining_time": "1:43:51", "throughput": 1484.54, "total_tokens": 29116128} {"current_steps": 137970, "total_steps": 181800, "loss": 0.0016, "lr": 8.342843975878912e-06, "epoch": 15.178217821782178, "percentage": 75.89, "elapsed_time": "5:26:53", "remaining_time": "1:43:50", "throughput": 1484.54, "total_tokens": 29117216} {"current_steps": 137975, "total_steps": 181800, "loss": 0.0068, "lr": 8.341054331543252e-06, "epoch": 15.17876787678768, "percentage": 75.89, "elapsed_time": "5:26:54", "remaining_time": "1:43:50", "throughput": 1484.54, "total_tokens": 29118240} {"current_steps": 137980, "total_steps": 181800, "loss": 0.0046, "lr": 8.339264840745101e-06, "epoch": 15.179317931793179, "percentage": 75.9, "elapsed_time": "5:26:54", "remaining_time": "1:43:49", "throughput": 1484.54, "total_tokens": 29119264} {"current_steps": 137985, "total_steps": 181800, "loss": 0.092, "lr": 8.337475503500952e-06, "epoch": 15.17986798679868, "percentage": 75.9, "elapsed_time": "5:26:55", "remaining_time": "1:43:48", "throughput": 1484.54, "total_tokens": 29120256} {"current_steps": 137990, "total_steps": 181800, "loss": 0.0015, "lr": 8.335686319827305e-06, "epoch": 15.180418041804181, "percentage": 75.9, "elapsed_time": "5:26:56", "remaining_time": "1:43:47", "throughput": 1484.54, "total_tokens": 29121280} {"current_steps": 137995, "total_steps": 181800, "loss": 0.0014, "lr": 8.333897289740639e-06, "epoch": 15.18096809680968, "percentage": 75.9, "elapsed_time": "5:26:57", "remaining_time": "1:43:47", "throughput": 1484.54, "total_tokens": 29122336} {"current_steps": 138000, "total_steps": 181800, "loss": 0.0097, "lr": 8.332108413257435e-06, "epoch": 15.181518151815181, "percentage": 75.91, "elapsed_time": "5:26:57", "remaining_time": "1:43:46", "throughput": 1484.54, "total_tokens": 29123360} {"current_steps": 138005, "total_steps": 181800, "loss": 0.0034, "lr": 8.330319690394193e-06, "epoch": 15.182068206820682, "percentage": 75.91, "elapsed_time": "5:26:58", "remaining_time": "1:43:45", "throughput": 1484.55, "total_tokens": 29124480} {"current_steps": 138010, "total_steps": 181800, "loss": 0.0044, "lr": 8.328531121167394e-06, "epoch": 15.182618261826182, "percentage": 75.91, "elapsed_time": "5:26:59", "remaining_time": "1:43:45", "throughput": 1484.54, "total_tokens": 29125472} {"current_steps": 138015, "total_steps": 181800, "loss": 0.0051, "lr": 8.32674270559353e-06, "epoch": 15.183168316831683, "percentage": 75.92, "elapsed_time": "5:26:59", "remaining_time": "1:43:44", "throughput": 1484.55, "total_tokens": 29126560} {"current_steps": 138020, "total_steps": 181800, "loss": 0.0351, "lr": 8.324954443689082e-06, "epoch": 15.183718371837184, "percentage": 75.92, "elapsed_time": "5:27:00", "remaining_time": "1:43:43", "throughput": 1484.55, "total_tokens": 29127584} {"current_steps": 138025, "total_steps": 181800, "loss": 0.0012, "lr": 8.323166335470515e-06, "epoch": 15.184268426842685, "percentage": 75.92, "elapsed_time": "5:27:01", "remaining_time": "1:43:42", "throughput": 1484.55, "total_tokens": 29128672} {"current_steps": 138030, "total_steps": 181800, "loss": 0.0063, "lr": 8.321378380954331e-06, "epoch": 15.184818481848184, "percentage": 75.92, "elapsed_time": "5:27:01", "remaining_time": "1:43:42", "throughput": 1484.55, "total_tokens": 29129728} {"current_steps": 138035, "total_steps": 181800, "loss": 0.0939, "lr": 8.319590580156994e-06, "epoch": 15.185368536853685, "percentage": 75.93, "elapsed_time": "5:27:02", "remaining_time": "1:43:41", "throughput": 1484.56, "total_tokens": 29130880} {"current_steps": 138040, "total_steps": 181800, "loss": 0.0004, "lr": 8.317802933094983e-06, "epoch": 15.185918591859187, "percentage": 75.93, "elapsed_time": "5:27:03", "remaining_time": "1:43:40", "throughput": 1484.56, "total_tokens": 29131936} {"current_steps": 138045, "total_steps": 181800, "loss": 0.0035, "lr": 8.316015439784789e-06, "epoch": 15.186468646864686, "percentage": 75.93, "elapsed_time": "5:27:03", "remaining_time": "1:43:40", "throughput": 1484.56, "total_tokens": 29132992} {"current_steps": 138050, "total_steps": 181800, "loss": 0.0734, "lr": 8.314228100242864e-06, "epoch": 15.187018701870187, "percentage": 75.94, "elapsed_time": "5:27:04", "remaining_time": "1:43:39", "throughput": 1484.57, "total_tokens": 29134112} {"current_steps": 138055, "total_steps": 181800, "loss": 0.0279, "lr": 8.3124409144857e-06, "epoch": 15.187568756875688, "percentage": 75.94, "elapsed_time": "5:27:05", "remaining_time": "1:43:38", "throughput": 1484.57, "total_tokens": 29135168} {"current_steps": 138060, "total_steps": 181800, "loss": 0.001, "lr": 8.310653882529753e-06, "epoch": 15.188118811881187, "percentage": 75.94, "elapsed_time": "5:27:06", "remaining_time": "1:43:37", "throughput": 1484.57, "total_tokens": 29136192} {"current_steps": 138065, "total_steps": 181800, "loss": 0.0058, "lr": 8.308867004391502e-06, "epoch": 15.188668866886688, "percentage": 75.94, "elapsed_time": "5:27:06", "remaining_time": "1:43:37", "throughput": 1484.58, "total_tokens": 29137312} {"current_steps": 138070, "total_steps": 181800, "loss": 0.074, "lr": 8.307080280087423e-06, "epoch": 15.18921892189219, "percentage": 75.95, "elapsed_time": "5:27:07", "remaining_time": "1:43:36", "throughput": 1484.58, "total_tokens": 29138368} {"current_steps": 138075, "total_steps": 181800, "loss": 0.0018, "lr": 8.305293709633965e-06, "epoch": 15.189768976897689, "percentage": 75.95, "elapsed_time": "5:27:08", "remaining_time": "1:43:35", "throughput": 1484.58, "total_tokens": 29139456} {"current_steps": 138080, "total_steps": 181800, "loss": 0.078, "lr": 8.303507293047613e-06, "epoch": 15.19031903190319, "percentage": 75.95, "elapsed_time": "5:27:08", "remaining_time": "1:43:35", "throughput": 1484.58, "total_tokens": 29140480} {"current_steps": 138085, "total_steps": 181800, "loss": 0.0327, "lr": 8.301721030344823e-06, "epoch": 15.190869086908691, "percentage": 75.95, "elapsed_time": "5:27:09", "remaining_time": "1:43:34", "throughput": 1484.58, "total_tokens": 29141472} {"current_steps": 138090, "total_steps": 181800, "loss": 0.1257, "lr": 8.29993492154205e-06, "epoch": 15.191419141914192, "percentage": 75.96, "elapsed_time": "5:27:10", "remaining_time": "1:43:33", "throughput": 1484.58, "total_tokens": 29142560} {"current_steps": 138095, "total_steps": 181800, "loss": 0.0052, "lr": 8.29814896665576e-06, "epoch": 15.191969196919691, "percentage": 75.96, "elapsed_time": "5:27:10", "remaining_time": "1:43:32", "throughput": 1484.58, "total_tokens": 29143584} {"current_steps": 138100, "total_steps": 181800, "loss": 0.0321, "lr": 8.29636316570242e-06, "epoch": 15.192519251925193, "percentage": 75.96, "elapsed_time": "5:27:11", "remaining_time": "1:43:32", "throughput": 1484.58, "total_tokens": 29144640} {"current_steps": 138105, "total_steps": 181800, "loss": 0.0116, "lr": 8.294577518698493e-06, "epoch": 15.193069306930694, "percentage": 75.97, "elapsed_time": "5:27:12", "remaining_time": "1:43:31", "throughput": 1484.59, "total_tokens": 29145728} {"current_steps": 138110, "total_steps": 181800, "loss": 0.0013, "lr": 8.292792025660429e-06, "epoch": 15.193619361936193, "percentage": 75.97, "elapsed_time": "5:27:12", "remaining_time": "1:43:30", "throughput": 1484.58, "total_tokens": 29146688} {"current_steps": 138115, "total_steps": 181800, "loss": 0.0559, "lr": 8.291006686604677e-06, "epoch": 15.194169416941694, "percentage": 75.97, "elapsed_time": "5:27:13", "remaining_time": "1:43:29", "throughput": 1484.58, "total_tokens": 29147680} {"current_steps": 138120, "total_steps": 181800, "loss": 0.0034, "lr": 8.289221501547698e-06, "epoch": 15.194719471947195, "percentage": 75.97, "elapsed_time": "5:27:14", "remaining_time": "1:43:29", "throughput": 1484.58, "total_tokens": 29148736} {"current_steps": 138125, "total_steps": 181800, "loss": 0.0066, "lr": 8.287436470505943e-06, "epoch": 15.195269526952695, "percentage": 75.98, "elapsed_time": "5:27:14", "remaining_time": "1:43:28", "throughput": 1484.59, "total_tokens": 29149824} {"current_steps": 138130, "total_steps": 181800, "loss": 0.0014, "lr": 8.285651593495878e-06, "epoch": 15.195819581958196, "percentage": 75.98, "elapsed_time": "5:27:15", "remaining_time": "1:43:27", "throughput": 1484.59, "total_tokens": 29150880} {"current_steps": 138135, "total_steps": 181800, "loss": 0.0075, "lr": 8.28386687053394e-06, "epoch": 15.196369636963697, "percentage": 75.98, "elapsed_time": "5:27:16", "remaining_time": "1:43:27", "throughput": 1484.59, "total_tokens": 29151968} {"current_steps": 138140, "total_steps": 181800, "loss": 0.0278, "lr": 8.282082301636573e-06, "epoch": 15.196919691969198, "percentage": 75.98, "elapsed_time": "5:27:17", "remaining_time": "1:43:26", "throughput": 1484.59, "total_tokens": 29153024} {"current_steps": 138145, "total_steps": 181800, "loss": 0.0014, "lr": 8.280297886820237e-06, "epoch": 15.197469746974697, "percentage": 75.99, "elapsed_time": "5:27:17", "remaining_time": "1:43:25", "throughput": 1484.6, "total_tokens": 29154144} {"current_steps": 138150, "total_steps": 181800, "loss": 0.0006, "lr": 8.278513626101367e-06, "epoch": 15.198019801980198, "percentage": 75.99, "elapsed_time": "5:27:18", "remaining_time": "1:43:24", "throughput": 1484.6, "total_tokens": 29155168} {"current_steps": 138155, "total_steps": 181800, "loss": 0.0009, "lr": 8.276729519496412e-06, "epoch": 15.1985698569857, "percentage": 75.99, "elapsed_time": "5:27:19", "remaining_time": "1:43:24", "throughput": 1484.6, "total_tokens": 29156224} {"current_steps": 138160, "total_steps": 181800, "loss": 0.0047, "lr": 8.274945567021828e-06, "epoch": 15.199119911991199, "percentage": 76.0, "elapsed_time": "5:27:19", "remaining_time": "1:43:23", "throughput": 1484.6, "total_tokens": 29157184} {"current_steps": 138165, "total_steps": 181800, "loss": 0.0009, "lr": 8.273161768694032e-06, "epoch": 15.1996699669967, "percentage": 76.0, "elapsed_time": "5:27:20", "remaining_time": "1:43:22", "throughput": 1484.6, "total_tokens": 29158208} {"current_steps": 138170, "total_steps": 181800, "loss": 0.0399, "lr": 8.271378124529488e-06, "epoch": 15.2002200220022, "percentage": 76.0, "elapsed_time": "5:27:21", "remaining_time": "1:43:22", "throughput": 1484.6, "total_tokens": 29159232} {"current_steps": 138175, "total_steps": 181800, "loss": 0.0568, "lr": 8.269594634544617e-06, "epoch": 15.2007700770077, "percentage": 76.0, "elapsed_time": "5:27:21", "remaining_time": "1:43:21", "throughput": 1484.6, "total_tokens": 29160224} {"current_steps": 138180, "total_steps": 181800, "loss": 0.0842, "lr": 8.267811298755865e-06, "epoch": 15.201320132013201, "percentage": 76.01, "elapsed_time": "5:27:22", "remaining_time": "1:43:20", "throughput": 1484.6, "total_tokens": 29161280} {"current_steps": 138185, "total_steps": 181800, "loss": 0.0403, "lr": 8.266028117179673e-06, "epoch": 15.201870187018702, "percentage": 76.01, "elapsed_time": "5:27:23", "remaining_time": "1:43:19", "throughput": 1484.6, "total_tokens": 29162336} {"current_steps": 138190, "total_steps": 181800, "loss": 0.0145, "lr": 8.264245089832461e-06, "epoch": 15.202420242024202, "percentage": 76.01, "elapsed_time": "5:27:23", "remaining_time": "1:43:19", "throughput": 1484.6, "total_tokens": 29163424} {"current_steps": 138195, "total_steps": 181800, "loss": 0.0317, "lr": 8.262462216730685e-06, "epoch": 15.202970297029703, "percentage": 76.01, "elapsed_time": "5:27:24", "remaining_time": "1:43:18", "throughput": 1484.61, "total_tokens": 29164512} {"current_steps": 138200, "total_steps": 181800, "loss": 0.0456, "lr": 8.26067949789075e-06, "epoch": 15.203520352035204, "percentage": 76.02, "elapsed_time": "5:27:25", "remaining_time": "1:43:17", "throughput": 1484.61, "total_tokens": 29165536} {"current_steps": 138205, "total_steps": 181800, "loss": 0.1654, "lr": 8.25889693332911e-06, "epoch": 15.204070407040705, "percentage": 76.02, "elapsed_time": "5:27:26", "remaining_time": "1:43:17", "throughput": 1484.61, "total_tokens": 29166592} {"current_steps": 138210, "total_steps": 181800, "loss": 0.0011, "lr": 8.257114523062177e-06, "epoch": 15.204620462046204, "percentage": 76.02, "elapsed_time": "5:27:26", "remaining_time": "1:43:16", "throughput": 1484.61, "total_tokens": 29167616} {"current_steps": 138215, "total_steps": 181800, "loss": 0.001, "lr": 8.255332267106383e-06, "epoch": 15.205170517051705, "percentage": 76.03, "elapsed_time": "5:27:27", "remaining_time": "1:43:15", "throughput": 1484.61, "total_tokens": 29168672} {"current_steps": 138220, "total_steps": 181800, "loss": 0.1518, "lr": 8.253550165478166e-06, "epoch": 15.205720572057206, "percentage": 76.03, "elapsed_time": "5:27:28", "remaining_time": "1:43:14", "throughput": 1484.61, "total_tokens": 29169728} {"current_steps": 138225, "total_steps": 181800, "loss": 0.0066, "lr": 8.25176821819394e-06, "epoch": 15.206270627062706, "percentage": 76.03, "elapsed_time": "5:27:28", "remaining_time": "1:43:14", "throughput": 1484.61, "total_tokens": 29170784} {"current_steps": 138230, "total_steps": 181800, "loss": 0.0014, "lr": 8.249986425270124e-06, "epoch": 15.206820682068207, "percentage": 76.03, "elapsed_time": "5:27:29", "remaining_time": "1:43:13", "throughput": 1484.62, "total_tokens": 29171904} {"current_steps": 138235, "total_steps": 181800, "loss": 0.0106, "lr": 8.248204786723144e-06, "epoch": 15.207370737073708, "percentage": 76.04, "elapsed_time": "5:27:30", "remaining_time": "1:43:12", "throughput": 1484.62, "total_tokens": 29172896} {"current_steps": 138240, "total_steps": 181800, "loss": 0.0007, "lr": 8.246423302569423e-06, "epoch": 15.207920792079207, "percentage": 76.04, "elapsed_time": "5:27:30", "remaining_time": "1:43:12", "throughput": 1484.62, "total_tokens": 29173984} {"current_steps": 138245, "total_steps": 181800, "loss": 0.0991, "lr": 8.244641972825384e-06, "epoch": 15.208470847084708, "percentage": 76.04, "elapsed_time": "5:27:31", "remaining_time": "1:43:11", "throughput": 1484.62, "total_tokens": 29175008} {"current_steps": 138250, "total_steps": 181800, "loss": 0.0057, "lr": 8.242860797507445e-06, "epoch": 15.20902090209021, "percentage": 76.05, "elapsed_time": "5:27:32", "remaining_time": "1:43:10", "throughput": 1484.62, "total_tokens": 29176064} {"current_steps": 138255, "total_steps": 181800, "loss": 0.0053, "lr": 8.241079776632008e-06, "epoch": 15.209570957095709, "percentage": 76.05, "elapsed_time": "5:27:32", "remaining_time": "1:43:09", "throughput": 1484.62, "total_tokens": 29177120} {"current_steps": 138260, "total_steps": 181800, "loss": 0.0428, "lr": 8.239298910215502e-06, "epoch": 15.21012101210121, "percentage": 76.05, "elapsed_time": "5:27:33", "remaining_time": "1:43:09", "throughput": 1484.63, "total_tokens": 29178208} {"current_steps": 138265, "total_steps": 181800, "loss": 0.0136, "lr": 8.23751819827433e-06, "epoch": 15.210671067106711, "percentage": 76.05, "elapsed_time": "5:27:34", "remaining_time": "1:43:08", "throughput": 1484.63, "total_tokens": 29179264} {"current_steps": 138270, "total_steps": 181800, "loss": 0.026, "lr": 8.235737640824908e-06, "epoch": 15.211221122112212, "percentage": 76.06, "elapsed_time": "5:27:34", "remaining_time": "1:43:07", "throughput": 1484.63, "total_tokens": 29180288} {"current_steps": 138275, "total_steps": 181800, "loss": 0.0033, "lr": 8.233957237883657e-06, "epoch": 15.211771177117711, "percentage": 76.06, "elapsed_time": "5:27:35", "remaining_time": "1:43:07", "throughput": 1484.63, "total_tokens": 29181344} {"current_steps": 138280, "total_steps": 181800, "loss": 0.1918, "lr": 8.232176989466968e-06, "epoch": 15.212321232123212, "percentage": 76.06, "elapsed_time": "5:27:36", "remaining_time": "1:43:06", "throughput": 1484.63, "total_tokens": 29182432} {"current_steps": 138285, "total_steps": 181800, "loss": 0.0016, "lr": 8.230396895591267e-06, "epoch": 15.212871287128714, "percentage": 76.06, "elapsed_time": "5:27:37", "remaining_time": "1:43:05", "throughput": 1484.63, "total_tokens": 29183488} {"current_steps": 138290, "total_steps": 181800, "loss": 0.0019, "lr": 8.228616956272942e-06, "epoch": 15.213421342134213, "percentage": 76.07, "elapsed_time": "5:27:37", "remaining_time": "1:43:04", "throughput": 1484.63, "total_tokens": 29184512} {"current_steps": 138295, "total_steps": 181800, "loss": 0.0204, "lr": 8.226837171528407e-06, "epoch": 15.213971397139714, "percentage": 76.07, "elapsed_time": "5:27:38", "remaining_time": "1:43:04", "throughput": 1484.64, "total_tokens": 29185600} {"current_steps": 138300, "total_steps": 181800, "loss": 0.059, "lr": 8.225057541374074e-06, "epoch": 15.214521452145215, "percentage": 76.07, "elapsed_time": "5:27:39", "remaining_time": "1:43:03", "throughput": 1484.64, "total_tokens": 29186656} {"current_steps": 138305, "total_steps": 181800, "loss": 0.0019, "lr": 8.223278065826326e-06, "epoch": 15.215071507150714, "percentage": 76.08, "elapsed_time": "5:27:39", "remaining_time": "1:43:02", "throughput": 1484.64, "total_tokens": 29187712} {"current_steps": 138310, "total_steps": 181800, "loss": 0.0083, "lr": 8.221498744901584e-06, "epoch": 15.215621562156215, "percentage": 76.08, "elapsed_time": "5:27:40", "remaining_time": "1:43:02", "throughput": 1484.64, "total_tokens": 29188704} {"current_steps": 138315, "total_steps": 181800, "loss": 0.3053, "lr": 8.219719578616228e-06, "epoch": 15.216171617161717, "percentage": 76.08, "elapsed_time": "5:27:41", "remaining_time": "1:43:01", "throughput": 1484.64, "total_tokens": 29189760} {"current_steps": 138320, "total_steps": 181800, "loss": 0.0007, "lr": 8.217940566986673e-06, "epoch": 15.216721672167218, "percentage": 76.08, "elapsed_time": "5:27:41", "remaining_time": "1:43:00", "throughput": 1484.64, "total_tokens": 29190784} {"current_steps": 138325, "total_steps": 181800, "loss": 0.0218, "lr": 8.2161617100293e-06, "epoch": 15.217271727172717, "percentage": 76.09, "elapsed_time": "5:27:42", "remaining_time": "1:42:59", "throughput": 1484.64, "total_tokens": 29191840} {"current_steps": 138330, "total_steps": 181800, "loss": 0.0167, "lr": 8.21438300776051e-06, "epoch": 15.217821782178218, "percentage": 76.09, "elapsed_time": "5:27:43", "remaining_time": "1:42:59", "throughput": 1484.65, "total_tokens": 29192928} {"current_steps": 138335, "total_steps": 181800, "loss": 0.0071, "lr": 8.212604460196704e-06, "epoch": 15.218371837183719, "percentage": 76.09, "elapsed_time": "5:27:43", "remaining_time": "1:42:58", "throughput": 1484.65, "total_tokens": 29194016} {"current_steps": 138340, "total_steps": 181800, "loss": 0.0405, "lr": 8.21082606735426e-06, "epoch": 15.218921892189218, "percentage": 76.09, "elapsed_time": "5:27:44", "remaining_time": "1:42:57", "throughput": 1484.65, "total_tokens": 29195040} {"current_steps": 138345, "total_steps": 181800, "loss": 0.0017, "lr": 8.209047829249586e-06, "epoch": 15.21947194719472, "percentage": 76.1, "elapsed_time": "5:27:45", "remaining_time": "1:42:56", "throughput": 1484.65, "total_tokens": 29196064} {"current_steps": 138350, "total_steps": 181800, "loss": 0.0014, "lr": 8.207269745899048e-06, "epoch": 15.22002200220022, "percentage": 76.1, "elapsed_time": "5:27:45", "remaining_time": "1:42:56", "throughput": 1484.65, "total_tokens": 29197056} {"current_steps": 138355, "total_steps": 181800, "loss": 0.0057, "lr": 8.205491817319052e-06, "epoch": 15.22057205720572, "percentage": 76.1, "elapsed_time": "5:27:46", "remaining_time": "1:42:55", "throughput": 1484.65, "total_tokens": 29198112} {"current_steps": 138360, "total_steps": 181800, "loss": 0.0104, "lr": 8.203714043525986e-06, "epoch": 15.221122112211221, "percentage": 76.11, "elapsed_time": "5:27:47", "remaining_time": "1:42:54", "throughput": 1484.65, "total_tokens": 29199104} {"current_steps": 138365, "total_steps": 181800, "loss": 0.0025, "lr": 8.201936424536219e-06, "epoch": 15.221672167216722, "percentage": 76.11, "elapsed_time": "5:27:48", "remaining_time": "1:42:54", "throughput": 1484.65, "total_tokens": 29200192} {"current_steps": 138370, "total_steps": 181800, "loss": 0.0082, "lr": 8.200158960366152e-06, "epoch": 15.222222222222221, "percentage": 76.11, "elapsed_time": "5:27:48", "remaining_time": "1:42:53", "throughput": 1484.65, "total_tokens": 29201184} {"current_steps": 138375, "total_steps": 181800, "loss": 0.0057, "lr": 8.198381651032158e-06, "epoch": 15.222772277227723, "percentage": 76.11, "elapsed_time": "5:27:49", "remaining_time": "1:42:52", "throughput": 1484.65, "total_tokens": 29202240} {"current_steps": 138380, "total_steps": 181800, "loss": 0.0036, "lr": 8.196604496550612e-06, "epoch": 15.223322332233224, "percentage": 76.12, "elapsed_time": "5:27:50", "remaining_time": "1:42:51", "throughput": 1484.66, "total_tokens": 29203328} {"current_steps": 138385, "total_steps": 181800, "loss": 0.0038, "lr": 8.194827496937896e-06, "epoch": 15.223872387238725, "percentage": 76.12, "elapsed_time": "5:27:50", "remaining_time": "1:42:51", "throughput": 1484.66, "total_tokens": 29204352} {"current_steps": 138390, "total_steps": 181800, "loss": 0.0056, "lr": 8.193050652210393e-06, "epoch": 15.224422442244224, "percentage": 76.12, "elapsed_time": "5:27:51", "remaining_time": "1:42:50", "throughput": 1484.65, "total_tokens": 29205344} {"current_steps": 138395, "total_steps": 181800, "loss": 0.0062, "lr": 8.191273962384486e-06, "epoch": 15.224972497249725, "percentage": 76.12, "elapsed_time": "5:27:52", "remaining_time": "1:42:49", "throughput": 1484.65, "total_tokens": 29206400} {"current_steps": 138400, "total_steps": 181800, "loss": 0.0027, "lr": 8.18949742747654e-06, "epoch": 15.225522552255226, "percentage": 76.13, "elapsed_time": "5:27:52", "remaining_time": "1:42:49", "throughput": 1484.65, "total_tokens": 29207424} {"current_steps": 138405, "total_steps": 181800, "loss": 0.0119, "lr": 8.187721047502923e-06, "epoch": 15.226072607260726, "percentage": 76.13, "elapsed_time": "5:27:53", "remaining_time": "1:42:48", "throughput": 1484.66, "total_tokens": 29208512} {"current_steps": 138410, "total_steps": 181800, "loss": 0.0445, "lr": 8.185944822480013e-06, "epoch": 15.226622662266227, "percentage": 76.13, "elapsed_time": "5:27:54", "remaining_time": "1:42:47", "throughput": 1484.66, "total_tokens": 29209504} {"current_steps": 138415, "total_steps": 181800, "loss": 0.002, "lr": 8.18416875242419e-06, "epoch": 15.227172717271728, "percentage": 76.14, "elapsed_time": "5:27:54", "remaining_time": "1:42:46", "throughput": 1484.66, "total_tokens": 29210560} {"current_steps": 138420, "total_steps": 181800, "loss": 0.0064, "lr": 8.182392837351804e-06, "epoch": 15.227722772277227, "percentage": 76.14, "elapsed_time": "5:27:55", "remaining_time": "1:42:46", "throughput": 1484.66, "total_tokens": 29211616} {"current_steps": 138425, "total_steps": 181800, "loss": 0.0012, "lr": 8.180617077279245e-06, "epoch": 15.228272827282728, "percentage": 76.14, "elapsed_time": "5:27:56", "remaining_time": "1:42:45", "throughput": 1484.66, "total_tokens": 29212672} {"current_steps": 138430, "total_steps": 181800, "loss": 0.0446, "lr": 8.178841472222856e-06, "epoch": 15.22882288228823, "percentage": 76.14, "elapsed_time": "5:27:57", "remaining_time": "1:42:44", "throughput": 1484.66, "total_tokens": 29213760} {"current_steps": 138435, "total_steps": 181800, "loss": 0.0027, "lr": 8.177066022199026e-06, "epoch": 15.229372937293729, "percentage": 76.15, "elapsed_time": "5:27:57", "remaining_time": "1:42:44", "throughput": 1484.67, "total_tokens": 29214848} {"current_steps": 138440, "total_steps": 181800, "loss": 0.051, "lr": 8.175290727224095e-06, "epoch": 15.22992299229923, "percentage": 76.15, "elapsed_time": "5:27:58", "remaining_time": "1:42:43", "throughput": 1484.67, "total_tokens": 29215840} {"current_steps": 138445, "total_steps": 181800, "loss": 0.0368, "lr": 8.173515587314438e-06, "epoch": 15.23047304730473, "percentage": 76.15, "elapsed_time": "5:27:59", "remaining_time": "1:42:42", "throughput": 1484.67, "total_tokens": 29216928} {"current_steps": 138450, "total_steps": 181800, "loss": 0.0694, "lr": 8.171740602486419e-06, "epoch": 15.231023102310232, "percentage": 76.16, "elapsed_time": "5:27:59", "remaining_time": "1:42:41", "throughput": 1484.67, "total_tokens": 29217984} {"current_steps": 138455, "total_steps": 181800, "loss": 0.0897, "lr": 8.169965772756385e-06, "epoch": 15.231573157315731, "percentage": 76.16, "elapsed_time": "5:28:00", "remaining_time": "1:42:41", "throughput": 1484.67, "total_tokens": 29219072} {"current_steps": 138460, "total_steps": 181800, "loss": 0.0055, "lr": 8.16819109814071e-06, "epoch": 15.232123212321232, "percentage": 76.16, "elapsed_time": "5:28:01", "remaining_time": "1:42:40", "throughput": 1484.67, "total_tokens": 29220128} {"current_steps": 138465, "total_steps": 181800, "loss": 0.0396, "lr": 8.166416578655739e-06, "epoch": 15.232673267326733, "percentage": 76.16, "elapsed_time": "5:28:01", "remaining_time": "1:42:39", "throughput": 1484.68, "total_tokens": 29221248} {"current_steps": 138470, "total_steps": 181800, "loss": 0.1361, "lr": 8.164642214317814e-06, "epoch": 15.233223322332233, "percentage": 76.17, "elapsed_time": "5:28:02", "remaining_time": "1:42:39", "throughput": 1484.68, "total_tokens": 29222304} {"current_steps": 138475, "total_steps": 181800, "loss": 0.0023, "lr": 8.162868005143318e-06, "epoch": 15.233773377337734, "percentage": 76.17, "elapsed_time": "5:28:03", "remaining_time": "1:42:38", "throughput": 1484.68, "total_tokens": 29223360} {"current_steps": 138480, "total_steps": 181800, "loss": 0.1248, "lr": 8.161093951148582e-06, "epoch": 15.234323432343235, "percentage": 76.17, "elapsed_time": "5:28:03", "remaining_time": "1:42:37", "throughput": 1484.68, "total_tokens": 29224416} {"current_steps": 138485, "total_steps": 181800, "loss": 0.0019, "lr": 8.15932005234997e-06, "epoch": 15.234873487348734, "percentage": 76.17, "elapsed_time": "5:28:04", "remaining_time": "1:42:36", "throughput": 1484.69, "total_tokens": 29225504} {"current_steps": 138490, "total_steps": 181800, "loss": 0.0019, "lr": 8.157546308763825e-06, "epoch": 15.235423542354235, "percentage": 76.18, "elapsed_time": "5:28:05", "remaining_time": "1:42:36", "throughput": 1484.69, "total_tokens": 29226656} {"current_steps": 138495, "total_steps": 181800, "loss": 0.0015, "lr": 8.155772720406484e-06, "epoch": 15.235973597359736, "percentage": 76.18, "elapsed_time": "5:28:06", "remaining_time": "1:42:35", "throughput": 1484.7, "total_tokens": 29227776} {"current_steps": 138500, "total_steps": 181800, "loss": 0.0028, "lr": 8.153999287294307e-06, "epoch": 15.236523652365236, "percentage": 76.18, "elapsed_time": "5:28:06", "remaining_time": "1:42:34", "throughput": 1484.7, "total_tokens": 29228832} {"current_steps": 138505, "total_steps": 181800, "loss": 0.0064, "lr": 8.15222600944363e-06, "epoch": 15.237073707370737, "percentage": 76.19, "elapsed_time": "5:28:07", "remaining_time": "1:42:34", "throughput": 1484.7, "total_tokens": 29229920} {"current_steps": 138510, "total_steps": 181800, "loss": 0.0551, "lr": 8.150452886870812e-06, "epoch": 15.237623762376238, "percentage": 76.19, "elapsed_time": "5:28:08", "remaining_time": "1:42:33", "throughput": 1484.7, "total_tokens": 29230976} {"current_steps": 138515, "total_steps": 181800, "loss": 0.0016, "lr": 8.148679919592186e-06, "epoch": 15.238173817381739, "percentage": 76.19, "elapsed_time": "5:28:08", "remaining_time": "1:42:32", "throughput": 1484.7, "total_tokens": 29231968} {"current_steps": 138520, "total_steps": 181800, "loss": 0.0702, "lr": 8.146907107624083e-06, "epoch": 15.238723872387238, "percentage": 76.19, "elapsed_time": "5:28:09", "remaining_time": "1:42:31", "throughput": 1484.7, "total_tokens": 29232960} {"current_steps": 138525, "total_steps": 181800, "loss": 0.0047, "lr": 8.145134450982858e-06, "epoch": 15.23927392739274, "percentage": 76.2, "elapsed_time": "5:28:10", "remaining_time": "1:42:31", "throughput": 1484.7, "total_tokens": 29233984} {"current_steps": 138530, "total_steps": 181800, "loss": 0.0015, "lr": 8.143361949684825e-06, "epoch": 15.23982398239824, "percentage": 76.2, "elapsed_time": "5:28:10", "remaining_time": "1:42:30", "throughput": 1484.7, "total_tokens": 29235040} {"current_steps": 138535, "total_steps": 181800, "loss": 0.0096, "lr": 8.14158960374635e-06, "epoch": 15.24037403740374, "percentage": 76.2, "elapsed_time": "5:28:11", "remaining_time": "1:42:29", "throughput": 1484.7, "total_tokens": 29236096} {"current_steps": 138540, "total_steps": 181800, "loss": 0.0257, "lr": 8.139817413183757e-06, "epoch": 15.24092409240924, "percentage": 76.2, "elapsed_time": "5:28:12", "remaining_time": "1:42:29", "throughput": 1484.71, "total_tokens": 29237152} {"current_steps": 138545, "total_steps": 181800, "loss": 0.0043, "lr": 8.138045378013364e-06, "epoch": 15.241474147414742, "percentage": 76.21, "elapsed_time": "5:28:12", "remaining_time": "1:42:28", "throughput": 1484.71, "total_tokens": 29238208} {"current_steps": 138550, "total_steps": 181800, "loss": 0.0778, "lr": 8.136273498251529e-06, "epoch": 15.242024202420241, "percentage": 76.21, "elapsed_time": "5:28:13", "remaining_time": "1:42:27", "throughput": 1484.71, "total_tokens": 29239264} {"current_steps": 138555, "total_steps": 181800, "loss": 0.1066, "lr": 8.134501773914557e-06, "epoch": 15.242574257425742, "percentage": 76.21, "elapsed_time": "5:28:14", "remaining_time": "1:42:26", "throughput": 1484.71, "total_tokens": 29240320} {"current_steps": 138560, "total_steps": 181800, "loss": 0.023, "lr": 8.132730205018793e-06, "epoch": 15.243124312431243, "percentage": 76.22, "elapsed_time": "5:28:14", "remaining_time": "1:42:26", "throughput": 1484.71, "total_tokens": 29241408} {"current_steps": 138565, "total_steps": 181800, "loss": 0.0538, "lr": 8.130958791580567e-06, "epoch": 15.243674367436745, "percentage": 76.22, "elapsed_time": "5:28:15", "remaining_time": "1:42:25", "throughput": 1484.71, "total_tokens": 29242432} {"current_steps": 138570, "total_steps": 181800, "loss": 0.0024, "lr": 8.129187533616192e-06, "epoch": 15.244224422442244, "percentage": 76.22, "elapsed_time": "5:28:16", "remaining_time": "1:42:24", "throughput": 1484.72, "total_tokens": 29243552} {"current_steps": 138575, "total_steps": 181800, "loss": 0.0099, "lr": 8.127416431142006e-06, "epoch": 15.244774477447745, "percentage": 76.22, "elapsed_time": "5:28:17", "remaining_time": "1:42:24", "throughput": 1484.72, "total_tokens": 29244608} {"current_steps": 138580, "total_steps": 181800, "loss": 0.0477, "lr": 8.125645484174321e-06, "epoch": 15.245324532453246, "percentage": 76.23, "elapsed_time": "5:28:17", "remaining_time": "1:42:23", "throughput": 1484.72, "total_tokens": 29245728} {"current_steps": 138585, "total_steps": 181800, "loss": 0.0021, "lr": 8.123874692729471e-06, "epoch": 15.245874587458745, "percentage": 76.23, "elapsed_time": "5:28:18", "remaining_time": "1:42:22", "throughput": 1484.72, "total_tokens": 29246688} {"current_steps": 138590, "total_steps": 181800, "loss": 0.0019, "lr": 8.122104056823765e-06, "epoch": 15.246424642464246, "percentage": 76.23, "elapsed_time": "5:28:19", "remaining_time": "1:42:21", "throughput": 1484.72, "total_tokens": 29247712} {"current_steps": 138595, "total_steps": 181800, "loss": 0.0131, "lr": 8.120333576473523e-06, "epoch": 15.246974697469748, "percentage": 76.23, "elapsed_time": "5:28:19", "remaining_time": "1:42:21", "throughput": 1484.72, "total_tokens": 29248800} {"current_steps": 138600, "total_steps": 181800, "loss": 0.0288, "lr": 8.118563251695077e-06, "epoch": 15.247524752475247, "percentage": 76.24, "elapsed_time": "5:28:20", "remaining_time": "1:42:20", "throughput": 1484.73, "total_tokens": 29249856} {"current_steps": 138605, "total_steps": 181800, "loss": 0.004, "lr": 8.116793082504733e-06, "epoch": 15.248074807480748, "percentage": 76.24, "elapsed_time": "5:28:21", "remaining_time": "1:42:19", "throughput": 1484.73, "total_tokens": 29250880} {"current_steps": 138610, "total_steps": 181800, "loss": 0.0198, "lr": 8.115023068918797e-06, "epoch": 15.248624862486249, "percentage": 76.24, "elapsed_time": "5:28:21", "remaining_time": "1:42:18", "throughput": 1484.73, "total_tokens": 29251936} {"current_steps": 138615, "total_steps": 181800, "loss": 0.0065, "lr": 8.113253210953592e-06, "epoch": 15.249174917491748, "percentage": 76.25, "elapsed_time": "5:28:22", "remaining_time": "1:42:18", "throughput": 1484.73, "total_tokens": 29252960} {"current_steps": 138620, "total_steps": 181800, "loss": 0.0014, "lr": 8.111483508625428e-06, "epoch": 15.24972497249725, "percentage": 76.25, "elapsed_time": "5:28:23", "remaining_time": "1:42:17", "throughput": 1484.73, "total_tokens": 29254048} {"current_steps": 138625, "total_steps": 181800, "loss": 0.0063, "lr": 8.109713961950627e-06, "epoch": 15.25027502750275, "percentage": 76.25, "elapsed_time": "5:28:23", "remaining_time": "1:42:16", "throughput": 1484.73, "total_tokens": 29255072} {"current_steps": 138630, "total_steps": 181800, "loss": 0.004, "lr": 8.107944570945487e-06, "epoch": 15.250825082508252, "percentage": 76.25, "elapsed_time": "5:28:24", "remaining_time": "1:42:16", "throughput": 1484.73, "total_tokens": 29256128} {"current_steps": 138635, "total_steps": 181800, "loss": 0.0404, "lr": 8.106175335626304e-06, "epoch": 15.251375137513751, "percentage": 76.26, "elapsed_time": "5:28:25", "remaining_time": "1:42:15", "throughput": 1484.73, "total_tokens": 29257152} {"current_steps": 138640, "total_steps": 181800, "loss": 0.0011, "lr": 8.10440625600941e-06, "epoch": 15.251925192519252, "percentage": 76.26, "elapsed_time": "5:28:26", "remaining_time": "1:42:14", "throughput": 1484.73, "total_tokens": 29258208} {"current_steps": 138645, "total_steps": 181800, "loss": 0.0021, "lr": 8.102637332111085e-06, "epoch": 15.252475247524753, "percentage": 76.26, "elapsed_time": "5:28:26", "remaining_time": "1:42:13", "throughput": 1484.74, "total_tokens": 29259264} {"current_steps": 138650, "total_steps": 181800, "loss": 0.1117, "lr": 8.100868563947645e-06, "epoch": 15.253025302530252, "percentage": 76.27, "elapsed_time": "5:28:27", "remaining_time": "1:42:13", "throughput": 1484.74, "total_tokens": 29260320} {"current_steps": 138655, "total_steps": 181800, "loss": 0.009, "lr": 8.099099951535397e-06, "epoch": 15.253575357535754, "percentage": 76.27, "elapsed_time": "5:28:28", "remaining_time": "1:42:12", "throughput": 1484.74, "total_tokens": 29261440} {"current_steps": 138660, "total_steps": 181800, "loss": 0.0093, "lr": 8.097331494890629e-06, "epoch": 15.254125412541255, "percentage": 76.27, "elapsed_time": "5:28:28", "remaining_time": "1:42:11", "throughput": 1484.75, "total_tokens": 29262560} {"current_steps": 138665, "total_steps": 181800, "loss": 0.0441, "lr": 8.09556319402965e-06, "epoch": 15.254675467546754, "percentage": 76.27, "elapsed_time": "5:28:29", "remaining_time": "1:42:11", "throughput": 1484.75, "total_tokens": 29263552} {"current_steps": 138670, "total_steps": 181800, "loss": 0.0022, "lr": 8.09379504896875e-06, "epoch": 15.255225522552255, "percentage": 76.28, "elapsed_time": "5:28:30", "remaining_time": "1:42:10", "throughput": 1484.75, "total_tokens": 29264640} {"current_steps": 138675, "total_steps": 181800, "loss": 0.0192, "lr": 8.092027059724227e-06, "epoch": 15.255775577557756, "percentage": 76.28, "elapsed_time": "5:28:30", "remaining_time": "1:42:09", "throughput": 1484.75, "total_tokens": 29265728} {"current_steps": 138680, "total_steps": 181800, "loss": 0.0223, "lr": 8.090259226312386e-06, "epoch": 15.256325632563255, "percentage": 76.28, "elapsed_time": "5:28:31", "remaining_time": "1:42:08", "throughput": 1484.75, "total_tokens": 29266720} {"current_steps": 138685, "total_steps": 181800, "loss": 0.0689, "lr": 8.088491548749503e-06, "epoch": 15.256875687568757, "percentage": 76.28, "elapsed_time": "5:28:32", "remaining_time": "1:42:08", "throughput": 1484.75, "total_tokens": 29267776} {"current_steps": 138690, "total_steps": 181800, "loss": 0.0658, "lr": 8.086724027051887e-06, "epoch": 15.257425742574258, "percentage": 76.29, "elapsed_time": "5:28:32", "remaining_time": "1:42:07", "throughput": 1484.75, "total_tokens": 29268832} {"current_steps": 138695, "total_steps": 181800, "loss": 0.0015, "lr": 8.084956661235809e-06, "epoch": 15.257975797579759, "percentage": 76.29, "elapsed_time": "5:28:33", "remaining_time": "1:42:06", "throughput": 1484.76, "total_tokens": 29269952} {"current_steps": 138700, "total_steps": 181800, "loss": 0.0024, "lr": 8.08318945131758e-06, "epoch": 15.258525852585258, "percentage": 76.29, "elapsed_time": "5:28:34", "remaining_time": "1:42:06", "throughput": 1484.76, "total_tokens": 29271008} {"current_steps": 138705, "total_steps": 181800, "loss": 0.0992, "lr": 8.081422397313467e-06, "epoch": 15.25907590759076, "percentage": 76.3, "elapsed_time": "5:28:34", "remaining_time": "1:42:05", "throughput": 1484.76, "total_tokens": 29272032} {"current_steps": 138710, "total_steps": 181800, "loss": 0.0156, "lr": 8.079655499239766e-06, "epoch": 15.25962596259626, "percentage": 76.3, "elapsed_time": "5:28:35", "remaining_time": "1:42:04", "throughput": 1484.76, "total_tokens": 29273120} {"current_steps": 138715, "total_steps": 181800, "loss": 0.001, "lr": 8.07788875711277e-06, "epoch": 15.26017601760176, "percentage": 76.3, "elapsed_time": "5:28:36", "remaining_time": "1:42:03", "throughput": 1484.76, "total_tokens": 29274144} {"current_steps": 138720, "total_steps": 181800, "loss": 0.0171, "lr": 8.076122170948744e-06, "epoch": 15.26072607260726, "percentage": 76.3, "elapsed_time": "5:28:37", "remaining_time": "1:42:03", "throughput": 1484.77, "total_tokens": 29275232} {"current_steps": 138725, "total_steps": 181800, "loss": 0.0146, "lr": 8.074355740763986e-06, "epoch": 15.261276127612762, "percentage": 76.31, "elapsed_time": "5:28:37", "remaining_time": "1:42:02", "throughput": 1484.77, "total_tokens": 29276288} {"current_steps": 138730, "total_steps": 181800, "loss": 0.0013, "lr": 8.072589466574764e-06, "epoch": 15.261826182618261, "percentage": 76.31, "elapsed_time": "5:28:38", "remaining_time": "1:42:01", "throughput": 1484.77, "total_tokens": 29277344} {"current_steps": 138735, "total_steps": 181800, "loss": 0.0026, "lr": 8.07082334839736e-06, "epoch": 15.262376237623762, "percentage": 76.31, "elapsed_time": "5:28:39", "remaining_time": "1:42:01", "throughput": 1484.77, "total_tokens": 29278400} {"current_steps": 138740, "total_steps": 181800, "loss": 0.0036, "lr": 8.069057386248064e-06, "epoch": 15.262926292629263, "percentage": 76.31, "elapsed_time": "5:28:39", "remaining_time": "1:42:00", "throughput": 1484.78, "total_tokens": 29279456} {"current_steps": 138745, "total_steps": 181800, "loss": 0.0043, "lr": 8.067291580143132e-06, "epoch": 15.263476347634764, "percentage": 76.32, "elapsed_time": "5:28:40", "remaining_time": "1:41:59", "throughput": 1484.77, "total_tokens": 29280448} {"current_steps": 138750, "total_steps": 181800, "loss": 0.0337, "lr": 8.065525930098857e-06, "epoch": 15.264026402640264, "percentage": 76.32, "elapsed_time": "5:28:41", "remaining_time": "1:41:58", "throughput": 1484.77, "total_tokens": 29281440} {"current_steps": 138755, "total_steps": 181800, "loss": 0.0732, "lr": 8.063760436131504e-06, "epoch": 15.264576457645765, "percentage": 76.32, "elapsed_time": "5:28:41", "remaining_time": "1:41:58", "throughput": 1484.77, "total_tokens": 29282432} {"current_steps": 138760, "total_steps": 181800, "loss": 0.0034, "lr": 8.061995098257336e-06, "epoch": 15.265126512651266, "percentage": 76.33, "elapsed_time": "5:28:42", "remaining_time": "1:41:57", "throughput": 1484.77, "total_tokens": 29283488} {"current_steps": 138765, "total_steps": 181800, "loss": 0.0248, "lr": 8.060229916492631e-06, "epoch": 15.265676567656765, "percentage": 76.33, "elapsed_time": "5:28:43", "remaining_time": "1:41:56", "throughput": 1484.77, "total_tokens": 29284544} {"current_steps": 138770, "total_steps": 181800, "loss": 0.0006, "lr": 8.058464890853659e-06, "epoch": 15.266226622662266, "percentage": 76.33, "elapsed_time": "5:28:43", "remaining_time": "1:41:56", "throughput": 1484.78, "total_tokens": 29285632} {"current_steps": 138775, "total_steps": 181800, "loss": 0.0024, "lr": 8.056700021356694e-06, "epoch": 15.266776677667767, "percentage": 76.33, "elapsed_time": "5:28:44", "remaining_time": "1:41:55", "throughput": 1484.78, "total_tokens": 29286688} {"current_steps": 138780, "total_steps": 181800, "loss": 0.0027, "lr": 8.054935308017997e-06, "epoch": 15.267326732673267, "percentage": 76.34, "elapsed_time": "5:28:45", "remaining_time": "1:41:54", "throughput": 1484.78, "total_tokens": 29287776} {"current_steps": 138785, "total_steps": 181800, "loss": 0.0571, "lr": 8.053170750853819e-06, "epoch": 15.267876787678768, "percentage": 76.34, "elapsed_time": "5:28:45", "remaining_time": "1:41:53", "throughput": 1484.79, "total_tokens": 29288864} {"current_steps": 138790, "total_steps": 181800, "loss": 0.0018, "lr": 8.051406349880435e-06, "epoch": 15.268426842684269, "percentage": 76.34, "elapsed_time": "5:28:46", "remaining_time": "1:41:53", "throughput": 1484.79, "total_tokens": 29289984} {"current_steps": 138795, "total_steps": 181800, "loss": 0.1005, "lr": 8.049642105114117e-06, "epoch": 15.268976897689768, "percentage": 76.34, "elapsed_time": "5:28:47", "remaining_time": "1:41:52", "throughput": 1484.79, "total_tokens": 29290976} {"current_steps": 138800, "total_steps": 181800, "loss": 0.0713, "lr": 8.047878016571103e-06, "epoch": 15.26952695269527, "percentage": 76.35, "elapsed_time": "5:28:48", "remaining_time": "1:41:51", "throughput": 1484.79, "total_tokens": 29292064} {"current_steps": 138805, "total_steps": 181800, "loss": 0.0005, "lr": 8.046114084267673e-06, "epoch": 15.27007700770077, "percentage": 76.35, "elapsed_time": "5:28:48", "remaining_time": "1:41:50", "throughput": 1484.8, "total_tokens": 29293184} {"current_steps": 138810, "total_steps": 181800, "loss": 0.001, "lr": 8.044350308220064e-06, "epoch": 15.270627062706271, "percentage": 76.35, "elapsed_time": "5:28:49", "remaining_time": "1:41:50", "throughput": 1484.8, "total_tokens": 29294208} {"current_steps": 138815, "total_steps": 181800, "loss": 0.0224, "lr": 8.04258668844455e-06, "epoch": 15.27117711771177, "percentage": 76.36, "elapsed_time": "5:28:50", "remaining_time": "1:41:49", "throughput": 1484.8, "total_tokens": 29295264} {"current_steps": 138820, "total_steps": 181800, "loss": 0.0786, "lr": 8.040823224957372e-06, "epoch": 15.271727172717272, "percentage": 76.36, "elapsed_time": "5:28:50", "remaining_time": "1:41:48", "throughput": 1484.8, "total_tokens": 29296352} {"current_steps": 138825, "total_steps": 181800, "loss": 0.0065, "lr": 8.039059917774788e-06, "epoch": 15.272277227722773, "percentage": 76.36, "elapsed_time": "5:28:51", "remaining_time": "1:41:48", "throughput": 1484.81, "total_tokens": 29297440} {"current_steps": 138830, "total_steps": 181800, "loss": 0.1446, "lr": 8.037296766913057e-06, "epoch": 15.272827282728272, "percentage": 76.36, "elapsed_time": "5:28:52", "remaining_time": "1:41:47", "throughput": 1484.81, "total_tokens": 29298528} {"current_steps": 138835, "total_steps": 181800, "loss": 0.0892, "lr": 8.035533772388414e-06, "epoch": 15.273377337733773, "percentage": 76.37, "elapsed_time": "5:28:52", "remaining_time": "1:41:46", "throughput": 1484.81, "total_tokens": 29299616} {"current_steps": 138840, "total_steps": 181800, "loss": 0.0248, "lr": 8.033770934217124e-06, "epoch": 15.273927392739274, "percentage": 76.37, "elapsed_time": "5:28:53", "remaining_time": "1:41:45", "throughput": 1484.82, "total_tokens": 29300704} {"current_steps": 138845, "total_steps": 181800, "loss": 0.0164, "lr": 8.032008252415419e-06, "epoch": 15.274477447744774, "percentage": 76.37, "elapsed_time": "5:28:54", "remaining_time": "1:41:45", "throughput": 1484.82, "total_tokens": 29301792} {"current_steps": 138850, "total_steps": 181800, "loss": 0.0371, "lr": 8.030245726999552e-06, "epoch": 15.275027502750275, "percentage": 76.38, "elapsed_time": "5:28:54", "remaining_time": "1:41:44", "throughput": 1484.82, "total_tokens": 29302784} {"current_steps": 138855, "total_steps": 181800, "loss": 0.0257, "lr": 8.028483357985774e-06, "epoch": 15.275577557755776, "percentage": 76.38, "elapsed_time": "5:28:55", "remaining_time": "1:41:43", "throughput": 1484.82, "total_tokens": 29303904} {"current_steps": 138860, "total_steps": 181800, "loss": 0.1612, "lr": 8.026721145390315e-06, "epoch": 15.276127612761275, "percentage": 76.38, "elapsed_time": "5:28:56", "remaining_time": "1:41:43", "throughput": 1484.82, "total_tokens": 29304992} {"current_steps": 138865, "total_steps": 181800, "loss": 0.1929, "lr": 8.024959089229429e-06, "epoch": 15.276677667766776, "percentage": 76.38, "elapsed_time": "5:28:57", "remaining_time": "1:41:42", "throughput": 1484.82, "total_tokens": 29305984} {"current_steps": 138870, "total_steps": 181800, "loss": 0.0159, "lr": 8.02319718951935e-06, "epoch": 15.277227722772277, "percentage": 76.39, "elapsed_time": "5:28:57", "remaining_time": "1:41:41", "throughput": 1484.83, "total_tokens": 29307072} {"current_steps": 138875, "total_steps": 181800, "loss": 0.0023, "lr": 8.021435446276306e-06, "epoch": 15.277777777777779, "percentage": 76.39, "elapsed_time": "5:28:58", "remaining_time": "1:41:40", "throughput": 1484.82, "total_tokens": 29308032} {"current_steps": 138880, "total_steps": 181800, "loss": 0.0019, "lr": 8.01967385951655e-06, "epoch": 15.278327832783278, "percentage": 76.39, "elapsed_time": "5:28:59", "remaining_time": "1:41:40", "throughput": 1484.82, "total_tokens": 29309056} {"current_steps": 138885, "total_steps": 181800, "loss": 0.0542, "lr": 8.017912429256307e-06, "epoch": 15.278877887788779, "percentage": 76.39, "elapsed_time": "5:28:59", "remaining_time": "1:41:39", "throughput": 1484.83, "total_tokens": 29310144} {"current_steps": 138890, "total_steps": 181800, "loss": 0.0076, "lr": 8.016151155511826e-06, "epoch": 15.27942794279428, "percentage": 76.4, "elapsed_time": "5:29:00", "remaining_time": "1:41:38", "throughput": 1484.83, "total_tokens": 29311200} {"current_steps": 138895, "total_steps": 181800, "loss": 0.0038, "lr": 8.01439003829933e-06, "epoch": 15.27997799779978, "percentage": 76.4, "elapsed_time": "5:29:01", "remaining_time": "1:41:38", "throughput": 1484.83, "total_tokens": 29312288} {"current_steps": 138900, "total_steps": 181800, "loss": 0.0111, "lr": 8.012629077635041e-06, "epoch": 15.28052805280528, "percentage": 76.4, "elapsed_time": "5:29:01", "remaining_time": "1:41:37", "throughput": 1484.83, "total_tokens": 29313312} {"current_steps": 138905, "total_steps": 181800, "loss": 0.0008, "lr": 8.010868273535201e-06, "epoch": 15.281078107810782, "percentage": 76.41, "elapsed_time": "5:29:02", "remaining_time": "1:41:36", "throughput": 1484.83, "total_tokens": 29314336} {"current_steps": 138910, "total_steps": 181800, "loss": 0.0028, "lr": 8.009107626016037e-06, "epoch": 15.281628162816281, "percentage": 76.41, "elapsed_time": "5:29:03", "remaining_time": "1:41:35", "throughput": 1484.83, "total_tokens": 29315392} {"current_steps": 138915, "total_steps": 181800, "loss": 0.0004, "lr": 8.007347135093782e-06, "epoch": 15.282178217821782, "percentage": 76.41, "elapsed_time": "5:29:03", "remaining_time": "1:41:35", "throughput": 1484.83, "total_tokens": 29316448} {"current_steps": 138920, "total_steps": 181800, "loss": 0.2068, "lr": 8.005586800784654e-06, "epoch": 15.282728272827283, "percentage": 76.41, "elapsed_time": "5:29:04", "remaining_time": "1:41:34", "throughput": 1484.83, "total_tokens": 29317472} {"current_steps": 138925, "total_steps": 181800, "loss": 0.016, "lr": 8.003826623104869e-06, "epoch": 15.283278327832782, "percentage": 76.42, "elapsed_time": "5:29:05", "remaining_time": "1:41:33", "throughput": 1484.83, "total_tokens": 29318496} {"current_steps": 138930, "total_steps": 181800, "loss": 0.0172, "lr": 8.002066602070668e-06, "epoch": 15.283828382838283, "percentage": 76.42, "elapsed_time": "5:29:05", "remaining_time": "1:41:33", "throughput": 1484.83, "total_tokens": 29319520} {"current_steps": 138935, "total_steps": 181800, "loss": 0.0041, "lr": 8.000306737698251e-06, "epoch": 15.284378437843785, "percentage": 76.42, "elapsed_time": "5:29:06", "remaining_time": "1:41:32", "throughput": 1484.84, "total_tokens": 29320608} {"current_steps": 138940, "total_steps": 181800, "loss": 0.0044, "lr": 7.998547030003853e-06, "epoch": 15.284928492849286, "percentage": 76.42, "elapsed_time": "5:29:07", "remaining_time": "1:41:31", "throughput": 1484.84, "total_tokens": 29321632} {"current_steps": 138945, "total_steps": 181800, "loss": 0.0312, "lr": 7.996787479003698e-06, "epoch": 15.285478547854785, "percentage": 76.43, "elapsed_time": "5:29:08", "remaining_time": "1:41:30", "throughput": 1484.84, "total_tokens": 29322656} {"current_steps": 138950, "total_steps": 181800, "loss": 0.116, "lr": 7.995028084713981e-06, "epoch": 15.286028602860286, "percentage": 76.43, "elapsed_time": "5:29:08", "remaining_time": "1:41:30", "throughput": 1484.84, "total_tokens": 29323680} {"current_steps": 138955, "total_steps": 181800, "loss": 0.0321, "lr": 7.993268847150945e-06, "epoch": 15.286578657865787, "percentage": 76.43, "elapsed_time": "5:29:09", "remaining_time": "1:41:29", "throughput": 1484.84, "total_tokens": 29324736} {"current_steps": 138960, "total_steps": 181800, "loss": 0.0032, "lr": 7.991509766330776e-06, "epoch": 15.287128712871286, "percentage": 76.44, "elapsed_time": "5:29:10", "remaining_time": "1:41:28", "throughput": 1484.84, "total_tokens": 29325760} {"current_steps": 138965, "total_steps": 181800, "loss": 0.0025, "lr": 7.989750842269702e-06, "epoch": 15.287678767876788, "percentage": 76.44, "elapsed_time": "5:29:10", "remaining_time": "1:41:28", "throughput": 1484.84, "total_tokens": 29326784} {"current_steps": 138970, "total_steps": 181800, "loss": 0.0999, "lr": 7.98799207498394e-06, "epoch": 15.288228822882289, "percentage": 76.44, "elapsed_time": "5:29:11", "remaining_time": "1:41:27", "throughput": 1484.84, "total_tokens": 29327840} {"current_steps": 138975, "total_steps": 181800, "loss": 0.0012, "lr": 7.986233464489683e-06, "epoch": 15.288778877887788, "percentage": 76.44, "elapsed_time": "5:29:12", "remaining_time": "1:41:26", "throughput": 1484.84, "total_tokens": 29328864} {"current_steps": 138980, "total_steps": 181800, "loss": 0.0055, "lr": 7.984475010803158e-06, "epoch": 15.289328932893289, "percentage": 76.45, "elapsed_time": "5:29:12", "remaining_time": "1:41:25", "throughput": 1484.84, "total_tokens": 29329920} {"current_steps": 138985, "total_steps": 181800, "loss": 0.0064, "lr": 7.982716713940552e-06, "epoch": 15.28987898789879, "percentage": 76.45, "elapsed_time": "5:29:13", "remaining_time": "1:41:25", "throughput": 1484.84, "total_tokens": 29331008} {"current_steps": 138990, "total_steps": 181800, "loss": 0.0277, "lr": 7.98095857391809e-06, "epoch": 15.290429042904291, "percentage": 76.45, "elapsed_time": "5:29:14", "remaining_time": "1:41:24", "throughput": 1484.85, "total_tokens": 29332128} {"current_steps": 138995, "total_steps": 181800, "loss": 0.0014, "lr": 7.97920059075196e-06, "epoch": 15.29097909790979, "percentage": 76.45, "elapsed_time": "5:29:14", "remaining_time": "1:41:23", "throughput": 1484.85, "total_tokens": 29333184} {"current_steps": 139000, "total_steps": 181800, "loss": 0.0143, "lr": 7.977442764458367e-06, "epoch": 15.291529152915292, "percentage": 76.46, "elapsed_time": "5:29:15", "remaining_time": "1:41:23", "throughput": 1484.85, "total_tokens": 29334208} {"current_steps": 139005, "total_steps": 181800, "loss": 0.0033, "lr": 7.975685095053525e-06, "epoch": 15.292079207920793, "percentage": 76.46, "elapsed_time": "5:29:16", "remaining_time": "1:41:22", "throughput": 1484.85, "total_tokens": 29335200} {"current_steps": 139010, "total_steps": 181800, "loss": 0.0097, "lr": 7.973927582553625e-06, "epoch": 15.292629262926292, "percentage": 76.46, "elapsed_time": "5:29:17", "remaining_time": "1:41:21", "throughput": 1484.85, "total_tokens": 29336256} {"current_steps": 139015, "total_steps": 181800, "loss": 0.0025, "lr": 7.972170226974856e-06, "epoch": 15.293179317931793, "percentage": 76.47, "elapsed_time": "5:29:17", "remaining_time": "1:41:20", "throughput": 1484.85, "total_tokens": 29337280} {"current_steps": 139020, "total_steps": 181800, "loss": 0.003, "lr": 7.970413028333423e-06, "epoch": 15.293729372937294, "percentage": 76.47, "elapsed_time": "5:29:18", "remaining_time": "1:41:20", "throughput": 1484.85, "total_tokens": 29338272} {"current_steps": 139025, "total_steps": 181800, "loss": 0.0015, "lr": 7.968655986645523e-06, "epoch": 15.294279427942794, "percentage": 76.47, "elapsed_time": "5:29:19", "remaining_time": "1:41:19", "throughput": 1484.85, "total_tokens": 29339264} {"current_steps": 139030, "total_steps": 181800, "loss": 0.0945, "lr": 7.966899101927356e-06, "epoch": 15.294829482948295, "percentage": 76.47, "elapsed_time": "5:29:19", "remaining_time": "1:41:18", "throughput": 1484.85, "total_tokens": 29340320} {"current_steps": 139035, "total_steps": 181800, "loss": 0.0014, "lr": 7.965142374195106e-06, "epoch": 15.295379537953796, "percentage": 76.48, "elapsed_time": "5:29:20", "remaining_time": "1:41:18", "throughput": 1484.85, "total_tokens": 29341376} {"current_steps": 139040, "total_steps": 181800, "loss": 0.0016, "lr": 7.963385803464957e-06, "epoch": 15.295929592959295, "percentage": 76.48, "elapsed_time": "5:29:21", "remaining_time": "1:41:17", "throughput": 1484.85, "total_tokens": 29342464} {"current_steps": 139045, "total_steps": 181800, "loss": 0.004, "lr": 7.961629389753115e-06, "epoch": 15.296479647964796, "percentage": 76.48, "elapsed_time": "5:29:21", "remaining_time": "1:41:16", "throughput": 1484.86, "total_tokens": 29343552} {"current_steps": 139050, "total_steps": 181800, "loss": 0.0053, "lr": 7.959873133075748e-06, "epoch": 15.297029702970297, "percentage": 76.49, "elapsed_time": "5:29:22", "remaining_time": "1:41:15", "throughput": 1484.86, "total_tokens": 29344576} {"current_steps": 139055, "total_steps": 181800, "loss": 0.1884, "lr": 7.958117033449056e-06, "epoch": 15.297579757975798, "percentage": 76.49, "elapsed_time": "5:29:23", "remaining_time": "1:41:15", "throughput": 1484.86, "total_tokens": 29345600} {"current_steps": 139060, "total_steps": 181800, "loss": 0.0904, "lr": 7.956361090889231e-06, "epoch": 15.298129812981298, "percentage": 76.49, "elapsed_time": "5:29:23", "remaining_time": "1:41:14", "throughput": 1484.86, "total_tokens": 29346592} {"current_steps": 139065, "total_steps": 181800, "loss": 0.0261, "lr": 7.954605305412437e-06, "epoch": 15.298679867986799, "percentage": 76.49, "elapsed_time": "5:29:24", "remaining_time": "1:41:13", "throughput": 1484.86, "total_tokens": 29347680} {"current_steps": 139070, "total_steps": 181800, "loss": 0.1249, "lr": 7.952849677034877e-06, "epoch": 15.2992299229923, "percentage": 76.5, "elapsed_time": "5:29:25", "remaining_time": "1:41:12", "throughput": 1484.86, "total_tokens": 29348800} {"current_steps": 139075, "total_steps": 181800, "loss": 0.0474, "lr": 7.95109420577271e-06, "epoch": 15.2997799779978, "percentage": 76.5, "elapsed_time": "5:29:26", "remaining_time": "1:41:12", "throughput": 1484.86, "total_tokens": 29349824} {"current_steps": 139080, "total_steps": 181800, "loss": 0.0161, "lr": 7.94933889164213e-06, "epoch": 15.3003300330033, "percentage": 76.5, "elapsed_time": "5:29:26", "remaining_time": "1:41:11", "throughput": 1484.87, "total_tokens": 29350912} {"current_steps": 139085, "total_steps": 181800, "loss": 0.001, "lr": 7.947583734659319e-06, "epoch": 15.300880088008801, "percentage": 76.5, "elapsed_time": "5:29:27", "remaining_time": "1:41:10", "throughput": 1484.87, "total_tokens": 29351936} {"current_steps": 139090, "total_steps": 181800, "loss": 0.0093, "lr": 7.945828734840438e-06, "epoch": 15.3014301430143, "percentage": 76.51, "elapsed_time": "5:29:28", "remaining_time": "1:41:10", "throughput": 1484.87, "total_tokens": 29352992} {"current_steps": 139095, "total_steps": 181800, "loss": 0.0338, "lr": 7.944073892201679e-06, "epoch": 15.301980198019802, "percentage": 76.51, "elapsed_time": "5:29:28", "remaining_time": "1:41:09", "throughput": 1484.87, "total_tokens": 29354016} {"current_steps": 139100, "total_steps": 181800, "loss": 0.0011, "lr": 7.942319206759196e-06, "epoch": 15.302530253025303, "percentage": 76.51, "elapsed_time": "5:29:29", "remaining_time": "1:41:08", "throughput": 1484.87, "total_tokens": 29355072} {"current_steps": 139105, "total_steps": 181800, "loss": 0.0332, "lr": 7.940564678529183e-06, "epoch": 15.303080308030804, "percentage": 76.52, "elapsed_time": "5:29:30", "remaining_time": "1:41:07", "throughput": 1484.87, "total_tokens": 29356160} {"current_steps": 139110, "total_steps": 181800, "loss": 0.0461, "lr": 7.938810307527788e-06, "epoch": 15.303630363036303, "percentage": 76.52, "elapsed_time": "5:29:30", "remaining_time": "1:41:07", "throughput": 1484.87, "total_tokens": 29357120} {"current_steps": 139115, "total_steps": 181800, "loss": 0.0171, "lr": 7.937056093771194e-06, "epoch": 15.304180418041804, "percentage": 76.52, "elapsed_time": "5:29:31", "remaining_time": "1:41:06", "throughput": 1484.87, "total_tokens": 29358144} {"current_steps": 139120, "total_steps": 181800, "loss": 0.0073, "lr": 7.935302037275574e-06, "epoch": 15.304730473047305, "percentage": 76.52, "elapsed_time": "5:29:32", "remaining_time": "1:41:05", "throughput": 1484.88, "total_tokens": 29359296} {"current_steps": 139125, "total_steps": 181800, "loss": 0.0174, "lr": 7.933548138057081e-06, "epoch": 15.305280528052805, "percentage": 76.53, "elapsed_time": "5:29:32", "remaining_time": "1:41:05", "throughput": 1484.88, "total_tokens": 29360352} {"current_steps": 139130, "total_steps": 181800, "loss": 0.0831, "lr": 7.931794396131891e-06, "epoch": 15.305830583058306, "percentage": 76.53, "elapsed_time": "5:29:33", "remaining_time": "1:41:04", "throughput": 1484.88, "total_tokens": 29361344} {"current_steps": 139135, "total_steps": 181800, "loss": 0.0129, "lr": 7.930040811516154e-06, "epoch": 15.306380638063807, "percentage": 76.53, "elapsed_time": "5:29:34", "remaining_time": "1:41:03", "throughput": 1484.88, "total_tokens": 29362464} {"current_steps": 139140, "total_steps": 181800, "loss": 0.0054, "lr": 7.92828738422604e-06, "epoch": 15.306930693069306, "percentage": 76.53, "elapsed_time": "5:29:34", "remaining_time": "1:41:02", "throughput": 1484.88, "total_tokens": 29363520} {"current_steps": 139145, "total_steps": 181800, "loss": 0.0007, "lr": 7.926534114277717e-06, "epoch": 15.307480748074807, "percentage": 76.54, "elapsed_time": "5:29:35", "remaining_time": "1:41:02", "throughput": 1484.88, "total_tokens": 29364544} {"current_steps": 139150, "total_steps": 181800, "loss": 0.0052, "lr": 7.924781001687329e-06, "epoch": 15.308030803080309, "percentage": 76.54, "elapsed_time": "5:29:36", "remaining_time": "1:41:01", "throughput": 1484.89, "total_tokens": 29365664} {"current_steps": 139155, "total_steps": 181800, "loss": 0.028, "lr": 7.923028046471052e-06, "epoch": 15.308580858085808, "percentage": 76.54, "elapsed_time": "5:29:37", "remaining_time": "1:41:00", "throughput": 1484.89, "total_tokens": 29366752} {"current_steps": 139160, "total_steps": 181800, "loss": 0.005, "lr": 7.921275248645027e-06, "epoch": 15.309130913091309, "percentage": 76.55, "elapsed_time": "5:29:37", "remaining_time": "1:41:00", "throughput": 1484.89, "total_tokens": 29367776} {"current_steps": 139165, "total_steps": 181800, "loss": 0.0025, "lr": 7.919522608225406e-06, "epoch": 15.30968096809681, "percentage": 76.55, "elapsed_time": "5:29:38", "remaining_time": "1:40:59", "throughput": 1484.89, "total_tokens": 29368864} {"current_steps": 139170, "total_steps": 181800, "loss": 0.0151, "lr": 7.917770125228346e-06, "epoch": 15.310231023102311, "percentage": 76.55, "elapsed_time": "5:29:39", "remaining_time": "1:40:58", "throughput": 1484.89, "total_tokens": 29369920} {"current_steps": 139175, "total_steps": 181800, "loss": 0.0224, "lr": 7.916017799670006e-06, "epoch": 15.31078107810781, "percentage": 76.55, "elapsed_time": "5:29:39", "remaining_time": "1:40:57", "throughput": 1484.9, "total_tokens": 29370976} {"current_steps": 139180, "total_steps": 181800, "loss": 0.0142, "lr": 7.91426563156654e-06, "epoch": 15.311331133113312, "percentage": 76.56, "elapsed_time": "5:29:40", "remaining_time": "1:40:57", "throughput": 1484.9, "total_tokens": 29372000} {"current_steps": 139185, "total_steps": 181800, "loss": 0.0066, "lr": 7.91251362093409e-06, "epoch": 15.311881188118813, "percentage": 76.56, "elapsed_time": "5:29:41", "remaining_time": "1:40:56", "throughput": 1484.9, "total_tokens": 29373024} {"current_steps": 139190, "total_steps": 181800, "loss": 0.0819, "lr": 7.91076176778879e-06, "epoch": 15.312431243124312, "percentage": 76.56, "elapsed_time": "5:29:41", "remaining_time": "1:40:55", "throughput": 1484.89, "total_tokens": 29374016} {"current_steps": 139195, "total_steps": 181800, "loss": 0.026, "lr": 7.909010072146803e-06, "epoch": 15.312981298129813, "percentage": 76.56, "elapsed_time": "5:29:42", "remaining_time": "1:40:55", "throughput": 1484.89, "total_tokens": 29375040} {"current_steps": 139200, "total_steps": 181800, "loss": 0.0011, "lr": 7.907258534024276e-06, "epoch": 15.313531353135314, "percentage": 76.57, "elapsed_time": "5:29:43", "remaining_time": "1:40:54", "throughput": 1484.9, "total_tokens": 29376096} {"current_steps": 139205, "total_steps": 181800, "loss": 0.0423, "lr": 7.905507153437337e-06, "epoch": 15.314081408140813, "percentage": 76.57, "elapsed_time": "5:29:43", "remaining_time": "1:40:53", "throughput": 1484.9, "total_tokens": 29377152} {"current_steps": 139210, "total_steps": 181800, "loss": 0.0528, "lr": 7.903755930402144e-06, "epoch": 15.314631463146315, "percentage": 76.57, "elapsed_time": "5:29:44", "remaining_time": "1:40:52", "throughput": 1484.89, "total_tokens": 29378112} {"current_steps": 139215, "total_steps": 181800, "loss": 0.0044, "lr": 7.90200486493482e-06, "epoch": 15.315181518151816, "percentage": 76.58, "elapsed_time": "5:29:45", "remaining_time": "1:40:52", "throughput": 1484.89, "total_tokens": 29379136} {"current_steps": 139220, "total_steps": 181800, "loss": 0.0407, "lr": 7.90025395705152e-06, "epoch": 15.315731573157315, "percentage": 76.58, "elapsed_time": "5:29:46", "remaining_time": "1:40:51", "throughput": 1484.89, "total_tokens": 29380160} {"current_steps": 139225, "total_steps": 181800, "loss": 0.0303, "lr": 7.898503206768368e-06, "epoch": 15.316281628162816, "percentage": 76.58, "elapsed_time": "5:29:46", "remaining_time": "1:40:50", "throughput": 1484.9, "total_tokens": 29381216} {"current_steps": 139230, "total_steps": 181800, "loss": 0.0025, "lr": 7.896752614101508e-06, "epoch": 15.316831683168317, "percentage": 76.58, "elapsed_time": "5:29:47", "remaining_time": "1:40:50", "throughput": 1484.9, "total_tokens": 29382240} {"current_steps": 139235, "total_steps": 181800, "loss": 0.0006, "lr": 7.895002179067077e-06, "epoch": 15.317381738173818, "percentage": 76.59, "elapsed_time": "5:29:48", "remaining_time": "1:40:49", "throughput": 1484.9, "total_tokens": 29383296} {"current_steps": 139240, "total_steps": 181800, "loss": 0.0216, "lr": 7.893251901681194e-06, "epoch": 15.317931793179318, "percentage": 76.59, "elapsed_time": "5:29:48", "remaining_time": "1:40:48", "throughput": 1484.9, "total_tokens": 29384384} {"current_steps": 139245, "total_steps": 181800, "loss": 0.0076, "lr": 7.891501781960009e-06, "epoch": 15.318481848184819, "percentage": 76.59, "elapsed_time": "5:29:49", "remaining_time": "1:40:47", "throughput": 1484.9, "total_tokens": 29385472} {"current_steps": 139250, "total_steps": 181800, "loss": 0.006, "lr": 7.889751819919644e-06, "epoch": 15.31903190319032, "percentage": 76.6, "elapsed_time": "5:29:50", "remaining_time": "1:40:47", "throughput": 1484.91, "total_tokens": 29386528} {"current_steps": 139255, "total_steps": 181800, "loss": 0.0564, "lr": 7.88800201557621e-06, "epoch": 15.319581958195819, "percentage": 76.6, "elapsed_time": "5:29:50", "remaining_time": "1:40:46", "throughput": 1484.91, "total_tokens": 29387584} {"current_steps": 139260, "total_steps": 181800, "loss": 0.0058, "lr": 7.886252368945866e-06, "epoch": 15.32013201320132, "percentage": 76.6, "elapsed_time": "5:29:51", "remaining_time": "1:40:45", "throughput": 1484.91, "total_tokens": 29388640} {"current_steps": 139265, "total_steps": 181800, "loss": 0.0427, "lr": 7.88450288004471e-06, "epoch": 15.320682068206821, "percentage": 76.6, "elapsed_time": "5:29:52", "remaining_time": "1:40:45", "throughput": 1484.91, "total_tokens": 29389728} {"current_steps": 139270, "total_steps": 181800, "loss": 0.0339, "lr": 7.882753548888891e-06, "epoch": 15.32123212321232, "percentage": 76.61, "elapsed_time": "5:29:52", "remaining_time": "1:40:44", "throughput": 1484.92, "total_tokens": 29390848} {"current_steps": 139275, "total_steps": 181800, "loss": 0.0024, "lr": 7.881004375494516e-06, "epoch": 15.321782178217822, "percentage": 76.61, "elapsed_time": "5:29:53", "remaining_time": "1:40:43", "throughput": 1484.92, "total_tokens": 29391904} {"current_steps": 139280, "total_steps": 181800, "loss": 0.0039, "lr": 7.879255359877705e-06, "epoch": 15.322332233223323, "percentage": 76.61, "elapsed_time": "5:29:54", "remaining_time": "1:40:42", "throughput": 1484.92, "total_tokens": 29392928} {"current_steps": 139285, "total_steps": 181800, "loss": 0.0058, "lr": 7.877506502054576e-06, "epoch": 15.322882288228822, "percentage": 76.61, "elapsed_time": "5:29:54", "remaining_time": "1:40:42", "throughput": 1484.92, "total_tokens": 29393952} {"current_steps": 139290, "total_steps": 181800, "loss": 0.0004, "lr": 7.875757802041258e-06, "epoch": 15.323432343234323, "percentage": 76.62, "elapsed_time": "5:29:55", "remaining_time": "1:40:41", "throughput": 1484.92, "total_tokens": 29394944} {"current_steps": 139295, "total_steps": 181800, "loss": 0.014, "lr": 7.874009259853871e-06, "epoch": 15.323982398239824, "percentage": 76.62, "elapsed_time": "5:29:56", "remaining_time": "1:40:40", "throughput": 1484.92, "total_tokens": 29396000} {"current_steps": 139300, "total_steps": 181800, "loss": 0.0035, "lr": 7.872260875508523e-06, "epoch": 15.324532453245325, "percentage": 76.62, "elapsed_time": "5:29:57", "remaining_time": "1:40:40", "throughput": 1484.92, "total_tokens": 29397024} {"current_steps": 139305, "total_steps": 181800, "loss": 0.0313, "lr": 7.87051264902132e-06, "epoch": 15.325082508250825, "percentage": 76.63, "elapsed_time": "5:29:57", "remaining_time": "1:40:39", "throughput": 1484.92, "total_tokens": 29398080} {"current_steps": 139310, "total_steps": 181800, "loss": 0.0285, "lr": 7.868764580408388e-06, "epoch": 15.325632563256326, "percentage": 76.63, "elapsed_time": "5:29:58", "remaining_time": "1:40:38", "throughput": 1484.93, "total_tokens": 29399168} {"current_steps": 139315, "total_steps": 181800, "loss": 0.0449, "lr": 7.867016669685817e-06, "epoch": 15.326182618261827, "percentage": 76.63, "elapsed_time": "5:29:59", "remaining_time": "1:40:37", "throughput": 1484.93, "total_tokens": 29400224} {"current_steps": 139320, "total_steps": 181800, "loss": 0.0016, "lr": 7.86526891686975e-06, "epoch": 15.326732673267326, "percentage": 76.63, "elapsed_time": "5:29:59", "remaining_time": "1:40:37", "throughput": 1484.93, "total_tokens": 29401344} {"current_steps": 139325, "total_steps": 181800, "loss": 0.0125, "lr": 7.863521321976276e-06, "epoch": 15.327282728272827, "percentage": 76.64, "elapsed_time": "5:30:00", "remaining_time": "1:40:36", "throughput": 1484.94, "total_tokens": 29402432} {"current_steps": 139330, "total_steps": 181800, "loss": 0.0193, "lr": 7.861773885021495e-06, "epoch": 15.327832783278328, "percentage": 76.64, "elapsed_time": "5:30:01", "remaining_time": "1:40:35", "throughput": 1484.94, "total_tokens": 29403520} {"current_steps": 139335, "total_steps": 181800, "loss": 0.0075, "lr": 7.860026606021528e-06, "epoch": 15.328382838283828, "percentage": 76.64, "elapsed_time": "5:30:01", "remaining_time": "1:40:34", "throughput": 1484.94, "total_tokens": 29404576} {"current_steps": 139340, "total_steps": 181800, "loss": 0.0055, "lr": 7.858279484992465e-06, "epoch": 15.328932893289329, "percentage": 76.64, "elapsed_time": "5:30:02", "remaining_time": "1:40:34", "throughput": 1484.94, "total_tokens": 29405664} {"current_steps": 139345, "total_steps": 181800, "loss": 0.0049, "lr": 7.856532521950414e-06, "epoch": 15.32948294829483, "percentage": 76.65, "elapsed_time": "5:30:03", "remaining_time": "1:40:33", "throughput": 1484.94, "total_tokens": 29406688} {"current_steps": 139350, "total_steps": 181800, "loss": 0.0012, "lr": 7.854785716911484e-06, "epoch": 15.33003300330033, "percentage": 76.65, "elapsed_time": "5:30:03", "remaining_time": "1:40:32", "throughput": 1484.95, "total_tokens": 29407808} {"current_steps": 139355, "total_steps": 181800, "loss": 0.1086, "lr": 7.853039069891757e-06, "epoch": 15.33058305830583, "percentage": 76.65, "elapsed_time": "5:30:04", "remaining_time": "1:40:32", "throughput": 1484.95, "total_tokens": 29408896} {"current_steps": 139360, "total_steps": 181800, "loss": 0.0739, "lr": 7.851292580907352e-06, "epoch": 15.331133113311331, "percentage": 76.66, "elapsed_time": "5:30:05", "remaining_time": "1:40:31", "throughput": 1484.95, "total_tokens": 29409952} {"current_steps": 139365, "total_steps": 181800, "loss": 0.0068, "lr": 7.849546249974347e-06, "epoch": 15.331683168316832, "percentage": 76.66, "elapsed_time": "5:30:05", "remaining_time": "1:40:30", "throughput": 1484.96, "total_tokens": 29411008} {"current_steps": 139370, "total_steps": 181800, "loss": 0.0437, "lr": 7.84780007710885e-06, "epoch": 15.332233223322332, "percentage": 76.66, "elapsed_time": "5:30:06", "remaining_time": "1:40:29", "throughput": 1484.96, "total_tokens": 29412064} {"current_steps": 139375, "total_steps": 181800, "loss": 0.0542, "lr": 7.846054062326944e-06, "epoch": 15.332783278327833, "percentage": 76.66, "elapsed_time": "5:30:07", "remaining_time": "1:40:29", "throughput": 1484.96, "total_tokens": 29413120} {"current_steps": 139380, "total_steps": 181800, "loss": 0.1059, "lr": 7.844308205644723e-06, "epoch": 15.333333333333334, "percentage": 76.67, "elapsed_time": "5:30:08", "remaining_time": "1:40:28", "throughput": 1484.96, "total_tokens": 29414176} {"current_steps": 139385, "total_steps": 181800, "loss": 0.0089, "lr": 7.842562507078291e-06, "epoch": 15.333883388338833, "percentage": 76.67, "elapsed_time": "5:30:08", "remaining_time": "1:40:27", "throughput": 1484.96, "total_tokens": 29415232} {"current_steps": 139390, "total_steps": 181800, "loss": 0.0868, "lr": 7.840816966643727e-06, "epoch": 15.334433443344334, "percentage": 76.67, "elapsed_time": "5:30:09", "remaining_time": "1:40:27", "throughput": 1484.96, "total_tokens": 29416256} {"current_steps": 139395, "total_steps": 181800, "loss": 0.0279, "lr": 7.839071584357114e-06, "epoch": 15.334983498349835, "percentage": 76.67, "elapsed_time": "5:30:10", "remaining_time": "1:40:26", "throughput": 1484.96, "total_tokens": 29417312} {"current_steps": 139400, "total_steps": 181800, "loss": 0.1084, "lr": 7.83732636023454e-06, "epoch": 15.335533553355335, "percentage": 76.68, "elapsed_time": "5:30:10", "remaining_time": "1:40:25", "throughput": 1484.97, "total_tokens": 29418400} {"current_steps": 139405, "total_steps": 181800, "loss": 0.005, "lr": 7.835581294292093e-06, "epoch": 15.336083608360836, "percentage": 76.68, "elapsed_time": "5:30:11", "remaining_time": "1:40:24", "throughput": 1484.97, "total_tokens": 29419392} {"current_steps": 139410, "total_steps": 181800, "loss": 0.0792, "lr": 7.833836386545867e-06, "epoch": 15.336633663366337, "percentage": 76.68, "elapsed_time": "5:30:12", "remaining_time": "1:40:24", "throughput": 1484.96, "total_tokens": 29420384} {"current_steps": 139415, "total_steps": 181800, "loss": 0.065, "lr": 7.832091637011934e-06, "epoch": 15.337183718371838, "percentage": 76.69, "elapsed_time": "5:30:12", "remaining_time": "1:40:23", "throughput": 1484.96, "total_tokens": 29421376} {"current_steps": 139420, "total_steps": 181800, "loss": 0.0227, "lr": 7.830347045706368e-06, "epoch": 15.337733773377337, "percentage": 76.69, "elapsed_time": "5:30:13", "remaining_time": "1:40:22", "throughput": 1484.96, "total_tokens": 29422432} {"current_steps": 139425, "total_steps": 181800, "loss": 0.0899, "lr": 7.828602612645258e-06, "epoch": 15.338283828382838, "percentage": 76.69, "elapsed_time": "5:30:14", "remaining_time": "1:40:22", "throughput": 1484.97, "total_tokens": 29423488} {"current_steps": 139430, "total_steps": 181800, "loss": 0.0627, "lr": 7.826858337844676e-06, "epoch": 15.33883388338834, "percentage": 76.69, "elapsed_time": "5:30:14", "remaining_time": "1:40:21", "throughput": 1484.97, "total_tokens": 29424544} {"current_steps": 139435, "total_steps": 181800, "loss": 0.0081, "lr": 7.825114221320696e-06, "epoch": 15.339383938393839, "percentage": 76.7, "elapsed_time": "5:30:15", "remaining_time": "1:40:20", "throughput": 1484.97, "total_tokens": 29425600} {"current_steps": 139440, "total_steps": 181800, "loss": 0.0014, "lr": 7.823370263089406e-06, "epoch": 15.33993399339934, "percentage": 76.7, "elapsed_time": "5:30:16", "remaining_time": "1:40:19", "throughput": 1484.97, "total_tokens": 29426624} {"current_steps": 139445, "total_steps": 181800, "loss": 0.0042, "lr": 7.821626463166861e-06, "epoch": 15.340484048404841, "percentage": 76.7, "elapsed_time": "5:30:17", "remaining_time": "1:40:19", "throughput": 1484.97, "total_tokens": 29427648} {"current_steps": 139450, "total_steps": 181800, "loss": 0.0013, "lr": 7.81988282156915e-06, "epoch": 15.34103410341034, "percentage": 76.71, "elapsed_time": "5:30:17", "remaining_time": "1:40:18", "throughput": 1484.97, "total_tokens": 29428736} {"current_steps": 139455, "total_steps": 181800, "loss": 0.0281, "lr": 7.818139338312327e-06, "epoch": 15.341584158415841, "percentage": 76.71, "elapsed_time": "5:30:18", "remaining_time": "1:40:17", "throughput": 1484.98, "total_tokens": 29429824} {"current_steps": 139460, "total_steps": 181800, "loss": 0.0035, "lr": 7.816396013412471e-06, "epoch": 15.342134213421343, "percentage": 76.71, "elapsed_time": "5:30:19", "remaining_time": "1:40:17", "throughput": 1484.98, "total_tokens": 29430848} {"current_steps": 139465, "total_steps": 181800, "loss": 0.1026, "lr": 7.814652846885654e-06, "epoch": 15.342684268426842, "percentage": 76.71, "elapsed_time": "5:30:19", "remaining_time": "1:40:16", "throughput": 1484.98, "total_tokens": 29431936} {"current_steps": 139470, "total_steps": 181800, "loss": 0.0047, "lr": 7.812909838747929e-06, "epoch": 15.343234323432343, "percentage": 76.72, "elapsed_time": "5:30:20", "remaining_time": "1:40:15", "throughput": 1484.98, "total_tokens": 29433024} {"current_steps": 139475, "total_steps": 181800, "loss": 0.0045, "lr": 7.811166989015372e-06, "epoch": 15.343784378437844, "percentage": 76.72, "elapsed_time": "5:30:21", "remaining_time": "1:40:14", "throughput": 1484.98, "total_tokens": 29434080} {"current_steps": 139480, "total_steps": 181800, "loss": 0.0048, "lr": 7.809424297704035e-06, "epoch": 15.344334433443345, "percentage": 76.72, "elapsed_time": "5:30:21", "remaining_time": "1:40:14", "throughput": 1484.99, "total_tokens": 29435136} {"current_steps": 139485, "total_steps": 181800, "loss": 0.0087, "lr": 7.807681764829993e-06, "epoch": 15.344884488448844, "percentage": 76.72, "elapsed_time": "5:30:22", "remaining_time": "1:40:13", "throughput": 1484.99, "total_tokens": 29436256} {"current_steps": 139490, "total_steps": 181800, "loss": 0.0049, "lr": 7.805939390409292e-06, "epoch": 15.345434543454346, "percentage": 76.73, "elapsed_time": "5:30:23", "remaining_time": "1:40:12", "throughput": 1484.99, "total_tokens": 29437280} {"current_steps": 139495, "total_steps": 181800, "loss": 0.0457, "lr": 7.804197174457995e-06, "epoch": 15.345984598459847, "percentage": 76.73, "elapsed_time": "5:30:23", "remaining_time": "1:40:12", "throughput": 1484.99, "total_tokens": 29438336} {"current_steps": 139500, "total_steps": 181800, "loss": 0.0031, "lr": 7.802455116992169e-06, "epoch": 15.346534653465346, "percentage": 76.73, "elapsed_time": "5:30:24", "remaining_time": "1:40:11", "throughput": 1485.0, "total_tokens": 29439424} {"current_steps": 139505, "total_steps": 181800, "loss": 0.0375, "lr": 7.800713218027855e-06, "epoch": 15.347084708470847, "percentage": 76.74, "elapsed_time": "5:30:25", "remaining_time": "1:40:10", "throughput": 1485.0, "total_tokens": 29440512} {"current_steps": 139510, "total_steps": 181800, "loss": 0.0047, "lr": 7.798971477581125e-06, "epoch": 15.347634763476348, "percentage": 76.74, "elapsed_time": "5:30:25", "remaining_time": "1:40:09", "throughput": 1485.0, "total_tokens": 29441632} {"current_steps": 139515, "total_steps": 181800, "loss": 0.0027, "lr": 7.797229895668007e-06, "epoch": 15.348184818481847, "percentage": 76.74, "elapsed_time": "5:30:26", "remaining_time": "1:40:09", "throughput": 1485.0, "total_tokens": 29442688} {"current_steps": 139520, "total_steps": 181800, "loss": 0.0069, "lr": 7.795488472304571e-06, "epoch": 15.348734873487349, "percentage": 76.74, "elapsed_time": "5:30:27", "remaining_time": "1:40:08", "throughput": 1485.01, "total_tokens": 29443744} {"current_steps": 139525, "total_steps": 181800, "loss": 0.001, "lr": 7.793747207506868e-06, "epoch": 15.34928492849285, "percentage": 76.75, "elapsed_time": "5:30:28", "remaining_time": "1:40:07", "throughput": 1485.01, "total_tokens": 29444736} {"current_steps": 139530, "total_steps": 181800, "loss": 0.0031, "lr": 7.792006101290933e-06, "epoch": 15.34983498349835, "percentage": 76.75, "elapsed_time": "5:30:28", "remaining_time": "1:40:07", "throughput": 1485.01, "total_tokens": 29445760} {"current_steps": 139535, "total_steps": 181800, "loss": 0.0021, "lr": 7.790265153672829e-06, "epoch": 15.35038503850385, "percentage": 76.75, "elapsed_time": "5:30:29", "remaining_time": "1:40:06", "throughput": 1485.01, "total_tokens": 29446848} {"current_steps": 139540, "total_steps": 181800, "loss": 0.0021, "lr": 7.788524364668594e-06, "epoch": 15.350935093509351, "percentage": 76.75, "elapsed_time": "5:30:30", "remaining_time": "1:40:05", "throughput": 1485.01, "total_tokens": 29447872} {"current_steps": 139545, "total_steps": 181800, "loss": 0.0062, "lr": 7.786783734294261e-06, "epoch": 15.351485148514852, "percentage": 76.76, "elapsed_time": "5:30:30", "remaining_time": "1:40:04", "throughput": 1485.01, "total_tokens": 29448960} {"current_steps": 139550, "total_steps": 181800, "loss": 0.119, "lr": 7.785043262565884e-06, "epoch": 15.352035203520352, "percentage": 76.76, "elapsed_time": "5:30:31", "remaining_time": "1:40:04", "throughput": 1485.02, "total_tokens": 29450048} {"current_steps": 139555, "total_steps": 181800, "loss": 0.0009, "lr": 7.783302949499501e-06, "epoch": 15.352585258525853, "percentage": 76.76, "elapsed_time": "5:30:32", "remaining_time": "1:40:03", "throughput": 1485.02, "total_tokens": 29451104} {"current_steps": 139560, "total_steps": 181800, "loss": 0.0137, "lr": 7.781562795111164e-06, "epoch": 15.353135313531354, "percentage": 76.77, "elapsed_time": "5:30:32", "remaining_time": "1:40:02", "throughput": 1485.02, "total_tokens": 29452128} {"current_steps": 139565, "total_steps": 181800, "loss": 0.1276, "lr": 7.7798227994169e-06, "epoch": 15.353685368536853, "percentage": 76.77, "elapsed_time": "5:30:33", "remaining_time": "1:40:02", "throughput": 1485.02, "total_tokens": 29453216} {"current_steps": 139570, "total_steps": 181800, "loss": 0.0041, "lr": 7.778082962432736e-06, "epoch": 15.354235423542354, "percentage": 76.77, "elapsed_time": "5:30:34", "remaining_time": "1:40:01", "throughput": 1485.02, "total_tokens": 29454272} {"current_steps": 139575, "total_steps": 181800, "loss": 0.0027, "lr": 7.77634328417472e-06, "epoch": 15.354785478547855, "percentage": 76.77, "elapsed_time": "5:30:34", "remaining_time": "1:40:00", "throughput": 1485.02, "total_tokens": 29455296} {"current_steps": 139580, "total_steps": 181800, "loss": 0.0044, "lr": 7.774603764658891e-06, "epoch": 15.355335533553355, "percentage": 76.78, "elapsed_time": "5:30:35", "remaining_time": "1:39:59", "throughput": 1485.02, "total_tokens": 29456352} {"current_steps": 139585, "total_steps": 181800, "loss": 0.0025, "lr": 7.772864403901264e-06, "epoch": 15.355885588558856, "percentage": 76.78, "elapsed_time": "5:30:36", "remaining_time": "1:39:59", "throughput": 1485.02, "total_tokens": 29457376} {"current_steps": 139590, "total_steps": 181800, "loss": 0.1043, "lr": 7.77112520191789e-06, "epoch": 15.356435643564357, "percentage": 76.78, "elapsed_time": "5:30:36", "remaining_time": "1:39:58", "throughput": 1485.02, "total_tokens": 29458368} {"current_steps": 139595, "total_steps": 181800, "loss": 0.0045, "lr": 7.769386158724776e-06, "epoch": 15.356985698569858, "percentage": 76.78, "elapsed_time": "5:30:37", "remaining_time": "1:39:57", "throughput": 1485.02, "total_tokens": 29459424} {"current_steps": 139600, "total_steps": 181800, "loss": 0.1177, "lr": 7.767647274337971e-06, "epoch": 15.357535753575357, "percentage": 76.79, "elapsed_time": "5:30:38", "remaining_time": "1:39:56", "throughput": 1485.03, "total_tokens": 29460512} {"current_steps": 139605, "total_steps": 181800, "loss": 0.0046, "lr": 7.765908548773485e-06, "epoch": 15.358085808580858, "percentage": 76.79, "elapsed_time": "5:30:39", "remaining_time": "1:39:56", "throughput": 1485.03, "total_tokens": 29461632} {"current_steps": 139610, "total_steps": 181800, "loss": 0.0018, "lr": 7.76416998204735e-06, "epoch": 15.35863586358636, "percentage": 76.79, "elapsed_time": "5:30:39", "remaining_time": "1:39:55", "throughput": 1485.04, "total_tokens": 29462720} {"current_steps": 139615, "total_steps": 181800, "loss": 0.1716, "lr": 7.7624315741756e-06, "epoch": 15.359185918591859, "percentage": 76.8, "elapsed_time": "5:30:40", "remaining_time": "1:39:54", "throughput": 1485.04, "total_tokens": 29463808} {"current_steps": 139620, "total_steps": 181800, "loss": 0.0408, "lr": 7.760693325174235e-06, "epoch": 15.35973597359736, "percentage": 76.8, "elapsed_time": "5:30:41", "remaining_time": "1:39:54", "throughput": 1485.04, "total_tokens": 29464864} {"current_steps": 139625, "total_steps": 181800, "loss": 0.0209, "lr": 7.758955235059295e-06, "epoch": 15.36028602860286, "percentage": 76.8, "elapsed_time": "5:30:41", "remaining_time": "1:39:53", "throughput": 1485.04, "total_tokens": 29465920} {"current_steps": 139630, "total_steps": 181800, "loss": 0.0204, "lr": 7.757217303846787e-06, "epoch": 15.36083608360836, "percentage": 76.8, "elapsed_time": "5:30:42", "remaining_time": "1:39:52", "throughput": 1485.04, "total_tokens": 29467008} {"current_steps": 139635, "total_steps": 181800, "loss": 0.0335, "lr": 7.75547953155273e-06, "epoch": 15.361386138613861, "percentage": 76.81, "elapsed_time": "5:30:43", "remaining_time": "1:39:51", "throughput": 1485.05, "total_tokens": 29468032} {"current_steps": 139640, "total_steps": 181800, "loss": 0.0502, "lr": 7.753741918193155e-06, "epoch": 15.361936193619362, "percentage": 76.81, "elapsed_time": "5:30:43", "remaining_time": "1:39:51", "throughput": 1485.05, "total_tokens": 29469120} {"current_steps": 139645, "total_steps": 181800, "loss": 0.0179, "lr": 7.752004463784055e-06, "epoch": 15.362486248624862, "percentage": 76.81, "elapsed_time": "5:30:44", "remaining_time": "1:39:50", "throughput": 1485.05, "total_tokens": 29470176} {"current_steps": 139650, "total_steps": 181800, "loss": 0.0012, "lr": 7.750267168341463e-06, "epoch": 15.363036303630363, "percentage": 76.82, "elapsed_time": "5:30:45", "remaining_time": "1:39:49", "throughput": 1485.05, "total_tokens": 29471232} {"current_steps": 139655, "total_steps": 181800, "loss": 0.013, "lr": 7.748530031881379e-06, "epoch": 15.363586358635864, "percentage": 76.82, "elapsed_time": "5:30:45", "remaining_time": "1:39:49", "throughput": 1485.05, "total_tokens": 29472320} {"current_steps": 139660, "total_steps": 181800, "loss": 0.0006, "lr": 7.74679305441981e-06, "epoch": 15.364136413641365, "percentage": 76.82, "elapsed_time": "5:30:46", "remaining_time": "1:39:48", "throughput": 1485.06, "total_tokens": 29473472} {"current_steps": 139665, "total_steps": 181800, "loss": 0.0011, "lr": 7.745056235972767e-06, "epoch": 15.364686468646864, "percentage": 76.82, "elapsed_time": "5:30:47", "remaining_time": "1:39:47", "throughput": 1485.06, "total_tokens": 29474560} {"current_steps": 139670, "total_steps": 181800, "loss": 0.0038, "lr": 7.743319576556263e-06, "epoch": 15.365236523652365, "percentage": 76.83, "elapsed_time": "5:30:48", "remaining_time": "1:39:46", "throughput": 1485.06, "total_tokens": 29475584} {"current_steps": 139675, "total_steps": 181800, "loss": 0.0551, "lr": 7.74158307618631e-06, "epoch": 15.365786578657866, "percentage": 76.83, "elapsed_time": "5:30:48", "remaining_time": "1:39:46", "throughput": 1485.06, "total_tokens": 29476640} {"current_steps": 139680, "total_steps": 181800, "loss": 0.0508, "lr": 7.739846734878906e-06, "epoch": 15.366336633663366, "percentage": 76.83, "elapsed_time": "5:30:49", "remaining_time": "1:39:45", "throughput": 1485.07, "total_tokens": 29477696} {"current_steps": 139685, "total_steps": 181800, "loss": 0.0019, "lr": 7.73811055265004e-06, "epoch": 15.366886688668867, "percentage": 76.83, "elapsed_time": "5:30:50", "remaining_time": "1:39:44", "throughput": 1485.07, "total_tokens": 29478720} {"current_steps": 139690, "total_steps": 181800, "loss": 0.0023, "lr": 7.73637452951573e-06, "epoch": 15.367436743674368, "percentage": 76.84, "elapsed_time": "5:30:50", "remaining_time": "1:39:44", "throughput": 1485.07, "total_tokens": 29479776} {"current_steps": 139695, "total_steps": 181800, "loss": 0.012, "lr": 7.734638665491972e-06, "epoch": 15.367986798679867, "percentage": 76.84, "elapsed_time": "5:30:51", "remaining_time": "1:39:43", "throughput": 1485.07, "total_tokens": 29480832} {"current_steps": 139700, "total_steps": 181800, "loss": 0.0811, "lr": 7.73290296059477e-06, "epoch": 15.368536853685368, "percentage": 76.84, "elapsed_time": "5:30:52", "remaining_time": "1:39:42", "throughput": 1485.07, "total_tokens": 29481856} {"current_steps": 139705, "total_steps": 181800, "loss": 0.0042, "lr": 7.731167414840118e-06, "epoch": 15.36908690869087, "percentage": 76.85, "elapsed_time": "5:30:52", "remaining_time": "1:39:41", "throughput": 1485.07, "total_tokens": 29482880} {"current_steps": 139710, "total_steps": 181800, "loss": 0.0024, "lr": 7.729432028244002e-06, "epoch": 15.369636963696369, "percentage": 76.85, "elapsed_time": "5:30:53", "remaining_time": "1:39:41", "throughput": 1485.07, "total_tokens": 29483872} {"current_steps": 139715, "total_steps": 181800, "loss": 0.0232, "lr": 7.72769680082243e-06, "epoch": 15.37018701870187, "percentage": 76.85, "elapsed_time": "5:30:54", "remaining_time": "1:39:40", "throughput": 1485.07, "total_tokens": 29484960} {"current_steps": 139720, "total_steps": 181800, "loss": 0.0006, "lr": 7.725961732591383e-06, "epoch": 15.370737073707371, "percentage": 76.85, "elapsed_time": "5:30:54", "remaining_time": "1:39:39", "throughput": 1485.07, "total_tokens": 29485952} {"current_steps": 139725, "total_steps": 181800, "loss": 0.0884, "lr": 7.724226823566854e-06, "epoch": 15.371287128712872, "percentage": 76.86, "elapsed_time": "5:30:55", "remaining_time": "1:39:39", "throughput": 1485.07, "total_tokens": 29486944} {"current_steps": 139730, "total_steps": 181800, "loss": 0.2324, "lr": 7.722492073764848e-06, "epoch": 15.371837183718371, "percentage": 76.86, "elapsed_time": "5:30:56", "remaining_time": "1:39:38", "throughput": 1485.07, "total_tokens": 29487968} {"current_steps": 139735, "total_steps": 181800, "loss": 0.0037, "lr": 7.720757483201332e-06, "epoch": 15.372387238723872, "percentage": 76.86, "elapsed_time": "5:30:57", "remaining_time": "1:39:37", "throughput": 1485.06, "total_tokens": 29488960} {"current_steps": 139740, "total_steps": 181800, "loss": 0.0053, "lr": 7.719023051892313e-06, "epoch": 15.372937293729374, "percentage": 76.86, "elapsed_time": "5:30:57", "remaining_time": "1:39:36", "throughput": 1485.06, "total_tokens": 29489984} {"current_steps": 139745, "total_steps": 181800, "loss": 0.001, "lr": 7.717288779853757e-06, "epoch": 15.373487348734873, "percentage": 76.87, "elapsed_time": "5:30:58", "remaining_time": "1:39:36", "throughput": 1485.06, "total_tokens": 29491008} {"current_steps": 139750, "total_steps": 181800, "loss": 0.0882, "lr": 7.715554667101657e-06, "epoch": 15.374037403740374, "percentage": 76.87, "elapsed_time": "5:30:59", "remaining_time": "1:39:35", "throughput": 1485.06, "total_tokens": 29492032} {"current_steps": 139755, "total_steps": 181800, "loss": 0.163, "lr": 7.713820713652004e-06, "epoch": 15.374587458745875, "percentage": 76.87, "elapsed_time": "5:30:59", "remaining_time": "1:39:34", "throughput": 1485.06, "total_tokens": 29492992} {"current_steps": 139760, "total_steps": 181800, "loss": 0.0064, "lr": 7.712086919520762e-06, "epoch": 15.375137513751374, "percentage": 76.88, "elapsed_time": "5:31:00", "remaining_time": "1:39:34", "throughput": 1485.06, "total_tokens": 29494048} {"current_steps": 139765, "total_steps": 181800, "loss": 0.0435, "lr": 7.710353284723928e-06, "epoch": 15.375687568756875, "percentage": 76.88, "elapsed_time": "5:31:01", "remaining_time": "1:39:33", "throughput": 1485.05, "total_tokens": 29495104} {"current_steps": 139770, "total_steps": 181800, "loss": 0.0018, "lr": 7.70861980927747e-06, "epoch": 15.376237623762377, "percentage": 76.88, "elapsed_time": "5:31:02", "remaining_time": "1:39:32", "throughput": 1485.05, "total_tokens": 29496128} {"current_steps": 139775, "total_steps": 181800, "loss": 0.0048, "lr": 7.70688649319736e-06, "epoch": 15.376787678767876, "percentage": 76.88, "elapsed_time": "5:31:02", "remaining_time": "1:39:31", "throughput": 1485.05, "total_tokens": 29497152} {"current_steps": 139780, "total_steps": 181800, "loss": 0.0019, "lr": 7.70515333649958e-06, "epoch": 15.377337733773377, "percentage": 76.89, "elapsed_time": "5:31:03", "remaining_time": "1:39:31", "throughput": 1485.05, "total_tokens": 29498208} {"current_steps": 139785, "total_steps": 181800, "loss": 0.0777, "lr": 7.703420339200101e-06, "epoch": 15.377887788778878, "percentage": 76.89, "elapsed_time": "5:31:04", "remaining_time": "1:39:30", "throughput": 1485.05, "total_tokens": 29499296} {"current_steps": 139790, "total_steps": 181800, "loss": 0.0935, "lr": 7.701687501314905e-06, "epoch": 15.37843784378438, "percentage": 76.89, "elapsed_time": "5:31:04", "remaining_time": "1:39:29", "throughput": 1485.05, "total_tokens": 29500320} {"current_steps": 139795, "total_steps": 181800, "loss": 0.0036, "lr": 7.699954822859957e-06, "epoch": 15.378987898789878, "percentage": 76.89, "elapsed_time": "5:31:05", "remaining_time": "1:39:29", "throughput": 1485.06, "total_tokens": 29501408} {"current_steps": 139800, "total_steps": 181800, "loss": 0.0018, "lr": 7.698222303851213e-06, "epoch": 15.37953795379538, "percentage": 76.9, "elapsed_time": "5:31:06", "remaining_time": "1:39:28", "throughput": 1485.06, "total_tokens": 29502464} {"current_steps": 139805, "total_steps": 181800, "loss": 0.0248, "lr": 7.696489944304652e-06, "epoch": 15.38008800880088, "percentage": 76.9, "elapsed_time": "5:31:06", "remaining_time": "1:39:27", "throughput": 1485.06, "total_tokens": 29503616} {"current_steps": 139810, "total_steps": 181800, "loss": 0.0037, "lr": 7.694757744236241e-06, "epoch": 15.38063806380638, "percentage": 76.9, "elapsed_time": "5:31:07", "remaining_time": "1:39:26", "throughput": 1485.06, "total_tokens": 29504640} {"current_steps": 139815, "total_steps": 181800, "loss": 0.0259, "lr": 7.693025703661952e-06, "epoch": 15.381188118811881, "percentage": 76.91, "elapsed_time": "5:31:08", "remaining_time": "1:39:26", "throughput": 1485.07, "total_tokens": 29505696} {"current_steps": 139820, "total_steps": 181800, "loss": 0.0082, "lr": 7.691293822597742e-06, "epoch": 15.381738173817382, "percentage": 76.91, "elapsed_time": "5:31:08", "remaining_time": "1:39:25", "throughput": 1485.07, "total_tokens": 29506752} {"current_steps": 139825, "total_steps": 181800, "loss": 0.0008, "lr": 7.689562101059561e-06, "epoch": 15.382288228822881, "percentage": 76.91, "elapsed_time": "5:31:09", "remaining_time": "1:39:24", "throughput": 1485.07, "total_tokens": 29507872} {"current_steps": 139830, "total_steps": 181800, "loss": 0.0075, "lr": 7.68783053906339e-06, "epoch": 15.382838283828383, "percentage": 76.91, "elapsed_time": "5:31:10", "remaining_time": "1:39:24", "throughput": 1485.07, "total_tokens": 29508896} {"current_steps": 139835, "total_steps": 181800, "loss": 0.0038, "lr": 7.686099136625169e-06, "epoch": 15.383388338833884, "percentage": 76.92, "elapsed_time": "5:31:11", "remaining_time": "1:39:23", "throughput": 1485.07, "total_tokens": 29509920} {"current_steps": 139840, "total_steps": 181800, "loss": 0.007, "lr": 7.684367893760863e-06, "epoch": 15.383938393839385, "percentage": 76.92, "elapsed_time": "5:31:11", "remaining_time": "1:39:22", "throughput": 1485.07, "total_tokens": 29511008} {"current_steps": 139845, "total_steps": 181800, "loss": 0.0031, "lr": 7.682636810486437e-06, "epoch": 15.384488448844884, "percentage": 76.92, "elapsed_time": "5:31:12", "remaining_time": "1:39:21", "throughput": 1485.07, "total_tokens": 29512000} {"current_steps": 139850, "total_steps": 181800, "loss": 0.023, "lr": 7.680905886817832e-06, "epoch": 15.385038503850385, "percentage": 76.93, "elapsed_time": "5:31:13", "remaining_time": "1:39:21", "throughput": 1485.07, "total_tokens": 29513024} {"current_steps": 139855, "total_steps": 181800, "loss": 0.0022, "lr": 7.679175122771013e-06, "epoch": 15.385588558855886, "percentage": 76.93, "elapsed_time": "5:31:13", "remaining_time": "1:39:20", "throughput": 1485.08, "total_tokens": 29514112} {"current_steps": 139860, "total_steps": 181800, "loss": 0.1624, "lr": 7.677444518361918e-06, "epoch": 15.386138613861386, "percentage": 76.93, "elapsed_time": "5:31:14", "remaining_time": "1:39:19", "throughput": 1485.08, "total_tokens": 29515200} {"current_steps": 139865, "total_steps": 181800, "loss": 0.0485, "lr": 7.675714073606504e-06, "epoch": 15.386688668866887, "percentage": 76.93, "elapsed_time": "5:31:15", "remaining_time": "1:39:19", "throughput": 1485.08, "total_tokens": 29516192} {"current_steps": 139870, "total_steps": 181800, "loss": 0.0365, "lr": 7.673983788520731e-06, "epoch": 15.387238723872388, "percentage": 76.94, "elapsed_time": "5:31:15", "remaining_time": "1:39:18", "throughput": 1485.08, "total_tokens": 29517344} {"current_steps": 139875, "total_steps": 181800, "loss": 0.1067, "lr": 7.672253663120526e-06, "epoch": 15.387788778877887, "percentage": 76.94, "elapsed_time": "5:31:16", "remaining_time": "1:39:17", "throughput": 1485.08, "total_tokens": 29518368} {"current_steps": 139880, "total_steps": 181800, "loss": 0.0176, "lr": 7.670523697421853e-06, "epoch": 15.388338833883388, "percentage": 76.94, "elapsed_time": "5:31:17", "remaining_time": "1:39:16", "throughput": 1485.09, "total_tokens": 29519456} {"current_steps": 139885, "total_steps": 181800, "loss": 0.0016, "lr": 7.668793891440638e-06, "epoch": 15.38888888888889, "percentage": 76.94, "elapsed_time": "5:31:17", "remaining_time": "1:39:16", "throughput": 1485.09, "total_tokens": 29520576} {"current_steps": 139890, "total_steps": 181800, "loss": 0.1028, "lr": 7.667064245192843e-06, "epoch": 15.389438943894389, "percentage": 76.95, "elapsed_time": "5:31:18", "remaining_time": "1:39:15", "throughput": 1485.09, "total_tokens": 29521632} {"current_steps": 139895, "total_steps": 181800, "loss": 0.0723, "lr": 7.66533475869439e-06, "epoch": 15.38998899889989, "percentage": 76.95, "elapsed_time": "5:31:19", "remaining_time": "1:39:14", "throughput": 1485.1, "total_tokens": 29522784} {"current_steps": 139900, "total_steps": 181800, "loss": 0.0044, "lr": 7.663605431961229e-06, "epoch": 15.39053905390539, "percentage": 76.95, "elapsed_time": "5:31:20", "remaining_time": "1:39:14", "throughput": 1485.1, "total_tokens": 29523808} {"current_steps": 139905, "total_steps": 181800, "loss": 0.0296, "lr": 7.661876265009307e-06, "epoch": 15.391089108910892, "percentage": 76.96, "elapsed_time": "5:31:20", "remaining_time": "1:39:13", "throughput": 1485.1, "total_tokens": 29524864} {"current_steps": 139910, "total_steps": 181800, "loss": 0.0925, "lr": 7.660147257854544e-06, "epoch": 15.391639163916391, "percentage": 76.96, "elapsed_time": "5:31:21", "remaining_time": "1:39:12", "throughput": 1485.11, "total_tokens": 29525952} {"current_steps": 139915, "total_steps": 181800, "loss": 0.0027, "lr": 7.658418410512889e-06, "epoch": 15.392189218921892, "percentage": 76.96, "elapsed_time": "5:31:22", "remaining_time": "1:39:11", "throughput": 1485.11, "total_tokens": 29527072} {"current_steps": 139920, "total_steps": 181800, "loss": 0.002, "lr": 7.65668972300027e-06, "epoch": 15.392739273927393, "percentage": 76.96, "elapsed_time": "5:31:22", "remaining_time": "1:39:11", "throughput": 1485.11, "total_tokens": 29528064} {"current_steps": 139925, "total_steps": 181800, "loss": 0.0026, "lr": 7.654961195332608e-06, "epoch": 15.393289328932893, "percentage": 76.97, "elapsed_time": "5:31:23", "remaining_time": "1:39:10", "throughput": 1485.11, "total_tokens": 29529088} {"current_steps": 139930, "total_steps": 181800, "loss": 0.0119, "lr": 7.653232827525859e-06, "epoch": 15.393839383938394, "percentage": 76.97, "elapsed_time": "5:31:24", "remaining_time": "1:39:09", "throughput": 1485.11, "total_tokens": 29530176} {"current_steps": 139935, "total_steps": 181800, "loss": 0.0041, "lr": 7.651504619595931e-06, "epoch": 15.394389438943895, "percentage": 76.97, "elapsed_time": "5:31:24", "remaining_time": "1:39:09", "throughput": 1485.11, "total_tokens": 29531232} {"current_steps": 139940, "total_steps": 181800, "loss": 0.0038, "lr": 7.649776571558768e-06, "epoch": 15.394939493949394, "percentage": 76.97, "elapsed_time": "5:31:25", "remaining_time": "1:39:08", "throughput": 1485.12, "total_tokens": 29532320} {"current_steps": 139945, "total_steps": 181800, "loss": 0.05, "lr": 7.64804868343029e-06, "epoch": 15.395489548954895, "percentage": 76.98, "elapsed_time": "5:31:26", "remaining_time": "1:39:07", "throughput": 1485.12, "total_tokens": 29533344} {"current_steps": 139950, "total_steps": 181800, "loss": 0.0332, "lr": 7.646320955226413e-06, "epoch": 15.396039603960396, "percentage": 76.98, "elapsed_time": "5:31:26", "remaining_time": "1:39:06", "throughput": 1485.11, "total_tokens": 29534336} {"current_steps": 139955, "total_steps": 181800, "loss": 0.0066, "lr": 7.644593386963067e-06, "epoch": 15.396589658965897, "percentage": 76.98, "elapsed_time": "5:31:27", "remaining_time": "1:39:06", "throughput": 1485.11, "total_tokens": 29535360} {"current_steps": 139960, "total_steps": 181800, "loss": 0.012, "lr": 7.642865978656186e-06, "epoch": 15.397139713971397, "percentage": 76.99, "elapsed_time": "5:31:28", "remaining_time": "1:39:05", "throughput": 1485.12, "total_tokens": 29536480} {"current_steps": 139965, "total_steps": 181800, "loss": 0.0019, "lr": 7.641138730321671e-06, "epoch": 15.397689768976898, "percentage": 76.99, "elapsed_time": "5:31:28", "remaining_time": "1:39:04", "throughput": 1485.12, "total_tokens": 29537504} {"current_steps": 139970, "total_steps": 181800, "loss": 0.0107, "lr": 7.639411641975461e-06, "epoch": 15.398239823982399, "percentage": 76.99, "elapsed_time": "5:31:29", "remaining_time": "1:39:04", "throughput": 1485.12, "total_tokens": 29538560} {"current_steps": 139975, "total_steps": 181800, "loss": 0.001, "lr": 7.637684713633453e-06, "epoch": 15.398789878987898, "percentage": 76.99, "elapsed_time": "5:31:30", "remaining_time": "1:39:03", "throughput": 1485.12, "total_tokens": 29539616} {"current_steps": 139980, "total_steps": 181800, "loss": 0.0027, "lr": 7.635957945311573e-06, "epoch": 15.3993399339934, "percentage": 77.0, "elapsed_time": "5:31:31", "remaining_time": "1:39:02", "throughput": 1485.12, "total_tokens": 29540640} {"current_steps": 139985, "total_steps": 181800, "loss": 0.1095, "lr": 7.634231337025747e-06, "epoch": 15.3998899889989, "percentage": 77.0, "elapsed_time": "5:31:31", "remaining_time": "1:39:01", "throughput": 1485.12, "total_tokens": 29541664} {"current_steps": 139990, "total_steps": 181800, "loss": 0.0108, "lr": 7.63250488879187e-06, "epoch": 15.4004400440044, "percentage": 77.0, "elapsed_time": "5:31:32", "remaining_time": "1:39:01", "throughput": 1485.13, "total_tokens": 29542752} {"current_steps": 139995, "total_steps": 181800, "loss": 0.0064, "lr": 7.630778600625869e-06, "epoch": 15.400990099009901, "percentage": 77.0, "elapsed_time": "5:31:33", "remaining_time": "1:39:00", "throughput": 1485.13, "total_tokens": 29543808} {"current_steps": 140000, "total_steps": 181800, "loss": 0.0533, "lr": 7.629052472543638e-06, "epoch": 15.401540154015402, "percentage": 77.01, "elapsed_time": "5:31:33", "remaining_time": "1:38:59", "throughput": 1485.13, "total_tokens": 29544896} {"current_steps": 140005, "total_steps": 181800, "loss": 0.0286, "lr": 7.627326504561103e-06, "epoch": 15.402090209020901, "percentage": 77.01, "elapsed_time": "5:31:34", "remaining_time": "1:38:59", "throughput": 1485.13, "total_tokens": 29545984} {"current_steps": 140010, "total_steps": 181800, "loss": 0.1062, "lr": 7.625600696694155e-06, "epoch": 15.402640264026402, "percentage": 77.01, "elapsed_time": "5:31:35", "remaining_time": "1:38:58", "throughput": 1485.14, "total_tokens": 29547072} {"current_steps": 140015, "total_steps": 181800, "loss": 0.1694, "lr": 7.623875048958709e-06, "epoch": 15.403190319031903, "percentage": 77.02, "elapsed_time": "5:31:35", "remaining_time": "1:38:57", "throughput": 1485.14, "total_tokens": 29548192} {"current_steps": 140020, "total_steps": 181800, "loss": 0.0015, "lr": 7.6221495613706785e-06, "epoch": 15.403740374037405, "percentage": 77.02, "elapsed_time": "5:31:36", "remaining_time": "1:38:56", "throughput": 1485.14, "total_tokens": 29549216} {"current_steps": 140025, "total_steps": 181800, "loss": 0.0017, "lr": 7.620424233945947e-06, "epoch": 15.404290429042904, "percentage": 77.02, "elapsed_time": "5:31:37", "remaining_time": "1:38:56", "throughput": 1485.14, "total_tokens": 29550208} {"current_steps": 140030, "total_steps": 181800, "loss": 0.0061, "lr": 7.618699066700433e-06, "epoch": 15.404840484048405, "percentage": 77.02, "elapsed_time": "5:31:37", "remaining_time": "1:38:55", "throughput": 1485.14, "total_tokens": 29551264} {"current_steps": 140035, "total_steps": 181800, "loss": 0.08, "lr": 7.616974059650031e-06, "epoch": 15.405390539053906, "percentage": 77.03, "elapsed_time": "5:31:38", "remaining_time": "1:38:54", "throughput": 1485.15, "total_tokens": 29552352} {"current_steps": 140040, "total_steps": 181800, "loss": 0.0058, "lr": 7.615249212810621e-06, "epoch": 15.405940594059405, "percentage": 77.03, "elapsed_time": "5:31:39", "remaining_time": "1:38:53", "throughput": 1485.15, "total_tokens": 29553408} {"current_steps": 140045, "total_steps": 181800, "loss": 0.0016, "lr": 7.613524526198135e-06, "epoch": 15.406490649064907, "percentage": 77.03, "elapsed_time": "5:31:39", "remaining_time": "1:38:53", "throughput": 1485.15, "total_tokens": 29554432} {"current_steps": 140050, "total_steps": 181800, "loss": 0.0403, "lr": 7.611799999828439e-06, "epoch": 15.407040704070408, "percentage": 77.04, "elapsed_time": "5:31:40", "remaining_time": "1:38:52", "throughput": 1485.15, "total_tokens": 29555456} {"current_steps": 140055, "total_steps": 181800, "loss": 0.0053, "lr": 7.610075633717451e-06, "epoch": 15.407590759075907, "percentage": 77.04, "elapsed_time": "5:31:41", "remaining_time": "1:38:51", "throughput": 1485.15, "total_tokens": 29556512} {"current_steps": 140060, "total_steps": 181800, "loss": 0.0026, "lr": 7.60835142788105e-06, "epoch": 15.408140814081408, "percentage": 77.04, "elapsed_time": "5:31:42", "remaining_time": "1:38:51", "throughput": 1485.15, "total_tokens": 29557472} {"current_steps": 140065, "total_steps": 181800, "loss": 0.0756, "lr": 7.606627382335119e-06, "epoch": 15.408690869086909, "percentage": 77.04, "elapsed_time": "5:31:42", "remaining_time": "1:38:50", "throughput": 1485.15, "total_tokens": 29558496} {"current_steps": 140070, "total_steps": 181800, "loss": 0.0031, "lr": 7.604903497095558e-06, "epoch": 15.409240924092408, "percentage": 77.05, "elapsed_time": "5:31:43", "remaining_time": "1:38:49", "throughput": 1485.15, "total_tokens": 29559552} {"current_steps": 140075, "total_steps": 181800, "loss": 0.0019, "lr": 7.603179772178254e-06, "epoch": 15.40979097909791, "percentage": 77.05, "elapsed_time": "5:31:44", "remaining_time": "1:38:48", "throughput": 1485.15, "total_tokens": 29560544} {"current_steps": 140080, "total_steps": 181800, "loss": 0.0032, "lr": 7.601456207599103e-06, "epoch": 15.41034103410341, "percentage": 77.05, "elapsed_time": "5:31:44", "remaining_time": "1:38:48", "throughput": 1485.15, "total_tokens": 29561568} {"current_steps": 140085, "total_steps": 181800, "loss": 0.0145, "lr": 7.599732803373979e-06, "epoch": 15.410891089108912, "percentage": 77.05, "elapsed_time": "5:31:45", "remaining_time": "1:38:47", "throughput": 1485.15, "total_tokens": 29562688} {"current_steps": 140090, "total_steps": 181800, "loss": 0.001, "lr": 7.598009559518765e-06, "epoch": 15.411441144114411, "percentage": 77.06, "elapsed_time": "5:31:46", "remaining_time": "1:38:46", "throughput": 1485.15, "total_tokens": 29563712} {"current_steps": 140095, "total_steps": 181800, "loss": 0.0076, "lr": 7.5962864760493525e-06, "epoch": 15.411991199119912, "percentage": 77.06, "elapsed_time": "5:31:46", "remaining_time": "1:38:46", "throughput": 1485.15, "total_tokens": 29564736} {"current_steps": 140100, "total_steps": 181800, "loss": 0.0013, "lr": 7.5945635529815986e-06, "epoch": 15.412541254125413, "percentage": 77.06, "elapsed_time": "5:31:47", "remaining_time": "1:38:45", "throughput": 1485.15, "total_tokens": 29565824} {"current_steps": 140105, "total_steps": 181800, "loss": 0.002, "lr": 7.592840790331418e-06, "epoch": 15.413091309130913, "percentage": 77.07, "elapsed_time": "5:31:48", "remaining_time": "1:38:44", "throughput": 1485.16, "total_tokens": 29566880} {"current_steps": 140110, "total_steps": 181800, "loss": 0.0014, "lr": 7.591118188114671e-06, "epoch": 15.413641364136414, "percentage": 77.07, "elapsed_time": "5:31:48", "remaining_time": "1:38:43", "throughput": 1485.15, "total_tokens": 29567872} {"current_steps": 140115, "total_steps": 181800, "loss": 0.0089, "lr": 7.589395746347228e-06, "epoch": 15.414191419141915, "percentage": 77.07, "elapsed_time": "5:31:49", "remaining_time": "1:38:43", "throughput": 1485.16, "total_tokens": 29568928} {"current_steps": 140120, "total_steps": 181800, "loss": 0.0729, "lr": 7.587673465044976e-06, "epoch": 15.414741474147414, "percentage": 77.07, "elapsed_time": "5:31:50", "remaining_time": "1:38:42", "throughput": 1485.16, "total_tokens": 29570016} {"current_steps": 140125, "total_steps": 181800, "loss": 0.0066, "lr": 7.585951344223774e-06, "epoch": 15.415291529152915, "percentage": 77.08, "elapsed_time": "5:31:51", "remaining_time": "1:38:41", "throughput": 1485.16, "total_tokens": 29571072} {"current_steps": 140130, "total_steps": 181800, "loss": 0.0125, "lr": 7.584229383899502e-06, "epoch": 15.415841584158416, "percentage": 77.08, "elapsed_time": "5:31:51", "remaining_time": "1:38:41", "throughput": 1485.17, "total_tokens": 29572224} {"current_steps": 140135, "total_steps": 181800, "loss": 0.0463, "lr": 7.582507584088039e-06, "epoch": 15.416391639163916, "percentage": 77.08, "elapsed_time": "5:31:52", "remaining_time": "1:38:40", "throughput": 1485.17, "total_tokens": 29573312} {"current_steps": 140140, "total_steps": 181800, "loss": 0.0084, "lr": 7.580785944805238e-06, "epoch": 15.416941694169417, "percentage": 77.08, "elapsed_time": "5:31:53", "remaining_time": "1:38:39", "throughput": 1485.17, "total_tokens": 29574368} {"current_steps": 140145, "total_steps": 181800, "loss": 0.004, "lr": 7.579064466066985e-06, "epoch": 15.417491749174918, "percentage": 77.09, "elapsed_time": "5:31:53", "remaining_time": "1:38:38", "throughput": 1485.17, "total_tokens": 29575392} {"current_steps": 140150, "total_steps": 181800, "loss": 0.0164, "lr": 7.577343147889132e-06, "epoch": 15.418041804180419, "percentage": 77.09, "elapsed_time": "5:31:54", "remaining_time": "1:38:38", "throughput": 1485.17, "total_tokens": 29576384} {"current_steps": 140155, "total_steps": 181800, "loss": 0.0214, "lr": 7.57562199028754e-06, "epoch": 15.418591859185918, "percentage": 77.09, "elapsed_time": "5:31:55", "remaining_time": "1:38:37", "throughput": 1485.18, "total_tokens": 29577568} {"current_steps": 140160, "total_steps": 181800, "loss": 0.0399, "lr": 7.573900993278079e-06, "epoch": 15.41914191419142, "percentage": 77.1, "elapsed_time": "5:31:55", "remaining_time": "1:38:36", "throughput": 1485.18, "total_tokens": 29578560} {"current_steps": 140165, "total_steps": 181800, "loss": 0.0089, "lr": 7.572180156876613e-06, "epoch": 15.41969196919692, "percentage": 77.1, "elapsed_time": "5:31:56", "remaining_time": "1:38:36", "throughput": 1485.18, "total_tokens": 29579648} {"current_steps": 140170, "total_steps": 181800, "loss": 0.0044, "lr": 7.570459481099007e-06, "epoch": 15.42024202420242, "percentage": 77.1, "elapsed_time": "5:31:57", "remaining_time": "1:38:35", "throughput": 1485.19, "total_tokens": 29580768} {"current_steps": 140175, "total_steps": 181800, "loss": 0.1329, "lr": 7.568738965961111e-06, "epoch": 15.42079207920792, "percentage": 77.1, "elapsed_time": "5:31:57", "remaining_time": "1:38:34", "throughput": 1485.19, "total_tokens": 29581888} {"current_steps": 140180, "total_steps": 181800, "loss": 0.0371, "lr": 7.5670186114787765e-06, "epoch": 15.421342134213422, "percentage": 77.11, "elapsed_time": "5:31:58", "remaining_time": "1:38:33", "throughput": 1485.19, "total_tokens": 29582912} {"current_steps": 140185, "total_steps": 181800, "loss": 0.0032, "lr": 7.565298417667865e-06, "epoch": 15.421892189218921, "percentage": 77.11, "elapsed_time": "5:31:59", "remaining_time": "1:38:33", "throughput": 1485.19, "total_tokens": 29584000} {"current_steps": 140190, "total_steps": 181800, "loss": 0.0015, "lr": 7.563578384544234e-06, "epoch": 15.422442244224422, "percentage": 77.11, "elapsed_time": "5:31:59", "remaining_time": "1:38:32", "throughput": 1485.19, "total_tokens": 29585024} {"current_steps": 140195, "total_steps": 181800, "loss": 0.1073, "lr": 7.56185851212374e-06, "epoch": 15.422992299229923, "percentage": 77.11, "elapsed_time": "5:32:00", "remaining_time": "1:38:31", "throughput": 1485.2, "total_tokens": 29586112} {"current_steps": 140200, "total_steps": 181800, "loss": 0.0591, "lr": 7.5601388004222315e-06, "epoch": 15.423542354235423, "percentage": 77.12, "elapsed_time": "5:32:01", "remaining_time": "1:38:31", "throughput": 1485.2, "total_tokens": 29587296} {"current_steps": 140205, "total_steps": 181800, "loss": 0.0428, "lr": 7.558419249455545e-06, "epoch": 15.424092409240924, "percentage": 77.12, "elapsed_time": "5:32:02", "remaining_time": "1:38:30", "throughput": 1485.21, "total_tokens": 29588384} {"current_steps": 140210, "total_steps": 181800, "loss": 0.0873, "lr": 7.5566998592395464e-06, "epoch": 15.424642464246425, "percentage": 77.12, "elapsed_time": "5:32:02", "remaining_time": "1:38:29", "throughput": 1485.21, "total_tokens": 29589408} {"current_steps": 140215, "total_steps": 181800, "loss": 0.0048, "lr": 7.554980629790068e-06, "epoch": 15.425192519251926, "percentage": 77.13, "elapsed_time": "5:32:03", "remaining_time": "1:38:28", "throughput": 1485.21, "total_tokens": 29590432} {"current_steps": 140220, "total_steps": 181800, "loss": 0.0034, "lr": 7.553261561122962e-06, "epoch": 15.425742574257425, "percentage": 77.13, "elapsed_time": "5:32:04", "remaining_time": "1:38:28", "throughput": 1485.21, "total_tokens": 29591488} {"current_steps": 140225, "total_steps": 181800, "loss": 0.0619, "lr": 7.551542653254082e-06, "epoch": 15.426292629262926, "percentage": 77.13, "elapsed_time": "5:32:04", "remaining_time": "1:38:27", "throughput": 1485.21, "total_tokens": 29592544} {"current_steps": 140230, "total_steps": 181800, "loss": 0.0479, "lr": 7.5498239061992495e-06, "epoch": 15.426842684268427, "percentage": 77.13, "elapsed_time": "5:32:05", "remaining_time": "1:38:26", "throughput": 1485.21, "total_tokens": 29593600} {"current_steps": 140235, "total_steps": 181800, "loss": 0.037, "lr": 7.548105319974328e-06, "epoch": 15.427392739273927, "percentage": 77.14, "elapsed_time": "5:32:06", "remaining_time": "1:38:26", "throughput": 1485.21, "total_tokens": 29594624} {"current_steps": 140240, "total_steps": 181800, "loss": 0.1108, "lr": 7.546386894595137e-06, "epoch": 15.427942794279428, "percentage": 77.14, "elapsed_time": "5:32:06", "remaining_time": "1:38:25", "throughput": 1485.22, "total_tokens": 29595744} {"current_steps": 140245, "total_steps": 181800, "loss": 0.0089, "lr": 7.5446686300775195e-06, "epoch": 15.428492849284929, "percentage": 77.14, "elapsed_time": "5:32:07", "remaining_time": "1:38:24", "throughput": 1485.22, "total_tokens": 29596800} {"current_steps": 140250, "total_steps": 181800, "loss": 0.0024, "lr": 7.542950526437326e-06, "epoch": 15.429042904290428, "percentage": 77.15, "elapsed_time": "5:32:08", "remaining_time": "1:38:23", "throughput": 1485.22, "total_tokens": 29597888} {"current_steps": 140255, "total_steps": 181800, "loss": 0.0016, "lr": 7.541232583690375e-06, "epoch": 15.42959295929593, "percentage": 77.15, "elapsed_time": "5:32:08", "remaining_time": "1:38:23", "throughput": 1485.22, "total_tokens": 29598944} {"current_steps": 140260, "total_steps": 181800, "loss": 0.0021, "lr": 7.53951480185251e-06, "epoch": 15.43014301430143, "percentage": 77.15, "elapsed_time": "5:32:09", "remaining_time": "1:38:22", "throughput": 1485.22, "total_tokens": 29599936} {"current_steps": 140265, "total_steps": 181800, "loss": 0.0507, "lr": 7.537797180939551e-06, "epoch": 15.430693069306932, "percentage": 77.15, "elapsed_time": "5:32:10", "remaining_time": "1:38:21", "throughput": 1485.23, "total_tokens": 29601056} {"current_steps": 140270, "total_steps": 181800, "loss": 0.0076, "lr": 7.536079720967345e-06, "epoch": 15.43124312431243, "percentage": 77.16, "elapsed_time": "5:32:11", "remaining_time": "1:38:21", "throughput": 1485.23, "total_tokens": 29602112} {"current_steps": 140275, "total_steps": 181800, "loss": 0.0403, "lr": 7.534362421951707e-06, "epoch": 15.431793179317932, "percentage": 77.16, "elapsed_time": "5:32:11", "remaining_time": "1:38:20", "throughput": 1485.23, "total_tokens": 29603232} {"current_steps": 140280, "total_steps": 181800, "loss": 0.0334, "lr": 7.5326452839084654e-06, "epoch": 15.432343234323433, "percentage": 77.16, "elapsed_time": "5:32:12", "remaining_time": "1:38:19", "throughput": 1485.23, "total_tokens": 29604288} {"current_steps": 140285, "total_steps": 181800, "loss": 0.1188, "lr": 7.53092830685346e-06, "epoch": 15.432893289328932, "percentage": 77.16, "elapsed_time": "5:32:13", "remaining_time": "1:38:18", "throughput": 1485.24, "total_tokens": 29605344} {"current_steps": 140290, "total_steps": 181800, "loss": 0.0271, "lr": 7.529211490802498e-06, "epoch": 15.433443344334433, "percentage": 77.17, "elapsed_time": "5:32:13", "remaining_time": "1:38:18", "throughput": 1485.24, "total_tokens": 29606432} {"current_steps": 140295, "total_steps": 181800, "loss": 0.065, "lr": 7.52749483577142e-06, "epoch": 15.433993399339935, "percentage": 77.17, "elapsed_time": "5:32:14", "remaining_time": "1:38:17", "throughput": 1485.24, "total_tokens": 29607488} {"current_steps": 140300, "total_steps": 181800, "loss": 0.0062, "lr": 7.52577834177603e-06, "epoch": 15.434543454345434, "percentage": 77.17, "elapsed_time": "5:32:15", "remaining_time": "1:38:16", "throughput": 1485.24, "total_tokens": 29608480} {"current_steps": 140305, "total_steps": 181800, "loss": 0.152, "lr": 7.524062008832153e-06, "epoch": 15.435093509350935, "percentage": 77.18, "elapsed_time": "5:32:15", "remaining_time": "1:38:16", "throughput": 1485.24, "total_tokens": 29609504} {"current_steps": 140310, "total_steps": 181800, "loss": 0.0008, "lr": 7.5223458369556215e-06, "epoch": 15.435643564356436, "percentage": 77.18, "elapsed_time": "5:32:16", "remaining_time": "1:38:15", "throughput": 1485.24, "total_tokens": 29610624} {"current_steps": 140315, "total_steps": 181800, "loss": 0.0072, "lr": 7.520629826162234e-06, "epoch": 15.436193619361935, "percentage": 77.18, "elapsed_time": "5:32:17", "remaining_time": "1:38:14", "throughput": 1485.24, "total_tokens": 29611616} {"current_steps": 140320, "total_steps": 181800, "loss": 0.0006, "lr": 7.5189139764678205e-06, "epoch": 15.436743674367436, "percentage": 77.18, "elapsed_time": "5:32:17", "remaining_time": "1:38:13", "throughput": 1485.24, "total_tokens": 29612640} {"current_steps": 140325, "total_steps": 181800, "loss": 0.1229, "lr": 7.517198287888189e-06, "epoch": 15.437293729372938, "percentage": 77.19, "elapsed_time": "5:32:18", "remaining_time": "1:38:13", "throughput": 1485.24, "total_tokens": 29613728} {"current_steps": 140330, "total_steps": 181800, "loss": 0.0036, "lr": 7.515482760439144e-06, "epoch": 15.437843784378439, "percentage": 77.19, "elapsed_time": "5:32:19", "remaining_time": "1:38:12", "throughput": 1485.25, "total_tokens": 29614784} {"current_steps": 140335, "total_steps": 181800, "loss": 0.0903, "lr": 7.513767394136504e-06, "epoch": 15.438393839383938, "percentage": 77.19, "elapsed_time": "5:32:20", "remaining_time": "1:38:11", "throughput": 1485.25, "total_tokens": 29615808} {"current_steps": 140340, "total_steps": 181800, "loss": 0.0083, "lr": 7.512052188996086e-06, "epoch": 15.438943894389439, "percentage": 77.19, "elapsed_time": "5:32:20", "remaining_time": "1:38:10", "throughput": 1485.25, "total_tokens": 29616928} {"current_steps": 140345, "total_steps": 181800, "loss": 0.0064, "lr": 7.510337145033686e-06, "epoch": 15.43949394939494, "percentage": 77.2, "elapsed_time": "5:32:21", "remaining_time": "1:38:10", "throughput": 1485.26, "total_tokens": 29618080} {"current_steps": 140350, "total_steps": 181800, "loss": 0.0278, "lr": 7.508622262265122e-06, "epoch": 15.44004400440044, "percentage": 77.2, "elapsed_time": "5:32:22", "remaining_time": "1:38:09", "throughput": 1485.26, "total_tokens": 29619168} {"current_steps": 140355, "total_steps": 181800, "loss": 0.1098, "lr": 7.506907540706187e-06, "epoch": 15.44059405940594, "percentage": 77.2, "elapsed_time": "5:32:22", "remaining_time": "1:38:08", "throughput": 1485.26, "total_tokens": 29620160} {"current_steps": 140360, "total_steps": 181800, "loss": 0.0302, "lr": 7.505192980372691e-06, "epoch": 15.441144114411442, "percentage": 77.21, "elapsed_time": "5:32:23", "remaining_time": "1:38:08", "throughput": 1485.26, "total_tokens": 29621184} {"current_steps": 140365, "total_steps": 181800, "loss": 0.0018, "lr": 7.503478581280443e-06, "epoch": 15.441694169416941, "percentage": 77.21, "elapsed_time": "5:32:24", "remaining_time": "1:38:07", "throughput": 1485.26, "total_tokens": 29622208} {"current_steps": 140370, "total_steps": 181800, "loss": 0.0034, "lr": 7.501764343445231e-06, "epoch": 15.442244224422442, "percentage": 77.21, "elapsed_time": "5:32:24", "remaining_time": "1:38:06", "throughput": 1485.26, "total_tokens": 29623232} {"current_steps": 140375, "total_steps": 181800, "loss": 0.1, "lr": 7.5000502668828686e-06, "epoch": 15.442794279427943, "percentage": 77.21, "elapsed_time": "5:32:25", "remaining_time": "1:38:05", "throughput": 1485.26, "total_tokens": 29624320} {"current_steps": 140380, "total_steps": 181800, "loss": 0.0011, "lr": 7.498336351609136e-06, "epoch": 15.443344334433444, "percentage": 77.22, "elapsed_time": "5:32:26", "remaining_time": "1:38:05", "throughput": 1485.26, "total_tokens": 29625376} {"current_steps": 140385, "total_steps": 181800, "loss": 0.0017, "lr": 7.496622597639849e-06, "epoch": 15.443894389438944, "percentage": 77.22, "elapsed_time": "5:32:26", "remaining_time": "1:38:04", "throughput": 1485.27, "total_tokens": 29626496} {"current_steps": 140390, "total_steps": 181800, "loss": 0.0019, "lr": 7.4949090049907855e-06, "epoch": 15.444444444444445, "percentage": 77.22, "elapsed_time": "5:32:27", "remaining_time": "1:38:03", "throughput": 1485.27, "total_tokens": 29627520} {"current_steps": 140395, "total_steps": 181800, "loss": 0.0026, "lr": 7.4931955736777446e-06, "epoch": 15.444994499449946, "percentage": 77.22, "elapsed_time": "5:32:28", "remaining_time": "1:38:03", "throughput": 1485.27, "total_tokens": 29628576} {"current_steps": 140400, "total_steps": 181800, "loss": 0.0116, "lr": 7.491482303716526e-06, "epoch": 15.445544554455445, "percentage": 77.23, "elapsed_time": "5:32:28", "remaining_time": "1:38:02", "throughput": 1485.27, "total_tokens": 29629632} {"current_steps": 140405, "total_steps": 181800, "loss": 0.0113, "lr": 7.489769195122906e-06, "epoch": 15.446094609460946, "percentage": 77.23, "elapsed_time": "5:32:29", "remaining_time": "1:38:01", "throughput": 1485.27, "total_tokens": 29630688} {"current_steps": 140410, "total_steps": 181800, "loss": 0.0138, "lr": 7.48805624791269e-06, "epoch": 15.446644664466447, "percentage": 77.23, "elapsed_time": "5:32:30", "remaining_time": "1:38:00", "throughput": 1485.27, "total_tokens": 29631712} {"current_steps": 140415, "total_steps": 181800, "loss": 0.1024, "lr": 7.48634346210165e-06, "epoch": 15.447194719471947, "percentage": 77.24, "elapsed_time": "5:32:31", "remaining_time": "1:38:00", "throughput": 1485.28, "total_tokens": 29632768} {"current_steps": 140420, "total_steps": 181800, "loss": 0.004, "lr": 7.484630837705575e-06, "epoch": 15.447744774477448, "percentage": 77.24, "elapsed_time": "5:32:31", "remaining_time": "1:37:59", "throughput": 1485.28, "total_tokens": 29633824} {"current_steps": 140425, "total_steps": 181800, "loss": 0.0028, "lr": 7.4829183747402635e-06, "epoch": 15.448294829482949, "percentage": 77.24, "elapsed_time": "5:32:32", "remaining_time": "1:37:58", "throughput": 1485.28, "total_tokens": 29634848} {"current_steps": 140430, "total_steps": 181800, "loss": 0.0022, "lr": 7.481206073221478e-06, "epoch": 15.448844884488448, "percentage": 77.24, "elapsed_time": "5:32:33", "remaining_time": "1:37:58", "throughput": 1485.27, "total_tokens": 29635808} {"current_steps": 140435, "total_steps": 181800, "loss": 0.0012, "lr": 7.479493933165019e-06, "epoch": 15.44939493949395, "percentage": 77.25, "elapsed_time": "5:32:33", "remaining_time": "1:37:57", "throughput": 1485.27, "total_tokens": 29636832} {"current_steps": 140440, "total_steps": 181800, "loss": 0.2175, "lr": 7.477781954586657e-06, "epoch": 15.44994499449945, "percentage": 77.25, "elapsed_time": "5:32:34", "remaining_time": "1:37:56", "throughput": 1485.28, "total_tokens": 29637888} {"current_steps": 140445, "total_steps": 181800, "loss": 0.0043, "lr": 7.476070137502164e-06, "epoch": 15.450495049504951, "percentage": 77.25, "elapsed_time": "5:32:35", "remaining_time": "1:37:55", "throughput": 1485.28, "total_tokens": 29638944} {"current_steps": 140450, "total_steps": 181800, "loss": 0.063, "lr": 7.474358481927321e-06, "epoch": 15.45104510451045, "percentage": 77.26, "elapsed_time": "5:32:35", "remaining_time": "1:37:55", "throughput": 1485.29, "total_tokens": 29640128} {"current_steps": 140455, "total_steps": 181800, "loss": 0.1148, "lr": 7.472646987877907e-06, "epoch": 15.451595159515952, "percentage": 77.26, "elapsed_time": "5:32:36", "remaining_time": "1:37:54", "throughput": 1485.29, "total_tokens": 29641216} {"current_steps": 140460, "total_steps": 181800, "loss": 0.0043, "lr": 7.470935655369704e-06, "epoch": 15.452145214521453, "percentage": 77.26, "elapsed_time": "5:32:37", "remaining_time": "1:37:53", "throughput": 1485.29, "total_tokens": 29642304} {"current_steps": 140465, "total_steps": 181800, "loss": 0.0058, "lr": 7.469224484418477e-06, "epoch": 15.452695269526952, "percentage": 77.26, "elapsed_time": "5:32:37", "remaining_time": "1:37:53", "throughput": 1485.29, "total_tokens": 29643360} {"current_steps": 140470, "total_steps": 181800, "loss": 0.2187, "lr": 7.467513475039986e-06, "epoch": 15.453245324532453, "percentage": 77.27, "elapsed_time": "5:32:38", "remaining_time": "1:37:52", "throughput": 1485.3, "total_tokens": 29644416} {"current_steps": 140475, "total_steps": 181800, "loss": 0.0066, "lr": 7.465802627250013e-06, "epoch": 15.453795379537954, "percentage": 77.27, "elapsed_time": "5:32:39", "remaining_time": "1:37:51", "throughput": 1485.3, "total_tokens": 29645440} {"current_steps": 140480, "total_steps": 181800, "loss": 0.038, "lr": 7.464091941064322e-06, "epoch": 15.454345434543454, "percentage": 77.27, "elapsed_time": "5:32:39", "remaining_time": "1:37:50", "throughput": 1485.3, "total_tokens": 29646496} {"current_steps": 140485, "total_steps": 181800, "loss": 0.0875, "lr": 7.4623814164986875e-06, "epoch": 15.454895489548955, "percentage": 77.27, "elapsed_time": "5:32:40", "remaining_time": "1:37:50", "throughput": 1485.3, "total_tokens": 29647488} {"current_steps": 140490, "total_steps": 181800, "loss": 0.0197, "lr": 7.4606710535688685e-06, "epoch": 15.455445544554456, "percentage": 77.28, "elapsed_time": "5:32:41", "remaining_time": "1:37:49", "throughput": 1485.29, "total_tokens": 29648480} {"current_steps": 140495, "total_steps": 181800, "loss": 0.0229, "lr": 7.458960852290622e-06, "epoch": 15.455995599559955, "percentage": 77.28, "elapsed_time": "5:32:42", "remaining_time": "1:37:48", "throughput": 1485.3, "total_tokens": 29649536} {"current_steps": 140500, "total_steps": 181800, "loss": 0.0611, "lr": 7.457250812679722e-06, "epoch": 15.456545654565456, "percentage": 77.28, "elapsed_time": "5:32:42", "remaining_time": "1:37:48", "throughput": 1485.3, "total_tokens": 29650624} {"current_steps": 140505, "total_steps": 181800, "loss": 0.0061, "lr": 7.4555409347519176e-06, "epoch": 15.457095709570957, "percentage": 77.29, "elapsed_time": "5:32:43", "remaining_time": "1:37:47", "throughput": 1485.3, "total_tokens": 29651616} {"current_steps": 140510, "total_steps": 181800, "loss": 0.0062, "lr": 7.453831218522972e-06, "epoch": 15.457645764576458, "percentage": 77.29, "elapsed_time": "5:32:44", "remaining_time": "1:37:46", "throughput": 1485.3, "total_tokens": 29652672} {"current_steps": 140515, "total_steps": 181800, "loss": 0.0035, "lr": 7.452121664008654e-06, "epoch": 15.458195819581958, "percentage": 77.29, "elapsed_time": "5:32:44", "remaining_time": "1:37:45", "throughput": 1485.3, "total_tokens": 29653696} {"current_steps": 140520, "total_steps": 181800, "loss": 0.0024, "lr": 7.450412271224702e-06, "epoch": 15.458745874587459, "percentage": 77.29, "elapsed_time": "5:32:45", "remaining_time": "1:37:45", "throughput": 1485.3, "total_tokens": 29654688} {"current_steps": 140525, "total_steps": 181800, "loss": 0.0091, "lr": 7.4487030401868855e-06, "epoch": 15.45929592959296, "percentage": 77.3, "elapsed_time": "5:32:46", "remaining_time": "1:37:44", "throughput": 1485.3, "total_tokens": 29655840} {"current_steps": 140530, "total_steps": 181800, "loss": 0.0187, "lr": 7.446993970910946e-06, "epoch": 15.45984598459846, "percentage": 77.3, "elapsed_time": "5:32:46", "remaining_time": "1:37:43", "throughput": 1485.31, "total_tokens": 29656896} {"current_steps": 140535, "total_steps": 181800, "loss": 0.0775, "lr": 7.445285063412638e-06, "epoch": 15.46039603960396, "percentage": 77.3, "elapsed_time": "5:32:47", "remaining_time": "1:37:43", "throughput": 1485.31, "total_tokens": 29657952} {"current_steps": 140540, "total_steps": 181800, "loss": 0.0019, "lr": 7.443576317707724e-06, "epoch": 15.460946094609461, "percentage": 77.3, "elapsed_time": "5:32:48", "remaining_time": "1:37:42", "throughput": 1485.31, "total_tokens": 29659008} {"current_steps": 140545, "total_steps": 181800, "loss": 0.1014, "lr": 7.441867733811933e-06, "epoch": 15.46149614961496, "percentage": 77.31, "elapsed_time": "5:32:48", "remaining_time": "1:37:41", "throughput": 1485.31, "total_tokens": 29660032} {"current_steps": 140550, "total_steps": 181800, "loss": 0.0134, "lr": 7.440159311741029e-06, "epoch": 15.462046204620462, "percentage": 77.31, "elapsed_time": "5:32:49", "remaining_time": "1:37:40", "throughput": 1485.32, "total_tokens": 29661184} {"current_steps": 140555, "total_steps": 181800, "loss": 0.1282, "lr": 7.438451051510753e-06, "epoch": 15.462596259625963, "percentage": 77.31, "elapsed_time": "5:32:50", "remaining_time": "1:37:40", "throughput": 1485.32, "total_tokens": 29662240} {"current_steps": 140560, "total_steps": 181800, "loss": 0.0192, "lr": 7.436742953136835e-06, "epoch": 15.463146314631462, "percentage": 77.32, "elapsed_time": "5:32:51", "remaining_time": "1:37:39", "throughput": 1485.32, "total_tokens": 29663264} {"current_steps": 140565, "total_steps": 181800, "loss": 0.0017, "lr": 7.435035016635033e-06, "epoch": 15.463696369636963, "percentage": 77.32, "elapsed_time": "5:32:51", "remaining_time": "1:37:38", "throughput": 1485.32, "total_tokens": 29664256} {"current_steps": 140570, "total_steps": 181800, "loss": 0.1132, "lr": 7.433327242021085e-06, "epoch": 15.464246424642464, "percentage": 77.32, "elapsed_time": "5:32:52", "remaining_time": "1:37:38", "throughput": 1485.32, "total_tokens": 29665344} {"current_steps": 140575, "total_steps": 181800, "loss": 0.0101, "lr": 7.4316196293107375e-06, "epoch": 15.464796479647966, "percentage": 77.32, "elapsed_time": "5:32:53", "remaining_time": "1:37:37", "throughput": 1485.32, "total_tokens": 29666368} {"current_steps": 140580, "total_steps": 181800, "loss": 0.0117, "lr": 7.429912178519721e-06, "epoch": 15.465346534653465, "percentage": 77.33, "elapsed_time": "5:32:53", "remaining_time": "1:37:36", "throughput": 1485.32, "total_tokens": 29667392} {"current_steps": 140585, "total_steps": 181800, "loss": 0.0264, "lr": 7.428204889663768e-06, "epoch": 15.465896589658966, "percentage": 77.33, "elapsed_time": "5:32:54", "remaining_time": "1:37:35", "throughput": 1485.32, "total_tokens": 29668416} {"current_steps": 140590, "total_steps": 181800, "loss": 0.0229, "lr": 7.426497762758614e-06, "epoch": 15.466446644664467, "percentage": 77.33, "elapsed_time": "5:32:55", "remaining_time": "1:37:35", "throughput": 1485.32, "total_tokens": 29669472} {"current_steps": 140595, "total_steps": 181800, "loss": 0.089, "lr": 7.42479079782e-06, "epoch": 15.466996699669966, "percentage": 77.33, "elapsed_time": "5:32:55", "remaining_time": "1:37:34", "throughput": 1485.32, "total_tokens": 29670528} {"current_steps": 140600, "total_steps": 181800, "loss": 0.0771, "lr": 7.423083994863664e-06, "epoch": 15.467546754675467, "percentage": 77.34, "elapsed_time": "5:32:56", "remaining_time": "1:37:33", "throughput": 1485.32, "total_tokens": 29671520} {"current_steps": 140605, "total_steps": 181800, "loss": 0.004, "lr": 7.421377353905329e-06, "epoch": 15.468096809680969, "percentage": 77.34, "elapsed_time": "5:32:57", "remaining_time": "1:37:33", "throughput": 1485.32, "total_tokens": 29672608} {"current_steps": 140610, "total_steps": 181800, "loss": 0.0422, "lr": 7.419670874960716e-06, "epoch": 15.468646864686468, "percentage": 77.34, "elapsed_time": "5:32:57", "remaining_time": "1:37:32", "throughput": 1485.33, "total_tokens": 29673696} {"current_steps": 140615, "total_steps": 181800, "loss": 0.0244, "lr": 7.417964558045567e-06, "epoch": 15.469196919691969, "percentage": 77.35, "elapsed_time": "5:32:58", "remaining_time": "1:37:31", "throughput": 1485.32, "total_tokens": 29674688} {"current_steps": 140620, "total_steps": 181800, "loss": 0.0299, "lr": 7.416258403175594e-06, "epoch": 15.46974697469747, "percentage": 77.35, "elapsed_time": "5:32:59", "remaining_time": "1:37:30", "throughput": 1485.33, "total_tokens": 29675808} {"current_steps": 140625, "total_steps": 181800, "loss": 0.0349, "lr": 7.414552410366532e-06, "epoch": 15.47029702970297, "percentage": 77.35, "elapsed_time": "5:32:59", "remaining_time": "1:37:30", "throughput": 1485.33, "total_tokens": 29676896} {"current_steps": 140630, "total_steps": 181800, "loss": 0.0042, "lr": 7.4128465796341084e-06, "epoch": 15.47084708470847, "percentage": 77.35, "elapsed_time": "5:33:00", "remaining_time": "1:37:29", "throughput": 1485.33, "total_tokens": 29677952} {"current_steps": 140635, "total_steps": 181800, "loss": 0.0009, "lr": 7.411140910994033e-06, "epoch": 15.471397139713972, "percentage": 77.36, "elapsed_time": "5:33:01", "remaining_time": "1:37:28", "throughput": 1485.33, "total_tokens": 29678976} {"current_steps": 140640, "total_steps": 181800, "loss": 0.0019, "lr": 7.409435404462037e-06, "epoch": 15.471947194719473, "percentage": 77.36, "elapsed_time": "5:33:02", "remaining_time": "1:37:27", "throughput": 1485.33, "total_tokens": 29680000} {"current_steps": 140645, "total_steps": 181800, "loss": 0.0591, "lr": 7.407730060053828e-06, "epoch": 15.472497249724972, "percentage": 77.36, "elapsed_time": "5:33:02", "remaining_time": "1:37:27", "throughput": 1485.34, "total_tokens": 29681120} {"current_steps": 140650, "total_steps": 181800, "loss": 0.004, "lr": 7.406024877785128e-06, "epoch": 15.473047304730473, "percentage": 77.37, "elapsed_time": "5:33:03", "remaining_time": "1:37:26", "throughput": 1485.34, "total_tokens": 29682208} {"current_steps": 140655, "total_steps": 181800, "loss": 0.0059, "lr": 7.404319857671662e-06, "epoch": 15.473597359735974, "percentage": 77.37, "elapsed_time": "5:33:04", "remaining_time": "1:37:25", "throughput": 1485.34, "total_tokens": 29683232} {"current_steps": 140660, "total_steps": 181800, "loss": 0.0846, "lr": 7.402614999729129e-06, "epoch": 15.474147414741473, "percentage": 77.37, "elapsed_time": "5:33:04", "remaining_time": "1:37:25", "throughput": 1485.35, "total_tokens": 29684320} {"current_steps": 140665, "total_steps": 181800, "loss": 0.0705, "lr": 7.40091030397326e-06, "epoch": 15.474697469746975, "percentage": 77.37, "elapsed_time": "5:33:05", "remaining_time": "1:37:24", "throughput": 1485.35, "total_tokens": 29685344} {"current_steps": 140670, "total_steps": 181800, "loss": 0.0057, "lr": 7.399205770419745e-06, "epoch": 15.475247524752476, "percentage": 77.38, "elapsed_time": "5:33:06", "remaining_time": "1:37:23", "throughput": 1485.34, "total_tokens": 29686336} {"current_steps": 140675, "total_steps": 181800, "loss": 0.012, "lr": 7.397501399084314e-06, "epoch": 15.475797579757975, "percentage": 77.38, "elapsed_time": "5:33:06", "remaining_time": "1:37:22", "throughput": 1485.35, "total_tokens": 29687424} {"current_steps": 140680, "total_steps": 181800, "loss": 0.095, "lr": 7.395797189982656e-06, "epoch": 15.476347634763476, "percentage": 77.38, "elapsed_time": "5:33:07", "remaining_time": "1:37:22", "throughput": 1485.35, "total_tokens": 29688416} {"current_steps": 140685, "total_steps": 181800, "loss": 0.013, "lr": 7.39409314313049e-06, "epoch": 15.476897689768977, "percentage": 77.38, "elapsed_time": "5:33:08", "remaining_time": "1:37:21", "throughput": 1485.35, "total_tokens": 29689440} {"current_steps": 140690, "total_steps": 181800, "loss": 0.0315, "lr": 7.392389258543528e-06, "epoch": 15.477447744774478, "percentage": 77.39, "elapsed_time": "5:33:08", "remaining_time": "1:37:20", "throughput": 1485.34, "total_tokens": 29690432} {"current_steps": 140695, "total_steps": 181800, "loss": 0.0426, "lr": 7.3906855362374575e-06, "epoch": 15.477997799779978, "percentage": 77.39, "elapsed_time": "5:33:09", "remaining_time": "1:37:20", "throughput": 1485.34, "total_tokens": 29691456} {"current_steps": 140700, "total_steps": 181800, "loss": 0.0102, "lr": 7.388981976227993e-06, "epoch": 15.478547854785479, "percentage": 77.39, "elapsed_time": "5:33:10", "remaining_time": "1:37:19", "throughput": 1485.35, "total_tokens": 29692544} {"current_steps": 140705, "total_steps": 181800, "loss": 0.0041, "lr": 7.387278578530834e-06, "epoch": 15.47909790979098, "percentage": 77.4, "elapsed_time": "5:33:11", "remaining_time": "1:37:18", "throughput": 1485.34, "total_tokens": 29693536} {"current_steps": 140710, "total_steps": 181800, "loss": 0.0052, "lr": 7.3855753431616606e-06, "epoch": 15.479647964796479, "percentage": 77.4, "elapsed_time": "5:33:11", "remaining_time": "1:37:17", "throughput": 1485.34, "total_tokens": 29694560} {"current_steps": 140715, "total_steps": 181800, "loss": 0.0089, "lr": 7.383872270136205e-06, "epoch": 15.48019801980198, "percentage": 77.4, "elapsed_time": "5:33:12", "remaining_time": "1:37:17", "throughput": 1485.34, "total_tokens": 29695520} {"current_steps": 140720, "total_steps": 181800, "loss": 0.046, "lr": 7.382169359470134e-06, "epoch": 15.480748074807481, "percentage": 77.4, "elapsed_time": "5:33:13", "remaining_time": "1:37:16", "throughput": 1485.34, "total_tokens": 29696512} {"current_steps": 140725, "total_steps": 181800, "loss": 0.0032, "lr": 7.380466611179165e-06, "epoch": 15.48129812981298, "percentage": 77.41, "elapsed_time": "5:33:13", "remaining_time": "1:37:15", "throughput": 1485.34, "total_tokens": 29697504} {"current_steps": 140730, "total_steps": 181800, "loss": 0.0156, "lr": 7.378764025278978e-06, "epoch": 15.481848184818482, "percentage": 77.41, "elapsed_time": "5:33:14", "remaining_time": "1:37:15", "throughput": 1485.34, "total_tokens": 29698528} {"current_steps": 140735, "total_steps": 181800, "loss": 0.0422, "lr": 7.377061601785262e-06, "epoch": 15.482398239823983, "percentage": 77.41, "elapsed_time": "5:33:15", "remaining_time": "1:37:14", "throughput": 1485.34, "total_tokens": 29699584} {"current_steps": 140740, "total_steps": 181800, "loss": 0.114, "lr": 7.375359340713711e-06, "epoch": 15.482948294829482, "percentage": 77.41, "elapsed_time": "5:33:15", "remaining_time": "1:37:13", "throughput": 1485.34, "total_tokens": 29700640} {"current_steps": 140745, "total_steps": 181800, "loss": 0.0052, "lr": 7.373657242080023e-06, "epoch": 15.483498349834983, "percentage": 77.42, "elapsed_time": "5:33:16", "remaining_time": "1:37:12", "throughput": 1485.34, "total_tokens": 29701696} {"current_steps": 140750, "total_steps": 181800, "loss": 0.1336, "lr": 7.3719553058998716e-06, "epoch": 15.484048404840484, "percentage": 77.42, "elapsed_time": "5:33:17", "remaining_time": "1:37:12", "throughput": 1485.34, "total_tokens": 29702720} {"current_steps": 140755, "total_steps": 181800, "loss": 0.1965, "lr": 7.370253532188959e-06, "epoch": 15.484598459845985, "percentage": 77.42, "elapsed_time": "5:33:17", "remaining_time": "1:37:11", "throughput": 1485.34, "total_tokens": 29703776} {"current_steps": 140760, "total_steps": 181800, "loss": 0.0748, "lr": 7.368551920962951e-06, "epoch": 15.485148514851485, "percentage": 77.43, "elapsed_time": "5:33:18", "remaining_time": "1:37:10", "throughput": 1485.34, "total_tokens": 29704800} {"current_steps": 140765, "total_steps": 181800, "loss": 0.0809, "lr": 7.366850472237538e-06, "epoch": 15.485698569856986, "percentage": 77.43, "elapsed_time": "5:33:19", "remaining_time": "1:37:10", "throughput": 1485.35, "total_tokens": 29705984} {"current_steps": 140770, "total_steps": 181800, "loss": 0.0134, "lr": 7.365149186028414e-06, "epoch": 15.486248624862487, "percentage": 77.43, "elapsed_time": "5:33:19", "remaining_time": "1:37:09", "throughput": 1485.35, "total_tokens": 29707072} {"current_steps": 140775, "total_steps": 181800, "loss": 0.0036, "lr": 7.3634480623512355e-06, "epoch": 15.486798679867986, "percentage": 77.43, "elapsed_time": "5:33:20", "remaining_time": "1:37:08", "throughput": 1485.35, "total_tokens": 29708096} {"current_steps": 140780, "total_steps": 181800, "loss": 0.0153, "lr": 7.361747101221706e-06, "epoch": 15.487348734873487, "percentage": 77.44, "elapsed_time": "5:33:21", "remaining_time": "1:37:07", "throughput": 1485.35, "total_tokens": 29709120} {"current_steps": 140785, "total_steps": 181800, "loss": 0.0019, "lr": 7.360046302655479e-06, "epoch": 15.487898789878988, "percentage": 77.44, "elapsed_time": "5:33:22", "remaining_time": "1:37:07", "throughput": 1485.36, "total_tokens": 29710208} {"current_steps": 140790, "total_steps": 181800, "loss": 0.008, "lr": 7.358345666668249e-06, "epoch": 15.488448844884488, "percentage": 77.44, "elapsed_time": "5:33:22", "remaining_time": "1:37:06", "throughput": 1485.36, "total_tokens": 29711328} {"current_steps": 140795, "total_steps": 181800, "loss": 0.0046, "lr": 7.3566451932756744e-06, "epoch": 15.488998899889989, "percentage": 77.44, "elapsed_time": "5:33:23", "remaining_time": "1:37:05", "throughput": 1485.36, "total_tokens": 29712352} {"current_steps": 140800, "total_steps": 181800, "loss": 0.0021, "lr": 7.354944882493436e-06, "epoch": 15.48954895489549, "percentage": 77.45, "elapsed_time": "5:33:24", "remaining_time": "1:37:05", "throughput": 1485.36, "total_tokens": 29713440} {"current_steps": 140805, "total_steps": 181800, "loss": 0.0061, "lr": 7.353244734337209e-06, "epoch": 15.490099009900991, "percentage": 77.45, "elapsed_time": "5:33:24", "remaining_time": "1:37:04", "throughput": 1485.37, "total_tokens": 29714496} {"current_steps": 140810, "total_steps": 181800, "loss": 0.093, "lr": 7.351544748822653e-06, "epoch": 15.49064906490649, "percentage": 77.45, "elapsed_time": "5:33:25", "remaining_time": "1:37:03", "throughput": 1485.37, "total_tokens": 29715584} {"current_steps": 140815, "total_steps": 181800, "loss": 0.0022, "lr": 7.349844925965446e-06, "epoch": 15.491199119911991, "percentage": 77.46, "elapsed_time": "5:33:26", "remaining_time": "1:37:02", "throughput": 1485.38, "total_tokens": 29716736} {"current_steps": 140820, "total_steps": 181800, "loss": 0.0482, "lr": 7.3481452657812475e-06, "epoch": 15.491749174917492, "percentage": 77.46, "elapsed_time": "5:33:26", "remaining_time": "1:37:02", "throughput": 1485.38, "total_tokens": 29717792} {"current_steps": 140825, "total_steps": 181800, "loss": 0.0086, "lr": 7.3464457682857115e-06, "epoch": 15.492299229922992, "percentage": 77.46, "elapsed_time": "5:33:27", "remaining_time": "1:37:01", "throughput": 1485.38, "total_tokens": 29718880} {"current_steps": 140830, "total_steps": 181800, "loss": 0.073, "lr": 7.344746433494529e-06, "epoch": 15.492849284928493, "percentage": 77.46, "elapsed_time": "5:33:28", "remaining_time": "1:37:00", "throughput": 1485.38, "total_tokens": 29719904} {"current_steps": 140835, "total_steps": 181800, "loss": 0.0018, "lr": 7.343047261423336e-06, "epoch": 15.493399339933994, "percentage": 77.47, "elapsed_time": "5:33:28", "remaining_time": "1:37:00", "throughput": 1485.38, "total_tokens": 29720928} {"current_steps": 140840, "total_steps": 181800, "loss": 0.0009, "lr": 7.341348252087815e-06, "epoch": 15.493949394939493, "percentage": 77.47, "elapsed_time": "5:33:29", "remaining_time": "1:36:59", "throughput": 1485.38, "total_tokens": 29722016} {"current_steps": 140845, "total_steps": 181800, "loss": 0.0479, "lr": 7.339649405503612e-06, "epoch": 15.494499449944994, "percentage": 77.47, "elapsed_time": "5:33:30", "remaining_time": "1:36:58", "throughput": 1485.38, "total_tokens": 29723040} {"current_steps": 140850, "total_steps": 181800, "loss": 0.0461, "lr": 7.337950721686379e-06, "epoch": 15.495049504950495, "percentage": 77.48, "elapsed_time": "5:33:31", "remaining_time": "1:36:57", "throughput": 1485.39, "total_tokens": 29724160} {"current_steps": 140855, "total_steps": 181800, "loss": 0.0324, "lr": 7.336252200651777e-06, "epoch": 15.495599559955995, "percentage": 77.48, "elapsed_time": "5:33:31", "remaining_time": "1:36:57", "throughput": 1485.39, "total_tokens": 29725248} {"current_steps": 140860, "total_steps": 181800, "loss": 0.0047, "lr": 7.334553842415465e-06, "epoch": 15.496149614961496, "percentage": 77.48, "elapsed_time": "5:33:32", "remaining_time": "1:36:56", "throughput": 1485.39, "total_tokens": 29726368} {"current_steps": 140865, "total_steps": 181800, "loss": 0.0106, "lr": 7.3328556469931e-06, "epoch": 15.496699669966997, "percentage": 77.48, "elapsed_time": "5:33:33", "remaining_time": "1:36:55", "throughput": 1485.39, "total_tokens": 29727392} {"current_steps": 140870, "total_steps": 181800, "loss": 0.003, "lr": 7.331157614400331e-06, "epoch": 15.497249724972498, "percentage": 77.49, "elapsed_time": "5:33:33", "remaining_time": "1:36:55", "throughput": 1485.4, "total_tokens": 29728480} {"current_steps": 140875, "total_steps": 181800, "loss": 0.0672, "lr": 7.329459744652792e-06, "epoch": 15.497799779977997, "percentage": 77.49, "elapsed_time": "5:33:34", "remaining_time": "1:36:54", "throughput": 1485.4, "total_tokens": 29729536} {"current_steps": 140880, "total_steps": 181800, "loss": 0.0018, "lr": 7.32776203776615e-06, "epoch": 15.498349834983498, "percentage": 77.49, "elapsed_time": "5:33:35", "remaining_time": "1:36:53", "throughput": 1485.4, "total_tokens": 29730560} {"current_steps": 140885, "total_steps": 181800, "loss": 0.043, "lr": 7.326064493756033e-06, "epoch": 15.498899889989, "percentage": 77.49, "elapsed_time": "5:33:35", "remaining_time": "1:36:52", "throughput": 1485.4, "total_tokens": 29731648} {"current_steps": 140890, "total_steps": 181800, "loss": 0.0204, "lr": 7.324367112638114e-06, "epoch": 15.499449944994499, "percentage": 77.5, "elapsed_time": "5:33:36", "remaining_time": "1:36:52", "throughput": 1485.4, "total_tokens": 29732704} {"current_steps": 140895, "total_steps": 181800, "loss": 0.0034, "lr": 7.322669894428019e-06, "epoch": 15.5, "percentage": 77.5, "elapsed_time": "5:33:37", "remaining_time": "1:36:51", "throughput": 1485.41, "total_tokens": 29733792} {"current_steps": 140900, "total_steps": 181800, "loss": 0.0033, "lr": 7.320972839141388e-06, "epoch": 15.500550055005501, "percentage": 77.5, "elapsed_time": "5:33:37", "remaining_time": "1:36:50", "throughput": 1485.4, "total_tokens": 29734784} {"current_steps": 140905, "total_steps": 181800, "loss": 0.0019, "lr": 7.319275946793874e-06, "epoch": 15.501100110011, "percentage": 77.51, "elapsed_time": "5:33:38", "remaining_time": "1:36:50", "throughput": 1485.4, "total_tokens": 29735808} {"current_steps": 140910, "total_steps": 181800, "loss": 0.0031, "lr": 7.317579217401102e-06, "epoch": 15.501650165016502, "percentage": 77.51, "elapsed_time": "5:33:39", "remaining_time": "1:36:49", "throughput": 1485.4, "total_tokens": 29736832} {"current_steps": 140915, "total_steps": 181800, "loss": 0.0078, "lr": 7.315882650978717e-06, "epoch": 15.502200220022003, "percentage": 77.51, "elapsed_time": "5:33:40", "remaining_time": "1:36:48", "throughput": 1485.4, "total_tokens": 29737824} {"current_steps": 140920, "total_steps": 181800, "loss": 0.0162, "lr": 7.314186247542365e-06, "epoch": 15.502750275027502, "percentage": 77.51, "elapsed_time": "5:33:40", "remaining_time": "1:36:47", "throughput": 1485.4, "total_tokens": 29738912} {"current_steps": 140925, "total_steps": 181800, "loss": 0.0901, "lr": 7.312490007107664e-06, "epoch": 15.503300330033003, "percentage": 77.52, "elapsed_time": "5:33:41", "remaining_time": "1:36:47", "throughput": 1485.41, "total_tokens": 29740000} {"current_steps": 140930, "total_steps": 181800, "loss": 0.0032, "lr": 7.310793929690263e-06, "epoch": 15.503850385038504, "percentage": 77.52, "elapsed_time": "5:33:42", "remaining_time": "1:36:46", "throughput": 1485.41, "total_tokens": 29741024} {"current_steps": 140935, "total_steps": 181800, "loss": 0.0015, "lr": 7.309098015305785e-06, "epoch": 15.504400440044005, "percentage": 77.52, "elapsed_time": "5:33:42", "remaining_time": "1:36:45", "throughput": 1485.41, "total_tokens": 29742080} {"current_steps": 140940, "total_steps": 181800, "loss": 0.0722, "lr": 7.3074022639698535e-06, "epoch": 15.504950495049505, "percentage": 77.52, "elapsed_time": "5:33:43", "remaining_time": "1:36:45", "throughput": 1485.41, "total_tokens": 29743168} {"current_steps": 140945, "total_steps": 181800, "loss": 0.0016, "lr": 7.305706675698107e-06, "epoch": 15.505500550055006, "percentage": 77.53, "elapsed_time": "5:33:44", "remaining_time": "1:36:44", "throughput": 1485.41, "total_tokens": 29744192} {"current_steps": 140950, "total_steps": 181800, "loss": 0.0815, "lr": 7.304011250506171e-06, "epoch": 15.506050605060507, "percentage": 77.53, "elapsed_time": "5:33:44", "remaining_time": "1:36:43", "throughput": 1485.42, "total_tokens": 29745312} {"current_steps": 140955, "total_steps": 181800, "loss": 0.0189, "lr": 7.3023159884096805e-06, "epoch": 15.506600660066006, "percentage": 77.53, "elapsed_time": "5:33:45", "remaining_time": "1:36:42", "throughput": 1485.42, "total_tokens": 29746336} {"current_steps": 140960, "total_steps": 181800, "loss": 0.0031, "lr": 7.300620889424251e-06, "epoch": 15.507150715071507, "percentage": 77.54, "elapsed_time": "5:33:46", "remaining_time": "1:36:42", "throughput": 1485.42, "total_tokens": 29747424} {"current_steps": 140965, "total_steps": 181800, "loss": 0.0597, "lr": 7.298925953565497e-06, "epoch": 15.507700770077008, "percentage": 77.54, "elapsed_time": "5:33:46", "remaining_time": "1:36:41", "throughput": 1485.42, "total_tokens": 29748448} {"current_steps": 140970, "total_steps": 181800, "loss": 0.1092, "lr": 7.297231180849048e-06, "epoch": 15.508250825082508, "percentage": 77.54, "elapsed_time": "5:33:47", "remaining_time": "1:36:40", "throughput": 1485.42, "total_tokens": 29749536} {"current_steps": 140975, "total_steps": 181800, "loss": 0.0027, "lr": 7.295536571290526e-06, "epoch": 15.508800880088009, "percentage": 77.54, "elapsed_time": "5:33:48", "remaining_time": "1:36:40", "throughput": 1485.43, "total_tokens": 29750624} {"current_steps": 140980, "total_steps": 181800, "loss": 0.056, "lr": 7.2938421249055564e-06, "epoch": 15.50935093509351, "percentage": 77.55, "elapsed_time": "5:33:49", "remaining_time": "1:36:39", "throughput": 1485.43, "total_tokens": 29751648} {"current_steps": 140985, "total_steps": 181800, "loss": 0.002, "lr": 7.292147841709749e-06, "epoch": 15.509900990099009, "percentage": 77.55, "elapsed_time": "5:33:49", "remaining_time": "1:36:38", "throughput": 1485.43, "total_tokens": 29752672} {"current_steps": 140990, "total_steps": 181800, "loss": 0.0038, "lr": 7.290453721718707e-06, "epoch": 15.51045104510451, "percentage": 77.55, "elapsed_time": "5:33:50", "remaining_time": "1:36:37", "throughput": 1485.43, "total_tokens": 29753760} {"current_steps": 140995, "total_steps": 181800, "loss": 0.0987, "lr": 7.288759764948063e-06, "epoch": 15.511001100110011, "percentage": 77.56, "elapsed_time": "5:33:51", "remaining_time": "1:36:37", "throughput": 1485.43, "total_tokens": 29754784} {"current_steps": 141000, "total_steps": 181800, "loss": 0.0052, "lr": 7.287065971413415e-06, "epoch": 15.511551155115512, "percentage": 77.56, "elapsed_time": "5:33:51", "remaining_time": "1:36:36", "throughput": 1485.43, "total_tokens": 29755840} {"current_steps": 141005, "total_steps": 181800, "loss": 0.0035, "lr": 7.285372341130381e-06, "epoch": 15.512101210121012, "percentage": 77.56, "elapsed_time": "5:33:52", "remaining_time": "1:36:35", "throughput": 1485.43, "total_tokens": 29756896} {"current_steps": 141010, "total_steps": 181800, "loss": 0.0054, "lr": 7.283678874114577e-06, "epoch": 15.512651265126513, "percentage": 77.56, "elapsed_time": "5:33:53", "remaining_time": "1:36:35", "throughput": 1485.43, "total_tokens": 29757984} {"current_steps": 141015, "total_steps": 181800, "loss": 0.0353, "lr": 7.281985570381597e-06, "epoch": 15.513201320132014, "percentage": 77.57, "elapsed_time": "5:33:53", "remaining_time": "1:36:34", "throughput": 1485.44, "total_tokens": 29759040} {"current_steps": 141020, "total_steps": 181800, "loss": 0.0401, "lr": 7.280292429947061e-06, "epoch": 15.513751375137513, "percentage": 77.57, "elapsed_time": "5:33:54", "remaining_time": "1:36:33", "throughput": 1485.44, "total_tokens": 29760064} {"current_steps": 141025, "total_steps": 181800, "loss": 0.0034, "lr": 7.278599452826557e-06, "epoch": 15.514301430143014, "percentage": 77.57, "elapsed_time": "5:33:55", "remaining_time": "1:36:32", "throughput": 1485.44, "total_tokens": 29761120} {"current_steps": 141030, "total_steps": 181800, "loss": 0.0403, "lr": 7.2769066390357e-06, "epoch": 15.514851485148515, "percentage": 77.57, "elapsed_time": "5:33:55", "remaining_time": "1:36:32", "throughput": 1485.44, "total_tokens": 29762240} {"current_steps": 141035, "total_steps": 181800, "loss": 0.0925, "lr": 7.275213988590099e-06, "epoch": 15.515401540154015, "percentage": 77.58, "elapsed_time": "5:33:56", "remaining_time": "1:36:31", "throughput": 1485.44, "total_tokens": 29763296} {"current_steps": 141040, "total_steps": 181800, "loss": 0.0044, "lr": 7.273521501505337e-06, "epoch": 15.515951595159516, "percentage": 77.58, "elapsed_time": "5:33:57", "remaining_time": "1:36:30", "throughput": 1485.44, "total_tokens": 29764320} {"current_steps": 141045, "total_steps": 181800, "loss": 0.1392, "lr": 7.271829177797029e-06, "epoch": 15.516501650165017, "percentage": 77.58, "elapsed_time": "5:33:58", "remaining_time": "1:36:29", "throughput": 1485.45, "total_tokens": 29765408} {"current_steps": 141050, "total_steps": 181800, "loss": 0.0052, "lr": 7.270137017480757e-06, "epoch": 15.517051705170516, "percentage": 77.59, "elapsed_time": "5:33:58", "remaining_time": "1:36:29", "throughput": 1485.45, "total_tokens": 29766432} {"current_steps": 141055, "total_steps": 181800, "loss": 0.0118, "lr": 7.268445020572132e-06, "epoch": 15.517601760176017, "percentage": 77.59, "elapsed_time": "5:33:59", "remaining_time": "1:36:28", "throughput": 1485.45, "total_tokens": 29767456} {"current_steps": 141060, "total_steps": 181800, "loss": 0.004, "lr": 7.266753187086733e-06, "epoch": 15.518151815181518, "percentage": 77.59, "elapsed_time": "5:34:00", "remaining_time": "1:36:27", "throughput": 1485.45, "total_tokens": 29768544} {"current_steps": 141065, "total_steps": 181800, "loss": 0.0077, "lr": 7.265061517040161e-06, "epoch": 15.51870187018702, "percentage": 77.59, "elapsed_time": "5:34:00", "remaining_time": "1:36:27", "throughput": 1485.45, "total_tokens": 29769600} {"current_steps": 141070, "total_steps": 181800, "loss": 0.0579, "lr": 7.263370010448014e-06, "epoch": 15.519251925192519, "percentage": 77.6, "elapsed_time": "5:34:01", "remaining_time": "1:36:26", "throughput": 1485.45, "total_tokens": 29770688} {"current_steps": 141075, "total_steps": 181800, "loss": 0.0012, "lr": 7.261678667325866e-06, "epoch": 15.51980198019802, "percentage": 77.6, "elapsed_time": "5:34:02", "remaining_time": "1:36:25", "throughput": 1485.45, "total_tokens": 29771712} {"current_steps": 141080, "total_steps": 181800, "loss": 0.0307, "lr": 7.259987487689324e-06, "epoch": 15.520352035203521, "percentage": 77.6, "elapsed_time": "5:34:02", "remaining_time": "1:36:24", "throughput": 1485.45, "total_tokens": 29772704} {"current_steps": 141085, "total_steps": 181800, "loss": 0.0262, "lr": 7.258296471553958e-06, "epoch": 15.52090209020902, "percentage": 77.6, "elapsed_time": "5:34:03", "remaining_time": "1:36:24", "throughput": 1485.45, "total_tokens": 29773760} {"current_steps": 141090, "total_steps": 181800, "loss": 0.0106, "lr": 7.256605618935358e-06, "epoch": 15.521452145214521, "percentage": 77.61, "elapsed_time": "5:34:04", "remaining_time": "1:36:23", "throughput": 1485.45, "total_tokens": 29774784} {"current_steps": 141095, "total_steps": 181800, "loss": 0.0146, "lr": 7.254914929849118e-06, "epoch": 15.522002200220022, "percentage": 77.61, "elapsed_time": "5:34:04", "remaining_time": "1:36:22", "throughput": 1485.46, "total_tokens": 29775872} {"current_steps": 141100, "total_steps": 181800, "loss": 0.1106, "lr": 7.253224404310805e-06, "epoch": 15.522552255225522, "percentage": 77.61, "elapsed_time": "5:34:05", "remaining_time": "1:36:22", "throughput": 1485.46, "total_tokens": 29776896} {"current_steps": 141105, "total_steps": 181800, "loss": 0.0034, "lr": 7.251534042336014e-06, "epoch": 15.523102310231023, "percentage": 77.62, "elapsed_time": "5:34:06", "remaining_time": "1:36:21", "throughput": 1485.46, "total_tokens": 29777984} {"current_steps": 141110, "total_steps": 181800, "loss": 0.0749, "lr": 7.249843843940315e-06, "epoch": 15.523652365236524, "percentage": 77.62, "elapsed_time": "5:34:07", "remaining_time": "1:36:20", "throughput": 1485.46, "total_tokens": 29779040} {"current_steps": 141115, "total_steps": 181800, "loss": 0.0075, "lr": 7.248153809139285e-06, "epoch": 15.524202420242025, "percentage": 77.62, "elapsed_time": "5:34:07", "remaining_time": "1:36:19", "throughput": 1485.46, "total_tokens": 29780096} {"current_steps": 141120, "total_steps": 181800, "loss": 0.1048, "lr": 7.2464639379485e-06, "epoch": 15.524752475247524, "percentage": 77.62, "elapsed_time": "5:34:08", "remaining_time": "1:36:19", "throughput": 1485.47, "total_tokens": 29781248} {"current_steps": 141125, "total_steps": 181800, "loss": 0.1009, "lr": 7.244774230383547e-06, "epoch": 15.525302530253025, "percentage": 77.63, "elapsed_time": "5:34:09", "remaining_time": "1:36:18", "throughput": 1485.47, "total_tokens": 29782272} {"current_steps": 141130, "total_steps": 181800, "loss": 0.087, "lr": 7.24308468645998e-06, "epoch": 15.525852585258527, "percentage": 77.63, "elapsed_time": "5:34:09", "remaining_time": "1:36:17", "throughput": 1485.47, "total_tokens": 29783232} {"current_steps": 141135, "total_steps": 181800, "loss": 0.0573, "lr": 7.241395306193391e-06, "epoch": 15.526402640264026, "percentage": 77.63, "elapsed_time": "5:34:10", "remaining_time": "1:36:17", "throughput": 1485.47, "total_tokens": 29784320} {"current_steps": 141140, "total_steps": 181800, "loss": 0.0394, "lr": 7.2397060895993324e-06, "epoch": 15.526952695269527, "percentage": 77.63, "elapsed_time": "5:34:11", "remaining_time": "1:36:16", "throughput": 1485.47, "total_tokens": 29785408} {"current_steps": 141145, "total_steps": 181800, "loss": 0.0063, "lr": 7.238017036693379e-06, "epoch": 15.527502750275028, "percentage": 77.64, "elapsed_time": "5:34:11", "remaining_time": "1:36:15", "throughput": 1485.47, "total_tokens": 29786496} {"current_steps": 141150, "total_steps": 181800, "loss": 0.0016, "lr": 7.236328147491109e-06, "epoch": 15.528052805280527, "percentage": 77.64, "elapsed_time": "5:34:12", "remaining_time": "1:36:14", "throughput": 1485.47, "total_tokens": 29787520} {"current_steps": 141155, "total_steps": 181800, "loss": 0.1623, "lr": 7.234639422008069e-06, "epoch": 15.528602860286028, "percentage": 77.64, "elapsed_time": "5:34:13", "remaining_time": "1:36:14", "throughput": 1485.48, "total_tokens": 29788608} {"current_steps": 141160, "total_steps": 181800, "loss": 0.1275, "lr": 7.2329508602598435e-06, "epoch": 15.52915291529153, "percentage": 77.65, "elapsed_time": "5:34:13", "remaining_time": "1:36:13", "throughput": 1485.48, "total_tokens": 29789664} {"current_steps": 141165, "total_steps": 181800, "loss": 0.0663, "lr": 7.231262462261973e-06, "epoch": 15.52970297029703, "percentage": 77.65, "elapsed_time": "5:34:14", "remaining_time": "1:36:12", "throughput": 1485.48, "total_tokens": 29790720} {"current_steps": 141170, "total_steps": 181800, "loss": 0.0676, "lr": 7.2295742280300395e-06, "epoch": 15.53025302530253, "percentage": 77.65, "elapsed_time": "5:34:15", "remaining_time": "1:36:12", "throughput": 1485.48, "total_tokens": 29791776} {"current_steps": 141175, "total_steps": 181800, "loss": 0.1094, "lr": 7.227886157579586e-06, "epoch": 15.530803080308031, "percentage": 77.65, "elapsed_time": "5:34:15", "remaining_time": "1:36:11", "throughput": 1485.48, "total_tokens": 29792832} {"current_steps": 141180, "total_steps": 181800, "loss": 0.0026, "lr": 7.226198250926178e-06, "epoch": 15.531353135313532, "percentage": 77.66, "elapsed_time": "5:34:16", "remaining_time": "1:36:10", "throughput": 1485.48, "total_tokens": 29793888} {"current_steps": 141185, "total_steps": 181800, "loss": 0.0478, "lr": 7.2245105080853805e-06, "epoch": 15.531903190319031, "percentage": 77.66, "elapsed_time": "5:34:17", "remaining_time": "1:36:09", "throughput": 1485.48, "total_tokens": 29794912} {"current_steps": 141190, "total_steps": 181800, "loss": 0.0014, "lr": 7.2228229290727315e-06, "epoch": 15.532453245324533, "percentage": 77.66, "elapsed_time": "5:34:18", "remaining_time": "1:36:09", "throughput": 1485.49, "total_tokens": 29796000} {"current_steps": 141195, "total_steps": 181800, "loss": 0.0009, "lr": 7.221135513903798e-06, "epoch": 15.533003300330034, "percentage": 77.67, "elapsed_time": "5:34:18", "remaining_time": "1:36:08", "throughput": 1485.49, "total_tokens": 29796992} {"current_steps": 141200, "total_steps": 181800, "loss": 0.004, "lr": 7.219448262594125e-06, "epoch": 15.533553355335533, "percentage": 77.67, "elapsed_time": "5:34:19", "remaining_time": "1:36:07", "throughput": 1485.49, "total_tokens": 29798144} {"current_steps": 141205, "total_steps": 181800, "loss": 0.0112, "lr": 7.2177611751592626e-06, "epoch": 15.534103410341034, "percentage": 77.67, "elapsed_time": "5:34:20", "remaining_time": "1:36:07", "throughput": 1485.49, "total_tokens": 29799168} {"current_steps": 141210, "total_steps": 181800, "loss": 0.0578, "lr": 7.216074251614768e-06, "epoch": 15.534653465346535, "percentage": 77.67, "elapsed_time": "5:34:20", "remaining_time": "1:36:06", "throughput": 1485.49, "total_tokens": 29800160} {"current_steps": 141215, "total_steps": 181800, "loss": 0.0054, "lr": 7.21438749197618e-06, "epoch": 15.535203520352034, "percentage": 77.68, "elapsed_time": "5:34:21", "remaining_time": "1:36:05", "throughput": 1485.49, "total_tokens": 29801216} {"current_steps": 141220, "total_steps": 181800, "loss": 0.0499, "lr": 7.2127008962590534e-06, "epoch": 15.535753575357536, "percentage": 77.68, "elapsed_time": "5:34:22", "remaining_time": "1:36:04", "throughput": 1485.49, "total_tokens": 29802240} {"current_steps": 141225, "total_steps": 181800, "loss": 0.1259, "lr": 7.211014464478929e-06, "epoch": 15.536303630363037, "percentage": 77.68, "elapsed_time": "5:34:22", "remaining_time": "1:36:04", "throughput": 1485.49, "total_tokens": 29803264} {"current_steps": 141230, "total_steps": 181800, "loss": 0.055, "lr": 7.209328196651341e-06, "epoch": 15.536853685368538, "percentage": 77.68, "elapsed_time": "5:34:23", "remaining_time": "1:36:03", "throughput": 1485.5, "total_tokens": 29804352} {"current_steps": 141235, "total_steps": 181800, "loss": 0.0535, "lr": 7.207642092791836e-06, "epoch": 15.537403740374037, "percentage": 77.69, "elapsed_time": "5:34:24", "remaining_time": "1:36:02", "throughput": 1485.5, "total_tokens": 29805408} {"current_steps": 141240, "total_steps": 181800, "loss": 0.0573, "lr": 7.205956152915957e-06, "epoch": 15.537953795379538, "percentage": 77.69, "elapsed_time": "5:34:24", "remaining_time": "1:36:02", "throughput": 1485.5, "total_tokens": 29806432} {"current_steps": 141245, "total_steps": 181800, "loss": 0.0114, "lr": 7.204270377039249e-06, "epoch": 15.53850385038504, "percentage": 77.69, "elapsed_time": "5:34:25", "remaining_time": "1:36:01", "throughput": 1485.5, "total_tokens": 29807488} {"current_steps": 141250, "total_steps": 181800, "loss": 0.0624, "lr": 7.2025847651772425e-06, "epoch": 15.539053905390539, "percentage": 77.7, "elapsed_time": "5:34:26", "remaining_time": "1:36:00", "throughput": 1485.5, "total_tokens": 29808544} {"current_steps": 141255, "total_steps": 181800, "loss": 0.0135, "lr": 7.2008993173454665e-06, "epoch": 15.53960396039604, "percentage": 77.7, "elapsed_time": "5:34:27", "remaining_time": "1:35:59", "throughput": 1485.51, "total_tokens": 29809696} {"current_steps": 141260, "total_steps": 181800, "loss": 0.0978, "lr": 7.199214033559457e-06, "epoch": 15.54015401540154, "percentage": 77.7, "elapsed_time": "5:34:27", "remaining_time": "1:35:59", "throughput": 1485.51, "total_tokens": 29810688} {"current_steps": 141265, "total_steps": 181800, "loss": 0.0278, "lr": 7.197528913834753e-06, "epoch": 15.54070407040704, "percentage": 77.7, "elapsed_time": "5:34:28", "remaining_time": "1:35:58", "throughput": 1485.51, "total_tokens": 29811680} {"current_steps": 141270, "total_steps": 181800, "loss": 0.0017, "lr": 7.195843958186888e-06, "epoch": 15.541254125412541, "percentage": 77.71, "elapsed_time": "5:34:29", "remaining_time": "1:35:57", "throughput": 1485.51, "total_tokens": 29812768} {"current_steps": 141275, "total_steps": 181800, "loss": 0.006, "lr": 7.194159166631387e-06, "epoch": 15.541804180418042, "percentage": 77.71, "elapsed_time": "5:34:29", "remaining_time": "1:35:57", "throughput": 1485.51, "total_tokens": 29813792} {"current_steps": 141280, "total_steps": 181800, "loss": 0.0043, "lr": 7.192474539183769e-06, "epoch": 15.542354235423542, "percentage": 77.71, "elapsed_time": "5:34:30", "remaining_time": "1:35:56", "throughput": 1485.51, "total_tokens": 29814816} {"current_steps": 141285, "total_steps": 181800, "loss": 0.035, "lr": 7.190790075859577e-06, "epoch": 15.542904290429043, "percentage": 77.71, "elapsed_time": "5:34:31", "remaining_time": "1:35:55", "throughput": 1485.51, "total_tokens": 29815904} {"current_steps": 141290, "total_steps": 181800, "loss": 0.0143, "lr": 7.189105776674318e-06, "epoch": 15.543454345434544, "percentage": 77.72, "elapsed_time": "5:34:31", "remaining_time": "1:35:54", "throughput": 1485.51, "total_tokens": 29816928} {"current_steps": 141295, "total_steps": 181800, "loss": 0.0372, "lr": 7.187421641643524e-06, "epoch": 15.544004400440045, "percentage": 77.72, "elapsed_time": "5:34:32", "remaining_time": "1:35:54", "throughput": 1485.51, "total_tokens": 29817888} {"current_steps": 141300, "total_steps": 181800, "loss": 0.1231, "lr": 7.185737670782727e-06, "epoch": 15.544554455445544, "percentage": 77.72, "elapsed_time": "5:34:33", "remaining_time": "1:35:53", "throughput": 1485.51, "total_tokens": 29818912} {"current_steps": 141305, "total_steps": 181800, "loss": 0.1522, "lr": 7.184053864107429e-06, "epoch": 15.545104510451045, "percentage": 77.73, "elapsed_time": "5:34:33", "remaining_time": "1:35:52", "throughput": 1485.51, "total_tokens": 29819936} {"current_steps": 141310, "total_steps": 181800, "loss": 0.0042, "lr": 7.182370221633164e-06, "epoch": 15.545654565456546, "percentage": 77.73, "elapsed_time": "5:34:34", "remaining_time": "1:35:52", "throughput": 1485.51, "total_tokens": 29820992} {"current_steps": 141315, "total_steps": 181800, "loss": 0.0035, "lr": 7.180686743375439e-06, "epoch": 15.546204620462046, "percentage": 77.73, "elapsed_time": "5:34:35", "remaining_time": "1:35:51", "throughput": 1485.51, "total_tokens": 29822016} {"current_steps": 141320, "total_steps": 181800, "loss": 0.0048, "lr": 7.17900342934977e-06, "epoch": 15.546754675467547, "percentage": 77.73, "elapsed_time": "5:34:35", "remaining_time": "1:35:50", "throughput": 1485.51, "total_tokens": 29823072} {"current_steps": 141325, "total_steps": 181800, "loss": 0.0453, "lr": 7.177320279571684e-06, "epoch": 15.547304730473048, "percentage": 77.74, "elapsed_time": "5:34:36", "remaining_time": "1:35:49", "throughput": 1485.51, "total_tokens": 29824128} {"current_steps": 141330, "total_steps": 181800, "loss": 0.0082, "lr": 7.175637294056678e-06, "epoch": 15.547854785478547, "percentage": 77.74, "elapsed_time": "5:34:37", "remaining_time": "1:35:49", "throughput": 1485.52, "total_tokens": 29825248} {"current_steps": 141335, "total_steps": 181800, "loss": 0.0034, "lr": 7.173954472820277e-06, "epoch": 15.548404840484048, "percentage": 77.74, "elapsed_time": "5:34:38", "remaining_time": "1:35:48", "throughput": 1485.52, "total_tokens": 29826336} {"current_steps": 141340, "total_steps": 181800, "loss": 0.0456, "lr": 7.172271815877984e-06, "epoch": 15.54895489548955, "percentage": 77.74, "elapsed_time": "5:34:38", "remaining_time": "1:35:47", "throughput": 1485.52, "total_tokens": 29827360} {"current_steps": 141345, "total_steps": 181800, "loss": 0.1119, "lr": 7.1705893232453e-06, "epoch": 15.549504950495049, "percentage": 77.75, "elapsed_time": "5:34:39", "remaining_time": "1:35:47", "throughput": 1485.52, "total_tokens": 29828448} {"current_steps": 141350, "total_steps": 181800, "loss": 0.1123, "lr": 7.168906994937738e-06, "epoch": 15.55005500550055, "percentage": 77.75, "elapsed_time": "5:34:40", "remaining_time": "1:35:46", "throughput": 1485.53, "total_tokens": 29829536} {"current_steps": 141355, "total_steps": 181800, "loss": 0.0676, "lr": 7.167224830970806e-06, "epoch": 15.55060506050605, "percentage": 77.75, "elapsed_time": "5:34:40", "remaining_time": "1:35:45", "throughput": 1485.53, "total_tokens": 29830592} {"current_steps": 141360, "total_steps": 181800, "loss": 0.02, "lr": 7.165542831360011e-06, "epoch": 15.551155115511552, "percentage": 77.76, "elapsed_time": "5:34:41", "remaining_time": "1:35:44", "throughput": 1485.53, "total_tokens": 29831680} {"current_steps": 141365, "total_steps": 181800, "loss": 0.0416, "lr": 7.16386099612085e-06, "epoch": 15.551705170517051, "percentage": 77.76, "elapsed_time": "5:34:42", "remaining_time": "1:35:44", "throughput": 1485.53, "total_tokens": 29832704} {"current_steps": 141370, "total_steps": 181800, "loss": 0.0297, "lr": 7.162179325268817e-06, "epoch": 15.552255225522552, "percentage": 77.76, "elapsed_time": "5:34:42", "remaining_time": "1:35:43", "throughput": 1485.53, "total_tokens": 29833760} {"current_steps": 141375, "total_steps": 181800, "loss": 0.0485, "lr": 7.160497818819417e-06, "epoch": 15.552805280528053, "percentage": 77.76, "elapsed_time": "5:34:43", "remaining_time": "1:35:42", "throughput": 1485.54, "total_tokens": 29834848} {"current_steps": 141380, "total_steps": 181800, "loss": 0.0082, "lr": 7.15881647678815e-06, "epoch": 15.553355335533553, "percentage": 77.77, "elapsed_time": "5:34:44", "remaining_time": "1:35:42", "throughput": 1485.54, "total_tokens": 29835904} {"current_steps": 141385, "total_steps": 181800, "loss": 0.0424, "lr": 7.157135299190515e-06, "epoch": 15.553905390539054, "percentage": 77.77, "elapsed_time": "5:34:44", "remaining_time": "1:35:41", "throughput": 1485.54, "total_tokens": 29836960} {"current_steps": 141390, "total_steps": 181800, "loss": 0.0051, "lr": 7.155454286042004e-06, "epoch": 15.554455445544555, "percentage": 77.77, "elapsed_time": "5:34:45", "remaining_time": "1:35:40", "throughput": 1485.54, "total_tokens": 29838016} {"current_steps": 141395, "total_steps": 181800, "loss": 0.0011, "lr": 7.153773437358102e-06, "epoch": 15.555005500550054, "percentage": 77.78, "elapsed_time": "5:34:46", "remaining_time": "1:35:39", "throughput": 1485.54, "total_tokens": 29839072} {"current_steps": 141400, "total_steps": 181800, "loss": 0.005, "lr": 7.152092753154313e-06, "epoch": 15.555555555555555, "percentage": 77.78, "elapsed_time": "5:34:47", "remaining_time": "1:35:39", "throughput": 1485.54, "total_tokens": 29840160} {"current_steps": 141405, "total_steps": 181800, "loss": 0.0044, "lr": 7.150412233446114e-06, "epoch": 15.556105610561056, "percentage": 77.78, "elapsed_time": "5:34:47", "remaining_time": "1:35:38", "throughput": 1485.55, "total_tokens": 29841216} {"current_steps": 141410, "total_steps": 181800, "loss": 0.0116, "lr": 7.1487318782489985e-06, "epoch": 15.556655665566556, "percentage": 77.78, "elapsed_time": "5:34:48", "remaining_time": "1:35:37", "throughput": 1485.54, "total_tokens": 29842176} {"current_steps": 141415, "total_steps": 181800, "loss": 0.0706, "lr": 7.147051687578463e-06, "epoch": 15.557205720572057, "percentage": 77.79, "elapsed_time": "5:34:49", "remaining_time": "1:35:36", "throughput": 1485.55, "total_tokens": 29843328} {"current_steps": 141420, "total_steps": 181800, "loss": 0.01, "lr": 7.1453716614499784e-06, "epoch": 15.557755775577558, "percentage": 77.79, "elapsed_time": "5:34:49", "remaining_time": "1:35:36", "throughput": 1485.55, "total_tokens": 29844320} {"current_steps": 141425, "total_steps": 181800, "loss": 0.0369, "lr": 7.143691799879046e-06, "epoch": 15.558305830583059, "percentage": 77.79, "elapsed_time": "5:34:50", "remaining_time": "1:35:35", "throughput": 1485.55, "total_tokens": 29845408} {"current_steps": 141430, "total_steps": 181800, "loss": 0.0687, "lr": 7.1420121028811265e-06, "epoch": 15.558855885588558, "percentage": 77.79, "elapsed_time": "5:34:51", "remaining_time": "1:35:34", "throughput": 1485.55, "total_tokens": 29846496} {"current_steps": 141435, "total_steps": 181800, "loss": 0.0072, "lr": 7.140332570471714e-06, "epoch": 15.55940594059406, "percentage": 77.8, "elapsed_time": "5:34:51", "remaining_time": "1:35:34", "throughput": 1485.55, "total_tokens": 29847520} {"current_steps": 141440, "total_steps": 181800, "loss": 0.1887, "lr": 7.138653202666296e-06, "epoch": 15.55995599559956, "percentage": 77.8, "elapsed_time": "5:34:52", "remaining_time": "1:35:33", "throughput": 1485.55, "total_tokens": 29848512} {"current_steps": 141445, "total_steps": 181800, "loss": 0.0039, "lr": 7.1369739994803285e-06, "epoch": 15.56050605060506, "percentage": 77.8, "elapsed_time": "5:34:53", "remaining_time": "1:35:32", "throughput": 1485.55, "total_tokens": 29849536} {"current_steps": 141450, "total_steps": 181800, "loss": 0.0108, "lr": 7.135294960929312e-06, "epoch": 15.561056105610561, "percentage": 77.81, "elapsed_time": "5:34:53", "remaining_time": "1:35:31", "throughput": 1485.55, "total_tokens": 29850592} {"current_steps": 141455, "total_steps": 181800, "loss": 0.0297, "lr": 7.133616087028699e-06, "epoch": 15.561606160616062, "percentage": 77.81, "elapsed_time": "5:34:54", "remaining_time": "1:35:31", "throughput": 1485.56, "total_tokens": 29851648} {"current_steps": 141460, "total_steps": 181800, "loss": 0.0481, "lr": 7.131937377793985e-06, "epoch": 15.562156215621561, "percentage": 77.81, "elapsed_time": "5:34:55", "remaining_time": "1:35:30", "throughput": 1485.55, "total_tokens": 29852640} {"current_steps": 141465, "total_steps": 181800, "loss": 0.0021, "lr": 7.1302588332406186e-06, "epoch": 15.562706270627062, "percentage": 77.81, "elapsed_time": "5:34:55", "remaining_time": "1:35:29", "throughput": 1485.56, "total_tokens": 29853728} {"current_steps": 141470, "total_steps": 181800, "loss": 0.0561, "lr": 7.128580453384082e-06, "epoch": 15.563256325632564, "percentage": 77.82, "elapsed_time": "5:34:56", "remaining_time": "1:35:29", "throughput": 1485.56, "total_tokens": 29854816} {"current_steps": 141475, "total_steps": 181800, "loss": 0.0063, "lr": 7.126902238239852e-06, "epoch": 15.563806380638063, "percentage": 77.82, "elapsed_time": "5:34:57", "remaining_time": "1:35:28", "throughput": 1485.56, "total_tokens": 29855904} {"current_steps": 141480, "total_steps": 181800, "loss": 0.0487, "lr": 7.125224187823382e-06, "epoch": 15.564356435643564, "percentage": 77.82, "elapsed_time": "5:34:58", "remaining_time": "1:35:27", "throughput": 1485.56, "total_tokens": 29856960} {"current_steps": 141485, "total_steps": 181800, "loss": 0.0039, "lr": 7.123546302150149e-06, "epoch": 15.564906490649065, "percentage": 77.82, "elapsed_time": "5:34:58", "remaining_time": "1:35:26", "throughput": 1485.56, "total_tokens": 29857984} {"current_steps": 141490, "total_steps": 181800, "loss": 0.0826, "lr": 7.121868581235613e-06, "epoch": 15.565456545654566, "percentage": 77.83, "elapsed_time": "5:34:59", "remaining_time": "1:35:26", "throughput": 1485.56, "total_tokens": 29859008} {"current_steps": 141495, "total_steps": 181800, "loss": 0.0055, "lr": 7.120191025095218e-06, "epoch": 15.566006600660065, "percentage": 77.83, "elapsed_time": "5:35:00", "remaining_time": "1:35:25", "throughput": 1485.56, "total_tokens": 29860032} {"current_steps": 141500, "total_steps": 181800, "loss": 0.0244, "lr": 7.118513633744461e-06, "epoch": 15.566556655665567, "percentage": 77.83, "elapsed_time": "5:35:00", "remaining_time": "1:35:24", "throughput": 1485.57, "total_tokens": 29861088} {"current_steps": 141505, "total_steps": 181800, "loss": 0.0548, "lr": 7.116836407198782e-06, "epoch": 15.567106710671068, "percentage": 77.84, "elapsed_time": "5:35:01", "remaining_time": "1:35:24", "throughput": 1485.57, "total_tokens": 29862176} {"current_steps": 141510, "total_steps": 181800, "loss": 0.0849, "lr": 7.115159345473635e-06, "epoch": 15.567656765676567, "percentage": 77.84, "elapsed_time": "5:35:02", "remaining_time": "1:35:23", "throughput": 1485.57, "total_tokens": 29863296} {"current_steps": 141515, "total_steps": 181800, "loss": 0.006, "lr": 7.113482448584488e-06, "epoch": 15.568206820682068, "percentage": 77.84, "elapsed_time": "5:35:02", "remaining_time": "1:35:22", "throughput": 1485.57, "total_tokens": 29864288} {"current_steps": 141520, "total_steps": 181800, "loss": 0.1693, "lr": 7.111805716546782e-06, "epoch": 15.56875687568757, "percentage": 77.84, "elapsed_time": "5:35:03", "remaining_time": "1:35:21", "throughput": 1485.58, "total_tokens": 29865440} {"current_steps": 141525, "total_steps": 181800, "loss": 0.0176, "lr": 7.11012914937598e-06, "epoch": 15.569306930693068, "percentage": 77.85, "elapsed_time": "5:35:04", "remaining_time": "1:35:21", "throughput": 1485.58, "total_tokens": 29866464} {"current_steps": 141530, "total_steps": 181800, "loss": 0.0041, "lr": 7.1084527470875404e-06, "epoch": 15.56985698569857, "percentage": 77.85, "elapsed_time": "5:35:04", "remaining_time": "1:35:20", "throughput": 1485.58, "total_tokens": 29867520} {"current_steps": 141535, "total_steps": 181800, "loss": 0.007, "lr": 7.106776509696903e-06, "epoch": 15.57040704070407, "percentage": 77.85, "elapsed_time": "5:35:05", "remaining_time": "1:35:19", "throughput": 1485.58, "total_tokens": 29868608} {"current_steps": 141540, "total_steps": 181800, "loss": 0.0105, "lr": 7.105100437219523e-06, "epoch": 15.570957095709572, "percentage": 77.85, "elapsed_time": "5:35:06", "remaining_time": "1:35:19", "throughput": 1485.58, "total_tokens": 29869632} {"current_steps": 141545, "total_steps": 181800, "loss": 0.0663, "lr": 7.103424529670841e-06, "epoch": 15.571507150715071, "percentage": 77.86, "elapsed_time": "5:35:07", "remaining_time": "1:35:18", "throughput": 1485.58, "total_tokens": 29870624} {"current_steps": 141550, "total_steps": 181800, "loss": 0.002, "lr": 7.101748787066303e-06, "epoch": 15.572057205720572, "percentage": 77.86, "elapsed_time": "5:35:07", "remaining_time": "1:35:17", "throughput": 1485.58, "total_tokens": 29871712} {"current_steps": 141555, "total_steps": 181800, "loss": 0.0055, "lr": 7.100073209421371e-06, "epoch": 15.572607260726073, "percentage": 77.86, "elapsed_time": "5:35:08", "remaining_time": "1:35:16", "throughput": 1485.59, "total_tokens": 29872768} {"current_steps": 141560, "total_steps": 181800, "loss": 0.0275, "lr": 7.098397796751466e-06, "epoch": 15.573157315731573, "percentage": 77.87, "elapsed_time": "5:35:09", "remaining_time": "1:35:16", "throughput": 1485.59, "total_tokens": 29873824} {"current_steps": 141565, "total_steps": 181800, "loss": 0.0505, "lr": 7.096722549072043e-06, "epoch": 15.573707370737074, "percentage": 77.87, "elapsed_time": "5:35:09", "remaining_time": "1:35:15", "throughput": 1485.59, "total_tokens": 29874880} {"current_steps": 141570, "total_steps": 181800, "loss": 0.0131, "lr": 7.095047466398533e-06, "epoch": 15.574257425742575, "percentage": 77.87, "elapsed_time": "5:35:10", "remaining_time": "1:35:14", "throughput": 1485.59, "total_tokens": 29875904} {"current_steps": 141575, "total_steps": 181800, "loss": 0.0032, "lr": 7.093372548746386e-06, "epoch": 15.574807480748074, "percentage": 77.87, "elapsed_time": "5:35:11", "remaining_time": "1:35:14", "throughput": 1485.59, "total_tokens": 29877024} {"current_steps": 141580, "total_steps": 181800, "loss": 0.0013, "lr": 7.091697796131025e-06, "epoch": 15.575357535753575, "percentage": 77.88, "elapsed_time": "5:35:11", "remaining_time": "1:35:13", "throughput": 1485.59, "total_tokens": 29878048} {"current_steps": 141585, "total_steps": 181800, "loss": 0.0055, "lr": 7.090023208567889e-06, "epoch": 15.575907590759076, "percentage": 77.88, "elapsed_time": "5:35:12", "remaining_time": "1:35:12", "throughput": 1485.59, "total_tokens": 29879072} {"current_steps": 141590, "total_steps": 181800, "loss": 0.0943, "lr": 7.088348786072424e-06, "epoch": 15.576457645764577, "percentage": 77.88, "elapsed_time": "5:35:13", "remaining_time": "1:35:11", "throughput": 1485.6, "total_tokens": 29880160} {"current_steps": 141595, "total_steps": 181800, "loss": 0.0221, "lr": 7.086674528660048e-06, "epoch": 15.577007700770077, "percentage": 77.89, "elapsed_time": "5:35:13", "remaining_time": "1:35:11", "throughput": 1485.6, "total_tokens": 29881216} {"current_steps": 141600, "total_steps": 181800, "loss": 0.0143, "lr": 7.085000436346204e-06, "epoch": 15.577557755775578, "percentage": 77.89, "elapsed_time": "5:35:14", "remaining_time": "1:35:10", "throughput": 1485.6, "total_tokens": 29882208} {"current_steps": 141605, "total_steps": 181800, "loss": 0.026, "lr": 7.083326509146312e-06, "epoch": 15.578107810781079, "percentage": 77.89, "elapsed_time": "5:35:15", "remaining_time": "1:35:09", "throughput": 1485.6, "total_tokens": 29883232} {"current_steps": 141610, "total_steps": 181800, "loss": 0.0047, "lr": 7.08165274707579e-06, "epoch": 15.578657865786578, "percentage": 77.89, "elapsed_time": "5:35:15", "remaining_time": "1:35:09", "throughput": 1485.6, "total_tokens": 29884256} {"current_steps": 141615, "total_steps": 181800, "loss": 0.0087, "lr": 7.07997915015009e-06, "epoch": 15.57920792079208, "percentage": 77.9, "elapsed_time": "5:35:16", "remaining_time": "1:35:08", "throughput": 1485.6, "total_tokens": 29885376} {"current_steps": 141620, "total_steps": 181800, "loss": 0.0239, "lr": 7.078305718384618e-06, "epoch": 15.57975797579758, "percentage": 77.9, "elapsed_time": "5:35:17", "remaining_time": "1:35:07", "throughput": 1485.6, "total_tokens": 29886432} {"current_steps": 141625, "total_steps": 181800, "loss": 0.0033, "lr": 7.076632451794807e-06, "epoch": 15.58030803080308, "percentage": 77.9, "elapsed_time": "5:35:18", "remaining_time": "1:35:06", "throughput": 1485.61, "total_tokens": 29887520} {"current_steps": 141630, "total_steps": 181800, "loss": 0.0102, "lr": 7.074959350396076e-06, "epoch": 15.58085808580858, "percentage": 77.9, "elapsed_time": "5:35:18", "remaining_time": "1:35:06", "throughput": 1485.61, "total_tokens": 29888576} {"current_steps": 141635, "total_steps": 181800, "loss": 0.0023, "lr": 7.0732864142038365e-06, "epoch": 15.581408140814082, "percentage": 77.91, "elapsed_time": "5:35:19", "remaining_time": "1:35:05", "throughput": 1485.61, "total_tokens": 29889664} {"current_steps": 141640, "total_steps": 181800, "loss": 0.0095, "lr": 7.071613643233513e-06, "epoch": 15.581958195819581, "percentage": 77.91, "elapsed_time": "5:35:20", "remaining_time": "1:35:04", "throughput": 1485.61, "total_tokens": 29890720} {"current_steps": 141645, "total_steps": 181800, "loss": 0.0428, "lr": 7.0699410375005215e-06, "epoch": 15.582508250825082, "percentage": 77.91, "elapsed_time": "5:35:20", "remaining_time": "1:35:04", "throughput": 1485.61, "total_tokens": 29891808} {"current_steps": 141650, "total_steps": 181800, "loss": 0.0066, "lr": 7.068268597020292e-06, "epoch": 15.583058305830583, "percentage": 77.92, "elapsed_time": "5:35:21", "remaining_time": "1:35:03", "throughput": 1485.62, "total_tokens": 29892864} {"current_steps": 141655, "total_steps": 181800, "loss": 0.0046, "lr": 7.066596321808222e-06, "epoch": 15.583608360836084, "percentage": 77.92, "elapsed_time": "5:35:22", "remaining_time": "1:35:02", "throughput": 1485.62, "total_tokens": 29893888} {"current_steps": 141660, "total_steps": 181800, "loss": 0.0018, "lr": 7.064924211879722e-06, "epoch": 15.584158415841584, "percentage": 77.92, "elapsed_time": "5:35:22", "remaining_time": "1:35:01", "throughput": 1485.62, "total_tokens": 29894976} {"current_steps": 141665, "total_steps": 181800, "loss": 0.0103, "lr": 7.06325226725022e-06, "epoch": 15.584708470847085, "percentage": 77.92, "elapsed_time": "5:35:23", "remaining_time": "1:35:01", "throughput": 1485.62, "total_tokens": 29896032} {"current_steps": 141670, "total_steps": 181800, "loss": 0.1455, "lr": 7.061580487935096e-06, "epoch": 15.585258525852586, "percentage": 77.93, "elapsed_time": "5:35:24", "remaining_time": "1:35:00", "throughput": 1485.62, "total_tokens": 29897152} {"current_steps": 141675, "total_steps": 181800, "loss": 0.0092, "lr": 7.059908873949794e-06, "epoch": 15.585808580858085, "percentage": 77.93, "elapsed_time": "5:35:24", "remaining_time": "1:34:59", "throughput": 1485.62, "total_tokens": 29898176} {"current_steps": 141680, "total_steps": 181800, "loss": 0.0041, "lr": 7.0582374253097025e-06, "epoch": 15.586358635863586, "percentage": 77.93, "elapsed_time": "5:35:25", "remaining_time": "1:34:59", "throughput": 1485.62, "total_tokens": 29899200} {"current_steps": 141685, "total_steps": 181800, "loss": 0.004, "lr": 7.056566142030222e-06, "epoch": 15.586908690869087, "percentage": 77.93, "elapsed_time": "5:35:26", "remaining_time": "1:34:58", "throughput": 1485.63, "total_tokens": 29900320} {"current_steps": 141690, "total_steps": 181800, "loss": 0.171, "lr": 7.0548950241267675e-06, "epoch": 15.587458745874587, "percentage": 77.94, "elapsed_time": "5:35:27", "remaining_time": "1:34:57", "throughput": 1485.63, "total_tokens": 29901344} {"current_steps": 141695, "total_steps": 181800, "loss": 0.0056, "lr": 7.053224071614725e-06, "epoch": 15.588008800880088, "percentage": 77.94, "elapsed_time": "5:35:27", "remaining_time": "1:34:56", "throughput": 1485.63, "total_tokens": 29902400} {"current_steps": 141700, "total_steps": 181800, "loss": 0.0778, "lr": 7.051553284509507e-06, "epoch": 15.588558855885589, "percentage": 77.94, "elapsed_time": "5:35:28", "remaining_time": "1:34:56", "throughput": 1485.63, "total_tokens": 29903456} {"current_steps": 141705, "total_steps": 181800, "loss": 0.0463, "lr": 7.049882662826518e-06, "epoch": 15.589108910891088, "percentage": 77.95, "elapsed_time": "5:35:29", "remaining_time": "1:34:55", "throughput": 1485.63, "total_tokens": 29904512} {"current_steps": 141710, "total_steps": 181800, "loss": 0.0044, "lr": 7.048212206581137e-06, "epoch": 15.58965896589659, "percentage": 77.95, "elapsed_time": "5:35:29", "remaining_time": "1:34:54", "throughput": 1485.64, "total_tokens": 29905568} {"current_steps": 141715, "total_steps": 181800, "loss": 0.0592, "lr": 7.046541915788779e-06, "epoch": 15.59020902090209, "percentage": 77.95, "elapsed_time": "5:35:30", "remaining_time": "1:34:54", "throughput": 1485.64, "total_tokens": 29906624} {"current_steps": 141720, "total_steps": 181800, "loss": 0.0053, "lr": 7.04487179046483e-06, "epoch": 15.590759075907592, "percentage": 77.95, "elapsed_time": "5:35:31", "remaining_time": "1:34:53", "throughput": 1485.64, "total_tokens": 29907616} {"current_steps": 141725, "total_steps": 181800, "loss": 0.0273, "lr": 7.043201830624674e-06, "epoch": 15.591309130913091, "percentage": 77.96, "elapsed_time": "5:35:31", "remaining_time": "1:34:52", "throughput": 1485.64, "total_tokens": 29908704} {"current_steps": 141730, "total_steps": 181800, "loss": 0.0053, "lr": 7.04153203628371e-06, "epoch": 15.591859185918592, "percentage": 77.96, "elapsed_time": "5:35:32", "remaining_time": "1:34:51", "throughput": 1485.64, "total_tokens": 29909792} {"current_steps": 141735, "total_steps": 181800, "loss": 0.0791, "lr": 7.0398624074573265e-06, "epoch": 15.592409240924093, "percentage": 77.96, "elapsed_time": "5:35:33", "remaining_time": "1:34:51", "throughput": 1485.64, "total_tokens": 29910816} {"current_steps": 141740, "total_steps": 181800, "loss": 0.058, "lr": 7.038192944160923e-06, "epoch": 15.592959295929592, "percentage": 77.96, "elapsed_time": "5:35:33", "remaining_time": "1:34:50", "throughput": 1485.65, "total_tokens": 29911904} {"current_steps": 141745, "total_steps": 181800, "loss": 0.0269, "lr": 7.036523646409876e-06, "epoch": 15.593509350935093, "percentage": 77.97, "elapsed_time": "5:35:34", "remaining_time": "1:34:49", "throughput": 1485.65, "total_tokens": 29913024} {"current_steps": 141750, "total_steps": 181800, "loss": 0.0024, "lr": 7.03485451421956e-06, "epoch": 15.594059405940595, "percentage": 77.97, "elapsed_time": "5:35:35", "remaining_time": "1:34:49", "throughput": 1485.65, "total_tokens": 29914016} {"current_steps": 141755, "total_steps": 181800, "loss": 0.1607, "lr": 7.033185547605373e-06, "epoch": 15.594609460946094, "percentage": 77.97, "elapsed_time": "5:35:36", "remaining_time": "1:34:48", "throughput": 1485.65, "total_tokens": 29915040} {"current_steps": 141760, "total_steps": 181800, "loss": 0.0712, "lr": 7.031516746582692e-06, "epoch": 15.595159515951595, "percentage": 77.98, "elapsed_time": "5:35:36", "remaining_time": "1:34:47", "throughput": 1485.65, "total_tokens": 29916192} {"current_steps": 141765, "total_steps": 181800, "loss": 0.1579, "lr": 7.029848111166906e-06, "epoch": 15.595709570957096, "percentage": 77.98, "elapsed_time": "5:35:37", "remaining_time": "1:34:46", "throughput": 1485.66, "total_tokens": 29917280} {"current_steps": 141770, "total_steps": 181800, "loss": 0.064, "lr": 7.028179641373389e-06, "epoch": 15.596259625962595, "percentage": 77.98, "elapsed_time": "5:35:38", "remaining_time": "1:34:46", "throughput": 1485.66, "total_tokens": 29918336} {"current_steps": 141775, "total_steps": 181800, "loss": 0.0016, "lr": 7.026511337217509e-06, "epoch": 15.596809680968097, "percentage": 77.98, "elapsed_time": "5:35:38", "remaining_time": "1:34:45", "throughput": 1485.66, "total_tokens": 29919392} {"current_steps": 141780, "total_steps": 181800, "loss": 0.04, "lr": 7.024843198714656e-06, "epoch": 15.597359735973598, "percentage": 77.99, "elapsed_time": "5:35:39", "remaining_time": "1:34:44", "throughput": 1485.66, "total_tokens": 29920480} {"current_steps": 141785, "total_steps": 181800, "loss": 0.0025, "lr": 7.023175225880191e-06, "epoch": 15.597909790979099, "percentage": 77.99, "elapsed_time": "5:35:40", "remaining_time": "1:34:44", "throughput": 1485.66, "total_tokens": 29921536} {"current_steps": 141790, "total_steps": 181800, "loss": 0.0106, "lr": 7.021507418729492e-06, "epoch": 15.598459845984598, "percentage": 77.99, "elapsed_time": "5:35:40", "remaining_time": "1:34:43", "throughput": 1485.67, "total_tokens": 29922688} {"current_steps": 141795, "total_steps": 181800, "loss": 0.0529, "lr": 7.019839777277942e-06, "epoch": 15.599009900990099, "percentage": 78.0, "elapsed_time": "5:35:41", "remaining_time": "1:34:42", "throughput": 1485.67, "total_tokens": 29923680} {"current_steps": 141800, "total_steps": 181800, "loss": 0.0024, "lr": 7.01817230154089e-06, "epoch": 15.5995599559956, "percentage": 78.0, "elapsed_time": "5:35:42", "remaining_time": "1:34:41", "throughput": 1485.67, "total_tokens": 29924768} {"current_steps": 141805, "total_steps": 181800, "loss": 0.004, "lr": 7.016504991533726e-06, "epoch": 15.6001100110011, "percentage": 78.0, "elapsed_time": "5:35:42", "remaining_time": "1:34:41", "throughput": 1485.67, "total_tokens": 29925792} {"current_steps": 141810, "total_steps": 181800, "loss": 0.1284, "lr": 7.014837847271799e-06, "epoch": 15.6006600660066, "percentage": 78.0, "elapsed_time": "5:35:43", "remaining_time": "1:34:40", "throughput": 1485.68, "total_tokens": 29926880} {"current_steps": 141815, "total_steps": 181800, "loss": 0.0407, "lr": 7.01317086877048e-06, "epoch": 15.601210121012102, "percentage": 78.01, "elapsed_time": "5:35:44", "remaining_time": "1:34:39", "throughput": 1485.67, "total_tokens": 29927872} {"current_steps": 141820, "total_steps": 181800, "loss": 0.0027, "lr": 7.011504056045143e-06, "epoch": 15.601760176017601, "percentage": 78.01, "elapsed_time": "5:35:44", "remaining_time": "1:34:39", "throughput": 1485.68, "total_tokens": 29928960} {"current_steps": 141825, "total_steps": 181800, "loss": 0.0009, "lr": 7.009837409111133e-06, "epoch": 15.602310231023102, "percentage": 78.01, "elapsed_time": "5:35:45", "remaining_time": "1:34:38", "throughput": 1485.68, "total_tokens": 29930048} {"current_steps": 141830, "total_steps": 181800, "loss": 0.0376, "lr": 7.0081709279838256e-06, "epoch": 15.602860286028603, "percentage": 78.01, "elapsed_time": "5:35:46", "remaining_time": "1:34:37", "throughput": 1485.68, "total_tokens": 29931136} {"current_steps": 141835, "total_steps": 181800, "loss": 0.0144, "lr": 7.006504612678569e-06, "epoch": 15.603410341034103, "percentage": 78.02, "elapsed_time": "5:35:47", "remaining_time": "1:34:36", "throughput": 1485.69, "total_tokens": 29932192} {"current_steps": 141840, "total_steps": 181800, "loss": 0.0014, "lr": 7.0048384632107305e-06, "epoch": 15.603960396039604, "percentage": 78.02, "elapsed_time": "5:35:47", "remaining_time": "1:34:36", "throughput": 1485.69, "total_tokens": 29933312} {"current_steps": 141845, "total_steps": 181800, "loss": 0.0037, "lr": 7.003172479595651e-06, "epoch": 15.604510451045105, "percentage": 78.02, "elapsed_time": "5:35:48", "remaining_time": "1:34:35", "throughput": 1485.69, "total_tokens": 29934304} {"current_steps": 141850, "total_steps": 181800, "loss": 0.1007, "lr": 7.0015066618487e-06, "epoch": 15.605060506050606, "percentage": 78.03, "elapsed_time": "5:35:49", "remaining_time": "1:34:34", "throughput": 1485.69, "total_tokens": 29935424} {"current_steps": 141855, "total_steps": 181800, "loss": 0.0747, "lr": 6.999841009985231e-06, "epoch": 15.605610561056105, "percentage": 78.03, "elapsed_time": "5:35:49", "remaining_time": "1:34:33", "throughput": 1485.69, "total_tokens": 29936384} {"current_steps": 141860, "total_steps": 181800, "loss": 0.0493, "lr": 6.998175524020581e-06, "epoch": 15.606160616061606, "percentage": 78.03, "elapsed_time": "5:35:50", "remaining_time": "1:34:33", "throughput": 1485.69, "total_tokens": 29937408} {"current_steps": 141865, "total_steps": 181800, "loss": 0.0046, "lr": 6.996510203970119e-06, "epoch": 15.606710671067107, "percentage": 78.03, "elapsed_time": "5:35:51", "remaining_time": "1:34:32", "throughput": 1485.69, "total_tokens": 29938464} {"current_steps": 141870, "total_steps": 181800, "loss": 0.0012, "lr": 6.994845049849175e-06, "epoch": 15.607260726072607, "percentage": 78.04, "elapsed_time": "5:35:51", "remaining_time": "1:34:31", "throughput": 1485.7, "total_tokens": 29939552} {"current_steps": 141875, "total_steps": 181800, "loss": 0.005, "lr": 6.993180061673105e-06, "epoch": 15.607810781078108, "percentage": 78.04, "elapsed_time": "5:35:52", "remaining_time": "1:34:31", "throughput": 1485.7, "total_tokens": 29940608} {"current_steps": 141880, "total_steps": 181800, "loss": 0.0085, "lr": 6.991515239457261e-06, "epoch": 15.608360836083609, "percentage": 78.04, "elapsed_time": "5:35:53", "remaining_time": "1:34:30", "throughput": 1485.7, "total_tokens": 29941632} {"current_steps": 141885, "total_steps": 181800, "loss": 0.0051, "lr": 6.989850583216978e-06, "epoch": 15.608910891089108, "percentage": 78.04, "elapsed_time": "5:35:53", "remaining_time": "1:34:29", "throughput": 1485.7, "total_tokens": 29942688} {"current_steps": 141890, "total_steps": 181800, "loss": 0.0128, "lr": 6.988186092967594e-06, "epoch": 15.60946094609461, "percentage": 78.05, "elapsed_time": "5:35:54", "remaining_time": "1:34:28", "throughput": 1485.7, "total_tokens": 29943712} {"current_steps": 141895, "total_steps": 181800, "loss": 0.0702, "lr": 6.986521768724463e-06, "epoch": 15.61001100110011, "percentage": 78.05, "elapsed_time": "5:35:55", "remaining_time": "1:34:28", "throughput": 1485.7, "total_tokens": 29944768} {"current_steps": 141900, "total_steps": 181800, "loss": 0.0034, "lr": 6.984857610502912e-06, "epoch": 15.61056105610561, "percentage": 78.05, "elapsed_time": "5:35:56", "remaining_time": "1:34:27", "throughput": 1485.7, "total_tokens": 29945856} {"current_steps": 141905, "total_steps": 181800, "loss": 0.0651, "lr": 6.983193618318282e-06, "epoch": 15.61111111111111, "percentage": 78.06, "elapsed_time": "5:35:56", "remaining_time": "1:34:26", "throughput": 1485.71, "total_tokens": 29946912} {"current_steps": 141910, "total_steps": 181800, "loss": 0.0291, "lr": 6.9815297921859174e-06, "epoch": 15.611661166116612, "percentage": 78.06, "elapsed_time": "5:35:57", "remaining_time": "1:34:26", "throughput": 1485.71, "total_tokens": 29947968} {"current_steps": 141915, "total_steps": 181800, "loss": 0.0325, "lr": 6.97986613212114e-06, "epoch": 15.612211221122113, "percentage": 78.06, "elapsed_time": "5:35:58", "remaining_time": "1:34:25", "throughput": 1485.71, "total_tokens": 29949056} {"current_steps": 141920, "total_steps": 181800, "loss": 0.039, "lr": 6.978202638139297e-06, "epoch": 15.612761276127612, "percentage": 78.06, "elapsed_time": "5:35:58", "remaining_time": "1:34:24", "throughput": 1485.71, "total_tokens": 29950080} {"current_steps": 141925, "total_steps": 181800, "loss": 0.0187, "lr": 6.976539310255706e-06, "epoch": 15.613311331133113, "percentage": 78.07, "elapsed_time": "5:35:59", "remaining_time": "1:34:23", "throughput": 1485.71, "total_tokens": 29951136} {"current_steps": 141930, "total_steps": 181800, "loss": 0.0357, "lr": 6.974876148485704e-06, "epoch": 15.613861386138614, "percentage": 78.07, "elapsed_time": "5:36:00", "remaining_time": "1:34:23", "throughput": 1485.72, "total_tokens": 29952224} {"current_steps": 141935, "total_steps": 181800, "loss": 0.0092, "lr": 6.973213152844626e-06, "epoch": 15.614411441144114, "percentage": 78.07, "elapsed_time": "5:36:00", "remaining_time": "1:34:22", "throughput": 1485.72, "total_tokens": 29953280} {"current_steps": 141940, "total_steps": 181800, "loss": 0.0265, "lr": 6.971550323347784e-06, "epoch": 15.614961496149615, "percentage": 78.07, "elapsed_time": "5:36:01", "remaining_time": "1:34:21", "throughput": 1485.71, "total_tokens": 29954272} {"current_steps": 141945, "total_steps": 181800, "loss": 0.1184, "lr": 6.9698876600105215e-06, "epoch": 15.615511551155116, "percentage": 78.08, "elapsed_time": "5:36:02", "remaining_time": "1:34:21", "throughput": 1485.71, "total_tokens": 29955296} {"current_steps": 141950, "total_steps": 181800, "loss": 0.0018, "lr": 6.9682251628481435e-06, "epoch": 15.616061606160617, "percentage": 78.08, "elapsed_time": "5:36:02", "remaining_time": "1:34:20", "throughput": 1485.71, "total_tokens": 29956256} {"current_steps": 141955, "total_steps": 181800, "loss": 0.0522, "lr": 6.966562831875989e-06, "epoch": 15.616611661166116, "percentage": 78.08, "elapsed_time": "5:36:03", "remaining_time": "1:34:19", "throughput": 1485.71, "total_tokens": 29957344} {"current_steps": 141960, "total_steps": 181800, "loss": 0.0024, "lr": 6.964900667109364e-06, "epoch": 15.617161716171617, "percentage": 78.09, "elapsed_time": "5:36:04", "remaining_time": "1:34:18", "throughput": 1485.72, "total_tokens": 29958400} {"current_steps": 141965, "total_steps": 181800, "loss": 0.0663, "lr": 6.963238668563596e-06, "epoch": 15.617711771177119, "percentage": 78.09, "elapsed_time": "5:36:04", "remaining_time": "1:34:18", "throughput": 1485.72, "total_tokens": 29959520} {"current_steps": 141970, "total_steps": 181800, "loss": 0.0015, "lr": 6.961576836254011e-06, "epoch": 15.618261826182618, "percentage": 78.09, "elapsed_time": "5:36:05", "remaining_time": "1:34:17", "throughput": 1485.72, "total_tokens": 29960544} {"current_steps": 141975, "total_steps": 181800, "loss": 0.0047, "lr": 6.9599151701959075e-06, "epoch": 15.618811881188119, "percentage": 78.09, "elapsed_time": "5:36:06", "remaining_time": "1:34:16", "throughput": 1485.72, "total_tokens": 29961600} {"current_steps": 141980, "total_steps": 181800, "loss": 0.062, "lr": 6.958253670404616e-06, "epoch": 15.61936193619362, "percentage": 78.1, "elapsed_time": "5:36:07", "remaining_time": "1:34:16", "throughput": 1485.72, "total_tokens": 29962624} {"current_steps": 141985, "total_steps": 181800, "loss": 0.0121, "lr": 6.956592336895437e-06, "epoch": 15.61991199119912, "percentage": 78.1, "elapsed_time": "5:36:07", "remaining_time": "1:34:15", "throughput": 1485.72, "total_tokens": 29963584} {"current_steps": 141990, "total_steps": 181800, "loss": 0.0018, "lr": 6.95493116968369e-06, "epoch": 15.62046204620462, "percentage": 78.1, "elapsed_time": "5:36:08", "remaining_time": "1:34:14", "throughput": 1485.72, "total_tokens": 29964640} {"current_steps": 141995, "total_steps": 181800, "loss": 0.004, "lr": 6.95327016878469e-06, "epoch": 15.621012101210122, "percentage": 78.11, "elapsed_time": "5:36:09", "remaining_time": "1:34:13", "throughput": 1485.72, "total_tokens": 29965728} {"current_steps": 142000, "total_steps": 181800, "loss": 0.0058, "lr": 6.951609334213729e-06, "epoch": 15.62156215621562, "percentage": 78.11, "elapsed_time": "5:36:09", "remaining_time": "1:34:13", "throughput": 1485.73, "total_tokens": 29966816} {"current_steps": 142005, "total_steps": 181800, "loss": 0.0228, "lr": 6.9499486659861335e-06, "epoch": 15.622112211221122, "percentage": 78.11, "elapsed_time": "5:36:10", "remaining_time": "1:34:12", "throughput": 1485.73, "total_tokens": 29967872} {"current_steps": 142010, "total_steps": 181800, "loss": 0.0396, "lr": 6.9482881641172004e-06, "epoch": 15.622662266226623, "percentage": 78.11, "elapsed_time": "5:36:11", "remaining_time": "1:34:11", "throughput": 1485.73, "total_tokens": 29968960} {"current_steps": 142015, "total_steps": 181800, "loss": 0.0062, "lr": 6.9466278286222264e-06, "epoch": 15.623212321232124, "percentage": 78.12, "elapsed_time": "5:36:11", "remaining_time": "1:34:11", "throughput": 1485.73, "total_tokens": 29970016} {"current_steps": 142020, "total_steps": 181800, "loss": 0.0019, "lr": 6.944967659516522e-06, "epoch": 15.623762376237623, "percentage": 78.12, "elapsed_time": "5:36:12", "remaining_time": "1:34:10", "throughput": 1485.73, "total_tokens": 29971040} {"current_steps": 142025, "total_steps": 181800, "loss": 0.0011, "lr": 6.943307656815384e-06, "epoch": 15.624312431243125, "percentage": 78.12, "elapsed_time": "5:36:13", "remaining_time": "1:34:09", "throughput": 1485.73, "total_tokens": 29972128} {"current_steps": 142030, "total_steps": 181800, "loss": 0.0333, "lr": 6.941647820534122e-06, "epoch": 15.624862486248626, "percentage": 78.12, "elapsed_time": "5:36:13", "remaining_time": "1:34:08", "throughput": 1485.73, "total_tokens": 29973152} {"current_steps": 142035, "total_steps": 181800, "loss": 0.0968, "lr": 6.939988150688029e-06, "epoch": 15.625412541254125, "percentage": 78.13, "elapsed_time": "5:36:14", "remaining_time": "1:34:08", "throughput": 1485.74, "total_tokens": 29974208} {"current_steps": 142040, "total_steps": 181800, "loss": 0.0061, "lr": 6.938328647292391e-06, "epoch": 15.625962596259626, "percentage": 78.13, "elapsed_time": "5:36:15", "remaining_time": "1:34:07", "throughput": 1485.74, "total_tokens": 29975296} {"current_steps": 142045, "total_steps": 181800, "loss": 0.0026, "lr": 6.936669310362512e-06, "epoch": 15.626512651265127, "percentage": 78.13, "elapsed_time": "5:36:16", "remaining_time": "1:34:06", "throughput": 1485.74, "total_tokens": 29976288} {"current_steps": 142050, "total_steps": 181800, "loss": 0.0359, "lr": 6.9350101399136836e-06, "epoch": 15.627062706270626, "percentage": 78.14, "elapsed_time": "5:36:16", "remaining_time": "1:34:06", "throughput": 1485.74, "total_tokens": 29977312} {"current_steps": 142055, "total_steps": 181800, "loss": 0.0068, "lr": 6.933351135961205e-06, "epoch": 15.627612761276128, "percentage": 78.14, "elapsed_time": "5:36:17", "remaining_time": "1:34:05", "throughput": 1485.74, "total_tokens": 29978400} {"current_steps": 142060, "total_steps": 181800, "loss": 0.0237, "lr": 6.931692298520359e-06, "epoch": 15.628162816281629, "percentage": 78.14, "elapsed_time": "5:36:18", "remaining_time": "1:34:04", "throughput": 1485.74, "total_tokens": 29979456} {"current_steps": 142065, "total_steps": 181800, "loss": 0.0088, "lr": 6.9300336276064305e-06, "epoch": 15.628712871287128, "percentage": 78.14, "elapsed_time": "5:36:18", "remaining_time": "1:34:03", "throughput": 1485.74, "total_tokens": 29980512} {"current_steps": 142070, "total_steps": 181800, "loss": 0.0007, "lr": 6.928375123234718e-06, "epoch": 15.629262926292629, "percentage": 78.15, "elapsed_time": "5:36:19", "remaining_time": "1:34:03", "throughput": 1485.74, "total_tokens": 29981568} {"current_steps": 142075, "total_steps": 181800, "loss": 0.0386, "lr": 6.9267167854204895e-06, "epoch": 15.62981298129813, "percentage": 78.15, "elapsed_time": "5:36:20", "remaining_time": "1:34:02", "throughput": 1485.75, "total_tokens": 29982688} {"current_steps": 142080, "total_steps": 181800, "loss": 0.0025, "lr": 6.925058614179042e-06, "epoch": 15.630363036303631, "percentage": 78.15, "elapsed_time": "5:36:20", "remaining_time": "1:34:01", "throughput": 1485.75, "total_tokens": 29983680} {"current_steps": 142085, "total_steps": 181800, "loss": 0.0554, "lr": 6.923400609525666e-06, "epoch": 15.63091309130913, "percentage": 78.15, "elapsed_time": "5:36:21", "remaining_time": "1:34:01", "throughput": 1485.75, "total_tokens": 29984832} {"current_steps": 142090, "total_steps": 181800, "loss": 0.0028, "lr": 6.921742771475623e-06, "epoch": 15.631463146314632, "percentage": 78.16, "elapsed_time": "5:36:22", "remaining_time": "1:34:00", "throughput": 1485.76, "total_tokens": 29985888} {"current_steps": 142095, "total_steps": 181800, "loss": 0.0121, "lr": 6.92008510004421e-06, "epoch": 15.632013201320133, "percentage": 78.16, "elapsed_time": "5:36:22", "remaining_time": "1:33:59", "throughput": 1485.76, "total_tokens": 29986976} {"current_steps": 142100, "total_steps": 181800, "loss": 0.0028, "lr": 6.918427595246687e-06, "epoch": 15.632563256325632, "percentage": 78.16, "elapsed_time": "5:36:23", "remaining_time": "1:33:58", "throughput": 1485.76, "total_tokens": 29988032} {"current_steps": 142105, "total_steps": 181800, "loss": 0.0521, "lr": 6.916770257098343e-06, "epoch": 15.633113311331133, "percentage": 78.17, "elapsed_time": "5:36:24", "remaining_time": "1:33:58", "throughput": 1485.76, "total_tokens": 29989120} {"current_steps": 142110, "total_steps": 181800, "loss": 0.0005, "lr": 6.915113085614458e-06, "epoch": 15.633663366336634, "percentage": 78.17, "elapsed_time": "5:36:25", "remaining_time": "1:33:57", "throughput": 1485.77, "total_tokens": 29990240} {"current_steps": 142115, "total_steps": 181800, "loss": 0.0036, "lr": 6.91345608081029e-06, "epoch": 15.634213421342134, "percentage": 78.17, "elapsed_time": "5:36:25", "remaining_time": "1:33:56", "throughput": 1485.77, "total_tokens": 29991296} {"current_steps": 142120, "total_steps": 181800, "loss": 0.0028, "lr": 6.911799242701126e-06, "epoch": 15.634763476347635, "percentage": 78.17, "elapsed_time": "5:36:26", "remaining_time": "1:33:56", "throughput": 1485.77, "total_tokens": 29992352} {"current_steps": 142125, "total_steps": 181800, "loss": 0.0846, "lr": 6.910142571302228e-06, "epoch": 15.635313531353136, "percentage": 78.18, "elapsed_time": "5:36:27", "remaining_time": "1:33:55", "throughput": 1485.77, "total_tokens": 29993408} {"current_steps": 142130, "total_steps": 181800, "loss": 0.0027, "lr": 6.908486066628861e-06, "epoch": 15.635863586358635, "percentage": 78.18, "elapsed_time": "5:36:27", "remaining_time": "1:33:54", "throughput": 1485.77, "total_tokens": 29994432} {"current_steps": 142135, "total_steps": 181800, "loss": 0.0034, "lr": 6.906829728696293e-06, "epoch": 15.636413641364136, "percentage": 78.18, "elapsed_time": "5:36:28", "remaining_time": "1:33:53", "throughput": 1485.78, "total_tokens": 29995520} {"current_steps": 142140, "total_steps": 181800, "loss": 0.0127, "lr": 6.905173557519795e-06, "epoch": 15.636963696369637, "percentage": 78.18, "elapsed_time": "5:36:29", "remaining_time": "1:33:53", "throughput": 1485.78, "total_tokens": 29996544} {"current_steps": 142145, "total_steps": 181800, "loss": 0.0517, "lr": 6.903517553114635e-06, "epoch": 15.637513751375138, "percentage": 78.19, "elapsed_time": "5:36:29", "remaining_time": "1:33:52", "throughput": 1485.78, "total_tokens": 29997632} {"current_steps": 142150, "total_steps": 181800, "loss": 0.0109, "lr": 6.901861715496074e-06, "epoch": 15.638063806380638, "percentage": 78.19, "elapsed_time": "5:36:30", "remaining_time": "1:33:51", "throughput": 1485.78, "total_tokens": 29998688} {"current_steps": 142155, "total_steps": 181800, "loss": 0.0116, "lr": 6.900206044679361e-06, "epoch": 15.638613861386139, "percentage": 78.19, "elapsed_time": "5:36:31", "remaining_time": "1:33:51", "throughput": 1485.78, "total_tokens": 29999712} {"current_steps": 142160, "total_steps": 181800, "loss": 0.0368, "lr": 6.898550540679763e-06, "epoch": 15.63916391639164, "percentage": 78.2, "elapsed_time": "5:36:31", "remaining_time": "1:33:50", "throughput": 1485.78, "total_tokens": 30000704} {"current_steps": 142165, "total_steps": 181800, "loss": 0.054, "lr": 6.8968952035125376e-06, "epoch": 15.63971397139714, "percentage": 78.2, "elapsed_time": "5:36:32", "remaining_time": "1:33:49", "throughput": 1485.78, "total_tokens": 30001792} {"current_steps": 142170, "total_steps": 181800, "loss": 0.0536, "lr": 6.895240033192951e-06, "epoch": 15.64026402640264, "percentage": 78.2, "elapsed_time": "5:36:33", "remaining_time": "1:33:48", "throughput": 1485.78, "total_tokens": 30002816} {"current_steps": 142175, "total_steps": 181800, "loss": 0.0085, "lr": 6.893585029736249e-06, "epoch": 15.640814081408141, "percentage": 78.2, "elapsed_time": "5:36:33", "remaining_time": "1:33:48", "throughput": 1485.78, "total_tokens": 30003872} {"current_steps": 142180, "total_steps": 181800, "loss": 0.0938, "lr": 6.891930193157678e-06, "epoch": 15.64136413641364, "percentage": 78.21, "elapsed_time": "5:36:34", "remaining_time": "1:33:47", "throughput": 1485.79, "total_tokens": 30004960} {"current_steps": 142185, "total_steps": 181800, "loss": 0.1378, "lr": 6.890275523472506e-06, "epoch": 15.641914191419142, "percentage": 78.21, "elapsed_time": "5:36:35", "remaining_time": "1:33:46", "throughput": 1485.79, "total_tokens": 30006016} {"current_steps": 142190, "total_steps": 181800, "loss": 0.0079, "lr": 6.888621020695965e-06, "epoch": 15.642464246424643, "percentage": 78.21, "elapsed_time": "5:36:36", "remaining_time": "1:33:46", "throughput": 1485.79, "total_tokens": 30007072} {"current_steps": 142195, "total_steps": 181800, "loss": 0.0419, "lr": 6.8869666848433155e-06, "epoch": 15.643014301430142, "percentage": 78.22, "elapsed_time": "5:36:36", "remaining_time": "1:33:45", "throughput": 1485.79, "total_tokens": 30008160} {"current_steps": 142200, "total_steps": 181800, "loss": 0.003, "lr": 6.885312515929809e-06, "epoch": 15.643564356435643, "percentage": 78.22, "elapsed_time": "5:36:37", "remaining_time": "1:33:44", "throughput": 1485.79, "total_tokens": 30009184} {"current_steps": 142205, "total_steps": 181800, "loss": 0.0008, "lr": 6.883658513970676e-06, "epoch": 15.644114411441144, "percentage": 78.22, "elapsed_time": "5:36:38", "remaining_time": "1:33:43", "throughput": 1485.79, "total_tokens": 30010144} {"current_steps": 142210, "total_steps": 181800, "loss": 0.0693, "lr": 6.88200467898118e-06, "epoch": 15.644664466446645, "percentage": 78.22, "elapsed_time": "5:36:38", "remaining_time": "1:33:43", "throughput": 1485.8, "total_tokens": 30011264} {"current_steps": 142215, "total_steps": 181800, "loss": 0.0007, "lr": 6.880351010976544e-06, "epoch": 15.645214521452145, "percentage": 78.23, "elapsed_time": "5:36:39", "remaining_time": "1:33:42", "throughput": 1485.8, "total_tokens": 30012288} {"current_steps": 142220, "total_steps": 181800, "loss": 0.0783, "lr": 6.878697509972015e-06, "epoch": 15.645764576457646, "percentage": 78.23, "elapsed_time": "5:36:40", "remaining_time": "1:33:41", "throughput": 1485.8, "total_tokens": 30013312} {"current_steps": 142225, "total_steps": 181800, "loss": 0.0591, "lr": 6.877044175982847e-06, "epoch": 15.646314631463147, "percentage": 78.23, "elapsed_time": "5:36:40", "remaining_time": "1:33:41", "throughput": 1485.8, "total_tokens": 30014368} {"current_steps": 142230, "total_steps": 181800, "loss": 0.1357, "lr": 6.875391009024257e-06, "epoch": 15.646864686468646, "percentage": 78.23, "elapsed_time": "5:36:41", "remaining_time": "1:33:40", "throughput": 1485.8, "total_tokens": 30015392} {"current_steps": 142235, "total_steps": 181800, "loss": 0.0119, "lr": 6.873738009111499e-06, "epoch": 15.647414741474147, "percentage": 78.24, "elapsed_time": "5:36:42", "remaining_time": "1:33:39", "throughput": 1485.8, "total_tokens": 30016512} {"current_steps": 142240, "total_steps": 181800, "loss": 0.0027, "lr": 6.872085176259796e-06, "epoch": 15.647964796479648, "percentage": 78.24, "elapsed_time": "5:36:42", "remaining_time": "1:33:38", "throughput": 1485.81, "total_tokens": 30017632} {"current_steps": 142245, "total_steps": 181800, "loss": 0.0025, "lr": 6.87043251048439e-06, "epoch": 15.648514851485148, "percentage": 78.24, "elapsed_time": "5:36:43", "remaining_time": "1:33:38", "throughput": 1485.81, "total_tokens": 30018688} {"current_steps": 142250, "total_steps": 181800, "loss": 0.002, "lr": 6.868780011800499e-06, "epoch": 15.649064906490649, "percentage": 78.25, "elapsed_time": "5:36:44", "remaining_time": "1:33:37", "throughput": 1485.81, "total_tokens": 30019744} {"current_steps": 142255, "total_steps": 181800, "loss": 0.0559, "lr": 6.867127680223365e-06, "epoch": 15.64961496149615, "percentage": 78.25, "elapsed_time": "5:36:44", "remaining_time": "1:33:36", "throughput": 1485.81, "total_tokens": 30020704} {"current_steps": 142260, "total_steps": 181800, "loss": 0.0113, "lr": 6.865475515768219e-06, "epoch": 15.65016501650165, "percentage": 78.25, "elapsed_time": "5:36:45", "remaining_time": "1:33:36", "throughput": 1485.81, "total_tokens": 30021728} {"current_steps": 142265, "total_steps": 181800, "loss": 0.0146, "lr": 6.863823518450277e-06, "epoch": 15.65071507150715, "percentage": 78.25, "elapsed_time": "5:36:46", "remaining_time": "1:33:35", "throughput": 1485.79, "total_tokens": 30022752} {"current_steps": 142270, "total_steps": 181800, "loss": 0.0765, "lr": 6.86217168828478e-06, "epoch": 15.651265126512651, "percentage": 78.26, "elapsed_time": "5:36:47", "remaining_time": "1:33:34", "throughput": 1485.8, "total_tokens": 30023840} {"current_steps": 142275, "total_steps": 181800, "loss": 0.0042, "lr": 6.8605200252869425e-06, "epoch": 15.651815181518153, "percentage": 78.26, "elapsed_time": "5:36:47", "remaining_time": "1:33:33", "throughput": 1485.8, "total_tokens": 30024864} {"current_steps": 142280, "total_steps": 181800, "loss": 0.001, "lr": 6.85886852947197e-06, "epoch": 15.652365236523652, "percentage": 78.26, "elapsed_time": "5:36:48", "remaining_time": "1:33:33", "throughput": 1485.8, "total_tokens": 30025952} {"current_steps": 142285, "total_steps": 181800, "loss": 0.0048, "lr": 6.85721720085512e-06, "epoch": 15.652915291529153, "percentage": 78.26, "elapsed_time": "5:36:49", "remaining_time": "1:33:32", "throughput": 1485.8, "total_tokens": 30027040} {"current_steps": 142290, "total_steps": 181800, "loss": 0.0011, "lr": 6.855566039451594e-06, "epoch": 15.653465346534654, "percentage": 78.27, "elapsed_time": "5:36:50", "remaining_time": "1:33:31", "throughput": 1485.81, "total_tokens": 30028128} {"current_steps": 142295, "total_steps": 181800, "loss": 0.0054, "lr": 6.853915045276599e-06, "epoch": 15.654015401540153, "percentage": 78.27, "elapsed_time": "5:36:50", "remaining_time": "1:33:31", "throughput": 1485.81, "total_tokens": 30029184} {"current_steps": 142300, "total_steps": 181800, "loss": 0.0023, "lr": 6.852264218345369e-06, "epoch": 15.654565456545654, "percentage": 78.27, "elapsed_time": "5:36:51", "remaining_time": "1:33:30", "throughput": 1485.81, "total_tokens": 30030208} {"current_steps": 142305, "total_steps": 181800, "loss": 0.0058, "lr": 6.850613558673105e-06, "epoch": 15.655115511551156, "percentage": 78.28, "elapsed_time": "5:36:52", "remaining_time": "1:33:29", "throughput": 1485.81, "total_tokens": 30031232} {"current_steps": 142310, "total_steps": 181800, "loss": 0.0014, "lr": 6.848963066275027e-06, "epoch": 15.655665566556655, "percentage": 78.28, "elapsed_time": "5:36:52", "remaining_time": "1:33:28", "throughput": 1485.81, "total_tokens": 30032256} {"current_steps": 142315, "total_steps": 181800, "loss": 0.0052, "lr": 6.8473127411663564e-06, "epoch": 15.656215621562156, "percentage": 78.28, "elapsed_time": "5:36:53", "remaining_time": "1:33:28", "throughput": 1485.81, "total_tokens": 30033344} {"current_steps": 142320, "total_steps": 181800, "loss": 0.0535, "lr": 6.8456625833622835e-06, "epoch": 15.656765676567657, "percentage": 78.28, "elapsed_time": "5:36:54", "remaining_time": "1:33:27", "throughput": 1485.81, "total_tokens": 30034400} {"current_steps": 142325, "total_steps": 181800, "loss": 0.0083, "lr": 6.844012592878035e-06, "epoch": 15.657315731573158, "percentage": 78.29, "elapsed_time": "5:36:54", "remaining_time": "1:33:26", "throughput": 1485.82, "total_tokens": 30035520} {"current_steps": 142330, "total_steps": 181800, "loss": 0.0028, "lr": 6.842362769728802e-06, "epoch": 15.657865786578657, "percentage": 78.29, "elapsed_time": "5:36:55", "remaining_time": "1:33:26", "throughput": 1485.82, "total_tokens": 30036608} {"current_steps": 142335, "total_steps": 181800, "loss": 0.0024, "lr": 6.8407131139298e-06, "epoch": 15.658415841584159, "percentage": 78.29, "elapsed_time": "5:36:56", "remaining_time": "1:33:25", "throughput": 1485.82, "total_tokens": 30037664} {"current_steps": 142340, "total_steps": 181800, "loss": 0.0013, "lr": 6.839063625496239e-06, "epoch": 15.65896589658966, "percentage": 78.29, "elapsed_time": "5:36:56", "remaining_time": "1:33:24", "throughput": 1485.82, "total_tokens": 30038720} {"current_steps": 142345, "total_steps": 181800, "loss": 0.0117, "lr": 6.837414304443307e-06, "epoch": 15.659515951595159, "percentage": 78.3, "elapsed_time": "5:36:57", "remaining_time": "1:33:23", "throughput": 1485.82, "total_tokens": 30039712} {"current_steps": 142350, "total_steps": 181800, "loss": 0.0359, "lr": 6.835765150786219e-06, "epoch": 15.66006600660066, "percentage": 78.3, "elapsed_time": "5:36:58", "remaining_time": "1:33:23", "throughput": 1485.82, "total_tokens": 30040736} {"current_steps": 142355, "total_steps": 181800, "loss": 0.0795, "lr": 6.834116164540158e-06, "epoch": 15.660616061606161, "percentage": 78.3, "elapsed_time": "5:36:58", "remaining_time": "1:33:22", "throughput": 1485.82, "total_tokens": 30041792} {"current_steps": 142360, "total_steps": 181800, "loss": 0.0565, "lr": 6.832467345720342e-06, "epoch": 15.66116611661166, "percentage": 78.31, "elapsed_time": "5:36:59", "remaining_time": "1:33:21", "throughput": 1485.82, "total_tokens": 30042880} {"current_steps": 142365, "total_steps": 181800, "loss": 0.0095, "lr": 6.830818694341947e-06, "epoch": 15.661716171617162, "percentage": 78.31, "elapsed_time": "5:37:00", "remaining_time": "1:33:21", "throughput": 1485.83, "total_tokens": 30043936} {"current_steps": 142370, "total_steps": 181800, "loss": 0.0021, "lr": 6.82917021042018e-06, "epoch": 15.662266226622663, "percentage": 78.31, "elapsed_time": "5:37:01", "remaining_time": "1:33:20", "throughput": 1485.83, "total_tokens": 30045024} {"current_steps": 142375, "total_steps": 181800, "loss": 0.0342, "lr": 6.827521893970237e-06, "epoch": 15.662816281628164, "percentage": 78.31, "elapsed_time": "5:37:01", "remaining_time": "1:33:19", "throughput": 1485.83, "total_tokens": 30046080} {"current_steps": 142380, "total_steps": 181800, "loss": 0.0486, "lr": 6.8258737450073e-06, "epoch": 15.663366336633663, "percentage": 78.32, "elapsed_time": "5:37:02", "remaining_time": "1:33:18", "throughput": 1485.83, "total_tokens": 30047072} {"current_steps": 142385, "total_steps": 181800, "loss": 0.0054, "lr": 6.824225763546571e-06, "epoch": 15.663916391639164, "percentage": 78.32, "elapsed_time": "5:37:03", "remaining_time": "1:33:18", "throughput": 1485.83, "total_tokens": 30048160} {"current_steps": 142390, "total_steps": 181800, "loss": 0.0028, "lr": 6.822577949603229e-06, "epoch": 15.664466446644665, "percentage": 78.32, "elapsed_time": "5:37:03", "remaining_time": "1:33:17", "throughput": 1485.83, "total_tokens": 30049184} {"current_steps": 142395, "total_steps": 181800, "loss": 0.1088, "lr": 6.820930303192449e-06, "epoch": 15.665016501650165, "percentage": 78.33, "elapsed_time": "5:37:04", "remaining_time": "1:33:16", "throughput": 1485.84, "total_tokens": 30050272} {"current_steps": 142400, "total_steps": 181800, "loss": 0.0633, "lr": 6.819282824329448e-06, "epoch": 15.665566556655666, "percentage": 78.33, "elapsed_time": "5:37:05", "remaining_time": "1:33:16", "throughput": 1485.84, "total_tokens": 30051296} {"current_steps": 142405, "total_steps": 181800, "loss": 0.0044, "lr": 6.817635513029385e-06, "epoch": 15.666116611661167, "percentage": 78.33, "elapsed_time": "5:37:05", "remaining_time": "1:33:15", "throughput": 1485.84, "total_tokens": 30052320} {"current_steps": 142410, "total_steps": 181800, "loss": 0.0126, "lr": 6.81598836930746e-06, "epoch": 15.666666666666666, "percentage": 78.33, "elapsed_time": "5:37:06", "remaining_time": "1:33:14", "throughput": 1485.84, "total_tokens": 30053440} {"current_steps": 142415, "total_steps": 181800, "loss": 0.0946, "lr": 6.8143413931788415e-06, "epoch": 15.667216721672167, "percentage": 78.34, "elapsed_time": "5:37:07", "remaining_time": "1:33:13", "throughput": 1485.84, "total_tokens": 30054528} {"current_steps": 142420, "total_steps": 181800, "loss": 0.0052, "lr": 6.812694584658708e-06, "epoch": 15.667766776677668, "percentage": 78.34, "elapsed_time": "5:37:07", "remaining_time": "1:33:13", "throughput": 1485.84, "total_tokens": 30055520} {"current_steps": 142425, "total_steps": 181800, "loss": 0.0022, "lr": 6.811047943762239e-06, "epoch": 15.668316831683168, "percentage": 78.34, "elapsed_time": "5:37:08", "remaining_time": "1:33:12", "throughput": 1485.85, "total_tokens": 30056640} {"current_steps": 142430, "total_steps": 181800, "loss": 0.0015, "lr": 6.809401470504615e-06, "epoch": 15.668866886688669, "percentage": 78.34, "elapsed_time": "5:37:09", "remaining_time": "1:33:11", "throughput": 1485.85, "total_tokens": 30057728} {"current_steps": 142435, "total_steps": 181800, "loss": 0.0064, "lr": 6.807755164901014e-06, "epoch": 15.66941694169417, "percentage": 78.35, "elapsed_time": "5:37:09", "remaining_time": "1:33:10", "throughput": 1485.85, "total_tokens": 30058720} {"current_steps": 142440, "total_steps": 181800, "loss": 0.0079, "lr": 6.806109026966606e-06, "epoch": 15.66996699669967, "percentage": 78.35, "elapsed_time": "5:37:10", "remaining_time": "1:33:10", "throughput": 1485.85, "total_tokens": 30059808} {"current_steps": 142445, "total_steps": 181800, "loss": 0.0023, "lr": 6.8044630567165505e-06, "epoch": 15.67051705170517, "percentage": 78.35, "elapsed_time": "5:37:11", "remaining_time": "1:33:09", "throughput": 1485.85, "total_tokens": 30060832} {"current_steps": 142450, "total_steps": 181800, "loss": 0.0052, "lr": 6.802817254166038e-06, "epoch": 15.671067106710671, "percentage": 78.36, "elapsed_time": "5:37:12", "remaining_time": "1:33:08", "throughput": 1485.85, "total_tokens": 30061888} {"current_steps": 142455, "total_steps": 181800, "loss": 0.0277, "lr": 6.801171619330213e-06, "epoch": 15.671617161716172, "percentage": 78.36, "elapsed_time": "5:37:12", "remaining_time": "1:33:08", "throughput": 1485.85, "total_tokens": 30062944} {"current_steps": 142460, "total_steps": 181800, "loss": 0.0008, "lr": 6.79952615222427e-06, "epoch": 15.672167216721672, "percentage": 78.36, "elapsed_time": "5:37:13", "remaining_time": "1:33:07", "throughput": 1485.85, "total_tokens": 30063968} {"current_steps": 142465, "total_steps": 181800, "loss": 0.0103, "lr": 6.797880852863361e-06, "epoch": 15.672717271727173, "percentage": 78.36, "elapsed_time": "5:37:14", "remaining_time": "1:33:06", "throughput": 1485.86, "total_tokens": 30065056} {"current_steps": 142470, "total_steps": 181800, "loss": 0.0454, "lr": 6.796235721262642e-06, "epoch": 15.673267326732674, "percentage": 78.37, "elapsed_time": "5:37:14", "remaining_time": "1:33:05", "throughput": 1485.86, "total_tokens": 30066112} {"current_steps": 142475, "total_steps": 181800, "loss": 0.1378, "lr": 6.794590757437291e-06, "epoch": 15.673817381738173, "percentage": 78.37, "elapsed_time": "5:37:15", "remaining_time": "1:33:05", "throughput": 1485.86, "total_tokens": 30067168} {"current_steps": 142480, "total_steps": 181800, "loss": 0.0434, "lr": 6.792945961402456e-06, "epoch": 15.674367436743674, "percentage": 78.37, "elapsed_time": "5:37:16", "remaining_time": "1:33:04", "throughput": 1485.86, "total_tokens": 30068192} {"current_steps": 142485, "total_steps": 181800, "loss": 0.0478, "lr": 6.791301333173297e-06, "epoch": 15.674917491749175, "percentage": 78.37, "elapsed_time": "5:37:16", "remaining_time": "1:33:03", "throughput": 1485.86, "total_tokens": 30069248} {"current_steps": 142490, "total_steps": 181800, "loss": 0.0841, "lr": 6.7896568727649875e-06, "epoch": 15.675467546754675, "percentage": 78.38, "elapsed_time": "5:37:17", "remaining_time": "1:33:03", "throughput": 1485.86, "total_tokens": 30070272} {"current_steps": 142495, "total_steps": 181800, "loss": 0.2031, "lr": 6.788012580192662e-06, "epoch": 15.676017601760176, "percentage": 78.38, "elapsed_time": "5:37:18", "remaining_time": "1:33:02", "throughput": 1485.86, "total_tokens": 30071264} {"current_steps": 142500, "total_steps": 181800, "loss": 0.0027, "lr": 6.786368455471498e-06, "epoch": 15.676567656765677, "percentage": 78.38, "elapsed_time": "5:37:18", "remaining_time": "1:33:01", "throughput": 1485.86, "total_tokens": 30072256} {"current_steps": 142505, "total_steps": 181800, "loss": 0.0011, "lr": 6.784724498616632e-06, "epoch": 15.677117711771178, "percentage": 78.39, "elapsed_time": "5:37:19", "remaining_time": "1:33:00", "throughput": 1485.86, "total_tokens": 30073280} {"current_steps": 142510, "total_steps": 181800, "loss": 0.0891, "lr": 6.783080709643214e-06, "epoch": 15.677667766776677, "percentage": 78.39, "elapsed_time": "5:37:20", "remaining_time": "1:33:00", "throughput": 1485.86, "total_tokens": 30074336} {"current_steps": 142515, "total_steps": 181800, "loss": 0.0927, "lr": 6.781437088566397e-06, "epoch": 15.678217821782178, "percentage": 78.39, "elapsed_time": "5:37:21", "remaining_time": "1:32:59", "throughput": 1485.86, "total_tokens": 30075424} {"current_steps": 142520, "total_steps": 181800, "loss": 0.0409, "lr": 6.779793635401335e-06, "epoch": 15.67876787678768, "percentage": 78.39, "elapsed_time": "5:37:21", "remaining_time": "1:32:58", "throughput": 1485.87, "total_tokens": 30076544} {"current_steps": 142525, "total_steps": 181800, "loss": 0.001, "lr": 6.778150350163179e-06, "epoch": 15.679317931793179, "percentage": 78.4, "elapsed_time": "5:37:22", "remaining_time": "1:32:58", "throughput": 1485.87, "total_tokens": 30077696} {"current_steps": 142530, "total_steps": 181800, "loss": 0.0364, "lr": 6.776507232867069e-06, "epoch": 15.67986798679868, "percentage": 78.4, "elapsed_time": "5:37:23", "remaining_time": "1:32:57", "throughput": 1485.87, "total_tokens": 30078720} {"current_steps": 142535, "total_steps": 181800, "loss": 0.007, "lr": 6.774864283528137e-06, "epoch": 15.680418041804181, "percentage": 78.4, "elapsed_time": "5:37:23", "remaining_time": "1:32:56", "throughput": 1485.88, "total_tokens": 30079776} {"current_steps": 142540, "total_steps": 181800, "loss": 0.1278, "lr": 6.773221502161536e-06, "epoch": 15.68096809680968, "percentage": 78.4, "elapsed_time": "5:37:24", "remaining_time": "1:32:55", "throughput": 1485.88, "total_tokens": 30080864} {"current_steps": 142545, "total_steps": 181800, "loss": 0.0158, "lr": 6.77157888878241e-06, "epoch": 15.681518151815181, "percentage": 78.41, "elapsed_time": "5:37:25", "remaining_time": "1:32:55", "throughput": 1485.88, "total_tokens": 30081952} {"current_steps": 142550, "total_steps": 181800, "loss": 0.0024, "lr": 6.769936443405897e-06, "epoch": 15.682068206820682, "percentage": 78.41, "elapsed_time": "5:37:25", "remaining_time": "1:32:54", "throughput": 1485.88, "total_tokens": 30083008} {"current_steps": 142555, "total_steps": 181800, "loss": 0.0879, "lr": 6.768294166047134e-06, "epoch": 15.682618261826182, "percentage": 78.41, "elapsed_time": "5:37:26", "remaining_time": "1:32:53", "throughput": 1485.88, "total_tokens": 30084032} {"current_steps": 142560, "total_steps": 181800, "loss": 0.0042, "lr": 6.766652056721248e-06, "epoch": 15.683168316831683, "percentage": 78.42, "elapsed_time": "5:37:27", "remaining_time": "1:32:53", "throughput": 1485.88, "total_tokens": 30085024} {"current_steps": 142565, "total_steps": 181800, "loss": 0.001, "lr": 6.76501011544339e-06, "epoch": 15.683718371837184, "percentage": 78.42, "elapsed_time": "5:37:27", "remaining_time": "1:32:52", "throughput": 1485.88, "total_tokens": 30086112} {"current_steps": 142570, "total_steps": 181800, "loss": 0.0032, "lr": 6.7633683422286735e-06, "epoch": 15.684268426842685, "percentage": 78.42, "elapsed_time": "5:37:28", "remaining_time": "1:32:51", "throughput": 1485.89, "total_tokens": 30087200} {"current_steps": 142575, "total_steps": 181800, "loss": 0.0151, "lr": 6.761726737092242e-06, "epoch": 15.684818481848184, "percentage": 78.42, "elapsed_time": "5:37:29", "remaining_time": "1:32:50", "throughput": 1485.89, "total_tokens": 30088256} {"current_steps": 142580, "total_steps": 181800, "loss": 0.1585, "lr": 6.7600853000492324e-06, "epoch": 15.685368536853685, "percentage": 78.43, "elapsed_time": "5:37:30", "remaining_time": "1:32:50", "throughput": 1485.89, "total_tokens": 30089376} {"current_steps": 142585, "total_steps": 181800, "loss": 0.006, "lr": 6.758444031114755e-06, "epoch": 15.685918591859187, "percentage": 78.43, "elapsed_time": "5:37:30", "remaining_time": "1:32:49", "throughput": 1485.9, "total_tokens": 30090432} {"current_steps": 142590, "total_steps": 181800, "loss": 0.1046, "lr": 6.7568029303039515e-06, "epoch": 15.686468646864686, "percentage": 78.43, "elapsed_time": "5:37:31", "remaining_time": "1:32:48", "throughput": 1485.9, "total_tokens": 30091488} {"current_steps": 142595, "total_steps": 181800, "loss": 0.051, "lr": 6.755161997631937e-06, "epoch": 15.687018701870187, "percentage": 78.44, "elapsed_time": "5:37:32", "remaining_time": "1:32:48", "throughput": 1485.9, "total_tokens": 30092640} {"current_steps": 142600, "total_steps": 181800, "loss": 0.0121, "lr": 6.753521233113838e-06, "epoch": 15.687568756875688, "percentage": 78.44, "elapsed_time": "5:37:32", "remaining_time": "1:32:47", "throughput": 1485.9, "total_tokens": 30093632} {"current_steps": 142605, "total_steps": 181800, "loss": 0.05, "lr": 6.751880636764787e-06, "epoch": 15.688118811881187, "percentage": 78.44, "elapsed_time": "5:37:33", "remaining_time": "1:32:46", "throughput": 1485.91, "total_tokens": 30094752} {"current_steps": 142610, "total_steps": 181800, "loss": 0.0116, "lr": 6.750240208599887e-06, "epoch": 15.688668866886688, "percentage": 78.44, "elapsed_time": "5:37:34", "remaining_time": "1:32:45", "throughput": 1485.91, "total_tokens": 30095776} {"current_steps": 142615, "total_steps": 181800, "loss": 0.0042, "lr": 6.748599948634274e-06, "epoch": 15.68921892189219, "percentage": 78.45, "elapsed_time": "5:37:34", "remaining_time": "1:32:45", "throughput": 1485.91, "total_tokens": 30096768} {"current_steps": 142620, "total_steps": 181800, "loss": 0.0035, "lr": 6.7469598568830505e-06, "epoch": 15.689768976897689, "percentage": 78.45, "elapsed_time": "5:37:35", "remaining_time": "1:32:44", "throughput": 1485.91, "total_tokens": 30097824} {"current_steps": 142625, "total_steps": 181800, "loss": 0.0008, "lr": 6.745319933361344e-06, "epoch": 15.69031903190319, "percentage": 78.45, "elapsed_time": "5:37:36", "remaining_time": "1:32:43", "throughput": 1485.91, "total_tokens": 30098848} {"current_steps": 142630, "total_steps": 181800, "loss": 0.0037, "lr": 6.7436801780842605e-06, "epoch": 15.690869086908691, "percentage": 78.45, "elapsed_time": "5:37:36", "remaining_time": "1:32:43", "throughput": 1485.91, "total_tokens": 30099904} {"current_steps": 142635, "total_steps": 181800, "loss": 0.0509, "lr": 6.742040591066914e-06, "epoch": 15.691419141914192, "percentage": 78.46, "elapsed_time": "5:37:37", "remaining_time": "1:32:42", "throughput": 1485.91, "total_tokens": 30101024} {"current_steps": 142640, "total_steps": 181800, "loss": 0.0082, "lr": 6.740401172324426e-06, "epoch": 15.691969196919691, "percentage": 78.46, "elapsed_time": "5:37:38", "remaining_time": "1:32:41", "throughput": 1485.91, "total_tokens": 30102048} {"current_steps": 142645, "total_steps": 181800, "loss": 0.0252, "lr": 6.738761921871892e-06, "epoch": 15.692519251925193, "percentage": 78.46, "elapsed_time": "5:37:38", "remaining_time": "1:32:40", "throughput": 1485.92, "total_tokens": 30103104} {"current_steps": 142650, "total_steps": 181800, "loss": 0.0021, "lr": 6.737122839724436e-06, "epoch": 15.693069306930694, "percentage": 78.47, "elapsed_time": "5:37:39", "remaining_time": "1:32:40", "throughput": 1485.92, "total_tokens": 30104224} {"current_steps": 142655, "total_steps": 181800, "loss": 0.005, "lr": 6.735483925897146e-06, "epoch": 15.693619361936193, "percentage": 78.47, "elapsed_time": "5:37:40", "remaining_time": "1:32:39", "throughput": 1485.92, "total_tokens": 30105280} {"current_steps": 142660, "total_steps": 181800, "loss": 0.1292, "lr": 6.733845180405135e-06, "epoch": 15.694169416941694, "percentage": 78.47, "elapsed_time": "5:37:41", "remaining_time": "1:32:38", "throughput": 1485.93, "total_tokens": 30106400} {"current_steps": 142665, "total_steps": 181800, "loss": 0.0219, "lr": 6.732206603263519e-06, "epoch": 15.694719471947195, "percentage": 78.47, "elapsed_time": "5:37:41", "remaining_time": "1:32:38", "throughput": 1485.93, "total_tokens": 30107392} {"current_steps": 142670, "total_steps": 181800, "loss": 0.1036, "lr": 6.730568194487385e-06, "epoch": 15.695269526952695, "percentage": 78.48, "elapsed_time": "5:37:42", "remaining_time": "1:32:37", "throughput": 1485.93, "total_tokens": 30108448} {"current_steps": 142675, "total_steps": 181800, "loss": 0.0048, "lr": 6.728929954091834e-06, "epoch": 15.695819581958196, "percentage": 78.48, "elapsed_time": "5:37:43", "remaining_time": "1:32:36", "throughput": 1485.93, "total_tokens": 30109472} {"current_steps": 142680, "total_steps": 181800, "loss": 0.0598, "lr": 6.727291882091974e-06, "epoch": 15.696369636963697, "percentage": 78.48, "elapsed_time": "5:37:43", "remaining_time": "1:32:35", "throughput": 1485.93, "total_tokens": 30110496} {"current_steps": 142685, "total_steps": 181800, "loss": 0.0079, "lr": 6.725653978502888e-06, "epoch": 15.696919691969196, "percentage": 78.48, "elapsed_time": "5:37:44", "remaining_time": "1:32:35", "throughput": 1485.93, "total_tokens": 30111520} {"current_steps": 142690, "total_steps": 181800, "loss": 0.0744, "lr": 6.7240162433396815e-06, "epoch": 15.697469746974697, "percentage": 78.49, "elapsed_time": "5:37:45", "remaining_time": "1:32:34", "throughput": 1485.93, "total_tokens": 30112576} {"current_steps": 142695, "total_steps": 181800, "loss": 0.0331, "lr": 6.722378676617455e-06, "epoch": 15.698019801980198, "percentage": 78.49, "elapsed_time": "5:37:45", "remaining_time": "1:32:33", "throughput": 1485.93, "total_tokens": 30113568} {"current_steps": 142700, "total_steps": 181800, "loss": 0.0035, "lr": 6.7207412783512865e-06, "epoch": 15.6985698569857, "percentage": 78.49, "elapsed_time": "5:37:46", "remaining_time": "1:32:33", "throughput": 1485.93, "total_tokens": 30114560} {"current_steps": 142705, "total_steps": 181800, "loss": 0.1287, "lr": 6.71910404855628e-06, "epoch": 15.699119911991199, "percentage": 78.5, "elapsed_time": "5:37:47", "remaining_time": "1:32:32", "throughput": 1485.92, "total_tokens": 30115520} {"current_steps": 142710, "total_steps": 181800, "loss": 0.0257, "lr": 6.717466987247514e-06, "epoch": 15.6996699669967, "percentage": 78.5, "elapsed_time": "5:37:47", "remaining_time": "1:32:31", "throughput": 1485.92, "total_tokens": 30116576} {"current_steps": 142715, "total_steps": 181800, "loss": 0.0951, "lr": 6.715830094440081e-06, "epoch": 15.7002200220022, "percentage": 78.5, "elapsed_time": "5:37:48", "remaining_time": "1:32:30", "throughput": 1485.93, "total_tokens": 30117632} {"current_steps": 142720, "total_steps": 181800, "loss": 0.0109, "lr": 6.714193370149077e-06, "epoch": 15.7007700770077, "percentage": 78.5, "elapsed_time": "5:37:49", "remaining_time": "1:32:30", "throughput": 1485.93, "total_tokens": 30118656} {"current_steps": 142725, "total_steps": 181800, "loss": 0.0925, "lr": 6.71255681438957e-06, "epoch": 15.701320132013201, "percentage": 78.51, "elapsed_time": "5:37:49", "remaining_time": "1:32:29", "throughput": 1485.92, "total_tokens": 30119648} {"current_steps": 142730, "total_steps": 181800, "loss": 0.0709, "lr": 6.710920427176659e-06, "epoch": 15.701870187018702, "percentage": 78.51, "elapsed_time": "5:37:50", "remaining_time": "1:32:28", "throughput": 1485.93, "total_tokens": 30120704} {"current_steps": 142735, "total_steps": 181800, "loss": 0.0023, "lr": 6.709284208525413e-06, "epoch": 15.702420242024202, "percentage": 78.51, "elapsed_time": "5:37:51", "remaining_time": "1:32:28", "throughput": 1485.93, "total_tokens": 30121728} {"current_steps": 142740, "total_steps": 181800, "loss": 0.0213, "lr": 6.707648158450924e-06, "epoch": 15.702970297029703, "percentage": 78.51, "elapsed_time": "5:37:52", "remaining_time": "1:32:27", "throughput": 1485.93, "total_tokens": 30122784} {"current_steps": 142745, "total_steps": 181800, "loss": 0.0012, "lr": 6.706012276968257e-06, "epoch": 15.703520352035204, "percentage": 78.52, "elapsed_time": "5:37:52", "remaining_time": "1:32:26", "throughput": 1485.93, "total_tokens": 30123872} {"current_steps": 142750, "total_steps": 181800, "loss": 0.1055, "lr": 6.704376564092496e-06, "epoch": 15.704070407040705, "percentage": 78.52, "elapsed_time": "5:37:53", "remaining_time": "1:32:25", "throughput": 1485.93, "total_tokens": 30124864} {"current_steps": 142755, "total_steps": 181800, "loss": 0.0571, "lr": 6.702741019838724e-06, "epoch": 15.704620462046204, "percentage": 78.52, "elapsed_time": "5:37:54", "remaining_time": "1:32:25", "throughput": 1485.93, "total_tokens": 30125888} {"current_steps": 142760, "total_steps": 181800, "loss": 0.0103, "lr": 6.7011056442219995e-06, "epoch": 15.705170517051705, "percentage": 78.53, "elapsed_time": "5:37:54", "remaining_time": "1:32:24", "throughput": 1485.93, "total_tokens": 30126976} {"current_steps": 142765, "total_steps": 181800, "loss": 0.0035, "lr": 6.699470437257413e-06, "epoch": 15.705720572057206, "percentage": 78.53, "elapsed_time": "5:37:55", "remaining_time": "1:32:23", "throughput": 1485.93, "total_tokens": 30127968} {"current_steps": 142770, "total_steps": 181800, "loss": 0.0049, "lr": 6.69783539896002e-06, "epoch": 15.706270627062706, "percentage": 78.53, "elapsed_time": "5:37:56", "remaining_time": "1:32:23", "throughput": 1485.93, "total_tokens": 30128992} {"current_steps": 142775, "total_steps": 181800, "loss": 0.0048, "lr": 6.696200529344896e-06, "epoch": 15.706820682068207, "percentage": 78.53, "elapsed_time": "5:37:56", "remaining_time": "1:32:22", "throughput": 1485.93, "total_tokens": 30130112} {"current_steps": 142780, "total_steps": 181800, "loss": 0.041, "lr": 6.6945658284271125e-06, "epoch": 15.707370737073708, "percentage": 78.54, "elapsed_time": "5:37:57", "remaining_time": "1:32:21", "throughput": 1485.94, "total_tokens": 30131200} {"current_steps": 142785, "total_steps": 181800, "loss": 0.0362, "lr": 6.692931296221727e-06, "epoch": 15.707920792079207, "percentage": 78.54, "elapsed_time": "5:37:58", "remaining_time": "1:32:20", "throughput": 1485.94, "total_tokens": 30132256} {"current_steps": 142790, "total_steps": 181800, "loss": 0.0029, "lr": 6.691296932743815e-06, "epoch": 15.708470847084708, "percentage": 78.54, "elapsed_time": "5:37:58", "remaining_time": "1:32:20", "throughput": 1485.94, "total_tokens": 30133248} {"current_steps": 142795, "total_steps": 181800, "loss": 0.1316, "lr": 6.689662738008437e-06, "epoch": 15.70902090209021, "percentage": 78.55, "elapsed_time": "5:37:59", "remaining_time": "1:32:19", "throughput": 1485.94, "total_tokens": 30134368} {"current_steps": 142800, "total_steps": 181800, "loss": 0.0571, "lr": 6.6880287120306416e-06, "epoch": 15.70957095709571, "percentage": 78.55, "elapsed_time": "5:38:00", "remaining_time": "1:32:18", "throughput": 1485.94, "total_tokens": 30135424} {"current_steps": 142805, "total_steps": 181800, "loss": 0.0016, "lr": 6.686394854825498e-06, "epoch": 15.71012101210121, "percentage": 78.55, "elapsed_time": "5:38:01", "remaining_time": "1:32:18", "throughput": 1485.94, "total_tokens": 30136416} {"current_steps": 142810, "total_steps": 181800, "loss": 0.0475, "lr": 6.684761166408066e-06, "epoch": 15.710671067106711, "percentage": 78.55, "elapsed_time": "5:38:01", "remaining_time": "1:32:17", "throughput": 1485.94, "total_tokens": 30137472} {"current_steps": 142815, "total_steps": 181800, "loss": 0.0885, "lr": 6.683127646793411e-06, "epoch": 15.711221122112212, "percentage": 78.56, "elapsed_time": "5:38:02", "remaining_time": "1:32:16", "throughput": 1485.94, "total_tokens": 30138496} {"current_steps": 142820, "total_steps": 181800, "loss": 0.0036, "lr": 6.681494295996576e-06, "epoch": 15.711771177117711, "percentage": 78.56, "elapsed_time": "5:38:03", "remaining_time": "1:32:15", "throughput": 1485.95, "total_tokens": 30139584} {"current_steps": 142825, "total_steps": 181800, "loss": 0.0075, "lr": 6.679861114032612e-06, "epoch": 15.712321232123212, "percentage": 78.56, "elapsed_time": "5:38:03", "remaining_time": "1:32:15", "throughput": 1485.95, "total_tokens": 30140704} {"current_steps": 142830, "total_steps": 181800, "loss": 0.0035, "lr": 6.678228100916578e-06, "epoch": 15.712871287128714, "percentage": 78.56, "elapsed_time": "5:38:04", "remaining_time": "1:32:14", "throughput": 1485.95, "total_tokens": 30141760} {"current_steps": 142835, "total_steps": 181800, "loss": 0.0701, "lr": 6.676595256663523e-06, "epoch": 15.713421342134213, "percentage": 78.57, "elapsed_time": "5:38:05", "remaining_time": "1:32:13", "throughput": 1485.95, "total_tokens": 30142816} {"current_steps": 142840, "total_steps": 181800, "loss": 0.0991, "lr": 6.674962581288505e-06, "epoch": 15.713971397139714, "percentage": 78.57, "elapsed_time": "5:38:05", "remaining_time": "1:32:13", "throughput": 1485.95, "total_tokens": 30143808} {"current_steps": 142845, "total_steps": 181800, "loss": 0.0046, "lr": 6.673330074806564e-06, "epoch": 15.714521452145215, "percentage": 78.57, "elapsed_time": "5:38:06", "remaining_time": "1:32:12", "throughput": 1485.95, "total_tokens": 30144864} {"current_steps": 142850, "total_steps": 181800, "loss": 0.0079, "lr": 6.671697737232738e-06, "epoch": 15.715071507150714, "percentage": 78.58, "elapsed_time": "5:38:07", "remaining_time": "1:32:11", "throughput": 1485.95, "total_tokens": 30145888} {"current_steps": 142855, "total_steps": 181800, "loss": 0.0042, "lr": 6.670065568582087e-06, "epoch": 15.715621562156215, "percentage": 78.58, "elapsed_time": "5:38:07", "remaining_time": "1:32:10", "throughput": 1485.95, "total_tokens": 30146944} {"current_steps": 142860, "total_steps": 181800, "loss": 0.0039, "lr": 6.66843356886964e-06, "epoch": 15.716171617161717, "percentage": 78.58, "elapsed_time": "5:38:08", "remaining_time": "1:32:10", "throughput": 1485.95, "total_tokens": 30147968} {"current_steps": 142865, "total_steps": 181800, "loss": 0.0142, "lr": 6.66680173811044e-06, "epoch": 15.716721672167218, "percentage": 78.58, "elapsed_time": "5:38:09", "remaining_time": "1:32:09", "throughput": 1485.96, "total_tokens": 30149056} {"current_steps": 142870, "total_steps": 181800, "loss": 0.0029, "lr": 6.665170076319541e-06, "epoch": 15.717271727172717, "percentage": 78.59, "elapsed_time": "5:38:10", "remaining_time": "1:32:08", "throughput": 1485.96, "total_tokens": 30150112} {"current_steps": 142875, "total_steps": 181800, "loss": 0.0353, "lr": 6.663538583511966e-06, "epoch": 15.717821782178218, "percentage": 78.59, "elapsed_time": "5:38:10", "remaining_time": "1:32:08", "throughput": 1485.96, "total_tokens": 30151200} {"current_steps": 142880, "total_steps": 181800, "loss": 0.0064, "lr": 6.661907259702763e-06, "epoch": 15.718371837183719, "percentage": 78.59, "elapsed_time": "5:38:11", "remaining_time": "1:32:07", "throughput": 1485.96, "total_tokens": 30152224} {"current_steps": 142885, "total_steps": 181800, "loss": 0.0015, "lr": 6.660276104906954e-06, "epoch": 15.718921892189218, "percentage": 78.59, "elapsed_time": "5:38:12", "remaining_time": "1:32:06", "throughput": 1485.96, "total_tokens": 30153248} {"current_steps": 142890, "total_steps": 181800, "loss": 0.002, "lr": 6.658645119139578e-06, "epoch": 15.71947194719472, "percentage": 78.6, "elapsed_time": "5:38:12", "remaining_time": "1:32:05", "throughput": 1485.96, "total_tokens": 30154272} {"current_steps": 142895, "total_steps": 181800, "loss": 0.0009, "lr": 6.657014302415679e-06, "epoch": 15.72002200220022, "percentage": 78.6, "elapsed_time": "5:38:13", "remaining_time": "1:32:05", "throughput": 1485.96, "total_tokens": 30155296} {"current_steps": 142900, "total_steps": 181800, "loss": 0.0568, "lr": 6.655383654750269e-06, "epoch": 15.72057205720572, "percentage": 78.6, "elapsed_time": "5:38:14", "remaining_time": "1:32:04", "throughput": 1485.96, "total_tokens": 30156352} {"current_steps": 142905, "total_steps": 181800, "loss": 0.0825, "lr": 6.653753176158392e-06, "epoch": 15.721122112211221, "percentage": 78.61, "elapsed_time": "5:38:14", "remaining_time": "1:32:03", "throughput": 1485.97, "total_tokens": 30157440} {"current_steps": 142910, "total_steps": 181800, "loss": 0.0012, "lr": 6.65212286665507e-06, "epoch": 15.721672167216722, "percentage": 78.61, "elapsed_time": "5:38:15", "remaining_time": "1:32:03", "throughput": 1485.97, "total_tokens": 30158528} {"current_steps": 142915, "total_steps": 181800, "loss": 0.0902, "lr": 6.65049272625532e-06, "epoch": 15.722222222222221, "percentage": 78.61, "elapsed_time": "5:38:16", "remaining_time": "1:32:02", "throughput": 1485.97, "total_tokens": 30159616} {"current_steps": 142920, "total_steps": 181800, "loss": 0.0104, "lr": 6.648862754974172e-06, "epoch": 15.722772277227723, "percentage": 78.61, "elapsed_time": "5:38:16", "remaining_time": "1:32:01", "throughput": 1485.97, "total_tokens": 30160672} {"current_steps": 142925, "total_steps": 181800, "loss": 0.0627, "lr": 6.647232952826651e-06, "epoch": 15.723322332233224, "percentage": 78.62, "elapsed_time": "5:38:17", "remaining_time": "1:32:00", "throughput": 1485.98, "total_tokens": 30161728} {"current_steps": 142930, "total_steps": 181800, "loss": 0.1195, "lr": 6.645603319827787e-06, "epoch": 15.723872387238725, "percentage": 78.62, "elapsed_time": "5:38:18", "remaining_time": "1:32:00", "throughput": 1485.98, "total_tokens": 30162752} {"current_steps": 142935, "total_steps": 181800, "loss": 0.0028, "lr": 6.643973855992585e-06, "epoch": 15.724422442244224, "percentage": 78.62, "elapsed_time": "5:38:18", "remaining_time": "1:31:59", "throughput": 1485.98, "total_tokens": 30163808} {"current_steps": 142940, "total_steps": 181800, "loss": 0.0012, "lr": 6.642344561336064e-06, "epoch": 15.724972497249725, "percentage": 78.62, "elapsed_time": "5:38:19", "remaining_time": "1:31:58", "throughput": 1485.98, "total_tokens": 30164864} {"current_steps": 142945, "total_steps": 181800, "loss": 0.0072, "lr": 6.6407154358732435e-06, "epoch": 15.725522552255226, "percentage": 78.63, "elapsed_time": "5:38:20", "remaining_time": "1:31:57", "throughput": 1485.98, "total_tokens": 30165920} {"current_steps": 142950, "total_steps": 181800, "loss": 0.0016, "lr": 6.639086479619139e-06, "epoch": 15.726072607260726, "percentage": 78.63, "elapsed_time": "5:38:21", "remaining_time": "1:31:57", "throughput": 1485.98, "total_tokens": 30166944} {"current_steps": 142955, "total_steps": 181800, "loss": 0.0129, "lr": 6.637457692588772e-06, "epoch": 15.726622662266227, "percentage": 78.63, "elapsed_time": "5:38:21", "remaining_time": "1:31:56", "throughput": 1485.98, "total_tokens": 30168000} {"current_steps": 142960, "total_steps": 181800, "loss": 0.0886, "lr": 6.635829074797148e-06, "epoch": 15.727172717271728, "percentage": 78.64, "elapsed_time": "5:38:22", "remaining_time": "1:31:55", "throughput": 1485.98, "total_tokens": 30169056} {"current_steps": 142965, "total_steps": 181800, "loss": 0.0124, "lr": 6.634200626259265e-06, "epoch": 15.727722772277227, "percentage": 78.64, "elapsed_time": "5:38:23", "remaining_time": "1:31:55", "throughput": 1485.99, "total_tokens": 30170144} {"current_steps": 142970, "total_steps": 181800, "loss": 0.0056, "lr": 6.632572346990151e-06, "epoch": 15.728272827282728, "percentage": 78.64, "elapsed_time": "5:38:23", "remaining_time": "1:31:54", "throughput": 1485.99, "total_tokens": 30171168} {"current_steps": 142975, "total_steps": 181800, "loss": 0.0164, "lr": 6.6309442370047965e-06, "epoch": 15.72882288228823, "percentage": 78.64, "elapsed_time": "5:38:24", "remaining_time": "1:31:53", "throughput": 1485.99, "total_tokens": 30172256} {"current_steps": 142980, "total_steps": 181800, "loss": 0.0162, "lr": 6.629316296318213e-06, "epoch": 15.729372937293729, "percentage": 78.65, "elapsed_time": "5:38:25", "remaining_time": "1:31:52", "throughput": 1485.99, "total_tokens": 30173376} {"current_steps": 142985, "total_steps": 181800, "loss": 0.0053, "lr": 6.627688524945414e-06, "epoch": 15.72992299229923, "percentage": 78.65, "elapsed_time": "5:38:25", "remaining_time": "1:31:52", "throughput": 1486.0, "total_tokens": 30174432} {"current_steps": 142990, "total_steps": 181800, "loss": 0.0039, "lr": 6.626060922901389e-06, "epoch": 15.73047304730473, "percentage": 78.65, "elapsed_time": "5:38:26", "remaining_time": "1:31:51", "throughput": 1486.0, "total_tokens": 30175456} {"current_steps": 142995, "total_steps": 181800, "loss": 0.001, "lr": 6.624433490201148e-06, "epoch": 15.731023102310232, "percentage": 78.66, "elapsed_time": "5:38:27", "remaining_time": "1:31:50", "throughput": 1486.0, "total_tokens": 30176544} {"current_steps": 143000, "total_steps": 181800, "loss": 0.0046, "lr": 6.6228062268596815e-06, "epoch": 15.731573157315731, "percentage": 78.66, "elapsed_time": "5:38:27", "remaining_time": "1:31:50", "throughput": 1486.0, "total_tokens": 30177600} {"current_steps": 143005, "total_steps": 181800, "loss": 0.0794, "lr": 6.621179132891989e-06, "epoch": 15.732123212321232, "percentage": 78.66, "elapsed_time": "5:38:28", "remaining_time": "1:31:49", "throughput": 1486.0, "total_tokens": 30178688} {"current_steps": 143010, "total_steps": 181800, "loss": 0.0391, "lr": 6.619552208313079e-06, "epoch": 15.732673267326733, "percentage": 78.66, "elapsed_time": "5:38:29", "remaining_time": "1:31:48", "throughput": 1486.01, "total_tokens": 30179744} {"current_steps": 143015, "total_steps": 181800, "loss": 0.2059, "lr": 6.61792545313793e-06, "epoch": 15.733223322332233, "percentage": 78.67, "elapsed_time": "5:38:29", "remaining_time": "1:31:47", "throughput": 1486.01, "total_tokens": 30180832} {"current_steps": 143020, "total_steps": 181800, "loss": 0.0053, "lr": 6.616298867381546e-06, "epoch": 15.733773377337734, "percentage": 78.67, "elapsed_time": "5:38:30", "remaining_time": "1:31:47", "throughput": 1486.01, "total_tokens": 30181888} {"current_steps": 143025, "total_steps": 181800, "loss": 0.004, "lr": 6.6146724510589066e-06, "epoch": 15.734323432343235, "percentage": 78.67, "elapsed_time": "5:38:31", "remaining_time": "1:31:46", "throughput": 1486.01, "total_tokens": 30182944} {"current_steps": 143030, "total_steps": 181800, "loss": 0.0036, "lr": 6.6130462041850195e-06, "epoch": 15.734873487348734, "percentage": 78.67, "elapsed_time": "5:38:32", "remaining_time": "1:31:45", "throughput": 1486.02, "total_tokens": 30184064} {"current_steps": 143035, "total_steps": 181800, "loss": 0.0026, "lr": 6.611420126774853e-06, "epoch": 15.735423542354235, "percentage": 78.68, "elapsed_time": "5:38:32", "remaining_time": "1:31:45", "throughput": 1486.02, "total_tokens": 30185088} {"current_steps": 143040, "total_steps": 181800, "loss": 0.0502, "lr": 6.609794218843404e-06, "epoch": 15.735973597359736, "percentage": 78.68, "elapsed_time": "5:38:33", "remaining_time": "1:31:44", "throughput": 1486.02, "total_tokens": 30186176} {"current_steps": 143045, "total_steps": 181800, "loss": 0.0444, "lr": 6.608168480405666e-06, "epoch": 15.736523652365236, "percentage": 78.68, "elapsed_time": "5:38:34", "remaining_time": "1:31:43", "throughput": 1486.02, "total_tokens": 30187232} {"current_steps": 143050, "total_steps": 181800, "loss": 0.0015, "lr": 6.60654291147661e-06, "epoch": 15.737073707370737, "percentage": 78.69, "elapsed_time": "5:38:34", "remaining_time": "1:31:42", "throughput": 1486.03, "total_tokens": 30188320} {"current_steps": 143055, "total_steps": 181800, "loss": 0.0038, "lr": 6.604917512071218e-06, "epoch": 15.737623762376238, "percentage": 78.69, "elapsed_time": "5:38:35", "remaining_time": "1:31:42", "throughput": 1486.03, "total_tokens": 30189376} {"current_steps": 143060, "total_steps": 181800, "loss": 0.0039, "lr": 6.603292282204482e-06, "epoch": 15.738173817381739, "percentage": 78.69, "elapsed_time": "5:38:36", "remaining_time": "1:31:41", "throughput": 1486.03, "total_tokens": 30190432} {"current_steps": 143065, "total_steps": 181800, "loss": 0.0031, "lr": 6.601667221891356e-06, "epoch": 15.738723872387238, "percentage": 78.69, "elapsed_time": "5:38:36", "remaining_time": "1:31:40", "throughput": 1486.03, "total_tokens": 30191520} {"current_steps": 143070, "total_steps": 181800, "loss": 0.2291, "lr": 6.6000423311468525e-06, "epoch": 15.73927392739274, "percentage": 78.7, "elapsed_time": "5:38:37", "remaining_time": "1:31:40", "throughput": 1486.03, "total_tokens": 30192576} {"current_steps": 143075, "total_steps": 181800, "loss": 0.0529, "lr": 6.598417609985927e-06, "epoch": 15.73982398239824, "percentage": 78.7, "elapsed_time": "5:38:38", "remaining_time": "1:31:39", "throughput": 1486.04, "total_tokens": 30193664} {"current_steps": 143080, "total_steps": 181800, "loss": 0.0025, "lr": 6.5967930584235505e-06, "epoch": 15.74037403740374, "percentage": 78.7, "elapsed_time": "5:38:38", "remaining_time": "1:31:38", "throughput": 1486.04, "total_tokens": 30194720} {"current_steps": 143085, "total_steps": 181800, "loss": 0.0525, "lr": 6.595168676474708e-06, "epoch": 15.74092409240924, "percentage": 78.7, "elapsed_time": "5:38:39", "remaining_time": "1:31:37", "throughput": 1486.04, "total_tokens": 30195776} {"current_steps": 143090, "total_steps": 181800, "loss": 0.004, "lr": 6.593544464154358e-06, "epoch": 15.741474147414742, "percentage": 78.71, "elapsed_time": "5:38:40", "remaining_time": "1:31:37", "throughput": 1486.04, "total_tokens": 30196864} {"current_steps": 143095, "total_steps": 181800, "loss": 0.0157, "lr": 6.5919204214774765e-06, "epoch": 15.742024202420241, "percentage": 78.71, "elapsed_time": "5:38:41", "remaining_time": "1:31:36", "throughput": 1486.04, "total_tokens": 30197920} {"current_steps": 143100, "total_steps": 181800, "loss": 0.0524, "lr": 6.590296548459041e-06, "epoch": 15.742574257425742, "percentage": 78.71, "elapsed_time": "5:38:41", "remaining_time": "1:31:35", "throughput": 1486.05, "total_tokens": 30199040} {"current_steps": 143105, "total_steps": 181800, "loss": 0.0049, "lr": 6.588672845113997e-06, "epoch": 15.743124312431243, "percentage": 78.72, "elapsed_time": "5:38:42", "remaining_time": "1:31:35", "throughput": 1486.05, "total_tokens": 30200032} {"current_steps": 143110, "total_steps": 181800, "loss": 0.0027, "lr": 6.58704931145733e-06, "epoch": 15.743674367436743, "percentage": 78.72, "elapsed_time": "5:38:43", "remaining_time": "1:31:34", "throughput": 1486.05, "total_tokens": 30201056} {"current_steps": 143115, "total_steps": 181800, "loss": 0.0407, "lr": 6.585425947503987e-06, "epoch": 15.744224422442244, "percentage": 78.72, "elapsed_time": "5:38:43", "remaining_time": "1:31:33", "throughput": 1486.04, "total_tokens": 30202016} {"current_steps": 143120, "total_steps": 181800, "loss": 0.0014, "lr": 6.583802753268936e-06, "epoch": 15.744774477447745, "percentage": 78.72, "elapsed_time": "5:38:44", "remaining_time": "1:31:32", "throughput": 1486.04, "total_tokens": 30203072} {"current_steps": 143125, "total_steps": 181800, "loss": 0.0335, "lr": 6.582179728767146e-06, "epoch": 15.745324532453246, "percentage": 78.73, "elapsed_time": "5:38:45", "remaining_time": "1:31:32", "throughput": 1486.05, "total_tokens": 30204160} {"current_steps": 143130, "total_steps": 181800, "loss": 0.0143, "lr": 6.58055687401356e-06, "epoch": 15.745874587458745, "percentage": 78.73, "elapsed_time": "5:38:45", "remaining_time": "1:31:31", "throughput": 1486.05, "total_tokens": 30205216} {"current_steps": 143135, "total_steps": 181800, "loss": 0.0037, "lr": 6.57893418902315e-06, "epoch": 15.746424642464246, "percentage": 78.73, "elapsed_time": "5:38:46", "remaining_time": "1:31:30", "throughput": 1486.05, "total_tokens": 30206240} {"current_steps": 143140, "total_steps": 181800, "loss": 0.0062, "lr": 6.577311673810857e-06, "epoch": 15.746974697469748, "percentage": 78.73, "elapsed_time": "5:38:47", "remaining_time": "1:31:30", "throughput": 1486.05, "total_tokens": 30207232} {"current_steps": 143145, "total_steps": 181800, "loss": 0.0019, "lr": 6.575689328391648e-06, "epoch": 15.747524752475247, "percentage": 78.74, "elapsed_time": "5:38:47", "remaining_time": "1:31:29", "throughput": 1486.05, "total_tokens": 30208256} {"current_steps": 143150, "total_steps": 181800, "loss": 0.172, "lr": 6.574067152780467e-06, "epoch": 15.748074807480748, "percentage": 78.74, "elapsed_time": "5:38:48", "remaining_time": "1:31:28", "throughput": 1486.05, "total_tokens": 30209280} {"current_steps": 143155, "total_steps": 181800, "loss": 0.0403, "lr": 6.572445146992262e-06, "epoch": 15.748624862486249, "percentage": 78.74, "elapsed_time": "5:38:49", "remaining_time": "1:31:27", "throughput": 1486.05, "total_tokens": 30210400} {"current_steps": 143160, "total_steps": 181800, "loss": 0.0016, "lr": 6.570823311041999e-06, "epoch": 15.749174917491748, "percentage": 78.75, "elapsed_time": "5:38:50", "remaining_time": "1:31:27", "throughput": 1486.05, "total_tokens": 30211392} {"current_steps": 143165, "total_steps": 181800, "loss": 0.0033, "lr": 6.569201644944606e-06, "epoch": 15.74972497249725, "percentage": 78.75, "elapsed_time": "5:38:50", "remaining_time": "1:31:26", "throughput": 1486.06, "total_tokens": 30212544} {"current_steps": 143170, "total_steps": 181800, "loss": 0.0339, "lr": 6.567580148715044e-06, "epoch": 15.75027502750275, "percentage": 78.75, "elapsed_time": "5:38:51", "remaining_time": "1:31:25", "throughput": 1486.06, "total_tokens": 30213664} {"current_steps": 143175, "total_steps": 181800, "loss": 0.092, "lr": 6.565958822368251e-06, "epoch": 15.750825082508252, "percentage": 78.75, "elapsed_time": "5:38:52", "remaining_time": "1:31:25", "throughput": 1486.06, "total_tokens": 30214688} {"current_steps": 143180, "total_steps": 181800, "loss": 0.0019, "lr": 6.564337665919154e-06, "epoch": 15.751375137513751, "percentage": 78.76, "elapsed_time": "5:38:52", "remaining_time": "1:31:24", "throughput": 1486.06, "total_tokens": 30215744} {"current_steps": 143185, "total_steps": 181800, "loss": 0.1043, "lr": 6.5627166793827275e-06, "epoch": 15.751925192519252, "percentage": 78.76, "elapsed_time": "5:38:53", "remaining_time": "1:31:23", "throughput": 1486.06, "total_tokens": 30216800} {"current_steps": 143190, "total_steps": 181800, "loss": 0.0033, "lr": 6.561095862773886e-06, "epoch": 15.752475247524753, "percentage": 78.76, "elapsed_time": "5:38:54", "remaining_time": "1:31:22", "throughput": 1486.07, "total_tokens": 30217888} {"current_steps": 143195, "total_steps": 181800, "loss": 0.003, "lr": 6.559475216107585e-06, "epoch": 15.753025302530252, "percentage": 78.77, "elapsed_time": "5:38:54", "remaining_time": "1:31:22", "throughput": 1486.07, "total_tokens": 30218912} {"current_steps": 143200, "total_steps": 181800, "loss": 0.063, "lr": 6.55785473939875e-06, "epoch": 15.753575357535754, "percentage": 78.77, "elapsed_time": "5:38:55", "remaining_time": "1:31:21", "throughput": 1486.07, "total_tokens": 30219936} {"current_steps": 143205, "total_steps": 181800, "loss": 0.0036, "lr": 6.5562344326623116e-06, "epoch": 15.754125412541255, "percentage": 78.77, "elapsed_time": "5:38:56", "remaining_time": "1:31:20", "throughput": 1486.07, "total_tokens": 30221024} {"current_steps": 143210, "total_steps": 181800, "loss": 0.0166, "lr": 6.554614295913211e-06, "epoch": 15.754675467546754, "percentage": 78.77, "elapsed_time": "5:38:56", "remaining_time": "1:31:20", "throughput": 1486.07, "total_tokens": 30222144} {"current_steps": 143215, "total_steps": 181800, "loss": 0.0091, "lr": 6.552994329166382e-06, "epoch": 15.755225522552255, "percentage": 78.78, "elapsed_time": "5:38:57", "remaining_time": "1:31:19", "throughput": 1486.08, "total_tokens": 30223232} {"current_steps": 143220, "total_steps": 181800, "loss": 0.0759, "lr": 6.551374532436755e-06, "epoch": 15.755775577557756, "percentage": 78.78, "elapsed_time": "5:38:58", "remaining_time": "1:31:18", "throughput": 1486.08, "total_tokens": 30224256} {"current_steps": 143225, "total_steps": 181800, "loss": 0.0949, "lr": 6.549754905739258e-06, "epoch": 15.756325632563257, "percentage": 78.78, "elapsed_time": "5:38:58", "remaining_time": "1:31:17", "throughput": 1486.08, "total_tokens": 30225312} {"current_steps": 143230, "total_steps": 181800, "loss": 0.0022, "lr": 6.54813544908881e-06, "epoch": 15.756875687568757, "percentage": 78.78, "elapsed_time": "5:38:59", "remaining_time": "1:31:17", "throughput": 1486.08, "total_tokens": 30226432} {"current_steps": 143235, "total_steps": 181800, "loss": 0.0151, "lr": 6.5465161625003516e-06, "epoch": 15.757425742574258, "percentage": 78.79, "elapsed_time": "5:39:00", "remaining_time": "1:31:16", "throughput": 1486.08, "total_tokens": 30227488} {"current_steps": 143240, "total_steps": 181800, "loss": 0.0209, "lr": 6.544897045988791e-06, "epoch": 15.757975797579759, "percentage": 78.79, "elapsed_time": "5:39:01", "remaining_time": "1:31:15", "throughput": 1486.09, "total_tokens": 30228544} {"current_steps": 143245, "total_steps": 181800, "loss": 0.1365, "lr": 6.543278099569059e-06, "epoch": 15.758525852585258, "percentage": 78.79, "elapsed_time": "5:39:01", "remaining_time": "1:31:15", "throughput": 1486.09, "total_tokens": 30229632} {"current_steps": 143250, "total_steps": 181800, "loss": 0.0669, "lr": 6.541659323256083e-06, "epoch": 15.75907590759076, "percentage": 78.8, "elapsed_time": "5:39:02", "remaining_time": "1:31:14", "throughput": 1486.09, "total_tokens": 30230688} {"current_steps": 143255, "total_steps": 181800, "loss": 0.0073, "lr": 6.540040717064769e-06, "epoch": 15.75962596259626, "percentage": 78.8, "elapsed_time": "5:39:03", "remaining_time": "1:31:13", "throughput": 1486.09, "total_tokens": 30231808} {"current_steps": 143260, "total_steps": 181800, "loss": 0.086, "lr": 6.538422281010048e-06, "epoch": 15.76017601760176, "percentage": 78.8, "elapsed_time": "5:39:03", "remaining_time": "1:31:12", "throughput": 1486.1, "total_tokens": 30232928} {"current_steps": 143265, "total_steps": 181800, "loss": 0.0024, "lr": 6.536804015106823e-06, "epoch": 15.76072607260726, "percentage": 78.8, "elapsed_time": "5:39:04", "remaining_time": "1:31:12", "throughput": 1486.1, "total_tokens": 30233984} {"current_steps": 143270, "total_steps": 181800, "loss": 0.0368, "lr": 6.535185919370018e-06, "epoch": 15.761276127612762, "percentage": 78.81, "elapsed_time": "5:39:05", "remaining_time": "1:31:11", "throughput": 1486.1, "total_tokens": 30235072} {"current_steps": 143275, "total_steps": 181800, "loss": 0.0022, "lr": 6.533567993814549e-06, "epoch": 15.761826182618261, "percentage": 78.81, "elapsed_time": "5:39:05", "remaining_time": "1:31:10", "throughput": 1486.11, "total_tokens": 30236192} {"current_steps": 143280, "total_steps": 181800, "loss": 0.0405, "lr": 6.531950238455317e-06, "epoch": 15.762376237623762, "percentage": 78.81, "elapsed_time": "5:39:06", "remaining_time": "1:31:10", "throughput": 1486.11, "total_tokens": 30237152} {"current_steps": 143285, "total_steps": 181800, "loss": 0.0028, "lr": 6.530332653307245e-06, "epoch": 15.762926292629263, "percentage": 78.81, "elapsed_time": "5:39:07", "remaining_time": "1:31:09", "throughput": 1486.11, "total_tokens": 30238176} {"current_steps": 143290, "total_steps": 181800, "loss": 0.0028, "lr": 6.5287152383852326e-06, "epoch": 15.763476347634764, "percentage": 78.82, "elapsed_time": "5:39:07", "remaining_time": "1:31:08", "throughput": 1486.11, "total_tokens": 30239200} {"current_steps": 143295, "total_steps": 181800, "loss": 0.0017, "lr": 6.527097993704181e-06, "epoch": 15.764026402640264, "percentage": 78.82, "elapsed_time": "5:39:08", "remaining_time": "1:31:07", "throughput": 1486.11, "total_tokens": 30240256} {"current_steps": 143300, "total_steps": 181800, "loss": 0.0623, "lr": 6.525480919279006e-06, "epoch": 15.764576457645765, "percentage": 78.82, "elapsed_time": "5:39:09", "remaining_time": "1:31:07", "throughput": 1486.11, "total_tokens": 30241280} {"current_steps": 143305, "total_steps": 181800, "loss": 0.0068, "lr": 6.523864015124606e-06, "epoch": 15.765126512651266, "percentage": 78.83, "elapsed_time": "5:39:10", "remaining_time": "1:31:06", "throughput": 1486.11, "total_tokens": 30242400} {"current_steps": 143310, "total_steps": 181800, "loss": 0.007, "lr": 6.5222472812558945e-06, "epoch": 15.765676567656765, "percentage": 78.83, "elapsed_time": "5:39:10", "remaining_time": "1:31:05", "throughput": 1486.11, "total_tokens": 30243488} {"current_steps": 143315, "total_steps": 181800, "loss": 0.0357, "lr": 6.520630717687762e-06, "epoch": 15.766226622662266, "percentage": 78.83, "elapsed_time": "5:39:11", "remaining_time": "1:31:05", "throughput": 1486.11, "total_tokens": 30244512} {"current_steps": 143320, "total_steps": 181800, "loss": 0.0054, "lr": 6.519014324435102e-06, "epoch": 15.766776677667767, "percentage": 78.83, "elapsed_time": "5:39:12", "remaining_time": "1:31:04", "throughput": 1486.12, "total_tokens": 30245568} {"current_steps": 143325, "total_steps": 181800, "loss": 0.0103, "lr": 6.51739810151282e-06, "epoch": 15.767326732673267, "percentage": 78.84, "elapsed_time": "5:39:12", "remaining_time": "1:31:03", "throughput": 1486.12, "total_tokens": 30246624} {"current_steps": 143330, "total_steps": 181800, "loss": 0.0021, "lr": 6.515782048935809e-06, "epoch": 15.767876787678768, "percentage": 78.84, "elapsed_time": "5:39:13", "remaining_time": "1:31:02", "throughput": 1486.12, "total_tokens": 30247680} {"current_steps": 143335, "total_steps": 181800, "loss": 0.0709, "lr": 6.514166166718974e-06, "epoch": 15.768426842684269, "percentage": 78.84, "elapsed_time": "5:39:14", "remaining_time": "1:31:02", "throughput": 1486.12, "total_tokens": 30248768} {"current_steps": 143340, "total_steps": 181800, "loss": 0.0056, "lr": 6.512550454877198e-06, "epoch": 15.768976897689768, "percentage": 78.84, "elapsed_time": "5:39:14", "remaining_time": "1:31:01", "throughput": 1486.12, "total_tokens": 30249856} {"current_steps": 143345, "total_steps": 181800, "loss": 0.0101, "lr": 6.510934913425368e-06, "epoch": 15.76952695269527, "percentage": 78.85, "elapsed_time": "5:39:15", "remaining_time": "1:31:00", "throughput": 1486.13, "total_tokens": 30250944} {"current_steps": 143350, "total_steps": 181800, "loss": 0.1541, "lr": 6.509319542378384e-06, "epoch": 15.77007700770077, "percentage": 78.85, "elapsed_time": "5:39:16", "remaining_time": "1:31:00", "throughput": 1486.13, "total_tokens": 30252064} {"current_steps": 143355, "total_steps": 181800, "loss": 0.0062, "lr": 6.5077043417511225e-06, "epoch": 15.770627062706271, "percentage": 78.85, "elapsed_time": "5:39:16", "remaining_time": "1:30:59", "throughput": 1486.13, "total_tokens": 30253088} {"current_steps": 143360, "total_steps": 181800, "loss": 0.0668, "lr": 6.506089311558478e-06, "epoch": 15.77117711771177, "percentage": 78.86, "elapsed_time": "5:39:17", "remaining_time": "1:30:58", "throughput": 1486.13, "total_tokens": 30254144} {"current_steps": 143365, "total_steps": 181800, "loss": 0.0485, "lr": 6.50447445181534e-06, "epoch": 15.771727172717272, "percentage": 78.86, "elapsed_time": "5:39:18", "remaining_time": "1:30:57", "throughput": 1486.14, "total_tokens": 30255264} {"current_steps": 143370, "total_steps": 181800, "loss": 0.0089, "lr": 6.502859762536578e-06, "epoch": 15.772277227722773, "percentage": 78.86, "elapsed_time": "5:39:18", "remaining_time": "1:30:57", "throughput": 1486.14, "total_tokens": 30256320} {"current_steps": 143375, "total_steps": 181800, "loss": 0.0087, "lr": 6.501245243737089e-06, "epoch": 15.772827282728272, "percentage": 78.86, "elapsed_time": "5:39:19", "remaining_time": "1:30:56", "throughput": 1486.14, "total_tokens": 30257344} {"current_steps": 143380, "total_steps": 181800, "loss": 0.0107, "lr": 6.499630895431741e-06, "epoch": 15.773377337733773, "percentage": 78.87, "elapsed_time": "5:39:20", "remaining_time": "1:30:55", "throughput": 1486.14, "total_tokens": 30258400} {"current_steps": 143385, "total_steps": 181800, "loss": 0.0252, "lr": 6.498016717635416e-06, "epoch": 15.773927392739274, "percentage": 78.87, "elapsed_time": "5:39:21", "remaining_time": "1:30:55", "throughput": 1486.14, "total_tokens": 30259424} {"current_steps": 143390, "total_steps": 181800, "loss": 0.0022, "lr": 6.496402710363e-06, "epoch": 15.774477447744774, "percentage": 78.87, "elapsed_time": "5:39:21", "remaining_time": "1:30:54", "throughput": 1486.14, "total_tokens": 30260480} {"current_steps": 143395, "total_steps": 181800, "loss": 0.0423, "lr": 6.494788873629354e-06, "epoch": 15.775027502750275, "percentage": 78.88, "elapsed_time": "5:39:22", "remaining_time": "1:30:53", "throughput": 1486.15, "total_tokens": 30261568} {"current_steps": 143400, "total_steps": 181800, "loss": 0.0088, "lr": 6.493175207449367e-06, "epoch": 15.775577557755776, "percentage": 78.88, "elapsed_time": "5:39:23", "remaining_time": "1:30:52", "throughput": 1486.15, "total_tokens": 30262592} {"current_steps": 143405, "total_steps": 181800, "loss": 0.0473, "lr": 6.491561711837899e-06, "epoch": 15.776127612761275, "percentage": 78.88, "elapsed_time": "5:39:23", "remaining_time": "1:30:52", "throughput": 1486.15, "total_tokens": 30263616} {"current_steps": 143410, "total_steps": 181800, "loss": 0.0581, "lr": 6.48994838680983e-06, "epoch": 15.776677667766776, "percentage": 78.88, "elapsed_time": "5:39:24", "remaining_time": "1:30:51", "throughput": 1486.15, "total_tokens": 30264704} {"current_steps": 143415, "total_steps": 181800, "loss": 0.0853, "lr": 6.488335232380016e-06, "epoch": 15.777227722772277, "percentage": 78.89, "elapsed_time": "5:39:25", "remaining_time": "1:30:50", "throughput": 1486.15, "total_tokens": 30265824} {"current_steps": 143420, "total_steps": 181800, "loss": 0.003, "lr": 6.486722248563335e-06, "epoch": 15.777777777777779, "percentage": 78.89, "elapsed_time": "5:39:25", "remaining_time": "1:30:50", "throughput": 1486.16, "total_tokens": 30266880} {"current_steps": 143425, "total_steps": 181800, "loss": 0.0041, "lr": 6.485109435374659e-06, "epoch": 15.778327832783278, "percentage": 78.89, "elapsed_time": "5:39:26", "remaining_time": "1:30:49", "throughput": 1486.16, "total_tokens": 30267968} {"current_steps": 143430, "total_steps": 181800, "loss": 0.0094, "lr": 6.483496792828845e-06, "epoch": 15.778877887788779, "percentage": 78.89, "elapsed_time": "5:39:27", "remaining_time": "1:30:48", "throughput": 1486.16, "total_tokens": 30269024} {"current_steps": 143435, "total_steps": 181800, "loss": 0.0021, "lr": 6.481884320940748e-06, "epoch": 15.77942794279428, "percentage": 78.9, "elapsed_time": "5:39:27", "remaining_time": "1:30:47", "throughput": 1486.16, "total_tokens": 30270112} {"current_steps": 143440, "total_steps": 181800, "loss": 0.095, "lr": 6.48027201972524e-06, "epoch": 15.77997799779978, "percentage": 78.9, "elapsed_time": "5:39:28", "remaining_time": "1:30:47", "throughput": 1486.17, "total_tokens": 30271232} {"current_steps": 143445, "total_steps": 181800, "loss": 0.0054, "lr": 6.478659889197175e-06, "epoch": 15.78052805280528, "percentage": 78.9, "elapsed_time": "5:39:29", "remaining_time": "1:30:46", "throughput": 1486.17, "total_tokens": 30272320} {"current_steps": 143450, "total_steps": 181800, "loss": 0.0527, "lr": 6.477047929371421e-06, "epoch": 15.781078107810782, "percentage": 78.91, "elapsed_time": "5:39:30", "remaining_time": "1:30:45", "throughput": 1486.17, "total_tokens": 30273376} {"current_steps": 143455, "total_steps": 181800, "loss": 0.0051, "lr": 6.47543614026283e-06, "epoch": 15.781628162816281, "percentage": 78.91, "elapsed_time": "5:39:30", "remaining_time": "1:30:45", "throughput": 1486.18, "total_tokens": 30274496} {"current_steps": 143460, "total_steps": 181800, "loss": 0.0022, "lr": 6.473824521886249e-06, "epoch": 15.782178217821782, "percentage": 78.91, "elapsed_time": "5:39:31", "remaining_time": "1:30:44", "throughput": 1486.18, "total_tokens": 30275520} {"current_steps": 143465, "total_steps": 181800, "loss": 0.001, "lr": 6.4722130742565445e-06, "epoch": 15.782728272827283, "percentage": 78.91, "elapsed_time": "5:39:32", "remaining_time": "1:30:43", "throughput": 1486.18, "total_tokens": 30276512} {"current_steps": 143470, "total_steps": 181800, "loss": 0.0021, "lr": 6.4706017973885535e-06, "epoch": 15.783278327832782, "percentage": 78.92, "elapsed_time": "5:39:32", "remaining_time": "1:30:42", "throughput": 1486.17, "total_tokens": 30277504} {"current_steps": 143475, "total_steps": 181800, "loss": 0.0071, "lr": 6.468990691297133e-06, "epoch": 15.783828382838283, "percentage": 78.92, "elapsed_time": "5:39:33", "remaining_time": "1:30:42", "throughput": 1486.17, "total_tokens": 30278528} {"current_steps": 143480, "total_steps": 181800, "loss": 0.015, "lr": 6.467379755997144e-06, "epoch": 15.784378437843785, "percentage": 78.92, "elapsed_time": "5:39:34", "remaining_time": "1:30:41", "throughput": 1486.18, "total_tokens": 30279584} {"current_steps": 143485, "total_steps": 181800, "loss": 0.0606, "lr": 6.465768991503413e-06, "epoch": 15.784928492849286, "percentage": 78.92, "elapsed_time": "5:39:34", "remaining_time": "1:30:40", "throughput": 1486.18, "total_tokens": 30280640} {"current_steps": 143490, "total_steps": 181800, "loss": 0.0025, "lr": 6.4641583978308026e-06, "epoch": 15.785478547854785, "percentage": 78.93, "elapsed_time": "5:39:35", "remaining_time": "1:30:40", "throughput": 1486.18, "total_tokens": 30281664} {"current_steps": 143495, "total_steps": 181800, "loss": 0.002, "lr": 6.462547974994143e-06, "epoch": 15.786028602860286, "percentage": 78.93, "elapsed_time": "5:39:36", "remaining_time": "1:30:39", "throughput": 1486.18, "total_tokens": 30282752} {"current_steps": 143500, "total_steps": 181800, "loss": 0.0618, "lr": 6.460937723008284e-06, "epoch": 15.786578657865787, "percentage": 78.93, "elapsed_time": "5:39:36", "remaining_time": "1:30:38", "throughput": 1486.18, "total_tokens": 30283776} {"current_steps": 143505, "total_steps": 181800, "loss": 0.0427, "lr": 6.459327641888074e-06, "epoch": 15.787128712871286, "percentage": 78.94, "elapsed_time": "5:39:37", "remaining_time": "1:30:37", "throughput": 1486.18, "total_tokens": 30284800} {"current_steps": 143510, "total_steps": 181800, "loss": 0.0038, "lr": 6.4577177316483386e-06, "epoch": 15.787678767876788, "percentage": 78.94, "elapsed_time": "5:39:38", "remaining_time": "1:30:37", "throughput": 1486.18, "total_tokens": 30285888} {"current_steps": 143515, "total_steps": 181800, "loss": 0.0084, "lr": 6.456107992303926e-06, "epoch": 15.788228822882289, "percentage": 78.94, "elapsed_time": "5:39:38", "remaining_time": "1:30:36", "throughput": 1486.19, "total_tokens": 30286944} {"current_steps": 143520, "total_steps": 181800, "loss": 0.0049, "lr": 6.454498423869659e-06, "epoch": 15.788778877887788, "percentage": 78.94, "elapsed_time": "5:39:39", "remaining_time": "1:30:35", "throughput": 1486.18, "total_tokens": 30287936} {"current_steps": 143525, "total_steps": 181800, "loss": 0.1314, "lr": 6.4528890263603925e-06, "epoch": 15.789328932893289, "percentage": 78.95, "elapsed_time": "5:39:40", "remaining_time": "1:30:34", "throughput": 1486.19, "total_tokens": 30288992} {"current_steps": 143530, "total_steps": 181800, "loss": 0.007, "lr": 6.451279799790938e-06, "epoch": 15.78987898789879, "percentage": 78.95, "elapsed_time": "5:39:41", "remaining_time": "1:30:34", "throughput": 1486.19, "total_tokens": 30290048} {"current_steps": 143535, "total_steps": 181800, "loss": 0.0966, "lr": 6.44967074417614e-06, "epoch": 15.79042904290429, "percentage": 78.95, "elapsed_time": "5:39:41", "remaining_time": "1:30:33", "throughput": 1486.19, "total_tokens": 30291040} {"current_steps": 143540, "total_steps": 181800, "loss": 0.0097, "lr": 6.44806185953083e-06, "epoch": 15.79097909790979, "percentage": 78.95, "elapsed_time": "5:39:42", "remaining_time": "1:30:32", "throughput": 1486.19, "total_tokens": 30292064} {"current_steps": 143545, "total_steps": 181800, "loss": 0.1085, "lr": 6.446453145869824e-06, "epoch": 15.791529152915292, "percentage": 78.96, "elapsed_time": "5:39:43", "remaining_time": "1:30:32", "throughput": 1486.19, "total_tokens": 30293152} {"current_steps": 143550, "total_steps": 181800, "loss": 0.0044, "lr": 6.444844603207967e-06, "epoch": 15.792079207920793, "percentage": 78.96, "elapsed_time": "5:39:43", "remaining_time": "1:30:31", "throughput": 1486.19, "total_tokens": 30294240} {"current_steps": 143555, "total_steps": 181800, "loss": 0.0693, "lr": 6.443236231560063e-06, "epoch": 15.792629262926292, "percentage": 78.96, "elapsed_time": "5:39:44", "remaining_time": "1:30:30", "throughput": 1486.19, "total_tokens": 30295264} {"current_steps": 143560, "total_steps": 181800, "loss": 0.01, "lr": 6.4416280309409466e-06, "epoch": 15.793179317931793, "percentage": 78.97, "elapsed_time": "5:39:45", "remaining_time": "1:30:29", "throughput": 1486.19, "total_tokens": 30296256} {"current_steps": 143565, "total_steps": 181800, "loss": 0.0047, "lr": 6.440020001365449e-06, "epoch": 15.793729372937294, "percentage": 78.97, "elapsed_time": "5:39:45", "remaining_time": "1:30:29", "throughput": 1486.19, "total_tokens": 30297312} {"current_steps": 143570, "total_steps": 181800, "loss": 0.0052, "lr": 6.4384121428483715e-06, "epoch": 15.794279427942794, "percentage": 78.97, "elapsed_time": "5:39:46", "remaining_time": "1:30:28", "throughput": 1486.2, "total_tokens": 30298400} {"current_steps": 143575, "total_steps": 181800, "loss": 0.0027, "lr": 6.436804455404552e-06, "epoch": 15.794829482948295, "percentage": 78.97, "elapsed_time": "5:39:47", "remaining_time": "1:30:27", "throughput": 1486.2, "total_tokens": 30299456} {"current_steps": 143580, "total_steps": 181800, "loss": 0.0057, "lr": 6.435196939048796e-06, "epoch": 15.795379537953796, "percentage": 78.98, "elapsed_time": "5:39:47", "remaining_time": "1:30:27", "throughput": 1486.2, "total_tokens": 30300480} {"current_steps": 143585, "total_steps": 181800, "loss": 0.0458, "lr": 6.433589593795917e-06, "epoch": 15.795929592959295, "percentage": 78.98, "elapsed_time": "5:39:48", "remaining_time": "1:30:26", "throughput": 1486.2, "total_tokens": 30301600} {"current_steps": 143590, "total_steps": 181800, "loss": 0.0028, "lr": 6.431982419660732e-06, "epoch": 15.796479647964796, "percentage": 78.98, "elapsed_time": "5:39:49", "remaining_time": "1:30:25", "throughput": 1486.2, "total_tokens": 30302656} {"current_steps": 143595, "total_steps": 181800, "loss": 0.0061, "lr": 6.430375416658055e-06, "epoch": 15.797029702970297, "percentage": 78.99, "elapsed_time": "5:39:50", "remaining_time": "1:30:24", "throughput": 1486.2, "total_tokens": 30303712} {"current_steps": 143600, "total_steps": 181800, "loss": 0.0188, "lr": 6.428768584802705e-06, "epoch": 15.797579757975798, "percentage": 78.99, "elapsed_time": "5:39:50", "remaining_time": "1:30:24", "throughput": 1486.21, "total_tokens": 30304800} {"current_steps": 143605, "total_steps": 181800, "loss": 0.0078, "lr": 6.4271619241094845e-06, "epoch": 15.798129812981298, "percentage": 78.99, "elapsed_time": "5:39:51", "remaining_time": "1:30:23", "throughput": 1486.21, "total_tokens": 30305824} {"current_steps": 143610, "total_steps": 181800, "loss": 0.002, "lr": 6.425555434593191e-06, "epoch": 15.798679867986799, "percentage": 78.99, "elapsed_time": "5:39:52", "remaining_time": "1:30:22", "throughput": 1486.21, "total_tokens": 30306848} {"current_steps": 143615, "total_steps": 181800, "loss": 0.0377, "lr": 6.42394911626864e-06, "epoch": 15.7992299229923, "percentage": 79.0, "elapsed_time": "5:39:52", "remaining_time": "1:30:22", "throughput": 1486.21, "total_tokens": 30307936} {"current_steps": 143620, "total_steps": 181800, "loss": 0.0802, "lr": 6.422342969150646e-06, "epoch": 15.7997799779978, "percentage": 79.0, "elapsed_time": "5:39:53", "remaining_time": "1:30:21", "throughput": 1486.21, "total_tokens": 30308992} {"current_steps": 143625, "total_steps": 181800, "loss": 0.0036, "lr": 6.420736993253995e-06, "epoch": 15.8003300330033, "percentage": 79.0, "elapsed_time": "5:39:54", "remaining_time": "1:30:20", "throughput": 1486.21, "total_tokens": 30310048} {"current_steps": 143630, "total_steps": 181800, "loss": 0.0186, "lr": 6.4191311885935026e-06, "epoch": 15.800880088008801, "percentage": 79.0, "elapsed_time": "5:39:54", "remaining_time": "1:30:19", "throughput": 1486.21, "total_tokens": 30311040} {"current_steps": 143635, "total_steps": 181800, "loss": 0.0052, "lr": 6.417525555183954e-06, "epoch": 15.8014301430143, "percentage": 79.01, "elapsed_time": "5:39:55", "remaining_time": "1:30:19", "throughput": 1486.21, "total_tokens": 30312096} {"current_steps": 143640, "total_steps": 181800, "loss": 0.0463, "lr": 6.415920093040162e-06, "epoch": 15.801980198019802, "percentage": 79.01, "elapsed_time": "5:39:56", "remaining_time": "1:30:18", "throughput": 1486.21, "total_tokens": 30313120} {"current_steps": 143645, "total_steps": 181800, "loss": 0.004, "lr": 6.414314802176913e-06, "epoch": 15.802530253025303, "percentage": 79.01, "elapsed_time": "5:39:56", "remaining_time": "1:30:17", "throughput": 1486.22, "total_tokens": 30314240} {"current_steps": 143650, "total_steps": 181800, "loss": 0.0486, "lr": 6.412709682609003e-06, "epoch": 15.803080308030804, "percentage": 79.02, "elapsed_time": "5:39:57", "remaining_time": "1:30:17", "throughput": 1486.22, "total_tokens": 30315328} {"current_steps": 143655, "total_steps": 181800, "loss": 0.0582, "lr": 6.4111047343512365e-06, "epoch": 15.803630363036303, "percentage": 79.02, "elapsed_time": "5:39:58", "remaining_time": "1:30:16", "throughput": 1486.22, "total_tokens": 30316384} {"current_steps": 143660, "total_steps": 181800, "loss": 0.098, "lr": 6.4094999574183936e-06, "epoch": 15.804180418041804, "percentage": 79.02, "elapsed_time": "5:39:59", "remaining_time": "1:30:15", "throughput": 1486.22, "total_tokens": 30317472} {"current_steps": 143665, "total_steps": 181800, "loss": 0.0512, "lr": 6.407895351825274e-06, "epoch": 15.804730473047305, "percentage": 79.02, "elapsed_time": "5:39:59", "remaining_time": "1:30:14", "throughput": 1486.22, "total_tokens": 30318496} {"current_steps": 143670, "total_steps": 181800, "loss": 0.0026, "lr": 6.406290917586655e-06, "epoch": 15.805280528052805, "percentage": 79.03, "elapsed_time": "5:40:00", "remaining_time": "1:30:14", "throughput": 1486.23, "total_tokens": 30319584} {"current_steps": 143675, "total_steps": 181800, "loss": 0.0297, "lr": 6.404686654717329e-06, "epoch": 15.805830583058306, "percentage": 79.03, "elapsed_time": "5:40:01", "remaining_time": "1:30:13", "throughput": 1486.23, "total_tokens": 30320672} {"current_steps": 143680, "total_steps": 181800, "loss": 0.0979, "lr": 6.4030825632320905e-06, "epoch": 15.806380638063807, "percentage": 79.03, "elapsed_time": "5:40:01", "remaining_time": "1:30:12", "throughput": 1486.23, "total_tokens": 30321760} {"current_steps": 143685, "total_steps": 181800, "loss": 0.0107, "lr": 6.401478643145711e-06, "epoch": 15.806930693069306, "percentage": 79.03, "elapsed_time": "5:40:02", "remaining_time": "1:30:12", "throughput": 1486.23, "total_tokens": 30322784} {"current_steps": 143690, "total_steps": 181800, "loss": 0.0118, "lr": 6.399874894472985e-06, "epoch": 15.807480748074807, "percentage": 79.04, "elapsed_time": "5:40:03", "remaining_time": "1:30:11", "throughput": 1486.23, "total_tokens": 30323808} {"current_steps": 143695, "total_steps": 181800, "loss": 0.0115, "lr": 6.398271317228685e-06, "epoch": 15.808030803080309, "percentage": 79.04, "elapsed_time": "5:40:03", "remaining_time": "1:30:10", "throughput": 1486.23, "total_tokens": 30324864} {"current_steps": 143700, "total_steps": 181800, "loss": 0.0043, "lr": 6.396667911427587e-06, "epoch": 15.808580858085808, "percentage": 79.04, "elapsed_time": "5:40:04", "remaining_time": "1:30:09", "throughput": 1486.24, "total_tokens": 30325920} {"current_steps": 143705, "total_steps": 181800, "loss": 0.0352, "lr": 6.395064677084475e-06, "epoch": 15.809130913091309, "percentage": 79.05, "elapsed_time": "5:40:05", "remaining_time": "1:30:09", "throughput": 1486.24, "total_tokens": 30327040} {"current_steps": 143710, "total_steps": 181800, "loss": 0.1139, "lr": 6.393461614214122e-06, "epoch": 15.80968096809681, "percentage": 79.05, "elapsed_time": "5:40:05", "remaining_time": "1:30:08", "throughput": 1486.24, "total_tokens": 30328096} {"current_steps": 143715, "total_steps": 181800, "loss": 0.0099, "lr": 6.391858722831312e-06, "epoch": 15.810231023102311, "percentage": 79.05, "elapsed_time": "5:40:06", "remaining_time": "1:30:07", "throughput": 1486.24, "total_tokens": 30329120} {"current_steps": 143720, "total_steps": 181800, "loss": 0.0042, "lr": 6.390256002950815e-06, "epoch": 15.81078107810781, "percentage": 79.05, "elapsed_time": "5:40:07", "remaining_time": "1:30:07", "throughput": 1486.24, "total_tokens": 30330176} {"current_steps": 143725, "total_steps": 181800, "loss": 0.0053, "lr": 6.388653454587387e-06, "epoch": 15.811331133113312, "percentage": 79.06, "elapsed_time": "5:40:07", "remaining_time": "1:30:06", "throughput": 1486.24, "total_tokens": 30331168} {"current_steps": 143730, "total_steps": 181800, "loss": 0.0061, "lr": 6.387051077755812e-06, "epoch": 15.811881188118813, "percentage": 79.06, "elapsed_time": "5:40:08", "remaining_time": "1:30:05", "throughput": 1486.24, "total_tokens": 30332224} {"current_steps": 143735, "total_steps": 181800, "loss": 0.0026, "lr": 6.3854488724708564e-06, "epoch": 15.812431243124312, "percentage": 79.06, "elapsed_time": "5:40:09", "remaining_time": "1:30:04", "throughput": 1486.25, "total_tokens": 30333280} {"current_steps": 143740, "total_steps": 181800, "loss": 0.0049, "lr": 6.38384683874729e-06, "epoch": 15.812981298129813, "percentage": 79.06, "elapsed_time": "5:40:10", "remaining_time": "1:30:04", "throughput": 1486.25, "total_tokens": 30334336} {"current_steps": 143745, "total_steps": 181800, "loss": 0.0027, "lr": 6.382244976599877e-06, "epoch": 15.813531353135314, "percentage": 79.07, "elapsed_time": "5:40:10", "remaining_time": "1:30:03", "throughput": 1486.25, "total_tokens": 30335392} {"current_steps": 143750, "total_steps": 181800, "loss": 0.0485, "lr": 6.380643286043372e-06, "epoch": 15.814081408140813, "percentage": 79.07, "elapsed_time": "5:40:11", "remaining_time": "1:30:02", "throughput": 1486.25, "total_tokens": 30336448} {"current_steps": 143755, "total_steps": 181800, "loss": 0.0249, "lr": 6.37904176709255e-06, "epoch": 15.814631463146315, "percentage": 79.07, "elapsed_time": "5:40:12", "remaining_time": "1:30:02", "throughput": 1486.25, "total_tokens": 30337472} {"current_steps": 143760, "total_steps": 181800, "loss": 0.0031, "lr": 6.377440419762157e-06, "epoch": 15.815181518151816, "percentage": 79.08, "elapsed_time": "5:40:12", "remaining_time": "1:30:01", "throughput": 1486.25, "total_tokens": 30338560} {"current_steps": 143765, "total_steps": 181800, "loss": 0.0053, "lr": 6.3758392440669584e-06, "epoch": 15.815731573157315, "percentage": 79.08, "elapsed_time": "5:40:13", "remaining_time": "1:30:00", "throughput": 1486.25, "total_tokens": 30339584} {"current_steps": 143770, "total_steps": 181800, "loss": 0.0015, "lr": 6.374238240021721e-06, "epoch": 15.816281628162816, "percentage": 79.08, "elapsed_time": "5:40:14", "remaining_time": "1:29:59", "throughput": 1486.25, "total_tokens": 30340640} {"current_steps": 143775, "total_steps": 181800, "loss": 0.0546, "lr": 6.372637407641186e-06, "epoch": 15.816831683168317, "percentage": 79.08, "elapsed_time": "5:40:14", "remaining_time": "1:29:59", "throughput": 1486.26, "total_tokens": 30341696} {"current_steps": 143780, "total_steps": 181800, "loss": 0.0063, "lr": 6.371036746940121e-06, "epoch": 15.817381738173818, "percentage": 79.09, "elapsed_time": "5:40:15", "remaining_time": "1:29:58", "throughput": 1486.26, "total_tokens": 30342752} {"current_steps": 143785, "total_steps": 181800, "loss": 0.0062, "lr": 6.369436257933264e-06, "epoch": 15.817931793179318, "percentage": 79.09, "elapsed_time": "5:40:16", "remaining_time": "1:29:57", "throughput": 1486.26, "total_tokens": 30343744} {"current_steps": 143790, "total_steps": 181800, "loss": 0.0056, "lr": 6.367835940635372e-06, "epoch": 15.818481848184819, "percentage": 79.09, "elapsed_time": "5:40:16", "remaining_time": "1:29:57", "throughput": 1486.26, "total_tokens": 30344768} {"current_steps": 143795, "total_steps": 181800, "loss": 0.0008, "lr": 6.366235795061204e-06, "epoch": 15.81903190319032, "percentage": 79.1, "elapsed_time": "5:40:17", "remaining_time": "1:29:56", "throughput": 1486.26, "total_tokens": 30345856} {"current_steps": 143800, "total_steps": 181800, "loss": 0.0128, "lr": 6.36463582122549e-06, "epoch": 15.819581958195819, "percentage": 79.1, "elapsed_time": "5:40:18", "remaining_time": "1:29:55", "throughput": 1486.26, "total_tokens": 30346848} {"current_steps": 143805, "total_steps": 181800, "loss": 0.0016, "lr": 6.3630360191429955e-06, "epoch": 15.82013201320132, "percentage": 79.1, "elapsed_time": "5:40:19", "remaining_time": "1:29:54", "throughput": 1486.26, "total_tokens": 30347872} {"current_steps": 143810, "total_steps": 181800, "loss": 0.0175, "lr": 6.361436388828454e-06, "epoch": 15.820682068206821, "percentage": 79.1, "elapsed_time": "5:40:19", "remaining_time": "1:29:54", "throughput": 1486.26, "total_tokens": 30348992} {"current_steps": 143815, "total_steps": 181800, "loss": 0.0037, "lr": 6.3598369302966e-06, "epoch": 15.82123212321232, "percentage": 79.11, "elapsed_time": "5:40:20", "remaining_time": "1:29:53", "throughput": 1486.26, "total_tokens": 30350048} {"current_steps": 143820, "total_steps": 181800, "loss": 0.0105, "lr": 6.35823764356219e-06, "epoch": 15.821782178217822, "percentage": 79.11, "elapsed_time": "5:40:21", "remaining_time": "1:29:52", "throughput": 1486.26, "total_tokens": 30351072} {"current_steps": 143825, "total_steps": 181800, "loss": 0.0505, "lr": 6.356638528639955e-06, "epoch": 15.822332233223323, "percentage": 79.11, "elapsed_time": "5:40:21", "remaining_time": "1:29:52", "throughput": 1486.26, "total_tokens": 30352096} {"current_steps": 143830, "total_steps": 181800, "loss": 0.0067, "lr": 6.355039585544642e-06, "epoch": 15.822882288228822, "percentage": 79.11, "elapsed_time": "5:40:22", "remaining_time": "1:29:51", "throughput": 1486.26, "total_tokens": 30353152} {"current_steps": 143835, "total_steps": 181800, "loss": 0.0065, "lr": 6.353440814290987e-06, "epoch": 15.823432343234323, "percentage": 79.12, "elapsed_time": "5:40:23", "remaining_time": "1:29:50", "throughput": 1486.27, "total_tokens": 30354240} {"current_steps": 143840, "total_steps": 181800, "loss": 0.1359, "lr": 6.35184221489371e-06, "epoch": 15.823982398239824, "percentage": 79.12, "elapsed_time": "5:40:23", "remaining_time": "1:29:49", "throughput": 1486.27, "total_tokens": 30355360} {"current_steps": 143845, "total_steps": 181800, "loss": 0.0064, "lr": 6.350243787367563e-06, "epoch": 15.824532453245325, "percentage": 79.12, "elapsed_time": "5:40:24", "remaining_time": "1:29:49", "throughput": 1486.27, "total_tokens": 30356416} {"current_steps": 143850, "total_steps": 181800, "loss": 0.0008, "lr": 6.348645531727257e-06, "epoch": 15.825082508250825, "percentage": 79.13, "elapsed_time": "5:40:25", "remaining_time": "1:29:48", "throughput": 1486.28, "total_tokens": 30357472} {"current_steps": 143855, "total_steps": 181800, "loss": 0.0025, "lr": 6.3470474479875475e-06, "epoch": 15.825632563256326, "percentage": 79.13, "elapsed_time": "5:40:25", "remaining_time": "1:29:47", "throughput": 1486.28, "total_tokens": 30358496} {"current_steps": 143860, "total_steps": 181800, "loss": 0.0074, "lr": 6.345449536163153e-06, "epoch": 15.826182618261827, "percentage": 79.13, "elapsed_time": "5:40:26", "remaining_time": "1:29:47", "throughput": 1486.28, "total_tokens": 30359552} {"current_steps": 143865, "total_steps": 181800, "loss": 0.0166, "lr": 6.34385179626879e-06, "epoch": 15.826732673267326, "percentage": 79.13, "elapsed_time": "5:40:27", "remaining_time": "1:29:46", "throughput": 1486.28, "total_tokens": 30360640} {"current_steps": 143870, "total_steps": 181800, "loss": 0.0013, "lr": 6.3422542283192e-06, "epoch": 15.827282728272827, "percentage": 79.14, "elapsed_time": "5:40:27", "remaining_time": "1:29:45", "throughput": 1486.28, "total_tokens": 30361728} {"current_steps": 143875, "total_steps": 181800, "loss": 0.0026, "lr": 6.3406568323290946e-06, "epoch": 15.827832783278328, "percentage": 79.14, "elapsed_time": "5:40:28", "remaining_time": "1:29:44", "throughput": 1486.29, "total_tokens": 30362816} {"current_steps": 143880, "total_steps": 181800, "loss": 0.0025, "lr": 6.3390596083132e-06, "epoch": 15.828382838283828, "percentage": 79.14, "elapsed_time": "5:40:29", "remaining_time": "1:29:44", "throughput": 1486.29, "total_tokens": 30363904} {"current_steps": 143885, "total_steps": 181800, "loss": 0.0058, "lr": 6.337462556286247e-06, "epoch": 15.828932893289329, "percentage": 79.14, "elapsed_time": "5:40:30", "remaining_time": "1:29:43", "throughput": 1486.29, "total_tokens": 30364960} {"current_steps": 143890, "total_steps": 181800, "loss": 0.0835, "lr": 6.3358656762629395e-06, "epoch": 15.82948294829483, "percentage": 79.15, "elapsed_time": "5:40:30", "remaining_time": "1:29:42", "throughput": 1486.29, "total_tokens": 30366016} {"current_steps": 143895, "total_steps": 181800, "loss": 0.0078, "lr": 6.3342689682580085e-06, "epoch": 15.83003300330033, "percentage": 79.15, "elapsed_time": "5:40:31", "remaining_time": "1:29:42", "throughput": 1486.29, "total_tokens": 30367040} {"current_steps": 143900, "total_steps": 181800, "loss": 0.0557, "lr": 6.332672432286154e-06, "epoch": 15.83058305830583, "percentage": 79.15, "elapsed_time": "5:40:32", "remaining_time": "1:29:41", "throughput": 1486.29, "total_tokens": 30368064} {"current_steps": 143905, "total_steps": 181800, "loss": 0.1174, "lr": 6.331076068362104e-06, "epoch": 15.831133113311331, "percentage": 79.16, "elapsed_time": "5:40:32", "remaining_time": "1:29:40", "throughput": 1486.29, "total_tokens": 30369088} {"current_steps": 143910, "total_steps": 181800, "loss": 0.0035, "lr": 6.329479876500574e-06, "epoch": 15.831683168316832, "percentage": 79.16, "elapsed_time": "5:40:33", "remaining_time": "1:29:39", "throughput": 1486.29, "total_tokens": 30370176} {"current_steps": 143915, "total_steps": 181800, "loss": 0.0106, "lr": 6.32788385671626e-06, "epoch": 15.832233223322332, "percentage": 79.16, "elapsed_time": "5:40:34", "remaining_time": "1:29:39", "throughput": 1486.29, "total_tokens": 30371232} {"current_steps": 143920, "total_steps": 181800, "loss": 0.0014, "lr": 6.32628800902389e-06, "epoch": 15.832783278327833, "percentage": 79.16, "elapsed_time": "5:40:34", "remaining_time": "1:29:38", "throughput": 1486.3, "total_tokens": 30372288} {"current_steps": 143925, "total_steps": 181800, "loss": 0.0074, "lr": 6.324692333438156e-06, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "5:40:35", "remaining_time": "1:29:37", "throughput": 1486.3, "total_tokens": 30373312} {"current_steps": 143930, "total_steps": 181800, "loss": 0.0443, "lr": 6.323096829973776e-06, "epoch": 15.833883388338833, "percentage": 79.17, "elapsed_time": "5:40:36", "remaining_time": "1:29:37", "throughput": 1486.29, "total_tokens": 30374272} {"current_steps": 143935, "total_steps": 181800, "loss": 0.0023, "lr": 6.321501498645446e-06, "epoch": 15.834433443344334, "percentage": 79.17, "elapsed_time": "5:40:36", "remaining_time": "1:29:36", "throughput": 1486.3, "total_tokens": 30375392} {"current_steps": 143940, "total_steps": 181800, "loss": 0.0037, "lr": 6.3199063394678735e-06, "epoch": 15.834983498349835, "percentage": 79.17, "elapsed_time": "5:40:37", "remaining_time": "1:29:35", "throughput": 1486.3, "total_tokens": 30376448} {"current_steps": 143945, "total_steps": 181800, "loss": 0.0086, "lr": 6.318311352455766e-06, "epoch": 15.835533553355335, "percentage": 79.18, "elapsed_time": "5:40:38", "remaining_time": "1:29:34", "throughput": 1486.3, "total_tokens": 30377504} {"current_steps": 143950, "total_steps": 181800, "loss": 0.031, "lr": 6.316716537623813e-06, "epoch": 15.836083608360836, "percentage": 79.18, "elapsed_time": "5:40:39", "remaining_time": "1:29:34", "throughput": 1486.3, "total_tokens": 30378528} {"current_steps": 143955, "total_steps": 181800, "loss": 0.0016, "lr": 6.3151218949867255e-06, "epoch": 15.836633663366337, "percentage": 79.18, "elapsed_time": "5:40:39", "remaining_time": "1:29:33", "throughput": 1486.3, "total_tokens": 30379616} {"current_steps": 143960, "total_steps": 181800, "loss": 0.0501, "lr": 6.313527424559193e-06, "epoch": 15.837183718371836, "percentage": 79.19, "elapsed_time": "5:40:40", "remaining_time": "1:29:32", "throughput": 1486.3, "total_tokens": 30380640} {"current_steps": 143965, "total_steps": 181800, "loss": 0.002, "lr": 6.3119331263558984e-06, "epoch": 15.837733773377337, "percentage": 79.19, "elapsed_time": "5:40:41", "remaining_time": "1:29:32", "throughput": 1486.3, "total_tokens": 30381664} {"current_steps": 143970, "total_steps": 181800, "loss": 0.0035, "lr": 6.310339000391563e-06, "epoch": 15.838283828382838, "percentage": 79.19, "elapsed_time": "5:40:41", "remaining_time": "1:29:31", "throughput": 1486.31, "total_tokens": 30382848} {"current_steps": 143975, "total_steps": 181800, "loss": 0.0005, "lr": 6.308745046680856e-06, "epoch": 15.83883388338834, "percentage": 79.19, "elapsed_time": "5:40:42", "remaining_time": "1:29:30", "throughput": 1486.31, "total_tokens": 30383936} {"current_steps": 143980, "total_steps": 181800, "loss": 0.0016, "lr": 6.307151265238484e-06, "epoch": 15.839383938393839, "percentage": 79.2, "elapsed_time": "5:40:43", "remaining_time": "1:29:29", "throughput": 1486.31, "total_tokens": 30384992} {"current_steps": 143985, "total_steps": 181800, "loss": 0.0017, "lr": 6.305557656079131e-06, "epoch": 15.83993399339934, "percentage": 79.2, "elapsed_time": "5:40:43", "remaining_time": "1:29:29", "throughput": 1486.32, "total_tokens": 30386112} {"current_steps": 143990, "total_steps": 181800, "loss": 0.0006, "lr": 6.303964219217476e-06, "epoch": 15.840484048404841, "percentage": 79.2, "elapsed_time": "5:40:44", "remaining_time": "1:29:28", "throughput": 1486.32, "total_tokens": 30387200} {"current_steps": 143995, "total_steps": 181800, "loss": 0.0024, "lr": 6.30237095466821e-06, "epoch": 15.84103410341034, "percentage": 79.21, "elapsed_time": "5:40:45", "remaining_time": "1:29:27", "throughput": 1486.32, "total_tokens": 30388256} {"current_steps": 144000, "total_steps": 181800, "loss": 0.023, "lr": 6.30077786244602e-06, "epoch": 15.841584158415841, "percentage": 79.21, "elapsed_time": "5:40:45", "remaining_time": "1:29:27", "throughput": 1486.32, "total_tokens": 30389280} {"current_steps": 144005, "total_steps": 181800, "loss": 0.012, "lr": 6.299184942565592e-06, "epoch": 15.842134213421343, "percentage": 79.21, "elapsed_time": "5:40:46", "remaining_time": "1:29:26", "throughput": 1486.32, "total_tokens": 30390272} {"current_steps": 144010, "total_steps": 181800, "loss": 0.0039, "lr": 6.297592195041605e-06, "epoch": 15.842684268426842, "percentage": 79.21, "elapsed_time": "5:40:47", "remaining_time": "1:29:25", "throughput": 1486.32, "total_tokens": 30391328} {"current_steps": 144015, "total_steps": 181800, "loss": 0.1061, "lr": 6.295999619888729e-06, "epoch": 15.843234323432343, "percentage": 79.22, "elapsed_time": "5:40:48", "remaining_time": "1:29:24", "throughput": 1486.32, "total_tokens": 30392384} {"current_steps": 144020, "total_steps": 181800, "loss": 0.0077, "lr": 6.2944072171216564e-06, "epoch": 15.843784378437844, "percentage": 79.22, "elapsed_time": "5:40:48", "remaining_time": "1:29:24", "throughput": 1486.32, "total_tokens": 30393408} {"current_steps": 144025, "total_steps": 181800, "loss": 0.0237, "lr": 6.2928149867550495e-06, "epoch": 15.844334433443345, "percentage": 79.22, "elapsed_time": "5:40:49", "remaining_time": "1:29:23", "throughput": 1486.33, "total_tokens": 30394464} {"current_steps": 144030, "total_steps": 181800, "loss": 0.164, "lr": 6.291222928803592e-06, "epoch": 15.844884488448844, "percentage": 79.22, "elapsed_time": "5:40:50", "remaining_time": "1:29:22", "throughput": 1486.33, "total_tokens": 30395520} {"current_steps": 144035, "total_steps": 181800, "loss": 0.0176, "lr": 6.28963104328196e-06, "epoch": 15.845434543454346, "percentage": 79.23, "elapsed_time": "5:40:50", "remaining_time": "1:29:22", "throughput": 1486.33, "total_tokens": 30396512} {"current_steps": 144040, "total_steps": 181800, "loss": 0.0051, "lr": 6.288039330204815e-06, "epoch": 15.845984598459847, "percentage": 79.23, "elapsed_time": "5:40:51", "remaining_time": "1:29:21", "throughput": 1486.33, "total_tokens": 30397536} {"current_steps": 144045, "total_steps": 181800, "loss": 0.0159, "lr": 6.2864477895868415e-06, "epoch": 15.846534653465346, "percentage": 79.23, "elapsed_time": "5:40:52", "remaining_time": "1:29:20", "throughput": 1486.32, "total_tokens": 30398528} {"current_steps": 144050, "total_steps": 181800, "loss": 0.0014, "lr": 6.284856421442689e-06, "epoch": 15.847084708470847, "percentage": 79.24, "elapsed_time": "5:40:52", "remaining_time": "1:29:19", "throughput": 1486.32, "total_tokens": 30399552} {"current_steps": 144055, "total_steps": 181800, "loss": 0.028, "lr": 6.283265225787036e-06, "epoch": 15.847634763476348, "percentage": 79.24, "elapsed_time": "5:40:53", "remaining_time": "1:29:19", "throughput": 1486.33, "total_tokens": 30400608} {"current_steps": 144060, "total_steps": 181800, "loss": 0.0109, "lr": 6.281674202634552e-06, "epoch": 15.848184818481847, "percentage": 79.24, "elapsed_time": "5:40:54", "remaining_time": "1:29:18", "throughput": 1486.33, "total_tokens": 30401664} {"current_steps": 144065, "total_steps": 181800, "loss": 0.0645, "lr": 6.280083351999888e-06, "epoch": 15.848734873487349, "percentage": 79.24, "elapsed_time": "5:40:54", "remaining_time": "1:29:17", "throughput": 1486.33, "total_tokens": 30402752} {"current_steps": 144070, "total_steps": 181800, "loss": 0.0393, "lr": 6.27849267389772e-06, "epoch": 15.84928492849285, "percentage": 79.25, "elapsed_time": "5:40:55", "remaining_time": "1:29:17", "throughput": 1486.33, "total_tokens": 30403808} {"current_steps": 144075, "total_steps": 181800, "loss": 0.0042, "lr": 6.276902168342702e-06, "epoch": 15.84983498349835, "percentage": 79.25, "elapsed_time": "5:40:56", "remaining_time": "1:29:16", "throughput": 1486.33, "total_tokens": 30404832} {"current_steps": 144080, "total_steps": 181800, "loss": 0.0266, "lr": 6.275311835349487e-06, "epoch": 15.85038503850385, "percentage": 79.25, "elapsed_time": "5:40:56", "remaining_time": "1:29:15", "throughput": 1486.33, "total_tokens": 30405824} {"current_steps": 144085, "total_steps": 181800, "loss": 0.083, "lr": 6.273721674932737e-06, "epoch": 15.850935093509351, "percentage": 79.25, "elapsed_time": "5:40:57", "remaining_time": "1:29:14", "throughput": 1486.33, "total_tokens": 30406816} {"current_steps": 144090, "total_steps": 181800, "loss": 0.0516, "lr": 6.272131687107108e-06, "epoch": 15.851485148514852, "percentage": 79.26, "elapsed_time": "5:40:58", "remaining_time": "1:29:14", "throughput": 1486.33, "total_tokens": 30407936} {"current_steps": 144095, "total_steps": 181800, "loss": 0.0468, "lr": 6.270541871887261e-06, "epoch": 15.852035203520352, "percentage": 79.26, "elapsed_time": "5:40:59", "remaining_time": "1:29:13", "throughput": 1486.33, "total_tokens": 30408960} {"current_steps": 144100, "total_steps": 181800, "loss": 0.002, "lr": 6.268952229287842e-06, "epoch": 15.852585258525853, "percentage": 79.26, "elapsed_time": "5:40:59", "remaining_time": "1:29:12", "throughput": 1486.33, "total_tokens": 30409952} {"current_steps": 144105, "total_steps": 181800, "loss": 0.0047, "lr": 6.267362759323498e-06, "epoch": 15.853135313531354, "percentage": 79.27, "elapsed_time": "5:41:00", "remaining_time": "1:29:12", "throughput": 1486.33, "total_tokens": 30410944} {"current_steps": 144110, "total_steps": 181800, "loss": 0.0104, "lr": 6.265773462008881e-06, "epoch": 15.853685368536853, "percentage": 79.27, "elapsed_time": "5:41:01", "remaining_time": "1:29:11", "throughput": 1486.33, "total_tokens": 30412064} {"current_steps": 144115, "total_steps": 181800, "loss": 0.0044, "lr": 6.264184337358639e-06, "epoch": 15.854235423542354, "percentage": 79.27, "elapsed_time": "5:41:01", "remaining_time": "1:29:10", "throughput": 1486.34, "total_tokens": 30413120} {"current_steps": 144120, "total_steps": 181800, "loss": 0.0052, "lr": 6.262595385387429e-06, "epoch": 15.854785478547855, "percentage": 79.27, "elapsed_time": "5:41:02", "remaining_time": "1:29:09", "throughput": 1486.34, "total_tokens": 30414240} {"current_steps": 144125, "total_steps": 181800, "loss": 0.0373, "lr": 6.261006606109884e-06, "epoch": 15.855335533553355, "percentage": 79.28, "elapsed_time": "5:41:03", "remaining_time": "1:29:09", "throughput": 1486.34, "total_tokens": 30415264} {"current_steps": 144130, "total_steps": 181800, "loss": 0.0027, "lr": 6.259417999540645e-06, "epoch": 15.855885588558856, "percentage": 79.28, "elapsed_time": "5:41:03", "remaining_time": "1:29:08", "throughput": 1486.34, "total_tokens": 30416256} {"current_steps": 144135, "total_steps": 181800, "loss": 0.0095, "lr": 6.257829565694365e-06, "epoch": 15.856435643564357, "percentage": 79.28, "elapsed_time": "5:41:04", "remaining_time": "1:29:07", "throughput": 1486.34, "total_tokens": 30417248} {"current_steps": 144140, "total_steps": 181800, "loss": 0.129, "lr": 6.256241304585667e-06, "epoch": 15.856985698569858, "percentage": 79.28, "elapsed_time": "5:41:05", "remaining_time": "1:29:07", "throughput": 1486.34, "total_tokens": 30418304} {"current_steps": 144145, "total_steps": 181800, "loss": 0.0031, "lr": 6.254653216229198e-06, "epoch": 15.857535753575357, "percentage": 79.29, "elapsed_time": "5:41:05", "remaining_time": "1:29:06", "throughput": 1486.34, "total_tokens": 30419328} {"current_steps": 144150, "total_steps": 181800, "loss": 0.0095, "lr": 6.253065300639604e-06, "epoch": 15.858085808580858, "percentage": 79.29, "elapsed_time": "5:41:06", "remaining_time": "1:29:05", "throughput": 1486.34, "total_tokens": 30420416} {"current_steps": 144155, "total_steps": 181800, "loss": 0.0266, "lr": 6.251477557831506e-06, "epoch": 15.85863586358636, "percentage": 79.29, "elapsed_time": "5:41:07", "remaining_time": "1:29:04", "throughput": 1486.35, "total_tokens": 30421504} {"current_steps": 144160, "total_steps": 181800, "loss": 0.0238, "lr": 6.249889987819549e-06, "epoch": 15.859185918591859, "percentage": 79.3, "elapsed_time": "5:41:08", "remaining_time": "1:29:04", "throughput": 1486.35, "total_tokens": 30422528} {"current_steps": 144165, "total_steps": 181800, "loss": 0.0043, "lr": 6.248302590618349e-06, "epoch": 15.85973597359736, "percentage": 79.3, "elapsed_time": "5:41:08", "remaining_time": "1:29:03", "throughput": 1486.35, "total_tokens": 30423552} {"current_steps": 144170, "total_steps": 181800, "loss": 0.003, "lr": 6.24671536624255e-06, "epoch": 15.86028602860286, "percentage": 79.3, "elapsed_time": "5:41:09", "remaining_time": "1:29:02", "throughput": 1486.35, "total_tokens": 30424576} {"current_steps": 144175, "total_steps": 181800, "loss": 0.0172, "lr": 6.245128314706783e-06, "epoch": 15.86083608360836, "percentage": 79.3, "elapsed_time": "5:41:10", "remaining_time": "1:29:02", "throughput": 1486.35, "total_tokens": 30425664} {"current_steps": 144180, "total_steps": 181800, "loss": 0.003, "lr": 6.2435414360256596e-06, "epoch": 15.861386138613861, "percentage": 79.31, "elapsed_time": "5:41:10", "remaining_time": "1:29:01", "throughput": 1486.35, "total_tokens": 30426752} {"current_steps": 144185, "total_steps": 181800, "loss": 0.0111, "lr": 6.241954730213823e-06, "epoch": 15.861936193619362, "percentage": 79.31, "elapsed_time": "5:41:11", "remaining_time": "1:29:00", "throughput": 1486.35, "total_tokens": 30427808} {"current_steps": 144190, "total_steps": 181800, "loss": 0.0019, "lr": 6.240368197285881e-06, "epoch": 15.862486248624862, "percentage": 79.31, "elapsed_time": "5:41:12", "remaining_time": "1:28:59", "throughput": 1486.35, "total_tokens": 30428864} {"current_steps": 144195, "total_steps": 181800, "loss": 0.0377, "lr": 6.238781837256472e-06, "epoch": 15.863036303630363, "percentage": 79.32, "elapsed_time": "5:41:12", "remaining_time": "1:28:59", "throughput": 1486.35, "total_tokens": 30429888} {"current_steps": 144200, "total_steps": 181800, "loss": 0.0079, "lr": 6.237195650140201e-06, "epoch": 15.863586358635864, "percentage": 79.32, "elapsed_time": "5:41:13", "remaining_time": "1:28:58", "throughput": 1486.36, "total_tokens": 30431008} {"current_steps": 144205, "total_steps": 181800, "loss": 0.0013, "lr": 6.235609635951692e-06, "epoch": 15.864136413641365, "percentage": 79.32, "elapsed_time": "5:41:14", "remaining_time": "1:28:57", "throughput": 1486.36, "total_tokens": 30432128} {"current_steps": 144210, "total_steps": 181800, "loss": 0.0401, "lr": 6.234023794705574e-06, "epoch": 15.864686468646864, "percentage": 79.32, "elapsed_time": "5:41:14", "remaining_time": "1:28:57", "throughput": 1486.36, "total_tokens": 30433184} {"current_steps": 144215, "total_steps": 181800, "loss": 0.0019, "lr": 6.232438126416454e-06, "epoch": 15.865236523652365, "percentage": 79.33, "elapsed_time": "5:41:15", "remaining_time": "1:28:56", "throughput": 1486.37, "total_tokens": 30434272} {"current_steps": 144220, "total_steps": 181800, "loss": 0.0014, "lr": 6.230852631098941e-06, "epoch": 15.865786578657866, "percentage": 79.33, "elapsed_time": "5:41:16", "remaining_time": "1:28:55", "throughput": 1486.37, "total_tokens": 30435392} {"current_steps": 144225, "total_steps": 181800, "loss": 0.0754, "lr": 6.22926730876765e-06, "epoch": 15.866336633663366, "percentage": 79.33, "elapsed_time": "5:41:16", "remaining_time": "1:28:54", "throughput": 1486.37, "total_tokens": 30436448} {"current_steps": 144230, "total_steps": 181800, "loss": 0.0058, "lr": 6.227682159437195e-06, "epoch": 15.866886688668867, "percentage": 79.33, "elapsed_time": "5:41:17", "remaining_time": "1:28:54", "throughput": 1486.37, "total_tokens": 30437472} {"current_steps": 144235, "total_steps": 181800, "loss": 0.0029, "lr": 6.2260971831221956e-06, "epoch": 15.867436743674368, "percentage": 79.34, "elapsed_time": "5:41:18", "remaining_time": "1:28:53", "throughput": 1486.38, "total_tokens": 30438560} {"current_steps": 144240, "total_steps": 181800, "loss": 0.0057, "lr": 6.224512379837247e-06, "epoch": 15.867986798679867, "percentage": 79.34, "elapsed_time": "5:41:19", "remaining_time": "1:28:52", "throughput": 1486.38, "total_tokens": 30439584} {"current_steps": 144245, "total_steps": 181800, "loss": 0.0098, "lr": 6.2229277495969515e-06, "epoch": 15.868536853685368, "percentage": 79.34, "elapsed_time": "5:41:19", "remaining_time": "1:28:52", "throughput": 1486.38, "total_tokens": 30440672} {"current_steps": 144250, "total_steps": 181800, "loss": 0.0012, "lr": 6.2213432924159296e-06, "epoch": 15.86908690869087, "percentage": 79.35, "elapsed_time": "5:41:20", "remaining_time": "1:28:51", "throughput": 1486.38, "total_tokens": 30441664} {"current_steps": 144255, "total_steps": 181800, "loss": 0.0049, "lr": 6.219759008308768e-06, "epoch": 15.869636963696369, "percentage": 79.35, "elapsed_time": "5:41:21", "remaining_time": "1:28:50", "throughput": 1486.38, "total_tokens": 30442720} {"current_steps": 144260, "total_steps": 181800, "loss": 0.0251, "lr": 6.218174897290077e-06, "epoch": 15.87018701870187, "percentage": 79.35, "elapsed_time": "5:41:21", "remaining_time": "1:28:49", "throughput": 1486.38, "total_tokens": 30443744} {"current_steps": 144265, "total_steps": 181800, "loss": 0.04, "lr": 6.21659095937446e-06, "epoch": 15.870737073707371, "percentage": 79.35, "elapsed_time": "5:41:22", "remaining_time": "1:28:49", "throughput": 1486.39, "total_tokens": 30444864} {"current_steps": 144270, "total_steps": 181800, "loss": 0.1292, "lr": 6.215007194576505e-06, "epoch": 15.871287128712872, "percentage": 79.36, "elapsed_time": "5:41:23", "remaining_time": "1:28:48", "throughput": 1486.39, "total_tokens": 30445952} {"current_steps": 144275, "total_steps": 181800, "loss": 0.0969, "lr": 6.2134236029108225e-06, "epoch": 15.871837183718371, "percentage": 79.36, "elapsed_time": "5:41:23", "remaining_time": "1:28:47", "throughput": 1486.39, "total_tokens": 30447072} {"current_steps": 144280, "total_steps": 181800, "loss": 0.1106, "lr": 6.211840184391993e-06, "epoch": 15.872387238723872, "percentage": 79.36, "elapsed_time": "5:41:24", "remaining_time": "1:28:47", "throughput": 1486.39, "total_tokens": 30448096} {"current_steps": 144285, "total_steps": 181800, "loss": 0.0037, "lr": 6.210256939034617e-06, "epoch": 15.872937293729374, "percentage": 79.36, "elapsed_time": "5:41:25", "remaining_time": "1:28:46", "throughput": 1486.39, "total_tokens": 30449120} {"current_steps": 144290, "total_steps": 181800, "loss": 0.0067, "lr": 6.208673866853293e-06, "epoch": 15.873487348734873, "percentage": 79.37, "elapsed_time": "5:41:25", "remaining_time": "1:28:45", "throughput": 1486.4, "total_tokens": 30450208} {"current_steps": 144295, "total_steps": 181800, "loss": 0.0069, "lr": 6.2070909678626e-06, "epoch": 15.874037403740374, "percentage": 79.37, "elapsed_time": "5:41:26", "remaining_time": "1:28:44", "throughput": 1486.4, "total_tokens": 30451296} {"current_steps": 144300, "total_steps": 181800, "loss": 0.0019, "lr": 6.205508242077138e-06, "epoch": 15.874587458745875, "percentage": 79.37, "elapsed_time": "5:41:27", "remaining_time": "1:28:44", "throughput": 1486.4, "total_tokens": 30452352} {"current_steps": 144305, "total_steps": 181800, "loss": 0.0009, "lr": 6.203925689511478e-06, "epoch": 15.875137513751374, "percentage": 79.38, "elapsed_time": "5:41:27", "remaining_time": "1:28:43", "throughput": 1486.4, "total_tokens": 30453408} {"current_steps": 144310, "total_steps": 181800, "loss": 0.0209, "lr": 6.202343310180225e-06, "epoch": 15.875687568756875, "percentage": 79.38, "elapsed_time": "5:41:28", "remaining_time": "1:28:42", "throughput": 1486.4, "total_tokens": 30454368} {"current_steps": 144315, "total_steps": 181800, "loss": 0.066, "lr": 6.200761104097946e-06, "epoch": 15.876237623762377, "percentage": 79.38, "elapsed_time": "5:41:29", "remaining_time": "1:28:41", "throughput": 1486.4, "total_tokens": 30455456} {"current_steps": 144320, "total_steps": 181800, "loss": 0.0914, "lr": 6.199179071279232e-06, "epoch": 15.876787678767876, "percentage": 79.38, "elapsed_time": "5:41:30", "remaining_time": "1:28:41", "throughput": 1486.4, "total_tokens": 30456480} {"current_steps": 144325, "total_steps": 181800, "loss": 0.0042, "lr": 6.19759721173867e-06, "epoch": 15.877337733773377, "percentage": 79.39, "elapsed_time": "5:41:30", "remaining_time": "1:28:40", "throughput": 1486.4, "total_tokens": 30457536} {"current_steps": 144330, "total_steps": 181800, "loss": 0.0951, "lr": 6.196015525490825e-06, "epoch": 15.877887788778878, "percentage": 79.39, "elapsed_time": "5:41:31", "remaining_time": "1:28:39", "throughput": 1486.41, "total_tokens": 30458624} {"current_steps": 144335, "total_steps": 181800, "loss": 0.0324, "lr": 6.194434012550291e-06, "epoch": 15.87843784378438, "percentage": 79.39, "elapsed_time": "5:41:32", "remaining_time": "1:28:39", "throughput": 1486.41, "total_tokens": 30459680} {"current_steps": 144340, "total_steps": 181800, "loss": 0.002, "lr": 6.192852672931626e-06, "epoch": 15.878987898789878, "percentage": 79.39, "elapsed_time": "5:41:32", "remaining_time": "1:28:38", "throughput": 1486.41, "total_tokens": 30460704} {"current_steps": 144345, "total_steps": 181800, "loss": 0.0688, "lr": 6.191271506649413e-06, "epoch": 15.87953795379538, "percentage": 79.4, "elapsed_time": "5:41:33", "remaining_time": "1:28:37", "throughput": 1486.41, "total_tokens": 30461728} {"current_steps": 144350, "total_steps": 181800, "loss": 0.0049, "lr": 6.189690513718232e-06, "epoch": 15.88008800880088, "percentage": 79.4, "elapsed_time": "5:41:34", "remaining_time": "1:28:36", "throughput": 1486.41, "total_tokens": 30462816} {"current_steps": 144355, "total_steps": 181800, "loss": 0.0565, "lr": 6.188109694152641e-06, "epoch": 15.88063806380638, "percentage": 79.4, "elapsed_time": "5:41:34", "remaining_time": "1:28:36", "throughput": 1486.42, "total_tokens": 30463936} {"current_steps": 144360, "total_steps": 181800, "loss": 0.0607, "lr": 6.1865290479672235e-06, "epoch": 15.881188118811881, "percentage": 79.41, "elapsed_time": "5:41:35", "remaining_time": "1:28:35", "throughput": 1486.42, "total_tokens": 30465024} {"current_steps": 144365, "total_steps": 181800, "loss": 0.0349, "lr": 6.184948575176538e-06, "epoch": 15.881738173817382, "percentage": 79.41, "elapsed_time": "5:41:36", "remaining_time": "1:28:34", "throughput": 1486.42, "total_tokens": 30466176} {"current_steps": 144370, "total_steps": 181800, "loss": 0.0076, "lr": 6.183368275795148e-06, "epoch": 15.882288228822881, "percentage": 79.41, "elapsed_time": "5:41:36", "remaining_time": "1:28:34", "throughput": 1486.43, "total_tokens": 30467296} {"current_steps": 144375, "total_steps": 181800, "loss": 0.0052, "lr": 6.181788149837625e-06, "epoch": 15.882838283828383, "percentage": 79.41, "elapsed_time": "5:41:37", "remaining_time": "1:28:33", "throughput": 1486.43, "total_tokens": 30468320} {"current_steps": 144380, "total_steps": 181800, "loss": 0.03, "lr": 6.18020819731853e-06, "epoch": 15.883388338833884, "percentage": 79.42, "elapsed_time": "5:41:38", "remaining_time": "1:28:32", "throughput": 1486.43, "total_tokens": 30469408} {"current_steps": 144385, "total_steps": 181800, "loss": 0.0104, "lr": 6.17862841825243e-06, "epoch": 15.883938393839383, "percentage": 79.42, "elapsed_time": "5:41:39", "remaining_time": "1:28:31", "throughput": 1486.43, "total_tokens": 30470464} {"current_steps": 144390, "total_steps": 181800, "loss": 0.0474, "lr": 6.177048812653882e-06, "epoch": 15.884488448844884, "percentage": 79.42, "elapsed_time": "5:41:39", "remaining_time": "1:28:31", "throughput": 1486.43, "total_tokens": 30471488} {"current_steps": 144395, "total_steps": 181800, "loss": 0.0556, "lr": 6.1754693805374355e-06, "epoch": 15.885038503850385, "percentage": 79.43, "elapsed_time": "5:41:40", "remaining_time": "1:28:30", "throughput": 1486.43, "total_tokens": 30472512} {"current_steps": 144400, "total_steps": 181800, "loss": 0.0018, "lr": 6.1738901219176555e-06, "epoch": 15.885588558855886, "percentage": 79.43, "elapsed_time": "5:41:41", "remaining_time": "1:28:29", "throughput": 1486.43, "total_tokens": 30473504} {"current_steps": 144405, "total_steps": 181800, "loss": 0.0323, "lr": 6.172311036809103e-06, "epoch": 15.886138613861386, "percentage": 79.43, "elapsed_time": "5:41:41", "remaining_time": "1:28:29", "throughput": 1486.44, "total_tokens": 30474624} {"current_steps": 144410, "total_steps": 181800, "loss": 0.0113, "lr": 6.170732125226319e-06, "epoch": 15.886688668866887, "percentage": 79.43, "elapsed_time": "5:41:42", "remaining_time": "1:28:28", "throughput": 1486.44, "total_tokens": 30475648} {"current_steps": 144415, "total_steps": 181800, "loss": 0.0876, "lr": 6.169153387183871e-06, "epoch": 15.887238723872388, "percentage": 79.44, "elapsed_time": "5:41:43", "remaining_time": "1:28:27", "throughput": 1486.43, "total_tokens": 30476672} {"current_steps": 144420, "total_steps": 181800, "loss": 0.0024, "lr": 6.1675748226962894e-06, "epoch": 15.887788778877887, "percentage": 79.44, "elapsed_time": "5:41:43", "remaining_time": "1:28:26", "throughput": 1486.44, "total_tokens": 30477728} {"current_steps": 144425, "total_steps": 181800, "loss": 0.037, "lr": 6.165996431778142e-06, "epoch": 15.888338833883388, "percentage": 79.44, "elapsed_time": "5:41:44", "remaining_time": "1:28:26", "throughput": 1486.44, "total_tokens": 30478848} {"current_steps": 144430, "total_steps": 181800, "loss": 0.0224, "lr": 6.164418214443962e-06, "epoch": 15.88888888888889, "percentage": 79.44, "elapsed_time": "5:41:45", "remaining_time": "1:28:25", "throughput": 1486.44, "total_tokens": 30479936} {"current_steps": 144435, "total_steps": 181800, "loss": 0.0063, "lr": 6.1628401707083e-06, "epoch": 15.88943894389439, "percentage": 79.45, "elapsed_time": "5:41:45", "remaining_time": "1:28:24", "throughput": 1486.44, "total_tokens": 30480960} {"current_steps": 144440, "total_steps": 181800, "loss": 0.0248, "lr": 6.16126230058571e-06, "epoch": 15.88998899889989, "percentage": 79.45, "elapsed_time": "5:41:46", "remaining_time": "1:28:24", "throughput": 1486.44, "total_tokens": 30482016} {"current_steps": 144445, "total_steps": 181800, "loss": 0.0181, "lr": 6.159684604090718e-06, "epoch": 15.89053905390539, "percentage": 79.45, "elapsed_time": "5:41:47", "remaining_time": "1:28:23", "throughput": 1486.45, "total_tokens": 30483072} {"current_steps": 144450, "total_steps": 181800, "loss": 0.0267, "lr": 6.158107081237879e-06, "epoch": 15.891089108910892, "percentage": 79.46, "elapsed_time": "5:41:48", "remaining_time": "1:28:22", "throughput": 1486.45, "total_tokens": 30484128} {"current_steps": 144455, "total_steps": 181800, "loss": 0.0488, "lr": 6.156529732041719e-06, "epoch": 15.891639163916391, "percentage": 79.46, "elapsed_time": "5:41:48", "remaining_time": "1:28:21", "throughput": 1486.45, "total_tokens": 30485152} {"current_steps": 144460, "total_steps": 181800, "loss": 0.0747, "lr": 6.15495255651678e-06, "epoch": 15.892189218921892, "percentage": 79.46, "elapsed_time": "5:41:49", "remaining_time": "1:28:21", "throughput": 1486.45, "total_tokens": 30486144} {"current_steps": 144465, "total_steps": 181800, "loss": 0.0924, "lr": 6.153375554677612e-06, "epoch": 15.892739273927393, "percentage": 79.46, "elapsed_time": "5:41:50", "remaining_time": "1:28:20", "throughput": 1486.45, "total_tokens": 30487200} {"current_steps": 144470, "total_steps": 181800, "loss": 0.1042, "lr": 6.15179872653873e-06, "epoch": 15.893289328932893, "percentage": 79.47, "elapsed_time": "5:41:50", "remaining_time": "1:28:19", "throughput": 1486.45, "total_tokens": 30488224} {"current_steps": 144475, "total_steps": 181800, "loss": 0.0446, "lr": 6.150222072114678e-06, "epoch": 15.893839383938394, "percentage": 79.47, "elapsed_time": "5:41:51", "remaining_time": "1:28:19", "throughput": 1486.45, "total_tokens": 30489312} {"current_steps": 144480, "total_steps": 181800, "loss": 0.1114, "lr": 6.148645591419988e-06, "epoch": 15.894389438943895, "percentage": 79.47, "elapsed_time": "5:41:52", "remaining_time": "1:28:18", "throughput": 1486.45, "total_tokens": 30490336} {"current_steps": 144485, "total_steps": 181800, "loss": 0.1889, "lr": 6.147069284469178e-06, "epoch": 15.894939493949394, "percentage": 79.47, "elapsed_time": "5:41:52", "remaining_time": "1:28:17", "throughput": 1486.45, "total_tokens": 30491456} {"current_steps": 144490, "total_steps": 181800, "loss": 0.0021, "lr": 6.1454931512767825e-06, "epoch": 15.895489548954895, "percentage": 79.48, "elapsed_time": "5:41:53", "remaining_time": "1:28:16", "throughput": 1486.45, "total_tokens": 30492416} {"current_steps": 144495, "total_steps": 181800, "loss": 0.003, "lr": 6.143917191857332e-06, "epoch": 15.896039603960396, "percentage": 79.48, "elapsed_time": "5:41:54", "remaining_time": "1:28:16", "throughput": 1486.45, "total_tokens": 30493472} {"current_steps": 144500, "total_steps": 181800, "loss": 0.0116, "lr": 6.142341406225355e-06, "epoch": 15.896589658965897, "percentage": 79.48, "elapsed_time": "5:41:54", "remaining_time": "1:28:15", "throughput": 1486.45, "total_tokens": 30494528} {"current_steps": 144505, "total_steps": 181800, "loss": 0.0113, "lr": 6.140765794395367e-06, "epoch": 15.897139713971397, "percentage": 79.49, "elapsed_time": "5:41:55", "remaining_time": "1:28:14", "throughput": 1486.45, "total_tokens": 30495584} {"current_steps": 144510, "total_steps": 181800, "loss": 0.0071, "lr": 6.139190356381885e-06, "epoch": 15.897689768976898, "percentage": 79.49, "elapsed_time": "5:41:56", "remaining_time": "1:28:14", "throughput": 1486.46, "total_tokens": 30496704} {"current_steps": 144515, "total_steps": 181800, "loss": 0.0437, "lr": 6.1376150921994335e-06, "epoch": 15.898239823982399, "percentage": 79.49, "elapsed_time": "5:41:57", "remaining_time": "1:28:13", "throughput": 1486.46, "total_tokens": 30497664} {"current_steps": 144520, "total_steps": 181800, "loss": 0.2019, "lr": 6.136040001862536e-06, "epoch": 15.898789878987898, "percentage": 79.49, "elapsed_time": "5:41:57", "remaining_time": "1:28:12", "throughput": 1486.46, "total_tokens": 30498752} {"current_steps": 144525, "total_steps": 181800, "loss": 0.0144, "lr": 6.13446508538571e-06, "epoch": 15.8993399339934, "percentage": 79.5, "elapsed_time": "5:41:58", "remaining_time": "1:28:11", "throughput": 1486.46, "total_tokens": 30499872} {"current_steps": 144530, "total_steps": 181800, "loss": 0.0187, "lr": 6.1328903427834674e-06, "epoch": 15.8998899889989, "percentage": 79.5, "elapsed_time": "5:41:59", "remaining_time": "1:28:11", "throughput": 1486.46, "total_tokens": 30500896} {"current_steps": 144535, "total_steps": 181800, "loss": 0.0596, "lr": 6.131315774070315e-06, "epoch": 15.9004400440044, "percentage": 79.5, "elapsed_time": "5:41:59", "remaining_time": "1:28:10", "throughput": 1486.47, "total_tokens": 30501952} {"current_steps": 144540, "total_steps": 181800, "loss": 0.1046, "lr": 6.129741379260778e-06, "epoch": 15.900990099009901, "percentage": 79.5, "elapsed_time": "5:42:00", "remaining_time": "1:28:09", "throughput": 1486.47, "total_tokens": 30503072} {"current_steps": 144545, "total_steps": 181800, "loss": 0.0021, "lr": 6.128167158369353e-06, "epoch": 15.901540154015402, "percentage": 79.51, "elapsed_time": "5:42:01", "remaining_time": "1:28:09", "throughput": 1486.47, "total_tokens": 30504192} {"current_steps": 144550, "total_steps": 181800, "loss": 0.0023, "lr": 6.126593111410556e-06, "epoch": 15.902090209020901, "percentage": 79.51, "elapsed_time": "5:42:01", "remaining_time": "1:28:08", "throughput": 1486.48, "total_tokens": 30505312} {"current_steps": 144555, "total_steps": 181800, "loss": 0.0029, "lr": 6.1250192383988995e-06, "epoch": 15.902640264026402, "percentage": 79.51, "elapsed_time": "5:42:02", "remaining_time": "1:28:07", "throughput": 1486.48, "total_tokens": 30506336} {"current_steps": 144560, "total_steps": 181800, "loss": 0.0013, "lr": 6.123445539348877e-06, "epoch": 15.903190319031903, "percentage": 79.52, "elapsed_time": "5:42:03", "remaining_time": "1:28:06", "throughput": 1486.48, "total_tokens": 30507456} {"current_steps": 144565, "total_steps": 181800, "loss": 0.0157, "lr": 6.121872014275007e-06, "epoch": 15.903740374037405, "percentage": 79.52, "elapsed_time": "5:42:03", "remaining_time": "1:28:06", "throughput": 1486.49, "total_tokens": 30508512} {"current_steps": 144570, "total_steps": 181800, "loss": 0.0077, "lr": 6.1202986631917755e-06, "epoch": 15.904290429042904, "percentage": 79.52, "elapsed_time": "5:42:04", "remaining_time": "1:28:05", "throughput": 1486.49, "total_tokens": 30509600} {"current_steps": 144575, "total_steps": 181800, "loss": 0.0259, "lr": 6.118725486113694e-06, "epoch": 15.904840484048405, "percentage": 79.52, "elapsed_time": "5:42:05", "remaining_time": "1:28:04", "throughput": 1486.49, "total_tokens": 30510592} {"current_steps": 144580, "total_steps": 181800, "loss": 0.0014, "lr": 6.1171524830552665e-06, "epoch": 15.905390539053906, "percentage": 79.53, "elapsed_time": "5:42:05", "remaining_time": "1:28:04", "throughput": 1486.49, "total_tokens": 30511680} {"current_steps": 144585, "total_steps": 181800, "loss": 0.0161, "lr": 6.115579654030976e-06, "epoch": 15.905940594059405, "percentage": 79.53, "elapsed_time": "5:42:06", "remaining_time": "1:28:03", "throughput": 1486.49, "total_tokens": 30512704} {"current_steps": 144590, "total_steps": 181800, "loss": 0.0068, "lr": 6.114006999055333e-06, "epoch": 15.906490649064907, "percentage": 79.53, "elapsed_time": "5:42:07", "remaining_time": "1:28:02", "throughput": 1486.49, "total_tokens": 30513728} {"current_steps": 144595, "total_steps": 181800, "loss": 0.0022, "lr": 6.1124345181428235e-06, "epoch": 15.907040704070408, "percentage": 79.54, "elapsed_time": "5:42:08", "remaining_time": "1:28:01", "throughput": 1486.49, "total_tokens": 30514816} {"current_steps": 144600, "total_steps": 181800, "loss": 0.0011, "lr": 6.110862211307936e-06, "epoch": 15.907590759075907, "percentage": 79.54, "elapsed_time": "5:42:08", "remaining_time": "1:28:01", "throughput": 1486.5, "total_tokens": 30515904} {"current_steps": 144605, "total_steps": 181800, "loss": 0.0026, "lr": 6.109290078565169e-06, "epoch": 15.908140814081408, "percentage": 79.54, "elapsed_time": "5:42:09", "remaining_time": "1:28:00", "throughput": 1486.5, "total_tokens": 30516960} {"current_steps": 144610, "total_steps": 181800, "loss": 0.0019, "lr": 6.10771811992901e-06, "epoch": 15.908690869086909, "percentage": 79.54, "elapsed_time": "5:42:10", "remaining_time": "1:27:59", "throughput": 1486.5, "total_tokens": 30518016} {"current_steps": 144615, "total_steps": 181800, "loss": 0.0141, "lr": 6.106146335413953e-06, "epoch": 15.909240924092408, "percentage": 79.55, "elapsed_time": "5:42:10", "remaining_time": "1:27:59", "throughput": 1486.5, "total_tokens": 30519104} {"current_steps": 144620, "total_steps": 181800, "loss": 0.0406, "lr": 6.1045747250344815e-06, "epoch": 15.90979097909791, "percentage": 79.55, "elapsed_time": "5:42:11", "remaining_time": "1:27:58", "throughput": 1486.5, "total_tokens": 30520192} {"current_steps": 144625, "total_steps": 181800, "loss": 0.0058, "lr": 6.10300328880507e-06, "epoch": 15.91034103410341, "percentage": 79.55, "elapsed_time": "5:42:12", "remaining_time": "1:27:57", "throughput": 1486.51, "total_tokens": 30521248} {"current_steps": 144630, "total_steps": 181800, "loss": 0.0177, "lr": 6.101432026740217e-06, "epoch": 15.910891089108912, "percentage": 79.55, "elapsed_time": "5:42:12", "remaining_time": "1:27:56", "throughput": 1486.51, "total_tokens": 30522368} {"current_steps": 144635, "total_steps": 181800, "loss": 0.0042, "lr": 6.099860938854382e-06, "epoch": 15.911441144114411, "percentage": 79.56, "elapsed_time": "5:42:13", "remaining_time": "1:27:56", "throughput": 1486.51, "total_tokens": 30523456} {"current_steps": 144640, "total_steps": 181800, "loss": 0.1826, "lr": 6.098290025162073e-06, "epoch": 15.911991199119912, "percentage": 79.56, "elapsed_time": "5:42:14", "remaining_time": "1:27:55", "throughput": 1486.52, "total_tokens": 30524576} {"current_steps": 144645, "total_steps": 181800, "loss": 0.0755, "lr": 6.096719285677754e-06, "epoch": 15.912541254125413, "percentage": 79.56, "elapsed_time": "5:42:14", "remaining_time": "1:27:54", "throughput": 1486.52, "total_tokens": 30525632} {"current_steps": 144650, "total_steps": 181800, "loss": 0.0009, "lr": 6.0951487204158966e-06, "epoch": 15.913091309130913, "percentage": 79.57, "elapsed_time": "5:42:15", "remaining_time": "1:27:54", "throughput": 1486.52, "total_tokens": 30526688} {"current_steps": 144655, "total_steps": 181800, "loss": 0.0028, "lr": 6.093578329390992e-06, "epoch": 15.913641364136414, "percentage": 79.57, "elapsed_time": "5:42:16", "remaining_time": "1:27:53", "throughput": 1486.52, "total_tokens": 30527744} {"current_steps": 144660, "total_steps": 181800, "loss": 0.0029, "lr": 6.092008112617492e-06, "epoch": 15.914191419141915, "percentage": 79.57, "elapsed_time": "5:42:17", "remaining_time": "1:27:52", "throughput": 1486.52, "total_tokens": 30528800} {"current_steps": 144665, "total_steps": 181800, "loss": 0.0014, "lr": 6.090438070109883e-06, "epoch": 15.914741474147414, "percentage": 79.57, "elapsed_time": "5:42:17", "remaining_time": "1:27:51", "throughput": 1486.53, "total_tokens": 30529856} {"current_steps": 144670, "total_steps": 181800, "loss": 0.0007, "lr": 6.088868201882638e-06, "epoch": 15.915291529152915, "percentage": 79.58, "elapsed_time": "5:42:18", "remaining_time": "1:27:51", "throughput": 1486.52, "total_tokens": 30530848} {"current_steps": 144675, "total_steps": 181800, "loss": 0.0016, "lr": 6.0872985079502176e-06, "epoch": 15.915841584158416, "percentage": 79.58, "elapsed_time": "5:42:19", "remaining_time": "1:27:50", "throughput": 1486.53, "total_tokens": 30531936} {"current_steps": 144680, "total_steps": 181800, "loss": 0.0032, "lr": 6.085728988327094e-06, "epoch": 15.916391639163916, "percentage": 79.58, "elapsed_time": "5:42:19", "remaining_time": "1:27:49", "throughput": 1486.53, "total_tokens": 30533024} {"current_steps": 144685, "total_steps": 181800, "loss": 0.0134, "lr": 6.084159643027726e-06, "epoch": 15.916941694169417, "percentage": 79.58, "elapsed_time": "5:42:20", "remaining_time": "1:27:49", "throughput": 1486.53, "total_tokens": 30534048} {"current_steps": 144690, "total_steps": 181800, "loss": 0.1182, "lr": 6.082590472066588e-06, "epoch": 15.917491749174918, "percentage": 79.59, "elapsed_time": "5:42:21", "remaining_time": "1:27:48", "throughput": 1486.53, "total_tokens": 30535104} {"current_steps": 144695, "total_steps": 181800, "loss": 0.0013, "lr": 6.081021475458129e-06, "epoch": 15.918041804180419, "percentage": 79.59, "elapsed_time": "5:42:21", "remaining_time": "1:27:47", "throughput": 1486.53, "total_tokens": 30536128} {"current_steps": 144700, "total_steps": 181800, "loss": 0.0035, "lr": 6.079452653216816e-06, "epoch": 15.918591859185918, "percentage": 79.59, "elapsed_time": "5:42:22", "remaining_time": "1:27:46", "throughput": 1486.54, "total_tokens": 30537216} {"current_steps": 144705, "total_steps": 181800, "loss": 0.0018, "lr": 6.077884005357118e-06, "epoch": 15.91914191419142, "percentage": 79.6, "elapsed_time": "5:42:23", "remaining_time": "1:27:46", "throughput": 1486.54, "total_tokens": 30538304} {"current_steps": 144710, "total_steps": 181800, "loss": 0.1345, "lr": 6.076315531893473e-06, "epoch": 15.91969196919692, "percentage": 79.6, "elapsed_time": "5:42:23", "remaining_time": "1:27:45", "throughput": 1486.54, "total_tokens": 30539392} {"current_steps": 144715, "total_steps": 181800, "loss": 0.0023, "lr": 6.074747232840358e-06, "epoch": 15.92024202420242, "percentage": 79.6, "elapsed_time": "5:42:24", "remaining_time": "1:27:44", "throughput": 1486.55, "total_tokens": 30540480} {"current_steps": 144720, "total_steps": 181800, "loss": 0.0588, "lr": 6.073179108212207e-06, "epoch": 15.92079207920792, "percentage": 79.6, "elapsed_time": "5:42:25", "remaining_time": "1:27:44", "throughput": 1486.55, "total_tokens": 30541536} {"current_steps": 144725, "total_steps": 181800, "loss": 0.0101, "lr": 6.071611158023483e-06, "epoch": 15.921342134213422, "percentage": 79.61, "elapsed_time": "5:42:25", "remaining_time": "1:27:43", "throughput": 1486.55, "total_tokens": 30542592} {"current_steps": 144730, "total_steps": 181800, "loss": 0.0045, "lr": 6.070043382288643e-06, "epoch": 15.921892189218921, "percentage": 79.61, "elapsed_time": "5:42:26", "remaining_time": "1:27:42", "throughput": 1486.55, "total_tokens": 30543616} {"current_steps": 144735, "total_steps": 181800, "loss": 0.0021, "lr": 6.068475781022123e-06, "epoch": 15.922442244224422, "percentage": 79.61, "elapsed_time": "5:42:27", "remaining_time": "1:27:41", "throughput": 1486.54, "total_tokens": 30544704} {"current_steps": 144740, "total_steps": 181800, "loss": 0.043, "lr": 6.066908354238385e-06, "epoch": 15.922992299229923, "percentage": 79.61, "elapsed_time": "5:42:28", "remaining_time": "1:27:41", "throughput": 1486.54, "total_tokens": 30545792} {"current_steps": 144745, "total_steps": 181800, "loss": 0.0104, "lr": 6.065341101951869e-06, "epoch": 15.923542354235423, "percentage": 79.62, "elapsed_time": "5:42:28", "remaining_time": "1:27:40", "throughput": 1486.55, "total_tokens": 30546880} {"current_steps": 144750, "total_steps": 181800, "loss": 0.1024, "lr": 6.063774024177002e-06, "epoch": 15.924092409240924, "percentage": 79.62, "elapsed_time": "5:42:29", "remaining_time": "1:27:39", "throughput": 1486.55, "total_tokens": 30547904} {"current_steps": 144755, "total_steps": 181800, "loss": 0.0011, "lr": 6.062207120928256e-06, "epoch": 15.924642464246425, "percentage": 79.62, "elapsed_time": "5:42:30", "remaining_time": "1:27:39", "throughput": 1486.55, "total_tokens": 30548928} {"current_steps": 144760, "total_steps": 181800, "loss": 0.0506, "lr": 6.060640392220054e-06, "epoch": 15.925192519251926, "percentage": 79.63, "elapsed_time": "5:42:30", "remaining_time": "1:27:38", "throughput": 1486.55, "total_tokens": 30550016} {"current_steps": 144765, "total_steps": 181800, "loss": 0.009, "lr": 6.059073838066851e-06, "epoch": 15.925742574257425, "percentage": 79.63, "elapsed_time": "5:42:31", "remaining_time": "1:27:37", "throughput": 1486.55, "total_tokens": 30551008} {"current_steps": 144770, "total_steps": 181800, "loss": 0.0041, "lr": 6.0575074584830745e-06, "epoch": 15.926292629262926, "percentage": 79.63, "elapsed_time": "5:42:32", "remaining_time": "1:27:36", "throughput": 1486.55, "total_tokens": 30552032} {"current_steps": 144775, "total_steps": 181800, "loss": 0.0131, "lr": 6.055941253483155e-06, "epoch": 15.926842684268427, "percentage": 79.63, "elapsed_time": "5:42:33", "remaining_time": "1:27:36", "throughput": 1486.55, "total_tokens": 30553024} {"current_steps": 144780, "total_steps": 181800, "loss": 0.006, "lr": 6.0543752230815324e-06, "epoch": 15.927392739273927, "percentage": 79.64, "elapsed_time": "5:42:33", "remaining_time": "1:27:35", "throughput": 1486.55, "total_tokens": 30554048} {"current_steps": 144785, "total_steps": 181800, "loss": 0.0014, "lr": 6.052809367292653e-06, "epoch": 15.927942794279428, "percentage": 79.64, "elapsed_time": "5:42:34", "remaining_time": "1:27:34", "throughput": 1486.55, "total_tokens": 30555168} {"current_steps": 144790, "total_steps": 181800, "loss": 0.0013, "lr": 6.051243686130928e-06, "epoch": 15.928492849284929, "percentage": 79.64, "elapsed_time": "5:42:35", "remaining_time": "1:27:34", "throughput": 1486.55, "total_tokens": 30556224} {"current_steps": 144795, "total_steps": 181800, "loss": 0.0009, "lr": 6.049678179610807e-06, "epoch": 15.929042904290428, "percentage": 79.65, "elapsed_time": "5:42:35", "remaining_time": "1:27:33", "throughput": 1486.55, "total_tokens": 30557280} {"current_steps": 144800, "total_steps": 181800, "loss": 0.109, "lr": 6.0481128477467005e-06, "epoch": 15.92959295929593, "percentage": 79.65, "elapsed_time": "5:42:36", "remaining_time": "1:27:32", "throughput": 1486.55, "total_tokens": 30558304} {"current_steps": 144805, "total_steps": 181800, "loss": 0.0101, "lr": 6.04654769055305e-06, "epoch": 15.93014301430143, "percentage": 79.65, "elapsed_time": "5:42:37", "remaining_time": "1:27:31", "throughput": 1486.55, "total_tokens": 30559296} {"current_steps": 144810, "total_steps": 181800, "loss": 0.0038, "lr": 6.0449827080442694e-06, "epoch": 15.930693069306932, "percentage": 79.65, "elapsed_time": "5:42:37", "remaining_time": "1:27:31", "throughput": 1486.55, "total_tokens": 30560320} {"current_steps": 144815, "total_steps": 181800, "loss": 0.0071, "lr": 6.043417900234788e-06, "epoch": 15.93124312431243, "percentage": 79.66, "elapsed_time": "5:42:38", "remaining_time": "1:27:30", "throughput": 1486.55, "total_tokens": 30561344} {"current_steps": 144820, "total_steps": 181800, "loss": 0.0103, "lr": 6.041853267139033e-06, "epoch": 15.931793179317932, "percentage": 79.66, "elapsed_time": "5:42:39", "remaining_time": "1:27:29", "throughput": 1486.55, "total_tokens": 30562400} {"current_steps": 144825, "total_steps": 181800, "loss": 0.0073, "lr": 6.040288808771413e-06, "epoch": 15.932343234323433, "percentage": 79.66, "elapsed_time": "5:42:39", "remaining_time": "1:27:29", "throughput": 1486.56, "total_tokens": 30563456} {"current_steps": 144830, "total_steps": 181800, "loss": 0.0038, "lr": 6.038724525146361e-06, "epoch": 15.932893289328932, "percentage": 79.66, "elapsed_time": "5:42:40", "remaining_time": "1:27:28", "throughput": 1486.56, "total_tokens": 30564544} {"current_steps": 144835, "total_steps": 181800, "loss": 0.0027, "lr": 6.037160416278278e-06, "epoch": 15.933443344334433, "percentage": 79.67, "elapsed_time": "5:42:41", "remaining_time": "1:27:27", "throughput": 1486.56, "total_tokens": 30565600} {"current_steps": 144840, "total_steps": 181800, "loss": 0.0945, "lr": 6.035596482181588e-06, "epoch": 15.933993399339935, "percentage": 79.67, "elapsed_time": "5:42:41", "remaining_time": "1:27:26", "throughput": 1486.56, "total_tokens": 30566688} {"current_steps": 144845, "total_steps": 181800, "loss": 0.1074, "lr": 6.0340327228707135e-06, "epoch": 15.934543454345434, "percentage": 79.67, "elapsed_time": "5:42:42", "remaining_time": "1:27:26", "throughput": 1486.57, "total_tokens": 30567744} {"current_steps": 144850, "total_steps": 181800, "loss": 0.003, "lr": 6.032469138360053e-06, "epoch": 15.935093509350935, "percentage": 79.68, "elapsed_time": "5:42:43", "remaining_time": "1:27:25", "throughput": 1486.57, "total_tokens": 30568768} {"current_steps": 144855, "total_steps": 181800, "loss": 0.004, "lr": 6.030905728664027e-06, "epoch": 15.935643564356436, "percentage": 79.68, "elapsed_time": "5:42:44", "remaining_time": "1:27:24", "throughput": 1486.57, "total_tokens": 30569856} {"current_steps": 144860, "total_steps": 181800, "loss": 0.0749, "lr": 6.029342493797041e-06, "epoch": 15.936193619361937, "percentage": 79.68, "elapsed_time": "5:42:44", "remaining_time": "1:27:24", "throughput": 1486.57, "total_tokens": 30570976} {"current_steps": 144865, "total_steps": 181800, "loss": 0.085, "lr": 6.027779433773498e-06, "epoch": 15.936743674367436, "percentage": 79.68, "elapsed_time": "5:42:45", "remaining_time": "1:27:23", "throughput": 1486.58, "total_tokens": 30572064} {"current_steps": 144870, "total_steps": 181800, "loss": 0.0058, "lr": 6.026216548607805e-06, "epoch": 15.937293729372938, "percentage": 79.69, "elapsed_time": "5:42:46", "remaining_time": "1:27:22", "throughput": 1486.58, "total_tokens": 30573152} {"current_steps": 144875, "total_steps": 181800, "loss": 0.0089, "lr": 6.02465383831437e-06, "epoch": 15.937843784378439, "percentage": 79.69, "elapsed_time": "5:42:46", "remaining_time": "1:27:21", "throughput": 1486.58, "total_tokens": 30574240} {"current_steps": 144880, "total_steps": 181800, "loss": 0.0048, "lr": 6.023091302907605e-06, "epoch": 15.938393839383938, "percentage": 79.69, "elapsed_time": "5:42:47", "remaining_time": "1:27:21", "throughput": 1486.59, "total_tokens": 30575328} {"current_steps": 144885, "total_steps": 181800, "loss": 0.0012, "lr": 6.021528942401899e-06, "epoch": 15.938943894389439, "percentage": 79.69, "elapsed_time": "5:42:48", "remaining_time": "1:27:20", "throughput": 1486.59, "total_tokens": 30576352} {"current_steps": 144890, "total_steps": 181800, "loss": 0.0046, "lr": 6.019966756811648e-06, "epoch": 15.93949394939494, "percentage": 79.7, "elapsed_time": "5:42:48", "remaining_time": "1:27:19", "throughput": 1486.59, "total_tokens": 30577472} {"current_steps": 144895, "total_steps": 181800, "loss": 0.0028, "lr": 6.018404746151257e-06, "epoch": 15.94004400440044, "percentage": 79.7, "elapsed_time": "5:42:49", "remaining_time": "1:27:19", "throughput": 1486.59, "total_tokens": 30578560} {"current_steps": 144900, "total_steps": 181800, "loss": 0.0028, "lr": 6.016842910435119e-06, "epoch": 15.94059405940594, "percentage": 79.7, "elapsed_time": "5:42:50", "remaining_time": "1:27:18", "throughput": 1486.6, "total_tokens": 30579712} {"current_steps": 144905, "total_steps": 181800, "loss": 0.0991, "lr": 6.015281249677637e-06, "epoch": 15.941144114411442, "percentage": 79.71, "elapsed_time": "5:42:50", "remaining_time": "1:27:17", "throughput": 1486.6, "total_tokens": 30580736} {"current_steps": 144910, "total_steps": 181800, "loss": 0.0012, "lr": 6.0137197638932025e-06, "epoch": 15.941694169416941, "percentage": 79.71, "elapsed_time": "5:42:51", "remaining_time": "1:27:16", "throughput": 1486.6, "total_tokens": 30581792} {"current_steps": 144915, "total_steps": 181800, "loss": 0.0046, "lr": 6.012158453096192e-06, "epoch": 15.942244224422442, "percentage": 79.71, "elapsed_time": "5:42:52", "remaining_time": "1:27:16", "throughput": 1486.6, "total_tokens": 30582816} {"current_steps": 144920, "total_steps": 181800, "loss": 0.0027, "lr": 6.010597317301014e-06, "epoch": 15.942794279427943, "percentage": 79.71, "elapsed_time": "5:42:52", "remaining_time": "1:27:15", "throughput": 1486.61, "total_tokens": 30583872} {"current_steps": 144925, "total_steps": 181800, "loss": 0.0086, "lr": 6.0090363565220405e-06, "epoch": 15.943344334433444, "percentage": 79.72, "elapsed_time": "5:42:53", "remaining_time": "1:27:14", "throughput": 1486.61, "total_tokens": 30584928} {"current_steps": 144930, "total_steps": 181800, "loss": 0.1277, "lr": 6.007475570773666e-06, "epoch": 15.943894389438944, "percentage": 79.72, "elapsed_time": "5:42:54", "remaining_time": "1:27:14", "throughput": 1486.61, "total_tokens": 30585952} {"current_steps": 144935, "total_steps": 181800, "loss": 0.0012, "lr": 6.005914960070283e-06, "epoch": 15.944444444444445, "percentage": 79.72, "elapsed_time": "5:42:55", "remaining_time": "1:27:13", "throughput": 1486.6, "total_tokens": 30586944} {"current_steps": 144940, "total_steps": 181800, "loss": 0.002, "lr": 6.004354524426262e-06, "epoch": 15.944994499449946, "percentage": 79.72, "elapsed_time": "5:42:55", "remaining_time": "1:27:12", "throughput": 1486.6, "total_tokens": 30587904} {"current_steps": 144945, "total_steps": 181800, "loss": 0.016, "lr": 6.002794263855996e-06, "epoch": 15.945544554455445, "percentage": 79.73, "elapsed_time": "5:42:56", "remaining_time": "1:27:11", "throughput": 1486.6, "total_tokens": 30588960} {"current_steps": 144950, "total_steps": 181800, "loss": 0.0031, "lr": 6.001234178373852e-06, "epoch": 15.946094609460946, "percentage": 79.73, "elapsed_time": "5:42:57", "remaining_time": "1:27:11", "throughput": 1486.61, "total_tokens": 30590016} {"current_steps": 144955, "total_steps": 181800, "loss": 0.0063, "lr": 5.999674267994215e-06, "epoch": 15.946644664466447, "percentage": 79.73, "elapsed_time": "5:42:57", "remaining_time": "1:27:10", "throughput": 1486.6, "total_tokens": 30591008} {"current_steps": 144960, "total_steps": 181800, "loss": 0.0102, "lr": 5.998114532731475e-06, "epoch": 15.947194719471947, "percentage": 79.74, "elapsed_time": "5:42:58", "remaining_time": "1:27:09", "throughput": 1486.61, "total_tokens": 30592128} {"current_steps": 144965, "total_steps": 181800, "loss": 0.0048, "lr": 5.996554972599982e-06, "epoch": 15.947744774477448, "percentage": 79.74, "elapsed_time": "5:42:59", "remaining_time": "1:27:09", "throughput": 1486.61, "total_tokens": 30593184} {"current_steps": 144970, "total_steps": 181800, "loss": 0.0082, "lr": 5.994995587614136e-06, "epoch": 15.948294829482949, "percentage": 79.74, "elapsed_time": "5:42:59", "remaining_time": "1:27:08", "throughput": 1486.61, "total_tokens": 30594208} {"current_steps": 144975, "total_steps": 181800, "loss": 0.0028, "lr": 5.9934363777882914e-06, "epoch": 15.948844884488448, "percentage": 79.74, "elapsed_time": "5:43:00", "remaining_time": "1:27:07", "throughput": 1486.61, "total_tokens": 30595232} {"current_steps": 144980, "total_steps": 181800, "loss": 0.0384, "lr": 5.99187734313682e-06, "epoch": 15.94939493949395, "percentage": 79.75, "elapsed_time": "5:43:01", "remaining_time": "1:27:06", "throughput": 1486.61, "total_tokens": 30596224} {"current_steps": 144985, "total_steps": 181800, "loss": 0.0042, "lr": 5.990318483674093e-06, "epoch": 15.94994499449945, "percentage": 79.75, "elapsed_time": "5:43:01", "remaining_time": "1:27:06", "throughput": 1486.61, "total_tokens": 30597312} {"current_steps": 144990, "total_steps": 181800, "loss": 0.0007, "lr": 5.988759799414478e-06, "epoch": 15.950495049504951, "percentage": 79.75, "elapsed_time": "5:43:02", "remaining_time": "1:27:05", "throughput": 1486.61, "total_tokens": 30598368} {"current_steps": 144995, "total_steps": 181800, "loss": 0.0012, "lr": 5.987201290372349e-06, "epoch": 15.95104510451045, "percentage": 79.76, "elapsed_time": "5:43:03", "remaining_time": "1:27:04", "throughput": 1486.61, "total_tokens": 30599392} {"current_steps": 145000, "total_steps": 181800, "loss": 0.0025, "lr": 5.9856429565620626e-06, "epoch": 15.951595159515952, "percentage": 79.76, "elapsed_time": "5:43:03", "remaining_time": "1:27:04", "throughput": 1486.62, "total_tokens": 30600544} {"current_steps": 145005, "total_steps": 181800, "loss": 0.0014, "lr": 5.984084797997974e-06, "epoch": 15.952145214521453, "percentage": 79.76, "elapsed_time": "5:43:04", "remaining_time": "1:27:03", "throughput": 1486.62, "total_tokens": 30601632} {"current_steps": 145010, "total_steps": 181800, "loss": 0.1174, "lr": 5.98252681469445e-06, "epoch": 15.952695269526952, "percentage": 79.76, "elapsed_time": "5:43:05", "remaining_time": "1:27:02", "throughput": 1486.63, "total_tokens": 30602688} {"current_steps": 145015, "total_steps": 181800, "loss": 0.0019, "lr": 5.980969006665851e-06, "epoch": 15.953245324532453, "percentage": 79.77, "elapsed_time": "5:43:06", "remaining_time": "1:27:01", "throughput": 1486.63, "total_tokens": 30603712} {"current_steps": 145020, "total_steps": 181800, "loss": 0.0036, "lr": 5.979411373926544e-06, "epoch": 15.953795379537954, "percentage": 79.77, "elapsed_time": "5:43:06", "remaining_time": "1:27:01", "throughput": 1486.63, "total_tokens": 30604768} {"current_steps": 145025, "total_steps": 181800, "loss": 0.0021, "lr": 5.977853916490872e-06, "epoch": 15.954345434543454, "percentage": 79.77, "elapsed_time": "5:43:07", "remaining_time": "1:27:00", "throughput": 1486.63, "total_tokens": 30605792} {"current_steps": 145030, "total_steps": 181800, "loss": 0.0698, "lr": 5.976296634373188e-06, "epoch": 15.954895489548955, "percentage": 79.77, "elapsed_time": "5:43:08", "remaining_time": "1:26:59", "throughput": 1486.63, "total_tokens": 30606816} {"current_steps": 145035, "total_steps": 181800, "loss": 0.0025, "lr": 5.974739527587856e-06, "epoch": 15.955445544554456, "percentage": 79.78, "elapsed_time": "5:43:08", "remaining_time": "1:26:59", "throughput": 1486.63, "total_tokens": 30607840} {"current_steps": 145040, "total_steps": 181800, "loss": 0.138, "lr": 5.973182596149213e-06, "epoch": 15.955995599559955, "percentage": 79.78, "elapsed_time": "5:43:09", "remaining_time": "1:26:58", "throughput": 1486.63, "total_tokens": 30608832} {"current_steps": 145045, "total_steps": 181800, "loss": 0.0011, "lr": 5.971625840071618e-06, "epoch": 15.956545654565456, "percentage": 79.78, "elapsed_time": "5:43:10", "remaining_time": "1:26:57", "throughput": 1486.63, "total_tokens": 30609888} {"current_steps": 145050, "total_steps": 181800, "loss": 0.0627, "lr": 5.970069259369421e-06, "epoch": 15.957095709570957, "percentage": 79.79, "elapsed_time": "5:43:10", "remaining_time": "1:26:56", "throughput": 1486.63, "total_tokens": 30610944} {"current_steps": 145055, "total_steps": 181800, "loss": 0.0076, "lr": 5.9685128540569595e-06, "epoch": 15.957645764576458, "percentage": 79.79, "elapsed_time": "5:43:11", "remaining_time": "1:26:56", "throughput": 1486.63, "total_tokens": 30612032} {"current_steps": 145060, "total_steps": 181800, "loss": 0.0916, "lr": 5.9669566241485865e-06, "epoch": 15.958195819581958, "percentage": 79.79, "elapsed_time": "5:43:12", "remaining_time": "1:26:55", "throughput": 1486.64, "total_tokens": 30613088} {"current_steps": 145065, "total_steps": 181800, "loss": 0.0017, "lr": 5.965400569658639e-06, "epoch": 15.958745874587459, "percentage": 79.79, "elapsed_time": "5:43:12", "remaining_time": "1:26:54", "throughput": 1486.64, "total_tokens": 30614112} {"current_steps": 145070, "total_steps": 181800, "loss": 0.0057, "lr": 5.963844690601458e-06, "epoch": 15.95929592959296, "percentage": 79.8, "elapsed_time": "5:43:13", "remaining_time": "1:26:54", "throughput": 1486.64, "total_tokens": 30615200} {"current_steps": 145075, "total_steps": 181800, "loss": 0.0029, "lr": 5.962288986991394e-06, "epoch": 15.95984598459846, "percentage": 79.8, "elapsed_time": "5:43:14", "remaining_time": "1:26:53", "throughput": 1486.64, "total_tokens": 30616256} {"current_steps": 145080, "total_steps": 181800, "loss": 0.0032, "lr": 5.9607334588427685e-06, "epoch": 15.96039603960396, "percentage": 79.8, "elapsed_time": "5:43:14", "remaining_time": "1:26:52", "throughput": 1486.65, "total_tokens": 30617344} {"current_steps": 145085, "total_steps": 181800, "loss": 0.0034, "lr": 5.959178106169936e-06, "epoch": 15.960946094609461, "percentage": 79.8, "elapsed_time": "5:43:15", "remaining_time": "1:26:51", "throughput": 1486.65, "total_tokens": 30618400} {"current_steps": 145090, "total_steps": 181800, "loss": 0.0256, "lr": 5.957622928987214e-06, "epoch": 15.96149614961496, "percentage": 79.81, "elapsed_time": "5:43:16", "remaining_time": "1:26:51", "throughput": 1486.65, "total_tokens": 30619424} {"current_steps": 145095, "total_steps": 181800, "loss": 0.077, "lr": 5.956067927308953e-06, "epoch": 15.962046204620462, "percentage": 79.81, "elapsed_time": "5:43:16", "remaining_time": "1:26:50", "throughput": 1486.65, "total_tokens": 30620480} {"current_steps": 145100, "total_steps": 181800, "loss": 0.1076, "lr": 5.954513101149467e-06, "epoch": 15.962596259625963, "percentage": 79.81, "elapsed_time": "5:43:17", "remaining_time": "1:26:49", "throughput": 1486.66, "total_tokens": 30621632} {"current_steps": 145105, "total_steps": 181800, "loss": 0.0187, "lr": 5.952958450523094e-06, "epoch": 15.963146314631462, "percentage": 79.82, "elapsed_time": "5:43:18", "remaining_time": "1:26:49", "throughput": 1486.66, "total_tokens": 30622656} {"current_steps": 145110, "total_steps": 181800, "loss": 0.0126, "lr": 5.951403975444172e-06, "epoch": 15.963696369636963, "percentage": 79.82, "elapsed_time": "5:43:19", "remaining_time": "1:26:48", "throughput": 1486.66, "total_tokens": 30623680} {"current_steps": 145115, "total_steps": 181800, "loss": 0.0197, "lr": 5.949849675927011e-06, "epoch": 15.964246424642464, "percentage": 79.82, "elapsed_time": "5:43:19", "remaining_time": "1:26:47", "throughput": 1486.66, "total_tokens": 30624768} {"current_steps": 145120, "total_steps": 181800, "loss": 0.0653, "lr": 5.948295551985952e-06, "epoch": 15.964796479647966, "percentage": 79.82, "elapsed_time": "5:43:20", "remaining_time": "1:26:46", "throughput": 1486.66, "total_tokens": 30625760} {"current_steps": 145125, "total_steps": 181800, "loss": 0.0808, "lr": 5.946741603635303e-06, "epoch": 15.965346534653465, "percentage": 79.83, "elapsed_time": "5:43:21", "remaining_time": "1:26:46", "throughput": 1486.66, "total_tokens": 30626784} {"current_steps": 145130, "total_steps": 181800, "loss": 0.0059, "lr": 5.945187830889395e-06, "epoch": 15.965896589658966, "percentage": 79.83, "elapsed_time": "5:43:21", "remaining_time": "1:26:45", "throughput": 1486.66, "total_tokens": 30627808} {"current_steps": 145135, "total_steps": 181800, "loss": 0.0019, "lr": 5.943634233762554e-06, "epoch": 15.966446644664467, "percentage": 79.83, "elapsed_time": "5:43:22", "remaining_time": "1:26:44", "throughput": 1486.66, "total_tokens": 30628864} {"current_steps": 145140, "total_steps": 181800, "loss": 0.0032, "lr": 5.942080812269085e-06, "epoch": 15.966996699669966, "percentage": 79.83, "elapsed_time": "5:43:23", "remaining_time": "1:26:44", "throughput": 1486.66, "total_tokens": 30629856} {"current_steps": 145145, "total_steps": 181800, "loss": 0.0049, "lr": 5.94052756642332e-06, "epoch": 15.967546754675467, "percentage": 79.84, "elapsed_time": "5:43:23", "remaining_time": "1:26:43", "throughput": 1486.67, "total_tokens": 30631008} {"current_steps": 145150, "total_steps": 181800, "loss": 0.0007, "lr": 5.938974496239566e-06, "epoch": 15.968096809680969, "percentage": 79.84, "elapsed_time": "5:43:24", "remaining_time": "1:26:42", "throughput": 1486.67, "total_tokens": 30632032} {"current_steps": 145155, "total_steps": 181800, "loss": 0.0051, "lr": 5.937421601732132e-06, "epoch": 15.968646864686468, "percentage": 79.84, "elapsed_time": "5:43:25", "remaining_time": "1:26:41", "throughput": 1486.67, "total_tokens": 30633088} {"current_steps": 145160, "total_steps": 181800, "loss": 0.0013, "lr": 5.935868882915335e-06, "epoch": 15.969196919691969, "percentage": 79.85, "elapsed_time": "5:43:25", "remaining_time": "1:26:41", "throughput": 1486.67, "total_tokens": 30634112} {"current_steps": 145165, "total_steps": 181800, "loss": 0.0631, "lr": 5.934316339803495e-06, "epoch": 15.96974697469747, "percentage": 79.85, "elapsed_time": "5:43:26", "remaining_time": "1:26:40", "throughput": 1486.67, "total_tokens": 30635168} {"current_steps": 145170, "total_steps": 181800, "loss": 0.0664, "lr": 5.932763972410901e-06, "epoch": 15.97029702970297, "percentage": 79.85, "elapsed_time": "5:43:27", "remaining_time": "1:26:39", "throughput": 1486.67, "total_tokens": 30636192} {"current_steps": 145175, "total_steps": 181800, "loss": 0.0027, "lr": 5.931211780751883e-06, "epoch": 15.97084708470847, "percentage": 79.85, "elapsed_time": "5:43:27", "remaining_time": "1:26:39", "throughput": 1486.67, "total_tokens": 30637216} {"current_steps": 145180, "total_steps": 181800, "loss": 0.0571, "lr": 5.929659764840728e-06, "epoch": 15.971397139713972, "percentage": 79.86, "elapsed_time": "5:43:28", "remaining_time": "1:26:38", "throughput": 1486.68, "total_tokens": 30638336} {"current_steps": 145185, "total_steps": 181800, "loss": 0.0306, "lr": 5.92810792469175e-06, "epoch": 15.971947194719473, "percentage": 79.86, "elapsed_time": "5:43:29", "remaining_time": "1:26:37", "throughput": 1486.68, "total_tokens": 30639456} {"current_steps": 145190, "total_steps": 181800, "loss": 0.0014, "lr": 5.926556260319255e-06, "epoch": 15.972497249724972, "percentage": 79.86, "elapsed_time": "5:43:29", "remaining_time": "1:26:36", "throughput": 1486.68, "total_tokens": 30640512} {"current_steps": 145195, "total_steps": 181800, "loss": 0.0817, "lr": 5.925004771737533e-06, "epoch": 15.973047304730473, "percentage": 79.87, "elapsed_time": "5:43:30", "remaining_time": "1:26:36", "throughput": 1486.68, "total_tokens": 30641536} {"current_steps": 145200, "total_steps": 181800, "loss": 0.0036, "lr": 5.9234534589608924e-06, "epoch": 15.973597359735974, "percentage": 79.87, "elapsed_time": "5:43:31", "remaining_time": "1:26:35", "throughput": 1486.68, "total_tokens": 30642592} {"current_steps": 145205, "total_steps": 181800, "loss": 0.0031, "lr": 5.921902322003625e-06, "epoch": 15.974147414741473, "percentage": 79.87, "elapsed_time": "5:43:32", "remaining_time": "1:26:34", "throughput": 1486.68, "total_tokens": 30643584} {"current_steps": 145210, "total_steps": 181800, "loss": 0.0022, "lr": 5.920351360880033e-06, "epoch": 15.974697469746975, "percentage": 79.87, "elapsed_time": "5:43:32", "remaining_time": "1:26:33", "throughput": 1486.69, "total_tokens": 30644672} {"current_steps": 145215, "total_steps": 181800, "loss": 0.1035, "lr": 5.918800575604402e-06, "epoch": 15.975247524752476, "percentage": 79.88, "elapsed_time": "5:43:33", "remaining_time": "1:26:33", "throughput": 1486.69, "total_tokens": 30645696} {"current_steps": 145220, "total_steps": 181800, "loss": 0.0695, "lr": 5.91724996619103e-06, "epoch": 15.975797579757975, "percentage": 79.88, "elapsed_time": "5:43:34", "remaining_time": "1:26:32", "throughput": 1486.69, "total_tokens": 30646784} {"current_steps": 145225, "total_steps": 181800, "loss": 0.0088, "lr": 5.915699532654215e-06, "epoch": 15.976347634763476, "percentage": 79.88, "elapsed_time": "5:43:34", "remaining_time": "1:26:31", "throughput": 1486.69, "total_tokens": 30647808} {"current_steps": 145230, "total_steps": 181800, "loss": 0.0255, "lr": 5.914149275008232e-06, "epoch": 15.976897689768977, "percentage": 79.88, "elapsed_time": "5:43:35", "remaining_time": "1:26:31", "throughput": 1486.69, "total_tokens": 30648864} {"current_steps": 145235, "total_steps": 181800, "loss": 0.0221, "lr": 5.9125991932673845e-06, "epoch": 15.977447744774478, "percentage": 79.89, "elapsed_time": "5:43:36", "remaining_time": "1:26:30", "throughput": 1486.7, "total_tokens": 30649952} {"current_steps": 145240, "total_steps": 181800, "loss": 0.0542, "lr": 5.911049287445944e-06, "epoch": 15.977997799779978, "percentage": 79.89, "elapsed_time": "5:43:36", "remaining_time": "1:26:29", "throughput": 1486.7, "total_tokens": 30651008} {"current_steps": 145245, "total_steps": 181800, "loss": 0.1003, "lr": 5.909499557558201e-06, "epoch": 15.978547854785479, "percentage": 79.89, "elapsed_time": "5:43:37", "remaining_time": "1:26:28", "throughput": 1486.7, "total_tokens": 30652064} {"current_steps": 145250, "total_steps": 181800, "loss": 0.0054, "lr": 5.907950003618451e-06, "epoch": 15.97909790979098, "percentage": 79.9, "elapsed_time": "5:43:38", "remaining_time": "1:26:28", "throughput": 1486.7, "total_tokens": 30653152} {"current_steps": 145255, "total_steps": 181800, "loss": 0.0046, "lr": 5.906400625640954e-06, "epoch": 15.979647964796479, "percentage": 79.9, "elapsed_time": "5:43:38", "remaining_time": "1:26:27", "throughput": 1486.7, "total_tokens": 30654208} {"current_steps": 145260, "total_steps": 181800, "loss": 0.0534, "lr": 5.904851423640009e-06, "epoch": 15.98019801980198, "percentage": 79.9, "elapsed_time": "5:43:39", "remaining_time": "1:26:26", "throughput": 1486.71, "total_tokens": 30655264} {"current_steps": 145265, "total_steps": 181800, "loss": 0.0006, "lr": 5.903302397629884e-06, "epoch": 15.980748074807481, "percentage": 79.9, "elapsed_time": "5:43:40", "remaining_time": "1:26:26", "throughput": 1486.71, "total_tokens": 30656352} {"current_steps": 145270, "total_steps": 181800, "loss": 0.0067, "lr": 5.901753547624853e-06, "epoch": 15.98129812981298, "percentage": 79.91, "elapsed_time": "5:43:40", "remaining_time": "1:26:25", "throughput": 1486.71, "total_tokens": 30657472} {"current_steps": 145275, "total_steps": 181800, "loss": 0.0099, "lr": 5.900204873639192e-06, "epoch": 15.981848184818482, "percentage": 79.91, "elapsed_time": "5:43:41", "remaining_time": "1:26:24", "throughput": 1486.71, "total_tokens": 30658496} {"current_steps": 145280, "total_steps": 181800, "loss": 0.0399, "lr": 5.898656375687181e-06, "epoch": 15.982398239823983, "percentage": 79.91, "elapsed_time": "5:43:42", "remaining_time": "1:26:23", "throughput": 1486.72, "total_tokens": 30659552} {"current_steps": 145285, "total_steps": 181800, "loss": 0.0007, "lr": 5.897108053783093e-06, "epoch": 15.982948294829484, "percentage": 79.91, "elapsed_time": "5:43:43", "remaining_time": "1:26:23", "throughput": 1486.72, "total_tokens": 30660608} {"current_steps": 145290, "total_steps": 181800, "loss": 0.0022, "lr": 5.895559907941195e-06, "epoch": 15.983498349834983, "percentage": 79.92, "elapsed_time": "5:43:43", "remaining_time": "1:26:22", "throughput": 1486.72, "total_tokens": 30661696} {"current_steps": 145295, "total_steps": 181800, "loss": 0.0596, "lr": 5.894011938175747e-06, "epoch": 15.984048404840484, "percentage": 79.92, "elapsed_time": "5:43:44", "remaining_time": "1:26:21", "throughput": 1486.72, "total_tokens": 30662688} {"current_steps": 145300, "total_steps": 181800, "loss": 0.0019, "lr": 5.892464144501023e-06, "epoch": 15.984598459845985, "percentage": 79.92, "elapsed_time": "5:43:45", "remaining_time": "1:26:21", "throughput": 1486.72, "total_tokens": 30663712} {"current_steps": 145305, "total_steps": 181800, "loss": 0.0013, "lr": 5.89091652693129e-06, "epoch": 15.985148514851485, "percentage": 79.93, "elapsed_time": "5:43:45", "remaining_time": "1:26:20", "throughput": 1486.72, "total_tokens": 30664768} {"current_steps": 145310, "total_steps": 181800, "loss": 0.0207, "lr": 5.889369085480814e-06, "epoch": 15.985698569856986, "percentage": 79.93, "elapsed_time": "5:43:46", "remaining_time": "1:26:19", "throughput": 1486.72, "total_tokens": 30665856} {"current_steps": 145315, "total_steps": 181800, "loss": 0.0032, "lr": 5.887821820163855e-06, "epoch": 15.986248624862487, "percentage": 79.93, "elapsed_time": "5:43:47", "remaining_time": "1:26:18", "throughput": 1486.73, "total_tokens": 30666912} {"current_steps": 145320, "total_steps": 181800, "loss": 0.0072, "lr": 5.886274730994662e-06, "epoch": 15.986798679867986, "percentage": 79.93, "elapsed_time": "5:43:47", "remaining_time": "1:26:18", "throughput": 1486.73, "total_tokens": 30667968} {"current_steps": 145325, "total_steps": 181800, "loss": 0.0011, "lr": 5.884727817987512e-06, "epoch": 15.987348734873487, "percentage": 79.94, "elapsed_time": "5:43:48", "remaining_time": "1:26:17", "throughput": 1486.73, "total_tokens": 30668960} {"current_steps": 145330, "total_steps": 181800, "loss": 0.0022, "lr": 5.883181081156647e-06, "epoch": 15.987898789878988, "percentage": 79.94, "elapsed_time": "5:43:49", "remaining_time": "1:26:16", "throughput": 1486.73, "total_tokens": 30670016} {"current_steps": 145335, "total_steps": 181800, "loss": 0.1082, "lr": 5.881634520516327e-06, "epoch": 15.988448844884488, "percentage": 79.94, "elapsed_time": "5:43:49", "remaining_time": "1:26:16", "throughput": 1486.73, "total_tokens": 30671072} {"current_steps": 145340, "total_steps": 181800, "loss": 0.0724, "lr": 5.880088136080814e-06, "epoch": 15.988998899889989, "percentage": 79.94, "elapsed_time": "5:43:50", "remaining_time": "1:26:15", "throughput": 1486.73, "total_tokens": 30672128} {"current_steps": 145345, "total_steps": 181800, "loss": 0.0078, "lr": 5.87854192786435e-06, "epoch": 15.98954895489549, "percentage": 79.95, "elapsed_time": "5:43:51", "remaining_time": "1:26:14", "throughput": 1486.74, "total_tokens": 30673248} {"current_steps": 145350, "total_steps": 181800, "loss": 0.0369, "lr": 5.876995895881194e-06, "epoch": 15.990099009900991, "percentage": 79.95, "elapsed_time": "5:43:51", "remaining_time": "1:26:13", "throughput": 1486.74, "total_tokens": 30674336} {"current_steps": 145355, "total_steps": 181800, "loss": 0.0889, "lr": 5.875450040145591e-06, "epoch": 15.99064906490649, "percentage": 79.95, "elapsed_time": "5:43:52", "remaining_time": "1:26:13", "throughput": 1486.74, "total_tokens": 30675360} {"current_steps": 145360, "total_steps": 181800, "loss": 0.0115, "lr": 5.873904360671775e-06, "epoch": 15.991199119911991, "percentage": 79.96, "elapsed_time": "5:43:53", "remaining_time": "1:26:12", "throughput": 1486.74, "total_tokens": 30676384} {"current_steps": 145365, "total_steps": 181800, "loss": 0.077, "lr": 5.87235885747402e-06, "epoch": 15.991749174917492, "percentage": 79.96, "elapsed_time": "5:43:53", "remaining_time": "1:26:11", "throughput": 1486.74, "total_tokens": 30677408} {"current_steps": 145370, "total_steps": 181800, "loss": 0.0566, "lr": 5.870813530566546e-06, "epoch": 15.992299229922992, "percentage": 79.96, "elapsed_time": "5:43:54", "remaining_time": "1:26:11", "throughput": 1486.74, "total_tokens": 30678432} {"current_steps": 145375, "total_steps": 181800, "loss": 0.0673, "lr": 5.869268379963613e-06, "epoch": 15.992849284928493, "percentage": 79.96, "elapsed_time": "5:43:55", "remaining_time": "1:26:10", "throughput": 1486.74, "total_tokens": 30679456} {"current_steps": 145380, "total_steps": 181800, "loss": 0.0524, "lr": 5.867723405679454e-06, "epoch": 15.993399339933994, "percentage": 79.97, "elapsed_time": "5:43:56", "remaining_time": "1:26:09", "throughput": 1486.75, "total_tokens": 30680544} {"current_steps": 145385, "total_steps": 181800, "loss": 0.0061, "lr": 5.866178607728301e-06, "epoch": 15.993949394939493, "percentage": 79.97, "elapsed_time": "5:43:56", "remaining_time": "1:26:08", "throughput": 1486.75, "total_tokens": 30681568} {"current_steps": 145390, "total_steps": 181800, "loss": 0.0015, "lr": 5.864633986124396e-06, "epoch": 15.994499449944994, "percentage": 79.97, "elapsed_time": "5:43:57", "remaining_time": "1:26:08", "throughput": 1486.75, "total_tokens": 30682592} {"current_steps": 145395, "total_steps": 181800, "loss": 0.033, "lr": 5.86308954088198e-06, "epoch": 15.995049504950495, "percentage": 79.98, "elapsed_time": "5:43:58", "remaining_time": "1:26:07", "throughput": 1486.75, "total_tokens": 30683616} {"current_steps": 145400, "total_steps": 181800, "loss": 0.0463, "lr": 5.861545272015289e-06, "epoch": 15.995599559955995, "percentage": 79.98, "elapsed_time": "5:43:58", "remaining_time": "1:26:06", "throughput": 1486.75, "total_tokens": 30684704} {"current_steps": 145405, "total_steps": 181800, "loss": 0.0631, "lr": 5.8600011795385545e-06, "epoch": 15.996149614961496, "percentage": 79.98, "elapsed_time": "5:43:59", "remaining_time": "1:26:06", "throughput": 1486.76, "total_tokens": 30685792} {"current_steps": 145410, "total_steps": 181800, "loss": 0.0049, "lr": 5.8584572634659964e-06, "epoch": 15.996699669966997, "percentage": 79.98, "elapsed_time": "5:44:00", "remaining_time": "1:26:05", "throughput": 1486.76, "total_tokens": 30686880} {"current_steps": 145415, "total_steps": 181800, "loss": 0.0821, "lr": 5.8569135238118606e-06, "epoch": 15.997249724972498, "percentage": 79.99, "elapsed_time": "5:44:00", "remaining_time": "1:26:04", "throughput": 1486.76, "total_tokens": 30687936} {"current_steps": 145420, "total_steps": 181800, "loss": 0.0286, "lr": 5.855369960590354e-06, "epoch": 15.997799779977997, "percentage": 79.99, "elapsed_time": "5:44:01", "remaining_time": "1:26:03", "throughput": 1486.76, "total_tokens": 30689024} {"current_steps": 145425, "total_steps": 181800, "loss": 0.0053, "lr": 5.853826573815727e-06, "epoch": 15.998349834983498, "percentage": 79.99, "elapsed_time": "5:44:02", "remaining_time": "1:26:03", "throughput": 1486.77, "total_tokens": 30690112} {"current_steps": 145430, "total_steps": 181800, "loss": 0.0069, "lr": 5.852283363502195e-06, "epoch": 15.998899889989, "percentage": 79.99, "elapsed_time": "5:44:02", "remaining_time": "1:26:02", "throughput": 1486.77, "total_tokens": 30691200} {"current_steps": 145435, "total_steps": 181800, "loss": 0.0106, "lr": 5.850740329663973e-06, "epoch": 15.999449944994499, "percentage": 80.0, "elapsed_time": "5:44:03", "remaining_time": "1:26:01", "throughput": 1486.77, "total_tokens": 30692192} {"current_steps": 145440, "total_steps": 181800, "loss": 0.0331, "lr": 5.849197472315296e-06, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "5:44:04", "remaining_time": "1:26:01", "throughput": 1486.76, "total_tokens": 30693088} {"current_steps": 145440, "total_steps": 181800, "eval_loss": 0.07597047090530396, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "5:44:41", "remaining_time": "1:26:10", "throughput": 1484.1, "total_tokens": 30693088} {"current_steps": 145445, "total_steps": 181800, "loss": 0.0642, "lr": 5.847654791470367e-06, "epoch": 16.0005500550055, "percentage": 80.0, "elapsed_time": "5:44:44", "remaining_time": "1:26:10", "throughput": 1483.95, "total_tokens": 30694208} {"current_steps": 145450, "total_steps": 181800, "loss": 0.007, "lr": 5.846112287143415e-06, "epoch": 16.001100110011002, "percentage": 80.01, "elapsed_time": "5:44:44", "remaining_time": "1:26:09", "throughput": 1483.95, "total_tokens": 30695232} {"current_steps": 145455, "total_steps": 181800, "loss": 0.0038, "lr": 5.8445699593486615e-06, "epoch": 16.001650165016503, "percentage": 80.01, "elapsed_time": "5:44:45", "remaining_time": "1:26:08", "throughput": 1483.95, "total_tokens": 30696256} {"current_steps": 145460, "total_steps": 181800, "loss": 0.0019, "lr": 5.84302780810031e-06, "epoch": 16.002200220022, "percentage": 80.01, "elapsed_time": "5:44:46", "remaining_time": "1:26:07", "throughput": 1483.95, "total_tokens": 30697344} {"current_steps": 145465, "total_steps": 181800, "loss": 0.0022, "lr": 5.841485833412583e-06, "epoch": 16.002750275027502, "percentage": 80.01, "elapsed_time": "5:44:46", "remaining_time": "1:26:07", "throughput": 1483.95, "total_tokens": 30698304} {"current_steps": 145470, "total_steps": 181800, "loss": 0.0046, "lr": 5.839944035299682e-06, "epoch": 16.003300330033003, "percentage": 80.02, "elapsed_time": "5:44:47", "remaining_time": "1:26:06", "throughput": 1483.96, "total_tokens": 30699488} {"current_steps": 145475, "total_steps": 181800, "loss": 0.0055, "lr": 5.838402413775831e-06, "epoch": 16.003850385038504, "percentage": 80.02, "elapsed_time": "5:44:48", "remaining_time": "1:26:05", "throughput": 1483.96, "total_tokens": 30700544} {"current_steps": 145480, "total_steps": 181800, "loss": 0.1087, "lr": 5.836860968855224e-06, "epoch": 16.004400440044005, "percentage": 80.02, "elapsed_time": "5:44:49", "remaining_time": "1:26:05", "throughput": 1483.96, "total_tokens": 30701632} {"current_steps": 145485, "total_steps": 181800, "loss": 0.002, "lr": 5.835319700552072e-06, "epoch": 16.004950495049506, "percentage": 80.02, "elapsed_time": "5:44:49", "remaining_time": "1:26:04", "throughput": 1483.95, "total_tokens": 30702688} {"current_steps": 145490, "total_steps": 181800, "loss": 0.0081, "lr": 5.8337786088805884e-06, "epoch": 16.005500550055004, "percentage": 80.03, "elapsed_time": "5:44:50", "remaining_time": "1:26:03", "throughput": 1483.95, "total_tokens": 30703744} {"current_steps": 145495, "total_steps": 181800, "loss": 0.0025, "lr": 5.832237693854966e-06, "epoch": 16.006050605060505, "percentage": 80.03, "elapsed_time": "5:44:51", "remaining_time": "1:26:03", "throughput": 1483.95, "total_tokens": 30704832} {"current_steps": 145500, "total_steps": 181800, "loss": 0.0711, "lr": 5.830696955489417e-06, "epoch": 16.006600660066006, "percentage": 80.03, "elapsed_time": "5:44:52", "remaining_time": "1:26:02", "throughput": 1483.95, "total_tokens": 30705856} {"current_steps": 145505, "total_steps": 181800, "loss": 0.0027, "lr": 5.82915639379813e-06, "epoch": 16.007150715071507, "percentage": 80.04, "elapsed_time": "5:44:52", "remaining_time": "1:26:01", "throughput": 1483.95, "total_tokens": 30706880} {"current_steps": 145510, "total_steps": 181800, "loss": 0.0021, "lr": 5.827616008795308e-06, "epoch": 16.007700770077008, "percentage": 80.04, "elapsed_time": "5:44:53", "remaining_time": "1:26:00", "throughput": 1483.95, "total_tokens": 30708000} {"current_steps": 145515, "total_steps": 181800, "loss": 0.0085, "lr": 5.826075800495156e-06, "epoch": 16.00825082508251, "percentage": 80.04, "elapsed_time": "5:44:54", "remaining_time": "1:26:00", "throughput": 1483.95, "total_tokens": 30708960} {"current_steps": 145520, "total_steps": 181800, "loss": 0.0046, "lr": 5.824535768911856e-06, "epoch": 16.00880088008801, "percentage": 80.04, "elapsed_time": "5:44:54", "remaining_time": "1:25:59", "throughput": 1483.95, "total_tokens": 30709984} {"current_steps": 145525, "total_steps": 181800, "loss": 0.0914, "lr": 5.822995914059618e-06, "epoch": 16.009350935093508, "percentage": 80.05, "elapsed_time": "5:44:55", "remaining_time": "1:25:58", "throughput": 1483.95, "total_tokens": 30711040} {"current_steps": 145530, "total_steps": 181800, "loss": 0.0039, "lr": 5.821456235952621e-06, "epoch": 16.00990099009901, "percentage": 80.05, "elapsed_time": "5:44:56", "remaining_time": "1:25:58", "throughput": 1483.95, "total_tokens": 30712128} {"current_steps": 145535, "total_steps": 181800, "loss": 0.0326, "lr": 5.819916734605049e-06, "epoch": 16.01045104510451, "percentage": 80.05, "elapsed_time": "5:44:56", "remaining_time": "1:25:57", "throughput": 1483.95, "total_tokens": 30713152} {"current_steps": 145540, "total_steps": 181800, "loss": 0.0031, "lr": 5.818377410031112e-06, "epoch": 16.01100110011001, "percentage": 80.06, "elapsed_time": "5:44:57", "remaining_time": "1:25:56", "throughput": 1483.96, "total_tokens": 30714272} {"current_steps": 145545, "total_steps": 181800, "loss": 0.0048, "lr": 5.816838262244981e-06, "epoch": 16.011551155115512, "percentage": 80.06, "elapsed_time": "5:44:58", "remaining_time": "1:25:55", "throughput": 1483.96, "total_tokens": 30715360} {"current_steps": 145550, "total_steps": 181800, "loss": 0.0309, "lr": 5.815299291260851e-06, "epoch": 16.012101210121013, "percentage": 80.06, "elapsed_time": "5:44:58", "remaining_time": "1:25:55", "throughput": 1483.96, "total_tokens": 30716416} {"current_steps": 145555, "total_steps": 181800, "loss": 0.0128, "lr": 5.8137604970929046e-06, "epoch": 16.01265126512651, "percentage": 80.06, "elapsed_time": "5:44:59", "remaining_time": "1:25:54", "throughput": 1483.97, "total_tokens": 30717568} {"current_steps": 145560, "total_steps": 181800, "loss": 0.1138, "lr": 5.812221879755314e-06, "epoch": 16.013201320132012, "percentage": 80.07, "elapsed_time": "5:45:00", "remaining_time": "1:25:53", "throughput": 1483.97, "total_tokens": 30718592} {"current_steps": 145565, "total_steps": 181800, "loss": 0.0072, "lr": 5.810683439262266e-06, "epoch": 16.013751375137513, "percentage": 80.07, "elapsed_time": "5:45:01", "remaining_time": "1:25:53", "throughput": 1483.97, "total_tokens": 30719712} {"current_steps": 145570, "total_steps": 181800, "loss": 0.0079, "lr": 5.809145175627947e-06, "epoch": 16.014301430143014, "percentage": 80.07, "elapsed_time": "5:45:01", "remaining_time": "1:25:52", "throughput": 1483.97, "total_tokens": 30720736} {"current_steps": 145575, "total_steps": 181800, "loss": 0.0016, "lr": 5.8076070888665236e-06, "epoch": 16.014851485148515, "percentage": 80.07, "elapsed_time": "5:45:02", "remaining_time": "1:25:51", "throughput": 1483.97, "total_tokens": 30721792} {"current_steps": 145580, "total_steps": 181800, "loss": 0.0164, "lr": 5.806069178992182e-06, "epoch": 16.015401540154016, "percentage": 80.08, "elapsed_time": "5:45:03", "remaining_time": "1:25:50", "throughput": 1483.97, "total_tokens": 30722784} {"current_steps": 145585, "total_steps": 181800, "loss": 0.0078, "lr": 5.804531446019082e-06, "epoch": 16.015951595159517, "percentage": 80.08, "elapsed_time": "5:45:03", "remaining_time": "1:25:50", "throughput": 1483.97, "total_tokens": 30723808} {"current_steps": 145590, "total_steps": 181800, "loss": 0.0194, "lr": 5.802993889961414e-06, "epoch": 16.016501650165015, "percentage": 80.08, "elapsed_time": "5:45:04", "remaining_time": "1:25:49", "throughput": 1483.97, "total_tokens": 30724864} {"current_steps": 145595, "total_steps": 181800, "loss": 0.016, "lr": 5.801456510833333e-06, "epoch": 16.017051705170516, "percentage": 80.09, "elapsed_time": "5:45:05", "remaining_time": "1:25:48", "throughput": 1483.97, "total_tokens": 30725952} {"current_steps": 145600, "total_steps": 181800, "loss": 0.0102, "lr": 5.799919308649013e-06, "epoch": 16.017601760176017, "percentage": 80.09, "elapsed_time": "5:45:05", "remaining_time": "1:25:48", "throughput": 1483.98, "total_tokens": 30727008} {"current_steps": 145605, "total_steps": 181800, "loss": 0.0029, "lr": 5.798382283422632e-06, "epoch": 16.01815181518152, "percentage": 80.09, "elapsed_time": "5:45:06", "remaining_time": "1:25:47", "throughput": 1483.98, "total_tokens": 30728032} {"current_steps": 145610, "total_steps": 181800, "loss": 0.0249, "lr": 5.796845435168341e-06, "epoch": 16.01870187018702, "percentage": 80.09, "elapsed_time": "5:45:07", "remaining_time": "1:25:46", "throughput": 1483.98, "total_tokens": 30729152} {"current_steps": 145615, "total_steps": 181800, "loss": 0.0049, "lr": 5.795308763900317e-06, "epoch": 16.01925192519252, "percentage": 80.1, "elapsed_time": "5:45:07", "remaining_time": "1:25:45", "throughput": 1483.98, "total_tokens": 30730208} {"current_steps": 145620, "total_steps": 181800, "loss": 0.0011, "lr": 5.79377226963271e-06, "epoch": 16.019801980198018, "percentage": 80.1, "elapsed_time": "5:45:08", "remaining_time": "1:25:45", "throughput": 1483.98, "total_tokens": 30731200} {"current_steps": 145625, "total_steps": 181800, "loss": 0.0145, "lr": 5.79223595237969e-06, "epoch": 16.02035203520352, "percentage": 80.1, "elapsed_time": "5:45:09", "remaining_time": "1:25:44", "throughput": 1483.98, "total_tokens": 30732288} {"current_steps": 145630, "total_steps": 181800, "loss": 0.0598, "lr": 5.7906998121554204e-06, "epoch": 16.02090209020902, "percentage": 80.1, "elapsed_time": "5:45:10", "remaining_time": "1:25:43", "throughput": 1483.98, "total_tokens": 30733312} {"current_steps": 145635, "total_steps": 181800, "loss": 0.0247, "lr": 5.789163848974044e-06, "epoch": 16.02145214521452, "percentage": 80.11, "elapsed_time": "5:45:10", "remaining_time": "1:25:43", "throughput": 1483.98, "total_tokens": 30734368} {"current_steps": 145640, "total_steps": 181800, "loss": 0.0136, "lr": 5.787628062849734e-06, "epoch": 16.022002200220022, "percentage": 80.11, "elapsed_time": "5:45:11", "remaining_time": "1:25:42", "throughput": 1483.99, "total_tokens": 30735424} {"current_steps": 145645, "total_steps": 181800, "loss": 0.0554, "lr": 5.786092453796638e-06, "epoch": 16.022552255225524, "percentage": 80.11, "elapsed_time": "5:45:12", "remaining_time": "1:25:41", "throughput": 1483.99, "total_tokens": 30736448} {"current_steps": 145650, "total_steps": 181800, "loss": 0.0063, "lr": 5.784557021828902e-06, "epoch": 16.023102310231025, "percentage": 80.12, "elapsed_time": "5:45:12", "remaining_time": "1:25:40", "throughput": 1483.98, "total_tokens": 30737408} {"current_steps": 145655, "total_steps": 181800, "loss": 0.0016, "lr": 5.783021766960681e-06, "epoch": 16.023652365236522, "percentage": 80.12, "elapsed_time": "5:45:13", "remaining_time": "1:25:40", "throughput": 1483.98, "total_tokens": 30738464} {"current_steps": 145660, "total_steps": 181800, "loss": 0.0062, "lr": 5.781486689206128e-06, "epoch": 16.024202420242023, "percentage": 80.12, "elapsed_time": "5:45:14", "remaining_time": "1:25:39", "throughput": 1483.98, "total_tokens": 30739488} {"current_steps": 145665, "total_steps": 181800, "loss": 0.0382, "lr": 5.779951788579399e-06, "epoch": 16.024752475247524, "percentage": 80.12, "elapsed_time": "5:45:14", "remaining_time": "1:25:38", "throughput": 1483.99, "total_tokens": 30740576} {"current_steps": 145670, "total_steps": 181800, "loss": 0.002, "lr": 5.77841706509463e-06, "epoch": 16.025302530253025, "percentage": 80.13, "elapsed_time": "5:45:15", "remaining_time": "1:25:37", "throughput": 1483.99, "total_tokens": 30741696} {"current_steps": 145675, "total_steps": 181800, "loss": 0.0052, "lr": 5.776882518765961e-06, "epoch": 16.025852585258527, "percentage": 80.13, "elapsed_time": "5:45:16", "remaining_time": "1:25:37", "throughput": 1484.0, "total_tokens": 30742784} {"current_steps": 145680, "total_steps": 181800, "loss": 0.005, "lr": 5.7753481496075425e-06, "epoch": 16.026402640264028, "percentage": 80.13, "elapsed_time": "5:45:16", "remaining_time": "1:25:36", "throughput": 1484.0, "total_tokens": 30743840} {"current_steps": 145685, "total_steps": 181800, "loss": 0.0379, "lr": 5.773813957633514e-06, "epoch": 16.02695269526953, "percentage": 80.13, "elapsed_time": "5:45:17", "remaining_time": "1:25:35", "throughput": 1484.0, "total_tokens": 30744864} {"current_steps": 145690, "total_steps": 181800, "loss": 0.1837, "lr": 5.772279942858025e-06, "epoch": 16.027502750275026, "percentage": 80.14, "elapsed_time": "5:45:18", "remaining_time": "1:25:35", "throughput": 1484.0, "total_tokens": 30745920} {"current_steps": 145695, "total_steps": 181800, "loss": 0.0028, "lr": 5.770746105295202e-06, "epoch": 16.028052805280527, "percentage": 80.14, "elapsed_time": "5:45:18", "remaining_time": "1:25:34", "throughput": 1484.0, "total_tokens": 30747008} {"current_steps": 145700, "total_steps": 181800, "loss": 0.0023, "lr": 5.769212444959182e-06, "epoch": 16.02860286028603, "percentage": 80.14, "elapsed_time": "5:45:19", "remaining_time": "1:25:33", "throughput": 1484.01, "total_tokens": 30748128} {"current_steps": 145705, "total_steps": 181800, "loss": 0.0004, "lr": 5.767678961864109e-06, "epoch": 16.02915291529153, "percentage": 80.15, "elapsed_time": "5:45:20", "remaining_time": "1:25:32", "throughput": 1484.01, "total_tokens": 30749184} {"current_steps": 145710, "total_steps": 181800, "loss": 0.0009, "lr": 5.7661456560241025e-06, "epoch": 16.02970297029703, "percentage": 80.15, "elapsed_time": "5:45:21", "remaining_time": "1:25:32", "throughput": 1484.01, "total_tokens": 30750240} {"current_steps": 145715, "total_steps": 181800, "loss": 0.0052, "lr": 5.764612527453303e-06, "epoch": 16.03025302530253, "percentage": 80.15, "elapsed_time": "5:45:21", "remaining_time": "1:25:31", "throughput": 1484.01, "total_tokens": 30751328} {"current_steps": 145720, "total_steps": 181800, "loss": 0.0348, "lr": 5.763079576165844e-06, "epoch": 16.03080308030803, "percentage": 80.15, "elapsed_time": "5:45:22", "remaining_time": "1:25:30", "throughput": 1484.02, "total_tokens": 30752416} {"current_steps": 145725, "total_steps": 181800, "loss": 0.0034, "lr": 5.7615468021758465e-06, "epoch": 16.03135313531353, "percentage": 80.16, "elapsed_time": "5:45:23", "remaining_time": "1:25:30", "throughput": 1484.02, "total_tokens": 30753504} {"current_steps": 145730, "total_steps": 181800, "loss": 0.069, "lr": 5.760014205497447e-06, "epoch": 16.03190319031903, "percentage": 80.16, "elapsed_time": "5:45:23", "remaining_time": "1:25:29", "throughput": 1484.02, "total_tokens": 30754592} {"current_steps": 145735, "total_steps": 181800, "loss": 0.0193, "lr": 5.758481786144757e-06, "epoch": 16.032453245324533, "percentage": 80.16, "elapsed_time": "5:45:24", "remaining_time": "1:25:28", "throughput": 1484.02, "total_tokens": 30755584} {"current_steps": 145740, "total_steps": 181800, "loss": 0.0234, "lr": 5.756949544131907e-06, "epoch": 16.033003300330034, "percentage": 80.17, "elapsed_time": "5:45:25", "remaining_time": "1:25:27", "throughput": 1484.02, "total_tokens": 30756672} {"current_steps": 145745, "total_steps": 181800, "loss": 0.0078, "lr": 5.755417479473027e-06, "epoch": 16.033553355335535, "percentage": 80.17, "elapsed_time": "5:45:25", "remaining_time": "1:25:27", "throughput": 1484.03, "total_tokens": 30757728} {"current_steps": 145750, "total_steps": 181800, "loss": 0.0042, "lr": 5.753885592182221e-06, "epoch": 16.034103410341036, "percentage": 80.17, "elapsed_time": "5:45:26", "remaining_time": "1:25:26", "throughput": 1484.03, "total_tokens": 30758784} {"current_steps": 145755, "total_steps": 181800, "loss": 0.0095, "lr": 5.7523538822736225e-06, "epoch": 16.034653465346533, "percentage": 80.17, "elapsed_time": "5:45:27", "remaining_time": "1:25:25", "throughput": 1484.03, "total_tokens": 30759872} {"current_steps": 145760, "total_steps": 181800, "loss": 0.0033, "lr": 5.750822349761345e-06, "epoch": 16.035203520352034, "percentage": 80.18, "elapsed_time": "5:45:27", "remaining_time": "1:25:25", "throughput": 1484.03, "total_tokens": 30760896} {"current_steps": 145765, "total_steps": 181800, "loss": 0.0424, "lr": 5.749290994659495e-06, "epoch": 16.035753575357536, "percentage": 80.18, "elapsed_time": "5:45:28", "remaining_time": "1:25:24", "throughput": 1484.03, "total_tokens": 30761856} {"current_steps": 145770, "total_steps": 181800, "loss": 0.0023, "lr": 5.74775981698219e-06, "epoch": 16.036303630363037, "percentage": 80.18, "elapsed_time": "5:45:29", "remaining_time": "1:25:23", "throughput": 1484.03, "total_tokens": 30762976} {"current_steps": 145775, "total_steps": 181800, "loss": 0.0948, "lr": 5.7462288167435455e-06, "epoch": 16.036853685368538, "percentage": 80.18, "elapsed_time": "5:45:30", "remaining_time": "1:25:22", "throughput": 1484.03, "total_tokens": 30764096} {"current_steps": 145780, "total_steps": 181800, "loss": 0.0239, "lr": 5.744697993957679e-06, "epoch": 16.03740374037404, "percentage": 80.19, "elapsed_time": "5:45:30", "remaining_time": "1:25:22", "throughput": 1484.04, "total_tokens": 30765152} {"current_steps": 145785, "total_steps": 181800, "loss": 0.0067, "lr": 5.743167348638689e-06, "epoch": 16.037953795379536, "percentage": 80.19, "elapsed_time": "5:45:31", "remaining_time": "1:25:21", "throughput": 1484.04, "total_tokens": 30766208} {"current_steps": 145790, "total_steps": 181800, "loss": 0.0045, "lr": 5.74163688080068e-06, "epoch": 16.038503850385037, "percentage": 80.19, "elapsed_time": "5:45:32", "remaining_time": "1:25:20", "throughput": 1484.04, "total_tokens": 30767296} {"current_steps": 145795, "total_steps": 181800, "loss": 0.0012, "lr": 5.740106590457764e-06, "epoch": 16.03905390539054, "percentage": 80.2, "elapsed_time": "5:45:32", "remaining_time": "1:25:20", "throughput": 1484.04, "total_tokens": 30768320} {"current_steps": 145800, "total_steps": 181800, "loss": 0.0014, "lr": 5.738576477624041e-06, "epoch": 16.03960396039604, "percentage": 80.2, "elapsed_time": "5:45:33", "remaining_time": "1:25:19", "throughput": 1484.04, "total_tokens": 30769376} {"current_steps": 145805, "total_steps": 181800, "loss": 0.2391, "lr": 5.737046542313626e-06, "epoch": 16.04015401540154, "percentage": 80.2, "elapsed_time": "5:45:34", "remaining_time": "1:25:18", "throughput": 1484.04, "total_tokens": 30770432} {"current_steps": 145810, "total_steps": 181800, "loss": 0.0106, "lr": 5.73551678454061e-06, "epoch": 16.040704070407042, "percentage": 80.2, "elapsed_time": "5:45:34", "remaining_time": "1:25:17", "throughput": 1484.04, "total_tokens": 30771456} {"current_steps": 145815, "total_steps": 181800, "loss": 0.0006, "lr": 5.733987204319083e-06, "epoch": 16.041254125412543, "percentage": 80.21, "elapsed_time": "5:45:35", "remaining_time": "1:25:17", "throughput": 1484.04, "total_tokens": 30772448} {"current_steps": 145820, "total_steps": 181800, "loss": 0.0042, "lr": 5.732457801663158e-06, "epoch": 16.04180418041804, "percentage": 80.21, "elapsed_time": "5:45:36", "remaining_time": "1:25:16", "throughput": 1484.05, "total_tokens": 30773504} {"current_steps": 145825, "total_steps": 181800, "loss": 0.0922, "lr": 5.730928576586917e-06, "epoch": 16.04235423542354, "percentage": 80.21, "elapsed_time": "5:45:36", "remaining_time": "1:25:15", "throughput": 1484.04, "total_tokens": 30774496} {"current_steps": 145830, "total_steps": 181800, "loss": 0.1368, "lr": 5.7293995291044595e-06, "epoch": 16.042904290429043, "percentage": 80.21, "elapsed_time": "5:45:37", "remaining_time": "1:25:15", "throughput": 1484.04, "total_tokens": 30775520} {"current_steps": 145835, "total_steps": 181800, "loss": 0.0886, "lr": 5.727870659229889e-06, "epoch": 16.043454345434544, "percentage": 80.22, "elapsed_time": "5:45:38", "remaining_time": "1:25:14", "throughput": 1484.04, "total_tokens": 30776576} {"current_steps": 145840, "total_steps": 181800, "loss": 0.0034, "lr": 5.726341966977281e-06, "epoch": 16.044004400440045, "percentage": 80.22, "elapsed_time": "5:45:38", "remaining_time": "1:25:13", "throughput": 1484.05, "total_tokens": 30777632} {"current_steps": 145845, "total_steps": 181800, "loss": 0.0488, "lr": 5.724813452360736e-06, "epoch": 16.044554455445546, "percentage": 80.22, "elapsed_time": "5:45:39", "remaining_time": "1:25:12", "throughput": 1484.05, "total_tokens": 30778688} {"current_steps": 145850, "total_steps": 181800, "loss": 0.0023, "lr": 5.723285115394328e-06, "epoch": 16.045104510451043, "percentage": 80.23, "elapsed_time": "5:45:40", "remaining_time": "1:25:12", "throughput": 1484.05, "total_tokens": 30779712} {"current_steps": 145855, "total_steps": 181800, "loss": 0.0014, "lr": 5.721756956092153e-06, "epoch": 16.045654565456545, "percentage": 80.23, "elapsed_time": "5:45:41", "remaining_time": "1:25:11", "throughput": 1484.05, "total_tokens": 30780832} {"current_steps": 145860, "total_steps": 181800, "loss": 0.0023, "lr": 5.7202289744683e-06, "epoch": 16.046204620462046, "percentage": 80.23, "elapsed_time": "5:45:41", "remaining_time": "1:25:10", "throughput": 1484.05, "total_tokens": 30781920} {"current_steps": 145865, "total_steps": 181800, "loss": 0.093, "lr": 5.718701170536839e-06, "epoch": 16.046754675467547, "percentage": 80.23, "elapsed_time": "5:45:42", "remaining_time": "1:25:10", "throughput": 1484.06, "total_tokens": 30782976} {"current_steps": 145870, "total_steps": 181800, "loss": 0.0026, "lr": 5.717173544311863e-06, "epoch": 16.047304730473048, "percentage": 80.24, "elapsed_time": "5:45:43", "remaining_time": "1:25:09", "throughput": 1484.06, "total_tokens": 30784032} {"current_steps": 145875, "total_steps": 181800, "loss": 0.0024, "lr": 5.715646095807439e-06, "epoch": 16.04785478547855, "percentage": 80.24, "elapsed_time": "5:45:43", "remaining_time": "1:25:08", "throughput": 1484.06, "total_tokens": 30785088} {"current_steps": 145880, "total_steps": 181800, "loss": 0.0073, "lr": 5.714118825037659e-06, "epoch": 16.04840484048405, "percentage": 80.24, "elapsed_time": "5:45:44", "remaining_time": "1:25:07", "throughput": 1484.06, "total_tokens": 30786144} {"current_steps": 145885, "total_steps": 181800, "loss": 0.0678, "lr": 5.712591732016584e-06, "epoch": 16.048954895489548, "percentage": 80.24, "elapsed_time": "5:45:45", "remaining_time": "1:25:07", "throughput": 1484.06, "total_tokens": 30787232} {"current_steps": 145890, "total_steps": 181800, "loss": 0.0042, "lr": 5.711064816758297e-06, "epoch": 16.04950495049505, "percentage": 80.25, "elapsed_time": "5:45:45", "remaining_time": "1:25:06", "throughput": 1484.06, "total_tokens": 30788256} {"current_steps": 145895, "total_steps": 181800, "loss": 0.0099, "lr": 5.709538079276877e-06, "epoch": 16.05005500550055, "percentage": 80.25, "elapsed_time": "5:45:46", "remaining_time": "1:25:05", "throughput": 1484.06, "total_tokens": 30789248} {"current_steps": 145900, "total_steps": 181800, "loss": 0.0766, "lr": 5.708011519586379e-06, "epoch": 16.05060506050605, "percentage": 80.25, "elapsed_time": "5:45:47", "remaining_time": "1:25:05", "throughput": 1484.06, "total_tokens": 30790336} {"current_steps": 145905, "total_steps": 181800, "loss": 0.0707, "lr": 5.70648513770089e-06, "epoch": 16.051155115511552, "percentage": 80.26, "elapsed_time": "5:45:47", "remaining_time": "1:25:04", "throughput": 1484.07, "total_tokens": 30791392} {"current_steps": 145910, "total_steps": 181800, "loss": 0.0056, "lr": 5.704958933634464e-06, "epoch": 16.051705170517053, "percentage": 80.26, "elapsed_time": "5:45:48", "remaining_time": "1:25:03", "throughput": 1484.07, "total_tokens": 30792416} {"current_steps": 145915, "total_steps": 181800, "loss": 0.0014, "lr": 5.703432907401171e-06, "epoch": 16.05225522552255, "percentage": 80.26, "elapsed_time": "5:45:49", "remaining_time": "1:25:02", "throughput": 1484.07, "total_tokens": 30793440} {"current_steps": 145920, "total_steps": 181800, "loss": 0.0223, "lr": 5.7019070590150855e-06, "epoch": 16.05280528052805, "percentage": 80.26, "elapsed_time": "5:45:50", "remaining_time": "1:25:02", "throughput": 1484.07, "total_tokens": 30794560} {"current_steps": 145925, "total_steps": 181800, "loss": 0.003, "lr": 5.700381388490253e-06, "epoch": 16.053355335533553, "percentage": 80.27, "elapsed_time": "5:45:50", "remaining_time": "1:25:01", "throughput": 1484.07, "total_tokens": 30795616} {"current_steps": 145930, "total_steps": 181800, "loss": 0.0019, "lr": 5.698855895840754e-06, "epoch": 16.053905390539054, "percentage": 80.27, "elapsed_time": "5:45:51", "remaining_time": "1:25:00", "throughput": 1484.08, "total_tokens": 30796736} {"current_steps": 145935, "total_steps": 181800, "loss": 0.0317, "lr": 5.697330581080637e-06, "epoch": 16.054455445544555, "percentage": 80.27, "elapsed_time": "5:45:52", "remaining_time": "1:25:00", "throughput": 1484.07, "total_tokens": 30797696} {"current_steps": 145940, "total_steps": 181800, "loss": 0.001, "lr": 5.695805444223956e-06, "epoch": 16.055005500550056, "percentage": 80.28, "elapsed_time": "5:45:52", "remaining_time": "1:24:59", "throughput": 1484.07, "total_tokens": 30798752} {"current_steps": 145945, "total_steps": 181800, "loss": 0.0028, "lr": 5.6942804852847726e-06, "epoch": 16.055555555555557, "percentage": 80.28, "elapsed_time": "5:45:53", "remaining_time": "1:24:58", "throughput": 1484.07, "total_tokens": 30799776} {"current_steps": 145950, "total_steps": 181800, "loss": 0.0058, "lr": 5.692755704277148e-06, "epoch": 16.056105610561055, "percentage": 80.28, "elapsed_time": "5:45:54", "remaining_time": "1:24:57", "throughput": 1484.07, "total_tokens": 30800800} {"current_steps": 145955, "total_steps": 181800, "loss": 0.0049, "lr": 5.691231101215125e-06, "epoch": 16.056655665566556, "percentage": 80.28, "elapsed_time": "5:45:54", "remaining_time": "1:24:57", "throughput": 1484.08, "total_tokens": 30801888} {"current_steps": 145960, "total_steps": 181800, "loss": 0.1073, "lr": 5.689706676112766e-06, "epoch": 16.057205720572057, "percentage": 80.29, "elapsed_time": "5:45:55", "remaining_time": "1:24:56", "throughput": 1484.08, "total_tokens": 30802944} {"current_steps": 145965, "total_steps": 181800, "loss": 0.0234, "lr": 5.688182428984107e-06, "epoch": 16.057755775577558, "percentage": 80.29, "elapsed_time": "5:45:56", "remaining_time": "1:24:55", "throughput": 1484.08, "total_tokens": 30803968} {"current_steps": 145970, "total_steps": 181800, "loss": 0.0037, "lr": 5.686658359843203e-06, "epoch": 16.05830583058306, "percentage": 80.29, "elapsed_time": "5:45:56", "remaining_time": "1:24:55", "throughput": 1484.08, "total_tokens": 30805024} {"current_steps": 145975, "total_steps": 181800, "loss": 0.0029, "lr": 5.685134468704109e-06, "epoch": 16.05885588558856, "percentage": 80.29, "elapsed_time": "5:45:57", "remaining_time": "1:24:54", "throughput": 1484.08, "total_tokens": 30806112} {"current_steps": 145980, "total_steps": 181800, "loss": 0.0829, "lr": 5.6836107555808565e-06, "epoch": 16.059405940594058, "percentage": 80.3, "elapsed_time": "5:45:58", "remaining_time": "1:24:53", "throughput": 1484.08, "total_tokens": 30807168} {"current_steps": 145985, "total_steps": 181800, "loss": 0.0006, "lr": 5.6820872204875005e-06, "epoch": 16.05995599559956, "percentage": 80.3, "elapsed_time": "5:45:59", "remaining_time": "1:24:52", "throughput": 1484.09, "total_tokens": 30808224} {"current_steps": 145990, "total_steps": 181800, "loss": 0.0112, "lr": 5.680563863438071e-06, "epoch": 16.06050605060506, "percentage": 80.3, "elapsed_time": "5:45:59", "remaining_time": "1:24:52", "throughput": 1484.09, "total_tokens": 30809312} {"current_steps": 145995, "total_steps": 181800, "loss": 0.0094, "lr": 5.679040684446621e-06, "epoch": 16.06105610561056, "percentage": 80.31, "elapsed_time": "5:46:00", "remaining_time": "1:24:51", "throughput": 1484.09, "total_tokens": 30810368} {"current_steps": 146000, "total_steps": 181800, "loss": 0.0133, "lr": 5.677517683527172e-06, "epoch": 16.061606160616062, "percentage": 80.31, "elapsed_time": "5:46:01", "remaining_time": "1:24:50", "throughput": 1484.09, "total_tokens": 30811392} {"current_steps": 146005, "total_steps": 181800, "loss": 0.0017, "lr": 5.675994860693773e-06, "epoch": 16.062156215621563, "percentage": 80.31, "elapsed_time": "5:46:01", "remaining_time": "1:24:50", "throughput": 1484.09, "total_tokens": 30812448} {"current_steps": 146010, "total_steps": 181800, "loss": 0.0034, "lr": 5.6744722159604635e-06, "epoch": 16.062706270627064, "percentage": 80.31, "elapsed_time": "5:46:02", "remaining_time": "1:24:49", "throughput": 1484.09, "total_tokens": 30813472} {"current_steps": 146015, "total_steps": 181800, "loss": 0.0067, "lr": 5.672949749341264e-06, "epoch": 16.063256325632562, "percentage": 80.32, "elapsed_time": "5:46:03", "remaining_time": "1:24:48", "throughput": 1484.09, "total_tokens": 30814464} {"current_steps": 146020, "total_steps": 181800, "loss": 0.0038, "lr": 5.671427460850221e-06, "epoch": 16.063806380638063, "percentage": 80.32, "elapsed_time": "5:46:03", "remaining_time": "1:24:47", "throughput": 1484.09, "total_tokens": 30815488} {"current_steps": 146025, "total_steps": 181800, "loss": 0.0251, "lr": 5.669905350501348e-06, "epoch": 16.064356435643564, "percentage": 80.32, "elapsed_time": "5:46:04", "remaining_time": "1:24:47", "throughput": 1484.1, "total_tokens": 30816608} {"current_steps": 146030, "total_steps": 181800, "loss": 0.0044, "lr": 5.668383418308681e-06, "epoch": 16.064906490649065, "percentage": 80.32, "elapsed_time": "5:46:05", "remaining_time": "1:24:46", "throughput": 1484.1, "total_tokens": 30817664} {"current_steps": 146035, "total_steps": 181800, "loss": 0.028, "lr": 5.6668616642862545e-06, "epoch": 16.065456545654566, "percentage": 80.33, "elapsed_time": "5:46:05", "remaining_time": "1:24:45", "throughput": 1484.1, "total_tokens": 30818720} {"current_steps": 146040, "total_steps": 181800, "loss": 0.0008, "lr": 5.665340088448082e-06, "epoch": 16.066006600660067, "percentage": 80.33, "elapsed_time": "5:46:06", "remaining_time": "1:24:45", "throughput": 1484.1, "total_tokens": 30819840} {"current_steps": 146045, "total_steps": 181800, "loss": 0.0085, "lr": 5.663818690808198e-06, "epoch": 16.066556655665565, "percentage": 80.33, "elapsed_time": "5:46:07", "remaining_time": "1:24:44", "throughput": 1484.11, "total_tokens": 30820928} {"current_steps": 146050, "total_steps": 181800, "loss": 0.1317, "lr": 5.6622974713806174e-06, "epoch": 16.067106710671066, "percentage": 80.34, "elapsed_time": "5:46:08", "remaining_time": "1:24:43", "throughput": 1484.11, "total_tokens": 30822016} {"current_steps": 146055, "total_steps": 181800, "loss": 0.0024, "lr": 5.660776430179357e-06, "epoch": 16.067656765676567, "percentage": 80.34, "elapsed_time": "5:46:08", "remaining_time": "1:24:42", "throughput": 1484.11, "total_tokens": 30823072} {"current_steps": 146060, "total_steps": 181800, "loss": 0.0431, "lr": 5.659255567218441e-06, "epoch": 16.068206820682068, "percentage": 80.34, "elapsed_time": "5:46:09", "remaining_time": "1:24:42", "throughput": 1484.11, "total_tokens": 30824128} {"current_steps": 146065, "total_steps": 181800, "loss": 0.0895, "lr": 5.657734882511883e-06, "epoch": 16.06875687568757, "percentage": 80.34, "elapsed_time": "5:46:10", "remaining_time": "1:24:41", "throughput": 1484.11, "total_tokens": 30825152} {"current_steps": 146070, "total_steps": 181800, "loss": 0.0006, "lr": 5.6562143760737094e-06, "epoch": 16.06930693069307, "percentage": 80.35, "elapsed_time": "5:46:10", "remaining_time": "1:24:40", "throughput": 1484.12, "total_tokens": 30826272} {"current_steps": 146075, "total_steps": 181800, "loss": 0.001, "lr": 5.6546940479179274e-06, "epoch": 16.06985698569857, "percentage": 80.35, "elapsed_time": "5:46:11", "remaining_time": "1:24:39", "throughput": 1484.12, "total_tokens": 30827392} {"current_steps": 146080, "total_steps": 181800, "loss": 0.0092, "lr": 5.653173898058539e-06, "epoch": 16.07040704070407, "percentage": 80.35, "elapsed_time": "5:46:12", "remaining_time": "1:24:39", "throughput": 1484.12, "total_tokens": 30828416} {"current_steps": 146085, "total_steps": 181800, "loss": 0.0027, "lr": 5.651653926509564e-06, "epoch": 16.07095709570957, "percentage": 80.35, "elapsed_time": "5:46:12", "remaining_time": "1:24:38", "throughput": 1484.12, "total_tokens": 30829504} {"current_steps": 146090, "total_steps": 181800, "loss": 0.0016, "lr": 5.6501341332850126e-06, "epoch": 16.07150715071507, "percentage": 80.36, "elapsed_time": "5:46:13", "remaining_time": "1:24:37", "throughput": 1484.13, "total_tokens": 30830592} {"current_steps": 146095, "total_steps": 181800, "loss": 0.0033, "lr": 5.648614518398892e-06, "epoch": 16.072057205720572, "percentage": 80.36, "elapsed_time": "5:46:14", "remaining_time": "1:24:37", "throughput": 1484.13, "total_tokens": 30831648} {"current_steps": 146100, "total_steps": 181800, "loss": 0.0606, "lr": 5.6470950818652085e-06, "epoch": 16.072607260726073, "percentage": 80.36, "elapsed_time": "5:46:14", "remaining_time": "1:24:36", "throughput": 1484.13, "total_tokens": 30832640} {"current_steps": 146105, "total_steps": 181800, "loss": 0.0021, "lr": 5.6455758236979575e-06, "epoch": 16.073157315731574, "percentage": 80.37, "elapsed_time": "5:46:15", "remaining_time": "1:24:35", "throughput": 1484.13, "total_tokens": 30833696} {"current_steps": 146110, "total_steps": 181800, "loss": 0.0041, "lr": 5.644056743911153e-06, "epoch": 16.073707370737075, "percentage": 80.37, "elapsed_time": "5:46:16", "remaining_time": "1:24:34", "throughput": 1484.13, "total_tokens": 30834720} {"current_steps": 146115, "total_steps": 181800, "loss": 0.002, "lr": 5.64253784251878e-06, "epoch": 16.074257425742573, "percentage": 80.37, "elapsed_time": "5:46:16", "remaining_time": "1:24:34", "throughput": 1484.13, "total_tokens": 30835744} {"current_steps": 146120, "total_steps": 181800, "loss": 0.0025, "lr": 5.641019119534849e-06, "epoch": 16.074807480748074, "percentage": 80.37, "elapsed_time": "5:46:17", "remaining_time": "1:24:33", "throughput": 1484.13, "total_tokens": 30836800} {"current_steps": 146125, "total_steps": 181800, "loss": 0.0027, "lr": 5.639500574973363e-06, "epoch": 16.075357535753575, "percentage": 80.38, "elapsed_time": "5:46:18", "remaining_time": "1:24:32", "throughput": 1484.14, "total_tokens": 30837952} {"current_steps": 146130, "total_steps": 181800, "loss": 0.095, "lr": 5.6379822088483025e-06, "epoch": 16.075907590759076, "percentage": 80.38, "elapsed_time": "5:46:19", "remaining_time": "1:24:32", "throughput": 1484.14, "total_tokens": 30838976} {"current_steps": 146135, "total_steps": 181800, "loss": 0.0377, "lr": 5.6364640211736765e-06, "epoch": 16.076457645764577, "percentage": 80.38, "elapsed_time": "5:46:19", "remaining_time": "1:24:31", "throughput": 1484.14, "total_tokens": 30840000} {"current_steps": 146140, "total_steps": 181800, "loss": 0.0051, "lr": 5.634946011963471e-06, "epoch": 16.07700770077008, "percentage": 80.39, "elapsed_time": "5:46:20", "remaining_time": "1:24:30", "throughput": 1484.14, "total_tokens": 30841088} {"current_steps": 146145, "total_steps": 181800, "loss": 0.0368, "lr": 5.633428181231662e-06, "epoch": 16.077557755775576, "percentage": 80.39, "elapsed_time": "5:46:21", "remaining_time": "1:24:29", "throughput": 1484.14, "total_tokens": 30842176} {"current_steps": 146150, "total_steps": 181800, "loss": 0.0031, "lr": 5.6319105289922655e-06, "epoch": 16.078107810781077, "percentage": 80.39, "elapsed_time": "5:46:21", "remaining_time": "1:24:29", "throughput": 1484.15, "total_tokens": 30843296} {"current_steps": 146155, "total_steps": 181800, "loss": 0.0011, "lr": 5.630393055259247e-06, "epoch": 16.078657865786578, "percentage": 80.39, "elapsed_time": "5:46:22", "remaining_time": "1:24:28", "throughput": 1484.15, "total_tokens": 30844352} {"current_steps": 146160, "total_steps": 181800, "loss": 0.0038, "lr": 5.6288757600466094e-06, "epoch": 16.07920792079208, "percentage": 80.4, "elapsed_time": "5:46:23", "remaining_time": "1:24:27", "throughput": 1484.15, "total_tokens": 30845344} {"current_steps": 146165, "total_steps": 181800, "loss": 0.0008, "lr": 5.62735864336833e-06, "epoch": 16.07975797579758, "percentage": 80.4, "elapsed_time": "5:46:23", "remaining_time": "1:24:27", "throughput": 1484.15, "total_tokens": 30846336} {"current_steps": 146170, "total_steps": 181800, "loss": 0.0005, "lr": 5.6258417052383826e-06, "epoch": 16.08030803080308, "percentage": 80.4, "elapsed_time": "5:46:24", "remaining_time": "1:24:26", "throughput": 1484.15, "total_tokens": 30847328} {"current_steps": 146175, "total_steps": 181800, "loss": 0.1087, "lr": 5.624324945670756e-06, "epoch": 16.080858085808583, "percentage": 80.4, "elapsed_time": "5:46:25", "remaining_time": "1:24:25", "throughput": 1484.15, "total_tokens": 30848384} {"current_steps": 146180, "total_steps": 181800, "loss": 0.0021, "lr": 5.622808364679427e-06, "epoch": 16.08140814081408, "percentage": 80.41, "elapsed_time": "5:46:25", "remaining_time": "1:24:24", "throughput": 1484.15, "total_tokens": 30849504} {"current_steps": 146185, "total_steps": 181800, "loss": 0.0017, "lr": 5.621291962278385e-06, "epoch": 16.08195819581958, "percentage": 80.41, "elapsed_time": "5:46:26", "remaining_time": "1:24:24", "throughput": 1484.15, "total_tokens": 30850560} {"current_steps": 146190, "total_steps": 181800, "loss": 0.0003, "lr": 5.619775738481595e-06, "epoch": 16.082508250825082, "percentage": 80.41, "elapsed_time": "5:46:27", "remaining_time": "1:24:23", "throughput": 1484.15, "total_tokens": 30851616} {"current_steps": 146195, "total_steps": 181800, "loss": 0.0186, "lr": 5.618259693303024e-06, "epoch": 16.083058305830583, "percentage": 80.42, "elapsed_time": "5:46:28", "remaining_time": "1:24:22", "throughput": 1484.15, "total_tokens": 30852640} {"current_steps": 146200, "total_steps": 181800, "loss": 0.0519, "lr": 5.6167438267566625e-06, "epoch": 16.083608360836084, "percentage": 80.42, "elapsed_time": "5:46:28", "remaining_time": "1:24:22", "throughput": 1484.16, "total_tokens": 30853696} {"current_steps": 146205, "total_steps": 181800, "loss": 0.0422, "lr": 5.615228138856457e-06, "epoch": 16.084158415841586, "percentage": 80.42, "elapsed_time": "5:46:29", "remaining_time": "1:24:21", "throughput": 1484.15, "total_tokens": 30854688} {"current_steps": 146210, "total_steps": 181800, "loss": 0.0102, "lr": 5.613712629616408e-06, "epoch": 16.084708470847083, "percentage": 80.42, "elapsed_time": "5:46:30", "remaining_time": "1:24:20", "throughput": 1484.16, "total_tokens": 30855744} {"current_steps": 146215, "total_steps": 181800, "loss": 0.0017, "lr": 5.612197299050464e-06, "epoch": 16.085258525852584, "percentage": 80.43, "elapsed_time": "5:46:30", "remaining_time": "1:24:19", "throughput": 1484.15, "total_tokens": 30856736} {"current_steps": 146220, "total_steps": 181800, "loss": 0.0678, "lr": 5.610682147172588e-06, "epoch": 16.085808580858085, "percentage": 80.43, "elapsed_time": "5:46:31", "remaining_time": "1:24:19", "throughput": 1484.16, "total_tokens": 30857856} {"current_steps": 146225, "total_steps": 181800, "loss": 0.0313, "lr": 5.60916717399676e-06, "epoch": 16.086358635863586, "percentage": 80.43, "elapsed_time": "5:46:32", "remaining_time": "1:24:18", "throughput": 1484.16, "total_tokens": 30858976} {"current_steps": 146230, "total_steps": 181800, "loss": 0.0009, "lr": 5.607652379536924e-06, "epoch": 16.086908690869087, "percentage": 80.43, "elapsed_time": "5:46:32", "remaining_time": "1:24:17", "throughput": 1484.17, "total_tokens": 30860032} {"current_steps": 146235, "total_steps": 181800, "loss": 0.1143, "lr": 5.606137763807051e-06, "epoch": 16.08745874587459, "percentage": 80.44, "elapsed_time": "5:46:33", "remaining_time": "1:24:17", "throughput": 1484.17, "total_tokens": 30861088} {"current_steps": 146240, "total_steps": 181800, "loss": 0.1719, "lr": 5.604623326821109e-06, "epoch": 16.08800880088009, "percentage": 80.44, "elapsed_time": "5:46:34", "remaining_time": "1:24:16", "throughput": 1484.17, "total_tokens": 30862144} {"current_steps": 146245, "total_steps": 181800, "loss": 0.0015, "lr": 5.6031090685930375e-06, "epoch": 16.088558855885587, "percentage": 80.44, "elapsed_time": "5:46:34", "remaining_time": "1:24:15", "throughput": 1484.17, "total_tokens": 30863200} {"current_steps": 146250, "total_steps": 181800, "loss": 0.0023, "lr": 5.601594989136813e-06, "epoch": 16.08910891089109, "percentage": 80.45, "elapsed_time": "5:46:35", "remaining_time": "1:24:14", "throughput": 1484.17, "total_tokens": 30864288} {"current_steps": 146255, "total_steps": 181800, "loss": 0.0641, "lr": 5.600081088466369e-06, "epoch": 16.08965896589659, "percentage": 80.45, "elapsed_time": "5:46:36", "remaining_time": "1:24:14", "throughput": 1484.18, "total_tokens": 30865440} {"current_steps": 146260, "total_steps": 181800, "loss": 0.0045, "lr": 5.598567366595675e-06, "epoch": 16.09020902090209, "percentage": 80.45, "elapsed_time": "5:46:36", "remaining_time": "1:24:13", "throughput": 1484.18, "total_tokens": 30866528} {"current_steps": 146265, "total_steps": 181800, "loss": 0.0059, "lr": 5.597053823538672e-06, "epoch": 16.09075907590759, "percentage": 80.45, "elapsed_time": "5:46:37", "remaining_time": "1:24:12", "throughput": 1484.18, "total_tokens": 30867488} {"current_steps": 146270, "total_steps": 181800, "loss": 0.0978, "lr": 5.595540459309312e-06, "epoch": 16.091309130913093, "percentage": 80.46, "elapsed_time": "5:46:38", "remaining_time": "1:24:12", "throughput": 1484.19, "total_tokens": 30868608} {"current_steps": 146275, "total_steps": 181800, "loss": 0.0005, "lr": 5.594027273921551e-06, "epoch": 16.09185918591859, "percentage": 80.46, "elapsed_time": "5:46:39", "remaining_time": "1:24:11", "throughput": 1484.18, "total_tokens": 30869600} {"current_steps": 146280, "total_steps": 181800, "loss": 0.0048, "lr": 5.5925142673893205e-06, "epoch": 16.09240924092409, "percentage": 80.46, "elapsed_time": "5:46:39", "remaining_time": "1:24:10", "throughput": 1484.18, "total_tokens": 30870624} {"current_steps": 146285, "total_steps": 181800, "loss": 0.0357, "lr": 5.591001439726582e-06, "epoch": 16.092959295929592, "percentage": 80.46, "elapsed_time": "5:46:40", "remaining_time": "1:24:09", "throughput": 1484.19, "total_tokens": 30871776} {"current_steps": 146290, "total_steps": 181800, "loss": 0.0019, "lr": 5.589488790947265e-06, "epoch": 16.093509350935093, "percentage": 80.47, "elapsed_time": "5:46:41", "remaining_time": "1:24:09", "throughput": 1484.19, "total_tokens": 30872864} {"current_steps": 146295, "total_steps": 181800, "loss": 0.0293, "lr": 5.587976321065311e-06, "epoch": 16.094059405940595, "percentage": 80.47, "elapsed_time": "5:46:41", "remaining_time": "1:24:08", "throughput": 1484.19, "total_tokens": 30873888} {"current_steps": 146300, "total_steps": 181800, "loss": 0.0025, "lr": 5.586464030094674e-06, "epoch": 16.094609460946096, "percentage": 80.47, "elapsed_time": "5:46:42", "remaining_time": "1:24:07", "throughput": 1484.19, "total_tokens": 30874880} {"current_steps": 146305, "total_steps": 181800, "loss": 0.0022, "lr": 5.584951918049275e-06, "epoch": 16.095159515951597, "percentage": 80.48, "elapsed_time": "5:46:43", "remaining_time": "1:24:07", "throughput": 1484.19, "total_tokens": 30875904} {"current_steps": 146310, "total_steps": 181800, "loss": 0.0927, "lr": 5.5834399849430644e-06, "epoch": 16.095709570957094, "percentage": 80.48, "elapsed_time": "5:46:43", "remaining_time": "1:24:06", "throughput": 1484.19, "total_tokens": 30876960} {"current_steps": 146315, "total_steps": 181800, "loss": 0.0021, "lr": 5.581928230789973e-06, "epoch": 16.096259625962595, "percentage": 80.48, "elapsed_time": "5:46:44", "remaining_time": "1:24:05", "throughput": 1484.19, "total_tokens": 30878016} {"current_steps": 146320, "total_steps": 181800, "loss": 0.0287, "lr": 5.580416655603915e-06, "epoch": 16.096809680968097, "percentage": 80.48, "elapsed_time": "5:46:45", "remaining_time": "1:24:04", "throughput": 1484.2, "total_tokens": 30879072} {"current_steps": 146325, "total_steps": 181800, "loss": 0.0055, "lr": 5.578905259398853e-06, "epoch": 16.097359735973598, "percentage": 80.49, "elapsed_time": "5:46:45", "remaining_time": "1:24:04", "throughput": 1484.2, "total_tokens": 30880128} {"current_steps": 146330, "total_steps": 181800, "loss": 0.0737, "lr": 5.577394042188702e-06, "epoch": 16.0979097909791, "percentage": 80.49, "elapsed_time": "5:46:46", "remaining_time": "1:24:03", "throughput": 1484.2, "total_tokens": 30881216} {"current_steps": 146335, "total_steps": 181800, "loss": 0.0587, "lr": 5.5758830039873835e-06, "epoch": 16.0984598459846, "percentage": 80.49, "elapsed_time": "5:46:47", "remaining_time": "1:24:02", "throughput": 1484.2, "total_tokens": 30882272} {"current_steps": 146340, "total_steps": 181800, "loss": 0.0016, "lr": 5.574372144808837e-06, "epoch": 16.099009900990097, "percentage": 80.5, "elapsed_time": "5:46:48", "remaining_time": "1:24:02", "throughput": 1484.2, "total_tokens": 30883296} {"current_steps": 146345, "total_steps": 181800, "loss": 0.0033, "lr": 5.572861464666976e-06, "epoch": 16.0995599559956, "percentage": 80.5, "elapsed_time": "5:46:48", "remaining_time": "1:24:01", "throughput": 1484.21, "total_tokens": 30884384} {"current_steps": 146350, "total_steps": 181800, "loss": 0.0164, "lr": 5.571350963575728e-06, "epoch": 16.1001100110011, "percentage": 80.5, "elapsed_time": "5:46:49", "remaining_time": "1:24:00", "throughput": 1484.21, "total_tokens": 30885472} {"current_steps": 146355, "total_steps": 181800, "loss": 0.0025, "lr": 5.5698406415490205e-06, "epoch": 16.1006600660066, "percentage": 80.5, "elapsed_time": "5:46:50", "remaining_time": "1:23:59", "throughput": 1484.21, "total_tokens": 30886432} {"current_steps": 146360, "total_steps": 181800, "loss": 0.02, "lr": 5.568330498600763e-06, "epoch": 16.1012101210121, "percentage": 80.51, "elapsed_time": "5:46:50", "remaining_time": "1:23:59", "throughput": 1484.21, "total_tokens": 30887456} {"current_steps": 146365, "total_steps": 181800, "loss": 0.0584, "lr": 5.5668205347448875e-06, "epoch": 16.101760176017603, "percentage": 80.51, "elapsed_time": "5:46:51", "remaining_time": "1:23:58", "throughput": 1484.21, "total_tokens": 30888512} {"current_steps": 146370, "total_steps": 181800, "loss": 0.0276, "lr": 5.565310749995292e-06, "epoch": 16.102310231023104, "percentage": 80.51, "elapsed_time": "5:46:52", "remaining_time": "1:23:57", "throughput": 1484.21, "total_tokens": 30889600} {"current_steps": 146375, "total_steps": 181800, "loss": 0.0015, "lr": 5.56380114436591e-06, "epoch": 16.1028602860286, "percentage": 80.51, "elapsed_time": "5:46:52", "remaining_time": "1:23:57", "throughput": 1484.21, "total_tokens": 30890656} {"current_steps": 146380, "total_steps": 181800, "loss": 0.0648, "lr": 5.562291717870641e-06, "epoch": 16.103410341034103, "percentage": 80.52, "elapsed_time": "5:46:53", "remaining_time": "1:23:56", "throughput": 1484.21, "total_tokens": 30891680} {"current_steps": 146385, "total_steps": 181800, "loss": 0.0016, "lr": 5.5607824705234015e-06, "epoch": 16.103960396039604, "percentage": 80.52, "elapsed_time": "5:46:54", "remaining_time": "1:23:55", "throughput": 1484.21, "total_tokens": 30892736} {"current_steps": 146390, "total_steps": 181800, "loss": 0.0229, "lr": 5.559273402338109e-06, "epoch": 16.104510451045105, "percentage": 80.52, "elapsed_time": "5:46:54", "remaining_time": "1:23:54", "throughput": 1484.21, "total_tokens": 30893760} {"current_steps": 146395, "total_steps": 181800, "loss": 0.1063, "lr": 5.557764513328656e-06, "epoch": 16.105060506050606, "percentage": 80.53, "elapsed_time": "5:46:55", "remaining_time": "1:23:54", "throughput": 1484.21, "total_tokens": 30894752} {"current_steps": 146400, "total_steps": 181800, "loss": 0.002, "lr": 5.556255803508967e-06, "epoch": 16.105610561056107, "percentage": 80.53, "elapsed_time": "5:46:56", "remaining_time": "1:23:53", "throughput": 1484.21, "total_tokens": 30895840} {"current_steps": 146405, "total_steps": 181800, "loss": 0.0007, "lr": 5.554747272892929e-06, "epoch": 16.106160616061604, "percentage": 80.53, "elapsed_time": "5:46:56", "remaining_time": "1:23:52", "throughput": 1484.22, "total_tokens": 30896896} {"current_steps": 146410, "total_steps": 181800, "loss": 0.0516, "lr": 5.553238921494458e-06, "epoch": 16.106710671067106, "percentage": 80.53, "elapsed_time": "5:46:57", "remaining_time": "1:23:52", "throughput": 1484.22, "total_tokens": 30897920} {"current_steps": 146415, "total_steps": 181800, "loss": 0.0017, "lr": 5.551730749327458e-06, "epoch": 16.107260726072607, "percentage": 80.54, "elapsed_time": "5:46:58", "remaining_time": "1:23:51", "throughput": 1484.22, "total_tokens": 30898944} {"current_steps": 146420, "total_steps": 181800, "loss": 0.0076, "lr": 5.550222756405815e-06, "epoch": 16.107810781078108, "percentage": 80.54, "elapsed_time": "5:46:59", "remaining_time": "1:23:50", "throughput": 1484.22, "total_tokens": 30900032} {"current_steps": 146425, "total_steps": 181800, "loss": 0.059, "lr": 5.5487149427434435e-06, "epoch": 16.10836083608361, "percentage": 80.54, "elapsed_time": "5:46:59", "remaining_time": "1:23:49", "throughput": 1484.22, "total_tokens": 30901056} {"current_steps": 146430, "total_steps": 181800, "loss": 0.0435, "lr": 5.547207308354235e-06, "epoch": 16.10891089108911, "percentage": 80.54, "elapsed_time": "5:47:00", "remaining_time": "1:23:49", "throughput": 1484.22, "total_tokens": 30902144} {"current_steps": 146435, "total_steps": 181800, "loss": 0.1324, "lr": 5.545699853252073e-06, "epoch": 16.10946094609461, "percentage": 80.55, "elapsed_time": "5:47:01", "remaining_time": "1:23:48", "throughput": 1484.22, "total_tokens": 30903200} {"current_steps": 146440, "total_steps": 181800, "loss": 0.004, "lr": 5.54419257745086e-06, "epoch": 16.11001100110011, "percentage": 80.55, "elapsed_time": "5:47:01", "remaining_time": "1:23:47", "throughput": 1484.23, "total_tokens": 30904288} {"current_steps": 146445, "total_steps": 181800, "loss": 0.0056, "lr": 5.54268548096449e-06, "epoch": 16.11056105610561, "percentage": 80.55, "elapsed_time": "5:47:02", "remaining_time": "1:23:47", "throughput": 1484.23, "total_tokens": 30905312} {"current_steps": 146450, "total_steps": 181800, "loss": 0.0022, "lr": 5.541178563806859e-06, "epoch": 16.11111111111111, "percentage": 80.56, "elapsed_time": "5:47:03", "remaining_time": "1:23:46", "throughput": 1484.23, "total_tokens": 30906368} {"current_steps": 146455, "total_steps": 181800, "loss": 0.0048, "lr": 5.539671825991846e-06, "epoch": 16.111661166116612, "percentage": 80.56, "elapsed_time": "5:47:03", "remaining_time": "1:23:45", "throughput": 1484.23, "total_tokens": 30907424} {"current_steps": 146460, "total_steps": 181800, "loss": 0.0176, "lr": 5.538165267533335e-06, "epoch": 16.112211221122113, "percentage": 80.56, "elapsed_time": "5:47:04", "remaining_time": "1:23:44", "throughput": 1484.23, "total_tokens": 30908416} {"current_steps": 146465, "total_steps": 181800, "loss": 0.1612, "lr": 5.536658888445215e-06, "epoch": 16.112761276127614, "percentage": 80.56, "elapsed_time": "5:47:05", "remaining_time": "1:23:44", "throughput": 1484.23, "total_tokens": 30909472} {"current_steps": 146470, "total_steps": 181800, "loss": 0.0026, "lr": 5.535152688741368e-06, "epoch": 16.11331133113311, "percentage": 80.57, "elapsed_time": "5:47:05", "remaining_time": "1:23:43", "throughput": 1484.23, "total_tokens": 30910528} {"current_steps": 146475, "total_steps": 181800, "loss": 0.0728, "lr": 5.533646668435688e-06, "epoch": 16.113861386138613, "percentage": 80.57, "elapsed_time": "5:47:06", "remaining_time": "1:23:42", "throughput": 1484.23, "total_tokens": 30911584} {"current_steps": 146480, "total_steps": 181800, "loss": 0.0972, "lr": 5.532140827542046e-06, "epoch": 16.114411441144114, "percentage": 80.57, "elapsed_time": "5:47:07", "remaining_time": "1:23:41", "throughput": 1484.24, "total_tokens": 30912704} {"current_steps": 146485, "total_steps": 181800, "loss": 0.0669, "lr": 5.5306351660743135e-06, "epoch": 16.114961496149615, "percentage": 80.57, "elapsed_time": "5:47:08", "remaining_time": "1:23:41", "throughput": 1484.24, "total_tokens": 30913728} {"current_steps": 146490, "total_steps": 181800, "loss": 0.0392, "lr": 5.52912968404638e-06, "epoch": 16.115511551155116, "percentage": 80.58, "elapsed_time": "5:47:08", "remaining_time": "1:23:40", "throughput": 1484.24, "total_tokens": 30914816} {"current_steps": 146495, "total_steps": 181800, "loss": 0.0021, "lr": 5.52762438147211e-06, "epoch": 16.116061606160617, "percentage": 80.58, "elapsed_time": "5:47:09", "remaining_time": "1:23:39", "throughput": 1484.24, "total_tokens": 30915904} {"current_steps": 146500, "total_steps": 181800, "loss": 0.0166, "lr": 5.526119258365381e-06, "epoch": 16.116611661166118, "percentage": 80.58, "elapsed_time": "5:47:10", "remaining_time": "1:23:39", "throughput": 1484.25, "total_tokens": 30916960} {"current_steps": 146505, "total_steps": 181800, "loss": 0.003, "lr": 5.5246143147400735e-06, "epoch": 16.117161716171616, "percentage": 80.59, "elapsed_time": "5:47:10", "remaining_time": "1:23:38", "throughput": 1484.25, "total_tokens": 30918080} {"current_steps": 146510, "total_steps": 181800, "loss": 0.0424, "lr": 5.523109550610045e-06, "epoch": 16.117711771177117, "percentage": 80.59, "elapsed_time": "5:47:11", "remaining_time": "1:23:37", "throughput": 1484.25, "total_tokens": 30919136} {"current_steps": 146515, "total_steps": 181800, "loss": 0.0935, "lr": 5.521604965989174e-06, "epoch": 16.118261826182618, "percentage": 80.59, "elapsed_time": "5:47:12", "remaining_time": "1:23:36", "throughput": 1484.25, "total_tokens": 30920192} {"current_steps": 146520, "total_steps": 181800, "loss": 0.0147, "lr": 5.520100560891317e-06, "epoch": 16.11881188118812, "percentage": 80.59, "elapsed_time": "5:47:12", "remaining_time": "1:23:36", "throughput": 1484.25, "total_tokens": 30921184} {"current_steps": 146525, "total_steps": 181800, "loss": 0.1632, "lr": 5.518596335330348e-06, "epoch": 16.11936193619362, "percentage": 80.6, "elapsed_time": "5:47:13", "remaining_time": "1:23:35", "throughput": 1484.26, "total_tokens": 30922304} {"current_steps": 146530, "total_steps": 181800, "loss": 0.0027, "lr": 5.517092289320133e-06, "epoch": 16.11991199119912, "percentage": 80.6, "elapsed_time": "5:47:14", "remaining_time": "1:23:34", "throughput": 1484.26, "total_tokens": 30923424} {"current_steps": 146535, "total_steps": 181800, "loss": 0.0307, "lr": 5.515588422874527e-06, "epoch": 16.120462046204622, "percentage": 80.6, "elapsed_time": "5:47:14", "remaining_time": "1:23:34", "throughput": 1484.26, "total_tokens": 30924416} {"current_steps": 146540, "total_steps": 181800, "loss": 0.0046, "lr": 5.514084736007394e-06, "epoch": 16.12101210121012, "percentage": 80.61, "elapsed_time": "5:47:15", "remaining_time": "1:23:33", "throughput": 1484.26, "total_tokens": 30925440} {"current_steps": 146545, "total_steps": 181800, "loss": 0.0105, "lr": 5.512581228732597e-06, "epoch": 16.12156215621562, "percentage": 80.61, "elapsed_time": "5:47:16", "remaining_time": "1:23:32", "throughput": 1484.26, "total_tokens": 30926496} {"current_steps": 146550, "total_steps": 181800, "loss": 0.0035, "lr": 5.511077901063977e-06, "epoch": 16.122112211221122, "percentage": 80.61, "elapsed_time": "5:47:16", "remaining_time": "1:23:31", "throughput": 1484.26, "total_tokens": 30927552} {"current_steps": 146555, "total_steps": 181800, "loss": 0.0014, "lr": 5.509574753015401e-06, "epoch": 16.122662266226623, "percentage": 80.61, "elapsed_time": "5:47:17", "remaining_time": "1:23:31", "throughput": 1484.26, "total_tokens": 30928608} {"current_steps": 146560, "total_steps": 181800, "loss": 0.0045, "lr": 5.508071784600724e-06, "epoch": 16.123212321232124, "percentage": 80.62, "elapsed_time": "5:47:18", "remaining_time": "1:23:30", "throughput": 1484.27, "total_tokens": 30929696} {"current_steps": 146565, "total_steps": 181800, "loss": 0.0008, "lr": 5.5065689958338025e-06, "epoch": 16.123762376237625, "percentage": 80.62, "elapsed_time": "5:47:19", "remaining_time": "1:23:29", "throughput": 1484.27, "total_tokens": 30930752} {"current_steps": 146570, "total_steps": 181800, "loss": 0.0029, "lr": 5.50506638672848e-06, "epoch": 16.124312431243123, "percentage": 80.62, "elapsed_time": "5:47:19", "remaining_time": "1:23:29", "throughput": 1484.27, "total_tokens": 30931776} {"current_steps": 146575, "total_steps": 181800, "loss": 0.0826, "lr": 5.503563957298599e-06, "epoch": 16.124862486248624, "percentage": 80.62, "elapsed_time": "5:47:20", "remaining_time": "1:23:28", "throughput": 1484.27, "total_tokens": 30932832} {"current_steps": 146580, "total_steps": 181800, "loss": 0.0015, "lr": 5.502061707558012e-06, "epoch": 16.125412541254125, "percentage": 80.63, "elapsed_time": "5:47:21", "remaining_time": "1:23:27", "throughput": 1484.27, "total_tokens": 30933824} {"current_steps": 146585, "total_steps": 181800, "loss": 0.0021, "lr": 5.500559637520569e-06, "epoch": 16.125962596259626, "percentage": 80.63, "elapsed_time": "5:47:21", "remaining_time": "1:23:26", "throughput": 1484.27, "total_tokens": 30934880} {"current_steps": 146590, "total_steps": 181800, "loss": 0.0031, "lr": 5.499057747200117e-06, "epoch": 16.126512651265127, "percentage": 80.63, "elapsed_time": "5:47:22", "remaining_time": "1:23:26", "throughput": 1484.27, "total_tokens": 30935936} {"current_steps": 146595, "total_steps": 181800, "loss": 0.0134, "lr": 5.497556036610493e-06, "epoch": 16.127062706270628, "percentage": 80.64, "elapsed_time": "5:47:23", "remaining_time": "1:23:25", "throughput": 1484.27, "total_tokens": 30936960} {"current_steps": 146600, "total_steps": 181800, "loss": 0.0016, "lr": 5.49605450576553e-06, "epoch": 16.12761276127613, "percentage": 80.64, "elapsed_time": "5:47:23", "remaining_time": "1:23:24", "throughput": 1484.28, "total_tokens": 30938112} {"current_steps": 146605, "total_steps": 181800, "loss": 0.0057, "lr": 5.49455315467908e-06, "epoch": 16.128162816281627, "percentage": 80.64, "elapsed_time": "5:47:24", "remaining_time": "1:23:24", "throughput": 1484.28, "total_tokens": 30939168} {"current_steps": 146610, "total_steps": 181800, "loss": 0.1382, "lr": 5.493051983364966e-06, "epoch": 16.128712871287128, "percentage": 80.64, "elapsed_time": "5:47:25", "remaining_time": "1:23:23", "throughput": 1484.28, "total_tokens": 30940224} {"current_steps": 146615, "total_steps": 181800, "loss": 0.0252, "lr": 5.491550991837033e-06, "epoch": 16.12926292629263, "percentage": 80.65, "elapsed_time": "5:47:25", "remaining_time": "1:23:22", "throughput": 1484.28, "total_tokens": 30941312} {"current_steps": 146620, "total_steps": 181800, "loss": 0.0715, "lr": 5.490050180109121e-06, "epoch": 16.12981298129813, "percentage": 80.65, "elapsed_time": "5:47:26", "remaining_time": "1:23:21", "throughput": 1484.28, "total_tokens": 30942336} {"current_steps": 146625, "total_steps": 181800, "loss": 0.0845, "lr": 5.488549548195046e-06, "epoch": 16.13036303630363, "percentage": 80.65, "elapsed_time": "5:47:27", "remaining_time": "1:23:21", "throughput": 1484.29, "total_tokens": 30943424} {"current_steps": 146630, "total_steps": 181800, "loss": 0.0071, "lr": 5.487049096108654e-06, "epoch": 16.130913091309132, "percentage": 80.65, "elapsed_time": "5:47:28", "remaining_time": "1:23:20", "throughput": 1484.29, "total_tokens": 30944512} {"current_steps": 146635, "total_steps": 181800, "loss": 0.0012, "lr": 5.485548823863762e-06, "epoch": 16.13146314631463, "percentage": 80.66, "elapsed_time": "5:47:28", "remaining_time": "1:23:19", "throughput": 1484.29, "total_tokens": 30945568} {"current_steps": 146640, "total_steps": 181800, "loss": 0.0083, "lr": 5.484048731474203e-06, "epoch": 16.13201320132013, "percentage": 80.66, "elapsed_time": "5:47:29", "remaining_time": "1:23:19", "throughput": 1484.29, "total_tokens": 30946592} {"current_steps": 146645, "total_steps": 181800, "loss": 0.0026, "lr": 5.482548818953806e-06, "epoch": 16.132563256325632, "percentage": 80.66, "elapsed_time": "5:47:30", "remaining_time": "1:23:18", "throughput": 1484.29, "total_tokens": 30947584} {"current_steps": 146650, "total_steps": 181800, "loss": 0.0134, "lr": 5.481049086316386e-06, "epoch": 16.133113311331133, "percentage": 80.67, "elapsed_time": "5:47:30", "remaining_time": "1:23:17", "throughput": 1484.29, "total_tokens": 30948608} {"current_steps": 146655, "total_steps": 181800, "loss": 0.0544, "lr": 5.479549533575778e-06, "epoch": 16.133663366336634, "percentage": 80.67, "elapsed_time": "5:47:31", "remaining_time": "1:23:16", "throughput": 1484.29, "total_tokens": 30949728} {"current_steps": 146660, "total_steps": 181800, "loss": 0.0046, "lr": 5.478050160745788e-06, "epoch": 16.134213421342135, "percentage": 80.67, "elapsed_time": "5:47:32", "remaining_time": "1:23:16", "throughput": 1484.29, "total_tokens": 30950752} {"current_steps": 146665, "total_steps": 181800, "loss": 0.0038, "lr": 5.476550967840249e-06, "epoch": 16.134763476347636, "percentage": 80.67, "elapsed_time": "5:47:32", "remaining_time": "1:23:15", "throughput": 1484.29, "total_tokens": 30951744} {"current_steps": 146670, "total_steps": 181800, "loss": 0.0041, "lr": 5.475051954872964e-06, "epoch": 16.135313531353134, "percentage": 80.68, "elapsed_time": "5:47:33", "remaining_time": "1:23:14", "throughput": 1484.29, "total_tokens": 30952800} {"current_steps": 146675, "total_steps": 181800, "loss": 0.1369, "lr": 5.473553121857758e-06, "epoch": 16.135863586358635, "percentage": 80.68, "elapsed_time": "5:47:34", "remaining_time": "1:23:14", "throughput": 1484.29, "total_tokens": 30953856} {"current_steps": 146680, "total_steps": 181800, "loss": 0.002, "lr": 5.472054468808449e-06, "epoch": 16.136413641364136, "percentage": 80.68, "elapsed_time": "5:47:34", "remaining_time": "1:23:13", "throughput": 1484.3, "total_tokens": 30954912} {"current_steps": 146685, "total_steps": 181800, "loss": 0.0761, "lr": 5.470555995738835e-06, "epoch": 16.136963696369637, "percentage": 80.68, "elapsed_time": "5:47:35", "remaining_time": "1:23:12", "throughput": 1484.3, "total_tokens": 30956000} {"current_steps": 146690, "total_steps": 181800, "loss": 0.0012, "lr": 5.469057702662744e-06, "epoch": 16.13751375137514, "percentage": 80.69, "elapsed_time": "5:47:36", "remaining_time": "1:23:11", "throughput": 1484.3, "total_tokens": 30957088} {"current_steps": 146695, "total_steps": 181800, "loss": 0.0145, "lr": 5.467559589593968e-06, "epoch": 16.13806380638064, "percentage": 80.69, "elapsed_time": "5:47:37", "remaining_time": "1:23:11", "throughput": 1484.31, "total_tokens": 30958176} {"current_steps": 146700, "total_steps": 181800, "loss": 0.0144, "lr": 5.466061656546323e-06, "epoch": 16.138613861386137, "percentage": 80.69, "elapsed_time": "5:47:37", "remaining_time": "1:23:10", "throughput": 1484.31, "total_tokens": 30959200} {"current_steps": 146705, "total_steps": 181800, "loss": 0.0381, "lr": 5.464563903533623e-06, "epoch": 16.139163916391638, "percentage": 80.7, "elapsed_time": "5:47:38", "remaining_time": "1:23:09", "throughput": 1484.31, "total_tokens": 30960256} {"current_steps": 146710, "total_steps": 181800, "loss": 0.1094, "lr": 5.463066330569661e-06, "epoch": 16.13971397139714, "percentage": 80.7, "elapsed_time": "5:47:39", "remaining_time": "1:23:09", "throughput": 1484.31, "total_tokens": 30961248} {"current_steps": 146715, "total_steps": 181800, "loss": 0.1158, "lr": 5.461568937668238e-06, "epoch": 16.14026402640264, "percentage": 80.7, "elapsed_time": "5:47:39", "remaining_time": "1:23:08", "throughput": 1484.31, "total_tokens": 30962336} {"current_steps": 146720, "total_steps": 181800, "loss": 0.003, "lr": 5.460071724843163e-06, "epoch": 16.14081408140814, "percentage": 80.7, "elapsed_time": "5:47:40", "remaining_time": "1:23:07", "throughput": 1484.31, "total_tokens": 30963392} {"current_steps": 146725, "total_steps": 181800, "loss": 0.034, "lr": 5.4585746921082235e-06, "epoch": 16.141364136413642, "percentage": 80.71, "elapsed_time": "5:47:41", "remaining_time": "1:23:06", "throughput": 1484.31, "total_tokens": 30964480} {"current_steps": 146730, "total_steps": 181800, "loss": 0.008, "lr": 5.4570778394772256e-06, "epoch": 16.141914191419144, "percentage": 80.71, "elapsed_time": "5:47:41", "remaining_time": "1:23:06", "throughput": 1484.31, "total_tokens": 30965504} {"current_steps": 146735, "total_steps": 181800, "loss": 0.097, "lr": 5.455581166963971e-06, "epoch": 16.14246424642464, "percentage": 80.71, "elapsed_time": "5:47:42", "remaining_time": "1:23:05", "throughput": 1484.31, "total_tokens": 30966560} {"current_steps": 146740, "total_steps": 181800, "loss": 0.0072, "lr": 5.454084674582238e-06, "epoch": 16.143014301430142, "percentage": 80.72, "elapsed_time": "5:47:43", "remaining_time": "1:23:04", "throughput": 1484.31, "total_tokens": 30967584} {"current_steps": 146745, "total_steps": 181800, "loss": 0.0803, "lr": 5.452588362345837e-06, "epoch": 16.143564356435643, "percentage": 80.72, "elapsed_time": "5:47:43", "remaining_time": "1:23:04", "throughput": 1484.32, "total_tokens": 30968704} {"current_steps": 146750, "total_steps": 181800, "loss": 0.0206, "lr": 5.451092230268539e-06, "epoch": 16.144114411441144, "percentage": 80.72, "elapsed_time": "5:47:44", "remaining_time": "1:23:03", "throughput": 1484.32, "total_tokens": 30969760} {"current_steps": 146755, "total_steps": 181800, "loss": 0.0095, "lr": 5.449596278364147e-06, "epoch": 16.144664466446645, "percentage": 80.72, "elapsed_time": "5:47:45", "remaining_time": "1:23:02", "throughput": 1484.32, "total_tokens": 30970752} {"current_steps": 146760, "total_steps": 181800, "loss": 0.0021, "lr": 5.448100506646447e-06, "epoch": 16.145214521452147, "percentage": 80.73, "elapsed_time": "5:47:45", "remaining_time": "1:23:01", "throughput": 1484.32, "total_tokens": 30971776} {"current_steps": 146765, "total_steps": 181800, "loss": 0.0736, "lr": 5.446604915129219e-06, "epoch": 16.145764576457644, "percentage": 80.73, "elapsed_time": "5:47:46", "remaining_time": "1:23:01", "throughput": 1484.32, "total_tokens": 30972736} {"current_steps": 146770, "total_steps": 181800, "loss": 0.0745, "lr": 5.4451095038262595e-06, "epoch": 16.146314631463145, "percentage": 80.73, "elapsed_time": "5:47:47", "remaining_time": "1:23:00", "throughput": 1484.32, "total_tokens": 30973824} {"current_steps": 146775, "total_steps": 181800, "loss": 0.0056, "lr": 5.443614272751333e-06, "epoch": 16.146864686468646, "percentage": 80.73, "elapsed_time": "5:47:48", "remaining_time": "1:22:59", "throughput": 1484.32, "total_tokens": 30974912} {"current_steps": 146780, "total_steps": 181800, "loss": 0.072, "lr": 5.442119221918238e-06, "epoch": 16.147414741474147, "percentage": 80.74, "elapsed_time": "5:47:48", "remaining_time": "1:22:59", "throughput": 1484.32, "total_tokens": 30975936} {"current_steps": 146785, "total_steps": 181800, "loss": 0.0552, "lr": 5.440624351340737e-06, "epoch": 16.14796479647965, "percentage": 80.74, "elapsed_time": "5:47:49", "remaining_time": "1:22:58", "throughput": 1484.32, "total_tokens": 30976960} {"current_steps": 146790, "total_steps": 181800, "loss": 0.0097, "lr": 5.439129661032616e-06, "epoch": 16.14851485148515, "percentage": 80.74, "elapsed_time": "5:47:50", "remaining_time": "1:22:57", "throughput": 1484.32, "total_tokens": 30977984} {"current_steps": 146795, "total_steps": 181800, "loss": 0.0036, "lr": 5.437635151007658e-06, "epoch": 16.14906490649065, "percentage": 80.75, "elapsed_time": "5:47:50", "remaining_time": "1:22:56", "throughput": 1484.32, "total_tokens": 30979072} {"current_steps": 146800, "total_steps": 181800, "loss": 0.0059, "lr": 5.436140821279623e-06, "epoch": 16.149614961496148, "percentage": 80.75, "elapsed_time": "5:47:51", "remaining_time": "1:22:56", "throughput": 1484.33, "total_tokens": 30980128} {"current_steps": 146805, "total_steps": 181800, "loss": 0.0072, "lr": 5.434646671862298e-06, "epoch": 16.15016501650165, "percentage": 80.75, "elapsed_time": "5:47:52", "remaining_time": "1:22:55", "throughput": 1484.33, "total_tokens": 30981248} {"current_steps": 146810, "total_steps": 181800, "loss": 0.104, "lr": 5.433152702769437e-06, "epoch": 16.15071507150715, "percentage": 80.75, "elapsed_time": "5:47:52", "remaining_time": "1:22:54", "throughput": 1484.33, "total_tokens": 30982304} {"current_steps": 146815, "total_steps": 181800, "loss": 0.0038, "lr": 5.43165891401482e-06, "epoch": 16.15126512651265, "percentage": 80.76, "elapsed_time": "5:47:53", "remaining_time": "1:22:54", "throughput": 1484.33, "total_tokens": 30983392} {"current_steps": 146820, "total_steps": 181800, "loss": 0.0321, "lr": 5.43016530561222e-06, "epoch": 16.151815181518153, "percentage": 80.76, "elapsed_time": "5:47:54", "remaining_time": "1:22:53", "throughput": 1484.34, "total_tokens": 30984480} {"current_steps": 146825, "total_steps": 181800, "loss": 0.0029, "lr": 5.428671877575389e-06, "epoch": 16.152365236523654, "percentage": 80.76, "elapsed_time": "5:47:54", "remaining_time": "1:22:52", "throughput": 1484.34, "total_tokens": 30985504} {"current_steps": 146830, "total_steps": 181800, "loss": 0.002, "lr": 5.427178629918106e-06, "epoch": 16.15291529152915, "percentage": 80.76, "elapsed_time": "5:47:55", "remaining_time": "1:22:51", "throughput": 1484.34, "total_tokens": 30986560} {"current_steps": 146835, "total_steps": 181800, "loss": 0.0068, "lr": 5.425685562654123e-06, "epoch": 16.153465346534652, "percentage": 80.77, "elapsed_time": "5:47:56", "remaining_time": "1:22:51", "throughput": 1484.34, "total_tokens": 30987584} {"current_steps": 146840, "total_steps": 181800, "loss": 0.0407, "lr": 5.424192675797199e-06, "epoch": 16.154015401540153, "percentage": 80.77, "elapsed_time": "5:47:57", "remaining_time": "1:22:50", "throughput": 1484.34, "total_tokens": 30988640} {"current_steps": 146845, "total_steps": 181800, "loss": 0.0035, "lr": 5.422699969361094e-06, "epoch": 16.154565456545654, "percentage": 80.77, "elapsed_time": "5:47:57", "remaining_time": "1:22:49", "throughput": 1484.34, "total_tokens": 30989664} {"current_steps": 146850, "total_steps": 181800, "loss": 0.0653, "lr": 5.421207443359575e-06, "epoch": 16.155115511551156, "percentage": 80.78, "elapsed_time": "5:47:58", "remaining_time": "1:22:49", "throughput": 1484.34, "total_tokens": 30990688} {"current_steps": 146855, "total_steps": 181800, "loss": 0.004, "lr": 5.4197150978063965e-06, "epoch": 16.155665566556657, "percentage": 80.78, "elapsed_time": "5:47:59", "remaining_time": "1:22:48", "throughput": 1484.35, "total_tokens": 30991808} {"current_steps": 146860, "total_steps": 181800, "loss": 0.0096, "lr": 5.418222932715306e-06, "epoch": 16.156215621562158, "percentage": 80.78, "elapsed_time": "5:47:59", "remaining_time": "1:22:47", "throughput": 1484.35, "total_tokens": 30992832} {"current_steps": 146865, "total_steps": 181800, "loss": 0.0124, "lr": 5.416730948100054e-06, "epoch": 16.156765676567655, "percentage": 80.78, "elapsed_time": "5:48:00", "remaining_time": "1:22:46", "throughput": 1484.34, "total_tokens": 30993792} {"current_steps": 146870, "total_steps": 181800, "loss": 0.0017, "lr": 5.415239143974396e-06, "epoch": 16.157315731573156, "percentage": 80.79, "elapsed_time": "5:48:01", "remaining_time": "1:22:46", "throughput": 1484.34, "total_tokens": 30994816} {"current_steps": 146875, "total_steps": 181800, "loss": 0.1078, "lr": 5.41374752035208e-06, "epoch": 16.157865786578657, "percentage": 80.79, "elapsed_time": "5:48:01", "remaining_time": "1:22:45", "throughput": 1484.34, "total_tokens": 30995872} {"current_steps": 146880, "total_steps": 181800, "loss": 0.0015, "lr": 5.412256077246863e-06, "epoch": 16.15841584158416, "percentage": 80.79, "elapsed_time": "5:48:02", "remaining_time": "1:22:44", "throughput": 1484.34, "total_tokens": 30996896} {"current_steps": 146885, "total_steps": 181800, "loss": 0.037, "lr": 5.410764814672481e-06, "epoch": 16.15896589658966, "percentage": 80.79, "elapsed_time": "5:48:03", "remaining_time": "1:22:44", "throughput": 1484.35, "total_tokens": 30997984} {"current_steps": 146890, "total_steps": 181800, "loss": 0.1258, "lr": 5.409273732642675e-06, "epoch": 16.15951595159516, "percentage": 80.8, "elapsed_time": "5:48:03", "remaining_time": "1:22:43", "throughput": 1484.35, "total_tokens": 30999072} {"current_steps": 146895, "total_steps": 181800, "loss": 0.001, "lr": 5.407782831171198e-06, "epoch": 16.16006600660066, "percentage": 80.8, "elapsed_time": "5:48:04", "remaining_time": "1:22:42", "throughput": 1484.35, "total_tokens": 31000160} {"current_steps": 146900, "total_steps": 181800, "loss": 0.0393, "lr": 5.406292110271777e-06, "epoch": 16.16061606160616, "percentage": 80.8, "elapsed_time": "5:48:05", "remaining_time": "1:22:41", "throughput": 1484.36, "total_tokens": 31001216} {"current_steps": 146905, "total_steps": 181800, "loss": 0.0479, "lr": 5.404801569958162e-06, "epoch": 16.16116611661166, "percentage": 80.81, "elapsed_time": "5:48:05", "remaining_time": "1:22:41", "throughput": 1484.36, "total_tokens": 31002240} {"current_steps": 146910, "total_steps": 181800, "loss": 0.0806, "lr": 5.403311210244094e-06, "epoch": 16.16171617161716, "percentage": 80.81, "elapsed_time": "5:48:06", "remaining_time": "1:22:40", "throughput": 1484.36, "total_tokens": 31003296} {"current_steps": 146915, "total_steps": 181800, "loss": 0.0018, "lr": 5.401821031143298e-06, "epoch": 16.162266226622663, "percentage": 80.81, "elapsed_time": "5:48:07", "remaining_time": "1:22:39", "throughput": 1484.36, "total_tokens": 31004448} {"current_steps": 146920, "total_steps": 181800, "loss": 0.0027, "lr": 5.400331032669517e-06, "epoch": 16.162816281628164, "percentage": 80.81, "elapsed_time": "5:48:08", "remaining_time": "1:22:38", "throughput": 1484.36, "total_tokens": 31005440} {"current_steps": 146925, "total_steps": 181800, "loss": 0.0019, "lr": 5.398841214836484e-06, "epoch": 16.163366336633665, "percentage": 80.82, "elapsed_time": "5:48:08", "remaining_time": "1:22:38", "throughput": 1484.36, "total_tokens": 31006496} {"current_steps": 146930, "total_steps": 181800, "loss": 0.0007, "lr": 5.397351577657911e-06, "epoch": 16.163916391639162, "percentage": 80.82, "elapsed_time": "5:48:09", "remaining_time": "1:22:37", "throughput": 1484.36, "total_tokens": 31007520} {"current_steps": 146935, "total_steps": 181800, "loss": 0.0021, "lr": 5.395862121147554e-06, "epoch": 16.164466446644663, "percentage": 80.82, "elapsed_time": "5:48:10", "remaining_time": "1:22:36", "throughput": 1484.37, "total_tokens": 31008576} {"current_steps": 146940, "total_steps": 181800, "loss": 0.0357, "lr": 5.394372845319123e-06, "epoch": 16.165016501650165, "percentage": 80.83, "elapsed_time": "5:48:10", "remaining_time": "1:22:36", "throughput": 1484.37, "total_tokens": 31009664} {"current_steps": 146945, "total_steps": 181800, "loss": 0.0476, "lr": 5.392883750186356e-06, "epoch": 16.165566556655666, "percentage": 80.83, "elapsed_time": "5:48:11", "remaining_time": "1:22:35", "throughput": 1484.37, "total_tokens": 31010720} {"current_steps": 146950, "total_steps": 181800, "loss": 0.0801, "lr": 5.391394835762972e-06, "epoch": 16.166116611661167, "percentage": 80.83, "elapsed_time": "5:48:12", "remaining_time": "1:22:34", "throughput": 1484.37, "total_tokens": 31011776} {"current_steps": 146955, "total_steps": 181800, "loss": 0.0094, "lr": 5.3899061020626865e-06, "epoch": 16.166666666666668, "percentage": 80.83, "elapsed_time": "5:48:12", "remaining_time": "1:22:33", "throughput": 1484.37, "total_tokens": 31012800} {"current_steps": 146960, "total_steps": 181800, "loss": 0.0006, "lr": 5.388417549099226e-06, "epoch": 16.16721672167217, "percentage": 80.84, "elapsed_time": "5:48:13", "remaining_time": "1:22:33", "throughput": 1484.38, "total_tokens": 31013920} {"current_steps": 146965, "total_steps": 181800, "loss": 0.0007, "lr": 5.38692917688631e-06, "epoch": 16.167766776677666, "percentage": 80.84, "elapsed_time": "5:48:14", "remaining_time": "1:22:32", "throughput": 1484.38, "total_tokens": 31014944} {"current_steps": 146970, "total_steps": 181800, "loss": 0.0108, "lr": 5.3854409854376645e-06, "epoch": 16.168316831683168, "percentage": 80.84, "elapsed_time": "5:48:14", "remaining_time": "1:22:31", "throughput": 1484.38, "total_tokens": 31016032} {"current_steps": 146975, "total_steps": 181800, "loss": 0.0057, "lr": 5.3839529747669954e-06, "epoch": 16.16886688668867, "percentage": 80.84, "elapsed_time": "5:48:15", "remaining_time": "1:22:31", "throughput": 1484.38, "total_tokens": 31017120} {"current_steps": 146980, "total_steps": 181800, "loss": 0.125, "lr": 5.382465144888016e-06, "epoch": 16.16941694169417, "percentage": 80.85, "elapsed_time": "5:48:16", "remaining_time": "1:22:30", "throughput": 1484.38, "total_tokens": 31018176} {"current_steps": 146985, "total_steps": 181800, "loss": 0.0183, "lr": 5.380977495814446e-06, "epoch": 16.16996699669967, "percentage": 80.85, "elapsed_time": "5:48:17", "remaining_time": "1:22:29", "throughput": 1484.38, "total_tokens": 31019232} {"current_steps": 146990, "total_steps": 181800, "loss": 0.0016, "lr": 5.379490027559977e-06, "epoch": 16.170517051705172, "percentage": 80.85, "elapsed_time": "5:48:17", "remaining_time": "1:22:28", "throughput": 1484.39, "total_tokens": 31020320} {"current_steps": 146995, "total_steps": 181800, "loss": 0.0277, "lr": 5.3780027401383495e-06, "epoch": 16.17106710671067, "percentage": 80.86, "elapsed_time": "5:48:18", "remaining_time": "1:22:28", "throughput": 1484.39, "total_tokens": 31021408} {"current_steps": 147000, "total_steps": 181800, "loss": 0.0397, "lr": 5.376515633563256e-06, "epoch": 16.17161716171617, "percentage": 80.86, "elapsed_time": "5:48:19", "remaining_time": "1:22:27", "throughput": 1484.39, "total_tokens": 31022432} {"current_steps": 147005, "total_steps": 181800, "loss": 0.014, "lr": 5.375028707848393e-06, "epoch": 16.17216721672167, "percentage": 80.86, "elapsed_time": "5:48:19", "remaining_time": "1:22:26", "throughput": 1484.39, "total_tokens": 31023520} {"current_steps": 147010, "total_steps": 181800, "loss": 0.0111, "lr": 5.37354196300748e-06, "epoch": 16.172717271727173, "percentage": 80.86, "elapsed_time": "5:48:20", "remaining_time": "1:22:26", "throughput": 1484.4, "total_tokens": 31024576} {"current_steps": 147015, "total_steps": 181800, "loss": 0.0827, "lr": 5.372055399054207e-06, "epoch": 16.173267326732674, "percentage": 80.87, "elapsed_time": "5:48:21", "remaining_time": "1:22:25", "throughput": 1484.4, "total_tokens": 31025632} {"current_steps": 147020, "total_steps": 181800, "loss": 0.0613, "lr": 5.37056901600228e-06, "epoch": 16.173817381738175, "percentage": 80.87, "elapsed_time": "5:48:21", "remaining_time": "1:22:24", "throughput": 1484.4, "total_tokens": 31026656} {"current_steps": 147025, "total_steps": 181800, "loss": 0.0036, "lr": 5.369082813865409e-06, "epoch": 16.174367436743676, "percentage": 80.87, "elapsed_time": "5:48:22", "remaining_time": "1:22:23", "throughput": 1484.4, "total_tokens": 31027680} {"current_steps": 147030, "total_steps": 181800, "loss": 0.0075, "lr": 5.367596792657273e-06, "epoch": 16.174917491749174, "percentage": 80.87, "elapsed_time": "5:48:23", "remaining_time": "1:22:23", "throughput": 1484.4, "total_tokens": 31028800} {"current_steps": 147035, "total_steps": 181800, "loss": 0.0076, "lr": 5.366110952391584e-06, "epoch": 16.175467546754675, "percentage": 80.88, "elapsed_time": "5:48:23", "remaining_time": "1:22:22", "throughput": 1484.4, "total_tokens": 31029824} {"current_steps": 147040, "total_steps": 181800, "loss": 0.0048, "lr": 5.36462529308202e-06, "epoch": 16.176017601760176, "percentage": 80.88, "elapsed_time": "5:48:24", "remaining_time": "1:22:21", "throughput": 1484.4, "total_tokens": 31030848} {"current_steps": 147045, "total_steps": 181800, "loss": 0.0006, "lr": 5.363139814742293e-06, "epoch": 16.176567656765677, "percentage": 80.88, "elapsed_time": "5:48:25", "remaining_time": "1:22:21", "throughput": 1484.41, "total_tokens": 31031936} {"current_steps": 147050, "total_steps": 181800, "loss": 0.0999, "lr": 5.361654517386075e-06, "epoch": 16.177117711771178, "percentage": 80.89, "elapsed_time": "5:48:25", "remaining_time": "1:22:20", "throughput": 1484.41, "total_tokens": 31032992} {"current_steps": 147055, "total_steps": 181800, "loss": 0.01, "lr": 5.3601694010270655e-06, "epoch": 16.17766776677668, "percentage": 80.89, "elapsed_time": "5:48:26", "remaining_time": "1:22:19", "throughput": 1484.41, "total_tokens": 31034080} {"current_steps": 147060, "total_steps": 181800, "loss": 0.0032, "lr": 5.358684465678956e-06, "epoch": 16.178217821782177, "percentage": 80.89, "elapsed_time": "5:48:27", "remaining_time": "1:22:18", "throughput": 1484.41, "total_tokens": 31035136} {"current_steps": 147065, "total_steps": 181800, "loss": 0.0027, "lr": 5.3571997113554206e-06, "epoch": 16.178767876787678, "percentage": 80.89, "elapsed_time": "5:48:28", "remaining_time": "1:22:18", "throughput": 1484.41, "total_tokens": 31036160} {"current_steps": 147070, "total_steps": 181800, "loss": 0.0041, "lr": 5.355715138070155e-06, "epoch": 16.17931793179318, "percentage": 80.9, "elapsed_time": "5:48:28", "remaining_time": "1:22:17", "throughput": 1484.41, "total_tokens": 31037184} {"current_steps": 147075, "total_steps": 181800, "loss": 0.0017, "lr": 5.354230745836833e-06, "epoch": 16.17986798679868, "percentage": 80.9, "elapsed_time": "5:48:29", "remaining_time": "1:22:16", "throughput": 1484.41, "total_tokens": 31038240} {"current_steps": 147080, "total_steps": 181800, "loss": 0.1027, "lr": 5.352746534669137e-06, "epoch": 16.18041804180418, "percentage": 80.9, "elapsed_time": "5:48:30", "remaining_time": "1:22:16", "throughput": 1484.41, "total_tokens": 31039232} {"current_steps": 147085, "total_steps": 181800, "loss": 0.0092, "lr": 5.3512625045807565e-06, "epoch": 16.180968096809682, "percentage": 80.9, "elapsed_time": "5:48:30", "remaining_time": "1:22:15", "throughput": 1484.41, "total_tokens": 31040288} {"current_steps": 147090, "total_steps": 181800, "loss": 0.0011, "lr": 5.349778655585361e-06, "epoch": 16.181518151815183, "percentage": 80.91, "elapsed_time": "5:48:31", "remaining_time": "1:22:14", "throughput": 1484.41, "total_tokens": 31041344} {"current_steps": 147095, "total_steps": 181800, "loss": 0.016, "lr": 5.34829498769662e-06, "epoch": 16.18206820682068, "percentage": 80.91, "elapsed_time": "5:48:32", "remaining_time": "1:22:13", "throughput": 1484.42, "total_tokens": 31042432} {"current_steps": 147100, "total_steps": 181800, "loss": 0.0063, "lr": 5.34681150092822e-06, "epoch": 16.182618261826182, "percentage": 80.91, "elapsed_time": "5:48:32", "remaining_time": "1:22:13", "throughput": 1484.42, "total_tokens": 31043456} {"current_steps": 147105, "total_steps": 181800, "loss": 0.0024, "lr": 5.345328195293814e-06, "epoch": 16.183168316831683, "percentage": 80.92, "elapsed_time": "5:48:33", "remaining_time": "1:22:12", "throughput": 1484.41, "total_tokens": 31044416} {"current_steps": 147110, "total_steps": 181800, "loss": 0.0767, "lr": 5.343845070807102e-06, "epoch": 16.183718371837184, "percentage": 80.92, "elapsed_time": "5:48:34", "remaining_time": "1:22:11", "throughput": 1484.42, "total_tokens": 31045472} {"current_steps": 147115, "total_steps": 181800, "loss": 0.0015, "lr": 5.342362127481737e-06, "epoch": 16.184268426842685, "percentage": 80.92, "elapsed_time": "5:48:34", "remaining_time": "1:22:11", "throughput": 1484.42, "total_tokens": 31046560} {"current_steps": 147120, "total_steps": 181800, "loss": 0.0036, "lr": 5.340879365331381e-06, "epoch": 16.184818481848186, "percentage": 80.92, "elapsed_time": "5:48:35", "remaining_time": "1:22:10", "throughput": 1484.42, "total_tokens": 31047616} {"current_steps": 147125, "total_steps": 181800, "loss": 0.0017, "lr": 5.339396784369713e-06, "epoch": 16.185368536853684, "percentage": 80.93, "elapsed_time": "5:48:36", "remaining_time": "1:22:09", "throughput": 1484.42, "total_tokens": 31048640} {"current_steps": 147130, "total_steps": 181800, "loss": 0.0646, "lr": 5.3379143846103845e-06, "epoch": 16.185918591859185, "percentage": 80.93, "elapsed_time": "5:48:37", "remaining_time": "1:22:08", "throughput": 1484.42, "total_tokens": 31049728} {"current_steps": 147135, "total_steps": 181800, "loss": 0.0077, "lr": 5.336432166067062e-06, "epoch": 16.186468646864686, "percentage": 80.93, "elapsed_time": "5:48:37", "remaining_time": "1:22:08", "throughput": 1484.43, "total_tokens": 31050784} {"current_steps": 147140, "total_steps": 181800, "loss": 0.004, "lr": 5.334950128753419e-06, "epoch": 16.187018701870187, "percentage": 80.94, "elapsed_time": "5:48:38", "remaining_time": "1:22:07", "throughput": 1484.43, "total_tokens": 31051872} {"current_steps": 147145, "total_steps": 181800, "loss": 0.0213, "lr": 5.333468272683096e-06, "epoch": 16.187568756875688, "percentage": 80.94, "elapsed_time": "5:48:39", "remaining_time": "1:22:06", "throughput": 1484.43, "total_tokens": 31052960} {"current_steps": 147150, "total_steps": 181800, "loss": 0.0023, "lr": 5.331986597869768e-06, "epoch": 16.18811881188119, "percentage": 80.94, "elapsed_time": "5:48:39", "remaining_time": "1:22:06", "throughput": 1484.43, "total_tokens": 31054016} {"current_steps": 147155, "total_steps": 181800, "loss": 0.0114, "lr": 5.3305051043270715e-06, "epoch": 16.18866886688669, "percentage": 80.94, "elapsed_time": "5:48:40", "remaining_time": "1:22:05", "throughput": 1484.44, "total_tokens": 31055104} {"current_steps": 147160, "total_steps": 181800, "loss": 0.0651, "lr": 5.32902379206868e-06, "epoch": 16.189218921892188, "percentage": 80.95, "elapsed_time": "5:48:41", "remaining_time": "1:22:04", "throughput": 1484.44, "total_tokens": 31056160} {"current_steps": 147165, "total_steps": 181800, "loss": 0.1198, "lr": 5.327542661108229e-06, "epoch": 16.18976897689769, "percentage": 80.95, "elapsed_time": "5:48:41", "remaining_time": "1:22:03", "throughput": 1484.44, "total_tokens": 31057248} {"current_steps": 147170, "total_steps": 181800, "loss": 0.0098, "lr": 5.326061711459379e-06, "epoch": 16.19031903190319, "percentage": 80.95, "elapsed_time": "5:48:42", "remaining_time": "1:22:03", "throughput": 1484.44, "total_tokens": 31058272} {"current_steps": 147175, "total_steps": 181800, "loss": 0.0123, "lr": 5.324580943135784e-06, "epoch": 16.19086908690869, "percentage": 80.95, "elapsed_time": "5:48:43", "remaining_time": "1:22:02", "throughput": 1484.44, "total_tokens": 31059296} {"current_steps": 147180, "total_steps": 181800, "loss": 0.0132, "lr": 5.323100356151078e-06, "epoch": 16.191419141914192, "percentage": 80.96, "elapsed_time": "5:48:43", "remaining_time": "1:22:01", "throughput": 1484.44, "total_tokens": 31060288} {"current_steps": 147185, "total_steps": 181800, "loss": 0.0042, "lr": 5.321619950518922e-06, "epoch": 16.191969196919693, "percentage": 80.96, "elapsed_time": "5:48:44", "remaining_time": "1:22:01", "throughput": 1484.44, "total_tokens": 31061376} {"current_steps": 147190, "total_steps": 181800, "loss": 0.0682, "lr": 5.320139726252946e-06, "epoch": 16.19251925192519, "percentage": 80.96, "elapsed_time": "5:48:45", "remaining_time": "1:22:00", "throughput": 1484.44, "total_tokens": 31062400} {"current_steps": 147195, "total_steps": 181800, "loss": 0.0021, "lr": 5.318659683366797e-06, "epoch": 16.193069306930692, "percentage": 80.97, "elapsed_time": "5:48:45", "remaining_time": "1:21:59", "throughput": 1484.44, "total_tokens": 31063488} {"current_steps": 147200, "total_steps": 181800, "loss": 0.0016, "lr": 5.3171798218741245e-06, "epoch": 16.193619361936193, "percentage": 80.97, "elapsed_time": "5:48:46", "remaining_time": "1:21:58", "throughput": 1484.45, "total_tokens": 31064608} {"current_steps": 147205, "total_steps": 181800, "loss": 0.0098, "lr": 5.315700141788554e-06, "epoch": 16.194169416941694, "percentage": 80.97, "elapsed_time": "5:48:47", "remaining_time": "1:21:58", "throughput": 1484.45, "total_tokens": 31065728} {"current_steps": 147210, "total_steps": 181800, "loss": 0.0028, "lr": 5.314220643123738e-06, "epoch": 16.194719471947195, "percentage": 80.97, "elapsed_time": "5:48:48", "remaining_time": "1:21:57", "throughput": 1484.44, "total_tokens": 31066816} {"current_steps": 147215, "total_steps": 181800, "loss": 0.0082, "lr": 5.312741325893303e-06, "epoch": 16.195269526952696, "percentage": 80.98, "elapsed_time": "5:48:48", "remaining_time": "1:21:56", "throughput": 1484.44, "total_tokens": 31067872} {"current_steps": 147220, "total_steps": 181800, "loss": 0.0009, "lr": 5.31126219011088e-06, "epoch": 16.195819581958197, "percentage": 80.98, "elapsed_time": "5:48:49", "remaining_time": "1:21:56", "throughput": 1484.44, "total_tokens": 31068928} {"current_steps": 147225, "total_steps": 181800, "loss": 0.095, "lr": 5.309783235790103e-06, "epoch": 16.196369636963695, "percentage": 80.98, "elapsed_time": "5:48:50", "remaining_time": "1:21:55", "throughput": 1484.44, "total_tokens": 31069984} {"current_steps": 147230, "total_steps": 181800, "loss": 0.0014, "lr": 5.308304462944608e-06, "epoch": 16.196919691969196, "percentage": 80.98, "elapsed_time": "5:48:51", "remaining_time": "1:21:54", "throughput": 1484.45, "total_tokens": 31071104} {"current_steps": 147235, "total_steps": 181800, "loss": 0.0256, "lr": 5.306825871588026e-06, "epoch": 16.197469746974697, "percentage": 80.99, "elapsed_time": "5:48:51", "remaining_time": "1:21:53", "throughput": 1484.45, "total_tokens": 31072224} {"current_steps": 147240, "total_steps": 181800, "loss": 0.1473, "lr": 5.305347461733981e-06, "epoch": 16.198019801980198, "percentage": 80.99, "elapsed_time": "5:48:52", "remaining_time": "1:21:53", "throughput": 1484.45, "total_tokens": 31073216} {"current_steps": 147245, "total_steps": 181800, "loss": 0.1193, "lr": 5.303869233396092e-06, "epoch": 16.1985698569857, "percentage": 80.99, "elapsed_time": "5:48:53", "remaining_time": "1:21:52", "throughput": 1484.45, "total_tokens": 31074272} {"current_steps": 147250, "total_steps": 181800, "loss": 0.0417, "lr": 5.302391186587988e-06, "epoch": 16.1991199119912, "percentage": 81.0, "elapsed_time": "5:48:53", "remaining_time": "1:21:51", "throughput": 1484.45, "total_tokens": 31075296} {"current_steps": 147255, "total_steps": 181800, "loss": 0.003, "lr": 5.3009133213232946e-06, "epoch": 16.199669966996698, "percentage": 81.0, "elapsed_time": "5:48:54", "remaining_time": "1:21:51", "throughput": 1484.45, "total_tokens": 31076352} {"current_steps": 147260, "total_steps": 181800, "loss": 0.0049, "lr": 5.2994356376156354e-06, "epoch": 16.2002200220022, "percentage": 81.0, "elapsed_time": "5:48:55", "remaining_time": "1:21:50", "throughput": 1484.46, "total_tokens": 31077408} {"current_steps": 147265, "total_steps": 181800, "loss": 0.0021, "lr": 5.2979581354786255e-06, "epoch": 16.2007700770077, "percentage": 81.0, "elapsed_time": "5:48:55", "remaining_time": "1:21:49", "throughput": 1484.46, "total_tokens": 31078528} {"current_steps": 147270, "total_steps": 181800, "loss": 0.0061, "lr": 5.296480814925875e-06, "epoch": 16.2013201320132, "percentage": 81.01, "elapsed_time": "5:48:56", "remaining_time": "1:21:48", "throughput": 1484.46, "total_tokens": 31079520} {"current_steps": 147275, "total_steps": 181800, "loss": 0.0069, "lr": 5.295003675971011e-06, "epoch": 16.201870187018702, "percentage": 81.01, "elapsed_time": "5:48:57", "remaining_time": "1:21:48", "throughput": 1484.46, "total_tokens": 31080576} {"current_steps": 147280, "total_steps": 181800, "loss": 0.0019, "lr": 5.2935267186276395e-06, "epoch": 16.202420242024203, "percentage": 81.01, "elapsed_time": "5:48:57", "remaining_time": "1:21:47", "throughput": 1484.46, "total_tokens": 31081600} {"current_steps": 147285, "total_steps": 181800, "loss": 0.0372, "lr": 5.292049942909374e-06, "epoch": 16.202970297029704, "percentage": 81.01, "elapsed_time": "5:48:58", "remaining_time": "1:21:46", "throughput": 1484.47, "total_tokens": 31082720} {"current_steps": 147290, "total_steps": 181800, "loss": 0.0031, "lr": 5.290573348829833e-06, "epoch": 16.203520352035202, "percentage": 81.02, "elapsed_time": "5:48:59", "remaining_time": "1:21:46", "throughput": 1484.47, "total_tokens": 31083776} {"current_steps": 147295, "total_steps": 181800, "loss": 0.0015, "lr": 5.289096936402616e-06, "epoch": 16.204070407040703, "percentage": 81.02, "elapsed_time": "5:49:00", "remaining_time": "1:21:45", "throughput": 1484.47, "total_tokens": 31084832} {"current_steps": 147300, "total_steps": 181800, "loss": 0.0268, "lr": 5.287620705641339e-06, "epoch": 16.204620462046204, "percentage": 81.02, "elapsed_time": "5:49:00", "remaining_time": "1:21:44", "throughput": 1484.47, "total_tokens": 31085888} {"current_steps": 147305, "total_steps": 181800, "loss": 0.0115, "lr": 5.286144656559597e-06, "epoch": 16.205170517051705, "percentage": 81.03, "elapsed_time": "5:49:01", "remaining_time": "1:21:43", "throughput": 1484.47, "total_tokens": 31086976} {"current_steps": 147310, "total_steps": 181800, "loss": 0.1086, "lr": 5.284668789170999e-06, "epoch": 16.205720572057206, "percentage": 81.03, "elapsed_time": "5:49:02", "remaining_time": "1:21:43", "throughput": 1484.48, "total_tokens": 31088064} {"current_steps": 147315, "total_steps": 181800, "loss": 0.0412, "lr": 5.283193103489156e-06, "epoch": 16.206270627062707, "percentage": 81.03, "elapsed_time": "5:49:02", "remaining_time": "1:21:42", "throughput": 1484.48, "total_tokens": 31089120} {"current_steps": 147320, "total_steps": 181800, "loss": 0.006, "lr": 5.2817175995276555e-06, "epoch": 16.206820682068205, "percentage": 81.03, "elapsed_time": "5:49:03", "remaining_time": "1:21:41", "throughput": 1484.48, "total_tokens": 31090208} {"current_steps": 147325, "total_steps": 181800, "loss": 0.0516, "lr": 5.280242277300107e-06, "epoch": 16.207370737073706, "percentage": 81.04, "elapsed_time": "5:49:04", "remaining_time": "1:21:41", "throughput": 1484.48, "total_tokens": 31091296} {"current_steps": 147330, "total_steps": 181800, "loss": 0.0012, "lr": 5.278767136820104e-06, "epoch": 16.207920792079207, "percentage": 81.04, "elapsed_time": "5:49:04", "remaining_time": "1:21:40", "throughput": 1484.49, "total_tokens": 31092384} {"current_steps": 147335, "total_steps": 181800, "loss": 0.0045, "lr": 5.2772921781012345e-06, "epoch": 16.20847084708471, "percentage": 81.04, "elapsed_time": "5:49:05", "remaining_time": "1:21:39", "throughput": 1484.49, "total_tokens": 31093440} {"current_steps": 147340, "total_steps": 181800, "loss": 0.0453, "lr": 5.275817401157099e-06, "epoch": 16.20902090209021, "percentage": 81.05, "elapsed_time": "5:49:06", "remaining_time": "1:21:38", "throughput": 1484.49, "total_tokens": 31094464} {"current_steps": 147345, "total_steps": 181800, "loss": 0.0654, "lr": 5.274342806001289e-06, "epoch": 16.20957095709571, "percentage": 81.05, "elapsed_time": "5:49:06", "remaining_time": "1:21:38", "throughput": 1484.49, "total_tokens": 31095520} {"current_steps": 147350, "total_steps": 181800, "loss": 0.0011, "lr": 5.272868392647404e-06, "epoch": 16.21012101210121, "percentage": 81.05, "elapsed_time": "5:49:07", "remaining_time": "1:21:37", "throughput": 1484.49, "total_tokens": 31096512} {"current_steps": 147355, "total_steps": 181800, "loss": 0.0292, "lr": 5.271394161109025e-06, "epoch": 16.21067106710671, "percentage": 81.05, "elapsed_time": "5:49:08", "remaining_time": "1:21:36", "throughput": 1484.49, "total_tokens": 31097600} {"current_steps": 147360, "total_steps": 181800, "loss": 0.056, "lr": 5.269920111399732e-06, "epoch": 16.21122112211221, "percentage": 81.06, "elapsed_time": "5:49:09", "remaining_time": "1:21:36", "throughput": 1484.49, "total_tokens": 31098624} {"current_steps": 147365, "total_steps": 181800, "loss": 0.0383, "lr": 5.268446243533118e-06, "epoch": 16.21177117711771, "percentage": 81.06, "elapsed_time": "5:49:09", "remaining_time": "1:21:35", "throughput": 1484.49, "total_tokens": 31099584} {"current_steps": 147370, "total_steps": 181800, "loss": 0.0995, "lr": 5.2669725575227676e-06, "epoch": 16.212321232123212, "percentage": 81.06, "elapsed_time": "5:49:10", "remaining_time": "1:21:34", "throughput": 1484.49, "total_tokens": 31100704} {"current_steps": 147375, "total_steps": 181800, "loss": 0.0094, "lr": 5.2654990533822665e-06, "epoch": 16.212871287128714, "percentage": 81.06, "elapsed_time": "5:49:11", "remaining_time": "1:21:33", "throughput": 1484.5, "total_tokens": 31101792} {"current_steps": 147380, "total_steps": 181800, "loss": 0.0036, "lr": 5.264025731125194e-06, "epoch": 16.213421342134215, "percentage": 81.07, "elapsed_time": "5:49:11", "remaining_time": "1:21:33", "throughput": 1484.5, "total_tokens": 31102880} {"current_steps": 147385, "total_steps": 181800, "loss": 0.0417, "lr": 5.2625525907651185e-06, "epoch": 16.213971397139716, "percentage": 81.07, "elapsed_time": "5:49:12", "remaining_time": "1:21:32", "throughput": 1484.5, "total_tokens": 31103904} {"current_steps": 147390, "total_steps": 181800, "loss": 0.006, "lr": 5.2610796323156326e-06, "epoch": 16.214521452145213, "percentage": 81.07, "elapsed_time": "5:49:13", "remaining_time": "1:21:31", "throughput": 1484.5, "total_tokens": 31104992} {"current_steps": 147395, "total_steps": 181800, "loss": 0.0032, "lr": 5.259606855790295e-06, "epoch": 16.215071507150714, "percentage": 81.08, "elapsed_time": "5:49:13", "remaining_time": "1:21:31", "throughput": 1484.5, "total_tokens": 31106048} {"current_steps": 147400, "total_steps": 181800, "loss": 0.0242, "lr": 5.258134261202691e-06, "epoch": 16.215621562156215, "percentage": 81.08, "elapsed_time": "5:49:14", "remaining_time": "1:21:30", "throughput": 1484.5, "total_tokens": 31107040} {"current_steps": 147405, "total_steps": 181800, "loss": 0.0333, "lr": 5.256661848566396e-06, "epoch": 16.216171617161717, "percentage": 81.08, "elapsed_time": "5:49:15", "remaining_time": "1:21:29", "throughput": 1484.51, "total_tokens": 31108160} {"current_steps": 147410, "total_steps": 181800, "loss": 0.0346, "lr": 5.255189617894967e-06, "epoch": 16.216721672167218, "percentage": 81.08, "elapsed_time": "5:49:15", "remaining_time": "1:21:28", "throughput": 1484.51, "total_tokens": 31109184} {"current_steps": 147415, "total_steps": 181800, "loss": 0.037, "lr": 5.253717569201988e-06, "epoch": 16.21727172717272, "percentage": 81.09, "elapsed_time": "5:49:16", "remaining_time": "1:21:28", "throughput": 1484.51, "total_tokens": 31110272} {"current_steps": 147420, "total_steps": 181800, "loss": 0.0742, "lr": 5.252245702501013e-06, "epoch": 16.217821782178216, "percentage": 81.09, "elapsed_time": "5:49:17", "remaining_time": "1:21:27", "throughput": 1484.51, "total_tokens": 31111296} {"current_steps": 147425, "total_steps": 181800, "loss": 0.0026, "lr": 5.2507740178056154e-06, "epoch": 16.218371837183717, "percentage": 81.09, "elapsed_time": "5:49:17", "remaining_time": "1:21:26", "throughput": 1484.51, "total_tokens": 31112384} {"current_steps": 147430, "total_steps": 181800, "loss": 0.0402, "lr": 5.249302515129362e-06, "epoch": 16.21892189218922, "percentage": 81.09, "elapsed_time": "5:49:18", "remaining_time": "1:21:26", "throughput": 1484.51, "total_tokens": 31113440} {"current_steps": 147435, "total_steps": 181800, "loss": 0.001, "lr": 5.2478311944858025e-06, "epoch": 16.21947194719472, "percentage": 81.1, "elapsed_time": "5:49:19", "remaining_time": "1:21:25", "throughput": 1484.51, "total_tokens": 31114464} {"current_steps": 147440, "total_steps": 181800, "loss": 0.1618, "lr": 5.246360055888514e-06, "epoch": 16.22002200220022, "percentage": 81.1, "elapsed_time": "5:49:20", "remaining_time": "1:21:24", "throughput": 1484.51, "total_tokens": 31115488} {"current_steps": 147445, "total_steps": 181800, "loss": 0.0029, "lr": 5.244889099351036e-06, "epoch": 16.22057205720572, "percentage": 81.1, "elapsed_time": "5:49:20", "remaining_time": "1:21:23", "throughput": 1484.52, "total_tokens": 31116576} {"current_steps": 147450, "total_steps": 181800, "loss": 0.0087, "lr": 5.243418324886945e-06, "epoch": 16.221122112211223, "percentage": 81.11, "elapsed_time": "5:49:21", "remaining_time": "1:21:23", "throughput": 1484.52, "total_tokens": 31117632} {"current_steps": 147455, "total_steps": 181800, "loss": 0.0014, "lr": 5.241947732509778e-06, "epoch": 16.22167216721672, "percentage": 81.11, "elapsed_time": "5:49:22", "remaining_time": "1:21:22", "throughput": 1484.52, "total_tokens": 31118656} {"current_steps": 147460, "total_steps": 181800, "loss": 0.0035, "lr": 5.240477322233101e-06, "epoch": 16.22222222222222, "percentage": 81.11, "elapsed_time": "5:49:22", "remaining_time": "1:21:21", "throughput": 1484.52, "total_tokens": 31119744} {"current_steps": 147465, "total_steps": 181800, "loss": 0.0114, "lr": 5.239007094070467e-06, "epoch": 16.222772277227723, "percentage": 81.11, "elapsed_time": "5:49:23", "remaining_time": "1:21:21", "throughput": 1484.52, "total_tokens": 31120800} {"current_steps": 147470, "total_steps": 181800, "loss": 0.0189, "lr": 5.237537048035418e-06, "epoch": 16.223322332233224, "percentage": 81.12, "elapsed_time": "5:49:24", "remaining_time": "1:21:20", "throughput": 1484.52, "total_tokens": 31121824} {"current_steps": 147475, "total_steps": 181800, "loss": 0.0007, "lr": 5.236067184141513e-06, "epoch": 16.223872387238725, "percentage": 81.12, "elapsed_time": "5:49:24", "remaining_time": "1:21:19", "throughput": 1484.53, "total_tokens": 31122912} {"current_steps": 147480, "total_steps": 181800, "loss": 0.079, "lr": 5.234597502402286e-06, "epoch": 16.224422442244226, "percentage": 81.12, "elapsed_time": "5:49:25", "remaining_time": "1:21:18", "throughput": 1484.53, "total_tokens": 31123936} {"current_steps": 147485, "total_steps": 181800, "loss": 0.0095, "lr": 5.233128002831289e-06, "epoch": 16.224972497249723, "percentage": 81.12, "elapsed_time": "5:49:26", "remaining_time": "1:21:18", "throughput": 1484.53, "total_tokens": 31124960} {"current_steps": 147490, "total_steps": 181800, "loss": 0.1622, "lr": 5.231658685442073e-06, "epoch": 16.225522552255224, "percentage": 81.13, "elapsed_time": "5:49:26", "remaining_time": "1:21:17", "throughput": 1484.53, "total_tokens": 31126048} {"current_steps": 147495, "total_steps": 181800, "loss": 0.0501, "lr": 5.230189550248174e-06, "epoch": 16.226072607260726, "percentage": 81.13, "elapsed_time": "5:49:27", "remaining_time": "1:21:16", "throughput": 1484.53, "total_tokens": 31127104} {"current_steps": 147500, "total_steps": 181800, "loss": 0.0102, "lr": 5.228720597263123e-06, "epoch": 16.226622662266227, "percentage": 81.13, "elapsed_time": "5:49:28", "remaining_time": "1:21:16", "throughput": 1484.53, "total_tokens": 31128192} {"current_steps": 147505, "total_steps": 181800, "loss": 0.005, "lr": 5.2272518265004765e-06, "epoch": 16.227172717271728, "percentage": 81.14, "elapsed_time": "5:49:29", "remaining_time": "1:21:15", "throughput": 1484.54, "total_tokens": 31129248} {"current_steps": 147510, "total_steps": 181800, "loss": 0.0548, "lr": 5.2257832379737525e-06, "epoch": 16.22772277227723, "percentage": 81.14, "elapsed_time": "5:49:29", "remaining_time": "1:21:14", "throughput": 1484.54, "total_tokens": 31130336} {"current_steps": 147515, "total_steps": 181800, "loss": 0.0287, "lr": 5.224314831696498e-06, "epoch": 16.22827282728273, "percentage": 81.14, "elapsed_time": "5:49:30", "remaining_time": "1:21:13", "throughput": 1484.54, "total_tokens": 31131328} {"current_steps": 147520, "total_steps": 181800, "loss": 0.0187, "lr": 5.22284660768225e-06, "epoch": 16.228822882288227, "percentage": 81.14, "elapsed_time": "5:49:31", "remaining_time": "1:21:13", "throughput": 1484.54, "total_tokens": 31132384} {"current_steps": 147525, "total_steps": 181800, "loss": 0.0059, "lr": 5.221378565944529e-06, "epoch": 16.22937293729373, "percentage": 81.15, "elapsed_time": "5:49:31", "remaining_time": "1:21:12", "throughput": 1484.54, "total_tokens": 31133472} {"current_steps": 147530, "total_steps": 181800, "loss": 0.0021, "lr": 5.219910706496875e-06, "epoch": 16.22992299229923, "percentage": 81.15, "elapsed_time": "5:49:32", "remaining_time": "1:21:11", "throughput": 1484.54, "total_tokens": 31134464} {"current_steps": 147535, "total_steps": 181800, "loss": 0.005, "lr": 5.2184430293528096e-06, "epoch": 16.23047304730473, "percentage": 81.15, "elapsed_time": "5:49:33", "remaining_time": "1:21:11", "throughput": 1484.54, "total_tokens": 31135488} {"current_steps": 147540, "total_steps": 181800, "loss": 0.055, "lr": 5.2169755345258615e-06, "epoch": 16.231023102310232, "percentage": 81.16, "elapsed_time": "5:49:33", "remaining_time": "1:21:10", "throughput": 1484.54, "total_tokens": 31136544} {"current_steps": 147545, "total_steps": 181800, "loss": 0.0456, "lr": 5.215508222029564e-06, "epoch": 16.231573157315733, "percentage": 81.16, "elapsed_time": "5:49:34", "remaining_time": "1:21:09", "throughput": 1484.54, "total_tokens": 31137632} {"current_steps": 147550, "total_steps": 181800, "loss": 0.05, "lr": 5.214041091877425e-06, "epoch": 16.23212321232123, "percentage": 81.16, "elapsed_time": "5:49:35", "remaining_time": "1:21:08", "throughput": 1484.54, "total_tokens": 31138624} {"current_steps": 147555, "total_steps": 181800, "loss": 0.1353, "lr": 5.212574144082982e-06, "epoch": 16.23267326732673, "percentage": 81.16, "elapsed_time": "5:49:35", "remaining_time": "1:21:08", "throughput": 1484.54, "total_tokens": 31139648} {"current_steps": 147560, "total_steps": 181800, "loss": 0.1016, "lr": 5.211107378659744e-06, "epoch": 16.233223322332233, "percentage": 81.17, "elapsed_time": "5:49:36", "remaining_time": "1:21:07", "throughput": 1484.54, "total_tokens": 31140704} {"current_steps": 147565, "total_steps": 181800, "loss": 0.1858, "lr": 5.209640795621238e-06, "epoch": 16.233773377337734, "percentage": 81.17, "elapsed_time": "5:49:37", "remaining_time": "1:21:06", "throughput": 1484.54, "total_tokens": 31141696} {"current_steps": 147570, "total_steps": 181800, "loss": 0.0712, "lr": 5.208174394980972e-06, "epoch": 16.234323432343235, "percentage": 81.17, "elapsed_time": "5:49:37", "remaining_time": "1:21:06", "throughput": 1484.55, "total_tokens": 31142880} {"current_steps": 147575, "total_steps": 181800, "loss": 0.0034, "lr": 5.206708176752461e-06, "epoch": 16.234873487348736, "percentage": 81.17, "elapsed_time": "5:49:38", "remaining_time": "1:21:05", "throughput": 1484.55, "total_tokens": 31143936} {"current_steps": 147580, "total_steps": 181800, "loss": 0.0017, "lr": 5.205242140949235e-06, "epoch": 16.235423542354237, "percentage": 81.18, "elapsed_time": "5:49:39", "remaining_time": "1:21:04", "throughput": 1484.55, "total_tokens": 31145024} {"current_steps": 147585, "total_steps": 181800, "loss": 0.0013, "lr": 5.203776287584786e-06, "epoch": 16.235973597359735, "percentage": 81.18, "elapsed_time": "5:49:40", "remaining_time": "1:21:03", "throughput": 1484.56, "total_tokens": 31146080} {"current_steps": 147590, "total_steps": 181800, "loss": 0.0176, "lr": 5.202310616672637e-06, "epoch": 16.236523652365236, "percentage": 81.18, "elapsed_time": "5:49:40", "remaining_time": "1:21:03", "throughput": 1484.56, "total_tokens": 31147168} {"current_steps": 147595, "total_steps": 181800, "loss": 0.0771, "lr": 5.200845128226284e-06, "epoch": 16.237073707370737, "percentage": 81.19, "elapsed_time": "5:49:41", "remaining_time": "1:21:02", "throughput": 1484.56, "total_tokens": 31148192} {"current_steps": 147600, "total_steps": 181800, "loss": 0.0547, "lr": 5.1993798222592425e-06, "epoch": 16.237623762376238, "percentage": 81.19, "elapsed_time": "5:49:42", "remaining_time": "1:21:01", "throughput": 1484.56, "total_tokens": 31149248} {"current_steps": 147605, "total_steps": 181800, "loss": 0.0048, "lr": 5.197914698785022e-06, "epoch": 16.23817381738174, "percentage": 81.19, "elapsed_time": "5:49:42", "remaining_time": "1:21:01", "throughput": 1484.56, "total_tokens": 31150336} {"current_steps": 147610, "total_steps": 181800, "loss": 0.0015, "lr": 5.196449757817112e-06, "epoch": 16.23872387238724, "percentage": 81.19, "elapsed_time": "5:49:43", "remaining_time": "1:21:00", "throughput": 1484.57, "total_tokens": 31151424} {"current_steps": 147615, "total_steps": 181800, "loss": 0.0064, "lr": 5.194984999369029e-06, "epoch": 16.239273927392738, "percentage": 81.2, "elapsed_time": "5:49:44", "remaining_time": "1:20:59", "throughput": 1484.57, "total_tokens": 31152448} {"current_steps": 147620, "total_steps": 181800, "loss": 0.0478, "lr": 5.1935204234542676e-06, "epoch": 16.23982398239824, "percentage": 81.2, "elapsed_time": "5:49:44", "remaining_time": "1:20:58", "throughput": 1484.57, "total_tokens": 31153472} {"current_steps": 147625, "total_steps": 181800, "loss": 0.0496, "lr": 5.1920560300863175e-06, "epoch": 16.24037403740374, "percentage": 81.2, "elapsed_time": "5:49:45", "remaining_time": "1:20:58", "throughput": 1484.56, "total_tokens": 31154464} {"current_steps": 147630, "total_steps": 181800, "loss": 0.0635, "lr": 5.1905918192786814e-06, "epoch": 16.24092409240924, "percentage": 81.2, "elapsed_time": "5:49:46", "remaining_time": "1:20:57", "throughput": 1484.57, "total_tokens": 31155520} {"current_steps": 147635, "total_steps": 181800, "loss": 0.0372, "lr": 5.1891277910448535e-06, "epoch": 16.241474147414742, "percentage": 81.21, "elapsed_time": "5:49:46", "remaining_time": "1:20:56", "throughput": 1484.57, "total_tokens": 31156608} {"current_steps": 147640, "total_steps": 181800, "loss": 0.0334, "lr": 5.187663945398339e-06, "epoch": 16.242024202420243, "percentage": 81.21, "elapsed_time": "5:49:47", "remaining_time": "1:20:55", "throughput": 1484.57, "total_tokens": 31157632} {"current_steps": 147645, "total_steps": 181800, "loss": 0.0041, "lr": 5.186200282352616e-06, "epoch": 16.242574257425744, "percentage": 81.21, "elapsed_time": "5:49:48", "remaining_time": "1:20:55", "throughput": 1484.57, "total_tokens": 31158624} {"current_steps": 147650, "total_steps": 181800, "loss": 0.0965, "lr": 5.184736801921169e-06, "epoch": 16.24312431243124, "percentage": 81.22, "elapsed_time": "5:49:49", "remaining_time": "1:20:54", "throughput": 1484.57, "total_tokens": 31159616} {"current_steps": 147655, "total_steps": 181800, "loss": 0.0014, "lr": 5.1832735041174975e-06, "epoch": 16.243674367436743, "percentage": 81.22, "elapsed_time": "5:49:49", "remaining_time": "1:20:53", "throughput": 1484.57, "total_tokens": 31160672} {"current_steps": 147660, "total_steps": 181800, "loss": 0.0254, "lr": 5.181810388955086e-06, "epoch": 16.244224422442244, "percentage": 81.22, "elapsed_time": "5:49:50", "remaining_time": "1:20:53", "throughput": 1484.57, "total_tokens": 31161664} {"current_steps": 147665, "total_steps": 181800, "loss": 0.0722, "lr": 5.1803474564474235e-06, "epoch": 16.244774477447745, "percentage": 81.22, "elapsed_time": "5:49:51", "remaining_time": "1:20:52", "throughput": 1484.57, "total_tokens": 31162784} {"current_steps": 147670, "total_steps": 181800, "loss": 0.0103, "lr": 5.178884706607989e-06, "epoch": 16.245324532453246, "percentage": 81.23, "elapsed_time": "5:49:51", "remaining_time": "1:20:51", "throughput": 1484.57, "total_tokens": 31163872} {"current_steps": 147675, "total_steps": 181800, "loss": 0.0016, "lr": 5.177422139450255e-06, "epoch": 16.245874587458747, "percentage": 81.23, "elapsed_time": "5:49:52", "remaining_time": "1:20:50", "throughput": 1484.57, "total_tokens": 31164928} {"current_steps": 147680, "total_steps": 181800, "loss": 0.0167, "lr": 5.175959754987716e-06, "epoch": 16.246424642464245, "percentage": 81.23, "elapsed_time": "5:49:53", "remaining_time": "1:20:50", "throughput": 1484.58, "total_tokens": 31165984} {"current_steps": 147685, "total_steps": 181800, "loss": 0.0005, "lr": 5.17449755323384e-06, "epoch": 16.246974697469746, "percentage": 81.23, "elapsed_time": "5:49:53", "remaining_time": "1:20:49", "throughput": 1484.58, "total_tokens": 31167008} {"current_steps": 147690, "total_steps": 181800, "loss": 0.0038, "lr": 5.173035534202103e-06, "epoch": 16.247524752475247, "percentage": 81.24, "elapsed_time": "5:49:54", "remaining_time": "1:20:48", "throughput": 1484.58, "total_tokens": 31168032} {"current_steps": 147695, "total_steps": 181800, "loss": 0.0187, "lr": 5.171573697905993e-06, "epoch": 16.248074807480748, "percentage": 81.24, "elapsed_time": "5:49:55", "remaining_time": "1:20:48", "throughput": 1484.58, "total_tokens": 31169088} {"current_steps": 147700, "total_steps": 181800, "loss": 0.0133, "lr": 5.170112044358966e-06, "epoch": 16.24862486248625, "percentage": 81.24, "elapsed_time": "5:49:55", "remaining_time": "1:20:47", "throughput": 1484.58, "total_tokens": 31170080} {"current_steps": 147705, "total_steps": 181800, "loss": 0.0055, "lr": 5.168650573574507e-06, "epoch": 16.24917491749175, "percentage": 81.25, "elapsed_time": "5:49:56", "remaining_time": "1:20:46", "throughput": 1484.58, "total_tokens": 31171168} {"current_steps": 147710, "total_steps": 181800, "loss": 0.0019, "lr": 5.167189285566079e-06, "epoch": 16.24972497249725, "percentage": 81.25, "elapsed_time": "5:49:57", "remaining_time": "1:20:45", "throughput": 1484.58, "total_tokens": 31172288} {"current_steps": 147715, "total_steps": 181800, "loss": 0.0053, "lr": 5.1657281803471375e-06, "epoch": 16.25027502750275, "percentage": 81.25, "elapsed_time": "5:49:58", "remaining_time": "1:20:45", "throughput": 1484.58, "total_tokens": 31173312} {"current_steps": 147720, "total_steps": 181800, "loss": 0.0027, "lr": 5.164267257931177e-06, "epoch": 16.25082508250825, "percentage": 81.25, "elapsed_time": "5:49:58", "remaining_time": "1:20:44", "throughput": 1484.58, "total_tokens": 31174368} {"current_steps": 147725, "total_steps": 181800, "loss": 0.0069, "lr": 5.16280651833164e-06, "epoch": 16.25137513751375, "percentage": 81.26, "elapsed_time": "5:49:59", "remaining_time": "1:20:43", "throughput": 1484.58, "total_tokens": 31175392} {"current_steps": 147730, "total_steps": 181800, "loss": 0.1349, "lr": 5.161345961562003e-06, "epoch": 16.251925192519252, "percentage": 81.26, "elapsed_time": "5:50:00", "remaining_time": "1:20:43", "throughput": 1484.59, "total_tokens": 31176448} {"current_steps": 147735, "total_steps": 181800, "loss": 0.0107, "lr": 5.159885587635718e-06, "epoch": 16.252475247524753, "percentage": 81.26, "elapsed_time": "5:50:00", "remaining_time": "1:20:42", "throughput": 1484.59, "total_tokens": 31177536} {"current_steps": 147740, "total_steps": 181800, "loss": 0.0078, "lr": 5.158425396566244e-06, "epoch": 16.253025302530254, "percentage": 81.27, "elapsed_time": "5:50:01", "remaining_time": "1:20:41", "throughput": 1484.59, "total_tokens": 31178624} {"current_steps": 147745, "total_steps": 181800, "loss": 0.0054, "lr": 5.156965388367041e-06, "epoch": 16.253575357535752, "percentage": 81.27, "elapsed_time": "5:50:02", "remaining_time": "1:20:40", "throughput": 1484.59, "total_tokens": 31179712} {"current_steps": 147750, "total_steps": 181800, "loss": 0.001, "lr": 5.155505563051566e-06, "epoch": 16.254125412541253, "percentage": 81.27, "elapsed_time": "5:50:02", "remaining_time": "1:20:40", "throughput": 1484.6, "total_tokens": 31180864} {"current_steps": 147755, "total_steps": 181800, "loss": 0.0364, "lr": 5.154045920633282e-06, "epoch": 16.254675467546754, "percentage": 81.27, "elapsed_time": "5:50:03", "remaining_time": "1:20:39", "throughput": 1484.6, "total_tokens": 31181920} {"current_steps": 147760, "total_steps": 181800, "loss": 0.06, "lr": 5.152586461125633e-06, "epoch": 16.255225522552255, "percentage": 81.28, "elapsed_time": "5:50:04", "remaining_time": "1:20:38", "throughput": 1484.6, "total_tokens": 31182944} {"current_steps": 147765, "total_steps": 181800, "loss": 0.0063, "lr": 5.151127184542065e-06, "epoch": 16.255775577557756, "percentage": 81.28, "elapsed_time": "5:50:04", "remaining_time": "1:20:38", "throughput": 1484.6, "total_tokens": 31184000} {"current_steps": 147770, "total_steps": 181800, "loss": 0.0017, "lr": 5.14966809089604e-06, "epoch": 16.256325632563257, "percentage": 81.28, "elapsed_time": "5:50:05", "remaining_time": "1:20:37", "throughput": 1484.61, "total_tokens": 31185088} {"current_steps": 147775, "total_steps": 181800, "loss": 0.1091, "lr": 5.148209180200983e-06, "epoch": 16.25687568756876, "percentage": 81.28, "elapsed_time": "5:50:06", "remaining_time": "1:20:36", "throughput": 1484.61, "total_tokens": 31186144} {"current_steps": 147780, "total_steps": 181800, "loss": 0.0027, "lr": 5.1467504524703725e-06, "epoch": 16.257425742574256, "percentage": 81.29, "elapsed_time": "5:50:07", "remaining_time": "1:20:35", "throughput": 1484.61, "total_tokens": 31187136} {"current_steps": 147785, "total_steps": 181800, "loss": 0.0327, "lr": 5.1452919077176335e-06, "epoch": 16.257975797579757, "percentage": 81.29, "elapsed_time": "5:50:07", "remaining_time": "1:20:35", "throughput": 1484.61, "total_tokens": 31188224} {"current_steps": 147790, "total_steps": 181800, "loss": 0.0014, "lr": 5.1438335459562085e-06, "epoch": 16.258525852585258, "percentage": 81.29, "elapsed_time": "5:50:08", "remaining_time": "1:20:34", "throughput": 1484.61, "total_tokens": 31189184} {"current_steps": 147795, "total_steps": 181800, "loss": 0.0364, "lr": 5.142375367199548e-06, "epoch": 16.25907590759076, "percentage": 81.3, "elapsed_time": "5:50:09", "remaining_time": "1:20:33", "throughput": 1484.61, "total_tokens": 31190304} {"current_steps": 147800, "total_steps": 181800, "loss": 0.1151, "lr": 5.140917371461076e-06, "epoch": 16.25962596259626, "percentage": 81.3, "elapsed_time": "5:50:09", "remaining_time": "1:20:33", "throughput": 1484.61, "total_tokens": 31191296} {"current_steps": 147805, "total_steps": 181800, "loss": 0.0016, "lr": 5.139459558754242e-06, "epoch": 16.26017601760176, "percentage": 81.3, "elapsed_time": "5:50:10", "remaining_time": "1:20:32", "throughput": 1484.61, "total_tokens": 31192352} {"current_steps": 147810, "total_steps": 181800, "loss": 0.0196, "lr": 5.1380019290924844e-06, "epoch": 16.260726072607262, "percentage": 81.3, "elapsed_time": "5:50:11", "remaining_time": "1:20:31", "throughput": 1484.61, "total_tokens": 31193408} {"current_steps": 147815, "total_steps": 181800, "loss": 0.0311, "lr": 5.136544482489225e-06, "epoch": 16.26127612761276, "percentage": 81.31, "elapsed_time": "5:50:11", "remaining_time": "1:20:30", "throughput": 1484.61, "total_tokens": 31194464} {"current_steps": 147820, "total_steps": 181800, "loss": 0.0471, "lr": 5.135087218957912e-06, "epoch": 16.26182618261826, "percentage": 81.31, "elapsed_time": "5:50:12", "remaining_time": "1:20:30", "throughput": 1484.61, "total_tokens": 31195488} {"current_steps": 147825, "total_steps": 181800, "loss": 0.0019, "lr": 5.13363013851196e-06, "epoch": 16.262376237623762, "percentage": 81.31, "elapsed_time": "5:50:13", "remaining_time": "1:20:29", "throughput": 1484.61, "total_tokens": 31196512} {"current_steps": 147830, "total_steps": 181800, "loss": 0.0359, "lr": 5.132173241164814e-06, "epoch": 16.262926292629263, "percentage": 81.31, "elapsed_time": "5:50:13", "remaining_time": "1:20:28", "throughput": 1484.62, "total_tokens": 31197600} {"current_steps": 147835, "total_steps": 181800, "loss": 0.0372, "lr": 5.130716526929885e-06, "epoch": 16.263476347634764, "percentage": 81.32, "elapsed_time": "5:50:14", "remaining_time": "1:20:28", "throughput": 1484.62, "total_tokens": 31198688} {"current_steps": 147840, "total_steps": 181800, "loss": 0.0015, "lr": 5.12925999582061e-06, "epoch": 16.264026402640265, "percentage": 81.32, "elapsed_time": "5:50:15", "remaining_time": "1:20:27", "throughput": 1484.62, "total_tokens": 31199776} {"current_steps": 147845, "total_steps": 181800, "loss": 0.0752, "lr": 5.127803647850418e-06, "epoch": 16.264576457645763, "percentage": 81.32, "elapsed_time": "5:50:15", "remaining_time": "1:20:26", "throughput": 1484.62, "total_tokens": 31200800} {"current_steps": 147850, "total_steps": 181800, "loss": 0.0292, "lr": 5.126347483032715e-06, "epoch": 16.265126512651264, "percentage": 81.33, "elapsed_time": "5:50:16", "remaining_time": "1:20:25", "throughput": 1484.62, "total_tokens": 31201824} {"current_steps": 147855, "total_steps": 181800, "loss": 0.0617, "lr": 5.124891501380938e-06, "epoch": 16.265676567656765, "percentage": 81.33, "elapsed_time": "5:50:17", "remaining_time": "1:20:25", "throughput": 1484.62, "total_tokens": 31202880} {"current_steps": 147860, "total_steps": 181800, "loss": 0.0605, "lr": 5.123435702908494e-06, "epoch": 16.266226622662266, "percentage": 81.33, "elapsed_time": "5:50:18", "remaining_time": "1:20:24", "throughput": 1484.62, "total_tokens": 31203936} {"current_steps": 147865, "total_steps": 181800, "loss": 0.0034, "lr": 5.121980087628803e-06, "epoch": 16.266776677667767, "percentage": 81.33, "elapsed_time": "5:50:18", "remaining_time": "1:20:23", "throughput": 1484.62, "total_tokens": 31204960} {"current_steps": 147870, "total_steps": 181800, "loss": 0.0025, "lr": 5.1205246555552925e-06, "epoch": 16.26732673267327, "percentage": 81.34, "elapsed_time": "5:50:19", "remaining_time": "1:20:23", "throughput": 1484.62, "total_tokens": 31205984} {"current_steps": 147875, "total_steps": 181800, "loss": 0.1588, "lr": 5.119069406701365e-06, "epoch": 16.26787678767877, "percentage": 81.34, "elapsed_time": "5:50:20", "remaining_time": "1:20:22", "throughput": 1484.63, "total_tokens": 31207040} {"current_steps": 147880, "total_steps": 181800, "loss": 0.0018, "lr": 5.117614341080429e-06, "epoch": 16.268426842684267, "percentage": 81.34, "elapsed_time": "5:50:20", "remaining_time": "1:20:21", "throughput": 1484.63, "total_tokens": 31208128} {"current_steps": 147885, "total_steps": 181800, "loss": 0.0026, "lr": 5.1161594587059074e-06, "epoch": 16.268976897689768, "percentage": 81.34, "elapsed_time": "5:50:21", "remaining_time": "1:20:20", "throughput": 1484.63, "total_tokens": 31209152} {"current_steps": 147890, "total_steps": 181800, "loss": 0.0072, "lr": 5.11470475959119e-06, "epoch": 16.26952695269527, "percentage": 81.35, "elapsed_time": "5:50:22", "remaining_time": "1:20:20", "throughput": 1484.63, "total_tokens": 31210240} {"current_steps": 147895, "total_steps": 181800, "loss": 0.0026, "lr": 5.113250243749712e-06, "epoch": 16.27007700770077, "percentage": 81.35, "elapsed_time": "5:50:22", "remaining_time": "1:20:19", "throughput": 1484.64, "total_tokens": 31211360} {"current_steps": 147900, "total_steps": 181800, "loss": 0.0063, "lr": 5.111795911194861e-06, "epoch": 16.27062706270627, "percentage": 81.35, "elapsed_time": "5:50:23", "remaining_time": "1:20:18", "throughput": 1484.64, "total_tokens": 31212384} {"current_steps": 147905, "total_steps": 181800, "loss": 0.0219, "lr": 5.110341761940038e-06, "epoch": 16.271177117711773, "percentage": 81.36, "elapsed_time": "5:50:24", "remaining_time": "1:20:18", "throughput": 1484.64, "total_tokens": 31213408} {"current_steps": 147910, "total_steps": 181800, "loss": 0.0177, "lr": 5.10888779599866e-06, "epoch": 16.27172717271727, "percentage": 81.36, "elapsed_time": "5:50:24", "remaining_time": "1:20:17", "throughput": 1484.64, "total_tokens": 31214496} {"current_steps": 147915, "total_steps": 181800, "loss": 0.0045, "lr": 5.1074340133841075e-06, "epoch": 16.27227722772277, "percentage": 81.36, "elapsed_time": "5:50:25", "remaining_time": "1:20:16", "throughput": 1484.64, "total_tokens": 31215616} {"current_steps": 147920, "total_steps": 181800, "loss": 0.0115, "lr": 5.105980414109793e-06, "epoch": 16.272827282728272, "percentage": 81.36, "elapsed_time": "5:50:26", "remaining_time": "1:20:15", "throughput": 1484.65, "total_tokens": 31216672} {"current_steps": 147925, "total_steps": 181800, "loss": 0.0538, "lr": 5.104526998189119e-06, "epoch": 16.273377337733773, "percentage": 81.37, "elapsed_time": "5:50:27", "remaining_time": "1:20:15", "throughput": 1484.65, "total_tokens": 31217760} {"current_steps": 147930, "total_steps": 181800, "loss": 0.0147, "lr": 5.1030737656354635e-06, "epoch": 16.273927392739274, "percentage": 81.37, "elapsed_time": "5:50:27", "remaining_time": "1:20:14", "throughput": 1484.65, "total_tokens": 31218816} {"current_steps": 147935, "total_steps": 181800, "loss": 0.0012, "lr": 5.101620716462238e-06, "epoch": 16.274477447744776, "percentage": 81.37, "elapsed_time": "5:50:28", "remaining_time": "1:20:13", "throughput": 1484.66, "total_tokens": 31219936} {"current_steps": 147940, "total_steps": 181800, "loss": 0.0013, "lr": 5.100167850682819e-06, "epoch": 16.275027502750277, "percentage": 81.38, "elapsed_time": "5:50:29", "remaining_time": "1:20:13", "throughput": 1484.65, "total_tokens": 31220928} {"current_steps": 147945, "total_steps": 181800, "loss": 0.2881, "lr": 5.098715168310611e-06, "epoch": 16.275577557755774, "percentage": 81.38, "elapsed_time": "5:50:29", "remaining_time": "1:20:12", "throughput": 1484.66, "total_tokens": 31221984} {"current_steps": 147950, "total_steps": 181800, "loss": 0.0635, "lr": 5.097262669358987e-06, "epoch": 16.276127612761275, "percentage": 81.38, "elapsed_time": "5:50:30", "remaining_time": "1:20:11", "throughput": 1484.65, "total_tokens": 31223008} {"current_steps": 147955, "total_steps": 181800, "loss": 0.0052, "lr": 5.095810353841346e-06, "epoch": 16.276677667766776, "percentage": 81.38, "elapsed_time": "5:50:31", "remaining_time": "1:20:10", "throughput": 1484.65, "total_tokens": 31224000} {"current_steps": 147960, "total_steps": 181800, "loss": 0.0054, "lr": 5.0943582217710726e-06, "epoch": 16.277227722772277, "percentage": 81.39, "elapsed_time": "5:50:31", "remaining_time": "1:20:10", "throughput": 1484.66, "total_tokens": 31225120} {"current_steps": 147965, "total_steps": 181800, "loss": 0.0464, "lr": 5.092906273161544e-06, "epoch": 16.27777777777778, "percentage": 81.39, "elapsed_time": "5:50:32", "remaining_time": "1:20:09", "throughput": 1484.66, "total_tokens": 31226144} {"current_steps": 147970, "total_steps": 181800, "loss": 0.01, "lr": 5.091454508026153e-06, "epoch": 16.27832783278328, "percentage": 81.39, "elapsed_time": "5:50:33", "remaining_time": "1:20:08", "throughput": 1484.66, "total_tokens": 31227200} {"current_steps": 147975, "total_steps": 181800, "loss": 0.0663, "lr": 5.090002926378265e-06, "epoch": 16.278877887788777, "percentage": 81.39, "elapsed_time": "5:50:33", "remaining_time": "1:20:08", "throughput": 1484.66, "total_tokens": 31228256} {"current_steps": 147980, "total_steps": 181800, "loss": 0.0503, "lr": 5.0885515282312665e-06, "epoch": 16.27942794279428, "percentage": 81.4, "elapsed_time": "5:50:34", "remaining_time": "1:20:07", "throughput": 1484.66, "total_tokens": 31229280} {"current_steps": 147985, "total_steps": 181800, "loss": 0.0227, "lr": 5.087100313598542e-06, "epoch": 16.27997799779978, "percentage": 81.4, "elapsed_time": "5:50:35", "remaining_time": "1:20:06", "throughput": 1484.66, "total_tokens": 31230272} {"current_steps": 147990, "total_steps": 181800, "loss": 0.0077, "lr": 5.085649282493449e-06, "epoch": 16.28052805280528, "percentage": 81.4, "elapsed_time": "5:50:36", "remaining_time": "1:20:05", "throughput": 1484.66, "total_tokens": 31231264} {"current_steps": 147995, "total_steps": 181800, "loss": 0.0349, "lr": 5.084198434929379e-06, "epoch": 16.28107810781078, "percentage": 81.41, "elapsed_time": "5:50:36", "remaining_time": "1:20:05", "throughput": 1484.66, "total_tokens": 31232352} {"current_steps": 148000, "total_steps": 181800, "loss": 0.0969, "lr": 5.0827477709196964e-06, "epoch": 16.281628162816283, "percentage": 81.41, "elapsed_time": "5:50:37", "remaining_time": "1:20:04", "throughput": 1484.66, "total_tokens": 31233408} {"current_steps": 148005, "total_steps": 181800, "loss": 0.003, "lr": 5.081297290477763e-06, "epoch": 16.282178217821784, "percentage": 81.41, "elapsed_time": "5:50:38", "remaining_time": "1:20:03", "throughput": 1484.66, "total_tokens": 31234464} {"current_steps": 148010, "total_steps": 181800, "loss": 0.0046, "lr": 5.079846993616955e-06, "epoch": 16.28272827282728, "percentage": 81.41, "elapsed_time": "5:50:38", "remaining_time": "1:20:03", "throughput": 1484.67, "total_tokens": 31235520} {"current_steps": 148015, "total_steps": 181800, "loss": 0.0133, "lr": 5.078396880350639e-06, "epoch": 16.283278327832782, "percentage": 81.42, "elapsed_time": "5:50:39", "remaining_time": "1:20:02", "throughput": 1484.67, "total_tokens": 31236576} {"current_steps": 148020, "total_steps": 181800, "loss": 0.0017, "lr": 5.076946950692185e-06, "epoch": 16.283828382838283, "percentage": 81.42, "elapsed_time": "5:50:40", "remaining_time": "1:20:01", "throughput": 1484.67, "total_tokens": 31237632} {"current_steps": 148025, "total_steps": 181800, "loss": 0.0012, "lr": 5.0754972046549525e-06, "epoch": 16.284378437843785, "percentage": 81.42, "elapsed_time": "5:50:40", "remaining_time": "1:20:00", "throughput": 1484.67, "total_tokens": 31238688} {"current_steps": 148030, "total_steps": 181800, "loss": 0.0043, "lr": 5.0740476422522945e-06, "epoch": 16.284928492849286, "percentage": 81.42, "elapsed_time": "5:50:41", "remaining_time": "1:20:00", "throughput": 1484.67, "total_tokens": 31239712} {"current_steps": 148035, "total_steps": 181800, "loss": 0.0089, "lr": 5.072598263497577e-06, "epoch": 16.285478547854787, "percentage": 81.43, "elapsed_time": "5:50:42", "remaining_time": "1:19:59", "throughput": 1484.67, "total_tokens": 31240736} {"current_steps": 148040, "total_steps": 181800, "loss": 0.0046, "lr": 5.071149068404158e-06, "epoch": 16.286028602860284, "percentage": 81.43, "elapsed_time": "5:50:42", "remaining_time": "1:19:58", "throughput": 1484.67, "total_tokens": 31241728} {"current_steps": 148045, "total_steps": 181800, "loss": 0.0102, "lr": 5.069700056985404e-06, "epoch": 16.286578657865785, "percentage": 81.43, "elapsed_time": "5:50:43", "remaining_time": "1:19:58", "throughput": 1484.67, "total_tokens": 31242752} {"current_steps": 148050, "total_steps": 181800, "loss": 0.0019, "lr": 5.0682512292546616e-06, "epoch": 16.287128712871286, "percentage": 81.44, "elapsed_time": "5:50:44", "remaining_time": "1:19:57", "throughput": 1484.67, "total_tokens": 31243808} {"current_steps": 148055, "total_steps": 181800, "loss": 0.0321, "lr": 5.066802585225275e-06, "epoch": 16.287678767876788, "percentage": 81.44, "elapsed_time": "5:50:44", "remaining_time": "1:19:56", "throughput": 1484.67, "total_tokens": 31244896} {"current_steps": 148060, "total_steps": 181800, "loss": 0.0044, "lr": 5.065354124910612e-06, "epoch": 16.28822882288229, "percentage": 81.44, "elapsed_time": "5:50:45", "remaining_time": "1:19:55", "throughput": 1484.67, "total_tokens": 31245920} {"current_steps": 148065, "total_steps": 181800, "loss": 0.0078, "lr": 5.063905848324008e-06, "epoch": 16.28877887788779, "percentage": 81.44, "elapsed_time": "5:50:46", "remaining_time": "1:19:55", "throughput": 1484.67, "total_tokens": 31246944} {"current_steps": 148070, "total_steps": 181800, "loss": 0.0059, "lr": 5.062457755478816e-06, "epoch": 16.28932893289329, "percentage": 81.45, "elapsed_time": "5:50:47", "remaining_time": "1:19:54", "throughput": 1484.68, "total_tokens": 31248032} {"current_steps": 148075, "total_steps": 181800, "loss": 0.0015, "lr": 5.06100984638839e-06, "epoch": 16.28987898789879, "percentage": 81.45, "elapsed_time": "5:50:47", "remaining_time": "1:19:53", "throughput": 1484.68, "total_tokens": 31249120} {"current_steps": 148080, "total_steps": 181800, "loss": 0.0055, "lr": 5.059562121066063e-06, "epoch": 16.29042904290429, "percentage": 81.45, "elapsed_time": "5:50:48", "remaining_time": "1:19:53", "throughput": 1484.68, "total_tokens": 31250176} {"current_steps": 148085, "total_steps": 181800, "loss": 0.0022, "lr": 5.058114579525191e-06, "epoch": 16.29097909790979, "percentage": 81.45, "elapsed_time": "5:50:49", "remaining_time": "1:19:52", "throughput": 1484.69, "total_tokens": 31251264} {"current_steps": 148090, "total_steps": 181800, "loss": 0.01, "lr": 5.0566672217791015e-06, "epoch": 16.29152915291529, "percentage": 81.46, "elapsed_time": "5:50:49", "remaining_time": "1:19:51", "throughput": 1484.69, "total_tokens": 31252352} {"current_steps": 148095, "total_steps": 181800, "loss": 0.0567, "lr": 5.055220047841139e-06, "epoch": 16.292079207920793, "percentage": 81.46, "elapsed_time": "5:50:50", "remaining_time": "1:19:50", "throughput": 1484.69, "total_tokens": 31253408} {"current_steps": 148100, "total_steps": 181800, "loss": 0.0197, "lr": 5.053773057724651e-06, "epoch": 16.292629262926294, "percentage": 81.46, "elapsed_time": "5:50:51", "remaining_time": "1:19:50", "throughput": 1484.69, "total_tokens": 31254464} {"current_steps": 148105, "total_steps": 181800, "loss": 0.0163, "lr": 5.05232625144296e-06, "epoch": 16.293179317931795, "percentage": 81.47, "elapsed_time": "5:50:51", "remaining_time": "1:19:49", "throughput": 1484.69, "total_tokens": 31255456} {"current_steps": 148110, "total_steps": 181800, "loss": 0.1514, "lr": 5.050879629009409e-06, "epoch": 16.293729372937293, "percentage": 81.47, "elapsed_time": "5:50:52", "remaining_time": "1:19:48", "throughput": 1484.69, "total_tokens": 31256480} {"current_steps": 148115, "total_steps": 181800, "loss": 0.0153, "lr": 5.0494331904373305e-06, "epoch": 16.294279427942794, "percentage": 81.47, "elapsed_time": "5:50:53", "remaining_time": "1:19:48", "throughput": 1484.69, "total_tokens": 31257536} {"current_steps": 148120, "total_steps": 181800, "loss": 0.0038, "lr": 5.047986935740045e-06, "epoch": 16.294829482948295, "percentage": 81.47, "elapsed_time": "5:50:53", "remaining_time": "1:19:47", "throughput": 1484.69, "total_tokens": 31258592} {"current_steps": 148125, "total_steps": 181800, "loss": 0.0471, "lr": 5.046540864930893e-06, "epoch": 16.295379537953796, "percentage": 81.48, "elapsed_time": "5:50:54", "remaining_time": "1:19:46", "throughput": 1484.7, "total_tokens": 31259648} {"current_steps": 148130, "total_steps": 181800, "loss": 0.0067, "lr": 5.0450949780231956e-06, "epoch": 16.295929592959297, "percentage": 81.48, "elapsed_time": "5:50:55", "remaining_time": "1:19:45", "throughput": 1484.7, "total_tokens": 31260704} {"current_steps": 148135, "total_steps": 181800, "loss": 0.0072, "lr": 5.04364927503029e-06, "epoch": 16.296479647964798, "percentage": 81.48, "elapsed_time": "5:50:55", "remaining_time": "1:19:45", "throughput": 1484.7, "total_tokens": 31261760} {"current_steps": 148140, "total_steps": 181800, "loss": 0.0028, "lr": 5.042203755965494e-06, "epoch": 16.297029702970296, "percentage": 81.49, "elapsed_time": "5:50:56", "remaining_time": "1:19:44", "throughput": 1484.7, "total_tokens": 31262816} {"current_steps": 148145, "total_steps": 181800, "loss": 0.0026, "lr": 5.040758420842123e-06, "epoch": 16.297579757975797, "percentage": 81.49, "elapsed_time": "5:50:57", "remaining_time": "1:19:43", "throughput": 1484.7, "total_tokens": 31263808} {"current_steps": 148150, "total_steps": 181800, "loss": 0.0031, "lr": 5.039313269673504e-06, "epoch": 16.298129812981298, "percentage": 81.49, "elapsed_time": "5:50:58", "remaining_time": "1:19:43", "throughput": 1484.7, "total_tokens": 31264896} {"current_steps": 148155, "total_steps": 181800, "loss": 0.0069, "lr": 5.037868302472956e-06, "epoch": 16.2986798679868, "percentage": 81.49, "elapsed_time": "5:50:58", "remaining_time": "1:19:42", "throughput": 1484.71, "total_tokens": 31265984} {"current_steps": 148160, "total_steps": 181800, "loss": 0.0013, "lr": 5.036423519253805e-06, "epoch": 16.2992299229923, "percentage": 81.5, "elapsed_time": "5:50:59", "remaining_time": "1:19:41", "throughput": 1484.71, "total_tokens": 31267040} {"current_steps": 148165, "total_steps": 181800, "loss": 0.001, "lr": 5.034978920029357e-06, "epoch": 16.2997799779978, "percentage": 81.5, "elapsed_time": "5:51:00", "remaining_time": "1:19:40", "throughput": 1484.71, "total_tokens": 31268064} {"current_steps": 148170, "total_steps": 181800, "loss": 0.0036, "lr": 5.033534504812923e-06, "epoch": 16.300330033003302, "percentage": 81.5, "elapsed_time": "5:51:00", "remaining_time": "1:19:40", "throughput": 1484.71, "total_tokens": 31269120} {"current_steps": 148175, "total_steps": 181800, "loss": 0.0028, "lr": 5.032090273617826e-06, "epoch": 16.3008800880088, "percentage": 81.5, "elapsed_time": "5:51:01", "remaining_time": "1:19:39", "throughput": 1484.71, "total_tokens": 31270080} {"current_steps": 148180, "total_steps": 181800, "loss": 0.03, "lr": 5.030646226457364e-06, "epoch": 16.3014301430143, "percentage": 81.51, "elapsed_time": "5:51:02", "remaining_time": "1:19:38", "throughput": 1484.71, "total_tokens": 31271168} {"current_steps": 148185, "total_steps": 181800, "loss": 0.0043, "lr": 5.029202363344856e-06, "epoch": 16.301980198019802, "percentage": 81.51, "elapsed_time": "5:51:02", "remaining_time": "1:19:37", "throughput": 1484.71, "total_tokens": 31272192} {"current_steps": 148190, "total_steps": 181800, "loss": 0.067, "lr": 5.027758684293612e-06, "epoch": 16.302530253025303, "percentage": 81.51, "elapsed_time": "5:51:03", "remaining_time": "1:19:37", "throughput": 1484.71, "total_tokens": 31273248} {"current_steps": 148195, "total_steps": 181800, "loss": 0.0101, "lr": 5.026315189316927e-06, "epoch": 16.303080308030804, "percentage": 81.52, "elapsed_time": "5:51:04", "remaining_time": "1:19:36", "throughput": 1484.71, "total_tokens": 31274304} {"current_steps": 148200, "total_steps": 181800, "loss": 0.0341, "lr": 5.0248718784281165e-06, "epoch": 16.303630363036305, "percentage": 81.52, "elapsed_time": "5:51:04", "remaining_time": "1:19:35", "throughput": 1484.71, "total_tokens": 31275328} {"current_steps": 148205, "total_steps": 181800, "loss": 0.0079, "lr": 5.023428751640472e-06, "epoch": 16.304180418041803, "percentage": 81.52, "elapsed_time": "5:51:05", "remaining_time": "1:19:35", "throughput": 1484.71, "total_tokens": 31276352} {"current_steps": 148210, "total_steps": 181800, "loss": 0.0014, "lr": 5.021985808967294e-06, "epoch": 16.304730473047304, "percentage": 81.52, "elapsed_time": "5:51:06", "remaining_time": "1:19:34", "throughput": 1484.71, "total_tokens": 31277440} {"current_steps": 148215, "total_steps": 181800, "loss": 0.0008, "lr": 5.020543050421897e-06, "epoch": 16.305280528052805, "percentage": 81.53, "elapsed_time": "5:51:06", "remaining_time": "1:19:33", "throughput": 1484.71, "total_tokens": 31278464} {"current_steps": 148220, "total_steps": 181800, "loss": 0.0086, "lr": 5.019100476017563e-06, "epoch": 16.305830583058306, "percentage": 81.53, "elapsed_time": "5:51:07", "remaining_time": "1:19:32", "throughput": 1484.71, "total_tokens": 31279488} {"current_steps": 148225, "total_steps": 181800, "loss": 0.0551, "lr": 5.017658085767596e-06, "epoch": 16.306380638063807, "percentage": 81.53, "elapsed_time": "5:51:08", "remaining_time": "1:19:32", "throughput": 1484.72, "total_tokens": 31280576} {"current_steps": 148230, "total_steps": 181800, "loss": 0.0041, "lr": 5.016215879685279e-06, "epoch": 16.306930693069308, "percentage": 81.53, "elapsed_time": "5:51:09", "remaining_time": "1:19:31", "throughput": 1484.72, "total_tokens": 31281664} {"current_steps": 148235, "total_steps": 181800, "loss": 0.0911, "lr": 5.0147738577839165e-06, "epoch": 16.30748074807481, "percentage": 81.54, "elapsed_time": "5:51:09", "remaining_time": "1:19:30", "throughput": 1484.73, "total_tokens": 31282816} {"current_steps": 148240, "total_steps": 181800, "loss": 0.0011, "lr": 5.013332020076788e-06, "epoch": 16.308030803080307, "percentage": 81.54, "elapsed_time": "5:51:10", "remaining_time": "1:19:30", "throughput": 1484.73, "total_tokens": 31283872} {"current_steps": 148245, "total_steps": 181800, "loss": 0.0595, "lr": 5.0118903665771905e-06, "epoch": 16.308580858085808, "percentage": 81.54, "elapsed_time": "5:51:11", "remaining_time": "1:19:29", "throughput": 1484.73, "total_tokens": 31284896} {"current_steps": 148250, "total_steps": 181800, "loss": 0.0893, "lr": 5.0104488972984116e-06, "epoch": 16.30913091309131, "percentage": 81.55, "elapsed_time": "5:51:11", "remaining_time": "1:19:28", "throughput": 1484.73, "total_tokens": 31285984} {"current_steps": 148255, "total_steps": 181800, "loss": 0.1743, "lr": 5.009007612253735e-06, "epoch": 16.30968096809681, "percentage": 81.55, "elapsed_time": "5:51:12", "remaining_time": "1:19:27", "throughput": 1484.73, "total_tokens": 31287008} {"current_steps": 148260, "total_steps": 181800, "loss": 0.0141, "lr": 5.007566511456435e-06, "epoch": 16.31023102310231, "percentage": 81.55, "elapsed_time": "5:51:13", "remaining_time": "1:19:27", "throughput": 1484.73, "total_tokens": 31288032} {"current_steps": 148265, "total_steps": 181800, "loss": 0.0304, "lr": 5.006125594919803e-06, "epoch": 16.310781078107812, "percentage": 81.55, "elapsed_time": "5:51:13", "remaining_time": "1:19:26", "throughput": 1484.73, "total_tokens": 31289088} {"current_steps": 148270, "total_steps": 181800, "loss": 0.0018, "lr": 5.004684862657116e-06, "epoch": 16.31133113311331, "percentage": 81.56, "elapsed_time": "5:51:14", "remaining_time": "1:19:25", "throughput": 1484.74, "total_tokens": 31290208} {"current_steps": 148275, "total_steps": 181800, "loss": 0.0059, "lr": 5.00324431468166e-06, "epoch": 16.31188118811881, "percentage": 81.56, "elapsed_time": "5:51:15", "remaining_time": "1:19:25", "throughput": 1484.73, "total_tokens": 31291168} {"current_steps": 148280, "total_steps": 181800, "loss": 0.0034, "lr": 5.001803951006706e-06, "epoch": 16.312431243124312, "percentage": 81.56, "elapsed_time": "5:51:15", "remaining_time": "1:19:24", "throughput": 1484.74, "total_tokens": 31292256} {"current_steps": 148285, "total_steps": 181800, "loss": 0.0017, "lr": 5.000363771645522e-06, "epoch": 16.312981298129813, "percentage": 81.56, "elapsed_time": "5:51:16", "remaining_time": "1:19:23", "throughput": 1484.74, "total_tokens": 31293312} {"current_steps": 148290, "total_steps": 181800, "loss": 0.0052, "lr": 4.998923776611397e-06, "epoch": 16.313531353135314, "percentage": 81.57, "elapsed_time": "5:51:17", "remaining_time": "1:19:22", "throughput": 1484.74, "total_tokens": 31294432} {"current_steps": 148295, "total_steps": 181800, "loss": 0.1046, "lr": 4.997483965917585e-06, "epoch": 16.314081408140815, "percentage": 81.57, "elapsed_time": "5:51:18", "remaining_time": "1:19:22", "throughput": 1484.74, "total_tokens": 31295456} {"current_steps": 148300, "total_steps": 181800, "loss": 0.0105, "lr": 4.996044339577366e-06, "epoch": 16.314631463146316, "percentage": 81.57, "elapsed_time": "5:51:18", "remaining_time": "1:19:21", "throughput": 1484.74, "total_tokens": 31296512} {"current_steps": 148305, "total_steps": 181800, "loss": 0.0019, "lr": 4.994604897604016e-06, "epoch": 16.315181518151814, "percentage": 81.58, "elapsed_time": "5:51:19", "remaining_time": "1:19:20", "throughput": 1484.75, "total_tokens": 31297600} {"current_steps": 148310, "total_steps": 181800, "loss": 0.0485, "lr": 4.993165640010786e-06, "epoch": 16.315731573157315, "percentage": 81.58, "elapsed_time": "5:51:20", "remaining_time": "1:19:20", "throughput": 1484.75, "total_tokens": 31298624} {"current_steps": 148315, "total_steps": 181800, "loss": 0.0017, "lr": 4.991726566810953e-06, "epoch": 16.316281628162816, "percentage": 81.58, "elapsed_time": "5:51:20", "remaining_time": "1:19:19", "throughput": 1484.75, "total_tokens": 31299744} {"current_steps": 148320, "total_steps": 181800, "loss": 0.0968, "lr": 4.990287678017769e-06, "epoch": 16.316831683168317, "percentage": 81.58, "elapsed_time": "5:51:21", "remaining_time": "1:19:18", "throughput": 1484.75, "total_tokens": 31300832} {"current_steps": 148325, "total_steps": 181800, "loss": 0.0223, "lr": 4.988848973644502e-06, "epoch": 16.317381738173818, "percentage": 81.59, "elapsed_time": "5:51:22", "remaining_time": "1:19:17", "throughput": 1484.75, "total_tokens": 31301856} {"current_steps": 148330, "total_steps": 181800, "loss": 0.2289, "lr": 4.987410453704419e-06, "epoch": 16.31793179317932, "percentage": 81.59, "elapsed_time": "5:51:22", "remaining_time": "1:19:17", "throughput": 1484.76, "total_tokens": 31302976} {"current_steps": 148335, "total_steps": 181800, "loss": 0.002, "lr": 4.985972118210763e-06, "epoch": 16.318481848184817, "percentage": 81.59, "elapsed_time": "5:51:23", "remaining_time": "1:19:16", "throughput": 1484.76, "total_tokens": 31303968} {"current_steps": 148340, "total_steps": 181800, "loss": 0.011, "lr": 4.984533967176805e-06, "epoch": 16.319031903190318, "percentage": 81.6, "elapsed_time": "5:51:24", "remaining_time": "1:19:15", "throughput": 1484.76, "total_tokens": 31304960} {"current_steps": 148345, "total_steps": 181800, "loss": 0.1317, "lr": 4.983096000615789e-06, "epoch": 16.31958195819582, "percentage": 81.6, "elapsed_time": "5:51:24", "remaining_time": "1:19:15", "throughput": 1484.76, "total_tokens": 31306016} {"current_steps": 148350, "total_steps": 181800, "loss": 0.0245, "lr": 4.981658218540977e-06, "epoch": 16.32013201320132, "percentage": 81.6, "elapsed_time": "5:51:25", "remaining_time": "1:19:14", "throughput": 1484.76, "total_tokens": 31307072} {"current_steps": 148355, "total_steps": 181800, "loss": 0.0051, "lr": 4.980220620965609e-06, "epoch": 16.32068206820682, "percentage": 81.6, "elapsed_time": "5:51:26", "remaining_time": "1:19:13", "throughput": 1484.76, "total_tokens": 31308160} {"current_steps": 148360, "total_steps": 181800, "loss": 0.001, "lr": 4.97878320790294e-06, "epoch": 16.321232123212322, "percentage": 81.61, "elapsed_time": "5:51:27", "remaining_time": "1:19:12", "throughput": 1484.76, "total_tokens": 31309216} {"current_steps": 148365, "total_steps": 181800, "loss": 0.0017, "lr": 4.977345979366227e-06, "epoch": 16.321782178217823, "percentage": 81.61, "elapsed_time": "5:51:27", "remaining_time": "1:19:12", "throughput": 1484.77, "total_tokens": 31310304} {"current_steps": 148370, "total_steps": 181800, "loss": 0.0049, "lr": 4.975908935368701e-06, "epoch": 16.32233223322332, "percentage": 81.61, "elapsed_time": "5:51:28", "remaining_time": "1:19:11", "throughput": 1484.77, "total_tokens": 31311424} {"current_steps": 148375, "total_steps": 181800, "loss": 0.0394, "lr": 4.97447207592362e-06, "epoch": 16.322882288228822, "percentage": 81.61, "elapsed_time": "5:51:29", "remaining_time": "1:19:10", "throughput": 1484.77, "total_tokens": 31312448} {"current_steps": 148380, "total_steps": 181800, "loss": 0.0271, "lr": 4.973035401044216e-06, "epoch": 16.323432343234323, "percentage": 81.62, "elapsed_time": "5:51:29", "remaining_time": "1:19:10", "throughput": 1484.77, "total_tokens": 31313440} {"current_steps": 148385, "total_steps": 181800, "loss": 0.0042, "lr": 4.971598910743733e-06, "epoch": 16.323982398239824, "percentage": 81.62, "elapsed_time": "5:51:30", "remaining_time": "1:19:09", "throughput": 1484.77, "total_tokens": 31314464} {"current_steps": 148390, "total_steps": 181800, "loss": 0.0264, "lr": 4.97016260503542e-06, "epoch": 16.324532453245325, "percentage": 81.62, "elapsed_time": "5:51:31", "remaining_time": "1:19:08", "throughput": 1484.77, "total_tokens": 31315488} {"current_steps": 148395, "total_steps": 181800, "loss": 0.0417, "lr": 4.9687264839324986e-06, "epoch": 16.325082508250826, "percentage": 81.63, "elapsed_time": "5:51:31", "remaining_time": "1:19:07", "throughput": 1484.77, "total_tokens": 31316512} {"current_steps": 148400, "total_steps": 181800, "loss": 0.0294, "lr": 4.967290547448222e-06, "epoch": 16.325632563256324, "percentage": 81.63, "elapsed_time": "5:51:32", "remaining_time": "1:19:07", "throughput": 1484.77, "total_tokens": 31317536} {"current_steps": 148405, "total_steps": 181800, "loss": 0.0549, "lr": 4.965854795595815e-06, "epoch": 16.326182618261825, "percentage": 81.63, "elapsed_time": "5:51:33", "remaining_time": "1:19:06", "throughput": 1484.77, "total_tokens": 31318560} {"current_steps": 148410, "total_steps": 181800, "loss": 0.033, "lr": 4.964419228388504e-06, "epoch": 16.326732673267326, "percentage": 81.63, "elapsed_time": "5:51:33", "remaining_time": "1:19:05", "throughput": 1484.77, "total_tokens": 31319552} {"current_steps": 148415, "total_steps": 181800, "loss": 0.0231, "lr": 4.962983845839528e-06, "epoch": 16.327282728272827, "percentage": 81.64, "elapsed_time": "5:51:34", "remaining_time": "1:19:05", "throughput": 1484.77, "total_tokens": 31320576} {"current_steps": 148420, "total_steps": 181800, "loss": 0.0074, "lr": 4.961548647962114e-06, "epoch": 16.32783278327833, "percentage": 81.64, "elapsed_time": "5:51:35", "remaining_time": "1:19:04", "throughput": 1484.77, "total_tokens": 31321728} {"current_steps": 148425, "total_steps": 181800, "loss": 0.0009, "lr": 4.9601136347694975e-06, "epoch": 16.32838283828383, "percentage": 81.64, "elapsed_time": "5:51:35", "remaining_time": "1:19:03", "throughput": 1484.77, "total_tokens": 31322784} {"current_steps": 148430, "total_steps": 181800, "loss": 0.0685, "lr": 4.958678806274897e-06, "epoch": 16.32893289328933, "percentage": 81.64, "elapsed_time": "5:51:36", "remaining_time": "1:19:02", "throughput": 1484.77, "total_tokens": 31323808} {"current_steps": 148435, "total_steps": 181800, "loss": 0.0007, "lr": 4.957244162491531e-06, "epoch": 16.329482948294828, "percentage": 81.65, "elapsed_time": "5:51:37", "remaining_time": "1:19:02", "throughput": 1484.78, "total_tokens": 31324928} {"current_steps": 148440, "total_steps": 181800, "loss": 0.0043, "lr": 4.955809703432629e-06, "epoch": 16.33003300330033, "percentage": 81.65, "elapsed_time": "5:51:38", "remaining_time": "1:19:01", "throughput": 1484.78, "total_tokens": 31325920} {"current_steps": 148445, "total_steps": 181800, "loss": 0.0278, "lr": 4.954375429111419e-06, "epoch": 16.33058305830583, "percentage": 81.65, "elapsed_time": "5:51:38", "remaining_time": "1:19:00", "throughput": 1484.78, "total_tokens": 31327040} {"current_steps": 148450, "total_steps": 181800, "loss": 0.002, "lr": 4.952941339541103e-06, "epoch": 16.33113311331133, "percentage": 81.66, "elapsed_time": "5:51:39", "remaining_time": "1:19:00", "throughput": 1484.78, "total_tokens": 31328096} {"current_steps": 148455, "total_steps": 181800, "loss": 0.0023, "lr": 4.951507434734914e-06, "epoch": 16.331683168316832, "percentage": 81.66, "elapsed_time": "5:51:40", "remaining_time": "1:18:59", "throughput": 1484.79, "total_tokens": 31329152} {"current_steps": 148460, "total_steps": 181800, "loss": 0.0005, "lr": 4.950073714706055e-06, "epoch": 16.332233223322334, "percentage": 81.66, "elapsed_time": "5:51:40", "remaining_time": "1:18:58", "throughput": 1484.79, "total_tokens": 31330208} {"current_steps": 148465, "total_steps": 181800, "loss": 0.002, "lr": 4.948640179467751e-06, "epoch": 16.33278327832783, "percentage": 81.66, "elapsed_time": "5:51:41", "remaining_time": "1:18:57", "throughput": 1484.79, "total_tokens": 31331232} {"current_steps": 148470, "total_steps": 181800, "loss": 0.0101, "lr": 4.947206829033202e-06, "epoch": 16.333333333333332, "percentage": 81.67, "elapsed_time": "5:51:42", "remaining_time": "1:18:57", "throughput": 1484.79, "total_tokens": 31332352} {"current_steps": 148475, "total_steps": 181800, "loss": 0.0285, "lr": 4.945773663415626e-06, "epoch": 16.333883388338833, "percentage": 81.67, "elapsed_time": "5:51:42", "remaining_time": "1:18:56", "throughput": 1484.79, "total_tokens": 31333440} {"current_steps": 148480, "total_steps": 181800, "loss": 0.0052, "lr": 4.944340682628237e-06, "epoch": 16.334433443344334, "percentage": 81.67, "elapsed_time": "5:51:43", "remaining_time": "1:18:55", "throughput": 1484.8, "total_tokens": 31334496} {"current_steps": 148485, "total_steps": 181800, "loss": 0.0417, "lr": 4.942907886684231e-06, "epoch": 16.334983498349835, "percentage": 81.67, "elapsed_time": "5:51:44", "remaining_time": "1:18:55", "throughput": 1484.8, "total_tokens": 31335520} {"current_steps": 148490, "total_steps": 181800, "loss": 0.0083, "lr": 4.941475275596827e-06, "epoch": 16.335533553355337, "percentage": 81.68, "elapsed_time": "5:51:44", "remaining_time": "1:18:54", "throughput": 1484.8, "total_tokens": 31336608} {"current_steps": 148495, "total_steps": 181800, "loss": 0.0084, "lr": 4.9400428493792175e-06, "epoch": 16.336083608360838, "percentage": 81.68, "elapsed_time": "5:51:45", "remaining_time": "1:18:53", "throughput": 1484.8, "total_tokens": 31337664} {"current_steps": 148500, "total_steps": 181800, "loss": 0.1574, "lr": 4.9386106080445946e-06, "epoch": 16.336633663366335, "percentage": 81.68, "elapsed_time": "5:51:46", "remaining_time": "1:18:52", "throughput": 1484.8, "total_tokens": 31338720} {"current_steps": 148505, "total_steps": 181800, "loss": 0.0037, "lr": 4.9371785516061865e-06, "epoch": 16.337183718371836, "percentage": 81.69, "elapsed_time": "5:51:47", "remaining_time": "1:18:52", "throughput": 1484.8, "total_tokens": 31339776} {"current_steps": 148510, "total_steps": 181800, "loss": 0.007, "lr": 4.935746680077166e-06, "epoch": 16.337733773377337, "percentage": 81.69, "elapsed_time": "5:51:47", "remaining_time": "1:18:51", "throughput": 1484.81, "total_tokens": 31340896} {"current_steps": 148515, "total_steps": 181800, "loss": 0.0336, "lr": 4.934314993470751e-06, "epoch": 16.33828382838284, "percentage": 81.69, "elapsed_time": "5:51:48", "remaining_time": "1:18:50", "throughput": 1484.81, "total_tokens": 31342016} {"current_steps": 148520, "total_steps": 181800, "loss": 0.0608, "lr": 4.932883491800125e-06, "epoch": 16.33883388338834, "percentage": 81.69, "elapsed_time": "5:51:49", "remaining_time": "1:18:50", "throughput": 1484.82, "total_tokens": 31343104} {"current_steps": 148525, "total_steps": 181800, "loss": 0.0011, "lr": 4.931452175078474e-06, "epoch": 16.33938393839384, "percentage": 81.7, "elapsed_time": "5:51:49", "remaining_time": "1:18:49", "throughput": 1484.82, "total_tokens": 31344160} {"current_steps": 148530, "total_steps": 181800, "loss": 0.0909, "lr": 4.930021043319002e-06, "epoch": 16.33993399339934, "percentage": 81.7, "elapsed_time": "5:51:50", "remaining_time": "1:18:48", "throughput": 1484.82, "total_tokens": 31345184} {"current_steps": 148535, "total_steps": 181800, "loss": 0.0053, "lr": 4.928590096534894e-06, "epoch": 16.34048404840484, "percentage": 81.7, "elapsed_time": "5:51:51", "remaining_time": "1:18:47", "throughput": 1484.82, "total_tokens": 31346304} {"current_steps": 148540, "total_steps": 181800, "loss": 0.1027, "lr": 4.9271593347393455e-06, "epoch": 16.34103410341034, "percentage": 81.71, "elapsed_time": "5:51:51", "remaining_time": "1:18:47", "throughput": 1484.82, "total_tokens": 31347360} {"current_steps": 148545, "total_steps": 181800, "loss": 0.0544, "lr": 4.925728757945539e-06, "epoch": 16.34158415841584, "percentage": 81.71, "elapsed_time": "5:51:52", "remaining_time": "1:18:46", "throughput": 1484.82, "total_tokens": 31348384} {"current_steps": 148550, "total_steps": 181800, "loss": 0.0039, "lr": 4.924298366166652e-06, "epoch": 16.342134213421343, "percentage": 81.71, "elapsed_time": "5:51:53", "remaining_time": "1:18:45", "throughput": 1484.83, "total_tokens": 31349440} {"current_steps": 148555, "total_steps": 181800, "loss": 0.0013, "lr": 4.922868159415878e-06, "epoch": 16.342684268426844, "percentage": 81.71, "elapsed_time": "5:51:53", "remaining_time": "1:18:45", "throughput": 1484.83, "total_tokens": 31350496} {"current_steps": 148560, "total_steps": 181800, "loss": 0.0546, "lr": 4.921438137706383e-06, "epoch": 16.343234323432345, "percentage": 81.72, "elapsed_time": "5:51:54", "remaining_time": "1:18:44", "throughput": 1484.83, "total_tokens": 31351552} {"current_steps": 148565, "total_steps": 181800, "loss": 0.1594, "lr": 4.920008301051371e-06, "epoch": 16.343784378437842, "percentage": 81.72, "elapsed_time": "5:51:55", "remaining_time": "1:18:43", "throughput": 1484.83, "total_tokens": 31352640} {"current_steps": 148570, "total_steps": 181800, "loss": 0.0014, "lr": 4.918578649464006e-06, "epoch": 16.344334433443343, "percentage": 81.72, "elapsed_time": "5:51:55", "remaining_time": "1:18:42", "throughput": 1484.83, "total_tokens": 31353696} {"current_steps": 148575, "total_steps": 181800, "loss": 0.0012, "lr": 4.917149182957459e-06, "epoch": 16.344884488448844, "percentage": 81.72, "elapsed_time": "5:51:56", "remaining_time": "1:18:42", "throughput": 1484.83, "total_tokens": 31354688} {"current_steps": 148580, "total_steps": 181800, "loss": 0.0091, "lr": 4.915719901544919e-06, "epoch": 16.345434543454346, "percentage": 81.73, "elapsed_time": "5:51:57", "remaining_time": "1:18:41", "throughput": 1484.83, "total_tokens": 31355776} {"current_steps": 148585, "total_steps": 181800, "loss": 0.0578, "lr": 4.9142908052395436e-06, "epoch": 16.345984598459847, "percentage": 81.73, "elapsed_time": "5:51:58", "remaining_time": "1:18:40", "throughput": 1484.83, "total_tokens": 31356800} {"current_steps": 148590, "total_steps": 181800, "loss": 0.0477, "lr": 4.9128618940545126e-06, "epoch": 16.346534653465348, "percentage": 81.73, "elapsed_time": "5:51:58", "remaining_time": "1:18:40", "throughput": 1484.83, "total_tokens": 31357824} {"current_steps": 148595, "total_steps": 181800, "loss": 0.0076, "lr": 4.911433168003002e-06, "epoch": 16.34708470847085, "percentage": 81.74, "elapsed_time": "5:51:59", "remaining_time": "1:18:39", "throughput": 1484.84, "total_tokens": 31358912} {"current_steps": 148600, "total_steps": 181800, "loss": 0.0195, "lr": 4.910004627098164e-06, "epoch": 16.347634763476346, "percentage": 81.74, "elapsed_time": "5:52:00", "remaining_time": "1:18:38", "throughput": 1484.84, "total_tokens": 31359968} {"current_steps": 148605, "total_steps": 181800, "loss": 0.0013, "lr": 4.90857627135318e-06, "epoch": 16.348184818481847, "percentage": 81.74, "elapsed_time": "5:52:00", "remaining_time": "1:18:37", "throughput": 1484.84, "total_tokens": 31361056} {"current_steps": 148610, "total_steps": 181800, "loss": 0.0431, "lr": 4.907148100781203e-06, "epoch": 16.34873487348735, "percentage": 81.74, "elapsed_time": "5:52:01", "remaining_time": "1:18:37", "throughput": 1484.84, "total_tokens": 31362144} {"current_steps": 148615, "total_steps": 181800, "loss": 0.0065, "lr": 4.9057201153954065e-06, "epoch": 16.34928492849285, "percentage": 81.75, "elapsed_time": "5:52:02", "remaining_time": "1:18:36", "throughput": 1484.84, "total_tokens": 31363168} {"current_steps": 148620, "total_steps": 181800, "loss": 0.0007, "lr": 4.9042923152089384e-06, "epoch": 16.34983498349835, "percentage": 81.75, "elapsed_time": "5:52:02", "remaining_time": "1:18:35", "throughput": 1484.84, "total_tokens": 31364224} {"current_steps": 148625, "total_steps": 181800, "loss": 0.0014, "lr": 4.902864700234966e-06, "epoch": 16.350385038503852, "percentage": 81.75, "elapsed_time": "5:52:03", "remaining_time": "1:18:35", "throughput": 1484.84, "total_tokens": 31365216} {"current_steps": 148630, "total_steps": 181800, "loss": 0.0044, "lr": 4.90143727048665e-06, "epoch": 16.35093509350935, "percentage": 81.75, "elapsed_time": "5:52:04", "remaining_time": "1:18:34", "throughput": 1484.84, "total_tokens": 31366240} {"current_steps": 148635, "total_steps": 181800, "loss": 0.0017, "lr": 4.900010025977145e-06, "epoch": 16.35148514851485, "percentage": 81.76, "elapsed_time": "5:52:04", "remaining_time": "1:18:33", "throughput": 1484.85, "total_tokens": 31367328} {"current_steps": 148640, "total_steps": 181800, "loss": 0.1557, "lr": 4.8985829667195945e-06, "epoch": 16.35203520352035, "percentage": 81.76, "elapsed_time": "5:52:05", "remaining_time": "1:18:32", "throughput": 1484.85, "total_tokens": 31368352} {"current_steps": 148645, "total_steps": 181800, "loss": 0.0662, "lr": 4.897156092727162e-06, "epoch": 16.352585258525853, "percentage": 81.76, "elapsed_time": "5:52:06", "remaining_time": "1:18:32", "throughput": 1484.85, "total_tokens": 31369408} {"current_steps": 148650, "total_steps": 181800, "loss": 0.007, "lr": 4.895729404012992e-06, "epoch": 16.353135313531354, "percentage": 81.77, "elapsed_time": "5:52:07", "remaining_time": "1:18:31", "throughput": 1484.85, "total_tokens": 31370528} {"current_steps": 148655, "total_steps": 181800, "loss": 0.0058, "lr": 4.894302900590247e-06, "epoch": 16.353685368536855, "percentage": 81.77, "elapsed_time": "5:52:07", "remaining_time": "1:18:30", "throughput": 1484.86, "total_tokens": 31371648} {"current_steps": 148660, "total_steps": 181800, "loss": 0.0893, "lr": 4.892876582472061e-06, "epoch": 16.354235423542356, "percentage": 81.77, "elapsed_time": "5:52:08", "remaining_time": "1:18:30", "throughput": 1484.86, "total_tokens": 31372672} {"current_steps": 148665, "total_steps": 181800, "loss": 0.0159, "lr": 4.891450449671581e-06, "epoch": 16.354785478547853, "percentage": 81.77, "elapsed_time": "5:52:09", "remaining_time": "1:18:29", "throughput": 1484.86, "total_tokens": 31373728} {"current_steps": 148670, "total_steps": 181800, "loss": 0.0031, "lr": 4.890024502201956e-06, "epoch": 16.355335533553355, "percentage": 81.78, "elapsed_time": "5:52:09", "remaining_time": "1:18:28", "throughput": 1484.86, "total_tokens": 31374816} {"current_steps": 148675, "total_steps": 181800, "loss": 0.0487, "lr": 4.8885987400763195e-06, "epoch": 16.355885588558856, "percentage": 81.78, "elapsed_time": "5:52:10", "remaining_time": "1:18:27", "throughput": 1484.86, "total_tokens": 31375872} {"current_steps": 148680, "total_steps": 181800, "loss": 0.0406, "lr": 4.887173163307821e-06, "epoch": 16.356435643564357, "percentage": 81.78, "elapsed_time": "5:52:11", "remaining_time": "1:18:27", "throughput": 1484.87, "total_tokens": 31376960} {"current_steps": 148685, "total_steps": 181800, "loss": 0.0904, "lr": 4.885747771909599e-06, "epoch": 16.356985698569858, "percentage": 81.78, "elapsed_time": "5:52:11", "remaining_time": "1:18:26", "throughput": 1484.87, "total_tokens": 31378048} {"current_steps": 148690, "total_steps": 181800, "loss": 0.0667, "lr": 4.884322565894783e-06, "epoch": 16.35753575357536, "percentage": 81.79, "elapsed_time": "5:52:12", "remaining_time": "1:18:25", "throughput": 1484.87, "total_tokens": 31379168} {"current_steps": 148695, "total_steps": 181800, "loss": 0.0302, "lr": 4.882897545276522e-06, "epoch": 16.358085808580856, "percentage": 81.79, "elapsed_time": "5:52:13", "remaining_time": "1:18:25", "throughput": 1484.87, "total_tokens": 31380192} {"current_steps": 148700, "total_steps": 181800, "loss": 0.0028, "lr": 4.8814727100679304e-06, "epoch": 16.358635863586358, "percentage": 81.79, "elapsed_time": "5:52:13", "remaining_time": "1:18:24", "throughput": 1484.88, "total_tokens": 31381312} {"current_steps": 148705, "total_steps": 181800, "loss": 0.0236, "lr": 4.880048060282153e-06, "epoch": 16.35918591859186, "percentage": 81.8, "elapsed_time": "5:52:14", "remaining_time": "1:18:23", "throughput": 1484.88, "total_tokens": 31382368} {"current_steps": 148710, "total_steps": 181800, "loss": 0.0497, "lr": 4.878623595932324e-06, "epoch": 16.35973597359736, "percentage": 81.8, "elapsed_time": "5:52:15", "remaining_time": "1:18:22", "throughput": 1484.88, "total_tokens": 31383424} {"current_steps": 148715, "total_steps": 181800, "loss": 0.0084, "lr": 4.877199317031561e-06, "epoch": 16.36028602860286, "percentage": 81.8, "elapsed_time": "5:52:16", "remaining_time": "1:18:22", "throughput": 1484.88, "total_tokens": 31384512} {"current_steps": 148720, "total_steps": 181800, "loss": 0.0502, "lr": 4.875775223593004e-06, "epoch": 16.360836083608362, "percentage": 81.8, "elapsed_time": "5:52:16", "remaining_time": "1:18:21", "throughput": 1484.88, "total_tokens": 31385536} {"current_steps": 148725, "total_steps": 181800, "loss": 0.1052, "lr": 4.8743513156297605e-06, "epoch": 16.361386138613863, "percentage": 81.81, "elapsed_time": "5:52:17", "remaining_time": "1:18:20", "throughput": 1484.89, "total_tokens": 31386656} {"current_steps": 148730, "total_steps": 181800, "loss": 0.1283, "lr": 4.8729275931549715e-06, "epoch": 16.36193619361936, "percentage": 81.81, "elapsed_time": "5:52:18", "remaining_time": "1:18:20", "throughput": 1484.89, "total_tokens": 31387744} {"current_steps": 148735, "total_steps": 181800, "loss": 0.0174, "lr": 4.871504056181747e-06, "epoch": 16.36248624862486, "percentage": 81.81, "elapsed_time": "5:52:18", "remaining_time": "1:18:19", "throughput": 1484.89, "total_tokens": 31388736} {"current_steps": 148740, "total_steps": 181800, "loss": 0.0423, "lr": 4.8700807047232065e-06, "epoch": 16.363036303630363, "percentage": 81.82, "elapsed_time": "5:52:19", "remaining_time": "1:18:18", "throughput": 1484.89, "total_tokens": 31389760} {"current_steps": 148745, "total_steps": 181800, "loss": 0.0673, "lr": 4.868657538792482e-06, "epoch": 16.363586358635864, "percentage": 81.82, "elapsed_time": "5:52:20", "remaining_time": "1:18:17", "throughput": 1484.89, "total_tokens": 31390816} {"current_steps": 148750, "total_steps": 181800, "loss": 0.0053, "lr": 4.867234558402675e-06, "epoch": 16.364136413641365, "percentage": 81.82, "elapsed_time": "5:52:20", "remaining_time": "1:18:17", "throughput": 1484.89, "total_tokens": 31391872} {"current_steps": 148755, "total_steps": 181800, "loss": 0.0335, "lr": 4.86581176356691e-06, "epoch": 16.364686468646866, "percentage": 81.82, "elapsed_time": "5:52:21", "remaining_time": "1:18:16", "throughput": 1484.89, "total_tokens": 31392928} {"current_steps": 148760, "total_steps": 181800, "loss": 0.1192, "lr": 4.8643891542982935e-06, "epoch": 16.365236523652364, "percentage": 81.83, "elapsed_time": "5:52:22", "remaining_time": "1:18:15", "throughput": 1484.89, "total_tokens": 31393952} {"current_steps": 148765, "total_steps": 181800, "loss": 0.0037, "lr": 4.862966730609938e-06, "epoch": 16.365786578657865, "percentage": 81.83, "elapsed_time": "5:52:22", "remaining_time": "1:18:15", "throughput": 1484.89, "total_tokens": 31395008} {"current_steps": 148770, "total_steps": 181800, "loss": 0.002, "lr": 4.861544492514963e-06, "epoch": 16.366336633663366, "percentage": 81.83, "elapsed_time": "5:52:23", "remaining_time": "1:18:14", "throughput": 1484.9, "total_tokens": 31396064} {"current_steps": 148775, "total_steps": 181800, "loss": 0.0828, "lr": 4.8601224400264625e-06, "epoch": 16.366886688668867, "percentage": 81.83, "elapsed_time": "5:52:24", "remaining_time": "1:18:13", "throughput": 1484.9, "total_tokens": 31397152} {"current_steps": 148780, "total_steps": 181800, "loss": 0.0017, "lr": 4.858700573157557e-06, "epoch": 16.367436743674368, "percentage": 81.84, "elapsed_time": "5:52:25", "remaining_time": "1:18:12", "throughput": 1484.9, "total_tokens": 31398208} {"current_steps": 148785, "total_steps": 181800, "loss": 0.0993, "lr": 4.8572788919213404e-06, "epoch": 16.36798679867987, "percentage": 81.84, "elapsed_time": "5:52:25", "remaining_time": "1:18:12", "throughput": 1484.9, "total_tokens": 31399296} {"current_steps": 148790, "total_steps": 181800, "loss": 0.0031, "lr": 4.855857396330915e-06, "epoch": 16.36853685368537, "percentage": 81.84, "elapsed_time": "5:52:26", "remaining_time": "1:18:11", "throughput": 1484.9, "total_tokens": 31400352} {"current_steps": 148795, "total_steps": 181800, "loss": 0.1941, "lr": 4.854436086399386e-06, "epoch": 16.369086908690868, "percentage": 81.85, "elapsed_time": "5:52:27", "remaining_time": "1:18:10", "throughput": 1484.91, "total_tokens": 31401408} {"current_steps": 148800, "total_steps": 181800, "loss": 0.2273, "lr": 4.853014962139851e-06, "epoch": 16.36963696369637, "percentage": 81.85, "elapsed_time": "5:52:27", "remaining_time": "1:18:10", "throughput": 1484.91, "total_tokens": 31402592} {"current_steps": 148805, "total_steps": 181800, "loss": 0.0096, "lr": 4.851594023565418e-06, "epoch": 16.37018701870187, "percentage": 81.85, "elapsed_time": "5:52:28", "remaining_time": "1:18:09", "throughput": 1484.91, "total_tokens": 31403552} {"current_steps": 148810, "total_steps": 181800, "loss": 0.043, "lr": 4.8501732706891735e-06, "epoch": 16.37073707370737, "percentage": 81.85, "elapsed_time": "5:52:29", "remaining_time": "1:18:08", "throughput": 1484.91, "total_tokens": 31404640} {"current_steps": 148815, "total_steps": 181800, "loss": 0.0022, "lr": 4.848752703524207e-06, "epoch": 16.371287128712872, "percentage": 81.86, "elapsed_time": "5:52:29", "remaining_time": "1:18:07", "throughput": 1484.91, "total_tokens": 31405632} {"current_steps": 148820, "total_steps": 181800, "loss": 0.0078, "lr": 4.847332322083617e-06, "epoch": 16.371837183718373, "percentage": 81.86, "elapsed_time": "5:52:30", "remaining_time": "1:18:07", "throughput": 1484.91, "total_tokens": 31406688} {"current_steps": 148825, "total_steps": 181800, "loss": 0.1027, "lr": 4.845912126380495e-06, "epoch": 16.37238723872387, "percentage": 81.86, "elapsed_time": "5:52:31", "remaining_time": "1:18:06", "throughput": 1484.91, "total_tokens": 31407712} {"current_steps": 148830, "total_steps": 181800, "loss": 0.008, "lr": 4.844492116427934e-06, "epoch": 16.372937293729372, "percentage": 81.86, "elapsed_time": "5:52:31", "remaining_time": "1:18:05", "throughput": 1484.92, "total_tokens": 31408832} {"current_steps": 148835, "total_steps": 181800, "loss": 0.0366, "lr": 4.8430722922390235e-06, "epoch": 16.373487348734873, "percentage": 81.87, "elapsed_time": "5:52:32", "remaining_time": "1:18:05", "throughput": 1484.92, "total_tokens": 31409888} {"current_steps": 148840, "total_steps": 181800, "loss": 0.0016, "lr": 4.841652653826831e-06, "epoch": 16.374037403740374, "percentage": 81.87, "elapsed_time": "5:52:33", "remaining_time": "1:18:04", "throughput": 1484.92, "total_tokens": 31410944} {"current_steps": 148845, "total_steps": 181800, "loss": 0.0576, "lr": 4.840233201204464e-06, "epoch": 16.374587458745875, "percentage": 81.87, "elapsed_time": "5:52:33", "remaining_time": "1:18:03", "throughput": 1484.92, "total_tokens": 31412000} {"current_steps": 148850, "total_steps": 181800, "loss": 0.0015, "lr": 4.838813934384983e-06, "epoch": 16.375137513751376, "percentage": 81.88, "elapsed_time": "5:52:34", "remaining_time": "1:18:02", "throughput": 1484.92, "total_tokens": 31413056} {"current_steps": 148855, "total_steps": 181800, "loss": 0.0971, "lr": 4.837394853381485e-06, "epoch": 16.375687568756877, "percentage": 81.88, "elapsed_time": "5:52:35", "remaining_time": "1:18:02", "throughput": 1484.93, "total_tokens": 31414144} {"current_steps": 148860, "total_steps": 181800, "loss": 0.0898, "lr": 4.835975958207048e-06, "epoch": 16.376237623762375, "percentage": 81.88, "elapsed_time": "5:52:36", "remaining_time": "1:18:01", "throughput": 1484.93, "total_tokens": 31415168} {"current_steps": 148865, "total_steps": 181800, "loss": 0.0135, "lr": 4.834557248874738e-06, "epoch": 16.376787678767876, "percentage": 81.88, "elapsed_time": "5:52:36", "remaining_time": "1:18:00", "throughput": 1484.93, "total_tokens": 31416224} {"current_steps": 148870, "total_steps": 181800, "loss": 0.0025, "lr": 4.833138725397643e-06, "epoch": 16.377337733773377, "percentage": 81.89, "elapsed_time": "5:52:37", "remaining_time": "1:18:00", "throughput": 1484.93, "total_tokens": 31417248} {"current_steps": 148875, "total_steps": 181800, "loss": 0.0021, "lr": 4.831720387788827e-06, "epoch": 16.377887788778878, "percentage": 81.89, "elapsed_time": "5:52:38", "remaining_time": "1:17:59", "throughput": 1484.93, "total_tokens": 31418272} {"current_steps": 148880, "total_steps": 181800, "loss": 0.0028, "lr": 4.830302236061365e-06, "epoch": 16.37843784378438, "percentage": 81.89, "elapsed_time": "5:52:38", "remaining_time": "1:17:58", "throughput": 1484.93, "total_tokens": 31419296} {"current_steps": 148885, "total_steps": 181800, "loss": 0.0007, "lr": 4.828884270228334e-06, "epoch": 16.37898789878988, "percentage": 81.89, "elapsed_time": "5:52:39", "remaining_time": "1:17:57", "throughput": 1484.93, "total_tokens": 31420320} {"current_steps": 148890, "total_steps": 181800, "loss": 0.0026, "lr": 4.827466490302792e-06, "epoch": 16.379537953795378, "percentage": 81.9, "elapsed_time": "5:52:40", "remaining_time": "1:17:57", "throughput": 1484.92, "total_tokens": 31421312} {"current_steps": 148895, "total_steps": 181800, "loss": 0.0139, "lr": 4.826048896297821e-06, "epoch": 16.38008800880088, "percentage": 81.9, "elapsed_time": "5:52:40", "remaining_time": "1:17:56", "throughput": 1484.93, "total_tokens": 31422368} {"current_steps": 148900, "total_steps": 181800, "loss": 0.0151, "lr": 4.824631488226475e-06, "epoch": 16.38063806380638, "percentage": 81.9, "elapsed_time": "5:52:41", "remaining_time": "1:17:55", "throughput": 1484.93, "total_tokens": 31423456} {"current_steps": 148905, "total_steps": 181800, "loss": 0.0015, "lr": 4.823214266101814e-06, "epoch": 16.38118811881188, "percentage": 81.91, "elapsed_time": "5:52:42", "remaining_time": "1:17:55", "throughput": 1484.93, "total_tokens": 31424576} {"current_steps": 148910, "total_steps": 181800, "loss": 0.015, "lr": 4.821797229936903e-06, "epoch": 16.381738173817382, "percentage": 81.91, "elapsed_time": "5:52:42", "remaining_time": "1:17:54", "throughput": 1484.94, "total_tokens": 31425632} {"current_steps": 148915, "total_steps": 181800, "loss": 0.0034, "lr": 4.820380379744807e-06, "epoch": 16.382288228822883, "percentage": 81.91, "elapsed_time": "5:52:43", "remaining_time": "1:17:53", "throughput": 1484.94, "total_tokens": 31426720} {"current_steps": 148920, "total_steps": 181800, "loss": 0.0009, "lr": 4.818963715538586e-06, "epoch": 16.382838283828384, "percentage": 81.91, "elapsed_time": "5:52:44", "remaining_time": "1:17:52", "throughput": 1484.94, "total_tokens": 31427744} {"current_steps": 148925, "total_steps": 181800, "loss": 0.0008, "lr": 4.817547237331293e-06, "epoch": 16.383388338833882, "percentage": 81.92, "elapsed_time": "5:52:45", "remaining_time": "1:17:52", "throughput": 1484.94, "total_tokens": 31428832} {"current_steps": 148930, "total_steps": 181800, "loss": 0.0226, "lr": 4.816130945135977e-06, "epoch": 16.383938393839383, "percentage": 81.92, "elapsed_time": "5:52:45", "remaining_time": "1:17:51", "throughput": 1484.94, "total_tokens": 31429920} {"current_steps": 148935, "total_steps": 181800, "loss": 0.1302, "lr": 4.814714838965698e-06, "epoch": 16.384488448844884, "percentage": 81.92, "elapsed_time": "5:52:46", "remaining_time": "1:17:50", "throughput": 1484.95, "total_tokens": 31431008} {"current_steps": 148940, "total_steps": 181800, "loss": 0.0023, "lr": 4.813298918833506e-06, "epoch": 16.385038503850385, "percentage": 81.93, "elapsed_time": "5:52:47", "remaining_time": "1:17:50", "throughput": 1484.95, "total_tokens": 31432064} {"current_steps": 148945, "total_steps": 181800, "loss": 0.0503, "lr": 4.811883184752458e-06, "epoch": 16.385588558855886, "percentage": 81.93, "elapsed_time": "5:52:47", "remaining_time": "1:17:49", "throughput": 1484.95, "total_tokens": 31433152} {"current_steps": 148950, "total_steps": 181800, "loss": 0.0052, "lr": 4.810467636735594e-06, "epoch": 16.386138613861387, "percentage": 81.93, "elapsed_time": "5:52:48", "remaining_time": "1:17:48", "throughput": 1484.95, "total_tokens": 31434208} {"current_steps": 148955, "total_steps": 181800, "loss": 0.001, "lr": 4.809052274795956e-06, "epoch": 16.38668866886689, "percentage": 81.93, "elapsed_time": "5:52:49", "remaining_time": "1:17:47", "throughput": 1484.96, "total_tokens": 31435296} {"current_steps": 148960, "total_steps": 181800, "loss": 0.0057, "lr": 4.807637098946602e-06, "epoch": 16.387238723872386, "percentage": 81.94, "elapsed_time": "5:52:49", "remaining_time": "1:17:47", "throughput": 1484.95, "total_tokens": 31436288} {"current_steps": 148965, "total_steps": 181800, "loss": 0.0027, "lr": 4.806222109200559e-06, "epoch": 16.387788778877887, "percentage": 81.94, "elapsed_time": "5:52:50", "remaining_time": "1:17:46", "throughput": 1484.96, "total_tokens": 31437376} {"current_steps": 148970, "total_steps": 181800, "loss": 0.006, "lr": 4.80480730557088e-06, "epoch": 16.388338833883388, "percentage": 81.94, "elapsed_time": "5:52:51", "remaining_time": "1:17:45", "throughput": 1484.96, "total_tokens": 31438400} {"current_steps": 148975, "total_steps": 181800, "loss": 0.1738, "lr": 4.803392688070605e-06, "epoch": 16.38888888888889, "percentage": 81.94, "elapsed_time": "5:52:51", "remaining_time": "1:17:45", "throughput": 1484.96, "total_tokens": 31439392} {"current_steps": 148980, "total_steps": 181800, "loss": 0.0042, "lr": 4.801978256712764e-06, "epoch": 16.38943894389439, "percentage": 81.95, "elapsed_time": "5:52:52", "remaining_time": "1:17:44", "throughput": 1484.96, "total_tokens": 31440416} {"current_steps": 148985, "total_steps": 181800, "loss": 0.0099, "lr": 4.800564011510403e-06, "epoch": 16.38998899889989, "percentage": 81.95, "elapsed_time": "5:52:53", "remaining_time": "1:17:43", "throughput": 1484.95, "total_tokens": 31441408} {"current_steps": 148990, "total_steps": 181800, "loss": 0.0137, "lr": 4.799149952476545e-06, "epoch": 16.39053905390539, "percentage": 81.95, "elapsed_time": "5:52:54", "remaining_time": "1:17:42", "throughput": 1484.96, "total_tokens": 31442496} {"current_steps": 148995, "total_steps": 181800, "loss": 0.003, "lr": 4.797736079624227e-06, "epoch": 16.39108910891089, "percentage": 81.96, "elapsed_time": "5:52:54", "remaining_time": "1:17:42", "throughput": 1484.96, "total_tokens": 31443520} {"current_steps": 149000, "total_steps": 181800, "loss": 0.0019, "lr": 4.7963223929664875e-06, "epoch": 16.39163916391639, "percentage": 81.96, "elapsed_time": "5:52:55", "remaining_time": "1:17:41", "throughput": 1484.96, "total_tokens": 31444576} {"current_steps": 149005, "total_steps": 181800, "loss": 0.0567, "lr": 4.794908892516345e-06, "epoch": 16.392189218921892, "percentage": 81.96, "elapsed_time": "5:52:56", "remaining_time": "1:17:40", "throughput": 1484.96, "total_tokens": 31445600} {"current_steps": 149010, "total_steps": 181800, "loss": 0.0256, "lr": 4.793495578286838e-06, "epoch": 16.392739273927393, "percentage": 81.96, "elapsed_time": "5:52:56", "remaining_time": "1:17:39", "throughput": 1484.96, "total_tokens": 31446688} {"current_steps": 149015, "total_steps": 181800, "loss": 0.0025, "lr": 4.792082450290983e-06, "epoch": 16.393289328932894, "percentage": 81.97, "elapsed_time": "5:52:57", "remaining_time": "1:17:39", "throughput": 1484.97, "total_tokens": 31447808} {"current_steps": 149020, "total_steps": 181800, "loss": 0.003, "lr": 4.790669508541809e-06, "epoch": 16.393839383938396, "percentage": 81.97, "elapsed_time": "5:52:58", "remaining_time": "1:17:38", "throughput": 1484.97, "total_tokens": 31448832} {"current_steps": 149025, "total_steps": 181800, "loss": 0.0072, "lr": 4.7892567530523316e-06, "epoch": 16.394389438943893, "percentage": 81.97, "elapsed_time": "5:52:58", "remaining_time": "1:17:37", "throughput": 1484.96, "total_tokens": 31449824} {"current_steps": 149030, "total_steps": 181800, "loss": 0.0037, "lr": 4.787844183835577e-06, "epoch": 16.394939493949394, "percentage": 81.97, "elapsed_time": "5:52:59", "remaining_time": "1:17:37", "throughput": 1484.96, "total_tokens": 31450848} {"current_steps": 149035, "total_steps": 181800, "loss": 0.0844, "lr": 4.7864318009045725e-06, "epoch": 16.395489548954895, "percentage": 81.98, "elapsed_time": "5:53:00", "remaining_time": "1:17:36", "throughput": 1484.97, "total_tokens": 31451936} {"current_steps": 149040, "total_steps": 181800, "loss": 0.0054, "lr": 4.785019604272323e-06, "epoch": 16.396039603960396, "percentage": 81.98, "elapsed_time": "5:53:00", "remaining_time": "1:17:35", "throughput": 1484.97, "total_tokens": 31453024} {"current_steps": 149045, "total_steps": 181800, "loss": 0.0825, "lr": 4.783607593951844e-06, "epoch": 16.396589658965897, "percentage": 81.98, "elapsed_time": "5:53:01", "remaining_time": "1:17:34", "throughput": 1484.97, "total_tokens": 31454048} {"current_steps": 149050, "total_steps": 181800, "loss": 0.0446, "lr": 4.782195769956152e-06, "epoch": 16.3971397139714, "percentage": 81.99, "elapsed_time": "5:53:02", "remaining_time": "1:17:34", "throughput": 1484.97, "total_tokens": 31455168} {"current_steps": 149055, "total_steps": 181800, "loss": 0.0046, "lr": 4.78078413229826e-06, "epoch": 16.397689768976896, "percentage": 81.99, "elapsed_time": "5:53:02", "remaining_time": "1:17:33", "throughput": 1484.98, "total_tokens": 31456224} {"current_steps": 149060, "total_steps": 181800, "loss": 0.073, "lr": 4.779372680991184e-06, "epoch": 16.398239823982397, "percentage": 81.99, "elapsed_time": "5:53:03", "remaining_time": "1:17:32", "throughput": 1484.98, "total_tokens": 31457248} {"current_steps": 149065, "total_steps": 181800, "loss": 0.0075, "lr": 4.77796141604793e-06, "epoch": 16.3987898789879, "percentage": 81.99, "elapsed_time": "5:53:04", "remaining_time": "1:17:32", "throughput": 1484.98, "total_tokens": 31458304} {"current_steps": 149070, "total_steps": 181800, "loss": 0.0411, "lr": 4.7765503374814915e-06, "epoch": 16.3993399339934, "percentage": 82.0, "elapsed_time": "5:53:05", "remaining_time": "1:17:31", "throughput": 1484.98, "total_tokens": 31459360} {"current_steps": 149075, "total_steps": 181800, "loss": 0.0405, "lr": 4.775139445304894e-06, "epoch": 16.3998899889989, "percentage": 82.0, "elapsed_time": "5:53:05", "remaining_time": "1:17:30", "throughput": 1484.98, "total_tokens": 31460416} {"current_steps": 149080, "total_steps": 181800, "loss": 0.0389, "lr": 4.773728739531125e-06, "epoch": 16.4004400440044, "percentage": 82.0, "elapsed_time": "5:53:06", "remaining_time": "1:17:29", "throughput": 1484.98, "total_tokens": 31461472} {"current_steps": 149085, "total_steps": 181800, "loss": 0.0072, "lr": 4.772318220173192e-06, "epoch": 16.400990099009903, "percentage": 82.0, "elapsed_time": "5:53:07", "remaining_time": "1:17:29", "throughput": 1484.98, "total_tokens": 31462496} {"current_steps": 149090, "total_steps": 181800, "loss": 0.0556, "lr": 4.770907887244103e-06, "epoch": 16.4015401540154, "percentage": 82.01, "elapsed_time": "5:53:07", "remaining_time": "1:17:28", "throughput": 1484.98, "total_tokens": 31463552} {"current_steps": 149095, "total_steps": 181800, "loss": 0.0116, "lr": 4.769497740756842e-06, "epoch": 16.4020902090209, "percentage": 82.01, "elapsed_time": "5:53:08", "remaining_time": "1:17:27", "throughput": 1484.99, "total_tokens": 31464672} {"current_steps": 149100, "total_steps": 181800, "loss": 0.0011, "lr": 4.768087780724418e-06, "epoch": 16.402640264026402, "percentage": 82.01, "elapsed_time": "5:53:09", "remaining_time": "1:17:27", "throughput": 1484.99, "total_tokens": 31465696} {"current_steps": 149105, "total_steps": 181800, "loss": 0.0073, "lr": 4.7666780071598165e-06, "epoch": 16.403190319031903, "percentage": 82.02, "elapsed_time": "5:53:09", "remaining_time": "1:17:26", "throughput": 1484.99, "total_tokens": 31466720} {"current_steps": 149110, "total_steps": 181800, "loss": 0.0031, "lr": 4.765268420076033e-06, "epoch": 16.403740374037405, "percentage": 82.02, "elapsed_time": "5:53:10", "remaining_time": "1:17:25", "throughput": 1484.99, "total_tokens": 31467712} {"current_steps": 149115, "total_steps": 181800, "loss": 0.0988, "lr": 4.76385901948607e-06, "epoch": 16.404290429042906, "percentage": 82.02, "elapsed_time": "5:53:11", "remaining_time": "1:17:24", "throughput": 1484.99, "total_tokens": 31468736} {"current_steps": 149120, "total_steps": 181800, "loss": 0.0366, "lr": 4.762449805402899e-06, "epoch": 16.404840484048403, "percentage": 82.02, "elapsed_time": "5:53:11", "remaining_time": "1:17:24", "throughput": 1484.99, "total_tokens": 31469824} {"current_steps": 149125, "total_steps": 181800, "loss": 0.217, "lr": 4.761040777839523e-06, "epoch": 16.405390539053904, "percentage": 82.03, "elapsed_time": "5:53:12", "remaining_time": "1:17:23", "throughput": 1484.99, "total_tokens": 31470912} {"current_steps": 149130, "total_steps": 181800, "loss": 0.2103, "lr": 4.759631936808917e-06, "epoch": 16.405940594059405, "percentage": 82.03, "elapsed_time": "5:53:13", "remaining_time": "1:17:22", "throughput": 1485.0, "total_tokens": 31472000} {"current_steps": 149135, "total_steps": 181800, "loss": 0.0112, "lr": 4.758223282324078e-06, "epoch": 16.406490649064907, "percentage": 82.03, "elapsed_time": "5:53:14", "remaining_time": "1:17:22", "throughput": 1485.0, "total_tokens": 31473056} {"current_steps": 149140, "total_steps": 181800, "loss": 0.0019, "lr": 4.756814814397978e-06, "epoch": 16.407040704070408, "percentage": 82.04, "elapsed_time": "5:53:14", "remaining_time": "1:17:21", "throughput": 1485.0, "total_tokens": 31474208} {"current_steps": 149145, "total_steps": 181800, "loss": 0.0989, "lr": 4.7554065330435994e-06, "epoch": 16.40759075907591, "percentage": 82.04, "elapsed_time": "5:53:15", "remaining_time": "1:17:20", "throughput": 1485.0, "total_tokens": 31475264} {"current_steps": 149150, "total_steps": 181800, "loss": 0.0082, "lr": 4.753998438273932e-06, "epoch": 16.40814081408141, "percentage": 82.04, "elapsed_time": "5:53:16", "remaining_time": "1:17:19", "throughput": 1485.01, "total_tokens": 31476352} {"current_steps": 149155, "total_steps": 181800, "loss": 0.0447, "lr": 4.752590530101939e-06, "epoch": 16.408690869086907, "percentage": 82.04, "elapsed_time": "5:53:16", "remaining_time": "1:17:19", "throughput": 1485.01, "total_tokens": 31477408} {"current_steps": 149160, "total_steps": 181800, "loss": 0.0347, "lr": 4.751182808540611e-06, "epoch": 16.40924092409241, "percentage": 82.05, "elapsed_time": "5:53:17", "remaining_time": "1:17:18", "throughput": 1485.01, "total_tokens": 31478464} {"current_steps": 149165, "total_steps": 181800, "loss": 0.0377, "lr": 4.749775273602908e-06, "epoch": 16.40979097909791, "percentage": 82.05, "elapsed_time": "5:53:18", "remaining_time": "1:17:17", "throughput": 1485.01, "total_tokens": 31479456} {"current_steps": 149170, "total_steps": 181800, "loss": 0.0223, "lr": 4.748367925301809e-06, "epoch": 16.41034103410341, "percentage": 82.05, "elapsed_time": "5:53:18", "remaining_time": "1:17:17", "throughput": 1485.01, "total_tokens": 31480576} {"current_steps": 149175, "total_steps": 181800, "loss": 0.0485, "lr": 4.746960763650291e-06, "epoch": 16.41089108910891, "percentage": 82.05, "elapsed_time": "5:53:19", "remaining_time": "1:17:16", "throughput": 1485.01, "total_tokens": 31481600} {"current_steps": 149180, "total_steps": 181800, "loss": 0.0075, "lr": 4.745553788661309e-06, "epoch": 16.411441144114413, "percentage": 82.06, "elapsed_time": "5:53:20", "remaining_time": "1:17:15", "throughput": 1485.01, "total_tokens": 31482624} {"current_steps": 149185, "total_steps": 181800, "loss": 0.0662, "lr": 4.744147000347848e-06, "epoch": 16.41199119911991, "percentage": 82.06, "elapsed_time": "5:53:20", "remaining_time": "1:17:14", "throughput": 1485.02, "total_tokens": 31483744} {"current_steps": 149190, "total_steps": 181800, "loss": 0.0588, "lr": 4.742740398722864e-06, "epoch": 16.41254125412541, "percentage": 82.06, "elapsed_time": "5:53:21", "remaining_time": "1:17:14", "throughput": 1485.02, "total_tokens": 31484800} {"current_steps": 149195, "total_steps": 181800, "loss": 0.0361, "lr": 4.7413339837993145e-06, "epoch": 16.413091309130913, "percentage": 82.07, "elapsed_time": "5:53:22", "remaining_time": "1:17:13", "throughput": 1485.02, "total_tokens": 31485888} {"current_steps": 149200, "total_steps": 181800, "loss": 0.0028, "lr": 4.739927755590168e-06, "epoch": 16.413641364136414, "percentage": 82.07, "elapsed_time": "5:53:22", "remaining_time": "1:17:12", "throughput": 1485.02, "total_tokens": 31486912} {"current_steps": 149205, "total_steps": 181800, "loss": 0.0363, "lr": 4.738521714108387e-06, "epoch": 16.414191419141915, "percentage": 82.07, "elapsed_time": "5:53:23", "remaining_time": "1:17:12", "throughput": 1485.02, "total_tokens": 31487904} {"current_steps": 149210, "total_steps": 181800, "loss": 0.0024, "lr": 4.737115859366934e-06, "epoch": 16.414741474147416, "percentage": 82.07, "elapsed_time": "5:53:24", "remaining_time": "1:17:11", "throughput": 1485.02, "total_tokens": 31488928} {"current_steps": 149215, "total_steps": 181800, "loss": 0.0393, "lr": 4.735710191378761e-06, "epoch": 16.415291529152917, "percentage": 82.08, "elapsed_time": "5:53:25", "remaining_time": "1:17:10", "throughput": 1485.02, "total_tokens": 31489984} {"current_steps": 149220, "total_steps": 181800, "loss": 0.0016, "lr": 4.73430471015682e-06, "epoch": 16.415841584158414, "percentage": 82.08, "elapsed_time": "5:53:25", "remaining_time": "1:17:09", "throughput": 1485.02, "total_tokens": 31491008} {"current_steps": 149225, "total_steps": 181800, "loss": 0.0009, "lr": 4.732899415714065e-06, "epoch": 16.416391639163916, "percentage": 82.08, "elapsed_time": "5:53:26", "remaining_time": "1:17:09", "throughput": 1485.02, "total_tokens": 31492064} {"current_steps": 149230, "total_steps": 181800, "loss": 0.0283, "lr": 4.7314943080634585e-06, "epoch": 16.416941694169417, "percentage": 82.08, "elapsed_time": "5:53:27", "remaining_time": "1:17:08", "throughput": 1485.02, "total_tokens": 31493056} {"current_steps": 149235, "total_steps": 181800, "loss": 0.0797, "lr": 4.730089387217937e-06, "epoch": 16.417491749174918, "percentage": 82.09, "elapsed_time": "5:53:27", "remaining_time": "1:17:07", "throughput": 1485.02, "total_tokens": 31494080} {"current_steps": 149240, "total_steps": 181800, "loss": 0.0049, "lr": 4.72868465319046e-06, "epoch": 16.41804180418042, "percentage": 82.09, "elapsed_time": "5:53:28", "remaining_time": "1:17:07", "throughput": 1485.03, "total_tokens": 31495168} {"current_steps": 149245, "total_steps": 181800, "loss": 0.0195, "lr": 4.727280105993964e-06, "epoch": 16.41859185918592, "percentage": 82.09, "elapsed_time": "5:53:29", "remaining_time": "1:17:06", "throughput": 1485.03, "total_tokens": 31496192} {"current_steps": 149250, "total_steps": 181800, "loss": 0.0106, "lr": 4.725875745641406e-06, "epoch": 16.419141914191417, "percentage": 82.1, "elapsed_time": "5:53:29", "remaining_time": "1:17:05", "throughput": 1485.03, "total_tokens": 31497248} {"current_steps": 149255, "total_steps": 181800, "loss": 0.0023, "lr": 4.724471572145717e-06, "epoch": 16.41969196919692, "percentage": 82.1, "elapsed_time": "5:53:30", "remaining_time": "1:17:04", "throughput": 1485.03, "total_tokens": 31498272} {"current_steps": 149260, "total_steps": 181800, "loss": 0.005, "lr": 4.723067585519844e-06, "epoch": 16.42024202420242, "percentage": 82.1, "elapsed_time": "5:53:31", "remaining_time": "1:17:04", "throughput": 1485.03, "total_tokens": 31499328} {"current_steps": 149265, "total_steps": 181800, "loss": 0.0023, "lr": 4.721663785776734e-06, "epoch": 16.42079207920792, "percentage": 82.1, "elapsed_time": "5:53:31", "remaining_time": "1:17:03", "throughput": 1485.03, "total_tokens": 31500384} {"current_steps": 149270, "total_steps": 181800, "loss": 0.0028, "lr": 4.7202601729293115e-06, "epoch": 16.421342134213422, "percentage": 82.11, "elapsed_time": "5:53:32", "remaining_time": "1:17:02", "throughput": 1485.03, "total_tokens": 31501504} {"current_steps": 149275, "total_steps": 181800, "loss": 0.0095, "lr": 4.718856746990524e-06, "epoch": 16.421892189218923, "percentage": 82.11, "elapsed_time": "5:53:33", "remaining_time": "1:17:02", "throughput": 1485.03, "total_tokens": 31502496} {"current_steps": 149280, "total_steps": 181800, "loss": 0.0042, "lr": 4.7174535079733045e-06, "epoch": 16.422442244224424, "percentage": 82.11, "elapsed_time": "5:53:34", "remaining_time": "1:17:01", "throughput": 1485.04, "total_tokens": 31503616} {"current_steps": 149285, "total_steps": 181800, "loss": 0.012, "lr": 4.71605045589057e-06, "epoch": 16.42299229922992, "percentage": 82.11, "elapsed_time": "5:53:34", "remaining_time": "1:17:00", "throughput": 1485.04, "total_tokens": 31504704} {"current_steps": 149290, "total_steps": 181800, "loss": 0.0109, "lr": 4.714647590755278e-06, "epoch": 16.423542354235423, "percentage": 82.12, "elapsed_time": "5:53:35", "remaining_time": "1:16:59", "throughput": 1485.04, "total_tokens": 31505760} {"current_steps": 149295, "total_steps": 181800, "loss": 0.0032, "lr": 4.713244912580339e-06, "epoch": 16.424092409240924, "percentage": 82.12, "elapsed_time": "5:53:36", "remaining_time": "1:16:59", "throughput": 1485.04, "total_tokens": 31506784} {"current_steps": 149300, "total_steps": 181800, "loss": 0.0081, "lr": 4.711842421378696e-06, "epoch": 16.424642464246425, "percentage": 82.12, "elapsed_time": "5:53:36", "remaining_time": "1:16:58", "throughput": 1485.05, "total_tokens": 31507904} {"current_steps": 149305, "total_steps": 181800, "loss": 0.0171, "lr": 4.710440117163262e-06, "epoch": 16.425192519251926, "percentage": 82.13, "elapsed_time": "5:53:37", "remaining_time": "1:16:57", "throughput": 1485.05, "total_tokens": 31508960} {"current_steps": 149310, "total_steps": 181800, "loss": 0.1854, "lr": 4.70903799994696e-06, "epoch": 16.425742574257427, "percentage": 82.13, "elapsed_time": "5:53:38", "remaining_time": "1:16:57", "throughput": 1485.05, "total_tokens": 31510016} {"current_steps": 149315, "total_steps": 181800, "loss": 0.0255, "lr": 4.707636069742722e-06, "epoch": 16.426292629262925, "percentage": 82.13, "elapsed_time": "5:53:38", "remaining_time": "1:16:56", "throughput": 1485.05, "total_tokens": 31511008} {"current_steps": 149320, "total_steps": 181800, "loss": 0.1396, "lr": 4.706234326563461e-06, "epoch": 16.426842684268426, "percentage": 82.13, "elapsed_time": "5:53:39", "remaining_time": "1:16:55", "throughput": 1485.05, "total_tokens": 31512032} {"current_steps": 149325, "total_steps": 181800, "loss": 0.0037, "lr": 4.70483277042211e-06, "epoch": 16.427392739273927, "percentage": 82.14, "elapsed_time": "5:53:40", "remaining_time": "1:16:54", "throughput": 1485.05, "total_tokens": 31513088} {"current_steps": 149330, "total_steps": 181800, "loss": 0.0091, "lr": 4.703431401331573e-06, "epoch": 16.427942794279428, "percentage": 82.14, "elapsed_time": "5:53:40", "remaining_time": "1:16:54", "throughput": 1485.05, "total_tokens": 31514144} {"current_steps": 149335, "total_steps": 181800, "loss": 0.0018, "lr": 4.702030219304765e-06, "epoch": 16.42849284928493, "percentage": 82.14, "elapsed_time": "5:53:41", "remaining_time": "1:16:53", "throughput": 1485.05, "total_tokens": 31515200} {"current_steps": 149340, "total_steps": 181800, "loss": 0.0988, "lr": 4.700629224354613e-06, "epoch": 16.42904290429043, "percentage": 82.15, "elapsed_time": "5:53:42", "remaining_time": "1:16:52", "throughput": 1485.05, "total_tokens": 31516256} {"current_steps": 149345, "total_steps": 181800, "loss": 0.1048, "lr": 4.699228416494006e-06, "epoch": 16.42959295929593, "percentage": 82.15, "elapsed_time": "5:53:43", "remaining_time": "1:16:52", "throughput": 1485.05, "total_tokens": 31517280} {"current_steps": 149350, "total_steps": 181800, "loss": 0.0363, "lr": 4.697827795735882e-06, "epoch": 16.43014301430143, "percentage": 82.15, "elapsed_time": "5:53:43", "remaining_time": "1:16:51", "throughput": 1485.06, "total_tokens": 31518368} {"current_steps": 149355, "total_steps": 181800, "loss": 0.0021, "lr": 4.696427362093137e-06, "epoch": 16.43069306930693, "percentage": 82.15, "elapsed_time": "5:53:44", "remaining_time": "1:16:50", "throughput": 1485.05, "total_tokens": 31519360} {"current_steps": 149360, "total_steps": 181800, "loss": 0.0083, "lr": 4.695027115578674e-06, "epoch": 16.43124312431243, "percentage": 82.16, "elapsed_time": "5:53:45", "remaining_time": "1:16:49", "throughput": 1485.06, "total_tokens": 31520480} {"current_steps": 149365, "total_steps": 181800, "loss": 0.0014, "lr": 4.693627056205407e-06, "epoch": 16.431793179317932, "percentage": 82.16, "elapsed_time": "5:53:45", "remaining_time": "1:16:49", "throughput": 1485.06, "total_tokens": 31521536} {"current_steps": 149370, "total_steps": 181800, "loss": 0.0065, "lr": 4.692227183986231e-06, "epoch": 16.432343234323433, "percentage": 82.16, "elapsed_time": "5:53:46", "remaining_time": "1:16:48", "throughput": 1485.06, "total_tokens": 31522624} {"current_steps": 149375, "total_steps": 181800, "loss": 0.0034, "lr": 4.69082749893405e-06, "epoch": 16.432893289328934, "percentage": 82.16, "elapsed_time": "5:53:47", "remaining_time": "1:16:47", "throughput": 1485.06, "total_tokens": 31523616} {"current_steps": 149380, "total_steps": 181800, "loss": 0.0243, "lr": 4.689428001061774e-06, "epoch": 16.433443344334435, "percentage": 82.17, "elapsed_time": "5:53:47", "remaining_time": "1:16:47", "throughput": 1485.06, "total_tokens": 31524640} {"current_steps": 149385, "total_steps": 181800, "loss": 0.004, "lr": 4.6880286903822875e-06, "epoch": 16.433993399339933, "percentage": 82.17, "elapsed_time": "5:53:48", "remaining_time": "1:16:46", "throughput": 1485.06, "total_tokens": 31525696} {"current_steps": 149390, "total_steps": 181800, "loss": 0.0009, "lr": 4.686629566908501e-06, "epoch": 16.434543454345434, "percentage": 82.17, "elapsed_time": "5:53:49", "remaining_time": "1:16:45", "throughput": 1485.06, "total_tokens": 31526720} {"current_steps": 149395, "total_steps": 181800, "loss": 0.0873, "lr": 4.685230630653298e-06, "epoch": 16.435093509350935, "percentage": 82.18, "elapsed_time": "5:53:49", "remaining_time": "1:16:44", "throughput": 1485.06, "total_tokens": 31527744} {"current_steps": 149400, "total_steps": 181800, "loss": 0.0366, "lr": 4.68383188162958e-06, "epoch": 16.435643564356436, "percentage": 82.18, "elapsed_time": "5:53:50", "remaining_time": "1:16:44", "throughput": 1485.07, "total_tokens": 31528864} {"current_steps": 149405, "total_steps": 181800, "loss": 0.0415, "lr": 4.682433319850229e-06, "epoch": 16.436193619361937, "percentage": 82.18, "elapsed_time": "5:53:51", "remaining_time": "1:16:43", "throughput": 1485.07, "total_tokens": 31529952} {"current_steps": 149410, "total_steps": 181800, "loss": 0.039, "lr": 4.681034945328141e-06, "epoch": 16.436743674367438, "percentage": 82.18, "elapsed_time": "5:53:52", "remaining_time": "1:16:42", "throughput": 1485.07, "total_tokens": 31531040} {"current_steps": 149415, "total_steps": 181800, "loss": 0.0005, "lr": 4.6796367580762116e-06, "epoch": 16.437293729372936, "percentage": 82.19, "elapsed_time": "5:53:52", "remaining_time": "1:16:42", "throughput": 1485.07, "total_tokens": 31532064} {"current_steps": 149420, "total_steps": 181800, "loss": 0.0038, "lr": 4.678238758107317e-06, "epoch": 16.437843784378437, "percentage": 82.19, "elapsed_time": "5:53:53", "remaining_time": "1:16:41", "throughput": 1485.07, "total_tokens": 31533120} {"current_steps": 149425, "total_steps": 181800, "loss": 0.0038, "lr": 4.676840945434338e-06, "epoch": 16.438393839383938, "percentage": 82.19, "elapsed_time": "5:53:54", "remaining_time": "1:16:40", "throughput": 1485.08, "total_tokens": 31534240} {"current_steps": 149430, "total_steps": 181800, "loss": 0.1175, "lr": 4.675443320070166e-06, "epoch": 16.43894389438944, "percentage": 82.19, "elapsed_time": "5:53:54", "remaining_time": "1:16:39", "throughput": 1485.08, "total_tokens": 31535360} {"current_steps": 149435, "total_steps": 181800, "loss": 0.0501, "lr": 4.674045882027681e-06, "epoch": 16.43949394939494, "percentage": 82.2, "elapsed_time": "5:53:55", "remaining_time": "1:16:39", "throughput": 1485.08, "total_tokens": 31536352} {"current_steps": 149440, "total_steps": 181800, "loss": 0.003, "lr": 4.672648631319765e-06, "epoch": 16.44004400440044, "percentage": 82.2, "elapsed_time": "5:53:56", "remaining_time": "1:16:38", "throughput": 1485.08, "total_tokens": 31537376} {"current_steps": 149445, "total_steps": 181800, "loss": 0.0218, "lr": 4.671251567959295e-06, "epoch": 16.440594059405942, "percentage": 82.2, "elapsed_time": "5:53:56", "remaining_time": "1:16:37", "throughput": 1485.08, "total_tokens": 31538496} {"current_steps": 149450, "total_steps": 181800, "loss": 0.0358, "lr": 4.669854691959139e-06, "epoch": 16.44114411441144, "percentage": 82.21, "elapsed_time": "5:53:57", "remaining_time": "1:16:37", "throughput": 1485.09, "total_tokens": 31539584} {"current_steps": 149455, "total_steps": 181800, "loss": 0.1539, "lr": 4.66845800333218e-06, "epoch": 16.44169416941694, "percentage": 82.21, "elapsed_time": "5:53:58", "remaining_time": "1:16:36", "throughput": 1485.09, "total_tokens": 31540640} {"current_steps": 149460, "total_steps": 181800, "loss": 0.0291, "lr": 4.667061502091283e-06, "epoch": 16.442244224422442, "percentage": 82.21, "elapsed_time": "5:53:58", "remaining_time": "1:16:35", "throughput": 1485.09, "total_tokens": 31541728} {"current_steps": 149465, "total_steps": 181800, "loss": 0.0025, "lr": 4.665665188249324e-06, "epoch": 16.442794279427943, "percentage": 82.21, "elapsed_time": "5:53:59", "remaining_time": "1:16:34", "throughput": 1485.09, "total_tokens": 31542784} {"current_steps": 149470, "total_steps": 181800, "loss": 0.0756, "lr": 4.6642690618191764e-06, "epoch": 16.443344334433444, "percentage": 82.22, "elapsed_time": "5:54:00", "remaining_time": "1:16:34", "throughput": 1485.09, "total_tokens": 31543808} {"current_steps": 149475, "total_steps": 181800, "loss": 0.0026, "lr": 4.662873122813699e-06, "epoch": 16.443894389438945, "percentage": 82.22, "elapsed_time": "5:54:00", "remaining_time": "1:16:33", "throughput": 1485.1, "total_tokens": 31544896} {"current_steps": 149480, "total_steps": 181800, "loss": 0.0034, "lr": 4.661477371245765e-06, "epoch": 16.444444444444443, "percentage": 82.22, "elapsed_time": "5:54:01", "remaining_time": "1:16:32", "throughput": 1485.1, "total_tokens": 31545952} {"current_steps": 149485, "total_steps": 181800, "loss": 0.1123, "lr": 4.66008180712823e-06, "epoch": 16.444994499449944, "percentage": 82.22, "elapsed_time": "5:54:02", "remaining_time": "1:16:32", "throughput": 1485.1, "total_tokens": 31547008} {"current_steps": 149490, "total_steps": 181800, "loss": 0.0732, "lr": 4.65868643047396e-06, "epoch": 16.445544554455445, "percentage": 82.23, "elapsed_time": "5:54:03", "remaining_time": "1:16:31", "throughput": 1485.1, "total_tokens": 31548064} {"current_steps": 149495, "total_steps": 181800, "loss": 0.0254, "lr": 4.657291241295825e-06, "epoch": 16.446094609460946, "percentage": 82.23, "elapsed_time": "5:54:03", "remaining_time": "1:16:30", "throughput": 1485.1, "total_tokens": 31549056} {"current_steps": 149500, "total_steps": 181800, "loss": 0.0135, "lr": 4.655896239606666e-06, "epoch": 16.446644664466447, "percentage": 82.23, "elapsed_time": "5:54:04", "remaining_time": "1:16:29", "throughput": 1485.1, "total_tokens": 31550176} {"current_steps": 149505, "total_steps": 181800, "loss": 0.0147, "lr": 4.654501425419358e-06, "epoch": 16.44719471947195, "percentage": 82.24, "elapsed_time": "5:54:05", "remaining_time": "1:16:29", "throughput": 1485.11, "total_tokens": 31551264} {"current_steps": 149510, "total_steps": 181800, "loss": 0.007, "lr": 4.65310679874674e-06, "epoch": 16.44774477447745, "percentage": 82.24, "elapsed_time": "5:54:05", "remaining_time": "1:16:28", "throughput": 1485.11, "total_tokens": 31552288} {"current_steps": 149515, "total_steps": 181800, "loss": 0.0029, "lr": 4.651712359601678e-06, "epoch": 16.448294829482947, "percentage": 82.24, "elapsed_time": "5:54:06", "remaining_time": "1:16:27", "throughput": 1485.11, "total_tokens": 31553344} {"current_steps": 149520, "total_steps": 181800, "loss": 0.0022, "lr": 4.6503181079970144e-06, "epoch": 16.448844884488448, "percentage": 82.24, "elapsed_time": "5:54:07", "remaining_time": "1:16:27", "throughput": 1485.11, "total_tokens": 31554432} {"current_steps": 149525, "total_steps": 181800, "loss": 0.0024, "lr": 4.6489240439456044e-06, "epoch": 16.44939493949395, "percentage": 82.25, "elapsed_time": "5:54:07", "remaining_time": "1:16:26", "throughput": 1485.11, "total_tokens": 31555488} {"current_steps": 149530, "total_steps": 181800, "loss": 0.0017, "lr": 4.647530167460304e-06, "epoch": 16.44994499449945, "percentage": 82.25, "elapsed_time": "5:54:08", "remaining_time": "1:16:25", "throughput": 1485.11, "total_tokens": 31556544} {"current_steps": 149535, "total_steps": 181800, "loss": 0.0023, "lr": 4.646136478553945e-06, "epoch": 16.45049504950495, "percentage": 82.25, "elapsed_time": "5:54:09", "remaining_time": "1:16:24", "throughput": 1485.12, "total_tokens": 31557664} {"current_steps": 149540, "total_steps": 181800, "loss": 0.0481, "lr": 4.644742977239383e-06, "epoch": 16.451045104510452, "percentage": 82.26, "elapsed_time": "5:54:09", "remaining_time": "1:16:24", "throughput": 1485.12, "total_tokens": 31558752} {"current_steps": 149545, "total_steps": 181800, "loss": 0.0029, "lr": 4.6433496635294535e-06, "epoch": 16.45159515951595, "percentage": 82.26, "elapsed_time": "5:54:10", "remaining_time": "1:16:23", "throughput": 1485.12, "total_tokens": 31559808} {"current_steps": 149550, "total_steps": 181800, "loss": 0.0564, "lr": 4.641956537437e-06, "epoch": 16.45214521452145, "percentage": 82.26, "elapsed_time": "5:54:11", "remaining_time": "1:16:22", "throughput": 1485.12, "total_tokens": 31560832} {"current_steps": 149555, "total_steps": 181800, "loss": 0.0097, "lr": 4.640563598974873e-06, "epoch": 16.452695269526952, "percentage": 82.26, "elapsed_time": "5:54:12", "remaining_time": "1:16:22", "throughput": 1485.12, "total_tokens": 31561792} {"current_steps": 149560, "total_steps": 181800, "loss": 0.1148, "lr": 4.6391708481558936e-06, "epoch": 16.453245324532453, "percentage": 82.27, "elapsed_time": "5:54:12", "remaining_time": "1:16:21", "throughput": 1485.12, "total_tokens": 31562816} {"current_steps": 149565, "total_steps": 181800, "loss": 0.1392, "lr": 4.6377782849929135e-06, "epoch": 16.453795379537954, "percentage": 82.27, "elapsed_time": "5:54:13", "remaining_time": "1:16:20", "throughput": 1485.12, "total_tokens": 31563872} {"current_steps": 149570, "total_steps": 181800, "loss": 0.002, "lr": 4.636385909498761e-06, "epoch": 16.454345434543455, "percentage": 82.27, "elapsed_time": "5:54:14", "remaining_time": "1:16:19", "throughput": 1485.12, "total_tokens": 31564960} {"current_steps": 149575, "total_steps": 181800, "loss": 0.0031, "lr": 4.634993721686262e-06, "epoch": 16.454895489548957, "percentage": 82.27, "elapsed_time": "5:54:14", "remaining_time": "1:16:19", "throughput": 1485.12, "total_tokens": 31565952} {"current_steps": 149580, "total_steps": 181800, "loss": 0.0402, "lr": 4.633601721568254e-06, "epoch": 16.455445544554454, "percentage": 82.28, "elapsed_time": "5:54:15", "remaining_time": "1:16:18", "throughput": 1485.12, "total_tokens": 31566944} {"current_steps": 149585, "total_steps": 181800, "loss": 0.0068, "lr": 4.632209909157564e-06, "epoch": 16.455995599559955, "percentage": 82.28, "elapsed_time": "5:54:16", "remaining_time": "1:16:17", "throughput": 1485.12, "total_tokens": 31568000} {"current_steps": 149590, "total_steps": 181800, "loss": 0.0073, "lr": 4.630818284467028e-06, "epoch": 16.456545654565456, "percentage": 82.28, "elapsed_time": "5:54:16", "remaining_time": "1:16:17", "throughput": 1485.12, "total_tokens": 31569088} {"current_steps": 149595, "total_steps": 181800, "loss": 0.0098, "lr": 4.629426847509469e-06, "epoch": 16.457095709570957, "percentage": 82.29, "elapsed_time": "5:54:17", "remaining_time": "1:16:16", "throughput": 1485.13, "total_tokens": 31570144} {"current_steps": 149600, "total_steps": 181800, "loss": 0.0591, "lr": 4.6280355982977e-06, "epoch": 16.45764576457646, "percentage": 82.29, "elapsed_time": "5:54:18", "remaining_time": "1:16:15", "throughput": 1485.13, "total_tokens": 31571264} {"current_steps": 149605, "total_steps": 181800, "loss": 0.0232, "lr": 4.626644536844552e-06, "epoch": 16.45819581958196, "percentage": 82.29, "elapsed_time": "5:54:18", "remaining_time": "1:16:14", "throughput": 1485.13, "total_tokens": 31572288} {"current_steps": 149610, "total_steps": 181800, "loss": 0.0105, "lr": 4.625253663162851e-06, "epoch": 16.458745874587457, "percentage": 82.29, "elapsed_time": "5:54:19", "remaining_time": "1:16:14", "throughput": 1485.13, "total_tokens": 31573344} {"current_steps": 149615, "total_steps": 181800, "loss": 0.0035, "lr": 4.623862977265403e-06, "epoch": 16.459295929592958, "percentage": 82.3, "elapsed_time": "5:54:20", "remaining_time": "1:16:13", "throughput": 1485.14, "total_tokens": 31574464} {"current_steps": 149620, "total_steps": 181800, "loss": 0.0032, "lr": 4.6224724791650385e-06, "epoch": 16.45984598459846, "percentage": 82.3, "elapsed_time": "5:54:21", "remaining_time": "1:16:12", "throughput": 1485.13, "total_tokens": 31575488} {"current_steps": 149625, "total_steps": 181800, "loss": 0.011, "lr": 4.6210821688745634e-06, "epoch": 16.46039603960396, "percentage": 82.3, "elapsed_time": "5:54:21", "remaining_time": "1:16:12", "throughput": 1485.14, "total_tokens": 31576544} {"current_steps": 149630, "total_steps": 181800, "loss": 0.0042, "lr": 4.619692046406798e-06, "epoch": 16.46094609460946, "percentage": 82.3, "elapsed_time": "5:54:22", "remaining_time": "1:16:11", "throughput": 1485.14, "total_tokens": 31577568} {"current_steps": 149635, "total_steps": 181800, "loss": 0.0532, "lr": 4.61830211177455e-06, "epoch": 16.461496149614963, "percentage": 82.31, "elapsed_time": "5:54:23", "remaining_time": "1:16:10", "throughput": 1485.14, "total_tokens": 31578656} {"current_steps": 149640, "total_steps": 181800, "loss": 0.005, "lr": 4.616912364990627e-06, "epoch": 16.462046204620464, "percentage": 82.31, "elapsed_time": "5:54:23", "remaining_time": "1:16:09", "throughput": 1485.14, "total_tokens": 31579712} {"current_steps": 149645, "total_steps": 181800, "loss": 0.0013, "lr": 4.615522806067852e-06, "epoch": 16.46259625962596, "percentage": 82.31, "elapsed_time": "5:54:24", "remaining_time": "1:16:09", "throughput": 1485.14, "total_tokens": 31580736} {"current_steps": 149650, "total_steps": 181800, "loss": 0.0108, "lr": 4.614133435019011e-06, "epoch": 16.463146314631462, "percentage": 82.32, "elapsed_time": "5:54:25", "remaining_time": "1:16:08", "throughput": 1485.14, "total_tokens": 31581856} {"current_steps": 149655, "total_steps": 181800, "loss": 0.0641, "lr": 4.612744251856929e-06, "epoch": 16.463696369636963, "percentage": 82.32, "elapsed_time": "5:54:25", "remaining_time": "1:16:07", "throughput": 1485.14, "total_tokens": 31582880} {"current_steps": 149660, "total_steps": 181800, "loss": 0.0689, "lr": 4.6113552565943934e-06, "epoch": 16.464246424642464, "percentage": 82.32, "elapsed_time": "5:54:26", "remaining_time": "1:16:07", "throughput": 1485.15, "total_tokens": 31584000} {"current_steps": 149665, "total_steps": 181800, "loss": 0.1579, "lr": 4.609966449244215e-06, "epoch": 16.464796479647966, "percentage": 82.32, "elapsed_time": "5:54:27", "remaining_time": "1:16:06", "throughput": 1485.15, "total_tokens": 31585024} {"current_steps": 149670, "total_steps": 181800, "loss": 0.088, "lr": 4.608577829819197e-06, "epoch": 16.465346534653467, "percentage": 82.33, "elapsed_time": "5:54:27", "remaining_time": "1:16:05", "throughput": 1485.15, "total_tokens": 31586080} {"current_steps": 149675, "total_steps": 181800, "loss": 0.1742, "lr": 4.607189398332126e-06, "epoch": 16.465896589658964, "percentage": 82.33, "elapsed_time": "5:54:28", "remaining_time": "1:16:04", "throughput": 1485.15, "total_tokens": 31587136} {"current_steps": 149680, "total_steps": 181800, "loss": 0.0151, "lr": 4.605801154795811e-06, "epoch": 16.466446644664465, "percentage": 82.33, "elapsed_time": "5:54:29", "remaining_time": "1:16:04", "throughput": 1485.15, "total_tokens": 31588160} {"current_steps": 149685, "total_steps": 181800, "loss": 0.0728, "lr": 4.60441309922304e-06, "epoch": 16.466996699669966, "percentage": 82.33, "elapsed_time": "5:54:30", "remaining_time": "1:16:03", "throughput": 1485.15, "total_tokens": 31589152} {"current_steps": 149690, "total_steps": 181800, "loss": 0.0011, "lr": 4.603025231626601e-06, "epoch": 16.467546754675467, "percentage": 82.34, "elapsed_time": "5:54:30", "remaining_time": "1:16:02", "throughput": 1485.15, "total_tokens": 31590240} {"current_steps": 149695, "total_steps": 181800, "loss": 0.0057, "lr": 4.601637552019292e-06, "epoch": 16.46809680968097, "percentage": 82.34, "elapsed_time": "5:54:31", "remaining_time": "1:16:02", "throughput": 1485.16, "total_tokens": 31591360} {"current_steps": 149700, "total_steps": 181800, "loss": 0.0038, "lr": 4.6002500604139e-06, "epoch": 16.46864686468647, "percentage": 82.34, "elapsed_time": "5:54:32", "remaining_time": "1:16:01", "throughput": 1485.16, "total_tokens": 31592384} {"current_steps": 149705, "total_steps": 181800, "loss": 0.0032, "lr": 4.598862756823222e-06, "epoch": 16.46919691969197, "percentage": 82.35, "elapsed_time": "5:54:32", "remaining_time": "1:16:00", "throughput": 1485.16, "total_tokens": 31593408} {"current_steps": 149710, "total_steps": 181800, "loss": 0.0052, "lr": 4.597475641260035e-06, "epoch": 16.46974697469747, "percentage": 82.35, "elapsed_time": "5:54:33", "remaining_time": "1:15:59", "throughput": 1485.15, "total_tokens": 31594496} {"current_steps": 149715, "total_steps": 181800, "loss": 0.0043, "lr": 4.596088713737118e-06, "epoch": 16.47029702970297, "percentage": 82.35, "elapsed_time": "5:54:34", "remaining_time": "1:15:59", "throughput": 1485.15, "total_tokens": 31595584} {"current_steps": 149720, "total_steps": 181800, "loss": 0.0029, "lr": 4.594701974267263e-06, "epoch": 16.47084708470847, "percentage": 82.35, "elapsed_time": "5:54:35", "remaining_time": "1:15:58", "throughput": 1485.16, "total_tokens": 31596736} {"current_steps": 149725, "total_steps": 181800, "loss": 0.0837, "lr": 4.593315422863248e-06, "epoch": 16.47139713971397, "percentage": 82.36, "elapsed_time": "5:54:35", "remaining_time": "1:15:57", "throughput": 1485.16, "total_tokens": 31597824} {"current_steps": 149730, "total_steps": 181800, "loss": 0.0017, "lr": 4.591929059537858e-06, "epoch": 16.471947194719473, "percentage": 82.36, "elapsed_time": "5:54:36", "remaining_time": "1:15:57", "throughput": 1485.16, "total_tokens": 31598912} {"current_steps": 149735, "total_steps": 181800, "loss": 0.0068, "lr": 4.590542884303867e-06, "epoch": 16.472497249724974, "percentage": 82.36, "elapsed_time": "5:54:37", "remaining_time": "1:15:56", "throughput": 1485.16, "total_tokens": 31600000} {"current_steps": 149740, "total_steps": 181800, "loss": 0.2403, "lr": 4.5891568971740406e-06, "epoch": 16.47304730473047, "percentage": 82.37, "elapsed_time": "5:54:37", "remaining_time": "1:15:55", "throughput": 1485.17, "total_tokens": 31601120} {"current_steps": 149745, "total_steps": 181800, "loss": 0.1589, "lr": 4.587771098161167e-06, "epoch": 16.473597359735972, "percentage": 82.37, "elapsed_time": "5:54:38", "remaining_time": "1:15:54", "throughput": 1485.17, "total_tokens": 31602144} {"current_steps": 149750, "total_steps": 181800, "loss": 0.0008, "lr": 4.586385487278008e-06, "epoch": 16.474147414741473, "percentage": 82.37, "elapsed_time": "5:54:39", "remaining_time": "1:15:54", "throughput": 1485.17, "total_tokens": 31603200} {"current_steps": 149755, "total_steps": 181800, "loss": 0.001, "lr": 4.585000064537337e-06, "epoch": 16.474697469746975, "percentage": 82.37, "elapsed_time": "5:54:39", "remaining_time": "1:15:53", "throughput": 1485.17, "total_tokens": 31604288} {"current_steps": 149760, "total_steps": 181800, "loss": 0.002, "lr": 4.583614829951932e-06, "epoch": 16.475247524752476, "percentage": 82.38, "elapsed_time": "5:54:40", "remaining_time": "1:15:52", "throughput": 1485.17, "total_tokens": 31605280} {"current_steps": 149765, "total_steps": 181800, "loss": 0.0371, "lr": 4.582229783534545e-06, "epoch": 16.475797579757977, "percentage": 82.38, "elapsed_time": "5:54:41", "remaining_time": "1:15:52", "throughput": 1485.17, "total_tokens": 31606304} {"current_steps": 149770, "total_steps": 181800, "loss": 0.0293, "lr": 4.580844925297955e-06, "epoch": 16.476347634763478, "percentage": 82.38, "elapsed_time": "5:54:41", "remaining_time": "1:15:51", "throughput": 1485.17, "total_tokens": 31607328} {"current_steps": 149775, "total_steps": 181800, "loss": 0.0229, "lr": 4.579460255254914e-06, "epoch": 16.476897689768975, "percentage": 82.38, "elapsed_time": "5:54:42", "remaining_time": "1:15:50", "throughput": 1485.17, "total_tokens": 31608384} {"current_steps": 149780, "total_steps": 181800, "loss": 0.0038, "lr": 4.578075773418189e-06, "epoch": 16.477447744774476, "percentage": 82.39, "elapsed_time": "5:54:43", "remaining_time": "1:15:49", "throughput": 1485.17, "total_tokens": 31609408} {"current_steps": 149785, "total_steps": 181800, "loss": 0.0173, "lr": 4.576691479800546e-06, "epoch": 16.477997799779978, "percentage": 82.39, "elapsed_time": "5:54:44", "remaining_time": "1:15:49", "throughput": 1485.18, "total_tokens": 31610496} {"current_steps": 149790, "total_steps": 181800, "loss": 0.0021, "lr": 4.575307374414731e-06, "epoch": 16.47854785478548, "percentage": 82.39, "elapsed_time": "5:54:44", "remaining_time": "1:15:48", "throughput": 1485.18, "total_tokens": 31611552} {"current_steps": 149795, "total_steps": 181800, "loss": 0.058, "lr": 4.573923457273513e-06, "epoch": 16.47909790979098, "percentage": 82.4, "elapsed_time": "5:54:45", "remaining_time": "1:15:47", "throughput": 1485.18, "total_tokens": 31612608} {"current_steps": 149800, "total_steps": 181800, "loss": 0.0038, "lr": 4.572539728389641e-06, "epoch": 16.47964796479648, "percentage": 82.4, "elapsed_time": "5:54:46", "remaining_time": "1:15:47", "throughput": 1485.18, "total_tokens": 31613696} {"current_steps": 149805, "total_steps": 181800, "loss": 0.002, "lr": 4.571156187775863e-06, "epoch": 16.480198019801982, "percentage": 82.4, "elapsed_time": "5:54:46", "remaining_time": "1:15:46", "throughput": 1485.18, "total_tokens": 31614784} {"current_steps": 149810, "total_steps": 181800, "loss": 0.0071, "lr": 4.569772835444935e-06, "epoch": 16.48074807480748, "percentage": 82.4, "elapsed_time": "5:54:47", "remaining_time": "1:15:45", "throughput": 1485.19, "total_tokens": 31615872} {"current_steps": 149815, "total_steps": 181800, "loss": 0.0015, "lr": 4.5683896714096095e-06, "epoch": 16.48129812981298, "percentage": 82.41, "elapsed_time": "5:54:48", "remaining_time": "1:15:44", "throughput": 1485.19, "total_tokens": 31616896} {"current_steps": 149820, "total_steps": 181800, "loss": 0.0104, "lr": 4.567006695682635e-06, "epoch": 16.48184818481848, "percentage": 82.41, "elapsed_time": "5:54:48", "remaining_time": "1:15:44", "throughput": 1485.19, "total_tokens": 31618016} {"current_steps": 149825, "total_steps": 181800, "loss": 0.0466, "lr": 4.5656239082767586e-06, "epoch": 16.482398239823983, "percentage": 82.41, "elapsed_time": "5:54:49", "remaining_time": "1:15:43", "throughput": 1485.19, "total_tokens": 31619072} {"current_steps": 149830, "total_steps": 181800, "loss": 0.0212, "lr": 4.564241309204714e-06, "epoch": 16.482948294829484, "percentage": 82.41, "elapsed_time": "5:54:50", "remaining_time": "1:15:42", "throughput": 1485.2, "total_tokens": 31620192} {"current_steps": 149835, "total_steps": 181800, "loss": 0.0105, "lr": 4.56285889847925e-06, "epoch": 16.483498349834985, "percentage": 82.42, "elapsed_time": "5:54:50", "remaining_time": "1:15:42", "throughput": 1485.2, "total_tokens": 31621184} {"current_steps": 149840, "total_steps": 181800, "loss": 0.0899, "lr": 4.561476676113108e-06, "epoch": 16.484048404840483, "percentage": 82.42, "elapsed_time": "5:54:51", "remaining_time": "1:15:41", "throughput": 1485.2, "total_tokens": 31622272} {"current_steps": 149845, "total_steps": 181800, "loss": 0.1011, "lr": 4.5600946421190365e-06, "epoch": 16.484598459845984, "percentage": 82.42, "elapsed_time": "5:54:52", "remaining_time": "1:15:40", "throughput": 1485.2, "total_tokens": 31623328} {"current_steps": 149850, "total_steps": 181800, "loss": 0.0428, "lr": 4.558712796509765e-06, "epoch": 16.485148514851485, "percentage": 82.43, "elapsed_time": "5:54:52", "remaining_time": "1:15:39", "throughput": 1485.21, "total_tokens": 31624448} {"current_steps": 149855, "total_steps": 181800, "loss": 0.1408, "lr": 4.557331139298021e-06, "epoch": 16.485698569856986, "percentage": 82.43, "elapsed_time": "5:54:53", "remaining_time": "1:15:39", "throughput": 1485.21, "total_tokens": 31625472} {"current_steps": 149860, "total_steps": 181800, "loss": 0.023, "lr": 4.555949670496553e-06, "epoch": 16.486248624862487, "percentage": 82.43, "elapsed_time": "5:54:54", "remaining_time": "1:15:38", "throughput": 1485.2, "total_tokens": 31626464} {"current_steps": 149865, "total_steps": 181800, "loss": 0.0554, "lr": 4.554568390118083e-06, "epoch": 16.486798679867988, "percentage": 82.43, "elapsed_time": "5:54:55", "remaining_time": "1:15:37", "throughput": 1485.21, "total_tokens": 31627552} {"current_steps": 149870, "total_steps": 181800, "loss": 0.0031, "lr": 4.553187298175343e-06, "epoch": 16.48734873487349, "percentage": 82.44, "elapsed_time": "5:54:55", "remaining_time": "1:15:37", "throughput": 1485.21, "total_tokens": 31628608} {"current_steps": 149875, "total_steps": 181800, "loss": 0.0255, "lr": 4.5518063946810715e-06, "epoch": 16.487898789878987, "percentage": 82.44, "elapsed_time": "5:54:56", "remaining_time": "1:15:36", "throughput": 1485.21, "total_tokens": 31629632} {"current_steps": 149880, "total_steps": 181800, "loss": 0.067, "lr": 4.550425679647982e-06, "epoch": 16.488448844884488, "percentage": 82.44, "elapsed_time": "5:54:57", "remaining_time": "1:15:35", "throughput": 1485.21, "total_tokens": 31630720} {"current_steps": 149885, "total_steps": 181800, "loss": 0.0003, "lr": 4.549045153088813e-06, "epoch": 16.48899889988999, "percentage": 82.44, "elapsed_time": "5:54:57", "remaining_time": "1:15:34", "throughput": 1485.21, "total_tokens": 31631776} {"current_steps": 149890, "total_steps": 181800, "loss": 0.0028, "lr": 4.547664815016275e-06, "epoch": 16.48954895489549, "percentage": 82.45, "elapsed_time": "5:54:58", "remaining_time": "1:15:34", "throughput": 1485.21, "total_tokens": 31632768} {"current_steps": 149895, "total_steps": 181800, "loss": 0.0132, "lr": 4.546284665443095e-06, "epoch": 16.49009900990099, "percentage": 82.45, "elapsed_time": "5:54:59", "remaining_time": "1:15:33", "throughput": 1485.22, "total_tokens": 31633920} {"current_steps": 149900, "total_steps": 181800, "loss": 0.0024, "lr": 4.544904704382003e-06, "epoch": 16.490649064906492, "percentage": 82.45, "elapsed_time": "5:54:59", "remaining_time": "1:15:32", "throughput": 1485.22, "total_tokens": 31634976} {"current_steps": 149905, "total_steps": 181800, "loss": 0.0826, "lr": 4.543524931845703e-06, "epoch": 16.49119911991199, "percentage": 82.46, "elapsed_time": "5:55:00", "remaining_time": "1:15:32", "throughput": 1485.22, "total_tokens": 31636032} {"current_steps": 149910, "total_steps": 181800, "loss": 0.0327, "lr": 4.5421453478469215e-06, "epoch": 16.49174917491749, "percentage": 82.46, "elapsed_time": "5:55:01", "remaining_time": "1:15:31", "throughput": 1485.22, "total_tokens": 31637152} {"current_steps": 149915, "total_steps": 181800, "loss": 0.0031, "lr": 4.5407659523983655e-06, "epoch": 16.492299229922992, "percentage": 82.46, "elapsed_time": "5:55:01", "remaining_time": "1:15:30", "throughput": 1485.22, "total_tokens": 31638176} {"current_steps": 149920, "total_steps": 181800, "loss": 0.003, "lr": 4.539386745512758e-06, "epoch": 16.492849284928493, "percentage": 82.46, "elapsed_time": "5:55:02", "remaining_time": "1:15:29", "throughput": 1485.23, "total_tokens": 31639264} {"current_steps": 149925, "total_steps": 181800, "loss": 0.0024, "lr": 4.538007727202798e-06, "epoch": 16.493399339933994, "percentage": 82.47, "elapsed_time": "5:55:03", "remaining_time": "1:15:29", "throughput": 1485.23, "total_tokens": 31640352} {"current_steps": 149930, "total_steps": 181800, "loss": 0.0014, "lr": 4.536628897481202e-06, "epoch": 16.493949394939495, "percentage": 82.47, "elapsed_time": "5:55:04", "remaining_time": "1:15:28", "throughput": 1485.23, "total_tokens": 31641440} {"current_steps": 149935, "total_steps": 181800, "loss": 0.0267, "lr": 4.535250256360685e-06, "epoch": 16.494499449944996, "percentage": 82.47, "elapsed_time": "5:55:04", "remaining_time": "1:15:27", "throughput": 1485.24, "total_tokens": 31642528} {"current_steps": 149940, "total_steps": 181800, "loss": 0.0433, "lr": 4.533871803853942e-06, "epoch": 16.495049504950494, "percentage": 82.48, "elapsed_time": "5:55:05", "remaining_time": "1:15:27", "throughput": 1485.24, "total_tokens": 31643552} {"current_steps": 149945, "total_steps": 181800, "loss": 0.0093, "lr": 4.532493539973687e-06, "epoch": 16.495599559955995, "percentage": 82.48, "elapsed_time": "5:55:06", "remaining_time": "1:15:26", "throughput": 1485.24, "total_tokens": 31644608} {"current_steps": 149950, "total_steps": 181800, "loss": 0.0435, "lr": 4.5311154647326105e-06, "epoch": 16.496149614961496, "percentage": 82.48, "elapsed_time": "5:55:06", "remaining_time": "1:15:25", "throughput": 1485.23, "total_tokens": 31645568} {"current_steps": 149955, "total_steps": 181800, "loss": 0.0021, "lr": 4.52973757814342e-06, "epoch": 16.496699669966997, "percentage": 82.48, "elapsed_time": "5:55:07", "remaining_time": "1:15:24", "throughput": 1485.24, "total_tokens": 31646624} {"current_steps": 149960, "total_steps": 181800, "loss": 0.002, "lr": 4.528359880218824e-06, "epoch": 16.497249724972498, "percentage": 82.49, "elapsed_time": "5:55:08", "remaining_time": "1:15:24", "throughput": 1485.23, "total_tokens": 31647616} {"current_steps": 149965, "total_steps": 181800, "loss": 0.1038, "lr": 4.5269823709715055e-06, "epoch": 16.497799779978, "percentage": 82.49, "elapsed_time": "5:55:08", "remaining_time": "1:15:23", "throughput": 1485.24, "total_tokens": 31648672} {"current_steps": 149970, "total_steps": 181800, "loss": 0.0094, "lr": 4.525605050414173e-06, "epoch": 16.498349834983497, "percentage": 82.49, "elapsed_time": "5:55:09", "remaining_time": "1:15:22", "throughput": 1485.24, "total_tokens": 31649728} {"current_steps": 149975, "total_steps": 181800, "loss": 0.002, "lr": 4.524227918559512e-06, "epoch": 16.498899889988998, "percentage": 82.49, "elapsed_time": "5:55:10", "remaining_time": "1:15:22", "throughput": 1485.24, "total_tokens": 31650784} {"current_steps": 149980, "total_steps": 181800, "loss": 0.0019, "lr": 4.522850975420212e-06, "epoch": 16.4994499449945, "percentage": 82.5, "elapsed_time": "5:55:10", "remaining_time": "1:15:21", "throughput": 1485.24, "total_tokens": 31651840} {"current_steps": 149985, "total_steps": 181800, "loss": 0.0223, "lr": 4.52147422100897e-06, "epoch": 16.5, "percentage": 82.5, "elapsed_time": "5:55:11", "remaining_time": "1:15:20", "throughput": 1485.24, "total_tokens": 31652960} {"current_steps": 149990, "total_steps": 181800, "loss": 0.0059, "lr": 4.520097655338479e-06, "epoch": 16.5005500550055, "percentage": 82.5, "elapsed_time": "5:55:12", "remaining_time": "1:15:19", "throughput": 1485.25, "total_tokens": 31654048} {"current_steps": 149995, "total_steps": 181800, "loss": 0.0138, "lr": 4.518721278421414e-06, "epoch": 16.501100110011002, "percentage": 82.51, "elapsed_time": "5:55:12", "remaining_time": "1:15:19", "throughput": 1485.25, "total_tokens": 31655104} {"current_steps": 150000, "total_steps": 181800, "loss": 0.0134, "lr": 4.517345090270473e-06, "epoch": 16.501650165016503, "percentage": 82.51, "elapsed_time": "5:55:13", "remaining_time": "1:15:18", "throughput": 1485.25, "total_tokens": 31656224} {"current_steps": 150005, "total_steps": 181800, "loss": 0.0018, "lr": 4.515969090898328e-06, "epoch": 16.502200220022, "percentage": 82.51, "elapsed_time": "5:55:14", "remaining_time": "1:15:17", "throughput": 1485.25, "total_tokens": 31657216} {"current_steps": 150010, "total_steps": 181800, "loss": 0.0014, "lr": 4.514593280317666e-06, "epoch": 16.502750275027502, "percentage": 82.51, "elapsed_time": "5:55:15", "remaining_time": "1:15:17", "throughput": 1485.26, "total_tokens": 31658336} {"current_steps": 150015, "total_steps": 181800, "loss": 0.0049, "lr": 4.513217658541174e-06, "epoch": 16.503300330033003, "percentage": 82.52, "elapsed_time": "5:55:15", "remaining_time": "1:15:16", "throughput": 1485.26, "total_tokens": 31659392} {"current_steps": 150020, "total_steps": 181800, "loss": 0.0071, "lr": 4.511842225581519e-06, "epoch": 16.503850385038504, "percentage": 82.52, "elapsed_time": "5:55:16", "remaining_time": "1:15:15", "throughput": 1485.26, "total_tokens": 31660448} {"current_steps": 150025, "total_steps": 181800, "loss": 0.021, "lr": 4.510466981451391e-06, "epoch": 16.504400440044005, "percentage": 82.52, "elapsed_time": "5:55:17", "remaining_time": "1:15:14", "throughput": 1485.26, "total_tokens": 31661504} {"current_steps": 150030, "total_steps": 181800, "loss": 0.0266, "lr": 4.509091926163447e-06, "epoch": 16.504950495049506, "percentage": 82.52, "elapsed_time": "5:55:17", "remaining_time": "1:15:14", "throughput": 1485.26, "total_tokens": 31662624} {"current_steps": 150035, "total_steps": 181800, "loss": 0.0498, "lr": 4.507717059730379e-06, "epoch": 16.505500550055004, "percentage": 82.53, "elapsed_time": "5:55:18", "remaining_time": "1:15:13", "throughput": 1485.27, "total_tokens": 31663680} {"current_steps": 150040, "total_steps": 181800, "loss": 0.1191, "lr": 4.506342382164844e-06, "epoch": 16.506050605060505, "percentage": 82.53, "elapsed_time": "5:55:19", "remaining_time": "1:15:12", "throughput": 1485.26, "total_tokens": 31664672} {"current_steps": 150045, "total_steps": 181800, "loss": 0.067, "lr": 4.504967893479517e-06, "epoch": 16.506600660066006, "percentage": 82.53, "elapsed_time": "5:55:19", "remaining_time": "1:15:12", "throughput": 1485.27, "total_tokens": 31665728} {"current_steps": 150050, "total_steps": 181800, "loss": 0.0087, "lr": 4.503593593687072e-06, "epoch": 16.507150715071507, "percentage": 82.54, "elapsed_time": "5:55:20", "remaining_time": "1:15:11", "throughput": 1485.27, "total_tokens": 31666816} {"current_steps": 150055, "total_steps": 181800, "loss": 0.0701, "lr": 4.502219482800163e-06, "epoch": 16.507700770077008, "percentage": 82.54, "elapsed_time": "5:55:21", "remaining_time": "1:15:10", "throughput": 1485.27, "total_tokens": 31667904} {"current_steps": 150060, "total_steps": 181800, "loss": 0.0338, "lr": 4.500845560831468e-06, "epoch": 16.50825082508251, "percentage": 82.54, "elapsed_time": "5:55:21", "remaining_time": "1:15:09", "throughput": 1485.27, "total_tokens": 31668992} {"current_steps": 150065, "total_steps": 181800, "loss": 0.0026, "lr": 4.499471827793641e-06, "epoch": 16.50880088008801, "percentage": 82.54, "elapsed_time": "5:55:22", "remaining_time": "1:15:09", "throughput": 1485.28, "total_tokens": 31670080} {"current_steps": 150070, "total_steps": 181800, "loss": 0.0031, "lr": 4.498098283699337e-06, "epoch": 16.509350935093508, "percentage": 82.55, "elapsed_time": "5:55:23", "remaining_time": "1:15:08", "throughput": 1485.28, "total_tokens": 31671168} {"current_steps": 150075, "total_steps": 181800, "loss": 0.0074, "lr": 4.4967249285612325e-06, "epoch": 16.50990099009901, "percentage": 82.55, "elapsed_time": "5:55:24", "remaining_time": "1:15:07", "throughput": 1485.28, "total_tokens": 31672160} {"current_steps": 150080, "total_steps": 181800, "loss": 0.0058, "lr": 4.495351762391969e-06, "epoch": 16.51045104510451, "percentage": 82.55, "elapsed_time": "5:55:24", "remaining_time": "1:15:07", "throughput": 1485.28, "total_tokens": 31673184} {"current_steps": 150085, "total_steps": 181800, "loss": 0.0199, "lr": 4.49397878520422e-06, "epoch": 16.51100110011001, "percentage": 82.56, "elapsed_time": "5:55:25", "remaining_time": "1:15:06", "throughput": 1485.28, "total_tokens": 31674304} {"current_steps": 150090, "total_steps": 181800, "loss": 0.0316, "lr": 4.492605997010624e-06, "epoch": 16.511551155115512, "percentage": 82.56, "elapsed_time": "5:55:26", "remaining_time": "1:15:05", "throughput": 1485.28, "total_tokens": 31675328} {"current_steps": 150095, "total_steps": 181800, "loss": 0.0018, "lr": 4.4912333978238355e-06, "epoch": 16.512101210121013, "percentage": 82.56, "elapsed_time": "5:55:26", "remaining_time": "1:15:04", "throughput": 1485.28, "total_tokens": 31676352} {"current_steps": 150100, "total_steps": 181800, "loss": 0.0077, "lr": 4.489860987656505e-06, "epoch": 16.51265126512651, "percentage": 82.56, "elapsed_time": "5:55:27", "remaining_time": "1:15:04", "throughput": 1485.29, "total_tokens": 31677408} {"current_steps": 150105, "total_steps": 181800, "loss": 0.0077, "lr": 4.488488766521284e-06, "epoch": 16.513201320132012, "percentage": 82.57, "elapsed_time": "5:55:28", "remaining_time": "1:15:03", "throughput": 1485.28, "total_tokens": 31678432} {"current_steps": 150110, "total_steps": 181800, "loss": 0.0022, "lr": 4.487116734430827e-06, "epoch": 16.513751375137513, "percentage": 82.57, "elapsed_time": "5:55:28", "remaining_time": "1:15:02", "throughput": 1485.28, "total_tokens": 31679392} {"current_steps": 150115, "total_steps": 181800, "loss": 0.0013, "lr": 4.485744891397772e-06, "epoch": 16.514301430143014, "percentage": 82.57, "elapsed_time": "5:55:29", "remaining_time": "1:15:02", "throughput": 1485.29, "total_tokens": 31680512} {"current_steps": 150120, "total_steps": 181800, "loss": 0.0038, "lr": 4.484373237434755e-06, "epoch": 16.514851485148515, "percentage": 82.57, "elapsed_time": "5:55:30", "remaining_time": "1:15:01", "throughput": 1485.28, "total_tokens": 31681504} {"current_steps": 150125, "total_steps": 181800, "loss": 0.0326, "lr": 4.483001772554435e-06, "epoch": 16.515401540154016, "percentage": 82.58, "elapsed_time": "5:55:30", "remaining_time": "1:15:00", "throughput": 1485.29, "total_tokens": 31682624} {"current_steps": 150130, "total_steps": 181800, "loss": 0.0039, "lr": 4.481630496769429e-06, "epoch": 16.515951595159517, "percentage": 82.58, "elapsed_time": "5:55:31", "remaining_time": "1:14:59", "throughput": 1485.29, "total_tokens": 31683680} {"current_steps": 150135, "total_steps": 181800, "loss": 0.008, "lr": 4.4802594100923995e-06, "epoch": 16.516501650165015, "percentage": 82.58, "elapsed_time": "5:55:32", "remaining_time": "1:14:59", "throughput": 1485.29, "total_tokens": 31684672} {"current_steps": 150140, "total_steps": 181800, "loss": 0.0585, "lr": 4.478888512535972e-06, "epoch": 16.517051705170516, "percentage": 82.59, "elapsed_time": "5:55:33", "remaining_time": "1:14:58", "throughput": 1485.29, "total_tokens": 31685696} {"current_steps": 150145, "total_steps": 181800, "loss": 0.0032, "lr": 4.47751780411278e-06, "epoch": 16.517601760176017, "percentage": 82.59, "elapsed_time": "5:55:33", "remaining_time": "1:14:57", "throughput": 1485.29, "total_tokens": 31686848} {"current_steps": 150150, "total_steps": 181800, "loss": 0.0006, "lr": 4.4761472848354635e-06, "epoch": 16.51815181518152, "percentage": 82.59, "elapsed_time": "5:55:34", "remaining_time": "1:14:57", "throughput": 1485.3, "total_tokens": 31687904} {"current_steps": 150155, "total_steps": 181800, "loss": 0.1628, "lr": 4.4747769547166415e-06, "epoch": 16.51870187018702, "percentage": 82.59, "elapsed_time": "5:55:35", "remaining_time": "1:14:56", "throughput": 1485.3, "total_tokens": 31688960} {"current_steps": 150160, "total_steps": 181800, "loss": 0.1411, "lr": 4.473406813768952e-06, "epoch": 16.51925192519252, "percentage": 82.6, "elapsed_time": "5:55:35", "remaining_time": "1:14:55", "throughput": 1485.3, "total_tokens": 31690016} {"current_steps": 150165, "total_steps": 181800, "loss": 0.0061, "lr": 4.472036862005027e-06, "epoch": 16.519801980198018, "percentage": 82.6, "elapsed_time": "5:55:36", "remaining_time": "1:14:54", "throughput": 1485.3, "total_tokens": 31691136} {"current_steps": 150170, "total_steps": 181800, "loss": 0.0011, "lr": 4.470667099437484e-06, "epoch": 16.52035203520352, "percentage": 82.6, "elapsed_time": "5:55:37", "remaining_time": "1:14:54", "throughput": 1485.3, "total_tokens": 31692160} {"current_steps": 150175, "total_steps": 181800, "loss": 0.1035, "lr": 4.469297526078958e-06, "epoch": 16.52090209020902, "percentage": 82.6, "elapsed_time": "5:55:37", "remaining_time": "1:14:53", "throughput": 1485.3, "total_tokens": 31693216} {"current_steps": 150180, "total_steps": 181800, "loss": 0.0195, "lr": 4.467928141942063e-06, "epoch": 16.52145214521452, "percentage": 82.61, "elapsed_time": "5:55:38", "remaining_time": "1:14:52", "throughput": 1485.3, "total_tokens": 31694240} {"current_steps": 150185, "total_steps": 181800, "loss": 0.0057, "lr": 4.4665589470394175e-06, "epoch": 16.522002200220022, "percentage": 82.61, "elapsed_time": "5:55:39", "remaining_time": "1:14:52", "throughput": 1485.3, "total_tokens": 31695232} {"current_steps": 150190, "total_steps": 181800, "loss": 0.0044, "lr": 4.465189941383643e-06, "epoch": 16.522552255225524, "percentage": 82.61, "elapsed_time": "5:55:39", "remaining_time": "1:14:51", "throughput": 1485.3, "total_tokens": 31696288} {"current_steps": 150195, "total_steps": 181800, "loss": 0.0011, "lr": 4.463821124987364e-06, "epoch": 16.523102310231025, "percentage": 82.62, "elapsed_time": "5:55:40", "remaining_time": "1:14:50", "throughput": 1485.3, "total_tokens": 31697344} {"current_steps": 150200, "total_steps": 181800, "loss": 0.0015, "lr": 4.462452497863193e-06, "epoch": 16.523652365236522, "percentage": 82.62, "elapsed_time": "5:55:41", "remaining_time": "1:14:49", "throughput": 1485.3, "total_tokens": 31698368} {"current_steps": 150205, "total_steps": 181800, "loss": 0.017, "lr": 4.461084060023743e-06, "epoch": 16.524202420242023, "percentage": 82.62, "elapsed_time": "5:55:42", "remaining_time": "1:14:49", "throughput": 1485.3, "total_tokens": 31699392} {"current_steps": 150210, "total_steps": 181800, "loss": 0.0674, "lr": 4.459715811481621e-06, "epoch": 16.524752475247524, "percentage": 82.62, "elapsed_time": "5:55:42", "remaining_time": "1:14:48", "throughput": 1485.31, "total_tokens": 31700480} {"current_steps": 150215, "total_steps": 181800, "loss": 0.065, "lr": 4.4583477522494425e-06, "epoch": 16.525302530253025, "percentage": 82.63, "elapsed_time": "5:55:43", "remaining_time": "1:14:47", "throughput": 1485.31, "total_tokens": 31701568} {"current_steps": 150220, "total_steps": 181800, "loss": 0.0891, "lr": 4.456979882339815e-06, "epoch": 16.525852585258527, "percentage": 82.63, "elapsed_time": "5:55:44", "remaining_time": "1:14:47", "throughput": 1485.31, "total_tokens": 31702592} {"current_steps": 150225, "total_steps": 181800, "loss": 0.0189, "lr": 4.4556122017653526e-06, "epoch": 16.526402640264028, "percentage": 82.63, "elapsed_time": "5:55:44", "remaining_time": "1:14:46", "throughput": 1485.31, "total_tokens": 31703616} {"current_steps": 150230, "total_steps": 181800, "loss": 0.0031, "lr": 4.454244710538655e-06, "epoch": 16.52695269526953, "percentage": 82.63, "elapsed_time": "5:55:45", "remaining_time": "1:14:45", "throughput": 1485.31, "total_tokens": 31704672} {"current_steps": 150235, "total_steps": 181800, "loss": 0.002, "lr": 4.4528774086723175e-06, "epoch": 16.527502750275026, "percentage": 82.64, "elapsed_time": "5:55:46", "remaining_time": "1:14:44", "throughput": 1485.31, "total_tokens": 31705728} {"current_steps": 150240, "total_steps": 181800, "loss": 0.0146, "lr": 4.451510296178957e-06, "epoch": 16.528052805280527, "percentage": 82.64, "elapsed_time": "5:55:46", "remaining_time": "1:14:44", "throughput": 1485.32, "total_tokens": 31706816} {"current_steps": 150245, "total_steps": 181800, "loss": 0.0732, "lr": 4.450143373071158e-06, "epoch": 16.52860286028603, "percentage": 82.64, "elapsed_time": "5:55:47", "remaining_time": "1:14:43", "throughput": 1485.32, "total_tokens": 31707936} {"current_steps": 150250, "total_steps": 181800, "loss": 0.0643, "lr": 4.448776639361529e-06, "epoch": 16.52915291529153, "percentage": 82.65, "elapsed_time": "5:55:48", "remaining_time": "1:14:42", "throughput": 1485.32, "total_tokens": 31708960} {"current_steps": 150255, "total_steps": 181800, "loss": 0.062, "lr": 4.447410095062671e-06, "epoch": 16.52970297029703, "percentage": 82.65, "elapsed_time": "5:55:48", "remaining_time": "1:14:42", "throughput": 1485.32, "total_tokens": 31710016} {"current_steps": 150260, "total_steps": 181800, "loss": 0.0126, "lr": 4.446043740187164e-06, "epoch": 16.53025302530253, "percentage": 82.65, "elapsed_time": "5:55:49", "remaining_time": "1:14:41", "throughput": 1485.32, "total_tokens": 31711072} {"current_steps": 150265, "total_steps": 181800, "loss": 0.0055, "lr": 4.444677574747616e-06, "epoch": 16.53080308030803, "percentage": 82.65, "elapsed_time": "5:55:50", "remaining_time": "1:14:40", "throughput": 1485.32, "total_tokens": 31712128} {"current_steps": 150270, "total_steps": 181800, "loss": 0.0461, "lr": 4.443311598756606e-06, "epoch": 16.53135313531353, "percentage": 82.66, "elapsed_time": "5:55:50", "remaining_time": "1:14:39", "throughput": 1485.33, "total_tokens": 31713184} {"current_steps": 150275, "total_steps": 181800, "loss": 0.0008, "lr": 4.441945812226725e-06, "epoch": 16.53190319031903, "percentage": 82.66, "elapsed_time": "5:55:51", "remaining_time": "1:14:39", "throughput": 1485.33, "total_tokens": 31714272} {"current_steps": 150280, "total_steps": 181800, "loss": 0.1105, "lr": 4.440580215170576e-06, "epoch": 16.532453245324533, "percentage": 82.66, "elapsed_time": "5:55:52", "remaining_time": "1:14:38", "throughput": 1485.33, "total_tokens": 31715328} {"current_steps": 150285, "total_steps": 181800, "loss": 0.0342, "lr": 4.439214807600725e-06, "epoch": 16.533003300330034, "percentage": 82.67, "elapsed_time": "5:55:53", "remaining_time": "1:14:37", "throughput": 1485.33, "total_tokens": 31716384} {"current_steps": 150290, "total_steps": 181800, "loss": 0.0028, "lr": 4.437849589529772e-06, "epoch": 16.533553355335535, "percentage": 82.67, "elapsed_time": "5:55:53", "remaining_time": "1:14:37", "throughput": 1485.34, "total_tokens": 31717504} {"current_steps": 150295, "total_steps": 181800, "loss": 0.1955, "lr": 4.436484560970286e-06, "epoch": 16.534103410341036, "percentage": 82.67, "elapsed_time": "5:55:54", "remaining_time": "1:14:36", "throughput": 1485.34, "total_tokens": 31718560} {"current_steps": 150300, "total_steps": 181800, "loss": 0.0027, "lr": 4.435119721934861e-06, "epoch": 16.534653465346533, "percentage": 82.67, "elapsed_time": "5:55:55", "remaining_time": "1:14:35", "throughput": 1485.34, "total_tokens": 31719648} {"current_steps": 150305, "total_steps": 181800, "loss": 0.0797, "lr": 4.433755072436063e-06, "epoch": 16.535203520352034, "percentage": 82.68, "elapsed_time": "5:55:55", "remaining_time": "1:14:34", "throughput": 1485.34, "total_tokens": 31720736} {"current_steps": 150310, "total_steps": 181800, "loss": 0.0195, "lr": 4.432390612486476e-06, "epoch": 16.535753575357536, "percentage": 82.68, "elapsed_time": "5:55:56", "remaining_time": "1:14:34", "throughput": 1485.35, "total_tokens": 31721888} {"current_steps": 150315, "total_steps": 181800, "loss": 0.0167, "lr": 4.431026342098682e-06, "epoch": 16.536303630363037, "percentage": 82.68, "elapsed_time": "5:55:57", "remaining_time": "1:14:33", "throughput": 1485.35, "total_tokens": 31722944} {"current_steps": 150320, "total_steps": 181800, "loss": 0.0493, "lr": 4.429662261285242e-06, "epoch": 16.536853685368538, "percentage": 82.68, "elapsed_time": "5:55:57", "remaining_time": "1:14:32", "throughput": 1485.35, "total_tokens": 31724000} {"current_steps": 150325, "total_steps": 181800, "loss": 0.0029, "lr": 4.4282983700587394e-06, "epoch": 16.53740374037404, "percentage": 82.69, "elapsed_time": "5:55:58", "remaining_time": "1:14:32", "throughput": 1485.35, "total_tokens": 31724992} {"current_steps": 150330, "total_steps": 181800, "loss": 0.0053, "lr": 4.426934668431734e-06, "epoch": 16.537953795379536, "percentage": 82.69, "elapsed_time": "5:55:59", "remaining_time": "1:14:31", "throughput": 1485.35, "total_tokens": 31726016} {"current_steps": 150335, "total_steps": 181800, "loss": 0.0033, "lr": 4.4255711564168e-06, "epoch": 16.538503850385037, "percentage": 82.69, "elapsed_time": "5:55:59", "remaining_time": "1:14:30", "throughput": 1485.35, "total_tokens": 31727040} {"current_steps": 150340, "total_steps": 181800, "loss": 0.0166, "lr": 4.424207834026509e-06, "epoch": 16.53905390539054, "percentage": 82.7, "elapsed_time": "5:56:00", "remaining_time": "1:14:29", "throughput": 1485.35, "total_tokens": 31728128} {"current_steps": 150345, "total_steps": 181800, "loss": 0.0617, "lr": 4.422844701273415e-06, "epoch": 16.53960396039604, "percentage": 82.7, "elapsed_time": "5:56:01", "remaining_time": "1:14:29", "throughput": 1485.35, "total_tokens": 31729152} {"current_steps": 150350, "total_steps": 181800, "loss": 0.0101, "lr": 4.421481758170095e-06, "epoch": 16.54015401540154, "percentage": 82.7, "elapsed_time": "5:56:02", "remaining_time": "1:14:28", "throughput": 1485.35, "total_tokens": 31730176} {"current_steps": 150355, "total_steps": 181800, "loss": 0.0036, "lr": 4.420119004729103e-06, "epoch": 16.540704070407042, "percentage": 82.7, "elapsed_time": "5:56:02", "remaining_time": "1:14:27", "throughput": 1485.36, "total_tokens": 31731264} {"current_steps": 150360, "total_steps": 181800, "loss": 0.0059, "lr": 4.4187564409629955e-06, "epoch": 16.541254125412543, "percentage": 82.71, "elapsed_time": "5:56:03", "remaining_time": "1:14:27", "throughput": 1485.36, "total_tokens": 31732416} {"current_steps": 150365, "total_steps": 181800, "loss": 0.0054, "lr": 4.417394066884331e-06, "epoch": 16.54180418041804, "percentage": 82.71, "elapsed_time": "5:56:04", "remaining_time": "1:14:26", "throughput": 1485.36, "total_tokens": 31733440} {"current_steps": 150370, "total_steps": 181800, "loss": 0.0017, "lr": 4.416031882505675e-06, "epoch": 16.54235423542354, "percentage": 82.71, "elapsed_time": "5:56:04", "remaining_time": "1:14:25", "throughput": 1485.37, "total_tokens": 31734560} {"current_steps": 150375, "total_steps": 181800, "loss": 0.035, "lr": 4.4146698878395706e-06, "epoch": 16.542904290429043, "percentage": 82.71, "elapsed_time": "5:56:05", "remaining_time": "1:14:24", "throughput": 1485.37, "total_tokens": 31735584} {"current_steps": 150380, "total_steps": 181800, "loss": 0.0565, "lr": 4.413308082898582e-06, "epoch": 16.543454345434544, "percentage": 82.72, "elapsed_time": "5:56:06", "remaining_time": "1:14:24", "throughput": 1485.37, "total_tokens": 31736640} {"current_steps": 150385, "total_steps": 181800, "loss": 0.0036, "lr": 4.4119464676952465e-06, "epoch": 16.544004400440045, "percentage": 82.72, "elapsed_time": "5:56:06", "remaining_time": "1:14:23", "throughput": 1485.37, "total_tokens": 31737696} {"current_steps": 150390, "total_steps": 181800, "loss": 0.0157, "lr": 4.410585042242124e-06, "epoch": 16.544554455445546, "percentage": 82.72, "elapsed_time": "5:56:07", "remaining_time": "1:14:22", "throughput": 1485.37, "total_tokens": 31738720} {"current_steps": 150395, "total_steps": 181800, "loss": 0.0855, "lr": 4.409223806551763e-06, "epoch": 16.545104510451043, "percentage": 82.73, "elapsed_time": "5:56:08", "remaining_time": "1:14:22", "throughput": 1485.37, "total_tokens": 31739776} {"current_steps": 150400, "total_steps": 181800, "loss": 0.0022, "lr": 4.407862760636702e-06, "epoch": 16.545654565456545, "percentage": 82.73, "elapsed_time": "5:56:08", "remaining_time": "1:14:21", "throughput": 1485.37, "total_tokens": 31740864} {"current_steps": 150405, "total_steps": 181800, "loss": 0.0042, "lr": 4.406501904509494e-06, "epoch": 16.546204620462046, "percentage": 82.73, "elapsed_time": "5:56:09", "remaining_time": "1:14:20", "throughput": 1485.37, "total_tokens": 31741856} {"current_steps": 150410, "total_steps": 181800, "loss": 0.0642, "lr": 4.40514123818267e-06, "epoch": 16.546754675467547, "percentage": 82.73, "elapsed_time": "5:56:10", "remaining_time": "1:14:19", "throughput": 1485.38, "total_tokens": 31742944} {"current_steps": 150415, "total_steps": 181800, "loss": 0.0058, "lr": 4.4037807616687826e-06, "epoch": 16.547304730473048, "percentage": 82.74, "elapsed_time": "5:56:11", "remaining_time": "1:14:19", "throughput": 1485.38, "total_tokens": 31744000} {"current_steps": 150420, "total_steps": 181800, "loss": 0.074, "lr": 4.402420474980359e-06, "epoch": 16.54785478547855, "percentage": 82.74, "elapsed_time": "5:56:11", "remaining_time": "1:14:18", "throughput": 1485.38, "total_tokens": 31745088} {"current_steps": 150425, "total_steps": 181800, "loss": 0.0093, "lr": 4.401060378129943e-06, "epoch": 16.54840484048405, "percentage": 82.74, "elapsed_time": "5:56:12", "remaining_time": "1:14:17", "throughput": 1485.38, "total_tokens": 31746144} {"current_steps": 150430, "total_steps": 181800, "loss": 0.0694, "lr": 4.399700471130075e-06, "epoch": 16.548954895489548, "percentage": 82.74, "elapsed_time": "5:56:13", "remaining_time": "1:14:17", "throughput": 1485.38, "total_tokens": 31747200} {"current_steps": 150435, "total_steps": 181800, "loss": 0.0056, "lr": 4.398340753993274e-06, "epoch": 16.54950495049505, "percentage": 82.75, "elapsed_time": "5:56:13", "remaining_time": "1:14:16", "throughput": 1485.39, "total_tokens": 31748288} {"current_steps": 150440, "total_steps": 181800, "loss": 0.0009, "lr": 4.396981226732089e-06, "epoch": 16.55005500550055, "percentage": 82.75, "elapsed_time": "5:56:14", "remaining_time": "1:14:15", "throughput": 1485.38, "total_tokens": 31749280} {"current_steps": 150445, "total_steps": 181800, "loss": 0.0013, "lr": 4.395621889359036e-06, "epoch": 16.55060506050605, "percentage": 82.75, "elapsed_time": "5:56:15", "remaining_time": "1:14:14", "throughput": 1485.38, "total_tokens": 31750272} {"current_steps": 150450, "total_steps": 181800, "loss": 0.0017, "lr": 4.3942627418866485e-06, "epoch": 16.551155115511552, "percentage": 82.76, "elapsed_time": "5:56:15", "remaining_time": "1:14:14", "throughput": 1485.38, "total_tokens": 31751328} {"current_steps": 150455, "total_steps": 181800, "loss": 0.001, "lr": 4.392903784327462e-06, "epoch": 16.551705170517053, "percentage": 82.76, "elapsed_time": "5:56:16", "remaining_time": "1:14:13", "throughput": 1485.38, "total_tokens": 31752352} {"current_steps": 150460, "total_steps": 181800, "loss": 0.0925, "lr": 4.391545016693985e-06, "epoch": 16.55225522552255, "percentage": 82.76, "elapsed_time": "5:56:17", "remaining_time": "1:14:12", "throughput": 1485.38, "total_tokens": 31753344} {"current_steps": 150465, "total_steps": 181800, "loss": 0.0182, "lr": 4.390186438998753e-06, "epoch": 16.55280528052805, "percentage": 82.76, "elapsed_time": "5:56:17", "remaining_time": "1:14:12", "throughput": 1485.38, "total_tokens": 31754400} {"current_steps": 150470, "total_steps": 181800, "loss": 0.104, "lr": 4.388828051254287e-06, "epoch": 16.553355335533553, "percentage": 82.77, "elapsed_time": "5:56:18", "remaining_time": "1:14:11", "throughput": 1485.38, "total_tokens": 31755424} {"current_steps": 150475, "total_steps": 181800, "loss": 0.0054, "lr": 4.387469853473095e-06, "epoch": 16.553905390539054, "percentage": 82.77, "elapsed_time": "5:56:19", "remaining_time": "1:14:10", "throughput": 1485.39, "total_tokens": 31756512} {"current_steps": 150480, "total_steps": 181800, "loss": 0.1417, "lr": 4.386111845667701e-06, "epoch": 16.554455445544555, "percentage": 82.77, "elapsed_time": "5:56:19", "remaining_time": "1:14:09", "throughput": 1485.39, "total_tokens": 31757568} {"current_steps": 150485, "total_steps": 181800, "loss": 0.001, "lr": 4.384754027850624e-06, "epoch": 16.555005500550056, "percentage": 82.78, "elapsed_time": "5:56:20", "remaining_time": "1:14:09", "throughput": 1485.39, "total_tokens": 31758592} {"current_steps": 150490, "total_steps": 181800, "loss": 0.0575, "lr": 4.383396400034381e-06, "epoch": 16.555555555555557, "percentage": 82.78, "elapsed_time": "5:56:21", "remaining_time": "1:14:08", "throughput": 1485.39, "total_tokens": 31759680} {"current_steps": 150495, "total_steps": 181800, "loss": 0.0036, "lr": 4.3820389622314825e-06, "epoch": 16.556105610561055, "percentage": 82.78, "elapsed_time": "5:56:22", "remaining_time": "1:14:07", "throughput": 1485.39, "total_tokens": 31760704} {"current_steps": 150500, "total_steps": 181800, "loss": 0.016, "lr": 4.380681714454432e-06, "epoch": 16.556655665566556, "percentage": 82.78, "elapsed_time": "5:56:22", "remaining_time": "1:14:07", "throughput": 1485.39, "total_tokens": 31761728} {"current_steps": 150505, "total_steps": 181800, "loss": 0.0986, "lr": 4.379324656715741e-06, "epoch": 16.557205720572057, "percentage": 82.79, "elapsed_time": "5:56:23", "remaining_time": "1:14:06", "throughput": 1485.39, "total_tokens": 31762784} {"current_steps": 150510, "total_steps": 181800, "loss": 0.0367, "lr": 4.377967789027923e-06, "epoch": 16.557755775577558, "percentage": 82.79, "elapsed_time": "5:56:24", "remaining_time": "1:14:05", "throughput": 1485.39, "total_tokens": 31763808} {"current_steps": 150515, "total_steps": 181800, "loss": 0.1724, "lr": 4.376611111403487e-06, "epoch": 16.55830583058306, "percentage": 82.79, "elapsed_time": "5:56:24", "remaining_time": "1:14:04", "throughput": 1485.39, "total_tokens": 31764832} {"current_steps": 150520, "total_steps": 181800, "loss": 0.0101, "lr": 4.375254623854927e-06, "epoch": 16.55885588558856, "percentage": 82.79, "elapsed_time": "5:56:25", "remaining_time": "1:14:04", "throughput": 1485.39, "total_tokens": 31765888} {"current_steps": 150525, "total_steps": 181800, "loss": 0.0054, "lr": 4.373898326394746e-06, "epoch": 16.55940594059406, "percentage": 82.8, "elapsed_time": "5:56:26", "remaining_time": "1:14:03", "throughput": 1485.39, "total_tokens": 31766944} {"current_steps": 150530, "total_steps": 181800, "loss": 0.0374, "lr": 4.37254221903545e-06, "epoch": 16.55995599559956, "percentage": 82.8, "elapsed_time": "5:56:26", "remaining_time": "1:14:02", "throughput": 1485.39, "total_tokens": 31767968} {"current_steps": 150535, "total_steps": 181800, "loss": 0.009, "lr": 4.371186301789529e-06, "epoch": 16.56050605060506, "percentage": 82.8, "elapsed_time": "5:56:27", "remaining_time": "1:14:02", "throughput": 1485.39, "total_tokens": 31768992} {"current_steps": 150540, "total_steps": 181800, "loss": 0.0025, "lr": 4.369830574669484e-06, "epoch": 16.56105610561056, "percentage": 82.81, "elapsed_time": "5:56:28", "remaining_time": "1:14:01", "throughput": 1485.39, "total_tokens": 31769984} {"current_steps": 150545, "total_steps": 181800, "loss": 0.0397, "lr": 4.368475037687819e-06, "epoch": 16.561606160616062, "percentage": 82.81, "elapsed_time": "5:56:28", "remaining_time": "1:14:00", "throughput": 1485.39, "total_tokens": 31771040} {"current_steps": 150550, "total_steps": 181800, "loss": 0.0961, "lr": 4.367119690857014e-06, "epoch": 16.562156215621563, "percentage": 82.81, "elapsed_time": "5:56:29", "remaining_time": "1:13:59", "throughput": 1485.39, "total_tokens": 31772064} {"current_steps": 150555, "total_steps": 181800, "loss": 0.006, "lr": 4.365764534189573e-06, "epoch": 16.562706270627064, "percentage": 82.81, "elapsed_time": "5:56:30", "remaining_time": "1:13:59", "throughput": 1485.39, "total_tokens": 31773056} {"current_steps": 150560, "total_steps": 181800, "loss": 0.0154, "lr": 4.364409567697972e-06, "epoch": 16.563256325632562, "percentage": 82.82, "elapsed_time": "5:56:31", "remaining_time": "1:13:58", "throughput": 1485.39, "total_tokens": 31774112} {"current_steps": 150565, "total_steps": 181800, "loss": 0.0997, "lr": 4.363054791394705e-06, "epoch": 16.563806380638063, "percentage": 82.82, "elapsed_time": "5:56:31", "remaining_time": "1:13:57", "throughput": 1485.4, "total_tokens": 31775168} {"current_steps": 150570, "total_steps": 181800, "loss": 0.0093, "lr": 4.361700205292265e-06, "epoch": 16.564356435643564, "percentage": 82.82, "elapsed_time": "5:56:32", "remaining_time": "1:13:57", "throughput": 1485.4, "total_tokens": 31776256} {"current_steps": 150575, "total_steps": 181800, "loss": 0.1098, "lr": 4.360345809403127e-06, "epoch": 16.564906490649065, "percentage": 82.82, "elapsed_time": "5:56:33", "remaining_time": "1:13:56", "throughput": 1485.4, "total_tokens": 31777312} {"current_steps": 150580, "total_steps": 181800, "loss": 0.0079, "lr": 4.358991603739782e-06, "epoch": 16.565456545654566, "percentage": 82.83, "elapsed_time": "5:56:33", "remaining_time": "1:13:55", "throughput": 1485.41, "total_tokens": 31778464} {"current_steps": 150585, "total_steps": 181800, "loss": 0.144, "lr": 4.357637588314708e-06, "epoch": 16.566006600660067, "percentage": 82.83, "elapsed_time": "5:56:34", "remaining_time": "1:13:54", "throughput": 1485.41, "total_tokens": 31779616} {"current_steps": 150590, "total_steps": 181800, "loss": 0.0039, "lr": 4.356283763140376e-06, "epoch": 16.566556655665565, "percentage": 82.83, "elapsed_time": "5:56:35", "remaining_time": "1:13:54", "throughput": 1485.41, "total_tokens": 31780640} {"current_steps": 150595, "total_steps": 181800, "loss": 0.1707, "lr": 4.354930128229273e-06, "epoch": 16.567106710671066, "percentage": 82.84, "elapsed_time": "5:56:35", "remaining_time": "1:13:53", "throughput": 1485.42, "total_tokens": 31781760} {"current_steps": 150600, "total_steps": 181800, "loss": 0.0025, "lr": 4.353576683593871e-06, "epoch": 16.567656765676567, "percentage": 82.84, "elapsed_time": "5:56:36", "remaining_time": "1:13:52", "throughput": 1485.42, "total_tokens": 31782848} {"current_steps": 150605, "total_steps": 181800, "loss": 0.0354, "lr": 4.3522234292466515e-06, "epoch": 16.568206820682068, "percentage": 82.84, "elapsed_time": "5:56:37", "remaining_time": "1:13:52", "throughput": 1485.42, "total_tokens": 31783872} {"current_steps": 150610, "total_steps": 181800, "loss": 0.036, "lr": 4.350870365200083e-06, "epoch": 16.56875687568757, "percentage": 82.84, "elapsed_time": "5:56:37", "remaining_time": "1:13:51", "throughput": 1485.42, "total_tokens": 31784992} {"current_steps": 150615, "total_steps": 181800, "loss": 0.0709, "lr": 4.349517491466623e-06, "epoch": 16.56930693069307, "percentage": 82.85, "elapsed_time": "5:56:38", "remaining_time": "1:13:50", "throughput": 1485.42, "total_tokens": 31785984} {"current_steps": 150620, "total_steps": 181800, "loss": 0.0068, "lr": 4.348164808058755e-06, "epoch": 16.56985698569857, "percentage": 82.85, "elapsed_time": "5:56:39", "remaining_time": "1:13:49", "throughput": 1485.42, "total_tokens": 31787072} {"current_steps": 150625, "total_steps": 181800, "loss": 0.0007, "lr": 4.346812314988943e-06, "epoch": 16.57040704070407, "percentage": 82.85, "elapsed_time": "5:56:40", "remaining_time": "1:13:49", "throughput": 1485.42, "total_tokens": 31788128} {"current_steps": 150630, "total_steps": 181800, "loss": 0.0635, "lr": 4.345460012269656e-06, "epoch": 16.57095709570957, "percentage": 82.85, "elapsed_time": "5:56:40", "remaining_time": "1:13:48", "throughput": 1485.43, "total_tokens": 31789248} {"current_steps": 150635, "total_steps": 181800, "loss": 0.0529, "lr": 4.344107899913352e-06, "epoch": 16.57150715071507, "percentage": 82.86, "elapsed_time": "5:56:41", "remaining_time": "1:13:47", "throughput": 1485.43, "total_tokens": 31790368} {"current_steps": 150640, "total_steps": 181800, "loss": 0.0458, "lr": 4.342755977932489e-06, "epoch": 16.572057205720572, "percentage": 82.86, "elapsed_time": "5:56:42", "remaining_time": "1:13:47", "throughput": 1485.44, "total_tokens": 31791488} {"current_steps": 150645, "total_steps": 181800, "loss": 0.0063, "lr": 4.341404246339539e-06, "epoch": 16.572607260726073, "percentage": 82.86, "elapsed_time": "5:56:42", "remaining_time": "1:13:46", "throughput": 1485.44, "total_tokens": 31792512} {"current_steps": 150650, "total_steps": 181800, "loss": 0.0027, "lr": 4.340052705146947e-06, "epoch": 16.573157315731574, "percentage": 82.87, "elapsed_time": "5:56:43", "remaining_time": "1:13:45", "throughput": 1485.44, "total_tokens": 31793536} {"current_steps": 150655, "total_steps": 181800, "loss": 0.009, "lr": 4.338701354367172e-06, "epoch": 16.573707370737075, "percentage": 82.87, "elapsed_time": "5:56:44", "remaining_time": "1:13:44", "throughput": 1485.43, "total_tokens": 31794496} {"current_steps": 150660, "total_steps": 181800, "loss": 0.0111, "lr": 4.337350194012682e-06, "epoch": 16.574257425742573, "percentage": 82.87, "elapsed_time": "5:56:44", "remaining_time": "1:13:44", "throughput": 1485.44, "total_tokens": 31795616} {"current_steps": 150665, "total_steps": 181800, "loss": 0.0072, "lr": 4.335999224095913e-06, "epoch": 16.574807480748074, "percentage": 82.87, "elapsed_time": "5:56:45", "remaining_time": "1:13:43", "throughput": 1485.44, "total_tokens": 31796672} {"current_steps": 150670, "total_steps": 181800, "loss": 0.0069, "lr": 4.33464844462933e-06, "epoch": 16.575357535753575, "percentage": 82.88, "elapsed_time": "5:56:46", "remaining_time": "1:13:42", "throughput": 1485.44, "total_tokens": 31797792} {"current_steps": 150675, "total_steps": 181800, "loss": 0.0014, "lr": 4.33329785562537e-06, "epoch": 16.575907590759076, "percentage": 82.88, "elapsed_time": "5:56:46", "remaining_time": "1:13:42", "throughput": 1485.45, "total_tokens": 31798848} {"current_steps": 150680, "total_steps": 181800, "loss": 0.0526, "lr": 4.331947457096486e-06, "epoch": 16.576457645764577, "percentage": 82.88, "elapsed_time": "5:56:47", "remaining_time": "1:13:41", "throughput": 1485.45, "total_tokens": 31799872} {"current_steps": 150685, "total_steps": 181800, "loss": 0.0036, "lr": 4.330597249055132e-06, "epoch": 16.57700770077008, "percentage": 82.89, "elapsed_time": "5:56:48", "remaining_time": "1:13:40", "throughput": 1485.45, "total_tokens": 31800992} {"current_steps": 150690, "total_steps": 181800, "loss": 0.0132, "lr": 4.329247231513739e-06, "epoch": 16.577557755775576, "percentage": 82.89, "elapsed_time": "5:56:49", "remaining_time": "1:13:39", "throughput": 1485.45, "total_tokens": 31802048} {"current_steps": 150695, "total_steps": 181800, "loss": 0.0023, "lr": 4.3278974044847595e-06, "epoch": 16.578107810781077, "percentage": 82.89, "elapsed_time": "5:56:49", "remaining_time": "1:13:39", "throughput": 1485.45, "total_tokens": 31803040} {"current_steps": 150700, "total_steps": 181800, "loss": 0.0092, "lr": 4.326547767980626e-06, "epoch": 16.578657865786578, "percentage": 82.89, "elapsed_time": "5:56:50", "remaining_time": "1:13:38", "throughput": 1485.45, "total_tokens": 31804128} {"current_steps": 150705, "total_steps": 181800, "loss": 0.0012, "lr": 4.325198322013787e-06, "epoch": 16.57920792079208, "percentage": 82.9, "elapsed_time": "5:56:51", "remaining_time": "1:13:37", "throughput": 1485.45, "total_tokens": 31805152} {"current_steps": 150710, "total_steps": 181800, "loss": 0.0025, "lr": 4.323849066596669e-06, "epoch": 16.57975797579758, "percentage": 82.9, "elapsed_time": "5:56:51", "remaining_time": "1:13:37", "throughput": 1485.46, "total_tokens": 31806208} {"current_steps": 150715, "total_steps": 181800, "loss": 0.004, "lr": 4.322500001741714e-06, "epoch": 16.58030803080308, "percentage": 82.9, "elapsed_time": "5:56:52", "remaining_time": "1:13:36", "throughput": 1485.46, "total_tokens": 31807264} {"current_steps": 150720, "total_steps": 181800, "loss": 0.0017, "lr": 4.321151127461359e-06, "epoch": 16.580858085808583, "percentage": 82.9, "elapsed_time": "5:56:53", "remaining_time": "1:13:35", "throughput": 1485.46, "total_tokens": 31808320} {"current_steps": 150725, "total_steps": 181800, "loss": 0.005, "lr": 4.319802443768025e-06, "epoch": 16.58140814081408, "percentage": 82.91, "elapsed_time": "5:56:53", "remaining_time": "1:13:34", "throughput": 1485.46, "total_tokens": 31809408} {"current_steps": 150730, "total_steps": 181800, "loss": 0.0025, "lr": 4.318453950674153e-06, "epoch": 16.58195819581958, "percentage": 82.91, "elapsed_time": "5:56:54", "remaining_time": "1:13:34", "throughput": 1485.46, "total_tokens": 31810496} {"current_steps": 150735, "total_steps": 181800, "loss": 0.0119, "lr": 4.317105648192171e-06, "epoch": 16.582508250825082, "percentage": 82.91, "elapsed_time": "5:56:55", "remaining_time": "1:13:33", "throughput": 1485.47, "total_tokens": 31811584} {"current_steps": 150740, "total_steps": 181800, "loss": 0.0285, "lr": 4.315757536334486e-06, "epoch": 16.583058305830583, "percentage": 82.92, "elapsed_time": "5:56:55", "remaining_time": "1:13:32", "throughput": 1485.47, "total_tokens": 31812704} {"current_steps": 150745, "total_steps": 181800, "loss": 0.1169, "lr": 4.314409615113552e-06, "epoch": 16.583608360836084, "percentage": 82.92, "elapsed_time": "5:56:56", "remaining_time": "1:13:32", "throughput": 1485.47, "total_tokens": 31813696} {"current_steps": 150750, "total_steps": 181800, "loss": 0.1682, "lr": 4.313061884541775e-06, "epoch": 16.584158415841586, "percentage": 82.92, "elapsed_time": "5:56:57", "remaining_time": "1:13:31", "throughput": 1485.47, "total_tokens": 31814752} {"current_steps": 150755, "total_steps": 181800, "loss": 0.005, "lr": 4.311714344631582e-06, "epoch": 16.584708470847083, "percentage": 82.92, "elapsed_time": "5:56:57", "remaining_time": "1:13:30", "throughput": 1485.48, "total_tokens": 31815840} {"current_steps": 150760, "total_steps": 181800, "loss": 0.0264, "lr": 4.3103669953953925e-06, "epoch": 16.585258525852584, "percentage": 82.93, "elapsed_time": "5:56:58", "remaining_time": "1:13:29", "throughput": 1485.48, "total_tokens": 31816928} {"current_steps": 150765, "total_steps": 181800, "loss": 0.0053, "lr": 4.309019836845615e-06, "epoch": 16.585808580858085, "percentage": 82.93, "elapsed_time": "5:56:59", "remaining_time": "1:13:29", "throughput": 1485.48, "total_tokens": 31818048} {"current_steps": 150770, "total_steps": 181800, "loss": 0.0538, "lr": 4.307672868994675e-06, "epoch": 16.586358635863586, "percentage": 82.93, "elapsed_time": "5:57:00", "remaining_time": "1:13:28", "throughput": 1485.48, "total_tokens": 31819072} {"current_steps": 150775, "total_steps": 181800, "loss": 0.0239, "lr": 4.306326091854992e-06, "epoch": 16.586908690869087, "percentage": 82.93, "elapsed_time": "5:57:00", "remaining_time": "1:13:27", "throughput": 1485.48, "total_tokens": 31820096} {"current_steps": 150780, "total_steps": 181800, "loss": 0.012, "lr": 4.304979505438964e-06, "epoch": 16.58745874587459, "percentage": 82.94, "elapsed_time": "5:57:01", "remaining_time": "1:13:27", "throughput": 1485.49, "total_tokens": 31821184} {"current_steps": 150785, "total_steps": 181800, "loss": 0.0048, "lr": 4.303633109759015e-06, "epoch": 16.58800880088009, "percentage": 82.94, "elapsed_time": "5:57:02", "remaining_time": "1:13:26", "throughput": 1485.48, "total_tokens": 31822144} {"current_steps": 150790, "total_steps": 181800, "loss": 0.0064, "lr": 4.302286904827543e-06, "epoch": 16.588558855885587, "percentage": 82.94, "elapsed_time": "5:57:02", "remaining_time": "1:13:25", "throughput": 1485.48, "total_tokens": 31823200} {"current_steps": 150795, "total_steps": 181800, "loss": 0.0037, "lr": 4.300940890656963e-06, "epoch": 16.58910891089109, "percentage": 82.95, "elapsed_time": "5:57:03", "remaining_time": "1:13:24", "throughput": 1485.49, "total_tokens": 31824256} {"current_steps": 150800, "total_steps": 181800, "loss": 0.0097, "lr": 4.299595067259682e-06, "epoch": 16.58965896589659, "percentage": 82.95, "elapsed_time": "5:57:04", "remaining_time": "1:13:24", "throughput": 1485.49, "total_tokens": 31825312} {"current_steps": 150805, "total_steps": 181800, "loss": 0.0568, "lr": 4.298249434648094e-06, "epoch": 16.59020902090209, "percentage": 82.95, "elapsed_time": "5:57:04", "remaining_time": "1:13:23", "throughput": 1485.48, "total_tokens": 31826304} {"current_steps": 150810, "total_steps": 181800, "loss": 0.0821, "lr": 4.296903992834614e-06, "epoch": 16.59075907590759, "percentage": 82.95, "elapsed_time": "5:57:05", "remaining_time": "1:13:22", "throughput": 1485.49, "total_tokens": 31827360} {"current_steps": 150815, "total_steps": 181800, "loss": 0.0013, "lr": 4.295558741831629e-06, "epoch": 16.591309130913093, "percentage": 82.96, "elapsed_time": "5:57:06", "remaining_time": "1:13:22", "throughput": 1485.49, "total_tokens": 31828448} {"current_steps": 150820, "total_steps": 181800, "loss": 0.0029, "lr": 4.294213681651552e-06, "epoch": 16.59185918591859, "percentage": 82.96, "elapsed_time": "5:57:06", "remaining_time": "1:13:21", "throughput": 1485.49, "total_tokens": 31829536} {"current_steps": 150825, "total_steps": 181800, "loss": 0.0037, "lr": 4.292868812306763e-06, "epoch": 16.59240924092409, "percentage": 82.96, "elapsed_time": "5:57:07", "remaining_time": "1:13:20", "throughput": 1485.49, "total_tokens": 31830624} {"current_steps": 150830, "total_steps": 181800, "loss": 0.0022, "lr": 4.291524133809668e-06, "epoch": 16.592959295929592, "percentage": 82.96, "elapsed_time": "5:57:08", "remaining_time": "1:13:19", "throughput": 1485.49, "total_tokens": 31831648} {"current_steps": 150835, "total_steps": 181800, "loss": 0.0036, "lr": 4.290179646172665e-06, "epoch": 16.593509350935093, "percentage": 82.97, "elapsed_time": "5:57:09", "remaining_time": "1:13:19", "throughput": 1485.5, "total_tokens": 31832704} {"current_steps": 150840, "total_steps": 181800, "loss": 0.0024, "lr": 4.288835349408132e-06, "epoch": 16.594059405940595, "percentage": 82.97, "elapsed_time": "5:57:09", "remaining_time": "1:13:18", "throughput": 1485.5, "total_tokens": 31833760} {"current_steps": 150845, "total_steps": 181800, "loss": 0.0284, "lr": 4.287491243528471e-06, "epoch": 16.594609460946096, "percentage": 82.97, "elapsed_time": "5:57:10", "remaining_time": "1:13:17", "throughput": 1485.5, "total_tokens": 31834816} {"current_steps": 150850, "total_steps": 181800, "loss": 0.0038, "lr": 4.2861473285460644e-06, "epoch": 16.595159515951597, "percentage": 82.98, "elapsed_time": "5:57:11", "remaining_time": "1:13:17", "throughput": 1485.5, "total_tokens": 31835840} {"current_steps": 150855, "total_steps": 181800, "loss": 0.0018, "lr": 4.284803604473284e-06, "epoch": 16.595709570957094, "percentage": 82.98, "elapsed_time": "5:57:11", "remaining_time": "1:13:16", "throughput": 1485.5, "total_tokens": 31836896} {"current_steps": 150860, "total_steps": 181800, "loss": 0.0536, "lr": 4.283460071322543e-06, "epoch": 16.596259625962595, "percentage": 82.98, "elapsed_time": "5:57:12", "remaining_time": "1:13:15", "throughput": 1485.5, "total_tokens": 31837920} {"current_steps": 150865, "total_steps": 181800, "loss": 0.0019, "lr": 4.282116729106203e-06, "epoch": 16.596809680968097, "percentage": 82.98, "elapsed_time": "5:57:13", "remaining_time": "1:13:14", "throughput": 1485.5, "total_tokens": 31839008} {"current_steps": 150870, "total_steps": 181800, "loss": 0.0039, "lr": 4.280773577836661e-06, "epoch": 16.597359735973598, "percentage": 82.99, "elapsed_time": "5:57:13", "remaining_time": "1:13:14", "throughput": 1485.5, "total_tokens": 31840064} {"current_steps": 150875, "total_steps": 181800, "loss": 0.0008, "lr": 4.279430617526284e-06, "epoch": 16.5979097909791, "percentage": 82.99, "elapsed_time": "5:57:14", "remaining_time": "1:13:13", "throughput": 1485.5, "total_tokens": 31841088} {"current_steps": 150880, "total_steps": 181800, "loss": 0.0034, "lr": 4.2780878481874456e-06, "epoch": 16.5984598459846, "percentage": 82.99, "elapsed_time": "5:57:15", "remaining_time": "1:13:12", "throughput": 1485.5, "total_tokens": 31842112} {"current_steps": 150885, "total_steps": 181800, "loss": 0.0389, "lr": 4.27674526983253e-06, "epoch": 16.599009900990097, "percentage": 83.0, "elapsed_time": "5:57:15", "remaining_time": "1:13:12", "throughput": 1485.51, "total_tokens": 31843200} {"current_steps": 150890, "total_steps": 181800, "loss": 0.05, "lr": 4.275402882473908e-06, "epoch": 16.5995599559956, "percentage": 83.0, "elapsed_time": "5:57:16", "remaining_time": "1:13:11", "throughput": 1485.51, "total_tokens": 31844320} {"current_steps": 150895, "total_steps": 181800, "loss": 0.1316, "lr": 4.274060686123959e-06, "epoch": 16.6001100110011, "percentage": 83.0, "elapsed_time": "5:57:17", "remaining_time": "1:13:10", "throughput": 1485.51, "total_tokens": 31845344} {"current_steps": 150900, "total_steps": 181800, "loss": 0.0052, "lr": 4.272718680795049e-06, "epoch": 16.6006600660066, "percentage": 83.0, "elapsed_time": "5:57:17", "remaining_time": "1:13:09", "throughput": 1485.51, "total_tokens": 31846336} {"current_steps": 150905, "total_steps": 181800, "loss": 0.0296, "lr": 4.271376866499535e-06, "epoch": 16.6012101210121, "percentage": 83.01, "elapsed_time": "5:57:18", "remaining_time": "1:13:09", "throughput": 1485.51, "total_tokens": 31847392} {"current_steps": 150910, "total_steps": 181800, "loss": 0.0024, "lr": 4.270035243249803e-06, "epoch": 16.601760176017603, "percentage": 83.01, "elapsed_time": "5:57:19", "remaining_time": "1:13:08", "throughput": 1485.51, "total_tokens": 31848448} {"current_steps": 150915, "total_steps": 181800, "loss": 0.0486, "lr": 4.268693811058197e-06, "epoch": 16.602310231023104, "percentage": 83.01, "elapsed_time": "5:57:20", "remaining_time": "1:13:07", "throughput": 1485.52, "total_tokens": 31849504} {"current_steps": 150920, "total_steps": 181800, "loss": 0.0028, "lr": 4.267352569937105e-06, "epoch": 16.6028602860286, "percentage": 83.01, "elapsed_time": "5:57:20", "remaining_time": "1:13:07", "throughput": 1485.52, "total_tokens": 31850592} {"current_steps": 150925, "total_steps": 181800, "loss": 0.0376, "lr": 4.266011519898874e-06, "epoch": 16.603410341034103, "percentage": 83.02, "elapsed_time": "5:57:21", "remaining_time": "1:13:06", "throughput": 1485.52, "total_tokens": 31851648} {"current_steps": 150930, "total_steps": 181800, "loss": 0.005, "lr": 4.2646706609558605e-06, "epoch": 16.603960396039604, "percentage": 83.02, "elapsed_time": "5:57:22", "remaining_time": "1:13:05", "throughput": 1485.52, "total_tokens": 31852672} {"current_steps": 150935, "total_steps": 181800, "loss": 0.0009, "lr": 4.263329993120432e-06, "epoch": 16.604510451045105, "percentage": 83.02, "elapsed_time": "5:57:22", "remaining_time": "1:13:04", "throughput": 1485.52, "total_tokens": 31853728} {"current_steps": 150940, "total_steps": 181800, "loss": 0.005, "lr": 4.261989516404938e-06, "epoch": 16.605060506050606, "percentage": 83.03, "elapsed_time": "5:57:23", "remaining_time": "1:13:04", "throughput": 1485.52, "total_tokens": 31854720} {"current_steps": 150945, "total_steps": 181800, "loss": 0.0052, "lr": 4.260649230821734e-06, "epoch": 16.605610561056107, "percentage": 83.03, "elapsed_time": "5:57:24", "remaining_time": "1:13:03", "throughput": 1485.52, "total_tokens": 31855808} {"current_steps": 150950, "total_steps": 181800, "loss": 0.0033, "lr": 4.25930913638318e-06, "epoch": 16.606160616061608, "percentage": 83.03, "elapsed_time": "5:57:24", "remaining_time": "1:13:02", "throughput": 1485.52, "total_tokens": 31856832} {"current_steps": 150955, "total_steps": 181800, "loss": 0.0008, "lr": 4.257969233101614e-06, "epoch": 16.606710671067106, "percentage": 83.03, "elapsed_time": "5:57:25", "remaining_time": "1:13:02", "throughput": 1485.52, "total_tokens": 31857824} {"current_steps": 150960, "total_steps": 181800, "loss": 0.0112, "lr": 4.2566295209894e-06, "epoch": 16.607260726072607, "percentage": 83.04, "elapsed_time": "5:57:26", "remaining_time": "1:13:01", "throughput": 1485.52, "total_tokens": 31858944} {"current_steps": 150965, "total_steps": 181800, "loss": 0.0091, "lr": 4.255290000058879e-06, "epoch": 16.607810781078108, "percentage": 83.04, "elapsed_time": "5:57:26", "remaining_time": "1:13:00", "throughput": 1485.53, "total_tokens": 31860000} {"current_steps": 150970, "total_steps": 181800, "loss": 0.0032, "lr": 4.253950670322388e-06, "epoch": 16.60836083608361, "percentage": 83.04, "elapsed_time": "5:57:27", "remaining_time": "1:12:59", "throughput": 1485.53, "total_tokens": 31861024} {"current_steps": 150975, "total_steps": 181800, "loss": 0.0065, "lr": 4.25261153179228e-06, "epoch": 16.60891089108911, "percentage": 83.04, "elapsed_time": "5:57:28", "remaining_time": "1:12:59", "throughput": 1485.53, "total_tokens": 31862080} {"current_steps": 150980, "total_steps": 181800, "loss": 0.0062, "lr": 4.251272584480894e-06, "epoch": 16.60946094609461, "percentage": 83.05, "elapsed_time": "5:57:29", "remaining_time": "1:12:58", "throughput": 1485.53, "total_tokens": 31863136} {"current_steps": 150985, "total_steps": 181800, "loss": 0.0162, "lr": 4.249933828400582e-06, "epoch": 16.61001100110011, "percentage": 83.05, "elapsed_time": "5:57:29", "remaining_time": "1:12:57", "throughput": 1485.53, "total_tokens": 31864256} {"current_steps": 150990, "total_steps": 181800, "loss": 0.0365, "lr": 4.2485952635636705e-06, "epoch": 16.61056105610561, "percentage": 83.05, "elapsed_time": "5:57:30", "remaining_time": "1:12:57", "throughput": 1485.53, "total_tokens": 31865280} {"current_steps": 150995, "total_steps": 181800, "loss": 0.0031, "lr": 4.247256889982493e-06, "epoch": 16.61111111111111, "percentage": 83.06, "elapsed_time": "5:57:31", "remaining_time": "1:12:56", "throughput": 1485.54, "total_tokens": 31866400} {"current_steps": 151000, "total_steps": 181800, "loss": 0.1201, "lr": 4.245918707669391e-06, "epoch": 16.611661166116612, "percentage": 83.06, "elapsed_time": "5:57:31", "remaining_time": "1:12:55", "throughput": 1485.54, "total_tokens": 31867424} {"current_steps": 151005, "total_steps": 181800, "loss": 0.0035, "lr": 4.244580716636698e-06, "epoch": 16.612211221122113, "percentage": 83.06, "elapsed_time": "5:57:32", "remaining_time": "1:12:54", "throughput": 1485.54, "total_tokens": 31868480} {"current_steps": 151010, "total_steps": 181800, "loss": 0.0012, "lr": 4.24324291689675e-06, "epoch": 16.612761276127614, "percentage": 83.06, "elapsed_time": "5:57:33", "remaining_time": "1:12:54", "throughput": 1485.55, "total_tokens": 31869632} {"current_steps": 151015, "total_steps": 181800, "loss": 0.0232, "lr": 4.2419053084618746e-06, "epoch": 16.61331133113311, "percentage": 83.07, "elapsed_time": "5:57:33", "remaining_time": "1:12:53", "throughput": 1485.55, "total_tokens": 31870688} {"current_steps": 151020, "total_steps": 181800, "loss": 0.0425, "lr": 4.240567891344388e-06, "epoch": 16.613861386138613, "percentage": 83.07, "elapsed_time": "5:57:34", "remaining_time": "1:12:52", "throughput": 1485.55, "total_tokens": 31871776} {"current_steps": 151025, "total_steps": 181800, "loss": 0.0077, "lr": 4.239230665556634e-06, "epoch": 16.614411441144114, "percentage": 83.07, "elapsed_time": "5:57:35", "remaining_time": "1:12:52", "throughput": 1485.55, "total_tokens": 31872800} {"current_steps": 151030, "total_steps": 181800, "loss": 0.0703, "lr": 4.23789363111092e-06, "epoch": 16.614961496149615, "percentage": 83.07, "elapsed_time": "5:57:35", "remaining_time": "1:12:51", "throughput": 1485.55, "total_tokens": 31873824} {"current_steps": 151035, "total_steps": 181800, "loss": 0.005, "lr": 4.23655678801958e-06, "epoch": 16.615511551155116, "percentage": 83.08, "elapsed_time": "5:57:36", "remaining_time": "1:12:50", "throughput": 1485.55, "total_tokens": 31874880} {"current_steps": 151040, "total_steps": 181800, "loss": 0.0027, "lr": 4.23522013629494e-06, "epoch": 16.616061606160617, "percentage": 83.08, "elapsed_time": "5:57:37", "remaining_time": "1:12:49", "throughput": 1485.55, "total_tokens": 31875936} {"current_steps": 151045, "total_steps": 181800, "loss": 0.1051, "lr": 4.233883675949304e-06, "epoch": 16.616611661166118, "percentage": 83.08, "elapsed_time": "5:57:37", "remaining_time": "1:12:49", "throughput": 1485.55, "total_tokens": 31876928} {"current_steps": 151050, "total_steps": 181800, "loss": 0.0075, "lr": 4.232547406995005e-06, "epoch": 16.617161716171616, "percentage": 83.09, "elapsed_time": "5:57:38", "remaining_time": "1:12:48", "throughput": 1485.55, "total_tokens": 31877984} {"current_steps": 151055, "total_steps": 181800, "loss": 0.0021, "lr": 4.231211329444346e-06, "epoch": 16.617711771177117, "percentage": 83.09, "elapsed_time": "5:57:39", "remaining_time": "1:12:47", "throughput": 1485.56, "total_tokens": 31879040} {"current_steps": 151060, "total_steps": 181800, "loss": 0.0034, "lr": 4.229875443309645e-06, "epoch": 16.618261826182618, "percentage": 83.09, "elapsed_time": "5:57:40", "remaining_time": "1:12:47", "throughput": 1485.56, "total_tokens": 31880096} {"current_steps": 151065, "total_steps": 181800, "loss": 0.0015, "lr": 4.228539748603219e-06, "epoch": 16.61881188118812, "percentage": 83.09, "elapsed_time": "5:57:40", "remaining_time": "1:12:46", "throughput": 1485.56, "total_tokens": 31881152} {"current_steps": 151070, "total_steps": 181800, "loss": 0.0031, "lr": 4.227204245337374e-06, "epoch": 16.61936193619362, "percentage": 83.1, "elapsed_time": "5:57:41", "remaining_time": "1:12:45", "throughput": 1485.56, "total_tokens": 31882176} {"current_steps": 151075, "total_steps": 181800, "loss": 0.0624, "lr": 4.225868933524421e-06, "epoch": 16.61991199119912, "percentage": 83.1, "elapsed_time": "5:57:42", "remaining_time": "1:12:44", "throughput": 1485.56, "total_tokens": 31883232} {"current_steps": 151080, "total_steps": 181800, "loss": 0.0013, "lr": 4.224533813176662e-06, "epoch": 16.620462046204622, "percentage": 83.1, "elapsed_time": "5:57:42", "remaining_time": "1:12:44", "throughput": 1485.56, "total_tokens": 31884224} {"current_steps": 151085, "total_steps": 181800, "loss": 0.0035, "lr": 4.223198884306412e-06, "epoch": 16.62101210121012, "percentage": 83.11, "elapsed_time": "5:57:43", "remaining_time": "1:12:43", "throughput": 1485.56, "total_tokens": 31885248} {"current_steps": 151090, "total_steps": 181800, "loss": 0.0023, "lr": 4.221864146925963e-06, "epoch": 16.62156215621562, "percentage": 83.11, "elapsed_time": "5:57:44", "remaining_time": "1:12:42", "throughput": 1485.56, "total_tokens": 31886304} {"current_steps": 151095, "total_steps": 181800, "loss": 0.0073, "lr": 4.220529601047621e-06, "epoch": 16.622112211221122, "percentage": 83.11, "elapsed_time": "5:57:44", "remaining_time": "1:12:42", "throughput": 1485.56, "total_tokens": 31887360} {"current_steps": 151100, "total_steps": 181800, "loss": 0.0072, "lr": 4.219195246683691e-06, "epoch": 16.622662266226623, "percentage": 83.11, "elapsed_time": "5:57:45", "remaining_time": "1:12:41", "throughput": 1485.56, "total_tokens": 31888384} {"current_steps": 151105, "total_steps": 181800, "loss": 0.0038, "lr": 4.217861083846464e-06, "epoch": 16.623212321232124, "percentage": 83.12, "elapsed_time": "5:57:46", "remaining_time": "1:12:40", "throughput": 1485.56, "total_tokens": 31889408} {"current_steps": 151110, "total_steps": 181800, "loss": 0.0115, "lr": 4.216527112548243e-06, "epoch": 16.623762376237625, "percentage": 83.12, "elapsed_time": "5:57:46", "remaining_time": "1:12:39", "throughput": 1485.56, "total_tokens": 31890496} {"current_steps": 151115, "total_steps": 181800, "loss": 0.0338, "lr": 4.2151933328013125e-06, "epoch": 16.624312431243123, "percentage": 83.12, "elapsed_time": "5:57:47", "remaining_time": "1:12:39", "throughput": 1485.57, "total_tokens": 31891584} {"current_steps": 151120, "total_steps": 181800, "loss": 0.0052, "lr": 4.213859744617973e-06, "epoch": 16.624862486248624, "percentage": 83.12, "elapsed_time": "5:57:48", "remaining_time": "1:12:38", "throughput": 1485.57, "total_tokens": 31892672} {"current_steps": 151125, "total_steps": 181800, "loss": 0.0246, "lr": 4.21252634801052e-06, "epoch": 16.625412541254125, "percentage": 83.13, "elapsed_time": "5:57:49", "remaining_time": "1:12:37", "throughput": 1485.57, "total_tokens": 31893728} {"current_steps": 151130, "total_steps": 181800, "loss": 0.0013, "lr": 4.21119314299123e-06, "epoch": 16.625962596259626, "percentage": 83.13, "elapsed_time": "5:57:49", "remaining_time": "1:12:37", "throughput": 1485.57, "total_tokens": 31894752} {"current_steps": 151135, "total_steps": 181800, "loss": 0.003, "lr": 4.209860129572404e-06, "epoch": 16.626512651265127, "percentage": 83.13, "elapsed_time": "5:57:50", "remaining_time": "1:12:36", "throughput": 1485.57, "total_tokens": 31895776} {"current_steps": 151140, "total_steps": 181800, "loss": 0.0022, "lr": 4.208527307766319e-06, "epoch": 16.627062706270628, "percentage": 83.14, "elapsed_time": "5:57:51", "remaining_time": "1:12:35", "throughput": 1485.57, "total_tokens": 31896832} {"current_steps": 151145, "total_steps": 181800, "loss": 0.0023, "lr": 4.207194677585258e-06, "epoch": 16.62761276127613, "percentage": 83.14, "elapsed_time": "5:57:51", "remaining_time": "1:12:34", "throughput": 1485.57, "total_tokens": 31897888} {"current_steps": 151150, "total_steps": 181800, "loss": 0.0337, "lr": 4.205862239041505e-06, "epoch": 16.628162816281627, "percentage": 83.14, "elapsed_time": "5:57:52", "remaining_time": "1:12:34", "throughput": 1485.58, "total_tokens": 31898944} {"current_steps": 151155, "total_steps": 181800, "loss": 0.0098, "lr": 4.204529992147346e-06, "epoch": 16.628712871287128, "percentage": 83.14, "elapsed_time": "5:57:53", "remaining_time": "1:12:33", "throughput": 1485.58, "total_tokens": 31900032} {"current_steps": 151160, "total_steps": 181800, "loss": 0.0025, "lr": 4.203197936915051e-06, "epoch": 16.62926292629263, "percentage": 83.15, "elapsed_time": "5:57:53", "remaining_time": "1:12:32", "throughput": 1485.59, "total_tokens": 31901184} {"current_steps": 151165, "total_steps": 181800, "loss": 0.0712, "lr": 4.201866073356908e-06, "epoch": 16.62981298129813, "percentage": 83.15, "elapsed_time": "5:57:54", "remaining_time": "1:12:32", "throughput": 1485.59, "total_tokens": 31902272} {"current_steps": 151170, "total_steps": 181800, "loss": 0.093, "lr": 4.200534401485179e-06, "epoch": 16.63036303630363, "percentage": 83.15, "elapsed_time": "5:57:55", "remaining_time": "1:12:31", "throughput": 1485.59, "total_tokens": 31903328} {"current_steps": 151175, "total_steps": 181800, "loss": 0.0007, "lr": 4.1992029213121455e-06, "epoch": 16.630913091309132, "percentage": 83.15, "elapsed_time": "5:57:55", "remaining_time": "1:12:30", "throughput": 1485.59, "total_tokens": 31904416} {"current_steps": 151180, "total_steps": 181800, "loss": 0.0006, "lr": 4.197871632850081e-06, "epoch": 16.63146314631463, "percentage": 83.16, "elapsed_time": "5:57:56", "remaining_time": "1:12:29", "throughput": 1485.59, "total_tokens": 31905440} {"current_steps": 151185, "total_steps": 181800, "loss": 0.0338, "lr": 4.196540536111246e-06, "epoch": 16.63201320132013, "percentage": 83.16, "elapsed_time": "5:57:57", "remaining_time": "1:12:29", "throughput": 1485.59, "total_tokens": 31906496} {"current_steps": 151190, "total_steps": 181800, "loss": 0.1177, "lr": 4.195209631107921e-06, "epoch": 16.632563256325632, "percentage": 83.16, "elapsed_time": "5:57:57", "remaining_time": "1:12:28", "throughput": 1485.59, "total_tokens": 31907552} {"current_steps": 151195, "total_steps": 181800, "loss": 0.0094, "lr": 4.193878917852362e-06, "epoch": 16.633113311331133, "percentage": 83.17, "elapsed_time": "5:57:58", "remaining_time": "1:12:27", "throughput": 1485.59, "total_tokens": 31908576} {"current_steps": 151200, "total_steps": 181800, "loss": 0.005, "lr": 4.1925483963568405e-06, "epoch": 16.633663366336634, "percentage": 83.17, "elapsed_time": "5:57:59", "remaining_time": "1:12:27", "throughput": 1485.6, "total_tokens": 31909664} {"current_steps": 151205, "total_steps": 181800, "loss": 0.0115, "lr": 4.191218066633609e-06, "epoch": 16.634213421342135, "percentage": 83.17, "elapsed_time": "5:58:00", "remaining_time": "1:12:26", "throughput": 1485.6, "total_tokens": 31910720} {"current_steps": 151210, "total_steps": 181800, "loss": 0.0047, "lr": 4.189887928694939e-06, "epoch": 16.634763476347636, "percentage": 83.17, "elapsed_time": "5:58:00", "remaining_time": "1:12:25", "throughput": 1485.6, "total_tokens": 31911776} {"current_steps": 151215, "total_steps": 181800, "loss": 0.008, "lr": 4.18855798255309e-06, "epoch": 16.635313531353134, "percentage": 83.18, "elapsed_time": "5:58:01", "remaining_time": "1:12:24", "throughput": 1485.6, "total_tokens": 31912864} {"current_steps": 151220, "total_steps": 181800, "loss": 0.0017, "lr": 4.1872282282203105e-06, "epoch": 16.635863586358635, "percentage": 83.18, "elapsed_time": "5:58:02", "remaining_time": "1:12:24", "throughput": 1485.6, "total_tokens": 31913952} {"current_steps": 151225, "total_steps": 181800, "loss": 0.0653, "lr": 4.185898665708868e-06, "epoch": 16.636413641364136, "percentage": 83.18, "elapsed_time": "5:58:02", "remaining_time": "1:12:23", "throughput": 1485.6, "total_tokens": 31914976} {"current_steps": 151230, "total_steps": 181800, "loss": 0.01, "lr": 4.184569295031002e-06, "epoch": 16.636963696369637, "percentage": 83.18, "elapsed_time": "5:58:03", "remaining_time": "1:12:22", "throughput": 1485.61, "total_tokens": 31916032} {"current_steps": 151235, "total_steps": 181800, "loss": 0.0097, "lr": 4.183240116198975e-06, "epoch": 16.63751375137514, "percentage": 83.19, "elapsed_time": "5:58:04", "remaining_time": "1:12:22", "throughput": 1485.61, "total_tokens": 31917088} {"current_steps": 151240, "total_steps": 181800, "loss": 0.0019, "lr": 4.181911129225039e-06, "epoch": 16.63806380638064, "percentage": 83.19, "elapsed_time": "5:58:04", "remaining_time": "1:12:21", "throughput": 1485.61, "total_tokens": 31918208} {"current_steps": 151245, "total_steps": 181800, "loss": 0.0373, "lr": 4.180582334121433e-06, "epoch": 16.638613861386137, "percentage": 83.19, "elapsed_time": "5:58:05", "remaining_time": "1:12:20", "throughput": 1485.61, "total_tokens": 31919264} {"current_steps": 151250, "total_steps": 181800, "loss": 0.0116, "lr": 4.179253730900418e-06, "epoch": 16.639163916391638, "percentage": 83.2, "elapsed_time": "5:58:06", "remaining_time": "1:12:19", "throughput": 1485.61, "total_tokens": 31920320} {"current_steps": 151255, "total_steps": 181800, "loss": 0.0078, "lr": 4.177925319574228e-06, "epoch": 16.63971397139714, "percentage": 83.2, "elapsed_time": "5:58:06", "remaining_time": "1:12:19", "throughput": 1485.62, "total_tokens": 31921376} {"current_steps": 151260, "total_steps": 181800, "loss": 0.0035, "lr": 4.176597100155103e-06, "epoch": 16.64026402640264, "percentage": 83.2, "elapsed_time": "5:58:07", "remaining_time": "1:12:18", "throughput": 1485.62, "total_tokens": 31922528} {"current_steps": 151265, "total_steps": 181800, "loss": 0.0077, "lr": 4.175269072655291e-06, "epoch": 16.64081408140814, "percentage": 83.2, "elapsed_time": "5:58:08", "remaining_time": "1:12:17", "throughput": 1485.62, "total_tokens": 31923552} {"current_steps": 151270, "total_steps": 181800, "loss": 0.0014, "lr": 4.173941237087031e-06, "epoch": 16.641364136413642, "percentage": 83.21, "elapsed_time": "5:58:09", "remaining_time": "1:12:17", "throughput": 1485.62, "total_tokens": 31924640} {"current_steps": 151275, "total_steps": 181800, "loss": 0.0016, "lr": 4.172613593462566e-06, "epoch": 16.641914191419144, "percentage": 83.21, "elapsed_time": "5:58:09", "remaining_time": "1:12:16", "throughput": 1485.63, "total_tokens": 31925728} {"current_steps": 151280, "total_steps": 181800, "loss": 0.0499, "lr": 4.171286141794131e-06, "epoch": 16.64246424642464, "percentage": 83.21, "elapsed_time": "5:58:10", "remaining_time": "1:12:15", "throughput": 1485.63, "total_tokens": 31926720} {"current_steps": 151285, "total_steps": 181800, "loss": 0.0006, "lr": 4.1699588820939466e-06, "epoch": 16.643014301430142, "percentage": 83.22, "elapsed_time": "5:58:11", "remaining_time": "1:12:14", "throughput": 1485.63, "total_tokens": 31927776} {"current_steps": 151290, "total_steps": 181800, "loss": 0.006, "lr": 4.1686318143742604e-06, "epoch": 16.643564356435643, "percentage": 83.22, "elapsed_time": "5:58:11", "remaining_time": "1:12:14", "throughput": 1485.63, "total_tokens": 31928832} {"current_steps": 151295, "total_steps": 181800, "loss": 0.072, "lr": 4.167304938647296e-06, "epoch": 16.644114411441144, "percentage": 83.22, "elapsed_time": "5:58:12", "remaining_time": "1:12:13", "throughput": 1485.63, "total_tokens": 31929920} {"current_steps": 151300, "total_steps": 181800, "loss": 0.1216, "lr": 4.1659782549252925e-06, "epoch": 16.644664466446645, "percentage": 83.22, "elapsed_time": "5:58:13", "remaining_time": "1:12:12", "throughput": 1485.63, "total_tokens": 31930912} {"current_steps": 151305, "total_steps": 181800, "loss": 0.0014, "lr": 4.16465176322047e-06, "epoch": 16.645214521452147, "percentage": 83.23, "elapsed_time": "5:58:13", "remaining_time": "1:12:12", "throughput": 1485.63, "total_tokens": 31931968} {"current_steps": 151310, "total_steps": 181800, "loss": 0.0039, "lr": 4.163325463545048e-06, "epoch": 16.645764576457644, "percentage": 83.23, "elapsed_time": "5:58:14", "remaining_time": "1:12:11", "throughput": 1485.64, "total_tokens": 31933088} {"current_steps": 151315, "total_steps": 181800, "loss": 0.003, "lr": 4.161999355911264e-06, "epoch": 16.646314631463145, "percentage": 83.23, "elapsed_time": "5:58:15", "remaining_time": "1:12:10", "throughput": 1485.63, "total_tokens": 31934080} {"current_steps": 151320, "total_steps": 181800, "loss": 0.0411, "lr": 4.160673440331328e-06, "epoch": 16.646864686468646, "percentage": 83.23, "elapsed_time": "5:58:15", "remaining_time": "1:12:09", "throughput": 1485.64, "total_tokens": 31935136} {"current_steps": 151325, "total_steps": 181800, "loss": 0.0049, "lr": 4.159347716817463e-06, "epoch": 16.647414741474147, "percentage": 83.24, "elapsed_time": "5:58:16", "remaining_time": "1:12:09", "throughput": 1485.64, "total_tokens": 31936192} {"current_steps": 151330, "total_steps": 181800, "loss": 0.0798, "lr": 4.158022185381896e-06, "epoch": 16.64796479647965, "percentage": 83.24, "elapsed_time": "5:58:17", "remaining_time": "1:12:08", "throughput": 1485.64, "total_tokens": 31937216} {"current_steps": 151335, "total_steps": 181800, "loss": 0.087, "lr": 4.156696846036831e-06, "epoch": 16.64851485148515, "percentage": 83.24, "elapsed_time": "5:58:18", "remaining_time": "1:12:07", "throughput": 1485.64, "total_tokens": 31938272} {"current_steps": 151340, "total_steps": 181800, "loss": 0.0011, "lr": 4.155371698794497e-06, "epoch": 16.64906490649065, "percentage": 83.25, "elapsed_time": "5:58:18", "remaining_time": "1:12:07", "throughput": 1485.64, "total_tokens": 31939264} {"current_steps": 151345, "total_steps": 181800, "loss": 0.0107, "lr": 4.1540467436670946e-06, "epoch": 16.649614961496148, "percentage": 83.25, "elapsed_time": "5:58:19", "remaining_time": "1:12:06", "throughput": 1485.64, "total_tokens": 31940288} {"current_steps": 151350, "total_steps": 181800, "loss": 0.0011, "lr": 4.1527219806668375e-06, "epoch": 16.65016501650165, "percentage": 83.25, "elapsed_time": "5:58:20", "remaining_time": "1:12:05", "throughput": 1485.64, "total_tokens": 31941376} {"current_steps": 151355, "total_steps": 181800, "loss": 0.002, "lr": 4.151397409805946e-06, "epoch": 16.65071507150715, "percentage": 83.25, "elapsed_time": "5:58:20", "remaining_time": "1:12:04", "throughput": 1485.64, "total_tokens": 31942400} {"current_steps": 151360, "total_steps": 181800, "loss": 0.0023, "lr": 4.1500730310966155e-06, "epoch": 16.65126512651265, "percentage": 83.26, "elapsed_time": "5:58:21", "remaining_time": "1:12:04", "throughput": 1485.64, "total_tokens": 31943424} {"current_steps": 151365, "total_steps": 181800, "loss": 0.0077, "lr": 4.148748844551062e-06, "epoch": 16.651815181518153, "percentage": 83.26, "elapsed_time": "5:58:22", "remaining_time": "1:12:03", "throughput": 1485.64, "total_tokens": 31944448} {"current_steps": 151370, "total_steps": 181800, "loss": 0.0027, "lr": 4.147424850181486e-06, "epoch": 16.652365236523654, "percentage": 83.26, "elapsed_time": "5:58:22", "remaining_time": "1:12:02", "throughput": 1485.64, "total_tokens": 31945472} {"current_steps": 151375, "total_steps": 181800, "loss": 0.0038, "lr": 4.146101048000081e-06, "epoch": 16.652915291529155, "percentage": 83.26, "elapsed_time": "5:58:23", "remaining_time": "1:12:02", "throughput": 1485.64, "total_tokens": 31946560} {"current_steps": 151380, "total_steps": 181800, "loss": 0.0042, "lr": 4.144777438019057e-06, "epoch": 16.653465346534652, "percentage": 83.27, "elapsed_time": "5:58:24", "remaining_time": "1:12:01", "throughput": 1485.64, "total_tokens": 31947616} {"current_steps": 151385, "total_steps": 181800, "loss": 0.0501, "lr": 4.1434540202506115e-06, "epoch": 16.654015401540153, "percentage": 83.27, "elapsed_time": "5:58:24", "remaining_time": "1:12:00", "throughput": 1485.65, "total_tokens": 31948672} {"current_steps": 151390, "total_steps": 181800, "loss": 0.005, "lr": 4.14213079470695e-06, "epoch": 16.654565456545654, "percentage": 83.27, "elapsed_time": "5:58:25", "remaining_time": "1:11:59", "throughput": 1485.65, "total_tokens": 31949792} {"current_steps": 151395, "total_steps": 181800, "loss": 0.122, "lr": 4.1408077614002585e-06, "epoch": 16.655115511551156, "percentage": 83.28, "elapsed_time": "5:58:26", "remaining_time": "1:11:59", "throughput": 1485.65, "total_tokens": 31950816} {"current_steps": 151400, "total_steps": 181800, "loss": 0.0012, "lr": 4.1394849203427284e-06, "epoch": 16.655665566556657, "percentage": 83.28, "elapsed_time": "5:58:26", "remaining_time": "1:11:58", "throughput": 1485.65, "total_tokens": 31951936} {"current_steps": 151405, "total_steps": 181800, "loss": 0.135, "lr": 4.138162271546555e-06, "epoch": 16.656215621562158, "percentage": 83.28, "elapsed_time": "5:58:27", "remaining_time": "1:11:57", "throughput": 1485.66, "total_tokens": 31952992} {"current_steps": 151410, "total_steps": 181800, "loss": 0.0086, "lr": 4.1368398150239296e-06, "epoch": 16.656765676567655, "percentage": 83.28, "elapsed_time": "5:58:28", "remaining_time": "1:11:57", "throughput": 1485.66, "total_tokens": 31954016} {"current_steps": 151415, "total_steps": 181800, "loss": 0.0022, "lr": 4.135517550787046e-06, "epoch": 16.657315731573156, "percentage": 83.29, "elapsed_time": "5:58:29", "remaining_time": "1:11:56", "throughput": 1485.66, "total_tokens": 31955040} {"current_steps": 151420, "total_steps": 181800, "loss": 0.0006, "lr": 4.134195478848088e-06, "epoch": 16.657865786578657, "percentage": 83.29, "elapsed_time": "5:58:29", "remaining_time": "1:11:55", "throughput": 1485.66, "total_tokens": 31956128} {"current_steps": 151425, "total_steps": 181800, "loss": 0.0347, "lr": 4.132873599219231e-06, "epoch": 16.65841584158416, "percentage": 83.29, "elapsed_time": "5:58:30", "remaining_time": "1:11:54", "throughput": 1485.66, "total_tokens": 31957216} {"current_steps": 151430, "total_steps": 181800, "loss": 0.0033, "lr": 4.131551911912668e-06, "epoch": 16.65896589658966, "percentage": 83.29, "elapsed_time": "5:58:31", "remaining_time": "1:11:54", "throughput": 1485.66, "total_tokens": 31958208} {"current_steps": 151435, "total_steps": 181800, "loss": 0.0006, "lr": 4.1302304169405726e-06, "epoch": 16.65951595159516, "percentage": 83.3, "elapsed_time": "5:58:31", "remaining_time": "1:11:53", "throughput": 1485.66, "total_tokens": 31959232} {"current_steps": 151440, "total_steps": 181800, "loss": 0.039, "lr": 4.1289091143151295e-06, "epoch": 16.66006600660066, "percentage": 83.3, "elapsed_time": "5:58:32", "remaining_time": "1:11:52", "throughput": 1485.66, "total_tokens": 31960352} {"current_steps": 151445, "total_steps": 181800, "loss": 0.0555, "lr": 4.127588004048524e-06, "epoch": 16.66061606160616, "percentage": 83.3, "elapsed_time": "5:58:33", "remaining_time": "1:11:52", "throughput": 1485.66, "total_tokens": 31961408} {"current_steps": 151450, "total_steps": 181800, "loss": 0.0331, "lr": 4.126267086152916e-06, "epoch": 16.66116611661166, "percentage": 83.31, "elapsed_time": "5:58:33", "remaining_time": "1:11:51", "throughput": 1485.67, "total_tokens": 31962464} {"current_steps": 151455, "total_steps": 181800, "loss": 0.0025, "lr": 4.124946360640494e-06, "epoch": 16.66171617161716, "percentage": 83.31, "elapsed_time": "5:58:34", "remaining_time": "1:11:50", "throughput": 1485.67, "total_tokens": 31963584} {"current_steps": 151460, "total_steps": 181800, "loss": 0.0103, "lr": 4.123625827523419e-06, "epoch": 16.662266226622663, "percentage": 83.31, "elapsed_time": "5:58:35", "remaining_time": "1:11:49", "throughput": 1485.67, "total_tokens": 31964640} {"current_steps": 151465, "total_steps": 181800, "loss": 0.0007, "lr": 4.122305486813868e-06, "epoch": 16.662816281628164, "percentage": 83.31, "elapsed_time": "5:58:35", "remaining_time": "1:11:49", "throughput": 1485.67, "total_tokens": 31965632} {"current_steps": 151470, "total_steps": 181800, "loss": 0.077, "lr": 4.120985338524017e-06, "epoch": 16.663366336633665, "percentage": 83.32, "elapsed_time": "5:58:36", "remaining_time": "1:11:48", "throughput": 1485.67, "total_tokens": 31966720} {"current_steps": 151475, "total_steps": 181800, "loss": 0.0021, "lr": 4.119665382666016e-06, "epoch": 16.663916391639162, "percentage": 83.32, "elapsed_time": "5:58:37", "remaining_time": "1:11:47", "throughput": 1485.68, "total_tokens": 31967808} {"current_steps": 151480, "total_steps": 181800, "loss": 0.0065, "lr": 4.118345619252048e-06, "epoch": 16.664466446644663, "percentage": 83.32, "elapsed_time": "5:58:38", "remaining_time": "1:11:47", "throughput": 1485.68, "total_tokens": 31968864} {"current_steps": 151485, "total_steps": 181800, "loss": 0.0018, "lr": 4.117026048294262e-06, "epoch": 16.665016501650165, "percentage": 83.33, "elapsed_time": "5:58:38", "remaining_time": "1:11:46", "throughput": 1485.68, "total_tokens": 31969920} {"current_steps": 151490, "total_steps": 181800, "loss": 0.0043, "lr": 4.115706669804831e-06, "epoch": 16.665566556655666, "percentage": 83.33, "elapsed_time": "5:58:39", "remaining_time": "1:11:45", "throughput": 1485.68, "total_tokens": 31970944} {"current_steps": 151495, "total_steps": 181800, "loss": 0.0034, "lr": 4.114387483795906e-06, "epoch": 16.666116611661167, "percentage": 83.33, "elapsed_time": "5:58:40", "remaining_time": "1:11:44", "throughput": 1485.68, "total_tokens": 31972000} {"current_steps": 151500, "total_steps": 181800, "loss": 0.0398, "lr": 4.113068490279648e-06, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "5:58:40", "remaining_time": "1:11:44", "throughput": 1485.68, "total_tokens": 31973056} {"current_steps": 151505, "total_steps": 181800, "loss": 0.0738, "lr": 4.111749689268224e-06, "epoch": 16.66721672167217, "percentage": 83.34, "elapsed_time": "5:58:41", "remaining_time": "1:11:43", "throughput": 1485.68, "total_tokens": 31974112} {"current_steps": 151510, "total_steps": 181800, "loss": 0.0016, "lr": 4.110431080773772e-06, "epoch": 16.667766776677666, "percentage": 83.34, "elapsed_time": "5:58:42", "remaining_time": "1:11:42", "throughput": 1485.68, "total_tokens": 31975168} {"current_steps": 151515, "total_steps": 181800, "loss": 0.0056, "lr": 4.1091126648084594e-06, "epoch": 16.668316831683168, "percentage": 83.34, "elapsed_time": "5:58:42", "remaining_time": "1:11:42", "throughput": 1485.69, "total_tokens": 31976224} {"current_steps": 151520, "total_steps": 181800, "loss": 0.0028, "lr": 4.10779444138443e-06, "epoch": 16.66886688668867, "percentage": 83.34, "elapsed_time": "5:58:43", "remaining_time": "1:11:41", "throughput": 1485.69, "total_tokens": 31977280} {"current_steps": 151525, "total_steps": 181800, "loss": 0.0059, "lr": 4.1064764105138205e-06, "epoch": 16.66941694169417, "percentage": 83.35, "elapsed_time": "5:58:44", "remaining_time": "1:11:40", "throughput": 1485.69, "total_tokens": 31978304} {"current_steps": 151530, "total_steps": 181800, "loss": 0.0985, "lr": 4.105158572208809e-06, "epoch": 16.66996699669967, "percentage": 83.35, "elapsed_time": "5:58:44", "remaining_time": "1:11:39", "throughput": 1485.69, "total_tokens": 31979360} {"current_steps": 151535, "total_steps": 181800, "loss": 0.0415, "lr": 4.10384092648152e-06, "epoch": 16.670517051705172, "percentage": 83.35, "elapsed_time": "5:58:45", "remaining_time": "1:11:39", "throughput": 1485.69, "total_tokens": 31980448} {"current_steps": 151540, "total_steps": 181800, "loss": 0.0028, "lr": 4.1025234733440995e-06, "epoch": 16.67106710671067, "percentage": 83.36, "elapsed_time": "5:58:46", "remaining_time": "1:11:38", "throughput": 1485.69, "total_tokens": 31981472} {"current_steps": 151545, "total_steps": 181800, "loss": 0.0039, "lr": 4.101206212808698e-06, "epoch": 16.67161716171617, "percentage": 83.36, "elapsed_time": "5:58:47", "remaining_time": "1:11:37", "throughput": 1485.7, "total_tokens": 31982592} {"current_steps": 151550, "total_steps": 181800, "loss": 0.067, "lr": 4.099889144887442e-06, "epoch": 16.67216721672167, "percentage": 83.36, "elapsed_time": "5:58:47", "remaining_time": "1:11:37", "throughput": 1485.7, "total_tokens": 31983680} {"current_steps": 151555, "total_steps": 181800, "loss": 0.0013, "lr": 4.098572269592482e-06, "epoch": 16.672717271727173, "percentage": 83.36, "elapsed_time": "5:58:48", "remaining_time": "1:11:36", "throughput": 1485.7, "total_tokens": 31984704} {"current_steps": 151560, "total_steps": 181800, "loss": 0.0081, "lr": 4.097255586935958e-06, "epoch": 16.673267326732674, "percentage": 83.37, "elapsed_time": "5:58:49", "remaining_time": "1:11:35", "throughput": 1485.7, "total_tokens": 31985760} {"current_steps": 151565, "total_steps": 181800, "loss": 0.0992, "lr": 4.09593909692999e-06, "epoch": 16.673817381738175, "percentage": 83.37, "elapsed_time": "5:58:49", "remaining_time": "1:11:34", "throughput": 1485.7, "total_tokens": 31986880} {"current_steps": 151570, "total_steps": 181800, "loss": 0.0175, "lr": 4.094622799586728e-06, "epoch": 16.674367436743676, "percentage": 83.37, "elapsed_time": "5:58:50", "remaining_time": "1:11:34", "throughput": 1485.71, "total_tokens": 31987936} {"current_steps": 151575, "total_steps": 181800, "loss": 0.0042, "lr": 4.0933066949182915e-06, "epoch": 16.674917491749174, "percentage": 83.37, "elapsed_time": "5:58:51", "remaining_time": "1:11:33", "throughput": 1485.71, "total_tokens": 31988992} {"current_steps": 151580, "total_steps": 181800, "loss": 0.0038, "lr": 4.0919907829368165e-06, "epoch": 16.675467546754675, "percentage": 83.38, "elapsed_time": "5:58:51", "remaining_time": "1:11:32", "throughput": 1485.7, "total_tokens": 31989984} {"current_steps": 151585, "total_steps": 181800, "loss": 0.0168, "lr": 4.090675063654434e-06, "epoch": 16.676017601760176, "percentage": 83.38, "elapsed_time": "5:58:52", "remaining_time": "1:11:32", "throughput": 1485.7, "total_tokens": 31991008} {"current_steps": 151590, "total_steps": 181800, "loss": 0.0248, "lr": 4.089359537083259e-06, "epoch": 16.676567656765677, "percentage": 83.38, "elapsed_time": "5:58:53", "remaining_time": "1:11:31", "throughput": 1485.71, "total_tokens": 31992064} {"current_steps": 151595, "total_steps": 181800, "loss": 0.0078, "lr": 4.08804420323543e-06, "epoch": 16.677117711771178, "percentage": 83.39, "elapsed_time": "5:58:53", "remaining_time": "1:11:30", "throughput": 1485.71, "total_tokens": 31993088} {"current_steps": 151600, "total_steps": 181800, "loss": 0.0029, "lr": 4.086729062123057e-06, "epoch": 16.67766776677668, "percentage": 83.39, "elapsed_time": "5:58:54", "remaining_time": "1:11:29", "throughput": 1485.71, "total_tokens": 31994112} {"current_steps": 151605, "total_steps": 181800, "loss": 0.0652, "lr": 4.085414113758274e-06, "epoch": 16.678217821782177, "percentage": 83.39, "elapsed_time": "5:58:55", "remaining_time": "1:11:29", "throughput": 1485.71, "total_tokens": 31995200} {"current_steps": 151610, "total_steps": 181800, "loss": 0.052, "lr": 4.084099358153188e-06, "epoch": 16.678767876787678, "percentage": 83.39, "elapsed_time": "5:58:56", "remaining_time": "1:11:28", "throughput": 1485.71, "total_tokens": 31996256} {"current_steps": 151615, "total_steps": 181800, "loss": 0.131, "lr": 4.0827847953199185e-06, "epoch": 16.67931793179318, "percentage": 83.4, "elapsed_time": "5:58:56", "remaining_time": "1:11:27", "throughput": 1485.71, "total_tokens": 31997280} {"current_steps": 151620, "total_steps": 181800, "loss": 0.1288, "lr": 4.081470425270592e-06, "epoch": 16.67986798679868, "percentage": 83.4, "elapsed_time": "5:58:57", "remaining_time": "1:11:27", "throughput": 1485.71, "total_tokens": 31998304} {"current_steps": 151625, "total_steps": 181800, "loss": 0.0507, "lr": 4.080156248017311e-06, "epoch": 16.68041804180418, "percentage": 83.4, "elapsed_time": "5:58:58", "remaining_time": "1:11:26", "throughput": 1485.71, "total_tokens": 31999392} {"current_steps": 151630, "total_steps": 181800, "loss": 0.002, "lr": 4.078842263572194e-06, "epoch": 16.680968096809682, "percentage": 83.4, "elapsed_time": "5:58:58", "remaining_time": "1:11:25", "throughput": 1485.72, "total_tokens": 32000480} {"current_steps": 151635, "total_steps": 181800, "loss": 0.0538, "lr": 4.077528471947353e-06, "epoch": 16.681518151815183, "percentage": 83.41, "elapsed_time": "5:58:59", "remaining_time": "1:11:24", "throughput": 1485.72, "total_tokens": 32001504} {"current_steps": 151640, "total_steps": 181800, "loss": 0.0028, "lr": 4.076214873154877e-06, "epoch": 16.68206820682068, "percentage": 83.41, "elapsed_time": "5:59:00", "remaining_time": "1:11:24", "throughput": 1485.72, "total_tokens": 32002624} {"current_steps": 151645, "total_steps": 181800, "loss": 0.0209, "lr": 4.0749014672069014e-06, "epoch": 16.682618261826182, "percentage": 83.41, "elapsed_time": "5:59:00", "remaining_time": "1:11:23", "throughput": 1485.72, "total_tokens": 32003616} {"current_steps": 151650, "total_steps": 181800, "loss": 0.1034, "lr": 4.073588254115513e-06, "epoch": 16.683168316831683, "percentage": 83.42, "elapsed_time": "5:59:01", "remaining_time": "1:11:22", "throughput": 1485.72, "total_tokens": 32004640} {"current_steps": 151655, "total_steps": 181800, "loss": 0.0036, "lr": 4.072275233892825e-06, "epoch": 16.683718371837184, "percentage": 83.42, "elapsed_time": "5:59:02", "remaining_time": "1:11:22", "throughput": 1485.72, "total_tokens": 32005760} {"current_steps": 151660, "total_steps": 181800, "loss": 0.1442, "lr": 4.070962406550935e-06, "epoch": 16.684268426842685, "percentage": 83.42, "elapsed_time": "5:59:02", "remaining_time": "1:11:21", "throughput": 1485.72, "total_tokens": 32006816} {"current_steps": 151665, "total_steps": 181800, "loss": 0.0055, "lr": 4.069649772101936e-06, "epoch": 16.684818481848186, "percentage": 83.42, "elapsed_time": "5:59:03", "remaining_time": "1:11:20", "throughput": 1485.73, "total_tokens": 32007904} {"current_steps": 151670, "total_steps": 181800, "loss": 0.0242, "lr": 4.068337330557931e-06, "epoch": 16.685368536853684, "percentage": 83.43, "elapsed_time": "5:59:04", "remaining_time": "1:11:19", "throughput": 1485.73, "total_tokens": 32008928} {"current_steps": 151675, "total_steps": 181800, "loss": 0.0405, "lr": 4.067025081931017e-06, "epoch": 16.685918591859185, "percentage": 83.43, "elapsed_time": "5:59:04", "remaining_time": "1:11:19", "throughput": 1485.73, "total_tokens": 32010016} {"current_steps": 151680, "total_steps": 181800, "loss": 0.0407, "lr": 4.065713026233295e-06, "epoch": 16.686468646864686, "percentage": 83.43, "elapsed_time": "5:59:05", "remaining_time": "1:11:18", "throughput": 1485.73, "total_tokens": 32011104} {"current_steps": 151685, "total_steps": 181800, "loss": 0.0161, "lr": 4.0644011634768496e-06, "epoch": 16.687018701870187, "percentage": 83.44, "elapsed_time": "5:59:06", "remaining_time": "1:11:17", "throughput": 1485.73, "total_tokens": 32012160} {"current_steps": 151690, "total_steps": 181800, "loss": 0.0014, "lr": 4.0630894936737664e-06, "epoch": 16.687568756875688, "percentage": 83.44, "elapsed_time": "5:59:07", "remaining_time": "1:11:17", "throughput": 1485.73, "total_tokens": 32013152} {"current_steps": 151695, "total_steps": 181800, "loss": 0.0685, "lr": 4.061778016836148e-06, "epoch": 16.68811881188119, "percentage": 83.44, "elapsed_time": "5:59:07", "remaining_time": "1:11:16", "throughput": 1485.74, "total_tokens": 32014272} {"current_steps": 151700, "total_steps": 181800, "loss": 0.007, "lr": 4.060466732976062e-06, "epoch": 16.68866886688669, "percentage": 83.44, "elapsed_time": "5:59:08", "remaining_time": "1:11:15", "throughput": 1485.74, "total_tokens": 32015296} {"current_steps": 151705, "total_steps": 181800, "loss": 0.0237, "lr": 4.059155642105616e-06, "epoch": 16.689218921892188, "percentage": 83.45, "elapsed_time": "5:59:09", "remaining_time": "1:11:14", "throughput": 1485.74, "total_tokens": 32016384} {"current_steps": 151710, "total_steps": 181800, "loss": 0.0058, "lr": 4.057844744236888e-06, "epoch": 16.68976897689769, "percentage": 83.45, "elapsed_time": "5:59:09", "remaining_time": "1:11:14", "throughput": 1485.74, "total_tokens": 32017376} {"current_steps": 151715, "total_steps": 181800, "loss": 0.0013, "lr": 4.056534039381949e-06, "epoch": 16.69031903190319, "percentage": 83.45, "elapsed_time": "5:59:10", "remaining_time": "1:11:13", "throughput": 1485.74, "total_tokens": 32018432} {"current_steps": 151720, "total_steps": 181800, "loss": 0.101, "lr": 4.05522352755289e-06, "epoch": 16.69086908690869, "percentage": 83.45, "elapsed_time": "5:59:11", "remaining_time": "1:11:12", "throughput": 1485.74, "total_tokens": 32019488} {"current_steps": 151725, "total_steps": 181800, "loss": 0.0467, "lr": 4.053913208761781e-06, "epoch": 16.691419141914192, "percentage": 83.46, "elapsed_time": "5:59:11", "remaining_time": "1:11:12", "throughput": 1485.74, "total_tokens": 32020576} {"current_steps": 151730, "total_steps": 181800, "loss": 0.0507, "lr": 4.052603083020703e-06, "epoch": 16.691969196919693, "percentage": 83.46, "elapsed_time": "5:59:12", "remaining_time": "1:11:11", "throughput": 1485.75, "total_tokens": 32021696} {"current_steps": 151735, "total_steps": 181800, "loss": 0.0029, "lr": 4.051293150341737e-06, "epoch": 16.69251925192519, "percentage": 83.46, "elapsed_time": "5:59:13", "remaining_time": "1:11:10", "throughput": 1485.75, "total_tokens": 32022784} {"current_steps": 151740, "total_steps": 181800, "loss": 0.0217, "lr": 4.049983410736946e-06, "epoch": 16.693069306930692, "percentage": 83.47, "elapsed_time": "5:59:13", "remaining_time": "1:11:09", "throughput": 1485.75, "total_tokens": 32023808} {"current_steps": 151745, "total_steps": 181800, "loss": 0.0015, "lr": 4.048673864218408e-06, "epoch": 16.693619361936193, "percentage": 83.47, "elapsed_time": "5:59:14", "remaining_time": "1:11:09", "throughput": 1485.75, "total_tokens": 32024832} {"current_steps": 151750, "total_steps": 181800, "loss": 0.0337, "lr": 4.04736451079819e-06, "epoch": 16.694169416941694, "percentage": 83.47, "elapsed_time": "5:59:15", "remaining_time": "1:11:08", "throughput": 1485.75, "total_tokens": 32025856} {"current_steps": 151755, "total_steps": 181800, "loss": 0.0353, "lr": 4.046055350488354e-06, "epoch": 16.694719471947195, "percentage": 83.47, "elapsed_time": "5:59:16", "remaining_time": "1:11:07", "throughput": 1485.75, "total_tokens": 32026880} {"current_steps": 151760, "total_steps": 181800, "loss": 0.0249, "lr": 4.044746383300971e-06, "epoch": 16.695269526952696, "percentage": 83.48, "elapsed_time": "5:59:16", "remaining_time": "1:11:07", "throughput": 1485.75, "total_tokens": 32027968} {"current_steps": 151765, "total_steps": 181800, "loss": 0.0018, "lr": 4.043437609248105e-06, "epoch": 16.695819581958197, "percentage": 83.48, "elapsed_time": "5:59:17", "remaining_time": "1:11:06", "throughput": 1485.75, "total_tokens": 32029056} {"current_steps": 151770, "total_steps": 181800, "loss": 0.033, "lr": 4.042129028341823e-06, "epoch": 16.696369636963695, "percentage": 83.48, "elapsed_time": "5:59:18", "remaining_time": "1:11:05", "throughput": 1485.75, "total_tokens": 32030080} {"current_steps": 151775, "total_steps": 181800, "loss": 0.018, "lr": 4.040820640594184e-06, "epoch": 16.696919691969196, "percentage": 83.48, "elapsed_time": "5:59:18", "remaining_time": "1:11:04", "throughput": 1485.76, "total_tokens": 32031200} {"current_steps": 151780, "total_steps": 181800, "loss": 0.0024, "lr": 4.039512446017238e-06, "epoch": 16.697469746974697, "percentage": 83.49, "elapsed_time": "5:59:19", "remaining_time": "1:11:04", "throughput": 1485.76, "total_tokens": 32032320} {"current_steps": 151785, "total_steps": 181800, "loss": 0.0619, "lr": 4.038204444623045e-06, "epoch": 16.698019801980198, "percentage": 83.49, "elapsed_time": "5:59:20", "remaining_time": "1:11:03", "throughput": 1485.76, "total_tokens": 32033408} {"current_steps": 151790, "total_steps": 181800, "loss": 0.0914, "lr": 4.036896636423665e-06, "epoch": 16.6985698569857, "percentage": 83.49, "elapsed_time": "5:59:20", "remaining_time": "1:11:02", "throughput": 1485.76, "total_tokens": 32034400} {"current_steps": 151795, "total_steps": 181800, "loss": 0.0064, "lr": 4.035589021431157e-06, "epoch": 16.6991199119912, "percentage": 83.5, "elapsed_time": "5:59:21", "remaining_time": "1:11:02", "throughput": 1485.77, "total_tokens": 32035520} {"current_steps": 151800, "total_steps": 181800, "loss": 0.0316, "lr": 4.034281599657563e-06, "epoch": 16.6996699669967, "percentage": 83.5, "elapsed_time": "5:59:22", "remaining_time": "1:11:01", "throughput": 1485.77, "total_tokens": 32036608} {"current_steps": 151805, "total_steps": 181800, "loss": 0.0387, "lr": 4.032974371114931e-06, "epoch": 16.7002200220022, "percentage": 83.5, "elapsed_time": "5:59:22", "remaining_time": "1:11:00", "throughput": 1485.77, "total_tokens": 32037696} {"current_steps": 151810, "total_steps": 181800, "loss": 0.0025, "lr": 4.031667335815317e-06, "epoch": 16.7007700770077, "percentage": 83.5, "elapsed_time": "5:59:23", "remaining_time": "1:10:59", "throughput": 1485.77, "total_tokens": 32038720} {"current_steps": 151815, "total_steps": 181800, "loss": 0.0005, "lr": 4.03036049377076e-06, "epoch": 16.7013201320132, "percentage": 83.51, "elapsed_time": "5:59:24", "remaining_time": "1:10:59", "throughput": 1485.77, "total_tokens": 32039776} {"current_steps": 151820, "total_steps": 181800, "loss": 0.1206, "lr": 4.029053844993308e-06, "epoch": 16.701870187018702, "percentage": 83.51, "elapsed_time": "5:59:25", "remaining_time": "1:10:58", "throughput": 1485.78, "total_tokens": 32040864} {"current_steps": 151825, "total_steps": 181800, "loss": 0.0018, "lr": 4.027747389495007e-06, "epoch": 16.702420242024203, "percentage": 83.51, "elapsed_time": "5:59:25", "remaining_time": "1:10:57", "throughput": 1485.78, "total_tokens": 32041952} {"current_steps": 151830, "total_steps": 181800, "loss": 0.0045, "lr": 4.026441127287892e-06, "epoch": 16.702970297029704, "percentage": 83.51, "elapsed_time": "5:59:26", "remaining_time": "1:10:57", "throughput": 1485.78, "total_tokens": 32043072} {"current_steps": 151835, "total_steps": 181800, "loss": 0.0976, "lr": 4.0251350583840106e-06, "epoch": 16.703520352035202, "percentage": 83.52, "elapsed_time": "5:59:27", "remaining_time": "1:10:56", "throughput": 1485.79, "total_tokens": 32044128} {"current_steps": 151840, "total_steps": 181800, "loss": 0.0017, "lr": 4.023829182795386e-06, "epoch": 16.704070407040703, "percentage": 83.52, "elapsed_time": "5:59:27", "remaining_time": "1:10:55", "throughput": 1485.79, "total_tokens": 32045184} {"current_steps": 151845, "total_steps": 181800, "loss": 0.1288, "lr": 4.022523500534065e-06, "epoch": 16.704620462046204, "percentage": 83.52, "elapsed_time": "5:59:28", "remaining_time": "1:10:54", "throughput": 1485.79, "total_tokens": 32046336} {"current_steps": 151850, "total_steps": 181800, "loss": 0.0834, "lr": 4.0212180116120854e-06, "epoch": 16.705170517051705, "percentage": 83.53, "elapsed_time": "5:59:29", "remaining_time": "1:10:54", "throughput": 1485.8, "total_tokens": 32047392} {"current_steps": 151855, "total_steps": 181800, "loss": 0.002, "lr": 4.019912716041466e-06, "epoch": 16.705720572057206, "percentage": 83.53, "elapsed_time": "5:59:29", "remaining_time": "1:10:53", "throughput": 1485.8, "total_tokens": 32048448} {"current_steps": 151860, "total_steps": 181800, "loss": 0.0047, "lr": 4.018607613834249e-06, "epoch": 16.706270627062707, "percentage": 83.53, "elapsed_time": "5:59:30", "remaining_time": "1:10:52", "throughput": 1485.8, "total_tokens": 32049504} {"current_steps": 151865, "total_steps": 181800, "loss": 0.0429, "lr": 4.017302705002452e-06, "epoch": 16.706820682068205, "percentage": 83.53, "elapsed_time": "5:59:31", "remaining_time": "1:10:52", "throughput": 1485.8, "total_tokens": 32050624} {"current_steps": 151870, "total_steps": 181800, "loss": 0.0055, "lr": 4.015997989558112e-06, "epoch": 16.707370737073706, "percentage": 83.54, "elapsed_time": "5:59:31", "remaining_time": "1:10:51", "throughput": 1485.8, "total_tokens": 32051680} {"current_steps": 151875, "total_steps": 181800, "loss": 0.0246, "lr": 4.014693467513248e-06, "epoch": 16.707920792079207, "percentage": 83.54, "elapsed_time": "5:59:32", "remaining_time": "1:10:50", "throughput": 1485.8, "total_tokens": 32052736} {"current_steps": 151880, "total_steps": 181800, "loss": 0.0088, "lr": 4.013389138879881e-06, "epoch": 16.70847084708471, "percentage": 83.54, "elapsed_time": "5:59:33", "remaining_time": "1:10:49", "throughput": 1485.8, "total_tokens": 32053792} {"current_steps": 151885, "total_steps": 181800, "loss": 0.0008, "lr": 4.012085003670041e-06, "epoch": 16.70902090209021, "percentage": 83.55, "elapsed_time": "5:59:34", "remaining_time": "1:10:49", "throughput": 1485.81, "total_tokens": 32054848} {"current_steps": 151890, "total_steps": 181800, "loss": 0.0055, "lr": 4.010781061895738e-06, "epoch": 16.70957095709571, "percentage": 83.55, "elapsed_time": "5:59:34", "remaining_time": "1:10:48", "throughput": 1485.81, "total_tokens": 32055872} {"current_steps": 151895, "total_steps": 181800, "loss": 0.0109, "lr": 4.009477313569002e-06, "epoch": 16.71012101210121, "percentage": 83.55, "elapsed_time": "5:59:35", "remaining_time": "1:10:47", "throughput": 1485.81, "total_tokens": 32056928} {"current_steps": 151900, "total_steps": 181800, "loss": 0.0285, "lr": 4.008173758701833e-06, "epoch": 16.71067106710671, "percentage": 83.55, "elapsed_time": "5:59:36", "remaining_time": "1:10:47", "throughput": 1485.81, "total_tokens": 32057952} {"current_steps": 151905, "total_steps": 181800, "loss": 0.1257, "lr": 4.006870397306256e-06, "epoch": 16.71122112211221, "percentage": 83.56, "elapsed_time": "5:59:36", "remaining_time": "1:10:46", "throughput": 1485.81, "total_tokens": 32059040} {"current_steps": 151910, "total_steps": 181800, "loss": 0.0038, "lr": 4.005567229394286e-06, "epoch": 16.71177117711771, "percentage": 83.56, "elapsed_time": "5:59:37", "remaining_time": "1:10:45", "throughput": 1485.81, "total_tokens": 32060096} {"current_steps": 151915, "total_steps": 181800, "loss": 0.1325, "lr": 4.004264254977927e-06, "epoch": 16.712321232123212, "percentage": 83.56, "elapsed_time": "5:59:38", "remaining_time": "1:10:44", "throughput": 1485.81, "total_tokens": 32061184} {"current_steps": 151920, "total_steps": 181800, "loss": 0.0683, "lr": 4.002961474069186e-06, "epoch": 16.712871287128714, "percentage": 83.56, "elapsed_time": "5:59:38", "remaining_time": "1:10:44", "throughput": 1485.82, "total_tokens": 32062336} {"current_steps": 151925, "total_steps": 181800, "loss": 0.0451, "lr": 4.001658886680079e-06, "epoch": 16.713421342134215, "percentage": 83.57, "elapsed_time": "5:59:39", "remaining_time": "1:10:43", "throughput": 1485.82, "total_tokens": 32063456} {"current_steps": 151930, "total_steps": 181800, "loss": 0.0746, "lr": 4.000356492822599e-06, "epoch": 16.713971397139716, "percentage": 83.57, "elapsed_time": "5:59:40", "remaining_time": "1:10:42", "throughput": 1485.83, "total_tokens": 32064544} {"current_steps": 151935, "total_steps": 181800, "loss": 0.1121, "lr": 3.999054292508758e-06, "epoch": 16.714521452145213, "percentage": 83.57, "elapsed_time": "5:59:40", "remaining_time": "1:10:42", "throughput": 1485.83, "total_tokens": 32065632} {"current_steps": 151940, "total_steps": 181800, "loss": 0.0102, "lr": 3.9977522857505615e-06, "epoch": 16.715071507150714, "percentage": 83.58, "elapsed_time": "5:59:41", "remaining_time": "1:10:41", "throughput": 1485.83, "total_tokens": 32066688} {"current_steps": 151945, "total_steps": 181800, "loss": 0.0015, "lr": 3.9964504725599986e-06, "epoch": 16.715621562156215, "percentage": 83.58, "elapsed_time": "5:59:42", "remaining_time": "1:10:40", "throughput": 1485.83, "total_tokens": 32067776} {"current_steps": 151950, "total_steps": 181800, "loss": 0.0019, "lr": 3.995148852949079e-06, "epoch": 16.716171617161717, "percentage": 83.58, "elapsed_time": "5:59:43", "remaining_time": "1:10:39", "throughput": 1485.83, "total_tokens": 32068800} {"current_steps": 151955, "total_steps": 181800, "loss": 0.0032, "lr": 3.993847426929787e-06, "epoch": 16.716721672167218, "percentage": 83.58, "elapsed_time": "5:59:43", "remaining_time": "1:10:39", "throughput": 1485.84, "total_tokens": 32069888} {"current_steps": 151960, "total_steps": 181800, "loss": 0.0091, "lr": 3.992546194514124e-06, "epoch": 16.71727172717272, "percentage": 83.59, "elapsed_time": "5:59:44", "remaining_time": "1:10:38", "throughput": 1485.84, "total_tokens": 32070944} {"current_steps": 151965, "total_steps": 181800, "loss": 0.006, "lr": 3.991245155714091e-06, "epoch": 16.717821782178216, "percentage": 83.59, "elapsed_time": "5:59:45", "remaining_time": "1:10:37", "throughput": 1485.84, "total_tokens": 32072032} {"current_steps": 151970, "total_steps": 181800, "loss": 0.0233, "lr": 3.98994431054166e-06, "epoch": 16.718371837183717, "percentage": 83.59, "elapsed_time": "5:59:45", "remaining_time": "1:10:37", "throughput": 1485.84, "total_tokens": 32073088} {"current_steps": 151975, "total_steps": 181800, "loss": 0.0073, "lr": 3.988643659008839e-06, "epoch": 16.71892189218922, "percentage": 83.59, "elapsed_time": "5:59:46", "remaining_time": "1:10:36", "throughput": 1485.84, "total_tokens": 32074144} {"current_steps": 151980, "total_steps": 181800, "loss": 0.0827, "lr": 3.9873432011276e-06, "epoch": 16.71947194719472, "percentage": 83.6, "elapsed_time": "5:59:47", "remaining_time": "1:10:35", "throughput": 1485.84, "total_tokens": 32075200} {"current_steps": 151985, "total_steps": 181800, "loss": 0.0202, "lr": 3.9860429369099424e-06, "epoch": 16.72002200220022, "percentage": 83.6, "elapsed_time": "5:59:47", "remaining_time": "1:10:34", "throughput": 1485.85, "total_tokens": 32076256} {"current_steps": 151990, "total_steps": 181800, "loss": 0.0824, "lr": 3.984742866367838e-06, "epoch": 16.72057205720572, "percentage": 83.6, "elapsed_time": "5:59:48", "remaining_time": "1:10:34", "throughput": 1485.85, "total_tokens": 32077312} {"current_steps": 151995, "total_steps": 181800, "loss": 0.0408, "lr": 3.9834429895132755e-06, "epoch": 16.721122112211223, "percentage": 83.61, "elapsed_time": "5:59:49", "remaining_time": "1:10:33", "throughput": 1485.85, "total_tokens": 32078368} {"current_steps": 152000, "total_steps": 181800, "loss": 0.0026, "lr": 3.982143306358238e-06, "epoch": 16.72167216721672, "percentage": 83.61, "elapsed_time": "5:59:49", "remaining_time": "1:10:32", "throughput": 1485.85, "total_tokens": 32079392} {"current_steps": 152005, "total_steps": 181800, "loss": 0.0035, "lr": 3.980843816914695e-06, "epoch": 16.72222222222222, "percentage": 83.61, "elapsed_time": "5:59:50", "remaining_time": "1:10:32", "throughput": 1485.85, "total_tokens": 32080512} {"current_steps": 152010, "total_steps": 181800, "loss": 0.0797, "lr": 3.979544521194636e-06, "epoch": 16.722772277227723, "percentage": 83.61, "elapsed_time": "5:59:51", "remaining_time": "1:10:31", "throughput": 1485.86, "total_tokens": 32081600} {"current_steps": 152015, "total_steps": 181800, "loss": 0.0574, "lr": 3.978245419210019e-06, "epoch": 16.723322332233224, "percentage": 83.62, "elapsed_time": "5:59:52", "remaining_time": "1:10:30", "throughput": 1485.86, "total_tokens": 32082656} {"current_steps": 152020, "total_steps": 181800, "loss": 0.0389, "lr": 3.976946510972831e-06, "epoch": 16.723872387238725, "percentage": 83.62, "elapsed_time": "5:59:52", "remaining_time": "1:10:29", "throughput": 1485.86, "total_tokens": 32083648} {"current_steps": 152025, "total_steps": 181800, "loss": 0.0023, "lr": 3.975647796495044e-06, "epoch": 16.724422442244226, "percentage": 83.62, "elapsed_time": "5:59:53", "remaining_time": "1:10:29", "throughput": 1485.86, "total_tokens": 32084736} {"current_steps": 152030, "total_steps": 181800, "loss": 0.0053, "lr": 3.974349275788616e-06, "epoch": 16.724972497249723, "percentage": 83.62, "elapsed_time": "5:59:54", "remaining_time": "1:10:28", "throughput": 1485.86, "total_tokens": 32085760} {"current_steps": 152035, "total_steps": 181800, "loss": 0.0074, "lr": 3.973050948865525e-06, "epoch": 16.725522552255224, "percentage": 83.63, "elapsed_time": "5:59:54", "remaining_time": "1:10:27", "throughput": 1485.86, "total_tokens": 32086784} {"current_steps": 152040, "total_steps": 181800, "loss": 0.0605, "lr": 3.971752815737739e-06, "epoch": 16.726072607260726, "percentage": 83.63, "elapsed_time": "5:59:55", "remaining_time": "1:10:27", "throughput": 1485.86, "total_tokens": 32087776} {"current_steps": 152045, "total_steps": 181800, "loss": 0.0029, "lr": 3.970454876417207e-06, "epoch": 16.726622662266227, "percentage": 83.63, "elapsed_time": "5:59:56", "remaining_time": "1:10:26", "throughput": 1485.86, "total_tokens": 32088832} {"current_steps": 152050, "total_steps": 181800, "loss": 0.0026, "lr": 3.9691571309159045e-06, "epoch": 16.727172717271728, "percentage": 83.64, "elapsed_time": "5:59:56", "remaining_time": "1:10:25", "throughput": 1485.86, "total_tokens": 32089920} {"current_steps": 152055, "total_steps": 181800, "loss": 0.0716, "lr": 3.967859579245786e-06, "epoch": 16.72772277227723, "percentage": 83.64, "elapsed_time": "5:59:57", "remaining_time": "1:10:24", "throughput": 1485.86, "total_tokens": 32090944} {"current_steps": 152060, "total_steps": 181800, "loss": 0.0015, "lr": 3.966562221418821e-06, "epoch": 16.72827282728273, "percentage": 83.64, "elapsed_time": "5:59:58", "remaining_time": "1:10:24", "throughput": 1485.86, "total_tokens": 32092032} {"current_steps": 152065, "total_steps": 181800, "loss": 0.009, "lr": 3.9652650574469595e-06, "epoch": 16.728822882288227, "percentage": 83.64, "elapsed_time": "5:59:58", "remaining_time": "1:10:23", "throughput": 1485.86, "total_tokens": 32093088} {"current_steps": 152070, "total_steps": 181800, "loss": 0.0268, "lr": 3.963968087342152e-06, "epoch": 16.72937293729373, "percentage": 83.65, "elapsed_time": "5:59:59", "remaining_time": "1:10:22", "throughput": 1485.86, "total_tokens": 32094112} {"current_steps": 152075, "total_steps": 181800, "loss": 0.0544, "lr": 3.9626713111163535e-06, "epoch": 16.72992299229923, "percentage": 83.65, "elapsed_time": "6:00:00", "remaining_time": "1:10:22", "throughput": 1485.87, "total_tokens": 32095168} {"current_steps": 152080, "total_steps": 181800, "loss": 0.0006, "lr": 3.96137472878152e-06, "epoch": 16.73047304730473, "percentage": 83.65, "elapsed_time": "6:00:01", "remaining_time": "1:10:21", "throughput": 1485.87, "total_tokens": 32096192} {"current_steps": 152085, "total_steps": 181800, "loss": 0.0108, "lr": 3.960078340349607e-06, "epoch": 16.731023102310232, "percentage": 83.66, "elapsed_time": "6:00:01", "remaining_time": "1:10:20", "throughput": 1485.87, "total_tokens": 32097280} {"current_steps": 152090, "total_steps": 181800, "loss": 0.0048, "lr": 3.958782145832554e-06, "epoch": 16.731573157315733, "percentage": 83.66, "elapsed_time": "6:00:02", "remaining_time": "1:10:19", "throughput": 1485.87, "total_tokens": 32098304} {"current_steps": 152095, "total_steps": 181800, "loss": 0.0017, "lr": 3.957486145242306e-06, "epoch": 16.73212321232123, "percentage": 83.66, "elapsed_time": "6:00:03", "remaining_time": "1:10:19", "throughput": 1485.87, "total_tokens": 32099296} {"current_steps": 152100, "total_steps": 181800, "loss": 0.0716, "lr": 3.956190338590815e-06, "epoch": 16.73267326732673, "percentage": 83.66, "elapsed_time": "6:00:03", "remaining_time": "1:10:18", "throughput": 1485.87, "total_tokens": 32100288} {"current_steps": 152105, "total_steps": 181800, "loss": 0.0466, "lr": 3.954894725890015e-06, "epoch": 16.733223322332233, "percentage": 83.67, "elapsed_time": "6:00:04", "remaining_time": "1:10:17", "throughput": 1485.87, "total_tokens": 32101376} {"current_steps": 152110, "total_steps": 181800, "loss": 0.0026, "lr": 3.953599307151851e-06, "epoch": 16.733773377337734, "percentage": 83.67, "elapsed_time": "6:00:05", "remaining_time": "1:10:17", "throughput": 1485.87, "total_tokens": 32102400} {"current_steps": 152115, "total_steps": 181800, "loss": 0.0777, "lr": 3.952304082388269e-06, "epoch": 16.734323432343235, "percentage": 83.67, "elapsed_time": "6:00:05", "remaining_time": "1:10:16", "throughput": 1485.87, "total_tokens": 32103392} {"current_steps": 152120, "total_steps": 181800, "loss": 0.0051, "lr": 3.951009051611196e-06, "epoch": 16.734873487348736, "percentage": 83.67, "elapsed_time": "6:00:06", "remaining_time": "1:10:15", "throughput": 1485.87, "total_tokens": 32104416} {"current_steps": 152125, "total_steps": 181800, "loss": 0.0048, "lr": 3.949714214832578e-06, "epoch": 16.735423542354237, "percentage": 83.68, "elapsed_time": "6:00:07", "remaining_time": "1:10:14", "throughput": 1485.87, "total_tokens": 32105472} {"current_steps": 152130, "total_steps": 181800, "loss": 0.0013, "lr": 3.948419572064338e-06, "epoch": 16.735973597359735, "percentage": 83.68, "elapsed_time": "6:00:07", "remaining_time": "1:10:14", "throughput": 1485.87, "total_tokens": 32106496} {"current_steps": 152135, "total_steps": 181800, "loss": 0.0074, "lr": 3.947125123318413e-06, "epoch": 16.736523652365236, "percentage": 83.68, "elapsed_time": "6:00:08", "remaining_time": "1:10:13", "throughput": 1485.87, "total_tokens": 32107616} {"current_steps": 152140, "total_steps": 181800, "loss": 0.0104, "lr": 3.945830868606737e-06, "epoch": 16.737073707370737, "percentage": 83.69, "elapsed_time": "6:00:09", "remaining_time": "1:10:12", "throughput": 1485.87, "total_tokens": 32108640} {"current_steps": 152145, "total_steps": 181800, "loss": 0.0683, "lr": 3.944536807941232e-06, "epoch": 16.737623762376238, "percentage": 83.69, "elapsed_time": "6:00:09", "remaining_time": "1:10:12", "throughput": 1485.87, "total_tokens": 32109664} {"current_steps": 152150, "total_steps": 181800, "loss": 0.0985, "lr": 3.943242941333833e-06, "epoch": 16.73817381738174, "percentage": 83.69, "elapsed_time": "6:00:10", "remaining_time": "1:10:11", "throughput": 1485.87, "total_tokens": 32110720} {"current_steps": 152155, "total_steps": 181800, "loss": 0.0501, "lr": 3.941949268796457e-06, "epoch": 16.73872387238724, "percentage": 83.69, "elapsed_time": "6:00:11", "remaining_time": "1:10:10", "throughput": 1485.88, "total_tokens": 32111808} {"current_steps": 152160, "total_steps": 181800, "loss": 0.047, "lr": 3.9406557903410275e-06, "epoch": 16.739273927392738, "percentage": 83.7, "elapsed_time": "6:00:12", "remaining_time": "1:10:09", "throughput": 1485.87, "total_tokens": 32112768} {"current_steps": 152165, "total_steps": 181800, "loss": 0.0038, "lr": 3.939362505979469e-06, "epoch": 16.73982398239824, "percentage": 83.7, "elapsed_time": "6:00:12", "remaining_time": "1:10:09", "throughput": 1485.87, "total_tokens": 32113792} {"current_steps": 152170, "total_steps": 181800, "loss": 0.0052, "lr": 3.938069415723697e-06, "epoch": 16.74037403740374, "percentage": 83.7, "elapsed_time": "6:00:13", "remaining_time": "1:10:08", "throughput": 1485.88, "total_tokens": 32114880} {"current_steps": 152175, "total_steps": 181800, "loss": 0.0191, "lr": 3.936776519585641e-06, "epoch": 16.74092409240924, "percentage": 83.7, "elapsed_time": "6:00:14", "remaining_time": "1:10:07", "throughput": 1485.88, "total_tokens": 32115968} {"current_steps": 152180, "total_steps": 181800, "loss": 0.0145, "lr": 3.935483817577207e-06, "epoch": 16.741474147414742, "percentage": 83.71, "elapsed_time": "6:00:15", "remaining_time": "1:10:07", "throughput": 1485.87, "total_tokens": 32117056} {"current_steps": 152185, "total_steps": 181800, "loss": 0.0174, "lr": 3.934191309710306e-06, "epoch": 16.742024202420243, "percentage": 83.71, "elapsed_time": "6:00:15", "remaining_time": "1:10:06", "throughput": 1485.87, "total_tokens": 32118112} {"current_steps": 152190, "total_steps": 181800, "loss": 0.0408, "lr": 3.932898995996856e-06, "epoch": 16.742574257425744, "percentage": 83.71, "elapsed_time": "6:00:16", "remaining_time": "1:10:05", "throughput": 1485.87, "total_tokens": 32119168} {"current_steps": 152195, "total_steps": 181800, "loss": 0.0169, "lr": 3.931606876448765e-06, "epoch": 16.74312431243124, "percentage": 83.72, "elapsed_time": "6:00:17", "remaining_time": "1:10:04", "throughput": 1485.87, "total_tokens": 32120256} {"current_steps": 152200, "total_steps": 181800, "loss": 0.1175, "lr": 3.930314951077952e-06, "epoch": 16.743674367436743, "percentage": 83.72, "elapsed_time": "6:00:17", "remaining_time": "1:10:04", "throughput": 1485.87, "total_tokens": 32121312} {"current_steps": 152205, "total_steps": 181800, "loss": 0.0536, "lr": 3.929023219896314e-06, "epoch": 16.744224422442244, "percentage": 83.72, "elapsed_time": "6:00:18", "remaining_time": "1:10:03", "throughput": 1485.88, "total_tokens": 32122432} {"current_steps": 152210, "total_steps": 181800, "loss": 0.0436, "lr": 3.927731682915753e-06, "epoch": 16.744774477447745, "percentage": 83.72, "elapsed_time": "6:00:19", "remaining_time": "1:10:02", "throughput": 1485.88, "total_tokens": 32123520} {"current_steps": 152215, "total_steps": 181800, "loss": 0.0114, "lr": 3.9264403401481855e-06, "epoch": 16.745324532453246, "percentage": 83.73, "elapsed_time": "6:00:19", "remaining_time": "1:10:02", "throughput": 1485.88, "total_tokens": 32124512} {"current_steps": 152220, "total_steps": 181800, "loss": 0.1731, "lr": 3.925149191605496e-06, "epoch": 16.745874587458747, "percentage": 83.73, "elapsed_time": "6:00:20", "remaining_time": "1:10:01", "throughput": 1485.88, "total_tokens": 32125600} {"current_steps": 152225, "total_steps": 181800, "loss": 0.0189, "lr": 3.923858237299596e-06, "epoch": 16.746424642464248, "percentage": 83.73, "elapsed_time": "6:00:21", "remaining_time": "1:10:00", "throughput": 1485.88, "total_tokens": 32126656} {"current_steps": 152230, "total_steps": 181800, "loss": 0.0006, "lr": 3.922567477242386e-06, "epoch": 16.746974697469746, "percentage": 83.73, "elapsed_time": "6:00:21", "remaining_time": "1:09:59", "throughput": 1485.89, "total_tokens": 32127744} {"current_steps": 152235, "total_steps": 181800, "loss": 0.0151, "lr": 3.9212769114457535e-06, "epoch": 16.747524752475247, "percentage": 83.74, "elapsed_time": "6:00:22", "remaining_time": "1:09:59", "throughput": 1485.89, "total_tokens": 32128864} {"current_steps": 152240, "total_steps": 181800, "loss": 0.0008, "lr": 3.9199865399216e-06, "epoch": 16.748074807480748, "percentage": 83.74, "elapsed_time": "6:00:23", "remaining_time": "1:09:58", "throughput": 1485.89, "total_tokens": 32129856} {"current_steps": 152245, "total_steps": 181800, "loss": 0.07, "lr": 3.918696362681812e-06, "epoch": 16.74862486248625, "percentage": 83.74, "elapsed_time": "6:00:24", "remaining_time": "1:09:57", "throughput": 1485.89, "total_tokens": 32130848} {"current_steps": 152250, "total_steps": 181800, "loss": 0.0186, "lr": 3.9174063797382836e-06, "epoch": 16.74917491749175, "percentage": 83.75, "elapsed_time": "6:00:24", "remaining_time": "1:09:57", "throughput": 1485.89, "total_tokens": 32131904} {"current_steps": 152255, "total_steps": 181800, "loss": 0.0469, "lr": 3.916116591102909e-06, "epoch": 16.74972497249725, "percentage": 83.75, "elapsed_time": "6:00:25", "remaining_time": "1:09:56", "throughput": 1485.89, "total_tokens": 32132992} {"current_steps": 152260, "total_steps": 181800, "loss": 0.0075, "lr": 3.914826996787566e-06, "epoch": 16.75027502750275, "percentage": 83.75, "elapsed_time": "6:00:26", "remaining_time": "1:09:55", "throughput": 1485.89, "total_tokens": 32133952} {"current_steps": 152265, "total_steps": 181800, "loss": 0.1219, "lr": 3.913537596804151e-06, "epoch": 16.75082508250825, "percentage": 83.75, "elapsed_time": "6:00:26", "remaining_time": "1:09:54", "throughput": 1485.89, "total_tokens": 32135072} {"current_steps": 152270, "total_steps": 181800, "loss": 0.0045, "lr": 3.912248391164533e-06, "epoch": 16.75137513751375, "percentage": 83.76, "elapsed_time": "6:00:27", "remaining_time": "1:09:54", "throughput": 1485.89, "total_tokens": 32136096} {"current_steps": 152275, "total_steps": 181800, "loss": 0.0041, "lr": 3.910959379880611e-06, "epoch": 16.751925192519252, "percentage": 83.76, "elapsed_time": "6:00:28", "remaining_time": "1:09:53", "throughput": 1485.89, "total_tokens": 32137184} {"current_steps": 152280, "total_steps": 181800, "loss": 0.001, "lr": 3.909670562964252e-06, "epoch": 16.752475247524753, "percentage": 83.76, "elapsed_time": "6:00:28", "remaining_time": "1:09:52", "throughput": 1485.9, "total_tokens": 32138240} {"current_steps": 152285, "total_steps": 181800, "loss": 0.0339, "lr": 3.908381940427336e-06, "epoch": 16.753025302530254, "percentage": 83.77, "elapsed_time": "6:00:29", "remaining_time": "1:09:52", "throughput": 1485.9, "total_tokens": 32139328} {"current_steps": 152290, "total_steps": 181800, "loss": 0.0026, "lr": 3.907093512281751e-06, "epoch": 16.753575357535752, "percentage": 83.77, "elapsed_time": "6:00:30", "remaining_time": "1:09:51", "throughput": 1485.9, "total_tokens": 32140320} {"current_steps": 152295, "total_steps": 181800, "loss": 0.013, "lr": 3.90580527853936e-06, "epoch": 16.754125412541253, "percentage": 83.77, "elapsed_time": "6:00:30", "remaining_time": "1:09:50", "throughput": 1485.9, "total_tokens": 32141344} {"current_steps": 152300, "total_steps": 181800, "loss": 0.034, "lr": 3.904517239212041e-06, "epoch": 16.754675467546754, "percentage": 83.77, "elapsed_time": "6:00:31", "remaining_time": "1:09:49", "throughput": 1485.9, "total_tokens": 32142368} {"current_steps": 152305, "total_steps": 181800, "loss": 0.0107, "lr": 3.9032293943116665e-06, "epoch": 16.755225522552255, "percentage": 83.78, "elapsed_time": "6:00:32", "remaining_time": "1:09:49", "throughput": 1485.9, "total_tokens": 32143392} {"current_steps": 152310, "total_steps": 181800, "loss": 0.1748, "lr": 3.90194174385009e-06, "epoch": 16.755775577557756, "percentage": 83.78, "elapsed_time": "6:00:33", "remaining_time": "1:09:48", "throughput": 1485.9, "total_tokens": 32144416} {"current_steps": 152315, "total_steps": 181800, "loss": 0.0023, "lr": 3.900654287839206e-06, "epoch": 16.756325632563257, "percentage": 83.78, "elapsed_time": "6:00:33", "remaining_time": "1:09:47", "throughput": 1485.89, "total_tokens": 32145408} {"current_steps": 152320, "total_steps": 181800, "loss": 0.0057, "lr": 3.899367026290868e-06, "epoch": 16.75687568756876, "percentage": 83.78, "elapsed_time": "6:00:34", "remaining_time": "1:09:47", "throughput": 1485.9, "total_tokens": 32146464} {"current_steps": 152325, "total_steps": 181800, "loss": 0.005, "lr": 3.898079959216933e-06, "epoch": 16.757425742574256, "percentage": 83.79, "elapsed_time": "6:00:35", "remaining_time": "1:09:46", "throughput": 1485.9, "total_tokens": 32147520} {"current_steps": 152330, "total_steps": 181800, "loss": 0.0012, "lr": 3.8967930866292746e-06, "epoch": 16.757975797579757, "percentage": 83.79, "elapsed_time": "6:00:35", "remaining_time": "1:09:45", "throughput": 1485.9, "total_tokens": 32148576} {"current_steps": 152335, "total_steps": 181800, "loss": 0.0049, "lr": 3.895506408539739e-06, "epoch": 16.758525852585258, "percentage": 83.79, "elapsed_time": "6:00:36", "remaining_time": "1:09:44", "throughput": 1485.9, "total_tokens": 32149664} {"current_steps": 152340, "total_steps": 181800, "loss": 0.0016, "lr": 3.894219924960199e-06, "epoch": 16.75907590759076, "percentage": 83.8, "elapsed_time": "6:00:37", "remaining_time": "1:09:44", "throughput": 1485.9, "total_tokens": 32150720} {"current_steps": 152345, "total_steps": 181800, "loss": 0.0137, "lr": 3.89293363590251e-06, "epoch": 16.75962596259626, "percentage": 83.8, "elapsed_time": "6:00:37", "remaining_time": "1:09:43", "throughput": 1485.9, "total_tokens": 32151776} {"current_steps": 152350, "total_steps": 181800, "loss": 0.0033, "lr": 3.891647541378515e-06, "epoch": 16.76017601760176, "percentage": 83.8, "elapsed_time": "6:00:38", "remaining_time": "1:09:42", "throughput": 1485.9, "total_tokens": 32152800} {"current_steps": 152355, "total_steps": 181800, "loss": 0.0445, "lr": 3.890361641400087e-06, "epoch": 16.760726072607262, "percentage": 83.8, "elapsed_time": "6:00:39", "remaining_time": "1:09:42", "throughput": 1485.9, "total_tokens": 32153856} {"current_steps": 152360, "total_steps": 181800, "loss": 0.0044, "lr": 3.889075935979056e-06, "epoch": 16.76127612761276, "percentage": 83.81, "elapsed_time": "6:00:39", "remaining_time": "1:09:41", "throughput": 1485.9, "total_tokens": 32154880} {"current_steps": 152365, "total_steps": 181800, "loss": 0.0721, "lr": 3.887790425127286e-06, "epoch": 16.76182618261826, "percentage": 83.81, "elapsed_time": "6:00:40", "remaining_time": "1:09:40", "throughput": 1485.9, "total_tokens": 32155904} {"current_steps": 152370, "total_steps": 181800, "loss": 0.0776, "lr": 3.8865051088566225e-06, "epoch": 16.762376237623762, "percentage": 83.81, "elapsed_time": "6:00:41", "remaining_time": "1:09:39", "throughput": 1485.91, "total_tokens": 32156992} {"current_steps": 152375, "total_steps": 181800, "loss": 0.1064, "lr": 3.885219987178906e-06, "epoch": 16.762926292629263, "percentage": 83.81, "elapsed_time": "6:00:42", "remaining_time": "1:09:39", "throughput": 1485.91, "total_tokens": 32158112} {"current_steps": 152380, "total_steps": 181800, "loss": 0.0102, "lr": 3.883935060105992e-06, "epoch": 16.763476347634764, "percentage": 83.82, "elapsed_time": "6:00:42", "remaining_time": "1:09:38", "throughput": 1485.91, "total_tokens": 32159168} {"current_steps": 152385, "total_steps": 181800, "loss": 0.0081, "lr": 3.882650327649709e-06, "epoch": 16.764026402640265, "percentage": 83.82, "elapsed_time": "6:00:43", "remaining_time": "1:09:37", "throughput": 1485.91, "total_tokens": 32160224} {"current_steps": 152390, "total_steps": 181800, "loss": 0.0326, "lr": 3.881365789821912e-06, "epoch": 16.764576457645763, "percentage": 83.82, "elapsed_time": "6:00:44", "remaining_time": "1:09:37", "throughput": 1485.91, "total_tokens": 32161248} {"current_steps": 152395, "total_steps": 181800, "loss": 0.0548, "lr": 3.880081446634426e-06, "epoch": 16.765126512651264, "percentage": 83.83, "elapsed_time": "6:00:44", "remaining_time": "1:09:36", "throughput": 1485.92, "total_tokens": 32162368} {"current_steps": 152400, "total_steps": 181800, "loss": 0.004, "lr": 3.878797298099096e-06, "epoch": 16.765676567656765, "percentage": 83.83, "elapsed_time": "6:00:45", "remaining_time": "1:09:35", "throughput": 1485.92, "total_tokens": 32163392} {"current_steps": 152405, "total_steps": 181800, "loss": 0.0886, "lr": 3.877513344227762e-06, "epoch": 16.766226622662266, "percentage": 83.83, "elapsed_time": "6:00:46", "remaining_time": "1:09:34", "throughput": 1485.92, "total_tokens": 32164448} {"current_steps": 152410, "total_steps": 181800, "loss": 0.007, "lr": 3.876229585032245e-06, "epoch": 16.766776677667767, "percentage": 83.83, "elapsed_time": "6:00:46", "remaining_time": "1:09:34", "throughput": 1485.92, "total_tokens": 32165440} {"current_steps": 152415, "total_steps": 181800, "loss": 0.0032, "lr": 3.874946020524389e-06, "epoch": 16.76732673267327, "percentage": 83.84, "elapsed_time": "6:00:47", "remaining_time": "1:09:33", "throughput": 1485.92, "total_tokens": 32166496} {"current_steps": 152420, "total_steps": 181800, "loss": 0.0044, "lr": 3.87366265071602e-06, "epoch": 16.76787678767877, "percentage": 83.84, "elapsed_time": "6:00:48", "remaining_time": "1:09:32", "throughput": 1485.92, "total_tokens": 32167488} {"current_steps": 152425, "total_steps": 181800, "loss": 0.0093, "lr": 3.872379475618954e-06, "epoch": 16.768426842684267, "percentage": 83.84, "elapsed_time": "6:00:48", "remaining_time": "1:09:32", "throughput": 1485.92, "total_tokens": 32168544} {"current_steps": 152430, "total_steps": 181800, "loss": 0.0086, "lr": 3.871096495245039e-06, "epoch": 16.768976897689768, "percentage": 83.84, "elapsed_time": "6:00:49", "remaining_time": "1:09:31", "throughput": 1485.92, "total_tokens": 32169600} {"current_steps": 152435, "total_steps": 181800, "loss": 0.0384, "lr": 3.8698137096060845e-06, "epoch": 16.76952695269527, "percentage": 83.85, "elapsed_time": "6:00:50", "remaining_time": "1:09:30", "throughput": 1485.92, "total_tokens": 32170656} {"current_steps": 152440, "total_steps": 181800, "loss": 0.0301, "lr": 3.8685311187139225e-06, "epoch": 16.77007700770077, "percentage": 83.85, "elapsed_time": "6:00:51", "remaining_time": "1:09:29", "throughput": 1485.92, "total_tokens": 32171680} {"current_steps": 152445, "total_steps": 181800, "loss": 0.0036, "lr": 3.867248722580369e-06, "epoch": 16.77062706270627, "percentage": 83.85, "elapsed_time": "6:00:51", "remaining_time": "1:09:29", "throughput": 1485.92, "total_tokens": 32172768} {"current_steps": 152450, "total_steps": 181800, "loss": 0.0521, "lr": 3.865966521217238e-06, "epoch": 16.771177117711773, "percentage": 83.86, "elapsed_time": "6:00:52", "remaining_time": "1:09:28", "throughput": 1485.92, "total_tokens": 32173792} {"current_steps": 152455, "total_steps": 181800, "loss": 0.0074, "lr": 3.864684514636352e-06, "epoch": 16.77172717271727, "percentage": 83.86, "elapsed_time": "6:00:53", "remaining_time": "1:09:27", "throughput": 1485.92, "total_tokens": 32174816} {"current_steps": 152460, "total_steps": 181800, "loss": 0.0031, "lr": 3.863402702849528e-06, "epoch": 16.77227722772277, "percentage": 83.86, "elapsed_time": "6:00:53", "remaining_time": "1:09:27", "throughput": 1485.92, "total_tokens": 32175872} {"current_steps": 152465, "total_steps": 181800, "loss": 0.0624, "lr": 3.862121085868584e-06, "epoch": 16.772827282728272, "percentage": 83.86, "elapsed_time": "6:00:54", "remaining_time": "1:09:26", "throughput": 1485.93, "total_tokens": 32176960} {"current_steps": 152470, "total_steps": 181800, "loss": 0.0036, "lr": 3.860839663705329e-06, "epoch": 16.773377337733773, "percentage": 83.87, "elapsed_time": "6:00:55", "remaining_time": "1:09:25", "throughput": 1485.93, "total_tokens": 32177984} {"current_steps": 152475, "total_steps": 181800, "loss": 0.001, "lr": 3.859558436371563e-06, "epoch": 16.773927392739274, "percentage": 83.87, "elapsed_time": "6:00:55", "remaining_time": "1:09:24", "throughput": 1485.93, "total_tokens": 32179136} {"current_steps": 152480, "total_steps": 181800, "loss": 0.0938, "lr": 3.8582774038791095e-06, "epoch": 16.774477447744776, "percentage": 83.87, "elapsed_time": "6:00:56", "remaining_time": "1:09:24", "throughput": 1485.93, "total_tokens": 32180160} {"current_steps": 152485, "total_steps": 181800, "loss": 0.0698, "lr": 3.856996566239757e-06, "epoch": 16.775027502750277, "percentage": 83.88, "elapsed_time": "6:00:57", "remaining_time": "1:09:23", "throughput": 1485.94, "total_tokens": 32181280} {"current_steps": 152490, "total_steps": 181800, "loss": 0.003, "lr": 3.855715923465333e-06, "epoch": 16.775577557755774, "percentage": 83.88, "elapsed_time": "6:00:57", "remaining_time": "1:09:22", "throughput": 1485.94, "total_tokens": 32182368} {"current_steps": 152495, "total_steps": 181800, "loss": 0.0009, "lr": 3.854435475567628e-06, "epoch": 16.776127612761275, "percentage": 83.88, "elapsed_time": "6:00:58", "remaining_time": "1:09:22", "throughput": 1485.94, "total_tokens": 32183392} {"current_steps": 152500, "total_steps": 181800, "loss": 0.003, "lr": 3.853155222558441e-06, "epoch": 16.776677667766776, "percentage": 83.88, "elapsed_time": "6:00:59", "remaining_time": "1:09:21", "throughput": 1485.94, "total_tokens": 32184384} {"current_steps": 152505, "total_steps": 181800, "loss": 0.0762, "lr": 3.851875164449581e-06, "epoch": 16.777227722772277, "percentage": 83.89, "elapsed_time": "6:01:00", "remaining_time": "1:09:20", "throughput": 1485.94, "total_tokens": 32185408} {"current_steps": 152510, "total_steps": 181800, "loss": 0.0027, "lr": 3.850595301252832e-06, "epoch": 16.77777777777778, "percentage": 83.89, "elapsed_time": "6:01:00", "remaining_time": "1:09:20", "throughput": 1485.94, "total_tokens": 32186464} {"current_steps": 152515, "total_steps": 181800, "loss": 0.0038, "lr": 3.8493156329799965e-06, "epoch": 16.77832783278328, "percentage": 83.89, "elapsed_time": "6:01:01", "remaining_time": "1:09:19", "throughput": 1485.94, "total_tokens": 32187488} {"current_steps": 152520, "total_steps": 181800, "loss": 0.041, "lr": 3.848036159642879e-06, "epoch": 16.778877887788777, "percentage": 83.89, "elapsed_time": "6:01:02", "remaining_time": "1:09:18", "throughput": 1485.94, "total_tokens": 32188576} {"current_steps": 152525, "total_steps": 181800, "loss": 0.0014, "lr": 3.846756881253255e-06, "epoch": 16.77942794279428, "percentage": 83.9, "elapsed_time": "6:01:02", "remaining_time": "1:09:17", "throughput": 1485.94, "total_tokens": 32189568} {"current_steps": 152530, "total_steps": 181800, "loss": 0.0542, "lr": 3.84547779782293e-06, "epoch": 16.77997799779978, "percentage": 83.9, "elapsed_time": "6:01:03", "remaining_time": "1:09:17", "throughput": 1485.94, "total_tokens": 32190624} {"current_steps": 152535, "total_steps": 181800, "loss": 0.0346, "lr": 3.8441989093636835e-06, "epoch": 16.78052805280528, "percentage": 83.9, "elapsed_time": "6:01:04", "remaining_time": "1:09:16", "throughput": 1485.94, "total_tokens": 32191680} {"current_steps": 152540, "total_steps": 181800, "loss": 0.1062, "lr": 3.8429202158872995e-06, "epoch": 16.78107810781078, "percentage": 83.91, "elapsed_time": "6:01:04", "remaining_time": "1:09:15", "throughput": 1485.94, "total_tokens": 32192672} {"current_steps": 152545, "total_steps": 181800, "loss": 0.1167, "lr": 3.841641717405567e-06, "epoch": 16.781628162816283, "percentage": 83.91, "elapsed_time": "6:01:05", "remaining_time": "1:09:15", "throughput": 1485.94, "total_tokens": 32193760} {"current_steps": 152550, "total_steps": 181800, "loss": 0.0014, "lr": 3.840363413930267e-06, "epoch": 16.782178217821784, "percentage": 83.91, "elapsed_time": "6:01:06", "remaining_time": "1:09:14", "throughput": 1485.94, "total_tokens": 32194848} {"current_steps": 152555, "total_steps": 181800, "loss": 0.0264, "lr": 3.839085305473195e-06, "epoch": 16.78272827282728, "percentage": 83.91, "elapsed_time": "6:01:06", "remaining_time": "1:09:13", "throughput": 1485.94, "total_tokens": 32195936} {"current_steps": 152560, "total_steps": 181800, "loss": 0.0021, "lr": 3.837807392046116e-06, "epoch": 16.783278327832782, "percentage": 83.92, "elapsed_time": "6:01:07", "remaining_time": "1:09:12", "throughput": 1485.94, "total_tokens": 32196992} {"current_steps": 152565, "total_steps": 181800, "loss": 0.0043, "lr": 3.836529673660808e-06, "epoch": 16.783828382838283, "percentage": 83.92, "elapsed_time": "6:01:08", "remaining_time": "1:09:12", "throughput": 1485.95, "total_tokens": 32198048} {"current_steps": 152570, "total_steps": 181800, "loss": 0.1173, "lr": 3.835252150329049e-06, "epoch": 16.784378437843785, "percentage": 83.92, "elapsed_time": "6:01:09", "remaining_time": "1:09:11", "throughput": 1485.95, "total_tokens": 32199136} {"current_steps": 152575, "total_steps": 181800, "loss": 0.0149, "lr": 3.8339748220626165e-06, "epoch": 16.784928492849286, "percentage": 83.92, "elapsed_time": "6:01:09", "remaining_time": "1:09:10", "throughput": 1485.95, "total_tokens": 32200128} {"current_steps": 152580, "total_steps": 181800, "loss": 0.0576, "lr": 3.832697688873288e-06, "epoch": 16.785478547854787, "percentage": 83.93, "elapsed_time": "6:01:10", "remaining_time": "1:09:10", "throughput": 1485.95, "total_tokens": 32201280} {"current_steps": 152585, "total_steps": 181800, "loss": 0.0012, "lr": 3.8314207507728265e-06, "epoch": 16.786028602860284, "percentage": 83.93, "elapsed_time": "6:01:11", "remaining_time": "1:09:09", "throughput": 1485.95, "total_tokens": 32202304} {"current_steps": 152590, "total_steps": 181800, "loss": 0.0041, "lr": 3.830144007772998e-06, "epoch": 16.786578657865785, "percentage": 83.93, "elapsed_time": "6:01:11", "remaining_time": "1:09:08", "throughput": 1485.95, "total_tokens": 32203392} {"current_steps": 152595, "total_steps": 181800, "loss": 0.0095, "lr": 3.828867459885579e-06, "epoch": 16.787128712871286, "percentage": 83.94, "elapsed_time": "6:01:12", "remaining_time": "1:09:07", "throughput": 1485.96, "total_tokens": 32204448} {"current_steps": 152600, "total_steps": 181800, "loss": 0.0069, "lr": 3.827591107122322e-06, "epoch": 16.787678767876788, "percentage": 83.94, "elapsed_time": "6:01:13", "remaining_time": "1:09:07", "throughput": 1485.96, "total_tokens": 32205504} {"current_steps": 152605, "total_steps": 181800, "loss": 0.0658, "lr": 3.826314949494999e-06, "epoch": 16.78822882288229, "percentage": 83.94, "elapsed_time": "6:01:13", "remaining_time": "1:09:06", "throughput": 1485.96, "total_tokens": 32206624} {"current_steps": 152610, "total_steps": 181800, "loss": 0.0025, "lr": 3.825038987015378e-06, "epoch": 16.78877887788779, "percentage": 83.94, "elapsed_time": "6:01:14", "remaining_time": "1:09:05", "throughput": 1485.96, "total_tokens": 32207648} {"current_steps": 152615, "total_steps": 181800, "loss": 0.0346, "lr": 3.823763219695206e-06, "epoch": 16.78932893289329, "percentage": 83.95, "elapsed_time": "6:01:15", "remaining_time": "1:09:05", "throughput": 1485.96, "total_tokens": 32208704} {"current_steps": 152620, "total_steps": 181800, "loss": 0.0046, "lr": 3.822487647546252e-06, "epoch": 16.78987898789879, "percentage": 83.95, "elapsed_time": "6:01:16", "remaining_time": "1:09:04", "throughput": 1485.96, "total_tokens": 32209728} {"current_steps": 152625, "total_steps": 181800, "loss": 0.1288, "lr": 3.821212270580263e-06, "epoch": 16.79042904290429, "percentage": 83.95, "elapsed_time": "6:01:16", "remaining_time": "1:09:03", "throughput": 1485.96, "total_tokens": 32210784} {"current_steps": 152630, "total_steps": 181800, "loss": 0.0085, "lr": 3.819937088808997e-06, "epoch": 16.79097909790979, "percentage": 83.95, "elapsed_time": "6:01:17", "remaining_time": "1:09:02", "throughput": 1485.96, "total_tokens": 32211744} {"current_steps": 152635, "total_steps": 181800, "loss": 0.0012, "lr": 3.8186621022442135e-06, "epoch": 16.79152915291529, "percentage": 83.96, "elapsed_time": "6:01:18", "remaining_time": "1:09:02", "throughput": 1485.96, "total_tokens": 32212800} {"current_steps": 152640, "total_steps": 181800, "loss": 0.0231, "lr": 3.8173873108976525e-06, "epoch": 16.792079207920793, "percentage": 83.96, "elapsed_time": "6:01:18", "remaining_time": "1:09:01", "throughput": 1485.96, "total_tokens": 32213856} {"current_steps": 152645, "total_steps": 181800, "loss": 0.1269, "lr": 3.816112714781073e-06, "epoch": 16.792629262926294, "percentage": 83.96, "elapsed_time": "6:01:19", "remaining_time": "1:09:00", "throughput": 1485.96, "total_tokens": 32214944} {"current_steps": 152650, "total_steps": 181800, "loss": 0.0049, "lr": 3.814838313906213e-06, "epoch": 16.793179317931795, "percentage": 83.97, "elapsed_time": "6:01:20", "remaining_time": "1:09:00", "throughput": 1485.96, "total_tokens": 32215968} {"current_steps": 152655, "total_steps": 181800, "loss": 0.0011, "lr": 3.8135641082848284e-06, "epoch": 16.793729372937293, "percentage": 83.97, "elapsed_time": "6:01:20", "remaining_time": "1:08:59", "throughput": 1485.96, "total_tokens": 32216992} {"current_steps": 152660, "total_steps": 181800, "loss": 0.0098, "lr": 3.8122900979286504e-06, "epoch": 16.794279427942794, "percentage": 83.97, "elapsed_time": "6:01:21", "remaining_time": "1:08:58", "throughput": 1485.96, "total_tokens": 32218080} {"current_steps": 152665, "total_steps": 181800, "loss": 0.0643, "lr": 3.811016282849428e-06, "epoch": 16.794829482948295, "percentage": 83.97, "elapsed_time": "6:01:22", "remaining_time": "1:08:57", "throughput": 1485.96, "total_tokens": 32219104} {"current_steps": 152670, "total_steps": 181800, "loss": 0.1394, "lr": 3.8097426630589073e-06, "epoch": 16.795379537953796, "percentage": 83.98, "elapsed_time": "6:01:23", "remaining_time": "1:08:57", "throughput": 1485.96, "total_tokens": 32220096} {"current_steps": 152675, "total_steps": 181800, "loss": 0.0056, "lr": 3.8084692385688127e-06, "epoch": 16.795929592959297, "percentage": 83.98, "elapsed_time": "6:01:23", "remaining_time": "1:08:56", "throughput": 1485.96, "total_tokens": 32221120} {"current_steps": 152680, "total_steps": 181800, "loss": 0.0839, "lr": 3.8071960093908955e-06, "epoch": 16.796479647964798, "percentage": 83.98, "elapsed_time": "6:01:24", "remaining_time": "1:08:55", "throughput": 1485.96, "total_tokens": 32222144} {"current_steps": 152685, "total_steps": 181800, "loss": 0.0036, "lr": 3.805922975536877e-06, "epoch": 16.797029702970296, "percentage": 83.99, "elapsed_time": "6:01:25", "remaining_time": "1:08:55", "throughput": 1485.96, "total_tokens": 32223168} {"current_steps": 152690, "total_steps": 181800, "loss": 0.0016, "lr": 3.804650137018498e-06, "epoch": 16.797579757975797, "percentage": 83.99, "elapsed_time": "6:01:25", "remaining_time": "1:08:54", "throughput": 1485.96, "total_tokens": 32224288} {"current_steps": 152695, "total_steps": 181800, "loss": 0.0012, "lr": 3.803377493847493e-06, "epoch": 16.798129812981298, "percentage": 83.99, "elapsed_time": "6:01:26", "remaining_time": "1:08:53", "throughput": 1485.96, "total_tokens": 32225312} {"current_steps": 152700, "total_steps": 181800, "loss": 0.0044, "lr": 3.8021050460355867e-06, "epoch": 16.7986798679868, "percentage": 83.99, "elapsed_time": "6:01:27", "remaining_time": "1:08:52", "throughput": 1485.97, "total_tokens": 32226464} {"current_steps": 152705, "total_steps": 181800, "loss": 0.0073, "lr": 3.8008327935945027e-06, "epoch": 16.7992299229923, "percentage": 84.0, "elapsed_time": "6:01:27", "remaining_time": "1:08:52", "throughput": 1485.97, "total_tokens": 32227552} {"current_steps": 152710, "total_steps": 181800, "loss": 0.1491, "lr": 3.799560736535973e-06, "epoch": 16.7997799779978, "percentage": 84.0, "elapsed_time": "6:01:28", "remaining_time": "1:08:51", "throughput": 1485.97, "total_tokens": 32228608} {"current_steps": 152715, "total_steps": 181800, "loss": 0.1853, "lr": 3.798288874871714e-06, "epoch": 16.8003300330033, "percentage": 84.0, "elapsed_time": "6:01:29", "remaining_time": "1:08:50", "throughput": 1485.97, "total_tokens": 32229632} {"current_steps": 152720, "total_steps": 181800, "loss": 0.0058, "lr": 3.7970172086134543e-06, "epoch": 16.8008800880088, "percentage": 84.0, "elapsed_time": "6:01:29", "remaining_time": "1:08:50", "throughput": 1485.97, "total_tokens": 32230688} {"current_steps": 152725, "total_steps": 181800, "loss": 0.0464, "lr": 3.795745737772918e-06, "epoch": 16.8014301430143, "percentage": 84.01, "elapsed_time": "6:01:30", "remaining_time": "1:08:49", "throughput": 1485.97, "total_tokens": 32231712} {"current_steps": 152730, "total_steps": 181800, "loss": 0.0039, "lr": 3.7944744623618107e-06, "epoch": 16.801980198019802, "percentage": 84.01, "elapsed_time": "6:01:31", "remaining_time": "1:08:48", "throughput": 1485.97, "total_tokens": 32232800} {"current_steps": 152735, "total_steps": 181800, "loss": 0.004, "lr": 3.793203382391866e-06, "epoch": 16.802530253025303, "percentage": 84.01, "elapsed_time": "6:01:32", "remaining_time": "1:08:47", "throughput": 1485.98, "total_tokens": 32233888} {"current_steps": 152740, "total_steps": 181800, "loss": 0.1293, "lr": 3.791932497874781e-06, "epoch": 16.803080308030804, "percentage": 84.02, "elapsed_time": "6:01:32", "remaining_time": "1:08:47", "throughput": 1485.98, "total_tokens": 32234912} {"current_steps": 152745, "total_steps": 181800, "loss": 0.079, "lr": 3.7906618088222796e-06, "epoch": 16.803630363036305, "percentage": 84.02, "elapsed_time": "6:01:33", "remaining_time": "1:08:46", "throughput": 1485.98, "total_tokens": 32235936} {"current_steps": 152750, "total_steps": 181800, "loss": 0.0145, "lr": 3.789391315246077e-06, "epoch": 16.804180418041803, "percentage": 84.02, "elapsed_time": "6:01:34", "remaining_time": "1:08:45", "throughput": 1485.98, "total_tokens": 32236992} {"current_steps": 152755, "total_steps": 181800, "loss": 0.0021, "lr": 3.7881210171578697e-06, "epoch": 16.804730473047304, "percentage": 84.02, "elapsed_time": "6:01:34", "remaining_time": "1:08:45", "throughput": 1485.98, "total_tokens": 32237984} {"current_steps": 152760, "total_steps": 181800, "loss": 0.1288, "lr": 3.7868509145693787e-06, "epoch": 16.805280528052805, "percentage": 84.03, "elapsed_time": "6:01:35", "remaining_time": "1:08:44", "throughput": 1485.98, "total_tokens": 32239040} {"current_steps": 152765, "total_steps": 181800, "loss": 0.0038, "lr": 3.7855810074922977e-06, "epoch": 16.805830583058306, "percentage": 84.03, "elapsed_time": "6:01:36", "remaining_time": "1:08:43", "throughput": 1485.98, "total_tokens": 32240096} {"current_steps": 152770, "total_steps": 181800, "loss": 0.0018, "lr": 3.784311295938342e-06, "epoch": 16.806380638063807, "percentage": 84.03, "elapsed_time": "6:01:36", "remaining_time": "1:08:42", "throughput": 1485.98, "total_tokens": 32241184} {"current_steps": 152775, "total_steps": 181800, "loss": 0.0356, "lr": 3.7830417799192053e-06, "epoch": 16.806930693069308, "percentage": 84.03, "elapsed_time": "6:01:37", "remaining_time": "1:08:42", "throughput": 1485.98, "total_tokens": 32242176} {"current_steps": 152780, "total_steps": 181800, "loss": 0.1253, "lr": 3.7817724594465893e-06, "epoch": 16.80748074807481, "percentage": 84.04, "elapsed_time": "6:01:38", "remaining_time": "1:08:41", "throughput": 1485.98, "total_tokens": 32243200} {"current_steps": 152785, "total_steps": 181800, "loss": 0.0071, "lr": 3.780503334532201e-06, "epoch": 16.808030803080307, "percentage": 84.04, "elapsed_time": "6:01:38", "remaining_time": "1:08:40", "throughput": 1485.98, "total_tokens": 32244288} {"current_steps": 152790, "total_steps": 181800, "loss": 0.0416, "lr": 3.779234405187726e-06, "epoch": 16.808580858085808, "percentage": 84.04, "elapsed_time": "6:01:39", "remaining_time": "1:08:40", "throughput": 1485.98, "total_tokens": 32245312} {"current_steps": 152795, "total_steps": 181800, "loss": 0.012, "lr": 3.777965671424871e-06, "epoch": 16.80913091309131, "percentage": 84.05, "elapsed_time": "6:01:40", "remaining_time": "1:08:39", "throughput": 1485.98, "total_tokens": 32246368} {"current_steps": 152800, "total_steps": 181800, "loss": 0.0093, "lr": 3.7766971332553193e-06, "epoch": 16.80968096809681, "percentage": 84.05, "elapsed_time": "6:01:41", "remaining_time": "1:08:38", "throughput": 1485.98, "total_tokens": 32247392} {"current_steps": 152805, "total_steps": 181800, "loss": 0.0015, "lr": 3.7754287906907633e-06, "epoch": 16.81023102310231, "percentage": 84.05, "elapsed_time": "6:01:41", "remaining_time": "1:08:37", "throughput": 1485.99, "total_tokens": 32248480} {"current_steps": 152810, "total_steps": 181800, "loss": 0.0061, "lr": 3.7741606437429024e-06, "epoch": 16.810781078107812, "percentage": 84.05, "elapsed_time": "6:01:42", "remaining_time": "1:08:37", "throughput": 1485.99, "total_tokens": 32249536} {"current_steps": 152815, "total_steps": 181800, "loss": 0.0577, "lr": 3.7728926924234103e-06, "epoch": 16.81133113311331, "percentage": 84.06, "elapsed_time": "6:01:43", "remaining_time": "1:08:36", "throughput": 1485.99, "total_tokens": 32250624} {"current_steps": 152820, "total_steps": 181800, "loss": 0.008, "lr": 3.771624936743989e-06, "epoch": 16.81188118811881, "percentage": 84.06, "elapsed_time": "6:01:43", "remaining_time": "1:08:35", "throughput": 1485.99, "total_tokens": 32251648} {"current_steps": 152825, "total_steps": 181800, "loss": 0.001, "lr": 3.7703573767163132e-06, "epoch": 16.812431243124312, "percentage": 84.06, "elapsed_time": "6:01:44", "remaining_time": "1:08:35", "throughput": 1485.99, "total_tokens": 32252640} {"current_steps": 152830, "total_steps": 181800, "loss": 0.0026, "lr": 3.769090012352061e-06, "epoch": 16.812981298129813, "percentage": 84.06, "elapsed_time": "6:01:45", "remaining_time": "1:08:34", "throughput": 1485.99, "total_tokens": 32253696} {"current_steps": 152835, "total_steps": 181800, "loss": 0.043, "lr": 3.767822843662916e-06, "epoch": 16.813531353135314, "percentage": 84.07, "elapsed_time": "6:01:45", "remaining_time": "1:08:33", "throughput": 1485.99, "total_tokens": 32254752} {"current_steps": 152840, "total_steps": 181800, "loss": 0.0094, "lr": 3.7665558706605623e-06, "epoch": 16.814081408140815, "percentage": 84.07, "elapsed_time": "6:01:46", "remaining_time": "1:08:32", "throughput": 1485.99, "total_tokens": 32255776} {"current_steps": 152845, "total_steps": 181800, "loss": 0.0014, "lr": 3.7652890933566804e-06, "epoch": 16.814631463146316, "percentage": 84.07, "elapsed_time": "6:01:47", "remaining_time": "1:08:32", "throughput": 1485.99, "total_tokens": 32256800} {"current_steps": 152850, "total_steps": 181800, "loss": 0.0191, "lr": 3.764022511762938e-06, "epoch": 16.815181518151814, "percentage": 84.08, "elapsed_time": "6:01:47", "remaining_time": "1:08:31", "throughput": 1485.99, "total_tokens": 32257824} {"current_steps": 152855, "total_steps": 181800, "loss": 0.0353, "lr": 3.7627561258910064e-06, "epoch": 16.815731573157315, "percentage": 84.08, "elapsed_time": "6:01:48", "remaining_time": "1:08:30", "throughput": 1485.99, "total_tokens": 32258880} {"current_steps": 152860, "total_steps": 181800, "loss": 0.0022, "lr": 3.7614899357525574e-06, "epoch": 16.816281628162816, "percentage": 84.08, "elapsed_time": "6:01:49", "remaining_time": "1:08:30", "throughput": 1485.99, "total_tokens": 32259968} {"current_steps": 152865, "total_steps": 181800, "loss": 0.0021, "lr": 3.7602239413592673e-06, "epoch": 16.816831683168317, "percentage": 84.08, "elapsed_time": "6:01:50", "remaining_time": "1:08:29", "throughput": 1485.99, "total_tokens": 32260960} {"current_steps": 152870, "total_steps": 181800, "loss": 0.0177, "lr": 3.758958142722807e-06, "epoch": 16.817381738173818, "percentage": 84.09, "elapsed_time": "6:01:50", "remaining_time": "1:08:28", "throughput": 1485.99, "total_tokens": 32261984} {"current_steps": 152875, "total_steps": 181800, "loss": 0.0006, "lr": 3.7576925398548373e-06, "epoch": 16.81793179317932, "percentage": 84.09, "elapsed_time": "6:01:51", "remaining_time": "1:08:27", "throughput": 1485.99, "total_tokens": 32263040} {"current_steps": 152880, "total_steps": 181800, "loss": 0.0037, "lr": 3.7564271327670153e-06, "epoch": 16.818481848184817, "percentage": 84.09, "elapsed_time": "6:01:52", "remaining_time": "1:08:27", "throughput": 1485.99, "total_tokens": 32264096} {"current_steps": 152885, "total_steps": 181800, "loss": 0.0296, "lr": 3.7551619214710175e-06, "epoch": 16.819031903190318, "percentage": 84.1, "elapsed_time": "6:01:52", "remaining_time": "1:08:26", "throughput": 1486.0, "total_tokens": 32265184} {"current_steps": 152890, "total_steps": 181800, "loss": 0.0665, "lr": 3.7538969059784906e-06, "epoch": 16.81958195819582, "percentage": 84.1, "elapsed_time": "6:01:53", "remaining_time": "1:08:25", "throughput": 1485.99, "total_tokens": 32266176} {"current_steps": 152895, "total_steps": 181800, "loss": 0.0619, "lr": 3.752632086301103e-06, "epoch": 16.82013201320132, "percentage": 84.1, "elapsed_time": "6:01:54", "remaining_time": "1:08:25", "throughput": 1485.99, "total_tokens": 32267200} {"current_steps": 152900, "total_steps": 181800, "loss": 0.0048, "lr": 3.751367462450514e-06, "epoch": 16.82068206820682, "percentage": 84.1, "elapsed_time": "6:01:54", "remaining_time": "1:08:24", "throughput": 1486.0, "total_tokens": 32268288} {"current_steps": 152905, "total_steps": 181800, "loss": 0.0013, "lr": 3.750103034438371e-06, "epoch": 16.821232123212322, "percentage": 84.11, "elapsed_time": "6:01:55", "remaining_time": "1:08:23", "throughput": 1486.0, "total_tokens": 32269344} {"current_steps": 152910, "total_steps": 181800, "loss": 0.0028, "lr": 3.748838802276336e-06, "epoch": 16.821782178217823, "percentage": 84.11, "elapsed_time": "6:01:56", "remaining_time": "1:08:22", "throughput": 1486.0, "total_tokens": 32270368} {"current_steps": 152915, "total_steps": 181800, "loss": 0.0028, "lr": 3.7475747659760502e-06, "epoch": 16.82233223322332, "percentage": 84.11, "elapsed_time": "6:01:57", "remaining_time": "1:08:22", "throughput": 1486.0, "total_tokens": 32271424} {"current_steps": 152920, "total_steps": 181800, "loss": 0.0015, "lr": 3.7463109255491736e-06, "epoch": 16.822882288228822, "percentage": 84.11, "elapsed_time": "6:01:57", "remaining_time": "1:08:21", "throughput": 1486.0, "total_tokens": 32272512} {"current_steps": 152925, "total_steps": 181800, "loss": 0.0032, "lr": 3.7450472810073523e-06, "epoch": 16.823432343234323, "percentage": 84.12, "elapsed_time": "6:01:58", "remaining_time": "1:08:20", "throughput": 1486.0, "total_tokens": 32273568} {"current_steps": 152930, "total_steps": 181800, "loss": 0.0462, "lr": 3.743783832362227e-06, "epoch": 16.823982398239824, "percentage": 84.12, "elapsed_time": "6:01:59", "remaining_time": "1:08:20", "throughput": 1486.0, "total_tokens": 32274560} {"current_steps": 152935, "total_steps": 181800, "loss": 0.0496, "lr": 3.7425205796254525e-06, "epoch": 16.824532453245325, "percentage": 84.12, "elapsed_time": "6:01:59", "remaining_time": "1:08:19", "throughput": 1486.0, "total_tokens": 32275648} {"current_steps": 152940, "total_steps": 181800, "loss": 0.0007, "lr": 3.741257522808664e-06, "epoch": 16.825082508250826, "percentage": 84.13, "elapsed_time": "6:02:00", "remaining_time": "1:08:18", "throughput": 1486.0, "total_tokens": 32276704} {"current_steps": 152945, "total_steps": 181800, "loss": 0.0659, "lr": 3.7399946619234986e-06, "epoch": 16.825632563256324, "percentage": 84.13, "elapsed_time": "6:02:01", "remaining_time": "1:08:17", "throughput": 1486.0, "total_tokens": 32277728} {"current_steps": 152950, "total_steps": 181800, "loss": 0.0456, "lr": 3.7387319969816035e-06, "epoch": 16.826182618261825, "percentage": 84.13, "elapsed_time": "6:02:01", "remaining_time": "1:08:17", "throughput": 1486.0, "total_tokens": 32278752} {"current_steps": 152955, "total_steps": 181800, "loss": 0.0016, "lr": 3.737469527994611e-06, "epoch": 16.826732673267326, "percentage": 84.13, "elapsed_time": "6:02:02", "remaining_time": "1:08:16", "throughput": 1486.0, "total_tokens": 32279808} {"current_steps": 152960, "total_steps": 181800, "loss": 0.0037, "lr": 3.736207254974164e-06, "epoch": 16.827282728272827, "percentage": 84.14, "elapsed_time": "6:02:03", "remaining_time": "1:08:15", "throughput": 1486.0, "total_tokens": 32280864} {"current_steps": 152965, "total_steps": 181800, "loss": 0.0591, "lr": 3.7349451779318924e-06, "epoch": 16.82783278327833, "percentage": 84.14, "elapsed_time": "6:02:03", "remaining_time": "1:08:15", "throughput": 1486.0, "total_tokens": 32281920} {"current_steps": 152970, "total_steps": 181800, "loss": 0.0011, "lr": 3.733683296879423e-06, "epoch": 16.82838283828383, "percentage": 84.14, "elapsed_time": "6:02:04", "remaining_time": "1:08:14", "throughput": 1486.01, "total_tokens": 32283008} {"current_steps": 152975, "total_steps": 181800, "loss": 0.0113, "lr": 3.732421611828388e-06, "epoch": 16.82893289328933, "percentage": 84.14, "elapsed_time": "6:02:05", "remaining_time": "1:08:13", "throughput": 1486.01, "total_tokens": 32284128} {"current_steps": 152980, "total_steps": 181800, "loss": 0.0036, "lr": 3.7311601227904197e-06, "epoch": 16.829482948294828, "percentage": 84.15, "elapsed_time": "6:02:06", "remaining_time": "1:08:12", "throughput": 1486.01, "total_tokens": 32285152} {"current_steps": 152985, "total_steps": 181800, "loss": 0.0059, "lr": 3.7298988297771455e-06, "epoch": 16.83003300330033, "percentage": 84.15, "elapsed_time": "6:02:06", "remaining_time": "1:08:12", "throughput": 1486.01, "total_tokens": 32286176} {"current_steps": 152990, "total_steps": 181800, "loss": 0.0041, "lr": 3.7286377328001914e-06, "epoch": 16.83058305830583, "percentage": 84.15, "elapsed_time": "6:02:07", "remaining_time": "1:08:11", "throughput": 1486.01, "total_tokens": 32287264} {"current_steps": 152995, "total_steps": 181800, "loss": 0.0515, "lr": 3.7273768318711683e-06, "epoch": 16.83113311331133, "percentage": 84.16, "elapsed_time": "6:02:08", "remaining_time": "1:08:10", "throughput": 1486.01, "total_tokens": 32288320} {"current_steps": 153000, "total_steps": 181800, "loss": 0.0019, "lr": 3.726116127001711e-06, "epoch": 16.831683168316832, "percentage": 84.16, "elapsed_time": "6:02:08", "remaining_time": "1:08:10", "throughput": 1486.01, "total_tokens": 32289408} {"current_steps": 153005, "total_steps": 181800, "loss": 0.1335, "lr": 3.7248556182034267e-06, "epoch": 16.832233223322334, "percentage": 84.16, "elapsed_time": "6:02:09", "remaining_time": "1:08:09", "throughput": 1486.01, "total_tokens": 32290464} {"current_steps": 153010, "total_steps": 181800, "loss": 0.0296, "lr": 3.7235953054879397e-06, "epoch": 16.83278327832783, "percentage": 84.16, "elapsed_time": "6:02:10", "remaining_time": "1:08:08", "throughput": 1486.01, "total_tokens": 32291488} {"current_steps": 153015, "total_steps": 181800, "loss": 0.0015, "lr": 3.722335188866871e-06, "epoch": 16.833333333333332, "percentage": 84.17, "elapsed_time": "6:02:11", "remaining_time": "1:08:08", "throughput": 1486.01, "total_tokens": 32292544} {"current_steps": 153020, "total_steps": 181800, "loss": 0.0004, "lr": 3.7210752683518256e-06, "epoch": 16.833883388338833, "percentage": 84.17, "elapsed_time": "6:02:11", "remaining_time": "1:08:07", "throughput": 1486.01, "total_tokens": 32293600} {"current_steps": 153025, "total_steps": 181800, "loss": 0.1165, "lr": 3.719815543954422e-06, "epoch": 16.834433443344334, "percentage": 84.17, "elapsed_time": "6:02:12", "remaining_time": "1:08:06", "throughput": 1486.01, "total_tokens": 32294656} {"current_steps": 153030, "total_steps": 181800, "loss": 0.0007, "lr": 3.7185560156862615e-06, "epoch": 16.834983498349835, "percentage": 84.17, "elapsed_time": "6:02:13", "remaining_time": "1:08:05", "throughput": 1486.01, "total_tokens": 32295616} {"current_steps": 153035, "total_steps": 181800, "loss": 0.0027, "lr": 3.71729668355896e-06, "epoch": 16.835533553355337, "percentage": 84.18, "elapsed_time": "6:02:13", "remaining_time": "1:08:05", "throughput": 1486.01, "total_tokens": 32296672} {"current_steps": 153040, "total_steps": 181800, "loss": 0.004, "lr": 3.716037547584128e-06, "epoch": 16.836083608360838, "percentage": 84.18, "elapsed_time": "6:02:14", "remaining_time": "1:08:04", "throughput": 1486.01, "total_tokens": 32297760} {"current_steps": 153045, "total_steps": 181800, "loss": 0.0044, "lr": 3.714778607773359e-06, "epoch": 16.836633663366335, "percentage": 84.18, "elapsed_time": "6:02:15", "remaining_time": "1:08:03", "throughput": 1486.01, "total_tokens": 32298784} {"current_steps": 153050, "total_steps": 181800, "loss": 0.0021, "lr": 3.7135198641382677e-06, "epoch": 16.837183718371836, "percentage": 84.19, "elapsed_time": "6:02:15", "remaining_time": "1:08:03", "throughput": 1486.01, "total_tokens": 32299904} {"current_steps": 153055, "total_steps": 181800, "loss": 0.0067, "lr": 3.7122613166904435e-06, "epoch": 16.837733773377337, "percentage": 84.19, "elapsed_time": "6:02:16", "remaining_time": "1:08:02", "throughput": 1486.02, "total_tokens": 32301024} {"current_steps": 153060, "total_steps": 181800, "loss": 0.1429, "lr": 3.7110029654414958e-06, "epoch": 16.83828382838284, "percentage": 84.19, "elapsed_time": "6:02:17", "remaining_time": "1:08:01", "throughput": 1486.02, "total_tokens": 32302048} {"current_steps": 153065, "total_steps": 181800, "loss": 0.0037, "lr": 3.7097448104030153e-06, "epoch": 16.83883388338834, "percentage": 84.19, "elapsed_time": "6:02:18", "remaining_time": "1:08:00", "throughput": 1486.01, "total_tokens": 32303008} {"current_steps": 153070, "total_steps": 181800, "loss": 0.0118, "lr": 3.7084868515865983e-06, "epoch": 16.83938393839384, "percentage": 84.2, "elapsed_time": "6:02:18", "remaining_time": "1:08:00", "throughput": 1486.01, "total_tokens": 32303968} {"current_steps": 153075, "total_steps": 181800, "loss": 0.0052, "lr": 3.7072290890038496e-06, "epoch": 16.83993399339934, "percentage": 84.2, "elapsed_time": "6:02:19", "remaining_time": "1:07:59", "throughput": 1486.01, "total_tokens": 32305024} {"current_steps": 153080, "total_steps": 181800, "loss": 0.0013, "lr": 3.7059715226663515e-06, "epoch": 16.84048404840484, "percentage": 84.2, "elapsed_time": "6:02:20", "remaining_time": "1:07:58", "throughput": 1486.01, "total_tokens": 32306080} {"current_steps": 153085, "total_steps": 181800, "loss": 0.0024, "lr": 3.704714152585692e-06, "epoch": 16.84103410341034, "percentage": 84.21, "elapsed_time": "6:02:20", "remaining_time": "1:07:58", "throughput": 1486.01, "total_tokens": 32307136} {"current_steps": 153090, "total_steps": 181800, "loss": 0.002, "lr": 3.7034569787734675e-06, "epoch": 16.84158415841584, "percentage": 84.21, "elapsed_time": "6:02:21", "remaining_time": "1:07:57", "throughput": 1486.01, "total_tokens": 32308224} {"current_steps": 153095, "total_steps": 181800, "loss": 0.0073, "lr": 3.7022000012412517e-06, "epoch": 16.842134213421343, "percentage": 84.21, "elapsed_time": "6:02:22", "remaining_time": "1:07:56", "throughput": 1486.02, "total_tokens": 32309280} {"current_steps": 153100, "total_steps": 181800, "loss": 0.0313, "lr": 3.700943220000647e-06, "epoch": 16.842684268426844, "percentage": 84.21, "elapsed_time": "6:02:22", "remaining_time": "1:07:55", "throughput": 1486.02, "total_tokens": 32310304} {"current_steps": 153105, "total_steps": 181800, "loss": 0.0012, "lr": 3.699686635063232e-06, "epoch": 16.843234323432345, "percentage": 84.22, "elapsed_time": "6:02:23", "remaining_time": "1:07:55", "throughput": 1486.02, "total_tokens": 32311360} {"current_steps": 153110, "total_steps": 181800, "loss": 0.012, "lr": 3.6984302464405764e-06, "epoch": 16.843784378437842, "percentage": 84.22, "elapsed_time": "6:02:24", "remaining_time": "1:07:54", "throughput": 1486.02, "total_tokens": 32312448} {"current_steps": 153115, "total_steps": 181800, "loss": 0.0034, "lr": 3.697174054144273e-06, "epoch": 16.844334433443343, "percentage": 84.22, "elapsed_time": "6:02:25", "remaining_time": "1:07:53", "throughput": 1486.02, "total_tokens": 32313568} {"current_steps": 153120, "total_steps": 181800, "loss": 0.0066, "lr": 3.6959180581858904e-06, "epoch": 16.844884488448844, "percentage": 84.22, "elapsed_time": "6:02:25", "remaining_time": "1:07:53", "throughput": 1486.03, "total_tokens": 32314688} {"current_steps": 153125, "total_steps": 181800, "loss": 0.0646, "lr": 3.6946622585770057e-06, "epoch": 16.845434543454346, "percentage": 84.23, "elapsed_time": "6:02:26", "remaining_time": "1:07:52", "throughput": 1486.03, "total_tokens": 32315712} {"current_steps": 153130, "total_steps": 181800, "loss": 0.0007, "lr": 3.693406655329204e-06, "epoch": 16.845984598459847, "percentage": 84.23, "elapsed_time": "6:02:27", "remaining_time": "1:07:51", "throughput": 1486.02, "total_tokens": 32316736} {"current_steps": 153135, "total_steps": 181800, "loss": 0.0019, "lr": 3.692151248454043e-06, "epoch": 16.846534653465348, "percentage": 84.23, "elapsed_time": "6:02:27", "remaining_time": "1:07:50", "throughput": 1486.02, "total_tokens": 32317728} {"current_steps": 153140, "total_steps": 181800, "loss": 0.0005, "lr": 3.690896037963104e-06, "epoch": 16.847084708470845, "percentage": 84.24, "elapsed_time": "6:02:28", "remaining_time": "1:07:50", "throughput": 1486.02, "total_tokens": 32318784} {"current_steps": 153145, "total_steps": 181800, "loss": 0.029, "lr": 3.6896410238679484e-06, "epoch": 16.847634763476346, "percentage": 84.24, "elapsed_time": "6:02:29", "remaining_time": "1:07:49", "throughput": 1486.02, "total_tokens": 32319808} {"current_steps": 153150, "total_steps": 181800, "loss": 0.0092, "lr": 3.6883862061801417e-06, "epoch": 16.848184818481847, "percentage": 84.24, "elapsed_time": "6:02:29", "remaining_time": "1:07:48", "throughput": 1486.02, "total_tokens": 32320864} {"current_steps": 153155, "total_steps": 181800, "loss": 0.0696, "lr": 3.6871315849112605e-06, "epoch": 16.84873487348735, "percentage": 84.24, "elapsed_time": "6:02:30", "remaining_time": "1:07:48", "throughput": 1486.02, "total_tokens": 32321888} {"current_steps": 153160, "total_steps": 181800, "loss": 0.0009, "lr": 3.6858771600728566e-06, "epoch": 16.84928492849285, "percentage": 84.25, "elapsed_time": "6:02:31", "remaining_time": "1:07:47", "throughput": 1486.02, "total_tokens": 32322912} {"current_steps": 153165, "total_steps": 181800, "loss": 0.0751, "lr": 3.6846229316764987e-06, "epoch": 16.84983498349835, "percentage": 84.25, "elapsed_time": "6:02:32", "remaining_time": "1:07:46", "throughput": 1486.02, "total_tokens": 32323936} {"current_steps": 153170, "total_steps": 181800, "loss": 0.113, "lr": 3.6833688997337386e-06, "epoch": 16.850385038503852, "percentage": 84.25, "elapsed_time": "6:02:32", "remaining_time": "1:07:45", "throughput": 1486.02, "total_tokens": 32325024} {"current_steps": 153175, "total_steps": 181800, "loss": 0.0119, "lr": 3.6821150642561448e-06, "epoch": 16.85093509350935, "percentage": 84.25, "elapsed_time": "6:02:33", "remaining_time": "1:07:45", "throughput": 1486.02, "total_tokens": 32326048} {"current_steps": 153180, "total_steps": 181800, "loss": 0.0015, "lr": 3.680861425255261e-06, "epoch": 16.85148514851485, "percentage": 84.26, "elapsed_time": "6:02:34", "remaining_time": "1:07:44", "throughput": 1486.02, "total_tokens": 32327136} {"current_steps": 153185, "total_steps": 181800, "loss": 0.0101, "lr": 3.6796079827426444e-06, "epoch": 16.85203520352035, "percentage": 84.26, "elapsed_time": "6:02:34", "remaining_time": "1:07:43", "throughput": 1486.02, "total_tokens": 32328128} {"current_steps": 153190, "total_steps": 181800, "loss": 0.0103, "lr": 3.678354736729861e-06, "epoch": 16.852585258525853, "percentage": 84.26, "elapsed_time": "6:02:35", "remaining_time": "1:07:43", "throughput": 1486.02, "total_tokens": 32329184} {"current_steps": 153195, "total_steps": 181800, "loss": 0.0014, "lr": 3.677101687228443e-06, "epoch": 16.853135313531354, "percentage": 84.27, "elapsed_time": "6:02:36", "remaining_time": "1:07:42", "throughput": 1486.02, "total_tokens": 32330208} {"current_steps": 153200, "total_steps": 181800, "loss": 0.0484, "lr": 3.6758488342499534e-06, "epoch": 16.853685368536855, "percentage": 84.27, "elapsed_time": "6:02:36", "remaining_time": "1:07:41", "throughput": 1486.02, "total_tokens": 32331168} {"current_steps": 153205, "total_steps": 181800, "loss": 0.0014, "lr": 3.6745961778059306e-06, "epoch": 16.854235423542356, "percentage": 84.27, "elapsed_time": "6:02:37", "remaining_time": "1:07:40", "throughput": 1486.02, "total_tokens": 32332224} {"current_steps": 153210, "total_steps": 181800, "loss": 0.0022, "lr": 3.6733437179079123e-06, "epoch": 16.854785478547853, "percentage": 84.27, "elapsed_time": "6:02:38", "remaining_time": "1:07:40", "throughput": 1486.03, "total_tokens": 32333344} {"current_steps": 153215, "total_steps": 181800, "loss": 0.0023, "lr": 3.672091454567464e-06, "epoch": 16.855335533553355, "percentage": 84.28, "elapsed_time": "6:02:38", "remaining_time": "1:07:39", "throughput": 1486.03, "total_tokens": 32334528} {"current_steps": 153220, "total_steps": 181800, "loss": 0.0055, "lr": 3.670839387796107e-06, "epoch": 16.855885588558856, "percentage": 84.28, "elapsed_time": "6:02:39", "remaining_time": "1:07:38", "throughput": 1486.03, "total_tokens": 32335552} {"current_steps": 153225, "total_steps": 181800, "loss": 0.0076, "lr": 3.669587517605394e-06, "epoch": 16.856435643564357, "percentage": 84.28, "elapsed_time": "6:02:40", "remaining_time": "1:07:38", "throughput": 1486.03, "total_tokens": 32336544} {"current_steps": 153230, "total_steps": 181800, "loss": 0.0365, "lr": 3.6683358440068594e-06, "epoch": 16.856985698569858, "percentage": 84.28, "elapsed_time": "6:02:41", "remaining_time": "1:07:37", "throughput": 1486.03, "total_tokens": 32337568} {"current_steps": 153235, "total_steps": 181800, "loss": 0.0247, "lr": 3.66708436701203e-06, "epoch": 16.85753575357536, "percentage": 84.29, "elapsed_time": "6:02:41", "remaining_time": "1:07:36", "throughput": 1486.04, "total_tokens": 32338688} {"current_steps": 153240, "total_steps": 181800, "loss": 0.0044, "lr": 3.6658330866324474e-06, "epoch": 16.858085808580856, "percentage": 84.29, "elapsed_time": "6:02:42", "remaining_time": "1:07:35", "throughput": 1486.04, "total_tokens": 32339776} {"current_steps": 153245, "total_steps": 181800, "loss": 0.0048, "lr": 3.6645820028796464e-06, "epoch": 16.858635863586358, "percentage": 84.29, "elapsed_time": "6:02:43", "remaining_time": "1:07:35", "throughput": 1486.04, "total_tokens": 32340864} {"current_steps": 153250, "total_steps": 181800, "loss": 0.0053, "lr": 3.6633311157651588e-06, "epoch": 16.85918591859186, "percentage": 84.3, "elapsed_time": "6:02:43", "remaining_time": "1:07:34", "throughput": 1486.04, "total_tokens": 32341888} {"current_steps": 153255, "total_steps": 181800, "loss": 0.1209, "lr": 3.6620804253005126e-06, "epoch": 16.85973597359736, "percentage": 84.3, "elapsed_time": "6:02:44", "remaining_time": "1:07:33", "throughput": 1486.04, "total_tokens": 32342912} {"current_steps": 153260, "total_steps": 181800, "loss": 0.003, "lr": 3.6608299314972227e-06, "epoch": 16.86028602860286, "percentage": 84.3, "elapsed_time": "6:02:45", "remaining_time": "1:07:33", "throughput": 1486.04, "total_tokens": 32343968} {"current_steps": 153265, "total_steps": 181800, "loss": 0.0399, "lr": 3.659579634366833e-06, "epoch": 16.860836083608362, "percentage": 84.3, "elapsed_time": "6:02:45", "remaining_time": "1:07:32", "throughput": 1486.04, "total_tokens": 32344992} {"current_steps": 153270, "total_steps": 181800, "loss": 0.0048, "lr": 3.6583295339208485e-06, "epoch": 16.861386138613863, "percentage": 84.31, "elapsed_time": "6:02:46", "remaining_time": "1:07:31", "throughput": 1486.05, "total_tokens": 32346048} {"current_steps": 153275, "total_steps": 181800, "loss": 0.0784, "lr": 3.657079630170804e-06, "epoch": 16.86193619361936, "percentage": 84.31, "elapsed_time": "6:02:47", "remaining_time": "1:07:30", "throughput": 1486.05, "total_tokens": 32347104} {"current_steps": 153280, "total_steps": 181800, "loss": 0.003, "lr": 3.655829923128218e-06, "epoch": 16.86248624862486, "percentage": 84.31, "elapsed_time": "6:02:47", "remaining_time": "1:07:30", "throughput": 1486.05, "total_tokens": 32348192} {"current_steps": 153285, "total_steps": 181800, "loss": 0.0216, "lr": 3.6545804128046006e-06, "epoch": 16.863036303630363, "percentage": 84.32, "elapsed_time": "6:02:48", "remaining_time": "1:07:29", "throughput": 1486.05, "total_tokens": 32349248} {"current_steps": 153290, "total_steps": 181800, "loss": 0.134, "lr": 3.6533310992114792e-06, "epoch": 16.863586358635864, "percentage": 84.32, "elapsed_time": "6:02:49", "remaining_time": "1:07:28", "throughput": 1486.05, "total_tokens": 32350240} {"current_steps": 153295, "total_steps": 181800, "loss": 0.0049, "lr": 3.652081982360356e-06, "epoch": 16.864136413641365, "percentage": 84.32, "elapsed_time": "6:02:49", "remaining_time": "1:07:28", "throughput": 1486.05, "total_tokens": 32351264} {"current_steps": 153300, "total_steps": 181800, "loss": 0.0641, "lr": 3.6508330622627485e-06, "epoch": 16.864686468646866, "percentage": 84.32, "elapsed_time": "6:02:50", "remaining_time": "1:07:27", "throughput": 1486.05, "total_tokens": 32352288} {"current_steps": 153305, "total_steps": 181800, "loss": 0.0028, "lr": 3.649584338930176e-06, "epoch": 16.865236523652364, "percentage": 84.33, "elapsed_time": "6:02:51", "remaining_time": "1:07:26", "throughput": 1486.05, "total_tokens": 32353376} {"current_steps": 153310, "total_steps": 181800, "loss": 0.0032, "lr": 3.6483358123741317e-06, "epoch": 16.865786578657865, "percentage": 84.33, "elapsed_time": "6:02:52", "remaining_time": "1:07:25", "throughput": 1486.05, "total_tokens": 32354400} {"current_steps": 153315, "total_steps": 181800, "loss": 0.002, "lr": 3.6470874826061375e-06, "epoch": 16.866336633663366, "percentage": 84.33, "elapsed_time": "6:02:52", "remaining_time": "1:07:25", "throughput": 1486.06, "total_tokens": 32355520} {"current_steps": 153320, "total_steps": 181800, "loss": 0.1084, "lr": 3.645839349637692e-06, "epoch": 16.866886688668867, "percentage": 84.33, "elapsed_time": "6:02:53", "remaining_time": "1:07:24", "throughput": 1486.06, "total_tokens": 32356544} {"current_steps": 153325, "total_steps": 181800, "loss": 0.0046, "lr": 3.6445914134802942e-06, "epoch": 16.867436743674368, "percentage": 84.34, "elapsed_time": "6:02:54", "remaining_time": "1:07:23", "throughput": 1486.06, "total_tokens": 32357600} {"current_steps": 153330, "total_steps": 181800, "loss": 0.006, "lr": 3.6433436741454467e-06, "epoch": 16.86798679867987, "percentage": 84.34, "elapsed_time": "6:02:54", "remaining_time": "1:07:23", "throughput": 1486.06, "total_tokens": 32358624} {"current_steps": 153335, "total_steps": 181800, "loss": 0.0539, "lr": 3.6420961316446567e-06, "epoch": 16.86853685368537, "percentage": 84.34, "elapsed_time": "6:02:55", "remaining_time": "1:07:22", "throughput": 1486.06, "total_tokens": 32359680} {"current_steps": 153340, "total_steps": 181800, "loss": 0.0013, "lr": 3.6408487859894202e-06, "epoch": 16.869086908690868, "percentage": 84.35, "elapsed_time": "6:02:56", "remaining_time": "1:07:21", "throughput": 1486.06, "total_tokens": 32360736} {"current_steps": 153345, "total_steps": 181800, "loss": 0.124, "lr": 3.639601637191234e-06, "epoch": 16.86963696369637, "percentage": 84.35, "elapsed_time": "6:02:56", "remaining_time": "1:07:20", "throughput": 1486.06, "total_tokens": 32361760} {"current_steps": 153350, "total_steps": 181800, "loss": 0.001, "lr": 3.638354685261583e-06, "epoch": 16.87018701870187, "percentage": 84.35, "elapsed_time": "6:02:57", "remaining_time": "1:07:20", "throughput": 1486.06, "total_tokens": 32362752} {"current_steps": 153355, "total_steps": 181800, "loss": 0.1484, "lr": 3.6371079302119667e-06, "epoch": 16.87073707370737, "percentage": 84.35, "elapsed_time": "6:02:58", "remaining_time": "1:07:19", "throughput": 1486.06, "total_tokens": 32363744} {"current_steps": 153360, "total_steps": 181800, "loss": 0.0723, "lr": 3.6358613720538724e-06, "epoch": 16.871287128712872, "percentage": 84.36, "elapsed_time": "6:02:58", "remaining_time": "1:07:18", "throughput": 1486.06, "total_tokens": 32364800} {"current_steps": 153365, "total_steps": 181800, "loss": 0.009, "lr": 3.6346150107988032e-06, "epoch": 16.871837183718373, "percentage": 84.36, "elapsed_time": "6:02:59", "remaining_time": "1:07:18", "throughput": 1486.06, "total_tokens": 32365856} {"current_steps": 153370, "total_steps": 181800, "loss": 0.001, "lr": 3.633368846458232e-06, "epoch": 16.87238723872387, "percentage": 84.36, "elapsed_time": "6:03:00", "remaining_time": "1:07:17", "throughput": 1486.06, "total_tokens": 32366912} {"current_steps": 153375, "total_steps": 181800, "loss": 0.0143, "lr": 3.6321228790436425e-06, "epoch": 16.872937293729372, "percentage": 84.36, "elapsed_time": "6:03:01", "remaining_time": "1:07:16", "throughput": 1486.06, "total_tokens": 32367904} {"current_steps": 153380, "total_steps": 181800, "loss": 0.0128, "lr": 3.63087710856653e-06, "epoch": 16.873487348734873, "percentage": 84.37, "elapsed_time": "6:03:01", "remaining_time": "1:07:15", "throughput": 1486.06, "total_tokens": 32368960} {"current_steps": 153385, "total_steps": 181800, "loss": 0.007, "lr": 3.6296315350383635e-06, "epoch": 16.874037403740374, "percentage": 84.37, "elapsed_time": "6:03:02", "remaining_time": "1:07:15", "throughput": 1486.06, "total_tokens": 32370016} {"current_steps": 153390, "total_steps": 181800, "loss": 0.0804, "lr": 3.6283861584706287e-06, "epoch": 16.874587458745875, "percentage": 84.37, "elapsed_time": "6:03:03", "remaining_time": "1:07:14", "throughput": 1486.06, "total_tokens": 32371072} {"current_steps": 153395, "total_steps": 181800, "loss": 0.0049, "lr": 3.6271409788748073e-06, "epoch": 16.875137513751376, "percentage": 84.38, "elapsed_time": "6:03:03", "remaining_time": "1:07:13", "throughput": 1486.07, "total_tokens": 32372160} {"current_steps": 153400, "total_steps": 181800, "loss": 0.0205, "lr": 3.6258959962623686e-06, "epoch": 16.875687568756877, "percentage": 84.38, "elapsed_time": "6:03:04", "remaining_time": "1:07:13", "throughput": 1486.07, "total_tokens": 32373248} {"current_steps": 153405, "total_steps": 181800, "loss": 0.08, "lr": 3.6246512106447946e-06, "epoch": 16.876237623762375, "percentage": 84.38, "elapsed_time": "6:03:05", "remaining_time": "1:07:12", "throughput": 1486.07, "total_tokens": 32374304} {"current_steps": 153410, "total_steps": 181800, "loss": 0.0554, "lr": 3.6234066220335455e-06, "epoch": 16.876787678767876, "percentage": 84.38, "elapsed_time": "6:03:05", "remaining_time": "1:07:11", "throughput": 1486.08, "total_tokens": 32375424} {"current_steps": 153415, "total_steps": 181800, "loss": 0.0944, "lr": 3.622162230440104e-06, "epoch": 16.877337733773377, "percentage": 84.39, "elapsed_time": "6:03:06", "remaining_time": "1:07:10", "throughput": 1486.08, "total_tokens": 32376480} {"current_steps": 153420, "total_steps": 181800, "loss": 0.048, "lr": 3.6209180358759394e-06, "epoch": 16.877887788778878, "percentage": 84.39, "elapsed_time": "6:03:07", "remaining_time": "1:07:10", "throughput": 1486.08, "total_tokens": 32377536} {"current_steps": 153425, "total_steps": 181800, "loss": 0.0205, "lr": 3.619674038352508e-06, "epoch": 16.87843784378438, "percentage": 84.39, "elapsed_time": "6:03:07", "remaining_time": "1:07:09", "throughput": 1486.08, "total_tokens": 32378624} {"current_steps": 153430, "total_steps": 181800, "loss": 0.0056, "lr": 3.6184302378812872e-06, "epoch": 16.87898789878988, "percentage": 84.39, "elapsed_time": "6:03:08", "remaining_time": "1:07:08", "throughput": 1486.08, "total_tokens": 32379680} {"current_steps": 153435, "total_steps": 181800, "loss": 0.004, "lr": 3.6171866344737323e-06, "epoch": 16.879537953795378, "percentage": 84.4, "elapsed_time": "6:03:09", "remaining_time": "1:07:08", "throughput": 1486.09, "total_tokens": 32380800} {"current_steps": 153440, "total_steps": 181800, "loss": 0.005, "lr": 3.615943228141311e-06, "epoch": 16.88008800880088, "percentage": 84.4, "elapsed_time": "6:03:09", "remaining_time": "1:07:07", "throughput": 1486.09, "total_tokens": 32381856} {"current_steps": 153445, "total_steps": 181800, "loss": 0.0036, "lr": 3.614700018895473e-06, "epoch": 16.88063806380638, "percentage": 84.4, "elapsed_time": "6:03:10", "remaining_time": "1:07:06", "throughput": 1486.09, "total_tokens": 32382912} {"current_steps": 153450, "total_steps": 181800, "loss": 0.1453, "lr": 3.6134570067476865e-06, "epoch": 16.88118811881188, "percentage": 84.41, "elapsed_time": "6:03:11", "remaining_time": "1:07:05", "throughput": 1486.09, "total_tokens": 32384032} {"current_steps": 153455, "total_steps": 181800, "loss": 0.0049, "lr": 3.6122141917094064e-06, "epoch": 16.881738173817382, "percentage": 84.41, "elapsed_time": "6:03:12", "remaining_time": "1:07:05", "throughput": 1486.09, "total_tokens": 32385088} {"current_steps": 153460, "total_steps": 181800, "loss": 0.0052, "lr": 3.610971573792088e-06, "epoch": 16.882288228822883, "percentage": 84.41, "elapsed_time": "6:03:12", "remaining_time": "1:07:04", "throughput": 1486.1, "total_tokens": 32386144} {"current_steps": 153465, "total_steps": 181800, "loss": 0.0103, "lr": 3.609729153007174e-06, "epoch": 16.882838283828384, "percentage": 84.41, "elapsed_time": "6:03:13", "remaining_time": "1:07:03", "throughput": 1486.1, "total_tokens": 32387232} {"current_steps": 153470, "total_steps": 181800, "loss": 0.0637, "lr": 3.6084869293661255e-06, "epoch": 16.883388338833882, "percentage": 84.42, "elapsed_time": "6:03:14", "remaining_time": "1:07:03", "throughput": 1486.1, "total_tokens": 32388224} {"current_steps": 153475, "total_steps": 181800, "loss": 0.0096, "lr": 3.6072449028803857e-06, "epoch": 16.883938393839383, "percentage": 84.42, "elapsed_time": "6:03:14", "remaining_time": "1:07:02", "throughput": 1486.1, "total_tokens": 32389280} {"current_steps": 153480, "total_steps": 181800, "loss": 0.0168, "lr": 3.606003073561409e-06, "epoch": 16.884488448844884, "percentage": 84.42, "elapsed_time": "6:03:15", "remaining_time": "1:07:01", "throughput": 1486.1, "total_tokens": 32390368} {"current_steps": 153485, "total_steps": 181800, "loss": 0.0048, "lr": 3.604761441420637e-06, "epoch": 16.885038503850385, "percentage": 84.43, "elapsed_time": "6:03:16", "remaining_time": "1:07:00", "throughput": 1486.1, "total_tokens": 32391392} {"current_steps": 153490, "total_steps": 181800, "loss": 0.0072, "lr": 3.6035200064695072e-06, "epoch": 16.885588558855886, "percentage": 84.43, "elapsed_time": "6:03:16", "remaining_time": "1:07:00", "throughput": 1486.1, "total_tokens": 32392416} {"current_steps": 153495, "total_steps": 181800, "loss": 0.0462, "lr": 3.6022787687194747e-06, "epoch": 16.886138613861387, "percentage": 84.43, "elapsed_time": "6:03:17", "remaining_time": "1:06:59", "throughput": 1486.1, "total_tokens": 32393504} {"current_steps": 153500, "total_steps": 181800, "loss": 0.0026, "lr": 3.601037728181961e-06, "epoch": 16.88668866886689, "percentage": 84.43, "elapsed_time": "6:03:18", "remaining_time": "1:06:58", "throughput": 1486.11, "total_tokens": 32394624} {"current_steps": 153505, "total_steps": 181800, "loss": 0.0121, "lr": 3.599796884868417e-06, "epoch": 16.887238723872386, "percentage": 84.44, "elapsed_time": "6:03:18", "remaining_time": "1:06:58", "throughput": 1486.11, "total_tokens": 32395680} {"current_steps": 153510, "total_steps": 181800, "loss": 0.0014, "lr": 3.598556238790282e-06, "epoch": 16.887788778877887, "percentage": 84.44, "elapsed_time": "6:03:19", "remaining_time": "1:06:57", "throughput": 1486.11, "total_tokens": 32396800} {"current_steps": 153515, "total_steps": 181800, "loss": 0.0301, "lr": 3.597315789958977e-06, "epoch": 16.888338833883388, "percentage": 84.44, "elapsed_time": "6:03:20", "remaining_time": "1:06:56", "throughput": 1486.12, "total_tokens": 32397920} {"current_steps": 153520, "total_steps": 181800, "loss": 0.0531, "lr": 3.596075538385951e-06, "epoch": 16.88888888888889, "percentage": 84.44, "elapsed_time": "6:03:21", "remaining_time": "1:06:55", "throughput": 1486.12, "total_tokens": 32398944} {"current_steps": 153525, "total_steps": 181800, "loss": 0.0123, "lr": 3.5948354840826177e-06, "epoch": 16.88943894389439, "percentage": 84.45, "elapsed_time": "6:03:21", "remaining_time": "1:06:55", "throughput": 1486.12, "total_tokens": 32400000} {"current_steps": 153530, "total_steps": 181800, "loss": 0.0576, "lr": 3.5935956270604173e-06, "epoch": 16.88998899889989, "percentage": 84.45, "elapsed_time": "6:03:22", "remaining_time": "1:06:54", "throughput": 1486.12, "total_tokens": 32401024} {"current_steps": 153535, "total_steps": 181800, "loss": 0.0021, "lr": 3.5923559673307767e-06, "epoch": 16.89053905390539, "percentage": 84.45, "elapsed_time": "6:03:23", "remaining_time": "1:06:53", "throughput": 1486.12, "total_tokens": 32402112} {"current_steps": 153540, "total_steps": 181800, "loss": 0.0048, "lr": 3.591116504905115e-06, "epoch": 16.89108910891089, "percentage": 84.46, "elapsed_time": "6:03:23", "remaining_time": "1:06:53", "throughput": 1486.12, "total_tokens": 32403200} {"current_steps": 153545, "total_steps": 181800, "loss": 0.0009, "lr": 3.5898772397948645e-06, "epoch": 16.89163916391639, "percentage": 84.46, "elapsed_time": "6:03:24", "remaining_time": "1:06:52", "throughput": 1486.13, "total_tokens": 32404288} {"current_steps": 153550, "total_steps": 181800, "loss": 0.0028, "lr": 3.588638172011435e-06, "epoch": 16.892189218921892, "percentage": 84.46, "elapsed_time": "6:03:25", "remaining_time": "1:06:51", "throughput": 1486.13, "total_tokens": 32405376} {"current_steps": 153555, "total_steps": 181800, "loss": 0.0437, "lr": 3.587399301566263e-06, "epoch": 16.892739273927393, "percentage": 84.46, "elapsed_time": "6:03:25", "remaining_time": "1:06:50", "throughput": 1486.13, "total_tokens": 32406432} {"current_steps": 153560, "total_steps": 181800, "loss": 0.1146, "lr": 3.586160628470747e-06, "epoch": 16.893289328932894, "percentage": 84.47, "elapsed_time": "6:03:26", "remaining_time": "1:06:50", "throughput": 1486.13, "total_tokens": 32407424} {"current_steps": 153565, "total_steps": 181800, "loss": 0.0018, "lr": 3.584922152736317e-06, "epoch": 16.893839383938392, "percentage": 84.47, "elapsed_time": "6:03:27", "remaining_time": "1:06:49", "throughput": 1486.13, "total_tokens": 32408480} {"current_steps": 153570, "total_steps": 181800, "loss": 0.0064, "lr": 3.5836838743743854e-06, "epoch": 16.894389438943893, "percentage": 84.47, "elapsed_time": "6:03:27", "remaining_time": "1:06:48", "throughput": 1486.13, "total_tokens": 32409536} {"current_steps": 153575, "total_steps": 181800, "loss": 0.0861, "lr": 3.582445793396358e-06, "epoch": 16.894939493949394, "percentage": 84.47, "elapsed_time": "6:03:28", "remaining_time": "1:06:48", "throughput": 1486.14, "total_tokens": 32410592} {"current_steps": 153580, "total_steps": 181800, "loss": 0.0112, "lr": 3.581207909813658e-06, "epoch": 16.895489548954895, "percentage": 84.48, "elapsed_time": "6:03:29", "remaining_time": "1:06:47", "throughput": 1486.14, "total_tokens": 32411616} {"current_steps": 153585, "total_steps": 181800, "loss": 0.0049, "lr": 3.5799702236376796e-06, "epoch": 16.896039603960396, "percentage": 84.48, "elapsed_time": "6:03:30", "remaining_time": "1:06:46", "throughput": 1486.14, "total_tokens": 32412704} {"current_steps": 153590, "total_steps": 181800, "loss": 0.0628, "lr": 3.578732734879839e-06, "epoch": 16.896589658965897, "percentage": 84.48, "elapsed_time": "6:03:30", "remaining_time": "1:06:45", "throughput": 1486.14, "total_tokens": 32413728} {"current_steps": 153595, "total_steps": 181800, "loss": 0.1192, "lr": 3.5774954435515456e-06, "epoch": 16.8971397139714, "percentage": 84.49, "elapsed_time": "6:03:31", "remaining_time": "1:06:45", "throughput": 1486.14, "total_tokens": 32414848} {"current_steps": 153600, "total_steps": 181800, "loss": 0.089, "lr": 3.576258349664191e-06, "epoch": 16.897689768976896, "percentage": 84.49, "elapsed_time": "6:03:32", "remaining_time": "1:06:44", "throughput": 1486.15, "total_tokens": 32416000} {"current_steps": 153605, "total_steps": 181800, "loss": 0.0803, "lr": 3.5750214532291883e-06, "epoch": 16.898239823982397, "percentage": 84.49, "elapsed_time": "6:03:32", "remaining_time": "1:06:43", "throughput": 1486.15, "total_tokens": 32417120} {"current_steps": 153610, "total_steps": 181800, "loss": 0.0024, "lr": 3.5737847542579333e-06, "epoch": 16.8987898789879, "percentage": 84.49, "elapsed_time": "6:03:33", "remaining_time": "1:06:43", "throughput": 1486.15, "total_tokens": 32418080} {"current_steps": 153615, "total_steps": 181800, "loss": 0.0034, "lr": 3.572548252761815e-06, "epoch": 16.8993399339934, "percentage": 84.5, "elapsed_time": "6:03:34", "remaining_time": "1:06:42", "throughput": 1486.15, "total_tokens": 32419168} {"current_steps": 153620, "total_steps": 181800, "loss": 0.1465, "lr": 3.57131194875224e-06, "epoch": 16.8998899889989, "percentage": 84.5, "elapsed_time": "6:03:34", "remaining_time": "1:06:41", "throughput": 1486.15, "total_tokens": 32420224} {"current_steps": 153625, "total_steps": 181800, "loss": 0.0052, "lr": 3.5700758422405973e-06, "epoch": 16.9004400440044, "percentage": 84.5, "elapsed_time": "6:03:35", "remaining_time": "1:06:40", "throughput": 1486.16, "total_tokens": 32421312} {"current_steps": 153630, "total_steps": 181800, "loss": 0.0211, "lr": 3.568839933238291e-06, "epoch": 16.900990099009903, "percentage": 84.5, "elapsed_time": "6:03:36", "remaining_time": "1:06:40", "throughput": 1486.16, "total_tokens": 32422400} {"current_steps": 153635, "total_steps": 181800, "loss": 0.0046, "lr": 3.5676042217567014e-06, "epoch": 16.9015401540154, "percentage": 84.51, "elapsed_time": "6:03:36", "remaining_time": "1:06:39", "throughput": 1486.16, "total_tokens": 32423488} {"current_steps": 153640, "total_steps": 181800, "loss": 0.064, "lr": 3.566368707807216e-06, "epoch": 16.9020902090209, "percentage": 84.51, "elapsed_time": "6:03:37", "remaining_time": "1:06:38", "throughput": 1486.16, "total_tokens": 32424544} {"current_steps": 153645, "total_steps": 181800, "loss": 0.0054, "lr": 3.5651333914012235e-06, "epoch": 16.902640264026402, "percentage": 84.51, "elapsed_time": "6:03:38", "remaining_time": "1:06:38", "throughput": 1486.16, "total_tokens": 32425568} {"current_steps": 153650, "total_steps": 181800, "loss": 0.1037, "lr": 3.5638982725501174e-06, "epoch": 16.903190319031903, "percentage": 84.52, "elapsed_time": "6:03:38", "remaining_time": "1:06:37", "throughput": 1486.16, "total_tokens": 32426592} {"current_steps": 153655, "total_steps": 181800, "loss": 0.0047, "lr": 3.562663351265269e-06, "epoch": 16.903740374037405, "percentage": 84.52, "elapsed_time": "6:03:39", "remaining_time": "1:06:36", "throughput": 1486.16, "total_tokens": 32427584} {"current_steps": 153660, "total_steps": 181800, "loss": 0.001, "lr": 3.561428627558072e-06, "epoch": 16.904290429042906, "percentage": 84.52, "elapsed_time": "6:03:40", "remaining_time": "1:06:36", "throughput": 1486.16, "total_tokens": 32428544} {"current_steps": 153665, "total_steps": 181800, "loss": 0.0942, "lr": 3.5601941014398925e-06, "epoch": 16.904840484048403, "percentage": 84.52, "elapsed_time": "6:03:41", "remaining_time": "1:06:35", "throughput": 1486.16, "total_tokens": 32429632} {"current_steps": 153670, "total_steps": 181800, "loss": 0.0029, "lr": 3.558959772922124e-06, "epoch": 16.905390539053904, "percentage": 84.53, "elapsed_time": "6:03:41", "remaining_time": "1:06:34", "throughput": 1486.16, "total_tokens": 32430688} {"current_steps": 153675, "total_steps": 181800, "loss": 0.1645, "lr": 3.55772564201613e-06, "epoch": 16.905940594059405, "percentage": 84.53, "elapsed_time": "6:03:42", "remaining_time": "1:06:33", "throughput": 1486.16, "total_tokens": 32431680} {"current_steps": 153680, "total_steps": 181800, "loss": 0.0569, "lr": 3.5564917087332867e-06, "epoch": 16.906490649064907, "percentage": 84.53, "elapsed_time": "6:03:43", "remaining_time": "1:06:33", "throughput": 1486.16, "total_tokens": 32432736} {"current_steps": 153685, "total_steps": 181800, "loss": 0.0018, "lr": 3.5552579730849773e-06, "epoch": 16.907040704070408, "percentage": 84.54, "elapsed_time": "6:03:43", "remaining_time": "1:06:32", "throughput": 1486.16, "total_tokens": 32433792} {"current_steps": 153690, "total_steps": 181800, "loss": 0.0146, "lr": 3.554024435082559e-06, "epoch": 16.90759075907591, "percentage": 84.54, "elapsed_time": "6:03:44", "remaining_time": "1:06:31", "throughput": 1486.16, "total_tokens": 32434848} {"current_steps": 153695, "total_steps": 181800, "loss": 0.001, "lr": 3.5527910947374123e-06, "epoch": 16.90814081408141, "percentage": 84.54, "elapsed_time": "6:03:45", "remaining_time": "1:06:31", "throughput": 1486.17, "total_tokens": 32435904} {"current_steps": 153700, "total_steps": 181800, "loss": 0.0028, "lr": 3.551557952060894e-06, "epoch": 16.908690869086907, "percentage": 84.54, "elapsed_time": "6:03:45", "remaining_time": "1:06:30", "throughput": 1486.17, "total_tokens": 32436992} {"current_steps": 153705, "total_steps": 181800, "loss": 0.0031, "lr": 3.5503250070643727e-06, "epoch": 16.90924092409241, "percentage": 84.55, "elapsed_time": "6:03:46", "remaining_time": "1:06:29", "throughput": 1486.17, "total_tokens": 32437984} {"current_steps": 153710, "total_steps": 181800, "loss": 0.0342, "lr": 3.5490922597592206e-06, "epoch": 16.90979097909791, "percentage": 84.55, "elapsed_time": "6:03:47", "remaining_time": "1:06:28", "throughput": 1486.17, "total_tokens": 32439008} {"current_steps": 153715, "total_steps": 181800, "loss": 0.0038, "lr": 3.547859710156784e-06, "epoch": 16.91034103410341, "percentage": 84.55, "elapsed_time": "6:03:47", "remaining_time": "1:06:28", "throughput": 1486.17, "total_tokens": 32440064} {"current_steps": 153720, "total_steps": 181800, "loss": 0.0047, "lr": 3.5466273582684366e-06, "epoch": 16.91089108910891, "percentage": 84.55, "elapsed_time": "6:03:48", "remaining_time": "1:06:27", "throughput": 1486.17, "total_tokens": 32441088} {"current_steps": 153725, "total_steps": 181800, "loss": 0.0043, "lr": 3.545395204105534e-06, "epoch": 16.911441144114413, "percentage": 84.56, "elapsed_time": "6:03:49", "remaining_time": "1:06:26", "throughput": 1486.17, "total_tokens": 32442080} {"current_steps": 153730, "total_steps": 181800, "loss": 0.0395, "lr": 3.544163247679419e-06, "epoch": 16.91199119911991, "percentage": 84.56, "elapsed_time": "6:03:50", "remaining_time": "1:06:26", "throughput": 1486.17, "total_tokens": 32443136} {"current_steps": 153735, "total_steps": 181800, "loss": 0.0048, "lr": 3.542931489001458e-06, "epoch": 16.91254125412541, "percentage": 84.56, "elapsed_time": "6:03:50", "remaining_time": "1:06:25", "throughput": 1486.17, "total_tokens": 32444192} {"current_steps": 153740, "total_steps": 181800, "loss": 0.0018, "lr": 3.5416999280830004e-06, "epoch": 16.913091309130913, "percentage": 84.57, "elapsed_time": "6:03:51", "remaining_time": "1:06:24", "throughput": 1486.17, "total_tokens": 32445280} {"current_steps": 153745, "total_steps": 181800, "loss": 0.0227, "lr": 3.5404685649354036e-06, "epoch": 16.913641364136414, "percentage": 84.57, "elapsed_time": "6:03:52", "remaining_time": "1:06:23", "throughput": 1486.17, "total_tokens": 32446272} {"current_steps": 153750, "total_steps": 181800, "loss": 0.0077, "lr": 3.5392373995700114e-06, "epoch": 16.914191419141915, "percentage": 84.57, "elapsed_time": "6:03:52", "remaining_time": "1:06:23", "throughput": 1486.17, "total_tokens": 32447392} {"current_steps": 153755, "total_steps": 181800, "loss": 0.0052, "lr": 3.5380064319981644e-06, "epoch": 16.914741474147416, "percentage": 84.57, "elapsed_time": "6:03:53", "remaining_time": "1:06:22", "throughput": 1486.17, "total_tokens": 32448416} {"current_steps": 153760, "total_steps": 181800, "loss": 0.1584, "lr": 3.5367756622312148e-06, "epoch": 16.915291529152917, "percentage": 84.58, "elapsed_time": "6:03:54", "remaining_time": "1:06:21", "throughput": 1486.18, "total_tokens": 32449472} {"current_steps": 153765, "total_steps": 181800, "loss": 0.0176, "lr": 3.5355450902805036e-06, "epoch": 16.915841584158414, "percentage": 84.58, "elapsed_time": "6:03:54", "remaining_time": "1:06:21", "throughput": 1486.18, "total_tokens": 32450592} {"current_steps": 153770, "total_steps": 181800, "loss": 0.0011, "lr": 3.5343147161573777e-06, "epoch": 16.916391639163916, "percentage": 84.58, "elapsed_time": "6:03:55", "remaining_time": "1:06:20", "throughput": 1486.19, "total_tokens": 32451744} {"current_steps": 153775, "total_steps": 181800, "loss": 0.0655, "lr": 3.5330845398731745e-06, "epoch": 16.916941694169417, "percentage": 84.58, "elapsed_time": "6:03:56", "remaining_time": "1:06:19", "throughput": 1486.19, "total_tokens": 32452768} {"current_steps": 153780, "total_steps": 181800, "loss": 0.0016, "lr": 3.531854561439224e-06, "epoch": 16.917491749174918, "percentage": 84.59, "elapsed_time": "6:03:56", "remaining_time": "1:06:18", "throughput": 1486.19, "total_tokens": 32453856} {"current_steps": 153785, "total_steps": 181800, "loss": 0.0034, "lr": 3.5306247808668758e-06, "epoch": 16.91804180418042, "percentage": 84.59, "elapsed_time": "6:03:57", "remaining_time": "1:06:18", "throughput": 1486.19, "total_tokens": 32454944} {"current_steps": 153790, "total_steps": 181800, "loss": 0.0008, "lr": 3.529395198167451e-06, "epoch": 16.91859185918592, "percentage": 84.59, "elapsed_time": "6:03:58", "remaining_time": "1:06:17", "throughput": 1486.19, "total_tokens": 32456000} {"current_steps": 153795, "total_steps": 181800, "loss": 0.0592, "lr": 3.528165813352288e-06, "epoch": 16.919141914191417, "percentage": 84.6, "elapsed_time": "6:03:59", "remaining_time": "1:06:16", "throughput": 1486.19, "total_tokens": 32457056} {"current_steps": 153800, "total_steps": 181800, "loss": 0.0037, "lr": 3.5269366264327226e-06, "epoch": 16.91969196919692, "percentage": 84.6, "elapsed_time": "6:03:59", "remaining_time": "1:06:16", "throughput": 1486.2, "total_tokens": 32458144} {"current_steps": 153805, "total_steps": 181800, "loss": 0.0252, "lr": 3.5257076374200725e-06, "epoch": 16.92024202420242, "percentage": 84.6, "elapsed_time": "6:04:00", "remaining_time": "1:06:15", "throughput": 1486.2, "total_tokens": 32459168} {"current_steps": 153810, "total_steps": 181800, "loss": 0.0012, "lr": 3.5244788463256766e-06, "epoch": 16.92079207920792, "percentage": 84.6, "elapsed_time": "6:04:01", "remaining_time": "1:06:14", "throughput": 1486.2, "total_tokens": 32460224} {"current_steps": 153815, "total_steps": 181800, "loss": 0.027, "lr": 3.523250253160848e-06, "epoch": 16.921342134213422, "percentage": 84.61, "elapsed_time": "6:04:01", "remaining_time": "1:06:13", "throughput": 1486.2, "total_tokens": 32461248} {"current_steps": 153820, "total_steps": 181800, "loss": 0.0812, "lr": 3.522021857936916e-06, "epoch": 16.921892189218923, "percentage": 84.61, "elapsed_time": "6:04:02", "remaining_time": "1:06:13", "throughput": 1486.2, "total_tokens": 32462336} {"current_steps": 153825, "total_steps": 181800, "loss": 0.0071, "lr": 3.5207936606652115e-06, "epoch": 16.922442244224424, "percentage": 84.61, "elapsed_time": "6:04:03", "remaining_time": "1:06:12", "throughput": 1486.2, "total_tokens": 32463424} {"current_steps": 153830, "total_steps": 181800, "loss": 0.0079, "lr": 3.5195656613570354e-06, "epoch": 16.92299229922992, "percentage": 84.61, "elapsed_time": "6:04:03", "remaining_time": "1:06:11", "throughput": 1486.21, "total_tokens": 32464512} {"current_steps": 153835, "total_steps": 181800, "loss": 0.003, "lr": 3.5183378600237237e-06, "epoch": 16.923542354235423, "percentage": 84.62, "elapsed_time": "6:04:04", "remaining_time": "1:06:11", "throughput": 1486.21, "total_tokens": 32465664} {"current_steps": 153840, "total_steps": 181800, "loss": 0.0828, "lr": 3.5171102566765757e-06, "epoch": 16.924092409240924, "percentage": 84.62, "elapsed_time": "6:04:05", "remaining_time": "1:06:10", "throughput": 1486.21, "total_tokens": 32466720} {"current_steps": 153845, "total_steps": 181800, "loss": 0.0132, "lr": 3.515882851326921e-06, "epoch": 16.924642464246425, "percentage": 84.62, "elapsed_time": "6:04:05", "remaining_time": "1:06:09", "throughput": 1486.22, "total_tokens": 32467776} {"current_steps": 153850, "total_steps": 181800, "loss": 0.004, "lr": 3.5146556439860617e-06, "epoch": 16.925192519251926, "percentage": 84.63, "elapsed_time": "6:04:06", "remaining_time": "1:06:08", "throughput": 1486.21, "total_tokens": 32468768} {"current_steps": 153855, "total_steps": 181800, "loss": 0.0025, "lr": 3.5134286346653084e-06, "epoch": 16.925742574257427, "percentage": 84.63, "elapsed_time": "6:04:07", "remaining_time": "1:06:08", "throughput": 1486.21, "total_tokens": 32469792} {"current_steps": 153860, "total_steps": 181800, "loss": 0.0021, "lr": 3.5122018233759797e-06, "epoch": 16.926292629262925, "percentage": 84.63, "elapsed_time": "6:04:08", "remaining_time": "1:06:07", "throughput": 1486.21, "total_tokens": 32470784} {"current_steps": 153865, "total_steps": 181800, "loss": 0.0367, "lr": 3.5109752101293775e-06, "epoch": 16.926842684268426, "percentage": 84.63, "elapsed_time": "6:04:08", "remaining_time": "1:06:06", "throughput": 1486.21, "total_tokens": 32471840} {"current_steps": 153870, "total_steps": 181800, "loss": 0.0143, "lr": 3.509748794936796e-06, "epoch": 16.927392739273927, "percentage": 84.64, "elapsed_time": "6:04:09", "remaining_time": "1:06:06", "throughput": 1486.22, "total_tokens": 32472896} {"current_steps": 153875, "total_steps": 181800, "loss": 0.0512, "lr": 3.508522577809556e-06, "epoch": 16.927942794279428, "percentage": 84.64, "elapsed_time": "6:04:10", "remaining_time": "1:06:05", "throughput": 1486.22, "total_tokens": 32473952} {"current_steps": 153880, "total_steps": 181800, "loss": 0.002, "lr": 3.5072965587589405e-06, "epoch": 16.92849284928493, "percentage": 84.64, "elapsed_time": "6:04:10", "remaining_time": "1:06:04", "throughput": 1486.22, "total_tokens": 32475008} {"current_steps": 153885, "total_steps": 181800, "loss": 0.0012, "lr": 3.506070737796269e-06, "epoch": 16.92904290429043, "percentage": 84.65, "elapsed_time": "6:04:11", "remaining_time": "1:06:03", "throughput": 1486.22, "total_tokens": 32476096} {"current_steps": 153890, "total_steps": 181800, "loss": 0.0324, "lr": 3.504845114932831e-06, "epoch": 16.92959295929593, "percentage": 84.65, "elapsed_time": "6:04:12", "remaining_time": "1:06:03", "throughput": 1486.22, "total_tokens": 32477120} {"current_steps": 153895, "total_steps": 181800, "loss": 0.0034, "lr": 3.503619690179913e-06, "epoch": 16.93014301430143, "percentage": 84.65, "elapsed_time": "6:04:12", "remaining_time": "1:06:02", "throughput": 1486.22, "total_tokens": 32478112} {"current_steps": 153900, "total_steps": 181800, "loss": 0.0481, "lr": 3.502394463548825e-06, "epoch": 16.93069306930693, "percentage": 84.65, "elapsed_time": "6:04:13", "remaining_time": "1:06:01", "throughput": 1486.22, "total_tokens": 32479168} {"current_steps": 153905, "total_steps": 181800, "loss": 0.0056, "lr": 3.5011694350508468e-06, "epoch": 16.93124312431243, "percentage": 84.66, "elapsed_time": "6:04:14", "remaining_time": "1:06:01", "throughput": 1486.23, "total_tokens": 32480288} {"current_steps": 153910, "total_steps": 181800, "loss": 0.0633, "lr": 3.499944604697272e-06, "epoch": 16.931793179317932, "percentage": 84.66, "elapsed_time": "6:04:14", "remaining_time": "1:06:00", "throughput": 1486.23, "total_tokens": 32481376} {"current_steps": 153915, "total_steps": 181800, "loss": 0.0071, "lr": 3.498719972499398e-06, "epoch": 16.932343234323433, "percentage": 84.66, "elapsed_time": "6:04:15", "remaining_time": "1:05:59", "throughput": 1486.23, "total_tokens": 32482432} {"current_steps": 153920, "total_steps": 181800, "loss": 0.0212, "lr": 3.4974955384684982e-06, "epoch": 16.932893289328934, "percentage": 84.66, "elapsed_time": "6:04:16", "remaining_time": "1:05:58", "throughput": 1486.23, "total_tokens": 32483456} {"current_steps": 153925, "total_steps": 181800, "loss": 0.0185, "lr": 3.4962713026158694e-06, "epoch": 16.933443344334435, "percentage": 84.67, "elapsed_time": "6:04:16", "remaining_time": "1:05:58", "throughput": 1486.23, "total_tokens": 32484448} {"current_steps": 153930, "total_steps": 181800, "loss": 0.0029, "lr": 3.4950472649527832e-06, "epoch": 16.933993399339933, "percentage": 84.67, "elapsed_time": "6:04:17", "remaining_time": "1:05:57", "throughput": 1486.23, "total_tokens": 32485568} {"current_steps": 153935, "total_steps": 181800, "loss": 0.0866, "lr": 3.4938234254905304e-06, "epoch": 16.934543454345434, "percentage": 84.67, "elapsed_time": "6:04:18", "remaining_time": "1:05:56", "throughput": 1486.23, "total_tokens": 32486624} {"current_steps": 153940, "total_steps": 181800, "loss": 0.0934, "lr": 3.4925997842403912e-06, "epoch": 16.935093509350935, "percentage": 84.68, "elapsed_time": "6:04:19", "remaining_time": "1:05:56", "throughput": 1486.23, "total_tokens": 32487680} {"current_steps": 153945, "total_steps": 181800, "loss": 0.0016, "lr": 3.491376341213634e-06, "epoch": 16.935643564356436, "percentage": 84.68, "elapsed_time": "6:04:19", "remaining_time": "1:05:55", "throughput": 1486.24, "total_tokens": 32488768} {"current_steps": 153950, "total_steps": 181800, "loss": 0.0398, "lr": 3.4901530964215443e-06, "epoch": 16.936193619361937, "percentage": 84.68, "elapsed_time": "6:04:20", "remaining_time": "1:05:54", "throughput": 1486.24, "total_tokens": 32489760} {"current_steps": 153955, "total_steps": 181800, "loss": 0.0088, "lr": 3.4889300498753884e-06, "epoch": 16.936743674367438, "percentage": 84.68, "elapsed_time": "6:04:21", "remaining_time": "1:05:53", "throughput": 1486.24, "total_tokens": 32490784} {"current_steps": 153960, "total_steps": 181800, "loss": 0.0057, "lr": 3.4877072015864486e-06, "epoch": 16.937293729372936, "percentage": 84.69, "elapsed_time": "6:04:21", "remaining_time": "1:05:53", "throughput": 1486.24, "total_tokens": 32491840} {"current_steps": 153965, "total_steps": 181800, "loss": 0.0073, "lr": 3.48648455156598e-06, "epoch": 16.937843784378437, "percentage": 84.69, "elapsed_time": "6:04:22", "remaining_time": "1:05:52", "throughput": 1486.24, "total_tokens": 32492832} {"current_steps": 153970, "total_steps": 181800, "loss": 0.0149, "lr": 3.4852620998252622e-06, "epoch": 16.938393839383938, "percentage": 84.69, "elapsed_time": "6:04:23", "remaining_time": "1:05:51", "throughput": 1486.24, "total_tokens": 32493920} {"current_steps": 153975, "total_steps": 181800, "loss": 0.068, "lr": 3.4840398463755667e-06, "epoch": 16.93894389438944, "percentage": 84.69, "elapsed_time": "6:04:23", "remaining_time": "1:05:51", "throughput": 1486.24, "total_tokens": 32494976} {"current_steps": 153980, "total_steps": 181800, "loss": 0.0007, "lr": 3.4828177912281434e-06, "epoch": 16.93949394939494, "percentage": 84.7, "elapsed_time": "6:04:24", "remaining_time": "1:05:50", "throughput": 1486.24, "total_tokens": 32496064} {"current_steps": 153985, "total_steps": 181800, "loss": 0.0067, "lr": 3.4815959343942715e-06, "epoch": 16.94004400440044, "percentage": 84.7, "elapsed_time": "6:04:25", "remaining_time": "1:05:49", "throughput": 1486.24, "total_tokens": 32497120} {"current_steps": 153990, "total_steps": 181800, "loss": 0.0087, "lr": 3.4803742758852038e-06, "epoch": 16.94059405940594, "percentage": 84.7, "elapsed_time": "6:04:25", "remaining_time": "1:05:48", "throughput": 1486.25, "total_tokens": 32498240} {"current_steps": 153995, "total_steps": 181800, "loss": 0.1498, "lr": 3.479152815712189e-06, "epoch": 16.94114411441144, "percentage": 84.71, "elapsed_time": "6:04:26", "remaining_time": "1:05:48", "throughput": 1486.25, "total_tokens": 32499232} {"current_steps": 154000, "total_steps": 181800, "loss": 0.0439, "lr": 3.477931553886507e-06, "epoch": 16.94169416941694, "percentage": 84.71, "elapsed_time": "6:04:27", "remaining_time": "1:05:47", "throughput": 1486.25, "total_tokens": 32500256} {"current_steps": 154005, "total_steps": 181800, "loss": 0.0031, "lr": 3.4767104904193963e-06, "epoch": 16.942244224422442, "percentage": 84.71, "elapsed_time": "6:04:28", "remaining_time": "1:05:46", "throughput": 1486.25, "total_tokens": 32501312} {"current_steps": 154010, "total_steps": 181800, "loss": 0.0495, "lr": 3.475489625322123e-06, "epoch": 16.942794279427943, "percentage": 84.71, "elapsed_time": "6:04:28", "remaining_time": "1:05:46", "throughput": 1486.25, "total_tokens": 32502368} {"current_steps": 154015, "total_steps": 181800, "loss": 0.0035, "lr": 3.4742689586059337e-06, "epoch": 16.943344334433444, "percentage": 84.72, "elapsed_time": "6:04:29", "remaining_time": "1:05:45", "throughput": 1486.25, "total_tokens": 32503456} {"current_steps": 154020, "total_steps": 181800, "loss": 0.0041, "lr": 3.4730484902820717e-06, "epoch": 16.943894389438945, "percentage": 84.72, "elapsed_time": "6:04:30", "remaining_time": "1:05:44", "throughput": 1486.26, "total_tokens": 32504576} {"current_steps": 154025, "total_steps": 181800, "loss": 0.02, "lr": 3.4718282203617947e-06, "epoch": 16.944444444444443, "percentage": 84.72, "elapsed_time": "6:04:30", "remaining_time": "1:05:43", "throughput": 1486.26, "total_tokens": 32505600} {"current_steps": 154030, "total_steps": 181800, "loss": 0.0944, "lr": 3.470608148856344e-06, "epoch": 16.944994499449944, "percentage": 84.72, "elapsed_time": "6:04:31", "remaining_time": "1:05:43", "throughput": 1486.26, "total_tokens": 32506656} {"current_steps": 154035, "total_steps": 181800, "loss": 0.1073, "lr": 3.4693882757769745e-06, "epoch": 16.945544554455445, "percentage": 84.73, "elapsed_time": "6:04:32", "remaining_time": "1:05:42", "throughput": 1486.26, "total_tokens": 32507712} {"current_steps": 154040, "total_steps": 181800, "loss": 0.0231, "lr": 3.4681686011349218e-06, "epoch": 16.946094609460946, "percentage": 84.73, "elapsed_time": "6:04:32", "remaining_time": "1:05:41", "throughput": 1486.26, "total_tokens": 32508736} {"current_steps": 154045, "total_steps": 181800, "loss": 0.0271, "lr": 3.466949124941421e-06, "epoch": 16.946644664466447, "percentage": 84.73, "elapsed_time": "6:04:33", "remaining_time": "1:05:41", "throughput": 1486.26, "total_tokens": 32509760} {"current_steps": 154050, "total_steps": 181800, "loss": 0.043, "lr": 3.4657298472077214e-06, "epoch": 16.94719471947195, "percentage": 84.74, "elapsed_time": "6:04:34", "remaining_time": "1:05:40", "throughput": 1486.26, "total_tokens": 32510784} {"current_steps": 154055, "total_steps": 181800, "loss": 0.0783, "lr": 3.4645107679450535e-06, "epoch": 16.94774477447745, "percentage": 84.74, "elapsed_time": "6:04:34", "remaining_time": "1:05:39", "throughput": 1486.26, "total_tokens": 32511872} {"current_steps": 154060, "total_steps": 181800, "loss": 0.0785, "lr": 3.4632918871646546e-06, "epoch": 16.948294829482947, "percentage": 84.74, "elapsed_time": "6:04:35", "remaining_time": "1:05:38", "throughput": 1486.26, "total_tokens": 32512960} {"current_steps": 154065, "total_steps": 181800, "loss": 0.1297, "lr": 3.4620732048777668e-06, "epoch": 16.948844884488448, "percentage": 84.74, "elapsed_time": "6:04:36", "remaining_time": "1:05:38", "throughput": 1486.26, "total_tokens": 32513984} {"current_steps": 154070, "total_steps": 181800, "loss": 0.0021, "lr": 3.4608547210956107e-06, "epoch": 16.94939493949395, "percentage": 84.75, "elapsed_time": "6:04:36", "remaining_time": "1:05:37", "throughput": 1486.26, "total_tokens": 32514976} {"current_steps": 154075, "total_steps": 181800, "loss": 0.0725, "lr": 3.459636435829425e-06, "epoch": 16.94994499449945, "percentage": 84.75, "elapsed_time": "6:04:37", "remaining_time": "1:05:36", "throughput": 1486.26, "total_tokens": 32516032} {"current_steps": 154080, "total_steps": 181800, "loss": 0.0035, "lr": 3.458418349090428e-06, "epoch": 16.95049504950495, "percentage": 84.75, "elapsed_time": "6:04:38", "remaining_time": "1:05:36", "throughput": 1486.27, "total_tokens": 32517184} {"current_steps": 154085, "total_steps": 181800, "loss": 0.0884, "lr": 3.4572004608898535e-06, "epoch": 16.951045104510452, "percentage": 84.76, "elapsed_time": "6:04:39", "remaining_time": "1:05:35", "throughput": 1486.27, "total_tokens": 32518304} {"current_steps": 154090, "total_steps": 181800, "loss": 0.0008, "lr": 3.4559827712389305e-06, "epoch": 16.95159515951595, "percentage": 84.76, "elapsed_time": "6:04:39", "remaining_time": "1:05:34", "throughput": 1486.28, "total_tokens": 32519360} {"current_steps": 154095, "total_steps": 181800, "loss": 0.0065, "lr": 3.454765280148872e-06, "epoch": 16.95214521452145, "percentage": 84.76, "elapsed_time": "6:04:40", "remaining_time": "1:05:33", "throughput": 1486.28, "total_tokens": 32520416} {"current_steps": 154100, "total_steps": 181800, "loss": 0.0026, "lr": 3.453547987630909e-06, "epoch": 16.952695269526952, "percentage": 84.76, "elapsed_time": "6:04:41", "remaining_time": "1:05:33", "throughput": 1486.28, "total_tokens": 32521440} {"current_steps": 154105, "total_steps": 181800, "loss": 0.0512, "lr": 3.452330893696254e-06, "epoch": 16.953245324532453, "percentage": 84.77, "elapsed_time": "6:04:41", "remaining_time": "1:05:32", "throughput": 1486.28, "total_tokens": 32522592} {"current_steps": 154110, "total_steps": 181800, "loss": 0.0125, "lr": 3.4511139983561202e-06, "epoch": 16.953795379537954, "percentage": 84.77, "elapsed_time": "6:04:42", "remaining_time": "1:05:31", "throughput": 1486.28, "total_tokens": 32523648} {"current_steps": 154115, "total_steps": 181800, "loss": 0.0009, "lr": 3.449897301621727e-06, "epoch": 16.954345434543455, "percentage": 84.77, "elapsed_time": "6:04:43", "remaining_time": "1:05:31", "throughput": 1486.29, "total_tokens": 32524704} {"current_steps": 154120, "total_steps": 181800, "loss": 0.0021, "lr": 3.448680803504292e-06, "epoch": 16.954895489548957, "percentage": 84.77, "elapsed_time": "6:04:43", "remaining_time": "1:05:30", "throughput": 1486.29, "total_tokens": 32525760} {"current_steps": 154125, "total_steps": 181800, "loss": 0.0028, "lr": 3.4474645040150298e-06, "epoch": 16.955445544554454, "percentage": 84.78, "elapsed_time": "6:04:44", "remaining_time": "1:05:29", "throughput": 1486.29, "total_tokens": 32526816} {"current_steps": 154130, "total_steps": 181800, "loss": 0.1267, "lr": 3.446248403165145e-06, "epoch": 16.955995599559955, "percentage": 84.78, "elapsed_time": "6:04:45", "remaining_time": "1:05:28", "throughput": 1486.29, "total_tokens": 32527904} {"current_steps": 154135, "total_steps": 181800, "loss": 0.0039, "lr": 3.445032500965842e-06, "epoch": 16.956545654565456, "percentage": 84.78, "elapsed_time": "6:04:45", "remaining_time": "1:05:28", "throughput": 1486.3, "total_tokens": 32529024} {"current_steps": 154140, "total_steps": 181800, "loss": 0.0555, "lr": 3.4438167974283287e-06, "epoch": 16.957095709570957, "percentage": 84.79, "elapsed_time": "6:04:46", "remaining_time": "1:05:27", "throughput": 1486.3, "total_tokens": 32530048} {"current_steps": 154145, "total_steps": 181800, "loss": 0.0212, "lr": 3.442601292563813e-06, "epoch": 16.95764576457646, "percentage": 84.79, "elapsed_time": "6:04:47", "remaining_time": "1:05:26", "throughput": 1486.3, "total_tokens": 32531104} {"current_steps": 154150, "total_steps": 181800, "loss": 0.057, "lr": 3.441385986383505e-06, "epoch": 16.95819581958196, "percentage": 84.79, "elapsed_time": "6:04:48", "remaining_time": "1:05:26", "throughput": 1486.3, "total_tokens": 32532288} {"current_steps": 154155, "total_steps": 181800, "loss": 0.012, "lr": 3.4401708788985966e-06, "epoch": 16.958745874587457, "percentage": 84.79, "elapsed_time": "6:04:48", "remaining_time": "1:05:25", "throughput": 1486.3, "total_tokens": 32533344} {"current_steps": 154160, "total_steps": 181800, "loss": 0.0007, "lr": 3.4389559701202806e-06, "epoch": 16.959295929592958, "percentage": 84.8, "elapsed_time": "6:04:49", "remaining_time": "1:05:24", "throughput": 1486.3, "total_tokens": 32534336} {"current_steps": 154165, "total_steps": 181800, "loss": 0.0127, "lr": 3.4377412600597682e-06, "epoch": 16.95984598459846, "percentage": 84.8, "elapsed_time": "6:04:50", "remaining_time": "1:05:23", "throughput": 1486.31, "total_tokens": 32535456} {"current_steps": 154170, "total_steps": 181800, "loss": 0.0215, "lr": 3.4365267487282417e-06, "epoch": 16.96039603960396, "percentage": 84.8, "elapsed_time": "6:04:50", "remaining_time": "1:05:23", "throughput": 1486.31, "total_tokens": 32536512} {"current_steps": 154175, "total_steps": 181800, "loss": 0.0033, "lr": 3.4353124361369006e-06, "epoch": 16.96094609460946, "percentage": 84.8, "elapsed_time": "6:04:51", "remaining_time": "1:05:22", "throughput": 1486.31, "total_tokens": 32537568} {"current_steps": 154180, "total_steps": 181800, "loss": 0.1048, "lr": 3.4340983222969443e-06, "epoch": 16.961496149614963, "percentage": 84.81, "elapsed_time": "6:04:52", "remaining_time": "1:05:21", "throughput": 1486.31, "total_tokens": 32538624} {"current_steps": 154185, "total_steps": 181800, "loss": 0.0068, "lr": 3.432884407219547e-06, "epoch": 16.962046204620464, "percentage": 84.81, "elapsed_time": "6:04:52", "remaining_time": "1:05:21", "throughput": 1486.31, "total_tokens": 32539680} {"current_steps": 154190, "total_steps": 181800, "loss": 0.0319, "lr": 3.431670690915914e-06, "epoch": 16.96259625962596, "percentage": 84.81, "elapsed_time": "6:04:53", "remaining_time": "1:05:20", "throughput": 1486.31, "total_tokens": 32540672} {"current_steps": 154195, "total_steps": 181800, "loss": 0.0132, "lr": 3.430457173397217e-06, "epoch": 16.963146314631462, "percentage": 84.82, "elapsed_time": "6:04:54", "remaining_time": "1:05:19", "throughput": 1486.31, "total_tokens": 32541728} {"current_steps": 154200, "total_steps": 181800, "loss": 0.0081, "lr": 3.4292438546746437e-06, "epoch": 16.963696369636963, "percentage": 84.82, "elapsed_time": "6:04:54", "remaining_time": "1:05:18", "throughput": 1486.31, "total_tokens": 32542784} {"current_steps": 154205, "total_steps": 181800, "loss": 0.0113, "lr": 3.4280307347593853e-06, "epoch": 16.964246424642464, "percentage": 84.82, "elapsed_time": "6:04:55", "remaining_time": "1:05:18", "throughput": 1486.31, "total_tokens": 32543808} {"current_steps": 154210, "total_steps": 181800, "loss": 0.0007, "lr": 3.426817813662611e-06, "epoch": 16.964796479647966, "percentage": 84.82, "elapsed_time": "6:04:56", "remaining_time": "1:05:17", "throughput": 1486.31, "total_tokens": 32544832} {"current_steps": 154215, "total_steps": 181800, "loss": 0.006, "lr": 3.4256050913955117e-06, "epoch": 16.965346534653467, "percentage": 84.83, "elapsed_time": "6:04:57", "remaining_time": "1:05:16", "throughput": 1486.31, "total_tokens": 32545888} {"current_steps": 154220, "total_steps": 181800, "loss": 0.0015, "lr": 3.4243925679692535e-06, "epoch": 16.965896589658964, "percentage": 84.83, "elapsed_time": "6:04:57", "remaining_time": "1:05:16", "throughput": 1486.32, "total_tokens": 32546976} {"current_steps": 154225, "total_steps": 181800, "loss": 0.0021, "lr": 3.423180243395019e-06, "epoch": 16.966446644664465, "percentage": 84.83, "elapsed_time": "6:04:58", "remaining_time": "1:05:15", "throughput": 1486.31, "total_tokens": 32547936} {"current_steps": 154230, "total_steps": 181800, "loss": 0.1096, "lr": 3.421968117683974e-06, "epoch": 16.966996699669966, "percentage": 84.83, "elapsed_time": "6:04:59", "remaining_time": "1:05:14", "throughput": 1486.32, "total_tokens": 32548960} {"current_steps": 154235, "total_steps": 181800, "loss": 0.0044, "lr": 3.4207561908472934e-06, "epoch": 16.967546754675467, "percentage": 84.84, "elapsed_time": "6:04:59", "remaining_time": "1:05:13", "throughput": 1486.32, "total_tokens": 32550048} {"current_steps": 154240, "total_steps": 181800, "loss": 0.001, "lr": 3.4195444628961572e-06, "epoch": 16.96809680968097, "percentage": 84.84, "elapsed_time": "6:05:00", "remaining_time": "1:05:13", "throughput": 1486.32, "total_tokens": 32551104} {"current_steps": 154245, "total_steps": 181800, "loss": 0.0744, "lr": 3.4183329338417224e-06, "epoch": 16.96864686468647, "percentage": 84.84, "elapsed_time": "6:05:01", "remaining_time": "1:05:12", "throughput": 1486.32, "total_tokens": 32552224} {"current_steps": 154250, "total_steps": 181800, "loss": 0.0702, "lr": 3.41712160369515e-06, "epoch": 16.96919691969197, "percentage": 84.85, "elapsed_time": "6:05:01", "remaining_time": "1:05:11", "throughput": 1486.33, "total_tokens": 32553312} {"current_steps": 154255, "total_steps": 181800, "loss": 0.1296, "lr": 3.4159104724676122e-06, "epoch": 16.96974697469747, "percentage": 84.85, "elapsed_time": "6:05:02", "remaining_time": "1:05:11", "throughput": 1486.33, "total_tokens": 32554336} {"current_steps": 154260, "total_steps": 181800, "loss": 0.1339, "lr": 3.4146995401702715e-06, "epoch": 16.97029702970297, "percentage": 84.85, "elapsed_time": "6:05:03", "remaining_time": "1:05:10", "throughput": 1486.33, "total_tokens": 32555456} {"current_steps": 154265, "total_steps": 181800, "loss": 0.0538, "lr": 3.413488806814294e-06, "epoch": 16.97084708470847, "percentage": 84.85, "elapsed_time": "6:05:03", "remaining_time": "1:05:09", "throughput": 1486.33, "total_tokens": 32556480} {"current_steps": 154270, "total_steps": 181800, "loss": 0.0721, "lr": 3.4122782724108295e-06, "epoch": 16.97139713971397, "percentage": 84.86, "elapsed_time": "6:05:04", "remaining_time": "1:05:08", "throughput": 1486.33, "total_tokens": 32557504} {"current_steps": 154275, "total_steps": 181800, "loss": 0.0012, "lr": 3.4110679369710326e-06, "epoch": 16.971947194719473, "percentage": 84.86, "elapsed_time": "6:05:05", "remaining_time": "1:05:08", "throughput": 1486.33, "total_tokens": 32558528} {"current_steps": 154280, "total_steps": 181800, "loss": 0.0009, "lr": 3.4098578005060696e-06, "epoch": 16.972497249724974, "percentage": 84.86, "elapsed_time": "6:05:06", "remaining_time": "1:05:07", "throughput": 1486.33, "total_tokens": 32559552} {"current_steps": 154285, "total_steps": 181800, "loss": 0.0051, "lr": 3.4086478630270813e-06, "epoch": 16.97304730473047, "percentage": 84.87, "elapsed_time": "6:05:06", "remaining_time": "1:05:06", "throughput": 1486.33, "total_tokens": 32560608} {"current_steps": 154290, "total_steps": 181800, "loss": 0.0096, "lr": 3.4074381245452232e-06, "epoch": 16.973597359735972, "percentage": 84.87, "elapsed_time": "6:05:07", "remaining_time": "1:05:06", "throughput": 1486.33, "total_tokens": 32561664} {"current_steps": 154295, "total_steps": 181800, "loss": 0.0024, "lr": 3.406228585071655e-06, "epoch": 16.974147414741473, "percentage": 84.87, "elapsed_time": "6:05:08", "remaining_time": "1:05:05", "throughput": 1486.34, "total_tokens": 32562752} {"current_steps": 154300, "total_steps": 181800, "loss": 0.0651, "lr": 3.4050192446175107e-06, "epoch": 16.974697469746975, "percentage": 84.87, "elapsed_time": "6:05:08", "remaining_time": "1:05:04", "throughput": 1486.33, "total_tokens": 32563744} {"current_steps": 154305, "total_steps": 181800, "loss": 0.0053, "lr": 3.403810103193944e-06, "epoch": 16.975247524752476, "percentage": 84.88, "elapsed_time": "6:05:09", "remaining_time": "1:05:03", "throughput": 1486.33, "total_tokens": 32564704} {"current_steps": 154310, "total_steps": 181800, "loss": 0.0287, "lr": 3.402601160812094e-06, "epoch": 16.975797579757977, "percentage": 84.88, "elapsed_time": "6:05:10", "remaining_time": "1:05:03", "throughput": 1486.33, "total_tokens": 32565792} {"current_steps": 154315, "total_steps": 181800, "loss": 0.062, "lr": 3.401392417483107e-06, "epoch": 16.976347634763478, "percentage": 84.88, "elapsed_time": "6:05:10", "remaining_time": "1:05:02", "throughput": 1486.34, "total_tokens": 32566848} {"current_steps": 154320, "total_steps": 181800, "loss": 0.0087, "lr": 3.400183873218124e-06, "epoch": 16.976897689768975, "percentage": 84.88, "elapsed_time": "6:05:11", "remaining_time": "1:05:01", "throughput": 1486.34, "total_tokens": 32567904} {"current_steps": 154325, "total_steps": 181800, "loss": 0.0537, "lr": 3.398975528028278e-06, "epoch": 16.977447744774476, "percentage": 84.89, "elapsed_time": "6:05:12", "remaining_time": "1:05:01", "throughput": 1486.34, "total_tokens": 32568960} {"current_steps": 154330, "total_steps": 181800, "loss": 0.0578, "lr": 3.3977673819247157e-06, "epoch": 16.977997799779978, "percentage": 84.89, "elapsed_time": "6:05:12", "remaining_time": "1:05:00", "throughput": 1486.34, "total_tokens": 32569952} {"current_steps": 154335, "total_steps": 181800, "loss": 0.1278, "lr": 3.3965594349185588e-06, "epoch": 16.97854785478548, "percentage": 84.89, "elapsed_time": "6:05:13", "remaining_time": "1:04:59", "throughput": 1486.34, "total_tokens": 32571008} {"current_steps": 154340, "total_steps": 181800, "loss": 0.1151, "lr": 3.3953516870209534e-06, "epoch": 16.97909790979098, "percentage": 84.9, "elapsed_time": "6:05:14", "remaining_time": "1:04:58", "throughput": 1486.34, "total_tokens": 32572160} {"current_steps": 154345, "total_steps": 181800, "loss": 0.0015, "lr": 3.394144138243019e-06, "epoch": 16.97964796479648, "percentage": 84.9, "elapsed_time": "6:05:14", "remaining_time": "1:04:58", "throughput": 1486.35, "total_tokens": 32573248} {"current_steps": 154350, "total_steps": 181800, "loss": 0.0016, "lr": 3.392936788595891e-06, "epoch": 16.980198019801982, "percentage": 84.9, "elapsed_time": "6:05:15", "remaining_time": "1:04:57", "throughput": 1486.35, "total_tokens": 32574304} {"current_steps": 154355, "total_steps": 181800, "loss": 0.0277, "lr": 3.3917296380907014e-06, "epoch": 16.98074807480748, "percentage": 84.9, "elapsed_time": "6:05:16", "remaining_time": "1:04:56", "throughput": 1486.35, "total_tokens": 32575392} {"current_steps": 154360, "total_steps": 181800, "loss": 0.102, "lr": 3.3905226867385648e-06, "epoch": 16.98129812981298, "percentage": 84.91, "elapsed_time": "6:05:17", "remaining_time": "1:04:56", "throughput": 1486.35, "total_tokens": 32576448} {"current_steps": 154365, "total_steps": 181800, "loss": 0.0016, "lr": 3.3893159345506187e-06, "epoch": 16.98184818481848, "percentage": 84.91, "elapsed_time": "6:05:17", "remaining_time": "1:04:55", "throughput": 1486.35, "total_tokens": 32577472} {"current_steps": 154370, "total_steps": 181800, "loss": 0.1154, "lr": 3.3881093815379712e-06, "epoch": 16.982398239823983, "percentage": 84.91, "elapsed_time": "6:05:18", "remaining_time": "1:04:54", "throughput": 1486.35, "total_tokens": 32578560} {"current_steps": 154375, "total_steps": 181800, "loss": 0.0855, "lr": 3.3869030277117493e-06, "epoch": 16.982948294829484, "percentage": 84.91, "elapsed_time": "6:05:19", "remaining_time": "1:04:53", "throughput": 1486.36, "total_tokens": 32579616} {"current_steps": 154380, "total_steps": 181800, "loss": 0.0008, "lr": 3.3856968730830745e-06, "epoch": 16.983498349834985, "percentage": 84.92, "elapsed_time": "6:05:19", "remaining_time": "1:04:53", "throughput": 1486.35, "total_tokens": 32580640} {"current_steps": 154385, "total_steps": 181800, "loss": 0.0108, "lr": 3.3844909176630577e-06, "epoch": 16.984048404840483, "percentage": 84.92, "elapsed_time": "6:05:20", "remaining_time": "1:04:52", "throughput": 1486.36, "total_tokens": 32581728} {"current_steps": 154390, "total_steps": 181800, "loss": 0.0035, "lr": 3.3832851614628206e-06, "epoch": 16.984598459845984, "percentage": 84.92, "elapsed_time": "6:05:21", "remaining_time": "1:04:51", "throughput": 1486.36, "total_tokens": 32582720} {"current_steps": 154395, "total_steps": 181800, "loss": 0.0085, "lr": 3.382079604493471e-06, "epoch": 16.985148514851485, "percentage": 84.93, "elapsed_time": "6:05:21", "remaining_time": "1:04:51", "throughput": 1486.36, "total_tokens": 32583744} {"current_steps": 154400, "total_steps": 181800, "loss": 0.033, "lr": 3.3808742467661164e-06, "epoch": 16.985698569856986, "percentage": 84.93, "elapsed_time": "6:05:22", "remaining_time": "1:04:50", "throughput": 1486.36, "total_tokens": 32584832} {"current_steps": 154405, "total_steps": 181800, "loss": 0.0029, "lr": 3.3796690882918673e-06, "epoch": 16.986248624862487, "percentage": 84.93, "elapsed_time": "6:05:23", "remaining_time": "1:04:49", "throughput": 1486.36, "total_tokens": 32585888} {"current_steps": 154410, "total_steps": 181800, "loss": 0.1249, "lr": 3.3784641290818375e-06, "epoch": 16.986798679867988, "percentage": 84.93, "elapsed_time": "6:05:23", "remaining_time": "1:04:48", "throughput": 1486.36, "total_tokens": 32586912} {"current_steps": 154415, "total_steps": 181800, "loss": 0.0049, "lr": 3.3772593691471315e-06, "epoch": 16.98734873487349, "percentage": 84.94, "elapsed_time": "6:05:24", "remaining_time": "1:04:48", "throughput": 1486.36, "total_tokens": 32587936} {"current_steps": 154420, "total_steps": 181800, "loss": 0.002, "lr": 3.3760548084988517e-06, "epoch": 16.987898789878987, "percentage": 84.94, "elapsed_time": "6:05:25", "remaining_time": "1:04:47", "throughput": 1486.36, "total_tokens": 32588960} {"current_steps": 154425, "total_steps": 181800, "loss": 0.0219, "lr": 3.3748504471480923e-06, "epoch": 16.988448844884488, "percentage": 84.94, "elapsed_time": "6:05:26", "remaining_time": "1:04:46", "throughput": 1486.36, "total_tokens": 32589984} {"current_steps": 154430, "total_steps": 181800, "loss": 0.0018, "lr": 3.373646285105958e-06, "epoch": 16.98899889988999, "percentage": 84.94, "elapsed_time": "6:05:26", "remaining_time": "1:04:46", "throughput": 1486.36, "total_tokens": 32591072} {"current_steps": 154435, "total_steps": 181800, "loss": 0.061, "lr": 3.3724423223835565e-06, "epoch": 16.98954895489549, "percentage": 84.95, "elapsed_time": "6:05:27", "remaining_time": "1:04:45", "throughput": 1486.36, "total_tokens": 32592160} {"current_steps": 154440, "total_steps": 181800, "loss": 0.0025, "lr": 3.3712385589919682e-06, "epoch": 16.99009900990099, "percentage": 84.95, "elapsed_time": "6:05:28", "remaining_time": "1:04:44", "throughput": 1486.37, "total_tokens": 32593312} {"current_steps": 154445, "total_steps": 181800, "loss": 0.0026, "lr": 3.3700349949423034e-06, "epoch": 16.990649064906492, "percentage": 84.95, "elapsed_time": "6:05:28", "remaining_time": "1:04:43", "throughput": 1486.37, "total_tokens": 32594368} {"current_steps": 154450, "total_steps": 181800, "loss": 0.0015, "lr": 3.3688316302456417e-06, "epoch": 16.99119911991199, "percentage": 84.96, "elapsed_time": "6:05:29", "remaining_time": "1:04:43", "throughput": 1486.37, "total_tokens": 32595392} {"current_steps": 154455, "total_steps": 181800, "loss": 0.0012, "lr": 3.3676284649130834e-06, "epoch": 16.99174917491749, "percentage": 84.96, "elapsed_time": "6:05:30", "remaining_time": "1:04:42", "throughput": 1486.37, "total_tokens": 32596416} {"current_steps": 154460, "total_steps": 181800, "loss": 0.0075, "lr": 3.366425498955708e-06, "epoch": 16.992299229922992, "percentage": 84.96, "elapsed_time": "6:05:30", "remaining_time": "1:04:41", "throughput": 1486.37, "total_tokens": 32597504} {"current_steps": 154465, "total_steps": 181800, "loss": 0.018, "lr": 3.3652227323846096e-06, "epoch": 16.992849284928493, "percentage": 84.96, "elapsed_time": "6:05:31", "remaining_time": "1:04:41", "throughput": 1486.38, "total_tokens": 32598560} {"current_steps": 154470, "total_steps": 181800, "loss": 0.0159, "lr": 3.364020165210874e-06, "epoch": 16.993399339933994, "percentage": 84.97, "elapsed_time": "6:05:32", "remaining_time": "1:04:40", "throughput": 1486.38, "total_tokens": 32599584} {"current_steps": 154475, "total_steps": 181800, "loss": 0.0011, "lr": 3.3628177974455803e-06, "epoch": 16.993949394939495, "percentage": 84.97, "elapsed_time": "6:05:32", "remaining_time": "1:04:39", "throughput": 1486.38, "total_tokens": 32600672} {"current_steps": 154480, "total_steps": 181800, "loss": 0.0033, "lr": 3.361615629099818e-06, "epoch": 16.994499449944996, "percentage": 84.97, "elapsed_time": "6:05:33", "remaining_time": "1:04:38", "throughput": 1486.38, "total_tokens": 32601792} {"current_steps": 154485, "total_steps": 181800, "loss": 0.0073, "lr": 3.3604136601846524e-06, "epoch": 16.995049504950494, "percentage": 84.98, "elapsed_time": "6:05:34", "remaining_time": "1:04:38", "throughput": 1486.39, "total_tokens": 32602848} {"current_steps": 154490, "total_steps": 181800, "loss": 0.0197, "lr": 3.3592118907111724e-06, "epoch": 16.995599559955995, "percentage": 84.98, "elapsed_time": "6:05:35", "remaining_time": "1:04:37", "throughput": 1486.39, "total_tokens": 32603872} {"current_steps": 154495, "total_steps": 181800, "loss": 0.0563, "lr": 3.3580103206904577e-06, "epoch": 16.996149614961496, "percentage": 84.98, "elapsed_time": "6:05:35", "remaining_time": "1:04:36", "throughput": 1486.39, "total_tokens": 32604896} {"current_steps": 154500, "total_steps": 181800, "loss": 0.0013, "lr": 3.356808950133572e-06, "epoch": 16.996699669966997, "percentage": 84.98, "elapsed_time": "6:05:36", "remaining_time": "1:04:36", "throughput": 1486.39, "total_tokens": 32606048} {"current_steps": 154505, "total_steps": 181800, "loss": 0.1071, "lr": 3.355607779051598e-06, "epoch": 16.997249724972498, "percentage": 84.99, "elapsed_time": "6:05:37", "remaining_time": "1:04:35", "throughput": 1486.39, "total_tokens": 32607104} {"current_steps": 154510, "total_steps": 181800, "loss": 0.0039, "lr": 3.354406807455601e-06, "epoch": 16.997799779978, "percentage": 84.99, "elapsed_time": "6:05:37", "remaining_time": "1:04:34", "throughput": 1486.39, "total_tokens": 32608160} {"current_steps": 154515, "total_steps": 181800, "loss": 0.0011, "lr": 3.3532060353566457e-06, "epoch": 16.998349834983497, "percentage": 84.99, "elapsed_time": "6:05:38", "remaining_time": "1:04:33", "throughput": 1486.4, "total_tokens": 32609280} {"current_steps": 154520, "total_steps": 181800, "loss": 0.0025, "lr": 3.3520054627658033e-06, "epoch": 16.998899889988998, "percentage": 84.99, "elapsed_time": "6:05:39", "remaining_time": "1:04:33", "throughput": 1486.4, "total_tokens": 32610336} {"current_steps": 154525, "total_steps": 181800, "loss": 0.0399, "lr": 3.3508050896941366e-06, "epoch": 16.9994499449945, "percentage": 85.0, "elapsed_time": "6:05:39", "remaining_time": "1:04:32", "throughput": 1486.4, "total_tokens": 32611456} {"current_steps": 154530, "total_steps": 181800, "loss": 0.1504, "lr": 3.349604916152718e-06, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "6:05:40", "remaining_time": "1:04:31", "throughput": 1486.4, "total_tokens": 32612480} {"current_steps": 154530, "total_steps": 181800, "eval_loss": 0.07643326371908188, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "6:06:17", "remaining_time": "1:04:38", "throughput": 1483.9, "total_tokens": 32612480} {"current_steps": 154535, "total_steps": 181800, "loss": 0.0292, "lr": 3.3484049421525997e-06, "epoch": 17.0005500550055, "percentage": 85.0, "elapsed_time": "6:06:20", "remaining_time": "1:04:38", "throughput": 1483.75, "total_tokens": 32613504} {"current_steps": 154540, "total_steps": 181800, "loss": 0.0025, "lr": 3.347205167704842e-06, "epoch": 17.001100110011002, "percentage": 85.01, "elapsed_time": "6:06:21", "remaining_time": "1:04:37", "throughput": 1483.75, "total_tokens": 32614592} {"current_steps": 154545, "total_steps": 181800, "loss": 0.0025, "lr": 3.3460055928205003e-06, "epoch": 17.001650165016503, "percentage": 85.01, "elapsed_time": "6:06:21", "remaining_time": "1:04:36", "throughput": 1483.75, "total_tokens": 32615680} {"current_steps": 154550, "total_steps": 181800, "loss": 0.0104, "lr": 3.3448062175106378e-06, "epoch": 17.002200220022, "percentage": 85.01, "elapsed_time": "6:06:22", "remaining_time": "1:04:35", "throughput": 1483.76, "total_tokens": 32616736} {"current_steps": 154555, "total_steps": 181800, "loss": 0.006, "lr": 3.3436070417863092e-06, "epoch": 17.002750275027502, "percentage": 85.01, "elapsed_time": "6:06:23", "remaining_time": "1:04:35", "throughput": 1483.76, "total_tokens": 32617792} {"current_steps": 154560, "total_steps": 181800, "loss": 0.0729, "lr": 3.3424080656585617e-06, "epoch": 17.003300330033003, "percentage": 85.02, "elapsed_time": "6:06:23", "remaining_time": "1:04:34", "throughput": 1483.76, "total_tokens": 32618848} {"current_steps": 154565, "total_steps": 181800, "loss": 0.0392, "lr": 3.3412092891384416e-06, "epoch": 17.003850385038504, "percentage": 85.02, "elapsed_time": "6:06:24", "remaining_time": "1:04:33", "throughput": 1483.76, "total_tokens": 32619968} {"current_steps": 154570, "total_steps": 181800, "loss": 0.0409, "lr": 3.34001071223701e-06, "epoch": 17.004400440044005, "percentage": 85.02, "elapsed_time": "6:06:25", "remaining_time": "1:04:33", "throughput": 1483.76, "total_tokens": 32621056} {"current_steps": 154575, "total_steps": 181800, "loss": 0.0217, "lr": 3.3388123349652993e-06, "epoch": 17.004950495049506, "percentage": 85.02, "elapsed_time": "6:06:26", "remaining_time": "1:04:32", "throughput": 1483.75, "total_tokens": 32622112} {"current_steps": 154580, "total_steps": 181800, "loss": 0.0998, "lr": 3.337614157334362e-06, "epoch": 17.005500550055004, "percentage": 85.03, "elapsed_time": "6:06:26", "remaining_time": "1:04:31", "throughput": 1483.75, "total_tokens": 32623136} {"current_steps": 154585, "total_steps": 181800, "loss": 0.0148, "lr": 3.336416179355245e-06, "epoch": 17.006050605060505, "percentage": 85.03, "elapsed_time": "6:06:27", "remaining_time": "1:04:30", "throughput": 1483.75, "total_tokens": 32624192} {"current_steps": 154590, "total_steps": 181800, "loss": 0.0051, "lr": 3.335218401038981e-06, "epoch": 17.006600660066006, "percentage": 85.03, "elapsed_time": "6:06:28", "remaining_time": "1:04:30", "throughput": 1483.75, "total_tokens": 32625216} {"current_steps": 154595, "total_steps": 181800, "loss": 0.075, "lr": 3.334020822396616e-06, "epoch": 17.007150715071507, "percentage": 85.04, "elapsed_time": "6:06:29", "remaining_time": "1:04:29", "throughput": 1483.75, "total_tokens": 32626304} {"current_steps": 154600, "total_steps": 181800, "loss": 0.0063, "lr": 3.3328234434391816e-06, "epoch": 17.007700770077008, "percentage": 85.04, "elapsed_time": "6:06:29", "remaining_time": "1:04:28", "throughput": 1483.75, "total_tokens": 32627328} {"current_steps": 154605, "total_steps": 181800, "loss": 0.0587, "lr": 3.3316262641777147e-06, "epoch": 17.00825082508251, "percentage": 85.04, "elapsed_time": "6:06:30", "remaining_time": "1:04:28", "throughput": 1483.75, "total_tokens": 32628416} {"current_steps": 154610, "total_steps": 181800, "loss": 0.0025, "lr": 3.3304292846232573e-06, "epoch": 17.00880088008801, "percentage": 85.04, "elapsed_time": "6:06:31", "remaining_time": "1:04:27", "throughput": 1483.75, "total_tokens": 32629472} {"current_steps": 154615, "total_steps": 181800, "loss": 0.1278, "lr": 3.3292325047868305e-06, "epoch": 17.009350935093508, "percentage": 85.05, "elapsed_time": "6:06:31", "remaining_time": "1:04:26", "throughput": 1483.75, "total_tokens": 32630496} {"current_steps": 154620, "total_steps": 181800, "loss": 0.072, "lr": 3.3280359246794733e-06, "epoch": 17.00990099009901, "percentage": 85.05, "elapsed_time": "6:06:32", "remaining_time": "1:04:25", "throughput": 1483.76, "total_tokens": 32631552} {"current_steps": 154625, "total_steps": 181800, "loss": 0.0076, "lr": 3.3268395443122104e-06, "epoch": 17.01045104510451, "percentage": 85.05, "elapsed_time": "6:06:33", "remaining_time": "1:04:25", "throughput": 1483.75, "total_tokens": 32632544} {"current_steps": 154630, "total_steps": 181800, "loss": 0.049, "lr": 3.3256433636960627e-06, "epoch": 17.01100110011001, "percentage": 85.06, "elapsed_time": "6:06:33", "remaining_time": "1:04:24", "throughput": 1483.75, "total_tokens": 32633568} {"current_steps": 154635, "total_steps": 181800, "loss": 0.0238, "lr": 3.324447382842061e-06, "epoch": 17.011551155115512, "percentage": 85.06, "elapsed_time": "6:06:34", "remaining_time": "1:04:23", "throughput": 1483.76, "total_tokens": 32634688} {"current_steps": 154640, "total_steps": 181800, "loss": 0.0215, "lr": 3.3232516017612235e-06, "epoch": 17.012101210121013, "percentage": 85.06, "elapsed_time": "6:06:35", "remaining_time": "1:04:23", "throughput": 1483.76, "total_tokens": 32635712} {"current_steps": 154645, "total_steps": 181800, "loss": 0.0721, "lr": 3.322056020464581e-06, "epoch": 17.01265126512651, "percentage": 85.06, "elapsed_time": "6:06:35", "remaining_time": "1:04:22", "throughput": 1483.76, "total_tokens": 32636736} {"current_steps": 154650, "total_steps": 181800, "loss": 0.0027, "lr": 3.3208606389631467e-06, "epoch": 17.013201320132012, "percentage": 85.07, "elapsed_time": "6:06:36", "remaining_time": "1:04:21", "throughput": 1483.76, "total_tokens": 32637792} {"current_steps": 154655, "total_steps": 181800, "loss": 0.0016, "lr": 3.3196654572679315e-06, "epoch": 17.013751375137513, "percentage": 85.07, "elapsed_time": "6:06:37", "remaining_time": "1:04:20", "throughput": 1483.76, "total_tokens": 32638816} {"current_steps": 154660, "total_steps": 181800, "loss": 0.0013, "lr": 3.318470475389962e-06, "epoch": 17.014301430143014, "percentage": 85.07, "elapsed_time": "6:06:38", "remaining_time": "1:04:20", "throughput": 1483.76, "total_tokens": 32639904} {"current_steps": 154665, "total_steps": 181800, "loss": 0.1402, "lr": 3.3172756933402356e-06, "epoch": 17.014851485148515, "percentage": 85.07, "elapsed_time": "6:06:38", "remaining_time": "1:04:19", "throughput": 1483.76, "total_tokens": 32640992} {"current_steps": 154670, "total_steps": 181800, "loss": 0.0609, "lr": 3.3160811111297876e-06, "epoch": 17.015401540154016, "percentage": 85.08, "elapsed_time": "6:06:39", "remaining_time": "1:04:18", "throughput": 1483.77, "total_tokens": 32642048} {"current_steps": 154675, "total_steps": 181800, "loss": 0.0514, "lr": 3.3148867287696115e-06, "epoch": 17.015951595159517, "percentage": 85.08, "elapsed_time": "6:06:40", "remaining_time": "1:04:18", "throughput": 1483.77, "total_tokens": 32643104} {"current_steps": 154680, "total_steps": 181800, "loss": 0.031, "lr": 3.3136925462707134e-06, "epoch": 17.016501650165015, "percentage": 85.08, "elapsed_time": "6:06:40", "remaining_time": "1:04:17", "throughput": 1483.77, "total_tokens": 32644128} {"current_steps": 154685, "total_steps": 181800, "loss": 0.031, "lr": 3.312498563644115e-06, "epoch": 17.017051705170516, "percentage": 85.09, "elapsed_time": "6:06:41", "remaining_time": "1:04:16", "throughput": 1483.77, "total_tokens": 32645184} {"current_steps": 154690, "total_steps": 181800, "loss": 0.0374, "lr": 3.311304780900801e-06, "epoch": 17.017601760176017, "percentage": 85.09, "elapsed_time": "6:06:42", "remaining_time": "1:04:15", "throughput": 1483.77, "total_tokens": 32646336} {"current_steps": 154695, "total_steps": 181800, "loss": 0.0029, "lr": 3.310111198051785e-06, "epoch": 17.01815181518152, "percentage": 85.09, "elapsed_time": "6:06:43", "remaining_time": "1:04:15", "throughput": 1483.76, "total_tokens": 32647456} {"current_steps": 154700, "total_steps": 181800, "loss": 0.1547, "lr": 3.30891781510807e-06, "epoch": 17.01870187018702, "percentage": 85.09, "elapsed_time": "6:06:43", "remaining_time": "1:04:14", "throughput": 1483.76, "total_tokens": 32648544} {"current_steps": 154705, "total_steps": 181800, "loss": 0.0042, "lr": 3.307724632080647e-06, "epoch": 17.01925192519252, "percentage": 85.1, "elapsed_time": "6:06:44", "remaining_time": "1:04:13", "throughput": 1483.76, "total_tokens": 32649568} {"current_steps": 154710, "total_steps": 181800, "loss": 0.0359, "lr": 3.3065316489805237e-06, "epoch": 17.019801980198018, "percentage": 85.1, "elapsed_time": "6:06:45", "remaining_time": "1:04:13", "throughput": 1483.77, "total_tokens": 32650656} {"current_steps": 154715, "total_steps": 181800, "loss": 0.0024, "lr": 3.305338865818683e-06, "epoch": 17.02035203520352, "percentage": 85.1, "elapsed_time": "6:06:45", "remaining_time": "1:04:12", "throughput": 1483.77, "total_tokens": 32651744} {"current_steps": 154720, "total_steps": 181800, "loss": 0.105, "lr": 3.304146282606127e-06, "epoch": 17.02090209020902, "percentage": 85.1, "elapsed_time": "6:06:46", "remaining_time": "1:04:11", "throughput": 1483.77, "total_tokens": 32652736} {"current_steps": 154725, "total_steps": 181800, "loss": 0.0724, "lr": 3.302953899353842e-06, "epoch": 17.02145214521452, "percentage": 85.11, "elapsed_time": "6:06:47", "remaining_time": "1:04:11", "throughput": 1483.77, "total_tokens": 32653728} {"current_steps": 154730, "total_steps": 181800, "loss": 0.0091, "lr": 3.3017617160728155e-06, "epoch": 17.022002200220022, "percentage": 85.11, "elapsed_time": "6:06:48", "remaining_time": "1:04:10", "throughput": 1483.77, "total_tokens": 32654752} {"current_steps": 154735, "total_steps": 181800, "loss": 0.0025, "lr": 3.3005697327740476e-06, "epoch": 17.022552255225524, "percentage": 85.11, "elapsed_time": "6:06:48", "remaining_time": "1:04:09", "throughput": 1483.77, "total_tokens": 32655744} {"current_steps": 154740, "total_steps": 181800, "loss": 0.0082, "lr": 3.29937794946851e-06, "epoch": 17.023102310231025, "percentage": 85.12, "elapsed_time": "6:06:49", "remaining_time": "1:04:08", "throughput": 1483.77, "total_tokens": 32656768} {"current_steps": 154745, "total_steps": 181800, "loss": 0.0506, "lr": 3.2981863661671996e-06, "epoch": 17.023652365236522, "percentage": 85.12, "elapsed_time": "6:06:50", "remaining_time": "1:04:08", "throughput": 1483.77, "total_tokens": 32657856} {"current_steps": 154750, "total_steps": 181800, "loss": 0.0503, "lr": 3.2969949828810855e-06, "epoch": 17.024202420242023, "percentage": 85.12, "elapsed_time": "6:06:50", "remaining_time": "1:04:07", "throughput": 1483.77, "total_tokens": 32658944} {"current_steps": 154755, "total_steps": 181800, "loss": 0.0024, "lr": 3.2958037996211527e-06, "epoch": 17.024752475247524, "percentage": 85.12, "elapsed_time": "6:06:51", "remaining_time": "1:04:06", "throughput": 1483.77, "total_tokens": 32660000} {"current_steps": 154760, "total_steps": 181800, "loss": 0.0617, "lr": 3.29461281639839e-06, "epoch": 17.025302530253025, "percentage": 85.13, "elapsed_time": "6:06:52", "remaining_time": "1:04:06", "throughput": 1483.78, "total_tokens": 32661056} {"current_steps": 154765, "total_steps": 181800, "loss": 0.0052, "lr": 3.2934220332237584e-06, "epoch": 17.025852585258527, "percentage": 85.13, "elapsed_time": "6:06:52", "remaining_time": "1:04:05", "throughput": 1483.78, "total_tokens": 32662144} {"current_steps": 154770, "total_steps": 181800, "loss": 0.0026, "lr": 3.292231450108246e-06, "epoch": 17.026402640264028, "percentage": 85.13, "elapsed_time": "6:06:53", "remaining_time": "1:04:04", "throughput": 1483.78, "total_tokens": 32663200} {"current_steps": 154775, "total_steps": 181800, "loss": 0.0017, "lr": 3.2910410670628222e-06, "epoch": 17.02695269526953, "percentage": 85.13, "elapsed_time": "6:06:54", "remaining_time": "1:04:03", "throughput": 1483.78, "total_tokens": 32664224} {"current_steps": 154780, "total_steps": 181800, "loss": 0.0041, "lr": 3.2898508840984415e-06, "epoch": 17.027502750275026, "percentage": 85.14, "elapsed_time": "6:06:54", "remaining_time": "1:04:03", "throughput": 1483.78, "total_tokens": 32665312} {"current_steps": 154785, "total_steps": 181800, "loss": 0.126, "lr": 3.288660901226101e-06, "epoch": 17.028052805280527, "percentage": 85.14, "elapsed_time": "6:06:55", "remaining_time": "1:04:02", "throughput": 1483.78, "total_tokens": 32666368} {"current_steps": 154790, "total_steps": 181800, "loss": 0.0448, "lr": 3.2874711184567476e-06, "epoch": 17.02860286028603, "percentage": 85.14, "elapsed_time": "6:06:56", "remaining_time": "1:04:01", "throughput": 1483.78, "total_tokens": 32667392} {"current_steps": 154795, "total_steps": 181800, "loss": 0.0016, "lr": 3.286281535801361e-06, "epoch": 17.02915291529153, "percentage": 85.15, "elapsed_time": "6:06:56", "remaining_time": "1:04:01", "throughput": 1483.78, "total_tokens": 32668416} {"current_steps": 154800, "total_steps": 181800, "loss": 0.0034, "lr": 3.2850921532708967e-06, "epoch": 17.02970297029703, "percentage": 85.15, "elapsed_time": "6:06:57", "remaining_time": "1:04:00", "throughput": 1483.78, "total_tokens": 32669472} {"current_steps": 154805, "total_steps": 181800, "loss": 0.0034, "lr": 3.2839029708763123e-06, "epoch": 17.03025302530253, "percentage": 85.15, "elapsed_time": "6:06:58", "remaining_time": "1:03:59", "throughput": 1483.78, "total_tokens": 32670464} {"current_steps": 154810, "total_steps": 181800, "loss": 0.097, "lr": 3.2827139886285775e-06, "epoch": 17.03080308030803, "percentage": 85.15, "elapsed_time": "6:06:59", "remaining_time": "1:03:58", "throughput": 1483.78, "total_tokens": 32671520} {"current_steps": 154815, "total_steps": 181800, "loss": 0.0022, "lr": 3.2815252065386494e-06, "epoch": 17.03135313531353, "percentage": 85.16, "elapsed_time": "6:06:59", "remaining_time": "1:03:58", "throughput": 1483.78, "total_tokens": 32672512} {"current_steps": 154820, "total_steps": 181800, "loss": 0.0491, "lr": 3.2803366246174777e-06, "epoch": 17.03190319031903, "percentage": 85.16, "elapsed_time": "6:07:00", "remaining_time": "1:03:57", "throughput": 1483.78, "total_tokens": 32673536} {"current_steps": 154825, "total_steps": 181800, "loss": 0.0039, "lr": 3.279148242876026e-06, "epoch": 17.032453245324533, "percentage": 85.16, "elapsed_time": "6:07:01", "remaining_time": "1:03:56", "throughput": 1483.78, "total_tokens": 32674560} {"current_steps": 154830, "total_steps": 181800, "loss": 0.0073, "lr": 3.2779600613252357e-06, "epoch": 17.033003300330034, "percentage": 85.17, "elapsed_time": "6:07:01", "remaining_time": "1:03:56", "throughput": 1483.79, "total_tokens": 32675648} {"current_steps": 154835, "total_steps": 181800, "loss": 0.1003, "lr": 3.2767720799760705e-06, "epoch": 17.033553355335535, "percentage": 85.17, "elapsed_time": "6:07:02", "remaining_time": "1:03:55", "throughput": 1483.79, "total_tokens": 32676672} {"current_steps": 154840, "total_steps": 181800, "loss": 0.0012, "lr": 3.275584298839468e-06, "epoch": 17.034103410341036, "percentage": 85.17, "elapsed_time": "6:07:03", "remaining_time": "1:03:54", "throughput": 1483.79, "total_tokens": 32677792} {"current_steps": 154845, "total_steps": 181800, "loss": 0.0008, "lr": 3.274396717926381e-06, "epoch": 17.034653465346533, "percentage": 85.17, "elapsed_time": "6:07:03", "remaining_time": "1:03:53", "throughput": 1483.79, "total_tokens": 32678912} {"current_steps": 154850, "total_steps": 181800, "loss": 0.0857, "lr": 3.2732093372477594e-06, "epoch": 17.035203520352034, "percentage": 85.18, "elapsed_time": "6:07:04", "remaining_time": "1:03:53", "throughput": 1483.8, "total_tokens": 32680000} {"current_steps": 154855, "total_steps": 181800, "loss": 0.0054, "lr": 3.2720221568145387e-06, "epoch": 17.035753575357536, "percentage": 85.18, "elapsed_time": "6:07:05", "remaining_time": "1:03:52", "throughput": 1483.8, "total_tokens": 32681088} {"current_steps": 154860, "total_steps": 181800, "loss": 0.0247, "lr": 3.2708351766376657e-06, "epoch": 17.036303630363037, "percentage": 85.18, "elapsed_time": "6:07:05", "remaining_time": "1:03:51", "throughput": 1483.8, "total_tokens": 32682112} {"current_steps": 154865, "total_steps": 181800, "loss": 0.0433, "lr": 3.2696483967280754e-06, "epoch": 17.036853685368538, "percentage": 85.18, "elapsed_time": "6:07:06", "remaining_time": "1:03:50", "throughput": 1483.8, "total_tokens": 32683072} {"current_steps": 154870, "total_steps": 181800, "loss": 0.0342, "lr": 3.2684618170967075e-06, "epoch": 17.03740374037404, "percentage": 85.19, "elapsed_time": "6:07:07", "remaining_time": "1:03:50", "throughput": 1483.8, "total_tokens": 32684128} {"current_steps": 154875, "total_steps": 181800, "loss": 0.002, "lr": 3.267275437754505e-06, "epoch": 17.037953795379536, "percentage": 85.19, "elapsed_time": "6:07:08", "remaining_time": "1:03:49", "throughput": 1483.8, "total_tokens": 32685120} {"current_steps": 154880, "total_steps": 181800, "loss": 0.0638, "lr": 3.2660892587123904e-06, "epoch": 17.038503850385037, "percentage": 85.19, "elapsed_time": "6:07:08", "remaining_time": "1:03:48", "throughput": 1483.8, "total_tokens": 32686208} {"current_steps": 154885, "total_steps": 181800, "loss": 0.0034, "lr": 3.264903279981307e-06, "epoch": 17.03905390539054, "percentage": 85.2, "elapsed_time": "6:07:09", "remaining_time": "1:03:48", "throughput": 1483.81, "total_tokens": 32687392} {"current_steps": 154890, "total_steps": 181800, "loss": 0.0022, "lr": 3.2637175015721805e-06, "epoch": 17.03960396039604, "percentage": 85.2, "elapsed_time": "6:07:10", "remaining_time": "1:03:47", "throughput": 1483.81, "total_tokens": 32688416} {"current_steps": 154895, "total_steps": 181800, "loss": 0.0132, "lr": 3.2625319234959373e-06, "epoch": 17.04015401540154, "percentage": 85.2, "elapsed_time": "6:07:10", "remaining_time": "1:03:46", "throughput": 1483.81, "total_tokens": 32689440} {"current_steps": 154900, "total_steps": 181800, "loss": 0.001, "lr": 3.261346545763502e-06, "epoch": 17.040704070407042, "percentage": 85.2, "elapsed_time": "6:07:11", "remaining_time": "1:03:45", "throughput": 1483.81, "total_tokens": 32690496} {"current_steps": 154905, "total_steps": 181800, "loss": 0.0252, "lr": 3.2601613683858085e-06, "epoch": 17.041254125412543, "percentage": 85.21, "elapsed_time": "6:07:12", "remaining_time": "1:03:45", "throughput": 1483.81, "total_tokens": 32691584} {"current_steps": 154910, "total_steps": 181800, "loss": 0.0052, "lr": 3.2589763913737805e-06, "epoch": 17.04180418041804, "percentage": 85.21, "elapsed_time": "6:07:12", "remaining_time": "1:03:44", "throughput": 1483.81, "total_tokens": 32692640} {"current_steps": 154915, "total_steps": 181800, "loss": 0.004, "lr": 3.2577916147383343e-06, "epoch": 17.04235423542354, "percentage": 85.21, "elapsed_time": "6:07:13", "remaining_time": "1:03:43", "throughput": 1483.81, "total_tokens": 32693696} {"current_steps": 154920, "total_steps": 181800, "loss": 0.0016, "lr": 3.2566070384903836e-06, "epoch": 17.042904290429043, "percentage": 85.21, "elapsed_time": "6:07:14", "remaining_time": "1:03:43", "throughput": 1483.82, "total_tokens": 32694784} {"current_steps": 154925, "total_steps": 181800, "loss": 0.0016, "lr": 3.255422662640853e-06, "epoch": 17.043454345434544, "percentage": 85.22, "elapsed_time": "6:07:14", "remaining_time": "1:03:42", "throughput": 1483.82, "total_tokens": 32695776} {"current_steps": 154930, "total_steps": 181800, "loss": 0.0026, "lr": 3.254238487200656e-06, "epoch": 17.044004400440045, "percentage": 85.22, "elapsed_time": "6:07:15", "remaining_time": "1:03:41", "throughput": 1483.82, "total_tokens": 32696864} {"current_steps": 154935, "total_steps": 181800, "loss": 0.0017, "lr": 3.2530545121807145e-06, "epoch": 17.044554455445546, "percentage": 85.22, "elapsed_time": "6:07:16", "remaining_time": "1:03:40", "throughput": 1483.82, "total_tokens": 32697856} {"current_steps": 154940, "total_steps": 181800, "loss": 0.0013, "lr": 3.251870737591936e-06, "epoch": 17.045104510451043, "percentage": 85.23, "elapsed_time": "6:07:16", "remaining_time": "1:03:40", "throughput": 1483.82, "total_tokens": 32698944} {"current_steps": 154945, "total_steps": 181800, "loss": 0.0365, "lr": 3.2506871634452236e-06, "epoch": 17.045654565456545, "percentage": 85.23, "elapsed_time": "6:07:17", "remaining_time": "1:03:39", "throughput": 1483.82, "total_tokens": 32700000} {"current_steps": 154950, "total_steps": 181800, "loss": 0.0015, "lr": 3.2495037897514957e-06, "epoch": 17.046204620462046, "percentage": 85.23, "elapsed_time": "6:07:18", "remaining_time": "1:03:38", "throughput": 1483.82, "total_tokens": 32701024} {"current_steps": 154955, "total_steps": 181800, "loss": 0.0041, "lr": 3.2483206165216466e-06, "epoch": 17.046754675467547, "percentage": 85.23, "elapsed_time": "6:07:19", "remaining_time": "1:03:38", "throughput": 1483.82, "total_tokens": 32702048} {"current_steps": 154960, "total_steps": 181800, "loss": 0.0023, "lr": 3.247137643766593e-06, "epoch": 17.047304730473048, "percentage": 85.24, "elapsed_time": "6:07:19", "remaining_time": "1:03:37", "throughput": 1483.83, "total_tokens": 32703200} {"current_steps": 154965, "total_steps": 181800, "loss": 0.0104, "lr": 3.2459548714972365e-06, "epoch": 17.04785478547855, "percentage": 85.24, "elapsed_time": "6:07:20", "remaining_time": "1:03:36", "throughput": 1483.83, "total_tokens": 32704224} {"current_steps": 154970, "total_steps": 181800, "loss": 0.0031, "lr": 3.2447722997244718e-06, "epoch": 17.04840484048405, "percentage": 85.24, "elapsed_time": "6:07:21", "remaining_time": "1:03:35", "throughput": 1483.83, "total_tokens": 32705312} {"current_steps": 154975, "total_steps": 181800, "loss": 0.0553, "lr": 3.2435899284592063e-06, "epoch": 17.048954895489548, "percentage": 85.24, "elapsed_time": "6:07:21", "remaining_time": "1:03:35", "throughput": 1483.83, "total_tokens": 32706336} {"current_steps": 154980, "total_steps": 181800, "loss": 0.0038, "lr": 3.2424077577123265e-06, "epoch": 17.04950495049505, "percentage": 85.25, "elapsed_time": "6:07:22", "remaining_time": "1:03:34", "throughput": 1483.83, "total_tokens": 32707392} {"current_steps": 154985, "total_steps": 181800, "loss": 0.0045, "lr": 3.2412257874947367e-06, "epoch": 17.05005500550055, "percentage": 85.25, "elapsed_time": "6:07:23", "remaining_time": "1:03:33", "throughput": 1483.83, "total_tokens": 32708448} {"current_steps": 154990, "total_steps": 181800, "loss": 0.01, "lr": 3.2400440178173315e-06, "epoch": 17.05060506050605, "percentage": 85.25, "elapsed_time": "6:07:23", "remaining_time": "1:03:33", "throughput": 1483.83, "total_tokens": 32709472} {"current_steps": 154995, "total_steps": 181800, "loss": 0.003, "lr": 3.2388624486909936e-06, "epoch": 17.051155115511552, "percentage": 85.26, "elapsed_time": "6:07:24", "remaining_time": "1:03:32", "throughput": 1483.84, "total_tokens": 32710592} {"current_steps": 155000, "total_steps": 181800, "loss": 0.0014, "lr": 3.237681080126623e-06, "epoch": 17.051705170517053, "percentage": 85.26, "elapsed_time": "6:07:25", "remaining_time": "1:03:31", "throughput": 1483.84, "total_tokens": 32711616} {"current_steps": 155005, "total_steps": 181800, "loss": 0.0599, "lr": 3.2364999121351047e-06, "epoch": 17.05225522552255, "percentage": 85.26, "elapsed_time": "6:07:25", "remaining_time": "1:03:30", "throughput": 1483.83, "total_tokens": 32712576} {"current_steps": 155010, "total_steps": 181800, "loss": 0.0025, "lr": 3.235318944727317e-06, "epoch": 17.05280528052805, "percentage": 85.26, "elapsed_time": "6:07:26", "remaining_time": "1:03:30", "throughput": 1483.84, "total_tokens": 32713664} {"current_steps": 155015, "total_steps": 181800, "loss": 0.0026, "lr": 3.2341381779141535e-06, "epoch": 17.053355335533553, "percentage": 85.27, "elapsed_time": "6:07:27", "remaining_time": "1:03:29", "throughput": 1483.84, "total_tokens": 32714752} {"current_steps": 155020, "total_steps": 181800, "loss": 0.003, "lr": 3.2329576117064914e-06, "epoch": 17.053905390539054, "percentage": 85.27, "elapsed_time": "6:07:28", "remaining_time": "1:03:28", "throughput": 1483.84, "total_tokens": 32715808} {"current_steps": 155025, "total_steps": 181800, "loss": 0.002, "lr": 3.2317772461152197e-06, "epoch": 17.054455445544555, "percentage": 85.27, "elapsed_time": "6:07:28", "remaining_time": "1:03:28", "throughput": 1483.84, "total_tokens": 32716864} {"current_steps": 155030, "total_steps": 181800, "loss": 0.0313, "lr": 3.2305970811512127e-06, "epoch": 17.055005500550056, "percentage": 85.28, "elapsed_time": "6:07:29", "remaining_time": "1:03:27", "throughput": 1483.84, "total_tokens": 32717920} {"current_steps": 155035, "total_steps": 181800, "loss": 0.0658, "lr": 3.2294171168253394e-06, "epoch": 17.055555555555557, "percentage": 85.28, "elapsed_time": "6:07:30", "remaining_time": "1:03:26", "throughput": 1483.85, "total_tokens": 32719008} {"current_steps": 155040, "total_steps": 181800, "loss": 0.0012, "lr": 3.2282373531484833e-06, "epoch": 17.056105610561055, "percentage": 85.28, "elapsed_time": "6:07:30", "remaining_time": "1:03:25", "throughput": 1483.85, "total_tokens": 32720128} {"current_steps": 155045, "total_steps": 181800, "loss": 0.004, "lr": 3.2270577901315184e-06, "epoch": 17.056655665566556, "percentage": 85.28, "elapsed_time": "6:07:31", "remaining_time": "1:03:25", "throughput": 1483.85, "total_tokens": 32721216} {"current_steps": 155050, "total_steps": 181800, "loss": 0.109, "lr": 3.225878427785317e-06, "epoch": 17.057205720572057, "percentage": 85.29, "elapsed_time": "6:07:32", "remaining_time": "1:03:24", "throughput": 1483.85, "total_tokens": 32722240} {"current_steps": 155055, "total_steps": 181800, "loss": 0.0127, "lr": 3.2246992661207453e-06, "epoch": 17.057755775577558, "percentage": 85.29, "elapsed_time": "6:07:32", "remaining_time": "1:03:23", "throughput": 1483.86, "total_tokens": 32723296} {"current_steps": 155060, "total_steps": 181800, "loss": 0.2031, "lr": 3.2235203051486695e-06, "epoch": 17.05830583058306, "percentage": 85.29, "elapsed_time": "6:07:33", "remaining_time": "1:03:23", "throughput": 1483.86, "total_tokens": 32724352} {"current_steps": 155065, "total_steps": 181800, "loss": 0.0892, "lr": 3.2223415448799613e-06, "epoch": 17.05885588558856, "percentage": 85.29, "elapsed_time": "6:07:34", "remaining_time": "1:03:22", "throughput": 1483.86, "total_tokens": 32725376} {"current_steps": 155070, "total_steps": 181800, "loss": 0.0418, "lr": 3.2211629853254737e-06, "epoch": 17.059405940594058, "percentage": 85.3, "elapsed_time": "6:07:34", "remaining_time": "1:03:21", "throughput": 1483.86, "total_tokens": 32726496} {"current_steps": 155075, "total_steps": 181800, "loss": 0.0108, "lr": 3.219984626496078e-06, "epoch": 17.05995599559956, "percentage": 85.3, "elapsed_time": "6:07:35", "remaining_time": "1:03:20", "throughput": 1483.86, "total_tokens": 32727584} {"current_steps": 155080, "total_steps": 181800, "loss": 0.0458, "lr": 3.218806468402641e-06, "epoch": 17.06050605060506, "percentage": 85.3, "elapsed_time": "6:07:36", "remaining_time": "1:03:20", "throughput": 1483.86, "total_tokens": 32728608} {"current_steps": 155085, "total_steps": 181800, "loss": 0.0012, "lr": 3.2176285110560034e-06, "epoch": 17.06105610561056, "percentage": 85.31, "elapsed_time": "6:07:37", "remaining_time": "1:03:19", "throughput": 1483.86, "total_tokens": 32729632} {"current_steps": 155090, "total_steps": 181800, "loss": 0.0083, "lr": 3.2164507544670403e-06, "epoch": 17.061606160616062, "percentage": 85.31, "elapsed_time": "6:07:37", "remaining_time": "1:03:18", "throughput": 1483.87, "total_tokens": 32730720} {"current_steps": 155095, "total_steps": 181800, "loss": 0.0648, "lr": 3.21527319864659e-06, "epoch": 17.062156215621563, "percentage": 85.31, "elapsed_time": "6:07:38", "remaining_time": "1:03:18", "throughput": 1483.87, "total_tokens": 32731776} {"current_steps": 155100, "total_steps": 181800, "loss": 0.0009, "lr": 3.2140958436055135e-06, "epoch": 17.062706270627064, "percentage": 85.31, "elapsed_time": "6:07:39", "remaining_time": "1:03:17", "throughput": 1483.87, "total_tokens": 32732864} {"current_steps": 155105, "total_steps": 181800, "loss": 0.0074, "lr": 3.2129186893546685e-06, "epoch": 17.063256325632562, "percentage": 85.32, "elapsed_time": "6:07:39", "remaining_time": "1:03:16", "throughput": 1483.87, "total_tokens": 32733952} {"current_steps": 155110, "total_steps": 181800, "loss": 0.0028, "lr": 3.211741735904891e-06, "epoch": 17.063806380638063, "percentage": 85.32, "elapsed_time": "6:07:40", "remaining_time": "1:03:15", "throughput": 1483.88, "total_tokens": 32735008} {"current_steps": 155115, "total_steps": 181800, "loss": 0.0194, "lr": 3.210564983267042e-06, "epoch": 17.064356435643564, "percentage": 85.32, "elapsed_time": "6:07:41", "remaining_time": "1:03:15", "throughput": 1483.88, "total_tokens": 32736064} {"current_steps": 155120, "total_steps": 181800, "loss": 0.0031, "lr": 3.209388431451954e-06, "epoch": 17.064906490649065, "percentage": 85.32, "elapsed_time": "6:07:41", "remaining_time": "1:03:14", "throughput": 1483.88, "total_tokens": 32737120} {"current_steps": 155125, "total_steps": 181800, "loss": 0.0172, "lr": 3.2082120804704796e-06, "epoch": 17.065456545654566, "percentage": 85.33, "elapsed_time": "6:07:42", "remaining_time": "1:03:13", "throughput": 1483.88, "total_tokens": 32738208} {"current_steps": 155130, "total_steps": 181800, "loss": 0.0036, "lr": 3.2070359303334545e-06, "epoch": 17.066006600660067, "percentage": 85.33, "elapsed_time": "6:07:43", "remaining_time": "1:03:13", "throughput": 1483.88, "total_tokens": 32739264} {"current_steps": 155135, "total_steps": 181800, "loss": 0.0899, "lr": 3.2058599810517233e-06, "epoch": 17.066556655665565, "percentage": 85.33, "elapsed_time": "6:07:43", "remaining_time": "1:03:12", "throughput": 1483.88, "total_tokens": 32740256} {"current_steps": 155140, "total_steps": 181800, "loss": 0.2116, "lr": 3.2046842326361264e-06, "epoch": 17.067106710671066, "percentage": 85.34, "elapsed_time": "6:07:44", "remaining_time": "1:03:11", "throughput": 1483.88, "total_tokens": 32741344} {"current_steps": 155145, "total_steps": 181800, "loss": 0.0175, "lr": 3.2035086850974892e-06, "epoch": 17.067656765676567, "percentage": 85.34, "elapsed_time": "6:07:45", "remaining_time": "1:03:10", "throughput": 1483.89, "total_tokens": 32742464} {"current_steps": 155150, "total_steps": 181800, "loss": 0.0014, "lr": 3.2023333384466615e-06, "epoch": 17.068206820682068, "percentage": 85.34, "elapsed_time": "6:07:45", "remaining_time": "1:03:10", "throughput": 1483.89, "total_tokens": 32743488} {"current_steps": 155155, "total_steps": 181800, "loss": 0.0044, "lr": 3.201158192694462e-06, "epoch": 17.06875687568757, "percentage": 85.34, "elapsed_time": "6:07:46", "remaining_time": "1:03:09", "throughput": 1483.89, "total_tokens": 32744544} {"current_steps": 155160, "total_steps": 181800, "loss": 0.014, "lr": 3.199983247851726e-06, "epoch": 17.06930693069307, "percentage": 85.35, "elapsed_time": "6:07:47", "remaining_time": "1:03:08", "throughput": 1483.89, "total_tokens": 32745632} {"current_steps": 155165, "total_steps": 181800, "loss": 0.0431, "lr": 3.198808503929293e-06, "epoch": 17.06985698569857, "percentage": 85.35, "elapsed_time": "6:07:48", "remaining_time": "1:03:08", "throughput": 1483.89, "total_tokens": 32746656} {"current_steps": 155170, "total_steps": 181800, "loss": 0.0055, "lr": 3.197633960937971e-06, "epoch": 17.07040704070407, "percentage": 85.35, "elapsed_time": "6:07:48", "remaining_time": "1:03:07", "throughput": 1483.89, "total_tokens": 32747712} {"current_steps": 155175, "total_steps": 181800, "loss": 0.0019, "lr": 3.1964596188886033e-06, "epoch": 17.07095709570957, "percentage": 85.35, "elapsed_time": "6:07:49", "remaining_time": "1:03:06", "throughput": 1483.9, "total_tokens": 32748768} {"current_steps": 155180, "total_steps": 181800, "loss": 0.0239, "lr": 3.1952854777920036e-06, "epoch": 17.07150715071507, "percentage": 85.36, "elapsed_time": "6:07:50", "remaining_time": "1:03:05", "throughput": 1483.89, "total_tokens": 32749760} {"current_steps": 155185, "total_steps": 181800, "loss": 0.0054, "lr": 3.1941115376589894e-06, "epoch": 17.072057205720572, "percentage": 85.36, "elapsed_time": "6:07:50", "remaining_time": "1:03:05", "throughput": 1483.9, "total_tokens": 32750848} {"current_steps": 155190, "total_steps": 181800, "loss": 0.0029, "lr": 3.1929377985003865e-06, "epoch": 17.072607260726073, "percentage": 85.36, "elapsed_time": "6:07:51", "remaining_time": "1:03:04", "throughput": 1483.9, "total_tokens": 32751904} {"current_steps": 155195, "total_steps": 181800, "loss": 0.0351, "lr": 3.1917642603270153e-06, "epoch": 17.073157315731574, "percentage": 85.37, "elapsed_time": "6:07:52", "remaining_time": "1:03:03", "throughput": 1483.9, "total_tokens": 32752896} {"current_steps": 155200, "total_steps": 181800, "loss": 0.0296, "lr": 3.1905909231496832e-06, "epoch": 17.073707370737075, "percentage": 85.37, "elapsed_time": "6:07:52", "remaining_time": "1:03:03", "throughput": 1483.9, "total_tokens": 32753984} {"current_steps": 155205, "total_steps": 181800, "loss": 0.03, "lr": 3.189417786979218e-06, "epoch": 17.074257425742573, "percentage": 85.37, "elapsed_time": "6:07:53", "remaining_time": "1:03:02", "throughput": 1483.9, "total_tokens": 32755040} {"current_steps": 155210, "total_steps": 181800, "loss": 0.0058, "lr": 3.1882448518264136e-06, "epoch": 17.074807480748074, "percentage": 85.37, "elapsed_time": "6:07:54", "remaining_time": "1:03:01", "throughput": 1483.9, "total_tokens": 32756096} {"current_steps": 155215, "total_steps": 181800, "loss": 0.0081, "lr": 3.1870721177020945e-06, "epoch": 17.075357535753575, "percentage": 85.38, "elapsed_time": "6:07:54", "remaining_time": "1:03:00", "throughput": 1483.9, "total_tokens": 32757088} {"current_steps": 155220, "total_steps": 181800, "loss": 0.0208, "lr": 3.1858995846170665e-06, "epoch": 17.075907590759076, "percentage": 85.38, "elapsed_time": "6:07:55", "remaining_time": "1:03:00", "throughput": 1483.9, "total_tokens": 32758144} {"current_steps": 155225, "total_steps": 181800, "loss": 0.0226, "lr": 3.1847272525821314e-06, "epoch": 17.076457645764577, "percentage": 85.38, "elapsed_time": "6:07:56", "remaining_time": "1:02:59", "throughput": 1483.9, "total_tokens": 32759168} {"current_steps": 155230, "total_steps": 181800, "loss": 0.0539, "lr": 3.1835551216081007e-06, "epoch": 17.07700770077008, "percentage": 85.39, "elapsed_time": "6:07:57", "remaining_time": "1:02:58", "throughput": 1483.91, "total_tokens": 32760224} {"current_steps": 155235, "total_steps": 181800, "loss": 0.0143, "lr": 3.1823831917057706e-06, "epoch": 17.077557755775576, "percentage": 85.39, "elapsed_time": "6:07:57", "remaining_time": "1:02:58", "throughput": 1483.91, "total_tokens": 32761248} {"current_steps": 155240, "total_steps": 181800, "loss": 0.0381, "lr": 3.1812114628859495e-06, "epoch": 17.078107810781077, "percentage": 85.39, "elapsed_time": "6:07:58", "remaining_time": "1:02:57", "throughput": 1483.91, "total_tokens": 32762272} {"current_steps": 155245, "total_steps": 181800, "loss": 0.004, "lr": 3.180039935159429e-06, "epoch": 17.078657865786578, "percentage": 85.39, "elapsed_time": "6:07:59", "remaining_time": "1:02:56", "throughput": 1483.91, "total_tokens": 32763328} {"current_steps": 155250, "total_steps": 181800, "loss": 0.0088, "lr": 3.1788686085370085e-06, "epoch": 17.07920792079208, "percentage": 85.4, "elapsed_time": "6:07:59", "remaining_time": "1:02:55", "throughput": 1483.91, "total_tokens": 32764384} {"current_steps": 155255, "total_steps": 181800, "loss": 0.003, "lr": 3.1776974830294903e-06, "epoch": 17.07975797579758, "percentage": 85.4, "elapsed_time": "6:08:00", "remaining_time": "1:02:55", "throughput": 1483.91, "total_tokens": 32765440} {"current_steps": 155260, "total_steps": 181800, "loss": 0.1193, "lr": 3.176526558647658e-06, "epoch": 17.08030803080308, "percentage": 85.4, "elapsed_time": "6:08:01", "remaining_time": "1:02:54", "throughput": 1483.91, "total_tokens": 32766432} {"current_steps": 155265, "total_steps": 181800, "loss": 0.0148, "lr": 3.175355835402316e-06, "epoch": 17.080858085808583, "percentage": 85.4, "elapsed_time": "6:08:01", "remaining_time": "1:02:53", "throughput": 1483.91, "total_tokens": 32767488} {"current_steps": 155270, "total_steps": 181800, "loss": 0.0195, "lr": 3.17418531330424e-06, "epoch": 17.08140814081408, "percentage": 85.41, "elapsed_time": "6:08:02", "remaining_time": "1:02:53", "throughput": 1483.91, "total_tokens": 32768448} {"current_steps": 155275, "total_steps": 181800, "loss": 0.0092, "lr": 3.1730149923642234e-06, "epoch": 17.08195819581958, "percentage": 85.41, "elapsed_time": "6:08:03", "remaining_time": "1:02:52", "throughput": 1483.91, "total_tokens": 32769472} {"current_steps": 155280, "total_steps": 181800, "loss": 0.0061, "lr": 3.1718448725930607e-06, "epoch": 17.082508250825082, "percentage": 85.41, "elapsed_time": "6:08:03", "remaining_time": "1:02:51", "throughput": 1483.91, "total_tokens": 32770528} {"current_steps": 155285, "total_steps": 181800, "loss": 0.0051, "lr": 3.1706749540015234e-06, "epoch": 17.083058305830583, "percentage": 85.42, "elapsed_time": "6:08:04", "remaining_time": "1:02:50", "throughput": 1483.91, "total_tokens": 32771584} {"current_steps": 155290, "total_steps": 181800, "loss": 0.0109, "lr": 3.1695052366004064e-06, "epoch": 17.083608360836084, "percentage": 85.42, "elapsed_time": "6:08:05", "remaining_time": "1:02:50", "throughput": 1483.91, "total_tokens": 32772672} {"current_steps": 155295, "total_steps": 181800, "loss": 0.0019, "lr": 3.1683357204004837e-06, "epoch": 17.084158415841586, "percentage": 85.42, "elapsed_time": "6:08:05", "remaining_time": "1:02:49", "throughput": 1483.91, "total_tokens": 32773728} {"current_steps": 155300, "total_steps": 181800, "loss": 0.0025, "lr": 3.1671664054125304e-06, "epoch": 17.084708470847083, "percentage": 85.42, "elapsed_time": "6:08:06", "remaining_time": "1:02:48", "throughput": 1483.92, "total_tokens": 32774752} {"current_steps": 155305, "total_steps": 181800, "loss": 0.003, "lr": 3.1659972916473295e-06, "epoch": 17.085258525852584, "percentage": 85.43, "elapsed_time": "6:08:07", "remaining_time": "1:02:48", "throughput": 1483.92, "total_tokens": 32775840} {"current_steps": 155310, "total_steps": 181800, "loss": 0.0711, "lr": 3.164828379115653e-06, "epoch": 17.085808580858085, "percentage": 85.43, "elapsed_time": "6:08:08", "remaining_time": "1:02:47", "throughput": 1483.92, "total_tokens": 32776896} {"current_steps": 155315, "total_steps": 181800, "loss": 0.0114, "lr": 3.163659667828281e-06, "epoch": 17.086358635863586, "percentage": 85.43, "elapsed_time": "6:08:08", "remaining_time": "1:02:46", "throughput": 1483.92, "total_tokens": 32777984} {"current_steps": 155320, "total_steps": 181800, "loss": 0.009, "lr": 3.162491157795977e-06, "epoch": 17.086908690869087, "percentage": 85.43, "elapsed_time": "6:08:09", "remaining_time": "1:02:45", "throughput": 1483.93, "total_tokens": 32779072} {"current_steps": 155325, "total_steps": 181800, "loss": 0.0012, "lr": 3.161322849029513e-06, "epoch": 17.08745874587459, "percentage": 85.44, "elapsed_time": "6:08:10", "remaining_time": "1:02:45", "throughput": 1483.93, "total_tokens": 32780160} {"current_steps": 155330, "total_steps": 181800, "loss": 0.1106, "lr": 3.160154741539653e-06, "epoch": 17.08800880088009, "percentage": 85.44, "elapsed_time": "6:08:10", "remaining_time": "1:02:44", "throughput": 1483.93, "total_tokens": 32781120} {"current_steps": 155335, "total_steps": 181800, "loss": 0.0066, "lr": 3.1589868353371686e-06, "epoch": 17.088558855885587, "percentage": 85.44, "elapsed_time": "6:08:11", "remaining_time": "1:02:43", "throughput": 1483.93, "total_tokens": 32782208} {"current_steps": 155340, "total_steps": 181800, "loss": 0.0252, "lr": 3.157819130432829e-06, "epoch": 17.08910891089109, "percentage": 85.45, "elapsed_time": "6:08:12", "remaining_time": "1:02:43", "throughput": 1483.93, "total_tokens": 32783200} {"current_steps": 155345, "total_steps": 181800, "loss": 0.006, "lr": 3.1566516268373868e-06, "epoch": 17.08965896589659, "percentage": 85.45, "elapsed_time": "6:08:12", "remaining_time": "1:02:42", "throughput": 1483.93, "total_tokens": 32784288} {"current_steps": 155350, "total_steps": 181800, "loss": 0.0887, "lr": 3.1554843245616027e-06, "epoch": 17.09020902090209, "percentage": 85.45, "elapsed_time": "6:08:13", "remaining_time": "1:02:41", "throughput": 1483.93, "total_tokens": 32785408} {"current_steps": 155355, "total_steps": 181800, "loss": 0.0014, "lr": 3.1543172236162405e-06, "epoch": 17.09075907590759, "percentage": 85.45, "elapsed_time": "6:08:14", "remaining_time": "1:02:40", "throughput": 1483.94, "total_tokens": 32786528} {"current_steps": 155360, "total_steps": 181800, "loss": 0.0024, "lr": 3.15315032401205e-06, "epoch": 17.091309130913093, "percentage": 85.46, "elapsed_time": "6:08:14", "remaining_time": "1:02:40", "throughput": 1483.94, "total_tokens": 32787616} {"current_steps": 155365, "total_steps": 181800, "loss": 0.0045, "lr": 3.1519836257597884e-06, "epoch": 17.09185918591859, "percentage": 85.46, "elapsed_time": "6:08:15", "remaining_time": "1:02:39", "throughput": 1483.94, "total_tokens": 32788608} {"current_steps": 155370, "total_steps": 181800, "loss": 0.0387, "lr": 3.1508171288702178e-06, "epoch": 17.09240924092409, "percentage": 85.46, "elapsed_time": "6:08:16", "remaining_time": "1:02:38", "throughput": 1483.94, "total_tokens": 32789632} {"current_steps": 155375, "total_steps": 181800, "loss": 0.0013, "lr": 3.1496508333540733e-06, "epoch": 17.092959295929592, "percentage": 85.46, "elapsed_time": "6:08:17", "remaining_time": "1:02:38", "throughput": 1483.94, "total_tokens": 32790720} {"current_steps": 155380, "total_steps": 181800, "loss": 0.0017, "lr": 3.1484847392221185e-06, "epoch": 17.093509350935093, "percentage": 85.47, "elapsed_time": "6:08:17", "remaining_time": "1:02:37", "throughput": 1483.95, "total_tokens": 32791808} {"current_steps": 155385, "total_steps": 181800, "loss": 0.0018, "lr": 3.1473188464850893e-06, "epoch": 17.094059405940595, "percentage": 85.47, "elapsed_time": "6:08:18", "remaining_time": "1:02:36", "throughput": 1483.95, "total_tokens": 32792864} {"current_steps": 155390, "total_steps": 181800, "loss": 0.0856, "lr": 3.146153155153736e-06, "epoch": 17.094609460946096, "percentage": 85.47, "elapsed_time": "6:08:19", "remaining_time": "1:02:35", "throughput": 1483.95, "total_tokens": 32793888} {"current_steps": 155395, "total_steps": 181800, "loss": 0.0027, "lr": 3.1449876652388104e-06, "epoch": 17.095159515951597, "percentage": 85.48, "elapsed_time": "6:08:19", "remaining_time": "1:02:35", "throughput": 1483.95, "total_tokens": 32794880} {"current_steps": 155400, "total_steps": 181800, "loss": 0.0634, "lr": 3.1438223767510376e-06, "epoch": 17.095709570957094, "percentage": 85.48, "elapsed_time": "6:08:20", "remaining_time": "1:02:34", "throughput": 1483.94, "total_tokens": 32795840} {"current_steps": 155405, "total_steps": 181800, "loss": 0.0667, "lr": 3.142657289701173e-06, "epoch": 17.096259625962595, "percentage": 85.48, "elapsed_time": "6:08:21", "remaining_time": "1:02:33", "throughput": 1483.95, "total_tokens": 32796960} {"current_steps": 155410, "total_steps": 181800, "loss": 0.0028, "lr": 3.1414924040999493e-06, "epoch": 17.096809680968097, "percentage": 85.48, "elapsed_time": "6:08:21", "remaining_time": "1:02:33", "throughput": 1483.95, "total_tokens": 32798080} {"current_steps": 155415, "total_steps": 181800, "loss": 0.0026, "lr": 3.1403277199580943e-06, "epoch": 17.097359735973598, "percentage": 85.49, "elapsed_time": "6:08:22", "remaining_time": "1:02:32", "throughput": 1483.96, "total_tokens": 32799168} {"current_steps": 155420, "total_steps": 181800, "loss": 0.0097, "lr": 3.1391632372863495e-06, "epoch": 17.0979097909791, "percentage": 85.49, "elapsed_time": "6:08:23", "remaining_time": "1:02:31", "throughput": 1483.96, "total_tokens": 32800192} {"current_steps": 155425, "total_steps": 181800, "loss": 0.1463, "lr": 3.1379989560954478e-06, "epoch": 17.0984598459846, "percentage": 85.49, "elapsed_time": "6:08:23", "remaining_time": "1:02:30", "throughput": 1483.95, "total_tokens": 32801184} {"current_steps": 155430, "total_steps": 181800, "loss": 0.0769, "lr": 3.1368348763961248e-06, "epoch": 17.099009900990097, "percentage": 85.5, "elapsed_time": "6:08:24", "remaining_time": "1:02:30", "throughput": 1483.95, "total_tokens": 32802208} {"current_steps": 155435, "total_steps": 181800, "loss": 0.0047, "lr": 3.1356709981991056e-06, "epoch": 17.0995599559956, "percentage": 85.5, "elapsed_time": "6:08:25", "remaining_time": "1:02:29", "throughput": 1483.95, "total_tokens": 32803232} {"current_steps": 155440, "total_steps": 181800, "loss": 0.0286, "lr": 3.1345073215151066e-06, "epoch": 17.1001100110011, "percentage": 85.5, "elapsed_time": "6:08:25", "remaining_time": "1:02:28", "throughput": 1483.96, "total_tokens": 32804320} {"current_steps": 155445, "total_steps": 181800, "loss": 0.0033, "lr": 3.1333438463548693e-06, "epoch": 17.1006600660066, "percentage": 85.5, "elapsed_time": "6:08:26", "remaining_time": "1:02:28", "throughput": 1483.96, "total_tokens": 32805408} {"current_steps": 155450, "total_steps": 181800, "loss": 0.0136, "lr": 3.132180572729096e-06, "epoch": 17.1012101210121, "percentage": 85.51, "elapsed_time": "6:08:27", "remaining_time": "1:02:27", "throughput": 1483.96, "total_tokens": 32806432} {"current_steps": 155455, "total_steps": 181800, "loss": 0.018, "lr": 3.131017500648534e-06, "epoch": 17.101760176017603, "percentage": 85.51, "elapsed_time": "6:08:28", "remaining_time": "1:02:26", "throughput": 1483.96, "total_tokens": 32807424} {"current_steps": 155460, "total_steps": 181800, "loss": 0.0103, "lr": 3.1298546301238907e-06, "epoch": 17.102310231023104, "percentage": 85.51, "elapsed_time": "6:08:28", "remaining_time": "1:02:25", "throughput": 1483.96, "total_tokens": 32808448} {"current_steps": 155465, "total_steps": 181800, "loss": 0.0982, "lr": 3.128691961165875e-06, "epoch": 17.1028602860286, "percentage": 85.51, "elapsed_time": "6:08:29", "remaining_time": "1:02:25", "throughput": 1483.96, "total_tokens": 32809536} {"current_steps": 155470, "total_steps": 181800, "loss": 0.1664, "lr": 3.1275294937852168e-06, "epoch": 17.103410341034103, "percentage": 85.52, "elapsed_time": "6:08:30", "remaining_time": "1:02:24", "throughput": 1483.96, "total_tokens": 32810528} {"current_steps": 155475, "total_steps": 181800, "loss": 0.0018, "lr": 3.126367227992619e-06, "epoch": 17.103960396039604, "percentage": 85.52, "elapsed_time": "6:08:30", "remaining_time": "1:02:23", "throughput": 1483.96, "total_tokens": 32811616} {"current_steps": 155480, "total_steps": 181800, "loss": 0.0114, "lr": 3.1252051637987973e-06, "epoch": 17.104510451045105, "percentage": 85.52, "elapsed_time": "6:08:31", "remaining_time": "1:02:23", "throughput": 1483.97, "total_tokens": 32812672} {"current_steps": 155485, "total_steps": 181800, "loss": 0.0024, "lr": 3.1240433012144687e-06, "epoch": 17.105060506050606, "percentage": 85.53, "elapsed_time": "6:08:32", "remaining_time": "1:02:22", "throughput": 1483.97, "total_tokens": 32813760} {"current_steps": 155490, "total_steps": 181800, "loss": 0.0007, "lr": 3.122881640250333e-06, "epoch": 17.105610561056107, "percentage": 85.53, "elapsed_time": "6:08:32", "remaining_time": "1:02:21", "throughput": 1483.97, "total_tokens": 32814784} {"current_steps": 155495, "total_steps": 181800, "loss": 0.0005, "lr": 3.121720180917104e-06, "epoch": 17.106160616061604, "percentage": 85.53, "elapsed_time": "6:08:33", "remaining_time": "1:02:20", "throughput": 1483.98, "total_tokens": 32815968} {"current_steps": 155500, "total_steps": 181800, "loss": 0.003, "lr": 3.120558923225475e-06, "epoch": 17.106710671067106, "percentage": 85.53, "elapsed_time": "6:08:34", "remaining_time": "1:02:20", "throughput": 1483.98, "total_tokens": 32816992} {"current_steps": 155505, "total_steps": 181800, "loss": 0.013, "lr": 3.1193978671861606e-06, "epoch": 17.107260726072607, "percentage": 85.54, "elapsed_time": "6:08:34", "remaining_time": "1:02:19", "throughput": 1483.98, "total_tokens": 32818080} {"current_steps": 155510, "total_steps": 181800, "loss": 0.086, "lr": 3.118237012809852e-06, "epoch": 17.107810781078108, "percentage": 85.54, "elapsed_time": "6:08:35", "remaining_time": "1:02:18", "throughput": 1483.98, "total_tokens": 32819136} {"current_steps": 155515, "total_steps": 181800, "loss": 0.0677, "lr": 3.1170763601072543e-06, "epoch": 17.10836083608361, "percentage": 85.54, "elapsed_time": "6:08:36", "remaining_time": "1:02:18", "throughput": 1483.98, "total_tokens": 32820160} {"current_steps": 155520, "total_steps": 181800, "loss": 0.0113, "lr": 3.1159159090890677e-06, "epoch": 17.10891089108911, "percentage": 85.54, "elapsed_time": "6:08:36", "remaining_time": "1:02:17", "throughput": 1483.98, "total_tokens": 32821216} {"current_steps": 155525, "total_steps": 181800, "loss": 0.0165, "lr": 3.114755659765978e-06, "epoch": 17.10946094609461, "percentage": 85.55, "elapsed_time": "6:08:37", "remaining_time": "1:02:16", "throughput": 1483.98, "total_tokens": 32822272} {"current_steps": 155530, "total_steps": 181800, "loss": 0.0345, "lr": 3.1135956121486898e-06, "epoch": 17.11001100110011, "percentage": 85.55, "elapsed_time": "6:08:38", "remaining_time": "1:02:15", "throughput": 1483.98, "total_tokens": 32823296} {"current_steps": 155535, "total_steps": 181800, "loss": 0.0379, "lr": 3.1124357662478816e-06, "epoch": 17.11056105610561, "percentage": 85.55, "elapsed_time": "6:08:39", "remaining_time": "1:02:15", "throughput": 1483.99, "total_tokens": 32824384} {"current_steps": 155540, "total_steps": 181800, "loss": 0.0061, "lr": 3.11127612207425e-06, "epoch": 17.11111111111111, "percentage": 85.56, "elapsed_time": "6:08:39", "remaining_time": "1:02:14", "throughput": 1483.99, "total_tokens": 32825440} {"current_steps": 155545, "total_steps": 181800, "loss": 0.0032, "lr": 3.110116679638492e-06, "epoch": 17.111661166116612, "percentage": 85.56, "elapsed_time": "6:08:40", "remaining_time": "1:02:13", "throughput": 1483.99, "total_tokens": 32826496} {"current_steps": 155550, "total_steps": 181800, "loss": 0.1358, "lr": 3.1089574389512766e-06, "epoch": 17.112211221122113, "percentage": 85.56, "elapsed_time": "6:08:41", "remaining_time": "1:02:13", "throughput": 1483.99, "total_tokens": 32827584} {"current_steps": 155555, "total_steps": 181800, "loss": 0.0069, "lr": 3.1077984000233013e-06, "epoch": 17.112761276127614, "percentage": 85.56, "elapsed_time": "6:08:41", "remaining_time": "1:02:12", "throughput": 1484.0, "total_tokens": 32828704} {"current_steps": 155560, "total_steps": 181800, "loss": 0.0088, "lr": 3.1066395628652435e-06, "epoch": 17.11331133113311, "percentage": 85.57, "elapsed_time": "6:08:42", "remaining_time": "1:02:11", "throughput": 1484.0, "total_tokens": 32829728} {"current_steps": 155565, "total_steps": 181800, "loss": 0.003, "lr": 3.105480927487775e-06, "epoch": 17.113861386138613, "percentage": 85.57, "elapsed_time": "6:08:43", "remaining_time": "1:02:10", "throughput": 1484.0, "total_tokens": 32830752} {"current_steps": 155570, "total_steps": 181800, "loss": 0.0556, "lr": 3.10432249390159e-06, "epoch": 17.114411441144114, "percentage": 85.57, "elapsed_time": "6:08:43", "remaining_time": "1:02:10", "throughput": 1484.0, "total_tokens": 32831840} {"current_steps": 155575, "total_steps": 181800, "loss": 0.0055, "lr": 3.1031642621173555e-06, "epoch": 17.114961496149615, "percentage": 85.57, "elapsed_time": "6:08:44", "remaining_time": "1:02:09", "throughput": 1484.0, "total_tokens": 32832960} {"current_steps": 155580, "total_steps": 181800, "loss": 0.0085, "lr": 3.1020062321457518e-06, "epoch": 17.115511551155116, "percentage": 85.58, "elapsed_time": "6:08:45", "remaining_time": "1:02:08", "throughput": 1484.0, "total_tokens": 32833952} {"current_steps": 155585, "total_steps": 181800, "loss": 0.0101, "lr": 3.10084840399745e-06, "epoch": 17.116061606160617, "percentage": 85.58, "elapsed_time": "6:08:45", "remaining_time": "1:02:08", "throughput": 1484.0, "total_tokens": 32834976} {"current_steps": 155590, "total_steps": 181800, "loss": 0.0013, "lr": 3.0996907776831148e-06, "epoch": 17.116611661166118, "percentage": 85.58, "elapsed_time": "6:08:46", "remaining_time": "1:02:07", "throughput": 1484.01, "total_tokens": 32836064} {"current_steps": 155595, "total_steps": 181800, "loss": 0.022, "lr": 3.098533353213423e-06, "epoch": 17.117161716171616, "percentage": 85.59, "elapsed_time": "6:08:47", "remaining_time": "1:02:06", "throughput": 1484.01, "total_tokens": 32837152} {"current_steps": 155600, "total_steps": 181800, "loss": 0.1509, "lr": 3.097376130599042e-06, "epoch": 17.117711771177117, "percentage": 85.59, "elapsed_time": "6:08:48", "remaining_time": "1:02:05", "throughput": 1484.01, "total_tokens": 32838272} {"current_steps": 155605, "total_steps": 181800, "loss": 0.0109, "lr": 3.0962191098506314e-06, "epoch": 17.118261826182618, "percentage": 85.59, "elapsed_time": "6:08:48", "remaining_time": "1:02:05", "throughput": 1484.01, "total_tokens": 32839232} {"current_steps": 155610, "total_steps": 181800, "loss": 0.022, "lr": 3.0950622909788648e-06, "epoch": 17.11881188118812, "percentage": 85.59, "elapsed_time": "6:08:49", "remaining_time": "1:02:04", "throughput": 1484.01, "total_tokens": 32840256} {"current_steps": 155615, "total_steps": 181800, "loss": 0.0117, "lr": 3.0939056739943932e-06, "epoch": 17.11936193619362, "percentage": 85.6, "elapsed_time": "6:08:50", "remaining_time": "1:02:03", "throughput": 1484.01, "total_tokens": 32841344} {"current_steps": 155620, "total_steps": 181800, "loss": 0.0012, "lr": 3.0927492589078844e-06, "epoch": 17.11991199119912, "percentage": 85.6, "elapsed_time": "6:08:50", "remaining_time": "1:02:03", "throughput": 1484.01, "total_tokens": 32842368} {"current_steps": 155625, "total_steps": 181800, "loss": 0.0188, "lr": 3.09159304572999e-06, "epoch": 17.120462046204622, "percentage": 85.6, "elapsed_time": "6:08:51", "remaining_time": "1:02:02", "throughput": 1484.01, "total_tokens": 32843392} {"current_steps": 155630, "total_steps": 181800, "loss": 0.0774, "lr": 3.090437034471369e-06, "epoch": 17.12101210121012, "percentage": 85.61, "elapsed_time": "6:08:52", "remaining_time": "1:02:01", "throughput": 1484.01, "total_tokens": 32844416} {"current_steps": 155635, "total_steps": 181800, "loss": 0.0021, "lr": 3.0892812251426816e-06, "epoch": 17.12156215621562, "percentage": 85.61, "elapsed_time": "6:08:52", "remaining_time": "1:02:00", "throughput": 1484.02, "total_tokens": 32845536} {"current_steps": 155640, "total_steps": 181800, "loss": 0.0098, "lr": 3.0881256177545727e-06, "epoch": 17.122112211221122, "percentage": 85.61, "elapsed_time": "6:08:53", "remaining_time": "1:02:00", "throughput": 1484.02, "total_tokens": 32846592} {"current_steps": 155645, "total_steps": 181800, "loss": 0.0068, "lr": 3.0869702123177e-06, "epoch": 17.122662266226623, "percentage": 85.61, "elapsed_time": "6:08:54", "remaining_time": "1:01:59", "throughput": 1484.02, "total_tokens": 32847648} {"current_steps": 155650, "total_steps": 181800, "loss": 0.0021, "lr": 3.085815008842699e-06, "epoch": 17.123212321232124, "percentage": 85.62, "elapsed_time": "6:08:54", "remaining_time": "1:01:58", "throughput": 1484.02, "total_tokens": 32848672} {"current_steps": 155655, "total_steps": 181800, "loss": 0.0031, "lr": 3.0846600073402287e-06, "epoch": 17.123762376237625, "percentage": 85.62, "elapsed_time": "6:08:55", "remaining_time": "1:01:58", "throughput": 1484.02, "total_tokens": 32849696} {"current_steps": 155660, "total_steps": 181800, "loss": 0.0041, "lr": 3.083505207820936e-06, "epoch": 17.124312431243123, "percentage": 85.62, "elapsed_time": "6:08:56", "remaining_time": "1:01:57", "throughput": 1484.02, "total_tokens": 32850720} {"current_steps": 155665, "total_steps": 181800, "loss": 0.0185, "lr": 3.0823506102954537e-06, "epoch": 17.124862486248624, "percentage": 85.62, "elapsed_time": "6:08:56", "remaining_time": "1:01:56", "throughput": 1484.02, "total_tokens": 32851744} {"current_steps": 155670, "total_steps": 181800, "loss": 0.0287, "lr": 3.0811962147744345e-06, "epoch": 17.125412541254125, "percentage": 85.63, "elapsed_time": "6:08:57", "remaining_time": "1:01:55", "throughput": 1484.02, "total_tokens": 32852768} {"current_steps": 155675, "total_steps": 181800, "loss": 0.0023, "lr": 3.0800420212685116e-06, "epoch": 17.125962596259626, "percentage": 85.63, "elapsed_time": "6:08:58", "remaining_time": "1:01:55", "throughput": 1484.02, "total_tokens": 32853760} {"current_steps": 155680, "total_steps": 181800, "loss": 0.014, "lr": 3.0788880297883183e-06, "epoch": 17.126512651265127, "percentage": 85.63, "elapsed_time": "6:08:59", "remaining_time": "1:01:54", "throughput": 1484.02, "total_tokens": 32854848} {"current_steps": 155685, "total_steps": 181800, "loss": 0.1266, "lr": 3.077734240344496e-06, "epoch": 17.127062706270628, "percentage": 85.64, "elapsed_time": "6:08:59", "remaining_time": "1:01:53", "throughput": 1484.03, "total_tokens": 32855936} {"current_steps": 155690, "total_steps": 181800, "loss": 0.0027, "lr": 3.0765806529476774e-06, "epoch": 17.12761276127613, "percentage": 85.64, "elapsed_time": "6:09:00", "remaining_time": "1:01:53", "throughput": 1484.03, "total_tokens": 32857056} {"current_steps": 155695, "total_steps": 181800, "loss": 0.0808, "lr": 3.0754272676084993e-06, "epoch": 17.128162816281627, "percentage": 85.64, "elapsed_time": "6:09:01", "remaining_time": "1:01:52", "throughput": 1484.03, "total_tokens": 32858016} {"current_steps": 155700, "total_steps": 181800, "loss": 0.0437, "lr": 3.0742740843375887e-06, "epoch": 17.128712871287128, "percentage": 85.64, "elapsed_time": "6:09:01", "remaining_time": "1:01:51", "throughput": 1484.03, "total_tokens": 32859008} {"current_steps": 155705, "total_steps": 181800, "loss": 0.1162, "lr": 3.0731211031455654e-06, "epoch": 17.12926292629263, "percentage": 85.65, "elapsed_time": "6:09:02", "remaining_time": "1:01:50", "throughput": 1484.03, "total_tokens": 32860064} {"current_steps": 155710, "total_steps": 181800, "loss": 0.0061, "lr": 3.0719683240430672e-06, "epoch": 17.12981298129813, "percentage": 85.65, "elapsed_time": "6:09:03", "remaining_time": "1:01:50", "throughput": 1484.03, "total_tokens": 32861120} {"current_steps": 155715, "total_steps": 181800, "loss": 0.0157, "lr": 3.0708157470407117e-06, "epoch": 17.13036303630363, "percentage": 85.65, "elapsed_time": "6:09:03", "remaining_time": "1:01:49", "throughput": 1484.03, "total_tokens": 32862112} {"current_steps": 155720, "total_steps": 181800, "loss": 0.0009, "lr": 3.0696633721491313e-06, "epoch": 17.130913091309132, "percentage": 85.65, "elapsed_time": "6:09:04", "remaining_time": "1:01:48", "throughput": 1484.03, "total_tokens": 32863168} {"current_steps": 155725, "total_steps": 181800, "loss": 0.0039, "lr": 3.06851119937894e-06, "epoch": 17.13146314631463, "percentage": 85.66, "elapsed_time": "6:09:05", "remaining_time": "1:01:48", "throughput": 1484.03, "total_tokens": 32864224} {"current_steps": 155730, "total_steps": 181800, "loss": 0.0237, "lr": 3.0673592287407515e-06, "epoch": 17.13201320132013, "percentage": 85.66, "elapsed_time": "6:09:05", "remaining_time": "1:01:47", "throughput": 1484.03, "total_tokens": 32865312} {"current_steps": 155735, "total_steps": 181800, "loss": 0.003, "lr": 3.066207460245196e-06, "epoch": 17.132563256325632, "percentage": 85.66, "elapsed_time": "6:09:06", "remaining_time": "1:01:46", "throughput": 1484.04, "total_tokens": 32866368} {"current_steps": 155740, "total_steps": 181800, "loss": 0.0567, "lr": 3.065055893902874e-06, "epoch": 17.133113311331133, "percentage": 85.67, "elapsed_time": "6:09:07", "remaining_time": "1:01:45", "throughput": 1484.04, "total_tokens": 32867456} {"current_steps": 155745, "total_steps": 181800, "loss": 0.0025, "lr": 3.063904529724407e-06, "epoch": 17.133663366336634, "percentage": 85.67, "elapsed_time": "6:09:07", "remaining_time": "1:01:45", "throughput": 1484.04, "total_tokens": 32868480} {"current_steps": 155750, "total_steps": 181800, "loss": 0.0468, "lr": 3.0627533677204113e-06, "epoch": 17.134213421342135, "percentage": 85.67, "elapsed_time": "6:09:08", "remaining_time": "1:01:44", "throughput": 1484.04, "total_tokens": 32869632} {"current_steps": 155755, "total_steps": 181800, "loss": 0.0035, "lr": 3.061602407901487e-06, "epoch": 17.134763476347636, "percentage": 85.67, "elapsed_time": "6:09:09", "remaining_time": "1:01:43", "throughput": 1484.05, "total_tokens": 32870720} {"current_steps": 155760, "total_steps": 181800, "loss": 0.0786, "lr": 3.060451650278251e-06, "epoch": 17.135313531353134, "percentage": 85.68, "elapsed_time": "6:09:10", "remaining_time": "1:01:43", "throughput": 1484.05, "total_tokens": 32871776} {"current_steps": 155765, "total_steps": 181800, "loss": 0.0069, "lr": 3.0593010948613e-06, "epoch": 17.135863586358635, "percentage": 85.68, "elapsed_time": "6:09:10", "remaining_time": "1:01:42", "throughput": 1484.05, "total_tokens": 32872768} {"current_steps": 155770, "total_steps": 181800, "loss": 0.0056, "lr": 3.058150741661242e-06, "epoch": 17.136413641364136, "percentage": 85.68, "elapsed_time": "6:09:11", "remaining_time": "1:01:41", "throughput": 1484.05, "total_tokens": 32873856} {"current_steps": 155775, "total_steps": 181800, "loss": 0.0014, "lr": 3.057000590688683e-06, "epoch": 17.136963696369637, "percentage": 85.68, "elapsed_time": "6:09:12", "remaining_time": "1:01:40", "throughput": 1484.05, "total_tokens": 32874944} {"current_steps": 155780, "total_steps": 181800, "loss": 0.1236, "lr": 3.0558506419542167e-06, "epoch": 17.13751375137514, "percentage": 85.69, "elapsed_time": "6:09:12", "remaining_time": "1:01:40", "throughput": 1484.05, "total_tokens": 32876000} {"current_steps": 155785, "total_steps": 181800, "loss": 0.066, "lr": 3.0547008954684513e-06, "epoch": 17.13806380638064, "percentage": 85.69, "elapsed_time": "6:09:13", "remaining_time": "1:01:39", "throughput": 1484.05, "total_tokens": 32876992} {"current_steps": 155790, "total_steps": 181800, "loss": 0.0481, "lr": 3.0535513512419762e-06, "epoch": 17.138613861386137, "percentage": 85.69, "elapsed_time": "6:09:14", "remaining_time": "1:01:38", "throughput": 1484.05, "total_tokens": 32878016} {"current_steps": 155795, "total_steps": 181800, "loss": 0.003, "lr": 3.052402009285382e-06, "epoch": 17.139163916391638, "percentage": 85.7, "elapsed_time": "6:09:14", "remaining_time": "1:01:38", "throughput": 1484.05, "total_tokens": 32879008} {"current_steps": 155800, "total_steps": 181800, "loss": 0.002, "lr": 3.0512528696092695e-06, "epoch": 17.13971397139714, "percentage": 85.7, "elapsed_time": "6:09:15", "remaining_time": "1:01:37", "throughput": 1484.05, "total_tokens": 32880064} {"current_steps": 155805, "total_steps": 181800, "loss": 0.1783, "lr": 3.050103932224224e-06, "epoch": 17.14026402640264, "percentage": 85.7, "elapsed_time": "6:09:16", "remaining_time": "1:01:36", "throughput": 1484.05, "total_tokens": 32881056} {"current_steps": 155810, "total_steps": 181800, "loss": 0.0031, "lr": 3.048955197140846e-06, "epoch": 17.14081408140814, "percentage": 85.7, "elapsed_time": "6:09:16", "remaining_time": "1:01:35", "throughput": 1484.05, "total_tokens": 32882080} {"current_steps": 155815, "total_steps": 181800, "loss": 0.0549, "lr": 3.0478066643697124e-06, "epoch": 17.141364136413642, "percentage": 85.71, "elapsed_time": "6:09:17", "remaining_time": "1:01:35", "throughput": 1484.05, "total_tokens": 32883104} {"current_steps": 155820, "total_steps": 181800, "loss": 0.0022, "lr": 3.0466583339214066e-06, "epoch": 17.141914191419144, "percentage": 85.71, "elapsed_time": "6:09:18", "remaining_time": "1:01:34", "throughput": 1484.06, "total_tokens": 32884192} {"current_steps": 155825, "total_steps": 181800, "loss": 0.0168, "lr": 3.0455102058065176e-06, "epoch": 17.14246424642464, "percentage": 85.71, "elapsed_time": "6:09:19", "remaining_time": "1:01:33", "throughput": 1484.06, "total_tokens": 32885216} {"current_steps": 155830, "total_steps": 181800, "loss": 0.0045, "lr": 3.0443622800356258e-06, "epoch": 17.143014301430142, "percentage": 85.72, "elapsed_time": "6:09:19", "remaining_time": "1:01:33", "throughput": 1484.06, "total_tokens": 32886336} {"current_steps": 155835, "total_steps": 181800, "loss": 0.0006, "lr": 3.0432145566193173e-06, "epoch": 17.143564356435643, "percentage": 85.72, "elapsed_time": "6:09:20", "remaining_time": "1:01:32", "throughput": 1484.06, "total_tokens": 32887424} {"current_steps": 155840, "total_steps": 181800, "loss": 0.003, "lr": 3.0420670355681635e-06, "epoch": 17.144114411441144, "percentage": 85.72, "elapsed_time": "6:09:21", "remaining_time": "1:01:31", "throughput": 1484.06, "total_tokens": 32888416} {"current_steps": 155845, "total_steps": 181800, "loss": 0.0054, "lr": 3.0409197168927345e-06, "epoch": 17.144664466446645, "percentage": 85.72, "elapsed_time": "6:09:21", "remaining_time": "1:01:30", "throughput": 1484.06, "total_tokens": 32889408} {"current_steps": 155850, "total_steps": 181800, "loss": 0.0007, "lr": 3.0397726006036188e-06, "epoch": 17.145214521452147, "percentage": 85.73, "elapsed_time": "6:09:22", "remaining_time": "1:01:30", "throughput": 1484.06, "total_tokens": 32890464} {"current_steps": 155855, "total_steps": 181800, "loss": 0.0303, "lr": 3.038625686711377e-06, "epoch": 17.145764576457644, "percentage": 85.73, "elapsed_time": "6:09:23", "remaining_time": "1:01:29", "throughput": 1484.06, "total_tokens": 32891488} {"current_steps": 155860, "total_steps": 181800, "loss": 0.0059, "lr": 3.037478975226582e-06, "epoch": 17.146314631463145, "percentage": 85.73, "elapsed_time": "6:09:23", "remaining_time": "1:01:28", "throughput": 1484.06, "total_tokens": 32892544} {"current_steps": 155865, "total_steps": 181800, "loss": 0.0759, "lr": 3.036332466159811e-06, "epoch": 17.146864686468646, "percentage": 85.73, "elapsed_time": "6:09:24", "remaining_time": "1:01:28", "throughput": 1484.07, "total_tokens": 32893632} {"current_steps": 155870, "total_steps": 181800, "loss": 0.0038, "lr": 3.035186159521619e-06, "epoch": 17.147414741474147, "percentage": 85.74, "elapsed_time": "6:09:25", "remaining_time": "1:01:27", "throughput": 1484.07, "total_tokens": 32894656} {"current_steps": 155875, "total_steps": 181800, "loss": 0.105, "lr": 3.0340400553225817e-06, "epoch": 17.14796479647965, "percentage": 85.74, "elapsed_time": "6:09:25", "remaining_time": "1:01:26", "throughput": 1484.07, "total_tokens": 32895712} {"current_steps": 155880, "total_steps": 181800, "loss": 0.013, "lr": 3.0328941535732512e-06, "epoch": 17.14851485148515, "percentage": 85.74, "elapsed_time": "6:09:26", "remaining_time": "1:01:25", "throughput": 1484.07, "total_tokens": 32896736} {"current_steps": 155885, "total_steps": 181800, "loss": 0.002, "lr": 3.0317484542841973e-06, "epoch": 17.14906490649065, "percentage": 85.75, "elapsed_time": "6:09:27", "remaining_time": "1:01:25", "throughput": 1484.07, "total_tokens": 32897760} {"current_steps": 155890, "total_steps": 181800, "loss": 0.0039, "lr": 3.0306029574659777e-06, "epoch": 17.149614961496148, "percentage": 85.75, "elapsed_time": "6:09:27", "remaining_time": "1:01:24", "throughput": 1484.07, "total_tokens": 32898784} {"current_steps": 155895, "total_steps": 181800, "loss": 0.0015, "lr": 3.0294576631291456e-06, "epoch": 17.15016501650165, "percentage": 85.75, "elapsed_time": "6:09:28", "remaining_time": "1:01:23", "throughput": 1484.07, "total_tokens": 32899808} {"current_steps": 155900, "total_steps": 181800, "loss": 0.0092, "lr": 3.028312571284264e-06, "epoch": 17.15071507150715, "percentage": 85.75, "elapsed_time": "6:09:29", "remaining_time": "1:01:23", "throughput": 1484.07, "total_tokens": 32900832} {"current_steps": 155905, "total_steps": 181800, "loss": 0.0377, "lr": 3.027167681941878e-06, "epoch": 17.15126512651265, "percentage": 85.76, "elapsed_time": "6:09:30", "remaining_time": "1:01:22", "throughput": 1484.07, "total_tokens": 32901888} {"current_steps": 155910, "total_steps": 181800, "loss": 0.0343, "lr": 3.0260229951125487e-06, "epoch": 17.151815181518153, "percentage": 85.76, "elapsed_time": "6:09:30", "remaining_time": "1:01:21", "throughput": 1484.07, "total_tokens": 32902912} {"current_steps": 155915, "total_steps": 181800, "loss": 0.0523, "lr": 3.024878510806817e-06, "epoch": 17.152365236523654, "percentage": 85.76, "elapsed_time": "6:09:31", "remaining_time": "1:01:20", "throughput": 1484.07, "total_tokens": 32904000} {"current_steps": 155920, "total_steps": 181800, "loss": 0.1208, "lr": 3.0237342290352356e-06, "epoch": 17.15291529152915, "percentage": 85.76, "elapsed_time": "6:09:32", "remaining_time": "1:01:20", "throughput": 1484.07, "total_tokens": 32905056} {"current_steps": 155925, "total_steps": 181800, "loss": 0.0548, "lr": 3.0225901498083547e-06, "epoch": 17.153465346534652, "percentage": 85.77, "elapsed_time": "6:09:32", "remaining_time": "1:01:19", "throughput": 1484.08, "total_tokens": 32906112} {"current_steps": 155930, "total_steps": 181800, "loss": 0.1091, "lr": 3.0214462731367078e-06, "epoch": 17.154015401540153, "percentage": 85.77, "elapsed_time": "6:09:33", "remaining_time": "1:01:18", "throughput": 1484.07, "total_tokens": 32907104} {"current_steps": 155935, "total_steps": 181800, "loss": 0.0087, "lr": 3.0203025990308527e-06, "epoch": 17.154565456545654, "percentage": 85.77, "elapsed_time": "6:09:34", "remaining_time": "1:01:18", "throughput": 1484.08, "total_tokens": 32908192} {"current_steps": 155940, "total_steps": 181800, "loss": 0.0865, "lr": 3.0191591275013142e-06, "epoch": 17.155115511551156, "percentage": 85.78, "elapsed_time": "6:09:34", "remaining_time": "1:01:17", "throughput": 1484.08, "total_tokens": 32909248} {"current_steps": 155945, "total_steps": 181800, "loss": 0.0058, "lr": 3.0180158585586397e-06, "epoch": 17.155665566556657, "percentage": 85.78, "elapsed_time": "6:09:35", "remaining_time": "1:01:16", "throughput": 1484.08, "total_tokens": 32910304} {"current_steps": 155950, "total_steps": 181800, "loss": 0.0676, "lr": 3.0168727922133713e-06, "epoch": 17.156215621562158, "percentage": 85.78, "elapsed_time": "6:09:36", "remaining_time": "1:01:15", "throughput": 1484.08, "total_tokens": 32911360} {"current_steps": 155955, "total_steps": 181800, "loss": 0.1262, "lr": 3.01572992847603e-06, "epoch": 17.156765676567655, "percentage": 85.78, "elapsed_time": "6:09:36", "remaining_time": "1:01:15", "throughput": 1484.08, "total_tokens": 32912416} {"current_steps": 155960, "total_steps": 181800, "loss": 0.0123, "lr": 3.0145872673571633e-06, "epoch": 17.157315731573156, "percentage": 85.79, "elapsed_time": "6:09:37", "remaining_time": "1:01:14", "throughput": 1484.08, "total_tokens": 32913440} {"current_steps": 155965, "total_steps": 181800, "loss": 0.0252, "lr": 3.0134448088672967e-06, "epoch": 17.157865786578657, "percentage": 85.79, "elapsed_time": "6:09:38", "remaining_time": "1:01:13", "throughput": 1484.08, "total_tokens": 32914432} {"current_steps": 155970, "total_steps": 181800, "loss": 0.0107, "lr": 3.012302553016952e-06, "epoch": 17.15841584158416, "percentage": 85.79, "elapsed_time": "6:09:39", "remaining_time": "1:01:13", "throughput": 1484.08, "total_tokens": 32915488} {"current_steps": 155975, "total_steps": 181800, "loss": 0.0008, "lr": 3.0111604998166647e-06, "epoch": 17.15896589658966, "percentage": 85.79, "elapsed_time": "6:09:39", "remaining_time": "1:01:12", "throughput": 1484.08, "total_tokens": 32916512} {"current_steps": 155980, "total_steps": 181800, "loss": 0.1388, "lr": 3.010018649276966e-06, "epoch": 17.15951595159516, "percentage": 85.8, "elapsed_time": "6:09:40", "remaining_time": "1:01:11", "throughput": 1484.08, "total_tokens": 32917568} {"current_steps": 155985, "total_steps": 181800, "loss": 0.0624, "lr": 3.0088770014083694e-06, "epoch": 17.16006600660066, "percentage": 85.8, "elapsed_time": "6:09:41", "remaining_time": "1:01:10", "throughput": 1484.08, "total_tokens": 32918592} {"current_steps": 155990, "total_steps": 181800, "loss": 0.0051, "lr": 3.0077355562214053e-06, "epoch": 17.16061606160616, "percentage": 85.8, "elapsed_time": "6:09:41", "remaining_time": "1:01:10", "throughput": 1484.09, "total_tokens": 32919744} {"current_steps": 155995, "total_steps": 181800, "loss": 0.0008, "lr": 3.0065943137265825e-06, "epoch": 17.16116611661166, "percentage": 85.81, "elapsed_time": "6:09:42", "remaining_time": "1:01:09", "throughput": 1484.09, "total_tokens": 32920832} {"current_steps": 156000, "total_steps": 181800, "loss": 0.0761, "lr": 3.0054532739344278e-06, "epoch": 17.16171617161716, "percentage": 85.81, "elapsed_time": "6:09:43", "remaining_time": "1:01:08", "throughput": 1484.09, "total_tokens": 32921888} {"current_steps": 156005, "total_steps": 181800, "loss": 0.0033, "lr": 3.004312436855464e-06, "epoch": 17.162266226622663, "percentage": 85.81, "elapsed_time": "6:09:43", "remaining_time": "1:01:08", "throughput": 1484.1, "total_tokens": 32922976} {"current_steps": 156010, "total_steps": 181800, "loss": 0.0046, "lr": 3.00317180250019e-06, "epoch": 17.162816281628164, "percentage": 85.81, "elapsed_time": "6:09:44", "remaining_time": "1:01:07", "throughput": 1484.1, "total_tokens": 32924064} {"current_steps": 156015, "total_steps": 181800, "loss": 0.0017, "lr": 3.0020313708791324e-06, "epoch": 17.163366336633665, "percentage": 85.82, "elapsed_time": "6:09:45", "remaining_time": "1:01:06", "throughput": 1484.1, "total_tokens": 32925120} {"current_steps": 156020, "total_steps": 181800, "loss": 0.0073, "lr": 3.0008911420027903e-06, "epoch": 17.163916391639162, "percentage": 85.82, "elapsed_time": "6:09:45", "remaining_time": "1:01:05", "throughput": 1484.1, "total_tokens": 32926144} {"current_steps": 156025, "total_steps": 181800, "loss": 0.0011, "lr": 2.999751115881683e-06, "epoch": 17.164466446644663, "percentage": 85.82, "elapsed_time": "6:09:46", "remaining_time": "1:01:05", "throughput": 1484.1, "total_tokens": 32927200} {"current_steps": 156030, "total_steps": 181800, "loss": 0.0747, "lr": 2.998611292526307e-06, "epoch": 17.165016501650165, "percentage": 85.83, "elapsed_time": "6:09:47", "remaining_time": "1:01:04", "throughput": 1484.1, "total_tokens": 32928256} {"current_steps": 156035, "total_steps": 181800, "loss": 0.0017, "lr": 2.9974716719471746e-06, "epoch": 17.165566556655666, "percentage": 85.83, "elapsed_time": "6:09:48", "remaining_time": "1:01:03", "throughput": 1484.1, "total_tokens": 32929312} {"current_steps": 156040, "total_steps": 181800, "loss": 0.0706, "lr": 2.9963322541547935e-06, "epoch": 17.166116611661167, "percentage": 85.83, "elapsed_time": "6:09:48", "remaining_time": "1:01:03", "throughput": 1484.1, "total_tokens": 32930304} {"current_steps": 156045, "total_steps": 181800, "loss": 0.0059, "lr": 2.995193039159655e-06, "epoch": 17.166666666666668, "percentage": 85.83, "elapsed_time": "6:09:49", "remaining_time": "1:01:02", "throughput": 1484.1, "total_tokens": 32931360} {"current_steps": 156050, "total_steps": 181800, "loss": 0.0047, "lr": 2.9940540269722678e-06, "epoch": 17.16721672167217, "percentage": 85.84, "elapsed_time": "6:09:50", "remaining_time": "1:01:01", "throughput": 1484.11, "total_tokens": 32932448} {"current_steps": 156055, "total_steps": 181800, "loss": 0.0047, "lr": 2.9929152176031207e-06, "epoch": 17.167766776677666, "percentage": 85.84, "elapsed_time": "6:09:50", "remaining_time": "1:01:00", "throughput": 1484.11, "total_tokens": 32933536} {"current_steps": 156060, "total_steps": 181800, "loss": 0.0019, "lr": 2.9917766110627133e-06, "epoch": 17.168316831683168, "percentage": 85.84, "elapsed_time": "6:09:51", "remaining_time": "1:01:00", "throughput": 1484.11, "total_tokens": 32934624} {"current_steps": 156065, "total_steps": 181800, "loss": 0.07, "lr": 2.990638207361546e-06, "epoch": 17.16886688668867, "percentage": 85.84, "elapsed_time": "6:09:52", "remaining_time": "1:00:59", "throughput": 1484.12, "total_tokens": 32935712} {"current_steps": 156070, "total_steps": 181800, "loss": 0.0505, "lr": 2.9895000065100986e-06, "epoch": 17.16941694169417, "percentage": 85.85, "elapsed_time": "6:09:52", "remaining_time": "1:00:58", "throughput": 1484.12, "total_tokens": 32936768} {"current_steps": 156075, "total_steps": 181800, "loss": 0.0253, "lr": 2.9883620085188745e-06, "epoch": 17.16996699669967, "percentage": 85.85, "elapsed_time": "6:09:53", "remaining_time": "1:00:58", "throughput": 1484.12, "total_tokens": 32937824} {"current_steps": 156080, "total_steps": 181800, "loss": 0.0025, "lr": 2.987224213398354e-06, "epoch": 17.170517051705172, "percentage": 85.85, "elapsed_time": "6:09:54", "remaining_time": "1:00:57", "throughput": 1484.12, "total_tokens": 32938816} {"current_steps": 156085, "total_steps": 181800, "loss": 0.1525, "lr": 2.9860866211590204e-06, "epoch": 17.17106710671067, "percentage": 85.86, "elapsed_time": "6:09:54", "remaining_time": "1:00:56", "throughput": 1484.12, "total_tokens": 32939904} {"current_steps": 156090, "total_steps": 181800, "loss": 0.0198, "lr": 2.984949231811365e-06, "epoch": 17.17161716171617, "percentage": 85.86, "elapsed_time": "6:09:55", "remaining_time": "1:00:55", "throughput": 1484.12, "total_tokens": 32940992} {"current_steps": 156095, "total_steps": 181800, "loss": 0.0029, "lr": 2.9838120453658662e-06, "epoch": 17.17216721672167, "percentage": 85.86, "elapsed_time": "6:09:56", "remaining_time": "1:00:55", "throughput": 1484.13, "total_tokens": 32942112} {"current_steps": 156100, "total_steps": 181800, "loss": 0.072, "lr": 2.9826750618330153e-06, "epoch": 17.172717271727173, "percentage": 85.86, "elapsed_time": "6:09:56", "remaining_time": "1:00:54", "throughput": 1484.13, "total_tokens": 32943168} {"current_steps": 156105, "total_steps": 181800, "loss": 0.0009, "lr": 2.9815382812232813e-06, "epoch": 17.173267326732674, "percentage": 85.87, "elapsed_time": "6:09:57", "remaining_time": "1:00:53", "throughput": 1484.13, "total_tokens": 32944192} {"current_steps": 156110, "total_steps": 181800, "loss": 0.004, "lr": 2.9804017035471395e-06, "epoch": 17.173817381738175, "percentage": 85.87, "elapsed_time": "6:09:58", "remaining_time": "1:00:53", "throughput": 1484.13, "total_tokens": 32945216} {"current_steps": 156115, "total_steps": 181800, "loss": 0.0076, "lr": 2.979265328815067e-06, "epoch": 17.174367436743676, "percentage": 85.87, "elapsed_time": "6:09:59", "remaining_time": "1:00:52", "throughput": 1484.13, "total_tokens": 32946240} {"current_steps": 156120, "total_steps": 181800, "loss": 0.0745, "lr": 2.978129157037543e-06, "epoch": 17.174917491749174, "percentage": 85.87, "elapsed_time": "6:09:59", "remaining_time": "1:00:51", "throughput": 1484.13, "total_tokens": 32947328} {"current_steps": 156125, "total_steps": 181800, "loss": 0.1247, "lr": 2.9769931882250383e-06, "epoch": 17.175467546754675, "percentage": 85.88, "elapsed_time": "6:10:00", "remaining_time": "1:00:50", "throughput": 1484.13, "total_tokens": 32948384} {"current_steps": 156130, "total_steps": 181800, "loss": 0.0036, "lr": 2.9758574223880204e-06, "epoch": 17.176017601760176, "percentage": 85.88, "elapsed_time": "6:10:01", "remaining_time": "1:00:50", "throughput": 1484.13, "total_tokens": 32949440} {"current_steps": 156135, "total_steps": 181800, "loss": 0.0037, "lr": 2.9747218595369497e-06, "epoch": 17.176567656765677, "percentage": 85.88, "elapsed_time": "6:10:01", "remaining_time": "1:00:49", "throughput": 1484.13, "total_tokens": 32950432} {"current_steps": 156140, "total_steps": 181800, "loss": 0.0034, "lr": 2.973586499682307e-06, "epoch": 17.177117711771178, "percentage": 85.89, "elapsed_time": "6:10:02", "remaining_time": "1:00:48", "throughput": 1484.13, "total_tokens": 32951488} {"current_steps": 156145, "total_steps": 181800, "loss": 0.0062, "lr": 2.9724513428345394e-06, "epoch": 17.17766776677668, "percentage": 85.89, "elapsed_time": "6:10:03", "remaining_time": "1:00:48", "throughput": 1484.13, "total_tokens": 32952512} {"current_steps": 156150, "total_steps": 181800, "loss": 0.0632, "lr": 2.9713163890041224e-06, "epoch": 17.178217821782177, "percentage": 85.89, "elapsed_time": "6:10:03", "remaining_time": "1:00:47", "throughput": 1484.13, "total_tokens": 32953504} {"current_steps": 156155, "total_steps": 181800, "loss": 0.006, "lr": 2.9701816382015134e-06, "epoch": 17.178767876787678, "percentage": 85.89, "elapsed_time": "6:10:04", "remaining_time": "1:00:46", "throughput": 1484.13, "total_tokens": 32954592} {"current_steps": 156160, "total_steps": 181800, "loss": 0.0011, "lr": 2.9690470904371658e-06, "epoch": 17.17931793179318, "percentage": 85.9, "elapsed_time": "6:10:05", "remaining_time": "1:00:45", "throughput": 1484.14, "total_tokens": 32955712} {"current_steps": 156165, "total_steps": 181800, "loss": 0.0018, "lr": 2.9679127457215433e-06, "epoch": 17.17986798679868, "percentage": 85.9, "elapsed_time": "6:10:05", "remaining_time": "1:00:45", "throughput": 1484.14, "total_tokens": 32956864} {"current_steps": 156170, "total_steps": 181800, "loss": 0.1034, "lr": 2.9667786040650987e-06, "epoch": 17.18041804180418, "percentage": 85.9, "elapsed_time": "6:10:06", "remaining_time": "1:00:44", "throughput": 1484.15, "total_tokens": 32957920} {"current_steps": 156175, "total_steps": 181800, "loss": 0.009, "lr": 2.9656446654782705e-06, "epoch": 17.180968096809682, "percentage": 85.9, "elapsed_time": "6:10:07", "remaining_time": "1:00:43", "throughput": 1484.15, "total_tokens": 32958944} {"current_steps": 156180, "total_steps": 181800, "loss": 0.092, "lr": 2.964510929971534e-06, "epoch": 17.181518151815183, "percentage": 85.91, "elapsed_time": "6:10:08", "remaining_time": "1:00:43", "throughput": 1484.15, "total_tokens": 32960000} {"current_steps": 156185, "total_steps": 181800, "loss": 0.0308, "lr": 2.9633773975553224e-06, "epoch": 17.18206820682068, "percentage": 85.91, "elapsed_time": "6:10:08", "remaining_time": "1:00:42", "throughput": 1484.15, "total_tokens": 32961056} {"current_steps": 156190, "total_steps": 181800, "loss": 0.0611, "lr": 2.9622440682400915e-06, "epoch": 17.182618261826182, "percentage": 85.91, "elapsed_time": "6:10:09", "remaining_time": "1:00:41", "throughput": 1484.15, "total_tokens": 32962112} {"current_steps": 156195, "total_steps": 181800, "loss": 0.0038, "lr": 2.9611109420362827e-06, "epoch": 17.183168316831683, "percentage": 85.92, "elapsed_time": "6:10:10", "remaining_time": "1:00:40", "throughput": 1484.15, "total_tokens": 32963104} {"current_steps": 156200, "total_steps": 181800, "loss": 0.0322, "lr": 2.9599780189543348e-06, "epoch": 17.183718371837184, "percentage": 85.92, "elapsed_time": "6:10:10", "remaining_time": "1:00:40", "throughput": 1484.15, "total_tokens": 32964160} {"current_steps": 156205, "total_steps": 181800, "loss": 0.0061, "lr": 2.958845299004692e-06, "epoch": 17.184268426842685, "percentage": 85.92, "elapsed_time": "6:10:11", "remaining_time": "1:00:39", "throughput": 1484.15, "total_tokens": 32965152} {"current_steps": 156210, "total_steps": 181800, "loss": 0.0036, "lr": 2.957712782197794e-06, "epoch": 17.184818481848186, "percentage": 85.92, "elapsed_time": "6:10:12", "remaining_time": "1:00:38", "throughput": 1484.15, "total_tokens": 32966208} {"current_steps": 156215, "total_steps": 181800, "loss": 0.0262, "lr": 2.9565804685440875e-06, "epoch": 17.185368536853684, "percentage": 85.93, "elapsed_time": "6:10:12", "remaining_time": "1:00:38", "throughput": 1484.15, "total_tokens": 32967232} {"current_steps": 156220, "total_steps": 181800, "loss": 0.0513, "lr": 2.9554483580540026e-06, "epoch": 17.185918591859185, "percentage": 85.93, "elapsed_time": "6:10:13", "remaining_time": "1:00:37", "throughput": 1484.15, "total_tokens": 32968256} {"current_steps": 156225, "total_steps": 181800, "loss": 0.0034, "lr": 2.954316450737965e-06, "epoch": 17.186468646864686, "percentage": 85.93, "elapsed_time": "6:10:14", "remaining_time": "1:00:36", "throughput": 1484.15, "total_tokens": 32969248} {"current_steps": 156230, "total_steps": 181800, "loss": 0.0025, "lr": 2.9531847466064217e-06, "epoch": 17.187018701870187, "percentage": 85.94, "elapsed_time": "6:10:14", "remaining_time": "1:00:35", "throughput": 1484.15, "total_tokens": 32970336} {"current_steps": 156235, "total_steps": 181800, "loss": 0.0025, "lr": 2.9520532456697835e-06, "epoch": 17.187568756875688, "percentage": 85.94, "elapsed_time": "6:10:15", "remaining_time": "1:00:35", "throughput": 1484.15, "total_tokens": 32971328} {"current_steps": 156240, "total_steps": 181800, "loss": 0.0024, "lr": 2.9509219479385007e-06, "epoch": 17.18811881188119, "percentage": 85.94, "elapsed_time": "6:10:16", "remaining_time": "1:00:34", "throughput": 1484.15, "total_tokens": 32972416} {"current_steps": 156245, "total_steps": 181800, "loss": 0.0134, "lr": 2.94979085342299e-06, "epoch": 17.18866886688669, "percentage": 85.94, "elapsed_time": "6:10:17", "remaining_time": "1:00:33", "throughput": 1484.15, "total_tokens": 32973472} {"current_steps": 156250, "total_steps": 181800, "loss": 0.0018, "lr": 2.9486599621336737e-06, "epoch": 17.189218921892188, "percentage": 85.95, "elapsed_time": "6:10:17", "remaining_time": "1:00:33", "throughput": 1484.15, "total_tokens": 32974528} {"current_steps": 156255, "total_steps": 181800, "loss": 0.0399, "lr": 2.947529274080979e-06, "epoch": 17.18976897689769, "percentage": 85.95, "elapsed_time": "6:10:18", "remaining_time": "1:00:32", "throughput": 1484.16, "total_tokens": 32975584} {"current_steps": 156260, "total_steps": 181800, "loss": 0.003, "lr": 2.946398789275323e-06, "epoch": 17.19031903190319, "percentage": 85.95, "elapsed_time": "6:10:19", "remaining_time": "1:00:31", "throughput": 1484.16, "total_tokens": 32976608} {"current_steps": 156265, "total_steps": 181800, "loss": 0.1128, "lr": 2.945268507727125e-06, "epoch": 17.19086908690869, "percentage": 85.95, "elapsed_time": "6:10:19", "remaining_time": "1:00:30", "throughput": 1484.16, "total_tokens": 32977664} {"current_steps": 156270, "total_steps": 181800, "loss": 0.0043, "lr": 2.9441384294468106e-06, "epoch": 17.191419141914192, "percentage": 85.96, "elapsed_time": "6:10:20", "remaining_time": "1:00:30", "throughput": 1484.16, "total_tokens": 32978720} {"current_steps": 156275, "total_steps": 181800, "loss": 0.0735, "lr": 2.9430085544447816e-06, "epoch": 17.191969196919693, "percentage": 85.96, "elapsed_time": "6:10:21", "remaining_time": "1:00:29", "throughput": 1484.16, "total_tokens": 32979808} {"current_steps": 156280, "total_steps": 181800, "loss": 0.0047, "lr": 2.9418788827314663e-06, "epoch": 17.19251925192519, "percentage": 85.96, "elapsed_time": "6:10:21", "remaining_time": "1:00:28", "throughput": 1484.16, "total_tokens": 32980832} {"current_steps": 156285, "total_steps": 181800, "loss": 0.0072, "lr": 2.9407494143172646e-06, "epoch": 17.193069306930692, "percentage": 85.97, "elapsed_time": "6:10:22", "remaining_time": "1:00:28", "throughput": 1484.16, "total_tokens": 32981888} {"current_steps": 156290, "total_steps": 181800, "loss": 0.0197, "lr": 2.9396201492125937e-06, "epoch": 17.193619361936193, "percentage": 85.97, "elapsed_time": "6:10:23", "remaining_time": "1:00:27", "throughput": 1484.16, "total_tokens": 32982944} {"current_steps": 156295, "total_steps": 181800, "loss": 0.0014, "lr": 2.9384910874278527e-06, "epoch": 17.194169416941694, "percentage": 85.97, "elapsed_time": "6:10:23", "remaining_time": "1:00:26", "throughput": 1484.17, "total_tokens": 32984064} {"current_steps": 156300, "total_steps": 181800, "loss": 0.0028, "lr": 2.9373622289734533e-06, "epoch": 17.194719471947195, "percentage": 85.97, "elapsed_time": "6:10:24", "remaining_time": "1:00:25", "throughput": 1484.17, "total_tokens": 32985152} {"current_steps": 156305, "total_steps": 181800, "loss": 0.0017, "lr": 2.9362335738598063e-06, "epoch": 17.195269526952696, "percentage": 85.98, "elapsed_time": "6:10:25", "remaining_time": "1:00:25", "throughput": 1484.17, "total_tokens": 32986176} {"current_steps": 156310, "total_steps": 181800, "loss": 0.0077, "lr": 2.935105122097301e-06, "epoch": 17.195819581958197, "percentage": 85.98, "elapsed_time": "6:10:26", "remaining_time": "1:00:24", "throughput": 1484.17, "total_tokens": 32987264} {"current_steps": 156315, "total_steps": 181800, "loss": 0.0744, "lr": 2.933976873696348e-06, "epoch": 17.196369636963695, "percentage": 85.98, "elapsed_time": "6:10:26", "remaining_time": "1:00:23", "throughput": 1484.17, "total_tokens": 32988320} {"current_steps": 156320, "total_steps": 181800, "loss": 0.0003, "lr": 2.9328488286673393e-06, "epoch": 17.196919691969196, "percentage": 85.98, "elapsed_time": "6:10:27", "remaining_time": "1:00:23", "throughput": 1484.17, "total_tokens": 32989312} {"current_steps": 156325, "total_steps": 181800, "loss": 0.0207, "lr": 2.9317209870206725e-06, "epoch": 17.197469746974697, "percentage": 85.99, "elapsed_time": "6:10:28", "remaining_time": "1:00:22", "throughput": 1484.18, "total_tokens": 32990432} {"current_steps": 156330, "total_steps": 181800, "loss": 0.0282, "lr": 2.93059334876675e-06, "epoch": 17.198019801980198, "percentage": 85.99, "elapsed_time": "6:10:28", "remaining_time": "1:00:21", "throughput": 1484.18, "total_tokens": 32991488} {"current_steps": 156335, "total_steps": 181800, "loss": 0.0033, "lr": 2.9294659139159518e-06, "epoch": 17.1985698569857, "percentage": 85.99, "elapsed_time": "6:10:29", "remaining_time": "1:00:20", "throughput": 1484.18, "total_tokens": 32992576} {"current_steps": 156340, "total_steps": 181800, "loss": 0.0794, "lr": 2.928338682478682e-06, "epoch": 17.1991199119912, "percentage": 86.0, "elapsed_time": "6:10:30", "remaining_time": "1:00:20", "throughput": 1484.18, "total_tokens": 32993600} {"current_steps": 156345, "total_steps": 181800, "loss": 0.0546, "lr": 2.927211654465323e-06, "epoch": 17.199669966996698, "percentage": 86.0, "elapsed_time": "6:10:30", "remaining_time": "1:00:19", "throughput": 1484.18, "total_tokens": 32994624} {"current_steps": 156350, "total_steps": 181800, "loss": 0.0031, "lr": 2.9260848298862524e-06, "epoch": 17.2002200220022, "percentage": 86.0, "elapsed_time": "6:10:31", "remaining_time": "1:00:18", "throughput": 1484.18, "total_tokens": 32995648} {"current_steps": 156355, "total_steps": 181800, "loss": 0.0292, "lr": 2.9249582087518793e-06, "epoch": 17.2007700770077, "percentage": 86.0, "elapsed_time": "6:10:32", "remaining_time": "1:00:18", "throughput": 1484.18, "total_tokens": 32996736} {"current_steps": 156360, "total_steps": 181800, "loss": 0.0308, "lr": 2.9238317910725705e-06, "epoch": 17.2013201320132, "percentage": 86.01, "elapsed_time": "6:10:32", "remaining_time": "1:00:17", "throughput": 1484.18, "total_tokens": 32997760} {"current_steps": 156365, "total_steps": 181800, "loss": 0.0089, "lr": 2.922705576858706e-06, "epoch": 17.201870187018702, "percentage": 86.01, "elapsed_time": "6:10:33", "remaining_time": "1:00:16", "throughput": 1484.19, "total_tokens": 32998816} {"current_steps": 156370, "total_steps": 181800, "loss": 0.011, "lr": 2.9215795661206746e-06, "epoch": 17.202420242024203, "percentage": 86.01, "elapsed_time": "6:10:34", "remaining_time": "1:00:15", "throughput": 1484.19, "total_tokens": 32999872} {"current_steps": 156375, "total_steps": 181800, "loss": 0.0053, "lr": 2.920453758868846e-06, "epoch": 17.202970297029704, "percentage": 86.01, "elapsed_time": "6:10:34", "remaining_time": "1:00:15", "throughput": 1484.19, "total_tokens": 33000864} {"current_steps": 156380, "total_steps": 181800, "loss": 0.0047, "lr": 2.9193281551136014e-06, "epoch": 17.203520352035202, "percentage": 86.02, "elapsed_time": "6:10:35", "remaining_time": "1:00:14", "throughput": 1484.19, "total_tokens": 33001952} {"current_steps": 156385, "total_steps": 181800, "loss": 0.0912, "lr": 2.9182027548653177e-06, "epoch": 17.204070407040703, "percentage": 86.02, "elapsed_time": "6:10:36", "remaining_time": "1:00:13", "throughput": 1484.19, "total_tokens": 33003008} {"current_steps": 156390, "total_steps": 181800, "loss": 0.0015, "lr": 2.9170775581343594e-06, "epoch": 17.204620462046204, "percentage": 86.02, "elapsed_time": "6:10:37", "remaining_time": "1:00:13", "throughput": 1484.19, "total_tokens": 33004128} {"current_steps": 156395, "total_steps": 181800, "loss": 0.0593, "lr": 2.915952564931107e-06, "epoch": 17.205170517051705, "percentage": 86.03, "elapsed_time": "6:10:37", "remaining_time": "1:00:12", "throughput": 1484.2, "total_tokens": 33005184} {"current_steps": 156400, "total_steps": 181800, "loss": 0.001, "lr": 2.914827775265916e-06, "epoch": 17.205720572057206, "percentage": 86.03, "elapsed_time": "6:10:38", "remaining_time": "1:00:11", "throughput": 1484.2, "total_tokens": 33006272} {"current_steps": 156405, "total_steps": 181800, "loss": 0.0505, "lr": 2.913703189149164e-06, "epoch": 17.206270627062707, "percentage": 86.03, "elapsed_time": "6:10:39", "remaining_time": "1:00:10", "throughput": 1484.2, "total_tokens": 33007296} {"current_steps": 156410, "total_steps": 181800, "loss": 0.0049, "lr": 2.912578806591207e-06, "epoch": 17.206820682068205, "percentage": 86.03, "elapsed_time": "6:10:39", "remaining_time": "1:00:10", "throughput": 1484.2, "total_tokens": 33008320} {"current_steps": 156415, "total_steps": 181800, "loss": 0.0056, "lr": 2.911454627602414e-06, "epoch": 17.207370737073706, "percentage": 86.04, "elapsed_time": "6:10:40", "remaining_time": "1:00:09", "throughput": 1484.2, "total_tokens": 33009376} {"current_steps": 156420, "total_steps": 181800, "loss": 0.1316, "lr": 2.9103306521931495e-06, "epoch": 17.207920792079207, "percentage": 86.04, "elapsed_time": "6:10:41", "remaining_time": "1:00:08", "throughput": 1484.2, "total_tokens": 33010400} {"current_steps": 156425, "total_steps": 181800, "loss": 0.0081, "lr": 2.9092068803737605e-06, "epoch": 17.20847084708471, "percentage": 86.04, "elapsed_time": "6:10:41", "remaining_time": "1:00:08", "throughput": 1484.2, "total_tokens": 33011456} {"current_steps": 156430, "total_steps": 181800, "loss": 0.0064, "lr": 2.9080833121546193e-06, "epoch": 17.20902090209021, "percentage": 86.05, "elapsed_time": "6:10:42", "remaining_time": "1:00:07", "throughput": 1484.2, "total_tokens": 33012512} {"current_steps": 156435, "total_steps": 181800, "loss": 0.0039, "lr": 2.9069599475460673e-06, "epoch": 17.20957095709571, "percentage": 86.05, "elapsed_time": "6:10:43", "remaining_time": "1:00:06", "throughput": 1484.2, "total_tokens": 33013536} {"current_steps": 156440, "total_steps": 181800, "loss": 0.0047, "lr": 2.9058367865584637e-06, "epoch": 17.21012101210121, "percentage": 86.05, "elapsed_time": "6:10:43", "remaining_time": "1:00:05", "throughput": 1484.2, "total_tokens": 33014528} {"current_steps": 156445, "total_steps": 181800, "loss": 0.0089, "lr": 2.904713829202166e-06, "epoch": 17.21067106710671, "percentage": 86.05, "elapsed_time": "6:10:44", "remaining_time": "1:00:05", "throughput": 1484.2, "total_tokens": 33015552} {"current_steps": 156450, "total_steps": 181800, "loss": 0.0588, "lr": 2.9035910754875136e-06, "epoch": 17.21122112211221, "percentage": 86.06, "elapsed_time": "6:10:45", "remaining_time": "1:00:04", "throughput": 1484.2, "total_tokens": 33016544} {"current_steps": 156455, "total_steps": 181800, "loss": 0.0014, "lr": 2.9024685254248648e-06, "epoch": 17.21177117711771, "percentage": 86.06, "elapsed_time": "6:10:46", "remaining_time": "1:00:03", "throughput": 1484.2, "total_tokens": 33017632} {"current_steps": 156460, "total_steps": 181800, "loss": 0.004, "lr": 2.9013461790245584e-06, "epoch": 17.212321232123212, "percentage": 86.06, "elapsed_time": "6:10:46", "remaining_time": "1:00:03", "throughput": 1484.2, "total_tokens": 33018656} {"current_steps": 156465, "total_steps": 181800, "loss": 0.0004, "lr": 2.9002240362969364e-06, "epoch": 17.212871287128714, "percentage": 86.06, "elapsed_time": "6:10:47", "remaining_time": "1:00:02", "throughput": 1484.2, "total_tokens": 33019744} {"current_steps": 156470, "total_steps": 181800, "loss": 0.0061, "lr": 2.8991020972523457e-06, "epoch": 17.213421342134215, "percentage": 86.07, "elapsed_time": "6:10:48", "remaining_time": "1:00:01", "throughput": 1484.2, "total_tokens": 33020768} {"current_steps": 156475, "total_steps": 181800, "loss": 0.0017, "lr": 2.897980361901126e-06, "epoch": 17.213971397139716, "percentage": 86.07, "elapsed_time": "6:10:48", "remaining_time": "1:00:00", "throughput": 1484.2, "total_tokens": 33021792} {"current_steps": 156480, "total_steps": 181800, "loss": 0.0053, "lr": 2.896858830253621e-06, "epoch": 17.214521452145213, "percentage": 86.07, "elapsed_time": "6:10:49", "remaining_time": "1:00:00", "throughput": 1484.21, "total_tokens": 33022848} {"current_steps": 156485, "total_steps": 181800, "loss": 0.1088, "lr": 2.895737502320159e-06, "epoch": 17.215071507150714, "percentage": 86.08, "elapsed_time": "6:10:50", "remaining_time": "0:59:59", "throughput": 1484.21, "total_tokens": 33023936} {"current_steps": 156490, "total_steps": 181800, "loss": 0.0713, "lr": 2.8946163781110758e-06, "epoch": 17.215621562156215, "percentage": 86.08, "elapsed_time": "6:10:50", "remaining_time": "0:59:58", "throughput": 1484.21, "total_tokens": 33024928} {"current_steps": 156495, "total_steps": 181800, "loss": 0.0006, "lr": 2.893495457636705e-06, "epoch": 17.216171617161717, "percentage": 86.08, "elapsed_time": "6:10:51", "remaining_time": "0:59:58", "throughput": 1484.21, "total_tokens": 33026048} {"current_steps": 156500, "total_steps": 181800, "loss": 0.0494, "lr": 2.8923747409073805e-06, "epoch": 17.216721672167218, "percentage": 86.08, "elapsed_time": "6:10:52", "remaining_time": "0:59:57", "throughput": 1484.21, "total_tokens": 33027072} {"current_steps": 156505, "total_steps": 181800, "loss": 0.0294, "lr": 2.891254227933432e-06, "epoch": 17.21727172717272, "percentage": 86.09, "elapsed_time": "6:10:52", "remaining_time": "0:59:56", "throughput": 1484.21, "total_tokens": 33028096} {"current_steps": 156510, "total_steps": 181800, "loss": 0.0029, "lr": 2.890133918725188e-06, "epoch": 17.217821782178216, "percentage": 86.09, "elapsed_time": "6:10:53", "remaining_time": "0:59:55", "throughput": 1484.21, "total_tokens": 33029088} {"current_steps": 156515, "total_steps": 181800, "loss": 0.0057, "lr": 2.8890138132929622e-06, "epoch": 17.218371837183717, "percentage": 86.09, "elapsed_time": "6:10:54", "remaining_time": "0:59:55", "throughput": 1484.22, "total_tokens": 33030240} {"current_steps": 156520, "total_steps": 181800, "loss": 0.0016, "lr": 2.887893911647091e-06, "epoch": 17.21892189218922, "percentage": 86.09, "elapsed_time": "6:10:55", "remaining_time": "0:59:54", "throughput": 1484.22, "total_tokens": 33031264} {"current_steps": 156525, "total_steps": 181800, "loss": 0.1692, "lr": 2.886774213797888e-06, "epoch": 17.21947194719472, "percentage": 86.1, "elapsed_time": "6:10:55", "remaining_time": "0:59:53", "throughput": 1484.21, "total_tokens": 33032288} {"current_steps": 156530, "total_steps": 181800, "loss": 0.0091, "lr": 2.885654719755676e-06, "epoch": 17.22002200220022, "percentage": 86.1, "elapsed_time": "6:10:56", "remaining_time": "0:59:53", "throughput": 1484.22, "total_tokens": 33033376} {"current_steps": 156535, "total_steps": 181800, "loss": 0.0109, "lr": 2.884535429530777e-06, "epoch": 17.22057205720572, "percentage": 86.1, "elapsed_time": "6:10:57", "remaining_time": "0:59:52", "throughput": 1484.22, "total_tokens": 33034432} {"current_steps": 156540, "total_steps": 181800, "loss": 0.0417, "lr": 2.8834163431334995e-06, "epoch": 17.221122112211223, "percentage": 86.11, "elapsed_time": "6:10:57", "remaining_time": "0:59:51", "throughput": 1484.22, "total_tokens": 33035488} {"current_steps": 156545, "total_steps": 181800, "loss": 0.0014, "lr": 2.8822974605741655e-06, "epoch": 17.22167216721672, "percentage": 86.11, "elapsed_time": "6:10:58", "remaining_time": "0:59:50", "throughput": 1484.22, "total_tokens": 33036544} {"current_steps": 156550, "total_steps": 181800, "loss": 0.0023, "lr": 2.8811787818630754e-06, "epoch": 17.22222222222222, "percentage": 86.11, "elapsed_time": "6:10:59", "remaining_time": "0:59:50", "throughput": 1484.22, "total_tokens": 33037504} {"current_steps": 156555, "total_steps": 181800, "loss": 0.0187, "lr": 2.880060307010549e-06, "epoch": 17.222772277227723, "percentage": 86.11, "elapsed_time": "6:10:59", "remaining_time": "0:59:49", "throughput": 1484.22, "total_tokens": 33038528} {"current_steps": 156560, "total_steps": 181800, "loss": 0.0048, "lr": 2.8789420360268964e-06, "epoch": 17.223322332233224, "percentage": 86.12, "elapsed_time": "6:11:00", "remaining_time": "0:59:48", "throughput": 1484.22, "total_tokens": 33039552} {"current_steps": 156565, "total_steps": 181800, "loss": 0.048, "lr": 2.8778239689224163e-06, "epoch": 17.223872387238725, "percentage": 86.12, "elapsed_time": "6:11:01", "remaining_time": "0:59:48", "throughput": 1484.22, "total_tokens": 33040640} {"current_steps": 156570, "total_steps": 181800, "loss": 0.0037, "lr": 2.8767061057074245e-06, "epoch": 17.224422442244226, "percentage": 86.12, "elapsed_time": "6:11:01", "remaining_time": "0:59:47", "throughput": 1484.22, "total_tokens": 33041632} {"current_steps": 156575, "total_steps": 181800, "loss": 0.0337, "lr": 2.8755884463922134e-06, "epoch": 17.224972497249723, "percentage": 86.12, "elapsed_time": "6:11:02", "remaining_time": "0:59:46", "throughput": 1484.22, "total_tokens": 33042720} {"current_steps": 156580, "total_steps": 181800, "loss": 0.0681, "lr": 2.8744709909870824e-06, "epoch": 17.225522552255224, "percentage": 86.13, "elapsed_time": "6:11:03", "remaining_time": "0:59:45", "throughput": 1484.23, "total_tokens": 33043840} {"current_steps": 156585, "total_steps": 181800, "loss": 0.008, "lr": 2.873353739502338e-06, "epoch": 17.226072607260726, "percentage": 86.13, "elapsed_time": "6:11:04", "remaining_time": "0:59:45", "throughput": 1484.23, "total_tokens": 33044928} {"current_steps": 156590, "total_steps": 181800, "loss": 0.0013, "lr": 2.872236691948271e-06, "epoch": 17.226622662266227, "percentage": 86.13, "elapsed_time": "6:11:04", "remaining_time": "0:59:44", "throughput": 1484.23, "total_tokens": 33045952} {"current_steps": 156595, "total_steps": 181800, "loss": 0.053, "lr": 2.8711198483351882e-06, "epoch": 17.227172717271728, "percentage": 86.14, "elapsed_time": "6:11:05", "remaining_time": "0:59:43", "throughput": 1484.23, "total_tokens": 33046976} {"current_steps": 156600, "total_steps": 181800, "loss": 0.0016, "lr": 2.8700032086733745e-06, "epoch": 17.22772277227723, "percentage": 86.14, "elapsed_time": "6:11:06", "remaining_time": "0:59:43", "throughput": 1484.23, "total_tokens": 33048064} {"current_steps": 156605, "total_steps": 181800, "loss": 0.0032, "lr": 2.8688867729731172e-06, "epoch": 17.22827282728273, "percentage": 86.14, "elapsed_time": "6:11:06", "remaining_time": "0:59:42", "throughput": 1484.23, "total_tokens": 33049056} {"current_steps": 156610, "total_steps": 181800, "loss": 0.0488, "lr": 2.867770541244713e-06, "epoch": 17.228822882288227, "percentage": 86.14, "elapsed_time": "6:11:07", "remaining_time": "0:59:41", "throughput": 1484.23, "total_tokens": 33050112} {"current_steps": 156615, "total_steps": 181800, "loss": 0.0716, "lr": 2.8666545134984455e-06, "epoch": 17.22937293729373, "percentage": 86.15, "elapsed_time": "6:11:08", "remaining_time": "0:59:40", "throughput": 1484.23, "total_tokens": 33051136} {"current_steps": 156620, "total_steps": 181800, "loss": 0.0084, "lr": 2.8655386897446067e-06, "epoch": 17.22992299229923, "percentage": 86.15, "elapsed_time": "6:11:08", "remaining_time": "0:59:40", "throughput": 1484.23, "total_tokens": 33052160} {"current_steps": 156625, "total_steps": 181800, "loss": 0.003, "lr": 2.86442306999348e-06, "epoch": 17.23047304730473, "percentage": 86.15, "elapsed_time": "6:11:09", "remaining_time": "0:59:39", "throughput": 1484.24, "total_tokens": 33053184} {"current_steps": 156630, "total_steps": 181800, "loss": 0.0037, "lr": 2.863307654255337e-06, "epoch": 17.231023102310232, "percentage": 86.16, "elapsed_time": "6:11:10", "remaining_time": "0:59:38", "throughput": 1484.24, "total_tokens": 33054208} {"current_steps": 156635, "total_steps": 181800, "loss": 0.0359, "lr": 2.8621924425404708e-06, "epoch": 17.231573157315733, "percentage": 86.16, "elapsed_time": "6:11:10", "remaining_time": "0:59:38", "throughput": 1484.23, "total_tokens": 33055168} {"current_steps": 156640, "total_steps": 181800, "loss": 0.0327, "lr": 2.861077434859147e-06, "epoch": 17.23212321232123, "percentage": 86.16, "elapsed_time": "6:11:11", "remaining_time": "0:59:37", "throughput": 1484.23, "total_tokens": 33056192} {"current_steps": 156645, "total_steps": 181800, "loss": 0.0112, "lr": 2.8599626312216522e-06, "epoch": 17.23267326732673, "percentage": 86.16, "elapsed_time": "6:11:12", "remaining_time": "0:59:36", "throughput": 1484.23, "total_tokens": 33057248} {"current_steps": 156650, "total_steps": 181800, "loss": 0.0072, "lr": 2.8588480316382617e-06, "epoch": 17.233223322332233, "percentage": 86.17, "elapsed_time": "6:11:12", "remaining_time": "0:59:35", "throughput": 1484.23, "total_tokens": 33058272} {"current_steps": 156655, "total_steps": 181800, "loss": 0.0044, "lr": 2.857733636119239e-06, "epoch": 17.233773377337734, "percentage": 86.17, "elapsed_time": "6:11:13", "remaining_time": "0:59:35", "throughput": 1484.23, "total_tokens": 33059328} {"current_steps": 156660, "total_steps": 181800, "loss": 0.0377, "lr": 2.8566194446748656e-06, "epoch": 17.234323432343235, "percentage": 86.17, "elapsed_time": "6:11:14", "remaining_time": "0:59:34", "throughput": 1484.24, "total_tokens": 33060384} {"current_steps": 156665, "total_steps": 181800, "loss": 0.0036, "lr": 2.8555054573153993e-06, "epoch": 17.234873487348736, "percentage": 86.17, "elapsed_time": "6:11:15", "remaining_time": "0:59:33", "throughput": 1484.24, "total_tokens": 33061408} {"current_steps": 156670, "total_steps": 181800, "loss": 0.0041, "lr": 2.8543916740511157e-06, "epoch": 17.235423542354237, "percentage": 86.18, "elapsed_time": "6:11:15", "remaining_time": "0:59:33", "throughput": 1484.24, "total_tokens": 33062464} {"current_steps": 156675, "total_steps": 181800, "loss": 0.0032, "lr": 2.8532780948922812e-06, "epoch": 17.235973597359735, "percentage": 86.18, "elapsed_time": "6:11:16", "remaining_time": "0:59:32", "throughput": 1484.24, "total_tokens": 33063456} {"current_steps": 156680, "total_steps": 181800, "loss": 0.0058, "lr": 2.8521647198491514e-06, "epoch": 17.236523652365236, "percentage": 86.18, "elapsed_time": "6:11:17", "remaining_time": "0:59:31", "throughput": 1484.24, "total_tokens": 33064512} {"current_steps": 156685, "total_steps": 181800, "loss": 0.0062, "lr": 2.851051548931996e-06, "epoch": 17.237073707370737, "percentage": 86.19, "elapsed_time": "6:11:17", "remaining_time": "0:59:30", "throughput": 1484.24, "total_tokens": 33065568} {"current_steps": 156690, "total_steps": 181800, "loss": 0.0136, "lr": 2.8499385821510654e-06, "epoch": 17.237623762376238, "percentage": 86.19, "elapsed_time": "6:11:18", "remaining_time": "0:59:30", "throughput": 1484.24, "total_tokens": 33066656} {"current_steps": 156695, "total_steps": 181800, "loss": 0.0794, "lr": 2.848825819516629e-06, "epoch": 17.23817381738174, "percentage": 86.19, "elapsed_time": "6:11:19", "remaining_time": "0:59:29", "throughput": 1484.24, "total_tokens": 33067712} {"current_steps": 156700, "total_steps": 181800, "loss": 0.0032, "lr": 2.8477132610389284e-06, "epoch": 17.23872387238724, "percentage": 86.19, "elapsed_time": "6:11:19", "remaining_time": "0:59:28", "throughput": 1484.24, "total_tokens": 33068736} {"current_steps": 156705, "total_steps": 181800, "loss": 0.0023, "lr": 2.8466009067282252e-06, "epoch": 17.239273927392738, "percentage": 86.2, "elapsed_time": "6:11:20", "remaining_time": "0:59:28", "throughput": 1484.25, "total_tokens": 33069824} {"current_steps": 156710, "total_steps": 181800, "loss": 0.0491, "lr": 2.8454887565947776e-06, "epoch": 17.23982398239824, "percentage": 86.2, "elapsed_time": "6:11:21", "remaining_time": "0:59:27", "throughput": 1484.25, "total_tokens": 33070944} {"current_steps": 156715, "total_steps": 181800, "loss": 0.0198, "lr": 2.8443768106488215e-06, "epoch": 17.24037403740374, "percentage": 86.2, "elapsed_time": "6:11:21", "remaining_time": "0:59:26", "throughput": 1484.25, "total_tokens": 33071968} {"current_steps": 156720, "total_steps": 181800, "loss": 0.0051, "lr": 2.8432650689006216e-06, "epoch": 17.24092409240924, "percentage": 86.2, "elapsed_time": "6:11:22", "remaining_time": "0:59:25", "throughput": 1484.25, "total_tokens": 33073088} {"current_steps": 156725, "total_steps": 181800, "loss": 0.0012, "lr": 2.8421535313604085e-06, "epoch": 17.241474147414742, "percentage": 86.21, "elapsed_time": "6:11:23", "remaining_time": "0:59:25", "throughput": 1484.25, "total_tokens": 33074080} {"current_steps": 156730, "total_steps": 181800, "loss": 0.0364, "lr": 2.841042198038435e-06, "epoch": 17.242024202420243, "percentage": 86.21, "elapsed_time": "6:11:24", "remaining_time": "0:59:24", "throughput": 1484.25, "total_tokens": 33075104} {"current_steps": 156735, "total_steps": 181800, "loss": 0.0558, "lr": 2.839931068944948e-06, "epoch": 17.242574257425744, "percentage": 86.21, "elapsed_time": "6:11:24", "remaining_time": "0:59:23", "throughput": 1484.25, "total_tokens": 33076128} {"current_steps": 156740, "total_steps": 181800, "loss": 0.0247, "lr": 2.838820144090182e-06, "epoch": 17.24312431243124, "percentage": 86.22, "elapsed_time": "6:11:25", "remaining_time": "0:59:23", "throughput": 1484.26, "total_tokens": 33077248} {"current_steps": 156745, "total_steps": 181800, "loss": 0.108, "lr": 2.837709423484372e-06, "epoch": 17.243674367436743, "percentage": 86.22, "elapsed_time": "6:11:26", "remaining_time": "0:59:22", "throughput": 1484.26, "total_tokens": 33078304} {"current_steps": 156750, "total_steps": 181800, "loss": 0.0041, "lr": 2.8365989071377636e-06, "epoch": 17.244224422442244, "percentage": 86.22, "elapsed_time": "6:11:26", "remaining_time": "0:59:21", "throughput": 1484.26, "total_tokens": 33079328} {"current_steps": 156755, "total_steps": 181800, "loss": 0.0764, "lr": 2.835488595060584e-06, "epoch": 17.244774477447745, "percentage": 86.22, "elapsed_time": "6:11:27", "remaining_time": "0:59:20", "throughput": 1484.26, "total_tokens": 33080352} {"current_steps": 156760, "total_steps": 181800, "loss": 0.0098, "lr": 2.834378487263073e-06, "epoch": 17.245324532453246, "percentage": 86.23, "elapsed_time": "6:11:28", "remaining_time": "0:59:20", "throughput": 1484.26, "total_tokens": 33081408} {"current_steps": 156765, "total_steps": 181800, "loss": 0.0046, "lr": 2.8332685837554608e-06, "epoch": 17.245874587458747, "percentage": 86.23, "elapsed_time": "6:11:28", "remaining_time": "0:59:19", "throughput": 1484.26, "total_tokens": 33082464} {"current_steps": 156770, "total_steps": 181800, "loss": 0.0026, "lr": 2.8321588845479724e-06, "epoch": 17.246424642464245, "percentage": 86.23, "elapsed_time": "6:11:29", "remaining_time": "0:59:18", "throughput": 1484.26, "total_tokens": 33083456} {"current_steps": 156775, "total_steps": 181800, "loss": 0.1165, "lr": 2.8310493896508415e-06, "epoch": 17.246974697469746, "percentage": 86.23, "elapsed_time": "6:11:30", "remaining_time": "0:59:18", "throughput": 1484.26, "total_tokens": 33084480} {"current_steps": 156780, "total_steps": 181800, "loss": 0.0043, "lr": 2.829940099074288e-06, "epoch": 17.247524752475247, "percentage": 86.24, "elapsed_time": "6:11:30", "remaining_time": "0:59:17", "throughput": 1484.26, "total_tokens": 33085504} {"current_steps": 156785, "total_steps": 181800, "loss": 0.0031, "lr": 2.828831012828537e-06, "epoch": 17.248074807480748, "percentage": 86.24, "elapsed_time": "6:11:31", "remaining_time": "0:59:16", "throughput": 1484.26, "total_tokens": 33086560} {"current_steps": 156790, "total_steps": 181800, "loss": 0.0583, "lr": 2.8277221309238157e-06, "epoch": 17.24862486248625, "percentage": 86.24, "elapsed_time": "6:11:32", "remaining_time": "0:59:15", "throughput": 1484.26, "total_tokens": 33087616} {"current_steps": 156795, "total_steps": 181800, "loss": 0.0591, "lr": 2.8266134533703386e-06, "epoch": 17.24917491749175, "percentage": 86.25, "elapsed_time": "6:11:33", "remaining_time": "0:59:15", "throughput": 1484.27, "total_tokens": 33088736} {"current_steps": 156800, "total_steps": 181800, "loss": 0.0351, "lr": 2.8255049801783285e-06, "epoch": 17.24972497249725, "percentage": 86.25, "elapsed_time": "6:11:33", "remaining_time": "0:59:14", "throughput": 1484.27, "total_tokens": 33089856} {"current_steps": 156805, "total_steps": 181800, "loss": 0.095, "lr": 2.8243967113579934e-06, "epoch": 17.25027502750275, "percentage": 86.25, "elapsed_time": "6:11:34", "remaining_time": "0:59:13", "throughput": 1484.27, "total_tokens": 33090880} {"current_steps": 156810, "total_steps": 181800, "loss": 0.0083, "lr": 2.8232886469195587e-06, "epoch": 17.25082508250825, "percentage": 86.25, "elapsed_time": "6:11:35", "remaining_time": "0:59:13", "throughput": 1484.27, "total_tokens": 33092000} {"current_steps": 156815, "total_steps": 181800, "loss": 0.0287, "lr": 2.8221807868732243e-06, "epoch": 17.25137513751375, "percentage": 86.26, "elapsed_time": "6:11:35", "remaining_time": "0:59:12", "throughput": 1484.27, "total_tokens": 33093024} {"current_steps": 156820, "total_steps": 181800, "loss": 0.0009, "lr": 2.821073131229207e-06, "epoch": 17.251925192519252, "percentage": 86.26, "elapsed_time": "6:11:36", "remaining_time": "0:59:11", "throughput": 1484.28, "total_tokens": 33094112} {"current_steps": 156825, "total_steps": 181800, "loss": 0.0036, "lr": 2.819965679997724e-06, "epoch": 17.252475247524753, "percentage": 86.26, "elapsed_time": "6:11:37", "remaining_time": "0:59:10", "throughput": 1484.28, "total_tokens": 33095136} {"current_steps": 156830, "total_steps": 181800, "loss": 0.0047, "lr": 2.81885843318897e-06, "epoch": 17.253025302530254, "percentage": 86.27, "elapsed_time": "6:11:37", "remaining_time": "0:59:10", "throughput": 1484.28, "total_tokens": 33096192} {"current_steps": 156835, "total_steps": 181800, "loss": 0.0019, "lr": 2.817751390813156e-06, "epoch": 17.253575357535752, "percentage": 86.27, "elapsed_time": "6:11:38", "remaining_time": "0:59:09", "throughput": 1484.28, "total_tokens": 33097248} {"current_steps": 156840, "total_steps": 181800, "loss": 0.0632, "lr": 2.816644552880479e-06, "epoch": 17.254125412541253, "percentage": 86.27, "elapsed_time": "6:11:39", "remaining_time": "0:59:08", "throughput": 1484.28, "total_tokens": 33098272} {"current_steps": 156845, "total_steps": 181800, "loss": 0.0191, "lr": 2.8155379194011455e-06, "epoch": 17.254675467546754, "percentage": 86.27, "elapsed_time": "6:11:39", "remaining_time": "0:59:08", "throughput": 1484.28, "total_tokens": 33099328} {"current_steps": 156850, "total_steps": 181800, "loss": 0.0172, "lr": 2.814431490385361e-06, "epoch": 17.255225522552255, "percentage": 86.28, "elapsed_time": "6:11:40", "remaining_time": "0:59:07", "throughput": 1484.28, "total_tokens": 33100384} {"current_steps": 156855, "total_steps": 181800, "loss": 0.0018, "lr": 2.8133252658433084e-06, "epoch": 17.255775577557756, "percentage": 86.28, "elapsed_time": "6:11:41", "remaining_time": "0:59:06", "throughput": 1484.28, "total_tokens": 33101376} {"current_steps": 156860, "total_steps": 181800, "loss": 0.0377, "lr": 2.8122192457851942e-06, "epoch": 17.256325632563257, "percentage": 86.28, "elapsed_time": "6:11:42", "remaining_time": "0:59:05", "throughput": 1484.28, "total_tokens": 33102400} {"current_steps": 156865, "total_steps": 181800, "loss": 0.0064, "lr": 2.81111343022121e-06, "epoch": 17.25687568756876, "percentage": 86.28, "elapsed_time": "6:11:42", "remaining_time": "0:59:05", "throughput": 1484.28, "total_tokens": 33103424} {"current_steps": 156870, "total_steps": 181800, "loss": 0.0736, "lr": 2.810007819161542e-06, "epoch": 17.257425742574256, "percentage": 86.29, "elapsed_time": "6:11:43", "remaining_time": "0:59:04", "throughput": 1484.29, "total_tokens": 33104576} {"current_steps": 156875, "total_steps": 181800, "loss": 0.0085, "lr": 2.8089024126163822e-06, "epoch": 17.257975797579757, "percentage": 86.29, "elapsed_time": "6:11:44", "remaining_time": "0:59:03", "throughput": 1484.29, "total_tokens": 33105600} {"current_steps": 156880, "total_steps": 181800, "loss": 0.0014, "lr": 2.8077972105959223e-06, "epoch": 17.258525852585258, "percentage": 86.29, "elapsed_time": "6:11:44", "remaining_time": "0:59:03", "throughput": 1484.28, "total_tokens": 33106624} {"current_steps": 156885, "total_steps": 181800, "loss": 0.0693, "lr": 2.8066922131103512e-06, "epoch": 17.25907590759076, "percentage": 86.3, "elapsed_time": "6:11:45", "remaining_time": "0:59:02", "throughput": 1484.28, "total_tokens": 33107648} {"current_steps": 156890, "total_steps": 181800, "loss": 0.013, "lr": 2.80558742016985e-06, "epoch": 17.25962596259626, "percentage": 86.3, "elapsed_time": "6:11:46", "remaining_time": "0:59:01", "throughput": 1484.29, "total_tokens": 33108768} {"current_steps": 156895, "total_steps": 181800, "loss": 0.0008, "lr": 2.804482831784591e-06, "epoch": 17.26017601760176, "percentage": 86.3, "elapsed_time": "6:11:46", "remaining_time": "0:59:00", "throughput": 1484.29, "total_tokens": 33109792} {"current_steps": 156900, "total_steps": 181800, "loss": 0.0025, "lr": 2.8033784479647663e-06, "epoch": 17.260726072607262, "percentage": 86.3, "elapsed_time": "6:11:47", "remaining_time": "0:59:00", "throughput": 1484.29, "total_tokens": 33110752} {"current_steps": 156905, "total_steps": 181800, "loss": 0.0539, "lr": 2.8022742687205507e-06, "epoch": 17.26127612761276, "percentage": 86.31, "elapsed_time": "6:11:48", "remaining_time": "0:58:59", "throughput": 1484.29, "total_tokens": 33111808} {"current_steps": 156910, "total_steps": 181800, "loss": 0.002, "lr": 2.8011702940621248e-06, "epoch": 17.26182618261826, "percentage": 86.31, "elapsed_time": "6:11:48", "remaining_time": "0:58:58", "throughput": 1484.28, "total_tokens": 33112768} {"current_steps": 156915, "total_steps": 181800, "loss": 0.0018, "lr": 2.8000665239996644e-06, "epoch": 17.262376237623762, "percentage": 86.31, "elapsed_time": "6:11:49", "remaining_time": "0:58:58", "throughput": 1484.28, "total_tokens": 33113792} {"current_steps": 156920, "total_steps": 181800, "loss": 0.0053, "lr": 2.7989629585433304e-06, "epoch": 17.262926292629263, "percentage": 86.31, "elapsed_time": "6:11:50", "remaining_time": "0:58:57", "throughput": 1484.28, "total_tokens": 33114816} {"current_steps": 156925, "total_steps": 181800, "loss": 0.0217, "lr": 2.797859597703306e-06, "epoch": 17.263476347634764, "percentage": 86.32, "elapsed_time": "6:11:50", "remaining_time": "0:58:56", "throughput": 1484.29, "total_tokens": 33115904} {"current_steps": 156930, "total_steps": 181800, "loss": 0.1375, "lr": 2.7967564414897535e-06, "epoch": 17.264026402640265, "percentage": 86.32, "elapsed_time": "6:11:51", "remaining_time": "0:58:55", "throughput": 1484.29, "total_tokens": 33116928} {"current_steps": 156935, "total_steps": 181800, "loss": 0.0051, "lr": 2.795653489912839e-06, "epoch": 17.264576457645763, "percentage": 86.32, "elapsed_time": "6:11:52", "remaining_time": "0:58:55", "throughput": 1484.29, "total_tokens": 33118016} {"current_steps": 156940, "total_steps": 181800, "loss": 0.0012, "lr": 2.7945507429827405e-06, "epoch": 17.265126512651264, "percentage": 86.33, "elapsed_time": "6:11:53", "remaining_time": "0:58:54", "throughput": 1484.29, "total_tokens": 33119040} {"current_steps": 156945, "total_steps": 181800, "loss": 0.0643, "lr": 2.793448200709606e-06, "epoch": 17.265676567656765, "percentage": 86.33, "elapsed_time": "6:11:53", "remaining_time": "0:58:53", "throughput": 1484.29, "total_tokens": 33120096} {"current_steps": 156950, "total_steps": 181800, "loss": 0.0047, "lr": 2.79234586310361e-06, "epoch": 17.266226622662266, "percentage": 86.33, "elapsed_time": "6:11:54", "remaining_time": "0:58:53", "throughput": 1484.29, "total_tokens": 33121184} {"current_steps": 156955, "total_steps": 181800, "loss": 0.0052, "lr": 2.7912437301749026e-06, "epoch": 17.266776677667767, "percentage": 86.33, "elapsed_time": "6:11:55", "remaining_time": "0:58:52", "throughput": 1484.29, "total_tokens": 33122208} {"current_steps": 156960, "total_steps": 181800, "loss": 0.2685, "lr": 2.790141801933638e-06, "epoch": 17.26732673267327, "percentage": 86.34, "elapsed_time": "6:11:55", "remaining_time": "0:58:51", "throughput": 1484.3, "total_tokens": 33123264} {"current_steps": 156965, "total_steps": 181800, "loss": 0.0022, "lr": 2.7890400783899873e-06, "epoch": 17.26787678767877, "percentage": 86.34, "elapsed_time": "6:11:56", "remaining_time": "0:58:50", "throughput": 1484.3, "total_tokens": 33124320} {"current_steps": 156970, "total_steps": 181800, "loss": 0.0315, "lr": 2.787938559554093e-06, "epoch": 17.268426842684267, "percentage": 86.34, "elapsed_time": "6:11:57", "remaining_time": "0:58:50", "throughput": 1484.3, "total_tokens": 33125472} {"current_steps": 156975, "total_steps": 181800, "loss": 0.1153, "lr": 2.7868372454361136e-06, "epoch": 17.268976897689768, "percentage": 86.34, "elapsed_time": "6:11:57", "remaining_time": "0:58:49", "throughput": 1484.3, "total_tokens": 33126528} {"current_steps": 156980, "total_steps": 181800, "loss": 0.0086, "lr": 2.7857361360461994e-06, "epoch": 17.26952695269527, "percentage": 86.35, "elapsed_time": "6:11:58", "remaining_time": "0:58:48", "throughput": 1484.31, "total_tokens": 33127616} {"current_steps": 156985, "total_steps": 181800, "loss": 0.0252, "lr": 2.784635231394489e-06, "epoch": 17.27007700770077, "percentage": 86.35, "elapsed_time": "6:11:59", "remaining_time": "0:58:48", "throughput": 1484.3, "total_tokens": 33128608} {"current_steps": 156990, "total_steps": 181800, "loss": 0.2078, "lr": 2.783534531491136e-06, "epoch": 17.27062706270627, "percentage": 86.35, "elapsed_time": "6:11:59", "remaining_time": "0:58:47", "throughput": 1484.31, "total_tokens": 33129664} {"current_steps": 156995, "total_steps": 181800, "loss": 0.0066, "lr": 2.782434036346282e-06, "epoch": 17.271177117711773, "percentage": 86.36, "elapsed_time": "6:12:00", "remaining_time": "0:58:46", "throughput": 1484.31, "total_tokens": 33130720} {"current_steps": 157000, "total_steps": 181800, "loss": 0.0247, "lr": 2.78133374597008e-06, "epoch": 17.27172717271727, "percentage": 86.36, "elapsed_time": "6:12:01", "remaining_time": "0:58:45", "throughput": 1484.31, "total_tokens": 33131776} {"current_steps": 157005, "total_steps": 181800, "loss": 0.0008, "lr": 2.780233660372664e-06, "epoch": 17.27227722772277, "percentage": 86.36, "elapsed_time": "6:12:02", "remaining_time": "0:58:45", "throughput": 1484.31, "total_tokens": 33132864} {"current_steps": 157010, "total_steps": 181800, "loss": 0.0021, "lr": 2.7791337795641663e-06, "epoch": 17.272827282728272, "percentage": 86.36, "elapsed_time": "6:12:02", "remaining_time": "0:58:44", "throughput": 1484.31, "total_tokens": 33133856} {"current_steps": 157015, "total_steps": 181800, "loss": 0.0922, "lr": 2.778034103554736e-06, "epoch": 17.273377337733773, "percentage": 86.37, "elapsed_time": "6:12:03", "remaining_time": "0:58:43", "throughput": 1484.31, "total_tokens": 33134848} {"current_steps": 157020, "total_steps": 181800, "loss": 0.0008, "lr": 2.7769346323544916e-06, "epoch": 17.273927392739274, "percentage": 86.37, "elapsed_time": "6:12:04", "remaining_time": "0:58:43", "throughput": 1484.31, "total_tokens": 33135904} {"current_steps": 157025, "total_steps": 181800, "loss": 0.0572, "lr": 2.7758353659735865e-06, "epoch": 17.274477447744776, "percentage": 86.37, "elapsed_time": "6:12:04", "remaining_time": "0:58:42", "throughput": 1484.31, "total_tokens": 33136960} {"current_steps": 157030, "total_steps": 181800, "loss": 0.0021, "lr": 2.774736304422143e-06, "epoch": 17.275027502750277, "percentage": 86.38, "elapsed_time": "6:12:05", "remaining_time": "0:58:41", "throughput": 1484.31, "total_tokens": 33137952} {"current_steps": 157035, "total_steps": 181800, "loss": 0.0995, "lr": 2.7736374477102837e-06, "epoch": 17.275577557755774, "percentage": 86.38, "elapsed_time": "6:12:06", "remaining_time": "0:58:40", "throughput": 1484.31, "total_tokens": 33139072} {"current_steps": 157040, "total_steps": 181800, "loss": 0.0536, "lr": 2.772538795848151e-06, "epoch": 17.276127612761275, "percentage": 86.38, "elapsed_time": "6:12:06", "remaining_time": "0:58:40", "throughput": 1484.31, "total_tokens": 33140096} {"current_steps": 157045, "total_steps": 181800, "loss": 0.0628, "lr": 2.7714403488458552e-06, "epoch": 17.276677667766776, "percentage": 86.38, "elapsed_time": "6:12:07", "remaining_time": "0:58:39", "throughput": 1484.31, "total_tokens": 33141088} {"current_steps": 157050, "total_steps": 181800, "loss": 0.1045, "lr": 2.770342106713528e-06, "epoch": 17.277227722772277, "percentage": 86.39, "elapsed_time": "6:12:08", "remaining_time": "0:58:38", "throughput": 1484.31, "total_tokens": 33142112} {"current_steps": 157055, "total_steps": 181800, "loss": 0.0118, "lr": 2.7692440694612964e-06, "epoch": 17.27777777777778, "percentage": 86.39, "elapsed_time": "6:12:08", "remaining_time": "0:58:38", "throughput": 1484.32, "total_tokens": 33143168} {"current_steps": 157060, "total_steps": 181800, "loss": 0.0011, "lr": 2.7681462370992673e-06, "epoch": 17.27832783278328, "percentage": 86.39, "elapsed_time": "6:12:09", "remaining_time": "0:58:37", "throughput": 1484.32, "total_tokens": 33144256} {"current_steps": 157065, "total_steps": 181800, "loss": 0.002, "lr": 2.7670486096375735e-06, "epoch": 17.278877887788777, "percentage": 86.39, "elapsed_time": "6:12:10", "remaining_time": "0:58:36", "throughput": 1484.32, "total_tokens": 33145280} {"current_steps": 157070, "total_steps": 181800, "loss": 0.0029, "lr": 2.7659511870863185e-06, "epoch": 17.27942794279428, "percentage": 86.4, "elapsed_time": "6:12:10", "remaining_time": "0:58:35", "throughput": 1484.32, "total_tokens": 33146240} {"current_steps": 157075, "total_steps": 181800, "loss": 0.0026, "lr": 2.7648539694556302e-06, "epoch": 17.27997799779978, "percentage": 86.4, "elapsed_time": "6:12:11", "remaining_time": "0:58:35", "throughput": 1484.32, "total_tokens": 33147296} {"current_steps": 157080, "total_steps": 181800, "loss": 0.0061, "lr": 2.763756956755606e-06, "epoch": 17.28052805280528, "percentage": 86.4, "elapsed_time": "6:12:12", "remaining_time": "0:58:34", "throughput": 1484.32, "total_tokens": 33148320} {"current_steps": 157085, "total_steps": 181800, "loss": 0.0553, "lr": 2.762660148996363e-06, "epoch": 17.28107810781078, "percentage": 86.41, "elapsed_time": "6:12:13", "remaining_time": "0:58:33", "throughput": 1484.32, "total_tokens": 33149344} {"current_steps": 157090, "total_steps": 181800, "loss": 0.0226, "lr": 2.7615635461880172e-06, "epoch": 17.281628162816283, "percentage": 86.41, "elapsed_time": "6:12:13", "remaining_time": "0:58:33", "throughput": 1484.32, "total_tokens": 33150496} {"current_steps": 157095, "total_steps": 181800, "loss": 0.0092, "lr": 2.7604671483406647e-06, "epoch": 17.282178217821784, "percentage": 86.41, "elapsed_time": "6:12:14", "remaining_time": "0:58:32", "throughput": 1484.33, "total_tokens": 33151552} {"current_steps": 157100, "total_steps": 181800, "loss": 0.003, "lr": 2.759370955464419e-06, "epoch": 17.28272827282728, "percentage": 86.41, "elapsed_time": "6:12:15", "remaining_time": "0:58:31", "throughput": 1484.33, "total_tokens": 33152576} {"current_steps": 157105, "total_steps": 181800, "loss": 0.0327, "lr": 2.758274967569374e-06, "epoch": 17.283278327832782, "percentage": 86.42, "elapsed_time": "6:12:15", "remaining_time": "0:58:30", "throughput": 1484.33, "total_tokens": 33153728} {"current_steps": 157110, "total_steps": 181800, "loss": 0.0067, "lr": 2.757179184665637e-06, "epoch": 17.283828382838283, "percentage": 86.42, "elapsed_time": "6:12:16", "remaining_time": "0:58:30", "throughput": 1484.33, "total_tokens": 33154784} {"current_steps": 157115, "total_steps": 181800, "loss": 0.0016, "lr": 2.75608360676331e-06, "epoch": 17.284378437843785, "percentage": 86.42, "elapsed_time": "6:12:17", "remaining_time": "0:58:29", "throughput": 1484.33, "total_tokens": 33155840} {"current_steps": 157120, "total_steps": 181800, "loss": 0.0052, "lr": 2.7549882338724823e-06, "epoch": 17.284928492849286, "percentage": 86.42, "elapsed_time": "6:12:17", "remaining_time": "0:58:28", "throughput": 1484.33, "total_tokens": 33156832} {"current_steps": 157125, "total_steps": 181800, "loss": 0.0128, "lr": 2.7538930660032603e-06, "epoch": 17.285478547854787, "percentage": 86.43, "elapsed_time": "6:12:18", "remaining_time": "0:58:28", "throughput": 1484.33, "total_tokens": 33157888} {"current_steps": 157130, "total_steps": 181800, "loss": 0.0385, "lr": 2.7527981031657298e-06, "epoch": 17.286028602860284, "percentage": 86.43, "elapsed_time": "6:12:19", "remaining_time": "0:58:27", "throughput": 1484.33, "total_tokens": 33158912} {"current_steps": 157135, "total_steps": 181800, "loss": 0.0006, "lr": 2.7517033453699743e-06, "epoch": 17.286578657865785, "percentage": 86.43, "elapsed_time": "6:12:19", "remaining_time": "0:58:26", "throughput": 1484.33, "total_tokens": 33159968} {"current_steps": 157140, "total_steps": 181800, "loss": 0.0534, "lr": 2.7506087926261027e-06, "epoch": 17.287128712871286, "percentage": 86.44, "elapsed_time": "6:12:20", "remaining_time": "0:58:25", "throughput": 1484.33, "total_tokens": 33160992} {"current_steps": 157145, "total_steps": 181800, "loss": 0.0051, "lr": 2.7495144449441927e-06, "epoch": 17.287678767876788, "percentage": 86.44, "elapsed_time": "6:12:21", "remaining_time": "0:58:25", "throughput": 1484.34, "total_tokens": 33162048} {"current_steps": 157150, "total_steps": 181800, "loss": 0.2267, "lr": 2.7484203023343285e-06, "epoch": 17.28822882288229, "percentage": 86.44, "elapsed_time": "6:12:22", "remaining_time": "0:58:24", "throughput": 1484.34, "total_tokens": 33163104} {"current_steps": 157155, "total_steps": 181800, "loss": 0.0895, "lr": 2.747326364806599e-06, "epoch": 17.28877887788779, "percentage": 86.44, "elapsed_time": "6:12:22", "remaining_time": "0:58:23", "throughput": 1484.34, "total_tokens": 33164192} {"current_steps": 157160, "total_steps": 181800, "loss": 0.0007, "lr": 2.746232632371082e-06, "epoch": 17.28932893289329, "percentage": 86.45, "elapsed_time": "6:12:23", "remaining_time": "0:58:23", "throughput": 1484.34, "total_tokens": 33165216} {"current_steps": 157165, "total_steps": 181800, "loss": 0.0027, "lr": 2.745139105037861e-06, "epoch": 17.28987898789879, "percentage": 86.45, "elapsed_time": "6:12:24", "remaining_time": "0:58:22", "throughput": 1484.34, "total_tokens": 33166240} {"current_steps": 157170, "total_steps": 181800, "loss": 0.0022, "lr": 2.7440457828170172e-06, "epoch": 17.29042904290429, "percentage": 86.45, "elapsed_time": "6:12:24", "remaining_time": "0:58:21", "throughput": 1484.34, "total_tokens": 33167296} {"current_steps": 157175, "total_steps": 181800, "loss": 0.0044, "lr": 2.7429526657186206e-06, "epoch": 17.29097909790979, "percentage": 86.45, "elapsed_time": "6:12:25", "remaining_time": "0:58:20", "throughput": 1484.34, "total_tokens": 33168384} {"current_steps": 157180, "total_steps": 181800, "loss": 0.0015, "lr": 2.7418597537527514e-06, "epoch": 17.29152915291529, "percentage": 86.46, "elapsed_time": "6:12:26", "remaining_time": "0:58:20", "throughput": 1484.34, "total_tokens": 33169440} {"current_steps": 157185, "total_steps": 181800, "loss": 0.0948, "lr": 2.7407670469294765e-06, "epoch": 17.292079207920793, "percentage": 86.46, "elapsed_time": "6:12:26", "remaining_time": "0:58:19", "throughput": 1484.35, "total_tokens": 33170560} {"current_steps": 157190, "total_steps": 181800, "loss": 0.0064, "lr": 2.7396745452588775e-06, "epoch": 17.292629262926294, "percentage": 86.46, "elapsed_time": "6:12:27", "remaining_time": "0:58:18", "throughput": 1484.35, "total_tokens": 33171616} {"current_steps": 157195, "total_steps": 181800, "loss": 0.0026, "lr": 2.738582248751012e-06, "epoch": 17.293179317931795, "percentage": 86.47, "elapsed_time": "6:12:28", "remaining_time": "0:58:18", "throughput": 1484.36, "total_tokens": 33172736} {"current_steps": 157200, "total_steps": 181800, "loss": 0.0007, "lr": 2.7374901574159506e-06, "epoch": 17.293729372937293, "percentage": 86.47, "elapsed_time": "6:12:28", "remaining_time": "0:58:17", "throughput": 1484.35, "total_tokens": 33173728} {"current_steps": 157205, "total_steps": 181800, "loss": 0.0012, "lr": 2.7363982712637626e-06, "epoch": 17.294279427942794, "percentage": 86.47, "elapsed_time": "6:12:29", "remaining_time": "0:58:16", "throughput": 1484.36, "total_tokens": 33174816} {"current_steps": 157210, "total_steps": 181800, "loss": 0.004, "lr": 2.7353065903045065e-06, "epoch": 17.294829482948295, "percentage": 86.47, "elapsed_time": "6:12:30", "remaining_time": "0:58:15", "throughput": 1484.36, "total_tokens": 33175840} {"current_steps": 157215, "total_steps": 181800, "loss": 0.0318, "lr": 2.7342151145482497e-06, "epoch": 17.295379537953796, "percentage": 86.48, "elapsed_time": "6:12:31", "remaining_time": "0:58:15", "throughput": 1484.34, "total_tokens": 33176864} {"current_steps": 157220, "total_steps": 181800, "loss": 0.0528, "lr": 2.7331238440050447e-06, "epoch": 17.295929592959297, "percentage": 86.48, "elapsed_time": "6:12:31", "remaining_time": "0:58:14", "throughput": 1484.34, "total_tokens": 33177888} {"current_steps": 157225, "total_steps": 181800, "loss": 0.0064, "lr": 2.732032778684951e-06, "epoch": 17.296479647964798, "percentage": 86.48, "elapsed_time": "6:12:32", "remaining_time": "0:58:13", "throughput": 1484.34, "total_tokens": 33178912} {"current_steps": 157230, "total_steps": 181800, "loss": 0.0335, "lr": 2.7309419185980317e-06, "epoch": 17.297029702970296, "percentage": 86.49, "elapsed_time": "6:12:33", "remaining_time": "0:58:13", "throughput": 1484.35, "total_tokens": 33179968} {"current_steps": 157235, "total_steps": 181800, "loss": 0.0331, "lr": 2.7298512637543292e-06, "epoch": 17.297579757975797, "percentage": 86.49, "elapsed_time": "6:12:33", "remaining_time": "0:58:12", "throughput": 1484.35, "total_tokens": 33181024} {"current_steps": 157240, "total_steps": 181800, "loss": 0.0923, "lr": 2.7287608141639055e-06, "epoch": 17.298129812981298, "percentage": 86.49, "elapsed_time": "6:12:34", "remaining_time": "0:58:11", "throughput": 1484.35, "total_tokens": 33182112} {"current_steps": 157245, "total_steps": 181800, "loss": 0.0014, "lr": 2.7276705698368097e-06, "epoch": 17.2986798679868, "percentage": 86.49, "elapsed_time": "6:12:35", "remaining_time": "0:58:10", "throughput": 1484.35, "total_tokens": 33183136} {"current_steps": 157250, "total_steps": 181800, "loss": 0.0016, "lr": 2.7265805307830796e-06, "epoch": 17.2992299229923, "percentage": 86.5, "elapsed_time": "6:12:36", "remaining_time": "0:58:10", "throughput": 1484.35, "total_tokens": 33184128} {"current_steps": 157255, "total_steps": 181800, "loss": 0.0015, "lr": 2.72549069701277e-06, "epoch": 17.2997799779978, "percentage": 86.5, "elapsed_time": "6:12:36", "remaining_time": "0:58:09", "throughput": 1484.35, "total_tokens": 33185184} {"current_steps": 157260, "total_steps": 181800, "loss": 0.0078, "lr": 2.724401068535923e-06, "epoch": 17.300330033003302, "percentage": 86.5, "elapsed_time": "6:12:37", "remaining_time": "0:58:08", "throughput": 1484.35, "total_tokens": 33186240} {"current_steps": 157265, "total_steps": 181800, "loss": 0.0019, "lr": 2.723311645362589e-06, "epoch": 17.3008800880088, "percentage": 86.5, "elapsed_time": "6:12:38", "remaining_time": "0:58:08", "throughput": 1484.35, "total_tokens": 33187296} {"current_steps": 157270, "total_steps": 181800, "loss": 0.0007, "lr": 2.7222224275027993e-06, "epoch": 17.3014301430143, "percentage": 86.51, "elapsed_time": "6:12:38", "remaining_time": "0:58:07", "throughput": 1484.36, "total_tokens": 33188384} {"current_steps": 157275, "total_steps": 181800, "loss": 0.0035, "lr": 2.7211334149665925e-06, "epoch": 17.301980198019802, "percentage": 86.51, "elapsed_time": "6:12:39", "remaining_time": "0:58:06", "throughput": 1484.36, "total_tokens": 33189408} {"current_steps": 157280, "total_steps": 181800, "loss": 0.0104, "lr": 2.7200446077640105e-06, "epoch": 17.302530253025303, "percentage": 86.51, "elapsed_time": "6:12:40", "remaining_time": "0:58:05", "throughput": 1484.36, "total_tokens": 33190432} {"current_steps": 157285, "total_steps": 181800, "loss": 0.0126, "lr": 2.718956005905085e-06, "epoch": 17.303080308030804, "percentage": 86.52, "elapsed_time": "6:12:40", "remaining_time": "0:58:05", "throughput": 1484.36, "total_tokens": 33191456} {"current_steps": 157290, "total_steps": 181800, "loss": 0.0011, "lr": 2.7178676093998546e-06, "epoch": 17.303630363036305, "percentage": 86.52, "elapsed_time": "6:12:41", "remaining_time": "0:58:04", "throughput": 1484.36, "total_tokens": 33192512} {"current_steps": 157295, "total_steps": 181800, "loss": 0.0009, "lr": 2.7167794182583472e-06, "epoch": 17.304180418041803, "percentage": 86.52, "elapsed_time": "6:12:42", "remaining_time": "0:58:03", "throughput": 1484.36, "total_tokens": 33193568} {"current_steps": 157300, "total_steps": 181800, "loss": 0.0013, "lr": 2.7156914324905858e-06, "epoch": 17.304730473047304, "percentage": 86.52, "elapsed_time": "6:12:42", "remaining_time": "0:58:03", "throughput": 1484.36, "total_tokens": 33194560} {"current_steps": 157305, "total_steps": 181800, "loss": 0.0122, "lr": 2.714603652106609e-06, "epoch": 17.305280528052805, "percentage": 86.53, "elapsed_time": "6:12:43", "remaining_time": "0:58:02", "throughput": 1484.36, "total_tokens": 33195648} {"current_steps": 157310, "total_steps": 181800, "loss": 0.0043, "lr": 2.713516077116429e-06, "epoch": 17.305830583058306, "percentage": 86.53, "elapsed_time": "6:12:44", "remaining_time": "0:58:01", "throughput": 1484.36, "total_tokens": 33196640} {"current_steps": 157315, "total_steps": 181800, "loss": 0.0103, "lr": 2.712428707530082e-06, "epoch": 17.306380638063807, "percentage": 86.53, "elapsed_time": "6:12:44", "remaining_time": "0:58:00", "throughput": 1484.36, "total_tokens": 33197760} {"current_steps": 157320, "total_steps": 181800, "loss": 0.0026, "lr": 2.7113415433575875e-06, "epoch": 17.306930693069308, "percentage": 86.53, "elapsed_time": "6:12:45", "remaining_time": "0:58:00", "throughput": 1484.37, "total_tokens": 33198880} {"current_steps": 157325, "total_steps": 181800, "loss": 0.0424, "lr": 2.7102545846089567e-06, "epoch": 17.30748074807481, "percentage": 86.54, "elapsed_time": "6:12:46", "remaining_time": "0:57:59", "throughput": 1484.37, "total_tokens": 33200000} {"current_steps": 157330, "total_steps": 181800, "loss": 0.0022, "lr": 2.709167831294221e-06, "epoch": 17.308030803080307, "percentage": 86.54, "elapsed_time": "6:12:47", "remaining_time": "0:57:58", "throughput": 1484.37, "total_tokens": 33201088} {"current_steps": 157335, "total_steps": 181800, "loss": 0.04, "lr": 2.708081283423383e-06, "epoch": 17.308580858085808, "percentage": 86.54, "elapsed_time": "6:12:47", "remaining_time": "0:57:58", "throughput": 1484.38, "total_tokens": 33202144} {"current_steps": 157340, "total_steps": 181800, "loss": 0.1083, "lr": 2.706994941006463e-06, "epoch": 17.30913091309131, "percentage": 86.55, "elapsed_time": "6:12:48", "remaining_time": "0:57:57", "throughput": 1484.38, "total_tokens": 33203200} {"current_steps": 157345, "total_steps": 181800, "loss": 0.0258, "lr": 2.705908804053478e-06, "epoch": 17.30968096809681, "percentage": 86.55, "elapsed_time": "6:12:49", "remaining_time": "0:57:56", "throughput": 1484.38, "total_tokens": 33204288} {"current_steps": 157350, "total_steps": 181800, "loss": 0.0654, "lr": 2.7048228725744305e-06, "epoch": 17.31023102310231, "percentage": 86.55, "elapsed_time": "6:12:49", "remaining_time": "0:57:55", "throughput": 1484.38, "total_tokens": 33205344} {"current_steps": 157355, "total_steps": 181800, "loss": 0.0905, "lr": 2.7037371465793383e-06, "epoch": 17.310781078107812, "percentage": 86.55, "elapsed_time": "6:12:50", "remaining_time": "0:57:55", "throughput": 1484.39, "total_tokens": 33206464} {"current_steps": 157360, "total_steps": 181800, "loss": 0.0315, "lr": 2.702651626078198e-06, "epoch": 17.31133113311331, "percentage": 86.56, "elapsed_time": "6:12:51", "remaining_time": "0:57:54", "throughput": 1484.39, "total_tokens": 33207552} {"current_steps": 157365, "total_steps": 181800, "loss": 0.012, "lr": 2.701566311081016e-06, "epoch": 17.31188118811881, "percentage": 86.56, "elapsed_time": "6:12:51", "remaining_time": "0:57:53", "throughput": 1484.39, "total_tokens": 33208640} {"current_steps": 157370, "total_steps": 181800, "loss": 0.0978, "lr": 2.7004812015977987e-06, "epoch": 17.312431243124312, "percentage": 86.56, "elapsed_time": "6:12:52", "remaining_time": "0:57:53", "throughput": 1484.39, "total_tokens": 33209664} {"current_steps": 157375, "total_steps": 181800, "loss": 0.0028, "lr": 2.699396297638543e-06, "epoch": 17.312981298129813, "percentage": 86.56, "elapsed_time": "6:12:53", "remaining_time": "0:57:52", "throughput": 1484.39, "total_tokens": 33210688} {"current_steps": 157380, "total_steps": 181800, "loss": 0.0016, "lr": 2.6983115992132574e-06, "epoch": 17.313531353135314, "percentage": 86.57, "elapsed_time": "6:12:53", "remaining_time": "0:57:51", "throughput": 1484.39, "total_tokens": 33211744} {"current_steps": 157385, "total_steps": 181800, "loss": 0.1488, "lr": 2.6972271063319315e-06, "epoch": 17.314081408140815, "percentage": 86.57, "elapsed_time": "6:12:54", "remaining_time": "0:57:50", "throughput": 1484.39, "total_tokens": 33212832} {"current_steps": 157390, "total_steps": 181800, "loss": 0.1382, "lr": 2.6961428190045574e-06, "epoch": 17.314631463146316, "percentage": 86.57, "elapsed_time": "6:12:55", "remaining_time": "0:57:50", "throughput": 1484.4, "total_tokens": 33213920} {"current_steps": 157395, "total_steps": 181800, "loss": 0.0042, "lr": 2.6950587372411325e-06, "epoch": 17.315181518151814, "percentage": 86.58, "elapsed_time": "6:12:56", "remaining_time": "0:57:49", "throughput": 1484.4, "total_tokens": 33214976} {"current_steps": 157400, "total_steps": 181800, "loss": 0.0516, "lr": 2.693974861051646e-06, "epoch": 17.315731573157315, "percentage": 86.58, "elapsed_time": "6:12:56", "remaining_time": "0:57:48", "throughput": 1484.4, "total_tokens": 33216000} {"current_steps": 157405, "total_steps": 181800, "loss": 0.0033, "lr": 2.692891190446098e-06, "epoch": 17.316281628162816, "percentage": 86.58, "elapsed_time": "6:12:57", "remaining_time": "0:57:48", "throughput": 1484.4, "total_tokens": 33217024} {"current_steps": 157410, "total_steps": 181800, "loss": 0.0011, "lr": 2.691807725434464e-06, "epoch": 17.316831683168317, "percentage": 86.58, "elapsed_time": "6:12:58", "remaining_time": "0:57:47", "throughput": 1484.4, "total_tokens": 33218080} {"current_steps": 157415, "total_steps": 181800, "loss": 0.0157, "lr": 2.690724466026731e-06, "epoch": 17.317381738173818, "percentage": 86.59, "elapsed_time": "6:12:58", "remaining_time": "0:57:46", "throughput": 1484.4, "total_tokens": 33219104} {"current_steps": 157420, "total_steps": 181800, "loss": 0.0014, "lr": 2.6896414122328904e-06, "epoch": 17.31793179317932, "percentage": 86.59, "elapsed_time": "6:12:59", "remaining_time": "0:57:45", "throughput": 1484.4, "total_tokens": 33220192} {"current_steps": 157425, "total_steps": 181800, "loss": 0.0017, "lr": 2.688558564062915e-06, "epoch": 17.318481848184817, "percentage": 86.59, "elapsed_time": "6:13:00", "remaining_time": "0:57:45", "throughput": 1484.4, "total_tokens": 33221280} {"current_steps": 157430, "total_steps": 181800, "loss": 0.0027, "lr": 2.6874759215267887e-06, "epoch": 17.319031903190318, "percentage": 86.6, "elapsed_time": "6:13:00", "remaining_time": "0:57:44", "throughput": 1484.41, "total_tokens": 33222336} {"current_steps": 157435, "total_steps": 181800, "loss": 0.0404, "lr": 2.6863934846344974e-06, "epoch": 17.31958195819582, "percentage": 86.6, "elapsed_time": "6:13:01", "remaining_time": "0:57:43", "throughput": 1484.4, "total_tokens": 33223328} {"current_steps": 157440, "total_steps": 181800, "loss": 0.0165, "lr": 2.6853112533960027e-06, "epoch": 17.32013201320132, "percentage": 86.6, "elapsed_time": "6:13:02", "remaining_time": "0:57:43", "throughput": 1484.4, "total_tokens": 33224320} {"current_steps": 157445, "total_steps": 181800, "loss": 0.0557, "lr": 2.6842292278212915e-06, "epoch": 17.32068206820682, "percentage": 86.6, "elapsed_time": "6:13:02", "remaining_time": "0:57:42", "throughput": 1484.41, "total_tokens": 33225440} {"current_steps": 157450, "total_steps": 181800, "loss": 0.0036, "lr": 2.683147407920328e-06, "epoch": 17.321232123212322, "percentage": 86.61, "elapsed_time": "6:13:03", "remaining_time": "0:57:41", "throughput": 1484.41, "total_tokens": 33226560} {"current_steps": 157455, "total_steps": 181800, "loss": 0.0298, "lr": 2.682065793703084e-06, "epoch": 17.321782178217823, "percentage": 86.61, "elapsed_time": "6:13:04", "remaining_time": "0:57:40", "throughput": 1484.41, "total_tokens": 33227680} {"current_steps": 157460, "total_steps": 181800, "loss": 0.108, "lr": 2.6809843851795357e-06, "epoch": 17.32233223322332, "percentage": 86.61, "elapsed_time": "6:13:05", "remaining_time": "0:57:40", "throughput": 1484.41, "total_tokens": 33228672} {"current_steps": 157465, "total_steps": 181800, "loss": 0.0058, "lr": 2.6799031823596416e-06, "epoch": 17.322882288228822, "percentage": 86.61, "elapsed_time": "6:13:05", "remaining_time": "0:57:39", "throughput": 1484.41, "total_tokens": 33229728} {"current_steps": 157470, "total_steps": 181800, "loss": 0.0016, "lr": 2.6788221852533713e-06, "epoch": 17.323432343234323, "percentage": 86.62, "elapsed_time": "6:13:06", "remaining_time": "0:57:38", "throughput": 1484.42, "total_tokens": 33230784} {"current_steps": 157475, "total_steps": 181800, "loss": 0.0052, "lr": 2.6777413938706837e-06, "epoch": 17.323982398239824, "percentage": 86.62, "elapsed_time": "6:13:07", "remaining_time": "0:57:38", "throughput": 1484.42, "total_tokens": 33231872} {"current_steps": 157480, "total_steps": 181800, "loss": 0.0025, "lr": 2.676660808221548e-06, "epoch": 17.324532453245325, "percentage": 86.62, "elapsed_time": "6:13:07", "remaining_time": "0:57:37", "throughput": 1484.42, "total_tokens": 33232992} {"current_steps": 157485, "total_steps": 181800, "loss": 0.0544, "lr": 2.6755804283159103e-06, "epoch": 17.325082508250826, "percentage": 86.63, "elapsed_time": "6:13:08", "remaining_time": "0:57:36", "throughput": 1484.42, "total_tokens": 33234016} {"current_steps": 157490, "total_steps": 181800, "loss": 0.0024, "lr": 2.6745002541637394e-06, "epoch": 17.325632563256324, "percentage": 86.63, "elapsed_time": "6:13:09", "remaining_time": "0:57:35", "throughput": 1484.43, "total_tokens": 33235104} {"current_steps": 157495, "total_steps": 181800, "loss": 0.0161, "lr": 2.6734202857749884e-06, "epoch": 17.326182618261825, "percentage": 86.63, "elapsed_time": "6:13:09", "remaining_time": "0:57:35", "throughput": 1484.43, "total_tokens": 33236128} {"current_steps": 157500, "total_steps": 181800, "loss": 0.0118, "lr": 2.6723405231596055e-06, "epoch": 17.326732673267326, "percentage": 86.63, "elapsed_time": "6:13:10", "remaining_time": "0:57:34", "throughput": 1484.43, "total_tokens": 33237216} {"current_steps": 157505, "total_steps": 181800, "loss": 0.0357, "lr": 2.6712609663275517e-06, "epoch": 17.327282728272827, "percentage": 86.64, "elapsed_time": "6:13:11", "remaining_time": "0:57:33", "throughput": 1484.43, "total_tokens": 33238240} {"current_steps": 157510, "total_steps": 181800, "loss": 0.0003, "lr": 2.670181615288764e-06, "epoch": 17.32783278327833, "percentage": 86.64, "elapsed_time": "6:13:11", "remaining_time": "0:57:33", "throughput": 1484.43, "total_tokens": 33239296} {"current_steps": 157515, "total_steps": 181800, "loss": 0.0021, "lr": 2.6691024700532003e-06, "epoch": 17.32838283828383, "percentage": 86.64, "elapsed_time": "6:13:12", "remaining_time": "0:57:32", "throughput": 1484.43, "total_tokens": 33240384} {"current_steps": 157520, "total_steps": 181800, "loss": 0.1026, "lr": 2.668023530630806e-06, "epoch": 17.32893289328933, "percentage": 86.64, "elapsed_time": "6:13:13", "remaining_time": "0:57:31", "throughput": 1484.43, "total_tokens": 33241408} {"current_steps": 157525, "total_steps": 181800, "loss": 0.0357, "lr": 2.6669447970315257e-06, "epoch": 17.329482948294828, "percentage": 86.65, "elapsed_time": "6:13:14", "remaining_time": "0:57:30", "throughput": 1484.43, "total_tokens": 33242400} {"current_steps": 157530, "total_steps": 181800, "loss": 0.0057, "lr": 2.665866269265291e-06, "epoch": 17.33003300330033, "percentage": 86.65, "elapsed_time": "6:13:14", "remaining_time": "0:57:30", "throughput": 1484.43, "total_tokens": 33243424} {"current_steps": 157535, "total_steps": 181800, "loss": 0.0074, "lr": 2.6647879473420568e-06, "epoch": 17.33058305830583, "percentage": 86.65, "elapsed_time": "6:13:15", "remaining_time": "0:57:29", "throughput": 1484.44, "total_tokens": 33244544} {"current_steps": 157540, "total_steps": 181800, "loss": 0.0799, "lr": 2.663709831271749e-06, "epoch": 17.33113311331133, "percentage": 86.66, "elapsed_time": "6:13:16", "remaining_time": "0:57:28", "throughput": 1484.44, "total_tokens": 33245632} {"current_steps": 157545, "total_steps": 181800, "loss": 0.0021, "lr": 2.6626319210643095e-06, "epoch": 17.331683168316832, "percentage": 86.66, "elapsed_time": "6:13:16", "remaining_time": "0:57:28", "throughput": 1484.44, "total_tokens": 33246656} {"current_steps": 157550, "total_steps": 181800, "loss": 0.0025, "lr": 2.6615542167296782e-06, "epoch": 17.332233223322334, "percentage": 86.66, "elapsed_time": "6:13:17", "remaining_time": "0:57:27", "throughput": 1484.44, "total_tokens": 33247744} {"current_steps": 157555, "total_steps": 181800, "loss": 0.2627, "lr": 2.6604767182777796e-06, "epoch": 17.33278327832783, "percentage": 86.66, "elapsed_time": "6:13:18", "remaining_time": "0:57:26", "throughput": 1484.44, "total_tokens": 33248832} {"current_steps": 157560, "total_steps": 181800, "loss": 0.0984, "lr": 2.6593994257185506e-06, "epoch": 17.333333333333332, "percentage": 86.67, "elapsed_time": "6:13:18", "remaining_time": "0:57:25", "throughput": 1484.44, "total_tokens": 33249824} {"current_steps": 157565, "total_steps": 181800, "loss": 0.0601, "lr": 2.658322339061911e-06, "epoch": 17.333883388338833, "percentage": 86.67, "elapsed_time": "6:13:19", "remaining_time": "0:57:25", "throughput": 1484.45, "total_tokens": 33250944} {"current_steps": 157570, "total_steps": 181800, "loss": 0.0958, "lr": 2.6572454583177946e-06, "epoch": 17.334433443344334, "percentage": 86.67, "elapsed_time": "6:13:20", "remaining_time": "0:57:24", "throughput": 1484.45, "total_tokens": 33251968} {"current_steps": 157575, "total_steps": 181800, "loss": 0.0172, "lr": 2.656168783496132e-06, "epoch": 17.334983498349835, "percentage": 86.67, "elapsed_time": "6:13:20", "remaining_time": "0:57:23", "throughput": 1484.45, "total_tokens": 33253120} {"current_steps": 157580, "total_steps": 181800, "loss": 0.0048, "lr": 2.655092314606833e-06, "epoch": 17.335533553355337, "percentage": 86.68, "elapsed_time": "6:13:21", "remaining_time": "0:57:23", "throughput": 1484.45, "total_tokens": 33254176} {"current_steps": 157585, "total_steps": 181800, "loss": 0.0013, "lr": 2.654016051659833e-06, "epoch": 17.336083608360838, "percentage": 86.68, "elapsed_time": "6:13:22", "remaining_time": "0:57:22", "throughput": 1484.45, "total_tokens": 33255200} {"current_steps": 157590, "total_steps": 181800, "loss": 0.0994, "lr": 2.652939994665038e-06, "epoch": 17.336633663366335, "percentage": 86.68, "elapsed_time": "6:13:23", "remaining_time": "0:57:21", "throughput": 1484.45, "total_tokens": 33256256} {"current_steps": 157595, "total_steps": 181800, "loss": 0.0119, "lr": 2.651864143632379e-06, "epoch": 17.337183718371836, "percentage": 86.69, "elapsed_time": "6:13:23", "remaining_time": "0:57:20", "throughput": 1484.46, "total_tokens": 33257344} {"current_steps": 157600, "total_steps": 181800, "loss": 0.0892, "lr": 2.6507884985717575e-06, "epoch": 17.337733773377337, "percentage": 86.69, "elapsed_time": "6:13:24", "remaining_time": "0:57:20", "throughput": 1484.46, "total_tokens": 33258336} {"current_steps": 157605, "total_steps": 181800, "loss": 0.0643, "lr": 2.6497130594930946e-06, "epoch": 17.33828382838284, "percentage": 86.69, "elapsed_time": "6:13:25", "remaining_time": "0:57:19", "throughput": 1484.46, "total_tokens": 33259392} {"current_steps": 157610, "total_steps": 181800, "loss": 0.0027, "lr": 2.6486378264063083e-06, "epoch": 17.33883388338834, "percentage": 86.69, "elapsed_time": "6:13:25", "remaining_time": "0:57:18", "throughput": 1484.46, "total_tokens": 33260448} {"current_steps": 157615, "total_steps": 181800, "loss": 0.1116, "lr": 2.647562799321296e-06, "epoch": 17.33938393839384, "percentage": 86.7, "elapsed_time": "6:13:26", "remaining_time": "0:57:18", "throughput": 1484.46, "total_tokens": 33261472} {"current_steps": 157620, "total_steps": 181800, "loss": 0.0025, "lr": 2.6464879782479746e-06, "epoch": 17.33993399339934, "percentage": 86.7, "elapsed_time": "6:13:27", "remaining_time": "0:57:17", "throughput": 1484.46, "total_tokens": 33262560} {"current_steps": 157625, "total_steps": 181800, "loss": 0.0043, "lr": 2.645413363196245e-06, "epoch": 17.34048404840484, "percentage": 86.7, "elapsed_time": "6:13:27", "remaining_time": "0:57:16", "throughput": 1484.46, "total_tokens": 33263552} {"current_steps": 157630, "total_steps": 181800, "loss": 0.002, "lr": 2.644338954176012e-06, "epoch": 17.34103410341034, "percentage": 86.71, "elapsed_time": "6:13:28", "remaining_time": "0:57:15", "throughput": 1484.46, "total_tokens": 33264544} {"current_steps": 157635, "total_steps": 181800, "loss": 0.0656, "lr": 2.6432647511971858e-06, "epoch": 17.34158415841584, "percentage": 86.71, "elapsed_time": "6:13:29", "remaining_time": "0:57:15", "throughput": 1484.46, "total_tokens": 33265536} {"current_steps": 157640, "total_steps": 181800, "loss": 0.0043, "lr": 2.642190754269652e-06, "epoch": 17.342134213421343, "percentage": 86.71, "elapsed_time": "6:13:29", "remaining_time": "0:57:14", "throughput": 1484.46, "total_tokens": 33266624} {"current_steps": 157645, "total_steps": 181800, "loss": 0.0027, "lr": 2.6411169634033285e-06, "epoch": 17.342684268426844, "percentage": 86.71, "elapsed_time": "6:13:30", "remaining_time": "0:57:13", "throughput": 1484.46, "total_tokens": 33267616} {"current_steps": 157650, "total_steps": 181800, "loss": 0.0007, "lr": 2.6400433786080982e-06, "epoch": 17.343234323432345, "percentage": 86.72, "elapsed_time": "6:13:31", "remaining_time": "0:57:13", "throughput": 1484.46, "total_tokens": 33268672} {"current_steps": 157655, "total_steps": 181800, "loss": 0.1177, "lr": 2.6389699998938533e-06, "epoch": 17.343784378437842, "percentage": 86.72, "elapsed_time": "6:13:32", "remaining_time": "0:57:12", "throughput": 1484.46, "total_tokens": 33269664} {"current_steps": 157660, "total_steps": 181800, "loss": 0.0285, "lr": 2.6378968272704917e-06, "epoch": 17.344334433443343, "percentage": 86.72, "elapsed_time": "6:13:32", "remaining_time": "0:57:11", "throughput": 1484.45, "total_tokens": 33270624} {"current_steps": 157665, "total_steps": 181800, "loss": 0.0013, "lr": 2.6368238607479056e-06, "epoch": 17.344884488448844, "percentage": 86.72, "elapsed_time": "6:13:33", "remaining_time": "0:57:10", "throughput": 1484.46, "total_tokens": 33271712} {"current_steps": 157670, "total_steps": 181800, "loss": 0.004, "lr": 2.635751100335987e-06, "epoch": 17.345434543454346, "percentage": 86.73, "elapsed_time": "6:13:34", "remaining_time": "0:57:10", "throughput": 1484.46, "total_tokens": 33272768} {"current_steps": 157675, "total_steps": 181800, "loss": 0.0007, "lr": 2.6346785460446194e-06, "epoch": 17.345984598459847, "percentage": 86.73, "elapsed_time": "6:13:34", "remaining_time": "0:57:09", "throughput": 1484.46, "total_tokens": 33273824} {"current_steps": 157680, "total_steps": 181800, "loss": 0.0143, "lr": 2.633606197883684e-06, "epoch": 17.346534653465348, "percentage": 86.73, "elapsed_time": "6:13:35", "remaining_time": "0:57:08", "throughput": 1484.46, "total_tokens": 33274848} {"current_steps": 157685, "total_steps": 181800, "loss": 0.0707, "lr": 2.6325340558630675e-06, "epoch": 17.34708470847085, "percentage": 86.74, "elapsed_time": "6:13:36", "remaining_time": "0:57:08", "throughput": 1484.46, "total_tokens": 33275840} {"current_steps": 157690, "total_steps": 181800, "loss": 0.0062, "lr": 2.6314621199926502e-06, "epoch": 17.347634763476346, "percentage": 86.74, "elapsed_time": "6:13:36", "remaining_time": "0:57:07", "throughput": 1484.46, "total_tokens": 33276832} {"current_steps": 157695, "total_steps": 181800, "loss": 0.0376, "lr": 2.6303903902823194e-06, "epoch": 17.348184818481847, "percentage": 86.74, "elapsed_time": "6:13:37", "remaining_time": "0:57:06", "throughput": 1484.46, "total_tokens": 33277952} {"current_steps": 157700, "total_steps": 181800, "loss": 0.0055, "lr": 2.629318866741948e-06, "epoch": 17.34873487348735, "percentage": 86.74, "elapsed_time": "6:13:38", "remaining_time": "0:57:05", "throughput": 1484.46, "total_tokens": 33279040} {"current_steps": 157705, "total_steps": 181800, "loss": 0.0082, "lr": 2.6282475493814017e-06, "epoch": 17.34928492849285, "percentage": 86.75, "elapsed_time": "6:13:38", "remaining_time": "0:57:05", "throughput": 1484.47, "total_tokens": 33280096} {"current_steps": 157710, "total_steps": 181800, "loss": 0.003, "lr": 2.6271764382105685e-06, "epoch": 17.34983498349835, "percentage": 86.75, "elapsed_time": "6:13:39", "remaining_time": "0:57:04", "throughput": 1484.47, "total_tokens": 33281152} {"current_steps": 157715, "total_steps": 181800, "loss": 0.1749, "lr": 2.626105533239312e-06, "epoch": 17.350385038503852, "percentage": 86.75, "elapsed_time": "6:13:40", "remaining_time": "0:57:03", "throughput": 1484.47, "total_tokens": 33282240} {"current_steps": 157720, "total_steps": 181800, "loss": 0.0626, "lr": 2.6250348344775023e-06, "epoch": 17.35093509350935, "percentage": 86.75, "elapsed_time": "6:13:40", "remaining_time": "0:57:03", "throughput": 1484.47, "total_tokens": 33283264} {"current_steps": 157725, "total_steps": 181800, "loss": 0.0009, "lr": 2.6239643419350146e-06, "epoch": 17.35148514851485, "percentage": 86.76, "elapsed_time": "6:13:41", "remaining_time": "0:57:02", "throughput": 1484.47, "total_tokens": 33284256} {"current_steps": 157730, "total_steps": 181800, "loss": 0.0041, "lr": 2.622894055621708e-06, "epoch": 17.35203520352035, "percentage": 86.76, "elapsed_time": "6:13:42", "remaining_time": "0:57:01", "throughput": 1484.47, "total_tokens": 33285312} {"current_steps": 157735, "total_steps": 181800, "loss": 0.1151, "lr": 2.621823975547452e-06, "epoch": 17.352585258525853, "percentage": 86.76, "elapsed_time": "6:13:43", "remaining_time": "0:57:00", "throughput": 1484.47, "total_tokens": 33286368} {"current_steps": 157740, "total_steps": 181800, "loss": 0.0605, "lr": 2.620754101722109e-06, "epoch": 17.353135313531354, "percentage": 86.77, "elapsed_time": "6:13:43", "remaining_time": "0:57:00", "throughput": 1484.47, "total_tokens": 33287424} {"current_steps": 157745, "total_steps": 181800, "loss": 0.0857, "lr": 2.6196844341555256e-06, "epoch": 17.353685368536855, "percentage": 86.77, "elapsed_time": "6:13:44", "remaining_time": "0:56:59", "throughput": 1484.47, "total_tokens": 33288512} {"current_steps": 157750, "total_steps": 181800, "loss": 0.0023, "lr": 2.6186149728575805e-06, "epoch": 17.354235423542356, "percentage": 86.77, "elapsed_time": "6:13:45", "remaining_time": "0:56:58", "throughput": 1484.48, "total_tokens": 33289600} {"current_steps": 157755, "total_steps": 181800, "loss": 0.0916, "lr": 2.617545717838116e-06, "epoch": 17.354785478547853, "percentage": 86.77, "elapsed_time": "6:13:45", "remaining_time": "0:56:58", "throughput": 1484.48, "total_tokens": 33290688} {"current_steps": 157760, "total_steps": 181800, "loss": 0.0776, "lr": 2.6164766691069987e-06, "epoch": 17.355335533553355, "percentage": 86.78, "elapsed_time": "6:13:46", "remaining_time": "0:56:57", "throughput": 1484.48, "total_tokens": 33291744} {"current_steps": 157765, "total_steps": 181800, "loss": 0.0091, "lr": 2.6154078266740766e-06, "epoch": 17.355885588558856, "percentage": 86.78, "elapsed_time": "6:13:47", "remaining_time": "0:56:56", "throughput": 1484.48, "total_tokens": 33292704} {"current_steps": 157770, "total_steps": 181800, "loss": 0.1304, "lr": 2.614339190549192e-06, "epoch": 17.356435643564357, "percentage": 86.78, "elapsed_time": "6:13:47", "remaining_time": "0:56:55", "throughput": 1484.48, "total_tokens": 33293696} {"current_steps": 157775, "total_steps": 181800, "loss": 0.0896, "lr": 2.6132707607422036e-06, "epoch": 17.356985698569858, "percentage": 86.78, "elapsed_time": "6:13:48", "remaining_time": "0:56:55", "throughput": 1484.48, "total_tokens": 33294848} {"current_steps": 157780, "total_steps": 181800, "loss": 0.0085, "lr": 2.6122025372629533e-06, "epoch": 17.35753575357536, "percentage": 86.79, "elapsed_time": "6:13:49", "remaining_time": "0:56:54", "throughput": 1484.48, "total_tokens": 33295904} {"current_steps": 157785, "total_steps": 181800, "loss": 0.0075, "lr": 2.6111345201212974e-06, "epoch": 17.358085808580856, "percentage": 86.79, "elapsed_time": "6:13:49", "remaining_time": "0:56:53", "throughput": 1484.49, "total_tokens": 33296960} {"current_steps": 157790, "total_steps": 181800, "loss": 0.004, "lr": 2.610066709327069e-06, "epoch": 17.358635863586358, "percentage": 86.79, "elapsed_time": "6:13:50", "remaining_time": "0:56:53", "throughput": 1484.49, "total_tokens": 33297984} {"current_steps": 157795, "total_steps": 181800, "loss": 0.0013, "lr": 2.6089991048901084e-06, "epoch": 17.35918591859186, "percentage": 86.8, "elapsed_time": "6:13:51", "remaining_time": "0:56:52", "throughput": 1484.49, "total_tokens": 33299008} {"current_steps": 157800, "total_steps": 181800, "loss": 0.0083, "lr": 2.607931706820266e-06, "epoch": 17.35973597359736, "percentage": 86.8, "elapsed_time": "6:13:52", "remaining_time": "0:56:51", "throughput": 1484.49, "total_tokens": 33300128} {"current_steps": 157805, "total_steps": 181800, "loss": 0.0017, "lr": 2.606864515127361e-06, "epoch": 17.36028602860286, "percentage": 86.8, "elapsed_time": "6:13:52", "remaining_time": "0:56:51", "throughput": 1484.49, "total_tokens": 33301152} {"current_steps": 157810, "total_steps": 181800, "loss": 0.0004, "lr": 2.6057975298212496e-06, "epoch": 17.360836083608362, "percentage": 86.8, "elapsed_time": "6:13:53", "remaining_time": "0:56:50", "throughput": 1484.49, "total_tokens": 33302240} {"current_steps": 157815, "total_steps": 181800, "loss": 0.0024, "lr": 2.6047307509117545e-06, "epoch": 17.361386138613863, "percentage": 86.81, "elapsed_time": "6:13:54", "remaining_time": "0:56:49", "throughput": 1484.5, "total_tokens": 33303328} {"current_steps": 157820, "total_steps": 181800, "loss": 0.0194, "lr": 2.6036641784087074e-06, "epoch": 17.36193619361936, "percentage": 86.81, "elapsed_time": "6:13:54", "remaining_time": "0:56:48", "throughput": 1484.5, "total_tokens": 33304416} {"current_steps": 157825, "total_steps": 181800, "loss": 0.0051, "lr": 2.602597812321947e-06, "epoch": 17.36248624862486, "percentage": 86.81, "elapsed_time": "6:13:55", "remaining_time": "0:56:48", "throughput": 1484.5, "total_tokens": 33305472} {"current_steps": 157830, "total_steps": 181800, "loss": 0.0033, "lr": 2.6015316526612876e-06, "epoch": 17.363036303630363, "percentage": 86.82, "elapsed_time": "6:13:56", "remaining_time": "0:56:47", "throughput": 1484.5, "total_tokens": 33306496} {"current_steps": 157835, "total_steps": 181800, "loss": 0.0109, "lr": 2.6004656994365634e-06, "epoch": 17.363586358635864, "percentage": 86.82, "elapsed_time": "6:13:56", "remaining_time": "0:56:46", "throughput": 1484.5, "total_tokens": 33307520} {"current_steps": 157840, "total_steps": 181800, "loss": 0.0006, "lr": 2.5993999526576053e-06, "epoch": 17.364136413641365, "percentage": 86.82, "elapsed_time": "6:13:57", "remaining_time": "0:56:46", "throughput": 1484.5, "total_tokens": 33308512} {"current_steps": 157845, "total_steps": 181800, "loss": 0.0033, "lr": 2.598334412334222e-06, "epoch": 17.364686468646866, "percentage": 86.82, "elapsed_time": "6:13:58", "remaining_time": "0:56:45", "throughput": 1484.5, "total_tokens": 33309568} {"current_steps": 157850, "total_steps": 181800, "loss": 0.0058, "lr": 2.597269078476247e-06, "epoch": 17.365236523652364, "percentage": 86.83, "elapsed_time": "6:13:58", "remaining_time": "0:56:44", "throughput": 1484.5, "total_tokens": 33310592} {"current_steps": 157855, "total_steps": 181800, "loss": 0.0343, "lr": 2.5962039510934873e-06, "epoch": 17.365786578657865, "percentage": 86.83, "elapsed_time": "6:13:59", "remaining_time": "0:56:43", "throughput": 1484.51, "total_tokens": 33311744} {"current_steps": 157860, "total_steps": 181800, "loss": 0.1041, "lr": 2.595139030195773e-06, "epoch": 17.366336633663366, "percentage": 86.83, "elapsed_time": "6:14:00", "remaining_time": "0:56:43", "throughput": 1484.51, "total_tokens": 33312768} {"current_steps": 157865, "total_steps": 181800, "loss": 0.0825, "lr": 2.594074315792902e-06, "epoch": 17.366886688668867, "percentage": 86.83, "elapsed_time": "6:14:00", "remaining_time": "0:56:42", "throughput": 1484.51, "total_tokens": 33313824} {"current_steps": 157870, "total_steps": 181800, "loss": 0.0556, "lr": 2.5930098078947002e-06, "epoch": 17.367436743674368, "percentage": 86.84, "elapsed_time": "6:14:01", "remaining_time": "0:56:41", "throughput": 1484.51, "total_tokens": 33314848} {"current_steps": 157875, "total_steps": 181800, "loss": 0.0064, "lr": 2.591945506510979e-06, "epoch": 17.36798679867987, "percentage": 86.84, "elapsed_time": "6:14:02", "remaining_time": "0:56:41", "throughput": 1484.51, "total_tokens": 33315872} {"current_steps": 157880, "total_steps": 181800, "loss": 0.0874, "lr": 2.5908814116515382e-06, "epoch": 17.36853685368537, "percentage": 86.84, "elapsed_time": "6:14:03", "remaining_time": "0:56:40", "throughput": 1484.51, "total_tokens": 33316896} {"current_steps": 157885, "total_steps": 181800, "loss": 0.0441, "lr": 2.589817523326196e-06, "epoch": 17.369086908690868, "percentage": 86.85, "elapsed_time": "6:14:03", "remaining_time": "0:56:39", "throughput": 1484.51, "total_tokens": 33317952} {"current_steps": 157890, "total_steps": 181800, "loss": 0.0845, "lr": 2.588753841544747e-06, "epoch": 17.36963696369637, "percentage": 86.85, "elapsed_time": "6:14:04", "remaining_time": "0:56:38", "throughput": 1484.51, "total_tokens": 33319040} {"current_steps": 157895, "total_steps": 181800, "loss": 0.0034, "lr": 2.5876903663169998e-06, "epoch": 17.37018701870187, "percentage": 86.85, "elapsed_time": "6:14:05", "remaining_time": "0:56:38", "throughput": 1484.51, "total_tokens": 33320064} {"current_steps": 157900, "total_steps": 181800, "loss": 0.1661, "lr": 2.5866270976527607e-06, "epoch": 17.37073707370737, "percentage": 86.85, "elapsed_time": "6:14:05", "remaining_time": "0:56:37", "throughput": 1484.51, "total_tokens": 33321088} {"current_steps": 157905, "total_steps": 181800, "loss": 0.0326, "lr": 2.585564035561824e-06, "epoch": 17.371287128712872, "percentage": 86.86, "elapsed_time": "6:14:06", "remaining_time": "0:56:36", "throughput": 1484.52, "total_tokens": 33322208} {"current_steps": 157910, "total_steps": 181800, "loss": 0.0939, "lr": 2.584501180053986e-06, "epoch": 17.371837183718373, "percentage": 86.86, "elapsed_time": "6:14:07", "remaining_time": "0:56:36", "throughput": 1484.52, "total_tokens": 33323296} {"current_steps": 157915, "total_steps": 181800, "loss": 0.0039, "lr": 2.5834385311390487e-06, "epoch": 17.37238723872387, "percentage": 86.86, "elapsed_time": "6:14:07", "remaining_time": "0:56:35", "throughput": 1484.52, "total_tokens": 33324416} {"current_steps": 157920, "total_steps": 181800, "loss": 0.004, "lr": 2.5823760888267907e-06, "epoch": 17.372937293729372, "percentage": 86.86, "elapsed_time": "6:14:08", "remaining_time": "0:56:34", "throughput": 1484.53, "total_tokens": 33325504} {"current_steps": 157925, "total_steps": 181800, "loss": 0.0059, "lr": 2.5813138531270235e-06, "epoch": 17.373487348734873, "percentage": 86.87, "elapsed_time": "6:14:09", "remaining_time": "0:56:33", "throughput": 1484.52, "total_tokens": 33326496} {"current_steps": 157930, "total_steps": 181800, "loss": 0.0379, "lr": 2.5802518240495318e-06, "epoch": 17.374037403740374, "percentage": 86.87, "elapsed_time": "6:14:09", "remaining_time": "0:56:33", "throughput": 1484.53, "total_tokens": 33327616} {"current_steps": 157935, "total_steps": 181800, "loss": 0.019, "lr": 2.5791900016040953e-06, "epoch": 17.374587458745875, "percentage": 86.87, "elapsed_time": "6:14:10", "remaining_time": "0:56:32", "throughput": 1484.53, "total_tokens": 33328640} {"current_steps": 157940, "total_steps": 181800, "loss": 0.0015, "lr": 2.578128385800513e-06, "epoch": 17.375137513751376, "percentage": 86.88, "elapsed_time": "6:14:11", "remaining_time": "0:56:31", "throughput": 1484.53, "total_tokens": 33329664} {"current_steps": 157945, "total_steps": 181800, "loss": 0.0325, "lr": 2.577066976648554e-06, "epoch": 17.375687568756877, "percentage": 86.88, "elapsed_time": "6:14:12", "remaining_time": "0:56:31", "throughput": 1484.53, "total_tokens": 33330688} {"current_steps": 157950, "total_steps": 181800, "loss": 0.0188, "lr": 2.5760057741580106e-06, "epoch": 17.376237623762375, "percentage": 86.88, "elapsed_time": "6:14:12", "remaining_time": "0:56:30", "throughput": 1484.53, "total_tokens": 33331712} {"current_steps": 157955, "total_steps": 181800, "loss": 0.004, "lr": 2.574944778338667e-06, "epoch": 17.376787678767876, "percentage": 86.88, "elapsed_time": "6:14:13", "remaining_time": "0:56:29", "throughput": 1484.53, "total_tokens": 33332800} {"current_steps": 157960, "total_steps": 181800, "loss": 0.0088, "lr": 2.57388398920029e-06, "epoch": 17.377337733773377, "percentage": 86.89, "elapsed_time": "6:14:14", "remaining_time": "0:56:28", "throughput": 1484.53, "total_tokens": 33333856} {"current_steps": 157965, "total_steps": 181800, "loss": 0.0006, "lr": 2.57282340675267e-06, "epoch": 17.377887788778878, "percentage": 86.89, "elapsed_time": "6:14:14", "remaining_time": "0:56:28", "throughput": 1484.53, "total_tokens": 33334912} {"current_steps": 157970, "total_steps": 181800, "loss": 0.0024, "lr": 2.5717630310055696e-06, "epoch": 17.37843784378438, "percentage": 86.89, "elapsed_time": "6:14:15", "remaining_time": "0:56:27", "throughput": 1484.53, "total_tokens": 33335936} {"current_steps": 157975, "total_steps": 181800, "loss": 0.0233, "lr": 2.570702861968774e-06, "epoch": 17.37898789878988, "percentage": 86.89, "elapsed_time": "6:14:16", "remaining_time": "0:56:26", "throughput": 1484.53, "total_tokens": 33336928} {"current_steps": 157980, "total_steps": 181800, "loss": 0.1197, "lr": 2.5696428996520415e-06, "epoch": 17.379537953795378, "percentage": 86.9, "elapsed_time": "6:14:16", "remaining_time": "0:56:26", "throughput": 1484.53, "total_tokens": 33337952} {"current_steps": 157985, "total_steps": 181800, "loss": 0.0012, "lr": 2.5685831440651454e-06, "epoch": 17.38008800880088, "percentage": 86.9, "elapsed_time": "6:14:17", "remaining_time": "0:56:25", "throughput": 1484.53, "total_tokens": 33339072} {"current_steps": 157990, "total_steps": 181800, "loss": 0.0481, "lr": 2.5675235952178604e-06, "epoch": 17.38063806380638, "percentage": 86.9, "elapsed_time": "6:14:18", "remaining_time": "0:56:24", "throughput": 1484.54, "total_tokens": 33340128} {"current_steps": 157995, "total_steps": 181800, "loss": 0.0031, "lr": 2.5664642531199434e-06, "epoch": 17.38118811881188, "percentage": 86.91, "elapsed_time": "6:14:18", "remaining_time": "0:56:23", "throughput": 1484.54, "total_tokens": 33341184} {"current_steps": 158000, "total_steps": 181800, "loss": 0.0071, "lr": 2.5654051177811637e-06, "epoch": 17.381738173817382, "percentage": 86.91, "elapsed_time": "6:14:19", "remaining_time": "0:56:23", "throughput": 1484.54, "total_tokens": 33342240} {"current_steps": 158005, "total_steps": 181800, "loss": 0.0234, "lr": 2.5643461892112753e-06, "epoch": 17.382288228822883, "percentage": 86.91, "elapsed_time": "6:14:20", "remaining_time": "0:56:22", "throughput": 1484.54, "total_tokens": 33343296} {"current_steps": 158010, "total_steps": 181800, "loss": 0.0123, "lr": 2.563287467420042e-06, "epoch": 17.382838283828384, "percentage": 86.91, "elapsed_time": "6:14:21", "remaining_time": "0:56:21", "throughput": 1484.54, "total_tokens": 33344352} {"current_steps": 158015, "total_steps": 181800, "loss": 0.0436, "lr": 2.5622289524172283e-06, "epoch": 17.383388338833882, "percentage": 86.92, "elapsed_time": "6:14:21", "remaining_time": "0:56:21", "throughput": 1484.55, "total_tokens": 33345440} {"current_steps": 158020, "total_steps": 181800, "loss": 0.0613, "lr": 2.5611706442125764e-06, "epoch": 17.383938393839383, "percentage": 86.92, "elapsed_time": "6:14:22", "remaining_time": "0:56:20", "throughput": 1484.55, "total_tokens": 33346464} {"current_steps": 158025, "total_steps": 181800, "loss": 0.0067, "lr": 2.560112542815854e-06, "epoch": 17.384488448844884, "percentage": 86.92, "elapsed_time": "6:14:23", "remaining_time": "0:56:19", "throughput": 1484.55, "total_tokens": 33347520} {"current_steps": 158030, "total_steps": 181800, "loss": 0.0058, "lr": 2.5590546482368084e-06, "epoch": 17.385038503850385, "percentage": 86.93, "elapsed_time": "6:14:23", "remaining_time": "0:56:18", "throughput": 1484.55, "total_tokens": 33348544} {"current_steps": 158035, "total_steps": 181800, "loss": 0.0252, "lr": 2.557996960485179e-06, "epoch": 17.385588558855886, "percentage": 86.93, "elapsed_time": "6:14:24", "remaining_time": "0:56:18", "throughput": 1484.55, "total_tokens": 33349568} {"current_steps": 158040, "total_steps": 181800, "loss": 0.0101, "lr": 2.5569394795707276e-06, "epoch": 17.386138613861387, "percentage": 86.93, "elapsed_time": "6:14:25", "remaining_time": "0:56:17", "throughput": 1484.55, "total_tokens": 33350592} {"current_steps": 158045, "total_steps": 181800, "loss": 0.0375, "lr": 2.5558822055031906e-06, "epoch": 17.38668866886689, "percentage": 86.93, "elapsed_time": "6:14:25", "remaining_time": "0:56:16", "throughput": 1484.55, "total_tokens": 33351712} {"current_steps": 158050, "total_steps": 181800, "loss": 0.0362, "lr": 2.554825138292327e-06, "epoch": 17.387238723872386, "percentage": 86.94, "elapsed_time": "6:14:26", "remaining_time": "0:56:16", "throughput": 1484.55, "total_tokens": 33352832} {"current_steps": 158055, "total_steps": 181800, "loss": 0.0116, "lr": 2.5537682779478655e-06, "epoch": 17.387788778877887, "percentage": 86.94, "elapsed_time": "6:14:27", "remaining_time": "0:56:15", "throughput": 1484.55, "total_tokens": 33353856} {"current_steps": 158060, "total_steps": 181800, "loss": 0.0134, "lr": 2.5527116244795506e-06, "epoch": 17.388338833883388, "percentage": 86.94, "elapsed_time": "6:14:27", "remaining_time": "0:56:14", "throughput": 1484.56, "total_tokens": 33354912} {"current_steps": 158065, "total_steps": 181800, "loss": 0.0012, "lr": 2.5516551778971193e-06, "epoch": 17.38888888888889, "percentage": 86.94, "elapsed_time": "6:14:28", "remaining_time": "0:56:13", "throughput": 1484.55, "total_tokens": 33355904} {"current_steps": 158070, "total_steps": 181800, "loss": 0.0493, "lr": 2.5505989382103106e-06, "epoch": 17.38943894389439, "percentage": 86.95, "elapsed_time": "6:14:29", "remaining_time": "0:56:13", "throughput": 1484.55, "total_tokens": 33356960} {"current_steps": 158075, "total_steps": 181800, "loss": 0.0044, "lr": 2.5495429054288617e-06, "epoch": 17.38998899889989, "percentage": 86.95, "elapsed_time": "6:14:30", "remaining_time": "0:56:12", "throughput": 1484.56, "total_tokens": 33358016} {"current_steps": 158080, "total_steps": 181800, "loss": 0.0042, "lr": 2.548487079562506e-06, "epoch": 17.39053905390539, "percentage": 86.95, "elapsed_time": "6:14:30", "remaining_time": "0:56:11", "throughput": 1484.56, "total_tokens": 33359040} {"current_steps": 158085, "total_steps": 181800, "loss": 0.1791, "lr": 2.5474314606209664e-06, "epoch": 17.39108910891089, "percentage": 86.96, "elapsed_time": "6:14:31", "remaining_time": "0:56:11", "throughput": 1484.56, "total_tokens": 33360096} {"current_steps": 158090, "total_steps": 181800, "loss": 0.004, "lr": 2.5463760486139827e-06, "epoch": 17.39163916391639, "percentage": 86.96, "elapsed_time": "6:14:32", "remaining_time": "0:56:10", "throughput": 1484.56, "total_tokens": 33361184} {"current_steps": 158095, "total_steps": 181800, "loss": 0.0099, "lr": 2.545320843551269e-06, "epoch": 17.392189218921892, "percentage": 86.96, "elapsed_time": "6:14:32", "remaining_time": "0:56:09", "throughput": 1484.56, "total_tokens": 33362240} {"current_steps": 158100, "total_steps": 181800, "loss": 0.0063, "lr": 2.5442658454425616e-06, "epoch": 17.392739273927393, "percentage": 86.96, "elapsed_time": "6:14:33", "remaining_time": "0:56:08", "throughput": 1484.56, "total_tokens": 33363296} {"current_steps": 158105, "total_steps": 181800, "loss": 0.0018, "lr": 2.543211054297584e-06, "epoch": 17.393289328932894, "percentage": 86.97, "elapsed_time": "6:14:34", "remaining_time": "0:56:08", "throughput": 1484.56, "total_tokens": 33364352} {"current_steps": 158110, "total_steps": 181800, "loss": 0.0024, "lr": 2.54215647012605e-06, "epoch": 17.393839383938396, "percentage": 86.97, "elapsed_time": "6:14:34", "remaining_time": "0:56:07", "throughput": 1484.57, "total_tokens": 33365440} {"current_steps": 158115, "total_steps": 181800, "loss": 0.0014, "lr": 2.541102092937686e-06, "epoch": 17.394389438943893, "percentage": 86.97, "elapsed_time": "6:14:35", "remaining_time": "0:56:06", "throughput": 1484.57, "total_tokens": 33366432} {"current_steps": 158120, "total_steps": 181800, "loss": 0.0045, "lr": 2.5400479227422056e-06, "epoch": 17.394939493949394, "percentage": 86.97, "elapsed_time": "6:14:36", "remaining_time": "0:56:06", "throughput": 1484.57, "total_tokens": 33367584} {"current_steps": 158125, "total_steps": 181800, "loss": 0.0072, "lr": 2.538993959549324e-06, "epoch": 17.395489548954895, "percentage": 86.98, "elapsed_time": "6:14:36", "remaining_time": "0:56:05", "throughput": 1484.57, "total_tokens": 33368672} {"current_steps": 158130, "total_steps": 181800, "loss": 0.0026, "lr": 2.537940203368763e-06, "epoch": 17.396039603960396, "percentage": 86.98, "elapsed_time": "6:14:37", "remaining_time": "0:56:04", "throughput": 1484.58, "total_tokens": 33369760} {"current_steps": 158135, "total_steps": 181800, "loss": 0.0251, "lr": 2.536886654210224e-06, "epoch": 17.396589658965897, "percentage": 86.98, "elapsed_time": "6:14:38", "remaining_time": "0:56:03", "throughput": 1484.58, "total_tokens": 33370816} {"current_steps": 158140, "total_steps": 181800, "loss": 0.0022, "lr": 2.5358333120834243e-06, "epoch": 17.3971397139714, "percentage": 86.99, "elapsed_time": "6:14:39", "remaining_time": "0:56:03", "throughput": 1484.58, "total_tokens": 33371872} {"current_steps": 158145, "total_steps": 181800, "loss": 0.0954, "lr": 2.5347801769980724e-06, "epoch": 17.397689768976896, "percentage": 86.99, "elapsed_time": "6:14:39", "remaining_time": "0:56:02", "throughput": 1484.58, "total_tokens": 33372960} {"current_steps": 158150, "total_steps": 181800, "loss": 0.0543, "lr": 2.5337272489638656e-06, "epoch": 17.398239823982397, "percentage": 86.99, "elapsed_time": "6:14:40", "remaining_time": "0:56:01", "throughput": 1484.58, "total_tokens": 33374016} {"current_steps": 158155, "total_steps": 181800, "loss": 0.014, "lr": 2.532674527990517e-06, "epoch": 17.3987898789879, "percentage": 86.99, "elapsed_time": "6:14:41", "remaining_time": "0:56:01", "throughput": 1484.59, "total_tokens": 33375136} {"current_steps": 158160, "total_steps": 181800, "loss": 0.0885, "lr": 2.5316220140877226e-06, "epoch": 17.3993399339934, "percentage": 87.0, "elapsed_time": "6:14:41", "remaining_time": "0:56:00", "throughput": 1484.59, "total_tokens": 33376224} {"current_steps": 158165, "total_steps": 181800, "loss": 0.0028, "lr": 2.5305697072651957e-06, "epoch": 17.3998899889989, "percentage": 87.0, "elapsed_time": "6:14:42", "remaining_time": "0:55:59", "throughput": 1484.59, "total_tokens": 33377280} {"current_steps": 158170, "total_steps": 181800, "loss": 0.0053, "lr": 2.529517607532622e-06, "epoch": 17.4004400440044, "percentage": 87.0, "elapsed_time": "6:14:43", "remaining_time": "0:55:58", "throughput": 1484.59, "total_tokens": 33378304} {"current_steps": 158175, "total_steps": 181800, "loss": 0.0458, "lr": 2.5284657148996997e-06, "epoch": 17.400990099009903, "percentage": 87.0, "elapsed_time": "6:14:43", "remaining_time": "0:55:58", "throughput": 1484.59, "total_tokens": 33379392} {"current_steps": 158180, "total_steps": 181800, "loss": 0.0092, "lr": 2.527414029376124e-06, "epoch": 17.4015401540154, "percentage": 87.01, "elapsed_time": "6:14:44", "remaining_time": "0:55:57", "throughput": 1484.6, "total_tokens": 33380480} {"current_steps": 158185, "total_steps": 181800, "loss": 0.0505, "lr": 2.526362550971592e-06, "epoch": 17.4020902090209, "percentage": 87.01, "elapsed_time": "6:14:45", "remaining_time": "0:55:56", "throughput": 1484.6, "total_tokens": 33381536} {"current_steps": 158190, "total_steps": 181800, "loss": 0.0988, "lr": 2.5253112796957966e-06, "epoch": 17.402640264026402, "percentage": 87.01, "elapsed_time": "6:14:45", "remaining_time": "0:55:56", "throughput": 1484.6, "total_tokens": 33382624} {"current_steps": 158195, "total_steps": 181800, "loss": 0.0932, "lr": 2.5242602155584216e-06, "epoch": 17.403190319031903, "percentage": 87.02, "elapsed_time": "6:14:46", "remaining_time": "0:55:55", "throughput": 1484.6, "total_tokens": 33383648} {"current_steps": 158200, "total_steps": 181800, "loss": 0.0141, "lr": 2.5232093585691508e-06, "epoch": 17.403740374037405, "percentage": 87.02, "elapsed_time": "6:14:47", "remaining_time": "0:55:54", "throughput": 1484.61, "total_tokens": 33384768} {"current_steps": 158205, "total_steps": 181800, "loss": 0.0183, "lr": 2.522158708737679e-06, "epoch": 17.404290429042906, "percentage": 87.02, "elapsed_time": "6:14:47", "remaining_time": "0:55:53", "throughput": 1484.61, "total_tokens": 33385824} {"current_steps": 158210, "total_steps": 181800, "loss": 0.0038, "lr": 2.5211082660736796e-06, "epoch": 17.404840484048403, "percentage": 87.02, "elapsed_time": "6:14:48", "remaining_time": "0:55:53", "throughput": 1484.61, "total_tokens": 33386848} {"current_steps": 158215, "total_steps": 181800, "loss": 0.0073, "lr": 2.5200580305868416e-06, "epoch": 17.405390539053904, "percentage": 87.03, "elapsed_time": "6:14:49", "remaining_time": "0:55:52", "throughput": 1484.61, "total_tokens": 33387872} {"current_steps": 158220, "total_steps": 181800, "loss": 0.026, "lr": 2.5190080022868434e-06, "epoch": 17.405940594059405, "percentage": 87.03, "elapsed_time": "6:14:50", "remaining_time": "0:55:51", "throughput": 1484.61, "total_tokens": 33388864} {"current_steps": 158225, "total_steps": 181800, "loss": 0.0084, "lr": 2.517958181183355e-06, "epoch": 17.406490649064907, "percentage": 87.03, "elapsed_time": "6:14:50", "remaining_time": "0:55:51", "throughput": 1484.61, "total_tokens": 33389984} {"current_steps": 158230, "total_steps": 181800, "loss": 0.0009, "lr": 2.5169085672860666e-06, "epoch": 17.407040704070408, "percentage": 87.04, "elapsed_time": "6:14:51", "remaining_time": "0:55:50", "throughput": 1484.61, "total_tokens": 33391072} {"current_steps": 158235, "total_steps": 181800, "loss": 0.015, "lr": 2.5158591606046363e-06, "epoch": 17.40759075907591, "percentage": 87.04, "elapsed_time": "6:14:52", "remaining_time": "0:55:49", "throughput": 1484.61, "total_tokens": 33392096} {"current_steps": 158240, "total_steps": 181800, "loss": 0.0029, "lr": 2.5148099611487454e-06, "epoch": 17.40814081408141, "percentage": 87.04, "elapsed_time": "6:14:52", "remaining_time": "0:55:48", "throughput": 1484.62, "total_tokens": 33393216} {"current_steps": 158245, "total_steps": 181800, "loss": 0.002, "lr": 2.5137609689280638e-06, "epoch": 17.408690869086907, "percentage": 87.04, "elapsed_time": "6:14:53", "remaining_time": "0:55:48", "throughput": 1484.62, "total_tokens": 33394304} {"current_steps": 158250, "total_steps": 181800, "loss": 0.0081, "lr": 2.512712183952254e-06, "epoch": 17.40924092409241, "percentage": 87.05, "elapsed_time": "6:14:54", "remaining_time": "0:55:47", "throughput": 1484.62, "total_tokens": 33395264} {"current_steps": 158255, "total_steps": 181800, "loss": 0.1425, "lr": 2.5116636062309905e-06, "epoch": 17.40979097909791, "percentage": 87.05, "elapsed_time": "6:14:54", "remaining_time": "0:55:46", "throughput": 1484.62, "total_tokens": 33396384} {"current_steps": 158260, "total_steps": 181800, "loss": 0.0059, "lr": 2.5106152357739277e-06, "epoch": 17.41034103410341, "percentage": 87.05, "elapsed_time": "6:14:55", "remaining_time": "0:55:46", "throughput": 1484.62, "total_tokens": 33397440} {"current_steps": 158265, "total_steps": 181800, "loss": 0.0039, "lr": 2.509567072590735e-06, "epoch": 17.41089108910891, "percentage": 87.05, "elapsed_time": "6:14:56", "remaining_time": "0:55:45", "throughput": 1484.62, "total_tokens": 33398464} {"current_steps": 158270, "total_steps": 181800, "loss": 0.074, "lr": 2.508519116691069e-06, "epoch": 17.411441144114413, "percentage": 87.06, "elapsed_time": "6:14:56", "remaining_time": "0:55:44", "throughput": 1484.62, "total_tokens": 33399488} {"current_steps": 158275, "total_steps": 181800, "loss": 0.0023, "lr": 2.507471368084588e-06, "epoch": 17.41199119911991, "percentage": 87.06, "elapsed_time": "6:14:57", "remaining_time": "0:55:43", "throughput": 1484.63, "total_tokens": 33400576} {"current_steps": 158280, "total_steps": 181800, "loss": 0.0075, "lr": 2.506423826780957e-06, "epoch": 17.41254125412541, "percentage": 87.06, "elapsed_time": "6:14:58", "remaining_time": "0:55:43", "throughput": 1484.63, "total_tokens": 33401728} {"current_steps": 158285, "total_steps": 181800, "loss": 0.1207, "lr": 2.505376492789824e-06, "epoch": 17.413091309130913, "percentage": 87.07, "elapsed_time": "6:14:58", "remaining_time": "0:55:42", "throughput": 1484.64, "total_tokens": 33402816} {"current_steps": 158290, "total_steps": 181800, "loss": 0.2598, "lr": 2.504329366120836e-06, "epoch": 17.413641364136414, "percentage": 87.07, "elapsed_time": "6:14:59", "remaining_time": "0:55:41", "throughput": 1484.64, "total_tokens": 33403840} {"current_steps": 158295, "total_steps": 181800, "loss": 0.0143, "lr": 2.50328244678365e-06, "epoch": 17.414191419141915, "percentage": 87.07, "elapsed_time": "6:15:00", "remaining_time": "0:55:41", "throughput": 1484.64, "total_tokens": 33404864} {"current_steps": 158300, "total_steps": 181800, "loss": 0.0239, "lr": 2.502235734787914e-06, "epoch": 17.414741474147416, "percentage": 87.07, "elapsed_time": "6:15:01", "remaining_time": "0:55:40", "throughput": 1484.64, "total_tokens": 33405984} {"current_steps": 158305, "total_steps": 181800, "loss": 0.0019, "lr": 2.5011892301432832e-06, "epoch": 17.415291529152917, "percentage": 87.08, "elapsed_time": "6:15:01", "remaining_time": "0:55:39", "throughput": 1484.64, "total_tokens": 33406976} {"current_steps": 158310, "total_steps": 181800, "loss": 0.068, "lr": 2.5001429328593923e-06, "epoch": 17.415841584158414, "percentage": 87.08, "elapsed_time": "6:15:02", "remaining_time": "0:55:38", "throughput": 1484.64, "total_tokens": 33408032} {"current_steps": 158315, "total_steps": 181800, "loss": 0.0265, "lr": 2.4990968429458835e-06, "epoch": 17.416391639163916, "percentage": 87.08, "elapsed_time": "6:15:03", "remaining_time": "0:55:38", "throughput": 1484.64, "total_tokens": 33409056} {"current_steps": 158320, "total_steps": 181800, "loss": 0.0207, "lr": 2.498050960412407e-06, "epoch": 17.416941694169417, "percentage": 87.08, "elapsed_time": "6:15:03", "remaining_time": "0:55:37", "throughput": 1484.64, "total_tokens": 33410080} {"current_steps": 158325, "total_steps": 181800, "loss": 0.0057, "lr": 2.497005285268594e-06, "epoch": 17.417491749174918, "percentage": 87.09, "elapsed_time": "6:15:04", "remaining_time": "0:55:36", "throughput": 1484.64, "total_tokens": 33411072} {"current_steps": 158330, "total_steps": 181800, "loss": 0.0922, "lr": 2.495959817524085e-06, "epoch": 17.41804180418042, "percentage": 87.09, "elapsed_time": "6:15:05", "remaining_time": "0:55:36", "throughput": 1484.64, "total_tokens": 33412064} {"current_steps": 158335, "total_steps": 181800, "loss": 0.0671, "lr": 2.4949145571885184e-06, "epoch": 17.41859185918592, "percentage": 87.09, "elapsed_time": "6:15:05", "remaining_time": "0:55:35", "throughput": 1484.64, "total_tokens": 33413120} {"current_steps": 158340, "total_steps": 181800, "loss": 0.0105, "lr": 2.493869504271523e-06, "epoch": 17.419141914191417, "percentage": 87.1, "elapsed_time": "6:15:06", "remaining_time": "0:55:34", "throughput": 1484.64, "total_tokens": 33414208} {"current_steps": 158345, "total_steps": 181800, "loss": 0.0042, "lr": 2.492824658782736e-06, "epoch": 17.41969196919692, "percentage": 87.1, "elapsed_time": "6:15:07", "remaining_time": "0:55:33", "throughput": 1484.64, "total_tokens": 33415264} {"current_steps": 158350, "total_steps": 181800, "loss": 0.004, "lr": 2.4917800207317792e-06, "epoch": 17.42024202420242, "percentage": 87.1, "elapsed_time": "6:15:07", "remaining_time": "0:55:33", "throughput": 1484.65, "total_tokens": 33416352} {"current_steps": 158355, "total_steps": 181800, "loss": 0.0486, "lr": 2.4907355901282877e-06, "epoch": 17.42079207920792, "percentage": 87.1, "elapsed_time": "6:15:08", "remaining_time": "0:55:32", "throughput": 1484.65, "total_tokens": 33417408} {"current_steps": 158360, "total_steps": 181800, "loss": 0.0675, "lr": 2.489691366981889e-06, "epoch": 17.421342134213422, "percentage": 87.11, "elapsed_time": "6:15:09", "remaining_time": "0:55:31", "throughput": 1484.65, "total_tokens": 33418464} {"current_steps": 158365, "total_steps": 181800, "loss": 0.0183, "lr": 2.4886473513021978e-06, "epoch": 17.421892189218923, "percentage": 87.11, "elapsed_time": "6:15:10", "remaining_time": "0:55:31", "throughput": 1484.65, "total_tokens": 33419488} {"current_steps": 158370, "total_steps": 181800, "loss": 0.0067, "lr": 2.4876035430988457e-06, "epoch": 17.422442244224424, "percentage": 87.11, "elapsed_time": "6:15:10", "remaining_time": "0:55:30", "throughput": 1484.65, "total_tokens": 33420576} {"current_steps": 158375, "total_steps": 181800, "loss": 0.0469, "lr": 2.486559942381447e-06, "epoch": 17.42299229922992, "percentage": 87.11, "elapsed_time": "6:15:11", "remaining_time": "0:55:29", "throughput": 1484.65, "total_tokens": 33421664} {"current_steps": 158380, "total_steps": 181800, "loss": 0.0013, "lr": 2.485516549159625e-06, "epoch": 17.423542354235423, "percentage": 87.12, "elapsed_time": "6:15:12", "remaining_time": "0:55:28", "throughput": 1484.66, "total_tokens": 33422752} {"current_steps": 158385, "total_steps": 181800, "loss": 0.0602, "lr": 2.4844733634429907e-06, "epoch": 17.424092409240924, "percentage": 87.12, "elapsed_time": "6:15:12", "remaining_time": "0:55:28", "throughput": 1484.66, "total_tokens": 33423776} {"current_steps": 158390, "total_steps": 181800, "loss": 0.0022, "lr": 2.4834303852411615e-06, "epoch": 17.424642464246425, "percentage": 87.12, "elapsed_time": "6:15:13", "remaining_time": "0:55:27", "throughput": 1484.66, "total_tokens": 33424896} {"current_steps": 158395, "total_steps": 181800, "loss": 0.0802, "lr": 2.4823876145637524e-06, "epoch": 17.425192519251926, "percentage": 87.13, "elapsed_time": "6:15:14", "remaining_time": "0:55:26", "throughput": 1484.66, "total_tokens": 33425984} {"current_steps": 158400, "total_steps": 181800, "loss": 0.1602, "lr": 2.4813450514203697e-06, "epoch": 17.425742574257427, "percentage": 87.13, "elapsed_time": "6:15:14", "remaining_time": "0:55:26", "throughput": 1484.66, "total_tokens": 33426976} {"current_steps": 158405, "total_steps": 181800, "loss": 0.0057, "lr": 2.480302695820627e-06, "epoch": 17.426292629262925, "percentage": 87.13, "elapsed_time": "6:15:15", "remaining_time": "0:55:25", "throughput": 1484.67, "total_tokens": 33428096} {"current_steps": 158410, "total_steps": 181800, "loss": 0.02, "lr": 2.479260547774123e-06, "epoch": 17.426842684268426, "percentage": 87.13, "elapsed_time": "6:15:16", "remaining_time": "0:55:24", "throughput": 1484.67, "total_tokens": 33429216} {"current_steps": 158415, "total_steps": 181800, "loss": 0.0014, "lr": 2.4782186072904693e-06, "epoch": 17.427392739273927, "percentage": 87.14, "elapsed_time": "6:15:16", "remaining_time": "0:55:23", "throughput": 1484.67, "total_tokens": 33430240} {"current_steps": 158420, "total_steps": 181800, "loss": 0.1106, "lr": 2.477176874379272e-06, "epoch": 17.427942794279428, "percentage": 87.14, "elapsed_time": "6:15:17", "remaining_time": "0:55:23", "throughput": 1484.67, "total_tokens": 33431328} {"current_steps": 158425, "total_steps": 181800, "loss": 0.0018, "lr": 2.4761353490501237e-06, "epoch": 17.42849284928493, "percentage": 87.14, "elapsed_time": "6:15:18", "remaining_time": "0:55:22", "throughput": 1484.67, "total_tokens": 33432352} {"current_steps": 158430, "total_steps": 181800, "loss": 0.0498, "lr": 2.475094031312633e-06, "epoch": 17.42904290429043, "percentage": 87.15, "elapsed_time": "6:15:19", "remaining_time": "0:55:21", "throughput": 1484.67, "total_tokens": 33433440} {"current_steps": 158435, "total_steps": 181800, "loss": 0.006, "lr": 2.4740529211763895e-06, "epoch": 17.42959295929593, "percentage": 87.15, "elapsed_time": "6:15:19", "remaining_time": "0:55:21", "throughput": 1484.67, "total_tokens": 33434464} {"current_steps": 158440, "total_steps": 181800, "loss": 0.0534, "lr": 2.4730120186509885e-06, "epoch": 17.43014301430143, "percentage": 87.15, "elapsed_time": "6:15:20", "remaining_time": "0:55:20", "throughput": 1484.67, "total_tokens": 33435456} {"current_steps": 158445, "total_steps": 181800, "loss": 0.0794, "lr": 2.4719713237460277e-06, "epoch": 17.43069306930693, "percentage": 87.15, "elapsed_time": "6:15:21", "remaining_time": "0:55:19", "throughput": 1484.67, "total_tokens": 33436480} {"current_steps": 158450, "total_steps": 181800, "loss": 0.0269, "lr": 2.4709308364710943e-06, "epoch": 17.43124312431243, "percentage": 87.16, "elapsed_time": "6:15:21", "remaining_time": "0:55:18", "throughput": 1484.68, "total_tokens": 33437568} {"current_steps": 158455, "total_steps": 181800, "loss": 0.0013, "lr": 2.4698905568357885e-06, "epoch": 17.431793179317932, "percentage": 87.16, "elapsed_time": "6:15:22", "remaining_time": "0:55:18", "throughput": 1484.68, "total_tokens": 33438656} {"current_steps": 158460, "total_steps": 181800, "loss": 0.0025, "lr": 2.4688504848496885e-06, "epoch": 17.432343234323433, "percentage": 87.16, "elapsed_time": "6:15:23", "remaining_time": "0:55:17", "throughput": 1484.68, "total_tokens": 33439744} {"current_steps": 158465, "total_steps": 181800, "loss": 0.0025, "lr": 2.467810620522376e-06, "epoch": 17.432893289328934, "percentage": 87.16, "elapsed_time": "6:15:23", "remaining_time": "0:55:16", "throughput": 1484.68, "total_tokens": 33440768} {"current_steps": 158470, "total_steps": 181800, "loss": 0.0161, "lr": 2.4667709638634434e-06, "epoch": 17.433443344334435, "percentage": 87.17, "elapsed_time": "6:15:24", "remaining_time": "0:55:16", "throughput": 1484.68, "total_tokens": 33441856} {"current_steps": 158475, "total_steps": 181800, "loss": 0.0067, "lr": 2.4657315148824746e-06, "epoch": 17.433993399339933, "percentage": 87.17, "elapsed_time": "6:15:25", "remaining_time": "0:55:15", "throughput": 1484.69, "total_tokens": 33442912} {"current_steps": 158480, "total_steps": 181800, "loss": 0.0036, "lr": 2.464692273589042e-06, "epoch": 17.434543454345434, "percentage": 87.17, "elapsed_time": "6:15:25", "remaining_time": "0:55:14", "throughput": 1484.69, "total_tokens": 33444032} {"current_steps": 158485, "total_steps": 181800, "loss": 0.0884, "lr": 2.4636532399927304e-06, "epoch": 17.435093509350935, "percentage": 87.18, "elapsed_time": "6:15:26", "remaining_time": "0:55:13", "throughput": 1484.7, "total_tokens": 33445184} {"current_steps": 158490, "total_steps": 181800, "loss": 0.0061, "lr": 2.4626144141031067e-06, "epoch": 17.435643564356436, "percentage": 87.18, "elapsed_time": "6:15:27", "remaining_time": "0:55:13", "throughput": 1484.7, "total_tokens": 33446208} {"current_steps": 158495, "total_steps": 181800, "loss": 0.0405, "lr": 2.4615757959297574e-06, "epoch": 17.436193619361937, "percentage": 87.18, "elapsed_time": "6:15:27", "remaining_time": "0:55:12", "throughput": 1484.69, "total_tokens": 33447200} {"current_steps": 158500, "total_steps": 181800, "loss": 0.0081, "lr": 2.460537385482245e-06, "epoch": 17.436743674367438, "percentage": 87.18, "elapsed_time": "6:15:28", "remaining_time": "0:55:11", "throughput": 1484.69, "total_tokens": 33448224} {"current_steps": 158505, "total_steps": 181800, "loss": 0.0193, "lr": 2.4594991827701445e-06, "epoch": 17.437293729372936, "percentage": 87.19, "elapsed_time": "6:15:29", "remaining_time": "0:55:11", "throughput": 1484.7, "total_tokens": 33449280} {"current_steps": 158510, "total_steps": 181800, "loss": 0.0079, "lr": 2.458461187803027e-06, "epoch": 17.437843784378437, "percentage": 87.19, "elapsed_time": "6:15:30", "remaining_time": "0:55:10", "throughput": 1484.7, "total_tokens": 33450368} {"current_steps": 158515, "total_steps": 181800, "loss": 0.0034, "lr": 2.457423400590453e-06, "epoch": 17.438393839383938, "percentage": 87.19, "elapsed_time": "6:15:30", "remaining_time": "0:55:09", "throughput": 1484.7, "total_tokens": 33451424} {"current_steps": 158520, "total_steps": 181800, "loss": 0.0046, "lr": 2.4563858211419932e-06, "epoch": 17.43894389438944, "percentage": 87.19, "elapsed_time": "6:15:31", "remaining_time": "0:55:08", "throughput": 1484.7, "total_tokens": 33452480} {"current_steps": 158525, "total_steps": 181800, "loss": 0.0342, "lr": 2.4553484494672097e-06, "epoch": 17.43949394939494, "percentage": 87.2, "elapsed_time": "6:15:32", "remaining_time": "0:55:08", "throughput": 1484.7, "total_tokens": 33453568} {"current_steps": 158530, "total_steps": 181800, "loss": 0.0731, "lr": 2.454311285575653e-06, "epoch": 17.44004400440044, "percentage": 87.2, "elapsed_time": "6:15:32", "remaining_time": "0:55:07", "throughput": 1484.7, "total_tokens": 33454560} {"current_steps": 158535, "total_steps": 181800, "loss": 0.0239, "lr": 2.4532743294768984e-06, "epoch": 17.440594059405942, "percentage": 87.2, "elapsed_time": "6:15:33", "remaining_time": "0:55:06", "throughput": 1484.7, "total_tokens": 33455616} {"current_steps": 158540, "total_steps": 181800, "loss": 0.0017, "lr": 2.4522375811804916e-06, "epoch": 17.44114411441144, "percentage": 87.21, "elapsed_time": "6:15:34", "remaining_time": "0:55:06", "throughput": 1484.7, "total_tokens": 33456640} {"current_steps": 158545, "total_steps": 181800, "loss": 0.04, "lr": 2.451201040695994e-06, "epoch": 17.44169416941694, "percentage": 87.21, "elapsed_time": "6:15:34", "remaining_time": "0:55:05", "throughput": 1484.71, "total_tokens": 33457728} {"current_steps": 158550, "total_steps": 181800, "loss": 0.0032, "lr": 2.4501647080329595e-06, "epoch": 17.442244224422442, "percentage": 87.21, "elapsed_time": "6:15:35", "remaining_time": "0:55:04", "throughput": 1484.71, "total_tokens": 33458752} {"current_steps": 158555, "total_steps": 181800, "loss": 0.1386, "lr": 2.4491285832009298e-06, "epoch": 17.442794279427943, "percentage": 87.21, "elapsed_time": "6:15:36", "remaining_time": "0:55:03", "throughput": 1484.71, "total_tokens": 33459872} {"current_steps": 158560, "total_steps": 181800, "loss": 0.0501, "lr": 2.4480926662094617e-06, "epoch": 17.443344334433444, "percentage": 87.22, "elapsed_time": "6:15:36", "remaining_time": "0:55:03", "throughput": 1484.71, "total_tokens": 33460992} {"current_steps": 158565, "total_steps": 181800, "loss": 0.0863, "lr": 2.447056957068103e-06, "epoch": 17.443894389438945, "percentage": 87.22, "elapsed_time": "6:15:37", "remaining_time": "0:55:02", "throughput": 1484.72, "total_tokens": 33462112} {"current_steps": 158570, "total_steps": 181800, "loss": 0.0014, "lr": 2.4460214557864014e-06, "epoch": 17.444444444444443, "percentage": 87.22, "elapsed_time": "6:15:38", "remaining_time": "0:55:01", "throughput": 1484.72, "total_tokens": 33463200} {"current_steps": 158575, "total_steps": 181800, "loss": 0.0051, "lr": 2.4449861623738967e-06, "epoch": 17.444994499449944, "percentage": 87.22, "elapsed_time": "6:15:39", "remaining_time": "0:55:01", "throughput": 1484.72, "total_tokens": 33464224} {"current_steps": 158580, "total_steps": 181800, "loss": 0.017, "lr": 2.4439510768401286e-06, "epoch": 17.445544554455445, "percentage": 87.23, "elapsed_time": "6:15:39", "remaining_time": "0:55:00", "throughput": 1484.72, "total_tokens": 33465280} {"current_steps": 158585, "total_steps": 181800, "loss": 0.0098, "lr": 2.4429161991946447e-06, "epoch": 17.446094609460946, "percentage": 87.23, "elapsed_time": "6:15:40", "remaining_time": "0:54:59", "throughput": 1484.72, "total_tokens": 33466304} {"current_steps": 158590, "total_steps": 181800, "loss": 0.0055, "lr": 2.4418815294469684e-06, "epoch": 17.446644664466447, "percentage": 87.23, "elapsed_time": "6:15:41", "remaining_time": "0:54:58", "throughput": 1484.72, "total_tokens": 33467328} {"current_steps": 158595, "total_steps": 181800, "loss": 0.0045, "lr": 2.4408470676066553e-06, "epoch": 17.44719471947195, "percentage": 87.24, "elapsed_time": "6:15:41", "remaining_time": "0:54:58", "throughput": 1484.72, "total_tokens": 33468416} {"current_steps": 158600, "total_steps": 181800, "loss": 0.0288, "lr": 2.4398128136832317e-06, "epoch": 17.44774477447745, "percentage": 87.24, "elapsed_time": "6:15:42", "remaining_time": "0:54:57", "throughput": 1484.73, "total_tokens": 33469472} {"current_steps": 158605, "total_steps": 181800, "loss": 0.0006, "lr": 2.43877876768622e-06, "epoch": 17.448294829482947, "percentage": 87.24, "elapsed_time": "6:15:43", "remaining_time": "0:54:56", "throughput": 1484.72, "total_tokens": 33470464} {"current_steps": 158610, "total_steps": 181800, "loss": 0.0507, "lr": 2.437744929625166e-06, "epoch": 17.448844884488448, "percentage": 87.24, "elapsed_time": "6:15:43", "remaining_time": "0:54:56", "throughput": 1484.73, "total_tokens": 33471552} {"current_steps": 158615, "total_steps": 181800, "loss": 0.0407, "lr": 2.436711299509584e-06, "epoch": 17.44939493949395, "percentage": 87.25, "elapsed_time": "6:15:44", "remaining_time": "0:54:55", "throughput": 1484.73, "total_tokens": 33472576} {"current_steps": 158620, "total_steps": 181800, "loss": 0.0034, "lr": 2.4356778773490076e-06, "epoch": 17.44994499449945, "percentage": 87.25, "elapsed_time": "6:15:45", "remaining_time": "0:54:54", "throughput": 1484.73, "total_tokens": 33473600} {"current_steps": 158625, "total_steps": 181800, "loss": 0.0021, "lr": 2.434644663152963e-06, "epoch": 17.45049504950495, "percentage": 87.25, "elapsed_time": "6:15:45", "remaining_time": "0:54:53", "throughput": 1484.73, "total_tokens": 33474720} {"current_steps": 158630, "total_steps": 181800, "loss": 0.0025, "lr": 2.4336116569309703e-06, "epoch": 17.451045104510452, "percentage": 87.26, "elapsed_time": "6:15:46", "remaining_time": "0:54:53", "throughput": 1484.73, "total_tokens": 33475776} {"current_steps": 158635, "total_steps": 181800, "loss": 0.0012, "lr": 2.4325788586925523e-06, "epoch": 17.45159515951595, "percentage": 87.26, "elapsed_time": "6:15:47", "remaining_time": "0:54:52", "throughput": 1484.73, "total_tokens": 33476832} {"current_steps": 158640, "total_steps": 181800, "loss": 0.004, "lr": 2.431546268447221e-06, "epoch": 17.45214521452145, "percentage": 87.26, "elapsed_time": "6:15:48", "remaining_time": "0:54:51", "throughput": 1484.73, "total_tokens": 33477888} {"current_steps": 158645, "total_steps": 181800, "loss": 0.0792, "lr": 2.430513886204505e-06, "epoch": 17.452695269526952, "percentage": 87.26, "elapsed_time": "6:15:48", "remaining_time": "0:54:51", "throughput": 1484.73, "total_tokens": 33478880} {"current_steps": 158650, "total_steps": 181800, "loss": 0.0032, "lr": 2.429481711973908e-06, "epoch": 17.453245324532453, "percentage": 87.27, "elapsed_time": "6:15:49", "remaining_time": "0:54:50", "throughput": 1484.73, "total_tokens": 33479968} {"current_steps": 158655, "total_steps": 181800, "loss": 0.0077, "lr": 2.4284497457649464e-06, "epoch": 17.453795379537954, "percentage": 87.27, "elapsed_time": "6:15:50", "remaining_time": "0:54:49", "throughput": 1484.73, "total_tokens": 33480992} {"current_steps": 158660, "total_steps": 181800, "loss": 0.0057, "lr": 2.4274179875871382e-06, "epoch": 17.454345434543455, "percentage": 87.27, "elapsed_time": "6:15:50", "remaining_time": "0:54:48", "throughput": 1484.74, "total_tokens": 33482144} {"current_steps": 158665, "total_steps": 181800, "loss": 0.032, "lr": 2.4263864374499816e-06, "epoch": 17.454895489548957, "percentage": 87.27, "elapsed_time": "6:15:51", "remaining_time": "0:54:48", "throughput": 1484.74, "total_tokens": 33483168} {"current_steps": 158670, "total_steps": 181800, "loss": 0.0124, "lr": 2.425355095362994e-06, "epoch": 17.455445544554454, "percentage": 87.28, "elapsed_time": "6:15:52", "remaining_time": "0:54:47", "throughput": 1484.74, "total_tokens": 33484224} {"current_steps": 158675, "total_steps": 181800, "loss": 0.0308, "lr": 2.4243239613356726e-06, "epoch": 17.455995599559955, "percentage": 87.28, "elapsed_time": "6:15:52", "remaining_time": "0:54:46", "throughput": 1484.74, "total_tokens": 33485280} {"current_steps": 158680, "total_steps": 181800, "loss": 0.0142, "lr": 2.4232930353775217e-06, "epoch": 17.456545654565456, "percentage": 87.28, "elapsed_time": "6:15:53", "remaining_time": "0:54:46", "throughput": 1484.74, "total_tokens": 33486304} {"current_steps": 158685, "total_steps": 181800, "loss": 0.0008, "lr": 2.422262317498053e-06, "epoch": 17.457095709570957, "percentage": 87.29, "elapsed_time": "6:15:54", "remaining_time": "0:54:45", "throughput": 1484.74, "total_tokens": 33487360} {"current_steps": 158690, "total_steps": 181800, "loss": 0.0036, "lr": 2.4212318077067584e-06, "epoch": 17.45764576457646, "percentage": 87.29, "elapsed_time": "6:15:54", "remaining_time": "0:54:44", "throughput": 1484.74, "total_tokens": 33488384} {"current_steps": 158695, "total_steps": 181800, "loss": 0.0043, "lr": 2.420201506013131e-06, "epoch": 17.45819581958196, "percentage": 87.29, "elapsed_time": "6:15:55", "remaining_time": "0:54:43", "throughput": 1484.75, "total_tokens": 33489440} {"current_steps": 158700, "total_steps": 181800, "loss": 0.0187, "lr": 2.419171412426674e-06, "epoch": 17.458745874587457, "percentage": 87.29, "elapsed_time": "6:15:56", "remaining_time": "0:54:43", "throughput": 1484.75, "total_tokens": 33490496} {"current_steps": 158705, "total_steps": 181800, "loss": 0.0011, "lr": 2.418141526956877e-06, "epoch": 17.459295929592958, "percentage": 87.3, "elapsed_time": "6:15:57", "remaining_time": "0:54:42", "throughput": 1484.75, "total_tokens": 33491520} {"current_steps": 158710, "total_steps": 181800, "loss": 0.022, "lr": 2.417111849613232e-06, "epoch": 17.45984598459846, "percentage": 87.3, "elapsed_time": "6:15:57", "remaining_time": "0:54:41", "throughput": 1484.75, "total_tokens": 33492608} {"current_steps": 158715, "total_steps": 181800, "loss": 0.0096, "lr": 2.416082380405235e-06, "epoch": 17.46039603960396, "percentage": 87.3, "elapsed_time": "6:15:58", "remaining_time": "0:54:41", "throughput": 1484.75, "total_tokens": 33493696} {"current_steps": 158720, "total_steps": 181800, "loss": 0.0026, "lr": 2.415053119342367e-06, "epoch": 17.46094609460946, "percentage": 87.3, "elapsed_time": "6:15:59", "remaining_time": "0:54:40", "throughput": 1484.76, "total_tokens": 33494816} {"current_steps": 158725, "total_steps": 181800, "loss": 0.1016, "lr": 2.41402406643412e-06, "epoch": 17.461496149614963, "percentage": 87.31, "elapsed_time": "6:15:59", "remaining_time": "0:54:39", "throughput": 1484.75, "total_tokens": 33495808} {"current_steps": 158730, "total_steps": 181800, "loss": 0.0522, "lr": 2.412995221689973e-06, "epoch": 17.462046204620464, "percentage": 87.31, "elapsed_time": "6:16:00", "remaining_time": "0:54:38", "throughput": 1484.75, "total_tokens": 33496800} {"current_steps": 158735, "total_steps": 181800, "loss": 0.0029, "lr": 2.4119665851194102e-06, "epoch": 17.46259625962596, "percentage": 87.31, "elapsed_time": "6:16:01", "remaining_time": "0:54:38", "throughput": 1484.76, "total_tokens": 33497888} {"current_steps": 158740, "total_steps": 181800, "loss": 0.0036, "lr": 2.4109381567319152e-06, "epoch": 17.463146314631462, "percentage": 87.32, "elapsed_time": "6:16:01", "remaining_time": "0:54:37", "throughput": 1484.76, "total_tokens": 33498976} {"current_steps": 158745, "total_steps": 181800, "loss": 0.0034, "lr": 2.409909936536961e-06, "epoch": 17.463696369636963, "percentage": 87.32, "elapsed_time": "6:16:02", "remaining_time": "0:54:36", "throughput": 1484.76, "total_tokens": 33499968} {"current_steps": 158750, "total_steps": 181800, "loss": 0.0444, "lr": 2.408881924544032e-06, "epoch": 17.464246424642464, "percentage": 87.32, "elapsed_time": "6:16:03", "remaining_time": "0:54:36", "throughput": 1484.76, "total_tokens": 33500992} {"current_steps": 158755, "total_steps": 181800, "loss": 0.076, "lr": 2.40785412076259e-06, "epoch": 17.464796479647966, "percentage": 87.32, "elapsed_time": "6:16:03", "remaining_time": "0:54:35", "throughput": 1484.76, "total_tokens": 33502144} {"current_steps": 158760, "total_steps": 181800, "loss": 0.003, "lr": 2.4068265252021245e-06, "epoch": 17.465346534653467, "percentage": 87.33, "elapsed_time": "6:16:04", "remaining_time": "0:54:34", "throughput": 1484.77, "total_tokens": 33503232} {"current_steps": 158765, "total_steps": 181800, "loss": 0.0152, "lr": 2.4057991378720916e-06, "epoch": 17.465896589658964, "percentage": 87.33, "elapsed_time": "6:16:05", "remaining_time": "0:54:33", "throughput": 1484.77, "total_tokens": 33504288} {"current_steps": 158770, "total_steps": 181800, "loss": 0.0007, "lr": 2.404771958781965e-06, "epoch": 17.466446644664465, "percentage": 87.33, "elapsed_time": "6:16:06", "remaining_time": "0:54:33", "throughput": 1484.77, "total_tokens": 33505344} {"current_steps": 158775, "total_steps": 181800, "loss": 0.0315, "lr": 2.40374498794122e-06, "epoch": 17.466996699669966, "percentage": 87.33, "elapsed_time": "6:16:06", "remaining_time": "0:54:32", "throughput": 1484.77, "total_tokens": 33506400} {"current_steps": 158780, "total_steps": 181800, "loss": 0.0092, "lr": 2.40271822535931e-06, "epoch": 17.467546754675467, "percentage": 87.34, "elapsed_time": "6:16:07", "remaining_time": "0:54:31", "throughput": 1484.77, "total_tokens": 33507424} {"current_steps": 158785, "total_steps": 181800, "loss": 0.0014, "lr": 2.4016916710457057e-06, "epoch": 17.46809680968097, "percentage": 87.34, "elapsed_time": "6:16:08", "remaining_time": "0:54:31", "throughput": 1484.77, "total_tokens": 33508512} {"current_steps": 158790, "total_steps": 181800, "loss": 0.0019, "lr": 2.4006653250098625e-06, "epoch": 17.46864686468647, "percentage": 87.34, "elapsed_time": "6:16:08", "remaining_time": "0:54:30", "throughput": 1484.78, "total_tokens": 33509600} {"current_steps": 158795, "total_steps": 181800, "loss": 0.0266, "lr": 2.3996391872612404e-06, "epoch": 17.46919691969197, "percentage": 87.35, "elapsed_time": "6:16:09", "remaining_time": "0:54:29", "throughput": 1484.78, "total_tokens": 33510688} {"current_steps": 158800, "total_steps": 181800, "loss": 0.0059, "lr": 2.398613257809307e-06, "epoch": 17.46974697469747, "percentage": 87.35, "elapsed_time": "6:16:10", "remaining_time": "0:54:28", "throughput": 1484.78, "total_tokens": 33511744} {"current_steps": 158805, "total_steps": 181800, "loss": 0.1025, "lr": 2.3975875366635036e-06, "epoch": 17.47029702970297, "percentage": 87.35, "elapsed_time": "6:16:10", "remaining_time": "0:54:28", "throughput": 1484.78, "total_tokens": 33512800} {"current_steps": 158810, "total_steps": 181800, "loss": 0.0181, "lr": 2.3965620238332933e-06, "epoch": 17.47084708470847, "percentage": 87.35, "elapsed_time": "6:16:11", "remaining_time": "0:54:27", "throughput": 1484.78, "total_tokens": 33513824} {"current_steps": 158815, "total_steps": 181800, "loss": 0.0012, "lr": 2.395536719328129e-06, "epoch": 17.47139713971397, "percentage": 87.36, "elapsed_time": "6:16:12", "remaining_time": "0:54:26", "throughput": 1484.78, "total_tokens": 33514880} {"current_steps": 158820, "total_steps": 181800, "loss": 0.1793, "lr": 2.394511623157447e-06, "epoch": 17.471947194719473, "percentage": 87.36, "elapsed_time": "6:16:12", "remaining_time": "0:54:26", "throughput": 1484.78, "total_tokens": 33515904} {"current_steps": 158825, "total_steps": 181800, "loss": 0.1333, "lr": 2.393486735330705e-06, "epoch": 17.472497249724974, "percentage": 87.36, "elapsed_time": "6:16:13", "remaining_time": "0:54:25", "throughput": 1484.79, "total_tokens": 33517024} {"current_steps": 158830, "total_steps": 181800, "loss": 0.0601, "lr": 2.3924620558573503e-06, "epoch": 17.47304730473047, "percentage": 87.37, "elapsed_time": "6:16:14", "remaining_time": "0:54:24", "throughput": 1484.78, "total_tokens": 33518016} {"current_steps": 158835, "total_steps": 181800, "loss": 0.0208, "lr": 2.3914375847468277e-06, "epoch": 17.473597359735972, "percentage": 87.37, "elapsed_time": "6:16:15", "remaining_time": "0:54:23", "throughput": 1484.78, "total_tokens": 33519008} {"current_steps": 158840, "total_steps": 181800, "loss": 0.0033, "lr": 2.3904133220085778e-06, "epoch": 17.474147414741473, "percentage": 87.37, "elapsed_time": "6:16:15", "remaining_time": "0:54:23", "throughput": 1484.79, "total_tokens": 33520160} {"current_steps": 158845, "total_steps": 181800, "loss": 0.0518, "lr": 2.389389267652034e-06, "epoch": 17.474697469746975, "percentage": 87.37, "elapsed_time": "6:16:16", "remaining_time": "0:54:22", "throughput": 1484.79, "total_tokens": 33521184} {"current_steps": 158850, "total_steps": 181800, "loss": 0.0017, "lr": 2.3883654216866393e-06, "epoch": 17.475247524752476, "percentage": 87.38, "elapsed_time": "6:16:17", "remaining_time": "0:54:21", "throughput": 1484.79, "total_tokens": 33522272} {"current_steps": 158855, "total_steps": 181800, "loss": 0.0015, "lr": 2.38734178412183e-06, "epoch": 17.475797579757977, "percentage": 87.38, "elapsed_time": "6:16:17", "remaining_time": "0:54:21", "throughput": 1484.79, "total_tokens": 33523296} {"current_steps": 158860, "total_steps": 181800, "loss": 0.0286, "lr": 2.3863183549670433e-06, "epoch": 17.476347634763478, "percentage": 87.38, "elapsed_time": "6:16:18", "remaining_time": "0:54:20", "throughput": 1484.79, "total_tokens": 33524320} {"current_steps": 158865, "total_steps": 181800, "loss": 0.0848, "lr": 2.3852951342317133e-06, "epoch": 17.476897689768975, "percentage": 87.38, "elapsed_time": "6:16:19", "remaining_time": "0:54:19", "throughput": 1484.79, "total_tokens": 33525312} {"current_steps": 158870, "total_steps": 181800, "loss": 0.0053, "lr": 2.38427212192526e-06, "epoch": 17.477447744774476, "percentage": 87.39, "elapsed_time": "6:16:19", "remaining_time": "0:54:18", "throughput": 1484.79, "total_tokens": 33526400} {"current_steps": 158875, "total_steps": 181800, "loss": 0.0738, "lr": 2.3832493180571238e-06, "epoch": 17.477997799779978, "percentage": 87.39, "elapsed_time": "6:16:20", "remaining_time": "0:54:18", "throughput": 1484.79, "total_tokens": 33527488} {"current_steps": 158880, "total_steps": 181800, "loss": 0.0019, "lr": 2.382226722636721e-06, "epoch": 17.47854785478548, "percentage": 87.39, "elapsed_time": "6:16:21", "remaining_time": "0:54:17", "throughput": 1484.8, "total_tokens": 33528544} {"current_steps": 158885, "total_steps": 181800, "loss": 0.0013, "lr": 2.3812043356734813e-06, "epoch": 17.47909790979098, "percentage": 87.4, "elapsed_time": "6:16:21", "remaining_time": "0:54:16", "throughput": 1484.8, "total_tokens": 33529600} {"current_steps": 158890, "total_steps": 181800, "loss": 0.0085, "lr": 2.38018215717683e-06, "epoch": 17.47964796479648, "percentage": 87.4, "elapsed_time": "6:16:22", "remaining_time": "0:54:16", "throughput": 1484.8, "total_tokens": 33530656} {"current_steps": 158895, "total_steps": 181800, "loss": 0.0376, "lr": 2.3791601871561845e-06, "epoch": 17.480198019801982, "percentage": 87.4, "elapsed_time": "6:16:23", "remaining_time": "0:54:15", "throughput": 1484.8, "total_tokens": 33531744} {"current_steps": 158900, "total_steps": 181800, "loss": 0.0085, "lr": 2.3781384256209684e-06, "epoch": 17.48074807480748, "percentage": 87.4, "elapsed_time": "6:16:24", "remaining_time": "0:54:14", "throughput": 1484.8, "total_tokens": 33532800} {"current_steps": 158905, "total_steps": 181800, "loss": 0.0045, "lr": 2.3771168725805927e-06, "epoch": 17.48129812981298, "percentage": 87.41, "elapsed_time": "6:16:24", "remaining_time": "0:54:13", "throughput": 1484.8, "total_tokens": 33533856} {"current_steps": 158910, "total_steps": 181800, "loss": 0.0034, "lr": 2.3760955280444725e-06, "epoch": 17.48184818481848, "percentage": 87.41, "elapsed_time": "6:16:25", "remaining_time": "0:54:13", "throughput": 1484.81, "total_tokens": 33534912} {"current_steps": 158915, "total_steps": 181800, "loss": 0.0022, "lr": 2.375074392022028e-06, "epoch": 17.482398239823983, "percentage": 87.41, "elapsed_time": "6:16:26", "remaining_time": "0:54:12", "throughput": 1484.81, "total_tokens": 33535968} {"current_steps": 158920, "total_steps": 181800, "loss": 0.0019, "lr": 2.374053464522663e-06, "epoch": 17.482948294829484, "percentage": 87.41, "elapsed_time": "6:16:26", "remaining_time": "0:54:11", "throughput": 1484.81, "total_tokens": 33537056} {"current_steps": 158925, "total_steps": 181800, "loss": 0.0034, "lr": 2.3730327455557977e-06, "epoch": 17.483498349834985, "percentage": 87.42, "elapsed_time": "6:16:27", "remaining_time": "0:54:11", "throughput": 1484.81, "total_tokens": 33538048} {"current_steps": 158930, "total_steps": 181800, "loss": 0.1683, "lr": 2.372012235130827e-06, "epoch": 17.484048404840483, "percentage": 87.42, "elapsed_time": "6:16:28", "remaining_time": "0:54:10", "throughput": 1484.81, "total_tokens": 33539104} {"current_steps": 158935, "total_steps": 181800, "loss": 0.0029, "lr": 2.3709919332571606e-06, "epoch": 17.484598459845984, "percentage": 87.42, "elapsed_time": "6:16:28", "remaining_time": "0:54:09", "throughput": 1484.81, "total_tokens": 33540128} {"current_steps": 158940, "total_steps": 181800, "loss": 0.0009, "lr": 2.369971839944202e-06, "epoch": 17.485148514851485, "percentage": 87.43, "elapsed_time": "6:16:29", "remaining_time": "0:54:09", "throughput": 1484.81, "total_tokens": 33541216} {"current_steps": 158945, "total_steps": 181800, "loss": 0.0657, "lr": 2.368951955201354e-06, "epoch": 17.485698569856986, "percentage": 87.43, "elapsed_time": "6:16:30", "remaining_time": "0:54:08", "throughput": 1484.81, "total_tokens": 33542208} {"current_steps": 158950, "total_steps": 181800, "loss": 0.0087, "lr": 2.367932279038021e-06, "epoch": 17.486248624862487, "percentage": 87.43, "elapsed_time": "6:16:30", "remaining_time": "0:54:07", "throughput": 1484.81, "total_tokens": 33543232} {"current_steps": 158955, "total_steps": 181800, "loss": 0.0041, "lr": 2.3669128114635953e-06, "epoch": 17.486798679867988, "percentage": 87.43, "elapsed_time": "6:16:31", "remaining_time": "0:54:06", "throughput": 1484.81, "total_tokens": 33544256} {"current_steps": 158960, "total_steps": 181800, "loss": 0.068, "lr": 2.365893552487469e-06, "epoch": 17.48734873487349, "percentage": 87.44, "elapsed_time": "6:16:32", "remaining_time": "0:54:06", "throughput": 1484.81, "total_tokens": 33545312} {"current_steps": 158965, "total_steps": 181800, "loss": 0.0505, "lr": 2.3648745021190438e-06, "epoch": 17.487898789878987, "percentage": 87.44, "elapsed_time": "6:16:32", "remaining_time": "0:54:05", "throughput": 1484.81, "total_tokens": 33546304} {"current_steps": 158970, "total_steps": 181800, "loss": 0.0023, "lr": 2.363855660367706e-06, "epoch": 17.488448844884488, "percentage": 87.44, "elapsed_time": "6:16:33", "remaining_time": "0:54:04", "throughput": 1484.81, "total_tokens": 33547328} {"current_steps": 158975, "total_steps": 181800, "loss": 0.0086, "lr": 2.3628370272428564e-06, "epoch": 17.48899889988999, "percentage": 87.44, "elapsed_time": "6:16:34", "remaining_time": "0:54:04", "throughput": 1484.81, "total_tokens": 33548352} {"current_steps": 158980, "total_steps": 181800, "loss": 0.0015, "lr": 2.3618186027538736e-06, "epoch": 17.48954895489549, "percentage": 87.45, "elapsed_time": "6:16:35", "remaining_time": "0:54:03", "throughput": 1484.81, "total_tokens": 33549440} {"current_steps": 158985, "total_steps": 181800, "loss": 0.0215, "lr": 2.3608003869101393e-06, "epoch": 17.49009900990099, "percentage": 87.45, "elapsed_time": "6:16:35", "remaining_time": "0:54:02", "throughput": 1484.82, "total_tokens": 33550528} {"current_steps": 158990, "total_steps": 181800, "loss": 0.0828, "lr": 2.359782379721051e-06, "epoch": 17.490649064906492, "percentage": 87.45, "elapsed_time": "6:16:36", "remaining_time": "0:54:01", "throughput": 1484.82, "total_tokens": 33551616} {"current_steps": 158995, "total_steps": 181800, "loss": 0.1041, "lr": 2.3587645811959796e-06, "epoch": 17.49119911991199, "percentage": 87.46, "elapsed_time": "6:16:37", "remaining_time": "0:54:01", "throughput": 1484.82, "total_tokens": 33552608} {"current_steps": 159000, "total_steps": 181800, "loss": 0.0457, "lr": 2.357746991344312e-06, "epoch": 17.49174917491749, "percentage": 87.46, "elapsed_time": "6:16:37", "remaining_time": "0:54:00", "throughput": 1484.82, "total_tokens": 33553696} {"current_steps": 159005, "total_steps": 181800, "loss": 0.0023, "lr": 2.356729610175429e-06, "epoch": 17.492299229922992, "percentage": 87.46, "elapsed_time": "6:16:38", "remaining_time": "0:53:59", "throughput": 1484.82, "total_tokens": 33554784} {"current_steps": 159010, "total_steps": 181800, "loss": 0.0026, "lr": 2.3557124376987012e-06, "epoch": 17.492849284928493, "percentage": 87.46, "elapsed_time": "6:16:39", "remaining_time": "0:53:59", "throughput": 1484.83, "total_tokens": 33555872} {"current_steps": 159015, "total_steps": 181800, "loss": 0.0383, "lr": 2.3546954739235074e-06, "epoch": 17.493399339933994, "percentage": 87.47, "elapsed_time": "6:16:39", "remaining_time": "0:53:58", "throughput": 1484.83, "total_tokens": 33556928} {"current_steps": 159020, "total_steps": 181800, "loss": 0.0124, "lr": 2.3536787188592176e-06, "epoch": 17.493949394939495, "percentage": 87.47, "elapsed_time": "6:16:40", "remaining_time": "0:53:57", "throughput": 1484.83, "total_tokens": 33557952} {"current_steps": 159025, "total_steps": 181800, "loss": 0.0072, "lr": 2.3526621725152022e-06, "epoch": 17.494499449944996, "percentage": 87.47, "elapsed_time": "6:16:41", "remaining_time": "0:53:56", "throughput": 1484.83, "total_tokens": 33558976} {"current_steps": 159030, "total_steps": 181800, "loss": 0.0857, "lr": 2.351645834900837e-06, "epoch": 17.495049504950494, "percentage": 87.48, "elapsed_time": "6:16:41", "remaining_time": "0:53:56", "throughput": 1484.83, "total_tokens": 33560064} {"current_steps": 159035, "total_steps": 181800, "loss": 0.0893, "lr": 2.3506297060254813e-06, "epoch": 17.495599559955995, "percentage": 87.48, "elapsed_time": "6:16:42", "remaining_time": "0:53:55", "throughput": 1484.83, "total_tokens": 33561056} {"current_steps": 159040, "total_steps": 181800, "loss": 0.0052, "lr": 2.349613785898508e-06, "epoch": 17.496149614961496, "percentage": 87.48, "elapsed_time": "6:16:43", "remaining_time": "0:53:54", "throughput": 1484.83, "total_tokens": 33562144} {"current_steps": 159045, "total_steps": 181800, "loss": 0.0054, "lr": 2.348598074529271e-06, "epoch": 17.496699669966997, "percentage": 87.48, "elapsed_time": "6:16:44", "remaining_time": "0:53:54", "throughput": 1484.83, "total_tokens": 33563200} {"current_steps": 159050, "total_steps": 181800, "loss": 0.0023, "lr": 2.34758257192714e-06, "epoch": 17.497249724972498, "percentage": 87.49, "elapsed_time": "6:16:44", "remaining_time": "0:53:53", "throughput": 1484.83, "total_tokens": 33564224} {"current_steps": 159055, "total_steps": 181800, "loss": 0.0473, "lr": 2.3465672781014663e-06, "epoch": 17.497799779978, "percentage": 87.49, "elapsed_time": "6:16:45", "remaining_time": "0:53:52", "throughput": 1484.83, "total_tokens": 33565248} {"current_steps": 159060, "total_steps": 181800, "loss": 0.0009, "lr": 2.345552193061612e-06, "epoch": 17.498349834983497, "percentage": 87.49, "elapsed_time": "6:16:46", "remaining_time": "0:53:51", "throughput": 1484.84, "total_tokens": 33566336} {"current_steps": 159065, "total_steps": 181800, "loss": 0.0571, "lr": 2.344537316816936e-06, "epoch": 17.498899889988998, "percentage": 87.49, "elapsed_time": "6:16:46", "remaining_time": "0:53:51", "throughput": 1484.84, "total_tokens": 33567424} {"current_steps": 159070, "total_steps": 181800, "loss": 0.0017, "lr": 2.343522649376789e-06, "epoch": 17.4994499449945, "percentage": 87.5, "elapsed_time": "6:16:47", "remaining_time": "0:53:50", "throughput": 1484.84, "total_tokens": 33568448} {"current_steps": 159075, "total_steps": 181800, "loss": 0.003, "lr": 2.3425081907505198e-06, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "6:16:48", "remaining_time": "0:53:49", "throughput": 1484.84, "total_tokens": 33569504} {"current_steps": 159080, "total_steps": 181800, "loss": 0.0056, "lr": 2.3414939409474783e-06, "epoch": 17.5005500550055, "percentage": 87.5, "elapsed_time": "6:16:48", "remaining_time": "0:53:49", "throughput": 1484.84, "total_tokens": 33570560} {"current_steps": 159085, "total_steps": 181800, "loss": 0.0103, "lr": 2.3404798999770134e-06, "epoch": 17.501100110011002, "percentage": 87.51, "elapsed_time": "6:16:49", "remaining_time": "0:53:48", "throughput": 1484.84, "total_tokens": 33571616} {"current_steps": 159090, "total_steps": 181800, "loss": 0.0118, "lr": 2.339466067848478e-06, "epoch": 17.501650165016503, "percentage": 87.51, "elapsed_time": "6:16:50", "remaining_time": "0:53:47", "throughput": 1484.84, "total_tokens": 33572672} {"current_steps": 159095, "total_steps": 181800, "loss": 0.0845, "lr": 2.33845244457121e-06, "epoch": 17.502200220022, "percentage": 87.51, "elapsed_time": "6:16:50", "remaining_time": "0:53:46", "throughput": 1484.85, "total_tokens": 33573728} {"current_steps": 159100, "total_steps": 181800, "loss": 0.0055, "lr": 2.3374390301545477e-06, "epoch": 17.502750275027502, "percentage": 87.51, "elapsed_time": "6:16:51", "remaining_time": "0:53:46", "throughput": 1484.85, "total_tokens": 33574784} {"current_steps": 159105, "total_steps": 181800, "loss": 0.05, "lr": 2.336425824607841e-06, "epoch": 17.503300330033003, "percentage": 87.52, "elapsed_time": "6:16:52", "remaining_time": "0:53:45", "throughput": 1484.85, "total_tokens": 33575840} {"current_steps": 159110, "total_steps": 181800, "loss": 0.0037, "lr": 2.335412827940417e-06, "epoch": 17.503850385038504, "percentage": 87.52, "elapsed_time": "6:16:52", "remaining_time": "0:53:44", "throughput": 1484.85, "total_tokens": 33576896} {"current_steps": 159115, "total_steps": 181800, "loss": 0.1986, "lr": 2.334400040161616e-06, "epoch": 17.504400440044005, "percentage": 87.52, "elapsed_time": "6:16:53", "remaining_time": "0:53:44", "throughput": 1484.85, "total_tokens": 33577952} {"current_steps": 159120, "total_steps": 181800, "loss": 0.0045, "lr": 2.333387461280781e-06, "epoch": 17.504950495049506, "percentage": 87.52, "elapsed_time": "6:16:54", "remaining_time": "0:53:43", "throughput": 1484.86, "total_tokens": 33579072} {"current_steps": 159125, "total_steps": 181800, "loss": 0.0022, "lr": 2.332375091307229e-06, "epoch": 17.505500550055004, "percentage": 87.53, "elapsed_time": "6:16:55", "remaining_time": "0:53:42", "throughput": 1484.86, "total_tokens": 33580160} {"current_steps": 159130, "total_steps": 181800, "loss": 0.0062, "lr": 2.3313629302503053e-06, "epoch": 17.506050605060505, "percentage": 87.53, "elapsed_time": "6:16:55", "remaining_time": "0:53:41", "throughput": 1484.86, "total_tokens": 33581216} {"current_steps": 159135, "total_steps": 181800, "loss": 0.0184, "lr": 2.330350978119328e-06, "epoch": 17.506600660066006, "percentage": 87.53, "elapsed_time": "6:16:56", "remaining_time": "0:53:41", "throughput": 1484.86, "total_tokens": 33582304} {"current_steps": 159140, "total_steps": 181800, "loss": 0.0035, "lr": 2.3293392349236277e-06, "epoch": 17.507150715071507, "percentage": 87.54, "elapsed_time": "6:16:57", "remaining_time": "0:53:40", "throughput": 1484.86, "total_tokens": 33583328} {"current_steps": 159145, "total_steps": 181800, "loss": 0.0064, "lr": 2.3283277006725335e-06, "epoch": 17.507700770077008, "percentage": 87.54, "elapsed_time": "6:16:57", "remaining_time": "0:53:39", "throughput": 1484.86, "total_tokens": 33584320} {"current_steps": 159150, "total_steps": 181800, "loss": 0.0038, "lr": 2.32731637537536e-06, "epoch": 17.50825082508251, "percentage": 87.54, "elapsed_time": "6:16:58", "remaining_time": "0:53:39", "throughput": 1484.86, "total_tokens": 33585312} {"current_steps": 159155, "total_steps": 181800, "loss": 0.1294, "lr": 2.326305259041436e-06, "epoch": 17.50880088008801, "percentage": 87.54, "elapsed_time": "6:16:59", "remaining_time": "0:53:38", "throughput": 1484.86, "total_tokens": 33586400} {"current_steps": 159160, "total_steps": 181800, "loss": 0.002, "lr": 2.3252943516800713e-06, "epoch": 17.509350935093508, "percentage": 87.55, "elapsed_time": "6:16:59", "remaining_time": "0:53:37", "throughput": 1484.87, "total_tokens": 33587488} {"current_steps": 159165, "total_steps": 181800, "loss": 0.1119, "lr": 2.3242836533005936e-06, "epoch": 17.50990099009901, "percentage": 87.55, "elapsed_time": "6:17:00", "remaining_time": "0:53:36", "throughput": 1484.87, "total_tokens": 33588544} {"current_steps": 159170, "total_steps": 181800, "loss": 0.0014, "lr": 2.3232731639123096e-06, "epoch": 17.51045104510451, "percentage": 87.55, "elapsed_time": "6:17:01", "remaining_time": "0:53:36", "throughput": 1484.87, "total_tokens": 33589568} {"current_steps": 159175, "total_steps": 181800, "loss": 0.0026, "lr": 2.322262883524534e-06, "epoch": 17.51100110011001, "percentage": 87.56, "elapsed_time": "6:17:01", "remaining_time": "0:53:35", "throughput": 1484.87, "total_tokens": 33590688} {"current_steps": 159180, "total_steps": 181800, "loss": 0.0325, "lr": 2.321252812146582e-06, "epoch": 17.511551155115512, "percentage": 87.56, "elapsed_time": "6:17:02", "remaining_time": "0:53:34", "throughput": 1484.87, "total_tokens": 33591776} {"current_steps": 159185, "total_steps": 181800, "loss": 0.0045, "lr": 2.3202429497877598e-06, "epoch": 17.512101210121013, "percentage": 87.56, "elapsed_time": "6:17:03", "remaining_time": "0:53:34", "throughput": 1484.88, "total_tokens": 33592832} {"current_steps": 159190, "total_steps": 181800, "loss": 0.0037, "lr": 2.3192332964573764e-06, "epoch": 17.51265126512651, "percentage": 87.56, "elapsed_time": "6:17:04", "remaining_time": "0:53:33", "throughput": 1484.88, "total_tokens": 33593920} {"current_steps": 159195, "total_steps": 181800, "loss": 0.007, "lr": 2.318223852164736e-06, "epoch": 17.513201320132012, "percentage": 87.57, "elapsed_time": "6:17:04", "remaining_time": "0:53:32", "throughput": 1484.88, "total_tokens": 33595040} {"current_steps": 159200, "total_steps": 181800, "loss": 0.0011, "lr": 2.317214616919139e-06, "epoch": 17.513751375137513, "percentage": 87.57, "elapsed_time": "6:17:05", "remaining_time": "0:53:31", "throughput": 1484.88, "total_tokens": 33596000} {"current_steps": 159205, "total_steps": 181800, "loss": 0.0074, "lr": 2.3162055907298973e-06, "epoch": 17.514301430143014, "percentage": 87.57, "elapsed_time": "6:17:06", "remaining_time": "0:53:31", "throughput": 1484.88, "total_tokens": 33597088} {"current_steps": 159210, "total_steps": 181800, "loss": 0.0178, "lr": 2.3151967736062985e-06, "epoch": 17.514851485148515, "percentage": 87.57, "elapsed_time": "6:17:06", "remaining_time": "0:53:30", "throughput": 1484.88, "total_tokens": 33598144} {"current_steps": 159215, "total_steps": 181800, "loss": 0.027, "lr": 2.3141881655576488e-06, "epoch": 17.515401540154016, "percentage": 87.58, "elapsed_time": "6:17:07", "remaining_time": "0:53:29", "throughput": 1484.89, "total_tokens": 33599296} {"current_steps": 159220, "total_steps": 181800, "loss": 0.0053, "lr": 2.313179766593243e-06, "epoch": 17.515951595159517, "percentage": 87.58, "elapsed_time": "6:17:08", "remaining_time": "0:53:29", "throughput": 1484.89, "total_tokens": 33600352} {"current_steps": 159225, "total_steps": 181800, "loss": 0.0054, "lr": 2.312171576722369e-06, "epoch": 17.516501650165015, "percentage": 87.58, "elapsed_time": "6:17:08", "remaining_time": "0:53:28", "throughput": 1484.89, "total_tokens": 33601376} {"current_steps": 159230, "total_steps": 181800, "loss": 0.1131, "lr": 2.3111635959543217e-06, "epoch": 17.517051705170516, "percentage": 87.59, "elapsed_time": "6:17:09", "remaining_time": "0:53:27", "throughput": 1484.89, "total_tokens": 33602432} {"current_steps": 159235, "total_steps": 181800, "loss": 0.066, "lr": 2.3101558242983934e-06, "epoch": 17.517601760176017, "percentage": 87.59, "elapsed_time": "6:17:10", "remaining_time": "0:53:26", "throughput": 1484.89, "total_tokens": 33603456} {"current_steps": 159240, "total_steps": 181800, "loss": 0.0609, "lr": 2.3091482617638743e-06, "epoch": 17.51815181518152, "percentage": 87.59, "elapsed_time": "6:17:10", "remaining_time": "0:53:26", "throughput": 1484.9, "total_tokens": 33604544} {"current_steps": 159245, "total_steps": 181800, "loss": 0.0014, "lr": 2.3081409083600484e-06, "epoch": 17.51870187018702, "percentage": 87.59, "elapsed_time": "6:17:11", "remaining_time": "0:53:25", "throughput": 1484.9, "total_tokens": 33605664} {"current_steps": 159250, "total_steps": 181800, "loss": 0.1163, "lr": 2.307133764096195e-06, "epoch": 17.51925192519252, "percentage": 87.6, "elapsed_time": "6:17:12", "remaining_time": "0:53:24", "throughput": 1484.9, "total_tokens": 33606752} {"current_steps": 159255, "total_steps": 181800, "loss": 0.1692, "lr": 2.3061268289816e-06, "epoch": 17.519801980198018, "percentage": 87.6, "elapsed_time": "6:17:12", "remaining_time": "0:53:24", "throughput": 1484.9, "total_tokens": 33607808} {"current_steps": 159260, "total_steps": 181800, "loss": 0.054, "lr": 2.3051201030255486e-06, "epoch": 17.52035203520352, "percentage": 87.6, "elapsed_time": "6:17:13", "remaining_time": "0:53:23", "throughput": 1484.9, "total_tokens": 33608864} {"current_steps": 159265, "total_steps": 181800, "loss": 0.069, "lr": 2.3041135862373107e-06, "epoch": 17.52090209020902, "percentage": 87.6, "elapsed_time": "6:17:14", "remaining_time": "0:53:22", "throughput": 1484.9, "total_tokens": 33609888} {"current_steps": 159270, "total_steps": 181800, "loss": 0.0021, "lr": 2.3031072786261737e-06, "epoch": 17.52145214521452, "percentage": 87.61, "elapsed_time": "6:17:15", "remaining_time": "0:53:21", "throughput": 1484.91, "total_tokens": 33610944} {"current_steps": 159275, "total_steps": 181800, "loss": 0.0982, "lr": 2.302101180201399e-06, "epoch": 17.522002200220022, "percentage": 87.61, "elapsed_time": "6:17:15", "remaining_time": "0:53:21", "throughput": 1484.91, "total_tokens": 33612032} {"current_steps": 159280, "total_steps": 181800, "loss": 0.0022, "lr": 2.301095290972272e-06, "epoch": 17.522552255225524, "percentage": 87.61, "elapsed_time": "6:17:16", "remaining_time": "0:53:20", "throughput": 1484.91, "total_tokens": 33613056} {"current_steps": 159285, "total_steps": 181800, "loss": 0.0282, "lr": 2.300089610948053e-06, "epoch": 17.523102310231025, "percentage": 87.62, "elapsed_time": "6:17:17", "remaining_time": "0:53:19", "throughput": 1484.91, "total_tokens": 33614080} {"current_steps": 159290, "total_steps": 181800, "loss": 0.0407, "lr": 2.2990841401380136e-06, "epoch": 17.523652365236522, "percentage": 87.62, "elapsed_time": "6:17:17", "remaining_time": "0:53:19", "throughput": 1484.91, "total_tokens": 33615104} {"current_steps": 159295, "total_steps": 181800, "loss": 0.0184, "lr": 2.2980788785514294e-06, "epoch": 17.524202420242023, "percentage": 87.62, "elapsed_time": "6:17:18", "remaining_time": "0:53:18", "throughput": 1484.91, "total_tokens": 33616160} {"current_steps": 159300, "total_steps": 181800, "loss": 0.0045, "lr": 2.2970738261975545e-06, "epoch": 17.524752475247524, "percentage": 87.62, "elapsed_time": "6:17:19", "remaining_time": "0:53:17", "throughput": 1484.91, "total_tokens": 33617216} {"current_steps": 159305, "total_steps": 181800, "loss": 0.0015, "lr": 2.2960689830856615e-06, "epoch": 17.525302530253025, "percentage": 87.63, "elapsed_time": "6:17:19", "remaining_time": "0:53:16", "throughput": 1484.91, "total_tokens": 33618272} {"current_steps": 159310, "total_steps": 181800, "loss": 0.0021, "lr": 2.295064349225004e-06, "epoch": 17.525852585258527, "percentage": 87.63, "elapsed_time": "6:17:20", "remaining_time": "0:53:16", "throughput": 1484.92, "total_tokens": 33619424} {"current_steps": 159315, "total_steps": 181800, "loss": 0.0329, "lr": 2.2940599246248364e-06, "epoch": 17.526402640264028, "percentage": 87.63, "elapsed_time": "6:17:21", "remaining_time": "0:53:15", "throughput": 1484.92, "total_tokens": 33620480} {"current_steps": 159320, "total_steps": 181800, "loss": 0.162, "lr": 2.293055709294431e-06, "epoch": 17.52695269526953, "percentage": 87.63, "elapsed_time": "6:17:21", "remaining_time": "0:53:14", "throughput": 1484.92, "total_tokens": 33621472} {"current_steps": 159325, "total_steps": 181800, "loss": 0.0465, "lr": 2.2920517032430284e-06, "epoch": 17.527502750275026, "percentage": 87.64, "elapsed_time": "6:17:22", "remaining_time": "0:53:14", "throughput": 1484.92, "total_tokens": 33622528} {"current_steps": 159330, "total_steps": 181800, "loss": 0.0757, "lr": 2.2910479064798985e-06, "epoch": 17.528052805280527, "percentage": 87.64, "elapsed_time": "6:17:23", "remaining_time": "0:53:13", "throughput": 1484.92, "total_tokens": 33623616} {"current_steps": 159335, "total_steps": 181800, "loss": 0.0182, "lr": 2.2900443190142785e-06, "epoch": 17.52860286028603, "percentage": 87.64, "elapsed_time": "6:17:24", "remaining_time": "0:53:12", "throughput": 1484.92, "total_tokens": 33624608} {"current_steps": 159340, "total_steps": 181800, "loss": 0.0436, "lr": 2.289040940855422e-06, "epoch": 17.52915291529153, "percentage": 87.65, "elapsed_time": "6:17:24", "remaining_time": "0:53:11", "throughput": 1484.92, "total_tokens": 33625664} {"current_steps": 159345, "total_steps": 181800, "loss": 0.103, "lr": 2.2880377720125744e-06, "epoch": 17.52970297029703, "percentage": 87.65, "elapsed_time": "6:17:25", "remaining_time": "0:53:11", "throughput": 1484.92, "total_tokens": 33626720} {"current_steps": 159350, "total_steps": 181800, "loss": 0.0008, "lr": 2.287034812494987e-06, "epoch": 17.53025302530253, "percentage": 87.65, "elapsed_time": "6:17:26", "remaining_time": "0:53:10", "throughput": 1484.92, "total_tokens": 33627744} {"current_steps": 159355, "total_steps": 181800, "loss": 0.0738, "lr": 2.286032062311902e-06, "epoch": 17.53080308030803, "percentage": 87.65, "elapsed_time": "6:17:26", "remaining_time": "0:53:09", "throughput": 1484.93, "total_tokens": 33628800} {"current_steps": 159360, "total_steps": 181800, "loss": 0.0054, "lr": 2.2850295214725647e-06, "epoch": 17.53135313531353, "percentage": 87.66, "elapsed_time": "6:17:27", "remaining_time": "0:53:09", "throughput": 1484.93, "total_tokens": 33629888} {"current_steps": 159365, "total_steps": 181800, "loss": 0.0041, "lr": 2.284027189986204e-06, "epoch": 17.53190319031903, "percentage": 87.66, "elapsed_time": "6:17:28", "remaining_time": "0:53:08", "throughput": 1484.93, "total_tokens": 33630944} {"current_steps": 159370, "total_steps": 181800, "loss": 0.0064, "lr": 2.2830250678620686e-06, "epoch": 17.532453245324533, "percentage": 87.66, "elapsed_time": "6:17:28", "remaining_time": "0:53:07", "throughput": 1484.93, "total_tokens": 33631968} {"current_steps": 159375, "total_steps": 181800, "loss": 0.0054, "lr": 2.2820231551093805e-06, "epoch": 17.533003300330034, "percentage": 87.67, "elapsed_time": "6:17:29", "remaining_time": "0:53:06", "throughput": 1484.94, "total_tokens": 33633152} {"current_steps": 159380, "total_steps": 181800, "loss": 0.004, "lr": 2.2810214517373945e-06, "epoch": 17.533553355335535, "percentage": 87.67, "elapsed_time": "6:17:30", "remaining_time": "0:53:06", "throughput": 1484.94, "total_tokens": 33634176} {"current_steps": 159385, "total_steps": 181800, "loss": 0.1155, "lr": 2.2800199577553307e-06, "epoch": 17.534103410341036, "percentage": 87.67, "elapsed_time": "6:17:30", "remaining_time": "0:53:05", "throughput": 1484.93, "total_tokens": 33635168} {"current_steps": 159390, "total_steps": 181800, "loss": 0.0073, "lr": 2.2790186731724174e-06, "epoch": 17.534653465346533, "percentage": 87.67, "elapsed_time": "6:17:31", "remaining_time": "0:53:04", "throughput": 1484.94, "total_tokens": 33636224} {"current_steps": 159395, "total_steps": 181800, "loss": 0.0591, "lr": 2.278017597997892e-06, "epoch": 17.535203520352034, "percentage": 87.68, "elapsed_time": "6:17:32", "remaining_time": "0:53:04", "throughput": 1484.94, "total_tokens": 33637312} {"current_steps": 159400, "total_steps": 181800, "loss": 0.0545, "lr": 2.277016732240969e-06, "epoch": 17.535753575357536, "percentage": 87.68, "elapsed_time": "6:17:33", "remaining_time": "0:53:03", "throughput": 1484.94, "total_tokens": 33638368} {"current_steps": 159405, "total_steps": 181800, "loss": 0.0071, "lr": 2.2760160759108805e-06, "epoch": 17.536303630363037, "percentage": 87.68, "elapsed_time": "6:17:33", "remaining_time": "0:53:02", "throughput": 1484.94, "total_tokens": 33639488} {"current_steps": 159410, "total_steps": 181800, "loss": 0.0265, "lr": 2.2750156290168522e-06, "epoch": 17.536853685368538, "percentage": 87.68, "elapsed_time": "6:17:34", "remaining_time": "0:53:01", "throughput": 1484.94, "total_tokens": 33640512} {"current_steps": 159415, "total_steps": 181800, "loss": 0.0062, "lr": 2.2740153915680963e-06, "epoch": 17.53740374037404, "percentage": 87.69, "elapsed_time": "6:17:35", "remaining_time": "0:53:01", "throughput": 1484.95, "total_tokens": 33641568} {"current_steps": 159420, "total_steps": 181800, "loss": 0.0076, "lr": 2.273015363573838e-06, "epoch": 17.537953795379536, "percentage": 87.69, "elapsed_time": "6:17:35", "remaining_time": "0:53:00", "throughput": 1484.95, "total_tokens": 33642624} {"current_steps": 159425, "total_steps": 181800, "loss": 0.0042, "lr": 2.272015545043288e-06, "epoch": 17.538503850385037, "percentage": 87.69, "elapsed_time": "6:17:36", "remaining_time": "0:52:59", "throughput": 1484.95, "total_tokens": 33643712} {"current_steps": 159430, "total_steps": 181800, "loss": 0.0132, "lr": 2.271015935985671e-06, "epoch": 17.53905390539054, "percentage": 87.7, "elapsed_time": "6:17:37", "remaining_time": "0:52:59", "throughput": 1484.95, "total_tokens": 33644768} {"current_steps": 159435, "total_steps": 181800, "loss": 0.0019, "lr": 2.2700165364101856e-06, "epoch": 17.53960396039604, "percentage": 87.7, "elapsed_time": "6:17:37", "remaining_time": "0:52:58", "throughput": 1484.95, "total_tokens": 33645792} {"current_steps": 159440, "total_steps": 181800, "loss": 0.0026, "lr": 2.269017346326055e-06, "epoch": 17.54015401540154, "percentage": 87.7, "elapsed_time": "6:17:38", "remaining_time": "0:52:57", "throughput": 1484.95, "total_tokens": 33646784} {"current_steps": 159445, "total_steps": 181800, "loss": 0.0272, "lr": 2.268018365742486e-06, "epoch": 17.540704070407042, "percentage": 87.7, "elapsed_time": "6:17:39", "remaining_time": "0:52:56", "throughput": 1484.95, "total_tokens": 33647840} {"current_steps": 159450, "total_steps": 181800, "loss": 0.0316, "lr": 2.2670195946686844e-06, "epoch": 17.541254125412543, "percentage": 87.71, "elapsed_time": "6:17:39", "remaining_time": "0:52:56", "throughput": 1484.96, "total_tokens": 33648960} {"current_steps": 159455, "total_steps": 181800, "loss": 0.0009, "lr": 2.2660210331138492e-06, "epoch": 17.54180418041804, "percentage": 87.71, "elapsed_time": "6:17:40", "remaining_time": "0:52:55", "throughput": 1484.96, "total_tokens": 33650048} {"current_steps": 159460, "total_steps": 181800, "loss": 0.0263, "lr": 2.2650226810871922e-06, "epoch": 17.54235423542354, "percentage": 87.71, "elapsed_time": "6:17:41", "remaining_time": "0:52:54", "throughput": 1484.96, "total_tokens": 33651104} {"current_steps": 159465, "total_steps": 181800, "loss": 0.0096, "lr": 2.264024538597909e-06, "epoch": 17.542904290429043, "percentage": 87.71, "elapsed_time": "6:17:41", "remaining_time": "0:52:54", "throughput": 1484.96, "total_tokens": 33652160} {"current_steps": 159470, "total_steps": 181800, "loss": 0.0064, "lr": 2.263026605655208e-06, "epoch": 17.543454345434544, "percentage": 87.72, "elapsed_time": "6:17:42", "remaining_time": "0:52:53", "throughput": 1484.97, "total_tokens": 33653280} {"current_steps": 159475, "total_steps": 181800, "loss": 0.0625, "lr": 2.26202888226828e-06, "epoch": 17.544004400440045, "percentage": 87.72, "elapsed_time": "6:17:43", "remaining_time": "0:52:52", "throughput": 1484.97, "total_tokens": 33654304} {"current_steps": 159480, "total_steps": 181800, "loss": 0.0495, "lr": 2.2610313684463177e-06, "epoch": 17.544554455445546, "percentage": 87.72, "elapsed_time": "6:17:44", "remaining_time": "0:52:51", "throughput": 1484.97, "total_tokens": 33655424} {"current_steps": 159485, "total_steps": 181800, "loss": 0.0017, "lr": 2.260034064198521e-06, "epoch": 17.545104510451043, "percentage": 87.73, "elapsed_time": "6:17:44", "remaining_time": "0:52:51", "throughput": 1484.97, "total_tokens": 33656480} {"current_steps": 159490, "total_steps": 181800, "loss": 0.0025, "lr": 2.259036969534073e-06, "epoch": 17.545654565456545, "percentage": 87.73, "elapsed_time": "6:17:45", "remaining_time": "0:52:50", "throughput": 1484.97, "total_tokens": 33657472} {"current_steps": 159495, "total_steps": 181800, "loss": 0.0902, "lr": 2.2580400844621708e-06, "epoch": 17.546204620462046, "percentage": 87.73, "elapsed_time": "6:17:46", "remaining_time": "0:52:49", "throughput": 1484.97, "total_tokens": 33658528} {"current_steps": 159500, "total_steps": 181800, "loss": 0.0013, "lr": 2.2570434089920044e-06, "epoch": 17.546754675467547, "percentage": 87.73, "elapsed_time": "6:17:46", "remaining_time": "0:52:49", "throughput": 1484.97, "total_tokens": 33659520} {"current_steps": 159505, "total_steps": 181800, "loss": 0.0608, "lr": 2.256046943132753e-06, "epoch": 17.547304730473048, "percentage": 87.74, "elapsed_time": "6:17:47", "remaining_time": "0:52:48", "throughput": 1484.97, "total_tokens": 33660576} {"current_steps": 159510, "total_steps": 181800, "loss": 0.0027, "lr": 2.255050686893606e-06, "epoch": 17.54785478547855, "percentage": 87.74, "elapsed_time": "6:17:48", "remaining_time": "0:52:47", "throughput": 1484.97, "total_tokens": 33661632} {"current_steps": 159515, "total_steps": 181800, "loss": 0.0043, "lr": 2.25405464028374e-06, "epoch": 17.54840484048405, "percentage": 87.74, "elapsed_time": "6:17:48", "remaining_time": "0:52:46", "throughput": 1484.98, "total_tokens": 33662688} {"current_steps": 159520, "total_steps": 181800, "loss": 0.0051, "lr": 2.2530588033123356e-06, "epoch": 17.548954895489548, "percentage": 87.74, "elapsed_time": "6:17:49", "remaining_time": "0:52:46", "throughput": 1484.98, "total_tokens": 33663776} {"current_steps": 159525, "total_steps": 181800, "loss": 0.0331, "lr": 2.252063175988578e-06, "epoch": 17.54950495049505, "percentage": 87.75, "elapsed_time": "6:17:50", "remaining_time": "0:52:45", "throughput": 1484.98, "total_tokens": 33664896} {"current_steps": 159530, "total_steps": 181800, "loss": 0.0038, "lr": 2.2510677583216346e-06, "epoch": 17.55005500550055, "percentage": 87.75, "elapsed_time": "6:17:50", "remaining_time": "0:52:44", "throughput": 1484.99, "total_tokens": 33666016} {"current_steps": 159535, "total_steps": 181800, "loss": 0.0011, "lr": 2.2500725503206892e-06, "epoch": 17.55060506050605, "percentage": 87.75, "elapsed_time": "6:17:51", "remaining_time": "0:52:44", "throughput": 1484.99, "total_tokens": 33667072} {"current_steps": 159540, "total_steps": 181800, "loss": 0.0005, "lr": 2.2490775519949048e-06, "epoch": 17.551155115511552, "percentage": 87.76, "elapsed_time": "6:17:52", "remaining_time": "0:52:43", "throughput": 1484.99, "total_tokens": 33668096} {"current_steps": 159545, "total_steps": 181800, "loss": 0.0069, "lr": 2.2480827633534566e-06, "epoch": 17.551705170517053, "percentage": 87.76, "elapsed_time": "6:17:52", "remaining_time": "0:52:42", "throughput": 1484.99, "total_tokens": 33669152} {"current_steps": 159550, "total_steps": 181800, "loss": 0.0509, "lr": 2.24708818440551e-06, "epoch": 17.55225522552255, "percentage": 87.76, "elapsed_time": "6:17:53", "remaining_time": "0:52:41", "throughput": 1484.99, "total_tokens": 33670176} {"current_steps": 159555, "total_steps": 181800, "loss": 0.0452, "lr": 2.246093815160233e-06, "epoch": 17.55280528052805, "percentage": 87.76, "elapsed_time": "6:17:54", "remaining_time": "0:52:41", "throughput": 1484.99, "total_tokens": 33671232} {"current_steps": 159560, "total_steps": 181800, "loss": 0.0035, "lr": 2.2450996556267976e-06, "epoch": 17.553355335533553, "percentage": 87.77, "elapsed_time": "6:17:55", "remaining_time": "0:52:40", "throughput": 1484.99, "total_tokens": 33672320} {"current_steps": 159565, "total_steps": 181800, "loss": 0.005, "lr": 2.2441057058143532e-06, "epoch": 17.553905390539054, "percentage": 87.77, "elapsed_time": "6:17:55", "remaining_time": "0:52:39", "throughput": 1485.0, "total_tokens": 33673408} {"current_steps": 159570, "total_steps": 181800, "loss": 0.0115, "lr": 2.2431119657320697e-06, "epoch": 17.554455445544555, "percentage": 87.77, "elapsed_time": "6:17:56", "remaining_time": "0:52:39", "throughput": 1485.0, "total_tokens": 33674464} {"current_steps": 159575, "total_steps": 181800, "loss": 0.0024, "lr": 2.2421184353891013e-06, "epoch": 17.555005500550056, "percentage": 87.78, "elapsed_time": "6:17:57", "remaining_time": "0:52:38", "throughput": 1485.0, "total_tokens": 33675488} {"current_steps": 159580, "total_steps": 181800, "loss": 0.0187, "lr": 2.2411251147946065e-06, "epoch": 17.555555555555557, "percentage": 87.78, "elapsed_time": "6:17:57", "remaining_time": "0:52:37", "throughput": 1485.0, "total_tokens": 33676608} {"current_steps": 159585, "total_steps": 181800, "loss": 0.0046, "lr": 2.2401320039577483e-06, "epoch": 17.556105610561055, "percentage": 87.78, "elapsed_time": "6:17:58", "remaining_time": "0:52:36", "throughput": 1485.0, "total_tokens": 33677664} {"current_steps": 159590, "total_steps": 181800, "loss": 0.0091, "lr": 2.2391391028876635e-06, "epoch": 17.556655665566556, "percentage": 87.78, "elapsed_time": "6:17:59", "remaining_time": "0:52:36", "throughput": 1485.0, "total_tokens": 33678720} {"current_steps": 159595, "total_steps": 181800, "loss": 0.0456, "lr": 2.238146411593517e-06, "epoch": 17.557205720572057, "percentage": 87.79, "elapsed_time": "6:17:59", "remaining_time": "0:52:35", "throughput": 1485.01, "total_tokens": 33679840} {"current_steps": 159600, "total_steps": 181800, "loss": 0.0043, "lr": 2.237153930084454e-06, "epoch": 17.557755775577558, "percentage": 87.79, "elapsed_time": "6:18:00", "remaining_time": "0:52:34", "throughput": 1485.01, "total_tokens": 33680960} {"current_steps": 159605, "total_steps": 181800, "loss": 0.004, "lr": 2.2361616583696176e-06, "epoch": 17.55830583058306, "percentage": 87.79, "elapsed_time": "6:18:01", "remaining_time": "0:52:34", "throughput": 1485.02, "total_tokens": 33682080} {"current_steps": 159610, "total_steps": 181800, "loss": 0.0465, "lr": 2.235169596458153e-06, "epoch": 17.55885588558856, "percentage": 87.79, "elapsed_time": "6:18:01", "remaining_time": "0:52:33", "throughput": 1485.02, "total_tokens": 33683168} {"current_steps": 159615, "total_steps": 181800, "loss": 0.0864, "lr": 2.2341777443592088e-06, "epoch": 17.55940594059406, "percentage": 87.8, "elapsed_time": "6:18:02", "remaining_time": "0:52:32", "throughput": 1485.02, "total_tokens": 33684192} {"current_steps": 159620, "total_steps": 181800, "loss": 0.003, "lr": 2.2331861020819274e-06, "epoch": 17.55995599559956, "percentage": 87.8, "elapsed_time": "6:18:03", "remaining_time": "0:52:31", "throughput": 1485.02, "total_tokens": 33685248} {"current_steps": 159625, "total_steps": 181800, "loss": 0.0331, "lr": 2.232194669635446e-06, "epoch": 17.56050605060506, "percentage": 87.8, "elapsed_time": "6:18:04", "remaining_time": "0:52:31", "throughput": 1485.02, "total_tokens": 33686240} {"current_steps": 159630, "total_steps": 181800, "loss": 0.0678, "lr": 2.2312034470288955e-06, "epoch": 17.56105610561056, "percentage": 87.81, "elapsed_time": "6:18:04", "remaining_time": "0:52:30", "throughput": 1485.02, "total_tokens": 33687296} {"current_steps": 159635, "total_steps": 181800, "loss": 0.0535, "lr": 2.230212434271417e-06, "epoch": 17.561606160616062, "percentage": 87.81, "elapsed_time": "6:18:05", "remaining_time": "0:52:29", "throughput": 1485.02, "total_tokens": 33688352} {"current_steps": 159640, "total_steps": 181800, "loss": 0.0094, "lr": 2.22922163137215e-06, "epoch": 17.562156215621563, "percentage": 87.81, "elapsed_time": "6:18:06", "remaining_time": "0:52:29", "throughput": 1485.03, "total_tokens": 33689472} {"current_steps": 159645, "total_steps": 181800, "loss": 0.016, "lr": 2.228231038340217e-06, "epoch": 17.562706270627064, "percentage": 87.81, "elapsed_time": "6:18:06", "remaining_time": "0:52:28", "throughput": 1485.03, "total_tokens": 33690560} {"current_steps": 159650, "total_steps": 181800, "loss": 0.0019, "lr": 2.2272406551847534e-06, "epoch": 17.563256325632562, "percentage": 87.82, "elapsed_time": "6:18:07", "remaining_time": "0:52:27", "throughput": 1485.03, "total_tokens": 33691616} {"current_steps": 159655, "total_steps": 181800, "loss": 0.1173, "lr": 2.226250481914882e-06, "epoch": 17.563806380638063, "percentage": 87.82, "elapsed_time": "6:18:08", "remaining_time": "0:52:26", "throughput": 1485.03, "total_tokens": 33692640} {"current_steps": 159660, "total_steps": 181800, "loss": 0.0038, "lr": 2.2252605185397373e-06, "epoch": 17.564356435643564, "percentage": 87.82, "elapsed_time": "6:18:08", "remaining_time": "0:52:26", "throughput": 1485.03, "total_tokens": 33693696} {"current_steps": 159665, "total_steps": 181800, "loss": 0.0518, "lr": 2.224270765068434e-06, "epoch": 17.564906490649065, "percentage": 87.82, "elapsed_time": "6:18:09", "remaining_time": "0:52:25", "throughput": 1485.03, "total_tokens": 33694752} {"current_steps": 159670, "total_steps": 181800, "loss": 0.0714, "lr": 2.2232812215100984e-06, "epoch": 17.565456545654566, "percentage": 87.83, "elapsed_time": "6:18:10", "remaining_time": "0:52:24", "throughput": 1485.03, "total_tokens": 33695776} {"current_steps": 159675, "total_steps": 181800, "loss": 0.0053, "lr": 2.2222918878738536e-06, "epoch": 17.566006600660067, "percentage": 87.83, "elapsed_time": "6:18:10", "remaining_time": "0:52:24", "throughput": 1485.04, "total_tokens": 33696832} {"current_steps": 159680, "total_steps": 181800, "loss": 0.0027, "lr": 2.2213027641688116e-06, "epoch": 17.566556655665565, "percentage": 87.83, "elapsed_time": "6:18:11", "remaining_time": "0:52:23", "throughput": 1485.04, "total_tokens": 33697920} {"current_steps": 159685, "total_steps": 181800, "loss": 0.0482, "lr": 2.2203138504040934e-06, "epoch": 17.567106710671066, "percentage": 87.84, "elapsed_time": "6:18:12", "remaining_time": "0:52:22", "throughput": 1485.04, "total_tokens": 33698976} {"current_steps": 159690, "total_steps": 181800, "loss": 0.0329, "lr": 2.2193251465888103e-06, "epoch": 17.567656765676567, "percentage": 87.84, "elapsed_time": "6:18:12", "remaining_time": "0:52:21", "throughput": 1485.04, "total_tokens": 33700000} {"current_steps": 159695, "total_steps": 181800, "loss": 0.0067, "lr": 2.2183366527320753e-06, "epoch": 17.568206820682068, "percentage": 87.84, "elapsed_time": "6:18:13", "remaining_time": "0:52:21", "throughput": 1485.04, "total_tokens": 33701120} {"current_steps": 159700, "total_steps": 181800, "loss": 0.0018, "lr": 2.217348368843003e-06, "epoch": 17.56875687568757, "percentage": 87.84, "elapsed_time": "6:18:14", "remaining_time": "0:52:20", "throughput": 1485.05, "total_tokens": 33702176} {"current_steps": 159705, "total_steps": 181800, "loss": 0.0008, "lr": 2.2163602949306942e-06, "epoch": 17.56930693069307, "percentage": 87.85, "elapsed_time": "6:18:15", "remaining_time": "0:52:19", "throughput": 1485.05, "total_tokens": 33703232} {"current_steps": 159710, "total_steps": 181800, "loss": 0.0013, "lr": 2.2153724310042644e-06, "epoch": 17.56985698569857, "percentage": 87.85, "elapsed_time": "6:18:15", "remaining_time": "0:52:19", "throughput": 1485.05, "total_tokens": 33704320} {"current_steps": 159715, "total_steps": 181800, "loss": 0.0042, "lr": 2.2143847770728144e-06, "epoch": 17.57040704070407, "percentage": 87.85, "elapsed_time": "6:18:16", "remaining_time": "0:52:18", "throughput": 1485.05, "total_tokens": 33705344} {"current_steps": 159720, "total_steps": 181800, "loss": 0.036, "lr": 2.213397333145442e-06, "epoch": 17.57095709570957, "percentage": 87.85, "elapsed_time": "6:18:17", "remaining_time": "0:52:17", "throughput": 1485.05, "total_tokens": 33706368} {"current_steps": 159725, "total_steps": 181800, "loss": 0.0624, "lr": 2.212410099231252e-06, "epoch": 17.57150715071507, "percentage": 87.86, "elapsed_time": "6:18:18", "remaining_time": "0:52:17", "throughput": 1485.04, "total_tokens": 33707424} {"current_steps": 159730, "total_steps": 181800, "loss": 0.0429, "lr": 2.2114230753393443e-06, "epoch": 17.572057205720572, "percentage": 87.86, "elapsed_time": "6:18:18", "remaining_time": "0:52:16", "throughput": 1485.04, "total_tokens": 33708480} {"current_steps": 159735, "total_steps": 181800, "loss": 0.0012, "lr": 2.210436261478818e-06, "epoch": 17.572607260726073, "percentage": 87.86, "elapsed_time": "6:18:19", "remaining_time": "0:52:15", "throughput": 1485.04, "total_tokens": 33709536} {"current_steps": 159740, "total_steps": 181800, "loss": 0.0038, "lr": 2.209449657658769e-06, "epoch": 17.573157315731574, "percentage": 87.87, "elapsed_time": "6:18:20", "remaining_time": "0:52:14", "throughput": 1485.04, "total_tokens": 33710592} {"current_steps": 159745, "total_steps": 181800, "loss": 0.0635, "lr": 2.2084632638882775e-06, "epoch": 17.573707370737075, "percentage": 87.87, "elapsed_time": "6:18:20", "remaining_time": "0:52:14", "throughput": 1485.04, "total_tokens": 33711616} {"current_steps": 159750, "total_steps": 181800, "loss": 0.0015, "lr": 2.2074770801764453e-06, "epoch": 17.574257425742573, "percentage": 87.87, "elapsed_time": "6:18:21", "remaining_time": "0:52:13", "throughput": 1485.04, "total_tokens": 33712672} {"current_steps": 159755, "total_steps": 181800, "loss": 0.0016, "lr": 2.2064911065323603e-06, "epoch": 17.574807480748074, "percentage": 87.87, "elapsed_time": "6:18:22", "remaining_time": "0:52:12", "throughput": 1485.04, "total_tokens": 33713696} {"current_steps": 159760, "total_steps": 181800, "loss": 0.0023, "lr": 2.205505342965114e-06, "epoch": 17.575357535753575, "percentage": 87.88, "elapsed_time": "6:18:22", "remaining_time": "0:52:12", "throughput": 1485.05, "total_tokens": 33714752} {"current_steps": 159765, "total_steps": 181800, "loss": 0.0806, "lr": 2.204519789483786e-06, "epoch": 17.575907590759076, "percentage": 87.88, "elapsed_time": "6:18:23", "remaining_time": "0:52:11", "throughput": 1485.05, "total_tokens": 33715840} {"current_steps": 159770, "total_steps": 181800, "loss": 0.0066, "lr": 2.203534446097458e-06, "epoch": 17.576457645764577, "percentage": 87.88, "elapsed_time": "6:18:24", "remaining_time": "0:52:10", "throughput": 1485.05, "total_tokens": 33716896} {"current_steps": 159775, "total_steps": 181800, "loss": 0.0023, "lr": 2.2025493128152165e-06, "epoch": 17.57700770077008, "percentage": 87.89, "elapsed_time": "6:18:24", "remaining_time": "0:52:09", "throughput": 1485.05, "total_tokens": 33718016} {"current_steps": 159780, "total_steps": 181800, "loss": 0.1176, "lr": 2.201564389646135e-06, "epoch": 17.577557755775576, "percentage": 87.89, "elapsed_time": "6:18:25", "remaining_time": "0:52:09", "throughput": 1485.05, "total_tokens": 33719040} {"current_steps": 159785, "total_steps": 181800, "loss": 0.0501, "lr": 2.200579676599296e-06, "epoch": 17.578107810781077, "percentage": 87.89, "elapsed_time": "6:18:26", "remaining_time": "0:52:08", "throughput": 1485.05, "total_tokens": 33720032} {"current_steps": 159790, "total_steps": 181800, "loss": 0.002, "lr": 2.1995951736837773e-06, "epoch": 17.578657865786578, "percentage": 87.89, "elapsed_time": "6:18:26", "remaining_time": "0:52:07", "throughput": 1485.05, "total_tokens": 33721120} {"current_steps": 159795, "total_steps": 181800, "loss": 0.0617, "lr": 2.198610880908644e-06, "epoch": 17.57920792079208, "percentage": 87.9, "elapsed_time": "6:18:27", "remaining_time": "0:52:07", "throughput": 1485.06, "total_tokens": 33722176} {"current_steps": 159800, "total_steps": 181800, "loss": 0.0719, "lr": 2.1976267982829784e-06, "epoch": 17.57975797579758, "percentage": 87.9, "elapsed_time": "6:18:28", "remaining_time": "0:52:06", "throughput": 1485.06, "total_tokens": 33723232} {"current_steps": 159805, "total_steps": 181800, "loss": 0.0026, "lr": 2.1966429258158423e-06, "epoch": 17.58030803080308, "percentage": 87.9, "elapsed_time": "6:18:29", "remaining_time": "0:52:05", "throughput": 1485.06, "total_tokens": 33724288} {"current_steps": 159810, "total_steps": 181800, "loss": 0.0102, "lr": 2.195659263516303e-06, "epoch": 17.580858085808583, "percentage": 87.9, "elapsed_time": "6:18:29", "remaining_time": "0:52:04", "throughput": 1485.06, "total_tokens": 33725376} {"current_steps": 159815, "total_steps": 181800, "loss": 0.0087, "lr": 2.1946758113934345e-06, "epoch": 17.58140814081408, "percentage": 87.91, "elapsed_time": "6:18:30", "remaining_time": "0:52:04", "throughput": 1485.06, "total_tokens": 33726400} {"current_steps": 159820, "total_steps": 181800, "loss": 0.0421, "lr": 2.193692569456293e-06, "epoch": 17.58195819581958, "percentage": 87.91, "elapsed_time": "6:18:31", "remaining_time": "0:52:03", "throughput": 1485.06, "total_tokens": 33727424} {"current_steps": 159825, "total_steps": 181800, "loss": 0.0031, "lr": 2.1927095377139496e-06, "epoch": 17.582508250825082, "percentage": 87.91, "elapsed_time": "6:18:31", "remaining_time": "0:52:02", "throughput": 1485.06, "total_tokens": 33728448} {"current_steps": 159830, "total_steps": 181800, "loss": 0.0027, "lr": 2.1917267161754545e-06, "epoch": 17.583058305830583, "percentage": 87.92, "elapsed_time": "6:18:32", "remaining_time": "0:52:02", "throughput": 1485.06, "total_tokens": 33729536} {"current_steps": 159835, "total_steps": 181800, "loss": 0.0514, "lr": 2.190744104849868e-06, "epoch": 17.583608360836084, "percentage": 87.92, "elapsed_time": "6:18:33", "remaining_time": "0:52:01", "throughput": 1485.07, "total_tokens": 33730656} {"current_steps": 159840, "total_steps": 181800, "loss": 0.0056, "lr": 2.189761703746246e-06, "epoch": 17.584158415841586, "percentage": 87.92, "elapsed_time": "6:18:33", "remaining_time": "0:52:00", "throughput": 1485.07, "total_tokens": 33731776} {"current_steps": 159845, "total_steps": 181800, "loss": 0.0293, "lr": 2.1887795128736483e-06, "epoch": 17.584708470847083, "percentage": 87.92, "elapsed_time": "6:18:34", "remaining_time": "0:51:59", "throughput": 1485.08, "total_tokens": 33732864} {"current_steps": 159850, "total_steps": 181800, "loss": 0.001, "lr": 2.187797532241126e-06, "epoch": 17.585258525852584, "percentage": 87.93, "elapsed_time": "6:18:35", "remaining_time": "0:51:59", "throughput": 1485.08, "total_tokens": 33733952} {"current_steps": 159855, "total_steps": 181800, "loss": 0.004, "lr": 2.1868157618577274e-06, "epoch": 17.585808580858085, "percentage": 87.93, "elapsed_time": "6:18:35", "remaining_time": "0:51:58", "throughput": 1485.08, "total_tokens": 33734976} {"current_steps": 159860, "total_steps": 181800, "loss": 0.1269, "lr": 2.1858342017324978e-06, "epoch": 17.586358635863586, "percentage": 87.93, "elapsed_time": "6:18:36", "remaining_time": "0:51:57", "throughput": 1485.08, "total_tokens": 33736064} {"current_steps": 159865, "total_steps": 181800, "loss": 0.024, "lr": 2.184852851874486e-06, "epoch": 17.586908690869087, "percentage": 87.93, "elapsed_time": "6:18:37", "remaining_time": "0:51:57", "throughput": 1485.08, "total_tokens": 33737088} {"current_steps": 159870, "total_steps": 181800, "loss": 0.0013, "lr": 2.183871712292737e-06, "epoch": 17.58745874587459, "percentage": 87.94, "elapsed_time": "6:18:38", "remaining_time": "0:51:56", "throughput": 1485.08, "total_tokens": 33738112} {"current_steps": 159875, "total_steps": 181800, "loss": 0.0108, "lr": 2.1828907829962998e-06, "epoch": 17.58800880088009, "percentage": 87.94, "elapsed_time": "6:18:38", "remaining_time": "0:51:55", "throughput": 1485.08, "total_tokens": 33739200} {"current_steps": 159880, "total_steps": 181800, "loss": 0.0021, "lr": 2.181910063994211e-06, "epoch": 17.588558855885587, "percentage": 87.94, "elapsed_time": "6:18:39", "remaining_time": "0:51:54", "throughput": 1485.09, "total_tokens": 33740224} {"current_steps": 159885, "total_steps": 181800, "loss": 0.0221, "lr": 2.180929555295502e-06, "epoch": 17.58910891089109, "percentage": 87.95, "elapsed_time": "6:18:40", "remaining_time": "0:51:54", "throughput": 1485.09, "total_tokens": 33741312} {"current_steps": 159890, "total_steps": 181800, "loss": 0.019, "lr": 2.1799492569092196e-06, "epoch": 17.58965896589659, "percentage": 87.95, "elapsed_time": "6:18:40", "remaining_time": "0:51:53", "throughput": 1485.09, "total_tokens": 33742496} {"current_steps": 159895, "total_steps": 181800, "loss": 0.0019, "lr": 2.1789691688443912e-06, "epoch": 17.59020902090209, "percentage": 87.95, "elapsed_time": "6:18:41", "remaining_time": "0:51:52", "throughput": 1485.1, "total_tokens": 33743584} {"current_steps": 159900, "total_steps": 181800, "loss": 0.0041, "lr": 2.1779892911100524e-06, "epoch": 17.59075907590759, "percentage": 87.95, "elapsed_time": "6:18:42", "remaining_time": "0:51:52", "throughput": 1485.1, "total_tokens": 33744640} {"current_steps": 159905, "total_steps": 181800, "loss": 0.1061, "lr": 2.17700962371524e-06, "epoch": 17.591309130913093, "percentage": 87.96, "elapsed_time": "6:18:42", "remaining_time": "0:51:51", "throughput": 1485.1, "total_tokens": 33745664} {"current_steps": 159910, "total_steps": 181800, "loss": 0.0409, "lr": 2.1760301666689743e-06, "epoch": 17.59185918591859, "percentage": 87.96, "elapsed_time": "6:18:43", "remaining_time": "0:51:50", "throughput": 1485.1, "total_tokens": 33746752} {"current_steps": 159915, "total_steps": 181800, "loss": 0.0016, "lr": 2.17505091998029e-06, "epoch": 17.59240924092409, "percentage": 87.96, "elapsed_time": "6:18:44", "remaining_time": "0:51:49", "throughput": 1485.1, "total_tokens": 33747776} {"current_steps": 159920, "total_steps": 181800, "loss": 0.0521, "lr": 2.1740718836582046e-06, "epoch": 17.592959295929592, "percentage": 87.96, "elapsed_time": "6:18:44", "remaining_time": "0:51:49", "throughput": 1485.1, "total_tokens": 33748832} {"current_steps": 159925, "total_steps": 181800, "loss": 0.0243, "lr": 2.1730930577117475e-06, "epoch": 17.593509350935093, "percentage": 87.97, "elapsed_time": "6:18:45", "remaining_time": "0:51:48", "throughput": 1485.1, "total_tokens": 33749888} {"current_steps": 159930, "total_steps": 181800, "loss": 0.0024, "lr": 2.1721144421499418e-06, "epoch": 17.594059405940595, "percentage": 87.97, "elapsed_time": "6:18:46", "remaining_time": "0:51:47", "throughput": 1485.11, "total_tokens": 33750976} {"current_steps": 159935, "total_steps": 181800, "loss": 0.0494, "lr": 2.1711360369817994e-06, "epoch": 17.594609460946096, "percentage": 87.97, "elapsed_time": "6:18:46", "remaining_time": "0:51:47", "throughput": 1485.11, "total_tokens": 33752064} {"current_steps": 159940, "total_steps": 181800, "loss": 0.0012, "lr": 2.1701578422163442e-06, "epoch": 17.595159515951597, "percentage": 87.98, "elapsed_time": "6:18:47", "remaining_time": "0:51:46", "throughput": 1485.11, "total_tokens": 33753088} {"current_steps": 159945, "total_steps": 181800, "loss": 0.0069, "lr": 2.1691798578625883e-06, "epoch": 17.595709570957094, "percentage": 87.98, "elapsed_time": "6:18:48", "remaining_time": "0:51:45", "throughput": 1485.11, "total_tokens": 33754208} {"current_steps": 159950, "total_steps": 181800, "loss": 0.0043, "lr": 2.1682020839295465e-06, "epoch": 17.596259625962595, "percentage": 87.98, "elapsed_time": "6:18:49", "remaining_time": "0:51:44", "throughput": 1485.11, "total_tokens": 33755264} {"current_steps": 159955, "total_steps": 181800, "loss": 0.0868, "lr": 2.167224520426228e-06, "epoch": 17.596809680968097, "percentage": 87.98, "elapsed_time": "6:18:49", "remaining_time": "0:51:44", "throughput": 1485.12, "total_tokens": 33756320} {"current_steps": 159960, "total_steps": 181800, "loss": 0.0014, "lr": 2.1662471673616456e-06, "epoch": 17.597359735973598, "percentage": 87.99, "elapsed_time": "6:18:50", "remaining_time": "0:51:43", "throughput": 1485.11, "total_tokens": 33757312} {"current_steps": 159965, "total_steps": 181800, "loss": 0.1357, "lr": 2.1652700247448117e-06, "epoch": 17.5979097909791, "percentage": 87.99, "elapsed_time": "6:18:51", "remaining_time": "0:51:42", "throughput": 1485.12, "total_tokens": 33758432} {"current_steps": 159970, "total_steps": 181800, "loss": 0.0288, "lr": 2.164293092584721e-06, "epoch": 17.5984598459846, "percentage": 87.99, "elapsed_time": "6:18:51", "remaining_time": "0:51:42", "throughput": 1485.12, "total_tokens": 33759520} {"current_steps": 159975, "total_steps": 181800, "loss": 0.084, "lr": 2.1633163708903866e-06, "epoch": 17.599009900990097, "percentage": 88.0, "elapsed_time": "6:18:52", "remaining_time": "0:51:41", "throughput": 1485.13, "total_tokens": 33760640} {"current_steps": 159980, "total_steps": 181800, "loss": 0.0043, "lr": 2.1623398596708034e-06, "epoch": 17.5995599559956, "percentage": 88.0, "elapsed_time": "6:18:53", "remaining_time": "0:51:40", "throughput": 1485.13, "total_tokens": 33761696} {"current_steps": 159985, "total_steps": 181800, "loss": 0.0043, "lr": 2.1613635589349756e-06, "epoch": 17.6001100110011, "percentage": 88.0, "elapsed_time": "6:18:53", "remaining_time": "0:51:39", "throughput": 1485.13, "total_tokens": 33762752} {"current_steps": 159990, "total_steps": 181800, "loss": 0.0797, "lr": 2.1603874686919048e-06, "epoch": 17.6006600660066, "percentage": 88.0, "elapsed_time": "6:18:54", "remaining_time": "0:51:39", "throughput": 1485.13, "total_tokens": 33763808} {"current_steps": 159995, "total_steps": 181800, "loss": 0.0087, "lr": 2.15941158895058e-06, "epoch": 17.6012101210121, "percentage": 88.01, "elapsed_time": "6:18:55", "remaining_time": "0:51:38", "throughput": 1485.13, "total_tokens": 33764832} {"current_steps": 160000, "total_steps": 181800, "loss": 0.0669, "lr": 2.1584359197200004e-06, "epoch": 17.601760176017603, "percentage": 88.01, "elapsed_time": "6:18:55", "remaining_time": "0:51:37", "throughput": 1485.13, "total_tokens": 33765856} {"current_steps": 160005, "total_steps": 181800, "loss": 0.0391, "lr": 2.1574604610091587e-06, "epoch": 17.602310231023104, "percentage": 88.01, "elapsed_time": "6:18:56", "remaining_time": "0:51:37", "throughput": 1485.13, "total_tokens": 33766912} {"current_steps": 160010, "total_steps": 181800, "loss": 0.0091, "lr": 2.156485212827039e-06, "epoch": 17.6028602860286, "percentage": 88.01, "elapsed_time": "6:18:57", "remaining_time": "0:51:36", "throughput": 1485.13, "total_tokens": 33767936} {"current_steps": 160015, "total_steps": 181800, "loss": 0.004, "lr": 2.155510175182632e-06, "epoch": 17.603410341034103, "percentage": 88.02, "elapsed_time": "6:18:58", "remaining_time": "0:51:35", "throughput": 1485.13, "total_tokens": 33768960} {"current_steps": 160020, "total_steps": 181800, "loss": 0.0321, "lr": 2.154535348084932e-06, "epoch": 17.603960396039604, "percentage": 88.02, "elapsed_time": "6:18:58", "remaining_time": "0:51:34", "throughput": 1485.13, "total_tokens": 33770048} {"current_steps": 160025, "total_steps": 181800, "loss": 0.0026, "lr": 2.1535607315429112e-06, "epoch": 17.604510451045105, "percentage": 88.02, "elapsed_time": "6:18:59", "remaining_time": "0:51:34", "throughput": 1485.13, "total_tokens": 33771072} {"current_steps": 160030, "total_steps": 181800, "loss": 0.0073, "lr": 2.152586325565564e-06, "epoch": 17.605060506050606, "percentage": 88.03, "elapsed_time": "6:19:00", "remaining_time": "0:51:33", "throughput": 1485.13, "total_tokens": 33772128} {"current_steps": 160035, "total_steps": 181800, "loss": 0.0329, "lr": 2.151612130161859e-06, "epoch": 17.605610561056107, "percentage": 88.03, "elapsed_time": "6:19:00", "remaining_time": "0:51:32", "throughput": 1485.14, "total_tokens": 33773216} {"current_steps": 160040, "total_steps": 181800, "loss": 0.026, "lr": 2.150638145340783e-06, "epoch": 17.606160616061608, "percentage": 88.03, "elapsed_time": "6:19:01", "remaining_time": "0:51:32", "throughput": 1485.14, "total_tokens": 33774304} {"current_steps": 160045, "total_steps": 181800, "loss": 0.031, "lr": 2.1496643711113153e-06, "epoch": 17.606710671067106, "percentage": 88.03, "elapsed_time": "6:19:02", "remaining_time": "0:51:31", "throughput": 1485.14, "total_tokens": 33775392} {"current_steps": 160050, "total_steps": 181800, "loss": 0.0579, "lr": 2.148690807482423e-06, "epoch": 17.607260726072607, "percentage": 88.04, "elapsed_time": "6:19:02", "remaining_time": "0:51:30", "throughput": 1485.15, "total_tokens": 33776480} {"current_steps": 160055, "total_steps": 181800, "loss": 0.0018, "lr": 2.147717454463086e-06, "epoch": 17.607810781078108, "percentage": 88.04, "elapsed_time": "6:19:03", "remaining_time": "0:51:29", "throughput": 1485.15, "total_tokens": 33777504} {"current_steps": 160060, "total_steps": 181800, "loss": 0.0018, "lr": 2.1467443120622653e-06, "epoch": 17.60836083608361, "percentage": 88.04, "elapsed_time": "6:19:04", "remaining_time": "0:51:29", "throughput": 1485.15, "total_tokens": 33778560} {"current_steps": 160065, "total_steps": 181800, "loss": 0.0054, "lr": 2.145771380288944e-06, "epoch": 17.60891089108911, "percentage": 88.04, "elapsed_time": "6:19:04", "remaining_time": "0:51:28", "throughput": 1485.15, "total_tokens": 33779616} {"current_steps": 160070, "total_steps": 181800, "loss": 0.1, "lr": 2.144798659152075e-06, "epoch": 17.60946094609461, "percentage": 88.05, "elapsed_time": "6:19:05", "remaining_time": "0:51:27", "throughput": 1485.15, "total_tokens": 33780640} {"current_steps": 160075, "total_steps": 181800, "loss": 0.0092, "lr": 2.14382614866063e-06, "epoch": 17.61001100110011, "percentage": 88.05, "elapsed_time": "6:19:06", "remaining_time": "0:51:27", "throughput": 1485.15, "total_tokens": 33781696} {"current_steps": 160080, "total_steps": 181800, "loss": 0.0022, "lr": 2.1428538488235754e-06, "epoch": 17.61056105610561, "percentage": 88.05, "elapsed_time": "6:19:07", "remaining_time": "0:51:26", "throughput": 1485.15, "total_tokens": 33782752} {"current_steps": 160085, "total_steps": 181800, "loss": 0.1053, "lr": 2.1418817596498663e-06, "epoch": 17.61111111111111, "percentage": 88.06, "elapsed_time": "6:19:07", "remaining_time": "0:51:25", "throughput": 1485.15, "total_tokens": 33783776} {"current_steps": 160090, "total_steps": 181800, "loss": 0.0069, "lr": 2.1409098811484674e-06, "epoch": 17.611661166116612, "percentage": 88.06, "elapsed_time": "6:19:08", "remaining_time": "0:51:24", "throughput": 1485.15, "total_tokens": 33784864} {"current_steps": 160095, "total_steps": 181800, "loss": 0.001, "lr": 2.139938213328335e-06, "epoch": 17.612211221122113, "percentage": 88.06, "elapsed_time": "6:19:09", "remaining_time": "0:51:24", "throughput": 1485.15, "total_tokens": 33785856} {"current_steps": 160100, "total_steps": 181800, "loss": 0.0071, "lr": 2.1389667561984127e-06, "epoch": 17.612761276127614, "percentage": 88.06, "elapsed_time": "6:19:09", "remaining_time": "0:51:23", "throughput": 1485.15, "total_tokens": 33786912} {"current_steps": 160105, "total_steps": 181800, "loss": 0.0396, "lr": 2.1379955097676734e-06, "epoch": 17.61331133113311, "percentage": 88.07, "elapsed_time": "6:19:10", "remaining_time": "0:51:22", "throughput": 1485.16, "total_tokens": 33788000} {"current_steps": 160110, "total_steps": 181800, "loss": 0.0039, "lr": 2.1370244740450546e-06, "epoch": 17.613861386138613, "percentage": 88.07, "elapsed_time": "6:19:11", "remaining_time": "0:51:22", "throughput": 1485.16, "total_tokens": 33788992} {"current_steps": 160115, "total_steps": 181800, "loss": 0.123, "lr": 2.1360536490395154e-06, "epoch": 17.614411441144114, "percentage": 88.07, "elapsed_time": "6:19:11", "remaining_time": "0:51:21", "throughput": 1485.16, "total_tokens": 33790016} {"current_steps": 160120, "total_steps": 181800, "loss": 0.0318, "lr": 2.1350830347599992e-06, "epoch": 17.614961496149615, "percentage": 88.07, "elapsed_time": "6:19:12", "remaining_time": "0:51:20", "throughput": 1485.16, "total_tokens": 33791040} {"current_steps": 160125, "total_steps": 181800, "loss": 0.0272, "lr": 2.134112631215443e-06, "epoch": 17.615511551155116, "percentage": 88.08, "elapsed_time": "6:19:13", "remaining_time": "0:51:19", "throughput": 1485.16, "total_tokens": 33792128} {"current_steps": 160130, "total_steps": 181800, "loss": 0.0227, "lr": 2.133142438414801e-06, "epoch": 17.616061606160617, "percentage": 88.08, "elapsed_time": "6:19:13", "remaining_time": "0:51:19", "throughput": 1485.16, "total_tokens": 33793216} {"current_steps": 160135, "total_steps": 181800, "loss": 0.0045, "lr": 2.1321724563670127e-06, "epoch": 17.616611661166118, "percentage": 88.08, "elapsed_time": "6:19:14", "remaining_time": "0:51:18", "throughput": 1485.17, "total_tokens": 33794336} {"current_steps": 160140, "total_steps": 181800, "loss": 0.0208, "lr": 2.131202685081024e-06, "epoch": 17.617161716171616, "percentage": 88.09, "elapsed_time": "6:19:15", "remaining_time": "0:51:17", "throughput": 1485.17, "total_tokens": 33795360} {"current_steps": 160145, "total_steps": 181800, "loss": 0.0187, "lr": 2.130233124565764e-06, "epoch": 17.617711771177117, "percentage": 88.09, "elapsed_time": "6:19:15", "remaining_time": "0:51:17", "throughput": 1485.17, "total_tokens": 33796448} {"current_steps": 160150, "total_steps": 181800, "loss": 0.0058, "lr": 2.1292637748301674e-06, "epoch": 17.618261826182618, "percentage": 88.09, "elapsed_time": "6:19:16", "remaining_time": "0:51:16", "throughput": 1485.17, "total_tokens": 33797504} {"current_steps": 160155, "total_steps": 181800, "loss": 0.0149, "lr": 2.128294635883177e-06, "epoch": 17.61881188118812, "percentage": 88.09, "elapsed_time": "6:19:17", "remaining_time": "0:51:15", "throughput": 1485.17, "total_tokens": 33798624} {"current_steps": 160160, "total_steps": 181800, "loss": 0.0015, "lr": 2.12732570773371e-06, "epoch": 17.61936193619362, "percentage": 88.1, "elapsed_time": "6:19:18", "remaining_time": "0:51:14", "throughput": 1485.18, "total_tokens": 33799712} {"current_steps": 160165, "total_steps": 181800, "loss": 0.0027, "lr": 2.1263569903907182e-06, "epoch": 17.61991199119912, "percentage": 88.1, "elapsed_time": "6:19:18", "remaining_time": "0:51:14", "throughput": 1485.18, "total_tokens": 33800800} {"current_steps": 160170, "total_steps": 181800, "loss": 0.0019, "lr": 2.1253884838631167e-06, "epoch": 17.620462046204622, "percentage": 88.1, "elapsed_time": "6:19:19", "remaining_time": "0:51:13", "throughput": 1485.19, "total_tokens": 33801952} {"current_steps": 160175, "total_steps": 181800, "loss": 0.0013, "lr": 2.1244201881598287e-06, "epoch": 17.62101210121012, "percentage": 88.11, "elapsed_time": "6:19:20", "remaining_time": "0:51:12", "throughput": 1485.19, "total_tokens": 33803072} {"current_steps": 160180, "total_steps": 181800, "loss": 0.0072, "lr": 2.1234521032897857e-06, "epoch": 17.62156215621562, "percentage": 88.11, "elapsed_time": "6:19:20", "remaining_time": "0:51:12", "throughput": 1485.19, "total_tokens": 33804160} {"current_steps": 160185, "total_steps": 181800, "loss": 0.0007, "lr": 2.1224842292619033e-06, "epoch": 17.622112211221122, "percentage": 88.11, "elapsed_time": "6:19:21", "remaining_time": "0:51:11", "throughput": 1485.19, "total_tokens": 33805152} {"current_steps": 160190, "total_steps": 181800, "loss": 0.0015, "lr": 2.121516566085108e-06, "epoch": 17.622662266226623, "percentage": 88.11, "elapsed_time": "6:19:22", "remaining_time": "0:51:10", "throughput": 1485.19, "total_tokens": 33806208} {"current_steps": 160195, "total_steps": 181800, "loss": 0.0038, "lr": 2.120549113768322e-06, "epoch": 17.623212321232124, "percentage": 88.12, "elapsed_time": "6:19:22", "remaining_time": "0:51:09", "throughput": 1485.2, "total_tokens": 33807296} {"current_steps": 160200, "total_steps": 181800, "loss": 0.0233, "lr": 2.1195818723204473e-06, "epoch": 17.623762376237625, "percentage": 88.12, "elapsed_time": "6:19:23", "remaining_time": "0:51:09", "throughput": 1485.2, "total_tokens": 33808384} {"current_steps": 160205, "total_steps": 181800, "loss": 0.0029, "lr": 2.118614841750416e-06, "epoch": 17.624312431243123, "percentage": 88.12, "elapsed_time": "6:19:24", "remaining_time": "0:51:08", "throughput": 1485.2, "total_tokens": 33809408} {"current_steps": 160210, "total_steps": 181800, "loss": 0.0053, "lr": 2.117648022067126e-06, "epoch": 17.624862486248624, "percentage": 88.12, "elapsed_time": "6:19:24", "remaining_time": "0:51:07", "throughput": 1485.2, "total_tokens": 33810560} {"current_steps": 160215, "total_steps": 181800, "loss": 0.0026, "lr": 2.116681413279498e-06, "epoch": 17.625412541254125, "percentage": 88.13, "elapsed_time": "6:19:25", "remaining_time": "0:51:07", "throughput": 1485.2, "total_tokens": 33811584} {"current_steps": 160220, "total_steps": 181800, "loss": 0.0979, "lr": 2.115715015396433e-06, "epoch": 17.625962596259626, "percentage": 88.13, "elapsed_time": "6:19:26", "remaining_time": "0:51:06", "throughput": 1485.21, "total_tokens": 33812608} {"current_steps": 160225, "total_steps": 181800, "loss": 0.007, "lr": 2.1147488284268436e-06, "epoch": 17.626512651265127, "percentage": 88.13, "elapsed_time": "6:19:26", "remaining_time": "0:51:05", "throughput": 1485.21, "total_tokens": 33813760} {"current_steps": 160230, "total_steps": 181800, "loss": 0.1228, "lr": 2.113782852379634e-06, "epoch": 17.627062706270628, "percentage": 88.14, "elapsed_time": "6:19:27", "remaining_time": "0:51:04", "throughput": 1485.21, "total_tokens": 33814816} {"current_steps": 160235, "total_steps": 181800, "loss": 0.0024, "lr": 2.1128170872637078e-06, "epoch": 17.62761276127613, "percentage": 88.14, "elapsed_time": "6:19:28", "remaining_time": "0:51:04", "throughput": 1485.22, "total_tokens": 33815936} {"current_steps": 160240, "total_steps": 181800, "loss": 0.0698, "lr": 2.111851533087961e-06, "epoch": 17.628162816281627, "percentage": 88.14, "elapsed_time": "6:19:29", "remaining_time": "0:51:03", "throughput": 1485.22, "total_tokens": 33817024} {"current_steps": 160245, "total_steps": 181800, "loss": 0.0194, "lr": 2.110886189861294e-06, "epoch": 17.628712871287128, "percentage": 88.14, "elapsed_time": "6:19:29", "remaining_time": "0:51:02", "throughput": 1485.22, "total_tokens": 33818016} {"current_steps": 160250, "total_steps": 181800, "loss": 0.0043, "lr": 2.1099210575926066e-06, "epoch": 17.62926292629263, "percentage": 88.15, "elapsed_time": "6:19:30", "remaining_time": "0:51:02", "throughput": 1485.22, "total_tokens": 33819168} {"current_steps": 160255, "total_steps": 181800, "loss": 0.0048, "lr": 2.1089561362907963e-06, "epoch": 17.62981298129813, "percentage": 88.15, "elapsed_time": "6:19:31", "remaining_time": "0:51:01", "throughput": 1485.22, "total_tokens": 33820224} {"current_steps": 160260, "total_steps": 181800, "loss": 0.001, "lr": 2.1079914259647533e-06, "epoch": 17.63036303630363, "percentage": 88.15, "elapsed_time": "6:19:31", "remaining_time": "0:51:00", "throughput": 1485.22, "total_tokens": 33821248} {"current_steps": 160265, "total_steps": 181800, "loss": 0.0008, "lr": 2.107026926623365e-06, "epoch": 17.630913091309132, "percentage": 88.15, "elapsed_time": "6:19:32", "remaining_time": "0:50:59", "throughput": 1485.22, "total_tokens": 33822272} {"current_steps": 160270, "total_steps": 181800, "loss": 0.0923, "lr": 2.1060626382755274e-06, "epoch": 17.63146314631463, "percentage": 88.16, "elapsed_time": "6:19:33", "remaining_time": "0:50:59", "throughput": 1485.22, "total_tokens": 33823296} {"current_steps": 160275, "total_steps": 181800, "loss": 0.0118, "lr": 2.1050985609301216e-06, "epoch": 17.63201320132013, "percentage": 88.16, "elapsed_time": "6:19:33", "remaining_time": "0:50:58", "throughput": 1485.23, "total_tokens": 33824416} {"current_steps": 160280, "total_steps": 181800, "loss": 0.0008, "lr": 2.104134694596038e-06, "epoch": 17.632563256325632, "percentage": 88.16, "elapsed_time": "6:19:34", "remaining_time": "0:50:57", "throughput": 1485.23, "total_tokens": 33825504} {"current_steps": 160285, "total_steps": 181800, "loss": 0.091, "lr": 2.103171039282162e-06, "epoch": 17.633113311331133, "percentage": 88.17, "elapsed_time": "6:19:35", "remaining_time": "0:50:57", "throughput": 1485.23, "total_tokens": 33826528} {"current_steps": 160290, "total_steps": 181800, "loss": 0.001, "lr": 2.102207594997366e-06, "epoch": 17.633663366336634, "percentage": 88.17, "elapsed_time": "6:19:35", "remaining_time": "0:50:56", "throughput": 1485.23, "total_tokens": 33827584} {"current_steps": 160295, "total_steps": 181800, "loss": 0.0046, "lr": 2.10124436175054e-06, "epoch": 17.634213421342135, "percentage": 88.17, "elapsed_time": "6:19:36", "remaining_time": "0:50:55", "throughput": 1485.23, "total_tokens": 33828608} {"current_steps": 160300, "total_steps": 181800, "loss": 0.007, "lr": 2.10028133955055e-06, "epoch": 17.634763476347636, "percentage": 88.17, "elapsed_time": "6:19:37", "remaining_time": "0:50:54", "throughput": 1485.23, "total_tokens": 33829632} {"current_steps": 160305, "total_steps": 181800, "loss": 0.0027, "lr": 2.0993185284062826e-06, "epoch": 17.635313531353134, "percentage": 88.18, "elapsed_time": "6:19:38", "remaining_time": "0:50:54", "throughput": 1485.23, "total_tokens": 33830688} {"current_steps": 160310, "total_steps": 181800, "loss": 0.0013, "lr": 2.098355928326609e-06, "epoch": 17.635863586358635, "percentage": 88.18, "elapsed_time": "6:19:38", "remaining_time": "0:50:53", "throughput": 1485.24, "total_tokens": 33831776} {"current_steps": 160315, "total_steps": 181800, "loss": 0.0012, "lr": 2.097393539320397e-06, "epoch": 17.636413641364136, "percentage": 88.18, "elapsed_time": "6:19:39", "remaining_time": "0:50:52", "throughput": 1485.24, "total_tokens": 33832864} {"current_steps": 160320, "total_steps": 181800, "loss": 0.0025, "lr": 2.0964313613965225e-06, "epoch": 17.636963696369637, "percentage": 88.18, "elapsed_time": "6:19:40", "remaining_time": "0:50:52", "throughput": 1485.24, "total_tokens": 33833920} {"current_steps": 160325, "total_steps": 181800, "loss": 0.0012, "lr": 2.0954693945638455e-06, "epoch": 17.63751375137514, "percentage": 88.19, "elapsed_time": "6:19:40", "remaining_time": "0:50:51", "throughput": 1485.24, "total_tokens": 33834944} {"current_steps": 160330, "total_steps": 181800, "loss": 0.1812, "lr": 2.0945076388312417e-06, "epoch": 17.63806380638064, "percentage": 88.19, "elapsed_time": "6:19:41", "remaining_time": "0:50:50", "throughput": 1485.24, "total_tokens": 33835968} {"current_steps": 160335, "total_steps": 181800, "loss": 0.0917, "lr": 2.093546094207566e-06, "epoch": 17.638613861386137, "percentage": 88.19, "elapsed_time": "6:19:42", "remaining_time": "0:50:49", "throughput": 1485.24, "total_tokens": 33836992} {"current_steps": 160340, "total_steps": 181800, "loss": 0.0073, "lr": 2.0925847607016824e-06, "epoch": 17.639163916391638, "percentage": 88.2, "elapsed_time": "6:19:42", "remaining_time": "0:50:49", "throughput": 1485.24, "total_tokens": 33838048} {"current_steps": 160345, "total_steps": 181800, "loss": 0.0061, "lr": 2.091623638322457e-06, "epoch": 17.63971397139714, "percentage": 88.2, "elapsed_time": "6:19:43", "remaining_time": "0:50:48", "throughput": 1485.24, "total_tokens": 33839072} {"current_steps": 160350, "total_steps": 181800, "loss": 0.0535, "lr": 2.0906627270787403e-06, "epoch": 17.64026402640264, "percentage": 88.2, "elapsed_time": "6:19:44", "remaining_time": "0:50:47", "throughput": 1485.24, "total_tokens": 33840160} {"current_steps": 160355, "total_steps": 181800, "loss": 0.0036, "lr": 2.0897020269793984e-06, "epoch": 17.64081408140814, "percentage": 88.2, "elapsed_time": "6:19:44", "remaining_time": "0:50:47", "throughput": 1485.24, "total_tokens": 33841184} {"current_steps": 160360, "total_steps": 181800, "loss": 0.0168, "lr": 2.0887415380332733e-06, "epoch": 17.641364136413642, "percentage": 88.21, "elapsed_time": "6:19:45", "remaining_time": "0:50:46", "throughput": 1485.24, "total_tokens": 33842240} {"current_steps": 160365, "total_steps": 181800, "loss": 0.0223, "lr": 2.0877812602492246e-06, "epoch": 17.641914191419144, "percentage": 88.21, "elapsed_time": "6:19:46", "remaining_time": "0:50:45", "throughput": 1485.25, "total_tokens": 33843296} {"current_steps": 160370, "total_steps": 181800, "loss": 0.0018, "lr": 2.086821193636107e-06, "epoch": 17.64246424642464, "percentage": 88.21, "elapsed_time": "6:19:47", "remaining_time": "0:50:44", "throughput": 1485.25, "total_tokens": 33844384} {"current_steps": 160375, "total_steps": 181800, "loss": 0.139, "lr": 2.0858613382027576e-06, "epoch": 17.643014301430142, "percentage": 88.22, "elapsed_time": "6:19:47", "remaining_time": "0:50:44", "throughput": 1485.25, "total_tokens": 33845440} {"current_steps": 160380, "total_steps": 181800, "loss": 0.1832, "lr": 2.084901693958033e-06, "epoch": 17.643564356435643, "percentage": 88.22, "elapsed_time": "6:19:48", "remaining_time": "0:50:43", "throughput": 1485.25, "total_tokens": 33846432} {"current_steps": 160385, "total_steps": 181800, "loss": 0.0068, "lr": 2.0839422609107735e-06, "epoch": 17.644114411441144, "percentage": 88.22, "elapsed_time": "6:19:49", "remaining_time": "0:50:42", "throughput": 1485.25, "total_tokens": 33847520} {"current_steps": 160390, "total_steps": 181800, "loss": 0.0119, "lr": 2.082983039069819e-06, "epoch": 17.644664466446645, "percentage": 88.22, "elapsed_time": "6:19:49", "remaining_time": "0:50:42", "throughput": 1485.25, "total_tokens": 33848576} {"current_steps": 160395, "total_steps": 181800, "loss": 0.0056, "lr": 2.082024028444013e-06, "epoch": 17.645214521452147, "percentage": 88.23, "elapsed_time": "6:19:50", "remaining_time": "0:50:41", "throughput": 1485.25, "total_tokens": 33849632} {"current_steps": 160400, "total_steps": 181800, "loss": 0.0014, "lr": 2.081065229042195e-06, "epoch": 17.645764576457644, "percentage": 88.23, "elapsed_time": "6:19:51", "remaining_time": "0:50:40", "throughput": 1485.25, "total_tokens": 33850656} {"current_steps": 160405, "total_steps": 181800, "loss": 0.0051, "lr": 2.080106640873203e-06, "epoch": 17.646314631463145, "percentage": 88.23, "elapsed_time": "6:19:51", "remaining_time": "0:50:40", "throughput": 1485.25, "total_tokens": 33851680} {"current_steps": 160410, "total_steps": 181800, "loss": 0.032, "lr": 2.0791482639458736e-06, "epoch": 17.646864686468646, "percentage": 88.23, "elapsed_time": "6:19:52", "remaining_time": "0:50:39", "throughput": 1485.26, "total_tokens": 33852800} {"current_steps": 160415, "total_steps": 181800, "loss": 0.0353, "lr": 2.0781900982690284e-06, "epoch": 17.647414741474147, "percentage": 88.24, "elapsed_time": "6:19:53", "remaining_time": "0:50:38", "throughput": 1485.26, "total_tokens": 33853792} {"current_steps": 160420, "total_steps": 181800, "loss": 0.0875, "lr": 2.077232143851507e-06, "epoch": 17.64796479647965, "percentage": 88.24, "elapsed_time": "6:19:53", "remaining_time": "0:50:37", "throughput": 1485.26, "total_tokens": 33854848} {"current_steps": 160425, "total_steps": 181800, "loss": 0.0083, "lr": 2.076274400702144e-06, "epoch": 17.64851485148515, "percentage": 88.24, "elapsed_time": "6:19:54", "remaining_time": "0:50:37", "throughput": 1485.26, "total_tokens": 33855904} {"current_steps": 160430, "total_steps": 181800, "loss": 0.0231, "lr": 2.075316868829755e-06, "epoch": 17.64906490649065, "percentage": 88.25, "elapsed_time": "6:19:55", "remaining_time": "0:50:36", "throughput": 1485.26, "total_tokens": 33856960} {"current_steps": 160435, "total_steps": 181800, "loss": 0.0067, "lr": 2.074359548243171e-06, "epoch": 17.649614961496148, "percentage": 88.25, "elapsed_time": "6:19:55", "remaining_time": "0:50:35", "throughput": 1485.26, "total_tokens": 33858080} {"current_steps": 160440, "total_steps": 181800, "loss": 0.0134, "lr": 2.0734024389512134e-06, "epoch": 17.65016501650165, "percentage": 88.25, "elapsed_time": "6:19:56", "remaining_time": "0:50:35", "throughput": 1485.27, "total_tokens": 33859136} {"current_steps": 160445, "total_steps": 181800, "loss": 0.0017, "lr": 2.0724455409627087e-06, "epoch": 17.65071507150715, "percentage": 88.25, "elapsed_time": "6:19:57", "remaining_time": "0:50:34", "throughput": 1485.27, "total_tokens": 33860224} {"current_steps": 160450, "total_steps": 181800, "loss": 0.007, "lr": 2.0714888542864657e-06, "epoch": 17.65126512651265, "percentage": 88.26, "elapsed_time": "6:19:58", "remaining_time": "0:50:33", "throughput": 1485.27, "total_tokens": 33861280} {"current_steps": 160455, "total_steps": 181800, "loss": 0.0316, "lr": 2.0705323789313088e-06, "epoch": 17.651815181518153, "percentage": 88.26, "elapsed_time": "6:19:58", "remaining_time": "0:50:32", "throughput": 1485.27, "total_tokens": 33862304} {"current_steps": 160460, "total_steps": 181800, "loss": 0.0024, "lr": 2.069576114906055e-06, "epoch": 17.652365236523654, "percentage": 88.26, "elapsed_time": "6:19:59", "remaining_time": "0:50:32", "throughput": 1485.27, "total_tokens": 33863296} {"current_steps": 160465, "total_steps": 181800, "loss": 0.0863, "lr": 2.0686200622195117e-06, "epoch": 17.652915291529155, "percentage": 88.26, "elapsed_time": "6:20:00", "remaining_time": "0:50:31", "throughput": 1485.27, "total_tokens": 33864384} {"current_steps": 160470, "total_steps": 181800, "loss": 0.045, "lr": 2.0676642208804996e-06, "epoch": 17.653465346534652, "percentage": 88.27, "elapsed_time": "6:20:00", "remaining_time": "0:50:30", "throughput": 1485.27, "total_tokens": 33865408} {"current_steps": 160475, "total_steps": 181800, "loss": 0.0949, "lr": 2.0667085908978173e-06, "epoch": 17.654015401540153, "percentage": 88.27, "elapsed_time": "6:20:01", "remaining_time": "0:50:30", "throughput": 1485.27, "total_tokens": 33866432} {"current_steps": 160480, "total_steps": 181800, "loss": 0.0009, "lr": 2.065753172280277e-06, "epoch": 17.654565456545654, "percentage": 88.27, "elapsed_time": "6:20:02", "remaining_time": "0:50:29", "throughput": 1485.27, "total_tokens": 33867520} {"current_steps": 160485, "total_steps": 181800, "loss": 0.0017, "lr": 2.0647979650366882e-06, "epoch": 17.655115511551156, "percentage": 88.28, "elapsed_time": "6:20:02", "remaining_time": "0:50:28", "throughput": 1485.27, "total_tokens": 33868576} {"current_steps": 160490, "total_steps": 181800, "loss": 0.0017, "lr": 2.063842969175847e-06, "epoch": 17.655665566556657, "percentage": 88.28, "elapsed_time": "6:20:03", "remaining_time": "0:50:27", "throughput": 1485.28, "total_tokens": 33869664} {"current_steps": 160495, "total_steps": 181800, "loss": 0.066, "lr": 2.0628881847065658e-06, "epoch": 17.656215621562158, "percentage": 88.28, "elapsed_time": "6:20:04", "remaining_time": "0:50:27", "throughput": 1485.28, "total_tokens": 33870688} {"current_steps": 160500, "total_steps": 181800, "loss": 0.0698, "lr": 2.061933611637637e-06, "epoch": 17.656765676567655, "percentage": 88.28, "elapsed_time": "6:20:04", "remaining_time": "0:50:26", "throughput": 1485.28, "total_tokens": 33871776} {"current_steps": 160505, "total_steps": 181800, "loss": 0.0011, "lr": 2.060979249977854e-06, "epoch": 17.657315731573156, "percentage": 88.29, "elapsed_time": "6:20:05", "remaining_time": "0:50:25", "throughput": 1485.28, "total_tokens": 33872896} {"current_steps": 160510, "total_steps": 181800, "loss": 0.0065, "lr": 2.060025099736018e-06, "epoch": 17.657865786578657, "percentage": 88.29, "elapsed_time": "6:20:06", "remaining_time": "0:50:25", "throughput": 1485.29, "total_tokens": 33874016} {"current_steps": 160515, "total_steps": 181800, "loss": 0.0026, "lr": 2.059071160920925e-06, "epoch": 17.65841584158416, "percentage": 88.29, "elapsed_time": "6:20:07", "remaining_time": "0:50:24", "throughput": 1485.29, "total_tokens": 33875104} {"current_steps": 160520, "total_steps": 181800, "loss": 0.0397, "lr": 2.058117433541368e-06, "epoch": 17.65896589658966, "percentage": 88.29, "elapsed_time": "6:20:07", "remaining_time": "0:50:23", "throughput": 1485.29, "total_tokens": 33876160} {"current_steps": 160525, "total_steps": 181800, "loss": 0.0025, "lr": 2.0571639176061337e-06, "epoch": 17.65951595159516, "percentage": 88.3, "elapsed_time": "6:20:08", "remaining_time": "0:50:22", "throughput": 1485.29, "total_tokens": 33877184} {"current_steps": 160530, "total_steps": 181800, "loss": 0.0051, "lr": 2.0562106131240045e-06, "epoch": 17.66006600660066, "percentage": 88.3, "elapsed_time": "6:20:09", "remaining_time": "0:50:22", "throughput": 1485.29, "total_tokens": 33878240} {"current_steps": 160535, "total_steps": 181800, "loss": 0.0709, "lr": 2.055257520103776e-06, "epoch": 17.66061606160616, "percentage": 88.3, "elapsed_time": "6:20:09", "remaining_time": "0:50:21", "throughput": 1485.29, "total_tokens": 33879232} {"current_steps": 160540, "total_steps": 181800, "loss": 0.005, "lr": 2.0543046385542277e-06, "epoch": 17.66116611661166, "percentage": 88.31, "elapsed_time": "6:20:10", "remaining_time": "0:50:20", "throughput": 1485.29, "total_tokens": 33880320} {"current_steps": 160545, "total_steps": 181800, "loss": 0.0506, "lr": 2.053351968484146e-06, "epoch": 17.66171617161716, "percentage": 88.31, "elapsed_time": "6:20:11", "remaining_time": "0:50:20", "throughput": 1485.3, "total_tokens": 33881376} {"current_steps": 160550, "total_steps": 181800, "loss": 0.0113, "lr": 2.0523995099023114e-06, "epoch": 17.662266226622663, "percentage": 88.31, "elapsed_time": "6:20:11", "remaining_time": "0:50:19", "throughput": 1485.3, "total_tokens": 33882432} {"current_steps": 160555, "total_steps": 181800, "loss": 0.0035, "lr": 2.0514472628174906e-06, "epoch": 17.662816281628164, "percentage": 88.31, "elapsed_time": "6:20:12", "remaining_time": "0:50:18", "throughput": 1485.3, "total_tokens": 33883456} {"current_steps": 160560, "total_steps": 181800, "loss": 0.0025, "lr": 2.0504952272384777e-06, "epoch": 17.663366336633665, "percentage": 88.32, "elapsed_time": "6:20:13", "remaining_time": "0:50:17", "throughput": 1485.3, "total_tokens": 33884480} {"current_steps": 160565, "total_steps": 181800, "loss": 0.0027, "lr": 2.0495434031740314e-06, "epoch": 17.663916391639162, "percentage": 88.32, "elapsed_time": "6:20:13", "remaining_time": "0:50:17", "throughput": 1485.3, "total_tokens": 33885600} {"current_steps": 160570, "total_steps": 181800, "loss": 0.0033, "lr": 2.0485917906329283e-06, "epoch": 17.664466446644663, "percentage": 88.32, "elapsed_time": "6:20:14", "remaining_time": "0:50:16", "throughput": 1485.3, "total_tokens": 33886656} {"current_steps": 160575, "total_steps": 181800, "loss": 0.0022, "lr": 2.0476403896239503e-06, "epoch": 17.665016501650165, "percentage": 88.33, "elapsed_time": "6:20:15", "remaining_time": "0:50:15", "throughput": 1485.3, "total_tokens": 33887744} {"current_steps": 160580, "total_steps": 181800, "loss": 0.0056, "lr": 2.046689200155849e-06, "epoch": 17.665566556655666, "percentage": 88.33, "elapsed_time": "6:20:16", "remaining_time": "0:50:15", "throughput": 1485.3, "total_tokens": 33888736} {"current_steps": 160585, "total_steps": 181800, "loss": 0.1184, "lr": 2.045738222237406e-06, "epoch": 17.666116611661167, "percentage": 88.33, "elapsed_time": "6:20:16", "remaining_time": "0:50:14", "throughput": 1485.3, "total_tokens": 33889792} {"current_steps": 160590, "total_steps": 181800, "loss": 0.0014, "lr": 2.0447874558773756e-06, "epoch": 17.666666666666668, "percentage": 88.33, "elapsed_time": "6:20:17", "remaining_time": "0:50:13", "throughput": 1485.31, "total_tokens": 33890912} {"current_steps": 160595, "total_steps": 181800, "loss": 0.0574, "lr": 2.0438369010845226e-06, "epoch": 17.66721672167217, "percentage": 88.34, "elapsed_time": "6:20:18", "remaining_time": "0:50:12", "throughput": 1485.31, "total_tokens": 33892032} {"current_steps": 160600, "total_steps": 181800, "loss": 0.0024, "lr": 2.0428865578676152e-06, "epoch": 17.667766776677666, "percentage": 88.34, "elapsed_time": "6:20:18", "remaining_time": "0:50:12", "throughput": 1485.31, "total_tokens": 33893024} {"current_steps": 160605, "total_steps": 181800, "loss": 0.0114, "lr": 2.0419364262353994e-06, "epoch": 17.668316831683168, "percentage": 88.34, "elapsed_time": "6:20:19", "remaining_time": "0:50:11", "throughput": 1485.31, "total_tokens": 33894016} {"current_steps": 160610, "total_steps": 181800, "loss": 0.0013, "lr": 2.040986506196646e-06, "epoch": 17.66886688668867, "percentage": 88.34, "elapsed_time": "6:20:20", "remaining_time": "0:50:10", "throughput": 1485.31, "total_tokens": 33895136} {"current_steps": 160615, "total_steps": 181800, "loss": 0.0028, "lr": 2.040036797760103e-06, "epoch": 17.66941694169417, "percentage": 88.35, "elapsed_time": "6:20:20", "remaining_time": "0:50:10", "throughput": 1485.31, "total_tokens": 33896160} {"current_steps": 160620, "total_steps": 181800, "loss": 0.0021, "lr": 2.0390873009345198e-06, "epoch": 17.66996699669967, "percentage": 88.35, "elapsed_time": "6:20:21", "remaining_time": "0:50:09", "throughput": 1485.31, "total_tokens": 33897184} {"current_steps": 160625, "total_steps": 181800, "loss": 0.0343, "lr": 2.0381380157286495e-06, "epoch": 17.670517051705172, "percentage": 88.35, "elapsed_time": "6:20:22", "remaining_time": "0:50:08", "throughput": 1485.31, "total_tokens": 33898208} {"current_steps": 160630, "total_steps": 181800, "loss": 0.0336, "lr": 2.037188942151244e-06, "epoch": 17.67106710671067, "percentage": 88.36, "elapsed_time": "6:20:22", "remaining_time": "0:50:07", "throughput": 1485.31, "total_tokens": 33899232} {"current_steps": 160635, "total_steps": 181800, "loss": 0.0688, "lr": 2.036240080211052e-06, "epoch": 17.67161716171617, "percentage": 88.36, "elapsed_time": "6:20:23", "remaining_time": "0:50:07", "throughput": 1485.31, "total_tokens": 33900288} {"current_steps": 160640, "total_steps": 181800, "loss": 0.0414, "lr": 2.035291429916819e-06, "epoch": 17.67216721672167, "percentage": 88.36, "elapsed_time": "6:20:24", "remaining_time": "0:50:06", "throughput": 1485.32, "total_tokens": 33901312} {"current_steps": 160645, "total_steps": 181800, "loss": 0.0014, "lr": 2.03434299127728e-06, "epoch": 17.672717271727173, "percentage": 88.36, "elapsed_time": "6:20:25", "remaining_time": "0:50:05", "throughput": 1485.31, "total_tokens": 33902272} {"current_steps": 160650, "total_steps": 181800, "loss": 0.013, "lr": 2.0333947643011803e-06, "epoch": 17.673267326732674, "percentage": 88.37, "elapsed_time": "6:20:25", "remaining_time": "0:50:05", "throughput": 1485.31, "total_tokens": 33903328} {"current_steps": 160655, "total_steps": 181800, "loss": 0.0067, "lr": 2.0324467489972606e-06, "epoch": 17.673817381738175, "percentage": 88.37, "elapsed_time": "6:20:26", "remaining_time": "0:50:04", "throughput": 1485.32, "total_tokens": 33904416} {"current_steps": 160660, "total_steps": 181800, "loss": 0.039, "lr": 2.0314989453742635e-06, "epoch": 17.674367436743676, "percentage": 88.37, "elapsed_time": "6:20:27", "remaining_time": "0:50:03", "throughput": 1485.32, "total_tokens": 33905504} {"current_steps": 160665, "total_steps": 181800, "loss": 0.0021, "lr": 2.030551353440921e-06, "epoch": 17.674917491749174, "percentage": 88.37, "elapsed_time": "6:20:27", "remaining_time": "0:50:02", "throughput": 1485.32, "total_tokens": 33906592} {"current_steps": 160670, "total_steps": 181800, "loss": 0.0759, "lr": 2.029603973205957e-06, "epoch": 17.675467546754675, "percentage": 88.38, "elapsed_time": "6:20:28", "remaining_time": "0:50:02", "throughput": 1485.32, "total_tokens": 33907680} {"current_steps": 160675, "total_steps": 181800, "loss": 0.1026, "lr": 2.028656804678117e-06, "epoch": 17.676017601760176, "percentage": 88.38, "elapsed_time": "6:20:29", "remaining_time": "0:50:01", "throughput": 1485.33, "total_tokens": 33908768} {"current_steps": 160680, "total_steps": 181800, "loss": 0.0147, "lr": 2.0277098478661216e-06, "epoch": 17.676567656765677, "percentage": 88.38, "elapsed_time": "6:20:29", "remaining_time": "0:50:00", "throughput": 1485.33, "total_tokens": 33909824} {"current_steps": 160685, "total_steps": 181800, "loss": 0.031, "lr": 2.0267631027787003e-06, "epoch": 17.677117711771178, "percentage": 88.39, "elapsed_time": "6:20:30", "remaining_time": "0:50:00", "throughput": 1485.33, "total_tokens": 33910976} {"current_steps": 160690, "total_steps": 181800, "loss": 0.0058, "lr": 2.0258165694245825e-06, "epoch": 17.67766776677668, "percentage": 88.39, "elapsed_time": "6:20:31", "remaining_time": "0:49:59", "throughput": 1485.34, "total_tokens": 33912064} {"current_steps": 160695, "total_steps": 181800, "loss": 0.0027, "lr": 2.024870247812488e-06, "epoch": 17.678217821782177, "percentage": 88.39, "elapsed_time": "6:20:31", "remaining_time": "0:49:58", "throughput": 1485.34, "total_tokens": 33913152} {"current_steps": 160700, "total_steps": 181800, "loss": 0.0524, "lr": 2.0239241379511413e-06, "epoch": 17.678767876787678, "percentage": 88.39, "elapsed_time": "6:20:32", "remaining_time": "0:49:57", "throughput": 1485.34, "total_tokens": 33914144} {"current_steps": 160705, "total_steps": 181800, "loss": 0.0159, "lr": 2.0229782398492576e-06, "epoch": 17.67931793179318, "percentage": 88.4, "elapsed_time": "6:20:33", "remaining_time": "0:49:57", "throughput": 1485.34, "total_tokens": 33915200} {"current_steps": 160710, "total_steps": 181800, "loss": 0.0069, "lr": 2.02203255351556e-06, "epoch": 17.67986798679868, "percentage": 88.4, "elapsed_time": "6:20:33", "remaining_time": "0:49:56", "throughput": 1485.35, "total_tokens": 33916352} {"current_steps": 160715, "total_steps": 181800, "loss": 0.0598, "lr": 2.0210870789587637e-06, "epoch": 17.68041804180418, "percentage": 88.4, "elapsed_time": "6:20:34", "remaining_time": "0:49:55", "throughput": 1485.35, "total_tokens": 33917472} {"current_steps": 160720, "total_steps": 181800, "loss": 0.0034, "lr": 2.020141816187579e-06, "epoch": 17.680968096809682, "percentage": 88.4, "elapsed_time": "6:20:35", "remaining_time": "0:49:55", "throughput": 1485.35, "total_tokens": 33918496} {"current_steps": 160725, "total_steps": 181800, "loss": 0.0081, "lr": 2.0191967652107237e-06, "epoch": 17.681518151815183, "percentage": 88.41, "elapsed_time": "6:20:36", "remaining_time": "0:49:54", "throughput": 1485.35, "total_tokens": 33919552} {"current_steps": 160730, "total_steps": 181800, "loss": 0.1333, "lr": 2.0182519260369015e-06, "epoch": 17.68206820682068, "percentage": 88.41, "elapsed_time": "6:20:36", "remaining_time": "0:49:53", "throughput": 1485.35, "total_tokens": 33920576} {"current_steps": 160735, "total_steps": 181800, "loss": 0.0269, "lr": 2.0173072986748254e-06, "epoch": 17.682618261826182, "percentage": 88.41, "elapsed_time": "6:20:37", "remaining_time": "0:49:52", "throughput": 1485.35, "total_tokens": 33921600} {"current_steps": 160740, "total_steps": 181800, "loss": 0.0096, "lr": 2.0163628831331964e-06, "epoch": 17.683168316831683, "percentage": 88.42, "elapsed_time": "6:20:38", "remaining_time": "0:49:52", "throughput": 1485.35, "total_tokens": 33922688} {"current_steps": 160745, "total_steps": 181800, "loss": 0.0382, "lr": 2.0154186794207246e-06, "epoch": 17.683718371837184, "percentage": 88.42, "elapsed_time": "6:20:38", "remaining_time": "0:49:51", "throughput": 1485.36, "total_tokens": 33923776} {"current_steps": 160750, "total_steps": 181800, "loss": 0.0013, "lr": 2.014474687546111e-06, "epoch": 17.684268426842685, "percentage": 88.42, "elapsed_time": "6:20:39", "remaining_time": "0:49:50", "throughput": 1485.36, "total_tokens": 33924768} {"current_steps": 160755, "total_steps": 181800, "loss": 0.1031, "lr": 2.013530907518052e-06, "epoch": 17.684818481848186, "percentage": 88.42, "elapsed_time": "6:20:40", "remaining_time": "0:49:50", "throughput": 1485.36, "total_tokens": 33925856} {"current_steps": 160760, "total_steps": 181800, "loss": 0.0011, "lr": 2.012587339345251e-06, "epoch": 17.685368536853684, "percentage": 88.43, "elapsed_time": "6:20:40", "remaining_time": "0:49:49", "throughput": 1485.36, "total_tokens": 33926848} {"current_steps": 160765, "total_steps": 181800, "loss": 0.0046, "lr": 2.011643983036404e-06, "epoch": 17.685918591859185, "percentage": 88.43, "elapsed_time": "6:20:41", "remaining_time": "0:49:48", "throughput": 1485.36, "total_tokens": 33927936} {"current_steps": 160770, "total_steps": 181800, "loss": 0.0013, "lr": 2.0107008386001965e-06, "epoch": 17.686468646864686, "percentage": 88.43, "elapsed_time": "6:20:42", "remaining_time": "0:49:47", "throughput": 1485.36, "total_tokens": 33928992} {"current_steps": 160775, "total_steps": 181800, "loss": 0.002, "lr": 2.0097579060453343e-06, "epoch": 17.687018701870187, "percentage": 88.44, "elapsed_time": "6:20:42", "remaining_time": "0:49:47", "throughput": 1485.36, "total_tokens": 33930112} {"current_steps": 160780, "total_steps": 181800, "loss": 0.0024, "lr": 2.008815185380497e-06, "epoch": 17.687568756875688, "percentage": 88.44, "elapsed_time": "6:20:43", "remaining_time": "0:49:46", "throughput": 1485.37, "total_tokens": 33931168} {"current_steps": 160785, "total_steps": 181800, "loss": 0.012, "lr": 2.0078726766143833e-06, "epoch": 17.68811881188119, "percentage": 88.44, "elapsed_time": "6:20:44", "remaining_time": "0:49:45", "throughput": 1485.37, "total_tokens": 33932288} {"current_steps": 160790, "total_steps": 181800, "loss": 0.0006, "lr": 2.006930379755673e-06, "epoch": 17.68866886688669, "percentage": 88.44, "elapsed_time": "6:20:45", "remaining_time": "0:49:45", "throughput": 1485.37, "total_tokens": 33933408} {"current_steps": 160795, "total_steps": 181800, "loss": 0.0007, "lr": 2.005988294813049e-06, "epoch": 17.689218921892188, "percentage": 88.45, "elapsed_time": "6:20:45", "remaining_time": "0:49:44", "throughput": 1485.38, "total_tokens": 33934464} {"current_steps": 160800, "total_steps": 181800, "loss": 0.0013, "lr": 2.005046421795198e-06, "epoch": 17.68976897689769, "percentage": 88.45, "elapsed_time": "6:20:46", "remaining_time": "0:49:43", "throughput": 1485.38, "total_tokens": 33935488} {"current_steps": 160805, "total_steps": 181800, "loss": 0.0032, "lr": 2.0041047607108037e-06, "epoch": 17.69031903190319, "percentage": 88.45, "elapsed_time": "6:20:47", "remaining_time": "0:49:42", "throughput": 1485.38, "total_tokens": 33936576} {"current_steps": 160810, "total_steps": 181800, "loss": 0.0043, "lr": 2.003163311568537e-06, "epoch": 17.69086908690869, "percentage": 88.45, "elapsed_time": "6:20:47", "remaining_time": "0:49:42", "throughput": 1485.38, "total_tokens": 33937632} {"current_steps": 160815, "total_steps": 181800, "loss": 0.0839, "lr": 2.0022220743770833e-06, "epoch": 17.691419141914192, "percentage": 88.46, "elapsed_time": "6:20:48", "remaining_time": "0:49:41", "throughput": 1485.38, "total_tokens": 33938656} {"current_steps": 160820, "total_steps": 181800, "loss": 0.0285, "lr": 2.0012810491451094e-06, "epoch": 17.691969196919693, "percentage": 88.46, "elapsed_time": "6:20:49", "remaining_time": "0:49:40", "throughput": 1485.38, "total_tokens": 33939680} {"current_steps": 160825, "total_steps": 181800, "loss": 0.0013, "lr": 2.000340235881293e-06, "epoch": 17.69251925192519, "percentage": 88.46, "elapsed_time": "6:20:49", "remaining_time": "0:49:40", "throughput": 1485.38, "total_tokens": 33940800} {"current_steps": 160830, "total_steps": 181800, "loss": 0.0668, "lr": 1.9993996345943067e-06, "epoch": 17.693069306930692, "percentage": 88.47, "elapsed_time": "6:20:50", "remaining_time": "0:49:39", "throughput": 1485.39, "total_tokens": 33941888} {"current_steps": 160835, "total_steps": 181800, "loss": 0.0428, "lr": 1.9984592452928137e-06, "epoch": 17.693619361936193, "percentage": 88.47, "elapsed_time": "6:20:51", "remaining_time": "0:49:38", "throughput": 1485.39, "total_tokens": 33942944} {"current_steps": 160840, "total_steps": 181800, "loss": 0.0087, "lr": 1.997519067985487e-06, "epoch": 17.694169416941694, "percentage": 88.47, "elapsed_time": "6:20:51", "remaining_time": "0:49:37", "throughput": 1485.39, "total_tokens": 33944000} {"current_steps": 160845, "total_steps": 181800, "loss": 0.1397, "lr": 1.9965791026809873e-06, "epoch": 17.694719471947195, "percentage": 88.47, "elapsed_time": "6:20:52", "remaining_time": "0:49:37", "throughput": 1485.39, "total_tokens": 33945120} {"current_steps": 160850, "total_steps": 181800, "loss": 0.0063, "lr": 1.995639349387984e-06, "epoch": 17.695269526952696, "percentage": 88.48, "elapsed_time": "6:20:53", "remaining_time": "0:49:36", "throughput": 1485.4, "total_tokens": 33946176} {"current_steps": 160855, "total_steps": 181800, "loss": 0.0032, "lr": 1.9946998081151303e-06, "epoch": 17.695819581958197, "percentage": 88.48, "elapsed_time": "6:20:53", "remaining_time": "0:49:35", "throughput": 1485.4, "total_tokens": 33947296} {"current_steps": 160860, "total_steps": 181800, "loss": 0.0051, "lr": 1.9937604788710902e-06, "epoch": 17.696369636963695, "percentage": 88.48, "elapsed_time": "6:20:54", "remaining_time": "0:49:35", "throughput": 1485.4, "total_tokens": 33948384} {"current_steps": 160865, "total_steps": 181800, "loss": 0.0132, "lr": 1.9928213616645237e-06, "epoch": 17.696919691969196, "percentage": 88.48, "elapsed_time": "6:20:55", "remaining_time": "0:49:34", "throughput": 1485.4, "total_tokens": 33949440} {"current_steps": 160870, "total_steps": 181800, "loss": 0.0484, "lr": 1.9918824565040768e-06, "epoch": 17.697469746974697, "percentage": 88.49, "elapsed_time": "6:20:56", "remaining_time": "0:49:33", "throughput": 1485.4, "total_tokens": 33950432} {"current_steps": 160875, "total_steps": 181800, "loss": 0.0103, "lr": 1.9909437633984146e-06, "epoch": 17.698019801980198, "percentage": 88.49, "elapsed_time": "6:20:56", "remaining_time": "0:49:32", "throughput": 1485.4, "total_tokens": 33951456} {"current_steps": 160880, "total_steps": 181800, "loss": 0.0124, "lr": 1.990005282356183e-06, "epoch": 17.6985698569857, "percentage": 88.49, "elapsed_time": "6:20:57", "remaining_time": "0:49:32", "throughput": 1485.4, "total_tokens": 33952480} {"current_steps": 160885, "total_steps": 181800, "loss": 0.0784, "lr": 1.989067013386023e-06, "epoch": 17.6991199119912, "percentage": 88.5, "elapsed_time": "6:20:58", "remaining_time": "0:49:31", "throughput": 1485.4, "total_tokens": 33953568} {"current_steps": 160890, "total_steps": 181800, "loss": 0.0068, "lr": 1.988128956496599e-06, "epoch": 17.6996699669967, "percentage": 88.5, "elapsed_time": "6:20:58", "remaining_time": "0:49:30", "throughput": 1485.41, "total_tokens": 33954624} {"current_steps": 160895, "total_steps": 181800, "loss": 0.0067, "lr": 1.987191111696546e-06, "epoch": 17.7002200220022, "percentage": 88.5, "elapsed_time": "6:20:59", "remaining_time": "0:49:30", "throughput": 1485.41, "total_tokens": 33955712} {"current_steps": 160900, "total_steps": 181800, "loss": 0.0068, "lr": 1.98625347899451e-06, "epoch": 17.7007700770077, "percentage": 88.5, "elapsed_time": "6:21:00", "remaining_time": "0:49:29", "throughput": 1485.41, "total_tokens": 33956800} {"current_steps": 160905, "total_steps": 181800, "loss": 0.0493, "lr": 1.9853160583991366e-06, "epoch": 17.7013201320132, "percentage": 88.51, "elapsed_time": "6:21:00", "remaining_time": "0:49:28", "throughput": 1485.41, "total_tokens": 33957792} {"current_steps": 160910, "total_steps": 181800, "loss": 0.0012, "lr": 1.984378849919055e-06, "epoch": 17.701870187018702, "percentage": 88.51, "elapsed_time": "6:21:01", "remaining_time": "0:49:27", "throughput": 1485.41, "total_tokens": 33958848} {"current_steps": 160915, "total_steps": 181800, "loss": 0.0038, "lr": 1.983441853562909e-06, "epoch": 17.702420242024203, "percentage": 88.51, "elapsed_time": "6:21:02", "remaining_time": "0:49:27", "throughput": 1485.41, "total_tokens": 33959872} {"current_steps": 160920, "total_steps": 181800, "loss": 0.0011, "lr": 1.982505069339338e-06, "epoch": 17.702970297029704, "percentage": 88.51, "elapsed_time": "6:21:02", "remaining_time": "0:49:26", "throughput": 1485.41, "total_tokens": 33960928} {"current_steps": 160925, "total_steps": 181800, "loss": 0.0036, "lr": 1.9815684972569747e-06, "epoch": 17.703520352035202, "percentage": 88.52, "elapsed_time": "6:21:03", "remaining_time": "0:49:25", "throughput": 1485.41, "total_tokens": 33961984} {"current_steps": 160930, "total_steps": 181800, "loss": 0.0592, "lr": 1.9806321373244506e-06, "epoch": 17.704070407040703, "percentage": 88.52, "elapsed_time": "6:21:04", "remaining_time": "0:49:25", "throughput": 1485.41, "total_tokens": 33963008} {"current_steps": 160935, "total_steps": 181800, "loss": 0.0356, "lr": 1.979695989550387e-06, "epoch": 17.704620462046204, "percentage": 88.52, "elapsed_time": "6:21:05", "remaining_time": "0:49:24", "throughput": 1485.42, "total_tokens": 33964096} {"current_steps": 160940, "total_steps": 181800, "loss": 0.0071, "lr": 1.9787600539434264e-06, "epoch": 17.705170517051705, "percentage": 88.53, "elapsed_time": "6:21:05", "remaining_time": "0:49:23", "throughput": 1485.42, "total_tokens": 33965120} {"current_steps": 160945, "total_steps": 181800, "loss": 0.0059, "lr": 1.977824330512179e-06, "epoch": 17.705720572057206, "percentage": 88.53, "elapsed_time": "6:21:06", "remaining_time": "0:49:22", "throughput": 1485.42, "total_tokens": 33966144} {"current_steps": 160950, "total_steps": 181800, "loss": 0.0451, "lr": 1.976888819265285e-06, "epoch": 17.706270627062707, "percentage": 88.53, "elapsed_time": "6:21:07", "remaining_time": "0:49:22", "throughput": 1485.42, "total_tokens": 33967264} {"current_steps": 160955, "total_steps": 181800, "loss": 0.0441, "lr": 1.97595352021136e-06, "epoch": 17.706820682068205, "percentage": 88.53, "elapsed_time": "6:21:07", "remaining_time": "0:49:21", "throughput": 1485.42, "total_tokens": 33968352} {"current_steps": 160960, "total_steps": 181800, "loss": 0.0044, "lr": 1.9750184333590187e-06, "epoch": 17.707370737073706, "percentage": 88.54, "elapsed_time": "6:21:08", "remaining_time": "0:49:20", "throughput": 1485.43, "total_tokens": 33969504} {"current_steps": 160965, "total_steps": 181800, "loss": 0.0368, "lr": 1.974083558716891e-06, "epoch": 17.707920792079207, "percentage": 88.54, "elapsed_time": "6:21:09", "remaining_time": "0:49:20", "throughput": 1485.43, "total_tokens": 33970560} {"current_steps": 160970, "total_steps": 181800, "loss": 0.006, "lr": 1.973148896293578e-06, "epoch": 17.70847084708471, "percentage": 88.54, "elapsed_time": "6:21:09", "remaining_time": "0:49:19", "throughput": 1485.43, "total_tokens": 33971616} {"current_steps": 160975, "total_steps": 181800, "loss": 0.067, "lr": 1.972214446097703e-06, "epoch": 17.70902090209021, "percentage": 88.55, "elapsed_time": "6:21:10", "remaining_time": "0:49:18", "throughput": 1485.43, "total_tokens": 33972640} {"current_steps": 160980, "total_steps": 181800, "loss": 0.0321, "lr": 1.971280208137885e-06, "epoch": 17.70957095709571, "percentage": 88.55, "elapsed_time": "6:21:11", "remaining_time": "0:49:18", "throughput": 1485.43, "total_tokens": 33973728} {"current_steps": 160985, "total_steps": 181800, "loss": 0.0004, "lr": 1.9703461824227194e-06, "epoch": 17.71012101210121, "percentage": 88.55, "elapsed_time": "6:21:11", "remaining_time": "0:49:17", "throughput": 1485.43, "total_tokens": 33974720} {"current_steps": 160990, "total_steps": 181800, "loss": 0.063, "lr": 1.969412368960827e-06, "epoch": 17.71067106710671, "percentage": 88.55, "elapsed_time": "6:21:12", "remaining_time": "0:49:16", "throughput": 1485.44, "total_tokens": 33975808} {"current_steps": 160995, "total_steps": 181800, "loss": 0.0544, "lr": 1.968478767760812e-06, "epoch": 17.71122112211221, "percentage": 88.56, "elapsed_time": "6:21:13", "remaining_time": "0:49:15", "throughput": 1485.44, "total_tokens": 33976864} {"current_steps": 161000, "total_steps": 181800, "loss": 0.0586, "lr": 1.9675453788312704e-06, "epoch": 17.71177117711771, "percentage": 88.56, "elapsed_time": "6:21:14", "remaining_time": "0:49:15", "throughput": 1485.44, "total_tokens": 33977888} {"current_steps": 161005, "total_steps": 181800, "loss": 0.0034, "lr": 1.966612202180812e-06, "epoch": 17.712321232123212, "percentage": 88.56, "elapsed_time": "6:21:14", "remaining_time": "0:49:14", "throughput": 1485.43, "total_tokens": 33978880} {"current_steps": 161010, "total_steps": 181800, "loss": 0.0026, "lr": 1.9656792378180357e-06, "epoch": 17.712871287128714, "percentage": 88.56, "elapsed_time": "6:21:15", "remaining_time": "0:49:13", "throughput": 1485.44, "total_tokens": 33979936} {"current_steps": 161015, "total_steps": 181800, "loss": 0.0884, "lr": 1.964746485751545e-06, "epoch": 17.713421342134215, "percentage": 88.57, "elapsed_time": "6:21:16", "remaining_time": "0:49:13", "throughput": 1485.44, "total_tokens": 33980960} {"current_steps": 161020, "total_steps": 181800, "loss": 0.1793, "lr": 1.9638139459899315e-06, "epoch": 17.713971397139716, "percentage": 88.57, "elapsed_time": "6:21:16", "remaining_time": "0:49:12", "throughput": 1485.43, "total_tokens": 33981920} {"current_steps": 161025, "total_steps": 181800, "loss": 0.0066, "lr": 1.9628816185417897e-06, "epoch": 17.714521452145213, "percentage": 88.57, "elapsed_time": "6:21:17", "remaining_time": "0:49:11", "throughput": 1485.43, "total_tokens": 33982944} {"current_steps": 161030, "total_steps": 181800, "loss": 0.0612, "lr": 1.961949503415711e-06, "epoch": 17.715071507150714, "percentage": 88.58, "elapsed_time": "6:21:18", "remaining_time": "0:49:10", "throughput": 1485.44, "total_tokens": 33984032} {"current_steps": 161035, "total_steps": 181800, "loss": 0.0717, "lr": 1.9610176006202905e-06, "epoch": 17.715621562156215, "percentage": 88.58, "elapsed_time": "6:21:18", "remaining_time": "0:49:10", "throughput": 1485.44, "total_tokens": 33985120} {"current_steps": 161040, "total_steps": 181800, "loss": 0.001, "lr": 1.9600859101641194e-06, "epoch": 17.716171617161717, "percentage": 88.58, "elapsed_time": "6:21:19", "remaining_time": "0:49:09", "throughput": 1485.44, "total_tokens": 33986240} {"current_steps": 161045, "total_steps": 181800, "loss": 0.0236, "lr": 1.959154432055782e-06, "epoch": 17.716721672167218, "percentage": 88.58, "elapsed_time": "6:21:20", "remaining_time": "0:49:08", "throughput": 1485.44, "total_tokens": 33987264} {"current_steps": 161050, "total_steps": 181800, "loss": 0.0298, "lr": 1.9582231663038546e-06, "epoch": 17.71727172717272, "percentage": 88.59, "elapsed_time": "6:21:20", "remaining_time": "0:49:08", "throughput": 1485.45, "total_tokens": 33988320} {"current_steps": 161055, "total_steps": 181800, "loss": 0.0067, "lr": 1.9572921129169365e-06, "epoch": 17.717821782178216, "percentage": 88.59, "elapsed_time": "6:21:21", "remaining_time": "0:49:07", "throughput": 1485.45, "total_tokens": 33989376} {"current_steps": 161060, "total_steps": 181800, "loss": 0.0016, "lr": 1.956361271903592e-06, "epoch": 17.718371837183717, "percentage": 88.59, "elapsed_time": "6:21:22", "remaining_time": "0:49:06", "throughput": 1485.45, "total_tokens": 33990400} {"current_steps": 161065, "total_steps": 181800, "loss": 0.1076, "lr": 1.9554306432724103e-06, "epoch": 17.71892189218922, "percentage": 88.59, "elapsed_time": "6:21:22", "remaining_time": "0:49:05", "throughput": 1485.45, "total_tokens": 33991424} {"current_steps": 161070, "total_steps": 181800, "loss": 0.0038, "lr": 1.954500227031969e-06, "epoch": 17.71947194719472, "percentage": 88.6, "elapsed_time": "6:21:23", "remaining_time": "0:49:05", "throughput": 1485.45, "total_tokens": 33992480} {"current_steps": 161075, "total_steps": 181800, "loss": 0.0099, "lr": 1.95357002319084e-06, "epoch": 17.72002200220022, "percentage": 88.6, "elapsed_time": "6:21:24", "remaining_time": "0:49:04", "throughput": 1485.45, "total_tokens": 33993568} {"current_steps": 161080, "total_steps": 181800, "loss": 0.0216, "lr": 1.952640031757599e-06, "epoch": 17.72057205720572, "percentage": 88.6, "elapsed_time": "6:21:25", "remaining_time": "0:49:03", "throughput": 1485.45, "total_tokens": 33994592} {"current_steps": 161085, "total_steps": 181800, "loss": 0.0044, "lr": 1.9517102527408097e-06, "epoch": 17.721122112211223, "percentage": 88.61, "elapsed_time": "6:21:25", "remaining_time": "0:49:03", "throughput": 1485.45, "total_tokens": 33995616} {"current_steps": 161090, "total_steps": 181800, "loss": 0.0048, "lr": 1.9507806861490507e-06, "epoch": 17.72167216721672, "percentage": 88.61, "elapsed_time": "6:21:26", "remaining_time": "0:49:02", "throughput": 1485.45, "total_tokens": 33996704} {"current_steps": 161095, "total_steps": 181800, "loss": 0.08, "lr": 1.94985133199089e-06, "epoch": 17.72222222222222, "percentage": 88.61, "elapsed_time": "6:21:27", "remaining_time": "0:49:01", "throughput": 1485.46, "total_tokens": 33997824} {"current_steps": 161100, "total_steps": 181800, "loss": 0.0186, "lr": 1.948922190274882e-06, "epoch": 17.722772277227723, "percentage": 88.61, "elapsed_time": "6:21:27", "remaining_time": "0:49:00", "throughput": 1485.46, "total_tokens": 33998912} {"current_steps": 161105, "total_steps": 181800, "loss": 0.0686, "lr": 1.9479932610096035e-06, "epoch": 17.723322332233224, "percentage": 88.62, "elapsed_time": "6:21:28", "remaining_time": "0:49:00", "throughput": 1485.46, "total_tokens": 33999904} {"current_steps": 161110, "total_steps": 181800, "loss": 0.0087, "lr": 1.9470645442036056e-06, "epoch": 17.723872387238725, "percentage": 88.62, "elapsed_time": "6:21:29", "remaining_time": "0:48:59", "throughput": 1485.46, "total_tokens": 34000960} {"current_steps": 161115, "total_steps": 181800, "loss": 0.0019, "lr": 1.9461360398654566e-06, "epoch": 17.724422442244226, "percentage": 88.62, "elapsed_time": "6:21:29", "remaining_time": "0:48:58", "throughput": 1485.46, "total_tokens": 34002016} {"current_steps": 161120, "total_steps": 181800, "loss": 0.1409, "lr": 1.945207748003702e-06, "epoch": 17.724972497249723, "percentage": 88.62, "elapsed_time": "6:21:30", "remaining_time": "0:48:58", "throughput": 1485.46, "total_tokens": 34003040} {"current_steps": 161125, "total_steps": 181800, "loss": 0.0813, "lr": 1.9442796686269083e-06, "epoch": 17.725522552255224, "percentage": 88.63, "elapsed_time": "6:21:31", "remaining_time": "0:48:57", "throughput": 1485.46, "total_tokens": 34004064} {"current_steps": 161130, "total_steps": 181800, "loss": 0.039, "lr": 1.9433518017436287e-06, "epoch": 17.726072607260726, "percentage": 88.63, "elapsed_time": "6:21:31", "remaining_time": "0:48:56", "throughput": 1485.46, "total_tokens": 34005088} {"current_steps": 161135, "total_steps": 181800, "loss": 0.0887, "lr": 1.9424241473624067e-06, "epoch": 17.726622662266227, "percentage": 88.63, "elapsed_time": "6:21:32", "remaining_time": "0:48:55", "throughput": 1485.46, "total_tokens": 34006144} {"current_steps": 161140, "total_steps": 181800, "loss": 0.0033, "lr": 1.941496705491802e-06, "epoch": 17.727172717271728, "percentage": 88.64, "elapsed_time": "6:21:33", "remaining_time": "0:48:55", "throughput": 1485.46, "total_tokens": 34007168} {"current_steps": 161145, "total_steps": 181800, "loss": 0.0037, "lr": 1.9405694761403554e-06, "epoch": 17.72772277227723, "percentage": 88.64, "elapsed_time": "6:21:34", "remaining_time": "0:48:54", "throughput": 1485.46, "total_tokens": 34008256} {"current_steps": 161150, "total_steps": 181800, "loss": 0.0063, "lr": 1.9396424593166124e-06, "epoch": 17.72827282728273, "percentage": 88.64, "elapsed_time": "6:21:34", "remaining_time": "0:48:53", "throughput": 1485.46, "total_tokens": 34009248} {"current_steps": 161155, "total_steps": 181800, "loss": 0.1474, "lr": 1.9387156550291247e-06, "epoch": 17.728822882288227, "percentage": 88.64, "elapsed_time": "6:21:35", "remaining_time": "0:48:53", "throughput": 1485.46, "total_tokens": 34010208} {"current_steps": 161160, "total_steps": 181800, "loss": 0.0047, "lr": 1.9377890632864243e-06, "epoch": 17.72937293729373, "percentage": 88.65, "elapsed_time": "6:21:36", "remaining_time": "0:48:52", "throughput": 1485.46, "total_tokens": 34011200} {"current_steps": 161165, "total_steps": 181800, "loss": 0.0034, "lr": 1.93686268409706e-06, "epoch": 17.72992299229923, "percentage": 88.65, "elapsed_time": "6:21:36", "remaining_time": "0:48:51", "throughput": 1485.46, "total_tokens": 34012288} {"current_steps": 161170, "total_steps": 181800, "loss": 0.0027, "lr": 1.9359365174695665e-06, "epoch": 17.73047304730473, "percentage": 88.65, "elapsed_time": "6:21:37", "remaining_time": "0:48:50", "throughput": 1485.46, "total_tokens": 34013312} {"current_steps": 161175, "total_steps": 181800, "loss": 0.0011, "lr": 1.9350105634124733e-06, "epoch": 17.731023102310232, "percentage": 88.66, "elapsed_time": "6:21:38", "remaining_time": "0:48:50", "throughput": 1485.46, "total_tokens": 34014304} {"current_steps": 161180, "total_steps": 181800, "loss": 0.0049, "lr": 1.9340848219343232e-06, "epoch": 17.731573157315733, "percentage": 88.66, "elapsed_time": "6:21:38", "remaining_time": "0:48:49", "throughput": 1485.46, "total_tokens": 34015392} {"current_steps": 161185, "total_steps": 181800, "loss": 0.0242, "lr": 1.933159293043646e-06, "epoch": 17.73212321232123, "percentage": 88.66, "elapsed_time": "6:21:39", "remaining_time": "0:48:48", "throughput": 1485.46, "total_tokens": 34016448} {"current_steps": 161190, "total_steps": 181800, "loss": 0.0333, "lr": 1.9322339767489676e-06, "epoch": 17.73267326732673, "percentage": 88.66, "elapsed_time": "6:21:40", "remaining_time": "0:48:48", "throughput": 1485.46, "total_tokens": 34017472} {"current_steps": 161195, "total_steps": 181800, "loss": 0.0325, "lr": 1.9313088730588234e-06, "epoch": 17.733223322332233, "percentage": 88.67, "elapsed_time": "6:21:40", "remaining_time": "0:48:47", "throughput": 1485.47, "total_tokens": 34018528} {"current_steps": 161200, "total_steps": 181800, "loss": 0.0017, "lr": 1.9303839819817345e-06, "epoch": 17.733773377337734, "percentage": 88.67, "elapsed_time": "6:21:41", "remaining_time": "0:48:46", "throughput": 1485.47, "total_tokens": 34019552} {"current_steps": 161205, "total_steps": 181800, "loss": 0.0098, "lr": 1.9294593035262236e-06, "epoch": 17.734323432343235, "percentage": 88.67, "elapsed_time": "6:21:42", "remaining_time": "0:48:45", "throughput": 1485.46, "total_tokens": 34020576} {"current_steps": 161210, "total_steps": 181800, "loss": 0.1461, "lr": 1.928534837700821e-06, "epoch": 17.734873487348736, "percentage": 88.67, "elapsed_time": "6:21:43", "remaining_time": "0:48:45", "throughput": 1485.47, "total_tokens": 34021632} {"current_steps": 161215, "total_steps": 181800, "loss": 0.0089, "lr": 1.927610584514036e-06, "epoch": 17.735423542354237, "percentage": 88.68, "elapsed_time": "6:21:43", "remaining_time": "0:48:44", "throughput": 1485.47, "total_tokens": 34022688} {"current_steps": 161220, "total_steps": 181800, "loss": 0.0016, "lr": 1.9266865439744014e-06, "epoch": 17.735973597359735, "percentage": 88.68, "elapsed_time": "6:21:44", "remaining_time": "0:48:43", "throughput": 1485.47, "total_tokens": 34023808} {"current_steps": 161225, "total_steps": 181800, "loss": 0.0817, "lr": 1.925762716090418e-06, "epoch": 17.736523652365236, "percentage": 88.68, "elapsed_time": "6:21:45", "remaining_time": "0:48:43", "throughput": 1485.47, "total_tokens": 34024800} {"current_steps": 161230, "total_steps": 181800, "loss": 0.0082, "lr": 1.9248391008706124e-06, "epoch": 17.737073707370737, "percentage": 88.69, "elapsed_time": "6:21:45", "remaining_time": "0:48:42", "throughput": 1485.47, "total_tokens": 34025824} {"current_steps": 161235, "total_steps": 181800, "loss": 0.0022, "lr": 1.923915698323489e-06, "epoch": 17.737623762376238, "percentage": 88.69, "elapsed_time": "6:21:46", "remaining_time": "0:48:41", "throughput": 1485.47, "total_tokens": 34026880} {"current_steps": 161240, "total_steps": 181800, "loss": 0.0018, "lr": 1.922992508457561e-06, "epoch": 17.73817381738174, "percentage": 88.69, "elapsed_time": "6:21:47", "remaining_time": "0:48:40", "throughput": 1485.47, "total_tokens": 34027968} {"current_steps": 161245, "total_steps": 181800, "loss": 0.0499, "lr": 1.9220695312813398e-06, "epoch": 17.73872387238724, "percentage": 88.69, "elapsed_time": "6:21:47", "remaining_time": "0:48:40", "throughput": 1485.48, "total_tokens": 34029056} {"current_steps": 161250, "total_steps": 181800, "loss": 0.0024, "lr": 1.921146766803328e-06, "epoch": 17.739273927392738, "percentage": 88.7, "elapsed_time": "6:21:48", "remaining_time": "0:48:39", "throughput": 1485.47, "total_tokens": 34030048} {"current_steps": 161255, "total_steps": 181800, "loss": 0.0146, "lr": 1.920224215032035e-06, "epoch": 17.73982398239824, "percentage": 88.7, "elapsed_time": "6:21:49", "remaining_time": "0:48:38", "throughput": 1485.47, "total_tokens": 34031072} {"current_steps": 161260, "total_steps": 181800, "loss": 0.0107, "lr": 1.9193018759759595e-06, "epoch": 17.74037403740374, "percentage": 88.7, "elapsed_time": "6:21:49", "remaining_time": "0:48:38", "throughput": 1485.47, "total_tokens": 34032096} {"current_steps": 161265, "total_steps": 181800, "loss": 0.073, "lr": 1.918379749643601e-06, "epoch": 17.74092409240924, "percentage": 88.7, "elapsed_time": "6:21:50", "remaining_time": "0:48:37", "throughput": 1485.48, "total_tokens": 34033184} {"current_steps": 161270, "total_steps": 181800, "loss": 0.0017, "lr": 1.9174578360434653e-06, "epoch": 17.741474147414742, "percentage": 88.71, "elapsed_time": "6:21:51", "remaining_time": "0:48:36", "throughput": 1485.48, "total_tokens": 34034240} {"current_steps": 161275, "total_steps": 181800, "loss": 0.0549, "lr": 1.9165361351840383e-06, "epoch": 17.742024202420243, "percentage": 88.71, "elapsed_time": "6:21:51", "remaining_time": "0:48:35", "throughput": 1485.48, "total_tokens": 34035296} {"current_steps": 161280, "total_steps": 181800, "loss": 0.0148, "lr": 1.9156146470738297e-06, "epoch": 17.742574257425744, "percentage": 88.71, "elapsed_time": "6:21:52", "remaining_time": "0:48:35", "throughput": 1485.48, "total_tokens": 34036352} {"current_steps": 161285, "total_steps": 181800, "loss": 0.074, "lr": 1.9146933717213212e-06, "epoch": 17.74312431243124, "percentage": 88.72, "elapsed_time": "6:21:53", "remaining_time": "0:48:34", "throughput": 1485.48, "total_tokens": 34037344} {"current_steps": 161290, "total_steps": 181800, "loss": 0.0017, "lr": 1.9137723091350006e-06, "epoch": 17.743674367436743, "percentage": 88.72, "elapsed_time": "6:21:54", "remaining_time": "0:48:33", "throughput": 1485.48, "total_tokens": 34038400} {"current_steps": 161295, "total_steps": 181800, "loss": 0.0411, "lr": 1.9128514593233672e-06, "epoch": 17.744224422442244, "percentage": 88.72, "elapsed_time": "6:21:54", "remaining_time": "0:48:33", "throughput": 1485.49, "total_tokens": 34039520} {"current_steps": 161300, "total_steps": 181800, "loss": 0.0019, "lr": 1.9119308222948997e-06, "epoch": 17.744774477447745, "percentage": 88.72, "elapsed_time": "6:21:55", "remaining_time": "0:48:32", "throughput": 1485.49, "total_tokens": 34040544} {"current_steps": 161305, "total_steps": 181800, "loss": 0.0804, "lr": 1.911010398058094e-06, "epoch": 17.745324532453246, "percentage": 88.73, "elapsed_time": "6:21:56", "remaining_time": "0:48:31", "throughput": 1485.48, "total_tokens": 34041568} {"current_steps": 161310, "total_steps": 181800, "loss": 0.0119, "lr": 1.9100901866214244e-06, "epoch": 17.745874587458747, "percentage": 88.73, "elapsed_time": "6:21:56", "remaining_time": "0:48:30", "throughput": 1485.49, "total_tokens": 34042688} {"current_steps": 161315, "total_steps": 181800, "loss": 0.0072, "lr": 1.90917018799337e-06, "epoch": 17.746424642464248, "percentage": 88.73, "elapsed_time": "6:21:57", "remaining_time": "0:48:30", "throughput": 1485.49, "total_tokens": 34043776} {"current_steps": 161320, "total_steps": 181800, "loss": 0.0954, "lr": 1.9082504021824156e-06, "epoch": 17.746974697469746, "percentage": 88.73, "elapsed_time": "6:21:58", "remaining_time": "0:48:29", "throughput": 1485.49, "total_tokens": 34044832} {"current_steps": 161325, "total_steps": 181800, "loss": 0.0045, "lr": 1.907330829197035e-06, "epoch": 17.747524752475247, "percentage": 88.74, "elapsed_time": "6:21:58", "remaining_time": "0:48:28", "throughput": 1485.5, "total_tokens": 34045920} {"current_steps": 161330, "total_steps": 181800, "loss": 0.0083, "lr": 1.9064114690457102e-06, "epoch": 17.748074807480748, "percentage": 88.74, "elapsed_time": "6:21:59", "remaining_time": "0:48:28", "throughput": 1485.5, "total_tokens": 34047072} {"current_steps": 161335, "total_steps": 181800, "loss": 0.0131, "lr": 1.9054923217369098e-06, "epoch": 17.74862486248625, "percentage": 88.74, "elapsed_time": "6:22:00", "remaining_time": "0:48:27", "throughput": 1485.51, "total_tokens": 34048192} {"current_steps": 161340, "total_steps": 181800, "loss": 0.0672, "lr": 1.904573387279099e-06, "epoch": 17.74917491749175, "percentage": 88.75, "elapsed_time": "6:22:00", "remaining_time": "0:48:26", "throughput": 1485.51, "total_tokens": 34049248} {"current_steps": 161345, "total_steps": 181800, "loss": 0.0119, "lr": 1.9036546656807596e-06, "epoch": 17.74972497249725, "percentage": 88.75, "elapsed_time": "6:22:01", "remaining_time": "0:48:25", "throughput": 1485.51, "total_tokens": 34050304} {"current_steps": 161350, "total_steps": 181800, "loss": 0.0008, "lr": 1.9027361569503465e-06, "epoch": 17.75027502750275, "percentage": 88.75, "elapsed_time": "6:22:02", "remaining_time": "0:48:25", "throughput": 1485.51, "total_tokens": 34051392} {"current_steps": 161355, "total_steps": 181800, "loss": 0.0037, "lr": 1.9018178610963306e-06, "epoch": 17.75082508250825, "percentage": 88.75, "elapsed_time": "6:22:03", "remaining_time": "0:48:24", "throughput": 1485.51, "total_tokens": 34052448} {"current_steps": 161360, "total_steps": 181800, "loss": 0.1386, "lr": 1.9008997781271825e-06, "epoch": 17.75137513751375, "percentage": 88.76, "elapsed_time": "6:22:03", "remaining_time": "0:48:23", "throughput": 1485.51, "total_tokens": 34053504} {"current_steps": 161365, "total_steps": 181800, "loss": 0.0015, "lr": 1.8999819080513514e-06, "epoch": 17.751925192519252, "percentage": 88.76, "elapsed_time": "6:22:04", "remaining_time": "0:48:23", "throughput": 1485.51, "total_tokens": 34054560} {"current_steps": 161370, "total_steps": 181800, "loss": 0.0261, "lr": 1.8990642508773053e-06, "epoch": 17.752475247524753, "percentage": 88.76, "elapsed_time": "6:22:05", "remaining_time": "0:48:22", "throughput": 1485.51, "total_tokens": 34055584} {"current_steps": 161375, "total_steps": 181800, "loss": 0.0015, "lr": 1.898146806613496e-06, "epoch": 17.753025302530254, "percentage": 88.77, "elapsed_time": "6:22:05", "remaining_time": "0:48:21", "throughput": 1485.51, "total_tokens": 34056576} {"current_steps": 161380, "total_steps": 181800, "loss": 0.0091, "lr": 1.8972295752683833e-06, "epoch": 17.753575357535752, "percentage": 88.77, "elapsed_time": "6:22:06", "remaining_time": "0:48:20", "throughput": 1485.51, "total_tokens": 34057600} {"current_steps": 161385, "total_steps": 181800, "loss": 0.0016, "lr": 1.8963125568504242e-06, "epoch": 17.754125412541253, "percentage": 88.77, "elapsed_time": "6:22:07", "remaining_time": "0:48:20", "throughput": 1485.51, "total_tokens": 34058624} {"current_steps": 161390, "total_steps": 181800, "loss": 0.0746, "lr": 1.8953957513680621e-06, "epoch": 17.754675467546754, "percentage": 88.77, "elapsed_time": "6:22:07", "remaining_time": "0:48:19", "throughput": 1485.52, "total_tokens": 34059744} {"current_steps": 161395, "total_steps": 181800, "loss": 0.0007, "lr": 1.8944791588297512e-06, "epoch": 17.755225522552255, "percentage": 88.78, "elapsed_time": "6:22:08", "remaining_time": "0:48:18", "throughput": 1485.52, "total_tokens": 34060928} {"current_steps": 161400, "total_steps": 181800, "loss": 0.0059, "lr": 1.893562779243943e-06, "epoch": 17.755775577557756, "percentage": 88.78, "elapsed_time": "6:22:09", "remaining_time": "0:48:18", "throughput": 1485.52, "total_tokens": 34061952} {"current_steps": 161405, "total_steps": 181800, "loss": 0.0032, "lr": 1.8926466126190729e-06, "epoch": 17.756325632563257, "percentage": 88.78, "elapsed_time": "6:22:09", "remaining_time": "0:48:17", "throughput": 1485.52, "total_tokens": 34062976} {"current_steps": 161410, "total_steps": 181800, "loss": 0.0181, "lr": 1.891730658963592e-06, "epoch": 17.75687568756876, "percentage": 88.78, "elapsed_time": "6:22:10", "remaining_time": "0:48:16", "throughput": 1485.53, "total_tokens": 34064032} {"current_steps": 161415, "total_steps": 181800, "loss": 0.0847, "lr": 1.8908149182859408e-06, "epoch": 17.757425742574256, "percentage": 88.79, "elapsed_time": "6:22:11", "remaining_time": "0:48:15", "throughput": 1485.53, "total_tokens": 34065088} {"current_steps": 161420, "total_steps": 181800, "loss": 0.0058, "lr": 1.8898993905945627e-06, "epoch": 17.757975797579757, "percentage": 88.79, "elapsed_time": "6:22:12", "remaining_time": "0:48:15", "throughput": 1485.53, "total_tokens": 34066144} {"current_steps": 161425, "total_steps": 181800, "loss": 0.001, "lr": 1.8889840758978928e-06, "epoch": 17.758525852585258, "percentage": 88.79, "elapsed_time": "6:22:12", "remaining_time": "0:48:14", "throughput": 1485.53, "total_tokens": 34067104} {"current_steps": 161430, "total_steps": 181800, "loss": 0.0023, "lr": 1.8880689742043656e-06, "epoch": 17.75907590759076, "percentage": 88.8, "elapsed_time": "6:22:13", "remaining_time": "0:48:13", "throughput": 1485.53, "total_tokens": 34068160} {"current_steps": 161435, "total_steps": 181800, "loss": 0.0093, "lr": 1.8871540855224134e-06, "epoch": 17.75962596259626, "percentage": 88.8, "elapsed_time": "6:22:14", "remaining_time": "0:48:13", "throughput": 1485.53, "total_tokens": 34069248} {"current_steps": 161440, "total_steps": 181800, "loss": 0.0365, "lr": 1.8862394098604713e-06, "epoch": 17.76017601760176, "percentage": 88.8, "elapsed_time": "6:22:14", "remaining_time": "0:48:12", "throughput": 1485.53, "total_tokens": 34070272} {"current_steps": 161445, "total_steps": 181800, "loss": 0.0003, "lr": 1.8853249472269768e-06, "epoch": 17.760726072607262, "percentage": 88.8, "elapsed_time": "6:22:15", "remaining_time": "0:48:11", "throughput": 1485.53, "total_tokens": 34071328} {"current_steps": 161450, "total_steps": 181800, "loss": 0.107, "lr": 1.8844106976303482e-06, "epoch": 17.76127612761276, "percentage": 88.81, "elapsed_time": "6:22:16", "remaining_time": "0:48:10", "throughput": 1485.53, "total_tokens": 34072416} {"current_steps": 161455, "total_steps": 181800, "loss": 0.0027, "lr": 1.8834966610790094e-06, "epoch": 17.76182618261826, "percentage": 88.81, "elapsed_time": "6:22:16", "remaining_time": "0:48:10", "throughput": 1485.53, "total_tokens": 34073440} {"current_steps": 161460, "total_steps": 181800, "loss": 0.0064, "lr": 1.8825828375813952e-06, "epoch": 17.762376237623762, "percentage": 88.81, "elapsed_time": "6:22:17", "remaining_time": "0:48:09", "throughput": 1485.53, "total_tokens": 34074400} {"current_steps": 161465, "total_steps": 181800, "loss": 0.1466, "lr": 1.8816692271459186e-06, "epoch": 17.762926292629263, "percentage": 88.81, "elapsed_time": "6:22:18", "remaining_time": "0:48:08", "throughput": 1485.53, "total_tokens": 34075488} {"current_steps": 161470, "total_steps": 181800, "loss": 0.0042, "lr": 1.880755829781003e-06, "epoch": 17.763476347634764, "percentage": 88.82, "elapsed_time": "6:22:18", "remaining_time": "0:48:08", "throughput": 1485.53, "total_tokens": 34076544} {"current_steps": 161475, "total_steps": 181800, "loss": 0.0223, "lr": 1.8798426454950696e-06, "epoch": 17.764026402640265, "percentage": 88.82, "elapsed_time": "6:22:19", "remaining_time": "0:48:07", "throughput": 1485.54, "total_tokens": 34077600} {"current_steps": 161480, "total_steps": 181800, "loss": 0.0879, "lr": 1.8789296742965284e-06, "epoch": 17.764576457645763, "percentage": 88.82, "elapsed_time": "6:22:20", "remaining_time": "0:48:06", "throughput": 1485.54, "total_tokens": 34078688} {"current_steps": 161485, "total_steps": 181800, "loss": 0.0025, "lr": 1.8780169161938033e-06, "epoch": 17.765126512651264, "percentage": 88.83, "elapsed_time": "6:22:20", "remaining_time": "0:48:06", "throughput": 1485.54, "total_tokens": 34079776} {"current_steps": 161490, "total_steps": 181800, "loss": 0.0474, "lr": 1.8771043711952986e-06, "epoch": 17.765676567656765, "percentage": 88.83, "elapsed_time": "6:22:21", "remaining_time": "0:48:05", "throughput": 1485.54, "total_tokens": 34080800} {"current_steps": 161495, "total_steps": 181800, "loss": 0.0436, "lr": 1.8761920393094268e-06, "epoch": 17.766226622662266, "percentage": 88.83, "elapsed_time": "6:22:22", "remaining_time": "0:48:04", "throughput": 1485.54, "total_tokens": 34081792} {"current_steps": 161500, "total_steps": 181800, "loss": 0.0103, "lr": 1.8752799205445982e-06, "epoch": 17.766776677667767, "percentage": 88.83, "elapsed_time": "6:22:23", "remaining_time": "0:48:03", "throughput": 1485.54, "total_tokens": 34082816} {"current_steps": 161505, "total_steps": 181800, "loss": 0.1009, "lr": 1.8743680149092168e-06, "epoch": 17.76732673267327, "percentage": 88.84, "elapsed_time": "6:22:23", "remaining_time": "0:48:03", "throughput": 1485.54, "total_tokens": 34083904} {"current_steps": 161510, "total_steps": 181800, "loss": 0.0008, "lr": 1.873456322411693e-06, "epoch": 17.76787678767877, "percentage": 88.84, "elapsed_time": "6:22:24", "remaining_time": "0:48:02", "throughput": 1485.54, "total_tokens": 34084960} {"current_steps": 161515, "total_steps": 181800, "loss": 0.1115, "lr": 1.8725448430604197e-06, "epoch": 17.768426842684267, "percentage": 88.84, "elapsed_time": "6:22:25", "remaining_time": "0:48:01", "throughput": 1485.55, "total_tokens": 34086048} {"current_steps": 161520, "total_steps": 181800, "loss": 0.0453, "lr": 1.8716335768638072e-06, "epoch": 17.768976897689768, "percentage": 88.84, "elapsed_time": "6:22:25", "remaining_time": "0:48:01", "throughput": 1485.55, "total_tokens": 34087104} {"current_steps": 161525, "total_steps": 181800, "loss": 0.0017, "lr": 1.8707225238302456e-06, "epoch": 17.76952695269527, "percentage": 88.85, "elapsed_time": "6:22:26", "remaining_time": "0:48:00", "throughput": 1485.55, "total_tokens": 34088160} {"current_steps": 161530, "total_steps": 181800, "loss": 0.0044, "lr": 1.8698116839681369e-06, "epoch": 17.77007700770077, "percentage": 88.85, "elapsed_time": "6:22:27", "remaining_time": "0:47:59", "throughput": 1485.55, "total_tokens": 34089248} {"current_steps": 161535, "total_steps": 181800, "loss": 0.0316, "lr": 1.8689010572858795e-06, "epoch": 17.77062706270627, "percentage": 88.85, "elapsed_time": "6:22:27", "remaining_time": "0:47:58", "throughput": 1485.55, "total_tokens": 34090304} {"current_steps": 161540, "total_steps": 181800, "loss": 0.0012, "lr": 1.867990643791856e-06, "epoch": 17.771177117711773, "percentage": 88.86, "elapsed_time": "6:22:28", "remaining_time": "0:47:58", "throughput": 1485.55, "total_tokens": 34091360} {"current_steps": 161545, "total_steps": 181800, "loss": 0.0055, "lr": 1.8670804434944677e-06, "epoch": 17.77172717271727, "percentage": 88.86, "elapsed_time": "6:22:29", "remaining_time": "0:47:57", "throughput": 1485.55, "total_tokens": 34092384} {"current_steps": 161550, "total_steps": 181800, "loss": 0.0887, "lr": 1.8661704564020999e-06, "epoch": 17.77227722772277, "percentage": 88.86, "elapsed_time": "6:22:29", "remaining_time": "0:47:56", "throughput": 1485.55, "total_tokens": 34093440} {"current_steps": 161555, "total_steps": 181800, "loss": 0.0433, "lr": 1.8652606825231289e-06, "epoch": 17.772827282728272, "percentage": 88.86, "elapsed_time": "6:22:30", "remaining_time": "0:47:56", "throughput": 1485.56, "total_tokens": 34094496} {"current_steps": 161560, "total_steps": 181800, "loss": 0.0017, "lr": 1.8643511218659564e-06, "epoch": 17.773377337733773, "percentage": 88.87, "elapsed_time": "6:22:31", "remaining_time": "0:47:55", "throughput": 1485.56, "total_tokens": 34095552} {"current_steps": 161565, "total_steps": 181800, "loss": 0.0433, "lr": 1.8634417744389593e-06, "epoch": 17.773927392739274, "percentage": 88.87, "elapsed_time": "6:22:32", "remaining_time": "0:47:54", "throughput": 1485.56, "total_tokens": 34096576} {"current_steps": 161570, "total_steps": 181800, "loss": 0.0119, "lr": 1.8625326402505138e-06, "epoch": 17.774477447744776, "percentage": 88.87, "elapsed_time": "6:22:32", "remaining_time": "0:47:53", "throughput": 1485.56, "total_tokens": 34097568} {"current_steps": 161575, "total_steps": 181800, "loss": 0.0921, "lr": 1.8616237193090053e-06, "epoch": 17.775027502750277, "percentage": 88.88, "elapsed_time": "6:22:33", "remaining_time": "0:47:53", "throughput": 1485.56, "total_tokens": 34098656} {"current_steps": 161580, "total_steps": 181800, "loss": 0.2096, "lr": 1.8607150116228044e-06, "epoch": 17.775577557755774, "percentage": 88.88, "elapsed_time": "6:22:34", "remaining_time": "0:47:52", "throughput": 1485.56, "total_tokens": 34099744} {"current_steps": 161585, "total_steps": 181800, "loss": 0.0751, "lr": 1.8598065172002909e-06, "epoch": 17.776127612761275, "percentage": 88.88, "elapsed_time": "6:22:34", "remaining_time": "0:47:51", "throughput": 1485.56, "total_tokens": 34100832} {"current_steps": 161590, "total_steps": 181800, "loss": 0.0036, "lr": 1.8588982360498386e-06, "epoch": 17.776677667766776, "percentage": 88.88, "elapsed_time": "6:22:35", "remaining_time": "0:47:51", "throughput": 1485.56, "total_tokens": 34101856} {"current_steps": 161595, "total_steps": 181800, "loss": 0.0021, "lr": 1.8579901681798157e-06, "epoch": 17.777227722772277, "percentage": 88.89, "elapsed_time": "6:22:36", "remaining_time": "0:47:50", "throughput": 1485.56, "total_tokens": 34102880} {"current_steps": 161600, "total_steps": 181800, "loss": 0.0016, "lr": 1.857082313598596e-06, "epoch": 17.77777777777778, "percentage": 88.89, "elapsed_time": "6:22:36", "remaining_time": "0:47:49", "throughput": 1485.56, "total_tokens": 34103904} {"current_steps": 161605, "total_steps": 181800, "loss": 0.0979, "lr": 1.8561746723145395e-06, "epoch": 17.77832783278328, "percentage": 88.89, "elapsed_time": "6:22:37", "remaining_time": "0:47:48", "throughput": 1485.56, "total_tokens": 34104960} {"current_steps": 161610, "total_steps": 181800, "loss": 0.002, "lr": 1.8552672443360148e-06, "epoch": 17.778877887788777, "percentage": 88.89, "elapsed_time": "6:22:38", "remaining_time": "0:47:48", "throughput": 1485.57, "total_tokens": 34106048} {"current_steps": 161615, "total_steps": 181800, "loss": 0.0077, "lr": 1.8543600296713898e-06, "epoch": 17.77942794279428, "percentage": 88.9, "elapsed_time": "6:22:38", "remaining_time": "0:47:47", "throughput": 1485.57, "total_tokens": 34107104} {"current_steps": 161620, "total_steps": 181800, "loss": 0.0034, "lr": 1.8534530283290191e-06, "epoch": 17.77997799779978, "percentage": 88.9, "elapsed_time": "6:22:39", "remaining_time": "0:47:46", "throughput": 1485.57, "total_tokens": 34108160} {"current_steps": 161625, "total_steps": 181800, "loss": 0.0462, "lr": 1.8525462403172683e-06, "epoch": 17.78052805280528, "percentage": 88.9, "elapsed_time": "6:22:40", "remaining_time": "0:47:46", "throughput": 1485.58, "total_tokens": 34109312} {"current_steps": 161630, "total_steps": 181800, "loss": 0.0387, "lr": 1.851639665644489e-06, "epoch": 17.78107810781078, "percentage": 88.91, "elapsed_time": "6:22:41", "remaining_time": "0:47:45", "throughput": 1485.58, "total_tokens": 34110464} {"current_steps": 161635, "total_steps": 181800, "loss": 0.0011, "lr": 1.8507333043190411e-06, "epoch": 17.781628162816283, "percentage": 88.91, "elapsed_time": "6:22:41", "remaining_time": "0:47:44", "throughput": 1485.58, "total_tokens": 34111552} {"current_steps": 161640, "total_steps": 181800, "loss": 0.0635, "lr": 1.8498271563492737e-06, "epoch": 17.782178217821784, "percentage": 88.91, "elapsed_time": "6:22:42", "remaining_time": "0:47:43", "throughput": 1485.58, "total_tokens": 34112544} {"current_steps": 161645, "total_steps": 181800, "loss": 0.0053, "lr": 1.848921221743541e-06, "epoch": 17.78272827282728, "percentage": 88.91, "elapsed_time": "6:22:43", "remaining_time": "0:47:43", "throughput": 1485.58, "total_tokens": 34113600} {"current_steps": 161650, "total_steps": 181800, "loss": 0.0026, "lr": 1.8480155005101947e-06, "epoch": 17.783278327832782, "percentage": 88.92, "elapsed_time": "6:22:43", "remaining_time": "0:47:42", "throughput": 1485.58, "total_tokens": 34114624} {"current_steps": 161655, "total_steps": 181800, "loss": 0.0067, "lr": 1.847109992657578e-06, "epoch": 17.783828382838283, "percentage": 88.92, "elapsed_time": "6:22:44", "remaining_time": "0:47:41", "throughput": 1485.58, "total_tokens": 34115648} {"current_steps": 161660, "total_steps": 181800, "loss": 0.0044, "lr": 1.8462046981940429e-06, "epoch": 17.784378437843785, "percentage": 88.92, "elapsed_time": "6:22:45", "remaining_time": "0:47:41", "throughput": 1485.59, "total_tokens": 34116736} {"current_steps": 161665, "total_steps": 181800, "loss": 0.0012, "lr": 1.8452996171279269e-06, "epoch": 17.784928492849286, "percentage": 88.92, "elapsed_time": "6:22:45", "remaining_time": "0:47:40", "throughput": 1485.59, "total_tokens": 34117824} {"current_steps": 161670, "total_steps": 181800, "loss": 0.1353, "lr": 1.8443947494675679e-06, "epoch": 17.785478547854787, "percentage": 88.93, "elapsed_time": "6:22:46", "remaining_time": "0:47:39", "throughput": 1485.59, "total_tokens": 34118848} {"current_steps": 161675, "total_steps": 181800, "loss": 0.0007, "lr": 1.8434900952213174e-06, "epoch": 17.786028602860284, "percentage": 88.93, "elapsed_time": "6:22:47", "remaining_time": "0:47:38", "throughput": 1485.59, "total_tokens": 34119872} {"current_steps": 161680, "total_steps": 181800, "loss": 0.0442, "lr": 1.8425856543975051e-06, "epoch": 17.786578657865785, "percentage": 88.93, "elapsed_time": "6:22:47", "remaining_time": "0:47:38", "throughput": 1485.59, "total_tokens": 34120896} {"current_steps": 161685, "total_steps": 181800, "loss": 0.0013, "lr": 1.8416814270044712e-06, "epoch": 17.787128712871286, "percentage": 88.94, "elapsed_time": "6:22:48", "remaining_time": "0:47:37", "throughput": 1485.59, "total_tokens": 34121920} {"current_steps": 161690, "total_steps": 181800, "loss": 0.0017, "lr": 1.8407774130505483e-06, "epoch": 17.787678767876788, "percentage": 88.94, "elapsed_time": "6:22:49", "remaining_time": "0:47:36", "throughput": 1485.59, "total_tokens": 34122912} {"current_steps": 161695, "total_steps": 181800, "loss": 0.0563, "lr": 1.8398736125440602e-06, "epoch": 17.78822882288229, "percentage": 88.94, "elapsed_time": "6:22:50", "remaining_time": "0:47:36", "throughput": 1485.59, "total_tokens": 34124000} {"current_steps": 161700, "total_steps": 181800, "loss": 0.002, "lr": 1.8389700254933472e-06, "epoch": 17.78877887788779, "percentage": 88.94, "elapsed_time": "6:22:50", "remaining_time": "0:47:35", "throughput": 1485.59, "total_tokens": 34125056} {"current_steps": 161705, "total_steps": 181800, "loss": 0.0096, "lr": 1.8380666519067308e-06, "epoch": 17.78932893289329, "percentage": 88.95, "elapsed_time": "6:22:51", "remaining_time": "0:47:34", "throughput": 1485.59, "total_tokens": 34126144} {"current_steps": 161710, "total_steps": 181800, "loss": 0.1128, "lr": 1.8371634917925456e-06, "epoch": 17.78987898789879, "percentage": 88.95, "elapsed_time": "6:22:52", "remaining_time": "0:47:33", "throughput": 1485.59, "total_tokens": 34127200} {"current_steps": 161715, "total_steps": 181800, "loss": 0.0053, "lr": 1.8362605451591103e-06, "epoch": 17.79042904290429, "percentage": 88.95, "elapsed_time": "6:22:52", "remaining_time": "0:47:33", "throughput": 1485.6, "total_tokens": 34128288} {"current_steps": 161720, "total_steps": 181800, "loss": 0.0018, "lr": 1.835357812014743e-06, "epoch": 17.79097909790979, "percentage": 88.95, "elapsed_time": "6:22:53", "remaining_time": "0:47:32", "throughput": 1485.6, "total_tokens": 34129376} {"current_steps": 161725, "total_steps": 181800, "loss": 0.0175, "lr": 1.8344552923677705e-06, "epoch": 17.79152915291529, "percentage": 88.96, "elapsed_time": "6:22:54", "remaining_time": "0:47:31", "throughput": 1485.6, "total_tokens": 34130432} {"current_steps": 161730, "total_steps": 181800, "loss": 0.0149, "lr": 1.8335529862264973e-06, "epoch": 17.792079207920793, "percentage": 88.96, "elapsed_time": "6:22:54", "remaining_time": "0:47:31", "throughput": 1485.6, "total_tokens": 34131520} {"current_steps": 161735, "total_steps": 181800, "loss": 0.005, "lr": 1.8326508935992609e-06, "epoch": 17.792629262926294, "percentage": 88.96, "elapsed_time": "6:22:55", "remaining_time": "0:47:30", "throughput": 1485.6, "total_tokens": 34132576} {"current_steps": 161740, "total_steps": 181800, "loss": 0.1004, "lr": 1.8317490144943633e-06, "epoch": 17.793179317931795, "percentage": 88.97, "elapsed_time": "6:22:56", "remaining_time": "0:47:29", "throughput": 1485.61, "total_tokens": 34133632} {"current_steps": 161745, "total_steps": 181800, "loss": 0.0019, "lr": 1.8308473489201144e-06, "epoch": 17.793729372937293, "percentage": 88.97, "elapsed_time": "6:22:56", "remaining_time": "0:47:28", "throughput": 1485.61, "total_tokens": 34134720} {"current_steps": 161750, "total_steps": 181800, "loss": 0.0021, "lr": 1.8299458968848327e-06, "epoch": 17.794279427942794, "percentage": 88.97, "elapsed_time": "6:22:57", "remaining_time": "0:47:28", "throughput": 1485.61, "total_tokens": 34135744} {"current_steps": 161755, "total_steps": 181800, "loss": 0.0041, "lr": 1.829044658396817e-06, "epoch": 17.794829482948295, "percentage": 88.97, "elapsed_time": "6:22:58", "remaining_time": "0:47:27", "throughput": 1485.61, "total_tokens": 34136896} {"current_steps": 161760, "total_steps": 181800, "loss": 0.0021, "lr": 1.828143633464377e-06, "epoch": 17.795379537953796, "percentage": 88.98, "elapsed_time": "6:22:58", "remaining_time": "0:47:26", "throughput": 1485.62, "total_tokens": 34137952} {"current_steps": 161765, "total_steps": 181800, "loss": 0.0752, "lr": 1.827242822095823e-06, "epoch": 17.795929592959297, "percentage": 88.98, "elapsed_time": "6:22:59", "remaining_time": "0:47:26", "throughput": 1485.62, "total_tokens": 34139008} {"current_steps": 161770, "total_steps": 181800, "loss": 0.0422, "lr": 1.8263422242994461e-06, "epoch": 17.796479647964798, "percentage": 88.98, "elapsed_time": "6:23:00", "remaining_time": "0:47:25", "throughput": 1485.62, "total_tokens": 34140032} {"current_steps": 161775, "total_steps": 181800, "loss": 0.0025, "lr": 1.825441840083561e-06, "epoch": 17.797029702970296, "percentage": 88.99, "elapsed_time": "6:23:01", "remaining_time": "0:47:24", "throughput": 1485.62, "total_tokens": 34141152} {"current_steps": 161780, "total_steps": 181800, "loss": 0.0036, "lr": 1.824541669456456e-06, "epoch": 17.797579757975797, "percentage": 88.99, "elapsed_time": "6:23:01", "remaining_time": "0:47:23", "throughput": 1485.62, "total_tokens": 34142176} {"current_steps": 161785, "total_steps": 181800, "loss": 0.0597, "lr": 1.8236417124264272e-06, "epoch": 17.798129812981298, "percentage": 88.99, "elapsed_time": "6:23:02", "remaining_time": "0:47:23", "throughput": 1485.63, "total_tokens": 34143296} {"current_steps": 161790, "total_steps": 181800, "loss": 0.0066, "lr": 1.8227419690017705e-06, "epoch": 17.7986798679868, "percentage": 88.99, "elapsed_time": "6:23:03", "remaining_time": "0:47:22", "throughput": 1485.63, "total_tokens": 34144352} {"current_steps": 161795, "total_steps": 181800, "loss": 0.0154, "lr": 1.8218424391907795e-06, "epoch": 17.7992299229923, "percentage": 89.0, "elapsed_time": "6:23:03", "remaining_time": "0:47:21", "throughput": 1485.63, "total_tokens": 34145408} {"current_steps": 161800, "total_steps": 181800, "loss": 0.0027, "lr": 1.8209431230017477e-06, "epoch": 17.7997799779978, "percentage": 89.0, "elapsed_time": "6:23:04", "remaining_time": "0:47:21", "throughput": 1485.63, "total_tokens": 34146464} {"current_steps": 161805, "total_steps": 181800, "loss": 0.0043, "lr": 1.8200440204429626e-06, "epoch": 17.8003300330033, "percentage": 89.0, "elapsed_time": "6:23:05", "remaining_time": "0:47:20", "throughput": 1485.63, "total_tokens": 34147520} {"current_steps": 161810, "total_steps": 181800, "loss": 0.0017, "lr": 1.8191451315227066e-06, "epoch": 17.8008800880088, "percentage": 89.0, "elapsed_time": "6:23:05", "remaining_time": "0:47:19", "throughput": 1485.63, "total_tokens": 34148544} {"current_steps": 161815, "total_steps": 181800, "loss": 0.0007, "lr": 1.8182464562492619e-06, "epoch": 17.8014301430143, "percentage": 89.01, "elapsed_time": "6:23:06", "remaining_time": "0:47:18", "throughput": 1485.63, "total_tokens": 34149600} {"current_steps": 161820, "total_steps": 181800, "loss": 0.0323, "lr": 1.817347994630919e-06, "epoch": 17.801980198019802, "percentage": 89.01, "elapsed_time": "6:23:07", "remaining_time": "0:47:18", "throughput": 1485.63, "total_tokens": 34150656} {"current_steps": 161825, "total_steps": 181800, "loss": 0.0255, "lr": 1.8164497466759606e-06, "epoch": 17.802530253025303, "percentage": 89.01, "elapsed_time": "6:23:07", "remaining_time": "0:47:17", "throughput": 1485.64, "total_tokens": 34151744} {"current_steps": 161830, "total_steps": 181800, "loss": 0.0056, "lr": 1.8155517123926574e-06, "epoch": 17.803080308030804, "percentage": 89.02, "elapsed_time": "6:23:08", "remaining_time": "0:47:16", "throughput": 1485.64, "total_tokens": 34152768} {"current_steps": 161835, "total_steps": 181800, "loss": 0.0264, "lr": 1.8146538917892864e-06, "epoch": 17.803630363036305, "percentage": 89.02, "elapsed_time": "6:23:09", "remaining_time": "0:47:16", "throughput": 1485.64, "total_tokens": 34153760} {"current_steps": 161840, "total_steps": 181800, "loss": 0.0375, "lr": 1.8137562848741297e-06, "epoch": 17.804180418041803, "percentage": 89.02, "elapsed_time": "6:23:10", "remaining_time": "0:47:15", "throughput": 1485.64, "total_tokens": 34154816} {"current_steps": 161845, "total_steps": 181800, "loss": 0.0785, "lr": 1.81285889165545e-06, "epoch": 17.804730473047304, "percentage": 89.02, "elapsed_time": "6:23:10", "remaining_time": "0:47:14", "throughput": 1485.64, "total_tokens": 34155840} {"current_steps": 161850, "total_steps": 181800, "loss": 0.0049, "lr": 1.8119617121415244e-06, "epoch": 17.805280528052805, "percentage": 89.03, "elapsed_time": "6:23:11", "remaining_time": "0:47:13", "throughput": 1485.64, "total_tokens": 34156928} {"current_steps": 161855, "total_steps": 181800, "loss": 0.0024, "lr": 1.8110647463406266e-06, "epoch": 17.805830583058306, "percentage": 89.03, "elapsed_time": "6:23:12", "remaining_time": "0:47:13", "throughput": 1485.64, "total_tokens": 34157984} {"current_steps": 161860, "total_steps": 181800, "loss": 0.0011, "lr": 1.810167994261011e-06, "epoch": 17.806380638063807, "percentage": 89.03, "elapsed_time": "6:23:12", "remaining_time": "0:47:12", "throughput": 1485.64, "total_tokens": 34159072} {"current_steps": 161865, "total_steps": 181800, "loss": 0.0296, "lr": 1.8092714559109576e-06, "epoch": 17.806930693069308, "percentage": 89.03, "elapsed_time": "6:23:13", "remaining_time": "0:47:11", "throughput": 1485.64, "total_tokens": 34160096} {"current_steps": 161870, "total_steps": 181800, "loss": 0.0056, "lr": 1.808375131298712e-06, "epoch": 17.80748074807481, "percentage": 89.04, "elapsed_time": "6:23:14", "remaining_time": "0:47:11", "throughput": 1485.65, "total_tokens": 34161152} {"current_steps": 161875, "total_steps": 181800, "loss": 0.0054, "lr": 1.8074790204325481e-06, "epoch": 17.808030803080307, "percentage": 89.04, "elapsed_time": "6:23:14", "remaining_time": "0:47:10", "throughput": 1485.64, "total_tokens": 34162176} {"current_steps": 161880, "total_steps": 181800, "loss": 0.0088, "lr": 1.8065831233207236e-06, "epoch": 17.808580858085808, "percentage": 89.04, "elapsed_time": "6:23:15", "remaining_time": "0:47:09", "throughput": 1485.65, "total_tokens": 34163232} {"current_steps": 161885, "total_steps": 181800, "loss": 0.0102, "lr": 1.8056874399714902e-06, "epoch": 17.80913091309131, "percentage": 89.05, "elapsed_time": "6:23:16", "remaining_time": "0:47:08", "throughput": 1485.65, "total_tokens": 34164320} {"current_steps": 161890, "total_steps": 181800, "loss": 0.007, "lr": 1.8047919703931077e-06, "epoch": 17.80968096809681, "percentage": 89.05, "elapsed_time": "6:23:16", "remaining_time": "0:47:08", "throughput": 1485.65, "total_tokens": 34165440} {"current_steps": 161895, "total_steps": 181800, "loss": 0.0596, "lr": 1.803896714593825e-06, "epoch": 17.81023102310231, "percentage": 89.05, "elapsed_time": "6:23:17", "remaining_time": "0:47:07", "throughput": 1485.66, "total_tokens": 34166528} {"current_steps": 161900, "total_steps": 181800, "loss": 0.0017, "lr": 1.8030016725818998e-06, "epoch": 17.810781078107812, "percentage": 89.05, "elapsed_time": "6:23:18", "remaining_time": "0:47:06", "throughput": 1485.66, "total_tokens": 34167552} {"current_steps": 161905, "total_steps": 181800, "loss": 0.0227, "lr": 1.8021068443655753e-06, "epoch": 17.81133113311331, "percentage": 89.06, "elapsed_time": "6:23:18", "remaining_time": "0:47:06", "throughput": 1485.65, "total_tokens": 34168544} {"current_steps": 161910, "total_steps": 181800, "loss": 0.0256, "lr": 1.8012122299530976e-06, "epoch": 17.81188118811881, "percentage": 89.06, "elapsed_time": "6:23:19", "remaining_time": "0:47:05", "throughput": 1485.66, "total_tokens": 34169632} {"current_steps": 161915, "total_steps": 181800, "loss": 0.0279, "lr": 1.8003178293527212e-06, "epoch": 17.812431243124312, "percentage": 89.06, "elapsed_time": "6:23:20", "remaining_time": "0:47:04", "throughput": 1485.66, "total_tokens": 34170688} {"current_steps": 161920, "total_steps": 181800, "loss": 0.0119, "lr": 1.7994236425726757e-06, "epoch": 17.812981298129813, "percentage": 89.06, "elapsed_time": "6:23:21", "remaining_time": "0:47:03", "throughput": 1485.66, "total_tokens": 34171776} {"current_steps": 161925, "total_steps": 181800, "loss": 0.0091, "lr": 1.7985296696212156e-06, "epoch": 17.813531353135314, "percentage": 89.07, "elapsed_time": "6:23:21", "remaining_time": "0:47:03", "throughput": 1485.67, "total_tokens": 34172896} {"current_steps": 161930, "total_steps": 181800, "loss": 0.0045, "lr": 1.7976359105065704e-06, "epoch": 17.814081408140815, "percentage": 89.07, "elapsed_time": "6:23:22", "remaining_time": "0:47:02", "throughput": 1485.67, "total_tokens": 34174048} {"current_steps": 161935, "total_steps": 181800, "loss": 0.0095, "lr": 1.7967423652369837e-06, "epoch": 17.814631463146316, "percentage": 89.07, "elapsed_time": "6:23:23", "remaining_time": "0:47:01", "throughput": 1485.67, "total_tokens": 34175136} {"current_steps": 161940, "total_steps": 181800, "loss": 0.1222, "lr": 1.7958490338206901e-06, "epoch": 17.815181518151814, "percentage": 89.08, "elapsed_time": "6:23:23", "remaining_time": "0:47:01", "throughput": 1485.67, "total_tokens": 34176128} {"current_steps": 161945, "total_steps": 181800, "loss": 0.0139, "lr": 1.7949559162659168e-06, "epoch": 17.815731573157315, "percentage": 89.08, "elapsed_time": "6:23:24", "remaining_time": "0:47:00", "throughput": 1485.67, "total_tokens": 34177184} {"current_steps": 161950, "total_steps": 181800, "loss": 0.0441, "lr": 1.7940630125809043e-06, "epoch": 17.816281628162816, "percentage": 89.08, "elapsed_time": "6:23:25", "remaining_time": "0:46:59", "throughput": 1485.68, "total_tokens": 34178272} {"current_steps": 161955, "total_steps": 181800, "loss": 0.0462, "lr": 1.7931703227738793e-06, "epoch": 17.816831683168317, "percentage": 89.08, "elapsed_time": "6:23:25", "remaining_time": "0:46:59", "throughput": 1485.68, "total_tokens": 34179328} {"current_steps": 161960, "total_steps": 181800, "loss": 0.0014, "lr": 1.7922778468530633e-06, "epoch": 17.817381738173818, "percentage": 89.09, "elapsed_time": "6:23:26", "remaining_time": "0:46:58", "throughput": 1485.68, "total_tokens": 34180384} {"current_steps": 161965, "total_steps": 181800, "loss": 0.0119, "lr": 1.7913855848266852e-06, "epoch": 17.81793179317932, "percentage": 89.09, "elapsed_time": "6:23:27", "remaining_time": "0:46:57", "throughput": 1485.68, "total_tokens": 34181472} {"current_steps": 161970, "total_steps": 181800, "loss": 0.0227, "lr": 1.7904935367029752e-06, "epoch": 17.818481848184817, "percentage": 89.09, "elapsed_time": "6:23:27", "remaining_time": "0:46:56", "throughput": 1485.68, "total_tokens": 34182560} {"current_steps": 161975, "total_steps": 181800, "loss": 0.0215, "lr": 1.7896017024901428e-06, "epoch": 17.819031903190318, "percentage": 89.1, "elapsed_time": "6:23:28", "remaining_time": "0:46:56", "throughput": 1485.69, "total_tokens": 34183680} {"current_steps": 161980, "total_steps": 181800, "loss": 0.0428, "lr": 1.7887100821964209e-06, "epoch": 17.81958195819582, "percentage": 89.1, "elapsed_time": "6:23:29", "remaining_time": "0:46:55", "throughput": 1485.69, "total_tokens": 34184768} {"current_steps": 161985, "total_steps": 181800, "loss": 0.0028, "lr": 1.7878186758300137e-06, "epoch": 17.82013201320132, "percentage": 89.1, "elapsed_time": "6:23:30", "remaining_time": "0:46:54", "throughput": 1485.69, "total_tokens": 34185824} {"current_steps": 161990, "total_steps": 181800, "loss": 0.0572, "lr": 1.786927483399145e-06, "epoch": 17.82068206820682, "percentage": 89.1, "elapsed_time": "6:23:30", "remaining_time": "0:46:54", "throughput": 1485.69, "total_tokens": 34186912} {"current_steps": 161995, "total_steps": 181800, "loss": 0.0409, "lr": 1.7860365049120309e-06, "epoch": 17.821232123212322, "percentage": 89.11, "elapsed_time": "6:23:31", "remaining_time": "0:46:53", "throughput": 1485.7, "total_tokens": 34188096} {"current_steps": 162000, "total_steps": 181800, "loss": 0.1632, "lr": 1.7851457403768756e-06, "epoch": 17.821782178217823, "percentage": 89.11, "elapsed_time": "6:23:32", "remaining_time": "0:46:52", "throughput": 1485.7, "total_tokens": 34189184} {"current_steps": 162005, "total_steps": 181800, "loss": 0.0023, "lr": 1.784255189801895e-06, "epoch": 17.82233223322332, "percentage": 89.11, "elapsed_time": "6:23:32", "remaining_time": "0:46:51", "throughput": 1485.71, "total_tokens": 34190304} {"current_steps": 162010, "total_steps": 181800, "loss": 0.0024, "lr": 1.7833648531952907e-06, "epoch": 17.822882288228822, "percentage": 89.11, "elapsed_time": "6:23:33", "remaining_time": "0:46:51", "throughput": 1485.71, "total_tokens": 34191360} {"current_steps": 162015, "total_steps": 181800, "loss": 0.068, "lr": 1.7824747305652783e-06, "epoch": 17.823432343234323, "percentage": 89.12, "elapsed_time": "6:23:34", "remaining_time": "0:46:50", "throughput": 1485.71, "total_tokens": 34192384} {"current_steps": 162020, "total_steps": 181800, "loss": 0.0011, "lr": 1.7815848219200488e-06, "epoch": 17.823982398239824, "percentage": 89.12, "elapsed_time": "6:23:34", "remaining_time": "0:46:49", "throughput": 1485.71, "total_tokens": 34193408} {"current_steps": 162025, "total_steps": 181800, "loss": 0.0114, "lr": 1.7806951272678119e-06, "epoch": 17.824532453245325, "percentage": 89.12, "elapsed_time": "6:23:35", "remaining_time": "0:46:49", "throughput": 1485.71, "total_tokens": 34194464} {"current_steps": 162030, "total_steps": 181800, "loss": 0.1364, "lr": 1.7798056466167696e-06, "epoch": 17.825082508250826, "percentage": 89.13, "elapsed_time": "6:23:36", "remaining_time": "0:46:48", "throughput": 1485.71, "total_tokens": 34195552} {"current_steps": 162035, "total_steps": 181800, "loss": 0.1618, "lr": 1.7789163799751124e-06, "epoch": 17.825632563256324, "percentage": 89.13, "elapsed_time": "6:23:36", "remaining_time": "0:46:47", "throughput": 1485.71, "total_tokens": 34196608} {"current_steps": 162040, "total_steps": 181800, "loss": 0.0797, "lr": 1.778027327351045e-06, "epoch": 17.826182618261825, "percentage": 89.13, "elapsed_time": "6:23:37", "remaining_time": "0:46:46", "throughput": 1485.72, "total_tokens": 34197792} {"current_steps": 162045, "total_steps": 181800, "loss": 0.0115, "lr": 1.7771384887527526e-06, "epoch": 17.826732673267326, "percentage": 89.13, "elapsed_time": "6:23:38", "remaining_time": "0:46:46", "throughput": 1485.72, "total_tokens": 34198816} {"current_steps": 162050, "total_steps": 181800, "loss": 0.0038, "lr": 1.7762498641884312e-06, "epoch": 17.827282728272827, "percentage": 89.14, "elapsed_time": "6:23:39", "remaining_time": "0:46:45", "throughput": 1485.72, "total_tokens": 34199904} {"current_steps": 162055, "total_steps": 181800, "loss": 0.0053, "lr": 1.7753614536662772e-06, "epoch": 17.82783278327833, "percentage": 89.14, "elapsed_time": "6:23:39", "remaining_time": "0:46:44", "throughput": 1485.72, "total_tokens": 34200896} {"current_steps": 162060, "total_steps": 181800, "loss": 0.0922, "lr": 1.7744732571944644e-06, "epoch": 17.82838283828383, "percentage": 89.14, "elapsed_time": "6:23:40", "remaining_time": "0:46:44", "throughput": 1485.72, "total_tokens": 34201984} {"current_steps": 162065, "total_steps": 181800, "loss": 0.0958, "lr": 1.7735852747811948e-06, "epoch": 17.82893289328933, "percentage": 89.14, "elapsed_time": "6:23:41", "remaining_time": "0:46:43", "throughput": 1485.73, "total_tokens": 34203040} {"current_steps": 162070, "total_steps": 181800, "loss": 0.0678, "lr": 1.7726975064346423e-06, "epoch": 17.829482948294828, "percentage": 89.15, "elapsed_time": "6:23:41", "remaining_time": "0:46:42", "throughput": 1485.73, "total_tokens": 34204096} {"current_steps": 162075, "total_steps": 181800, "loss": 0.0055, "lr": 1.7718099521629865e-06, "epoch": 17.83003300330033, "percentage": 89.15, "elapsed_time": "6:23:42", "remaining_time": "0:46:41", "throughput": 1485.73, "total_tokens": 34205216} {"current_steps": 162080, "total_steps": 181800, "loss": 0.0112, "lr": 1.7709226119744155e-06, "epoch": 17.83058305830583, "percentage": 89.15, "elapsed_time": "6:23:43", "remaining_time": "0:46:41", "throughput": 1485.73, "total_tokens": 34206208} {"current_steps": 162085, "total_steps": 181800, "loss": 0.0738, "lr": 1.7700354858771001e-06, "epoch": 17.83113311331133, "percentage": 89.16, "elapsed_time": "6:23:43", "remaining_time": "0:46:40", "throughput": 1485.73, "total_tokens": 34207296} {"current_steps": 162090, "total_steps": 181800, "loss": 0.0045, "lr": 1.7691485738792285e-06, "epoch": 17.831683168316832, "percentage": 89.16, "elapsed_time": "6:23:44", "remaining_time": "0:46:39", "throughput": 1485.73, "total_tokens": 34208320} {"current_steps": 162095, "total_steps": 181800, "loss": 0.0089, "lr": 1.7682618759889664e-06, "epoch": 17.832233223322334, "percentage": 89.16, "elapsed_time": "6:23:45", "remaining_time": "0:46:39", "throughput": 1485.73, "total_tokens": 34209408} {"current_steps": 162100, "total_steps": 181800, "loss": 0.0006, "lr": 1.767375392214482e-06, "epoch": 17.83278327832783, "percentage": 89.16, "elapsed_time": "6:23:45", "remaining_time": "0:46:38", "throughput": 1485.73, "total_tokens": 34210400} {"current_steps": 162105, "total_steps": 181800, "loss": 0.0025, "lr": 1.7664891225639495e-06, "epoch": 17.833333333333332, "percentage": 89.17, "elapsed_time": "6:23:46", "remaining_time": "0:46:37", "throughput": 1485.73, "total_tokens": 34211456} {"current_steps": 162110, "total_steps": 181800, "loss": 0.0437, "lr": 1.7656030670455404e-06, "epoch": 17.833883388338833, "percentage": 89.17, "elapsed_time": "6:23:47", "remaining_time": "0:46:36", "throughput": 1485.73, "total_tokens": 34212480} {"current_steps": 162115, "total_steps": 181800, "loss": 0.0465, "lr": 1.7647172256674227e-06, "epoch": 17.834433443344334, "percentage": 89.17, "elapsed_time": "6:23:48", "remaining_time": "0:46:36", "throughput": 1485.74, "total_tokens": 34213568} {"current_steps": 162120, "total_steps": 181800, "loss": 0.0061, "lr": 1.7638315984377568e-06, "epoch": 17.834983498349835, "percentage": 89.17, "elapsed_time": "6:23:48", "remaining_time": "0:46:35", "throughput": 1485.74, "total_tokens": 34214560} {"current_steps": 162125, "total_steps": 181800, "loss": 0.0059, "lr": 1.7629461853647e-06, "epoch": 17.835533553355337, "percentage": 89.18, "elapsed_time": "6:23:49", "remaining_time": "0:46:34", "throughput": 1485.74, "total_tokens": 34215616} {"current_steps": 162130, "total_steps": 181800, "loss": 0.0651, "lr": 1.7620609864564237e-06, "epoch": 17.836083608360838, "percentage": 89.18, "elapsed_time": "6:23:50", "remaining_time": "0:46:34", "throughput": 1485.74, "total_tokens": 34216640} {"current_steps": 162135, "total_steps": 181800, "loss": 0.0575, "lr": 1.7611760017210767e-06, "epoch": 17.836633663366335, "percentage": 89.18, "elapsed_time": "6:23:50", "remaining_time": "0:46:33", "throughput": 1485.74, "total_tokens": 34217696} {"current_steps": 162140, "total_steps": 181800, "loss": 0.0035, "lr": 1.760291231166819e-06, "epoch": 17.837183718371836, "percentage": 89.19, "elapsed_time": "6:23:51", "remaining_time": "0:46:32", "throughput": 1485.74, "total_tokens": 34218752} {"current_steps": 162145, "total_steps": 181800, "loss": 0.0127, "lr": 1.7594066748018085e-06, "epoch": 17.837733773377337, "percentage": 89.19, "elapsed_time": "6:23:52", "remaining_time": "0:46:31", "throughput": 1485.74, "total_tokens": 34219808} {"current_steps": 162150, "total_steps": 181800, "loss": 0.0009, "lr": 1.758522332634191e-06, "epoch": 17.83828382838284, "percentage": 89.19, "elapsed_time": "6:23:52", "remaining_time": "0:46:31", "throughput": 1485.74, "total_tokens": 34220864} {"current_steps": 162155, "total_steps": 181800, "loss": 0.0035, "lr": 1.757638204672124e-06, "epoch": 17.83883388338834, "percentage": 89.19, "elapsed_time": "6:23:53", "remaining_time": "0:46:30", "throughput": 1485.74, "total_tokens": 34221888} {"current_steps": 162160, "total_steps": 181800, "loss": 0.0472, "lr": 1.756754290923751e-06, "epoch": 17.83938393839384, "percentage": 89.2, "elapsed_time": "6:23:54", "remaining_time": "0:46:29", "throughput": 1485.75, "total_tokens": 34223008} {"current_steps": 162165, "total_steps": 181800, "loss": 0.0019, "lr": 1.7558705913972211e-06, "epoch": 17.83993399339934, "percentage": 89.2, "elapsed_time": "6:23:54", "remaining_time": "0:46:29", "throughput": 1485.74, "total_tokens": 34224000} {"current_steps": 162170, "total_steps": 181800, "loss": 0.0748, "lr": 1.7549871061006806e-06, "epoch": 17.84048404840484, "percentage": 89.2, "elapsed_time": "6:23:55", "remaining_time": "0:46:28", "throughput": 1485.74, "total_tokens": 34225056} {"current_steps": 162175, "total_steps": 181800, "loss": 0.0355, "lr": 1.7541038350422645e-06, "epoch": 17.84103410341034, "percentage": 89.21, "elapsed_time": "6:23:56", "remaining_time": "0:46:27", "throughput": 1485.74, "total_tokens": 34226080} {"current_steps": 162180, "total_steps": 181800, "loss": 0.0073, "lr": 1.7532207782301247e-06, "epoch": 17.84158415841584, "percentage": 89.21, "elapsed_time": "6:23:57", "remaining_time": "0:46:26", "throughput": 1485.75, "total_tokens": 34227168} {"current_steps": 162185, "total_steps": 181800, "loss": 0.0015, "lr": 1.7523379356723934e-06, "epoch": 17.842134213421343, "percentage": 89.21, "elapsed_time": "6:23:57", "remaining_time": "0:46:26", "throughput": 1485.75, "total_tokens": 34228160} {"current_steps": 162190, "total_steps": 181800, "loss": 0.0096, "lr": 1.751455307377206e-06, "epoch": 17.842684268426844, "percentage": 89.21, "elapsed_time": "6:23:58", "remaining_time": "0:46:25", "throughput": 1485.75, "total_tokens": 34229216} {"current_steps": 162195, "total_steps": 181800, "loss": 0.0905, "lr": 1.7505728933526978e-06, "epoch": 17.843234323432345, "percentage": 89.22, "elapsed_time": "6:23:59", "remaining_time": "0:46:24", "throughput": 1485.75, "total_tokens": 34230304} {"current_steps": 162200, "total_steps": 181800, "loss": 0.0368, "lr": 1.7496906936070035e-06, "epoch": 17.843784378437842, "percentage": 89.22, "elapsed_time": "6:23:59", "remaining_time": "0:46:24", "throughput": 1485.75, "total_tokens": 34231360} {"current_steps": 162205, "total_steps": 181800, "loss": 0.0031, "lr": 1.7488087081482557e-06, "epoch": 17.844334433443343, "percentage": 89.22, "elapsed_time": "6:24:00", "remaining_time": "0:46:23", "throughput": 1485.75, "total_tokens": 34232384} {"current_steps": 162210, "total_steps": 181800, "loss": 0.0268, "lr": 1.747926936984584e-06, "epoch": 17.844884488448844, "percentage": 89.22, "elapsed_time": "6:24:01", "remaining_time": "0:46:22", "throughput": 1485.75, "total_tokens": 34233376} {"current_steps": 162215, "total_steps": 181800, "loss": 0.0606, "lr": 1.747045380124107e-06, "epoch": 17.845434543454346, "percentage": 89.23, "elapsed_time": "6:24:01", "remaining_time": "0:46:21", "throughput": 1485.75, "total_tokens": 34234432} {"current_steps": 162220, "total_steps": 181800, "loss": 0.0029, "lr": 1.7461640375749543e-06, "epoch": 17.845984598459847, "percentage": 89.23, "elapsed_time": "6:24:02", "remaining_time": "0:46:21", "throughput": 1485.74, "total_tokens": 34235456} {"current_steps": 162225, "total_steps": 181800, "loss": 0.0047, "lr": 1.74528290934525e-06, "epoch": 17.846534653465348, "percentage": 89.23, "elapsed_time": "6:24:03", "remaining_time": "0:46:20", "throughput": 1485.74, "total_tokens": 34236512} {"current_steps": 162230, "total_steps": 181800, "loss": 0.004, "lr": 1.7444019954431178e-06, "epoch": 17.847084708470845, "percentage": 89.24, "elapsed_time": "6:24:04", "remaining_time": "0:46:19", "throughput": 1485.74, "total_tokens": 34237600} {"current_steps": 162235, "total_steps": 181800, "loss": 0.0072, "lr": 1.743521295876674e-06, "epoch": 17.847634763476346, "percentage": 89.24, "elapsed_time": "6:24:04", "remaining_time": "0:46:19", "throughput": 1485.74, "total_tokens": 34238688} {"current_steps": 162240, "total_steps": 181800, "loss": 0.0511, "lr": 1.742640810654028e-06, "epoch": 17.848184818481847, "percentage": 89.24, "elapsed_time": "6:24:05", "remaining_time": "0:46:18", "throughput": 1485.75, "total_tokens": 34239744} {"current_steps": 162245, "total_steps": 181800, "loss": 0.189, "lr": 1.7417605397833103e-06, "epoch": 17.84873487348735, "percentage": 89.24, "elapsed_time": "6:24:06", "remaining_time": "0:46:17", "throughput": 1485.75, "total_tokens": 34240800} {"current_steps": 162250, "total_steps": 181800, "loss": 0.0026, "lr": 1.7408804832726194e-06, "epoch": 17.84928492849285, "percentage": 89.25, "elapsed_time": "6:24:06", "remaining_time": "0:46:16", "throughput": 1485.75, "total_tokens": 34241856} {"current_steps": 162255, "total_steps": 181800, "loss": 0.0048, "lr": 1.7400006411300712e-06, "epoch": 17.84983498349835, "percentage": 89.25, "elapsed_time": "6:24:07", "remaining_time": "0:46:16", "throughput": 1485.75, "total_tokens": 34242912} {"current_steps": 162260, "total_steps": 181800, "loss": 0.0022, "lr": 1.7391210133637815e-06, "epoch": 17.850385038503852, "percentage": 89.25, "elapsed_time": "6:24:08", "remaining_time": "0:46:15", "throughput": 1485.75, "total_tokens": 34243904} {"current_steps": 162265, "total_steps": 181800, "loss": 0.0022, "lr": 1.7382415999818462e-06, "epoch": 17.85093509350935, "percentage": 89.25, "elapsed_time": "6:24:08", "remaining_time": "0:46:14", "throughput": 1485.75, "total_tokens": 34244928} {"current_steps": 162270, "total_steps": 181800, "loss": 0.0147, "lr": 1.7373624009923817e-06, "epoch": 17.85148514851485, "percentage": 89.26, "elapsed_time": "6:24:09", "remaining_time": "0:46:14", "throughput": 1485.75, "total_tokens": 34245984} {"current_steps": 162275, "total_steps": 181800, "loss": 0.0018, "lr": 1.7364834164034782e-06, "epoch": 17.85203520352035, "percentage": 89.26, "elapsed_time": "6:24:10", "remaining_time": "0:46:13", "throughput": 1485.75, "total_tokens": 34246976} {"current_steps": 162280, "total_steps": 181800, "loss": 0.0083, "lr": 1.735604646223249e-06, "epoch": 17.852585258525853, "percentage": 89.26, "elapsed_time": "6:24:11", "remaining_time": "0:46:12", "throughput": 1485.75, "total_tokens": 34248064} {"current_steps": 162285, "total_steps": 181800, "loss": 0.0381, "lr": 1.73472609045979e-06, "epoch": 17.853135313531354, "percentage": 89.27, "elapsed_time": "6:24:11", "remaining_time": "0:46:12", "throughput": 1485.75, "total_tokens": 34249088} {"current_steps": 162290, "total_steps": 181800, "loss": 0.0727, "lr": 1.7338477491211923e-06, "epoch": 17.853685368536855, "percentage": 89.27, "elapsed_time": "6:24:12", "remaining_time": "0:46:11", "throughput": 1485.75, "total_tokens": 34250208} {"current_steps": 162295, "total_steps": 181800, "loss": 0.0007, "lr": 1.7329696222155607e-06, "epoch": 17.854235423542356, "percentage": 89.27, "elapsed_time": "6:24:13", "remaining_time": "0:46:10", "throughput": 1485.75, "total_tokens": 34251200} {"current_steps": 162300, "total_steps": 181800, "loss": 0.0103, "lr": 1.732091709750977e-06, "epoch": 17.854785478547853, "percentage": 89.27, "elapsed_time": "6:24:13", "remaining_time": "0:46:09", "throughput": 1485.76, "total_tokens": 34252288} {"current_steps": 162305, "total_steps": 181800, "loss": 0.0087, "lr": 1.7312140117355464e-06, "epoch": 17.855335533553355, "percentage": 89.28, "elapsed_time": "6:24:14", "remaining_time": "0:46:09", "throughput": 1485.76, "total_tokens": 34253312} {"current_steps": 162310, "total_steps": 181800, "loss": 0.1539, "lr": 1.7303365281773453e-06, "epoch": 17.855885588558856, "percentage": 89.28, "elapsed_time": "6:24:15", "remaining_time": "0:46:08", "throughput": 1485.75, "total_tokens": 34254304} {"current_steps": 162315, "total_steps": 181800, "loss": 0.0987, "lr": 1.729459259084465e-06, "epoch": 17.856435643564357, "percentage": 89.28, "elapsed_time": "6:24:15", "remaining_time": "0:46:07", "throughput": 1485.75, "total_tokens": 34255328} {"current_steps": 162320, "total_steps": 181800, "loss": 0.0022, "lr": 1.7285822044649985e-06, "epoch": 17.856985698569858, "percentage": 89.28, "elapsed_time": "6:24:16", "remaining_time": "0:46:07", "throughput": 1485.76, "total_tokens": 34256480} {"current_steps": 162325, "total_steps": 181800, "loss": 0.0051, "lr": 1.7277053643270203e-06, "epoch": 17.85753575357536, "percentage": 89.29, "elapsed_time": "6:24:17", "remaining_time": "0:46:06", "throughput": 1485.76, "total_tokens": 34257536} {"current_steps": 162330, "total_steps": 181800, "loss": 0.0028, "lr": 1.7268287386786153e-06, "epoch": 17.858085808580856, "percentage": 89.29, "elapsed_time": "6:24:17", "remaining_time": "0:46:05", "throughput": 1485.76, "total_tokens": 34258560} {"current_steps": 162335, "total_steps": 181800, "loss": 0.0939, "lr": 1.7259523275278634e-06, "epoch": 17.858635863586358, "percentage": 89.29, "elapsed_time": "6:24:18", "remaining_time": "0:46:04", "throughput": 1485.76, "total_tokens": 34259616} {"current_steps": 162340, "total_steps": 181800, "loss": 0.0031, "lr": 1.7250761308828356e-06, "epoch": 17.85918591859186, "percentage": 89.3, "elapsed_time": "6:24:19", "remaining_time": "0:46:04", "throughput": 1485.76, "total_tokens": 34260672} {"current_steps": 162345, "total_steps": 181800, "loss": 0.0034, "lr": 1.7242001487516175e-06, "epoch": 17.85973597359736, "percentage": 89.3, "elapsed_time": "6:24:20", "remaining_time": "0:46:03", "throughput": 1485.77, "total_tokens": 34261792} {"current_steps": 162350, "total_steps": 181800, "loss": 0.0161, "lr": 1.72332438114228e-06, "epoch": 17.86028602860286, "percentage": 89.3, "elapsed_time": "6:24:20", "remaining_time": "0:46:02", "throughput": 1485.77, "total_tokens": 34262816} {"current_steps": 162355, "total_steps": 181800, "loss": 0.0036, "lr": 1.7224488280628864e-06, "epoch": 17.860836083608362, "percentage": 89.3, "elapsed_time": "6:24:21", "remaining_time": "0:46:02", "throughput": 1485.77, "total_tokens": 34263840} {"current_steps": 162360, "total_steps": 181800, "loss": 0.0023, "lr": 1.7215734895215163e-06, "epoch": 17.861386138613863, "percentage": 89.31, "elapsed_time": "6:24:22", "remaining_time": "0:46:01", "throughput": 1485.77, "total_tokens": 34264896} {"current_steps": 162365, "total_steps": 181800, "loss": 0.0009, "lr": 1.7206983655262298e-06, "epoch": 17.86193619361936, "percentage": 89.31, "elapsed_time": "6:24:22", "remaining_time": "0:46:00", "throughput": 1485.77, "total_tokens": 34265920} {"current_steps": 162370, "total_steps": 181800, "loss": 0.0458, "lr": 1.7198234560850984e-06, "epoch": 17.86248624862486, "percentage": 89.31, "elapsed_time": "6:24:23", "remaining_time": "0:45:59", "throughput": 1485.77, "total_tokens": 34267008} {"current_steps": 162375, "total_steps": 181800, "loss": 0.0194, "lr": 1.718948761206185e-06, "epoch": 17.863036303630363, "percentage": 89.32, "elapsed_time": "6:24:24", "remaining_time": "0:45:59", "throughput": 1485.77, "total_tokens": 34268096} {"current_steps": 162380, "total_steps": 181800, "loss": 0.0033, "lr": 1.7180742808975443e-06, "epoch": 17.863586358635864, "percentage": 89.32, "elapsed_time": "6:24:24", "remaining_time": "0:45:58", "throughput": 1485.78, "total_tokens": 34269184} {"current_steps": 162385, "total_steps": 181800, "loss": 0.0084, "lr": 1.7172000151672473e-06, "epoch": 17.864136413641365, "percentage": 89.32, "elapsed_time": "6:24:25", "remaining_time": "0:45:57", "throughput": 1485.78, "total_tokens": 34270208} {"current_steps": 162390, "total_steps": 181800, "loss": 0.0799, "lr": 1.716325964023341e-06, "epoch": 17.864686468646866, "percentage": 89.32, "elapsed_time": "6:24:26", "remaining_time": "0:45:57", "throughput": 1485.77, "total_tokens": 34271168} {"current_steps": 162395, "total_steps": 181800, "loss": 0.0013, "lr": 1.7154521274738849e-06, "epoch": 17.865236523652364, "percentage": 89.33, "elapsed_time": "6:24:26", "remaining_time": "0:45:56", "throughput": 1485.77, "total_tokens": 34272192} {"current_steps": 162400, "total_steps": 181800, "loss": 0.0026, "lr": 1.7145785055269397e-06, "epoch": 17.865786578657865, "percentage": 89.33, "elapsed_time": "6:24:27", "remaining_time": "0:45:55", "throughput": 1485.77, "total_tokens": 34273184} {"current_steps": 162405, "total_steps": 181800, "loss": 0.0067, "lr": 1.7137050981905433e-06, "epoch": 17.866336633663366, "percentage": 89.33, "elapsed_time": "6:24:28", "remaining_time": "0:45:54", "throughput": 1485.77, "total_tokens": 34274272} {"current_steps": 162410, "total_steps": 181800, "loss": 0.0018, "lr": 1.7128319054727614e-06, "epoch": 17.866886688668867, "percentage": 89.33, "elapsed_time": "6:24:29", "remaining_time": "0:45:54", "throughput": 1485.77, "total_tokens": 34275296} {"current_steps": 162415, "total_steps": 181800, "loss": 0.0038, "lr": 1.7119589273816267e-06, "epoch": 17.867436743674368, "percentage": 89.34, "elapsed_time": "6:24:29", "remaining_time": "0:45:53", "throughput": 1485.77, "total_tokens": 34276320} {"current_steps": 162420, "total_steps": 181800, "loss": 0.0498, "lr": 1.7110861639251962e-06, "epoch": 17.86798679867987, "percentage": 89.34, "elapsed_time": "6:24:30", "remaining_time": "0:45:52", "throughput": 1485.77, "total_tokens": 34277344} {"current_steps": 162425, "total_steps": 181800, "loss": 0.0467, "lr": 1.7102136151115056e-06, "epoch": 17.86853685368537, "percentage": 89.34, "elapsed_time": "6:24:31", "remaining_time": "0:45:52", "throughput": 1485.78, "total_tokens": 34278432} {"current_steps": 162430, "total_steps": 181800, "loss": 0.0014, "lr": 1.709341280948601e-06, "epoch": 17.869086908690868, "percentage": 89.35, "elapsed_time": "6:24:31", "remaining_time": "0:45:51", "throughput": 1485.77, "total_tokens": 34279424} {"current_steps": 162435, "total_steps": 181800, "loss": 0.3175, "lr": 1.708469161444526e-06, "epoch": 17.86963696369637, "percentage": 89.35, "elapsed_time": "6:24:32", "remaining_time": "0:45:50", "throughput": 1485.78, "total_tokens": 34280512} {"current_steps": 162440, "total_steps": 181800, "loss": 0.003, "lr": 1.70759725660731e-06, "epoch": 17.87018701870187, "percentage": 89.35, "elapsed_time": "6:24:33", "remaining_time": "0:45:49", "throughput": 1485.78, "total_tokens": 34281568} {"current_steps": 162445, "total_steps": 181800, "loss": 0.0023, "lr": 1.7067255664449999e-06, "epoch": 17.87073707370737, "percentage": 89.35, "elapsed_time": "6:24:33", "remaining_time": "0:45:49", "throughput": 1485.78, "total_tokens": 34282656} {"current_steps": 162450, "total_steps": 181800, "loss": 0.0012, "lr": 1.7058540909656196e-06, "epoch": 17.871287128712872, "percentage": 89.36, "elapsed_time": "6:24:34", "remaining_time": "0:45:48", "throughput": 1485.78, "total_tokens": 34283744} {"current_steps": 162455, "total_steps": 181800, "loss": 0.0016, "lr": 1.7049828301771986e-06, "epoch": 17.871837183718373, "percentage": 89.36, "elapsed_time": "6:24:35", "remaining_time": "0:45:47", "throughput": 1485.78, "total_tokens": 34284800} {"current_steps": 162460, "total_steps": 181800, "loss": 0.0049, "lr": 1.704111784087778e-06, "epoch": 17.87238723872387, "percentage": 89.36, "elapsed_time": "6:24:35", "remaining_time": "0:45:47", "throughput": 1485.78, "total_tokens": 34285792} {"current_steps": 162465, "total_steps": 181800, "loss": 0.0121, "lr": 1.703240952705379e-06, "epoch": 17.872937293729372, "percentage": 89.36, "elapsed_time": "6:24:36", "remaining_time": "0:45:46", "throughput": 1485.78, "total_tokens": 34286816} {"current_steps": 162470, "total_steps": 181800, "loss": 0.0012, "lr": 1.7023703360380339e-06, "epoch": 17.873487348734873, "percentage": 89.37, "elapsed_time": "6:24:37", "remaining_time": "0:45:45", "throughput": 1485.78, "total_tokens": 34287872} {"current_steps": 162475, "total_steps": 181800, "loss": 0.0561, "lr": 1.7014999340937588e-06, "epoch": 17.874037403740374, "percentage": 89.37, "elapsed_time": "6:24:37", "remaining_time": "0:45:44", "throughput": 1485.78, "total_tokens": 34288864} {"current_steps": 162480, "total_steps": 181800, "loss": 0.0111, "lr": 1.7006297468805776e-06, "epoch": 17.874587458745875, "percentage": 89.37, "elapsed_time": "6:24:38", "remaining_time": "0:45:44", "throughput": 1485.79, "total_tokens": 34289952} {"current_steps": 162485, "total_steps": 181800, "loss": 0.0033, "lr": 1.6997597744065119e-06, "epoch": 17.875137513751376, "percentage": 89.38, "elapsed_time": "6:24:39", "remaining_time": "0:45:43", "throughput": 1485.79, "total_tokens": 34291008} {"current_steps": 162490, "total_steps": 181800, "loss": 0.0122, "lr": 1.6988900166795802e-06, "epoch": 17.875687568756877, "percentage": 89.38, "elapsed_time": "6:24:40", "remaining_time": "0:45:42", "throughput": 1485.79, "total_tokens": 34292096} {"current_steps": 162495, "total_steps": 181800, "loss": 0.0012, "lr": 1.698020473707801e-06, "epoch": 17.876237623762375, "percentage": 89.38, "elapsed_time": "6:24:40", "remaining_time": "0:45:42", "throughput": 1485.79, "total_tokens": 34293216} {"current_steps": 162500, "total_steps": 181800, "loss": 0.0016, "lr": 1.6971511454991874e-06, "epoch": 17.876787678767876, "percentage": 89.38, "elapsed_time": "6:24:41", "remaining_time": "0:45:41", "throughput": 1485.79, "total_tokens": 34294272} {"current_steps": 162505, "total_steps": 181800, "loss": 0.0278, "lr": 1.696282032061744e-06, "epoch": 17.877337733773377, "percentage": 89.39, "elapsed_time": "6:24:42", "remaining_time": "0:45:40", "throughput": 1485.8, "total_tokens": 34295360} {"current_steps": 162510, "total_steps": 181800, "loss": 0.004, "lr": 1.6954131334034922e-06, "epoch": 17.877887788778878, "percentage": 89.39, "elapsed_time": "6:24:42", "remaining_time": "0:45:39", "throughput": 1485.8, "total_tokens": 34296416} {"current_steps": 162515, "total_steps": 181800, "loss": 0.0045, "lr": 1.6945444495324259e-06, "epoch": 17.87843784378438, "percentage": 89.39, "elapsed_time": "6:24:43", "remaining_time": "0:45:39", "throughput": 1485.8, "total_tokens": 34297504} {"current_steps": 162520, "total_steps": 181800, "loss": 0.0357, "lr": 1.6936759804565688e-06, "epoch": 17.87898789878988, "percentage": 89.39, "elapsed_time": "6:24:44", "remaining_time": "0:45:38", "throughput": 1485.8, "total_tokens": 34298528} {"current_steps": 162525, "total_steps": 181800, "loss": 0.0018, "lr": 1.6928077261839148e-06, "epoch": 17.879537953795378, "percentage": 89.4, "elapsed_time": "6:24:44", "remaining_time": "0:45:37", "throughput": 1485.8, "total_tokens": 34299552} {"current_steps": 162530, "total_steps": 181800, "loss": 0.0028, "lr": 1.6919396867224658e-06, "epoch": 17.88008800880088, "percentage": 89.4, "elapsed_time": "6:24:45", "remaining_time": "0:45:37", "throughput": 1485.81, "total_tokens": 34300704} {"current_steps": 162535, "total_steps": 181800, "loss": 0.2054, "lr": 1.691071862080229e-06, "epoch": 17.88063806380638, "percentage": 89.4, "elapsed_time": "6:24:46", "remaining_time": "0:45:36", "throughput": 1485.81, "total_tokens": 34301792} {"current_steps": 162540, "total_steps": 181800, "loss": 0.0134, "lr": 1.6902042522651955e-06, "epoch": 17.88118811881188, "percentage": 89.41, "elapsed_time": "6:24:46", "remaining_time": "0:45:35", "throughput": 1485.81, "total_tokens": 34302816} {"current_steps": 162545, "total_steps": 181800, "loss": 0.0035, "lr": 1.6893368572853618e-06, "epoch": 17.881738173817382, "percentage": 89.41, "elapsed_time": "6:24:47", "remaining_time": "0:45:34", "throughput": 1485.81, "total_tokens": 34303840} {"current_steps": 162550, "total_steps": 181800, "loss": 0.0036, "lr": 1.6884696771487297e-06, "epoch": 17.882288228822883, "percentage": 89.41, "elapsed_time": "6:24:48", "remaining_time": "0:45:34", "throughput": 1485.81, "total_tokens": 34304896} {"current_steps": 162555, "total_steps": 181800, "loss": 0.0024, "lr": 1.6876027118632815e-06, "epoch": 17.882838283828384, "percentage": 89.41, "elapsed_time": "6:24:49", "remaining_time": "0:45:33", "throughput": 1485.81, "total_tokens": 34305952} {"current_steps": 162560, "total_steps": 181800, "loss": 0.0462, "lr": 1.6867359614370192e-06, "epoch": 17.883388338833882, "percentage": 89.42, "elapsed_time": "6:24:49", "remaining_time": "0:45:32", "throughput": 1485.81, "total_tokens": 34306976} {"current_steps": 162565, "total_steps": 181800, "loss": 0.06, "lr": 1.685869425877923e-06, "epoch": 17.883938393839383, "percentage": 89.42, "elapsed_time": "6:24:50", "remaining_time": "0:45:32", "throughput": 1485.82, "total_tokens": 34308096} {"current_steps": 162570, "total_steps": 181800, "loss": 0.0643, "lr": 1.6850031051939774e-06, "epoch": 17.884488448844884, "percentage": 89.42, "elapsed_time": "6:24:51", "remaining_time": "0:45:31", "throughput": 1485.82, "total_tokens": 34309120} {"current_steps": 162575, "total_steps": 181800, "loss": 0.0011, "lr": 1.6841369993931683e-06, "epoch": 17.885038503850385, "percentage": 89.43, "elapsed_time": "6:24:51", "remaining_time": "0:45:30", "throughput": 1485.81, "total_tokens": 34310112} {"current_steps": 162580, "total_steps": 181800, "loss": 0.0093, "lr": 1.6832711084834835e-06, "epoch": 17.885588558855886, "percentage": 89.43, "elapsed_time": "6:24:52", "remaining_time": "0:45:29", "throughput": 1485.81, "total_tokens": 34311136} {"current_steps": 162585, "total_steps": 181800, "loss": 0.0007, "lr": 1.6824054324729027e-06, "epoch": 17.886138613861387, "percentage": 89.43, "elapsed_time": "6:24:53", "remaining_time": "0:45:29", "throughput": 1485.82, "total_tokens": 34312192} {"current_steps": 162590, "total_steps": 181800, "loss": 0.0009, "lr": 1.681539971369403e-06, "epoch": 17.88668866886689, "percentage": 89.43, "elapsed_time": "6:24:53", "remaining_time": "0:45:28", "throughput": 1485.82, "total_tokens": 34313216} {"current_steps": 162595, "total_steps": 181800, "loss": 0.0035, "lr": 1.6806747251809584e-06, "epoch": 17.887238723872386, "percentage": 89.44, "elapsed_time": "6:24:54", "remaining_time": "0:45:27", "throughput": 1485.82, "total_tokens": 34314272} {"current_steps": 162600, "total_steps": 181800, "loss": 0.1435, "lr": 1.6798096939155404e-06, "epoch": 17.887788778877887, "percentage": 89.44, "elapsed_time": "6:24:55", "remaining_time": "0:45:27", "throughput": 1485.82, "total_tokens": 34315296} {"current_steps": 162605, "total_steps": 181800, "loss": 0.0009, "lr": 1.678944877581129e-06, "epoch": 17.888338833883388, "percentage": 89.44, "elapsed_time": "6:24:55", "remaining_time": "0:45:26", "throughput": 1485.82, "total_tokens": 34316384} {"current_steps": 162610, "total_steps": 181800, "loss": 0.0382, "lr": 1.6780802761856979e-06, "epoch": 17.88888888888889, "percentage": 89.44, "elapsed_time": "6:24:56", "remaining_time": "0:45:25", "throughput": 1485.82, "total_tokens": 34317536} {"current_steps": 162615, "total_steps": 181800, "loss": 0.0274, "lr": 1.6772158897372077e-06, "epoch": 17.88943894389439, "percentage": 89.45, "elapsed_time": "6:24:57", "remaining_time": "0:45:24", "throughput": 1485.83, "total_tokens": 34318592} {"current_steps": 162620, "total_steps": 181800, "loss": 0.0669, "lr": 1.676351718243624e-06, "epoch": 17.88998899889989, "percentage": 89.45, "elapsed_time": "6:24:58", "remaining_time": "0:45:24", "throughput": 1485.83, "total_tokens": 34319616} {"current_steps": 162625, "total_steps": 181800, "loss": 0.0025, "lr": 1.6754877617129183e-06, "epoch": 17.89053905390539, "percentage": 89.45, "elapsed_time": "6:24:58", "remaining_time": "0:45:23", "throughput": 1485.83, "total_tokens": 34320768} {"current_steps": 162630, "total_steps": 181800, "loss": 0.0013, "lr": 1.6746240201530456e-06, "epoch": 17.89108910891089, "percentage": 89.46, "elapsed_time": "6:24:59", "remaining_time": "0:45:22", "throughput": 1485.84, "total_tokens": 34321920} {"current_steps": 162635, "total_steps": 181800, "loss": 0.0028, "lr": 1.6737604935719686e-06, "epoch": 17.89163916391639, "percentage": 89.46, "elapsed_time": "6:25:00", "remaining_time": "0:45:22", "throughput": 1485.84, "total_tokens": 34322944} {"current_steps": 162640, "total_steps": 181800, "loss": 0.0026, "lr": 1.6728971819776562e-06, "epoch": 17.892189218921892, "percentage": 89.46, "elapsed_time": "6:25:00", "remaining_time": "0:45:21", "throughput": 1485.84, "total_tokens": 34324000} {"current_steps": 162645, "total_steps": 181800, "loss": 0.0048, "lr": 1.6720340853780491e-06, "epoch": 17.892739273927393, "percentage": 89.46, "elapsed_time": "6:25:01", "remaining_time": "0:45:20", "throughput": 1485.84, "total_tokens": 34325120} {"current_steps": 162650, "total_steps": 181800, "loss": 0.0324, "lr": 1.6711712037811162e-06, "epoch": 17.893289328932894, "percentage": 89.47, "elapsed_time": "6:25:02", "remaining_time": "0:45:19", "throughput": 1485.85, "total_tokens": 34326240} {"current_steps": 162655, "total_steps": 181800, "loss": 0.0543, "lr": 1.6703085371948007e-06, "epoch": 17.893839383938392, "percentage": 89.47, "elapsed_time": "6:25:02", "remaining_time": "0:45:19", "throughput": 1485.85, "total_tokens": 34327264} {"current_steps": 162660, "total_steps": 181800, "loss": 0.0038, "lr": 1.669446085627055e-06, "epoch": 17.894389438943893, "percentage": 89.47, "elapsed_time": "6:25:03", "remaining_time": "0:45:18", "throughput": 1485.84, "total_tokens": 34328256} {"current_steps": 162665, "total_steps": 181800, "loss": 0.0012, "lr": 1.6685838490858364e-06, "epoch": 17.894939493949394, "percentage": 89.47, "elapsed_time": "6:25:04", "remaining_time": "0:45:17", "throughput": 1485.85, "total_tokens": 34329344} {"current_steps": 162670, "total_steps": 181800, "loss": 0.0585, "lr": 1.6677218275790773e-06, "epoch": 17.895489548954895, "percentage": 89.48, "elapsed_time": "6:25:04", "remaining_time": "0:45:17", "throughput": 1485.85, "total_tokens": 34330464} {"current_steps": 162675, "total_steps": 181800, "loss": 0.0111, "lr": 1.6668600211147385e-06, "epoch": 17.896039603960396, "percentage": 89.48, "elapsed_time": "6:25:05", "remaining_time": "0:45:16", "throughput": 1485.86, "total_tokens": 34331616} {"current_steps": 162680, "total_steps": 181800, "loss": 0.0058, "lr": 1.6659984297007465e-06, "epoch": 17.896589658965897, "percentage": 89.48, "elapsed_time": "6:25:06", "remaining_time": "0:45:15", "throughput": 1485.86, "total_tokens": 34332704} {"current_steps": 162685, "total_steps": 181800, "loss": 0.058, "lr": 1.665137053345056e-06, "epoch": 17.8971397139714, "percentage": 89.49, "elapsed_time": "6:25:06", "remaining_time": "0:45:15", "throughput": 1485.86, "total_tokens": 34333728} {"current_steps": 162690, "total_steps": 181800, "loss": 0.0819, "lr": 1.6642758920555972e-06, "epoch": 17.897689768976896, "percentage": 89.49, "elapsed_time": "6:25:07", "remaining_time": "0:45:14", "throughput": 1485.86, "total_tokens": 34334752} {"current_steps": 162695, "total_steps": 181800, "loss": 0.0379, "lr": 1.663414945840308e-06, "epoch": 17.898239823982397, "percentage": 89.49, "elapsed_time": "6:25:08", "remaining_time": "0:45:13", "throughput": 1485.86, "total_tokens": 34335776} {"current_steps": 162700, "total_steps": 181800, "loss": 0.0019, "lr": 1.6625542147071293e-06, "epoch": 17.8987898789879, "percentage": 89.49, "elapsed_time": "6:25:09", "remaining_time": "0:45:12", "throughput": 1485.86, "total_tokens": 34336832} {"current_steps": 162705, "total_steps": 181800, "loss": 0.1256, "lr": 1.661693698663988e-06, "epoch": 17.8993399339934, "percentage": 89.5, "elapsed_time": "6:25:09", "remaining_time": "0:45:12", "throughput": 1485.86, "total_tokens": 34337888} {"current_steps": 162710, "total_steps": 181800, "loss": 0.0203, "lr": 1.6608333977188194e-06, "epoch": 17.8998899889989, "percentage": 89.5, "elapsed_time": "6:25:10", "remaining_time": "0:45:11", "throughput": 1485.86, "total_tokens": 34338880} {"current_steps": 162715, "total_steps": 181800, "loss": 0.0365, "lr": 1.659973311879545e-06, "epoch": 17.9004400440044, "percentage": 89.5, "elapsed_time": "6:25:11", "remaining_time": "0:45:10", "throughput": 1485.86, "total_tokens": 34339936} {"current_steps": 162720, "total_steps": 181800, "loss": 0.075, "lr": 1.6591134411541004e-06, "epoch": 17.900990099009903, "percentage": 89.5, "elapsed_time": "6:25:11", "remaining_time": "0:45:10", "throughput": 1485.86, "total_tokens": 34340992} {"current_steps": 162725, "total_steps": 181800, "loss": 0.0607, "lr": 1.6582537855504065e-06, "epoch": 17.9015401540154, "percentage": 89.51, "elapsed_time": "6:25:12", "remaining_time": "0:45:09", "throughput": 1485.86, "total_tokens": 34342048} {"current_steps": 162730, "total_steps": 181800, "loss": 0.0035, "lr": 1.6573943450763907e-06, "epoch": 17.9020902090209, "percentage": 89.51, "elapsed_time": "6:25:13", "remaining_time": "0:45:08", "throughput": 1485.86, "total_tokens": 34343104} {"current_steps": 162735, "total_steps": 181800, "loss": 0.1132, "lr": 1.6565351197399658e-06, "epoch": 17.902640264026402, "percentage": 89.51, "elapsed_time": "6:25:13", "remaining_time": "0:45:07", "throughput": 1485.86, "total_tokens": 34344096} {"current_steps": 162740, "total_steps": 181800, "loss": 0.0791, "lr": 1.6556761095490592e-06, "epoch": 17.903190319031903, "percentage": 89.52, "elapsed_time": "6:25:14", "remaining_time": "0:45:07", "throughput": 1485.86, "total_tokens": 34345152} {"current_steps": 162745, "total_steps": 181800, "loss": 0.001, "lr": 1.654817314511581e-06, "epoch": 17.903740374037405, "percentage": 89.52, "elapsed_time": "6:25:15", "remaining_time": "0:45:06", "throughput": 1485.87, "total_tokens": 34346208} {"current_steps": 162750, "total_steps": 181800, "loss": 0.0191, "lr": 1.6539587346354469e-06, "epoch": 17.904290429042906, "percentage": 89.52, "elapsed_time": "6:25:15", "remaining_time": "0:45:05", "throughput": 1485.87, "total_tokens": 34347296} {"current_steps": 162755, "total_steps": 181800, "loss": 0.0081, "lr": 1.6531003699285786e-06, "epoch": 17.904840484048403, "percentage": 89.52, "elapsed_time": "6:25:16", "remaining_time": "0:45:05", "throughput": 1485.87, "total_tokens": 34348416} {"current_steps": 162760, "total_steps": 181800, "loss": 0.0011, "lr": 1.6522422203988753e-06, "epoch": 17.905390539053904, "percentage": 89.53, "elapsed_time": "6:25:17", "remaining_time": "0:45:04", "throughput": 1485.87, "total_tokens": 34349408} {"current_steps": 162765, "total_steps": 181800, "loss": 0.0562, "lr": 1.6513842860542583e-06, "epoch": 17.905940594059405, "percentage": 89.53, "elapsed_time": "6:25:18", "remaining_time": "0:45:03", "throughput": 1485.87, "total_tokens": 34350432} {"current_steps": 162770, "total_steps": 181800, "loss": 0.0977, "lr": 1.6505265669026243e-06, "epoch": 17.906490649064907, "percentage": 89.53, "elapsed_time": "6:25:18", "remaining_time": "0:45:02", "throughput": 1485.87, "total_tokens": 34351424} {"current_steps": 162775, "total_steps": 181800, "loss": 0.0035, "lr": 1.6496690629518834e-06, "epoch": 17.907040704070408, "percentage": 89.54, "elapsed_time": "6:25:19", "remaining_time": "0:45:02", "throughput": 1485.87, "total_tokens": 34352480} {"current_steps": 162780, "total_steps": 181800, "loss": 0.0072, "lr": 1.6488117742099406e-06, "epoch": 17.90759075907591, "percentage": 89.54, "elapsed_time": "6:25:20", "remaining_time": "0:45:01", "throughput": 1485.87, "total_tokens": 34353568} {"current_steps": 162785, "total_steps": 181800, "loss": 0.0015, "lr": 1.6479547006846925e-06, "epoch": 17.90814081408141, "percentage": 89.54, "elapsed_time": "6:25:20", "remaining_time": "0:45:00", "throughput": 1485.87, "total_tokens": 34354592} {"current_steps": 162790, "total_steps": 181800, "loss": 0.0006, "lr": 1.6470978423840406e-06, "epoch": 17.908690869086907, "percentage": 89.54, "elapsed_time": "6:25:21", "remaining_time": "0:45:00", "throughput": 1485.88, "total_tokens": 34355648} {"current_steps": 162795, "total_steps": 181800, "loss": 0.017, "lr": 1.6462411993158815e-06, "epoch": 17.90924092409241, "percentage": 89.55, "elapsed_time": "6:25:22", "remaining_time": "0:44:59", "throughput": 1485.88, "total_tokens": 34356736} {"current_steps": 162800, "total_steps": 181800, "loss": 0.0024, "lr": 1.6453847714881149e-06, "epoch": 17.90979097909791, "percentage": 89.55, "elapsed_time": "6:25:22", "remaining_time": "0:44:58", "throughput": 1485.88, "total_tokens": 34357696} {"current_steps": 162805, "total_steps": 181800, "loss": 0.0249, "lr": 1.6445285589086257e-06, "epoch": 17.91034103410341, "percentage": 89.55, "elapsed_time": "6:25:23", "remaining_time": "0:44:57", "throughput": 1485.88, "total_tokens": 34358752} {"current_steps": 162810, "total_steps": 181800, "loss": 0.0115, "lr": 1.6436725615853105e-06, "epoch": 17.91089108910891, "percentage": 89.55, "elapsed_time": "6:25:24", "remaining_time": "0:44:57", "throughput": 1485.88, "total_tokens": 34359808} {"current_steps": 162815, "total_steps": 181800, "loss": 0.0152, "lr": 1.6428167795260601e-06, "epoch": 17.911441144114413, "percentage": 89.56, "elapsed_time": "6:25:24", "remaining_time": "0:44:56", "throughput": 1485.88, "total_tokens": 34360864} {"current_steps": 162820, "total_steps": 181800, "loss": 0.0038, "lr": 1.6419612127387574e-06, "epoch": 17.91199119911991, "percentage": 89.56, "elapsed_time": "6:25:25", "remaining_time": "0:44:55", "throughput": 1485.88, "total_tokens": 34361952} {"current_steps": 162825, "total_steps": 181800, "loss": 0.0045, "lr": 1.641105861231293e-06, "epoch": 17.91254125412541, "percentage": 89.56, "elapsed_time": "6:25:26", "remaining_time": "0:44:55", "throughput": 1485.88, "total_tokens": 34363008} {"current_steps": 162830, "total_steps": 181800, "loss": 0.0156, "lr": 1.6402507250115411e-06, "epoch": 17.913091309130913, "percentage": 89.57, "elapsed_time": "6:25:26", "remaining_time": "0:44:54", "throughput": 1485.89, "total_tokens": 34364032} {"current_steps": 162835, "total_steps": 181800, "loss": 0.0011, "lr": 1.639395804087393e-06, "epoch": 17.913641364136414, "percentage": 89.57, "elapsed_time": "6:25:27", "remaining_time": "0:44:53", "throughput": 1485.89, "total_tokens": 34365088} {"current_steps": 162840, "total_steps": 181800, "loss": 0.0024, "lr": 1.6385410984667254e-06, "epoch": 17.914191419141915, "percentage": 89.57, "elapsed_time": "6:25:28", "remaining_time": "0:44:52", "throughput": 1485.89, "total_tokens": 34366208} {"current_steps": 162845, "total_steps": 181800, "loss": 0.0043, "lr": 1.6376866081574127e-06, "epoch": 17.914741474147416, "percentage": 89.57, "elapsed_time": "6:25:29", "remaining_time": "0:44:52", "throughput": 1485.89, "total_tokens": 34367232} {"current_steps": 162850, "total_steps": 181800, "loss": 0.0062, "lr": 1.6368323331673346e-06, "epoch": 17.915291529152917, "percentage": 89.58, "elapsed_time": "6:25:29", "remaining_time": "0:44:51", "throughput": 1485.89, "total_tokens": 34368320} {"current_steps": 162855, "total_steps": 181800, "loss": 0.0413, "lr": 1.6359782735043627e-06, "epoch": 17.915841584158414, "percentage": 89.58, "elapsed_time": "6:25:30", "remaining_time": "0:44:50", "throughput": 1485.89, "total_tokens": 34369344} {"current_steps": 162860, "total_steps": 181800, "loss": 0.0075, "lr": 1.6351244291763629e-06, "epoch": 17.916391639163916, "percentage": 89.58, "elapsed_time": "6:25:31", "remaining_time": "0:44:50", "throughput": 1485.89, "total_tokens": 34370400} {"current_steps": 162865, "total_steps": 181800, "loss": 0.0024, "lr": 1.634270800191212e-06, "epoch": 17.916941694169417, "percentage": 89.58, "elapsed_time": "6:25:31", "remaining_time": "0:44:49", "throughput": 1485.9, "total_tokens": 34371456} {"current_steps": 162870, "total_steps": 181800, "loss": 0.001, "lr": 1.6334173865567737e-06, "epoch": 17.917491749174918, "percentage": 89.59, "elapsed_time": "6:25:32", "remaining_time": "0:44:48", "throughput": 1485.9, "total_tokens": 34372512} {"current_steps": 162875, "total_steps": 181800, "loss": 0.0011, "lr": 1.6325641882809188e-06, "epoch": 17.91804180418042, "percentage": 89.59, "elapsed_time": "6:25:33", "remaining_time": "0:44:47", "throughput": 1485.89, "total_tokens": 34373472} {"current_steps": 162880, "total_steps": 181800, "loss": 0.0074, "lr": 1.6317112053715083e-06, "epoch": 17.91859185918592, "percentage": 89.59, "elapsed_time": "6:25:33", "remaining_time": "0:44:47", "throughput": 1485.9, "total_tokens": 34374528} {"current_steps": 162885, "total_steps": 181800, "loss": 0.0993, "lr": 1.6308584378363968e-06, "epoch": 17.919141914191417, "percentage": 89.6, "elapsed_time": "6:25:34", "remaining_time": "0:44:46", "throughput": 1485.9, "total_tokens": 34375552} {"current_steps": 162890, "total_steps": 181800, "loss": 0.0447, "lr": 1.6300058856834498e-06, "epoch": 17.91969196919692, "percentage": 89.6, "elapsed_time": "6:25:35", "remaining_time": "0:44:45", "throughput": 1485.9, "total_tokens": 34376672} {"current_steps": 162895, "total_steps": 181800, "loss": 0.0021, "lr": 1.6291535489205256e-06, "epoch": 17.92024202420242, "percentage": 89.6, "elapsed_time": "6:25:35", "remaining_time": "0:44:45", "throughput": 1485.9, "total_tokens": 34377760} {"current_steps": 162900, "total_steps": 181800, "loss": 0.0076, "lr": 1.6283014275554814e-06, "epoch": 17.92079207920792, "percentage": 89.6, "elapsed_time": "6:25:36", "remaining_time": "0:44:44", "throughput": 1485.9, "total_tokens": 34378816} {"current_steps": 162905, "total_steps": 181800, "loss": 0.0274, "lr": 1.6274495215961694e-06, "epoch": 17.921342134213422, "percentage": 89.61, "elapsed_time": "6:25:37", "remaining_time": "0:44:43", "throughput": 1485.9, "total_tokens": 34379840} {"current_steps": 162910, "total_steps": 181800, "loss": 0.0528, "lr": 1.626597831050436e-06, "epoch": 17.921892189218923, "percentage": 89.61, "elapsed_time": "6:25:38", "remaining_time": "0:44:42", "throughput": 1485.9, "total_tokens": 34380896} {"current_steps": 162915, "total_steps": 181800, "loss": 0.0471, "lr": 1.625746355926136e-06, "epoch": 17.922442244224424, "percentage": 89.61, "elapsed_time": "6:25:38", "remaining_time": "0:44:42", "throughput": 1485.91, "total_tokens": 34382016} {"current_steps": 162920, "total_steps": 181800, "loss": 0.0094, "lr": 1.6248950962311133e-06, "epoch": 17.92299229922992, "percentage": 89.61, "elapsed_time": "6:25:39", "remaining_time": "0:44:41", "throughput": 1485.91, "total_tokens": 34383072} {"current_steps": 162925, "total_steps": 181800, "loss": 0.0058, "lr": 1.624044051973217e-06, "epoch": 17.923542354235423, "percentage": 89.62, "elapsed_time": "6:25:40", "remaining_time": "0:44:40", "throughput": 1485.91, "total_tokens": 34384160} {"current_steps": 162930, "total_steps": 181800, "loss": 0.0024, "lr": 1.6231932231602936e-06, "epoch": 17.924092409240924, "percentage": 89.62, "elapsed_time": "6:25:40", "remaining_time": "0:44:40", "throughput": 1485.91, "total_tokens": 34385216} {"current_steps": 162935, "total_steps": 181800, "loss": 0.0014, "lr": 1.622342609800176e-06, "epoch": 17.924642464246425, "percentage": 89.62, "elapsed_time": "6:25:41", "remaining_time": "0:44:39", "throughput": 1485.91, "total_tokens": 34386208} {"current_steps": 162940, "total_steps": 181800, "loss": 0.0185, "lr": 1.6214922119007159e-06, "epoch": 17.925192519251926, "percentage": 89.63, "elapsed_time": "6:25:42", "remaining_time": "0:44:38", "throughput": 1485.92, "total_tokens": 34387328} {"current_steps": 162945, "total_steps": 181800, "loss": 0.0028, "lr": 1.6206420294697377e-06, "epoch": 17.925742574257427, "percentage": 89.63, "elapsed_time": "6:25:42", "remaining_time": "0:44:37", "throughput": 1485.92, "total_tokens": 34388416} {"current_steps": 162950, "total_steps": 181800, "loss": 0.1294, "lr": 1.6197920625150826e-06, "epoch": 17.926292629262925, "percentage": 89.63, "elapsed_time": "6:25:43", "remaining_time": "0:44:37", "throughput": 1485.92, "total_tokens": 34389472} {"current_steps": 162955, "total_steps": 181800, "loss": 0.0028, "lr": 1.6189423110445884e-06, "epoch": 17.926842684268426, "percentage": 89.63, "elapsed_time": "6:25:44", "remaining_time": "0:44:36", "throughput": 1485.92, "total_tokens": 34390496} {"current_steps": 162960, "total_steps": 181800, "loss": 0.0096, "lr": 1.6180927750660823e-06, "epoch": 17.927392739273927, "percentage": 89.64, "elapsed_time": "6:25:44", "remaining_time": "0:44:35", "throughput": 1485.92, "total_tokens": 34391488} {"current_steps": 162965, "total_steps": 181800, "loss": 0.0043, "lr": 1.617243454587397e-06, "epoch": 17.927942794279428, "percentage": 89.64, "elapsed_time": "6:25:45", "remaining_time": "0:44:35", "throughput": 1485.92, "total_tokens": 34392576} {"current_steps": 162970, "total_steps": 181800, "loss": 0.0018, "lr": 1.6163943496163597e-06, "epoch": 17.92849284928493, "percentage": 89.64, "elapsed_time": "6:25:46", "remaining_time": "0:44:34", "throughput": 1485.92, "total_tokens": 34393600} {"current_steps": 162975, "total_steps": 181800, "loss": 0.0037, "lr": 1.6155454601607916e-06, "epoch": 17.92904290429043, "percentage": 89.65, "elapsed_time": "6:25:46", "remaining_time": "0:44:33", "throughput": 1485.92, "total_tokens": 34394624} {"current_steps": 162980, "total_steps": 181800, "loss": 0.0097, "lr": 1.6146967862285201e-06, "epoch": 17.92959295929593, "percentage": 89.65, "elapsed_time": "6:25:47", "remaining_time": "0:44:32", "throughput": 1485.92, "total_tokens": 34395680} {"current_steps": 162985, "total_steps": 181800, "loss": 0.0039, "lr": 1.6138483278273663e-06, "epoch": 17.93014301430143, "percentage": 89.65, "elapsed_time": "6:25:48", "remaining_time": "0:44:32", "throughput": 1485.92, "total_tokens": 34396704} {"current_steps": 162990, "total_steps": 181800, "loss": 0.0307, "lr": 1.613000084965155e-06, "epoch": 17.93069306930693, "percentage": 89.65, "elapsed_time": "6:25:49", "remaining_time": "0:44:31", "throughput": 1485.93, "total_tokens": 34397760} {"current_steps": 162995, "total_steps": 181800, "loss": 0.0015, "lr": 1.612152057649699e-06, "epoch": 17.93124312431243, "percentage": 89.66, "elapsed_time": "6:25:49", "remaining_time": "0:44:30", "throughput": 1485.93, "total_tokens": 34398816} {"current_steps": 163000, "total_steps": 181800, "loss": 0.0019, "lr": 1.6113042458888118e-06, "epoch": 17.931793179317932, "percentage": 89.66, "elapsed_time": "6:25:50", "remaining_time": "0:44:30", "throughput": 1485.93, "total_tokens": 34399872} {"current_steps": 163005, "total_steps": 181800, "loss": 0.0008, "lr": 1.6104566496903118e-06, "epoch": 17.932343234323433, "percentage": 89.66, "elapsed_time": "6:25:51", "remaining_time": "0:44:29", "throughput": 1485.93, "total_tokens": 34400992} {"current_steps": 163010, "total_steps": 181800, "loss": 0.0004, "lr": 1.609609269062007e-06, "epoch": 17.932893289328934, "percentage": 89.66, "elapsed_time": "6:25:51", "remaining_time": "0:44:28", "throughput": 1485.93, "total_tokens": 34402080} {"current_steps": 163015, "total_steps": 181800, "loss": 0.1349, "lr": 1.6087621040117157e-06, "epoch": 17.933443344334435, "percentage": 89.67, "elapsed_time": "6:25:52", "remaining_time": "0:44:27", "throughput": 1485.94, "total_tokens": 34403168} {"current_steps": 163020, "total_steps": 181800, "loss": 0.0328, "lr": 1.6079151545472377e-06, "epoch": 17.933993399339933, "percentage": 89.67, "elapsed_time": "6:25:53", "remaining_time": "0:44:27", "throughput": 1485.94, "total_tokens": 34404224} {"current_steps": 163025, "total_steps": 181800, "loss": 0.0054, "lr": 1.6070684206763775e-06, "epoch": 17.934543454345434, "percentage": 89.67, "elapsed_time": "6:25:53", "remaining_time": "0:44:26", "throughput": 1485.94, "total_tokens": 34405344} {"current_steps": 163030, "total_steps": 181800, "loss": 0.0046, "lr": 1.6062219024069485e-06, "epoch": 17.935093509350935, "percentage": 89.68, "elapsed_time": "6:25:54", "remaining_time": "0:44:25", "throughput": 1485.94, "total_tokens": 34406432} {"current_steps": 163035, "total_steps": 181800, "loss": 0.0031, "lr": 1.6053755997467417e-06, "epoch": 17.935643564356436, "percentage": 89.68, "elapsed_time": "6:25:55", "remaining_time": "0:44:25", "throughput": 1485.95, "total_tokens": 34407488} {"current_steps": 163040, "total_steps": 181800, "loss": 0.0083, "lr": 1.604529512703562e-06, "epoch": 17.936193619361937, "percentage": 89.68, "elapsed_time": "6:25:55", "remaining_time": "0:44:24", "throughput": 1485.94, "total_tokens": 34408448} {"current_steps": 163045, "total_steps": 181800, "loss": 0.0014, "lr": 1.6036836412852113e-06, "epoch": 17.936743674367438, "percentage": 89.68, "elapsed_time": "6:25:56", "remaining_time": "0:44:23", "throughput": 1485.94, "total_tokens": 34409440} {"current_steps": 163050, "total_steps": 181800, "loss": 0.0029, "lr": 1.602837985499478e-06, "epoch": 17.937293729372936, "percentage": 89.69, "elapsed_time": "6:25:57", "remaining_time": "0:44:22", "throughput": 1485.94, "total_tokens": 34410432} {"current_steps": 163055, "total_steps": 181800, "loss": 0.0034, "lr": 1.601992545354164e-06, "epoch": 17.937843784378437, "percentage": 89.69, "elapsed_time": "6:25:58", "remaining_time": "0:44:22", "throughput": 1485.94, "total_tokens": 34411488} {"current_steps": 163060, "total_steps": 181800, "loss": 0.0071, "lr": 1.601147320857052e-06, "epoch": 17.938393839383938, "percentage": 89.69, "elapsed_time": "6:25:58", "remaining_time": "0:44:21", "throughput": 1485.94, "total_tokens": 34412512} {"current_steps": 163065, "total_steps": 181800, "loss": 0.0064, "lr": 1.600302312015939e-06, "epoch": 17.93894389438944, "percentage": 89.69, "elapsed_time": "6:25:59", "remaining_time": "0:44:20", "throughput": 1485.95, "total_tokens": 34413664} {"current_steps": 163070, "total_steps": 181800, "loss": 0.0658, "lr": 1.599457518838615e-06, "epoch": 17.93949394939494, "percentage": 89.7, "elapsed_time": "6:26:00", "remaining_time": "0:44:20", "throughput": 1485.95, "total_tokens": 34414784} {"current_steps": 163075, "total_steps": 181800, "loss": 0.0024, "lr": 1.5986129413328582e-06, "epoch": 17.94004400440044, "percentage": 89.7, "elapsed_time": "6:26:00", "remaining_time": "0:44:19", "throughput": 1485.95, "total_tokens": 34415904} {"current_steps": 163080, "total_steps": 181800, "loss": 0.1081, "lr": 1.5977685795064618e-06, "epoch": 17.94059405940594, "percentage": 89.7, "elapsed_time": "6:26:01", "remaining_time": "0:44:18", "throughput": 1485.96, "total_tokens": 34416960} {"current_steps": 163085, "total_steps": 181800, "loss": 0.0739, "lr": 1.5969244333671974e-06, "epoch": 17.94114411441144, "percentage": 89.71, "elapsed_time": "6:26:02", "remaining_time": "0:44:18", "throughput": 1485.95, "total_tokens": 34417952} {"current_steps": 163090, "total_steps": 181800, "loss": 0.001, "lr": 1.596080502922856e-06, "epoch": 17.94169416941694, "percentage": 89.71, "elapsed_time": "6:26:02", "remaining_time": "0:44:17", "throughput": 1485.95, "total_tokens": 34418944} {"current_steps": 163095, "total_steps": 181800, "loss": 0.0012, "lr": 1.5952367881812064e-06, "epoch": 17.942244224422442, "percentage": 89.71, "elapsed_time": "6:26:03", "remaining_time": "0:44:16", "throughput": 1485.95, "total_tokens": 34420000} {"current_steps": 163100, "total_steps": 181800, "loss": 0.0275, "lr": 1.5943932891500257e-06, "epoch": 17.942794279427943, "percentage": 89.71, "elapsed_time": "6:26:04", "remaining_time": "0:44:15", "throughput": 1485.96, "total_tokens": 34421088} {"current_steps": 163105, "total_steps": 181800, "loss": 0.0014, "lr": 1.5935500058370995e-06, "epoch": 17.943344334433444, "percentage": 89.72, "elapsed_time": "6:26:04", "remaining_time": "0:44:15", "throughput": 1485.96, "total_tokens": 34422176} {"current_steps": 163110, "total_steps": 181800, "loss": 0.0342, "lr": 1.592706938250188e-06, "epoch": 17.943894389438945, "percentage": 89.72, "elapsed_time": "6:26:05", "remaining_time": "0:44:14", "throughput": 1485.96, "total_tokens": 34423200} {"current_steps": 163115, "total_steps": 181800, "loss": 0.078, "lr": 1.5918640863970602e-06, "epoch": 17.944444444444443, "percentage": 89.72, "elapsed_time": "6:26:06", "remaining_time": "0:44:13", "throughput": 1485.96, "total_tokens": 34424224} {"current_steps": 163120, "total_steps": 181800, "loss": 0.1259, "lr": 1.5910214502854958e-06, "epoch": 17.944994499449944, "percentage": 89.72, "elapsed_time": "6:26:07", "remaining_time": "0:44:13", "throughput": 1485.96, "total_tokens": 34425280} {"current_steps": 163125, "total_steps": 181800, "loss": 0.0013, "lr": 1.5901790299232444e-06, "epoch": 17.945544554455445, "percentage": 89.73, "elapsed_time": "6:26:07", "remaining_time": "0:44:12", "throughput": 1485.96, "total_tokens": 34426304} {"current_steps": 163130, "total_steps": 181800, "loss": 0.0582, "lr": 1.5893368253180884e-06, "epoch": 17.946094609460946, "percentage": 89.73, "elapsed_time": "6:26:08", "remaining_time": "0:44:11", "throughput": 1485.96, "total_tokens": 34427392} {"current_steps": 163135, "total_steps": 181800, "loss": 0.0209, "lr": 1.5884948364777802e-06, "epoch": 17.946644664466447, "percentage": 89.73, "elapsed_time": "6:26:09", "remaining_time": "0:44:10", "throughput": 1485.96, "total_tokens": 34428448} {"current_steps": 163140, "total_steps": 181800, "loss": 0.0004, "lr": 1.5876530634100772e-06, "epoch": 17.94719471947195, "percentage": 89.74, "elapsed_time": "6:26:09", "remaining_time": "0:44:10", "throughput": 1485.96, "total_tokens": 34429472} {"current_steps": 163145, "total_steps": 181800, "loss": 0.005, "lr": 1.5868115061227457e-06, "epoch": 17.94774477447745, "percentage": 89.74, "elapsed_time": "6:26:10", "remaining_time": "0:44:09", "throughput": 1485.97, "total_tokens": 34430528} {"current_steps": 163150, "total_steps": 181800, "loss": 0.05, "lr": 1.5859701646235347e-06, "epoch": 17.948294829482947, "percentage": 89.74, "elapsed_time": "6:26:11", "remaining_time": "0:44:08", "throughput": 1485.97, "total_tokens": 34431616} {"current_steps": 163155, "total_steps": 181800, "loss": 0.0845, "lr": 1.5851290389202022e-06, "epoch": 17.948844884488448, "percentage": 89.74, "elapsed_time": "6:26:11", "remaining_time": "0:44:08", "throughput": 1485.97, "total_tokens": 34432768} {"current_steps": 163160, "total_steps": 181800, "loss": 0.018, "lr": 1.5842881290205031e-06, "epoch": 17.94939493949395, "percentage": 89.75, "elapsed_time": "6:26:12", "remaining_time": "0:44:07", "throughput": 1485.97, "total_tokens": 34433728} {"current_steps": 163165, "total_steps": 181800, "loss": 0.0145, "lr": 1.5834474349321783e-06, "epoch": 17.94994499449945, "percentage": 89.75, "elapsed_time": "6:26:13", "remaining_time": "0:44:06", "throughput": 1485.97, "total_tokens": 34434784} {"current_steps": 163170, "total_steps": 181800, "loss": 0.1653, "lr": 1.582606956662988e-06, "epoch": 17.95049504950495, "percentage": 89.75, "elapsed_time": "6:26:13", "remaining_time": "0:44:05", "throughput": 1485.97, "total_tokens": 34435808} {"current_steps": 163175, "total_steps": 181800, "loss": 0.048, "lr": 1.5817666942206683e-06, "epoch": 17.951045104510452, "percentage": 89.76, "elapsed_time": "6:26:14", "remaining_time": "0:44:05", "throughput": 1485.97, "total_tokens": 34436832} {"current_steps": 163180, "total_steps": 181800, "loss": 0.1539, "lr": 1.580926647612968e-06, "epoch": 17.95159515951595, "percentage": 89.76, "elapsed_time": "6:26:15", "remaining_time": "0:44:04", "throughput": 1485.97, "total_tokens": 34437856} {"current_steps": 163185, "total_steps": 181800, "loss": 0.0011, "lr": 1.580086816847634e-06, "epoch": 17.95214521452145, "percentage": 89.76, "elapsed_time": "6:26:15", "remaining_time": "0:44:03", "throughput": 1485.97, "total_tokens": 34438880} {"current_steps": 163190, "total_steps": 181800, "loss": 0.0576, "lr": 1.5792472019323962e-06, "epoch": 17.952695269526952, "percentage": 89.76, "elapsed_time": "6:26:16", "remaining_time": "0:44:03", "throughput": 1485.97, "total_tokens": 34439936} {"current_steps": 163195, "total_steps": 181800, "loss": 0.0829, "lr": 1.5784078028750038e-06, "epoch": 17.953245324532453, "percentage": 89.77, "elapsed_time": "6:26:17", "remaining_time": "0:44:02", "throughput": 1485.98, "total_tokens": 34440992} {"current_steps": 163200, "total_steps": 181800, "loss": 0.0051, "lr": 1.577568619683184e-06, "epoch": 17.953795379537954, "percentage": 89.77, "elapsed_time": "6:26:18", "remaining_time": "0:44:01", "throughput": 1485.98, "total_tokens": 34442016} {"current_steps": 163205, "total_steps": 181800, "loss": 0.0716, "lr": 1.576729652364678e-06, "epoch": 17.954345434543455, "percentage": 89.77, "elapsed_time": "6:26:18", "remaining_time": "0:44:00", "throughput": 1485.98, "total_tokens": 34443136} {"current_steps": 163210, "total_steps": 181800, "loss": 0.003, "lr": 1.5758909009272127e-06, "epoch": 17.954895489548957, "percentage": 89.77, "elapsed_time": "6:26:19", "remaining_time": "0:44:00", "throughput": 1485.98, "total_tokens": 34444192} {"current_steps": 163215, "total_steps": 181800, "loss": 0.0338, "lr": 1.5750523653785181e-06, "epoch": 17.955445544554454, "percentage": 89.78, "elapsed_time": "6:26:20", "remaining_time": "0:43:59", "throughput": 1485.98, "total_tokens": 34445248} {"current_steps": 163220, "total_steps": 181800, "loss": 0.01, "lr": 1.5742140457263328e-06, "epoch": 17.955995599559955, "percentage": 89.78, "elapsed_time": "6:26:20", "remaining_time": "0:43:58", "throughput": 1485.98, "total_tokens": 34446336} {"current_steps": 163225, "total_steps": 181800, "loss": 0.0506, "lr": 1.5733759419783696e-06, "epoch": 17.956545654565456, "percentage": 89.78, "elapsed_time": "6:26:21", "remaining_time": "0:43:58", "throughput": 1485.99, "total_tokens": 34447392} {"current_steps": 163230, "total_steps": 181800, "loss": 0.0027, "lr": 1.572538054142364e-06, "epoch": 17.957095709570957, "percentage": 89.79, "elapsed_time": "6:26:22", "remaining_time": "0:43:57", "throughput": 1485.99, "total_tokens": 34448416} {"current_steps": 163235, "total_steps": 181800, "loss": 0.048, "lr": 1.5717003822260323e-06, "epoch": 17.95764576457646, "percentage": 89.79, "elapsed_time": "6:26:22", "remaining_time": "0:43:56", "throughput": 1485.99, "total_tokens": 34449472} {"current_steps": 163240, "total_steps": 181800, "loss": 0.1549, "lr": 1.5708629262370905e-06, "epoch": 17.95819581958196, "percentage": 89.79, "elapsed_time": "6:26:23", "remaining_time": "0:43:55", "throughput": 1485.99, "total_tokens": 34450592} {"current_steps": 163245, "total_steps": 181800, "loss": 0.0793, "lr": 1.5700256861832713e-06, "epoch": 17.958745874587457, "percentage": 89.79, "elapsed_time": "6:26:24", "remaining_time": "0:43:55", "throughput": 1485.99, "total_tokens": 34451552} {"current_steps": 163250, "total_steps": 181800, "loss": 0.0537, "lr": 1.5691886620722768e-06, "epoch": 17.959295929592958, "percentage": 89.8, "elapsed_time": "6:26:24", "remaining_time": "0:43:54", "throughput": 1485.99, "total_tokens": 34452576} {"current_steps": 163255, "total_steps": 181800, "loss": 0.099, "lr": 1.5683518539118314e-06, "epoch": 17.95984598459846, "percentage": 89.8, "elapsed_time": "6:26:25", "remaining_time": "0:43:53", "throughput": 1485.99, "total_tokens": 34453568} {"current_steps": 163260, "total_steps": 181800, "loss": 0.1025, "lr": 1.5675152617096427e-06, "epoch": 17.96039603960396, "percentage": 89.8, "elapsed_time": "6:26:26", "remaining_time": "0:43:53", "throughput": 1485.99, "total_tokens": 34454560} {"current_steps": 163265, "total_steps": 181800, "loss": 0.0008, "lr": 1.5666788854734187e-06, "epoch": 17.96094609460946, "percentage": 89.8, "elapsed_time": "6:26:27", "remaining_time": "0:43:52", "throughput": 1485.99, "total_tokens": 34455616} {"current_steps": 163270, "total_steps": 181800, "loss": 0.0117, "lr": 1.5658427252108699e-06, "epoch": 17.961496149614963, "percentage": 89.81, "elapsed_time": "6:26:27", "remaining_time": "0:43:51", "throughput": 1485.99, "total_tokens": 34456704} {"current_steps": 163275, "total_steps": 181800, "loss": 0.0019, "lr": 1.5650067809297037e-06, "epoch": 17.962046204620464, "percentage": 89.81, "elapsed_time": "6:26:28", "remaining_time": "0:43:50", "throughput": 1485.99, "total_tokens": 34457728} {"current_steps": 163280, "total_steps": 181800, "loss": 0.0038, "lr": 1.5641710526376307e-06, "epoch": 17.96259625962596, "percentage": 89.81, "elapsed_time": "6:26:29", "remaining_time": "0:43:50", "throughput": 1485.99, "total_tokens": 34458816} {"current_steps": 163285, "total_steps": 181800, "loss": 0.0166, "lr": 1.5633355403423477e-06, "epoch": 17.963146314631462, "percentage": 89.82, "elapsed_time": "6:26:29", "remaining_time": "0:43:49", "throughput": 1485.99, "total_tokens": 34459840} {"current_steps": 163290, "total_steps": 181800, "loss": 0.0021, "lr": 1.5625002440515484e-06, "epoch": 17.963696369636963, "percentage": 89.82, "elapsed_time": "6:26:30", "remaining_time": "0:43:48", "throughput": 1485.99, "total_tokens": 34460864} {"current_steps": 163295, "total_steps": 181800, "loss": 0.0074, "lr": 1.5616651637729436e-06, "epoch": 17.964246424642464, "percentage": 89.82, "elapsed_time": "6:26:31", "remaining_time": "0:43:48", "throughput": 1485.99, "total_tokens": 34461856} {"current_steps": 163300, "total_steps": 181800, "loss": 0.0344, "lr": 1.560830299514221e-06, "epoch": 17.964796479647966, "percentage": 89.82, "elapsed_time": "6:26:31", "remaining_time": "0:43:47", "throughput": 1485.99, "total_tokens": 34462912} {"current_steps": 163305, "total_steps": 181800, "loss": 0.1803, "lr": 1.5599956512830777e-06, "epoch": 17.965346534653467, "percentage": 89.83, "elapsed_time": "6:26:32", "remaining_time": "0:43:46", "throughput": 1485.99, "total_tokens": 34463936} {"current_steps": 163310, "total_steps": 181800, "loss": 0.0904, "lr": 1.5591612190872102e-06, "epoch": 17.965896589658964, "percentage": 89.83, "elapsed_time": "6:26:33", "remaining_time": "0:43:45", "throughput": 1485.99, "total_tokens": 34464960} {"current_steps": 163315, "total_steps": 181800, "loss": 0.0846, "lr": 1.5583270029343011e-06, "epoch": 17.966446644664465, "percentage": 89.83, "elapsed_time": "6:26:33", "remaining_time": "0:43:45", "throughput": 1485.99, "total_tokens": 34466016} {"current_steps": 163320, "total_steps": 181800, "loss": 0.006, "lr": 1.55749300283205e-06, "epoch": 17.966996699669966, "percentage": 89.83, "elapsed_time": "6:26:34", "remaining_time": "0:43:44", "throughput": 1486.0, "total_tokens": 34467104} {"current_steps": 163325, "total_steps": 181800, "loss": 0.0017, "lr": 1.5566592187881313e-06, "epoch": 17.967546754675467, "percentage": 89.84, "elapsed_time": "6:26:35", "remaining_time": "0:43:43", "throughput": 1486.0, "total_tokens": 34468192} {"current_steps": 163330, "total_steps": 181800, "loss": 0.0006, "lr": 1.5558256508102358e-06, "epoch": 17.96809680968097, "percentage": 89.84, "elapsed_time": "6:26:36", "remaining_time": "0:43:43", "throughput": 1486.0, "total_tokens": 34469248} {"current_steps": 163335, "total_steps": 181800, "loss": 0.0025, "lr": 1.5549922989060495e-06, "epoch": 17.96864686468647, "percentage": 89.84, "elapsed_time": "6:26:36", "remaining_time": "0:43:42", "throughput": 1486.0, "total_tokens": 34470336} {"current_steps": 163340, "total_steps": 181800, "loss": 0.0321, "lr": 1.5541591630832465e-06, "epoch": 17.96919691969197, "percentage": 89.85, "elapsed_time": "6:26:37", "remaining_time": "0:43:41", "throughput": 1486.0, "total_tokens": 34471392} {"current_steps": 163345, "total_steps": 181800, "loss": 0.0125, "lr": 1.5533262433495093e-06, "epoch": 17.96974697469747, "percentage": 89.85, "elapsed_time": "6:26:38", "remaining_time": "0:43:40", "throughput": 1486.0, "total_tokens": 34472448} {"current_steps": 163350, "total_steps": 181800, "loss": 0.0374, "lr": 1.5524935397125156e-06, "epoch": 17.97029702970297, "percentage": 89.85, "elapsed_time": "6:26:38", "remaining_time": "0:43:40", "throughput": 1486.01, "total_tokens": 34473504} {"current_steps": 163355, "total_steps": 181800, "loss": 0.007, "lr": 1.5516610521799313e-06, "epoch": 17.97084708470847, "percentage": 89.85, "elapsed_time": "6:26:39", "remaining_time": "0:43:39", "throughput": 1486.01, "total_tokens": 34474560} {"current_steps": 163360, "total_steps": 181800, "loss": 0.0349, "lr": 1.550828780759439e-06, "epoch": 17.97139713971397, "percentage": 89.86, "elapsed_time": "6:26:40", "remaining_time": "0:43:38", "throughput": 1486.01, "total_tokens": 34475584} {"current_steps": 163365, "total_steps": 181800, "loss": 0.0591, "lr": 1.549996725458705e-06, "epoch": 17.971947194719473, "percentage": 89.86, "elapsed_time": "6:26:40", "remaining_time": "0:43:38", "throughput": 1486.01, "total_tokens": 34476672} {"current_steps": 163370, "total_steps": 181800, "loss": 0.0283, "lr": 1.5491648862854008e-06, "epoch": 17.972497249724974, "percentage": 89.86, "elapsed_time": "6:26:41", "remaining_time": "0:43:37", "throughput": 1486.01, "total_tokens": 34477696} {"current_steps": 163375, "total_steps": 181800, "loss": 0.0061, "lr": 1.5483332632471925e-06, "epoch": 17.97304730473047, "percentage": 89.87, "elapsed_time": "6:26:42", "remaining_time": "0:43:36", "throughput": 1486.01, "total_tokens": 34478720} {"current_steps": 163380, "total_steps": 181800, "loss": 0.0025, "lr": 1.547501856351738e-06, "epoch": 17.973597359735972, "percentage": 89.87, "elapsed_time": "6:26:42", "remaining_time": "0:43:35", "throughput": 1486.01, "total_tokens": 34479808} {"current_steps": 163385, "total_steps": 181800, "loss": 0.0064, "lr": 1.546670665606706e-06, "epoch": 17.974147414741473, "percentage": 89.87, "elapsed_time": "6:26:43", "remaining_time": "0:43:35", "throughput": 1486.01, "total_tokens": 34480864} {"current_steps": 163390, "total_steps": 181800, "loss": 0.0185, "lr": 1.545839691019757e-06, "epoch": 17.974697469746975, "percentage": 89.87, "elapsed_time": "6:26:44", "remaining_time": "0:43:34", "throughput": 1486.01, "total_tokens": 34481856} {"current_steps": 163395, "total_steps": 181800, "loss": 0.0054, "lr": 1.5450089325985516e-06, "epoch": 17.975247524752476, "percentage": 89.88, "elapsed_time": "6:26:44", "remaining_time": "0:43:33", "throughput": 1486.01, "total_tokens": 34482880} {"current_steps": 163400, "total_steps": 181800, "loss": 0.0834, "lr": 1.544178390350745e-06, "epoch": 17.975797579757977, "percentage": 89.88, "elapsed_time": "6:26:45", "remaining_time": "0:43:33", "throughput": 1486.01, "total_tokens": 34483936} {"current_steps": 163405, "total_steps": 181800, "loss": 0.0011, "lr": 1.5433480642839892e-06, "epoch": 17.976347634763478, "percentage": 89.88, "elapsed_time": "6:26:46", "remaining_time": "0:43:32", "throughput": 1486.01, "total_tokens": 34484992} {"current_steps": 163410, "total_steps": 181800, "loss": 0.0835, "lr": 1.5425179544059392e-06, "epoch": 17.976897689768975, "percentage": 89.88, "elapsed_time": "6:26:47", "remaining_time": "0:43:31", "throughput": 1486.01, "total_tokens": 34486016} {"current_steps": 163415, "total_steps": 181800, "loss": 0.0013, "lr": 1.5416880607242446e-06, "epoch": 17.977447744774476, "percentage": 89.89, "elapsed_time": "6:26:47", "remaining_time": "0:43:30", "throughput": 1486.02, "total_tokens": 34487104} {"current_steps": 163420, "total_steps": 181800, "loss": 0.0126, "lr": 1.5408583832465517e-06, "epoch": 17.977997799779978, "percentage": 89.89, "elapsed_time": "6:26:48", "remaining_time": "0:43:30", "throughput": 1486.02, "total_tokens": 34488128} {"current_steps": 163425, "total_steps": 181800, "loss": 0.1136, "lr": 1.5400289219805159e-06, "epoch": 17.97854785478548, "percentage": 89.89, "elapsed_time": "6:26:49", "remaining_time": "0:43:29", "throughput": 1486.02, "total_tokens": 34489152} {"current_steps": 163430, "total_steps": 181800, "loss": 0.0134, "lr": 1.5391996769337724e-06, "epoch": 17.97909790979098, "percentage": 89.9, "elapsed_time": "6:26:49", "remaining_time": "0:43:28", "throughput": 1486.02, "total_tokens": 34490304} {"current_steps": 163435, "total_steps": 181800, "loss": 0.0039, "lr": 1.5383706481139708e-06, "epoch": 17.97964796479648, "percentage": 89.9, "elapsed_time": "6:26:50", "remaining_time": "0:43:28", "throughput": 1486.03, "total_tokens": 34491392} {"current_steps": 163440, "total_steps": 181800, "loss": 0.0419, "lr": 1.537541835528747e-06, "epoch": 17.980198019801982, "percentage": 89.9, "elapsed_time": "6:26:51", "remaining_time": "0:43:27", "throughput": 1486.03, "total_tokens": 34492480} {"current_steps": 163445, "total_steps": 181800, "loss": 0.0037, "lr": 1.5367132391857385e-06, "epoch": 17.98074807480748, "percentage": 89.9, "elapsed_time": "6:26:51", "remaining_time": "0:43:26", "throughput": 1486.03, "total_tokens": 34493568} {"current_steps": 163450, "total_steps": 181800, "loss": 0.0074, "lr": 1.53588485909259e-06, "epoch": 17.98129812981298, "percentage": 89.91, "elapsed_time": "6:26:52", "remaining_time": "0:43:25", "throughput": 1486.03, "total_tokens": 34494656} {"current_steps": 163455, "total_steps": 181800, "loss": 0.0033, "lr": 1.5350566952569312e-06, "epoch": 17.98184818481848, "percentage": 89.91, "elapsed_time": "6:26:53", "remaining_time": "0:43:25", "throughput": 1486.03, "total_tokens": 34495680} {"current_steps": 163460, "total_steps": 181800, "loss": 0.0031, "lr": 1.534228747686395e-06, "epoch": 17.982398239823983, "percentage": 89.91, "elapsed_time": "6:26:53", "remaining_time": "0:43:24", "throughput": 1486.03, "total_tokens": 34496736} {"current_steps": 163465, "total_steps": 181800, "loss": 0.0538, "lr": 1.533401016388611e-06, "epoch": 17.982948294829484, "percentage": 89.91, "elapsed_time": "6:26:54", "remaining_time": "0:43:23", "throughput": 1486.04, "total_tokens": 34497824} {"current_steps": 163470, "total_steps": 181800, "loss": 0.0053, "lr": 1.5325735013712123e-06, "epoch": 17.983498349834985, "percentage": 89.92, "elapsed_time": "6:26:55", "remaining_time": "0:43:23", "throughput": 1486.04, "total_tokens": 34498848} {"current_steps": 163475, "total_steps": 181800, "loss": 0.0132, "lr": 1.5317462026418206e-06, "epoch": 17.984048404840483, "percentage": 89.92, "elapsed_time": "6:26:56", "remaining_time": "0:43:22", "throughput": 1486.04, "total_tokens": 34499904} {"current_steps": 163480, "total_steps": 181800, "loss": 0.0729, "lr": 1.5309191202080602e-06, "epoch": 17.984598459845984, "percentage": 89.92, "elapsed_time": "6:26:56", "remaining_time": "0:43:21", "throughput": 1486.04, "total_tokens": 34500960} {"current_steps": 163485, "total_steps": 181800, "loss": 0.0011, "lr": 1.5300922540775614e-06, "epoch": 17.985148514851485, "percentage": 89.93, "elapsed_time": "6:26:57", "remaining_time": "0:43:21", "throughput": 1486.04, "total_tokens": 34501984} {"current_steps": 163490, "total_steps": 181800, "loss": 0.0013, "lr": 1.5292656042579373e-06, "epoch": 17.985698569856986, "percentage": 89.93, "elapsed_time": "6:26:58", "remaining_time": "0:43:20", "throughput": 1486.04, "total_tokens": 34503040} {"current_steps": 163495, "total_steps": 181800, "loss": 0.0013, "lr": 1.528439170756815e-06, "epoch": 17.986248624862487, "percentage": 89.93, "elapsed_time": "6:26:58", "remaining_time": "0:43:19", "throughput": 1486.04, "total_tokens": 34504160} {"current_steps": 163500, "total_steps": 181800, "loss": 0.0045, "lr": 1.5276129535818001e-06, "epoch": 17.986798679867988, "percentage": 89.93, "elapsed_time": "6:26:59", "remaining_time": "0:43:18", "throughput": 1486.04, "total_tokens": 34505152} {"current_steps": 163505, "total_steps": 181800, "loss": 0.0058, "lr": 1.5267869527405137e-06, "epoch": 17.98734873487349, "percentage": 89.94, "elapsed_time": "6:27:00", "remaining_time": "0:43:18", "throughput": 1486.04, "total_tokens": 34506176} {"current_steps": 163510, "total_steps": 181800, "loss": 0.0819, "lr": 1.5259611682405722e-06, "epoch": 17.987898789878987, "percentage": 89.94, "elapsed_time": "6:27:00", "remaining_time": "0:43:17", "throughput": 1486.04, "total_tokens": 34507168} {"current_steps": 163515, "total_steps": 181800, "loss": 0.0504, "lr": 1.5251356000895832e-06, "epoch": 17.988448844884488, "percentage": 89.94, "elapsed_time": "6:27:01", "remaining_time": "0:43:16", "throughput": 1486.04, "total_tokens": 34508224} {"current_steps": 163520, "total_steps": 181800, "loss": 0.0063, "lr": 1.524310248295152e-06, "epoch": 17.98899889988999, "percentage": 89.94, "elapsed_time": "6:27:02", "remaining_time": "0:43:16", "throughput": 1486.05, "total_tokens": 34509312} {"current_steps": 163525, "total_steps": 181800, "loss": 0.0012, "lr": 1.5234851128648919e-06, "epoch": 17.98954895489549, "percentage": 89.95, "elapsed_time": "6:27:02", "remaining_time": "0:43:15", "throughput": 1486.05, "total_tokens": 34510400} {"current_steps": 163530, "total_steps": 181800, "loss": 0.0021, "lr": 1.5226601938063995e-06, "epoch": 17.99009900990099, "percentage": 89.95, "elapsed_time": "6:27:03", "remaining_time": "0:43:14", "throughput": 1486.05, "total_tokens": 34511392} {"current_steps": 163535, "total_steps": 181800, "loss": 0.121, "lr": 1.5218354911272825e-06, "epoch": 17.990649064906492, "percentage": 89.95, "elapsed_time": "6:27:04", "remaining_time": "0:43:13", "throughput": 1486.05, "total_tokens": 34512448} {"current_steps": 163540, "total_steps": 181800, "loss": 0.0089, "lr": 1.5210110048351461e-06, "epoch": 17.99119911991199, "percentage": 89.96, "elapsed_time": "6:27:04", "remaining_time": "0:43:13", "throughput": 1486.05, "total_tokens": 34513504} {"current_steps": 163545, "total_steps": 181800, "loss": 0.0029, "lr": 1.5201867349375814e-06, "epoch": 17.99174917491749, "percentage": 89.96, "elapsed_time": "6:27:05", "remaining_time": "0:43:12", "throughput": 1486.05, "total_tokens": 34514528} {"current_steps": 163550, "total_steps": 181800, "loss": 0.0571, "lr": 1.5193626814421936e-06, "epoch": 17.992299229922992, "percentage": 89.96, "elapsed_time": "6:27:06", "remaining_time": "0:43:11", "throughput": 1486.05, "total_tokens": 34515616} {"current_steps": 163555, "total_steps": 181800, "loss": 0.0023, "lr": 1.5185388443565679e-06, "epoch": 17.992849284928493, "percentage": 89.96, "elapsed_time": "6:27:07", "remaining_time": "0:43:11", "throughput": 1486.05, "total_tokens": 34516672} {"current_steps": 163560, "total_steps": 181800, "loss": 0.1451, "lr": 1.5177152236883012e-06, "epoch": 17.993399339933994, "percentage": 89.97, "elapsed_time": "6:27:07", "remaining_time": "0:43:10", "throughput": 1486.06, "total_tokens": 34517760} {"current_steps": 163565, "total_steps": 181800, "loss": 0.0081, "lr": 1.5168918194449906e-06, "epoch": 17.993949394939495, "percentage": 89.97, "elapsed_time": "6:27:08", "remaining_time": "0:43:09", "throughput": 1486.06, "total_tokens": 34518816} {"current_steps": 163570, "total_steps": 181800, "loss": 0.0021, "lr": 1.5160686316342155e-06, "epoch": 17.994499449944996, "percentage": 89.97, "elapsed_time": "6:27:09", "remaining_time": "0:43:08", "throughput": 1486.06, "total_tokens": 34519904} {"current_steps": 163575, "total_steps": 181800, "loss": 0.0158, "lr": 1.5152456602635729e-06, "epoch": 17.995049504950494, "percentage": 89.98, "elapsed_time": "6:27:09", "remaining_time": "0:43:08", "throughput": 1486.06, "total_tokens": 34520928} {"current_steps": 163580, "total_steps": 181800, "loss": 0.0568, "lr": 1.5144229053406373e-06, "epoch": 17.995599559955995, "percentage": 89.98, "elapsed_time": "6:27:10", "remaining_time": "0:43:07", "throughput": 1486.06, "total_tokens": 34521984} {"current_steps": 163585, "total_steps": 181800, "loss": 0.0621, "lr": 1.513600366872997e-06, "epoch": 17.996149614961496, "percentage": 89.98, "elapsed_time": "6:27:11", "remaining_time": "0:43:06", "throughput": 1486.06, "total_tokens": 34523040} {"current_steps": 163590, "total_steps": 181800, "loss": 0.0764, "lr": 1.5127780448682322e-06, "epoch": 17.996699669966997, "percentage": 89.98, "elapsed_time": "6:27:11", "remaining_time": "0:43:06", "throughput": 1486.07, "total_tokens": 34524128} {"current_steps": 163595, "total_steps": 181800, "loss": 0.0985, "lr": 1.51195593933392e-06, "epoch": 17.997249724972498, "percentage": 89.99, "elapsed_time": "6:27:12", "remaining_time": "0:43:05", "throughput": 1486.07, "total_tokens": 34525184} {"current_steps": 163600, "total_steps": 181800, "loss": 0.0028, "lr": 1.5111340502776433e-06, "epoch": 17.997799779978, "percentage": 89.99, "elapsed_time": "6:27:13", "remaining_time": "0:43:04", "throughput": 1486.06, "total_tokens": 34526176} {"current_steps": 163605, "total_steps": 181800, "loss": 0.0047, "lr": 1.5103123777069683e-06, "epoch": 17.998349834983497, "percentage": 89.99, "elapsed_time": "6:27:13", "remaining_time": "0:43:03", "throughput": 1486.07, "total_tokens": 34527232} {"current_steps": 163610, "total_steps": 181800, "loss": 0.0384, "lr": 1.5094909216294777e-06, "epoch": 17.998899889988998, "percentage": 89.99, "elapsed_time": "6:27:14", "remaining_time": "0:43:03", "throughput": 1486.06, "total_tokens": 34528224} {"current_steps": 163615, "total_steps": 181800, "loss": 0.0034, "lr": 1.5086696820527352e-06, "epoch": 17.9994499449945, "percentage": 90.0, "elapsed_time": "6:27:15", "remaining_time": "0:43:02", "throughput": 1486.06, "total_tokens": 34529184} {"current_steps": 163620, "total_steps": 181800, "loss": 0.0958, "lr": 1.5078486589843093e-06, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "6:27:16", "remaining_time": "0:43:01", "throughput": 1486.06, "total_tokens": 34530176} {"current_steps": 163620, "total_steps": 181800, "eval_loss": 0.0780656486749649, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "6:27:53", "remaining_time": "0:43:05", "throughput": 1483.69, "total_tokens": 34530176} {"current_steps": 163625, "total_steps": 181800, "loss": 0.005, "lr": 1.507027852431775e-06, "epoch": 18.0005500550055, "percentage": 90.0, "elapsed_time": "6:27:55", "remaining_time": "0:43:05", "throughput": 1483.58, "total_tokens": 34531232} {"current_steps": 163630, "total_steps": 181800, "loss": 0.0041, "lr": 1.5062072624026868e-06, "epoch": 18.001100110011002, "percentage": 90.01, "elapsed_time": "6:27:56", "remaining_time": "0:43:04", "throughput": 1483.58, "total_tokens": 34532256} {"current_steps": 163635, "total_steps": 181800, "loss": 0.0018, "lr": 1.5053868889046169e-06, "epoch": 18.001650165016503, "percentage": 90.01, "elapsed_time": "6:27:57", "remaining_time": "0:43:03", "throughput": 1483.58, "total_tokens": 34533344} {"current_steps": 163640, "total_steps": 181800, "loss": 0.0498, "lr": 1.5045667319451228e-06, "epoch": 18.002200220022, "percentage": 90.01, "elapsed_time": "6:27:57", "remaining_time": "0:43:03", "throughput": 1483.58, "total_tokens": 34534400} {"current_steps": 163645, "total_steps": 181800, "loss": 0.004, "lr": 1.50374679153176e-06, "epoch": 18.002750275027502, "percentage": 90.01, "elapsed_time": "6:27:58", "remaining_time": "0:43:02", "throughput": 1483.58, "total_tokens": 34535424} {"current_steps": 163650, "total_steps": 181800, "loss": 0.0562, "lr": 1.5029270676720885e-06, "epoch": 18.003300330033003, "percentage": 90.02, "elapsed_time": "6:27:59", "remaining_time": "0:43:01", "throughput": 1483.58, "total_tokens": 34536480} {"current_steps": 163655, "total_steps": 181800, "loss": 0.0027, "lr": 1.5021075603736613e-06, "epoch": 18.003850385038504, "percentage": 90.02, "elapsed_time": "6:27:59", "remaining_time": "0:43:01", "throughput": 1483.58, "total_tokens": 34537504} {"current_steps": 163660, "total_steps": 181800, "loss": 0.0257, "lr": 1.5012882696440384e-06, "epoch": 18.004400440044005, "percentage": 90.02, "elapsed_time": "6:28:00", "remaining_time": "0:43:00", "throughput": 1483.58, "total_tokens": 34538624} {"current_steps": 163665, "total_steps": 181800, "loss": 0.0061, "lr": 1.500469195490764e-06, "epoch": 18.004950495049506, "percentage": 90.02, "elapsed_time": "6:28:01", "remaining_time": "0:42:59", "throughput": 1483.57, "total_tokens": 34539616} {"current_steps": 163670, "total_steps": 181800, "loss": 0.0653, "lr": 1.4996503379213878e-06, "epoch": 18.005500550055004, "percentage": 90.03, "elapsed_time": "6:28:02", "remaining_time": "0:42:58", "throughput": 1483.57, "total_tokens": 34540672} {"current_steps": 163675, "total_steps": 181800, "loss": 0.0031, "lr": 1.4988316969434564e-06, "epoch": 18.006050605060505, "percentage": 90.03, "elapsed_time": "6:28:02", "remaining_time": "0:42:58", "throughput": 1483.58, "total_tokens": 34541760} {"current_steps": 163680, "total_steps": 181800, "loss": 0.0006, "lr": 1.4980132725645163e-06, "epoch": 18.006600660066006, "percentage": 90.03, "elapsed_time": "6:28:03", "remaining_time": "0:42:57", "throughput": 1483.57, "total_tokens": 34542816} {"current_steps": 163685, "total_steps": 181800, "loss": 0.0023, "lr": 1.4971950647921146e-06, "epoch": 18.007150715071507, "percentage": 90.04, "elapsed_time": "6:28:04", "remaining_time": "0:42:56", "throughput": 1483.57, "total_tokens": 34543840} {"current_steps": 163690, "total_steps": 181800, "loss": 0.007, "lr": 1.4963770736337896e-06, "epoch": 18.007700770077008, "percentage": 90.04, "elapsed_time": "6:28:04", "remaining_time": "0:42:56", "throughput": 1483.57, "total_tokens": 34544896} {"current_steps": 163695, "total_steps": 181800, "loss": 0.0021, "lr": 1.4955592990970712e-06, "epoch": 18.00825082508251, "percentage": 90.04, "elapsed_time": "6:28:05", "remaining_time": "0:42:55", "throughput": 1483.58, "total_tokens": 34546016} {"current_steps": 163700, "total_steps": 181800, "loss": 0.0035, "lr": 1.494741741189512e-06, "epoch": 18.00880088008801, "percentage": 90.04, "elapsed_time": "6:28:06", "remaining_time": "0:42:54", "throughput": 1483.58, "total_tokens": 34547040} {"current_steps": 163705, "total_steps": 181800, "loss": 0.0274, "lr": 1.4939243999186336e-06, "epoch": 18.009350935093508, "percentage": 90.05, "elapsed_time": "6:28:07", "remaining_time": "0:42:54", "throughput": 1483.57, "total_tokens": 34548064} {"current_steps": 163710, "total_steps": 181800, "loss": 0.0049, "lr": 1.4931072752919746e-06, "epoch": 18.00990099009901, "percentage": 90.05, "elapsed_time": "6:28:07", "remaining_time": "0:42:53", "throughput": 1483.58, "total_tokens": 34549152} {"current_steps": 163715, "total_steps": 181800, "loss": 0.0016, "lr": 1.4922903673170703e-06, "epoch": 18.01045104510451, "percentage": 90.05, "elapsed_time": "6:28:08", "remaining_time": "0:42:52", "throughput": 1483.58, "total_tokens": 34550240} {"current_steps": 163720, "total_steps": 181800, "loss": 0.0373, "lr": 1.4914736760014425e-06, "epoch": 18.01100110011001, "percentage": 90.06, "elapsed_time": "6:28:09", "remaining_time": "0:42:51", "throughput": 1483.58, "total_tokens": 34551264} {"current_steps": 163725, "total_steps": 181800, "loss": 0.0123, "lr": 1.4906572013526243e-06, "epoch": 18.011551155115512, "percentage": 90.06, "elapsed_time": "6:28:09", "remaining_time": "0:42:51", "throughput": 1483.58, "total_tokens": 34552352} {"current_steps": 163730, "total_steps": 181800, "loss": 0.0066, "lr": 1.4898409433781347e-06, "epoch": 18.012101210121013, "percentage": 90.06, "elapsed_time": "6:28:10", "remaining_time": "0:42:50", "throughput": 1483.58, "total_tokens": 34553440} {"current_steps": 163735, "total_steps": 181800, "loss": 0.0009, "lr": 1.4890249020855007e-06, "epoch": 18.01265126512651, "percentage": 90.06, "elapsed_time": "6:28:11", "remaining_time": "0:42:49", "throughput": 1483.59, "total_tokens": 34554528} {"current_steps": 163740, "total_steps": 181800, "loss": 0.0352, "lr": 1.4882090774822444e-06, "epoch": 18.013201320132012, "percentage": 90.07, "elapsed_time": "6:28:11", "remaining_time": "0:42:49", "throughput": 1483.59, "total_tokens": 34555616} {"current_steps": 163745, "total_steps": 181800, "loss": 0.1538, "lr": 1.487393469575879e-06, "epoch": 18.013751375137513, "percentage": 90.07, "elapsed_time": "6:28:12", "remaining_time": "0:42:48", "throughput": 1483.59, "total_tokens": 34556672} {"current_steps": 163750, "total_steps": 181800, "loss": 0.0315, "lr": 1.4865780783739292e-06, "epoch": 18.014301430143014, "percentage": 90.07, "elapsed_time": "6:28:13", "remaining_time": "0:42:47", "throughput": 1483.59, "total_tokens": 34557696} {"current_steps": 163755, "total_steps": 181800, "loss": 0.0198, "lr": 1.4857629038839083e-06, "epoch": 18.014851485148515, "percentage": 90.07, "elapsed_time": "6:28:13", "remaining_time": "0:42:46", "throughput": 1483.59, "total_tokens": 34558752} {"current_steps": 163760, "total_steps": 181800, "loss": 0.0797, "lr": 1.4849479461133214e-06, "epoch": 18.015401540154016, "percentage": 90.08, "elapsed_time": "6:28:14", "remaining_time": "0:42:46", "throughput": 1483.59, "total_tokens": 34559808} {"current_steps": 163765, "total_steps": 181800, "loss": 0.0005, "lr": 1.4841332050696877e-06, "epoch": 18.015951595159517, "percentage": 90.08, "elapsed_time": "6:28:15", "remaining_time": "0:42:45", "throughput": 1483.59, "total_tokens": 34560768} {"current_steps": 163770, "total_steps": 181800, "loss": 0.076, "lr": 1.483318680760515e-06, "epoch": 18.016501650165015, "percentage": 90.08, "elapsed_time": "6:28:16", "remaining_time": "0:42:44", "throughput": 1483.59, "total_tokens": 34561824} {"current_steps": 163775, "total_steps": 181800, "loss": 0.0025, "lr": 1.4825043731933108e-06, "epoch": 18.017051705170516, "percentage": 90.09, "elapsed_time": "6:28:16", "remaining_time": "0:42:44", "throughput": 1483.6, "total_tokens": 34562976} {"current_steps": 163780, "total_steps": 181800, "loss": 0.0099, "lr": 1.4816902823755808e-06, "epoch": 18.017601760176017, "percentage": 90.09, "elapsed_time": "6:28:17", "remaining_time": "0:42:43", "throughput": 1483.6, "total_tokens": 34564064} {"current_steps": 163785, "total_steps": 181800, "loss": 0.048, "lr": 1.4808764083148212e-06, "epoch": 18.01815181518152, "percentage": 90.09, "elapsed_time": "6:28:18", "remaining_time": "0:42:42", "throughput": 1483.6, "total_tokens": 34565056} {"current_steps": 163790, "total_steps": 181800, "loss": 0.052, "lr": 1.4800627510185379e-06, "epoch": 18.01870187018702, "percentage": 90.09, "elapsed_time": "6:28:18", "remaining_time": "0:42:41", "throughput": 1483.6, "total_tokens": 34566144} {"current_steps": 163795, "total_steps": 181800, "loss": 0.0802, "lr": 1.4792493104942324e-06, "epoch": 18.01925192519252, "percentage": 90.1, "elapsed_time": "6:28:19", "remaining_time": "0:42:41", "throughput": 1483.6, "total_tokens": 34567136} {"current_steps": 163800, "total_steps": 181800, "loss": 0.0934, "lr": 1.4784360867494017e-06, "epoch": 18.019801980198018, "percentage": 90.1, "elapsed_time": "6:28:20", "remaining_time": "0:42:40", "throughput": 1483.6, "total_tokens": 34568160} {"current_steps": 163805, "total_steps": 181800, "loss": 0.0027, "lr": 1.4776230797915402e-06, "epoch": 18.02035203520352, "percentage": 90.1, "elapsed_time": "6:28:20", "remaining_time": "0:42:39", "throughput": 1483.6, "total_tokens": 34569184} {"current_steps": 163810, "total_steps": 181800, "loss": 0.0041, "lr": 1.4768102896281333e-06, "epoch": 18.02090209020902, "percentage": 90.1, "elapsed_time": "6:28:21", "remaining_time": "0:42:39", "throughput": 1483.6, "total_tokens": 34570240} {"current_steps": 163815, "total_steps": 181800, "loss": 0.2229, "lr": 1.4759977162666861e-06, "epoch": 18.02145214521452, "percentage": 90.11, "elapsed_time": "6:28:22", "remaining_time": "0:42:38", "throughput": 1483.6, "total_tokens": 34571360} {"current_steps": 163820, "total_steps": 181800, "loss": 0.0021, "lr": 1.475185359714673e-06, "epoch": 18.022002200220022, "percentage": 90.11, "elapsed_time": "6:28:22", "remaining_time": "0:42:37", "throughput": 1483.61, "total_tokens": 34572448} {"current_steps": 163825, "total_steps": 181800, "loss": 0.0609, "lr": 1.4743732199795885e-06, "epoch": 18.022552255225524, "percentage": 90.11, "elapsed_time": "6:28:23", "remaining_time": "0:42:36", "throughput": 1483.6, "total_tokens": 34573440} {"current_steps": 163830, "total_steps": 181800, "loss": 0.0806, "lr": 1.4735612970689233e-06, "epoch": 18.023102310231025, "percentage": 90.12, "elapsed_time": "6:28:24", "remaining_time": "0:42:36", "throughput": 1483.61, "total_tokens": 34574496} {"current_steps": 163835, "total_steps": 181800, "loss": 0.001, "lr": 1.4727495909901495e-06, "epoch": 18.023652365236522, "percentage": 90.12, "elapsed_time": "6:28:25", "remaining_time": "0:42:35", "throughput": 1483.61, "total_tokens": 34575520} {"current_steps": 163840, "total_steps": 181800, "loss": 0.0011, "lr": 1.4719381017507555e-06, "epoch": 18.024202420242023, "percentage": 90.12, "elapsed_time": "6:28:25", "remaining_time": "0:42:34", "throughput": 1483.61, "total_tokens": 34576576} {"current_steps": 163845, "total_steps": 181800, "loss": 0.0056, "lr": 1.471126829358216e-06, "epoch": 18.024752475247524, "percentage": 90.12, "elapsed_time": "6:28:26", "remaining_time": "0:42:34", "throughput": 1483.61, "total_tokens": 34577632} {"current_steps": 163850, "total_steps": 181800, "loss": 0.0028, "lr": 1.4703157738200108e-06, "epoch": 18.025302530253025, "percentage": 90.13, "elapsed_time": "6:28:27", "remaining_time": "0:42:33", "throughput": 1483.61, "total_tokens": 34578656} {"current_steps": 163855, "total_steps": 181800, "loss": 0.0411, "lr": 1.4695049351436175e-06, "epoch": 18.025852585258527, "percentage": 90.13, "elapsed_time": "6:28:27", "remaining_time": "0:42:32", "throughput": 1483.61, "total_tokens": 34579648} {"current_steps": 163860, "total_steps": 181800, "loss": 0.0275, "lr": 1.4686943133365023e-06, "epoch": 18.026402640264028, "percentage": 90.13, "elapsed_time": "6:28:28", "remaining_time": "0:42:31", "throughput": 1483.61, "total_tokens": 34580672} {"current_steps": 163865, "total_steps": 181800, "loss": 0.0302, "lr": 1.4678839084061424e-06, "epoch": 18.02695269526953, "percentage": 90.13, "elapsed_time": "6:28:29", "remaining_time": "0:42:31", "throughput": 1483.61, "total_tokens": 34581760} {"current_steps": 163870, "total_steps": 181800, "loss": 0.0019, "lr": 1.4670737203600043e-06, "epoch": 18.027502750275026, "percentage": 90.14, "elapsed_time": "6:28:29", "remaining_time": "0:42:30", "throughput": 1483.61, "total_tokens": 34582752} {"current_steps": 163875, "total_steps": 181800, "loss": 0.0022, "lr": 1.466263749205557e-06, "epoch": 18.028052805280527, "percentage": 90.14, "elapsed_time": "6:28:30", "remaining_time": "0:42:29", "throughput": 1483.61, "total_tokens": 34583872} {"current_steps": 163880, "total_steps": 181800, "loss": 0.0031, "lr": 1.465453994950261e-06, "epoch": 18.02860286028603, "percentage": 90.14, "elapsed_time": "6:28:31", "remaining_time": "0:42:29", "throughput": 1483.61, "total_tokens": 34584832} {"current_steps": 163885, "total_steps": 181800, "loss": 0.0444, "lr": 1.4646444576015828e-06, "epoch": 18.02915291529153, "percentage": 90.15, "elapsed_time": "6:28:31", "remaining_time": "0:42:28", "throughput": 1483.61, "total_tokens": 34585888} {"current_steps": 163890, "total_steps": 181800, "loss": 0.1081, "lr": 1.4638351371669857e-06, "epoch": 18.02970297029703, "percentage": 90.15, "elapsed_time": "6:28:32", "remaining_time": "0:42:27", "throughput": 1483.61, "total_tokens": 34586944} {"current_steps": 163895, "total_steps": 181800, "loss": 0.0011, "lr": 1.4630260336539275e-06, "epoch": 18.03025302530253, "percentage": 90.15, "elapsed_time": "6:28:33", "remaining_time": "0:42:26", "throughput": 1483.61, "total_tokens": 34587936} {"current_steps": 163900, "total_steps": 181800, "loss": 0.0114, "lr": 1.462217147069861e-06, "epoch": 18.03080308030803, "percentage": 90.15, "elapsed_time": "6:28:34", "remaining_time": "0:42:26", "throughput": 1483.61, "total_tokens": 34589024} {"current_steps": 163905, "total_steps": 181800, "loss": 0.0018, "lr": 1.4614084774222464e-06, "epoch": 18.03135313531353, "percentage": 90.16, "elapsed_time": "6:28:34", "remaining_time": "0:42:25", "throughput": 1483.62, "total_tokens": 34590112} {"current_steps": 163910, "total_steps": 181800, "loss": 0.0294, "lr": 1.460600024718528e-06, "epoch": 18.03190319031903, "percentage": 90.16, "elapsed_time": "6:28:35", "remaining_time": "0:42:24", "throughput": 1483.62, "total_tokens": 34591104} {"current_steps": 163915, "total_steps": 181800, "loss": 0.0009, "lr": 1.4597917889661722e-06, "epoch": 18.032453245324533, "percentage": 90.16, "elapsed_time": "6:28:36", "remaining_time": "0:42:24", "throughput": 1483.62, "total_tokens": 34592160} {"current_steps": 163920, "total_steps": 181800, "loss": 0.0437, "lr": 1.45898377017262e-06, "epoch": 18.033003300330034, "percentage": 90.17, "elapsed_time": "6:28:36", "remaining_time": "0:42:23", "throughput": 1483.62, "total_tokens": 34593216} {"current_steps": 163925, "total_steps": 181800, "loss": 0.1176, "lr": 1.4581759683453156e-06, "epoch": 18.033553355335535, "percentage": 90.17, "elapsed_time": "6:28:37", "remaining_time": "0:42:22", "throughput": 1483.62, "total_tokens": 34594304} {"current_steps": 163930, "total_steps": 181800, "loss": 0.0059, "lr": 1.4573683834917085e-06, "epoch": 18.034103410341036, "percentage": 90.17, "elapsed_time": "6:28:38", "remaining_time": "0:42:21", "throughput": 1483.62, "total_tokens": 34595360} {"current_steps": 163935, "total_steps": 181800, "loss": 0.0297, "lr": 1.456561015619237e-06, "epoch": 18.034653465346533, "percentage": 90.17, "elapsed_time": "6:28:38", "remaining_time": "0:42:21", "throughput": 1483.62, "total_tokens": 34596384} {"current_steps": 163940, "total_steps": 181800, "loss": 0.0056, "lr": 1.4557538647353458e-06, "epoch": 18.035203520352034, "percentage": 90.18, "elapsed_time": "6:28:39", "remaining_time": "0:42:20", "throughput": 1483.62, "total_tokens": 34597472} {"current_steps": 163945, "total_steps": 181800, "loss": 0.1183, "lr": 1.4549469308474755e-06, "epoch": 18.035753575357536, "percentage": 90.18, "elapsed_time": "6:28:40", "remaining_time": "0:42:19", "throughput": 1483.63, "total_tokens": 34598528} {"current_steps": 163950, "total_steps": 181800, "loss": 0.0036, "lr": 1.4541402139630594e-06, "epoch": 18.036303630363037, "percentage": 90.18, "elapsed_time": "6:28:40", "remaining_time": "0:42:19", "throughput": 1483.63, "total_tokens": 34599584} {"current_steps": 163955, "total_steps": 181800, "loss": 0.0016, "lr": 1.4533337140895386e-06, "epoch": 18.036853685368538, "percentage": 90.18, "elapsed_time": "6:28:41", "remaining_time": "0:42:18", "throughput": 1483.63, "total_tokens": 34600704} {"current_steps": 163960, "total_steps": 181800, "loss": 0.0339, "lr": 1.452527431234338e-06, "epoch": 18.03740374037404, "percentage": 90.19, "elapsed_time": "6:28:42", "remaining_time": "0:42:17", "throughput": 1483.63, "total_tokens": 34601792} {"current_steps": 163965, "total_steps": 181800, "loss": 0.0077, "lr": 1.4517213654048929e-06, "epoch": 18.037953795379536, "percentage": 90.19, "elapsed_time": "6:28:43", "remaining_time": "0:42:16", "throughput": 1483.64, "total_tokens": 34602848} {"current_steps": 163970, "total_steps": 181800, "loss": 0.0485, "lr": 1.4509155166086363e-06, "epoch": 18.038503850385037, "percentage": 90.19, "elapsed_time": "6:28:43", "remaining_time": "0:42:16", "throughput": 1483.64, "total_tokens": 34603872} {"current_steps": 163975, "total_steps": 181800, "loss": 0.0015, "lr": 1.4501098848529875e-06, "epoch": 18.03905390539054, "percentage": 90.2, "elapsed_time": "6:28:44", "remaining_time": "0:42:15", "throughput": 1483.63, "total_tokens": 34604864} {"current_steps": 163980, "total_steps": 181800, "loss": 0.0014, "lr": 1.4493044701453766e-06, "epoch": 18.03960396039604, "percentage": 90.2, "elapsed_time": "6:28:45", "remaining_time": "0:42:14", "throughput": 1483.63, "total_tokens": 34605888} {"current_steps": 163985, "total_steps": 181800, "loss": 0.0017, "lr": 1.4484992724932257e-06, "epoch": 18.04015401540154, "percentage": 90.2, "elapsed_time": "6:28:45", "remaining_time": "0:42:14", "throughput": 1483.63, "total_tokens": 34606880} {"current_steps": 163990, "total_steps": 181800, "loss": 0.0098, "lr": 1.4476942919039587e-06, "epoch": 18.040704070407042, "percentage": 90.2, "elapsed_time": "6:28:46", "remaining_time": "0:42:13", "throughput": 1483.64, "total_tokens": 34607968} {"current_steps": 163995, "total_steps": 181800, "loss": 0.0028, "lr": 1.446889528384987e-06, "epoch": 18.041254125412543, "percentage": 90.21, "elapsed_time": "6:28:47", "remaining_time": "0:42:12", "throughput": 1483.64, "total_tokens": 34609024} {"current_steps": 164000, "total_steps": 181800, "loss": 0.0009, "lr": 1.446084981943735e-06, "epoch": 18.04180418041804, "percentage": 90.21, "elapsed_time": "6:28:47", "remaining_time": "0:42:11", "throughput": 1483.64, "total_tokens": 34610080} {"current_steps": 164005, "total_steps": 181800, "loss": 0.0027, "lr": 1.445280652587616e-06, "epoch": 18.04235423542354, "percentage": 90.21, "elapsed_time": "6:28:48", "remaining_time": "0:42:11", "throughput": 1483.64, "total_tokens": 34611168} {"current_steps": 164010, "total_steps": 181800, "loss": 0.004, "lr": 1.4444765403240413e-06, "epoch": 18.042904290429043, "percentage": 90.21, "elapsed_time": "6:28:49", "remaining_time": "0:42:10", "throughput": 1483.64, "total_tokens": 34612256} {"current_steps": 164015, "total_steps": 181800, "loss": 0.0052, "lr": 1.4436726451604266e-06, "epoch": 18.043454345434544, "percentage": 90.22, "elapsed_time": "6:28:49", "remaining_time": "0:42:09", "throughput": 1483.65, "total_tokens": 34613376} {"current_steps": 164020, "total_steps": 181800, "loss": 0.0052, "lr": 1.4428689671041774e-06, "epoch": 18.044004400440045, "percentage": 90.22, "elapsed_time": "6:28:50", "remaining_time": "0:42:09", "throughput": 1483.65, "total_tokens": 34614464} {"current_steps": 164025, "total_steps": 181800, "loss": 0.0258, "lr": 1.4420655061626932e-06, "epoch": 18.044554455445546, "percentage": 90.22, "elapsed_time": "6:28:51", "remaining_time": "0:42:08", "throughput": 1483.65, "total_tokens": 34615456} {"current_steps": 164030, "total_steps": 181800, "loss": 0.0006, "lr": 1.4412622623433958e-06, "epoch": 18.045104510451043, "percentage": 90.23, "elapsed_time": "6:28:51", "remaining_time": "0:42:07", "throughput": 1483.65, "total_tokens": 34616448} {"current_steps": 164035, "total_steps": 181800, "loss": 0.0061, "lr": 1.440459235653674e-06, "epoch": 18.045654565456545, "percentage": 90.23, "elapsed_time": "6:28:52", "remaining_time": "0:42:06", "throughput": 1483.65, "total_tokens": 34617472} {"current_steps": 164040, "total_steps": 181800, "loss": 0.001, "lr": 1.4396564261009382e-06, "epoch": 18.046204620462046, "percentage": 90.23, "elapsed_time": "6:28:53", "remaining_time": "0:42:06", "throughput": 1483.65, "total_tokens": 34618624} {"current_steps": 164045, "total_steps": 181800, "loss": 0.0062, "lr": 1.4388538336925856e-06, "epoch": 18.046754675467547, "percentage": 90.23, "elapsed_time": "6:28:54", "remaining_time": "0:42:05", "throughput": 1483.66, "total_tokens": 34619680} {"current_steps": 164050, "total_steps": 181800, "loss": 0.0019, "lr": 1.4380514584360072e-06, "epoch": 18.047304730473048, "percentage": 90.24, "elapsed_time": "6:28:54", "remaining_time": "0:42:04", "throughput": 1483.66, "total_tokens": 34620800} {"current_steps": 164055, "total_steps": 181800, "loss": 0.0946, "lr": 1.4372493003386028e-06, "epoch": 18.04785478547855, "percentage": 90.24, "elapsed_time": "6:28:55", "remaining_time": "0:42:04", "throughput": 1483.66, "total_tokens": 34621856} {"current_steps": 164060, "total_steps": 181800, "loss": 0.0638, "lr": 1.4364473594077639e-06, "epoch": 18.04840484048405, "percentage": 90.24, "elapsed_time": "6:28:56", "remaining_time": "0:42:03", "throughput": 1483.66, "total_tokens": 34622944} {"current_steps": 164065, "total_steps": 181800, "loss": 0.0021, "lr": 1.435645635650887e-06, "epoch": 18.048954895489548, "percentage": 90.24, "elapsed_time": "6:28:56", "remaining_time": "0:42:02", "throughput": 1483.67, "total_tokens": 34624000} {"current_steps": 164070, "total_steps": 181800, "loss": 0.0033, "lr": 1.4348441290753551e-06, "epoch": 18.04950495049505, "percentage": 90.25, "elapsed_time": "6:28:57", "remaining_time": "0:42:01", "throughput": 1483.66, "total_tokens": 34624992} {"current_steps": 164075, "total_steps": 181800, "loss": 0.0139, "lr": 1.434042839688557e-06, "epoch": 18.05005500550055, "percentage": 90.25, "elapsed_time": "6:28:58", "remaining_time": "0:42:01", "throughput": 1483.66, "total_tokens": 34626016} {"current_steps": 164080, "total_steps": 181800, "loss": 0.0384, "lr": 1.4332417674978782e-06, "epoch": 18.05060506050605, "percentage": 90.25, "elapsed_time": "6:28:58", "remaining_time": "0:42:00", "throughput": 1483.67, "total_tokens": 34627104} {"current_steps": 164085, "total_steps": 181800, "loss": 0.0043, "lr": 1.4324409125107018e-06, "epoch": 18.051155115511552, "percentage": 90.26, "elapsed_time": "6:28:59", "remaining_time": "0:41:59", "throughput": 1483.67, "total_tokens": 34628160} {"current_steps": 164090, "total_steps": 181800, "loss": 0.0072, "lr": 1.4316402747344055e-06, "epoch": 18.051705170517053, "percentage": 90.26, "elapsed_time": "6:29:00", "remaining_time": "0:41:59", "throughput": 1483.67, "total_tokens": 34629248} {"current_steps": 164095, "total_steps": 181800, "loss": 0.0021, "lr": 1.4308398541763773e-06, "epoch": 18.05225522552255, "percentage": 90.26, "elapsed_time": "6:29:00", "remaining_time": "0:41:58", "throughput": 1483.67, "total_tokens": 34630368} {"current_steps": 164100, "total_steps": 181800, "loss": 0.0004, "lr": 1.430039650843984e-06, "epoch": 18.05280528052805, "percentage": 90.26, "elapsed_time": "6:29:01", "remaining_time": "0:41:57", "throughput": 1483.68, "total_tokens": 34631424} {"current_steps": 164105, "total_steps": 181800, "loss": 0.0025, "lr": 1.4292396647446081e-06, "epoch": 18.053355335533553, "percentage": 90.27, "elapsed_time": "6:29:02", "remaining_time": "0:41:56", "throughput": 1483.68, "total_tokens": 34632512} {"current_steps": 164110, "total_steps": 181800, "loss": 0.0021, "lr": 1.4284398958856165e-06, "epoch": 18.053905390539054, "percentage": 90.27, "elapsed_time": "6:29:03", "remaining_time": "0:41:56", "throughput": 1483.68, "total_tokens": 34633504} {"current_steps": 164115, "total_steps": 181800, "loss": 0.0012, "lr": 1.4276403442743835e-06, "epoch": 18.054455445544555, "percentage": 90.27, "elapsed_time": "6:29:03", "remaining_time": "0:41:55", "throughput": 1483.68, "total_tokens": 34634560} {"current_steps": 164120, "total_steps": 181800, "loss": 0.1036, "lr": 1.426841009918284e-06, "epoch": 18.055005500550056, "percentage": 90.28, "elapsed_time": "6:29:04", "remaining_time": "0:41:54", "throughput": 1483.68, "total_tokens": 34635584} {"current_steps": 164125, "total_steps": 181800, "loss": 0.1003, "lr": 1.4260418928246727e-06, "epoch": 18.055555555555557, "percentage": 90.28, "elapsed_time": "6:29:05", "remaining_time": "0:41:54", "throughput": 1483.68, "total_tokens": 34636640} {"current_steps": 164130, "total_steps": 181800, "loss": 0.0005, "lr": 1.4252429930009276e-06, "epoch": 18.056105610561055, "percentage": 90.28, "elapsed_time": "6:29:05", "remaining_time": "0:41:53", "throughput": 1483.68, "total_tokens": 34637696} {"current_steps": 164135, "total_steps": 181800, "loss": 0.012, "lr": 1.4244443104544064e-06, "epoch": 18.056655665566556, "percentage": 90.28, "elapsed_time": "6:29:06", "remaining_time": "0:41:52", "throughput": 1483.69, "total_tokens": 34638784} {"current_steps": 164140, "total_steps": 181800, "loss": 0.0359, "lr": 1.4236458451924617e-06, "epoch": 18.057205720572057, "percentage": 90.29, "elapsed_time": "6:29:07", "remaining_time": "0:41:51", "throughput": 1483.69, "total_tokens": 34639840} {"current_steps": 164145, "total_steps": 181800, "loss": 0.0044, "lr": 1.4228475972224625e-06, "epoch": 18.057755775577558, "percentage": 90.29, "elapsed_time": "6:29:07", "remaining_time": "0:41:51", "throughput": 1483.68, "total_tokens": 34640832} {"current_steps": 164150, "total_steps": 181800, "loss": 0.0016, "lr": 1.4220495665517642e-06, "epoch": 18.05830583058306, "percentage": 90.29, "elapsed_time": "6:29:08", "remaining_time": "0:41:50", "throughput": 1483.69, "total_tokens": 34641920} {"current_steps": 164155, "total_steps": 181800, "loss": 0.0035, "lr": 1.4212517531877246e-06, "epoch": 18.05885588558856, "percentage": 90.29, "elapsed_time": "6:29:09", "remaining_time": "0:41:49", "throughput": 1483.69, "total_tokens": 34642944} {"current_steps": 164160, "total_steps": 181800, "loss": 0.0024, "lr": 1.4204541571376933e-06, "epoch": 18.059405940594058, "percentage": 90.3, "elapsed_time": "6:29:09", "remaining_time": "0:41:49", "throughput": 1483.69, "total_tokens": 34643936} {"current_steps": 164165, "total_steps": 181800, "loss": 0.0086, "lr": 1.4196567784090177e-06, "epoch": 18.05995599559956, "percentage": 90.3, "elapsed_time": "6:29:10", "remaining_time": "0:41:48", "throughput": 1483.69, "total_tokens": 34644992} {"current_steps": 164170, "total_steps": 181800, "loss": 0.005, "lr": 1.4188596170090495e-06, "epoch": 18.06050605060506, "percentage": 90.3, "elapsed_time": "6:29:11", "remaining_time": "0:41:47", "throughput": 1483.69, "total_tokens": 34646048} {"current_steps": 164175, "total_steps": 181800, "loss": 0.0849, "lr": 1.418062672945139e-06, "epoch": 18.06105610561056, "percentage": 90.31, "elapsed_time": "6:29:11", "remaining_time": "0:41:46", "throughput": 1483.69, "total_tokens": 34647072} {"current_steps": 164180, "total_steps": 181800, "loss": 0.0753, "lr": 1.41726594622463e-06, "epoch": 18.061606160616062, "percentage": 90.31, "elapsed_time": "6:29:12", "remaining_time": "0:41:46", "throughput": 1483.69, "total_tokens": 34648096} {"current_steps": 164185, "total_steps": 181800, "loss": 0.019, "lr": 1.416469436854867e-06, "epoch": 18.062156215621563, "percentage": 90.31, "elapsed_time": "6:29:13", "remaining_time": "0:41:45", "throughput": 1483.69, "total_tokens": 34649056} {"current_steps": 164190, "total_steps": 181800, "loss": 0.0048, "lr": 1.4156731448431853e-06, "epoch": 18.062706270627064, "percentage": 90.31, "elapsed_time": "6:29:14", "remaining_time": "0:41:44", "throughput": 1483.69, "total_tokens": 34650112} {"current_steps": 164195, "total_steps": 181800, "loss": 0.034, "lr": 1.4148770701969295e-06, "epoch": 18.063256325632562, "percentage": 90.32, "elapsed_time": "6:29:14", "remaining_time": "0:41:44", "throughput": 1483.69, "total_tokens": 34651200} {"current_steps": 164200, "total_steps": 181800, "loss": 0.0057, "lr": 1.4140812129234321e-06, "epoch": 18.063806380638063, "percentage": 90.32, "elapsed_time": "6:29:15", "remaining_time": "0:41:43", "throughput": 1483.69, "total_tokens": 34652192} {"current_steps": 164205, "total_steps": 181800, "loss": 0.0051, "lr": 1.4132855730300294e-06, "epoch": 18.064356435643564, "percentage": 90.32, "elapsed_time": "6:29:16", "remaining_time": "0:41:42", "throughput": 1483.69, "total_tokens": 34653216} {"current_steps": 164210, "total_steps": 181800, "loss": 0.1021, "lr": 1.4124901505240596e-06, "epoch": 18.064906490649065, "percentage": 90.32, "elapsed_time": "6:29:16", "remaining_time": "0:41:41", "throughput": 1483.69, "total_tokens": 34654304} {"current_steps": 164215, "total_steps": 181800, "loss": 0.0024, "lr": 1.4116949454128476e-06, "epoch": 18.065456545654566, "percentage": 90.33, "elapsed_time": "6:29:17", "remaining_time": "0:41:41", "throughput": 1483.69, "total_tokens": 34655360} {"current_steps": 164220, "total_steps": 181800, "loss": 0.0064, "lr": 1.4108999577037263e-06, "epoch": 18.066006600660067, "percentage": 90.33, "elapsed_time": "6:29:18", "remaining_time": "0:41:40", "throughput": 1483.69, "total_tokens": 34656416} {"current_steps": 164225, "total_steps": 181800, "loss": 0.0312, "lr": 1.4101051874040177e-06, "epoch": 18.066556655665565, "percentage": 90.33, "elapsed_time": "6:29:18", "remaining_time": "0:41:39", "throughput": 1483.69, "total_tokens": 34657472} {"current_steps": 164230, "total_steps": 181800, "loss": 0.0011, "lr": 1.4093106345210494e-06, "epoch": 18.067106710671066, "percentage": 90.34, "elapsed_time": "6:29:19", "remaining_time": "0:41:39", "throughput": 1483.7, "total_tokens": 34658528} {"current_steps": 164235, "total_steps": 181800, "loss": 0.0811, "lr": 1.4085162990621486e-06, "epoch": 18.067656765676567, "percentage": 90.34, "elapsed_time": "6:29:20", "remaining_time": "0:41:38", "throughput": 1483.69, "total_tokens": 34659520} {"current_steps": 164240, "total_steps": 181800, "loss": 0.1095, "lr": 1.407722181034632e-06, "epoch": 18.068206820682068, "percentage": 90.34, "elapsed_time": "6:29:20", "remaining_time": "0:41:37", "throughput": 1483.69, "total_tokens": 34660512} {"current_steps": 164245, "total_steps": 181800, "loss": 0.064, "lr": 1.406928280445821e-06, "epoch": 18.06875687568757, "percentage": 90.34, "elapsed_time": "6:29:21", "remaining_time": "0:41:36", "throughput": 1483.7, "total_tokens": 34661664} {"current_steps": 164250, "total_steps": 181800, "loss": 0.0004, "lr": 1.406134597303027e-06, "epoch": 18.06930693069307, "percentage": 90.35, "elapsed_time": "6:29:22", "remaining_time": "0:41:36", "throughput": 1483.7, "total_tokens": 34662688} {"current_steps": 164255, "total_steps": 181800, "loss": 0.0055, "lr": 1.4053411316135718e-06, "epoch": 18.06985698569857, "percentage": 90.35, "elapsed_time": "6:29:23", "remaining_time": "0:41:35", "throughput": 1483.7, "total_tokens": 34663744} {"current_steps": 164260, "total_steps": 181800, "loss": 0.0039, "lr": 1.404547883384763e-06, "epoch": 18.07040704070407, "percentage": 90.35, "elapsed_time": "6:29:23", "remaining_time": "0:41:34", "throughput": 1483.7, "total_tokens": 34664800} {"current_steps": 164265, "total_steps": 181800, "loss": 0.0056, "lr": 1.4037548526239147e-06, "epoch": 18.07095709570957, "percentage": 90.35, "elapsed_time": "6:29:24", "remaining_time": "0:41:34", "throughput": 1483.7, "total_tokens": 34665856} {"current_steps": 164270, "total_steps": 181800, "loss": 0.0358, "lr": 1.4029620393383376e-06, "epoch": 18.07150715071507, "percentage": 90.36, "elapsed_time": "6:29:25", "remaining_time": "0:41:33", "throughput": 1483.71, "total_tokens": 34666944} {"current_steps": 164275, "total_steps": 181800, "loss": 0.0005, "lr": 1.4021694435353393e-06, "epoch": 18.072057205720572, "percentage": 90.36, "elapsed_time": "6:29:25", "remaining_time": "0:41:32", "throughput": 1483.71, "total_tokens": 34668032} {"current_steps": 164280, "total_steps": 181800, "loss": 0.0021, "lr": 1.4013770652222146e-06, "epoch": 18.072607260726073, "percentage": 90.36, "elapsed_time": "6:29:26", "remaining_time": "0:41:31", "throughput": 1483.71, "total_tokens": 34669088} {"current_steps": 164285, "total_steps": 181800, "loss": 0.0347, "lr": 1.4005849044062769e-06, "epoch": 18.073157315731574, "percentage": 90.37, "elapsed_time": "6:29:27", "remaining_time": "0:41:31", "throughput": 1483.71, "total_tokens": 34670176} {"current_steps": 164290, "total_steps": 181800, "loss": 0.1887, "lr": 1.399792961094823e-06, "epoch": 18.073707370737075, "percentage": 90.37, "elapsed_time": "6:29:27", "remaining_time": "0:41:30", "throughput": 1483.71, "total_tokens": 34671200} {"current_steps": 164295, "total_steps": 181800, "loss": 0.0006, "lr": 1.3990012352951554e-06, "epoch": 18.074257425742573, "percentage": 90.37, "elapsed_time": "6:29:28", "remaining_time": "0:41:29", "throughput": 1483.71, "total_tokens": 34672288} {"current_steps": 164300, "total_steps": 181800, "loss": 0.0014, "lr": 1.3982097270145684e-06, "epoch": 18.074807480748074, "percentage": 90.37, "elapsed_time": "6:29:29", "remaining_time": "0:41:29", "throughput": 1483.72, "total_tokens": 34673376} {"current_steps": 164305, "total_steps": 181800, "loss": 0.0297, "lr": 1.397418436260356e-06, "epoch": 18.075357535753575, "percentage": 90.38, "elapsed_time": "6:29:29", "remaining_time": "0:41:28", "throughput": 1483.72, "total_tokens": 34674400} {"current_steps": 164310, "total_steps": 181800, "loss": 0.0301, "lr": 1.3966273630398124e-06, "epoch": 18.075907590759076, "percentage": 90.38, "elapsed_time": "6:29:30", "remaining_time": "0:41:27", "throughput": 1483.72, "total_tokens": 34675392} {"current_steps": 164315, "total_steps": 181800, "loss": 0.1255, "lr": 1.3958365073602264e-06, "epoch": 18.076457645764577, "percentage": 90.38, "elapsed_time": "6:29:31", "remaining_time": "0:41:26", "throughput": 1483.72, "total_tokens": 34676512} {"current_steps": 164320, "total_steps": 181800, "loss": 0.0454, "lr": 1.3950458692288893e-06, "epoch": 18.07700770077008, "percentage": 90.39, "elapsed_time": "6:29:32", "remaining_time": "0:41:26", "throughput": 1483.72, "total_tokens": 34677568} {"current_steps": 164325, "total_steps": 181800, "loss": 0.0062, "lr": 1.3942554486530924e-06, "epoch": 18.077557755775576, "percentage": 90.39, "elapsed_time": "6:29:32", "remaining_time": "0:41:25", "throughput": 1483.72, "total_tokens": 34678592} {"current_steps": 164330, "total_steps": 181800, "loss": 0.0352, "lr": 1.3934652456401103e-06, "epoch": 18.078107810781077, "percentage": 90.39, "elapsed_time": "6:29:33", "remaining_time": "0:41:24", "throughput": 1483.72, "total_tokens": 34679680} {"current_steps": 164335, "total_steps": 181800, "loss": 0.0015, "lr": 1.3926752601972376e-06, "epoch": 18.078657865786578, "percentage": 90.39, "elapsed_time": "6:29:34", "remaining_time": "0:41:24", "throughput": 1483.72, "total_tokens": 34680672} {"current_steps": 164340, "total_steps": 181800, "loss": 0.0022, "lr": 1.391885492331743e-06, "epoch": 18.07920792079208, "percentage": 90.4, "elapsed_time": "6:29:34", "remaining_time": "0:41:23", "throughput": 1483.72, "total_tokens": 34681760} {"current_steps": 164345, "total_steps": 181800, "loss": 0.007, "lr": 1.3910959420509128e-06, "epoch": 18.07975797579758, "percentage": 90.4, "elapsed_time": "6:29:35", "remaining_time": "0:41:22", "throughput": 1483.72, "total_tokens": 34682752} {"current_steps": 164350, "total_steps": 181800, "loss": 0.005, "lr": 1.3903066093620242e-06, "epoch": 18.08030803080308, "percentage": 90.4, "elapsed_time": "6:29:36", "remaining_time": "0:41:21", "throughput": 1483.73, "total_tokens": 34683840} {"current_steps": 164355, "total_steps": 181800, "loss": 0.0567, "lr": 1.3895174942723494e-06, "epoch": 18.080858085808583, "percentage": 90.4, "elapsed_time": "6:29:36", "remaining_time": "0:41:21", "throughput": 1483.73, "total_tokens": 34684928} {"current_steps": 164360, "total_steps": 181800, "loss": 0.0595, "lr": 1.3887285967891655e-06, "epoch": 18.08140814081408, "percentage": 90.41, "elapsed_time": "6:29:37", "remaining_time": "0:41:20", "throughput": 1483.73, "total_tokens": 34685984} {"current_steps": 164365, "total_steps": 181800, "loss": 0.0015, "lr": 1.3879399169197366e-06, "epoch": 18.08195819581958, "percentage": 90.41, "elapsed_time": "6:29:38", "remaining_time": "0:41:19", "throughput": 1483.73, "total_tokens": 34687040} {"current_steps": 164370, "total_steps": 181800, "loss": 0.0019, "lr": 1.387151454671337e-06, "epoch": 18.082508250825082, "percentage": 90.41, "elapsed_time": "6:29:38", "remaining_time": "0:41:19", "throughput": 1483.73, "total_tokens": 34688096} {"current_steps": 164375, "total_steps": 181800, "loss": 0.2023, "lr": 1.3863632100512308e-06, "epoch": 18.083058305830583, "percentage": 90.42, "elapsed_time": "6:29:39", "remaining_time": "0:41:18", "throughput": 1483.73, "total_tokens": 34689088} {"current_steps": 164380, "total_steps": 181800, "loss": 0.0034, "lr": 1.3855751830666841e-06, "epoch": 18.083608360836084, "percentage": 90.42, "elapsed_time": "6:29:40", "remaining_time": "0:41:17", "throughput": 1483.73, "total_tokens": 34690144} {"current_steps": 164385, "total_steps": 181800, "loss": 0.0076, "lr": 1.3847873737249606e-06, "epoch": 18.084158415841586, "percentage": 90.42, "elapsed_time": "6:29:41", "remaining_time": "0:41:16", "throughput": 1483.73, "total_tokens": 34691136} {"current_steps": 164390, "total_steps": 181800, "loss": 0.006, "lr": 1.3839997820333183e-06, "epoch": 18.084708470847083, "percentage": 90.42, "elapsed_time": "6:29:41", "remaining_time": "0:41:16", "throughput": 1483.73, "total_tokens": 34692192} {"current_steps": 164395, "total_steps": 181800, "loss": 0.0029, "lr": 1.383212407999021e-06, "epoch": 18.085258525852584, "percentage": 90.43, "elapsed_time": "6:29:42", "remaining_time": "0:41:15", "throughput": 1483.73, "total_tokens": 34693216} {"current_steps": 164400, "total_steps": 181800, "loss": 0.018, "lr": 1.3824252516293212e-06, "epoch": 18.085808580858085, "percentage": 90.43, "elapsed_time": "6:29:43", "remaining_time": "0:41:14", "throughput": 1483.74, "total_tokens": 34694368} {"current_steps": 164405, "total_steps": 181800, "loss": 0.0155, "lr": 1.3816383129314714e-06, "epoch": 18.086358635863586, "percentage": 90.43, "elapsed_time": "6:29:43", "remaining_time": "0:41:14", "throughput": 1483.74, "total_tokens": 34695392} {"current_steps": 164410, "total_steps": 181800, "loss": 0.0991, "lr": 1.3808515919127352e-06, "epoch": 18.086908690869087, "percentage": 90.43, "elapsed_time": "6:29:44", "remaining_time": "0:41:13", "throughput": 1483.74, "total_tokens": 34696544} {"current_steps": 164415, "total_steps": 181800, "loss": 0.022, "lr": 1.3800650885803513e-06, "epoch": 18.08745874587459, "percentage": 90.44, "elapsed_time": "6:29:45", "remaining_time": "0:41:12", "throughput": 1483.74, "total_tokens": 34697568} {"current_steps": 164420, "total_steps": 181800, "loss": 0.0286, "lr": 1.3792788029415775e-06, "epoch": 18.08800880088009, "percentage": 90.44, "elapsed_time": "6:29:45", "remaining_time": "0:41:11", "throughput": 1483.74, "total_tokens": 34698624} {"current_steps": 164425, "total_steps": 181800, "loss": 0.0988, "lr": 1.3784927350036558e-06, "epoch": 18.088558855885587, "percentage": 90.44, "elapsed_time": "6:29:46", "remaining_time": "0:41:11", "throughput": 1483.75, "total_tokens": 34699680} {"current_steps": 164430, "total_steps": 181800, "loss": 0.0029, "lr": 1.3777068847738272e-06, "epoch": 18.08910891089109, "percentage": 90.45, "elapsed_time": "6:29:47", "remaining_time": "0:41:10", "throughput": 1483.75, "total_tokens": 34700864} {"current_steps": 164435, "total_steps": 181800, "loss": 0.002, "lr": 1.3769212522593417e-06, "epoch": 18.08965896589659, "percentage": 90.45, "elapsed_time": "6:29:47", "remaining_time": "0:41:09", "throughput": 1483.76, "total_tokens": 34702016} {"current_steps": 164440, "total_steps": 181800, "loss": 0.026, "lr": 1.3761358374674348e-06, "epoch": 18.09020902090209, "percentage": 90.45, "elapsed_time": "6:29:48", "remaining_time": "0:41:09", "throughput": 1483.76, "total_tokens": 34703104} {"current_steps": 164445, "total_steps": 181800, "loss": 0.0012, "lr": 1.375350640405354e-06, "epoch": 18.09075907590759, "percentage": 90.45, "elapsed_time": "6:29:49", "remaining_time": "0:41:08", "throughput": 1483.76, "total_tokens": 34704096} {"current_steps": 164450, "total_steps": 181800, "loss": 0.0361, "lr": 1.3745656610803292e-06, "epoch": 18.091309130913093, "percentage": 90.46, "elapsed_time": "6:29:50", "remaining_time": "0:41:07", "throughput": 1483.76, "total_tokens": 34705152} {"current_steps": 164455, "total_steps": 181800, "loss": 0.0073, "lr": 1.3737808994995937e-06, "epoch": 18.09185918591859, "percentage": 90.46, "elapsed_time": "6:29:50", "remaining_time": "0:41:07", "throughput": 1483.76, "total_tokens": 34706176} {"current_steps": 164460, "total_steps": 181800, "loss": 0.0119, "lr": 1.3729963556703807e-06, "epoch": 18.09240924092409, "percentage": 90.46, "elapsed_time": "6:29:51", "remaining_time": "0:41:06", "throughput": 1483.76, "total_tokens": 34707232} {"current_steps": 164465, "total_steps": 181800, "loss": 0.0054, "lr": 1.3722120295999285e-06, "epoch": 18.092959295929592, "percentage": 90.46, "elapsed_time": "6:29:52", "remaining_time": "0:41:05", "throughput": 1483.76, "total_tokens": 34708256} {"current_steps": 164470, "total_steps": 181800, "loss": 0.0868, "lr": 1.3714279212954538e-06, "epoch": 18.093509350935093, "percentage": 90.47, "elapsed_time": "6:29:52", "remaining_time": "0:41:04", "throughput": 1483.76, "total_tokens": 34709312} {"current_steps": 164475, "total_steps": 181800, "loss": 0.003, "lr": 1.3706440307641954e-06, "epoch": 18.094059405940595, "percentage": 90.47, "elapsed_time": "6:29:53", "remaining_time": "0:41:04", "throughput": 1483.77, "total_tokens": 34710464} {"current_steps": 164480, "total_steps": 181800, "loss": 0.0066, "lr": 1.3698603580133696e-06, "epoch": 18.094609460946096, "percentage": 90.47, "elapsed_time": "6:29:54", "remaining_time": "0:41:03", "throughput": 1483.77, "total_tokens": 34711488} {"current_steps": 164485, "total_steps": 181800, "loss": 0.0525, "lr": 1.3690769030502038e-06, "epoch": 18.095159515951597, "percentage": 90.48, "elapsed_time": "6:29:54", "remaining_time": "0:41:02", "throughput": 1483.77, "total_tokens": 34712576} {"current_steps": 164490, "total_steps": 181800, "loss": 0.0017, "lr": 1.3682936658819145e-06, "epoch": 18.095709570957094, "percentage": 90.48, "elapsed_time": "6:29:55", "remaining_time": "0:41:02", "throughput": 1483.77, "total_tokens": 34713664} {"current_steps": 164495, "total_steps": 181800, "loss": 0.0589, "lr": 1.367510646515724e-06, "epoch": 18.096259625962595, "percentage": 90.48, "elapsed_time": "6:29:56", "remaining_time": "0:41:01", "throughput": 1483.77, "total_tokens": 34714720} {"current_steps": 164500, "total_steps": 181800, "loss": 0.0494, "lr": 1.366727844958851e-06, "epoch": 18.096809680968097, "percentage": 90.48, "elapsed_time": "6:29:56", "remaining_time": "0:41:00", "throughput": 1483.78, "total_tokens": 34715776} {"current_steps": 164505, "total_steps": 181800, "loss": 0.0043, "lr": 1.3659452612185013e-06, "epoch": 18.097359735973598, "percentage": 90.49, "elapsed_time": "6:29:57", "remaining_time": "0:40:59", "throughput": 1483.78, "total_tokens": 34716896} {"current_steps": 164510, "total_steps": 181800, "loss": 0.0537, "lr": 1.3651628953018997e-06, "epoch": 18.0979097909791, "percentage": 90.49, "elapsed_time": "6:29:58", "remaining_time": "0:40:59", "throughput": 1483.78, "total_tokens": 34717984} {"current_steps": 164515, "total_steps": 181800, "loss": 0.0197, "lr": 1.3643807472162456e-06, "epoch": 18.0984598459846, "percentage": 90.49, "elapsed_time": "6:29:58", "remaining_time": "0:40:58", "throughput": 1483.78, "total_tokens": 34719040} {"current_steps": 164520, "total_steps": 181800, "loss": 0.0042, "lr": 1.363598816968753e-06, "epoch": 18.099009900990097, "percentage": 90.5, "elapsed_time": "6:29:59", "remaining_time": "0:40:57", "throughput": 1483.79, "total_tokens": 34720160} {"current_steps": 164525, "total_steps": 181800, "loss": 0.0115, "lr": 1.3628171045666327e-06, "epoch": 18.0995599559956, "percentage": 90.5, "elapsed_time": "6:30:00", "remaining_time": "0:40:57", "throughput": 1483.79, "total_tokens": 34721312} {"current_steps": 164530, "total_steps": 181800, "loss": 0.0019, "lr": 1.362035610017079e-06, "epoch": 18.1001100110011, "percentage": 90.5, "elapsed_time": "6:30:01", "remaining_time": "0:40:56", "throughput": 1483.79, "total_tokens": 34722336} {"current_steps": 164535, "total_steps": 181800, "loss": 0.0126, "lr": 1.3612543333273054e-06, "epoch": 18.1006600660066, "percentage": 90.5, "elapsed_time": "6:30:01", "remaining_time": "0:40:55", "throughput": 1483.79, "total_tokens": 34723392} {"current_steps": 164540, "total_steps": 181800, "loss": 0.0126, "lr": 1.360473274504509e-06, "epoch": 18.1012101210121, "percentage": 90.51, "elapsed_time": "6:30:02", "remaining_time": "0:40:54", "throughput": 1483.8, "total_tokens": 34724448} {"current_steps": 164545, "total_steps": 181800, "loss": 0.022, "lr": 1.3596924335558813e-06, "epoch": 18.101760176017603, "percentage": 90.51, "elapsed_time": "6:30:03", "remaining_time": "0:40:54", "throughput": 1483.8, "total_tokens": 34725504} {"current_steps": 164550, "total_steps": 181800, "loss": 0.0689, "lr": 1.358911810488625e-06, "epoch": 18.102310231023104, "percentage": 90.51, "elapsed_time": "6:30:03", "remaining_time": "0:40:53", "throughput": 1483.8, "total_tokens": 34726528} {"current_steps": 164555, "total_steps": 181800, "loss": 0.1102, "lr": 1.3581314053099343e-06, "epoch": 18.1028602860286, "percentage": 90.51, "elapsed_time": "6:30:04", "remaining_time": "0:40:52", "throughput": 1483.8, "total_tokens": 34727584} {"current_steps": 164560, "total_steps": 181800, "loss": 0.0023, "lr": 1.3573512180270087e-06, "epoch": 18.103410341034103, "percentage": 90.52, "elapsed_time": "6:30:05", "remaining_time": "0:40:52", "throughput": 1483.8, "total_tokens": 34728640} {"current_steps": 164565, "total_steps": 181800, "loss": 0.0025, "lr": 1.356571248647029e-06, "epoch": 18.103960396039604, "percentage": 90.52, "elapsed_time": "6:30:05", "remaining_time": "0:40:51", "throughput": 1483.8, "total_tokens": 34729696} {"current_steps": 164570, "total_steps": 181800, "loss": 0.0296, "lr": 1.3557914971771834e-06, "epoch": 18.104510451045105, "percentage": 90.52, "elapsed_time": "6:30:06", "remaining_time": "0:40:50", "throughput": 1483.81, "total_tokens": 34730816} {"current_steps": 164575, "total_steps": 181800, "loss": 0.0022, "lr": 1.355011963624664e-06, "epoch": 18.105060506050606, "percentage": 90.53, "elapsed_time": "6:30:07", "remaining_time": "0:40:49", "throughput": 1483.8, "total_tokens": 34731808} {"current_steps": 164580, "total_steps": 181800, "loss": 0.0064, "lr": 1.3542326479966506e-06, "epoch": 18.105610561056107, "percentage": 90.53, "elapsed_time": "6:30:07", "remaining_time": "0:40:49", "throughput": 1483.81, "total_tokens": 34732896} {"current_steps": 164585, "total_steps": 181800, "loss": 0.0253, "lr": 1.353453550300335e-06, "epoch": 18.106160616061604, "percentage": 90.53, "elapsed_time": "6:30:08", "remaining_time": "0:40:48", "throughput": 1483.81, "total_tokens": 34733952} {"current_steps": 164590, "total_steps": 181800, "loss": 0.0008, "lr": 1.3526746705428888e-06, "epoch": 18.106710671067106, "percentage": 90.53, "elapsed_time": "6:30:09", "remaining_time": "0:40:47", "throughput": 1483.81, "total_tokens": 34735008} {"current_steps": 164595, "total_steps": 181800, "loss": 0.1051, "lr": 1.3518960087314903e-06, "epoch": 18.107260726072607, "percentage": 90.54, "elapsed_time": "6:30:10", "remaining_time": "0:40:47", "throughput": 1483.81, "total_tokens": 34736064} {"current_steps": 164600, "total_steps": 181800, "loss": 0.0033, "lr": 1.3511175648733221e-06, "epoch": 18.107810781078108, "percentage": 90.54, "elapsed_time": "6:30:10", "remaining_time": "0:40:46", "throughput": 1483.81, "total_tokens": 34737088} {"current_steps": 164605, "total_steps": 181800, "loss": 0.0016, "lr": 1.3503393389755537e-06, "epoch": 18.10836083608361, "percentage": 90.54, "elapsed_time": "6:30:11", "remaining_time": "0:40:45", "throughput": 1483.81, "total_tokens": 34738144} {"current_steps": 164610, "total_steps": 181800, "loss": 0.0105, "lr": 1.349561331045357e-06, "epoch": 18.10891089108911, "percentage": 90.54, "elapsed_time": "6:30:12", "remaining_time": "0:40:44", "throughput": 1483.82, "total_tokens": 34739264} {"current_steps": 164615, "total_steps": 181800, "loss": 0.0927, "lr": 1.3487835410899096e-06, "epoch": 18.10946094609461, "percentage": 90.55, "elapsed_time": "6:30:12", "remaining_time": "0:40:44", "throughput": 1483.82, "total_tokens": 34740256} {"current_steps": 164620, "total_steps": 181800, "loss": 0.0015, "lr": 1.3480059691163726e-06, "epoch": 18.11001100110011, "percentage": 90.55, "elapsed_time": "6:30:13", "remaining_time": "0:40:43", "throughput": 1483.82, "total_tokens": 34741376} {"current_steps": 164625, "total_steps": 181800, "loss": 0.0018, "lr": 1.3472286151319181e-06, "epoch": 18.11056105610561, "percentage": 90.55, "elapsed_time": "6:30:14", "remaining_time": "0:40:42", "throughput": 1483.82, "total_tokens": 34742432} {"current_steps": 164630, "total_steps": 181800, "loss": 0.0355, "lr": 1.3464514791437038e-06, "epoch": 18.11111111111111, "percentage": 90.56, "elapsed_time": "6:30:14", "remaining_time": "0:40:42", "throughput": 1483.82, "total_tokens": 34743520} {"current_steps": 164635, "total_steps": 181800, "loss": 0.1018, "lr": 1.3456745611588939e-06, "epoch": 18.111661166116612, "percentage": 90.56, "elapsed_time": "6:30:15", "remaining_time": "0:40:41", "throughput": 1483.83, "total_tokens": 34744672} {"current_steps": 164640, "total_steps": 181800, "loss": 0.0129, "lr": 1.3448978611846574e-06, "epoch": 18.112211221122113, "percentage": 90.56, "elapsed_time": "6:30:16", "remaining_time": "0:40:40", "throughput": 1483.83, "total_tokens": 34745728} {"current_steps": 164645, "total_steps": 181800, "loss": 0.115, "lr": 1.3441213792281442e-06, "epoch": 18.112761276127614, "percentage": 90.56, "elapsed_time": "6:30:16", "remaining_time": "0:40:39", "throughput": 1483.83, "total_tokens": 34746816} {"current_steps": 164650, "total_steps": 181800, "loss": 0.0413, "lr": 1.3433451152965155e-06, "epoch": 18.11331133113311, "percentage": 90.57, "elapsed_time": "6:30:17", "remaining_time": "0:40:39", "throughput": 1483.83, "total_tokens": 34747872} {"current_steps": 164655, "total_steps": 181800, "loss": 0.0248, "lr": 1.3425690693969234e-06, "epoch": 18.113861386138613, "percentage": 90.57, "elapsed_time": "6:30:18", "remaining_time": "0:40:38", "throughput": 1483.84, "total_tokens": 34748960} {"current_steps": 164660, "total_steps": 181800, "loss": 0.003, "lr": 1.3417932415365153e-06, "epoch": 18.114411441144114, "percentage": 90.57, "elapsed_time": "6:30:18", "remaining_time": "0:40:37", "throughput": 1483.84, "total_tokens": 34750080} {"current_steps": 164665, "total_steps": 181800, "loss": 0.0023, "lr": 1.3410176317224465e-06, "epoch": 18.114961496149615, "percentage": 90.57, "elapsed_time": "6:30:19", "remaining_time": "0:40:37", "throughput": 1483.84, "total_tokens": 34751104} {"current_steps": 164670, "total_steps": 181800, "loss": 0.001, "lr": 1.340242239961867e-06, "epoch": 18.115511551155116, "percentage": 90.58, "elapsed_time": "6:30:20", "remaining_time": "0:40:36", "throughput": 1483.83, "total_tokens": 34752128} {"current_steps": 164675, "total_steps": 181800, "loss": 0.0473, "lr": 1.3394670662619236e-06, "epoch": 18.116061606160617, "percentage": 90.58, "elapsed_time": "6:30:21", "remaining_time": "0:40:35", "throughput": 1483.83, "total_tokens": 34753120} {"current_steps": 164680, "total_steps": 181800, "loss": 0.0832, "lr": 1.3386921106297607e-06, "epoch": 18.116611661166118, "percentage": 90.58, "elapsed_time": "6:30:21", "remaining_time": "0:40:34", "throughput": 1483.83, "total_tokens": 34754208} {"current_steps": 164685, "total_steps": 181800, "loss": 0.0519, "lr": 1.3379173730725142e-06, "epoch": 18.117161716171616, "percentage": 90.59, "elapsed_time": "6:30:22", "remaining_time": "0:40:34", "throughput": 1483.83, "total_tokens": 34755264} {"current_steps": 164690, "total_steps": 181800, "loss": 0.1136, "lr": 1.337142853597334e-06, "epoch": 18.117711771177117, "percentage": 90.59, "elapsed_time": "6:30:23", "remaining_time": "0:40:33", "throughput": 1483.83, "total_tokens": 34756352} {"current_steps": 164695, "total_steps": 181800, "loss": 0.0016, "lr": 1.336368552211345e-06, "epoch": 18.118261826182618, "percentage": 90.59, "elapsed_time": "6:30:24", "remaining_time": "0:40:32", "throughput": 1483.84, "total_tokens": 34757504} {"current_steps": 164700, "total_steps": 181800, "loss": 0.0016, "lr": 1.3355944689216998e-06, "epoch": 18.11881188118812, "percentage": 90.59, "elapsed_time": "6:30:24", "remaining_time": "0:40:32", "throughput": 1483.84, "total_tokens": 34758496} {"current_steps": 164705, "total_steps": 181800, "loss": 0.012, "lr": 1.334820603735526e-06, "epoch": 18.11936193619362, "percentage": 90.6, "elapsed_time": "6:30:25", "remaining_time": "0:40:31", "throughput": 1483.84, "total_tokens": 34759520} {"current_steps": 164710, "total_steps": 181800, "loss": 0.0021, "lr": 1.3340469566599483e-06, "epoch": 18.11991199119912, "percentage": 90.6, "elapsed_time": "6:30:26", "remaining_time": "0:40:30", "throughput": 1483.84, "total_tokens": 34760640} {"current_steps": 164715, "total_steps": 181800, "loss": 0.0379, "lr": 1.3332735277021113e-06, "epoch": 18.120462046204622, "percentage": 90.6, "elapsed_time": "6:30:26", "remaining_time": "0:40:29", "throughput": 1483.85, "total_tokens": 34761760} {"current_steps": 164720, "total_steps": 181800, "loss": 0.0014, "lr": 1.3325003168691314e-06, "epoch": 18.12101210121012, "percentage": 90.61, "elapsed_time": "6:30:27", "remaining_time": "0:40:29", "throughput": 1483.84, "total_tokens": 34762752} {"current_steps": 164725, "total_steps": 181800, "loss": 0.1468, "lr": 1.3317273241681362e-06, "epoch": 18.12156215621562, "percentage": 90.61, "elapsed_time": "6:30:28", "remaining_time": "0:40:28", "throughput": 1483.85, "total_tokens": 34763840} {"current_steps": 164730, "total_steps": 181800, "loss": 0.191, "lr": 1.3309545496062586e-06, "epoch": 18.122112211221122, "percentage": 90.61, "elapsed_time": "6:30:28", "remaining_time": "0:40:27", "throughput": 1483.85, "total_tokens": 34764832} {"current_steps": 164735, "total_steps": 181800, "loss": 0.0127, "lr": 1.330181993190613e-06, "epoch": 18.122662266226623, "percentage": 90.61, "elapsed_time": "6:30:29", "remaining_time": "0:40:27", "throughput": 1483.84, "total_tokens": 34765824} {"current_steps": 164740, "total_steps": 181800, "loss": 0.0032, "lr": 1.3294096549283236e-06, "epoch": 18.123212321232124, "percentage": 90.62, "elapsed_time": "6:30:30", "remaining_time": "0:40:26", "throughput": 1483.85, "total_tokens": 34766880} {"current_steps": 164745, "total_steps": 181800, "loss": 0.0931, "lr": 1.3286375348265045e-06, "epoch": 18.123762376237625, "percentage": 90.62, "elapsed_time": "6:30:30", "remaining_time": "0:40:25", "throughput": 1483.85, "total_tokens": 34767968} {"current_steps": 164750, "total_steps": 181800, "loss": 0.0036, "lr": 1.3278656328922807e-06, "epoch": 18.124312431243123, "percentage": 90.62, "elapsed_time": "6:30:31", "remaining_time": "0:40:24", "throughput": 1483.85, "total_tokens": 34768992} {"current_steps": 164755, "total_steps": 181800, "loss": 0.0041, "lr": 1.3270939491327543e-06, "epoch": 18.124862486248624, "percentage": 90.62, "elapsed_time": "6:30:32", "remaining_time": "0:40:24", "throughput": 1483.85, "total_tokens": 34770016} {"current_steps": 164760, "total_steps": 181800, "loss": 0.0041, "lr": 1.3263224835550425e-06, "epoch": 18.125412541254125, "percentage": 90.63, "elapsed_time": "6:30:33", "remaining_time": "0:40:23", "throughput": 1483.85, "total_tokens": 34771008} {"current_steps": 164765, "total_steps": 181800, "loss": 0.0045, "lr": 1.3255512361662613e-06, "epoch": 18.125962596259626, "percentage": 90.63, "elapsed_time": "6:30:33", "remaining_time": "0:40:22", "throughput": 1483.85, "total_tokens": 34772096} {"current_steps": 164770, "total_steps": 181800, "loss": 0.0018, "lr": 1.324780206973511e-06, "epoch": 18.126512651265127, "percentage": 90.63, "elapsed_time": "6:30:34", "remaining_time": "0:40:22", "throughput": 1483.85, "total_tokens": 34773152} {"current_steps": 164775, "total_steps": 181800, "loss": 0.0303, "lr": 1.324009395983905e-06, "epoch": 18.127062706270628, "percentage": 90.64, "elapsed_time": "6:30:35", "remaining_time": "0:40:21", "throughput": 1483.85, "total_tokens": 34774272} {"current_steps": 164780, "total_steps": 181800, "loss": 0.0034, "lr": 1.3232388032045406e-06, "epoch": 18.12761276127613, "percentage": 90.64, "elapsed_time": "6:30:35", "remaining_time": "0:40:20", "throughput": 1483.86, "total_tokens": 34775424} {"current_steps": 164785, "total_steps": 181800, "loss": 0.0023, "lr": 1.3224684286425203e-06, "epoch": 18.128162816281627, "percentage": 90.64, "elapsed_time": "6:30:36", "remaining_time": "0:40:19", "throughput": 1483.86, "total_tokens": 34776448} {"current_steps": 164790, "total_steps": 181800, "loss": 0.0381, "lr": 1.3216982723049527e-06, "epoch": 18.128712871287128, "percentage": 90.64, "elapsed_time": "6:30:37", "remaining_time": "0:40:19", "throughput": 1483.86, "total_tokens": 34777536} {"current_steps": 164795, "total_steps": 181800, "loss": 0.0196, "lr": 1.320928334198926e-06, "epoch": 18.12926292629263, "percentage": 90.65, "elapsed_time": "6:30:37", "remaining_time": "0:40:18", "throughput": 1483.87, "total_tokens": 34778656} {"current_steps": 164800, "total_steps": 181800, "loss": 0.003, "lr": 1.3201586143315432e-06, "epoch": 18.12981298129813, "percentage": 90.65, "elapsed_time": "6:30:38", "remaining_time": "0:40:17", "throughput": 1483.87, "total_tokens": 34779776} {"current_steps": 164805, "total_steps": 181800, "loss": 0.1168, "lr": 1.3193891127098984e-06, "epoch": 18.13036303630363, "percentage": 90.65, "elapsed_time": "6:30:39", "remaining_time": "0:40:17", "throughput": 1483.87, "total_tokens": 34780832} {"current_steps": 164810, "total_steps": 181800, "loss": 0.0029, "lr": 1.3186198293410722e-06, "epoch": 18.130913091309132, "percentage": 90.65, "elapsed_time": "6:30:39", "remaining_time": "0:40:16", "throughput": 1483.87, "total_tokens": 34781856} {"current_steps": 164815, "total_steps": 181800, "loss": 0.0824, "lr": 1.3178507642321703e-06, "epoch": 18.13146314631463, "percentage": 90.66, "elapsed_time": "6:30:40", "remaining_time": "0:40:15", "throughput": 1483.87, "total_tokens": 34782848} {"current_steps": 164820, "total_steps": 181800, "loss": 0.0396, "lr": 1.3170819173902698e-06, "epoch": 18.13201320132013, "percentage": 90.66, "elapsed_time": "6:30:41", "remaining_time": "0:40:14", "throughput": 1483.87, "total_tokens": 34783808} {"current_steps": 164825, "total_steps": 181800, "loss": 0.0051, "lr": 1.3163132888224655e-06, "epoch": 18.132563256325632, "percentage": 90.66, "elapsed_time": "6:30:41", "remaining_time": "0:40:14", "throughput": 1483.87, "total_tokens": 34784864} {"current_steps": 164830, "total_steps": 181800, "loss": 0.0017, "lr": 1.3155448785358376e-06, "epoch": 18.133113311331133, "percentage": 90.67, "elapsed_time": "6:30:42", "remaining_time": "0:40:13", "throughput": 1483.88, "total_tokens": 34786016} {"current_steps": 164835, "total_steps": 181800, "loss": 0.0317, "lr": 1.3147766865374638e-06, "epoch": 18.133663366336634, "percentage": 90.67, "elapsed_time": "6:30:43", "remaining_time": "0:40:12", "throughput": 1483.88, "total_tokens": 34787104} {"current_steps": 164840, "total_steps": 181800, "loss": 0.0066, "lr": 1.3140087128344275e-06, "epoch": 18.134213421342135, "percentage": 90.67, "elapsed_time": "6:30:44", "remaining_time": "0:40:12", "throughput": 1483.88, "total_tokens": 34788160} {"current_steps": 164845, "total_steps": 181800, "loss": 0.002, "lr": 1.3132409574338117e-06, "epoch": 18.134763476347636, "percentage": 90.67, "elapsed_time": "6:30:44", "remaining_time": "0:40:11", "throughput": 1483.88, "total_tokens": 34789216} {"current_steps": 164850, "total_steps": 181800, "loss": 0.134, "lr": 1.3124734203426831e-06, "epoch": 18.135313531353134, "percentage": 90.68, "elapsed_time": "6:30:45", "remaining_time": "0:40:10", "throughput": 1483.88, "total_tokens": 34790336} {"current_steps": 164855, "total_steps": 181800, "loss": 0.004, "lr": 1.3117061015681275e-06, "epoch": 18.135863586358635, "percentage": 90.68, "elapsed_time": "6:30:46", "remaining_time": "0:40:09", "throughput": 1483.89, "total_tokens": 34791392} {"current_steps": 164860, "total_steps": 181800, "loss": 0.0038, "lr": 1.3109390011172035e-06, "epoch": 18.136413641364136, "percentage": 90.68, "elapsed_time": "6:30:46", "remaining_time": "0:40:09", "throughput": 1483.89, "total_tokens": 34792448} {"current_steps": 164865, "total_steps": 181800, "loss": 0.0672, "lr": 1.3101721189969913e-06, "epoch": 18.136963696369637, "percentage": 90.68, "elapsed_time": "6:30:47", "remaining_time": "0:40:08", "throughput": 1483.89, "total_tokens": 34793504} {"current_steps": 164870, "total_steps": 181800, "loss": 0.0008, "lr": 1.3094054552145519e-06, "epoch": 18.13751375137514, "percentage": 90.69, "elapsed_time": "6:30:48", "remaining_time": "0:40:07", "throughput": 1483.89, "total_tokens": 34794464} {"current_steps": 164875, "total_steps": 181800, "loss": 0.0013, "lr": 1.3086390097769547e-06, "epoch": 18.13806380638064, "percentage": 90.69, "elapsed_time": "6:30:48", "remaining_time": "0:40:07", "throughput": 1483.89, "total_tokens": 34795520} {"current_steps": 164880, "total_steps": 181800, "loss": 0.0031, "lr": 1.3078727826912663e-06, "epoch": 18.138613861386137, "percentage": 90.69, "elapsed_time": "6:30:49", "remaining_time": "0:40:06", "throughput": 1483.89, "total_tokens": 34796704} {"current_steps": 164885, "total_steps": 181800, "loss": 0.0717, "lr": 1.3071067739645448e-06, "epoch": 18.139163916391638, "percentage": 90.7, "elapsed_time": "6:30:50", "remaining_time": "0:40:05", "throughput": 1483.9, "total_tokens": 34797760} {"current_steps": 164890, "total_steps": 181800, "loss": 0.0045, "lr": 1.3063409836038515e-06, "epoch": 18.13971397139714, "percentage": 90.7, "elapsed_time": "6:30:50", "remaining_time": "0:40:04", "throughput": 1483.9, "total_tokens": 34798848} {"current_steps": 164895, "total_steps": 181800, "loss": 0.0137, "lr": 1.3055754116162416e-06, "epoch": 18.14026402640264, "percentage": 90.7, "elapsed_time": "6:30:51", "remaining_time": "0:40:04", "throughput": 1483.9, "total_tokens": 34799936} {"current_steps": 164900, "total_steps": 181800, "loss": 0.0061, "lr": 1.3048100580087764e-06, "epoch": 18.14081408140814, "percentage": 90.7, "elapsed_time": "6:30:52", "remaining_time": "0:40:03", "throughput": 1483.9, "total_tokens": 34801024} {"current_steps": 164905, "total_steps": 181800, "loss": 0.0728, "lr": 1.3040449227885053e-06, "epoch": 18.141364136413642, "percentage": 90.71, "elapsed_time": "6:30:53", "remaining_time": "0:40:02", "throughput": 1483.9, "total_tokens": 34802016} {"current_steps": 164910, "total_steps": 181800, "loss": 0.0637, "lr": 1.3032800059624817e-06, "epoch": 18.141914191419144, "percentage": 90.71, "elapsed_time": "6:30:53", "remaining_time": "0:40:02", "throughput": 1483.9, "total_tokens": 34803008} {"current_steps": 164915, "total_steps": 181800, "loss": 0.0026, "lr": 1.3025153075377577e-06, "epoch": 18.14246424642464, "percentage": 90.71, "elapsed_time": "6:30:54", "remaining_time": "0:40:01", "throughput": 1483.9, "total_tokens": 34804032} {"current_steps": 164920, "total_steps": 181800, "loss": 0.0602, "lr": 1.3017508275213808e-06, "epoch": 18.143014301430142, "percentage": 90.72, "elapsed_time": "6:30:55", "remaining_time": "0:40:00", "throughput": 1483.9, "total_tokens": 34805120} {"current_steps": 164925, "total_steps": 181800, "loss": 0.0066, "lr": 1.3009865659203896e-06, "epoch": 18.143564356435643, "percentage": 90.72, "elapsed_time": "6:30:55", "remaining_time": "0:39:59", "throughput": 1483.91, "total_tokens": 34806240} {"current_steps": 164930, "total_steps": 181800, "loss": 0.0735, "lr": 1.300222522741834e-06, "epoch": 18.144114411441144, "percentage": 90.72, "elapsed_time": "6:30:56", "remaining_time": "0:39:59", "throughput": 1483.91, "total_tokens": 34807232} {"current_steps": 164935, "total_steps": 181800, "loss": 0.001, "lr": 1.2994586979927559e-06, "epoch": 18.144664466446645, "percentage": 90.72, "elapsed_time": "6:30:57", "remaining_time": "0:39:58", "throughput": 1483.91, "total_tokens": 34808256} {"current_steps": 164940, "total_steps": 181800, "loss": 0.0546, "lr": 1.2986950916801965e-06, "epoch": 18.145214521452147, "percentage": 90.73, "elapsed_time": "6:30:57", "remaining_time": "0:39:57", "throughput": 1483.9, "total_tokens": 34809248} {"current_steps": 164945, "total_steps": 181800, "loss": 0.0588, "lr": 1.297931703811192e-06, "epoch": 18.145764576457644, "percentage": 90.73, "elapsed_time": "6:30:58", "remaining_time": "0:39:57", "throughput": 1483.91, "total_tokens": 34810304} {"current_steps": 164950, "total_steps": 181800, "loss": 0.0161, "lr": 1.297168534392773e-06, "epoch": 18.146314631463145, "percentage": 90.73, "elapsed_time": "6:30:59", "remaining_time": "0:39:56", "throughput": 1483.91, "total_tokens": 34811360} {"current_steps": 164955, "total_steps": 181800, "loss": 0.0028, "lr": 1.2964055834319784e-06, "epoch": 18.146864686468646, "percentage": 90.73, "elapsed_time": "6:30:59", "remaining_time": "0:39:55", "throughput": 1483.91, "total_tokens": 34812416} {"current_steps": 164960, "total_steps": 181800, "loss": 0.0074, "lr": 1.295642850935841e-06, "epoch": 18.147414741474147, "percentage": 90.74, "elapsed_time": "6:31:00", "remaining_time": "0:39:54", "throughput": 1483.91, "total_tokens": 34813408} {"current_steps": 164965, "total_steps": 181800, "loss": 0.1017, "lr": 1.2948803369113915e-06, "epoch": 18.14796479647965, "percentage": 90.74, "elapsed_time": "6:31:01", "remaining_time": "0:39:54", "throughput": 1483.91, "total_tokens": 34814464} {"current_steps": 164970, "total_steps": 181800, "loss": 0.0033, "lr": 1.2941180413656552e-06, "epoch": 18.14851485148515, "percentage": 90.74, "elapsed_time": "6:31:02", "remaining_time": "0:39:53", "throughput": 1483.91, "total_tokens": 34815456} {"current_steps": 164975, "total_steps": 181800, "loss": 0.0109, "lr": 1.2933559643056536e-06, "epoch": 18.14906490649065, "percentage": 90.75, "elapsed_time": "6:31:02", "remaining_time": "0:39:52", "throughput": 1483.91, "total_tokens": 34816544} {"current_steps": 164980, "total_steps": 181800, "loss": 0.0025, "lr": 1.2925941057384177e-06, "epoch": 18.149614961496148, "percentage": 90.75, "elapsed_time": "6:31:03", "remaining_time": "0:39:52", "throughput": 1483.91, "total_tokens": 34817632} {"current_steps": 164985, "total_steps": 181800, "loss": 0.0107, "lr": 1.291832465670964e-06, "epoch": 18.15016501650165, "percentage": 90.75, "elapsed_time": "6:31:04", "remaining_time": "0:39:51", "throughput": 1483.91, "total_tokens": 34818720} {"current_steps": 164990, "total_steps": 181800, "loss": 0.0013, "lr": 1.2910710441103119e-06, "epoch": 18.15071507150715, "percentage": 90.75, "elapsed_time": "6:31:04", "remaining_time": "0:39:50", "throughput": 1483.91, "total_tokens": 34819744} {"current_steps": 164995, "total_steps": 181800, "loss": 0.0016, "lr": 1.2903098410634861e-06, "epoch": 18.15126512651265, "percentage": 90.76, "elapsed_time": "6:31:05", "remaining_time": "0:39:49", "throughput": 1483.92, "total_tokens": 34820800} {"current_steps": 165000, "total_steps": 181800, "loss": 0.0122, "lr": 1.2895488565374952e-06, "epoch": 18.151815181518153, "percentage": 90.76, "elapsed_time": "6:31:06", "remaining_time": "0:39:49", "throughput": 1483.92, "total_tokens": 34821888} {"current_steps": 165005, "total_steps": 181800, "loss": 0.0041, "lr": 1.2887880905393584e-06, "epoch": 18.152365236523654, "percentage": 90.76, "elapsed_time": "6:31:06", "remaining_time": "0:39:48", "throughput": 1483.92, "total_tokens": 34822944} {"current_steps": 165010, "total_steps": 181800, "loss": 0.0433, "lr": 1.2880275430760784e-06, "epoch": 18.15291529152915, "percentage": 90.76, "elapsed_time": "6:31:07", "remaining_time": "0:39:47", "throughput": 1483.92, "total_tokens": 34823968} {"current_steps": 165015, "total_steps": 181800, "loss": 0.0036, "lr": 1.287267214154672e-06, "epoch": 18.153465346534652, "percentage": 90.77, "elapsed_time": "6:31:08", "remaining_time": "0:39:47", "throughput": 1483.92, "total_tokens": 34825024} {"current_steps": 165020, "total_steps": 181800, "loss": 0.0016, "lr": 1.2865071037821501e-06, "epoch": 18.154015401540153, "percentage": 90.77, "elapsed_time": "6:31:08", "remaining_time": "0:39:46", "throughput": 1483.92, "total_tokens": 34826080} {"current_steps": 165025, "total_steps": 181800, "loss": 0.0639, "lr": 1.2857472119655073e-06, "epoch": 18.154565456545654, "percentage": 90.77, "elapsed_time": "6:31:09", "remaining_time": "0:39:45", "throughput": 1483.92, "total_tokens": 34827136} {"current_steps": 165030, "total_steps": 181800, "loss": 0.0039, "lr": 1.2849875387117572e-06, "epoch": 18.155115511551156, "percentage": 90.78, "elapsed_time": "6:31:10", "remaining_time": "0:39:45", "throughput": 1483.93, "total_tokens": 34828288} {"current_steps": 165035, "total_steps": 181800, "loss": 0.0372, "lr": 1.2842280840278997e-06, "epoch": 18.155665566556657, "percentage": 90.78, "elapsed_time": "6:31:10", "remaining_time": "0:39:44", "throughput": 1483.93, "total_tokens": 34829376} {"current_steps": 165040, "total_steps": 181800, "loss": 0.0012, "lr": 1.2834688479209267e-06, "epoch": 18.156215621562158, "percentage": 90.78, "elapsed_time": "6:31:11", "remaining_time": "0:39:43", "throughput": 1483.94, "total_tokens": 34830464} {"current_steps": 165045, "total_steps": 181800, "loss": 0.0196, "lr": 1.2827098303978407e-06, "epoch": 18.156765676567655, "percentage": 90.78, "elapsed_time": "6:31:12", "remaining_time": "0:39:42", "throughput": 1483.94, "total_tokens": 34831552} {"current_steps": 165050, "total_steps": 181800, "loss": 0.0678, "lr": 1.2819510314656363e-06, "epoch": 18.157315731573156, "percentage": 90.79, "elapsed_time": "6:31:13", "remaining_time": "0:39:42", "throughput": 1483.94, "total_tokens": 34832608} {"current_steps": 165055, "total_steps": 181800, "loss": 0.0412, "lr": 1.2811924511313133e-06, "epoch": 18.157865786578657, "percentage": 90.79, "elapsed_time": "6:31:13", "remaining_time": "0:39:41", "throughput": 1483.94, "total_tokens": 34833696} {"current_steps": 165060, "total_steps": 181800, "loss": 0.1976, "lr": 1.280434089401858e-06, "epoch": 18.15841584158416, "percentage": 90.79, "elapsed_time": "6:31:14", "remaining_time": "0:39:40", "throughput": 1483.94, "total_tokens": 34834752} {"current_steps": 165065, "total_steps": 181800, "loss": 0.0661, "lr": 1.2796759462842562e-06, "epoch": 18.15896589658966, "percentage": 90.79, "elapsed_time": "6:31:15", "remaining_time": "0:39:40", "throughput": 1483.95, "total_tokens": 34835840} {"current_steps": 165070, "total_steps": 181800, "loss": 0.0183, "lr": 1.2789180217854996e-06, "epoch": 18.15951595159516, "percentage": 90.8, "elapsed_time": "6:31:15", "remaining_time": "0:39:39", "throughput": 1483.95, "total_tokens": 34836928} {"current_steps": 165075, "total_steps": 181800, "loss": 0.0054, "lr": 1.2781603159125743e-06, "epoch": 18.16006600660066, "percentage": 90.8, "elapsed_time": "6:31:16", "remaining_time": "0:39:38", "throughput": 1483.95, "total_tokens": 34838016} {"current_steps": 165080, "total_steps": 181800, "loss": 0.0033, "lr": 1.2774028286724638e-06, "epoch": 18.16061606160616, "percentage": 90.8, "elapsed_time": "6:31:17", "remaining_time": "0:39:37", "throughput": 1483.95, "total_tokens": 34839040} {"current_steps": 165085, "total_steps": 181800, "loss": 0.2039, "lr": 1.2766455600721482e-06, "epoch": 18.16116611661166, "percentage": 90.81, "elapsed_time": "6:31:17", "remaining_time": "0:39:37", "throughput": 1483.95, "total_tokens": 34840064} {"current_steps": 165090, "total_steps": 181800, "loss": 0.0038, "lr": 1.2758885101186058e-06, "epoch": 18.16171617161716, "percentage": 90.81, "elapsed_time": "6:31:18", "remaining_time": "0:39:36", "throughput": 1483.95, "total_tokens": 34841152} {"current_steps": 165095, "total_steps": 181800, "loss": 0.0221, "lr": 1.2751316788188166e-06, "epoch": 18.162266226622663, "percentage": 90.81, "elapsed_time": "6:31:19", "remaining_time": "0:39:35", "throughput": 1483.96, "total_tokens": 34842208} {"current_steps": 165100, "total_steps": 181800, "loss": 0.0455, "lr": 1.2743750661797503e-06, "epoch": 18.162816281628164, "percentage": 90.81, "elapsed_time": "6:31:19", "remaining_time": "0:39:35", "throughput": 1483.96, "total_tokens": 34843232} {"current_steps": 165105, "total_steps": 181800, "loss": 0.0214, "lr": 1.2736186722083876e-06, "epoch": 18.163366336633665, "percentage": 90.82, "elapsed_time": "6:31:20", "remaining_time": "0:39:34", "throughput": 1483.96, "total_tokens": 34844256} {"current_steps": 165110, "total_steps": 181800, "loss": 0.0011, "lr": 1.2728624969116976e-06, "epoch": 18.163916391639162, "percentage": 90.82, "elapsed_time": "6:31:21", "remaining_time": "0:39:33", "throughput": 1483.96, "total_tokens": 34845376} {"current_steps": 165115, "total_steps": 181800, "loss": 0.0434, "lr": 1.2721065402966441e-06, "epoch": 18.164466446644663, "percentage": 90.82, "elapsed_time": "6:31:22", "remaining_time": "0:39:32", "throughput": 1483.96, "total_tokens": 34846368} {"current_steps": 165120, "total_steps": 181800, "loss": 0.0019, "lr": 1.2713508023702053e-06, "epoch": 18.165016501650165, "percentage": 90.83, "elapsed_time": "6:31:22", "remaining_time": "0:39:32", "throughput": 1483.96, "total_tokens": 34847392} {"current_steps": 165125, "total_steps": 181800, "loss": 0.0033, "lr": 1.2705952831393336e-06, "epoch": 18.165566556655666, "percentage": 90.83, "elapsed_time": "6:31:23", "remaining_time": "0:39:31", "throughput": 1483.96, "total_tokens": 34848512} {"current_steps": 165130, "total_steps": 181800, "loss": 0.0332, "lr": 1.2698399826110014e-06, "epoch": 18.166116611661167, "percentage": 90.83, "elapsed_time": "6:31:24", "remaining_time": "0:39:30", "throughput": 1483.97, "total_tokens": 34849600} {"current_steps": 165135, "total_steps": 181800, "loss": 0.0392, "lr": 1.2690849007921695e-06, "epoch": 18.166666666666668, "percentage": 90.83, "elapsed_time": "6:31:24", "remaining_time": "0:39:30", "throughput": 1483.97, "total_tokens": 34850656} {"current_steps": 165140, "total_steps": 181800, "loss": 0.0027, "lr": 1.268330037689791e-06, "epoch": 18.16721672167217, "percentage": 90.84, "elapsed_time": "6:31:25", "remaining_time": "0:39:29", "throughput": 1483.97, "total_tokens": 34851744} {"current_steps": 165145, "total_steps": 181800, "loss": 0.0011, "lr": 1.2675753933108297e-06, "epoch": 18.167766776677666, "percentage": 90.84, "elapsed_time": "6:31:26", "remaining_time": "0:39:28", "throughput": 1483.97, "total_tokens": 34852800} {"current_steps": 165150, "total_steps": 181800, "loss": 0.0237, "lr": 1.2668209676622356e-06, "epoch": 18.168316831683168, "percentage": 90.84, "elapsed_time": "6:31:26", "remaining_time": "0:39:27", "throughput": 1483.97, "total_tokens": 34853856} {"current_steps": 165155, "total_steps": 181800, "loss": 0.0021, "lr": 1.2660667607509669e-06, "epoch": 18.16886688668867, "percentage": 90.84, "elapsed_time": "6:31:27", "remaining_time": "0:39:27", "throughput": 1483.97, "total_tokens": 34854912} {"current_steps": 165160, "total_steps": 181800, "loss": 0.0057, "lr": 1.265312772583971e-06, "epoch": 18.16941694169417, "percentage": 90.85, "elapsed_time": "6:31:28", "remaining_time": "0:39:26", "throughput": 1483.97, "total_tokens": 34855968} {"current_steps": 165165, "total_steps": 181800, "loss": 0.0784, "lr": 1.2645590031681976e-06, "epoch": 18.16996699669967, "percentage": 90.85, "elapsed_time": "6:31:28", "remaining_time": "0:39:25", "throughput": 1483.97, "total_tokens": 34856928} {"current_steps": 165170, "total_steps": 181800, "loss": 0.0029, "lr": 1.263805452510597e-06, "epoch": 18.170517051705172, "percentage": 90.85, "elapsed_time": "6:31:29", "remaining_time": "0:39:25", "throughput": 1483.97, "total_tokens": 34857984} {"current_steps": 165175, "total_steps": 181800, "loss": 0.1127, "lr": 1.2630521206181079e-06, "epoch": 18.17106710671067, "percentage": 90.86, "elapsed_time": "6:31:30", "remaining_time": "0:39:24", "throughput": 1483.97, "total_tokens": 34859008} {"current_steps": 165180, "total_steps": 181800, "loss": 0.0104, "lr": 1.2622990074976804e-06, "epoch": 18.17161716171617, "percentage": 90.86, "elapsed_time": "6:31:31", "remaining_time": "0:39:23", "throughput": 1483.98, "total_tokens": 34860096} {"current_steps": 165185, "total_steps": 181800, "loss": 0.0049, "lr": 1.2615461131562507e-06, "epoch": 18.17216721672167, "percentage": 90.86, "elapsed_time": "6:31:31", "remaining_time": "0:39:22", "throughput": 1483.98, "total_tokens": 34861152} {"current_steps": 165190, "total_steps": 181800, "loss": 0.0026, "lr": 1.26079343760076e-06, "epoch": 18.172717271727173, "percentage": 90.86, "elapsed_time": "6:31:32", "remaining_time": "0:39:22", "throughput": 1483.98, "total_tokens": 34862208} {"current_steps": 165195, "total_steps": 181800, "loss": 0.0007, "lr": 1.260040980838148e-06, "epoch": 18.173267326732674, "percentage": 90.87, "elapsed_time": "6:31:33", "remaining_time": "0:39:21", "throughput": 1483.98, "total_tokens": 34863232} {"current_steps": 165200, "total_steps": 181800, "loss": 0.0067, "lr": 1.2592887428753418e-06, "epoch": 18.173817381738175, "percentage": 90.87, "elapsed_time": "6:31:33", "remaining_time": "0:39:20", "throughput": 1483.98, "total_tokens": 34864256} {"current_steps": 165205, "total_steps": 181800, "loss": 0.0056, "lr": 1.2585367237192835e-06, "epoch": 18.174367436743676, "percentage": 90.87, "elapsed_time": "6:31:34", "remaining_time": "0:39:20", "throughput": 1483.98, "total_tokens": 34865312} {"current_steps": 165210, "total_steps": 181800, "loss": 0.0257, "lr": 1.2577849233769008e-06, "epoch": 18.174917491749174, "percentage": 90.87, "elapsed_time": "6:31:35", "remaining_time": "0:39:19", "throughput": 1483.98, "total_tokens": 34866400} {"current_steps": 165215, "total_steps": 181800, "loss": 0.0807, "lr": 1.2570333418551184e-06, "epoch": 18.175467546754675, "percentage": 90.88, "elapsed_time": "6:31:35", "remaining_time": "0:39:18", "throughput": 1483.98, "total_tokens": 34867456} {"current_steps": 165220, "total_steps": 181800, "loss": 0.0097, "lr": 1.2562819791608644e-06, "epoch": 18.176017601760176, "percentage": 90.88, "elapsed_time": "6:31:36", "remaining_time": "0:39:17", "throughput": 1483.98, "total_tokens": 34868480} {"current_steps": 165225, "total_steps": 181800, "loss": 0.0063, "lr": 1.2555308353010692e-06, "epoch": 18.176567656765677, "percentage": 90.88, "elapsed_time": "6:31:37", "remaining_time": "0:39:17", "throughput": 1483.99, "total_tokens": 34869568} {"current_steps": 165230, "total_steps": 181800, "loss": 0.0107, "lr": 1.2547799102826551e-06, "epoch": 18.177117711771178, "percentage": 90.89, "elapsed_time": "6:31:37", "remaining_time": "0:39:16", "throughput": 1483.99, "total_tokens": 34870624} {"current_steps": 165235, "total_steps": 181800, "loss": 0.0855, "lr": 1.254029204112539e-06, "epoch": 18.17766776677668, "percentage": 90.89, "elapsed_time": "6:31:38", "remaining_time": "0:39:15", "throughput": 1483.99, "total_tokens": 34871680} {"current_steps": 165240, "total_steps": 181800, "loss": 0.0772, "lr": 1.2532787167976401e-06, "epoch": 18.178217821782177, "percentage": 90.89, "elapsed_time": "6:31:39", "remaining_time": "0:39:15", "throughput": 1483.99, "total_tokens": 34872736} {"current_steps": 165245, "total_steps": 181800, "loss": 0.0592, "lr": 1.2525284483448751e-06, "epoch": 18.178767876787678, "percentage": 90.89, "elapsed_time": "6:31:40", "remaining_time": "0:39:14", "throughput": 1483.99, "total_tokens": 34873856} {"current_steps": 165250, "total_steps": 181800, "loss": 0.006, "lr": 1.2517783987611637e-06, "epoch": 18.17931793179318, "percentage": 90.9, "elapsed_time": "6:31:40", "remaining_time": "0:39:13", "throughput": 1483.99, "total_tokens": 34874880} {"current_steps": 165255, "total_steps": 181800, "loss": 0.0015, "lr": 1.2510285680534112e-06, "epoch": 18.17986798679868, "percentage": 90.9, "elapsed_time": "6:31:41", "remaining_time": "0:39:12", "throughput": 1483.99, "total_tokens": 34875936} {"current_steps": 165260, "total_steps": 181800, "loss": 0.0028, "lr": 1.2502789562285371e-06, "epoch": 18.18041804180418, "percentage": 90.9, "elapsed_time": "6:31:42", "remaining_time": "0:39:12", "throughput": 1483.99, "total_tokens": 34876928} {"current_steps": 165265, "total_steps": 181800, "loss": 0.0028, "lr": 1.2495295632934417e-06, "epoch": 18.180968096809682, "percentage": 90.9, "elapsed_time": "6:31:42", "remaining_time": "0:39:11", "throughput": 1483.99, "total_tokens": 34877984} {"current_steps": 165270, "total_steps": 181800, "loss": 0.0842, "lr": 1.2487803892550388e-06, "epoch": 18.181518151815183, "percentage": 90.91, "elapsed_time": "6:31:43", "remaining_time": "0:39:10", "throughput": 1483.99, "total_tokens": 34879008} {"current_steps": 165275, "total_steps": 181800, "loss": 0.0095, "lr": 1.2480314341202281e-06, "epoch": 18.18206820682068, "percentage": 90.91, "elapsed_time": "6:31:44", "remaining_time": "0:39:10", "throughput": 1483.99, "total_tokens": 34880000} {"current_steps": 165280, "total_steps": 181800, "loss": 0.0111, "lr": 1.2472826978959128e-06, "epoch": 18.182618261826182, "percentage": 90.91, "elapsed_time": "6:31:44", "remaining_time": "0:39:09", "throughput": 1484.0, "total_tokens": 34881088} {"current_steps": 165285, "total_steps": 181800, "loss": 0.001, "lr": 1.2465341805889985e-06, "epoch": 18.183168316831683, "percentage": 90.92, "elapsed_time": "6:31:45", "remaining_time": "0:39:08", "throughput": 1484.0, "total_tokens": 34882176} {"current_steps": 165290, "total_steps": 181800, "loss": 0.0028, "lr": 1.2457858822063794e-06, "epoch": 18.183718371837184, "percentage": 90.92, "elapsed_time": "6:31:46", "remaining_time": "0:39:07", "throughput": 1484.0, "total_tokens": 34883200} {"current_steps": 165295, "total_steps": 181800, "loss": 0.1491, "lr": 1.2450378027549559e-06, "epoch": 18.184268426842685, "percentage": 90.92, "elapsed_time": "6:31:46", "remaining_time": "0:39:07", "throughput": 1484.0, "total_tokens": 34884256} {"current_steps": 165300, "total_steps": 181800, "loss": 0.0049, "lr": 1.2442899422416166e-06, "epoch": 18.184818481848186, "percentage": 90.92, "elapsed_time": "6:31:47", "remaining_time": "0:39:06", "throughput": 1484.0, "total_tokens": 34885312} {"current_steps": 165305, "total_steps": 181800, "loss": 0.0076, "lr": 1.243542300673256e-06, "epoch": 18.185368536853684, "percentage": 90.93, "elapsed_time": "6:31:48", "remaining_time": "0:39:05", "throughput": 1484.0, "total_tokens": 34886336} {"current_steps": 165310, "total_steps": 181800, "loss": 0.0088, "lr": 1.2427948780567716e-06, "epoch": 18.185918591859185, "percentage": 90.93, "elapsed_time": "6:31:48", "remaining_time": "0:39:05", "throughput": 1484.0, "total_tokens": 34887328} {"current_steps": 165315, "total_steps": 181800, "loss": 0.0026, "lr": 1.2420476743990439e-06, "epoch": 18.186468646864686, "percentage": 90.93, "elapsed_time": "6:31:49", "remaining_time": "0:39:04", "throughput": 1484.0, "total_tokens": 34888384} {"current_steps": 165320, "total_steps": 181800, "loss": 0.046, "lr": 1.2413006897069673e-06, "epoch": 18.187018701870187, "percentage": 90.94, "elapsed_time": "6:31:50", "remaining_time": "0:39:03", "throughput": 1484.01, "total_tokens": 34889568} {"current_steps": 165325, "total_steps": 181800, "loss": 0.0033, "lr": 1.2405539239874198e-06, "epoch": 18.187568756875688, "percentage": 90.94, "elapsed_time": "6:31:51", "remaining_time": "0:39:02", "throughput": 1484.01, "total_tokens": 34890560} {"current_steps": 165330, "total_steps": 181800, "loss": 0.0627, "lr": 1.239807377247282e-06, "epoch": 18.18811881188119, "percentage": 90.94, "elapsed_time": "6:31:51", "remaining_time": "0:39:02", "throughput": 1484.01, "total_tokens": 34891584} {"current_steps": 165335, "total_steps": 181800, "loss": 0.0436, "lr": 1.2390610494934397e-06, "epoch": 18.18866886688669, "percentage": 90.94, "elapsed_time": "6:31:52", "remaining_time": "0:39:01", "throughput": 1484.01, "total_tokens": 34892704} {"current_steps": 165340, "total_steps": 181800, "loss": 0.0013, "lr": 1.2383149407327683e-06, "epoch": 18.189218921892188, "percentage": 90.95, "elapsed_time": "6:31:53", "remaining_time": "0:39:00", "throughput": 1484.01, "total_tokens": 34893728} {"current_steps": 165345, "total_steps": 181800, "loss": 0.0028, "lr": 1.2375690509721511e-06, "epoch": 18.18976897689769, "percentage": 90.95, "elapsed_time": "6:31:53", "remaining_time": "0:39:00", "throughput": 1484.01, "total_tokens": 34894720} {"current_steps": 165350, "total_steps": 181800, "loss": 0.1029, "lr": 1.2368233802184575e-06, "epoch": 18.19031903190319, "percentage": 90.95, "elapsed_time": "6:31:54", "remaining_time": "0:38:59", "throughput": 1484.01, "total_tokens": 34895808} {"current_steps": 165355, "total_steps": 181800, "loss": 0.0618, "lr": 1.2360779284785574e-06, "epoch": 18.19086908690869, "percentage": 90.95, "elapsed_time": "6:31:55", "remaining_time": "0:38:58", "throughput": 1484.01, "total_tokens": 34896800} {"current_steps": 165360, "total_steps": 181800, "loss": 0.1382, "lr": 1.2353326957593224e-06, "epoch": 18.191419141914192, "percentage": 90.96, "elapsed_time": "6:31:55", "remaining_time": "0:38:57", "throughput": 1484.01, "total_tokens": 34897888} {"current_steps": 165365, "total_steps": 181800, "loss": 0.0026, "lr": 1.2345876820676227e-06, "epoch": 18.191969196919693, "percentage": 90.96, "elapsed_time": "6:31:56", "remaining_time": "0:38:57", "throughput": 1484.02, "total_tokens": 34898976} {"current_steps": 165370, "total_steps": 181800, "loss": 0.064, "lr": 1.2338428874103303e-06, "epoch": 18.19251925192519, "percentage": 90.96, "elapsed_time": "6:31:57", "remaining_time": "0:38:56", "throughput": 1484.01, "total_tokens": 34899968} {"current_steps": 165375, "total_steps": 181800, "loss": 0.065, "lr": 1.2330983117943007e-06, "epoch": 18.193069306930692, "percentage": 90.97, "elapsed_time": "6:31:57", "remaining_time": "0:38:55", "throughput": 1484.01, "total_tokens": 34900960} {"current_steps": 165380, "total_steps": 181800, "loss": 0.0543, "lr": 1.232353955226398e-06, "epoch": 18.193619361936193, "percentage": 90.97, "elapsed_time": "6:31:58", "remaining_time": "0:38:55", "throughput": 1484.01, "total_tokens": 34901984} {"current_steps": 165385, "total_steps": 181800, "loss": 0.0106, "lr": 1.2316098177134888e-06, "epoch": 18.194169416941694, "percentage": 90.97, "elapsed_time": "6:31:59", "remaining_time": "0:38:54", "throughput": 1484.01, "total_tokens": 34903008} {"current_steps": 165390, "total_steps": 181800, "loss": 0.0574, "lr": 1.2308658992624206e-06, "epoch": 18.194719471947195, "percentage": 90.97, "elapsed_time": "6:32:00", "remaining_time": "0:38:53", "throughput": 1484.02, "total_tokens": 34904096} {"current_steps": 165395, "total_steps": 181800, "loss": 0.0025, "lr": 1.2301221998800571e-06, "epoch": 18.195269526952696, "percentage": 90.98, "elapsed_time": "6:32:00", "remaining_time": "0:38:52", "throughput": 1484.02, "total_tokens": 34905184} {"current_steps": 165400, "total_steps": 181800, "loss": 0.0225, "lr": 1.2293787195732541e-06, "epoch": 18.195819581958197, "percentage": 90.98, "elapsed_time": "6:32:01", "remaining_time": "0:38:52", "throughput": 1484.02, "total_tokens": 34906272} {"current_steps": 165405, "total_steps": 181800, "loss": 0.0821, "lr": 1.228635458348859e-06, "epoch": 18.196369636963695, "percentage": 90.98, "elapsed_time": "6:32:02", "remaining_time": "0:38:51", "throughput": 1484.02, "total_tokens": 34907328} {"current_steps": 165410, "total_steps": 181800, "loss": 0.0021, "lr": 1.2278924162137246e-06, "epoch": 18.196919691969196, "percentage": 90.98, "elapsed_time": "6:32:02", "remaining_time": "0:38:50", "throughput": 1484.03, "total_tokens": 34908480} {"current_steps": 165415, "total_steps": 181800, "loss": 0.0018, "lr": 1.2271495931746979e-06, "epoch": 18.197469746974697, "percentage": 90.99, "elapsed_time": "6:32:03", "remaining_time": "0:38:50", "throughput": 1484.03, "total_tokens": 34909600} {"current_steps": 165420, "total_steps": 181800, "loss": 0.0006, "lr": 1.2264069892386266e-06, "epoch": 18.198019801980198, "percentage": 90.99, "elapsed_time": "6:32:04", "remaining_time": "0:38:49", "throughput": 1484.03, "total_tokens": 34910688} {"current_steps": 165425, "total_steps": 181800, "loss": 0.0591, "lr": 1.2256646044123576e-06, "epoch": 18.1985698569857, "percentage": 90.99, "elapsed_time": "6:32:04", "remaining_time": "0:38:48", "throughput": 1484.03, "total_tokens": 34911712} {"current_steps": 165430, "total_steps": 181800, "loss": 0.0049, "lr": 1.2249224387027248e-06, "epoch": 18.1991199119912, "percentage": 91.0, "elapsed_time": "6:32:05", "remaining_time": "0:38:47", "throughput": 1484.04, "total_tokens": 34912768} {"current_steps": 165435, "total_steps": 181800, "loss": 0.0008, "lr": 1.2241804921165778e-06, "epoch": 18.199669966996698, "percentage": 91.0, "elapsed_time": "6:32:06", "remaining_time": "0:38:47", "throughput": 1484.04, "total_tokens": 34913856} {"current_steps": 165440, "total_steps": 181800, "loss": 0.0034, "lr": 1.223438764660753e-06, "epoch": 18.2002200220022, "percentage": 91.0, "elapsed_time": "6:32:06", "remaining_time": "0:38:46", "throughput": 1484.04, "total_tokens": 34914880} {"current_steps": 165445, "total_steps": 181800, "loss": 0.0051, "lr": 1.2226972563420784e-06, "epoch": 18.2007700770077, "percentage": 91.0, "elapsed_time": "6:32:07", "remaining_time": "0:38:45", "throughput": 1484.04, "total_tokens": 34915936} {"current_steps": 165450, "total_steps": 181800, "loss": 0.0075, "lr": 1.221955967167393e-06, "epoch": 18.2013201320132, "percentage": 91.01, "elapsed_time": "6:32:08", "remaining_time": "0:38:45", "throughput": 1484.04, "total_tokens": 34917024} {"current_steps": 165455, "total_steps": 181800, "loss": 0.0317, "lr": 1.22121489714353e-06, "epoch": 18.201870187018702, "percentage": 91.01, "elapsed_time": "6:32:08", "remaining_time": "0:38:44", "throughput": 1484.04, "total_tokens": 34918048} {"current_steps": 165460, "total_steps": 181800, "loss": 0.0071, "lr": 1.220474046277323e-06, "epoch": 18.202420242024203, "percentage": 91.01, "elapsed_time": "6:32:09", "remaining_time": "0:38:43", "throughput": 1484.05, "total_tokens": 34919168} {"current_steps": 165465, "total_steps": 181800, "loss": 0.0041, "lr": 1.2197334145755968e-06, "epoch": 18.202970297029704, "percentage": 91.01, "elapsed_time": "6:32:10", "remaining_time": "0:38:42", "throughput": 1484.05, "total_tokens": 34920224} {"current_steps": 165470, "total_steps": 181800, "loss": 0.002, "lr": 1.2189930020451711e-06, "epoch": 18.203520352035202, "percentage": 91.02, "elapsed_time": "6:32:11", "remaining_time": "0:38:42", "throughput": 1484.05, "total_tokens": 34921216} {"current_steps": 165475, "total_steps": 181800, "loss": 0.0077, "lr": 1.2182528086928824e-06, "epoch": 18.204070407040703, "percentage": 91.02, "elapsed_time": "6:32:11", "remaining_time": "0:38:41", "throughput": 1484.05, "total_tokens": 34922272} {"current_steps": 165480, "total_steps": 181800, "loss": 0.0026, "lr": 1.217512834525536e-06, "epoch": 18.204620462046204, "percentage": 91.02, "elapsed_time": "6:32:12", "remaining_time": "0:38:40", "throughput": 1484.05, "total_tokens": 34923296} {"current_steps": 165485, "total_steps": 181800, "loss": 0.0698, "lr": 1.216773079549971e-06, "epoch": 18.205170517051705, "percentage": 91.03, "elapsed_time": "6:32:13", "remaining_time": "0:38:40", "throughput": 1484.05, "total_tokens": 34924288} {"current_steps": 165490, "total_steps": 181800, "loss": 0.0156, "lr": 1.216033543772993e-06, "epoch": 18.205720572057206, "percentage": 91.03, "elapsed_time": "6:32:13", "remaining_time": "0:38:39", "throughput": 1484.05, "total_tokens": 34925408} {"current_steps": 165495, "total_steps": 181800, "loss": 0.0102, "lr": 1.2152942272014216e-06, "epoch": 18.206270627062707, "percentage": 91.03, "elapsed_time": "6:32:14", "remaining_time": "0:38:38", "throughput": 1484.05, "total_tokens": 34926528} {"current_steps": 165500, "total_steps": 181800, "loss": 0.0311, "lr": 1.214555129842071e-06, "epoch": 18.206820682068205, "percentage": 91.03, "elapsed_time": "6:32:15", "remaining_time": "0:38:37", "throughput": 1484.06, "total_tokens": 34927584} {"current_steps": 165505, "total_steps": 181800, "loss": 0.0064, "lr": 1.213816251701752e-06, "epoch": 18.207370737073706, "percentage": 91.04, "elapsed_time": "6:32:15", "remaining_time": "0:38:37", "throughput": 1484.06, "total_tokens": 34928640} {"current_steps": 165510, "total_steps": 181800, "loss": 0.0019, "lr": 1.2130775927872734e-06, "epoch": 18.207920792079207, "percentage": 91.04, "elapsed_time": "6:32:16", "remaining_time": "0:38:36", "throughput": 1484.06, "total_tokens": 34929760} {"current_steps": 165515, "total_steps": 181800, "loss": 0.0025, "lr": 1.2123391531054461e-06, "epoch": 18.20847084708471, "percentage": 91.04, "elapsed_time": "6:32:17", "remaining_time": "0:38:35", "throughput": 1484.06, "total_tokens": 34930816} {"current_steps": 165520, "total_steps": 181800, "loss": 0.0798, "lr": 1.2116009326630734e-06, "epoch": 18.20902090209021, "percentage": 91.05, "elapsed_time": "6:32:17", "remaining_time": "0:38:35", "throughput": 1484.07, "total_tokens": 34931904} {"current_steps": 165525, "total_steps": 181800, "loss": 0.0017, "lr": 1.2108629314669606e-06, "epoch": 18.20957095709571, "percentage": 91.05, "elapsed_time": "6:32:18", "remaining_time": "0:38:34", "throughput": 1484.07, "total_tokens": 34932960} {"current_steps": 165530, "total_steps": 181800, "loss": 0.0942, "lr": 1.210125149523908e-06, "epoch": 18.21012101210121, "percentage": 91.05, "elapsed_time": "6:32:19", "remaining_time": "0:38:33", "throughput": 1484.07, "total_tokens": 34934048} {"current_steps": 165535, "total_steps": 181800, "loss": 0.0135, "lr": 1.2093875868407212e-06, "epoch": 18.21067106710671, "percentage": 91.05, "elapsed_time": "6:32:20", "remaining_time": "0:38:32", "throughput": 1484.07, "total_tokens": 34935104} {"current_steps": 165540, "total_steps": 181800, "loss": 0.0728, "lr": 1.2086502434241865e-06, "epoch": 18.21122112211221, "percentage": 91.06, "elapsed_time": "6:32:20", "remaining_time": "0:38:32", "throughput": 1484.08, "total_tokens": 34936224} {"current_steps": 165545, "total_steps": 181800, "loss": 0.0097, "lr": 1.2079131192811094e-06, "epoch": 18.21177117711771, "percentage": 91.06, "elapsed_time": "6:32:21", "remaining_time": "0:38:31", "throughput": 1484.07, "total_tokens": 34937248} {"current_steps": 165550, "total_steps": 181800, "loss": 0.0099, "lr": 1.207176214418282e-06, "epoch": 18.212321232123212, "percentage": 91.06, "elapsed_time": "6:32:22", "remaining_time": "0:38:30", "throughput": 1484.08, "total_tokens": 34938304} {"current_steps": 165555, "total_steps": 181800, "loss": 0.0541, "lr": 1.2064395288424901e-06, "epoch": 18.212871287128714, "percentage": 91.06, "elapsed_time": "6:32:22", "remaining_time": "0:38:30", "throughput": 1484.08, "total_tokens": 34939360} {"current_steps": 165560, "total_steps": 181800, "loss": 0.0035, "lr": 1.2057030625605343e-06, "epoch": 18.213421342134215, "percentage": 91.07, "elapsed_time": "6:32:23", "remaining_time": "0:38:29", "throughput": 1484.08, "total_tokens": 34940416} {"current_steps": 165565, "total_steps": 181800, "loss": 0.0047, "lr": 1.2049668155791894e-06, "epoch": 18.213971397139716, "percentage": 91.07, "elapsed_time": "6:32:24", "remaining_time": "0:38:28", "throughput": 1484.08, "total_tokens": 34941408} {"current_steps": 165570, "total_steps": 181800, "loss": 0.0153, "lr": 1.2042307879052472e-06, "epoch": 18.214521452145213, "percentage": 91.07, "elapsed_time": "6:32:24", "remaining_time": "0:38:27", "throughput": 1484.08, "total_tokens": 34942432} {"current_steps": 165575, "total_steps": 181800, "loss": 0.0394, "lr": 1.203494979545497e-06, "epoch": 18.215071507150714, "percentage": 91.08, "elapsed_time": "6:32:25", "remaining_time": "0:38:27", "throughput": 1484.08, "total_tokens": 34943456} {"current_steps": 165580, "total_steps": 181800, "loss": 0.0022, "lr": 1.2027593905067108e-06, "epoch": 18.215621562156215, "percentage": 91.08, "elapsed_time": "6:32:26", "remaining_time": "0:38:26", "throughput": 1484.08, "total_tokens": 34944576} {"current_steps": 165585, "total_steps": 181800, "loss": 0.1428, "lr": 1.2020240207956752e-06, "epoch": 18.216171617161717, "percentage": 91.08, "elapsed_time": "6:32:26", "remaining_time": "0:38:25", "throughput": 1484.08, "total_tokens": 34945632} {"current_steps": 165590, "total_steps": 181800, "loss": 0.0024, "lr": 1.2012888704191677e-06, "epoch": 18.216721672167218, "percentage": 91.08, "elapsed_time": "6:32:27", "remaining_time": "0:38:25", "throughput": 1484.08, "total_tokens": 34946624} {"current_steps": 165595, "total_steps": 181800, "loss": 0.0032, "lr": 1.20055393938395e-06, "epoch": 18.21727172717272, "percentage": 91.09, "elapsed_time": "6:32:28", "remaining_time": "0:38:24", "throughput": 1484.08, "total_tokens": 34947680} {"current_steps": 165600, "total_steps": 181800, "loss": 0.051, "lr": 1.1998192276968162e-06, "epoch": 18.217821782178216, "percentage": 91.09, "elapsed_time": "6:32:29", "remaining_time": "0:38:23", "throughput": 1484.08, "total_tokens": 34948672} {"current_steps": 165605, "total_steps": 181800, "loss": 0.0031, "lr": 1.1990847353645224e-06, "epoch": 18.218371837183717, "percentage": 91.09, "elapsed_time": "6:32:29", "remaining_time": "0:38:22", "throughput": 1484.08, "total_tokens": 34949728} {"current_steps": 165610, "total_steps": 181800, "loss": 0.0784, "lr": 1.198350462393849e-06, "epoch": 18.21892189218922, "percentage": 91.09, "elapsed_time": "6:32:30", "remaining_time": "0:38:22", "throughput": 1484.08, "total_tokens": 34950752} {"current_steps": 165615, "total_steps": 181800, "loss": 0.0135, "lr": 1.1976164087915576e-06, "epoch": 18.21947194719472, "percentage": 91.1, "elapsed_time": "6:32:31", "remaining_time": "0:38:21", "throughput": 1484.08, "total_tokens": 34951840} {"current_steps": 165620, "total_steps": 181800, "loss": 0.0061, "lr": 1.196882574564412e-06, "epoch": 18.22002200220022, "percentage": 91.1, "elapsed_time": "6:32:31", "remaining_time": "0:38:20", "throughput": 1484.08, "total_tokens": 34952800} {"current_steps": 165625, "total_steps": 181800, "loss": 0.0972, "lr": 1.196148959719176e-06, "epoch": 18.22057205720572, "percentage": 91.1, "elapsed_time": "6:32:32", "remaining_time": "0:38:20", "throughput": 1484.08, "total_tokens": 34953888} {"current_steps": 165630, "total_steps": 181800, "loss": 0.0019, "lr": 1.195415564262617e-06, "epoch": 18.221122112211223, "percentage": 91.11, "elapsed_time": "6:32:33", "remaining_time": "0:38:19", "throughput": 1484.09, "total_tokens": 34954976} {"current_steps": 165635, "total_steps": 181800, "loss": 0.007, "lr": 1.1946823882014874e-06, "epoch": 18.22167216721672, "percentage": 91.11, "elapsed_time": "6:32:33", "remaining_time": "0:38:18", "throughput": 1484.09, "total_tokens": 34956000} {"current_steps": 165640, "total_steps": 181800, "loss": 0.0423, "lr": 1.1939494315425487e-06, "epoch": 18.22222222222222, "percentage": 91.11, "elapsed_time": "6:32:34", "remaining_time": "0:38:18", "throughput": 1484.09, "total_tokens": 34957056} {"current_steps": 165645, "total_steps": 181800, "loss": 0.0311, "lr": 1.1932166942925538e-06, "epoch": 18.222772277227723, "percentage": 91.11, "elapsed_time": "6:32:35", "remaining_time": "0:38:17", "throughput": 1484.09, "total_tokens": 34958112} {"current_steps": 165650, "total_steps": 181800, "loss": 0.001, "lr": 1.1924841764582584e-06, "epoch": 18.223322332233224, "percentage": 91.12, "elapsed_time": "6:32:35", "remaining_time": "0:38:16", "throughput": 1484.09, "total_tokens": 34959232} {"current_steps": 165655, "total_steps": 181800, "loss": 0.0012, "lr": 1.1917518780464126e-06, "epoch": 18.223872387238725, "percentage": 91.12, "elapsed_time": "6:32:36", "remaining_time": "0:38:15", "throughput": 1484.1, "total_tokens": 34960320} {"current_steps": 165660, "total_steps": 181800, "loss": 0.0087, "lr": 1.191019799063761e-06, "epoch": 18.224422442244226, "percentage": 91.12, "elapsed_time": "6:32:37", "remaining_time": "0:38:15", "throughput": 1484.1, "total_tokens": 34961344} {"current_steps": 165665, "total_steps": 181800, "loss": 0.0195, "lr": 1.1902879395170624e-06, "epoch": 18.224972497249723, "percentage": 91.12, "elapsed_time": "6:32:38", "remaining_time": "0:38:14", "throughput": 1484.09, "total_tokens": 34962336} {"current_steps": 165670, "total_steps": 181800, "loss": 0.0007, "lr": 1.1895562994130499e-06, "epoch": 18.225522552255224, "percentage": 91.13, "elapsed_time": "6:32:38", "remaining_time": "0:38:13", "throughput": 1484.09, "total_tokens": 34963328} {"current_steps": 165675, "total_steps": 181800, "loss": 0.0265, "lr": 1.1888248787584737e-06, "epoch": 18.226072607260726, "percentage": 91.13, "elapsed_time": "6:32:39", "remaining_time": "0:38:13", "throughput": 1484.09, "total_tokens": 34964352} {"current_steps": 165680, "total_steps": 181800, "loss": 0.0034, "lr": 1.1880936775600704e-06, "epoch": 18.226622662266227, "percentage": 91.13, "elapsed_time": "6:32:40", "remaining_time": "0:38:12", "throughput": 1484.1, "total_tokens": 34965440} {"current_steps": 165685, "total_steps": 181800, "loss": 0.081, "lr": 1.1873626958245814e-06, "epoch": 18.227172717271728, "percentage": 91.14, "elapsed_time": "6:32:40", "remaining_time": "0:38:11", "throughput": 1484.1, "total_tokens": 34966496} {"current_steps": 165690, "total_steps": 181800, "loss": 0.0679, "lr": 1.186631933558749e-06, "epoch": 18.22772277227723, "percentage": 91.14, "elapsed_time": "6:32:41", "remaining_time": "0:38:10", "throughput": 1484.1, "total_tokens": 34967584} {"current_steps": 165695, "total_steps": 181800, "loss": 0.0025, "lr": 1.1859013907692979e-06, "epoch": 18.22827282728273, "percentage": 91.14, "elapsed_time": "6:32:42", "remaining_time": "0:38:10", "throughput": 1484.1, "total_tokens": 34968672} {"current_steps": 165700, "total_steps": 181800, "loss": 0.0073, "lr": 1.18517106746297e-06, "epoch": 18.228822882288227, "percentage": 91.14, "elapsed_time": "6:32:42", "remaining_time": "0:38:09", "throughput": 1484.1, "total_tokens": 34969728} {"current_steps": 165705, "total_steps": 181800, "loss": 0.021, "lr": 1.1844409636464938e-06, "epoch": 18.22937293729373, "percentage": 91.15, "elapsed_time": "6:32:43", "remaining_time": "0:38:08", "throughput": 1484.1, "total_tokens": 34970752} {"current_steps": 165710, "total_steps": 181800, "loss": 0.0033, "lr": 1.1837110793265937e-06, "epoch": 18.22992299229923, "percentage": 91.15, "elapsed_time": "6:32:44", "remaining_time": "0:38:08", "throughput": 1484.11, "total_tokens": 34971840} {"current_steps": 165715, "total_steps": 181800, "loss": 0.0058, "lr": 1.182981414510001e-06, "epoch": 18.23047304730473, "percentage": 91.15, "elapsed_time": "6:32:44", "remaining_time": "0:38:07", "throughput": 1484.11, "total_tokens": 34972896} {"current_steps": 165720, "total_steps": 181800, "loss": 0.0049, "lr": 1.1822519692034406e-06, "epoch": 18.231023102310232, "percentage": 91.16, "elapsed_time": "6:32:45", "remaining_time": "0:38:06", "throughput": 1484.11, "total_tokens": 34973984} {"current_steps": 165725, "total_steps": 181800, "loss": 0.0023, "lr": 1.1815227434136378e-06, "epoch": 18.231573157315733, "percentage": 91.16, "elapsed_time": "6:32:46", "remaining_time": "0:38:05", "throughput": 1484.11, "total_tokens": 34975008} {"current_steps": 165730, "total_steps": 181800, "loss": 0.0463, "lr": 1.1807937371473094e-06, "epoch": 18.23212321232123, "percentage": 91.16, "elapsed_time": "6:32:47", "remaining_time": "0:38:05", "throughput": 1484.11, "total_tokens": 34976064} {"current_steps": 165735, "total_steps": 181800, "loss": 0.0241, "lr": 1.180064950411172e-06, "epoch": 18.23267326732673, "percentage": 91.16, "elapsed_time": "6:32:47", "remaining_time": "0:38:04", "throughput": 1484.11, "total_tokens": 34977152} {"current_steps": 165740, "total_steps": 181800, "loss": 0.0117, "lr": 1.1793363832119486e-06, "epoch": 18.233223322332233, "percentage": 91.17, "elapsed_time": "6:32:48", "remaining_time": "0:38:03", "throughput": 1484.11, "total_tokens": 34978144} {"current_steps": 165745, "total_steps": 181800, "loss": 0.0615, "lr": 1.17860803555635e-06, "epoch": 18.233773377337734, "percentage": 91.17, "elapsed_time": "6:32:49", "remaining_time": "0:38:03", "throughput": 1484.12, "total_tokens": 34979264} {"current_steps": 165750, "total_steps": 181800, "loss": 0.112, "lr": 1.1778799074510932e-06, "epoch": 18.234323432343235, "percentage": 91.17, "elapsed_time": "6:32:49", "remaining_time": "0:38:02", "throughput": 1484.12, "total_tokens": 34980288} {"current_steps": 165755, "total_steps": 181800, "loss": 0.1341, "lr": 1.1771519989028868e-06, "epoch": 18.234873487348736, "percentage": 91.17, "elapsed_time": "6:32:50", "remaining_time": "0:38:01", "throughput": 1484.12, "total_tokens": 34981312} {"current_steps": 165760, "total_steps": 181800, "loss": 0.0672, "lr": 1.1764243099184364e-06, "epoch": 18.235423542354237, "percentage": 91.18, "elapsed_time": "6:32:51", "remaining_time": "0:38:00", "throughput": 1484.12, "total_tokens": 34982336} {"current_steps": 165765, "total_steps": 181800, "loss": 0.0072, "lr": 1.1756968405044532e-06, "epoch": 18.235973597359735, "percentage": 91.18, "elapsed_time": "6:32:51", "remaining_time": "0:38:00", "throughput": 1484.12, "total_tokens": 34983360} {"current_steps": 165770, "total_steps": 181800, "loss": 0.0238, "lr": 1.1749695906676377e-06, "epoch": 18.236523652365236, "percentage": 91.18, "elapsed_time": "6:32:52", "remaining_time": "0:37:59", "throughput": 1484.12, "total_tokens": 34984448} {"current_steps": 165775, "total_steps": 181800, "loss": 0.0048, "lr": 1.1742425604146956e-06, "epoch": 18.237073707370737, "percentage": 91.19, "elapsed_time": "6:32:53", "remaining_time": "0:37:58", "throughput": 1484.12, "total_tokens": 34985504} {"current_steps": 165780, "total_steps": 181800, "loss": 0.0985, "lr": 1.1735157497523325e-06, "epoch": 18.237623762376238, "percentage": 91.19, "elapsed_time": "6:32:53", "remaining_time": "0:37:58", "throughput": 1484.12, "total_tokens": 34986560} {"current_steps": 165785, "total_steps": 181800, "loss": 0.0424, "lr": 1.1727891586872348e-06, "epoch": 18.23817381738174, "percentage": 91.19, "elapsed_time": "6:32:54", "remaining_time": "0:37:57", "throughput": 1484.12, "total_tokens": 34987552} {"current_steps": 165790, "total_steps": 181800, "loss": 0.0589, "lr": 1.1720627872261108e-06, "epoch": 18.23872387238724, "percentage": 91.19, "elapsed_time": "6:32:55", "remaining_time": "0:37:56", "throughput": 1484.12, "total_tokens": 34988608} {"current_steps": 165795, "total_steps": 181800, "loss": 0.0992, "lr": 1.1713366353756472e-06, "epoch": 18.239273927392738, "percentage": 91.2, "elapsed_time": "6:32:55", "remaining_time": "0:37:55", "throughput": 1484.12, "total_tokens": 34989632} {"current_steps": 165800, "total_steps": 181800, "loss": 0.1431, "lr": 1.1706107031425383e-06, "epoch": 18.23982398239824, "percentage": 91.2, "elapsed_time": "6:32:56", "remaining_time": "0:37:55", "throughput": 1484.12, "total_tokens": 34990656} {"current_steps": 165805, "total_steps": 181800, "loss": 0.0542, "lr": 1.1698849905334819e-06, "epoch": 18.24037403740374, "percentage": 91.2, "elapsed_time": "6:32:57", "remaining_time": "0:37:54", "throughput": 1484.12, "total_tokens": 34991680} {"current_steps": 165810, "total_steps": 181800, "loss": 0.034, "lr": 1.1691594975551557e-06, "epoch": 18.24092409240924, "percentage": 91.2, "elapsed_time": "6:32:58", "remaining_time": "0:37:53", "throughput": 1484.12, "total_tokens": 34992736} {"current_steps": 165815, "total_steps": 181800, "loss": 0.1035, "lr": 1.1684342242142544e-06, "epoch": 18.241474147414742, "percentage": 91.21, "elapsed_time": "6:32:58", "remaining_time": "0:37:53", "throughput": 1484.12, "total_tokens": 34993760} {"current_steps": 165820, "total_steps": 181800, "loss": 0.0026, "lr": 1.1677091705174614e-06, "epoch": 18.242024202420243, "percentage": 91.21, "elapsed_time": "6:32:59", "remaining_time": "0:37:52", "throughput": 1484.12, "total_tokens": 34994784} {"current_steps": 165825, "total_steps": 181800, "loss": 0.0024, "lr": 1.1669843364714521e-06, "epoch": 18.242574257425744, "percentage": 91.21, "elapsed_time": "6:33:00", "remaining_time": "0:37:51", "throughput": 1484.13, "total_tokens": 34995872} {"current_steps": 165830, "total_steps": 181800, "loss": 0.003, "lr": 1.1662597220829103e-06, "epoch": 18.24312431243124, "percentage": 91.22, "elapsed_time": "6:33:00", "remaining_time": "0:37:50", "throughput": 1484.13, "total_tokens": 34996960} {"current_steps": 165835, "total_steps": 181800, "loss": 0.0019, "lr": 1.165535327358519e-06, "epoch": 18.243674367436743, "percentage": 91.22, "elapsed_time": "6:33:01", "remaining_time": "0:37:50", "throughput": 1484.13, "total_tokens": 34998016} {"current_steps": 165840, "total_steps": 181800, "loss": 0.007, "lr": 1.1648111523049537e-06, "epoch": 18.244224422442244, "percentage": 91.22, "elapsed_time": "6:33:02", "remaining_time": "0:37:49", "throughput": 1484.13, "total_tokens": 34999072} {"current_steps": 165845, "total_steps": 181800, "loss": 0.003, "lr": 1.164087196928887e-06, "epoch": 18.244774477447745, "percentage": 91.22, "elapsed_time": "6:33:02", "remaining_time": "0:37:48", "throughput": 1484.13, "total_tokens": 35000096} {"current_steps": 165850, "total_steps": 181800, "loss": 0.0189, "lr": 1.1633634612369882e-06, "epoch": 18.245324532453246, "percentage": 91.23, "elapsed_time": "6:33:03", "remaining_time": "0:37:48", "throughput": 1484.13, "total_tokens": 35001120} {"current_steps": 165855, "total_steps": 181800, "loss": 0.0105, "lr": 1.1626399452359299e-06, "epoch": 18.245874587458747, "percentage": 91.23, "elapsed_time": "6:33:04", "remaining_time": "0:37:47", "throughput": 1484.13, "total_tokens": 35002144} {"current_steps": 165860, "total_steps": 181800, "loss": 0.0051, "lr": 1.1619166489323818e-06, "epoch": 18.246424642464245, "percentage": 91.23, "elapsed_time": "6:33:04", "remaining_time": "0:37:46", "throughput": 1484.13, "total_tokens": 35003200} {"current_steps": 165865, "total_steps": 181800, "loss": 0.1578, "lr": 1.1611935723330108e-06, "epoch": 18.246974697469746, "percentage": 91.23, "elapsed_time": "6:33:05", "remaining_time": "0:37:45", "throughput": 1484.13, "total_tokens": 35004288} {"current_steps": 165870, "total_steps": 181800, "loss": 0.1065, "lr": 1.160470715444481e-06, "epoch": 18.247524752475247, "percentage": 91.24, "elapsed_time": "6:33:06", "remaining_time": "0:37:45", "throughput": 1484.13, "total_tokens": 35005312} {"current_steps": 165875, "total_steps": 181800, "loss": 0.0258, "lr": 1.159748078273451e-06, "epoch": 18.248074807480748, "percentage": 91.24, "elapsed_time": "6:33:07", "remaining_time": "0:37:44", "throughput": 1484.14, "total_tokens": 35006400} {"current_steps": 165880, "total_steps": 181800, "loss": 0.0032, "lr": 1.1590256608265849e-06, "epoch": 18.24862486248625, "percentage": 91.24, "elapsed_time": "6:33:07", "remaining_time": "0:37:43", "throughput": 1484.14, "total_tokens": 35007424} {"current_steps": 165885, "total_steps": 181800, "loss": 0.0008, "lr": 1.1583034631105354e-06, "epoch": 18.24917491749175, "percentage": 91.25, "elapsed_time": "6:33:08", "remaining_time": "0:37:43", "throughput": 1484.14, "total_tokens": 35008480} {"current_steps": 165890, "total_steps": 181800, "loss": 0.0406, "lr": 1.1575814851319644e-06, "epoch": 18.24972497249725, "percentage": 91.25, "elapsed_time": "6:33:09", "remaining_time": "0:37:42", "throughput": 1484.14, "total_tokens": 35009504} {"current_steps": 165895, "total_steps": 181800, "loss": 0.0127, "lr": 1.1568597268975272e-06, "epoch": 18.25027502750275, "percentage": 91.25, "elapsed_time": "6:33:09", "remaining_time": "0:37:41", "throughput": 1484.14, "total_tokens": 35010528} {"current_steps": 165900, "total_steps": 181800, "loss": 0.0025, "lr": 1.1561381884138688e-06, "epoch": 18.25082508250825, "percentage": 91.25, "elapsed_time": "6:33:10", "remaining_time": "0:37:40", "throughput": 1484.14, "total_tokens": 35011552} {"current_steps": 165905, "total_steps": 181800, "loss": 0.0479, "lr": 1.155416869687645e-06, "epoch": 18.25137513751375, "percentage": 91.26, "elapsed_time": "6:33:11", "remaining_time": "0:37:40", "throughput": 1484.14, "total_tokens": 35012640} {"current_steps": 165910, "total_steps": 181800, "loss": 0.0094, "lr": 1.154695770725503e-06, "epoch": 18.251925192519252, "percentage": 91.26, "elapsed_time": "6:33:11", "remaining_time": "0:37:39", "throughput": 1484.14, "total_tokens": 35013696} {"current_steps": 165915, "total_steps": 181800, "loss": 0.0823, "lr": 1.1539748915340847e-06, "epoch": 18.252475247524753, "percentage": 91.26, "elapsed_time": "6:33:12", "remaining_time": "0:37:38", "throughput": 1484.15, "total_tokens": 35014752} {"current_steps": 165920, "total_steps": 181800, "loss": 0.021, "lr": 1.1532542321200407e-06, "epoch": 18.253025302530254, "percentage": 91.27, "elapsed_time": "6:33:13", "remaining_time": "0:37:38", "throughput": 1484.15, "total_tokens": 35015776} {"current_steps": 165925, "total_steps": 181800, "loss": 0.0024, "lr": 1.152533792490007e-06, "epoch": 18.253575357535752, "percentage": 91.27, "elapsed_time": "6:33:13", "remaining_time": "0:37:37", "throughput": 1484.15, "total_tokens": 35016832} {"current_steps": 165930, "total_steps": 181800, "loss": 0.0039, "lr": 1.1518135726506312e-06, "epoch": 18.254125412541253, "percentage": 91.27, "elapsed_time": "6:33:14", "remaining_time": "0:37:36", "throughput": 1484.15, "total_tokens": 35017856} {"current_steps": 165935, "total_steps": 181800, "loss": 0.001, "lr": 1.1510935726085414e-06, "epoch": 18.254675467546754, "percentage": 91.27, "elapsed_time": "6:33:15", "remaining_time": "0:37:35", "throughput": 1484.15, "total_tokens": 35019008} {"current_steps": 165940, "total_steps": 181800, "loss": 0.0303, "lr": 1.1503737923703821e-06, "epoch": 18.255225522552255, "percentage": 91.28, "elapsed_time": "6:33:15", "remaining_time": "0:37:35", "throughput": 1484.15, "total_tokens": 35020096} {"current_steps": 165945, "total_steps": 181800, "loss": 0.0061, "lr": 1.1496542319427789e-06, "epoch": 18.255775577557756, "percentage": 91.28, "elapsed_time": "6:33:16", "remaining_time": "0:37:34", "throughput": 1484.16, "total_tokens": 35021152} {"current_steps": 165950, "total_steps": 181800, "loss": 0.0008, "lr": 1.1489348913323706e-06, "epoch": 18.256325632563257, "percentage": 91.28, "elapsed_time": "6:33:17", "remaining_time": "0:37:33", "throughput": 1484.16, "total_tokens": 35022240} {"current_steps": 165955, "total_steps": 181800, "loss": 0.0009, "lr": 1.1482157705457852e-06, "epoch": 18.25687568756876, "percentage": 91.28, "elapsed_time": "6:33:18", "remaining_time": "0:37:33", "throughput": 1484.16, "total_tokens": 35023328} {"current_steps": 165960, "total_steps": 181800, "loss": 0.0047, "lr": 1.1474968695896482e-06, "epoch": 18.257425742574256, "percentage": 91.29, "elapsed_time": "6:33:18", "remaining_time": "0:37:32", "throughput": 1484.16, "total_tokens": 35024416} {"current_steps": 165965, "total_steps": 181800, "loss": 0.027, "lr": 1.1467781884705874e-06, "epoch": 18.257975797579757, "percentage": 91.29, "elapsed_time": "6:33:19", "remaining_time": "0:37:31", "throughput": 1484.16, "total_tokens": 35025472} {"current_steps": 165970, "total_steps": 181800, "loss": 0.0036, "lr": 1.1460597271952257e-06, "epoch": 18.258525852585258, "percentage": 91.29, "elapsed_time": "6:33:20", "remaining_time": "0:37:30", "throughput": 1484.17, "total_tokens": 35026528} {"current_steps": 165975, "total_steps": 181800, "loss": 0.0038, "lr": 1.145341485770185e-06, "epoch": 18.25907590759076, "percentage": 91.3, "elapsed_time": "6:33:20", "remaining_time": "0:37:30", "throughput": 1484.17, "total_tokens": 35027584} {"current_steps": 165980, "total_steps": 181800, "loss": 0.0079, "lr": 1.144623464202088e-06, "epoch": 18.25962596259626, "percentage": 91.3, "elapsed_time": "6:33:21", "remaining_time": "0:37:29", "throughput": 1484.17, "total_tokens": 35028576} {"current_steps": 165985, "total_steps": 181800, "loss": 0.1114, "lr": 1.1439056624975465e-06, "epoch": 18.26017601760176, "percentage": 91.3, "elapsed_time": "6:33:22", "remaining_time": "0:37:28", "throughput": 1484.17, "total_tokens": 35029600} {"current_steps": 165990, "total_steps": 181800, "loss": 0.002, "lr": 1.1431880806631822e-06, "epoch": 18.260726072607262, "percentage": 91.3, "elapsed_time": "6:33:22", "remaining_time": "0:37:28", "throughput": 1484.17, "total_tokens": 35030624} {"current_steps": 165995, "total_steps": 181800, "loss": 0.0043, "lr": 1.1424707187056072e-06, "epoch": 18.26127612761276, "percentage": 91.31, "elapsed_time": "6:33:23", "remaining_time": "0:37:27", "throughput": 1484.17, "total_tokens": 35031680} {"current_steps": 166000, "total_steps": 181800, "loss": 0.1191, "lr": 1.1417535766314268e-06, "epoch": 18.26182618261826, "percentage": 91.31, "elapsed_time": "6:33:24", "remaining_time": "0:37:26", "throughput": 1484.17, "total_tokens": 35032736} {"current_steps": 166005, "total_steps": 181800, "loss": 0.0015, "lr": 1.1410366544472556e-06, "epoch": 18.262376237623762, "percentage": 91.31, "elapsed_time": "6:33:24", "remaining_time": "0:37:25", "throughput": 1484.17, "total_tokens": 35033760} {"current_steps": 166010, "total_steps": 181800, "loss": 0.0007, "lr": 1.1403199521597047e-06, "epoch": 18.262926292629263, "percentage": 91.31, "elapsed_time": "6:33:25", "remaining_time": "0:37:25", "throughput": 1484.17, "total_tokens": 35034784} {"current_steps": 166015, "total_steps": 181800, "loss": 0.0061, "lr": 1.1396034697753717e-06, "epoch": 18.263476347634764, "percentage": 91.32, "elapsed_time": "6:33:26", "remaining_time": "0:37:24", "throughput": 1484.17, "total_tokens": 35035840} {"current_steps": 166020, "total_steps": 181800, "loss": 0.0375, "lr": 1.1388872073008704e-06, "epoch": 18.264026402640265, "percentage": 91.32, "elapsed_time": "6:33:27", "remaining_time": "0:37:23", "throughput": 1484.17, "total_tokens": 35036928} {"current_steps": 166025, "total_steps": 181800, "loss": 0.0246, "lr": 1.1381711647427907e-06, "epoch": 18.264576457645763, "percentage": 91.32, "elapsed_time": "6:33:27", "remaining_time": "0:37:23", "throughput": 1484.18, "total_tokens": 35038080} {"current_steps": 166030, "total_steps": 181800, "loss": 0.0041, "lr": 1.1374553421077349e-06, "epoch": 18.265126512651264, "percentage": 91.33, "elapsed_time": "6:33:28", "remaining_time": "0:37:22", "throughput": 1484.18, "total_tokens": 35039232} {"current_steps": 166035, "total_steps": 181800, "loss": 0.0074, "lr": 1.1367397394023094e-06, "epoch": 18.265676567656765, "percentage": 91.33, "elapsed_time": "6:33:29", "remaining_time": "0:37:21", "throughput": 1484.18, "total_tokens": 35040256} {"current_steps": 166040, "total_steps": 181800, "loss": 0.0028, "lr": 1.1360243566330975e-06, "epoch": 18.266226622662266, "percentage": 91.33, "elapsed_time": "6:33:29", "remaining_time": "0:37:20", "throughput": 1484.19, "total_tokens": 35041376} {"current_steps": 166045, "total_steps": 181800, "loss": 0.1133, "lr": 1.1353091938067023e-06, "epoch": 18.266776677667767, "percentage": 91.33, "elapsed_time": "6:33:30", "remaining_time": "0:37:20", "throughput": 1484.19, "total_tokens": 35042432} {"current_steps": 166050, "total_steps": 181800, "loss": 0.1209, "lr": 1.1345942509297076e-06, "epoch": 18.26732673267327, "percentage": 91.34, "elapsed_time": "6:33:31", "remaining_time": "0:37:19", "throughput": 1484.19, "total_tokens": 35043456} {"current_steps": 166055, "total_steps": 181800, "loss": 0.0023, "lr": 1.1338795280087106e-06, "epoch": 18.26787678767877, "percentage": 91.34, "elapsed_time": "6:33:31", "remaining_time": "0:37:18", "throughput": 1484.19, "total_tokens": 35044480} {"current_steps": 166060, "total_steps": 181800, "loss": 0.0061, "lr": 1.1331650250502895e-06, "epoch": 18.268426842684267, "percentage": 91.34, "elapsed_time": "6:33:32", "remaining_time": "0:37:18", "throughput": 1484.19, "total_tokens": 35045568} {"current_steps": 166065, "total_steps": 181800, "loss": 0.0092, "lr": 1.1324507420610336e-06, "epoch": 18.268976897689768, "percentage": 91.34, "elapsed_time": "6:33:33", "remaining_time": "0:37:17", "throughput": 1484.19, "total_tokens": 35046592} {"current_steps": 166070, "total_steps": 181800, "loss": 0.0494, "lr": 1.1317366790475292e-06, "epoch": 18.26952695269527, "percentage": 91.35, "elapsed_time": "6:33:34", "remaining_time": "0:37:16", "throughput": 1484.19, "total_tokens": 35047648} {"current_steps": 166075, "total_steps": 181800, "loss": 0.0341, "lr": 1.1310228360163544e-06, "epoch": 18.27007700770077, "percentage": 91.35, "elapsed_time": "6:33:34", "remaining_time": "0:37:15", "throughput": 1484.19, "total_tokens": 35048672} {"current_steps": 166080, "total_steps": 181800, "loss": 0.0803, "lr": 1.1303092129740872e-06, "epoch": 18.27062706270627, "percentage": 91.35, "elapsed_time": "6:33:35", "remaining_time": "0:37:15", "throughput": 1484.19, "total_tokens": 35049728} {"current_steps": 166085, "total_steps": 181800, "loss": 0.0822, "lr": 1.1295958099273057e-06, "epoch": 18.271177117711773, "percentage": 91.36, "elapsed_time": "6:33:36", "remaining_time": "0:37:14", "throughput": 1484.19, "total_tokens": 35050816} {"current_steps": 166090, "total_steps": 181800, "loss": 0.0085, "lr": 1.1288826268825852e-06, "epoch": 18.27172717271727, "percentage": 91.36, "elapsed_time": "6:33:36", "remaining_time": "0:37:13", "throughput": 1484.2, "total_tokens": 35051904} {"current_steps": 166095, "total_steps": 181800, "loss": 0.0787, "lr": 1.128169663846504e-06, "epoch": 18.27227722772277, "percentage": 91.36, "elapsed_time": "6:33:37", "remaining_time": "0:37:13", "throughput": 1484.2, "total_tokens": 35053024} {"current_steps": 166100, "total_steps": 181800, "loss": 0.0048, "lr": 1.1274569208256231e-06, "epoch": 18.272827282728272, "percentage": 91.36, "elapsed_time": "6:33:38", "remaining_time": "0:37:12", "throughput": 1484.2, "total_tokens": 35054048} {"current_steps": 166105, "total_steps": 181800, "loss": 0.0074, "lr": 1.1267443978265207e-06, "epoch": 18.273377337733773, "percentage": 91.37, "elapsed_time": "6:33:38", "remaining_time": "0:37:11", "throughput": 1484.2, "total_tokens": 35055136} {"current_steps": 166110, "total_steps": 181800, "loss": 0.0044, "lr": 1.1260320948557585e-06, "epoch": 18.273927392739274, "percentage": 91.37, "elapsed_time": "6:33:39", "remaining_time": "0:37:10", "throughput": 1484.2, "total_tokens": 35056192} {"current_steps": 166115, "total_steps": 181800, "loss": 0.0747, "lr": 1.1253200119199003e-06, "epoch": 18.274477447744776, "percentage": 91.37, "elapsed_time": "6:33:40", "remaining_time": "0:37:10", "throughput": 1484.2, "total_tokens": 35057184} {"current_steps": 166120, "total_steps": 181800, "loss": 0.0037, "lr": 1.1246081490255105e-06, "epoch": 18.275027502750277, "percentage": 91.38, "elapsed_time": "6:33:40", "remaining_time": "0:37:09", "throughput": 1484.2, "total_tokens": 35058208} {"current_steps": 166125, "total_steps": 181800, "loss": 0.082, "lr": 1.1238965061791506e-06, "epoch": 18.275577557755774, "percentage": 91.38, "elapsed_time": "6:33:41", "remaining_time": "0:37:08", "throughput": 1484.2, "total_tokens": 35059296} {"current_steps": 166130, "total_steps": 181800, "loss": 0.0041, "lr": 1.1231850833873847e-06, "epoch": 18.276127612761275, "percentage": 91.38, "elapsed_time": "6:33:42", "remaining_time": "0:37:08", "throughput": 1484.21, "total_tokens": 35060352} {"current_steps": 166135, "total_steps": 181800, "loss": 0.0703, "lr": 1.122473880656763e-06, "epoch": 18.276677667766776, "percentage": 91.38, "elapsed_time": "6:33:42", "remaining_time": "0:37:07", "throughput": 1484.21, "total_tokens": 35061376} {"current_steps": 166140, "total_steps": 181800, "loss": 0.0531, "lr": 1.1217628979938388e-06, "epoch": 18.277227722772277, "percentage": 91.39, "elapsed_time": "6:33:43", "remaining_time": "0:37:06", "throughput": 1484.21, "total_tokens": 35062464} {"current_steps": 166145, "total_steps": 181800, "loss": 0.0387, "lr": 1.1210521354051707e-06, "epoch": 18.27777777777778, "percentage": 91.39, "elapsed_time": "6:33:44", "remaining_time": "0:37:06", "throughput": 1484.21, "total_tokens": 35063520} {"current_steps": 166150, "total_steps": 181800, "loss": 0.0469, "lr": 1.1203415928973033e-06, "epoch": 18.27832783278328, "percentage": 91.39, "elapsed_time": "6:33:45", "remaining_time": "0:37:05", "throughput": 1484.21, "total_tokens": 35064640} {"current_steps": 166155, "total_steps": 181800, "loss": 0.0178, "lr": 1.1196312704767952e-06, "epoch": 18.278877887788777, "percentage": 91.39, "elapsed_time": "6:33:45", "remaining_time": "0:37:04", "throughput": 1484.21, "total_tokens": 35065664} {"current_steps": 166160, "total_steps": 181800, "loss": 0.0141, "lr": 1.118921168150186e-06, "epoch": 18.27942794279428, "percentage": 91.4, "elapsed_time": "6:33:46", "remaining_time": "0:37:03", "throughput": 1484.21, "total_tokens": 35066720} {"current_steps": 166165, "total_steps": 181800, "loss": 0.0023, "lr": 1.1182112859240146e-06, "epoch": 18.27997799779978, "percentage": 91.4, "elapsed_time": "6:33:47", "remaining_time": "0:37:03", "throughput": 1484.22, "total_tokens": 35067808} {"current_steps": 166170, "total_steps": 181800, "loss": 0.0041, "lr": 1.117501623804837e-06, "epoch": 18.28052805280528, "percentage": 91.4, "elapsed_time": "6:33:47", "remaining_time": "0:37:02", "throughput": 1484.22, "total_tokens": 35068832} {"current_steps": 166175, "total_steps": 181800, "loss": 0.0016, "lr": 1.1167921817991838e-06, "epoch": 18.28107810781078, "percentage": 91.41, "elapsed_time": "6:33:48", "remaining_time": "0:37:01", "throughput": 1484.22, "total_tokens": 35069920} {"current_steps": 166180, "total_steps": 181800, "loss": 0.0038, "lr": 1.1160829599135946e-06, "epoch": 18.281628162816283, "percentage": 91.41, "elapsed_time": "6:33:49", "remaining_time": "0:37:01", "throughput": 1484.22, "total_tokens": 35071008} {"current_steps": 166185, "total_steps": 181800, "loss": 0.044, "lr": 1.1153739581546141e-06, "epoch": 18.282178217821784, "percentage": 91.41, "elapsed_time": "6:33:49", "remaining_time": "0:37:00", "throughput": 1484.23, "total_tokens": 35072128} {"current_steps": 166190, "total_steps": 181800, "loss": 0.0026, "lr": 1.1146651765287648e-06, "epoch": 18.28272827282728, "percentage": 91.41, "elapsed_time": "6:33:50", "remaining_time": "0:36:59", "throughput": 1484.23, "total_tokens": 35073184} {"current_steps": 166195, "total_steps": 181800, "loss": 0.0039, "lr": 1.1139566150425885e-06, "epoch": 18.283278327832782, "percentage": 91.42, "elapsed_time": "6:33:51", "remaining_time": "0:36:58", "throughput": 1484.23, "total_tokens": 35074240} {"current_steps": 166200, "total_steps": 181800, "loss": 0.0023, "lr": 1.1132482737026162e-06, "epoch": 18.283828382838283, "percentage": 91.42, "elapsed_time": "6:33:52", "remaining_time": "0:36:58", "throughput": 1484.23, "total_tokens": 35075296} {"current_steps": 166205, "total_steps": 181800, "loss": 0.001, "lr": 1.1125401525153623e-06, "epoch": 18.284378437843785, "percentage": 91.42, "elapsed_time": "6:33:52", "remaining_time": "0:36:57", "throughput": 1484.23, "total_tokens": 35076384} {"current_steps": 166210, "total_steps": 181800, "loss": 0.004, "lr": 1.1118322514873714e-06, "epoch": 18.284928492849286, "percentage": 91.42, "elapsed_time": "6:33:53", "remaining_time": "0:36:56", "throughput": 1484.23, "total_tokens": 35077472} {"current_steps": 166215, "total_steps": 181800, "loss": 0.0144, "lr": 1.1111245706251578e-06, "epoch": 18.285478547854787, "percentage": 91.43, "elapsed_time": "6:33:54", "remaining_time": "0:36:56", "throughput": 1484.24, "total_tokens": 35078528} {"current_steps": 166220, "total_steps": 181800, "loss": 0.0055, "lr": 1.1104171099352467e-06, "epoch": 18.286028602860284, "percentage": 91.43, "elapsed_time": "6:33:54", "remaining_time": "0:36:55", "throughput": 1484.24, "total_tokens": 35079552} {"current_steps": 166225, "total_steps": 181800, "loss": 0.0025, "lr": 1.1097098694241582e-06, "epoch": 18.286578657865785, "percentage": 91.43, "elapsed_time": "6:33:55", "remaining_time": "0:36:54", "throughput": 1484.24, "total_tokens": 35080608} {"current_steps": 166230, "total_steps": 181800, "loss": 0.049, "lr": 1.1090028490984089e-06, "epoch": 18.287128712871286, "percentage": 91.44, "elapsed_time": "6:33:56", "remaining_time": "0:36:53", "throughput": 1484.24, "total_tokens": 35081664} {"current_steps": 166235, "total_steps": 181800, "loss": 0.0386, "lr": 1.108296048964516e-06, "epoch": 18.287678767876788, "percentage": 91.44, "elapsed_time": "6:33:56", "remaining_time": "0:36:53", "throughput": 1484.24, "total_tokens": 35082720} {"current_steps": 166240, "total_steps": 181800, "loss": 0.0042, "lr": 1.107589469028994e-06, "epoch": 18.28822882288229, "percentage": 91.44, "elapsed_time": "6:33:57", "remaining_time": "0:36:52", "throughput": 1484.24, "total_tokens": 35083776} {"current_steps": 166245, "total_steps": 181800, "loss": 0.0252, "lr": 1.1068831092983567e-06, "epoch": 18.28877887788779, "percentage": 91.44, "elapsed_time": "6:33:58", "remaining_time": "0:36:51", "throughput": 1484.24, "total_tokens": 35084864} {"current_steps": 166250, "total_steps": 181800, "loss": 0.0028, "lr": 1.106176969779113e-06, "epoch": 18.28932893289329, "percentage": 91.45, "elapsed_time": "6:33:58", "remaining_time": "0:36:51", "throughput": 1484.24, "total_tokens": 35085888} {"current_steps": 166255, "total_steps": 181800, "loss": 0.005, "lr": 1.1054710504777688e-06, "epoch": 18.28987898789879, "percentage": 91.45, "elapsed_time": "6:33:59", "remaining_time": "0:36:50", "throughput": 1484.24, "total_tokens": 35086912} {"current_steps": 166260, "total_steps": 181800, "loss": 0.0042, "lr": 1.1047653514008355e-06, "epoch": 18.29042904290429, "percentage": 91.45, "elapsed_time": "6:34:00", "remaining_time": "0:36:49", "throughput": 1484.24, "total_tokens": 35087936} {"current_steps": 166265, "total_steps": 181800, "loss": 0.066, "lr": 1.1040598725548052e-06, "epoch": 18.29097909790979, "percentage": 91.45, "elapsed_time": "6:34:01", "remaining_time": "0:36:48", "throughput": 1484.24, "total_tokens": 35088992} {"current_steps": 166270, "total_steps": 181800, "loss": 0.1157, "lr": 1.1033546139461975e-06, "epoch": 18.29152915291529, "percentage": 91.46, "elapsed_time": "6:34:01", "remaining_time": "0:36:48", "throughput": 1484.25, "total_tokens": 35090144} {"current_steps": 166275, "total_steps": 181800, "loss": 0.0033, "lr": 1.1026495755815046e-06, "epoch": 18.292079207920793, "percentage": 91.46, "elapsed_time": "6:34:02", "remaining_time": "0:36:47", "throughput": 1484.25, "total_tokens": 35091232} {"current_steps": 166280, "total_steps": 181800, "loss": 0.0092, "lr": 1.1019447574672187e-06, "epoch": 18.292629262926294, "percentage": 91.46, "elapsed_time": "6:34:03", "remaining_time": "0:36:46", "throughput": 1484.25, "total_tokens": 35092224} {"current_steps": 166285, "total_steps": 181800, "loss": 0.0043, "lr": 1.1012401596098426e-06, "epoch": 18.293179317931795, "percentage": 91.47, "elapsed_time": "6:34:03", "remaining_time": "0:36:46", "throughput": 1484.25, "total_tokens": 35093216} {"current_steps": 166290, "total_steps": 181800, "loss": 0.0018, "lr": 1.1005357820158656e-06, "epoch": 18.293729372937293, "percentage": 91.47, "elapsed_time": "6:34:04", "remaining_time": "0:36:45", "throughput": 1484.25, "total_tokens": 35094336} {"current_steps": 166295, "total_steps": 181800, "loss": 0.0541, "lr": 1.0998316246917828e-06, "epoch": 18.294279427942794, "percentage": 91.47, "elapsed_time": "6:34:05", "remaining_time": "0:36:44", "throughput": 1484.25, "total_tokens": 35095360} {"current_steps": 166300, "total_steps": 181800, "loss": 0.0036, "lr": 1.0991276876440887e-06, "epoch": 18.294829482948295, "percentage": 91.47, "elapsed_time": "6:34:05", "remaining_time": "0:36:43", "throughput": 1484.25, "total_tokens": 35096448} {"current_steps": 166305, "total_steps": 181800, "loss": 0.0709, "lr": 1.0984239708792588e-06, "epoch": 18.295379537953796, "percentage": 91.48, "elapsed_time": "6:34:06", "remaining_time": "0:36:43", "throughput": 1484.26, "total_tokens": 35097504} {"current_steps": 166310, "total_steps": 181800, "loss": 0.0119, "lr": 1.0977204744037906e-06, "epoch": 18.295929592959297, "percentage": 91.48, "elapsed_time": "6:34:07", "remaining_time": "0:36:42", "throughput": 1484.26, "total_tokens": 35098560} {"current_steps": 166315, "total_steps": 181800, "loss": 0.0181, "lr": 1.0970171982241624e-06, "epoch": 18.296479647964798, "percentage": 91.48, "elapsed_time": "6:34:07", "remaining_time": "0:36:41", "throughput": 1484.26, "total_tokens": 35099680} {"current_steps": 166320, "total_steps": 181800, "loss": 0.0029, "lr": 1.0963141423468575e-06, "epoch": 18.297029702970296, "percentage": 91.49, "elapsed_time": "6:34:08", "remaining_time": "0:36:41", "throughput": 1484.26, "total_tokens": 35100736} {"current_steps": 166325, "total_steps": 181800, "loss": 0.0316, "lr": 1.0956113067783547e-06, "epoch": 18.297579757975797, "percentage": 91.49, "elapsed_time": "6:34:09", "remaining_time": "0:36:40", "throughput": 1484.26, "total_tokens": 35101760} {"current_steps": 166330, "total_steps": 181800, "loss": 0.0024, "lr": 1.0949086915251288e-06, "epoch": 18.298129812981298, "percentage": 91.49, "elapsed_time": "6:34:09", "remaining_time": "0:36:39", "throughput": 1484.26, "total_tokens": 35102816} {"current_steps": 166335, "total_steps": 181800, "loss": 0.0039, "lr": 1.094206296593664e-06, "epoch": 18.2986798679868, "percentage": 91.49, "elapsed_time": "6:34:10", "remaining_time": "0:36:38", "throughput": 1484.26, "total_tokens": 35103840} {"current_steps": 166340, "total_steps": 181800, "loss": 0.0068, "lr": 1.093504121990424e-06, "epoch": 18.2992299229923, "percentage": 91.5, "elapsed_time": "6:34:11", "remaining_time": "0:36:38", "throughput": 1484.27, "total_tokens": 35104928} {"current_steps": 166345, "total_steps": 181800, "loss": 0.0039, "lr": 1.0928021677218903e-06, "epoch": 18.2997799779978, "percentage": 91.5, "elapsed_time": "6:34:12", "remaining_time": "0:36:37", "throughput": 1484.27, "total_tokens": 35106080} {"current_steps": 166350, "total_steps": 181800, "loss": 0.098, "lr": 1.0921004337945212e-06, "epoch": 18.300330033003302, "percentage": 91.5, "elapsed_time": "6:34:12", "remaining_time": "0:36:36", "throughput": 1484.27, "total_tokens": 35107168} {"current_steps": 166355, "total_steps": 181800, "loss": 0.0019, "lr": 1.0913989202147922e-06, "epoch": 18.3008800880088, "percentage": 91.5, "elapsed_time": "6:34:13", "remaining_time": "0:36:36", "throughput": 1484.27, "total_tokens": 35108192} {"current_steps": 166360, "total_steps": 181800, "loss": 0.1694, "lr": 1.0906976269891706e-06, "epoch": 18.3014301430143, "percentage": 91.51, "elapsed_time": "6:34:14", "remaining_time": "0:36:35", "throughput": 1484.28, "total_tokens": 35109248} {"current_steps": 166365, "total_steps": 181800, "loss": 0.0015, "lr": 1.0899965541241119e-06, "epoch": 18.301980198019802, "percentage": 91.51, "elapsed_time": "6:34:14", "remaining_time": "0:36:34", "throughput": 1484.28, "total_tokens": 35110304} {"current_steps": 166370, "total_steps": 181800, "loss": 0.0116, "lr": 1.0892957016260836e-06, "epoch": 18.302530253025303, "percentage": 91.51, "elapsed_time": "6:34:15", "remaining_time": "0:36:33", "throughput": 1484.28, "total_tokens": 35111328} {"current_steps": 166375, "total_steps": 181800, "loss": 0.002, "lr": 1.0885950695015467e-06, "epoch": 18.303080308030804, "percentage": 91.52, "elapsed_time": "6:34:16", "remaining_time": "0:36:33", "throughput": 1484.28, "total_tokens": 35112384} {"current_steps": 166380, "total_steps": 181800, "loss": 0.0031, "lr": 1.0878946577569465e-06, "epoch": 18.303630363036305, "percentage": 91.52, "elapsed_time": "6:34:16", "remaining_time": "0:36:32", "throughput": 1484.28, "total_tokens": 35113472} {"current_steps": 166385, "total_steps": 181800, "loss": 0.0097, "lr": 1.0871944663987526e-06, "epoch": 18.304180418041803, "percentage": 91.52, "elapsed_time": "6:34:17", "remaining_time": "0:36:31", "throughput": 1484.28, "total_tokens": 35114496} {"current_steps": 166390, "total_steps": 181800, "loss": 0.0303, "lr": 1.0864944954334155e-06, "epoch": 18.304730473047304, "percentage": 91.52, "elapsed_time": "6:34:18", "remaining_time": "0:36:31", "throughput": 1484.28, "total_tokens": 35115520} {"current_steps": 166395, "total_steps": 181800, "loss": 0.006, "lr": 1.08579474486738e-06, "epoch": 18.305280528052805, "percentage": 91.53, "elapsed_time": "6:34:18", "remaining_time": "0:36:30", "throughput": 1484.29, "total_tokens": 35116608} {"current_steps": 166400, "total_steps": 181800, "loss": 0.0016, "lr": 1.085095214707102e-06, "epoch": 18.305830583058306, "percentage": 91.53, "elapsed_time": "6:34:19", "remaining_time": "0:36:29", "throughput": 1484.29, "total_tokens": 35117664} {"current_steps": 166405, "total_steps": 181800, "loss": 0.0133, "lr": 1.0843959049590208e-06, "epoch": 18.306380638063807, "percentage": 91.53, "elapsed_time": "6:34:20", "remaining_time": "0:36:28", "throughput": 1484.29, "total_tokens": 35118720} {"current_steps": 166410, "total_steps": 181800, "loss": 0.0023, "lr": 1.0836968156295895e-06, "epoch": 18.306930693069308, "percentage": 91.53, "elapsed_time": "6:34:20", "remaining_time": "0:36:28", "throughput": 1484.29, "total_tokens": 35119776} {"current_steps": 166415, "total_steps": 181800, "loss": 0.005, "lr": 1.0829979467252504e-06, "epoch": 18.30748074807481, "percentage": 91.54, "elapsed_time": "6:34:21", "remaining_time": "0:36:27", "throughput": 1484.29, "total_tokens": 35120832} {"current_steps": 166420, "total_steps": 181800, "loss": 0.054, "lr": 1.08229929825244e-06, "epoch": 18.308030803080307, "percentage": 91.54, "elapsed_time": "6:34:22", "remaining_time": "0:36:26", "throughput": 1484.29, "total_tokens": 35121856} {"current_steps": 166425, "total_steps": 181800, "loss": 0.0058, "lr": 1.081600870217603e-06, "epoch": 18.308580858085808, "percentage": 91.54, "elapsed_time": "6:34:23", "remaining_time": "0:36:26", "throughput": 1484.29, "total_tokens": 35122912} {"current_steps": 166430, "total_steps": 181800, "loss": 0.1691, "lr": 1.0809026626271701e-06, "epoch": 18.30913091309131, "percentage": 91.55, "elapsed_time": "6:34:23", "remaining_time": "0:36:25", "throughput": 1484.29, "total_tokens": 35123968} {"current_steps": 166435, "total_steps": 181800, "loss": 0.1019, "lr": 1.0802046754875839e-06, "epoch": 18.30968096809681, "percentage": 91.55, "elapsed_time": "6:34:24", "remaining_time": "0:36:24", "throughput": 1484.3, "total_tokens": 35125024} {"current_steps": 166440, "total_steps": 181800, "loss": 0.0036, "lr": 1.0795069088052694e-06, "epoch": 18.31023102310231, "percentage": 91.55, "elapsed_time": "6:34:25", "remaining_time": "0:36:23", "throughput": 1484.3, "total_tokens": 35126048} {"current_steps": 166445, "total_steps": 181800, "loss": 0.0102, "lr": 1.0788093625866608e-06, "epoch": 18.310781078107812, "percentage": 91.55, "elapsed_time": "6:34:25", "remaining_time": "0:36:23", "throughput": 1484.3, "total_tokens": 35127104} {"current_steps": 166450, "total_steps": 181800, "loss": 0.1318, "lr": 1.0781120368381913e-06, "epoch": 18.31133113311331, "percentage": 91.56, "elapsed_time": "6:34:26", "remaining_time": "0:36:22", "throughput": 1484.3, "total_tokens": 35128224} {"current_steps": 166455, "total_steps": 181800, "loss": 0.0029, "lr": 1.077414931566284e-06, "epoch": 18.31188118811881, "percentage": 91.56, "elapsed_time": "6:34:27", "remaining_time": "0:36:21", "throughput": 1484.3, "total_tokens": 35129280} {"current_steps": 166460, "total_steps": 181800, "loss": 0.0073, "lr": 1.076718046777364e-06, "epoch": 18.312431243124312, "percentage": 91.56, "elapsed_time": "6:34:27", "remaining_time": "0:36:21", "throughput": 1484.31, "total_tokens": 35130368} {"current_steps": 166465, "total_steps": 181800, "loss": 0.0638, "lr": 1.0760213824778515e-06, "epoch": 18.312981298129813, "percentage": 91.56, "elapsed_time": "6:34:28", "remaining_time": "0:36:20", "throughput": 1484.31, "total_tokens": 35131456} {"current_steps": 166470, "total_steps": 181800, "loss": 0.0156, "lr": 1.0753249386741715e-06, "epoch": 18.313531353135314, "percentage": 91.57, "elapsed_time": "6:34:29", "remaining_time": "0:36:19", "throughput": 1484.31, "total_tokens": 35132576} {"current_steps": 166475, "total_steps": 181800, "loss": 0.0091, "lr": 1.0746287153727442e-06, "epoch": 18.314081408140815, "percentage": 91.57, "elapsed_time": "6:34:29", "remaining_time": "0:36:18", "throughput": 1484.31, "total_tokens": 35133632} {"current_steps": 166480, "total_steps": 181800, "loss": 0.0031, "lr": 1.073932712579981e-06, "epoch": 18.314631463146316, "percentage": 91.57, "elapsed_time": "6:34:30", "remaining_time": "0:36:18", "throughput": 1484.31, "total_tokens": 35134656} {"current_steps": 166485, "total_steps": 181800, "loss": 0.005, "lr": 1.0732369303023015e-06, "epoch": 18.315181518151814, "percentage": 91.58, "elapsed_time": "6:34:31", "remaining_time": "0:36:17", "throughput": 1484.31, "total_tokens": 35135680} {"current_steps": 166490, "total_steps": 181800, "loss": 0.0483, "lr": 1.072541368546115e-06, "epoch": 18.315731573157315, "percentage": 91.58, "elapsed_time": "6:34:32", "remaining_time": "0:36:16", "throughput": 1484.32, "total_tokens": 35136800} {"current_steps": 166495, "total_steps": 181800, "loss": 0.0058, "lr": 1.0718460273178299e-06, "epoch": 18.316281628162816, "percentage": 91.58, "elapsed_time": "6:34:32", "remaining_time": "0:36:16", "throughput": 1484.32, "total_tokens": 35137856} {"current_steps": 166500, "total_steps": 181800, "loss": 0.0047, "lr": 1.0711509066238607e-06, "epoch": 18.316831683168317, "percentage": 91.58, "elapsed_time": "6:34:33", "remaining_time": "0:36:15", "throughput": 1484.32, "total_tokens": 35138880} {"current_steps": 166505, "total_steps": 181800, "loss": 0.0037, "lr": 1.0704560064706105e-06, "epoch": 18.317381738173818, "percentage": 91.59, "elapsed_time": "6:34:34", "remaining_time": "0:36:14", "throughput": 1484.32, "total_tokens": 35140000} {"current_steps": 166510, "total_steps": 181800, "loss": 0.0026, "lr": 1.0697613268644852e-06, "epoch": 18.31793179317932, "percentage": 91.59, "elapsed_time": "6:34:34", "remaining_time": "0:36:13", "throughput": 1484.32, "total_tokens": 35141024} {"current_steps": 166515, "total_steps": 181800, "loss": 0.0011, "lr": 1.0690668678118909e-06, "epoch": 18.318481848184817, "percentage": 91.59, "elapsed_time": "6:34:35", "remaining_time": "0:36:13", "throughput": 1484.32, "total_tokens": 35142080} {"current_steps": 166520, "total_steps": 181800, "loss": 0.0112, "lr": 1.068372629319217e-06, "epoch": 18.319031903190318, "percentage": 91.6, "elapsed_time": "6:34:36", "remaining_time": "0:36:12", "throughput": 1484.32, "total_tokens": 35143072} {"current_steps": 166525, "total_steps": 181800, "loss": 0.0349, "lr": 1.067678611392872e-06, "epoch": 18.31958195819582, "percentage": 91.6, "elapsed_time": "6:34:36", "remaining_time": "0:36:11", "throughput": 1484.32, "total_tokens": 35144096} {"current_steps": 166530, "total_steps": 181800, "loss": 0.0765, "lr": 1.0669848140392486e-06, "epoch": 18.32013201320132, "percentage": 91.6, "elapsed_time": "6:34:37", "remaining_time": "0:36:11", "throughput": 1484.32, "total_tokens": 35145120} {"current_steps": 166535, "total_steps": 181800, "loss": 0.0044, "lr": 1.0662912372647437e-06, "epoch": 18.32068206820682, "percentage": 91.6, "elapsed_time": "6:34:38", "remaining_time": "0:36:10", "throughput": 1484.32, "total_tokens": 35146144} {"current_steps": 166540, "total_steps": 181800, "loss": 0.0025, "lr": 1.06559788107575e-06, "epoch": 18.321232123212322, "percentage": 91.61, "elapsed_time": "6:34:38", "remaining_time": "0:36:09", "throughput": 1484.33, "total_tokens": 35147232} {"current_steps": 166545, "total_steps": 181800, "loss": 0.1319, "lr": 1.0649047454786538e-06, "epoch": 18.321782178217823, "percentage": 91.61, "elapsed_time": "6:34:39", "remaining_time": "0:36:08", "throughput": 1484.33, "total_tokens": 35148288} {"current_steps": 166550, "total_steps": 181800, "loss": 0.013, "lr": 1.0642118304798442e-06, "epoch": 18.32233223322332, "percentage": 91.61, "elapsed_time": "6:34:40", "remaining_time": "0:36:08", "throughput": 1484.33, "total_tokens": 35149408} {"current_steps": 166555, "total_steps": 181800, "loss": 0.0371, "lr": 1.0635191360857083e-06, "epoch": 18.322882288228822, "percentage": 91.61, "elapsed_time": "6:34:40", "remaining_time": "0:36:07", "throughput": 1484.34, "total_tokens": 35150496} {"current_steps": 166560, "total_steps": 181800, "loss": 0.0253, "lr": 1.0628266623026323e-06, "epoch": 18.323432343234323, "percentage": 91.62, "elapsed_time": "6:34:41", "remaining_time": "0:36:06", "throughput": 1484.34, "total_tokens": 35151520} {"current_steps": 166565, "total_steps": 181800, "loss": 0.0887, "lr": 1.0621344091369972e-06, "epoch": 18.323982398239824, "percentage": 91.62, "elapsed_time": "6:34:42", "remaining_time": "0:36:06", "throughput": 1484.34, "total_tokens": 35152576} {"current_steps": 166570, "total_steps": 181800, "loss": 0.0061, "lr": 1.0614423765951786e-06, "epoch": 18.324532453245325, "percentage": 91.62, "elapsed_time": "6:34:43", "remaining_time": "0:36:05", "throughput": 1484.34, "total_tokens": 35153632} {"current_steps": 166575, "total_steps": 181800, "loss": 0.0006, "lr": 1.0607505646835659e-06, "epoch": 18.325082508250826, "percentage": 91.63, "elapsed_time": "6:34:43", "remaining_time": "0:36:04", "throughput": 1484.34, "total_tokens": 35154720} {"current_steps": 166580, "total_steps": 181800, "loss": 0.0541, "lr": 1.060058973408523e-06, "epoch": 18.325632563256324, "percentage": 91.63, "elapsed_time": "6:34:44", "remaining_time": "0:36:03", "throughput": 1484.34, "total_tokens": 35155744} {"current_steps": 166585, "total_steps": 181800, "loss": 0.0022, "lr": 1.0593676027764287e-06, "epoch": 18.326182618261825, "percentage": 91.63, "elapsed_time": "6:34:45", "remaining_time": "0:36:03", "throughput": 1484.34, "total_tokens": 35156768} {"current_steps": 166590, "total_steps": 181800, "loss": 0.0017, "lr": 1.0586764527936583e-06, "epoch": 18.326732673267326, "percentage": 91.63, "elapsed_time": "6:34:45", "remaining_time": "0:36:02", "throughput": 1484.34, "total_tokens": 35157824} {"current_steps": 166595, "total_steps": 181800, "loss": 0.0024, "lr": 1.0579855234665758e-06, "epoch": 18.327282728272827, "percentage": 91.64, "elapsed_time": "6:34:46", "remaining_time": "0:36:01", "throughput": 1484.34, "total_tokens": 35158880} {"current_steps": 166600, "total_steps": 181800, "loss": 0.0428, "lr": 1.0572948148015543e-06, "epoch": 18.32783278327833, "percentage": 91.64, "elapsed_time": "6:34:47", "remaining_time": "0:36:01", "throughput": 1484.34, "total_tokens": 35159936} {"current_steps": 166605, "total_steps": 181800, "loss": 0.0043, "lr": 1.0566043268049608e-06, "epoch": 18.32838283828383, "percentage": 91.64, "elapsed_time": "6:34:47", "remaining_time": "0:36:00", "throughput": 1484.35, "total_tokens": 35160992} {"current_steps": 166610, "total_steps": 181800, "loss": 0.0084, "lr": 1.0559140594831512e-06, "epoch": 18.32893289328933, "percentage": 91.64, "elapsed_time": "6:34:48", "remaining_time": "0:35:59", "throughput": 1484.35, "total_tokens": 35162016} {"current_steps": 166615, "total_steps": 181800, "loss": 0.0008, "lr": 1.05522401284249e-06, "epoch": 18.329482948294828, "percentage": 91.65, "elapsed_time": "6:34:49", "remaining_time": "0:35:58", "throughput": 1484.35, "total_tokens": 35163040} {"current_steps": 166620, "total_steps": 181800, "loss": 0.0059, "lr": 1.0545341868893416e-06, "epoch": 18.33003300330033, "percentage": 91.65, "elapsed_time": "6:34:49", "remaining_time": "0:35:58", "throughput": 1484.35, "total_tokens": 35164096} {"current_steps": 166625, "total_steps": 181800, "loss": 0.0948, "lr": 1.0538445816300646e-06, "epoch": 18.33058305830583, "percentage": 91.65, "elapsed_time": "6:34:50", "remaining_time": "0:35:57", "throughput": 1484.35, "total_tokens": 35165216} {"current_steps": 166630, "total_steps": 181800, "loss": 0.0263, "lr": 1.0531551970710124e-06, "epoch": 18.33113311331133, "percentage": 91.66, "elapsed_time": "6:34:51", "remaining_time": "0:35:56", "throughput": 1484.35, "total_tokens": 35166272} {"current_steps": 166635, "total_steps": 181800, "loss": 0.0013, "lr": 1.0524660332185326e-06, "epoch": 18.331683168316832, "percentage": 91.66, "elapsed_time": "6:34:52", "remaining_time": "0:35:56", "throughput": 1484.35, "total_tokens": 35167328} {"current_steps": 166640, "total_steps": 181800, "loss": 0.0846, "lr": 1.0517770900789843e-06, "epoch": 18.332233223322334, "percentage": 91.66, "elapsed_time": "6:34:52", "remaining_time": "0:35:55", "throughput": 1484.36, "total_tokens": 35168416} {"current_steps": 166645, "total_steps": 181800, "loss": 0.0459, "lr": 1.0510883676587147e-06, "epoch": 18.33278327832783, "percentage": 91.66, "elapsed_time": "6:34:53", "remaining_time": "0:35:54", "throughput": 1484.36, "total_tokens": 35169472} {"current_steps": 166650, "total_steps": 181800, "loss": 0.1463, "lr": 1.0503998659640747e-06, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "6:34:54", "remaining_time": "0:35:54", "throughput": 1484.36, "total_tokens": 35170496} {"current_steps": 166655, "total_steps": 181800, "loss": 0.0269, "lr": 1.0497115850014062e-06, "epoch": 18.333883388338833, "percentage": 91.67, "elapsed_time": "6:34:54", "remaining_time": "0:35:53", "throughput": 1484.36, "total_tokens": 35171520} {"current_steps": 166660, "total_steps": 181800, "loss": 0.0022, "lr": 1.0490235247770513e-06, "epoch": 18.334433443344334, "percentage": 91.67, "elapsed_time": "6:34:55", "remaining_time": "0:35:52", "throughput": 1484.36, "total_tokens": 35172544} {"current_steps": 166665, "total_steps": 181800, "loss": 0.0576, "lr": 1.0483356852973553e-06, "epoch": 18.334983498349835, "percentage": 91.67, "elapsed_time": "6:34:56", "remaining_time": "0:35:51", "throughput": 1484.36, "total_tokens": 35173632} {"current_steps": 166670, "total_steps": 181800, "loss": 0.1589, "lr": 1.0476480665686545e-06, "epoch": 18.335533553355337, "percentage": 91.68, "elapsed_time": "6:34:56", "remaining_time": "0:35:51", "throughput": 1484.36, "total_tokens": 35174624} {"current_steps": 166675, "total_steps": 181800, "loss": 0.0118, "lr": 1.0469606685972882e-06, "epoch": 18.336083608360838, "percentage": 91.68, "elapsed_time": "6:34:57", "remaining_time": "0:35:50", "throughput": 1484.36, "total_tokens": 35175712} {"current_steps": 166680, "total_steps": 181800, "loss": 0.0779, "lr": 1.0462734913895934e-06, "epoch": 18.336633663366335, "percentage": 91.68, "elapsed_time": "6:34:58", "remaining_time": "0:35:49", "throughput": 1484.36, "total_tokens": 35176768} {"current_steps": 166685, "total_steps": 181800, "loss": 0.0015, "lr": 1.0455865349519006e-06, "epoch": 18.337183718371836, "percentage": 91.69, "elapsed_time": "6:34:58", "remaining_time": "0:35:49", "throughput": 1484.37, "total_tokens": 35177856} {"current_steps": 166690, "total_steps": 181800, "loss": 0.002, "lr": 1.0448997992905441e-06, "epoch": 18.337733773377337, "percentage": 91.69, "elapsed_time": "6:34:59", "remaining_time": "0:35:48", "throughput": 1484.36, "total_tokens": 35178848} {"current_steps": 166695, "total_steps": 181800, "loss": 0.1, "lr": 1.044213284411849e-06, "epoch": 18.33828382838284, "percentage": 91.69, "elapsed_time": "6:35:00", "remaining_time": "0:35:47", "throughput": 1484.37, "total_tokens": 35179936} {"current_steps": 166700, "total_steps": 181800, "loss": 0.002, "lr": 1.043526990322144e-06, "epoch": 18.33883388338834, "percentage": 91.69, "elapsed_time": "6:35:00", "remaining_time": "0:35:46", "throughput": 1484.37, "total_tokens": 35180992} {"current_steps": 166705, "total_steps": 181800, "loss": 0.0011, "lr": 1.042840917027757e-06, "epoch": 18.33938393839384, "percentage": 91.7, "elapsed_time": "6:35:01", "remaining_time": "0:35:46", "throughput": 1484.37, "total_tokens": 35181984} {"current_steps": 166710, "total_steps": 181800, "loss": 0.1735, "lr": 1.042155064535008e-06, "epoch": 18.33993399339934, "percentage": 91.7, "elapsed_time": "6:35:02", "remaining_time": "0:35:45", "throughput": 1484.36, "total_tokens": 35182944} {"current_steps": 166715, "total_steps": 181800, "loss": 0.0191, "lr": 1.0414694328502256e-06, "epoch": 18.34048404840484, "percentage": 91.7, "elapsed_time": "6:35:03", "remaining_time": "0:35:44", "throughput": 1484.37, "total_tokens": 35184032} {"current_steps": 166720, "total_steps": 181800, "loss": 0.0988, "lr": 1.0407840219797154e-06, "epoch": 18.34103410341034, "percentage": 91.71, "elapsed_time": "6:35:03", "remaining_time": "0:35:44", "throughput": 1484.37, "total_tokens": 35185056} {"current_steps": 166725, "total_steps": 181800, "loss": 0.0461, "lr": 1.040098831929809e-06, "epoch": 18.34158415841584, "percentage": 91.71, "elapsed_time": "6:35:04", "remaining_time": "0:35:43", "throughput": 1484.37, "total_tokens": 35186112} {"current_steps": 166730, "total_steps": 181800, "loss": 0.0019, "lr": 1.039413862706809e-06, "epoch": 18.342134213421343, "percentage": 91.71, "elapsed_time": "6:35:05", "remaining_time": "0:35:42", "throughput": 1484.37, "total_tokens": 35187136} {"current_steps": 166735, "total_steps": 181800, "loss": 0.0029, "lr": 1.038729114317033e-06, "epoch": 18.342684268426844, "percentage": 91.71, "elapsed_time": "6:35:05", "remaining_time": "0:35:41", "throughput": 1484.37, "total_tokens": 35188128} {"current_steps": 166740, "total_steps": 181800, "loss": 0.0092, "lr": 1.0380445867667982e-06, "epoch": 18.343234323432345, "percentage": 91.72, "elapsed_time": "6:35:06", "remaining_time": "0:35:41", "throughput": 1484.37, "total_tokens": 35189152} {"current_steps": 166745, "total_steps": 181800, "loss": 0.0697, "lr": 1.0373602800624049e-06, "epoch": 18.343784378437842, "percentage": 91.72, "elapsed_time": "6:35:07", "remaining_time": "0:35:40", "throughput": 1484.37, "total_tokens": 35190176} {"current_steps": 166750, "total_steps": 181800, "loss": 0.1399, "lr": 1.0366761942101677e-06, "epoch": 18.344334433443343, "percentage": 91.72, "elapsed_time": "6:35:07", "remaining_time": "0:35:39", "throughput": 1484.37, "total_tokens": 35191232} {"current_steps": 166755, "total_steps": 181800, "loss": 0.0719, "lr": 1.0359923292163815e-06, "epoch": 18.344884488448844, "percentage": 91.72, "elapsed_time": "6:35:08", "remaining_time": "0:35:39", "throughput": 1484.37, "total_tokens": 35192320} {"current_steps": 166760, "total_steps": 181800, "loss": 0.0027, "lr": 1.0353086850873578e-06, "epoch": 18.345434543454346, "percentage": 91.73, "elapsed_time": "6:35:09", "remaining_time": "0:35:38", "throughput": 1484.37, "total_tokens": 35193376} {"current_steps": 166765, "total_steps": 181800, "loss": 0.0012, "lr": 1.0346252618293971e-06, "epoch": 18.345984598459847, "percentage": 91.73, "elapsed_time": "6:35:09", "remaining_time": "0:35:37", "throughput": 1484.37, "total_tokens": 35194464} {"current_steps": 166770, "total_steps": 181800, "loss": 0.0046, "lr": 1.033942059448792e-06, "epoch": 18.346534653465348, "percentage": 91.73, "elapsed_time": "6:35:10", "remaining_time": "0:35:36", "throughput": 1484.38, "total_tokens": 35195552} {"current_steps": 166775, "total_steps": 181800, "loss": 0.0009, "lr": 1.0332590779518452e-06, "epoch": 18.34708470847085, "percentage": 91.74, "elapsed_time": "6:35:11", "remaining_time": "0:35:36", "throughput": 1484.38, "total_tokens": 35196576} {"current_steps": 166780, "total_steps": 181800, "loss": 0.0199, "lr": 1.0325763173448494e-06, "epoch": 18.347634763476346, "percentage": 91.74, "elapsed_time": "6:35:12", "remaining_time": "0:35:35", "throughput": 1484.38, "total_tokens": 35197632} {"current_steps": 166785, "total_steps": 181800, "loss": 0.0011, "lr": 1.0318937776340937e-06, "epoch": 18.348184818481847, "percentage": 91.74, "elapsed_time": "6:35:12", "remaining_time": "0:35:34", "throughput": 1484.38, "total_tokens": 35198720} {"current_steps": 166790, "total_steps": 181800, "loss": 0.0617, "lr": 1.031211458825873e-06, "epoch": 18.34873487348735, "percentage": 91.74, "elapsed_time": "6:35:13", "remaining_time": "0:35:34", "throughput": 1484.39, "total_tokens": 35199840} {"current_steps": 166795, "total_steps": 181800, "loss": 0.105, "lr": 1.0305293609264771e-06, "epoch": 18.34928492849285, "percentage": 91.75, "elapsed_time": "6:35:14", "remaining_time": "0:35:33", "throughput": 1484.39, "total_tokens": 35200864} {"current_steps": 166800, "total_steps": 181800, "loss": 0.037, "lr": 1.0298474839421895e-06, "epoch": 18.34983498349835, "percentage": 91.75, "elapsed_time": "6:35:14", "remaining_time": "0:35:32", "throughput": 1484.39, "total_tokens": 35201920} {"current_steps": 166805, "total_steps": 181800, "loss": 0.1164, "lr": 1.0291658278792971e-06, "epoch": 18.350385038503852, "percentage": 91.75, "elapsed_time": "6:35:15", "remaining_time": "0:35:31", "throughput": 1484.39, "total_tokens": 35203040} {"current_steps": 166810, "total_steps": 181800, "loss": 0.0036, "lr": 1.0284843927440751e-06, "epoch": 18.35093509350935, "percentage": 91.75, "elapsed_time": "6:35:16", "remaining_time": "0:35:31", "throughput": 1484.39, "total_tokens": 35204096} {"current_steps": 166815, "total_steps": 181800, "loss": 0.1165, "lr": 1.0278031785428132e-06, "epoch": 18.35148514851485, "percentage": 91.76, "elapsed_time": "6:35:16", "remaining_time": "0:35:30", "throughput": 1484.4, "total_tokens": 35205216} {"current_steps": 166820, "total_steps": 181800, "loss": 0.0167, "lr": 1.0271221852817896e-06, "epoch": 18.35203520352035, "percentage": 91.76, "elapsed_time": "6:35:17", "remaining_time": "0:35:29", "throughput": 1484.4, "total_tokens": 35206272} {"current_steps": 166825, "total_steps": 181800, "loss": 0.0016, "lr": 1.0264414129672745e-06, "epoch": 18.352585258525853, "percentage": 91.76, "elapsed_time": "6:35:18", "remaining_time": "0:35:29", "throughput": 1484.4, "total_tokens": 35207424} {"current_steps": 166830, "total_steps": 181800, "loss": 0.0023, "lr": 1.0257608616055458e-06, "epoch": 18.353135313531354, "percentage": 91.77, "elapsed_time": "6:35:18", "remaining_time": "0:35:28", "throughput": 1484.4, "total_tokens": 35208448} {"current_steps": 166835, "total_steps": 181800, "loss": 0.1072, "lr": 1.0250805312028739e-06, "epoch": 18.353685368536855, "percentage": 91.77, "elapsed_time": "6:35:19", "remaining_time": "0:35:27", "throughput": 1484.4, "total_tokens": 35209504} {"current_steps": 166840, "total_steps": 181800, "loss": 0.0009, "lr": 1.024400421765534e-06, "epoch": 18.354235423542356, "percentage": 91.77, "elapsed_time": "6:35:20", "remaining_time": "0:35:26", "throughput": 1484.41, "total_tokens": 35210592} {"current_steps": 166845, "total_steps": 181800, "loss": 0.0022, "lr": 1.023720533299788e-06, "epoch": 18.354785478547853, "percentage": 91.77, "elapsed_time": "6:35:21", "remaining_time": "0:35:26", "throughput": 1484.41, "total_tokens": 35211584} {"current_steps": 166850, "total_steps": 181800, "loss": 0.0014, "lr": 1.0230408658119028e-06, "epoch": 18.355335533553355, "percentage": 91.78, "elapsed_time": "6:35:21", "remaining_time": "0:35:25", "throughput": 1484.41, "total_tokens": 35212640} {"current_steps": 166855, "total_steps": 181800, "loss": 0.0869, "lr": 1.0223614193081515e-06, "epoch": 18.355885588558856, "percentage": 91.78, "elapsed_time": "6:35:22", "remaining_time": "0:35:24", "throughput": 1484.41, "total_tokens": 35213696} {"current_steps": 166860, "total_steps": 181800, "loss": 0.0119, "lr": 1.0216821937947818e-06, "epoch": 18.356435643564357, "percentage": 91.78, "elapsed_time": "6:35:23", "remaining_time": "0:35:24", "throughput": 1484.41, "total_tokens": 35214752} {"current_steps": 166865, "total_steps": 181800, "loss": 0.0886, "lr": 1.0210031892780664e-06, "epoch": 18.356985698569858, "percentage": 91.78, "elapsed_time": "6:35:23", "remaining_time": "0:35:23", "throughput": 1484.41, "total_tokens": 35215744} {"current_steps": 166870, "total_steps": 181800, "loss": 0.0015, "lr": 1.0203244057642557e-06, "epoch": 18.35753575357536, "percentage": 91.79, "elapsed_time": "6:35:24", "remaining_time": "0:35:22", "throughput": 1484.41, "total_tokens": 35216800} {"current_steps": 166875, "total_steps": 181800, "loss": 0.0571, "lr": 1.019645843259609e-06, "epoch": 18.358085808580856, "percentage": 91.79, "elapsed_time": "6:35:25", "remaining_time": "0:35:21", "throughput": 1484.41, "total_tokens": 35217920} {"current_steps": 166880, "total_steps": 181800, "loss": 0.008, "lr": 1.018967501770382e-06, "epoch": 18.358635863586358, "percentage": 91.79, "elapsed_time": "6:35:25", "remaining_time": "0:35:21", "throughput": 1484.41, "total_tokens": 35218880} {"current_steps": 166885, "total_steps": 181800, "loss": 0.0059, "lr": 1.01828938130282e-06, "epoch": 18.35918591859186, "percentage": 91.8, "elapsed_time": "6:35:26", "remaining_time": "0:35:20", "throughput": 1484.41, "total_tokens": 35219968} {"current_steps": 166890, "total_steps": 181800, "loss": 0.0535, "lr": 1.0176114818631815e-06, "epoch": 18.35973597359736, "percentage": 91.8, "elapsed_time": "6:35:27", "remaining_time": "0:35:19", "throughput": 1484.42, "total_tokens": 35221088} {"current_steps": 166895, "total_steps": 181800, "loss": 0.0985, "lr": 1.016933803457712e-06, "epoch": 18.36028602860286, "percentage": 91.8, "elapsed_time": "6:35:27", "remaining_time": "0:35:19", "throughput": 1484.42, "total_tokens": 35222144} {"current_steps": 166900, "total_steps": 181800, "loss": 0.0232, "lr": 1.0162563460926505e-06, "epoch": 18.360836083608362, "percentage": 91.8, "elapsed_time": "6:35:28", "remaining_time": "0:35:18", "throughput": 1484.42, "total_tokens": 35223136} {"current_steps": 166905, "total_steps": 181800, "loss": 0.0217, "lr": 1.015579109774245e-06, "epoch": 18.361386138613863, "percentage": 91.81, "elapsed_time": "6:35:29", "remaining_time": "0:35:17", "throughput": 1484.42, "total_tokens": 35224192} {"current_steps": 166910, "total_steps": 181800, "loss": 0.0438, "lr": 1.014902094508738e-06, "epoch": 18.36193619361936, "percentage": 91.81, "elapsed_time": "6:35:29", "remaining_time": "0:35:16", "throughput": 1484.42, "total_tokens": 35225216} {"current_steps": 166915, "total_steps": 181800, "loss": 0.076, "lr": 1.0142253003023739e-06, "epoch": 18.36248624862486, "percentage": 91.81, "elapsed_time": "6:35:30", "remaining_time": "0:35:16", "throughput": 1484.42, "total_tokens": 35226336} {"current_steps": 166920, "total_steps": 181800, "loss": 0.0248, "lr": 1.013548727161384e-06, "epoch": 18.363036303630363, "percentage": 91.82, "elapsed_time": "6:35:31", "remaining_time": "0:35:15", "throughput": 1484.42, "total_tokens": 35227392} {"current_steps": 166925, "total_steps": 181800, "loss": 0.0026, "lr": 1.0128723750920027e-06, "epoch": 18.363586358635864, "percentage": 91.82, "elapsed_time": "6:35:32", "remaining_time": "0:35:14", "throughput": 1484.42, "total_tokens": 35228416} {"current_steps": 166930, "total_steps": 181800, "loss": 0.0379, "lr": 1.012196244100469e-06, "epoch": 18.364136413641365, "percentage": 91.82, "elapsed_time": "6:35:32", "remaining_time": "0:35:14", "throughput": 1484.42, "total_tokens": 35229472} {"current_steps": 166935, "total_steps": 181800, "loss": 0.0057, "lr": 1.0115203341930113e-06, "epoch": 18.364686468646866, "percentage": 91.82, "elapsed_time": "6:35:33", "remaining_time": "0:35:13", "throughput": 1484.43, "total_tokens": 35230560} {"current_steps": 166940, "total_steps": 181800, "loss": 0.0876, "lr": 1.0108446453758607e-06, "epoch": 18.365236523652364, "percentage": 91.83, "elapsed_time": "6:35:34", "remaining_time": "0:35:12", "throughput": 1484.43, "total_tokens": 35231584} {"current_steps": 166945, "total_steps": 181800, "loss": 0.0528, "lr": 1.0101691776552458e-06, "epoch": 18.365786578657865, "percentage": 91.83, "elapsed_time": "6:35:34", "remaining_time": "0:35:11", "throughput": 1484.43, "total_tokens": 35232608} {"current_steps": 166950, "total_steps": 181800, "loss": 0.0059, "lr": 1.0094939310373863e-06, "epoch": 18.366336633663366, "percentage": 91.83, "elapsed_time": "6:35:35", "remaining_time": "0:35:11", "throughput": 1484.43, "total_tokens": 35233728} {"current_steps": 166955, "total_steps": 181800, "loss": 0.0664, "lr": 1.0088189055285135e-06, "epoch": 18.366886688668867, "percentage": 91.83, "elapsed_time": "6:35:36", "remaining_time": "0:35:10", "throughput": 1484.43, "total_tokens": 35234752} {"current_steps": 166960, "total_steps": 181800, "loss": 0.0027, "lr": 1.008144101134839e-06, "epoch": 18.367436743674368, "percentage": 91.84, "elapsed_time": "6:35:36", "remaining_time": "0:35:09", "throughput": 1484.43, "total_tokens": 35235840} {"current_steps": 166965, "total_steps": 181800, "loss": 0.0523, "lr": 1.0074695178625914e-06, "epoch": 18.36798679867987, "percentage": 91.84, "elapsed_time": "6:35:37", "remaining_time": "0:35:09", "throughput": 1484.44, "total_tokens": 35236928} {"current_steps": 166970, "total_steps": 181800, "loss": 0.0225, "lr": 1.006795155717985e-06, "epoch": 18.36853685368537, "percentage": 91.84, "elapsed_time": "6:35:38", "remaining_time": "0:35:08", "throughput": 1484.44, "total_tokens": 35237984} {"current_steps": 166975, "total_steps": 181800, "loss": 0.0024, "lr": 1.0061210147072314e-06, "epoch": 18.369086908690868, "percentage": 91.85, "elapsed_time": "6:35:38", "remaining_time": "0:35:07", "throughput": 1484.44, "total_tokens": 35239008} {"current_steps": 166980, "total_steps": 181800, "loss": 0.0011, "lr": 1.0054470948365535e-06, "epoch": 18.36963696369637, "percentage": 91.85, "elapsed_time": "6:35:39", "remaining_time": "0:35:06", "throughput": 1484.44, "total_tokens": 35240096} {"current_steps": 166985, "total_steps": 181800, "loss": 0.0837, "lr": 1.004773396112152e-06, "epoch": 18.37018701870187, "percentage": 91.85, "elapsed_time": "6:35:40", "remaining_time": "0:35:06", "throughput": 1484.44, "total_tokens": 35241120} {"current_steps": 166990, "total_steps": 181800, "loss": 0.0014, "lr": 1.0040999185402355e-06, "epoch": 18.37073707370737, "percentage": 91.85, "elapsed_time": "6:35:41", "remaining_time": "0:35:05", "throughput": 1484.44, "total_tokens": 35242208} {"current_steps": 166995, "total_steps": 181800, "loss": 0.0579, "lr": 1.0034266621270216e-06, "epoch": 18.371287128712872, "percentage": 91.86, "elapsed_time": "6:35:41", "remaining_time": "0:35:04", "throughput": 1484.44, "total_tokens": 35243264} {"current_steps": 167000, "total_steps": 181800, "loss": 0.0369, "lr": 1.002753626878708e-06, "epoch": 18.371837183718373, "percentage": 91.86, "elapsed_time": "6:35:42", "remaining_time": "0:35:04", "throughput": 1484.45, "total_tokens": 35244320} {"current_steps": 167005, "total_steps": 181800, "loss": 0.0455, "lr": 1.0020808128015009e-06, "epoch": 18.37238723872387, "percentage": 91.86, "elapsed_time": "6:35:43", "remaining_time": "0:35:03", "throughput": 1484.45, "total_tokens": 35245440} {"current_steps": 167010, "total_steps": 181800, "loss": 0.0598, "lr": 1.0014082199016006e-06, "epoch": 18.372937293729372, "percentage": 91.86, "elapsed_time": "6:35:43", "remaining_time": "0:35:02", "throughput": 1484.45, "total_tokens": 35246496} {"current_steps": 167015, "total_steps": 181800, "loss": 0.0066, "lr": 1.0007358481851998e-06, "epoch": 18.373487348734873, "percentage": 91.87, "elapsed_time": "6:35:44", "remaining_time": "0:35:01", "throughput": 1484.45, "total_tokens": 35247552} {"current_steps": 167020, "total_steps": 181800, "loss": 0.0054, "lr": 1.0000636976585043e-06, "epoch": 18.374037403740374, "percentage": 91.87, "elapsed_time": "6:35:45", "remaining_time": "0:35:01", "throughput": 1484.45, "total_tokens": 35248608} {"current_steps": 167025, "total_steps": 181800, "loss": 0.0762, "lr": 9.99391768327701e-07, "epoch": 18.374587458745875, "percentage": 91.87, "elapsed_time": "6:35:45", "remaining_time": "0:35:00", "throughput": 1484.45, "total_tokens": 35249600} {"current_steps": 167030, "total_steps": 181800, "loss": 0.0684, "lr": 9.987200601989932e-07, "epoch": 18.375137513751376, "percentage": 91.88, "elapsed_time": "6:35:46", "remaining_time": "0:34:59", "throughput": 1484.45, "total_tokens": 35250624} {"current_steps": 167035, "total_steps": 181800, "loss": 0.002, "lr": 9.98048573278565e-07, "epoch": 18.375687568756877, "percentage": 91.88, "elapsed_time": "6:35:47", "remaining_time": "0:34:59", "throughput": 1484.45, "total_tokens": 35251712} {"current_steps": 167040, "total_steps": 181800, "loss": 0.1122, "lr": 9.973773075726029e-07, "epoch": 18.376237623762375, "percentage": 91.88, "elapsed_time": "6:35:47", "remaining_time": "0:34:58", "throughput": 1484.46, "total_tokens": 35252800} {"current_steps": 167045, "total_steps": 181800, "loss": 0.008, "lr": 9.967062630872991e-07, "epoch": 18.376787678767876, "percentage": 91.88, "elapsed_time": "6:35:48", "remaining_time": "0:34:57", "throughput": 1484.46, "total_tokens": 35253824} {"current_steps": 167050, "total_steps": 181800, "loss": 0.0843, "lr": 9.960354398288296e-07, "epoch": 18.377337733773377, "percentage": 91.89, "elapsed_time": "6:35:49", "remaining_time": "0:34:56", "throughput": 1484.46, "total_tokens": 35254848} {"current_steps": 167055, "total_steps": 181800, "loss": 0.0703, "lr": 9.95364837803392e-07, "epoch": 18.377887788778878, "percentage": 91.89, "elapsed_time": "6:35:50", "remaining_time": "0:34:56", "throughput": 1484.46, "total_tokens": 35255872} {"current_steps": 167060, "total_steps": 181800, "loss": 0.0051, "lr": 9.946944570171536e-07, "epoch": 18.37843784378438, "percentage": 91.89, "elapsed_time": "6:35:50", "remaining_time": "0:34:55", "throughput": 1484.46, "total_tokens": 35256864} {"current_steps": 167065, "total_steps": 181800, "loss": 0.0093, "lr": 9.940242974762981e-07, "epoch": 18.37898789878988, "percentage": 91.89, "elapsed_time": "6:35:51", "remaining_time": "0:34:54", "throughput": 1484.45, "total_tokens": 35257824} {"current_steps": 167070, "total_steps": 181800, "loss": 0.0021, "lr": 9.933543591870044e-07, "epoch": 18.379537953795378, "percentage": 91.9, "elapsed_time": "6:35:52", "remaining_time": "0:34:54", "throughput": 1484.45, "total_tokens": 35258880} {"current_steps": 167075, "total_steps": 181800, "loss": 0.0008, "lr": 9.926846421554393e-07, "epoch": 18.38008800880088, "percentage": 91.9, "elapsed_time": "6:35:52", "remaining_time": "0:34:53", "throughput": 1484.45, "total_tokens": 35259872} {"current_steps": 167080, "total_steps": 181800, "loss": 0.0009, "lr": 9.920151463877785e-07, "epoch": 18.38063806380638, "percentage": 91.9, "elapsed_time": "6:35:53", "remaining_time": "0:34:52", "throughput": 1484.45, "total_tokens": 35260896} {"current_steps": 167085, "total_steps": 181800, "loss": 0.0883, "lr": 9.913458718902007e-07, "epoch": 18.38118811881188, "percentage": 91.91, "elapsed_time": "6:35:54", "remaining_time": "0:34:52", "throughput": 1484.45, "total_tokens": 35261952} {"current_steps": 167090, "total_steps": 181800, "loss": 0.0031, "lr": 9.90676818668862e-07, "epoch": 18.381738173817382, "percentage": 91.91, "elapsed_time": "6:35:54", "remaining_time": "0:34:51", "throughput": 1484.45, "total_tokens": 35262944} {"current_steps": 167095, "total_steps": 181800, "loss": 0.0172, "lr": 9.900079867299379e-07, "epoch": 18.382288228822883, "percentage": 91.91, "elapsed_time": "6:35:55", "remaining_time": "0:34:50", "throughput": 1484.45, "total_tokens": 35263968} {"current_steps": 167100, "total_steps": 181800, "loss": 0.0417, "lr": 9.893393760795871e-07, "epoch": 18.382838283828384, "percentage": 91.91, "elapsed_time": "6:35:56", "remaining_time": "0:34:49", "throughput": 1484.45, "total_tokens": 35265056} {"current_steps": 167105, "total_steps": 181800, "loss": 0.0065, "lr": 9.886709867239774e-07, "epoch": 18.383388338833882, "percentage": 91.92, "elapsed_time": "6:35:57", "remaining_time": "0:34:49", "throughput": 1484.45, "total_tokens": 35266176} {"current_steps": 167110, "total_steps": 181800, "loss": 0.0031, "lr": 9.880028186692591e-07, "epoch": 18.383938393839383, "percentage": 91.92, "elapsed_time": "6:35:57", "remaining_time": "0:34:48", "throughput": 1484.46, "total_tokens": 35267328} {"current_steps": 167115, "total_steps": 181800, "loss": 0.136, "lr": 9.873348719215996e-07, "epoch": 18.384488448844884, "percentage": 91.92, "elapsed_time": "6:35:58", "remaining_time": "0:34:47", "throughput": 1484.46, "total_tokens": 35268288} {"current_steps": 167120, "total_steps": 181800, "loss": 0.0134, "lr": 9.866671464871552e-07, "epoch": 18.385038503850385, "percentage": 91.93, "elapsed_time": "6:35:59", "remaining_time": "0:34:47", "throughput": 1484.46, "total_tokens": 35269344} {"current_steps": 167125, "total_steps": 181800, "loss": 0.0012, "lr": 9.859996423720708e-07, "epoch": 18.385588558855886, "percentage": 91.93, "elapsed_time": "6:35:59", "remaining_time": "0:34:46", "throughput": 1484.46, "total_tokens": 35270368} {"current_steps": 167130, "total_steps": 181800, "loss": 0.0329, "lr": 9.85332359582511e-07, "epoch": 18.386138613861387, "percentage": 91.93, "elapsed_time": "6:36:00", "remaining_time": "0:34:45", "throughput": 1484.46, "total_tokens": 35271456} {"current_steps": 167135, "total_steps": 181800, "loss": 0.0084, "lr": 9.846652981246153e-07, "epoch": 18.38668866886689, "percentage": 91.93, "elapsed_time": "6:36:01", "remaining_time": "0:34:44", "throughput": 1484.46, "total_tokens": 35272544} {"current_steps": 167140, "total_steps": 181800, "loss": 0.0027, "lr": 9.839984580045369e-07, "epoch": 18.387238723872386, "percentage": 91.94, "elapsed_time": "6:36:01", "remaining_time": "0:34:44", "throughput": 1484.46, "total_tokens": 35273568} {"current_steps": 167145, "total_steps": 181800, "loss": 0.0792, "lr": 9.833318392284212e-07, "epoch": 18.387788778877887, "percentage": 91.94, "elapsed_time": "6:36:02", "remaining_time": "0:34:43", "throughput": 1484.47, "total_tokens": 35274656} {"current_steps": 167150, "total_steps": 181800, "loss": 0.0066, "lr": 9.826654418024106e-07, "epoch": 18.388338833883388, "percentage": 91.94, "elapsed_time": "6:36:03", "remaining_time": "0:34:42", "throughput": 1484.47, "total_tokens": 35275744} {"current_steps": 167155, "total_steps": 181800, "loss": 0.0042, "lr": 9.819992657326526e-07, "epoch": 18.38888888888889, "percentage": 91.94, "elapsed_time": "6:36:03", "remaining_time": "0:34:42", "throughput": 1484.47, "total_tokens": 35276832} {"current_steps": 167160, "total_steps": 181800, "loss": 0.0037, "lr": 9.813333110252787e-07, "epoch": 18.38943894389439, "percentage": 91.95, "elapsed_time": "6:36:04", "remaining_time": "0:34:41", "throughput": 1484.47, "total_tokens": 35277920} {"current_steps": 167165, "total_steps": 181800, "loss": 0.0027, "lr": 9.806675776864256e-07, "epoch": 18.38998899889989, "percentage": 91.95, "elapsed_time": "6:36:05", "remaining_time": "0:34:40", "throughput": 1484.48, "total_tokens": 35279072} {"current_steps": 167170, "total_steps": 181800, "loss": 0.0219, "lr": 9.800020657222408e-07, "epoch": 18.39053905390539, "percentage": 91.95, "elapsed_time": "6:36:05", "remaining_time": "0:34:39", "throughput": 1484.48, "total_tokens": 35280160} {"current_steps": 167175, "total_steps": 181800, "loss": 0.0018, "lr": 9.793367751388505e-07, "epoch": 18.39108910891089, "percentage": 91.96, "elapsed_time": "6:36:06", "remaining_time": "0:34:39", "throughput": 1484.48, "total_tokens": 35281216} {"current_steps": 167180, "total_steps": 181800, "loss": 0.0281, "lr": 9.786717059423856e-07, "epoch": 18.39163916391639, "percentage": 91.96, "elapsed_time": "6:36:07", "remaining_time": "0:34:38", "throughput": 1484.47, "total_tokens": 35282272} {"current_steps": 167185, "total_steps": 181800, "loss": 0.0783, "lr": 9.780068581389772e-07, "epoch": 18.392189218921892, "percentage": 91.96, "elapsed_time": "6:36:08", "remaining_time": "0:34:37", "throughput": 1484.47, "total_tokens": 35283328} {"current_steps": 167190, "total_steps": 181800, "loss": 0.0008, "lr": 9.773422317347515e-07, "epoch": 18.392739273927393, "percentage": 91.96, "elapsed_time": "6:36:08", "remaining_time": "0:34:37", "throughput": 1484.47, "total_tokens": 35284352} {"current_steps": 167195, "total_steps": 181800, "loss": 0.005, "lr": 9.766778267358333e-07, "epoch": 18.393289328932894, "percentage": 91.97, "elapsed_time": "6:36:09", "remaining_time": "0:34:36", "throughput": 1484.48, "total_tokens": 35285440} {"current_steps": 167200, "total_steps": 181800, "loss": 0.0036, "lr": 9.760136431483545e-07, "epoch": 18.393839383938396, "percentage": 91.97, "elapsed_time": "6:36:10", "remaining_time": "0:34:35", "throughput": 1484.48, "total_tokens": 35286528} {"current_steps": 167205, "total_steps": 181800, "loss": 0.0018, "lr": 9.75349680978424e-07, "epoch": 18.394389438943893, "percentage": 91.97, "elapsed_time": "6:36:11", "remaining_time": "0:34:34", "throughput": 1484.48, "total_tokens": 35287584} {"current_steps": 167210, "total_steps": 181800, "loss": 0.0048, "lr": 9.746859402321728e-07, "epoch": 18.394939493949394, "percentage": 91.97, "elapsed_time": "6:36:11", "remaining_time": "0:34:34", "throughput": 1484.48, "total_tokens": 35288704} {"current_steps": 167215, "total_steps": 181800, "loss": 0.0449, "lr": 9.740224209157073e-07, "epoch": 18.395489548954895, "percentage": 91.98, "elapsed_time": "6:36:12", "remaining_time": "0:34:33", "throughput": 1484.48, "total_tokens": 35289696} {"current_steps": 167220, "total_steps": 181800, "loss": 0.0032, "lr": 9.73359123035153e-07, "epoch": 18.396039603960396, "percentage": 91.98, "elapsed_time": "6:36:13", "remaining_time": "0:34:32", "throughput": 1484.48, "total_tokens": 35290720} {"current_steps": 167225, "total_steps": 181800, "loss": 0.0011, "lr": 9.726960465966162e-07, "epoch": 18.396589658965897, "percentage": 91.98, "elapsed_time": "6:36:13", "remaining_time": "0:34:32", "throughput": 1484.48, "total_tokens": 35291776} {"current_steps": 167230, "total_steps": 181800, "loss": 0.0028, "lr": 9.720331916062085e-07, "epoch": 18.3971397139714, "percentage": 91.99, "elapsed_time": "6:36:14", "remaining_time": "0:34:31", "throughput": 1484.48, "total_tokens": 35292800} {"current_steps": 167235, "total_steps": 181800, "loss": 0.0033, "lr": 9.71370558070045e-07, "epoch": 18.397689768976896, "percentage": 91.99, "elapsed_time": "6:36:15", "remaining_time": "0:34:30", "throughput": 1484.49, "total_tokens": 35293888} {"current_steps": 167240, "total_steps": 181800, "loss": 0.0177, "lr": 9.707081459942258e-07, "epoch": 18.398239823982397, "percentage": 91.99, "elapsed_time": "6:36:15", "remaining_time": "0:34:29", "throughput": 1484.49, "total_tokens": 35294944} {"current_steps": 167245, "total_steps": 181800, "loss": 0.1347, "lr": 9.70045955384863e-07, "epoch": 18.3987898789879, "percentage": 91.99, "elapsed_time": "6:36:16", "remaining_time": "0:34:29", "throughput": 1484.49, "total_tokens": 35296032} {"current_steps": 167250, "total_steps": 181800, "loss": 0.002, "lr": 9.693839862480514e-07, "epoch": 18.3993399339934, "percentage": 92.0, "elapsed_time": "6:36:17", "remaining_time": "0:34:28", "throughput": 1484.49, "total_tokens": 35297152} {"current_steps": 167255, "total_steps": 181800, "loss": 0.0702, "lr": 9.687222385898976e-07, "epoch": 18.3998899889989, "percentage": 92.0, "elapsed_time": "6:36:17", "remaining_time": "0:34:27", "throughput": 1484.49, "total_tokens": 35298208} {"current_steps": 167260, "total_steps": 181800, "loss": 0.0578, "lr": 9.680607124165048e-07, "epoch": 18.4004400440044, "percentage": 92.0, "elapsed_time": "6:36:18", "remaining_time": "0:34:27", "throughput": 1484.5, "total_tokens": 35299296} {"current_steps": 167265, "total_steps": 181800, "loss": 0.0097, "lr": 9.673994077339571e-07, "epoch": 18.400990099009903, "percentage": 92.0, "elapsed_time": "6:36:19", "remaining_time": "0:34:26", "throughput": 1484.5, "total_tokens": 35300384} {"current_steps": 167270, "total_steps": 181800, "loss": 0.0008, "lr": 9.667383245483635e-07, "epoch": 18.4015401540154, "percentage": 92.01, "elapsed_time": "6:36:20", "remaining_time": "0:34:25", "throughput": 1484.5, "total_tokens": 35301440} {"current_steps": 167275, "total_steps": 181800, "loss": 0.0039, "lr": 9.66077462865811e-07, "epoch": 18.4020902090209, "percentage": 92.01, "elapsed_time": "6:36:20", "remaining_time": "0:34:24", "throughput": 1484.5, "total_tokens": 35302528} {"current_steps": 167280, "total_steps": 181800, "loss": 0.0862, "lr": 9.654168226923833e-07, "epoch": 18.402640264026402, "percentage": 92.01, "elapsed_time": "6:36:21", "remaining_time": "0:34:24", "throughput": 1484.5, "total_tokens": 35303584} {"current_steps": 167285, "total_steps": 181800, "loss": 0.1426, "lr": 9.647564040341783e-07, "epoch": 18.403190319031903, "percentage": 92.02, "elapsed_time": "6:36:22", "remaining_time": "0:34:23", "throughput": 1484.5, "total_tokens": 35304576} {"current_steps": 167290, "total_steps": 181800, "loss": 0.0075, "lr": 9.640962068972802e-07, "epoch": 18.403740374037405, "percentage": 92.02, "elapsed_time": "6:36:22", "remaining_time": "0:34:22", "throughput": 1484.51, "total_tokens": 35305664} {"current_steps": 167295, "total_steps": 181800, "loss": 0.0099, "lr": 9.634362312877788e-07, "epoch": 18.404290429042906, "percentage": 92.02, "elapsed_time": "6:36:23", "remaining_time": "0:34:22", "throughput": 1484.51, "total_tokens": 35306720} {"current_steps": 167300, "total_steps": 181800, "loss": 0.0108, "lr": 9.627764772117492e-07, "epoch": 18.404840484048403, "percentage": 92.02, "elapsed_time": "6:36:24", "remaining_time": "0:34:21", "throughput": 1484.51, "total_tokens": 35307808} {"current_steps": 167305, "total_steps": 181800, "loss": 0.0023, "lr": 9.621169446752705e-07, "epoch": 18.405390539053904, "percentage": 92.03, "elapsed_time": "6:36:24", "remaining_time": "0:34:20", "throughput": 1484.51, "total_tokens": 35308896} {"current_steps": 167310, "total_steps": 181800, "loss": 0.0816, "lr": 9.614576336844289e-07, "epoch": 18.405940594059405, "percentage": 92.03, "elapsed_time": "6:36:25", "remaining_time": "0:34:19", "throughput": 1484.52, "total_tokens": 35310016} {"current_steps": 167315, "total_steps": 181800, "loss": 0.0095, "lr": 9.60798544245295e-07, "epoch": 18.406490649064907, "percentage": 92.03, "elapsed_time": "6:36:26", "remaining_time": "0:34:19", "throughput": 1484.52, "total_tokens": 35311040} {"current_steps": 167320, "total_steps": 181800, "loss": 0.0022, "lr": 9.601396763639498e-07, "epoch": 18.407040704070408, "percentage": 92.04, "elapsed_time": "6:36:26", "remaining_time": "0:34:18", "throughput": 1484.52, "total_tokens": 35312128} {"current_steps": 167325, "total_steps": 181800, "loss": 0.1011, "lr": 9.594810300464607e-07, "epoch": 18.40759075907591, "percentage": 92.04, "elapsed_time": "6:36:27", "remaining_time": "0:34:17", "throughput": 1484.52, "total_tokens": 35313152} {"current_steps": 167330, "total_steps": 181800, "loss": 0.0411, "lr": 9.588226052988952e-07, "epoch": 18.40814081408141, "percentage": 92.04, "elapsed_time": "6:36:28", "remaining_time": "0:34:17", "throughput": 1484.52, "total_tokens": 35314240} {"current_steps": 167335, "total_steps": 181800, "loss": 0.0018, "lr": 9.581644021273317e-07, "epoch": 18.408690869086907, "percentage": 92.04, "elapsed_time": "6:36:29", "remaining_time": "0:34:16", "throughput": 1484.52, "total_tokens": 35315264} {"current_steps": 167340, "total_steps": 181800, "loss": 0.0024, "lr": 9.575064205378265e-07, "epoch": 18.40924092409241, "percentage": 92.05, "elapsed_time": "6:36:29", "remaining_time": "0:34:15", "throughput": 1484.52, "total_tokens": 35316320} {"current_steps": 167345, "total_steps": 181800, "loss": 0.0031, "lr": 9.56848660536447e-07, "epoch": 18.40979097909791, "percentage": 92.05, "elapsed_time": "6:36:30", "remaining_time": "0:34:14", "throughput": 1484.52, "total_tokens": 35317408} {"current_steps": 167350, "total_steps": 181800, "loss": 0.0009, "lr": 9.561911221292602e-07, "epoch": 18.41034103410341, "percentage": 92.05, "elapsed_time": "6:36:31", "remaining_time": "0:34:14", "throughput": 1484.52, "total_tokens": 35318368} {"current_steps": 167355, "total_steps": 181800, "loss": 0.0241, "lr": 9.555338053223173e-07, "epoch": 18.41089108910891, "percentage": 92.05, "elapsed_time": "6:36:31", "remaining_time": "0:34:13", "throughput": 1484.52, "total_tokens": 35319424} {"current_steps": 167360, "total_steps": 181800, "loss": 0.0019, "lr": 9.548767101216883e-07, "epoch": 18.411441144114413, "percentage": 92.06, "elapsed_time": "6:36:32", "remaining_time": "0:34:12", "throughput": 1484.52, "total_tokens": 35320480} {"current_steps": 167365, "total_steps": 181800, "loss": 0.07, "lr": 9.542198365334182e-07, "epoch": 18.41199119911991, "percentage": 92.06, "elapsed_time": "6:36:33", "remaining_time": "0:34:12", "throughput": 1484.53, "total_tokens": 35321536} {"current_steps": 167370, "total_steps": 181800, "loss": 0.0035, "lr": 9.535631845635635e-07, "epoch": 18.41254125412541, "percentage": 92.06, "elapsed_time": "6:36:33", "remaining_time": "0:34:11", "throughput": 1484.53, "total_tokens": 35322592} {"current_steps": 167375, "total_steps": 181800, "loss": 0.0017, "lr": 9.529067542181829e-07, "epoch": 18.413091309130913, "percentage": 92.07, "elapsed_time": "6:36:34", "remaining_time": "0:34:10", "throughput": 1484.53, "total_tokens": 35323680} {"current_steps": 167380, "total_steps": 181800, "loss": 0.0027, "lr": 9.522505455033193e-07, "epoch": 18.413641364136414, "percentage": 92.07, "elapsed_time": "6:36:35", "remaining_time": "0:34:09", "throughput": 1484.53, "total_tokens": 35324704} {"current_steps": 167385, "total_steps": 181800, "loss": 0.0022, "lr": 9.515945584250258e-07, "epoch": 18.414191419141915, "percentage": 92.07, "elapsed_time": "6:36:35", "remaining_time": "0:34:09", "throughput": 1484.53, "total_tokens": 35325824} {"current_steps": 167390, "total_steps": 181800, "loss": 0.0256, "lr": 9.509387929893476e-07, "epoch": 18.414741474147416, "percentage": 92.07, "elapsed_time": "6:36:36", "remaining_time": "0:34:08", "throughput": 1484.53, "total_tokens": 35326848} {"current_steps": 167395, "total_steps": 181800, "loss": 0.0017, "lr": 9.502832492023217e-07, "epoch": 18.415291529152917, "percentage": 92.08, "elapsed_time": "6:36:37", "remaining_time": "0:34:07", "throughput": 1484.54, "total_tokens": 35327968} {"current_steps": 167400, "total_steps": 181800, "loss": 0.0709, "lr": 9.496279270699931e-07, "epoch": 18.415841584158414, "percentage": 92.08, "elapsed_time": "6:36:37", "remaining_time": "0:34:07", "throughput": 1484.54, "total_tokens": 35328992} {"current_steps": 167405, "total_steps": 181800, "loss": 0.004, "lr": 9.489728265984071e-07, "epoch": 18.416391639163916, "percentage": 92.08, "elapsed_time": "6:36:38", "remaining_time": "0:34:06", "throughput": 1484.54, "total_tokens": 35330048} {"current_steps": 167410, "total_steps": 181800, "loss": 0.0031, "lr": 9.483179477935977e-07, "epoch": 18.416941694169417, "percentage": 92.08, "elapsed_time": "6:36:39", "remaining_time": "0:34:05", "throughput": 1484.54, "total_tokens": 35331104} {"current_steps": 167415, "total_steps": 181800, "loss": 0.0048, "lr": 9.476632906616017e-07, "epoch": 18.417491749174918, "percentage": 92.09, "elapsed_time": "6:36:40", "remaining_time": "0:34:05", "throughput": 1484.54, "total_tokens": 35332160} {"current_steps": 167420, "total_steps": 181800, "loss": 0.0047, "lr": 9.470088552084505e-07, "epoch": 18.41804180418042, "percentage": 92.09, "elapsed_time": "6:36:40", "remaining_time": "0:34:04", "throughput": 1484.54, "total_tokens": 35333216} {"current_steps": 167425, "total_steps": 181800, "loss": 0.0482, "lr": 9.463546414401752e-07, "epoch": 18.41859185918592, "percentage": 92.09, "elapsed_time": "6:36:41", "remaining_time": "0:34:03", "throughput": 1484.54, "total_tokens": 35334304} {"current_steps": 167430, "total_steps": 181800, "loss": 0.0939, "lr": 9.457006493628073e-07, "epoch": 18.419141914191417, "percentage": 92.1, "elapsed_time": "6:36:42", "remaining_time": "0:34:02", "throughput": 1484.55, "total_tokens": 35335360} {"current_steps": 167435, "total_steps": 181800, "loss": 0.0366, "lr": 9.45046878982378e-07, "epoch": 18.41969196919692, "percentage": 92.1, "elapsed_time": "6:36:42", "remaining_time": "0:34:02", "throughput": 1484.55, "total_tokens": 35336416} {"current_steps": 167440, "total_steps": 181800, "loss": 0.1009, "lr": 9.443933303049074e-07, "epoch": 18.42024202420242, "percentage": 92.1, "elapsed_time": "6:36:43", "remaining_time": "0:34:01", "throughput": 1484.55, "total_tokens": 35337440} {"current_steps": 167445, "total_steps": 181800, "loss": 0.0073, "lr": 9.437400033364185e-07, "epoch": 18.42079207920792, "percentage": 92.1, "elapsed_time": "6:36:44", "remaining_time": "0:34:00", "throughput": 1484.55, "total_tokens": 35338496} {"current_steps": 167450, "total_steps": 181800, "loss": 0.0018, "lr": 9.430868980829372e-07, "epoch": 18.421342134213422, "percentage": 92.11, "elapsed_time": "6:36:44", "remaining_time": "0:34:00", "throughput": 1484.55, "total_tokens": 35339488} {"current_steps": 167455, "total_steps": 181800, "loss": 0.0486, "lr": 9.424340145504778e-07, "epoch": 18.421892189218923, "percentage": 92.11, "elapsed_time": "6:36:45", "remaining_time": "0:33:59", "throughput": 1484.55, "total_tokens": 35340608} {"current_steps": 167460, "total_steps": 181800, "loss": 0.1759, "lr": 9.417813527450608e-07, "epoch": 18.422442244224424, "percentage": 92.11, "elapsed_time": "6:36:46", "remaining_time": "0:33:58", "throughput": 1484.55, "total_tokens": 35341632} {"current_steps": 167465, "total_steps": 181800, "loss": 0.003, "lr": 9.411289126727008e-07, "epoch": 18.42299229922992, "percentage": 92.11, "elapsed_time": "6:36:46", "remaining_time": "0:33:57", "throughput": 1484.55, "total_tokens": 35342720} {"current_steps": 167470, "total_steps": 181800, "loss": 0.0116, "lr": 9.404766943394122e-07, "epoch": 18.423542354235423, "percentage": 92.12, "elapsed_time": "6:36:47", "remaining_time": "0:33:57", "throughput": 1484.55, "total_tokens": 35343744} {"current_steps": 167475, "total_steps": 181800, "loss": 0.0987, "lr": 9.398246977512043e-07, "epoch": 18.424092409240924, "percentage": 92.12, "elapsed_time": "6:36:48", "remaining_time": "0:33:56", "throughput": 1484.55, "total_tokens": 35344768} {"current_steps": 167480, "total_steps": 181800, "loss": 0.0842, "lr": 9.391729229140861e-07, "epoch": 18.424642464246425, "percentage": 92.12, "elapsed_time": "6:36:49", "remaining_time": "0:33:55", "throughput": 1484.55, "total_tokens": 35345792} {"current_steps": 167485, "total_steps": 181800, "loss": 0.0041, "lr": 9.385213698340667e-07, "epoch": 18.425192519251926, "percentage": 92.13, "elapsed_time": "6:36:49", "remaining_time": "0:33:55", "throughput": 1484.56, "total_tokens": 35346848} {"current_steps": 167490, "total_steps": 181800, "loss": 0.0049, "lr": 9.378700385171496e-07, "epoch": 18.425742574257427, "percentage": 92.13, "elapsed_time": "6:36:50", "remaining_time": "0:33:54", "throughput": 1484.56, "total_tokens": 35347936} {"current_steps": 167495, "total_steps": 181800, "loss": 0.0009, "lr": 9.372189289693384e-07, "epoch": 18.426292629262925, "percentage": 92.13, "elapsed_time": "6:36:51", "remaining_time": "0:33:53", "throughput": 1484.56, "total_tokens": 35348928} {"current_steps": 167500, "total_steps": 181800, "loss": 0.0366, "lr": 9.365680411966338e-07, "epoch": 18.426842684268426, "percentage": 92.13, "elapsed_time": "6:36:51", "remaining_time": "0:33:52", "throughput": 1484.56, "total_tokens": 35349984} {"current_steps": 167505, "total_steps": 181800, "loss": 0.1175, "lr": 9.359173752050338e-07, "epoch": 18.427392739273927, "percentage": 92.14, "elapsed_time": "6:36:52", "remaining_time": "0:33:52", "throughput": 1484.56, "total_tokens": 35351040} {"current_steps": 167510, "total_steps": 181800, "loss": 0.0635, "lr": 9.352669310005391e-07, "epoch": 18.427942794279428, "percentage": 92.14, "elapsed_time": "6:36:53", "remaining_time": "0:33:51", "throughput": 1484.56, "total_tokens": 35352096} {"current_steps": 167515, "total_steps": 181800, "loss": 0.0059, "lr": 9.346167085891394e-07, "epoch": 18.42849284928493, "percentage": 92.14, "elapsed_time": "6:36:53", "remaining_time": "0:33:50", "throughput": 1484.56, "total_tokens": 35353120} {"current_steps": 167520, "total_steps": 181800, "loss": 0.0018, "lr": 9.3396670797683e-07, "epoch": 18.42904290429043, "percentage": 92.15, "elapsed_time": "6:36:54", "remaining_time": "0:33:50", "throughput": 1484.56, "total_tokens": 35354144} {"current_steps": 167525, "total_steps": 181800, "loss": 0.0431, "lr": 9.333169291696031e-07, "epoch": 18.42959295929593, "percentage": 92.15, "elapsed_time": "6:36:55", "remaining_time": "0:33:49", "throughput": 1484.56, "total_tokens": 35355200} {"current_steps": 167530, "total_steps": 181800, "loss": 0.0087, "lr": 9.32667372173443e-07, "epoch": 18.43014301430143, "percentage": 92.15, "elapsed_time": "6:36:55", "remaining_time": "0:33:48", "throughput": 1484.56, "total_tokens": 35356224} {"current_steps": 167535, "total_steps": 181800, "loss": 0.0252, "lr": 9.320180369943421e-07, "epoch": 18.43069306930693, "percentage": 92.15, "elapsed_time": "6:36:56", "remaining_time": "0:33:47", "throughput": 1484.56, "total_tokens": 35357280} {"current_steps": 167540, "total_steps": 181800, "loss": 0.0335, "lr": 9.313689236382788e-07, "epoch": 18.43124312431243, "percentage": 92.16, "elapsed_time": "6:36:57", "remaining_time": "0:33:47", "throughput": 1484.56, "total_tokens": 35358304} {"current_steps": 167545, "total_steps": 181800, "loss": 0.0066, "lr": 9.307200321112375e-07, "epoch": 18.431793179317932, "percentage": 92.16, "elapsed_time": "6:36:57", "remaining_time": "0:33:46", "throughput": 1484.56, "total_tokens": 35359328} {"current_steps": 167550, "total_steps": 181800, "loss": 0.0073, "lr": 9.300713624192047e-07, "epoch": 18.432343234323433, "percentage": 92.16, "elapsed_time": "6:36:58", "remaining_time": "0:33:45", "throughput": 1484.56, "total_tokens": 35360288} {"current_steps": 167555, "total_steps": 181800, "loss": 0.0004, "lr": 9.294229145681565e-07, "epoch": 18.432893289328934, "percentage": 92.16, "elapsed_time": "6:36:59", "remaining_time": "0:33:45", "throughput": 1484.56, "total_tokens": 35361280} {"current_steps": 167560, "total_steps": 181800, "loss": 0.0037, "lr": 9.287746885640603e-07, "epoch": 18.433443344334435, "percentage": 92.17, "elapsed_time": "6:37:00", "remaining_time": "0:33:44", "throughput": 1484.56, "total_tokens": 35362336} {"current_steps": 167565, "total_steps": 181800, "loss": 0.016, "lr": 9.281266844129027e-07, "epoch": 18.433993399339933, "percentage": 92.17, "elapsed_time": "6:37:00", "remaining_time": "0:33:43", "throughput": 1484.56, "total_tokens": 35363392} {"current_steps": 167570, "total_steps": 181800, "loss": 0.0014, "lr": 9.274789021206459e-07, "epoch": 18.434543454345434, "percentage": 92.17, "elapsed_time": "6:37:01", "remaining_time": "0:33:42", "throughput": 1484.56, "total_tokens": 35364416} {"current_steps": 167575, "total_steps": 181800, "loss": 0.0011, "lr": 9.268313416932683e-07, "epoch": 18.435093509350935, "percentage": 92.18, "elapsed_time": "6:37:02", "remaining_time": "0:33:42", "throughput": 1484.57, "total_tokens": 35365504} {"current_steps": 167580, "total_steps": 181800, "loss": 0.0043, "lr": 9.261840031367347e-07, "epoch": 18.435643564356436, "percentage": 92.18, "elapsed_time": "6:37:02", "remaining_time": "0:33:41", "throughput": 1484.57, "total_tokens": 35366624} {"current_steps": 167585, "total_steps": 181800, "loss": 0.0337, "lr": 9.255368864570097e-07, "epoch": 18.436193619361937, "percentage": 92.18, "elapsed_time": "6:37:03", "remaining_time": "0:33:40", "throughput": 1484.57, "total_tokens": 35367680} {"current_steps": 167590, "total_steps": 181800, "loss": 0.0158, "lr": 9.248899916600606e-07, "epoch": 18.436743674367438, "percentage": 92.18, "elapsed_time": "6:37:04", "remaining_time": "0:33:40", "throughput": 1484.57, "total_tokens": 35368768} {"current_steps": 167595, "total_steps": 181800, "loss": 0.1221, "lr": 9.242433187518468e-07, "epoch": 18.437293729372936, "percentage": 92.19, "elapsed_time": "6:37:04", "remaining_time": "0:33:39", "throughput": 1484.58, "total_tokens": 35369888} {"current_steps": 167600, "total_steps": 181800, "loss": 0.0393, "lr": 9.2359686773833e-07, "epoch": 18.437843784378437, "percentage": 92.19, "elapsed_time": "6:37:05", "remaining_time": "0:33:38", "throughput": 1484.58, "total_tokens": 35370912} {"current_steps": 167605, "total_steps": 181800, "loss": 0.0066, "lr": 9.229506386254693e-07, "epoch": 18.438393839383938, "percentage": 92.19, "elapsed_time": "6:37:06", "remaining_time": "0:33:37", "throughput": 1484.58, "total_tokens": 35371936} {"current_steps": 167610, "total_steps": 181800, "loss": 0.0573, "lr": 9.223046314192158e-07, "epoch": 18.43894389438944, "percentage": 92.19, "elapsed_time": "6:37:06", "remaining_time": "0:33:37", "throughput": 1484.58, "total_tokens": 35372992} {"current_steps": 167615, "total_steps": 181800, "loss": 0.0061, "lr": 9.21658846125531e-07, "epoch": 18.43949394939494, "percentage": 92.2, "elapsed_time": "6:37:07", "remaining_time": "0:33:36", "throughput": 1484.58, "total_tokens": 35374016} {"current_steps": 167620, "total_steps": 181800, "loss": 0.0794, "lr": 9.210132827503604e-07, "epoch": 18.44004400440044, "percentage": 92.2, "elapsed_time": "6:37:08", "remaining_time": "0:33:35", "throughput": 1484.58, "total_tokens": 35375008} {"current_steps": 167625, "total_steps": 181800, "loss": 0.0259, "lr": 9.203679412996575e-07, "epoch": 18.440594059405942, "percentage": 92.2, "elapsed_time": "6:37:09", "remaining_time": "0:33:35", "throughput": 1484.58, "total_tokens": 35376064} {"current_steps": 167630, "total_steps": 181800, "loss": 0.0808, "lr": 9.197228217793675e-07, "epoch": 18.44114411441144, "percentage": 92.21, "elapsed_time": "6:37:09", "remaining_time": "0:33:34", "throughput": 1484.58, "total_tokens": 35377184} {"current_steps": 167635, "total_steps": 181800, "loss": 0.0097, "lr": 9.190779241954356e-07, "epoch": 18.44169416941694, "percentage": 92.21, "elapsed_time": "6:37:10", "remaining_time": "0:33:33", "throughput": 1484.58, "total_tokens": 35378240} {"current_steps": 167640, "total_steps": 181800, "loss": 0.0314, "lr": 9.184332485538128e-07, "epoch": 18.442244224422442, "percentage": 92.21, "elapsed_time": "6:37:11", "remaining_time": "0:33:32", "throughput": 1484.58, "total_tokens": 35379264} {"current_steps": 167645, "total_steps": 181800, "loss": 0.0518, "lr": 9.177887948604302e-07, "epoch": 18.442794279427943, "percentage": 92.21, "elapsed_time": "6:37:11", "remaining_time": "0:33:32", "throughput": 1484.59, "total_tokens": 35380320} {"current_steps": 167650, "total_steps": 181800, "loss": 0.0022, "lr": 9.171445631212361e-07, "epoch": 18.443344334433444, "percentage": 92.22, "elapsed_time": "6:37:12", "remaining_time": "0:33:31", "throughput": 1484.59, "total_tokens": 35381344} {"current_steps": 167655, "total_steps": 181800, "loss": 0.0049, "lr": 9.165005533421616e-07, "epoch": 18.443894389438945, "percentage": 92.22, "elapsed_time": "6:37:13", "remaining_time": "0:33:30", "throughput": 1484.59, "total_tokens": 35382432} {"current_steps": 167660, "total_steps": 181800, "loss": 0.0021, "lr": 9.158567655291439e-07, "epoch": 18.444444444444443, "percentage": 92.22, "elapsed_time": "6:37:13", "remaining_time": "0:33:30", "throughput": 1484.59, "total_tokens": 35383456} {"current_steps": 167665, "total_steps": 181800, "loss": 0.0047, "lr": 9.152131996881224e-07, "epoch": 18.444994499449944, "percentage": 92.22, "elapsed_time": "6:37:14", "remaining_time": "0:33:29", "throughput": 1484.59, "total_tokens": 35384512} {"current_steps": 167670, "total_steps": 181800, "loss": 0.1146, "lr": 9.145698558250204e-07, "epoch": 18.445544554455445, "percentage": 92.23, "elapsed_time": "6:37:15", "remaining_time": "0:33:28", "throughput": 1484.59, "total_tokens": 35385568} {"current_steps": 167675, "total_steps": 181800, "loss": 0.0033, "lr": 9.139267339457747e-07, "epoch": 18.446094609460946, "percentage": 92.23, "elapsed_time": "6:37:15", "remaining_time": "0:33:27", "throughput": 1484.59, "total_tokens": 35386592} {"current_steps": 167680, "total_steps": 181800, "loss": 0.1027, "lr": 9.132838340563055e-07, "epoch": 18.446644664466447, "percentage": 92.23, "elapsed_time": "6:37:16", "remaining_time": "0:33:27", "throughput": 1484.59, "total_tokens": 35387616} {"current_steps": 167685, "total_steps": 181800, "loss": 0.1201, "lr": 9.126411561625414e-07, "epoch": 18.44719471947195, "percentage": 92.24, "elapsed_time": "6:37:17", "remaining_time": "0:33:26", "throughput": 1484.59, "total_tokens": 35388704} {"current_steps": 167690, "total_steps": 181800, "loss": 0.1189, "lr": 9.119987002704028e-07, "epoch": 18.44774477447745, "percentage": 92.24, "elapsed_time": "6:37:18", "remaining_time": "0:33:25", "throughput": 1484.59, "total_tokens": 35389696} {"current_steps": 167695, "total_steps": 181800, "loss": 0.072, "lr": 9.113564663858154e-07, "epoch": 18.448294829482947, "percentage": 92.24, "elapsed_time": "6:37:18", "remaining_time": "0:33:25", "throughput": 1484.59, "total_tokens": 35390688} {"current_steps": 167700, "total_steps": 181800, "loss": 0.0012, "lr": 9.107144545146995e-07, "epoch": 18.448844884488448, "percentage": 92.24, "elapsed_time": "6:37:19", "remaining_time": "0:33:24", "throughput": 1484.59, "total_tokens": 35391680} {"current_steps": 167705, "total_steps": 181800, "loss": 0.0044, "lr": 9.100726646629699e-07, "epoch": 18.44939493949395, "percentage": 92.25, "elapsed_time": "6:37:20", "remaining_time": "0:33:23", "throughput": 1484.6, "total_tokens": 35392864} {"current_steps": 167710, "total_steps": 181800, "loss": 0.0021, "lr": 9.094310968365383e-07, "epoch": 18.44994499449945, "percentage": 92.25, "elapsed_time": "6:37:20", "remaining_time": "0:33:22", "throughput": 1484.6, "total_tokens": 35393920} {"current_steps": 167715, "total_steps": 181800, "loss": 0.0092, "lr": 9.087897510413196e-07, "epoch": 18.45049504950495, "percentage": 92.25, "elapsed_time": "6:37:21", "remaining_time": "0:33:22", "throughput": 1484.6, "total_tokens": 35394976} {"current_steps": 167720, "total_steps": 181800, "loss": 0.0015, "lr": 9.081486272832257e-07, "epoch": 18.451045104510452, "percentage": 92.26, "elapsed_time": "6:37:22", "remaining_time": "0:33:21", "throughput": 1484.6, "total_tokens": 35396064} {"current_steps": 167725, "total_steps": 181800, "loss": 0.0629, "lr": 9.075077255681686e-07, "epoch": 18.45159515951595, "percentage": 92.26, "elapsed_time": "6:37:22", "remaining_time": "0:33:20", "throughput": 1484.6, "total_tokens": 35397088} {"current_steps": 167730, "total_steps": 181800, "loss": 0.0053, "lr": 9.068670459020517e-07, "epoch": 18.45214521452145, "percentage": 92.26, "elapsed_time": "6:37:23", "remaining_time": "0:33:20", "throughput": 1484.6, "total_tokens": 35398112} {"current_steps": 167735, "total_steps": 181800, "loss": 0.0049, "lr": 9.062265882907761e-07, "epoch": 18.452695269526952, "percentage": 92.26, "elapsed_time": "6:37:24", "remaining_time": "0:33:19", "throughput": 1484.6, "total_tokens": 35399232} {"current_steps": 167740, "total_steps": 181800, "loss": 0.005, "lr": 9.055863527402536e-07, "epoch": 18.453245324532453, "percentage": 92.27, "elapsed_time": "6:37:24", "remaining_time": "0:33:18", "throughput": 1484.61, "total_tokens": 35400352} {"current_steps": 167745, "total_steps": 181800, "loss": 0.0037, "lr": 9.049463392563767e-07, "epoch": 18.453795379537954, "percentage": 92.27, "elapsed_time": "6:37:25", "remaining_time": "0:33:17", "throughput": 1484.61, "total_tokens": 35401408} {"current_steps": 167750, "total_steps": 181800, "loss": 0.0052, "lr": 9.043065478450491e-07, "epoch": 18.454345434543455, "percentage": 92.27, "elapsed_time": "6:37:26", "remaining_time": "0:33:17", "throughput": 1484.61, "total_tokens": 35402432} {"current_steps": 167755, "total_steps": 181800, "loss": 0.0034, "lr": 9.03666978512166e-07, "epoch": 18.454895489548957, "percentage": 92.27, "elapsed_time": "6:37:26", "remaining_time": "0:33:16", "throughput": 1484.61, "total_tokens": 35403488} {"current_steps": 167760, "total_steps": 181800, "loss": 0.0546, "lr": 9.030276312636199e-07, "epoch": 18.455445544554454, "percentage": 92.28, "elapsed_time": "6:37:27", "remaining_time": "0:33:15", "throughput": 1484.61, "total_tokens": 35404544} {"current_steps": 167765, "total_steps": 181800, "loss": 0.0703, "lr": 9.023885061053089e-07, "epoch": 18.455995599559955, "percentage": 92.28, "elapsed_time": "6:37:28", "remaining_time": "0:33:15", "throughput": 1484.61, "total_tokens": 35405568} {"current_steps": 167770, "total_steps": 181800, "loss": 0.0205, "lr": 9.017496030431199e-07, "epoch": 18.456545654565456, "percentage": 92.28, "elapsed_time": "6:37:29", "remaining_time": "0:33:14", "throughput": 1484.62, "total_tokens": 35406688} {"current_steps": 167775, "total_steps": 181800, "loss": 0.0017, "lr": 9.011109220829344e-07, "epoch": 18.457095709570957, "percentage": 92.29, "elapsed_time": "6:37:29", "remaining_time": "0:33:13", "throughput": 1484.62, "total_tokens": 35407712} {"current_steps": 167780, "total_steps": 181800, "loss": 0.0042, "lr": 9.004724632306505e-07, "epoch": 18.45764576457646, "percentage": 92.29, "elapsed_time": "6:37:30", "remaining_time": "0:33:12", "throughput": 1484.62, "total_tokens": 35408768} {"current_steps": 167785, "total_steps": 181800, "loss": 0.0111, "lr": 8.998342264921467e-07, "epoch": 18.45819581958196, "percentage": 92.29, "elapsed_time": "6:37:31", "remaining_time": "0:33:12", "throughput": 1484.62, "total_tokens": 35409792} {"current_steps": 167790, "total_steps": 181800, "loss": 0.1416, "lr": 8.991962118733099e-07, "epoch": 18.458745874587457, "percentage": 92.29, "elapsed_time": "6:37:31", "remaining_time": "0:33:11", "throughput": 1484.62, "total_tokens": 35410816} {"current_steps": 167795, "total_steps": 181800, "loss": 0.0891, "lr": 8.985584193800161e-07, "epoch": 18.459295929592958, "percentage": 92.3, "elapsed_time": "6:37:32", "remaining_time": "0:33:10", "throughput": 1484.62, "total_tokens": 35411872} {"current_steps": 167800, "total_steps": 181800, "loss": 0.0624, "lr": 8.979208490181413e-07, "epoch": 18.45984598459846, "percentage": 92.3, "elapsed_time": "6:37:33", "remaining_time": "0:33:10", "throughput": 1484.62, "total_tokens": 35412992} {"current_steps": 167805, "total_steps": 181800, "loss": 0.0543, "lr": 8.972835007935637e-07, "epoch": 18.46039603960396, "percentage": 92.3, "elapsed_time": "6:37:33", "remaining_time": "0:33:09", "throughput": 1484.63, "total_tokens": 35414144} {"current_steps": 167810, "total_steps": 181800, "loss": 0.0015, "lr": 8.966463747121595e-07, "epoch": 18.46094609460946, "percentage": 92.3, "elapsed_time": "6:37:34", "remaining_time": "0:33:08", "throughput": 1484.63, "total_tokens": 35415136} {"current_steps": 167815, "total_steps": 181800, "loss": 0.0054, "lr": 8.960094707798045e-07, "epoch": 18.461496149614963, "percentage": 92.31, "elapsed_time": "6:37:35", "remaining_time": "0:33:07", "throughput": 1484.63, "total_tokens": 35416224} {"current_steps": 167820, "total_steps": 181800, "loss": 0.0069, "lr": 8.953727890023606e-07, "epoch": 18.462046204620464, "percentage": 92.31, "elapsed_time": "6:37:35", "remaining_time": "0:33:07", "throughput": 1484.63, "total_tokens": 35417248} {"current_steps": 167825, "total_steps": 181800, "loss": 0.0471, "lr": 8.947363293856981e-07, "epoch": 18.46259625962596, "percentage": 92.31, "elapsed_time": "6:37:36", "remaining_time": "0:33:06", "throughput": 1484.63, "total_tokens": 35418304} {"current_steps": 167830, "total_steps": 181800, "loss": 0.008, "lr": 8.941000919356873e-07, "epoch": 18.463146314631462, "percentage": 92.32, "elapsed_time": "6:37:37", "remaining_time": "0:33:05", "throughput": 1484.63, "total_tokens": 35419328} {"current_steps": 167835, "total_steps": 181800, "loss": 0.0134, "lr": 8.93464076658182e-07, "epoch": 18.463696369636963, "percentage": 92.32, "elapsed_time": "6:37:38", "remaining_time": "0:33:05", "throughput": 1484.63, "total_tokens": 35420416} {"current_steps": 167840, "total_steps": 181800, "loss": 0.0021, "lr": 8.928282835590579e-07, "epoch": 18.464246424642464, "percentage": 92.32, "elapsed_time": "6:37:38", "remaining_time": "0:33:04", "throughput": 1484.63, "total_tokens": 35421472} {"current_steps": 167845, "total_steps": 181800, "loss": 0.0007, "lr": 8.92192712644166e-07, "epoch": 18.464796479647966, "percentage": 92.32, "elapsed_time": "6:37:39", "remaining_time": "0:33:03", "throughput": 1484.64, "total_tokens": 35422528} {"current_steps": 167850, "total_steps": 181800, "loss": 0.0138, "lr": 8.915573639193653e-07, "epoch": 18.465346534653467, "percentage": 92.33, "elapsed_time": "6:37:40", "remaining_time": "0:33:03", "throughput": 1484.64, "total_tokens": 35423584} {"current_steps": 167855, "total_steps": 181800, "loss": 0.0017, "lr": 8.909222373905124e-07, "epoch": 18.465896589658964, "percentage": 92.33, "elapsed_time": "6:37:40", "remaining_time": "0:33:02", "throughput": 1484.64, "total_tokens": 35424704} {"current_steps": 167860, "total_steps": 181800, "loss": 0.0031, "lr": 8.90287333063461e-07, "epoch": 18.466446644664465, "percentage": 92.33, "elapsed_time": "6:37:41", "remaining_time": "0:33:01", "throughput": 1484.64, "total_tokens": 35425760} {"current_steps": 167865, "total_steps": 181800, "loss": 0.0087, "lr": 8.896526509440589e-07, "epoch": 18.466996699669966, "percentage": 92.33, "elapsed_time": "6:37:42", "remaining_time": "0:33:00", "throughput": 1484.64, "total_tokens": 35426816} {"current_steps": 167870, "total_steps": 181800, "loss": 0.0585, "lr": 8.890181910381629e-07, "epoch": 18.467546754675467, "percentage": 92.34, "elapsed_time": "6:37:42", "remaining_time": "0:33:00", "throughput": 1484.65, "total_tokens": 35427872} {"current_steps": 167875, "total_steps": 181800, "loss": 0.0772, "lr": 8.883839533516153e-07, "epoch": 18.46809680968097, "percentage": 92.34, "elapsed_time": "6:37:43", "remaining_time": "0:32:59", "throughput": 1484.65, "total_tokens": 35428928} {"current_steps": 167880, "total_steps": 181800, "loss": 0.1249, "lr": 8.877499378902643e-07, "epoch": 18.46864686468647, "percentage": 92.34, "elapsed_time": "6:37:44", "remaining_time": "0:32:58", "throughput": 1484.65, "total_tokens": 35429984} {"current_steps": 167885, "total_steps": 181800, "loss": 0.0204, "lr": 8.871161446599496e-07, "epoch": 18.46919691969197, "percentage": 92.35, "elapsed_time": "6:37:44", "remaining_time": "0:32:58", "throughput": 1484.65, "total_tokens": 35431072} {"current_steps": 167890, "total_steps": 181800, "loss": 0.0019, "lr": 8.864825736665167e-07, "epoch": 18.46974697469747, "percentage": 92.35, "elapsed_time": "6:37:45", "remaining_time": "0:32:57", "throughput": 1484.65, "total_tokens": 35432160} {"current_steps": 167895, "total_steps": 181800, "loss": 0.0078, "lr": 8.858492249158024e-07, "epoch": 18.47029702970297, "percentage": 92.35, "elapsed_time": "6:37:46", "remaining_time": "0:32:56", "throughput": 1484.65, "total_tokens": 35433152} {"current_steps": 167900, "total_steps": 181800, "loss": 0.0659, "lr": 8.85216098413641e-07, "epoch": 18.47084708470847, "percentage": 92.35, "elapsed_time": "6:37:46", "remaining_time": "0:32:55", "throughput": 1484.66, "total_tokens": 35434272} {"current_steps": 167905, "total_steps": 181800, "loss": 0.007, "lr": 8.845831941658777e-07, "epoch": 18.47139713971397, "percentage": 92.36, "elapsed_time": "6:37:47", "remaining_time": "0:32:55", "throughput": 1484.66, "total_tokens": 35435296} {"current_steps": 167910, "total_steps": 181800, "loss": 0.0011, "lr": 8.839505121783359e-07, "epoch": 18.471947194719473, "percentage": 92.36, "elapsed_time": "6:37:48", "remaining_time": "0:32:54", "throughput": 1484.65, "total_tokens": 35436288} {"current_steps": 167915, "total_steps": 181800, "loss": 0.0007, "lr": 8.833180524568524e-07, "epoch": 18.472497249724974, "percentage": 92.36, "elapsed_time": "6:37:49", "remaining_time": "0:32:53", "throughput": 1484.66, "total_tokens": 35437344} {"current_steps": 167920, "total_steps": 181800, "loss": 0.0028, "lr": 8.826858150072503e-07, "epoch": 18.47304730473047, "percentage": 92.37, "elapsed_time": "6:37:49", "remaining_time": "0:32:53", "throughput": 1484.66, "total_tokens": 35438432} {"current_steps": 167925, "total_steps": 181800, "loss": 0.0008, "lr": 8.820537998353639e-07, "epoch": 18.473597359735972, "percentage": 92.37, "elapsed_time": "6:37:50", "remaining_time": "0:32:52", "throughput": 1484.66, "total_tokens": 35439456} {"current_steps": 167930, "total_steps": 181800, "loss": 0.0032, "lr": 8.814220069470136e-07, "epoch": 18.474147414741473, "percentage": 92.37, "elapsed_time": "6:37:51", "remaining_time": "0:32:51", "throughput": 1484.66, "total_tokens": 35440512} {"current_steps": 167935, "total_steps": 181800, "loss": 0.0019, "lr": 8.807904363480251e-07, "epoch": 18.474697469746975, "percentage": 92.37, "elapsed_time": "6:37:51", "remaining_time": "0:32:50", "throughput": 1484.66, "total_tokens": 35441536} {"current_steps": 167940, "total_steps": 181800, "loss": 0.0375, "lr": 8.801590880442162e-07, "epoch": 18.475247524752476, "percentage": 92.38, "elapsed_time": "6:37:52", "remaining_time": "0:32:50", "throughput": 1484.66, "total_tokens": 35442624} {"current_steps": 167945, "total_steps": 181800, "loss": 0.0067, "lr": 8.795279620414071e-07, "epoch": 18.475797579757977, "percentage": 92.38, "elapsed_time": "6:37:53", "remaining_time": "0:32:49", "throughput": 1484.66, "total_tokens": 35443616} {"current_steps": 167950, "total_steps": 181800, "loss": 0.0027, "lr": 8.788970583454099e-07, "epoch": 18.476347634763478, "percentage": 92.38, "elapsed_time": "6:37:53", "remaining_time": "0:32:48", "throughput": 1484.66, "total_tokens": 35444640} {"current_steps": 167955, "total_steps": 181800, "loss": 0.0067, "lr": 8.782663769620531e-07, "epoch": 18.476897689768975, "percentage": 92.38, "elapsed_time": "6:37:54", "remaining_time": "0:32:48", "throughput": 1484.66, "total_tokens": 35445728} {"current_steps": 167960, "total_steps": 181800, "loss": 0.0018, "lr": 8.77635917897135e-07, "epoch": 18.477447744774476, "percentage": 92.39, "elapsed_time": "6:37:55", "remaining_time": "0:32:47", "throughput": 1484.67, "total_tokens": 35446848} {"current_steps": 167965, "total_steps": 181800, "loss": 0.0782, "lr": 8.770056811564731e-07, "epoch": 18.477997799779978, "percentage": 92.39, "elapsed_time": "6:37:55", "remaining_time": "0:32:46", "throughput": 1484.67, "total_tokens": 35447904} {"current_steps": 167970, "total_steps": 181800, "loss": 0.0036, "lr": 8.763756667458739e-07, "epoch": 18.47854785478548, "percentage": 92.39, "elapsed_time": "6:37:56", "remaining_time": "0:32:45", "throughput": 1484.67, "total_tokens": 35448992} {"current_steps": 167975, "total_steps": 181800, "loss": 0.0044, "lr": 8.757458746711439e-07, "epoch": 18.47909790979098, "percentage": 92.4, "elapsed_time": "6:37:57", "remaining_time": "0:32:45", "throughput": 1484.67, "total_tokens": 35449984} {"current_steps": 167980, "total_steps": 181800, "loss": 0.0013, "lr": 8.751163049380895e-07, "epoch": 18.47964796479648, "percentage": 92.4, "elapsed_time": "6:37:58", "remaining_time": "0:32:44", "throughput": 1484.67, "total_tokens": 35451072} {"current_steps": 167985, "total_steps": 181800, "loss": 0.0082, "lr": 8.744869575525116e-07, "epoch": 18.480198019801982, "percentage": 92.4, "elapsed_time": "6:37:58", "remaining_time": "0:32:43", "throughput": 1484.67, "total_tokens": 35452096} {"current_steps": 167990, "total_steps": 181800, "loss": 0.0013, "lr": 8.738578325202085e-07, "epoch": 18.48074807480748, "percentage": 92.4, "elapsed_time": "6:37:59", "remaining_time": "0:32:43", "throughput": 1484.67, "total_tokens": 35453120} {"current_steps": 167995, "total_steps": 181800, "loss": 0.0082, "lr": 8.732289298469864e-07, "epoch": 18.48129812981298, "percentage": 92.41, "elapsed_time": "6:38:00", "remaining_time": "0:32:42", "throughput": 1484.67, "total_tokens": 35454176} {"current_steps": 168000, "total_steps": 181800, "loss": 0.0047, "lr": 8.726002495386298e-07, "epoch": 18.48184818481848, "percentage": 92.41, "elapsed_time": "6:38:00", "remaining_time": "0:32:41", "throughput": 1484.68, "total_tokens": 35455264} {"current_steps": 168005, "total_steps": 181800, "loss": 0.0048, "lr": 8.719717916009451e-07, "epoch": 18.482398239823983, "percentage": 92.41, "elapsed_time": "6:38:01", "remaining_time": "0:32:40", "throughput": 1484.68, "total_tokens": 35456320} {"current_steps": 168010, "total_steps": 181800, "loss": 0.1095, "lr": 8.713435560397137e-07, "epoch": 18.482948294829484, "percentage": 92.41, "elapsed_time": "6:38:02", "remaining_time": "0:32:40", "throughput": 1484.68, "total_tokens": 35457376} {"current_steps": 168015, "total_steps": 181800, "loss": 0.0517, "lr": 8.707155428607311e-07, "epoch": 18.483498349834985, "percentage": 92.42, "elapsed_time": "6:38:02", "remaining_time": "0:32:39", "throughput": 1484.68, "total_tokens": 35458336} {"current_steps": 168020, "total_steps": 181800, "loss": 0.0022, "lr": 8.700877520697898e-07, "epoch": 18.484048404840483, "percentage": 92.42, "elapsed_time": "6:38:03", "remaining_time": "0:32:38", "throughput": 1484.68, "total_tokens": 35459424} {"current_steps": 168025, "total_steps": 181800, "loss": 0.006, "lr": 8.694601836726657e-07, "epoch": 18.484598459845984, "percentage": 92.42, "elapsed_time": "6:38:04", "remaining_time": "0:32:38", "throughput": 1484.68, "total_tokens": 35460416} {"current_steps": 168030, "total_steps": 181800, "loss": 0.0221, "lr": 8.688328376751515e-07, "epoch": 18.485148514851485, "percentage": 92.43, "elapsed_time": "6:38:04", "remaining_time": "0:32:37", "throughput": 1484.68, "total_tokens": 35461440} {"current_steps": 168035, "total_steps": 181800, "loss": 0.001, "lr": 8.68205714083023e-07, "epoch": 18.485698569856986, "percentage": 92.43, "elapsed_time": "6:38:05", "remaining_time": "0:32:36", "throughput": 1484.67, "total_tokens": 35462400} {"current_steps": 168040, "total_steps": 181800, "loss": 0.0005, "lr": 8.675788129020645e-07, "epoch": 18.486248624862487, "percentage": 92.43, "elapsed_time": "6:38:06", "remaining_time": "0:32:35", "throughput": 1484.68, "total_tokens": 35463520} {"current_steps": 168045, "total_steps": 181800, "loss": 0.047, "lr": 8.669521341380549e-07, "epoch": 18.486798679867988, "percentage": 92.43, "elapsed_time": "6:38:07", "remaining_time": "0:32:35", "throughput": 1484.68, "total_tokens": 35464544} {"current_steps": 168050, "total_steps": 181800, "loss": 0.0014, "lr": 8.663256777967616e-07, "epoch": 18.48734873487349, "percentage": 92.44, "elapsed_time": "6:38:07", "remaining_time": "0:32:34", "throughput": 1484.68, "total_tokens": 35465568} {"current_steps": 168055, "total_steps": 181800, "loss": 0.0044, "lr": 8.656994438839688e-07, "epoch": 18.487898789878987, "percentage": 92.44, "elapsed_time": "6:38:08", "remaining_time": "0:32:33", "throughput": 1484.68, "total_tokens": 35466656} {"current_steps": 168060, "total_steps": 181800, "loss": 0.0018, "lr": 8.650734324054443e-07, "epoch": 18.488448844884488, "percentage": 92.44, "elapsed_time": "6:38:09", "remaining_time": "0:32:33", "throughput": 1484.68, "total_tokens": 35467680} {"current_steps": 168065, "total_steps": 181800, "loss": 0.0609, "lr": 8.64447643366953e-07, "epoch": 18.48899889988999, "percentage": 92.44, "elapsed_time": "6:38:09", "remaining_time": "0:32:32", "throughput": 1484.68, "total_tokens": 35468768} {"current_steps": 168070, "total_steps": 181800, "loss": 0.0119, "lr": 8.63822076774265e-07, "epoch": 18.48954895489549, "percentage": 92.45, "elapsed_time": "6:38:10", "remaining_time": "0:32:31", "throughput": 1484.68, "total_tokens": 35469760} {"current_steps": 168075, "total_steps": 181800, "loss": 0.0139, "lr": 8.631967326331508e-07, "epoch": 18.49009900990099, "percentage": 92.45, "elapsed_time": "6:38:11", "remaining_time": "0:32:30", "throughput": 1484.68, "total_tokens": 35470880} {"current_steps": 168080, "total_steps": 181800, "loss": 0.0122, "lr": 8.625716109493698e-07, "epoch": 18.490649064906492, "percentage": 92.45, "elapsed_time": "6:38:11", "remaining_time": "0:32:30", "throughput": 1484.69, "total_tokens": 35471968} {"current_steps": 168085, "total_steps": 181800, "loss": 0.0666, "lr": 8.619467117286867e-07, "epoch": 18.49119911991199, "percentage": 92.46, "elapsed_time": "6:38:12", "remaining_time": "0:32:29", "throughput": 1484.69, "total_tokens": 35473024} {"current_steps": 168090, "total_steps": 181800, "loss": 0.0043, "lr": 8.613220349768525e-07, "epoch": 18.49174917491749, "percentage": 92.46, "elapsed_time": "6:38:13", "remaining_time": "0:32:28", "throughput": 1484.69, "total_tokens": 35474080} {"current_steps": 168095, "total_steps": 181800, "loss": 0.0024, "lr": 8.60697580699632e-07, "epoch": 18.492299229922992, "percentage": 92.46, "elapsed_time": "6:38:13", "remaining_time": "0:32:28", "throughput": 1484.69, "total_tokens": 35475072} {"current_steps": 168100, "total_steps": 181800, "loss": 0.002, "lr": 8.600733489027791e-07, "epoch": 18.492849284928493, "percentage": 92.46, "elapsed_time": "6:38:14", "remaining_time": "0:32:27", "throughput": 1484.69, "total_tokens": 35476160} {"current_steps": 168105, "total_steps": 181800, "loss": 0.0796, "lr": 8.594493395920473e-07, "epoch": 18.493399339933994, "percentage": 92.47, "elapsed_time": "6:38:15", "remaining_time": "0:32:26", "throughput": 1484.69, "total_tokens": 35477152} {"current_steps": 168110, "total_steps": 181800, "loss": 0.0435, "lr": 8.588255527731903e-07, "epoch": 18.493949394939495, "percentage": 92.47, "elapsed_time": "6:38:16", "remaining_time": "0:32:25", "throughput": 1484.69, "total_tokens": 35478272} {"current_steps": 168115, "total_steps": 181800, "loss": 0.0014, "lr": 8.582019884519482e-07, "epoch": 18.494499449944996, "percentage": 92.47, "elapsed_time": "6:38:16", "remaining_time": "0:32:25", "throughput": 1484.69, "total_tokens": 35479296} {"current_steps": 168120, "total_steps": 181800, "loss": 0.0369, "lr": 8.575786466340802e-07, "epoch": 18.495049504950494, "percentage": 92.48, "elapsed_time": "6:38:17", "remaining_time": "0:32:24", "throughput": 1484.69, "total_tokens": 35480320} {"current_steps": 168125, "total_steps": 181800, "loss": 0.0414, "lr": 8.569555273253205e-07, "epoch": 18.495599559955995, "percentage": 92.48, "elapsed_time": "6:38:18", "remaining_time": "0:32:23", "throughput": 1484.7, "total_tokens": 35481408} {"current_steps": 168130, "total_steps": 181800, "loss": 0.0006, "lr": 8.563326305314146e-07, "epoch": 18.496149614961496, "percentage": 92.48, "elapsed_time": "6:38:18", "remaining_time": "0:32:23", "throughput": 1484.7, "total_tokens": 35482432} {"current_steps": 168135, "total_steps": 181800, "loss": 0.0154, "lr": 8.557099562581106e-07, "epoch": 18.496699669966997, "percentage": 92.48, "elapsed_time": "6:38:19", "remaining_time": "0:32:22", "throughput": 1484.7, "total_tokens": 35483520} {"current_steps": 168140, "total_steps": 181800, "loss": 0.0368, "lr": 8.550875045111401e-07, "epoch": 18.497249724972498, "percentage": 92.49, "elapsed_time": "6:38:20", "remaining_time": "0:32:21", "throughput": 1484.7, "total_tokens": 35484576} {"current_steps": 168145, "total_steps": 181800, "loss": 0.1383, "lr": 8.544652752962456e-07, "epoch": 18.497799779978, "percentage": 92.49, "elapsed_time": "6:38:20", "remaining_time": "0:32:20", "throughput": 1484.7, "total_tokens": 35485600} {"current_steps": 168150, "total_steps": 181800, "loss": 0.19, "lr": 8.538432686191533e-07, "epoch": 18.498349834983497, "percentage": 92.49, "elapsed_time": "6:38:21", "remaining_time": "0:32:20", "throughput": 1484.7, "total_tokens": 35486656} {"current_steps": 168155, "total_steps": 181800, "loss": 0.0345, "lr": 8.532214844856029e-07, "epoch": 18.498899889988998, "percentage": 92.49, "elapsed_time": "6:38:22", "remaining_time": "0:32:19", "throughput": 1484.7, "total_tokens": 35487712} {"current_steps": 168160, "total_steps": 181800, "loss": 0.0724, "lr": 8.52599922901326e-07, "epoch": 18.4994499449945, "percentage": 92.5, "elapsed_time": "6:38:22", "remaining_time": "0:32:18", "throughput": 1484.7, "total_tokens": 35488736} {"current_steps": 168165, "total_steps": 181800, "loss": 0.0209, "lr": 8.519785838720457e-07, "epoch": 18.5, "percentage": 92.5, "elapsed_time": "6:38:23", "remaining_time": "0:32:18", "throughput": 1484.7, "total_tokens": 35489792} {"current_steps": 168170, "total_steps": 181800, "loss": 0.0028, "lr": 8.513574674034936e-07, "epoch": 18.5005500550055, "percentage": 92.5, "elapsed_time": "6:38:24", "remaining_time": "0:32:17", "throughput": 1484.71, "total_tokens": 35490880} {"current_steps": 168175, "total_steps": 181800, "loss": 0.016, "lr": 8.507365735013928e-07, "epoch": 18.501100110011002, "percentage": 92.51, "elapsed_time": "6:38:25", "remaining_time": "0:32:16", "throughput": 1484.71, "total_tokens": 35492064} {"current_steps": 168180, "total_steps": 181800, "loss": 0.0031, "lr": 8.501159021714611e-07, "epoch": 18.501650165016503, "percentage": 92.51, "elapsed_time": "6:38:25", "remaining_time": "0:32:15", "throughput": 1484.71, "total_tokens": 35493056} {"current_steps": 168185, "total_steps": 181800, "loss": 0.0011, "lr": 8.494954534194216e-07, "epoch": 18.502200220022, "percentage": 92.51, "elapsed_time": "6:38:26", "remaining_time": "0:32:15", "throughput": 1484.71, "total_tokens": 35494112} {"current_steps": 168190, "total_steps": 181800, "loss": 0.0027, "lr": 8.488752272509975e-07, "epoch": 18.502750275027502, "percentage": 92.51, "elapsed_time": "6:38:27", "remaining_time": "0:32:14", "throughput": 1484.71, "total_tokens": 35495168} {"current_steps": 168195, "total_steps": 181800, "loss": 0.0029, "lr": 8.482552236719038e-07, "epoch": 18.503300330033003, "percentage": 92.52, "elapsed_time": "6:38:27", "remaining_time": "0:32:13", "throughput": 1484.71, "total_tokens": 35496224} {"current_steps": 168200, "total_steps": 181800, "loss": 0.0653, "lr": 8.476354426878497e-07, "epoch": 18.503850385038504, "percentage": 92.52, "elapsed_time": "6:38:28", "remaining_time": "0:32:13", "throughput": 1484.72, "total_tokens": 35497280} {"current_steps": 168205, "total_steps": 181800, "loss": 0.0989, "lr": 8.470158843045501e-07, "epoch": 18.504400440044005, "percentage": 92.52, "elapsed_time": "6:38:29", "remaining_time": "0:32:12", "throughput": 1484.72, "total_tokens": 35498368} {"current_steps": 168210, "total_steps": 181800, "loss": 0.0904, "lr": 8.463965485277143e-07, "epoch": 18.504950495049506, "percentage": 92.52, "elapsed_time": "6:38:29", "remaining_time": "0:32:11", "throughput": 1484.72, "total_tokens": 35499456} {"current_steps": 168215, "total_steps": 181800, "loss": 0.0037, "lr": 8.457774353630516e-07, "epoch": 18.505500550055004, "percentage": 92.53, "elapsed_time": "6:38:30", "remaining_time": "0:32:11", "throughput": 1484.72, "total_tokens": 35500512} {"current_steps": 168220, "total_steps": 181800, "loss": 0.0011, "lr": 8.451585448162713e-07, "epoch": 18.506050605060505, "percentage": 92.53, "elapsed_time": "6:38:31", "remaining_time": "0:32:10", "throughput": 1484.72, "total_tokens": 35501536} {"current_steps": 168225, "total_steps": 181800, "loss": 0.0022, "lr": 8.445398768930745e-07, "epoch": 18.506600660066006, "percentage": 92.53, "elapsed_time": "6:38:31", "remaining_time": "0:32:09", "throughput": 1484.72, "total_tokens": 35502560} {"current_steps": 168230, "total_steps": 181800, "loss": 0.0022, "lr": 8.439214315991595e-07, "epoch": 18.507150715071507, "percentage": 92.54, "elapsed_time": "6:38:32", "remaining_time": "0:32:08", "throughput": 1484.72, "total_tokens": 35503552} {"current_steps": 168235, "total_steps": 181800, "loss": 0.049, "lr": 8.433032089402326e-07, "epoch": 18.507700770077008, "percentage": 92.54, "elapsed_time": "6:38:33", "remaining_time": "0:32:08", "throughput": 1484.72, "total_tokens": 35504576} {"current_steps": 168240, "total_steps": 181800, "loss": 0.0031, "lr": 8.426852089219838e-07, "epoch": 18.50825082508251, "percentage": 92.54, "elapsed_time": "6:38:33", "remaining_time": "0:32:07", "throughput": 1484.72, "total_tokens": 35505632} {"current_steps": 168245, "total_steps": 181800, "loss": 0.1122, "lr": 8.420674315501142e-07, "epoch": 18.50880088008801, "percentage": 92.54, "elapsed_time": "6:38:34", "remaining_time": "0:32:06", "throughput": 1484.72, "total_tokens": 35506656} {"current_steps": 168250, "total_steps": 181800, "loss": 0.0033, "lr": 8.414498768303219e-07, "epoch": 18.509350935093508, "percentage": 92.55, "elapsed_time": "6:38:35", "remaining_time": "0:32:06", "throughput": 1484.72, "total_tokens": 35507680} {"current_steps": 168255, "total_steps": 181800, "loss": 0.0696, "lr": 8.408325447682886e-07, "epoch": 18.50990099009901, "percentage": 92.55, "elapsed_time": "6:38:36", "remaining_time": "0:32:05", "throughput": 1484.73, "total_tokens": 35508800} {"current_steps": 168260, "total_steps": 181800, "loss": 0.0022, "lr": 8.402154353697123e-07, "epoch": 18.51045104510451, "percentage": 92.55, "elapsed_time": "6:38:36", "remaining_time": "0:32:04", "throughput": 1484.72, "total_tokens": 35509760} {"current_steps": 168265, "total_steps": 181800, "loss": 0.0237, "lr": 8.395985486402774e-07, "epoch": 18.51100110011001, "percentage": 92.56, "elapsed_time": "6:38:37", "remaining_time": "0:32:03", "throughput": 1484.73, "total_tokens": 35510848} {"current_steps": 168270, "total_steps": 181800, "loss": 0.0723, "lr": 8.389818845856656e-07, "epoch": 18.511551155115512, "percentage": 92.56, "elapsed_time": "6:38:38", "remaining_time": "0:32:03", "throughput": 1484.73, "total_tokens": 35512032} {"current_steps": 168275, "total_steps": 181800, "loss": 0.0006, "lr": 8.383654432115696e-07, "epoch": 18.512101210121013, "percentage": 92.56, "elapsed_time": "6:38:38", "remaining_time": "0:32:02", "throughput": 1484.74, "total_tokens": 35513120} {"current_steps": 168280, "total_steps": 181800, "loss": 0.0016, "lr": 8.377492245236596e-07, "epoch": 18.51265126512651, "percentage": 92.56, "elapsed_time": "6:38:39", "remaining_time": "0:32:01", "throughput": 1484.73, "total_tokens": 35514112} {"current_steps": 168285, "total_steps": 181800, "loss": 0.0515, "lr": 8.371332285276257e-07, "epoch": 18.513201320132012, "percentage": 92.57, "elapsed_time": "6:38:40", "remaining_time": "0:32:01", "throughput": 1484.73, "total_tokens": 35515136} {"current_steps": 168290, "total_steps": 181800, "loss": 0.0057, "lr": 8.365174552291382e-07, "epoch": 18.513751375137513, "percentage": 92.57, "elapsed_time": "6:38:40", "remaining_time": "0:32:00", "throughput": 1484.74, "total_tokens": 35516192} {"current_steps": 168295, "total_steps": 181800, "loss": 0.0654, "lr": 8.359019046338762e-07, "epoch": 18.514301430143014, "percentage": 92.57, "elapsed_time": "6:38:41", "remaining_time": "0:31:59", "throughput": 1484.74, "total_tokens": 35517216} {"current_steps": 168300, "total_steps": 181800, "loss": 0.0036, "lr": 8.352865767475071e-07, "epoch": 18.514851485148515, "percentage": 92.57, "elapsed_time": "6:38:42", "remaining_time": "0:31:58", "throughput": 1484.74, "total_tokens": 35518304} {"current_steps": 168305, "total_steps": 181800, "loss": 0.0025, "lr": 8.346714715757098e-07, "epoch": 18.515401540154016, "percentage": 92.58, "elapsed_time": "6:38:42", "remaining_time": "0:31:58", "throughput": 1484.74, "total_tokens": 35519360} {"current_steps": 168310, "total_steps": 181800, "loss": 0.0025, "lr": 8.340565891241491e-07, "epoch": 18.515951595159517, "percentage": 92.58, "elapsed_time": "6:38:43", "remaining_time": "0:31:57", "throughput": 1484.74, "total_tokens": 35520416} {"current_steps": 168315, "total_steps": 181800, "loss": 0.0019, "lr": 8.334419293984957e-07, "epoch": 18.516501650165015, "percentage": 92.58, "elapsed_time": "6:38:44", "remaining_time": "0:31:56", "throughput": 1484.74, "total_tokens": 35521472} {"current_steps": 168320, "total_steps": 181800, "loss": 0.0021, "lr": 8.328274924044089e-07, "epoch": 18.517051705170516, "percentage": 92.59, "elapsed_time": "6:38:45", "remaining_time": "0:31:56", "throughput": 1484.74, "total_tokens": 35522560} {"current_steps": 168325, "total_steps": 181800, "loss": 0.0746, "lr": 8.322132781475534e-07, "epoch": 18.517601760176017, "percentage": 92.59, "elapsed_time": "6:38:45", "remaining_time": "0:31:55", "throughput": 1484.74, "total_tokens": 35523584} {"current_steps": 168330, "total_steps": 181800, "loss": 0.1865, "lr": 8.315992866335914e-07, "epoch": 18.51815181518152, "percentage": 92.59, "elapsed_time": "6:38:46", "remaining_time": "0:31:54", "throughput": 1484.74, "total_tokens": 35524608} {"current_steps": 168335, "total_steps": 181800, "loss": 0.0012, "lr": 8.309855178681825e-07, "epoch": 18.51870187018702, "percentage": 92.59, "elapsed_time": "6:38:47", "remaining_time": "0:31:53", "throughput": 1484.75, "total_tokens": 35525696} {"current_steps": 168340, "total_steps": 181800, "loss": 0.0025, "lr": 8.303719718569858e-07, "epoch": 18.51925192519252, "percentage": 92.6, "elapsed_time": "6:38:47", "remaining_time": "0:31:53", "throughput": 1484.75, "total_tokens": 35526752} {"current_steps": 168345, "total_steps": 181800, "loss": 0.0831, "lr": 8.297586486056496e-07, "epoch": 18.519801980198018, "percentage": 92.6, "elapsed_time": "6:38:48", "remaining_time": "0:31:52", "throughput": 1484.75, "total_tokens": 35527776} {"current_steps": 168350, "total_steps": 181800, "loss": 0.068, "lr": 8.291455481198307e-07, "epoch": 18.52035203520352, "percentage": 92.6, "elapsed_time": "6:38:49", "remaining_time": "0:31:51", "throughput": 1484.75, "total_tokens": 35528864} {"current_steps": 168355, "total_steps": 181800, "loss": 0.0025, "lr": 8.285326704051772e-07, "epoch": 18.52090209020902, "percentage": 92.6, "elapsed_time": "6:38:49", "remaining_time": "0:31:51", "throughput": 1484.75, "total_tokens": 35529856} {"current_steps": 168360, "total_steps": 181800, "loss": 0.0159, "lr": 8.2792001546734e-07, "epoch": 18.52145214521452, "percentage": 92.61, "elapsed_time": "6:38:50", "remaining_time": "0:31:50", "throughput": 1484.75, "total_tokens": 35530944} {"current_steps": 168365, "total_steps": 181800, "loss": 0.0049, "lr": 8.273075833119675e-07, "epoch": 18.522002200220022, "percentage": 92.61, "elapsed_time": "6:38:51", "remaining_time": "0:31:49", "throughput": 1484.76, "total_tokens": 35532064} {"current_steps": 168370, "total_steps": 181800, "loss": 0.0008, "lr": 8.266953739446998e-07, "epoch": 18.522552255225524, "percentage": 92.61, "elapsed_time": "6:38:51", "remaining_time": "0:31:48", "throughput": 1484.76, "total_tokens": 35533120} {"current_steps": 168375, "total_steps": 181800, "loss": 0.0153, "lr": 8.260833873711849e-07, "epoch": 18.523102310231025, "percentage": 92.62, "elapsed_time": "6:38:52", "remaining_time": "0:31:48", "throughput": 1484.76, "total_tokens": 35534144} {"current_steps": 168380, "total_steps": 181800, "loss": 0.0053, "lr": 8.254716235970544e-07, "epoch": 18.523652365236522, "percentage": 92.62, "elapsed_time": "6:38:53", "remaining_time": "0:31:47", "throughput": 1484.76, "total_tokens": 35535168} {"current_steps": 168385, "total_steps": 181800, "loss": 0.0219, "lr": 8.24860082627954e-07, "epoch": 18.524202420242023, "percentage": 92.62, "elapsed_time": "6:38:53", "remaining_time": "0:31:46", "throughput": 1484.76, "total_tokens": 35536224} {"current_steps": 168390, "total_steps": 181800, "loss": 0.0025, "lr": 8.242487644695179e-07, "epoch": 18.524752475247524, "percentage": 92.62, "elapsed_time": "6:38:54", "remaining_time": "0:31:46", "throughput": 1484.76, "total_tokens": 35537312} {"current_steps": 168395, "total_steps": 181800, "loss": 0.1002, "lr": 8.236376691273806e-07, "epoch": 18.525302530253025, "percentage": 92.63, "elapsed_time": "6:38:55", "remaining_time": "0:31:45", "throughput": 1484.76, "total_tokens": 35538368} {"current_steps": 168400, "total_steps": 181800, "loss": 0.0122, "lr": 8.230267966071737e-07, "epoch": 18.525852585258527, "percentage": 92.63, "elapsed_time": "6:38:56", "remaining_time": "0:31:44", "throughput": 1484.77, "total_tokens": 35539456} {"current_steps": 168405, "total_steps": 181800, "loss": 0.1159, "lr": 8.224161469145286e-07, "epoch": 18.526402640264028, "percentage": 92.63, "elapsed_time": "6:38:56", "remaining_time": "0:31:43", "throughput": 1484.77, "total_tokens": 35540480} {"current_steps": 168410, "total_steps": 181800, "loss": 0.0331, "lr": 8.218057200550717e-07, "epoch": 18.52695269526953, "percentage": 92.63, "elapsed_time": "6:38:57", "remaining_time": "0:31:43", "throughput": 1484.77, "total_tokens": 35541568} {"current_steps": 168415, "total_steps": 181800, "loss": 0.0049, "lr": 8.211955160344287e-07, "epoch": 18.527502750275026, "percentage": 92.64, "elapsed_time": "6:38:58", "remaining_time": "0:31:42", "throughput": 1484.77, "total_tokens": 35542656} {"current_steps": 168420, "total_steps": 181800, "loss": 0.0262, "lr": 8.205855348582231e-07, "epoch": 18.528052805280527, "percentage": 92.64, "elapsed_time": "6:38:58", "remaining_time": "0:31:41", "throughput": 1484.77, "total_tokens": 35543680} {"current_steps": 168425, "total_steps": 181800, "loss": 0.0034, "lr": 8.199757765320836e-07, "epoch": 18.52860286028603, "percentage": 92.64, "elapsed_time": "6:38:59", "remaining_time": "0:31:41", "throughput": 1484.78, "total_tokens": 35544800} {"current_steps": 168430, "total_steps": 181800, "loss": 0.0011, "lr": 8.193662410616198e-07, "epoch": 18.52915291529153, "percentage": 92.65, "elapsed_time": "6:39:00", "remaining_time": "0:31:40", "throughput": 1484.78, "total_tokens": 35545888} {"current_steps": 168435, "total_steps": 181800, "loss": 0.0615, "lr": 8.187569284524576e-07, "epoch": 18.52970297029703, "percentage": 92.65, "elapsed_time": "6:39:00", "remaining_time": "0:31:39", "throughput": 1484.78, "total_tokens": 35546912} {"current_steps": 168440, "total_steps": 181800, "loss": 0.0235, "lr": 8.181478387102065e-07, "epoch": 18.53025302530253, "percentage": 92.65, "elapsed_time": "6:39:01", "remaining_time": "0:31:38", "throughput": 1484.78, "total_tokens": 35547968} {"current_steps": 168445, "total_steps": 181800, "loss": 0.0907, "lr": 8.175389718404814e-07, "epoch": 18.53080308030803, "percentage": 92.65, "elapsed_time": "6:39:02", "remaining_time": "0:31:38", "throughput": 1484.78, "total_tokens": 35549056} {"current_steps": 168450, "total_steps": 181800, "loss": 0.0026, "lr": 8.169303278489026e-07, "epoch": 18.53135313531353, "percentage": 92.66, "elapsed_time": "6:39:02", "remaining_time": "0:31:37", "throughput": 1484.78, "total_tokens": 35550144} {"current_steps": 168455, "total_steps": 181800, "loss": 0.0162, "lr": 8.16321906741066e-07, "epoch": 18.53190319031903, "percentage": 92.66, "elapsed_time": "6:39:03", "remaining_time": "0:31:36", "throughput": 1484.79, "total_tokens": 35551232} {"current_steps": 168460, "total_steps": 181800, "loss": 0.0259, "lr": 8.157137085225918e-07, "epoch": 18.532453245324533, "percentage": 92.66, "elapsed_time": "6:39:04", "remaining_time": "0:31:36", "throughput": 1484.79, "total_tokens": 35552320} {"current_steps": 168465, "total_steps": 181800, "loss": 0.0044, "lr": 8.151057331990786e-07, "epoch": 18.533003300330034, "percentage": 92.67, "elapsed_time": "6:39:05", "remaining_time": "0:31:35", "throughput": 1484.79, "total_tokens": 35553344} {"current_steps": 168470, "total_steps": 181800, "loss": 0.0415, "lr": 8.144979807761272e-07, "epoch": 18.533553355335535, "percentage": 92.67, "elapsed_time": "6:39:05", "remaining_time": "0:31:34", "throughput": 1484.79, "total_tokens": 35554336} {"current_steps": 168475, "total_steps": 181800, "loss": 0.0359, "lr": 8.138904512593443e-07, "epoch": 18.534103410341036, "percentage": 92.67, "elapsed_time": "6:39:06", "remaining_time": "0:31:33", "throughput": 1484.79, "total_tokens": 35555328} {"current_steps": 168480, "total_steps": 181800, "loss": 0.0037, "lr": 8.132831446543254e-07, "epoch": 18.534653465346533, "percentage": 92.67, "elapsed_time": "6:39:07", "remaining_time": "0:31:33", "throughput": 1484.78, "total_tokens": 35556320} {"current_steps": 168485, "total_steps": 181800, "loss": 0.0614, "lr": 8.126760609666745e-07, "epoch": 18.535203520352034, "percentage": 92.68, "elapsed_time": "6:39:07", "remaining_time": "0:31:32", "throughput": 1484.79, "total_tokens": 35557376} {"current_steps": 168490, "total_steps": 181800, "loss": 0.1441, "lr": 8.120692002019814e-07, "epoch": 18.535753575357536, "percentage": 92.68, "elapsed_time": "6:39:08", "remaining_time": "0:31:31", "throughput": 1484.79, "total_tokens": 35558400} {"current_steps": 168495, "total_steps": 181800, "loss": 0.0029, "lr": 8.114625623658362e-07, "epoch": 18.536303630363037, "percentage": 92.68, "elapsed_time": "6:39:09", "remaining_time": "0:31:31", "throughput": 1484.79, "total_tokens": 35559424} {"current_steps": 168500, "total_steps": 181800, "loss": 0.1114, "lr": 8.108561474638343e-07, "epoch": 18.536853685368538, "percentage": 92.68, "elapsed_time": "6:39:09", "remaining_time": "0:31:30", "throughput": 1484.79, "total_tokens": 35560512} {"current_steps": 168505, "total_steps": 181800, "loss": 0.1148, "lr": 8.10249955501563e-07, "epoch": 18.53740374037404, "percentage": 92.69, "elapsed_time": "6:39:10", "remaining_time": "0:31:29", "throughput": 1484.79, "total_tokens": 35561568} {"current_steps": 168510, "total_steps": 181800, "loss": 0.0218, "lr": 8.09643986484615e-07, "epoch": 18.537953795379536, "percentage": 92.69, "elapsed_time": "6:39:11", "remaining_time": "0:31:28", "throughput": 1484.79, "total_tokens": 35562656} {"current_steps": 168515, "total_steps": 181800, "loss": 0.0159, "lr": 8.09038240418572e-07, "epoch": 18.538503850385037, "percentage": 92.69, "elapsed_time": "6:39:11", "remaining_time": "0:31:28", "throughput": 1484.79, "total_tokens": 35563712} {"current_steps": 168520, "total_steps": 181800, "loss": 0.0131, "lr": 8.084327173090101e-07, "epoch": 18.53905390539054, "percentage": 92.7, "elapsed_time": "6:39:12", "remaining_time": "0:31:27", "throughput": 1484.79, "total_tokens": 35564704} {"current_steps": 168525, "total_steps": 181800, "loss": 0.0028, "lr": 8.078274171615191e-07, "epoch": 18.53960396039604, "percentage": 92.7, "elapsed_time": "6:39:13", "remaining_time": "0:31:26", "throughput": 1484.79, "total_tokens": 35565728} {"current_steps": 168530, "total_steps": 181800, "loss": 0.0149, "lr": 8.072223399816726e-07, "epoch": 18.54015401540154, "percentage": 92.7, "elapsed_time": "6:39:14", "remaining_time": "0:31:26", "throughput": 1484.79, "total_tokens": 35566784} {"current_steps": 168535, "total_steps": 181800, "loss": 0.0632, "lr": 8.066174857750492e-07, "epoch": 18.540704070407042, "percentage": 92.7, "elapsed_time": "6:39:14", "remaining_time": "0:31:25", "throughput": 1484.79, "total_tokens": 35567808} {"current_steps": 168540, "total_steps": 181800, "loss": 0.0759, "lr": 8.06012854547225e-07, "epoch": 18.541254125412543, "percentage": 92.71, "elapsed_time": "6:39:15", "remaining_time": "0:31:24", "throughput": 1484.79, "total_tokens": 35568832} {"current_steps": 168545, "total_steps": 181800, "loss": 0.1508, "lr": 8.054084463037681e-07, "epoch": 18.54180418041804, "percentage": 92.71, "elapsed_time": "6:39:16", "remaining_time": "0:31:23", "throughput": 1484.79, "total_tokens": 35569888} {"current_steps": 168550, "total_steps": 181800, "loss": 0.0223, "lr": 8.048042610502543e-07, "epoch": 18.54235423542354, "percentage": 92.71, "elapsed_time": "6:39:16", "remaining_time": "0:31:23", "throughput": 1484.79, "total_tokens": 35570944} {"current_steps": 168555, "total_steps": 181800, "loss": 0.053, "lr": 8.042002987922515e-07, "epoch": 18.542904290429043, "percentage": 92.71, "elapsed_time": "6:39:17", "remaining_time": "0:31:22", "throughput": 1484.8, "total_tokens": 35572000} {"current_steps": 168560, "total_steps": 181800, "loss": 0.0195, "lr": 8.035965595353162e-07, "epoch": 18.543454345434544, "percentage": 92.72, "elapsed_time": "6:39:18", "remaining_time": "0:31:21", "throughput": 1484.8, "total_tokens": 35573120} {"current_steps": 168565, "total_steps": 181800, "loss": 0.0024, "lr": 8.029930432850275e-07, "epoch": 18.544004400440045, "percentage": 92.72, "elapsed_time": "6:39:18", "remaining_time": "0:31:21", "throughput": 1484.8, "total_tokens": 35574176} {"current_steps": 168570, "total_steps": 181800, "loss": 0.002, "lr": 8.023897500469391e-07, "epoch": 18.544554455445546, "percentage": 92.72, "elapsed_time": "6:39:19", "remaining_time": "0:31:20", "throughput": 1484.8, "total_tokens": 35575232} {"current_steps": 168575, "total_steps": 181800, "loss": 0.0018, "lr": 8.01786679826616e-07, "epoch": 18.545104510451043, "percentage": 92.73, "elapsed_time": "6:39:20", "remaining_time": "0:31:19", "throughput": 1484.8, "total_tokens": 35576288} {"current_steps": 168580, "total_steps": 181800, "loss": 0.0118, "lr": 8.011838326296123e-07, "epoch": 18.545654565456545, "percentage": 92.73, "elapsed_time": "6:39:20", "remaining_time": "0:31:19", "throughput": 1484.8, "total_tokens": 35577312} {"current_steps": 168585, "total_steps": 181800, "loss": 0.001, "lr": 8.005812084614844e-07, "epoch": 18.546204620462046, "percentage": 92.73, "elapsed_time": "6:39:21", "remaining_time": "0:31:18", "throughput": 1484.8, "total_tokens": 35578336} {"current_steps": 168590, "total_steps": 181800, "loss": 0.0082, "lr": 7.999788073277865e-07, "epoch": 18.546754675467547, "percentage": 92.73, "elapsed_time": "6:39:22", "remaining_time": "0:31:17", "throughput": 1484.8, "total_tokens": 35579360} {"current_steps": 168595, "total_steps": 181800, "loss": 0.0342, "lr": 7.993766292340721e-07, "epoch": 18.547304730473048, "percentage": 92.74, "elapsed_time": "6:39:23", "remaining_time": "0:31:16", "throughput": 1484.81, "total_tokens": 35580448} {"current_steps": 168600, "total_steps": 181800, "loss": 0.0072, "lr": 7.987746741858926e-07, "epoch": 18.54785478547855, "percentage": 92.74, "elapsed_time": "6:39:23", "remaining_time": "0:31:16", "throughput": 1484.81, "total_tokens": 35581472} {"current_steps": 168605, "total_steps": 181800, "loss": 0.0806, "lr": 7.981729421887934e-07, "epoch": 18.54840484048405, "percentage": 92.74, "elapsed_time": "6:39:24", "remaining_time": "0:31:15", "throughput": 1484.81, "total_tokens": 35582592} {"current_steps": 168610, "total_steps": 181800, "loss": 0.0312, "lr": 7.975714332483203e-07, "epoch": 18.548954895489548, "percentage": 92.74, "elapsed_time": "6:39:25", "remaining_time": "0:31:14", "throughput": 1484.81, "total_tokens": 35583712} {"current_steps": 168615, "total_steps": 181800, "loss": 0.0016, "lr": 7.969701473700186e-07, "epoch": 18.54950495049505, "percentage": 92.75, "elapsed_time": "6:39:25", "remaining_time": "0:31:14", "throughput": 1484.82, "total_tokens": 35584800} {"current_steps": 168620, "total_steps": 181800, "loss": 0.0307, "lr": 7.963690845594258e-07, "epoch": 18.55005500550055, "percentage": 92.75, "elapsed_time": "6:39:26", "remaining_time": "0:31:13", "throughput": 1484.82, "total_tokens": 35585824} {"current_steps": 168625, "total_steps": 181800, "loss": 0.0018, "lr": 7.957682448220899e-07, "epoch": 18.55060506050605, "percentage": 92.75, "elapsed_time": "6:39:27", "remaining_time": "0:31:12", "throughput": 1484.82, "total_tokens": 35586944} {"current_steps": 168630, "total_steps": 181800, "loss": 0.0372, "lr": 7.951676281635428e-07, "epoch": 18.551155115511552, "percentage": 92.76, "elapsed_time": "6:39:27", "remaining_time": "0:31:11", "throughput": 1484.82, "total_tokens": 35587968} {"current_steps": 168635, "total_steps": 181800, "loss": 0.0047, "lr": 7.945672345893191e-07, "epoch": 18.551705170517053, "percentage": 92.76, "elapsed_time": "6:39:28", "remaining_time": "0:31:11", "throughput": 1484.82, "total_tokens": 35589024} {"current_steps": 168640, "total_steps": 181800, "loss": 0.0049, "lr": 7.939670641049585e-07, "epoch": 18.55225522552255, "percentage": 92.76, "elapsed_time": "6:39:29", "remaining_time": "0:31:10", "throughput": 1484.82, "total_tokens": 35590080} {"current_steps": 168645, "total_steps": 181800, "loss": 0.0114, "lr": 7.933671167159817e-07, "epoch": 18.55280528052805, "percentage": 92.76, "elapsed_time": "6:39:29", "remaining_time": "0:31:09", "throughput": 1484.82, "total_tokens": 35591104} {"current_steps": 168650, "total_steps": 181800, "loss": 0.0134, "lr": 7.927673924279288e-07, "epoch": 18.553355335533553, "percentage": 92.77, "elapsed_time": "6:39:30", "remaining_time": "0:31:09", "throughput": 1484.82, "total_tokens": 35592160} {"current_steps": 168655, "total_steps": 181800, "loss": 0.003, "lr": 7.921678912463232e-07, "epoch": 18.553905390539054, "percentage": 92.77, "elapsed_time": "6:39:31", "remaining_time": "0:31:08", "throughput": 1484.82, "total_tokens": 35593184} {"current_steps": 168660, "total_steps": 181800, "loss": 0.0023, "lr": 7.91568613176688e-07, "epoch": 18.554455445544555, "percentage": 92.77, "elapsed_time": "6:39:31", "remaining_time": "0:31:07", "throughput": 1484.82, "total_tokens": 35594208} {"current_steps": 168665, "total_steps": 181800, "loss": 0.0766, "lr": 7.909695582245524e-07, "epoch": 18.555005500550056, "percentage": 92.78, "elapsed_time": "6:39:32", "remaining_time": "0:31:06", "throughput": 1484.83, "total_tokens": 35595328} {"current_steps": 168670, "total_steps": 181800, "loss": 0.002, "lr": 7.903707263954285e-07, "epoch": 18.555555555555557, "percentage": 92.78, "elapsed_time": "6:39:33", "remaining_time": "0:31:06", "throughput": 1484.83, "total_tokens": 35596416} {"current_steps": 168675, "total_steps": 181800, "loss": 0.0019, "lr": 7.897721176948453e-07, "epoch": 18.556105610561055, "percentage": 92.78, "elapsed_time": "6:39:34", "remaining_time": "0:31:05", "throughput": 1484.83, "total_tokens": 35597536} {"current_steps": 168680, "total_steps": 181800, "loss": 0.0015, "lr": 7.891737321283149e-07, "epoch": 18.556655665566556, "percentage": 92.78, "elapsed_time": "6:39:34", "remaining_time": "0:31:04", "throughput": 1484.84, "total_tokens": 35598624} {"current_steps": 168685, "total_steps": 181800, "loss": 0.0012, "lr": 7.885755697013497e-07, "epoch": 18.557205720572057, "percentage": 92.79, "elapsed_time": "6:39:35", "remaining_time": "0:31:04", "throughput": 1484.84, "total_tokens": 35599616} {"current_steps": 168690, "total_steps": 181800, "loss": 0.0046, "lr": 7.879776304194675e-07, "epoch": 18.557755775577558, "percentage": 92.79, "elapsed_time": "6:39:36", "remaining_time": "0:31:03", "throughput": 1484.84, "total_tokens": 35600640} {"current_steps": 168695, "total_steps": 181800, "loss": 0.0011, "lr": 7.873799142881777e-07, "epoch": 18.55830583058306, "percentage": 92.79, "elapsed_time": "6:39:36", "remaining_time": "0:31:02", "throughput": 1484.84, "total_tokens": 35601696} {"current_steps": 168700, "total_steps": 181800, "loss": 0.0161, "lr": 7.867824213129899e-07, "epoch": 18.55885588558856, "percentage": 92.79, "elapsed_time": "6:39:37", "remaining_time": "0:31:01", "throughput": 1484.84, "total_tokens": 35602752} {"current_steps": 168705, "total_steps": 181800, "loss": 0.0155, "lr": 7.861851514994051e-07, "epoch": 18.55940594059406, "percentage": 92.8, "elapsed_time": "6:39:38", "remaining_time": "0:31:01", "throughput": 1484.84, "total_tokens": 35603776} {"current_steps": 168710, "total_steps": 181800, "loss": 0.0623, "lr": 7.855881048529357e-07, "epoch": 18.55995599559956, "percentage": 92.8, "elapsed_time": "6:39:38", "remaining_time": "0:31:00", "throughput": 1484.84, "total_tokens": 35604864} {"current_steps": 168715, "total_steps": 181800, "loss": 0.002, "lr": 7.849912813790855e-07, "epoch": 18.56050605060506, "percentage": 92.8, "elapsed_time": "6:39:39", "remaining_time": "0:30:59", "throughput": 1484.84, "total_tokens": 35605920} {"current_steps": 168720, "total_steps": 181800, "loss": 0.0022, "lr": 7.843946810833474e-07, "epoch": 18.56105610561056, "percentage": 92.81, "elapsed_time": "6:39:40", "remaining_time": "0:30:59", "throughput": 1484.84, "total_tokens": 35606976} {"current_steps": 168725, "total_steps": 181800, "loss": 0.0047, "lr": 7.837983039712227e-07, "epoch": 18.561606160616062, "percentage": 92.81, "elapsed_time": "6:39:40", "remaining_time": "0:30:58", "throughput": 1484.84, "total_tokens": 35608032} {"current_steps": 168730, "total_steps": 181800, "loss": 0.0707, "lr": 7.832021500482123e-07, "epoch": 18.562156215621563, "percentage": 92.81, "elapsed_time": "6:39:41", "remaining_time": "0:30:57", "throughput": 1484.84, "total_tokens": 35609088} {"current_steps": 168735, "total_steps": 181800, "loss": 0.0243, "lr": 7.826062193198036e-07, "epoch": 18.562706270627064, "percentage": 92.81, "elapsed_time": "6:39:42", "remaining_time": "0:30:56", "throughput": 1484.85, "total_tokens": 35610176} {"current_steps": 168740, "total_steps": 181800, "loss": 0.0854, "lr": 7.82010511791495e-07, "epoch": 18.563256325632562, "percentage": 92.82, "elapsed_time": "6:39:43", "remaining_time": "0:30:56", "throughput": 1484.85, "total_tokens": 35611264} {"current_steps": 168745, "total_steps": 181800, "loss": 0.0024, "lr": 7.814150274687737e-07, "epoch": 18.563806380638063, "percentage": 92.82, "elapsed_time": "6:39:43", "remaining_time": "0:30:55", "throughput": 1484.85, "total_tokens": 35612320} {"current_steps": 168750, "total_steps": 181800, "loss": 0.0036, "lr": 7.808197663571299e-07, "epoch": 18.564356435643564, "percentage": 92.82, "elapsed_time": "6:39:44", "remaining_time": "0:30:54", "throughput": 1484.85, "total_tokens": 35613408} {"current_steps": 168755, "total_steps": 181800, "loss": 0.0488, "lr": 7.802247284620479e-07, "epoch": 18.564906490649065, "percentage": 92.82, "elapsed_time": "6:39:45", "remaining_time": "0:30:54", "throughput": 1484.86, "total_tokens": 35614496} {"current_steps": 168760, "total_steps": 181800, "loss": 0.0335, "lr": 7.796299137890123e-07, "epoch": 18.565456545654566, "percentage": 92.83, "elapsed_time": "6:39:45", "remaining_time": "0:30:53", "throughput": 1484.86, "total_tokens": 35615552} {"current_steps": 168765, "total_steps": 181800, "loss": 0.0041, "lr": 7.790353223435076e-07, "epoch": 18.566006600660067, "percentage": 92.83, "elapsed_time": "6:39:46", "remaining_time": "0:30:52", "throughput": 1484.86, "total_tokens": 35616608} {"current_steps": 168770, "total_steps": 181800, "loss": 0.0743, "lr": 7.7844095413101e-07, "epoch": 18.566556655665565, "percentage": 92.83, "elapsed_time": "6:39:47", "remaining_time": "0:30:51", "throughput": 1484.86, "total_tokens": 35617664} {"current_steps": 168775, "total_steps": 181800, "loss": 0.0983, "lr": 7.778468091570012e-07, "epoch": 18.567106710671066, "percentage": 92.84, "elapsed_time": "6:39:47", "remaining_time": "0:30:51", "throughput": 1484.86, "total_tokens": 35618656} {"current_steps": 168780, "total_steps": 181800, "loss": 0.004, "lr": 7.772528874269547e-07, "epoch": 18.567656765676567, "percentage": 92.84, "elapsed_time": "6:39:48", "remaining_time": "0:30:50", "throughput": 1484.86, "total_tokens": 35619744} {"current_steps": 168785, "total_steps": 181800, "loss": 0.0591, "lr": 7.766591889463437e-07, "epoch": 18.568206820682068, "percentage": 92.84, "elapsed_time": "6:39:49", "remaining_time": "0:30:49", "throughput": 1484.86, "total_tokens": 35620800} {"current_steps": 168790, "total_steps": 181800, "loss": 0.0024, "lr": 7.760657137206445e-07, "epoch": 18.56875687568757, "percentage": 92.84, "elapsed_time": "6:39:49", "remaining_time": "0:30:49", "throughput": 1484.86, "total_tokens": 35621856} {"current_steps": 168795, "total_steps": 181800, "loss": 0.0039, "lr": 7.754724617553221e-07, "epoch": 18.56930693069307, "percentage": 92.85, "elapsed_time": "6:39:50", "remaining_time": "0:30:48", "throughput": 1484.87, "total_tokens": 35622912} {"current_steps": 168800, "total_steps": 181800, "loss": 0.0016, "lr": 7.748794330558446e-07, "epoch": 18.56985698569857, "percentage": 92.85, "elapsed_time": "6:39:51", "remaining_time": "0:30:47", "throughput": 1484.87, "total_tokens": 35624000} {"current_steps": 168805, "total_steps": 181800, "loss": 0.0012, "lr": 7.742866276276823e-07, "epoch": 18.57040704070407, "percentage": 92.85, "elapsed_time": "6:39:52", "remaining_time": "0:30:46", "throughput": 1484.87, "total_tokens": 35625024} {"current_steps": 168810, "total_steps": 181800, "loss": 0.0008, "lr": 7.73694045476292e-07, "epoch": 18.57095709570957, "percentage": 92.85, "elapsed_time": "6:39:52", "remaining_time": "0:30:46", "throughput": 1484.87, "total_tokens": 35626112} {"current_steps": 168815, "total_steps": 181800, "loss": 0.0451, "lr": 7.731016866071417e-07, "epoch": 18.57150715071507, "percentage": 92.86, "elapsed_time": "6:39:53", "remaining_time": "0:30:45", "throughput": 1484.87, "total_tokens": 35627200} {"current_steps": 168820, "total_steps": 181800, "loss": 0.0123, "lr": 7.725095510256853e-07, "epoch": 18.572057205720572, "percentage": 92.86, "elapsed_time": "6:39:54", "remaining_time": "0:30:44", "throughput": 1484.87, "total_tokens": 35628256} {"current_steps": 168825, "total_steps": 181800, "loss": 0.0024, "lr": 7.71917638737385e-07, "epoch": 18.572607260726073, "percentage": 92.86, "elapsed_time": "6:39:54", "remaining_time": "0:30:44", "throughput": 1484.88, "total_tokens": 35629312} {"current_steps": 168830, "total_steps": 181800, "loss": 0.0812, "lr": 7.713259497476949e-07, "epoch": 18.573157315731574, "percentage": 92.87, "elapsed_time": "6:39:55", "remaining_time": "0:30:43", "throughput": 1484.88, "total_tokens": 35630368} {"current_steps": 168835, "total_steps": 181800, "loss": 0.1198, "lr": 7.707344840620634e-07, "epoch": 18.573707370737075, "percentage": 92.87, "elapsed_time": "6:39:56", "remaining_time": "0:30:42", "throughput": 1484.88, "total_tokens": 35631392} {"current_steps": 168840, "total_steps": 181800, "loss": 0.0035, "lr": 7.701432416859499e-07, "epoch": 18.574257425742573, "percentage": 92.87, "elapsed_time": "6:39:56", "remaining_time": "0:30:41", "throughput": 1484.88, "total_tokens": 35632480} {"current_steps": 168845, "total_steps": 181800, "loss": 0.0042, "lr": 7.695522226248003e-07, "epoch": 18.574807480748074, "percentage": 92.87, "elapsed_time": "6:39:57", "remaining_time": "0:30:41", "throughput": 1484.88, "total_tokens": 35633568} {"current_steps": 168850, "total_steps": 181800, "loss": 0.0037, "lr": 7.689614268840573e-07, "epoch": 18.575357535753575, "percentage": 92.88, "elapsed_time": "6:39:58", "remaining_time": "0:30:40", "throughput": 1484.88, "total_tokens": 35634592} {"current_steps": 168855, "total_steps": 181800, "loss": 0.0049, "lr": 7.683708544691692e-07, "epoch": 18.575907590759076, "percentage": 92.88, "elapsed_time": "6:39:58", "remaining_time": "0:30:39", "throughput": 1484.88, "total_tokens": 35635680} {"current_steps": 168860, "total_steps": 181800, "loss": 0.002, "lr": 7.677805053855791e-07, "epoch": 18.576457645764577, "percentage": 92.88, "elapsed_time": "6:39:59", "remaining_time": "0:30:39", "throughput": 1484.89, "total_tokens": 35636768} {"current_steps": 168865, "total_steps": 181800, "loss": 0.0459, "lr": 7.671903796387325e-07, "epoch": 18.57700770077008, "percentage": 92.89, "elapsed_time": "6:40:00", "remaining_time": "0:30:38", "throughput": 1484.89, "total_tokens": 35637824} {"current_steps": 168870, "total_steps": 181800, "loss": 0.0034, "lr": 7.66600477234064e-07, "epoch": 18.577557755775576, "percentage": 92.89, "elapsed_time": "6:40:01", "remaining_time": "0:30:37", "throughput": 1484.89, "total_tokens": 35638880} {"current_steps": 168875, "total_steps": 181800, "loss": 0.0015, "lr": 7.660107981770081e-07, "epoch": 18.578107810781077, "percentage": 92.89, "elapsed_time": "6:40:01", "remaining_time": "0:30:36", "throughput": 1484.89, "total_tokens": 35639936} {"current_steps": 168880, "total_steps": 181800, "loss": 0.0152, "lr": 7.654213424730022e-07, "epoch": 18.578657865786578, "percentage": 92.89, "elapsed_time": "6:40:02", "remaining_time": "0:30:36", "throughput": 1484.89, "total_tokens": 35640960} {"current_steps": 168885, "total_steps": 181800, "loss": 0.0022, "lr": 7.64832110127478e-07, "epoch": 18.57920792079208, "percentage": 92.9, "elapsed_time": "6:40:03", "remaining_time": "0:30:35", "throughput": 1484.89, "total_tokens": 35641952} {"current_steps": 168890, "total_steps": 181800, "loss": 0.0595, "lr": 7.642431011458701e-07, "epoch": 18.57975797579758, "percentage": 92.9, "elapsed_time": "6:40:03", "remaining_time": "0:30:34", "throughput": 1484.89, "total_tokens": 35643008} {"current_steps": 168895, "total_steps": 181800, "loss": 0.0043, "lr": 7.636543155336046e-07, "epoch": 18.58030803080308, "percentage": 92.9, "elapsed_time": "6:40:04", "remaining_time": "0:30:34", "throughput": 1484.89, "total_tokens": 35644032} {"current_steps": 168900, "total_steps": 181800, "loss": 0.0416, "lr": 7.630657532961022e-07, "epoch": 18.580858085808583, "percentage": 92.9, "elapsed_time": "6:40:05", "remaining_time": "0:30:33", "throughput": 1484.89, "total_tokens": 35645088} {"current_steps": 168905, "total_steps": 181800, "loss": 0.0534, "lr": 7.624774144387975e-07, "epoch": 18.58140814081408, "percentage": 92.91, "elapsed_time": "6:40:05", "remaining_time": "0:30:32", "throughput": 1484.89, "total_tokens": 35646080} {"current_steps": 168910, "total_steps": 181800, "loss": 0.0017, "lr": 7.618892989671056e-07, "epoch": 18.58195819581958, "percentage": 92.91, "elapsed_time": "6:40:06", "remaining_time": "0:30:32", "throughput": 1484.89, "total_tokens": 35647136} {"current_steps": 168915, "total_steps": 181800, "loss": 0.0449, "lr": 7.613014068864499e-07, "epoch": 18.582508250825082, "percentage": 92.91, "elapsed_time": "6:40:07", "remaining_time": "0:30:31", "throughput": 1484.89, "total_tokens": 35648224} {"current_steps": 168920, "total_steps": 181800, "loss": 0.0012, "lr": 7.607137382022511e-07, "epoch": 18.583058305830583, "percentage": 92.92, "elapsed_time": "6:40:07", "remaining_time": "0:30:30", "throughput": 1484.9, "total_tokens": 35649280} {"current_steps": 168925, "total_steps": 181800, "loss": 0.0123, "lr": 7.601262929199188e-07, "epoch": 18.583608360836084, "percentage": 92.92, "elapsed_time": "6:40:08", "remaining_time": "0:30:29", "throughput": 1484.9, "total_tokens": 35650368} {"current_steps": 168930, "total_steps": 181800, "loss": 0.0324, "lr": 7.595390710448735e-07, "epoch": 18.584158415841586, "percentage": 92.92, "elapsed_time": "6:40:09", "remaining_time": "0:30:29", "throughput": 1484.9, "total_tokens": 35651392} {"current_steps": 168935, "total_steps": 181800, "loss": 0.0318, "lr": 7.589520725825222e-07, "epoch": 18.584708470847083, "percentage": 92.92, "elapsed_time": "6:40:10", "remaining_time": "0:30:28", "throughput": 1484.9, "total_tokens": 35652448} {"current_steps": 168940, "total_steps": 181800, "loss": 0.0487, "lr": 7.583652975382799e-07, "epoch": 18.585258525852584, "percentage": 92.93, "elapsed_time": "6:40:10", "remaining_time": "0:30:27", "throughput": 1484.9, "total_tokens": 35653408} {"current_steps": 168945, "total_steps": 181800, "loss": 0.0065, "lr": 7.577787459175534e-07, "epoch": 18.585808580858085, "percentage": 92.93, "elapsed_time": "6:40:11", "remaining_time": "0:30:27", "throughput": 1484.9, "total_tokens": 35654432} {"current_steps": 168950, "total_steps": 181800, "loss": 0.0012, "lr": 7.571924177257439e-07, "epoch": 18.586358635863586, "percentage": 92.93, "elapsed_time": "6:40:12", "remaining_time": "0:30:26", "throughput": 1484.9, "total_tokens": 35655456} {"current_steps": 168955, "total_steps": 181800, "loss": 0.0323, "lr": 7.566063129682638e-07, "epoch": 18.586908690869087, "percentage": 92.93, "elapsed_time": "6:40:12", "remaining_time": "0:30:25", "throughput": 1484.9, "total_tokens": 35656608} {"current_steps": 168960, "total_steps": 181800, "loss": 0.0733, "lr": 7.560204316505087e-07, "epoch": 18.58745874587459, "percentage": 92.94, "elapsed_time": "6:40:13", "remaining_time": "0:30:24", "throughput": 1484.9, "total_tokens": 35657696} {"current_steps": 168965, "total_steps": 181800, "loss": 0.0457, "lr": 7.554347737778772e-07, "epoch": 18.58800880088009, "percentage": 92.94, "elapsed_time": "6:40:14", "remaining_time": "0:30:24", "throughput": 1484.91, "total_tokens": 35658816} {"current_steps": 168970, "total_steps": 181800, "loss": 0.0099, "lr": 7.548493393557704e-07, "epoch": 18.588558855885587, "percentage": 92.94, "elapsed_time": "6:40:14", "remaining_time": "0:30:23", "throughput": 1484.91, "total_tokens": 35659840} {"current_steps": 168975, "total_steps": 181800, "loss": 0.0148, "lr": 7.54264128389584e-07, "epoch": 18.58910891089109, "percentage": 92.95, "elapsed_time": "6:40:15", "remaining_time": "0:30:22", "throughput": 1484.91, "total_tokens": 35660864} {"current_steps": 168980, "total_steps": 181800, "loss": 0.0013, "lr": 7.536791408847139e-07, "epoch": 18.58965896589659, "percentage": 92.95, "elapsed_time": "6:40:16", "remaining_time": "0:30:22", "throughput": 1484.91, "total_tokens": 35661888} {"current_steps": 168985, "total_steps": 181800, "loss": 0.0336, "lr": 7.53094376846547e-07, "epoch": 18.59020902090209, "percentage": 92.95, "elapsed_time": "6:40:16", "remaining_time": "0:30:21", "throughput": 1484.91, "total_tokens": 35662912} {"current_steps": 168990, "total_steps": 181800, "loss": 0.0077, "lr": 7.525098362804711e-07, "epoch": 18.59075907590759, "percentage": 92.95, "elapsed_time": "6:40:17", "remaining_time": "0:30:20", "throughput": 1484.91, "total_tokens": 35664032} {"current_steps": 168995, "total_steps": 181800, "loss": 0.0343, "lr": 7.519255191918789e-07, "epoch": 18.591309130913093, "percentage": 92.96, "elapsed_time": "6:40:18", "remaining_time": "0:30:19", "throughput": 1484.91, "total_tokens": 35665056} {"current_steps": 169000, "total_steps": 181800, "loss": 0.0088, "lr": 7.513414255861522e-07, "epoch": 18.59185918591859, "percentage": 92.96, "elapsed_time": "6:40:18", "remaining_time": "0:30:19", "throughput": 1484.91, "total_tokens": 35666112} {"current_steps": 169005, "total_steps": 181800, "loss": 0.0523, "lr": 7.507575554686813e-07, "epoch": 18.59240924092409, "percentage": 92.96, "elapsed_time": "6:40:19", "remaining_time": "0:30:18", "throughput": 1484.91, "total_tokens": 35667168} {"current_steps": 169010, "total_steps": 181800, "loss": 0.099, "lr": 7.501739088448395e-07, "epoch": 18.592959295929592, "percentage": 92.96, "elapsed_time": "6:40:20", "remaining_time": "0:30:17", "throughput": 1484.92, "total_tokens": 35668256} {"current_steps": 169015, "total_steps": 181800, "loss": 0.053, "lr": 7.49590485720006e-07, "epoch": 18.593509350935093, "percentage": 92.97, "elapsed_time": "6:40:21", "remaining_time": "0:30:17", "throughput": 1484.92, "total_tokens": 35669312} {"current_steps": 169020, "total_steps": 181800, "loss": 0.0062, "lr": 7.49007286099565e-07, "epoch": 18.594059405940595, "percentage": 92.97, "elapsed_time": "6:40:21", "remaining_time": "0:30:16", "throughput": 1484.92, "total_tokens": 35670368} {"current_steps": 169025, "total_steps": 181800, "loss": 0.0007, "lr": 7.484243099888822e-07, "epoch": 18.594609460946096, "percentage": 92.97, "elapsed_time": "6:40:22", "remaining_time": "0:30:15", "throughput": 1484.92, "total_tokens": 35671456} {"current_steps": 169030, "total_steps": 181800, "loss": 0.1182, "lr": 7.478415573933362e-07, "epoch": 18.595159515951597, "percentage": 92.98, "elapsed_time": "6:40:23", "remaining_time": "0:30:14", "throughput": 1484.92, "total_tokens": 35672480} {"current_steps": 169035, "total_steps": 181800, "loss": 0.0506, "lr": 7.472590283183006e-07, "epoch": 18.595709570957094, "percentage": 92.98, "elapsed_time": "6:40:23", "remaining_time": "0:30:14", "throughput": 1484.92, "total_tokens": 35673504} {"current_steps": 169040, "total_steps": 181800, "loss": 0.004, "lr": 7.466767227691379e-07, "epoch": 18.596259625962595, "percentage": 92.98, "elapsed_time": "6:40:24", "remaining_time": "0:30:13", "throughput": 1484.92, "total_tokens": 35674560} {"current_steps": 169045, "total_steps": 181800, "loss": 0.1351, "lr": 7.460946407512215e-07, "epoch": 18.596809680968097, "percentage": 92.98, "elapsed_time": "6:40:25", "remaining_time": "0:30:12", "throughput": 1484.92, "total_tokens": 35675584} {"current_steps": 169050, "total_steps": 181800, "loss": 0.1257, "lr": 7.455127822699082e-07, "epoch": 18.597359735973598, "percentage": 92.99, "elapsed_time": "6:40:25", "remaining_time": "0:30:12", "throughput": 1484.92, "total_tokens": 35676608} {"current_steps": 169055, "total_steps": 181800, "loss": 0.002, "lr": 7.449311473305659e-07, "epoch": 18.5979097909791, "percentage": 92.99, "elapsed_time": "6:40:26", "remaining_time": "0:30:11", "throughput": 1484.93, "total_tokens": 35677696} {"current_steps": 169060, "total_steps": 181800, "loss": 0.0413, "lr": 7.443497359385571e-07, "epoch": 18.5984598459846, "percentage": 92.99, "elapsed_time": "6:40:27", "remaining_time": "0:30:10", "throughput": 1484.92, "total_tokens": 35678720} {"current_steps": 169065, "total_steps": 181800, "loss": 0.0106, "lr": 7.437685480992356e-07, "epoch": 18.599009900990097, "percentage": 93.0, "elapsed_time": "6:40:27", "remaining_time": "0:30:09", "throughput": 1484.93, "total_tokens": 35679776} {"current_steps": 169070, "total_steps": 181800, "loss": 0.0032, "lr": 7.431875838179641e-07, "epoch": 18.5995599559956, "percentage": 93.0, "elapsed_time": "6:40:28", "remaining_time": "0:30:09", "throughput": 1484.93, "total_tokens": 35680832} {"current_steps": 169075, "total_steps": 181800, "loss": 0.0075, "lr": 7.426068431000882e-07, "epoch": 18.6001100110011, "percentage": 93.0, "elapsed_time": "6:40:29", "remaining_time": "0:30:08", "throughput": 1484.93, "total_tokens": 35681984} {"current_steps": 169080, "total_steps": 181800, "loss": 0.0078, "lr": 7.420263259509674e-07, "epoch": 18.6006600660066, "percentage": 93.0, "elapsed_time": "6:40:30", "remaining_time": "0:30:07", "throughput": 1484.94, "total_tokens": 35683072} {"current_steps": 169085, "total_steps": 181800, "loss": 0.0039, "lr": 7.414460323759503e-07, "epoch": 18.6012101210121, "percentage": 93.01, "elapsed_time": "6:40:30", "remaining_time": "0:30:07", "throughput": 1484.93, "total_tokens": 35684064} {"current_steps": 169090, "total_steps": 181800, "loss": 0.0072, "lr": 7.408659623803827e-07, "epoch": 18.601760176017603, "percentage": 93.01, "elapsed_time": "6:40:31", "remaining_time": "0:30:06", "throughput": 1484.93, "total_tokens": 35685088} {"current_steps": 169095, "total_steps": 181800, "loss": 0.1528, "lr": 7.402861159696156e-07, "epoch": 18.602310231023104, "percentage": 93.01, "elapsed_time": "6:40:32", "remaining_time": "0:30:05", "throughput": 1484.94, "total_tokens": 35686144} {"current_steps": 169100, "total_steps": 181800, "loss": 0.0017, "lr": 7.397064931489894e-07, "epoch": 18.6028602860286, "percentage": 93.01, "elapsed_time": "6:40:32", "remaining_time": "0:30:04", "throughput": 1484.94, "total_tokens": 35687168} {"current_steps": 169105, "total_steps": 181800, "loss": 0.0104, "lr": 7.39127093923847e-07, "epoch": 18.603410341034103, "percentage": 93.02, "elapsed_time": "6:40:33", "remaining_time": "0:30:04", "throughput": 1484.94, "total_tokens": 35688224} {"current_steps": 169110, "total_steps": 181800, "loss": 0.082, "lr": 7.385479182995259e-07, "epoch": 18.603960396039604, "percentage": 93.02, "elapsed_time": "6:40:34", "remaining_time": "0:30:03", "throughput": 1484.94, "total_tokens": 35689248} {"current_steps": 169115, "total_steps": 181800, "loss": 0.0519, "lr": 7.379689662813688e-07, "epoch": 18.604510451045105, "percentage": 93.02, "elapsed_time": "6:40:34", "remaining_time": "0:30:02", "throughput": 1484.94, "total_tokens": 35690304} {"current_steps": 169120, "total_steps": 181800, "loss": 0.0023, "lr": 7.373902378747105e-07, "epoch": 18.605060506050606, "percentage": 93.03, "elapsed_time": "6:40:35", "remaining_time": "0:30:02", "throughput": 1484.94, "total_tokens": 35691360} {"current_steps": 169125, "total_steps": 181800, "loss": 0.006, "lr": 7.368117330848856e-07, "epoch": 18.605610561056107, "percentage": 93.03, "elapsed_time": "6:40:36", "remaining_time": "0:30:01", "throughput": 1484.94, "total_tokens": 35692448} {"current_steps": 169130, "total_steps": 181800, "loss": 0.013, "lr": 7.362334519172231e-07, "epoch": 18.606160616061608, "percentage": 93.03, "elapsed_time": "6:40:36", "remaining_time": "0:30:00", "throughput": 1484.94, "total_tokens": 35693536} {"current_steps": 169135, "total_steps": 181800, "loss": 0.0041, "lr": 7.35655394377055e-07, "epoch": 18.606710671067106, "percentage": 93.03, "elapsed_time": "6:40:37", "remaining_time": "0:29:59", "throughput": 1484.95, "total_tokens": 35694624} {"current_steps": 169140, "total_steps": 181800, "loss": 0.0015, "lr": 7.350775604697046e-07, "epoch": 18.607260726072607, "percentage": 93.04, "elapsed_time": "6:40:38", "remaining_time": "0:29:59", "throughput": 1484.95, "total_tokens": 35695680} {"current_steps": 169145, "total_steps": 181800, "loss": 0.0025, "lr": 7.344999502005012e-07, "epoch": 18.607810781078108, "percentage": 93.04, "elapsed_time": "6:40:39", "remaining_time": "0:29:58", "throughput": 1484.95, "total_tokens": 35696768} {"current_steps": 169150, "total_steps": 181800, "loss": 0.0731, "lr": 7.339225635747709e-07, "epoch": 18.60836083608361, "percentage": 93.04, "elapsed_time": "6:40:39", "remaining_time": "0:29:57", "throughput": 1484.95, "total_tokens": 35697824} {"current_steps": 169155, "total_steps": 181800, "loss": 0.0053, "lr": 7.333454005978318e-07, "epoch": 18.60891089108911, "percentage": 93.04, "elapsed_time": "6:40:40", "remaining_time": "0:29:57", "throughput": 1484.96, "total_tokens": 35698912} {"current_steps": 169160, "total_steps": 181800, "loss": 0.0042, "lr": 7.327684612750046e-07, "epoch": 18.60946094609461, "percentage": 93.05, "elapsed_time": "6:40:41", "remaining_time": "0:29:56", "throughput": 1484.96, "total_tokens": 35699968} {"current_steps": 169165, "total_steps": 181800, "loss": 0.0128, "lr": 7.321917456116018e-07, "epoch": 18.61001100110011, "percentage": 93.05, "elapsed_time": "6:40:41", "remaining_time": "0:29:55", "throughput": 1484.96, "total_tokens": 35700992} {"current_steps": 169170, "total_steps": 181800, "loss": 0.0166, "lr": 7.316152536129439e-07, "epoch": 18.61056105610561, "percentage": 93.05, "elapsed_time": "6:40:42", "remaining_time": "0:29:54", "throughput": 1484.96, "total_tokens": 35702080} {"current_steps": 169175, "total_steps": 181800, "loss": 0.0081, "lr": 7.310389852843464e-07, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "6:40:43", "remaining_time": "0:29:54", "throughput": 1484.96, "total_tokens": 35703104} {"current_steps": 169180, "total_steps": 181800, "loss": 0.0008, "lr": 7.304629406311158e-07, "epoch": 18.611661166116612, "percentage": 93.06, "elapsed_time": "6:40:43", "remaining_time": "0:29:53", "throughput": 1484.96, "total_tokens": 35704160} {"current_steps": 169185, "total_steps": 181800, "loss": 0.0021, "lr": 7.298871196585621e-07, "epoch": 18.612211221122113, "percentage": 93.06, "elapsed_time": "6:40:44", "remaining_time": "0:29:52", "throughput": 1484.96, "total_tokens": 35705184} {"current_steps": 169190, "total_steps": 181800, "loss": 0.0221, "lr": 7.293115223719921e-07, "epoch": 18.612761276127614, "percentage": 93.06, "elapsed_time": "6:40:45", "remaining_time": "0:29:52", "throughput": 1484.96, "total_tokens": 35706208} {"current_steps": 169195, "total_steps": 181800, "loss": 0.0008, "lr": 7.287361487767153e-07, "epoch": 18.61331133113311, "percentage": 93.07, "elapsed_time": "6:40:45", "remaining_time": "0:29:51", "throughput": 1484.96, "total_tokens": 35707264} {"current_steps": 169200, "total_steps": 181800, "loss": 0.0466, "lr": 7.281609988780274e-07, "epoch": 18.613861386138613, "percentage": 93.07, "elapsed_time": "6:40:46", "remaining_time": "0:29:50", "throughput": 1484.96, "total_tokens": 35708320} {"current_steps": 169205, "total_steps": 181800, "loss": 0.0034, "lr": 7.275860726812301e-07, "epoch": 18.614411441144114, "percentage": 93.07, "elapsed_time": "6:40:47", "remaining_time": "0:29:49", "throughput": 1484.96, "total_tokens": 35709376} {"current_steps": 169210, "total_steps": 181800, "loss": 0.0018, "lr": 7.270113701916298e-07, "epoch": 18.614961496149615, "percentage": 93.07, "elapsed_time": "6:40:48", "remaining_time": "0:29:49", "throughput": 1484.97, "total_tokens": 35710464} {"current_steps": 169215, "total_steps": 181800, "loss": 0.0031, "lr": 7.26436891414517e-07, "epoch": 18.615511551155116, "percentage": 93.08, "elapsed_time": "6:40:48", "remaining_time": "0:29:48", "throughput": 1484.97, "total_tokens": 35711488} {"current_steps": 169220, "total_steps": 181800, "loss": 0.0132, "lr": 7.258626363551901e-07, "epoch": 18.616061606160617, "percentage": 93.08, "elapsed_time": "6:40:49", "remaining_time": "0:29:47", "throughput": 1484.97, "total_tokens": 35712576} {"current_steps": 169225, "total_steps": 181800, "loss": 0.005, "lr": 7.25288605018934e-07, "epoch": 18.616611661166118, "percentage": 93.08, "elapsed_time": "6:40:50", "remaining_time": "0:29:47", "throughput": 1484.97, "total_tokens": 35713568} {"current_steps": 169230, "total_steps": 181800, "loss": 0.0688, "lr": 7.247147974110469e-07, "epoch": 18.617161716171616, "percentage": 93.09, "elapsed_time": "6:40:50", "remaining_time": "0:29:46", "throughput": 1484.97, "total_tokens": 35714592} {"current_steps": 169235, "total_steps": 181800, "loss": 0.0083, "lr": 7.241412135368192e-07, "epoch": 18.617711771177117, "percentage": 93.09, "elapsed_time": "6:40:51", "remaining_time": "0:29:45", "throughput": 1484.97, "total_tokens": 35715648} {"current_steps": 169240, "total_steps": 181800, "loss": 0.0365, "lr": 7.235678534015272e-07, "epoch": 18.618261826182618, "percentage": 93.09, "elapsed_time": "6:40:52", "remaining_time": "0:29:45", "throughput": 1484.97, "total_tokens": 35716672} {"current_steps": 169245, "total_steps": 181800, "loss": 0.0282, "lr": 7.229947170104667e-07, "epoch": 18.61881188118812, "percentage": 93.09, "elapsed_time": "6:40:52", "remaining_time": "0:29:44", "throughput": 1484.97, "total_tokens": 35717728} {"current_steps": 169250, "total_steps": 181800, "loss": 0.0045, "lr": 7.22421804368914e-07, "epoch": 18.61936193619362, "percentage": 93.1, "elapsed_time": "6:40:53", "remaining_time": "0:29:43", "throughput": 1484.97, "total_tokens": 35718848} {"current_steps": 169255, "total_steps": 181800, "loss": 0.0033, "lr": 7.218491154821455e-07, "epoch": 18.61991199119912, "percentage": 93.1, "elapsed_time": "6:40:54", "remaining_time": "0:29:42", "throughput": 1484.97, "total_tokens": 35719872} {"current_steps": 169260, "total_steps": 181800, "loss": 0.0055, "lr": 7.212766503554458e-07, "epoch": 18.620462046204622, "percentage": 93.1, "elapsed_time": "6:40:54", "remaining_time": "0:29:42", "throughput": 1484.97, "total_tokens": 35720960} {"current_steps": 169265, "total_steps": 181800, "loss": 0.0009, "lr": 7.207044089940884e-07, "epoch": 18.62101210121012, "percentage": 93.11, "elapsed_time": "6:40:55", "remaining_time": "0:29:41", "throughput": 1484.97, "total_tokens": 35721984} {"current_steps": 169270, "total_steps": 181800, "loss": 0.0372, "lr": 7.201323914033525e-07, "epoch": 18.62156215621562, "percentage": 93.11, "elapsed_time": "6:40:56", "remaining_time": "0:29:40", "throughput": 1484.98, "total_tokens": 35723072} {"current_steps": 169275, "total_steps": 181800, "loss": 0.044, "lr": 7.195605975885033e-07, "epoch": 18.622112211221122, "percentage": 93.11, "elapsed_time": "6:40:57", "remaining_time": "0:29:40", "throughput": 1484.98, "total_tokens": 35724160} {"current_steps": 169280, "total_steps": 181800, "loss": 0.0017, "lr": 7.189890275548117e-07, "epoch": 18.622662266226623, "percentage": 93.11, "elapsed_time": "6:40:57", "remaining_time": "0:29:39", "throughput": 1484.98, "total_tokens": 35725248} {"current_steps": 169285, "total_steps": 181800, "loss": 0.0016, "lr": 7.184176813075483e-07, "epoch": 18.623212321232124, "percentage": 93.12, "elapsed_time": "6:40:58", "remaining_time": "0:29:38", "throughput": 1484.98, "total_tokens": 35726272} {"current_steps": 169290, "total_steps": 181800, "loss": 0.0987, "lr": 7.178465588519784e-07, "epoch": 18.623762376237625, "percentage": 93.12, "elapsed_time": "6:40:59", "remaining_time": "0:29:37", "throughput": 1484.98, "total_tokens": 35727328} {"current_steps": 169295, "total_steps": 181800, "loss": 0.0804, "lr": 7.172756601933645e-07, "epoch": 18.624312431243123, "percentage": 93.12, "elapsed_time": "6:40:59", "remaining_time": "0:29:37", "throughput": 1484.98, "total_tokens": 35728384} {"current_steps": 169300, "total_steps": 181800, "loss": 0.0167, "lr": 7.167049853369689e-07, "epoch": 18.624862486248624, "percentage": 93.12, "elapsed_time": "6:41:00", "remaining_time": "0:29:36", "throughput": 1484.99, "total_tokens": 35729472} {"current_steps": 169305, "total_steps": 181800, "loss": 0.0069, "lr": 7.161345342880487e-07, "epoch": 18.625412541254125, "percentage": 93.13, "elapsed_time": "6:41:01", "remaining_time": "0:29:35", "throughput": 1484.99, "total_tokens": 35730528} {"current_steps": 169310, "total_steps": 181800, "loss": 0.0009, "lr": 7.155643070518692e-07, "epoch": 18.625962596259626, "percentage": 93.13, "elapsed_time": "6:41:01", "remaining_time": "0:29:35", "throughput": 1484.99, "total_tokens": 35731520} {"current_steps": 169315, "total_steps": 181800, "loss": 0.0115, "lr": 7.14994303633676e-07, "epoch": 18.626512651265127, "percentage": 93.13, "elapsed_time": "6:41:02", "remaining_time": "0:29:34", "throughput": 1484.99, "total_tokens": 35732576} {"current_steps": 169320, "total_steps": 181800, "loss": 0.021, "lr": 7.144245240387259e-07, "epoch": 18.627062706270628, "percentage": 93.14, "elapsed_time": "6:41:03", "remaining_time": "0:29:33", "throughput": 1484.99, "total_tokens": 35733568} {"current_steps": 169325, "total_steps": 181800, "loss": 0.0016, "lr": 7.138549682722762e-07, "epoch": 18.62761276127613, "percentage": 93.14, "elapsed_time": "6:41:03", "remaining_time": "0:29:32", "throughput": 1484.99, "total_tokens": 35734624} {"current_steps": 169330, "total_steps": 181800, "loss": 0.0021, "lr": 7.132856363395696e-07, "epoch": 18.628162816281627, "percentage": 93.14, "elapsed_time": "6:41:04", "remaining_time": "0:29:32", "throughput": 1484.99, "total_tokens": 35735712} {"current_steps": 169335, "total_steps": 181800, "loss": 0.0867, "lr": 7.127165282458576e-07, "epoch": 18.628712871287128, "percentage": 93.14, "elapsed_time": "6:41:05", "remaining_time": "0:29:31", "throughput": 1484.99, "total_tokens": 35736768} {"current_steps": 169340, "total_steps": 181800, "loss": 0.1184, "lr": 7.121476439963831e-07, "epoch": 18.62926292629263, "percentage": 93.15, "elapsed_time": "6:41:05", "remaining_time": "0:29:30", "throughput": 1484.99, "total_tokens": 35737856} {"current_steps": 169345, "total_steps": 181800, "loss": 0.0076, "lr": 7.115789835963837e-07, "epoch": 18.62981298129813, "percentage": 93.15, "elapsed_time": "6:41:06", "remaining_time": "0:29:30", "throughput": 1485.0, "total_tokens": 35738912} {"current_steps": 169350, "total_steps": 181800, "loss": 0.0018, "lr": 7.110105470511108e-07, "epoch": 18.63036303630363, "percentage": 93.15, "elapsed_time": "6:41:07", "remaining_time": "0:29:29", "throughput": 1485.0, "total_tokens": 35739936} {"current_steps": 169355, "total_steps": 181800, "loss": 0.0038, "lr": 7.104423343657962e-07, "epoch": 18.630913091309132, "percentage": 93.15, "elapsed_time": "6:41:08", "remaining_time": "0:29:28", "throughput": 1485.0, "total_tokens": 35740960} {"current_steps": 169360, "total_steps": 181800, "loss": 0.1174, "lr": 7.09874345545683e-07, "epoch": 18.63146314631463, "percentage": 93.16, "elapsed_time": "6:41:08", "remaining_time": "0:29:27", "throughput": 1485.0, "total_tokens": 35742048} {"current_steps": 169365, "total_steps": 181800, "loss": 0.0012, "lr": 7.093065805960031e-07, "epoch": 18.63201320132013, "percentage": 93.16, "elapsed_time": "6:41:09", "remaining_time": "0:29:27", "throughput": 1485.0, "total_tokens": 35743168} {"current_steps": 169370, "total_steps": 181800, "loss": 0.003, "lr": 7.087390395219828e-07, "epoch": 18.632563256325632, "percentage": 93.16, "elapsed_time": "6:41:10", "remaining_time": "0:29:26", "throughput": 1485.0, "total_tokens": 35744192} {"current_steps": 169375, "total_steps": 181800, "loss": 0.0011, "lr": 7.081717223288625e-07, "epoch": 18.633113311331133, "percentage": 93.17, "elapsed_time": "6:41:10", "remaining_time": "0:29:25", "throughput": 1485.01, "total_tokens": 35745280} {"current_steps": 169380, "total_steps": 181800, "loss": 0.006, "lr": 7.076046290218629e-07, "epoch": 18.633663366336634, "percentage": 93.17, "elapsed_time": "6:41:11", "remaining_time": "0:29:25", "throughput": 1485.01, "total_tokens": 35746368} {"current_steps": 169385, "total_steps": 181800, "loss": 0.0029, "lr": 7.070377596062216e-07, "epoch": 18.634213421342135, "percentage": 93.17, "elapsed_time": "6:41:12", "remaining_time": "0:29:24", "throughput": 1485.01, "total_tokens": 35747392} {"current_steps": 169390, "total_steps": 181800, "loss": 0.0025, "lr": 7.064711140871538e-07, "epoch": 18.634763476347636, "percentage": 93.17, "elapsed_time": "6:41:12", "remaining_time": "0:29:23", "throughput": 1485.01, "total_tokens": 35748448} {"current_steps": 169395, "total_steps": 181800, "loss": 0.0098, "lr": 7.059046924698831e-07, "epoch": 18.635313531353134, "percentage": 93.18, "elapsed_time": "6:41:13", "remaining_time": "0:29:22", "throughput": 1485.01, "total_tokens": 35749504} {"current_steps": 169400, "total_steps": 181800, "loss": 0.0276, "lr": 7.05338494759633e-07, "epoch": 18.635863586358635, "percentage": 93.18, "elapsed_time": "6:41:14", "remaining_time": "0:29:22", "throughput": 1485.01, "total_tokens": 35750560} {"current_steps": 169405, "total_steps": 181800, "loss": 0.0056, "lr": 7.047725209616162e-07, "epoch": 18.636413641364136, "percentage": 93.18, "elapsed_time": "6:41:14", "remaining_time": "0:29:21", "throughput": 1485.02, "total_tokens": 35751680} {"current_steps": 169410, "total_steps": 181800, "loss": 0.0159, "lr": 7.04206771081059e-07, "epoch": 18.636963696369637, "percentage": 93.18, "elapsed_time": "6:41:15", "remaining_time": "0:29:20", "throughput": 1485.01, "total_tokens": 35752672} {"current_steps": 169415, "total_steps": 181800, "loss": 0.0169, "lr": 7.036412451231683e-07, "epoch": 18.63751375137514, "percentage": 93.19, "elapsed_time": "6:41:16", "remaining_time": "0:29:20", "throughput": 1485.01, "total_tokens": 35753696} {"current_steps": 169420, "total_steps": 181800, "loss": 0.0033, "lr": 7.030759430931538e-07, "epoch": 18.63806380638064, "percentage": 93.19, "elapsed_time": "6:41:17", "remaining_time": "0:29:19", "throughput": 1485.01, "total_tokens": 35754752} {"current_steps": 169425, "total_steps": 181800, "loss": 0.0013, "lr": 7.025108649962336e-07, "epoch": 18.638613861386137, "percentage": 93.19, "elapsed_time": "6:41:17", "remaining_time": "0:29:18", "throughput": 1485.01, "total_tokens": 35755776} {"current_steps": 169430, "total_steps": 181800, "loss": 0.0021, "lr": 7.019460108376091e-07, "epoch": 18.639163916391638, "percentage": 93.2, "elapsed_time": "6:41:18", "remaining_time": "0:29:17", "throughput": 1485.01, "total_tokens": 35756800} {"current_steps": 169435, "total_steps": 181800, "loss": 0.0039, "lr": 7.0138138062249e-07, "epoch": 18.63971397139714, "percentage": 93.2, "elapsed_time": "6:41:19", "remaining_time": "0:29:17", "throughput": 1485.01, "total_tokens": 35757792} {"current_steps": 169440, "total_steps": 181800, "loss": 0.0622, "lr": 7.008169743560806e-07, "epoch": 18.64026402640264, "percentage": 93.2, "elapsed_time": "6:41:19", "remaining_time": "0:29:16", "throughput": 1485.02, "total_tokens": 35758880} {"current_steps": 169445, "total_steps": 181800, "loss": 0.0395, "lr": 7.002527920435792e-07, "epoch": 18.64081408140814, "percentage": 93.2, "elapsed_time": "6:41:20", "remaining_time": "0:29:15", "throughput": 1485.02, "total_tokens": 35759936} {"current_steps": 169450, "total_steps": 181800, "loss": 0.0675, "lr": 6.996888336901902e-07, "epoch": 18.641364136413642, "percentage": 93.21, "elapsed_time": "6:41:21", "remaining_time": "0:29:15", "throughput": 1485.02, "total_tokens": 35760960} {"current_steps": 169455, "total_steps": 181800, "loss": 0.0024, "lr": 6.991250993011039e-07, "epoch": 18.641914191419144, "percentage": 93.21, "elapsed_time": "6:41:21", "remaining_time": "0:29:14", "throughput": 1485.02, "total_tokens": 35762080} {"current_steps": 169460, "total_steps": 181800, "loss": 0.0479, "lr": 6.985615888815273e-07, "epoch": 18.64246424642464, "percentage": 93.21, "elapsed_time": "6:41:22", "remaining_time": "0:29:13", "throughput": 1485.02, "total_tokens": 35763136} {"current_steps": 169465, "total_steps": 181800, "loss": 0.0019, "lr": 6.979983024366421e-07, "epoch": 18.643014301430142, "percentage": 93.22, "elapsed_time": "6:41:23", "remaining_time": "0:29:12", "throughput": 1485.02, "total_tokens": 35764128} {"current_steps": 169470, "total_steps": 181800, "loss": 0.0073, "lr": 6.974352399716472e-07, "epoch": 18.643564356435643, "percentage": 93.22, "elapsed_time": "6:41:23", "remaining_time": "0:29:12", "throughput": 1485.02, "total_tokens": 35765216} {"current_steps": 169475, "total_steps": 181800, "loss": 0.0041, "lr": 6.968724014917299e-07, "epoch": 18.644114411441144, "percentage": 93.22, "elapsed_time": "6:41:24", "remaining_time": "0:29:11", "throughput": 1485.02, "total_tokens": 35766208} {"current_steps": 169480, "total_steps": 181800, "loss": 0.0062, "lr": 6.963097870020807e-07, "epoch": 18.644664466446645, "percentage": 93.22, "elapsed_time": "6:41:25", "remaining_time": "0:29:10", "throughput": 1485.02, "total_tokens": 35767232} {"current_steps": 169485, "total_steps": 181800, "loss": 0.0305, "lr": 6.957473965078787e-07, "epoch": 18.645214521452147, "percentage": 93.23, "elapsed_time": "6:41:26", "remaining_time": "0:29:10", "throughput": 1485.02, "total_tokens": 35768320} {"current_steps": 169490, "total_steps": 181800, "loss": 0.0286, "lr": 6.951852300143114e-07, "epoch": 18.645764576457644, "percentage": 93.23, "elapsed_time": "6:41:26", "remaining_time": "0:29:09", "throughput": 1485.03, "total_tokens": 35769408} {"current_steps": 169495, "total_steps": 181800, "loss": 0.0019, "lr": 6.946232875265579e-07, "epoch": 18.646314631463145, "percentage": 93.23, "elapsed_time": "6:41:27", "remaining_time": "0:29:08", "throughput": 1485.03, "total_tokens": 35770432} {"current_steps": 169500, "total_steps": 181800, "loss": 0.0029, "lr": 6.940615690498003e-07, "epoch": 18.646864686468646, "percentage": 93.23, "elapsed_time": "6:41:28", "remaining_time": "0:29:07", "throughput": 1485.03, "total_tokens": 35771488} {"current_steps": 169505, "total_steps": 181800, "loss": 0.0014, "lr": 6.935000745892179e-07, "epoch": 18.647414741474147, "percentage": 93.24, "elapsed_time": "6:41:28", "remaining_time": "0:29:07", "throughput": 1485.03, "total_tokens": 35772544} {"current_steps": 169510, "total_steps": 181800, "loss": 0.0392, "lr": 6.929388041499757e-07, "epoch": 18.64796479647965, "percentage": 93.24, "elapsed_time": "6:41:29", "remaining_time": "0:29:06", "throughput": 1485.03, "total_tokens": 35773632} {"current_steps": 169515, "total_steps": 181800, "loss": 0.0084, "lr": 6.923777577372559e-07, "epoch": 18.64851485148515, "percentage": 93.24, "elapsed_time": "6:41:30", "remaining_time": "0:29:05", "throughput": 1485.03, "total_tokens": 35774688} {"current_steps": 169520, "total_steps": 181800, "loss": 0.044, "lr": 6.918169353562265e-07, "epoch": 18.64906490649065, "percentage": 93.25, "elapsed_time": "6:41:30", "remaining_time": "0:29:05", "throughput": 1485.04, "total_tokens": 35775776} {"current_steps": 169525, "total_steps": 181800, "loss": 0.0036, "lr": 6.912563370120528e-07, "epoch": 18.649614961496148, "percentage": 93.25, "elapsed_time": "6:41:31", "remaining_time": "0:29:04", "throughput": 1485.04, "total_tokens": 35776864} {"current_steps": 169530, "total_steps": 181800, "loss": 0.0046, "lr": 6.906959627099113e-07, "epoch": 18.65016501650165, "percentage": 93.25, "elapsed_time": "6:41:32", "remaining_time": "0:29:03", "throughput": 1485.04, "total_tokens": 35777888} {"current_steps": 169535, "total_steps": 181800, "loss": 0.0014, "lr": 6.901358124549562e-07, "epoch": 18.65071507150715, "percentage": 93.25, "elapsed_time": "6:41:32", "remaining_time": "0:29:03", "throughput": 1485.04, "total_tokens": 35778944} {"current_steps": 169540, "total_steps": 181800, "loss": 0.0799, "lr": 6.895758862523555e-07, "epoch": 18.65126512651265, "percentage": 93.26, "elapsed_time": "6:41:33", "remaining_time": "0:29:02", "throughput": 1485.04, "total_tokens": 35779936} {"current_steps": 169545, "total_steps": 181800, "loss": 0.0023, "lr": 6.890161841072662e-07, "epoch": 18.651815181518153, "percentage": 93.26, "elapsed_time": "6:41:34", "remaining_time": "0:29:01", "throughput": 1485.04, "total_tokens": 35781024} {"current_steps": 169550, "total_steps": 181800, "loss": 0.0068, "lr": 6.884567060248509e-07, "epoch": 18.652365236523654, "percentage": 93.26, "elapsed_time": "6:41:34", "remaining_time": "0:29:00", "throughput": 1485.04, "total_tokens": 35782016} {"current_steps": 169555, "total_steps": 181800, "loss": 0.0035, "lr": 6.878974520102638e-07, "epoch": 18.652915291529155, "percentage": 93.26, "elapsed_time": "6:41:35", "remaining_time": "0:29:00", "throughput": 1485.04, "total_tokens": 35783040} {"current_steps": 169560, "total_steps": 181800, "loss": 0.1037, "lr": 6.873384220686619e-07, "epoch": 18.653465346534652, "percentage": 93.27, "elapsed_time": "6:41:36", "remaining_time": "0:28:59", "throughput": 1485.04, "total_tokens": 35784064} {"current_steps": 169565, "total_steps": 181800, "loss": 0.0043, "lr": 6.867796162051937e-07, "epoch": 18.654015401540153, "percentage": 93.27, "elapsed_time": "6:41:37", "remaining_time": "0:28:58", "throughput": 1485.04, "total_tokens": 35785120} {"current_steps": 169570, "total_steps": 181800, "loss": 0.0042, "lr": 6.862210344250108e-07, "epoch": 18.654565456545654, "percentage": 93.27, "elapsed_time": "6:41:37", "remaining_time": "0:28:58", "throughput": 1485.04, "total_tokens": 35786176} {"current_steps": 169575, "total_steps": 181800, "loss": 0.0044, "lr": 6.856626767332646e-07, "epoch": 18.655115511551156, "percentage": 93.28, "elapsed_time": "6:41:38", "remaining_time": "0:28:57", "throughput": 1485.04, "total_tokens": 35787232} {"current_steps": 169580, "total_steps": 181800, "loss": 0.0042, "lr": 6.851045431350927e-07, "epoch": 18.655665566556657, "percentage": 93.28, "elapsed_time": "6:41:39", "remaining_time": "0:28:56", "throughput": 1485.04, "total_tokens": 35788256} {"current_steps": 169585, "total_steps": 181800, "loss": 0.0039, "lr": 6.845466336356494e-07, "epoch": 18.656215621562158, "percentage": 93.28, "elapsed_time": "6:41:39", "remaining_time": "0:28:55", "throughput": 1485.04, "total_tokens": 35789280} {"current_steps": 169590, "total_steps": 181800, "loss": 0.0404, "lr": 6.839889482400719e-07, "epoch": 18.656765676567655, "percentage": 93.28, "elapsed_time": "6:41:40", "remaining_time": "0:28:55", "throughput": 1485.04, "total_tokens": 35790304} {"current_steps": 169595, "total_steps": 181800, "loss": 0.085, "lr": 6.83431486953498e-07, "epoch": 18.657315731573156, "percentage": 93.29, "elapsed_time": "6:41:41", "remaining_time": "0:28:54", "throughput": 1485.04, "total_tokens": 35791328} {"current_steps": 169600, "total_steps": 181800, "loss": 0.0046, "lr": 6.828742497810708e-07, "epoch": 18.657865786578657, "percentage": 93.29, "elapsed_time": "6:41:41", "remaining_time": "0:28:53", "throughput": 1485.04, "total_tokens": 35792384} {"current_steps": 169605, "total_steps": 181800, "loss": 0.0456, "lr": 6.823172367279195e-07, "epoch": 18.65841584158416, "percentage": 93.29, "elapsed_time": "6:41:42", "remaining_time": "0:28:53", "throughput": 1485.04, "total_tokens": 35793440} {"current_steps": 169610, "total_steps": 181800, "loss": 0.1188, "lr": 6.817604477991818e-07, "epoch": 18.65896589658966, "percentage": 93.29, "elapsed_time": "6:41:43", "remaining_time": "0:28:52", "throughput": 1485.04, "total_tokens": 35794464} {"current_steps": 169615, "total_steps": 181800, "loss": 0.0059, "lr": 6.812038829999923e-07, "epoch": 18.65951595159516, "percentage": 93.3, "elapsed_time": "6:41:43", "remaining_time": "0:28:51", "throughput": 1485.05, "total_tokens": 35795584} {"current_steps": 169620, "total_steps": 181800, "loss": 0.0045, "lr": 6.806475423354747e-07, "epoch": 18.66006600660066, "percentage": 93.3, "elapsed_time": "6:41:44", "remaining_time": "0:28:50", "throughput": 1485.05, "total_tokens": 35796544} {"current_steps": 169625, "total_steps": 181800, "loss": 0.0917, "lr": 6.800914258107611e-07, "epoch": 18.66061606160616, "percentage": 93.3, "elapsed_time": "6:41:45", "remaining_time": "0:28:50", "throughput": 1485.04, "total_tokens": 35797504} {"current_steps": 169630, "total_steps": 181800, "loss": 0.0016, "lr": 6.795355334309777e-07, "epoch": 18.66116611661166, "percentage": 93.31, "elapsed_time": "6:41:46", "remaining_time": "0:28:49", "throughput": 1485.04, "total_tokens": 35798496} {"current_steps": 169635, "total_steps": 181800, "loss": 0.0013, "lr": 6.789798652012402e-07, "epoch": 18.66171617161716, "percentage": 93.31, "elapsed_time": "6:41:46", "remaining_time": "0:28:48", "throughput": 1485.04, "total_tokens": 35799520} {"current_steps": 169640, "total_steps": 181800, "loss": 0.0142, "lr": 6.78424421126675e-07, "epoch": 18.662266226622663, "percentage": 93.31, "elapsed_time": "6:41:47", "remaining_time": "0:28:48", "throughput": 1485.04, "total_tokens": 35800544} {"current_steps": 169645, "total_steps": 181800, "loss": 0.0033, "lr": 6.778692012124e-07, "epoch": 18.662816281628164, "percentage": 93.31, "elapsed_time": "6:41:48", "remaining_time": "0:28:47", "throughput": 1485.04, "total_tokens": 35801536} {"current_steps": 169650, "total_steps": 181800, "loss": 0.0015, "lr": 6.773142054635389e-07, "epoch": 18.663366336633665, "percentage": 93.32, "elapsed_time": "6:41:48", "remaining_time": "0:28:46", "throughput": 1485.04, "total_tokens": 35802560} {"current_steps": 169655, "total_steps": 181800, "loss": 0.0091, "lr": 6.76759433885199e-07, "epoch": 18.663916391639162, "percentage": 93.32, "elapsed_time": "6:41:49", "remaining_time": "0:28:45", "throughput": 1485.04, "total_tokens": 35803552} {"current_steps": 169660, "total_steps": 181800, "loss": 0.0073, "lr": 6.762048864824955e-07, "epoch": 18.664466446644663, "percentage": 93.32, "elapsed_time": "6:41:50", "remaining_time": "0:28:45", "throughput": 1485.04, "total_tokens": 35804608} {"current_steps": 169665, "total_steps": 181800, "loss": 0.0234, "lr": 6.756505632605381e-07, "epoch": 18.665016501650165, "percentage": 93.33, "elapsed_time": "6:41:50", "remaining_time": "0:28:44", "throughput": 1485.04, "total_tokens": 35805760} {"current_steps": 169670, "total_steps": 181800, "loss": 0.1063, "lr": 6.750964642244423e-07, "epoch": 18.665566556655666, "percentage": 93.33, "elapsed_time": "6:41:51", "remaining_time": "0:28:43", "throughput": 1485.05, "total_tokens": 35806816} {"current_steps": 169675, "total_steps": 181800, "loss": 0.014, "lr": 6.745425893793067e-07, "epoch": 18.666116611661167, "percentage": 93.33, "elapsed_time": "6:41:52", "remaining_time": "0:28:43", "throughput": 1485.05, "total_tokens": 35807936} {"current_steps": 169680, "total_steps": 181800, "loss": 0.0139, "lr": 6.739889387302411e-07, "epoch": 18.666666666666668, "percentage": 93.33, "elapsed_time": "6:41:53", "remaining_time": "0:28:42", "throughput": 1485.04, "total_tokens": 35809024} {"current_steps": 169685, "total_steps": 181800, "loss": 0.0299, "lr": 6.734355122823444e-07, "epoch": 18.66721672167217, "percentage": 93.34, "elapsed_time": "6:41:53", "remaining_time": "0:28:41", "throughput": 1485.04, "total_tokens": 35810080} {"current_steps": 169690, "total_steps": 181800, "loss": 0.1023, "lr": 6.728823100407234e-07, "epoch": 18.667766776677666, "percentage": 93.34, "elapsed_time": "6:41:54", "remaining_time": "0:28:40", "throughput": 1485.04, "total_tokens": 35811104} {"current_steps": 169695, "total_steps": 181800, "loss": 0.0322, "lr": 6.723293320104685e-07, "epoch": 18.668316831683168, "percentage": 93.34, "elapsed_time": "6:41:55", "remaining_time": "0:28:40", "throughput": 1485.04, "total_tokens": 35812192} {"current_steps": 169700, "total_steps": 181800, "loss": 0.0022, "lr": 6.717765781966839e-07, "epoch": 18.66886688668867, "percentage": 93.34, "elapsed_time": "6:41:55", "remaining_time": "0:28:39", "throughput": 1485.05, "total_tokens": 35813248} {"current_steps": 169705, "total_steps": 181800, "loss": 0.0185, "lr": 6.712240486044602e-07, "epoch": 18.66941694169417, "percentage": 93.35, "elapsed_time": "6:41:56", "remaining_time": "0:28:38", "throughput": 1485.05, "total_tokens": 35814336} {"current_steps": 169710, "total_steps": 181800, "loss": 0.0071, "lr": 6.706717432388876e-07, "epoch": 18.66996699669967, "percentage": 93.35, "elapsed_time": "6:41:57", "remaining_time": "0:28:38", "throughput": 1485.05, "total_tokens": 35815456} {"current_steps": 169715, "total_steps": 181800, "loss": 0.0194, "lr": 6.701196621050648e-07, "epoch": 18.670517051705172, "percentage": 93.35, "elapsed_time": "6:41:58", "remaining_time": "0:28:37", "throughput": 1485.05, "total_tokens": 35816576} {"current_steps": 169720, "total_steps": 181800, "loss": 0.0008, "lr": 6.695678052080684e-07, "epoch": 18.67106710671067, "percentage": 93.36, "elapsed_time": "6:41:58", "remaining_time": "0:28:36", "throughput": 1485.06, "total_tokens": 35817632} {"current_steps": 169725, "total_steps": 181800, "loss": 0.0445, "lr": 6.690161725529915e-07, "epoch": 18.67161716171617, "percentage": 93.36, "elapsed_time": "6:41:59", "remaining_time": "0:28:35", "throughput": 1485.06, "total_tokens": 35818688} {"current_steps": 169730, "total_steps": 181800, "loss": 0.0956, "lr": 6.684647641449215e-07, "epoch": 18.67216721672167, "percentage": 93.36, "elapsed_time": "6:42:00", "remaining_time": "0:28:35", "throughput": 1485.06, "total_tokens": 35819712} {"current_steps": 169735, "total_steps": 181800, "loss": 0.0621, "lr": 6.679135799889325e-07, "epoch": 18.672717271727173, "percentage": 93.36, "elapsed_time": "6:42:00", "remaining_time": "0:28:34", "throughput": 1485.06, "total_tokens": 35820800} {"current_steps": 169740, "total_steps": 181800, "loss": 0.0505, "lr": 6.673626200901117e-07, "epoch": 18.673267326732674, "percentage": 93.37, "elapsed_time": "6:42:01", "remaining_time": "0:28:33", "throughput": 1485.06, "total_tokens": 35821856} {"current_steps": 169745, "total_steps": 181800, "loss": 0.0062, "lr": 6.668118844535331e-07, "epoch": 18.673817381738175, "percentage": 93.37, "elapsed_time": "6:42:02", "remaining_time": "0:28:33", "throughput": 1485.06, "total_tokens": 35822880} {"current_steps": 169750, "total_steps": 181800, "loss": 0.0718, "lr": 6.662613730842704e-07, "epoch": 18.674367436743676, "percentage": 93.37, "elapsed_time": "6:42:02", "remaining_time": "0:28:32", "throughput": 1485.06, "total_tokens": 35823968} {"current_steps": 169755, "total_steps": 181800, "loss": 0.0909, "lr": 6.657110859874027e-07, "epoch": 18.674917491749174, "percentage": 93.37, "elapsed_time": "6:42:03", "remaining_time": "0:28:31", "throughput": 1485.06, "total_tokens": 35824992} {"current_steps": 169760, "total_steps": 181800, "loss": 0.0279, "lr": 6.651610231679956e-07, "epoch": 18.675467546754675, "percentage": 93.38, "elapsed_time": "6:42:04", "remaining_time": "0:28:30", "throughput": 1485.06, "total_tokens": 35826048} {"current_steps": 169765, "total_steps": 181800, "loss": 0.0251, "lr": 6.646111846311254e-07, "epoch": 18.676017601760176, "percentage": 93.38, "elapsed_time": "6:42:04", "remaining_time": "0:28:30", "throughput": 1485.07, "total_tokens": 35827136} {"current_steps": 169770, "total_steps": 181800, "loss": 0.0018, "lr": 6.640615703818575e-07, "epoch": 18.676567656765677, "percentage": 93.38, "elapsed_time": "6:42:05", "remaining_time": "0:28:29", "throughput": 1485.07, "total_tokens": 35828192} {"current_steps": 169775, "total_steps": 181800, "loss": 0.0015, "lr": 6.635121804252548e-07, "epoch": 18.677117711771178, "percentage": 93.39, "elapsed_time": "6:42:06", "remaining_time": "0:28:28", "throughput": 1485.07, "total_tokens": 35829216} {"current_steps": 169780, "total_steps": 181800, "loss": 0.0037, "lr": 6.629630147663823e-07, "epoch": 18.67766776677668, "percentage": 93.39, "elapsed_time": "6:42:06", "remaining_time": "0:28:28", "throughput": 1485.07, "total_tokens": 35830272} {"current_steps": 169785, "total_steps": 181800, "loss": 0.0022, "lr": 6.624140734103029e-07, "epoch": 18.678217821782177, "percentage": 93.39, "elapsed_time": "6:42:07", "remaining_time": "0:28:27", "throughput": 1485.07, "total_tokens": 35831360} {"current_steps": 169790, "total_steps": 181800, "loss": 0.0313, "lr": 6.618653563620736e-07, "epoch": 18.678767876787678, "percentage": 93.39, "elapsed_time": "6:42:08", "remaining_time": "0:28:26", "throughput": 1485.07, "total_tokens": 35832416} {"current_steps": 169795, "total_steps": 181800, "loss": 0.0651, "lr": 6.613168636267569e-07, "epoch": 18.67931793179318, "percentage": 93.4, "elapsed_time": "6:42:09", "remaining_time": "0:28:25", "throughput": 1485.08, "total_tokens": 35833504} {"current_steps": 169800, "total_steps": 181800, "loss": 0.0016, "lr": 6.607685952093989e-07, "epoch": 18.67986798679868, "percentage": 93.4, "elapsed_time": "6:42:09", "remaining_time": "0:28:25", "throughput": 1485.08, "total_tokens": 35834624} {"current_steps": 169805, "total_steps": 181800, "loss": 0.0041, "lr": 6.602205511150594e-07, "epoch": 18.68041804180418, "percentage": 93.4, "elapsed_time": "6:42:10", "remaining_time": "0:28:24", "throughput": 1485.08, "total_tokens": 35835744} {"current_steps": 169810, "total_steps": 181800, "loss": 0.0152, "lr": 6.596727313487872e-07, "epoch": 18.680968096809682, "percentage": 93.4, "elapsed_time": "6:42:11", "remaining_time": "0:28:23", "throughput": 1485.08, "total_tokens": 35836736} {"current_steps": 169815, "total_steps": 181800, "loss": 0.2011, "lr": 6.591251359156308e-07, "epoch": 18.681518151815183, "percentage": 93.41, "elapsed_time": "6:42:11", "remaining_time": "0:28:23", "throughput": 1485.09, "total_tokens": 35837824} {"current_steps": 169820, "total_steps": 181800, "loss": 0.0171, "lr": 6.585777648206392e-07, "epoch": 18.68206820682068, "percentage": 93.41, "elapsed_time": "6:42:12", "remaining_time": "0:28:22", "throughput": 1485.09, "total_tokens": 35838944} {"current_steps": 169825, "total_steps": 181800, "loss": 0.0072, "lr": 6.580306180688556e-07, "epoch": 18.682618261826182, "percentage": 93.41, "elapsed_time": "6:42:13", "remaining_time": "0:28:21", "throughput": 1485.09, "total_tokens": 35840032} {"current_steps": 169830, "total_steps": 181800, "loss": 0.0917, "lr": 6.574836956653257e-07, "epoch": 18.683168316831683, "percentage": 93.42, "elapsed_time": "6:42:13", "remaining_time": "0:28:21", "throughput": 1485.09, "total_tokens": 35841088} {"current_steps": 169835, "total_steps": 181800, "loss": 0.0367, "lr": 6.569369976150847e-07, "epoch": 18.683718371837184, "percentage": 93.42, "elapsed_time": "6:42:14", "remaining_time": "0:28:20", "throughput": 1485.1, "total_tokens": 35842144} {"current_steps": 169840, "total_steps": 181800, "loss": 0.0408, "lr": 6.563905239231755e-07, "epoch": 18.684268426842685, "percentage": 93.42, "elapsed_time": "6:42:15", "remaining_time": "0:28:19", "throughput": 1485.1, "total_tokens": 35843200} {"current_steps": 169845, "total_steps": 181800, "loss": 0.0015, "lr": 6.558442745946358e-07, "epoch": 18.684818481848186, "percentage": 93.42, "elapsed_time": "6:42:15", "remaining_time": "0:28:18", "throughput": 1485.1, "total_tokens": 35844224} {"current_steps": 169850, "total_steps": 181800, "loss": 0.0477, "lr": 6.55298249634495e-07, "epoch": 18.685368536853684, "percentage": 93.43, "elapsed_time": "6:42:16", "remaining_time": "0:28:18", "throughput": 1485.1, "total_tokens": 35845248} {"current_steps": 169855, "total_steps": 181800, "loss": 0.0017, "lr": 6.547524490477907e-07, "epoch": 18.685918591859185, "percentage": 93.43, "elapsed_time": "6:42:17", "remaining_time": "0:28:17", "throughput": 1485.09, "total_tokens": 35846240} {"current_steps": 169860, "total_steps": 181800, "loss": 0.0658, "lr": 6.542068728395523e-07, "epoch": 18.686468646864686, "percentage": 93.43, "elapsed_time": "6:42:18", "remaining_time": "0:28:16", "throughput": 1485.09, "total_tokens": 35847232} {"current_steps": 169865, "total_steps": 181800, "loss": 0.0988, "lr": 6.536615210148033e-07, "epoch": 18.687018701870187, "percentage": 93.44, "elapsed_time": "6:42:18", "remaining_time": "0:28:16", "throughput": 1485.09, "total_tokens": 35848288} {"current_steps": 169870, "total_steps": 181800, "loss": 0.0449, "lr": 6.531163935785734e-07, "epoch": 18.687568756875688, "percentage": 93.44, "elapsed_time": "6:42:19", "remaining_time": "0:28:15", "throughput": 1485.1, "total_tokens": 35849376} {"current_steps": 169875, "total_steps": 181800, "loss": 0.0683, "lr": 6.525714905358888e-07, "epoch": 18.68811881188119, "percentage": 93.44, "elapsed_time": "6:42:20", "remaining_time": "0:28:14", "throughput": 1485.09, "total_tokens": 35850368} {"current_steps": 169880, "total_steps": 181800, "loss": 0.027, "lr": 6.520268118917705e-07, "epoch": 18.68866886688669, "percentage": 93.44, "elapsed_time": "6:42:20", "remaining_time": "0:28:13", "throughput": 1485.09, "total_tokens": 35851392} {"current_steps": 169885, "total_steps": 181800, "loss": 0.0492, "lr": 6.514823576512369e-07, "epoch": 18.689218921892188, "percentage": 93.45, "elapsed_time": "6:42:21", "remaining_time": "0:28:13", "throughput": 1485.09, "total_tokens": 35852416} {"current_steps": 169890, "total_steps": 181800, "loss": 0.0496, "lr": 6.509381278193061e-07, "epoch": 18.68976897689769, "percentage": 93.45, "elapsed_time": "6:42:22", "remaining_time": "0:28:12", "throughput": 1485.1, "total_tokens": 35853504} {"current_steps": 169895, "total_steps": 181800, "loss": 0.0005, "lr": 6.503941224009963e-07, "epoch": 18.69031903190319, "percentage": 93.45, "elapsed_time": "6:42:22", "remaining_time": "0:28:11", "throughput": 1485.1, "total_tokens": 35854560} {"current_steps": 169900, "total_steps": 181800, "loss": 0.0342, "lr": 6.498503414013174e-07, "epoch": 18.69086908690869, "percentage": 93.45, "elapsed_time": "6:42:23", "remaining_time": "0:28:11", "throughput": 1485.1, "total_tokens": 35855616} {"current_steps": 169905, "total_steps": 181800, "loss": 0.0017, "lr": 6.493067848252849e-07, "epoch": 18.691419141914192, "percentage": 93.46, "elapsed_time": "6:42:24", "remaining_time": "0:28:10", "throughput": 1485.1, "total_tokens": 35856640} {"current_steps": 169910, "total_steps": 181800, "loss": 0.0027, "lr": 6.487634526779085e-07, "epoch": 18.691969196919693, "percentage": 93.46, "elapsed_time": "6:42:24", "remaining_time": "0:28:09", "throughput": 1485.1, "total_tokens": 35857664} {"current_steps": 169915, "total_steps": 181800, "loss": 0.001, "lr": 6.482203449641927e-07, "epoch": 18.69251925192519, "percentage": 93.46, "elapsed_time": "6:42:25", "remaining_time": "0:28:08", "throughput": 1485.1, "total_tokens": 35858656} {"current_steps": 169920, "total_steps": 181800, "loss": 0.003, "lr": 6.476774616891473e-07, "epoch": 18.693069306930692, "percentage": 93.47, "elapsed_time": "6:42:26", "remaining_time": "0:28:08", "throughput": 1485.1, "total_tokens": 35859744} {"current_steps": 169925, "total_steps": 181800, "loss": 0.0014, "lr": 6.471348028577712e-07, "epoch": 18.693619361936193, "percentage": 93.47, "elapsed_time": "6:42:27", "remaining_time": "0:28:07", "throughput": 1485.1, "total_tokens": 35860736} {"current_steps": 169930, "total_steps": 181800, "loss": 0.0016, "lr": 6.465923684750658e-07, "epoch": 18.694169416941694, "percentage": 93.47, "elapsed_time": "6:42:27", "remaining_time": "0:28:06", "throughput": 1485.1, "total_tokens": 35861792} {"current_steps": 169935, "total_steps": 181800, "loss": 0.0061, "lr": 6.460501585460382e-07, "epoch": 18.694719471947195, "percentage": 93.47, "elapsed_time": "6:42:28", "remaining_time": "0:28:06", "throughput": 1485.1, "total_tokens": 35862912} {"current_steps": 169940, "total_steps": 181800, "loss": 0.0713, "lr": 6.455081730756763e-07, "epoch": 18.695269526952696, "percentage": 93.48, "elapsed_time": "6:42:29", "remaining_time": "0:28:05", "throughput": 1485.11, "total_tokens": 35864000} {"current_steps": 169945, "total_steps": 181800, "loss": 0.0049, "lr": 6.449664120689813e-07, "epoch": 18.695819581958197, "percentage": 93.48, "elapsed_time": "6:42:29", "remaining_time": "0:28:04", "throughput": 1485.11, "total_tokens": 35865088} {"current_steps": 169950, "total_steps": 181800, "loss": 0.0641, "lr": 6.444248755309413e-07, "epoch": 18.696369636963695, "percentage": 93.48, "elapsed_time": "6:42:30", "remaining_time": "0:28:03", "throughput": 1485.11, "total_tokens": 35866112} {"current_steps": 169955, "total_steps": 181800, "loss": 0.0021, "lr": 6.438835634665491e-07, "epoch": 18.696919691969196, "percentage": 93.48, "elapsed_time": "6:42:31", "remaining_time": "0:28:03", "throughput": 1485.11, "total_tokens": 35867136} {"current_steps": 169960, "total_steps": 181800, "loss": 0.0612, "lr": 6.433424758808009e-07, "epoch": 18.697469746974697, "percentage": 93.49, "elapsed_time": "6:42:31", "remaining_time": "0:28:02", "throughput": 1485.11, "total_tokens": 35868160} {"current_steps": 169965, "total_steps": 181800, "loss": 0.0017, "lr": 6.428016127786735e-07, "epoch": 18.698019801980198, "percentage": 93.49, "elapsed_time": "6:42:32", "remaining_time": "0:28:01", "throughput": 1485.11, "total_tokens": 35869152} {"current_steps": 169970, "total_steps": 181800, "loss": 0.0082, "lr": 6.42260974165157e-07, "epoch": 18.6985698569857, "percentage": 93.49, "elapsed_time": "6:42:33", "remaining_time": "0:28:01", "throughput": 1485.11, "total_tokens": 35870176} {"current_steps": 169975, "total_steps": 181800, "loss": 0.1057, "lr": 6.417205600452336e-07, "epoch": 18.6991199119912, "percentage": 93.5, "elapsed_time": "6:42:33", "remaining_time": "0:28:00", "throughput": 1485.11, "total_tokens": 35871328} {"current_steps": 169980, "total_steps": 181800, "loss": 0.0027, "lr": 6.411803704238828e-07, "epoch": 18.6996699669967, "percentage": 93.5, "elapsed_time": "6:42:34", "remaining_time": "0:27:59", "throughput": 1485.11, "total_tokens": 35872288} {"current_steps": 169985, "total_steps": 181800, "loss": 0.0097, "lr": 6.406404053060838e-07, "epoch": 18.7002200220022, "percentage": 93.5, "elapsed_time": "6:42:35", "remaining_time": "0:27:58", "throughput": 1485.11, "total_tokens": 35873376} {"current_steps": 169990, "total_steps": 181800, "loss": 0.0029, "lr": 6.401006646968133e-07, "epoch": 18.7007700770077, "percentage": 93.5, "elapsed_time": "6:42:36", "remaining_time": "0:27:58", "throughput": 1485.12, "total_tokens": 35874528} {"current_steps": 169995, "total_steps": 181800, "loss": 0.0364, "lr": 6.395611486010478e-07, "epoch": 18.7013201320132, "percentage": 93.51, "elapsed_time": "6:42:36", "remaining_time": "0:27:57", "throughput": 1485.12, "total_tokens": 35875552} {"current_steps": 170000, "total_steps": 181800, "loss": 0.0429, "lr": 6.390218570237527e-07, "epoch": 18.701870187018702, "percentage": 93.51, "elapsed_time": "6:42:37", "remaining_time": "0:27:56", "throughput": 1485.12, "total_tokens": 35876640} {"current_steps": 170005, "total_steps": 181800, "loss": 0.2051, "lr": 6.384827899699103e-07, "epoch": 18.702420242024203, "percentage": 93.51, "elapsed_time": "6:42:38", "remaining_time": "0:27:56", "throughput": 1485.12, "total_tokens": 35877696} {"current_steps": 170010, "total_steps": 181800, "loss": 0.0465, "lr": 6.379439474444776e-07, "epoch": 18.702970297029704, "percentage": 93.51, "elapsed_time": "6:42:38", "remaining_time": "0:27:55", "throughput": 1485.12, "total_tokens": 35878720} {"current_steps": 170015, "total_steps": 181800, "loss": 0.0159, "lr": 6.374053294524257e-07, "epoch": 18.703520352035202, "percentage": 93.52, "elapsed_time": "6:42:39", "remaining_time": "0:27:54", "throughput": 1485.12, "total_tokens": 35879808} {"current_steps": 170020, "total_steps": 181800, "loss": 0.0018, "lr": 6.368669359987228e-07, "epoch": 18.704070407040703, "percentage": 93.52, "elapsed_time": "6:42:40", "remaining_time": "0:27:53", "throughput": 1485.12, "total_tokens": 35880768} {"current_steps": 170025, "total_steps": 181800, "loss": 0.0087, "lr": 6.363287670883233e-07, "epoch": 18.704620462046204, "percentage": 93.52, "elapsed_time": "6:42:40", "remaining_time": "0:27:53", "throughput": 1485.12, "total_tokens": 35881824} {"current_steps": 170030, "total_steps": 181800, "loss": 0.0021, "lr": 6.357908227261928e-07, "epoch": 18.705170517051705, "percentage": 93.53, "elapsed_time": "6:42:41", "remaining_time": "0:27:52", "throughput": 1485.12, "total_tokens": 35882848} {"current_steps": 170035, "total_steps": 181800, "loss": 0.0011, "lr": 6.352531029172881e-07, "epoch": 18.705720572057206, "percentage": 93.53, "elapsed_time": "6:42:42", "remaining_time": "0:27:51", "throughput": 1485.13, "total_tokens": 35883936} {"current_steps": 170040, "total_steps": 181800, "loss": 0.0074, "lr": 6.347156076665584e-07, "epoch": 18.706270627062707, "percentage": 93.53, "elapsed_time": "6:42:42", "remaining_time": "0:27:51", "throughput": 1485.13, "total_tokens": 35885056} {"current_steps": 170045, "total_steps": 181800, "loss": 0.0489, "lr": 6.341783369789661e-07, "epoch": 18.706820682068205, "percentage": 93.53, "elapsed_time": "6:42:43", "remaining_time": "0:27:50", "throughput": 1485.13, "total_tokens": 35886112} {"current_steps": 170050, "total_steps": 181800, "loss": 0.1343, "lr": 6.336412908594602e-07, "epoch": 18.707370737073706, "percentage": 93.54, "elapsed_time": "6:42:44", "remaining_time": "0:27:49", "throughput": 1485.13, "total_tokens": 35887168} {"current_steps": 170055, "total_steps": 181800, "loss": 0.0013, "lr": 6.331044693129923e-07, "epoch": 18.707920792079207, "percentage": 93.54, "elapsed_time": "6:42:44", "remaining_time": "0:27:48", "throughput": 1485.13, "total_tokens": 35888224} {"current_steps": 170060, "total_steps": 181800, "loss": 0.0015, "lr": 6.325678723445083e-07, "epoch": 18.70847084708471, "percentage": 93.54, "elapsed_time": "6:42:45", "remaining_time": "0:27:48", "throughput": 1485.13, "total_tokens": 35889248} {"current_steps": 170065, "total_steps": 181800, "loss": 0.1264, "lr": 6.320314999589516e-07, "epoch": 18.70902090209021, "percentage": 93.55, "elapsed_time": "6:42:46", "remaining_time": "0:27:47", "throughput": 1485.14, "total_tokens": 35890304} {"current_steps": 170070, "total_steps": 181800, "loss": 0.0011, "lr": 6.314953521612682e-07, "epoch": 18.70957095709571, "percentage": 93.55, "elapsed_time": "6:42:47", "remaining_time": "0:27:46", "throughput": 1485.14, "total_tokens": 35891360} {"current_steps": 170075, "total_steps": 181800, "loss": 0.0053, "lr": 6.309594289564014e-07, "epoch": 18.71012101210121, "percentage": 93.55, "elapsed_time": "6:42:47", "remaining_time": "0:27:46", "throughput": 1485.14, "total_tokens": 35892480} {"current_steps": 170080, "total_steps": 181800, "loss": 0.0034, "lr": 6.304237303492833e-07, "epoch": 18.71067106710671, "percentage": 93.55, "elapsed_time": "6:42:48", "remaining_time": "0:27:45", "throughput": 1485.15, "total_tokens": 35893600} {"current_steps": 170085, "total_steps": 181800, "loss": 0.1199, "lr": 6.298882563448599e-07, "epoch": 18.71122112211221, "percentage": 93.56, "elapsed_time": "6:42:49", "remaining_time": "0:27:44", "throughput": 1485.15, "total_tokens": 35894656} {"current_steps": 170090, "total_steps": 181800, "loss": 0.0193, "lr": 6.293530069480607e-07, "epoch": 18.71177117711771, "percentage": 93.56, "elapsed_time": "6:42:49", "remaining_time": "0:27:43", "throughput": 1485.15, "total_tokens": 35895744} {"current_steps": 170095, "total_steps": 181800, "loss": 0.0077, "lr": 6.288179821638235e-07, "epoch": 18.712321232123212, "percentage": 93.56, "elapsed_time": "6:42:50", "remaining_time": "0:27:43", "throughput": 1485.15, "total_tokens": 35896864} {"current_steps": 170100, "total_steps": 181800, "loss": 0.0024, "lr": 6.282831819970747e-07, "epoch": 18.712871287128714, "percentage": 93.56, "elapsed_time": "6:42:51", "remaining_time": "0:27:42", "throughput": 1485.16, "total_tokens": 35897984} {"current_steps": 170105, "total_steps": 181800, "loss": 0.0409, "lr": 6.27748606452741e-07, "epoch": 18.713421342134215, "percentage": 93.57, "elapsed_time": "6:42:51", "remaining_time": "0:27:41", "throughput": 1485.16, "total_tokens": 35899040} {"current_steps": 170110, "total_steps": 181800, "loss": 0.0618, "lr": 6.272142555357601e-07, "epoch": 18.713971397139716, "percentage": 93.57, "elapsed_time": "6:42:52", "remaining_time": "0:27:41", "throughput": 1485.16, "total_tokens": 35900064} {"current_steps": 170115, "total_steps": 181800, "loss": 0.0411, "lr": 6.266801292510449e-07, "epoch": 18.714521452145213, "percentage": 93.57, "elapsed_time": "6:42:53", "remaining_time": "0:27:40", "throughput": 1485.16, "total_tokens": 35901152} {"current_steps": 170120, "total_steps": 181800, "loss": 0.1199, "lr": 6.261462276035274e-07, "epoch": 18.715071507150714, "percentage": 93.58, "elapsed_time": "6:42:53", "remaining_time": "0:27:39", "throughput": 1485.16, "total_tokens": 35902208} {"current_steps": 170125, "total_steps": 181800, "loss": 0.0178, "lr": 6.256125505981258e-07, "epoch": 18.715621562156215, "percentage": 93.58, "elapsed_time": "6:42:54", "remaining_time": "0:27:39", "throughput": 1485.16, "total_tokens": 35903264} {"current_steps": 170130, "total_steps": 181800, "loss": 0.0019, "lr": 6.250790982397503e-07, "epoch": 18.716171617161717, "percentage": 93.58, "elapsed_time": "6:42:55", "remaining_time": "0:27:38", "throughput": 1485.17, "total_tokens": 35904320} {"current_steps": 170135, "total_steps": 181800, "loss": 0.1327, "lr": 6.245458705333301e-07, "epoch": 18.716721672167218, "percentage": 93.58, "elapsed_time": "6:42:55", "remaining_time": "0:27:37", "throughput": 1485.17, "total_tokens": 35905408} {"current_steps": 170140, "total_steps": 181800, "loss": 0.0049, "lr": 6.240128674837726e-07, "epoch": 18.71727172717272, "percentage": 93.59, "elapsed_time": "6:42:56", "remaining_time": "0:27:36", "throughput": 1485.17, "total_tokens": 35906464} {"current_steps": 170145, "total_steps": 181800, "loss": 0.0363, "lr": 6.23480089095993e-07, "epoch": 18.717821782178216, "percentage": 93.59, "elapsed_time": "6:42:57", "remaining_time": "0:27:36", "throughput": 1485.17, "total_tokens": 35907552} {"current_steps": 170150, "total_steps": 181800, "loss": 0.0243, "lr": 6.229475353749015e-07, "epoch": 18.718371837183717, "percentage": 93.59, "elapsed_time": "6:42:58", "remaining_time": "0:27:35", "throughput": 1485.18, "total_tokens": 35908672} {"current_steps": 170155, "total_steps": 181800, "loss": 0.0031, "lr": 6.224152063253996e-07, "epoch": 18.71892189218922, "percentage": 93.59, "elapsed_time": "6:42:58", "remaining_time": "0:27:34", "throughput": 1485.18, "total_tokens": 35909760} {"current_steps": 170160, "total_steps": 181800, "loss": 0.0721, "lr": 6.218831019524029e-07, "epoch": 18.71947194719472, "percentage": 93.6, "elapsed_time": "6:42:59", "remaining_time": "0:27:34", "throughput": 1485.18, "total_tokens": 35910848} {"current_steps": 170165, "total_steps": 181800, "loss": 0.005, "lr": 6.213512222608103e-07, "epoch": 18.72002200220022, "percentage": 93.6, "elapsed_time": "6:43:00", "remaining_time": "0:27:33", "throughput": 1485.18, "total_tokens": 35911872} {"current_steps": 170170, "total_steps": 181800, "loss": 0.0032, "lr": 6.20819567255529e-07, "epoch": 18.72057205720572, "percentage": 93.6, "elapsed_time": "6:43:00", "remaining_time": "0:27:32", "throughput": 1485.18, "total_tokens": 35912896} {"current_steps": 170175, "total_steps": 181800, "loss": 0.0027, "lr": 6.202881369414549e-07, "epoch": 18.721122112211223, "percentage": 93.61, "elapsed_time": "6:43:01", "remaining_time": "0:27:31", "throughput": 1485.18, "total_tokens": 35913984} {"current_steps": 170180, "total_steps": 181800, "loss": 0.0072, "lr": 6.197569313234841e-07, "epoch": 18.72167216721672, "percentage": 93.61, "elapsed_time": "6:43:02", "remaining_time": "0:27:31", "throughput": 1485.19, "total_tokens": 35915072} {"current_steps": 170185, "total_steps": 181800, "loss": 0.0027, "lr": 6.192259504065156e-07, "epoch": 18.72222222222222, "percentage": 93.61, "elapsed_time": "6:43:02", "remaining_time": "0:27:30", "throughput": 1485.18, "total_tokens": 35916032} {"current_steps": 170190, "total_steps": 181800, "loss": 0.0013, "lr": 6.1869519419544e-07, "epoch": 18.722772277227723, "percentage": 93.61, "elapsed_time": "6:43:03", "remaining_time": "0:27:29", "throughput": 1485.18, "total_tokens": 35917056} {"current_steps": 170195, "total_steps": 181800, "loss": 0.01, "lr": 6.181646626951559e-07, "epoch": 18.723322332233224, "percentage": 93.62, "elapsed_time": "6:43:04", "remaining_time": "0:27:29", "throughput": 1485.18, "total_tokens": 35918112} {"current_steps": 170200, "total_steps": 181800, "loss": 0.1027, "lr": 6.176343559105485e-07, "epoch": 18.723872387238725, "percentage": 93.62, "elapsed_time": "6:43:04", "remaining_time": "0:27:28", "throughput": 1485.18, "total_tokens": 35919136} {"current_steps": 170205, "total_steps": 181800, "loss": 0.0107, "lr": 6.171042738465027e-07, "epoch": 18.724422442244226, "percentage": 93.62, "elapsed_time": "6:43:05", "remaining_time": "0:27:27", "throughput": 1485.19, "total_tokens": 35920192} {"current_steps": 170210, "total_steps": 181800, "loss": 0.1005, "lr": 6.16574416507909e-07, "epoch": 18.724972497249723, "percentage": 93.62, "elapsed_time": "6:43:06", "remaining_time": "0:27:26", "throughput": 1485.19, "total_tokens": 35921280} {"current_steps": 170215, "total_steps": 181800, "loss": 0.0519, "lr": 6.16044783899647e-07, "epoch": 18.725522552255224, "percentage": 93.63, "elapsed_time": "6:43:07", "remaining_time": "0:27:26", "throughput": 1485.19, "total_tokens": 35922400} {"current_steps": 170220, "total_steps": 181800, "loss": 0.0032, "lr": 6.155153760265986e-07, "epoch": 18.726072607260726, "percentage": 93.63, "elapsed_time": "6:43:07", "remaining_time": "0:27:25", "throughput": 1485.19, "total_tokens": 35923456} {"current_steps": 170225, "total_steps": 181800, "loss": 0.0024, "lr": 6.149861928936463e-07, "epoch": 18.726622662266227, "percentage": 93.63, "elapsed_time": "6:43:08", "remaining_time": "0:27:24", "throughput": 1485.2, "total_tokens": 35924544} {"current_steps": 170230, "total_steps": 181800, "loss": 0.0022, "lr": 6.144572345056637e-07, "epoch": 18.727172717271728, "percentage": 93.64, "elapsed_time": "6:43:09", "remaining_time": "0:27:24", "throughput": 1485.2, "total_tokens": 35925600} {"current_steps": 170235, "total_steps": 181800, "loss": 0.0435, "lr": 6.139285008675305e-07, "epoch": 18.72772277227723, "percentage": 93.64, "elapsed_time": "6:43:09", "remaining_time": "0:27:23", "throughput": 1485.2, "total_tokens": 35926656} {"current_steps": 170240, "total_steps": 181800, "loss": 0.0011, "lr": 6.133999919841121e-07, "epoch": 18.72827282728273, "percentage": 93.64, "elapsed_time": "6:43:10", "remaining_time": "0:27:22", "throughput": 1485.2, "total_tokens": 35927712} {"current_steps": 170245, "total_steps": 181800, "loss": 0.0017, "lr": 6.12871707860288e-07, "epoch": 18.728822882288227, "percentage": 93.64, "elapsed_time": "6:43:11", "remaining_time": "0:27:21", "throughput": 1485.2, "total_tokens": 35928736} {"current_steps": 170250, "total_steps": 181800, "loss": 0.0079, "lr": 6.12343648500921e-07, "epoch": 18.72937293729373, "percentage": 93.65, "elapsed_time": "6:43:11", "remaining_time": "0:27:21", "throughput": 1485.2, "total_tokens": 35929760} {"current_steps": 170255, "total_steps": 181800, "loss": 0.0414, "lr": 6.118158139108821e-07, "epoch": 18.72992299229923, "percentage": 93.65, "elapsed_time": "6:43:12", "remaining_time": "0:27:20", "throughput": 1485.2, "total_tokens": 35930912} {"current_steps": 170260, "total_steps": 181800, "loss": 0.0084, "lr": 6.112882040950341e-07, "epoch": 18.73047304730473, "percentage": 93.65, "elapsed_time": "6:43:13", "remaining_time": "0:27:19", "throughput": 1485.21, "total_tokens": 35931936} {"current_steps": 170265, "total_steps": 181800, "loss": 0.0011, "lr": 6.107608190582398e-07, "epoch": 18.731023102310232, "percentage": 93.66, "elapsed_time": "6:43:13", "remaining_time": "0:27:19", "throughput": 1485.21, "total_tokens": 35933024} {"current_steps": 170270, "total_steps": 181800, "loss": 0.0021, "lr": 6.102336588053593e-07, "epoch": 18.731573157315733, "percentage": 93.66, "elapsed_time": "6:43:14", "remaining_time": "0:27:18", "throughput": 1485.21, "total_tokens": 35934048} {"current_steps": 170275, "total_steps": 181800, "loss": 0.0156, "lr": 6.097067233412496e-07, "epoch": 18.73212321232123, "percentage": 93.66, "elapsed_time": "6:43:15", "remaining_time": "0:27:17", "throughput": 1485.21, "total_tokens": 35935104} {"current_steps": 170280, "total_steps": 181800, "loss": 0.0713, "lr": 6.091800126707708e-07, "epoch": 18.73267326732673, "percentage": 93.66, "elapsed_time": "6:43:16", "remaining_time": "0:27:16", "throughput": 1485.21, "total_tokens": 35936160} {"current_steps": 170285, "total_steps": 181800, "loss": 0.0417, "lr": 6.086535267987776e-07, "epoch": 18.733223322332233, "percentage": 93.67, "elapsed_time": "6:43:16", "remaining_time": "0:27:16", "throughput": 1485.21, "total_tokens": 35937248} {"current_steps": 170290, "total_steps": 181800, "loss": 0.0028, "lr": 6.081272657301213e-07, "epoch": 18.733773377337734, "percentage": 93.67, "elapsed_time": "6:43:17", "remaining_time": "0:27:15", "throughput": 1485.21, "total_tokens": 35938304} {"current_steps": 170295, "total_steps": 181800, "loss": 0.0713, "lr": 6.076012294696509e-07, "epoch": 18.734323432343235, "percentage": 93.67, "elapsed_time": "6:43:18", "remaining_time": "0:27:14", "throughput": 1485.21, "total_tokens": 35939296} {"current_steps": 170300, "total_steps": 181800, "loss": 0.0098, "lr": 6.070754180222154e-07, "epoch": 18.734873487348736, "percentage": 93.67, "elapsed_time": "6:43:18", "remaining_time": "0:27:14", "throughput": 1485.22, "total_tokens": 35940384} {"current_steps": 170305, "total_steps": 181800, "loss": 0.0026, "lr": 6.065498313926582e-07, "epoch": 18.735423542354237, "percentage": 93.68, "elapsed_time": "6:43:19", "remaining_time": "0:27:13", "throughput": 1485.22, "total_tokens": 35941408} {"current_steps": 170310, "total_steps": 181800, "loss": 0.0061, "lr": 6.06024469585828e-07, "epoch": 18.735973597359735, "percentage": 93.68, "elapsed_time": "6:43:20", "remaining_time": "0:27:12", "throughput": 1485.22, "total_tokens": 35942496} {"current_steps": 170315, "total_steps": 181800, "loss": 0.0066, "lr": 6.054993326065656e-07, "epoch": 18.736523652365236, "percentage": 93.68, "elapsed_time": "6:43:20", "remaining_time": "0:27:11", "throughput": 1485.22, "total_tokens": 35943584} {"current_steps": 170320, "total_steps": 181800, "loss": 0.046, "lr": 6.049744204597085e-07, "epoch": 18.737073707370737, "percentage": 93.69, "elapsed_time": "6:43:21", "remaining_time": "0:27:11", "throughput": 1485.22, "total_tokens": 35944576} {"current_steps": 170325, "total_steps": 181800, "loss": 0.0024, "lr": 6.044497331501004e-07, "epoch": 18.737623762376238, "percentage": 93.69, "elapsed_time": "6:43:22", "remaining_time": "0:27:10", "throughput": 1485.22, "total_tokens": 35945696} {"current_steps": 170330, "total_steps": 181800, "loss": 0.043, "lr": 6.039252706825677e-07, "epoch": 18.73817381738174, "percentage": 93.69, "elapsed_time": "6:43:22", "remaining_time": "0:27:09", "throughput": 1485.22, "total_tokens": 35946752} {"current_steps": 170335, "total_steps": 181800, "loss": 0.0048, "lr": 6.034010330619511e-07, "epoch": 18.73872387238724, "percentage": 93.69, "elapsed_time": "6:43:23", "remaining_time": "0:27:09", "throughput": 1485.23, "total_tokens": 35947840} {"current_steps": 170340, "total_steps": 181800, "loss": 0.0768, "lr": 6.028770202930828e-07, "epoch": 18.739273927392738, "percentage": 93.7, "elapsed_time": "6:43:24", "remaining_time": "0:27:08", "throughput": 1485.23, "total_tokens": 35948896} {"current_steps": 170345, "total_steps": 181800, "loss": 0.0033, "lr": 6.023532323807867e-07, "epoch": 18.73982398239824, "percentage": 93.7, "elapsed_time": "6:43:25", "remaining_time": "0:27:07", "throughput": 1485.23, "total_tokens": 35949920} {"current_steps": 170350, "total_steps": 181800, "loss": 0.002, "lr": 6.01829669329898e-07, "epoch": 18.74037403740374, "percentage": 93.7, "elapsed_time": "6:43:25", "remaining_time": "0:27:06", "throughput": 1485.23, "total_tokens": 35950912} {"current_steps": 170355, "total_steps": 181800, "loss": 0.0047, "lr": 6.013063311452321e-07, "epoch": 18.74092409240924, "percentage": 93.7, "elapsed_time": "6:43:26", "remaining_time": "0:27:06", "throughput": 1485.23, "total_tokens": 35952032} {"current_steps": 170360, "total_steps": 181800, "loss": 0.0081, "lr": 6.007832178316242e-07, "epoch": 18.741474147414742, "percentage": 93.71, "elapsed_time": "6:43:27", "remaining_time": "0:27:05", "throughput": 1485.23, "total_tokens": 35953056} {"current_steps": 170365, "total_steps": 181800, "loss": 0.0471, "lr": 6.002603293938841e-07, "epoch": 18.742024202420243, "percentage": 93.71, "elapsed_time": "6:43:27", "remaining_time": "0:27:04", "throughput": 1485.23, "total_tokens": 35954048} {"current_steps": 170370, "total_steps": 181800, "loss": 0.0025, "lr": 5.997376658368387e-07, "epoch": 18.742574257425744, "percentage": 93.71, "elapsed_time": "6:43:28", "remaining_time": "0:27:04", "throughput": 1485.23, "total_tokens": 35955136} {"current_steps": 170375, "total_steps": 181800, "loss": 0.002, "lr": 5.992152271653062e-07, "epoch": 18.74312431243124, "percentage": 93.72, "elapsed_time": "6:43:29", "remaining_time": "0:27:03", "throughput": 1485.23, "total_tokens": 35956160} {"current_steps": 170380, "total_steps": 181800, "loss": 0.0366, "lr": 5.98693013384094e-07, "epoch": 18.743674367436743, "percentage": 93.72, "elapsed_time": "6:43:29", "remaining_time": "0:27:02", "throughput": 1485.23, "total_tokens": 35957152} {"current_steps": 170385, "total_steps": 181800, "loss": 0.0058, "lr": 5.981710244980204e-07, "epoch": 18.744224422442244, "percentage": 93.72, "elapsed_time": "6:43:30", "remaining_time": "0:27:01", "throughput": 1485.23, "total_tokens": 35958240} {"current_steps": 170390, "total_steps": 181800, "loss": 0.0059, "lr": 5.976492605118955e-07, "epoch": 18.744774477447745, "percentage": 93.72, "elapsed_time": "6:43:31", "remaining_time": "0:27:01", "throughput": 1485.23, "total_tokens": 35959296} {"current_steps": 170395, "total_steps": 181800, "loss": 0.062, "lr": 5.971277214305266e-07, "epoch": 18.745324532453246, "percentage": 93.73, "elapsed_time": "6:43:31", "remaining_time": "0:27:00", "throughput": 1485.24, "total_tokens": 35960352} {"current_steps": 170400, "total_steps": 181800, "loss": 0.0475, "lr": 5.966064072587235e-07, "epoch": 18.745874587458747, "percentage": 93.73, "elapsed_time": "6:43:32", "remaining_time": "0:26:59", "throughput": 1485.24, "total_tokens": 35961408} {"current_steps": 170405, "total_steps": 181800, "loss": 0.0171, "lr": 5.960853180012882e-07, "epoch": 18.746424642464248, "percentage": 93.73, "elapsed_time": "6:43:33", "remaining_time": "0:26:59", "throughput": 1485.23, "total_tokens": 35962400} {"current_steps": 170410, "total_steps": 181800, "loss": 0.0065, "lr": 5.955644536630278e-07, "epoch": 18.746974697469746, "percentage": 93.73, "elapsed_time": "6:43:33", "remaining_time": "0:26:58", "throughput": 1485.23, "total_tokens": 35963424} {"current_steps": 170415, "total_steps": 181800, "loss": 0.067, "lr": 5.950438142487386e-07, "epoch": 18.747524752475247, "percentage": 93.74, "elapsed_time": "6:43:34", "remaining_time": "0:26:57", "throughput": 1485.23, "total_tokens": 35964448} {"current_steps": 170420, "total_steps": 181800, "loss": 0.0096, "lr": 5.945233997632165e-07, "epoch": 18.748074807480748, "percentage": 93.74, "elapsed_time": "6:43:35", "remaining_time": "0:26:57", "throughput": 1485.24, "total_tokens": 35965504} {"current_steps": 170425, "total_steps": 181800, "loss": 0.0013, "lr": 5.940032102112636e-07, "epoch": 18.74862486248625, "percentage": 93.74, "elapsed_time": "6:43:36", "remaining_time": "0:26:56", "throughput": 1485.23, "total_tokens": 35966496} {"current_steps": 170430, "total_steps": 181800, "loss": 0.0204, "lr": 5.934832455976702e-07, "epoch": 18.74917491749175, "percentage": 93.75, "elapsed_time": "6:43:36", "remaining_time": "0:26:55", "throughput": 1485.23, "total_tokens": 35967488} {"current_steps": 170435, "total_steps": 181800, "loss": 0.001, "lr": 5.929635059272326e-07, "epoch": 18.74972497249725, "percentage": 93.75, "elapsed_time": "6:43:37", "remaining_time": "0:26:54", "throughput": 1485.24, "total_tokens": 35968576} {"current_steps": 170440, "total_steps": 181800, "loss": 0.0803, "lr": 5.924439912047386e-07, "epoch": 18.75027502750275, "percentage": 93.75, "elapsed_time": "6:43:38", "remaining_time": "0:26:54", "throughput": 1485.23, "total_tokens": 35969568} {"current_steps": 170445, "total_steps": 181800, "loss": 0.0612, "lr": 5.919247014349733e-07, "epoch": 18.75082508250825, "percentage": 93.75, "elapsed_time": "6:43:38", "remaining_time": "0:26:53", "throughput": 1485.24, "total_tokens": 35970656} {"current_steps": 170450, "total_steps": 181800, "loss": 0.0151, "lr": 5.914056366227272e-07, "epoch": 18.75137513751375, "percentage": 93.76, "elapsed_time": "6:43:39", "remaining_time": "0:26:52", "throughput": 1485.24, "total_tokens": 35971712} {"current_steps": 170455, "total_steps": 181800, "loss": 0.0023, "lr": 5.908867967727854e-07, "epoch": 18.751925192519252, "percentage": 93.76, "elapsed_time": "6:43:40", "remaining_time": "0:26:52", "throughput": 1485.24, "total_tokens": 35972832} {"current_steps": 170460, "total_steps": 181800, "loss": 0.0641, "lr": 5.903681818899249e-07, "epoch": 18.752475247524753, "percentage": 93.76, "elapsed_time": "6:43:40", "remaining_time": "0:26:51", "throughput": 1485.24, "total_tokens": 35973856} {"current_steps": 170465, "total_steps": 181800, "loss": 0.004, "lr": 5.898497919789303e-07, "epoch": 18.753025302530254, "percentage": 93.77, "elapsed_time": "6:43:41", "remaining_time": "0:26:50", "throughput": 1485.24, "total_tokens": 35974880} {"current_steps": 170470, "total_steps": 181800, "loss": 0.0805, "lr": 5.893316270445759e-07, "epoch": 18.753575357535752, "percentage": 93.77, "elapsed_time": "6:43:42", "remaining_time": "0:26:49", "throughput": 1485.25, "total_tokens": 35976032} {"current_steps": 170475, "total_steps": 181800, "loss": 0.0009, "lr": 5.888136870916383e-07, "epoch": 18.754125412541253, "percentage": 93.77, "elapsed_time": "6:43:42", "remaining_time": "0:26:49", "throughput": 1485.25, "total_tokens": 35977120} {"current_steps": 170480, "total_steps": 181800, "loss": 0.003, "lr": 5.882959721248916e-07, "epoch": 18.754675467546754, "percentage": 93.77, "elapsed_time": "6:43:43", "remaining_time": "0:26:48", "throughput": 1485.25, "total_tokens": 35978176} {"current_steps": 170485, "total_steps": 181800, "loss": 0.0037, "lr": 5.877784821491067e-07, "epoch": 18.755225522552255, "percentage": 93.78, "elapsed_time": "6:43:44", "remaining_time": "0:26:47", "throughput": 1485.25, "total_tokens": 35979264} {"current_steps": 170490, "total_steps": 181800, "loss": 0.0006, "lr": 5.872612171690522e-07, "epoch": 18.755775577557756, "percentage": 93.78, "elapsed_time": "6:43:45", "remaining_time": "0:26:47", "throughput": 1485.26, "total_tokens": 35980352} {"current_steps": 170495, "total_steps": 181800, "loss": 0.0005, "lr": 5.867441771894994e-07, "epoch": 18.756325632563257, "percentage": 93.78, "elapsed_time": "6:43:45", "remaining_time": "0:26:46", "throughput": 1485.26, "total_tokens": 35981440} {"current_steps": 170500, "total_steps": 181800, "loss": 0.0385, "lr": 5.862273622152109e-07, "epoch": 18.75687568756876, "percentage": 93.78, "elapsed_time": "6:43:46", "remaining_time": "0:26:45", "throughput": 1485.26, "total_tokens": 35982464} {"current_steps": 170505, "total_steps": 181800, "loss": 0.1049, "lr": 5.857107722509469e-07, "epoch": 18.757425742574256, "percentage": 93.79, "elapsed_time": "6:43:47", "remaining_time": "0:26:44", "throughput": 1485.26, "total_tokens": 35983456} {"current_steps": 170510, "total_steps": 181800, "loss": 0.0817, "lr": 5.851944073014703e-07, "epoch": 18.757975797579757, "percentage": 93.79, "elapsed_time": "6:43:47", "remaining_time": "0:26:44", "throughput": 1485.26, "total_tokens": 35984448} {"current_steps": 170515, "total_steps": 181800, "loss": 0.0357, "lr": 5.846782673715467e-07, "epoch": 18.758525852585258, "percentage": 93.79, "elapsed_time": "6:43:48", "remaining_time": "0:26:43", "throughput": 1485.26, "total_tokens": 35985536} {"current_steps": 170520, "total_steps": 181800, "loss": 0.0058, "lr": 5.84162352465925e-07, "epoch": 18.75907590759076, "percentage": 93.8, "elapsed_time": "6:43:49", "remaining_time": "0:26:42", "throughput": 1485.26, "total_tokens": 35986624} {"current_steps": 170525, "total_steps": 181800, "loss": 0.0038, "lr": 5.836466625893655e-07, "epoch": 18.75962596259626, "percentage": 93.8, "elapsed_time": "6:43:49", "remaining_time": "0:26:42", "throughput": 1485.26, "total_tokens": 35987712} {"current_steps": 170530, "total_steps": 181800, "loss": 0.1355, "lr": 5.831311977466169e-07, "epoch": 18.76017601760176, "percentage": 93.8, "elapsed_time": "6:43:50", "remaining_time": "0:26:41", "throughput": 1485.27, "total_tokens": 35988800} {"current_steps": 170535, "total_steps": 181800, "loss": 0.0061, "lr": 5.826159579424312e-07, "epoch": 18.760726072607262, "percentage": 93.8, "elapsed_time": "6:43:51", "remaining_time": "0:26:40", "throughput": 1485.27, "total_tokens": 35989824} {"current_steps": 170540, "total_steps": 181800, "loss": 0.0396, "lr": 5.821009431815572e-07, "epoch": 18.76127612761276, "percentage": 93.81, "elapsed_time": "6:43:51", "remaining_time": "0:26:39", "throughput": 1485.27, "total_tokens": 35990944} {"current_steps": 170545, "total_steps": 181800, "loss": 0.0015, "lr": 5.815861534687411e-07, "epoch": 18.76182618261826, "percentage": 93.81, "elapsed_time": "6:43:52", "remaining_time": "0:26:39", "throughput": 1485.27, "total_tokens": 35991936} {"current_steps": 170550, "total_steps": 181800, "loss": 0.0126, "lr": 5.81071588808732e-07, "epoch": 18.762376237623762, "percentage": 93.81, "elapsed_time": "6:43:53", "remaining_time": "0:26:38", "throughput": 1485.27, "total_tokens": 35992960} {"current_steps": 170555, "total_steps": 181800, "loss": 0.0134, "lr": 5.805572492062678e-07, "epoch": 18.762926292629263, "percentage": 93.81, "elapsed_time": "6:43:53", "remaining_time": "0:26:37", "throughput": 1485.27, "total_tokens": 35994016} {"current_steps": 170560, "total_steps": 181800, "loss": 0.0017, "lr": 5.800431346660862e-07, "epoch": 18.763476347634764, "percentage": 93.82, "elapsed_time": "6:43:54", "remaining_time": "0:26:37", "throughput": 1485.27, "total_tokens": 35995072} {"current_steps": 170565, "total_steps": 181800, "loss": 0.0013, "lr": 5.795292451929307e-07, "epoch": 18.764026402640265, "percentage": 93.82, "elapsed_time": "6:43:55", "remaining_time": "0:26:36", "throughput": 1485.28, "total_tokens": 35996160} {"current_steps": 170570, "total_steps": 181800, "loss": 0.0818, "lr": 5.790155807915365e-07, "epoch": 18.764576457645763, "percentage": 93.82, "elapsed_time": "6:43:56", "remaining_time": "0:26:35", "throughput": 1485.28, "total_tokens": 35997184} {"current_steps": 170575, "total_steps": 181800, "loss": 0.0016, "lr": 5.785021414666413e-07, "epoch": 18.765126512651264, "percentage": 93.83, "elapsed_time": "6:43:56", "remaining_time": "0:26:34", "throughput": 1485.28, "total_tokens": 35998240} {"current_steps": 170580, "total_steps": 181800, "loss": 0.0535, "lr": 5.779889272229693e-07, "epoch": 18.765676567656765, "percentage": 93.83, "elapsed_time": "6:43:57", "remaining_time": "0:26:34", "throughput": 1485.28, "total_tokens": 35999264} {"current_steps": 170585, "total_steps": 181800, "loss": 0.0035, "lr": 5.774759380652556e-07, "epoch": 18.766226622662266, "percentage": 93.83, "elapsed_time": "6:43:58", "remaining_time": "0:26:33", "throughput": 1485.28, "total_tokens": 36000320} {"current_steps": 170590, "total_steps": 181800, "loss": 0.0436, "lr": 5.769631739982267e-07, "epoch": 18.766776677667767, "percentage": 93.83, "elapsed_time": "6:43:58", "remaining_time": "0:26:32", "throughput": 1485.28, "total_tokens": 36001440} {"current_steps": 170595, "total_steps": 181800, "loss": 0.1246, "lr": 5.764506350266096e-07, "epoch": 18.76732673267327, "percentage": 93.84, "elapsed_time": "6:43:59", "remaining_time": "0:26:32", "throughput": 1485.28, "total_tokens": 36002464} {"current_steps": 170600, "total_steps": 181800, "loss": 0.0124, "lr": 5.759383211551256e-07, "epoch": 18.76787678767877, "percentage": 93.84, "elapsed_time": "6:44:00", "remaining_time": "0:26:31", "throughput": 1485.28, "total_tokens": 36003520} {"current_steps": 170605, "total_steps": 181800, "loss": 0.0019, "lr": 5.754262323885012e-07, "epoch": 18.768426842684267, "percentage": 93.84, "elapsed_time": "6:44:00", "remaining_time": "0:26:30", "throughput": 1485.29, "total_tokens": 36004608} {"current_steps": 170610, "total_steps": 181800, "loss": 0.0114, "lr": 5.749143687314495e-07, "epoch": 18.768976897689768, "percentage": 93.84, "elapsed_time": "6:44:01", "remaining_time": "0:26:29", "throughput": 1485.29, "total_tokens": 36005696} {"current_steps": 170615, "total_steps": 181800, "loss": 0.0643, "lr": 5.744027301886945e-07, "epoch": 18.76952695269527, "percentage": 93.85, "elapsed_time": "6:44:02", "remaining_time": "0:26:29", "throughput": 1485.29, "total_tokens": 36006656} {"current_steps": 170620, "total_steps": 181800, "loss": 0.0261, "lr": 5.738913167649462e-07, "epoch": 18.77007700770077, "percentage": 93.85, "elapsed_time": "6:44:02", "remaining_time": "0:26:28", "throughput": 1485.29, "total_tokens": 36007680} {"current_steps": 170625, "total_steps": 181800, "loss": 0.0042, "lr": 5.733801284649232e-07, "epoch": 18.77062706270627, "percentage": 93.85, "elapsed_time": "6:44:03", "remaining_time": "0:26:27", "throughput": 1485.29, "total_tokens": 36008736} {"current_steps": 170630, "total_steps": 181800, "loss": 0.0242, "lr": 5.728691652933355e-07, "epoch": 18.771177117711773, "percentage": 93.86, "elapsed_time": "6:44:04", "remaining_time": "0:26:27", "throughput": 1485.29, "total_tokens": 36009824} {"current_steps": 170635, "total_steps": 181800, "loss": 0.0018, "lr": 5.723584272548877e-07, "epoch": 18.77172717271727, "percentage": 93.86, "elapsed_time": "6:44:04", "remaining_time": "0:26:26", "throughput": 1485.29, "total_tokens": 36010880} {"current_steps": 170640, "total_steps": 181800, "loss": 0.0045, "lr": 5.718479143542954e-07, "epoch": 18.77227722772277, "percentage": 93.86, "elapsed_time": "6:44:05", "remaining_time": "0:26:25", "throughput": 1485.29, "total_tokens": 36011968} {"current_steps": 170645, "total_steps": 181800, "loss": 0.0067, "lr": 5.713376265962578e-07, "epoch": 18.772827282728272, "percentage": 93.86, "elapsed_time": "6:44:06", "remaining_time": "0:26:24", "throughput": 1485.29, "total_tokens": 36012992} {"current_steps": 170650, "total_steps": 181800, "loss": 0.0024, "lr": 5.708275639854765e-07, "epoch": 18.773377337733773, "percentage": 93.87, "elapsed_time": "6:44:07", "remaining_time": "0:26:24", "throughput": 1485.3, "total_tokens": 36014080} {"current_steps": 170655, "total_steps": 181800, "loss": 0.0035, "lr": 5.703177265266563e-07, "epoch": 18.773927392739274, "percentage": 93.87, "elapsed_time": "6:44:07", "remaining_time": "0:26:23", "throughput": 1485.3, "total_tokens": 36015104} {"current_steps": 170660, "total_steps": 181800, "loss": 0.0211, "lr": 5.69808114224496e-07, "epoch": 18.774477447744776, "percentage": 93.87, "elapsed_time": "6:44:08", "remaining_time": "0:26:22", "throughput": 1485.3, "total_tokens": 36016224} {"current_steps": 170665, "total_steps": 181800, "loss": 0.001, "lr": 5.692987270836919e-07, "epoch": 18.775027502750277, "percentage": 93.88, "elapsed_time": "6:44:09", "remaining_time": "0:26:22", "throughput": 1485.3, "total_tokens": 36017216} {"current_steps": 170670, "total_steps": 181800, "loss": 0.078, "lr": 5.687895651089403e-07, "epoch": 18.775577557755774, "percentage": 93.88, "elapsed_time": "6:44:09", "remaining_time": "0:26:21", "throughput": 1485.3, "total_tokens": 36018272} {"current_steps": 170675, "total_steps": 181800, "loss": 0.0901, "lr": 5.682806283049292e-07, "epoch": 18.776127612761275, "percentage": 93.88, "elapsed_time": "6:44:10", "remaining_time": "0:26:20", "throughput": 1485.31, "total_tokens": 36019392} {"current_steps": 170680, "total_steps": 181800, "loss": 0.0099, "lr": 5.677719166763518e-07, "epoch": 18.776677667766776, "percentage": 93.88, "elapsed_time": "6:44:11", "remaining_time": "0:26:19", "throughput": 1485.31, "total_tokens": 36020448} {"current_steps": 170685, "total_steps": 181800, "loss": 0.0028, "lr": 5.672634302278962e-07, "epoch": 18.777227722772277, "percentage": 93.89, "elapsed_time": "6:44:11", "remaining_time": "0:26:19", "throughput": 1485.31, "total_tokens": 36021504} {"current_steps": 170690, "total_steps": 181800, "loss": 0.048, "lr": 5.667551689642531e-07, "epoch": 18.77777777777778, "percentage": 93.89, "elapsed_time": "6:44:12", "remaining_time": "0:26:18", "throughput": 1485.31, "total_tokens": 36022592} {"current_steps": 170695, "total_steps": 181800, "loss": 0.0865, "lr": 5.66247132890102e-07, "epoch": 18.77832783278328, "percentage": 93.89, "elapsed_time": "6:44:13", "remaining_time": "0:26:17", "throughput": 1485.31, "total_tokens": 36023680} {"current_steps": 170700, "total_steps": 181800, "loss": 0.0036, "lr": 5.657393220101254e-07, "epoch": 18.778877887788777, "percentage": 93.89, "elapsed_time": "6:44:13", "remaining_time": "0:26:17", "throughput": 1485.32, "total_tokens": 36024704} {"current_steps": 170705, "total_steps": 181800, "loss": 0.0125, "lr": 5.652317363290055e-07, "epoch": 18.77942794279428, "percentage": 93.9, "elapsed_time": "6:44:14", "remaining_time": "0:26:16", "throughput": 1485.32, "total_tokens": 36025792} {"current_steps": 170710, "total_steps": 181800, "loss": 0.0043, "lr": 5.647243758514193e-07, "epoch": 18.77997799779978, "percentage": 93.9, "elapsed_time": "6:44:15", "remaining_time": "0:26:15", "throughput": 1485.32, "total_tokens": 36026848} {"current_steps": 170715, "total_steps": 181800, "loss": 0.0533, "lr": 5.642172405820433e-07, "epoch": 18.78052805280528, "percentage": 93.9, "elapsed_time": "6:44:15", "remaining_time": "0:26:15", "throughput": 1485.32, "total_tokens": 36027936} {"current_steps": 170720, "total_steps": 181800, "loss": 0.0047, "lr": 5.63710330525552e-07, "epoch": 18.78107810781078, "percentage": 93.91, "elapsed_time": "6:44:16", "remaining_time": "0:26:14", "throughput": 1485.33, "total_tokens": 36029056} {"current_steps": 170725, "total_steps": 181800, "loss": 0.0339, "lr": 5.632036456866163e-07, "epoch": 18.781628162816283, "percentage": 93.91, "elapsed_time": "6:44:17", "remaining_time": "0:26:13", "throughput": 1485.32, "total_tokens": 36030048} {"current_steps": 170730, "total_steps": 181800, "loss": 0.0867, "lr": 5.626971860699076e-07, "epoch": 18.782178217821784, "percentage": 93.91, "elapsed_time": "6:44:18", "remaining_time": "0:26:12", "throughput": 1485.33, "total_tokens": 36031104} {"current_steps": 170735, "total_steps": 181800, "loss": 0.0011, "lr": 5.621909516800916e-07, "epoch": 18.78272827282728, "percentage": 93.91, "elapsed_time": "6:44:18", "remaining_time": "0:26:12", "throughput": 1485.33, "total_tokens": 36032128} {"current_steps": 170740, "total_steps": 181800, "loss": 0.0027, "lr": 5.616849425218367e-07, "epoch": 18.783278327832782, "percentage": 93.92, "elapsed_time": "6:44:19", "remaining_time": "0:26:11", "throughput": 1485.33, "total_tokens": 36033184} {"current_steps": 170745, "total_steps": 181800, "loss": 0.0025, "lr": 5.611791585998061e-07, "epoch": 18.783828382838283, "percentage": 93.92, "elapsed_time": "6:44:20", "remaining_time": "0:26:10", "throughput": 1485.32, "total_tokens": 36034144} {"current_steps": 170750, "total_steps": 181800, "loss": 0.0027, "lr": 5.606735999186568e-07, "epoch": 18.784378437843785, "percentage": 93.92, "elapsed_time": "6:44:20", "remaining_time": "0:26:10", "throughput": 1485.33, "total_tokens": 36035200} {"current_steps": 170755, "total_steps": 181800, "loss": 0.1001, "lr": 5.601682664830549e-07, "epoch": 18.784928492849286, "percentage": 93.92, "elapsed_time": "6:44:21", "remaining_time": "0:26:09", "throughput": 1485.33, "total_tokens": 36036256} {"current_steps": 170760, "total_steps": 181800, "loss": 0.0018, "lr": 5.596631582976519e-07, "epoch": 18.785478547854787, "percentage": 93.93, "elapsed_time": "6:44:22", "remaining_time": "0:26:08", "throughput": 1485.33, "total_tokens": 36037344} {"current_steps": 170765, "total_steps": 181800, "loss": 0.003, "lr": 5.591582753671082e-07, "epoch": 18.786028602860284, "percentage": 93.93, "elapsed_time": "6:44:22", "remaining_time": "0:26:07", "throughput": 1485.33, "total_tokens": 36038400} {"current_steps": 170770, "total_steps": 181800, "loss": 0.0018, "lr": 5.586536176960728e-07, "epoch": 18.786578657865785, "percentage": 93.93, "elapsed_time": "6:44:23", "remaining_time": "0:26:07", "throughput": 1485.33, "total_tokens": 36039456} {"current_steps": 170775, "total_steps": 181800, "loss": 0.0969, "lr": 5.581491852892001e-07, "epoch": 18.787128712871286, "percentage": 93.94, "elapsed_time": "6:44:24", "remaining_time": "0:26:06", "throughput": 1485.34, "total_tokens": 36040544} {"current_steps": 170780, "total_steps": 181800, "loss": 0.0043, "lr": 5.576449781511394e-07, "epoch": 18.787678767876788, "percentage": 93.94, "elapsed_time": "6:44:24", "remaining_time": "0:26:05", "throughput": 1485.34, "total_tokens": 36041568} {"current_steps": 170785, "total_steps": 181800, "loss": 0.0013, "lr": 5.571409962865343e-07, "epoch": 18.78822882288229, "percentage": 93.94, "elapsed_time": "6:44:25", "remaining_time": "0:26:05", "throughput": 1485.34, "total_tokens": 36042592} {"current_steps": 170790, "total_steps": 181800, "loss": 0.0343, "lr": 5.566372397000335e-07, "epoch": 18.78877887788779, "percentage": 93.94, "elapsed_time": "6:44:26", "remaining_time": "0:26:04", "throughput": 1485.34, "total_tokens": 36043648} {"current_steps": 170795, "total_steps": 181800, "loss": 0.0025, "lr": 5.561337083962781e-07, "epoch": 18.78932893289329, "percentage": 93.95, "elapsed_time": "6:44:27", "remaining_time": "0:26:03", "throughput": 1485.34, "total_tokens": 36044704} {"current_steps": 170800, "total_steps": 181800, "loss": 0.1039, "lr": 5.556304023799058e-07, "epoch": 18.78987898789879, "percentage": 93.95, "elapsed_time": "6:44:27", "remaining_time": "0:26:02", "throughput": 1485.34, "total_tokens": 36045728} {"current_steps": 170805, "total_steps": 181800, "loss": 0.033, "lr": 5.55127321655563e-07, "epoch": 18.79042904290429, "percentage": 93.95, "elapsed_time": "6:44:28", "remaining_time": "0:26:02", "throughput": 1485.34, "total_tokens": 36046784} {"current_steps": 170810, "total_steps": 181800, "loss": 0.0263, "lr": 5.546244662278766e-07, "epoch": 18.79097909790979, "percentage": 93.95, "elapsed_time": "6:44:29", "remaining_time": "0:26:01", "throughput": 1485.34, "total_tokens": 36047936} {"current_steps": 170815, "total_steps": 181800, "loss": 0.0066, "lr": 5.541218361014927e-07, "epoch": 18.79152915291529, "percentage": 93.96, "elapsed_time": "6:44:29", "remaining_time": "0:26:00", "throughput": 1485.34, "total_tokens": 36048928} {"current_steps": 170820, "total_steps": 181800, "loss": 0.0015, "lr": 5.536194312810355e-07, "epoch": 18.792079207920793, "percentage": 93.96, "elapsed_time": "6:44:30", "remaining_time": "0:26:00", "throughput": 1485.34, "total_tokens": 36049920} {"current_steps": 170825, "total_steps": 181800, "loss": 0.1212, "lr": 5.531172517711347e-07, "epoch": 18.792629262926294, "percentage": 93.96, "elapsed_time": "6:44:31", "remaining_time": "0:25:59", "throughput": 1485.34, "total_tokens": 36050976} {"current_steps": 170830, "total_steps": 181800, "loss": 0.0086, "lr": 5.526152975764226e-07, "epoch": 18.793179317931795, "percentage": 93.97, "elapsed_time": "6:44:31", "remaining_time": "0:25:58", "throughput": 1485.35, "total_tokens": 36052064} {"current_steps": 170835, "total_steps": 181800, "loss": 0.0023, "lr": 5.521135687015261e-07, "epoch": 18.793729372937293, "percentage": 93.97, "elapsed_time": "6:44:32", "remaining_time": "0:25:57", "throughput": 1485.34, "total_tokens": 36053056} {"current_steps": 170840, "total_steps": 181800, "loss": 0.0452, "lr": 5.516120651510665e-07, "epoch": 18.794279427942794, "percentage": 93.97, "elapsed_time": "6:44:33", "remaining_time": "0:25:57", "throughput": 1485.35, "total_tokens": 36054208} {"current_steps": 170845, "total_steps": 181800, "loss": 0.1028, "lr": 5.511107869296677e-07, "epoch": 18.794829482948295, "percentage": 93.97, "elapsed_time": "6:44:33", "remaining_time": "0:25:56", "throughput": 1485.35, "total_tokens": 36055232} {"current_steps": 170850, "total_steps": 181800, "loss": 0.013, "lr": 5.506097340419458e-07, "epoch": 18.795379537953796, "percentage": 93.98, "elapsed_time": "6:44:34", "remaining_time": "0:25:55", "throughput": 1485.35, "total_tokens": 36056288} {"current_steps": 170855, "total_steps": 181800, "loss": 0.0037, "lr": 5.501089064925246e-07, "epoch": 18.795929592959297, "percentage": 93.98, "elapsed_time": "6:44:35", "remaining_time": "0:25:55", "throughput": 1485.35, "total_tokens": 36057312} {"current_steps": 170860, "total_steps": 181800, "loss": 0.0069, "lr": 5.496083042860201e-07, "epoch": 18.796479647964798, "percentage": 93.98, "elapsed_time": "6:44:35", "remaining_time": "0:25:54", "throughput": 1485.35, "total_tokens": 36058400} {"current_steps": 170865, "total_steps": 181800, "loss": 0.0016, "lr": 5.491079274270394e-07, "epoch": 18.797029702970296, "percentage": 93.99, "elapsed_time": "6:44:36", "remaining_time": "0:25:53", "throughput": 1485.35, "total_tokens": 36059424} {"current_steps": 170870, "total_steps": 181800, "loss": 0.0013, "lr": 5.486077759202013e-07, "epoch": 18.797579757975797, "percentage": 93.99, "elapsed_time": "6:44:37", "remaining_time": "0:25:52", "throughput": 1485.35, "total_tokens": 36060448} {"current_steps": 170875, "total_steps": 181800, "loss": 0.0289, "lr": 5.481078497701075e-07, "epoch": 18.798129812981298, "percentage": 93.99, "elapsed_time": "6:44:38", "remaining_time": "0:25:52", "throughput": 1485.35, "total_tokens": 36061440} {"current_steps": 170880, "total_steps": 181800, "loss": 0.0028, "lr": 5.476081489813767e-07, "epoch": 18.7986798679868, "percentage": 93.99, "elapsed_time": "6:44:38", "remaining_time": "0:25:51", "throughput": 1485.35, "total_tokens": 36062496} {"current_steps": 170885, "total_steps": 181800, "loss": 0.0617, "lr": 5.471086735586023e-07, "epoch": 18.7992299229923, "percentage": 94.0, "elapsed_time": "6:44:39", "remaining_time": "0:25:50", "throughput": 1485.35, "total_tokens": 36063520} {"current_steps": 170890, "total_steps": 181800, "loss": 0.0457, "lr": 5.466094235063973e-07, "epoch": 18.7997799779978, "percentage": 94.0, "elapsed_time": "6:44:40", "remaining_time": "0:25:50", "throughput": 1485.35, "total_tokens": 36064576} {"current_steps": 170895, "total_steps": 181800, "loss": 0.0081, "lr": 5.461103988293581e-07, "epoch": 18.8003300330033, "percentage": 94.0, "elapsed_time": "6:44:40", "remaining_time": "0:25:49", "throughput": 1485.36, "total_tokens": 36065632} {"current_steps": 170900, "total_steps": 181800, "loss": 0.0596, "lr": 5.456115995320866e-07, "epoch": 18.8008800880088, "percentage": 94.0, "elapsed_time": "6:44:41", "remaining_time": "0:25:48", "throughput": 1485.35, "total_tokens": 36066624} {"current_steps": 170905, "total_steps": 181800, "loss": 0.0755, "lr": 5.451130256191789e-07, "epoch": 18.8014301430143, "percentage": 94.01, "elapsed_time": "6:44:42", "remaining_time": "0:25:47", "throughput": 1485.36, "total_tokens": 36067712} {"current_steps": 170910, "total_steps": 181800, "loss": 0.0224, "lr": 5.446146770952288e-07, "epoch": 18.801980198019802, "percentage": 94.01, "elapsed_time": "6:44:42", "remaining_time": "0:25:47", "throughput": 1485.36, "total_tokens": 36068736} {"current_steps": 170915, "total_steps": 181800, "loss": 0.0437, "lr": 5.441165539648269e-07, "epoch": 18.802530253025303, "percentage": 94.01, "elapsed_time": "6:44:43", "remaining_time": "0:25:46", "throughput": 1485.36, "total_tokens": 36069792} {"current_steps": 170920, "total_steps": 181800, "loss": 0.002, "lr": 5.436186562325724e-07, "epoch": 18.803080308030804, "percentage": 94.02, "elapsed_time": "6:44:44", "remaining_time": "0:25:45", "throughput": 1485.36, "total_tokens": 36070816} {"current_steps": 170925, "total_steps": 181800, "loss": 0.0571, "lr": 5.431209839030477e-07, "epoch": 18.803630363036305, "percentage": 94.02, "elapsed_time": "6:44:44", "remaining_time": "0:25:45", "throughput": 1485.36, "total_tokens": 36071808} {"current_steps": 170930, "total_steps": 181800, "loss": 0.053, "lr": 5.426235369808408e-07, "epoch": 18.804180418041803, "percentage": 94.02, "elapsed_time": "6:44:45", "remaining_time": "0:25:44", "throughput": 1485.36, "total_tokens": 36072864} {"current_steps": 170935, "total_steps": 181800, "loss": 0.015, "lr": 5.421263154705397e-07, "epoch": 18.804730473047304, "percentage": 94.02, "elapsed_time": "6:44:46", "remaining_time": "0:25:43", "throughput": 1485.35, "total_tokens": 36073824} {"current_steps": 170940, "total_steps": 181800, "loss": 0.0019, "lr": 5.416293193767214e-07, "epoch": 18.805280528052805, "percentage": 94.03, "elapsed_time": "6:44:47", "remaining_time": "0:25:42", "throughput": 1485.36, "total_tokens": 36074848} {"current_steps": 170945, "total_steps": 181800, "loss": 0.0337, "lr": 5.411325487039709e-07, "epoch": 18.805830583058306, "percentage": 94.03, "elapsed_time": "6:44:47", "remaining_time": "0:25:42", "throughput": 1485.36, "total_tokens": 36075872} {"current_steps": 170950, "total_steps": 181800, "loss": 0.0016, "lr": 5.406360034568625e-07, "epoch": 18.806380638063807, "percentage": 94.03, "elapsed_time": "6:44:48", "remaining_time": "0:25:41", "throughput": 1485.36, "total_tokens": 36076960} {"current_steps": 170955, "total_steps": 181800, "loss": 0.081, "lr": 5.401396836399786e-07, "epoch": 18.806930693069308, "percentage": 94.03, "elapsed_time": "6:44:49", "remaining_time": "0:25:40", "throughput": 1485.36, "total_tokens": 36077984} {"current_steps": 170960, "total_steps": 181800, "loss": 0.0042, "lr": 5.396435892578905e-07, "epoch": 18.80748074807481, "percentage": 94.04, "elapsed_time": "6:44:49", "remaining_time": "0:25:40", "throughput": 1485.36, "total_tokens": 36079040} {"current_steps": 170965, "total_steps": 181800, "loss": 0.0457, "lr": 5.391477203151696e-07, "epoch": 18.808030803080307, "percentage": 94.04, "elapsed_time": "6:44:50", "remaining_time": "0:25:39", "throughput": 1485.36, "total_tokens": 36080128} {"current_steps": 170970, "total_steps": 181800, "loss": 0.0432, "lr": 5.386520768163872e-07, "epoch": 18.808580858085808, "percentage": 94.04, "elapsed_time": "6:44:51", "remaining_time": "0:25:38", "throughput": 1485.36, "total_tokens": 36081184} {"current_steps": 170975, "total_steps": 181800, "loss": 0.0024, "lr": 5.381566587661064e-07, "epoch": 18.80913091309131, "percentage": 94.05, "elapsed_time": "6:44:51", "remaining_time": "0:25:37", "throughput": 1485.37, "total_tokens": 36082272} {"current_steps": 170980, "total_steps": 181800, "loss": 0.0546, "lr": 5.376614661689012e-07, "epoch": 18.80968096809681, "percentage": 94.05, "elapsed_time": "6:44:52", "remaining_time": "0:25:37", "throughput": 1485.37, "total_tokens": 36083328} {"current_steps": 170985, "total_steps": 181800, "loss": 0.0021, "lr": 5.371664990293346e-07, "epoch": 18.81023102310231, "percentage": 94.05, "elapsed_time": "6:44:53", "remaining_time": "0:25:36", "throughput": 1485.37, "total_tokens": 36084448} {"current_steps": 170990, "total_steps": 181800, "loss": 0.1086, "lr": 5.366717573519614e-07, "epoch": 18.810781078107812, "percentage": 94.05, "elapsed_time": "6:44:53", "remaining_time": "0:25:35", "throughput": 1485.37, "total_tokens": 36085472} {"current_steps": 170995, "total_steps": 181800, "loss": 0.0038, "lr": 5.361772411413502e-07, "epoch": 18.81133113311331, "percentage": 94.06, "elapsed_time": "6:44:54", "remaining_time": "0:25:35", "throughput": 1485.37, "total_tokens": 36086528} {"current_steps": 171000, "total_steps": 181800, "loss": 0.0097, "lr": 5.3568295040205e-07, "epoch": 18.81188118811881, "percentage": 94.06, "elapsed_time": "6:44:55", "remaining_time": "0:25:34", "throughput": 1485.37, "total_tokens": 36087552} {"current_steps": 171005, "total_steps": 181800, "loss": 0.0018, "lr": 5.351888851386211e-07, "epoch": 18.812431243124312, "percentage": 94.06, "elapsed_time": "6:44:55", "remaining_time": "0:25:33", "throughput": 1485.37, "total_tokens": 36088640} {"current_steps": 171010, "total_steps": 181800, "loss": 0.0355, "lr": 5.34695045355621e-07, "epoch": 18.812981298129813, "percentage": 94.06, "elapsed_time": "6:44:56", "remaining_time": "0:25:33", "throughput": 1485.38, "total_tokens": 36089696} {"current_steps": 171015, "total_steps": 181800, "loss": 0.0852, "lr": 5.342014310575933e-07, "epoch": 18.813531353135314, "percentage": 94.07, "elapsed_time": "6:44:57", "remaining_time": "0:25:32", "throughput": 1485.38, "total_tokens": 36090816} {"current_steps": 171020, "total_steps": 181800, "loss": 0.0047, "lr": 5.337080422490954e-07, "epoch": 18.814081408140815, "percentage": 94.07, "elapsed_time": "6:44:58", "remaining_time": "0:25:31", "throughput": 1485.38, "total_tokens": 36091872} {"current_steps": 171025, "total_steps": 181800, "loss": 0.001, "lr": 5.33214878934668e-07, "epoch": 18.814631463146316, "percentage": 94.07, "elapsed_time": "6:44:58", "remaining_time": "0:25:30", "throughput": 1485.38, "total_tokens": 36092960} {"current_steps": 171030, "total_steps": 181800, "loss": 0.0034, "lr": 5.327219411188577e-07, "epoch": 18.815181518151814, "percentage": 94.08, "elapsed_time": "6:44:59", "remaining_time": "0:25:30", "throughput": 1485.39, "total_tokens": 36094048} {"current_steps": 171035, "total_steps": 181800, "loss": 0.0168, "lr": 5.322292288062081e-07, "epoch": 18.815731573157315, "percentage": 94.08, "elapsed_time": "6:45:00", "remaining_time": "0:25:29", "throughput": 1485.39, "total_tokens": 36095072} {"current_steps": 171040, "total_steps": 181800, "loss": 0.0011, "lr": 5.317367420012625e-07, "epoch": 18.816281628162816, "percentage": 94.08, "elapsed_time": "6:45:00", "remaining_time": "0:25:28", "throughput": 1485.39, "total_tokens": 36096128} {"current_steps": 171045, "total_steps": 181800, "loss": 0.056, "lr": 5.312444807085592e-07, "epoch": 18.816831683168317, "percentage": 94.08, "elapsed_time": "6:45:01", "remaining_time": "0:25:28", "throughput": 1485.39, "total_tokens": 36097184} {"current_steps": 171050, "total_steps": 181800, "loss": 0.0029, "lr": 5.307524449326363e-07, "epoch": 18.817381738173818, "percentage": 94.09, "elapsed_time": "6:45:02", "remaining_time": "0:25:27", "throughput": 1485.39, "total_tokens": 36098240} {"current_steps": 171055, "total_steps": 181800, "loss": 0.0062, "lr": 5.302606346780203e-07, "epoch": 18.81793179317932, "percentage": 94.09, "elapsed_time": "6:45:02", "remaining_time": "0:25:26", "throughput": 1485.39, "total_tokens": 36099296} {"current_steps": 171060, "total_steps": 181800, "loss": 0.0013, "lr": 5.297690499492525e-07, "epoch": 18.818481848184817, "percentage": 94.09, "elapsed_time": "6:45:03", "remaining_time": "0:25:25", "throughput": 1485.39, "total_tokens": 36100384} {"current_steps": 171065, "total_steps": 181800, "loss": 0.0061, "lr": 5.292776907508623e-07, "epoch": 18.819031903190318, "percentage": 94.1, "elapsed_time": "6:45:04", "remaining_time": "0:25:25", "throughput": 1485.4, "total_tokens": 36101504} {"current_steps": 171070, "total_steps": 181800, "loss": 0.0739, "lr": 5.287865570873796e-07, "epoch": 18.81958195819582, "percentage": 94.1, "elapsed_time": "6:45:04", "remaining_time": "0:25:24", "throughput": 1485.4, "total_tokens": 36102656} {"current_steps": 171075, "total_steps": 181800, "loss": 0.0134, "lr": 5.282956489633284e-07, "epoch": 18.82013201320132, "percentage": 94.1, "elapsed_time": "6:45:05", "remaining_time": "0:25:23", "throughput": 1485.41, "total_tokens": 36103776} {"current_steps": 171080, "total_steps": 181800, "loss": 0.0019, "lr": 5.278049663832302e-07, "epoch": 18.82068206820682, "percentage": 94.1, "elapsed_time": "6:45:06", "remaining_time": "0:25:23", "throughput": 1485.41, "total_tokens": 36104832} {"current_steps": 171085, "total_steps": 181800, "loss": 0.0182, "lr": 5.273145093516146e-07, "epoch": 18.821232123212322, "percentage": 94.11, "elapsed_time": "6:45:07", "remaining_time": "0:25:22", "throughput": 1485.41, "total_tokens": 36105888} {"current_steps": 171090, "total_steps": 181800, "loss": 0.002, "lr": 5.268242778729948e-07, "epoch": 18.821782178217823, "percentage": 94.11, "elapsed_time": "6:45:07", "remaining_time": "0:25:21", "throughput": 1485.41, "total_tokens": 36106976} {"current_steps": 171095, "total_steps": 181800, "loss": 0.0301, "lr": 5.263342719518921e-07, "epoch": 18.82233223322332, "percentage": 94.11, "elapsed_time": "6:45:08", "remaining_time": "0:25:20", "throughput": 1485.41, "total_tokens": 36108032} {"current_steps": 171100, "total_steps": 181800, "loss": 0.11, "lr": 5.258444915928252e-07, "epoch": 18.822882288228822, "percentage": 94.11, "elapsed_time": "6:45:09", "remaining_time": "0:25:20", "throughput": 1485.41, "total_tokens": 36109024} {"current_steps": 171105, "total_steps": 181800, "loss": 0.0026, "lr": 5.253549368003041e-07, "epoch": 18.823432343234323, "percentage": 94.12, "elapsed_time": "6:45:09", "remaining_time": "0:25:19", "throughput": 1485.41, "total_tokens": 36110048} {"current_steps": 171110, "total_steps": 181800, "loss": 0.003, "lr": 5.24865607578845e-07, "epoch": 18.823982398239824, "percentage": 94.12, "elapsed_time": "6:45:10", "remaining_time": "0:25:18", "throughput": 1485.41, "total_tokens": 36111104} {"current_steps": 171115, "total_steps": 181800, "loss": 0.0053, "lr": 5.243765039329524e-07, "epoch": 18.824532453245325, "percentage": 94.12, "elapsed_time": "6:45:11", "remaining_time": "0:25:18", "throughput": 1485.41, "total_tokens": 36112096} {"current_steps": 171120, "total_steps": 181800, "loss": 0.0141, "lr": 5.238876258671366e-07, "epoch": 18.825082508250826, "percentage": 94.13, "elapsed_time": "6:45:11", "remaining_time": "0:25:17", "throughput": 1485.41, "total_tokens": 36113120} {"current_steps": 171125, "total_steps": 181800, "loss": 0.0725, "lr": 5.233989733859052e-07, "epoch": 18.825632563256324, "percentage": 94.13, "elapsed_time": "6:45:12", "remaining_time": "0:25:16", "throughput": 1485.41, "total_tokens": 36114176} {"current_steps": 171130, "total_steps": 181800, "loss": 0.033, "lr": 5.2291054649376e-07, "epoch": 18.826182618261825, "percentage": 94.13, "elapsed_time": "6:45:13", "remaining_time": "0:25:15", "throughput": 1485.41, "total_tokens": 36115136} {"current_steps": 171135, "total_steps": 181800, "loss": 0.0014, "lr": 5.22422345195206e-07, "epoch": 18.826732673267326, "percentage": 94.13, "elapsed_time": "6:45:13", "remaining_time": "0:25:15", "throughput": 1485.41, "total_tokens": 36116160} {"current_steps": 171140, "total_steps": 181800, "loss": 0.0012, "lr": 5.219343694947365e-07, "epoch": 18.827282728272827, "percentage": 94.14, "elapsed_time": "6:45:14", "remaining_time": "0:25:14", "throughput": 1485.41, "total_tokens": 36117248} {"current_steps": 171145, "total_steps": 181800, "loss": 0.0005, "lr": 5.214466193968537e-07, "epoch": 18.82783278327833, "percentage": 94.14, "elapsed_time": "6:45:15", "remaining_time": "0:25:13", "throughput": 1485.42, "total_tokens": 36118336} {"current_steps": 171150, "total_steps": 181800, "loss": 0.0097, "lr": 5.209590949060483e-07, "epoch": 18.82838283828383, "percentage": 94.14, "elapsed_time": "6:45:16", "remaining_time": "0:25:13", "throughput": 1485.42, "total_tokens": 36119424} {"current_steps": 171155, "total_steps": 181800, "loss": 0.0016, "lr": 5.204717960268196e-07, "epoch": 18.82893289328933, "percentage": 94.14, "elapsed_time": "6:45:16", "remaining_time": "0:25:12", "throughput": 1485.42, "total_tokens": 36120480} {"current_steps": 171160, "total_steps": 181800, "loss": 0.1032, "lr": 5.199847227636556e-07, "epoch": 18.829482948294828, "percentage": 94.15, "elapsed_time": "6:45:17", "remaining_time": "0:25:11", "throughput": 1485.42, "total_tokens": 36121568} {"current_steps": 171165, "total_steps": 181800, "loss": 0.0049, "lr": 5.194978751210444e-07, "epoch": 18.83003300330033, "percentage": 94.15, "elapsed_time": "6:45:18", "remaining_time": "0:25:10", "throughput": 1485.43, "total_tokens": 36122688} {"current_steps": 171170, "total_steps": 181800, "loss": 0.0038, "lr": 5.190112531034769e-07, "epoch": 18.83058305830583, "percentage": 94.15, "elapsed_time": "6:45:18", "remaining_time": "0:25:10", "throughput": 1485.43, "total_tokens": 36123712} {"current_steps": 171175, "total_steps": 181800, "loss": 0.0008, "lr": 5.185248567154327e-07, "epoch": 18.83113311331133, "percentage": 94.16, "elapsed_time": "6:45:19", "remaining_time": "0:25:09", "throughput": 1485.43, "total_tokens": 36124832} {"current_steps": 171180, "total_steps": 181800, "loss": 0.0021, "lr": 5.180386859614001e-07, "epoch": 18.831683168316832, "percentage": 94.16, "elapsed_time": "6:45:20", "remaining_time": "0:25:08", "throughput": 1485.43, "total_tokens": 36125920} {"current_steps": 171185, "total_steps": 181800, "loss": 0.0074, "lr": 5.175527408458558e-07, "epoch": 18.832233223322334, "percentage": 94.16, "elapsed_time": "6:45:20", "remaining_time": "0:25:08", "throughput": 1485.43, "total_tokens": 36126944} {"current_steps": 171190, "total_steps": 181800, "loss": 0.0061, "lr": 5.170670213732798e-07, "epoch": 18.83278327832783, "percentage": 94.16, "elapsed_time": "6:45:21", "remaining_time": "0:25:07", "throughput": 1485.43, "total_tokens": 36128032} {"current_steps": 171195, "total_steps": 181800, "loss": 0.0277, "lr": 5.165815275481517e-07, "epoch": 18.833333333333332, "percentage": 94.17, "elapsed_time": "6:45:22", "remaining_time": "0:25:06", "throughput": 1485.43, "total_tokens": 36129056} {"current_steps": 171200, "total_steps": 181800, "loss": 0.0655, "lr": 5.16096259374943e-07, "epoch": 18.833883388338833, "percentage": 94.17, "elapsed_time": "6:45:22", "remaining_time": "0:25:05", "throughput": 1485.43, "total_tokens": 36130080} {"current_steps": 171205, "total_steps": 181800, "loss": 0.0005, "lr": 5.156112168581251e-07, "epoch": 18.834433443344334, "percentage": 94.17, "elapsed_time": "6:45:23", "remaining_time": "0:25:05", "throughput": 1485.43, "total_tokens": 36131072} {"current_steps": 171210, "total_steps": 181800, "loss": 0.0032, "lr": 5.151264000021666e-07, "epoch": 18.834983498349835, "percentage": 94.17, "elapsed_time": "6:45:24", "remaining_time": "0:25:04", "throughput": 1485.43, "total_tokens": 36132096} {"current_steps": 171215, "total_steps": 181800, "loss": 0.0523, "lr": 5.146418088115445e-07, "epoch": 18.835533553355337, "percentage": 94.18, "elapsed_time": "6:45:24", "remaining_time": "0:25:03", "throughput": 1485.44, "total_tokens": 36133152} {"current_steps": 171220, "total_steps": 181800, "loss": 0.0016, "lr": 5.141574432907165e-07, "epoch": 18.836083608360838, "percentage": 94.18, "elapsed_time": "6:45:25", "remaining_time": "0:25:03", "throughput": 1485.44, "total_tokens": 36134208} {"current_steps": 171225, "total_steps": 181800, "loss": 0.0018, "lr": 5.136733034441538e-07, "epoch": 18.836633663366335, "percentage": 94.18, "elapsed_time": "6:45:26", "remaining_time": "0:25:02", "throughput": 1485.43, "total_tokens": 36135200} {"current_steps": 171230, "total_steps": 181800, "loss": 0.0022, "lr": 5.131893892763085e-07, "epoch": 18.837183718371836, "percentage": 94.19, "elapsed_time": "6:45:27", "remaining_time": "0:25:01", "throughput": 1485.44, "total_tokens": 36136288} {"current_steps": 171235, "total_steps": 181800, "loss": 0.0544, "lr": 5.127057007916492e-07, "epoch": 18.837733773377337, "percentage": 94.19, "elapsed_time": "6:45:27", "remaining_time": "0:25:00", "throughput": 1485.44, "total_tokens": 36137376} {"current_steps": 171240, "total_steps": 181800, "loss": 0.0714, "lr": 5.122222379946334e-07, "epoch": 18.83828382838284, "percentage": 94.19, "elapsed_time": "6:45:28", "remaining_time": "0:25:00", "throughput": 1485.44, "total_tokens": 36138400} {"current_steps": 171245, "total_steps": 181800, "loss": 0.1623, "lr": 5.117390008897133e-07, "epoch": 18.83883388338834, "percentage": 94.19, "elapsed_time": "6:45:29", "remaining_time": "0:24:59", "throughput": 1485.44, "total_tokens": 36139360} {"current_steps": 171250, "total_steps": 181800, "loss": 0.0086, "lr": 5.112559894813434e-07, "epoch": 18.83938393839384, "percentage": 94.2, "elapsed_time": "6:45:29", "remaining_time": "0:24:58", "throughput": 1485.44, "total_tokens": 36140416} {"current_steps": 171255, "total_steps": 181800, "loss": 0.0023, "lr": 5.107732037739787e-07, "epoch": 18.83993399339934, "percentage": 94.2, "elapsed_time": "6:45:30", "remaining_time": "0:24:58", "throughput": 1485.44, "total_tokens": 36141472} {"current_steps": 171260, "total_steps": 181800, "loss": 0.0078, "lr": 5.102906437720656e-07, "epoch": 18.84048404840484, "percentage": 94.2, "elapsed_time": "6:45:31", "remaining_time": "0:24:57", "throughput": 1485.44, "total_tokens": 36142528} {"current_steps": 171265, "total_steps": 181800, "loss": 0.0377, "lr": 5.098083094800505e-07, "epoch": 18.84103410341034, "percentage": 94.21, "elapsed_time": "6:45:31", "remaining_time": "0:24:56", "throughput": 1485.44, "total_tokens": 36143616} {"current_steps": 171270, "total_steps": 181800, "loss": 0.0052, "lr": 5.093262009023797e-07, "epoch": 18.84158415841584, "percentage": 94.21, "elapsed_time": "6:45:32", "remaining_time": "0:24:56", "throughput": 1485.45, "total_tokens": 36144736} {"current_steps": 171275, "total_steps": 181800, "loss": 0.0352, "lr": 5.088443180434998e-07, "epoch": 18.842134213421343, "percentage": 94.21, "elapsed_time": "6:45:33", "remaining_time": "0:24:55", "throughput": 1485.45, "total_tokens": 36145760} {"current_steps": 171280, "total_steps": 181800, "loss": 0.0076, "lr": 5.08362660907849e-07, "epoch": 18.842684268426844, "percentage": 94.21, "elapsed_time": "6:45:33", "remaining_time": "0:24:54", "throughput": 1485.45, "total_tokens": 36146784} {"current_steps": 171285, "total_steps": 181800, "loss": 0.0176, "lr": 5.078812294998708e-07, "epoch": 18.843234323432345, "percentage": 94.22, "elapsed_time": "6:45:34", "remaining_time": "0:24:53", "throughput": 1485.45, "total_tokens": 36147872} {"current_steps": 171290, "total_steps": 181800, "loss": 0.1104, "lr": 5.074000238239924e-07, "epoch": 18.843784378437842, "percentage": 94.22, "elapsed_time": "6:45:35", "remaining_time": "0:24:53", "throughput": 1485.45, "total_tokens": 36148992} {"current_steps": 171295, "total_steps": 181800, "loss": 0.0378, "lr": 5.0691904388466e-07, "epoch": 18.844334433443343, "percentage": 94.22, "elapsed_time": "6:45:35", "remaining_time": "0:24:52", "throughput": 1485.46, "total_tokens": 36150080} {"current_steps": 171300, "total_steps": 181800, "loss": 0.0762, "lr": 5.064382896863007e-07, "epoch": 18.844884488448844, "percentage": 94.22, "elapsed_time": "6:45:36", "remaining_time": "0:24:51", "throughput": 1485.46, "total_tokens": 36151168} {"current_steps": 171305, "total_steps": 181800, "loss": 0.0019, "lr": 5.059577612333443e-07, "epoch": 18.845434543454346, "percentage": 94.23, "elapsed_time": "6:45:37", "remaining_time": "0:24:51", "throughput": 1485.46, "total_tokens": 36152256} {"current_steps": 171310, "total_steps": 181800, "loss": 0.0369, "lr": 5.054774585302264e-07, "epoch": 18.845984598459847, "percentage": 94.23, "elapsed_time": "6:45:38", "remaining_time": "0:24:50", "throughput": 1485.46, "total_tokens": 36153280} {"current_steps": 171315, "total_steps": 181800, "loss": 0.0118, "lr": 5.04997381581368e-07, "epoch": 18.846534653465348, "percentage": 94.23, "elapsed_time": "6:45:38", "remaining_time": "0:24:49", "throughput": 1485.46, "total_tokens": 36154304} {"current_steps": 171320, "total_steps": 181800, "loss": 0.0022, "lr": 5.045175303911937e-07, "epoch": 18.847084708470845, "percentage": 94.24, "elapsed_time": "6:45:39", "remaining_time": "0:24:48", "throughput": 1485.46, "total_tokens": 36155360} {"current_steps": 171325, "total_steps": 181800, "loss": 0.0327, "lr": 5.040379049641247e-07, "epoch": 18.847634763476346, "percentage": 94.24, "elapsed_time": "6:45:40", "remaining_time": "0:24:48", "throughput": 1485.46, "total_tokens": 36156416} {"current_steps": 171330, "total_steps": 181800, "loss": 0.0248, "lr": 5.035585053045855e-07, "epoch": 18.848184818481847, "percentage": 94.24, "elapsed_time": "6:45:40", "remaining_time": "0:24:47", "throughput": 1485.46, "total_tokens": 36157440} {"current_steps": 171335, "total_steps": 181800, "loss": 0.0074, "lr": 5.030793314169946e-07, "epoch": 18.84873487348735, "percentage": 94.24, "elapsed_time": "6:45:41", "remaining_time": "0:24:46", "throughput": 1485.47, "total_tokens": 36158528} {"current_steps": 171340, "total_steps": 181800, "loss": 0.0013, "lr": 5.02600383305768e-07, "epoch": 18.84928492849285, "percentage": 94.25, "elapsed_time": "6:45:42", "remaining_time": "0:24:46", "throughput": 1485.47, "total_tokens": 36159584} {"current_steps": 171345, "total_steps": 181800, "loss": 0.0021, "lr": 5.02121660975316e-07, "epoch": 18.84983498349835, "percentage": 94.25, "elapsed_time": "6:45:42", "remaining_time": "0:24:45", "throughput": 1485.47, "total_tokens": 36160672} {"current_steps": 171350, "total_steps": 181800, "loss": 0.0036, "lr": 5.016431644300517e-07, "epoch": 18.850385038503852, "percentage": 94.25, "elapsed_time": "6:45:43", "remaining_time": "0:24:44", "throughput": 1485.47, "total_tokens": 36161728} {"current_steps": 171355, "total_steps": 181800, "loss": 0.026, "lr": 5.011648936743885e-07, "epoch": 18.85093509350935, "percentage": 94.25, "elapsed_time": "6:45:44", "remaining_time": "0:24:43", "throughput": 1485.47, "total_tokens": 36162816} {"current_steps": 171360, "total_steps": 181800, "loss": 0.1144, "lr": 5.006868487127364e-07, "epoch": 18.85148514851485, "percentage": 94.26, "elapsed_time": "6:45:44", "remaining_time": "0:24:43", "throughput": 1485.47, "total_tokens": 36163840} {"current_steps": 171365, "total_steps": 181800, "loss": 0.0026, "lr": 5.002090295494949e-07, "epoch": 18.85203520352035, "percentage": 94.26, "elapsed_time": "6:45:45", "remaining_time": "0:24:42", "throughput": 1485.47, "total_tokens": 36164864} {"current_steps": 171370, "total_steps": 181800, "loss": 0.0041, "lr": 4.997314361890715e-07, "epoch": 18.852585258525853, "percentage": 94.26, "elapsed_time": "6:45:46", "remaining_time": "0:24:41", "throughput": 1485.48, "total_tokens": 36166016} {"current_steps": 171375, "total_steps": 181800, "loss": 0.0017, "lr": 4.992540686358682e-07, "epoch": 18.853135313531354, "percentage": 94.27, "elapsed_time": "6:45:47", "remaining_time": "0:24:41", "throughput": 1485.48, "total_tokens": 36166976} {"current_steps": 171380, "total_steps": 181800, "loss": 0.0352, "lr": 4.987769268942788e-07, "epoch": 18.853685368536855, "percentage": 94.27, "elapsed_time": "6:45:47", "remaining_time": "0:24:40", "throughput": 1485.48, "total_tokens": 36168000} {"current_steps": 171385, "total_steps": 181800, "loss": 0.0015, "lr": 4.983000109687081e-07, "epoch": 18.854235423542356, "percentage": 94.27, "elapsed_time": "6:45:48", "remaining_time": "0:24:39", "throughput": 1485.48, "total_tokens": 36169152} {"current_steps": 171390, "total_steps": 181800, "loss": 0.0864, "lr": 4.978233208635497e-07, "epoch": 18.854785478547853, "percentage": 94.27, "elapsed_time": "6:45:49", "remaining_time": "0:24:38", "throughput": 1485.49, "total_tokens": 36170240} {"current_steps": 171395, "total_steps": 181800, "loss": 0.002, "lr": 4.973468565831973e-07, "epoch": 18.855335533553355, "percentage": 94.28, "elapsed_time": "6:45:49", "remaining_time": "0:24:38", "throughput": 1485.49, "total_tokens": 36171296} {"current_steps": 171400, "total_steps": 181800, "loss": 0.005, "lr": 4.968706181320393e-07, "epoch": 18.855885588558856, "percentage": 94.28, "elapsed_time": "6:45:50", "remaining_time": "0:24:37", "throughput": 1485.49, "total_tokens": 36172320} {"current_steps": 171405, "total_steps": 181800, "loss": 0.0732, "lr": 4.963946055144691e-07, "epoch": 18.856435643564357, "percentage": 94.28, "elapsed_time": "6:45:51", "remaining_time": "0:24:36", "throughput": 1485.49, "total_tokens": 36173344} {"current_steps": 171410, "total_steps": 181800, "loss": 0.0499, "lr": 4.959188187348695e-07, "epoch": 18.856985698569858, "percentage": 94.28, "elapsed_time": "6:45:51", "remaining_time": "0:24:36", "throughput": 1485.49, "total_tokens": 36174368} {"current_steps": 171415, "total_steps": 181800, "loss": 0.0233, "lr": 4.954432577976315e-07, "epoch": 18.85753575357536, "percentage": 94.29, "elapsed_time": "6:45:52", "remaining_time": "0:24:35", "throughput": 1485.49, "total_tokens": 36175424} {"current_steps": 171420, "total_steps": 181800, "loss": 0.0067, "lr": 4.949679227071291e-07, "epoch": 18.858085808580856, "percentage": 94.29, "elapsed_time": "6:45:53", "remaining_time": "0:24:34", "throughput": 1485.49, "total_tokens": 36176608} {"current_steps": 171425, "total_steps": 181800, "loss": 0.0085, "lr": 4.944928134677535e-07, "epoch": 18.858635863586358, "percentage": 94.29, "elapsed_time": "6:45:53", "remaining_time": "0:24:33", "throughput": 1485.5, "total_tokens": 36177664} {"current_steps": 171430, "total_steps": 181800, "loss": 0.0169, "lr": 4.940179300838788e-07, "epoch": 18.85918591859186, "percentage": 94.3, "elapsed_time": "6:45:54", "remaining_time": "0:24:33", "throughput": 1485.49, "total_tokens": 36178656} {"current_steps": 171435, "total_steps": 181800, "loss": 0.0144, "lr": 4.935432725598793e-07, "epoch": 18.85973597359736, "percentage": 94.3, "elapsed_time": "6:45:55", "remaining_time": "0:24:32", "throughput": 1485.5, "total_tokens": 36179808} {"current_steps": 171440, "total_steps": 181800, "loss": 0.0838, "lr": 4.930688409001322e-07, "epoch": 18.86028602860286, "percentage": 94.3, "elapsed_time": "6:45:56", "remaining_time": "0:24:31", "throughput": 1485.5, "total_tokens": 36180896} {"current_steps": 171445, "total_steps": 181800, "loss": 0.0058, "lr": 4.925946351090116e-07, "epoch": 18.860836083608362, "percentage": 94.3, "elapsed_time": "6:45:56", "remaining_time": "0:24:31", "throughput": 1485.5, "total_tokens": 36181888} {"current_steps": 171450, "total_steps": 181800, "loss": 0.187, "lr": 4.921206551908864e-07, "epoch": 18.861386138613863, "percentage": 94.31, "elapsed_time": "6:45:57", "remaining_time": "0:24:30", "throughput": 1485.5, "total_tokens": 36182976} {"current_steps": 171455, "total_steps": 181800, "loss": 0.0031, "lr": 4.916469011501251e-07, "epoch": 18.86193619361936, "percentage": 94.31, "elapsed_time": "6:45:58", "remaining_time": "0:24:29", "throughput": 1485.5, "total_tokens": 36184032} {"current_steps": 171460, "total_steps": 181800, "loss": 0.0034, "lr": 4.911733729910911e-07, "epoch": 18.86248624862486, "percentage": 94.31, "elapsed_time": "6:45:58", "remaining_time": "0:24:28", "throughput": 1485.5, "total_tokens": 36185024} {"current_steps": 171465, "total_steps": 181800, "loss": 0.0115, "lr": 4.90700070718153e-07, "epoch": 18.863036303630363, "percentage": 94.32, "elapsed_time": "6:45:59", "remaining_time": "0:24:28", "throughput": 1485.5, "total_tokens": 36186048} {"current_steps": 171470, "total_steps": 181800, "loss": 0.0338, "lr": 4.902269943356713e-07, "epoch": 18.863586358635864, "percentage": 94.32, "elapsed_time": "6:46:00", "remaining_time": "0:24:27", "throughput": 1485.5, "total_tokens": 36187104} {"current_steps": 171475, "total_steps": 181800, "loss": 0.0102, "lr": 4.897541438480091e-07, "epoch": 18.864136413641365, "percentage": 94.32, "elapsed_time": "6:46:00", "remaining_time": "0:24:26", "throughput": 1485.5, "total_tokens": 36188128} {"current_steps": 171480, "total_steps": 181800, "loss": 0.001, "lr": 4.89281519259524e-07, "epoch": 18.864686468646866, "percentage": 94.32, "elapsed_time": "6:46:01", "remaining_time": "0:24:26", "throughput": 1485.51, "total_tokens": 36189216} {"current_steps": 171485, "total_steps": 181800, "loss": 0.0012, "lr": 4.888091205745626e-07, "epoch": 18.865236523652364, "percentage": 94.33, "elapsed_time": "6:46:02", "remaining_time": "0:24:25", "throughput": 1485.5, "total_tokens": 36190208} {"current_steps": 171490, "total_steps": 181800, "loss": 0.0962, "lr": 4.883369477974909e-07, "epoch": 18.865786578657865, "percentage": 94.33, "elapsed_time": "6:46:02", "remaining_time": "0:24:24", "throughput": 1485.51, "total_tokens": 36191264} {"current_steps": 171495, "total_steps": 181800, "loss": 0.0092, "lr": 4.878650009326552e-07, "epoch": 18.866336633663366, "percentage": 94.33, "elapsed_time": "6:46:03", "remaining_time": "0:24:23", "throughput": 1485.51, "total_tokens": 36192320} {"current_steps": 171500, "total_steps": 181800, "loss": 0.0051, "lr": 4.873932799844022e-07, "epoch": 18.866886688668867, "percentage": 94.33, "elapsed_time": "6:46:04", "remaining_time": "0:24:23", "throughput": 1485.51, "total_tokens": 36193344} {"current_steps": 171505, "total_steps": 181800, "loss": 0.0396, "lr": 4.869217849570868e-07, "epoch": 18.867436743674368, "percentage": 94.34, "elapsed_time": "6:46:04", "remaining_time": "0:24:22", "throughput": 1485.51, "total_tokens": 36194368} {"current_steps": 171510, "total_steps": 181800, "loss": 0.0044, "lr": 4.864505158550498e-07, "epoch": 18.86798679867987, "percentage": 94.34, "elapsed_time": "6:46:05", "remaining_time": "0:24:21", "throughput": 1485.51, "total_tokens": 36195488} {"current_steps": 171515, "total_steps": 181800, "loss": 0.0045, "lr": 4.85979472682635e-07, "epoch": 18.86853685368537, "percentage": 94.34, "elapsed_time": "6:46:06", "remaining_time": "0:24:21", "throughput": 1485.51, "total_tokens": 36196576} {"current_steps": 171520, "total_steps": 181800, "loss": 0.0425, "lr": 4.855086554441862e-07, "epoch": 18.869086908690868, "percentage": 94.35, "elapsed_time": "6:46:07", "remaining_time": "0:24:20", "throughput": 1485.51, "total_tokens": 36197600} {"current_steps": 171525, "total_steps": 181800, "loss": 0.1007, "lr": 4.850380641440388e-07, "epoch": 18.86963696369637, "percentage": 94.35, "elapsed_time": "6:46:07", "remaining_time": "0:24:19", "throughput": 1485.52, "total_tokens": 36198720} {"current_steps": 171530, "total_steps": 181800, "loss": 0.0015, "lr": 4.845676987865338e-07, "epoch": 18.87018701870187, "percentage": 94.35, "elapsed_time": "6:46:08", "remaining_time": "0:24:19", "throughput": 1485.52, "total_tokens": 36199776} {"current_steps": 171535, "total_steps": 181800, "loss": 0.0046, "lr": 4.840975593760011e-07, "epoch": 18.87073707370737, "percentage": 94.35, "elapsed_time": "6:46:09", "remaining_time": "0:24:18", "throughput": 1485.52, "total_tokens": 36200864} {"current_steps": 171540, "total_steps": 181800, "loss": 0.0067, "lr": 4.836276459167816e-07, "epoch": 18.871287128712872, "percentage": 94.36, "elapsed_time": "6:46:09", "remaining_time": "0:24:17", "throughput": 1485.52, "total_tokens": 36201984} {"current_steps": 171545, "total_steps": 181800, "loss": 0.0183, "lr": 4.831579584131996e-07, "epoch": 18.871837183718373, "percentage": 94.36, "elapsed_time": "6:46:10", "remaining_time": "0:24:16", "throughput": 1485.52, "total_tokens": 36203008} {"current_steps": 171550, "total_steps": 181800, "loss": 0.0336, "lr": 4.826884968695905e-07, "epoch": 18.87238723872387, "percentage": 94.36, "elapsed_time": "6:46:11", "remaining_time": "0:24:16", "throughput": 1485.52, "total_tokens": 36204064} {"current_steps": 171555, "total_steps": 181800, "loss": 0.089, "lr": 4.822192612902704e-07, "epoch": 18.872937293729372, "percentage": 94.36, "elapsed_time": "6:46:11", "remaining_time": "0:24:15", "throughput": 1485.52, "total_tokens": 36205056} {"current_steps": 171560, "total_steps": 181800, "loss": 0.0323, "lr": 4.817502516795747e-07, "epoch": 18.873487348734873, "percentage": 94.37, "elapsed_time": "6:46:12", "remaining_time": "0:24:14", "throughput": 1485.52, "total_tokens": 36206112} {"current_steps": 171565, "total_steps": 181800, "loss": 0.0794, "lr": 4.812814680418221e-07, "epoch": 18.874037403740374, "percentage": 94.37, "elapsed_time": "6:46:13", "remaining_time": "0:24:14", "throughput": 1485.52, "total_tokens": 36207072} {"current_steps": 171570, "total_steps": 181800, "loss": 0.0049, "lr": 4.808129103813313e-07, "epoch": 18.874587458745875, "percentage": 94.37, "elapsed_time": "6:46:13", "remaining_time": "0:24:13", "throughput": 1485.53, "total_tokens": 36208160} {"current_steps": 171575, "total_steps": 181800, "loss": 0.0028, "lr": 4.803445787024241e-07, "epoch": 18.875137513751376, "percentage": 94.38, "elapsed_time": "6:46:14", "remaining_time": "0:24:12", "throughput": 1485.52, "total_tokens": 36209120} {"current_steps": 171580, "total_steps": 181800, "loss": 0.0021, "lr": 4.798764730094163e-07, "epoch": 18.875687568756877, "percentage": 94.38, "elapsed_time": "6:46:15", "remaining_time": "0:24:11", "throughput": 1485.52, "total_tokens": 36210112} {"current_steps": 171585, "total_steps": 181800, "loss": 0.0392, "lr": 4.794085933066156e-07, "epoch": 18.876237623762375, "percentage": 94.38, "elapsed_time": "6:46:16", "remaining_time": "0:24:11", "throughput": 1485.53, "total_tokens": 36211232} {"current_steps": 171590, "total_steps": 181800, "loss": 0.0663, "lr": 4.789409395983435e-07, "epoch": 18.876787678767876, "percentage": 94.38, "elapsed_time": "6:46:16", "remaining_time": "0:24:10", "throughput": 1485.53, "total_tokens": 36212320} {"current_steps": 171595, "total_steps": 181800, "loss": 0.0302, "lr": 4.784735118889077e-07, "epoch": 18.877337733773377, "percentage": 94.39, "elapsed_time": "6:46:17", "remaining_time": "0:24:09", "throughput": 1485.53, "total_tokens": 36213440} {"current_steps": 171600, "total_steps": 181800, "loss": 0.0025, "lr": 4.780063101826132e-07, "epoch": 18.877887788778878, "percentage": 94.39, "elapsed_time": "6:46:18", "remaining_time": "0:24:09", "throughput": 1485.53, "total_tokens": 36214464} {"current_steps": 171605, "total_steps": 181800, "loss": 0.0064, "lr": 4.775393344837676e-07, "epoch": 18.87843784378438, "percentage": 94.39, "elapsed_time": "6:46:18", "remaining_time": "0:24:08", "throughput": 1485.53, "total_tokens": 36215520} {"current_steps": 171610, "total_steps": 181800, "loss": 0.011, "lr": 4.770725847966756e-07, "epoch": 18.87898789878988, "percentage": 94.39, "elapsed_time": "6:46:19", "remaining_time": "0:24:07", "throughput": 1485.53, "total_tokens": 36216576} {"current_steps": 171615, "total_steps": 181800, "loss": 0.0017, "lr": 4.766060611256368e-07, "epoch": 18.879537953795378, "percentage": 94.4, "elapsed_time": "6:46:20", "remaining_time": "0:24:06", "throughput": 1485.54, "total_tokens": 36217664} {"current_steps": 171620, "total_steps": 181800, "loss": 0.0358, "lr": 4.761397634749559e-07, "epoch": 18.88008800880088, "percentage": 94.4, "elapsed_time": "6:46:20", "remaining_time": "0:24:06", "throughput": 1485.54, "total_tokens": 36218720} {"current_steps": 171625, "total_steps": 181800, "loss": 0.0343, "lr": 4.7567369184892407e-07, "epoch": 18.88063806380638, "percentage": 94.4, "elapsed_time": "6:46:21", "remaining_time": "0:24:05", "throughput": 1485.54, "total_tokens": 36219840} {"current_steps": 171630, "total_steps": 181800, "loss": 0.1525, "lr": 4.752078462518406e-07, "epoch": 18.88118811881188, "percentage": 94.41, "elapsed_time": "6:46:22", "remaining_time": "0:24:04", "throughput": 1485.54, "total_tokens": 36220896} {"current_steps": 171635, "total_steps": 181800, "loss": 0.0052, "lr": 4.747422266879992e-07, "epoch": 18.881738173817382, "percentage": 94.41, "elapsed_time": "6:46:22", "remaining_time": "0:24:04", "throughput": 1485.54, "total_tokens": 36221952} {"current_steps": 171640, "total_steps": 181800, "loss": 0.0007, "lr": 4.7427683316168814e-07, "epoch": 18.882288228822883, "percentage": 94.41, "elapsed_time": "6:46:23", "remaining_time": "0:24:03", "throughput": 1485.54, "total_tokens": 36222912} {"current_steps": 171645, "total_steps": 181800, "loss": 0.0013, "lr": 4.7381166567720124e-07, "epoch": 18.882838283828384, "percentage": 94.41, "elapsed_time": "6:46:24", "remaining_time": "0:24:02", "throughput": 1485.54, "total_tokens": 36223968} {"current_steps": 171650, "total_steps": 181800, "loss": 0.124, "lr": 4.733467242388212e-07, "epoch": 18.883388338833882, "percentage": 94.42, "elapsed_time": "6:46:25", "remaining_time": "0:24:01", "throughput": 1485.54, "total_tokens": 36225024} {"current_steps": 171655, "total_steps": 181800, "loss": 0.0673, "lr": 4.72882008850839e-07, "epoch": 18.883938393839383, "percentage": 94.42, "elapsed_time": "6:46:25", "remaining_time": "0:24:01", "throughput": 1485.54, "total_tokens": 36226048} {"current_steps": 171660, "total_steps": 181800, "loss": 0.0064, "lr": 4.7241751951752897e-07, "epoch": 18.884488448844884, "percentage": 94.42, "elapsed_time": "6:46:26", "remaining_time": "0:24:00", "throughput": 1485.54, "total_tokens": 36227072} {"current_steps": 171665, "total_steps": 181800, "loss": 0.0423, "lr": 4.719532562431822e-07, "epoch": 18.885038503850385, "percentage": 94.43, "elapsed_time": "6:46:27", "remaining_time": "0:23:59", "throughput": 1485.55, "total_tokens": 36228160} {"current_steps": 171670, "total_steps": 181800, "loss": 0.1022, "lr": 4.714892190320702e-07, "epoch": 18.885588558855886, "percentage": 94.43, "elapsed_time": "6:46:27", "remaining_time": "0:23:59", "throughput": 1485.55, "total_tokens": 36229216} {"current_steps": 171675, "total_steps": 181800, "loss": 0.0222, "lr": 4.7102540788847013e-07, "epoch": 18.886138613861387, "percentage": 94.43, "elapsed_time": "6:46:28", "remaining_time": "0:23:58", "throughput": 1485.55, "total_tokens": 36230304} {"current_steps": 171680, "total_steps": 181800, "loss": 0.0033, "lr": 4.7056182281666194e-07, "epoch": 18.88668866886689, "percentage": 94.43, "elapsed_time": "6:46:29", "remaining_time": "0:23:57", "throughput": 1485.55, "total_tokens": 36231328} {"current_steps": 171685, "total_steps": 181800, "loss": 0.0113, "lr": 4.7009846382091436e-07, "epoch": 18.887238723872386, "percentage": 94.44, "elapsed_time": "6:46:29", "remaining_time": "0:23:56", "throughput": 1485.55, "total_tokens": 36232416} {"current_steps": 171690, "total_steps": 181800, "loss": 0.0081, "lr": 4.6963533090549904e-07, "epoch": 18.887788778877887, "percentage": 94.44, "elapsed_time": "6:46:30", "remaining_time": "0:23:56", "throughput": 1485.55, "total_tokens": 36233440} {"current_steps": 171695, "total_steps": 181800, "loss": 0.1175, "lr": 4.6917242407468476e-07, "epoch": 18.888338833883388, "percentage": 94.44, "elapsed_time": "6:46:31", "remaining_time": "0:23:55", "throughput": 1485.55, "total_tokens": 36234432} {"current_steps": 171700, "total_steps": 181800, "loss": 0.0369, "lr": 4.68709743332732e-07, "epoch": 18.88888888888889, "percentage": 94.44, "elapsed_time": "6:46:31", "remaining_time": "0:23:54", "throughput": 1485.55, "total_tokens": 36235520} {"current_steps": 171705, "total_steps": 181800, "loss": 0.0864, "lr": 4.682472886839151e-07, "epoch": 18.88943894389439, "percentage": 94.45, "elapsed_time": "6:46:32", "remaining_time": "0:23:54", "throughput": 1485.56, "total_tokens": 36236608} {"current_steps": 171710, "total_steps": 181800, "loss": 0.0007, "lr": 4.677850601324918e-07, "epoch": 18.88998899889989, "percentage": 94.45, "elapsed_time": "6:46:33", "remaining_time": "0:23:53", "throughput": 1485.56, "total_tokens": 36237632} {"current_steps": 171715, "total_steps": 181800, "loss": 0.0604, "lr": 4.673230576827198e-07, "epoch": 18.89053905390539, "percentage": 94.45, "elapsed_time": "6:46:34", "remaining_time": "0:23:52", "throughput": 1485.56, "total_tokens": 36238688} {"current_steps": 171720, "total_steps": 181800, "loss": 0.0009, "lr": 4.6686128133886233e-07, "epoch": 18.89108910891089, "percentage": 94.46, "elapsed_time": "6:46:34", "remaining_time": "0:23:51", "throughput": 1485.56, "total_tokens": 36239744} {"current_steps": 171725, "total_steps": 181800, "loss": 0.192, "lr": 4.6639973110516875e-07, "epoch": 18.89163916391639, "percentage": 94.46, "elapsed_time": "6:46:35", "remaining_time": "0:23:51", "throughput": 1485.56, "total_tokens": 36240800} {"current_steps": 171730, "total_steps": 181800, "loss": 0.0945, "lr": 4.6593840698589684e-07, "epoch": 18.892189218921892, "percentage": 94.46, "elapsed_time": "6:46:36", "remaining_time": "0:23:50", "throughput": 1485.56, "total_tokens": 36241824} {"current_steps": 171735, "total_steps": 181800, "loss": 0.0067, "lr": 4.654773089852987e-07, "epoch": 18.892739273927393, "percentage": 94.46, "elapsed_time": "6:46:36", "remaining_time": "0:23:49", "throughput": 1485.56, "total_tokens": 36242848} {"current_steps": 171740, "total_steps": 181800, "loss": 0.019, "lr": 4.6501643710762375e-07, "epoch": 18.893289328932894, "percentage": 94.47, "elapsed_time": "6:46:37", "remaining_time": "0:23:49", "throughput": 1485.56, "total_tokens": 36243904} {"current_steps": 171745, "total_steps": 181800, "loss": 0.0375, "lr": 4.645557913571214e-07, "epoch": 18.893839383938392, "percentage": 94.47, "elapsed_time": "6:46:38", "remaining_time": "0:23:48", "throughput": 1485.56, "total_tokens": 36244928} {"current_steps": 171750, "total_steps": 181800, "loss": 0.0666, "lr": 4.6409537173802973e-07, "epoch": 18.894389438943893, "percentage": 94.47, "elapsed_time": "6:46:38", "remaining_time": "0:23:47", "throughput": 1485.56, "total_tokens": 36245984} {"current_steps": 171755, "total_steps": 181800, "loss": 0.001, "lr": 4.636351782546039e-07, "epoch": 18.894939493949394, "percentage": 94.47, "elapsed_time": "6:46:39", "remaining_time": "0:23:46", "throughput": 1485.56, "total_tokens": 36247040} {"current_steps": 171760, "total_steps": 181800, "loss": 0.0876, "lr": 4.6317521091107095e-07, "epoch": 18.895489548954895, "percentage": 94.48, "elapsed_time": "6:46:40", "remaining_time": "0:23:46", "throughput": 1485.56, "total_tokens": 36248032} {"current_steps": 171765, "total_steps": 181800, "loss": 0.003, "lr": 4.627154697116859e-07, "epoch": 18.896039603960396, "percentage": 94.48, "elapsed_time": "6:46:40", "remaining_time": "0:23:45", "throughput": 1485.56, "total_tokens": 36249088} {"current_steps": 171770, "total_steps": 181800, "loss": 0.0307, "lr": 4.6225595466067585e-07, "epoch": 18.896589658965897, "percentage": 94.48, "elapsed_time": "6:46:41", "remaining_time": "0:23:44", "throughput": 1485.56, "total_tokens": 36250112} {"current_steps": 171775, "total_steps": 181800, "loss": 0.0565, "lr": 4.6179666576227633e-07, "epoch": 18.8971397139714, "percentage": 94.49, "elapsed_time": "6:46:42", "remaining_time": "0:23:44", "throughput": 1485.56, "total_tokens": 36251168} {"current_steps": 171780, "total_steps": 181800, "loss": 0.0014, "lr": 4.613376030207256e-07, "epoch": 18.897689768976896, "percentage": 94.49, "elapsed_time": "6:46:42", "remaining_time": "0:23:43", "throughput": 1485.57, "total_tokens": 36252224} {"current_steps": 171785, "total_steps": 181800, "loss": 0.0183, "lr": 4.608787664402481e-07, "epoch": 18.898239823982397, "percentage": 94.49, "elapsed_time": "6:46:43", "remaining_time": "0:23:42", "throughput": 1485.57, "total_tokens": 36253280} {"current_steps": 171790, "total_steps": 181800, "loss": 0.0028, "lr": 4.604201560250765e-07, "epoch": 18.8987898789879, "percentage": 94.49, "elapsed_time": "6:46:44", "remaining_time": "0:23:42", "throughput": 1485.57, "total_tokens": 36254368} {"current_steps": 171795, "total_steps": 181800, "loss": 0.0035, "lr": 4.59961771779438e-07, "epoch": 18.8993399339934, "percentage": 94.5, "elapsed_time": "6:46:45", "remaining_time": "0:23:41", "throughput": 1485.57, "total_tokens": 36255392} {"current_steps": 171800, "total_steps": 181800, "loss": 0.007, "lr": 4.59503613707557e-07, "epoch": 18.8998899889989, "percentage": 94.5, "elapsed_time": "6:46:45", "remaining_time": "0:23:40", "throughput": 1485.57, "total_tokens": 36256352} {"current_steps": 171805, "total_steps": 181800, "loss": 0.016, "lr": 4.5904568181365516e-07, "epoch": 18.9004400440044, "percentage": 94.5, "elapsed_time": "6:46:46", "remaining_time": "0:23:39", "throughput": 1485.57, "total_tokens": 36257440} {"current_steps": 171810, "total_steps": 181800, "loss": 0.0468, "lr": 4.58587976101954e-07, "epoch": 18.900990099009903, "percentage": 94.5, "elapsed_time": "6:46:47", "remaining_time": "0:23:39", "throughput": 1485.57, "total_tokens": 36258560} {"current_steps": 171815, "total_steps": 181800, "loss": 0.1092, "lr": 4.5813049657666976e-07, "epoch": 18.9015401540154, "percentage": 94.51, "elapsed_time": "6:46:47", "remaining_time": "0:23:38", "throughput": 1485.58, "total_tokens": 36259648} {"current_steps": 171820, "total_steps": 181800, "loss": 0.1501, "lr": 4.576732432420211e-07, "epoch": 18.9020902090209, "percentage": 94.51, "elapsed_time": "6:46:48", "remaining_time": "0:23:37", "throughput": 1485.58, "total_tokens": 36260704} {"current_steps": 171825, "total_steps": 181800, "loss": 0.0093, "lr": 4.5721621610221866e-07, "epoch": 18.902640264026402, "percentage": 94.51, "elapsed_time": "6:46:49", "remaining_time": "0:23:37", "throughput": 1485.58, "total_tokens": 36261728} {"current_steps": 171830, "total_steps": 181800, "loss": 0.0559, "lr": 4.5675941516148124e-07, "epoch": 18.903190319031903, "percentage": 94.52, "elapsed_time": "6:46:49", "remaining_time": "0:23:36", "throughput": 1485.58, "total_tokens": 36262784} {"current_steps": 171835, "total_steps": 181800, "loss": 0.0009, "lr": 4.563028404240166e-07, "epoch": 18.903740374037405, "percentage": 94.52, "elapsed_time": "6:46:50", "remaining_time": "0:23:35", "throughput": 1485.58, "total_tokens": 36263776} {"current_steps": 171840, "total_steps": 181800, "loss": 0.0109, "lr": 4.5584649189402975e-07, "epoch": 18.904290429042906, "percentage": 94.52, "elapsed_time": "6:46:51", "remaining_time": "0:23:34", "throughput": 1485.58, "total_tokens": 36264864} {"current_steps": 171845, "total_steps": 181800, "loss": 0.0084, "lr": 4.5539036957572556e-07, "epoch": 18.904840484048403, "percentage": 94.52, "elapsed_time": "6:46:51", "remaining_time": "0:23:34", "throughput": 1485.58, "total_tokens": 36265920} {"current_steps": 171850, "total_steps": 181800, "loss": 0.0331, "lr": 4.549344734733119e-07, "epoch": 18.905390539053904, "percentage": 94.53, "elapsed_time": "6:46:52", "remaining_time": "0:23:33", "throughput": 1485.58, "total_tokens": 36266912} {"current_steps": 171855, "total_steps": 181800, "loss": 0.0018, "lr": 4.544788035909936e-07, "epoch": 18.905940594059405, "percentage": 94.53, "elapsed_time": "6:46:53", "remaining_time": "0:23:32", "throughput": 1485.58, "total_tokens": 36267968} {"current_steps": 171860, "total_steps": 181800, "loss": 0.1585, "lr": 4.5402335993296465e-07, "epoch": 18.906490649064907, "percentage": 94.53, "elapsed_time": "6:46:54", "remaining_time": "0:23:32", "throughput": 1485.58, "total_tokens": 36269056} {"current_steps": 171865, "total_steps": 181800, "loss": 0.0026, "lr": 4.5356814250342163e-07, "epoch": 18.907040704070408, "percentage": 94.54, "elapsed_time": "6:46:54", "remaining_time": "0:23:31", "throughput": 1485.58, "total_tokens": 36270080} {"current_steps": 171870, "total_steps": 181800, "loss": 0.0005, "lr": 4.5311315130656394e-07, "epoch": 18.90759075907591, "percentage": 94.54, "elapsed_time": "6:46:55", "remaining_time": "0:23:30", "throughput": 1485.58, "total_tokens": 36271168} {"current_steps": 171875, "total_steps": 181800, "loss": 0.0768, "lr": 4.5265838634658275e-07, "epoch": 18.90814081408141, "percentage": 94.54, "elapsed_time": "6:46:56", "remaining_time": "0:23:29", "throughput": 1485.58, "total_tokens": 36272192} {"current_steps": 171880, "total_steps": 181800, "loss": 0.0604, "lr": 4.522038476276691e-07, "epoch": 18.908690869086907, "percentage": 94.54, "elapsed_time": "6:46:56", "remaining_time": "0:23:29", "throughput": 1485.58, "total_tokens": 36273216} {"current_steps": 171885, "total_steps": 181800, "loss": 0.0032, "lr": 4.5174953515401405e-07, "epoch": 18.90924092409241, "percentage": 94.55, "elapsed_time": "6:46:57", "remaining_time": "0:23:28", "throughput": 1485.59, "total_tokens": 36274304} {"current_steps": 171890, "total_steps": 181800, "loss": 0.0017, "lr": 4.5129544892980604e-07, "epoch": 18.90979097909791, "percentage": 94.55, "elapsed_time": "6:46:58", "remaining_time": "0:23:27", "throughput": 1485.59, "total_tokens": 36275360} {"current_steps": 171895, "total_steps": 181800, "loss": 0.0084, "lr": 4.5084158895922767e-07, "epoch": 18.91034103410341, "percentage": 94.55, "elapsed_time": "6:46:58", "remaining_time": "0:23:27", "throughput": 1485.59, "total_tokens": 36276416} {"current_steps": 171900, "total_steps": 181800, "loss": 0.004, "lr": 4.503879552464618e-07, "epoch": 18.91089108910891, "percentage": 94.55, "elapsed_time": "6:46:59", "remaining_time": "0:23:26", "throughput": 1485.59, "total_tokens": 36277408} {"current_steps": 171905, "total_steps": 181800, "loss": 0.0719, "lr": 4.4993454779568844e-07, "epoch": 18.911441144114413, "percentage": 94.56, "elapsed_time": "6:47:00", "remaining_time": "0:23:25", "throughput": 1485.59, "total_tokens": 36278496} {"current_steps": 171910, "total_steps": 181800, "loss": 0.0062, "lr": 4.494813666110903e-07, "epoch": 18.91199119911991, "percentage": 94.56, "elapsed_time": "6:47:00", "remaining_time": "0:23:24", "throughput": 1485.59, "total_tokens": 36279552} {"current_steps": 171915, "total_steps": 181800, "loss": 0.0089, "lr": 4.4902841169684183e-07, "epoch": 18.91254125412541, "percentage": 94.56, "elapsed_time": "6:47:01", "remaining_time": "0:23:24", "throughput": 1485.59, "total_tokens": 36280640} {"current_steps": 171920, "total_steps": 181800, "loss": 0.0057, "lr": 4.485756830571175e-07, "epoch": 18.913091309130913, "percentage": 94.57, "elapsed_time": "6:47:02", "remaining_time": "0:23:23", "throughput": 1485.6, "total_tokens": 36281696} {"current_steps": 171925, "total_steps": 181800, "loss": 0.1209, "lr": 4.4812318069609174e-07, "epoch": 18.913641364136414, "percentage": 94.57, "elapsed_time": "6:47:03", "remaining_time": "0:23:22", "throughput": 1485.59, "total_tokens": 36282688} {"current_steps": 171930, "total_steps": 181800, "loss": 0.0486, "lr": 4.476709046179306e-07, "epoch": 18.914191419141915, "percentage": 94.57, "elapsed_time": "6:47:03", "remaining_time": "0:23:22", "throughput": 1485.59, "total_tokens": 36283680} {"current_steps": 171935, "total_steps": 181800, "loss": 0.0183, "lr": 4.4721885482680583e-07, "epoch": 18.914741474147416, "percentage": 94.57, "elapsed_time": "6:47:04", "remaining_time": "0:23:21", "throughput": 1485.59, "total_tokens": 36284736} {"current_steps": 171940, "total_steps": 181800, "loss": 0.0205, "lr": 4.4676703132688346e-07, "epoch": 18.915291529152917, "percentage": 94.58, "elapsed_time": "6:47:05", "remaining_time": "0:23:20", "throughput": 1485.59, "total_tokens": 36285760} {"current_steps": 171945, "total_steps": 181800, "loss": 0.0024, "lr": 4.4631543412232966e-07, "epoch": 18.915841584158414, "percentage": 94.58, "elapsed_time": "6:47:05", "remaining_time": "0:23:19", "throughput": 1485.59, "total_tokens": 36286784} {"current_steps": 171950, "total_steps": 181800, "loss": 0.11, "lr": 4.4586406321730224e-07, "epoch": 18.916391639163916, "percentage": 94.58, "elapsed_time": "6:47:06", "remaining_time": "0:23:19", "throughput": 1485.59, "total_tokens": 36287840} {"current_steps": 171955, "total_steps": 181800, "loss": 0.0081, "lr": 4.4541291861596724e-07, "epoch": 18.916941694169417, "percentage": 94.58, "elapsed_time": "6:47:07", "remaining_time": "0:23:18", "throughput": 1485.6, "total_tokens": 36288896} {"current_steps": 171960, "total_steps": 181800, "loss": 0.0639, "lr": 4.4496200032247416e-07, "epoch": 18.917491749174918, "percentage": 94.59, "elapsed_time": "6:47:07", "remaining_time": "0:23:17", "throughput": 1485.6, "total_tokens": 36289952} {"current_steps": 171965, "total_steps": 181800, "loss": 0.0834, "lr": 4.4451130834098633e-07, "epoch": 18.91804180418042, "percentage": 94.59, "elapsed_time": "6:47:08", "remaining_time": "0:23:17", "throughput": 1485.6, "total_tokens": 36291040} {"current_steps": 171970, "total_steps": 181800, "loss": 0.0089, "lr": 4.440608426756532e-07, "epoch": 18.91859185918592, "percentage": 94.59, "elapsed_time": "6:47:09", "remaining_time": "0:23:16", "throughput": 1485.6, "total_tokens": 36292096} {"current_steps": 171975, "total_steps": 181800, "loss": 0.0015, "lr": 4.436106033306298e-07, "epoch": 18.919141914191417, "percentage": 94.6, "elapsed_time": "6:47:09", "remaining_time": "0:23:15", "throughput": 1485.6, "total_tokens": 36293184} {"current_steps": 171980, "total_steps": 181800, "loss": 0.0477, "lr": 4.431605903100655e-07, "epoch": 18.91969196919692, "percentage": 94.6, "elapsed_time": "6:47:10", "remaining_time": "0:23:14", "throughput": 1485.6, "total_tokens": 36294208} {"current_steps": 171985, "total_steps": 181800, "loss": 0.003, "lr": 4.4271080361810437e-07, "epoch": 18.92024202420242, "percentage": 94.6, "elapsed_time": "6:47:11", "remaining_time": "0:23:14", "throughput": 1485.6, "total_tokens": 36295200} {"current_steps": 171990, "total_steps": 181800, "loss": 0.0636, "lr": 4.4226124325889297e-07, "epoch": 18.92079207920792, "percentage": 94.6, "elapsed_time": "6:47:12", "remaining_time": "0:23:13", "throughput": 1485.6, "total_tokens": 36296256} {"current_steps": 171995, "total_steps": 181800, "loss": 0.0434, "lr": 4.41811909236578e-07, "epoch": 18.921342134213422, "percentage": 94.61, "elapsed_time": "6:47:12", "remaining_time": "0:23:12", "throughput": 1485.61, "total_tokens": 36297376} {"current_steps": 172000, "total_steps": 181800, "loss": 0.0008, "lr": 4.4136280155529783e-07, "epoch": 18.921892189218923, "percentage": 94.61, "elapsed_time": "6:47:13", "remaining_time": "0:23:12", "throughput": 1485.61, "total_tokens": 36298432} {"current_steps": 172005, "total_steps": 181800, "loss": 0.0024, "lr": 4.4091392021919087e-07, "epoch": 18.922442244224424, "percentage": 94.61, "elapsed_time": "6:47:14", "remaining_time": "0:23:11", "throughput": 1485.61, "total_tokens": 36299488} {"current_steps": 172010, "total_steps": 181800, "loss": 0.0109, "lr": 4.4046526523239816e-07, "epoch": 18.92299229922992, "percentage": 94.61, "elapsed_time": "6:47:14", "remaining_time": "0:23:10", "throughput": 1485.61, "total_tokens": 36300576} {"current_steps": 172015, "total_steps": 181800, "loss": 0.0029, "lr": 4.400168365990498e-07, "epoch": 18.923542354235423, "percentage": 94.62, "elapsed_time": "6:47:15", "remaining_time": "0:23:10", "throughput": 1485.61, "total_tokens": 36301632} {"current_steps": 172020, "total_steps": 181800, "loss": 0.2372, "lr": 4.3956863432328133e-07, "epoch": 18.924092409240924, "percentage": 94.62, "elapsed_time": "6:47:16", "remaining_time": "0:23:09", "throughput": 1485.61, "total_tokens": 36302688} {"current_steps": 172025, "total_steps": 181800, "loss": 0.011, "lr": 4.391206584092256e-07, "epoch": 18.924642464246425, "percentage": 94.62, "elapsed_time": "6:47:16", "remaining_time": "0:23:08", "throughput": 1485.62, "total_tokens": 36303808} {"current_steps": 172030, "total_steps": 181800, "loss": 0.0013, "lr": 4.3867290886100974e-07, "epoch": 18.925192519251926, "percentage": 94.63, "elapsed_time": "6:47:17", "remaining_time": "0:23:07", "throughput": 1485.62, "total_tokens": 36304832} {"current_steps": 172035, "total_steps": 181800, "loss": 0.0066, "lr": 4.382253856827584e-07, "epoch": 18.925742574257427, "percentage": 94.63, "elapsed_time": "6:47:18", "remaining_time": "0:23:07", "throughput": 1485.62, "total_tokens": 36305856} {"current_steps": 172040, "total_steps": 181800, "loss": 0.1673, "lr": 4.3777808887859873e-07, "epoch": 18.926292629262925, "percentage": 94.63, "elapsed_time": "6:47:18", "remaining_time": "0:23:06", "throughput": 1485.62, "total_tokens": 36306880} {"current_steps": 172045, "total_steps": 181800, "loss": 0.0041, "lr": 4.3733101845265245e-07, "epoch": 18.926842684268426, "percentage": 94.63, "elapsed_time": "6:47:19", "remaining_time": "0:23:05", "throughput": 1485.62, "total_tokens": 36307968} {"current_steps": 172050, "total_steps": 181800, "loss": 0.0017, "lr": 4.368841744090385e-07, "epoch": 18.927392739273927, "percentage": 94.64, "elapsed_time": "6:47:20", "remaining_time": "0:23:05", "throughput": 1485.62, "total_tokens": 36309056} {"current_steps": 172055, "total_steps": 181800, "loss": 0.0066, "lr": 4.364375567518758e-07, "epoch": 18.927942794279428, "percentage": 94.64, "elapsed_time": "6:47:20", "remaining_time": "0:23:04", "throughput": 1485.62, "total_tokens": 36310080} {"current_steps": 172060, "total_steps": 181800, "loss": 0.1275, "lr": 4.359911654852833e-07, "epoch": 18.92849284928493, "percentage": 94.64, "elapsed_time": "6:47:21", "remaining_time": "0:23:03", "throughput": 1485.62, "total_tokens": 36311136} {"current_steps": 172065, "total_steps": 181800, "loss": 0.0557, "lr": 4.355450006133716e-07, "epoch": 18.92904290429043, "percentage": 94.65, "elapsed_time": "6:47:22", "remaining_time": "0:23:02", "throughput": 1485.63, "total_tokens": 36312192} {"current_steps": 172070, "total_steps": 181800, "loss": 0.009, "lr": 4.3509906214025676e-07, "epoch": 18.92959295929593, "percentage": 94.65, "elapsed_time": "6:47:23", "remaining_time": "0:23:02", "throughput": 1485.63, "total_tokens": 36313216} {"current_steps": 172075, "total_steps": 181800, "loss": 0.0742, "lr": 4.3465335007004393e-07, "epoch": 18.93014301430143, "percentage": 94.65, "elapsed_time": "6:47:23", "remaining_time": "0:23:01", "throughput": 1485.62, "total_tokens": 36314208} {"current_steps": 172080, "total_steps": 181800, "loss": 0.0079, "lr": 4.342078644068437e-07, "epoch": 18.93069306930693, "percentage": 94.65, "elapsed_time": "6:47:24", "remaining_time": "0:23:00", "throughput": 1485.63, "total_tokens": 36315296} {"current_steps": 172085, "total_steps": 181800, "loss": 0.0732, "lr": 4.3376260515476384e-07, "epoch": 18.93124312431243, "percentage": 94.66, "elapsed_time": "6:47:25", "remaining_time": "0:23:00", "throughput": 1485.63, "total_tokens": 36316352} {"current_steps": 172090, "total_steps": 181800, "loss": 0.0226, "lr": 4.333175723179039e-07, "epoch": 18.931793179317932, "percentage": 94.66, "elapsed_time": "6:47:25", "remaining_time": "0:22:59", "throughput": 1485.63, "total_tokens": 36317376} {"current_steps": 172095, "total_steps": 181800, "loss": 0.0018, "lr": 4.3287276590037173e-07, "epoch": 18.932343234323433, "percentage": 94.66, "elapsed_time": "6:47:26", "remaining_time": "0:22:58", "throughput": 1485.63, "total_tokens": 36318432} {"current_steps": 172100, "total_steps": 181800, "loss": 0.0009, "lr": 4.324281859062612e-07, "epoch": 18.932893289328934, "percentage": 94.66, "elapsed_time": "6:47:27", "remaining_time": "0:22:57", "throughput": 1485.63, "total_tokens": 36319488} {"current_steps": 172105, "total_steps": 181800, "loss": 0.0526, "lr": 4.319838323396691e-07, "epoch": 18.933443344334435, "percentage": 94.67, "elapsed_time": "6:47:27", "remaining_time": "0:22:57", "throughput": 1485.63, "total_tokens": 36320544} {"current_steps": 172110, "total_steps": 181800, "loss": 0.0038, "lr": 4.3153970520469213e-07, "epoch": 18.933993399339933, "percentage": 94.67, "elapsed_time": "6:47:28", "remaining_time": "0:22:56", "throughput": 1485.63, "total_tokens": 36321536} {"current_steps": 172115, "total_steps": 181800, "loss": 0.1038, "lr": 4.3109580450542696e-07, "epoch": 18.934543454345434, "percentage": 94.67, "elapsed_time": "6:47:29", "remaining_time": "0:22:55", "throughput": 1485.63, "total_tokens": 36322560} {"current_steps": 172120, "total_steps": 181800, "loss": 0.0007, "lr": 4.3065213024596207e-07, "epoch": 18.935093509350935, "percentage": 94.68, "elapsed_time": "6:47:29", "remaining_time": "0:22:55", "throughput": 1485.64, "total_tokens": 36323680} {"current_steps": 172125, "total_steps": 181800, "loss": 0.0778, "lr": 4.302086824303886e-07, "epoch": 18.935643564356436, "percentage": 94.68, "elapsed_time": "6:47:30", "remaining_time": "0:22:54", "throughput": 1485.64, "total_tokens": 36324736} {"current_steps": 172130, "total_steps": 181800, "loss": 0.0013, "lr": 4.2976546106278935e-07, "epoch": 18.936193619361937, "percentage": 94.68, "elapsed_time": "6:47:31", "remaining_time": "0:22:53", "throughput": 1485.64, "total_tokens": 36325760} {"current_steps": 172135, "total_steps": 181800, "loss": 0.0033, "lr": 4.293224661472528e-07, "epoch": 18.936743674367438, "percentage": 94.68, "elapsed_time": "6:47:32", "remaining_time": "0:22:52", "throughput": 1485.64, "total_tokens": 36326816} {"current_steps": 172140, "total_steps": 181800, "loss": 0.011, "lr": 4.288796976878617e-07, "epoch": 18.937293729372936, "percentage": 94.69, "elapsed_time": "6:47:32", "remaining_time": "0:22:52", "throughput": 1485.64, "total_tokens": 36327904} {"current_steps": 172145, "total_steps": 181800, "loss": 0.0015, "lr": 4.284371556886962e-07, "epoch": 18.937843784378437, "percentage": 94.69, "elapsed_time": "6:47:33", "remaining_time": "0:22:51", "throughput": 1485.64, "total_tokens": 36328960} {"current_steps": 172150, "total_steps": 181800, "loss": 0.0213, "lr": 4.279948401538336e-07, "epoch": 18.938393839383938, "percentage": 94.69, "elapsed_time": "6:47:34", "remaining_time": "0:22:50", "throughput": 1485.63, "total_tokens": 36329952} {"current_steps": 172155, "total_steps": 181800, "loss": 0.0048, "lr": 4.2755275108735113e-07, "epoch": 18.93894389438944, "percentage": 94.69, "elapsed_time": "6:47:34", "remaining_time": "0:22:50", "throughput": 1485.63, "total_tokens": 36330976} {"current_steps": 172160, "total_steps": 181800, "loss": 0.0231, "lr": 4.2711088849332894e-07, "epoch": 18.93949394939494, "percentage": 94.7, "elapsed_time": "6:47:35", "remaining_time": "0:22:49", "throughput": 1485.63, "total_tokens": 36332032} {"current_steps": 172165, "total_steps": 181800, "loss": 0.0065, "lr": 4.2666925237582755e-07, "epoch": 18.94004400440044, "percentage": 94.7, "elapsed_time": "6:47:36", "remaining_time": "0:22:48", "throughput": 1485.63, "total_tokens": 36333024} {"current_steps": 172170, "total_steps": 181800, "loss": 0.0014, "lr": 4.262278427389271e-07, "epoch": 18.94059405940594, "percentage": 94.7, "elapsed_time": "6:47:37", "remaining_time": "0:22:47", "throughput": 1485.63, "total_tokens": 36334016} {"current_steps": 172175, "total_steps": 181800, "loss": 0.004, "lr": 4.2578665958669383e-07, "epoch": 18.94114411441144, "percentage": 94.71, "elapsed_time": "6:47:37", "remaining_time": "0:22:47", "throughput": 1485.63, "total_tokens": 36335040} {"current_steps": 172180, "total_steps": 181800, "loss": 0.004, "lr": 4.253457029231911e-07, "epoch": 18.94169416941694, "percentage": 94.71, "elapsed_time": "6:47:38", "remaining_time": "0:22:46", "throughput": 1485.63, "total_tokens": 36336064} {"current_steps": 172185, "total_steps": 181800, "loss": 0.0431, "lr": 4.2490497275248785e-07, "epoch": 18.942244224422442, "percentage": 94.71, "elapsed_time": "6:47:39", "remaining_time": "0:22:45", "throughput": 1485.63, "total_tokens": 36337088} {"current_steps": 172190, "total_steps": 181800, "loss": 0.0703, "lr": 4.24464469078642e-07, "epoch": 18.942794279427943, "percentage": 94.71, "elapsed_time": "6:47:39", "remaining_time": "0:22:45", "throughput": 1485.63, "total_tokens": 36338144} {"current_steps": 172195, "total_steps": 181800, "loss": 0.0887, "lr": 4.240241919057142e-07, "epoch": 18.943344334433444, "percentage": 94.72, "elapsed_time": "6:47:40", "remaining_time": "0:22:44", "throughput": 1485.63, "total_tokens": 36339136} {"current_steps": 172200, "total_steps": 181800, "loss": 0.005, "lr": 4.235841412377622e-07, "epoch": 18.943894389438945, "percentage": 94.72, "elapsed_time": "6:47:41", "remaining_time": "0:22:43", "throughput": 1485.63, "total_tokens": 36340224} {"current_steps": 172205, "total_steps": 181800, "loss": 0.0017, "lr": 4.2314431707884406e-07, "epoch": 18.944444444444443, "percentage": 94.72, "elapsed_time": "6:47:41", "remaining_time": "0:22:42", "throughput": 1485.63, "total_tokens": 36341280} {"current_steps": 172210, "total_steps": 181800, "loss": 0.0018, "lr": 4.2270471943300913e-07, "epoch": 18.944994499449944, "percentage": 94.72, "elapsed_time": "6:47:42", "remaining_time": "0:22:42", "throughput": 1485.63, "total_tokens": 36342368} {"current_steps": 172215, "total_steps": 181800, "loss": 0.0351, "lr": 4.2226534830431543e-07, "epoch": 18.945544554455445, "percentage": 94.73, "elapsed_time": "6:47:43", "remaining_time": "0:22:41", "throughput": 1485.63, "total_tokens": 36343392} {"current_steps": 172220, "total_steps": 181800, "loss": 0.0111, "lr": 4.2182620369680403e-07, "epoch": 18.946094609460946, "percentage": 94.73, "elapsed_time": "6:47:43", "remaining_time": "0:22:40", "throughput": 1485.63, "total_tokens": 36344416} {"current_steps": 172225, "total_steps": 181800, "loss": 0.0024, "lr": 4.213872856145273e-07, "epoch": 18.946644664466447, "percentage": 94.73, "elapsed_time": "6:47:44", "remaining_time": "0:22:40", "throughput": 1485.63, "total_tokens": 36345408} {"current_steps": 172230, "total_steps": 181800, "loss": 0.0024, "lr": 4.209485940615321e-07, "epoch": 18.94719471947195, "percentage": 94.74, "elapsed_time": "6:47:45", "remaining_time": "0:22:39", "throughput": 1485.63, "total_tokens": 36346464} {"current_steps": 172235, "total_steps": 181800, "loss": 0.0108, "lr": 4.205101290418595e-07, "epoch": 18.94774477447745, "percentage": 94.74, "elapsed_time": "6:47:46", "remaining_time": "0:22:38", "throughput": 1485.63, "total_tokens": 36347488} {"current_steps": 172240, "total_steps": 181800, "loss": 0.0787, "lr": 4.2007189055955076e-07, "epoch": 18.948294829482947, "percentage": 94.74, "elapsed_time": "6:47:46", "remaining_time": "0:22:37", "throughput": 1485.63, "total_tokens": 36348480} {"current_steps": 172245, "total_steps": 181800, "loss": 0.0061, "lr": 4.196338786186443e-07, "epoch": 18.948844884488448, "percentage": 94.74, "elapsed_time": "6:47:47", "remaining_time": "0:22:37", "throughput": 1485.63, "total_tokens": 36349504} {"current_steps": 172250, "total_steps": 181800, "loss": 0.0017, "lr": 4.191960932231759e-07, "epoch": 18.94939493949395, "percentage": 94.75, "elapsed_time": "6:47:48", "remaining_time": "0:22:36", "throughput": 1485.63, "total_tokens": 36350624} {"current_steps": 172255, "total_steps": 181800, "loss": 0.0051, "lr": 4.18758534377181e-07, "epoch": 18.94994499449945, "percentage": 94.75, "elapsed_time": "6:47:48", "remaining_time": "0:22:35", "throughput": 1485.64, "total_tokens": 36351680} {"current_steps": 172260, "total_steps": 181800, "loss": 0.0912, "lr": 4.183212020846983e-07, "epoch": 18.95049504950495, "percentage": 94.75, "elapsed_time": "6:47:49", "remaining_time": "0:22:35", "throughput": 1485.64, "total_tokens": 36352768} {"current_steps": 172265, "total_steps": 181800, "loss": 0.125, "lr": 4.178840963497521e-07, "epoch": 18.951045104510452, "percentage": 94.76, "elapsed_time": "6:47:50", "remaining_time": "0:22:34", "throughput": 1485.64, "total_tokens": 36353760} {"current_steps": 172270, "total_steps": 181800, "loss": 0.0912, "lr": 4.1744721717636993e-07, "epoch": 18.95159515951595, "percentage": 94.76, "elapsed_time": "6:47:50", "remaining_time": "0:22:33", "throughput": 1485.64, "total_tokens": 36354880} {"current_steps": 172275, "total_steps": 181800, "loss": 0.0639, "lr": 4.1701056456858456e-07, "epoch": 18.95214521452145, "percentage": 94.76, "elapsed_time": "6:47:51", "remaining_time": "0:22:33", "throughput": 1485.64, "total_tokens": 36355904} {"current_steps": 172280, "total_steps": 181800, "loss": 0.0241, "lr": 4.1657413853041225e-07, "epoch": 18.952695269526952, "percentage": 94.76, "elapsed_time": "6:47:52", "remaining_time": "0:22:32", "throughput": 1485.64, "total_tokens": 36356928} {"current_steps": 172285, "total_steps": 181800, "loss": 0.1035, "lr": 4.161379390658832e-07, "epoch": 18.953245324532453, "percentage": 94.77, "elapsed_time": "6:47:52", "remaining_time": "0:22:31", "throughput": 1485.64, "total_tokens": 36357952} {"current_steps": 172290, "total_steps": 181800, "loss": 0.004, "lr": 4.1570196617901346e-07, "epoch": 18.953795379537954, "percentage": 94.77, "elapsed_time": "6:47:53", "remaining_time": "0:22:30", "throughput": 1485.64, "total_tokens": 36359040} {"current_steps": 172295, "total_steps": 181800, "loss": 0.0742, "lr": 4.152662198738222e-07, "epoch": 18.954345434543455, "percentage": 94.77, "elapsed_time": "6:47:54", "remaining_time": "0:22:30", "throughput": 1485.64, "total_tokens": 36360096} {"current_steps": 172300, "total_steps": 181800, "loss": 0.0026, "lr": 4.1483070015432555e-07, "epoch": 18.954895489548957, "percentage": 94.77, "elapsed_time": "6:47:55", "remaining_time": "0:22:29", "throughput": 1485.65, "total_tokens": 36361216} {"current_steps": 172305, "total_steps": 181800, "loss": 0.0382, "lr": 4.1439540702453703e-07, "epoch": 18.955445544554454, "percentage": 94.78, "elapsed_time": "6:47:55", "remaining_time": "0:22:28", "throughput": 1485.65, "total_tokens": 36362336} {"current_steps": 172310, "total_steps": 181800, "loss": 0.0053, "lr": 4.1396034048846733e-07, "epoch": 18.955995599559955, "percentage": 94.78, "elapsed_time": "6:47:56", "remaining_time": "0:22:28", "throughput": 1485.65, "total_tokens": 36363424} {"current_steps": 172315, "total_steps": 181800, "loss": 0.003, "lr": 4.1352550055012985e-07, "epoch": 18.956545654565456, "percentage": 94.78, "elapsed_time": "6:47:57", "remaining_time": "0:22:27", "throughput": 1485.65, "total_tokens": 36364416} {"current_steps": 172320, "total_steps": 181800, "loss": 0.0483, "lr": 4.1309088721352694e-07, "epoch": 18.957095709570957, "percentage": 94.79, "elapsed_time": "6:47:57", "remaining_time": "0:22:26", "throughput": 1485.65, "total_tokens": 36365504} {"current_steps": 172325, "total_steps": 181800, "loss": 0.0583, "lr": 4.1265650048267214e-07, "epoch": 18.95764576457646, "percentage": 94.79, "elapsed_time": "6:47:58", "remaining_time": "0:22:25", "throughput": 1485.66, "total_tokens": 36366592} {"current_steps": 172330, "total_steps": 181800, "loss": 0.0031, "lr": 4.122223403615594e-07, "epoch": 18.95819581958196, "percentage": 94.79, "elapsed_time": "6:47:59", "remaining_time": "0:22:25", "throughput": 1485.66, "total_tokens": 36367680} {"current_steps": 172335, "total_steps": 181800, "loss": 0.0107, "lr": 4.117884068541994e-07, "epoch": 18.958745874587457, "percentage": 94.79, "elapsed_time": "6:47:59", "remaining_time": "0:22:24", "throughput": 1485.66, "total_tokens": 36368768} {"current_steps": 172340, "total_steps": 181800, "loss": 0.0321, "lr": 4.113546999645834e-07, "epoch": 18.959295929592958, "percentage": 94.8, "elapsed_time": "6:48:00", "remaining_time": "0:22:23", "throughput": 1485.66, "total_tokens": 36369760} {"current_steps": 172345, "total_steps": 181800, "loss": 0.0015, "lr": 4.109212196967138e-07, "epoch": 18.95984598459846, "percentage": 94.8, "elapsed_time": "6:48:01", "remaining_time": "0:22:23", "throughput": 1485.66, "total_tokens": 36370816} {"current_steps": 172350, "total_steps": 181800, "loss": 0.026, "lr": 4.104879660545846e-07, "epoch": 18.96039603960396, "percentage": 94.8, "elapsed_time": "6:48:01", "remaining_time": "0:22:22", "throughput": 1485.66, "total_tokens": 36371840} {"current_steps": 172355, "total_steps": 181800, "loss": 0.0064, "lr": 4.100549390421871e-07, "epoch": 18.96094609460946, "percentage": 94.8, "elapsed_time": "6:48:02", "remaining_time": "0:22:21", "throughput": 1485.66, "total_tokens": 36372896} {"current_steps": 172360, "total_steps": 181800, "loss": 0.0161, "lr": 4.0962213866351517e-07, "epoch": 18.961496149614963, "percentage": 94.81, "elapsed_time": "6:48:03", "remaining_time": "0:22:20", "throughput": 1485.66, "total_tokens": 36373888} {"current_steps": 172365, "total_steps": 181800, "loss": 0.0014, "lr": 4.0918956492255746e-07, "epoch": 18.962046204620464, "percentage": 94.81, "elapsed_time": "6:48:03", "remaining_time": "0:22:20", "throughput": 1485.66, "total_tokens": 36374976} {"current_steps": 172370, "total_steps": 181800, "loss": 0.0675, "lr": 4.087572178232968e-07, "epoch": 18.96259625962596, "percentage": 94.81, "elapsed_time": "6:48:04", "remaining_time": "0:22:19", "throughput": 1485.66, "total_tokens": 36376000} {"current_steps": 172375, "total_steps": 181800, "loss": 0.0203, "lr": 4.083250973697245e-07, "epoch": 18.963146314631462, "percentage": 94.82, "elapsed_time": "6:48:05", "remaining_time": "0:22:18", "throughput": 1485.66, "total_tokens": 36376992} {"current_steps": 172380, "total_steps": 181800, "loss": 0.02, "lr": 4.0789320356581786e-07, "epoch": 18.963696369636963, "percentage": 94.82, "elapsed_time": "6:48:06", "remaining_time": "0:22:18", "throughput": 1485.66, "total_tokens": 36378048} {"current_steps": 172385, "total_steps": 181800, "loss": 0.1393, "lr": 4.0746153641555705e-07, "epoch": 18.964246424642464, "percentage": 94.82, "elapsed_time": "6:48:06", "remaining_time": "0:22:17", "throughput": 1485.66, "total_tokens": 36379040} {"current_steps": 172390, "total_steps": 181800, "loss": 0.0015, "lr": 4.070300959229251e-07, "epoch": 18.964796479647966, "percentage": 94.82, "elapsed_time": "6:48:07", "remaining_time": "0:22:16", "throughput": 1485.66, "total_tokens": 36380096} {"current_steps": 172395, "total_steps": 181800, "loss": 0.0023, "lr": 4.065988820918937e-07, "epoch": 18.965346534653467, "percentage": 94.83, "elapsed_time": "6:48:08", "remaining_time": "0:22:15", "throughput": 1485.66, "total_tokens": 36381120} {"current_steps": 172400, "total_steps": 181800, "loss": 0.0621, "lr": 4.0616789492644025e-07, "epoch": 18.965896589658964, "percentage": 94.83, "elapsed_time": "6:48:08", "remaining_time": "0:22:15", "throughput": 1485.67, "total_tokens": 36382208} {"current_steps": 172405, "total_steps": 181800, "loss": 0.0105, "lr": 4.057371344305394e-07, "epoch": 18.966446644664465, "percentage": 94.83, "elapsed_time": "6:48:09", "remaining_time": "0:22:14", "throughput": 1485.67, "total_tokens": 36383264} {"current_steps": 172410, "total_steps": 181800, "loss": 0.0028, "lr": 4.0530660060815464e-07, "epoch": 18.966996699669966, "percentage": 94.83, "elapsed_time": "6:48:10", "remaining_time": "0:22:13", "throughput": 1485.67, "total_tokens": 36384352} {"current_steps": 172415, "total_steps": 181800, "loss": 0.0025, "lr": 4.0487629346325773e-07, "epoch": 18.967546754675467, "percentage": 94.84, "elapsed_time": "6:48:10", "remaining_time": "0:22:13", "throughput": 1485.67, "total_tokens": 36385376} {"current_steps": 172420, "total_steps": 181800, "loss": 0.0771, "lr": 4.0444621299981225e-07, "epoch": 18.96809680968097, "percentage": 94.84, "elapsed_time": "6:48:11", "remaining_time": "0:22:12", "throughput": 1485.67, "total_tokens": 36386432} {"current_steps": 172425, "total_steps": 181800, "loss": 0.0013, "lr": 4.040163592217872e-07, "epoch": 18.96864686468647, "percentage": 94.84, "elapsed_time": "6:48:12", "remaining_time": "0:22:11", "throughput": 1485.67, "total_tokens": 36387520} {"current_steps": 172430, "total_steps": 181800, "loss": 0.0022, "lr": 4.035867321331405e-07, "epoch": 18.96919691969197, "percentage": 94.85, "elapsed_time": "6:48:12", "remaining_time": "0:22:10", "throughput": 1485.68, "total_tokens": 36388640} {"current_steps": 172435, "total_steps": 181800, "loss": 0.0036, "lr": 4.031573317378301e-07, "epoch": 18.96974697469747, "percentage": 94.85, "elapsed_time": "6:48:13", "remaining_time": "0:22:10", "throughput": 1485.68, "total_tokens": 36389664} {"current_steps": 172440, "total_steps": 181800, "loss": 0.0063, "lr": 4.0272815803981954e-07, "epoch": 18.97029702970297, "percentage": 94.85, "elapsed_time": "6:48:14", "remaining_time": "0:22:09", "throughput": 1485.68, "total_tokens": 36390752} {"current_steps": 172445, "total_steps": 181800, "loss": 0.003, "lr": 4.022992110430557e-07, "epoch": 18.97084708470847, "percentage": 94.85, "elapsed_time": "6:48:15", "remaining_time": "0:22:08", "throughput": 1485.68, "total_tokens": 36391808} {"current_steps": 172450, "total_steps": 181800, "loss": 0.0022, "lr": 4.0187049075150194e-07, "epoch": 18.97139713971397, "percentage": 94.86, "elapsed_time": "6:48:15", "remaining_time": "0:22:08", "throughput": 1485.69, "total_tokens": 36392928} {"current_steps": 172455, "total_steps": 181800, "loss": 0.0032, "lr": 4.014419971690997e-07, "epoch": 18.971947194719473, "percentage": 94.86, "elapsed_time": "6:48:16", "remaining_time": "0:22:07", "throughput": 1485.69, "total_tokens": 36393984} {"current_steps": 172460, "total_steps": 181800, "loss": 0.0669, "lr": 4.0101373029980683e-07, "epoch": 18.972497249724974, "percentage": 94.86, "elapsed_time": "6:48:17", "remaining_time": "0:22:06", "throughput": 1485.68, "total_tokens": 36394976} {"current_steps": 172465, "total_steps": 181800, "loss": 0.0448, "lr": 4.005856901475646e-07, "epoch": 18.97304730473047, "percentage": 94.87, "elapsed_time": "6:48:17", "remaining_time": "0:22:05", "throughput": 1485.69, "total_tokens": 36396096} {"current_steps": 172470, "total_steps": 181800, "loss": 0.0052, "lr": 4.0015787671632e-07, "epoch": 18.973597359735972, "percentage": 94.87, "elapsed_time": "6:48:18", "remaining_time": "0:22:05", "throughput": 1485.69, "total_tokens": 36397120} {"current_steps": 172475, "total_steps": 181800, "loss": 0.0016, "lr": 3.997302900100197e-07, "epoch": 18.974147414741473, "percentage": 94.87, "elapsed_time": "6:48:19", "remaining_time": "0:22:04", "throughput": 1485.69, "total_tokens": 36398272} {"current_steps": 172480, "total_steps": 181800, "loss": 0.0091, "lr": 3.9930293003259957e-07, "epoch": 18.974697469746975, "percentage": 94.87, "elapsed_time": "6:48:19", "remaining_time": "0:22:03", "throughput": 1485.69, "total_tokens": 36399296} {"current_steps": 172485, "total_steps": 181800, "loss": 0.0011, "lr": 3.9887579678799526e-07, "epoch": 18.975247524752476, "percentage": 94.88, "elapsed_time": "6:48:20", "remaining_time": "0:22:03", "throughput": 1485.69, "total_tokens": 36400288} {"current_steps": 172490, "total_steps": 181800, "loss": 0.0015, "lr": 3.984488902801509e-07, "epoch": 18.975797579757977, "percentage": 94.88, "elapsed_time": "6:48:21", "remaining_time": "0:22:02", "throughput": 1485.69, "total_tokens": 36401312} {"current_steps": 172495, "total_steps": 181800, "loss": 0.0128, "lr": 3.9802221051299935e-07, "epoch": 18.976347634763478, "percentage": 94.88, "elapsed_time": "6:48:21", "remaining_time": "0:22:01", "throughput": 1485.69, "total_tokens": 36402336} {"current_steps": 172500, "total_steps": 181800, "loss": 0.0437, "lr": 3.9759575749047096e-07, "epoch": 18.976897689768975, "percentage": 94.88, "elapsed_time": "6:48:22", "remaining_time": "0:22:01", "throughput": 1485.7, "total_tokens": 36403456} {"current_steps": 172505, "total_steps": 181800, "loss": 0.0015, "lr": 3.971695312164986e-07, "epoch": 18.977447744774476, "percentage": 94.89, "elapsed_time": "6:48:23", "remaining_time": "0:22:00", "throughput": 1485.7, "total_tokens": 36404544} {"current_steps": 172510, "total_steps": 181800, "loss": 0.0029, "lr": 3.967435316950069e-07, "epoch": 18.977997799779978, "percentage": 94.89, "elapsed_time": "6:48:24", "remaining_time": "0:21:59", "throughput": 1485.7, "total_tokens": 36405632} {"current_steps": 172515, "total_steps": 181800, "loss": 0.0107, "lr": 3.963177589299233e-07, "epoch": 18.97854785478548, "percentage": 94.89, "elapsed_time": "6:48:24", "remaining_time": "0:21:58", "throughput": 1485.7, "total_tokens": 36406656} {"current_steps": 172520, "total_steps": 181800, "loss": 0.0084, "lr": 3.958922129251752e-07, "epoch": 18.97909790979098, "percentage": 94.9, "elapsed_time": "6:48:25", "remaining_time": "0:21:58", "throughput": 1485.7, "total_tokens": 36407680} {"current_steps": 172525, "total_steps": 181800, "loss": 0.001, "lr": 3.954668936846817e-07, "epoch": 18.97964796479648, "percentage": 94.9, "elapsed_time": "6:48:26", "remaining_time": "0:21:57", "throughput": 1485.7, "total_tokens": 36408672} {"current_steps": 172530, "total_steps": 181800, "loss": 0.0701, "lr": 3.9504180121236465e-07, "epoch": 18.980198019801982, "percentage": 94.9, "elapsed_time": "6:48:26", "remaining_time": "0:21:56", "throughput": 1485.7, "total_tokens": 36409760} {"current_steps": 172535, "total_steps": 181800, "loss": 0.0026, "lr": 3.946169355121404e-07, "epoch": 18.98074807480748, "percentage": 94.9, "elapsed_time": "6:48:27", "remaining_time": "0:21:56", "throughput": 1485.7, "total_tokens": 36410816} {"current_steps": 172540, "total_steps": 181800, "loss": 0.0662, "lr": 3.9419229658792523e-07, "epoch": 18.98129812981298, "percentage": 94.91, "elapsed_time": "6:48:28", "remaining_time": "0:21:55", "throughput": 1485.7, "total_tokens": 36411840} {"current_steps": 172545, "total_steps": 181800, "loss": 0.0406, "lr": 3.937678844436271e-07, "epoch": 18.98184818481848, "percentage": 94.91, "elapsed_time": "6:48:28", "remaining_time": "0:21:54", "throughput": 1485.71, "total_tokens": 36412928} {"current_steps": 172550, "total_steps": 181800, "loss": 0.0092, "lr": 3.933436990831707e-07, "epoch": 18.982398239823983, "percentage": 94.91, "elapsed_time": "6:48:29", "remaining_time": "0:21:53", "throughput": 1485.71, "total_tokens": 36413952} {"current_steps": 172555, "total_steps": 181800, "loss": 0.0303, "lr": 3.929197405104557e-07, "epoch": 18.982948294829484, "percentage": 94.91, "elapsed_time": "6:48:30", "remaining_time": "0:21:53", "throughput": 1485.71, "total_tokens": 36415008} {"current_steps": 172560, "total_steps": 181800, "loss": 0.0033, "lr": 3.9249600872938994e-07, "epoch": 18.983498349834985, "percentage": 94.92, "elapsed_time": "6:48:30", "remaining_time": "0:21:52", "throughput": 1485.71, "total_tokens": 36416032} {"current_steps": 172565, "total_steps": 181800, "loss": 0.0028, "lr": 3.920725037438816e-07, "epoch": 18.984048404840483, "percentage": 94.92, "elapsed_time": "6:48:31", "remaining_time": "0:21:51", "throughput": 1485.71, "total_tokens": 36417088} {"current_steps": 172570, "total_steps": 181800, "loss": 0.0018, "lr": 3.91649225557833e-07, "epoch": 18.984598459845984, "percentage": 94.92, "elapsed_time": "6:48:32", "remaining_time": "0:21:51", "throughput": 1485.71, "total_tokens": 36418144} {"current_steps": 172575, "total_steps": 181800, "loss": 0.0031, "lr": 3.9122617417514384e-07, "epoch": 18.985148514851485, "percentage": 94.93, "elapsed_time": "6:48:32", "remaining_time": "0:21:50", "throughput": 1485.71, "total_tokens": 36419232} {"current_steps": 172580, "total_steps": 181800, "loss": 0.0541, "lr": 3.908033495997193e-07, "epoch": 18.985698569856986, "percentage": 94.93, "elapsed_time": "6:48:33", "remaining_time": "0:21:49", "throughput": 1485.71, "total_tokens": 36420256} {"current_steps": 172585, "total_steps": 181800, "loss": 0.0523, "lr": 3.903807518354452e-07, "epoch": 18.986248624862487, "percentage": 94.93, "elapsed_time": "6:48:34", "remaining_time": "0:21:48", "throughput": 1485.71, "total_tokens": 36421344} {"current_steps": 172590, "total_steps": 181800, "loss": 0.0264, "lr": 3.899583808862295e-07, "epoch": 18.986798679867988, "percentage": 94.93, "elapsed_time": "6:48:35", "remaining_time": "0:21:48", "throughput": 1485.71, "total_tokens": 36422400} {"current_steps": 172595, "total_steps": 181800, "loss": 0.0636, "lr": 3.895362367559552e-07, "epoch": 18.98734873487349, "percentage": 94.94, "elapsed_time": "6:48:35", "remaining_time": "0:21:47", "throughput": 1485.72, "total_tokens": 36423488} {"current_steps": 172600, "total_steps": 181800, "loss": 0.0024, "lr": 3.891143194485164e-07, "epoch": 18.987898789878987, "percentage": 94.94, "elapsed_time": "6:48:36", "remaining_time": "0:21:46", "throughput": 1485.72, "total_tokens": 36424544} {"current_steps": 172605, "total_steps": 181800, "loss": 0.0429, "lr": 3.886926289677989e-07, "epoch": 18.988448844884488, "percentage": 94.94, "elapsed_time": "6:48:37", "remaining_time": "0:21:46", "throughput": 1485.72, "total_tokens": 36425600} {"current_steps": 172610, "total_steps": 181800, "loss": 0.039, "lr": 3.88271165317694e-07, "epoch": 18.98899889988999, "percentage": 94.94, "elapsed_time": "6:48:37", "remaining_time": "0:21:45", "throughput": 1485.72, "total_tokens": 36426752} {"current_steps": 172615, "total_steps": 181800, "loss": 0.0021, "lr": 3.878499285020848e-07, "epoch": 18.98954895489549, "percentage": 94.95, "elapsed_time": "6:48:38", "remaining_time": "0:21:44", "throughput": 1485.73, "total_tokens": 36427808} {"current_steps": 172620, "total_steps": 181800, "loss": 0.0137, "lr": 3.8742891852485143e-07, "epoch": 18.99009900990099, "percentage": 94.95, "elapsed_time": "6:48:39", "remaining_time": "0:21:43", "throughput": 1485.73, "total_tokens": 36428896} {"current_steps": 172625, "total_steps": 181800, "loss": 0.0405, "lr": 3.870081353898769e-07, "epoch": 18.990649064906492, "percentage": 94.95, "elapsed_time": "6:48:39", "remaining_time": "0:21:43", "throughput": 1485.73, "total_tokens": 36429984} {"current_steps": 172630, "total_steps": 181800, "loss": 0.0057, "lr": 3.865875791010359e-07, "epoch": 18.99119911991199, "percentage": 94.96, "elapsed_time": "6:48:40", "remaining_time": "0:21:42", "throughput": 1485.73, "total_tokens": 36431040} {"current_steps": 172635, "total_steps": 181800, "loss": 0.0013, "lr": 3.8616724966220596e-07, "epoch": 18.99174917491749, "percentage": 94.96, "elapsed_time": "6:48:41", "remaining_time": "0:21:41", "throughput": 1485.73, "total_tokens": 36432032} {"current_steps": 172640, "total_steps": 181800, "loss": 0.0198, "lr": 3.8574714707726444e-07, "epoch": 18.992299229922992, "percentage": 94.96, "elapsed_time": "6:48:41", "remaining_time": "0:21:41", "throughput": 1485.73, "total_tokens": 36433024} {"current_steps": 172645, "total_steps": 181800, "loss": 0.1289, "lr": 3.853272713500805e-07, "epoch": 18.992849284928493, "percentage": 94.96, "elapsed_time": "6:48:42", "remaining_time": "0:21:40", "throughput": 1485.73, "total_tokens": 36434112} {"current_steps": 172650, "total_steps": 181800, "loss": 0.02, "lr": 3.849076224845205e-07, "epoch": 18.993399339933994, "percentage": 94.97, "elapsed_time": "6:48:43", "remaining_time": "0:21:39", "throughput": 1485.73, "total_tokens": 36435136} {"current_steps": 172655, "total_steps": 181800, "loss": 0.1081, "lr": 3.844882004844591e-07, "epoch": 18.993949394939495, "percentage": 94.97, "elapsed_time": "6:48:44", "remaining_time": "0:21:38", "throughput": 1485.74, "total_tokens": 36436288} {"current_steps": 172660, "total_steps": 181800, "loss": 0.0078, "lr": 3.8406900535375713e-07, "epoch": 18.994499449944996, "percentage": 94.97, "elapsed_time": "6:48:44", "remaining_time": "0:21:38", "throughput": 1485.74, "total_tokens": 36437344} {"current_steps": 172665, "total_steps": 181800, "loss": 0.0313, "lr": 3.8365003709627535e-07, "epoch": 18.995049504950494, "percentage": 94.98, "elapsed_time": "6:48:45", "remaining_time": "0:21:37", "throughput": 1485.74, "total_tokens": 36438336} {"current_steps": 172670, "total_steps": 181800, "loss": 0.035, "lr": 3.832312957158857e-07, "epoch": 18.995599559955995, "percentage": 94.98, "elapsed_time": "6:48:46", "remaining_time": "0:21:36", "throughput": 1485.74, "total_tokens": 36439360} {"current_steps": 172675, "total_steps": 181800, "loss": 0.0022, "lr": 3.82812781216435e-07, "epoch": 18.996149614961496, "percentage": 94.98, "elapsed_time": "6:48:46", "remaining_time": "0:21:36", "throughput": 1485.74, "total_tokens": 36440416} {"current_steps": 172680, "total_steps": 181800, "loss": 0.0796, "lr": 3.823944936017926e-07, "epoch": 18.996699669966997, "percentage": 94.98, "elapsed_time": "6:48:47", "remaining_time": "0:21:35", "throughput": 1485.74, "total_tokens": 36441408} {"current_steps": 172685, "total_steps": 181800, "loss": 0.1083, "lr": 3.8197643287580243e-07, "epoch": 18.997249724972498, "percentage": 94.99, "elapsed_time": "6:48:48", "remaining_time": "0:21:34", "throughput": 1485.74, "total_tokens": 36442496} {"current_steps": 172690, "total_steps": 181800, "loss": 0.0012, "lr": 3.815585990423226e-07, "epoch": 18.997799779978, "percentage": 94.99, "elapsed_time": "6:48:48", "remaining_time": "0:21:33", "throughput": 1485.74, "total_tokens": 36443552} {"current_steps": 172695, "total_steps": 181800, "loss": 0.0054, "lr": 3.8114099210520836e-07, "epoch": 18.998349834983497, "percentage": 94.99, "elapsed_time": "6:48:49", "remaining_time": "0:21:33", "throughput": 1485.74, "total_tokens": 36444608} {"current_steps": 172700, "total_steps": 181800, "loss": 0.0404, "lr": 3.8072361206829834e-07, "epoch": 18.998899889988998, "percentage": 94.99, "elapsed_time": "6:48:50", "remaining_time": "0:21:32", "throughput": 1485.74, "total_tokens": 36445632} {"current_steps": 172705, "total_steps": 181800, "loss": 0.1746, "lr": 3.803064589354505e-07, "epoch": 18.9994499449945, "percentage": 95.0, "elapsed_time": "6:48:50", "remaining_time": "0:21:31", "throughput": 1485.74, "total_tokens": 36446624} {"current_steps": 172710, "total_steps": 181800, "loss": 0.0019, "lr": 3.7988953271050065e-07, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "6:48:51", "remaining_time": "0:21:31", "throughput": 1485.74, "total_tokens": 36447600} {"current_steps": 172710, "total_steps": 181800, "eval_loss": 0.07838060706853867, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "6:49:28", "remaining_time": "0:21:33", "throughput": 1483.5, "total_tokens": 36447600} {"current_steps": 172715, "total_steps": 181800, "loss": 0.0017, "lr": 3.7947283339729853e-07, "epoch": 19.0005500550055, "percentage": 95.0, "elapsed_time": "6:49:31", "remaining_time": "0:21:32", "throughput": 1483.38, "total_tokens": 36448624} {"current_steps": 172720, "total_steps": 181800, "loss": 0.0692, "lr": 3.7905636099968e-07, "epoch": 19.001100110011002, "percentage": 95.01, "elapsed_time": "6:49:32", "remaining_time": "0:21:31", "throughput": 1483.38, "total_tokens": 36449712} {"current_steps": 172725, "total_steps": 181800, "loss": 0.0051, "lr": 3.786401155214836e-07, "epoch": 19.001650165016503, "percentage": 95.01, "elapsed_time": "6:49:32", "remaining_time": "0:21:31", "throughput": 1483.38, "total_tokens": 36450768} {"current_steps": 172730, "total_steps": 181800, "loss": 0.0055, "lr": 3.782240969665479e-07, "epoch": 19.002200220022, "percentage": 95.01, "elapsed_time": "6:49:33", "remaining_time": "0:21:30", "throughput": 1483.38, "total_tokens": 36451792} {"current_steps": 172735, "total_steps": 181800, "loss": 0.0232, "lr": 3.7780830533870604e-07, "epoch": 19.002750275027502, "percentage": 95.01, "elapsed_time": "6:49:34", "remaining_time": "0:21:29", "throughput": 1483.38, "total_tokens": 36452880} {"current_steps": 172740, "total_steps": 181800, "loss": 0.0032, "lr": 3.77392740641791e-07, "epoch": 19.003300330033003, "percentage": 95.02, "elapsed_time": "6:49:34", "remaining_time": "0:21:28", "throughput": 1483.38, "total_tokens": 36453904} {"current_steps": 172745, "total_steps": 181800, "loss": 0.0083, "lr": 3.7697740287962744e-07, "epoch": 19.003850385038504, "percentage": 95.02, "elapsed_time": "6:49:35", "remaining_time": "0:21:28", "throughput": 1483.38, "total_tokens": 36454928} {"current_steps": 172750, "total_steps": 181800, "loss": 0.0025, "lr": 3.7656229205605133e-07, "epoch": 19.004400440044005, "percentage": 95.02, "elapsed_time": "6:49:36", "remaining_time": "0:21:27", "throughput": 1483.38, "total_tokens": 36455920} {"current_steps": 172755, "total_steps": 181800, "loss": 0.0044, "lr": 3.761474081748873e-07, "epoch": 19.004950495049506, "percentage": 95.02, "elapsed_time": "6:49:37", "remaining_time": "0:21:26", "throughput": 1483.37, "total_tokens": 36457008} {"current_steps": 172760, "total_steps": 181800, "loss": 0.0242, "lr": 3.7573275123995445e-07, "epoch": 19.005500550055004, "percentage": 95.03, "elapsed_time": "6:49:37", "remaining_time": "0:21:26", "throughput": 1483.38, "total_tokens": 36458096} {"current_steps": 172765, "total_steps": 181800, "loss": 0.0522, "lr": 3.753183212550776e-07, "epoch": 19.006050605060505, "percentage": 95.03, "elapsed_time": "6:49:38", "remaining_time": "0:21:25", "throughput": 1483.38, "total_tokens": 36459152} {"current_steps": 172770, "total_steps": 181800, "loss": 0.0055, "lr": 3.749041182240759e-07, "epoch": 19.006600660066006, "percentage": 95.03, "elapsed_time": "6:49:39", "remaining_time": "0:21:24", "throughput": 1483.37, "total_tokens": 36460144} {"current_steps": 172775, "total_steps": 181800, "loss": 0.0256, "lr": 3.7449014215076297e-07, "epoch": 19.007150715071507, "percentage": 95.04, "elapsed_time": "6:49:39", "remaining_time": "0:21:23", "throughput": 1483.37, "total_tokens": 36461200} {"current_steps": 172780, "total_steps": 181800, "loss": 0.0641, "lr": 3.740763930389607e-07, "epoch": 19.007700770077008, "percentage": 95.04, "elapsed_time": "6:49:40", "remaining_time": "0:21:23", "throughput": 1483.37, "total_tokens": 36462288} {"current_steps": 172785, "total_steps": 181800, "loss": 0.0031, "lr": 3.7366287089248273e-07, "epoch": 19.00825082508251, "percentage": 95.04, "elapsed_time": "6:49:41", "remaining_time": "0:21:22", "throughput": 1483.38, "total_tokens": 36463408} {"current_steps": 172790, "total_steps": 181800, "loss": 0.0165, "lr": 3.7324957571513163e-07, "epoch": 19.00880088008801, "percentage": 95.04, "elapsed_time": "6:49:42", "remaining_time": "0:21:21", "throughput": 1483.38, "total_tokens": 36464432} {"current_steps": 172795, "total_steps": 181800, "loss": 0.0038, "lr": 3.7283650751072654e-07, "epoch": 19.009350935093508, "percentage": 95.05, "elapsed_time": "6:49:42", "remaining_time": "0:21:21", "throughput": 1483.38, "total_tokens": 36465552} {"current_steps": 172800, "total_steps": 181800, "loss": 0.0008, "lr": 3.7242366628306714e-07, "epoch": 19.00990099009901, "percentage": 95.05, "elapsed_time": "6:49:43", "remaining_time": "0:21:20", "throughput": 1483.38, "total_tokens": 36466608} {"current_steps": 172805, "total_steps": 181800, "loss": 0.0341, "lr": 3.7201105203596154e-07, "epoch": 19.01045104510451, "percentage": 95.05, "elapsed_time": "6:49:44", "remaining_time": "0:21:19", "throughput": 1483.38, "total_tokens": 36467632} {"current_steps": 172810, "total_steps": 181800, "loss": 0.0073, "lr": 3.71598664773215e-07, "epoch": 19.01100110011001, "percentage": 95.06, "elapsed_time": "6:49:44", "remaining_time": "0:21:18", "throughput": 1483.38, "total_tokens": 36468656} {"current_steps": 172815, "total_steps": 181800, "loss": 0.0051, "lr": 3.711865044986246e-07, "epoch": 19.011551155115512, "percentage": 95.06, "elapsed_time": "6:49:45", "remaining_time": "0:21:18", "throughput": 1483.38, "total_tokens": 36469680} {"current_steps": 172820, "total_steps": 181800, "loss": 0.0013, "lr": 3.707745712159899e-07, "epoch": 19.012101210121013, "percentage": 95.06, "elapsed_time": "6:49:46", "remaining_time": "0:21:17", "throughput": 1483.38, "total_tokens": 36470736} {"current_steps": 172825, "total_steps": 181800, "loss": 0.0658, "lr": 3.70362864929108e-07, "epoch": 19.01265126512651, "percentage": 95.06, "elapsed_time": "6:49:46", "remaining_time": "0:21:16", "throughput": 1483.38, "total_tokens": 36471760} {"current_steps": 172830, "total_steps": 181800, "loss": 0.091, "lr": 3.69951385641773e-07, "epoch": 19.013201320132012, "percentage": 95.07, "elapsed_time": "6:49:47", "remaining_time": "0:21:16", "throughput": 1483.38, "total_tokens": 36472848} {"current_steps": 172835, "total_steps": 181800, "loss": 0.1057, "lr": 3.6954013335777636e-07, "epoch": 19.013751375137513, "percentage": 95.07, "elapsed_time": "6:49:48", "remaining_time": "0:21:15", "throughput": 1483.38, "total_tokens": 36473904} {"current_steps": 172840, "total_steps": 181800, "loss": 0.0008, "lr": 3.691291080809095e-07, "epoch": 19.014301430143014, "percentage": 95.07, "elapsed_time": "6:49:48", "remaining_time": "0:21:14", "throughput": 1483.39, "total_tokens": 36474960} {"current_steps": 172845, "total_steps": 181800, "loss": 0.0068, "lr": 3.6871830981496104e-07, "epoch": 19.014851485148515, "percentage": 95.07, "elapsed_time": "6:49:49", "remaining_time": "0:21:13", "throughput": 1483.38, "total_tokens": 36475952} {"current_steps": 172850, "total_steps": 181800, "loss": 0.1246, "lr": 3.6830773856371683e-07, "epoch": 19.015401540154016, "percentage": 95.08, "elapsed_time": "6:49:50", "remaining_time": "0:21:13", "throughput": 1483.38, "total_tokens": 36476976} {"current_steps": 172855, "total_steps": 181800, "loss": 0.0076, "lr": 3.678973943309627e-07, "epoch": 19.015951595159517, "percentage": 95.08, "elapsed_time": "6:49:51", "remaining_time": "0:21:12", "throughput": 1483.39, "total_tokens": 36478032} {"current_steps": 172860, "total_steps": 181800, "loss": 0.1643, "lr": 3.6748727712047624e-07, "epoch": 19.016501650165015, "percentage": 95.08, "elapsed_time": "6:49:51", "remaining_time": "0:21:11", "throughput": 1483.38, "total_tokens": 36479024} {"current_steps": 172865, "total_steps": 181800, "loss": 0.0514, "lr": 3.6707738693603776e-07, "epoch": 19.017051705170516, "percentage": 95.09, "elapsed_time": "6:49:52", "remaining_time": "0:21:11", "throughput": 1483.39, "total_tokens": 36480080} {"current_steps": 172870, "total_steps": 181800, "loss": 0.0488, "lr": 3.6666772378143034e-07, "epoch": 19.017601760176017, "percentage": 95.09, "elapsed_time": "6:49:53", "remaining_time": "0:21:10", "throughput": 1483.39, "total_tokens": 36481200} {"current_steps": 172875, "total_steps": 181800, "loss": 0.0021, "lr": 3.662582876604259e-07, "epoch": 19.01815181518152, "percentage": 95.09, "elapsed_time": "6:49:53", "remaining_time": "0:21:09", "throughput": 1483.39, "total_tokens": 36482160} {"current_steps": 172880, "total_steps": 181800, "loss": 0.0037, "lr": 3.6584907857679926e-07, "epoch": 19.01870187018702, "percentage": 95.09, "elapsed_time": "6:49:54", "remaining_time": "0:21:08", "throughput": 1483.39, "total_tokens": 36483248} {"current_steps": 172885, "total_steps": 181800, "loss": 0.0347, "lr": 3.6544009653431966e-07, "epoch": 19.01925192519252, "percentage": 95.1, "elapsed_time": "6:49:55", "remaining_time": "0:21:08", "throughput": 1483.39, "total_tokens": 36484336} {"current_steps": 172890, "total_steps": 181800, "loss": 0.1021, "lr": 3.65031341536759e-07, "epoch": 19.019801980198018, "percentage": 95.1, "elapsed_time": "6:49:55", "remaining_time": "0:21:07", "throughput": 1483.39, "total_tokens": 36485456} {"current_steps": 172895, "total_steps": 181800, "loss": 0.0021, "lr": 3.6462281358788097e-07, "epoch": 19.02035203520352, "percentage": 95.1, "elapsed_time": "6:49:56", "remaining_time": "0:21:06", "throughput": 1483.39, "total_tokens": 36486480} {"current_steps": 172900, "total_steps": 181800, "loss": 0.0041, "lr": 3.6421451269145477e-07, "epoch": 19.02090209020902, "percentage": 95.1, "elapsed_time": "6:49:57", "remaining_time": "0:21:06", "throughput": 1483.4, "total_tokens": 36487632} {"current_steps": 172905, "total_steps": 181800, "loss": 0.0701, "lr": 3.6380643885124135e-07, "epoch": 19.02145214521452, "percentage": 95.11, "elapsed_time": "6:49:57", "remaining_time": "0:21:05", "throughput": 1483.4, "total_tokens": 36488720} {"current_steps": 172910, "total_steps": 181800, "loss": 0.0026, "lr": 3.6339859207100424e-07, "epoch": 19.022002200220022, "percentage": 95.11, "elapsed_time": "6:49:58", "remaining_time": "0:21:04", "throughput": 1483.41, "total_tokens": 36489840} {"current_steps": 172915, "total_steps": 181800, "loss": 0.0437, "lr": 3.629909723544989e-07, "epoch": 19.022552255225524, "percentage": 95.11, "elapsed_time": "6:49:59", "remaining_time": "0:21:04", "throughput": 1483.41, "total_tokens": 36490896} {"current_steps": 172920, "total_steps": 181800, "loss": 0.0788, "lr": 3.625835797054833e-07, "epoch": 19.023102310231025, "percentage": 95.12, "elapsed_time": "6:50:00", "remaining_time": "0:21:03", "throughput": 1483.41, "total_tokens": 36492016} {"current_steps": 172925, "total_steps": 181800, "loss": 0.007, "lr": 3.6217641412771287e-07, "epoch": 19.023652365236522, "percentage": 95.12, "elapsed_time": "6:50:00", "remaining_time": "0:21:02", "throughput": 1483.41, "total_tokens": 36493040} {"current_steps": 172930, "total_steps": 181800, "loss": 0.0113, "lr": 3.617694756249429e-07, "epoch": 19.024202420242023, "percentage": 95.12, "elapsed_time": "6:50:01", "remaining_time": "0:21:01", "throughput": 1483.41, "total_tokens": 36494064} {"current_steps": 172935, "total_steps": 181800, "loss": 0.1038, "lr": 3.613627642009204e-07, "epoch": 19.024752475247524, "percentage": 95.12, "elapsed_time": "6:50:02", "remaining_time": "0:21:01", "throughput": 1483.41, "total_tokens": 36495184} {"current_steps": 172940, "total_steps": 181800, "loss": 0.0349, "lr": 3.6095627985938965e-07, "epoch": 19.025302530253025, "percentage": 95.13, "elapsed_time": "6:50:02", "remaining_time": "0:21:00", "throughput": 1483.41, "total_tokens": 36496208} {"current_steps": 172945, "total_steps": 181800, "loss": 0.05, "lr": 3.605500226041086e-07, "epoch": 19.025852585258527, "percentage": 95.13, "elapsed_time": "6:50:03", "remaining_time": "0:20:59", "throughput": 1483.42, "total_tokens": 36497264} {"current_steps": 172950, "total_steps": 181800, "loss": 0.0028, "lr": 3.601439924388106e-07, "epoch": 19.026402640264028, "percentage": 95.13, "elapsed_time": "6:50:04", "remaining_time": "0:20:59", "throughput": 1483.42, "total_tokens": 36498288} {"current_steps": 172955, "total_steps": 181800, "loss": 0.0062, "lr": 3.597381893672425e-07, "epoch": 19.02695269526953, "percentage": 95.13, "elapsed_time": "6:50:04", "remaining_time": "0:20:58", "throughput": 1483.42, "total_tokens": 36499344} {"current_steps": 172960, "total_steps": 181800, "loss": 0.0099, "lr": 3.593326133931457e-07, "epoch": 19.027502750275026, "percentage": 95.14, "elapsed_time": "6:50:05", "remaining_time": "0:20:57", "throughput": 1483.42, "total_tokens": 36500400} {"current_steps": 172965, "total_steps": 181800, "loss": 0.0028, "lr": 3.589272645202535e-07, "epoch": 19.028052805280527, "percentage": 95.14, "elapsed_time": "6:50:06", "remaining_time": "0:20:56", "throughput": 1483.42, "total_tokens": 36501424} {"current_steps": 172970, "total_steps": 181800, "loss": 0.0044, "lr": 3.5852214275230724e-07, "epoch": 19.02860286028603, "percentage": 95.14, "elapsed_time": "6:50:06", "remaining_time": "0:20:56", "throughput": 1483.42, "total_tokens": 36502480} {"current_steps": 172975, "total_steps": 181800, "loss": 0.0184, "lr": 3.5811724809303725e-07, "epoch": 19.02915291529153, "percentage": 95.15, "elapsed_time": "6:50:07", "remaining_time": "0:20:55", "throughput": 1483.42, "total_tokens": 36503568} {"current_steps": 172980, "total_steps": 181800, "loss": 0.0135, "lr": 3.577125805461767e-07, "epoch": 19.02970297029703, "percentage": 95.15, "elapsed_time": "6:50:08", "remaining_time": "0:20:54", "throughput": 1483.42, "total_tokens": 36504592} {"current_steps": 172985, "total_steps": 181800, "loss": 0.061, "lr": 3.5730814011545323e-07, "epoch": 19.03025302530253, "percentage": 95.15, "elapsed_time": "6:50:09", "remaining_time": "0:20:54", "throughput": 1483.42, "total_tokens": 36505680} {"current_steps": 172990, "total_steps": 181800, "loss": 0.1199, "lr": 3.5690392680459705e-07, "epoch": 19.03080308030803, "percentage": 95.15, "elapsed_time": "6:50:09", "remaining_time": "0:20:53", "throughput": 1483.42, "total_tokens": 36506704} {"current_steps": 172995, "total_steps": 181800, "loss": 0.0851, "lr": 3.5649994061733306e-07, "epoch": 19.03135313531353, "percentage": 95.16, "elapsed_time": "6:50:10", "remaining_time": "0:20:52", "throughput": 1483.43, "total_tokens": 36507760} {"current_steps": 173000, "total_steps": 181800, "loss": 0.0738, "lr": 3.56096181557386e-07, "epoch": 19.03190319031903, "percentage": 95.16, "elapsed_time": "6:50:11", "remaining_time": "0:20:51", "throughput": 1483.43, "total_tokens": 36508912} {"current_steps": 173005, "total_steps": 181800, "loss": 0.0693, "lr": 3.5569264962847235e-07, "epoch": 19.032453245324533, "percentage": 95.16, "elapsed_time": "6:50:11", "remaining_time": "0:20:51", "throughput": 1483.43, "total_tokens": 36509968} {"current_steps": 173010, "total_steps": 181800, "loss": 0.0685, "lr": 3.552893448343142e-07, "epoch": 19.033003300330034, "percentage": 95.17, "elapsed_time": "6:50:12", "remaining_time": "0:20:50", "throughput": 1483.44, "total_tokens": 36511056} {"current_steps": 173015, "total_steps": 181800, "loss": 0.0024, "lr": 3.5488626717862795e-07, "epoch": 19.033553355335535, "percentage": 95.17, "elapsed_time": "6:50:13", "remaining_time": "0:20:49", "throughput": 1483.44, "total_tokens": 36512144} {"current_steps": 173020, "total_steps": 181800, "loss": 0.0512, "lr": 3.5448341666513007e-07, "epoch": 19.034103410341036, "percentage": 95.17, "elapsed_time": "6:50:13", "remaining_time": "0:20:49", "throughput": 1483.44, "total_tokens": 36513200} {"current_steps": 173025, "total_steps": 181800, "loss": 0.0023, "lr": 3.540807932975343e-07, "epoch": 19.034653465346533, "percentage": 95.17, "elapsed_time": "6:50:14", "remaining_time": "0:20:48", "throughput": 1483.44, "total_tokens": 36514288} {"current_steps": 173030, "total_steps": 181800, "loss": 0.0015, "lr": 3.5367839707954596e-07, "epoch": 19.035203520352034, "percentage": 95.18, "elapsed_time": "6:50:15", "remaining_time": "0:20:47", "throughput": 1483.45, "total_tokens": 36515408} {"current_steps": 173035, "total_steps": 181800, "loss": 0.0177, "lr": 3.532762280148788e-07, "epoch": 19.035753575357536, "percentage": 95.18, "elapsed_time": "6:50:15", "remaining_time": "0:20:46", "throughput": 1483.45, "total_tokens": 36516464} {"current_steps": 173040, "total_steps": 181800, "loss": 0.01, "lr": 3.528742861072382e-07, "epoch": 19.036303630363037, "percentage": 95.18, "elapsed_time": "6:50:16", "remaining_time": "0:20:46", "throughput": 1483.45, "total_tokens": 36517552} {"current_steps": 173045, "total_steps": 181800, "loss": 0.0053, "lr": 3.524725713603294e-07, "epoch": 19.036853685368538, "percentage": 95.18, "elapsed_time": "6:50:17", "remaining_time": "0:20:45", "throughput": 1483.45, "total_tokens": 36518544} {"current_steps": 173050, "total_steps": 181800, "loss": 0.0188, "lr": 3.5207108377785234e-07, "epoch": 19.03740374037404, "percentage": 95.19, "elapsed_time": "6:50:18", "remaining_time": "0:20:44", "throughput": 1483.45, "total_tokens": 36519568} {"current_steps": 173055, "total_steps": 181800, "loss": 0.0887, "lr": 3.516698233635096e-07, "epoch": 19.037953795379536, "percentage": 95.19, "elapsed_time": "6:50:18", "remaining_time": "0:20:44", "throughput": 1483.45, "total_tokens": 36520624} {"current_steps": 173060, "total_steps": 181800, "loss": 0.0119, "lr": 3.51268790121001e-07, "epoch": 19.038503850385037, "percentage": 95.19, "elapsed_time": "6:50:19", "remaining_time": "0:20:43", "throughput": 1483.45, "total_tokens": 36521680} {"current_steps": 173065, "total_steps": 181800, "loss": 0.0009, "lr": 3.508679840540152e-07, "epoch": 19.03905390539054, "percentage": 95.2, "elapsed_time": "6:50:20", "remaining_time": "0:20:42", "throughput": 1483.45, "total_tokens": 36522672} {"current_steps": 173070, "total_steps": 181800, "loss": 0.0046, "lr": 3.504674051662549e-07, "epoch": 19.03960396039604, "percentage": 95.2, "elapsed_time": "6:50:20", "remaining_time": "0:20:41", "throughput": 1483.45, "total_tokens": 36523696} {"current_steps": 173075, "total_steps": 181800, "loss": 0.0039, "lr": 3.5006705346140867e-07, "epoch": 19.04015401540154, "percentage": 95.2, "elapsed_time": "6:50:21", "remaining_time": "0:20:41", "throughput": 1483.45, "total_tokens": 36524848} {"current_steps": 173080, "total_steps": 181800, "loss": 0.004, "lr": 3.496669289431653e-07, "epoch": 19.040704070407042, "percentage": 95.2, "elapsed_time": "6:50:22", "remaining_time": "0:20:40", "throughput": 1483.45, "total_tokens": 36525872} {"current_steps": 173085, "total_steps": 181800, "loss": 0.0045, "lr": 3.4926703161521356e-07, "epoch": 19.041254125412543, "percentage": 95.21, "elapsed_time": "6:50:22", "remaining_time": "0:20:39", "throughput": 1483.45, "total_tokens": 36526928} {"current_steps": 173090, "total_steps": 181800, "loss": 0.0015, "lr": 3.4886736148123656e-07, "epoch": 19.04180418041804, "percentage": 95.21, "elapsed_time": "6:50:23", "remaining_time": "0:20:39", "throughput": 1483.45, "total_tokens": 36527952} {"current_steps": 173095, "total_steps": 181800, "loss": 0.0006, "lr": 3.48467918544923e-07, "epoch": 19.04235423542354, "percentage": 95.21, "elapsed_time": "6:50:24", "remaining_time": "0:20:38", "throughput": 1483.45, "total_tokens": 36528976} {"current_steps": 173100, "total_steps": 181800, "loss": 0.0554, "lr": 3.480687028099533e-07, "epoch": 19.042904290429043, "percentage": 95.21, "elapsed_time": "6:50:24", "remaining_time": "0:20:37", "throughput": 1483.45, "total_tokens": 36530000} {"current_steps": 173105, "total_steps": 181800, "loss": 0.0012, "lr": 3.4766971428000226e-07, "epoch": 19.043454345434544, "percentage": 95.22, "elapsed_time": "6:50:25", "remaining_time": "0:20:36", "throughput": 1483.46, "total_tokens": 36531088} {"current_steps": 173110, "total_steps": 181800, "loss": 0.0021, "lr": 3.472709529587531e-07, "epoch": 19.044004400440045, "percentage": 95.22, "elapsed_time": "6:50:26", "remaining_time": "0:20:36", "throughput": 1483.46, "total_tokens": 36532112} {"current_steps": 173115, "total_steps": 181800, "loss": 0.01, "lr": 3.468724188498751e-07, "epoch": 19.044554455445546, "percentage": 95.22, "elapsed_time": "6:50:27", "remaining_time": "0:20:35", "throughput": 1483.46, "total_tokens": 36533136} {"current_steps": 173120, "total_steps": 181800, "loss": 0.0049, "lr": 3.4647411195704584e-07, "epoch": 19.045104510451043, "percentage": 95.23, "elapsed_time": "6:50:27", "remaining_time": "0:20:34", "throughput": 1483.46, "total_tokens": 36534224} {"current_steps": 173125, "total_steps": 181800, "loss": 0.0038, "lr": 3.4607603228393184e-07, "epoch": 19.045654565456545, "percentage": 95.23, "elapsed_time": "6:50:28", "remaining_time": "0:20:34", "throughput": 1483.46, "total_tokens": 36535280} {"current_steps": 173130, "total_steps": 181800, "loss": 0.0204, "lr": 3.4567817983420794e-07, "epoch": 19.046204620462046, "percentage": 95.23, "elapsed_time": "6:50:29", "remaining_time": "0:20:33", "throughput": 1483.46, "total_tokens": 36536368} {"current_steps": 173135, "total_steps": 181800, "loss": 0.0202, "lr": 3.4528055461153786e-07, "epoch": 19.046754675467547, "percentage": 95.23, "elapsed_time": "6:50:29", "remaining_time": "0:20:32", "throughput": 1483.46, "total_tokens": 36537424} {"current_steps": 173140, "total_steps": 181800, "loss": 0.0095, "lr": 3.4488315661958815e-07, "epoch": 19.047304730473048, "percentage": 95.24, "elapsed_time": "6:50:30", "remaining_time": "0:20:31", "throughput": 1483.47, "total_tokens": 36538512} {"current_steps": 173145, "total_steps": 181800, "loss": 0.0145, "lr": 3.44485985862017e-07, "epoch": 19.04785478547855, "percentage": 95.24, "elapsed_time": "6:50:31", "remaining_time": "0:20:31", "throughput": 1483.47, "total_tokens": 36539632} {"current_steps": 173150, "total_steps": 181800, "loss": 0.0024, "lr": 3.4408904234248806e-07, "epoch": 19.04840484048405, "percentage": 95.24, "elapsed_time": "6:50:31", "remaining_time": "0:20:30", "throughput": 1483.47, "total_tokens": 36540720} {"current_steps": 173155, "total_steps": 181800, "loss": 0.0096, "lr": 3.4369232606465683e-07, "epoch": 19.048954895489548, "percentage": 95.24, "elapsed_time": "6:50:32", "remaining_time": "0:20:29", "throughput": 1483.48, "total_tokens": 36541808} {"current_steps": 173160, "total_steps": 181800, "loss": 0.0021, "lr": 3.4329583703218704e-07, "epoch": 19.04950495049505, "percentage": 95.25, "elapsed_time": "6:50:33", "remaining_time": "0:20:29", "throughput": 1483.48, "total_tokens": 36542864} {"current_steps": 173165, "total_steps": 181800, "loss": 0.0042, "lr": 3.4289957524872575e-07, "epoch": 19.05005500550055, "percentage": 95.25, "elapsed_time": "6:50:33", "remaining_time": "0:20:28", "throughput": 1483.48, "total_tokens": 36543888} {"current_steps": 173170, "total_steps": 181800, "loss": 0.0029, "lr": 3.425035407179283e-07, "epoch": 19.05060506050605, "percentage": 95.25, "elapsed_time": "6:50:34", "remaining_time": "0:20:27", "throughput": 1483.48, "total_tokens": 36544912} {"current_steps": 173175, "total_steps": 181800, "loss": 0.0008, "lr": 3.4210773344344194e-07, "epoch": 19.051155115511552, "percentage": 95.26, "elapsed_time": "6:50:35", "remaining_time": "0:20:26", "throughput": 1483.48, "total_tokens": 36546032} {"current_steps": 173180, "total_steps": 181800, "loss": 0.0116, "lr": 3.4171215342891915e-07, "epoch": 19.051705170517053, "percentage": 95.26, "elapsed_time": "6:50:36", "remaining_time": "0:20:26", "throughput": 1483.48, "total_tokens": 36547024} {"current_steps": 173185, "total_steps": 181800, "loss": 0.112, "lr": 3.4131680067799876e-07, "epoch": 19.05225522552255, "percentage": 95.26, "elapsed_time": "6:50:36", "remaining_time": "0:20:25", "throughput": 1483.48, "total_tokens": 36548112} {"current_steps": 173190, "total_steps": 181800, "loss": 0.0068, "lr": 3.409216751943334e-07, "epoch": 19.05280528052805, "percentage": 95.26, "elapsed_time": "6:50:37", "remaining_time": "0:20:24", "throughput": 1483.49, "total_tokens": 36549200} {"current_steps": 173195, "total_steps": 181800, "loss": 0.0055, "lr": 3.40526776981559e-07, "epoch": 19.053355335533553, "percentage": 95.27, "elapsed_time": "6:50:38", "remaining_time": "0:20:24", "throughput": 1483.49, "total_tokens": 36550320} {"current_steps": 173200, "total_steps": 181800, "loss": 0.0013, "lr": 3.4013210604331714e-07, "epoch": 19.053905390539054, "percentage": 95.27, "elapsed_time": "6:50:38", "remaining_time": "0:20:23", "throughput": 1483.49, "total_tokens": 36551408} {"current_steps": 173205, "total_steps": 181800, "loss": 0.0351, "lr": 3.397376623832438e-07, "epoch": 19.054455445544555, "percentage": 95.27, "elapsed_time": "6:50:39", "remaining_time": "0:20:22", "throughput": 1483.49, "total_tokens": 36552432} {"current_steps": 173210, "total_steps": 181800, "loss": 0.0143, "lr": 3.393434460049749e-07, "epoch": 19.055005500550056, "percentage": 95.28, "elapsed_time": "6:50:40", "remaining_time": "0:20:21", "throughput": 1483.49, "total_tokens": 36553456} {"current_steps": 173215, "total_steps": 181800, "loss": 0.0572, "lr": 3.3894945691214653e-07, "epoch": 19.055555555555557, "percentage": 95.28, "elapsed_time": "6:50:40", "remaining_time": "0:20:21", "throughput": 1483.49, "total_tokens": 36554480} {"current_steps": 173220, "total_steps": 181800, "loss": 0.1165, "lr": 3.3855569510838627e-07, "epoch": 19.056105610561055, "percentage": 95.28, "elapsed_time": "6:50:41", "remaining_time": "0:20:20", "throughput": 1483.49, "total_tokens": 36555568} {"current_steps": 173225, "total_steps": 181800, "loss": 0.021, "lr": 3.381621605973245e-07, "epoch": 19.056655665566556, "percentage": 95.28, "elapsed_time": "6:50:42", "remaining_time": "0:20:19", "throughput": 1483.5, "total_tokens": 36556656} {"current_steps": 173230, "total_steps": 181800, "loss": 0.0551, "lr": 3.3776885338258626e-07, "epoch": 19.057205720572057, "percentage": 95.29, "elapsed_time": "6:50:42", "remaining_time": "0:20:19", "throughput": 1483.5, "total_tokens": 36557744} {"current_steps": 173235, "total_steps": 181800, "loss": 0.0143, "lr": 3.373757734678018e-07, "epoch": 19.057755775577558, "percentage": 95.29, "elapsed_time": "6:50:43", "remaining_time": "0:20:18", "throughput": 1483.5, "total_tokens": 36558800} {"current_steps": 173240, "total_steps": 181800, "loss": 0.0028, "lr": 3.369829208565878e-07, "epoch": 19.05830583058306, "percentage": 95.29, "elapsed_time": "6:50:44", "remaining_time": "0:20:17", "throughput": 1483.5, "total_tokens": 36559888} {"current_steps": 173245, "total_steps": 181800, "loss": 0.0207, "lr": 3.36590295552569e-07, "epoch": 19.05885588558856, "percentage": 95.29, "elapsed_time": "6:50:44", "remaining_time": "0:20:16", "throughput": 1483.5, "total_tokens": 36560944} {"current_steps": 173250, "total_steps": 181800, "loss": 0.0052, "lr": 3.3619789755936214e-07, "epoch": 19.059405940594058, "percentage": 95.3, "elapsed_time": "6:50:45", "remaining_time": "0:20:16", "throughput": 1483.5, "total_tokens": 36561968} {"current_steps": 173255, "total_steps": 181800, "loss": 0.0075, "lr": 3.3580572688058365e-07, "epoch": 19.05995599559956, "percentage": 95.3, "elapsed_time": "6:50:46", "remaining_time": "0:20:15", "throughput": 1483.51, "total_tokens": 36563056} {"current_steps": 173260, "total_steps": 181800, "loss": 0.0101, "lr": 3.354137835198501e-07, "epoch": 19.06050605060506, "percentage": 95.3, "elapsed_time": "6:50:47", "remaining_time": "0:20:14", "throughput": 1483.51, "total_tokens": 36564080} {"current_steps": 173265, "total_steps": 181800, "loss": 0.0017, "lr": 3.3502206748077524e-07, "epoch": 19.06105610561056, "percentage": 95.31, "elapsed_time": "6:50:47", "remaining_time": "0:20:14", "throughput": 1483.51, "total_tokens": 36565104} {"current_steps": 173270, "total_steps": 181800, "loss": 0.0055, "lr": 3.34630578766959e-07, "epoch": 19.061606160616062, "percentage": 95.31, "elapsed_time": "6:50:48", "remaining_time": "0:20:13", "throughput": 1483.51, "total_tokens": 36566160} {"current_steps": 173275, "total_steps": 181800, "loss": 0.0699, "lr": 3.342393173820235e-07, "epoch": 19.062156215621563, "percentage": 95.31, "elapsed_time": "6:50:49", "remaining_time": "0:20:12", "throughput": 1483.51, "total_tokens": 36567184} {"current_steps": 173280, "total_steps": 181800, "loss": 0.0831, "lr": 3.3384828332956586e-07, "epoch": 19.062706270627064, "percentage": 95.31, "elapsed_time": "6:50:49", "remaining_time": "0:20:12", "throughput": 1483.51, "total_tokens": 36568272} {"current_steps": 173285, "total_steps": 181800, "loss": 0.0067, "lr": 3.334574766131943e-07, "epoch": 19.063256325632562, "percentage": 95.32, "elapsed_time": "6:50:50", "remaining_time": "0:20:11", "throughput": 1483.51, "total_tokens": 36569296} {"current_steps": 173290, "total_steps": 181800, "loss": 0.0679, "lr": 3.330668972365086e-07, "epoch": 19.063806380638063, "percentage": 95.32, "elapsed_time": "6:50:51", "remaining_time": "0:20:10", "throughput": 1483.51, "total_tokens": 36570256} {"current_steps": 173295, "total_steps": 181800, "loss": 0.1341, "lr": 3.3267654520310886e-07, "epoch": 19.064356435643564, "percentage": 95.32, "elapsed_time": "6:50:51", "remaining_time": "0:20:09", "throughput": 1483.51, "total_tokens": 36571312} {"current_steps": 173300, "total_steps": 181800, "loss": 0.0436, "lr": 3.322864205165921e-07, "epoch": 19.064906490649065, "percentage": 95.32, "elapsed_time": "6:50:52", "remaining_time": "0:20:09", "throughput": 1483.51, "total_tokens": 36572432} {"current_steps": 173305, "total_steps": 181800, "loss": 0.0188, "lr": 3.3189652318055263e-07, "epoch": 19.065456545654566, "percentage": 95.33, "elapsed_time": "6:50:53", "remaining_time": "0:20:08", "throughput": 1483.51, "total_tokens": 36573424} {"current_steps": 173310, "total_steps": 181800, "loss": 0.0025, "lr": 3.315068531985904e-07, "epoch": 19.066006600660067, "percentage": 95.33, "elapsed_time": "6:50:53", "remaining_time": "0:20:07", "throughput": 1483.51, "total_tokens": 36574480} {"current_steps": 173315, "total_steps": 181800, "loss": 0.0494, "lr": 3.3111741057429145e-07, "epoch": 19.066556655665565, "percentage": 95.33, "elapsed_time": "6:50:54", "remaining_time": "0:20:07", "throughput": 1483.51, "total_tokens": 36575504} {"current_steps": 173320, "total_steps": 181800, "loss": 0.0271, "lr": 3.3072819531124455e-07, "epoch": 19.067106710671066, "percentage": 95.34, "elapsed_time": "6:50:55", "remaining_time": "0:20:06", "throughput": 1483.52, "total_tokens": 36576560} {"current_steps": 173325, "total_steps": 181800, "loss": 0.0111, "lr": 3.303392074130385e-07, "epoch": 19.067656765676567, "percentage": 95.34, "elapsed_time": "6:50:56", "remaining_time": "0:20:05", "throughput": 1483.52, "total_tokens": 36577616} {"current_steps": 173330, "total_steps": 181800, "loss": 0.0026, "lr": 3.299504468832565e-07, "epoch": 19.068206820682068, "percentage": 95.34, "elapsed_time": "6:50:56", "remaining_time": "0:20:04", "throughput": 1483.52, "total_tokens": 36578704} {"current_steps": 173335, "total_steps": 181800, "loss": 0.1447, "lr": 3.2956191372548737e-07, "epoch": 19.06875687568757, "percentage": 95.34, "elapsed_time": "6:50:57", "remaining_time": "0:20:04", "throughput": 1483.52, "total_tokens": 36579760} {"current_steps": 173340, "total_steps": 181800, "loss": 0.003, "lr": 3.291736079433061e-07, "epoch": 19.06930693069307, "percentage": 95.35, "elapsed_time": "6:50:58", "remaining_time": "0:20:03", "throughput": 1483.52, "total_tokens": 36580784} {"current_steps": 173345, "total_steps": 181800, "loss": 0.0024, "lr": 3.2878552954029304e-07, "epoch": 19.06985698569857, "percentage": 95.35, "elapsed_time": "6:50:58", "remaining_time": "0:20:02", "throughput": 1483.52, "total_tokens": 36581808} {"current_steps": 173350, "total_steps": 181800, "loss": 0.0327, "lr": 3.283976785200288e-07, "epoch": 19.07040704070407, "percentage": 95.35, "elapsed_time": "6:50:59", "remaining_time": "0:20:02", "throughput": 1483.52, "total_tokens": 36582832} {"current_steps": 173355, "total_steps": 181800, "loss": 0.036, "lr": 3.280100548860798e-07, "epoch": 19.07095709570957, "percentage": 95.35, "elapsed_time": "6:51:00", "remaining_time": "0:20:01", "throughput": 1483.52, "total_tokens": 36583920} {"current_steps": 173360, "total_steps": 181800, "loss": 0.0029, "lr": 3.276226586420239e-07, "epoch": 19.07150715071507, "percentage": 95.36, "elapsed_time": "6:51:00", "remaining_time": "0:20:00", "throughput": 1483.52, "total_tokens": 36584912} {"current_steps": 173365, "total_steps": 181800, "loss": 0.1331, "lr": 3.2723548979143313e-07, "epoch": 19.072057205720572, "percentage": 95.36, "elapsed_time": "6:51:01", "remaining_time": "0:19:59", "throughput": 1483.52, "total_tokens": 36586000} {"current_steps": 173370, "total_steps": 181800, "loss": 0.0891, "lr": 3.2684854833787416e-07, "epoch": 19.072607260726073, "percentage": 95.36, "elapsed_time": "6:51:02", "remaining_time": "0:19:59", "throughput": 1483.52, "total_tokens": 36587024} {"current_steps": 173375, "total_steps": 181800, "loss": 0.0098, "lr": 3.264618342849107e-07, "epoch": 19.073157315731574, "percentage": 95.37, "elapsed_time": "6:51:02", "remaining_time": "0:19:58", "throughput": 1483.53, "total_tokens": 36588080} {"current_steps": 173380, "total_steps": 181800, "loss": 0.0201, "lr": 3.2607534763611224e-07, "epoch": 19.073707370737075, "percentage": 95.37, "elapsed_time": "6:51:03", "remaining_time": "0:19:57", "throughput": 1483.53, "total_tokens": 36589168} {"current_steps": 173385, "total_steps": 181800, "loss": 0.0143, "lr": 3.256890883950342e-07, "epoch": 19.074257425742573, "percentage": 95.37, "elapsed_time": "6:51:04", "remaining_time": "0:19:57", "throughput": 1483.53, "total_tokens": 36590224} {"current_steps": 173390, "total_steps": 181800, "loss": 0.0974, "lr": 3.253030565652404e-07, "epoch": 19.074807480748074, "percentage": 95.37, "elapsed_time": "6:51:04", "remaining_time": "0:19:56", "throughput": 1483.53, "total_tokens": 36591312} {"current_steps": 173395, "total_steps": 181800, "loss": 0.0029, "lr": 3.249172521502891e-07, "epoch": 19.075357535753575, "percentage": 95.38, "elapsed_time": "6:51:05", "remaining_time": "0:19:55", "throughput": 1483.53, "total_tokens": 36592368} {"current_steps": 173400, "total_steps": 181800, "loss": 0.0039, "lr": 3.2453167515373584e-07, "epoch": 19.075907590759076, "percentage": 95.38, "elapsed_time": "6:51:06", "remaining_time": "0:19:54", "throughput": 1483.53, "total_tokens": 36593392} {"current_steps": 173405, "total_steps": 181800, "loss": 0.0037, "lr": 3.2414632557913327e-07, "epoch": 19.076457645764577, "percentage": 95.38, "elapsed_time": "6:51:07", "remaining_time": "0:19:54", "throughput": 1483.53, "total_tokens": 36594448} {"current_steps": 173410, "total_steps": 181800, "loss": 0.0037, "lr": 3.237612034300314e-07, "epoch": 19.07700770077008, "percentage": 95.39, "elapsed_time": "6:51:07", "remaining_time": "0:19:53", "throughput": 1483.54, "total_tokens": 36595504} {"current_steps": 173415, "total_steps": 181800, "loss": 0.0917, "lr": 3.2337630870998283e-07, "epoch": 19.077557755775576, "percentage": 95.39, "elapsed_time": "6:51:08", "remaining_time": "0:19:52", "throughput": 1483.54, "total_tokens": 36596592} {"current_steps": 173420, "total_steps": 181800, "loss": 0.1122, "lr": 3.2299164142253204e-07, "epoch": 19.078107810781077, "percentage": 95.39, "elapsed_time": "6:51:09", "remaining_time": "0:19:52", "throughput": 1483.54, "total_tokens": 36597648} {"current_steps": 173425, "total_steps": 181800, "loss": 0.0542, "lr": 3.226072015712317e-07, "epoch": 19.078657865786578, "percentage": 95.39, "elapsed_time": "6:51:09", "remaining_time": "0:19:51", "throughput": 1483.54, "total_tokens": 36598704} {"current_steps": 173430, "total_steps": 181800, "loss": 0.0017, "lr": 3.222229891596151e-07, "epoch": 19.07920792079208, "percentage": 95.4, "elapsed_time": "6:51:10", "remaining_time": "0:19:50", "throughput": 1483.54, "total_tokens": 36599760} {"current_steps": 173435, "total_steps": 181800, "loss": 0.039, "lr": 3.2183900419122946e-07, "epoch": 19.07975797579758, "percentage": 95.4, "elapsed_time": "6:51:11", "remaining_time": "0:19:49", "throughput": 1483.54, "total_tokens": 36600784} {"current_steps": 173440, "total_steps": 181800, "loss": 0.0057, "lr": 3.214552466696108e-07, "epoch": 19.08030803080308, "percentage": 95.4, "elapsed_time": "6:51:11", "remaining_time": "0:19:49", "throughput": 1483.54, "total_tokens": 36601840} {"current_steps": 173445, "total_steps": 181800, "loss": 0.0022, "lr": 3.2107171659829794e-07, "epoch": 19.080858085808583, "percentage": 95.4, "elapsed_time": "6:51:12", "remaining_time": "0:19:48", "throughput": 1483.54, "total_tokens": 36602896} {"current_steps": 173450, "total_steps": 181800, "loss": 0.0029, "lr": 3.2068841398082414e-07, "epoch": 19.08140814081408, "percentage": 95.41, "elapsed_time": "6:51:13", "remaining_time": "0:19:47", "throughput": 1483.54, "total_tokens": 36603920} {"current_steps": 173455, "total_steps": 181800, "loss": 0.1408, "lr": 3.203053388207228e-07, "epoch": 19.08195819581958, "percentage": 95.41, "elapsed_time": "6:51:13", "remaining_time": "0:19:47", "throughput": 1483.55, "total_tokens": 36605008} {"current_steps": 173460, "total_steps": 181800, "loss": 0.0892, "lr": 3.199224911215243e-07, "epoch": 19.082508250825082, "percentage": 95.41, "elapsed_time": "6:51:14", "remaining_time": "0:19:46", "throughput": 1483.55, "total_tokens": 36606032} {"current_steps": 173465, "total_steps": 181800, "loss": 0.067, "lr": 3.195398708867592e-07, "epoch": 19.083058305830583, "percentage": 95.42, "elapsed_time": "6:51:15", "remaining_time": "0:19:45", "throughput": 1483.55, "total_tokens": 36607056} {"current_steps": 173470, "total_steps": 181800, "loss": 0.0911, "lr": 3.1915747811995243e-07, "epoch": 19.083608360836084, "percentage": 95.42, "elapsed_time": "6:51:16", "remaining_time": "0:19:44", "throughput": 1483.55, "total_tokens": 36608144} {"current_steps": 173475, "total_steps": 181800, "loss": 0.163, "lr": 3.1877531282462627e-07, "epoch": 19.084158415841586, "percentage": 95.42, "elapsed_time": "6:51:16", "remaining_time": "0:19:44", "throughput": 1483.55, "total_tokens": 36609264} {"current_steps": 173480, "total_steps": 181800, "loss": 0.0703, "lr": 3.1839337500430557e-07, "epoch": 19.084708470847083, "percentage": 95.42, "elapsed_time": "6:51:17", "remaining_time": "0:19:43", "throughput": 1483.56, "total_tokens": 36610320} {"current_steps": 173485, "total_steps": 181800, "loss": 0.0012, "lr": 3.1801166466250976e-07, "epoch": 19.085258525852584, "percentage": 95.43, "elapsed_time": "6:51:18", "remaining_time": "0:19:42", "throughput": 1483.56, "total_tokens": 36611344} {"current_steps": 173490, "total_steps": 181800, "loss": 0.0461, "lr": 3.1763018180275826e-07, "epoch": 19.085808580858085, "percentage": 95.43, "elapsed_time": "6:51:18", "remaining_time": "0:19:42", "throughput": 1483.56, "total_tokens": 36612400} {"current_steps": 173495, "total_steps": 181800, "loss": 0.0032, "lr": 3.17248926428565e-07, "epoch": 19.086358635863586, "percentage": 95.43, "elapsed_time": "6:51:19", "remaining_time": "0:19:41", "throughput": 1483.56, "total_tokens": 36613488} {"current_steps": 173500, "total_steps": 181800, "loss": 0.0166, "lr": 3.168678985434437e-07, "epoch": 19.086908690869087, "percentage": 95.43, "elapsed_time": "6:51:20", "remaining_time": "0:19:40", "throughput": 1483.57, "total_tokens": 36614672} {"current_steps": 173505, "total_steps": 181800, "loss": 0.0018, "lr": 3.1648709815090824e-07, "epoch": 19.08745874587459, "percentage": 95.44, "elapsed_time": "6:51:20", "remaining_time": "0:19:39", "throughput": 1483.57, "total_tokens": 36615728} {"current_steps": 173510, "total_steps": 181800, "loss": 0.0066, "lr": 3.1610652525446425e-07, "epoch": 19.08800880088009, "percentage": 95.44, "elapsed_time": "6:51:21", "remaining_time": "0:19:39", "throughput": 1483.57, "total_tokens": 36616816} {"current_steps": 173515, "total_steps": 181800, "loss": 0.0459, "lr": 3.1572617985762276e-07, "epoch": 19.088558855885587, "percentage": 95.44, "elapsed_time": "6:51:22", "remaining_time": "0:19:38", "throughput": 1483.57, "total_tokens": 36617872} {"current_steps": 173520, "total_steps": 181800, "loss": 0.012, "lr": 3.153460619638893e-07, "epoch": 19.08910891089109, "percentage": 95.45, "elapsed_time": "6:51:22", "remaining_time": "0:19:37", "throughput": 1483.57, "total_tokens": 36618896} {"current_steps": 173525, "total_steps": 181800, "loss": 0.0059, "lr": 3.1496617157676655e-07, "epoch": 19.08965896589659, "percentage": 95.45, "elapsed_time": "6:51:23", "remaining_time": "0:19:37", "throughput": 1483.57, "total_tokens": 36619952} {"current_steps": 173530, "total_steps": 181800, "loss": 0.0612, "lr": 3.145865086997546e-07, "epoch": 19.09020902090209, "percentage": 95.45, "elapsed_time": "6:51:24", "remaining_time": "0:19:36", "throughput": 1483.58, "total_tokens": 36621104} {"current_steps": 173535, "total_steps": 181800, "loss": 0.0184, "lr": 3.1420707333635337e-07, "epoch": 19.09075907590759, "percentage": 95.45, "elapsed_time": "6:51:25", "remaining_time": "0:19:35", "throughput": 1483.58, "total_tokens": 36622096} {"current_steps": 173540, "total_steps": 181800, "loss": 0.0048, "lr": 3.138278654900628e-07, "epoch": 19.091309130913093, "percentage": 95.46, "elapsed_time": "6:51:25", "remaining_time": "0:19:34", "throughput": 1483.58, "total_tokens": 36623248} {"current_steps": 173545, "total_steps": 181800, "loss": 0.0026, "lr": 3.1344888516437465e-07, "epoch": 19.09185918591859, "percentage": 95.46, "elapsed_time": "6:51:26", "remaining_time": "0:19:34", "throughput": 1483.58, "total_tokens": 36624336} {"current_steps": 173550, "total_steps": 181800, "loss": 0.0013, "lr": 3.130701323627805e-07, "epoch": 19.09240924092409, "percentage": 95.46, "elapsed_time": "6:51:27", "remaining_time": "0:19:33", "throughput": 1483.58, "total_tokens": 36625360} {"current_steps": 173555, "total_steps": 181800, "loss": 0.045, "lr": 3.1269160708877475e-07, "epoch": 19.092959295929592, "percentage": 95.46, "elapsed_time": "6:51:27", "remaining_time": "0:19:32", "throughput": 1483.58, "total_tokens": 36626416} {"current_steps": 173560, "total_steps": 181800, "loss": 0.1528, "lr": 3.123133093458408e-07, "epoch": 19.093509350935093, "percentage": 95.47, "elapsed_time": "6:51:28", "remaining_time": "0:19:32", "throughput": 1483.58, "total_tokens": 36627408} {"current_steps": 173565, "total_steps": 181800, "loss": 0.0441, "lr": 3.1193523913747023e-07, "epoch": 19.094059405940595, "percentage": 95.47, "elapsed_time": "6:51:29", "remaining_time": "0:19:31", "throughput": 1483.58, "total_tokens": 36628464} {"current_steps": 173570, "total_steps": 181800, "loss": 0.0637, "lr": 3.115573964671492e-07, "epoch": 19.094609460946096, "percentage": 95.47, "elapsed_time": "6:51:29", "remaining_time": "0:19:30", "throughput": 1483.58, "total_tokens": 36629488} {"current_steps": 173575, "total_steps": 181800, "loss": 0.0053, "lr": 3.1117978133835267e-07, "epoch": 19.095159515951597, "percentage": 95.48, "elapsed_time": "6:51:30", "remaining_time": "0:19:29", "throughput": 1483.58, "total_tokens": 36630544} {"current_steps": 173580, "total_steps": 181800, "loss": 0.0092, "lr": 3.1080239375456956e-07, "epoch": 19.095709570957094, "percentage": 95.48, "elapsed_time": "6:51:31", "remaining_time": "0:19:29", "throughput": 1483.59, "total_tokens": 36631600} {"current_steps": 173585, "total_steps": 181800, "loss": 0.0084, "lr": 3.104252337192692e-07, "epoch": 19.096259625962595, "percentage": 95.48, "elapsed_time": "6:51:31", "remaining_time": "0:19:28", "throughput": 1483.59, "total_tokens": 36632656} {"current_steps": 173590, "total_steps": 181800, "loss": 0.0114, "lr": 3.100483012359351e-07, "epoch": 19.096809680968097, "percentage": 95.48, "elapsed_time": "6:51:32", "remaining_time": "0:19:27", "throughput": 1483.59, "total_tokens": 36633680} {"current_steps": 173595, "total_steps": 181800, "loss": 0.0201, "lr": 3.096715963080393e-07, "epoch": 19.097359735973598, "percentage": 95.49, "elapsed_time": "6:51:33", "remaining_time": "0:19:27", "throughput": 1483.59, "total_tokens": 36634768} {"current_steps": 173600, "total_steps": 181800, "loss": 0.0115, "lr": 3.092951189390514e-07, "epoch": 19.0979097909791, "percentage": 95.49, "elapsed_time": "6:51:34", "remaining_time": "0:19:26", "throughput": 1483.59, "total_tokens": 36635856} {"current_steps": 173605, "total_steps": 181800, "loss": 0.0539, "lr": 3.089188691324435e-07, "epoch": 19.0984598459846, "percentage": 95.49, "elapsed_time": "6:51:34", "remaining_time": "0:19:25", "throughput": 1483.6, "total_tokens": 36636944} {"current_steps": 173610, "total_steps": 181800, "loss": 0.0014, "lr": 3.0854284689167956e-07, "epoch": 19.099009900990097, "percentage": 95.5, "elapsed_time": "6:51:35", "remaining_time": "0:19:24", "throughput": 1483.6, "total_tokens": 36638032} {"current_steps": 173615, "total_steps": 181800, "loss": 0.1236, "lr": 3.081670522202318e-07, "epoch": 19.0995599559956, "percentage": 95.5, "elapsed_time": "6:51:36", "remaining_time": "0:19:24", "throughput": 1483.6, "total_tokens": 36639152} {"current_steps": 173620, "total_steps": 181800, "loss": 0.0119, "lr": 3.077914851215585e-07, "epoch": 19.1001100110011, "percentage": 95.5, "elapsed_time": "6:51:36", "remaining_time": "0:19:23", "throughput": 1483.6, "total_tokens": 36640240} {"current_steps": 173625, "total_steps": 181800, "loss": 0.0046, "lr": 3.074161455991209e-07, "epoch": 19.1006600660066, "percentage": 95.5, "elapsed_time": "6:51:37", "remaining_time": "0:19:22", "throughput": 1483.6, "total_tokens": 36641232} {"current_steps": 173630, "total_steps": 181800, "loss": 0.0032, "lr": 3.0704103365638284e-07, "epoch": 19.1012101210121, "percentage": 95.51, "elapsed_time": "6:51:38", "remaining_time": "0:19:22", "throughput": 1483.6, "total_tokens": 36642288} {"current_steps": 173635, "total_steps": 181800, "loss": 0.0019, "lr": 3.0666614929679705e-07, "epoch": 19.101760176017603, "percentage": 95.51, "elapsed_time": "6:51:38", "remaining_time": "0:19:21", "throughput": 1483.61, "total_tokens": 36643344} {"current_steps": 173640, "total_steps": 181800, "loss": 0.1895, "lr": 3.0629149252382194e-07, "epoch": 19.102310231023104, "percentage": 95.51, "elapsed_time": "6:51:39", "remaining_time": "0:19:20", "throughput": 1483.61, "total_tokens": 36644368} {"current_steps": 173645, "total_steps": 181800, "loss": 0.0042, "lr": 3.0591706334090473e-07, "epoch": 19.1028602860286, "percentage": 95.51, "elapsed_time": "6:51:40", "remaining_time": "0:19:20", "throughput": 1483.61, "total_tokens": 36645424} {"current_steps": 173650, "total_steps": 181800, "loss": 0.011, "lr": 3.055428617515038e-07, "epoch": 19.103410341034103, "percentage": 95.52, "elapsed_time": "6:51:40", "remaining_time": "0:19:19", "throughput": 1483.61, "total_tokens": 36646480} {"current_steps": 173655, "total_steps": 181800, "loss": 0.0783, "lr": 3.0516888775906636e-07, "epoch": 19.103960396039604, "percentage": 95.52, "elapsed_time": "6:51:41", "remaining_time": "0:19:18", "throughput": 1483.61, "total_tokens": 36647440} {"current_steps": 173660, "total_steps": 181800, "loss": 0.0123, "lr": 3.047951413670341e-07, "epoch": 19.104510451045105, "percentage": 95.52, "elapsed_time": "6:51:42", "remaining_time": "0:19:17", "throughput": 1483.6, "total_tokens": 36648432} {"current_steps": 173665, "total_steps": 181800, "loss": 0.0018, "lr": 3.044216225788571e-07, "epoch": 19.105060506050606, "percentage": 95.53, "elapsed_time": "6:51:42", "remaining_time": "0:19:17", "throughput": 1483.61, "total_tokens": 36649520} {"current_steps": 173670, "total_steps": 181800, "loss": 0.0027, "lr": 3.0404833139797695e-07, "epoch": 19.105610561056107, "percentage": 95.53, "elapsed_time": "6:51:43", "remaining_time": "0:19:16", "throughput": 1483.61, "total_tokens": 36650544} {"current_steps": 173675, "total_steps": 181800, "loss": 0.0234, "lr": 3.0367526782783263e-07, "epoch": 19.106160616061604, "percentage": 95.53, "elapsed_time": "6:51:44", "remaining_time": "0:19:15", "throughput": 1483.61, "total_tokens": 36651632} {"current_steps": 173680, "total_steps": 181800, "loss": 0.0038, "lr": 3.033024318718602e-07, "epoch": 19.106710671067106, "percentage": 95.53, "elapsed_time": "6:51:45", "remaining_time": "0:19:15", "throughput": 1483.61, "total_tokens": 36652688} {"current_steps": 173685, "total_steps": 181800, "loss": 0.0494, "lr": 3.0292982353349875e-07, "epoch": 19.107260726072607, "percentage": 95.54, "elapsed_time": "6:51:45", "remaining_time": "0:19:14", "throughput": 1483.61, "total_tokens": 36653744} {"current_steps": 173690, "total_steps": 181800, "loss": 0.0337, "lr": 3.0255744281618704e-07, "epoch": 19.107810781078108, "percentage": 95.54, "elapsed_time": "6:51:46", "remaining_time": "0:19:13", "throughput": 1483.61, "total_tokens": 36654768} {"current_steps": 173695, "total_steps": 181800, "loss": 0.0019, "lr": 3.0218528972335014e-07, "epoch": 19.10836083608361, "percentage": 95.54, "elapsed_time": "6:51:47", "remaining_time": "0:19:12", "throughput": 1483.61, "total_tokens": 36655824} {"current_steps": 173700, "total_steps": 181800, "loss": 0.0238, "lr": 3.018133642584187e-07, "epoch": 19.10891089108911, "percentage": 95.54, "elapsed_time": "6:51:47", "remaining_time": "0:19:12", "throughput": 1483.61, "total_tokens": 36656912} {"current_steps": 173705, "total_steps": 181800, "loss": 0.0026, "lr": 3.014416664248204e-07, "epoch": 19.10946094609461, "percentage": 95.55, "elapsed_time": "6:51:48", "remaining_time": "0:19:11", "throughput": 1483.62, "total_tokens": 36658064} {"current_steps": 173710, "total_steps": 181800, "loss": 0.0021, "lr": 3.0107019622598596e-07, "epoch": 19.11001100110011, "percentage": 95.55, "elapsed_time": "6:51:49", "remaining_time": "0:19:10", "throughput": 1483.62, "total_tokens": 36659152} {"current_steps": 173715, "total_steps": 181800, "loss": 0.0673, "lr": 3.0069895366533485e-07, "epoch": 19.11056105610561, "percentage": 95.55, "elapsed_time": "6:51:49", "remaining_time": "0:19:10", "throughput": 1483.62, "total_tokens": 36660176} {"current_steps": 173720, "total_steps": 181800, "loss": 0.1067, "lr": 3.0032793874629206e-07, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "6:51:50", "remaining_time": "0:19:09", "throughput": 1483.62, "total_tokens": 36661264} {"current_steps": 173725, "total_steps": 181800, "loss": 0.0031, "lr": 2.9995715147227157e-07, "epoch": 19.111661166116612, "percentage": 95.56, "elapsed_time": "6:51:51", "remaining_time": "0:19:08", "throughput": 1483.62, "total_tokens": 36662288} {"current_steps": 173730, "total_steps": 181800, "loss": 0.0006, "lr": 2.995865918466956e-07, "epoch": 19.112211221122113, "percentage": 95.56, "elapsed_time": "6:51:51", "remaining_time": "0:19:07", "throughput": 1483.62, "total_tokens": 36663312} {"current_steps": 173735, "total_steps": 181800, "loss": 0.0228, "lr": 2.9921625987297533e-07, "epoch": 19.112761276127614, "percentage": 95.56, "elapsed_time": "6:51:52", "remaining_time": "0:19:07", "throughput": 1483.62, "total_tokens": 36664336} {"current_steps": 173740, "total_steps": 181800, "loss": 0.1089, "lr": 2.9884615555452746e-07, "epoch": 19.11331133113311, "percentage": 95.57, "elapsed_time": "6:51:53", "remaining_time": "0:19:06", "throughput": 1483.63, "total_tokens": 36665456} {"current_steps": 173745, "total_steps": 181800, "loss": 0.001, "lr": 2.9847627889476316e-07, "epoch": 19.113861386138613, "percentage": 95.57, "elapsed_time": "6:51:54", "remaining_time": "0:19:05", "throughput": 1483.63, "total_tokens": 36666544} {"current_steps": 173750, "total_steps": 181800, "loss": 0.004, "lr": 2.9810662989708806e-07, "epoch": 19.114411441144114, "percentage": 95.57, "elapsed_time": "6:51:54", "remaining_time": "0:19:05", "throughput": 1483.63, "total_tokens": 36667632} {"current_steps": 173755, "total_steps": 181800, "loss": 0.0076, "lr": 2.9773720856491327e-07, "epoch": 19.114961496149615, "percentage": 95.57, "elapsed_time": "6:51:55", "remaining_time": "0:19:04", "throughput": 1483.64, "total_tokens": 36668752} {"current_steps": 173760, "total_steps": 181800, "loss": 0.0045, "lr": 2.973680149016389e-07, "epoch": 19.115511551155116, "percentage": 95.58, "elapsed_time": "6:51:56", "remaining_time": "0:19:03", "throughput": 1483.63, "total_tokens": 36669712} {"current_steps": 173765, "total_steps": 181800, "loss": 0.0031, "lr": 2.9699904891067055e-07, "epoch": 19.116061606160617, "percentage": 95.58, "elapsed_time": "6:51:56", "remaining_time": "0:19:02", "throughput": 1483.64, "total_tokens": 36670768} {"current_steps": 173770, "total_steps": 181800, "loss": 0.0048, "lr": 2.9663031059540825e-07, "epoch": 19.116611661166118, "percentage": 95.58, "elapsed_time": "6:51:57", "remaining_time": "0:19:02", "throughput": 1483.63, "total_tokens": 36671728} {"current_steps": 173775, "total_steps": 181800, "loss": 0.0454, "lr": 2.962617999592493e-07, "epoch": 19.117161716171616, "percentage": 95.59, "elapsed_time": "6:51:58", "remaining_time": "0:19:01", "throughput": 1483.63, "total_tokens": 36672784} {"current_steps": 173780, "total_steps": 181800, "loss": 0.0518, "lr": 2.9589351700559374e-07, "epoch": 19.117711771177117, "percentage": 95.59, "elapsed_time": "6:51:58", "remaining_time": "0:19:00", "throughput": 1483.64, "total_tokens": 36673840} {"current_steps": 173785, "total_steps": 181800, "loss": 0.0614, "lr": 2.955254617378361e-07, "epoch": 19.118261826182618, "percentage": 95.59, "elapsed_time": "6:51:59", "remaining_time": "0:19:00", "throughput": 1483.64, "total_tokens": 36674896} {"current_steps": 173790, "total_steps": 181800, "loss": 0.0015, "lr": 2.951576341593598e-07, "epoch": 19.11881188118812, "percentage": 95.59, "elapsed_time": "6:52:00", "remaining_time": "0:18:59", "throughput": 1483.64, "total_tokens": 36675984} {"current_steps": 173795, "total_steps": 181800, "loss": 0.0183, "lr": 2.947900342735649e-07, "epoch": 19.11936193619362, "percentage": 95.6, "elapsed_time": "6:52:00", "remaining_time": "0:18:58", "throughput": 1483.64, "total_tokens": 36677104} {"current_steps": 173800, "total_steps": 181800, "loss": 0.0165, "lr": 2.9442266208383194e-07, "epoch": 19.11991199119912, "percentage": 95.6, "elapsed_time": "6:52:01", "remaining_time": "0:18:57", "throughput": 1483.64, "total_tokens": 36678160} {"current_steps": 173805, "total_steps": 181800, "loss": 0.0661, "lr": 2.9405551759355555e-07, "epoch": 19.120462046204622, "percentage": 95.6, "elapsed_time": "6:52:02", "remaining_time": "0:18:57", "throughput": 1483.65, "total_tokens": 36679216} {"current_steps": 173810, "total_steps": 181800, "loss": 0.0031, "lr": 2.936886008061135e-07, "epoch": 19.12101210121012, "percentage": 95.61, "elapsed_time": "6:52:03", "remaining_time": "0:18:56", "throughput": 1483.65, "total_tokens": 36680272} {"current_steps": 173815, "total_steps": 181800, "loss": 0.0068, "lr": 2.933219117248837e-07, "epoch": 19.12156215621562, "percentage": 95.61, "elapsed_time": "6:52:03", "remaining_time": "0:18:55", "throughput": 1483.65, "total_tokens": 36681328} {"current_steps": 173820, "total_steps": 181800, "loss": 0.1106, "lr": 2.9295545035325224e-07, "epoch": 19.122112211221122, "percentage": 95.61, "elapsed_time": "6:52:04", "remaining_time": "0:18:55", "throughput": 1483.65, "total_tokens": 36682320} {"current_steps": 173825, "total_steps": 181800, "loss": 0.0075, "lr": 2.9258921669459705e-07, "epoch": 19.122662266226623, "percentage": 95.61, "elapsed_time": "6:52:05", "remaining_time": "0:18:54", "throughput": 1483.65, "total_tokens": 36683344} {"current_steps": 173830, "total_steps": 181800, "loss": 0.0007, "lr": 2.922232107522904e-07, "epoch": 19.123212321232124, "percentage": 95.62, "elapsed_time": "6:52:05", "remaining_time": "0:18:53", "throughput": 1483.65, "total_tokens": 36684368} {"current_steps": 173835, "total_steps": 181800, "loss": 0.0022, "lr": 2.9185743252970743e-07, "epoch": 19.123762376237625, "percentage": 95.62, "elapsed_time": "6:52:06", "remaining_time": "0:18:52", "throughput": 1483.65, "total_tokens": 36685456} {"current_steps": 173840, "total_steps": 181800, "loss": 0.0036, "lr": 2.914918820302176e-07, "epoch": 19.124312431243123, "percentage": 95.62, "elapsed_time": "6:52:07", "remaining_time": "0:18:52", "throughput": 1483.65, "total_tokens": 36686512} {"current_steps": 173845, "total_steps": 181800, "loss": 0.1119, "lr": 2.9112655925719044e-07, "epoch": 19.124862486248624, "percentage": 95.62, "elapsed_time": "6:52:07", "remaining_time": "0:18:51", "throughput": 1483.65, "total_tokens": 36687568} {"current_steps": 173850, "total_steps": 181800, "loss": 0.0024, "lr": 2.9076146421399277e-07, "epoch": 19.125412541254125, "percentage": 95.63, "elapsed_time": "6:52:08", "remaining_time": "0:18:50", "throughput": 1483.65, "total_tokens": 36688560} {"current_steps": 173855, "total_steps": 181800, "loss": 0.0218, "lr": 2.9039659690398844e-07, "epoch": 19.125962596259626, "percentage": 95.63, "elapsed_time": "6:52:09", "remaining_time": "0:18:50", "throughput": 1483.65, "total_tokens": 36689616} {"current_steps": 173860, "total_steps": 181800, "loss": 0.0517, "lr": 2.9003195733054435e-07, "epoch": 19.126512651265127, "percentage": 95.63, "elapsed_time": "6:52:09", "remaining_time": "0:18:49", "throughput": 1483.65, "total_tokens": 36690640} {"current_steps": 173865, "total_steps": 181800, "loss": 0.0031, "lr": 2.896675454970188e-07, "epoch": 19.127062706270628, "percentage": 95.64, "elapsed_time": "6:52:10", "remaining_time": "0:18:48", "throughput": 1483.65, "total_tokens": 36691696} {"current_steps": 173870, "total_steps": 181800, "loss": 0.1304, "lr": 2.8930336140677025e-07, "epoch": 19.12761276127613, "percentage": 95.64, "elapsed_time": "6:52:11", "remaining_time": "0:18:47", "throughput": 1483.65, "total_tokens": 36692688} {"current_steps": 173875, "total_steps": 181800, "loss": 0.0312, "lr": 2.889394050631544e-07, "epoch": 19.128162816281627, "percentage": 95.64, "elapsed_time": "6:52:12", "remaining_time": "0:18:47", "throughput": 1483.65, "total_tokens": 36693680} {"current_steps": 173880, "total_steps": 181800, "loss": 0.0041, "lr": 2.8857567646952687e-07, "epoch": 19.128712871287128, "percentage": 95.64, "elapsed_time": "6:52:12", "remaining_time": "0:18:46", "throughput": 1483.65, "total_tokens": 36694736} {"current_steps": 173885, "total_steps": 181800, "loss": 0.0017, "lr": 2.882121756292405e-07, "epoch": 19.12926292629263, "percentage": 95.65, "elapsed_time": "6:52:13", "remaining_time": "0:18:45", "throughput": 1483.65, "total_tokens": 36695760} {"current_steps": 173890, "total_steps": 181800, "loss": 0.0166, "lr": 2.8784890254564265e-07, "epoch": 19.12981298129813, "percentage": 95.65, "elapsed_time": "6:52:14", "remaining_time": "0:18:45", "throughput": 1483.65, "total_tokens": 36696816} {"current_steps": 173895, "total_steps": 181800, "loss": 0.0549, "lr": 2.874858572220862e-07, "epoch": 19.13036303630363, "percentage": 95.65, "elapsed_time": "6:52:14", "remaining_time": "0:18:44", "throughput": 1483.65, "total_tokens": 36697840} {"current_steps": 173900, "total_steps": 181800, "loss": 0.0081, "lr": 2.871230396619129e-07, "epoch": 19.130913091309132, "percentage": 95.65, "elapsed_time": "6:52:15", "remaining_time": "0:18:43", "throughput": 1483.65, "total_tokens": 36698928} {"current_steps": 173905, "total_steps": 181800, "loss": 0.0346, "lr": 2.8676044986846727e-07, "epoch": 19.13146314631463, "percentage": 95.66, "elapsed_time": "6:52:16", "remaining_time": "0:18:42", "throughput": 1483.65, "total_tokens": 36699920} {"current_steps": 173910, "total_steps": 181800, "loss": 0.0357, "lr": 2.863980878450939e-07, "epoch": 19.13201320132013, "percentage": 95.66, "elapsed_time": "6:52:16", "remaining_time": "0:18:42", "throughput": 1483.66, "total_tokens": 36700976} {"current_steps": 173915, "total_steps": 181800, "loss": 0.051, "lr": 2.86035953595129e-07, "epoch": 19.132563256325632, "percentage": 95.66, "elapsed_time": "6:52:17", "remaining_time": "0:18:41", "throughput": 1483.66, "total_tokens": 36702000} {"current_steps": 173920, "total_steps": 181800, "loss": 0.0045, "lr": 2.856740471219116e-07, "epoch": 19.133113311331133, "percentage": 95.67, "elapsed_time": "6:52:18", "remaining_time": "0:18:40", "throughput": 1483.66, "total_tokens": 36703088} {"current_steps": 173925, "total_steps": 181800, "loss": 0.0821, "lr": 2.8531236842878064e-07, "epoch": 19.133663366336634, "percentage": 95.67, "elapsed_time": "6:52:18", "remaining_time": "0:18:40", "throughput": 1483.66, "total_tokens": 36704144} {"current_steps": 173930, "total_steps": 181800, "loss": 0.03, "lr": 2.849509175190612e-07, "epoch": 19.134213421342135, "percentage": 95.67, "elapsed_time": "6:52:19", "remaining_time": "0:18:39", "throughput": 1483.66, "total_tokens": 36705168} {"current_steps": 173935, "total_steps": 181800, "loss": 0.0013, "lr": 2.845896943960952e-07, "epoch": 19.134763476347636, "percentage": 95.67, "elapsed_time": "6:52:20", "remaining_time": "0:18:38", "throughput": 1483.66, "total_tokens": 36706128} {"current_steps": 173940, "total_steps": 181800, "loss": 0.0018, "lr": 2.842286990631993e-07, "epoch": 19.135313531353134, "percentage": 95.68, "elapsed_time": "6:52:20", "remaining_time": "0:18:37", "throughput": 1483.66, "total_tokens": 36707184} {"current_steps": 173945, "total_steps": 181800, "loss": 0.1048, "lr": 2.8386793152371526e-07, "epoch": 19.135863586358635, "percentage": 95.68, "elapsed_time": "6:52:21", "remaining_time": "0:18:37", "throughput": 1483.66, "total_tokens": 36708176} {"current_steps": 173950, "total_steps": 181800, "loss": 0.0038, "lr": 2.835073917809572e-07, "epoch": 19.136413641364136, "percentage": 95.68, "elapsed_time": "6:52:22", "remaining_time": "0:18:36", "throughput": 1483.66, "total_tokens": 36709296} {"current_steps": 173955, "total_steps": 181800, "loss": 0.0069, "lr": 2.8314707983825015e-07, "epoch": 19.136963696369637, "percentage": 95.68, "elapsed_time": "6:52:23", "remaining_time": "0:18:35", "throughput": 1483.66, "total_tokens": 36710352} {"current_steps": 173960, "total_steps": 181800, "loss": 0.0562, "lr": 2.827869956989193e-07, "epoch": 19.13751375137514, "percentage": 95.69, "elapsed_time": "6:52:23", "remaining_time": "0:18:35", "throughput": 1483.66, "total_tokens": 36711408} {"current_steps": 173965, "total_steps": 181800, "loss": 0.0075, "lr": 2.8242713936627586e-07, "epoch": 19.13806380638064, "percentage": 95.69, "elapsed_time": "6:52:24", "remaining_time": "0:18:34", "throughput": 1483.66, "total_tokens": 36712400} {"current_steps": 173970, "total_steps": 181800, "loss": 0.0009, "lr": 2.820675108436449e-07, "epoch": 19.138613861386137, "percentage": 95.69, "elapsed_time": "6:52:25", "remaining_time": "0:18:33", "throughput": 1483.66, "total_tokens": 36713456} {"current_steps": 173975, "total_steps": 181800, "loss": 0.081, "lr": 2.8170811013433495e-07, "epoch": 19.139163916391638, "percentage": 95.7, "elapsed_time": "6:52:25", "remaining_time": "0:18:33", "throughput": 1483.66, "total_tokens": 36714480} {"current_steps": 173980, "total_steps": 181800, "loss": 0.001, "lr": 2.8134893724166e-07, "epoch": 19.13971397139714, "percentage": 95.7, "elapsed_time": "6:52:26", "remaining_time": "0:18:32", "throughput": 1483.66, "total_tokens": 36715504} {"current_steps": 173985, "total_steps": 181800, "loss": 0.0006, "lr": 2.809899921689313e-07, "epoch": 19.14026402640264, "percentage": 95.7, "elapsed_time": "6:52:27", "remaining_time": "0:18:31", "throughput": 1483.66, "total_tokens": 36716496} {"current_steps": 173990, "total_steps": 181800, "loss": 0.0887, "lr": 2.806312749194573e-07, "epoch": 19.14081408140814, "percentage": 95.7, "elapsed_time": "6:52:27", "remaining_time": "0:18:30", "throughput": 1483.67, "total_tokens": 36717584} {"current_steps": 173995, "total_steps": 181800, "loss": 0.0014, "lr": 2.802727854965409e-07, "epoch": 19.141364136413642, "percentage": 95.71, "elapsed_time": "6:52:28", "remaining_time": "0:18:30", "throughput": 1483.67, "total_tokens": 36718608} {"current_steps": 174000, "total_steps": 181800, "loss": 0.0248, "lr": 2.799145239034934e-07, "epoch": 19.141914191419144, "percentage": 95.71, "elapsed_time": "6:52:29", "remaining_time": "0:18:29", "throughput": 1483.67, "total_tokens": 36719664} {"current_steps": 174005, "total_steps": 181800, "loss": 0.1037, "lr": 2.795564901436065e-07, "epoch": 19.14246424642464, "percentage": 95.71, "elapsed_time": "6:52:29", "remaining_time": "0:18:28", "throughput": 1483.67, "total_tokens": 36720688} {"current_steps": 174010, "total_steps": 181800, "loss": 0.0092, "lr": 2.791986842201888e-07, "epoch": 19.143014301430142, "percentage": 95.72, "elapsed_time": "6:52:30", "remaining_time": "0:18:28", "throughput": 1483.67, "total_tokens": 36721808} {"current_steps": 174015, "total_steps": 181800, "loss": 0.0671, "lr": 2.7884110613653204e-07, "epoch": 19.143564356435643, "percentage": 95.72, "elapsed_time": "6:52:31", "remaining_time": "0:18:27", "throughput": 1483.67, "total_tokens": 36722832} {"current_steps": 174020, "total_steps": 181800, "loss": 0.1091, "lr": 2.784837558959391e-07, "epoch": 19.144114411441144, "percentage": 95.72, "elapsed_time": "6:52:32", "remaining_time": "0:18:26", "throughput": 1483.67, "total_tokens": 36723856} {"current_steps": 174025, "total_steps": 181800, "loss": 0.0012, "lr": 2.7812663350169357e-07, "epoch": 19.144664466446645, "percentage": 95.72, "elapsed_time": "6:52:32", "remaining_time": "0:18:25", "throughput": 1483.67, "total_tokens": 36724912} {"current_steps": 174030, "total_steps": 181800, "loss": 0.0058, "lr": 2.777697389570927e-07, "epoch": 19.145214521452147, "percentage": 95.73, "elapsed_time": "6:52:33", "remaining_time": "0:18:25", "throughput": 1483.67, "total_tokens": 36725904} {"current_steps": 174035, "total_steps": 181800, "loss": 0.0083, "lr": 2.7741307226542833e-07, "epoch": 19.145764576457644, "percentage": 95.73, "elapsed_time": "6:52:34", "remaining_time": "0:18:24", "throughput": 1483.67, "total_tokens": 36726960} {"current_steps": 174040, "total_steps": 181800, "loss": 0.0011, "lr": 2.77056633429984e-07, "epoch": 19.146314631463145, "percentage": 95.73, "elapsed_time": "6:52:34", "remaining_time": "0:18:23", "throughput": 1483.67, "total_tokens": 36727984} {"current_steps": 174045, "total_steps": 181800, "loss": 0.0027, "lr": 2.767004224540459e-07, "epoch": 19.146864686468646, "percentage": 95.73, "elapsed_time": "6:52:35", "remaining_time": "0:18:23", "throughput": 1483.68, "total_tokens": 36729104} {"current_steps": 174050, "total_steps": 181800, "loss": 0.0017, "lr": 2.763444393408948e-07, "epoch": 19.147414741474147, "percentage": 95.74, "elapsed_time": "6:52:36", "remaining_time": "0:18:22", "throughput": 1483.68, "total_tokens": 36730160} {"current_steps": 174055, "total_steps": 181800, "loss": 0.0769, "lr": 2.759886840938114e-07, "epoch": 19.14796479647965, "percentage": 95.74, "elapsed_time": "6:52:36", "remaining_time": "0:18:21", "throughput": 1483.68, "total_tokens": 36731184} {"current_steps": 174060, "total_steps": 181800, "loss": 0.0387, "lr": 2.756331567160819e-07, "epoch": 19.14851485148515, "percentage": 95.74, "elapsed_time": "6:52:37", "remaining_time": "0:18:20", "throughput": 1483.68, "total_tokens": 36732176} {"current_steps": 174065, "total_steps": 181800, "loss": 0.0018, "lr": 2.752778572109732e-07, "epoch": 19.14906490649065, "percentage": 95.75, "elapsed_time": "6:52:38", "remaining_time": "0:18:20", "throughput": 1483.68, "total_tokens": 36733200} {"current_steps": 174070, "total_steps": 181800, "loss": 0.0208, "lr": 2.7492278558176597e-07, "epoch": 19.149614961496148, "percentage": 95.75, "elapsed_time": "6:52:38", "remaining_time": "0:18:19", "throughput": 1483.68, "total_tokens": 36734224} {"current_steps": 174075, "total_steps": 181800, "loss": 0.0124, "lr": 2.745679418317326e-07, "epoch": 19.15016501650165, "percentage": 95.75, "elapsed_time": "6:52:39", "remaining_time": "0:18:18", "throughput": 1483.68, "total_tokens": 36735280} {"current_steps": 174080, "total_steps": 181800, "loss": 0.0028, "lr": 2.7421332596413997e-07, "epoch": 19.15071507150715, "percentage": 95.75, "elapsed_time": "6:52:40", "remaining_time": "0:18:18", "throughput": 1483.68, "total_tokens": 36736336} {"current_steps": 174085, "total_steps": 181800, "loss": 0.0497, "lr": 2.738589379822604e-07, "epoch": 19.15126512651265, "percentage": 95.76, "elapsed_time": "6:52:40", "remaining_time": "0:18:17", "throughput": 1483.68, "total_tokens": 36737424} {"current_steps": 174090, "total_steps": 181800, "loss": 0.0036, "lr": 2.7350477788935513e-07, "epoch": 19.151815181518153, "percentage": 95.76, "elapsed_time": "6:52:41", "remaining_time": "0:18:16", "throughput": 1483.68, "total_tokens": 36738480} {"current_steps": 174095, "total_steps": 181800, "loss": 0.0061, "lr": 2.731508456886939e-07, "epoch": 19.152365236523654, "percentage": 95.76, "elapsed_time": "6:52:42", "remaining_time": "0:18:15", "throughput": 1483.68, "total_tokens": 36739568} {"current_steps": 174100, "total_steps": 181800, "loss": 0.0857, "lr": 2.7279714138353785e-07, "epoch": 19.15291529152915, "percentage": 95.76, "elapsed_time": "6:52:43", "remaining_time": "0:18:15", "throughput": 1483.69, "total_tokens": 36740656} {"current_steps": 174105, "total_steps": 181800, "loss": 0.0231, "lr": 2.724436649771428e-07, "epoch": 19.153465346534652, "percentage": 95.77, "elapsed_time": "6:52:43", "remaining_time": "0:18:14", "throughput": 1483.69, "total_tokens": 36741744} {"current_steps": 174110, "total_steps": 181800, "loss": 0.0027, "lr": 2.7209041647277e-07, "epoch": 19.154015401540153, "percentage": 95.77, "elapsed_time": "6:52:44", "remaining_time": "0:18:13", "throughput": 1483.69, "total_tokens": 36742800} {"current_steps": 174115, "total_steps": 181800, "loss": 0.0042, "lr": 2.717373958736724e-07, "epoch": 19.154565456545654, "percentage": 95.77, "elapsed_time": "6:52:45", "remaining_time": "0:18:13", "throughput": 1483.69, "total_tokens": 36743856} {"current_steps": 174120, "total_steps": 181800, "loss": 0.0021, "lr": 2.7138460318310577e-07, "epoch": 19.155115511551156, "percentage": 95.78, "elapsed_time": "6:52:45", "remaining_time": "0:18:12", "throughput": 1483.69, "total_tokens": 36744912} {"current_steps": 174125, "total_steps": 181800, "loss": 0.0427, "lr": 2.71032038404323e-07, "epoch": 19.155665566556657, "percentage": 95.78, "elapsed_time": "6:52:46", "remaining_time": "0:18:11", "throughput": 1483.69, "total_tokens": 36745968} {"current_steps": 174130, "total_steps": 181800, "loss": 0.0176, "lr": 2.706797015405715e-07, "epoch": 19.156215621562158, "percentage": 95.78, "elapsed_time": "6:52:47", "remaining_time": "0:18:10", "throughput": 1483.7, "total_tokens": 36747088} {"current_steps": 174135, "total_steps": 181800, "loss": 0.0024, "lr": 2.703275925950988e-07, "epoch": 19.156765676567655, "percentage": 95.78, "elapsed_time": "6:52:47", "remaining_time": "0:18:10", "throughput": 1483.7, "total_tokens": 36748080} {"current_steps": 174140, "total_steps": 181800, "loss": 0.0017, "lr": 2.6997571157114933e-07, "epoch": 19.157315731573156, "percentage": 95.79, "elapsed_time": "6:52:48", "remaining_time": "0:18:09", "throughput": 1483.7, "total_tokens": 36749136} {"current_steps": 174145, "total_steps": 181800, "loss": 0.0016, "lr": 2.696240584719678e-07, "epoch": 19.157865786578657, "percentage": 95.79, "elapsed_time": "6:52:49", "remaining_time": "0:18:08", "throughput": 1483.7, "total_tokens": 36750224} {"current_steps": 174150, "total_steps": 181800, "loss": 0.0653, "lr": 2.692726333007961e-07, "epoch": 19.15841584158416, "percentage": 95.79, "elapsed_time": "6:52:50", "remaining_time": "0:18:08", "throughput": 1483.7, "total_tokens": 36751280} {"current_steps": 174155, "total_steps": 181800, "loss": 0.0203, "lr": 2.689214360608677e-07, "epoch": 19.15896589658966, "percentage": 95.79, "elapsed_time": "6:52:50", "remaining_time": "0:18:07", "throughput": 1483.7, "total_tokens": 36752336} {"current_steps": 174160, "total_steps": 181800, "loss": 0.1063, "lr": 2.685704667554273e-07, "epoch": 19.15951595159516, "percentage": 95.8, "elapsed_time": "6:52:51", "remaining_time": "0:18:06", "throughput": 1483.7, "total_tokens": 36753392} {"current_steps": 174165, "total_steps": 181800, "loss": 0.0216, "lr": 2.6821972538770557e-07, "epoch": 19.16006600660066, "percentage": 95.8, "elapsed_time": "6:52:52", "remaining_time": "0:18:05", "throughput": 1483.7, "total_tokens": 36754448} {"current_steps": 174170, "total_steps": 181800, "loss": 0.0355, "lr": 2.678692119609333e-07, "epoch": 19.16061606160616, "percentage": 95.8, "elapsed_time": "6:52:52", "remaining_time": "0:18:05", "throughput": 1483.71, "total_tokens": 36755504} {"current_steps": 174175, "total_steps": 181800, "loss": 0.0072, "lr": 2.675189264783412e-07, "epoch": 19.16116611661166, "percentage": 95.81, "elapsed_time": "6:52:53", "remaining_time": "0:18:04", "throughput": 1483.71, "total_tokens": 36756528} {"current_steps": 174180, "total_steps": 181800, "loss": 0.0009, "lr": 2.6716886894316007e-07, "epoch": 19.16171617161716, "percentage": 95.81, "elapsed_time": "6:52:54", "remaining_time": "0:18:03", "throughput": 1483.7, "total_tokens": 36757520} {"current_steps": 174185, "total_steps": 181800, "loss": 0.0032, "lr": 2.668190393586178e-07, "epoch": 19.162266226622663, "percentage": 95.81, "elapsed_time": "6:52:54", "remaining_time": "0:18:03", "throughput": 1483.7, "total_tokens": 36758544} {"current_steps": 174190, "total_steps": 181800, "loss": 0.0008, "lr": 2.66469437727937e-07, "epoch": 19.162816281628164, "percentage": 95.81, "elapsed_time": "6:52:55", "remaining_time": "0:18:02", "throughput": 1483.7, "total_tokens": 36759504} {"current_steps": 174195, "total_steps": 181800, "loss": 0.0801, "lr": 2.661200640543371e-07, "epoch": 19.163366336633665, "percentage": 95.82, "elapsed_time": "6:52:56", "remaining_time": "0:18:01", "throughput": 1483.7, "total_tokens": 36760496} {"current_steps": 174200, "total_steps": 181800, "loss": 0.0053, "lr": 2.6577091834103783e-07, "epoch": 19.163916391639162, "percentage": 95.82, "elapsed_time": "6:52:56", "remaining_time": "0:18:00", "throughput": 1483.7, "total_tokens": 36761520} {"current_steps": 174205, "total_steps": 181800, "loss": 0.0082, "lr": 2.6542200059126167e-07, "epoch": 19.164466446644663, "percentage": 95.82, "elapsed_time": "6:52:57", "remaining_time": "0:18:00", "throughput": 1483.7, "total_tokens": 36762640} {"current_steps": 174210, "total_steps": 181800, "loss": 0.0026, "lr": 2.650733108082226e-07, "epoch": 19.165016501650165, "percentage": 95.83, "elapsed_time": "6:52:58", "remaining_time": "0:17:59", "throughput": 1483.7, "total_tokens": 36763696} {"current_steps": 174215, "total_steps": 181800, "loss": 0.0052, "lr": 2.647248489951348e-07, "epoch": 19.165566556655666, "percentage": 95.83, "elapsed_time": "6:52:58", "remaining_time": "0:17:58", "throughput": 1483.71, "total_tokens": 36764848} {"current_steps": 174220, "total_steps": 181800, "loss": 0.001, "lr": 2.643766151552068e-07, "epoch": 19.166116611661167, "percentage": 95.83, "elapsed_time": "6:52:59", "remaining_time": "0:17:58", "throughput": 1483.71, "total_tokens": 36765872} {"current_steps": 174225, "total_steps": 181800, "loss": 0.006, "lr": 2.6402860929165277e-07, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "6:53:00", "remaining_time": "0:17:57", "throughput": 1483.71, "total_tokens": 36766928} {"current_steps": 174230, "total_steps": 181800, "loss": 0.1466, "lr": 2.636808314076755e-07, "epoch": 19.16721672167217, "percentage": 95.84, "elapsed_time": "6:53:01", "remaining_time": "0:17:56", "throughput": 1483.71, "total_tokens": 36767920} {"current_steps": 174235, "total_steps": 181800, "loss": 0.0036, "lr": 2.63333281506481e-07, "epoch": 19.167766776677666, "percentage": 95.84, "elapsed_time": "6:53:01", "remaining_time": "0:17:55", "throughput": 1483.71, "total_tokens": 36768912} {"current_steps": 174240, "total_steps": 181800, "loss": 0.0172, "lr": 2.629859595912776e-07, "epoch": 19.168316831683168, "percentage": 95.84, "elapsed_time": "6:53:02", "remaining_time": "0:17:55", "throughput": 1483.71, "total_tokens": 36769936} {"current_steps": 174245, "total_steps": 181800, "loss": 0.0024, "lr": 2.626388656652601e-07, "epoch": 19.16886688668867, "percentage": 95.84, "elapsed_time": "6:53:03", "remaining_time": "0:17:54", "throughput": 1483.71, "total_tokens": 36770992} {"current_steps": 174250, "total_steps": 181800, "loss": 0.0536, "lr": 2.6229199973163143e-07, "epoch": 19.16941694169417, "percentage": 95.85, "elapsed_time": "6:53:03", "remaining_time": "0:17:53", "throughput": 1483.71, "total_tokens": 36771952} {"current_steps": 174255, "total_steps": 181800, "loss": 0.0309, "lr": 2.619453617935863e-07, "epoch": 19.16996699669967, "percentage": 95.85, "elapsed_time": "6:53:04", "remaining_time": "0:17:53", "throughput": 1483.71, "total_tokens": 36772976} {"current_steps": 174260, "total_steps": 181800, "loss": 0.0433, "lr": 2.6159895185431936e-07, "epoch": 19.170517051705172, "percentage": 95.85, "elapsed_time": "6:53:05", "remaining_time": "0:17:52", "throughput": 1483.71, "total_tokens": 36774000} {"current_steps": 174265, "total_steps": 181800, "loss": 0.0023, "lr": 2.612527699170253e-07, "epoch": 19.17106710671067, "percentage": 95.86, "elapsed_time": "6:53:05", "remaining_time": "0:17:51", "throughput": 1483.71, "total_tokens": 36774992} {"current_steps": 174270, "total_steps": 181800, "loss": 0.0008, "lr": 2.609068159848932e-07, "epoch": 19.17161716171617, "percentage": 95.86, "elapsed_time": "6:53:06", "remaining_time": "0:17:50", "throughput": 1483.71, "total_tokens": 36776080} {"current_steps": 174275, "total_steps": 181800, "loss": 0.1297, "lr": 2.605610900611122e-07, "epoch": 19.17216721672167, "percentage": 95.86, "elapsed_time": "6:53:07", "remaining_time": "0:17:50", "throughput": 1483.71, "total_tokens": 36777072} {"current_steps": 174280, "total_steps": 181800, "loss": 0.0035, "lr": 2.602155921488686e-07, "epoch": 19.172717271727173, "percentage": 95.86, "elapsed_time": "6:53:07", "remaining_time": "0:17:49", "throughput": 1483.71, "total_tokens": 36778128} {"current_steps": 174285, "total_steps": 181800, "loss": 0.0125, "lr": 2.59870322251346e-07, "epoch": 19.173267326732674, "percentage": 95.87, "elapsed_time": "6:53:08", "remaining_time": "0:17:48", "throughput": 1483.71, "total_tokens": 36779184} {"current_steps": 174290, "total_steps": 181800, "loss": 0.0043, "lr": 2.5952528037172795e-07, "epoch": 19.173817381738175, "percentage": 95.87, "elapsed_time": "6:53:09", "remaining_time": "0:17:48", "throughput": 1483.71, "total_tokens": 36780176} {"current_steps": 174295, "total_steps": 181800, "loss": 0.0039, "lr": 2.591804665131925e-07, "epoch": 19.174367436743676, "percentage": 95.87, "elapsed_time": "6:53:10", "remaining_time": "0:17:47", "throughput": 1483.71, "total_tokens": 36781200} {"current_steps": 174300, "total_steps": 181800, "loss": 0.0034, "lr": 2.588358806789204e-07, "epoch": 19.174917491749174, "percentage": 95.87, "elapsed_time": "6:53:10", "remaining_time": "0:17:46", "throughput": 1483.71, "total_tokens": 36782192} {"current_steps": 174305, "total_steps": 181800, "loss": 0.0168, "lr": 2.584915228720869e-07, "epoch": 19.175467546754675, "percentage": 95.88, "elapsed_time": "6:53:11", "remaining_time": "0:17:46", "throughput": 1483.71, "total_tokens": 36783280} {"current_steps": 174310, "total_steps": 181800, "loss": 0.0055, "lr": 2.5814739309586167e-07, "epoch": 19.176017601760176, "percentage": 95.88, "elapsed_time": "6:53:12", "remaining_time": "0:17:45", "throughput": 1483.71, "total_tokens": 36784336} {"current_steps": 174315, "total_steps": 181800, "loss": 0.001, "lr": 2.5780349135342275e-07, "epoch": 19.176567656765677, "percentage": 95.88, "elapsed_time": "6:53:12", "remaining_time": "0:17:44", "throughput": 1483.71, "total_tokens": 36785360} {"current_steps": 174320, "total_steps": 181800, "loss": 0.0034, "lr": 2.5745981764793425e-07, "epoch": 19.177117711771178, "percentage": 95.89, "elapsed_time": "6:53:13", "remaining_time": "0:17:43", "throughput": 1483.71, "total_tokens": 36786448} {"current_steps": 174325, "total_steps": 181800, "loss": 0.119, "lr": 2.571163719825687e-07, "epoch": 19.17766776677668, "percentage": 95.89, "elapsed_time": "6:53:14", "remaining_time": "0:17:43", "throughput": 1483.71, "total_tokens": 36787504} {"current_steps": 174330, "total_steps": 181800, "loss": 0.001, "lr": 2.567731543604873e-07, "epoch": 19.178217821782177, "percentage": 95.89, "elapsed_time": "6:53:14", "remaining_time": "0:17:42", "throughput": 1483.72, "total_tokens": 36788656} {"current_steps": 174335, "total_steps": 181800, "loss": 0.0561, "lr": 2.5643016478485436e-07, "epoch": 19.178767876787678, "percentage": 95.89, "elapsed_time": "6:53:15", "remaining_time": "0:17:41", "throughput": 1483.72, "total_tokens": 36789680} {"current_steps": 174340, "total_steps": 181800, "loss": 0.0076, "lr": 2.560874032588312e-07, "epoch": 19.17931793179318, "percentage": 95.9, "elapsed_time": "6:53:16", "remaining_time": "0:17:41", "throughput": 1483.72, "total_tokens": 36790704} {"current_steps": 174345, "total_steps": 181800, "loss": 0.0011, "lr": 2.5574486978557633e-07, "epoch": 19.17986798679868, "percentage": 95.9, "elapsed_time": "6:53:16", "remaining_time": "0:17:40", "throughput": 1483.72, "total_tokens": 36791792} {"current_steps": 174350, "total_steps": 181800, "loss": 0.0431, "lr": 2.554025643682484e-07, "epoch": 19.18041804180418, "percentage": 95.9, "elapsed_time": "6:53:17", "remaining_time": "0:17:39", "throughput": 1483.72, "total_tokens": 36792816} {"current_steps": 174355, "total_steps": 181800, "loss": 0.1311, "lr": 2.5506048701000317e-07, "epoch": 19.180968096809682, "percentage": 95.9, "elapsed_time": "6:53:18", "remaining_time": "0:17:38", "throughput": 1483.72, "total_tokens": 36793936} {"current_steps": 174360, "total_steps": 181800, "loss": 0.0179, "lr": 2.5471863771399094e-07, "epoch": 19.181518151815183, "percentage": 95.91, "elapsed_time": "6:53:19", "remaining_time": "0:17:38", "throughput": 1483.73, "total_tokens": 36794992} {"current_steps": 174365, "total_steps": 181800, "loss": 0.0398, "lr": 2.54377016483362e-07, "epoch": 19.18206820682068, "percentage": 95.91, "elapsed_time": "6:53:19", "remaining_time": "0:17:37", "throughput": 1483.73, "total_tokens": 36796016} {"current_steps": 174370, "total_steps": 181800, "loss": 0.0009, "lr": 2.540356233212665e-07, "epoch": 19.182618261826182, "percentage": 95.91, "elapsed_time": "6:53:20", "remaining_time": "0:17:36", "throughput": 1483.73, "total_tokens": 36797072} {"current_steps": 174375, "total_steps": 181800, "loss": 0.0009, "lr": 2.5369445823084926e-07, "epoch": 19.183168316831683, "percentage": 95.92, "elapsed_time": "6:53:21", "remaining_time": "0:17:36", "throughput": 1483.73, "total_tokens": 36798192} {"current_steps": 174380, "total_steps": 181800, "loss": 0.0483, "lr": 2.533535212152577e-07, "epoch": 19.183718371837184, "percentage": 95.92, "elapsed_time": "6:53:21", "remaining_time": "0:17:35", "throughput": 1483.74, "total_tokens": 36799376} {"current_steps": 174385, "total_steps": 181800, "loss": 0.1037, "lr": 2.53012812277631e-07, "epoch": 19.184268426842685, "percentage": 95.92, "elapsed_time": "6:53:22", "remaining_time": "0:17:34", "throughput": 1483.74, "total_tokens": 36800400} {"current_steps": 174390, "total_steps": 181800, "loss": 0.0214, "lr": 2.5267233142111104e-07, "epoch": 19.184818481848186, "percentage": 95.92, "elapsed_time": "6:53:23", "remaining_time": "0:17:33", "throughput": 1483.74, "total_tokens": 36801424} {"current_steps": 174395, "total_steps": 181800, "loss": 0.0354, "lr": 2.5233207864883704e-07, "epoch": 19.185368536853684, "percentage": 95.93, "elapsed_time": "6:53:23", "remaining_time": "0:17:33", "throughput": 1483.74, "total_tokens": 36802448} {"current_steps": 174400, "total_steps": 181800, "loss": 0.0229, "lr": 2.5199205396393975e-07, "epoch": 19.185918591859185, "percentage": 95.93, "elapsed_time": "6:53:24", "remaining_time": "0:17:32", "throughput": 1483.74, "total_tokens": 36803504} {"current_steps": 174405, "total_steps": 181800, "loss": 0.1017, "lr": 2.5165225736955845e-07, "epoch": 19.186468646864686, "percentage": 95.93, "elapsed_time": "6:53:25", "remaining_time": "0:17:31", "throughput": 1483.74, "total_tokens": 36804560} {"current_steps": 174410, "total_steps": 181800, "loss": 0.0746, "lr": 2.5131268886882107e-07, "epoch": 19.187018701870187, "percentage": 95.94, "elapsed_time": "6:53:25", "remaining_time": "0:17:31", "throughput": 1483.74, "total_tokens": 36805616} {"current_steps": 174415, "total_steps": 181800, "loss": 0.003, "lr": 2.509733484648613e-07, "epoch": 19.187568756875688, "percentage": 95.94, "elapsed_time": "6:53:26", "remaining_time": "0:17:30", "throughput": 1483.74, "total_tokens": 36806672} {"current_steps": 174420, "total_steps": 181800, "loss": 0.1076, "lr": 2.506342361608044e-07, "epoch": 19.18811881188119, "percentage": 95.94, "elapsed_time": "6:53:27", "remaining_time": "0:17:29", "throughput": 1483.74, "total_tokens": 36807632} {"current_steps": 174425, "total_steps": 181800, "loss": 0.0704, "lr": 2.502953519597756e-07, "epoch": 19.18866886688669, "percentage": 95.94, "elapsed_time": "6:53:28", "remaining_time": "0:17:28", "throughput": 1483.74, "total_tokens": 36808752} {"current_steps": 174430, "total_steps": 181800, "loss": 0.0484, "lr": 2.4995669586489467e-07, "epoch": 19.189218921892188, "percentage": 95.95, "elapsed_time": "6:53:28", "remaining_time": "0:17:28", "throughput": 1483.74, "total_tokens": 36809776} {"current_steps": 174435, "total_steps": 181800, "loss": 0.0029, "lr": 2.4961826787928965e-07, "epoch": 19.18976897689769, "percentage": 95.95, "elapsed_time": "6:53:29", "remaining_time": "0:17:27", "throughput": 1483.74, "total_tokens": 36810832} {"current_steps": 174440, "total_steps": 181800, "loss": 0.0876, "lr": 2.492800680060775e-07, "epoch": 19.19031903190319, "percentage": 95.95, "elapsed_time": "6:53:30", "remaining_time": "0:17:26", "throughput": 1483.74, "total_tokens": 36811856} {"current_steps": 174445, "total_steps": 181800, "loss": 0.0008, "lr": 2.489420962483752e-07, "epoch": 19.19086908690869, "percentage": 95.95, "elapsed_time": "6:53:30", "remaining_time": "0:17:26", "throughput": 1483.74, "total_tokens": 36812912} {"current_steps": 174450, "total_steps": 181800, "loss": 0.002, "lr": 2.4860435260929404e-07, "epoch": 19.191419141914192, "percentage": 95.96, "elapsed_time": "6:53:31", "remaining_time": "0:17:25", "throughput": 1483.75, "total_tokens": 36813968} {"current_steps": 174455, "total_steps": 181800, "loss": 0.0352, "lr": 2.4826683709195384e-07, "epoch": 19.191969196919693, "percentage": 95.96, "elapsed_time": "6:53:32", "remaining_time": "0:17:24", "throughput": 1483.75, "total_tokens": 36815088} {"current_steps": 174460, "total_steps": 181800, "loss": 0.002, "lr": 2.479295496994577e-07, "epoch": 19.19251925192519, "percentage": 95.96, "elapsed_time": "6:53:32", "remaining_time": "0:17:23", "throughput": 1483.75, "total_tokens": 36816080} {"current_steps": 174465, "total_steps": 181800, "loss": 0.0865, "lr": 2.4759249043491694e-07, "epoch": 19.193069306930692, "percentage": 95.97, "elapsed_time": "6:53:33", "remaining_time": "0:17:23", "throughput": 1483.75, "total_tokens": 36817040} {"current_steps": 174470, "total_steps": 181800, "loss": 0.0018, "lr": 2.472556593014402e-07, "epoch": 19.193619361936193, "percentage": 95.97, "elapsed_time": "6:53:34", "remaining_time": "0:17:22", "throughput": 1483.75, "total_tokens": 36818096} {"current_steps": 174475, "total_steps": 181800, "loss": 0.073, "lr": 2.469190563021306e-07, "epoch": 19.194169416941694, "percentage": 95.97, "elapsed_time": "6:53:34", "remaining_time": "0:17:21", "throughput": 1483.75, "total_tokens": 36819184} {"current_steps": 174480, "total_steps": 181800, "loss": 0.0018, "lr": 2.4658268144009123e-07, "epoch": 19.194719471947195, "percentage": 95.97, "elapsed_time": "6:53:35", "remaining_time": "0:17:21", "throughput": 1483.75, "total_tokens": 36820208} {"current_steps": 174485, "total_steps": 181800, "loss": 0.0089, "lr": 2.462465347184195e-07, "epoch": 19.195269526952696, "percentage": 95.98, "elapsed_time": "6:53:36", "remaining_time": "0:17:20", "throughput": 1483.75, "total_tokens": 36821328} {"current_steps": 174490, "total_steps": 181800, "loss": 0.0601, "lr": 2.4591061614021584e-07, "epoch": 19.195819581958197, "percentage": 95.98, "elapsed_time": "6:53:37", "remaining_time": "0:17:19", "throughput": 1483.75, "total_tokens": 36822352} {"current_steps": 174495, "total_steps": 181800, "loss": 0.0513, "lr": 2.4557492570857765e-07, "epoch": 19.196369636963695, "percentage": 95.98, "elapsed_time": "6:53:37", "remaining_time": "0:17:18", "throughput": 1483.75, "total_tokens": 36823408} {"current_steps": 174500, "total_steps": 181800, "loss": 0.0018, "lr": 2.452394634265942e-07, "epoch": 19.196919691969196, "percentage": 95.98, "elapsed_time": "6:53:38", "remaining_time": "0:17:18", "throughput": 1483.76, "total_tokens": 36824464} {"current_steps": 174505, "total_steps": 181800, "loss": 0.0033, "lr": 2.44904229297363e-07, "epoch": 19.197469746974697, "percentage": 95.99, "elapsed_time": "6:53:39", "remaining_time": "0:17:17", "throughput": 1483.76, "total_tokens": 36825584} {"current_steps": 174510, "total_steps": 181800, "loss": 0.0309, "lr": 2.445692233239705e-07, "epoch": 19.198019801980198, "percentage": 95.99, "elapsed_time": "6:53:39", "remaining_time": "0:17:16", "throughput": 1483.76, "total_tokens": 36826672} {"current_steps": 174515, "total_steps": 181800, "loss": 0.0012, "lr": 2.44234445509503e-07, "epoch": 19.1985698569857, "percentage": 95.99, "elapsed_time": "6:53:40", "remaining_time": "0:17:16", "throughput": 1483.76, "total_tokens": 36827632} {"current_steps": 174520, "total_steps": 181800, "loss": 0.0627, "lr": 2.4389989585704985e-07, "epoch": 19.1991199119912, "percentage": 96.0, "elapsed_time": "6:53:41", "remaining_time": "0:17:15", "throughput": 1483.76, "total_tokens": 36828720} {"current_steps": 174525, "total_steps": 181800, "loss": 0.0022, "lr": 2.4356557436968905e-07, "epoch": 19.199669966996698, "percentage": 96.0, "elapsed_time": "6:53:41", "remaining_time": "0:17:14", "throughput": 1483.76, "total_tokens": 36829808} {"current_steps": 174530, "total_steps": 181800, "loss": 0.0439, "lr": 2.432314810505071e-07, "epoch": 19.2002200220022, "percentage": 96.0, "elapsed_time": "6:53:42", "remaining_time": "0:17:13", "throughput": 1483.76, "total_tokens": 36830832} {"current_steps": 174535, "total_steps": 181800, "loss": 0.0244, "lr": 2.4289761590258197e-07, "epoch": 19.2007700770077, "percentage": 96.0, "elapsed_time": "6:53:43", "remaining_time": "0:17:13", "throughput": 1483.76, "total_tokens": 36831824} {"current_steps": 174540, "total_steps": 181800, "loss": 0.0206, "lr": 2.425639789289891e-07, "epoch": 19.2013201320132, "percentage": 96.01, "elapsed_time": "6:53:43", "remaining_time": "0:17:12", "throughput": 1483.76, "total_tokens": 36832848} {"current_steps": 174545, "total_steps": 181800, "loss": 0.0084, "lr": 2.422305701328037e-07, "epoch": 19.201870187018702, "percentage": 96.01, "elapsed_time": "6:53:44", "remaining_time": "0:17:11", "throughput": 1483.76, "total_tokens": 36833904} {"current_steps": 174550, "total_steps": 181800, "loss": 0.0365, "lr": 2.418973895170984e-07, "epoch": 19.202420242024203, "percentage": 96.01, "elapsed_time": "6:53:45", "remaining_time": "0:17:11", "throughput": 1483.76, "total_tokens": 36834928} {"current_steps": 174555, "total_steps": 181800, "loss": 0.1529, "lr": 2.4156443708494846e-07, "epoch": 19.202970297029704, "percentage": 96.01, "elapsed_time": "6:53:46", "remaining_time": "0:17:10", "throughput": 1483.76, "total_tokens": 36835920} {"current_steps": 174560, "total_steps": 181800, "loss": 0.0586, "lr": 2.412317128394154e-07, "epoch": 19.203520352035202, "percentage": 96.02, "elapsed_time": "6:53:46", "remaining_time": "0:17:09", "throughput": 1483.76, "total_tokens": 36836976} {"current_steps": 174565, "total_steps": 181800, "loss": 0.1234, "lr": 2.4089921678356885e-07, "epoch": 19.204070407040703, "percentage": 96.02, "elapsed_time": "6:53:47", "remaining_time": "0:17:08", "throughput": 1483.76, "total_tokens": 36837968} {"current_steps": 174570, "total_steps": 181800, "loss": 0.0832, "lr": 2.4056694892047593e-07, "epoch": 19.204620462046204, "percentage": 96.02, "elapsed_time": "6:53:48", "remaining_time": "0:17:08", "throughput": 1483.76, "total_tokens": 36838928} {"current_steps": 174575, "total_steps": 181800, "loss": 0.002, "lr": 2.4023490925319524e-07, "epoch": 19.205170517051705, "percentage": 96.03, "elapsed_time": "6:53:48", "remaining_time": "0:17:07", "throughput": 1483.76, "total_tokens": 36840016} {"current_steps": 174580, "total_steps": 181800, "loss": 0.1106, "lr": 2.3990309778478824e-07, "epoch": 19.205720572057206, "percentage": 96.03, "elapsed_time": "6:53:49", "remaining_time": "0:17:06", "throughput": 1483.76, "total_tokens": 36841072} {"current_steps": 174585, "total_steps": 181800, "loss": 0.0588, "lr": 2.395715145183136e-07, "epoch": 19.206270627062707, "percentage": 96.03, "elapsed_time": "6:53:50", "remaining_time": "0:17:06", "throughput": 1483.76, "total_tokens": 36842096} {"current_steps": 174590, "total_steps": 181800, "loss": 0.0007, "lr": 2.3924015945682997e-07, "epoch": 19.206820682068205, "percentage": 96.03, "elapsed_time": "6:53:50", "remaining_time": "0:17:05", "throughput": 1483.77, "total_tokens": 36843184} {"current_steps": 174595, "total_steps": 181800, "loss": 0.0086, "lr": 2.389090326033849e-07, "epoch": 19.207370737073706, "percentage": 96.04, "elapsed_time": "6:53:51", "remaining_time": "0:17:04", "throughput": 1483.77, "total_tokens": 36844304} {"current_steps": 174600, "total_steps": 181800, "loss": 0.0538, "lr": 2.3857813396103433e-07, "epoch": 19.207920792079207, "percentage": 96.04, "elapsed_time": "6:53:52", "remaining_time": "0:17:04", "throughput": 1483.77, "total_tokens": 36845360} {"current_steps": 174605, "total_steps": 181800, "loss": 0.0335, "lr": 2.3824746353282855e-07, "epoch": 19.20847084708471, "percentage": 96.04, "elapsed_time": "6:53:52", "remaining_time": "0:17:03", "throughput": 1483.77, "total_tokens": 36846416} {"current_steps": 174610, "total_steps": 181800, "loss": 0.01, "lr": 2.3791702132181238e-07, "epoch": 19.20902090209021, "percentage": 96.05, "elapsed_time": "6:53:53", "remaining_time": "0:17:02", "throughput": 1483.78, "total_tokens": 36847536} {"current_steps": 174615, "total_steps": 181800, "loss": 0.0881, "lr": 2.375868073310361e-07, "epoch": 19.20957095709571, "percentage": 96.05, "elapsed_time": "6:53:54", "remaining_time": "0:17:01", "throughput": 1483.78, "total_tokens": 36848624} {"current_steps": 174620, "total_steps": 181800, "loss": 0.0576, "lr": 2.3725682156353902e-07, "epoch": 19.21012101210121, "percentage": 96.05, "elapsed_time": "6:53:54", "remaining_time": "0:17:01", "throughput": 1483.78, "total_tokens": 36849712} {"current_steps": 174625, "total_steps": 181800, "loss": 0.0483, "lr": 2.369270640223603e-07, "epoch": 19.21067106710671, "percentage": 96.05, "elapsed_time": "6:53:55", "remaining_time": "0:17:00", "throughput": 1483.79, "total_tokens": 36850832} {"current_steps": 174630, "total_steps": 181800, "loss": 0.0089, "lr": 2.365975347105448e-07, "epoch": 19.21122112211221, "percentage": 96.06, "elapsed_time": "6:53:56", "remaining_time": "0:16:59", "throughput": 1483.79, "total_tokens": 36851952} {"current_steps": 174635, "total_steps": 181800, "loss": 0.0008, "lr": 2.3626823363112894e-07, "epoch": 19.21177117711771, "percentage": 96.06, "elapsed_time": "6:53:57", "remaining_time": "0:16:59", "throughput": 1483.79, "total_tokens": 36853072} {"current_steps": 174640, "total_steps": 181800, "loss": 0.0126, "lr": 2.3593916078714084e-07, "epoch": 19.212321232123212, "percentage": 96.06, "elapsed_time": "6:53:57", "remaining_time": "0:16:58", "throughput": 1483.78, "total_tokens": 36854192} {"current_steps": 174645, "total_steps": 181800, "loss": 0.0013, "lr": 2.3561031618162254e-07, "epoch": 19.212871287128714, "percentage": 96.06, "elapsed_time": "6:53:58", "remaining_time": "0:16:57", "throughput": 1483.79, "total_tokens": 36855280} {"current_steps": 174650, "total_steps": 181800, "loss": 0.0007, "lr": 2.352816998175994e-07, "epoch": 19.213421342134215, "percentage": 96.07, "elapsed_time": "6:53:59", "remaining_time": "0:16:56", "throughput": 1483.79, "total_tokens": 36856400} {"current_steps": 174655, "total_steps": 181800, "loss": 0.0033, "lr": 2.349533116981051e-07, "epoch": 19.213971397139716, "percentage": 96.07, "elapsed_time": "6:54:00", "remaining_time": "0:16:56", "throughput": 1483.79, "total_tokens": 36857392} {"current_steps": 174660, "total_steps": 181800, "loss": 0.0784, "lr": 2.346251518261594e-07, "epoch": 19.214521452145213, "percentage": 96.07, "elapsed_time": "6:54:00", "remaining_time": "0:16:55", "throughput": 1483.79, "total_tokens": 36858448} {"current_steps": 174665, "total_steps": 181800, "loss": 0.0077, "lr": 2.3429722020478774e-07, "epoch": 19.215071507150714, "percentage": 96.08, "elapsed_time": "6:54:01", "remaining_time": "0:16:54", "throughput": 1483.79, "total_tokens": 36859600} {"current_steps": 174670, "total_steps": 181800, "loss": 0.0861, "lr": 2.3396951683701817e-07, "epoch": 19.215621562156215, "percentage": 96.08, "elapsed_time": "6:54:02", "remaining_time": "0:16:54", "throughput": 1483.8, "total_tokens": 36860656} {"current_steps": 174675, "total_steps": 181800, "loss": 0.0645, "lr": 2.3364204172586778e-07, "epoch": 19.216171617161717, "percentage": 96.08, "elapsed_time": "6:54:02", "remaining_time": "0:16:53", "throughput": 1483.8, "total_tokens": 36861744} {"current_steps": 174680, "total_steps": 181800, "loss": 0.0016, "lr": 2.333147948743536e-07, "epoch": 19.216721672167218, "percentage": 96.08, "elapsed_time": "6:54:03", "remaining_time": "0:16:52", "throughput": 1483.8, "total_tokens": 36862768} {"current_steps": 174685, "total_steps": 181800, "loss": 0.0015, "lr": 2.329877762854954e-07, "epoch": 19.21727172717272, "percentage": 96.09, "elapsed_time": "6:54:04", "remaining_time": "0:16:51", "throughput": 1483.8, "total_tokens": 36863824} {"current_steps": 174690, "total_steps": 181800, "loss": 0.0758, "lr": 2.326609859623019e-07, "epoch": 19.217821782178216, "percentage": 96.09, "elapsed_time": "6:54:04", "remaining_time": "0:16:51", "throughput": 1483.8, "total_tokens": 36864944} {"current_steps": 174695, "total_steps": 181800, "loss": 0.022, "lr": 2.3233442390778736e-07, "epoch": 19.218371837183717, "percentage": 96.09, "elapsed_time": "6:54:05", "remaining_time": "0:16:50", "throughput": 1483.8, "total_tokens": 36866000} {"current_steps": 174700, "total_steps": 181800, "loss": 0.0008, "lr": 2.320080901249605e-07, "epoch": 19.21892189218922, "percentage": 96.09, "elapsed_time": "6:54:06", "remaining_time": "0:16:49", "throughput": 1483.8, "total_tokens": 36866992} {"current_steps": 174705, "total_steps": 181800, "loss": 0.0012, "lr": 2.3168198461683278e-07, "epoch": 19.21947194719472, "percentage": 96.1, "elapsed_time": "6:54:06", "remaining_time": "0:16:49", "throughput": 1483.8, "total_tokens": 36868016} {"current_steps": 174710, "total_steps": 181800, "loss": 0.0017, "lr": 2.3135610738640734e-07, "epoch": 19.22002200220022, "percentage": 96.1, "elapsed_time": "6:54:07", "remaining_time": "0:16:48", "throughput": 1483.8, "total_tokens": 36869040} {"current_steps": 174715, "total_steps": 181800, "loss": 0.0014, "lr": 2.3103045843668735e-07, "epoch": 19.22057205720572, "percentage": 96.1, "elapsed_time": "6:54:08", "remaining_time": "0:16:47", "throughput": 1483.8, "total_tokens": 36870064} {"current_steps": 174720, "total_steps": 181800, "loss": 0.0065, "lr": 2.307050377706732e-07, "epoch": 19.221122112211223, "percentage": 96.11, "elapsed_time": "6:54:09", "remaining_time": "0:16:46", "throughput": 1483.81, "total_tokens": 36871152} {"current_steps": 174725, "total_steps": 181800, "loss": 0.0303, "lr": 2.303798453913625e-07, "epoch": 19.22167216721672, "percentage": 96.11, "elapsed_time": "6:54:09", "remaining_time": "0:16:46", "throughput": 1483.81, "total_tokens": 36872272} {"current_steps": 174730, "total_steps": 181800, "loss": 0.0228, "lr": 2.3005488130176112e-07, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "6:54:10", "remaining_time": "0:16:45", "throughput": 1483.81, "total_tokens": 36873328} {"current_steps": 174735, "total_steps": 181800, "loss": 0.1331, "lr": 2.2973014550485562e-07, "epoch": 19.222772277227723, "percentage": 96.11, "elapsed_time": "6:54:11", "remaining_time": "0:16:44", "throughput": 1483.81, "total_tokens": 36874384} {"current_steps": 174740, "total_steps": 181800, "loss": 0.0039, "lr": 2.2940563800364078e-07, "epoch": 19.223322332233224, "percentage": 96.12, "elapsed_time": "6:54:11", "remaining_time": "0:16:44", "throughput": 1483.81, "total_tokens": 36875472} {"current_steps": 174745, "total_steps": 181800, "loss": 0.0018, "lr": 2.2908135880110871e-07, "epoch": 19.223872387238725, "percentage": 96.12, "elapsed_time": "6:54:12", "remaining_time": "0:16:43", "throughput": 1483.82, "total_tokens": 36876528} {"current_steps": 174750, "total_steps": 181800, "loss": 0.0031, "lr": 2.2875730790024585e-07, "epoch": 19.224422442244226, "percentage": 96.12, "elapsed_time": "6:54:13", "remaining_time": "0:16:42", "throughput": 1483.82, "total_tokens": 36877616} {"current_steps": 174755, "total_steps": 181800, "loss": 0.0431, "lr": 2.2843348530404153e-07, "epoch": 19.224972497249723, "percentage": 96.12, "elapsed_time": "6:54:13", "remaining_time": "0:16:41", "throughput": 1483.82, "total_tokens": 36878736} {"current_steps": 174760, "total_steps": 181800, "loss": 0.0009, "lr": 2.2810989101547942e-07, "epoch": 19.225522552255224, "percentage": 96.13, "elapsed_time": "6:54:14", "remaining_time": "0:16:41", "throughput": 1483.82, "total_tokens": 36879728} {"current_steps": 174765, "total_steps": 181800, "loss": 0.0201, "lr": 2.2778652503754328e-07, "epoch": 19.226072607260726, "percentage": 96.13, "elapsed_time": "6:54:15", "remaining_time": "0:16:40", "throughput": 1483.82, "total_tokens": 36880784} {"current_steps": 174770, "total_steps": 181800, "loss": 0.0022, "lr": 2.2746338737321127e-07, "epoch": 19.226622662266227, "percentage": 96.13, "elapsed_time": "6:54:15", "remaining_time": "0:16:39", "throughput": 1483.82, "total_tokens": 36881776} {"current_steps": 174775, "total_steps": 181800, "loss": 0.0046, "lr": 2.271404780254588e-07, "epoch": 19.227172717271728, "percentage": 96.14, "elapsed_time": "6:54:16", "remaining_time": "0:16:39", "throughput": 1483.82, "total_tokens": 36882832} {"current_steps": 174780, "total_steps": 181800, "loss": 0.0017, "lr": 2.2681779699726958e-07, "epoch": 19.22772277227723, "percentage": 96.14, "elapsed_time": "6:54:17", "remaining_time": "0:16:38", "throughput": 1483.82, "total_tokens": 36883920} {"current_steps": 174785, "total_steps": 181800, "loss": 0.145, "lr": 2.2649534429161067e-07, "epoch": 19.22827282728273, "percentage": 96.14, "elapsed_time": "6:54:18", "remaining_time": "0:16:37", "throughput": 1483.83, "total_tokens": 36885008} {"current_steps": 174790, "total_steps": 181800, "loss": 0.0241, "lr": 2.261731199114575e-07, "epoch": 19.228822882288227, "percentage": 96.14, "elapsed_time": "6:54:18", "remaining_time": "0:16:36", "throughput": 1483.83, "total_tokens": 36886064} {"current_steps": 174795, "total_steps": 181800, "loss": 0.0087, "lr": 2.2585112385977992e-07, "epoch": 19.22937293729373, "percentage": 96.15, "elapsed_time": "6:54:19", "remaining_time": "0:16:36", "throughput": 1483.83, "total_tokens": 36887120} {"current_steps": 174800, "total_steps": 181800, "loss": 0.0012, "lr": 2.2552935613954495e-07, "epoch": 19.22992299229923, "percentage": 96.15, "elapsed_time": "6:54:20", "remaining_time": "0:16:35", "throughput": 1483.83, "total_tokens": 36888208} {"current_steps": 174805, "total_steps": 181800, "loss": 0.0009, "lr": 2.2520781675371695e-07, "epoch": 19.23047304730473, "percentage": 96.15, "elapsed_time": "6:54:20", "remaining_time": "0:16:34", "throughput": 1483.83, "total_tokens": 36889264} {"current_steps": 174810, "total_steps": 181800, "loss": 0.005, "lr": 2.2488650570526014e-07, "epoch": 19.231023102310232, "percentage": 96.16, "elapsed_time": "6:54:21", "remaining_time": "0:16:34", "throughput": 1483.83, "total_tokens": 36890256} {"current_steps": 174815, "total_steps": 181800, "loss": 0.0313, "lr": 2.2456542299713613e-07, "epoch": 19.231573157315733, "percentage": 96.16, "elapsed_time": "6:54:22", "remaining_time": "0:16:33", "throughput": 1483.83, "total_tokens": 36891280} {"current_steps": 174820, "total_steps": 181800, "loss": 0.0008, "lr": 2.2424456863230636e-07, "epoch": 19.23212321232123, "percentage": 96.16, "elapsed_time": "6:54:22", "remaining_time": "0:16:32", "throughput": 1483.83, "total_tokens": 36892304} {"current_steps": 174825, "total_steps": 181800, "loss": 0.0017, "lr": 2.2392394261372128e-07, "epoch": 19.23267326732673, "percentage": 96.16, "elapsed_time": "6:54:23", "remaining_time": "0:16:31", "throughput": 1483.83, "total_tokens": 36893424} {"current_steps": 174830, "total_steps": 181800, "loss": 0.0084, "lr": 2.236035449443452e-07, "epoch": 19.233223322332233, "percentage": 96.17, "elapsed_time": "6:54:24", "remaining_time": "0:16:31", "throughput": 1483.84, "total_tokens": 36894512} {"current_steps": 174835, "total_steps": 181800, "loss": 0.0625, "lr": 2.2328337562712576e-07, "epoch": 19.233773377337734, "percentage": 96.17, "elapsed_time": "6:54:24", "remaining_time": "0:16:30", "throughput": 1483.84, "total_tokens": 36895568} {"current_steps": 174840, "total_steps": 181800, "loss": 0.0391, "lr": 2.2296343466501057e-07, "epoch": 19.234323432343235, "percentage": 96.17, "elapsed_time": "6:54:25", "remaining_time": "0:16:29", "throughput": 1483.84, "total_tokens": 36896624} {"current_steps": 174845, "total_steps": 181800, "loss": 0.002, "lr": 2.2264372206095563e-07, "epoch": 19.234873487348736, "percentage": 96.17, "elapsed_time": "6:54:26", "remaining_time": "0:16:29", "throughput": 1483.84, "total_tokens": 36897744} {"current_steps": 174850, "total_steps": 181800, "loss": 0.1348, "lr": 2.2232423781790302e-07, "epoch": 19.235423542354237, "percentage": 96.18, "elapsed_time": "6:54:27", "remaining_time": "0:16:28", "throughput": 1483.85, "total_tokens": 36898832} {"current_steps": 174855, "total_steps": 181800, "loss": 0.0512, "lr": 2.2200498193880038e-07, "epoch": 19.235973597359735, "percentage": 96.18, "elapsed_time": "6:54:27", "remaining_time": "0:16:27", "throughput": 1483.84, "total_tokens": 36899824} {"current_steps": 174860, "total_steps": 181800, "loss": 0.1132, "lr": 2.2168595442658703e-07, "epoch": 19.236523652365236, "percentage": 96.18, "elapsed_time": "6:54:28", "remaining_time": "0:16:26", "throughput": 1483.85, "total_tokens": 36900912} {"current_steps": 174865, "total_steps": 181800, "loss": 0.0285, "lr": 2.2136715528420227e-07, "epoch": 19.237073707370737, "percentage": 96.19, "elapsed_time": "6:54:29", "remaining_time": "0:16:26", "throughput": 1483.85, "total_tokens": 36901968} {"current_steps": 174870, "total_steps": 181800, "loss": 0.0009, "lr": 2.2104858451458822e-07, "epoch": 19.237623762376238, "percentage": 96.19, "elapsed_time": "6:54:29", "remaining_time": "0:16:25", "throughput": 1483.85, "total_tokens": 36903024} {"current_steps": 174875, "total_steps": 181800, "loss": 0.0159, "lr": 2.2073024212068139e-07, "epoch": 19.23817381738174, "percentage": 96.19, "elapsed_time": "6:54:30", "remaining_time": "0:16:24", "throughput": 1483.85, "total_tokens": 36904112} {"current_steps": 174880, "total_steps": 181800, "loss": 0.0072, "lr": 2.2041212810541e-07, "epoch": 19.23872387238724, "percentage": 96.19, "elapsed_time": "6:54:31", "remaining_time": "0:16:24", "throughput": 1483.85, "total_tokens": 36905104} {"current_steps": 174885, "total_steps": 181800, "loss": 0.0009, "lr": 2.200942424717134e-07, "epoch": 19.239273927392738, "percentage": 96.2, "elapsed_time": "6:54:31", "remaining_time": "0:16:23", "throughput": 1483.85, "total_tokens": 36906192} {"current_steps": 174890, "total_steps": 181800, "loss": 0.0043, "lr": 2.197765852225142e-07, "epoch": 19.23982398239824, "percentage": 96.2, "elapsed_time": "6:54:32", "remaining_time": "0:16:22", "throughput": 1483.85, "total_tokens": 36907248} {"current_steps": 174895, "total_steps": 181800, "loss": 0.1226, "lr": 2.1945915636074621e-07, "epoch": 19.24037403740374, "percentage": 96.2, "elapsed_time": "6:54:33", "remaining_time": "0:16:22", "throughput": 1483.86, "total_tokens": 36908368} {"current_steps": 174900, "total_steps": 181800, "loss": 0.0053, "lr": 2.1914195588932929e-07, "epoch": 19.24092409240924, "percentage": 96.2, "elapsed_time": "6:54:33", "remaining_time": "0:16:21", "throughput": 1483.86, "total_tokens": 36909424} {"current_steps": 174905, "total_steps": 181800, "loss": 0.0052, "lr": 2.1882498381119164e-07, "epoch": 19.241474147414742, "percentage": 96.21, "elapsed_time": "6:54:34", "remaining_time": "0:16:20", "throughput": 1483.86, "total_tokens": 36910480} {"current_steps": 174910, "total_steps": 181800, "loss": 0.0013, "lr": 2.185082401292532e-07, "epoch": 19.242024202420243, "percentage": 96.21, "elapsed_time": "6:54:35", "remaining_time": "0:16:19", "throughput": 1483.86, "total_tokens": 36911536} {"current_steps": 174915, "total_steps": 181800, "loss": 0.0884, "lr": 2.1819172484643103e-07, "epoch": 19.242574257425744, "percentage": 96.21, "elapsed_time": "6:54:36", "remaining_time": "0:16:19", "throughput": 1483.86, "total_tokens": 36912624} {"current_steps": 174920, "total_steps": 181800, "loss": 0.0055, "lr": 2.178754379656478e-07, "epoch": 19.24312431243124, "percentage": 96.22, "elapsed_time": "6:54:36", "remaining_time": "0:16:18", "throughput": 1483.87, "total_tokens": 36913744} {"current_steps": 174925, "total_steps": 181800, "loss": 0.0391, "lr": 2.175593794898123e-07, "epoch": 19.243674367436743, "percentage": 96.22, "elapsed_time": "6:54:37", "remaining_time": "0:16:17", "throughput": 1483.87, "total_tokens": 36914800} {"current_steps": 174930, "total_steps": 181800, "loss": 0.0031, "lr": 2.1724354942183889e-07, "epoch": 19.244224422442244, "percentage": 96.22, "elapsed_time": "6:54:38", "remaining_time": "0:16:17", "throughput": 1483.87, "total_tokens": 36915856} {"current_steps": 174935, "total_steps": 181800, "loss": 0.0662, "lr": 2.1692794776464463e-07, "epoch": 19.244774477447745, "percentage": 96.22, "elapsed_time": "6:54:38", "remaining_time": "0:16:16", "throughput": 1483.87, "total_tokens": 36916944} {"current_steps": 174940, "total_steps": 181800, "loss": 0.0014, "lr": 2.1661257452113003e-07, "epoch": 19.245324532453246, "percentage": 96.23, "elapsed_time": "6:54:39", "remaining_time": "0:16:15", "throughput": 1483.87, "total_tokens": 36917968} {"current_steps": 174945, "total_steps": 181800, "loss": 0.0027, "lr": 2.1629742969420662e-07, "epoch": 19.245874587458747, "percentage": 96.23, "elapsed_time": "6:54:40", "remaining_time": "0:16:14", "throughput": 1483.88, "total_tokens": 36919024} {"current_steps": 174950, "total_steps": 181800, "loss": 0.0373, "lr": 2.1598251328677488e-07, "epoch": 19.246424642464245, "percentage": 96.23, "elapsed_time": "6:54:40", "remaining_time": "0:16:14", "throughput": 1483.88, "total_tokens": 36920112} {"current_steps": 174955, "total_steps": 181800, "loss": 0.0392, "lr": 2.156678253017408e-07, "epoch": 19.246974697469746, "percentage": 96.23, "elapsed_time": "6:54:41", "remaining_time": "0:16:13", "throughput": 1483.88, "total_tokens": 36921168} {"current_steps": 174960, "total_steps": 181800, "loss": 0.1094, "lr": 2.1535336574200482e-07, "epoch": 19.247524752475247, "percentage": 96.24, "elapsed_time": "6:54:42", "remaining_time": "0:16:12", "throughput": 1483.88, "total_tokens": 36922320} {"current_steps": 174965, "total_steps": 181800, "loss": 0.1919, "lr": 2.1503913461046187e-07, "epoch": 19.248074807480748, "percentage": 96.24, "elapsed_time": "6:54:42", "remaining_time": "0:16:12", "throughput": 1483.89, "total_tokens": 36923344} {"current_steps": 174970, "total_steps": 181800, "loss": 0.0628, "lr": 2.147251319100152e-07, "epoch": 19.24862486248625, "percentage": 96.24, "elapsed_time": "6:54:43", "remaining_time": "0:16:11", "throughput": 1483.89, "total_tokens": 36924400} {"current_steps": 174975, "total_steps": 181800, "loss": 0.0026, "lr": 2.1441135764355136e-07, "epoch": 19.24917491749175, "percentage": 96.25, "elapsed_time": "6:54:44", "remaining_time": "0:16:10", "throughput": 1483.89, "total_tokens": 36925456} {"current_steps": 174980, "total_steps": 181800, "loss": 0.0654, "lr": 2.140978118139625e-07, "epoch": 19.24972497249725, "percentage": 96.25, "elapsed_time": "6:54:44", "remaining_time": "0:16:09", "throughput": 1483.89, "total_tokens": 36926544} {"current_steps": 174985, "total_steps": 181800, "loss": 0.0241, "lr": 2.1378449442414073e-07, "epoch": 19.25027502750275, "percentage": 96.25, "elapsed_time": "6:54:45", "remaining_time": "0:16:09", "throughput": 1483.89, "total_tokens": 36927600} {"current_steps": 174990, "total_steps": 181800, "loss": 0.0512, "lr": 2.1347140547697543e-07, "epoch": 19.25082508250825, "percentage": 96.25, "elapsed_time": "6:54:46", "remaining_time": "0:16:08", "throughput": 1483.89, "total_tokens": 36928624} {"current_steps": 174995, "total_steps": 181800, "loss": 0.0009, "lr": 2.1315854497535036e-07, "epoch": 19.25137513751375, "percentage": 96.26, "elapsed_time": "6:54:47", "remaining_time": "0:16:07", "throughput": 1483.89, "total_tokens": 36929712} {"current_steps": 175000, "total_steps": 181800, "loss": 0.0989, "lr": 2.128459129221494e-07, "epoch": 19.251925192519252, "percentage": 96.26, "elapsed_time": "6:54:47", "remaining_time": "0:16:07", "throughput": 1483.9, "total_tokens": 36930768} {"current_steps": 175005, "total_steps": 181800, "loss": 0.0046, "lr": 2.125335093202535e-07, "epoch": 19.252475247524753, "percentage": 96.26, "elapsed_time": "6:54:48", "remaining_time": "0:16:06", "throughput": 1483.9, "total_tokens": 36931888} {"current_steps": 175010, "total_steps": 181800, "loss": 0.052, "lr": 2.1222133417254098e-07, "epoch": 19.253025302530254, "percentage": 96.27, "elapsed_time": "6:54:49", "remaining_time": "0:16:05", "throughput": 1483.9, "total_tokens": 36932880} {"current_steps": 175015, "total_steps": 181800, "loss": 0.001, "lr": 2.1190938748189004e-07, "epoch": 19.253575357535752, "percentage": 96.27, "elapsed_time": "6:54:49", "remaining_time": "0:16:04", "throughput": 1483.9, "total_tokens": 36933904} {"current_steps": 175020, "total_steps": 181800, "loss": 0.0021, "lr": 2.115976692511762e-07, "epoch": 19.254125412541253, "percentage": 96.27, "elapsed_time": "6:54:50", "remaining_time": "0:16:04", "throughput": 1483.9, "total_tokens": 36935088} {"current_steps": 175025, "total_steps": 181800, "loss": 0.0016, "lr": 2.112861794832749e-07, "epoch": 19.254675467546754, "percentage": 96.27, "elapsed_time": "6:54:51", "remaining_time": "0:16:03", "throughput": 1483.91, "total_tokens": 36936144} {"current_steps": 175030, "total_steps": 181800, "loss": 0.0359, "lr": 2.1097491818105053e-07, "epoch": 19.255225522552255, "percentage": 96.28, "elapsed_time": "6:54:51", "remaining_time": "0:16:02", "throughput": 1483.91, "total_tokens": 36937168} {"current_steps": 175035, "total_steps": 181800, "loss": 0.0024, "lr": 2.106638853473758e-07, "epoch": 19.255775577557756, "percentage": 96.28, "elapsed_time": "6:54:52", "remaining_time": "0:16:02", "throughput": 1483.91, "total_tokens": 36938224} {"current_steps": 175040, "total_steps": 181800, "loss": 0.0022, "lr": 2.1035308098511785e-07, "epoch": 19.256325632563257, "percentage": 96.28, "elapsed_time": "6:54:53", "remaining_time": "0:16:01", "throughput": 1483.91, "total_tokens": 36939216} {"current_steps": 175045, "total_steps": 181800, "loss": 0.0311, "lr": 2.100425050971383e-07, "epoch": 19.25687568756876, "percentage": 96.28, "elapsed_time": "6:54:53", "remaining_time": "0:16:00", "throughput": 1483.91, "total_tokens": 36940336} {"current_steps": 175050, "total_steps": 181800, "loss": 0.0007, "lr": 2.0973215768630427e-07, "epoch": 19.257425742574256, "percentage": 96.29, "elapsed_time": "6:54:54", "remaining_time": "0:15:59", "throughput": 1483.91, "total_tokens": 36941360} {"current_steps": 175055, "total_steps": 181800, "loss": 0.0016, "lr": 2.0942203875547185e-07, "epoch": 19.257975797579757, "percentage": 96.29, "elapsed_time": "6:54:55", "remaining_time": "0:15:59", "throughput": 1483.91, "total_tokens": 36942384} {"current_steps": 175060, "total_steps": 181800, "loss": 0.0009, "lr": 2.091121483075026e-07, "epoch": 19.258525852585258, "percentage": 96.29, "elapsed_time": "6:54:56", "remaining_time": "0:15:58", "throughput": 1483.91, "total_tokens": 36943504} {"current_steps": 175065, "total_steps": 181800, "loss": 0.0016, "lr": 2.088024863452498e-07, "epoch": 19.25907590759076, "percentage": 96.3, "elapsed_time": "6:54:56", "remaining_time": "0:15:57", "throughput": 1483.91, "total_tokens": 36944496} {"current_steps": 175070, "total_steps": 181800, "loss": 0.0026, "lr": 2.084930528715695e-07, "epoch": 19.25962596259626, "percentage": 96.3, "elapsed_time": "6:54:57", "remaining_time": "0:15:57", "throughput": 1483.91, "total_tokens": 36945552} {"current_steps": 175075, "total_steps": 181800, "loss": 0.0085, "lr": 2.0818384788930945e-07, "epoch": 19.26017601760176, "percentage": 96.3, "elapsed_time": "6:54:58", "remaining_time": "0:15:56", "throughput": 1483.91, "total_tokens": 36946608} {"current_steps": 175080, "total_steps": 181800, "loss": 0.0034, "lr": 2.0787487140132568e-07, "epoch": 19.260726072607262, "percentage": 96.3, "elapsed_time": "6:54:58", "remaining_time": "0:15:55", "throughput": 1483.91, "total_tokens": 36947664} {"current_steps": 175085, "total_steps": 181800, "loss": 0.0853, "lr": 2.075661234104631e-07, "epoch": 19.26127612761276, "percentage": 96.31, "elapsed_time": "6:54:59", "remaining_time": "0:15:54", "throughput": 1483.92, "total_tokens": 36948720} {"current_steps": 175090, "total_steps": 181800, "loss": 0.1951, "lr": 2.0725760391956396e-07, "epoch": 19.26182618261826, "percentage": 96.31, "elapsed_time": "6:55:00", "remaining_time": "0:15:54", "throughput": 1483.92, "total_tokens": 36949744} {"current_steps": 175095, "total_steps": 181800, "loss": 0.0014, "lr": 2.0694931293147591e-07, "epoch": 19.262376237623762, "percentage": 96.31, "elapsed_time": "6:55:00", "remaining_time": "0:15:53", "throughput": 1483.92, "total_tokens": 36950832} {"current_steps": 175100, "total_steps": 181800, "loss": 0.0017, "lr": 2.0664125044904113e-07, "epoch": 19.262926292629263, "percentage": 96.31, "elapsed_time": "6:55:01", "remaining_time": "0:15:52", "throughput": 1483.92, "total_tokens": 36951888} {"current_steps": 175105, "total_steps": 181800, "loss": 0.0019, "lr": 2.0633341647509353e-07, "epoch": 19.263476347634764, "percentage": 96.32, "elapsed_time": "6:55:02", "remaining_time": "0:15:52", "throughput": 1483.92, "total_tokens": 36952944} {"current_steps": 175110, "total_steps": 181800, "loss": 0.0266, "lr": 2.0602581101247798e-07, "epoch": 19.264026402640265, "percentage": 96.32, "elapsed_time": "6:55:02", "remaining_time": "0:15:51", "throughput": 1483.92, "total_tokens": 36953968} {"current_steps": 175115, "total_steps": 181800, "loss": 0.0019, "lr": 2.057184340640228e-07, "epoch": 19.264576457645763, "percentage": 96.32, "elapsed_time": "6:55:03", "remaining_time": "0:15:50", "throughput": 1483.92, "total_tokens": 36955024} {"current_steps": 175120, "total_steps": 181800, "loss": 0.0033, "lr": 2.0541128563256184e-07, "epoch": 19.265126512651264, "percentage": 96.33, "elapsed_time": "6:55:04", "remaining_time": "0:15:49", "throughput": 1483.92, "total_tokens": 36956080} {"current_steps": 175125, "total_steps": 181800, "loss": 0.0388, "lr": 2.0510436572093172e-07, "epoch": 19.265676567656765, "percentage": 96.33, "elapsed_time": "6:55:04", "remaining_time": "0:15:49", "throughput": 1483.92, "total_tokens": 36957072} {"current_steps": 175130, "total_steps": 181800, "loss": 0.0039, "lr": 2.047976743319524e-07, "epoch": 19.266226622662266, "percentage": 96.33, "elapsed_time": "6:55:05", "remaining_time": "0:15:48", "throughput": 1483.92, "total_tokens": 36958128} {"current_steps": 175135, "total_steps": 181800, "loss": 0.1235, "lr": 2.0449121146845774e-07, "epoch": 19.266776677667767, "percentage": 96.33, "elapsed_time": "6:55:06", "remaining_time": "0:15:47", "throughput": 1483.92, "total_tokens": 36959120} {"current_steps": 175140, "total_steps": 181800, "loss": 0.0064, "lr": 2.0418497713326768e-07, "epoch": 19.26732673267327, "percentage": 96.34, "elapsed_time": "6:55:07", "remaining_time": "0:15:47", "throughput": 1483.92, "total_tokens": 36960144} {"current_steps": 175145, "total_steps": 181800, "loss": 0.0927, "lr": 2.0387897132920774e-07, "epoch": 19.26787678767877, "percentage": 96.34, "elapsed_time": "6:55:07", "remaining_time": "0:15:46", "throughput": 1483.92, "total_tokens": 36961136} {"current_steps": 175150, "total_steps": 181800, "loss": 0.0196, "lr": 2.0357319405909792e-07, "epoch": 19.268426842684267, "percentage": 96.34, "elapsed_time": "6:55:08", "remaining_time": "0:15:45", "throughput": 1483.92, "total_tokens": 36962160} {"current_steps": 175155, "total_steps": 181800, "loss": 0.0031, "lr": 2.0326764532575537e-07, "epoch": 19.268976897689768, "percentage": 96.34, "elapsed_time": "6:55:09", "remaining_time": "0:15:44", "throughput": 1483.92, "total_tokens": 36963216} {"current_steps": 175160, "total_steps": 181800, "loss": 0.0012, "lr": 2.0296232513199452e-07, "epoch": 19.26952695269527, "percentage": 96.35, "elapsed_time": "6:55:09", "remaining_time": "0:15:44", "throughput": 1483.92, "total_tokens": 36964240} {"current_steps": 175165, "total_steps": 181800, "loss": 0.0712, "lr": 2.026572334806326e-07, "epoch": 19.27007700770077, "percentage": 96.35, "elapsed_time": "6:55:10", "remaining_time": "0:15:43", "throughput": 1483.92, "total_tokens": 36965264} {"current_steps": 175170, "total_steps": 181800, "loss": 0.0016, "lr": 2.023523703744784e-07, "epoch": 19.27062706270627, "percentage": 96.35, "elapsed_time": "6:55:11", "remaining_time": "0:15:42", "throughput": 1483.93, "total_tokens": 36966352} {"current_steps": 175175, "total_steps": 181800, "loss": 0.0941, "lr": 2.0204773581634362e-07, "epoch": 19.271177117711773, "percentage": 96.36, "elapsed_time": "6:55:11", "remaining_time": "0:15:42", "throughput": 1483.93, "total_tokens": 36967440} {"current_steps": 175180, "total_steps": 181800, "loss": 0.042, "lr": 2.017433298090371e-07, "epoch": 19.27172717271727, "percentage": 96.36, "elapsed_time": "6:55:12", "remaining_time": "0:15:41", "throughput": 1483.93, "total_tokens": 36968464} {"current_steps": 175185, "total_steps": 181800, "loss": 0.1441, "lr": 2.0143915235536214e-07, "epoch": 19.27227722772277, "percentage": 96.36, "elapsed_time": "6:55:13", "remaining_time": "0:15:40", "throughput": 1483.93, "total_tokens": 36969488} {"current_steps": 175190, "total_steps": 181800, "loss": 0.0043, "lr": 2.0113520345812209e-07, "epoch": 19.272827282728272, "percentage": 96.36, "elapsed_time": "6:55:13", "remaining_time": "0:15:40", "throughput": 1483.93, "total_tokens": 36970608} {"current_steps": 175195, "total_steps": 181800, "loss": 0.0023, "lr": 2.0083148312012024e-07, "epoch": 19.273377337733773, "percentage": 96.37, "elapsed_time": "6:55:14", "remaining_time": "0:15:39", "throughput": 1483.93, "total_tokens": 36971600} {"current_steps": 175200, "total_steps": 181800, "loss": 0.0553, "lr": 2.0052799134415433e-07, "epoch": 19.273927392739274, "percentage": 96.37, "elapsed_time": "6:55:15", "remaining_time": "0:15:38", "throughput": 1483.94, "total_tokens": 36972752} {"current_steps": 175205, "total_steps": 181800, "loss": 0.0781, "lr": 2.0022472813302218e-07, "epoch": 19.274477447744776, "percentage": 96.37, "elapsed_time": "6:55:16", "remaining_time": "0:15:37", "throughput": 1483.94, "total_tokens": 36973808} {"current_steps": 175210, "total_steps": 181800, "loss": 0.0775, "lr": 1.999216934895215e-07, "epoch": 19.275027502750277, "percentage": 96.38, "elapsed_time": "6:55:16", "remaining_time": "0:15:37", "throughput": 1483.94, "total_tokens": 36974832} {"current_steps": 175215, "total_steps": 181800, "loss": 0.0092, "lr": 1.9961888741643898e-07, "epoch": 19.275577557755774, "percentage": 96.38, "elapsed_time": "6:55:17", "remaining_time": "0:15:36", "throughput": 1483.94, "total_tokens": 36975920} {"current_steps": 175220, "total_steps": 181800, "loss": 0.0074, "lr": 1.993163099165668e-07, "epoch": 19.276127612761275, "percentage": 96.38, "elapsed_time": "6:55:18", "remaining_time": "0:15:35", "throughput": 1483.94, "total_tokens": 36977008} {"current_steps": 175225, "total_steps": 181800, "loss": 0.0054, "lr": 1.9901396099269998e-07, "epoch": 19.276677667766776, "percentage": 96.38, "elapsed_time": "6:55:18", "remaining_time": "0:15:35", "throughput": 1483.94, "total_tokens": 36978064} {"current_steps": 175230, "total_steps": 181800, "loss": 0.0561, "lr": 1.987118406476196e-07, "epoch": 19.277227722772277, "percentage": 96.39, "elapsed_time": "6:55:19", "remaining_time": "0:15:34", "throughput": 1483.94, "total_tokens": 36979120} {"current_steps": 175235, "total_steps": 181800, "loss": 0.0062, "lr": 1.9840994888411236e-07, "epoch": 19.27777777777778, "percentage": 96.39, "elapsed_time": "6:55:20", "remaining_time": "0:15:33", "throughput": 1483.95, "total_tokens": 36980176} {"current_steps": 175240, "total_steps": 181800, "loss": 0.0658, "lr": 1.981082857049593e-07, "epoch": 19.27832783278328, "percentage": 96.39, "elapsed_time": "6:55:20", "remaining_time": "0:15:32", "throughput": 1483.95, "total_tokens": 36981232} {"current_steps": 175245, "total_steps": 181800, "loss": 0.0018, "lr": 1.9780685111293883e-07, "epoch": 19.278877887788777, "percentage": 96.39, "elapsed_time": "6:55:21", "remaining_time": "0:15:32", "throughput": 1483.95, "total_tokens": 36982256} {"current_steps": 175250, "total_steps": 181800, "loss": 0.0067, "lr": 1.9750564511083202e-07, "epoch": 19.27942794279428, "percentage": 96.4, "elapsed_time": "6:55:22", "remaining_time": "0:15:31", "throughput": 1483.95, "total_tokens": 36983344} {"current_steps": 175255, "total_steps": 181800, "loss": 0.0074, "lr": 1.9720466770141444e-07, "epoch": 19.27997799779978, "percentage": 96.4, "elapsed_time": "6:55:22", "remaining_time": "0:15:30", "throughput": 1483.95, "total_tokens": 36984432} {"current_steps": 175260, "total_steps": 181800, "loss": 0.1389, "lr": 1.9690391888745886e-07, "epoch": 19.28052805280528, "percentage": 96.4, "elapsed_time": "6:55:23", "remaining_time": "0:15:30", "throughput": 1483.95, "total_tokens": 36985488} {"current_steps": 175265, "total_steps": 181800, "loss": 0.0586, "lr": 1.9660339867174082e-07, "epoch": 19.28107810781078, "percentage": 96.41, "elapsed_time": "6:55:24", "remaining_time": "0:15:29", "throughput": 1483.96, "total_tokens": 36986640} {"current_steps": 175270, "total_steps": 181800, "loss": 0.0904, "lr": 1.963031070570276e-07, "epoch": 19.281628162816283, "percentage": 96.41, "elapsed_time": "6:55:25", "remaining_time": "0:15:28", "throughput": 1483.96, "total_tokens": 36987696} {"current_steps": 175275, "total_steps": 181800, "loss": 0.0809, "lr": 1.960030440460836e-07, "epoch": 19.282178217821784, "percentage": 96.41, "elapsed_time": "6:55:25", "remaining_time": "0:15:27", "throughput": 1483.96, "total_tokens": 36988784} {"current_steps": 175280, "total_steps": 181800, "loss": 0.0577, "lr": 1.9570320964167887e-07, "epoch": 19.28272827282728, "percentage": 96.41, "elapsed_time": "6:55:26", "remaining_time": "0:15:27", "throughput": 1483.97, "total_tokens": 36989904} {"current_steps": 175285, "total_steps": 181800, "loss": 0.0044, "lr": 1.9540360384657508e-07, "epoch": 19.283278327832782, "percentage": 96.42, "elapsed_time": "6:55:27", "remaining_time": "0:15:26", "throughput": 1483.97, "total_tokens": 36990992} {"current_steps": 175290, "total_steps": 181800, "loss": 0.0043, "lr": 1.9510422666353668e-07, "epoch": 19.283828382838283, "percentage": 96.42, "elapsed_time": "6:55:27", "remaining_time": "0:15:25", "throughput": 1483.97, "total_tokens": 36992080} {"current_steps": 175295, "total_steps": 181800, "loss": 0.0295, "lr": 1.94805078095317e-07, "epoch": 19.284378437843785, "percentage": 96.42, "elapsed_time": "6:55:28", "remaining_time": "0:15:25", "throughput": 1483.97, "total_tokens": 36993104} {"current_steps": 175300, "total_steps": 181800, "loss": 0.0023, "lr": 1.9450615814467775e-07, "epoch": 19.284928492849286, "percentage": 96.42, "elapsed_time": "6:55:29", "remaining_time": "0:15:24", "throughput": 1483.98, "total_tokens": 36994224} {"current_steps": 175305, "total_steps": 181800, "loss": 0.0262, "lr": 1.9420746681436951e-07, "epoch": 19.285478547854787, "percentage": 96.43, "elapsed_time": "6:55:29", "remaining_time": "0:15:23", "throughput": 1483.98, "total_tokens": 36995248} {"current_steps": 175310, "total_steps": 181800, "loss": 0.0008, "lr": 1.9390900410715118e-07, "epoch": 19.286028602860284, "percentage": 96.43, "elapsed_time": "6:55:30", "remaining_time": "0:15:22", "throughput": 1483.98, "total_tokens": 36996368} {"current_steps": 175315, "total_steps": 181800, "loss": 0.0938, "lr": 1.9361077002577054e-07, "epoch": 19.286578657865785, "percentage": 96.43, "elapsed_time": "6:55:31", "remaining_time": "0:15:22", "throughput": 1483.98, "total_tokens": 36997456} {"current_steps": 175320, "total_steps": 181800, "loss": 0.0193, "lr": 1.9331276457297543e-07, "epoch": 19.287128712871286, "percentage": 96.44, "elapsed_time": "6:55:31", "remaining_time": "0:15:21", "throughput": 1483.98, "total_tokens": 36998544} {"current_steps": 175325, "total_steps": 181800, "loss": 0.0728, "lr": 1.9301498775151361e-07, "epoch": 19.287678767876788, "percentage": 96.44, "elapsed_time": "6:55:32", "remaining_time": "0:15:20", "throughput": 1483.98, "total_tokens": 36999536} {"current_steps": 175330, "total_steps": 181800, "loss": 0.0031, "lr": 1.9271743956412735e-07, "epoch": 19.28822882288229, "percentage": 96.44, "elapsed_time": "6:55:33", "remaining_time": "0:15:20", "throughput": 1483.98, "total_tokens": 37000592} {"current_steps": 175335, "total_steps": 181800, "loss": 0.0101, "lr": 1.924201200135617e-07, "epoch": 19.28877887788779, "percentage": 96.44, "elapsed_time": "6:55:33", "remaining_time": "0:15:19", "throughput": 1483.98, "total_tokens": 37001616} {"current_steps": 175340, "total_steps": 181800, "loss": 0.0019, "lr": 1.9212302910255608e-07, "epoch": 19.28932893289329, "percentage": 96.45, "elapsed_time": "6:55:34", "remaining_time": "0:15:18", "throughput": 1483.99, "total_tokens": 37002704} {"current_steps": 175345, "total_steps": 181800, "loss": 0.032, "lr": 1.9182616683384724e-07, "epoch": 19.28987898789879, "percentage": 96.45, "elapsed_time": "6:55:35", "remaining_time": "0:15:17", "throughput": 1483.99, "total_tokens": 37003760} {"current_steps": 175350, "total_steps": 181800, "loss": 0.0086, "lr": 1.9152953321017465e-07, "epoch": 19.29042904290429, "percentage": 96.45, "elapsed_time": "6:55:36", "remaining_time": "0:15:17", "throughput": 1483.99, "total_tokens": 37004816} {"current_steps": 175355, "total_steps": 181800, "loss": 0.0655, "lr": 1.9123312823426942e-07, "epoch": 19.29097909790979, "percentage": 96.45, "elapsed_time": "6:55:36", "remaining_time": "0:15:16", "throughput": 1483.99, "total_tokens": 37005872} {"current_steps": 175360, "total_steps": 181800, "loss": 0.0179, "lr": 1.9093695190886274e-07, "epoch": 19.29152915291529, "percentage": 96.46, "elapsed_time": "6:55:37", "remaining_time": "0:15:15", "throughput": 1483.99, "total_tokens": 37006896} {"current_steps": 175365, "total_steps": 181800, "loss": 0.0015, "lr": 1.9064100423668852e-07, "epoch": 19.292079207920793, "percentage": 96.46, "elapsed_time": "6:55:38", "remaining_time": "0:15:15", "throughput": 1483.99, "total_tokens": 37007984} {"current_steps": 175370, "total_steps": 181800, "loss": 0.0563, "lr": 1.903452852204668e-07, "epoch": 19.292629262926294, "percentage": 96.46, "elapsed_time": "6:55:38", "remaining_time": "0:15:14", "throughput": 1483.99, "total_tokens": 37008976} {"current_steps": 175375, "total_steps": 181800, "loss": 0.0011, "lr": 1.900497948629315e-07, "epoch": 19.293179317931795, "percentage": 96.47, "elapsed_time": "6:55:39", "remaining_time": "0:15:13", "throughput": 1484.0, "total_tokens": 37010096} {"current_steps": 175380, "total_steps": 181800, "loss": 0.0035, "lr": 1.897545331668027e-07, "epoch": 19.293729372937293, "percentage": 96.47, "elapsed_time": "6:55:40", "remaining_time": "0:15:12", "throughput": 1484.0, "total_tokens": 37011184} {"current_steps": 175385, "total_steps": 181800, "loss": 0.0034, "lr": 1.894595001348004e-07, "epoch": 19.294279427942794, "percentage": 96.47, "elapsed_time": "6:55:40", "remaining_time": "0:15:12", "throughput": 1484.0, "total_tokens": 37012208} {"current_steps": 175390, "total_steps": 181800, "loss": 0.0053, "lr": 1.8916469576964192e-07, "epoch": 19.294829482948295, "percentage": 96.47, "elapsed_time": "6:55:41", "remaining_time": "0:15:11", "throughput": 1484.0, "total_tokens": 37013296} {"current_steps": 175395, "total_steps": 181800, "loss": 0.0208, "lr": 1.8887012007405004e-07, "epoch": 19.295379537953796, "percentage": 96.48, "elapsed_time": "6:55:42", "remaining_time": "0:15:10", "throughput": 1484.0, "total_tokens": 37014352} {"current_steps": 175400, "total_steps": 181800, "loss": 0.0238, "lr": 1.8857577305073648e-07, "epoch": 19.295929592959297, "percentage": 96.48, "elapsed_time": "6:55:42", "remaining_time": "0:15:10", "throughput": 1484.0, "total_tokens": 37015344} {"current_steps": 175405, "total_steps": 181800, "loss": 0.1117, "lr": 1.8828165470241576e-07, "epoch": 19.296479647964798, "percentage": 96.48, "elapsed_time": "6:55:43", "remaining_time": "0:15:09", "throughput": 1484.0, "total_tokens": 37016400} {"current_steps": 175410, "total_steps": 181800, "loss": 0.0102, "lr": 1.8798776503179404e-07, "epoch": 19.297029702970296, "percentage": 96.49, "elapsed_time": "6:55:44", "remaining_time": "0:15:08", "throughput": 1484.0, "total_tokens": 37017424} {"current_steps": 175415, "total_steps": 181800, "loss": 0.0014, "lr": 1.8769410404158582e-07, "epoch": 19.297579757975797, "percentage": 96.49, "elapsed_time": "6:55:45", "remaining_time": "0:15:07", "throughput": 1484.0, "total_tokens": 37018480} {"current_steps": 175420, "total_steps": 181800, "loss": 0.0831, "lr": 1.8740067173449173e-07, "epoch": 19.298129812981298, "percentage": 96.49, "elapsed_time": "6:55:45", "remaining_time": "0:15:07", "throughput": 1484.0, "total_tokens": 37019536} {"current_steps": 175425, "total_steps": 181800, "loss": 0.0019, "lr": 1.8710746811322066e-07, "epoch": 19.2986798679868, "percentage": 96.49, "elapsed_time": "6:55:46", "remaining_time": "0:15:06", "throughput": 1484.01, "total_tokens": 37020592} {"current_steps": 175430, "total_steps": 181800, "loss": 0.0188, "lr": 1.8681449318047605e-07, "epoch": 19.2992299229923, "percentage": 96.5, "elapsed_time": "6:55:47", "remaining_time": "0:15:05", "throughput": 1484.01, "total_tokens": 37021616} {"current_steps": 175435, "total_steps": 181800, "loss": 0.0165, "lr": 1.8652174693895298e-07, "epoch": 19.2997799779978, "percentage": 96.5, "elapsed_time": "6:55:47", "remaining_time": "0:15:05", "throughput": 1484.01, "total_tokens": 37022704} {"current_steps": 175440, "total_steps": 181800, "loss": 0.0342, "lr": 1.8622922939135202e-07, "epoch": 19.300330033003302, "percentage": 96.5, "elapsed_time": "6:55:48", "remaining_time": "0:15:04", "throughput": 1484.01, "total_tokens": 37023760} {"current_steps": 175445, "total_steps": 181800, "loss": 0.0912, "lr": 1.8593694054037102e-07, "epoch": 19.3008800880088, "percentage": 96.5, "elapsed_time": "6:55:49", "remaining_time": "0:15:03", "throughput": 1484.01, "total_tokens": 37024784} {"current_steps": 175450, "total_steps": 181800, "loss": 0.1334, "lr": 1.8564488038870231e-07, "epoch": 19.3014301430143, "percentage": 96.51, "elapsed_time": "6:55:49", "remaining_time": "0:15:03", "throughput": 1484.01, "total_tokens": 37025808} {"current_steps": 175455, "total_steps": 181800, "loss": 0.0038, "lr": 1.8535304893903816e-07, "epoch": 19.301980198019802, "percentage": 96.51, "elapsed_time": "6:55:50", "remaining_time": "0:15:02", "throughput": 1484.01, "total_tokens": 37026832} {"current_steps": 175460, "total_steps": 181800, "loss": 0.0453, "lr": 1.850614461940653e-07, "epoch": 19.302530253025303, "percentage": 96.51, "elapsed_time": "6:55:51", "remaining_time": "0:15:01", "throughput": 1484.01, "total_tokens": 37027952} {"current_steps": 175465, "total_steps": 181800, "loss": 0.0208, "lr": 1.8477007215647603e-07, "epoch": 19.303080308030804, "percentage": 96.52, "elapsed_time": "6:55:51", "remaining_time": "0:15:00", "throughput": 1484.02, "total_tokens": 37029040} {"current_steps": 175470, "total_steps": 181800, "loss": 0.0009, "lr": 1.844789268289543e-07, "epoch": 19.303630363036305, "percentage": 96.52, "elapsed_time": "6:55:52", "remaining_time": "0:15:00", "throughput": 1484.02, "total_tokens": 37030064} {"current_steps": 175475, "total_steps": 181800, "loss": 0.0048, "lr": 1.8418801021417852e-07, "epoch": 19.304180418041803, "percentage": 96.52, "elapsed_time": "6:55:53", "remaining_time": "0:14:59", "throughput": 1484.02, "total_tokens": 37031120} {"current_steps": 175480, "total_steps": 181800, "loss": 0.0101, "lr": 1.8389732231483825e-07, "epoch": 19.304730473047304, "percentage": 96.52, "elapsed_time": "6:55:53", "remaining_time": "0:14:58", "throughput": 1484.02, "total_tokens": 37032240} {"current_steps": 175485, "total_steps": 181800, "loss": 0.0327, "lr": 1.836068631336063e-07, "epoch": 19.305280528052805, "percentage": 96.53, "elapsed_time": "6:55:54", "remaining_time": "0:14:58", "throughput": 1484.02, "total_tokens": 37033264} {"current_steps": 175490, "total_steps": 181800, "loss": 0.0012, "lr": 1.8331663267316113e-07, "epoch": 19.305830583058306, "percentage": 96.53, "elapsed_time": "6:55:55", "remaining_time": "0:14:57", "throughput": 1484.02, "total_tokens": 37034288} {"current_steps": 175495, "total_steps": 181800, "loss": 0.0011, "lr": 1.830266309361811e-07, "epoch": 19.306380638063807, "percentage": 96.53, "elapsed_time": "6:55:56", "remaining_time": "0:14:56", "throughput": 1484.02, "total_tokens": 37035312} {"current_steps": 175500, "total_steps": 181800, "loss": 0.0063, "lr": 1.8273685792533356e-07, "epoch": 19.306930693069308, "percentage": 96.53, "elapsed_time": "6:55:56", "remaining_time": "0:14:55", "throughput": 1484.02, "total_tokens": 37036400} {"current_steps": 175505, "total_steps": 181800, "loss": 0.0039, "lr": 1.8244731364329414e-07, "epoch": 19.30748074807481, "percentage": 96.54, "elapsed_time": "6:55:57", "remaining_time": "0:14:55", "throughput": 1484.02, "total_tokens": 37037424} {"current_steps": 175510, "total_steps": 181800, "loss": 0.0064, "lr": 1.8215799809272737e-07, "epoch": 19.308030803080307, "percentage": 96.54, "elapsed_time": "6:55:58", "remaining_time": "0:14:54", "throughput": 1484.03, "total_tokens": 37038512} {"current_steps": 175515, "total_steps": 181800, "loss": 0.0055, "lr": 1.8186891127630333e-07, "epoch": 19.308580858085808, "percentage": 96.54, "elapsed_time": "6:55:58", "remaining_time": "0:14:53", "throughput": 1484.03, "total_tokens": 37039600} {"current_steps": 175520, "total_steps": 181800, "loss": 0.0031, "lr": 1.815800531966838e-07, "epoch": 19.30913091309131, "percentage": 96.55, "elapsed_time": "6:55:59", "remaining_time": "0:14:53", "throughput": 1484.03, "total_tokens": 37040656} {"current_steps": 175525, "total_steps": 181800, "loss": 0.0114, "lr": 1.8129142385653052e-07, "epoch": 19.30968096809681, "percentage": 96.55, "elapsed_time": "6:56:00", "remaining_time": "0:14:52", "throughput": 1484.03, "total_tokens": 37041744} {"current_steps": 175530, "total_steps": 181800, "loss": 0.0287, "lr": 1.8100302325850805e-07, "epoch": 19.31023102310231, "percentage": 96.55, "elapsed_time": "6:56:00", "remaining_time": "0:14:51", "throughput": 1484.03, "total_tokens": 37042800} {"current_steps": 175535, "total_steps": 181800, "loss": 0.0059, "lr": 1.80714851405267e-07, "epoch": 19.310781078107812, "percentage": 96.55, "elapsed_time": "6:56:01", "remaining_time": "0:14:50", "throughput": 1484.04, "total_tokens": 37043888} {"current_steps": 175540, "total_steps": 181800, "loss": 0.0846, "lr": 1.8042690829947195e-07, "epoch": 19.31133113311331, "percentage": 96.56, "elapsed_time": "6:56:02", "remaining_time": "0:14:50", "throughput": 1484.04, "total_tokens": 37044976} {"current_steps": 175545, "total_steps": 181800, "loss": 0.0042, "lr": 1.8013919394377076e-07, "epoch": 19.31188118811881, "percentage": 96.56, "elapsed_time": "6:56:02", "remaining_time": "0:14:49", "throughput": 1484.04, "total_tokens": 37046032} {"current_steps": 175550, "total_steps": 181800, "loss": 0.0369, "lr": 1.7985170834081688e-07, "epoch": 19.312431243124312, "percentage": 96.56, "elapsed_time": "6:56:03", "remaining_time": "0:14:48", "throughput": 1484.04, "total_tokens": 37047088} {"current_steps": 175555, "total_steps": 181800, "loss": 0.0009, "lr": 1.7956445149326096e-07, "epoch": 19.312981298129813, "percentage": 96.56, "elapsed_time": "6:56:04", "remaining_time": "0:14:48", "throughput": 1484.04, "total_tokens": 37048208} {"current_steps": 175560, "total_steps": 181800, "loss": 0.0499, "lr": 1.792774234037481e-07, "epoch": 19.313531353135314, "percentage": 96.57, "elapsed_time": "6:56:05", "remaining_time": "0:14:47", "throughput": 1484.04, "total_tokens": 37049232} {"current_steps": 175565, "total_steps": 181800, "loss": 0.0009, "lr": 1.7899062407492618e-07, "epoch": 19.314081408140815, "percentage": 96.57, "elapsed_time": "6:56:05", "remaining_time": "0:14:46", "throughput": 1484.04, "total_tokens": 37050256} {"current_steps": 175570, "total_steps": 181800, "loss": 0.0029, "lr": 1.7870405350943475e-07, "epoch": 19.314631463146316, "percentage": 96.57, "elapsed_time": "6:56:06", "remaining_time": "0:14:45", "throughput": 1484.05, "total_tokens": 37051312} {"current_steps": 175575, "total_steps": 181800, "loss": 0.009, "lr": 1.7841771170991895e-07, "epoch": 19.315181518151814, "percentage": 96.58, "elapsed_time": "6:56:07", "remaining_time": "0:14:45", "throughput": 1484.05, "total_tokens": 37052336} {"current_steps": 175580, "total_steps": 181800, "loss": 0.0139, "lr": 1.781315986790183e-07, "epoch": 19.315731573157315, "percentage": 96.58, "elapsed_time": "6:56:07", "remaining_time": "0:14:44", "throughput": 1484.05, "total_tokens": 37053392} {"current_steps": 175585, "total_steps": 181800, "loss": 0.0381, "lr": 1.7784571441936682e-07, "epoch": 19.316281628162816, "percentage": 96.58, "elapsed_time": "6:56:08", "remaining_time": "0:14:43", "throughput": 1484.05, "total_tokens": 37054416} {"current_steps": 175590, "total_steps": 181800, "loss": 0.0464, "lr": 1.7756005893360128e-07, "epoch": 19.316831683168317, "percentage": 96.58, "elapsed_time": "6:56:09", "remaining_time": "0:14:43", "throughput": 1484.05, "total_tokens": 37055408} {"current_steps": 175595, "total_steps": 181800, "loss": 0.0009, "lr": 1.7727463222435292e-07, "epoch": 19.317381738173818, "percentage": 96.59, "elapsed_time": "6:56:09", "remaining_time": "0:14:42", "throughput": 1484.05, "total_tokens": 37056400} {"current_steps": 175600, "total_steps": 181800, "loss": 0.0389, "lr": 1.7698943429425296e-07, "epoch": 19.31793179317932, "percentage": 96.59, "elapsed_time": "6:56:10", "remaining_time": "0:14:41", "throughput": 1484.05, "total_tokens": 37057424} {"current_steps": 175605, "total_steps": 181800, "loss": 0.0218, "lr": 1.7670446514593264e-07, "epoch": 19.318481848184817, "percentage": 96.59, "elapsed_time": "6:56:11", "remaining_time": "0:14:40", "throughput": 1484.05, "total_tokens": 37058544} {"current_steps": 175610, "total_steps": 181800, "loss": 0.0037, "lr": 1.7641972478201207e-07, "epoch": 19.319031903190318, "percentage": 96.6, "elapsed_time": "6:56:11", "remaining_time": "0:14:40", "throughput": 1484.05, "total_tokens": 37059632} {"current_steps": 175615, "total_steps": 181800, "loss": 0.0061, "lr": 1.761352132051225e-07, "epoch": 19.31958195819582, "percentage": 96.6, "elapsed_time": "6:56:12", "remaining_time": "0:14:39", "throughput": 1484.06, "total_tokens": 37060752} {"current_steps": 175620, "total_steps": 181800, "loss": 0.0014, "lr": 1.7585093041788126e-07, "epoch": 19.32013201320132, "percentage": 96.6, "elapsed_time": "6:56:13", "remaining_time": "0:14:38", "throughput": 1484.06, "total_tokens": 37061808} {"current_steps": 175625, "total_steps": 181800, "loss": 0.0032, "lr": 1.755668764229085e-07, "epoch": 19.32068206820682, "percentage": 96.6, "elapsed_time": "6:56:13", "remaining_time": "0:14:38", "throughput": 1484.06, "total_tokens": 37062800} {"current_steps": 175630, "total_steps": 181800, "loss": 0.004, "lr": 1.7528305122282707e-07, "epoch": 19.321232123212322, "percentage": 96.61, "elapsed_time": "6:56:14", "remaining_time": "0:14:37", "throughput": 1484.06, "total_tokens": 37063888} {"current_steps": 175635, "total_steps": 181800, "loss": 0.0094, "lr": 1.749994548202488e-07, "epoch": 19.321782178217823, "percentage": 96.61, "elapsed_time": "6:56:15", "remaining_time": "0:14:36", "throughput": 1484.06, "total_tokens": 37064880} {"current_steps": 175640, "total_steps": 181800, "loss": 0.0928, "lr": 1.747160872177883e-07, "epoch": 19.32233223322332, "percentage": 96.61, "elapsed_time": "6:56:16", "remaining_time": "0:14:35", "throughput": 1484.06, "total_tokens": 37065968} {"current_steps": 175645, "total_steps": 181800, "loss": 0.0627, "lr": 1.7443294841805735e-07, "epoch": 19.322882288228822, "percentage": 96.61, "elapsed_time": "6:56:16", "remaining_time": "0:14:35", "throughput": 1484.06, "total_tokens": 37067056} {"current_steps": 175650, "total_steps": 181800, "loss": 0.0211, "lr": 1.7415003842366496e-07, "epoch": 19.323432343234323, "percentage": 96.62, "elapsed_time": "6:56:17", "remaining_time": "0:14:34", "throughput": 1484.07, "total_tokens": 37068144} {"current_steps": 175655, "total_steps": 181800, "loss": 0.0093, "lr": 1.7386735723722013e-07, "epoch": 19.323982398239824, "percentage": 96.62, "elapsed_time": "6:56:18", "remaining_time": "0:14:33", "throughput": 1484.07, "total_tokens": 37069168} {"current_steps": 175660, "total_steps": 181800, "loss": 0.0445, "lr": 1.735849048613264e-07, "epoch": 19.324532453245325, "percentage": 96.62, "elapsed_time": "6:56:18", "remaining_time": "0:14:33", "throughput": 1484.07, "total_tokens": 37070192} {"current_steps": 175665, "total_steps": 181800, "loss": 0.0844, "lr": 1.7330268129858717e-07, "epoch": 19.325082508250826, "percentage": 96.63, "elapsed_time": "6:56:19", "remaining_time": "0:14:32", "throughput": 1484.07, "total_tokens": 37071248} {"current_steps": 175670, "total_steps": 181800, "loss": 0.0052, "lr": 1.7302068655160596e-07, "epoch": 19.325632563256324, "percentage": 96.63, "elapsed_time": "6:56:20", "remaining_time": "0:14:31", "throughput": 1484.07, "total_tokens": 37072368} {"current_steps": 175675, "total_steps": 181800, "loss": 0.0047, "lr": 1.727389206229779e-07, "epoch": 19.326182618261825, "percentage": 96.63, "elapsed_time": "6:56:20", "remaining_time": "0:14:30", "throughput": 1484.07, "total_tokens": 37073392} {"current_steps": 175680, "total_steps": 181800, "loss": 0.0796, "lr": 1.7245738351530372e-07, "epoch": 19.326732673267326, "percentage": 96.63, "elapsed_time": "6:56:21", "remaining_time": "0:14:30", "throughput": 1484.07, "total_tokens": 37074416} {"current_steps": 175685, "total_steps": 181800, "loss": 0.1108, "lr": 1.7217607523117573e-07, "epoch": 19.327282728272827, "percentage": 96.64, "elapsed_time": "6:56:22", "remaining_time": "0:14:29", "throughput": 1484.07, "total_tokens": 37075472} {"current_steps": 175690, "total_steps": 181800, "loss": 0.1082, "lr": 1.7189499577318634e-07, "epoch": 19.32783278327833, "percentage": 96.64, "elapsed_time": "6:56:22", "remaining_time": "0:14:28", "throughput": 1484.08, "total_tokens": 37076560} {"current_steps": 175695, "total_steps": 181800, "loss": 0.0183, "lr": 1.7161414514392793e-07, "epoch": 19.32838283828383, "percentage": 96.64, "elapsed_time": "6:56:23", "remaining_time": "0:14:28", "throughput": 1484.08, "total_tokens": 37077648} {"current_steps": 175700, "total_steps": 181800, "loss": 0.0061, "lr": 1.713335233459873e-07, "epoch": 19.32893289328933, "percentage": 96.64, "elapsed_time": "6:56:24", "remaining_time": "0:14:27", "throughput": 1484.08, "total_tokens": 37078672} {"current_steps": 175705, "total_steps": 181800, "loss": 0.002, "lr": 1.7105313038195403e-07, "epoch": 19.329482948294828, "percentage": 96.65, "elapsed_time": "6:56:25", "remaining_time": "0:14:26", "throughput": 1484.08, "total_tokens": 37079760} {"current_steps": 175710, "total_steps": 181800, "loss": 0.0135, "lr": 1.7077296625440664e-07, "epoch": 19.33003300330033, "percentage": 96.65, "elapsed_time": "6:56:25", "remaining_time": "0:14:25", "throughput": 1484.08, "total_tokens": 37080848} {"current_steps": 175715, "total_steps": 181800, "loss": 0.0937, "lr": 1.7049303096593193e-07, "epoch": 19.33058305830583, "percentage": 96.65, "elapsed_time": "6:56:26", "remaining_time": "0:14:25", "throughput": 1484.09, "total_tokens": 37081936} {"current_steps": 175720, "total_steps": 181800, "loss": 0.0144, "lr": 1.7021332451910843e-07, "epoch": 19.33113311331133, "percentage": 96.66, "elapsed_time": "6:56:27", "remaining_time": "0:14:24", "throughput": 1484.09, "total_tokens": 37082992} {"current_steps": 175725, "total_steps": 181800, "loss": 0.0083, "lr": 1.699338469165146e-07, "epoch": 19.331683168316832, "percentage": 96.66, "elapsed_time": "6:56:27", "remaining_time": "0:14:23", "throughput": 1484.09, "total_tokens": 37084080} {"current_steps": 175730, "total_steps": 181800, "loss": 0.002, "lr": 1.6965459816072616e-07, "epoch": 19.332233223322334, "percentage": 96.66, "elapsed_time": "6:56:28", "remaining_time": "0:14:23", "throughput": 1484.09, "total_tokens": 37085104} {"current_steps": 175735, "total_steps": 181800, "loss": 0.0114, "lr": 1.6937557825431884e-07, "epoch": 19.33278327832783, "percentage": 96.66, "elapsed_time": "6:56:29", "remaining_time": "0:14:22", "throughput": 1484.09, "total_tokens": 37086160} {"current_steps": 175740, "total_steps": 181800, "loss": 0.009, "lr": 1.6909678719985723e-07, "epoch": 19.333333333333332, "percentage": 96.67, "elapsed_time": "6:56:29", "remaining_time": "0:14:21", "throughput": 1484.09, "total_tokens": 37087248} {"current_steps": 175745, "total_steps": 181800, "loss": 0.0055, "lr": 1.6881822499991706e-07, "epoch": 19.333883388338833, "percentage": 96.67, "elapsed_time": "6:56:30", "remaining_time": "0:14:21", "throughput": 1484.09, "total_tokens": 37088304} {"current_steps": 175750, "total_steps": 181800, "loss": 0.0038, "lr": 1.6853989165706575e-07, "epoch": 19.334433443344334, "percentage": 96.67, "elapsed_time": "6:56:31", "remaining_time": "0:14:20", "throughput": 1484.1, "total_tokens": 37089392} {"current_steps": 175755, "total_steps": 181800, "loss": 0.0207, "lr": 1.682617871738651e-07, "epoch": 19.334983498349835, "percentage": 96.67, "elapsed_time": "6:56:31", "remaining_time": "0:14:19", "throughput": 1484.1, "total_tokens": 37090384} {"current_steps": 175760, "total_steps": 181800, "loss": 0.0079, "lr": 1.6798391155288252e-07, "epoch": 19.335533553355337, "percentage": 96.68, "elapsed_time": "6:56:32", "remaining_time": "0:14:18", "throughput": 1484.1, "total_tokens": 37091472} {"current_steps": 175765, "total_steps": 181800, "loss": 0.0009, "lr": 1.6770626479667428e-07, "epoch": 19.336083608360838, "percentage": 96.68, "elapsed_time": "6:56:33", "remaining_time": "0:14:18", "throughput": 1484.1, "total_tokens": 37092496} {"current_steps": 175770, "total_steps": 181800, "loss": 0.0343, "lr": 1.6742884690780225e-07, "epoch": 19.336633663366335, "percentage": 96.68, "elapsed_time": "6:56:33", "remaining_time": "0:14:17", "throughput": 1484.1, "total_tokens": 37093520} {"current_steps": 175775, "total_steps": 181800, "loss": 0.0011, "lr": 1.671516578888227e-07, "epoch": 19.337183718371836, "percentage": 96.69, "elapsed_time": "6:56:34", "remaining_time": "0:14:16", "throughput": 1484.1, "total_tokens": 37094576} {"current_steps": 175780, "total_steps": 181800, "loss": 0.0287, "lr": 1.6687469774229193e-07, "epoch": 19.337733773377337, "percentage": 96.69, "elapsed_time": "6:56:35", "remaining_time": "0:14:16", "throughput": 1484.1, "total_tokens": 37095632} {"current_steps": 175785, "total_steps": 181800, "loss": 0.0037, "lr": 1.6659796647076064e-07, "epoch": 19.33828382838284, "percentage": 96.69, "elapsed_time": "6:56:36", "remaining_time": "0:14:15", "throughput": 1484.1, "total_tokens": 37096656} {"current_steps": 175790, "total_steps": 181800, "loss": 0.0033, "lr": 1.6632146407677685e-07, "epoch": 19.33883388338834, "percentage": 96.69, "elapsed_time": "6:56:36", "remaining_time": "0:14:14", "throughput": 1484.1, "total_tokens": 37097744} {"current_steps": 175795, "total_steps": 181800, "loss": 0.0031, "lr": 1.6604519056289403e-07, "epoch": 19.33938393839384, "percentage": 96.7, "elapsed_time": "6:56:37", "remaining_time": "0:14:13", "throughput": 1484.11, "total_tokens": 37098832} {"current_steps": 175800, "total_steps": 181800, "loss": 0.1593, "lr": 1.657691459316546e-07, "epoch": 19.33993399339934, "percentage": 96.7, "elapsed_time": "6:56:38", "remaining_time": "0:14:13", "throughput": 1484.11, "total_tokens": 37099888} {"current_steps": 175805, "total_steps": 181800, "loss": 0.0243, "lr": 1.6549333018560654e-07, "epoch": 19.34048404840484, "percentage": 96.7, "elapsed_time": "6:56:38", "remaining_time": "0:14:12", "throughput": 1484.11, "total_tokens": 37100976} {"current_steps": 175810, "total_steps": 181800, "loss": 0.0028, "lr": 1.6521774332728947e-07, "epoch": 19.34103410341034, "percentage": 96.71, "elapsed_time": "6:56:39", "remaining_time": "0:14:11", "throughput": 1484.11, "total_tokens": 37102032} {"current_steps": 175815, "total_steps": 181800, "loss": 0.0027, "lr": 1.64942385359243e-07, "epoch": 19.34158415841584, "percentage": 96.71, "elapsed_time": "6:56:40", "remaining_time": "0:14:11", "throughput": 1484.11, "total_tokens": 37103120} {"current_steps": 175820, "total_steps": 181800, "loss": 0.0033, "lr": 1.6466725628400404e-07, "epoch": 19.342134213421343, "percentage": 96.71, "elapsed_time": "6:56:40", "remaining_time": "0:14:10", "throughput": 1484.12, "total_tokens": 37104208} {"current_steps": 175825, "total_steps": 181800, "loss": 0.004, "lr": 1.6439235610411218e-07, "epoch": 19.342684268426844, "percentage": 96.71, "elapsed_time": "6:56:41", "remaining_time": "0:14:09", "throughput": 1484.12, "total_tokens": 37105200} {"current_steps": 175830, "total_steps": 181800, "loss": 0.066, "lr": 1.6411768482209599e-07, "epoch": 19.343234323432345, "percentage": 96.72, "elapsed_time": "6:56:42", "remaining_time": "0:14:08", "throughput": 1484.12, "total_tokens": 37106256} {"current_steps": 175835, "total_steps": 181800, "loss": 0.0756, "lr": 1.638432424404923e-07, "epoch": 19.343784378437842, "percentage": 96.72, "elapsed_time": "6:56:42", "remaining_time": "0:14:08", "throughput": 1484.12, "total_tokens": 37107248} {"current_steps": 175840, "total_steps": 181800, "loss": 0.054, "lr": 1.635690289618269e-07, "epoch": 19.344334433443343, "percentage": 96.72, "elapsed_time": "6:56:43", "remaining_time": "0:14:07", "throughput": 1484.12, "total_tokens": 37108304} {"current_steps": 175845, "total_steps": 181800, "loss": 0.0029, "lr": 1.632950443886283e-07, "epoch": 19.344884488448844, "percentage": 96.72, "elapsed_time": "6:56:44", "remaining_time": "0:14:06", "throughput": 1484.12, "total_tokens": 37109360} {"current_steps": 175850, "total_steps": 181800, "loss": 0.0126, "lr": 1.6302128872342225e-07, "epoch": 19.345434543454346, "percentage": 96.73, "elapsed_time": "6:56:45", "remaining_time": "0:14:06", "throughput": 1484.12, "total_tokens": 37110416} {"current_steps": 175855, "total_steps": 181800, "loss": 0.0009, "lr": 1.6274776196872898e-07, "epoch": 19.345984598459847, "percentage": 96.73, "elapsed_time": "6:56:45", "remaining_time": "0:14:05", "throughput": 1484.12, "total_tokens": 37111376} {"current_steps": 175860, "total_steps": 181800, "loss": 0.0057, "lr": 1.6247446412707423e-07, "epoch": 19.346534653465348, "percentage": 96.73, "elapsed_time": "6:56:46", "remaining_time": "0:14:04", "throughput": 1484.12, "total_tokens": 37112400} {"current_steps": 175865, "total_steps": 181800, "loss": 0.0011, "lr": 1.6220139520096988e-07, "epoch": 19.34708470847085, "percentage": 96.74, "elapsed_time": "6:56:47", "remaining_time": "0:14:03", "throughput": 1484.12, "total_tokens": 37113488} {"current_steps": 175870, "total_steps": 181800, "loss": 0.0038, "lr": 1.619285551929417e-07, "epoch": 19.347634763476346, "percentage": 96.74, "elapsed_time": "6:56:47", "remaining_time": "0:14:03", "throughput": 1484.12, "total_tokens": 37114576} {"current_steps": 175875, "total_steps": 181800, "loss": 0.0263, "lr": 1.6165594410549878e-07, "epoch": 19.348184818481847, "percentage": 96.74, "elapsed_time": "6:56:48", "remaining_time": "0:14:02", "throughput": 1484.12, "total_tokens": 37115600} {"current_steps": 175880, "total_steps": 181800, "loss": 0.0091, "lr": 1.61383561941153e-07, "epoch": 19.34873487348735, "percentage": 96.74, "elapsed_time": "6:56:49", "remaining_time": "0:14:01", "throughput": 1484.12, "total_tokens": 37116560} {"current_steps": 175885, "total_steps": 181800, "loss": 0.0036, "lr": 1.6111140870241347e-07, "epoch": 19.34928492849285, "percentage": 96.75, "elapsed_time": "6:56:49", "remaining_time": "0:14:01", "throughput": 1484.12, "total_tokens": 37117584} {"current_steps": 175890, "total_steps": 181800, "loss": 0.0181, "lr": 1.6083948439179486e-07, "epoch": 19.34983498349835, "percentage": 96.75, "elapsed_time": "6:56:50", "remaining_time": "0:14:00", "throughput": 1484.12, "total_tokens": 37118608} {"current_steps": 175895, "total_steps": 181800, "loss": 0.035, "lr": 1.605677890118007e-07, "epoch": 19.350385038503852, "percentage": 96.75, "elapsed_time": "6:56:51", "remaining_time": "0:13:59", "throughput": 1484.12, "total_tokens": 37119664} {"current_steps": 175900, "total_steps": 181800, "loss": 0.0745, "lr": 1.6029632256493177e-07, "epoch": 19.35093509350935, "percentage": 96.75, "elapsed_time": "6:56:51", "remaining_time": "0:13:58", "throughput": 1484.12, "total_tokens": 37120720} {"current_steps": 175905, "total_steps": 181800, "loss": 0.0545, "lr": 1.6002508505369161e-07, "epoch": 19.35148514851485, "percentage": 96.76, "elapsed_time": "6:56:52", "remaining_time": "0:13:58", "throughput": 1484.12, "total_tokens": 37121776} {"current_steps": 175910, "total_steps": 181800, "loss": 0.2102, "lr": 1.5975407648058384e-07, "epoch": 19.35203520352035, "percentage": 96.76, "elapsed_time": "6:56:53", "remaining_time": "0:13:57", "throughput": 1484.12, "total_tokens": 37122832} {"current_steps": 175915, "total_steps": 181800, "loss": 0.0975, "lr": 1.594832968481008e-07, "epoch": 19.352585258525853, "percentage": 96.76, "elapsed_time": "6:56:53", "remaining_time": "0:13:56", "throughput": 1484.12, "total_tokens": 37123856} {"current_steps": 175920, "total_steps": 181800, "loss": 0.1104, "lr": 1.592127461587406e-07, "epoch": 19.353135313531354, "percentage": 96.77, "elapsed_time": "6:56:54", "remaining_time": "0:13:56", "throughput": 1484.13, "total_tokens": 37124912} {"current_steps": 175925, "total_steps": 181800, "loss": 0.0007, "lr": 1.589424244149984e-07, "epoch": 19.353685368536855, "percentage": 96.77, "elapsed_time": "6:56:55", "remaining_time": "0:13:55", "throughput": 1484.13, "total_tokens": 37126000} {"current_steps": 175930, "total_steps": 181800, "loss": 0.0377, "lr": 1.586723316193639e-07, "epoch": 19.354235423542356, "percentage": 96.77, "elapsed_time": "6:56:56", "remaining_time": "0:13:54", "throughput": 1484.13, "total_tokens": 37127088} {"current_steps": 175935, "total_steps": 181800, "loss": 0.1127, "lr": 1.5840246777432678e-07, "epoch": 19.354785478547853, "percentage": 96.77, "elapsed_time": "6:56:56", "remaining_time": "0:13:53", "throughput": 1484.14, "total_tokens": 37128208} {"current_steps": 175940, "total_steps": 181800, "loss": 0.1098, "lr": 1.5813283288237114e-07, "epoch": 19.355335533553355, "percentage": 96.78, "elapsed_time": "6:56:57", "remaining_time": "0:13:53", "throughput": 1484.14, "total_tokens": 37129264} {"current_steps": 175945, "total_steps": 181800, "loss": 0.077, "lr": 1.5786342694598667e-07, "epoch": 19.355885588558856, "percentage": 96.78, "elapsed_time": "6:56:58", "remaining_time": "0:13:52", "throughput": 1484.14, "total_tokens": 37130352} {"current_steps": 175950, "total_steps": 181800, "loss": 0.0051, "lr": 1.575942499676547e-07, "epoch": 19.356435643564357, "percentage": 96.78, "elapsed_time": "6:56:58", "remaining_time": "0:13:51", "throughput": 1484.14, "total_tokens": 37131376} {"current_steps": 175955, "total_steps": 181800, "loss": 0.0183, "lr": 1.5732530194985385e-07, "epoch": 19.356985698569858, "percentage": 96.78, "elapsed_time": "6:56:59", "remaining_time": "0:13:51", "throughput": 1484.14, "total_tokens": 37132432} {"current_steps": 175960, "total_steps": 181800, "loss": 0.0714, "lr": 1.570565828950682e-07, "epoch": 19.35753575357536, "percentage": 96.79, "elapsed_time": "6:57:00", "remaining_time": "0:13:50", "throughput": 1484.14, "total_tokens": 37133520} {"current_steps": 175965, "total_steps": 181800, "loss": 0.003, "lr": 1.5678809280577077e-07, "epoch": 19.358085808580856, "percentage": 96.79, "elapsed_time": "6:57:00", "remaining_time": "0:13:49", "throughput": 1484.15, "total_tokens": 37134608} {"current_steps": 175970, "total_steps": 181800, "loss": 0.0675, "lr": 1.565198316844374e-07, "epoch": 19.358635863586358, "percentage": 96.79, "elapsed_time": "6:57:01", "remaining_time": "0:13:48", "throughput": 1484.15, "total_tokens": 37135760} {"current_steps": 175975, "total_steps": 181800, "loss": 0.0244, "lr": 1.5625179953353552e-07, "epoch": 19.35918591859186, "percentage": 96.8, "elapsed_time": "6:57:02", "remaining_time": "0:13:48", "throughput": 1484.15, "total_tokens": 37136816} {"current_steps": 175980, "total_steps": 181800, "loss": 0.0093, "lr": 1.5598399635554374e-07, "epoch": 19.35973597359736, "percentage": 96.8, "elapsed_time": "6:57:02", "remaining_time": "0:13:47", "throughput": 1484.15, "total_tokens": 37137840} {"current_steps": 175985, "total_steps": 181800, "loss": 0.013, "lr": 1.5571642215292392e-07, "epoch": 19.36028602860286, "percentage": 96.8, "elapsed_time": "6:57:03", "remaining_time": "0:13:46", "throughput": 1484.15, "total_tokens": 37138896} {"current_steps": 175990, "total_steps": 181800, "loss": 0.0025, "lr": 1.554490769281436e-07, "epoch": 19.360836083608362, "percentage": 96.8, "elapsed_time": "6:57:04", "remaining_time": "0:13:46", "throughput": 1484.15, "total_tokens": 37139952} {"current_steps": 175995, "total_steps": 181800, "loss": 0.0114, "lr": 1.5518196068367018e-07, "epoch": 19.361386138613863, "percentage": 96.81, "elapsed_time": "6:57:04", "remaining_time": "0:13:45", "throughput": 1484.16, "total_tokens": 37141104} {"current_steps": 176000, "total_steps": 181800, "loss": 0.0011, "lr": 1.5491507342196286e-07, "epoch": 19.36193619361936, "percentage": 96.81, "elapsed_time": "6:57:05", "remaining_time": "0:13:44", "throughput": 1484.16, "total_tokens": 37142160} {"current_steps": 176005, "total_steps": 181800, "loss": 0.0032, "lr": 1.54648415145478e-07, "epoch": 19.36248624862486, "percentage": 96.81, "elapsed_time": "6:57:06", "remaining_time": "0:13:43", "throughput": 1484.16, "total_tokens": 37143216} {"current_steps": 176010, "total_steps": 181800, "loss": 0.0018, "lr": 1.543819858566803e-07, "epoch": 19.363036303630363, "percentage": 96.82, "elapsed_time": "6:57:07", "remaining_time": "0:13:43", "throughput": 1484.16, "total_tokens": 37144240} {"current_steps": 176015, "total_steps": 181800, "loss": 0.0028, "lr": 1.5411578555802053e-07, "epoch": 19.363586358635864, "percentage": 96.82, "elapsed_time": "6:57:07", "remaining_time": "0:13:42", "throughput": 1484.16, "total_tokens": 37145264} {"current_steps": 176020, "total_steps": 181800, "loss": 0.0252, "lr": 1.5384981425195512e-07, "epoch": 19.364136413641365, "percentage": 96.82, "elapsed_time": "6:57:08", "remaining_time": "0:13:41", "throughput": 1484.16, "total_tokens": 37146256} {"current_steps": 176025, "total_steps": 181800, "loss": 0.0128, "lr": 1.5358407194093206e-07, "epoch": 19.364686468646866, "percentage": 96.82, "elapsed_time": "6:57:09", "remaining_time": "0:13:41", "throughput": 1484.17, "total_tokens": 37147376} {"current_steps": 176030, "total_steps": 181800, "loss": 0.0026, "lr": 1.533185586273994e-07, "epoch": 19.365236523652364, "percentage": 96.83, "elapsed_time": "6:57:09", "remaining_time": "0:13:40", "throughput": 1484.17, "total_tokens": 37148496} {"current_steps": 176035, "total_steps": 181800, "loss": 0.0063, "lr": 1.5305327431381078e-07, "epoch": 19.365786578657865, "percentage": 96.83, "elapsed_time": "6:57:10", "remaining_time": "0:13:39", "throughput": 1484.17, "total_tokens": 37149520} {"current_steps": 176040, "total_steps": 181800, "loss": 0.1492, "lr": 1.5278821900260588e-07, "epoch": 19.366336633663366, "percentage": 96.83, "elapsed_time": "6:57:11", "remaining_time": "0:13:39", "throughput": 1484.17, "total_tokens": 37150608} {"current_steps": 176045, "total_steps": 181800, "loss": 0.0007, "lr": 1.5252339269622994e-07, "epoch": 19.366886688668867, "percentage": 96.83, "elapsed_time": "6:57:11", "remaining_time": "0:13:38", "throughput": 1484.17, "total_tokens": 37151632} {"current_steps": 176050, "total_steps": 181800, "loss": 0.0025, "lr": 1.5225879539712273e-07, "epoch": 19.367436743674368, "percentage": 96.84, "elapsed_time": "6:57:12", "remaining_time": "0:13:37", "throughput": 1484.17, "total_tokens": 37152656} {"current_steps": 176055, "total_steps": 181800, "loss": 0.0035, "lr": 1.5199442710772117e-07, "epoch": 19.36798679867987, "percentage": 96.84, "elapsed_time": "6:57:13", "remaining_time": "0:13:36", "throughput": 1484.17, "total_tokens": 37153680} {"current_steps": 176060, "total_steps": 181800, "loss": 0.0902, "lr": 1.5173028783046493e-07, "epoch": 19.36853685368537, "percentage": 96.84, "elapsed_time": "6:57:13", "remaining_time": "0:13:36", "throughput": 1484.17, "total_tokens": 37154736} {"current_steps": 176065, "total_steps": 181800, "loss": 0.003, "lr": 1.5146637756778827e-07, "epoch": 19.369086908690868, "percentage": 96.85, "elapsed_time": "6:57:14", "remaining_time": "0:13:35", "throughput": 1484.17, "total_tokens": 37155760} {"current_steps": 176070, "total_steps": 181800, "loss": 0.0035, "lr": 1.5120269632212246e-07, "epoch": 19.36963696369637, "percentage": 96.85, "elapsed_time": "6:57:15", "remaining_time": "0:13:34", "throughput": 1484.17, "total_tokens": 37156752} {"current_steps": 176075, "total_steps": 181800, "loss": 0.0007, "lr": 1.50939244095899e-07, "epoch": 19.37018701870187, "percentage": 96.85, "elapsed_time": "6:57:16", "remaining_time": "0:13:34", "throughput": 1484.17, "total_tokens": 37157840} {"current_steps": 176080, "total_steps": 181800, "loss": 0.0021, "lr": 1.5067602089154086e-07, "epoch": 19.37073707370737, "percentage": 96.85, "elapsed_time": "6:57:16", "remaining_time": "0:13:33", "throughput": 1484.17, "total_tokens": 37158864} {"current_steps": 176085, "total_steps": 181800, "loss": 0.0052, "lr": 1.5041302671148226e-07, "epoch": 19.371287128712872, "percentage": 96.86, "elapsed_time": "6:57:17", "remaining_time": "0:13:32", "throughput": 1484.17, "total_tokens": 37159920} {"current_steps": 176090, "total_steps": 181800, "loss": 0.0047, "lr": 1.501502615581407e-07, "epoch": 19.371837183718373, "percentage": 96.86, "elapsed_time": "6:57:18", "remaining_time": "0:13:31", "throughput": 1484.18, "total_tokens": 37160976} {"current_steps": 176095, "total_steps": 181800, "loss": 0.1323, "lr": 1.4988772543393925e-07, "epoch": 19.37238723872387, "percentage": 96.86, "elapsed_time": "6:57:18", "remaining_time": "0:13:31", "throughput": 1484.18, "total_tokens": 37162064} {"current_steps": 176100, "total_steps": 181800, "loss": 0.0158, "lr": 1.4962541834129816e-07, "epoch": 19.372937293729372, "percentage": 96.86, "elapsed_time": "6:57:19", "remaining_time": "0:13:30", "throughput": 1484.18, "total_tokens": 37163152} {"current_steps": 176105, "total_steps": 181800, "loss": 0.0028, "lr": 1.4936334028263777e-07, "epoch": 19.373487348734873, "percentage": 96.87, "elapsed_time": "6:57:20", "remaining_time": "0:13:29", "throughput": 1484.18, "total_tokens": 37164176} {"current_steps": 176110, "total_steps": 181800, "loss": 0.0015, "lr": 1.4910149126036997e-07, "epoch": 19.374037403740374, "percentage": 96.87, "elapsed_time": "6:57:20", "remaining_time": "0:13:29", "throughput": 1484.19, "total_tokens": 37165328} {"current_steps": 176115, "total_steps": 181800, "loss": 0.0016, "lr": 1.488398712769068e-07, "epoch": 19.374587458745875, "percentage": 96.87, "elapsed_time": "6:57:21", "remaining_time": "0:13:28", "throughput": 1484.19, "total_tokens": 37166352} {"current_steps": 176120, "total_steps": 181800, "loss": 0.0016, "lr": 1.4857848033466292e-07, "epoch": 19.375137513751376, "percentage": 96.88, "elapsed_time": "6:57:22", "remaining_time": "0:13:27", "throughput": 1484.19, "total_tokens": 37167440} {"current_steps": 176125, "total_steps": 181800, "loss": 0.0669, "lr": 1.4831731843604756e-07, "epoch": 19.375687568756877, "percentage": 96.88, "elapsed_time": "6:57:22", "remaining_time": "0:13:26", "throughput": 1484.19, "total_tokens": 37168464} {"current_steps": 176130, "total_steps": 181800, "loss": 0.1562, "lr": 1.4805638558346714e-07, "epoch": 19.376237623762375, "percentage": 96.88, "elapsed_time": "6:57:23", "remaining_time": "0:13:26", "throughput": 1484.19, "total_tokens": 37169488} {"current_steps": 176135, "total_steps": 181800, "loss": 0.0795, "lr": 1.4779568177932523e-07, "epoch": 19.376787678767876, "percentage": 96.88, "elapsed_time": "6:57:24", "remaining_time": "0:13:25", "throughput": 1484.19, "total_tokens": 37170448} {"current_steps": 176140, "total_steps": 181800, "loss": 0.0012, "lr": 1.4753520702602552e-07, "epoch": 19.377337733773377, "percentage": 96.89, "elapsed_time": "6:57:25", "remaining_time": "0:13:24", "throughput": 1484.19, "total_tokens": 37171536} {"current_steps": 176145, "total_steps": 181800, "loss": 0.0022, "lr": 1.472749613259661e-07, "epoch": 19.377887788778878, "percentage": 96.89, "elapsed_time": "6:57:25", "remaining_time": "0:13:24", "throughput": 1484.19, "total_tokens": 37172592} {"current_steps": 176150, "total_steps": 181800, "loss": 0.085, "lr": 1.4701494468154775e-07, "epoch": 19.37843784378438, "percentage": 96.89, "elapsed_time": "6:57:26", "remaining_time": "0:13:23", "throughput": 1484.19, "total_tokens": 37173712} {"current_steps": 176155, "total_steps": 181800, "loss": 0.0472, "lr": 1.4675515709516863e-07, "epoch": 19.37898789878988, "percentage": 96.89, "elapsed_time": "6:57:27", "remaining_time": "0:13:22", "throughput": 1484.19, "total_tokens": 37174704} {"current_steps": 176160, "total_steps": 181800, "loss": 0.0506, "lr": 1.4649559856922124e-07, "epoch": 19.379537953795378, "percentage": 96.9, "elapsed_time": "6:57:27", "remaining_time": "0:13:21", "throughput": 1484.19, "total_tokens": 37175760} {"current_steps": 176165, "total_steps": 181800, "loss": 0.0346, "lr": 1.462362691061009e-07, "epoch": 19.38008800880088, "percentage": 96.9, "elapsed_time": "6:57:28", "remaining_time": "0:13:21", "throughput": 1484.19, "total_tokens": 37176752} {"current_steps": 176170, "total_steps": 181800, "loss": 0.0016, "lr": 1.459771687081918e-07, "epoch": 19.38063806380638, "percentage": 96.9, "elapsed_time": "6:57:29", "remaining_time": "0:13:20", "throughput": 1484.2, "total_tokens": 37177872} {"current_steps": 176175, "total_steps": 181800, "loss": 0.0458, "lr": 1.4571829737788369e-07, "epoch": 19.38118811881188, "percentage": 96.91, "elapsed_time": "6:57:29", "remaining_time": "0:13:19", "throughput": 1484.2, "total_tokens": 37178928} {"current_steps": 176180, "total_steps": 181800, "loss": 0.0071, "lr": 1.4545965511756632e-07, "epoch": 19.381738173817382, "percentage": 96.91, "elapsed_time": "6:57:30", "remaining_time": "0:13:19", "throughput": 1484.2, "total_tokens": 37179984} {"current_steps": 176185, "total_steps": 181800, "loss": 0.0395, "lr": 1.4520124192962115e-07, "epoch": 19.382288228822883, "percentage": 96.91, "elapsed_time": "6:57:31", "remaining_time": "0:13:18", "throughput": 1484.2, "total_tokens": 37181040} {"current_steps": 176190, "total_steps": 181800, "loss": 0.032, "lr": 1.449430578164296e-07, "epoch": 19.382838283828384, "percentage": 96.91, "elapsed_time": "6:57:31", "remaining_time": "0:13:17", "throughput": 1484.2, "total_tokens": 37182000} {"current_steps": 176195, "total_steps": 181800, "loss": 0.0035, "lr": 1.446851027803703e-07, "epoch": 19.383388338833882, "percentage": 96.92, "elapsed_time": "6:57:32", "remaining_time": "0:13:16", "throughput": 1484.2, "total_tokens": 37183088} {"current_steps": 176200, "total_steps": 181800, "loss": 0.0015, "lr": 1.444273768238219e-07, "epoch": 19.383938393839383, "percentage": 96.92, "elapsed_time": "6:57:33", "remaining_time": "0:13:16", "throughput": 1484.2, "total_tokens": 37184144} {"current_steps": 176205, "total_steps": 181800, "loss": 0.0646, "lr": 1.4416987994915755e-07, "epoch": 19.384488448844884, "percentage": 96.92, "elapsed_time": "6:57:34", "remaining_time": "0:13:15", "throughput": 1484.2, "total_tokens": 37185200} {"current_steps": 176210, "total_steps": 181800, "loss": 0.0025, "lr": 1.4391261215875308e-07, "epoch": 19.385038503850385, "percentage": 96.93, "elapsed_time": "6:57:34", "remaining_time": "0:13:14", "throughput": 1484.2, "total_tokens": 37186224} {"current_steps": 176215, "total_steps": 181800, "loss": 0.0016, "lr": 1.436555734549816e-07, "epoch": 19.385588558855886, "percentage": 96.93, "elapsed_time": "6:57:35", "remaining_time": "0:13:14", "throughput": 1484.2, "total_tokens": 37187280} {"current_steps": 176220, "total_steps": 181800, "loss": 0.0082, "lr": 1.4339876384020789e-07, "epoch": 19.386138613861387, "percentage": 96.93, "elapsed_time": "6:57:36", "remaining_time": "0:13:13", "throughput": 1484.2, "total_tokens": 37188336} {"current_steps": 176225, "total_steps": 181800, "loss": 0.0877, "lr": 1.431421833168023e-07, "epoch": 19.38668866886689, "percentage": 96.93, "elapsed_time": "6:57:36", "remaining_time": "0:13:12", "throughput": 1484.21, "total_tokens": 37189392} {"current_steps": 176230, "total_steps": 181800, "loss": 0.0049, "lr": 1.428858318871268e-07, "epoch": 19.387238723872386, "percentage": 96.94, "elapsed_time": "6:57:37", "remaining_time": "0:13:11", "throughput": 1484.21, "total_tokens": 37190480} {"current_steps": 176235, "total_steps": 181800, "loss": 0.0045, "lr": 1.4262970955354061e-07, "epoch": 19.387788778877887, "percentage": 96.94, "elapsed_time": "6:57:38", "remaining_time": "0:13:11", "throughput": 1484.21, "total_tokens": 37191504} {"current_steps": 176240, "total_steps": 181800, "loss": 0.0043, "lr": 1.4237381631841405e-07, "epoch": 19.388338833883388, "percentage": 96.94, "elapsed_time": "6:57:38", "remaining_time": "0:13:10", "throughput": 1484.21, "total_tokens": 37192528} {"current_steps": 176245, "total_steps": 181800, "loss": 0.0029, "lr": 1.4211815218409808e-07, "epoch": 19.38888888888889, "percentage": 96.94, "elapsed_time": "6:57:39", "remaining_time": "0:13:09", "throughput": 1484.21, "total_tokens": 37193584} {"current_steps": 176250, "total_steps": 181800, "loss": 0.0008, "lr": 1.4186271715295185e-07, "epoch": 19.38943894389439, "percentage": 96.95, "elapsed_time": "6:57:40", "remaining_time": "0:13:09", "throughput": 1484.21, "total_tokens": 37194608} {"current_steps": 176255, "total_steps": 181800, "loss": 0.0059, "lr": 1.4160751122732906e-07, "epoch": 19.38998899889989, "percentage": 96.95, "elapsed_time": "6:57:40", "remaining_time": "0:13:08", "throughput": 1484.21, "total_tokens": 37195664} {"current_steps": 176260, "total_steps": 181800, "loss": 0.0092, "lr": 1.4135253440958062e-07, "epoch": 19.39053905390539, "percentage": 96.95, "elapsed_time": "6:57:41", "remaining_time": "0:13:07", "throughput": 1484.21, "total_tokens": 37196720} {"current_steps": 176265, "total_steps": 181800, "loss": 0.0018, "lr": 1.410977867020574e-07, "epoch": 19.39108910891089, "percentage": 96.96, "elapsed_time": "6:57:42", "remaining_time": "0:13:06", "throughput": 1484.22, "total_tokens": 37197840} {"current_steps": 176270, "total_steps": 181800, "loss": 0.0015, "lr": 1.408432681071048e-07, "epoch": 19.39163916391639, "percentage": 96.96, "elapsed_time": "6:57:42", "remaining_time": "0:13:06", "throughput": 1484.22, "total_tokens": 37198896} {"current_steps": 176275, "total_steps": 181800, "loss": 0.0067, "lr": 1.4058897862707643e-07, "epoch": 19.392189218921892, "percentage": 96.96, "elapsed_time": "6:57:43", "remaining_time": "0:13:05", "throughput": 1484.22, "total_tokens": 37199888} {"current_steps": 176280, "total_steps": 181800, "loss": 0.0145, "lr": 1.4033491826430934e-07, "epoch": 19.392739273927393, "percentage": 96.96, "elapsed_time": "6:57:44", "remaining_time": "0:13:04", "throughput": 1484.22, "total_tokens": 37200976} {"current_steps": 176285, "total_steps": 181800, "loss": 0.0096, "lr": 1.400810870211461e-07, "epoch": 19.393289328932894, "percentage": 96.97, "elapsed_time": "6:57:45", "remaining_time": "0:13:04", "throughput": 1484.22, "total_tokens": 37202064} {"current_steps": 176290, "total_steps": 181800, "loss": 0.032, "lr": 1.3982748489992648e-07, "epoch": 19.393839383938396, "percentage": 96.97, "elapsed_time": "6:57:45", "remaining_time": "0:13:03", "throughput": 1484.22, "total_tokens": 37203120} {"current_steps": 176295, "total_steps": 181800, "loss": 0.0188, "lr": 1.3957411190298475e-07, "epoch": 19.394389438943893, "percentage": 96.97, "elapsed_time": "6:57:46", "remaining_time": "0:13:02", "throughput": 1484.22, "total_tokens": 37204208} {"current_steps": 176300, "total_steps": 181800, "loss": 0.0032, "lr": 1.3932096803266347e-07, "epoch": 19.394939493949394, "percentage": 96.97, "elapsed_time": "6:57:47", "remaining_time": "0:13:02", "throughput": 1484.23, "total_tokens": 37205264} {"current_steps": 176305, "total_steps": 181800, "loss": 0.0923, "lr": 1.3906805329129137e-07, "epoch": 19.395489548954895, "percentage": 96.98, "elapsed_time": "6:57:47", "remaining_time": "0:13:01", "throughput": 1484.23, "total_tokens": 37206352} {"current_steps": 176310, "total_steps": 181800, "loss": 0.0432, "lr": 1.3881536768119708e-07, "epoch": 19.396039603960396, "percentage": 96.98, "elapsed_time": "6:57:48", "remaining_time": "0:13:00", "throughput": 1484.23, "total_tokens": 37207440} {"current_steps": 176315, "total_steps": 181800, "loss": 0.0008, "lr": 1.385629112047121e-07, "epoch": 19.396589658965897, "percentage": 96.98, "elapsed_time": "6:57:49", "remaining_time": "0:12:59", "throughput": 1484.23, "total_tokens": 37208432} {"current_steps": 176320, "total_steps": 181800, "loss": 0.0541, "lr": 1.3831068386416513e-07, "epoch": 19.3971397139714, "percentage": 96.99, "elapsed_time": "6:57:49", "remaining_time": "0:12:59", "throughput": 1484.23, "total_tokens": 37209520} {"current_steps": 176325, "total_steps": 181800, "loss": 0.0026, "lr": 1.3805868566187652e-07, "epoch": 19.397689768976896, "percentage": 96.99, "elapsed_time": "6:57:50", "remaining_time": "0:12:58", "throughput": 1484.23, "total_tokens": 37210576} {"current_steps": 176330, "total_steps": 181800, "loss": 0.0383, "lr": 1.3780691660017499e-07, "epoch": 19.398239823982397, "percentage": 96.99, "elapsed_time": "6:57:51", "remaining_time": "0:12:57", "throughput": 1484.24, "total_tokens": 37211664} {"current_steps": 176335, "total_steps": 181800, "loss": 0.0019, "lr": 1.3755537668137252e-07, "epoch": 19.3987898789879, "percentage": 96.99, "elapsed_time": "6:57:51", "remaining_time": "0:12:57", "throughput": 1484.24, "total_tokens": 37212720} {"current_steps": 176340, "total_steps": 181800, "loss": 0.0048, "lr": 1.373040659077951e-07, "epoch": 19.3993399339934, "percentage": 97.0, "elapsed_time": "6:57:52", "remaining_time": "0:12:56", "throughput": 1484.24, "total_tokens": 37213808} {"current_steps": 176345, "total_steps": 181800, "loss": 0.0034, "lr": 1.3705298428175473e-07, "epoch": 19.3998899889989, "percentage": 97.0, "elapsed_time": "6:57:53", "remaining_time": "0:12:55", "throughput": 1484.24, "total_tokens": 37214864} {"current_steps": 176350, "total_steps": 181800, "loss": 0.0247, "lr": 1.3680213180556622e-07, "epoch": 19.4004400440044, "percentage": 97.0, "elapsed_time": "6:57:54", "remaining_time": "0:12:54", "throughput": 1484.24, "total_tokens": 37215952} {"current_steps": 176355, "total_steps": 181800, "loss": 0.1118, "lr": 1.3655150848154162e-07, "epoch": 19.400990099009903, "percentage": 97.0, "elapsed_time": "6:57:54", "remaining_time": "0:12:54", "throughput": 1484.25, "total_tokens": 37217072} {"current_steps": 176360, "total_steps": 181800, "loss": 0.0022, "lr": 1.3630111431199023e-07, "epoch": 19.4015401540154, "percentage": 97.01, "elapsed_time": "6:57:55", "remaining_time": "0:12:53", "throughput": 1484.25, "total_tokens": 37218192} {"current_steps": 176365, "total_steps": 181800, "loss": 0.0111, "lr": 1.3605094929922403e-07, "epoch": 19.4020902090209, "percentage": 97.01, "elapsed_time": "6:57:56", "remaining_time": "0:12:52", "throughput": 1484.25, "total_tokens": 37219280} {"current_steps": 176370, "total_steps": 181800, "loss": 0.0075, "lr": 1.3580101344554397e-07, "epoch": 19.402640264026402, "percentage": 97.01, "elapsed_time": "6:57:56", "remaining_time": "0:12:52", "throughput": 1484.26, "total_tokens": 37220368} {"current_steps": 176375, "total_steps": 181800, "loss": 0.001, "lr": 1.355513067532538e-07, "epoch": 19.403190319031903, "percentage": 97.02, "elapsed_time": "6:57:57", "remaining_time": "0:12:51", "throughput": 1484.26, "total_tokens": 37221424} {"current_steps": 176380, "total_steps": 181800, "loss": 0.075, "lr": 1.3530182922465716e-07, "epoch": 19.403740374037405, "percentage": 97.02, "elapsed_time": "6:57:58", "remaining_time": "0:12:50", "throughput": 1484.26, "total_tokens": 37222544} {"current_steps": 176385, "total_steps": 181800, "loss": 0.0053, "lr": 1.350525808620523e-07, "epoch": 19.404290429042906, "percentage": 97.02, "elapsed_time": "6:57:58", "remaining_time": "0:12:49", "throughput": 1484.26, "total_tokens": 37223600} {"current_steps": 176390, "total_steps": 181800, "loss": 0.0028, "lr": 1.3480356166773456e-07, "epoch": 19.404840484048403, "percentage": 97.02, "elapsed_time": "6:57:59", "remaining_time": "0:12:49", "throughput": 1484.26, "total_tokens": 37224656} {"current_steps": 176395, "total_steps": 181800, "loss": 0.0014, "lr": 1.345547716440021e-07, "epoch": 19.405390539053904, "percentage": 97.03, "elapsed_time": "6:58:00", "remaining_time": "0:12:48", "throughput": 1484.26, "total_tokens": 37225712} {"current_steps": 176400, "total_steps": 181800, "loss": 0.0938, "lr": 1.343062107931503e-07, "epoch": 19.405940594059405, "percentage": 97.03, "elapsed_time": "6:58:00", "remaining_time": "0:12:47", "throughput": 1484.26, "total_tokens": 37226736} {"current_steps": 176405, "total_steps": 181800, "loss": 0.0028, "lr": 1.340578791174635e-07, "epoch": 19.406490649064907, "percentage": 97.03, "elapsed_time": "6:58:01", "remaining_time": "0:12:47", "throughput": 1484.26, "total_tokens": 37227728} {"current_steps": 176410, "total_steps": 181800, "loss": 0.0042, "lr": 1.3380977661923144e-07, "epoch": 19.407040704070408, "percentage": 97.04, "elapsed_time": "6:58:02", "remaining_time": "0:12:46", "throughput": 1484.26, "total_tokens": 37228784} {"current_steps": 176415, "total_steps": 181800, "loss": 0.0501, "lr": 1.3356190330074403e-07, "epoch": 19.40759075907591, "percentage": 97.04, "elapsed_time": "6:58:03", "remaining_time": "0:12:45", "throughput": 1484.26, "total_tokens": 37229840} {"current_steps": 176420, "total_steps": 181800, "loss": 0.0416, "lr": 1.3331425916428552e-07, "epoch": 19.40814081408141, "percentage": 97.04, "elapsed_time": "6:58:03", "remaining_time": "0:12:44", "throughput": 1484.26, "total_tokens": 37230832} {"current_steps": 176425, "total_steps": 181800, "loss": 0.005, "lr": 1.3306684421213744e-07, "epoch": 19.408690869086907, "percentage": 97.04, "elapsed_time": "6:58:04", "remaining_time": "0:12:44", "throughput": 1484.26, "total_tokens": 37231888} {"current_steps": 176430, "total_steps": 181800, "loss": 0.006, "lr": 1.328196584465785e-07, "epoch": 19.40924092409241, "percentage": 97.05, "elapsed_time": "6:58:05", "remaining_time": "0:12:43", "throughput": 1484.27, "total_tokens": 37232976} {"current_steps": 176435, "total_steps": 181800, "loss": 0.0021, "lr": 1.3257270186988746e-07, "epoch": 19.40979097909791, "percentage": 97.05, "elapsed_time": "6:58:05", "remaining_time": "0:12:42", "throughput": 1484.27, "total_tokens": 37234032} {"current_steps": 176440, "total_steps": 181800, "loss": 0.0439, "lr": 1.3232597448434302e-07, "epoch": 19.41034103410341, "percentage": 97.05, "elapsed_time": "6:58:06", "remaining_time": "0:12:42", "throughput": 1484.27, "total_tokens": 37235152} {"current_steps": 176445, "total_steps": 181800, "loss": 0.0011, "lr": 1.320794762922184e-07, "epoch": 19.41089108910891, "percentage": 97.05, "elapsed_time": "6:58:07", "remaining_time": "0:12:41", "throughput": 1484.27, "total_tokens": 37236176} {"current_steps": 176450, "total_steps": 181800, "loss": 0.0019, "lr": 1.318332072957812e-07, "epoch": 19.411441144114413, "percentage": 97.06, "elapsed_time": "6:58:07", "remaining_time": "0:12:40", "throughput": 1484.27, "total_tokens": 37237200} {"current_steps": 176455, "total_steps": 181800, "loss": 0.005, "lr": 1.3158716749730739e-07, "epoch": 19.41199119911991, "percentage": 97.06, "elapsed_time": "6:58:08", "remaining_time": "0:12:39", "throughput": 1484.27, "total_tokens": 37238256} {"current_steps": 176460, "total_steps": 181800, "loss": 0.0039, "lr": 1.313413568990618e-07, "epoch": 19.41254125412541, "percentage": 97.06, "elapsed_time": "6:58:09", "remaining_time": "0:12:39", "throughput": 1484.28, "total_tokens": 37239376} {"current_steps": 176465, "total_steps": 181800, "loss": 0.0052, "lr": 1.310957755033093e-07, "epoch": 19.413091309130913, "percentage": 97.07, "elapsed_time": "6:58:09", "remaining_time": "0:12:38", "throughput": 1484.28, "total_tokens": 37240464} {"current_steps": 176470, "total_steps": 181800, "loss": 0.0078, "lr": 1.3085042331231202e-07, "epoch": 19.413641364136414, "percentage": 97.07, "elapsed_time": "6:58:10", "remaining_time": "0:12:37", "throughput": 1484.28, "total_tokens": 37241552} {"current_steps": 176475, "total_steps": 181800, "loss": 0.0072, "lr": 1.3060530032833475e-07, "epoch": 19.414191419141915, "percentage": 97.07, "elapsed_time": "6:58:11", "remaining_time": "0:12:37", "throughput": 1484.29, "total_tokens": 37242640} {"current_steps": 176480, "total_steps": 181800, "loss": 0.0262, "lr": 1.3036040655363402e-07, "epoch": 19.414741474147416, "percentage": 97.07, "elapsed_time": "6:58:11", "remaining_time": "0:12:36", "throughput": 1484.29, "total_tokens": 37243696} {"current_steps": 176485, "total_steps": 181800, "loss": 0.0743, "lr": 1.301157419904664e-07, "epoch": 19.415291529152917, "percentage": 97.08, "elapsed_time": "6:58:12", "remaining_time": "0:12:35", "throughput": 1484.29, "total_tokens": 37244752} {"current_steps": 176490, "total_steps": 181800, "loss": 0.1078, "lr": 1.2987130664109116e-07, "epoch": 19.415841584158414, "percentage": 97.08, "elapsed_time": "6:58:13", "remaining_time": "0:12:34", "throughput": 1484.29, "total_tokens": 37245872} {"current_steps": 176495, "total_steps": 181800, "loss": 0.0709, "lr": 1.296271005077565e-07, "epoch": 19.416391639163916, "percentage": 97.08, "elapsed_time": "6:58:14", "remaining_time": "0:12:34", "throughput": 1484.29, "total_tokens": 37246864} {"current_steps": 176500, "total_steps": 181800, "loss": 0.0043, "lr": 1.293831235927162e-07, "epoch": 19.416941694169417, "percentage": 97.08, "elapsed_time": "6:58:14", "remaining_time": "0:12:33", "throughput": 1484.29, "total_tokens": 37247920} {"current_steps": 176505, "total_steps": 181800, "loss": 0.0372, "lr": 1.2913937589821567e-07, "epoch": 19.417491749174918, "percentage": 97.09, "elapsed_time": "6:58:15", "remaining_time": "0:12:32", "throughput": 1484.29, "total_tokens": 37248912} {"current_steps": 176510, "total_steps": 181800, "loss": 0.0024, "lr": 1.288958574265059e-07, "epoch": 19.41804180418042, "percentage": 97.09, "elapsed_time": "6:58:16", "remaining_time": "0:12:32", "throughput": 1484.29, "total_tokens": 37249904} {"current_steps": 176515, "total_steps": 181800, "loss": 0.007, "lr": 1.2865256817982674e-07, "epoch": 19.41859185918592, "percentage": 97.09, "elapsed_time": "6:58:16", "remaining_time": "0:12:31", "throughput": 1484.29, "total_tokens": 37251024} {"current_steps": 176520, "total_steps": 181800, "loss": 0.0014, "lr": 1.2840950816042363e-07, "epoch": 19.419141914191417, "percentage": 97.1, "elapsed_time": "6:58:17", "remaining_time": "0:12:30", "throughput": 1484.29, "total_tokens": 37252112} {"current_steps": 176525, "total_steps": 181800, "loss": 0.0056, "lr": 1.2816667737053367e-07, "epoch": 19.41969196919692, "percentage": 97.1, "elapsed_time": "6:58:18", "remaining_time": "0:12:29", "throughput": 1484.3, "total_tokens": 37253200} {"current_steps": 176530, "total_steps": 181800, "loss": 0.0026, "lr": 1.2792407581239953e-07, "epoch": 19.42024202420242, "percentage": 97.1, "elapsed_time": "6:58:18", "remaining_time": "0:12:29", "throughput": 1484.3, "total_tokens": 37254320} {"current_steps": 176535, "total_steps": 181800, "loss": 0.1069, "lr": 1.2768170348824993e-07, "epoch": 19.42079207920792, "percentage": 97.1, "elapsed_time": "6:58:19", "remaining_time": "0:12:28", "throughput": 1484.3, "total_tokens": 37255376} {"current_steps": 176540, "total_steps": 181800, "loss": 0.0224, "lr": 1.2743956040032757e-07, "epoch": 19.421342134213422, "percentage": 97.11, "elapsed_time": "6:58:20", "remaining_time": "0:12:27", "throughput": 1484.3, "total_tokens": 37256400} {"current_steps": 176545, "total_steps": 181800, "loss": 0.0022, "lr": 1.271976465508584e-07, "epoch": 19.421892189218923, "percentage": 97.11, "elapsed_time": "6:58:20", "remaining_time": "0:12:27", "throughput": 1484.3, "total_tokens": 37257488} {"current_steps": 176550, "total_steps": 181800, "loss": 0.0503, "lr": 1.2695596194207405e-07, "epoch": 19.422442244224424, "percentage": 97.11, "elapsed_time": "6:58:21", "remaining_time": "0:12:26", "throughput": 1484.31, "total_tokens": 37258608} {"current_steps": 176555, "total_steps": 181800, "loss": 0.005, "lr": 1.2671450657620042e-07, "epoch": 19.42299229922992, "percentage": 97.11, "elapsed_time": "6:58:22", "remaining_time": "0:12:25", "throughput": 1484.31, "total_tokens": 37259728} {"current_steps": 176560, "total_steps": 181800, "loss": 0.0922, "lr": 1.2647328045546357e-07, "epoch": 19.423542354235423, "percentage": 97.12, "elapsed_time": "6:58:23", "remaining_time": "0:12:25", "throughput": 1484.31, "total_tokens": 37260720} {"current_steps": 176565, "total_steps": 181800, "loss": 0.006, "lr": 1.2623228358208672e-07, "epoch": 19.424092409240924, "percentage": 97.12, "elapsed_time": "6:58:23", "remaining_time": "0:12:24", "throughput": 1484.31, "total_tokens": 37261744} {"current_steps": 176570, "total_steps": 181800, "loss": 0.0865, "lr": 1.2599151595829305e-07, "epoch": 19.424642464246425, "percentage": 97.12, "elapsed_time": "6:58:24", "remaining_time": "0:12:23", "throughput": 1484.31, "total_tokens": 37262736} {"current_steps": 176575, "total_steps": 181800, "loss": 0.0679, "lr": 1.2575097758629751e-07, "epoch": 19.425192519251926, "percentage": 97.13, "elapsed_time": "6:58:25", "remaining_time": "0:12:22", "throughput": 1484.31, "total_tokens": 37263792} {"current_steps": 176580, "total_steps": 181800, "loss": 0.0775, "lr": 1.2551066846832328e-07, "epoch": 19.425742574257427, "percentage": 97.13, "elapsed_time": "6:58:25", "remaining_time": "0:12:22", "throughput": 1484.31, "total_tokens": 37264784} {"current_steps": 176585, "total_steps": 181800, "loss": 0.0981, "lr": 1.2527058860657691e-07, "epoch": 19.426292629262925, "percentage": 97.13, "elapsed_time": "6:58:26", "remaining_time": "0:12:21", "throughput": 1484.31, "total_tokens": 37265872} {"current_steps": 176590, "total_steps": 181800, "loss": 0.0035, "lr": 1.2503073800327614e-07, "epoch": 19.426842684268426, "percentage": 97.13, "elapsed_time": "6:58:27", "remaining_time": "0:12:20", "throughput": 1484.31, "total_tokens": 37266992} {"current_steps": 176595, "total_steps": 181800, "loss": 0.0066, "lr": 1.2479111666063304e-07, "epoch": 19.427392739273927, "percentage": 97.14, "elapsed_time": "6:58:27", "remaining_time": "0:12:20", "throughput": 1484.31, "total_tokens": 37267984} {"current_steps": 176600, "total_steps": 181800, "loss": 0.0061, "lr": 1.245517245808514e-07, "epoch": 19.427942794279428, "percentage": 97.14, "elapsed_time": "6:58:28", "remaining_time": "0:12:19", "throughput": 1484.31, "total_tokens": 37269008} {"current_steps": 176605, "total_steps": 181800, "loss": 0.0376, "lr": 1.2431256176614337e-07, "epoch": 19.42849284928493, "percentage": 97.14, "elapsed_time": "6:58:29", "remaining_time": "0:12:18", "throughput": 1484.31, "total_tokens": 37270032} {"current_steps": 176610, "total_steps": 181800, "loss": 0.0447, "lr": 1.2407362821870717e-07, "epoch": 19.42904290429043, "percentage": 97.15, "elapsed_time": "6:58:29", "remaining_time": "0:12:17", "throughput": 1484.31, "total_tokens": 37271088} {"current_steps": 176615, "total_steps": 181800, "loss": 0.083, "lr": 1.2383492394074937e-07, "epoch": 19.42959295929593, "percentage": 97.15, "elapsed_time": "6:58:30", "remaining_time": "0:12:17", "throughput": 1484.32, "total_tokens": 37272176} {"current_steps": 176620, "total_steps": 181800, "loss": 0.0016, "lr": 1.235964489344682e-07, "epoch": 19.43014301430143, "percentage": 97.15, "elapsed_time": "6:58:31", "remaining_time": "0:12:16", "throughput": 1484.32, "total_tokens": 37273328} {"current_steps": 176625, "total_steps": 181800, "loss": 0.0557, "lr": 1.2335820320205916e-07, "epoch": 19.43069306930693, "percentage": 97.15, "elapsed_time": "6:58:32", "remaining_time": "0:12:15", "throughput": 1484.32, "total_tokens": 37274384} {"current_steps": 176630, "total_steps": 181800, "loss": 0.0039, "lr": 1.2312018674572322e-07, "epoch": 19.43124312431243, "percentage": 97.16, "elapsed_time": "6:58:32", "remaining_time": "0:12:15", "throughput": 1484.32, "total_tokens": 37275376} {"current_steps": 176635, "total_steps": 181800, "loss": 0.006, "lr": 1.2288239956765313e-07, "epoch": 19.431793179317932, "percentage": 97.16, "elapsed_time": "6:58:33", "remaining_time": "0:12:14", "throughput": 1484.32, "total_tokens": 37276432} {"current_steps": 176640, "total_steps": 181800, "loss": 0.0712, "lr": 1.22644841670036e-07, "epoch": 19.432343234323433, "percentage": 97.16, "elapsed_time": "6:58:34", "remaining_time": "0:12:13", "throughput": 1484.33, "total_tokens": 37277552} {"current_steps": 176645, "total_steps": 181800, "loss": 0.0055, "lr": 1.224075130550617e-07, "epoch": 19.432893289328934, "percentage": 97.16, "elapsed_time": "6:58:34", "remaining_time": "0:12:12", "throughput": 1484.33, "total_tokens": 37278704} {"current_steps": 176650, "total_steps": 181800, "loss": 0.0033, "lr": 1.22170413724923e-07, "epoch": 19.433443344334435, "percentage": 97.17, "elapsed_time": "6:58:35", "remaining_time": "0:12:12", "throughput": 1484.33, "total_tokens": 37279728} {"current_steps": 176655, "total_steps": 181800, "loss": 0.012, "lr": 1.219335436818042e-07, "epoch": 19.433993399339933, "percentage": 97.17, "elapsed_time": "6:58:36", "remaining_time": "0:12:11", "throughput": 1484.33, "total_tokens": 37280720} {"current_steps": 176660, "total_steps": 181800, "loss": 0.0017, "lr": 1.2169690292788417e-07, "epoch": 19.434543454345434, "percentage": 97.17, "elapsed_time": "6:58:36", "remaining_time": "0:12:10", "throughput": 1484.33, "total_tokens": 37281744} {"current_steps": 176665, "total_steps": 181800, "loss": 0.0037, "lr": 1.2146049146534443e-07, "epoch": 19.435093509350935, "percentage": 97.18, "elapsed_time": "6:58:37", "remaining_time": "0:12:10", "throughput": 1484.33, "total_tokens": 37282832} {"current_steps": 176670, "total_steps": 181800, "loss": 0.0291, "lr": 1.2122430929636662e-07, "epoch": 19.435643564356436, "percentage": 97.18, "elapsed_time": "6:58:38", "remaining_time": "0:12:09", "throughput": 1484.33, "total_tokens": 37283856} {"current_steps": 176675, "total_steps": 181800, "loss": 0.0721, "lr": 1.20988356423124e-07, "epoch": 19.436193619361937, "percentage": 97.18, "elapsed_time": "6:58:38", "remaining_time": "0:12:08", "throughput": 1484.33, "total_tokens": 37284880} {"current_steps": 176680, "total_steps": 181800, "loss": 0.0038, "lr": 1.2075263284779815e-07, "epoch": 19.436743674367438, "percentage": 97.18, "elapsed_time": "6:58:39", "remaining_time": "0:12:07", "throughput": 1484.33, "total_tokens": 37285904} {"current_steps": 176685, "total_steps": 181800, "loss": 0.0043, "lr": 1.2051713857255398e-07, "epoch": 19.437293729372936, "percentage": 97.19, "elapsed_time": "6:58:40", "remaining_time": "0:12:07", "throughput": 1484.34, "total_tokens": 37287024} {"current_steps": 176690, "total_steps": 181800, "loss": 0.0485, "lr": 1.2028187359956754e-07, "epoch": 19.437843784378437, "percentage": 97.19, "elapsed_time": "6:58:41", "remaining_time": "0:12:06", "throughput": 1484.34, "total_tokens": 37288080} {"current_steps": 176695, "total_steps": 181800, "loss": 0.0608, "lr": 1.200468379310038e-07, "epoch": 19.438393839383938, "percentage": 97.19, "elapsed_time": "6:58:41", "remaining_time": "0:12:05", "throughput": 1484.34, "total_tokens": 37289168} {"current_steps": 176700, "total_steps": 181800, "loss": 0.0008, "lr": 1.1981203156902765e-07, "epoch": 19.43894389438944, "percentage": 97.19, "elapsed_time": "6:58:42", "remaining_time": "0:12:05", "throughput": 1484.34, "total_tokens": 37290192} {"current_steps": 176705, "total_steps": 181800, "loss": 0.0952, "lr": 1.1957745451580682e-07, "epoch": 19.43949394939494, "percentage": 97.2, "elapsed_time": "6:58:43", "remaining_time": "0:12:04", "throughput": 1484.34, "total_tokens": 37291184} {"current_steps": 176710, "total_steps": 181800, "loss": 0.0074, "lr": 1.193431067735007e-07, "epoch": 19.44004400440044, "percentage": 97.2, "elapsed_time": "6:58:43", "remaining_time": "0:12:03", "throughput": 1484.34, "total_tokens": 37292240} {"current_steps": 176715, "total_steps": 181800, "loss": 0.0275, "lr": 1.1910898834427143e-07, "epoch": 19.440594059405942, "percentage": 97.2, "elapsed_time": "6:58:44", "remaining_time": "0:12:02", "throughput": 1484.34, "total_tokens": 37293328} {"current_steps": 176720, "total_steps": 181800, "loss": 0.0159, "lr": 1.1887509923027562e-07, "epoch": 19.44114411441144, "percentage": 97.21, "elapsed_time": "6:58:45", "remaining_time": "0:12:02", "throughput": 1484.34, "total_tokens": 37294352} {"current_steps": 176725, "total_steps": 181800, "loss": 0.0368, "lr": 1.186414394336699e-07, "epoch": 19.44169416941694, "percentage": 97.21, "elapsed_time": "6:58:45", "remaining_time": "0:12:01", "throughput": 1484.35, "total_tokens": 37295440} {"current_steps": 176730, "total_steps": 181800, "loss": 0.002, "lr": 1.1840800895660531e-07, "epoch": 19.442244224422442, "percentage": 97.21, "elapsed_time": "6:58:46", "remaining_time": "0:12:00", "throughput": 1484.35, "total_tokens": 37296560} {"current_steps": 176735, "total_steps": 181800, "loss": 0.0129, "lr": 1.1817480780123569e-07, "epoch": 19.442794279427943, "percentage": 97.21, "elapsed_time": "6:58:47", "remaining_time": "0:12:00", "throughput": 1484.35, "total_tokens": 37297680} {"current_steps": 176740, "total_steps": 181800, "loss": 0.0283, "lr": 1.1794183596970654e-07, "epoch": 19.443344334433444, "percentage": 97.22, "elapsed_time": "6:58:47", "remaining_time": "0:11:59", "throughput": 1484.35, "total_tokens": 37298704} {"current_steps": 176745, "total_steps": 181800, "loss": 0.0353, "lr": 1.1770909346417169e-07, "epoch": 19.443894389438945, "percentage": 97.22, "elapsed_time": "6:58:48", "remaining_time": "0:11:58", "throughput": 1484.35, "total_tokens": 37299728} {"current_steps": 176750, "total_steps": 181800, "loss": 0.0608, "lr": 1.1747658028677112e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "6:58:49", "remaining_time": "0:11:57", "throughput": 1484.35, "total_tokens": 37300752} {"current_steps": 176755, "total_steps": 181800, "loss": 0.0283, "lr": 1.1724429643964752e-07, "epoch": 19.444994499449944, "percentage": 97.22, "elapsed_time": "6:58:50", "remaining_time": "0:11:57", "throughput": 1484.35, "total_tokens": 37301840} {"current_steps": 176760, "total_steps": 181800, "loss": 0.0126, "lr": 1.1701224192494365e-07, "epoch": 19.445544554455445, "percentage": 97.23, "elapsed_time": "6:58:50", "remaining_time": "0:11:56", "throughput": 1484.36, "total_tokens": 37302928} {"current_steps": 176765, "total_steps": 181800, "loss": 0.0035, "lr": 1.1678041674479945e-07, "epoch": 19.446094609460946, "percentage": 97.23, "elapsed_time": "6:58:51", "remaining_time": "0:11:55", "throughput": 1484.36, "total_tokens": 37303952} {"current_steps": 176770, "total_steps": 181800, "loss": 0.0245, "lr": 1.1654882090134933e-07, "epoch": 19.446644664466447, "percentage": 97.23, "elapsed_time": "6:58:52", "remaining_time": "0:11:55", "throughput": 1484.36, "total_tokens": 37305040} {"current_steps": 176775, "total_steps": 181800, "loss": 0.0383, "lr": 1.1631745439673047e-07, "epoch": 19.44719471947195, "percentage": 97.24, "elapsed_time": "6:58:52", "remaining_time": "0:11:54", "throughput": 1484.36, "total_tokens": 37306064} {"current_steps": 176780, "total_steps": 181800, "loss": 0.0018, "lr": 1.1608631723307173e-07, "epoch": 19.44774477447745, "percentage": 97.24, "elapsed_time": "6:58:53", "remaining_time": "0:11:53", "throughput": 1484.36, "total_tokens": 37307120} {"current_steps": 176785, "total_steps": 181800, "loss": 0.0082, "lr": 1.1585540941250472e-07, "epoch": 19.448294829482947, "percentage": 97.24, "elapsed_time": "6:58:54", "remaining_time": "0:11:53", "throughput": 1484.36, "total_tokens": 37308112} {"current_steps": 176790, "total_steps": 181800, "loss": 0.0053, "lr": 1.1562473093715554e-07, "epoch": 19.448844884488448, "percentage": 97.24, "elapsed_time": "6:58:54", "remaining_time": "0:11:52", "throughput": 1484.36, "total_tokens": 37309168} {"current_steps": 176795, "total_steps": 181800, "loss": 0.0681, "lr": 1.1539428180915579e-07, "epoch": 19.44939493949395, "percentage": 97.25, "elapsed_time": "6:58:55", "remaining_time": "0:11:51", "throughput": 1484.36, "total_tokens": 37310224} {"current_steps": 176800, "total_steps": 181800, "loss": 0.002, "lr": 1.1516406203062602e-07, "epoch": 19.44994499449945, "percentage": 97.25, "elapsed_time": "6:58:56", "remaining_time": "0:11:50", "throughput": 1484.36, "total_tokens": 37311280} {"current_steps": 176805, "total_steps": 181800, "loss": 0.0689, "lr": 1.1493407160368674e-07, "epoch": 19.45049504950495, "percentage": 97.25, "elapsed_time": "6:58:56", "remaining_time": "0:11:50", "throughput": 1484.36, "total_tokens": 37312336} {"current_steps": 176810, "total_steps": 181800, "loss": 0.1006, "lr": 1.1470431053046127e-07, "epoch": 19.451045104510452, "percentage": 97.26, "elapsed_time": "6:58:57", "remaining_time": "0:11:49", "throughput": 1484.36, "total_tokens": 37313328} {"current_steps": 176815, "total_steps": 181800, "loss": 0.0041, "lr": 1.1447477881306179e-07, "epoch": 19.45159515951595, "percentage": 97.26, "elapsed_time": "6:58:58", "remaining_time": "0:11:48", "throughput": 1484.36, "total_tokens": 37314352} {"current_steps": 176820, "total_steps": 181800, "loss": 0.0636, "lr": 1.1424547645360884e-07, "epoch": 19.45214521452145, "percentage": 97.26, "elapsed_time": "6:58:58", "remaining_time": "0:11:48", "throughput": 1484.36, "total_tokens": 37315344} {"current_steps": 176825, "total_steps": 181800, "loss": 0.0638, "lr": 1.140164034542146e-07, "epoch": 19.452695269526952, "percentage": 97.26, "elapsed_time": "6:58:59", "remaining_time": "0:11:47", "throughput": 1484.36, "total_tokens": 37316336} {"current_steps": 176830, "total_steps": 181800, "loss": 0.0129, "lr": 1.1378755981698852e-07, "epoch": 19.453245324532453, "percentage": 97.27, "elapsed_time": "6:59:00", "remaining_time": "0:11:46", "throughput": 1484.36, "total_tokens": 37317392} {"current_steps": 176835, "total_steps": 181800, "loss": 0.0047, "lr": 1.1355894554404278e-07, "epoch": 19.453795379537954, "percentage": 97.27, "elapsed_time": "6:59:01", "remaining_time": "0:11:45", "throughput": 1484.36, "total_tokens": 37318384} {"current_steps": 176840, "total_steps": 181800, "loss": 0.0009, "lr": 1.133305606374785e-07, "epoch": 19.454345434543455, "percentage": 97.27, "elapsed_time": "6:59:01", "remaining_time": "0:11:45", "throughput": 1484.36, "total_tokens": 37319376} {"current_steps": 176845, "total_steps": 181800, "loss": 0.0569, "lr": 1.1310240509940784e-07, "epoch": 19.454895489548957, "percentage": 97.27, "elapsed_time": "6:59:02", "remaining_time": "0:11:44", "throughput": 1484.36, "total_tokens": 37320400} {"current_steps": 176850, "total_steps": 181800, "loss": 0.0135, "lr": 1.1287447893192915e-07, "epoch": 19.455445544554454, "percentage": 97.28, "elapsed_time": "6:59:03", "remaining_time": "0:11:43", "throughput": 1484.36, "total_tokens": 37321456} {"current_steps": 176855, "total_steps": 181800, "loss": 0.0064, "lr": 1.126467821371463e-07, "epoch": 19.455995599559955, "percentage": 97.28, "elapsed_time": "6:59:03", "remaining_time": "0:11:43", "throughput": 1484.36, "total_tokens": 37322544} {"current_steps": 176860, "total_steps": 181800, "loss": 0.1184, "lr": 1.1241931471715483e-07, "epoch": 19.456545654565456, "percentage": 97.28, "elapsed_time": "6:59:04", "remaining_time": "0:11:42", "throughput": 1484.37, "total_tokens": 37323664} {"current_steps": 176865, "total_steps": 181800, "loss": 0.0057, "lr": 1.1219207667405307e-07, "epoch": 19.457095709570957, "percentage": 97.29, "elapsed_time": "6:59:05", "remaining_time": "0:11:41", "throughput": 1484.37, "total_tokens": 37324720} {"current_steps": 176870, "total_steps": 181800, "loss": 0.0056, "lr": 1.1196506800993378e-07, "epoch": 19.45764576457646, "percentage": 97.29, "elapsed_time": "6:59:05", "remaining_time": "0:11:40", "throughput": 1484.37, "total_tokens": 37325744} {"current_steps": 176875, "total_steps": 181800, "loss": 0.0824, "lr": 1.1173828872688974e-07, "epoch": 19.45819581958196, "percentage": 97.29, "elapsed_time": "6:59:06", "remaining_time": "0:11:40", "throughput": 1484.37, "total_tokens": 37326832} {"current_steps": 176880, "total_steps": 181800, "loss": 0.0688, "lr": 1.1151173882701093e-07, "epoch": 19.458745874587457, "percentage": 97.29, "elapsed_time": "6:59:07", "remaining_time": "0:11:39", "throughput": 1484.37, "total_tokens": 37327856} {"current_steps": 176885, "total_steps": 181800, "loss": 0.0641, "lr": 1.1128541831238737e-07, "epoch": 19.459295929592958, "percentage": 97.3, "elapsed_time": "6:59:07", "remaining_time": "0:11:38", "throughput": 1484.37, "total_tokens": 37328912} {"current_steps": 176890, "total_steps": 181800, "loss": 0.0078, "lr": 1.110593271851007e-07, "epoch": 19.45984598459846, "percentage": 97.3, "elapsed_time": "6:59:08", "remaining_time": "0:11:38", "throughput": 1484.37, "total_tokens": 37329968} {"current_steps": 176895, "total_steps": 181800, "loss": 0.0083, "lr": 1.1083346544724093e-07, "epoch": 19.46039603960396, "percentage": 97.3, "elapsed_time": "6:59:09", "remaining_time": "0:11:37", "throughput": 1484.38, "total_tokens": 37331024} {"current_steps": 176900, "total_steps": 181800, "loss": 0.0065, "lr": 1.1060783310088419e-07, "epoch": 19.46094609460946, "percentage": 97.3, "elapsed_time": "6:59:09", "remaining_time": "0:11:36", "throughput": 1484.38, "total_tokens": 37332080} {"current_steps": 176905, "total_steps": 181800, "loss": 0.0112, "lr": 1.1038243014811212e-07, "epoch": 19.461496149614963, "percentage": 97.31, "elapsed_time": "6:59:10", "remaining_time": "0:11:35", "throughput": 1484.38, "total_tokens": 37333168} {"current_steps": 176910, "total_steps": 181800, "loss": 0.0079, "lr": 1.1015725659100084e-07, "epoch": 19.462046204620464, "percentage": 97.31, "elapsed_time": "6:59:11", "remaining_time": "0:11:35", "throughput": 1484.38, "total_tokens": 37334256} {"current_steps": 176915, "total_steps": 181800, "loss": 0.0769, "lr": 1.099323124316265e-07, "epoch": 19.46259625962596, "percentage": 97.31, "elapsed_time": "6:59:12", "remaining_time": "0:11:34", "throughput": 1484.38, "total_tokens": 37335312} {"current_steps": 176920, "total_steps": 181800, "loss": 0.0045, "lr": 1.0970759767206518e-07, "epoch": 19.463146314631462, "percentage": 97.32, "elapsed_time": "6:59:12", "remaining_time": "0:11:33", "throughput": 1484.39, "total_tokens": 37336400} {"current_steps": 176925, "total_steps": 181800, "loss": 0.0012, "lr": 1.0948311231438468e-07, "epoch": 19.463696369636963, "percentage": 97.32, "elapsed_time": "6:59:13", "remaining_time": "0:11:33", "throughput": 1484.39, "total_tokens": 37337424} {"current_steps": 176930, "total_steps": 181800, "loss": 0.0108, "lr": 1.0925885636065558e-07, "epoch": 19.464246424642464, "percentage": 97.32, "elapsed_time": "6:59:14", "remaining_time": "0:11:32", "throughput": 1484.39, "total_tokens": 37338480} {"current_steps": 176935, "total_steps": 181800, "loss": 0.0648, "lr": 1.0903482981294011e-07, "epoch": 19.464796479647966, "percentage": 97.32, "elapsed_time": "6:59:14", "remaining_time": "0:11:31", "throughput": 1484.39, "total_tokens": 37339568} {"current_steps": 176940, "total_steps": 181800, "loss": 0.0019, "lr": 1.0881103267330884e-07, "epoch": 19.465346534653467, "percentage": 97.33, "elapsed_time": "6:59:15", "remaining_time": "0:11:30", "throughput": 1484.39, "total_tokens": 37340560} {"current_steps": 176945, "total_steps": 181800, "loss": 0.0076, "lr": 1.0858746494382399e-07, "epoch": 19.465896589658964, "percentage": 97.33, "elapsed_time": "6:59:16", "remaining_time": "0:11:30", "throughput": 1484.39, "total_tokens": 37341680} {"current_steps": 176950, "total_steps": 181800, "loss": 0.0071, "lr": 1.0836412662654505e-07, "epoch": 19.466446644664465, "percentage": 97.33, "elapsed_time": "6:59:16", "remaining_time": "0:11:29", "throughput": 1484.39, "total_tokens": 37342704} {"current_steps": 176955, "total_steps": 181800, "loss": 0.0013, "lr": 1.0814101772352592e-07, "epoch": 19.466996699669966, "percentage": 97.33, "elapsed_time": "6:59:17", "remaining_time": "0:11:28", "throughput": 1484.39, "total_tokens": 37343792} {"current_steps": 176960, "total_steps": 181800, "loss": 0.0029, "lr": 1.0791813823682884e-07, "epoch": 19.467546754675467, "percentage": 97.34, "elapsed_time": "6:59:18", "remaining_time": "0:11:28", "throughput": 1484.39, "total_tokens": 37344784} {"current_steps": 176965, "total_steps": 181800, "loss": 0.0073, "lr": 1.0769548816850495e-07, "epoch": 19.46809680968097, "percentage": 97.34, "elapsed_time": "6:59:18", "remaining_time": "0:11:27", "throughput": 1484.39, "total_tokens": 37345840} {"current_steps": 176970, "total_steps": 181800, "loss": 0.0033, "lr": 1.0747306752060815e-07, "epoch": 19.46864686468647, "percentage": 97.34, "elapsed_time": "6:59:19", "remaining_time": "0:11:26", "throughput": 1484.39, "total_tokens": 37346832} {"current_steps": 176975, "total_steps": 181800, "loss": 0.1299, "lr": 1.0725087629518959e-07, "epoch": 19.46919691969197, "percentage": 97.35, "elapsed_time": "6:59:20", "remaining_time": "0:11:25", "throughput": 1484.4, "total_tokens": 37347920} {"current_steps": 176980, "total_steps": 181800, "loss": 0.0737, "lr": 1.0702891449429209e-07, "epoch": 19.46974697469747, "percentage": 97.35, "elapsed_time": "6:59:21", "remaining_time": "0:11:25", "throughput": 1484.39, "total_tokens": 37348912} {"current_steps": 176985, "total_steps": 181800, "loss": 0.1107, "lr": 1.0680718211996399e-07, "epoch": 19.47029702970297, "percentage": 97.35, "elapsed_time": "6:59:21", "remaining_time": "0:11:24", "throughput": 1484.4, "total_tokens": 37350032} {"current_steps": 176990, "total_steps": 181800, "loss": 0.002, "lr": 1.0658567917425089e-07, "epoch": 19.47084708470847, "percentage": 97.35, "elapsed_time": "6:59:22", "remaining_time": "0:11:23", "throughput": 1484.4, "total_tokens": 37351088} {"current_steps": 176995, "total_steps": 181800, "loss": 0.0019, "lr": 1.0636440565919004e-07, "epoch": 19.47139713971397, "percentage": 97.36, "elapsed_time": "6:59:23", "remaining_time": "0:11:23", "throughput": 1484.4, "total_tokens": 37352176} {"current_steps": 177000, "total_steps": 181800, "loss": 0.011, "lr": 1.0614336157682703e-07, "epoch": 19.471947194719473, "percentage": 97.36, "elapsed_time": "6:59:23", "remaining_time": "0:11:22", "throughput": 1484.4, "total_tokens": 37353232} {"current_steps": 177005, "total_steps": 181800, "loss": 0.099, "lr": 1.0592254692919356e-07, "epoch": 19.472497249724974, "percentage": 97.36, "elapsed_time": "6:59:24", "remaining_time": "0:11:21", "throughput": 1484.4, "total_tokens": 37354224} {"current_steps": 177010, "total_steps": 181800, "loss": 0.0282, "lr": 1.0570196171832692e-07, "epoch": 19.47304730473047, "percentage": 97.37, "elapsed_time": "6:59:25", "remaining_time": "0:11:20", "throughput": 1484.4, "total_tokens": 37355280} {"current_steps": 177015, "total_steps": 181800, "loss": 0.001, "lr": 1.0548160594625878e-07, "epoch": 19.473597359735972, "percentage": 97.37, "elapsed_time": "6:59:25", "remaining_time": "0:11:20", "throughput": 1484.4, "total_tokens": 37356336} {"current_steps": 177020, "total_steps": 181800, "loss": 0.0013, "lr": 1.0526147961502086e-07, "epoch": 19.474147414741473, "percentage": 97.37, "elapsed_time": "6:59:26", "remaining_time": "0:11:19", "throughput": 1484.41, "total_tokens": 37357456} {"current_steps": 177025, "total_steps": 181800, "loss": 0.0077, "lr": 1.0504158272664488e-07, "epoch": 19.474697469746975, "percentage": 97.37, "elapsed_time": "6:59:27", "remaining_time": "0:11:18", "throughput": 1484.41, "total_tokens": 37358512} {"current_steps": 177030, "total_steps": 181800, "loss": 0.0056, "lr": 1.0482191528315143e-07, "epoch": 19.475247524752476, "percentage": 97.38, "elapsed_time": "6:59:27", "remaining_time": "0:11:18", "throughput": 1484.41, "total_tokens": 37359568} {"current_steps": 177035, "total_steps": 181800, "loss": 0.0275, "lr": 1.0460247728657225e-07, "epoch": 19.475797579757977, "percentage": 97.38, "elapsed_time": "6:59:28", "remaining_time": "0:11:17", "throughput": 1484.41, "total_tokens": 37360624} {"current_steps": 177040, "total_steps": 181800, "loss": 0.0066, "lr": 1.0438326873892512e-07, "epoch": 19.476347634763478, "percentage": 97.38, "elapsed_time": "6:59:29", "remaining_time": "0:11:16", "throughput": 1484.41, "total_tokens": 37361680} {"current_steps": 177045, "total_steps": 181800, "loss": 0.0009, "lr": 1.041642896422279e-07, "epoch": 19.476897689768975, "percentage": 97.38, "elapsed_time": "6:59:30", "remaining_time": "0:11:16", "throughput": 1484.41, "total_tokens": 37362736} {"current_steps": 177050, "total_steps": 181800, "loss": 0.0054, "lr": 1.0394553999850676e-07, "epoch": 19.477447744774476, "percentage": 97.39, "elapsed_time": "6:59:30", "remaining_time": "0:11:15", "throughput": 1484.41, "total_tokens": 37363728} {"current_steps": 177055, "total_steps": 181800, "loss": 0.0051, "lr": 1.037270198097684e-07, "epoch": 19.477997799779978, "percentage": 97.39, "elapsed_time": "6:59:31", "remaining_time": "0:11:14", "throughput": 1484.41, "total_tokens": 37364816} {"current_steps": 177060, "total_steps": 181800, "loss": 0.0131, "lr": 1.0350872907803622e-07, "epoch": 19.47854785478548, "percentage": 97.39, "elapsed_time": "6:59:32", "remaining_time": "0:11:13", "throughput": 1484.42, "total_tokens": 37365872} {"current_steps": 177065, "total_steps": 181800, "loss": 0.004, "lr": 1.0329066780531694e-07, "epoch": 19.47909790979098, "percentage": 97.4, "elapsed_time": "6:59:32", "remaining_time": "0:11:13", "throughput": 1484.41, "total_tokens": 37366864} {"current_steps": 177070, "total_steps": 181800, "loss": 0.0285, "lr": 1.0307283599362006e-07, "epoch": 19.47964796479648, "percentage": 97.4, "elapsed_time": "6:59:33", "remaining_time": "0:11:12", "throughput": 1484.42, "total_tokens": 37367952} {"current_steps": 177075, "total_steps": 181800, "loss": 0.0043, "lr": 1.0285523364495508e-07, "epoch": 19.480198019801982, "percentage": 97.4, "elapsed_time": "6:59:34", "remaining_time": "0:11:11", "throughput": 1484.42, "total_tokens": 37369040} {"current_steps": 177080, "total_steps": 181800, "loss": 0.1469, "lr": 1.026378607613232e-07, "epoch": 19.48074807480748, "percentage": 97.4, "elapsed_time": "6:59:34", "remaining_time": "0:11:11", "throughput": 1484.42, "total_tokens": 37370064} {"current_steps": 177085, "total_steps": 181800, "loss": 0.0351, "lr": 1.024207173447339e-07, "epoch": 19.48129812981298, "percentage": 97.41, "elapsed_time": "6:59:35", "remaining_time": "0:11:10", "throughput": 1484.42, "total_tokens": 37371184} {"current_steps": 177090, "total_steps": 181800, "loss": 0.0083, "lr": 1.022038033971856e-07, "epoch": 19.48184818481848, "percentage": 97.41, "elapsed_time": "6:59:36", "remaining_time": "0:11:09", "throughput": 1484.42, "total_tokens": 37372240} {"current_steps": 177095, "total_steps": 181800, "loss": 0.0035, "lr": 1.019871189206767e-07, "epoch": 19.482398239823983, "percentage": 97.41, "elapsed_time": "6:59:36", "remaining_time": "0:11:08", "throughput": 1484.43, "total_tokens": 37373328} {"current_steps": 177100, "total_steps": 181800, "loss": 0.0058, "lr": 1.0177066391720836e-07, "epoch": 19.482948294829484, "percentage": 97.41, "elapsed_time": "6:59:37", "remaining_time": "0:11:08", "throughput": 1484.43, "total_tokens": 37374352} {"current_steps": 177105, "total_steps": 181800, "loss": 0.0012, "lr": 1.0155443838876788e-07, "epoch": 19.483498349834985, "percentage": 97.42, "elapsed_time": "6:59:38", "remaining_time": "0:11:07", "throughput": 1484.43, "total_tokens": 37375440} {"current_steps": 177110, "total_steps": 181800, "loss": 0.0039, "lr": 1.0133844233735646e-07, "epoch": 19.484048404840483, "percentage": 97.42, "elapsed_time": "6:59:39", "remaining_time": "0:11:06", "throughput": 1484.43, "total_tokens": 37376464} {"current_steps": 177115, "total_steps": 181800, "loss": 0.0025, "lr": 1.011226757649586e-07, "epoch": 19.484598459845984, "percentage": 97.42, "elapsed_time": "6:59:39", "remaining_time": "0:11:06", "throughput": 1484.43, "total_tokens": 37377552} {"current_steps": 177120, "total_steps": 181800, "loss": 0.0044, "lr": 1.0090713867356715e-07, "epoch": 19.485148514851485, "percentage": 97.43, "elapsed_time": "6:59:40", "remaining_time": "0:11:05", "throughput": 1484.43, "total_tokens": 37378608} {"current_steps": 177125, "total_steps": 181800, "loss": 0.0048, "lr": 1.0069183106516666e-07, "epoch": 19.485698569856986, "percentage": 97.43, "elapsed_time": "6:59:41", "remaining_time": "0:11:04", "throughput": 1484.43, "total_tokens": 37379632} {"current_steps": 177130, "total_steps": 181800, "loss": 0.0128, "lr": 1.0047675294174164e-07, "epoch": 19.486248624862487, "percentage": 97.43, "elapsed_time": "6:59:41", "remaining_time": "0:11:03", "throughput": 1484.43, "total_tokens": 37380624} {"current_steps": 177135, "total_steps": 181800, "loss": 0.0017, "lr": 1.0026190430527382e-07, "epoch": 19.486798679867988, "percentage": 97.43, "elapsed_time": "6:59:42", "remaining_time": "0:11:03", "throughput": 1484.43, "total_tokens": 37381712} {"current_steps": 177140, "total_steps": 181800, "loss": 0.0577, "lr": 1.0004728515774497e-07, "epoch": 19.48734873487349, "percentage": 97.44, "elapsed_time": "6:59:43", "remaining_time": "0:11:02", "throughput": 1484.43, "total_tokens": 37382768} {"current_steps": 177145, "total_steps": 181800, "loss": 0.0489, "lr": 9.983289550113129e-08, "epoch": 19.487898789878987, "percentage": 97.44, "elapsed_time": "6:59:43", "remaining_time": "0:11:01", "throughput": 1484.44, "total_tokens": 37383856} {"current_steps": 177150, "total_steps": 181800, "loss": 0.0006, "lr": 9.961873533740895e-08, "epoch": 19.488448844884488, "percentage": 97.44, "elapsed_time": "6:59:44", "remaining_time": "0:11:01", "throughput": 1484.43, "total_tokens": 37384880} {"current_steps": 177155, "total_steps": 181800, "loss": 0.0038, "lr": 9.940480466855417e-08, "epoch": 19.48899889988999, "percentage": 97.44, "elapsed_time": "6:59:45", "remaining_time": "0:11:00", "throughput": 1484.43, "total_tokens": 37385968} {"current_steps": 177160, "total_steps": 181800, "loss": 0.0228, "lr": 9.919110349653482e-08, "epoch": 19.48954895489549, "percentage": 97.45, "elapsed_time": "6:59:46", "remaining_time": "0:10:59", "throughput": 1484.43, "total_tokens": 37386992} {"current_steps": 177165, "total_steps": 181800, "loss": 0.0058, "lr": 9.897763182332431e-08, "epoch": 19.49009900990099, "percentage": 97.45, "elapsed_time": "6:59:46", "remaining_time": "0:10:58", "throughput": 1484.43, "total_tokens": 37388112} {"current_steps": 177170, "total_steps": 181800, "loss": 0.0032, "lr": 9.876438965088496e-08, "epoch": 19.490649064906492, "percentage": 97.45, "elapsed_time": "6:59:47", "remaining_time": "0:10:58", "throughput": 1484.43, "total_tokens": 37389200} {"current_steps": 177175, "total_steps": 181800, "loss": 0.0307, "lr": 9.855137698119022e-08, "epoch": 19.49119911991199, "percentage": 97.46, "elapsed_time": "6:59:48", "remaining_time": "0:10:57", "throughput": 1484.43, "total_tokens": 37390192} {"current_steps": 177180, "total_steps": 181800, "loss": 0.0013, "lr": 9.833859381619404e-08, "epoch": 19.49174917491749, "percentage": 97.46, "elapsed_time": "6:59:48", "remaining_time": "0:10:56", "throughput": 1484.43, "total_tokens": 37391152} {"current_steps": 177185, "total_steps": 181800, "loss": 0.0434, "lr": 9.812604015786708e-08, "epoch": 19.492299229922992, "percentage": 97.46, "elapsed_time": "6:59:49", "remaining_time": "0:10:56", "throughput": 1484.43, "total_tokens": 37392208} {"current_steps": 177190, "total_steps": 181800, "loss": 0.0232, "lr": 9.791371600816057e-08, "epoch": 19.492849284928493, "percentage": 97.46, "elapsed_time": "6:59:50", "remaining_time": "0:10:55", "throughput": 1484.43, "total_tokens": 37393264} {"current_steps": 177195, "total_steps": 181800, "loss": 0.0116, "lr": 9.770162136903128e-08, "epoch": 19.493399339933994, "percentage": 97.47, "elapsed_time": "6:59:50", "remaining_time": "0:10:54", "throughput": 1484.43, "total_tokens": 37394288} {"current_steps": 177200, "total_steps": 181800, "loss": 0.0027, "lr": 9.74897562424415e-08, "epoch": 19.493949394939495, "percentage": 97.47, "elapsed_time": "6:59:51", "remaining_time": "0:10:53", "throughput": 1484.44, "total_tokens": 37395376} {"current_steps": 177205, "total_steps": 181800, "loss": 0.0023, "lr": 9.727812063033692e-08, "epoch": 19.494499449944996, "percentage": 97.47, "elapsed_time": "6:59:52", "remaining_time": "0:10:53", "throughput": 1484.44, "total_tokens": 37396496} {"current_steps": 177210, "total_steps": 181800, "loss": 0.0031, "lr": 9.706671453467154e-08, "epoch": 19.495049504950494, "percentage": 97.48, "elapsed_time": "6:59:53", "remaining_time": "0:10:52", "throughput": 1484.44, "total_tokens": 37397584} {"current_steps": 177215, "total_steps": 181800, "loss": 0.0014, "lr": 9.685553795739378e-08, "epoch": 19.495599559955995, "percentage": 97.48, "elapsed_time": "6:59:53", "remaining_time": "0:10:51", "throughput": 1484.44, "total_tokens": 37398608} {"current_steps": 177220, "total_steps": 181800, "loss": 0.0548, "lr": 9.664459090044653e-08, "epoch": 19.496149614961496, "percentage": 97.48, "elapsed_time": "6:59:54", "remaining_time": "0:10:51", "throughput": 1484.44, "total_tokens": 37399632} {"current_steps": 177225, "total_steps": 181800, "loss": 0.0321, "lr": 9.643387336577547e-08, "epoch": 19.496699669966997, "percentage": 97.48, "elapsed_time": "6:59:55", "remaining_time": "0:10:50", "throughput": 1484.44, "total_tokens": 37400592} {"current_steps": 177230, "total_steps": 181800, "loss": 0.0109, "lr": 9.622338535532627e-08, "epoch": 19.497249724972498, "percentage": 97.49, "elapsed_time": "6:59:55", "remaining_time": "0:10:49", "throughput": 1484.44, "total_tokens": 37401584} {"current_steps": 177235, "total_steps": 181800, "loss": 0.005, "lr": 9.601312687103347e-08, "epoch": 19.497799779978, "percentage": 97.49, "elapsed_time": "6:59:56", "remaining_time": "0:10:48", "throughput": 1484.44, "total_tokens": 37402704} {"current_steps": 177240, "total_steps": 181800, "loss": 0.0071, "lr": 9.580309791484e-08, "epoch": 19.498349834983497, "percentage": 97.49, "elapsed_time": "6:59:57", "remaining_time": "0:10:48", "throughput": 1484.44, "total_tokens": 37403728} {"current_steps": 177245, "total_steps": 181800, "loss": 0.0182, "lr": 9.559329848867759e-08, "epoch": 19.498899889988998, "percentage": 97.49, "elapsed_time": "6:59:57", "remaining_time": "0:10:47", "throughput": 1484.44, "total_tokens": 37404784} {"current_steps": 177250, "total_steps": 181800, "loss": 0.0173, "lr": 9.538372859448364e-08, "epoch": 19.4994499449945, "percentage": 97.5, "elapsed_time": "6:59:58", "remaining_time": "0:10:46", "throughput": 1484.44, "total_tokens": 37405808} {"current_steps": 177255, "total_steps": 181800, "loss": 0.0147, "lr": 9.517438823418434e-08, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "6:59:59", "remaining_time": "0:10:46", "throughput": 1484.44, "total_tokens": 37406832} {"current_steps": 177260, "total_steps": 181800, "loss": 0.0038, "lr": 9.496527740971429e-08, "epoch": 19.5005500550055, "percentage": 97.5, "elapsed_time": "6:59:59", "remaining_time": "0:10:45", "throughput": 1484.44, "total_tokens": 37407856} {"current_steps": 177265, "total_steps": 181800, "loss": 0.0822, "lr": 9.475639612299691e-08, "epoch": 19.501100110011002, "percentage": 97.51, "elapsed_time": "7:00:00", "remaining_time": "0:10:44", "throughput": 1484.44, "total_tokens": 37408912} {"current_steps": 177270, "total_steps": 181800, "loss": 0.0557, "lr": 9.454774437596126e-08, "epoch": 19.501650165016503, "percentage": 97.51, "elapsed_time": "7:00:01", "remaining_time": "0:10:44", "throughput": 1484.45, "total_tokens": 37410064} {"current_steps": 177275, "total_steps": 181800, "loss": 0.0019, "lr": 9.4339322170528e-08, "epoch": 19.502200220022, "percentage": 97.51, "elapsed_time": "7:00:02", "remaining_time": "0:10:43", "throughput": 1484.45, "total_tokens": 37411120} {"current_steps": 177280, "total_steps": 181800, "loss": 0.0026, "lr": 9.413112950861502e-08, "epoch": 19.502750275027502, "percentage": 97.51, "elapsed_time": "7:00:02", "remaining_time": "0:10:42", "throughput": 1484.45, "total_tokens": 37412176} {"current_steps": 177285, "total_steps": 181800, "loss": 0.0038, "lr": 9.39231663921486e-08, "epoch": 19.503300330033003, "percentage": 97.52, "elapsed_time": "7:00:03", "remaining_time": "0:10:41", "throughput": 1484.45, "total_tokens": 37413264} {"current_steps": 177290, "total_steps": 181800, "loss": 0.0856, "lr": 9.37154328230383e-08, "epoch": 19.503850385038504, "percentage": 97.52, "elapsed_time": "7:00:04", "remaining_time": "0:10:41", "throughput": 1484.46, "total_tokens": 37414384} {"current_steps": 177295, "total_steps": 181800, "loss": 0.0016, "lr": 9.350792880320203e-08, "epoch": 19.504400440044005, "percentage": 97.52, "elapsed_time": "7:00:04", "remaining_time": "0:10:40", "throughput": 1484.46, "total_tokens": 37415504} {"current_steps": 177300, "total_steps": 181800, "loss": 0.026, "lr": 9.330065433455493e-08, "epoch": 19.504950495049506, "percentage": 97.52, "elapsed_time": "7:00:05", "remaining_time": "0:10:39", "throughput": 1484.46, "total_tokens": 37416528} {"current_steps": 177305, "total_steps": 181800, "loss": 0.0255, "lr": 9.309360941900103e-08, "epoch": 19.505500550055004, "percentage": 97.53, "elapsed_time": "7:00:06", "remaining_time": "0:10:39", "throughput": 1484.46, "total_tokens": 37417552} {"current_steps": 177310, "total_steps": 181800, "loss": 0.0027, "lr": 9.288679405845268e-08, "epoch": 19.506050605060505, "percentage": 97.53, "elapsed_time": "7:00:06", "remaining_time": "0:10:38", "throughput": 1484.46, "total_tokens": 37418576} {"current_steps": 177315, "total_steps": 181800, "loss": 0.0389, "lr": 9.268020825481671e-08, "epoch": 19.506600660066006, "percentage": 97.53, "elapsed_time": "7:00:07", "remaining_time": "0:10:37", "throughput": 1484.46, "total_tokens": 37419600} {"current_steps": 177320, "total_steps": 181800, "loss": 0.0968, "lr": 9.247385200999437e-08, "epoch": 19.507150715071507, "percentage": 97.54, "elapsed_time": "7:00:08", "remaining_time": "0:10:36", "throughput": 1484.46, "total_tokens": 37420656} {"current_steps": 177325, "total_steps": 181800, "loss": 0.0044, "lr": 9.226772532588968e-08, "epoch": 19.507700770077008, "percentage": 97.54, "elapsed_time": "7:00:08", "remaining_time": "0:10:36", "throughput": 1484.46, "total_tokens": 37421680} {"current_steps": 177330, "total_steps": 181800, "loss": 0.0023, "lr": 9.206182820440113e-08, "epoch": 19.50825082508251, "percentage": 97.54, "elapsed_time": "7:00:09", "remaining_time": "0:10:35", "throughput": 1484.46, "total_tokens": 37422768} {"current_steps": 177335, "total_steps": 181800, "loss": 0.0018, "lr": 9.185616064742442e-08, "epoch": 19.50880088008801, "percentage": 97.54, "elapsed_time": "7:00:10", "remaining_time": "0:10:34", "throughput": 1484.46, "total_tokens": 37423760} {"current_steps": 177340, "total_steps": 181800, "loss": 0.0804, "lr": 9.165072265685804e-08, "epoch": 19.509350935093508, "percentage": 97.55, "elapsed_time": "7:00:11", "remaining_time": "0:10:34", "throughput": 1484.46, "total_tokens": 37424784} {"current_steps": 177345, "total_steps": 181800, "loss": 0.0059, "lr": 9.144551423459491e-08, "epoch": 19.50990099009901, "percentage": 97.55, "elapsed_time": "7:00:11", "remaining_time": "0:10:33", "throughput": 1484.46, "total_tokens": 37425840} {"current_steps": 177350, "total_steps": 181800, "loss": 0.0017, "lr": 9.124053538252796e-08, "epoch": 19.51045104510451, "percentage": 97.55, "elapsed_time": "7:00:12", "remaining_time": "0:10:32", "throughput": 1484.46, "total_tokens": 37426896} {"current_steps": 177355, "total_steps": 181800, "loss": 0.0098, "lr": 9.10357861025446e-08, "epoch": 19.51100110011001, "percentage": 97.56, "elapsed_time": "7:00:13", "remaining_time": "0:10:31", "throughput": 1484.46, "total_tokens": 37427952} {"current_steps": 177360, "total_steps": 181800, "loss": 0.0051, "lr": 9.083126639653216e-08, "epoch": 19.511551155115512, "percentage": 97.56, "elapsed_time": "7:00:13", "remaining_time": "0:10:31", "throughput": 1484.46, "total_tokens": 37428976} {"current_steps": 177365, "total_steps": 181800, "loss": 0.0236, "lr": 9.062697626637251e-08, "epoch": 19.512101210121013, "percentage": 97.56, "elapsed_time": "7:00:14", "remaining_time": "0:10:30", "throughput": 1484.46, "total_tokens": 37430000} {"current_steps": 177370, "total_steps": 181800, "loss": 0.0068, "lr": 9.0422915713953e-08, "epoch": 19.51265126512651, "percentage": 97.56, "elapsed_time": "7:00:15", "remaining_time": "0:10:29", "throughput": 1484.46, "total_tokens": 37431024} {"current_steps": 177375, "total_steps": 181800, "loss": 0.0021, "lr": 9.02190847411527e-08, "epoch": 19.513201320132012, "percentage": 97.57, "elapsed_time": "7:00:15", "remaining_time": "0:10:29", "throughput": 1484.46, "total_tokens": 37432016} {"current_steps": 177380, "total_steps": 181800, "loss": 0.0133, "lr": 9.001548334985066e-08, "epoch": 19.513751375137513, "percentage": 97.57, "elapsed_time": "7:00:16", "remaining_time": "0:10:28", "throughput": 1484.46, "total_tokens": 37433040} {"current_steps": 177385, "total_steps": 181800, "loss": 0.0692, "lr": 8.981211154192315e-08, "epoch": 19.514301430143014, "percentage": 97.57, "elapsed_time": "7:00:17", "remaining_time": "0:10:27", "throughput": 1484.46, "total_tokens": 37434032} {"current_steps": 177390, "total_steps": 181800, "loss": 0.0027, "lr": 8.960896931924367e-08, "epoch": 19.514851485148515, "percentage": 97.57, "elapsed_time": "7:00:17", "remaining_time": "0:10:26", "throughput": 1484.46, "total_tokens": 37435088} {"current_steps": 177395, "total_steps": 181800, "loss": 0.0016, "lr": 8.940605668368573e-08, "epoch": 19.515401540154016, "percentage": 97.58, "elapsed_time": "7:00:18", "remaining_time": "0:10:26", "throughput": 1484.46, "total_tokens": 37436112} {"current_steps": 177400, "total_steps": 181800, "loss": 0.0011, "lr": 8.920337363711728e-08, "epoch": 19.515951595159517, "percentage": 97.58, "elapsed_time": "7:00:19", "remaining_time": "0:10:25", "throughput": 1484.46, "total_tokens": 37437168} {"current_steps": 177405, "total_steps": 181800, "loss": 0.0772, "lr": 8.900092018140904e-08, "epoch": 19.516501650165015, "percentage": 97.58, "elapsed_time": "7:00:20", "remaining_time": "0:10:24", "throughput": 1484.47, "total_tokens": 37438256} {"current_steps": 177410, "total_steps": 181800, "loss": 0.0016, "lr": 8.879869631842619e-08, "epoch": 19.517051705170516, "percentage": 97.59, "elapsed_time": "7:00:20", "remaining_time": "0:10:24", "throughput": 1484.47, "total_tokens": 37439344} {"current_steps": 177415, "total_steps": 181800, "loss": 0.0177, "lr": 8.859670205003113e-08, "epoch": 19.517601760176017, "percentage": 97.59, "elapsed_time": "7:00:21", "remaining_time": "0:10:23", "throughput": 1484.47, "total_tokens": 37440400} {"current_steps": 177420, "total_steps": 181800, "loss": 0.0012, "lr": 8.839493737808901e-08, "epoch": 19.51815181518152, "percentage": 97.59, "elapsed_time": "7:00:22", "remaining_time": "0:10:22", "throughput": 1484.47, "total_tokens": 37441520} {"current_steps": 177425, "total_steps": 181800, "loss": 0.0028, "lr": 8.819340230445394e-08, "epoch": 19.51870187018702, "percentage": 97.59, "elapsed_time": "7:00:22", "remaining_time": "0:10:21", "throughput": 1484.47, "total_tokens": 37442544} {"current_steps": 177430, "total_steps": 181800, "loss": 0.0021, "lr": 8.79920968309883e-08, "epoch": 19.51925192519252, "percentage": 97.6, "elapsed_time": "7:00:23", "remaining_time": "0:10:21", "throughput": 1484.48, "total_tokens": 37443664} {"current_steps": 177435, "total_steps": 181800, "loss": 0.066, "lr": 8.779102095954616e-08, "epoch": 19.519801980198018, "percentage": 97.6, "elapsed_time": "7:00:24", "remaining_time": "0:10:20", "throughput": 1484.48, "total_tokens": 37444784} {"current_steps": 177440, "total_steps": 181800, "loss": 0.0391, "lr": 8.759017469197883e-08, "epoch": 19.52035203520352, "percentage": 97.6, "elapsed_time": "7:00:24", "remaining_time": "0:10:19", "throughput": 1484.48, "total_tokens": 37445840} {"current_steps": 177445, "total_steps": 181800, "loss": 0.112, "lr": 8.738955803014037e-08, "epoch": 19.52090209020902, "percentage": 97.6, "elapsed_time": "7:00:25", "remaining_time": "0:10:19", "throughput": 1484.48, "total_tokens": 37446896} {"current_steps": 177450, "total_steps": 181800, "loss": 0.0447, "lr": 8.718917097587653e-08, "epoch": 19.52145214521452, "percentage": 97.61, "elapsed_time": "7:00:26", "remaining_time": "0:10:18", "throughput": 1484.48, "total_tokens": 37447952} {"current_steps": 177455, "total_steps": 181800, "loss": 0.007, "lr": 8.698901353103306e-08, "epoch": 19.522002200220022, "percentage": 97.61, "elapsed_time": "7:00:26", "remaining_time": "0:10:17", "throughput": 1484.49, "total_tokens": 37449040} {"current_steps": 177460, "total_steps": 181800, "loss": 0.0723, "lr": 8.678908569746125e-08, "epoch": 19.522552255225524, "percentage": 97.61, "elapsed_time": "7:00:27", "remaining_time": "0:10:16", "throughput": 1484.49, "total_tokens": 37450064} {"current_steps": 177465, "total_steps": 181800, "loss": 0.0354, "lr": 8.658938747699851e-08, "epoch": 19.523102310231025, "percentage": 97.62, "elapsed_time": "7:00:28", "remaining_time": "0:10:16", "throughput": 1484.49, "total_tokens": 37451120} {"current_steps": 177470, "total_steps": 181800, "loss": 0.0063, "lr": 8.638991887148784e-08, "epoch": 19.523652365236522, "percentage": 97.62, "elapsed_time": "7:00:28", "remaining_time": "0:10:15", "throughput": 1484.49, "total_tokens": 37452208} {"current_steps": 177475, "total_steps": 181800, "loss": 0.0011, "lr": 8.619067988276663e-08, "epoch": 19.524202420242023, "percentage": 97.62, "elapsed_time": "7:00:29", "remaining_time": "0:10:14", "throughput": 1484.49, "total_tokens": 37453296} {"current_steps": 177480, "total_steps": 181800, "loss": 0.0013, "lr": 8.599167051267232e-08, "epoch": 19.524752475247524, "percentage": 97.62, "elapsed_time": "7:00:30", "remaining_time": "0:10:14", "throughput": 1484.5, "total_tokens": 37454416} {"current_steps": 177485, "total_steps": 181800, "loss": 0.0723, "lr": 8.579289076303398e-08, "epoch": 19.525302530253025, "percentage": 97.63, "elapsed_time": "7:00:31", "remaining_time": "0:10:13", "throughput": 1484.5, "total_tokens": 37455440} {"current_steps": 177490, "total_steps": 181800, "loss": 0.0521, "lr": 8.559434063568905e-08, "epoch": 19.525852585258527, "percentage": 97.63, "elapsed_time": "7:00:31", "remaining_time": "0:10:12", "throughput": 1484.5, "total_tokens": 37456464} {"current_steps": 177495, "total_steps": 181800, "loss": 0.0319, "lr": 8.539602013246661e-08, "epoch": 19.526402640264028, "percentage": 97.63, "elapsed_time": "7:00:32", "remaining_time": "0:10:11", "throughput": 1484.5, "total_tokens": 37457488} {"current_steps": 177500, "total_steps": 181800, "loss": 0.0013, "lr": 8.519792925519577e-08, "epoch": 19.52695269526953, "percentage": 97.63, "elapsed_time": "7:00:33", "remaining_time": "0:10:11", "throughput": 1484.5, "total_tokens": 37458576} {"current_steps": 177505, "total_steps": 181800, "loss": 0.0854, "lr": 8.500006800569726e-08, "epoch": 19.527502750275026, "percentage": 97.64, "elapsed_time": "7:00:33", "remaining_time": "0:10:10", "throughput": 1484.5, "total_tokens": 37459600} {"current_steps": 177510, "total_steps": 181800, "loss": 0.033, "lr": 8.480243638580021e-08, "epoch": 19.528052805280527, "percentage": 97.64, "elapsed_time": "7:00:34", "remaining_time": "0:10:09", "throughput": 1484.5, "total_tokens": 37460688} {"current_steps": 177515, "total_steps": 181800, "loss": 0.0075, "lr": 8.460503439731981e-08, "epoch": 19.52860286028603, "percentage": 97.64, "elapsed_time": "7:00:35", "remaining_time": "0:10:09", "throughput": 1484.5, "total_tokens": 37461712} {"current_steps": 177520, "total_steps": 181800, "loss": 0.0089, "lr": 8.44078620420824e-08, "epoch": 19.52915291529153, "percentage": 97.65, "elapsed_time": "7:00:35", "remaining_time": "0:10:08", "throughput": 1484.5, "total_tokens": 37462800} {"current_steps": 177525, "total_steps": 181800, "loss": 0.0901, "lr": 8.421091932190317e-08, "epoch": 19.52970297029703, "percentage": 97.65, "elapsed_time": "7:00:36", "remaining_time": "0:10:07", "throughput": 1484.5, "total_tokens": 37463792} {"current_steps": 177530, "total_steps": 181800, "loss": 0.0296, "lr": 8.401420623859458e-08, "epoch": 19.53025302530253, "percentage": 97.65, "elapsed_time": "7:00:37", "remaining_time": "0:10:07", "throughput": 1484.51, "total_tokens": 37464880} {"current_steps": 177535, "total_steps": 181800, "loss": 0.018, "lr": 8.381772279396905e-08, "epoch": 19.53080308030803, "percentage": 97.65, "elapsed_time": "7:00:37", "remaining_time": "0:10:06", "throughput": 1484.5, "total_tokens": 37465872} {"current_steps": 177540, "total_steps": 181800, "loss": 0.0083, "lr": 8.36214689898418e-08, "epoch": 19.53135313531353, "percentage": 97.66, "elapsed_time": "7:00:38", "remaining_time": "0:10:05", "throughput": 1484.5, "total_tokens": 37466896} {"current_steps": 177545, "total_steps": 181800, "loss": 0.0018, "lr": 8.342544482801972e-08, "epoch": 19.53190319031903, "percentage": 97.66, "elapsed_time": "7:00:39", "remaining_time": "0:10:04", "throughput": 1484.51, "total_tokens": 37467984} {"current_steps": 177550, "total_steps": 181800, "loss": 0.0173, "lr": 8.322965031030693e-08, "epoch": 19.532453245324533, "percentage": 97.66, "elapsed_time": "7:00:40", "remaining_time": "0:10:04", "throughput": 1484.51, "total_tokens": 37469104} {"current_steps": 177555, "total_steps": 181800, "loss": 0.0015, "lr": 8.30340854385131e-08, "epoch": 19.533003300330034, "percentage": 97.67, "elapsed_time": "7:00:40", "remaining_time": "0:10:03", "throughput": 1484.51, "total_tokens": 37470096} {"current_steps": 177560, "total_steps": 181800, "loss": 0.0717, "lr": 8.283875021443676e-08, "epoch": 19.533553355335535, "percentage": 97.67, "elapsed_time": "7:00:41", "remaining_time": "0:10:02", "throughput": 1484.51, "total_tokens": 37471184} {"current_steps": 177565, "total_steps": 181800, "loss": 0.0016, "lr": 8.264364463987928e-08, "epoch": 19.534103410341036, "percentage": 97.67, "elapsed_time": "7:00:42", "remaining_time": "0:10:02", "throughput": 1484.52, "total_tokens": 37472336} {"current_steps": 177570, "total_steps": 181800, "loss": 0.0459, "lr": 8.24487687166392e-08, "epoch": 19.534653465346533, "percentage": 97.67, "elapsed_time": "7:00:42", "remaining_time": "0:10:01", "throughput": 1484.52, "total_tokens": 37473456} {"current_steps": 177575, "total_steps": 181800, "loss": 0.0228, "lr": 8.225412244650954e-08, "epoch": 19.535203520352034, "percentage": 97.68, "elapsed_time": "7:00:43", "remaining_time": "0:10:00", "throughput": 1484.52, "total_tokens": 37474480} {"current_steps": 177580, "total_steps": 181800, "loss": 0.0008, "lr": 8.205970583129163e-08, "epoch": 19.535753575357536, "percentage": 97.68, "elapsed_time": "7:00:44", "remaining_time": "0:09:59", "throughput": 1484.52, "total_tokens": 37475472} {"current_steps": 177585, "total_steps": 181800, "loss": 0.006, "lr": 8.186551887277016e-08, "epoch": 19.536303630363037, "percentage": 97.68, "elapsed_time": "7:00:44", "remaining_time": "0:09:59", "throughput": 1484.52, "total_tokens": 37476560} {"current_steps": 177590, "total_steps": 181800, "loss": 0.0016, "lr": 8.167156157273537e-08, "epoch": 19.536853685368538, "percentage": 97.68, "elapsed_time": "7:00:45", "remaining_time": "0:09:58", "throughput": 1484.53, "total_tokens": 37477648} {"current_steps": 177595, "total_steps": 181800, "loss": 0.034, "lr": 8.147783393298026e-08, "epoch": 19.53740374037404, "percentage": 97.69, "elapsed_time": "7:00:46", "remaining_time": "0:09:57", "throughput": 1484.53, "total_tokens": 37478704} {"current_steps": 177600, "total_steps": 181800, "loss": 0.114, "lr": 8.128433595528396e-08, "epoch": 19.537953795379536, "percentage": 97.69, "elapsed_time": "7:00:46", "remaining_time": "0:09:57", "throughput": 1484.53, "total_tokens": 37479792} {"current_steps": 177605, "total_steps": 181800, "loss": 0.0027, "lr": 8.109106764143392e-08, "epoch": 19.538503850385037, "percentage": 97.69, "elapsed_time": "7:00:47", "remaining_time": "0:09:56", "throughput": 1484.53, "total_tokens": 37480880} {"current_steps": 177610, "total_steps": 181800, "loss": 0.0015, "lr": 8.089802899321208e-08, "epoch": 19.53905390539054, "percentage": 97.7, "elapsed_time": "7:00:48", "remaining_time": "0:09:55", "throughput": 1484.54, "total_tokens": 37482064} {"current_steps": 177615, "total_steps": 181800, "loss": 0.1026, "lr": 8.0705220012392e-08, "epoch": 19.53960396039604, "percentage": 97.7, "elapsed_time": "7:00:48", "remaining_time": "0:09:54", "throughput": 1484.54, "total_tokens": 37483152} {"current_steps": 177620, "total_steps": 181800, "loss": 0.0025, "lr": 8.051264070075837e-08, "epoch": 19.54015401540154, "percentage": 97.7, "elapsed_time": "7:00:49", "remaining_time": "0:09:54", "throughput": 1484.54, "total_tokens": 37484240} {"current_steps": 177625, "total_steps": 181800, "loss": 0.0022, "lr": 8.032029106007922e-08, "epoch": 19.540704070407042, "percentage": 97.7, "elapsed_time": "7:00:50", "remaining_time": "0:09:53", "throughput": 1484.54, "total_tokens": 37485264} {"current_steps": 177630, "total_steps": 181800, "loss": 0.0156, "lr": 8.012817109213089e-08, "epoch": 19.541254125412543, "percentage": 97.71, "elapsed_time": "7:00:51", "remaining_time": "0:09:52", "throughput": 1484.54, "total_tokens": 37486256} {"current_steps": 177635, "total_steps": 181800, "loss": 0.0234, "lr": 7.993628079868699e-08, "epoch": 19.54180418041804, "percentage": 97.71, "elapsed_time": "7:00:51", "remaining_time": "0:09:52", "throughput": 1484.54, "total_tokens": 37487280} {"current_steps": 177640, "total_steps": 181800, "loss": 0.0038, "lr": 7.974462018150718e-08, "epoch": 19.54235423542354, "percentage": 97.71, "elapsed_time": "7:00:52", "remaining_time": "0:09:51", "throughput": 1484.54, "total_tokens": 37488368} {"current_steps": 177645, "total_steps": 181800, "loss": 0.0247, "lr": 7.955318924236787e-08, "epoch": 19.542904290429043, "percentage": 97.71, "elapsed_time": "7:00:53", "remaining_time": "0:09:50", "throughput": 1484.55, "total_tokens": 37489424} {"current_steps": 177650, "total_steps": 181800, "loss": 0.1758, "lr": 7.936198798302596e-08, "epoch": 19.543454345434544, "percentage": 97.72, "elapsed_time": "7:00:53", "remaining_time": "0:09:49", "throughput": 1484.55, "total_tokens": 37490544} {"current_steps": 177655, "total_steps": 181800, "loss": 0.0755, "lr": 7.917101640524671e-08, "epoch": 19.544004400440045, "percentage": 97.72, "elapsed_time": "7:00:54", "remaining_time": "0:09:49", "throughput": 1484.55, "total_tokens": 37491600} {"current_steps": 177660, "total_steps": 181800, "loss": 0.0243, "lr": 7.898027451078982e-08, "epoch": 19.544554455445546, "percentage": 97.72, "elapsed_time": "7:00:55", "remaining_time": "0:09:48", "throughput": 1484.55, "total_tokens": 37492592} {"current_steps": 177665, "total_steps": 181800, "loss": 0.0354, "lr": 7.8789762301415e-08, "epoch": 19.545104510451043, "percentage": 97.73, "elapsed_time": "7:00:55", "remaining_time": "0:09:47", "throughput": 1484.55, "total_tokens": 37493648} {"current_steps": 177670, "total_steps": 181800, "loss": 0.0076, "lr": 7.859947977887638e-08, "epoch": 19.545654565456545, "percentage": 97.73, "elapsed_time": "7:00:56", "remaining_time": "0:09:47", "throughput": 1484.55, "total_tokens": 37494672} {"current_steps": 177675, "total_steps": 181800, "loss": 0.0032, "lr": 7.840942694492814e-08, "epoch": 19.546204620462046, "percentage": 97.73, "elapsed_time": "7:00:57", "remaining_time": "0:09:46", "throughput": 1484.55, "total_tokens": 37495728} {"current_steps": 177680, "total_steps": 181800, "loss": 0.0809, "lr": 7.821960380132165e-08, "epoch": 19.546754675467547, "percentage": 97.73, "elapsed_time": "7:00:57", "remaining_time": "0:09:45", "throughput": 1484.55, "total_tokens": 37496752} {"current_steps": 177685, "total_steps": 181800, "loss": 0.0014, "lr": 7.803001034980551e-08, "epoch": 19.547304730473048, "percentage": 97.74, "elapsed_time": "7:00:58", "remaining_time": "0:09:44", "throughput": 1484.55, "total_tokens": 37497776} {"current_steps": 177690, "total_steps": 181800, "loss": 0.17, "lr": 7.784064659212553e-08, "epoch": 19.54785478547855, "percentage": 97.74, "elapsed_time": "7:00:59", "remaining_time": "0:09:44", "throughput": 1484.55, "total_tokens": 37498768} {"current_steps": 177695, "total_steps": 181800, "loss": 0.0051, "lr": 7.76515125300331e-08, "epoch": 19.54840484048405, "percentage": 97.74, "elapsed_time": "7:01:00", "remaining_time": "0:09:43", "throughput": 1484.55, "total_tokens": 37499888} {"current_steps": 177700, "total_steps": 181800, "loss": 0.0031, "lr": 7.746260816526851e-08, "epoch": 19.548954895489548, "percentage": 97.74, "elapsed_time": "7:01:00", "remaining_time": "0:09:42", "throughput": 1484.55, "total_tokens": 37500912} {"current_steps": 177705, "total_steps": 181800, "loss": 0.0034, "lr": 7.727393349956924e-08, "epoch": 19.54950495049505, "percentage": 97.75, "elapsed_time": "7:01:01", "remaining_time": "0:09:42", "throughput": 1484.55, "total_tokens": 37501968} {"current_steps": 177710, "total_steps": 181800, "loss": 0.0847, "lr": 7.708548853467834e-08, "epoch": 19.55005500550055, "percentage": 97.75, "elapsed_time": "7:01:02", "remaining_time": "0:09:41", "throughput": 1484.56, "total_tokens": 37503088} {"current_steps": 177715, "total_steps": 181800, "loss": 0.0357, "lr": 7.689727327233054e-08, "epoch": 19.55060506050605, "percentage": 97.75, "elapsed_time": "7:01:02", "remaining_time": "0:09:40", "throughput": 1484.56, "total_tokens": 37504208} {"current_steps": 177720, "total_steps": 181800, "loss": 0.0705, "lr": 7.670928771426334e-08, "epoch": 19.551155115511552, "percentage": 97.76, "elapsed_time": "7:01:03", "remaining_time": "0:09:39", "throughput": 1484.56, "total_tokens": 37505264} {"current_steps": 177725, "total_steps": 181800, "loss": 0.0509, "lr": 7.65215318622059e-08, "epoch": 19.551705170517053, "percentage": 97.76, "elapsed_time": "7:01:04", "remaining_time": "0:09:39", "throughput": 1484.56, "total_tokens": 37506320} {"current_steps": 177730, "total_steps": 181800, "loss": 0.0017, "lr": 7.633400571789018e-08, "epoch": 19.55225522552255, "percentage": 97.76, "elapsed_time": "7:01:04", "remaining_time": "0:09:38", "throughput": 1484.57, "total_tokens": 37507408} {"current_steps": 177735, "total_steps": 181800, "loss": 0.1136, "lr": 7.614670928304535e-08, "epoch": 19.55280528052805, "percentage": 97.76, "elapsed_time": "7:01:05", "remaining_time": "0:09:37", "throughput": 1484.57, "total_tokens": 37508528} {"current_steps": 177740, "total_steps": 181800, "loss": 0.1543, "lr": 7.595964255939502e-08, "epoch": 19.553355335533553, "percentage": 97.77, "elapsed_time": "7:01:06", "remaining_time": "0:09:37", "throughput": 1484.58, "total_tokens": 37509648} {"current_steps": 177745, "total_steps": 181800, "loss": 0.0068, "lr": 7.577280554866561e-08, "epoch": 19.553905390539054, "percentage": 97.77, "elapsed_time": "7:01:06", "remaining_time": "0:09:36", "throughput": 1484.58, "total_tokens": 37510704} {"current_steps": 177750, "total_steps": 181800, "loss": 0.0267, "lr": 7.558619825257796e-08, "epoch": 19.554455445544555, "percentage": 97.77, "elapsed_time": "7:01:07", "remaining_time": "0:09:35", "throughput": 1484.58, "total_tokens": 37511824} {"current_steps": 177755, "total_steps": 181800, "loss": 0.1112, "lr": 7.53998206728529e-08, "epoch": 19.555005500550056, "percentage": 97.78, "elapsed_time": "7:01:08", "remaining_time": "0:09:35", "throughput": 1484.58, "total_tokens": 37512912} {"current_steps": 177760, "total_steps": 181800, "loss": 0.0036, "lr": 7.52136728112085e-08, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "7:01:09", "remaining_time": "0:09:34", "throughput": 1484.58, "total_tokens": 37513936} {"current_steps": 177765, "total_steps": 181800, "loss": 0.0026, "lr": 7.50277546693573e-08, "epoch": 19.556105610561055, "percentage": 97.78, "elapsed_time": "7:01:09", "remaining_time": "0:09:33", "throughput": 1484.59, "total_tokens": 37515024} {"current_steps": 177770, "total_steps": 181800, "loss": 0.0037, "lr": 7.484206624901735e-08, "epoch": 19.556655665566556, "percentage": 97.78, "elapsed_time": "7:01:10", "remaining_time": "0:09:32", "throughput": 1484.58, "total_tokens": 37516016} {"current_steps": 177775, "total_steps": 181800, "loss": 0.0636, "lr": 7.465660755189563e-08, "epoch": 19.557205720572057, "percentage": 97.79, "elapsed_time": "7:01:11", "remaining_time": "0:09:32", "throughput": 1484.59, "total_tokens": 37517104} {"current_steps": 177780, "total_steps": 181800, "loss": 0.0029, "lr": 7.447137857970465e-08, "epoch": 19.557755775577558, "percentage": 97.79, "elapsed_time": "7:01:11", "remaining_time": "0:09:31", "throughput": 1484.59, "total_tokens": 37518224} {"current_steps": 177785, "total_steps": 181800, "loss": 0.0109, "lr": 7.42863793341514e-08, "epoch": 19.55830583058306, "percentage": 97.79, "elapsed_time": "7:01:12", "remaining_time": "0:09:30", "throughput": 1484.59, "total_tokens": 37519312} {"current_steps": 177790, "total_steps": 181800, "loss": 0.0017, "lr": 7.410160981694003e-08, "epoch": 19.55885588558856, "percentage": 97.79, "elapsed_time": "7:01:13", "remaining_time": "0:09:30", "throughput": 1484.6, "total_tokens": 37520464} {"current_steps": 177795, "total_steps": 181800, "loss": 0.0134, "lr": 7.391707002977477e-08, "epoch": 19.55940594059406, "percentage": 97.8, "elapsed_time": "7:01:13", "remaining_time": "0:09:29", "throughput": 1484.6, "total_tokens": 37521520} {"current_steps": 177800, "total_steps": 181800, "loss": 0.0025, "lr": 7.373275997435148e-08, "epoch": 19.55995599559956, "percentage": 97.8, "elapsed_time": "7:01:14", "remaining_time": "0:09:28", "throughput": 1484.6, "total_tokens": 37522608} {"current_steps": 177805, "total_steps": 181800, "loss": 0.0062, "lr": 7.354867965237433e-08, "epoch": 19.56050605060506, "percentage": 97.8, "elapsed_time": "7:01:15", "remaining_time": "0:09:27", "throughput": 1484.6, "total_tokens": 37523600} {"current_steps": 177810, "total_steps": 181800, "loss": 0.007, "lr": 7.336482906553921e-08, "epoch": 19.56105610561056, "percentage": 97.81, "elapsed_time": "7:01:15", "remaining_time": "0:09:27", "throughput": 1484.6, "total_tokens": 37524656} {"current_steps": 177815, "total_steps": 181800, "loss": 0.0023, "lr": 7.318120821553919e-08, "epoch": 19.561606160616062, "percentage": 97.81, "elapsed_time": "7:01:16", "remaining_time": "0:09:26", "throughput": 1484.61, "total_tokens": 37525776} {"current_steps": 177820, "total_steps": 181800, "loss": 0.0016, "lr": 7.299781710406462e-08, "epoch": 19.562156215621563, "percentage": 97.81, "elapsed_time": "7:01:17", "remaining_time": "0:09:25", "throughput": 1484.61, "total_tokens": 37526832} {"current_steps": 177825, "total_steps": 181800, "loss": 0.0038, "lr": 7.281465573281132e-08, "epoch": 19.562706270627064, "percentage": 97.81, "elapsed_time": "7:01:17", "remaining_time": "0:09:25", "throughput": 1484.61, "total_tokens": 37527888} {"current_steps": 177830, "total_steps": 181800, "loss": 0.0058, "lr": 7.26317241034613e-08, "epoch": 19.563256325632562, "percentage": 97.82, "elapsed_time": "7:01:18", "remaining_time": "0:09:24", "throughput": 1484.61, "total_tokens": 37528912} {"current_steps": 177835, "total_steps": 181800, "loss": 0.0792, "lr": 7.244902221770489e-08, "epoch": 19.563806380638063, "percentage": 97.82, "elapsed_time": "7:01:19", "remaining_time": "0:09:23", "throughput": 1484.61, "total_tokens": 37529968} {"current_steps": 177840, "total_steps": 181800, "loss": 0.04, "lr": 7.226655007722405e-08, "epoch": 19.564356435643564, "percentage": 97.82, "elapsed_time": "7:01:20", "remaining_time": "0:09:22", "throughput": 1484.61, "total_tokens": 37531024} {"current_steps": 177845, "total_steps": 181800, "loss": 0.1382, "lr": 7.208430768370078e-08, "epoch": 19.564906490649065, "percentage": 97.82, "elapsed_time": "7:01:20", "remaining_time": "0:09:22", "throughput": 1484.61, "total_tokens": 37532080} {"current_steps": 177850, "total_steps": 181800, "loss": 0.0807, "lr": 7.190229503881707e-08, "epoch": 19.565456545654566, "percentage": 97.83, "elapsed_time": "7:01:21", "remaining_time": "0:09:21", "throughput": 1484.61, "total_tokens": 37533104} {"current_steps": 177855, "total_steps": 181800, "loss": 0.0007, "lr": 7.172051214424657e-08, "epoch": 19.566006600660067, "percentage": 97.83, "elapsed_time": "7:01:22", "remaining_time": "0:09:20", "throughput": 1484.61, "total_tokens": 37534128} {"current_steps": 177860, "total_steps": 181800, "loss": 0.0008, "lr": 7.153895900166574e-08, "epoch": 19.566556655665565, "percentage": 97.83, "elapsed_time": "7:01:22", "remaining_time": "0:09:20", "throughput": 1484.62, "total_tokens": 37535248} {"current_steps": 177865, "total_steps": 181800, "loss": 0.0815, "lr": 7.135763561274822e-08, "epoch": 19.567106710671066, "percentage": 97.84, "elapsed_time": "7:01:23", "remaining_time": "0:09:19", "throughput": 1484.62, "total_tokens": 37536304} {"current_steps": 177870, "total_steps": 181800, "loss": 0.0058, "lr": 7.11765419791649e-08, "epoch": 19.567656765676567, "percentage": 97.84, "elapsed_time": "7:01:24", "remaining_time": "0:09:18", "throughput": 1484.62, "total_tokens": 37537360} {"current_steps": 177875, "total_steps": 181800, "loss": 0.0028, "lr": 7.099567810258667e-08, "epoch": 19.568206820682068, "percentage": 97.84, "elapsed_time": "7:01:24", "remaining_time": "0:09:17", "throughput": 1484.62, "total_tokens": 37538352} {"current_steps": 177880, "total_steps": 181800, "loss": 0.1178, "lr": 7.081504398467886e-08, "epoch": 19.56875687568757, "percentage": 97.84, "elapsed_time": "7:01:25", "remaining_time": "0:09:17", "throughput": 1484.62, "total_tokens": 37539408} {"current_steps": 177885, "total_steps": 181800, "loss": 0.0282, "lr": 7.063463962710959e-08, "epoch": 19.56930693069307, "percentage": 97.85, "elapsed_time": "7:01:26", "remaining_time": "0:09:16", "throughput": 1484.62, "total_tokens": 37540432} {"current_steps": 177890, "total_steps": 181800, "loss": 0.1395, "lr": 7.045446503153307e-08, "epoch": 19.56985698569857, "percentage": 97.85, "elapsed_time": "7:01:26", "remaining_time": "0:09:15", "throughput": 1484.62, "total_tokens": 37541392} {"current_steps": 177895, "total_steps": 181800, "loss": 0.0015, "lr": 7.027452019961744e-08, "epoch": 19.57040704070407, "percentage": 97.85, "elapsed_time": "7:01:27", "remaining_time": "0:09:15", "throughput": 1484.62, "total_tokens": 37542448} {"current_steps": 177900, "total_steps": 181800, "loss": 0.148, "lr": 7.009480513302246e-08, "epoch": 19.57095709570957, "percentage": 97.85, "elapsed_time": "7:01:28", "remaining_time": "0:09:14", "throughput": 1484.62, "total_tokens": 37543472} {"current_steps": 177905, "total_steps": 181800, "loss": 0.0361, "lr": 6.991531983339684e-08, "epoch": 19.57150715071507, "percentage": 97.86, "elapsed_time": "7:01:29", "remaining_time": "0:09:13", "throughput": 1484.62, "total_tokens": 37544528} {"current_steps": 177910, "total_steps": 181800, "loss": 0.0019, "lr": 6.973606430240032e-08, "epoch": 19.572057205720572, "percentage": 97.86, "elapsed_time": "7:01:29", "remaining_time": "0:09:12", "throughput": 1484.62, "total_tokens": 37545584} {"current_steps": 177915, "total_steps": 181800, "loss": 0.0045, "lr": 6.955703854168438e-08, "epoch": 19.572607260726073, "percentage": 97.86, "elapsed_time": "7:01:30", "remaining_time": "0:09:12", "throughput": 1484.62, "total_tokens": 37546640} {"current_steps": 177920, "total_steps": 181800, "loss": 0.003, "lr": 6.937824255290048e-08, "epoch": 19.573157315731574, "percentage": 97.87, "elapsed_time": "7:01:31", "remaining_time": "0:09:11", "throughput": 1484.62, "total_tokens": 37547728} {"current_steps": 177925, "total_steps": 181800, "loss": 0.0019, "lr": 6.919967633769176e-08, "epoch": 19.573707370737075, "percentage": 97.87, "elapsed_time": "7:01:31", "remaining_time": "0:09:10", "throughput": 1484.63, "total_tokens": 37548816} {"current_steps": 177930, "total_steps": 181800, "loss": 0.1031, "lr": 6.902133989770687e-08, "epoch": 19.574257425742573, "percentage": 97.87, "elapsed_time": "7:01:32", "remaining_time": "0:09:10", "throughput": 1484.63, "total_tokens": 37549968} {"current_steps": 177935, "total_steps": 181800, "loss": 0.0379, "lr": 6.884323323458897e-08, "epoch": 19.574807480748074, "percentage": 97.87, "elapsed_time": "7:01:33", "remaining_time": "0:09:09", "throughput": 1484.63, "total_tokens": 37551088} {"current_steps": 177940, "total_steps": 181800, "loss": 0.0074, "lr": 6.866535634998117e-08, "epoch": 19.575357535753575, "percentage": 97.88, "elapsed_time": "7:01:33", "remaining_time": "0:09:08", "throughput": 1484.64, "total_tokens": 37552144} {"current_steps": 177945, "total_steps": 181800, "loss": 0.0042, "lr": 6.848770924552106e-08, "epoch": 19.575907590759076, "percentage": 97.88, "elapsed_time": "7:01:34", "remaining_time": "0:09:07", "throughput": 1484.64, "total_tokens": 37553168} {"current_steps": 177950, "total_steps": 181800, "loss": 0.116, "lr": 6.831029192284343e-08, "epoch": 19.576457645764577, "percentage": 97.88, "elapsed_time": "7:01:35", "remaining_time": "0:09:07", "throughput": 1484.64, "total_tokens": 37554224} {"current_steps": 177955, "total_steps": 181800, "loss": 0.1269, "lr": 6.813310438358866e-08, "epoch": 19.57700770077008, "percentage": 97.89, "elapsed_time": "7:01:35", "remaining_time": "0:09:06", "throughput": 1484.64, "total_tokens": 37555312} {"current_steps": 177960, "total_steps": 181800, "loss": 0.0828, "lr": 6.795614662938876e-08, "epoch": 19.577557755775576, "percentage": 97.89, "elapsed_time": "7:01:36", "remaining_time": "0:09:05", "throughput": 1484.64, "total_tokens": 37556368} {"current_steps": 177965, "total_steps": 181800, "loss": 0.0031, "lr": 6.777941866187576e-08, "epoch": 19.578107810781077, "percentage": 97.89, "elapsed_time": "7:01:37", "remaining_time": "0:09:05", "throughput": 1484.64, "total_tokens": 37557424} {"current_steps": 177970, "total_steps": 181800, "loss": 0.0465, "lr": 6.760292048267058e-08, "epoch": 19.578657865786578, "percentage": 97.89, "elapsed_time": "7:01:37", "remaining_time": "0:09:04", "throughput": 1484.65, "total_tokens": 37558544} {"current_steps": 177975, "total_steps": 181800, "loss": 0.1002, "lr": 6.742665209341081e-08, "epoch": 19.57920792079208, "percentage": 97.9, "elapsed_time": "7:01:38", "remaining_time": "0:09:03", "throughput": 1484.65, "total_tokens": 37559568} {"current_steps": 177980, "total_steps": 181800, "loss": 0.0016, "lr": 6.725061349571183e-08, "epoch": 19.57975797579758, "percentage": 97.9, "elapsed_time": "7:01:39", "remaining_time": "0:09:03", "throughput": 1484.65, "total_tokens": 37560624} {"current_steps": 177985, "total_steps": 181800, "loss": 0.0045, "lr": 6.707480469120009e-08, "epoch": 19.58030803080308, "percentage": 97.9, "elapsed_time": "7:01:40", "remaining_time": "0:09:02", "throughput": 1484.65, "total_tokens": 37561648} {"current_steps": 177990, "total_steps": 181800, "loss": 0.0019, "lr": 6.689922568149931e-08, "epoch": 19.580858085808583, "percentage": 97.9, "elapsed_time": "7:01:40", "remaining_time": "0:09:01", "throughput": 1484.65, "total_tokens": 37562736} {"current_steps": 177995, "total_steps": 181800, "loss": 0.0062, "lr": 6.672387646822209e-08, "epoch": 19.58140814081408, "percentage": 97.91, "elapsed_time": "7:01:41", "remaining_time": "0:09:00", "throughput": 1484.65, "total_tokens": 37563760} {"current_steps": 178000, "total_steps": 181800, "loss": 0.0028, "lr": 6.654875705298657e-08, "epoch": 19.58195819581958, "percentage": 97.91, "elapsed_time": "7:01:42", "remaining_time": "0:09:00", "throughput": 1484.65, "total_tokens": 37564816} {"current_steps": 178005, "total_steps": 181800, "loss": 0.0185, "lr": 6.637386743740537e-08, "epoch": 19.582508250825082, "percentage": 97.91, "elapsed_time": "7:01:42", "remaining_time": "0:08:59", "throughput": 1484.65, "total_tokens": 37565872} {"current_steps": 178010, "total_steps": 181800, "loss": 0.0726, "lr": 6.619920762309384e-08, "epoch": 19.583058305830583, "percentage": 97.92, "elapsed_time": "7:01:43", "remaining_time": "0:08:58", "throughput": 1484.66, "total_tokens": 37566960} {"current_steps": 178015, "total_steps": 181800, "loss": 0.0011, "lr": 6.602477761166181e-08, "epoch": 19.583608360836084, "percentage": 97.92, "elapsed_time": "7:01:44", "remaining_time": "0:08:58", "throughput": 1484.66, "total_tokens": 37568016} {"current_steps": 178020, "total_steps": 181800, "loss": 0.0011, "lr": 6.585057740471079e-08, "epoch": 19.584158415841586, "percentage": 97.92, "elapsed_time": "7:01:44", "remaining_time": "0:08:57", "throughput": 1484.66, "total_tokens": 37569040} {"current_steps": 178025, "total_steps": 181800, "loss": 0.0031, "lr": 6.567660700385337e-08, "epoch": 19.584708470847083, "percentage": 97.92, "elapsed_time": "7:01:45", "remaining_time": "0:08:56", "throughput": 1484.66, "total_tokens": 37570064} {"current_steps": 178030, "total_steps": 181800, "loss": 0.0045, "lr": 6.550286641068826e-08, "epoch": 19.585258525852584, "percentage": 97.93, "elapsed_time": "7:01:46", "remaining_time": "0:08:55", "throughput": 1484.65, "total_tokens": 37571056} {"current_steps": 178035, "total_steps": 181800, "loss": 0.0517, "lr": 6.532935562681974e-08, "epoch": 19.585808580858085, "percentage": 97.93, "elapsed_time": "7:01:46", "remaining_time": "0:08:55", "throughput": 1484.66, "total_tokens": 37572112} {"current_steps": 178040, "total_steps": 181800, "loss": 0.0021, "lr": 6.515607465384654e-08, "epoch": 19.586358635863586, "percentage": 97.93, "elapsed_time": "7:01:47", "remaining_time": "0:08:54", "throughput": 1484.66, "total_tokens": 37573136} {"current_steps": 178045, "total_steps": 181800, "loss": 0.0569, "lr": 6.498302349336461e-08, "epoch": 19.586908690869087, "percentage": 97.93, "elapsed_time": "7:01:48", "remaining_time": "0:08:53", "throughput": 1484.66, "total_tokens": 37574192} {"current_steps": 178050, "total_steps": 181800, "loss": 0.0677, "lr": 6.481020214696709e-08, "epoch": 19.58745874587459, "percentage": 97.94, "elapsed_time": "7:01:49", "remaining_time": "0:08:53", "throughput": 1484.66, "total_tokens": 37575280} {"current_steps": 178055, "total_steps": 181800, "loss": 0.0017, "lr": 6.463761061624995e-08, "epoch": 19.58800880088009, "percentage": 97.94, "elapsed_time": "7:01:49", "remaining_time": "0:08:52", "throughput": 1484.66, "total_tokens": 37576272} {"current_steps": 178060, "total_steps": 181800, "loss": 0.0077, "lr": 6.446524890280358e-08, "epoch": 19.588558855885587, "percentage": 97.94, "elapsed_time": "7:01:50", "remaining_time": "0:08:51", "throughput": 1484.66, "total_tokens": 37577328} {"current_steps": 178065, "total_steps": 181800, "loss": 0.0007, "lr": 6.42931170082156e-08, "epoch": 19.58910891089109, "percentage": 97.95, "elapsed_time": "7:01:51", "remaining_time": "0:08:50", "throughput": 1484.66, "total_tokens": 37578416} {"current_steps": 178070, "total_steps": 181800, "loss": 0.021, "lr": 6.412121493407087e-08, "epoch": 19.58965896589659, "percentage": 97.95, "elapsed_time": "7:01:51", "remaining_time": "0:08:50", "throughput": 1484.67, "total_tokens": 37579504} {"current_steps": 178075, "total_steps": 181800, "loss": 0.0132, "lr": 6.394954268195697e-08, "epoch": 19.59020902090209, "percentage": 97.95, "elapsed_time": "7:01:52", "remaining_time": "0:08:49", "throughput": 1484.67, "total_tokens": 37580592} {"current_steps": 178080, "total_steps": 181800, "loss": 0.0038, "lr": 6.37781002534532e-08, "epoch": 19.59075907590759, "percentage": 97.95, "elapsed_time": "7:01:53", "remaining_time": "0:08:48", "throughput": 1484.67, "total_tokens": 37581616} {"current_steps": 178085, "total_steps": 181800, "loss": 0.0036, "lr": 6.360688765014445e-08, "epoch": 19.591309130913093, "percentage": 97.96, "elapsed_time": "7:01:53", "remaining_time": "0:08:48", "throughput": 1484.67, "total_tokens": 37582640} {"current_steps": 178090, "total_steps": 181800, "loss": 0.0022, "lr": 6.34359048736044e-08, "epoch": 19.59185918591859, "percentage": 97.96, "elapsed_time": "7:01:54", "remaining_time": "0:08:47", "throughput": 1484.67, "total_tokens": 37583696} {"current_steps": 178095, "total_steps": 181800, "loss": 0.0055, "lr": 6.326515192540682e-08, "epoch": 19.59240924092409, "percentage": 97.96, "elapsed_time": "7:01:55", "remaining_time": "0:08:46", "throughput": 1484.67, "total_tokens": 37584720} {"current_steps": 178100, "total_steps": 181800, "loss": 0.0016, "lr": 6.309462880713102e-08, "epoch": 19.592959295929592, "percentage": 97.96, "elapsed_time": "7:01:55", "remaining_time": "0:08:45", "throughput": 1484.67, "total_tokens": 37585744} {"current_steps": 178105, "total_steps": 181800, "loss": 0.0159, "lr": 6.292433552034516e-08, "epoch": 19.593509350935093, "percentage": 97.97, "elapsed_time": "7:01:56", "remaining_time": "0:08:45", "throughput": 1484.67, "total_tokens": 37586832} {"current_steps": 178110, "total_steps": 181800, "loss": 0.0586, "lr": 6.275427206662021e-08, "epoch": 19.594059405940595, "percentage": 97.97, "elapsed_time": "7:01:57", "remaining_time": "0:08:44", "throughput": 1484.67, "total_tokens": 37587856} {"current_steps": 178115, "total_steps": 181800, "loss": 0.0651, "lr": 6.258443844752438e-08, "epoch": 19.594609460946096, "percentage": 97.97, "elapsed_time": "7:01:57", "remaining_time": "0:08:43", "throughput": 1484.67, "total_tokens": 37588944} {"current_steps": 178120, "total_steps": 181800, "loss": 0.0417, "lr": 6.241483466462029e-08, "epoch": 19.595159515951597, "percentage": 97.98, "elapsed_time": "7:01:58", "remaining_time": "0:08:43", "throughput": 1484.67, "total_tokens": 37589968} {"current_steps": 178125, "total_steps": 181800, "loss": 0.0935, "lr": 6.224546071947057e-08, "epoch": 19.595709570957094, "percentage": 97.98, "elapsed_time": "7:01:59", "remaining_time": "0:08:42", "throughput": 1484.67, "total_tokens": 37591024} {"current_steps": 178130, "total_steps": 181800, "loss": 0.0326, "lr": 6.207631661364066e-08, "epoch": 19.596259625962595, "percentage": 97.98, "elapsed_time": "7:02:00", "remaining_time": "0:08:41", "throughput": 1484.68, "total_tokens": 37592112} {"current_steps": 178135, "total_steps": 181800, "loss": 0.0174, "lr": 6.190740234868764e-08, "epoch": 19.596809680968097, "percentage": 97.98, "elapsed_time": "7:02:00", "remaining_time": "0:08:40", "throughput": 1484.68, "total_tokens": 37593200} {"current_steps": 178140, "total_steps": 181800, "loss": 0.0033, "lr": 6.173871792616581e-08, "epoch": 19.597359735973598, "percentage": 97.99, "elapsed_time": "7:02:01", "remaining_time": "0:08:40", "throughput": 1484.68, "total_tokens": 37594224} {"current_steps": 178145, "total_steps": 181800, "loss": 0.1164, "lr": 6.157026334763228e-08, "epoch": 19.5979097909791, "percentage": 97.99, "elapsed_time": "7:02:02", "remaining_time": "0:08:39", "throughput": 1484.68, "total_tokens": 37595312} {"current_steps": 178150, "total_steps": 181800, "loss": 0.0997, "lr": 6.140203861463855e-08, "epoch": 19.5984598459846, "percentage": 97.99, "elapsed_time": "7:02:02", "remaining_time": "0:08:38", "throughput": 1484.68, "total_tokens": 37596336} {"current_steps": 178155, "total_steps": 181800, "loss": 0.0073, "lr": 6.12340437287362e-08, "epoch": 19.599009900990097, "percentage": 98.0, "elapsed_time": "7:02:03", "remaining_time": "0:08:38", "throughput": 1484.68, "total_tokens": 37597424} {"current_steps": 178160, "total_steps": 181800, "loss": 0.0015, "lr": 6.106627869147119e-08, "epoch": 19.5995599559956, "percentage": 98.0, "elapsed_time": "7:02:04", "remaining_time": "0:08:37", "throughput": 1484.68, "total_tokens": 37598448} {"current_steps": 178165, "total_steps": 181800, "loss": 0.1042, "lr": 6.089874350439506e-08, "epoch": 19.6001100110011, "percentage": 98.0, "elapsed_time": "7:02:04", "remaining_time": "0:08:36", "throughput": 1484.69, "total_tokens": 37599504} {"current_steps": 178170, "total_steps": 181800, "loss": 0.0262, "lr": 6.073143816904548e-08, "epoch": 19.6006600660066, "percentage": 98.0, "elapsed_time": "7:02:05", "remaining_time": "0:08:35", "throughput": 1484.69, "total_tokens": 37600624} {"current_steps": 178175, "total_steps": 181800, "loss": 0.0081, "lr": 6.056436268696842e-08, "epoch": 19.6012101210121, "percentage": 98.01, "elapsed_time": "7:02:06", "remaining_time": "0:08:35", "throughput": 1484.69, "total_tokens": 37601616} {"current_steps": 178180, "total_steps": 181800, "loss": 0.005, "lr": 6.039751705970153e-08, "epoch": 19.601760176017603, "percentage": 98.01, "elapsed_time": "7:02:06", "remaining_time": "0:08:34", "throughput": 1484.69, "total_tokens": 37602576} {"current_steps": 178185, "total_steps": 181800, "loss": 0.0677, "lr": 6.02309012887825e-08, "epoch": 19.602310231023104, "percentage": 98.01, "elapsed_time": "7:02:07", "remaining_time": "0:08:33", "throughput": 1484.69, "total_tokens": 37603632} {"current_steps": 178190, "total_steps": 181800, "loss": 0.0409, "lr": 6.006451537574898e-08, "epoch": 19.6028602860286, "percentage": 98.01, "elapsed_time": "7:02:08", "remaining_time": "0:08:33", "throughput": 1484.69, "total_tokens": 37604688} {"current_steps": 178195, "total_steps": 181800, "loss": 0.0045, "lr": 5.989835932213583e-08, "epoch": 19.603410341034103, "percentage": 98.02, "elapsed_time": "7:02:09", "remaining_time": "0:08:32", "throughput": 1484.69, "total_tokens": 37605776} {"current_steps": 178200, "total_steps": 181800, "loss": 0.0019, "lr": 5.973243312946964e-08, "epoch": 19.603960396039604, "percentage": 98.02, "elapsed_time": "7:02:09", "remaining_time": "0:08:31", "throughput": 1484.69, "total_tokens": 37606832} {"current_steps": 178205, "total_steps": 181800, "loss": 0.0073, "lr": 5.9566736799282486e-08, "epoch": 19.604510451045105, "percentage": 98.02, "elapsed_time": "7:02:10", "remaining_time": "0:08:31", "throughput": 1484.69, "total_tokens": 37607920} {"current_steps": 178210, "total_steps": 181800, "loss": 0.0528, "lr": 5.9401270333100945e-08, "epoch": 19.605060506050606, "percentage": 98.03, "elapsed_time": "7:02:11", "remaining_time": "0:08:30", "throughput": 1484.69, "total_tokens": 37608912} {"current_steps": 178215, "total_steps": 181800, "loss": 0.0225, "lr": 5.923603373245157e-08, "epoch": 19.605610561056107, "percentage": 98.03, "elapsed_time": "7:02:11", "remaining_time": "0:08:29", "throughput": 1484.7, "total_tokens": 37610032} {"current_steps": 178220, "total_steps": 181800, "loss": 0.076, "lr": 5.907102699885259e-08, "epoch": 19.606160616061608, "percentage": 98.03, "elapsed_time": "7:02:12", "remaining_time": "0:08:28", "throughput": 1484.7, "total_tokens": 37611120} {"current_steps": 178225, "total_steps": 181800, "loss": 0.0019, "lr": 5.8906250133830556e-08, "epoch": 19.606710671067106, "percentage": 98.03, "elapsed_time": "7:02:13", "remaining_time": "0:08:28", "throughput": 1484.7, "total_tokens": 37612240} {"current_steps": 178230, "total_steps": 181800, "loss": 0.061, "lr": 5.87417031389037e-08, "epoch": 19.607260726072607, "percentage": 98.04, "elapsed_time": "7:02:13", "remaining_time": "0:08:27", "throughput": 1484.7, "total_tokens": 37613264} {"current_steps": 178235, "total_steps": 181800, "loss": 0.0796, "lr": 5.857738601558471e-08, "epoch": 19.607810781078108, "percentage": 98.04, "elapsed_time": "7:02:14", "remaining_time": "0:08:26", "throughput": 1484.71, "total_tokens": 37614352} {"current_steps": 178240, "total_steps": 181800, "loss": 0.0051, "lr": 5.8413298765389034e-08, "epoch": 19.60836083608361, "percentage": 98.04, "elapsed_time": "7:02:15", "remaining_time": "0:08:26", "throughput": 1484.71, "total_tokens": 37615440} {"current_steps": 178245, "total_steps": 181800, "loss": 0.0874, "lr": 5.824944138982935e-08, "epoch": 19.60891089108911, "percentage": 98.04, "elapsed_time": "7:02:15", "remaining_time": "0:08:25", "throughput": 1484.71, "total_tokens": 37616528} {"current_steps": 178250, "total_steps": 181800, "loss": 0.0015, "lr": 5.808581389041834e-08, "epoch": 19.60946094609461, "percentage": 98.05, "elapsed_time": "7:02:16", "remaining_time": "0:08:24", "throughput": 1484.71, "total_tokens": 37617552} {"current_steps": 178255, "total_steps": 181800, "loss": 0.008, "lr": 5.792241626866035e-08, "epoch": 19.61001100110011, "percentage": 98.05, "elapsed_time": "7:02:17", "remaining_time": "0:08:23", "throughput": 1484.71, "total_tokens": 37618576} {"current_steps": 178260, "total_steps": 181800, "loss": 0.0029, "lr": 5.775924852606529e-08, "epoch": 19.61056105610561, "percentage": 98.05, "elapsed_time": "7:02:18", "remaining_time": "0:08:23", "throughput": 1484.71, "total_tokens": 37619664} {"current_steps": 178265, "total_steps": 181800, "loss": 0.1052, "lr": 5.759631066413196e-08, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "7:02:18", "remaining_time": "0:08:22", "throughput": 1484.72, "total_tokens": 37620848} {"current_steps": 178270, "total_steps": 181800, "loss": 0.0388, "lr": 5.7433602684367485e-08, "epoch": 19.611661166116612, "percentage": 98.06, "elapsed_time": "7:02:19", "remaining_time": "0:08:21", "throughput": 1484.72, "total_tokens": 37621872} {"current_steps": 178275, "total_steps": 181800, "loss": 0.0044, "lr": 5.7271124588267886e-08, "epoch": 19.612211221122113, "percentage": 98.06, "elapsed_time": "7:02:20", "remaining_time": "0:08:21", "throughput": 1484.72, "total_tokens": 37622928} {"current_steps": 178280, "total_steps": 181800, "loss": 0.0027, "lr": 5.7108876377331975e-08, "epoch": 19.612761276127614, "percentage": 98.06, "elapsed_time": "7:02:20", "remaining_time": "0:08:20", "throughput": 1484.72, "total_tokens": 37623984} {"current_steps": 178285, "total_steps": 181800, "loss": 0.0027, "lr": 5.6946858053053e-08, "epoch": 19.61331133113311, "percentage": 98.07, "elapsed_time": "7:02:21", "remaining_time": "0:08:19", "throughput": 1484.72, "total_tokens": 37624976} {"current_steps": 178290, "total_steps": 181800, "loss": 0.0035, "lr": 5.678506961692698e-08, "epoch": 19.613861386138613, "percentage": 98.07, "elapsed_time": "7:02:22", "remaining_time": "0:08:18", "throughput": 1484.72, "total_tokens": 37626064} {"current_steps": 178295, "total_steps": 181800, "loss": 0.0034, "lr": 5.662351107044439e-08, "epoch": 19.614411441144114, "percentage": 98.07, "elapsed_time": "7:02:22", "remaining_time": "0:08:18", "throughput": 1484.72, "total_tokens": 37627120} {"current_steps": 178300, "total_steps": 181800, "loss": 0.0381, "lr": 5.646218241509571e-08, "epoch": 19.614961496149615, "percentage": 98.07, "elapsed_time": "7:02:23", "remaining_time": "0:08:17", "throughput": 1484.73, "total_tokens": 37628272} {"current_steps": 178305, "total_steps": 181800, "loss": 0.0095, "lr": 5.630108365236308e-08, "epoch": 19.615511551155116, "percentage": 98.08, "elapsed_time": "7:02:24", "remaining_time": "0:08:16", "throughput": 1484.73, "total_tokens": 37629328} {"current_steps": 178310, "total_steps": 181800, "loss": 0.0008, "lr": 5.614021478373699e-08, "epoch": 19.616061606160617, "percentage": 98.08, "elapsed_time": "7:02:24", "remaining_time": "0:08:16", "throughput": 1484.73, "total_tokens": 37630352} {"current_steps": 178315, "total_steps": 181800, "loss": 0.0438, "lr": 5.597957581069402e-08, "epoch": 19.616611661166118, "percentage": 98.08, "elapsed_time": "7:02:25", "remaining_time": "0:08:15", "throughput": 1484.73, "total_tokens": 37631472} {"current_steps": 178320, "total_steps": 181800, "loss": 0.0437, "lr": 5.5819166734719097e-08, "epoch": 19.617161716171616, "percentage": 98.09, "elapsed_time": "7:02:26", "remaining_time": "0:08:14", "throughput": 1484.73, "total_tokens": 37632528} {"current_steps": 178325, "total_steps": 181800, "loss": 0.088, "lr": 5.56589875572916e-08, "epoch": 19.617711771177117, "percentage": 98.09, "elapsed_time": "7:02:27", "remaining_time": "0:08:13", "throughput": 1484.73, "total_tokens": 37633584} {"current_steps": 178330, "total_steps": 181800, "loss": 0.0423, "lr": 5.549903827988534e-08, "epoch": 19.618261826182618, "percentage": 98.09, "elapsed_time": "7:02:27", "remaining_time": "0:08:13", "throughput": 1484.74, "total_tokens": 37634640} {"current_steps": 178335, "total_steps": 181800, "loss": 0.0024, "lr": 5.5339318903971374e-08, "epoch": 19.61881188118812, "percentage": 98.09, "elapsed_time": "7:02:28", "remaining_time": "0:08:12", "throughput": 1484.74, "total_tokens": 37635696} {"current_steps": 178340, "total_steps": 181800, "loss": 0.0497, "lr": 5.5179829431029064e-08, "epoch": 19.61936193619362, "percentage": 98.1, "elapsed_time": "7:02:29", "remaining_time": "0:08:11", "throughput": 1484.74, "total_tokens": 37636784} {"current_steps": 178345, "total_steps": 181800, "loss": 0.005, "lr": 5.502056986252391e-08, "epoch": 19.61991199119912, "percentage": 98.1, "elapsed_time": "7:02:29", "remaining_time": "0:08:11", "throughput": 1484.74, "total_tokens": 37637808} {"current_steps": 178350, "total_steps": 181800, "loss": 0.1424, "lr": 5.486154019992418e-08, "epoch": 19.620462046204622, "percentage": 98.1, "elapsed_time": "7:02:30", "remaining_time": "0:08:10", "throughput": 1484.74, "total_tokens": 37638896} {"current_steps": 178355, "total_steps": 181800, "loss": 0.0023, "lr": 5.470274044469537e-08, "epoch": 19.62101210121012, "percentage": 98.11, "elapsed_time": "7:02:31", "remaining_time": "0:08:09", "throughput": 1484.75, "total_tokens": 37640016} {"current_steps": 178360, "total_steps": 181800, "loss": 0.0013, "lr": 5.454417059830019e-08, "epoch": 19.62156215621562, "percentage": 98.11, "elapsed_time": "7:02:31", "remaining_time": "0:08:08", "throughput": 1484.74, "total_tokens": 37640976} {"current_steps": 178365, "total_steps": 181800, "loss": 0.1521, "lr": 5.438583066220415e-08, "epoch": 19.622112211221122, "percentage": 98.11, "elapsed_time": "7:02:32", "remaining_time": "0:08:08", "throughput": 1484.74, "total_tokens": 37642032} {"current_steps": 178370, "total_steps": 181800, "loss": 0.0426, "lr": 5.422772063786163e-08, "epoch": 19.622662266226623, "percentage": 98.11, "elapsed_time": "7:02:33", "remaining_time": "0:08:07", "throughput": 1484.75, "total_tokens": 37643120} {"current_steps": 178375, "total_steps": 181800, "loss": 0.0122, "lr": 5.406984052673258e-08, "epoch": 19.623212321232124, "percentage": 98.12, "elapsed_time": "7:02:33", "remaining_time": "0:08:06", "throughput": 1484.75, "total_tokens": 37644112} {"current_steps": 178380, "total_steps": 181800, "loss": 0.0013, "lr": 5.3912190330271395e-08, "epoch": 19.623762376237625, "percentage": 98.12, "elapsed_time": "7:02:34", "remaining_time": "0:08:06", "throughput": 1484.75, "total_tokens": 37645168} {"current_steps": 178385, "total_steps": 181800, "loss": 0.0411, "lr": 5.375477004993246e-08, "epoch": 19.624312431243123, "percentage": 98.12, "elapsed_time": "7:02:35", "remaining_time": "0:08:05", "throughput": 1484.75, "total_tokens": 37646256} {"current_steps": 178390, "total_steps": 181800, "loss": 0.0419, "lr": 5.359757968716461e-08, "epoch": 19.624862486248624, "percentage": 98.12, "elapsed_time": "7:02:35", "remaining_time": "0:08:04", "throughput": 1484.75, "total_tokens": 37647376} {"current_steps": 178395, "total_steps": 181800, "loss": 0.0071, "lr": 5.34406192434167e-08, "epoch": 19.625412541254125, "percentage": 98.13, "elapsed_time": "7:02:36", "remaining_time": "0:08:03", "throughput": 1484.76, "total_tokens": 37648496} {"current_steps": 178400, "total_steps": 181800, "loss": 0.0273, "lr": 5.3283888720137565e-08, "epoch": 19.625962596259626, "percentage": 98.13, "elapsed_time": "7:02:37", "remaining_time": "0:08:03", "throughput": 1484.76, "total_tokens": 37649520} {"current_steps": 178405, "total_steps": 181800, "loss": 0.1355, "lr": 5.312738811877049e-08, "epoch": 19.626512651265127, "percentage": 98.13, "elapsed_time": "7:02:38", "remaining_time": "0:08:02", "throughput": 1484.76, "total_tokens": 37650576} {"current_steps": 178410, "total_steps": 181800, "loss": 0.0082, "lr": 5.2971117440756e-08, "epoch": 19.627062706270628, "percentage": 98.14, "elapsed_time": "7:02:38", "remaining_time": "0:08:01", "throughput": 1484.76, "total_tokens": 37651696} {"current_steps": 178415, "total_steps": 181800, "loss": 0.0012, "lr": 5.28150766875346e-08, "epoch": 19.62761276127613, "percentage": 98.14, "elapsed_time": "7:02:39", "remaining_time": "0:08:01", "throughput": 1484.76, "total_tokens": 37652752} {"current_steps": 178420, "total_steps": 181800, "loss": 0.0015, "lr": 5.265926586054959e-08, "epoch": 19.628162816281627, "percentage": 98.14, "elapsed_time": "7:02:40", "remaining_time": "0:08:00", "throughput": 1484.76, "total_tokens": 37653808} {"current_steps": 178425, "total_steps": 181800, "loss": 0.1081, "lr": 5.250368496123037e-08, "epoch": 19.628712871287128, "percentage": 98.14, "elapsed_time": "7:02:40", "remaining_time": "0:07:59", "throughput": 1484.77, "total_tokens": 37654896} {"current_steps": 178430, "total_steps": 181800, "loss": 0.0042, "lr": 5.234833399101469e-08, "epoch": 19.62926292629263, "percentage": 98.15, "elapsed_time": "7:02:41", "remaining_time": "0:07:59", "throughput": 1484.77, "total_tokens": 37655984} {"current_steps": 178435, "total_steps": 181800, "loss": 0.0021, "lr": 5.219321295133472e-08, "epoch": 19.62981298129813, "percentage": 98.15, "elapsed_time": "7:02:42", "remaining_time": "0:07:58", "throughput": 1484.77, "total_tokens": 37657008} {"current_steps": 178440, "total_steps": 181800, "loss": 0.0014, "lr": 5.203832184361712e-08, "epoch": 19.63036303630363, "percentage": 98.15, "elapsed_time": "7:02:42", "remaining_time": "0:07:57", "throughput": 1484.77, "total_tokens": 37658032} {"current_steps": 178445, "total_steps": 181800, "loss": 0.0399, "lr": 5.188366066929129e-08, "epoch": 19.630913091309132, "percentage": 98.15, "elapsed_time": "7:02:43", "remaining_time": "0:07:56", "throughput": 1484.77, "total_tokens": 37659088} {"current_steps": 178450, "total_steps": 181800, "loss": 0.0421, "lr": 5.1729229429783865e-08, "epoch": 19.63146314631463, "percentage": 98.16, "elapsed_time": "7:02:44", "remaining_time": "0:07:56", "throughput": 1484.77, "total_tokens": 37660176} {"current_steps": 178455, "total_steps": 181800, "loss": 0.0011, "lr": 5.157502812651594e-08, "epoch": 19.63201320132013, "percentage": 98.16, "elapsed_time": "7:02:44", "remaining_time": "0:07:55", "throughput": 1484.77, "total_tokens": 37661232} {"current_steps": 178460, "total_steps": 181800, "loss": 0.0056, "lr": 5.142105676090858e-08, "epoch": 19.632563256325632, "percentage": 98.16, "elapsed_time": "7:02:45", "remaining_time": "0:07:54", "throughput": 1484.77, "total_tokens": 37662256} {"current_steps": 178465, "total_steps": 181800, "loss": 0.0006, "lr": 5.1267315334382895e-08, "epoch": 19.633113311331133, "percentage": 98.17, "elapsed_time": "7:02:46", "remaining_time": "0:07:54", "throughput": 1484.77, "total_tokens": 37663280} {"current_steps": 178470, "total_steps": 181800, "loss": 0.0012, "lr": 5.11138038483544e-08, "epoch": 19.633663366336634, "percentage": 98.17, "elapsed_time": "7:02:47", "remaining_time": "0:07:53", "throughput": 1484.77, "total_tokens": 37664368} {"current_steps": 178475, "total_steps": 181800, "loss": 0.0694, "lr": 5.0960522304235867e-08, "epoch": 19.634213421342135, "percentage": 98.17, "elapsed_time": "7:02:47", "remaining_time": "0:07:52", "throughput": 1484.78, "total_tokens": 37665520} {"current_steps": 178480, "total_steps": 181800, "loss": 0.0712, "lr": 5.08074707034456e-08, "epoch": 19.634763476347636, "percentage": 98.17, "elapsed_time": "7:02:48", "remaining_time": "0:07:51", "throughput": 1484.78, "total_tokens": 37666640} {"current_steps": 178485, "total_steps": 181800, "loss": 0.003, "lr": 5.0654649047390815e-08, "epoch": 19.635313531353134, "percentage": 98.18, "elapsed_time": "7:02:49", "remaining_time": "0:07:51", "throughput": 1484.78, "total_tokens": 37667696} {"current_steps": 178490, "total_steps": 181800, "loss": 0.0112, "lr": 5.050205733748148e-08, "epoch": 19.635863586358635, "percentage": 98.18, "elapsed_time": "7:02:49", "remaining_time": "0:07:50", "throughput": 1484.78, "total_tokens": 37668688} {"current_steps": 178495, "total_steps": 181800, "loss": 0.0023, "lr": 5.0349695575122033e-08, "epoch": 19.636413641364136, "percentage": 98.18, "elapsed_time": "7:02:50", "remaining_time": "0:07:49", "throughput": 1484.79, "total_tokens": 37669808} {"current_steps": 178500, "total_steps": 181800, "loss": 0.0308, "lr": 5.019756376171414e-08, "epoch": 19.636963696369637, "percentage": 98.18, "elapsed_time": "7:02:51", "remaining_time": "0:07:49", "throughput": 1484.79, "total_tokens": 37670864} {"current_steps": 178505, "total_steps": 181800, "loss": 0.0008, "lr": 5.0045661898667776e-08, "epoch": 19.63751375137514, "percentage": 98.19, "elapsed_time": "7:02:51", "remaining_time": "0:07:48", "throughput": 1484.79, "total_tokens": 37671920} {"current_steps": 178510, "total_steps": 181800, "loss": 0.0031, "lr": 4.989398998737349e-08, "epoch": 19.63806380638064, "percentage": 98.19, "elapsed_time": "7:02:52", "remaining_time": "0:07:47", "throughput": 1484.8, "total_tokens": 37673104} {"current_steps": 178515, "total_steps": 181800, "loss": 0.0292, "lr": 4.97425480292385e-08, "epoch": 19.638613861386137, "percentage": 98.19, "elapsed_time": "7:02:53", "remaining_time": "0:07:46", "throughput": 1484.8, "total_tokens": 37674160} {"current_steps": 178520, "total_steps": 181800, "loss": 0.0017, "lr": 4.959133602565336e-08, "epoch": 19.639163916391638, "percentage": 98.2, "elapsed_time": "7:02:53", "remaining_time": "0:07:46", "throughput": 1484.8, "total_tokens": 37675312} {"current_steps": 178525, "total_steps": 181800, "loss": 0.0034, "lr": 4.944035397801139e-08, "epoch": 19.63971397139714, "percentage": 98.2, "elapsed_time": "7:02:54", "remaining_time": "0:07:45", "throughput": 1484.8, "total_tokens": 37676400} {"current_steps": 178530, "total_steps": 181800, "loss": 0.0019, "lr": 4.928960188770593e-08, "epoch": 19.64026402640264, "percentage": 98.2, "elapsed_time": "7:02:55", "remaining_time": "0:07:44", "throughput": 1484.81, "total_tokens": 37677520} {"current_steps": 178535, "total_steps": 181800, "loss": 0.0058, "lr": 4.913907975612475e-08, "epoch": 19.64081408140814, "percentage": 98.2, "elapsed_time": "7:02:56", "remaining_time": "0:07:44", "throughput": 1484.81, "total_tokens": 37678608} {"current_steps": 178540, "total_steps": 181800, "loss": 0.0349, "lr": 4.8988787584655635e-08, "epoch": 19.641364136413642, "percentage": 98.21, "elapsed_time": "7:02:56", "remaining_time": "0:07:43", "throughput": 1484.81, "total_tokens": 37679568} {"current_steps": 178545, "total_steps": 181800, "loss": 0.002, "lr": 4.883872537468637e-08, "epoch": 19.641914191419144, "percentage": 98.21, "elapsed_time": "7:02:57", "remaining_time": "0:07:42", "throughput": 1484.81, "total_tokens": 37680624} {"current_steps": 178550, "total_steps": 181800, "loss": 0.0062, "lr": 4.868889312759639e-08, "epoch": 19.64246424642464, "percentage": 98.21, "elapsed_time": "7:02:58", "remaining_time": "0:07:41", "throughput": 1484.81, "total_tokens": 37681712} {"current_steps": 178555, "total_steps": 181800, "loss": 0.0837, "lr": 4.8539290844767937e-08, "epoch": 19.643014301430142, "percentage": 98.22, "elapsed_time": "7:02:58", "remaining_time": "0:07:41", "throughput": 1484.81, "total_tokens": 37682832} {"current_steps": 178560, "total_steps": 181800, "loss": 0.0012, "lr": 4.838991852758046e-08, "epoch": 19.643564356435643, "percentage": 98.22, "elapsed_time": "7:02:59", "remaining_time": "0:07:40", "throughput": 1484.81, "total_tokens": 37683792} {"current_steps": 178565, "total_steps": 181800, "loss": 0.0534, "lr": 4.824077617741063e-08, "epoch": 19.644114411441144, "percentage": 98.22, "elapsed_time": "7:03:00", "remaining_time": "0:07:39", "throughput": 1484.81, "total_tokens": 37684816} {"current_steps": 178570, "total_steps": 181800, "loss": 0.0366, "lr": 4.809186379563235e-08, "epoch": 19.644664466446645, "percentage": 98.22, "elapsed_time": "7:03:00", "remaining_time": "0:07:39", "throughput": 1484.82, "total_tokens": 37685936} {"current_steps": 178575, "total_steps": 181800, "loss": 0.0044, "lr": 4.794318138361675e-08, "epoch": 19.645214521452147, "percentage": 98.23, "elapsed_time": "7:03:01", "remaining_time": "0:07:38", "throughput": 1484.82, "total_tokens": 37686960} {"current_steps": 178580, "total_steps": 181800, "loss": 0.0278, "lr": 4.779472894273773e-08, "epoch": 19.645764576457644, "percentage": 98.23, "elapsed_time": "7:03:02", "remaining_time": "0:07:37", "throughput": 1484.82, "total_tokens": 37688080} {"current_steps": 178585, "total_steps": 181800, "loss": 0.0022, "lr": 4.764650647436086e-08, "epoch": 19.646314631463145, "percentage": 98.23, "elapsed_time": "7:03:02", "remaining_time": "0:07:36", "throughput": 1484.82, "total_tokens": 37689072} {"current_steps": 178590, "total_steps": 181800, "loss": 0.0111, "lr": 4.7498513979851725e-08, "epoch": 19.646864686468646, "percentage": 98.23, "elapsed_time": "7:03:03", "remaining_time": "0:07:36", "throughput": 1484.82, "total_tokens": 37690096} {"current_steps": 178595, "total_steps": 181800, "loss": 0.0031, "lr": 4.735075146057588e-08, "epoch": 19.647414741474147, "percentage": 98.24, "elapsed_time": "7:03:04", "remaining_time": "0:07:35", "throughput": 1484.82, "total_tokens": 37691120} {"current_steps": 178600, "total_steps": 181800, "loss": 0.0026, "lr": 4.720321891789614e-08, "epoch": 19.64796479647965, "percentage": 98.24, "elapsed_time": "7:03:05", "remaining_time": "0:07:34", "throughput": 1484.82, "total_tokens": 37692144} {"current_steps": 178605, "total_steps": 181800, "loss": 0.0875, "lr": 4.7055916353169746e-08, "epoch": 19.64851485148515, "percentage": 98.24, "elapsed_time": "7:03:05", "remaining_time": "0:07:34", "throughput": 1484.82, "total_tokens": 37693136} {"current_steps": 178610, "total_steps": 181800, "loss": 0.0065, "lr": 4.6908843767756725e-08, "epoch": 19.64906490649065, "percentage": 98.25, "elapsed_time": "7:03:06", "remaining_time": "0:07:33", "throughput": 1484.82, "total_tokens": 37694224} {"current_steps": 178615, "total_steps": 181800, "loss": 0.1049, "lr": 4.6762001163008773e-08, "epoch": 19.649614961496148, "percentage": 98.25, "elapsed_time": "7:03:07", "remaining_time": "0:07:32", "throughput": 1484.82, "total_tokens": 37695280} {"current_steps": 178620, "total_steps": 181800, "loss": 0.0257, "lr": 4.661538854028313e-08, "epoch": 19.65016501650165, "percentage": 98.25, "elapsed_time": "7:03:07", "remaining_time": "0:07:31", "throughput": 1484.82, "total_tokens": 37696368} {"current_steps": 178625, "total_steps": 181800, "loss": 0.0021, "lr": 4.646900590092873e-08, "epoch": 19.65071507150715, "percentage": 98.25, "elapsed_time": "7:03:08", "remaining_time": "0:07:31", "throughput": 1484.83, "total_tokens": 37697456} {"current_steps": 178630, "total_steps": 181800, "loss": 0.0058, "lr": 4.632285324629726e-08, "epoch": 19.65126512651265, "percentage": 98.26, "elapsed_time": "7:03:09", "remaining_time": "0:07:30", "throughput": 1484.83, "total_tokens": 37698512} {"current_steps": 178635, "total_steps": 181800, "loss": 0.0505, "lr": 4.617693057773209e-08, "epoch": 19.651815181518153, "percentage": 98.26, "elapsed_time": "7:03:09", "remaining_time": "0:07:29", "throughput": 1484.83, "total_tokens": 37699568} {"current_steps": 178640, "total_steps": 181800, "loss": 0.1162, "lr": 4.603123789658215e-08, "epoch": 19.652365236523654, "percentage": 98.26, "elapsed_time": "7:03:10", "remaining_time": "0:07:29", "throughput": 1484.83, "total_tokens": 37700560} {"current_steps": 178645, "total_steps": 181800, "loss": 0.0774, "lr": 4.588577520418802e-08, "epoch": 19.652915291529155, "percentage": 98.26, "elapsed_time": "7:03:11", "remaining_time": "0:07:28", "throughput": 1484.83, "total_tokens": 37701616} {"current_steps": 178650, "total_steps": 181800, "loss": 0.069, "lr": 4.574054250188753e-08, "epoch": 19.653465346534652, "percentage": 98.27, "elapsed_time": "7:03:11", "remaining_time": "0:07:27", "throughput": 1484.83, "total_tokens": 37702640} {"current_steps": 178655, "total_steps": 181800, "loss": 0.006, "lr": 4.559553979102405e-08, "epoch": 19.654015401540153, "percentage": 98.27, "elapsed_time": "7:03:12", "remaining_time": "0:07:27", "throughput": 1484.83, "total_tokens": 37703696} {"current_steps": 178660, "total_steps": 181800, "loss": 0.0948, "lr": 4.545076707293538e-08, "epoch": 19.654565456545654, "percentage": 98.27, "elapsed_time": "7:03:13", "remaining_time": "0:07:26", "throughput": 1484.83, "total_tokens": 37704720} {"current_steps": 178665, "total_steps": 181800, "loss": 0.0104, "lr": 4.5306224348948266e-08, "epoch": 19.655115511551156, "percentage": 98.28, "elapsed_time": "7:03:13", "remaining_time": "0:07:25", "throughput": 1484.83, "total_tokens": 37705808} {"current_steps": 178670, "total_steps": 181800, "loss": 0.0861, "lr": 4.516191162040051e-08, "epoch": 19.655665566556657, "percentage": 98.28, "elapsed_time": "7:03:14", "remaining_time": "0:07:24", "throughput": 1484.83, "total_tokens": 37706800} {"current_steps": 178675, "total_steps": 181800, "loss": 0.0248, "lr": 4.501782888862161e-08, "epoch": 19.656215621562158, "percentage": 98.28, "elapsed_time": "7:03:15", "remaining_time": "0:07:24", "throughput": 1484.83, "total_tokens": 37707824} {"current_steps": 178680, "total_steps": 181800, "loss": 0.0084, "lr": 4.487397615493827e-08, "epoch": 19.656765676567655, "percentage": 98.28, "elapsed_time": "7:03:16", "remaining_time": "0:07:23", "throughput": 1484.83, "total_tokens": 37708880} {"current_steps": 178685, "total_steps": 181800, "loss": 0.0726, "lr": 4.473035342067722e-08, "epoch": 19.657315731573156, "percentage": 98.29, "elapsed_time": "7:03:16", "remaining_time": "0:07:22", "throughput": 1484.83, "total_tokens": 37709968} {"current_steps": 178690, "total_steps": 181800, "loss": 0.0029, "lr": 4.4586960687162395e-08, "epoch": 19.657865786578657, "percentage": 98.29, "elapsed_time": "7:03:17", "remaining_time": "0:07:22", "throughput": 1484.83, "total_tokens": 37710992} {"current_steps": 178695, "total_steps": 181800, "loss": 0.0015, "lr": 4.444379795571496e-08, "epoch": 19.65841584158416, "percentage": 98.29, "elapsed_time": "7:03:18", "remaining_time": "0:07:21", "throughput": 1484.84, "total_tokens": 37712080} {"current_steps": 178700, "total_steps": 181800, "loss": 0.0359, "lr": 4.430086522765331e-08, "epoch": 19.65896589658966, "percentage": 98.29, "elapsed_time": "7:03:18", "remaining_time": "0:07:20", "throughput": 1484.84, "total_tokens": 37713168} {"current_steps": 178705, "total_steps": 181800, "loss": 0.0459, "lr": 4.415816250429583e-08, "epoch": 19.65951595159516, "percentage": 98.3, "elapsed_time": "7:03:19", "remaining_time": "0:07:19", "throughput": 1484.84, "total_tokens": 37714224} {"current_steps": 178710, "total_steps": 181800, "loss": 0.0178, "lr": 4.401568978695536e-08, "epoch": 19.66006600660066, "percentage": 98.3, "elapsed_time": "7:03:20", "remaining_time": "0:07:19", "throughput": 1484.84, "total_tokens": 37715312} {"current_steps": 178715, "total_steps": 181800, "loss": 0.0016, "lr": 4.387344707695029e-08, "epoch": 19.66061606160616, "percentage": 98.3, "elapsed_time": "7:03:20", "remaining_time": "0:07:18", "throughput": 1484.84, "total_tokens": 37716368} {"current_steps": 178720, "total_steps": 181800, "loss": 0.0125, "lr": 4.373143437558791e-08, "epoch": 19.66116611661166, "percentage": 98.31, "elapsed_time": "7:03:21", "remaining_time": "0:07:17", "throughput": 1484.85, "total_tokens": 37717424} {"current_steps": 178725, "total_steps": 181800, "loss": 0.0015, "lr": 4.3589651684175504e-08, "epoch": 19.66171617161716, "percentage": 98.31, "elapsed_time": "7:03:22", "remaining_time": "0:07:17", "throughput": 1484.85, "total_tokens": 37718512} {"current_steps": 178730, "total_steps": 181800, "loss": 0.0685, "lr": 4.344809900402591e-08, "epoch": 19.662266226622663, "percentage": 98.31, "elapsed_time": "7:03:22", "remaining_time": "0:07:16", "throughput": 1484.85, "total_tokens": 37719536} {"current_steps": 178735, "total_steps": 181800, "loss": 0.0056, "lr": 4.330677633643809e-08, "epoch": 19.662816281628164, "percentage": 98.31, "elapsed_time": "7:03:23", "remaining_time": "0:07:15", "throughput": 1484.85, "total_tokens": 37720528} {"current_steps": 178740, "total_steps": 181800, "loss": 0.0031, "lr": 4.316568368271379e-08, "epoch": 19.663366336633665, "percentage": 98.32, "elapsed_time": "7:03:24", "remaining_time": "0:07:14", "throughput": 1484.85, "total_tokens": 37721552} {"current_steps": 178745, "total_steps": 181800, "loss": 0.1178, "lr": 4.302482104416028e-08, "epoch": 19.663916391639162, "percentage": 98.32, "elapsed_time": "7:03:25", "remaining_time": "0:07:14", "throughput": 1484.85, "total_tokens": 37722672} {"current_steps": 178750, "total_steps": 181800, "loss": 0.0164, "lr": 4.288418842206821e-08, "epoch": 19.664466446644663, "percentage": 98.32, "elapsed_time": "7:03:25", "remaining_time": "0:07:13", "throughput": 1484.85, "total_tokens": 37723728} {"current_steps": 178755, "total_steps": 181800, "loss": 0.0027, "lr": 4.27437858177393e-08, "epoch": 19.665016501650165, "percentage": 98.33, "elapsed_time": "7:03:26", "remaining_time": "0:07:12", "throughput": 1484.85, "total_tokens": 37724752} {"current_steps": 178760, "total_steps": 181800, "loss": 0.0557, "lr": 4.26036132324642e-08, "epoch": 19.665566556655666, "percentage": 98.33, "elapsed_time": "7:03:27", "remaining_time": "0:07:12", "throughput": 1484.86, "total_tokens": 37725840} {"current_steps": 178765, "total_steps": 181800, "loss": 0.0056, "lr": 4.246367066753631e-08, "epoch": 19.666116611661167, "percentage": 98.33, "elapsed_time": "7:03:27", "remaining_time": "0:07:11", "throughput": 1484.86, "total_tokens": 37726960} {"current_steps": 178770, "total_steps": 181800, "loss": 0.0513, "lr": 4.23239581242435e-08, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "7:03:28", "remaining_time": "0:07:10", "throughput": 1484.86, "total_tokens": 37728048} {"current_steps": 178775, "total_steps": 181800, "loss": 0.0588, "lr": 4.2184475603876395e-08, "epoch": 19.66721672167217, "percentage": 98.34, "elapsed_time": "7:03:29", "remaining_time": "0:07:09", "throughput": 1484.87, "total_tokens": 37729136} {"current_steps": 178780, "total_steps": 181800, "loss": 0.0091, "lr": 4.2045223107717304e-08, "epoch": 19.667766776677666, "percentage": 98.34, "elapsed_time": "7:03:29", "remaining_time": "0:07:09", "throughput": 1484.86, "total_tokens": 37730096} {"current_steps": 178785, "total_steps": 181800, "loss": 0.0045, "lr": 4.1906200637054084e-08, "epoch": 19.668316831683168, "percentage": 98.34, "elapsed_time": "7:03:30", "remaining_time": "0:07:08", "throughput": 1484.86, "total_tokens": 37731120} {"current_steps": 178790, "total_steps": 181800, "loss": 0.1023, "lr": 4.176740819316349e-08, "epoch": 19.66886688668867, "percentage": 98.34, "elapsed_time": "7:03:31", "remaining_time": "0:07:07", "throughput": 1484.86, "total_tokens": 37732144} {"current_steps": 178795, "total_steps": 181800, "loss": 0.0161, "lr": 4.162884577732784e-08, "epoch": 19.66941694169417, "percentage": 98.35, "elapsed_time": "7:03:31", "remaining_time": "0:07:07", "throughput": 1484.87, "total_tokens": 37733264} {"current_steps": 178800, "total_steps": 181800, "loss": 0.0165, "lr": 4.1490513390821105e-08, "epoch": 19.66996699669967, "percentage": 98.35, "elapsed_time": "7:03:32", "remaining_time": "0:07:06", "throughput": 1484.87, "total_tokens": 37734320} {"current_steps": 178805, "total_steps": 181800, "loss": 0.0044, "lr": 4.1352411034920046e-08, "epoch": 19.670517051705172, "percentage": 98.35, "elapsed_time": "7:03:33", "remaining_time": "0:07:05", "throughput": 1484.87, "total_tokens": 37735440} {"current_steps": 178810, "total_steps": 181800, "loss": 0.0027, "lr": 4.121453871089864e-08, "epoch": 19.67106710671067, "percentage": 98.36, "elapsed_time": "7:03:33", "remaining_time": "0:07:04", "throughput": 1484.87, "total_tokens": 37736496} {"current_steps": 178815, "total_steps": 181800, "loss": 0.061, "lr": 4.10768964200281e-08, "epoch": 19.67161716171617, "percentage": 98.36, "elapsed_time": "7:03:34", "remaining_time": "0:07:04", "throughput": 1484.88, "total_tokens": 37737616} {"current_steps": 178820, "total_steps": 181800, "loss": 0.0784, "lr": 4.093948416357407e-08, "epoch": 19.67216721672167, "percentage": 98.36, "elapsed_time": "7:03:35", "remaining_time": "0:07:03", "throughput": 1484.88, "total_tokens": 37738640} {"current_steps": 178825, "total_steps": 181800, "loss": 0.0008, "lr": 4.0802301942802215e-08, "epoch": 19.672717271727173, "percentage": 98.36, "elapsed_time": "7:03:36", "remaining_time": "0:07:02", "throughput": 1484.88, "total_tokens": 37739728} {"current_steps": 178830, "total_steps": 181800, "loss": 0.0013, "lr": 4.066534975898095e-08, "epoch": 19.673267326732674, "percentage": 98.37, "elapsed_time": "7:03:36", "remaining_time": "0:07:02", "throughput": 1484.88, "total_tokens": 37740784} {"current_steps": 178835, "total_steps": 181800, "loss": 0.0703, "lr": 4.0528627613370394e-08, "epoch": 19.673817381738175, "percentage": 98.37, "elapsed_time": "7:03:37", "remaining_time": "0:07:01", "throughput": 1484.88, "total_tokens": 37741840} {"current_steps": 178840, "total_steps": 181800, "loss": 0.1244, "lr": 4.039213550723064e-08, "epoch": 19.674367436743676, "percentage": 98.37, "elapsed_time": "7:03:38", "remaining_time": "0:07:00", "throughput": 1484.88, "total_tokens": 37742864} {"current_steps": 178845, "total_steps": 181800, "loss": 0.0418, "lr": 4.0255873441819025e-08, "epoch": 19.674917491749174, "percentage": 98.37, "elapsed_time": "7:03:38", "remaining_time": "0:06:59", "throughput": 1484.88, "total_tokens": 37743920} {"current_steps": 178850, "total_steps": 181800, "loss": 0.0174, "lr": 4.011984141839287e-08, "epoch": 19.675467546754675, "percentage": 98.38, "elapsed_time": "7:03:39", "remaining_time": "0:06:59", "throughput": 1484.89, "total_tokens": 37745008} {"current_steps": 178855, "total_steps": 181800, "loss": 0.0013, "lr": 3.9984039438203944e-08, "epoch": 19.676017601760176, "percentage": 98.38, "elapsed_time": "7:03:40", "remaining_time": "0:06:58", "throughput": 1484.89, "total_tokens": 37746096} {"current_steps": 178860, "total_steps": 181800, "loss": 0.0041, "lr": 3.9848467502506816e-08, "epoch": 19.676567656765677, "percentage": 98.38, "elapsed_time": "7:03:40", "remaining_time": "0:06:57", "throughput": 1484.89, "total_tokens": 37747216} {"current_steps": 178865, "total_steps": 181800, "loss": 0.0079, "lr": 3.9713125612547695e-08, "epoch": 19.677117711771178, "percentage": 98.39, "elapsed_time": "7:03:41", "remaining_time": "0:06:57", "throughput": 1484.89, "total_tokens": 37748176} {"current_steps": 178870, "total_steps": 181800, "loss": 0.0084, "lr": 3.957801376957837e-08, "epoch": 19.67766776677668, "percentage": 98.39, "elapsed_time": "7:03:42", "remaining_time": "0:06:56", "throughput": 1484.89, "total_tokens": 37749264} {"current_steps": 178875, "total_steps": 181800, "loss": 0.069, "lr": 3.944313197483951e-08, "epoch": 19.678217821782177, "percentage": 98.39, "elapsed_time": "7:03:42", "remaining_time": "0:06:55", "throughput": 1484.89, "total_tokens": 37750320} {"current_steps": 178880, "total_steps": 181800, "loss": 0.1292, "lr": 3.930848022957734e-08, "epoch": 19.678767876787678, "percentage": 98.39, "elapsed_time": "7:03:43", "remaining_time": "0:06:55", "throughput": 1484.89, "total_tokens": 37751344} {"current_steps": 178885, "total_steps": 181800, "loss": 0.0016, "lr": 3.9174058535029753e-08, "epoch": 19.67931793179318, "percentage": 98.4, "elapsed_time": "7:03:44", "remaining_time": "0:06:54", "throughput": 1484.89, "total_tokens": 37752368} {"current_steps": 178890, "total_steps": 181800, "loss": 0.0842, "lr": 3.9039866892437435e-08, "epoch": 19.67986798679868, "percentage": 98.4, "elapsed_time": "7:03:44", "remaining_time": "0:06:53", "throughput": 1484.89, "total_tokens": 37753392} {"current_steps": 178895, "total_steps": 181800, "loss": 0.0016, "lr": 3.890590530303828e-08, "epoch": 19.68041804180418, "percentage": 98.4, "elapsed_time": "7:03:45", "remaining_time": "0:06:52", "throughput": 1484.89, "total_tokens": 37754416} {"current_steps": 178900, "total_steps": 181800, "loss": 0.0015, "lr": 3.877217376806463e-08, "epoch": 19.680968096809682, "percentage": 98.4, "elapsed_time": "7:03:46", "remaining_time": "0:06:52", "throughput": 1484.89, "total_tokens": 37755472} {"current_steps": 178905, "total_steps": 181800, "loss": 0.0122, "lr": 3.863867228875162e-08, "epoch": 19.681518151815183, "percentage": 98.41, "elapsed_time": "7:03:47", "remaining_time": "0:06:51", "throughput": 1484.89, "total_tokens": 37756496} {"current_steps": 178910, "total_steps": 181800, "loss": 0.0033, "lr": 3.850540086632881e-08, "epoch": 19.68206820682068, "percentage": 98.41, "elapsed_time": "7:03:47", "remaining_time": "0:06:50", "throughput": 1484.89, "total_tokens": 37757520} {"current_steps": 178915, "total_steps": 181800, "loss": 0.0216, "lr": 3.8372359502023e-08, "epoch": 19.682618261826182, "percentage": 98.41, "elapsed_time": "7:03:48", "remaining_time": "0:06:50", "throughput": 1484.89, "total_tokens": 37758576} {"current_steps": 178920, "total_steps": 181800, "loss": 0.008, "lr": 3.823954819706099e-08, "epoch": 19.683168316831683, "percentage": 98.42, "elapsed_time": "7:03:49", "remaining_time": "0:06:49", "throughput": 1484.89, "total_tokens": 37759600} {"current_steps": 178925, "total_steps": 181800, "loss": 0.0274, "lr": 3.810696695266958e-08, "epoch": 19.683718371837184, "percentage": 98.42, "elapsed_time": "7:03:49", "remaining_time": "0:06:48", "throughput": 1484.9, "total_tokens": 37760656} {"current_steps": 178930, "total_steps": 181800, "loss": 0.0069, "lr": 3.797461577006445e-08, "epoch": 19.684268426842685, "percentage": 98.42, "elapsed_time": "7:03:50", "remaining_time": "0:06:47", "throughput": 1484.9, "total_tokens": 37761680} {"current_steps": 178935, "total_steps": 181800, "loss": 0.0782, "lr": 3.78424946504724e-08, "epoch": 19.684818481848186, "percentage": 98.42, "elapsed_time": "7:03:51", "remaining_time": "0:06:47", "throughput": 1484.9, "total_tokens": 37762736} {"current_steps": 178940, "total_steps": 181800, "loss": 0.0054, "lr": 3.7710603595106365e-08, "epoch": 19.685368536853684, "percentage": 98.43, "elapsed_time": "7:03:51", "remaining_time": "0:06:46", "throughput": 1484.9, "total_tokens": 37763792} {"current_steps": 178945, "total_steps": 181800, "loss": 0.0162, "lr": 3.7578942605184795e-08, "epoch": 19.685918591859185, "percentage": 98.43, "elapsed_time": "7:03:52", "remaining_time": "0:06:45", "throughput": 1484.9, "total_tokens": 37764816} {"current_steps": 178950, "total_steps": 181800, "loss": 0.0362, "lr": 3.744751168192062e-08, "epoch": 19.686468646864686, "percentage": 98.43, "elapsed_time": "7:03:53", "remaining_time": "0:06:45", "throughput": 1484.9, "total_tokens": 37765808} {"current_steps": 178955, "total_steps": 181800, "loss": 0.0016, "lr": 3.7316310826523984e-08, "epoch": 19.687018701870187, "percentage": 98.44, "elapsed_time": "7:03:53", "remaining_time": "0:06:44", "throughput": 1484.9, "total_tokens": 37766832} {"current_steps": 178960, "total_steps": 181800, "loss": 0.0337, "lr": 3.718534004020224e-08, "epoch": 19.687568756875688, "percentage": 98.44, "elapsed_time": "7:03:54", "remaining_time": "0:06:43", "throughput": 1484.9, "total_tokens": 37767856} {"current_steps": 178965, "total_steps": 181800, "loss": 0.0146, "lr": 3.705459932416833e-08, "epoch": 19.68811881188119, "percentage": 98.44, "elapsed_time": "7:03:55", "remaining_time": "0:06:42", "throughput": 1484.9, "total_tokens": 37768880} {"current_steps": 178970, "total_steps": 181800, "loss": 0.0026, "lr": 3.6924088679621274e-08, "epoch": 19.68866886688669, "percentage": 98.44, "elapsed_time": "7:03:56", "remaining_time": "0:06:42", "throughput": 1484.9, "total_tokens": 37769968} {"current_steps": 178975, "total_steps": 181800, "loss": 0.0007, "lr": 3.679380810776845e-08, "epoch": 19.689218921892188, "percentage": 98.45, "elapsed_time": "7:03:56", "remaining_time": "0:06:41", "throughput": 1484.9, "total_tokens": 37770992} {"current_steps": 178980, "total_steps": 181800, "loss": 0.0198, "lr": 3.666375760980611e-08, "epoch": 19.68976897689769, "percentage": 98.45, "elapsed_time": "7:03:57", "remaining_time": "0:06:40", "throughput": 1484.9, "total_tokens": 37772048} {"current_steps": 178985, "total_steps": 181800, "loss": 0.0056, "lr": 3.653393718693887e-08, "epoch": 19.69031903190319, "percentage": 98.45, "elapsed_time": "7:03:58", "remaining_time": "0:06:40", "throughput": 1484.9, "total_tokens": 37773104} {"current_steps": 178990, "total_steps": 181800, "loss": 0.0052, "lr": 3.640434684035743e-08, "epoch": 19.69086908690869, "percentage": 98.45, "elapsed_time": "7:03:58", "remaining_time": "0:06:39", "throughput": 1484.91, "total_tokens": 37774288} {"current_steps": 178995, "total_steps": 181800, "loss": 0.0041, "lr": 3.627498657125805e-08, "epoch": 19.691419141914192, "percentage": 98.46, "elapsed_time": "7:03:59", "remaining_time": "0:06:38", "throughput": 1484.91, "total_tokens": 37775344} {"current_steps": 179000, "total_steps": 181800, "loss": 0.0037, "lr": 3.614585638083423e-08, "epoch": 19.691969196919693, "percentage": 98.46, "elapsed_time": "7:04:00", "remaining_time": "0:06:37", "throughput": 1484.91, "total_tokens": 37776432} {"current_steps": 179005, "total_steps": 181800, "loss": 0.1094, "lr": 3.60169562702739e-08, "epoch": 19.69251925192519, "percentage": 98.46, "elapsed_time": "7:04:00", "remaining_time": "0:06:37", "throughput": 1484.91, "total_tokens": 37777456} {"current_steps": 179010, "total_steps": 181800, "loss": 0.0892, "lr": 3.588828624076779e-08, "epoch": 19.693069306930692, "percentage": 98.47, "elapsed_time": "7:04:01", "remaining_time": "0:06:36", "throughput": 1484.91, "total_tokens": 37778512} {"current_steps": 179015, "total_steps": 181800, "loss": 0.0333, "lr": 3.575984629350104e-08, "epoch": 19.693619361936193, "percentage": 98.47, "elapsed_time": "7:04:02", "remaining_time": "0:06:35", "throughput": 1484.91, "total_tokens": 37779568} {"current_steps": 179020, "total_steps": 181800, "loss": 0.0339, "lr": 3.5631636429656054e-08, "epoch": 19.694169416941694, "percentage": 98.47, "elapsed_time": "7:04:02", "remaining_time": "0:06:35", "throughput": 1484.91, "total_tokens": 37780624} {"current_steps": 179025, "total_steps": 181800, "loss": 0.074, "lr": 3.550365665041522e-08, "epoch": 19.694719471947195, "percentage": 98.47, "elapsed_time": "7:04:03", "remaining_time": "0:06:34", "throughput": 1484.91, "total_tokens": 37781680} {"current_steps": 179030, "total_steps": 181800, "loss": 0.0547, "lr": 3.537590695695536e-08, "epoch": 19.695269526952696, "percentage": 98.48, "elapsed_time": "7:04:04", "remaining_time": "0:06:33", "throughput": 1484.92, "total_tokens": 37782768} {"current_steps": 179035, "total_steps": 181800, "loss": 0.0011, "lr": 3.5248387350461655e-08, "epoch": 19.695819581958197, "percentage": 98.48, "elapsed_time": "7:04:05", "remaining_time": "0:06:32", "throughput": 1484.92, "total_tokens": 37783792} {"current_steps": 179040, "total_steps": 181800, "loss": 0.0564, "lr": 3.5121097832099824e-08, "epoch": 19.696369636963695, "percentage": 98.48, "elapsed_time": "7:04:05", "remaining_time": "0:06:32", "throughput": 1484.92, "total_tokens": 37784816} {"current_steps": 179045, "total_steps": 181800, "loss": 0.103, "lr": 3.499403840304949e-08, "epoch": 19.696919691969196, "percentage": 98.48, "elapsed_time": "7:04:06", "remaining_time": "0:06:31", "throughput": 1484.92, "total_tokens": 37785872} {"current_steps": 179050, "total_steps": 181800, "loss": 0.0007, "lr": 3.486720906448193e-08, "epoch": 19.697469746974697, "percentage": 98.49, "elapsed_time": "7:04:07", "remaining_time": "0:06:30", "throughput": 1484.92, "total_tokens": 37786896} {"current_steps": 179055, "total_steps": 181800, "loss": 0.0009, "lr": 3.474060981756011e-08, "epoch": 19.698019801980198, "percentage": 98.49, "elapsed_time": "7:04:07", "remaining_time": "0:06:30", "throughput": 1484.92, "total_tokens": 37787984} {"current_steps": 179060, "total_steps": 181800, "loss": 0.0024, "lr": 3.461424066345531e-08, "epoch": 19.6985698569857, "percentage": 98.49, "elapsed_time": "7:04:08", "remaining_time": "0:06:29", "throughput": 1484.92, "total_tokens": 37789104} {"current_steps": 179065, "total_steps": 181800, "loss": 0.0064, "lr": 3.448810160333327e-08, "epoch": 19.6991199119912, "percentage": 98.5, "elapsed_time": "7:04:09", "remaining_time": "0:06:28", "throughput": 1484.92, "total_tokens": 37790128} {"current_steps": 179070, "total_steps": 181800, "loss": 0.0403, "lr": 3.436219263835416e-08, "epoch": 19.6996699669967, "percentage": 98.5, "elapsed_time": "7:04:09", "remaining_time": "0:06:27", "throughput": 1484.92, "total_tokens": 37791120} {"current_steps": 179075, "total_steps": 181800, "loss": 0.1158, "lr": 3.423651376967818e-08, "epoch": 19.7002200220022, "percentage": 98.5, "elapsed_time": "7:04:10", "remaining_time": "0:06:27", "throughput": 1484.92, "total_tokens": 37792176} {"current_steps": 179080, "total_steps": 181800, "loss": 0.0058, "lr": 3.4111064998465505e-08, "epoch": 19.7007700770077, "percentage": 98.5, "elapsed_time": "7:04:11", "remaining_time": "0:06:26", "throughput": 1484.93, "total_tokens": 37793328} {"current_steps": 179085, "total_steps": 181800, "loss": 0.0006, "lr": 3.398584632587076e-08, "epoch": 19.7013201320132, "percentage": 98.51, "elapsed_time": "7:04:11", "remaining_time": "0:06:25", "throughput": 1484.93, "total_tokens": 37794384} {"current_steps": 179090, "total_steps": 181800, "loss": 0.0015, "lr": 3.386085775304859e-08, "epoch": 19.701870187018702, "percentage": 98.51, "elapsed_time": "7:04:12", "remaining_time": "0:06:25", "throughput": 1484.93, "total_tokens": 37795440} {"current_steps": 179095, "total_steps": 181800, "loss": 0.085, "lr": 3.373609928115085e-08, "epoch": 19.702420242024203, "percentage": 98.51, "elapsed_time": "7:04:13", "remaining_time": "0:06:24", "throughput": 1484.93, "total_tokens": 37796528} {"current_steps": 179100, "total_steps": 181800, "loss": 0.1073, "lr": 3.3611570911326605e-08, "epoch": 19.702970297029704, "percentage": 98.51, "elapsed_time": "7:04:14", "remaining_time": "0:06:23", "throughput": 1484.94, "total_tokens": 37797616} {"current_steps": 179105, "total_steps": 181800, "loss": 0.0039, "lr": 3.348727264472773e-08, "epoch": 19.703520352035202, "percentage": 98.52, "elapsed_time": "7:04:14", "remaining_time": "0:06:23", "throughput": 1484.94, "total_tokens": 37798672} {"current_steps": 179110, "total_steps": 181800, "loss": 0.0016, "lr": 3.336320448249219e-08, "epoch": 19.704070407040703, "percentage": 98.52, "elapsed_time": "7:04:15", "remaining_time": "0:06:22", "throughput": 1484.94, "total_tokens": 37799696} {"current_steps": 179115, "total_steps": 181800, "loss": 0.0048, "lr": 3.323936642577186e-08, "epoch": 19.704620462046204, "percentage": 98.52, "elapsed_time": "7:04:16", "remaining_time": "0:06:21", "throughput": 1484.94, "total_tokens": 37800720} {"current_steps": 179120, "total_steps": 181800, "loss": 0.0151, "lr": 3.311575847570192e-08, "epoch": 19.705170517051705, "percentage": 98.53, "elapsed_time": "7:04:16", "remaining_time": "0:06:20", "throughput": 1484.94, "total_tokens": 37801776} {"current_steps": 179125, "total_steps": 181800, "loss": 0.001, "lr": 3.2992380633423133e-08, "epoch": 19.705720572057206, "percentage": 98.53, "elapsed_time": "7:04:17", "remaining_time": "0:06:20", "throughput": 1484.94, "total_tokens": 37802800} {"current_steps": 179130, "total_steps": 181800, "loss": 0.0209, "lr": 3.2869232900076264e-08, "epoch": 19.706270627062707, "percentage": 98.53, "elapsed_time": "7:04:18", "remaining_time": "0:06:19", "throughput": 1484.94, "total_tokens": 37803824} {"current_steps": 179135, "total_steps": 181800, "loss": 0.0061, "lr": 3.274631527679095e-08, "epoch": 19.706820682068205, "percentage": 98.53, "elapsed_time": "7:04:18", "remaining_time": "0:06:18", "throughput": 1484.94, "total_tokens": 37804944} {"current_steps": 179140, "total_steps": 181800, "loss": 0.0008, "lr": 3.26236277647024e-08, "epoch": 19.707370737073706, "percentage": 98.54, "elapsed_time": "7:04:19", "remaining_time": "0:06:18", "throughput": 1484.94, "total_tokens": 37806000} {"current_steps": 179145, "total_steps": 181800, "loss": 0.0104, "lr": 3.250117036494027e-08, "epoch": 19.707920792079207, "percentage": 98.54, "elapsed_time": "7:04:20", "remaining_time": "0:06:17", "throughput": 1484.94, "total_tokens": 37807024} {"current_steps": 179150, "total_steps": 181800, "loss": 0.0103, "lr": 3.2378943078636984e-08, "epoch": 19.70847084708471, "percentage": 98.54, "elapsed_time": "7:04:20", "remaining_time": "0:06:16", "throughput": 1484.94, "total_tokens": 37808080} {"current_steps": 179155, "total_steps": 181800, "loss": 0.0047, "lr": 3.225694590691386e-08, "epoch": 19.70902090209021, "percentage": 98.55, "elapsed_time": "7:04:21", "remaining_time": "0:06:15", "throughput": 1484.94, "total_tokens": 37809104} {"current_steps": 179160, "total_steps": 181800, "loss": 0.0037, "lr": 3.213517885090056e-08, "epoch": 19.70957095709571, "percentage": 98.55, "elapsed_time": "7:04:22", "remaining_time": "0:06:15", "throughput": 1484.95, "total_tokens": 37810224} {"current_steps": 179165, "total_steps": 181800, "loss": 0.0028, "lr": 3.201364191171285e-08, "epoch": 19.71012101210121, "percentage": 98.55, "elapsed_time": "7:04:23", "remaining_time": "0:06:14", "throughput": 1484.95, "total_tokens": 37811312} {"current_steps": 179170, "total_steps": 181800, "loss": 0.0018, "lr": 3.189233509047762e-08, "epoch": 19.71067106710671, "percentage": 98.55, "elapsed_time": "7:04:23", "remaining_time": "0:06:13", "throughput": 1484.95, "total_tokens": 37812336} {"current_steps": 179175, "total_steps": 181800, "loss": 0.2378, "lr": 3.177125838830786e-08, "epoch": 19.71122112211221, "percentage": 98.56, "elapsed_time": "7:04:24", "remaining_time": "0:06:13", "throughput": 1484.95, "total_tokens": 37813296} {"current_steps": 179180, "total_steps": 181800, "loss": 0.0995, "lr": 3.1650411806324885e-08, "epoch": 19.71177117711771, "percentage": 98.56, "elapsed_time": "7:04:25", "remaining_time": "0:06:12", "throughput": 1484.95, "total_tokens": 37814320} {"current_steps": 179185, "total_steps": 181800, "loss": 0.0034, "lr": 3.152979534563616e-08, "epoch": 19.712321232123212, "percentage": 98.56, "elapsed_time": "7:04:25", "remaining_time": "0:06:11", "throughput": 1484.94, "total_tokens": 37815312} {"current_steps": 179190, "total_steps": 181800, "loss": 0.0558, "lr": 3.140940900735745e-08, "epoch": 19.712871287128714, "percentage": 98.56, "elapsed_time": "7:04:26", "remaining_time": "0:06:10", "throughput": 1484.94, "total_tokens": 37816336} {"current_steps": 179195, "total_steps": 181800, "loss": 0.0013, "lr": 3.12892527925962e-08, "epoch": 19.713421342134215, "percentage": 98.57, "elapsed_time": "7:04:27", "remaining_time": "0:06:10", "throughput": 1484.95, "total_tokens": 37817456} {"current_steps": 179200, "total_steps": 181800, "loss": 0.0071, "lr": 3.1169326702459866e-08, "epoch": 19.713971397139716, "percentage": 98.57, "elapsed_time": "7:04:27", "remaining_time": "0:06:09", "throughput": 1484.95, "total_tokens": 37818512} {"current_steps": 179205, "total_steps": 181800, "loss": 0.0039, "lr": 3.104963073805589e-08, "epoch": 19.714521452145213, "percentage": 98.57, "elapsed_time": "7:04:28", "remaining_time": "0:06:08", "throughput": 1484.95, "total_tokens": 37819568} {"current_steps": 179210, "total_steps": 181800, "loss": 0.0088, "lr": 3.093016490048617e-08, "epoch": 19.715071507150714, "percentage": 98.58, "elapsed_time": "7:04:29", "remaining_time": "0:06:08", "throughput": 1484.95, "total_tokens": 37820624} {"current_steps": 179215, "total_steps": 181800, "loss": 0.0035, "lr": 3.08109291908526e-08, "epoch": 19.715621562156215, "percentage": 98.58, "elapsed_time": "7:04:29", "remaining_time": "0:06:07", "throughput": 1484.95, "total_tokens": 37821616} {"current_steps": 179220, "total_steps": 181800, "loss": 0.0042, "lr": 3.069192361025153e-08, "epoch": 19.716171617161717, "percentage": 98.58, "elapsed_time": "7:04:30", "remaining_time": "0:06:06", "throughput": 1484.95, "total_tokens": 37822672} {"current_steps": 179225, "total_steps": 181800, "loss": 0.0052, "lr": 3.057314815978207e-08, "epoch": 19.716721672167218, "percentage": 98.58, "elapsed_time": "7:04:31", "remaining_time": "0:06:05", "throughput": 1484.95, "total_tokens": 37823696} {"current_steps": 179230, "total_steps": 181800, "loss": 0.0631, "lr": 3.045460284054058e-08, "epoch": 19.71727172717272, "percentage": 98.59, "elapsed_time": "7:04:32", "remaining_time": "0:06:05", "throughput": 1484.95, "total_tokens": 37824784} {"current_steps": 179235, "total_steps": 181800, "loss": 0.0478, "lr": 3.033628765361507e-08, "epoch": 19.717821782178216, "percentage": 98.59, "elapsed_time": "7:04:32", "remaining_time": "0:06:04", "throughput": 1484.96, "total_tokens": 37825904} {"current_steps": 179240, "total_steps": 181800, "loss": 0.0017, "lr": 3.021820260009911e-08, "epoch": 19.718371837183717, "percentage": 98.59, "elapsed_time": "7:04:33", "remaining_time": "0:06:03", "throughput": 1484.96, "total_tokens": 37826928} {"current_steps": 179245, "total_steps": 181800, "loss": 0.0035, "lr": 3.010034768108072e-08, "epoch": 19.71892189218922, "percentage": 98.59, "elapsed_time": "7:04:34", "remaining_time": "0:06:03", "throughput": 1484.96, "total_tokens": 37827952} {"current_steps": 179250, "total_steps": 181800, "loss": 0.1217, "lr": 2.9982722897645146e-08, "epoch": 19.71947194719472, "percentage": 98.6, "elapsed_time": "7:04:34", "remaining_time": "0:06:02", "throughput": 1484.96, "total_tokens": 37829008} {"current_steps": 179255, "total_steps": 181800, "loss": 0.0061, "lr": 2.986532825087762e-08, "epoch": 19.72002200220022, "percentage": 98.6, "elapsed_time": "7:04:35", "remaining_time": "0:06:01", "throughput": 1484.96, "total_tokens": 37830064} {"current_steps": 179260, "total_steps": 181800, "loss": 0.0016, "lr": 2.9748163741857847e-08, "epoch": 19.72057205720572, "percentage": 98.6, "elapsed_time": "7:04:36", "remaining_time": "0:06:00", "throughput": 1484.96, "total_tokens": 37831088} {"current_steps": 179265, "total_steps": 181800, "loss": 0.1182, "lr": 2.963122937166829e-08, "epoch": 19.721122112211223, "percentage": 98.61, "elapsed_time": "7:04:36", "remaining_time": "0:06:00", "throughput": 1484.96, "total_tokens": 37832112} {"current_steps": 179270, "total_steps": 181800, "loss": 0.0069, "lr": 2.9514525141385863e-08, "epoch": 19.72167216721672, "percentage": 98.61, "elapsed_time": "7:04:37", "remaining_time": "0:05:59", "throughput": 1484.96, "total_tokens": 37833200} {"current_steps": 179275, "total_steps": 181800, "loss": 0.0013, "lr": 2.9398051052087483e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "7:04:38", "remaining_time": "0:05:58", "throughput": 1484.96, "total_tokens": 37834192} {"current_steps": 179280, "total_steps": 181800, "loss": 0.0016, "lr": 2.9281807104844516e-08, "epoch": 19.722772277227723, "percentage": 98.61, "elapsed_time": "7:04:38", "remaining_time": "0:05:58", "throughput": 1484.96, "total_tokens": 37835248} {"current_steps": 179285, "total_steps": 181800, "loss": 0.0025, "lr": 2.916579330072833e-08, "epoch": 19.723322332233224, "percentage": 98.62, "elapsed_time": "7:04:39", "remaining_time": "0:05:57", "throughput": 1484.96, "total_tokens": 37836240} {"current_steps": 179290, "total_steps": 181800, "loss": 0.002, "lr": 2.9050009640807508e-08, "epoch": 19.723872387238725, "percentage": 98.62, "elapsed_time": "7:04:40", "remaining_time": "0:05:56", "throughput": 1484.96, "total_tokens": 37837296} {"current_steps": 179295, "total_steps": 181800, "loss": 0.0011, "lr": 2.893445612615342e-08, "epoch": 19.724422442244226, "percentage": 98.62, "elapsed_time": "7:04:41", "remaining_time": "0:05:56", "throughput": 1484.96, "total_tokens": 37838320} {"current_steps": 179300, "total_steps": 181800, "loss": 0.0076, "lr": 2.881913275782633e-08, "epoch": 19.724972497249723, "percentage": 98.62, "elapsed_time": "7:04:41", "remaining_time": "0:05:55", "throughput": 1484.96, "total_tokens": 37839376} {"current_steps": 179305, "total_steps": 181800, "loss": 0.0032, "lr": 2.8704039536892048e-08, "epoch": 19.725522552255224, "percentage": 98.63, "elapsed_time": "7:04:42", "remaining_time": "0:05:54", "throughput": 1484.96, "total_tokens": 37840400} {"current_steps": 179310, "total_steps": 181800, "loss": 0.0037, "lr": 2.8589176464408063e-08, "epoch": 19.726072607260726, "percentage": 98.63, "elapsed_time": "7:04:43", "remaining_time": "0:05:53", "throughput": 1484.97, "total_tokens": 37841552} {"current_steps": 179315, "total_steps": 181800, "loss": 0.002, "lr": 2.8474543541437415e-08, "epoch": 19.726622662266227, "percentage": 98.63, "elapsed_time": "7:04:43", "remaining_time": "0:05:53", "throughput": 1484.97, "total_tokens": 37842608} {"current_steps": 179320, "total_steps": 181800, "loss": 0.1956, "lr": 2.8360140769034814e-08, "epoch": 19.727172717271728, "percentage": 98.64, "elapsed_time": "7:04:44", "remaining_time": "0:05:52", "throughput": 1484.97, "total_tokens": 37843600} {"current_steps": 179325, "total_steps": 181800, "loss": 0.0012, "lr": 2.82459681482522e-08, "epoch": 19.72772277227723, "percentage": 98.64, "elapsed_time": "7:04:45", "remaining_time": "0:05:51", "throughput": 1484.97, "total_tokens": 37844688} {"current_steps": 179330, "total_steps": 181800, "loss": 0.0083, "lr": 2.813202568014428e-08, "epoch": 19.72827282728273, "percentage": 98.64, "elapsed_time": "7:04:45", "remaining_time": "0:05:51", "throughput": 1484.97, "total_tokens": 37845680} {"current_steps": 179335, "total_steps": 181800, "loss": 0.004, "lr": 2.8018313365762995e-08, "epoch": 19.728822882288227, "percentage": 98.64, "elapsed_time": "7:04:46", "remaining_time": "0:05:50", "throughput": 1484.97, "total_tokens": 37846768} {"current_steps": 179340, "total_steps": 181800, "loss": 0.0178, "lr": 2.790483120615195e-08, "epoch": 19.72937293729373, "percentage": 98.65, "elapsed_time": "7:04:47", "remaining_time": "0:05:49", "throughput": 1484.97, "total_tokens": 37847760} {"current_steps": 179345, "total_steps": 181800, "loss": 0.1114, "lr": 2.7791579202360307e-08, "epoch": 19.72992299229923, "percentage": 98.65, "elapsed_time": "7:04:47", "remaining_time": "0:05:48", "throughput": 1484.97, "total_tokens": 37848848} {"current_steps": 179350, "total_steps": 181800, "loss": 0.0009, "lr": 2.7678557355428902e-08, "epoch": 19.73047304730473, "percentage": 98.65, "elapsed_time": "7:04:48", "remaining_time": "0:05:48", "throughput": 1484.97, "total_tokens": 37849904} {"current_steps": 179355, "total_steps": 181800, "loss": 0.0348, "lr": 2.756576566640412e-08, "epoch": 19.731023102310232, "percentage": 98.66, "elapsed_time": "7:04:49", "remaining_time": "0:05:47", "throughput": 1484.97, "total_tokens": 37850960} {"current_steps": 179360, "total_steps": 181800, "loss": 0.0004, "lr": 2.745320413632124e-08, "epoch": 19.731573157315733, "percentage": 98.66, "elapsed_time": "7:04:50", "remaining_time": "0:05:46", "throughput": 1484.98, "total_tokens": 37852080} {"current_steps": 179365, "total_steps": 181800, "loss": 0.0019, "lr": 2.734087276621833e-08, "epoch": 19.73212321232123, "percentage": 98.66, "elapsed_time": "7:04:50", "remaining_time": "0:05:46", "throughput": 1484.98, "total_tokens": 37853136} {"current_steps": 179370, "total_steps": 181800, "loss": 0.0521, "lr": 2.7228771557133438e-08, "epoch": 19.73267326732673, "percentage": 98.66, "elapsed_time": "7:04:51", "remaining_time": "0:05:45", "throughput": 1484.98, "total_tokens": 37854192} {"current_steps": 179375, "total_steps": 181800, "loss": 0.001, "lr": 2.71169005100963e-08, "epoch": 19.733223322332233, "percentage": 98.67, "elapsed_time": "7:04:52", "remaining_time": "0:05:44", "throughput": 1484.98, "total_tokens": 37855280} {"current_steps": 179380, "total_steps": 181800, "loss": 0.0007, "lr": 2.7005259626139423e-08, "epoch": 19.733773377337734, "percentage": 98.67, "elapsed_time": "7:04:52", "remaining_time": "0:05:43", "throughput": 1484.98, "total_tokens": 37856368} {"current_steps": 179385, "total_steps": 181800, "loss": 0.1157, "lr": 2.689384890629254e-08, "epoch": 19.734323432343235, "percentage": 98.67, "elapsed_time": "7:04:53", "remaining_time": "0:05:43", "throughput": 1484.99, "total_tokens": 37857456} {"current_steps": 179390, "total_steps": 181800, "loss": 0.0047, "lr": 2.6782668351582607e-08, "epoch": 19.734873487348736, "percentage": 98.67, "elapsed_time": "7:04:54", "remaining_time": "0:05:42", "throughput": 1484.99, "total_tokens": 37858480} {"current_steps": 179395, "total_steps": 181800, "loss": 0.0017, "lr": 2.6671717963033803e-08, "epoch": 19.735423542354237, "percentage": 98.68, "elapsed_time": "7:04:54", "remaining_time": "0:05:41", "throughput": 1484.99, "total_tokens": 37859472} {"current_steps": 179400, "total_steps": 181800, "loss": 0.0213, "lr": 2.6560997741667536e-08, "epoch": 19.735973597359735, "percentage": 98.68, "elapsed_time": "7:04:55", "remaining_time": "0:05:41", "throughput": 1484.99, "total_tokens": 37860560} {"current_steps": 179405, "total_steps": 181800, "loss": 0.0029, "lr": 2.645050768850521e-08, "epoch": 19.736523652365236, "percentage": 98.68, "elapsed_time": "7:04:56", "remaining_time": "0:05:40", "throughput": 1484.99, "total_tokens": 37861680} {"current_steps": 179410, "total_steps": 181800, "loss": 0.1676, "lr": 2.6340247804565454e-08, "epoch": 19.737073707370737, "percentage": 98.69, "elapsed_time": "7:04:56", "remaining_time": "0:05:39", "throughput": 1484.99, "total_tokens": 37862704} {"current_steps": 179415, "total_steps": 181800, "loss": 0.0029, "lr": 2.6230218090861347e-08, "epoch": 19.737623762376238, "percentage": 98.69, "elapsed_time": "7:04:57", "remaining_time": "0:05:38", "throughput": 1484.99, "total_tokens": 37863728} {"current_steps": 179420, "total_steps": 181800, "loss": 0.0019, "lr": 2.6120418548414293e-08, "epoch": 19.73817381738174, "percentage": 98.69, "elapsed_time": "7:04:58", "remaining_time": "0:05:38", "throughput": 1484.99, "total_tokens": 37864816} {"current_steps": 179425, "total_steps": 181800, "loss": 0.0015, "lr": 2.6010849178229045e-08, "epoch": 19.73872387238724, "percentage": 98.69, "elapsed_time": "7:04:58", "remaining_time": "0:05:37", "throughput": 1484.99, "total_tokens": 37865872} {"current_steps": 179430, "total_steps": 181800, "loss": 0.0113, "lr": 2.5901509981318684e-08, "epoch": 19.739273927392738, "percentage": 98.7, "elapsed_time": "7:04:59", "remaining_time": "0:05:36", "throughput": 1485.0, "total_tokens": 37866960} {"current_steps": 179435, "total_steps": 181800, "loss": 0.0046, "lr": 2.5792400958687956e-08, "epoch": 19.73982398239824, "percentage": 98.7, "elapsed_time": "7:05:00", "remaining_time": "0:05:36", "throughput": 1485.0, "total_tokens": 37867952} {"current_steps": 179440, "total_steps": 181800, "loss": 0.0667, "lr": 2.568352211134717e-08, "epoch": 19.74037403740374, "percentage": 98.7, "elapsed_time": "7:05:01", "remaining_time": "0:05:35", "throughput": 1485.0, "total_tokens": 37869040} {"current_steps": 179445, "total_steps": 181800, "loss": 0.1301, "lr": 2.5574873440298296e-08, "epoch": 19.74092409240924, "percentage": 98.7, "elapsed_time": "7:05:01", "remaining_time": "0:05:34", "throughput": 1485.0, "total_tokens": 37870064} {"current_steps": 179450, "total_steps": 181800, "loss": 0.0081, "lr": 2.5466454946540542e-08, "epoch": 19.741474147414742, "percentage": 98.71, "elapsed_time": "7:05:02", "remaining_time": "0:05:33", "throughput": 1485.0, "total_tokens": 37871056} {"current_steps": 179455, "total_steps": 181800, "loss": 0.0033, "lr": 2.535826663107588e-08, "epoch": 19.742024202420243, "percentage": 98.71, "elapsed_time": "7:05:03", "remaining_time": "0:05:33", "throughput": 1484.99, "total_tokens": 37872048} {"current_steps": 179460, "total_steps": 181800, "loss": 0.0365, "lr": 2.525030849490073e-08, "epoch": 19.742574257425744, "percentage": 98.71, "elapsed_time": "7:05:03", "remaining_time": "0:05:32", "throughput": 1485.0, "total_tokens": 37873136} {"current_steps": 179465, "total_steps": 181800, "loss": 0.1295, "lr": 2.514258053900598e-08, "epoch": 19.74312431243124, "percentage": 98.72, "elapsed_time": "7:05:04", "remaining_time": "0:05:31", "throughput": 1485.0, "total_tokens": 37874256} {"current_steps": 179470, "total_steps": 181800, "loss": 0.0049, "lr": 2.5035082764390816e-08, "epoch": 19.743674367436743, "percentage": 98.72, "elapsed_time": "7:05:05", "remaining_time": "0:05:31", "throughput": 1485.0, "total_tokens": 37875344} {"current_steps": 179475, "total_steps": 181800, "loss": 0.0298, "lr": 2.4927815172040568e-08, "epoch": 19.744224422442244, "percentage": 98.72, "elapsed_time": "7:05:05", "remaining_time": "0:05:30", "throughput": 1485.01, "total_tokens": 37876432} {"current_steps": 179480, "total_steps": 181800, "loss": 0.0093, "lr": 2.482077776294889e-08, "epoch": 19.744774477447745, "percentage": 98.72, "elapsed_time": "7:05:06", "remaining_time": "0:05:29", "throughput": 1485.01, "total_tokens": 37877520} {"current_steps": 179485, "total_steps": 181800, "loss": 0.0137, "lr": 2.471397053809832e-08, "epoch": 19.745324532453246, "percentage": 98.73, "elapsed_time": "7:05:07", "remaining_time": "0:05:28", "throughput": 1485.01, "total_tokens": 37878544} {"current_steps": 179490, "total_steps": 181800, "loss": 0.0025, "lr": 2.460739349847696e-08, "epoch": 19.745874587458747, "percentage": 98.73, "elapsed_time": "7:05:07", "remaining_time": "0:05:28", "throughput": 1485.01, "total_tokens": 37879536} {"current_steps": 179495, "total_steps": 181800, "loss": 0.0016, "lr": 2.4501046645064585e-08, "epoch": 19.746424642464248, "percentage": 98.73, "elapsed_time": "7:05:08", "remaining_time": "0:05:27", "throughput": 1485.01, "total_tokens": 37880592} {"current_steps": 179500, "total_steps": 181800, "loss": 0.0917, "lr": 2.4394929978838187e-08, "epoch": 19.746974697469746, "percentage": 98.73, "elapsed_time": "7:05:09", "remaining_time": "0:05:26", "throughput": 1485.01, "total_tokens": 37881616} {"current_steps": 179505, "total_steps": 181800, "loss": 0.0503, "lr": 2.4289043500783094e-08, "epoch": 19.747524752475247, "percentage": 98.74, "elapsed_time": "7:05:10", "remaining_time": "0:05:26", "throughput": 1485.01, "total_tokens": 37882704} {"current_steps": 179510, "total_steps": 181800, "loss": 0.019, "lr": 2.4183387211870746e-08, "epoch": 19.748074807480748, "percentage": 98.74, "elapsed_time": "7:05:10", "remaining_time": "0:05:25", "throughput": 1485.01, "total_tokens": 37883824} {"current_steps": 179515, "total_steps": 181800, "loss": 0.0034, "lr": 2.407796111307259e-08, "epoch": 19.74862486248625, "percentage": 98.74, "elapsed_time": "7:05:11", "remaining_time": "0:05:24", "throughput": 1485.01, "total_tokens": 37884816} {"current_steps": 179520, "total_steps": 181800, "loss": 0.1256, "lr": 2.3972765205365623e-08, "epoch": 19.74917491749175, "percentage": 98.75, "elapsed_time": "7:05:12", "remaining_time": "0:05:24", "throughput": 1485.01, "total_tokens": 37885872} {"current_steps": 179525, "total_steps": 181800, "loss": 0.0363, "lr": 2.3867799489718512e-08, "epoch": 19.74972497249725, "percentage": 98.75, "elapsed_time": "7:05:12", "remaining_time": "0:05:23", "throughput": 1485.02, "total_tokens": 37886928} {"current_steps": 179530, "total_steps": 181800, "loss": 0.0014, "lr": 2.3763063967094378e-08, "epoch": 19.75027502750275, "percentage": 98.75, "elapsed_time": "7:05:13", "remaining_time": "0:05:22", "throughput": 1485.02, "total_tokens": 37888016} {"current_steps": 179535, "total_steps": 181800, "loss": 0.1239, "lr": 2.3658558638461892e-08, "epoch": 19.75082508250825, "percentage": 98.75, "elapsed_time": "7:05:14", "remaining_time": "0:05:21", "throughput": 1485.02, "total_tokens": 37889104} {"current_steps": 179540, "total_steps": 181800, "loss": 0.0012, "lr": 2.355428350478417e-08, "epoch": 19.75137513751375, "percentage": 98.76, "elapsed_time": "7:05:14", "remaining_time": "0:05:21", "throughput": 1485.02, "total_tokens": 37890160} {"current_steps": 179545, "total_steps": 181800, "loss": 0.0024, "lr": 2.3450238567021555e-08, "epoch": 19.751925192519252, "percentage": 98.76, "elapsed_time": "7:05:15", "remaining_time": "0:05:20", "throughput": 1485.02, "total_tokens": 37891216} {"current_steps": 179550, "total_steps": 181800, "loss": 0.0012, "lr": 2.334642382613439e-08, "epoch": 19.752475247524753, "percentage": 98.76, "elapsed_time": "7:05:16", "remaining_time": "0:05:19", "throughput": 1485.02, "total_tokens": 37892272} {"current_steps": 179555, "total_steps": 181800, "loss": 0.0189, "lr": 2.3242839283077468e-08, "epoch": 19.753025302530254, "percentage": 98.77, "elapsed_time": "7:05:16", "remaining_time": "0:05:19", "throughput": 1485.02, "total_tokens": 37893328} {"current_steps": 179560, "total_steps": 181800, "loss": 0.0123, "lr": 2.3139484938805577e-08, "epoch": 19.753575357535752, "percentage": 98.77, "elapsed_time": "7:05:17", "remaining_time": "0:05:18", "throughput": 1485.03, "total_tokens": 37894416} {"current_steps": 179565, "total_steps": 181800, "loss": 0.012, "lr": 2.303636079427074e-08, "epoch": 19.754125412541253, "percentage": 98.77, "elapsed_time": "7:05:18", "remaining_time": "0:05:17", "throughput": 1485.03, "total_tokens": 37895440} {"current_steps": 179570, "total_steps": 181800, "loss": 0.0014, "lr": 2.2933466850427743e-08, "epoch": 19.754675467546754, "percentage": 98.77, "elapsed_time": "7:05:19", "remaining_time": "0:05:16", "throughput": 1485.03, "total_tokens": 37896560} {"current_steps": 179575, "total_steps": 181800, "loss": 0.1318, "lr": 2.283080310822028e-08, "epoch": 19.755225522552255, "percentage": 98.78, "elapsed_time": "7:05:19", "remaining_time": "0:05:16", "throughput": 1485.03, "total_tokens": 37897616} {"current_steps": 179580, "total_steps": 181800, "loss": 0.0005, "lr": 2.2728369568597586e-08, "epoch": 19.755775577557756, "percentage": 98.78, "elapsed_time": "7:05:20", "remaining_time": "0:05:15", "throughput": 1485.03, "total_tokens": 37898672} {"current_steps": 179585, "total_steps": 181800, "loss": 0.0035, "lr": 2.262616623250058e-08, "epoch": 19.756325632563257, "percentage": 98.78, "elapsed_time": "7:05:21", "remaining_time": "0:05:14", "throughput": 1485.03, "total_tokens": 37899696} {"current_steps": 179590, "total_steps": 181800, "loss": 0.0492, "lr": 2.2524193100872948e-08, "epoch": 19.75687568756876, "percentage": 98.78, "elapsed_time": "7:05:21", "remaining_time": "0:05:14", "throughput": 1485.03, "total_tokens": 37900688} {"current_steps": 179595, "total_steps": 181800, "loss": 0.0065, "lr": 2.2422450174655608e-08, "epoch": 19.757425742574256, "percentage": 98.79, "elapsed_time": "7:05:22", "remaining_time": "0:05:13", "throughput": 1485.03, "total_tokens": 37901776} {"current_steps": 179600, "total_steps": 181800, "loss": 0.0075, "lr": 2.232093745478392e-08, "epoch": 19.757975797579757, "percentage": 98.79, "elapsed_time": "7:05:23", "remaining_time": "0:05:12", "throughput": 1485.03, "total_tokens": 37902800} {"current_steps": 179605, "total_steps": 181800, "loss": 0.067, "lr": 2.2219654942193246e-08, "epoch": 19.758525852585258, "percentage": 98.79, "elapsed_time": "7:05:23", "remaining_time": "0:05:11", "throughput": 1485.03, "total_tokens": 37903824} {"current_steps": 179610, "total_steps": 181800, "loss": 0.001, "lr": 2.211860263782173e-08, "epoch": 19.75907590759076, "percentage": 98.8, "elapsed_time": "7:05:24", "remaining_time": "0:05:11", "throughput": 1485.03, "total_tokens": 37904848} {"current_steps": 179615, "total_steps": 181800, "loss": 0.0028, "lr": 2.20177805425964e-08, "epoch": 19.75962596259626, "percentage": 98.8, "elapsed_time": "7:05:25", "remaining_time": "0:05:10", "throughput": 1485.04, "total_tokens": 37905968} {"current_steps": 179620, "total_steps": 181800, "loss": 0.0044, "lr": 2.1917188657447076e-08, "epoch": 19.76017601760176, "percentage": 98.8, "elapsed_time": "7:05:25", "remaining_time": "0:05:09", "throughput": 1485.04, "total_tokens": 37907088} {"current_steps": 179625, "total_steps": 181800, "loss": 0.0225, "lr": 2.1816826983300786e-08, "epoch": 19.760726072607262, "percentage": 98.8, "elapsed_time": "7:05:26", "remaining_time": "0:05:09", "throughput": 1485.04, "total_tokens": 37908208} {"current_steps": 179630, "total_steps": 181800, "loss": 0.0188, "lr": 2.1716695521084575e-08, "epoch": 19.76127612761276, "percentage": 98.81, "elapsed_time": "7:05:27", "remaining_time": "0:05:08", "throughput": 1485.05, "total_tokens": 37909328} {"current_steps": 179635, "total_steps": 181800, "loss": 0.0873, "lr": 2.1616794271717143e-08, "epoch": 19.76182618261826, "percentage": 98.81, "elapsed_time": "7:05:28", "remaining_time": "0:05:07", "throughput": 1485.05, "total_tokens": 37910320} {"current_steps": 179640, "total_steps": 181800, "loss": 0.0028, "lr": 2.1517123236125535e-08, "epoch": 19.762376237623762, "percentage": 98.81, "elapsed_time": "7:05:28", "remaining_time": "0:05:06", "throughput": 1485.05, "total_tokens": 37911440} {"current_steps": 179645, "total_steps": 181800, "loss": 0.0041, "lr": 2.1417682415222908e-08, "epoch": 19.762926292629263, "percentage": 98.81, "elapsed_time": "7:05:29", "remaining_time": "0:05:06", "throughput": 1485.05, "total_tokens": 37912464} {"current_steps": 179650, "total_steps": 181800, "loss": 0.0029, "lr": 2.1318471809927965e-08, "epoch": 19.763476347634764, "percentage": 98.82, "elapsed_time": "7:05:30", "remaining_time": "0:05:05", "throughput": 1485.04, "total_tokens": 37913488} {"current_steps": 179655, "total_steps": 181800, "loss": 0.1127, "lr": 2.121949142115387e-08, "epoch": 19.764026402640265, "percentage": 98.82, "elapsed_time": "7:05:30", "remaining_time": "0:05:04", "throughput": 1485.04, "total_tokens": 37914576} {"current_steps": 179660, "total_steps": 181800, "loss": 0.0134, "lr": 2.1120741249816557e-08, "epoch": 19.764576457645763, "percentage": 98.82, "elapsed_time": "7:05:31", "remaining_time": "0:05:04", "throughput": 1485.04, "total_tokens": 37915696} {"current_steps": 179665, "total_steps": 181800, "loss": 0.0017, "lr": 2.1022221296820854e-08, "epoch": 19.765126512651264, "percentage": 98.83, "elapsed_time": "7:05:32", "remaining_time": "0:05:03", "throughput": 1485.05, "total_tokens": 37916784} {"current_steps": 179670, "total_steps": 181800, "loss": 0.0733, "lr": 2.092393156307715e-08, "epoch": 19.765676567656765, "percentage": 98.83, "elapsed_time": "7:05:33", "remaining_time": "0:05:02", "throughput": 1485.05, "total_tokens": 37917808} {"current_steps": 179675, "total_steps": 181800, "loss": 0.0127, "lr": 2.082587204949027e-08, "epoch": 19.766226622662266, "percentage": 98.83, "elapsed_time": "7:05:33", "remaining_time": "0:05:01", "throughput": 1485.05, "total_tokens": 37918832} {"current_steps": 179680, "total_steps": 181800, "loss": 0.0021, "lr": 2.0728042756967824e-08, "epoch": 19.766776677667767, "percentage": 98.83, "elapsed_time": "7:05:34", "remaining_time": "0:05:01", "throughput": 1485.04, "total_tokens": 37919792} {"current_steps": 179685, "total_steps": 181800, "loss": 0.0127, "lr": 2.0630443686409096e-08, "epoch": 19.76732673267327, "percentage": 98.84, "elapsed_time": "7:05:35", "remaining_time": "0:05:00", "throughput": 1485.04, "total_tokens": 37920816} {"current_steps": 179690, "total_steps": 181800, "loss": 0.0044, "lr": 2.0533074838710587e-08, "epoch": 19.76787678767877, "percentage": 98.84, "elapsed_time": "7:05:35", "remaining_time": "0:04:59", "throughput": 1485.04, "total_tokens": 37921840} {"current_steps": 179695, "total_steps": 181800, "loss": 0.0006, "lr": 2.0435936214774354e-08, "epoch": 19.768426842684267, "percentage": 98.84, "elapsed_time": "7:05:36", "remaining_time": "0:04:59", "throughput": 1485.04, "total_tokens": 37922864} {"current_steps": 179700, "total_steps": 181800, "loss": 0.016, "lr": 2.033902781549413e-08, "epoch": 19.768976897689768, "percentage": 98.84, "elapsed_time": "7:05:37", "remaining_time": "0:04:58", "throughput": 1485.04, "total_tokens": 37923824} {"current_steps": 179705, "total_steps": 181800, "loss": 0.1027, "lr": 2.024234964176086e-08, "epoch": 19.76952695269527, "percentage": 98.85, "elapsed_time": "7:05:37", "remaining_time": "0:04:57", "throughput": 1485.04, "total_tokens": 37924944} {"current_steps": 179710, "total_steps": 181800, "loss": 0.0029, "lr": 2.0145901694468283e-08, "epoch": 19.77007700770077, "percentage": 98.85, "elapsed_time": "7:05:38", "remaining_time": "0:04:57", "throughput": 1485.04, "total_tokens": 37925968} {"current_steps": 179715, "total_steps": 181800, "loss": 0.0448, "lr": 2.0049683974504572e-08, "epoch": 19.77062706270627, "percentage": 98.85, "elapsed_time": "7:05:39", "remaining_time": "0:04:56", "throughput": 1485.05, "total_tokens": 37926992} {"current_steps": 179720, "total_steps": 181800, "loss": 0.0005, "lr": 1.9953696482755136e-08, "epoch": 19.771177117711773, "percentage": 98.86, "elapsed_time": "7:05:39", "remaining_time": "0:04:55", "throughput": 1485.05, "total_tokens": 37928080} {"current_steps": 179725, "total_steps": 181800, "loss": 0.0373, "lr": 1.9857939220108147e-08, "epoch": 19.77172717271727, "percentage": 98.86, "elapsed_time": "7:05:40", "remaining_time": "0:04:54", "throughput": 1485.05, "total_tokens": 37929104} {"current_steps": 179730, "total_steps": 181800, "loss": 0.0018, "lr": 1.976241218744346e-08, "epoch": 19.77227722772277, "percentage": 98.86, "elapsed_time": "7:05:41", "remaining_time": "0:04:54", "throughput": 1485.05, "total_tokens": 37930128} {"current_steps": 179735, "total_steps": 181800, "loss": 0.0721, "lr": 1.9667115385640923e-08, "epoch": 19.772827282728272, "percentage": 98.86, "elapsed_time": "7:05:42", "remaining_time": "0:04:53", "throughput": 1485.05, "total_tokens": 37931152} {"current_steps": 179740, "total_steps": 181800, "loss": 0.0535, "lr": 1.957204881558039e-08, "epoch": 19.773377337733773, "percentage": 98.87, "elapsed_time": "7:05:42", "remaining_time": "0:04:52", "throughput": 1485.05, "total_tokens": 37932304} {"current_steps": 179745, "total_steps": 181800, "loss": 0.0626, "lr": 1.9477212478136163e-08, "epoch": 19.773927392739274, "percentage": 98.87, "elapsed_time": "7:05:43", "remaining_time": "0:04:52", "throughput": 1485.05, "total_tokens": 37933360} {"current_steps": 179750, "total_steps": 181800, "loss": 0.0073, "lr": 1.938260637418532e-08, "epoch": 19.774477447744776, "percentage": 98.87, "elapsed_time": "7:05:44", "remaining_time": "0:04:51", "throughput": 1485.05, "total_tokens": 37934416} {"current_steps": 179755, "total_steps": 181800, "loss": 0.0022, "lr": 1.9288230504596606e-08, "epoch": 19.775027502750277, "percentage": 98.88, "elapsed_time": "7:05:44", "remaining_time": "0:04:50", "throughput": 1485.06, "total_tokens": 37935504} {"current_steps": 179760, "total_steps": 181800, "loss": 0.0033, "lr": 1.9194084870244323e-08, "epoch": 19.775577557755774, "percentage": 98.88, "elapsed_time": "7:05:45", "remaining_time": "0:04:49", "throughput": 1485.06, "total_tokens": 37936528} {"current_steps": 179765, "total_steps": 181800, "loss": 0.0855, "lr": 1.9100169471988893e-08, "epoch": 19.776127612761275, "percentage": 98.88, "elapsed_time": "7:05:46", "remaining_time": "0:04:49", "throughput": 1485.06, "total_tokens": 37937584} {"current_steps": 179770, "total_steps": 181800, "loss": 0.0042, "lr": 1.900648431070462e-08, "epoch": 19.776677667766776, "percentage": 98.88, "elapsed_time": "7:05:46", "remaining_time": "0:04:48", "throughput": 1485.06, "total_tokens": 37938672} {"current_steps": 179775, "total_steps": 181800, "loss": 0.0433, "lr": 1.8913029387246372e-08, "epoch": 19.777227722772277, "percentage": 98.89, "elapsed_time": "7:05:47", "remaining_time": "0:04:47", "throughput": 1485.06, "total_tokens": 37939760} {"current_steps": 179780, "total_steps": 181800, "loss": 0.0029, "lr": 1.8819804702482903e-08, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "7:05:48", "remaining_time": "0:04:47", "throughput": 1485.07, "total_tokens": 37940848} {"current_steps": 179785, "total_steps": 181800, "loss": 0.0299, "lr": 1.8726810257269077e-08, "epoch": 19.77832783278328, "percentage": 98.89, "elapsed_time": "7:05:48", "remaining_time": "0:04:46", "throughput": 1485.06, "total_tokens": 37941808} {"current_steps": 179790, "total_steps": 181800, "loss": 0.0107, "lr": 1.8634046052462552e-08, "epoch": 19.778877887788777, "percentage": 98.89, "elapsed_time": "7:05:49", "remaining_time": "0:04:45", "throughput": 1485.06, "total_tokens": 37942864} {"current_steps": 179795, "total_steps": 181800, "loss": 0.0884, "lr": 1.854151208891819e-08, "epoch": 19.77942794279428, "percentage": 98.9, "elapsed_time": "7:05:50", "remaining_time": "0:04:44", "throughput": 1485.06, "total_tokens": 37943888} {"current_steps": 179800, "total_steps": 181800, "loss": 0.0015, "lr": 1.8449208367490868e-08, "epoch": 19.77997799779978, "percentage": 98.9, "elapsed_time": "7:05:51", "remaining_time": "0:04:44", "throughput": 1485.06, "total_tokens": 37944944} {"current_steps": 179805, "total_steps": 181800, "loss": 0.0563, "lr": 1.8357134889029903e-08, "epoch": 19.78052805280528, "percentage": 98.9, "elapsed_time": "7:05:51", "remaining_time": "0:04:43", "throughput": 1485.07, "total_tokens": 37946032} {"current_steps": 179810, "total_steps": 181800, "loss": 0.0015, "lr": 1.826529165438462e-08, "epoch": 19.78107810781078, "percentage": 98.91, "elapsed_time": "7:05:52", "remaining_time": "0:04:42", "throughput": 1485.07, "total_tokens": 37947088} {"current_steps": 179815, "total_steps": 181800, "loss": 0.1108, "lr": 1.8173678664398785e-08, "epoch": 19.781628162816283, "percentage": 98.91, "elapsed_time": "7:05:53", "remaining_time": "0:04:42", "throughput": 1485.07, "total_tokens": 37948112} {"current_steps": 179820, "total_steps": 181800, "loss": 0.042, "lr": 1.8082295919918945e-08, "epoch": 19.782178217821784, "percentage": 98.91, "elapsed_time": "7:05:53", "remaining_time": "0:04:41", "throughput": 1485.07, "total_tokens": 37949232} {"current_steps": 179825, "total_steps": 181800, "loss": 0.0018, "lr": 1.799114342178887e-08, "epoch": 19.78272827282728, "percentage": 98.91, "elapsed_time": "7:05:54", "remaining_time": "0:04:40", "throughput": 1485.07, "total_tokens": 37950320} {"current_steps": 179830, "total_steps": 181800, "loss": 0.0015, "lr": 1.7900221170844e-08, "epoch": 19.783278327832782, "percentage": 98.92, "elapsed_time": "7:05:55", "remaining_time": "0:04:39", "throughput": 1485.07, "total_tokens": 37951344} {"current_steps": 179835, "total_steps": 181800, "loss": 0.0033, "lr": 1.7809529167928107e-08, "epoch": 19.783828382838283, "percentage": 98.92, "elapsed_time": "7:05:55", "remaining_time": "0:04:39", "throughput": 1485.08, "total_tokens": 37952432} {"current_steps": 179840, "total_steps": 181800, "loss": 0.0017, "lr": 1.771906741387108e-08, "epoch": 19.784378437843785, "percentage": 98.92, "elapsed_time": "7:05:56", "remaining_time": "0:04:38", "throughput": 1485.08, "total_tokens": 37953456} {"current_steps": 179845, "total_steps": 181800, "loss": 0.0018, "lr": 1.7628835909513918e-08, "epoch": 19.784928492849286, "percentage": 98.92, "elapsed_time": "7:05:57", "remaining_time": "0:04:37", "throughput": 1485.08, "total_tokens": 37954448} {"current_steps": 179850, "total_steps": 181800, "loss": 0.0024, "lr": 1.7538834655680957e-08, "epoch": 19.785478547854787, "percentage": 98.93, "elapsed_time": "7:05:57", "remaining_time": "0:04:37", "throughput": 1485.08, "total_tokens": 37955472} {"current_steps": 179855, "total_steps": 181800, "loss": 0.047, "lr": 1.7449063653204866e-08, "epoch": 19.786028602860284, "percentage": 98.93, "elapsed_time": "7:05:58", "remaining_time": "0:04:36", "throughput": 1485.08, "total_tokens": 37956528} {"current_steps": 179860, "total_steps": 181800, "loss": 0.0035, "lr": 1.7359522902915537e-08, "epoch": 19.786578657865785, "percentage": 98.93, "elapsed_time": "7:05:59", "remaining_time": "0:04:35", "throughput": 1485.08, "total_tokens": 37957520} {"current_steps": 179865, "total_steps": 181800, "loss": 0.0266, "lr": 1.7270212405631757e-08, "epoch": 19.787128712871286, "percentage": 98.94, "elapsed_time": "7:06:00", "remaining_time": "0:04:34", "throughput": 1485.08, "total_tokens": 37958544} {"current_steps": 179870, "total_steps": 181800, "loss": 0.1092, "lr": 1.7181132162183423e-08, "epoch": 19.787678767876788, "percentage": 98.94, "elapsed_time": "7:06:00", "remaining_time": "0:04:34", "throughput": 1485.08, "total_tokens": 37959568} {"current_steps": 179875, "total_steps": 181800, "loss": 0.0305, "lr": 1.709228217338654e-08, "epoch": 19.78822882288229, "percentage": 98.94, "elapsed_time": "7:06:01", "remaining_time": "0:04:33", "throughput": 1485.08, "total_tokens": 37960624} {"current_steps": 179880, "total_steps": 181800, "loss": 0.0108, "lr": 1.700366244006546e-08, "epoch": 19.78877887788779, "percentage": 98.94, "elapsed_time": "7:06:02", "remaining_time": "0:04:32", "throughput": 1485.08, "total_tokens": 37961744} {"current_steps": 179885, "total_steps": 181800, "loss": 0.0465, "lr": 1.691527296303064e-08, "epoch": 19.78932893289329, "percentage": 98.95, "elapsed_time": "7:06:02", "remaining_time": "0:04:32", "throughput": 1485.08, "total_tokens": 37962832} {"current_steps": 179890, "total_steps": 181800, "loss": 0.0051, "lr": 1.6827113743100865e-08, "epoch": 19.78987898789879, "percentage": 98.95, "elapsed_time": "7:06:03", "remaining_time": "0:04:31", "throughput": 1485.08, "total_tokens": 37963856} {"current_steps": 179895, "total_steps": 181800, "loss": 0.0008, "lr": 1.6739184781086603e-08, "epoch": 19.79042904290429, "percentage": 98.95, "elapsed_time": "7:06:04", "remaining_time": "0:04:30", "throughput": 1485.08, "total_tokens": 37964880} {"current_steps": 179900, "total_steps": 181800, "loss": 0.0463, "lr": 1.6651486077801092e-08, "epoch": 19.79097909790979, "percentage": 98.95, "elapsed_time": "7:06:04", "remaining_time": "0:04:30", "throughput": 1485.08, "total_tokens": 37965904} {"current_steps": 179905, "total_steps": 181800, "loss": 0.0862, "lr": 1.6564017634049246e-08, "epoch": 19.79152915291529, "percentage": 98.96, "elapsed_time": "7:06:05", "remaining_time": "0:04:29", "throughput": 1485.08, "total_tokens": 37966928} {"current_steps": 179910, "total_steps": 181800, "loss": 0.0786, "lr": 1.6476779450638745e-08, "epoch": 19.792079207920793, "percentage": 98.96, "elapsed_time": "7:06:06", "remaining_time": "0:04:28", "throughput": 1485.09, "total_tokens": 37968016} {"current_steps": 179915, "total_steps": 181800, "loss": 0.0026, "lr": 1.6389771528371734e-08, "epoch": 19.792629262926294, "percentage": 98.96, "elapsed_time": "7:06:06", "remaining_time": "0:04:27", "throughput": 1485.09, "total_tokens": 37969072} {"current_steps": 179920, "total_steps": 181800, "loss": 0.0647, "lr": 1.6302993868055893e-08, "epoch": 19.793179317931795, "percentage": 98.97, "elapsed_time": "7:06:07", "remaining_time": "0:04:27", "throughput": 1485.09, "total_tokens": 37970128} {"current_steps": 179925, "total_steps": 181800, "loss": 0.0025, "lr": 1.621644647048226e-08, "epoch": 19.793729372937293, "percentage": 98.97, "elapsed_time": "7:06:08", "remaining_time": "0:04:26", "throughput": 1485.09, "total_tokens": 37971184} {"current_steps": 179930, "total_steps": 181800, "loss": 0.0063, "lr": 1.6130129336455745e-08, "epoch": 19.794279427942794, "percentage": 98.97, "elapsed_time": "7:06:08", "remaining_time": "0:04:25", "throughput": 1485.09, "total_tokens": 37972208} {"current_steps": 179935, "total_steps": 181800, "loss": 0.0035, "lr": 1.604404246677016e-08, "epoch": 19.794829482948295, "percentage": 98.97, "elapsed_time": "7:06:09", "remaining_time": "0:04:25", "throughput": 1485.09, "total_tokens": 37973296} {"current_steps": 179940, "total_steps": 181800, "loss": 0.0351, "lr": 1.595818586221931e-08, "epoch": 19.795379537953796, "percentage": 98.98, "elapsed_time": "7:06:10", "remaining_time": "0:04:24", "throughput": 1485.09, "total_tokens": 37974320} {"current_steps": 179945, "total_steps": 181800, "loss": 0.0018, "lr": 1.587255952359146e-08, "epoch": 19.795929592959297, "percentage": 98.98, "elapsed_time": "7:06:11", "remaining_time": "0:04:23", "throughput": 1485.09, "total_tokens": 37975408} {"current_steps": 179950, "total_steps": 181800, "loss": 0.0011, "lr": 1.5787163451677632e-08, "epoch": 19.796479647964798, "percentage": 98.98, "elapsed_time": "7:06:11", "remaining_time": "0:04:22", "throughput": 1485.09, "total_tokens": 37976464} {"current_steps": 179955, "total_steps": 181800, "loss": 0.017, "lr": 1.5701997647263323e-08, "epoch": 19.797029702970296, "percentage": 98.99, "elapsed_time": "7:06:12", "remaining_time": "0:04:22", "throughput": 1485.1, "total_tokens": 37977520} {"current_steps": 179960, "total_steps": 181800, "loss": 0.103, "lr": 1.561706211113678e-08, "epoch": 19.797579757975797, "percentage": 98.99, "elapsed_time": "7:06:13", "remaining_time": "0:04:21", "throughput": 1485.1, "total_tokens": 37978576} {"current_steps": 179965, "total_steps": 181800, "loss": 0.0697, "lr": 1.553235684408072e-08, "epoch": 19.798129812981298, "percentage": 98.99, "elapsed_time": "7:06:13", "remaining_time": "0:04:20", "throughput": 1485.1, "total_tokens": 37979664} {"current_steps": 179970, "total_steps": 181800, "loss": 0.0496, "lr": 1.544788184687229e-08, "epoch": 19.7986798679868, "percentage": 98.99, "elapsed_time": "7:06:14", "remaining_time": "0:04:20", "throughput": 1485.1, "total_tokens": 37980784} {"current_steps": 179975, "total_steps": 181800, "loss": 0.0043, "lr": 1.5363637120291428e-08, "epoch": 19.7992299229923, "percentage": 99.0, "elapsed_time": "7:06:15", "remaining_time": "0:04:19", "throughput": 1485.11, "total_tokens": 37981904} {"current_steps": 179980, "total_steps": 181800, "loss": 0.1661, "lr": 1.527962266511529e-08, "epoch": 19.7997799779978, "percentage": 99.0, "elapsed_time": "7:06:15", "remaining_time": "0:04:18", "throughput": 1485.11, "total_tokens": 37982960} {"current_steps": 179985, "total_steps": 181800, "loss": 0.0029, "lr": 1.5195838482118253e-08, "epoch": 19.8003300330033, "percentage": 99.0, "elapsed_time": "7:06:16", "remaining_time": "0:04:17", "throughput": 1485.11, "total_tokens": 37983952} {"current_steps": 179990, "total_steps": 181800, "loss": 0.0326, "lr": 1.5112284572074698e-08, "epoch": 19.8008800880088, "percentage": 99.0, "elapsed_time": "7:06:17", "remaining_time": "0:04:17", "throughput": 1485.11, "total_tokens": 37985040} {"current_steps": 179995, "total_steps": 181800, "loss": 0.0064, "lr": 1.5028960935747905e-08, "epoch": 19.8014301430143, "percentage": 99.01, "elapsed_time": "7:06:17", "remaining_time": "0:04:16", "throughput": 1485.11, "total_tokens": 37986096} {"current_steps": 180000, "total_steps": 181800, "loss": 0.0196, "lr": 1.494586757391503e-08, "epoch": 19.801980198019802, "percentage": 99.01, "elapsed_time": "7:06:18", "remaining_time": "0:04:15", "throughput": 1485.11, "total_tokens": 37987056} {"current_steps": 180005, "total_steps": 181800, "loss": 0.002, "lr": 1.4863004487333799e-08, "epoch": 19.802530253025303, "percentage": 99.01, "elapsed_time": "7:06:19", "remaining_time": "0:04:15", "throughput": 1485.11, "total_tokens": 37988080} {"current_steps": 180010, "total_steps": 181800, "loss": 0.0017, "lr": 1.4780371676773041e-08, "epoch": 19.803080308030804, "percentage": 99.02, "elapsed_time": "7:06:20", "remaining_time": "0:04:14", "throughput": 1485.11, "total_tokens": 37989168} {"current_steps": 180015, "total_steps": 181800, "loss": 0.005, "lr": 1.4697969142990486e-08, "epoch": 19.803630363036305, "percentage": 99.02, "elapsed_time": "7:06:20", "remaining_time": "0:04:13", "throughput": 1485.11, "total_tokens": 37990192} {"current_steps": 180020, "total_steps": 181800, "loss": 0.0748, "lr": 1.4615796886749412e-08, "epoch": 19.804180418041803, "percentage": 99.02, "elapsed_time": "7:06:21", "remaining_time": "0:04:12", "throughput": 1485.11, "total_tokens": 37991248} {"current_steps": 180025, "total_steps": 181800, "loss": 0.0204, "lr": 1.4533854908804767e-08, "epoch": 19.804730473047304, "percentage": 99.02, "elapsed_time": "7:06:22", "remaining_time": "0:04:12", "throughput": 1485.11, "total_tokens": 37992336} {"current_steps": 180030, "total_steps": 181800, "loss": 0.0602, "lr": 1.4452143209911507e-08, "epoch": 19.805280528052805, "percentage": 99.03, "elapsed_time": "7:06:22", "remaining_time": "0:04:11", "throughput": 1485.12, "total_tokens": 37993424} {"current_steps": 180035, "total_steps": 181800, "loss": 0.0011, "lr": 1.437066179082458e-08, "epoch": 19.805830583058306, "percentage": 99.03, "elapsed_time": "7:06:23", "remaining_time": "0:04:10", "throughput": 1485.12, "total_tokens": 37994480} {"current_steps": 180040, "total_steps": 181800, "loss": 0.0051, "lr": 1.4289410652293389e-08, "epoch": 19.806380638063807, "percentage": 99.03, "elapsed_time": "7:06:24", "remaining_time": "0:04:10", "throughput": 1485.12, "total_tokens": 37995536} {"current_steps": 180045, "total_steps": 181800, "loss": 0.0405, "lr": 1.4208389795067334e-08, "epoch": 19.806930693069308, "percentage": 99.03, "elapsed_time": "7:06:24", "remaining_time": "0:04:09", "throughput": 1485.12, "total_tokens": 37996560} {"current_steps": 180050, "total_steps": 181800, "loss": 0.0025, "lr": 1.4127599219895815e-08, "epoch": 19.80748074807481, "percentage": 99.04, "elapsed_time": "7:06:25", "remaining_time": "0:04:08", "throughput": 1485.12, "total_tokens": 37997552} {"current_steps": 180055, "total_steps": 181800, "loss": 0.0032, "lr": 1.4047038927517132e-08, "epoch": 19.808030803080307, "percentage": 99.04, "elapsed_time": "7:06:26", "remaining_time": "0:04:07", "throughput": 1485.12, "total_tokens": 37998608} {"current_steps": 180060, "total_steps": 181800, "loss": 0.0056, "lr": 1.3966708918680681e-08, "epoch": 19.808580858085808, "percentage": 99.04, "elapsed_time": "7:06:26", "remaining_time": "0:04:07", "throughput": 1485.12, "total_tokens": 37999696} {"current_steps": 180065, "total_steps": 181800, "loss": 0.0046, "lr": 1.3886609194121992e-08, "epoch": 19.80913091309131, "percentage": 99.05, "elapsed_time": "7:06:27", "remaining_time": "0:04:06", "throughput": 1485.12, "total_tokens": 38000752} {"current_steps": 180070, "total_steps": 181800, "loss": 0.0766, "lr": 1.3806739754579356e-08, "epoch": 19.80968096809681, "percentage": 99.05, "elapsed_time": "7:06:28", "remaining_time": "0:04:05", "throughput": 1485.12, "total_tokens": 38001840} {"current_steps": 180075, "total_steps": 181800, "loss": 0.1093, "lr": 1.3727100600793852e-08, "epoch": 19.81023102310231, "percentage": 99.05, "elapsed_time": "7:06:29", "remaining_time": "0:04:05", "throughput": 1485.12, "total_tokens": 38002832} {"current_steps": 180080, "total_steps": 181800, "loss": 0.0022, "lr": 1.3647691733492674e-08, "epoch": 19.810781078107812, "percentage": 99.05, "elapsed_time": "7:06:29", "remaining_time": "0:04:04", "throughput": 1485.13, "total_tokens": 38003920} {"current_steps": 180085, "total_steps": 181800, "loss": 0.1453, "lr": 1.356851315341412e-08, "epoch": 19.81133113311331, "percentage": 99.06, "elapsed_time": "7:06:30", "remaining_time": "0:04:03", "throughput": 1485.13, "total_tokens": 38005008} {"current_steps": 180090, "total_steps": 181800, "loss": 0.0634, "lr": 1.3489564861282611e-08, "epoch": 19.81188118811881, "percentage": 99.06, "elapsed_time": "7:06:31", "remaining_time": "0:04:02", "throughput": 1485.13, "total_tokens": 38006000} {"current_steps": 180095, "total_steps": 181800, "loss": 0.0798, "lr": 1.3410846857830894e-08, "epoch": 19.812431243124312, "percentage": 99.06, "elapsed_time": "7:06:31", "remaining_time": "0:04:02", "throughput": 1485.13, "total_tokens": 38007152} {"current_steps": 180100, "total_steps": 181800, "loss": 0.0006, "lr": 1.333235914377784e-08, "epoch": 19.812981298129813, "percentage": 99.06, "elapsed_time": "7:06:32", "remaining_time": "0:04:01", "throughput": 1485.13, "total_tokens": 38008240} {"current_steps": 180105, "total_steps": 181800, "loss": 0.0118, "lr": 1.3254101719853418e-08, "epoch": 19.813531353135314, "percentage": 99.07, "elapsed_time": "7:06:33", "remaining_time": "0:04:00", "throughput": 1485.13, "total_tokens": 38009296} {"current_steps": 180110, "total_steps": 181800, "loss": 0.0009, "lr": 1.3176074586773723e-08, "epoch": 19.814081408140815, "percentage": 99.07, "elapsed_time": "7:06:33", "remaining_time": "0:04:00", "throughput": 1485.13, "total_tokens": 38010320} {"current_steps": 180115, "total_steps": 181800, "loss": 0.0049, "lr": 1.3098277745263176e-08, "epoch": 19.814631463146316, "percentage": 99.07, "elapsed_time": "7:06:34", "remaining_time": "0:03:59", "throughput": 1485.14, "total_tokens": 38011408} {"current_steps": 180120, "total_steps": 181800, "loss": 0.0075, "lr": 1.3020711196035095e-08, "epoch": 19.815181518151814, "percentage": 99.08, "elapsed_time": "7:06:35", "remaining_time": "0:03:58", "throughput": 1485.14, "total_tokens": 38012496} {"current_steps": 180125, "total_steps": 181800, "loss": 0.0108, "lr": 1.2943374939805575e-08, "epoch": 19.815731573157315, "percentage": 99.08, "elapsed_time": "7:06:35", "remaining_time": "0:03:58", "throughput": 1485.14, "total_tokens": 38013616} {"current_steps": 180130, "total_steps": 181800, "loss": 0.0835, "lr": 1.2866268977285156e-08, "epoch": 19.816281628162816, "percentage": 99.08, "elapsed_time": "7:06:36", "remaining_time": "0:03:57", "throughput": 1485.14, "total_tokens": 38014640} {"current_steps": 180135, "total_steps": 181800, "loss": 0.1403, "lr": 1.2789393309187158e-08, "epoch": 19.816831683168317, "percentage": 99.08, "elapsed_time": "7:06:37", "remaining_time": "0:03:56", "throughput": 1485.14, "total_tokens": 38015728} {"current_steps": 180140, "total_steps": 181800, "loss": 0.0065, "lr": 1.2712747936219349e-08, "epoch": 19.817381738173818, "percentage": 99.09, "elapsed_time": "7:06:38", "remaining_time": "0:03:55", "throughput": 1485.15, "total_tokens": 38016784} {"current_steps": 180145, "total_steps": 181800, "loss": 0.0321, "lr": 1.2636332859089495e-08, "epoch": 19.81793179317932, "percentage": 99.09, "elapsed_time": "7:06:38", "remaining_time": "0:03:55", "throughput": 1485.15, "total_tokens": 38017808} {"current_steps": 180150, "total_steps": 181800, "loss": 0.0011, "lr": 1.2560148078497035e-08, "epoch": 19.818481848184817, "percentage": 99.09, "elapsed_time": "7:06:39", "remaining_time": "0:03:54", "throughput": 1485.15, "total_tokens": 38018864} {"current_steps": 180155, "total_steps": 181800, "loss": 0.0015, "lr": 1.2484193595152516e-08, "epoch": 19.819031903190318, "percentage": 99.1, "elapsed_time": "7:06:40", "remaining_time": "0:03:53", "throughput": 1485.15, "total_tokens": 38019952} {"current_steps": 180160, "total_steps": 181800, "loss": 0.0025, "lr": 1.2408469409747048e-08, "epoch": 19.81958195819582, "percentage": 99.1, "elapsed_time": "7:06:40", "remaining_time": "0:03:53", "throughput": 1485.15, "total_tokens": 38021040} {"current_steps": 180165, "total_steps": 181800, "loss": 0.0015, "lr": 1.2332975522982848e-08, "epoch": 19.82013201320132, "percentage": 99.1, "elapsed_time": "7:06:41", "remaining_time": "0:03:52", "throughput": 1485.16, "total_tokens": 38022128} {"current_steps": 180170, "total_steps": 181800, "loss": 0.0017, "lr": 1.2257711935556582e-08, "epoch": 19.82068206820682, "percentage": 99.1, "elapsed_time": "7:06:42", "remaining_time": "0:03:51", "throughput": 1485.16, "total_tokens": 38023184} {"current_steps": 180175, "total_steps": 181800, "loss": 0.0041, "lr": 1.2182678648159363e-08, "epoch": 19.821232123212322, "percentage": 99.11, "elapsed_time": "7:06:42", "remaining_time": "0:03:50", "throughput": 1485.16, "total_tokens": 38024208} {"current_steps": 180180, "total_steps": 181800, "loss": 0.0015, "lr": 1.210787566148508e-08, "epoch": 19.821782178217823, "percentage": 99.11, "elapsed_time": "7:06:43", "remaining_time": "0:03:50", "throughput": 1485.16, "total_tokens": 38025264} {"current_steps": 180185, "total_steps": 181800, "loss": 0.0443, "lr": 1.2033302976222071e-08, "epoch": 19.82233223322332, "percentage": 99.11, "elapsed_time": "7:06:44", "remaining_time": "0:03:49", "throughput": 1485.16, "total_tokens": 38026256} {"current_steps": 180190, "total_steps": 181800, "loss": 0.0093, "lr": 1.1958960593058676e-08, "epoch": 19.822882288228822, "percentage": 99.11, "elapsed_time": "7:06:44", "remaining_time": "0:03:48", "throughput": 1485.16, "total_tokens": 38027312} {"current_steps": 180195, "total_steps": 181800, "loss": 0.0555, "lr": 1.1884848512677683e-08, "epoch": 19.823432343234323, "percentage": 99.12, "elapsed_time": "7:06:45", "remaining_time": "0:03:48", "throughput": 1485.16, "total_tokens": 38028304} {"current_steps": 180200, "total_steps": 181800, "loss": 0.0021, "lr": 1.1810966735764651e-08, "epoch": 19.823982398239824, "percentage": 99.12, "elapsed_time": "7:06:46", "remaining_time": "0:03:47", "throughput": 1485.16, "total_tokens": 38029392} {"current_steps": 180205, "total_steps": 181800, "loss": 0.0054, "lr": 1.1737315262999593e-08, "epoch": 19.824532453245325, "percentage": 99.12, "elapsed_time": "7:06:46", "remaining_time": "0:03:46", "throughput": 1485.16, "total_tokens": 38030448} {"current_steps": 180210, "total_steps": 181800, "loss": 0.0108, "lr": 1.1663894095059747e-08, "epoch": 19.825082508250826, "percentage": 99.13, "elapsed_time": "7:06:47", "remaining_time": "0:03:45", "throughput": 1485.16, "total_tokens": 38031472} {"current_steps": 180215, "total_steps": 181800, "loss": 0.0122, "lr": 1.1590703232625122e-08, "epoch": 19.825632563256324, "percentage": 99.13, "elapsed_time": "7:06:48", "remaining_time": "0:03:45", "throughput": 1485.16, "total_tokens": 38032560} {"current_steps": 180220, "total_steps": 181800, "loss": 0.0866, "lr": 1.151774267636463e-08, "epoch": 19.826182618261825, "percentage": 99.13, "elapsed_time": "7:06:49", "remaining_time": "0:03:44", "throughput": 1485.16, "total_tokens": 38033616} {"current_steps": 180225, "total_steps": 181800, "loss": 0.0069, "lr": 1.144501242695828e-08, "epoch": 19.826732673267326, "percentage": 99.13, "elapsed_time": "7:06:49", "remaining_time": "0:03:43", "throughput": 1485.17, "total_tokens": 38034736} {"current_steps": 180230, "total_steps": 181800, "loss": 0.0016, "lr": 1.1372512485072206e-08, "epoch": 19.827282728272827, "percentage": 99.14, "elapsed_time": "7:06:50", "remaining_time": "0:03:43", "throughput": 1485.17, "total_tokens": 38035760} {"current_steps": 180235, "total_steps": 181800, "loss": 0.0953, "lr": 1.1300242851372545e-08, "epoch": 19.82783278327833, "percentage": 99.14, "elapsed_time": "7:06:51", "remaining_time": "0:03:42", "throughput": 1485.17, "total_tokens": 38036848} {"current_steps": 180240, "total_steps": 181800, "loss": 0.0814, "lr": 1.1228203526530978e-08, "epoch": 19.82838283828383, "percentage": 99.14, "elapsed_time": "7:06:51", "remaining_time": "0:03:41", "throughput": 1485.17, "total_tokens": 38037872} {"current_steps": 180245, "total_steps": 181800, "loss": 0.0157, "lr": 1.1156394511205315e-08, "epoch": 19.82893289328933, "percentage": 99.14, "elapsed_time": "7:06:52", "remaining_time": "0:03:40", "throughput": 1485.17, "total_tokens": 38038928} {"current_steps": 180250, "total_steps": 181800, "loss": 0.0064, "lr": 1.1084815806061688e-08, "epoch": 19.829482948294828, "percentage": 99.15, "elapsed_time": "7:06:53", "remaining_time": "0:03:40", "throughput": 1485.17, "total_tokens": 38039952} {"current_steps": 180255, "total_steps": 181800, "loss": 0.003, "lr": 1.1013467411757905e-08, "epoch": 19.83003300330033, "percentage": 99.15, "elapsed_time": "7:06:53", "remaining_time": "0:03:39", "throughput": 1485.17, "total_tokens": 38041008} {"current_steps": 180260, "total_steps": 181800, "loss": 0.0401, "lr": 1.0942349328951773e-08, "epoch": 19.83058305830583, "percentage": 99.15, "elapsed_time": "7:06:54", "remaining_time": "0:03:38", "throughput": 1485.17, "total_tokens": 38042096} {"current_steps": 180265, "total_steps": 181800, "loss": 0.0054, "lr": 1.0871461558301099e-08, "epoch": 19.83113311331133, "percentage": 99.16, "elapsed_time": "7:06:55", "remaining_time": "0:03:38", "throughput": 1485.18, "total_tokens": 38043152} {"current_steps": 180270, "total_steps": 181800, "loss": 0.0188, "lr": 1.0800804100455364e-08, "epoch": 19.831683168316832, "percentage": 99.16, "elapsed_time": "7:06:55", "remaining_time": "0:03:37", "throughput": 1485.18, "total_tokens": 38044176} {"current_steps": 180275, "total_steps": 181800, "loss": 0.0601, "lr": 1.07303769560696e-08, "epoch": 19.832233223322334, "percentage": 99.16, "elapsed_time": "7:06:56", "remaining_time": "0:03:36", "throughput": 1485.18, "total_tokens": 38045200} {"current_steps": 180280, "total_steps": 181800, "loss": 0.0056, "lr": 1.0660180125790509e-08, "epoch": 19.83278327832783, "percentage": 99.16, "elapsed_time": "7:06:57", "remaining_time": "0:03:35", "throughput": 1485.18, "total_tokens": 38046256} {"current_steps": 180285, "total_steps": 181800, "loss": 0.0012, "lr": 1.0590213610264798e-08, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "7:06:58", "remaining_time": "0:03:35", "throughput": 1485.18, "total_tokens": 38047376} {"current_steps": 180290, "total_steps": 181800, "loss": 0.0052, "lr": 1.0520477410136398e-08, "epoch": 19.833883388338833, "percentage": 99.17, "elapsed_time": "7:06:58", "remaining_time": "0:03:34", "throughput": 1485.18, "total_tokens": 38048496} {"current_steps": 180295, "total_steps": 181800, "loss": 0.0042, "lr": 1.0450971526052012e-08, "epoch": 19.834433443344334, "percentage": 99.17, "elapsed_time": "7:06:59", "remaining_time": "0:03:33", "throughput": 1485.18, "total_tokens": 38049488} {"current_steps": 180300, "total_steps": 181800, "loss": 0.0796, "lr": 1.0381695958647242e-08, "epoch": 19.834983498349835, "percentage": 99.17, "elapsed_time": "7:07:00", "remaining_time": "0:03:33", "throughput": 1485.18, "total_tokens": 38050448} {"current_steps": 180305, "total_steps": 181800, "loss": 0.0055, "lr": 1.0312650708566018e-08, "epoch": 19.835533553355337, "percentage": 99.18, "elapsed_time": "7:07:00", "remaining_time": "0:03:32", "throughput": 1485.18, "total_tokens": 38051504} {"current_steps": 180310, "total_steps": 181800, "loss": 0.0101, "lr": 1.0243835776441168e-08, "epoch": 19.836083608360838, "percentage": 99.18, "elapsed_time": "7:07:01", "remaining_time": "0:03:31", "throughput": 1485.18, "total_tokens": 38052560} {"current_steps": 180315, "total_steps": 181800, "loss": 0.0705, "lr": 1.017525116290552e-08, "epoch": 19.836633663366335, "percentage": 99.18, "elapsed_time": "7:07:02", "remaining_time": "0:03:31", "throughput": 1485.19, "total_tokens": 38053648} {"current_steps": 180320, "total_steps": 181800, "loss": 0.0014, "lr": 1.0106896868597449e-08, "epoch": 19.837183718371836, "percentage": 99.19, "elapsed_time": "7:07:02", "remaining_time": "0:03:30", "throughput": 1485.19, "total_tokens": 38054736} {"current_steps": 180325, "total_steps": 181800, "loss": 0.0029, "lr": 1.0038772894138681e-08, "epoch": 19.837733773377337, "percentage": 99.19, "elapsed_time": "7:07:03", "remaining_time": "0:03:29", "throughput": 1485.19, "total_tokens": 38055792} {"current_steps": 180330, "total_steps": 181800, "loss": 0.005, "lr": 9.970879240164822e-09, "epoch": 19.83828382838284, "percentage": 99.19, "elapsed_time": "7:07:04", "remaining_time": "0:03:28", "throughput": 1485.19, "total_tokens": 38056816} {"current_steps": 180335, "total_steps": 181800, "loss": 0.007, "lr": 9.903215907294817e-09, "epoch": 19.83883388338834, "percentage": 99.19, "elapsed_time": "7:07:04", "remaining_time": "0:03:28", "throughput": 1485.19, "total_tokens": 38057808} {"current_steps": 180340, "total_steps": 181800, "loss": 0.0259, "lr": 9.835782896155943e-09, "epoch": 19.83938393839384, "percentage": 99.2, "elapsed_time": "7:07:05", "remaining_time": "0:03:27", "throughput": 1485.19, "total_tokens": 38058768} {"current_steps": 180345, "total_steps": 181800, "loss": 0.0041, "lr": 9.768580207369926e-09, "epoch": 19.83993399339934, "percentage": 99.2, "elapsed_time": "7:07:06", "remaining_time": "0:03:26", "throughput": 1485.19, "total_tokens": 38059856} {"current_steps": 180350, "total_steps": 181800, "loss": 0.004, "lr": 9.701607841555715e-09, "epoch": 19.84048404840484, "percentage": 99.2, "elapsed_time": "7:07:06", "remaining_time": "0:03:26", "throughput": 1485.19, "total_tokens": 38060944} {"current_steps": 180355, "total_steps": 181800, "loss": 0.004, "lr": 9.634865799329484e-09, "epoch": 19.84103410341034, "percentage": 99.21, "elapsed_time": "7:07:07", "remaining_time": "0:03:25", "throughput": 1485.19, "total_tokens": 38062032} {"current_steps": 180360, "total_steps": 181800, "loss": 0.0091, "lr": 9.568354081307406e-09, "epoch": 19.84158415841584, "percentage": 99.21, "elapsed_time": "7:07:08", "remaining_time": "0:03:24", "throughput": 1485.19, "total_tokens": 38063088} {"current_steps": 180365, "total_steps": 181800, "loss": 0.0009, "lr": 9.502072688102881e-09, "epoch": 19.842134213421343, "percentage": 99.21, "elapsed_time": "7:07:09", "remaining_time": "0:03:23", "throughput": 1485.19, "total_tokens": 38064144} {"current_steps": 180370, "total_steps": 181800, "loss": 0.0025, "lr": 9.436021620326529e-09, "epoch": 19.842684268426844, "percentage": 99.21, "elapsed_time": "7:07:09", "remaining_time": "0:03:23", "throughput": 1485.2, "total_tokens": 38065200} {"current_steps": 180375, "total_steps": 181800, "loss": 0.0239, "lr": 9.3702008785862e-09, "epoch": 19.843234323432345, "percentage": 99.22, "elapsed_time": "7:07:10", "remaining_time": "0:03:22", "throughput": 1485.2, "total_tokens": 38066256} {"current_steps": 180380, "total_steps": 181800, "loss": 0.0022, "lr": 9.304610463489738e-09, "epoch": 19.843784378437842, "percentage": 99.22, "elapsed_time": "7:07:11", "remaining_time": "0:03:21", "throughput": 1485.2, "total_tokens": 38067312} {"current_steps": 180385, "total_steps": 181800, "loss": 0.0018, "lr": 9.239250375639441e-09, "epoch": 19.844334433443343, "percentage": 99.22, "elapsed_time": "7:07:11", "remaining_time": "0:03:21", "throughput": 1485.2, "total_tokens": 38068432} {"current_steps": 180390, "total_steps": 181800, "loss": 0.0027, "lr": 9.174120615640381e-09, "epoch": 19.844884488448844, "percentage": 99.22, "elapsed_time": "7:07:12", "remaining_time": "0:03:20", "throughput": 1485.21, "total_tokens": 38069552} {"current_steps": 180395, "total_steps": 181800, "loss": 0.0481, "lr": 9.1092211840893e-09, "epoch": 19.845434543454346, "percentage": 99.23, "elapsed_time": "7:07:13", "remaining_time": "0:03:19", "throughput": 1485.2, "total_tokens": 38070576} {"current_steps": 180400, "total_steps": 181800, "loss": 0.0255, "lr": 9.044552081588497e-09, "epoch": 19.845984598459847, "percentage": 99.23, "elapsed_time": "7:07:13", "remaining_time": "0:03:18", "throughput": 1485.2, "total_tokens": 38071600} {"current_steps": 180405, "total_steps": 181800, "loss": 0.0291, "lr": 8.980113308731942e-09, "epoch": 19.846534653465348, "percentage": 99.23, "elapsed_time": "7:07:14", "remaining_time": "0:03:18", "throughput": 1485.2, "total_tokens": 38072624} {"current_steps": 180410, "total_steps": 181800, "loss": 0.0015, "lr": 8.915904866116376e-09, "epoch": 19.847084708470845, "percentage": 99.24, "elapsed_time": "7:07:15", "remaining_time": "0:03:17", "throughput": 1485.21, "total_tokens": 38073680} {"current_steps": 180415, "total_steps": 181800, "loss": 0.0016, "lr": 8.851926754327444e-09, "epoch": 19.847634763476346, "percentage": 99.24, "elapsed_time": "7:07:15", "remaining_time": "0:03:16", "throughput": 1485.21, "total_tokens": 38074704} {"current_steps": 180420, "total_steps": 181800, "loss": 0.1203, "lr": 8.788178973959115e-09, "epoch": 19.848184818481847, "percentage": 99.24, "elapsed_time": "7:07:16", "remaining_time": "0:03:16", "throughput": 1485.21, "total_tokens": 38075760} {"current_steps": 180425, "total_steps": 181800, "loss": 0.003, "lr": 8.724661525599809e-09, "epoch": 19.84873487348735, "percentage": 99.24, "elapsed_time": "7:07:17", "remaining_time": "0:03:15", "throughput": 1485.21, "total_tokens": 38076816} {"current_steps": 180430, "total_steps": 181800, "loss": 0.0397, "lr": 8.66137440983239e-09, "epoch": 19.84928492849285, "percentage": 99.25, "elapsed_time": "7:07:18", "remaining_time": "0:03:14", "throughput": 1485.21, "total_tokens": 38077904} {"current_steps": 180435, "total_steps": 181800, "loss": 0.0039, "lr": 8.598317627239727e-09, "epoch": 19.84983498349835, "percentage": 99.25, "elapsed_time": "7:07:18", "remaining_time": "0:03:13", "throughput": 1485.21, "total_tokens": 38078960} {"current_steps": 180440, "total_steps": 181800, "loss": 0.0662, "lr": 8.535491178407462e-09, "epoch": 19.850385038503852, "percentage": 99.25, "elapsed_time": "7:07:19", "remaining_time": "0:03:13", "throughput": 1485.21, "total_tokens": 38080048} {"current_steps": 180445, "total_steps": 181800, "loss": 0.0027, "lr": 8.472895063910135e-09, "epoch": 19.85093509350935, "percentage": 99.25, "elapsed_time": "7:07:20", "remaining_time": "0:03:12", "throughput": 1485.21, "total_tokens": 38081072} {"current_steps": 180450, "total_steps": 181800, "loss": 0.1086, "lr": 8.410529284325064e-09, "epoch": 19.85148514851485, "percentage": 99.26, "elapsed_time": "7:07:20", "remaining_time": "0:03:11", "throughput": 1485.22, "total_tokens": 38082128} {"current_steps": 180455, "total_steps": 181800, "loss": 0.0856, "lr": 8.348393840226787e-09, "epoch": 19.85203520352035, "percentage": 99.26, "elapsed_time": "7:07:21", "remaining_time": "0:03:11", "throughput": 1485.22, "total_tokens": 38083152} {"current_steps": 180460, "total_steps": 181800, "loss": 0.0145, "lr": 8.286488732192621e-09, "epoch": 19.852585258525853, "percentage": 99.26, "elapsed_time": "7:07:22", "remaining_time": "0:03:10", "throughput": 1485.22, "total_tokens": 38084240} {"current_steps": 180465, "total_steps": 181800, "loss": 0.0021, "lr": 8.22481396078878e-09, "epoch": 19.853135313531354, "percentage": 99.27, "elapsed_time": "7:07:22", "remaining_time": "0:03:09", "throughput": 1485.22, "total_tokens": 38085264} {"current_steps": 180470, "total_steps": 181800, "loss": 0.0978, "lr": 8.163369526584252e-09, "epoch": 19.853685368536855, "percentage": 99.27, "elapsed_time": "7:07:23", "remaining_time": "0:03:08", "throughput": 1485.22, "total_tokens": 38086320} {"current_steps": 180475, "total_steps": 181800, "loss": 0.01, "lr": 8.102155430145253e-09, "epoch": 19.854235423542356, "percentage": 99.27, "elapsed_time": "7:07:24", "remaining_time": "0:03:08", "throughput": 1485.22, "total_tokens": 38087312} {"current_steps": 180480, "total_steps": 181800, "loss": 0.0021, "lr": 8.04117167203522e-09, "epoch": 19.854785478547853, "percentage": 99.27, "elapsed_time": "7:07:24", "remaining_time": "0:03:07", "throughput": 1485.22, "total_tokens": 38088336} {"current_steps": 180485, "total_steps": 181800, "loss": 0.0048, "lr": 7.98041825281759e-09, "epoch": 19.855335533553355, "percentage": 99.28, "elapsed_time": "7:07:25", "remaining_time": "0:03:06", "throughput": 1485.22, "total_tokens": 38089328} {"current_steps": 180490, "total_steps": 181800, "loss": 0.0728, "lr": 7.919895173053027e-09, "epoch": 19.855885588558856, "percentage": 99.28, "elapsed_time": "7:07:26", "remaining_time": "0:03:06", "throughput": 1485.22, "total_tokens": 38090416} {"current_steps": 180495, "total_steps": 181800, "loss": 0.1015, "lr": 7.859602433299417e-09, "epoch": 19.856435643564357, "percentage": 99.28, "elapsed_time": "7:07:26", "remaining_time": "0:03:05", "throughput": 1485.22, "total_tokens": 38091472} {"current_steps": 180500, "total_steps": 181800, "loss": 0.044, "lr": 7.799540034111874e-09, "epoch": 19.856985698569858, "percentage": 99.28, "elapsed_time": "7:07:27", "remaining_time": "0:03:04", "throughput": 1485.22, "total_tokens": 38092528} {"current_steps": 180505, "total_steps": 181800, "loss": 0.0068, "lr": 7.739707976042732e-09, "epoch": 19.85753575357536, "percentage": 99.29, "elapsed_time": "7:07:28", "remaining_time": "0:03:04", "throughput": 1485.22, "total_tokens": 38093552} {"current_steps": 180510, "total_steps": 181800, "loss": 0.0027, "lr": 7.680106259641551e-09, "epoch": 19.858085808580856, "percentage": 99.29, "elapsed_time": "7:07:29", "remaining_time": "0:03:03", "throughput": 1485.22, "total_tokens": 38094608} {"current_steps": 180515, "total_steps": 181800, "loss": 0.0112, "lr": 7.620734885463443e-09, "epoch": 19.858635863586358, "percentage": 99.29, "elapsed_time": "7:07:29", "remaining_time": "0:03:02", "throughput": 1485.22, "total_tokens": 38095632} {"current_steps": 180520, "total_steps": 181800, "loss": 0.0055, "lr": 7.561593854052418e-09, "epoch": 19.85918591859186, "percentage": 99.3, "elapsed_time": "7:07:30", "remaining_time": "0:03:01", "throughput": 1485.23, "total_tokens": 38096752} {"current_steps": 180525, "total_steps": 181800, "loss": 0.0026, "lr": 7.502683165952484e-09, "epoch": 19.85973597359736, "percentage": 99.3, "elapsed_time": "7:07:31", "remaining_time": "0:03:01", "throughput": 1485.23, "total_tokens": 38097776} {"current_steps": 180530, "total_steps": 181800, "loss": 0.0009, "lr": 7.444002821707652e-09, "epoch": 19.86028602860286, "percentage": 99.3, "elapsed_time": "7:07:31", "remaining_time": "0:03:00", "throughput": 1485.23, "total_tokens": 38098864} {"current_steps": 180535, "total_steps": 181800, "loss": 0.0569, "lr": 7.385552821859154e-09, "epoch": 19.860836083608362, "percentage": 99.3, "elapsed_time": "7:07:32", "remaining_time": "0:02:59", "throughput": 1485.23, "total_tokens": 38099920} {"current_steps": 180540, "total_steps": 181800, "loss": 0.0031, "lr": 7.3273331669454495e-09, "epoch": 19.861386138613863, "percentage": 99.31, "elapsed_time": "7:07:33", "remaining_time": "0:02:59", "throughput": 1485.23, "total_tokens": 38100944} {"current_steps": 180545, "total_steps": 181800, "loss": 0.097, "lr": 7.269343857504996e-09, "epoch": 19.86193619361936, "percentage": 99.31, "elapsed_time": "7:07:33", "remaining_time": "0:02:58", "throughput": 1485.23, "total_tokens": 38102032} {"current_steps": 180550, "total_steps": 181800, "loss": 0.0791, "lr": 7.211584894067924e-09, "epoch": 19.86248624862486, "percentage": 99.31, "elapsed_time": "7:07:34", "remaining_time": "0:02:57", "throughput": 1485.24, "total_tokens": 38103088} {"current_steps": 180555, "total_steps": 181800, "loss": 0.0049, "lr": 7.154056277169918e-09, "epoch": 19.863036303630363, "percentage": 99.32, "elapsed_time": "7:07:35", "remaining_time": "0:02:56", "throughput": 1485.24, "total_tokens": 38104144} {"current_steps": 180560, "total_steps": 181800, "loss": 0.0166, "lr": 7.096758007338333e-09, "epoch": 19.863586358635864, "percentage": 99.32, "elapsed_time": "7:07:35", "remaining_time": "0:02:56", "throughput": 1485.24, "total_tokens": 38105200} {"current_steps": 180565, "total_steps": 181800, "loss": 0.0019, "lr": 7.039690085106076e-09, "epoch": 19.864136413641365, "percentage": 99.32, "elapsed_time": "7:07:36", "remaining_time": "0:02:55", "throughput": 1485.24, "total_tokens": 38106192} {"current_steps": 180570, "total_steps": 181800, "loss": 0.0014, "lr": 6.982852510994953e-09, "epoch": 19.864686468646866, "percentage": 99.32, "elapsed_time": "7:07:37", "remaining_time": "0:02:54", "throughput": 1485.24, "total_tokens": 38107216} {"current_steps": 180575, "total_steps": 181800, "loss": 0.0664, "lr": 6.926245285529542e-09, "epoch": 19.865236523652364, "percentage": 99.33, "elapsed_time": "7:07:38", "remaining_time": "0:02:54", "throughput": 1485.24, "total_tokens": 38108240} {"current_steps": 180580, "total_steps": 181800, "loss": 0.1021, "lr": 6.86986840923165e-09, "epoch": 19.865786578657865, "percentage": 99.33, "elapsed_time": "7:07:38", "remaining_time": "0:02:53", "throughput": 1485.24, "total_tokens": 38109264} {"current_steps": 180585, "total_steps": 181800, "loss": 0.0057, "lr": 6.813721882623081e-09, "epoch": 19.866336633663366, "percentage": 99.33, "elapsed_time": "7:07:39", "remaining_time": "0:02:52", "throughput": 1485.24, "total_tokens": 38110320} {"current_steps": 180590, "total_steps": 181800, "loss": 0.0043, "lr": 6.757805706217313e-09, "epoch": 19.866886688668867, "percentage": 99.33, "elapsed_time": "7:07:40", "remaining_time": "0:02:51", "throughput": 1485.24, "total_tokens": 38111312} {"current_steps": 180595, "total_steps": 181800, "loss": 0.0728, "lr": 6.702119880533375e-09, "epoch": 19.867436743674368, "percentage": 99.34, "elapsed_time": "7:07:40", "remaining_time": "0:02:51", "throughput": 1485.24, "total_tokens": 38112368} {"current_steps": 180600, "total_steps": 181800, "loss": 0.0068, "lr": 6.646664406084746e-09, "epoch": 19.86798679867987, "percentage": 99.34, "elapsed_time": "7:07:41", "remaining_time": "0:02:50", "throughput": 1485.24, "total_tokens": 38113392} {"current_steps": 180605, "total_steps": 181800, "loss": 0.0013, "lr": 6.591439283379353e-09, "epoch": 19.86853685368537, "percentage": 99.34, "elapsed_time": "7:07:42", "remaining_time": "0:02:49", "throughput": 1485.24, "total_tokens": 38114544} {"current_steps": 180610, "total_steps": 181800, "loss": 0.0673, "lr": 6.5364445129251214e-09, "epoch": 19.869086908690868, "percentage": 99.35, "elapsed_time": "7:07:42", "remaining_time": "0:02:49", "throughput": 1485.24, "total_tokens": 38115600} {"current_steps": 180615, "total_steps": 181800, "loss": 0.0265, "lr": 6.481680095235532e-09, "epoch": 19.86963696369637, "percentage": 99.35, "elapsed_time": "7:07:43", "remaining_time": "0:02:48", "throughput": 1485.24, "total_tokens": 38116656} {"current_steps": 180620, "total_steps": 181800, "loss": 0.0682, "lr": 6.427146030807407e-09, "epoch": 19.87018701870187, "percentage": 99.35, "elapsed_time": "7:07:44", "remaining_time": "0:02:47", "throughput": 1485.25, "total_tokens": 38117776} {"current_steps": 180625, "total_steps": 181800, "loss": 0.0017, "lr": 6.372842320151451e-09, "epoch": 19.87073707370737, "percentage": 99.35, "elapsed_time": "7:07:44", "remaining_time": "0:02:46", "throughput": 1485.25, "total_tokens": 38118832} {"current_steps": 180630, "total_steps": 181800, "loss": 0.0347, "lr": 6.318768963758936e-09, "epoch": 19.871287128712872, "percentage": 99.36, "elapsed_time": "7:07:45", "remaining_time": "0:02:46", "throughput": 1485.25, "total_tokens": 38119856} {"current_steps": 180635, "total_steps": 181800, "loss": 0.0121, "lr": 6.264925962137791e-09, "epoch": 19.871837183718373, "percentage": 99.36, "elapsed_time": "7:07:46", "remaining_time": "0:02:45", "throughput": 1485.25, "total_tokens": 38120912} {"current_steps": 180640, "total_steps": 181800, "loss": 0.0037, "lr": 6.211313315776512e-09, "epoch": 19.87238723872387, "percentage": 99.36, "elapsed_time": "7:07:47", "remaining_time": "0:02:44", "throughput": 1485.25, "total_tokens": 38121936} {"current_steps": 180645, "total_steps": 181800, "loss": 0.0065, "lr": 6.157931025174701e-09, "epoch": 19.872937293729372, "percentage": 99.36, "elapsed_time": "7:07:47", "remaining_time": "0:02:44", "throughput": 1485.25, "total_tokens": 38122992} {"current_steps": 180650, "total_steps": 181800, "loss": 0.0178, "lr": 6.104779090820856e-09, "epoch": 19.873487348734873, "percentage": 99.37, "elapsed_time": "7:07:48", "remaining_time": "0:02:43", "throughput": 1485.25, "total_tokens": 38124112} {"current_steps": 180655, "total_steps": 181800, "loss": 0.0622, "lr": 6.05185751320625e-09, "epoch": 19.874037403740374, "percentage": 99.37, "elapsed_time": "7:07:49", "remaining_time": "0:02:42", "throughput": 1485.26, "total_tokens": 38125168} {"current_steps": 180660, "total_steps": 181800, "loss": 0.1457, "lr": 5.9991662928166045e-09, "epoch": 19.874587458745875, "percentage": 99.37, "elapsed_time": "7:07:49", "remaining_time": "0:02:41", "throughput": 1485.26, "total_tokens": 38126224} {"current_steps": 180665, "total_steps": 181800, "loss": 0.0257, "lr": 5.946705430143196e-09, "epoch": 19.875137513751376, "percentage": 99.38, "elapsed_time": "7:07:50", "remaining_time": "0:02:41", "throughput": 1485.26, "total_tokens": 38127280} {"current_steps": 180670, "total_steps": 181800, "loss": 0.0029, "lr": 5.894474925663418e-09, "epoch": 19.875687568756877, "percentage": 99.38, "elapsed_time": "7:07:51", "remaining_time": "0:02:40", "throughput": 1485.26, "total_tokens": 38128304} {"current_steps": 180675, "total_steps": 181800, "loss": 0.0602, "lr": 5.842474779860219e-09, "epoch": 19.876237623762375, "percentage": 99.38, "elapsed_time": "7:07:51", "remaining_time": "0:02:39", "throughput": 1485.26, "total_tokens": 38129360} {"current_steps": 180680, "total_steps": 181800, "loss": 0.0041, "lr": 5.7907049932137695e-09, "epoch": 19.876787678767876, "percentage": 99.38, "elapsed_time": "7:07:52", "remaining_time": "0:02:39", "throughput": 1485.26, "total_tokens": 38130416} {"current_steps": 180685, "total_steps": 181800, "loss": 0.0049, "lr": 5.7391655662014655e-09, "epoch": 19.877337733773377, "percentage": 99.39, "elapsed_time": "7:07:53", "remaining_time": "0:02:38", "throughput": 1485.26, "total_tokens": 38131472} {"current_steps": 180690, "total_steps": 181800, "loss": 0.0031, "lr": 5.687856499297928e-09, "epoch": 19.877887788778878, "percentage": 99.39, "elapsed_time": "7:07:53", "remaining_time": "0:02:37", "throughput": 1485.26, "total_tokens": 38132528} {"current_steps": 180695, "total_steps": 181800, "loss": 0.0138, "lr": 5.6367777929777765e-09, "epoch": 19.87843784378438, "percentage": 99.39, "elapsed_time": "7:07:54", "remaining_time": "0:02:37", "throughput": 1485.26, "total_tokens": 38133584} {"current_steps": 180700, "total_steps": 181800, "loss": 0.0037, "lr": 5.585929447707305e-09, "epoch": 19.87898789878988, "percentage": 99.39, "elapsed_time": "7:07:55", "remaining_time": "0:02:36", "throughput": 1485.26, "total_tokens": 38134608} {"current_steps": 180705, "total_steps": 181800, "loss": 0.1031, "lr": 5.535311463958359e-09, "epoch": 19.879537953795378, "percentage": 99.4, "elapsed_time": "7:07:55", "remaining_time": "0:02:35", "throughput": 1485.26, "total_tokens": 38135632} {"current_steps": 180710, "total_steps": 181800, "loss": 0.006, "lr": 5.4849238421972314e-09, "epoch": 19.88008800880088, "percentage": 99.4, "elapsed_time": "7:07:56", "remaining_time": "0:02:34", "throughput": 1485.27, "total_tokens": 38136752} {"current_steps": 180715, "total_steps": 181800, "loss": 0.003, "lr": 5.434766582887441e-09, "epoch": 19.88063806380638, "percentage": 99.4, "elapsed_time": "7:07:57", "remaining_time": "0:02:34", "throughput": 1485.27, "total_tokens": 38137744} {"current_steps": 180720, "total_steps": 181800, "loss": 0.0077, "lr": 5.384839686492505e-09, "epoch": 19.88118811881188, "percentage": 99.41, "elapsed_time": "7:07:58", "remaining_time": "0:02:33", "throughput": 1485.27, "total_tokens": 38138800} {"current_steps": 180725, "total_steps": 181800, "loss": 0.0046, "lr": 5.3351431534731656e-09, "epoch": 19.881738173817382, "percentage": 99.41, "elapsed_time": "7:07:58", "remaining_time": "0:02:32", "throughput": 1485.27, "total_tokens": 38139824} {"current_steps": 180730, "total_steps": 181800, "loss": 0.0602, "lr": 5.285676984284615e-09, "epoch": 19.882288228822883, "percentage": 99.41, "elapsed_time": "7:07:59", "remaining_time": "0:02:32", "throughput": 1485.27, "total_tokens": 38140816} {"current_steps": 180735, "total_steps": 181800, "loss": 0.0288, "lr": 5.236441179384821e-09, "epoch": 19.882838283828384, "percentage": 99.41, "elapsed_time": "7:08:00", "remaining_time": "0:02:31", "throughput": 1485.27, "total_tokens": 38141872} {"current_steps": 180740, "total_steps": 181800, "loss": 0.0007, "lr": 5.187435739226199e-09, "epoch": 19.883388338833882, "percentage": 99.42, "elapsed_time": "7:08:00", "remaining_time": "0:02:30", "throughput": 1485.27, "total_tokens": 38142928} {"current_steps": 180745, "total_steps": 181800, "loss": 0.0691, "lr": 5.138660664263939e-09, "epoch": 19.883938393839383, "percentage": 99.42, "elapsed_time": "7:08:01", "remaining_time": "0:02:29", "throughput": 1485.27, "total_tokens": 38143984} {"current_steps": 180750, "total_steps": 181800, "loss": 0.0585, "lr": 5.090115954942132e-09, "epoch": 19.884488448844884, "percentage": 99.42, "elapsed_time": "7:08:02", "remaining_time": "0:02:29", "throughput": 1485.27, "total_tokens": 38145040} {"current_steps": 180755, "total_steps": 181800, "loss": 0.0029, "lr": 5.041801611713193e-09, "epoch": 19.885038503850385, "percentage": 99.43, "elapsed_time": "7:08:02", "remaining_time": "0:02:28", "throughput": 1485.27, "total_tokens": 38146096} {"current_steps": 180760, "total_steps": 181800, "loss": 0.0008, "lr": 4.993717635018436e-09, "epoch": 19.885588558855886, "percentage": 99.43, "elapsed_time": "7:08:03", "remaining_time": "0:02:27", "throughput": 1485.27, "total_tokens": 38147152} {"current_steps": 180765, "total_steps": 181800, "loss": 0.0012, "lr": 4.945864025301949e-09, "epoch": 19.886138613861387, "percentage": 99.43, "elapsed_time": "7:08:04", "remaining_time": "0:02:27", "throughput": 1485.28, "total_tokens": 38148304} {"current_steps": 180770, "total_steps": 181800, "loss": 0.008, "lr": 4.8982407830078235e-09, "epoch": 19.88668866886689, "percentage": 99.43, "elapsed_time": "7:08:04", "remaining_time": "0:02:26", "throughput": 1485.28, "total_tokens": 38149328} {"current_steps": 180775, "total_steps": 181800, "loss": 0.0056, "lr": 4.850847908571821e-09, "epoch": 19.887238723872386, "percentage": 99.44, "elapsed_time": "7:08:05", "remaining_time": "0:02:25", "throughput": 1485.28, "total_tokens": 38150352} {"current_steps": 180780, "total_steps": 181800, "loss": 0.002, "lr": 4.803685402432479e-09, "epoch": 19.887788778877887, "percentage": 99.44, "elapsed_time": "7:08:06", "remaining_time": "0:02:24", "throughput": 1485.28, "total_tokens": 38151440} {"current_steps": 180785, "total_steps": 181800, "loss": 0.0227, "lr": 4.756753265022784e-09, "epoch": 19.888338833883388, "percentage": 99.44, "elapsed_time": "7:08:07", "remaining_time": "0:02:24", "throughput": 1485.28, "total_tokens": 38152496} {"current_steps": 180790, "total_steps": 181800, "loss": 0.0038, "lr": 4.710051496775725e-09, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "7:08:07", "remaining_time": "0:02:23", "throughput": 1485.28, "total_tokens": 38153552} {"current_steps": 180795, "total_steps": 181800, "loss": 0.0009, "lr": 4.6635800981242875e-09, "epoch": 19.88943894389439, "percentage": 99.45, "elapsed_time": "7:08:08", "remaining_time": "0:02:22", "throughput": 1485.29, "total_tokens": 38154672} {"current_steps": 180800, "total_steps": 181800, "loss": 0.0017, "lr": 4.617339069493132e-09, "epoch": 19.88998899889989, "percentage": 99.45, "elapsed_time": "7:08:09", "remaining_time": "0:02:22", "throughput": 1485.29, "total_tokens": 38155696} {"current_steps": 180805, "total_steps": 181800, "loss": 0.0606, "lr": 4.5713284113096944e-09, "epoch": 19.89053905390539, "percentage": 99.45, "elapsed_time": "7:08:09", "remaining_time": "0:02:21", "throughput": 1485.29, "total_tokens": 38156752} {"current_steps": 180810, "total_steps": 181800, "loss": 0.0775, "lr": 4.525548124001411e-09, "epoch": 19.89108910891089, "percentage": 99.46, "elapsed_time": "7:08:10", "remaining_time": "0:02:20", "throughput": 1485.29, "total_tokens": 38157776} {"current_steps": 180815, "total_steps": 181800, "loss": 0.0084, "lr": 4.4799982079846145e-09, "epoch": 19.89163916391639, "percentage": 99.46, "elapsed_time": "7:08:11", "remaining_time": "0:02:19", "throughput": 1485.29, "total_tokens": 38158832} {"current_steps": 180820, "total_steps": 181800, "loss": 0.005, "lr": 4.434678663681191e-09, "epoch": 19.892189218921892, "percentage": 99.46, "elapsed_time": "7:08:11", "remaining_time": "0:02:19", "throughput": 1485.29, "total_tokens": 38159856} {"current_steps": 180825, "total_steps": 181800, "loss": 0.0085, "lr": 4.389589491510249e-09, "epoch": 19.892739273927393, "percentage": 99.46, "elapsed_time": "7:08:12", "remaining_time": "0:02:18", "throughput": 1485.29, "total_tokens": 38160912} {"current_steps": 180830, "total_steps": 181800, "loss": 0.0059, "lr": 4.344730691885346e-09, "epoch": 19.893289328932894, "percentage": 99.47, "elapsed_time": "7:08:13", "remaining_time": "0:02:17", "throughput": 1485.29, "total_tokens": 38162000} {"current_steps": 180835, "total_steps": 181800, "loss": 0.001, "lr": 4.3001022652228165e-09, "epoch": 19.893839383938392, "percentage": 99.47, "elapsed_time": "7:08:13", "remaining_time": "0:02:17", "throughput": 1485.29, "total_tokens": 38163056} {"current_steps": 180840, "total_steps": 181800, "loss": 0.0019, "lr": 4.255704211930667e-09, "epoch": 19.894389438943893, "percentage": 99.47, "elapsed_time": "7:08:14", "remaining_time": "0:02:16", "throughput": 1485.29, "total_tokens": 38164080} {"current_steps": 180845, "total_steps": 181800, "loss": 0.1195, "lr": 4.21153653241968e-09, "epoch": 19.894939493949394, "percentage": 99.47, "elapsed_time": "7:08:15", "remaining_time": "0:02:15", "throughput": 1485.29, "total_tokens": 38165104} {"current_steps": 180850, "total_steps": 181800, "loss": 0.0048, "lr": 4.167599227097863e-09, "epoch": 19.895489548954895, "percentage": 99.48, "elapsed_time": "7:08:16", "remaining_time": "0:02:14", "throughput": 1485.29, "total_tokens": 38166160} {"current_steps": 180855, "total_steps": 181800, "loss": 0.0094, "lr": 4.123892296367671e-09, "epoch": 19.896039603960396, "percentage": 99.48, "elapsed_time": "7:08:16", "remaining_time": "0:02:14", "throughput": 1485.3, "total_tokens": 38167248} {"current_steps": 180860, "total_steps": 181800, "loss": 0.0055, "lr": 4.080415740634335e-09, "epoch": 19.896589658965897, "percentage": 99.48, "elapsed_time": "7:08:17", "remaining_time": "0:02:13", "throughput": 1485.3, "total_tokens": 38168272} {"current_steps": 180865, "total_steps": 181800, "loss": 0.0075, "lr": 4.037169560297538e-09, "epoch": 19.8971397139714, "percentage": 99.49, "elapsed_time": "7:08:18", "remaining_time": "0:02:12", "throughput": 1485.29, "total_tokens": 38169232} {"current_steps": 180870, "total_steps": 181800, "loss": 0.0055, "lr": 3.994153755754182e-09, "epoch": 19.897689768976896, "percentage": 99.49, "elapsed_time": "7:08:18", "remaining_time": "0:02:12", "throughput": 1485.29, "total_tokens": 38170256} {"current_steps": 180875, "total_steps": 181800, "loss": 0.1165, "lr": 3.951368327403948e-09, "epoch": 19.898239823982397, "percentage": 99.49, "elapsed_time": "7:08:19", "remaining_time": "0:02:11", "throughput": 1485.3, "total_tokens": 38171344} {"current_steps": 180880, "total_steps": 181800, "loss": 0.0819, "lr": 3.908813275640966e-09, "epoch": 19.8987898789879, "percentage": 99.49, "elapsed_time": "7:08:20", "remaining_time": "0:02:10", "throughput": 1485.3, "total_tokens": 38172496} {"current_steps": 180885, "total_steps": 181800, "loss": 0.0272, "lr": 3.8664886008538124e-09, "epoch": 19.8993399339934, "percentage": 99.5, "elapsed_time": "7:08:20", "remaining_time": "0:02:10", "throughput": 1485.3, "total_tokens": 38173584} {"current_steps": 180890, "total_steps": 181800, "loss": 0.0056, "lr": 3.824394303436618e-09, "epoch": 19.8998899889989, "percentage": 99.5, "elapsed_time": "7:08:21", "remaining_time": "0:02:09", "throughput": 1485.3, "total_tokens": 38174608} {"current_steps": 180895, "total_steps": 181800, "loss": 0.0016, "lr": 3.782530383775185e-09, "epoch": 19.9004400440044, "percentage": 99.5, "elapsed_time": "7:08:22", "remaining_time": "0:02:08", "throughput": 1485.3, "total_tokens": 38175568} {"current_steps": 180900, "total_steps": 181800, "loss": 0.0111, "lr": 3.740896842255315e-09, "epoch": 19.900990099009903, "percentage": 99.5, "elapsed_time": "7:08:22", "remaining_time": "0:02:07", "throughput": 1485.3, "total_tokens": 38176624} {"current_steps": 180905, "total_steps": 181800, "loss": 0.0085, "lr": 3.6994936792600355e-09, "epoch": 19.9015401540154, "percentage": 99.51, "elapsed_time": "7:08:23", "remaining_time": "0:02:07", "throughput": 1485.3, "total_tokens": 38177616} {"current_steps": 180910, "total_steps": 181800, "loss": 0.0561, "lr": 3.658320895175149e-09, "epoch": 19.9020902090209, "percentage": 99.51, "elapsed_time": "7:08:24", "remaining_time": "0:02:06", "throughput": 1485.3, "total_tokens": 38178704} {"current_steps": 180915, "total_steps": 181800, "loss": 0.0954, "lr": 3.6173784903753562e-09, "epoch": 19.902640264026402, "percentage": 99.51, "elapsed_time": "7:08:25", "remaining_time": "0:02:05", "throughput": 1485.3, "total_tokens": 38179760} {"current_steps": 180920, "total_steps": 181800, "loss": 0.0015, "lr": 3.5766664652409078e-09, "epoch": 19.903190319031903, "percentage": 99.52, "elapsed_time": "7:08:25", "remaining_time": "0:02:05", "throughput": 1485.31, "total_tokens": 38180848} {"current_steps": 180925, "total_steps": 181800, "loss": 0.0372, "lr": 3.5361848201437285e-09, "epoch": 19.903740374037405, "percentage": 99.52, "elapsed_time": "7:08:26", "remaining_time": "0:02:04", "throughput": 1485.31, "total_tokens": 38181904} {"current_steps": 180930, "total_steps": 181800, "loss": 0.005, "lr": 3.495933555461295e-09, "epoch": 19.904290429042906, "percentage": 99.52, "elapsed_time": "7:08:27", "remaining_time": "0:02:03", "throughput": 1485.3, "total_tokens": 38182864} {"current_steps": 180935, "total_steps": 181800, "loss": 0.056, "lr": 3.45591267155998e-09, "epoch": 19.904840484048403, "percentage": 99.52, "elapsed_time": "7:08:27", "remaining_time": "0:02:02", "throughput": 1485.3, "total_tokens": 38183856} {"current_steps": 180940, "total_steps": 181800, "loss": 0.0069, "lr": 3.416122168814484e-09, "epoch": 19.905390539053904, "percentage": 99.53, "elapsed_time": "7:08:28", "remaining_time": "0:02:02", "throughput": 1485.3, "total_tokens": 38184880} {"current_steps": 180945, "total_steps": 181800, "loss": 0.0436, "lr": 3.3765620475856298e-09, "epoch": 19.905940594059405, "percentage": 99.53, "elapsed_time": "7:08:29", "remaining_time": "0:02:01", "throughput": 1485.3, "total_tokens": 38185904} {"current_steps": 180950, "total_steps": 181800, "loss": 0.0174, "lr": 3.3372323082397905e-09, "epoch": 19.906490649064907, "percentage": 99.53, "elapsed_time": "7:08:29", "remaining_time": "0:02:00", "throughput": 1485.3, "total_tokens": 38186896} {"current_steps": 180955, "total_steps": 181800, "loss": 0.0058, "lr": 3.2981329511405644e-09, "epoch": 19.907040704070408, "percentage": 99.54, "elapsed_time": "7:08:30", "remaining_time": "0:02:00", "throughput": 1485.3, "total_tokens": 38187984} {"current_steps": 180960, "total_steps": 181800, "loss": 0.1017, "lr": 3.2592639766487742e-09, "epoch": 19.90759075907591, "percentage": 99.54, "elapsed_time": "7:08:31", "remaining_time": "0:01:59", "throughput": 1485.3, "total_tokens": 38189040} {"current_steps": 180965, "total_steps": 181800, "loss": 0.0178, "lr": 3.2206253851224665e-09, "epoch": 19.90814081408141, "percentage": 99.54, "elapsed_time": "7:08:31", "remaining_time": "0:01:58", "throughput": 1485.3, "total_tokens": 38190064} {"current_steps": 180970, "total_steps": 181800, "loss": 0.0041, "lr": 3.1822171769141374e-09, "epoch": 19.908690869086907, "percentage": 99.54, "elapsed_time": "7:08:32", "remaining_time": "0:01:57", "throughput": 1485.31, "total_tokens": 38191120} {"current_steps": 180975, "total_steps": 181800, "loss": 0.0011, "lr": 3.144039352384609e-09, "epoch": 19.90924092409241, "percentage": 99.55, "elapsed_time": "7:08:33", "remaining_time": "0:01:57", "throughput": 1485.3, "total_tokens": 38192080} {"current_steps": 180980, "total_steps": 181800, "loss": 0.0013, "lr": 3.1060919118780507e-09, "epoch": 19.90979097909791, "percentage": 99.55, "elapsed_time": "7:08:34", "remaining_time": "0:01:56", "throughput": 1485.31, "total_tokens": 38193200} {"current_steps": 180985, "total_steps": 181800, "loss": 0.062, "lr": 3.068374855749734e-09, "epoch": 19.91034103410341, "percentage": 99.55, "elapsed_time": "7:08:34", "remaining_time": "0:01:55", "throughput": 1485.31, "total_tokens": 38194288} {"current_steps": 180990, "total_steps": 181800, "loss": 0.0705, "lr": 3.030888184346603e-09, "epoch": 19.91089108910891, "percentage": 99.55, "elapsed_time": "7:08:35", "remaining_time": "0:01:55", "throughput": 1485.31, "total_tokens": 38195440} {"current_steps": 180995, "total_steps": 181800, "loss": 0.0032, "lr": 2.9936318980128275e-09, "epoch": 19.911441144114413, "percentage": 99.56, "elapsed_time": "7:08:36", "remaining_time": "0:01:54", "throughput": 1485.31, "total_tokens": 38196432} {"current_steps": 181000, "total_steps": 181800, "loss": 0.0803, "lr": 2.956605997089801e-09, "epoch": 19.91199119911991, "percentage": 99.56, "elapsed_time": "7:08:36", "remaining_time": "0:01:53", "throughput": 1485.31, "total_tokens": 38197456} {"current_steps": 181005, "total_steps": 181800, "loss": 0.002, "lr": 2.919810481921692e-09, "epoch": 19.91254125412541, "percentage": 99.56, "elapsed_time": "7:08:37", "remaining_time": "0:01:52", "throughput": 1485.31, "total_tokens": 38198448} {"current_steps": 181010, "total_steps": 181800, "loss": 0.0064, "lr": 2.8832453528471194e-09, "epoch": 19.913091309130913, "percentage": 99.57, "elapsed_time": "7:08:38", "remaining_time": "0:01:52", "throughput": 1485.31, "total_tokens": 38199504} {"current_steps": 181015, "total_steps": 181800, "loss": 0.0028, "lr": 2.8469106102047004e-09, "epoch": 19.913641364136414, "percentage": 99.57, "elapsed_time": "7:08:38", "remaining_time": "0:01:51", "throughput": 1485.31, "total_tokens": 38200592} {"current_steps": 181020, "total_steps": 181800, "loss": 0.0031, "lr": 2.810806254324727e-09, "epoch": 19.914191419141915, "percentage": 99.57, "elapsed_time": "7:08:39", "remaining_time": "0:01:50", "throughput": 1485.31, "total_tokens": 38201616} {"current_steps": 181025, "total_steps": 181800, "loss": 0.0007, "lr": 2.774932285545817e-09, "epoch": 19.914741474147416, "percentage": 99.57, "elapsed_time": "7:08:40", "remaining_time": "0:01:50", "throughput": 1485.31, "total_tokens": 38202576} {"current_steps": 181030, "total_steps": 181800, "loss": 0.0006, "lr": 2.7392887041927105e-09, "epoch": 19.915291529152917, "percentage": 99.58, "elapsed_time": "7:08:40", "remaining_time": "0:01:49", "throughput": 1485.32, "total_tokens": 38203696} {"current_steps": 181035, "total_steps": 181800, "loss": 0.0445, "lr": 2.7038755105984747e-09, "epoch": 19.915841584158414, "percentage": 99.58, "elapsed_time": "7:08:41", "remaining_time": "0:01:48", "throughput": 1485.32, "total_tokens": 38204784} {"current_steps": 181040, "total_steps": 181800, "loss": 0.0316, "lr": 2.6686927050878497e-09, "epoch": 19.916391639163916, "percentage": 99.58, "elapsed_time": "7:08:42", "remaining_time": "0:01:47", "throughput": 1485.32, "total_tokens": 38205840} {"current_steps": 181045, "total_steps": 181800, "loss": 0.019, "lr": 2.6337402879828e-09, "epoch": 19.916941694169417, "percentage": 99.58, "elapsed_time": "7:08:42", "remaining_time": "0:01:47", "throughput": 1485.32, "total_tokens": 38206896} {"current_steps": 181050, "total_steps": 181800, "loss": 0.0099, "lr": 2.5990182596080658e-09, "epoch": 19.917491749174918, "percentage": 99.59, "elapsed_time": "7:08:43", "remaining_time": "0:01:46", "throughput": 1485.32, "total_tokens": 38207888} {"current_steps": 181055, "total_steps": 181800, "loss": 0.0033, "lr": 2.564526620285612e-09, "epoch": 19.91804180418042, "percentage": 99.59, "elapsed_time": "7:08:44", "remaining_time": "0:01:45", "throughput": 1485.32, "total_tokens": 38208944} {"current_steps": 181060, "total_steps": 181800, "loss": 0.0026, "lr": 2.530265370329077e-09, "epoch": 19.91859185918592, "percentage": 99.59, "elapsed_time": "7:08:45", "remaining_time": "0:01:45", "throughput": 1485.32, "total_tokens": 38209968} {"current_steps": 181065, "total_steps": 181800, "loss": 0.0498, "lr": 2.496234510057649e-09, "epoch": 19.919141914191417, "percentage": 99.6, "elapsed_time": "7:08:45", "remaining_time": "0:01:44", "throughput": 1485.32, "total_tokens": 38210992} {"current_steps": 181070, "total_steps": 181800, "loss": 0.0016, "lr": 2.462434039782191e-09, "epoch": 19.91969196919692, "percentage": 99.6, "elapsed_time": "7:08:46", "remaining_time": "0:01:43", "throughput": 1485.32, "total_tokens": 38212080} {"current_steps": 181075, "total_steps": 181800, "loss": 0.0012, "lr": 2.4288639598163408e-09, "epoch": 19.92024202420242, "percentage": 99.6, "elapsed_time": "7:08:47", "remaining_time": "0:01:43", "throughput": 1485.33, "total_tokens": 38213136} {"current_steps": 181080, "total_steps": 181800, "loss": 0.0178, "lr": 2.3955242704681857e-09, "epoch": 19.92079207920792, "percentage": 99.6, "elapsed_time": "7:08:47", "remaining_time": "0:01:42", "throughput": 1485.33, "total_tokens": 38214224} {"current_steps": 181085, "total_steps": 181800, "loss": 0.0023, "lr": 2.3624149720458124e-09, "epoch": 19.921342134213422, "percentage": 99.61, "elapsed_time": "7:08:48", "remaining_time": "0:01:41", "throughput": 1485.33, "total_tokens": 38215248} {"current_steps": 181090, "total_steps": 181800, "loss": 0.0045, "lr": 2.329536064851756e-09, "epoch": 19.921892189218923, "percentage": 99.61, "elapsed_time": "7:08:49", "remaining_time": "0:01:40", "throughput": 1485.33, "total_tokens": 38216272} {"current_steps": 181095, "total_steps": 181800, "loss": 0.0065, "lr": 2.2968875491941044e-09, "epoch": 19.922442244224424, "percentage": 99.61, "elapsed_time": "7:08:49", "remaining_time": "0:01:40", "throughput": 1485.33, "total_tokens": 38217360} {"current_steps": 181100, "total_steps": 181800, "loss": 0.0714, "lr": 2.264469425369842e-09, "epoch": 19.92299229922992, "percentage": 99.61, "elapsed_time": "7:08:50", "remaining_time": "0:01:39", "throughput": 1485.33, "total_tokens": 38218416} {"current_steps": 181105, "total_steps": 181800, "loss": 0.0015, "lr": 2.232281693678728e-09, "epoch": 19.923542354235423, "percentage": 99.62, "elapsed_time": "7:08:51", "remaining_time": "0:01:38", "throughput": 1485.33, "total_tokens": 38219504} {"current_steps": 181110, "total_steps": 181800, "loss": 0.0197, "lr": 2.2003243544177486e-09, "epoch": 19.924092409240924, "percentage": 99.62, "elapsed_time": "7:08:51", "remaining_time": "0:01:38", "throughput": 1485.34, "total_tokens": 38220592} {"current_steps": 181115, "total_steps": 181800, "loss": 0.0062, "lr": 2.1685974078811123e-09, "epoch": 19.924642464246425, "percentage": 99.62, "elapsed_time": "7:08:52", "remaining_time": "0:01:37", "throughput": 1485.34, "total_tokens": 38221712} {"current_steps": 181120, "total_steps": 181800, "loss": 0.0013, "lr": 2.1371008543630277e-09, "epoch": 19.925192519251926, "percentage": 99.63, "elapsed_time": "7:08:53", "remaining_time": "0:01:36", "throughput": 1485.34, "total_tokens": 38222736} {"current_steps": 181125, "total_steps": 181800, "loss": 0.0042, "lr": 2.105834694149378e-09, "epoch": 19.925742574257427, "percentage": 99.63, "elapsed_time": "7:08:54", "remaining_time": "0:01:35", "throughput": 1485.34, "total_tokens": 38223824} {"current_steps": 181130, "total_steps": 181800, "loss": 0.0703, "lr": 2.0747989275343714e-09, "epoch": 19.926292629262925, "percentage": 99.63, "elapsed_time": "7:08:54", "remaining_time": "0:01:35", "throughput": 1485.34, "total_tokens": 38224912} {"current_steps": 181135, "total_steps": 181800, "loss": 0.0064, "lr": 2.0439935547983403e-09, "epoch": 19.926842684268426, "percentage": 99.63, "elapsed_time": "7:08:55", "remaining_time": "0:01:34", "throughput": 1485.34, "total_tokens": 38225936} {"current_steps": 181140, "total_steps": 181800, "loss": 0.0125, "lr": 2.013418576227166e-09, "epoch": 19.927392739273927, "percentage": 99.64, "elapsed_time": "7:08:56", "remaining_time": "0:01:33", "throughput": 1485.35, "total_tokens": 38227056} {"current_steps": 181145, "total_steps": 181800, "loss": 0.0019, "lr": 1.9830739921039567e-09, "epoch": 19.927942794279428, "percentage": 99.64, "elapsed_time": "7:08:56", "remaining_time": "0:01:33", "throughput": 1485.35, "total_tokens": 38228080} {"current_steps": 181150, "total_steps": 181800, "loss": 0.0493, "lr": 1.9529598027090423e-09, "epoch": 19.92849284928493, "percentage": 99.64, "elapsed_time": "7:08:57", "remaining_time": "0:01:32", "throughput": 1485.35, "total_tokens": 38229104} {"current_steps": 181155, "total_steps": 181800, "loss": 0.0023, "lr": 1.9230760083172038e-09, "epoch": 19.92904290429043, "percentage": 99.65, "elapsed_time": "7:08:58", "remaining_time": "0:01:31", "throughput": 1485.35, "total_tokens": 38230160} {"current_steps": 181160, "total_steps": 181800, "loss": 0.0024, "lr": 1.893422609205997e-09, "epoch": 19.92959295929593, "percentage": 99.65, "elapsed_time": "7:08:58", "remaining_time": "0:01:30", "throughput": 1485.35, "total_tokens": 38231248} {"current_steps": 181165, "total_steps": 181800, "loss": 0.002, "lr": 1.8639996056474264e-09, "epoch": 19.93014301430143, "percentage": 99.65, "elapsed_time": "7:08:59", "remaining_time": "0:01:30", "throughput": 1485.35, "total_tokens": 38232304} {"current_steps": 181170, "total_steps": 181800, "loss": 0.0018, "lr": 1.8348069979107207e-09, "epoch": 19.93069306930693, "percentage": 99.65, "elapsed_time": "7:09:00", "remaining_time": "0:01:29", "throughput": 1485.35, "total_tokens": 38233296} {"current_steps": 181175, "total_steps": 181800, "loss": 0.0153, "lr": 1.8058447862706606e-09, "epoch": 19.93124312431243, "percentage": 99.66, "elapsed_time": "7:09:00", "remaining_time": "0:01:28", "throughput": 1485.35, "total_tokens": 38234416} {"current_steps": 181180, "total_steps": 181800, "loss": 0.0074, "lr": 1.7771129709881484e-09, "epoch": 19.931793179317932, "percentage": 99.66, "elapsed_time": "7:09:01", "remaining_time": "0:01:28", "throughput": 1485.36, "total_tokens": 38235504} {"current_steps": 181185, "total_steps": 181800, "loss": 0.0661, "lr": 1.748611552332413e-09, "epoch": 19.932343234323433, "percentage": 99.66, "elapsed_time": "7:09:02", "remaining_time": "0:01:27", "throughput": 1485.36, "total_tokens": 38236688} {"current_steps": 181190, "total_steps": 181800, "loss": 0.0039, "lr": 1.7203405305643572e-09, "epoch": 19.932893289328934, "percentage": 99.66, "elapsed_time": "7:09:03", "remaining_time": "0:01:26", "throughput": 1485.36, "total_tokens": 38237712} {"current_steps": 181195, "total_steps": 181800, "loss": 0.0386, "lr": 1.692299905944883e-09, "epoch": 19.933443344334435, "percentage": 99.67, "elapsed_time": "7:09:03", "remaining_time": "0:01:25", "throughput": 1485.37, "total_tokens": 38238800} {"current_steps": 181200, "total_steps": 181800, "loss": 0.0012, "lr": 1.6644896787293417e-09, "epoch": 19.933993399339933, "percentage": 99.67, "elapsed_time": "7:09:04", "remaining_time": "0:01:25", "throughput": 1485.36, "total_tokens": 38239792} {"current_steps": 181205, "total_steps": 181800, "loss": 0.0025, "lr": 1.6369098491814116e-09, "epoch": 19.934543454345434, "percentage": 99.67, "elapsed_time": "7:09:05", "remaining_time": "0:01:24", "throughput": 1485.37, "total_tokens": 38240848} {"current_steps": 181210, "total_steps": 181800, "loss": 0.0039, "lr": 1.6095604175481171e-09, "epoch": 19.935093509350935, "percentage": 99.68, "elapsed_time": "7:09:05", "remaining_time": "0:01:23", "throughput": 1485.37, "total_tokens": 38241872} {"current_steps": 181215, "total_steps": 181800, "loss": 0.0336, "lr": 1.582441384082034e-09, "epoch": 19.935643564356436, "percentage": 99.68, "elapsed_time": "7:09:06", "remaining_time": "0:01:23", "throughput": 1485.36, "total_tokens": 38242832} {"current_steps": 181220, "total_steps": 181800, "loss": 0.0079, "lr": 1.5555527490385135e-09, "epoch": 19.936193619361937, "percentage": 99.68, "elapsed_time": "7:09:07", "remaining_time": "0:01:22", "throughput": 1485.36, "total_tokens": 38243888} {"current_steps": 181225, "total_steps": 181800, "loss": 0.0201, "lr": 1.5288945126618049e-09, "epoch": 19.936743674367438, "percentage": 99.68, "elapsed_time": "7:09:07", "remaining_time": "0:01:21", "throughput": 1485.37, "total_tokens": 38244976} {"current_steps": 181230, "total_steps": 181800, "loss": 0.0191, "lr": 1.5024666751961568e-09, "epoch": 19.937293729372936, "percentage": 99.69, "elapsed_time": "7:09:08", "remaining_time": "0:01:20", "throughput": 1485.37, "total_tokens": 38246064} {"current_steps": 181235, "total_steps": 181800, "loss": 0.0555, "lr": 1.4762692368858189e-09, "epoch": 19.937843784378437, "percentage": 99.69, "elapsed_time": "7:09:09", "remaining_time": "0:01:20", "throughput": 1485.37, "total_tokens": 38247184} {"current_steps": 181240, "total_steps": 181800, "loss": 0.0952, "lr": 1.4503021979750397e-09, "epoch": 19.938393839383938, "percentage": 99.69, "elapsed_time": "7:09:09", "remaining_time": "0:01:19", "throughput": 1485.37, "total_tokens": 38248176} {"current_steps": 181245, "total_steps": 181800, "loss": 0.0038, "lr": 1.4245655587025174e-09, "epoch": 19.93894389438944, "percentage": 99.69, "elapsed_time": "7:09:10", "remaining_time": "0:01:18", "throughput": 1485.37, "total_tokens": 38249296} {"current_steps": 181250, "total_steps": 181800, "loss": 0.001, "lr": 1.3990593193041746e-09, "epoch": 19.93949394939494, "percentage": 99.7, "elapsed_time": "7:09:11", "remaining_time": "0:01:18", "throughput": 1485.37, "total_tokens": 38250320} {"current_steps": 181255, "total_steps": 181800, "loss": 0.0065, "lr": 1.3737834800131577e-09, "epoch": 19.94004400440044, "percentage": 99.7, "elapsed_time": "7:09:11", "remaining_time": "0:01:17", "throughput": 1485.38, "total_tokens": 38251408} {"current_steps": 181260, "total_steps": 181800, "loss": 0.0288, "lr": 1.3487380410653894e-09, "epoch": 19.94059405940594, "percentage": 99.7, "elapsed_time": "7:09:12", "remaining_time": "0:01:16", "throughput": 1485.38, "total_tokens": 38252496} {"current_steps": 181265, "total_steps": 181800, "loss": 0.0572, "lr": 1.3239230026912408e-09, "epoch": 19.94114411441144, "percentage": 99.71, "elapsed_time": "7:09:13", "remaining_time": "0:01:16", "throughput": 1485.38, "total_tokens": 38253552} {"current_steps": 181270, "total_steps": 181800, "loss": 0.0401, "lr": 1.2993383651183078e-09, "epoch": 19.94169416941694, "percentage": 99.71, "elapsed_time": "7:09:14", "remaining_time": "0:01:15", "throughput": 1485.38, "total_tokens": 38254544} {"current_steps": 181275, "total_steps": 181800, "loss": 0.0028, "lr": 1.274984128574186e-09, "epoch": 19.942244224422442, "percentage": 99.71, "elapsed_time": "7:09:14", "remaining_time": "0:01:14", "throughput": 1485.38, "total_tokens": 38255632} {"current_steps": 181280, "total_steps": 181800, "loss": 0.0437, "lr": 1.2508602932836955e-09, "epoch": 19.942794279427943, "percentage": 99.71, "elapsed_time": "7:09:15", "remaining_time": "0:01:13", "throughput": 1485.38, "total_tokens": 38256752} {"current_steps": 181285, "total_steps": 181800, "loss": 0.0478, "lr": 1.2269668594661054e-09, "epoch": 19.943344334433444, "percentage": 99.72, "elapsed_time": "7:09:16", "remaining_time": "0:01:13", "throughput": 1485.38, "total_tokens": 38257744} {"current_steps": 181290, "total_steps": 181800, "loss": 0.0873, "lr": 1.2033038273462361e-09, "epoch": 19.943894389438945, "percentage": 99.72, "elapsed_time": "7:09:16", "remaining_time": "0:01:12", "throughput": 1485.39, "total_tokens": 38258832} {"current_steps": 181295, "total_steps": 181800, "loss": 0.1022, "lr": 1.179871197137805e-09, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "7:09:17", "remaining_time": "0:01:11", "throughput": 1485.39, "total_tokens": 38259984} {"current_steps": 181300, "total_steps": 181800, "loss": 0.0097, "lr": 1.1566689690600818e-09, "epoch": 19.944994499449944, "percentage": 99.72, "elapsed_time": "7:09:18", "remaining_time": "0:01:11", "throughput": 1485.39, "total_tokens": 38261136} {"current_steps": 181305, "total_steps": 181800, "loss": 0.0548, "lr": 1.133697143326784e-09, "epoch": 19.945544554455445, "percentage": 99.73, "elapsed_time": "7:09:18", "remaining_time": "0:01:10", "throughput": 1485.39, "total_tokens": 38262160} {"current_steps": 181310, "total_steps": 181800, "loss": 0.0711, "lr": 1.110955720148854e-09, "epoch": 19.946094609460946, "percentage": 99.73, "elapsed_time": "7:09:19", "remaining_time": "0:01:09", "throughput": 1485.39, "total_tokens": 38263184} {"current_steps": 181315, "total_steps": 181800, "loss": 0.0868, "lr": 1.0884446997344588e-09, "epoch": 19.946644664466447, "percentage": 99.73, "elapsed_time": "7:09:20", "remaining_time": "0:01:08", "throughput": 1485.39, "total_tokens": 38264208} {"current_steps": 181320, "total_steps": 181800, "loss": 0.0299, "lr": 1.066164082291765e-09, "epoch": 19.94719471947195, "percentage": 99.74, "elapsed_time": "7:09:20", "remaining_time": "0:01:08", "throughput": 1485.4, "total_tokens": 38265328} {"current_steps": 181325, "total_steps": 181800, "loss": 0.008, "lr": 1.0441138680261641e-09, "epoch": 19.94774477447745, "percentage": 99.74, "elapsed_time": "7:09:21", "remaining_time": "0:01:07", "throughput": 1485.4, "total_tokens": 38266384} {"current_steps": 181330, "total_steps": 181800, "loss": 0.0045, "lr": 1.0222940571430473e-09, "epoch": 19.948294829482947, "percentage": 99.74, "elapsed_time": "7:09:22", "remaining_time": "0:01:06", "throughput": 1485.4, "total_tokens": 38267472} {"current_steps": 181335, "total_steps": 181800, "loss": 0.004, "lr": 1.0007046498422545e-09, "epoch": 19.948844884488448, "percentage": 99.74, "elapsed_time": "7:09:23", "remaining_time": "0:01:06", "throughput": 1485.4, "total_tokens": 38268528} {"current_steps": 181340, "total_steps": 181800, "loss": 0.1021, "lr": 9.793456463208506e-10, "epoch": 19.94939493949395, "percentage": 99.75, "elapsed_time": "7:09:23", "remaining_time": "0:01:05", "throughput": 1485.4, "total_tokens": 38269584} {"current_steps": 181345, "total_steps": 181800, "loss": 0.0501, "lr": 9.582170467759e-10, "epoch": 19.94994499449945, "percentage": 99.75, "elapsed_time": "7:09:24", "remaining_time": "0:01:04", "throughput": 1485.4, "total_tokens": 38270608} {"current_steps": 181350, "total_steps": 181800, "loss": 0.0314, "lr": 9.373188514044673e-10, "epoch": 19.95049504950495, "percentage": 99.75, "elapsed_time": "7:09:25", "remaining_time": "0:01:03", "throughput": 1485.41, "total_tokens": 38271696} {"current_steps": 181355, "total_steps": 181800, "loss": 0.1984, "lr": 9.16651060398066e-10, "epoch": 19.951045104510452, "percentage": 99.76, "elapsed_time": "7:09:25", "remaining_time": "0:01:03", "throughput": 1485.41, "total_tokens": 38272720} {"current_steps": 181360, "total_steps": 181800, "loss": 0.0015, "lr": 8.962136739482096e-10, "epoch": 19.95159515951595, "percentage": 99.76, "elapsed_time": "7:09:26", "remaining_time": "0:01:02", "throughput": 1485.41, "total_tokens": 38273776} {"current_steps": 181365, "total_steps": 181800, "loss": 0.0693, "lr": 8.760066922408605e-10, "epoch": 19.95214521452145, "percentage": 99.76, "elapsed_time": "7:09:27", "remaining_time": "0:01:01", "throughput": 1485.41, "total_tokens": 38274864} {"current_steps": 181370, "total_steps": 181800, "loss": 0.0439, "lr": 8.560301154647566e-10, "epoch": 19.952695269526952, "percentage": 99.76, "elapsed_time": "7:09:27", "remaining_time": "0:01:01", "throughput": 1485.41, "total_tokens": 38275920} {"current_steps": 181375, "total_steps": 181800, "loss": 0.0016, "lr": 8.362839438030845e-10, "epoch": 19.953245324532453, "percentage": 99.77, "elapsed_time": "7:09:28", "remaining_time": "0:01:00", "throughput": 1485.41, "total_tokens": 38276944} {"current_steps": 181380, "total_steps": 181800, "loss": 0.1011, "lr": 8.167681774362557e-10, "epoch": 19.953795379537954, "percentage": 99.77, "elapsed_time": "7:09:29", "remaining_time": "0:00:59", "throughput": 1485.41, "total_tokens": 38278000} {"current_steps": 181385, "total_steps": 181800, "loss": 0.0073, "lr": 7.974828165446813e-10, "epoch": 19.954345434543455, "percentage": 99.77, "elapsed_time": "7:09:29", "remaining_time": "0:00:58", "throughput": 1485.41, "total_tokens": 38279056} {"current_steps": 181390, "total_steps": 181800, "loss": 0.0014, "lr": 7.784278613087726e-10, "epoch": 19.954895489548957, "percentage": 99.77, "elapsed_time": "7:09:30", "remaining_time": "0:00:58", "throughput": 1485.41, "total_tokens": 38280080} {"current_steps": 181395, "total_steps": 181800, "loss": 0.0141, "lr": 7.596033119033896e-10, "epoch": 19.955445544554454, "percentage": 99.78, "elapsed_time": "7:09:31", "remaining_time": "0:00:57", "throughput": 1485.41, "total_tokens": 38281136} {"current_steps": 181400, "total_steps": 181800, "loss": 0.0007, "lr": 7.410091684978415e-10, "epoch": 19.955995599559955, "percentage": 99.78, "elapsed_time": "7:09:32", "remaining_time": "0:00:56", "throughput": 1485.41, "total_tokens": 38282192} {"current_steps": 181405, "total_steps": 181800, "loss": 0.0085, "lr": 7.226454312669884e-10, "epoch": 19.956545654565456, "percentage": 99.78, "elapsed_time": "7:09:32", "remaining_time": "0:00:56", "throughput": 1485.42, "total_tokens": 38283248} {"current_steps": 181410, "total_steps": 181800, "loss": 0.1179, "lr": 7.045121003829148e-10, "epoch": 19.957095709570957, "percentage": 99.79, "elapsed_time": "7:09:33", "remaining_time": "0:00:55", "throughput": 1485.42, "total_tokens": 38284336} {"current_steps": 181415, "total_steps": 181800, "loss": 0.002, "lr": 6.866091760066029e-10, "epoch": 19.95764576457646, "percentage": 99.79, "elapsed_time": "7:09:34", "remaining_time": "0:00:54", "throughput": 1485.42, "total_tokens": 38285424} {"current_steps": 181420, "total_steps": 181800, "loss": 0.0033, "lr": 6.68936658307362e-10, "epoch": 19.95819581958196, "percentage": 99.79, "elapsed_time": "7:09:34", "remaining_time": "0:00:53", "throughput": 1485.42, "total_tokens": 38286544} {"current_steps": 181425, "total_steps": 181800, "loss": 0.0027, "lr": 6.514945474461743e-10, "epoch": 19.958745874587457, "percentage": 99.79, "elapsed_time": "7:09:35", "remaining_time": "0:00:53", "throughput": 1485.42, "total_tokens": 38287600} {"current_steps": 181430, "total_steps": 181800, "loss": 0.0047, "lr": 6.342828435840221e-10, "epoch": 19.959295929592958, "percentage": 99.8, "elapsed_time": "7:09:36", "remaining_time": "0:00:52", "throughput": 1485.43, "total_tokens": 38288656} {"current_steps": 181435, "total_steps": 181800, "loss": 0.002, "lr": 6.173015468791121e-10, "epoch": 19.95984598459846, "percentage": 99.8, "elapsed_time": "7:09:36", "remaining_time": "0:00:51", "throughput": 1485.43, "total_tokens": 38289712} {"current_steps": 181440, "total_steps": 181800, "loss": 0.032, "lr": 6.005506574896513e-10, "epoch": 19.96039603960396, "percentage": 99.8, "elapsed_time": "7:09:37", "remaining_time": "0:00:51", "throughput": 1485.43, "total_tokens": 38290736} {"current_steps": 181445, "total_steps": 181800, "loss": 0.0669, "lr": 5.840301755682953e-10, "epoch": 19.96094609460946, "percentage": 99.8, "elapsed_time": "7:09:38", "remaining_time": "0:00:50", "throughput": 1485.43, "total_tokens": 38291856} {"current_steps": 181450, "total_steps": 181800, "loss": 0.0531, "lr": 5.677401012704753e-10, "epoch": 19.961496149614963, "percentage": 99.81, "elapsed_time": "7:09:38", "remaining_time": "0:00:49", "throughput": 1485.43, "total_tokens": 38292944} {"current_steps": 181455, "total_steps": 181800, "loss": 0.0334, "lr": 5.516804347405202e-10, "epoch": 19.962046204620464, "percentage": 99.81, "elapsed_time": "7:09:39", "remaining_time": "0:00:49", "throughput": 1485.43, "total_tokens": 38293968} {"current_steps": 181460, "total_steps": 181800, "loss": 0.0104, "lr": 5.358511761338614e-10, "epoch": 19.96259625962596, "percentage": 99.81, "elapsed_time": "7:09:40", "remaining_time": "0:00:48", "throughput": 1485.44, "total_tokens": 38295120} {"current_steps": 181465, "total_steps": 181800, "loss": 0.0573, "lr": 5.202523255892766e-10, "epoch": 19.963146314631462, "percentage": 99.82, "elapsed_time": "7:09:41", "remaining_time": "0:00:47", "throughput": 1485.44, "total_tokens": 38296144} {"current_steps": 181470, "total_steps": 181800, "loss": 0.0036, "lr": 5.048838832538705e-10, "epoch": 19.963696369636963, "percentage": 99.82, "elapsed_time": "7:09:41", "remaining_time": "0:00:46", "throughput": 1485.44, "total_tokens": 38297200} {"current_steps": 181475, "total_steps": 181800, "loss": 0.0017, "lr": 4.897458492691964e-10, "epoch": 19.964246424642464, "percentage": 99.82, "elapsed_time": "7:09:42", "remaining_time": "0:00:46", "throughput": 1485.44, "total_tokens": 38298192} {"current_steps": 181480, "total_steps": 181800, "loss": 0.0051, "lr": 4.748382237740323e-10, "epoch": 19.964796479647966, "percentage": 99.82, "elapsed_time": "7:09:43", "remaining_time": "0:00:45", "throughput": 1485.44, "total_tokens": 38299248} {"current_steps": 181485, "total_steps": 181800, "loss": 0.022, "lr": 4.60161006907156e-10, "epoch": 19.965346534653467, "percentage": 99.83, "elapsed_time": "7:09:43", "remaining_time": "0:00:44", "throughput": 1485.44, "total_tokens": 38300272} {"current_steps": 181490, "total_steps": 181800, "loss": 0.0077, "lr": 4.457141988045699e-10, "epoch": 19.965896589658964, "percentage": 99.83, "elapsed_time": "7:09:44", "remaining_time": "0:00:44", "throughput": 1485.44, "total_tokens": 38301264} {"current_steps": 181495, "total_steps": 181800, "loss": 0.0011, "lr": 4.314977995967251e-10, "epoch": 19.966446644664465, "percentage": 99.83, "elapsed_time": "7:09:45", "remaining_time": "0:00:43", "throughput": 1485.44, "total_tokens": 38302352} {"current_steps": 181500, "total_steps": 181800, "loss": 0.0023, "lr": 4.1751180941407285e-10, "epoch": 19.966996699669966, "percentage": 99.83, "elapsed_time": "7:09:45", "remaining_time": "0:00:42", "throughput": 1485.44, "total_tokens": 38303408} {"current_steps": 181505, "total_steps": 181800, "loss": 0.0005, "lr": 4.0375622838983996e-10, "epoch": 19.967546754675467, "percentage": 99.84, "elapsed_time": "7:09:46", "remaining_time": "0:00:41", "throughput": 1485.44, "total_tokens": 38304496} {"current_steps": 181510, "total_steps": 181800, "loss": 0.0015, "lr": 3.902310566461509e-10, "epoch": 19.96809680968097, "percentage": 99.84, "elapsed_time": "7:09:47", "remaining_time": "0:00:41", "throughput": 1485.44, "total_tokens": 38305552} {"current_steps": 181515, "total_steps": 181800, "loss": 0.0481, "lr": 3.769362943106813e-10, "epoch": 19.96864686468647, "percentage": 99.84, "elapsed_time": "7:09:47", "remaining_time": "0:00:40", "throughput": 1485.45, "total_tokens": 38306608} {"current_steps": 181520, "total_steps": 181800, "loss": 0.0085, "lr": 3.638719415055558e-10, "epoch": 19.96919691969197, "percentage": 99.85, "elapsed_time": "7:09:48", "remaining_time": "0:00:39", "throughput": 1485.44, "total_tokens": 38307600} {"current_steps": 181525, "total_steps": 181800, "loss": 0.0023, "lr": 3.510379983501233e-10, "epoch": 19.96974697469747, "percentage": 99.85, "elapsed_time": "7:09:49", "remaining_time": "0:00:39", "throughput": 1485.45, "total_tokens": 38308656} {"current_steps": 181530, "total_steps": 181800, "loss": 0.0552, "lr": 3.384344649609572e-10, "epoch": 19.97029702970297, "percentage": 99.85, "elapsed_time": "7:09:50", "remaining_time": "0:00:38", "throughput": 1485.44, "total_tokens": 38309648} {"current_steps": 181535, "total_steps": 181800, "loss": 0.0425, "lr": 3.2606134146018206e-10, "epoch": 19.97084708470847, "percentage": 99.85, "elapsed_time": "7:09:50", "remaining_time": "0:00:37", "throughput": 1485.44, "total_tokens": 38310704} {"current_steps": 181540, "total_steps": 181800, "loss": 0.0183, "lr": 3.1391862795604465e-10, "epoch": 19.97139713971397, "percentage": 99.86, "elapsed_time": "7:09:51", "remaining_time": "0:00:36", "throughput": 1485.45, "total_tokens": 38311792} {"current_steps": 181545, "total_steps": 181800, "loss": 0.0537, "lr": 3.020063245623428e-10, "epoch": 19.971947194719473, "percentage": 99.86, "elapsed_time": "7:09:52", "remaining_time": "0:00:36", "throughput": 1485.45, "total_tokens": 38312880} {"current_steps": 181550, "total_steps": 181800, "loss": 0.0038, "lr": 2.903244313900988e-10, "epoch": 19.972497249724974, "percentage": 99.86, "elapsed_time": "7:09:52", "remaining_time": "0:00:35", "throughput": 1485.45, "total_tokens": 38313872} {"current_steps": 181555, "total_steps": 181800, "loss": 0.0912, "lr": 2.7887294854478385e-10, "epoch": 19.97304730473047, "percentage": 99.87, "elapsed_time": "7:09:53", "remaining_time": "0:00:34", "throughput": 1485.45, "total_tokens": 38314992} {"current_steps": 181560, "total_steps": 181800, "loss": 0.0038, "lr": 2.676518761346447e-10, "epoch": 19.973597359735972, "percentage": 99.87, "elapsed_time": "7:09:54", "remaining_time": "0:00:34", "throughput": 1485.45, "total_tokens": 38316016} {"current_steps": 181565, "total_steps": 181800, "loss": 0.0017, "lr": 2.5666121425960144e-10, "epoch": 19.974147414741473, "percentage": 99.87, "elapsed_time": "7:09:54", "remaining_time": "0:00:33", "throughput": 1485.45, "total_tokens": 38317072} {"current_steps": 181570, "total_steps": 181800, "loss": 0.0504, "lr": 2.4590096302234966e-10, "epoch": 19.974697469746975, "percentage": 99.87, "elapsed_time": "7:09:55", "remaining_time": "0:00:32", "throughput": 1485.45, "total_tokens": 38318128} {"current_steps": 181575, "total_steps": 181800, "loss": 0.0022, "lr": 2.3537112252558503e-10, "epoch": 19.975247524752476, "percentage": 99.88, "elapsed_time": "7:09:56", "remaining_time": "0:00:31", "throughput": 1485.46, "total_tokens": 38319184} {"current_steps": 181580, "total_steps": 181800, "loss": 0.0062, "lr": 2.2507169286090091e-10, "epoch": 19.975797579757977, "percentage": 99.88, "elapsed_time": "7:09:56", "remaining_time": "0:00:31", "throughput": 1485.45, "total_tokens": 38320208} {"current_steps": 181585, "total_steps": 181800, "loss": 0.0416, "lr": 2.150026741282174e-10, "epoch": 19.976347634763478, "percentage": 99.88, "elapsed_time": "7:09:57", "remaining_time": "0:00:30", "throughput": 1485.46, "total_tokens": 38321296} {"current_steps": 181590, "total_steps": 181800, "loss": 0.0035, "lr": 2.0516406641635234e-10, "epoch": 19.976897689768975, "percentage": 99.88, "elapsed_time": "7:09:58", "remaining_time": "0:00:29", "throughput": 1485.46, "total_tokens": 38322320} {"current_steps": 181595, "total_steps": 181800, "loss": 0.0722, "lr": 1.955558698168991e-10, "epoch": 19.977447744774476, "percentage": 99.89, "elapsed_time": "7:09:59", "remaining_time": "0:00:29", "throughput": 1485.46, "total_tokens": 38323440} {"current_steps": 181600, "total_steps": 181800, "loss": 0.0011, "lr": 1.8617808441867556e-10, "epoch": 19.977997799779978, "percentage": 99.89, "elapsed_time": "7:09:59", "remaining_time": "0:00:28", "throughput": 1485.46, "total_tokens": 38324464} {"current_steps": 181605, "total_steps": 181800, "loss": 0.0223, "lr": 1.77030710307724e-10, "epoch": 19.97854785478548, "percentage": 99.89, "elapsed_time": "7:10:00", "remaining_time": "0:00:27", "throughput": 1485.46, "total_tokens": 38325520} {"current_steps": 181610, "total_steps": 181800, "loss": 0.0045, "lr": 1.681137475700867e-10, "epoch": 19.97909790979098, "percentage": 99.9, "elapsed_time": "7:10:01", "remaining_time": "0:00:26", "throughput": 1485.46, "total_tokens": 38326576} {"current_steps": 181615, "total_steps": 181800, "loss": 0.0039, "lr": 1.5942719628903034e-10, "epoch": 19.97964796479648, "percentage": 99.9, "elapsed_time": "7:10:01", "remaining_time": "0:00:26", "throughput": 1485.47, "total_tokens": 38327664} {"current_steps": 181620, "total_steps": 181800, "loss": 0.0011, "lr": 1.5097105653949507e-10, "epoch": 19.980198019801982, "percentage": 99.9, "elapsed_time": "7:10:02", "remaining_time": "0:00:25", "throughput": 1485.47, "total_tokens": 38328688} {"current_steps": 181625, "total_steps": 181800, "loss": 0.0033, "lr": 1.4274532840197198e-10, "epoch": 19.98074807480748, "percentage": 99.9, "elapsed_time": "7:10:03", "remaining_time": "0:00:24", "throughput": 1485.47, "total_tokens": 38329744} {"current_steps": 181630, "total_steps": 181800, "loss": 0.0044, "lr": 1.3475001195417668e-10, "epoch": 19.98129812981298, "percentage": 99.91, "elapsed_time": "7:10:03", "remaining_time": "0:00:24", "throughput": 1485.47, "total_tokens": 38330832} {"current_steps": 181635, "total_steps": 181800, "loss": 0.0078, "lr": 1.2698510726827372e-10, "epoch": 19.98184818481848, "percentage": 99.91, "elapsed_time": "7:10:04", "remaining_time": "0:00:23", "throughput": 1485.47, "total_tokens": 38331856} {"current_steps": 181640, "total_steps": 181800, "loss": 0.0036, "lr": 1.1945061441642758e-10, "epoch": 19.982398239823983, "percentage": 99.91, "elapsed_time": "7:10:05", "remaining_time": "0:00:22", "throughput": 1485.47, "total_tokens": 38332880} {"current_steps": 181645, "total_steps": 181800, "loss": 0.0031, "lr": 1.1214653346525162e-10, "epoch": 19.982948294829484, "percentage": 99.91, "elapsed_time": "7:10:05", "remaining_time": "0:00:22", "throughput": 1485.47, "total_tokens": 38334032} {"current_steps": 181650, "total_steps": 181800, "loss": 0.0045, "lr": 1.0507286448691033e-10, "epoch": 19.983498349834985, "percentage": 99.92, "elapsed_time": "7:10:06", "remaining_time": "0:00:21", "throughput": 1485.47, "total_tokens": 38335024} {"current_steps": 181655, "total_steps": 181800, "loss": 0.0449, "lr": 9.822960754246602e-11, "epoch": 19.984048404840483, "percentage": 99.92, "elapsed_time": "7:10:07", "remaining_time": "0:00:20", "throughput": 1485.48, "total_tokens": 38336112} {"current_steps": 181660, "total_steps": 181800, "loss": 0.1017, "lr": 9.161676269575647e-11, "epoch": 19.984598459845984, "percentage": 99.92, "elapsed_time": "7:10:07", "remaining_time": "0:00:19", "throughput": 1485.47, "total_tokens": 38337104} {"current_steps": 181665, "total_steps": 181800, "loss": 0.0129, "lr": 8.523433001061953e-11, "epoch": 19.985148514851485, "percentage": 99.93, "elapsed_time": "7:10:08", "remaining_time": "0:00:19", "throughput": 1485.47, "total_tokens": 38338128} {"current_steps": 181670, "total_steps": 181800, "loss": 0.0008, "lr": 7.908230954256634e-11, "epoch": 19.985698569856986, "percentage": 99.93, "elapsed_time": "7:10:09", "remaining_time": "0:00:18", "throughput": 1485.47, "total_tokens": 38339152} {"current_steps": 181675, "total_steps": 181800, "loss": 0.0018, "lr": 7.316070134988361e-11, "epoch": 19.986248624862487, "percentage": 99.93, "elapsed_time": "7:10:10", "remaining_time": "0:00:17", "throughput": 1485.47, "total_tokens": 38340176} {"current_steps": 181680, "total_steps": 181800, "loss": 0.0015, "lr": 6.74695054880825e-11, "epoch": 19.986798679867988, "percentage": 99.93, "elapsed_time": "7:10:10", "remaining_time": "0:00:17", "throughput": 1485.48, "total_tokens": 38341264} {"current_steps": 181685, "total_steps": 181800, "loss": 0.1126, "lr": 6.200872200434748e-11, "epoch": 19.98734873487349, "percentage": 99.94, "elapsed_time": "7:10:11", "remaining_time": "0:00:16", "throughput": 1485.48, "total_tokens": 38342320} {"current_steps": 181690, "total_steps": 181800, "loss": 0.0013, "lr": 5.6778350956965264e-11, "epoch": 19.987898789878987, "percentage": 99.94, "elapsed_time": "7:10:12", "remaining_time": "0:00:15", "throughput": 1485.48, "total_tokens": 38343344} {"current_steps": 181695, "total_steps": 181800, "loss": 0.0024, "lr": 5.177839238756921e-11, "epoch": 19.988448844884488, "percentage": 99.94, "elapsed_time": "7:10:12", "remaining_time": "0:00:14", "throughput": 1485.48, "total_tokens": 38344400} {"current_steps": 181700, "total_steps": 181800, "loss": 0.001, "lr": 4.700884634611935e-11, "epoch": 19.98899889988999, "percentage": 99.94, "elapsed_time": "7:10:13", "remaining_time": "0:00:14", "throughput": 1485.48, "total_tokens": 38345488} {"current_steps": 181705, "total_steps": 181800, "loss": 0.0036, "lr": 4.2469712874249055e-11, "epoch": 19.98954895489549, "percentage": 99.95, "elapsed_time": "7:10:14", "remaining_time": "0:00:13", "throughput": 1485.48, "total_tokens": 38346512} {"current_steps": 181710, "total_steps": 181800, "loss": 0.0058, "lr": 3.8160992016367246e-11, "epoch": 19.99009900990099, "percentage": 99.95, "elapsed_time": "7:10:14", "remaining_time": "0:00:12", "throughput": 1485.48, "total_tokens": 38347600} {"current_steps": 181715, "total_steps": 181800, "loss": 0.0035, "lr": 3.4082683808556174e-11, "epoch": 19.990649064906492, "percentage": 99.95, "elapsed_time": "7:10:15", "remaining_time": "0:00:12", "throughput": 1485.48, "total_tokens": 38348624} {"current_steps": 181720, "total_steps": 181800, "loss": 0.0501, "lr": 3.023478829244919e-11, "epoch": 19.99119911991199, "percentage": 99.96, "elapsed_time": "7:10:16", "remaining_time": "0:00:11", "throughput": 1485.49, "total_tokens": 38349744} {"current_steps": 181725, "total_steps": 181800, "loss": 0.0451, "lr": 2.6617305501352996e-11, "epoch": 19.99174917491749, "percentage": 99.96, "elapsed_time": "7:10:16", "remaining_time": "0:00:10", "throughput": 1485.49, "total_tokens": 38350864} {"current_steps": 181730, "total_steps": 181800, "loss": 0.0348, "lr": 2.3230235465798722e-11, "epoch": 19.992299229922992, "percentage": 99.96, "elapsed_time": "7:10:17", "remaining_time": "0:00:09", "throughput": 1485.49, "total_tokens": 38351888} {"current_steps": 181735, "total_steps": 181800, "loss": 0.0804, "lr": 2.0073578221868616e-11, "epoch": 19.992849284928493, "percentage": 99.96, "elapsed_time": "7:10:18", "remaining_time": "0:00:09", "throughput": 1485.49, "total_tokens": 38352880} {"current_steps": 181740, "total_steps": 181800, "loss": 0.0016, "lr": 1.7147333797318254e-11, "epoch": 19.993399339933994, "percentage": 99.97, "elapsed_time": "7:10:19", "remaining_time": "0:00:08", "throughput": 1485.49, "total_tokens": 38354000} {"current_steps": 181745, "total_steps": 181800, "loss": 0.0396, "lr": 1.4451502219903213e-11, "epoch": 19.993949394939495, "percentage": 99.97, "elapsed_time": "7:10:19", "remaining_time": "0:00:07", "throughput": 1485.5, "total_tokens": 38355088} {"current_steps": 181750, "total_steps": 181800, "loss": 0.0969, "lr": 1.198608351182795e-11, "epoch": 19.994499449944996, "percentage": 99.97, "elapsed_time": "7:10:20", "remaining_time": "0:00:07", "throughput": 1485.5, "total_tokens": 38356176} {"current_steps": 181755, "total_steps": 181800, "loss": 0.0057, "lr": 9.75107769529693e-12, "epoch": 19.995049504950494, "percentage": 99.98, "elapsed_time": "7:10:21", "remaining_time": "0:00:06", "throughput": 1485.5, "total_tokens": 38357264} {"current_steps": 181760, "total_steps": 181800, "loss": 0.1512, "lr": 7.746484795290165e-12, "epoch": 19.995599559955995, "percentage": 99.98, "elapsed_time": "7:10:21", "remaining_time": "0:00:05", "throughput": 1485.5, "total_tokens": 38358352} {"current_steps": 181765, "total_steps": 181800, "loss": 0.003, "lr": 5.972304825685448e-12, "epoch": 19.996149614961496, "percentage": 99.98, "elapsed_time": "7:10:22", "remaining_time": "0:00:04", "throughput": 1485.51, "total_tokens": 38359440} {"current_steps": 181770, "total_steps": 181800, "loss": 0.0023, "lr": 4.428537805911681e-12, "epoch": 19.996699669966997, "percentage": 99.98, "elapsed_time": "7:10:23", "remaining_time": "0:00:04", "throughput": 1485.51, "total_tokens": 38360496} {"current_steps": 181775, "total_steps": 181800, "loss": 0.0016, "lr": 3.1151837498466507e-12, "epoch": 19.997249724972498, "percentage": 99.99, "elapsed_time": "7:10:23", "remaining_time": "0:00:03", "throughput": 1485.51, "total_tokens": 38361520} {"current_steps": 181780, "total_steps": 181800, "loss": 0.0628, "lr": 2.0322426685925876e-12, "epoch": 19.997799779978, "percentage": 99.99, "elapsed_time": "7:10:24", "remaining_time": "0:00:02", "throughput": 1485.51, "total_tokens": 38362544} {"current_steps": 181785, "total_steps": 181800, "loss": 0.1232, "lr": 1.1797145704761648e-12, "epoch": 19.998349834983497, "percentage": 99.99, "elapsed_time": "7:10:25", "remaining_time": "0:00:02", "throughput": 1485.51, "total_tokens": 38363632} {"current_steps": 181790, "total_steps": 181800, "loss": 0.0026, "lr": 5.575994665996121e-13, "epoch": 19.998899889988998, "percentage": 99.99, "elapsed_time": "7:10:25", "remaining_time": "0:00:01", "throughput": 1485.51, "total_tokens": 38364656} {"current_steps": 181795, "total_steps": 181800, "loss": 0.0619, "lr": 1.6589736251404475e-13, "epoch": 19.9994499449945, "percentage": 100.0, "elapsed_time": "7:10:26", "remaining_time": "0:00:00", "throughput": 1485.51, "total_tokens": 38365680} {"current_steps": 181800, "total_steps": 181800, "loss": 0.0013, "lr": 4.60826099502043e-15, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "7:10:27", "remaining_time": "0:00:00", "throughput": 1485.5, "total_tokens": 38366624} {"current_steps": 181800, "total_steps": 181800, "eval_loss": 0.07789125293493271, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "7:11:04", "remaining_time": "0:00:00", "throughput": 1483.37, "total_tokens": 38366624} {"current_steps": 181800, "total_steps": 181800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "7:11:06", "remaining_time": "0:00:00", "throughput": 1483.28, "total_tokens": 38366624}